Merge remote-tracking branch 'upstream/develop' into 1602-redmatrix-name
This commit is contained in:
Michael Vogel
commit
ec1bfe3d22
483 changed files with 23212 additions and 10894 deletions
2
boot.php
2
boot.php
|
|
@ -17,6 +17,8 @@
|
|||
* easily as email does today.
|
||||
*/
|
||||
|
||||
require_once('include/autoloader.php');
|
||||
|
||||
require_once('include/config.php');
|
||||
require_once('include/network.php');
|
||||
require_once('include/plugin.php');
|
||||
|
|
|
|||
|
|
@ -47,8 +47,10 @@ Friendica Documentation and Resources
|
|||
* [Theme Development](help/themes)
|
||||
* [Smarty 3 Templates](help/smarty3-templates)
|
||||
* [Database schema documantation](help/database)
|
||||
* [Class Autoloading](help/autoloader)
|
||||
* [Code - Reference(Doxygen generated - sets cookies)](doc/html/)
|
||||
|
||||
|
||||
**External Resources**
|
||||
|
||||
* [Main Website](http://friendica.com)
|
||||
|
|
|
|||
209
doc/autoloader.md
Normal file
209
doc/autoloader.md
Normal file
|
|
@ -0,0 +1,209 @@
|
|||
Autoloader
|
||||
==========
|
||||
|
||||
* [Home](help)
|
||||
|
||||
There is some initial support to class autoloading in Friendica core.
|
||||
|
||||
The autoloader code is in `include/autoloader.php`.
|
||||
It's derived from composer autoloader code.
|
||||
|
||||
Namespaces and Classes are mapped to folders and files in `library/`,
|
||||
and the map must be updated by hand, because we don't use composer yet.
|
||||
The mapping is defined by files in `include/autoloader/` folder.
|
||||
|
||||
Currently, only HTMLPurifier library is loaded using autoloader.
|
||||
|
||||
|
||||
## A quick introdution to class autoloading
|
||||
|
||||
The autoloader it's a way for php to automagically include the file that define a class when the class is first used, without the need to use "require_once" every time.
|
||||
|
||||
Once is setup you don't have to use it in any way. You need a class? you use the class.
|
||||
|
||||
At his basic is a function passed to the "spl_autoload_register()" function, which receive as argument the class name the script want and is it job to include the correct php file where that class is defined.
|
||||
The best source for documentation is [php site](http://php.net/manual/en/language.oop5.autoload.php).
|
||||
|
||||
One example, based on fictional friendica code.
|
||||
|
||||
Let's say you have a php file in "include/" that define a very useful class:
|
||||
|
||||
```
|
||||
file: include/ItemsManager.php
|
||||
<?php
|
||||
namespace \Friendica;
|
||||
|
||||
class ItemsManager {
|
||||
public function getAll() { ... }
|
||||
public function getByID($id) { ... }
|
||||
}
|
||||
```
|
||||
|
||||
The class "ItemsManager" has been declared in "Friendica" namespace.
|
||||
Namespaces are useful to keep things separated and avoid names clash (could be that a library you want to use defines a class named "ItemsManager", but as long as is in another namespace, you don't have any problem)
|
||||
|
||||
If we were using composer, we had configured it with path where to find the classes of "Friendica" namespace, and then the composer script will generate the autoloader machinery for us.
|
||||
As we don't use composer, we need check that the autoloader knows the Friendica namespace.
|
||||
So in "include/autoloader/autoload_psr4.php" there should be something like
|
||||
|
||||
```
|
||||
$vendorDir = dirname(dirname(dirname(__FILE__)))."/library";
|
||||
$baseDir = dirname($vendorDir);
|
||||
return array(
|
||||
"Friendica" => array($baseDir."/include");
|
||||
);
|
||||
```
|
||||
|
||||
|
||||
That tells the autoloader code to look for files that defines classes in "Friendica" namespace under "include/" folder. (And btw, that's why the file has the same name as the class it defines.)
|
||||
|
||||
*note*: The structure of files in "include/autoloader/" has been copied from the code generated by composer, to ease the work of enable autoloader for external libraries under "library/"
|
||||
|
||||
Let's say now that you need to load some items in a view, maybe in a fictional "mod/network.php".
|
||||
Somewere at the start of the scripts, the autoloader was initialized. In Friendica is done at the top of "boot.php", with "require_once('include/autoloader.php');".
|
||||
|
||||
The code will be something like:
|
||||
|
||||
```
|
||||
file: mod/network.php
|
||||
<?php
|
||||
|
||||
function network_content(&$a) {
|
||||
$itemsmanager = new \Friendica\ItemsManager();
|
||||
$items = $itemsmanager->getAll();
|
||||
|
||||
// pass $items to template
|
||||
// return result
|
||||
}
|
||||
```
|
||||
|
||||
That's a quite simple example, but look: no "require()"!
|
||||
You need to use a class, you use the class and you don't need to do anything more.
|
||||
|
||||
Going further: now we have a bunch of "*Manager" classes that cause some code duplication, let's define a BaseManager class, where to move all code in common between all managers:
|
||||
|
||||
```
|
||||
file: include/BaseManager.php
|
||||
<?php
|
||||
namespace \Friendica;
|
||||
|
||||
class BaseManager {
|
||||
public function thatFunctionEveryManagerUses() { ... }
|
||||
}
|
||||
```
|
||||
|
||||
and then let's change the ItemsManager class to use this code
|
||||
|
||||
```
|
||||
file: include/ItemsManager.php
|
||||
<?php
|
||||
namespace \Friendica;
|
||||
|
||||
class ItemsManager extends BaseManager {
|
||||
public function getAll() { ... }
|
||||
public function getByID($id) { ... }
|
||||
}
|
||||
```
|
||||
|
||||
The autoloader don't mind what you need the class for. You need a class, you get the class.
|
||||
It works with the "BaseManager" example here, it works when we need to call static methods on a class:
|
||||
|
||||
```
|
||||
file: include/dfrn.php
|
||||
<?php
|
||||
namespace \Friendica;
|
||||
|
||||
class dfrn {
|
||||
public static function mail($item, $owner) { ... }
|
||||
}
|
||||
```
|
||||
|
||||
```
|
||||
file: mod/mail.php
|
||||
<?php
|
||||
|
||||
mail_post($a){
|
||||
...
|
||||
\Friendica\dfrn::mail($item, $owner);
|
||||
...
|
||||
}
|
||||
```
|
||||
|
||||
If your code is in same namespace as the class you need, you don't need to prepend it:
|
||||
|
||||
```
|
||||
file: include/delivery.php
|
||||
<?php
|
||||
|
||||
namespace \Friendica;
|
||||
|
||||
// this is the same content of current include/delivery.php,
|
||||
// but has been declared to be in "Friendica" namespace
|
||||
|
||||
[...]
|
||||
switch($contact['network']) {
|
||||
|
||||
case NETWORK_DFRN:
|
||||
if ($mail) {
|
||||
$item['body'] = ...
|
||||
$atom = dfrn::mail($item, $owner);
|
||||
} elseif ($fsuggest) {
|
||||
$atom = dfrn::fsuggest($item, $owner);
|
||||
q("DELETE FROM `fsuggest` WHERE `id` = %d LIMIT 1", intval($item['id']));
|
||||
} elseif ($relocate)
|
||||
$atom = dfrn::relocate($owner, $uid);
|
||||
[...]
|
||||
```
|
||||
|
||||
This is real "include/delivery.php" unchanged, but as the code is declared to be in "Friendica" namespace, you don't need to write it when you need to use the "dfrn" class.
|
||||
But if you want to use classes from another library, you need to use the full namespace, e.g.
|
||||
|
||||
```
|
||||
<?php
|
||||
namespace \Frienidca;
|
||||
|
||||
class Diaspora {
|
||||
public function md2bbcode() {
|
||||
$html = \Michelf\MarkdownExtra::defaultTransform($text);
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
if you use that class in many places of the code and you don't want to write the full path to the class everytime, you can use the "use" php keyword
|
||||
|
||||
```
|
||||
<?php
|
||||
namespace \Frienidca;
|
||||
|
||||
use \Michelf\MarkdownExtra;
|
||||
|
||||
class Diaspora {
|
||||
public function md2bbcode() {
|
||||
$html = MarkdownExtra::defaultTransform($text);
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
Note that namespaces are like paths in filesystem, separated by "\", with the first "\" being the global scope.
|
||||
You can go more deep if you want to, like:
|
||||
|
||||
```
|
||||
<?php
|
||||
namespace \Friendica\Network;
|
||||
|
||||
class DFRN {
|
||||
}
|
||||
```
|
||||
|
||||
or
|
||||
|
||||
```
|
||||
<?php
|
||||
namespace \Friendica\DBA;
|
||||
|
||||
class MySQL {
|
||||
}
|
||||
```
|
||||
|
||||
So you can think of namespaces as folders in a unix filesystem, with global scope as the root ("\").
|
||||
|
||||
|
|
@ -814,8 +814,6 @@
|
|||
|
||||
if((strpos($txt,'<') !== false) || (strpos($txt,'>') !== false)) {
|
||||
|
||||
require_once('library/HTMLPurifier.auto.php');
|
||||
|
||||
$txt = html2bb_video($txt);
|
||||
$config = HTMLPurifier_Config::createDefault();
|
||||
$config->set('Cache.DefinitionImpl', null);
|
||||
|
|
@ -855,9 +853,6 @@
|
|||
if(requestdata('htmlstatus')) {
|
||||
$txt = requestdata('htmlstatus');
|
||||
if((strpos($txt,'<') !== false) || (strpos($txt,'>') !== false)) {
|
||||
|
||||
require_once('library/HTMLPurifier.auto.php');
|
||||
|
||||
$txt = html2bb_video($txt);
|
||||
|
||||
$config = HTMLPurifier_Config::createDefault();
|
||||
|
|
|
|||
69
include/autoloader.php
Normal file
69
include/autoloader.php
Normal file
|
|
@ -0,0 +1,69 @@
|
|||
<?php
|
||||
/**
|
||||
* @file include/autoloader.php
|
||||
*/
|
||||
|
||||
/**
|
||||
* @brief composer-derived autoloader init
|
||||
**/
|
||||
class FriendicaAutoloaderInit
|
||||
{
|
||||
private static $loader;
|
||||
|
||||
public static function loadClassLoader($class)
|
||||
{
|
||||
if ('Composer\Autoload\ClassLoader' === $class) {
|
||||
require __DIR__ . '/autoloader/ClassLoader.php';
|
||||
}
|
||||
}
|
||||
|
||||
public static function getLoader()
|
||||
{
|
||||
if (null !== self::$loader) {
|
||||
return self::$loader;
|
||||
}
|
||||
|
||||
spl_autoload_register(array('FriendicaAutoloaderInit', 'loadClassLoader'), true, true);
|
||||
self::$loader = $loader = new \Composer\Autoload\ClassLoader();
|
||||
spl_autoload_unregister(array('FriendicaAutoloaderInit', 'loadClassLoader'));
|
||||
|
||||
// library
|
||||
$map = require __DIR__ . '/autoloader/autoload_namespaces.php';
|
||||
foreach ($map as $namespace => $path) {
|
||||
$loader->set($namespace, $path);
|
||||
}
|
||||
|
||||
$map = require __DIR__ . '/autoloader/autoload_psr4.php';
|
||||
foreach ($map as $namespace => $path) {
|
||||
$loader->setPsr4($namespace, $path);
|
||||
}
|
||||
|
||||
$classMap = require __DIR__ . '/autoloader/autoload_classmap.php';
|
||||
if ($classMap) {
|
||||
$loader->addClassMap($classMap);
|
||||
}
|
||||
|
||||
$loader->register(true);
|
||||
|
||||
$includeFiles = require __DIR__ . '/autoloader/autoload_files.php';
|
||||
foreach ($includeFiles as $fileIdentifier => $file) {
|
||||
friendicaRequire($fileIdentifier, $file);
|
||||
}
|
||||
|
||||
|
||||
return $loader;
|
||||
}
|
||||
}
|
||||
|
||||
function friendicaRequire($fileIdentifier, $file)
|
||||
{
|
||||
if (empty($GLOBALS['__composer_autoload_files'][$fileIdentifier])) {
|
||||
require $file;
|
||||
|
||||
$GLOBALS['__composer_autoload_files'][$fileIdentifier] = true;
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
|
||||
return FriendicaAutoloaderInit::getLoader();
|
||||
413
include/autoloader/ClassLoader.php
Normal file
413
include/autoloader/ClassLoader.php
Normal file
|
|
@ -0,0 +1,413 @@
|
|||
<?php
|
||||
|
||||
/*
|
||||
* This file is part of Composer.
|
||||
*
|
||||
* (c) Nils Adermann <naderman@naderman.de>
|
||||
* Jordi Boggiano <j.boggiano@seld.be>
|
||||
*
|
||||
* For the full copyright and license information, please view the LICENSE.composer
|
||||
* file that was distributed with this source code.
|
||||
*/
|
||||
|
||||
namespace Composer\Autoload;
|
||||
|
||||
/**
|
||||
* ClassLoader implements a PSR-0 class loader
|
||||
*
|
||||
* See https://github.com/php-fig/fig-standards/blob/master/accepted/PSR-0.md
|
||||
*
|
||||
* $loader = new \Composer\Autoload\ClassLoader();
|
||||
*
|
||||
* // register classes with namespaces
|
||||
* $loader->add('Symfony\Component', __DIR__.'/component');
|
||||
* $loader->add('Symfony', __DIR__.'/framework');
|
||||
*
|
||||
* // activate the autoloader
|
||||
* $loader->register();
|
||||
*
|
||||
* // to enable searching the include path (eg. for PEAR packages)
|
||||
* $loader->setUseIncludePath(true);
|
||||
*
|
||||
* In this example, if you try to use a class in the Symfony\Component
|
||||
* namespace or one of its children (Symfony\Component\Console for instance),
|
||||
* the autoloader will first look for the class under the component/
|
||||
* directory, and it will then fallback to the framework/ directory if not
|
||||
* found before giving up.
|
||||
*
|
||||
* This class is loosely based on the Symfony UniversalClassLoader.
|
||||
*
|
||||
* @author Fabien Potencier <fabien@symfony.com>
|
||||
* @author Jordi Boggiano <j.boggiano@seld.be>
|
||||
*/
|
||||
class ClassLoader
|
||||
{
|
||||
// PSR-4
|
||||
private $prefixLengthsPsr4 = array();
|
||||
private $prefixDirsPsr4 = array();
|
||||
private $fallbackDirsPsr4 = array();
|
||||
|
||||
// PSR-0
|
||||
private $prefixesPsr0 = array();
|
||||
private $fallbackDirsPsr0 = array();
|
||||
|
||||
private $useIncludePath = false;
|
||||
private $classMap = array();
|
||||
|
||||
private $classMapAuthoritative = false;
|
||||
|
||||
public function getPrefixes()
|
||||
{
|
||||
if (!empty($this->prefixesPsr0)) {
|
||||
return call_user_func_array('array_merge', $this->prefixesPsr0);
|
||||
}
|
||||
|
||||
return array();
|
||||
}
|
||||
|
||||
public function getPrefixesPsr4()
|
||||
{
|
||||
return $this->prefixDirsPsr4;
|
||||
}
|
||||
|
||||
public function getFallbackDirs()
|
||||
{
|
||||
return $this->fallbackDirsPsr0;
|
||||
}
|
||||
|
||||
public function getFallbackDirsPsr4()
|
||||
{
|
||||
return $this->fallbackDirsPsr4;
|
||||
}
|
||||
|
||||
public function getClassMap()
|
||||
{
|
||||
return $this->classMap;
|
||||
}
|
||||
|
||||
/**
|
||||
* @param array $classMap Class to filename map
|
||||
*/
|
||||
public function addClassMap(array $classMap)
|
||||
{
|
||||
if ($this->classMap) {
|
||||
$this->classMap = array_merge($this->classMap, $classMap);
|
||||
} else {
|
||||
$this->classMap = $classMap;
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Registers a set of PSR-0 directories for a given prefix, either
|
||||
* appending or prepending to the ones previously set for this prefix.
|
||||
*
|
||||
* @param string $prefix The prefix
|
||||
* @param array|string $paths The PSR-0 root directories
|
||||
* @param bool $prepend Whether to prepend the directories
|
||||
*/
|
||||
public function add($prefix, $paths, $prepend = false)
|
||||
{
|
||||
if (!$prefix) {
|
||||
if ($prepend) {
|
||||
$this->fallbackDirsPsr0 = array_merge(
|
||||
(array) $paths,
|
||||
$this->fallbackDirsPsr0
|
||||
);
|
||||
} else {
|
||||
$this->fallbackDirsPsr0 = array_merge(
|
||||
$this->fallbackDirsPsr0,
|
||||
(array) $paths
|
||||
);
|
||||
}
|
||||
|
||||
return;
|
||||
}
|
||||
|
||||
$first = $prefix[0];
|
||||
if (!isset($this->prefixesPsr0[$first][$prefix])) {
|
||||
$this->prefixesPsr0[$first][$prefix] = (array) $paths;
|
||||
|
||||
return;
|
||||
}
|
||||
if ($prepend) {
|
||||
$this->prefixesPsr0[$first][$prefix] = array_merge(
|
||||
(array) $paths,
|
||||
$this->prefixesPsr0[$first][$prefix]
|
||||
);
|
||||
} else {
|
||||
$this->prefixesPsr0[$first][$prefix] = array_merge(
|
||||
$this->prefixesPsr0[$first][$prefix],
|
||||
(array) $paths
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Registers a set of PSR-4 directories for a given namespace, either
|
||||
* appending or prepending to the ones previously set for this namespace.
|
||||
*
|
||||
* @param string $prefix The prefix/namespace, with trailing '\\'
|
||||
* @param array|string $paths The PSR-0 base directories
|
||||
* @param bool $prepend Whether to prepend the directories
|
||||
*
|
||||
* @throws \InvalidArgumentException
|
||||
*/
|
||||
public function addPsr4($prefix, $paths, $prepend = false)
|
||||
{
|
||||
if (!$prefix) {
|
||||
// Register directories for the root namespace.
|
||||
if ($prepend) {
|
||||
$this->fallbackDirsPsr4 = array_merge(
|
||||
(array) $paths,
|
||||
$this->fallbackDirsPsr4
|
||||
);
|
||||
} else {
|
||||
$this->fallbackDirsPsr4 = array_merge(
|
||||
$this->fallbackDirsPsr4,
|
||||
(array) $paths
|
||||
);
|
||||
}
|
||||
} elseif (!isset($this->prefixDirsPsr4[$prefix])) {
|
||||
// Register directories for a new namespace.
|
||||
$length = strlen($prefix);
|
||||
if ('\\' !== $prefix[$length - 1]) {
|
||||
throw new \InvalidArgumentException("A non-empty PSR-4 prefix must end with a namespace separator.");
|
||||
}
|
||||
$this->prefixLengthsPsr4[$prefix[0]][$prefix] = $length;
|
||||
$this->prefixDirsPsr4[$prefix] = (array) $paths;
|
||||
} elseif ($prepend) {
|
||||
// Prepend directories for an already registered namespace.
|
||||
$this->prefixDirsPsr4[$prefix] = array_merge(
|
||||
(array) $paths,
|
||||
$this->prefixDirsPsr4[$prefix]
|
||||
);
|
||||
} else {
|
||||
// Append directories for an already registered namespace.
|
||||
$this->prefixDirsPsr4[$prefix] = array_merge(
|
||||
$this->prefixDirsPsr4[$prefix],
|
||||
(array) $paths
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Registers a set of PSR-0 directories for a given prefix,
|
||||
* replacing any others previously set for this prefix.
|
||||
*
|
||||
* @param string $prefix The prefix
|
||||
* @param array|string $paths The PSR-0 base directories
|
||||
*/
|
||||
public function set($prefix, $paths)
|
||||
{
|
||||
if (!$prefix) {
|
||||
$this->fallbackDirsPsr0 = (array) $paths;
|
||||
} else {
|
||||
$this->prefixesPsr0[$prefix[0]][$prefix] = (array) $paths;
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Registers a set of PSR-4 directories for a given namespace,
|
||||
* replacing any others previously set for this namespace.
|
||||
*
|
||||
* @param string $prefix The prefix/namespace, with trailing '\\'
|
||||
* @param array|string $paths The PSR-4 base directories
|
||||
*
|
||||
* @throws \InvalidArgumentException
|
||||
*/
|
||||
public function setPsr4($prefix, $paths)
|
||||
{
|
||||
if (!$prefix) {
|
||||
$this->fallbackDirsPsr4 = (array) $paths;
|
||||
} else {
|
||||
$length = strlen($prefix);
|
||||
if ('\\' !== $prefix[$length - 1]) {
|
||||
throw new \InvalidArgumentException("A non-empty PSR-4 prefix must end with a namespace separator.");
|
||||
}
|
||||
$this->prefixLengthsPsr4[$prefix[0]][$prefix] = $length;
|
||||
$this->prefixDirsPsr4[$prefix] = (array) $paths;
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Turns on searching the include path for class files.
|
||||
*
|
||||
* @param bool $useIncludePath
|
||||
*/
|
||||
public function setUseIncludePath($useIncludePath)
|
||||
{
|
||||
$this->useIncludePath = $useIncludePath;
|
||||
}
|
||||
|
||||
/**
|
||||
* Can be used to check if the autoloader uses the include path to check
|
||||
* for classes.
|
||||
*
|
||||
* @return bool
|
||||
*/
|
||||
public function getUseIncludePath()
|
||||
{
|
||||
return $this->useIncludePath;
|
||||
}
|
||||
|
||||
/**
|
||||
* Turns off searching the prefix and fallback directories for classes
|
||||
* that have not been registered with the class map.
|
||||
*
|
||||
* @param bool $classMapAuthoritative
|
||||
*/
|
||||
public function setClassMapAuthoritative($classMapAuthoritative)
|
||||
{
|
||||
$this->classMapAuthoritative = $classMapAuthoritative;
|
||||
}
|
||||
|
||||
/**
|
||||
* Should class lookup fail if not found in the current class map?
|
||||
*
|
||||
* @return bool
|
||||
*/
|
||||
public function isClassMapAuthoritative()
|
||||
{
|
||||
return $this->classMapAuthoritative;
|
||||
}
|
||||
|
||||
/**
|
||||
* Registers this instance as an autoloader.
|
||||
*
|
||||
* @param bool $prepend Whether to prepend the autoloader or not
|
||||
*/
|
||||
public function register($prepend = false)
|
||||
{
|
||||
spl_autoload_register(array($this, 'loadClass'), true, $prepend);
|
||||
}
|
||||
|
||||
/**
|
||||
* Unregisters this instance as an autoloader.
|
||||
*/
|
||||
public function unregister()
|
||||
{
|
||||
spl_autoload_unregister(array($this, 'loadClass'));
|
||||
}
|
||||
|
||||
/**
|
||||
* Loads the given class or interface.
|
||||
*
|
||||
* @param string $class The name of the class
|
||||
* @return bool|null True if loaded, null otherwise
|
||||
*/
|
||||
public function loadClass($class)
|
||||
{
|
||||
if ($file = $this->findFile($class)) {
|
||||
includeFile($file);
|
||||
|
||||
return true;
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Finds the path to the file where the class is defined.
|
||||
*
|
||||
* @param string $class The name of the class
|
||||
*
|
||||
* @return string|false The path if found, false otherwise
|
||||
*/
|
||||
public function findFile($class)
|
||||
{
|
||||
// work around for PHP 5.3.0 - 5.3.2 https://bugs.php.net/50731
|
||||
if ('\\' == $class[0]) {
|
||||
$class = substr($class, 1);
|
||||
}
|
||||
|
||||
// class map lookup
|
||||
if (isset($this->classMap[$class])) {
|
||||
return $this->classMap[$class];
|
||||
}
|
||||
if ($this->classMapAuthoritative) {
|
||||
return false;
|
||||
}
|
||||
|
||||
$file = $this->findFileWithExtension($class, '.php');
|
||||
|
||||
// Search for Hack files if we are running on HHVM
|
||||
if ($file === null && defined('HHVM_VERSION')) {
|
||||
$file = $this->findFileWithExtension($class, '.hh');
|
||||
}
|
||||
|
||||
if ($file === null) {
|
||||
// Remember that this class does not exist.
|
||||
return $this->classMap[$class] = false;
|
||||
}
|
||||
|
||||
return $file;
|
||||
}
|
||||
|
||||
private function findFileWithExtension($class, $ext)
|
||||
{
|
||||
// PSR-4 lookup
|
||||
$logicalPathPsr4 = strtr($class, '\\', DIRECTORY_SEPARATOR) . $ext;
|
||||
|
||||
$first = $class[0];
|
||||
if (isset($this->prefixLengthsPsr4[$first])) {
|
||||
foreach ($this->prefixLengthsPsr4[$first] as $prefix => $length) {
|
||||
if (0 === strpos($class, $prefix)) {
|
||||
foreach ($this->prefixDirsPsr4[$prefix] as $dir) {
|
||||
if (is_file($file = $dir . DIRECTORY_SEPARATOR . substr($logicalPathPsr4, $length))) {
|
||||
return $file;
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// PSR-4 fallback dirs
|
||||
foreach ($this->fallbackDirsPsr4 as $dir) {
|
||||
if (is_file($file = $dir . DIRECTORY_SEPARATOR . $logicalPathPsr4)) {
|
||||
return $file;
|
||||
}
|
||||
}
|
||||
|
||||
// PSR-0 lookup
|
||||
if (false !== $pos = strrpos($class, '\\')) {
|
||||
// namespaced class name
|
||||
$logicalPathPsr0 = substr($logicalPathPsr4, 0, $pos + 1)
|
||||
. strtr(substr($logicalPathPsr4, $pos + 1), '_', DIRECTORY_SEPARATOR);
|
||||
} else {
|
||||
// PEAR-like class name
|
||||
$logicalPathPsr0 = strtr($class, '_', DIRECTORY_SEPARATOR) . $ext;
|
||||
}
|
||||
|
||||
if (isset($this->prefixesPsr0[$first])) {
|
||||
foreach ($this->prefixesPsr0[$first] as $prefix => $dirs) {
|
||||
if (0 === strpos($class, $prefix)) {
|
||||
foreach ($dirs as $dir) {
|
||||
if (is_file($file = $dir . DIRECTORY_SEPARATOR . $logicalPathPsr0)) {
|
||||
return $file;
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// PSR-0 fallback dirs
|
||||
foreach ($this->fallbackDirsPsr0 as $dir) {
|
||||
if (is_file($file = $dir . DIRECTORY_SEPARATOR . $logicalPathPsr0)) {
|
||||
return $file;
|
||||
}
|
||||
}
|
||||
|
||||
// PSR-0 include paths.
|
||||
if ($this->useIncludePath && $file = stream_resolve_include_path($logicalPathPsr0)) {
|
||||
return $file;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Scope isolated include.
|
||||
*
|
||||
* Prevents access to $this/self from included files.
|
||||
*/
|
||||
function includeFile($file)
|
||||
{
|
||||
include $file;
|
||||
}
|
||||
19
include/autoloader/LICENSE.composer
Normal file
19
include/autoloader/LICENSE.composer
Normal file
|
|
@ -0,0 +1,19 @@
|
|||
Copyright (c) 2015 Nils Adermann, Jordi Boggiano
|
||||
|
||||
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, andor 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.
|
||||
9
include/autoloader/autoload_classmap.php
Normal file
9
include/autoloader/autoload_classmap.php
Normal file
|
|
@ -0,0 +1,9 @@
|
|||
<?php
|
||||
|
||||
// autoload_classmap.php @generated by Composer
|
||||
|
||||
$vendorDir = dirname(dirname(dirname(__FILE__)))."/library";
|
||||
$baseDir = dirname($vendorDir);
|
||||
|
||||
return array(
|
||||
);
|
||||
10
include/autoloader/autoload_files.php
Normal file
10
include/autoloader/autoload_files.php
Normal file
|
|
@ -0,0 +1,10 @@
|
|||
<?php
|
||||
|
||||
// autoload_files.php @generated by Composer
|
||||
|
||||
$vendorDir = dirname(dirname(dirname(__FILE__)))."/library";
|
||||
$baseDir = dirname($vendorDir);
|
||||
|
||||
return array(
|
||||
'2cffec82183ee1cea088009cef9a6fc3' => $vendorDir . '/ezyang/htmlpurifier/library/HTMLPurifier.composer.php',
|
||||
);
|
||||
10
include/autoloader/autoload_namespaces.php
Normal file
10
include/autoloader/autoload_namespaces.php
Normal file
|
|
@ -0,0 +1,10 @@
|
|||
<?php
|
||||
|
||||
// autoload_namespaces.php @generated by Composer
|
||||
|
||||
$vendorDir = dirname(dirname(dirname(__FILE__)))."/library";
|
||||
$baseDir = dirname($vendorDir);
|
||||
|
||||
return array(
|
||||
'HTMLPurifier' => array($vendorDir . '/ezyang/htmlpurifier/library'),
|
||||
);
|
||||
9
include/autoloader/autoload_psr4.php
Normal file
9
include/autoloader/autoload_psr4.php
Normal file
|
|
@ -0,0 +1,9 @@
|
|||
<?php
|
||||
|
||||
// autoload_psr4.php @generated by Composer
|
||||
|
||||
$vendorDir = dirname(dirname(dirname(__FILE__)))."/library";
|
||||
$baseDir = dirname($vendorDir);
|
||||
|
||||
return array(
|
||||
);
|
||||
|
|
@ -18,7 +18,6 @@ require_once("include/event.php");
|
|||
require_once("include/text.php");
|
||||
require_once("include/oembed.php");
|
||||
require_once("include/html2bbcode.php");
|
||||
require_once("library/HTMLPurifier.auto.php");
|
||||
|
||||
/**
|
||||
* @brief This class contain functions to create and send DFRN XML files
|
||||
|
|
|
|||
|
|
@ -76,7 +76,6 @@ function format_event_html($ev, $simple = false) {
|
|||
function parse_event($h) {
|
||||
|
||||
require_once('include/Scrape.php');
|
||||
require_once('library/HTMLPurifier.auto.php');
|
||||
require_once('include/html2bbcode');
|
||||
|
||||
$h = '<html><body>' . $h . '</body></html>';
|
||||
|
|
|
|||
|
|
@ -215,7 +215,7 @@ function mini_group_select($uid,$gid = 0) {
|
|||
|
||||
/**
|
||||
* @brief Create group sidebar widget
|
||||
*
|
||||
*
|
||||
* @param string $every
|
||||
* @param string $each
|
||||
* @param string $editmode
|
||||
|
|
@ -234,7 +234,7 @@ function group_side($every="contacts",$each="group",$editmode = "standard", $gro
|
|||
return '';
|
||||
|
||||
$groups = array();
|
||||
|
||||
|
||||
$groups[] = array(
|
||||
'text' => t('Everybody'),
|
||||
'id' => 0,
|
||||
|
|
@ -255,7 +255,7 @@ function group_side($every="contacts",$each="group",$editmode = "standard", $gro
|
|||
if(count($r)) {
|
||||
foreach($r as $rr) {
|
||||
$selected = (($group_id == $rr['id']) ? ' group-selected' : '');
|
||||
|
||||
|
||||
if ($editmode == "full") {
|
||||
$groupedit = array(
|
||||
'href' => "group/".$rr['id'],
|
||||
|
|
@ -264,7 +264,7 @@ function group_side($every="contacts",$each="group",$editmode = "standard", $gro
|
|||
} else {
|
||||
$groupedit = null;
|
||||
}
|
||||
|
||||
|
||||
$groups[] = array(
|
||||
'id' => $rr['id'],
|
||||
'cid' => $cid,
|
||||
|
|
@ -362,14 +362,13 @@ function groups_containing($uid,$c) {
|
|||
*/
|
||||
function groups_count_unseen() {
|
||||
|
||||
$r = q("SELECT `group`.`id`, `group`.`name`, COUNT(`item`.`id`) AS `count` FROM `group`, `group_member`, `item`
|
||||
WHERE `group`.`uid` = %d
|
||||
AND `item`.`uid` = %d
|
||||
AND `item`.`unseen` AND `item`.`visible`
|
||||
AND NOT `item`.`deleted`
|
||||
AND `item`.`contact-id` = `group_member`.`contact-id`
|
||||
AND `group_member`.`gid` = `group`.`id`
|
||||
GROUP BY `group`.`id` ",
|
||||
$r = q("SELECT `group`.`id`, `group`.`name`,
|
||||
(SELECT COUNT(*) FROM `item`
|
||||
WHERE `uid` = %d AND `unseen` AND
|
||||
`contact-id` IN (SELECT `contact-id` FROM `group_member`
|
||||
WHERE `group_member`.`gid` = `group`.`id` AND `group_member`.`uid` = %d)) AS `count`
|
||||
FROM `group` WHERE `group`.`uid` = %d;",
|
||||
intval(local_user()),
|
||||
intval(local_user()),
|
||||
intval(local_user())
|
||||
);
|
||||
|
|
|
|||
|
|
@ -1,21 +0,0 @@
|
|||
<?php
|
||||
|
||||
class HTMLPurifier_AttrDef_CSS_AlphaValue extends HTMLPurifier_AttrDef_CSS_Number
|
||||
{
|
||||
|
||||
public function __construct() {
|
||||
parent::__construct(false); // opacity is non-negative, but we will clamp it
|
||||
}
|
||||
|
||||
public function validate($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
|
||||
|
|
@ -1,28 +0,0 @@
|
|||
<?php
|
||||
|
||||
/**
|
||||
* Decorator which enables CSS properties to be disabled for specific elements.
