chore(release): 4.18.0 [skip ci]

# [4.18.0](https://github.com/ezyang/htmlpurifier/compare/v4.17.0...v4.18.0) (2024-11-01)

### Bug Fixes

* Adjust Core.AllowHostnameUnderscore to consider that "_" is defined as Unreserved Characters in RFC 3986 ([#406](https://github.com/ezyang/htmlpurifier/issues/406)) ([d9fbef8](d9fbef8e27))
* Avoid a deprecated error when the attribute name is numeric and DirectLex is used ([#412](https://github.com/ezyang/htmlpurifier/issues/412)) ([f0fbf51](f0fbf51098))
* checking that node has property name ([#399](https://github.com/ezyang/htmlpurifier/issues/399)) ([9ca5a36](9ca5a3687b))
* Ignore conditional comments ([#401](https://github.com/ezyang/htmlpurifier/issues/401)) ([4828fdf](4828fdf45a))
* Support PHP 8.4 ([#396](https://github.com/ezyang/htmlpurifier/issues/396)) ([92da247](92da2473ff))
* undefined array key warning ([#419](https://github.com/ezyang/htmlpurifier/issues/419)) ([01be377](01be377f93))

### Features

* Add allowfullscreen attr for iframe ([#411](https://github.com/ezyang/htmlpurifier/issues/411)) ([70754a2](70754a2533))
* add directive for removing blank nodes ([#404](https://github.com/ezyang/htmlpurifier/issues/404)) ([c9d60c9](c9d60c96d7))
* Add support for CSS aspect-ratio ([#408](https://github.com/ezyang/htmlpurifier/issues/408)) ([93bee73](93bee73349))
* Allow universal CSS values for all properties ([#410](https://github.com/ezyang/htmlpurifier/issues/410)) ([9723267](972326785d))

.gitattributes

@@ -1 +1,23 @@
-configdoc/usage.xml -crlf
+/.gitattributes export-ignore
+/.github export-ignore
+/.gitignore export-ignore
+/art export-ignore
+/benchmarks export-ignore
+/configdoc export-ignore
+/configdoc/usage.xml -crlf
+/docs export-ignore
+/Doxyfile export-ignore
+/extras export-ignore
+/INSTALL* export-ignore
+/maintenance export-ignore
+/NEWS export-ignore
+/package.php export-ignore
+/plugins export-ignore
+/phpdoc.ini export-ignore
+/smoketests export-ignore
+/test-* export-ignore
+/tests export-ignore
+/TODO export-ignore
+/update-for-release export-ignore
+/WYSIWYG export-ignore
+/release.config.js export-ignore

.github/workflows/ci.yml

@@ -0,0 +1,36 @@
+name: ci
+
+on:
+  push:
+  pull_request:
+
+jobs:
+  linux_tests:
+    runs-on: ubuntu-latest
+    strategy:
+      fail-fast: true
+      matrix:
+        php: ['5.6', '7.0', '7.1', '7.2', '7.3', '7.4', '8.0', '8.1', '8.2', '8.3', '8.4']
+
+    name: PHP ${{ matrix.php }}
+
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v3
+
+      - name: Setup PHP
+        uses: shivammathur/setup-php@v2
+        with:
+          php-version: ${{ matrix.php }}
+          tools: composer:v2
+          ini-values: error_reporting=E_ALL
+          extensions: iconv, bcmath, tidy, mbstring, intl
+
+      - name: Install dependencies
+        run: composer install
+
+      - name: Configure simpletest
+        run: cp test-settings.sample.php test-settings.php
+
+      - name: Execute Unit tests
+        run: php tests/index.php

.github/workflows/lint-pr.yml

@@ -0,0 +1,19 @@
+name: "Lint PR"
+
+on:
+  pull_request_target:
+    types:
+      - opened
+      - edited
+      - synchronize
+
+jobs:
+  main:
+    name: Validate PR title
+
+    runs-on: ubuntu-latest
+
+    steps:
+      - uses: amannn/action-semantic-pull-request@v4
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

.github/workflows/release.yml

@@ -0,0 +1,29 @@
+name: release
+
+on:
+  workflow_dispatch:
+
+jobs:
+  release:
+    runs-on: ubuntu-latest
+
+    name: Release
+
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v2
+
+      - name: Setup PHP
+        uses: shivammathur/setup-php@v2
+        with:
+          php-version: 8.2
+
+      - name: Run automated release process with semantic-release
+        uses: cycjimmy/semantic-release-action@v4
+        with:
+          extra_plugins: |
+            @semantic-release/changelog
+            @semantic-release/git
+            @semantic-release/exec
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

.gitignore

@@ -1,5 +1,7 @@
+tags
 conf/
 test-settings.php
+config-schema.php
 library/HTMLPurifier/DefinitionCache/Serializer/*/
 library/standalone/
 library/HTMLPurifier.standalone.php
@@ -16,3 +18,11 @@ docs/doxygen*
 *.phpt.php
 *.phpt.skip.php
 *.htmlt.ini
+*.patch
+/*.php
+vendor
+composer.lock
+*.rej
+*.orig
+*.bak
+core

Doxyfile

@@ -31,7 +31,7 @@ PROJECT_NAME           = HTMLPurifier
 # This could be handy for archiving the generated documentation or
 # if some version control system is used.
 
-PROJECT_NUMBER         = 3.3.0
+PROJECT_NUMBER         = 4.18.0
 
 # The OUTPUT_DIRECTORY tag is used to specify the (relative or absolute)
 # base path where the generated documentation will be put.

FOCUS

@@ -1,13 +0,0 @@
-7 - Major bugfixes
-
-[ Appendix A: Release focus IDs ]
-0 - N/A
-1 - Initial freshmeat announcement
-2 - Documentation
-3 - Code cleanup
-4 - Minor feature enhancements
-5 - Major feature enhancements
-6 - Minor bugfixes
-7 - Major bugfixes
-8 - Minor security fixes
-9 - Major security fixes

INSTALL

@@ -15,9 +15,8 @@ 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 PHP 5 and PHP 7, and is actively tested from PHP 5.3
+and up. It has no core dependencies with other libraries.
 
 These optional extensions can enhance the capabilities of HTML Purifier:
 
@@ -25,6 +24,13 @@ These optional extensions can enhance the capabilities of HTML Purifier:
     * bcmath : Used for unit conversion and imagecrash protection
     * tidy   : Used for pretty-printing HTML
 
+These optional libraries can enhance the capabilities of HTML Purifier:
+
+    * CSSTidy : Clean CSS stylesheets using %Core.ExtractStyleBlocks
+        Note: You should use the modernized fork of CSSTidy available
+        at https://github.com/Cerdic/CSSTidy
+    * Net_IDNA2 (PEAR) : IRI support using %Core.EnableIDNA
+        Note: This is not necessary for PHP 5.3 or later
 
 ---------------------------------------------------------------------------
 2.  Reconnaissance
@@ -95,31 +101,6 @@ Autoload compatibility
     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
@@ -132,11 +113,6 @@ Autoload compatibility
 
             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
 ----------------------
@@ -198,9 +174,7 @@ For advanced users
         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).
+    You can do these operations by yourself, if you like.
 
 
 ---------------------------------------------------------------------------
@@ -231,12 +205,12 @@ 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 */);
+    $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');
+    $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
@@ -251,7 +225,7 @@ reason, I do not include the solution in this document).
 For those of you using HTML 4.01 Transitional, you can disable
 XHTML output like this:
 
-    $config->set('HTML', 'Doctype', 'HTML 4.01 Transitional');
+    $config->set('HTML.Doctype', 'HTML 4.01 Transitional');
 
 Other supported doctypes include:
 
@@ -277,14 +251,14 @@ are, respectively, %HTML.Allowed, %URI.MakeAbsolute and %URI.Base, and
 %AutoFormat.AutoParagraph. The %Namespace.Directive naming convention
 translates to:
 
-    $config->set('Namespace', 'Directive', $value);
+    $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);
+    $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);
 
 
 ---------------------------------------------------------------------------
@@ -300,11 +274,9 @@ 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:
+to group:
 
-    chmod -R 0777 HTMLPurifier/DefinitionCache/Serializer
+    chmod -R 0775 HTMLPurifier/DefinitionCache/Serializer
 
 You can also chmod files via your FTP client; this option
 is usually accessible by right clicking the corresponding directory and
@@ -318,11 +290,11 @@ 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);
+    $config->set('Core.DefinitionCache', null);
 
 Or move the cache directory somewhere else (no trailing slash):
 
-    $config->set('Cache', 'SerializerPath', '/home/user/absolute/path');
+    $config->set('Cache.SerializerPath', '/home/user/absolute/path');
 
 
 ---------------------------------------------------------------------------
@@ -330,11 +302,6 @@ Or move the cache directory somewhere else (no trailing slash):
 
 The interface is mind-numbingly simple:
 
-    $purifier = new HTMLPurifier();
-    $clean_html = $purifier->purify( $dirty_html );
-
-...or, if you're using the configuration object:
-
     $purifier = new HTMLPurifier($config);
     $clean_html = $purifier->purify( $dirty_html );
 
@@ -353,7 +320,8 @@ If your website is in UTF-8 and XHTML Transitional, use this code:
 <?php
     require_once '/path/to/htmlpurifier/library/HTMLPurifier.auto.php';
 
-    $purifier = new HTMLPurifier();
+    $config = HTMLPurifier_Config::createDefault();
+    $purifier = new HTMLPurifier($config);
     $clean_html = $purifier->purify($dirty_html);
 ?>
 
@@ -363,8 +331,8 @@ If your website is in a different encoding or doctype, use this code:
     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
+    $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);

INSTALL.fr.utf8

@@ -1,69 +1,60 @@
-
+
 Installation
     Comment installer HTML Purifier
 
-Attention: Ce document a encode en UTF-8. Si les lettres avec les accents
-est essoreuse, prenez un mieux editeur de texte.
-
-À L'Aide: Je ne suis pas un diseur natif de français. Si vous trouvez une
-erreur dans ce document, racontez-moi! Merci.
-
-
-L'installation de HTML Purifier est trés simple, parce qu'il ne doit pas
-la configuration.  Dans le pied de de document, les utilisateurs
-impatient peuvent trouver le code, mais je recommande que vous lisez
-ce document pour quelques choses.
+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 dans PHP 5. PHP 5.0.5 est le dernier
-version que je le testais.  Il ne dépend de les autre librairies.
+HTML Purifier fonctionne avec PHP 5. PHP 5.3 est la dernière version testée.
+Il ne dépend pas d'autres librairies.
 
-Les extensions optionnel est iconv (en général déjà installer) et
-tidy (répandu aussi). Si vous utilisez UTF-8 et ne voulez pas
-l'indentation, vous pouvez utiliser HTML Purifier sans ces extensions.
+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 librarie
+2.  Inclure la librairie
 
-Utilisez:
+Quand vous devez l'utilisez, incluez le :
 
-    require_once '/path/to/library/HTMLPurifier.auto.php';
+    require_once('/path/to/library/HTMLPurifier.auto.php');
 
-...quand vous devez utiliser HTML Purifier (ne inclure pas quand vous
-ne devez pas, parce que HTML Purifier est trés grand.)
+Ne pas l'inclure si ce n'est pas nécessaire, car HTML Purifier est lourd.
 
-HTML Purifier utilise 'autoload'. Si vous avez définu la fonction
-__autoload, vous doivez ajoute cet programme:
+HTML Purifier utilise "autoload". Si vous avez défini la fonction __autoload,
+vous devez ajouter cette fonction :
 
     spl_autoload_register('__autoload')
 
-Plus d'information est dans le document 'INSTALL'.
+Plus d'informations dans le document "INSTALL".
 
+3.  Installation rapide
 
-3.   Installation vite
-
-Si votre site web est en UTF-8 et XHTML Transitional, utilisez:
+Si votre site Web est en UTF-8 et XHTML Transitional, utilisez :
 
 <?php
-    require_once '/path/to/htmlpurifier/library/HTMLPurifier.auto.php';
-
+    require_once('/path/to/htmlpurifier/library/HTMLPurifier.auto.php');
     $purificateur = new HTMLPurifier();
-    $html_propre = $purificateur->purify($html_salle);
+    $html_propre = $purificateur->purify($html_a_purifier);
 ?>
 
-Sinon, utilisez:
+Sinon, utilisez :
 
 <?php
-    require_once '/path/to/htmlpurifier/library/HTMLPurifier.auto.php';
-
-    $config = HTMLPurifier_Config::createDefault();
-    $config->set('Core', 'Encoding', 'ISO-8859-1'); //remplacez avec votre encoding
-    $config->set('Core', 'XHTML', true); //remplacez avec false si HTML 4.01
+    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_salle);
+    $html_propre = $purificateur->purify($html_a_purifier);
 ?>
 
+
     vim: et sw=4 sts=4

NEWS

@@ -1,3 +1,46 @@
+# [4.18.0](https://github.com/ezyang/htmlpurifier/compare/v4.17.0...v4.18.0) (2024-11-01)
+
+
+### Bug Fixes
+
+* Adjust Core.AllowHostnameUnderscore to consider that "_" is defined as Unreserved Characters in RFC 3986 ([#406](https://github.com/ezyang/htmlpurifier/issues/406)) ([d9fbef8](https://github.com/ezyang/htmlpurifier/commit/d9fbef8e27f6a0848a8987a8534351de98eb0fa1))
+* Avoid a deprecated error when the attribute name is numeric and DirectLex is used ([#412](https://github.com/ezyang/htmlpurifier/issues/412)) ([f0fbf51](https://github.com/ezyang/htmlpurifier/commit/f0fbf510981b27fc03168efdb17d6bff48f521af))
+* checking that node has property name ([#399](https://github.com/ezyang/htmlpurifier/issues/399)) ([9ca5a36](https://github.com/ezyang/htmlpurifier/commit/9ca5a3687bd2e6e42ed9d5199b2cfb1dbd6dbdc2))
+* Ignore conditional comments ([#401](https://github.com/ezyang/htmlpurifier/issues/401)) ([4828fdf](https://github.com/ezyang/htmlpurifier/commit/4828fdf45a93eeeacfcbcc855f96f9a7e6b4ed44))
+* Support PHP 8.4 ([#396](https://github.com/ezyang/htmlpurifier/issues/396)) ([92da247](https://github.com/ezyang/htmlpurifier/commit/92da2473ffbb3ed5e894560d4166b1ca8032aeb3))
+* undefined array key warning ([#419](https://github.com/ezyang/htmlpurifier/issues/419)) ([01be377](https://github.com/ezyang/htmlpurifier/commit/01be377f93654fad4d3fbc8c81779f14316eaecf))
+
+
+### Features
+
+* Add allowfullscreen attr for iframe ([#411](https://github.com/ezyang/htmlpurifier/issues/411)) ([70754a2](https://github.com/ezyang/htmlpurifier/commit/70754a253342f67a67425cfa81029db3a5c1bd28))
+* add directive for removing blank nodes ([#404](https://github.com/ezyang/htmlpurifier/issues/404)) ([c9d60c9](https://github.com/ezyang/htmlpurifier/commit/c9d60c96d799c02bc357c88a49f422034b6914fd))
+* Add support for CSS aspect-ratio ([#408](https://github.com/ezyang/htmlpurifier/issues/408)) ([93bee73](https://github.com/ezyang/htmlpurifier/commit/93bee733497a098b65daf5910f1c435d347860a4))
+* Allow universal CSS values for all properties ([#410](https://github.com/ezyang/htmlpurifier/issues/410)) ([9723267](https://github.com/ezyang/htmlpurifier/commit/972326785d201b81e1095bc296b99bbcfa8c7fd4))
+
+# [4.17.0](https://github.com/ezyang/htmlpurifier/compare/v4.16.0...v4.17.0) (2023-11-17)
+
+
+### Bug Fixes
+
+* CSSTidy ImportantComments not handled properly ([#359](https://github.com/ezyang/htmlpurifier/issues/359)) ([78a9b4d](https://github.com/ezyang/htmlpurifier/commit/78a9b4d0dae8bce9a70e4e7e551bf51e9a23706d))
+* fix CI ([#361](https://github.com/ezyang/htmlpurifier/issues/361)) ([9ec687c](https://github.com/ezyang/htmlpurifier/commit/9ec687c904a1fe66a5395d22c50f7043e045d1d3))
+* Invalid scheme check in Attr.TargetBlank ([#363](https://github.com/ezyang/htmlpurifier/issues/363)) ([0176ef4](https://github.com/ezyang/htmlpurifier/commit/0176ef4bb6f57103fdcb60a802603e60e81ee93e))
+* semantic release ([#339](https://github.com/ezyang/htmlpurifier/issues/339)) ([d82f3d9](https://github.com/ezyang/htmlpurifier/commit/d82f3d996a0d9b0f23364946d9a14408c1ad72c5))
+* semantic release ([#341](https://github.com/ezyang/htmlpurifier/issues/341)) ([e55fead](https://github.com/ezyang/htmlpurifier/commit/e55fead09f39430d30f48438f06e7bc2326efc94)), closes [#339](https://github.com/ezyang/htmlpurifier/issues/339)
+* Support for locales using decimal separators other than . (dot) ([#372](https://github.com/ezyang/htmlpurifier/issues/372)) ([43f49ac](https://github.com/ezyang/htmlpurifier/commit/43f49ac9a51b81dfd07d3bc8dcfc5ec5637a5e3b))
+
+
+### Features
+
+* Add support for all text-decoration properties ([#360](https://github.com/ezyang/htmlpurifier/issues/360)) ([2d775c0](https://github.com/ezyang/htmlpurifier/commit/2d775c01874e2f676ba1a2d9fe69b47c2a823061))
+* Allows commas to be included in tel URI ([#389](https://github.com/ezyang/htmlpurifier/issues/389)) ([ec92490](https://github.com/ezyang/htmlpurifier/commit/ec924901392f088d334622f806b9449b17b75d7b)), closes [#388](https://github.com/ezyang/htmlpurifier/issues/388)
+
+
+### Reverts
+
+* Revert "fix: semantic release (#339)" (#340) ([3e83215](https://github.com/ezyang/htmlpurifier/commit/3e832152a6173f880c6495a3ab2b0e5235e253a6)), closes [#339](https://github.com/ezyang/htmlpurifier/issues/339) [#340](https://github.com/ezyang/htmlpurifier/issues/340)
+
 NEWS ( CHANGELOG and HISTORY )                                     HTMLPurifier
 |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
 
@@ -9,6 +52,434 @@ NEWS ( CHANGELOG and HISTORY )                                     HTMLPurifier
     . Internal change
 ==========================
 
