Release 1.6.1, merged in 931 to HEAD.

git-svn-id: http://htmlpurifier.org/svnroot/htmlpurifier/branches/strict@1026 48356398-32a2-884e-a903-53898d9a118a

Doxyfile

@@ -4,7 +4,7 @@
 # Project related configuration options
 #---------------------------------------------------------------------------
 PROJECT_NAME           = HTML Purifier
-PROJECT_NUMBER         = 1.4.1
+PROJECT_NUMBER         = 1.6.1
 OUTPUT_DIRECTORY       = "C:/Documents and Settings/Edward/My Documents/My Webs/htmlpurifier/docs/doxygen"
 CREATE_SUBDIRS         = NO
 OUTPUT_LANGUAGE        = English

INSTALL

@@ -47,7 +47,9 @@ HTML Purifier is all about web-standards, so accordingly your webpages should
 be standards compliant.  HTML Purifier can deal with these doctypes:
 
 * XHTML 1.0 Transitional (default)
+* XHTML 1.0 Strict
 * HTML 4.01 Transitional
+* HTML 4.01 Strict
 
 ...and these character encodings:
 
@@ -87,7 +89,7 @@ into configuring things just for the heck of it, skip to 4.3).
 * Am I using UTF-8?
 * Am I using XHTML 1.0 Transitional?
 
-If you answered yes to any of these questions, instantiate a configuration
+If you answered no to any of these questions, instantiate a configuration
 object and read on:
 
     $config = HTMLPurifier_Config::createDefault();
@@ -141,7 +143,7 @@ versions will also allow strict-compliant output.
 4.3. Other settings
 
 There are more configuration directives which can be read about
-here: <http://hp.jpsband.org/live/configdoc/plain.html>  They're a bit boring,
+here: <http://htmlpurifier.org/live/configdoc/plain.html>  They're a bit boring,
 but they can help out for those of you who like to exert maximum control over
 your code.
 

INSTALL.fr.utf8

@@ -0,0 +1,71 @@
+
+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.
+
+
+1.  Compatibilité
+
+HTML Purifier fonctionne dans PHP 4 et PHP 5. PHP 4.3.9 est le dernier
+version que je le testais.  Il ne dépend de les autre 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.
+
+
+2.  Inclure la librarie
+
+Utilisez:
+
+    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.)
+
+Si vous n'aime pas que HTML Purifier change vos include_path, on peut
+change vos include_path, et:
+
+    require_once 'HTMLPurifier.php';
+
+Seuleument les contents dans library/ est essentiel; vous peut enlever
+les autre fichiers quand vous est dans une atmosphère professionnel.
+
+
+[En cours de construction]
+
+
+6.   Installation vite
+
+Si votre site web est en UTF-8 et XHTML Transitional, utilisez:
+
+<?php
+    require_once '/path/to/htmlpurifier/library/HTMLPurifier.auto.php';
+    
+    $purificateur = new HTMLPurifier();
+    $html_propre = $purificateur->purify($html_salle);
+?>
+
+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
+    $purificateur = new HTMLPurifier($config);
+    
+    $html_propre = $purificateur->purify($html_salle);
+?>

NEWS

@@ -9,6 +9,92 @@ NEWS ( CHANGELOG and HISTORY )                                     HTMLPurifier
     . Internal change
 ==========================
 
+1.7.0, unknown release date
+
+1.6.1, released 2007-05-05
+! Support for more deprecated attributes via transformations:
+  + hspace and vspace in img
+  + size and noshade in hr
+  + nowrap in td
+  + clear in br
+  + align in caption, table, img and hr
+  + type in ul, ol and li
+! DirectLex now preserves text in which a < bracket is followed by
+  a non-alphanumeric character. This means that certain emoticons
+  are now preserved.
+! %Core.RemoveInvalidImg is now operational, when set to false invalid
+  images will hang around with an empty src
+! target attribute in a tag supported, use %Attr.AllowedFrameTargets
+  to enable
+! CSS property white-space now allows nowrap (supported in all modern
+  browsers) but not others (which have spotty browser implementations)
+! XHTML 1.1 mode now sort-of works without any fatal errors, and
+  lang is now moved over to xml:lang.
+! Attribute transformation smoketest available at smoketests/attrTransform.php
+! Transformation of font's size attribute now handles super-large numbers
+- Possibly fatal bug with __autoload() fixed in module manager
+- Invert HTMLModuleManager->addModule() processing order to check
+  prefixes first and then the literal module
+- Empty strings get converted to empty arrays instead of arrays with
+  an empty string in them.
+- Merging in attribute lists now works.
+. Demo script removed: it has been added to the website's repository
+. Basic.php script modified to work out of the box
+. Refactor AttrTransform classes to reduce duplication
+. AttrTransform_TextAlign axed in favor of a more general
+  AttrTransform_EnumToCSS, refer to HTMLModule/TransformToStrict.php to
+  see how the new equivalent is implemented
+. Unit tests now use exclusively assertIdentical
+ 
+1.6.0, released 2007-04-01
+! Support for most common deprecated attributes via transformations:
+  + bgcolor in td, th, tr and table
+  + border in img
+  + name in a and img
+  + width in td, th and hr
+  + height in td, th
+! Support for CSS attribute 'height' added
+! Support for rel and rev attributes in a tags added, use %Attr.AllowedRel
+  and %Attr.AllowedRev to activate
+- You can define ID blacklists using regular expressions via
+  %Attr.IDBlacklistRegexp
+- Error messages are emitted when you attempt to "allow" elements or
+  attributes that HTML Purifier does not support
+
+1.5.1, unknown release date
+- Fix segfault in unit test. The problem is not very reproduceable and
+  I don't know what causes it, but a six line patch fixed it.
+
+1.5.0, released 2007-03-23
+! Added a rudimentary I18N and L10N system modeled off MediaWiki. It
+  doesn't actually do anything yet, but keep your eyes peeled.
+! docs/enduser-utf8.html explains how to use UTF-8 and HTML Purifier
+! Newly structured HTMLDefinition modeled off of XHTML 1.1 modules.
+  I am loathe to release beta quality APIs, but this is exactly that;
+  don't use the internal interfaces if you're not willing to do migration
+  later on.
+- Allow 'x' subtag in language codes
+- Fixed buggy chameleon-support for ins and del
+. Added support for IDREF attributes (i.e. for)
+. Renamed HTMLPurifier_AttrDef_Class to HTMLPurifier_AttrDef_Nmtokens
+. Removed context variable ParentType, replaced with IsInline, which
+  is false when you're not inline and an integer of the parent that
+  caused you to become inline when you are (so possibly zero)
+. Removed ElementDef->type in favor of ElementDef->descendants_are_inline
+  and HTMLDefinition->content_sets
+. StrictBlockquote now reports what elements its supposed to allow,
+  rather than what it does allow
+. Removed HTMLDefinition->info_flow_elements in favor of
+  HTMLDefinition->content_sets['Flow']
+. Removed redundant "exclusionary" definitions from DTD roster
+. StrictBlockquote now requires a construction parameter as if it
+  were an Required ChildDef, this is the "real" set of allowed elements
+. AttrDef partitioned into HTML, CSS and URI segments
+. Modify Youtube filter regexp to be multiline
+. Require both PHP5 and DOM extension in order to use DOMLex, fixes
+  some edge cases where a DOMDocument class exists in a PHP4 environment
+  due to DOM XML extension.
+
 1.4.1, released 2007-01-21
 ! docs/enduser-youtube.html updated according to new functionality
 - YouTube IDs can have underscores and dashes

README

@@ -19,4 +19,4 @@ 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://hp.jpsband.org/
+HTML Purifier can be found on the web at: http://htmlpurifier.org/

TODO

@@ -4,32 +4,36 @@ TODO List
 = KEY ====================
     # Flagship
     - Regular
-    ? At-risk
+    ? Maybe I'll Do It
 ==========================
 
-1.5 release
- # Implement all non-essential attribute transforms, configurable
+1.7 release [Advanced API]
+ # Complete advanced API, and fully document it
+ # Implement all edge-case attribute transforms
+ # Implement all deprecated tags and attributes
+ - Parse TinyMCE-style whitelist into our %HTML.Allow* whitelists (possibly
+   do this earlier)
+ ? HTML interface for tweaking configuration to see changes
+
+1.8 release [Refactor, refactor!]
  # URI validation routines tighter (see docs/dev-code-quality.html) (COMPLEX)
  # Advanced URI filtering schemes (see docs/proposal-new-directives.txt)
+ - Configuration profiles: predefined directives set with one func call
+ - Implement IDREF support (harder than it seems, since you cannot have
+   IDREFs to non-existent IDs)
+ - Allow non-ASCII characters in font names
+
+1.9 release [Error'ed]
  # Error logging for filtering/cleanup procedures
     - Requires I18N facilities to be created first (COMPLEX)
- ? Configuration profiles: sets of directives that get set with one func call
  - XSS-attempt detection
-
-1.6 release
- # Add pre-packaged "levels" of cleaning (custom behavior already done)
  - More fine-grained control over escaping behavior
     - Silently drop content inbetween SCRIPT tags (can be generalized to allow
       specification of elements that, when detected as foreign, trigger removal
       of children, although unbalanced tags could wreck havoc (or at least
       delete the rest of the document)).
- - Allow specifying global attributes on a tag-by-tag basis in
-   %HTML.AllowAttributes
- ? More user-friendly warnings when %HTML.Allow* attempts to specify a
-   tag or attribute that is not supported
- - Parse TinyMCE whitelist into our %HTML.Allow* whitelists
 
-1.7 release
+1.10 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>)
@@ -44,7 +48,7 @@ TODO List
  - Append something to duplicate IDs so they're still usable (impl. note: the
    dupe detector would also need to detect the suffix as well)
 
-2.0 release
+2.0 release [Beyond HTML]
  # Legit token based CSS parsing (will require revamping almost every
    AttrDef class)
  # Formatters for plaintext (COMPLEX)
@@ -53,33 +57,33 @@ TODO List
     - Linkify URLs
     - Smileys
     - Linkification for HTML Purifier docs: notably configuration and classes
-
-3.0 release
- - Extended HTML capabilities based on namespacing and tag transforms (COMPLEX)
-    - Hooks for adding custom processors to custom namespaced tags and
-      attributes, offer default implementation
-    - Lots of documentation and samples
  - Allow tags to be "armored", an internal flag that protects them
    from validation and passes them out unharmed
- - XHTML 1.1 support
  - Fixes for Firefox's inability to handle COL alignment props (Bug 915)
  - Automatically add non-breaking spaces to empty table cells when
    empty-cells:show is applied to have compatibility with Internet Explorer
  - Convert RTL/LTR override characters to <bdo> tags, or vice versa on demand.
    Also, enable disabling of directionality
 
+3.0 release [To XML and Beyond]
+ - Extended HTML capabilities based on namespacing and tag transforms (COMPLEX)
+    - Hooks for adding custom processors to custom namespaced tags and
+      attributes, offer default implementation
+    - Lots of documentation and samples
+ - XHTML 1.1 support
+
 Ongoing
  - Lots of profiling, make it faster!
  - Plugins for major CMSes (COMPLEX)
-    - WordPress
+    - WordPress (mostly written, needs beta-testing)
     - eFiction
     - more! (look for ones that use WYSIWYGs)
 
 Unknown release (on a scratch-an-itch basis)
- - Upgrade SimpleTest testing code to newest versions
- - Have 'lang' attribute be checked against official lists
- ? Semi-lossy dumb alternate character encoding transformations, achieved by
+ ? Semi-lossy dumb alternate character encoding transfor
+ ? Have 'lang' attribute be checked against official lists, achieved by
    encoding all characters that have string entity equivalents
+ - Explain how to use HTML Purifier in non-PHP languages
 
 Requested
  ? Native content compression, whitespace stripping (don't rely on Tidy, make

VERSION

@@ -0,0 +1 @@
+1.6.1

WHATSNEW

@@ -0,0 +1,7 @@
+The 1.6.1 release, code-named 'Ach! We missed something! Run!', completes
+HTML Purifier's roster of attribute transformations. It also implements
+a number of minor features (such as better font transformations, smarter
+HTML parsing, the CSS property 'white-space' and XHTML 1.1), a few bug
+fixes (most notably fixed __autoload compatibility issues) and a ton
+of refactoring. 1.6 was for things that absolutely could not wait: this
+release, developed in a more leisurely pace, fills in the gaps.

benchmarks/Lexer.php

@@ -7,6 +7,7 @@ set_include_path(get_include_path() . PATH_SEPARATOR . '../library/');
 
 require_once 'HTMLPurifier/ConfigSchema.php';
 require_once 'HTMLPurifier/Config.php';
+require_once 'HTMLPurifier/Context.php';
 
 $LEXERS = array();
 $RUNS = isset($GLOBALS['HTMLPurifierTest']['Runs'])
@@ -93,11 +94,14 @@ function print_lexers() {
 function do_benchmark($name, $document) {
     global $LEXERS, $RUNS;
     
+    $config = HTMLPurifier_Config::createDefault();
+    $context = new HTMLPurifier_Context();
+    
     $timer = new RowTimer($name);
     $timer->start();
     
     foreach($LEXERS as $key => $lexer) {
-        for ($i=0; $i<$RUNS; $i++) $tokens = $lexer->tokenizeHTML($document);
+        for ($i=0; $i<$RUNS; $i++) $tokens = $lexer->tokenizeHTML($document, $config, $context);
         $timer->setMarker($key);
     }
     

benchmarks/ProfileDirectLex.php

@@ -5,12 +5,15 @@ set_include_path(get_include_path() . PATH_SEPARATOR . '../library/');
 require_once 'HTMLPurifier/ConfigSchema.php';
 require_once 'HTMLPurifier/Config.php';
 require_once 'HTMLPurifier/Lexer/DirectLex.php';
+require_once 'HTMLPurifier/Context.php';
 
 $input = file_get_contents('samples/Lexer/4.html');
 $lexer = new HTMLPurifier_Lexer_DirectLex();
+$config = HTMLPurifier_Config::createDefault();
+$context = new HTMLPurifier_Context();
 
 for ($i = 0; $i < 10; $i++) {
-    $tokens = $lexer->tokenizeHTML($input);
+    $tokens = $lexer->tokenizeHTML($input, $config, $context);
 }
 
 ?>

configdoc/generate.php

@@ -24,8 +24,7 @@ error_reporting(E_ALL);
 // ---------------------------------------------------------------------------
 // Include HTML Purifier library
 
-set_include_path('../library' . PATH_SEPARATOR . get_include_path());
-require_once 'HTMLPurifier.php';
+require_once '../library/HTMLPurifier.auto.php';
 
 
 // ---------------------------------------------------------------------------
@@ -188,7 +187,7 @@ $xsl_processor->importStylesheet($xsl_dom_stylesheet);
 $html_output = $xsl_processor->transformToXML($dom_document);
 
 // some slight fudges to preserve backwards compatibility
-$html_output = str_replace('/>', ' />', $html_output); // <br /> not <br>
+$html_output = str_replace('/>', ' />', $html_output); // <br /> not <br/>
 $html_output = str_replace(' xmlns=""', '', $html_output); // rm unnecessary xmlns
 
 if (class_exists('Tidy')) {

docs/dev-advanced-api.html

@@ -0,0 +1,287 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN"
+    "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">
+<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en"><head>
+<meta http-equiv="Content-Type" content="text/html; charset=UTF-8" />
+<meta name="description" content="Functional specification for HTML Purifier's advanced API for defining custom filtering behavior." />
+<link rel="stylesheet" type="text/css" href="style.css" />
+
+<title>Advanced API - HTML Purifier</title>
+
+</head><body>
+
+<h1>Advanced API</h1>
+
+<div id="filing">Filed under Development</div>
+<div id="index">Return to the <a href="index.html">index</a>.</div>
+<div id="home"><a href="http://htmlpurifier.org/">HTML Purifier</a> End-User Documentation</div>
+
+<p>HTML Purifier currently natively supports only a subset of HTML's
+allowed elements, attributes, and behavior. This is by design,
+but as the user is always right, they'll need some method to overload
+these behaviors.</p>
+
+<p>Our goals are to let the user:</p>
+
+<dl>
+    <dt>Select</dt>
+    <dd><ul>
+        <li>Doctype</li>
+        <li>Mode: Lenient / Correctional</li>
+        <li>Elements / Attributes / Modules</li>
+        <li>Filterset</li>
+    </ul></dd>
+    <dt>Customize</dt>
+    <dd><ul>
+        <li>Attributes</li>
+        <li>Elements</li>
+    </ul></dd>
+    <dt>Internals</dt>
+    <dd><ul>
+        <li>Modules / Elements / Attributes / Attribute Types</li>
+        <li>Filtersets</li>
+        <li>Doctype</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 Mode</h3>
+
+<p>Within doctypes, there are various <strong>modes</strong> of operation.
+These indicate variant behaviors that, while not strictly changing the
+allowed set of elements and attributes, definitely affect the output.
+Currently, we have two modes, which may be used together:</p>
+
+<dl>
+    <dt>Lenient</dt>
+    <dd>
+        <p>Deprecated elements and attributes will be transformed into
+        standards-compliant alternatives when explicitly disallowed.</p>
+        <p>For example, in the XHTML 1.0 Strict doctype, a <code>center</code>
+        element would be turned into a <code>div</code> with the CSS property
+        <code>text-align:center;</code>, but in XHTML 1.0 Transitional
+        the element would be preserved.</p>
+        <p>This mode is on by default.</p>
+    </dd>
+    <dt>Correctional[items to correct]</dt>
+    <dd>
+        <p>Deprecated elements and attributes will be transformed into
+        standards-compliant alternatives whenever possible.
+        It may have various levels of operation.</p>
+        <p>Referring back to the previous example, the <code>center</code> element would
+        be transformed in both cases. However, elements without a
+        reasonable standards-compliant alternative will be preserved
+        in their form.</p>
+        <p>A user may want to correct certain deprecated attributes, but
+        not others. For example, the <code>bgcolor</code> attribute may be
+        acceptable, but the <code>center</code> element not; also, possibly,
+        an HTML Purifier transformation may be buggy, so the user wants
+        to forgo it. Thus, correctional accepts an array defining which
+        elements and attributes to cleanup, or no parameter at all, which
+        means everything gets corrected. This also means that each
+        correction needs to be given a unique ID that can be referenced
+        in this manner. (We may also allow globbing, like *.name or a.*
+        for mass-enabling correction, and subtractive mode, where things
+        specified stop correction.) This array gets passed into the
+        constructor of the mode's module.</p>
+        <p>This mode is on by default.</p>
+    </dd>
+</dl>
+
+<p>A possible call to select modes would be:</p>
+
+<pre>$config->set('HTML', 'Mode', array('correctional', 'lenient'));</pre>
+
+<p>If modes have extra parameters, a hash is necessary:</p>
+
+<pre>$config->set('HTML', 'Mode', array(
+    'correctional' => 'center,a.name',
+    'lenient' => true // this one's just boolean
+));</pre>
+
+<p>Modes may be specified along with the doctype declaration (we may want
+to get a better set of separator characters):</p>
+
+<pre>$config->setDoctype('XHTML Transitional 1.0', '+correctional[center,a.name] -lenient');</pre>
+
+<p>
+With regards to the various levels of operation conjectured in the
+Correctional mode, this is prompted by the fact that a user may want to
+correct certain problems but not others, for example, fix the <code>center</code>
+element but not the <code>u</code> element, both of which are deprecated.
+Having an integer <q>level</q> will not work very well for such fine
+grained tweaking, but an array of specific settings might.</p>
+
+<h3>Selecting Elements / Attributes / Modules</h3>
+
+<p></p>
+
+<p>If this cookie cutter approach doesn't appeal to a user, they may
+decide to roll their own filterset by selecting modules, elements and
+attributes to allow.</p>
+
+<p class="technical">This would make use of the same facilities
+as a filterset author would use, except that it would go under an
+<q>anonymous</q> filterset that would be auto-selected if any of the
+relevant module/elements/attribute selection configuration directives were
+non-null.</p>
+
+<p>In practice, this is the most commonly demanded feature. Most users are
+perfectly happy defining a filterset that looks like:</p>
+
+<pre>$config->setAllowedHTML('a[href,title];em;p;blockquote');</pre>
+
+<p class="technical">The directive %HTML.Allowed is a convenience function
+that may be fully expressed with the legacy interface, and thus is
+given its own setter.</p>
+
+<p>We currently support a separated interface, which also must be preserved:</p>
+
+<pre>$config->set('HTML', 'AllowedElements', 'a,em,p,blockquote');
+$config->set('HTML', 'AllowedAttributes', 'a.href,a.title');</pre>
+
+<p>A user may also choose to allow modules:</p>
+
+<pre>$config->set('HTML', 'AllowedModules', 'Hypertext,Text,Lists'); // or
+$config->setAllowedHTML('Hypertext,Text,Lists');</pre>
+
+<p>But it is not expected that this feature will be widely used.</p>
+
+<p class="fixme">The granularity of these modules is too coarse for
+the average user (for example, the core module loads everything from
+the essential <code>p</code> element to the not-so-safe <code>h1</code>
+element). How do we make this still a viable solution? Possible answers
+may be sub-modules or module parameters. This may not even be a problem,
+considering that most people won't be selecting modules.</p>
+
+<p class="technical">Modules are distinguished from regular elements by the
+case of their first letter. While XML distinguishes between and allows
+lower and uppercase letters in element names, most well-known XML
+languages use only lower-case
+element names for sake of consistency.</p>
+
+<p class="technical">Considering that, internally speaking, as mandated by
+the XHTML 1.1 Modularization specification, we have organized our
+elements around modules, considerable gymnastics will be needed to
+get this sort of functionality working.</p>
+
+<h3>Unified selector</h3>
+
+<p>Because selecting each and every one of these configuration options
+is a chore, we may wish to offer a specialized configuration method
+for selecting a filterset. Possibility:</p>
+
+<pre>function selectFilter($doctype, $filterset, $mode)</pre>
+
+<p>...which is simply a light wrapper over the individual configuration
+calls. A custom config file format or text format could also be adopted.</p>
+
+<h2>Customize</h2>
+
+<p>By reviewing topic posts in the support forum, we determined that
+there were two primarily demanded customization features people wanted:
+to add an attribute to an existing element, and to add an element.
+Thus, we'll want to create convenience functions for these common
+use-cases.</p>
+
+<p>Note that the functions described here are only available if
+a raw copy of <code>HTMLPurifier_HTMLDefinition</code> was retrieved.
+<code>addAttribute</code> may work on a processed copy, but for
+consistency's sake we will mandate this for everything.</p>
+
+<h3>Attributes</h3>
+
+<p>An attribute is bound to an element by a name and has a specific
+<code>AttrDef</code> that validates it. Thus, the interface should
+be:</p>
+
+<pre>function addAttribute($element, $attribute, $attribute_def);</pre>
+
+<p>With a use-case that looks like:</p>
+
+<pre>$def->addAttribute('a', 'rel', new HTMLPurifier_AttrDef_Enum(array('nofollow')));</pre>
+
+<p>The <code>$attribute_def</code> value can be a little flexible,
+to make things simpler. We'll let it also be:</p>
+
+<ul>
+    <li>Class name: We'll instantiate it for you</li>
+    <li>Function name: We'll create an <code>HTMLPurifier_AttrDef_Anonymous</code>
+        class with that function registered as a callback.</li>
+    <li>String attribute type: We'll use <code>HTMLPurifier_AttrTypes</code>
+        </li>
+    <li>String starting with <code>enum(</code>: We'll explode it and stuff it in an
+        <code>HTMLPurifier_AttrDef_Enum</code> for you.</li>
+</ul>
+
+<p>Making the previous example written as:</p>
+
+<pre>$def->addAttribute('a', 'rel', 'enum(nofollow)');</pre>
+
+<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, $content_model, $attributes = array());</pre>
+
+<p>Each parameter explained in depth:</p>
+
+<dl>
+    <dt><code>$element</code></dt>
+    <dd>Element name, ex. 'label'</dd>
+    <dt><code>$type</code></dt>
+    <dd>Content set to register in, ex. 'Inline' or 'Flow'</dd>
+    <dt><code>$content_model</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'.</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',
+    array(0 => array('Common'), 'color' => 'Color'));</pre>
+
+<p>We may want to Common attribute collection inclusion to be added
+by default.</p>
+
+<div id="version">$Id$</div>
+
+</body></html>

docs/dev-code-quality.txt

@@ -1,31 +1,16 @@
-<?xml version="1.0" encoding="UTF-8"?>
-<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN"
-    "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">
-<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en"><head>
-<meta http-equiv="Content-Type" content="text/html; charset=UTF-8" />
-<meta name="description" content="Discusses code quality issues and places that need to be refactored in HTML Purifier." />
-<link rel="stylesheet" type="text/css" href="./style.css" />
 