|
||||
*/
|
||||
class HTMLPurifier_AttrDef_CSS_DenyElementDecorator extends HTMLPurifier_AttrDef
|
||||
{
|
||||
public $def, $element;
|
||||
|
||||
/**
|
||||
* @param $def Definition to wrap
|
||||
* @param $element Element to deny
|
||||
*/
|
||||
public function __construct($def, $element) {
|
||||
$this->def = $def;
|
||||
$this->element = $element;
|
||||
}
|
||||
/**
|
||||
* Checks if CurrentToken is set and equal to $this->element
|
||||
*/
|
||||
public function validate($string, $config, $context) {
|
||||
$token = $context->get('CurrentToken', true);
|
||||
if ($token && $token->name == $this->element) return false;
|
||||
return $this->def->validate($string, $config, $context);
|
||||
}
|
||||
}
|
||||
|
||||
// vim: et sw=4 sts=4
|
||||
|
|
@ -1,72 +0,0 @@
|
|||
<?php
|
||||
|
||||
/**
|
||||
* Validates a font family list according to CSS spec
|
||||
* @todo whitelisting allowed fonts would be nice
|
||||
*/
|
||||
class HTMLPurifier_AttrDef_CSS_FontFamily extends HTMLPurifier_AttrDef
|
||||
{
|
||||
|
||||
public function validate($string, $config, $context) {
|
||||
static $generic_names = array(
|
||||
'serif' => true,
|
||||
'sans-serif' => true,
|
||||
'monospace' => true,
|
||||
'fantasy' => true,
|
||||
'cursive' => true
|
||||
);
|
||||
|
||||
// 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])) {
|
||||
$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);
|
||||
|
||||
// $font is a pure representation of the font name
|
||||
|
||||
if (ctype_alnum($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);
|
||||
|
||||
// These ugly transforms don't pose a security
|
||||
// risk (as \\ and \" might). 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.
|
||||
// (warning: this code relies on the selection of quotation
|
||||
// mark below)
|
||||
$font = str_replace('\\', '\\5C ', $font);
|
||||
$font = str_replace('"', '\\22 ', $font);
|
||||
|
||||
// complicated font, requires quoting
|
||||
$final .= "\"$font\", "; // note that this will later get turned into "
|
||||
}
|
||||
$final = rtrim($final, ', ');
|
||||
if ($final === '') return false;
|
||||
return $final;
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
// vim: et sw=4 sts=4
|
||||
|
|
@ -1,47 +0,0 @@
|
|||
<?php
|
||||
|
||||
/**
|
||||
* Represents a Length as defined by CSS.
|
||||
*/
|
||||
class HTMLPurifier_AttrDef_CSS_Length extends HTMLPurifier_AttrDef
|
||||
{
|
||||
|
||||
protected $min, $max;
|
||||
|
||||
/**
|
||||
* @param HTMLPurifier_Length $max Minimum length, or null for no bound. String is also acceptable.
|
||||
* @param HTMLPurifier_Length $max Maximum length, or null for no bound. String is also acceptable.
|
||||
*/
|
||||
public function __construct($min = null, $max = null) {
|
||||
$this->min = $min !== null ? HTMLPurifier_Length::make($min) : null;
|
||||
$this->max = $max !== null ? HTMLPurifier_Length::make($max) : null;
|
||||
}
|
||||
|
||||
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 $length->toString();
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
// vim: et sw=4 sts=4
|
||||
|
|
@ -1,78 +0,0 @@
|
|||
<?php
|
||||
|
||||
/**
|
||||
* Validates shorthand CSS property list-style.
|
||||
* @warning Does not support url tokens that have internal spaces.
|
||||
*/
|
||||
class HTMLPurifier_AttrDef_CSS_ListStyle extends HTMLPurifier_AttrDef
|
||||
{
|
||||
|
||||
/**
|
||||
* Local copy of component validators.
|
||||
* @note See HTMLPurifier_AttrDef_CSS_Font::$info for a similar impl.
|
||||
*/
|
||||
protected $info;
|
||||
|
||||
public function __construct($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'] = $def->info['list-style-image'];
|
||||
}
|
||||
|
||||
public function validate($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
|
||||
|
|
@ -1,40 +0,0 @@
|
|||
<?php
|
||||
|
||||
/**
|
||||
* Validates a Percentage as defined by the CSS spec.
|
||||
*/
|
||||
class HTMLPurifier_AttrDef_CSS_Percentage extends HTMLPurifier_AttrDef
|
||||
{
|
||||
|
||||
/**
|
||||
* Instance of HTMLPurifier_AttrDef_CSS_Number to defer number validation
|
||||
*/
|
||||
protected $number_def;
|
||||
|
||||
/**
|
||||
* @param Bool indicating whether to forbid negative values
|
||||
*/
|
||||
public function __construct($non_negative = false) {
|
||||
$this->number_def = new HTMLPurifier_AttrDef_CSS_Number($non_negative);
|
||||
}
|
||||
|
||||
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
|
||||
|
|
@ -1,28 +0,0 @@
|
|||
<?php
|
||||
|
||||
/**
|
||||
* Validates a boolean attribute
|
||||
*/
|
||||
class HTMLPurifier_AttrDef_HTML_Bool extends HTMLPurifier_AttrDef
|
||||
{
|
||||
|
||||
protected $name;
|
||||
public $minimized = true;
|
||||
|
||||
public function __construct($name = false) {$this->name = $name;}
|
||||
|
||||
public function validate($string, $config, $context) {
|
||||
if (empty($string)) return false;
|
||||
return $this->name;
|
||||
}
|
||||
|
||||
/**
|
||||
* @param $string Name of attribute
|
||||
*/
|
||||
public function make($string) {
|
||||
return new HTMLPurifier_AttrDef_HTML_Bool($string);
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
// vim: et sw=4 sts=4
|
||||
|
|
@ -1,32 +0,0 @@
|
|||
<?php
|
||||
|
||||
/**
|
||||
* Validates a color according to the HTML spec.
|
||||
*/
|
||||
class HTMLPurifier_AttrDef_HTML_Color extends HTMLPurifier_AttrDef
|
||||
{
|
||||
|
||||
public function validate($string, $config, $context) {
|
||||
|
||||
static $colors = null;
|
||||
if ($colors === null) $colors = $config->get('Core.ColorKeywords');
|
||||
|
||||
$string = trim($string);
|
||||
|
||||
if (empty($string)) return false;
|
||||
if (isset($colors[$string])) return $colors[$string];
|
||||
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
|
||||
|
|
@ -1,21 +0,0 @@
|
|||
<?php
|
||||
|
||||
/**
|
||||
* Special-case enum attribute definition that lazy loads allowed frame targets
|
||||
*/
|
||||
class HTMLPurifier_AttrDef_HTML_FrameTarget extends HTMLPurifier_AttrDef_Enum
|
||||
{
|
||||
|
||||
public $valid_values = false; // uninitialized value
|
||||
protected $case_sensitive = false;
|
||||
|
||||
public function __construct() {}
|
||||
|
||||
public function validate($string, $config, $context) {
|
||||
if ($this->valid_values === false) $this->valid_values = $config->get('Attr.AllowedFrameTargets');
|
||||
return parent::validate($string, $config, $context);
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
// vim: et sw=4 sts=4
|
||||
|
|
@ -1,70 +0,0 @@
|
|||
<?php
|
||||
|
||||
/**
|
||||
* Validates the HTML attribute ID.
|
||||
* @warning Even though this is the id processor, it
|
||||
* will ignore the directive Attr:IDBlacklist, since it will only
|
||||
* go according to the ID accumulator. Since the accumulator is
|
||||
* automatically generated, it will have already absorbed the
|
||||
* blacklist. If you're hacking around, make sure you use load()!
|
||||
*/
|
||||
|
||||
class HTMLPurifier_AttrDef_HTML_ID extends HTMLPurifier_AttrDef
|
||||
{
|
||||
|
||||
// ref functionality disabled, since we also have to verify
|
||||
// whether or not the ID it refers to exists
|
||||
|
||||
public function validate($id, $config, $context) {
|
||||
|
||||
if (!$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->ref) {
|
||||
$id_accumulator =& $context->get('IDAccumulator');
|
||||
if (isset($id_accumulator->ids[$id])) return false;
|
||||
//}
|
||||
|
||||
// we purposely avoid using regex, hopefully this is faster
|
||||
|
||||
if (ctype_alpha($id)) {
|
||||
$result = true;
|
||||
} else {
|
||||
if (!ctype_alpha(@$id[0])) return false;
|
||||
$trim = trim( // primitive style of regexps, I suppose
|
||||
$id,
|
||||
'A..Za..z0..9:-._'
|
||||
);
|
||||
$result = ($trim === '');
|
||||
}
|
||||
|
||||
$regexp = $config->get('Attr.IDBlacklistRegexp');
|
||||
if ($regexp && preg_match($regexp, $id)) {
|
||||
return false;
|
||||
}
|
||||
|
||||
if (/*!$this->ref && */$result) $id_accumulator->add($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 $result ? $id : false;
|
||||
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
// vim: et sw=4 sts=4
|
||||
|
|
@ -1,41 +0,0 @@
|
|||
<?php
|
||||
|
||||
/**
|
||||
* Validates the HTML type length (not to be confused with CSS's length).
|
||||
*
|
||||
* This accepts integer pixels or percentages as lengths for certain
|
||||
* HTML attributes.
|
||||
*/
|
||||
|
||||
class HTMLPurifier_AttrDef_HTML_Length extends HTMLPurifier_AttrDef_HTML_Pixels
|
||||
{
|
||||
|
||||
public function validate($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) $points) . '%';
|
||||
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
// vim: et sw=4 sts=4
|
||||
|
|
@ -1,41 +0,0 @@
|
|||
<?php
|
||||
|
||||
/**
|
||||
* Validates a MultiLength as defined by the HTML spec.
|
||||
*
|
||||
* A multilength is either a integer (pixel count), a percentage, or
|
||||
* a relative number.
|
||||
*/
|
||||
class HTMLPurifier_AttrDef_HTML_MultiLength extends HTMLPurifier_AttrDef_HTML_Length
|
||||
{
|
||||
|
||||
public function validate($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
|
||||
|
|
@ -1,48 +0,0 @@
|
|||
<?php
|
||||
|
||||
/**
|
||||
* Validates an integer representation of pixels according to the HTML spec.
|
||||
*/
|
||||
class HTMLPurifier_AttrDef_HTML_Pixels extends HTMLPurifier_AttrDef
|
||||
{
|
||||
|
||||
protected $max;
|
||||
|
||||
public function __construct($max = null) {
|
||||
$this->max = $max;
|
||||
}
|
||||
|
||||
public function validate($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) $int;
|
||||
|
||||
}
|
||||
|
||||
public function make($string) {
|
||||
if ($string === '') $max = null;
|
||||
else $max = (int) $string;
|
||||
$class = get_class($this);
|
||||
return new $class($max);
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
// vim: et sw=4 sts=4
|
||||
|
|
@ -1,15 +0,0 @@
|
|||
<?php
|
||||
|
||||
/**
|
||||
* Validates arbitrary text according to the HTML spec.
|
||||
*/
|
||||
class HTMLPurifier_AttrDef_Text extends HTMLPurifier_AttrDef
|
||||
{
|
||||
|
||||
public function validate($string, $config, $context) {
|
||||
return $this->parseCDATA($string);
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
// vim: et sw=4 sts=4
|
||||
|
|
@ -1,62 +0,0 @@
|
|||
<?php
|
||||
|
||||
/**
|
||||
* Validates a host according to the IPv4, IPv6 and DNS (future) specifications.
|
||||
*/
|
||||
class HTMLPurifier_AttrDef_URI_Host extends HTMLPurifier_AttrDef
|
||||
{
|
||||
|
||||
/**
|
||||
* Instance of HTMLPurifier_AttrDef_URI_IPv4 sub-validator
|
||||
*/
|
||||
protected $ipv4;
|
||||
|
||||
/**
|
||||
* Instance of HTMLPurifier_AttrDef_URI_IPv6 sub-validator
|
||||
*/
|
||||
protected $ipv6;
|
||||
|
||||
public function __construct() {
|
||||
$this->ipv4 = new HTMLPurifier_AttrDef_URI_IPv4();
|
||||
$this->ipv6 = new HTMLPurifier_AttrDef_URI_IPv6();
|
||||
}
|
||||
|
||||
public function validate($string, $config, $context) {
|
||||
$length = strlen($string);
|
||||
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 breaks I18N domain names, but we don't have proper IRI support,
|
||||
// so force users to insert Punycode. If there's complaining we'll
|
||||
// try to fix things into an international friendly form.
|
||||
|
||||
// The productions describing this are:
|
||||
$a = '[a-z]'; // alpha
|
||||
$an = '[a-z0-9]'; // alphanum
|
||||
$and = '[a-z0-9-]'; // alphanum | "-"
|
||||
// domainlabel = alphanum | alphanum *( alphanum | "-" ) alphanum
|
||||
$domainlabel = "$an($and*$an)?";
|
||||
// toplabel = alpha | alpha *( alphanum | "-" ) alphanum
|
||||
$toplabel = "$a($and*$an)?";
|
||||
// hostname = *( domainlabel "." ) toplabel [ "." ]
|
||||
$match = preg_match("/^($domainlabel\.)*$toplabel\.?$/i", $string);
|
||||
if (!$match) return false;
|
||||
|
||||
return $string;
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
// vim: et sw=4 sts=4
|
||||
|
|
@ -1,99 +0,0 @@
|
|||
<?php
|
||||
|
||||
/**
|
||||
* Validates an IPv6 address.
|
||||
* @author Feyd @ forums.devnetwork.net (public domain)
|
||||
* @note This function requires brackets to have been removed from address
|
||||
* in URI.
|
||||
*/
|
||||
class HTMLPurifier_AttrDef_URI_IPv6 extends HTMLPurifier_AttrDef_URI_IPv4
|
||||
{
|
||||
|
||||
public function validate($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
|
||||
|
|
@ -1,36 +0,0 @@
|
|||
<?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
|
||||
*/
|
||||
protected $attr;
|
||||
|
||||
/**
|
||||
* CSS declarations to add to style, needs trailing semicolon
|
||||
*/
|
||||
protected $css;
|
||||
|
||||
/**
|
||||
* @param $attr string attribute name to convert from
|
||||
* @param $css string CSS declarations to add to style (needs semicolon)
|
||||
*/
|
||||
public function __construct($attr, $css) {
|
||||
$this->attr = $attr;
|
||||
$this->css = $css;
|
||||
}
|
||||
|
||||
public function transform($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
|
||||
|
|
@ -1,58 +0,0 @@
|
|||
<?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
|
||||
*/
|
||||
protected $attr;
|
||||
|
||||
/**
|
||||
* Lookup array of attribute values to CSS
|
||||
*/
|
||||
protected $enumToCSS = array();
|
||||
|
||||
/**
|
||||
* Case sensitivity of the matching
|
||||
* @warning Currently can only be guaranteed to work with ASCII
|
||||
* values.
|
||||
*/
|
||||
protected $caseSensitive = false;
|
||||
|
||||
/**
|
||||
* @param $attr String attribute name to transform from
|
||||
* @param $enumToCSS Lookup array of attribute values to CSS
|
||||
* @param $case_sensitive Boolean case sensitivity indicator, default false
|
||||
*/
|
||||
public function __construct($attr, $enum_to_css, $case_sensitive = false) {
|
||||
$this->attr = $attr;
|
||||
$this->enumToCSS = $enum_to_css;
|
||||
$this->caseSensitive = (bool) $case_sensitive;
|
||||
}
|
||||
|
||||
public function transform($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
|
||||
|
|
@ -1,27 +0,0 @@
|
|||
<?php
|
||||
|
||||
/**
|
||||
* Class for handling width/height length attribute transformations to CSS
|
||||
*/
|
||||
class HTMLPurifier_AttrTransform_Length extends HTMLPurifier_AttrTransform
|
||||
{
|
||||
|
||||
protected $name;
|
||||
protected $cssName;
|
||||
|
||||
public function __construct($name, $css_name = null) {
|
||||
$this->name = $name;
|
||||
$this->cssName = $css_name ? $css_name : $name;
|
||||
}
|
||||
|
||||
public function transform($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 $attr;
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
// vim: et sw=4 sts=4
|
||||
|
|
@ -1,21 +0,0 @@
|
|||
<?php
|
||||
|
||||
/**
|
||||
* Pre-transform that changes deprecated name attribute to ID if necessary
|
||||
*/
|
||||
class HTMLPurifier_AttrTransform_Name extends HTMLPurifier_AttrTransform
|
||||
{
|
||||
|
||||
public function transform($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
|
||||
|
|
@ -1,27 +0,0 @@
|
|||
<?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() {
|
||||
$this->idDef = new HTMLPurifier_AttrDef_HTML_ID();
|
||||
}
|
||||
|
||||
public function transform($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
|
||||
|
|
@ -1,16 +0,0 @@
|
|||
<?php
|
||||
|
||||
/**
|
||||
* Writes default type for all objects. Currently only supports flash.
|
||||
*/
|
||||
class HTMLPurifier_AttrTransform_SafeObject extends HTMLPurifier_AttrTransform
|
||||
{
|
||||
public $name = "SafeObject";
|
||||
|
||||
function transform($attr, $config, $context) {
|
||||
if (!isset($attr['type'])) $attr['type'] = 'application/x-shockwave-flash';
|
||||
return $attr;
|
||||
}
|
||||
}
|
||||
|
||||
// vim: et sw=4 sts=4
|
||||
|
|
@ -1,18 +0,0 @@
|
|||
<?php
|
||||
|
||||
/**
|
||||
* Sets height/width defaults for <textarea>
|
||||
*/
|
||||
class HTMLPurifier_AttrTransform_Textarea extends HTMLPurifier_AttrTransform
|
||||
{
|
||||
|
||||
public function transform($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
|
||||
|
|
@ -1,98 +0,0 @@
|
|||
<?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 $class Class to load
|
||||
*/
|
||||
public static function autoload($class) {
|
||||
$file = HTMLPurifier_Bootstrap::getPath($class);
|
||||
if (!$file) return false;
|
||||
require HTMLPURIFIER_PREFIX . '/' . $file;
|
||||
return true;
|
||||
}
|
||||
|
||||
/**
|
||||
* Returns the path for a specific class.
|
||||
*/
|
||||
public static function getPath($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')) {
|
||||
$compat = version_compare(PHP_VERSION, '5.1.2', '<=') &&
|
||||
version_compare(PHP_VERSION, '5.1.0', '>=');
|
||||
foreach ($funcs as $func) {
|
||||
if (is_array($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
|
||||
|
|
@ -1,292 +0,0 @@
|
|||
<?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.
|
||||
*/
|
||||
public $info = array();
|
||||
|
||||
/**
|
||||
* Constructs the info array. The meat of this class.
|
||||
*/
|
||||
protected function doSetup($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'))
|
||||
));
|
||||
$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['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);
|
||||
|
||||
// partial support
|
||||
$this->info['white-space'] = new HTMLPurifier_AttrDef_Enum(array('nowrap'));
|
||||
|
||||
if ($config->get('CSS.Proprietary')) {
|
||||
$this->doSetupProprietary($config);
|
||||
}
|
||||
|
||||
if ($config->get('CSS.AllowTricky')) {
|
||||
$this->doSetupTricky($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);
|
||||
}
|
||||
|
||||
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();
|
||||
|
||||
// technically not proprietary, but CSS3, and no one supports it
|
||||
$this->info['opacity'] = new HTMLPurifier_AttrDef_CSS_AlphaValue();
|
||||
$this->info['-moz-opacity'] = new HTMLPurifier_AttrDef_CSS_AlphaValue();
|
||||
$this->info['-khtml-opacity'] = new HTMLPurifier_AttrDef_CSS_AlphaValue();
|
||||
|
||||
// only opacity, for now
|
||||
$this->info['filter'] = new HTMLPurifier_AttrDef_CSS_Filter();
|
||||
|
||||
}
|
||||
|
||||
protected function doSetupTricky($config) {
|
||||
$this->info['display'] = new HTMLPurifier_AttrDef_Enum(array(
|
||||
'inline', 'block', 'list-item', 'run-in', 'compact',
|
||||
'marker', 'table', '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'
|
||||
));
|
||||
$this->info['overflow'] = new HTMLPurifier_AttrDef_Enum(array('visible', 'hidden', 'auto', 'scroll'));
|
||||
}
|
||||
|
||||
|
||||
/**
|
||||
* Performs extra config-based processing. Based off of
|
||||
* HTMLPurifier_HTMLDefinition.
|
||||
* @todo Refactor duplicate elements into common class (probably using
|
||||
* composition, not inheritance).
|
||||
*/
|
||||
protected function setupConfigStuff($config) {
|
||||
|
||||
// setup allowed elements
|
||||
$support = "(for information on implementing this, see the ".
|
||||
"support forums) ";
|
||||
$allowed_attributes = $config->get('CSS.AllowedProperties');
|
||||
if ($allowed_attributes !== null) {
|
||||
foreach ($this->info as $name => $d) {
|
||||
if(!isset($allowed_attributes[$name])) unset($this->info[$name]);
|
||||
unset($allowed_attributes[$name]);
|
||||
}
|
||||
// emit errors
|
||||
foreach ($allowed_attributes 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);
|
||||
}
|
||||
}
|
||||
|
||||
}
|
||||
}
|
||||
|
||||
// vim: et sw=4 sts=4
|
||||
|
|
@ -1,26 +0,0 @@
|
|||
<?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
|
||||
{
|
||||
public $allow_empty = true;
|
||||
public $type = 'optional';
|
||||
public function validateChildren($tokens_of_children, $config, $context) {
|
||||
$result = parent::validateChildren($tokens_of_children, $config, $context);
|
||||
// we assume that $tokens_of_children is not modified
|
||||
if ($result === false) {
|
||||
if (empty($tokens_of_children)) return true;
|
||||
elseif ($this->whitespace) return $tokens_of_children;
|
||||
else return array();
|
||||
}
|
||||
return $result;
|
||||
}
|
||||
}
|
||||
|
||||
// vim: et sw=4 sts=4
|
||||
|
|
@ -1,117 +0,0 @@
|
|||
<?php
|
||||
|
||||
/**
|
||||
* Definition that allows a set of elements, but disallows empty children.
|
||||
*/
|
||||
class HTMLPurifier_ChildDef_Required extends HTMLPurifier_ChildDef
|
||||
{
|
||||
/**
|
||||
* Lookup table of allowed elements.
|
||||
* @public
|
||||
*/
|
||||
public $elements = array();
|
||||
/**
|
||||
* Whether or not the last passed node was all whitespace.
|
||||
*/
|
||||
protected $whitespace = false;
|
||||
/**
|
||||
* @param $elements List of allowed element names (lowercase).
|
||||
*/
|
||||
public function __construct($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;
|
||||
}
|
||||
public $allow_empty = false;
|
||||
public $type = 'required';
|
||||
public function validateChildren($tokens_of_children, $config, $context) {
|
||||
// Flag for subclasses
|
||||
$this->whitespace = false;
|
||||
|
||||
// if there are no tokens, delete parent node
|
||||
if (empty($tokens_of_children)) return false;
|
||||
|
||||
// the new set of children
|
||||
$result = array();
|
||||
|
||||
// current depth into the nest
|
||||
$nesting = 0;
|
||||
|
||||
// whether or not we're deleting a node
|
||||
$is_deleting = false;
|
||||
|
||||
// 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;
|
||||
|
||||
// some configuration
|
||||
$escape_invalid_children = $config->get('Core.EscapeInvalidChildren');
|
||||
|
||||
// generator
|
||||
$gen = new HTMLPurifier_Generator($config, $context);
|
||||
|
||||
foreach ($tokens_of_children as $token) {
|
||||
if (!empty($token->is_whitespace)) {
|
||||
$result[] = $token;
|
||||
continue;
|
||||
}
|
||||
$all_whitespace = false; // phew, we're not talking about whitespace
|
||||
|
||||
$is_child = ($nesting == 0);
|
||||
|
||||
if ($token instanceof HTMLPurifier_Token_Start) {
|
||||
$nesting++;
|
||||
} elseif ($token instanceof HTMLPurifier_Token_End) {
|
||||
$nesting--;
|
||||
}
|
||||
|
||||
if ($is_child) {
|
||||
$is_deleting = false;
|
||||
if (!isset($this->elements[$token->name])) {
|
||||
$is_deleting = true;
|
||||
if ($pcdata_allowed && $token instanceof HTMLPurifier_Token_Text) {
|
||||
$result[] = $token;
|
||||
} elseif ($pcdata_allowed && $escape_invalid_children) {
|
||||
$result[] = new HTMLPurifier_Token_Text(
|
||||
$gen->generateFromToken($token)
|
||||
);
|
||||
}
|
||||
continue;
|
||||
}
|
||||
}
|
||||
if (!$is_deleting || ($pcdata_allowed && $token instanceof HTMLPurifier_Token_Text)) {
|
||||
$result[] = $token;
|
||||
} elseif ($pcdata_allowed && $escape_invalid_children) {
|
||||
$result[] =
|
||||
new HTMLPurifier_Token_Text(
|
||||
$gen->generateFromToken($token)
|
||||
);
|
||||
} else {
|
||||
// drop silently
|
||||
}
|
||||
}
|
||||
if (empty($result)) return false;
|
||||
if ($all_whitespace) {
|
||||
$this->whitespace = true;
|
||||
return false;
|
||||
}
|
||||
if ($tokens_of_children == $result) return true;
|
||||
return $result;
|
||||
}
|
||||
}
|
||||
|
||||
// vim: et sw=4 sts=4
|
||||
|
|
@ -1,88 +0,0 @@
|
|||
<?php
|
||||
|
||||
/**
|
||||
* Takes the contents of blockquote when in strict and reformats for validation.
|
||||
*/
|
||||
class HTMLPurifier_ChildDef_StrictBlockquote extends HTMLPurifier_ChildDef_Required
|
||||
{
|
||||
protected $real_elements;
|
||||
protected $fake_elements;
|
||||
public $allow_empty = true;
|
||||
public $type = 'strictblockquote';
|
||||
protected $init = false;
|
||||
|
||||
/**
|
||||
* @note We don't want MakeWellFormed to auto-close inline elements since
|
||||
* they might be allowed.
|
||||
*/
|
||||
public function getAllowedElements($config) {
|
||||
$this->init($config);
|
||||
return $this->fake_elements;
|
||||
}
|
||||
|
||||
public function validateChildren($tokens_of_children, $config, $context) {
|
||||
|
||||
$this->init($config);
|
||||
|
||||
// trick the parent class into thinking it allows more
|
||||
$this->elements = $this->fake_elements;
|
||||
$result = parent::validateChildren($tokens_of_children, $config, $context);
|
||||
$this->elements = $this->real_elements;
|
||||
|
||||
if ($result === false) return array();
|
||||
if ($result === true) $result = $tokens_of_children;
|
||||
|
||||
$def = $config->getHTMLDefinition();
|
||||
$block_wrap_start = new HTMLPurifier_Token_Start($def->info_block_wrapper);
|
||||
$block_wrap_end = new HTMLPurifier_Token_End( $def->info_block_wrapper);
|
||||
$is_inline = false;
|
||||
$depth = 0;
|
||||
$ret = array();
|
||||
|
||||
// assuming that there are no comment tokens
|
||||
foreach ($result as $i => $token) {
|
||||
$token = $result[$i];
|
||||
// ifs are nested for readability
|
||||
if (!$is_inline) {
|
||||
if (!$depth) {
|
||||
if (
|
||||
($token instanceof HTMLPurifier_Token_Text && !$token->is_whitespace) ||
|
||||
(!$token instanceof HTMLPurifier_Token_Text && !isset($this->elements[$token->name]))
|
||||
) {
|
||||
$is_inline = true;
|
||||
$ret[] = $block_wrap_start;
|
||||
}
|
||||
}
|
||||
} else {
|
||||
if (!$depth) {
|
||||
// starting tokens have been inline text / empty
|
||||
if ($token instanceof HTMLPurifier_Token_Start || $token instanceof HTMLPurifier_Token_Empty) {
|
||||
if (isset($this->elements[$token->name])) {
|
||||
// ended
|
||||
$ret[] = $block_wrap_end;
|
||||
$is_inline = false;
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
$ret[] = $token;
|
||||
if ($token instanceof HTMLPurifier_Token_Start) $depth++;
|
||||
if ($token instanceof HTMLPurifier_Token_End) $depth--;
|
||||
}
|
||||
if ($is_inline) $ret[] = $block_wrap_end;
|
||||
return $ret;
|
||||
}
|
||||
|
||||
private function init($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
|
||||
|
|
@ -1,142 +0,0 @@
|
|||
<?php
|
||||
|
||||
/**
|
||||
* Definition for tables
|
||||
*/
|
||||
class HTMLPurifier_ChildDef_Table extends HTMLPurifier_ChildDef
|
||||
{
|
||||
public $allow_empty = false;
|
||||
public $type = 'table';
|
||||
public $elements = array('tr' => true, 'tbody' => true, 'thead' => true,
|
||||
'tfoot' => true, 'caption' => true, 'colgroup' => true, 'col' => true);
|
||||
public function __construct() {}
|
||||
public function validateChildren($tokens_of_children, $config, $context) {
|
||||
if (empty($tokens_of_children)) return false;
|
||||
|
||||
// this ensures that the loop gets run one last time before closing
|
||||
// up. It's a little bit of a hack, but it works! Just make sure you
|
||||
// get rid of the token later.
|
||||
$tokens_of_children[] = false;
|
||||
|
||||
// only one of these elements is allowed in a table
|
||||
$caption = false;
|
||||
$thead = false;
|
||||
$tfoot = false;
|
||||
|
||||
// as many of these as you want
|
||||
$cols = array();
|
||||
$content = array();
|
||||
|
||||
$nesting = 0; // current depth so we can determine nodes
|
||||
$is_collecting = false; // are we globbing together tokens to package
|
||||
// into one of the collectors?
|
||||
$collection = array(); // collected nodes
|
||||
$tag_index = 0; // the first node might be whitespace,
|
||||
// so this tells us where the start tag is
|
||||
|
||||
foreach ($tokens_of_children as $token) {
|
||||
$is_child = ($nesting == 0);
|
||||
|
||||
if ($token === false) {
|
||||
// terminating sequence started
|
||||
} elseif ($token instanceof HTMLPurifier_Token_Start) {
|
||||
$nesting++;
|
||||
} elseif ($token instanceof HTMLPurifier_Token_End) {
|
||||
$nesting--;
|
||||
}
|
||||
|
||||
// handle node collection
|
||||
if ($is_collecting) {
|
||||
if ($is_child) {
|
||||
// okay, let's stash the tokens away
|
||||
// first token tells us the type of the collection
|
||||
switch ($collection[$tag_index]->name) {
|
||||
case 'tr':
|
||||
case 'tbody':
|
||||
$content[] = $collection;
|
||||
break;
|
||||
case 'caption':
|
||||
if ($caption !== false) break;
|
||||
$caption = $collection;
|
||||
break;
|
||||
case 'thead':
|
||||
case 'tfoot':
|
||||
// access the appropriate variable, $thead or $tfoot
|
||||
$var = $collection[$tag_index]->name;
|
||||
if ($$var === false) {
|
||||
$$var = $collection;
|
||||
} else {
|
||||
// transmutate the first and less entries into
|
||||
// tbody tags, and then put into content
|
||||
$collection[$tag_index]->name = 'tbody';
|
||||
$collection[count($collection)-1]->name = 'tbody';
|
||||
$content[] = $collection;
|
||||
}
|
||||
break;
|
||||
case 'colgroup':
|
||||
$cols[] = $collection;
|
||||
break;
|
||||
}
|
||||
$collection = array();
|
||||
$is_collecting = false;
|
||||
$tag_index = 0;
|
||||
} else {
|
||||
// add the node to the collection
|
||||
$collection[] = $token;
|
||||
}
|
||||
}
|
||||
|
||||
// terminate
|
||||
if ($token === false) break;
|
||||
|
||||
if ($is_child) {
|
||||
// determine what we're dealing with
|
||||
if ($token->name == 'col') {
|
||||
// the only empty tag in the possie, we can handle it
|
||||
// immediately
|
||||
$cols[] = array_merge($collection, array($token));
|
||||
$collection = array();
|
||||
$tag_index = 0;
|
||||
continue;
|
||||
}
|
||||
switch($token->name) {
|
||||
case 'caption':
|
||||
case 'colgroup':
|
||||
case 'thead':
|
||||
case 'tfoot':
|
||||
case 'tbody':
|
||||
case 'tr':
|
||||
$is_collecting = true;
|
||||
$collection[] = $token;
|
||||
continue;
|
||||
default:
|
||||
if (!empty($token->is_whitespace)) {
|
||||
$collection[] = $token;
|
||||
$tag_index++;
|
||||
}
|
||||
continue;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
if (empty($content)) return false;
|
||||
|
||||
$ret = array();
|
||||
if ($caption !== false) $ret = array_merge($ret, $caption);
|
||||
if ($cols !== false) foreach ($cols as $token_array) $ret = array_merge($ret, $token_array);
|
||||
if ($thead !== false) $ret = array_merge($ret, $thead);
|
||||
if ($tfoot !== false) $ret = array_merge($ret, $tfoot);
|
||||
foreach ($content as $token_array) $ret = array_merge($ret, $token_array);
|
||||
if (!empty($collection) && $is_collecting == false){
|
||||
// grab the trailing space
|
||||
$ret = array_merge($ret, $collection);
|
||||
}
|
||||
|
||||
array_pop($tokens_of_children); // remove phantom token
|
||||
|
||||
return ($ret === $tokens_of_children) ? true : $ret;
|
||||
|
||||
}
|
||||
}
|
||||
|
||||
// vim: et sw=4 sts=4
|
||||
|
|
@ -1,580 +0,0 @@
|
|||
<?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
|
||||
*/
|
||||
public $version = '4.1.1';
|
||||
|
||||
/**
|
||||
* Bool indicator whether or not to automatically finalize
|
||||
* the object if a read operation is done
|
||||
*/
|
||||
public $autoFinalize = true;
|
||||
|
||||
// protected member variables
|
||||
|
||||
/**
|
||||
* Namespace indexed array of serials for specific namespaces (see
|
||||
* getSerial() for more info).