+4.15.0, released 2022-09-18
+! PHP 8.1 and 8.2 support, esp. fixes for deprecation warnings.  A joint effort
+  by David Rans, Tim Düsterhus, Kieran and John Flatness.
+! Allow contenteditable="false" (#336), contributed by Kieran.
+- Replace PHP 8.1 deprecated utf8_ functions with mbstring (#326),
+  contributed by John Flatness.
+- Enhanced composer suggestions with extensions (#317), contributed by
+  func0der.
+
+4.14.0, released 2021-12-24
+! Add "background-size" support (#289), contributed by Václav Smítal
+! Transform deprecated width attribute when tidying HTML, contributed by
+  Kieran.
+- PHP 8 support, contributed by Maksims Sļotovs.
+- Improved PHP 7.3 compatibility, contributed by kishor.
+- Avoid spurious magic quotes notice in PHP 7.4.  Thanks
+  Jasper Zonneveld for the fix.
+- Do not remove thead from table even if there are no tbody/tr (#264).
+  Thanks Marcus Artner for the fix.
+- Fix "Parameter must be an array or an object that implements
+  Countable" (#285)".  Thanks Kieran for this fix.
+. Fix unnecessary reference assignment, handling behavior change from
+  PHP5 and PHP7.  Thanks Arkadiusz Biczewski for the fix.
+
+4.13.0, released 2020-06-28
+! Add %HTML.Forms directive, which lets you accept forms in user
+  HTML without requiring full %HTML.Trusted.  Note that forms can
+  be (trivially) used to setup phishing; e.g., an attacker can
+  use CSS absolute positioning to overlay a form on top of a login
+  element, so please be sure to use this with care!   Fixes #213.
+  Thanks Mateusz Turcza for contributing this feature.
+! tr@bgcolor attribute is now supported.  Thanks Kieran Brahney
+  for this enhancement.
+- Further improvements to PHP 7.4 support, contributed by Witold
+  Wasiczko and Eloy Lafuente.
+- Fix PSR-0 compatibility.  Thanks Jordi Boggiano for contributing
+  part of this fix.
+- Fix bug with purifyArray where it doesn't work on empty arrays.
+  Thanks Fräntz Miccoli for the fix.
+- Reduce amount of maintenance scripts included in distribution
+  packages.  Thanks Sergei Morozov for this patch.
+- Remove leading zeros unless if it is only a zero, fixes #239.  Thanks
+  lubomirbartos for this fix.
+- Correct type hinting of maybeGet*, fixes #240.   Thanks Anders Jenbo
+  for this fix.
+
+4.12.0, released 2019-10-27
+! PHP 7.4 is supported, thank you Witold Wasiczko, Mateuz Turcza and
+  Edi Modrić
+- PHPDocs for HTMLModule::addElement() and Bool attr are fixed (thanks
+  Mateusz)
+
+4.11.0, released 2019-07-14
+# SafeScripting now matches case-sensitively against its whitelist (previously it was
+  case-insensitive.)  Thanks Dimitri Gritsajuk <gritsajuk.dimitri@gmail.com>
+  for reporting.
+! New directive %Core.AllowParseManyTags which allows parsing of many nested tags.
+  Thanks M. Suzuki <msuzuki1986@gmail.com> for contributing the patch.
+! purifyArray now supports multidimensional arrays.  Thanks
+  Sandro Miguel Marques <sandromiguel@sandromiguel.com> for contributing this patch.
+! initial and inherit settings available for width, height, and the min-/max-
+  versions thereof.  Thanks Michael Kliewe <info@phpgansta.de> for contributing
+  this patch.
+! More color names are supported.  Thanks Daijobou for contributing.
+- Compatibility fixes for PHP 7.3, including new CI for PHP 7.3
+  (thank you Lukas Neumann <lksnmnn@gmail.com>) and removal of
+  reserved words in our constants (thanks Darko Hrgovic <darko@darkodev.com>
+- Compatibility fixes for HHVM.  Thanks Mateusz Turcza for contributing
+  this fix.
+- HTML Purifier now never defines __autoload, fixing #196.  Thanks
+  Michael Kliewe for reporting.
+- In some situations, Config.php would report an undefined index: class
+  error; this has been fixed.  Thanks DiLong Fa for contributing
+  this fix.
+- We no longer produce <script /> tags; we always explicitly write
+  out the open and close tag.  Thanks Dimitri Gritsajuk
+  <gritsajuk.dimitri@gmail.com> for contributing this fix.
+- Better compatibility when IDNA constants are not present.  Thanks
+  Mateusz Turcza <xemlock@gmail.com> for contributing this fix.
+
+4.10.0, released 2018-02-22
+# PHP 5.3 is no longer officially supported by HTML Purifier
+  (we did not specifically break support, but we are no longer
+  testing on PHP 5.3)
+! Relative CSS length units are now supported
+- A few PHP 7.2 compatibility fixes, thanks John Flatness
+  <john@zerocrates.org>
+- Improve portability with old versions of libxml which don't
+  support accessing the data of a node
+- IDNA2008 is now used for converting domains to ASCII, fixing
+  some rather strange bugs with international domains
+- Fix race condition resulting in E_WARNING when creating
+  directories with Serializer
+
+4.9.3, released 2017-06-02
+- Workaround PHP 7.1 infinite loop when opcode cache is enabled.
+  Thanks @Xiphin (#134, #135)
+- Don't use autoloader when testing for DOMDocument.  Hypothetically,
+  this could cause your install to start using DirectLex if you had
+  previously been monkeypatching in a custom, autoloaded implementation
+  of DOMDocument.  Don't do that.  Thanks @Izumi-kun (#130)
+
+4.9.2, released 2017-03-12
+- Fixes PHP 5.3 compatibility
+- Fix breakage when decoding decimal entities.  Thanks @rybakit (#129)
+
+4.9.1, released 2017-03-08
+! %URI.DefaultScheme can now be set to null, in which case
+  all relative paths are removed.
+! New CSS properties: min-width, max-width, min-height, max-height (#94)
+! Transparency (rgba) and hsl/hsla supported where color CSS is present.
+  Thanks @fxbt for contributing the patch. (#118)
+- When idn_to_ascii is defined, we might accept malformed
+  hostnames.  Apply validation to the result in such cases.
+- Close directory when done in Serializer DefinitionCache (#100)
+- Deleted some asserts to avoid linters from choking (#97)
+- Rework Serializer cache behavior to avoid chmod'ing if possible (#32)
+- Embedded semicolons in strings in CSS are now handled correctly!
+- We accidentally dropped certain Unicode characters if there was
+  one or more invalid characters.  This has been fixed, thanks
+  to mpyw <ryosuke_i_628@yahoo.co.jp>
+- Fix for "Don't truncate upon encountering </div> when using DOMLex"
+  caused a regression with HTML 4.01 Strict parsing with libxml 2.9.1
+  (and maybe later versions, but known OK with libxml 2.9.4).  The
+  fix is to go about handling truncation a bit more cleverly so that
+  we can wrap with divs (sidestepping the bug) but slurping out the
+  rest of the text in case it ran off the end.  (#78)
+- Fix PREG_BACKTRACK_LIMIT_ERROR in HTMLPurifier_Filter_ExtractStyle.
+  Thanks @breathbath for contributing the report and fix (#120)
+- Fix entity decoding algorithm to be more conservative about
+  decoding entities that are missing trailing semicolon.
+  To get old behavior, set %Core.LegacyEntityDecoder to true.
+  (#119)
+- Workaround libxml bug when HTML tags are embedded inside
+  script tags.  To disable workaround set %Core.AggressivelyRemoveScript
+  to false. (#83)
+# By default, when a link has a target attribute associated
+  with it, we now also add rel="noopener" in order to
+  prevent the new window from being able to overwrite
+  the original frame.  To disable this protection,
+  set %HTML.TargetNoopener to FALSE.
+
+4.9.0 was cut on Git but never properly released; when we did the
+real release we decided to skip this version number.
+
+4.8.0, released 2016-07-16
+# By default, when a link has a target attribute associated
+  with it, we now also add rel="noreferrer" in order to
+  prevent the new window from being able to overwrite
+  the original frame.  To disable this protection,
+  set %HTML.TargetNoreferrer to FALSE.
+! Full PHP 7 compatibility, the test suite is ALL GO.
+! %CSS.AllowDuplicates permits duplicate CSS properties.
+! Support for 'tel' URIs.
+! Partial support for 'border-radius' properties when %CSS.AllowProprietary is true.
+  The slash syntax, i.e., 'border-radius: 2em 1em 4em / 0.5em 3em' is not
+  yet supported.
+! %Attr.ID.HTML5 turns on HTML5-style ID handling.
+- alt truncation could result in malformed UTF-8 sequence. Don't
+  truncate.  Thanks Brandon Farber for reporting.
+- Linkify regex is smarter, based off of Gruber's regex.
+- IDNA supported natively on PHP 5.3 and later.
+- Non all-numeric top-level names (e.g., foo.1f, 1f) are now
+  allowed.
+- Minor bounds error fix to squash a PHP 7 notice.
+- Support non-/tmp temporary directories for data:// validation
+- Give a better error message when a user attempts to allow
+  ul/ol without allowing li.
+- On some versions of PHP, the Serializer DefinitionCache could
+  infinite loop when the directory exists but is not listable. (#49)
+- Don't match for <body> inside comments with
+  %Core.ConvertDocumentToFragment. (#67)
+- SafeObject is now less case sensitive. (#57)
+- AutoFormat.RemoveEmpty.Predicate now correctly renders in
+  web form. (#85)
+
+4.7.0, released 2015-08-04
+# opacity is now considered a "tricky" CSS property rather than a
+  proprietary one.
+! %AutoFormat.RemoveEmpty.Predicate for specifying exactly when
+  an element should be considered "empty" (maybe preserve if it
+  has attributes), and modify iframe support so that the iframe
+  is removed if it is missing a src attribute.  Thanks meeva for
+  reporting.
+- Don't truncate upon encountering </div> when using DOMLex.  Thanks
+  Myrto Christina for finally convincing me to fix this.
+- Update YouTube filter for new code.
+- Fix parsing of rgb() values with spaces in them for 'border'
+  attribute.
+- Don't remove foo="" attributes if foo is a boolean attribute.  Thanks
+  valME for reporting.
+
+4.6.0, released 2013-11-30
+# Secure URI munge hashing algorithm has changed to hash_hmac("sha256", $url, $secret).
+  Please update any verification scripts you may have.
+# URI parsing algorithm was made more strict, so only prefixes which
+  looks like schemes will actually be schemes.  Thanks
+  Michael Gusev <mgusev@sugarcrm.com> for fixing.
+# %Core.EscapeInvalidChildren is no longer supported, and no longer does
+  anything.
+! New directive %Core.AllowHostnameUnderscore which allows underscores
+  in hostnames.
+- Eliminate quadratic behavior in DOMLex by using a proper queue.
+  Thanks Ole Laursen for noticing this.
+- Rewritten MakeWellFormed/FixNesting implementation eliminates quadratic
+  behavior in the rest of the purificaiton pipeline.  Thanks Chedburn
+  Networks for sponsoring this work.
+- Made Linkify URL parser a bit less permissive, so that non-breaking
+  spaces and commas are not included as part of URL.  Thanks nAS for fixing.
+- Fix some bad interactions with %HTML.Allowed and injectors.  Thanks
+  David Hirtz for reporting.
+- Fix infinite loop in DirectLex. Thanks Ashar Javed (@soaj1664ashar)
+  for reporting.
+
+4.5.0, released 2013-02-17
+# Fix bug where stacked attribute transforms clobber each other;
+  this also means it's no longer possible to override attribute
+  transforms in later modules.  No internal code was using this
+  but this may break some clients.
+# We now use SHA-1 to identify cached definitions, instead of MD5.
+! Support display:inline-block
+! Support for more white-space CSS values.
+! Permit underscores in font families
+! Support for page-break-* CSS3 properties when proprietary properties
+  are enabled.
+! New directive %Core.DisableExcludes; can be set to 'true' to turn off
+  SGML excludes checking.  If HTML Purifier is removing too much text
+  and you don't care about full standards compliance, try setting this to
+  'true'.
+- Use prepend for SPL autoloading on PHP 5.3 and later.
+- Fix bug with nofollow transform when pre-existing rel exists.
+- Fix bug where background:url() always gets lower-cased
+  (but not background-image:url())
+- Fix bug with non lower-case color names in HTML
+- Fix bug where data URI validation doesn't remove temporary files.
+  Thanks Javier Marín Ros <javiermarinros@gmail.com> for reporting.
+- Don't remove certain empty tags on RemoveEmpty.
+
+4.4.0, released 2012-01-18
+# Removed PEARSax3 handler.
+# URI.Munge now munges URIs inside the same host that go from https
+  to http.  Reported by Neike Taika-Tessaro.
+# Core.EscapeNonASCIICharacters now always transforms entities to
+  entities, even if target encoding is UTF-8.
+# Tighten up selector validation in ExtractStyleBlocks.
+  Non-syntactically valid selectors are now rejected, along with
+  some of the more obscure ones such as attribute selectors, the
+  :lang pseudoselector, and anything not in CSS2.1.  Furthermore,
+  ID and class selectors now work properly with the relevant
+  configuration attributes.  Also, mute errors when parsing CSS
+  with CSS Tidy.  Reported by Mario Heiderich and Norman Hippert.
+! Added support for 'scope' attribute on tables.
+! Added %HTML.TargetBlank, which adds target="blank" to all outgoing links.
+! Properly handle sub-lists directly nested inside of lists in
+  a standards compliant way, by moving them into the preceding <li>
+! Added %HTML.AllowedComments and %HTML.AllowedCommentsRegexp for
+  limited allowed comments in untrusted situations.
+! Implement iframes, and allow them to be used in untrusted mode with
+  %HTML.SafeIframe and %URI.SafeIframeRegexp.  Thanks Bradley M. Froehle
+  <brad.froehle@gmail.com> for submitting an initial version of the patch.
+! The Forms module now works properly for transitional doctypes.
+! Added support for internationalized domain names. You need the PEAR
+  Net_IDNA2 module to be in your path; if it is installed, ensure the
+  class can be loaded and then set %Core.EnableIDNA to true.
+- Color keywords are now case insensitive.  Thanks Yzmir Ramirez
+  <yramirez-htmlpurifier@adicio.com> for reporting.
+- Explicitly initialize anonModule variable to null.
+- Do not duplicate nofollow if already present.  Thanks 178
+  for reporting.
+- Do not add nofollow if hostname matches our current host.  Thanks 178
+  for reporting, and Neike Taika-Tessaro for helping diagnose.
+- Do not unset parser variable; this fixes intermittent serialization
+  problems.  Thanks Neike Taika-Tessaro for reporting, bill
+  <10010tiger@gmail.com> for diagnosing.
+- Fix iconv truncation bug, where non-UTF-8 target encodings see
+  output truncated after around 8000 characters.  Thanks Jörg Ludwig
+  <joerg.ludwig@iserv.eu> for reporting.
+- Fix broken table content model for XHTML1.1 (and also earlier
+  versions, although the W3C validator doesn't catch those violations).
+  Thanks GlitchMr <glitch.mr@gmail.com> for reporting.
+
+4.3.0, released 2011-03-27
+# Fixed broken caching of customized raw definitions, but requires an
+  API change.  The old API still works but will emit a warning,
+  see http://htmlpurifier.org/docs/enduser-customize.html#optimized
+  for how to upgrade your code.
+# Protect against Internet Explorer innerHTML behavior by specially
+  treating attributes with backticks but no angled brackets, quotes or
+  spaces.  This constitutes a slight semantic change, which can be
+  reverted using %Output.FixInnerHTML.  Reported by Neike Taika-Tessaro
+  and Mario Heiderich.
+# Protect against cssText/innerHTML by restricting allowed characters
+  used in fonts further than mandated by the specification and encoding
+  some extra special characters in URLs.  Reported by Neike
+  Taika-Tessaro and Mario Heiderich.
+! Added %HTML.Nofollow to add rel="nofollow" to external links.
+! More types of SPL autoloaders allowed on later versions of PHP.
+! Implementations for position, top, left, right, bottom, z-index
+  when %CSS.Trusted is on.
+! Add %Cache.SerializerPermissions option for custom serializer
+  directory/file permissions
+! Fix longstanding bug in Flash support for non-IE browsers, and
+  allow more wmode attributes.
+! Add %CSS.AllowedFonts to restrict permissible font names.
+- Switch to an iterative traversal of the DOM, which prevents us
+  from running out of stack space for deeply nested documents.
+  Thanks Maxim Krizhanovsky for contributing a patch.
+- Make removal of conditional IE comments ungreedy; thanks Bernd
+  for reporting.
+- Escape CDATA before removing Internet Explorer comments.
+- Fix removal of id attributes under certain conditions by ensuring
+  armor attributes are preserved when recreating tags.
+- Check if schema.ser was corrupted.
+- Check if zend.ze1_compatibility_mode is on, and error out if it is.
+  This safety check is only done for HTMLPurifier.auto.php; if you
+  are using standalone or the specialized includes files, you're
+  expected to know what you're doing.
+- Stop repeatedly writing the cache file after I'm done customizing a
+  raw definition.  Reported by ajh.
+- Switch to using require_once in the Bootstrap to work around bad
+  interaction with Zend Debugger and APC.  Reported by Antonio Parraga.
+- Fix URI handling when hostname is missing but scheme is present.
+  Reported by Neike Taika-Tessaro.
+- Fix missing numeric entities on DirectLex; thanks Neike Taika-Tessaro
+  for reporting.
+- Fix harmless notice from indexing into empty string.  Thanks Matthijs
+  Kooijman <matthijs@stdin.nl> for reporting.
+- Don't autoclose no parent elements are able to support the element
+  that triggered the autoclose.  In particular fixes strange behavior
+  of stray <li> tags.  Thanks pkuliga@gmail.com for reporting and
+  Neike Taika-Tessaro <pinkgothic@gmail.com> for debugging assistance.
+
+4.2.0, released 2010-09-15
+! Added %Core.RemoveProcessingInstructions, which lets you remove
+  <? ... ?> statements.
+! Added %URI.DisableResources functionality; the directive originally
+  did nothing.  Thanks David Rothstein for reporting.
+! Add documentation about configuration directive types.
+! Add %CSS.ForbiddenProperties configuration directive.
+! Add %HTML.FlashAllowFullScreen to permit embedded Flash objects
+  to utilize full-screen mode.
+! Add optional support for the <code>file</code> URI scheme, enable
+  by explicitly setting %URI.AllowedSchemes.
+! Add %Core.NormalizeNewlines options to allow turning off newline
+  normalization.
+- Fix improper handling of Internet Explorer conditional comments
+  by parser.  Thanks zmonteca for reporting.
+- Fix missing attributes bug when running on Mac Snow Leopard and APC.
+  Thanks sidepodcast for the fix.
+- Warn if an element is allowed, but an attribute it requires is
+  not allowed.
+
+4.1.1, released 2010-05-31
+- Fix undefined index warnings in maintenance scripts.
+- Fix bug in DirectLex for parsing elements with a single attribute
+  with entities.
+- Rewrite CSS output logic for font-family and url().  Thanks Mario
+  Heiderich <mario.heiderich@googlemail.com> for reporting and Takeshi
+  Terada <t-terada@violet.plala.or.jp> for suggesting the fix.
+- Emit an error for CollectErrors if a body is extracted
+- Fix bug where in background-position for center keyword handling.
+- Fix infinite loop when a wrapper element is inserted in a context
+  where it's not allowed.  Thanks Lars <lars@renoz.dk> for reporting.
+- Remove +x bit and shebang from index.php; only supported mode is to
+  explicitly call it with php.
+- Make test script less chatty when log_errors is on.
+
+4.1.0, released 2010-04-26
+! Support proprietary height attribute on table element
+! Support YouTube slideshows that contain /cp/ in their URL.
+! Support for data: URI scheme; not enabled by default, add it using
+  %URI.AllowedSchemes
+! Support flashvars when using %HTML.SafeObject and %HTML.SafeEmbed.
+! Support for Internet Explorer compatibility with %HTML.SafeObject
+  using %Output.FlashCompat.
+! Handle <ol><ol> properly, by inserting the necessary <li> tag.
+- Always quote the insides of url(...) in CSS.
+
+4.0.0, released 2009-07-07
+# APIs for ConfigSchema subsystem have substantially changed. See
+  docs/dev-config-bcbreaks.txt for details; in essence, anything that
+  had both namespace and directive now have a single unified key.
+# Some configuration directives were renamed, specifically:
+    %AutoFormatParam.PurifierLinkifyDocURL -> %AutoFormat.PurifierLinkify.DocURL
+    %FilterParam.ExtractStyleBlocksEscaping -> %Filter.ExtractStyleBlocks.Escaping
+    %FilterParam.ExtractStyleBlocksScope -> %Filter.ExtractStyleBlocks.Scope
+    %FilterParam.ExtractStyleBlocksTidyImpl -> %Filter.ExtractStyleBlocks.TidyImpl
+  As usual, the old directive names will still work, but will throw E_NOTICE
+  errors.
+# The allowed values for class have been relaxed to allow all of CDATA for
+  doctypes that are not XHTML 1.1 or XHTML 2.0.  For old behavior, set
+  %Attr.ClassUseCDATA to false.
+# Instead of appending the content model to an old content model, a blank
+  element will replace the old content model.  You can use #SUPER to get
+  the old content model.
+! More robust support for name="" and id=""
+! HTMLPurifier_Config::inherit($config) allows you to inherit one
+  configuration, and have changes to that configuration be propagated
+  to all of its children.
+! Implement %HTML.Attr.Name.UseCDATA, which relaxes validation rules on
+  the name attribute when set. Use with care. Thanks Ian Cook for
+  sponsoring.
+! Implement %AutoFormat.RemoveEmpty.RemoveNbsp, which removes empty
+  tags that contain non-breaking spaces as well other whitespace. You
+  can also modify which tags should have &nbsp; 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

README.md

@@ -1,9 +1,8 @@
-
-README
-    All about HTML Purifier
+HTML Purifier [![Build Status](https://github.com/ezyang/htmlpurifier/actions/workflows/ci.yml/badge.svg?branch=master)](https://github.com/ezyang/htmlpurifier/actions/workflows/ci.yml)
+=============
 
 HTML Purifier is an HTML filtering solution that uses a unique combination
-of robust whitelists and agressive parsing to ensure that not only are
+of robust whitelists and aggressive parsing to ensure that not only are
 XSS attacks thwarted, but the resulting HTML is standards compliant.
 
 HTML Purifier is oriented towards richly formatted documents from
@@ -19,6 +18,12 @@ Places to go:
   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/
+HTML Purifier can be found on the web at: [http://htmlpurifier.org/](http://htmlpurifier.org/)
 
-    vim: et sw=4 sts=4
+## Installation
+
+Package available on [Composer](https://packagist.org/packages/ezyang/htmlpurifier).
+
+If you're using Composer to manage dependencies, you can use
+
+    $ composer require ezyang/htmlpurifier

TODO

@@ -11,54 +11,68 @@ 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!
 
-- Investigate how early internal structures can be accessed; this would
-  prevent structures from being parsed and serialized multiple times.
-- Built-in support for target="_blank" on all external links
-- Allow <a id="asdf" name="asdf">
-- Convert configuration to allow an arbitrary number of namespaces;
-  then rename as appropriate.
+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
 ---------------
 
-4.1 release [It's All About Trust] (floating)
+4.9 release [OMG CONFIG PONIES]
+ ! Fix Printer. It's from the old days when we didn't have decent XML classes
+ ! Factor demo.php into a set of Printer classes, and then create a stub
+   file for users here (inside the actual HTML Purifier library)
+ - Fix error handling with form construction
+ - Do encoding validation in Printers, or at least, where user data comes in
+ - Config: Add examples to everything (make built-in which also automatically
+   gives output)
+ - Add "register" field to config schemas to eliminate dependence on
+   naming conventions (try to remember why we ultimately decided on tihs)
+
+5.0 release [HTML 5]
+ # Swap out code to use html5lib tokenizer and tree-builder
+ ! Allow turning off of FixNesting and required attribute insertion
+
+5.1 release [It's All About Trust] (floating)
  # Implement untrusted, dangerous elements/attributes
  # Implement IDREF support (harder than it seems, since you cannot have
    IDREFs to non-existent IDs)
+     - Implement <area> (client and server side image maps are blocking
+       on IDREF support)
  # Frameset XHTML 1.0 and HTML 4.01 doctypes
- - Implement <area>
  - Figure out how to simultaneously set %CSS.Trusted and %HTML.Trusted (?)
 
-4.2 release [Error'ed]
+5.2 release [Error'ed]
  # Error logging for filtering/cleanup procedures
- - XSS-attempt detection--certain errors are flagged XSS-like
-
-4.3 release [Do What I Mean, Not What I Say]
  # Additional support for poorly written HTML
     - Microsoft Word HTML cleaning (i.e. MsoNormal, but research essential!)
     - Friendly strict handling of <address> (block -> <br>)
- ? 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.)
- - Remove <span> tags that don't do anything (no attributes)
+ - 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)
- - Externalize inline CSS to promote clean HTML, proposed by Sander Tekelenburg
 
-5.0 release [Beyond HTML]
+6.0 release [Beyond HTML]
  # Legit token based CSS parsing (will require revamping almost every
-   AttrDef class). Probably will use CSSTidy class?
+   AttrDef class). Probably will use CSSTidy
  # More control over allowed CSS properties using a modularization
- # HTML 5 support
  # IRI support (this includes IDN)
  - Standardize token armor for all areas of processing
- - Convert RTL/LTR override characters to <bdo> tags, or vice versa on demand.
-   Also, enable disabling of directionality
 
-6.0 release [To XML and Beyond]
+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
@@ -69,27 +83,14 @@ Ongoing
  - Refactor unit tests into lots of test methods
  - Plugins for major CMSes (COMPLEX)
     - phpBB
-    - Drupal needs loving!
-    - Phorum need loving!
-    - more! (look for ones that use WYSIWYGs)
-    - Also, maybe a FAQ for extension writers with HTML Purifier
+    - 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
 
-Optimizations
- - Reduce size of internal data-structures (esp. HTMLDefinition)
- - Research memory usage of objects versus arrays
- - Combine multiple strategies into a single, single-pass strategy
- - Get PH5P working with the latest versions of DOM, which have much more
-   stringent error checking procedures. Maybe convert straight to tokens.
- - Get rid of set_include_path(). Save this for another major release.
-
 Neat feature related
- ! Factor demo.php into a set of Printer classes, and then create a stub
-   file for users here (inside the actual HTML Purifier library)
  ! 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)
@@ -106,14 +107,32 @@ Neat feature related
  - 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
- - Allow restriction of allowed class values
+ - 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
- ! Nested configuration namespaces
- - Distinguish between default settings and explicitly set settings, so
-   configurations can be merged
+ - 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)

VERSION

@@ -1 +1 @@
-3.3.0
+4.18.0

WHATSNEW

@@ -1,6 +0,0 @@
-HTML Purifier 3.3.0 is fixes a number of obscure bugs reported and fixed
-over a four month period.  It is probably the last release in the 3.x
-series.  Notable new features include support for the overflow CSS
-property; notable bugfixes include fixed YouTube rendering in certain
-versions of Firefox, CSSDefinition Printer, improved early PHP support
-and bugs in iconv.

benchmarks/.htaccess

@@ -1 +1,7 @@
-Deny from all
+<IfModule mod_authz_core.c>
+    Require all denied
+</IfModule>
+
+<IfModule !mod_authz_core.c>
+    Deny from all
+</ifModule>

benchmarks/Lexer.php

@@ -23,15 +23,16 @@ if (version_compare(PHP_VERSION, '5', '>=')) {
 class RowTimer extends Benchmark_Timer
 {
 
-    var $name;
+    public $name;
 
-    function RowTimer($name, $auto = false) {
+    public function __construct($name, $auto = false)
+    {
         $this->name = htmlentities($name);
         $this->Benchmark_Timer($auto);
     }
 
-    function getOutput() {
-
+    public function getOutput()
+    {
         $total  = $this->TimeElapsed();
         $result = $this->getProfiling();
         $dashes = '';
@@ -68,7 +69,8 @@ class RowTimer extends Benchmark_Timer
     }
 }
 
-function print_lexers() {
+function print_lexers()
+{
     global $LEXERS;
     $first = true;
     foreach ($LEXERS as $key => $value) {
@@ -78,7 +80,8 @@ function print_lexers() {
     }
 }
 
-function do_benchmark($name, $document) {
+function do_benchmark($name, $document)
+{
     global $LEXERS, $RUNS;
 
     $config = HTMLPurifier_Config::createDefault();

benchmarks/samples/Lexer/1.html

@@ -52,4 +52,5 @@
 </body>
 </html>
 
-<!-- vim: et sw=4 sts=4 -->
+<!-- vim: et sw=4 sts=4
+-->

benchmarks/samples/Lexer/2.html

@@ -16,4 +16,5 @@ function qs(el) {if (window.RegExp && window.encodeURIComponent) {var ue=el.href
 // -->
 </script><table border=0 cellspacing=0 cellpadding=4><tr><td nowrap><font size=-1><b>Web</b>&nbsp;&nbsp;&nbsp;&nbsp;<a id=1a class=q href="/imghp?hl=en&tab=wi" onClick="return qs(this);">Images</a>&nbsp;&nbsp;&nbsp;&nbsp;<a id=2a class=q href="http://groups.google.com/grphp?hl=en&tab=wg" onClick="return qs(this);">Groups</a>&nbsp;&nbsp;&nbsp;&nbsp;<a id=4a class=q href="http://news.google.com/nwshp?hl=en&tab=wn" onClick="return qs(this);">News</a>&nbsp;&nbsp;&nbsp;&nbsp;<a id=5a class=q href="http://froogle.google.com/frghp?hl=en&tab=wf" onClick="return qs(this);">Froogle</a>&nbsp;&nbsp;&nbsp;&nbsp;<a id=8a class=q href="/lochp?hl=en&tab=wl" onClick="return qs(this);">Local</a>&nbsp;&nbsp;&nbsp;&nbsp;<b><a href="/intl/en/options/" class=q>more&nbsp;&raquo;</a></b></font></td></tr></table><table cellspacing=0 cellpadding=0><tr><td width=25%>&nbsp;</td><td align=center><input type=hidden name=hl value=en><input maxlength=2048 size=55 name=q value="" title="Google Search"><br><input type=submit value="Google Search" name=btnG><input type=submit value="I'm Feeling Lucky" name=btnI></td><td valign=top nowrap width=25%><font size=-2>&nbsp;&nbsp;<a href=/advanced_search?hl=en>Advanced Search</a><br>&nbsp;&nbsp;<a href=/preferences?hl=en>Preferences</a><br>&nbsp;&nbsp;<a href=/language_tools?hl=en>Language Tools</a></font></td></tr></table></form><br><br><font size=-1><a href="/ads/">Advertising&nbsp;Programs</a> - <a href=/services/>Business Solutions</a> - <a href=/about.html>About Google</a></font><p><font size=-2>&copy;2006 Google</font></p></center></body></html>
 
-<!-- vim: et sw=4 sts=4 -->
+<!-- vim: et sw=4 sts=4
+-->

benchmarks/samples/Lexer/3.html

@@ -127,4 +127,5 @@ if (objAdMgr.isSlotAvailable("leaderboard")) {
 
 </html>
 
-<!-- vim: et sw=4 sts=4 -->
+<!-- vim: et sw=4 sts=4
+-->

benchmarks/samples/Lexer/4.html

@@ -539,4 +539,5 @@ Retrieved from "<a href="http://en.wikipedia.org/wiki/Tai_Chi_Chuan">http://en.w
 <!-- Served by srv25 in 0.089 secs. -->
 </body></html>
 