-<title>Code Quality Issues - HTML Purifier</title>
+Code Quality Issues
 
-</head><body>
-
-<h1>Code Quality Issues</h1>
-
-<div id="filing">Filed under Development</div>
-<div id="index">Return to the <a href="index.html">index</a>.</div>
-<div id="home"><a href="http://hp.jpsband.org/">HTML Purifier</a> End-User Documentation</div>
-
-<p>Okay, face it.  Programmers can get lazy, cut corners, or make mistakes. They
+Okay, face it.  Programmers can get lazy, cut corners, or make mistakes. They
 also can do quick prototypes, and then forget to rewrite them later.  Well,
 while I can't list mistakes in here, I can list prototype-like segments
 of code that should be aggressively refactored.  This does not list
-optimization issues, that needs to be done after intense profiling.</p>
+optimization issues, that needs to be done after intense profiling.
 
-<pre>
 docs/examples/demo.php - ad hoc HTML/PHP soup to the extreme
 
-AttrDef
+AttrDef - a lot of duplication, more generic classes need to be created;
+a lot of strtolower() calls, no legit casing
     Class - doesn't support Unicode characters (fringe); uses regular
         expressions
     Lang - code duplication; premature optimization
@@ -45,8 +30,3 @@ 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
-</pre>
-
-<div id="version">$Id$</div>
-
-</body></html>

docs/dev-naming.html

@@ -14,7 +14,7 @@
 
 <div id="filing">Filed under Development</div>
 <div id="index">Return to the <a href="index.html">index</a>.</div>
-<div id="home"><a href="http://hp.jpsband.org/">HTML Purifier</a> End-User Documentation</div>
+<div id="home"><a href="http://htmlpurifier.org/">HTML Purifier</a> End-User Documentation</div>
 
 <p>The classes in this library follow a few naming conventions, which may
 help you find the correct functionality more quickly.  Here they are:</p>

docs/dev-optimization.html

@@ -14,7 +14,7 @@
 
 <div id="filing">Filed under Development</div>
 <div id="index">Return to the <a href="index.html">index</a>.</div>
-<div id="home"><a href="http://hp.jpsband.org/">HTML Purifier</a> End-User Documentation</div>
+<div id="home"><a href="http://htmlpurifier.org/">HTML Purifier</a> End-User Documentation</div>
 
 <p>Here are some possible optimization techniques we can apply to code sections if
 they turn out to be slow.  Be sure not to prematurely optimize: if you get

docs/dev-progress.html

@@ -32,7 +32,7 @@ thead th {text-align:left;padding:0.1em;background-color:#EEE;}
 
 <div id="filing">Filed under Development</div>
 <div id="index">Return to the <a href="index.html">index</a>.</div>
-<div id="home"><a href="http://hp.jpsband.org/">HTML Purifier</a> End-User Documentation</div>
+<div id="home"><a href="http://htmlpurifier.org/">HTML Purifier</a> End-User Documentation</div>
 
 <h2>Key</h2>
 
@@ -142,7 +142,7 @@ thead th {text-align:left;padding:0.1em;background-color:#EEE;}
 
 <tbody>
 <tr><th colspan="2">Unknown</th></tr>
-<tr class="danger css1 impl-yes"><td>background-image</td><td>Dangerous, target milestone 1.3</td></tr>
+<tr class="danger css1 impl-yes"><td>background-image</td><td>Dangerous</td></tr>
 <tr class="css1 impl-yes"><td>background-attachment</td><td>ENUM(scroll, fixed),
     Depends on background-image</td></tr>
 <tr class="css1 impl-yes"><td>background-position</td><td>Depends on background-image</td></tr>
@@ -151,7 +151,7 @@ thead th {text-align:left;padding:0.1em;background-color:#EEE;}
     will not implement list-item, run-in (Opera only) or table (no IE);
     inline-block has incomplete IE6 support and requires -moz-inline-box
     for Mozilla. Unknown target milestone.</td></tr>
-<tr class="css1"><td>height</td><td>Interesting, why use it? Unknown target milestone.</td></tr>
+<tr class="css1 impl-yes"><td>height</td><td>Interesting, why use it? Unknown target milestone.</td></tr>
 <tr class="danger css1 impl-yes"><td>list-style-image</td><td>Dangerous?</td></tr>
 <tr class="impl-no"><td>max-height</td><td rowspan="4">No IE 5/6</td></tr>
 <tr class="impl-no"><td>min-height</td></tr>
@@ -168,9 +168,9 @@ thead th {text-align:left;padding:0.1em;background-color:#EEE;}
 <tr class="impl-no"><td>quotes</td><td>May be dropped from CSS2, fairly useless for inline context</td></tr>
 <tr class="impl-no"><td>visibility</td><td>ENUM(visible, hidden, collapse),
     Dangerous</td></tr>
-<tr class="css1 feature"><td>white-space</td><td>ENUM(normal, pre, nowrap, pre-wrap,
+<tr class="css1 feature impl-partial"><td>white-space</td><td>ENUM(normal, pre, nowrap, pre-wrap,
     pre-line), Spotty implementation:
-    pre (no IE 5/6), nowrap (no IE 5),
+    pre (no IE 5/6), <em>nowrap</em> (no IE 5, supported),
     pre-wrap (only Opera), pre-line (no support). Fixable? Unknown target milestone.</td></tr>
 </tbody>
 
@@ -238,14 +238,14 @@ Mozilla on inside and needs -moz-outline, no IE support.</td></tr>
 <tr><th colspan="3">Questionable</th></tr>
 <tr class="impl-no"><td>accesskey</td><td>A</td><td>May interfere with main interface</td></tr>
 <tr class="impl-no"><td>tabindex</td><td>A</td><td>May interfere with main interface</td></tr>
-<tr><td>target</td><td>A</td><td>Config enabled, only useful for frame layouts, disallowed in strict</td></tr>
+<tr class="impl-yes"><td>target</td><td>A</td><td>Config enabled, only useful for frame layouts, disallowed in strict</td></tr>
 </tbody>
 
 <tbody>
 <tr><th colspan="3">Miscellaneous</th></tr>
 <tr><td>datetime</td><td>DEL, INS</td><td>No visible effect, ISO format</td></tr>
-<tr><td>rel</td><td>A</td><td>Largely user-defined: nofollow, tag (see microformats)</td></tr>
-<tr><td>rev</td><td>A</td><td>Largely user-defined: vote-*</td></tr>
+<tr class="impl-yes"><td>rel</td><td>A</td><td>Largely user-defined: nofollow, tag (see microformats)</td></tr>
+<tr class="impl-yes"><td>rev</td><td>A</td><td>Largely user-defined: vote-*</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>
@@ -262,37 +262,37 @@ Mozilla on inside and needs -moz-outline, no IE support.</td></tr>
 </tbody>
 
 <tbody>
-<tr><th colspan="3">Transform, target milestone 1.4</th></tr>
-<tr><td rowspan="5">align</td><td>CAPTION</td><td>Near-equiv style 'caption-side', drop left and right</td></tr>
-    <tr><td>IMG</td><td rowspan="2">Margin-left and margin-right = auto or parent div</td></tr>
-    <tr><td>TABLE</td></tr>
-    <tr><td>HR</td><td>Near-equivalent style 'text-align' (Works for IE and Opera, but not Firefox). Also try <code>margin-right:auto; margin-left:0;</code> for left or <code>margin-right:0; margin-left:auto;</code> for right (optionally replacing 0 with the original margin for that side)</td></tr>
+<tr><th colspan="3">Transform</th></tr>
+<tr class="impl-yes"><td rowspan="5">align</td><td>CAPTION</td><td>'caption-side' for top/bottom, 'text-align' for left/right</td></tr>
+    <tr class="impl-yes"><td>IMG</td><td rowspan="3">See specimens/html-align-to-css.html</td></tr>
+    <tr class="impl-yes"><td>TABLE</td></tr>
+    <tr class="impl-yes"><td>HR</td></tr>
     <tr class="impl-yes"><td>H1, H2, H3, H4, H5, H6, P</td><td>Equivalent style 'text-align'</td></tr>
 <tr class="required impl-yes"><td>alt</td><td>IMG</td><td>Required, insert image filename if src is present or default invalid image text</td></tr>
-<tr><td rowspan="3">bgcolor</td><td>TABLE</td><td>Equivalent style 'background-color'</td></tr>
-    <tr><td>TR</td><td>Equivalent style 'background-color'</td></tr>
-    <tr><td>TD, TH</td><td>Equivalent style 'background-color'</td></tr>
-<tr><td>border</td><td>IMG</td><td>Near equivalent style 'border-width', as it only applies when link present</td></tr>
-<tr><td>clear</td><td>BR</td><td>Near-equiv style 'clear', transform 'all' into 'both'</td></tr>
+<tr class="impl-yes"><td rowspan="3">bgcolor</td><td>TABLE</td><td>Superset style 'background-color'</td></tr>
+    <tr class="impl-yes"><td>TR</td><td>Superset style 'background-color'</td></tr>
+    <tr class="impl-yes"><td>TD, TH</td><td>Superset style 'background-color'</td></tr>
+<tr class="impl-yes"><td>border</td><td>IMG</td><td>Equivalent style <code>border:[number]px solid</code></td></tr>
+<tr class="impl-yes"><td>clear</td><td>BR</td><td>Near-equiv style 'clear', transform 'all' into 'both'</td></tr>
 <tr class="impl-no"><td>compact</td><td>DL, OL, UL</td><td>Boolean, needs custom CSS class; rarely used anyway</td></tr>
 <tr class="required impl-yes"><td>dir</td><td>BDO</td><td>Required, insert ltr (or configuration value) if none</td></tr>
-<tr><td>height</td><td>TD, TH</td><td>Near-equiv style 'height', needs px suffix if original was in pixels</td></tr>
-<tr><td>hspace</td><td>IMG</td><td>Near-equiv styles 'margin-top' and 'margin-bottom', needs px suffix</td></tr>
+<tr class="impl-yes"><td>height</td><td>TD, TH</td><td>Near-equiv style 'height', needs px suffix if original was in pixels</td></tr>
+<tr class="impl-yes"><td>hspace</td><td>IMG</td><td>Near-equiv styles 'margin-top' and 'margin-bottom', needs px suffix</td></tr>
 <tr class="impl-yes"><td>lang</td><td>*</td><td>Copy value to xml:lang</td></tr>
-<tr><td rowspan="2">name</td><td>IMG</td><td>Turn into ID</td></tr>
-    <tr><td>A</td><td>Turn into ID? (not deprecated, though in which specs?)</td></tr>
-<tr><td>noshade</td><td>HR</td><td>Boolean, style 'border-style:solid;'</td></tr>
-<tr><td>nowrap</td><td>TD, TH</td><td>Boolean, style 'white-space:nowrap;' (not compat with IE5)</td></tr>
-<tr><td>size</td><td>HR</td><td>Near-equiv 'width', needs px suffix if original was pixels</td></tr>
+<tr class="impl-yes"><td rowspan="2">name</td><td>IMG</td><td>Turn into ID</td></tr>
+    <tr class="impl-yes"><td>A</td><td>Turn into ID</td></tr>
+<tr class="impl-yes"><td>noshade</td><td>HR</td><td>Boolean, style 'border-style:solid;'</td></tr>
+<tr class="impl-yes"><td>nowrap</td><td>TD, TH</td><td>Boolean, style 'white-space:nowrap;' (not compat with IE5)</td></tr>
+<tr class="impl-yes"><td>size</td><td>HR</td><td>Near-equiv 'height', needs px suffix if original was pixels</td></tr>
 <tr class="required impl-yes"><td>src</td><td>IMG</td><td>Required, insert blank or default img if not set</td></tr>
 <tr class="impl-yes"><td>start</td><td>OL</td><td>Poorly supported 'counter-reset', allowed in loose, dropped in strict</td></tr>
-<tr><td rowspan="3">type</td><td>LI</td><td rowspan="3">Equivalent style 'list-style-type', different allowed values though. (needs testing)</td></tr>
-    <tr><td>OL</td></tr>
-    <tr><td>UL</td></tr>
+<tr class="impl-yes"><td rowspan="3">type</td><td>LI</td><td rowspan="3">Equivalent style 'list-style-type', different allowed values though. (needs testing)</td></tr>
+    <tr class="impl-yes"><td>OL</td></tr>
+    <tr class="impl-yes"><td>UL</td></tr>
 <tr class="impl-yes"><td>value</td><td>LI</td><td>Poorly supported 'counter-reset', allowed in loose, dropped in strict</td></tr>
-<tr><td>vspace</td><td>IMG</td><td>Near-equiv styles 'margin-left' and 'margin-right', needs px suffix, see hspace</td></tr>
-<tr><td rowspan="2">width</td><td>HR</td><td rowspan="2">Near-equiv style 'width', needs px suffix if original was pixels</td></tr>
-    <tr><td>TD, TH</td></tr>
+<tr class="impl-yes"><td>vspace</td><td>IMG</td><td>Near-equiv styles 'margin-left' and 'margin-right', needs px suffix, see hspace</td></tr>
+<tr class="impl-yes"><td rowspan="2">width</td><td>HR</td><td rowspan="2">Near-equiv style 'width', needs px suffix if original was pixels</td></tr>
+    <tr class="impl-yes"><td>TD, TH</td></tr>
 </tbody>
 
 </table>

docs/enduser-id.html

@@ -15,7 +15,7 @@
 
 <div id="filing">Filed under End-User</div>
 <div id="index">Return to the <a href="index.html">index</a>.</div>
-<div id="home"><a href="http://hp.jpsband.org/">HTML Purifier</a> End-User Documentation</div>
+<div id="home"><a href="http://htmlpurifier.org/">HTML Purifier</a> End-User Documentation</div>
 
 <p>Prior to HTML Purifier 1.2.0, this library blithely accepted user input that
 looked like this:</p>

docs/enduser-overview.txt

@@ -36,7 +36,7 @@ forgiving lexer.  You may also be interested in the unit tests located in the
 tests/ folder, which provide a living document on how exactly the filter deals
 with malformed input.
 
-In summary:
+In summary (see corresponding classes for more details):
 
 1. Parse document into an array of tag and text tokens (Lexer)
 2. Remove all elements not on whitelist and transform certain other elements

docs/enduser-security.txt

@@ -6,45 +6,17 @@ through negligence of people. This class will do its job: no more, no less,
 and it's up to you to provide it the proper information and proper context
 to be effective. Things to remember:
 
-1. Character Encoding: UTF-8.
-    This segment will soon be obsoleted by enduser-utf8.html
-Currently, the parser runs under the assumption that it is dealing
-with UTF-8. Not ISO-8859-1 or Windows-1252, UTF-8. And definitely not "no
-character encoding explicitly stated" or UTF-7. If you're not using UTF-8 as
-your character encoding, make sure you configure HTML Purifier or switch
-to UTF-8. Now. Also, make sure any input is properly converted to UTF-8, or
-the parser will mangle it badly (though it won't be a security risk if you're
-outputting it as UTF-8 though).  Character encoding is, in general, a knotty
-issue, but do yourself a favor and learn about it:
-<http://www.joelonsoftware.com/articles/Unicode.html>
+1. Character Encoding: see enduser-utf8.html for more info.
 
-2. Doctype: XHTML 1.0 Transitional
-This is what the parser is outputting. For the most
-part, it's compatible with HTML 4.01, but XHTML enforces some very nice things
-that all web developers should use. Regardless, NO DOCTYPE is a NO. Quirks mode
-has waaaay too many quirks for a little parser to handle.  We did not select
-strict in order to prevent ourselves from being too draconic on users, but
-this may be configurable in the future.  Do you want standards compliance?
-The doctype is a good place to start.
+2. Doctype: document pending feature completion
+Not strictly necessary, actually. More in-depth discussion once we figure
+out how to get strict loose mode working.
 
-3. IDs
-    This segment is obsoleted by enduser-id.html
-They need to be unique, but without some knowledge of the
-rest of the document, it's difficult to know what's unique. %Attr.IDBlacklist
-needs to be set: we may want to consider disallowing IDs by default to
-save lazy programmers.
+3. IDs: see enduser-id.html for more info
 
-4. [PROJECTED] Links
-We're not going to try for spam protection (although
-some hooks for such a module might be nice) but we may offer the ability to
-only accept relative URLs. Pick the one that's right for you.
+4. Links: document pending feature completion
+Rudimentary blacklisting, we should also allow only relative URIs. We
+need a doc to explain the stuff.
 