|
||||
*/
|
||||
protected $serials = array();
|
||||
|
||||
/**
|
||||
* Serial for entire configuration object
|
||||
*/
|
||||
protected $serial;
|
||||
|
||||
/**
|
||||
* Parser for variables
|
||||
*/
|
||||
protected $parser;
|
||||
|
||||
/**
|
||||
* Reference HTMLPurifier_ConfigSchema for value checking
|
||||
* @note This is public for introspective purposes. Please don't
|
||||
* abuse!
|
||||
*/
|
||||
public $def;
|
||||
|
||||
/**
|
||||
* Indexed array of definitions
|
||||
*/
|
||||
protected $definitions;
|
||||
|
||||
/**
|
||||
* Bool indicator whether or not config is finalized
|
||||
*/
|
||||
protected $finalized = false;
|
||||
|
||||
/**
|
||||
* Property list containing configuration directives.
|
||||
*/
|
||||
protected $plist;
|
||||
|
||||
/**
|
||||
* Whether or not a set is taking place due to an
|
||||
* alias lookup.
|
||||
*/
|
||||
private $aliasMode;
|
||||
|
||||
/**
|
||||
* Set to false if you do not want line and file numbers in errors
|
||||
* (useful when unit testing)
|
||||
*/
|
||||
public $chatty = true;
|
||||
|
||||
/**
|
||||
* Current lock; only gets to this namespace are allowed.
|
||||
*/
|
||||
private $lock;
|
||||
|
||||
/**
|
||||
* @param $definition HTMLPurifier_ConfigSchema that defines what directives
|
||||
* are allowed.
|
||||
*/
|
||||
public function __construct($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 $config Variable that defines the state of the config
|
||||
* object. Can be: a HTMLPurifier_Config() object,
|
||||
* an array of directives based on loadArray(),
|
||||
* or a string filename of an ini file.
|
||||
* @param HTMLPurifier_ConfigSchema Schema object
|
||||
* @return Configured HTMLPurifier_Config object
|
||||
*/
|
||||
public static function create($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 Default HTMLPurifier_Config object.
|
||||
*/
|
||||
public static function createDefault() {
|
||||
$definition = HTMLPurifier_ConfigSchema::instance();
|
||||
$config = new HTMLPurifier_Config($definition);
|
||||
return $config;
|
||||
}
|
||||
|
||||
/**
|
||||
* Retreives a value from the configuration.
|
||||
* @param $key String key
|
||||
*/
|
||||
public function get($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);
|
||||
}
|
||||
|
||||
/**
|
||||
* Retreives an array of directives to values from a given namespace
|
||||
* @param $namespace String namespace
|
||||
*/
|
||||
public function getBatch($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 md5 signature of a segment of the configuration object
|
||||
* that uniquely identifies that particular configuration
|
||||
* @note Revision is handled specially and is removed from the batch
|
||||
* before processing!
|
||||
* @param $namespace Namespace to get serial for
|
||||
*/
|
||||
public function getBatchSerial($namespace) {
|
||||
if (empty($this->serials[$namespace])) {
|
||||
$batch = $this->getBatch($namespace);
|
||||
unset($batch['DefinitionRev']);
|
||||
$this->serials[$namespace] = md5(serialize($batch));
|
||||
}
|
||||
return $this->serials[$namespace];
|
||||
}
|
||||
|
||||
/**
|
||||
* Returns a md5 signature for the entire configuration object
|
||||
* that uniquely identifies that particular configuration
|
||||
*/
|
||||
public function getSerial() {
|
||||
if (empty($this->serial)) {
|
||||
$this->serial = md5(serialize($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 $key String key
|
||||
* @param $value Mixed value
|
||||
*/
|
||||
public function set($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
|
||||
*/
|
||||
private function _listify($lookup) {
|
||||
$list = array();
|
||||
foreach ($lookup as $name => $b) $list[] = $name;
|
||||
return implode(', ', $list);
|
||||
}
|
||||
|
||||
/**
|
||||
* Retrieves object reference to the HTML definition.
|
||||
* @param $raw Return a copy that has not been setup yet. Must be
|
||||
* called before it's been setup, otherwise won't work.
|
||||
*/
|
||||
public function getHTMLDefinition($raw = false) {
|
||||
return $this->getDefinition('HTML', $raw);
|
||||
}
|
||||
|
||||
/**
|
||||
* Retrieves object reference to the CSS definition
|
||||
* @param $raw Return a copy that has not been setup yet. Must be
|
||||
* called before it's been setup, otherwise won't work.
|
||||
*/
|
||||
public function getCSSDefinition($raw = false) {
|
||||
return $this->getDefinition('CSS', $raw);
|
||||
}
|
||||
|
||||
/**
|
||||
* Retrieves a definition
|
||||
* @param $type Type of definition: HTML, CSS, etc
|
||||
* @param $raw Whether or not definition should be returned raw
|
||||
*/
|
||||
public function getDefinition($type, $raw = false) {
|
||||
if (!$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) {
|
||||
// see if we can quickly supply a definition
|
||||
if (!empty($this->definitions[$type])) {
|
||||
if (!$this->definitions[$type]->setup) {
|
||||
$this->definitions[$type]->setup($this);
|
||||
$cache->set($this->definitions[$type], $this);
|
||||
}
|
||||
return $this->definitions[$type];
|
||||
}
|
||||
// memory check missed, try cache
|
||||
$this->definitions[$type] = $cache->get($this);
|
||||
if ($this->definitions[$type]) {
|
||||
// definition in cache, return it
|
||||
return $this->definitions[$type];
|
||||
}
|
||||
} elseif (
|
||||
!empty($this->definitions[$type]) &&
|
||||
!$this->definitions[$type]->setup
|
||||
) {
|
||||
// raw requested, raw in memory, quick return
|
||||
return $this->definitions[$type];
|
||||
}
|
||||
// quick checks failed, let's create the object
|
||||
if ($type == 'HTML') {
|
||||
$this->definitions[$type] = new HTMLPurifier_HTMLDefinition();
|
||||
} elseif ($type == 'CSS') {
|
||||
$this->definitions[$type] = new HTMLPurifier_CSSDefinition();
|
||||
} elseif ($type == 'URI') {
|
||||
$this->definitions[$type] = new HTMLPurifier_URIDefinition();
|
||||
} else {
|
||||
throw new HTMLPurifier_Exception("Definition of $type type not supported");
|
||||
}
|
||||
// quick abort if raw
|
||||
if ($raw) {
|
||||
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");
|
||||
}
|
||||
return $this->definitions[$type];
|
||||
}
|
||||
// set it up
|
||||
$this->lock = $type;
|
||||
$this->definitions[$type]->setup($this);
|
||||
$this->lock = null;
|
||||
// save in cache
|
||||
$cache->set($this->definitions[$type], $this);
|
||||
return $this->definitions[$type];
|
||||
}
|
||||
|
||||
/**
|
||||
* Loads configuration values from an array with the following structure:
|
||||
* Namespace.Directive => Value
|
||||
* @param $config_array Configuration associative array
|
||||
*/
|
||||
public function loadArray($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 => $value) {
|
||||
$this->set($namespace .'.'. $directive, $value);
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* 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 $allowed List of allowed namespaces/directives
|
||||
*/
|
||||
public static function getAllowedDirectivesForForm($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 $_GET or $_POST array to import
|
||||
* @param $index Index/name that the config variables are in
|
||||
* @param $allowed List of allowed namespaces/directives
|
||||
* @param $mq_fix Boolean whether or not to enable magic quotes fix
|
||||
* @param $schema Instance of HTMLPurifier_ConfigSchema to use, if not global copy
|
||||
*/
|
||||
public static function loadArrayFromForm($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.
|
||||
* @note Same parameters as loadArrayFromForm
|
||||
*/
|
||||
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
|
||||
*/
|
||||
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 $filename Name of ini file
|
||||
*/
|
||||
public function loadIni($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 $error String error message, or false for no error
|
||||
*/
|
||||
public function isFinalized($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() {
|
||||
$this->finalized = true;
|
||||
unset($this->parser);
|
||||
}
|
||||
|
||||
/**
|
||||
* Produces a nicely formatted error message by supplying the
|
||||
* stack frame information from two levels up and OUTSIDE of
|
||||
* HTMLPurifier_Config.
|
||||
*/
|
||||
protected function triggerError($msg, $no) {
|
||||
// determine previous stack frame
|
||||
$backtrace = debug_backtrace();
|
||||
if ($this->chatty && isset($backtrace[1])) {
|
||||
$frame = $backtrace[1];
|
||||
$extra = " on line {$frame['line']} in file {$frame['file']}";
|
||||
} else {
|
||||
$extra = '';
|
||||
}
|
||||
trigger_error($msg . $extra, $no);
|
||||
}
|
||||
|
||||
/**
|
||||
* Returns a serialized form of the configuration object that can
|
||||
* be reconstituted.
|
||||
*/
|
||||
public function serialize() {
|
||||
$this->getDefinition('HTML');
|
||||
$this->getDefinition('CSS');
|
||||
$this->getDefinition('URI');
|
||||
return serialize($this);
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
// vim: et sw=4 sts=4
|
||||
|
|
@ -1,66 +0,0 @@
|
|||
<?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
|
||||
{
|
||||
|
||||
protected $context, $obj, $member, $contents;
|
||||
|
||||
public function __construct($context, $obj, $member) {
|
||||
$this->context = $context;
|
||||
$this->obj = $obj;
|
||||
$this->member = $member;
|
||||
$this->contents =& $obj->$member;
|
||||
}
|
||||
|
||||
public function assertIsString() {
|
||||
if (!is_string($this->contents)) $this->error('must be a string');
|
||||
return $this;
|
||||
}
|
||||
|
||||
public function assertIsBool() {
|
||||
if (!is_bool($this->contents)) $this->error('must be a boolean');
|
||||
return $this;
|
||||
}
|
||||
|
||||
public function assertIsArray() {
|
||||
if (!is_array($this->contents)) $this->error('must be an array');
|
||||
return $this;
|
||||
}
|
||||
|
||||
public function assertNotNull() {
|
||||
if ($this->contents === null) $this->error('must not be null');
|
||||
return $this;
|
||||
}
|
||||
|
||||
public function assertAlnum() {
|
||||
$this->assertIsString();
|
||||
if (!ctype_alnum($this->contents)) $this->error('must be alphanumeric');
|
||||
return $this;
|
||||
}
|
||||
|
||||
public function assertNotEmpty() {
|
||||
if (empty($this->contents)) $this->error('must not be empty');
|
||||
return $this;
|
||||
}
|
||||
|
||||
public function assertIsLookup() {
|
||||
$this->assertIsArray();
|
||||
foreach ($this->contents as $v) {
|
||||
if ($v !== true) $this->error('must be a lookup array');
|
||||
}
|
||||
return $this;
|
||||
}
|
||||
|
||||
protected function error($msg) {
|
||||
throw new HTMLPurifier_ConfigSchema_Exception(ucfirst($this->member) . ' in ' . $this->context . ' ' . $msg);
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
// vim: et sw=4 sts=4
|
||||
Binary file not shown.
|
|
@ -1,18 +0,0 @@
|
|||
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. Note that this
|
||||
method is subtractive: it does its job by taking away from HTML Purifier
|
||||
usual feature set, so you cannot add a tag that HTML Purifier never
|
||||
supported in the first place (like embed, form or head). If you
|
||||
change this, you probably also want to change %HTML.AllowedAttributes.
|
||||
</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
|
||||
|
|
@ -1,82 +0,0 @@
|
|||
<?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.
|
||||
*/
|
||||
private $_storage = array();
|
||||
|
||||
/**
|
||||
* Registers a variable into the context.
|
||||
* @param $name String name
|
||||
* @param $ref Reference to variable to be registered
|
||||
*/
|
||||
public function register($name, &$ref) {
|
||||
if (isset($this->_storage[$name])) {
|
||||
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 $name String name
|
||||
* @param $ignore_error Boolean whether or not to ignore error
|
||||
*/
|
||||
public function &get($name, $ignore_error = false) {
|
||||
if (!isset($this->_storage[$name])) {
|
||||
if (!$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];
|
||||
}
|
||||
|
||||
/**
|
||||
* Destorys a variable in the context.
|
||||
* @param $name String name
|
||||
*/
|
||||
public function destroy($name) {
|
||||
if (!isset($this->_storage[$name])) {
|
||||
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 $name String name
|
||||
*/
|
||||
public function exists($name) {
|
||||
return isset($this->_storage[$name]);
|
||||
}
|
||||
|
||||
/**
|
||||
* Loads a series of variables from an associative array
|
||||
* @param $context_array Assoc array of variables to load
|
||||
*/
|
||||
public function loadArray($context_array) {
|
||||
foreach ($context_array as $key => $discard) {
|
||||
$this->register($key, $context_array[$key]);
|
||||
}
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
// vim: et sw=4 sts=4
|
||||
|
|
@ -1,39 +0,0 @@
|
|||
<?php
|
||||
|
||||
/**
|
||||
* Super-class for definition datatype objects, implements serialization
|
||||
* functions for the class.
|
||||
*/
|
||||
abstract class HTMLPurifier_Definition
|
||||
{
|
||||
|
||||
/**
|
||||
* Has setup() been called yet?
|
||||
*/
|
||||
public $setup = false;
|
||||
|
||||
/**
|
||||
* What type of definition is it?
|
||||
*/
|
||||
public $type;
|
||||
|
||||
/**
|
||||
* Sets up the definition object into the final form, something
|
||||
* not done by the constructor
|
||||
* @param $config HTMLPurifier_Config instance
|
||||
*/
|
||||
abstract protected function doSetup($config);
|
||||
|
||||
/**
|
||||
* Setup function that aborts if already setup
|
||||
* @param $config HTMLPurifier_Config instance
|
||||
*/
|
||||
public function setup($config) {
|
||||
if ($this->setup) return;
|
||||
$this->setup = true;
|
||||
$this->doSetup($config);
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
// vim: et sw=4 sts=4
|
||||
|
|
@ -1,62 +0,0 @@
|
|||
<?php
|
||||
|
||||
class HTMLPurifier_DefinitionCache_Decorator extends HTMLPurifier_DefinitionCache
|
||||
{
|
||||
|
||||
/**
|
||||
* Cache object we are decorating
|
||||
*/
|
||||
public $cache;
|
||||
|
||||
public function __construct() {}
|
||||
|
||||
/**
|
||||
* Lazy decorator function
|
||||
* @param $cache Reference to cache object to decorate
|
||||
*/
|
||||
public function decorate(&$cache) {
|
||||
$decorator = $this->copy();
|
||||
// reference is necessary for mocks in PHP 4
|
||||
$decorator->cache =& $cache;
|
||||
$decorator->type = $cache->type;
|
||||
return $decorator;
|
||||
}
|
||||
|
||||
/**
|
||||
* Cross-compatible clone substitute
|
||||
*/
|
||||
public function copy() {
|
||||
return new HTMLPurifier_DefinitionCache_Decorator();
|
||||
}
|
||||
|
||||
public function add($def, $config) {
|
||||
return $this->cache->add($def, $config);
|
||||
}
|
||||
|
||||
public function set($def, $config) {
|
||||
return $this->cache->set($def, $config);
|
||||
}
|
||||
|
||||
public function replace($def, $config) {
|
||||
return $this->cache->replace($def, $config);
|
||||
}
|
||||
|
||||
public function get($config) {
|
||||
return $this->cache->get($config);
|
||||
}
|
||||
|
||||
public function remove($config) {
|
||||
return $this->cache->remove($config);
|
||||
}
|
||||
|
||||
public function flush($config) {
|
||||
return $this->cache->flush($config);
|
||||
}
|
||||
|
||||
public function cleanup($config) {
|
||||
return $this->cache->cleanup($config);
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
// vim: et sw=4 sts=4
|
||||
|
|
@ -1,43 +0,0 @@
|
|||
<?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
|
||||
{
|
||||
|
||||
public $name = 'Cleanup';
|
||||
|
||||
public function copy() {
|
||||
return new HTMLPurifier_DefinitionCache_Decorator_Cleanup();
|
||||
}
|
||||
|
||||
public function add($def, $config) {
|
||||
$status = parent::add($def, $config);
|
||||
if (!$status) parent::cleanup($config);
|
||||
return $status;
|
||||
}
|
||||
|
||||
public function set($def, $config) {
|
||||
$status = parent::set($def, $config);
|
||||
if (!$status) parent::cleanup($config);
|
||||
return $status;
|
||||
}
|
||||
|
||||
public function replace($def, $config) {
|
||||
$status = parent::replace($def, $config);
|
||||
if (!$status) parent::cleanup($config);
|
||||
return $status;
|
||||
}
|
||||
|
||||
public function get($config) {
|
||||
$ret = parent::get($config);
|
||||
if (!$ret) parent::cleanup($config);
|
||||
return $ret;
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
// vim: et sw=4 sts=4
|
||||
|
|
@ -1,46 +0,0 @@
|
|||
<?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
|
||||
{
|
||||
|
||||
protected $definitions;
|
||||
public $name = 'Memory';
|
||||
|
||||
public function copy() {
|
||||
return new HTMLPurifier_DefinitionCache_Decorator_Memory();
|
||||
}
|
||||
|
||||
public function add($def, $config) {
|
||||
$status = parent::add($def, $config);
|
||||
if ($status) $this->definitions[$this->generateKey($config)] = $def;
|
||||
return $status;
|
||||
}
|
||||
|
||||
public function set($def, $config) {
|
||||
$status = parent::set($def, $config);
|
||||
if ($status) $this->definitions[$this->generateKey($config)] = $def;
|
||||
return $status;
|
||||
}
|
||||
|
||||
public function replace($def, $config) {
|
||||
$status = parent::replace($def, $config);
|
||||
if ($status) $this->definitions[$this->generateKey($config)] = $def;
|
||||
return $status;
|
||||
}
|
||||
|
||||
public function get($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
|
||||
|
|
@ -1,47 +0,0 @@
|
|||
<?php
|
||||
|
||||
require_once 'HTMLPurifier/DefinitionCache/Decorator.php';
|
||||
|
||||
/**
|
||||
* Definition cache decorator template.
|
||||
*/
|
||||
class HTMLPurifier_DefinitionCache_Decorator_Template extends
|
||||
HTMLPurifier_DefinitionCache_Decorator
|
||||
{
|
||||
|
||||
var $name = 'Template'; // replace this
|
||||
|
||||
function copy() {
|
||||
// replace class name with yours
|
||||
return new HTMLPurifier_DefinitionCache_Decorator_Template();
|
||||
}
|
||||
|
||||
// remove methods you don't need
|
||||
|
||||
function add($def, $config) {
|
||||
return parent::add($def, $config);
|
||||
}
|
||||
|
||||
function set($def, $config) {
|
||||
return parent::set($def, $config);
|
||||
}
|
||||
|
||||
function replace($def, $config) {
|
||||
return parent::replace($def, $config);
|
||||
}
|
||||
|
||||
function get($config) {
|
||||
return parent::get($config);
|
||||
}
|
||||
|
||||
function flush() {
|
||||
return parent::flush();
|
||||
}
|
||||
|
||||
function cleanup($config) {
|
||||
return parent::cleanup($config);
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
// vim: et sw=4 sts=4
|
||||
|
|
@ -1,39 +0,0 @@
|
|||
<?php
|
||||
|
||||
/**
|
||||
* Null cache object to use when no caching is on.
|
||||
*/
|
||||
class HTMLPurifier_DefinitionCache_Null extends HTMLPurifier_DefinitionCache
|
||||
{
|
||||
|
||||
public function add($def, $config) {
|
||||
return false;
|
||||
}
|
||||
|
||||
public function set($def, $config) {
|
||||
return false;
|
||||
}
|
||||
|
||||
public function replace($def, $config) {
|
||||
return false;
|
||||
}
|
||||
|
||||
public function remove($config) {
|
||||
return false;
|
||||
}
|
||||
|
||||
public function get($config) {
|
||||
return false;
|
||||
}
|
||||
|
||||
public function flush($config) {
|
||||
return false;
|
||||
}
|
||||
|
||||
public function cleanup($config) {
|
||||
return false;
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
// vim: et sw=4 sts=4
|
||||
|
|
@ -1,172 +0,0 @@
|
|||
<?php
|
||||
|
||||
class HTMLPurifier_DefinitionCache_Serializer extends
|
||||
HTMLPurifier_DefinitionCache
|
||||
{
|
||||
|
||||
public function add($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($def));
|
||||
}
|
||||
|
||||
public function set($def, $config) {
|
||||
if (!$this->checkDefType($def)) return;
|
||||
$file = $this->generateFilePath($config);
|
||||
if (!$this->_prepareDir($config)) return false;
|
||||
return $this->_write($file, serialize($def));
|
||||
}
|
||||
|
||||
public function replace($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($def));
|
||||
}
|
||||
|
||||
public function get($config) {
|
||||
$file = $this->generateFilePath($config);
|
||||
if (!file_exists($file)) return false;
|
||||
return unserialize(file_get_contents($file));
|
||||
}
|
||||
|
||||
public function remove($config) {
|
||||
$file = $this->generateFilePath($config);
|
||||
if (!file_exists($file)) return false;
|
||||
return unlink($file);
|
||||
}
|
||||
|
||||
public function flush($config) {
|
||||
if (!$this->_prepareDir($config)) return false;
|
||||
$dir = $this->generateDirectoryPath($config);
|
||||
$dh = opendir($dir);
|
||||
while (false !== ($filename = readdir($dh))) {
|
||||
if (empty($filename)) continue;
|
||||
if ($filename[0] === '.') continue;
|
||||
unlink($dir . '/' . $filename);
|
||||
}
|
||||
}
|
||||
|
||||
public function cleanup($config) {
|
||||
if (!$this->_prepareDir($config)) return false;
|
||||
$dir = $this->generateDirectoryPath($config);
|
||||
$dh = opendir($dir);
|
||||
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 . '/' . $filename);
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Generates the file path to the serial file corresponding to
|
||||
* the configuration and definition name
|
||||
* @todo Make protected
|
||||
*/
|
||||
public function generateFilePath($config) {
|
||||
$key = $this->generateKey($config);
|
||||
return $this->generateDirectoryPath($config) . '/' . $key . '.ser';
|
||||
}
|
||||
|
||||
/**
|
||||
* Generates the path to the directory contain this cache's serial files
|
||||
* @note No trailing slash
|
||||
* @todo Make protected
|
||||
*/
|
||||
public function generateDirectoryPath($config) {
|
||||
$base = $this->generateBaseDirectoryPath($config);
|
||||
return $base . '/' . $this->type;
|
||||
}
|
||||
|
||||
/**
|
||||
* Generates path to base directory that contains all definition type
|
||||
* serials
|
||||
* @todo Make protected
|
||||
*/
|
||||
public function generateBaseDirectoryPath($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 $file File name to write to
|
||||
* @param $data Data to write into file
|
||||
* @return Number of bytes written if success, or false if failure.
|
||||
*/
|
||||
private function _write($file, $data) {
|
||||
return file_put_contents($file, $data);
|
||||
}
|
||||
|
||||
/**
|
||||
* Prepares the directory that this type stores the serials in
|
||||
* @return True if successful
|
||||
*/
|
||||
private function _prepareDir($config) {
|
||||
$directory = $this->generateDirectoryPath($config);
|
||||
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)) {
|
||||
return false;
|
||||
}
|
||||
$old = umask(0022); // disable group and world writes
|
||||
mkdir($directory);
|
||||
umask($old);
|
||||
} elseif (!$this->_testPermissions($directory)) {
|
||||
return false;
|
||||
}
|
||||
return true;
|
||||
}
|
||||
|
||||
/**
|
||||
* Tests permissions on a directory and throws out friendly
|
||||
* error messages and attempts to chmod it itself if possible
|
||||
*/
|
||||
private function _testPermissions($dir) {
|
||||
// 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 '.$dir.' does not exist',
|
||||
E_USER_WARNING);
|
||||
return false;
|
||||
}
|
||||
if (function_exists('posix_getuid')) {
|
||||
// POSIX system, we can give more specific advice
|
||||
if (fileowner($dir) === posix_getuid()) {
|
||||
// we can chmod it ourselves
|
||||
chmod($dir, 0755);
|
||||
return true;
|
||||
} elseif (filegroup($dir) === posix_getgid()) {
|
||||
$chmod = '775';
|
||||
} else {
|
||||
// PHP's probably running as nobody, so we'll
|
||||
// need to give global permissions
|
||||
$chmod = '777';
|
||||
}
|
||||
trigger_error('Directory '.$dir.' not writable, '.
|
||||
'please chmod to ' . $chmod,
|
||||
E_USER_WARNING);
|
||||
} else {
|
||||
// generic error message
|
||||
trigger_error('Directory '.$dir.' not writable, '.
|
||||
'please alter file permissions',
|
||||
E_USER_WARNING);
|
||||
}
|
||||
return false;
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
// vim: et sw=4 sts=4
|
||||
File diff suppressed because one or more lines are too long
|
|
@ -1,135 +0,0 @@
|
|||
<?php
|
||||
|
||||
/**
|
||||
* 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
|
||||
{
|
||||
|
||||
public $name = 'ExtractStyleBlocks';
|
||||
private $_styleMatches = array();
|
||||
private $_tidy;
|
||||
|
||||
public function __construct() {
|
||||
$this->_tidy = new csstidy();
|
||||
}
|
||||
|
||||
/**
|
||||
* Save the contents of CSS blocks to style matches
|
||||
* @param $matches preg_replace style $matches array
|
||||
*/
|
||||
protected function styleCallback($matches) {
|
||||
$this->_styleMatches[] = $matches[1];
|
||||
}
|
||||
|
||||
/**
|
||||
* Removes inline <style> tags from HTML, saves them for later use
|
||||
* @todo Extend to indicate non-text/css style blocks
|
||||
*/
|
||||
public function preFilter($html, $config, $context) {
|
||||
$tidy = $config->get('Filter.ExtractStyleBlocks.TidyImpl');
|
||||
if ($tidy !== null) $this->_tidy = $tidy;
|
||||
$html = preg_replace_callback('#<style(?:\s.*)?>(.+)</style>#isU', array($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 $css CSS styling to clean
|
||||
* @param $config Instance of HTMLPurifier_Config
|
||||
* @param $context Instance of HTMLPurifier_Context
|
||||
* @return Cleaned CSS
|
||||
*/
|
||||
public function cleanCSS($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);
|
||||
$this->_tidy->parse($css);
|
||||
$css_definition = $config->getDefinition('CSS');
|
||||
foreach ($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 ($selector === '') continue; // should not happen
|
||||
if ($selector[0] === '+') {
|
||||
if ($selector !== '' && $selector[0] === '+') continue;
|
||||
}
|
||||
if (!empty($scopes)) {
|
||||
$new_selector = array(); // because multiple ones are possible
|
||||
$selectors = array_map('trim', explode(',', $selector));
|
||||
foreach ($scopes as $s1) {
|
||||
foreach ($selectors as $s2) {
|
||||
$new_selector[] = "$s1 $s2";
|
||||
}
|
||||
}
|
||||
$selector = implode(', ', $new_selector); // now it's a string
|
||||
}
|
||||
foreach ($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;
|
||||
}
|
||||
$this->_tidy->css[$k] = $new_decls;
|
||||
}
|
||||
// remove stuff that shouldn't be used, could be reenabled
|
||||
// after security risks are analyzed
|
||||
$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
|
||||
|
|
@ -1,39 +0,0 @@
|
|||
<?php
|
||||
|
||||
class HTMLPurifier_Filter_YouTube extends HTMLPurifier_Filter
|
||||
{
|
||||
|
||||
public $name = 'YouTube';
|
||||
|
||||
public function preFilter($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, $html);
|
||||
}
|
||||
|
||||
public function postFilter($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'), $html);
|
||||
}
|
||||
|
||||
protected function armorUrl($url) {
|
||||
return str_replace('--', '--', $url);
|
||||
}
|
||||
|
||||
protected function postFilterCallback($matches) {
|
||||
$url = $this->armorUrl($matches[1]);
|
||||
return '<object width="425" height="350" type="application/x-shockwave-flash" '.
|
||||
'data="http://www.youtube.com/'.$url.'">'.
|
||||
'<param name="movie" value="http://www.youtube.com/'.$url.'"></param>'.
|
||||
'<!--[if IE]>'.
|
||||
'<embed src="http://www.youtube.com/'.$url.'"'.
|
||||
'type="application/x-shockwave-flash"'.
|
||||
'wmode="transparent" width="425" height="350" />'.
|
||||
'<![endif]-->'.
|
||||
'</object>';
|
||||
|
||||
}
|
||||
}
|
||||
|
||||
// vim: et sw=4 sts=4
|
||||
|
|
@ -1,118 +0,0 @@
|
|||
<?php
|
||||
|
||||
/**
|
||||
* XHTML 1.1 Forms module, defines all form-related elements found in HTML 4.
|
||||
*/
|
||||
class HTMLPurifier_HTMLModule_Forms extends HTMLPurifier_HTMLModule
|
||||
{
|
||||
public $name = 'Forms';
|
||||
public $safe = false;
|
||||
|
||||
public $content_sets = array(
|
||||
'Block' => 'Form',
|
||||
'Inline' => 'Formctrl',
|
||||
);
|
||||
|
||||
public function setup($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#embeds',
|
||||
'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
|
||||
);
|
||||
|
||||
// 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
|
||||
|
|
@ -1,21 +0,0 @@
|
|||
<?php
|
||||
|
||||
class HTMLPurifier_HTMLModule_Tidy_Strict extends HTMLPurifier_HTMLModule_Tidy_XHTMLAndHTML4
|
||||
{
|
||||
public $name = 'Tidy_Strict';
|
||||
public $defaultLevel = 'light';
|
||||
|
||||
public function makeFixes() {
|
||||
$r = parent::makeFixes();
|
||||
$r['blockquote#content_model_type'] = 'strictblockquote';
|
||||
return $r;
|
||||
}
|
||||
|
||||
public $defines_child_def = true;
|
||||
public function getChildDef($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
|
||||
|
|
@ -1,51 +0,0 @@
|
|||
<?php
|
||||
|
||||
class HTMLPurifier_Injector_RemoveEmpty extends HTMLPurifier_Injector
|
||||
{
|
||||
|
||||
private $context, $config, $attrValidator, $removeNbsp, $removeNbspExceptions;
|
||||
|
||||
public function prepare($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');
|
||||
$this->attrValidator = new HTMLPurifier_AttrValidator();
|
||||
}
|
||||
|
||||
public function handleElement(&$token) {
|
||||
if (!$token instanceof HTMLPurifier_Token_Start) return;
|
||||
$next = false;
|
||||
for ($i = $this->inputIndex + 1, $c = count($this->inputTokens); $i < $c; $i++) {
|
||||
$next = $this->inputTokens[$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 == $token->name)) {
|
||||
if ($token->name == 'colgroup') return;
|
||||
$this->attrValidator->validateToken($token, $this->config, $this->context);
|
||||
$token->armor['ValidateAttributes'] = true;
|
||||
if (isset($token->attr['id']) || isset($token->attr['name'])) return;
|
||||
$token = $i - $this->inputIndex + 1;
|
||||
for ($b = $this->inputIndex - 1; $b > 0; $b--) {
|
||||
$prev = $this->inputTokens[$b];
|
||||
if ($prev instanceof HTMLPurifier_Token_Text && $prev->is_whitespace) continue;
|
||||
break;
|
||||
}
|
||||
// This is safe because we removed the token that triggered this.
|
||||
$this->rewind($b - 1);
|
||||
return;
|
||||
}
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
// vim: et sw=4 sts=4
|
||||
|
|
@ -1,63 +0,0 @@
|
|||
<?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
|
||||
|
|
@ -1,139 +0,0 @@
|
|||
<?php
|
||||
|
||||
/**
|
||||
* Proof-of-concept lexer that uses the PEAR package XML_HTMLSax3 to parse HTML.