-<!-- vim: et sw=4 sts=4 -->
+<!-- vim: et sw=4 sts=4
+-->

composer.json

@@ -0,0 +1,45 @@
+{
+    "name": "ezyang/htmlpurifier",
+    "description": "Standards compliant HTML filter written in PHP",
+    "type": "library",
+    "keywords": ["html"],
+    "homepage": "http://htmlpurifier.org/",
+    "license": "LGPL-2.1-or-later",
+    "authors": [
+        {
+            "name": "Edward Z. Yang",
+            "email": "admin@htmlpurifier.org",
+            "homepage": "http://ezyang.com"
+        }
+    ],
+    "require": {
+        "php": "~5.6.0 || ~7.0.0 || ~7.1.0 || ~7.2.0 || ~7.3.0 || ~7.4.0 || ~8.0.0 || ~8.1.0 || ~8.2.0 || ~8.3.0 || ~8.4.0"
+    },
+    "require-dev": {
+        "cerdic/css-tidy": "^1.7 || ^2.0",
+        "simpletest/simpletest": "dev-master"
+    },
+    "autoload": {
+        "psr-0": { "HTMLPurifier": "library/" },
+        "files": ["library/HTMLPurifier.composer.php"],
+        "exclude-from-classmap": [
+            "/library/HTMLPurifier/Language/"
+        ]
+    },
+    "suggest": {
+        "cerdic/css-tidy": "If you want to use the filter 'Filter.ExtractStyleBlocks'.",
+        "ext-iconv": "Converts text to and from non-UTF-8 encodings",
+        "ext-bcmath": "Used for unit conversion and imagecrash protection",
+        "ext-tidy": "Used for pretty-printing HTML"
+    },
+    "config": {
+        "sort-packages": true
+    },
+    "repositories": [
+        {
+            "type": "vcs",
+            "url": "https://github.com/ezyang/simpletest.git",
+            "no-api": true
+        }
+    ]
+}

configdoc/generate.php

@@ -18,22 +18,24 @@ TODO:
 if (version_compare(PHP_VERSION, '5.2', '<')) exit('PHP 5.2+ required.');
 error_reporting(E_ALL | E_STRICT);
 
-chdir(dirname(__FILE__));
-
 // load dual-libraries
-require_once '../extras/HTMLPurifierExtras.auto.php';
-require_once '../library/HTMLPurifier.auto.php';
+require_once dirname(__FILE__) . '/../extras/HTMLPurifierExtras.auto.php';
+require_once dirname(__FILE__) . '/../library/HTMLPurifier.auto.php';
 
 // setup HTML Purifier singleton
 HTMLPurifier::getInstance(array(
     'AutoFormat.PurifierLinkify' => true
 ));
 
-$interchange = HTMLPurifier_ConfigSchema_InterchangeBuilder::buildFromDirectory();
+$builder = new HTMLPurifier_ConfigSchema_InterchangeBuilder();
+$interchange = new HTMLPurifier_ConfigSchema_Interchange();
+$builder->buildDir($interchange);
+$loader = dirname(__FILE__) . '/../config-schema.php';
+if (file_exists($loader)) include $loader;
 $interchange->validate();
 
 $style = 'plain'; // use $_GET in the future, careful to validate!
-$configdoc_xml = 'configdoc.xml';
+$configdoc_xml = dirname(__FILE__) . '/configdoc.xml';
 
 $xml_builder = new HTMLPurifier_ConfigSchema_Builder_Xml();
 $xml_builder->openURI($configdoc_xml);
@@ -50,13 +52,13 @@ if (!$output) {
 }
 
 // write out
-file_put_contents("$style.html", $output);
+file_put_contents(dirname(__FILE__) . "/$style.html", $output);
 
 if (php_sapi_name() != 'cli') {
     // output (instant feedback if it's a browser)
     echo $output;
 } else {
-    echo 'Files generated successfully.';
+    echo "Files generated successfully.\n";
 }
 
 // vim: et sw=4 sts=4

configdoc/styles/plain.xsl

@@ -40,12 +40,26 @@
                             </xsl:apply-templates>
                         </ul>
                     </div>
+                    <div id="typesContainer">
+                        <h2>Types</h2>
+                        <xsl:apply-templates select="$typeLookup" mode="types" />
+                    </div>
                     <xsl:apply-templates />
                 </div>
             </body>
         </html>
     </xsl:template>
 
+    <xsl:template match="type" mode="types">
+        <div class="type-block">
+            <xsl:attribute name="id">type-<xsl:value-of select="@id" /></xsl:attribute>
+            <h3><code><xsl:value-of select="@id" /></code>: <xsl:value-of select="@name" /></h3>
+            <div class="type-description">
+                <xsl:copy-of xmlns:xhtml="http://www.w3.org/1999/xhtml" select="xhtml:div/node()" />
+            </div>
+        </div>
+    </xsl:template>
+
     <xsl:template match="title" mode="toc" />
     <xsl:template match="namespace" mode="toc">
         <xsl:param name="overflowNumber" />
@@ -192,10 +206,13 @@
             <td>
                 <xsl:variable name="type" select="text()" />
                 <xsl:attribute name="class">type type-<xsl:value-of select="$type" /></xsl:attribute>
-                <xsl:value-of select="$typeLookup/type[@id=$type]/text()" />
-                <xsl:if test="@allow-null='yes'">
-                    (or null)
-                </xsl:if>
+                <a>
+                    <xsl:attribute name="href">#type-<xsl:value-of select="$type" /></xsl:attribute>
+                    <xsl:value-of select="$typeLookup/type[@id=$type]/@name" />
+                    <xsl:if test="@allow-null='yes'">
+                        (or null)
+                    </xsl:if>
+                </a>
             </td>
         </tr>
     </xsl:template>
@@ -232,4 +249,5 @@
 
 </xsl:stylesheet>
 
-<!-- vim: et sw=4 sts=4 -->
+<!-- vim: et sw=4 sts=4
+-->

configdoc/types.xml

@@ -1,16 +1,69 @@
 <?xml version="1.0" encoding="UTF-8"?>
 <types>
-  <type id="string">String</type>
-  <type id="istring">Case-insensitive string</type>
-  <type id="text">Text</type>
-  <type id="itext">Case-insensitive text</type>
-  <type id="int">Integer</type>
-  <type id="float">Float</type>
-  <type id="bool">Boolean</type>
-  <type id="lookup">Lookup array</type>
-  <type id="list">Array list</type>
-  <type id="hash">Associative array</type>
-  <type id="mixed">Mixed</type>
+  <type id="string" name="String"><div xmlns="http://www.w3.org/1999/xhtml">
+    A <a
+    href="http://docs.php.net/manual/en/language.types.string.php">sequence
+    of characters</a>.
+  </div></type>
+  <type id="istring" name="Case-insensitive string"><div xmlns="http://www.w3.org/1999/xhtml">
+    A series of case-insensitive characters.  Internally, upper-case
+    ASCII characters will be converted to lower-case.
+  </div></type>
+  <type id="text" name="Text"><div xmlns="http://www.w3.org/1999/xhtml">
+    A series of characters that may contain newlines.  Text tends to
+    indicate human-oriented text, as opposed to a machine format.
+  </div></type>
+  <type id="itext" name="Case-insensitive text"><div xmlns="http://www.w3.org/1999/xhtml">
+    A series of case-insensitive characters that may contain newlines.
+  </div></type>
+  <type id="int" name="Integer"><div xmlns="http://www.w3.org/1999/xhtml">
+    An <a
+      href="http://docs.php.net/manual/en/language.types.integer.php">
+      integer</a>.  You are alternatively permitted to pass a string of
+    digits instead, which will be cast to an integer using
+    <code>(int)</code>.
+  </div></type>
+  <type id="float" name="Float"><div xmlns="http://www.w3.org/1999/xhtml">
+    A <a href="http://docs.php.net/manual/en/language.types.float.php">
+      floating point number</a>.  You are alternatively permitted to
+    pass a numeric string (as defined by <code>is_numeric()</code>),
+    which will be cast to a float using <code>(float)</code>.
+  </div></type>
+  <type id="bool" name="Boolean"><div xmlns="http://www.w3.org/1999/xhtml">
+    A <a
+      href="http://docs.php.net/manual/en/language.types.boolean.php">boolean</a>.
+    You are alternatively permitted to pass an integer <code>0</code> or
+    <code>1</code> (other integers are not permitted) or a string
+    <code>"on"</code>, <code>"true"</code> or <code>"1"</code> for
+    <code>true</code>, and <code>"off"</code>, <code>"false"</code> or
+    <code>"0"</code> for <code>false</code>.
+  </div></type>
+  <type id="lookup" name="Lookup array"><div xmlns="http://www.w3.org/1999/xhtml">
+    An array whose values are <code>true</code>, e.g. <code>array('key'
+      => true, 'key2' => true)</code>.  You are alternatively permitted
+    to pass an array list of the keys <code>array('key', 'key2')</code>
+    or a comma-separated string of keys <code>"key, key2"</code>.  If
+    you pass an array list of values, ensure that your values are
+    strictly numerically indexed: <code>array('key1', 2 =>
+      'key2')</code> will not do what you expect and emits a warning.
+  </div></type>
+  <type id="list" name="Array list"><div xmlns="http://www.w3.org/1999/xhtml">
+    An array which has consecutive integer indexes, e.g.
+    <code>array('val1', 'val2')</code>.  You are alternatively permitted
+    to pass a comma-separated string of keys <code>"val1, val2"</code>.
+    If your array is not in this form, <code>array_values</code> is run
+    on the array and a warning is emitted.
+  </div></type>
+  <type id="hash" name="Associative array"><div xmlns="http://www.w3.org/1999/xhtml">
+    An array which is a mapping of keys to values, e.g.
+    <code>array('key1' => 'val1', 'key2' => 'val2')</code>.  You are
+    alternatively permitted to pass a comma-separated string of
+    key-colon-value strings, e.g. <code>"key1: val1, key2: val2"</code>.
+  </div></type>
+  <type id="mixed" name="Mixed"><div xmlns="http://www.w3.org/1999/xhtml">
+    An arbitrary PHP value of any type.
+  </div></type>
 </types>
 
-<!-- vim: et sw=4 sts=4 -->
+<!-- vim: et sw=4 sts=4
+-->

configdoc/usage.xml

@@ -2,401 +2,610 @@
 <usage>
  <directive id="Core.CollectErrors">
   <file name="HTMLPurifier.php">
-   <line>131</line>
+   <line>162</line>
   </file>
   <file name="HTMLPurifier/Lexer.php">
-   <line>81</line>
+   <line>90</line>
+   <line>315</line>
   </file>
   <file name="HTMLPurifier/Lexer/DirectLex.php">
-   <line>53</line>
-   <line>73</line>
-   <line>348</line>
+   <line>67</line>
+   <line>87</line>
+   <line>385</line>
   </file>
   <file name="HTMLPurifier/Strategy/RemoveForeignElements.php">
-   <line>47</line>
+   <line>57</line>
   </file>
  </directive>
  <directive id="CSS.MaxImgLength">
   <file name="HTMLPurifier/CSSDefinition.php">
-   <line>157</line>
+   <line>253</line>
   </file>
  </directive>
  <directive id="CSS.Proprietary">
   <file name="HTMLPurifier/CSSDefinition.php">
-   <line>214</line>
+   <line>397</line>
   </file>
  </directive>
  <directive id="CSS.AllowTricky">
   <file name="HTMLPurifier/CSSDefinition.php">
-   <line>218</line>
+   <line>401</line>
+  </file>
+ </directive>
+ <directive id="CSS.Trusted">
+  <file name="HTMLPurifier/CSSDefinition.php">
+   <line>405</line>
   </file>
  </directive>
  <directive id="CSS.AllowImportant">
   <file name="HTMLPurifier/CSSDefinition.php">
-   <line>222</line>
+   <line>409</line>
   </file>
  </directive>
  <directive id="CSS.AllowedProperties">
   <file name="HTMLPurifier/CSSDefinition.php">
-   <line>275</line>
+   <line>538</line>
+  </file>
+ </directive>
+ <directive id="CSS.ForbiddenProperties">
+  <file name="HTMLPurifier/CSSDefinition.php">
+   <line>554</line>
   </file>
  </directive>
  <directive id="Cache.DefinitionImpl">
   <file name="HTMLPurifier/DefinitionCacheFactory.php">
-   <line>49</line>
+   <line>66</line>
   </file>
  </directive>
  <directive id="HTML.Doctype">
   <file name="HTMLPurifier/DoctypeRegistry.php">
-   <line>83</line>
+   <line>119</line>
   </file>
  </directive>
  <directive id="HTML.CustomDoctype">
   <file name="HTMLPurifier/DoctypeRegistry.php">
-   <line>85</line>
+   <line>123</line>
   </file>
  </directive>
  <directive id="HTML.XHTML">
   <file name="HTMLPurifier/DoctypeRegistry.php">
-   <line>88</line>
+   <line>128</line>
   </file>
  </directive>
  <directive id="HTML.Strict">
   <file name="HTMLPurifier/DoctypeRegistry.php">
-   <line>93</line>
+   <line>133</line>
   </file>
  </directive>
  <directive id="Core.Encoding">
   <file name="HTMLPurifier/Encoder.php">
-   <line>267</line>
-   <line>300</line>
+   <line>380</line>
+   <line>428</line>
   </file>
  </directive>
  <directive id="Test.ForceNoIconv">
   <file name="HTMLPurifier/Encoder.php">
-   <line>272</line>
-   <line>308</line>
+   <line>388</line>
+   <line>439</line>
   </file>
  </directive>
  <directive id="Core.EscapeNonASCIICharacters">
   <file name="HTMLPurifier/Encoder.php">
-   <line>304</line>
+   <line>429</line>
   </file>
  </directive>
  <directive id="Output.CommentScriptContents">
   <file name="HTMLPurifier/Generator.php">
-   <line>45</line>
+   <line>70</line>
+  </file>
+ </directive>
+ <directive id="Output.FixInnerHTML">
+  <file name="HTMLPurifier/Generator.php">
+   <line>71</line>
   </file>
  </directive>
  <directive id="Output.SortAttr">
   <file name="HTMLPurifier/Generator.php">
-   <line>46</line>
+   <line>72</line>
+  </file>
+ </directive>
+ <directive id="Output.FlashCompat">
+  <file name="HTMLPurifier/Generator.php">
+   <line>73</line>
   </file>
  </directive>
  <directive id="Output.TidyFormat">
   <file name="HTMLPurifier/Generator.php">
-   <line>75</line>
+   <line>104</line>
+  </file>
+ </directive>
+ <directive id="Core.NormalizeNewlines">
+  <file name="HTMLPurifier/Generator.php">
+   <line>122</line>
+  </file>
+  <file name="HTMLPurifier/Lexer.php">
+   <line>299</line>
   </file>
  </directive>
  <directive id="Output.Newline">
   <file name="HTMLPurifier/Generator.php">
-   <line>89</line>
+   <line>123</line>
   </file>
  </directive>
  <directive id="HTML.BlockWrapper">
   <file name="HTMLPurifier/HTMLDefinition.php">
-   <line>222</line>
+   <line>263</line>
   </file>
  </directive>
  <directive id="HTML.Parent">
   <file name="HTMLPurifier/HTMLDefinition.php">
-   <line>230</line>
+   <line>273</line>
   </file>
  </directive>
  <directive id="HTML.AllowedElements">
   <file name="HTMLPurifier/HTMLDefinition.php">
-   <line>247</line>
+   <line>291</line>
   </file>
  </directive>
  <directive id="HTML.AllowedAttributes">
   <file name="HTMLPurifier/HTMLDefinition.php">
-   <line>248</line>
+   <line>292</line>
   </file>
  </directive>
  <directive id="HTML.Allowed">
   <file name="HTMLPurifier/HTMLDefinition.php">
-   <line>251</line>
+   <line>295</line>
   </file>
  </directive>
  <directive id="HTML.ForbiddenElements">
   <file name="HTMLPurifier/HTMLDefinition.php">
-   <line>337</line>
+   <line>399</line>
   </file>
  </directive>
  <directive id="HTML.ForbiddenAttributes">
   <file name="HTMLPurifier/HTMLDefinition.php">
-   <line>338</line>
+   <line>400</line>
   </file>
  </directive>
  <directive id="HTML.Trusted">
   <file name="HTMLPurifier/HTMLModuleManager.php">
-   <line>202</line>
+   <line>234</line>
   </file>
   <file name="HTMLPurifier/Lexer.php">
-   <line>258</line>
+   <line>304</line>
+   <line>342</line>
+  </file>
+  <file name="HTMLPurifier/AttrDef/HTML/ContentEditable.php">
+   <line>8</line>
+  </file>
+  <file name="HTMLPurifier/HTMLModule/Iframe.php">
+   <line>43</line>
   </file>
   <file name="HTMLPurifier/HTMLModule/Image.php">
-   <line>27</line>
+   <line>37</line>
   </file>
   <file name="HTMLPurifier/Lexer/DirectLex.php">
-   <line>36</line>
+   <line>47</line>
   </file>
   <file name="HTMLPurifier/Strategy/RemoveForeignElements.php">
-   <line>23</line>
+   <line>30</line>
   </file>
  </directive>
  <directive id="HTML.AllowedModules">
   <file name="HTMLPurifier/HTMLModuleManager.php">
-   <line>209</line>
+   <line>241</line>
   </file>
  </directive>
  <directive id="HTML.CoreModules">
   <file name="HTMLPurifier/HTMLModuleManager.php">
-   <line>210</line>
+   <line>242</line>
   </file>
  </directive>
  <directive id="HTML.Proprietary">
   <file name="HTMLPurifier/HTMLModuleManager.php">
-   <line>221</line>
+   <line>256</line>
   </file>
  </directive>
  <directive id="HTML.SafeObject">
   <file name="HTMLPurifier/HTMLModuleManager.php">
-   <line>226</line>
+   <line>259</line>
   </file>
  </directive>
  <directive id="HTML.SafeEmbed">
   <file name="HTMLPurifier/HTMLModuleManager.php">
-   <line>229</line>
+   <line>262</line>
+  </file>
+ </directive>
+ <directive id="HTML.SafeScripting">
+  <file name="HTMLPurifier/HTMLModuleManager.php">
+   <line>265</line>
+  </file>
+  <file name="HTMLPurifier/HTMLModule/SafeScripting.php">
+   <line>22</line>
+  </file>
+ </directive>
+ <directive id="HTML.Nofollow">
+  <file name="HTMLPurifier/HTMLModuleManager.php">
+   <line>268</line>
+  </file>
+ </directive>
+ <directive id="HTML.TargetBlank">
+  <file name="HTMLPurifier/HTMLModuleManager.php">
+   <line>271</line>
+  </file>
+ </directive>
+ <directive id="HTML.TargetNoreferrer">
+  <file name="HTMLPurifier/HTMLModuleManager.php">
+   <line>276</line>
+  </file>
+ </directive>
+ <directive id="HTML.TargetNoopener">
+  <file name="HTMLPurifier/HTMLModuleManager.php">
+   <line>279</line>
   </file>
  </directive>
  <directive id="Attr.IDBlacklist">
   <file name="HTMLPurifier/IDAccumulator.php">
-   <line>26</line>
+   <line>27</line>
   </file>
  </directive>
  <directive id="Core.Language">
   <file name="HTMLPurifier/LanguageFactory.php">
-   <line>88</line>
+   <line>93</line>
   </file>
  </directive>
  <directive id="Core.LexerImpl">
   <file name="HTMLPurifier/Lexer.php">
-   <line>76</line>
+   <line>85</line>
   </file>
  </directive>
  <directive id="Core.MaintainLineNumbers">
   <file name="HTMLPurifier/Lexer.php">
-   <line>80</line>
+   <line>89</line>
   </file>
   <file name="HTMLPurifier/Lexer/DirectLex.php">
-   <line>48</line>
+   <line>62</line>
+  </file>
+ </directive>
+ <directive id="Core.LegacyEntityDecoder">
+  <file name="HTMLPurifier/Lexer.php">
+   <line>220</line>
+   <line>326</line>
   </file>
  </directive>
  <directive id="Core.ConvertDocumentToFragment">
   <file name="HTMLPurifier/Lexer.php">
-   <line>267</line>
+   <line>313</line>
+  </file>
+ </directive>
+ <directive id="Core.RemoveProcessingInstructions">
+  <file name="HTMLPurifier/Lexer.php">
+   <line>336</line>
+  </file>
+ </directive>
+ <directive id="Core.HiddenElements">
+  <file name="HTMLPurifier/Lexer.php">
+   <line>340</line>
+  </file>
+  <file name="HTMLPurifier/Strategy/RemoveForeignElements.php">
+   <line>36</line>
+  </file>
+ </directive>
+ <directive id="Core.AggressivelyRemoveScript">
+  <file name="HTMLPurifier/Lexer.php">
+   <line>341</line>
+  </file>
+ </directive>
+ <directive id="Core.RemoveScriptContents">
+  <file name="HTMLPurifier/Lexer.php">
+   <line>342</line>
+  </file>
+  <file name="HTMLPurifier/Strategy/RemoveForeignElements.php">
+   <line>35</line>
+  </file>
+ </directive>
+ <directive id="URI.">
+  <file name="HTMLPurifier/URIDefinition.php">
+   <line>65</line>
+  </file>
+  <file name="HTMLPurifier/URIFilter/Munge.php">
+   <line>46</line>
   </file>
  </directive>
  <directive id="URI.Host">
   <file name="HTMLPurifier/URIDefinition.php">
-   <line>64</line>
+   <line>76</line>
+  </file>
+  <file name="HTMLPurifier/URIScheme.php">
+   <line>89</line>
   </file>
  </directive>
  <directive id="URI.Base">
   <file name="HTMLPurifier/URIDefinition.php">
-   <line>65</line>
+   <line>77</line>
   </file>
  </directive>
  <directive id="URI.DefaultScheme">
   <file name="HTMLPurifier/URIDefinition.php">
-   <line>72</line>
+   <line>84</line>
   </file>
  </directive>
  <directive id="URI.AllowedSchemes">
   <file name="HTMLPurifier/URISchemeRegistry.php">
-   <line>42</line>
+   <line>48</line>
   </file>
  </directive>
  <directive id="URI.OverrideAllowedSchemes">
   <file name="HTMLPurifier/URISchemeRegistry.php">
-   <line>43</line>
+   <line>49</line>
+  </file>
+ </directive>
+ <directive id="CSS.AllowDuplicates">
+  <file name="HTMLPurifier/AttrDef/CSS.php">
+   <line>28</line>
   </file>
  </directive>
  <directive id="URI.Disable">
   <file name="HTMLPurifier/AttrDef/URI.php">
-   <line>28</line>
+   <line>47</line>
   </file>
  </directive>
  <directive id="Core.ColorKeywords">
   <file name="HTMLPurifier/AttrDef/CSS/Color.php">
-   <line>12</line>
+   <line>29</line>
   </file>
   <file name="HTMLPurifier/AttrDef/HTML/Color.php">
-   <line>12</line>
+   <line>19</line>
+  </file>
+ </directive>
+ <directive id="CSS.AllowedFonts">
+  <file name="HTMLPurifier/AttrDef/CSS/FontFamily.php">
+   <line>62</line>
+  </file>
+ </directive>
+ <directive id="Attr.AllowedClasses">
+  <file name="HTMLPurifier/AttrDef/HTML/Class.php">
+   <line>33</line>
+  </file>
+ </directive>
+ <directive id="Attr.ForbiddenClasses">
+  <file name="HTMLPurifier/AttrDef/HTML/Class.php">
+   <line>34</line>
   </file>
  </directive>
  <directive id="Attr.AllowedFrameTargets">
   <file name="HTMLPurifier/AttrDef/HTML/FrameTarget.php">
-   <line>15</line>
+   <line>32</line>
   </file>
  </directive>
  <directive id="Attr.EnableID">
   <file name="HTMLPurifier/AttrDef/HTML/ID.php">
-   <line>20</line>
+   <line>41</line>
   </file>
  </directive>
  <directive id="Attr.IDPrefix">
   <file name="HTMLPurifier/AttrDef/HTML/ID.php">
-   <line>26</line>
+   <line>51</line>
   </file>
  </directive>
  <directive id="Attr.IDPrefixLocal">
   <file name="HTMLPurifier/AttrDef/HTML/ID.php">
-   <line>28</line>
-   <line>31</line>
+   <line>53</line>
+   <line>58</line>
+  </file>
+ </directive>
+ <directive id="Attr.ID.HTML5">
+  <file name="HTMLPurifier/AttrDef/HTML/ID.php">
+   <line>75</line>
   </file>
  </directive>
  <directive id="Attr.IDBlacklistRegexp">
   <file name="HTMLPurifier/AttrDef/HTML/ID.php">
-   <line>54</line>
+   <line>97</line>
+  </file>
+ </directive>
+ <directive id="Attr.">
+  <file name="HTMLPurifier/AttrDef/HTML/LinkTypes.php">
+   <line>46</line>
+  </file>
+ </directive>
+ <directive id="Core.AllowHostnameUnderscore">
+  <file name="HTMLPurifier/AttrDef/URI/Host.php">
+   <line>71</line>
+  </file>
+ </directive>
+ <directive id="Core.EnableIDNA">
+  <file name="HTMLPurifier/AttrDef/URI/Host.php">
+   <line>103</line>
   </file>
  </directive>
  <directive id="Attr.DefaultTextDir">
   <file name="HTMLPurifier/AttrTransform/BdoDir.php">
-   <line>13</line>
+   <line>22</line>
   </file>
  </directive>
  <directive id="Core.RemoveInvalidImg">
   <file name="HTMLPurifier/AttrTransform/ImgRequired.php">
-   <line>18</line>
+   <line>24</line>
   </file>
   <file name="HTMLPurifier/Strategy/RemoveForeignElements.php">
-   <line>20</line>
+   <line>27</line>
   </file>
  </directive>
  <directive id="Attr.DefaultInvalidImage">
   <file name="HTMLPurifier/AttrTransform/ImgRequired.php">
-   <line>19</line>
+   <line>27</line>
   </file>
  </directive>
  <directive id="Attr.DefaultImageAlt">
   <file name="HTMLPurifier/AttrTransform/ImgRequired.php">
-   <line>25</line>
+   <line>33</line>
   </file>
  </directive>
  <directive id="Attr.DefaultInvalidImageAlt">
   <file name="HTMLPurifier/AttrTransform/ImgRequired.php">
-   <line>32</line>
+   <line>40</line>
   </file>
  </directive>
- <directive id="Core.EscapeInvalidChildren">
-  <file name="HTMLPurifier/ChildDef/Required.php">
-   <line>62</line>
+ <directive id="HTML.Attr.Name.UseCDATA">
+  <file name="HTMLPurifier/AttrTransform/Name.php">
+   <line>18</line>
+  </file>
+  <file name="HTMLPurifier/HTMLModule/Name.php">
+   <line>19</line>
+  </file>
+ </directive>
+ <directive id="HTML.FlashAllowFullScreen">
+  <file name="HTMLPurifier/AttrTransform/SafeParam.php">
+   <line>58</line>
   </file>
  </directive>
  <directive id="Cache.SerializerPath">
   <file name="HTMLPurifier/DefinitionCache/Serializer.php">
-   <line>91</line>
+   <line>185</line>
   </file>
  </directive>
- <directive id="FilterParam.ExtractStyleBlocksTidyImpl">
-  <file name="HTMLPurifier/Filter/ExtractStyleBlocks.php">
-   <line>41</line>
+ <directive id="Cache.SerializerPermissions">
+  <file name="HTMLPurifier/DefinitionCache/Serializer.php">
+   <line>202</line>
+   <line>218</line>
   </file>
  </directive>
- <directive id="FilterParam.ExtractStyleBlocksScope">
+ <directive id="Filter.ExtractStyleBlocks.TidyImpl">
   <file name="HTMLPurifier/Filter/ExtractStyleBlocks.php">
-   <line>65</line>
+   <line>106</line>
   </file>
  </directive>
- <directive id="FilterParam.ExtractStyleBlocksEscaping">
+ <directive id="Filter.ExtractStyleBlocks.Scope">
   <file name="HTMLPurifier/Filter/ExtractStyleBlocks.php">
-   <line>123</line>
+   <line>137</line>
+  </file>
+ </directive>
+ <directive id="Filter.ExtractStyleBlocks.Escaping">
+  <file name="HTMLPurifier/Filter/ExtractStyleBlocks.php">
+   <line>351</line>
+  </file>
+ </directive>
+ <directive id="HTML.Forms">
+  <file name="HTMLPurifier/HTMLModule/Forms.php">
+   <line>31</line>
+  </file>
+ </directive>
+ <directive id="HTML.SafeIframe">
+  <file name="HTMLPurifier/HTMLModule/Iframe.php">
+   <line>28</line>
+  </file>
+  <file name="HTMLPurifier/URIFilter/SafeIframe.php">
+   <line>48</line>
   </file>
  </directive>
  <directive id="HTML.MaxImgLength">
   <file name="HTMLPurifier/HTMLModule/Image.php">
-   <line>14</line>
+   <line>21</line>
   </file>
   <file name="HTMLPurifier/HTMLModule/SafeEmbed.php">
-   <line>13</line>
+   <line>18</line>
   </file>
   <file name="HTMLPurifier/HTMLModule/SafeObject.php">
-   <line>19</line>
+   <line>24</line>
   </file>
  </directive>
  <directive id="HTML.TidyLevel">
   <file name="HTMLPurifier/HTMLModule/Tidy.php">
-   <line>45</line>
+   <line>50</line>
   </file>
  </directive>
  <directive id="HTML.TidyAdd">
   <file name="HTMLPurifier/HTMLModule/Tidy.php">
-   <line>49</line>
+   <line>54</line>
   </file>
  </directive>
  <directive id="HTML.TidyRemove">
   <file name="HTMLPurifier/HTMLModule/Tidy.php">
-   <line>50</line>
+   <line>55</line>
   </file>
  </directive>
- <directive id="AutoFormatParam.PurifierLinkifyDocURL">
+ <directive id="AutoFormat.PurifierLinkify.DocURL">
   <file name="HTMLPurifier/Injector/PurifierLinkify.php">
-   <line>15</line>
+   <line>31</line>
+  </file>
+ </directive>
+ <directive id="AutoFormat.RemoveEmpty.RemoveNbsp">
+  <file name="HTMLPurifier/Injector/RemoveEmpty.php">
+   <line>46</line>
+  </file>
+ </directive>
+ <directive id="AutoFormat.RemoveEmpty.RemoveNbsp.Exceptions">
+  <file name="HTMLPurifier/Injector/RemoveEmpty.php">
+   <line>47</line>
+  </file>
+ </directive>
+ <directive id="AutoFormat.RemoveEmpty.Predicate">
+  <file name="HTMLPurifier/Injector/RemoveEmpty.php">
+   <line>48</line>
   </file>
  </directive>
  <directive id="Core.AggressivelyFixLt">
   <file name="HTMLPurifier/Lexer/DOMLex.php">
-   <line>44</line>
+   <line>54</line>
+  </file>
+ </directive>
+ <directive id="Core.AllowParseManyTags">
+  <file name="HTMLPurifier/Lexer/DOMLex.php">
+   <line>72</line>
+  </file>
+ </directive>
+ <directive id="Core.RemoveBlanks">
+  <file name="HTMLPurifier/Lexer/DOMLex.php">
+   <line>75</line>
   </file>
  </directive>
  <directive id="Core.DirectLexLineNumberSyncInterval">
   <file name="HTMLPurifier/Lexer/DirectLex.php">
-   <line>70</line>
+   <line>84</line>
+  </file>
+ </directive>
+ <directive id="Core.DisableExcludes">
+  <file name="HTMLPurifier/Strategy/FixNesting.php">
+   <line>54</line>
   </file>
  </directive>
  <directive id="Core.EscapeInvalidTags">
   <file name="HTMLPurifier/Strategy/MakeWellFormed.php">
-   <line>45</line>
+   <line>72</line>
   </file>
-  <file name="HTMLPurifier/Strategy/RemoveForeignElements.php">
-   <line>19</line>
-  </file>
- </directive>
- <directive id="Core.RemoveScriptContents">
-  <file name="HTMLPurifier/Strategy/RemoveForeignElements.php">
-   <line>25</line>
-  </file>
- </directive>
- <directive id="Core.HiddenElements">
   <file name="HTMLPurifier/Strategy/RemoveForeignElements.php">
    <line>26</line>
   </file>
  </directive>
+ <directive id="HTML.AllowedComments">
+  <file name="HTMLPurifier/Strategy/RemoveForeignElements.php">
+   <line>31</line>
+  </file>
+ </directive>
+ <directive id="HTML.AllowedCommentsRegexp">
+  <file name="HTMLPurifier/Strategy/RemoveForeignElements.php">
+   <line>32</line>
+  </file>
+ </directive>
  <directive id="URI.HostBlacklist">
   <file name="HTMLPurifier/URIFilter/HostBlacklist.php">
-   <line>8</line>
+   <line>25</line>
   </file>
  </directive>
  <directive id="URI.MungeResources">
   <file name="HTMLPurifier/URIFilter/Munge.php">
-   <line>14</line>
+   <line>48</line>
   </file>
  </directive>
  <directive id="URI.MungeSecretKey">
   <file name="HTMLPurifier/URIFilter/Munge.php">
-   <line>15</line>
+   <line>49</line>
+  </file>
+ </directive>
+ <directive id="URI.SafeIframeRegexp">
+  <file name="HTMLPurifier/URIFilter/SafeIframe.php">
+   <line>35</line>
   </file>
  </directive>
 </usage>