-5. CSS
-While we can prevent the most flagrant cases from affecting your
-layout (such as absolutely positioned elements), no amount of code is going
-to protect your pages from being attacked by garish colors and plain old
-bad taste.  A neat feature would be the ability to define acceptable colors
-in a document, but that's not likely to be implemented for a while.  In the
-meantime, be sure to make sure that floated elements (permitted, since they
-can be quite useful) can't mess up your layout. Once again, we may want to
-disable this by default to protect lazy developers.
+5. CSS: document pending
+Explain which CSS styles we blocked and why.

docs/enduser-slow.html

@@ -15,7 +15,7 @@
 
 <div id="filing">Filed under End-User</div>
 <div id="index">Return to the <a href="index.html">index</a>.</div>
-<div id="home"><a href="http://hp.jpsband.org/">HTML Purifier</a> End-User Documentation</div>
+<div id="home"><a href="http://htmlpurifier.org/">HTML Purifier</a> End-User Documentation</div>
 
 <p>HTML Purifier is a very powerful library. But with power comes great 
 responsibility, in the form of longer execution times.  Remember, this 

docs/enduser-utf8.html

@@ -10,7 +10,7 @@
     .minor td {font-style:italic;}
 </style>
 
-<title>UTF-8 - HTML Purifier</title>
+<title>UTF-8: The Secret of Character Encoding - HTML Purifier</title>
 
 <!-- Note to users: this document, though professing to be UTF-8, attempts
 to use only ASCII characters, because most webservers are configured
@@ -19,21 +19,27 @@ own advice for sake of portability.  -->
 
 </head><body>
 
-<h1>UTF-8</h1>
+<h1>UTF-8: The Secret of Character Encoding</h1>
 
 <div id="filing">Filed under End-User</div>
 <div id="index">Return to the <a href="index.html">index</a>.</div>
-<div id="home"><a href="http://hp.jpsband.org/">HTML Purifier</a> End-User Documentation</div>
+<div id="home"><a href="http://htmlpurifier.org/">HTML Purifier</a> End-User Documentation</div>
 
-<p>Character encoding and character sets, in truth, are not that
-difficult to understand. But if you don't understand them, you are going
-to be caught by surprise by some of HTML Purifier's behavior, namely
-the fact that it operates UTF-8 or the limitations of the character
-encoding transformations it does. This document will walk you through
+<p>Character encoding and character sets are not that
+difficult to understand, but so many people blithely stumble
+through the worlds of programming without knowing what to actually
+do about it, or say &quot;Ah, it's a job for those <em>internationalization</em>
+experts.&quot; No, it is not! This document will walk you through
 determining the encoding of your system and how you should handle
 this information. It will stay away from excessive discussion on
-the internals of character encoding, but offer the information in
-asides that can easily be skipped.</p>
+the internals of character encoding.</p>
+
+<p>This document is not designed to be read in its entirety: it will
+slowly introduce concepts that build on each other: you need not get to
+the bottom to have learned something new. However, I strongly
+recommend you read all the way to <strong>Why UTF-8?</strong>, because at least
+at that point you'd have made a conscious decision not to migrate,
+which can be a rewarding (but difficult) task.</p>
 
 <blockquote class="aside">
 <div class="label">Asides</div>
@@ -43,6 +49,50 @@ asides that can easily be skipped.</p>
     with a greater understanding of the underlying issues.</p>
 </blockquote>
 
+<h2>Table of Contents</h2>
+
+<ol id="toc">
+    <li><a href="#findcharset">Finding the real encoding</a></li>
+    <li><a href="#findmetacharset">Finding the embedded encoding</a></li>
+    <li><a href="#fixcharset">Fixing the encoding</a><ol>
+        <li><a href="#fixcharset-none">No embedded encoding</a></li>
+        <li><a href="#fixcharset-diff">Embedded encoding disagrees</a></li>
+        <li><a href="#fixcharset-server">Changing the server encoding</a><ol>
+            <li><a href="#fixcharset-server-php">PHP header() function</a></li>
+            <li><a href="#fixcharset-server-phpini">PHP ini directive</a></li>
+            <li><a href="#fixcharset-server-nophp">Non-PHP</a></li>
+            <li><a href="#fixcharset-server-htaccess">.htaccess</a></li>
+            <li><a href="#fixcharset-server-ext">File extensions</a></li>
+        </ol></li>
+        <li><a href="#fixcharset-xml">XML</a></li>
+        <li><a href="#fixcharset-internals">Inside the process</a></li>
+    </ol></li>
+    <li><a href="#whyutf8">Why UTF-8?</a><ol>
+        <li><a href="#whyutf8-i18n">Internationalization</a></li>
+        <li><a href="#whyutf8-user">User-friendly</a></li>
+        <li><a href="#whyutf8-forms">Forms</a><ol>
+            <li><a href="#whyutf8-forms-urlencoded">application/x-www-form-urlencoded</a></li>
+            <li><a href="#whyutf8-forms-multipart">multipart/form-data</a></li>
+        </ol></li>
+        <li><a href="#whyutf8-support">Well supported</a></li>
+        <li><a href="#whyutf8-htmlpurifier">HTML Purifiers</a></li>
+    </ol></li>
+    <li><a href="#migrate">Migrate to UTF-8</a><ol>
+        <li><a href="#migrate-db">Configuring your database</a><ol>
+            <li><a href="#migrate-db-legit">Legit method</a></li>
+            <li><a href="#migrate-db-binary">Binary</a></li>
+        </ol></li>
+        <li><a href="#migrate-editor">Text editor</a></li>
+        <li><a href="#migrate-bom">Byte Order Mark (headers already sent!)</a></li>
+        <li><a href="#migrate-fonts">Fonts</a><ol>
+            <li><a href="#migrate-fonts-obscure">Obscure scripts</a></li>
+            <li><a href="#migrate-fonts-occasional">Occasional use</a></li>
+        </ol></li>
+        <li><a href="#migrate-variablewidth">Dealing with variable width in functions</a></li>
+    </ol></li>
+    <li><a href="#externallinks">Further Reading</a></li>
+</ol>
+
 <h2 id="findcharset">Finding the real encoding</h2>
 
 <p>In the beginning, there was ASCII, and things were simple. But they
@@ -275,7 +325,7 @@ your own php.ini file, ask your support for details. Use:</p>
 
 <h4 id="fixcharset-server-nophp">Non-PHP</h4>
 
-<p>You may, for whatever reason, may need to set the character encoding
+<p>You may, for whatever reason, need to set the character encoding
 on non-PHP files, usually plain ol' HTML files. Doing this
 is more of a hit-or-miss process: depending on the software being
 used as a webserver and the configuration of that software, certain
@@ -386,8 +436,8 @@ processing instructions. They look like:</p>
 
 <p>For XHTML, this processing instruction theoretically
 overrides the <code>META</code> tag. In reality, this happens only when the
-XHTML is actually served as legit XML and not HTML, which is almost
-always never due to Internet Explorer's lack of support for 
+XHTML is actually served as legit XML and not HTML, which is almost always
+never due to Internet Explorer's lack of support for 
 <code>application/xhtml+xml</code> (even though doing so is often
 argued to be <a href="http://www.hixie.ch/advocacy/xhtml">good practice</a>).</p>
 
@@ -398,10 +448,10 @@ for XML files is UTF-8, which often butts heads with more common
 ISO-8859-1 encoding (you see this in garbled RSS feeds).</p>
 
 <p>In short, if you use XHTML and have gone through the
-trouble of adding the XML header, be sure to make sure it jives
+trouble of adding the XML header, make sure it jives
 with your <code>META</code> tags and HTTP headers.</p>
 
-<h3>Inside the process</h3>
+<h3 id="fixcharset-internals">Inside the process</h3>
 
 <p>This section is not required reading,
 but may answer some of your questions on what's going on in all
@@ -572,7 +622,7 @@ Each method has deficiencies, especially the former.</p>
 the page, you still have the trouble of what to do with characters
 that are outside of the character encoding's range. The behavior, once
 again, varies: Firefox 2.0 entity-izes them while Internet Explorer
-7.0 mangles them beyond intelligibility. For serious I18N purposes,
+7.0 mangles them beyond intelligibility. For serious internationalization purposes,
 this is not an option.</p>
 
 <p>The other possibility is to set Accept-Encoding to UTF-8, which
@@ -604,22 +654,378 @@ hounding you about broken pages.</p>
 
 <h3 id="whyutf8-htmlpurifier">HTML Purifier</h3>
 
-<p>And finally, we get to HTML Purifier.</p>
+<p>And finally, we get to HTML Purifier.  HTML Purifier is built to
+deal with UTF-8: any indications otherwise are the result of an
+encoder that converts text from your preferred encoding to UTF-8, and
+back again.  HTML Purifier never touches anything else, and leaves
+it up to the module iconv to do the dirty work.</p>
+
+<p>This approach, however, is not perfect. iconv is blithely unaware
+of HTML character entities. HTML Purifier, in order to
+protect against sophisticated escaping schemes, normalizes all character
+and numeric entities before processing the text. This leads to
+one important ramification:</p>
+
+<p><strong>Any character that is not supported by the target character
+set, regardless of whether or not it is in the form of a character
+entity or a raw character, will be silently ignored.</strong></p>
+
+<p>Example of this principle at work: say you have <code>&amp;theta;</code>
+in your HTML, but the output is in Latin-1 (which, understandably,
+does not understand Greek), the following process will occur (assuming you've
+set the encoding correctly using %Core.Encoding):</p>
+
+<ul>
+    <li>The <code>Encoder</code> will transform the text from ISO 8859-1 to UTF-8
+        (note that theta is preserved since it doesn't actually use
+        any non-ASCII characters): <code>&amp;theta;</code></li>
+    <li>The <code>EntityParser</code> will transform all named and numeric
+        character entities to their corresponding raw UTF-8 equivalents:
+        <code>&theta;</code></li>
+    <li>HTML Purifier processes the code: <code>&theta;</code></li>
+    <li>The <code>Encoder</code> now transforms the text back from UTF-8
+        to ISO 8859-1. Since Greek is not supported by ISO 8859-1, it
+        will be either ignored or replaced with a question mark:
+        <code>?</code></li>
+</ul>
+
+<p>This behaviour is quite unsatisfactory. It is a deal-breaker for
+international applications, and it can be mildly annoying for the provincial
+soul who occasionally needs a special character. Since 1.4.0, HTML
+Purifier has provided a slightly more palatable workaround using
+%Core.EscapeNonASCIICharacters. The process now looks like:</p>
+
+<ul>
+    <li>The <code>Encoder</code> transforms encoding to UTF-8: <code>&amp;theta;</code></li>
+    <li>The <code>EntityParser</code> transforms entities: <code>&theta;</code></li>
+    <li>HTML Purifier processes the code: <code>&theta;</code></li>
+    <li>The <code>Encoder</code> replaces all non-ASCII characters
+        with numeric entities: <code>&amp;#952;</code></li>
+    <li>For good measure, <code>Encoder</code> transforms encoding back to
+        original (which is strictly unnecessary for 99% of encodings
+        out there): <code>&amp;#952;</code> (remember, it's all ASCII!)</li>
+</ul>
+
+<p>...which means that this is only good for an occasional foray into
+the land of Unicode characters, and is totally unacceptable for Chinese
+or Japanese texts. The even bigger kicker is that, supposing the
+input encoding was actually ISO-8859-7, which <em>does</em> support
+theta, the character would get entity-ized anyway! (The Encoder does
+not discriminate).</p>
+
+<p>The current functionality is about where HTML Purifier will be for
+the rest of eternity. HTML Purifier could attempt to preserve the original
+form of the entities so that they could be substituted back in, only the
+DOM extension kills them off irreversibly. HTML Purifier could also attempt
+to be smart and only convert non-ASCII characters that weren't supported
+by the target encoding, but that would require reimplementing iconv
+with HTML awareness, something I will not do.</p>
+
+<p>So there: either it's UTF-8 or crippled international support. Your pick! (and I'm
+not being sarcastic here: some people could care less about other languages)</p>
 
 <h2 id="migrate">Migrate to UTF-8</h2>
 
-<h3 id="migrate-editor">Text editor</h3>
+<p>So, you've decided to bite the bullet, and want to migrate to UTF-8.
+Note that this is not for the faint-hearted, and you should expect
+the process to take longer than you think it will take.</p>
+
+<p>The general idea is that you convert all existing text to UTF-8,
+and then you set all the headers and META tags we discussed earlier
+to UTF-8. There are many ways going about doing this: you could
+write a conversion script that runs through the database and re-encodes
+everything as UTF-8 or you could do the conversion on the fly when someone
+reads the page. The details depend on your system, but I will cover
+some of the more subtle points of migration that may trip you up.</p>
 
 <h3 id="migrate-db">Configuring your database</h3>
 
-<h3 id="migrate-convert">Convert old text</h3>
+<p>Most modern databases, the most prominent open-source ones being MySQL
+4.1+ and PostgreSQL, support character encodings. If you're switching
+to UTF-8, logically speaking, you'd want to make sure your database
+knows about the change too. There are some caveats though:</p>
+
+<h4 id="migrate-db-legit">Legit method</h4>
+
+<p>Standardization in terms of SQL syntax for specifying character
+encodings is notoriously spotty. Refer to your respective database's
+documentation on how to do this properly.</p>
+
+<p>For <a href="http://dev.mysql.com/doc/refman/5.0/en/charset-conversion.html">MySQL</a>, <code>ALTER</code> will magically perform the
+character encoding conversion for you. However, you have
+to make sure that the text inside the column is what is says it is:
+if you had put Shift-JIS in an ISO 8859-1 column, MySQL will irreversibly mangle
+the text when you try to convert it to UTF-8. You'll have to convert
+it to a binary field, convert it to a Shift-JIS field (the real encoding),
+and then finally to UTF-8. Many a website had pages irreversibly mangled
+because they didn't realize that they'd been deluding themselves about
+the character encoding all along, don't become the next victim.</p>
+
+<p>For <a href="http://www.postgresql.org/docs/8.2/static/multibyte.html">PostgreSQL</a>, there appears to be no direct way to change the
+encoding of a database (as of 8.2). You will have to dump the data, and then reimport
+it into a new table. Make sure that your client encoding is set properly:
+this is how PostgreSQL knows to perform an encoding conversion.</p>
+
+<p>Many times, you will be also asked about the &quot;collation&quot; of
+the new column. Collation is how a DBMS sorts text, like ordering
+B, C and A into A, B and C (the problem gets surprisingly complicated
+when you get to languages like Thai and Japanese). If in doubt,
+going with the default setting is usually a safe bet.</p>
+
+<p>Once the conversion is all said and done, you still have to remember
+to set the client encoding (your encoding) properly on each database
+connection using <code>SET NAMES</code> (which is standard SQL and is
+usually supported).</p>
+
+<h4 id="migrate-db-binary">Binary</h4>
+
+<p>Due to the abovementioned compatibility issues, a more interoperable
+way of storing UTF-8 text is to stuff it in a binary datatype.
+<code>CHAR</code> becomes <code>BINARY</code>, <code>VARCHAR</code> becomes
+<code>VARBINARY</code> and <code>TEXT</code> becomes <code>BLOB</code>.
+Doing so can save you some huge headaches:</p>
+
+<ul>
+    <li>The syntax for binary data types is very portable,</li>
+    <li>MySQL 4.0 has <em>no</em> support for character encodings, so
+        if you want to support it you <em>have</em> to use binary,</li>
+    <li>MySQL, as of 5.1, has no support for four byte UTF-8 characters,
+        which represent characters beyond the basic multilingual
+        plane, and</li>
+    <li>You will never have to worry about your DBMS being too smart
+        and attempting to convert your text when you don't want it to.</li>
+</ul>
+
+<p>MediaWiki, a very prominent international application, uses binary fields
+for storing their data because of point three.</p>
+
+<p>There are drawbacks, of course:</p>
+
+<ul>
+    <li>Database tools like PHPMyAdmin won't be able to offer you inline
+        text editing, since it is declared as binary,</li>
+    <li>It's not semantically correct: it's really text not binary
+        (lying to the database),</li>
+    <li>Unless you use the not-very-portable wizardry mentioned above,
+        you have to change the encoding yourself (usually, you'd do
+        it on the fly), and</li>
+    <li>You will not have collation.</li>
+</ul>
+
+<p>Choose based on your circumstances.</p>
+
+<h3 id="migrate-editor">Text editor</h3>
+
+<p>For more flat-file oriented systems, you will often be tasked with
+converting reams of existing text and HTML files into UTF-8, as well as
+making sure that all new files uploaded are properly encoded. Once again,
+I can only point vaguely in the right direction for converting your
+existing files: make sure you backup, make sure you use
+<a href="http://php.net/ref.iconv">iconv</a>(), and
+make sure you know what the original character encoding of the files
+is (or are, depending on the tidiness of your system).</p>
+
+<p>However, I can proffer more specific advice on the subject of
+text editors. Many text editors have notoriously spotty Unicode support.
+To find out how your editor is doing, you can check out <a
+href="http://www.alanwood.net/unicode/utilities_editors.html">this list</a>
+or <a href="http://en.wikipedia.org/wiki/Comparison_of_text_editors#Encoding_support">Wikipedia's list.</a>
+I personally use Notepad++, which works like a charm when it comes to UTF-8.
+Usually, you will have to <strong>explicitly</strong> tell the editor through some dialogue
+(usually Save as or Format) what encoding you want it to use. An editor
+will often offer &quot;Unicode&quot; as a method of saving, which is
+ambiguous. Make sure you know whether or not they really mean UTF-8
+or UTF-16 (which is another flavor of Unicode).</p>
+
+<p>The two things to look out for are whether or not the editor
+supports <strong>font mixing</strong> (multiple
+fonts in one document) and whether or not it adds a <strong>BOM</strong>.
+Font mixing is important because fonts rarely have support for every
+language known to mankind: in order to be flexible, an editor must
+be able to take a little from here and a little from there, otherwise
+all your Chinese characters will come as nice boxes. We'll discuss
+BOM below.</p>
 
 <h3 id="migrate-bom">Byte Order Mark (headers already sent!)</h3>
 
+<p>The BOM, or <a href="http://en.wikipedia.org/wiki/Byte_Order_Mark">Byte
+Order Mark</a>, is a magical, invisible character placed at
+the beginning of UTF-8 files to tell people what the encoding is and
+what the endianness of the text is. It is also unnecessary.</p>
+
+<p>Because it's invisible, it often
+catches people by surprise when it starts doing things it shouldn't
+be doing. For example, this PHP file:</p>
+
+<pre><strong>BOM</strong>&lt;?php
+header('Location: index.php');
+?&gt;</pre>
+
+<p>...will fail with the all too familiar <strong>Headers already sent</strong>
+PHP error. And because the BOM is invisible, this culprit will go unnoticed.
+My suggestion is to only use ASCII in PHP pages, but if you must, make
+sure the page is saved WITHOUT the BOM.</p>
+
+<blockquote class="aside">
+    <p>The headers the error is referring to are <strong>HTTP headers</strong>,
+       which are sent to the browser before any HTML to tell it various
+       information. The moment any regular text (and yes, a BOM counts as
+       ordinary text) is output, the headers must be sent, and you are
+       not allowed to send anymore. Thus, the error.</p>
+</blockquote>
+
+<p>If you are reading in text files to insert into the middle of another
+page, it is strongly advised (but not strictly necessary) that you replace out the UTF-8 byte 
+sequence for BOM <code>&quot;\xEF\xBB\xBF&quot;</code> before inserting it in,
+via:</p>
+
+<pre>$text = str_replace(&quot;\xEF\xBB\xBF&quot;, '', $text);</pre>
+
+<h3 id="migrate-fonts">Fonts</h3>
+
+<p>Generally speaking, people who are having trouble with fonts fall
+into two categories:</p>
+
+<ul>
+<li>Those who want to
+use an extremely obscure language for which there is very little
+support even among native speakers of the language, and</li>
+<li>Those where the primary language of the text is
+well-supported but there are occasional characters
+that aren't supported.</li>
+</ul>
+
+<p>Yes, there's always a chance where an English user happens across
+a Sinhalese website and doesn't have the right font. But an English user
+who happens not to have the right fonts probably has no business reading Sinhalese
+anyway. So we'll deal with the other two edge cases.</p>
+
+<h4 id="migrate-fonts-obscure">Obscure scripts</h4>
+
+<p>If you run a Bengali website, you may get comments from users who
+would like to read your website but get heaps of question marks or
+other meaningless characters. Fixing this problem requires the
+installation of a font or language pack which is often highly
+dependent on what the language is. <a href="http://bn.wikipedia.org/wiki/%E0%A6%89%E0%A6%87%E0%A6%95%E0%A6%BF%E0%A6%AA%E0%A7%87%E0%A6%A1%E0%A6%BF%E0%A6%AF%E0%A6%BC%E0%A6%BE:Bangla_script_display_help">Here is an example</a>
+of such a help file for the Bengali language, I am sure there are
+others out there too. You just have to point users to the appropriate
+help file.</p>
+
+<h4 id="migrate-fonts-occasional">Occasional use</h4>
+
+<p>A prime example of when you'll see some very obscure Unicode
+characters embedded in what otherwise would be very bland ASCII are
+letters of the
+<a href="http://en.wikipedia.org/wiki/International_Phonetic_Alphabet">International
+Phonetic Alphabet (IPA)</a>, use to designate pronounciations in a very standard
+manner (you probably see them all the time in your dictionary). Your
+average font probably won't have support for all of the IPA characters
+like &#664; (bilabial click) or &#658; (voiced postalveolar fricative).
+So what's a poor browser to do? Font mix! Smart browsers like Mozilla Firefox
+and Internet Explorer 7 will borrow glyphs from other fonts in order
+to make sure that all the characters display properly.</p>
+
+<p>But what happens when the browser isn't smart and happens to be the
+most widely used browser in the entire world? Microsoft IE 6
+is not smart enough to borrow from other fonts when a character isn't
+present, so more often than not you'll be slapped with a nice big &#65533;.
+To get things to work, MSIE 6 needs a little nudge. You could configure it
+to use a different font to render the text, but you can acheive the same
+effect by selectively changing the font for blocks of special characters
+to known good Unicode fonts.</p>
+
+<p>Fortunantely, the folks over at Wikipedia have already done all the
+heavy lifting for you. Get the CSS from the horses mouth here:
+<a href="http://en.wikipedia.org/wiki/MediaWiki:Common.css">Common.css</a>,
+and search for &quot;.IPA&quot; There are also a smattering of
+other classes you can use for other purposes, check out 
+<a href="http://meta.wikimedia.org/wiki/Help:Special_characters#Displaying_Special_Characters">this page</a>
+for more details. For you lazy ones, this should work:</p>
+
+<pre>.Unicode {
+        font-family: Code2000, &quot;TITUS Cyberbit Basic&quot;, &quot;Doulos SIL&quot;,
+            &quot;Chrysanthi Unicode&quot;, &quot;Bitstream Cyberbit&quot;,
+            &quot;Bitstream CyberBase&quot;, Thryomanes, Gentium, GentiumAlt,
+            &quot;Lucida Grande&quot;, &quot;Arial Unicode MS&quot;, &quot;Microsoft Sans Serif&quot;,
+            &quot;Lucida Sans Unicode&quot;;
+        font-family /**/:inherit; /* resets fonts for everyone but IE6 */
+}</pre>
+
+<p>The standard usage goes along the lines of <code>&lt;span class=&quot;Unicode&quot;&gt;Crazy
+Unicode stuff here&lt;/span&gt;</code>. Characters in the
+<a href="http://en.wikipedia.org/wiki/Windows_Glyph_List_4">Windows Glyph List</a>
+usually don't need to be fixed, but for anything else you probably
+want to play it safe. Unless, of course, you don't care about IE6
+users.</p>
+
 <h3 id="migrate-variablewidth">Dealing with variable width in functions</h3>
 
+<p>When people claim that PHP6 will solve all our Unicode problems, they're
+misinformed. It will not fix any of the abovementioned troubles. It will,
+however, fix the problem we are about to discuss: processing UTF-8 text
+in PHP.</p>
+
+<p>PHP (as of PHP5) is blithely unaware of the existence of UTF-8 (with a few
+notable exceptions). Sometimes, this will cause problems, other times,
+this won't. So far, we've avoided discussing the architecture of
+UTF-8, so, we must first ask, what is UTF-8? Yes, it supports Unicode,
+and yes, it is variable width. Other traits:</p>
+
+<ul>
+    <li>Every character's byte sequence is unique and will never be found
+        inside the byte sequence of another character,</li>
+    <li>UTF-8 may use up to four bytes to encode a character,</li>
+    <li>UTF-8 text must be checked for well-formedness,</li>
+    <li>Pure ASCII is also valid UTF-8, and</li>
+    <li>Binary sorting will sort UTF-8 in the same order as Unicode.</li>
+</ul>
+
+<p>Each of these traits affect different domains of text processing
+in different ways. It is beyond the scope of this document to explain
+what precisely these implications are. PHPWact provides
+a very good <a href="http://www.phpwact.org/php/i18n/utf-8">reference document</a>
+on what to expect from each functions, although coverage is spotty in
+some areas. Their more general notes on
+<a href="http://www.phpwact.org/php/i18n/charsets">character sets</a>
+are also worth looking at for information on UTF-8. Some rules of thumb
+when dealing with Unicode text:</p>
+
+<ul>
+    <li>Do not EVER use functions that:<ul>
+        <li>...convert case (strtolower, strtoupper, ucfirst, ucwords)</li>
+        <li>...claim to be case-insensitive (str_ireplace, stristr, strcasecmp)</li>
+    </ul></li>
+    <li>Think twice before using functions that:<ul>
+        <li>...count characters (strlen will return bytes, not characters;
+            str_split and word_wrap may corrupt)</li>
+        <li>...entity-ize things (UTF-8 doesn't need entities)</li>
+        <li>...do very complex string processing (*printf)</li>
+    </ul></li>
+</ul>
+
+<p>Note: this list applies to UTF-8 encoded text only: if you have
+a string that you are 100% sure is ASCII, be my guest and use
+<code>strtolower</code> (HTML Purifier uses this function.)</p>
+
+<p>Regardless, always think in bytes, not characters. If you use strpos()
+to find the position of a character, it will be in bytes, but this
+usually won't matter since substr() also operates with byte indices!</p>
+
+<p>You'll also need to make sure your UTF-8 is well-formed and will
+probably need replacements for some of these functions. I recommend
+using Harry Fuecks' <a href="http://phputf8.sourceforge.net/">PHP
+UTF-8</a> library, rather than use mb_string directly. HTML Purifier
+also defines a few useful UTF-8 compatible functions: check out
+<code>Encoder.php</code> in the <code>/library/HTMLPurifier/</code>
+directory.</p>
+
 <h2 id="externallinks">Further Reading</h2>
 
+<p>Well, that's it. Hopefully this document has served as a very
+practical springboard into knowledge of how UTF-8 works.  You may have
+decided that you don't want to migrate yet: that's fine, just know
+what will happen to your output and what bug reports you may recieve.</p>
+
 <p>Many other developers have already discussed the subject of Unicode,
 UTF-8 and internationalization, and I would like to defer to them for
 a more in-depth look into character sets and encodings.</p>

docs/enduser-youtube.html

@@ -15,7 +15,7 @@
 
 <div id="filing">Filed under End-User</div>
 <div id="index">Return to the <a href="index.html">index</a>.</div>
-<div id="home"><a href="http://hp.jpsband.org/">HTML Purifier</a> End-User Documentation</div>
+<div id="home"><a href="http://htmlpurifier.org/">HTML Purifier</a> End-User Documentation</div>
 
 <p>Clients like their YouTube videos. It gives them a warm fuzzy feeling when
 they see a neat little embedded video player on their websites that can play
@@ -70,7 +70,7 @@ into your documents. YouTube's code goes like this:</p>
 class=&quot;embed-youtube&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://hp.jpsband.org/svnroot/htmlpurifier/trunk/library/HTMLPurifier/Filter/YouTube.php">Show me the code!</a></p>
+<a href="http://htmlpurifier.org/svnroot/htmlpurifier/trunk/library/HTMLPurifier/Filter/YouTube.php">Show me the code!</a></p>
 
 <p>And the corresponding usage:</p>
 

docs/examples/basic.php

@@ -1,14 +1,23 @@
-<?php exit;
+<?php
 
 // This file demonstrates basic usage of HTMLPurifier.
 