|
||||
*
|
||||
* PEAR, not suprisingly, also has a SAX parser for HTML. I don't know
|
||||
* very much about implementation, but it's fairly well written. However, that
|
||||
* abstraction comes at a price: performance. You need to have it installed,
|
||||
* and if the API changes, it might break our adapter. Not sure whether or not
|
||||
* it's UTF-8 aware, but it has some entity parsing trouble (in all areas,
|
||||
* text and attributes).
|
||||
*
|
||||
* Quite personally, I don't recommend using the PEAR class, and the defaults
|
||||
* don't use it. The unit tests do perform the tests on the SAX parser too, but
|
||||
* whatever it does for poorly formed HTML is up to it.
|
||||
*
|
||||
* @todo Generalize so that XML_HTMLSax is also supported.
|
||||
*
|
||||
* @warning Entity-resolution inside attributes is broken.
|
||||
*/
|
||||
|
||||
class HTMLPurifier_Lexer_PEARSax3 extends HTMLPurifier_Lexer
|
||||
{
|
||||
|
||||
/**
|
||||
* Internal accumulator array for SAX parsers.
|
||||
*/
|
||||
protected $tokens = array();
|
||||
protected $last_token_was_empty;
|
||||
|
||||
private $parent_handler;
|
||||
private $stack = array();
|
||||
|
||||
public function tokenizeHTML($string, $config, $context) {
|
||||
|
||||
$this->tokens = array();
|
||||
$this->last_token_was_empty = false;
|
||||
|
||||
$string = $this->normalize($string, $config, $context);
|
||||
|
||||
$this->parent_handler = set_error_handler(array($this, 'muteStrictErrorHandler'));
|
||||
|
||||
$parser = new XML_HTMLSax3();
|
||||
$parser->set_object($this);
|
||||
$parser->set_element_handler('openHandler','closeHandler');
|
||||
$parser->set_data_handler('dataHandler');
|
||||
$parser->set_escape_handler('escapeHandler');
|
||||
|
||||
// doesn't seem to work correctly for attributes
|
||||
$parser->set_option('XML_OPTION_ENTITIES_PARSED', 1);
|
||||
|
||||
$parser->parse($string);
|
||||
|
||||
restore_error_handler();
|
||||
|
||||
return $this->tokens;
|
||||
|
||||
}
|
||||
|
||||
/**
|
||||
* Open tag event handler, interface is defined by PEAR package.
|
||||
*/
|
||||
public function openHandler(&$parser, $name, $attrs, $closed) {
|
||||
// entities are not resolved in attrs
|
||||
foreach ($attrs as $key => $attr) {
|
||||
$attrs[$key] = $this->parseData($attr);
|
||||
}
|
||||
if ($closed) {
|
||||
$this->tokens[] = new HTMLPurifier_Token_Empty($name, $attrs);
|
||||
$this->last_token_was_empty = true;
|
||||
} else {
|
||||
$this->tokens[] = new HTMLPurifier_Token_Start($name, $attrs);
|
||||
}
|
||||
$this->stack[] = $name;
|
||||
return true;
|
||||
}
|
||||
|
||||
/**
|
||||
* Close tag event handler, interface is defined by PEAR package.
|
||||
*/
|
||||
public function closeHandler(&$parser, $name) {
|
||||
// HTMLSax3 seems to always send empty tags an extra close tag
|
||||
// check and ignore if you see it:
|
||||
// [TESTME] to make sure it doesn't overreach
|
||||
if ($this->last_token_was_empty) {
|
||||
$this->last_token_was_empty = false;
|
||||
return true;
|
||||
}
|
||||
$this->tokens[] = new HTMLPurifier_Token_End($name);
|
||||
if (!empty($this->stack)) array_pop($this->stack);
|
||||
return true;
|
||||
}
|
||||
|
||||
/**
|
||||
* Data event handler, interface is defined by PEAR package.
|
||||
*/
|
||||
public function dataHandler(&$parser, $data) {
|
||||
$this->last_token_was_empty = false;
|
||||
$this->tokens[] = new HTMLPurifier_Token_Text($data);
|
||||
return true;
|
||||
}
|
||||
|
||||
/**
|
||||
* Escaped text handler, interface is defined by PEAR package.
|
||||
*/
|
||||
public function escapeHandler(&$parser, $data) {
|
||||
if (strpos($data, '--') === 0) {
|
||||
// remove trailing and leading double-dashes
|
||||
$data = substr($data, 2);
|
||||
if (strlen($data) >= 2 && substr($data, -2) == "--") {
|
||||
$data = substr($data, 0, -2);
|
||||
}
|
||||
if (isset($this->stack[sizeof($this->stack) - 1]) &&
|
||||
$this->stack[sizeof($this->stack) - 1] == "style") {
|
||||
$this->tokens[] = new HTMLPurifier_Token_Text($data);
|
||||
} else {
|
||||
$this->tokens[] = new HTMLPurifier_Token_Comment($data);
|
||||
}
|
||||
$this->last_token_was_empty = false;
|
||||
}
|
||||
// CDATA is handled elsewhere, but if it was handled here:
|
||||
//if (strpos($data, '[CDATA[') === 0) {
|
||||
// $this->tokens[] = new HTMLPurifier_Token_Text(
|
||||
// substr($data, 7, strlen($data) - 9) );
|
||||
//}
|
||||
return true;
|
||||
}
|
||||
|
||||
/**
|
||||
* An error handler that mutes strict errors
|
||||
*/
|
||||
public function muteStrictErrorHandler($errno, $errstr, $errfile=null, $errline=null, $errcontext=null) {
|
||||
if ($errno == E_STRICT) return;
|
||||
return call_user_func($this->parent_handler, $errno, $errstr, $errfile, $errline, $errcontext);
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
// vim: et sw=4 sts=4
|
||||
|
|
@ -1,3906 +0,0 @@
|
|||
<?php
|
||||
|
||||
/**
|
||||
* Experimental HTML5-based parser using Jeroen van der Meer's PH5P library.
|
||||
* Occupies space in the HTML5 pseudo-namespace, which may cause conflicts.
|
||||
*
|
||||
* @note
|
||||
* Recent changes to PHP's DOM extension have resulted in some fatal
|
||||
* error conditions with the original version of PH5P. Pending changes,
|
||||
* this lexer will punt to DirectLex if DOM throughs an exception.
|
||||
*/
|
||||
|
||||
class HTMLPurifier_Lexer_PH5P extends HTMLPurifier_Lexer_DOMLex {
|
||||
|
||||
public function tokenizeHTML($html, $config, $context) {
|
||||
$new_html = $this->normalize($html, $config, $context);
|
||||
$new_html = $this->wrapHTML($new_html, $config, $context);
|
||||
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>
|
||||
getElementsByTagName('div')->item(0) // <div>
|
||||
, $tokens);
|
||||
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) {
|
||||
$data = str_replace("\r\n", "\n", $data);
|
||||
$data = 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(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 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, $this->entities)) {
|
||||
if ($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 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, 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 $this->dom;
|
||||
}
|
||||
}
|
||||
?>
|
||||
|
|
@ -1,328 +0,0 @@
|
|||
<?php
|
||||
|
||||
/**
|
||||
* Takes a well formed list of tokens and fixes their nesting.
|
||||
*
|
||||
* HTML elements dictate which elements are allowed to be their children,
|
||||
* for example, you can't have a p tag in a span tag. Other elements have
|
||||
* much more rigorous definitions: tables, for instance, require a specific
|
||||
* order for their elements. There are also constraints not expressible by
|
||||
* document type definitions, such as the chameleon nature of ins/del
|
||||
* tags and global child exclusions.
|
||||
*
|
||||
* The first major objective of this strategy is to iterate through all the
|
||||
* nodes (not tokens) of the list of tokens and determine whether or not
|
||||
* their children conform to the element's definition. If they do not, the
|
||||
* child definition may optionally supply an amended list of elements that
|
||||
* is valid or require that the entire node be deleted (and the previous
|
||||
* node rescanned).
|
||||
*
|
||||
* The second objective is to ensure that explicitly excluded elements of
|
||||
* an element do not appear in its children. Code that accomplishes this
|
||||
* task is pervasive through the strategy, though the two are distinct tasks
|
||||
* and could, theoretically, be seperated (although it's not recommended).
|
||||
*
|
||||
* @note Whether or not unrecognized children are silently dropped or
|
||||
* translated into text depends on the child definitions.
|
||||
*
|
||||
* @todo Enable nodes to be bubbled out of the structure.
|
||||
*/
|
||||
|
||||
class HTMLPurifier_Strategy_FixNesting extends HTMLPurifier_Strategy
|
||||
{
|
||||
|
||||
public function execute($tokens, $config, $context) {
|
||||
//####################################################################//
|
||||
// Pre-processing
|
||||
|
||||
// get a copy of the HTML definition
|
||||
$definition = $config->getHTMLDefinition();
|
||||
|
||||
// insert implicit "parent" node, will be removed at end.
|
||||
// DEFINITION CALL
|
||||
$parent_name = $definition->info_parent;
|
||||
array_unshift($tokens, new HTMLPurifier_Token_Start($parent_name));
|
||||
$tokens[] = new HTMLPurifier_Token_End($parent_name);
|
||||
|
||||
// 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 the indexes of all parents,
|
||||
// $stack[count($stack)-1] being the current parent
|
||||
$stack = array();
|
||||
|
||||
// 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();
|
||||
|
||||
// variable that contains the start token while we are processing
|
||||
// nodes. This enables error reporting to do its job
|
||||
$start_token = false;
|
||||
$context->register('CurrentToken', $start_token);
|
||||
|
||||
//####################################################################//
|
||||
// Loop
|
||||
|
||||
// iterate through all start nodes. Determining the start node
|
||||
// is complicated so it has been omitted from the loop construct
|
||||
for ($i = 0, $size = count($tokens) ; $i < $size; ) {
|
||||
|
||||
//################################################################//
|
||||
// Gather information on children
|
||||
|
||||
// child token accumulator
|
||||
$child_tokens = array();
|
||||
|
||||
// scroll to the end of this node, report number, and collect
|
||||
// all children
|
||||
for ($j = $i, $depth = 0; ; $j++) {
|
||||
if ($tokens[$j] instanceof HTMLPurifier_Token_Start) {
|
||||
$depth++;
|
||||
// skip token assignment on first iteration, this is the
|
||||
// token we currently are on
|
||||
if ($depth == 1) continue;
|
||||
} elseif ($tokens[$j] instanceof HTMLPurifier_Token_End) {
|
||||
$depth--;
|
||||
// skip token assignment on last iteration, this is the
|
||||
// end token of the token we're currently on
|
||||
if ($depth == 0) break;
|
||||
}
|
||||
$child_tokens[] = $tokens[$j];
|
||||
}
|
||||
|
||||
// $i is index of start token
|
||||
// $j is index of end token
|
||||
|
||||
$start_token = $tokens[$i]; // to make token available via CurrentToken
|
||||
|
||||
//################################################################//
|
||||
// Gather information on parent
|
||||
|
||||
// calculate parent information
|
||||
if ($count = count($stack)) {
|
||||
$parent_index = $stack[$count-1];
|
||||
$parent_name = $tokens[$parent_index]->name;
|
||||
if ($parent_index == 0) {
|
||||
$parent_def = $definition->info_parent_def;
|
||||
} else {
|
||||
$parent_def = $definition->info[$parent_name];
|
||||
}
|
||||
} else {
|
||||
// processing as if the parent were the "root" node
|
||||
// unknown info, it won't be used anyway, in the future,
|
||||
// we may want to enforce one element only (this is
|
||||
// necessary for HTML Purifier to clean entire documents
|
||||
$parent_index = $parent_name = $parent_def = null;
|
||||
}
|
||||
|
||||
// calculate context
|
||||
if ($is_inline === false) {
|
||||
// check if conditions make it inline
|
||||
if (!empty($parent_def) && $parent_def->descendants_are_inline) {
|
||||
$is_inline = $count - 1;
|
||||
}
|
||||
} else {
|
||||
// check if we're out of inline
|
||||
if ($count === $is_inline) {
|
||||
$is_inline = false;
|
||||
}
|
||||
}
|
||||
|
||||
//################################################################//
|
||||
// Determine whether element is explicitly excluded SGML-style
|
||||
|
||||
// determine whether or not element is excluded by checking all
|
||||
// parent exclusions. The array should not be very large, two
|
||||
// elements at most.
|
||||
$excluded = false;
|
||||
if (!empty($exclude_stack)) {
|
||||
foreach ($exclude_stack as $lookup) {
|
||||
if (isset($lookup[$tokens[$i]->name])) {
|
||||
$excluded = true;
|
||||
// no need to continue processing
|
||||
break;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
//################################################################//
|
||||
// Perform child validation
|
||||
|
||||
if ($excluded) {
|
||||
// there is an exclusion, remove the entire node
|
||||
$result = false;
|
||||
$excludes = array(); // not used, but good to initialize anyway
|
||||
} else {
|
||||
// DEFINITION CALL
|
||||
if ($i === 0) {
|
||||
// special processing for the first node
|
||||
$def = $definition->info_parent_def;
|
||||
} else {
|
||||
$def = $definition->info[$tokens[$i]->name];
|
||||
|
||||
}
|
||||
|
||||
if (!empty($def->child)) {
|
||||
// have DTD child def validate children
|
||||
$result = $def->child->validateChildren(
|
||||
$child_tokens, $config, $context);
|
||||
} else {
|
||||
// weird, no child definition, get rid of everything
|
||||
$result = false;
|
||||
}
|
||||
|
||||
// determine whether or not this element has any exclusions
|
||||
$excludes = $def->excludes;
|
||||
}
|
||||
|
||||
// $result is now a bool or array
|
||||
|
||||
//################################################################//
|
||||
// Process result by interpreting $result
|
||||
|
||||
if ($result === true || $child_tokens === $result) {
|
||||
// leave the node as is
|
||||
|
||||
// register start token as a parental node start
|
||||
$stack[] = $i;
|
||||
|
||||
// register exclusions if there are any
|
||||
if (!empty($excludes)) $exclude_stack[] = $excludes;
|
||||
|
||||
// move cursor to next possible start node
|
||||
$i++;
|
||||
|
||||
} elseif($result === false) {
|
||||
// remove entire node
|
||||
|
||||
if ($e) {
|
||||
if ($excluded) {
|
||||
$e->send(E_ERROR, 'Strategy_FixNesting: Node excluded');
|
||||
} else {
|
||||
$e->send(E_ERROR, 'Strategy_FixNesting: Node removed');
|
||||
}
|
||||
}
|
||||
|
||||
// calculate length of inner tokens and current tokens
|
||||
$length = $j - $i + 1;
|
||||
|
||||
// perform removal
|
||||
array_splice($tokens, $i, $length);
|
||||
|
||||
// update size
|
||||
$size -= $length;
|
||||
|
||||
// there is no start token to register,
|
||||
// current node is now the next possible start node
|
||||
// unless it turns out that we need to do a double-check
|
||||
|
||||
// this is a rought heuristic that covers 100% of HTML's
|
||||
// cases and 99% of all other cases. A child definition
|
||||
// that would be tricked by this would be something like:
|
||||
// ( | a b c) where it's all or nothing. Fortunately,
|
||||
// our current implementation claims that that case would
|
||||
// not allow empty, even if it did
|
||||
if (!$parent_def->child->allow_empty) {
|
||||
// we need to do a double-check
|
||||
$i = $parent_index;
|
||||
array_pop($stack);
|
||||
}
|
||||
|
||||
// PROJECTED OPTIMIZATION: Process all children elements before
|
||||
// reprocessing parent node.
|
||||
|
||||
} else {
|
||||
// replace node with $result
|
||||
|
||||
// calculate length of inner tokens
|
||||
$length = $j - $i - 1;
|
||||
|
||||
if ($e) {
|
||||
if (empty($result) && $length) {
|
||||
$e->send(E_ERROR, 'Strategy_FixNesting: Node contents removed');
|
||||
} else {
|
||||
$e->send(E_WARNING, 'Strategy_FixNesting: Node reorganized');
|
||||
}
|
||||
}
|
||||
|
||||
// perform replacement
|
||||
array_splice($tokens, $i + 1, $length, $result);
|
||||
|
||||
// update size
|
||||
$size -= $length;
|
||||
$size += count($result);
|
||||
|
||||
// register start token as a parental node start
|
||||
$stack[] = $i;
|
||||
|
||||
// register exclusions if there are any
|
||||
if (!empty($excludes)) $exclude_stack[] = $excludes;
|
||||
|
||||
// move cursor to next possible start node
|
||||
$i++;
|
||||
|
||||
}
|
||||
|
||||
//################################################################//
|
||||
// Scroll to next start node
|
||||
|
||||
// We assume, at this point, that $i is the index of the token
|
||||
// that is the first possible new start point for a node.
|
||||
|
||||
// Test if the token indeed is a start tag, if not, move forward
|
||||
// and test again.
|
||||
$size = count($tokens);
|
||||
while ($i < $size and !$tokens[$i] instanceof HTMLPurifier_Token_Start) {
|
||||
if ($tokens[$i] instanceof HTMLPurifier_Token_End) {
|
||||
// pop a token index off the stack if we ended a node
|
||||
array_pop($stack);
|
||||
// pop an exclusion lookup off exclusion stack if
|
||||
// we ended node and that node had exclusions
|
||||
if ($i == 0 || $i == $size - 1) {
|
||||
// use specialized var if it's the super-parent
|
||||
$s_excludes = $definition->info_parent_def->excludes;
|
||||
} else {
|
||||
$s_excludes = $definition->info[$tokens[$i]->name]->excludes;
|
||||
}
|
||||
if ($s_excludes) {
|
||||
array_pop($exclude_stack);
|
||||
}
|
||||
}
|
||||
$i++;
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
//####################################################################//
|
||||
// Post-processing
|
||||
|
||||
// remove implicit parent tokens at the beginning and end
|
||||
array_shift($tokens);
|
||||
array_pop($tokens);
|
||||
|
||||
// remove context variables
|
||||
$context->destroy('IsInline');
|
||||
$context->destroy('CurrentToken');
|
||||
|
||||
//####################################################################//
|
||||
// Return
|
||||
|
||||
return $tokens;
|
||||
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
// vim: et sw=4 sts=4
|
||||
|
|
@ -1,57 +0,0 @@
|
|||
<?php
|
||||
|
||||
/**
|
||||
* Abstract base token class that all others inherit from.
|
||||
*/
|
||||
class HTMLPurifier_Token {
|
||||
public $line; /**< Line number node was on in source document. Null if unknown. */
|
||||
public $col; /**< Column of line node was on in source document. Null if unknown. */
|
||||
|
||||
/**
|
||||
* Lookup array of processing that this token is exempt from.
|
||||
* Currently, valid values are "ValidateAttributes" and
|
||||
* "MakeWellFormed_TagClosedError"
|
||||
*/
|
||||
public $armor = array();
|
||||
|
||||
/**
|
||||
* Used during MakeWellFormed.
|
||||
*/
|
||||
public $skip;
|
||||
public $rewind;
|
||||
public $carryover;
|
||||
|
||||
public function __get($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.
|
||||
*/
|
||||
public function position($l = null, $c = null) {
|
||||
$this->line = $l;
|
||||
$this->col = $c;
|
||||
}
|
||||
|
||||
/**
|
||||
* Convenience function for DirectLex settings line/col position.
|
||||
*/
|
||||
public function rawPosition($l, $c) {
|
||||
if ($c === -1) $l++;
|
||||
$this->line = $l;
|
||||
$this->col = $c;
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
// vim: et sw=4 sts=4
|
||||
|
|
@ -1,22 +0,0 @@
|
|||
<?php
|
||||
|
||||
/**
|
||||
* Concrete comment token class. Generally will be ignored.
|
||||
*/
|
||||
class HTMLPurifier_Token_Comment extends HTMLPurifier_Token
|
||||
{
|
||||
public $data; /**< Character data within comment. */
|
||||
public $is_whitespace = true;
|
||||
/**
|
||||
* Transparent constructor.
|
||||
*
|
||||
* @param $data String comment data.
|
||||
*/
|
||||
public function __construct($data, $line = null, $col = null) {
|
||||
$this->data = $data;
|
||||
$this->line = $line;
|
||||
$this->col = $col;
|
||||
}
|
||||
}
|
||||
|
||||
// vim: et sw=4 sts=4
|
||||
|
|
@ -1,94 +0,0 @@
|
|||
<?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
|
||||
{
|
||||
|
||||
/**
|
||||
* Prototypes that will be cloned.
|
||||
* @private
|
||||
*/
|
||||
// p stands for prototype
|
||||
private $p_start, $p_end, $p_empty, $p_text, $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 $name Tag name
|
||||
* @param $attr Associative array of attributes
|
||||
* @return Generated HTMLPurifier_Token_Start
|
||||
*/
|
||||
public function createStart($name, $attr = array()) {
|
||||
$p = clone $this->p_start;
|
||||
$p->__construct($name, $attr);
|
||||
return $p;
|
||||
}
|
||||
|
||||
/**
|
||||
* Creates a HTMLPurifier_Token_End.
|
||||
* @param $name Tag name
|
||||
* @return Generated HTMLPurifier_Token_End
|
||||
*/
|
||||
public function createEnd($name) {
|
||||
$p = clone $this->p_end;
|
||||
$p->__construct($name);
|
||||
return $p;
|
||||
}
|
||||
|
||||
/**
|
||||
* Creates a HTMLPurifier_Token_Empty.
|
||||
* @param $name Tag name
|
||||
* @param $attr Associative array of attributes
|
||||
* @return Generated HTMLPurifier_Token_Empty
|
||||
*/
|
||||
public function createEmpty($name, $attr = array()) {
|
||||
$p = clone $this->p_empty;
|
||||
$p->__construct($name, $attr);
|
||||
return $p;
|
||||
}
|
||||
|
||||
/**
|
||||
* Creates a HTMLPurifier_Token_Text.
|
||||
* @param $data Data of text token
|
||||
* @return Generated HTMLPurifier_Token_Text
|
||||
*/
|
||||
public function createText($data) {
|
||||
$p = clone $this->p_text;
|
||||
$p->__construct($data);
|
||||
return $p;
|
||||
}
|
||||
|
||||
/**
|
||||
* Creates a HTMLPurifier_Token_Comment.
|
||||
* @param $data Data of comment token
|
||||
* @return Generated HTMLPurifier_Token_Comment
|
||||
*/
|
||||
public function createComment($data) {
|
||||
$p = clone $this->p_comment;
|
||||
$p->__construct($data);
|
||||
return $p;
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
// vim: et sw=4 sts=4
|
||||
|
|
@ -1,173 +0,0 @@
|
|||
<?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
|
||||
{
|
||||
|
||||
public $scheme, $userinfo, $host, $port, $path, $query, $fragment;
|
||||
|
||||
/**
|
||||
* @note Automatically normalizes scheme and port
|
||||
*/
|
||||
public function __construct($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 $config Instance of HTMLPurifier_Config
|
||||
* @param $context Instance of HTMLPurifier_Context
|
||||
* @return Scheme object appropriate for validating this URI
|
||||
*/
|
||||
public function getSchemeObj($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 = $registry->getScheme($def->defaultScheme, $config, $context);
|
||||
if (!$scheme_obj) {
|
||||
// something funky happened to the default scheme object
|
||||
trigger_error(
|
||||
'Default scheme object "' . $def->defaultScheme . '" was not readable',
|
||||
E_USER_WARNING
|
||||
);
|
||||
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 $config Instance of HTMLPurifier_Config
|
||||
* @param $context Instance of HTMLPurifier_Context
|
||||
* @return True if validation/filtering succeeds, false if failure
|
||||
*/
|
||||
public function validate($config, $context) {
|
||||
|
||||
// ABNF definitions from RFC 3986
|
||||
$chars_sub_delims = '!$&\'()*+,;=';
|
||||
$chars_gen_delims = ':/?#[]@';
|
||||
$chars_pchar = $chars_sub_delims . ':@';
|
||||
|
||||
// validate scheme (MUST BE FIRST!)
|
||||
if (!is_null($this->scheme) && is_null($this->host)) {
|
||||
$def = $config->getDefinition('URI');
|
||||
if ($def->defaultScheme === $this->scheme) {
|
||||
$this->scheme = null;
|
||||
}
|
||||
}
|
||||
|
||||
// validate host
|
||||
if (!is_null($this->host)) {
|
||||
$host_def = new HTMLPurifier_AttrDef_URI_Host();
|
||||
$this->host = $host_def->validate($this->host, $config, $context);
|
||||
if ($this->host === false) $this->host = null;
|
||||
}
|
||||
|
||||
// validate username
|
||||
if (!is_null($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
|
||||
$path_parts = array();
|
||||
$segments_encoder = new HTMLPurifier_PercentEncoder($chars_pchar . '/');
|
||||
if (!is_null($this->host)) {
|
||||
// path-abempty (hier and relative)
|
||||
$this->path = $segments_encoder->encode($this->path);
|
||||
} elseif ($this->path !== '' && $this->path[0] === '/') {
|
||||
// path-absolute (hier and relative)
|
||||
if (strlen($this->path) >= 2 && $this->path[1] === '/') {
|
||||
// This shouldn't ever happen!
|
||||
$this->path = '';
|
||||
} else {
|
||||
$this->path = $segments_encoder->encode($this->path);
|
||||
}
|
||||
} elseif (!is_null($this->scheme) && $this->path !== '') {
|
||||
// path-rootless (hier)
|
||||
// Short circuit evaluation means we don't need to check nz
|
||||
$this->path = $segments_encoder->encode($this->path);
|
||||
} elseif (is_null($this->scheme) && $this->path !== '') {
|
||||
// path-noscheme (relative)
|
||||
// (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
|
||||
$authority = null;
|
||||
if (!is_null($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
|
||||
$result = '';
|
||||
if (!is_null($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;
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
// vim: et sw=4 sts=4
|
||||
|
|
@ -1,45 +0,0 @@
|
|||
<?php
|
||||
|
||||
/**
|
||||
* Chainable filters for custom URI processing.
|
||||
*
|
||||
* These filters can perform custom actions on a URI filter object,
|
||||
* including transformation or blacklisting.
|
||||
*
|
||||
* @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
|
||||
*/
|
||||
public $name;
|
||||
|
||||
/**
|
||||
* True if this filter should be run after scheme validation.
|
||||
*/
|
||||
public $post = false;
|
||||
|
||||
/**
|
||||
* Performs initialization for the filter
|
||||
*/
|
||||
public function prepare($config) {return true;}
|
||||
|
||||
/**
|
||||
* Filter a URI object
|
||||
* @param $uri Reference to URI object variable
|
||||
* @param $config Instance of HTMLPurifier_Config
|
||||
* @param $context Instance of HTMLPurifier_Context
|
||||
* @return bool Whether or not to continue processing: false indicates
|
||||
* URL is no good, true indicates continue processing. Note that
|
||||
* all changes are committed directly on the URI object
|
||||
*/
|
||||
abstract public function filter(&$uri, $config, $context);
|
||||
|
||||
}
|
||||
|
||||
// vim: et sw=4 sts=4
|
||||
|
|
@ -1,23 +0,0 @@
|
|||
<?php
|
||||
|
||||
class HTMLPurifier_URIFilter_DisableExternal extends HTMLPurifier_URIFilter
|
||||
{
|
||||
public $name = 'DisableExternal';
|
||||
protected $ourHostParts = false;
|
||||
public function prepare($config) {
|
||||
$our_host = $config->getDefinition('URI')->host;
|
||||
if ($our_host !== null) $this->ourHostParts = array_reverse(explode('.', $our_host));
|
||||
}
|
||||
public function filter(&$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
|
||||
|
|
@ -1,12 +0,0 @@
|
|||
<?php
|
||||
|
||||
class HTMLPurifier_URIFilter_DisableExternalResources extends HTMLPurifier_URIFilter_DisableExternal
|
||||
{
|
||||
public $name = 'DisableExternalResources';
|
||||
public function filter(&$uri, $config, $context) {
|
||||
if (!$context->get('EmbeddedURI', true)) return true;
|
||||
return parent::filter($uri, $config, $context);
|
||||
}
|
||||
}
|
||||
|
||||
// vim: et sw=4 sts=4
|
||||
|
|
@ -1,21 +0,0 @@
|
|||
<?php
|
||||
|
||||
class HTMLPurifier_URIFilter_HostBlacklist extends HTMLPurifier_URIFilter
|
||||
{
|
||||
public $name = 'HostBlacklist';
|
||||
protected $blacklist = array();
|
||||
public function prepare($config) {
|
||||
$this->blacklist = $config->get('URI.HostBlacklist');
|
||||
return true;
|
||||
}
|
||||
public function filter(&$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
|
||||
|
|
@ -1,58 +0,0 @@
|
|||
<?php
|
||||
|
||||
class HTMLPurifier_URIFilter_Munge extends HTMLPurifier_URIFilter
|
||||
{
|
||||
public $name = 'Munge';
|
||||
public $post = true;
|
||||
private $target, $parser, $doEmbed, $secretKey;
|
||||
|
||||
protected $replace = array();
|
||||
|
||||
public function prepare($config) {
|
||||
$this->target = $config->get('URI.' . $this->name);
|
||||
$this->parser = new HTMLPurifier_URIParser();
|
||||
$this->doEmbed = $config->get('URI.MungeResources');
|
||||
$this->secretKey = $config->get('URI.MungeSecretKey');
|
||||
return true;
|
||||
}
|
||||
public function filter(&$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 (is_null($uri->host) || empty($scheme_obj->browsable)) {
|
||||
return true;
|
||||
}
|
||||
// don't redirect if target host is our host
|
||||
if ($uri->host === $config->getDefinition('URI')->host) {
|
||||
return true;
|
||||
}
|
||||
|
||||
$this->makeReplace($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 = $new_uri; // overwrite
|
||||
return true;
|
||||
}
|
||||
|
||||
protected function makeReplace($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) $this->replace['%t'] = sha1($this->secretKey . ':' . $string);
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
// vim: et sw=4 sts=4
|
||||
|
|
@ -1,42 +0,0 @@
|
|||
<?php
|
||||
|
||||
/**
|
||||
* Validator for the components of a URI for a specific scheme
|
||||
*/
|
||||
class HTMLPurifier_URIScheme
|
||||
{
|
||||
|
||||
/**
|
||||
* Scheme's default port (integer)
|
||||
*/
|
||||
public $default_port = null;
|
||||
|
||||
/**
|
||||
* Whether or not URIs of this schem are locatable by a browser
|
||||
* http and ftp are accessible, while mailto and news are not.
|
||||
*/
|
||||
public $browsable = false;
|
||||
|
||||
/**
|
||||
* Whether or not the URI always uses <hier_part>, resolves edge cases
|
||||
* with making relative URIs absolute
|
||||
*/
|
||||
public $hierarchical = false;
|
||||
|
||||
/**
|
||||
* Validates the components of a URI
|
||||
* @note This implementation should be called by children if they define
|
||||
* a default port, as it does port processing.
|
||||
* @param $uri Instance of HTMLPurifier_URI
|
||||
* @param $config HTMLPurifier_Config object
|
||||
* @param $context HTMLPurifier_Context object
|
||||
* @return Bool success or failure
|
||||
*/
|
||||
public function validate(&$uri, $config, $context) {
|
||||
if ($this->default_port == $uri->port) $uri->port = null;
|
||||
return true;
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
// vim: et sw=4 sts=4
|
||||
|
|
@ -1,22 +0,0 @@
|
|||
<?php
|
||||
|
||||
/**
|
||||
* Validates news (Usenet) as defined by generic RFC 1738
|
||||
*/
|
||||
class HTMLPurifier_URIScheme_news extends HTMLPurifier_URIScheme {
|
||||
|
||||
public $browsable = false;
|
||||
|
||||
public function validate(&$uri, $config, $context) {
|
||||
parent::validate($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
|
||||
|
|
@ -1,20 +0,0 @@
|
|||
<?php
|
||||
|
||||
/**
|
||||
* Validates nntp (Network News Transfer Protocol) as defined by generic RFC 1738
|
||||
*/
|
||||
class HTMLPurifier_URIScheme_nntp extends HTMLPurifier_URIScheme {
|
||||
|
||||
public $default_port = 119;
|
||||
public $browsable = false;
|
||||
|
||||
public function validate(&$uri, $config, $context) {
|
||||
parent::validate($uri, $config, $context);
|
||||
$uri->userinfo = null;
|
||||
$uri->query = null;
|
||||
return true;
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
// vim: et sw=4 sts=4
|
||||
|
|
@ -1,154 +0,0 @@
|
|||
<?php
|
||||
|
||||
/**
|
||||
* Parses string representations into their corresponding native PHP
|
||||
* variable type. The base implementation does a simple type-check.
|
||||
*/
|
||||
class HTMLPurifier_VarParser
|
||||
{
|
||||
|
||||
const STRING = 1;
|
||||
const ISTRING = 2;
|
||||
const TEXT = 3;
|
||||
const ITEXT = 4;
|
||||
const INT = 5;
|
||||
const FLOAT = 6;
|
||||
const BOOL = 7;
|
||||
const LOOKUP = 8;
|
||||
const ALIST = 9;
|
||||
const HASH = 10;
|
||||
const MIXED = 11;
|
||||
|
||||
/**
|
||||
* Lookup table of allowed types. Mainly for backwards compatibility, but
|
||||
* also convenient for transforming string type names to the integer constants.