docs/dev-advanced-api.html

@@ -17,202 +17,10 @@
 <div id="home"><a href="http://htmlpurifier.org/">HTML Purifier</a> End-User Documentation</div>
 
 <p>
-  <strong>Warning:</strong> This document may be out-of-date. When in doubt,
-  consult the source code documentation.
+  Please see <a href="enduser-customize.html">Customize!</a>
 </p>
 
-<p>HTML Purifier currently natively supports only a subset of HTML's
-allowed elements, attributes, and behavior; specifically, this subset
-is the set of elements that are safe for untrusted users to use.
-However, HTML Purifier is often utilized to ensure standards-compliance
-from input that is trusted (making it a sort of Tidy substitute),
-and often users need to define new elements or attributes. The
-advanced API is oriented specifically for these use-cases.</p>
-
-<p>Our goals are to let the user:</p>
-
-<dl>
-    <dt>Select</dt>
-    <dd><ul>
-        <li>Doctype</li>
-        <!-- <li>Filterset</li> -->
-        <li>Elements / Attributes / Modules</li>
-        <li>Tidy</li>
-    </ul></dd>
-    <dt>Customize</dt>
-    <dd><ul>
-        <li>Attributes</li>
-        <li>Elements</li>
-        <!--<li>Doctypes</li>-->
-    </ul></dd>
-</dl>
-
-<h2>Select</h2>
-
-<p>For basic use, the user will have to specify some basic parameters. This
-is not strictly necessary, as HTML Purifier's default setting will always
-output safe code, but is required for standards-compliant output.</p>
-
-<h3>Selecting a Doctype</h3>
-
-<p>The first thing to select is the <strong>doctype</strong>. This
-is essential for standards-compliant output.</p>
-
-<p class="technical">This identifier is based
-on the name the W3C has given to the document type and <em>not</em>
-the DTD identifier.</p>
-
-<p>This parameter is set via the configuration object:</p>
-
-<pre>$config->set('HTML', 'Doctype', 'XHTML 1.0 Transitional');</pre>
-
-<p>Due to historical reasons, the default doctype is XHTML 1.0
-Transitional, however, we really shouldn't be guessing what the user's
-doctype is. Fortunantely, people who can't be bothered to set this won't
-be bothered when their pages stop validating.</p>
-
-<h3>Selecting Elements / Attributes / Modules</h3>
-
-<p>HTML Purifier will, by default, allow as many elements and attributes
-as possible. However, a user may decide to roll their own filterset by
-selecting modules, elements and attributes to allow for their own
-specific use-case. This can be done using %HTML.Allowed:</p>
-
-<pre>$config->set('HTML', 'Allowed', 'a[href|title],em,p,blockquote');</pre>
-
-<p class="technical">The directive %HTML.Allowed is a convenience feature
-that may be fully expressed with the legacy interface.</p>
-
-<p>We currently support another interface from older versions:</p>
-
-<pre>$config->set('HTML', 'AllowedElements', 'a,em,p,blockquote');
-$config->set('HTML', 'AllowedAttributes', 'a.href,a.title');</pre>
-
-<p>A user may also choose to allow modules using a specialized
-directive:</p>
-
-<pre>$config->set('HTML', 'AllowedModules', 'Hypertext,Text,Lists');</pre>
-
-<p>But it is not expected that this feature will be widely used.</p>
-
-<p class="technical">Module selection will work slightly differently
-from the other AllowedElements and AllowedAttributes directives by
-directly modifying the doctype you are operating in, in the spirit of
-XHTML 1.1's modularization. We stop users from shooting themselves in the
-foot by mandating the modules in %HTML.CoreModules be used.</p>
-
-<p class="technical">Modules are distinguished from regular elements by the
-case of their first letter. While XML distinguishes between and allows
-lower and uppercase letters in element names, XHTML uses only lower-case
-element names for sake of consistency.</p>
-
-<h3>Selecting Tidy</h3>
-
-<p>The name of this segment of functionality is inspired off of Dave
-Ragget's program HTML Tidy, which purported to help clean up HTML. In
-HTML Purifier, Tidy functionality involves turning unsupported and
-deprecated elements into standards-compliant ones, maintaining
-backwards compatibility, and enforcing best practices.</p>
-
-<p>This is a complicated feature, and is explained more in depth at
-<a href="enduser-tidy.html">the Tidy documentation page</a>.</p>
-
-<!--
-<h3>Unified selector</h3>
-
-<p>Because selecting each and every one of these configuration options
-is a chore, we may wish to offer a specialized configuration method
-for selecting a filterset. Possibility:</p>
-
-<pre>function selectFilter($doctype, $filterset, $tidy)</pre>
-
-<p>...which is simply a light wrapper over the individual configuration
-calls. A custom config file format or text format could also be adopted.</p>
--->
-
-<h2>Customize</h2>
-
-<p>By reviewing topic posts in the support forum, we determined that
-there were two primarily demanded customization features people wanted:
-to add an attribute to an existing element, and to add an element.
-Thus, we'll want to create convenience functions for these common
-use-cases.</p>
-
-<p>Note that the functions described here are only available if
-a raw copy of <code>HTMLPurifier_HTMLDefinition</code> was retrieved.
-Furthermore, caching may prevent your changes from immediately
-being seen: consult <a href="enduser-customize.html">enduser-customize.html</a> on how
-to work around this.</p>
-
-<h3>Attributes</h3>
-
-<p>An attribute is bound to an element by a name and has a specific
-<code>AttrDef</code> that validates it. The interface is therefore:</p>
-
-<pre>function addAttribute($element, $attribute, $attribute_def);</pre>
-
-<p>Example of the functionality in action:</p>
-
-<pre>$def->addAttribute('a', 'rel', 'Enum#nofollow');</pre>
-
-<p>The <code>$attribute_def</code> value is flexible,
-to make things simpler. It can be a literal object or:</p>
-
-<ul>
-    <!--<li>Class name: We'll instantiate it for you</li>
-    <li>Function name: We'll create an <code>HTMLPurifier_AttrDef_Anonymous</code>
-        class with that function registered as a callback.</li>-->
-    <li>String attribute type: We'll use <code>HTMLPurifier_AttrTypes</code>
-        to resolve it for you. Any data that follows a hash mark (#) will
-        be used to customize the attribute type: in the example above,
-        we specify which values for Enum to allow.</li>
-</ul>
-
-<h3>Elements</h3>
-
-<p>An element requires certain information as specified by
-<code>HTMLPurifier_ElementDef</code>. However, not all of it is necessary,
-the usual things required are:</p>
-
-<ul>
-    <li>Attributes</li>
-    <li>Content model/type</li>
-    <li>Registration in a content set</li>
-</ul>
-
-<p>This suggests an API like this:</p>
-
-<pre>function addElement($element, $type, $contents,
-    $attr_collections = array(); $attributes = array());</pre>
-
-<p>Each parameter explained in depth:</p>
-
-<dl>
-    <dt><code>$element</code></dt>
-    <dd>Element name, ex. 'label'</dd>
-    <dt><code>$type</code></dt>
-    <dd>Content set to register in, ex. 'Inline' or 'Flow'</dd>
-    <dt><code>$contents</code></dt>
-    <dd>Description of allowed children. This is a merged form of
-        <code>HTMLPurifier_ElementDef</code>'s member variables
-        <code>$content_model</code> and <code>$content_model_type</code>,
-        where the form is <q>Type: Model</q>, ex. 'Optional: Inline'.
-        There are also a number of predefined templates one may use.</dd>
-    <dt><code>$attr_collections</code></dt>
-    <dd>Array (or string if only one) of attribute collection(s) to
-        merge into the attributes array.</dd>
-    <dt><code>$attributes</code></dt>
-    <dd>Array of attribute names to attribute definitions, much like
-        the above-described attribute customization.</dd>
-</dl>
-
-<p>A possible usage:</p>
-
-<pre>$def->addElement('font', 'Inline', 'Optional: Inline', 'Common',
-    array('color' => 'Color'));</pre>
-
-<p>See <code>HTMLPurifier/HTMLModule.php</code> for details.</p>
-
 </body></html>
 
-<!-- vim: et sw=4 sts=4 -->
+<!-- vim: et sw=4 sts=4
+-->

docs/dev-code-quality.txt

@@ -25,5 +25,6 @@ URIScheme - needs to have callable generic checks
     mailto - doesn't validate emails, doesn't validate querystring
     news - doesn't validate opaque path
     nntp - doesn't constrain path
+    tel - doesn't validate phone numbers, only allows characters '+', '1-9', and 'x'
 
     vim: et sw=4 sts=4

docs/dev-config-bcbreaks.txt

@@ -0,0 +1,79 @@
+
+Configuration Backwards-Compatibility Breaks
+
+In version 4.0.0, the configuration subsystem (composed of the outwards
+facing Config class, as well as the ConfigSchema and ConfigSchema_Interchange
+subsystems), was significantly revamped to make use of property lists.
+While most of the changes are internal, some internal APIs were changed for the
+sake of clarity. HTMLPurifier_Config was kept completely backwards compatible,
+although some of the functions were retrofitted with an unambiguous alternate
+syntax. Both of these changes are discussed in this document.
+
+
+
+1. Outwards Facing Changes
+--------------------------------------------------------------------------------
+
+The HTMLPurifier_Config class now takes an alternate syntax. The general rule
+is:
+
+    If you passed $namespace, $directive, pass "$namespace.$directive"
+    instead.
+
+An example:
+
+    $config->set('HTML', 'Allowed', 'p');
+
+becomes:
+
+    $config->set('HTML.Allowed', 'p');
+
+New configuration options may have more than one namespace, they might
+look something like %Filter.YouTube.Blacklist. While you could technically
+set it with ('HTML', 'YouTube.Blacklist'), the logical extension
+('HTML', 'YouTube', 'Blacklist') does not work.
+
+The old API will still work, but will emit E_USER_NOTICEs.
+
+
+
+2. Internal API Changes
+--------------------------------------------------------------------------------
+
+Some overarching notes: we've completely eliminated the notion of namespace;
+it's now an informal construct for organizing related configuration directives.
+
+Also, the validation routines for keys (formerly "$namespace.$directive")
+have been completely relaxed. I don't think it really should be necessary.
+
+2.1 HTMLPurifier_ConfigSchema
+
+First off, if you're interfacing with this class, you really shouldn't.
+HTMLPurifier_ConfigSchema_Builder_ConfigSchema is really the only class that
+should ever be creating HTMLPurifier_ConfigSchema, and HTMLPurifier_Config the
+only class that should be reading it.
+
+All namespace related methods were removed; they are completely unnecessary
+now. Any $namespace, $name arguments must be replaced with $key (where
+$key == "$namespace.$name"), including for addAlias().
+
+The $info and $defaults member variables are no longer indexed as
+[$namespace][$name]; they are now indexed as ["$namespace.$name"].
+
+All deprecated methods were finally removed, after having yelled at you as
+an E_USER_NOTICE for a while now.
+
+2.2 HTMLPurifier_ConfigSchema_Interchange
+
+Member variable $namespaces was removed.
+
+2.3 HTMLPurifier_ConfigSchema_Interchange_Id
+
+Member variable $namespace and $directive removed; member variable $key added.
+Any method that took $namespace, $directive now takes $key.
+
+2.4 HTMLPurifier_ConfigSchema_Interchange_Namespace
+
+Removed.
+
+    vim: et sw=4 sts=4

docs/dev-config-naming.txt

@@ -0,0 +1,165 @@
+Configuration naming
+
+HTML Purifier 4.0.0 features a new configuration naming system that
+allows arbitrary nesting of namespaces.  While there are certain cases
+in which using two namespaces is obviously better (the canonical example
+is where we were using AutoFormatParam to contain directives for AutoFormat
+parameters), it is unclear whether or not a general migration to highly
+namespaced directives is a good idea or not.
+
+== Case studies ==
+
+=== Attr.* ===
+
+We have a dead duck HTML.Attr.Name.UseCDATA which migrated before we decided
+to think this out thoroughly.
+
+We currently have a large number of directives in the Attr.* namespace.
+These directives tweak the behavior of some HTML attributes.  They have
+the properties:
+
+* While they apply to only one attribute at a time, the attribute can
+  span over multiple elements (not necessarily all attributes, either).
+  The information of which elements it impacts is either omitted or
+  informally stated (EnableID applies to all elements, DefaultImageAlt
+  applies to <img> tags, AllowedRev doesn't say but only applies to a tags).
+
+* There is a certain degree of clustering that could be applied, especially
+  to the ID directives.  The clustering could be done with respect to
+  what element/attribute was used, i.e.
+
+    *.id -> EnableID, IDBlacklistRegexp, IDBlacklist, IDPrefixLocal, IDPrefix
+    img.src -> DefaultInvalidImage
+    img.alt -> DefaultImageAlt, DefaultInvalidImageAlt
+    bdo.dir -> DefaultTextDir
+    a.rel -> AllowedRel
+    a.rev -> AllowedRev
+    a.target -> AllowedFrameTargets
+    a.name -> Name.UseCDATA
+
+* The directives often reference generic attribute types that were specified
+  in the DTD/specification.  However, some of the behavior specifically relies
+  on the fact that other use cases of the attribute are not, at current,
+  supported by HTML Purifier.
+
+    AllowedRel, AllowedRev -> heavily <a> specific; if <link> ends up being
+        allowed, we will also have to give users specificity there (we also
+        want to preserve generality) DTD %Linktypes, HTML5 distinguishes
+        between <link> and <a>/<area>
+    AllowedFrameTargets -> heavily <a> specific, but also used by <area>
+        and <form>. Transitional DTD %FrameTarget, not present in strict,
+        HTML5 calls them "browsing contexts"
+    Default*Image* -> as a default parameter, is almost entirely exlcusive
+        to <img>
+    EnableID -> global attribute
+    Name.UseCDATA -> heavily <a> specific, but has heavy other usage by
+        many things
+
+== AutoFormat.* ==
+
+These have the fairly normal pluggable architecture that lends itself to
+large amounts of namespaces (pluggability may be the key to figuring
+out when gratuitous namespacing is good.)  Properties:
+
+* Boolean directives are fair game for being namespaced: for example,
+  RemoveEmpty.RemoveNbsp triggers RemoveEmpty.RemoveNbsp.Exceptions,
+  the latter of which only makes sense when RemoveEmpty.RemoveNbsp
+  is set to true. (The same applies to RemoveNbsp too)
+
+The AutoFormat string is a bit long, but is the only bit of repeated
+context.
+
+== Core.* ==
+
+Core is the potpourri of directives, mostly regarding some minor behavioral
+tweaks for HTML handling abilities.
+
+    AggressivelyFixLt
+    AllowParseManyTags
+    ConvertDocumentToFragment
+    DirectLexLineNumberSyncInterval
+    LexerImpl
+    MaintainLineNumbers
+        Lexer
+    CollectErrors
+    Language
+        Error handling (Language is ostensibly a little more general, but
+        it's only used for error handling right now)
+    ColorKeywords
+        CSS and HTML
+    Encoding
+    EscapeNonASCIICharacters
+        Character encoding
+    EscapeInvalidChildren
+    EscapeInvalidTags
+    HiddenElements
+    RemoveInvalidImg
+        Lexing/Output
+    RemoveScriptContents
+        Deprecated
+
+== HTML.* ==
+
+    AllowedAttributes
+    AllowedElements
+    AllowedModules
+    Allowed
+    ForbiddenAttributes
+    ForbiddenElements
+        Element set tuning
+    BlockWrapper
+        Child def advanced twiddle
+    CoreModules
+    CustomDoctype
+        Advanced HTMLModuleManager twiddles
+    DefinitionID
+    DefinitionRev
+        Caching
+    Doctype
+    Parent
+    Strict
+    XHTML
+        Global environment
+    MaxImgLength
+        Attribute twiddle? (applies to two attributes)
+    Proprietary
+    SafeEmbed
+    SafeObject
+    Trusted
+        Extra functionality/tagsets
+    TidyAdd
+    TidyLevel
+    TidyRemove
+        Tidy
+
+== Output.* ==
+
+These directly affect the output of Generator. These are all advanced
+twiddles.
+
+== URI.* ==
+
+    AllowedSchemes
+    OverrideAllowedSchemes
+        Scheme tuning
+    Base
+    DefaultScheme
+    Host
+        Global environment
+    DefinitionID
+    DefinitionRev
+        Caching
+    DisableExternalResources
+    DisableExternal
+    DisableResources
+    Disable
+        Contextual/authority tuning
+    HostBlacklist
+        Authority tuning
+    MakeAbsolute
+    MungeResources
+    MungeSecretKey
+    Munge
+        Transformation behavior (munge can be grouped)
+
+

docs/dev-config-schema.html

@@ -114,7 +114,7 @@ Test.Example</pre>
         </tr>
         <tr>
           <td>VALUE-ALIASES</td>
-          <td>'baz' => 'bar'</td>
+          <td>'baz' =&gt; 'bar'</td>
           <td><em>Optional</em>. Mapping of one value to another, and
           should be a comma separated list of keypair duples. This
           is only allowed string, istring, text and itext TYPEs.</td>
@@ -213,7 +213,7 @@ Test.Example</pre>
         </tr>
         <tr>
           <td>lookup</td>
-          <td>array('key' => true)</td>
+          <td>array('key' =&gt; true)</td>
           <td>Lookup array, used with <code>isset($var[$key])</code></td>
         </tr>
         <tr>
@@ -223,12 +223,12 @@ Test.Example</pre>
         </tr>
         <tr>
           <td>hash</td>
-          <td>array('key' => 'val')</td>
+          <td>array('key' =&gt; 'val')</td>
           <td>Associative array of keys to values</td>
         </tr>
         <tr>
           <td>mixed</td>
-          <td>new stdclass</td>
+          <td>new stdClass</td>
           <td>Any PHP variable is fine</td>
         </tr>
       </tbody>
@@ -267,6 +267,41 @@ Test.Example</pre>
       If you ever make changes to your configuration directives, you
       will need to run this script again.
     </p>
+    <h2>Adding in-house schema definitions</h2>
+
+    <p>
+      Placing stuff directly in HTML Purifier's source tree is generally not a
+      good idea, so HTML Purifier 4.0.0+ has some facilities in place to make your
+      life easier.
+    </p>
+
+    <p>
+      The first is to pass an extra parameter to <code>maintenance/generate-schema-cache.php</code>
+      with the location of your directory (relative or absolute path will do). For example,
+      if I'm storing my custom definitions in <em>/var/htmlpurifier/myschema</em>, run:
+      <code>php maintenance/generate-schema-cache.php /var/htmlpurifier/myschema</code>.
+    </p>
+
+    <p>
+      Alternatively, you can create a small loader PHP file in the HTML Purifier base
+      directory named <code>config-schema.php</code> (this is the same directory
+      you would place a <code>test-settings.php</code> file).  In this file, add
+      the following line for each directory you want to load:
+    </p>
+
+<pre>$builder-&gt;buildDir($interchange, '/var/htmlpurifier/myschema');</pre>
+
+    <p>You can even load a single file using:</p>
+
+<pre>$builder-&gt;buildFile($interchange, '/var/htmlpurifier/myschema/MyApp.Directive.txt');</pre>
+
+    <p>Storing custom definitions that you don't plan on sending back upstream in
+    a separate directory is <em>definitely</em> a good idea! Additionally, picking
+    a good namespace can go a long way to saving you grief if you want to use
+    someone else's change, but they picked the same name, or if HTML Purifier
+    decides to add support for a configuration directive that has the same name.</p>
+
+    <!-- TODO: how to name directives that rely on naming conventions -->
 