-require_once '/path/to/htmlpurifier/library/HTMLPurifier.auto.php';
+// replace this with the path to the HTML Purifier library
+require_once '../../library/HTMLPurifier.auto.php';
 
-$purifier = new HTMLPurifier();
+$config = HTMLPurifier_Config::createDefault();
+
+// configuration goes here:
+$config->set('Core', 'Encoding', 'ISO-8859-1'); //replace with your encoding
+$config->set('Core', 'XHTML', true); // set to false if HTML 4.01
+
+$purifier = new HTMLPurifier($config);
+
+// untrusted input HTML
 $html = '<b>Simple and short';
 
 $pure_html = $purifier->purify($html);
 
-echo $pure_html;
+echo '<pre>' . htmlspecialchars($pure_html) . '</pre>';
 
 ?>

docs/examples/demo.php

@@ -1,136 +0,0 @@
-<?php
-
-// using _REQUEST because we accept GET and POST requests
-
-$content = empty($_REQUEST['xml']) ? 'text/html' : 'application/xhtml+xml';
-header("Content-type:$content;charset=UTF-8");
-
-// prevent PHP versions with shorttags from barfing
-echo '<?xml version="1.0" encoding="UTF-8" ?>
-';
-
-function getFormMethod() {
-    return (isset($_REQUEST['post'])) ? 'post' : 'get';
-}
-
-if (empty($_REQUEST['strict'])) {
-?><!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"
-     "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
-<?php
-} else {
-?>
-<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN"
-    "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">
-<?php
-}
-?>
-<html xmlns="http://www.w3.org/1999/xhtml" lang="en" xml:lang="en">
-<head>
-<title>HTML Purifier Live Demo</title>
-<meta http-equiv="Content-Type" content="text/html; charset=UTF-8" />
-</head>
-<body>
-<h1>HTML Purifier Live Demo</h1>
-<?php
-
-require_once '../../library/HTMLPurifier.auto.php';
-
-if (!empty($_REQUEST['html'])) { // start result
-    
-    if (strlen($_REQUEST['html']) > 50000) {
-        ?>
-        <p>Request exceeds maximum allowed text size of 50kb.</p>
-        <?php
-    } else { // start main processing
-    
-    $html = get_magic_quotes_gpc() ? stripslashes($_REQUEST['html']) : $_REQUEST['html'];
-    
-    $config = HTMLPurifier_Config::createDefault();
-    $config->set('Core', 'TidyFormat', !empty($_REQUEST['tidy']));
-    $config->set('HTML', 'Strict',     !empty($_REQUEST['strict']));
-    $purifier = new HTMLPurifier($config);
-    $pure_html = $purifier->purify($html);
-    
-?>
-<p>Here is your purified HTML:</p>
-<div style="border:5px solid #CCC;margin:0 10%;padding:1em;">
-<?php if(getFormMethod() == 'get') { ?>
-<div style="float:right;">
-    <a href="http://validator.w3.org/check?uri=referer"><img
-        src="http://www.w3.org/Icons/valid-xhtml10"
-        alt="Valid XHTML 1.0 Transitional" height="31" width="88" style="border:0;" /></a>
-</div>
-<?php } ?>
-<?php
-
-echo $pure_html;
-
-?>
-<div style="clear:both;"></div>
-</div>
-<p>Here is the source code of the purified HTML:</p>
-<pre><?php
-
-echo htmlspecialchars($pure_html, ENT_COMPAT, 'UTF-8');
-
-?></pre>
-<?php
-if (getFormMethod() == 'post') { // start POST validation notice
-?>
-<p>If you would like to validate the code with
-<a href="http://validator.w3.org/#validate-by-input">W3C's
-validator</a>, copy and paste the <em>entire</em> demo page's source.</p>
-<?php
-} // end POST validation notice
-
-} // end main processing
-
-// end result
-} else {
-
-?>
-<p>Welcome to the live demo.  Enter some HTML and see how HTML Purifier
-will filter it.</p>
-<?php
-
-}
-
-?>
-<form id="filter" action="demo.php<?php
-echo '?' . getFormMethod();
-if (isset($_REQUEST['profile']) || isset($_REQUEST['XDEBUG_PROFILE'])) {
-    echo '&amp;XDEBUG_PROFILE=1';
-} ?>" method="<?php echo getFormMethod();  ?>">
-    <fieldset>
-        <legend>HTML Purifier Input (<?php echo getFormMethod(); ?>)</legend>
-        <textarea name="html" cols="60" rows="15"><?php
-
-if (isset($html)) {
-    echo htmlspecialchars(
-            HTMLPurifier_Encoder::cleanUTF8($html), ENT_COMPAT, 'UTF-8');
-}
-        ?></textarea>
-        <?php if (getFormMethod() == 'get') { ?>
-            <p><strong>Warning:</strong> GET request method can only hold
-                8129 characters (probably less depending on your browser).
-                If you need to test anything
-                larger than that, try the <a href="demo.php?post">POST form</a>.</p>
-        <?php } ?>
-        <?php if (extension_loaded('tidy')) { ?>
-            <div>Nicely format output with Tidy? <input type="checkbox" value="1"
-            name="tidy"<?php if (!empty($_REQUEST['tidy'])) echo ' checked="checked"'; ?> /></div>
-        <?php } ?>
-        <div>XHTML 1.0 Strict output? <input type="checkbox" value="1"
-        name="strict"<?php if (!empty($_REQUEST['strict'])) echo ' checked="checked"'; ?> /></div>
-        <div>Serve as application/xhtml+xml? (not for IE) <input type="checkbox" value="1"
-        name="xml"<?php if (!empty($_REQUEST['xml'])) echo ' checked="checked"'; ?> /></div>
-        <div>
-            <input type="submit" value="Submit" name="submit" class="button" />
-        </div>
-    </fieldset>
-</form>
-<p>Return to <a href="http://hp.jpsband.org/">HTML Purifier's home page</a>.
-Try the form in <a href="demo.php?get">GET</a> and <a href="demo.php?post">POST</a> request
-flavors (GET is easy to validate with W3C, but POST allows larger inputs).</p>
-</body>
-</html>

docs/fixquotes.htc

@@ -0,0 +1,6 @@
+<public:attach event="oncontentready" onevent="init();" />
+<script>
+function init() {
+  element.innerHTML = '&#8220;'+element.innerHTML+'&#8221;';
+}
+</script>

docs/index.html

@@ -13,7 +13,7 @@
 
 <h1>Documentation</h1>
 
-<p><strong><a href="http://hp.jpsband.org/">HTML Purifier</a></strong> has documentation for all types of people.
+<p><strong><a href="http://htmlpurifier.org/">HTML Purifier</a></strong> has documentation for all types of people.
 Here is an index of all of them.</p>
 
 <h2>End-user</h2>
@@ -31,7 +31,7 @@ information for casual developers using HTML Purifier.</p>
 <dt><a href="enduser-slow.html">Speeding up HTML Purifier</a></dt>
 <dd>Explains how to speed up HTML Purifier through caching or inbound filtering.</dd>
 
-<dt><a href="enduser-utf8.html">UTF-8</a></dt>
+<dt><a href="enduser-utf8.html">UTF-8: The Secret of Character Encoding</a></dt>
 <dd>Describes the rationale for using UTF-8, the ramifications otherwise, and how to make the switch.</dd>
 
 </dl>
@@ -42,9 +42,6 @@ conventions.</p>
 
 <dl>
 
-<dt><a href="dev-code-quality.html">Code Quality Issues</a></dt>
-<dd>Discusses code quality issues and places that need to be refactored.</dd>
-
 <dt><a href="dev-progress.html">Implementation Progress</a></dt>
 <dd>Tables detailing HTML element and CSS property implementation coverage.</dd>
 
@@ -54,6 +51,10 @@ conventions.</p>
 <dt><a href="dev-optimization.html">Optimization</a></dt>
 <dd>Discusses possible methods of optimizing HTML Purifier.</dd>
 
+<dt><a href="dev-advanced-api.html">Advanced API</a></dt>
+<dd>Functional specification for HTML Purifier's advanced API for defining
+custom filtering behavior.</dd>
+
 </dl>
 
 <h2>Proposals</h2>
@@ -101,6 +102,12 @@ 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="enduser-code-quality.txt">Code Quality Issues</a></td>
+    <td>Enumerates code quality issues and places that need to be refactored.</td>
+</tr>
+
 <tr>
     <td>Proposal</td>
     <td><a href="proposal-filter-levels.txt">Filter levels</a></td>

docs/proposal-colors.html

@@ -15,7 +15,7 @@
 
 <div id="filing">Filed under Proposals</div>
 <div id="index">Return to the <a href="index.html">index</a>.</div>
-<div id="home"><a href="http://hp.jpsband.org/">HTML Purifier</a> End-User Documentation</div>
+<div id="home"><a href="http://htmlpurifier.org/">HTML Purifier</a> End-User Documentation</div>
 
 <p>Your website probably has a color-scheme.
 <span style="color:#090; background:#FFF;">Green on white</span>,

docs/proposal-config.txt

@@ -7,7 +7,7 @@ value is used for.  This means decentralized configuration declarations that
 are nevertheless error checking and a centralized configuration object.
 
 Directives are divided into namespaces, indicating the major portion of
-functionality they cover (although there may be overlaps.  Please consult
+functionality they cover (although there may be overlaps).  Please consult
 the documentation in ConfigDef for more information on these namespaces.
 
 Since configuration is dependant on context, internal classes require a
@@ -36,4 +36,5 @@ the definition, you'd have to force reconstruction.
 
 In practice, the pulling directives from the config object are
 solely need-based, and the flex points are littered throughout the
-setup() function.  Some sort of refactoring is likely in order.
+setup() function.  Some sort of refactoring is likely in order. See
+ref-xhtml-1.1.txt for more info.

docs/proposal-language.txt

@@ -1,42 +1,6 @@
 We are going to model our I18N/L10N off of MediaWiki's system.  Their's is
 obviously quite complicated, so we're going to simplify it a bit for our needs.
 
-== Structure ==
-
-First, you have a Language object.  This object contains all the localisable
-message strings, as well as other important language-specific settings and
-custom behavior (uppercasing, lowercasing, printing dates, formatting
-numbers, etc.)
-
-The object is constructed from two sources: subclassed versions of itself
-(classes) and Message files (messages).
-
-== General use ==
-
-You load a language object by calling the Language::factory() function. 
-This function the class file for the object (taking in account fallback 
-languages by using the fallback langauge's object but overloading the 
-language key) and returns that object. Nothing else happens.
-
-When a message/etc is requested, a lazy load initializor is called.  Now the
-real work starts.  We're first going to take the scenario that the language
-is not cached.  The system loads the Messages file by:
-
-    require( $filename );
-    $cache = compact( self::$mLocalisationKeys );	
-
-...where self::$mLocalisationKeys is the name of variables that could be used
-in the localization file. This lets you use things like:
-
-    $fallback = false;
-    $rtl = false;
-
-...and easily siphon them into arrays.
-
-Then, we load the $fallback language (if not set, English) to fill in the gaps in
-the messages.  There is specialized behavior for certain keys, as they can be
-mergeable maps, lists or alias lists (not sure what the last one is).
-
 == Caching ==
 
 MediaWiki has lots of caching mechanisms built in, which make the code somewhat

docs/ref-devnetwork.html

@@ -15,7 +15,7 @@
 
 <div id="filing">Filed under Reference</div>
 <div id="index">Return to the <a href="index.html">index</a>.</div>
-<div id="home"><a href="http://hp.jpsband.org/">HTML Purifier</a> End-User Documentation</div>
+<div id="home"><a href="http://htmlpurifier.org/">HTML Purifier</a> End-User Documentation</div>
 
 <p>Many thanks to the DevNetwork community for answering questions,
 theorizing about design, and offering encouragement during

docs/ref-loose-vs-strict.txt

@@ -32,6 +32,6 @@ A tag's attribute 'target' (for selecting frames) cut
     current behavior: no substitute, just delete when in strict, allow in loose
 Attribute 'name' deprecated in favor of 'id'
     current behavior: dropped silently
-    projected behavior: create proper AttrTransform (currently not allowed at all)
+    projected behavior: create proper AttrTransform
 [done] PRE tag allows SUB/SUP? (strict dtd comment vs syntax, loose disallows)
     current behavior: disallow as usual

docs/ref-xhtml-1.1.txt

@@ -1,21 +1,187 @@
 
-Getting XHTML 1.1 Working
-
-It's quite simple, according to <http://www.w3.org/TR/xhtml11/changes.html>
+XHTML 1.1 and HTML Purifier
 
+Todo for XHTML 1.1 support <http://www.w3.org/TR/xhtml11/changes.html>
 1. Scratch lang entirely in favor of xml:lang
 2. Scratch name entirely in favor of id (partially-done)
 3. Support Ruby <http://www.w3.org/TR/2001/REC-ruby-20010531/>
 
-...but that's only an informative section. More things to do:
+HTML Purifier uses the modularization of XHTML
+<http://www.w3.org/TR/xhtml-modularization/> to organize the internals
+of HTMLDefinition into a more manageable and extensible fashion. Rather
+than have one super-object, HTMLDefinition is split into HTMLModules,
+each of which are responsible for defining elements, their attributes,
+and other properties (for a more indepth coverage, see
+/library/HTMLPurifier/HTMLModule.php's docblock comments).
 
-1. Scratch style attribute (it's deprecated)
-2. Be module-aware (this might entail intelligent grouping in the definition
-   and allowing users to specifically remove certain modules (see 5))
-3. Cross-reference minimal content models with existing DTDs and determine
-   changes (todo)
-4. Watch out for the Legacy Module
-<http://www.w3.org/TR/2001/REC-xhtml-modularization-20010410/abstract_modules.html#s_legacymodule>
-5. Let users specify their own custom modules
-6. Study Modularization document
-<http://www.w3.org/TR/2001/REC-xhtml-modularization-20010410/>
+The modules that W3C defines and we support are:
+
+    * 5.1. Attribute Collections (technically not a module
+    * 5.2. Core Modules
+          o 5.2.2. Text Module
+          o 5.2.3. Hypertext Module
+          o 5.2.4. List Module
+    * 5.4. Text Extension Modules
+          o 5.4.1. Presentation Module
+          o 5.4.2. Edit Module
+          o 5.4.3. Bi-directional Text Module
+    * 5.6. Table Modules
+          o 5.6.2. Tables Module
+    * 5.7. Image Module
+    * 5.18. Style Attribute Module
+
+Modules that we don't support but coul support are:
+
+    * 5.6. Table Modules
+          o 5.6.1. Basic Tables Module [?]
+    * 5.8. Client-side Image Map Module [?]
+    * 5.9. Server-side Image Map Module [?]
+    * 5.12. Target Module [?]
+    * 5.21. Name Identification Module [deprecated]
+    * 5.22. Legacy Module [deprecated]
+
+These modules will not be implemented due to their dangerousness or
+inapplicability as an XHTML fragment:
+
+    * 5.2. Core Modules
+          o 5.2.1. Structure Module
+    * 5.3. Applet Module
+    * 5.5. Forms Modules
+          o 5.5.1. Basic Forms Module
+          o 5.5.2. Forms Module
+    * 5.10. Object Module
+    * 5.11. Frames Module
+    * 5.13. Iframe Module
+    * 5.14. Intrinsic Events Module
+    * 5.15. Metainformation Module
+    * 5.16. Scripting Module
+    * 5.17. Style Sheet Module
+    * 5.19. Link Module
+    * 5.20. Base Module
+
+We will not be using W3C's XML Schemas or DTDs directly due to the lack
+of robust tools for handling them (the main problem is that all the
+current parsers are usually PHP 5 only and solely-validating, not
+correcting).
+
+The abstraction of the HTMLDefinition creation process will also
+contribute to a need for a caching system. Cache invalidation would be
+difficult, but could be done by comparing the HTML and Attr config
+namespaces with a copy that was packaged along with the serialized
+HTMLDefinition object.
+
+== General Use-Case ==
+
+The outwards API of HTMLDefinition has been largely preserved, not
+only for backwards-compatibility but also by design. Instead,
+HTMLDefinition can be retrieved "raw", in which it loads a structure
+that closely resembles the modules of XHTML 1.1. This structure is very
+dynamic, making it easy to make cascading changes to global content
+sets or remove elements in bulk.
+
+However, once HTML Purifier needs the actual definition, it retrieves
+a finalized version of HTMLDefinition. The finalized definition involves
+processing the modules into a form that it is optimized for multiple
+calls. This final version is immutable and, even if editable, would
+be extremely hard to change.
+
+So, some code taking advantage of the XHTML modularization may look
+like this:
+
+<?php
+    $config = HTMLPurifier_Config::createDefault();
+    $def =& $config->getHTMLDefinition(true); // reference to raw
+    unset($def->modules['Hypertext']); // rm ''a'' link
+    $purifier = new HTMLPurifier($config);
+    $purifier->purify($html); // now the definition is finalized
+?>
+
+== Inclusions ==
+
+One of the nice features of HTMLDefinition is that piggy-backing off
+of global attribute and content sets is extremely easy to do.
+
+=== Attributes ===
+
+HTMLModule->elements[$element]->attr stores attribute information for the
+specific attributes of $element. This is quite close to the final
+API that HTML Purifier interfaces with, but there's an important
+extra feature: attr may also contain a array with a member index zero.
+
+<?php
+    HTMLModule->elements[$element]->attr[0] = array('AttrSet');
+?>
+
+Rather than map the attribute key 0 to an array (which should be
+an AttrDef), it defines a number of attribute collections that should
+be merged into this elements attribute array.
+
+Furthermore, the value of an attribute key, attribute value pair need
+not be a fully fledged AttrDef object. They can also be a string, which
+signifies a AttrDef that is looked up from a centralized registry
+AttrTypes. This allows more concise attribute definitions that look
+more like W3C's declarations, as well as offering a centralized point
+for modifying the behavior of one attribute type. And, of course, the
+old method of manually instantiating an AttrDef still works.
+
+=== Attribute Collections ===
+
+Attribute collections are stored and processed in the AttrCollections
+object, which is responsible for performing the inclusions signified
+by the 0 index. These attribute collections, too, are mutable, by
+using HTMLModule->attr_collections. You may add new attributes
+to a collection or define an entirely new collection for your module's
+use. Inclusions can also be cumulative.
+
+Attribute collections allow us to get rid of so called "global attributes"
+(which actually aren't so global).
+
+=== Content Models and ChildDef ===
+
+An implementation of the above-mentioned attributes and attribute
+collections was applied to the ChildDef system. HTML Purifier uses
+a proprietary system called ChildDef for performance and flexibility
+reasons, but this does not line up very well with W3C's notion of
+regexps for defining the allowed children of an element.
+
+HTMLPurifier->elements[$element]->content_model and 
+HTMLPurifier->elements[$element]->content_model_type store information
+about the final ChildDef that will be stored in
+HTMLPurifier->elements[$element]->child (we use a different variable
+because the two forms are sufficiently different).
+
+$content_model is an abstract, string representation of the internal
+state of ChildDef, while $content_model_type is a string identifier
+of which ChildDef subclass to instantiate. $content_model is processed
+by substituting all content set identifiers (capitalized element names)
+with their contents. It is then parsed and passed into the appropriate
+ChildDef class, as defined by the ContentSets->getChildDef() or the
+custom fallback HTMLModule->getChildDef() for custom child definitions
+not in the core.
+
+You'll need to use these facilities if you plan on referencing a content
+set like "Inline" or "Block", and using them is recommended even if you're
+not due to their conciseness.
+
+A few notes on $content_model: it's structure can be as complicated
+as you want, but the pipe symbol (|) is reserved for defining possible
+choices, due to the content sets implementation. For example, a content
+model that looks like:
+
+"Inline -> Block -> a"
+
+...when the Inline content set is defined as "span | b" and the Block
+content set is defined as "div | blockquote", will expand into:
+
+"span | b -> div | blockquote -> a"
+
+The custom HTMLModule->getChildDef() function will need to be able to
+then feed this information to ChildDef in a usable manner.
+
+=== Content Sets ===
+
+Content sets can be altered using HTMLModule->content_sets, an associative
+array of content set names to content set contents. If the content set
+already exists, your values are appended on to it (great for, say,
+registering the font tag as an inline element), otherwise it is
+created. They are substituted into content_model.

docs/specimens/LICENSE

@@ -0,0 +1,8 @@
+Licensing of Specimens
+
+Some files in this directory have different licenses:
+
+windows-live-mail-desktop-beta.html - donated by laacz, public domain
+img.png - LGPL, from <http://commons.wikimedia.org/wiki/Image:Pastille_chrome.png>
+
+All other files are by me, and are licensed under LGPL.