|
||||
*/
|
||||
static public $types = array(
|
||||
'string' => self::STRING,
|
||||
'istring' => self::ISTRING,
|
||||
'text' => self::TEXT,
|
||||
'itext' => self::ITEXT,
|
||||
'int' => self::INT,
|
||||
'float' => self::FLOAT,
|
||||
'bool' => self::BOOL,
|
||||
'lookup' => self::LOOKUP,
|
||||
'list' => self::ALIST,
|
||||
'hash' => self::HASH,
|
||||
'mixed' => self::MIXED
|
||||
);
|
||||
|
||||
/**
|
||||
* Lookup table of types that are string, and can have aliases or
|
||||
* allowed value lists.
|
||||
*/
|
||||
static public $stringTypes = array(
|
||||
self::STRING => true,
|
||||
self::ISTRING => true,
|
||||
self::TEXT => true,
|
||||
self::ITEXT => true,
|
||||
);
|
||||
|
||||
/**
|
||||
* Validate a variable according to type. Throws
|
||||
* HTMLPurifier_VarParserException if invalid.
|
||||
* It may return NULL as a valid type if $allow_null is true.
|
||||
*
|
||||
* @param $var Variable to validate
|
||||
* @param $type Type of variable, see HTMLPurifier_VarParser->types
|
||||
* @param $allow_null Whether or not to permit null as a value
|
||||
* @return Validated and type-coerced variable
|
||||
*/
|
||||
final public function parse($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::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 $var;
|
||||
case (self::INT):
|
||||
if (!is_int($var)) break;
|
||||
return $var;
|
||||
case (self::FLOAT):
|
||||
if (!is_float($var)) break;
|
||||
return $var;
|
||||
case (self::BOOL):
|
||||
if (!is_bool($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::MIXED):
|
||||
return $var;
|
||||
default:
|
||||
$this->errorInconsistent(get_class($this), $type);
|
||||
}
|
||||
$this->errorGeneric($var, $type);
|
||||
}
|
||||
|
||||
/**
|
||||
* Actually implements the parsing. Base implementation is to not
|
||||
* do anything to $var. Subclasses should overload this!
|
||||
*/
|
||||
protected function parseImplementation($var, $type, $allow_null) {
|
||||
return $var;
|
||||
}
|
||||
|
||||
/**
|
||||
* Throws an exception.
|
||||
*/
|
||||
protected function error($msg) {
|
||||
throw new HTMLPurifier_VarParserException($msg);
|
||||
}
|
||||
|
||||
/**
|
||||
* Throws an inconsistency exception.
|
||||
* @note This should not ever be called. It would be called if we
|
||||
* extend the allowed values of HTMLPurifier_VarParser without
|
||||
* updating subclasses.
|
||||
*/
|
||||
protected function errorInconsistent($class, $type) {
|
||||
throw new HTMLPurifier_Exception("Inconsistency in $class: ".HTMLPurifier_VarParser::getTypeName($type)." not implemented");
|
||||
}
|
||||
|
||||
/**
|
||||
* Generic error for if a type didn't work.
|
||||
*/
|
||||
protected function errorGeneric($var, $type) {
|
||||
$vtype = gettype($var);
|
||||
$this->error("Expected type ".HTMLPurifier_VarParser::getTypeName($type).", got $vtype");
|
||||
}
|
||||
|
||||
static public function getTypeName($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
|
||||
9
library/ezyang/htmlpurifier/CREDITS
Normal file
9
library/ezyang/htmlpurifier/CREDITS
Normal file
|
|
@ -0,0 +1,9 @@
|
|||
|
||||
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
|
||||
374
library/ezyang/htmlpurifier/INSTALL
Normal file
374
library/ezyang/htmlpurifier/INSTALL
Normal file
|
|
@ -0,0 +1,374 @@
|
|||
|
||||
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 only, and is actively tested from PHP 5.0.5 and
|
||||
up. It has no core dependencies with other libraries. PHP
|
||||
4 support was deprecated on December 31, 2007 with HTML Purifier 3.0.0.
|
||||
HTML Purifier is not compatible with zend.ze1_compatibility_mode.
|
||||
|
||||
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
|
||||
* Net_IDNA2 (PEAR) : IRI support using %Core.EnableIDNA
|
||||
|
||||
---------------------------------------------------------------------------
|
||||
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:
|
||||
|
||||
PHP VERSION IS LESS THAN 5.1.2, AND YOU'VE DEFINED __autoload
|
||||
Because spl_autoload_register() doesn't exist in early versions
|
||||
of PHP 5, HTML Purifier has no way of adding itself to the autoload
|
||||
stack. Modify your __autoload function to test
|
||||
HTMLPurifier_Bootstrap::autoload($class)
|
||||
|
||||
For example, suppose your autoload function looks like this:
|
||||
|
||||
function __autoload($class) {
|
||||
require str_replace('_', '/', $class) . '.php';
|
||||
return true;
|
||||
}
|
||||
|
||||
A modified version with HTML Purifier would look like this:
|
||||
|
||||
function __autoload($class) {
|
||||
if (HTMLPurifier_Bootstrap::autoload($class)) return true;
|
||||
require str_replace('_', '/', $class) . '.php';
|
||||
return true;
|
||||
}
|
||||
|
||||
Note that there *is* some custom behavior in our autoloader; the
|
||||
original autoloader in our example would work for 99% of the time,
|
||||
but would fail when including language files.
|
||||
|
||||
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')
|
||||
|
||||
Users should also be on guard if they use a version of PHP previous
|
||||
to 5.1.2 without an autoloader--HTML Purifier will define __autoload()
|
||||
for you, which can collide with an autoloader that was added by *you*
|
||||
later.
|
||||
|
||||
|
||||
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--in fact, you must modify your own
|
||||
autoload handler if you are using a version of PHP earlier than PHP 5.1.2
|
||||
(See "Autoload compatibility" above).
|
||||
|
||||
|
||||
---------------------------------------------------------------------------
|
||||
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 all. This may be necessary if your webserver runs as nobody, but is
|
||||
not recommended since it means any other user can write files in the
|
||||
directory. Use:
|
||||
|
||||
chmod -R 0777 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
|
||||
60
library/ezyang/htmlpurifier/INSTALL.fr.utf8
Normal file
60
library/ezyang/htmlpurifier/INSTALL.fr.utf8
Normal file
|
|
@ -0,0 +1,60 @@
|
|||
|
||||
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 5.0.5 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
|
||||
504
library/ezyang/htmlpurifier/LICENSE
Normal file
504
library/ezyang/htmlpurifier/LICENSE
Normal file
|
|
@ -0,0 +1,504 @@
|
|||
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
|
||||
1094
library/ezyang/htmlpurifier/NEWS
Normal file
1094
library/ezyang/htmlpurifier/NEWS
Normal file
|
|
@ -0,0 +1,1094 @@
|
|||
NEWS ( CHANGELOG and HISTORY ) HTMLPurifier
|
||||
|||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
|
||||
|
||||
= KEY ====================
|
||||
# Breaks back-compat
|
||||
! Feature
|
||||
- Bugfix
|
||||
+ Sub-comment
|
||||
. Internal change
|
||||
==========================
|
||||
|
||||
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
|
||||
24
library/ezyang/htmlpurifier/README
Normal file
24
library/ezyang/htmlpurifier/README
Normal file
|
|
@ -0,0 +1,24 @@
|
|||
|
||||
README
|
||||
All about HTML Purifier
|
||||
|
||||
HTML Purifier is an HTML filtering solution that uses a unique combination
|
||||
of robust whitelists and agressive 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/
|
||||
|
||||
vim: et sw=4 sts=4
|
||||
150
library/ezyang/htmlpurifier/TODO
Normal file
150
library/ezyang/htmlpurifier/TODO
Normal file
|
|
@ -0,0 +1,150 @@
|
|||
|
||||
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
|
||||
---------------
|
||||
|
||||
4.8 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
|
||||
1
library/ezyang/htmlpurifier/VERSION
Normal file
1
library/ezyang/htmlpurifier/VERSION
Normal file
|
|
@ -0,0 +1 @@
|
|||
4.7.0
|
||||
4
library/ezyang/htmlpurifier/WHATSNEW
Normal file
4
library/ezyang/htmlpurifier/WHATSNEW
Normal file
|
|
@ -0,0 +1,4 @@
|
|||
HTML Purifier 4.7.0 is a bugfix release, collecting two years
|
||||
worth of accumulated bug fixes. Highlighted bugfixes are updated
|
||||
YouTube filter code, corrected rgb() CSS parsing, and one new
|
||||
configuration option, %AutoFormat.RemoveEmpty.Predicate.
|
||||
20
library/ezyang/htmlpurifier/WYSIWYG
Normal file
20
library/ezyang/htmlpurifier/WYSIWYG
Normal file
|
|
@ -0,0 +1,20 @@
|
|||
|
||||
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
|
||||
22
library/ezyang/htmlpurifier/composer.json
Normal file
22
library/ezyang/htmlpurifier/composer.json
Normal file
|
|
@ -0,0 +1,22 @@
|
|||
{
|
||||
"name": "ezyang/htmlpurifier",
|
||||
"description": "Standards compliant HTML filter written in PHP",
|
||||
"type": "library",
|
||||
"keywords": ["html"],
|
||||
"homepage": "http://htmlpurifier.org/",
|
||||
"license": "LGPL",
|
||||
"authors": [
|
||||
{
|
||||
"name": "Edward Z. Yang",
|
||||
"email": "admin@htmlpurifier.org",
|
||||
"homepage": "http://ezyang.com"
|
||||
}
|
||||
],
|
||||
"require": {
|
||||
"php": ">=5.2"
|
||||
},
|
||||
"autoload": {
|
||||
"psr-0": { "HTMLPurifier": "library/" },
|
||||
"files": ["library/HTMLPurifier.composer.php"]
|
||||
}
|
||||
}
|
||||
|
|
@ -0,0 +1,91 @@
|
|||
<?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
|
||||
164
library/ezyang/htmlpurifier/extras/FSTools.php
Normal file
164
library/ezyang/htmlpurifier/extras/FSTools.php
Normal file
|
|
@ -0,0 +1,164 @@
|
|||
<?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
|
||||
141
library/ezyang/htmlpurifier/extras/FSTools/File.php
Normal file
141
library/ezyang/htmlpurifier/extras/FSTools/File.php
Normal file
|
|
@ -0,0 +1,141 @@
|
|||
<?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) $this->close();
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
// vim: et sw=4 sts=4
|
||||
|
|
@ -0,0 +1,11 @@
|
|||
<?php
|
||||
|
||||
/**
|
||||
* This is a stub include that automatically configures the include path.
|
||||
*/
|
||||
|
||||
set_include_path(dirname(__FILE__) . PATH_SEPARATOR . get_include_path() );
|
||||
require_once 'HTMLPurifierExtras.php';
|
||||
require_once 'HTMLPurifierExtras.autoload.php';
|
||||
|
||||
// vim: et sw=4 sts=4
|
||||
|
|
@ -0,0 +1,26 @@
|
|||
<?php
|
||||
|
||||
/**
|
||||
* @file
|
||||
* Convenience file that registers autoload handler for HTML Purifier.
|
||||
*
|
||||
* @warning
|
||||
* This autoloader does not contain the compatibility code seen in
|
||||
* HTMLPurifier_Bootstrap; the user is expected to make any necessary
|
||||
* changes to use this library.
|
||||
*/
|
||||
|
||||
if (function_exists('spl_autoload_register')) {
|
||||
spl_autoload_register(array('HTMLPurifierExtras', 'autoload'));
|
||||
if (function_exists('__autoload')) {
|
||||
// Be polite and ensure that userland autoload gets retained
|
||||
spl_autoload_register('__autoload');
|
||||
}
|
||||
} elseif (!function_exists('__autoload')) {
|
||||
function __autoload($class)
|
||||
{
|
||||
return HTMLPurifierExtras::autoload($class);
|
||||
}
|
||||
}
|
||||
|
||||
// vim: et sw=4 sts=4
|
||||
31
library/ezyang/htmlpurifier/extras/HTMLPurifierExtras.php
Normal file
31
library/ezyang/htmlpurifier/extras/HTMLPurifierExtras.php
Normal file
|
|
@ -0,0 +1,31 @@
|
|||
<?php
|
||||
|
||||
/**
|
||||
* Meta-class for HTML Purifier's extra class hierarchies, similar to
|
||||
* HTMLPurifier_Bootstrap.
|
||||
*/
|
||||
class HTMLPurifierExtras
|
||||
{
|
||||
|
||||
public static function autoload($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
|
||||
32
library/ezyang/htmlpurifier/extras/README
Normal file
32
library/ezyang/htmlpurifier/extras/README
Normal file
|
|
@ -0,0 +1,32 @@
|
|||
|
||||
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 $FS->fopen(...).
|
||||
This makes it a lot simpler to mock these filesystem calls for unit testing.
|
||||
|
||||
- FSTools_File: This object represents a single file, and has almost any
|
||||
method imaginable one would need.
|
||||
|
||||
Check the files themselves for more information.
|
||||
|
||||
vim: et sw=4 sts=4
|
||||
|
|
@ -3,6 +3,7 @@
|
|||
/**
|
||||
* @file
|
||||
* Convenience file that registers autoload handler for HTML Purifier.
|
||||
* It also does some sanity checks.
|
||||
*/
|
||||
|
||||
if (function_exists('spl_autoload_register') && function_exists('spl_autoload_unregister')) {
|
||||
|
|
@ -13,9 +14,14 @@ if (function_exists('spl_autoload_register') && function_exists('spl_autoload_un
|
|||
spl_autoload_register('__autoload');
|
||||
}
|
||||
} elseif (!function_exists('__autoload')) {
|
||||
function __autoload($class) {
|
||||
function __autoload($class)
|
||||
{
|
||||
return HTMLPurifier_Bootstrap::autoload($class);
|
||||
}
|
||||
}
|
||||
|
||||
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
|
||||
|
|
@ -0,0 +1,4 @@
|
|||
<?php
|
||||
if (!defined('HTMLPURIFIER_PREFIX')) {
|
||||
define('HTMLPURIFIER_PREFIX', dirname(__FILE__));
|
||||
}
|
||||
|
|
@ -8,11 +8,13 @@
|
|||
|
||||
/**
|
||||
* Purify HTML.
|
||||
* @param $html String HTML to purify
|
||||
* @param $config Configuration to use, can be any value accepted by
|
||||
* @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, $config = null) {
|
||||
function HTMLPurifier($html, $config = null)
|
||||
{
|
||||
static $purifier = false;
|
||||
if (!$purifier) {
|
||||
$purifier = new HTMLPurifier();
|
||||
|
|
@ -7,7 +7,7 @@
|
|||
* 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 4.1.1
|
||||
* @version 4.7.0
|
||||
*
|
||||
* @warning
|
||||
* You must *not* include any other HTML Purifier files before this file,
|
||||
|
|
@ -19,6 +19,7 @@
|
|||
*/
|
||||
|
||||
require 'HTMLPurifier.php';
|
||||
require 'HTMLPurifier/Arborize.php';
|
||||
require 'HTMLPurifier/AttrCollections.php';
|
||||
require 'HTMLPurifier/AttrDef.php';
|
||||
require 'HTMLPurifier/AttrTransform.php';
|
||||
|
|
@ -54,9 +55,11 @@ 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';
|
||||
|
|
@ -72,7 +75,9 @@ 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';
|
||||
|
|
@ -90,6 +95,7 @@ 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';
|
||||
|
|
@ -125,14 +131,17 @@ 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/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';
|
||||
|
|
@ -147,10 +156,12 @@ 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';
|
||||
|
|
@ -158,10 +169,12 @@ 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/Text.php';
|
||||
require 'HTMLPurifier/HTMLModule/Tidy.php';
|
||||
require 'HTMLPurifier/HTMLModule/XMLCommonAttributes.php';
|
||||
|
|
@ -180,6 +193,9 @@ 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';
|
||||
|
|
@ -196,10 +212,13 @@ 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';
|
||||
|
|
@ -7,7 +7,8 @@
|
|||
|
||||
require_once dirname(__FILE__) . '/HTMLPurifier.auto.php';
|
||||
|
||||
function kses($string, $allowed_html, $allowed_protocols = null) {
|
||||
function kses($string, $allowed_html, $allowed_protocols = null)
|
||||
{
|
||||
$config = HTMLPurifier_Config::createDefault();
|
||||
$allowed_elements = array();
|
||||
$allowed_attributes = array();
|
||||
|
|
@ -19,7 +20,6 @@ function kses($string, $allowed_html, $allowed_protocols = null) {
|
|||
}
|
||||
$config->set('HTML.AllowedElements', $allowed_elements);
|
||||
$config->set('HTML.AllowedAttributes', $allowed_attributes);
|
||||
$allowed_schemes = array();
|
||||
if ($allowed_protocols !== null) {
|
||||
$config->set('URI.AllowedSchemes', $allowed_protocols);
|
||||
}
|
||||
|
|
@ -19,7 +19,7 @@
|
|||
*/
|
||||
|
||||
/*
|
||||
HTML Purifier 4.1.1 - Standards Compliant HTML Filtering
|
||||
HTML Purifier 4.7.0 - Standards Compliant HTML Filtering
|
||||
Copyright (C) 2006-2008 Edward Z. Yang
|
||||
|
||||
This library is free software; you can redistribute it and/or
|
||||
|
|
@ -54,66 +54,97 @@
|
|||
class HTMLPurifier
|
||||
{
|
||||
|
||||
/** Version of HTML Purifier */
|
||||
public $version = '4.1.1';
|
||||
|
||||
/** Constant with version of HTML Purifier */
|
||||
const VERSION = '4.1.1';
|
||||
|
||||
/** Global configuration object */
|
||||
public $config;
|
||||
|
||||
/** Array of extra HTMLPurifier_Filter objects to run on HTML, for backwards compatibility */
|
||||
private $filters = array();
|
||||
|
||||
/** Single instance of HTML Purifier */
|
||||
private static $instance;
|
||||
|
||||
protected $strategy, $generator;
|
||||
/**
|
||||
* Version of HTML Purifier.
|
||||
* @type string
|
||||
*/
|
||||
public $version = '4.7.0';
|
||||
|
||||
/**
|
||||
* Resultant HTMLPurifier_Context of last run purification. Is an array
|
||||
* of contexts if the last called method was purifyArray().
|
||||
* Constant with version of HTML Purifier.
|
||||
*/
|
||||
const VERSION = '4.7.0';
|
||||
|
||||
/**
|
||||
* 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 $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).
|
||||
*
|
||||
* @param HTMLPurifier_Config $config Optional HTMLPurifier_Config object
|
||||
* for all instances of the purifier, if omitted, a default
|
||||
* configuration is supplied (which can be overridden on a
|
||||
* per-use basis).
|
||||
* The parameter can also be any type that
|
||||
* HTMLPurifier_Config::create() supports.
|
||||
*/
|
||||
public function __construct($config = null) {
|
||||
|
||||
public function __construct($config = null)
|
||||
{
|
||||
$this->config = HTMLPurifier_Config::create($config);
|
||||
|
||||
$this->strategy = new HTMLPurifier_Strategy_Core();
|
||||
|
||||
$this->strategy = new HTMLPurifier_Strategy_Core();
|
||||
}
|
||||
|
||||
/**
|
||||
* Adds a filter to process the output. First come first serve
|
||||
* @param $filter HTMLPurifier_Filter object
|
||||
*
|
||||
* @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);
|
||||
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 $html String of HTML to purify
|
||||
* @param $config HTMLPurifier_Config object for this operation, if omitted,
|
||||
* defaults to the config object specified during this
|
||||
* @param string $html String of HTML to purify
|
||||
* @param HTMLPurifier_Config $config Config object for this operation,
|
||||
* if omitted, defaults to the config object specified during this
|
||||
* object's construction. The parameter can also be any type
|
||||
* that HTMLPurifier_Config::create() supports.
|
||||
* @return Purified HTML
|
||||
*
|
||||
* @return string Purified HTML
|
||||
*/
|
||||
public function purify($html, $config = null) {
|
||||
|
||||
public function purify($html, $config = null)
|
||||
{
|
||||
// :TODO: make the config merge in, instead of replace
|
||||
$config = $config ? HTMLPurifier_Config::create($config) : $this->config;
|
||||
|
||||
|
|
@ -151,8 +182,12 @@ class HTMLPurifier
|
|||
unset($filter_flags['Custom']);
|
||||
$filters = array();
|
||||
foreach ($filter_flags as $filter => $flag) {
|
||||
if (!$flag) continue;
|
||||
if (strpos($filter, '.') !== false) continue;
|
||||
if (!$flag) {
|
||||
continue;
|
||||
}
|
||||
if (strpos($filter, '.') !== false) {
|
||||
continue;
|
||||
}
|
||||
$class = "HTMLPurifier_Filter_$filter";
|
||||
$filters[] = new $class;
|
||||
}
|
||||
|
|
@ -175,9 +210,12 @@ class HTMLPurifier
|
|||
// list of un-purified tokens
|
||||
$lexer->tokenizeHTML(
|
||||
// un-purified HTML
|
||||
$html, $config, $context
|
||||
$html,
|
||||
$config,
|
||||
$context
|
||||
),
|
||||
$config, $context
|
||||
$config,
|
||||
$context
|
||||
)
|
||||
);
|
||||
|
||||
|
|
@ -192,11 +230,15 @@ class HTMLPurifier
|
|||
|
||||
/**
|
||||
* Filters an array of HTML snippets
|
||||
* @param $config Optional HTMLPurifier_Config object for this operation.
|
||||
*
|
||||
* @param string[] $array_of_html Array of html snippets
|
||||
* @param HTMLPurifier_Config $config Optional config object for this operation.
|
||||
* See HTMLPurifier::purify() for more details.
|
||||
* @return Array of purified HTML
|
||||
*
|
||||
* @return string[] Array of purified HTML
|
||||
*/
|
||||
public function purifyArray($array_of_html, $config = null) {
|
||||
public function purifyArray($array_of_html, $config = null)
|
||||
{
|
||||
$context_array = array();
|
||||
foreach ($array_of_html as $key => $html) {
|
||||
$array_of_html[$key] = $this->purify($html, $config);
|
||||
|
|
@ -208,11 +250,16 @@ class HTMLPurifier
|
|||
|
||||
/**
|
||||
* Singleton for enforcing just one HTML Purifier in your system
|
||||
* @param $prototype Optional prototype HTMLPurifier instance to
|
||||
* overload singleton with, or HTMLPurifier_Config
|
||||
* instance to configure the generated version with.
|
||||
*
|
||||
* @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) {
|
||||
public static function instance($prototype = null)
|
||||
{
|
||||
if (!self::$instance || $prototype) {
|
||||
if ($prototype instanceof HTMLPurifier) {
|
||||
self::$instance = $prototype;
|
||||
|
|
@ -226,12 +273,20 @@ class HTMLPurifier
|
|||
}
|
||||
|
||||
/**
|
||||
* 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) {
|
||||
public static function getInstance($prototype = null)
|
||||
{
|
||||
return HTMLPurifier::instance($prototype);
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
// vim: et sw=4 sts=4
|
||||
|
|
@ -13,6 +13,7 @@
|
|||
$__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';
|
||||
|
|
@ -48,9 +49,11 @@ 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';
|
||||
|
|
@ -66,7 +69,9 @@ 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';
|
||||
|
|
@ -84,6 +89,7 @@ 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';
|
||||
|
|
@ -119,14 +125,17 @@ 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/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';
|
||||
|
|
@ -141,10 +150,12 @@ 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';
|
||||
|
|
@ -152,10 +163,12 @@ 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/Text.php';
|
||||
require_once $__dir . '/HTMLPurifier/HTMLModule/Tidy.php';
|
||||
require_once $__dir . '/HTMLPurifier/HTMLModule/XMLCommonAttributes.php';
|
||||
|
|
@ -174,6 +187,9 @@ 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';
|
||||
|
|
@ -190,10 +206,13 @@ 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 $__dir . '/HTMLPurifier/URIScheme/https.php';
|
||||
|
|
@ -0,0 +1,71 @@
|
|||
<?php
|
||||
|
||||
/**
|
||||
* Converts a stream of HTMLPurifier_Token into an HTMLPurifier_Node,
|
||||
* and back again.
|
||||
*
|
||||
* @note This transformation is not an equivalence. We mutate the input
|
||||
* token stream to make it so; see all [MUT] markers in code.
|
||||
*/
|
||||
class HTMLPurifier_Arborize
|
||||
{
|
||||
public static function arborize($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;
|
||||
}
|
||||
}
|
||||
|
|
@ -8,7 +8,8 @@ class HTMLPurifier_AttrCollections
|
|||
{
|
||||
|
||||
/**
|
||||
* Associative array of attribute collections, indexed by name
|
||||
* Associative array of attribute collections, indexed by name.
|
||||
* @type array
|
||||
*/
|
||||
public $info = array();
|
||||
|
||||
|
|
@ -16,10 +17,11 @@ class HTMLPurifier_AttrCollections
|
|||
* Performs all expansions on internal data for use by other inclusions
|
||||
* It also collects all attribute collection extensions from
|
||||
* modules
|
||||
* @param $attr_types HTMLPurifier_AttrTypes instance
|
||||
* @param $modules Hash array of HTMLPurifier_HTMLModule members
|
||||
* @param HTMLPurifier_AttrTypes $attr_types HTMLPurifier_AttrTypes instance
|
||||
* @param HTMLPurifier_HTMLModule[] $modules Hash array of HTMLPurifier_HTMLModule members
|
||||
*/
|
||||
public function __construct($attr_types, $modules) {
|
||||
public function __construct($attr_types, $modules)
|
||||
{
|
||||
// load extensions from the modules
|
||||
foreach ($modules as $module) {
|
||||
foreach ($module->attr_collections as $coll_i => $coll) {
|
||||
|
|
@ -30,7 +32,9 @@ class HTMLPurifier_AttrCollections
|
|||
if ($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);
|
||||
$this->info[$coll_i][$attr_i],
|
||||
$attr
|
||||
);
|
||||
continue;
|
||||
}
|
||||
$this->info[$coll_i][$attr_i] = $attr;
|
||||
|
|
@ -49,20 +53,29 @@ class HTMLPurifier_AttrCollections
|
|||
/**
|
||||
* Takes a reference to an attribute associative array and performs
|
||||
* all inclusions specified by the zero index.
|
||||
* @param &$attr Reference to attribute array
|
||||
* @param array &$attr Reference to attribute array
|
||||
*/
|
||||
public function performInclusions(&$attr) {
|
||||
if (!isset($attr[0])) return;
|
||||
public function performInclusions(&$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;
|
||||
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;
|
||||
if (!isset($this->info[$merge[$i]])) {
|
||||
continue;
|
||||
}
|
||||
foreach ($this->info[$merge[$i]] as $key => $value) {
|
||||
if (isset($attr[$key])) continue; // also catches more inclusions
|
||||
if (isset($attr[$key])) {
|
||||
continue;
|
||||
} // also catches more inclusions
|
||||
$attr[$key] = $value;
|
||||
}
|
||||
if (isset($this->info[$merge[$i]][0])) {
|
||||
|
|
@ -76,20 +89,24 @@ class HTMLPurifier_AttrCollections
|
|||
/**
|
||||
* Expands all string identifiers in an attribute array by replacing
|
||||
* them with the appropriate values inside HTMLPurifier_AttrTypes
|
||||
* @param &$attr Reference to attribute array
|
||||
* @param $attr_types HTMLPurifier_AttrTypes instance
|
||||
* @param array &$attr Reference to attribute array
|
||||
* @param HTMLPurifier_AttrTypes $attr_types HTMLPurifier_AttrTypes instance
|
||||
*/
|
||||
public function expandIdentifiers(&$attr, $attr_types) {
|
||||
|
||||
public function expandIdentifiers(&$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 ($def_i === 0) {
|
||||
continue;
|
||||
}
|
||||
|
||||
if (isset($processed[$def_i])) continue;
|
||||
if (isset($processed[$def_i])) {
|
||||
continue;
|
||||
}
|
||||
|
||||
// determine whether or not attribute is required
|
||||
if ($required = (strpos($def_i, '*') !== false)) {
|
||||
|
|
@ -120,9 +137,7 @@ class HTMLPurifier_AttrCollections
|
|||
unset($attr[$def_i]);
|
||||
}
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
// vim: et sw=4 sts=4
|
||||
|
|
@ -14,23 +14,25 @@ abstract class HTMLPurifier_AttrDef
|
|||
{
|
||||
|
||||
/**
|
||||
* Tells us whether or not an HTML attribute is minimized. Has no
|
||||
* meaning in other contexts.
|
||||
* 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
|
||||
* 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 to be validated and cleaned.
|
||||
* @param $config Mandatory HTMLPurifier_Config object.
|
||||
* @param $context Mandatory HTMLPurifier_AttrContext object.
|
||||
* @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, $context);
|
||||
|
||||
|
|
@ -55,7 +57,8 @@ abstract class HTMLPurifier_AttrDef
|
|||
* parsing XML, thus, this behavior may still be correct. We
|
||||
* assume that newlines have been normalized.
|
||||
*/
|
||||
public function parseCDATA($string) {
|
||||
public function parseCDATA($string)
|
||||
{
|
||||
$string = trim($string);
|
||||
$string = str_replace(array("\n", "\t", "\r"), ' ', $string);
|
||||
return $string;
|
||||
|
|
@ -63,10 +66,11 @@ abstract class HTMLPurifier_AttrDef
|
|||
|
||||
/**
|
||||
* Factory method for creating this class from a string.
|
||||
* @param $string String construction info
|
||||
* @return Created AttrDef object corresponding to $string
|
||||
* @param string $string String construction info
|
||||
* @return HTMLPurifier_AttrDef Created AttrDef object corresponding to $string
|
||||
*/
|
||||
public function make($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
|
||||
|
|
@ -77,16 +81,20 @@ abstract class HTMLPurifier_AttrDef
|
|||
/**
|
||||
* 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) {
|
||||
protected function mungeRgb($string)
|
||||
{
|
||||
return preg_replace('/rgb\((\d+)\s*,\s*(\d+)\s*,\s*(\d+)\)/', 'rgb(\1,\2,\3)', $string);
|
||||
}
|
||||
|
||||
/**
|
||||
* Parses a possibly escaped CSS string and returns the "pure"
|
||||
* Parses a possibly escaped CSS string and returns the "pure"
|
||||
* version of it.
|
||||
*/
|
||||
protected function expandCSSEscape($string) {
|
||||
protected function expandCSSEscape($string)
|
||||
{
|
||||
// flexibly parse it
|
||||
$ret = '';
|
||||
for ($i = 0, $c = strlen($string); $i < $c; $i++) {
|
||||
|
|
@ -99,25 +107,32 @@ abstract class HTMLPurifier_AttrDef
|
|||
if (ctype_xdigit($string[$i])) {
|
||||
$code = $string[$i];
|
||||
for ($a = 1, $i++; $i < $c && $a < 6; $i++, $a++) {
|
||||
if (!ctype_xdigit($string[$i])) break;
|
||||
if (!ctype_xdigit($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($char) === '') continue;
|
||||
if (HTMLPurifier_Encoder::cleanUTF8($char) === '') {
|
||||
continue;
|
||||
}
|
||||
$ret .= $char;
|
||||
if ($i < $c && trim($string[$i]) !== '') $i--;
|
||||
if ($i < $c && trim($string[$i]) !== '') {
|
||||
$i--;
|
||||
}
|
||||
continue;
|
||||
}
|
||||
if ($string[$i] === "\n") {
|
||||
continue;
|
||||
}
|
||||
if ($string[$i] === "\n") continue;
|
||||
}
|
||||
$ret .= $string[$i];
|
||||
}
|
||||
return $ret;
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
// vim: et sw=4 sts=4
|
||||
|
|
@ -14,8 +14,14 @@
|
|||
class HTMLPurifier_AttrDef_CSS extends HTMLPurifier_AttrDef
|
||||
{
|
||||
|
||||
public function validate($css, $config, $context) {
|
||||
|
||||
/**
|
||||
* @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();
|
||||
|
|
@ -36,34 +42,47 @@ class HTMLPurifier_AttrDef_CSS extends HTMLPurifier_AttrDef
|
|||
$context->register('CurrentCSSProperty', $property);
|
||||
|
||||
foreach ($declarations as $declaration) {
|
||||
if (!$declaration) continue;
|
||||
if (!strpos($declaration, ':')) continue;
|
||||
if (!$declaration) {
|
||||
continue;
|
||||
}
|
||||
if (!strpos($declaration, ':')) {
|
||||
continue;
|
||||
}
|
||||
list($property, $value) = explode(':', $declaration, 2);
|
||||
$property = trim($property);
|
||||
$value = trim($value);
|
||||
$value = trim($value);
|
||||
$ok = false;
|
||||
do {
|
||||
if (isset($definition->info[$property])) {
|
||||
$ok = true;
|
||||
break;
|
||||
}
|
||||
if (ctype_lower($property)) break;
|
||||
if (ctype_lower($property)) {
|
||||
break;
|
||||
}
|
||||
$property = strtolower($property);
|
||||
if (isset($definition->info[$property])) {
|
||||
$ok = true;
|
||||
break;
|
||||
}
|
||||
} while(0);
|
||||
if (!$ok) continue;
|
||||
} 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 );
|
||||
$value,
|
||||
$config,
|
||||
$context
|
||||
);
|
||||
} else {
|
||||
$result = 'inherit';
|
||||
}
|
||||
if ($result === false) continue;
|
||||
if ($result === false) {
|
||||
continue;
|
||||
}
|
||||
$propvalues[$property] = $result;
|
||||
}
|
||||
|
||||
|
|
@ -0,0 +1,34 @@
|
|||
<?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 $result;
|
||||
}
|
||||
}
|
||||
|
||||
// vim: et sw=4 sts=4
|
||||
|
|
@ -9,11 +9,16 @@ class HTMLPurifier_AttrDef_CSS_Background extends HTMLPurifier_AttrDef
|
|||
|
||||
/**
|
||||
* Local copy of component validators.