     <h2>Errors</h2>
 
@@ -373,4 +408,5 @@ Test.Example</pre>
   </body>
 </html>
 
-<!-- vim: et sw=4 sts=4 -->
+<!-- vim: et sw=4 sts=4
+-->

docs/dev-flush.html

@@ -64,4 +64,5 @@
 
 </body></html>
 
-<!-- vim: et sw=4 sts=4 -->
+<!-- vim: et sw=4 sts=4
+-->

docs/dev-naming.html

@@ -79,4 +79,5 @@ help you find the correct functionality more quickly.  Here they are:</p>
 
 </body></html>
 
-<!-- vim: et sw=4 sts=4 -->
+<!-- vim: et sw=4 sts=4
+-->

docs/dev-optimization.html

@@ -29,4 +29,5 @@ that itch, put it here!</p>
 
 </body></html>
 
-<!-- vim: et sw=4 sts=4 -->
+<!-- vim: et sw=4 sts=4
+-->

docs/dev-progress.html

@@ -255,7 +255,7 @@ Mozilla on inside and needs -moz-outline, no IE support.</td></tr>
 <tr class="feature"><td>axis</td><td>TD, TH</td><td>W3C only: No browser implementation</td></tr>
 <tr class="feature"><td>char</td><td>COL, COLGROUP, TBODY, TD, TFOOT, TH, THEAD, TR</td><td>W3C only: No browser implementation</td></tr>
 <tr class="feature"><td>headers</td><td>TD, TH</td><td>W3C only: No browser implementation</td></tr>
-<tr class="feature"><td>scope</td><td>TD, TH</td><td>W3C only: No browser implementation</td></tr>
+<tr class="impl-yes"><td>scope</td><td>TD, TH</td><td>W3C only: No browser implementation</td></tr>
 </tbody>
 
 <tbody class="impl-yes">
@@ -305,4 +305,5 @@ Mozilla on inside and needs -moz-outline, no IE support.</td></tr>
 
 </body></html>
 
-<!-- vim: et sw=4 sts=4 -->
+<!-- vim: et sw=4 sts=4
+-->

docs/enduser-customize.html

@@ -18,12 +18,11 @@
 <div id="home"><a href="http://htmlpurifier.org/">HTML Purifier</a> End-User Documentation</div>
 
 <p>
-  You may have heard of the <a href="dev-advanced-api.html">Advanced API</a>.
-  If you're interested in reading dry prose and boring functional
-  specifications, feel free to click that link to get a no-nonsense overview
-  on the Advanced API. For the rest of us, there's this tutorial. By the time
-  you're finished reading this, you should have a pretty good idea on
-  how to implement custom tags and attributes that HTML Purifier may not have.
+  HTML Purifier has this quirk where if you try to allow certain elements or
+  attributes, HTML Purifier will tell you that it's not supported, and that
+  you should go to the forums to find out how to implement it. Well, this
+  document is how to implement elements and attributes which HTML Purifier
+  doesn't support out of the box.
 </p>
 
 <h2>Is it necessary?</h2>
@@ -84,17 +83,6 @@
   limited to translations) above or below other corresponding text.
 </p>
 
-<h3>XHTML 2.0</h3>
-
-<p>
-  <a href="http://www.w3.org/TR/xhtml2/">XHTML 2.0</a> is still a
-  working draft, so any elements introduced in the
-  specification have not been implemented and will not be implemented
-  until we get a recommendation or proposal.  Because XHTML 2.0 is
-  an entirely new markup language, implementing rules for it will be
-  no easy task.
-</p>
-
 <h3>HTML 5</h3>
 
 <p>
@@ -156,9 +144,11 @@
 </p>
 
 <pre>$config = HTMLPurifier_Config::createDefault();
-$config->set('HTML', 'DefinitionID', 'enduser-customize.html tutorial');
-$config->set('HTML', 'DefinitionRev', 1);
-$def = $config->getHTMLDefinition(true);</pre>
+$config-&gt;set('HTML.DefinitionID', 'enduser-customize.html tutorial');
+$config-&gt;set('HTML.DefinitionRev', 1);
+if ($def = $config-&gt;maybeGetRawHTMLDefinition()) {
+    // our code will go here
+}</pre>
 
 <p>
   Assuming that HTML Purifier has already been properly loaded (hint:
@@ -186,23 +176,15 @@ $def = $config->getHTMLDefinition(true);</pre>
   </li>
   <li>
     The fourth line retrieves a raw <code>HTMLPurifier_HTMLDefinition</code>
-    object that we will be tweaking. If the parameter was removed, we
-    would be retrieving a fully formed definition object, which is somewhat
-    useless for customization purposes.
+    object that we will be tweaking.  Interestingly enough, we have
+    placed it in an if block: this is because
+    <code>maybeGetRawHTMLDefinition</code>, as its name suggests, may
+    return a NULL, in which case we should skip doing any
+    initialization.  This, in fact, will correspond to when our fully
+    customized object is already in the cache.
   </li>
 </ul>
 
-<h3>Broken backwards-compatibility</h3>
-
-<p>
-  Those of you who have already been twiddling around with the raw
-  HTML definition object, you'll be noticing that you're getting an error
-  when you attempt to retrieve the raw definition object without specifying
-  a DefinitionID.  It is vital to caching (see below) that you make a unique
-  name for your customized definition, so make up something right now and
-  things will operate again.
-</p>
-
 <h2>Turn off caching</h2>
 
 <p>
@@ -211,10 +193,10 @@ $def = $config->getHTMLDefinition(true);</pre>
 </p>
 
 <pre>$config = HTMLPurifier_Config::createDefault();
-$config->set('HTML', 'DefinitionID', 'enduser-customize.html tutorial');
-$config->set('HTML', 'DefinitionRev', 1);
-<strong>$config->set('Cache', 'DefinitionImpl', null); // remove this later!</strong>
-$def = $config->getHTMLDefinition(true);</pre>
+$config-&gt;set('HTML.DefinitionID', 'enduser-customize.html tutorial');
+$config-&gt;set('HTML.DefinitionRev', 1);
+<strong>$config-&gt;set('Cache.DefinitionImpl', null); // TODO: remove this later!</strong>
+$def = $config-&gt;getHTMLDefinition(true);</pre>
 
 <p>
   A few things should be mentioned about the caching mechanism before
@@ -267,10 +249,10 @@ $def = $config->getHTMLDefinition(true);</pre>
 </p>
 
 <pre>$config = HTMLPurifier_Config::createDefault();
-$config->set('HTML', 'DefinitionID', 'enduser-customize.html tutorial');
-$config->set('HTML', 'DefinitionRev', 1);
-$config->set('Cache', 'DefinitionImpl', null); // remove this later!
-$def = $config->getHTMLDefinition(true);
+$config-&gt;set('HTML.DefinitionID', 'enduser-customize.html tutorial');
+$config-&gt;set('HTML.DefinitionRev', 1);
+$config-&gt;set('Cache.DefinitionImpl', null); // remove this later!
+$def = $config-&gt;getHTMLDefinition(true);
 <strong>$def->addAttribute('a', 'target', 'Enum#_blank,_self,_target,_top');</strong></pre>
 
 <p>
@@ -385,11 +367,11 @@ $def = $config->getHTMLDefinition(true);
 </p>
 
 <pre>$config = HTMLPurifier_Config::createDefault();
-$config->set('HTML', 'DefinitionID', 'enduser-customize.html tutorial');
-$config->set('HTML', 'DefinitionRev', 1);
-$config->set('Cache', 'DefinitionImpl', null); // remove this later!
-$def = $config->getHTMLDefinition(true);
-<strong>$def->addAttribute('a', 'target', new HTMLPurifier_AttrDef_Enum(
+$config-&gt;set('HTML.DefinitionID', 'enduser-customize.html tutorial');
+$config-&gt;set('HTML.DefinitionRev', 1);
+$config-&gt;set('Cache.DefinitionImpl', null); // remove this later!
+$def = $config-&gt;getHTMLDefinition(true);
+<strong>$def-&gt;addAttribute('a', 'target', new HTMLPurifier_AttrDef_Enum(
   array('_blank','_self','_target','_top')
 ));</strong></pre>
 
@@ -724,7 +706,7 @@ $def = $config->getHTMLDefinition(true);
     or more flow elements, but no nested <code>form</code>s</strong></li>
   <li>What attributes does the element allow that are general? <strong>Common</strong></li>
   <li>What attributes does the element allow that are specific to this element? <strong>A whole bunch, see ATTLIST;
-    we're going to the vital ones: <code>action</code>, <code>method</code> and <code>name</code></strong></li>
+    we're going to do the vital ones: <code>action</code>, <code>method</code> and <code>name</code></strong></li>
 </ol>
 
 <p>
@@ -732,14 +714,14 @@ $def = $config->getHTMLDefinition(true);
 </p>
 
 <pre>$config = HTMLPurifier_Config::createDefault();
-$config->set('HTML', 'DefinitionID', 'enduser-customize.html tutorial');
-$config->set('HTML', 'DefinitionRev', 1);
-$config->set('Cache', 'DefinitionImpl', null); // remove this later!
-$def = $config->getHTMLDefinition(true);
-$def->addAttribute('a', 'target', new HTMLPurifier_AttrDef_Enum(
+$config-&gt;set('HTML.DefinitionID', 'enduser-customize.html tutorial');
+$config-&gt;set('HTML.DefinitionRev', 1);
+$config-&gt;set('Cache.DefinitionImpl', null); // remove this later!
+$def = $config-&gt;getHTMLDefinition(true);
+$def-&gt;addAttribute('a', 'target', new HTMLPurifier_AttrDef_Enum(
   array('_blank','_self','_target','_top')
 ));
-<strong>$form = $def->addElement(
+<strong>$form = $def-&gt;addElement(
   'form',   // name
   'Block',  // content set
   'Flow', // allowed children
@@ -750,7 +732,7 @@ $def->addAttribute('a', 'target', new HTMLPurifier_AttrDef_Enum(
     'name' => 'ID'
   )
 );
-$form->excludes = array('form' => true);</strong></pre>
+$form-&gt;excludes = array('form' => true);</strong></pre>
 
 <p>
   Each of the parameters corresponds to one of the questions we asked.
@@ -793,6 +775,76 @@ $form->excludes = array('form' => true);</strong></pre>
   <li><a href="http://repo.or.cz/w/htmlpurifier.git?a=blob;hb=HEAD;f=library/HTMLPurifier/ElementDef.php"><code>library/HTMLPurifier/ElementDef.php</code></a></li>
 </ul>
 
+<h2 id="optimized">Notes for HTML Purifier 4.2.0 and earlier</h3>
+
+<p>
+    Previously, this tutorial gave some incorrect template code for
+    editing raw definitions, and that template code will now produce the
+    error <q>Due to a documentation error in previous version of HTML
+    Purifier...</q>  Here is how to mechanically transform old-style
+    code into new-style code.
+</p>
+
+<p>
+    First, identify all code that edits the raw definition object, and
+    put it together.  Ensure none of this code must be run on every
+    request; if some sub-part needs to always be run, move it outside
+    this block.  Here is an example below, with the raw definition
+    object code bolded.
+</p>
+
+<pre>$config = HTMLPurifier_Config::createDefault();
+$config-&gt;set('HTML.DefinitionID', 'enduser-customize.html tutorial');
+$config-&gt;set('HTML.DefinitionRev', 1);
+$def = $config-&gt;getHTMLDefinition(true);
+<strong>$def->addAttribute('a', 'target', 'Enum#_blank,_self,_target,_top');</strong>
+$purifier = new HTMLPurifier($config);</pre>
+
+<p>
+    Next, replace the raw definition retrieval with a
+    maybeGetRawHTMLDefinition method call inside an if conditional, and
+    place the editing code inside that if block.
+</p>
+
+<pre>$config = HTMLPurifier_Config::createDefault();
+$config-&gt;set('HTML.DefinitionID', 'enduser-customize.html tutorial');
+$config-&gt;set('HTML.DefinitionRev', 1);
+<strong>if ($def = $config-&gt;maybeGetRawHTMLDefinition()) {
+    $def->addAttribute('a', 'target', 'Enum#_blank,_self,_target,_top');
+}</strong>
+$purifier = new HTMLPurifier($config);</pre>
+
+<p>
+    And you're done!  Alternatively, if you're OK with not ever caching
+    your code, the following will still work and not emit warnings.
+</p>
+
+<pre>$config = HTMLPurifier_Config::createDefault();
+$def = $config-&gt;getHTMLDefinition(true);
+$def->addAttribute('a', 'target', 'Enum#_blank,_self,_target,_top');
+$purifier = new HTMLPurifier($config);</pre>
+
+<p>
+    A slightly less efficient version of this was what was going on with
+    old versions of HTML Purifier.
+</p>
+
+<p>
+    <em>Technical notes:</em> ajh pointed out on <a
+        href="http://htmlpurifier.org/phorum/read.php?5,5164,5169#msg-5169">in a forum topic</a> that
+    HTML Purifier appeared to be repeatedly writing to the cache even
+    when a cache entry already existed.  Investigation lead to the
+    discovery of the following infelicity: caching of customized
+    definitions didn't actually work!  The problem was that even though
+    a cache file would be written out at the end of the process, there
+    was no way for HTML Purifier to say, <q>Actually, I've already got a
+        copy of your work, no need to reconfigure your
+        customizations</q>.  This required the API to change: placing
+    all of the customizations to the raw definition object in a
+    conditional which could be skipped.
+</p>
+
 </body></html>
 
-<!-- vim: et sw=4 sts=4 -->
+<!-- vim: et sw=4 sts=4
+-->

docs/enduser-id.html

@@ -31,7 +31,7 @@ by default.</p>
 
 <p>IDs, however, are quite useful functionality to have, so if users start
 complaining about broken anchors you'll probably want to turn them back on
-with %HTML.EnableAttrID. But before you go mucking around with the config
+with %Attr.EnableID. But before you go mucking around with the config
 object, it's probably worth to take some precautions to keep your page
 validating. Why?</p>
 
@@ -56,8 +56,8 @@ validating. Why?</p>
 deal with the most obvious solution: preventing users from using any IDs that
 appear elsewhere on the document.  The method is simple:</p>
 
-<pre>$config->set('HTML', 'EnableAttrID', true);
-$config->set('Attr', 'IDBlacklist' array(
+<pre>$config-&gt;set('Attr.EnableID', true);
+$config-&gt;set('Attr.IDBlacklist' array(
     'list', 'of', 'attribute', 'values', 'that', 'are', 'forbidden'
 ));</pre>
 
@@ -88,8 +88,8 @@ all, they might have simply specified a duplicate ID by accident.</p>
 <p>This method, too, is quite simple: add a prefix to all user IDs. With this
 code:</p>
 
-<pre>$config->set('HTML', 'EnableAttrID', true);
-$config->set('Attr', 'IDPrefix', 'user_');</pre>
+<pre>$config-&gt;set('Attr.EnableID', true);
+$config-&gt;set('Attr.IDPrefix', 'user_');</pre>
 
 <p>...this:</p>
 
@@ -109,7 +109,7 @@ user_ to the beginning.&quot;</p>
 nothing about multiple HTML Purifier outputs on one page.  Thus, we have
 a second configuration value to piggy-back off of: %Attr.IDPrefixLocal:</p>
 
-<pre>$config->set('Attr', 'IDPrefixLocal', 'comment' . $id . '_');</pre>
+<pre>$config-&gt;set('Attr.IDPrefixLocal', 'comment' . $id . '_');</pre>
 
 <p>This new attributes does nothing but append on to regular IDPrefix, but is
 special in that it is volatile: it's value is determined at run-time and
@@ -137,11 +137,12 @@ anchors is beyond me.</p>
 
 <p>To revert back to pre-1.2.0 behavior, simply:</p>
 
-<pre>$config->set('HTML', 'EnableAttrID', true);</pre>
+<pre>$config-&gt;set('Attr.EnableID', true);</pre>
 
 <p>Don't come crying to me when your page mysteriously stops validating, though.</p>
 
 </body>
 </html>
 
-<!-- vim: et sw=4 sts=4 -->
+<!-- vim: et sw=4 sts=4
+-->

docs/enduser-slow.html

@@ -116,4 +116,5 @@ if you decide to do that! Especially if you port HTML Purifier to C++.
 </body>
 </html>
 
-<!-- vim: et sw=4 sts=4 -->
+<!-- vim: et sw=4 sts=4
+-->

docs/enduser-tidy.html

@@ -76,7 +76,7 @@ associated with it, although it may change depending on your doctype.</p>
 change the level of cleaning by setting the %HTML.TidyLevel configuration
 directive:</p>
 
-<pre>$config->set('HTML', 'TidyLevel', 'heavy'); // burn baby burn!</pre>
+<pre>$config-&gt;set('HTML.TidyLevel', 'heavy'); // burn baby burn!</pre>
 
 <h2>Is the light level really light?</h2>
 
@@ -165,17 +165,17 @@ smoketest</a>.</p>
 so happy about the br@clear implementation. That's perfectly fine!
 HTML Purifier will make accomodations:</p>
 
-<pre>$config->set('HTML', 'Doctype', 'XHTML 1.0 Transitional');
-$config->set('HTML', 'TidyLevel', 'heavy'); // all changes, minus...
-<strong>$config->set('HTML', 'TidyRemove', 'br@clear');</strong></pre>
+<pre>$config-&gt;set('HTML.Doctype', 'XHTML 1.0 Transitional');
+$config-&gt;set('HTML.TidyLevel', 'heavy'); // all changes, minus...
+<strong>$config-&gt;set('HTML.TidyRemove', 'br@clear');</strong></pre>
 
 <p>That third line does the magic, removing the br@clear fix
 from the module, ensuring that <code>&lt;br clear="both" /&gt;</code>
 will pass through unharmed. The reverse is possible too:</p>
 
-<pre>$config->set('HTML', 'Doctype', 'XHTML 1.0 Transitional');
-$config->set('HTML', 'TidyLevel', 'none'); // no changes, plus...
-<strong>$config->set('HTML', 'TidyAdd', 'p@align');</strong></pre>
+<pre>$config-&gt;set('HTML.Doctype', 'XHTML 1.0 Transitional');
+$config-&gt;set('HTML.TidyLevel', 'none'); // no changes, plus...
+<strong>$config-&gt;set('HTML.TidyAdd', 'p@align');</strong></pre>
 
 <p>In this case, all transformations are shut off, except for the p@align
 one, which you found handy.</p>
@@ -227,4 +227,5 @@ effectively in the background.</p>
 
 </body></html>
 
-<!-- vim: et sw=4 sts=4 -->
+<!-- vim: et sw=4 sts=4
+-->

docs/enduser-uri-filter.html

@@ -160,27 +160,14 @@
 </p>
 
 <pre>$uri = $config->getDefinition('URI');
-$uri->addFilter(new HTMLPurifier_URIFilter_<strong>NameOfFilter</strong>());</pre>
+$uri->addFilter(new HTMLPurifier_URIFilter_<strong>NameOfFilter</strong>(), $config);</pre>
 
 <p>
-  If you want to be really fancy, you can define a configuration directive
-  for your filter and have HTML Purifier automatically manage whether or
-  not your filter gets loaded or not (this is how internal filters manage
-  things):
+    After adding a filter, you won't be able to set configuration directives.
+    Structure your code accordingly.
 </p>
 
-<pre>HTMLPurifier_ConfigSchema::define(
-    'URI', '<strong>NameOfFilter</strong>', false, 'bool',
-    '<strong>What your filter does.</strong>'
-);
-$uri = $config->getDefinition('URI', true);
-$uri->registerFilter(new HTMLPurifier_URIFilter_<strong>NameOfFilter</strong>());
-</pre>
-
-<p>
-  Now, your filter will only be called when %URI.<strong>NameOfFilter</strong>
-  is set to true.
-</p>
+<!-- XXX: link to new documentation system -->
 
 <h2>Post-filter</h2>
 
@@ -213,4 +200,5 @@ $uri->registerFilter(new HTMLPurifier_URIFilter_<strong>NameOfFilter</strong>())
 
 </body></html>
 
-<!-- vim: et sw=4 sts=4 -->
+<!-- vim: et sw=4 sts=4
+-->

docs/enduser-utf8.html

@@ -561,7 +561,7 @@ page on special characters</a> for more details.
 <h3 id="whyutf8-forms">Forms</h3>
 
 <p>While we're on the tack of users, how do non-UTF-8 web forms deal
-with characters that our outside of their character set? Rather than
+with characters that are outside of their character set? Rather than
 discuss what UTF-8 does right, we're going to show what could go wrong
 if you didn't use UTF-8 and people tried to use characters outside
 of your character encoding.</p>
@@ -1056,4 +1056,5 @@ a more in-depth look into character sets and encodings.</p>
 </body>
 </html>
 
-<!-- vim: et sw=4 sts=4 -->
+<!-- vim: et sw=4 sts=4
+-->

docs/enduser-youtube.html

@@ -67,7 +67,7 @@ into your documents. YouTube's code goes like this:</p>
 </ol>
 
 <p>What point 2 means is that if we have code like <code>&lt;span
-class=&quot;embed-youtube&quot;&gt;AyPzM5WK8ys&lt;/span&gt;</code> your
+class=&quot;youtube-embed&quot;&gt;AyPzM5WK8ys&lt;/span&gt;</code> your
 application can reconstruct the full object from this small snippet that
 passes through HTML Purifier <em>unharmed</em>.
 <a href="http://repo.or.cz/w/htmlpurifier.git?a=blob;hb=HEAD;f=library/HTMLPurifier/Filter/YouTube.php">Show me the code!</a></p>
@@ -75,7 +75,7 @@ passes through HTML Purifier <em>unharmed</em>.
 <p>And the corresponding usage:</p>
 
 <pre>&lt;?php
-    $config->set('Filter', 'YouTube', true);
+    $config-&gt;set('Filter.YouTube', true);
 ?&gt;</pre>
 