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

@@ -0,0 +1,165 @@
+<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN"
+   "http://www.w3.org/TR/html4/loose.dtd">
+<html>
+<head>
+<title>HTML align attribute to CSS - HTML Purifier Specimen</title>
+<style type="text/css">
+div.container {position:relative;height:110px;}
+div.container.legend .test {text-align:center;line-height:100px;}
+div.test {width:100px;height:100px;border:1px solid black;
+position:absolute;top:10px;}
+div.test.html {left:10px;}
+div.test.css  {left:140px;}
+table {background:#F00;}
+img {border:1px solid #000;}
+hr {width:50px;}
+div.segment {width:250px; float:left; margin-top:1em;}
+</style>
+</head>
+<body>
+
+<h1>HTML align attribute to CSS</h1>
+
+<p>Inspect source for methodology.</p>
+
+<div class="container legend">
+<div class="test html">
+    HTML
+</div>
+<div class="test css">
+    CSS
+</div>
+</div>
+
+<div class="segment">
+
+<h2>table.align</h2>
+
+<h3>left</h3>
+<div class="container">
+<div class="test html">
+    a<table align="left"><tr><td>O</td></tr></table>a
+</div>
+<div class="test css">
+    a<table style="float:left;"><tr><td>O</td></tr></table>a
+</div>
+</div>
+
+<h3>center</h3>
+<div class="container">
+<div class="test html">
+    a<table align="center"><tr><td>O</td></tr></table>a
+</div>
+<div class="test css">
+    a<table style="margin-left:auto; margin-right:auto;"><tr><td>O</td></tr></table>a
+</div>
+</div>
+
+<h3>right</h3>
+<div class="container">
+<div class="test html">
+    a<table align="right"><tr><td>O</td></tr></table>a
+</div>
+<div class="test css">
+    a<table style="float:right;"><tr><td>O</td></tr></table>a
+</div>
+</div>
+
+</div>
+
+<!-- ################################################################## -->
+
+<div class="segment">
+<h2>img.align</h2>
+<h3>left</h3>
+<div class="container">
+<div class="test html">
+    a<img src="img.png" align="left">a
+</div>
+<div class="test css">
+    a<img src="img.png" style="float:left;">a
+</div>
+</div>
+
+<h3>right</h3>
+<div class="container">
+<div class="test html">
+    a<img src="img.png" align="right">a
+</div>
+<div class="test css">
+    a<img src="img.png" style="float:right;">a
+</div>
+</div>
+
+<h3>bottom</h3>
+<div class="container">
+<div class="test html">
+    a<img src="img.png" align="bottom">a
+</div>
+<div class="test css">
+    a<img src="img.png" style="vertical-align:baseline;">a
+</div>
+</div>
+
+<h3>middle</h3>
+<div class="container">
+<div class="test html">
+    a<img src="img.png" align="middle">a
+</div>
+<div class="test css">
+    a<img src="img.png" style="vertical-align:middle;">a
+</div>
+</div>
+
+<h3>top</h3>
+<div class="container">
+<div class="test html">
+    a<img src="img.png" align="top">a
+</div>
+<div class="test css">
+    a<img src="img.png" style="vertical-align:top;">a
+</div>
+</div>
+
+</div>
+
+<!-- ################################################################## -->
+
+<div class="segment">
+
+<h2>hr.align</h2>
+
+<h3>left</h3>
+<div class="container">
+<div class="test html">
+    <hr align="left" />
+</div>
+<div class="test css">
+    <hr style="margin-right:auto; margin-left:0; text-align:left;" />
+</div>
+</div>
+
+<h3>center</h3>
+<div class="container">
+<div class="test html">
+    <hr align="center" />
+</div>
+<div class="test css">
+    <hr style="margin-right:auto; margin-left:auto; text-align:center;" />
+</div>
+</div>
+
+<h3>right</h3>
+<div class="container">
+<div class="test html">
+    <hr align="right" />
+</div>
+<div class="test css">
+    <hr style="margin-right:0; margin-left:auto; text-align:right;" />
+</div>
+</div>
+
+</div>
+
+</body>
+</html>

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

@@ -0,0 +1,74 @@
+<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.0 Transitional//EN">
+<HTML ChildAreas="4" xmlns:canvas><HEAD>
+<META http-equiv=Content-Type content=text/html;charset=windows-1257>
+<STYLE></STYLE>
+
+<META content="MSHTML 6.00.6000.16414" name=GENERATOR></HEAD>
+<BODY id=MailContainerBody 
+style="PADDING-RIGHT: 10px; PADDING-LEFT: 10px; FONT-SIZE: 10pt; COLOR: #000000; PADDING-TOP: 15px; FONT-FAMILY: Arial" 
+bgColor=#ff6600 leftMargin=0 background="" topMargin=0 
+name="Compose message area" acc_role="text" CanvasTabStop="false">
+<DIV 
+style="BORDER-TOP: #dddddd 1px solid; FONT-SIZE: 10pt; WIDTH: 100%; MARGIN-RIGHT: 10px; PADDING-TOP: 5px; BORDER-BOTTOM: #dddddd 1px solid; FONT-FAMILY: Verdana; HEIGHT: 25px; BACKGROUND-COLOR: #ffffff"><NOBR><SPAN 
+title="View a slideshow of the pictures in this e-mail message." 
+style="PADDING-RIGHT: 20px"><A style="COLOR: #0088e4" 
+href="http://g.msn.com/5meen_us/171?path=/photomail/{6fc0065f-ffdd-4ca6-9a4c-cc5a93dc122f}&amp;image=47D7B182CFEFB10!127&amp;imagehi=47D7B182CFEFB10!125&amp;CID=323550092004883216">Play 
+slideshow </A></SPAN><SPAN style="COLOR: #909090"><SPAN>|</SPAN><SPAN 
+style="PADDING-LEFT: 20px"> Download the highest quality version of a picture by 
+clicking the + above it </SPAN></SPAN></NOBR></DIV>
+<DIV 
+style="PADDING-RIGHT: 5px; PADDING-LEFT: 7px; PADDING-BOTTOM: 2px; WIDTH: 100%; PADDING-TOP: 2px">
+<OL>
+  <LI><IMG title="Angry smile emoticon" 
+  style="FLOAT: none; MARGIN: 0px; POSITION: static" tabIndex=-1 
+  alt="Angry smile emoticon" src="cid:49F0C856199E4D688D2D740680733D74@wc" 
+  MSNNonUserImageOrEmoticon="true">Un ka <FONT style="BACKGROUND-COLOR: #800000" 
+  color=#cc99ff><STRONG>Tev</STRONG></FONT> iet, un ko tu dari? 
+  <LI>Aha!</LI></OL>
+
+<UL>
+  <LI>Buletets 
+  <LI>
+  <DIV align=justify><A title=http://laacz.lv/blog/ 
+  href="http://laacz.lv/blog/">http://laacz.lv/blog/</A> un <A 
+  title=http://google.com/ href="http://google.com/">gugle</A></DIV>
+  <LI>Sarakstucitis</LI></UL></DIV><SPAN><SPAN xmlns:canvas="canvas-namespace-id" 
+layoutEmptyTextWellFont="Tahoma"><SPAN 
+style="MARGIN-BOTTOM: 15px; OVERFLOW: visible; HEIGHT: 16px"></SPAN><SPAN 
+style="MARGIN-BOTTOM: 25px; VERTICAL-ALIGN: top; OVERFLOW: visible; MARGIN-RIGHT: 25px; HEIGHT: 234px">
+<TABLE style="DISPLAY: inline">
+  <TBODY>
+  <TR>
+
+    <TD>
+      <DIV 
+      style="FONT-WEIGHT: bold; FONT-SIZE: 12pt; FONT-FAMILY: arial; TEXT-ALIGN: center"><A 
+      id=HiresARef 
+      title="Click here to view or download a high resolution version of this picture" 
+      style="COLOR: #0088e4; TEXT-DECORATION: none" 
+      href="http://byfiles.storage.msn.com/x1pMvt0I80jTgT6DuaCpEMbprX3nk3jNv_vjigxV_EYVSMyM_PKgEvDEUtuNhQC-F-23mTTcKyqx6eGaeK2e_wMJ0ikwpDdFntk4SY7pfJUv2g2Ck6R2S2vAA?download">+</A></DIV>
+      <DIV 
+      title="Click here to view the full image using the online photo viewer." 
+      style="DISPLAY: inline; OVERFLOW: hidden; WIDTH: 140px; HEIGHT: 140px"><A 
+      href="http://g.msn.com/5meen_us/171?path=/photomail/{6fc0065f-ffdd-4ca6-9a4c-cc5a93dc122f}&amp;image=47D7B182CFEFB10!127&amp;imagehi=47D7B182CFEFB10!125&amp;CID=323550092004883216" 
+      border="0"><IMG 
+      style="MARGIN-TOP: 15px; DISPLAY: inline-block; MARGIN-LEFT: 0px" 
+      height=109 src="cid:006A71303B80404E9FB6184E55D6A446@wc" width=140 
+      border=0></A></DIV></TD></TR>
+  <TR>
+    <TD>
+      <DIV 
+      style="FONT-SIZE: 10pt; WIDTH: 140px; FONT-FAMILY: verdana; TEXT-ALIGN: center"><EM><STRONG>This 
+      <U>is </U></STRONG><U>tit</U>le</EM> fo<STRONG>r <FONT 
+      face="Arial Black">t<FONT color=#800000 size=7>h<U>i</U></FONT>s 
+      </FONT>picture</STRONG></DIV></TD></TR></TBODY></TABLE></SPAN></SPAN></SPAN>
+
+<DIV 
+style="PADDING-RIGHT: 5px; PADDING-LEFT: 7px; PADDING-BOTTOM: 2px; WIDTH: 100%; PADDING-TOP: 2px; HEIGHT: 50px">
+<DIV>&nbsp;</DIV></DIV>
+<DIV 
+style="BORDER-TOP: #dddddd 1px solid; FONT-SIZE: 10pt; MARGIN-BOTTOM: 10px; WIDTH: 100%; COLOR: #909090; MARGIN-RIGHT: 10px; PADDING-TOP: 9px; FONT-FAMILY: Verdana; HEIGHT: 42px; BACKGROUND-COLOR: #ffffff"><NOBR><SPAN 
+title="Join Windows Live to share photos using Windows Live Photo E-mail.">Online 
+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>

docs/style.css

@@ -42,3 +42,27 @@ blockquote .label {font-weight:bold; font-size:1em; margin:0 0 .1em;
 
 /* Contains, without exception, $Id$, for SVN version info. */
 #version {text-align:right; font-style:italic; margin:2em 0;}
+
+#toc ol ol {list-style-type:lower-roman;}
+#toc ol {list-style-type:decimal;}
+#toc {list-style-type:upper-alpha;}
+
+q {
+  behavior: url(fixquotes.htc); /* IE fix */
+  quotes: '\201C' '\201D' '\2018' '\2019';
+}
+q:before {
+  content: open-quote;
+}
+q:after {
+  content: close-quote;
+}
+
+/* Marks off implementation details interesting only to the person writing
+   the class described in the spec. */
+.technical {margin-left:2em; }
+.technical:before {content:"Technical note: "; font-weight:bold; color:#061; }
+
+/* Marks off sections that are lacking. */
+.fixme {margin-left:2em; }
+.fixme:before {content:"Fix me: "; font-weight:bold; color:#C00; }

library/HTMLPurifier.php

@@ -22,7 +22,7 @@
  */
 
 /*
-    HTML Purifier 1.4.1 - Standards Compliant HTML Filtering
+    HTML Purifier 1.6.1 - Standards Compliant HTML Filtering
     Copyright (C) 2006 Edward Z. Yang
 
     This library is free software; you can redistribute it and/or
@@ -64,7 +64,7 @@ require_once 'HTMLPurifier/Encoder.php';
 class HTMLPurifier
 {
     
-    var $version = '1.4.1';
+    var $version = '1.6.1';
     
     var $config;
     var $filters;

library/HTMLPurifier/AttrCollections.php

@@ -0,0 +1,100 @@
+<?php
+
+require_once 'HTMLPurifier/AttrTypes.php';
+require_once 'HTMLPurifier/AttrDef/Lang.php';
+
+/**
+ * Defines common attribute collections that modules reference
+ */
+
+class HTMLPurifier_AttrCollections
+{
+    
+    /**
+     * Associative array of attribute collections, indexed by name
+     * @note Technically, the composition of these is more complicated,
+     *       but we bypass it using our own excludes property
+     */
+    var $info = array();
+    
+    /**
+     * 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 $modules Hash array of HTMLPurifier_HTMLModule members
+     */
+    function HTMLPurifier_AttrCollections($attr_types, $modules) {
+        $info =& $this->info;
+        // load extensions from the modules
+        foreach ($modules as $module) {
+            foreach ($module->attr_collections as $coll_i => $coll) {
+                foreach ($coll as $attr_i => $attr) {
+                    if ($attr_i === 0 && isset($info[$coll_i][$attr_i])) {
+                        // merge in includes
+                        $info[$coll_i][$attr_i] = array_merge(
+                            $info[$coll_i][$attr_i], $attr);
+                        continue;
+                    }
+                    $info[$coll_i][$attr_i] = $attr;
+                }
+            }
+        }
+        // perform internal expansions and inclusions
+        foreach ($info as $name => $attr) {
+            // merge attribute collections that include others
+            $this->performInclusions($info[$name]);
+            // replace string identifiers with actual attribute objects
+            $this->expandIdentifiers($info[$name], $attr_types);
+        }
+    }
+    
+    /**
+     * Takes a reference to an attribute associative array and performs
+     * all inclusions specified by the zero index.
+     * @param &$attr Reference to attribute array
+     */
+    function performInclusions(&$attr) {
+        if (!isset($attr[0])) return;
+        $merge = $attr[0];
+        // loop through all the inclusions
+        for ($i = 0; isset($merge[$i]); $i++) {
+            // foreach attribute of the inclusion, copy it over
+            foreach ($this->info[$merge[$i]] as $key => $value) {
+                if (isset($attr[$key])) continue; // also catches more inclusions
+                $attr[$key] = $value;
+            }
+            if (isset($info[$merge[$i]][0])) {
+                // recursion
+                $merge = array_merge($merge, isset($info[$merge[$i]][0]));
+            }
+        }
+        unset($attr[0]);
+    }
+    
+    /**
+     * Expands all string identifiers in an attribute array by replacing
+     * them with the appropriate values inside HTMLPurifier_AttrTypes
+     * @param &$attr Reference to attribute array
+     * @param $attr_types HTMLPurifier_AttrTypes instance
+     */
+    function expandIdentifiers(&$attr, $attr_types) {
+        foreach ($attr as $def_i => $def) {
+            if ($def_i === 0) continue;
+            if (!is_string($def)) continue;
+            if ($def === false) {
+                unset($attr[$def_i]);
+                continue;
+            }
+            if (isset($attr_types->info[$def])) {
+                $attr[$def_i] = $attr_types->info[$def];
+            } else {
+                trigger_error('Attempted to reference undefined attribute type', E_USER_ERROR);
+                unset($attr[$def_i]);
+            }
+        }
+    }
+    
+}
+
+?>

library/HTMLPurifier/AttrDef/CSS/Background.php

@@ -7,7 +7,7 @@ require_once 'HTMLPurifier/CSSDefinition.php';
  * Validates shorthand CSS property background.
  * @warning Does not support url tokens that have internal spaces.
  */
-class HTMLPurifier_AttrDef_Background extends HTMLPurifier_AttrDef
+class HTMLPurifier_AttrDef_CSS_Background extends HTMLPurifier_AttrDef
 {
     
     /**
@@ -16,7 +16,7 @@ class HTMLPurifier_AttrDef_Background extends HTMLPurifier_AttrDef
      */
     var $info;
     
-    function HTMLPurifier_AttrDef_Background($config) {
+    function HTMLPurifier_AttrDef_CSS_Background($config) {
         $def = $config->getCSSDefinition();
         $this->info['background-color'] = $def->info['background-color'];
         $this->info['background-image'] = $def->info['background-image'];

library/HTMLPurifier/AttrDef/CSS/BackgroundPosition.php

@@ -1,8 +1,8 @@
 <?php
 
 require_once 'HTMLPurifier/AttrDef.php';
-require_once 'HTMLPurifier/AttrDef/CSSLength.php';
-require_once 'HTMLPurifier/AttrDef/Percentage.php';
+require_once 'HTMLPurifier/AttrDef/CSS/Length.php';
+require_once 'HTMLPurifier/AttrDef/CSS/Percentage.php';
 
 /* W3C says:
     [ // adjective and number must be in correct order, even if
@@ -45,15 +45,15 @@ require_once 'HTMLPurifier/AttrDef/Percentage.php';
 /**
  * Validates the value of background-position.
  */
-class HTMLPurifier_AttrDef_BackgroundPosition extends HTMLPurifier_AttrDef
+class HTMLPurifier_AttrDef_CSS_BackgroundPosition extends HTMLPurifier_AttrDef
 {
     
     var $length;
     var $percentage;
     
-    function HTMLPurifier_AttrDef_BackgroundPosition() {
-        $this->length     = new HTMLPurifier_AttrDef_CSSLength();
-        $this->percentage = new HTMLPurifier_AttrDef_Percentage();
+    function HTMLPurifier_AttrDef_CSS_BackgroundPosition() {
+        $this->length     = new HTMLPurifier_AttrDef_CSS_Length();
+        $this->percentage = new HTMLPurifier_AttrDef_CSS_Percentage();
     }
     
     function validate($string, $config, &$context) {

library/HTMLPurifier/AttrDef/CSS/Border.php

@@ -5,7 +5,7 @@ require_once 'HTMLPurifier/AttrDef.php';
 /**
  * Validates the border property as defined by CSS.
  */
-class HTMLPurifier_AttrDef_Border extends HTMLPurifier_AttrDef
+class HTMLPurifier_AttrDef_CSS_Border extends HTMLPurifier_AttrDef
 {
     
     /**
@@ -13,7 +13,7 @@ class HTMLPurifier_AttrDef_Border extends HTMLPurifier_AttrDef
      */
     var $info = array();
     
-    function HTMLPurifier_AttrDef_Border($config) {
+    function HTMLPurifier_AttrDef_CSS_Border($config) {
         $def = $config->getCSSDefinition();
         $this->info['border-width'] = $def->info['border-width'];
         $this->info['border-style'] = $def->info['border-style'];

library/HTMLPurifier/AttrDef/CSS/Color.php

@@ -5,7 +5,7 @@ require_once 'HTMLPurifier/AttrDef.php';
 /**
  * Validates Color as defined by CSS.
  */
-class HTMLPurifier_AttrDef_Color extends HTMLPurifier_AttrDef
+class HTMLPurifier_AttrDef_CSS_Color extends HTMLPurifier_AttrDef
 {
     
     /**

library/HTMLPurifier/AttrDef/CSS/Composite.php

@@ -9,7 +9,7 @@
  * especially useful for CSS values, which often are a choice between
  * an enumerated set of predefined values or a flexible data type.
  */
-class HTMLPurifier_AttrDef_Composite extends HTMLPurifier_AttrDef
+class HTMLPurifier_AttrDef_CSS_Composite extends HTMLPurifier_AttrDef
 {
     
     /**
@@ -21,7 +21,7 @@ class HTMLPurifier_AttrDef_Composite extends HTMLPurifier_AttrDef
     /**
      * @param $defs List of HTMLPurifier_AttrDef objects
      */
-    function HTMLPurifier_AttrDef_Composite($defs) {
+    function HTMLPurifier_AttrDef_CSS_Composite($defs) {
         $this->defs = $defs;
     }
     

library/HTMLPurifier/AttrDef/CSS/Font.php

@@ -5,7 +5,7 @@ require_once 'HTMLPurifier/AttrDef.php';
 /**
  * Validates shorthand CSS property font.
  */
-class HTMLPurifier_AttrDef_Font extends HTMLPurifier_AttrDef
+class HTMLPurifier_AttrDef_CSS_Font extends HTMLPurifier_AttrDef
 {
     
     /**
@@ -30,7 +30,7 @@ class HTMLPurifier_AttrDef_Font extends HTMLPurifier_AttrDef
         'status-bar' => true
     );
     
-    function HTMLPurifier_AttrDef_Font($config) {
+    function HTMLPurifier_AttrDef_CSS_Font($config) {
         $def = $config->getCSSDefinition();
         $this->info['font-style']   = $def->info['font-style'];
         $this->info['font-variant'] = $def->info['font-variant'];

library/HTMLPurifier/AttrDef/CSS/FontFamily.php

@@ -7,7 +7,7 @@ require_once 'HTMLPurifier/AttrDef.php';
 /**
  * Validates a font family list according to CSS spec
  */
-class HTMLPurifier_AttrDef_FontFamily extends HTMLPurifier_AttrDef
+class HTMLPurifier_AttrDef_CSS_FontFamily extends HTMLPurifier_AttrDef
 {
     