|
||||
* @type HTMLPurifier_AttrDef[]
|
||||
* @note See HTMLPurifier_AttrDef_Font::$info for a similar impl.
|
||||
*/
|
||||
protected $info;
|
||||
|
||||
public function __construct($config) {
|
||||
/**
|
||||
* @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'];
|
||||
|
|
@ -22,40 +27,55 @@ class HTMLPurifier_AttrDef_CSS_Background extends HTMLPurifier_AttrDef
|
|||
$this->info['background-position'] = $def->info['background-position'];
|
||||
}
|
||||
|
||||
public function validate($string, $config, $context) {
|
||||
|
||||
/**
|
||||
* @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 ($string === '') return false;
|
||||
if ($string === '') {
|
||||
return false;
|
||||
}
|
||||
|
||||
// munge rgb() decl if necessary
|
||||
$string = $this->mungeRgb($string);
|
||||
|
||||
// assumes URI doesn't have spaces in it
|
||||
$bits = explode(' ', strtolower($string)); // bits to process
|
||||
$bits = explode(' ', $string); // bits to process
|
||||
|
||||
$caught = array();
|
||||
$caught['color'] = false;
|
||||
$caught['image'] = false;
|
||||
$caught['repeat'] = false;
|
||||
$caught['color'] = false;
|
||||
$caught['image'] = false;
|
||||
$caught['repeat'] = false;
|
||||
$caught['attachment'] = false;
|
||||
$caught['position'] = false;
|
||||
|
||||
$i = 0; // number of catches
|
||||
$none = false;
|
||||
|
||||
foreach ($bits as $bit) {
|
||||
if ($bit === '') continue;
|
||||
if ($bit === '') {
|
||||
continue;
|
||||
}
|
||||
foreach ($caught as $key => $status) {
|
||||
if ($key != 'position') {
|
||||
if ($status !== false) continue;
|
||||
if ($status !== false) {
|
||||
continue;
|
||||
}
|
||||
$r = $this->info['background-' . $key]->validate($bit, $config, $context);
|
||||
} else {
|
||||
$r = $bit;
|
||||
}
|
||||
if ($r === false) continue;
|
||||
if ($r === false) {
|
||||
continue;
|
||||
}
|
||||
if ($key == 'position') {
|
||||
if ($caught[$key] === false) $caught[$key] = '';
|
||||
if ($caught[$key] === false) {
|
||||
$caught[$key] = '';
|
||||
}
|
||||
$caught[$key] .= $r . ' ';
|
||||
} else {
|
||||
$caught[$key] = $r;
|
||||
|
|
@ -65,7 +85,9 @@ class HTMLPurifier_AttrDef_CSS_Background extends HTMLPurifier_AttrDef
|
|||
}
|
||||
}
|
||||
|
||||
if (!$i) return false;
|
||||
if (!$i) {
|
||||
return false;
|
||||
}
|
||||
if ($caught['position'] !== false) {
|
||||
$caught['position'] = $this->info['background-position']->
|
||||
validate($caught['position'], $config, $context);
|
||||
|
|
@ -73,15 +95,17 @@ class HTMLPurifier_AttrDef_CSS_Background extends HTMLPurifier_AttrDef
|
|||
|
||||
$ret = array();
|
||||
foreach ($caught as $value) {
|
||||
if ($value === false) continue;
|
||||
if ($value === false) {
|
||||
continue;
|
||||
}
|
||||
$ret[] = $value;
|
||||
}
|
||||
|
||||
if (empty($ret)) return false;
|
||||
if (empty($ret)) {
|
||||
return false;
|
||||
}
|
||||
return implode(' ', $ret);
|
||||
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
// vim: et sw=4 sts=4
|
||||
|
|
@ -44,15 +44,30 @@
|
|||
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();
|
||||
public function __construct()
|
||||
{
|
||||
$this->length = new HTMLPurifier_AttrDef_CSS_Length();
|
||||
$this->percentage = new HTMLPurifier_AttrDef_CSS_Percentage();
|
||||
}
|
||||
|
||||
public function validate($string, $config, $context) {
|
||||
/**
|
||||
* @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(' ', $string);
|
||||
|
||||
|
|
@ -74,7 +89,9 @@ class HTMLPurifier_AttrDef_CSS_BackgroundPosition extends HTMLPurifier_AttrDef
|
|||
);
|
||||
|
||||
foreach ($bits as $bit) {
|
||||
if ($bit === '') continue;
|
||||
if ($bit === '') {
|
||||
continue;
|
||||
}
|
||||
|
||||
// test for keyword
|
||||
$lbit = ctype_lower($bit) ? $bit : strtolower($bit);
|
||||
|
|
@ -104,30 +121,37 @@ class HTMLPurifier_AttrDef_CSS_BackgroundPosition extends HTMLPurifier_AttrDef
|
|||
$measures[] = $r;
|
||||
$i++;
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
if (!$i) return false; // no valid values were caught
|
||||
if (!$i) {
|
||||
return false;
|
||||
} // no valid values were caught
|
||||
|
||||
$ret = array();
|
||||
|
||||
// first keyword
|
||||
if ($keywords['h']) $ret[] = $keywords['h'];
|
||||
elseif ($keywords['ch']) {
|
||||
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);
|
||||
}
|
||||
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 ($keywords['v']) {
|
||||
$ret[] = $keywords['v'];
|
||||
} elseif ($keywords['cv']) {
|
||||
$ret[] = $keywords['cv'];
|
||||
} elseif (count($measures)) {
|
||||
$ret[] = array_shift($measures);
|
||||
}
|
||||
|
||||
if (empty($ret)) return false;
|
||||
if (empty($ret)) {
|
||||
return false;
|
||||
}
|
||||
return implode(' ', $ret);
|
||||
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
// vim: et sw=4 sts=4
|
||||
|
|
@ -8,17 +8,29 @@ class HTMLPurifier_AttrDef_CSS_Border extends HTMLPurifier_AttrDef
|
|||
|
||||
/**
|
||||
* Local copy of properties this property is shorthand for.
|
||||
* @type HTMLPurifier_AttrDef[]
|
||||
*/
|
||||
protected $info = array();
|
||||
|
||||
public function __construct($config) {
|
||||
/**
|
||||
* @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'] = $def->info['border-top-color'];
|
||||
}
|
||||
|
||||
public function validate($string, $config, $context) {
|
||||
/**
|
||||
* @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);
|
||||
|
|
@ -26,7 +38,9 @@ class HTMLPurifier_AttrDef_CSS_Border extends HTMLPurifier_AttrDef
|
|||
$ret = ''; // return value
|
||||
foreach ($bits as $bit) {
|
||||
foreach ($this->info as $propname => $validator) {
|
||||
if (isset($done[$propname])) continue;
|
||||
if (isset($done[$propname])) {
|
||||
continue;
|
||||
}
|
||||
$r = $validator->validate($bit, $config, $context);
|
||||
if ($r !== false) {
|
||||
$ret .= $r . ' ';
|
||||
|
|
@ -37,7 +51,6 @@ class HTMLPurifier_AttrDef_CSS_Border extends HTMLPurifier_AttrDef
|
|||
}
|
||||
return rtrim($ret);
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
// vim: et sw=4 sts=4
|
||||
|
|
@ -6,29 +6,47 @@
|
|||
class HTMLPurifier_AttrDef_CSS_Color extends HTMLPurifier_AttrDef
|
||||
{
|
||||
|
||||
public function validate($color, $config, $context) {
|
||||
|
||||
/**
|
||||
* @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 = $config->get('Core.ColorKeywords');
|
||||
if ($colors === null) {
|
||||
$colors = $config->get('Core.ColorKeywords');
|
||||
}
|
||||
|
||||
$color = trim($color);
|
||||
if ($color === '') return false;
|
||||
if ($color === '') {
|
||||
return false;
|
||||
}
|
||||
|
||||
$lower = strtolower($color);
|
||||
if (isset($colors[$lower])) return $colors[$lower];
|
||||
if (isset($colors[$lower])) {
|
||||
return $colors[$lower];
|
||||
}
|
||||
|
||||
if (strpos($color, 'rgb(') !== false) {
|
||||
// rgb literal handling
|
||||
$length = strlen($color);
|
||||
if (strpos($color, ')') !== $length - 1) return false;
|
||||
if (strpos($color, ')') !== $length - 1) {
|
||||
return false;
|
||||
}
|
||||
$triad = substr($color, 4, $length - 4 - 1);
|
||||
$parts = explode(',', $triad);
|
||||
if (count($parts) !== 3) return false;
|
||||
if (count($parts) !== 3) {
|
||||
return false;
|
||||
}
|
||||
$type = false; // to ensure that they're all the same type
|
||||
$new_parts = array();
|
||||
foreach ($parts as $part) {
|
||||
$part = trim($part);
|
||||
if ($part === '') return false;
|
||||
if ($part === '') {
|
||||
return false;
|
||||
}
|
||||
$length = strlen($part);
|
||||
if ($part[$length - 1] === '%') {
|
||||
// handle percents
|
||||
|
|
@ -37,9 +55,13 @@ class HTMLPurifier_AttrDef_CSS_Color extends HTMLPurifier_AttrDef
|
|||
} elseif ($type !== 'percentage') {
|
||||
return false;
|
||||
}
|
||||
$num = (float) substr($part, 0, $length - 1);
|
||||
if ($num < 0) $num = 0;
|
||||
if ($num > 100) $num = 100;
|
||||
$num = (float)substr($part, 0, $length - 1);
|
||||
if ($num < 0) {
|
||||
$num = 0;
|
||||
}
|
||||
if ($num > 100) {
|
||||
$num = 100;
|
||||
}
|
||||
$new_parts[] = "$num%";
|
||||
} else {
|
||||
// handle integers
|
||||
|
|
@ -48,10 +70,14 @@ class HTMLPurifier_AttrDef_CSS_Color extends HTMLPurifier_AttrDef
|
|||
} elseif ($type !== 'integer') {
|
||||
return false;
|
||||
}
|
||||
$num = (int) $part;
|
||||
if ($num < 0) $num = 0;
|
||||
if ($num > 255) $num = 255;
|
||||
$new_parts[] = (string) $num;
|
||||
$num = (int)$part;
|
||||
if ($num < 0) {
|
||||
$num = 0;
|
||||
}
|
||||
if ($num > 255) {
|
||||
$num = 255;
|
||||
}
|
||||
$new_parts[] = (string)$num;
|
||||
}
|
||||
}
|
||||
$new_triad = implode(',', $new_parts);
|
||||
|
|
@ -65,14 +91,15 @@ class HTMLPurifier_AttrDef_CSS_Color extends HTMLPurifier_AttrDef
|
|||
$color = '#' . $color;
|
||||
}
|
||||
$length = strlen($hex);
|
||||
if ($length !== 3 && $length !== 6) return false;
|
||||
if (!ctype_xdigit($hex)) return false;
|
||||
if ($length !== 3 && $length !== 6) {
|
||||
return false;
|
||||
}
|
||||
if (!ctype_xdigit($hex)) {
|
||||
return false;
|
||||
}
|
||||
}
|
||||
|
||||
return $color;
|
||||
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
// vim: et sw=4 sts=4
|
||||
|
|
@ -13,26 +13,36 @@ class HTMLPurifier_AttrDef_CSS_Composite extends HTMLPurifier_AttrDef
|
|||
{
|
||||
|
||||
/**
|
||||
* List of HTMLPurifier_AttrDef objects that may process strings
|
||||
* List of objects that may process strings.
|
||||
* @type HTMLPurifier_AttrDef[]
|
||||
* @todo Make protected
|
||||
*/
|
||||
public $defs;
|
||||
|
||||
/**
|
||||
* @param $defs List of HTMLPurifier_AttrDef objects
|
||||
* @param HTMLPurifier_AttrDef[] $defs List of HTMLPurifier_AttrDef objects
|
||||
*/
|
||||
public function __construct($defs) {
|
||||
public function __construct($defs)
|
||||
{
|
||||
$this->defs = $defs;
|
||||
}
|
||||
|
||||
public function validate($string, $config, $context) {
|
||||
/**
|
||||
* @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 $result;
|
||||
if ($result !== false) {
|
||||
return $result;
|
||||
}
|
||||
}
|
||||
return false;
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
// vim: et sw=4 sts=4
|
||||
|
|
@ -0,0 +1,44 @@
|
|||
<?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
|
||||
|
|
@ -7,23 +7,37 @@
|
|||
*/
|
||||
class HTMLPurifier_AttrDef_CSS_Filter extends HTMLPurifier_AttrDef
|
||||
{
|
||||
|
||||
/**
|
||||
* @type HTMLPurifier_AttrDef_Integer
|
||||
*/
|
||||
protected $intValidator;
|
||||
|
||||
public function __construct() {
|
||||
public function __construct()
|
||||
{
|
||||
$this->intValidator = new HTMLPurifier_AttrDef_Integer();
|
||||
}
|
||||
|
||||
public function validate($value, $config, $context) {
|
||||
/**
|
||||
* @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 $value;
|
||||
if ($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;
|
||||
) {
|
||||
return false;
|
||||
}
|
||||
$cursor = $function_length + 1;
|
||||
$parameters_length = strcspn($value, ')', $cursor);
|
||||
$parameters = substr($value, $cursor, $parameters_length);
|
||||
|
|
@ -32,15 +46,25 @@ class HTMLPurifier_AttrDef_CSS_Filter extends HTMLPurifier_AttrDef
|
|||
$lookup = array();
|
||||
foreach ($params as $param) {
|
||||
list($key, $value) = explode('=', $param);
|
||||
$key = trim($key);
|
||||
$key = trim($key);
|
||||
$value = trim($value);
|
||||
if (isset($lookup[$key])) continue;
|
||||
if ($key !== 'opacity') continue;
|
||||
if (isset($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) $value = '0';
|
||||
if ($value === false) {
|
||||
continue;
|
||||
}
|
||||
$int = (int)$value;
|
||||
if ($int > 100) {
|
||||
$value = '100';
|
||||
}
|
||||
if ($int < 0) {
|
||||
$value = '0';
|
||||
}
|
||||
$ret_params[] = "$key=$value";
|
||||
$lookup[$key] = true;
|
||||
}
|
||||
|
|
@ -48,7 +72,6 @@ class HTMLPurifier_AttrDef_CSS_Filter extends HTMLPurifier_AttrDef
|
|||
$ret_function = "$function($ret_parameters)";
|
||||
return $ret_function;
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
// vim: et sw=4 sts=4
|
||||
|
|
@ -7,8 +7,8 @@ class HTMLPurifier_AttrDef_CSS_Font extends HTMLPurifier_AttrDef
|
|||
{
|
||||
|
||||
/**
|
||||
* Local copy of component validators.
|
||||
*
|
||||
* 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
|
||||
|
|
@ -16,18 +16,28 @@ class HTMLPurifier_AttrDef_CSS_Font extends HTMLPurifier_AttrDef
|
|||
*/
|
||||
protected $info = array();
|
||||
|
||||
public function __construct($config) {
|
||||
/**
|
||||
* @param HTMLPurifier_Config $config
|
||||
*/
|
||||
public function __construct($config)
|
||||
{
|
||||
$def = $config->getCSSDefinition();
|
||||
$this->info['font-style'] = $def->info['font-style'];
|
||||
$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'];
|
||||
$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'] = $def->info['font-family'];
|
||||
}
|
||||
|
||||
public function validate($string, $config, $context) {
|
||||
|
||||
/**
|
||||
* @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,
|
||||
|
|
@ -39,7 +49,9 @@ class HTMLPurifier_AttrDef_CSS_Font extends HTMLPurifier_AttrDef
|
|||
|
||||
// regular pre-processing
|
||||
$string = $this->parseCDATA($string);
|
||||
if ($string === '') return false;
|
||||
if ($string === '') {
|
||||
return false;
|
||||
}
|
||||
|
||||
// check if it's one of the keywords
|
||||
$lowercase_string = strtolower($string);
|
||||
|
|
@ -54,15 +66,20 @@ class HTMLPurifier_AttrDef_CSS_Font extends HTMLPurifier_AttrDef
|
|||
$final = ''; // output
|
||||
|
||||
for ($i = 0, $size = count($bits); $i < $size; $i++) {
|
||||
if ($bits[$i] === '') continue;
|
||||
if ($bits[$i] === '') {
|
||||
continue;
|
||||
}
|
||||
switch ($stage) {
|
||||
|
||||
// attempting to catch font-style, font-variant or font-weight
|
||||
case 0:
|
||||
case 0: // attempting to catch font-style, font-variant or font-weight
|
||||
foreach ($stage_1 as $validator_name) {
|
||||
if (isset($caught[$validator_name])) continue;
|
||||
if (isset($caught[$validator_name])) {
|
||||
continue;
|
||||
}
|
||||
$r = $this->info[$validator_name]->validate(
|
||||
$bits[$i], $config, $context);
|
||||
$bits[$i],
|
||||
$config,
|
||||
$context
|
||||
);
|
||||
if ($r !== false) {
|
||||
$final .= $r . ' ';
|
||||
$caught[$validator_name] = true;
|
||||
|
|
@ -70,15 +87,17 @@ class HTMLPurifier_AttrDef_CSS_Font extends HTMLPurifier_AttrDef
|
|||
}
|
||||
}
|
||||
// all three caught, continue on
|
||||
if (count($caught) >= 3) $stage = 1;
|
||||
if ($r !== false) break;
|
||||
|
||||
// attempting to catch font-size and perhaps line-height
|
||||
case 1:
|
||||
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]);
|
||||
explode('/', $bits[$i]);
|
||||
if ($line_height === '') {
|
||||
// ooh, there's a space after the slash!
|
||||
$line_height = false;
|
||||
|
|
@ -89,14 +108,19 @@ class HTMLPurifier_AttrDef_CSS_Font extends HTMLPurifier_AttrDef
|
|||
$line_height = false;
|
||||
}
|
||||
$r = $this->info['font-size']->validate(
|
||||
$font_size, $config, $context);
|
||||
$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[$j] === '') {
|
||||
continue;
|
||||
}
|
||||
if ($bits[$j] === '/') {
|
||||
if ($found_slash) {
|
||||
return false;
|
||||
|
|
@ -116,7 +140,10 @@ class HTMLPurifier_AttrDef_CSS_Font extends HTMLPurifier_AttrDef
|
|||
if ($found_slash) {
|
||||
$i = $j;
|
||||
$r = $this->info['line-height']->validate(
|
||||
$line_height, $config, $context);
|
||||
$line_height,
|
||||
$config,
|
||||
$context
|
||||
);
|
||||
if ($r !== false) {
|
||||
$final .= '/' . $r;
|
||||
}
|
||||
|
|
@ -126,13 +153,14 @@ class HTMLPurifier_AttrDef_CSS_Font extends HTMLPurifier_AttrDef
|
|||
break;
|
||||
}
|
||||
return false;
|
||||
|
||||
// attempting to catch font-family
|
||||
case 2:
|
||||
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);
|
||||
$font_family,
|
||||
$config,
|
||||
$context
|
||||
);
|
||||
if ($r !== false) {
|
||||
$final .= $r . ' ';
|
||||
// processing completed successfully
|
||||
|
|
@ -143,7 +171,6 @@ class HTMLPurifier_AttrDef_CSS_Font extends HTMLPurifier_AttrDef
|
|||
}
|
||||
return false;
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
// vim: et sw=4 sts=4
|
||||
|
|
@ -0,0 +1,219 @@
|
|||
<?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
|
||||
|
|
@ -0,0 +1,32 @@
|
|||
<?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
|
||||
|
|
@ -5,20 +5,34 @@
|
|||
*/
|
||||
class HTMLPurifier_AttrDef_CSS_ImportantDecorator extends HTMLPurifier_AttrDef
|
||||
{
|
||||
public $def, $allow;
|
||||
/**
|
||||
* @type HTMLPurifier_AttrDef
|
||||
*/
|
||||
public $def;
|
||||
/**
|
||||
* @type bool
|
||||
*/
|
||||
public $allow;
|
||||
|
||||
/**
|
||||
* @param $def Definition to wrap
|
||||
* @param $allow Whether or not to allow !important
|
||||
* @param HTMLPurifier_AttrDef $def Definition to wrap
|
||||
* @param bool $allow Whether or not to allow !important
|
||||
*/
|
||||
public function __construct($def, $allow = false) {
|
||||
public function __construct($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, $context) {
|
||||
public function validate($string, $config, $context)
|
||||
{
|
||||
// test for ! and important tokens
|
||||
$string = trim($string);
|
||||
$is_important = false;
|
||||
|
|
@ -32,7 +46,9 @@ class HTMLPurifier_AttrDef_CSS_ImportantDecorator extends HTMLPurifier_AttrDef
|
|||
}
|
||||
}
|
||||
$string = $this->def->validate($string, $config, $context);
|
||||
if ($this->allow && $is_important) $string .= ' !important';
|
||||
if ($this->allow && $is_important) {
|
||||
$string .= ' !important';
|
||||
}
|
||||
return $string;
|
||||
}
|
||||
}
|
||||
|
|
@ -0,0 +1,77 @@
|
|||
<?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 $length->toString();
|
||||
}
|
||||
}
|
||||
|
||||
// vim: et sw=4 sts=4
|
||||
|
|
@ -0,0 +1,112 @@
|
|||
<?php
|
||||
|
||||
/**
|
||||
* Validates shorthand CSS property list-style.
|
||||
* @warning Does not support url tokens that have internal spaces.
|
||||
*/
|
||||
class HTMLPurifier_AttrDef_CSS_ListStyle extends HTMLPurifier_AttrDef
|
||||
{
|
||||
|
||||
/**
|
||||
* Local copy of validators.
|
||||
* @type HTMLPurifier_AttrDef[]
|
||||
* @note See HTMLPurifier_AttrDef_CSS_Font::$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
|
||||
|
|
@ -13,9 +13,9 @@
|
|||
*/
|
||||
class HTMLPurifier_AttrDef_CSS_Multiple extends HTMLPurifier_AttrDef
|
||||
{
|
||||
|
||||
/**
|
||||
* Instance of component definition to defer validation to.
|
||||
* @type HTMLPurifier_AttrDef
|
||||
* @todo Make protected
|
||||
*/
|
||||
public $single;
|
||||
|
|
@ -27,32 +27,45 @@ class HTMLPurifier_AttrDef_CSS_Multiple extends HTMLPurifier_AttrDef
|
|||
public $max;
|
||||
|
||||
/**
|
||||
* @param $single HTMLPurifier_AttrDef to multiply
|
||||
* @param $max Max number of values allowed (usually four)
|
||||
* @param HTMLPurifier_AttrDef $single HTMLPurifier_AttrDef to multiply
|
||||
* @param int $max Max number of values allowed (usually four)
|
||||
*/
|
||||
public function __construct($single, $max = 4) {
|
||||
public function __construct($single, $max = 4)
|
||||
{
|
||||
$this->single = $single;
|
||||
$this->max = $max;
|
||||
}
|
||||
|
||||
public function validate($string, $config, $context) {
|
||||
$string = $this->parseCDATA($string);
|
||||
if ($string === '') return false;
|
||||
/**
|
||||
* @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[$i])) continue;
|
||||
if (ctype_space($parts[$i])) {
|
||||
continue;
|
||||
}
|
||||
$result = $this->single->validate($parts[$i], $config, $context);
|
||||
if ($result !== false) {
|
||||
$final .= $result . ' ';
|
||||
$num++;
|
||||
}
|
||||
}
|
||||
if ($final === '') return false;
|
||||
if ($final === '') {
|
||||
return false;
|
||||
}
|
||||
return rtrim($final);
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
// vim: et sw=4 sts=4
|
||||
|
|
@ -7,32 +7,44 @@ class HTMLPurifier_AttrDef_CSS_Number extends HTMLPurifier_AttrDef
|
|||
{
|
||||
|
||||
/**
|
||||
* Bool indicating whether or not only positive values allowed.
|
||||
* Indicates whether or not only positive values are allowed.
|
||||
* @type bool
|
||||
*/
|
||||
protected $non_negative = false;
|
||||
|
||||
/**
|
||||
* @param $non_negative Bool indicating whether negatives are forbidden
|
||||
* @param bool $non_negative indicates whether negatives are forbidden
|
||||
*/
|
||||
public function __construct($non_negative = false) {
|
||||
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, $context) {
|
||||
|
||||
public function validate($number, $config, $context)
|
||||
{
|
||||
$number = $this->parseCDATA($number);
|
||||
|
||||
if ($number === '') return false;
|
||||
if ($number === '0') return '0';
|
||||
if ($number === '') {
|
||||
return false;
|
||||
}
|
||||
if ($number === '0') {
|
||||
return '0';
|
||||
}
|
||||
|
||||
$sign = '';
|
||||
switch ($number[0]) {
|
||||
case '-':
|
||||
if ($this->non_negative) return false;
|
||||
if ($this->non_negative) {
|
||||
return false;
|
||||
}
|
||||
$sign = '-';
|
||||
case '+':
|
||||
$number = substr($number, 1);
|
||||
|
|
@ -44,14 +56,20 @@ class HTMLPurifier_AttrDef_CSS_Number extends HTMLPurifier_AttrDef
|
|||
}
|
||||
|
||||
// Period is the only non-numeric character allowed
|
||||
if (strpos($number, '.') === false) return false;
|
||||
if (strpos($number, '.') === false) {
|
||||
return false;
|
||||
}
|
||||
|
||||
list($left, $right) = explode('.', $number, 2);
|
||||
|
||||
if ($left === '' && $right === '') return false;
|
||||
if ($left !== '' && !ctype_digit($left)) return false;
|
||||
if ($left === '' && $right === '') {
|
||||
return false;
|
||||
}
|
||||
if ($left !== '' && !ctype_digit($left)) {
|
||||
return false;
|
||||
}
|
||||
|
||||
$left = ltrim($left, '0');
|
||||
$left = ltrim($left, '0');
|
||||
$right = rtrim($right, '0');
|
||||
|
||||
if ($right === '') {
|
||||
|
|
@ -59,11 +77,8 @@ class HTMLPurifier_AttrDef_CSS_Number extends HTMLPurifier_AttrDef
|
|||
} elseif (!ctype_digit($right)) {
|
||||
return false;
|
||||
}
|
||||
|
||||
return $sign . $left . '.' . $right;
|
||||
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
// vim: et sw=4 sts=4
|
||||
|
|
@ -0,0 +1,54 @@
|
|||
<?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 "$number%";
|
||||
}
|
||||
}
|
||||
|
||||
// vim: et sw=4 sts=4
|
||||
|
|
@ -8,8 +8,14 @@
|
|||
class HTMLPurifier_AttrDef_CSS_TextDecoration extends HTMLPurifier_AttrDef
|
||||
{
|
||||
|
||||
public function validate($string, $config, $context) {
|
||||
|
||||
/**
|
||||
* @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,
|
||||
|
|
@ -18,7 +24,9 @@ class HTMLPurifier_AttrDef_CSS_TextDecoration extends HTMLPurifier_AttrDef
|
|||
|
||||
$string = strtolower($this->parseCDATA($string));
|
||||
|
||||
if ($string === 'none') return $string;
|
||||
if ($string === 'none') {
|
||||
return $string;
|
||||
}
|
||||
|
||||
$parts = explode(' ', $string);
|
||||
$final = '';
|
||||
|
|
@ -28,11 +36,11 @@ class HTMLPurifier_AttrDef_CSS_TextDecoration extends HTMLPurifier_AttrDef
|
|||
}
|
||||
}
|
||||
$final = rtrim($final);
|
||||
if ($final === '') return false;
|
||||
if ($final === '') {
|
||||
return false;
|
||||
}
|
||||
return $final;
|
||||
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
// vim: et sw=4 sts=4
|
||||
|
|
@ -12,25 +12,39 @@
|
|||
class HTMLPurifier_AttrDef_CSS_URI extends HTMLPurifier_AttrDef_URI
|
||||
{
|
||||
|
||||
public function __construct() {
|
||||
public function __construct()
|
||||
{
|
||||
parent::__construct(true); // always embedded
|
||||
}
|
||||
|
||||
public function validate($uri_string, $config, $context) {
|
||||
/**
|
||||
* @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($uri_string, 'url(') !== 0) return false;
|
||||
if (strpos($uri_string, 'url(') !== 0) {
|
||||
return false;
|
||||
}
|
||||
$uri_string = substr($uri_string, 4);
|
||||
$new_length = strlen($uri_string) - 1;
|
||||
if ($uri_string[$new_length] != ')') return false;
|
||||
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] !== $quote) return false;
|
||||
if ($uri[$new_length] !== $quote) {
|
||||
return false;
|
||||
}
|
||||
$uri = substr($uri, 1, $new_length - 1);
|
||||
}
|
||||
|
||||
|
|
@ -38,15 +52,23 @@ class HTMLPurifier_AttrDef_CSS_URI extends HTMLPurifier_AttrDef_URI
|
|||
|
||||
$result = parent::validate($uri, $config, $context);
|
||||
|
||||
if ($result === false) return false;
|
||||
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
|
||||
|
|
@ -0,0 +1,44 @@
|
|||
<?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
|
||||
|
|
@ -12,9 +12,10 @@ class HTMLPurifier_AttrDef_Enum extends HTMLPurifier_AttrDef
|
|||
|
||||
/**
|
||||
* Lookup table of valid values.
|
||||
* @type array
|
||||
* @todo Make protected
|
||||
*/
|
||||
public $valid_values = array();
|
||||
public $valid_values = array();
|
||||
|
||||
/**
|
||||
* Bool indicating whether or not enumeration is case sensitive.
|
||||
|
|
@ -23,17 +24,23 @@ class HTMLPurifier_AttrDef_Enum extends HTMLPurifier_AttrDef
|
|||
protected $case_sensitive = false; // values according to W3C spec
|
||||
|
||||
/**
|
||||
* @param $valid_values List of valid values
|
||||
* @param $case_sensitive Bool indicating whether or not case sensitive
|
||||
* @param array $valid_values List of valid values
|
||||
* @param bool $case_sensitive Whether or not case sensitive
|
||||
*/
|
||||
public function __construct(
|
||||
$valid_values = array(), $case_sensitive = false
|
||||
) {
|
||||
public function __construct($valid_values = array(), $case_sensitive = false)
|
||||
{
|
||||
$this->valid_values = array_flip($valid_values);
|
||||
$this->case_sensitive = $case_sensitive;
|
||||
}
|
||||
|
||||
public function validate($string, $config, $context) {
|
||||
/**
|
||||
* @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
|
||||
|
|
@ -45,11 +52,13 @@ class HTMLPurifier_AttrDef_Enum extends HTMLPurifier_AttrDef
|
|||
}
|
||||
|
||||
/**
|
||||
* @param $string In form of comma-delimited list of case-insensitive
|
||||
* @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) {
|
||||
public function make($string)
|
||||
{
|
||||
if (strlen($string) > 2 && $string[0] == 's' && $string[1] == ':') {
|
||||
$string = substr($string, 2);
|
||||
$sensitive = true;
|
||||
|
|
@ -59,7 +68,6 @@ class HTMLPurifier_AttrDef_Enum extends HTMLPurifier_AttrDef
|
|||
$values = explode(',', $string);
|
||||
return new HTMLPurifier_AttrDef_Enum($values, $sensitive);
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
// vim: et sw=4 sts=4
|
||||
|
|
@ -0,0 +1,48 @@
|
|||
<?php
|
||||
|
||||
/**
|
||||
* Validates a boolean attribute
|
||||
*/
|
||||
class HTMLPurifier_AttrDef_HTML_Bool extends HTMLPurifier_AttrDef
|
||||
{
|
||||
|
||||
/**
|
||||
* @type bool
|
||||
*/
|
||||
protected $name;
|
||||
|
||||
/**
|
||||
* @type bool
|
||||
*/
|
||||
public $minimized = true;
|
||||
|
||||
/**
|
||||
* @param bool $name
|
||||
*/
|
||||
public function __construct($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($string);
|
||||
}
|
||||
}
|
||||
|
||||
// vim: et sw=4 sts=4
|
||||
|
|
@ -5,7 +5,14 @@
|
|||
*/
|
||||
class HTMLPurifier_AttrDef_HTML_Class extends HTMLPurifier_AttrDef_HTML_Nmtokens
|
||||
{
|
||||
protected function split($string, $config, $context) {
|
||||
/**
|
||||
* @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") {
|
||||
|
|
@ -14,13 +21,20 @@ class HTMLPurifier_AttrDef_HTML_Class extends HTMLPurifier_AttrDef_HTML_Nmtokens
|
|||
return preg_split('/\s+/', $string);
|
||||
}
|
||||
}
|
||||
protected function filter($tokens, $config, $context) {
|
||||
|
||||
/**
|
||||
* @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])) &&
|
||||
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.