 <p>There is a bit going in the two code snippets, so let's explain.</p>
@@ -149,4 +149,5 @@ with the core!</p>
 </body>
 </html>
 
-<!-- vim: et sw=4 sts=4 -->
+<!-- vim: et sw=4 sts=4
+-->

docs/examples/basic.php

@@ -8,8 +8,8 @@ require_once '../../library/HTMLPurifier.auto.php';
 $config = HTMLPurifier_Config::createDefault();
 
 // configuration goes here:
-$config->set('Core', 'Encoding', 'UTF-8'); // replace with your encoding
-$config->set('HTML', 'Doctype', 'XHTML 1.0 Transitional'); // replace with your doctype
+$config->set('Core.Encoding', 'UTF-8'); // replace with your encoding
+$config->set('HTML.Doctype', 'XHTML 1.0 Transitional'); // replace with your doctype
 
 $purifier = new HTMLPurifier($config);
 

docs/fixquotes.htc

@@ -5,4 +5,5 @@ function init() {
 }
 </script>
 
-<!-- vim: et sw=4 sts=4 -->
+<!-- vim: et sw=4 sts=4
+-->

docs/index.html

@@ -117,6 +117,12 @@ the code. They may be upgraded to HTML files or stay as TXT scratchpads.</p>
     <td>Common security issues that may still arise (half-baked).</td>
 </tr>
 
+<tr>
+    <td>Development</td>
+    <td><a href="dev-config-bcbreaks.txt">Config BC Breaks</a></td>
+    <td>Backwards-incompatible changes in HTML Purifier 4.0.0</td>
+</tr>
+
 <tr>
     <td>Development</td>
     <td><a href="dev-code-quality.txt">Code Quality Issues</a></td>
@@ -178,4 +184,5 @@ the code. They may be upgraded to HTML files or stay as TXT scratchpads.</p>
 </body>
 </html>
 
-<!-- vim: et sw=4 sts=4 -->
+<!-- vim: et sw=4 sts=4
+-->

docs/proposal-colors.html

@@ -45,4 +45,5 @@ something like that?</li>
 </body>
 </html>
 
-<!-- vim: et sw=4 sts=4 -->
+<!-- vim: et sw=4 sts=4
+-->

docs/proposal-plists.txt

@@ -0,0 +1,218 @@
+THE UNIVERSAL DESIGN PATTERN: PROPERTIES
+Steve Yegge
+
+Implementation:
+    get(name)
+    put(name, value)
+    has(name)
+    remove(name)
+    iteration, with filtering [this will be our namespaces]
+    parent
+
+Representations:
+    - Keys are strings
+    - It's nice to not need to quote keys (if we formulate our own language,
+      consider this)
+    - Property not present representation (key missing)
+    - Frequent removal/re-add may have null help. If null is valid, use
+      another value. (PHP semantics are weird here)
+
+Data structures:
+    - LinkedHashMap is wonderful (O(1) access and maintains order)
+    - Using a special property that points to the parent is usual
+    - Multiple inheritance possible, need rules for which to lookup first
+    - Iterative inheritance is best
+    - Consider performance!
+
+Deletion
+    - Tricky problem with inheritance
+    - Distinguish between "not found" and "look in my parent for the property"
+    [Maybe HTML Purifier won't allow deletion]
+
+Read/write asymmetry (it's correct!)
+
+Read-only plists
+    - Allow ability to freeze [this is what we have already]
+    - Don't overuse it
+
+Performance:
+    - Intern strings (PHP does this already)
+    - Don't be case-insensitive
+    - If all properties in a plist are known a-priori, you can use a "perfect"
+      hash function. Often overkill.
+    - Copy-on-read caching "plundering" reduces lookup, but uses memory and can
+      grow stale. Use as last resort.
+    - Refactoring to fields. Watch for API compatibility, system complexity,
+      and lack of flexibility.
+    - Refrigerator: external data-structure to hold plists
+
+Transient properties:
+    [Don't need to worry about this]
+    - Use a separate plist for transient properties
+    - Non-numeric override; numeric should ADD
+    - Deletion: removeTransientProperty() and transientlyRemoveProperty()
+
+Persistence:
+    - XML/JSON are good
+    - Text-based is good for readability, maintainability and bootstrapping
+    - Compressed binary format for network transport [not necessary]
+    - RDBMS or XML database
+
+Querying: [not relevant]
+    - XML database is nice for XPath/XQuery
+    - jQuery for JSON
+    - Just load it all into a program
+
+Backfills/Data integrity:
+    - Use usual methods
+    - Lazy backfill is a nice hack
+
+Type systems:
+    - Flags: ReadOnly, Permanent, DontEnum
+    - Typed properties isn't that useful [It's also Not-PHP]
+    - Seperate meta-list of directive properties IS useful
+    - Duck typing is useful for systems designed fully around properties pattern
+
+Trade-off:
+    + Flexibility
+    + Extensibility
+    + Unit-testing/prototype-speed
+    - Performance
+    - Data integrity
+    - Navagability/Query-ability
+    - Reversability (hard to go back)
+
+HTML Purifier
+
+We are not happy with our current system of defining configuration directives,
+because it has become clear that things will get a lot nicer if we allow
+multiple namespaces, and there are some features that naturally lend themselves
+to inheritance, which we do not really support well.
+
+One of the considered implementation changes would be to go from a structure
+like:
+
+array(
+    'Namespace' => array(
+        'Directive' => 'val1',
+        'Directive2' => 'val2',
+    )
+)
+
+to:
+
+array(
+    'Namespace.Directive' => 'val1',
+    'Namespace.Directive2' => 'val2',
+)
+
+The below implementation takes more memory, however, and it makes it a bit
+complicated to grab all values from a namespace.
+
+The alternate implementation choice is to allow nested plists. This keeps
+iteration easy, but is problematic for inheritance (it would be difficult
+to distinguish a plist from an array) and retrieval (when specifying multiple
+namespaces we would need some multiple de-referencing).
+
+----
+
+We can bite the performance hit, and just do iteration with filter
+(the strncmp call should be relatively cheap). Then, users should be able
+to optimize doing something like:
+
+$config = HTMLPurifier_Config::createDefault();
+if (!file_exists('config.php')) {
+    // set up $config
+    $config->save('config.php');
+} else {
+    $config->load('config.php');
+}
+
+Or maybe memcache, or something. This means that "// set up $config" must
+not have any dynamic parts, or the user has to invalidate the cache when
+they do update it. We have to think about this a little more carefully; the
+file call might be more expensive.
+
+----
+
+This might get expensive, however, when we actually care about iterating
+over the configuration and want the actual values. So what about nesting the
+lists?
+
+"ns.sub.directive" => values['ns']['sub']['directive']
+
+We can distinguish between plists and arrays by using ArrayObjects for the
+plists, and regular arrays for the arrays? Alternatively, use ArrayObjects
+for the arrays, and regular arrays for the plists.
+
+----
+
+Implementation demands, and what has caused them:
+
+1. DefinitionCache, the HTML, CSS and URI namespaces have caches attached to them
+   Results:
+    - getBatchSerial()
+        - getBatch() : in general, the ability to traverse just a namespace
+
+2. AutoFormat/Filter, this is a plugin architecture, directives not hard-coded
+    - getBatch()
+
+3. Configuration form
+    - Namespaces used to organize directives
+
+Other than that, we have a pure plist. PERHAPS we should maintain separate things
+for these different demands.
+
+Issue 2: Directives for configuring the plugins are regular plists, but
+when enabling them, while it's "plist-ish", what you're really doing is adding
+them to an array of "autoformatters"/"filters" to enable. We can setup
+magic BC as well as in the new interface, but there should also be an
+add('AutoFormat', 'AutoParagraph'); which does the right thing.
+
+One thing to consider is whether or not inheritance rules will apply to these.
+I'd say yes. That means that they're still plisty, in fact, the underlying
+implementation will probably be a plist. However, they will get their OWN
+plists, and will NOT support nesting.
+
+Issue 1: Our current implementation is generally not efficient; md5(serialize($foo))
+is pretty expensive. So, I don't think there will be any problems if it
+gets "less" efficient, as long as we give users a properly fast alternative;
+DefinitionRev gives us a way to do this, by simply telling the user they must
+update it whenever they update Configuration directives as well. (There are
+obvious BC concerns here).
+
+In such a case, we simply iterate over our plist (performing full retrievals
+for each value), grab the entries we care about, and then serialize and hash.
+It's going to be slow either way, due to the ability of plists to inherit.
+If we ksort(), we don't have to traverse the entire array, however, the
+cost of a ksort() call may not be worth it.
+
+At this point, last time, I started worrying about the performance implications
+of allowing inheritance, and wondering whether or not I wanted to squash
+the plist. At first blush, our code might be under the assumption that
+accessing properties is cheap; but actually we prefer to copy out the value
+into a member variable if it's going to be used many times. With this is mind
+I don't think CPU consumption from a few nested function calls is going to
+be a problem. We *are* going to enforce a function only interface.
+
+The next issue at hand is how we're going to manage the "special" plists,
+which should still be able to be inherited. Basically, it means that multiple
+plists would be attached to the configuration object, which is not the
+best for memory performance. The alternative is to keep them all in one
+big plist, and then eat the one-time cost of traversing the entire plist
+to grab the appropriate values.
+
+I think at this point we can write the generic interface, and then set up separate
+plists if that ends up being necessary for performance (it probably won't.) Now
+lets code our generic plist implementation.
+
+----
+
+Iterating over the plist presents some problems. The way we've chosen to solve
+this is to squash all of the parents.
+
+----
+
+But I don't need iteration.
+
+    vim: et sw=4 sts=4

docs/ref-devnetwork.html

@@ -43,4 +43,5 @@ the development of this library in these forum threads:</p>
 </body>
 </html>
 
-<!-- vim: et sw=4 sts=4 -->
+<!-- vim: et sw=4 sts=4
+-->

docs/specimens/html-align-to-css.html

@@ -163,5 +163,3 @@ div.segment {width:250px; float:left; margin-top:1em;}
 
 </body>
 </html>
-
-<!-- vim: et sw=4 sts=4 -->

docs/specimens/jochem-blok-word.html

@@ -127,5 +127,3 @@ style='color:black'>www.example.com/disclaimer</span></a><o:p></o:p></span></p>
 </body>
 
 </html>
-
-<!-- vim: et sw=4 sts=4 -->

docs/specimens/windows-live-mail-desktop-beta.html

@@ -72,5 +72,3 @@ title="Join Windows Live to share photos using Windows Live Photo E-mail.">Onlin
 pictures are available for 30 days. <A style="COLOR: #0088e4"
 href="http://g.msn.com/5meen_us/175">Get Windows Live Mail desktop to create
 your own photo e-mails. </A></SPAN></NOBR></DIV></BODY></HTML>
-
-<!-- vim: et sw=4 sts=4 -->

extras/ConfigDoc/HTMLXSLTProcessor.php

@@ -11,7 +11,8 @@ class ConfigDoc_HTMLXSLTProcessor
      */
     protected $xsltProcessor;
 
-    public function __construct($proc = false) {
+    public function __construct($proc = false)
+    {
         if ($proc === false) $proc = new XSLTProcessor();
         $this->xsltProcessor = $proc;
     }
@@ -19,7 +20,8 @@ class ConfigDoc_HTMLXSLTProcessor
     /**
      * @note Allows a string $xsl filename to be passed
      */
-    public function importStylesheet($xsl) {
+    public function importStylesheet($xsl)
+    {
         if (is_string($xsl)) {
             $xsl_file = $xsl;
             $xsl = new DOMDocument();
@@ -34,7 +36,8 @@ class ConfigDoc_HTMLXSLTProcessor
      * @return string HTML output
      * @todo Rename to transformToXHTML, as transformToHTML is misleading
      */
-    public function transformToHTML($xml) {
+    public function transformToHTML($xml)
+    {
         if (is_string($xml)) {
             $dom = new DOMDocument();
             $dom->load($xml);
@@ -68,7 +71,8 @@ class ConfigDoc_HTMLXSLTProcessor
      * Bulk sets parameters for the XSL stylesheet
      * @param array $options Associative array of options to set
      */
-    public function setParameters($options) {
+    public function setParameters($options)
+    {
         foreach ($options as $name => $value) {
             $this->xsltProcessor->setParameter('', $name, $value);
         }
@@ -77,7 +81,8 @@ class ConfigDoc_HTMLXSLTProcessor
     /**
      * Forward any other calls to the XSLT processor
      */
-    public function __call($name, $arguments) {
+    public function __call($name, $arguments)
+    {
         call_user_func_array(array($this->xsltProcessor, $name), $arguments);
     }
 

extras/FSTools.php

@@ -15,7 +15,8 @@ class FSTools
     /**
      * Returns a global instance of FSTools
      */
-    static public function singleton() {
+    public static function singleton()
+    {
         if (empty(FSTools::$singleton)) FSTools::$singleton = new FSTools();
         return FSTools::$singleton;
     }
@@ -24,7 +25,8 @@ class FSTools
      * Sets our global singleton to something else; useful for overloading
      * functions.
      */
-    static public function setSingleton($singleton) {
+    public static function setSingleton($singleton)
+    {
         FSTools::$singleton = $singleton;
     }
 
@@ -33,7 +35,8 @@ class FSTools
      * @param string $folder Name of folder to create
      * @note Adapted from the PHP manual comment 76612
      */
-    public function mkdirr($folder) {
+    public function mkdirr($folder)
+    {
         $folders = preg_split("#[\\\\/]#", $folder);
         $base = '';
         for($i = 0, $c = count($folders); $i < $c; $i++) {
@@ -57,7 +60,8 @@ class FSTools
      * so that copied files, if PHP, have includes removed
      * @note Adapted from http://aidanlister.com/repos/v/function.copyr.php
      */
-    public function copyr($source, $dest) {
+    public function copyr($source, $dest)
+    {
         // Simple copy for a file
         if (is_file($source)) {
             return $this->copy($source, $dest);
@@ -92,7 +96,8 @@ class FSTools
      * ignore hidden files, unreadable files, etc. This function
      * applies to copyr().
      */
-    public function copyable($file) {
+    public function copyable($file)
+    {
         return true;
     }
 
@@ -131,7 +136,8 @@ class FSTools
     /**
      * Recursively globs a directory.
      */
-    public function globr($dir, $pattern, $flags = NULL) {
+    public function globr($dir, $pattern, $flags = 0)
+    {
         $files = $this->glob("$dir/$pattern", $flags);
         if ($files === false) $files = array();
         $sub_dirs = $this->glob("$dir/*", GLOB_ONLYDIR);
@@ -148,7 +154,8 @@ class FSTools
      * @warning This function will not work for functions that need
      *      to pass references; manually define a stub function for those.
      */
-    public function __call($name, $args) {
+    public function __call($name, $args)
+    {
         return call_user_func_array($name, $args);
     }
 

extras/FSTools/File.php

@@ -23,7 +23,8 @@ class FSTools_File
      * Filename of file you wish to instantiate.
      * @note This file need not exist
      */
-    public function __construct($name, $fs = false) {
+    public function __construct($name, $fs = false)
+    {
         $this->name = $name;
         $this->fs = $fs ? $fs : FSTools::singleton();
     }
@@ -38,27 +39,32 @@ class FSTools_File
      * Retrieves the contents of a file
      * @todo Throw an exception if file doesn't exist
      */
-    public function get() {
+    public function get()
+    {
         return $this->fs->file_get_contents($this->name);
     }
 
     /** Writes contents to a file, creates new file if necessary */
-    public function write($contents) {
+    public function write($contents)
+    {
         return $this->fs->file_put_contents($this->name, $contents);
     }
 
     /** Deletes the file */
-    public function delete() {
+    public function delete()
+    {
         return $this->fs->unlink($this->name);
     }
 
     /** Returns true if file exists and is a file. */
-    public function exists() {
+    public function exists()
+    {
         return $this->fs->is_file($this->name);
     }
 
     /** Returns last file modification time */
-    public function getMTime() {
+    public function getMTime()
+    {
         return $this->fs->filemtime($this->name);
     }
 
@@ -67,19 +73,22 @@ class FSTools_File
      * @note We ignore errors because of some weird owner trickery due
      *       to SVN duality
      */
-    public function chmod($octal_code) {
+    public function chmod($octal_code)
+    {
         return @$this->fs->chmod($this->name, $octal_code);
     }
 
     /** Opens file's handle */
-    public function open($mode) {
+    public function open($mode)
+    {
         if ($this->handle) $this->close();
         $this->handle = $this->fs->fopen($this->name, $mode);
         return true;
     }
 
     /** Closes file's handle */
-    public function close() {
+    public function close()
+    {
         if (!$this->handle) return false;
         $status = $this->fs->fclose($this->handle);
         $this->handle = false;
@@ -87,37 +96,43 @@ class FSTools_File
     }
 
     /** Retrieves a line from an open file, with optional max length $length */
-    public function getLine($length = null) {
+    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() {
+    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) {
+    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($string) {
+    public function put($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() {
+    public function eof()
+    {
         if (!$this->handle) return true;
         return $this->fs->feof($this->handle);
     }
 
-    public function __destruct() {
+    public function __destruct()
+    {
         if ($this->handle) $this->close();
     }
 

extras/HTMLPurifierExtras.autoload-legacy.php

@@ -0,0 +1,15 @@
+<?php
+
+/**
+ * @file
+ * Legacy autoloader for systems lacking spl_autoload_register
+ *
+ * Must be separate to prevent deprecation warning on PHP 7.2
+ */
+
+function __autoload($class)
+{
+    return HTMLPurifierExtras::autoload($class);
+}
+
+// vim: et sw=4 sts=4

extras/HTMLPurifierExtras.autoload.php

@@ -17,9 +17,7 @@ if (function_exists('spl_autoload_register')) {
         spl_autoload_register('__autoload');
     }
 } elseif (!function_exists('__autoload')) {
-    function __autoload($class) {
-        return HTMLPurifierExtras::autoload($class);
-    }
+    require dirname(__FILE__) . '/HTMLPurifierExtras.autoload-legacy.php';
 }
 
 // vim: et sw=4 sts=4

extras/HTMLPurifierExtras.php

@@ -7,14 +7,16 @@
 class HTMLPurifierExtras
 {
 
-    public static function autoload($class) {
+    public static function autoload($class)
+    {
         $path = HTMLPurifierExtras::getPath($class);
         if (!$path) return false;
         require $path;
         return true;
     }
 
-    public static function getPath($class) {
+    public static function getPath($class)
+    {
         if (
             strncmp('FSTools', $class, 7) !== 0 &&
             strncmp('ConfigDoc', $class, 9) !== 0

library/HTMLPurifier.autoload-legacy.php

@@ -0,0 +1,14 @@
+<?php
+
+/**
+ * @file
+ * Legacy autoloader for systems lacking spl_autoload_register
+ *
+ */
+
+spl_autoload_register(function($class)
+{
+     return HTMLPurifier_Bootstrap::autoload($class);
+});
+
+// vim: et sw=4 sts=4

library/HTMLPurifier.autoload.php

@@ -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 +14,12 @@ if (function_exists('spl_autoload_register') && function_exists('spl_autoload_un
         spl_autoload_register('__autoload');
     }
 } elseif (!function_exists('__autoload')) {
-    function __autoload($class) {
-        return HTMLPurifier_Bootstrap::autoload($class);
-    }
+    require dirname(__FILE__) . '/HTMLPurifier.autoload-legacy.php';
+}
+
+// phpcs:ignore PHPCompatibility.IniDirectives.RemovedIniDirectives.zend_ze1_compatibility_modeRemoved
+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

library/HTMLPurifier.composer.php

@@ -0,0 +1,4 @@
+<?php
+if (!defined('HTMLPURIFIER_PREFIX')) {
+    define('HTMLPURIFIER_PREFIX', dirname(__FILE__));
+}

library/HTMLPurifier.func.php

@@ -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();

library/HTMLPurifier.includes.php

@@ -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 3.3.0
+ * @version 4.18.0
  *
  * @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';
@@ -90,22 +95,26 @@ require 'HTMLPurifier/AttrDef/CSS/DenyElementDecorator.php';
 require 'HTMLPurifier/AttrDef/CSS/Filter.php';
 require 'HTMLPurifier/AttrDef/CSS/Font.php';
 require 'HTMLPurifier/AttrDef/CSS/FontFamily.php';
+require 'HTMLPurifier/AttrDef/CSS/Ident.php';
 require 'HTMLPurifier/AttrDef/CSS/ImportantDecorator.php';
 require 'HTMLPurifier/AttrDef/CSS/Length.php';
 require 'HTMLPurifier/AttrDef/CSS/ListStyle.php';
 require 'HTMLPurifier/AttrDef/CSS/Multiple.php';
 require 'HTMLPurifier/AttrDef/CSS/Percentage.php';
+require 'HTMLPurifier/AttrDef/CSS/Ratio.php';
 require 'HTMLPurifier/AttrDef/CSS/TextDecoration.php';
 require 'HTMLPurifier/AttrDef/CSS/URI.php';
 require 'HTMLPurifier/AttrDef/HTML/Bool.php';
+require 'HTMLPurifier/AttrDef/HTML/Nmtokens.php';
+require 'HTMLPurifier/AttrDef/HTML/Class.php';
 require 'HTMLPurifier/AttrDef/HTML/Color.php';
+require 'HTMLPurifier/AttrDef/HTML/ContentEditable.php';
 require 'HTMLPurifier/AttrDef/HTML/FrameTarget.php';
 require 'HTMLPurifier/AttrDef/HTML/ID.php';
 require 'HTMLPurifier/AttrDef/HTML/Pixels.php';
 require 'HTMLPurifier/AttrDef/HTML/Length.php';
 require 'HTMLPurifier/AttrDef/HTML/LinkTypes.php';
 require 'HTMLPurifier/AttrDef/HTML/MultiLength.php';
-require 'HTMLPurifier/AttrDef/HTML/Nmtokens.php';
 require 'HTMLPurifier/AttrDef/URI/Email.php';
 require 'HTMLPurifier/AttrDef/URI/Host.php';
 require 'HTMLPurifier/AttrDef/URI/IPv4.php';
@@ -123,14 +132,20 @@ require 'HTMLPurifier/AttrTransform/Input.php';
 require 'HTMLPurifier/AttrTransform/Lang.php';
 require 'HTMLPurifier/AttrTransform/Length.php';
 require 'HTMLPurifier/AttrTransform/Name.php';
+require 'HTMLPurifier/AttrTransform/NameSync.php';
+require 'HTMLPurifier/AttrTransform/Nofollow.php';
 require 'HTMLPurifier/AttrTransform/SafeEmbed.php';
 require 'HTMLPurifier/AttrTransform/SafeObject.php';
 require 'HTMLPurifier/AttrTransform/SafeParam.php';
 require 'HTMLPurifier/AttrTransform/ScriptRequired.php';
+require 'HTMLPurifier/AttrTransform/TargetBlank.php';
+require 'HTMLPurifier/AttrTransform/TargetNoopener.php';
+require 'HTMLPurifier/AttrTransform/TargetNoreferrer.php';
 require 'HTMLPurifier/AttrTransform/Textarea.php';
 require 'HTMLPurifier/ChildDef/Chameleon.php';
 require 'HTMLPurifier/ChildDef/Custom.php';
 require 'HTMLPurifier/ChildDef/Empty.php';
+require 'HTMLPurifier/ChildDef/List.php';
 require 'HTMLPurifier/ChildDef/Required.php';
 require 'HTMLPurifier/ChildDef/Optional.php';
 require 'HTMLPurifier/ChildDef/StrictBlockquote.php';
@@ -145,10 +160,12 @@ 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';
@@ -156,10 +173,14 @@ require 'HTMLPurifier/HTMLModule/Proprietary.php';
 require 'HTMLPurifier/HTMLModule/Ruby.php';
 require 'HTMLPurifier/HTMLModule/SafeEmbed.php';
 require 'HTMLPurifier/HTMLModule/SafeObject.php';
+require 'HTMLPurifier/HTMLModule/SafeScripting.php';
 require 'HTMLPurifier/HTMLModule/Scripting.php';
 require 'HTMLPurifier/HTMLModule/StyleAttribute.php';
 require 'HTMLPurifier/HTMLModule/Tables.php';
 require 'HTMLPurifier/HTMLModule/Target.php';
+require 'HTMLPurifier/HTMLModule/TargetBlank.php';
+require 'HTMLPurifier/HTMLModule/TargetNoopener.php';
+require 'HTMLPurifier/HTMLModule/TargetNoreferrer.php';
 require 'HTMLPurifier/HTMLModule/Text.php';
 require 'HTMLPurifier/HTMLModule/Tidy.php';
 require 'HTMLPurifier/HTMLModule/XMLCommonAttributes.php';
@@ -174,9 +195,13 @@ require 'HTMLPurifier/Injector/DisplayLinkURI.php';
 require 'HTMLPurifier/Injector/Linkify.php';
 require 'HTMLPurifier/Injector/PurifierLinkify.php';
 require 'HTMLPurifier/Injector/RemoveEmpty.php';
+require 'HTMLPurifier/Injector/RemoveSpansWithoutAttributes.php';
 require 'HTMLPurifier/Injector/SafeObject.php';
 require 'HTMLPurifier/Lexer/DOMLex.php';
 require 'HTMLPurifier/Lexer/DirectLex.php';
+require 'HTMLPurifier/Node/Comment.php';
+require 'HTMLPurifier/Node/Element.php';
+require 'HTMLPurifier/Node/Text.php';
 require 'HTMLPurifier/Strategy/Composite.php';
 require 'HTMLPurifier/Strategy/Core.php';
 require 'HTMLPurifier/Strategy/FixNesting.php';
@@ -193,14 +218,19 @@ require 'HTMLPurifier/Token/Start.php';
 require 'HTMLPurifier/Token/Text.php';
 require 'HTMLPurifier/URIFilter/DisableExternal.php';
 require 'HTMLPurifier/URIFilter/DisableExternalResources.php';
+require 'HTMLPurifier/URIFilter/DisableResources.php';
 require 'HTMLPurifier/URIFilter/HostBlacklist.php';
 require 'HTMLPurifier/URIFilter/MakeAbsolute.php';
 require 'HTMLPurifier/URIFilter/Munge.php';
+require 'HTMLPurifier/URIFilter/SafeIframe.php';
+require 'HTMLPurifier/URIScheme/data.php';
+require 'HTMLPurifier/URIScheme/file.php';
 require 'HTMLPurifier/URIScheme/ftp.php';
 require 'HTMLPurifier/URIScheme/http.php';
 require 'HTMLPurifier/URIScheme/https.php';
 require 'HTMLPurifier/URIScheme/mailto.php';
 require 'HTMLPurifier/URIScheme/news.php';
 require 'HTMLPurifier/URIScheme/nntp.php';
+require 'HTMLPurifier/URIScheme/tel.php';
 require 'HTMLPurifier/VarParser/Flexible.php';
 require 'HTMLPurifier/VarParser/Native.php';

library/HTMLPurifier.kses.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();
     $allowed_attributes = array();
@@ -17,11 +18,10 @@ function kses($string, $allowed_html, $allowed_protocols = null) {
             $allowed_attributes["$element.$attribute"] = true;
         }
     }
-    $config->set('HTML', 'AllowedElements', $allowed_elements);
-    $config->set('HTML', 'AllowedAttributes', $allowed_attributes);
-    $allowed_schemes = array();
+    $config->set('HTML.AllowedElements', $allowed_elements);
+    $config->set('HTML.AllowedAttributes', $allowed_attributes);
     if ($allowed_protocols !== null) {
-        $config->set('URI', 'AllowedSchemes', $allowed_protocols);
+        $config->set('URI.AllowedSchemes', $allowed_protocols);
     }
     $purifier = new HTMLPurifier($config);
     return $purifier->purify($string);

library/HTMLPurifier.php

@@ -19,7 +19,7 @@
  */
 
 /*
-    HTML Purifier 3.3.0 - Standards Compliant HTML Filtering
+    HTML Purifier 4.18.0 - 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 = '3.3.0';
-
-    /** Constant with version of HTML Purifier */
-    const VERSION = '3.3.0';
-
-    /** 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 = '4.18.0';
 