     /**

library/HTMLPurifier/AttrDef/CSS/Length.php

@@ -1,13 +1,12 @@
 <?php
 
 require_once 'HTMLPurifier/AttrDef.php';
-require_once 'HTMLPurifier/AttrDef/Number.php';
+require_once 'HTMLPurifier/AttrDef/CSS/Number.php';
 
 /**
  * Represents a Length as defined by CSS.
- * @warning Be sure not to confuse this with HTMLPurifier_AttrDef_Length!
  */
-class HTMLPurifier_AttrDef_CSSLength extends HTMLPurifier_AttrDef
+class HTMLPurifier_AttrDef_CSS_Length extends HTMLPurifier_AttrDef
 {
     
     /**
@@ -26,8 +25,8 @@ class HTMLPurifier_AttrDef_CSSLength extends HTMLPurifier_AttrDef
      * @param $non_negative Bool indication whether or not negative values are
      *                      allowed.
      */
-    function HTMLPurifier_AttrDef_CSSLength($non_negative = false) {
-        $this->number_def = new HTMLPurifier_AttrDef_Number($non_negative);
+    function HTMLPurifier_AttrDef_CSS_Length($non_negative = false) {
+        $this->number_def = new HTMLPurifier_AttrDef_CSS_Number($non_negative);
     }
     
     function validate($length, $config, &$context) {

library/HTMLPurifier/AttrDef/CSS/ListStyle.php

@@ -6,16 +6,16 @@ require_once 'HTMLPurifier/AttrDef.php';
  * Validates shorthand CSS property list-style.
  * @warning Does not support url tokens that have internal spaces.
  */
-class HTMLPurifier_AttrDef_ListStyle extends HTMLPurifier_AttrDef
+class HTMLPurifier_AttrDef_CSS_ListStyle extends HTMLPurifier_AttrDef
 {
     
     /**
      * Local copy of component validators.
-     * @note See HTMLPurifier_AttrDef_Font::$info for a similar impl.
+     * @note See HTMLPurifier_AttrDef_CSS_Font::$info for a similar impl.
      */
     var $info;
     
-    function HTMLPurifier_AttrDef_ListStyle($config) {
+    function HTMLPurifier_AttrDef_CSS_ListStyle($config) {
         $def = $config->getCSSDefinition();
         $this->info['list-style-type']     = $def->info['list-style-type'];
         $this->info['list-style-position'] = $def->info['list-style-position'];

library/HTMLPurifier/AttrDef/CSS/Multiple.php

@@ -13,7 +13,7 @@ require_once 'HTMLPurifier/AttrDef.php';
  *       can only be used alone: it will never manifest as part of a multi
  *       shorthand declaration.  Thus, this class does not allow inherit.
  */
-class HTMLPurifier_AttrDef_Multiple extends HTMLPurifier_AttrDef
+class HTMLPurifier_AttrDef_CSS_Multiple extends HTMLPurifier_AttrDef
 {
     
     /**
@@ -30,7 +30,7 @@ class HTMLPurifier_AttrDef_Multiple extends HTMLPurifier_AttrDef
      * @param $single HTMLPurifier_AttrDef to multiply
      * @param $max Max number of values allowed (usually four)
      */
-    function HTMLPurifier_AttrDef_Multiple($single, $max = 4) {
+    function HTMLPurifier_AttrDef_CSS_Multiple($single, $max = 4) {
         $this->single = $single;
         $this->max = $max;
     }

library/HTMLPurifier/AttrDef/CSS/Number.php

@@ -3,7 +3,7 @@
 /**
  * Validates a number as defined by the CSS spec.
  */
-class HTMLPurifier_AttrDef_Number extends HTMLPurifier_AttrDef
+class HTMLPurifier_AttrDef_CSS_Number extends HTMLPurifier_AttrDef
 {
     
     /**
@@ -14,7 +14,7 @@ class HTMLPurifier_AttrDef_Number extends HTMLPurifier_AttrDef
     /**
      * @param $non_negative Bool indicating whether negatives are forbidden
      */
-    function HTMLPurifier_AttrDef_Number($non_negative = false) {
+    function HTMLPurifier_AttrDef_CSS_Number($non_negative = false) {
         $this->non_negative = $non_negative;
     }
     

library/HTMLPurifier/AttrDef/CSS/Percentage.php

@@ -1,24 +1,24 @@
 <?php
 
 require_once 'HTMLPurifier/AttrDef.php';
-require_once 'HTMLPurifier/AttrDef/Number.php';
+require_once 'HTMLPurifier/AttrDef/CSS/Number.php';
 
 /**
  * Validates a Percentage as defined by the CSS spec.
  */
-class HTMLPurifier_AttrDef_Percentage extends HTMLPurifier_AttrDef
+class HTMLPurifier_AttrDef_CSS_Percentage extends HTMLPurifier_AttrDef
 {
     
     /**
-     * Instance of HTMLPurifier_AttrDef_Number to defer number validation
+     * Instance of HTMLPurifier_AttrDef_CSS_Number to defer number validation
      */
     var $number_def;
     
     /**
      * @param Bool indicating whether to forbid negative values
      */
-    function HTMLPurifier_AttrDef_Percentage($non_negative = false) {
-        $this->number_def = new HTMLPurifier_AttrDef_Number($non_negative);
+    function HTMLPurifier_AttrDef_CSS_Percentage($non_negative = false) {
+        $this->number_def = new HTMLPurifier_AttrDef_CSS_Number($non_negative);
     }
     
     function validate($string, $config, &$context) {

library/HTMLPurifier/AttrDef/CSS/TextDecoration.php

@@ -7,7 +7,7 @@ require_once 'HTMLPurifier/AttrDef.php';
  * @note This class could be generalized into a version that acts sort of
  *       like Enum except you can compound the allowed values.
  */
-class HTMLPurifier_AttrDef_TextDecoration extends HTMLPurifier_AttrDef
+class HTMLPurifier_AttrDef_CSS_TextDecoration extends HTMLPurifier_AttrDef
 {
     
     /**

library/HTMLPurifier/AttrDef/CSS/URI.php

@@ -4,17 +4,17 @@ require_once 'HTMLPurifier/AttrDef/URI.php';
 
 /**
  * Validates a URI in CSS syntax, which uses url('http://example.com')
- * @note While theoretically speaking we a URI in a CSS document could
+ * @note While theoretically speaking a URI in a CSS document could
  *       be non-embedded, as of CSS2 there is no such usage so we're
  *       generalizing it. This may need to be changed in the future.
  * @warning Since HTMLPurifier_AttrDef_CSS blindly uses semicolons as
  *          the separator, you cannot put a literal semicolon in
  *          in the URI. Try percent encoding it, in that case.
  */
-class HTMLPurifier_AttrDef_CSSURI extends HTMLPurifier_AttrDef_URI
+class HTMLPurifier_AttrDef_CSS_URI extends HTMLPurifier_AttrDef_URI
 {
     
-    function HTMLPurifier_AttrDef_CSSURI() {
+    function HTMLPurifier_AttrDef_CSS_URI() {
         $this->HTMLPurifier_AttrDef_URI(true); // always embedded
     }
     

library/HTMLPurifier/AttrDef/Enum.php

@@ -5,6 +5,9 @@ require_once 'HTMLPurifier/AttrDef.php';
 // Enum = Enumerated
 /**
  * Validates a keyword against a list of valid values.
+ * @warning The case-insensitive compare of this function uses PHP's
+ *          built-in strtolower and ctype_lower functions, which may
+ *          cause problems with international comparisons
  */
 class HTMLPurifier_AttrDef_Enum extends HTMLPurifier_AttrDef
 {
@@ -25,8 +28,8 @@ class HTMLPurifier_AttrDef_Enum extends HTMLPurifier_AttrDef
      * @param $case_sensitive Bool indicating whether or not case sensitive
      */
     function HTMLPurifier_AttrDef_Enum(
-        $valid_values = array(), $case_sensitive = false) {
-        
+        $valid_values = array(), $case_sensitive = false
+    ) {
         $this->valid_values = array_flip($valid_values);
         $this->case_sensitive = $case_sensitive;
     }
@@ -34,6 +37,7 @@ class HTMLPurifier_AttrDef_Enum extends HTMLPurifier_AttrDef
     function validate($string, $config, &$context) {
         $string = trim($string);
         if (!$this->case_sensitive) {
+            // we may want to do full case-insensitive libraries
             $string = ctype_lower($string) ? $string : strtolower($string);
         }
         $result = isset($this->valid_values[$string]);

library/HTMLPurifier/AttrDef/HTML/FrameTarget.php

@@ -0,0 +1,34 @@
+<?php
+
+HTMLPurifier_ConfigSchema::define(
+    'Attr', 'AllowedFrameTargets', array(), 'lookup',
+    'Lookup table of all allowed link frame targets.  Some commonly used '.
+    'link targets include _blank, _self, _parent and _top. Values should '.
+    'be lowercase, as validation will be done in a case-sensitive manner '.
+    'despite W3C\'s recommendation. XHTML 1.0 Strict does not permit '.
+    'the target attribute so this directive will have no effect in that '.
+    'doctype. XHTML 1.1 does not enable the Target module by default, you '.
+    'will have to manually enable it (see the module documentation for more details.)'
+);
+
+require_once 'HTMLPurifier/AttrDef/Enum.php';
+
+/**
+ * Special-case enum attribute definition that lazy loads allowed frame targets
+ */
+class HTMLPurifier_AttrDef_HTML_FrameTarget extends HTMLPurifier_AttrDef_Enum
+{
+    
+    var $valid_values = false; // uninitialized value
+    var $case_sensitive = false;
+    
+    function HTMLPurifier_AttrDef_HTML_FrameTarget() {}
+    
+    function validate($string, $config, &$context) {
+        if ($this->valid_values === false) $this->valid_values = $config->get('Attr', 'AllowedFrameTargets');
+        return parent::validate($string, $config, $context);
+    }
+    
+}
+
+?>

library/HTMLPurifier/AttrDef/HTML/ID.php

@@ -3,6 +3,22 @@
 require_once 'HTMLPurifier/AttrDef.php';
 require_once 'HTMLPurifier/IDAccumulator.php';
 
+HTMLPurifier_ConfigSchema::define(
+    'Attr', 'EnableID', false, 'bool',
+    'Allows the ID attribute in HTML.  This is disabled by default '.
+    'due to the fact that without proper configuration user input can '.
+    'easily break the validation of a webpage by specifying an ID that is '.
+    'already on the surrounding HTML.  If you don\'t mind throwing caution to '.
+    'the wind, enable this directive, but I strongly recommend you also '.
+    'consider blacklisting IDs you use (%Attr.IDBlacklist) or prefixing all '.
+    'user supplied IDs (%Attr.IDPrefix).  This directive has been available '.
+    'since 1.2.0, and when set to true reverts to the behavior of pre-1.2.0 '.
+    'versions.'
+);
+HTMLPurifier_ConfigSchema::defineAlias(
+    'HTML', 'EnableAttrID', 'Attr', 'EnableID'
+);
+
 HTMLPurifier_ConfigSchema::define(
     'Attr', 'IDPrefix', '', 'string',
     'String to prefix to IDs.  If you have no idea what IDs your pages '.
@@ -27,6 +43,14 @@ HTMLPurifier_ConfigSchema::define(
     'is set to a non-empty value! This directive was available since 1.2.0.'
 );
 
+HTMLPurifier_ConfigSchema::define(
+    'Attr', 'IDBlacklistRegexp', null, 'string/null',
+    'PCRE regular expression to be matched against all IDs. If the expression '.
+    'is matches, the ID is rejected. Use this with care: may cause '.
+    'significant degradation. ID matching is done after all other '.
+    'validation. This directive was available since 1.6.0.'
+);
+
 /**
  * Validates the HTML attribute ID.
  * @warning Even though this is the id processor, it
@@ -36,11 +60,16 @@ HTMLPurifier_ConfigSchema::define(
  *          blacklist. If you're hacking around, make sure you use load()!
  */
 
-class HTMLPurifier_AttrDef_ID extends HTMLPurifier_AttrDef
+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
+    
     function validate($id, $config, &$context) {
         
+        if (!$config->get('Attr', 'EnableID')) return false;
+        
         $id = trim($id); // trim it first
         
         if ($id === '') return false;
@@ -55,8 +84,10 @@ class HTMLPurifier_AttrDef_ID extends HTMLPurifier_AttrDef
                 '%Attr.IDPrefix is set', E_USER_WARNING);
         }
         
-        $id_accumulator =& $context->get('IDAccumulator');
-        if (isset($id_accumulator->ids[$id])) return false;
+        //if (!$this->ref) {
+            $id_accumulator =& $context->get('IDAccumulator');
+            if (isset($id_accumulator->ids[$id])) return false;
+        //}
         
         // we purposely avoid using regex, hopefully this is faster
         
@@ -71,7 +102,12 @@ class HTMLPurifier_AttrDef_ID extends HTMLPurifier_AttrDef
             $result = ($trim === '');
         }
         
-        if ($result) $id_accumulator->add($id);
+        $regexp = $config->get('Attr', 'IDBlacklistRegexp');
+        if ($regexp && preg_match($regexp, $id)) {
+            return false;
+        }
+        
+        if (/*!$this->ref && */$result) $id_accumulator->add($id);
         
         // if no change was made to the ID, return the result
         // else, return the new id if stripping whitespace made it

library/HTMLPurifier/AttrDef/HTML/Length.php

@@ -1,18 +1,16 @@
 <?php
 
 require_once 'HTMLPurifier/AttrDef.php';
-require_once 'HTMLPurifier/AttrDef/Pixels.php';
+require_once 'HTMLPurifier/AttrDef/HTML/Pixels.php';
 
 /**
  * Validates the HTML type length (not to be confused with CSS's length).
  * 
  * This accepts integer pixels or percentages as lengths for certain
- * HTML attributes. Don't use this for CSS: that's
- * HTMLPurifier_AttrDef_CSSLength which requires prefixes and allows a lot
- * more different types.
+ * HTML attributes.
  */
 
-class HTMLPurifier_AttrDef_Length extends HTMLPurifier_AttrDef_Pixels
+class HTMLPurifier_AttrDef_HTML_Length extends HTMLPurifier_AttrDef_HTML_Pixels
 {
     
     function validate($string, $config, &$context) {

library/HTMLPurifier/AttrDef/HTML/LinkTypes.php

@@ -0,0 +1,75 @@
+<?php
+
+require_once 'HTMLPurifier/AttrDef.php';
+
+HTMLPurifier_ConfigSchema::define(
+    'Attr', 'AllowedRel', array(), 'lookup',
+    'List of allowed forward document relationships in the rel attribute. '.
+    'Common values may be nofollow or print. By default, this is empty, '.
+    'meaning that no document relationships are allowed. This directive '.
+    'was available since 1.6.0.'
+);
+
+HTMLPurifier_ConfigSchema::define(
+    'Attr', 'AllowedRev', array(), 'lookup',
+    'List of allowed reverse document relationships in the rev attribute. '.
+    'This attribute is a bit of an edge-case; if you don\'t know what it '.
+    'is for, stay away. This directive was available since 1.6.0.'
+);
+
+/**
+ * Validates a rel/rev link attribute against a directive of allowed values
+ * @note We cannot use Enum because link types allow multiple
+ *       values.
+ * @note Assumes link types are ASCII text
+ */
+class HTMLPurifier_AttrDef_HTML_LinkTypes extends HTMLPurifier_AttrDef
+{
+    
+    /** Lookup array of attribute names to configuration name */
+    var $configLookup = array(
+        'rel' => 'AllowedRel',
+        'rev' => 'AllowedRev'
+    );
+    
+    /** Name config attribute to pull. */
+    var $name;
+    
+    function HTMLPurifier_AttrDef_HTML_LinkTypes($name) {
+        if (!isset($this->configLookup[$name])) {
+            trigger_error('Unrecognized attribute name for link '.
+                'relationship.', E_USER_ERROR);
+            return;
+        }
+        $this->name = $this->configLookup[$name];
+    }
+    
+    function validate($string, $config, &$context) {
+        
+        $allowed = $config->get('Attr', $this->name);
+        if (empty($allowed)) return false;
+        
+        $string = $this->parseCDATA($string);
+        $parts = explode(' ', $string);
+        
+        // lookup to prevent duplicates
+        $ret_lookup = array();
+        foreach ($parts as $part) {
+            $part = strtolower(trim($part));
+            if (!isset($allowed[$part])) continue;
+            $ret_lookup[$part] = true;
+        }
+        
+        if (empty($ret_lookup)) return false;
+        
+        $ret_array = array();
+        foreach ($ret_lookup as $part => $bool) $ret_array[] = $part;
+        $string = implode(' ', $ret_array);
+        
+        return $string;
+        
+    }
+    
+}
+
+?>

library/HTMLPurifier/AttrDef/HTML/MultiLength.php

@@ -1,7 +1,7 @@
 <?php
 
 require_once 'HTMLPurifier/AttrDef.php';
-require_once 'HTMLPurifier/AttrDef/Length.php';
+require_once 'HTMLPurifier/AttrDef/HTML/Length.php';
 
 /**
  * Validates a MultiLength as defined by the HTML spec.
@@ -9,7 +9,7 @@ require_once 'HTMLPurifier/AttrDef/Length.php';
  * A multilength is either a integer (pixel count), a percentage, or
  * a relative number.
  */
-class HTMLPurifier_AttrDef_MultiLength extends HTMLPurifier_AttrDef_Length
+class HTMLPurifier_AttrDef_HTML_MultiLength extends HTMLPurifier_AttrDef_HTML_Length
 {
     
     function validate($string, $config, &$context) {
@@ -27,12 +27,14 @@ class HTMLPurifier_AttrDef_MultiLength extends HTMLPurifier_AttrDef_Length
         
         $int = substr($string, 0, $length - 1);
         
+        if ($int == '') return '*';
         if (!is_numeric($int)) return false;
         
         $int = (int) $int;
         
-        if ($int < 0) return '0*';
-        
+        if ($int < 0) return false;
+        if ($int == 0) return '0';
+        if ($int == 1) return '*';
         return ((string) $int) . '*';
         
     }

library/HTMLPurifier/AttrDef/HTML/Nmtokens.php

@@ -4,9 +4,13 @@ require_once 'HTMLPurifier/AttrDef.php';
 require_once 'HTMLPurifier/Config.php';
 
 /**
- * Validates the contents of the global HTML attribute class.
+ * 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_Class extends HTMLPurifier_AttrDef
+class HTMLPurifier_AttrDef_HTML_Nmtokens extends HTMLPurifier_AttrDef
 {
     
     function validate($string, $config, &$context) {
@@ -31,10 +35,10 @@ class HTMLPurifier_AttrDef_Class extends HTMLPurifier_AttrDef
         
         if (empty($matches[1])) return false;
         
-        // reconstruct class string
+        // reconstruct string
         $new_string = '';
-        foreach ($matches[1] as $class_names) {
-            $new_string .= $class_names . ' ';
+        foreach ($matches[1] as $token) {
+            $new_string .= $token . ' ';
         }
         $new_string = rtrim($new_string);
         

library/HTMLPurifier/AttrDef/HTML/Pixels.php

@@ -5,7 +5,7 @@ require_once 'HTMLPurifier/AttrDef.php';
 /**
  * Validates an integer representation of pixels according to the HTML spec.
  */
-class HTMLPurifier_AttrDef_Pixels extends HTMLPurifier_AttrDef
+class HTMLPurifier_AttrDef_HTML_Pixels extends HTMLPurifier_AttrDef
 {
     
     function validate($string, $config, &$context) {

library/HTMLPurifier/AttrDef/Lang.php

@@ -46,7 +46,7 @@ class HTMLPurifier_AttrDef_Lang extends HTMLPurifier_AttrDef
         
         // process second subtag : $subtags[1]
         $length = strlen($subtags[1]);
-        if ($length == 0 || $length == 1 || $length > 8 || !ctype_alnum($subtags[1])) {
+        if ($length == 0 || ($length == 1 && $subtags[1] != 'x') || $length > 8 || !ctype_alnum($subtags[1])) {
             return $new_string;
         }
         if (!ctype_lower($subtags[1])) $subtags[1] = strtolower($subtags[1]);

library/HTMLPurifier/AttrDef/URI.php

@@ -3,7 +3,7 @@
 require_once 'HTMLPurifier/AttrDef.php';
 require_once 'HTMLPurifier/URIScheme.php';
 require_once 'HTMLPurifier/URISchemeRegistry.php';
-require_once 'HTMLPurifier/AttrDef/Host.php';
+require_once 'HTMLPurifier/AttrDef/URI/Host.php';
 require_once 'HTMLPurifier/PercentEncoder.php';
 
 HTMLPurifier_ConfigSchema::define(
@@ -77,6 +77,14 @@ HTMLPurifier_ConfigSchema::define(
     'This directive has been available since 1.3.0.'
 );
 
+HTMLPurifier_ConfigSchema::define(
+    'URI', 'Disable', false, 'bool',
+    'Disables all URIs in all forms. Not sure why you\'d want to do that '.
+    '(after all, the Internet\'s founded on the notion of a hyperlink). '.
+    'This directive has been available since 1.3.0.'
+);
+HTMLPurifier_ConfigSchema::defineAlias('Attr', 'DisableURI', 'URI', 'Disable');
+
 /**
  * Validates a URI as defined by RFC 3986.
  * @note Scheme-specific mechanics deferred to HTMLPurifier_URIScheme
@@ -92,7 +100,7 @@ class HTMLPurifier_AttrDef_URI extends HTMLPurifier_AttrDef
      * @param $embeds_resource_resource Does the URI here result in an extra HTTP request?
      */
     function HTMLPurifier_AttrDef_URI($embeds_resource = false) {
-        $this->host = new HTMLPurifier_AttrDef_Host();
+        $this->host = new HTMLPurifier_AttrDef_URI_Host();
         $this->PercentEncoder = new HTMLPurifier_PercentEncoder();
         $this->embeds_resource = (bool) $embeds_resource;
     }
@@ -102,6 +110,8 @@ class HTMLPurifier_AttrDef_URI extends HTMLPurifier_AttrDef
         // We'll write stack-based parsers later, for now, use regexps to
         // get things working as fast as possible (irony)
         