|
||||
|
|
@ -0,0 +1,51 @@
|
|||
<?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
|
||||
|
|
@ -0,0 +1,38 @@
|
|||
<?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
|
||||
|
|
@ -0,0 +1,105 @@
|
|||
<?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[$id])) {
|
||||
return false;
|
||||
}
|
||||
}
|
||||
|
||||
// we purposely avoid using regex, hopefully this is faster
|
||||
|
||||
if (ctype_alpha($id)) {
|
||||
$result = true;
|
||||
} else {
|
||||
if (!ctype_alpha(@$id[0])) {
|
||||
return false;
|
||||
}
|
||||
// primitive style of regexps, I suppose
|
||||
$trim = trim(
|
||||
$id,
|
||||
'A..Za..z0..9:-._'
|
||||
);
|
||||
$result = ($trim === '');
|
||||
}
|
||||
|
||||
$regexp = $config->get('Attr.IDBlacklistRegexp');
|
||||
if ($regexp && preg_match($regexp, $id)) {
|
||||
return false;
|
||||
}
|
||||
|
||||
if (!$this->selector && $result) {
|
||||
$id_accumulator->add($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 $result ? $id : false;
|
||||
}
|
||||
}
|
||||
|
||||
// vim: et sw=4 sts=4
|
||||
|
|
@ -0,0 +1,56 @@
|
|||
<?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
|
||||
|
|
@ -9,26 +9,44 @@
|
|||
class HTMLPurifier_AttrDef_HTML_LinkTypes extends HTMLPurifier_AttrDef
|
||||
{
|
||||
|
||||
/** Name config attribute to pull. */
|
||||
/**
|
||||
* Name config attribute to pull.
|
||||
* @type string
|
||||
*/
|
||||
protected $name;
|
||||
|
||||
public function __construct($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);
|
||||
trigger_error(
|
||||
'Unrecognized attribute name for link ' .
|
||||
'relationship.',
|
||||
E_USER_ERROR
|
||||
);
|
||||
return;
|
||||
}
|
||||
$this->name = $configLookup[$name];
|
||||
}
|
||||
|
||||
public function validate($string, $config, $context) {
|
||||
|
||||
/**
|
||||
* @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;
|
||||
if (empty($allowed)) {
|
||||
return false;
|
||||
}
|
||||
|
||||
$string = $this->parseCDATA($string);
|
||||
$parts = explode(' ', $string);
|
||||
|
|
@ -37,17 +55,18 @@ class HTMLPurifier_AttrDef_HTML_LinkTypes extends HTMLPurifier_AttrDef
|
|||
$ret_lookup = array();
|
||||
foreach ($parts as $part) {
|
||||
$part = strtolower(trim($part));
|
||||
if (!isset($allowed[$part])) continue;
|
||||
if (!isset($allowed[$part])) {
|
||||
continue;
|
||||
}
|
||||
$ret_lookup[$part] = true;
|
||||
}
|
||||
|
||||
if (empty($ret_lookup)) return false;
|
||||
if (empty($ret_lookup)) {
|
||||
return false;
|
||||
}
|
||||
$string = implode(' ', array_keys($ret_lookup));
|
||||
|
||||
return $string;
|
||||
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
// vim: et sw=4 sts=4
|
||||
|
|
@ -0,0 +1,60 @@
|
|||
<?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
|
||||
|
|
@ -6,24 +6,38 @@
|
|||
class HTMLPurifier_AttrDef_HTML_Nmtokens extends HTMLPurifier_AttrDef
|
||||
{
|
||||
|
||||
public function validate($string, $config, $context) {
|
||||
|
||||
/**
|
||||
* @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 (!$string) return false;
|
||||
if (!$string) {
|
||||
return false;
|
||||
}
|
||||
|
||||
$tokens = $this->split($string, $config, $context);
|
||||
$tokens = $this->filter($tokens, $config, $context);
|
||||
if (empty($tokens)) return false;
|
||||
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, $context) {
|
||||
protected function split($string, $config, $context)
|
||||
{
|
||||
// OPTIMIZABLE!
|
||||
// do the preg_match, capture all subpatterns for reformulation
|
||||
|
||||
|
|
@ -31,9 +45,9 @@ class HTMLPurifier_AttrDef_HTML_Nmtokens extends HTMLPurifier_AttrDef
|
|||
// 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
|
||||
$pattern = '/(?:(?<=\s)|\A)' . // look behind for space or string start
|
||||
'((?:--|-?[A-Za-z_])[A-Za-z_\-0-9]*)' .
|
||||
'(?:(?=\s)|\z)/'; // look ahead for space or string end
|
||||
preg_match_all($pattern, $string, $matches);
|
||||
return $matches[1];
|
||||
}
|
||||
|
|
@ -42,11 +56,15 @@ class HTMLPurifier_AttrDef_HTML_Nmtokens extends HTMLPurifier_AttrDef
|
|||
* 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, $context) {
|
||||
protected function filter($tokens, $config, $context)
|
||||
{
|
||||
return $tokens;
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
// vim: et sw=4 sts=4
|
||||
|
|
@ -0,0 +1,76 @@
|
|||
<?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
|
||||
|
|
@ -11,17 +11,20 @@ class HTMLPurifier_AttrDef_Integer extends HTMLPurifier_AttrDef
|
|||
{
|
||||
|
||||
/**
|
||||
* Bool indicating whether or not negative values are allowed
|
||||
* Whether or not negative values are allowed.
|
||||
* @type bool
|
||||
*/
|
||||
protected $negative = true;
|
||||
|
||||
/**
|
||||
* Bool indicating whether or not zero is allowed
|
||||
* Whether or not zero is allowed.
|
||||
* @type bool
|
||||
*/
|
||||
protected $zero = true;
|
||||
|
||||
/**
|
||||
* Bool indicating whether or not positive values are allowed
|
||||
* Whether or not positive values are allowed.
|
||||
* @type bool
|
||||
*/
|
||||
protected $positive = true;
|
||||
|
||||
|
|
@ -30,44 +33,59 @@ class HTMLPurifier_AttrDef_Integer extends HTMLPurifier_AttrDef
|
|||
* @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, $positive = true
|
||||
) {
|
||||
public function __construct($negative = true, $zero = true, $positive = true)
|
||||
{
|
||||
$this->negative = $negative;
|
||||
$this->zero = $zero;
|
||||
$this->zero = $zero;
|
||||
$this->positive = $positive;
|
||||
}
|
||||
|
||||
public function validate($integer, $config, $context) {
|
||||
|
||||
/**
|
||||
* @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 ($integer === '') return false;
|
||||
if ($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 && $integer[0] === '-' ) {
|
||||
if ($this->negative && $integer[0] === '-') {
|
||||
$digits = substr($integer, 1);
|
||||
if ($digits === '0') $integer = '0'; // rm minus sign for zero
|
||||
} elseif( $this->positive && $integer[0] === '+' ) {
|
||||
if ($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;
|
||||
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 && $integer < 0) return false;
|
||||
if (!$this->zero && $integer == 0) {
|
||||
return false;
|
||||
}
|
||||
if (!$this->positive && $integer > 0) {
|
||||
return false;
|
||||
}
|
||||
if (!$this->negative && $integer < 0) {
|
||||
return false;
|
||||
}
|
||||
|
||||
return $integer;
|
||||
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
// vim: et sw=4 sts=4
|
||||
|
|
@ -7,15 +7,25 @@
|
|||
class HTMLPurifier_AttrDef_Lang extends HTMLPurifier_AttrDef
|
||||
{
|
||||
|
||||
public function validate($string, $config, $context) {
|
||||
|
||||
/**
|
||||
* @param string $string
|
||||
* @param HTMLPurifier_Config $config
|
||||
* @param HTMLPurifier_Context $context
|
||||
* @return bool|string
|
||||
*/
|
||||
public function validate($string, $config, $context)
|
||||
{
|
||||
$string = trim($string);
|
||||
if (!$string) return false;
|
||||
if (!$string) {
|
||||
return false;
|
||||
}
|
||||
|
||||
$subtags = explode('-', $string);
|
||||
$num_subtags = count($subtags);
|
||||
|
||||
if ($num_subtags == 0) return false; // sanity check
|
||||
if ($num_subtags == 0) { // sanity check
|
||||
return false;
|
||||
}
|
||||
|
||||
// process primary subtag : $subtags[0]
|
||||
$length = strlen($subtags[0]);
|
||||
|
|
@ -23,15 +33,15 @@ class HTMLPurifier_AttrDef_Lang extends HTMLPurifier_AttrDef
|
|||
case 0:
|
||||
return false;
|
||||
case 1:
|
||||
if (! ($subtags[0] == 'x' || $subtags[0] == 'i') ) {
|
||||
if (!($subtags[0] == 'x' || $subtags[0] == 'i')) {
|
||||
return false;
|
||||
}
|
||||
break;
|
||||
case 2:
|
||||
case 3:
|
||||
if (! ctype_alpha($subtags[0]) ) {
|
||||
if (!ctype_alpha($subtags[0])) {
|
||||
return false;
|
||||
} elseif (! ctype_lower($subtags[0]) ) {
|
||||
} elseif (!ctype_lower($subtags[0])) {
|
||||
$subtags[0] = strtolower($subtags[0]);
|
||||
}
|
||||
break;
|
||||
|
|
@ -40,17 +50,23 @@ class HTMLPurifier_AttrDef_Lang extends HTMLPurifier_AttrDef
|
|||
}
|
||||
|
||||
$new_string = $subtags[0];
|
||||
if ($num_subtags == 1) return $new_string;
|
||||
if ($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]);
|
||||
if (!ctype_lower($subtags[1])) {
|
||||
$subtags[1] = strtolower($subtags[1]);
|
||||
}
|
||||
|
||||
$new_string .= '-' . $subtags[1];
|
||||
if ($num_subtags == 2) return $new_string;
|
||||
if ($num_subtags == 2) {
|
||||
return $new_string;
|
||||
}
|
||||
|
||||
// process all other subtags, index 2 and up
|
||||
for ($i = 2; $i < $num_subtags; $i++) {
|
||||
|
|
@ -63,11 +79,8 @@ class HTMLPurifier_AttrDef_Lang extends HTMLPurifier_AttrDef
|
|||
}
|
||||
$new_string .= '-' . $subtags[$i];
|
||||
}
|
||||
|
||||
return $new_string;
|
||||
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
// vim: et sw=4 sts=4
|
||||
|
|
@ -6,21 +6,41 @@
|
|||
class HTMLPurifier_AttrDef_Switch
|
||||
{
|
||||
|
||||
/**
|
||||
* @type string
|
||||
*/
|
||||
protected $tag;
|
||||
protected $withTag, $withoutTag;
|
||||
|
||||
/**
|
||||
* @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, $without_tag) {
|
||||
public function __construct($tag, $with_tag, $without_tag)
|
||||
{
|
||||
$this->tag = $tag;
|
||||
$this->withTag = $with_tag;
|
||||
$this->withoutTag = $without_tag;
|
||||
}
|
||||
|
||||
public function validate($string, $config, $context) {
|
||||
/**
|
||||
* @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);
|
||||
|
|
@ -28,7 +48,6 @@ class HTMLPurifier_AttrDef_Switch
|
|||
return $this->withTag->validate($string, $config, $context);
|
||||
}
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
// vim: et sw=4 sts=4
|
||||
|
|
@ -0,0 +1,21 @@
|
|||
<?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
|
||||
|
|
@ -7,31 +7,54 @@
|
|||
class HTMLPurifier_AttrDef_URI extends HTMLPurifier_AttrDef
|
||||
{
|
||||
|
||||
/**
|
||||
* @type HTMLPurifier_URIParser
|
||||
*/
|
||||
protected $parser;
|
||||
|
||||
/**
|
||||
* @type bool
|
||||
*/
|
||||
protected $embedsResource;
|
||||
|
||||
/**
|
||||
* @param $embeds_resource_resource Does the URI here result in an extra HTTP request?
|
||||
* @param bool $embeds_resource Does the URI here result in an extra HTTP request?
|
||||
*/
|
||||
public function __construct($embeds_resource = false) {
|
||||
public function __construct($embeds_resource = false)
|
||||
{
|
||||
$this->parser = new HTMLPurifier_URIParser();
|
||||
$this->embedsResource = (bool) $embeds_resource;
|
||||
$this->embedsResource = (bool)$embeds_resource;
|
||||
}
|
||||
|
||||
public function make($string) {
|
||||
$embeds = (bool) $string;
|
||||
/**
|
||||
* @param string $string
|
||||
* @return HTMLPurifier_AttrDef_URI
|
||||
*/
|
||||
public function make($string)
|
||||
{
|
||||
$embeds = ($string === 'embedded');
|
||||
return new HTMLPurifier_AttrDef_URI($embeds);
|
||||
}
|
||||
|
||||
public function validate($uri, $config, $context) {
|
||||
|
||||
if ($config->get('URI.Disable')) return false;
|
||||
/**
|
||||
* @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 ($uri === false) return false;
|
||||
if ($uri === false) {
|
||||
return false;
|
||||
}
|
||||
|
||||
// add embedded flag to context for validators
|
||||
$context->register('EmbeddedURI', $this->embedsResource);
|
||||
|
|
@ -41,23 +64,35 @@ class HTMLPurifier_AttrDef_URI extends HTMLPurifier_AttrDef
|
|||
|
||||
// generic validation
|
||||
$result = $uri->validate($config, $context);
|
||||
if (!$result) break;
|
||||
if (!$result) {
|
||||
break;
|
||||
}
|
||||
|
||||
// chained filtering
|
||||
$uri_def = $config->getDefinition('URI');
|
||||
$result = $uri_def->filter($uri, $config, $context);
|
||||
if (!$result) break;
|
||||
if (!$result) {
|
||||
break;
|
||||
}
|
||||
|
||||
// scheme-specific validation
|
||||
$scheme_obj = $uri->getSchemeObj($config, $context);
|
||||
if (!$scheme_obj) break;
|
||||
if ($this->embedsResource && !$scheme_obj->browsable) break;
|
||||
if (!$scheme_obj) {
|
||||
break;
|
||||
}
|
||||
if ($this->embedsResource && !$scheme_obj->browsable) {
|
||||
break;
|
||||
}
|
||||
$result = $scheme_obj->validate($uri, $config, $context);
|
||||
if (!$result) break;
|
||||
if (!$result) {
|
||||
break;
|
||||
}
|
||||
|
||||
// Post chained filtering
|
||||
$result = $uri_def->postFilter($uri, $config, $context);
|
||||
if (!$result) break;
|
||||
if (!$result) {
|
||||
break;
|
||||
}
|
||||
|
||||
// survived gauntlet
|
||||
$ok = true;
|
||||
|
|
@ -65,13 +100,12 @@ class HTMLPurifier_AttrDef_URI extends HTMLPurifier_AttrDef
|
|||
} while (false);
|
||||
|
||||
$context->destroy('EmbeddedURI');
|
||||
if (!$ok) return false;
|
||||
|
||||
if (!$ok) {
|
||||
return false;
|
||||
}
|
||||
// back to string
|
||||
return $uri->toString();
|
||||
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
// vim: et sw=4 sts=4
|
||||
|
|
@ -5,8 +5,11 @@ abstract class HTMLPurifier_AttrDef_URI_Email extends HTMLPurifier_AttrDef
|
|||
|
||||
/**
|
||||
* Unpacks a mailbox into its display-name and address
|
||||
* @param string $string
|
||||
* @return mixed
|
||||
*/
|
||||
function unpack($string) {
|
||||
public function unpack($string)
|
||||
{
|
||||
// needs to be implemented
|
||||
}
|
||||
|
||||
|
|
@ -7,15 +7,23 @@
|
|||
class HTMLPurifier_AttrDef_URI_Email_SimpleCheck extends HTMLPurifier_AttrDef_URI_Email
|
||||
{
|
||||
|
||||
public function validate($string, $config, $context) {
|
||||
/**
|
||||
* @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;
|
||||
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
|
||||
|
|
@ -0,0 +1,128 @@
|
|||
<?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') ? '_' : '';
|
||||
|
||||
// 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)?";
|
||||
// toplabel = alpha | alpha *( alphanum | "-" ) alphanum
|
||||
$toplabel = "$a($and*$an)?";
|
||||
// hostname = *( domainlabel "." ) toplabel [ "." ]
|
||||
if (preg_match("/^($domainlabel\.)*$toplabel\.?$/i", $string)) {
|
||||
return $string;
|
||||
}
|
||||
|
||||
// If we have Net_IDNA2 support, we can support IRIs by
|
||||
// punycoding them. (This is the most portable thing to do,
|
||||
// since otherwise we have to assume browsers support
|
||||
|
||||
if ($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('.', $new_parts);
|
||||
if (preg_match("/^($domainlabel\.)*$toplabel\.?$/i", $string)) {
|
||||
return $string;
|
||||
}
|
||||
} catch (Exception $e) {
|
||||
// XXX error reporting
|
||||
}
|
||||
}
|
||||
return false;
|
||||
}
|
||||
}
|
||||
|
||||
// vim: et sw=4 sts=4
|
||||
|
|
@ -8,32 +8,38 @@ class HTMLPurifier_AttrDef_URI_IPv4 extends HTMLPurifier_AttrDef
|
|||
{
|
||||
|
||||
/**
|
||||
* IPv4 regex, protected so that IPv6 can reuse it
|
||||
* IPv4 regex, protected so that IPv6 can reuse it.
|
||||
* @type string
|
||||
*/
|
||||
protected $ip4;
|
||||
|
||||
public function validate($aIP, $config, $context) {
|
||||
|
||||
if (!$this->ip4) $this->_loadRegex();
|
||||
|
||||
if (preg_match('#^' . $this->ip4 . '$#s', $aIP))
|
||||
{
|
||||
return $aIP;
|
||||
/**
|
||||
* @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() {
|
||||
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
|
||||
|
|
@ -0,0 +1,89 @@
|
|||
<?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
|
||||
|
|
@ -20,37 +20,41 @@ abstract class HTMLPurifier_AttrTransform
|
|||
/**
|
||||
* Abstract: makes changes to the attributes dependent on multiple values.
|
||||
*
|
||||
* @param $attr Assoc array of attributes, usually from
|
||||
* @param array $attr Assoc array of attributes, usually from
|
||||
* HTMLPurifier_Token_Tag::$attr
|
||||
* @param $config Mandatory HTMLPurifier_Config object.
|
||||
* @param $context Mandatory HTMLPurifier_Context object
|
||||
* @returns Processed attribute array.
|
||||
* @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 $attr Attribute array to process (passed by reference)
|
||||
* @param $css CSS to prepend
|
||||
* @param array &$attr Attribute array to process (passed by reference)
|
||||
* @param string $css CSS to prepend
|
||||
*/
|
||||
public function prependCSS(&$attr, $css) {
|
||||
public function prependCSS(&$attr, $css)
|
||||
{
|
||||
$attr['style'] = isset($attr['style']) ? $attr['style'] : '';
|
||||
$attr['style'] = $css . $attr['style'];
|
||||
}
|
||||
|
||||
/**
|
||||
* Retrieves and removes an attribute
|
||||
* @param $attr Attribute array to process (passed by reference)
|
||||
* @param $key Key of attribute to confiscate
|
||||
* @param array &$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[$key])) return null;
|
||||
public function confiscateAttr(&$attr, $key)
|
||||
{
|
||||
if (!isset($attr[$key])) {
|
||||
return null;
|
||||
}
|
||||
$value = $attr[$key];
|
||||
unset($attr[$key]);
|
||||
return $value;
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
// vim: et sw=4 sts=4
|
||||
|
|
@ -3,21 +3,26 @@
|
|||
/**
|
||||
* Pre-transform that changes proprietary background attribute to CSS.
|
||||
*/
|
||||
class HTMLPurifier_AttrTransform_Background extends HTMLPurifier_AttrTransform {
|
||||
|
||||
public function transform($attr, $config, $context) {
|
||||
|
||||
if (!isset($attr['background'])) return $attr;
|
||||
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 $attr;
|
||||
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
// vim: et sw=4 sts=4
|
||||
|
|
@ -8,12 +8,20 @@
|
|||
class HTMLPurifier_AttrTransform_BdoDir extends HTMLPurifier_AttrTransform
|
||||
{
|
||||
|
||||
public function transform($attr, $config, $context) {
|
||||
if (isset($attr['dir'])) return $attr;
|
||||
/**
|
||||
* @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 $attr;
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
// vim: et sw=4 sts=4
|
||||
|
|
@ -3,21 +3,26 @@
|
|||
/**
|
||||
* Pre-transform that changes deprecated bgcolor attribute to CSS.
|
||||
*/
|
||||
class HTMLPurifier_AttrTransform_BgColor extends HTMLPurifier_AttrTransform {
|
||||
|
||||
public function transform($attr, $config, $context) {
|
||||
|
||||
if (!isset($attr['bgcolor'])) return $attr;
|
||||
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
|
||||
|
|
@ -0,0 +1,47 @@
|
|||
<?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 $attr;
|
||||
}
|
||||
}
|
||||
|
||||
// vim: et sw=4 sts=4
|
||||
|
|
@ -3,16 +3,24 @@
|
|||
/**
|
||||
* Pre-transform that changes deprecated border attribute to CSS.
|
||||
*/
|
||||
class HTMLPurifier_AttrTransform_Border extends HTMLPurifier_AttrTransform {
|
||||
|
||||
public function transform($attr, $config, $context) {
|
||||
if (!isset($attr['border'])) return $attr;
|
||||
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
|
||||
|
|
@ -0,0 +1,68 @@
|
|||
<?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 $attr;
|
||||
}
|
||||
}
|
||||
|
||||
// vim: et sw=4 sts=4
|
||||
|
|
@ -11,11 +11,19 @@
|
|||
class HTMLPurifier_AttrTransform_ImgRequired extends HTMLPurifier_AttrTransform
|
||||
{
|
||||
|
||||
public function transform($attr, $config, $context) {
|
||||
|
||||
/**
|
||||
* @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 $attr;
|
||||
if ($config->get('Core.RemoveInvalidImg')) {
|
||||
return $attr;
|
||||
}
|
||||
$attr['src'] = $config->get('Attr.DefaultInvalidImage');
|
||||
$src = false;
|
||||
}
|
||||
|
|
@ -25,7 +33,7 @@ class HTMLPurifier_AttrTransform_ImgRequired extends HTMLPurifier_AttrTransform
|
|||
$alt = $config->get('Attr.DefaultImageAlt');
|
||||
if ($alt === null) {
|
||||
// truncate if the alt is too long
|
||||
$attr['alt'] = substr(basename($attr['src']),0,40);
|
||||
$attr['alt'] = substr(basename($attr['src']), 0, 40);
|
||||
} else {
|
||||
$attr['alt'] = $alt;
|
||||
}
|
||||
|
|
@ -33,11 +41,8 @@ class HTMLPurifier_AttrTransform_ImgRequired extends HTMLPurifier_AttrTransform
|
|||
$attr['alt'] = $config->get('Attr.DefaultInvalidImageAlt');
|
||||
}
|
||||
}
|
||||
|
||||
return $attr;
|
||||
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
// vim: et sw=4 sts=4
|
||||
|
|
@ -3,42 +3,59 @@
|
|||
/**
|
||||
* Pre-transform that changes deprecated hspace and vspace attributes to CSS
|
||||
*/
|
||||
class HTMLPurifier_AttrTransform_ImgSpace extends HTMLPurifier_AttrTransform {
|
||||
|
||||
class HTMLPurifier_AttrTransform_ImgSpace extends HTMLPurifier_AttrTransform
|
||||
{
|
||||
/**
|
||||
* @type string
|
||||
*/
|
||||
protected $attr;
|
||||
|
||||
/**
|
||||
* @type array
|
||||
*/
|
||||
protected $css = array(
|
||||
'hspace' => array('left', 'right'),
|
||||
'vspace' => array('top', 'bottom')
|
||||
);
|
||||
|
||||
public function __construct($attr) {
|
||||
/**
|
||||
* @param string $attr
|
||||
*/
|
||||
public function __construct($attr)
|
||||
{
|
||||
$this->attr = $attr;
|
||||
if (!isset($this->css[$attr])) {
|
||||
trigger_error(htmlspecialchars($attr) . ' is not valid space attribute');
|
||||
}
|
||||
}
|
||||
|
||||
public function transform($attr, $config, $context) {
|
||||
|
||||
if (!isset($attr[$this->attr])) return $attr;
|
||||
/**
|
||||
* @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 $attr;
|
||||
if (!isset($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
|
||||
|
|
@ -4,17 +4,31 @@
|
|||
* 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 {
|
||||
|
||||
class HTMLPurifier_AttrTransform_Input extends HTMLPurifier_AttrTransform
|
||||
{
|
||||
/**
|
||||
* @type HTMLPurifier_AttrDef_HTML_Pixels
|
||||
*/
|
||||
protected $pixels;
|
||||
|
||||
public function __construct() {
|
||||
public function __construct()
|
||||
{
|
||||
$this->pixels = new HTMLPurifier_AttrDef_HTML_Pixels();
|
||||
}
|
||||
|
||||
public function transform($attr, $config, $context) {
|
||||
if (!isset($attr['type'])) $t = 'text';
|
||||
else $t = strtolower($attr['type']);
|
||||
/**
|
||||
* @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']);
|
||||
}
|
||||
|
|
@ -23,8 +37,11 @@ class HTMLPurifier_AttrTransform_Input extends HTMLPurifier_AttrTransform {
|
|||
}
|
||||
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'] = $result;
|
||||
if ($result === false) {
|
||||
unset($attr['size']);
|
||||
} else {
|
||||
$attr['size'] = $result;
|
||||
}
|
||||
}
|
||||
if (isset($attr['src']) && $t !== 'image') {
|
||||
unset($attr['src']);
|
||||
|
|
@ -34,7 +51,6 @@ class HTMLPurifier_AttrTransform_Input extends HTMLPurifier_AttrTransform {
|
|||
}
|
||||
return $attr;
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
// vim: et sw=4 sts=4
|
||||
|
|
@ -8,9 +8,15 @@
|
|||
class HTMLPurifier_AttrTransform_Lang extends HTMLPurifier_AttrTransform
|
||||
{
|
||||
|
||||
public function transform($attr, $config, $context) {
|
||||
|
||||
$lang = isset($attr['lang']) ? $attr['lang'] : false;
|
||||
/**
|
||||
* @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 && $xml_lang === false) {
|
||||
|
|
@ -18,11 +24,8 @@ class HTMLPurifier_AttrTransform_Lang extends HTMLPurifier_AttrTransform
|
|||
} elseif ($xml_lang !== false) {
|
||||
$attr['lang'] = $xml_lang;
|
||||
}
|
||||
|
||||
return $attr;
|
||||
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
// vim: et sw=4 sts=4
|
||||
|
|
@ -0,0 +1,45 @@
|
|||
<?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
|
||||
|
|
@ -0,0 +1,33 @@
|
|||
<?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
|
||||
|
|
@ -0,0 +1,41 @@
|
|||
<?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
|
||||
|
|
@ -0,0 +1,52 @@
|
|||
<?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
|
||||
|
|
@ -2,9 +2,19 @@
|
|||
|
||||
class HTMLPurifier_AttrTransform_SafeEmbed extends HTMLPurifier_AttrTransform
|
||||
{
|
||||
/**
|
||||
* @type string
|
||||
*/
|
||||
public $name = "SafeEmbed";
|
||||
|
||||
public function transform($attr, $config, $context) {
|
||||
/**
|
||||
* @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';
|
||||
|
|
@ -0,0 +1,28 @@
|
|||
<?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
|
||||
|
|
@ -14,14 +14,30 @@
|
|||
*/
|
||||
class HTMLPurifier_AttrTransform_SafeParam extends HTMLPurifier_AttrTransform
|
||||
{
|
||||
/**
|
||||
* @type string
|
||||
*/
|
||||
public $name = "SafeParam";
|
||||
|
||||
/**
|
||||
* @type HTMLPurifier_AttrDef_URI
|
||||
*/
|
||||
private $uri;
|
||||
|
||||
public function __construct() {
|
||||
public function __construct()
|
||||
{
|
||||
$this->uri = new HTMLPurifier_AttrDef_URI(true); // embedded
|
||||
$this->wmode = new HTMLPurifier_AttrDef_Enum(array('window', 'opaque', 'transparent'));
|
||||
}
|
||||
|
||||
public function transform($attr, $config, $context) {
|
||||
/**
|
||||
* @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']) {
|
||||
|
|
@ -33,8 +49,15 @@ class HTMLPurifier_AttrTransform_SafeParam extends HTMLPurifier_AttrTransform
|
|||
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'] = 'window';
|
||||
$attr['value'] = $this->wmode->validate($attr['value'], $config, $context);
|
||||
break;
|
||||
case 'movie':
|
||||
case 'src':
|
||||
|
|
@ -5,7 +5,14 @@
|
|||
*/
|
||||
class HTMLPurifier_AttrTransform_ScriptRequired extends HTMLPurifier_AttrTransform
|
||||
{
|
||||
public function transform($attr, $config, $context) {
|
||||
/**
|
||||
* @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';
|
||||
}
|
||||
|
|
@ -0,0 +1,45 @@
|
|||
<?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
|
||||
|
|
@ -0,0 +1,27 @@
|
|||
<?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
|
||||
|
|
@ -6,7 +6,8 @@
|
|||
class HTMLPurifier_AttrTypes
|
||||
{
|
||||
/**
|
||||
* Lookup array of attribute string identifiers to concrete implementations
|
||||
* Lookup array of attribute string identifiers to concrete implementations.
|
||||
* @type HTMLPurifier_AttrDef[]
|
||||
*/
|
||||
protected $info = array();
|
||||
|
||||
|
|
@ -14,7 +15,15 @@ class HTMLPurifier_AttrTypes
|
|||
* Constructs the info array, supplying default implementations for attribute
|
||||
* types.
|
||||
*/
|
||||
public function __construct() {
|
||||
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();
|
||||
|
|
@ -29,6 +38,9 @@ class HTMLPurifier_AttrTypes
|
|||
$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();
|
||||
|
|
@ -44,32 +56,39 @@ class HTMLPurifier_AttrTypes
|
|||
$this->info['Number'] = new HTMLPurifier_AttrDef_Integer(false, false, true);
|
||||
}
|
||||
|
||||
private static function makeEnum($in)
|
||||
{
|
||||
return new HTMLPurifier_AttrDef_Clone(new HTMLPurifier_AttrDef_Enum(explode(',', $in)));
|
||||
}
|
||||
|
||||
/**
|
||||
* Retrieves a type
|
||||
* @param $type String type name
|
||||
* @return Object AttrDef for type
|
||||
* @param string $type String type name
|
||||
* @return HTMLPurifier_AttrDef Object AttrDef for type
|
||||
*/
|
||||
public function get($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 $string = '';
|
||||
if (strpos($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 $type String type name
|
||||
* @param $impl Object AttrDef for type
|
||||
* @param string $type String type name
|
||||
* @param HTMLPurifier_AttrDef $impl Object AttrDef for type
|
||||
*/
|
||||
public function set($type, $impl) {
|
||||
public function set($type, $impl)
|
||||
{
|
||||
$this->info[$type] = $impl;
|
||||
}
|
||||
}
|
||||
|
|
@ -9,17 +9,14 @@ class HTMLPurifier_AttrValidator
|
|||
{
|
||||
|
||||
/**
|
||||
* Validates the attributes of a token, returning a modified token
|
||||
* Validates the attributes of a token, mutating it as necessary.
|
||||
* that has valid tokens
|
||||
* @param $token Reference to token to validate. We require a reference
|
||||
* because the operation this class performs on the token are
|
||||
* not atomic, so the context CurrentToken to be updated
|
||||
* throughout
|
||||
* @param $config Instance of HTMLPurifier_Config
|
||||
* @param $context Instance of HTMLPurifier_Context
|
||||
* @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, $context) {
|
||||
|
||||
public function validateToken($token, $config, $context)
|
||||
{
|
||||
$definition = $config->getHTMLDefinition();
|
||||
$e =& $context->get('ErrorCollector', true);
|
||||
|
||||
|
|
@ -32,12 +29,15 @@ class HTMLPurifier_AttrValidator
|
|||
|
||||
// initialize CurrentToken if necessary
|
||||
$current_token =& $context->get('CurrentToken', true);
|
||||
if (!$current_token) $context->register('CurrentToken', $token);
|
||||
if (!$current_token) {
|
||||
$context->register('CurrentToken', $token);
|
||||
}
|
||||
|
||||
if (
|
||||
!$token instanceof HTMLPurifier_Token_Start &&
|
||||
if (!$token instanceof HTMLPurifier_Token_Start &&
|
||||
!$token instanceof HTMLPurifier_Token_Empty
|
||||
) return $token;
|
||||
) {
|
||||
return;
|
||||
}
|
||||
|
||||
// create alias to global definition array, see also $defs
|
||||
// DEFINITION CALL
|
||||
|
|
@ -51,7 +51,9 @@ class HTMLPurifier_AttrValidator
|
|||
foreach ($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, $attr);
|
||||
if ($attr != $o) {
|
||||
$e->send(E_NOTICE, 'AttrValidator: Attributes transformed', $o, $attr);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
|
|
@ -60,7 +62,9 @@ class HTMLPurifier_AttrValidator
|
|||
foreach ($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, $attr);
|
||||
if ($attr != $o) {
|
||||
$e->send(E_NOTICE, 'AttrValidator: Attributes transformed', $o, $attr);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
|
|
@ -77,7 +81,7 @@ class HTMLPurifier_AttrValidator
|
|||
foreach ($attr as $attr_key => $value) {
|
||||
|
||||
// call the definition
|
||||
if ( isset($defs[$attr_key]) ) {
|
||||
if (isset($defs[$attr_key])) {
|
||||
// there is a local definition defined
|
||||
if ($defs[$attr_key] === false) {
|
||||
// We've explicitly been told not to allow this element.