     /**
-     * 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 = '4.18.0';
+
+    /**
+     * 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|mixed $config Optional HTMLPurifier_Config object
+     *                for all instances of the purifier, if omitted, a default
+     *                configuration is supplied (which can be overridden on a
+     *                per-use basis).
      *                The parameter can also be any type that
      *                HTMLPurifier_Config::create() supports.
      */
-    public function __construct($config = null) {
-
+    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;
 
@@ -128,7 +159,7 @@ class HTMLPurifier
         $context->register('Generator', $this->generator);
 
         // set up global context variables
-        if ($config->get('Core', 'CollectErrors')) {
+        if ($config->get('Core.CollectErrors')) {
             // may get moved out if other facilities use it
             $language_factory = HTMLPurifier_LanguageFactory::instance();
             $language = $language_factory->create($config, $context);
@@ -151,7 +182,12 @@ class HTMLPurifier
         unset($filter_flags['Custom']);
         $filters = array();
         foreach ($filter_flags as $filter => $flag) {
-            if (!$flag) continue;
+            if (!$flag) {
+                continue;
+            }
+            if (strpos($filter, '.') !== false) {
+                continue;
+            }
             $class = "HTMLPurifier_Filter_$filter";
             $filters[] = new $class;
         }
@@ -174,9 +210,12 @@ class HTMLPurifier
                     // list of un-purified tokens
                     $lexer->tokenizeHTML(
                         // un-purified HTML
-                        $html, $config, $context
+                        $html,
+                        $config,
+                        $context
                     ),
-                    $config, $context
+                    $config,
+                    $context
                 )
             );
 
@@ -191,27 +230,41 @@ 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);
+        $array = array();
+        foreach($array_of_html as $key=>$value){
+            if (is_array($value)) {
+                $array[$key] = $this->purifyArray($value, $config);
+            } else {
+                $array[$key] = $this->purify($value, $config);
+            }
             $context_array[$key] = $this->context;
         }
         $this->context = $context_array;
-        return $array_of_html;
+        return $array;
     }
 
     /**
      * 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;
@@ -225,12 +278,20 @@ 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

library/HTMLPurifier.safe-includes.php

@@ -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';
@@ -84,22 +89,26 @@ require_once $__dir . '/HTMLPurifier/AttrDef/CSS/DenyElementDecorator.php';
 require_once $__dir . '/HTMLPurifier/AttrDef/CSS/Filter.php';
 require_once $__dir . '/HTMLPurifier/AttrDef/CSS/Font.php';
 require_once $__dir . '/HTMLPurifier/AttrDef/CSS/FontFamily.php';
+require_once $__dir . '/HTMLPurifier/AttrDef/CSS/Ident.php';
 require_once $__dir . '/HTMLPurifier/AttrDef/CSS/ImportantDecorator.php';
 require_once $__dir . '/HTMLPurifier/AttrDef/CSS/Length.php';
 require_once $__dir . '/HTMLPurifier/AttrDef/CSS/ListStyle.php';
 require_once $__dir . '/HTMLPurifier/AttrDef/CSS/Multiple.php';
 require_once $__dir . '/HTMLPurifier/AttrDef/CSS/Percentage.php';
+require_once $__dir . '/HTMLPurifier/AttrDef/CSS/Ratio.php';
 require_once $__dir . '/HTMLPurifier/AttrDef/CSS/TextDecoration.php';
 require_once $__dir . '/HTMLPurifier/AttrDef/CSS/URI.php';
 require_once $__dir . '/HTMLPurifier/AttrDef/HTML/Bool.php';
+require_once $__dir . '/HTMLPurifier/AttrDef/HTML/Nmtokens.php';
+require_once $__dir . '/HTMLPurifier/AttrDef/HTML/Class.php';
 require_once $__dir . '/HTMLPurifier/AttrDef/HTML/Color.php';
+require_once $__dir . '/HTMLPurifier/AttrDef/HTML/ContentEditable.php';
 require_once $__dir . '/HTMLPurifier/AttrDef/HTML/FrameTarget.php';
 require_once $__dir . '/HTMLPurifier/AttrDef/HTML/ID.php';
 require_once $__dir . '/HTMLPurifier/AttrDef/HTML/Pixels.php';
 require_once $__dir . '/HTMLPurifier/AttrDef/HTML/Length.php';
 require_once $__dir . '/HTMLPurifier/AttrDef/HTML/LinkTypes.php';
 require_once $__dir . '/HTMLPurifier/AttrDef/HTML/MultiLength.php';
-require_once $__dir . '/HTMLPurifier/AttrDef/HTML/Nmtokens.php';
 require_once $__dir . '/HTMLPurifier/AttrDef/URI/Email.php';
 require_once $__dir . '/HTMLPurifier/AttrDef/URI/Host.php';
 require_once $__dir . '/HTMLPurifier/AttrDef/URI/IPv4.php';
@@ -117,14 +126,20 @@ require_once $__dir . '/HTMLPurifier/AttrTransform/Input.php';
 require_once $__dir . '/HTMLPurifier/AttrTransform/Lang.php';
 require_once $__dir . '/HTMLPurifier/AttrTransform/Length.php';
 require_once $__dir . '/HTMLPurifier/AttrTransform/Name.php';
+require_once $__dir . '/HTMLPurifier/AttrTransform/NameSync.php';
+require_once $__dir . '/HTMLPurifier/AttrTransform/Nofollow.php';
 require_once $__dir . '/HTMLPurifier/AttrTransform/SafeEmbed.php';
 require_once $__dir . '/HTMLPurifier/AttrTransform/SafeObject.php';
 require_once $__dir . '/HTMLPurifier/AttrTransform/SafeParam.php';
 require_once $__dir . '/HTMLPurifier/AttrTransform/ScriptRequired.php';
+require_once $__dir . '/HTMLPurifier/AttrTransform/TargetBlank.php';
+require_once $__dir . '/HTMLPurifier/AttrTransform/TargetNoopener.php';
+require_once $__dir . '/HTMLPurifier/AttrTransform/TargetNoreferrer.php';
 require_once $__dir . '/HTMLPurifier/AttrTransform/Textarea.php';
 require_once $__dir . '/HTMLPurifier/ChildDef/Chameleon.php';
 require_once $__dir . '/HTMLPurifier/ChildDef/Custom.php';
 require_once $__dir . '/HTMLPurifier/ChildDef/Empty.php';
+require_once $__dir . '/HTMLPurifier/ChildDef/List.php';
 require_once $__dir . '/HTMLPurifier/ChildDef/Required.php';
 require_once $__dir . '/HTMLPurifier/ChildDef/Optional.php';
 require_once $__dir . '/HTMLPurifier/ChildDef/StrictBlockquote.php';
@@ -139,10 +154,12 @@ 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';
@@ -150,10 +167,14 @@ require_once $__dir . '/HTMLPurifier/HTMLModule/Proprietary.php';
 require_once $__dir . '/HTMLPurifier/HTMLModule/Ruby.php';
 require_once $__dir . '/HTMLPurifier/HTMLModule/SafeEmbed.php';
 require_once $__dir . '/HTMLPurifier/HTMLModule/SafeObject.php';
+require_once $__dir . '/HTMLPurifier/HTMLModule/SafeScripting.php';
 require_once $__dir . '/HTMLPurifier/HTMLModule/Scripting.php';
 require_once $__dir . '/HTMLPurifier/HTMLModule/StyleAttribute.php';
 require_once $__dir . '/HTMLPurifier/HTMLModule/Tables.php';
 require_once $__dir . '/HTMLPurifier/HTMLModule/Target.php';
+require_once $__dir . '/HTMLPurifier/HTMLModule/TargetBlank.php';
+require_once $__dir . '/HTMLPurifier/HTMLModule/TargetNoopener.php';
+require_once $__dir . '/HTMLPurifier/HTMLModule/TargetNoreferrer.php';
 require_once $__dir . '/HTMLPurifier/HTMLModule/Text.php';
 require_once $__dir . '/HTMLPurifier/HTMLModule/Tidy.php';
 require_once $__dir . '/HTMLPurifier/HTMLModule/XMLCommonAttributes.php';
@@ -168,9 +189,13 @@ require_once $__dir . '/HTMLPurifier/Injector/DisplayLinkURI.php';
 require_once $__dir . '/HTMLPurifier/Injector/Linkify.php';
 require_once $__dir . '/HTMLPurifier/Injector/PurifierLinkify.php';
 require_once $__dir . '/HTMLPurifier/Injector/RemoveEmpty.php';
+require_once $__dir . '/HTMLPurifier/Injector/RemoveSpansWithoutAttributes.php';
 require_once $__dir . '/HTMLPurifier/Injector/SafeObject.php';
 require_once $__dir . '/HTMLPurifier/Lexer/DOMLex.php';
 require_once $__dir . '/HTMLPurifier/Lexer/DirectLex.php';
+require_once $__dir . '/HTMLPurifier/Node/Comment.php';
+require_once $__dir . '/HTMLPurifier/Node/Element.php';
+require_once $__dir . '/HTMLPurifier/Node/Text.php';
 require_once $__dir . '/HTMLPurifier/Strategy/Composite.php';
 require_once $__dir . '/HTMLPurifier/Strategy/Core.php';
 require_once $__dir . '/HTMLPurifier/Strategy/FixNesting.php';
@@ -187,14 +212,19 @@ require_once $__dir . '/HTMLPurifier/Token/Start.php';
 require_once $__dir . '/HTMLPurifier/Token/Text.php';
 require_once $__dir . '/HTMLPurifier/URIFilter/DisableExternal.php';
 require_once $__dir . '/HTMLPurifier/URIFilter/DisableExternalResources.php';
+require_once $__dir . '/HTMLPurifier/URIFilter/DisableResources.php';
 require_once $__dir . '/HTMLPurifier/URIFilter/HostBlacklist.php';
 require_once $__dir . '/HTMLPurifier/URIFilter/MakeAbsolute.php';
 require_once $__dir . '/HTMLPurifier/URIFilter/Munge.php';
+require_once $__dir . '/HTMLPurifier/URIFilter/SafeIframe.php';
+require_once $__dir . '/HTMLPurifier/URIScheme/data.php';
+require_once $__dir . '/HTMLPurifier/URIScheme/file.php';
 require_once $__dir . '/HTMLPurifier/URIScheme/ftp.php';
 require_once $__dir . '/HTMLPurifier/URIScheme/http.php';
 require_once $__dir . '/HTMLPurifier/URIScheme/https.php';
 require_once $__dir . '/HTMLPurifier/URIScheme/mailto.php';
 require_once $__dir . '/HTMLPurifier/URIScheme/news.php';
 require_once $__dir . '/HTMLPurifier/URIScheme/nntp.php';
+require_once $__dir . '/HTMLPurifier/URIScheme/tel.php';
 require_once $__dir . '/HTMLPurifier/VarParser/Flexible.php';
 require_once $__dir . '/HTMLPurifier/VarParser/Native.php';

library/HTMLPurifier/Arborize.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;
+    }
+}

library/HTMLPurifier/AttrCollections.php

@@ -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 +17,16 @@ 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)
+    {
+        $this->doConstruct($attr_types, $modules);
+    }
+
+    public function doConstruct($attr_types, $modules)
+    {
         // load extensions from the modules
         foreach ($modules as $module) {
             foreach ($module->attr_collections as $coll_i => $coll) {
@@ -30,7 +37,9 @@ class HTMLPurifier_AttrCollections
                     if ($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] = $attr;
@@ -49,20 +58,29 @@ class HTMLPurifier_AttrCollections
     /**
      * Takes a reference to an attribute associative array and performs
      * all inclusions specified by the zero index.
-     * @param &$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 +94,24 @@ 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 +142,7 @@ class HTMLPurifier_AttrCollections
                 unset($attr[$def_i]);
             }
         }
-
     }
-
 }
 
 // vim: et sw=4 sts=4

library/HTMLPurifier/AttrDef.php

@@ -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
@@ -77,11 +81,64 @@ 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) {
-        return preg_replace('/rgb\((\d+)\s*,\s*(\d+)\s*,\s*(\d+)\)/', 'rgb(\1,\2,\3)', $string);
+    protected function mungeRgb($string)
+    {
+        $p = '\s*(\d+(\.\d+)?([%]?))\s*';
+
+        if (preg_match('/(rgba|hsla)\(/', $string)) {
+            return preg_replace('/(rgba|hsla)\('.$p.','.$p.','.$p.','.$p.'\)/', '\1(\2,\5,\8,\11)', $string);
+        }
+
+        return preg_replace('/(rgb|hsl)\('.$p.','.$p.','.$p.'\)/', '\1(\2,\5,\8)', $string);
     }
 
+    /**
+     * Parses a possibly escaped CSS string and returns the "pure"
+     * version of it.
+     */
+    protected function expandCSSEscape($string)
+    {
+        // flexibly parse it
+        $ret = '';
+        for ($i = 0, $c = strlen($string); $i < $c; $i++) {
+            if ($string[$i] === '\\') {
+                $i++;
+                if ($i >= $c) {
+                    $ret .= '\\';
+                    break;
+                }
+                if (ctype_xdigit($string[$i])) {
+                    $code = $string[$i];
+                    for ($a = 1, $i++; $i < $c && $a < 6; $i++, $a++) {
+                        if (!ctype_xdigit($string[$i])) {
+                            break;
+                        }
+                        $code .= $string[$i];
+                    }
+                    // We have to be extremely careful when adding
+                    // new characters, to make sure we're not breaking
+                    // the encoding.
+                    $char = HTMLPurifier_Encoder::unichr(hexdec($code));
+                    if (HTMLPurifier_Encoder::cleanUTF8($char) === '') {
+                        continue;
+                    }
+                    $ret .= $char;
+                    if ($i < $c && trim($string[$i]) !== '') {
+                        $i--;
+                    }
+                    continue;
+                }
+                if ($string[$i] === "\n") {
+                    continue;
+                }
+            }
+            $ret .= $string[$i];
+        }
+        return $ret;
+    }
 }
 
 // vim: et sw=4 sts=4

library/HTMLPurifier/AttrDef/CSS.php

@@ -14,20 +14,60 @@
 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();
+        $allow_duplicates = $config->get("CSS.AllowDuplicates");
 
-        // we're going to break the spec and explode by semicolons.
-        // This is because semicolon rarely appears in escaped form
-        // Doing this is generally flaky but fast
-        // IT MIGHT APPEAR IN URIs, see HTMLPurifier_AttrDef_CSSURI
-        // for details
+        $universal_attrdef = new HTMLPurifier_AttrDef_Enum(
+            array(
+                'initial',
+                'inherit',
+                'unset',
+            )
+        );
+
+        // According to the CSS2.1 spec, the places where a
+        // non-delimiting semicolon can appear are in strings
+        // escape sequences.   So here is some dumb hack to
+        // handle quotes.
+        $len = strlen($css);
+        $accum = "";
+        $declarations = array();
+        $quoted = false;
+        for ($i = 0; $i < $len; $i++) {
+            $c = strcspn($css, ";'\"", $i);
+            $accum .= substr($css, $i, $c);
+            $i += $c;
+            if ($i == $len) break;
+            $d = $css[$i];
+            if ($quoted) {
+                $accum .= $d;
+                if ($d == $quoted) {
+                    $quoted = false;
+                }
+            } else {
+                if ($d == ";") {
+                    $declarations[] = $accum;
+                    $accum = "";
+                } else {
+                    $accum .= $d;
+                    $quoted = $d;
+                }
+            }
+        }
+        if ($accum != "") $declarations[] = $accum;
 
-        $declarations = explode(';', $css);
         $propvalues = array();
+        $new_declarations = '';
 
         /**
          * Name of the current CSS property being validated.
@@ -36,35 +76,49 @@ 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;
-            // inefficient call, since the validator will do this again
-            if (strtolower(trim($value)) !== 'inherit') {
-                // inherit works for everything (but only on the base property)
-                $result = $definition->info[$property]->validate(
-                    $value, $config, $context );
-            } else {
-                $result = 'inherit';
+            } while (0);
+            if (!$ok) {
+                continue;
+            }
+            $result = $universal_attrdef->validate($value, $config, $context);
+            if ($result === false) {
+                $result = $definition->info[$property]->validate(
+                    $value,
+                    $config,
+                    $context
+                );
+            }
+            if ($result === false) {
+                continue;
+            }
+            if ($allow_duplicates) {
+                $new_declarations .= "$property:$result;";
+            } else {
+                $propvalues[$property] = $result;
             }
-            if ($result === false) continue;
-            $propvalues[$property] = $result;
         }
 
         $context->destroy('CurrentCSSProperty');
@@ -73,7 +127,6 @@ class HTMLPurifier_AttrDef_CSS extends HTMLPurifier_AttrDef
         // slightly inefficient, but it's the only way of getting rid of
         // duplicates. Perhaps config to optimize it, but not now.
 
-        $new_declarations = '';
         foreach ($propvalues as $prop => $value) {
             $new_declarations .= "$prop:$value;";
         }

library/HTMLPurifier/AttrDef/CSS/AlphaValue.php

@@ -3,19 +3,32 @@
 class HTMLPurifier_AttrDef_CSS_AlphaValue extends HTMLPurifier_AttrDef_CSS_Number
 {
 
-    public function __construct() {
+    public function __construct()
+    {
         parent::__construct(false); // opacity is non-negative, but we will clamp it
     }
 
-    public function validate($number, $config, $context) {
+    /**
+     * @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) $result = '1';
+        if ($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

library/HTMLPurifier/AttrDef/CSS/Background.php

@@ -9,53 +9,75 @@ 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'];
         $this->info['background-repeat'] = $def->info['background-repeat'];
         $this->info['background-attachment'] = $def->info['background-attachment'];
         $this->info['background-position'] = $def->info['background-position'];
+        $this->info['background-size'] = $def->info['background-size'];
     }
 
-    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;
+        $caught['size'] = 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 +87,9 @@ 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 +97,17 @@ 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

library/HTMLPurifier/AttrDef/CSS/BackgroundPosition.php

@@ -44,22 +44,38 @@
 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);
 
         $keywords = array();
         $keywords['h'] = false; // left, right
         $keywords['v'] = false; // top, bottom
-        $keywords['c'] = false; // center
+        $keywords['ch'] = false; // center (first word)
+        $keywords['cv'] = false; // center (second word)
         $measures = array();
 
         $i = 0;
@@ -73,12 +89,21 @@ 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);
             if (isset($lookup[$lbit])) {
                 $status = $lookup[$lbit];
+                if ($status == 'c') {
+                    if ($i == 0) {
+                        $status = 'ch';
+                    } else {
+                        $status = 'cv';
+                    }
+                }
                 $keywords[$status] = $lbit;
                 $i++;
             }
@@ -96,31 +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[] = $keywords['h'];
-        elseif (count($measures))   $ret[] = array_shift($measures);
-        elseif ($keywords['c']) {
-            $ret[] = $keywords['c'];
-            $keywords['c'] = false; // prevent re-use: center = center center
+        if ($keywords['h']) {
+            $ret[] = $keywords['h'];
+        } elseif ($keywords['ch']) {
+            $ret[] = $keywords['ch'];
+            $keywords['cv'] = false; // prevent re-use: center = center center
+        } elseif (count($measures)) {
+            $ret[] = array_shift($measures);
         }
 
-        if     ($keywords['v'])     $ret[] = $keywords['v'];
-        elseif (count($measures))   $ret[] = array_shift($measures);
-        elseif ($keywords['c'])     $ret[] = $keywords['c'];
+        if ($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

library/HTMLPurifier/AttrDef/CSS/Border.php

@@ -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

library/HTMLPurifier/AttrDef/CSS/Color.php

@@ -6,56 +6,137 @@
 class HTMLPurifier_AttrDef_CSS_Color extends HTMLPurifier_AttrDef
 {
 
-    public function validate($color, $config, $context) {
+    /**
+     * @type HTMLPurifier_AttrDef_CSS_AlphaValue
+     */
+    protected $alpha;
 