+        if ($config->get('URI', 'Disable')) return false;
+        
         // parse as CDATA
         $uri = $this->parseCDATA($uri);
         

library/HTMLPurifier/AttrDef/URI/Email.php

@@ -2,7 +2,7 @@
 
 require_once 'HTMLPurifier/AttrDef.php';
 
-class HTMLPurifier_AttrDef_Email extends HTMLPurifier_AttrDef
+class HTMLPurifier_AttrDef_URI_Email extends HTMLPurifier_AttrDef
 {
     
     /**

library/HTMLPurifier/AttrDef/URI/Email/SimpleCheck.php

@@ -1,12 +1,12 @@
 <?php
 
-require_once 'HTMLPurifier/AttrDef/Email.php';
+require_once 'HTMLPurifier/AttrDef/URI/Email.php';
 
 /**
  * Primitive email validation class based on the regexp found at 
  * http://www.regular-expressions.info/email.html
  */
-class HTMLPurifier_AttrDef_Email_SimpleCheck extends HTMLPurifier_AttrDef_Email
+class HTMLPurifier_AttrDef_URI_Email_SimpleCheck extends HTMLPurifier_AttrDef_URI_Email
 {
     
     function validate($string, $config, &$context) {

library/HTMLPurifier/AttrDef/URI/Host.php

@@ -1,28 +1,28 @@
 <?php
 
 require_once 'HTMLPurifier/AttrDef.php';
-require_once 'HTMLPurifier/AttrDef/IPv4.php';
-require_once 'HTMLPurifier/AttrDef/IPv6.php';
+require_once 'HTMLPurifier/AttrDef/URI/IPv4.php';
+require_once 'HTMLPurifier/AttrDef/URI/IPv6.php';
 
 /**
  * Validates a host according to the IPv4, IPv6 and DNS (future) specifications.
  */
-class HTMLPurifier_AttrDef_Host extends HTMLPurifier_AttrDef
+class HTMLPurifier_AttrDef_URI_Host extends HTMLPurifier_AttrDef
 {
     
     /**
-     * Instance of HTMLPurifier_AttrDef_IPv4 sub-validator
+     * Instance of HTMLPurifier_AttrDef_URI_IPv4 sub-validator
      */
     var $ipv4;
     
     /**
-     * Instance of HTMLPurifier_AttrDef_IPv6 sub-validator
+     * Instance of HTMLPurifier_AttrDef_URI_IPv6 sub-validator
      */
     var $ipv6;
     
-    function HTMLPurifier_AttrDef_Host() {
-        $this->ipv4 = new HTMLPurifier_AttrDef_IPv4();
-        $this->ipv6 = new HTMLPurifier_AttrDef_IPv6();
+    function HTMLPurifier_AttrDef_URI_Host() {
+        $this->ipv4 = new HTMLPurifier_AttrDef_URI_IPv4();
+        $this->ipv6 = new HTMLPurifier_AttrDef_URI_IPv6();
     }
     
     function validate($string, $config, &$context) {

library/HTMLPurifier/AttrDef/URI/IPv4.php

@@ -6,7 +6,7 @@ require_once 'HTMLPurifier/AttrDef.php';
  * Validates an IPv4 address
  * @author Feyd @ forums.devnetwork.net (public domain)
  */
-class HTMLPurifier_AttrDef_IPv4 extends HTMLPurifier_AttrDef
+class HTMLPurifier_AttrDef_URI_IPv4 extends HTMLPurifier_AttrDef
 {
     
     /**
@@ -15,7 +15,7 @@ class HTMLPurifier_AttrDef_IPv4 extends HTMLPurifier_AttrDef
      */
     var $ip4;
     
-    function HTMLPurifier_AttrDef_IPv4() {
+    function HTMLPurifier_AttrDef_URI_IPv4() {
         $oct = '(?:25[0-5]|2[0-4][0-9]|1[0-9]{2}|[1-9][0-9]|[0-9])'; // 0-255
         $this->ip4 = "(?:{$oct}\\.{$oct}\\.{$oct}\\.{$oct})";
     }

library/HTMLPurifier/AttrDef/URI/IPv6.php

@@ -1,6 +1,6 @@
 <?php
 
-require_once 'HTMLPurifier/AttrDef/IPv4.php';
+require_once 'HTMLPurifier/AttrDef/URI/IPv4.php';
 
 /**
  * Validates an IPv6 address.
@@ -8,7 +8,7 @@ require_once 'HTMLPurifier/AttrDef/IPv4.php';
  * @note This function requires brackets to have been removed from address
  *       in URI.
  */
-class HTMLPurifier_AttrDef_IPv6 extends HTMLPurifier_AttrDef_IPv4
+class HTMLPurifier_AttrDef_URI_IPv6 extends HTMLPurifier_AttrDef_URI_IPv4
 {
     
     function validate($aIP, $config, &$context) {

library/HTMLPurifier/AttrTransform.php

@@ -29,6 +29,30 @@ class HTMLPurifier_AttrTransform
     function transform($attr, $config, &$context) {
         trigger_error('Cannot call abstract function', E_USER_ERROR);
     }
+    
+    /**
+     * Prepends CSS properties to the style attribute, creating the
+     * attribute if it doesn't exist.
+     * @param $attr Attribute array to process (passed by reference)
+     * @param $css CSS to prepend
+     */
+    function prependCSS(&$attr, $css) {
+        $attr['style'] = isset($attr['style']) ? $attr['style'] : '';
+        $attr['style'] = $css . $attr['style'];
+    }
+    
+    /**
+     * Retrieves and removes an attribute
+     * @param $attr Attribute array to process (passed by reference)
+     * @param $key Key of attribute to confiscate
+     */
+    function confiscateAttr(&$attr, $key) {
+        if (!isset($attr[$key])) return null;
+        $value = $attr[$key];
+        unset($attr[$key]);
+        return $value;
+    }
+    
 }
 
 ?>

library/HTMLPurifier/AttrTransform/BgColor.php

@@ -0,0 +1,26 @@
+<?php
+
+require_once 'HTMLPurifier/AttrTransform.php';
+
+/**
+ * Pre-transform that changes deprecated bgcolor attribute to CSS.
+ */
+class HTMLPurifier_AttrTransform_BgColor
+extends HTMLPurifier_AttrTransform {
+
+    function transform($attr, $config, &$context) {
+        
+        if (!isset($attr['bgcolor'])) return $attr;
+        
+        $bgcolor = $this->confiscateAttr($attr, 'bgcolor');
+        // some validation should happen here
+        
+        $this->prependCSS($attr, "background-color:$bgcolor;");
+        
+        return $attr;
+        
+    }
+    
+}
+
+?>

library/HTMLPurifier/AttrTransform/BoolToCSS.php

@@ -0,0 +1,39 @@
+<?php
+
+require_once 'HTMLPurifier/AttrTransform.php';
+
+/**
+ * Pre-transform that changes converts a boolean attribute to fixed CSS
+ */
+class HTMLPurifier_AttrTransform_BoolToCSS
+extends HTMLPurifier_AttrTransform {
+    
+    /**
+     * Name of boolean attribute that is trigger
+     */
+    var $attr;
+    
+    /**
+     * CSS declarations to add to style, needs trailing semicolon
+     */
+    var $css;
+    
+    /**
+     * @param $attr string attribute name to convert from
+     * @param $css string CSS declarations to add to style (needs semicolon)
+     */
+    function HTMLPurifier_AttrTransform_BoolToCSS($attr, $css) {
+        $this->attr = $attr;
+        $this->css  = $css;
+    }
+    
+    function transform($attr, $config, &$context) {
+        if (!isset($attr[$this->attr])) return $attr;
+        unset($attr[$this->attr]);
+        $this->prependCSS($attr, $this->css);
+        return $attr;
+    }
+    
+}
+
+?>

library/HTMLPurifier/AttrTransform/Border.php

@@ -0,0 +1,20 @@
+<?php
+
+require_once 'HTMLPurifier/AttrTransform.php';
+
+/**
+ * Pre-transform that changes deprecated border attribute to CSS.
+ */
+class HTMLPurifier_AttrTransform_Border extends HTMLPurifier_AttrTransform {
+
+    function transform($attr, $config, &$context) {
+        if (!isset($attr['border'])) return $attr;
+        $border_width = $this->confiscateAttr($attr, 'border');
+        // some validation should happen here
+        $this->prependCSS($attr, "border:{$border_width}px solid;");
+        return $attr;
+    }
+    
+}
+
+?>

library/HTMLPurifier/AttrTransform/EnumToCSS.php

@@ -0,0 +1,60 @@
+<?php
+
+require_once 'HTMLPurifier/AttrTransform.php';
+
+/**
+ * Generic pre-transform that converts an attribute with a fixed number of
+ * values (enumerated) to CSS.
+ */
+class HTMLPurifier_AttrTransform_EnumToCSS extends HTMLPurifier_AttrTransform {
+    
+    /**
+     * Name of attribute to transform from
+     */
+    var $attr;
+    
+    /**
+     * Lookup array of attribute values to CSS
+     */
+    var $enumToCSS = array();
+    
+    /**
+     * Case sensitivity of the matching
+     * @warning Currently can only be guaranteed to work with ASCII
+     *          values.
+     */
+    var $caseSensitive = false;
+    
+    /**
+     * @param $attr String attribute name to transform from
+     * @param $enumToCSS Lookup array of attribute values to CSS
+     * @param $case_sensitive Boolean case sensitivity indicator, default false
+     */
+    function HTMLPurifier_AttrTransform_EnumToCSS($attr, $enum_to_css, $case_sensitive = false) {
+        $this->attr = $attr;
+        $this->enumToCSS = $enum_to_css;
+        $this->caseSensitive = (bool) $case_sensitive;
+    }
+    
+    function transform($attr, $config, &$context) {
+        
+        if (!isset($attr[$this->attr])) return $attr;
+        
+        $value = trim($attr[$this->attr]);
+        unset($attr[$this->attr]);
+        
+        if (!$this->caseSensitive) $value = strtolower($value);
+        
+        if (!isset($this->enumToCSS[$value])) {
+            return $attr;
+        }
+        
+        $this->prependCSS($attr, $this->enumToCSS[$value]);
+        
+        return $attr;
+        
+    }
+    
+}
+
+?>

library/HTMLPurifier/AttrTransform/ImgSpace.php

@@ -0,0 +1,47 @@
+<?php
+
+require_once 'HTMLPurifier/AttrTransform.php';
+
+/**
+ * Pre-transform that changes deprecated hspace and vspace attributes to CSS
+ */
+class HTMLPurifier_AttrTransform_ImgSpace
+extends HTMLPurifier_AttrTransform {
+    
+    var $attr;
+    var $css = array(
+        'hspace' => array('left', 'right'),
+        'vspace' => array('top', 'bottom')
+    );
+    
+    function HTMLPurifier_AttrTransform_ImgSpace($attr) {
+        $this->attr = $attr;
+        if (!isset($this->css[$attr])) {
+            trigger_error(htmlspecialchars($attr) . ' is not valid space attribute');
+        }
+    }
+    
+    function transform($attr, $config, &$context) {
+        
+        if (!isset($attr[$this->attr])) return $attr;
+        
+        $width = $this->confiscateAttr($attr, $this->attr);
+        // some validation could happen here
+        
+        if (!isset($this->css[$this->attr])) return $attr;
+        
+        $style = '';
+        foreach ($this->css[$this->attr] as $suffix) {
+            $property = "margin-$suffix";
+            $style .= "$property:{$width}px;";
+        }
+        
+        $this->prependCSS($attr, $style);
+        
+        return $attr;
+        
+    }
+    
+}
+
+?>

library/HTMLPurifier/AttrTransform/Length.php

@@ -0,0 +1,29 @@
+<?php
+
+require_once 'HTMLPurifier/AttrTransform.php';
+
+/**
+ * Class for handling width/height length attribute transformations to CSS
+ */
+class HTMLPurifier_AttrTransform_Length extends HTMLPurifier_AttrTransform
+{
+    
+    var $name;
+    var $cssName;
+    
+    function HTMLPurifier_AttrTransform_Length($name, $css_name = null) {
+        $this->name = $name;
+        $this->cssName = $css_name ? $css_name : $name;
+    }
+    
+    function transform($attr, $config, &$context) {
+        if (!isset($attr[$this->name])) return $attr;
+        $length = $this->confiscateAttr($attr, $this->name);
+        if(ctype_digit($length)) $length .= 'px';
+        $this->prependCSS($attr, $this->cssName . ":$length;");
+        return $attr;
+    }
+    
+}
+
+?>

library/HTMLPurifier/AttrTransform/Name.php

@@ -0,0 +1,21 @@
+<?php
+
+require_once 'HTMLPurifier/AttrTransform.php';
+
+/**
+ * Pre-transform that changes deprecated name attribute to ID if necessary
+ */
+class HTMLPurifier_AttrTransform_Name extends HTMLPurifier_AttrTransform
+{
+    
+    function transform($attr, $config, &$context) {
+        if (!isset($attr['name'])) return $attr;
+        $id = $this->confiscateAttr($attr, 'name');
+        if ( isset($attr['id']))   return $attr;
+        $attr['id'] = $id;
+        return $attr;
+    }
+    
+}
+
+?>

library/HTMLPurifier/AttrTransform/TextAlign.php

@@ -1,36 +0,0 @@
-<?php
-
-require_once 'HTMLPurifier/AttrTransform.php';
-
-/**
- * Pre-transform that changes deprecated align attribute to text-align.
- */
-class HTMLPurifier_AttrTransform_TextAlign
-    extends HTMLPurifier_AttrTransform {
-
-    function transform($attr, $config, &$context) {
-        
-        if (!isset($attr['align'])) return $attr;
-        
-        $align = strtolower(trim($attr['align']));
-        unset($attr['align']);
-        
-        $values = array('left' => 1,
-                        'right' => 1,
-                        'center' => 1,
-                        'justify' => 1);
-        
-        if (!isset($values[$align])) {
-            return $attr;
-        }
-        
-        $attr['style'] = isset($attr['style']) ? $attr['style'] : '';
-        $attr['style'] = "text-align:$align;" . $attr['style'];
-        
-        return $attr;
-        
-    }
-    
-}
-
-?>

library/HTMLPurifier/AttrTypes.php

@@ -0,0 +1,41 @@
+<?php
+
+require_once 'HTMLPurifier/AttrDef/HTML/ID.php';
+require_once 'HTMLPurifier/AttrDef/HTML/Length.php';
+require_once 'HTMLPurifier/AttrDef/HTML/MultiLength.php';
+require_once 'HTMLPurifier/AttrDef/HTML/Nmtokens.php';
+require_once 'HTMLPurifier/AttrDef/HTML/Pixels.php';
+require_once 'HTMLPurifier/AttrDef/Integer.php';
+require_once 'HTMLPurifier/AttrDef/Text.php';
+require_once 'HTMLPurifier/AttrDef/URI.php';
+
+/**
+ * Provides lookup array of attribute types to HTMLPurifier_AttrDef objects
+ */
+class HTMLPurifier_AttrTypes
+{
+    /**
+     * Lookup array of attribute string identifiers to concrete implementations
+     * @public
+     */
+    var $info = array();
+    
+    /**
+     * Constructs the info array
+     */
+    function HTMLPurifier_AttrTypes() {
+        $this->info['CDATA']    = new HTMLPurifier_AttrDef_Text();
+        $this->info['ID']       = new HTMLPurifier_AttrDef_HTML_ID();
+        $this->info['Length']   = new HTMLPurifier_AttrDef_HTML_Length();
+        $this->info['MultiLength'] = new HTMLPurifier_AttrDef_HTML_MultiLength();
+        $this->info['NMTOKENS'] = new HTMLPurifier_AttrDef_HTML_Nmtokens();
+        $this->info['Pixels']   = new HTMLPurifier_AttrDef_HTML_Pixels();
+        $this->info['Text']     = new HTMLPurifier_AttrDef_Text();
+        $this->info['URI']      = new HTMLPurifier_AttrDef_URI();
+        
+        // number is really a positive integer (one or more digits)
+        $this->info['Number']   = new HTMLPurifier_AttrDef_Integer(false, false, true);
+    }
+}
+
+?>

library/HTMLPurifier/CSSDefinition.php

@@ -1,19 +1,19 @@
 <?php
 
+require_once 'HTMLPurifier/AttrDef/CSS/Background.php';
+require_once 'HTMLPurifier/AttrDef/CSS/BackgroundPosition.php';
+require_once 'HTMLPurifier/AttrDef/CSS/Border.php';
+require_once 'HTMLPurifier/AttrDef/CSS/Color.php';
+require_once 'HTMLPurifier/AttrDef/CSS/Composite.php';
+require_once 'HTMLPurifier/AttrDef/CSS/Font.php';
+require_once 'HTMLPurifier/AttrDef/CSS/FontFamily.php';
+require_once 'HTMLPurifier/AttrDef/CSS/Length.php';
+require_once 'HTMLPurifier/AttrDef/CSS/ListStyle.php';
+require_once 'HTMLPurifier/AttrDef/CSS/Multiple.php';
+require_once 'HTMLPurifier/AttrDef/CSS/Percentage.php';
+require_once 'HTMLPurifier/AttrDef/CSS/TextDecoration.php';
+require_once 'HTMLPurifier/AttrDef/CSS/URI.php';
 require_once 'HTMLPurifier/AttrDef/Enum.php';
-require_once 'HTMLPurifier/AttrDef/Color.php';
-require_once 'HTMLPurifier/AttrDef/Composite.php';
-require_once 'HTMLPurifier/AttrDef/CSSLength.php';
-require_once 'HTMLPurifier/AttrDef/Percentage.php';
-require_once 'HTMLPurifier/AttrDef/Multiple.php';
-require_once 'HTMLPurifier/AttrDef/TextDecoration.php';
-require_once 'HTMLPurifier/AttrDef/FontFamily.php';
-require_once 'HTMLPurifier/AttrDef/Font.php';
-require_once 'HTMLPurifier/AttrDef/Border.php';
-require_once 'HTMLPurifier/AttrDef/ListStyle.php';
-require_once 'HTMLPurifier/AttrDef/CSSURI.php';
-require_once 'HTMLPurifier/AttrDef/BackgroundPosition.php';
-require_once 'HTMLPurifier/AttrDef/Background.php';
 
 /**
  * Defines allowed CSS attributes and what their values are.
@@ -43,7 +43,7 @@ class HTMLPurifier_CSSDefinition
             array('none', 'hidden', 'dotted', 'dashed', 'solid', 'double',
             'groove', 'ridge', 'inset', 'outset'), false);
         
-        $this->info['border-style'] = new HTMLPurifier_AttrDef_Multiple($border_style);
+        $this->info['border-style'] = new HTMLPurifier_AttrDef_CSS_Multiple($border_style);
         
         $this->info['clear'] = new HTMLPurifier_AttrDef_Enum(
             array('none', 'left', 'right', 'both'), false);
@@ -54,10 +54,10 @@ class HTMLPurifier_CSSDefinition
         $this->info['font-variant'] = new HTMLPurifier_AttrDef_Enum(
             array('normal', 'small-caps'), false);
         
-        $uri_or_none = new HTMLPurifier_AttrDef_Composite(
+        $uri_or_none = new HTMLPurifier_AttrDef_CSS_Composite(
             array(
                 new HTMLPurifier_AttrDef_Enum(array('none')),
-                new HTMLPurifier_AttrDef_CSSURI()
+                new HTMLPurifier_AttrDef_CSS_URI()
             )
         );
         
@@ -68,11 +68,11 @@ class HTMLPurifier_CSSDefinition
             'upper-roman', 'lower-alpha', 'upper-alpha', 'none'), false);
         $this->info['list-style-image'] = $uri_or_none;
         
-        $this->info['list-style'] = new HTMLPurifier_AttrDef_ListStyle($config);
+        $this->info['list-style'] = new HTMLPurifier_AttrDef_CSS_ListStyle($config);
         
         $this->info['text-transform'] = new HTMLPurifier_AttrDef_Enum(
             array('capitalize', 'uppercase', 'lowercase', 'none'), false);
-        $this->info['color'] = new HTMLPurifier_AttrDef_Color();
+        $this->info['color'] = new HTMLPurifier_AttrDef_CSS_Color();
         
         $this->info['background-image'] = $uri_or_none;
         $this->info['background-repeat'] = new HTMLPurifier_AttrDef_Enum(
@@ -81,96 +81,98 @@ class HTMLPurifier_CSSDefinition
         $this->info['background-attachment'] = new HTMLPurifier_AttrDef_Enum(
             array('scroll', 'fixed')
         );
-        $this->info['background-position'] = new HTMLPurifier_AttrDef_BackgroundPosition();
+        $this->info['background-position'] = new HTMLPurifier_AttrDef_CSS_BackgroundPosition();
         
         $border_color = 
         $this->info['border-top-color'] = 
         $this->info['border-bottom-color'] = 
         $this->info['border-left-color'] = 
         $this->info['border-right-color'] = 
-        $this->info['background-color'] = new HTMLPurifier_AttrDef_Composite(array(
+        $this->info['background-color'] = new HTMLPurifier_AttrDef_CSS_Composite(array(
             new HTMLPurifier_AttrDef_Enum(array('transparent')),
-            new HTMLPurifier_AttrDef_Color()
+            new HTMLPurifier_AttrDef_CSS_Color()
         ));
         
-        $this->info['background'] = new HTMLPurifier_AttrDef_Background($config);
+        $this->info['background'] = new HTMLPurifier_AttrDef_CSS_Background($config);
         
-        $this->info['border-color'] = new HTMLPurifier_AttrDef_Multiple($border_color);
+        $this->info['border-color'] = new HTMLPurifier_AttrDef_CSS_Multiple($border_color);
         
         $border_width = 
         $this->info['border-top-width'] = 
         $this->info['border-bottom-width'] = 
         $this->info['border-left-width'] = 
-        $this->info['border-right-width'] = new HTMLPurifier_AttrDef_Composite(array(
+        $this->info['border-right-width'] = new HTMLPurifier_AttrDef_CSS_Composite(array(
             new HTMLPurifier_AttrDef_Enum(array('thin', 'medium', 'thick')),
-            new HTMLPurifier_AttrDef_CSSLength(true) //disallow negative
+            new HTMLPurifier_AttrDef_CSS_Length(true) //disallow negative
         ));
         