|
||||
|
|
@ -89,15 +93,19 @@ class HTMLPurifier_AttrValidator
|
|||
} else {
|
||||
// validate according to the element's definition
|
||||
$result = $defs[$attr_key]->validate(
|
||||
$value, $config, $context
|
||||
);
|
||||
$value,
|
||||
$config,
|
||||
$context
|
||||
);
|
||||
}
|
||||
} elseif ( isset($d_defs[$attr_key]) ) {
|
||||
} elseif (isset($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
|
||||
);
|
||||
$value,
|
||||
$config,
|
||||
$context
|
||||
);
|
||||
} else {
|
||||
// system never heard of the attribute? DELETE!
|
||||
$result = false;
|
||||
|
|
@ -107,7 +115,9 @@ class HTMLPurifier_AttrValidator
|
|||
if ($result === false || $result === null) {
|
||||
// this is a generic error message that should replaced
|
||||
// with more specific ones when possible
|
||||
if ($e) $e->send(E_ERROR, 'AttrValidator: Attribute removed');
|
||||
if ($e) {
|
||||
$e->send(E_ERROR, 'AttrValidator: Attribute removed');
|
||||
}
|
||||
|
||||
// remove the attribute
|
||||
unset($attr[$attr_key]);
|
||||
|
|
@ -137,7 +147,9 @@ class HTMLPurifier_AttrValidator
|
|||
foreach ($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, $attr);
|
||||
if ($attr != $o) {
|
||||
$e->send(E_NOTICE, 'AttrValidator: Attributes transformed', $o, $attr);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
|
|
@ -145,14 +157,18 @@ class HTMLPurifier_AttrValidator
|
|||
foreach ($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, $attr);
|
||||
if ($attr != $o) {
|
||||
$e->send(E_NOTICE, 'AttrValidator: Attributes transformed', $o, $attr);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
$token->attr = $attr;
|
||||
|
||||
// destroy CurrentToken if we made it ourselves
|
||||
if (!$current_token) $context->destroy('CurrentToken');
|
||||
if (!$current_token) {
|
||||
$context->destroy('CurrentToken');
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
124
library/ezyang/htmlpurifier/library/HTMLPurifier/Bootstrap.php
Normal file
124
library/ezyang/htmlpurifier/library/HTMLPurifier/Bootstrap.php
Normal file
|
|
@ -0,0 +1,124 @@
|
|||
<?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
|
||||
|
|
@ -0,0 +1,474 @@
|
|||
<?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'))
|
||||
)
|
||||
);
|
||||
$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['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'));
|
||||
|
||||
}
|
||||
|
||||
/**
|
||||
* @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
|
||||
|
|
@ -1,48 +1,52 @@
|
|||
<?php
|
||||
|
||||
/**
|
||||
* Defines allowed child nodes and validates tokens against it.
|
||||
* 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;
|
||||
|
||||
/**
|
||||
* Bool that indicates whether or not an empty array of children is okay
|
||||
* 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
|
||||
* 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) {
|
||||
public function getAllowedElements($config)
|
||||
{
|
||||
return $this->elements;
|
||||
}
|
||||
|
||||
/**
|
||||
* Validates nodes according to definition and returns modification.
|
||||
*
|
||||
* @param $tokens_of_children Array of HTMLPurifier_Token
|
||||
* @param $config HTMLPurifier_Config object
|
||||
* @param $context HTMLPurifier_Context object
|
||||
* @return bool true to leave nodes as is
|
||||
* @return bool false to remove parent node
|
||||
* @return array of replacement child tokens
|
||||
* @param HTMLPurifier_Node[] $children Array of HTMLPurifier_Node
|
||||
* @param HTMLPurifier_Config $config HTMLPurifier_Config object
|
||||
* @param HTMLPurifier_Context $context HTMLPurifier_Context object
|
||||
* @return bool|array true to leave nodes as is, false to remove parent node, array of replacement children
|
||||
*/
|
||||
abstract public function validateChildren($tokens_of_children, $config, $context);
|
||||
abstract public function validateChildren($children, $config, $context);
|
||||
}
|
||||
|
||||
// vim: et sw=4 sts=4
|
||||
|
|
@ -14,33 +14,52 @@ 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 $inline List of elements to allow when inline.
|
||||
* @param $block List of elements to allow when block.
|
||||
* @param array $inline List of elements to allow when inline.
|
||||
* @param array $block List of elements to allow when block.
|
||||
*/
|
||||
public function __construct($inline, $block) {
|
||||
public function __construct($inline, $block)
|
||||
{
|
||||
$this->inline = new HTMLPurifier_ChildDef_Optional($inline);
|
||||
$this->block = new HTMLPurifier_ChildDef_Optional($block);
|
||||
$this->block = new HTMLPurifier_ChildDef_Optional($block);
|
||||
$this->elements = $this->block->elements;
|
||||
}
|
||||
|
||||
public function validateChildren($tokens_of_children, $config, $context) {
|
||||
/**
|
||||
* @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(
|
||||
$tokens_of_children, $config, $context);
|
||||
$children,
|
||||
$config,
|
||||
$context
|
||||
);
|
||||
} else {
|
||||
return $this->inline->validateChildren(
|
||||
$tokens_of_children, $config, $context);
|
||||
$children,
|
||||
$config,
|
||||
$context
|
||||
);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
|
@ -8,28 +8,42 @@
|
|||
*/
|
||||
class HTMLPurifier_ChildDef_Custom extends HTMLPurifier_ChildDef
|
||||
{
|
||||
public $type = 'custom';
|
||||
public $allow_empty = false;
|
||||
/**
|
||||
* Allowed child pattern as defined by the DTD
|
||||
* @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
|
||||
* @private
|
||||
* 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) {
|
||||
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() {
|
||||
protected function _compileRegex()
|
||||
{
|
||||
$raw = str_replace(' ', '', $this->dtd_regex);
|
||||
if ($raw{0} != '(') {
|
||||
$raw = "($raw)";
|
||||
|
|
@ -57,33 +71,31 @@ class HTMLPurifier_ChildDef_Custom extends HTMLPurifier_ChildDef
|
|||
|
||||
$this->_pcre_regex = $reg;
|
||||
}
|
||||
public function validateChildren($tokens_of_children, $config, $context) {
|
||||
|
||||
/**
|
||||
* @param HTMLPurifier_Node[] $children
|
||||
* @param HTMLPurifier_Config $config
|
||||
* @param HTMLPurifier_Context $context
|
||||
* @return bool
|
||||
*/
|
||||
public function validateChildren($children, $config, $context)
|
||||
{
|
||||
$list_of_children = '';
|
||||
$nesting = 0; // depth into the nest
|
||||
foreach ($tokens_of_children as $token) {
|
||||
if (!empty($token->is_whitespace)) continue;
|
||||
|
||||
$is_child = ($nesting == 0); // direct
|
||||
|
||||
if ($token instanceof HTMLPurifier_Token_Start) {
|
||||
$nesting++;
|
||||
} elseif ($token instanceof HTMLPurifier_Token_End) {
|
||||
$nesting--;
|
||||
}
|
||||
|
||||
if ($is_child) {
|
||||
$list_of_children .= $token->name . ',';
|
||||
foreach ($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.'$/',
|
||||
'/^,?' . $this->_pcre_regex . '$/',
|
||||
$list_of_children
|
||||
);
|
||||
|
||||
return (bool) $okay;
|
||||
return (bool)$okay;
|
||||
}
|
||||
}
|
||||
|
||||
|
|
@ -9,10 +9,28 @@
|
|||
*/
|
||||
class HTMLPurifier_ChildDef_Empty extends HTMLPurifier_ChildDef
|
||||
{
|
||||
/**
|
||||
* @type bool
|
||||
*/
|
||||
public $allow_empty = true;
|
||||
|
||||
/**
|
||||
* @type string
|
||||
*/
|
||||
public $type = 'empty';
|
||||
public function __construct() {}
|
||||
public function validateChildren($tokens_of_children, $config, $context) {
|
||||
|
||||
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();
|
||||
}
|
||||
}
|
||||
|
|
@ -0,0 +1,86 @@
|
|||
<?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;
|
||||
}
|
||||
|
||||
// the new set of children
|
||||
$result = array();
|
||||
|
||||
// a little sanity check to make sure it's not ALL whitespace
|
||||
$all_whitespace = true;
|
||||
|
||||
$current_li = false;
|
||||
|
||||
foreach ($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 === false) {
|
||||
$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
|
||||
|
|
@ -0,0 +1,45 @@
|
|||
<?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
|
||||
|
|
@ -0,0 +1,118 @@
|
|||
<?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
|
||||
|
|
@ -0,0 +1,110 @@
|
|||
<?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
|
||||
|
|
@ -0,0 +1,224 @@
|
|||
<?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
|
||||
920
library/ezyang/htmlpurifier/library/HTMLPurifier/Config.php
Normal file
920
library/ezyang/htmlpurifier/library/HTMLPurifier/Config.php
Normal file
|
|
@ -0,0 +1,920 @@
|
|||
<?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 = '4.7.0';
|
||||
|
||||
/**
|
||||
* 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; $i++) {
|
||||
// XXX this is not correct on some versions of HTML Purifier
|
||||
if ($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
|
||||
|
|
@ -3,21 +3,24 @@
|
|||
/**
|
||||
* Configuration definition, defines directives and their defaults.
|
||||
*/
|
||||
class HTMLPurifier_ConfigSchema {
|
||||
|
||||
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:
|
||||
* Definition of the directives.
|
||||
* The structure of this is:
|
||||
*
|
||||
* array(
|
||||
* 'Namespace' => array(
|
||||
|
|
@ -44,29 +47,43 @@ class HTMLPurifier_ConfigSchema {
|
|||
* 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
|
||||
*/
|
||||
static protected $singleton;
|
||||
protected static $singleton;
|
||||
|
||||
public function __construct() {
|
||||
public function __construct()
|
||||
{
|
||||
$this->defaultPlist = new HTMLPurifier_PropertyList();
|
||||
}
|
||||
|
||||
/**
|
||||
* Unserializes the default ConfigSchema.
|
||||
* @return HTMLPurifier_ConfigSchema
|
||||
*/
|
||||
public static function makeFromSerial() {
|
||||
return unserialize(file_get_contents(HTMLPURIFIER_PREFIX . '/HTMLPurifier/ConfigSchema/schema.ser'));
|
||||
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) {
|
||||
public static function instance($prototype = null)
|
||||
{
|
||||
if ($prototype !== null) {
|
||||
HTMLPurifier_ConfigSchema::$singleton = $prototype;
|
||||
} elseif (HTMLPurifier_ConfigSchema::$singleton === null || $prototype === true) {
|
||||
|
|
@ -80,17 +97,19 @@ class HTMLPurifier_ConfigSchema {
|
|||
* @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 $namespace Namespace the directive is in
|
||||
* @param $name Key of directive
|
||||
* @param $default Default value of directive
|
||||
* @param $type Allowed type of the directive. See
|
||||
* @param string $key Name of directive
|
||||
* @param mixed $default Default value of directive
|
||||
* @param string $type Allowed type of the directive. See
|
||||
* HTMLPurifier_DirectiveDef::$type for allowed values
|
||||
* @param $allow_null Whether or not to allow null values
|
||||
* @param bool $allow_null Whether or not to allow null values
|
||||
*/
|
||||
public function add($key, $default, $type, $allow_null) {
|
||||
public function add($key, $default, $type, $allow_null)
|
||||
{
|
||||
$obj = new stdclass();
|
||||
$obj->type = is_int($type) ? $type : HTMLPurifier_VarParser::$types[$type];
|
||||
if ($allow_null) $obj->allow_null = true;
|
||||
if ($allow_null) {
|
||||
$obj->allow_null = true;
|
||||
}
|
||||
$this->info[$key] = $obj;
|
||||
$this->defaults[$key] = $default;
|
||||
$this->defaultPlist->set($key, $default);
|
||||
|
|
@ -101,11 +120,11 @@ class HTMLPurifier_ConfigSchema {
|
|||
*
|
||||
* Directive value aliases are convenient for developers because it lets
|
||||
* them set a directive to several values and get the same result.
|
||||
* @param $namespace Directive's namespace
|
||||
* @param $name Name of Directive
|
||||
* @param $aliases Hash of aliased values to the real alias
|
||||
* @param string $key Name of Directive
|
||||
* @param array $aliases Hash of aliased values to the real alias
|
||||
*/
|
||||
public function addValueAliases($key, $aliases) {
|
||||
public function addValueAliases($key, $aliases)
|
||||
{
|
||||
if (!isset($this->info[$key]->aliases)) {
|
||||
$this->info[$key]->aliases = array();
|
||||
}
|
||||
|
|
@ -118,22 +137,21 @@ class HTMLPurifier_ConfigSchema {
|
|||
* Defines a set of allowed values for a directive.
|
||||
* @warning This is slightly different from the corresponding static
|
||||
* method definition.
|
||||
* @param $namespace Namespace of directive
|
||||
* @param $name Name of directive
|
||||
* @param $allowed Lookup array of allowed values
|
||||
* @param string $key Name of directive
|
||||
* @param array $allowed Lookup array of allowed values
|
||||
*/
|
||||
public function addAllowedValues($key, $allowed) {
|
||||
public function addAllowedValues($key, $allowed)
|
||||
{
|
||||
$this->info[$key]->allowed = $allowed;
|
||||
}
|
||||
|
||||
/**
|
||||
* Defines a directive alias for backwards compatibility
|
||||
* @param $namespace
|
||||
* @param $name Directive that will be aliased
|
||||
* @param $new_namespace
|
||||
* @param $new_name Directive that the alias will be to
|
||||
* @param string $key Directive that will be aliased
|
||||
* @param string $new_key Directive that the alias will be to
|
||||
*/
|
||||
public function addAlias($key, $new_key) {
|
||||
public function addAlias($key, $new_key)
|
||||
{
|
||||
$obj = new stdclass;
|
||||
$obj->key = $new_key;
|
||||
$obj->isAlias = true;
|
||||
|
|
@ -143,7 +161,8 @@ class HTMLPurifier_ConfigSchema {
|
|||
/**
|
||||
* Replaces any stdclass that only has the type property with type integer.
|
||||
*/
|
||||
public function postProcess() {
|
||||
public function postProcess()
|
||||
{
|
||||
foreach ($this->info as $key => $v) {
|
||||
if (count((array) $v) == 1) {
|
||||
$this->info[$key] = $v->type;
|
||||
|
|
@ -152,7 +171,6 @@ class HTMLPurifier_ConfigSchema {
|
|||
}
|
||||
}
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
// vim: et sw=4 sts=4
|
||||
|
|
@ -7,7 +7,12 @@
|
|||
class HTMLPurifier_ConfigSchema_Builder_ConfigSchema
|
||||
{
|
||||
|
||||
public function build($interchange) {
|
||||
/**
|
||||
* @param HTMLPurifier_ConfigSchema_Interchange $interchange
|
||||
* @return HTMLPurifier_ConfigSchema
|
||||
*/
|
||||
public function build($interchange)
|
||||
{
|
||||
$schema = new HTMLPurifier_ConfigSchema();
|
||||
foreach ($interchange->directives as $d) {
|
||||
$schema->add(
|
||||
|
|
@ -38,7 +43,6 @@ class HTMLPurifier_ConfigSchema_Builder_ConfigSchema
|
|||
$schema->postProcess();
|
||||
return $schema;
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
// vim: et sw=4 sts=4
|
||||
|
|
@ -7,10 +7,21 @@
|
|||
class HTMLPurifier_ConfigSchema_Builder_Xml extends XMLWriter
|
||||
{
|
||||
|
||||
/**
|
||||
* @type HTMLPurifier_ConfigSchema_Interchange
|
||||
*/
|
||||
protected $interchange;
|
||||
|
||||
/**
|
||||
* @type string
|
||||
*/
|
||||
private $namespace;
|
||||
|
||||
protected function writeHTMLDiv($html) {
|
||||
/**
|
||||
* @param string $html
|
||||
*/
|
||||
protected function writeHTMLDiv($html)
|
||||
{
|
||||
$this->startElement('div');
|
||||
|
||||
$purifier = HTMLPurifier::getInstance();
|
||||
|
|
@ -21,12 +32,23 @@ class HTMLPurifier_ConfigSchema_Builder_Xml extends XMLWriter
|
|||
$this->endElement(); // div
|
||||
}
|
||||
|
||||
protected function export($var) {
|
||||
if ($var === array()) return 'array()';
|
||||
/**
|
||||
* @param mixed $var
|
||||
* @return string
|
||||
*/
|
||||
protected function export($var)
|
||||
{
|
||||
if ($var === array()) {
|
||||
return 'array()';
|
||||
}
|
||||
return var_export($var, true);
|
||||
}
|
||||
|
||||
public function build($interchange) {
|
||||
/**
|
||||
* @param HTMLPurifier_ConfigSchema_Interchange $interchange
|
||||
*/
|
||||
public function build($interchange)
|
||||
{
|
||||
// global access, only use as last resort
|
||||
$this->interchange = $interchange;
|
||||
|
||||
|
|
@ -39,19 +61,26 @@ class HTMLPurifier_ConfigSchema_Builder_Xml extends XMLWriter
|
|||
$this->buildDirective($directive);
|
||||
}
|
||||
|
||||
if ($this->namespace) $this->endElement(); // namespace
|
||||
if ($this->namespace) {
|
||||
$this->endElement();
|
||||
} // namespace
|
||||
|
||||
$this->endElement(); // configdoc
|
||||
$this->flush();
|
||||
}
|
||||
|
||||
public function buildDirective($directive) {
|
||||
|
||||
/**
|
||||
* @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) $this->endElement(); // namespace
|
||||
if ($this->namespace) {
|
||||
$this->endElement();
|
||||
} // namespace
|
||||
$this->namespace = $directive->id->getRootNamespace();
|
||||
$this->startElement('namespace');
|
||||
$this->writeAttribute('id', $this->namespace);
|
||||
|
|
@ -64,43 +93,52 @@ class HTMLPurifier_ConfigSchema_Builder_Xml extends XMLWriter
|
|||
$this->writeElement('name', $directive->id->getDirective());
|
||||
|
||||
$this->startElement('aliases');
|
||||
foreach ($directive->aliases as $alias) $this->writeElement('alias', $alias->toString());
|
||||
foreach ($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);
|
||||
$this->endElement(); // allowed
|
||||
if ($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->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(); // 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->writeElement('version', $directive->deprecatedVersion);
|
||||
$this->writeElement('use', $directive->deprecatedUse->toString());
|
||||
$this->endElement(); // deprecated
|
||||
}
|
||||
|
||||
$this->startElement('description');
|
||||
$this->writeHTMLDiv($directive->description);
|
||||
$this->writeHTMLDiv($directive->description);
|
||||
$this->endElement(); // description
|
||||
|
||||
$this->endElement(); // directive
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
// vim: et sw=4 sts=4
|
||||
|
|
@ -10,18 +10,23 @@ 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) {
|
||||
public function addDirective($directive)
|
||||
{
|
||||
if (isset($this->directives[$i = $directive->id->toString()])) {
|
||||
throw new HTMLPurifier_ConfigSchema_Exception("Cannot redefine directive '$i'");
|
||||
}
|
||||
|
|
@ -32,11 +37,11 @@ class HTMLPurifier_ConfigSchema_Interchange
|
|||
* Convenience function to perform standard validation. Throws exception
|
||||
* on failed validation.
|
||||
*/
|
||||
public function validate() {
|
||||
public function validate()
|
||||
{
|
||||
$validator = new HTMLPurifier_ConfigSchema_Validator();
|
||||
return $validator->validate($this);
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
// vim: et sw=4 sts=4
|
||||
|
|
@ -7,71 +7,83 @@ class HTMLPurifier_ConfigSchema_Interchange_Directive
|
|||
{
|
||||
|
||||
/**
|
||||
* ID of directive, instance of HTMLPurifier_ConfigSchema_Interchange_Id.
|
||||
* ID of directive.
|
||||
* @type HTMLPurifier_ConfigSchema_Interchange_Id
|
||||
*/
|
||||
public $id;
|
||||
|
||||
/**
|
||||
* String type, e.g. 'integer' or 'istring'.
|
||||
* 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;
|
||||
|
||||
/**
|
||||
* Boolean whether or not null is allowed as a value.
|
||||
* 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).
|
||||
* 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,
|
||||
* 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, is an instance
|
||||
* of HTMLPurifier_ConfigSchema_Interchange_Id. Null if not deprecated.
|
||||
* 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
|
||||
|
|
@ -6,32 +6,53 @@
|
|||
class HTMLPurifier_ConfigSchema_Interchange_Id
|
||||
{
|
||||
|
||||
/**
|
||||
* @type string
|
||||
*/
|
||||
public $key;
|
||||
|
||||
public function __construct($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() {
|
||||
public function toString()
|
||||
{
|
||||
return $this->key;
|
||||
}
|
||||
|
||||
public function getRootNamespace() {
|
||||
/**
|
||||
* @return string
|
||||
*/
|
||||
public function getRootNamespace()
|
||||
{
|
||||
return substr($this->key, 0, strpos($this->key, "."));
|
||||
}
|
||||
|
||||
public function getDirective() {
|
||||
/**
|
||||
* @return string
|
||||
*/
|
||||
public function getDirective()
|
||||
{
|
||||
return substr($this->key, strpos($this->key, ".") + 1);
|
||||
}
|
||||
|
||||
public static function make($id) {
|
||||
/**
|
||||
* @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
|
||||
|
|
@ -5,21 +5,39 @@ class HTMLPurifier_ConfigSchema_InterchangeBuilder
|
|||
|
||||
/**
|
||||
* Used for processing DEFAULT, nothing else.
|
||||
* @type HTMLPurifier_VarParser
|
||||
*/
|
||||
protected $varParser;
|
||||
|
||||
public function __construct($varParser = null) {
|
||||
/**
|
||||
* @param HTMLPurifier_VarParser $varParser
|
||||
*/
|
||||
public function __construct($varParser = null)
|
||||
{
|
||||
$this->varParser = $varParser ? $varParser : new HTMLPurifier_VarParser_Native();
|
||||
}
|
||||
|
||||
public static function buildFromDirectory($dir = null) {
|
||||
$builder = new HTMLPurifier_ConfigSchema_InterchangeBuilder();
|
||||
/**
|
||||
* @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, $dir);
|
||||
}
|
||||
|
||||
public function buildDir($interchange, $dir = null) {
|
||||
if (!$dir) $dir = HTMLPURIFIER_PREFIX . '/HTMLPurifier/ConfigSchema/schema';
|
||||
/**
|
||||
* @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 = $info['name'];
|
||||
|
|
@ -39,24 +57,30 @@ class HTMLPurifier_ConfigSchema_InterchangeBuilder
|
|||
foreach ($files as $file) {
|
||||
$this->buildFile($interchange, $dir . '/' . $file);
|
||||
}
|
||||
|
||||
return $interchange;
|
||||
}
|
||||
|
||||
public function buildFile($interchange, $file) {
|
||||
/**
|
||||
* @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) )
|
||||
new HTMLPurifier_StringHash($parser->parseFile($file))
|
||||
);
|
||||
}
|
||||
|
||||
/**
|
||||
* Builds an interchange object based on a hash.
|
||||
* @param $interchange HTMLPurifier_ConfigSchema_Interchange object to build
|
||||
* @param $hash HTMLPurifier_ConfigSchema_StringHash source data
|
||||
* @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, $hash) {
|
||||
public function build($interchange, $hash)
|
||||
{
|
||||
if (!$hash instanceof HTMLPurifier_StringHash) {
|
||||
$hash = new HTMLPurifier_StringHash($hash);
|
||||
}
|
||||
|
|
@ -75,7 +99,13 @@ class HTMLPurifier_ConfigSchema_InterchangeBuilder
|
|||
$this->_findUnused($hash);
|
||||
}
|
||||
|
||||
public function buildDirective($interchange, $hash) {
|
||||
/**
|
||||
* @param HTMLPurifier_ConfigSchema_Interchange $interchange
|
||||
* @param HTMLPurifier_StringHash $hash
|
||||
* @throws HTMLPurifier_ConfigSchema_Exception
|
||||
*/
|
||||
public function buildDirective($interchange, $hash)
|
||||
{
|
||||
$directive = new HTMLPurifier_ConfigSchema_Interchange_Directive();
|
||||
|
||||
// These are required elements:
|
||||
|
|
@ -84,7 +114,9 @@ class HTMLPurifier_ConfigSchema_InterchangeBuilder
|
|||
|
||||
if (isset($hash['TYPE'])) {
|
||||
$type = explode('/', $hash->offsetGet('TYPE'));
|
||||
if (isset($type[1])) $directive->typeAllowsNull = true;
|
||||
if (isset($type[1])) {
|
||||
$directive->typeAllowsNull = true;
|
||||
}
|
||||
$directive->type = $type[0];
|
||||
} else {
|
||||
throw new HTMLPurifier_ConfigSchema_Exception("TYPE in directive hash '$id' not defined");
|
||||
|
|
@ -92,7 +124,11 @@ class HTMLPurifier_ConfigSchema_InterchangeBuilder
|
|||
|
||||
if (isset($hash['DEFAULT'])) {
|
||||
try {
|
||||
$directive->default = $this->varParser->parse($hash->offsetGet('DEFAULT'), $directive->type, $directive->typeAllowsNull);
|
||||
$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'");
|
||||
}
|
||||
|
|
@ -139,34 +175,45 @@ class HTMLPurifier_ConfigSchema_InterchangeBuilder
|
|||
|
||||
/**
|
||||
* Evaluates an array PHP code string without array() wrapper
|
||||
* @param string $contents
|
||||
*/
|
||||
protected function evalArray($contents) {
|
||||
return eval('return array('. $contents .');');
|
||||
protected function evalArray($contents)
|
||||
{
|
||||
return eval('return array(' . $contents . ');');
|
||||
}
|
||||
|
||||
/**
|
||||
* Converts an array list into a lookup array.
|
||||
* @param array $array
|
||||
* @return array
|
||||
*/
|
||||
protected function lookup($array) {
|
||||
protected function lookup($array)
|
||||
{
|
||||
$ret = array();
|
||||
foreach ($array as $val) $ret[$val] = true;
|
||||
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) {
|
||||
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 $hash Instance of ConfigSchema_StringHash to check.
|
||||
* @param HTMLPurifier_StringHash $hash Hash to check.
|
||||
*/
|
||||
protected function _findUnused($hash) {
|
||||
protected function _findUnused($hash)
|
||||
{
|
||||
$accessed = $hash->getAccessed();
|
||||
foreach ($hash as $k => $v) {
|
||||
if (!isset($accessed[$k])) {
|
||||
|
|
@ -174,7 +221,6 @@ class HTMLPurifier_ConfigSchema_InterchangeBuilder
|
|||
}
|
||||
}
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
// vim: et sw=4 sts=4
|
||||
|
|
@ -12,36 +12,48 @@ class HTMLPurifier_ConfigSchema_Validator
|
|||
{
|
||||
|
||||
/**
|
||||
* Easy to access global objects.
|
||||
* @type HTMLPurifier_ConfigSchema_Interchange
|
||||
*/
|
||||
protected $interchange, $aliases;
|
||||
protected $interchange;
|
||||
|
||||
/**
|
||||
* @type array
|
||||
*/
|
||||
protected $aliases;
|
||||
|
||||
/**
|
||||
* Context-stack to provide easy to read error messages.
|
||||
* @type array
|
||||
*/
|
||||
protected $context = array();
|
||||
|
||||
/**
|
||||
* HTMLPurifier_VarParser to test default's type.
|
||||
* to test default's type.
|
||||
* @type HTMLPurifier_VarParser
|
||||
*/
|
||||
protected $parser;
|
||||
|
||||
public function __construct() {
|
||||
public function __construct()
|
||||
{
|
||||
$this->parser = new HTMLPurifier_VarParser();
|
||||
}
|
||||
|
||||
/**
|
||||
* Validates a fully-formed interchange object. Throws an
|
||||
* HTMLPurifier_ConfigSchema_Exception if there's a problem.
|
||||
* Validates a fully-formed interchange object.
|
||||
* @param HTMLPurifier_ConfigSchema_Interchange $interchange
|
||||
* @return bool
|
||||
*/
|
||||
public function validate($interchange) {
|
||||
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 '$id'");
|
||||
if ($i != $id) {
|
||||
$this->error(false, "Integrity violation: key '$i' does not match internal id '$id'");
|
||||
}
|
||||
$this->validateDirective($directive);
|
||||
}
|
||||
return true;
|
||||
|
|
@ -49,8 +61,10 @@ class HTMLPurifier_ConfigSchema_Validator
|
|||
|
||||
/**
|
||||
* Validates a HTMLPurifier_ConfigSchema_Interchange_Id object.
|
||||
* @param HTMLPurifier_ConfigSchema_Interchange_Id $id
|
||||
*/
|
||||
public function validateId($id) {
|
||||
public function validateId($id)
|
||||
{
|
||||
$id_string = $id->toString();
|
||||
$this->context[] = "id '$id_string'";
|
||||
if (!$id instanceof HTMLPurifier_ConfigSchema_Interchange_Id) {
|
||||
|
|
@ -67,8 +81,10 @@ class HTMLPurifier_ConfigSchema_Validator
|
|||
|
||||
/**
|
||||
* Validates a HTMLPurifier_ConfigSchema_Interchange_Directive object.
|
||||
* @param HTMLPurifier_ConfigSchema_Interchange_Directive $d
|
||||
*/
|
||||
public function validateDirective($d) {
|
||||
public function validateDirective($d)
|
||||
{
|
||||
$id = $d->id->toString();
|
||||
$this->context[] = "directive '$id'";
|
||||
$this->validateId($d->id);
|
||||
|
|
@ -108,9 +124,13 @@ class HTMLPurifier_ConfigSchema_Validator
|
|||
/**
|
||||
* 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($d->allowed)) return;
|
||||
public function validateDirectiveAllowed($d)
|
||||
{
|
||||
if (is_null($d->allowed)) {
|
||||
return;
|
||||
}
|
||||
$this->with($d, 'allowed')
|
||||
->assertNotEmpty()
|
||||
->assertIsLookup(); // handled by InterchangeBuilder
|
||||
|
|
@ -119,7 +139,9 @@ class HTMLPurifier_ConfigSchema_Validator
|
|||
}
|
||||
$this->context[] = 'allowed';
|
||||
foreach ($d->allowed as $val => $x) {
|
||||
if (!is_string($val)) $this->error("value $val", 'must be a string');
|
||||
if (!is_string($val)) {
|
||||
$this->error("value $val", 'must be a string');
|
||||
}
|
||||
}
|
||||
array_pop($this->context);
|
||||
}
|
||||
|
|
@ -127,15 +149,23 @@ class HTMLPurifier_ConfigSchema_Validator
|
|||
/**
|
||||
* 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($d->valueAliases)) return;
|
||||
public function validateDirectiveValueAliases($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 (!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");
|
||||
}
|
||||
|
|
@ -155,8 +185,10 @@ class HTMLPurifier_ConfigSchema_Validator
|
|||
/**
|
||||
* Extra validation if $aliases member variable of
|
||||
* HTMLPurifier_ConfigSchema_Interchange_Directive is defined.
|
||||
* @param HTMLPurifier_ConfigSchema_Interchange_Directive $d
|
||||
*/
|
||||
public function validateDirectiveAliases($d) {
|
||||
public function validateDirectiveAliases($d)
|
||||
{
|
||||
$this->with($d, 'aliases')
|
||||
->assertIsArray(); // handled by InterchangeBuilder
|
||||
$this->context[] = 'aliases';
|
||||
|
|
@ -180,27 +212,37 @@ class HTMLPurifier_ConfigSchema_Validator
|
|||
/**
|
||||
* 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, $member) {
|
||||
protected function with($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());
|
||||
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 . ' ' . $msg));
|
||||
}
|
||||
|
||||
/**
|
||||
* Returns a formatted context string.
|
||||
* @return string
|
||||
*/
|
||||
protected function getFormattedContext() {
|
||||
protected function getFormattedContext()
|
||||
{
|
||||
return implode(' in ', array_reverse($this->context));
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
// vim: et sw=4 sts=4
|
||||
|
|
@ -0,0 +1,130 @@
|
|||
<?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
|
||||
Binary file not shown.
Some files were not shown because too many files have changed in this diff Show more
Loading…
Add table
Add a link
Reference in a new issue