+    public function __construct()
+    {
+        $this->alpha = new HTMLPurifier_AttrDef_CSS_AlphaValue();
+    }
+
+    /**
+     * @param string $color
+     * @param HTMLPurifier_Config $config
+     * @param HTMLPurifier_Context $context
+     * @return bool|string
+     */
+    public function validate($color, $config, $context)
+    {
         static $colors = null;
-        if ($colors === null) $colors = $config->get('Core', 'ColorKeywords');
+        if ($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
+        if (preg_match('#(rgb|rgba|hsl|hsla)\(#', $color, $matches) === 1) {
             $length = strlen($color);
-            if (strpos($color, ')') !== $length - 1) return false;
-            $triad = substr($color, 4, $length - 4 - 1);
-            $parts = explode(',', $triad);
-            if (count($parts) !== 3) return false;
-            $type = false; // to ensure that they're all the same type
+            if (strpos($color, ')') !== $length - 1) {
+                return false;
+            }
+
+            // get used function : rgb, rgba, hsl or hsla
+            $function = $matches[1];
+
+            $parameters_size = 3;
+            $alpha_channel = false;
+            if (substr($function, -1) === 'a') {
+                $parameters_size = 4;
+                $alpha_channel = true;
+            }
+
+            /*
+             * Allowed types for values :
+             * parameter_position => [type => max_value]
+             */
+            $allowed_types = array(
+                1 => array('percentage' => 100, 'integer' => 255),
+                2 => array('percentage' => 100, 'integer' => 255),
+                3 => array('percentage' => 100, 'integer' => 255),
+            );
+            $allow_different_types = false;
+
+            if (strpos($function, 'hsl') !== false) {
+                $allowed_types = array(
+                    1 => array('integer' => 360),
+                    2 => array('percentage' => 100),
+                    3 => array('percentage' => 100),
+                );
+                $allow_different_types = true;
+            }
+
+            $values = trim(str_replace($function, '', $color), ' ()');
+
+            $parts = explode(',', $values);
+            if (count($parts) !== $parameters_size) {
+                return false;
+            }
+
+            $type = false;
             $new_parts = array();
+            $i = 0;
+
             foreach ($parts as $part) {
+                $i++;
                 $part = trim($part);
-                if ($part === '') return false;
-                $length = strlen($part);
-                if ($part[$length - 1] === '%') {
-                    // handle percents
-                    if (!$type) {
-                        $type = 'percentage';
-                    } elseif ($type !== 'percentage') {
+
+                if ($part === '') {
+                    return false;
+                }
+
+                // different check for alpha channel
+                if ($alpha_channel === true && $i === count($parts)) {
+                    $result = $this->alpha->validate($part, $config, $context);
+
+                    if ($result === false) {
                         return false;
                     }
-                    $num = (float) substr($part, 0, $length - 1);
-                    if ($num < 0) $num = 0;
-                    if ($num > 100) $num = 100;
-                    $new_parts[] = "$num%";
+
+                    $new_parts[] = (string)$result;
+                    continue;
+                }
+
+                if (substr($part, -1) === '%') {
+                    $current_type = 'percentage';
                 } else {
-                    // handle integers
-                    if (!$type) {
-                        $type = 'integer';
-                    } elseif ($type !== 'integer') {
-                        return false;
-                    }
-                    $num = (int) $part;
-                    if ($num < 0) $num = 0;
-                    if ($num > 255) $num = 255;
-                    $new_parts[] = (string) $num;
+                    $current_type = 'integer';
+                }
+
+                if (!array_key_exists($current_type, $allowed_types[$i])) {
+                    return false;
+                }
+
+                if (!$type) {
+                    $type = $current_type;
+                }
+
+                if ($allow_different_types === false && $type != $current_type) {
+                    return false;
+                }
+
+                $max_value = $allowed_types[$i][$current_type];
+
+                if ($current_type == 'integer') {
+                    // Return value between range 0 -> $max_value
+                    $new_parts[] = (int)max(min($part, $max_value), 0);
+                } elseif ($current_type == 'percentage') {
+                    $new_parts[] = (float)max(min(rtrim($part, '%'), $max_value), 0) . '%';
                 }
             }
-            $new_triad = implode(',', $new_parts);
-            $color = "rgb($new_triad)";
+
+            $new_values = implode(',', $new_parts);
+
+            $color = $function . '(' . $new_values . ')';
         } else {
             // hexadecimal handling
             if ($color[0] === '#') {
@@ -65,12 +146,14 @@ 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;
-
     }
 
 }

library/HTMLPurifier/AttrDef/CSS/Composite.php

@@ -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

library/HTMLPurifier/AttrDef/CSS/DenyElementDecorator.php

@@ -5,22 +5,38 @@
  */
 class HTMLPurifier_AttrDef_CSS_DenyElementDecorator extends HTMLPurifier_AttrDef
 {
-    public $def, $element;
+    /**
+     * @type HTMLPurifier_AttrDef
+     */
+    public $def;
+    /**
+     * @type string
+     */
+    public $element;
 
     /**
-     * @param $def Definition to wrap
-     * @param $element Element to deny
+     * @param HTMLPurifier_AttrDef $def Definition to wrap
+     * @param string $element Element to deny
      */
-    public function __construct($def, $element) {
+    public function __construct($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, $context) {
+    public function validate($string, $config, $context)
+    {
         $token = $context->get('CurrentToken', true);
-        if ($token && $token->name == $this->element) return false;
+        if ($token && $token->name == $this->element) {
+            return false;
+        }
         return $this->def->validate($string, $config, $context);
     }
 }

library/HTMLPurifier/AttrDef/CSS/Filter.php

@@ -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

library/HTMLPurifier/AttrDef/CSS/Font.php

@@ -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

library/HTMLPurifier/AttrDef/CSS/FontFamily.php

@@ -2,12 +2,56 @@
 
 /**
  * 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) {
+    protected $mask = null;
+
+    public function __construct()
+    {
+        // Lowercase letters
+        $l = range('a', 'z');
+        // Uppercase letters
+        $u = range('A', 'Z');
+        // Digits
+        $d = range('0', '9');
+        // Special bytes used by UTF-8
+        $b = array_map('chr', range(0x80, 0xFF));
+        // All valid characters for the mask
+        $c = array_merge($l, $u, $d, $b);
+        // Concatenate all valid characters into a string 
+        // Use '_- ' as an initial value
+        $this->mask = array_reduce($c, function ($carry, $value) {
+            return $carry . $value;
+        }, '_- ');
+
+        /*
+            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,
@@ -15,73 +59,156 @@ class HTMLPurifier_AttrDef_CSS_FontFamily extends HTMLPurifier_AttrDef
             '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 $font) {
+        foreach ($fonts as $font) {
             $font = trim($font);
-            if ($font === '') continue;
+            if ($font === '') {
+                continue;
+            }
             // match a generic name
             if (isset($generic_names[$font])) {
-                $final .= $font . ', ';
+                if ($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);
-
-                $new_font = '';
-                for ($i = 0, $c = strlen($font); $i < $c; $i++) {
-                    if ($font[$i] === '\\') {
-                        $i++;
-                        if ($i >= $c) {
-                            $new_font .= '\\';
-                            break;
-                        }
-                        if (ctype_xdigit($font[$i])) {
-                            $code = $font[$i];
-                            for ($a = 1, $i++; $i < $c && $a < 6; $i++, $a++) {
-                                if (!ctype_xdigit($font[$i])) break;
-                                $code .= $font[$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;
-                            $new_font .= $char;
-                            if ($i < $c && trim($font[$i]) !== '') $i--;
-                            continue;
-                        }
-                        if ($font[$i] === "\n") continue;
-                    }
-                    $new_font .= $font[$i];
+                if ($length <= 2) {
+                    continue;
                 }
-
-                $font = $new_font;
+                $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;
             }
 
-            // complicated font, requires quoting
+            // bugger out on whitespace.  form feed (0C) really
+            // shouldn't show up regardless
+            $font = str_replace(array("\n", "\t", "\r", "\x0C"), ' ', $font);
 
-            // armor single quotes and new lines
-            $font = str_replace("\\", "\\\\", $font);
-            $font = str_replace("'", "\\'", $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 ($final === '') return false;
+        if ($final === '') {
+            return false;
+        }
         return $final;
     }
 

library/HTMLPurifier/AttrDef/CSS/Ident.php

@@ -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

library/HTMLPurifier/AttrDef/CSS/ImportantDecorator.php

@@ -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;
     }
 }

library/HTMLPurifier/AttrDef/CSS/Length.php

@@ -6,42 +6,72 @@
 class HTMLPurifier_AttrDef_CSS_Length extends HTMLPurifier_AttrDef
 {
 
-    protected $min, $max;
+    /**
+     * @type HTMLPurifier_Length|string
+     */
+    protected $min;
 
     /**
-     * @param HTMLPurifier_Length $max Minimum length, or null for no bound. String is also acceptable.
-     * @param HTMLPurifier_Length $max Maximum length, or null for no bound. String is also acceptable.
+     * @type HTMLPurifier_Length|string
      */
-    public function __construct($min = null, $max = null) {
+    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;
     }
 
-    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);
 
         // Optimizations
-        if ($string === '') return false;
-        if ($string === '0') return '0';
-        if (strlen($string) === 1) return false;
+        if ($string === '') {
+            return false;
+        }
+        if ($string === '0') {
+            return '0';
+        }
+        if (strlen($string) === 1) {
+            return false;
+        }
 
         $length = HTMLPurifier_Length::make($string);
-        if (!$length->isValid()) return false;
+        if (!$length->isValid()) {
+            return false;
+        }
 
         if ($this->min) {
             $c = $length->compareTo($this->min);
-            if ($c === false) return false;
-            if ($c < 0) return false;
+            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;
+            if ($c === false) {
+                return false;
+            }
+            if ($c > 0) {
+                return false;
+            }
         }
-
         return $length->toString();
     }
-
 }
 
 // vim: et sw=4 sts=4

library/HTMLPurifier/AttrDef/CSS/ListStyle.php

@@ -8,46 +8,72 @@ class HTMLPurifier_AttrDef_CSS_ListStyle extends HTMLPurifier_AttrDef
 {
 
     /**
-     * Local copy of component validators.
+     * Local copy of validators.
+     * @type HTMLPurifier_AttrDef[]
      * @note See HTMLPurifier_AttrDef_CSS_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['list-style-type']     = $def->info['list-style-type'];
+        $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) {
-
+    /**
+     * @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;
+        }
 
         // assumes URI doesn't have spaces in it
         $bits = explode(' ', strtolower($string)); // bits to process
 
         $caught = array();
-        $caught['type']     = false;
+        $caught['type'] = false;
         $caught['position'] = false;
-        $caught['image']    = false;
+        $caught['image'] = false;
 
         $i = 0; // number of catches
         $none = false;
 
         foreach ($bits as $bit) {
-            if ($i >= 3) return; // optimization bit
-            if ($bit === '') continue;
+            if ($i >= 3) {
+                return;
+            } // optimization bit
+            if ($bit === '') {
+                continue;
+            }
             foreach ($caught as $key => $status) {
-                if ($status !== false) continue;
+                if ($status !== false) {
+                    continue;
+                }
                 $r = $this->info['list-style-' . $key]->validate($bit, $config, $context);
-                if ($r === false) continue;
+                if ($r === false) {
+                    continue;
+                }
                 if ($r === 'none') {
-                    if ($none) continue;
-                    else $none = true;
-                    if ($key == 'image') continue;
+                    if ($none) {
+                        continue;
+                    } else {
+                        $none = true;
+                    }
+                    if ($key == 'image') {
+                        continue;
+                    }
                 }
                 $caught[$key] = $r;
                 $i++;
@@ -55,24 +81,32 @@ class HTMLPurifier_AttrDef_CSS_ListStyle extends HTMLPurifier_AttrDef
             }
         }
 
-        if (!$i) return false;
+        if (!$i) {
+            return false;
+        }
 
         $ret = array();
 
         // construct type
-        if ($caught['type']) $ret[] = $caught['type'];
+        if ($caught['type']) {
+            $ret[] = $caught['type'];
+        }
 
         // construct image
-        if ($caught['image']) $ret[] = $caught['image'];
+        if ($caught['image']) {
+            $ret[] = $caught['image'];
+        }
 
         // construct position
-        if ($caught['position']) $ret[] = $caught['position'];
+        if ($caught['position']) {
+            $ret[] = $caught['position'];
+        }
 
-        if (empty($ret)) return false;
+        if (empty($ret)) {
+            return false;
+        }
         return implode(' ', $ret);
-
     }
-
 }
 
 // vim: et sw=4 sts=4

library/HTMLPurifier/AttrDef/CSS/Multiple.php

@@ -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

library/HTMLPurifier/AttrDef/CSS/Number.php

@@ -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 +56,26 @@ 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($left)) {
+            return false;
+        }
+
+        // Remove leading zeros until positive number or a zero stays left
+        if (ltrim($left, '0') != '') {
+            $left = ltrim($left, '0');
+        } else {
+            $left = '0';
+        }
 
-        $left  = ltrim($left,  '0');
         $right = rtrim($right, '0');
 
         if ($right === '') {
@@ -59,11 +83,8 @@ class HTMLPurifier_AttrDef_CSS_Number extends HTMLPurifier_AttrDef
         } elseif (!ctype_digit($right)) {
             return false;
         }
-
         return $sign . $left . '.' . $right;
-
     }
-
 }
 
 // vim: et sw=4 sts=4

library/HTMLPurifier/AttrDef/CSS/Percentage.php

@@ -7,34 +7,48 @@ class HTMLPurifier_AttrDef_CSS_Percentage extends HTMLPurifier_AttrDef
 {
 
     /**
-     * Instance of HTMLPurifier_AttrDef_CSS_Number to defer number validation
+     * Instance to defer number validation to.
+     * @type HTMLPurifier_AttrDef_CSS_Number
      */
     protected $number_def;
 
     /**
-     * @param Bool indicating whether to forbid negative values
+     * @param bool $non_negative Whether to forbid negative values
      */
-    public function __construct($non_negative = false) {
+    public function __construct($non_negative = false)
+    {
         $this->number_def = new HTMLPurifier_AttrDef_CSS_Number($non_negative);
     }
 
-    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);
 
-        if ($string === '') return false;
+        if ($string === '') {
+            return false;
+        }
         $length = strlen($string);
-        if ($length === 1) return false;
-        if ($string[$length - 1] !== '%') return false;
+        if ($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 ($number === false) return false;
+        if ($number === false) {
+            return false;
+        }
         return "$number%";
-
     }
-
 }
 
 // vim: et sw=4 sts=4

library/HTMLPurifier/AttrDef/CSS/Ratio.php

@@ -0,0 +1,46 @@
+<?php
+
+/**
+ * Validates a ratio as defined by the CSS spec.
+ */
+class HTMLPurifier_AttrDef_CSS_Ratio extends HTMLPurifier_AttrDef
+{
+    /**
+     * @param   string               $ratio   Ratio to validate
+     * @param   HTMLPurifier_Config  $config  Configuration options
+     * @param   HTMLPurifier_Context $context Context
+     *
+     * @return  string|boolean
+     *
+     * @warning Some contexts do not pass $config, $context. These
+     *          variables should not be used without checking HTMLPurifier_Length
+     */
+    public function validate($ratio, $config, $context)
+    {
+        $ratio = $this->parseCDATA($ratio);
+
+        $parts = explode('/', $ratio, 2);
+        $length = count($parts);
+
+        if ($length < 1 || $length > 2) {
+            return false;
+        }
+
+        $num = new \HTMLPurifier_AttrDef_CSS_Number();
+
+        if ($length === 1) {
+            return $num->validate($parts[0], $config, $context);
+        }
+
+        $num1 = $num->validate($parts[0], $config, $context);
+        $num2 = $num->validate($parts[1], $config, $context);
+
+        if ($num1 === false || $num2 === false) {
+            return false;
+        }
+
+        return $num1 . '/' . $num2;
+    }
+}
+
+// vim: et sw=4 sts=4

library/HTMLPurifier/AttrDef/CSS/TextDecoration.php

@@ -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

library/HTMLPurifier/AttrDef/CSS/URI.php

@@ -12,45 +12,66 @@
 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);
+        if (strlen($uri_string) == 0) {
+            return false;
+        }
         $new_length = strlen($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);
         }
 
-        $keys   = array(  '(',   ')',   ',',   ' ',   '"',   "'");
-        $values = array('\\(', '\\)', '\\,', '\\ ', '\\"', "\\'");
-        $uri = str_replace($values, $keys, $uri);
+        $uri = $this->expandCSSEscape($uri);
 
         $result = parent::validate($uri, $config, $context);
 
-        if ($result === false) return false;
+        if ($result === false) {
+            return false;
+        }
 
-        // escape necessary characters according to CSS spec
-        // except for the comma, none of these should appear in the
-        // URI at all
-        $result = str_replace($keys, $values, $result);
+        // extra sanity check; should have been done by URI
+        $result = str_replace(array('"', "\\", "\n", "\x0c", "\r"), "", $result);
 
-        return "url($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

library/HTMLPurifier/AttrDef/Clone.php

@@ -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

library/HTMLPurifier/AttrDef/Enum.php

@@ -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

library/HTMLPurifier/AttrDef/HTML/Bool.php

@@ -6,23 +6,43 @@
 class HTMLPurifier_AttrDef_HTML_Bool extends HTMLPurifier_AttrDef
 {
 
+    /**
+     * @type string
+     */
     protected $name;
+
+    /**
+     * @type bool
+     */
     public $minimized = true;
 
-    public function __construct($name = false) {$this->name = $name;}
+    /**
+     * @param bool|string $name
+     */
+    public function __construct($name = false)
+    {
+        $this->name = $name;
+    }
 
-    public function validate($string, $config, $context) {
-        if (empty($string)) return false;
+    /**
+     * @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 Name of attribute
+     * @param string $string Name of attribute
+     * @return HTMLPurifier_AttrDef_HTML_Bool
      */
-    public function make($string) {
+    public function make($string)
+    {
         return new HTMLPurifier_AttrDef_HTML_Bool($string);
     }
-
 }
 
 // vim: et sw=4 sts=4

library/HTMLPurifier/AttrDef/HTML/Class.php

@@ -0,0 +1,48 @@
+<?php
+
+/**
+ * Implements special behavior for class attribute (normally NMTOKENS)
+ */
+class HTMLPurifier_AttrDef_HTML_Class extends HTMLPurifier_AttrDef_HTML_Nmtokens
+{
+    /**
+     * @param string $string
+     * @param HTMLPurifier_Config $config
+     * @param HTMLPurifier_Context $context
+     * @return bool|string
+     */
+    protected function split($string, $config, $context)
+    {
+        // really, this twiddle should be lazy loaded
+        $name = $config->getDefinition('HTML')->doctype->name;
+        if ($name == "XHTML 1.1" || $name == "XHTML 2.0") {
+            return parent::split($string, $config, $context);
+        } else {
+            return preg_split('/\s+/', $string);
+        }
+    }
+
+    /**
+     * @param array $tokens
+     * @param HTMLPurifier_Config $config
+     * @param HTMLPurifier_Context $context
+     * @return array
+     */
+    protected function filter($tokens, $config, $context)
+    {
+        $allowed = $config->get('Attr.AllowedClasses');
+        $forbidden = $config->get('Attr.ForbiddenClasses');
+        $ret = array();
+        foreach ($tokens as $token) {
+            if (($allowed === null || isset($allowed[$token])) &&
+                !isset($forbidden[$token]) &&
+                // We need this O(n) check because of PHP's array
+                // implementation that casts -0 to 0.
+                !in_array($token, $ret, true)
+            ) {
+                $ret[] = $token;
+            }
+        }
+        return $ret;
+    }
+}

library/HTMLPurifier/AttrDef/HTML/Color.php

@@ -6,27 +6,46 @@
 class HTMLPurifier_AttrDef_HTML_Color 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 $colors = null;
-        if ($colors === null) $colors = $config->get('Core', 'ColorKeywords');
+        if ($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 = $string;
+        if (empty($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];
-
+        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

library/HTMLPurifier/AttrDef/HTML/ContentEditable.php

@@ -0,0 +1,16 @@
+<?php
+
+class HTMLPurifier_AttrDef_HTML_ContentEditable extends HTMLPurifier_AttrDef
+{
+    public function validate($string, $config, $context)
+    {
+        $allowed = array('false');
+        if ($config->get('HTML.Trusted')) {
+            $allowed = array('', 'true', 'false');
+        }
+
+        $enum = new HTMLPurifier_AttrDef_Enum($allowed);
+
+        return $enum->validate($string, $config, $context);
+    }
+}

library/HTMLPurifier/AttrDef/HTML/FrameTarget.php

@@ -6,16 +6,33 @@
 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() {}
-
-    public function validate($string, $config, $context) {
-        if ($this->valid_values === false) $this->valid_values = $config->get('Attr', 'AllowedFrameTargets');
-        return parent::validate($string, $config, $context);
+    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

library/HTMLPurifier/AttrDef/HTML/ID.php

@@ -12,59 +12,102 @@
 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
+    // selector is NOT a valid thing to use for IDREFs, because IDREFs
+    // *must* target IDs that exist, whereas selector #ids do not.
 
-    public function validate($id, $config, $context) {
+    /**
+     * Determines whether or not we're validating an ID in a CSS
+     * selector context.
+     * @type bool
+     */
+    protected $selector;
 
-        if (!$config->get('Attr', 'EnableID')) return false;
+    /**
+     * @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 ($id === '') {
+            return false;
         }
 
-        //if (!$this->ref) {
+        $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[$id])) return false;
-        //}
+            if (isset($id_accumulator->ids[$id])) {
+                return false;
+            }
+        }
 
         // we purposely avoid using regex, hopefully this is faster
 
-        if (ctype_alpha($id)) {
-            $result = true;
+        if ($config->get('Attr.ID.HTML5') === true) {
+            if (preg_match('/[\t\n\x0b\x0c ]/', $id)) {
+                return false;
+            }
         } else {
-            if (!ctype_alpha(@$id[0])) return false;
-            $trim = trim( // primitive style of regexps, I suppose
-                $id,
-                'A..Za..z0..9:-._'
-              );
-            $result = ($trim === '');
+            if (ctype_alpha($id)) {
+                // OK
+            } else {
+                if (!ctype_alpha(@$id[0])) {
+                    return false;
+                }
+                // primitive style of regexps, I suppose
+                $trim = trim(
+                    $id,
+                    'A..Za..z0..9:-._'
+                );
+                if ($trim !== '') {
+                    return false;
+                }
+            }
         }
 
-        $regexp = $config->get('Attr', 'IDBlacklistRegexp');
+        $regexp = $config->get('Attr.IDBlacklistRegexp');
         if ($regexp && preg_match($regexp, $id)) {
             return false;
         }
 
-        if (/*!$this->ref && */$result) $id_accumulator->add($id);
+        if (!$this->selector) {
+            $id_accumulator->add($id);
+        }
 
         // if no change was made to the ID, return the result
         // else, return the new id if stripping whitespace made it
         //     valid, or return false.
-        return $result ? $id : false;
-
+        return $id;
     }
-
 }
 
 // vim: et sw=4 sts=4

library/HTMLPurifier/AttrDef/HTML/Length.php

@@ -10,32 +10,47 @@
 class HTMLPurifier_AttrDef_HTML_Length extends HTMLPurifier_AttrDef_HTML_Pixels
 {
 
-    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;
+        }
 
         $parent_result = parent::validate($string, $config, $context);
-        if ($parent_result !== false) return $parent_result;
+        if ($parent_result !== false) {
+            return $parent_result;
+        }
 
         $length = strlen($string);
         $last_char = $string[$length - 1];
 
-        if ($last_char !== '%') return false;
+        if ($last_char !== '%') {
+            return false;
+        }
 
         $points = substr($string, 0, $length - 1);
 
-        if (!is_numeric($points)) return false;
+        if (!is_numeric($points)) {
+            return false;
+        }
 
-        $points = (int) $points;
-
-        if ($points < 0) return '0%';
-        if ($points > 100) return '100%';
-
-        return ((string) $points) . '%';
+        $points = (int)$points;
 
+        if ($points < 0) {
+            return '0%';
+        }
+        if ($points > 100) {
+            return '100%';
+        }
+        return ((string)$points) . '%';
     }
-
 }
 
 // vim: et sw=4 sts=4

library/HTMLPurifier/AttrDef/HTML/LinkTypes.php

@@ -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) {
-
-        $allowed = $config->get('Attr', $this->name);
-        if (empty($allowed)) return false;
+    /**
+     * @param string $string
+     * @param HTMLPurifier_Config $config
+     * @param HTMLPurifier_Context $context
+     * @return bool|string
+     */
+    public function validate($string, $config, $context)
+    {
+        $allowed = $config->get('Attr.' . $this->name);
+        if (empty($allowed)) {
+            return false;
+        }
 
         $string = $this->parseCDATA($string);
         $parts = explode(' ', $string);
@@ -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

library/HTMLPurifier/AttrDef/HTML/MultiLength.php

@@ -9,33 +9,52 @@
 class HTMLPurifier_AttrDef_HTML_MultiLength extends HTMLPurifier_AttrDef_HTML_Length
 {
 
-    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;
+        }
 
         $parent_result = parent::validate($string, $config, $context);
-        if ($parent_result !== false) return $parent_result;
+        if ($parent_result !== false) {
+            return $parent_result;
+        }
 
         $length = strlen($string);
         $last_char = $string[$length - 1];
 
-        if ($last_char !== '*') return false;
+        if ($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) $int) . '*';
+        if ($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

library/HTMLPurifier/AttrDef/HTML/Nmtokens.php

@@ -2,21 +2,42 @@
 
 /**
  * Validates contents based on NMTOKENS attribute type.
- * @note The only current use for this is the class attribute in HTML
- * @note Could have some functionality factored out into Nmtoken class
- * @warning We cannot assume this class will be used only for 'class'
- *          attributes. Not sure how to hook in magic behavior, then.
  */
 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;
+        }
+        return implode(' ', $tokens);
+    }
+
+    /**
+     * Splits a space separated list of tokens into its constituent parts.
+     * @param string $string
+     * @param HTMLPurifier_Config $config
+     * @param HTMLPurifier_Context $context
+     * @return array
+     */
+    protected function split($string, $config, $context)
+    {
         // OPTIMIZABLE!
         // do the preg_match, capture all subpatterns for reformulation
 
@@ -24,25 +45,26 @@ 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).
-        $matches = array();
-        $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, $matches);
-
-        if (empty($matches[1])) return false;
-
-        // reconstruct string
-        $new_string = '';
-        foreach ($matches[1] as $token) {
-            $new_string .= $token . ' ';
-        }
-        $new_string = rtrim($new_string);
-
-        return $new_string;
-
+        return $matches[1];
     }
 
+    /**
+     * Template method for removing certain tokens based on arbitrary criteria.
+     * @note If we wanted to be really functional, we'd do an array_filter
+     *       with a callback. But... we're not.
+     * @param array $tokens
+     * @param HTMLPurifier_Config $config
+     * @param HTMLPurifier_Context $context
+     * @return array
+     */
+    protected function filter($tokens, $config, $context)
+    {
+        return $tokens;
+    }
 }
 
 // vim: et sw=4 sts=4