-        $this->info['border-width'] = new HTMLPurifier_AttrDef_Multiple($border_width);
+        $this->info['border-width'] = new HTMLPurifier_AttrDef_CSS_Multiple($border_width);
         
-        $this->info['letter-spacing'] = new HTMLPurifier_AttrDef_Composite(array(
+        $this->info['letter-spacing'] = new HTMLPurifier_AttrDef_CSS_Composite(array(
             new HTMLPurifier_AttrDef_Enum(array('normal')),
-            new HTMLPurifier_AttrDef_CSSLength()
+            new HTMLPurifier_AttrDef_CSS_Length()
         ));
         
-        $this->info['word-spacing'] = new HTMLPurifier_AttrDef_Composite(array(
+        $this->info['word-spacing'] = new HTMLPurifier_AttrDef_CSS_Composite(array(
             new HTMLPurifier_AttrDef_Enum(array('normal')),
-            new HTMLPurifier_AttrDef_CSSLength()
+            new HTMLPurifier_AttrDef_CSS_Length()
         ));
         
-        $this->info['font-size'] = new HTMLPurifier_AttrDef_Composite(array(
+        $this->info['font-size'] = new HTMLPurifier_AttrDef_CSS_Composite(array(
             new HTMLPurifier_AttrDef_Enum(array('xx-small', 'x-small',
                 'small', 'medium', 'large', 'x-large', 'xx-large',
                 'larger', 'smaller')),
-            new HTMLPurifier_AttrDef_Percentage(),
-            new HTMLPurifier_AttrDef_CSSLength()
+            new HTMLPurifier_AttrDef_CSS_Percentage(),
+            new HTMLPurifier_AttrDef_CSS_Length()
         ));
         
-        $this->info['line-height'] = new HTMLPurifier_AttrDef_Composite(array(
+        $this->info['line-height'] = new HTMLPurifier_AttrDef_CSS_Composite(array(
             new HTMLPurifier_AttrDef_Enum(array('normal')),
-            new HTMLPurifier_AttrDef_Number(true), // no negatives
-            new HTMLPurifier_AttrDef_CSSLength(true),
-            new HTMLPurifier_AttrDef_Percentage(true)
+            new HTMLPurifier_AttrDef_CSS_Number(true), // no negatives
+            new HTMLPurifier_AttrDef_CSS_Length(true),
+            new HTMLPurifier_AttrDef_CSS_Percentage(true)
         ));
         
         $margin =
         $this->info['margin-top'] = 
         $this->info['margin-bottom'] = 
         $this->info['margin-left'] = 
-        $this->info['margin-right'] = new HTMLPurifier_AttrDef_Composite(array(
-            new HTMLPurifier_AttrDef_CSSLength(),
-            new HTMLPurifier_AttrDef_Percentage(),
+        $this->info['margin-right'] = new HTMLPurifier_AttrDef_CSS_Composite(array(
+            new HTMLPurifier_AttrDef_CSS_Length(),
+            new HTMLPurifier_AttrDef_CSS_Percentage(),
             new HTMLPurifier_AttrDef_Enum(array('auto'))
         ));
         
-        $this->info['margin'] = new HTMLPurifier_AttrDef_Multiple($margin);
+        $this->info['margin'] = new HTMLPurifier_AttrDef_CSS_Multiple($margin);
         
         // non-negative
         $padding =
         $this->info['padding-top'] = 
         $this->info['padding-bottom'] = 
         $this->info['padding-left'] = 
-        $this->info['padding-right'] = new HTMLPurifier_AttrDef_Composite(array(
-            new HTMLPurifier_AttrDef_CSSLength(true),
-            new HTMLPurifier_AttrDef_Percentage(true)
+        $this->info['padding-right'] = new HTMLPurifier_AttrDef_CSS_Composite(array(
+            new HTMLPurifier_AttrDef_CSS_Length(true),
+            new HTMLPurifier_AttrDef_CSS_Percentage(true)
         ));
         
-        $this->info['padding'] = new HTMLPurifier_AttrDef_Multiple($padding);
+        $this->info['padding'] = new HTMLPurifier_AttrDef_CSS_Multiple($padding);
         
-        $this->info['text-indent'] = new HTMLPurifier_AttrDef_Composite(array(
-            new HTMLPurifier_AttrDef_CSSLength(),
-            new HTMLPurifier_AttrDef_Percentage()
+        $this->info['text-indent'] = new HTMLPurifier_AttrDef_CSS_Composite(array(
+            new HTMLPurifier_AttrDef_CSS_Length(),
+            new HTMLPurifier_AttrDef_CSS_Percentage()
         ));
         
-        $this->info['width'] = new HTMLPurifier_AttrDef_Composite(array(
-            new HTMLPurifier_AttrDef_CSSLength(true),
-            new HTMLPurifier_AttrDef_Percentage(true),
+        $this->info['width'] =
+        $this->info['height'] = 
+        new HTMLPurifier_AttrDef_CSS_Composite(array(
+            new HTMLPurifier_AttrDef_CSS_Length(true),
+            new HTMLPurifier_AttrDef_CSS_Percentage(true),
             new HTMLPurifier_AttrDef_Enum(array('auto'))
         ));
         
-        $this->info['text-decoration'] = new HTMLPurifier_AttrDef_TextDecoration();
+        $this->info['text-decoration'] = new HTMLPurifier_AttrDef_CSS_TextDecoration();
         
-        $this->info['font-family'] = new HTMLPurifier_AttrDef_FontFamily();
+        $this->info['font-family'] = new HTMLPurifier_AttrDef_CSS_FontFamily();
         
         // this could use specialized code
         $this->info['font-weight'] = new HTMLPurifier_AttrDef_Enum(
@@ -179,14 +181,14 @@ class HTMLPurifier_CSSDefinition
         
         // MUST be called after other font properties, as it references
         // a CSSDefinition object
-        $this->info['font'] = new HTMLPurifier_AttrDef_Font($config);
+        $this->info['font'] = new HTMLPurifier_AttrDef_CSS_Font($config);
         
         // same here
         $this->info['border'] =
         $this->info['border-bottom'] = 
         $this->info['border-top'] = 
         $this->info['border-left'] = 
-        $this->info['border-right'] = new HTMLPurifier_AttrDef_Border($config);
+        $this->info['border-right'] = new HTMLPurifier_AttrDef_CSS_Border($config);
         
         $this->info['border-collapse'] = new HTMLPurifier_AttrDef_Enum(array(
             'collapse', 'seperate'));
@@ -197,13 +199,16 @@ class HTMLPurifier_CSSDefinition
         $this->info['table-layout'] = new HTMLPurifier_AttrDef_Enum(array(
             'auto', 'fixed'));
         
-        $this->info['vertical-align'] = new HTMLPurifier_AttrDef_Composite(array(
+        $this->info['vertical-align'] = new HTMLPurifier_AttrDef_CSS_Composite(array(
             new HTMLPurifier_AttrDef_Enum(array('baseline', 'sub', 'super',
                 'top', 'text-top', 'middle', 'bottom', 'text-bottom')),
-            new HTMLPurifier_AttrDef_CSSLength(),
-            new HTMLPurifier_AttrDef_Percentage()
+            new HTMLPurifier_AttrDef_CSS_Length(),
+            new HTMLPurifier_AttrDef_CSS_Percentage()
         ));
         
+        // partial support
+        $this->info['white-space'] = new HTMLPurifier_AttrDef_Enum(array('nowrap'));
+        
     }
     
 }

library/HTMLPurifier/ChildDef/Chameleon.php

@@ -38,22 +38,13 @@ class HTMLPurifier_ChildDef_Chameleon extends HTMLPurifier_ChildDef
     }
     
     function validateChildren($tokens_of_children, $config, &$context) {
-        $parent_type = $context->get('ParentType');
-        switch ($parent_type) {
-            case 'unknown':
-            case 'inline':
-                $result = $this->inline->validateChildren(
-                    $tokens_of_children, $config, $context);
-                break;
-            case 'block':
-                $result = $this->block->validateChildren(
-                    $tokens_of_children, $config, $context);
-                break;
-            default:
-                trigger_error('Invalid context', E_USER_ERROR);
-                return false;
+        if ($context->get('IsInline') === false) {
+            return $this->block->validateChildren(
+                $tokens_of_children, $config, $context);
+        } else {
+            return $this->inline->validateChildren(
+                $tokens_of_children, $config, $context);
         }
-        return $result;
     }
 }
 

library/HTMLPurifier/ChildDef/Required.php

@@ -20,10 +20,13 @@ class HTMLPurifier_ChildDef_Required extends HTMLPurifier_ChildDef
             $elements = str_replace(' ', '', $elements);
             $elements = explode('|', $elements);
         }
-        $elements = array_flip($elements);
-        foreach ($elements as $i => $x) {
-            $elements[$i] = true;
-            if (empty($i)) unset($elements[$i]);
+        $keys = array_keys($elements);
+        if ($keys == array_keys($keys)) {
+            $elements = array_flip($elements);
+            foreach ($elements as $i => $x) {
+                $elements[$i] = true;
+                if (empty($i)) unset($elements[$i]);
+            }
         }
         $this->elements = $elements;
         $this->gen = new HTMLPurifier_Generator();

library/HTMLPurifier/ChildDef/StrictBlockquote.php

@@ -4,27 +4,31 @@ require_once 'HTMLPurifier/ChildDef/Required.php';
 
 /**
  * Takes the contents of blockquote when in strict and reformats for validation.
- * 
- * From XHTML 1.0 Transitional to Strict, there is a notable change where 
  */
 class   HTMLPurifier_ChildDef_StrictBlockquote
 extends HTMLPurifier_ChildDef_Required
 {
+    var $real_elements;
+    var $fake_elements;
     var $allow_empty = true;
     var $type = 'strictblockquote';
     var $init = false;
-    function HTMLPurifier_ChildDef_StrictBlockquote() {}
     function validateChildren($tokens_of_children, $config, &$context) {
         
         $def = $config->getHTMLDefinition();
         if (!$this->init) {
             // allow all inline elements
-            $this->elements = $def->info_flow_elements;
-            $this->elements['#PCDATA'] = true;
+            $this->real_elements = $this->elements;
+            $this->fake_elements = $def->info_content_sets['Flow'];
+            $this->fake_elements['#PCDATA'] = true;
             $this->init = true;
         }
         
+        // trick the parent class into thinking it allows more
+        $this->elements = $this->fake_elements;
         $result = parent::validateChildren($tokens_of_children, $config, $context);
+        $this->elements = $this->real_elements;
+        
         if ($result === false) return array();
         if ($result === true) $result = $tokens_of_children;
         
@@ -40,8 +44,10 @@ extends HTMLPurifier_ChildDef_Required
             // ifs are nested for readability
             if (!$is_inline) {
                 if (!$depth) {
-                     if (($token->type == 'text') ||
-                         ($def->info[$token->name]->type == 'inline')) {
+                     if (
+                        $token->type == 'text' ||
+                        !isset($this->elements[$token->name])
+                     ) {
                         $is_inline = true;
                         $ret[] = $block_wrap_start;
                      }
@@ -50,7 +56,7 @@ extends HTMLPurifier_ChildDef_Required
                 if (!$depth) {
                     // starting tokens have been inline text / empty
                     if ($token->type == 'start' || $token->type == 'empty') {
-                        if ($def->info[$token->name]->type == 'block') {
+                        if (isset($this->elements[$token->name])) {
                             // ended
                             $ret[] = $block_wrap_end;
                             $is_inline = false;

library/HTMLPurifier/Config.php

@@ -149,23 +149,36 @@ class HTMLPurifier_Config
             return;
         }
         $this->conf[$namespace][$key] = $value;
+        if ($namespace == 'HTML' || $namespace == 'Attr') {
+            // reset HTML definition if relevant attributes changed
+            $this->html_definition = null;
+        }
+        if ($namespace == 'CSS') {
+            $this->css_definition = null;
+        }
     }
     
     /**
-     * Retrieves a copy of the HTML definition.
+     * Retrieves reference to the HTML definition.
+     * @param $raw Return a copy that has not been setup yet. Must be
+     *             called before it's been setup, otherwise won't work.
      */
-    function getHTMLDefinition() {
-        if ($this->html_definition === null) {
-            $this->html_definition = new HTMLPurifier_HTMLDefinition();
-            $this->html_definition->setup($this);
+    function &getHTMLDefinition($raw = false) {
+        if (
+            empty($this->html_definition) || // hasn't ever been setup
+            ($raw && $this->html_definition->setup) // requesting new one
+        ) {
+            $this->html_definition = new HTMLPurifier_HTMLDefinition($this);
+            if ($raw) return $this->html_definition; // no setup!
         }
+        if (!$this->html_definition->setup) $this->html_definition->setup();
         return $this->html_definition;
     }
     
     /**
-     * Retrieves a copy of the CSS definition
+     * Retrieves reference to the CSS definition
      */
-    function getCSSDefinition() {
+    function &getCSSDefinition() {
         if ($this->css_definition === null) {
             $this->css_definition = new HTMLPurifier_CSSDefinition();
             $this->css_definition->setup($this);

library/HTMLPurifier/ConfigDef.php

@@ -0,0 +1,10 @@
+<?php
+
+/**
+ * Base class for configuration entity
+ */
+class HTMLPurifier_ConfigDef {
+    var $class = false;
+}
+
+?>

library/HTMLPurifier/ConfigDef/Directive.php

@@ -0,0 +1,74 @@
+<?php
+
+require_once 'HTMLPurifier/ConfigDef.php';
+
+/**
+ * Structure object containing definition of a directive.
+ * @note This structure does not contain default values
+ */
+class HTMLPurifier_ConfigDef_Directive extends HTMLPurifier_ConfigDef
+{
+    
+    var $class = 'directive';
+    
+    function HTMLPurifier_ConfigDef_Directive(
+        $type = null,
+        $descriptions = null,
+        $allow_null = null,
+        $allowed = null,
+        $aliases = null
+    ) {
+        if (        $type !== null)         $this->type = $type;
+        if ($descriptions !== null) $this->descriptions = $descriptions;
+        if (  $allow_null !== null)   $this->allow_null = $allow_null;
+        if (     $allowed !== null)      $this->allowed = $allowed;
+        if (     $aliases !== null)      $this->aliases = $aliases;
+    }
+    
+    /**
+     * Allowed type of the directive. Values are:
+     *      - string
+     *      - istring (case insensitive string)
+     *      - int
+     *      - float
+     *      - bool
+     *      - lookup (array of value => true)
+     *      - list (regular numbered index array)
+     *      - hash (array of key => value)
+     *      - mixed (anything goes)
+     */
+    var $type = 'mixed';
+    
+    /**
+     * Plaintext descriptions of the configuration entity is. Organized by
+     * file and line number, so multiple descriptions are allowed.
+     */
+    var $descriptions = array();
+    
+    /**
+     * Is null allowed? Has no effect for mixed type.
+     * @bool
+     */
+    var $allow_null = false;
+    
+    /**
+     * Lookup table of allowed values of the element, bool true if all allowed.
+     */
+    var $allowed = true;
+    
+    /**
+     * Hash of value aliases, i.e. values that are equivalent.
+     */
+    var $aliases = array();
+    
+    /**
+     * Adds a description to the array
+     */
+    function addDescription($file, $line, $description) {
+        if (!isset($this->descriptions[$file])) $this->descriptions[$file] = array();
+        $this->descriptions[$file][$line] = $description;
+    }
+    
+}
+
+?>

library/HTMLPurifier/ConfigDef/DirectiveAlias.php

@@ -0,0 +1,27 @@
+<?php
+
+require_once 'HTMLPurifier/ConfigDef.php';
+
+/**
+ * Structure object describing a directive alias
+ */
+class HTMLPurifier_ConfigDef_DirectiveAlias extends HTMLPurifier_ConfigDef
+{
+    var $class = 'alias';
+    
+    /**
+     * Namespace being aliased to
+     */
+    var $namespace;
+    /**
+     * Directive being aliased to
+     */
+    var $name;
+    
+    function HTMLPurifier_ConfigDef_DirectiveAlias($namespace, $name) {
+        $this->namespace = $namespace;
+        $this->name = $name;
+    }
+}
+
+?>

library/HTMLPurifier/ConfigDef/Namespace.php

@@ -0,0 +1,23 @@
+<?php
+
+require_once 'HTMLPurifier/ConfigDef.php';
+
+/**
+ * Structure object describing of a namespace
+ */
+class HTMLPurifier_ConfigDef_Namespace extends HTMLPurifier_ConfigDef {
+    
+    function HTMLPurifier_ConfigDef_Namespace($description = null) {
+        $this->description = $description;
+    }
+    
+    var $class = 'namespace';
+    
+    /**
+     * String description of what kinds of directives go in this namespace.
+     */
+    var $description;
+    
+}
+
+?>

library/HTMLPurifier/ConfigSchema.php

@@ -1,6 +1,10 @@
 <?php
 
 require_once 'HTMLPurifier/Error.php';
+require_once 'HTMLPurifier/ConfigDef.php';
+require_once 'HTMLPurifier/ConfigDef/Namespace.php';
+require_once 'HTMLPurifier/ConfigDef/Directive.php';
+require_once 'HTMLPurifier/ConfigDef/DirectiveAlias.php';
 
 /**
  * Configuration definition, defines directives and their defaults.
@@ -138,7 +142,7 @@ class HTMLPurifier_ConfigSchema {
                 return;
             }
             $def->info[$namespace][$name] =
-                new HTMLPurifier_ConfigEntity_Directive();
+                new HTMLPurifier_ConfigDef_Directive();
             $def->info[$namespace][$name]->type = $type;
             $def->info[$namespace][$name]->allow_null = $allow_null;
             $def->defaults[$namespace][$name]   = $default;
@@ -172,7 +176,7 @@ class HTMLPurifier_ConfigSchema {
             return;
         }
         $def->info[$namespace] = array();
-        $def->info_namespace[$namespace] = new HTMLPurifier_ConfigEntity_Namespace();
+        $def->info_namespace[$namespace] = new HTMLPurifier_ConfigDef_Namespace();
         $def->info_namespace[$namespace]->description = $description;
         $def->defaults[$namespace] = array();
     }
@@ -284,7 +288,7 @@ class HTMLPurifier_ConfigSchema {
             return;
         }
         $def->info[$namespace][$name] =
-            new HTMLPurifier_ConfigEntity_DirectiveAlias(
+            new HTMLPurifier_ConfigDef_DirectiveAlias(
                 $new_namespace, $new_name);
     }
     
@@ -330,6 +334,10 @@ class HTMLPurifier_ConfigSchema {
             case 'hash':
             case 'lookup':
                 if (is_string($var)) {
+                    // special case: technically, this is an array with
+                    // a single empty string item, but having an empty
+                    // array is more intuitive
+                    if ($var == '') return array();
                     // simplistic string to array method that only works
                     // for simple lists of tag names or alphanumeric characters
                     $var = explode(',',$var);
@@ -379,120 +387,4 @@ class HTMLPurifier_ConfigSchema {
     }
 }
 
-/**
- * Base class for configuration entity
- */
-class HTMLPurifier_ConfigEntity {
-    var $class = false;
-}
-
-/**
- * Structure object describing of a namespace
- */
-class HTMLPurifier_ConfigEntity_Namespace extends HTMLPurifier_ConfigEntity {
-    
-    function HTMLPurifier_ConfigEntity_Namespace($description = null) {
-        $this->description = $description;
-    }
-    
-    var $class = 'namespace';
-    
-    /**
-     * String description of what kinds of directives go in this namespace.
-     */
-    var $description;
-    
-}
-
-/**
- * Structure object containing definition of a directive.
- * @note This structure does not contain default values
- */
-class HTMLPurifier_ConfigEntity_Directive extends HTMLPurifier_ConfigEntity
-{
-    
-    var $class = 'directive';
-    
-    function HTMLPurifier_ConfigEntity_Directive(
-        $type = null,
-        $descriptions = null,
-        $allow_null = null,
-        $allowed = null,
-        $aliases = null
-    ) {
-        if (        $type !== null)         $this->type = $type;
-        if ($descriptions !== null) $this->descriptions = $descriptions;
-        if (  $allow_null !== null)   $this->allow_null = $allow_null;
-        if (     $allowed !== null)      $this->allowed = $allowed;
-        if (     $aliases !== null)      $this->aliases = $aliases;
-    }
-    
-    /**
-     * Allowed type of the directive. Values are:
-     *      - string
-     *      - istring (case insensitive string)
-     *      - int
-     *      - float
-     *      - bool
-     *      - lookup (array of value => true)
-     *      - list (regular numbered index array)
-     *      - hash (array of key => value)
-     *      - mixed (anything goes)
-     */
-    var $type = 'mixed';
-    
-    /**
-     * Plaintext descriptions of the configuration entity is. Organized by
-     * file and line number, so multiple descriptions are allowed.
-     */
-    var $descriptions = array();
-    
-    /**
-     * Is null allowed? Has no effect for mixed type.
-     * @bool
-     */
-    var $allow_null = false;
-    
-    /**
-     * Lookup table of allowed values of the element, bool true if all allowed.
-     */
-    var $allowed = true;
-    
-    /**
-     * Hash of value aliases, i.e. values that are equivalent.
-     */
-    var $aliases = array();
-    
-    /**
-     * Adds a description to the array
-     */
-    function addDescription($file, $line, $description) {
-        if (!isset($this->descriptions[$file])) $this->descriptions[$file] = array();
-        $this->descriptions[$file][$line] = $description;
-    }
-    
-}
-
-/**
- * Structure object describing a directive alias
- */
-class HTMLPurifier_ConfigEntity_DirectiveAlias extends HTMLPurifier_ConfigEntity
-{
-    var $class = 'alias';
-    
-    /**
-     * Namespace being aliased to
-     */
-    var $namespace;
-    /**
-     * Directive being aliased to
-     */
-    var $name;
-    
-    function HTMLPurifier_ConfigEntity_DirectiveAlias($namespace, $name) {
-        $this->namespace = $namespace;
-        $this->name = $name;
-    }
-}
-
 ?>

library/HTMLPurifier/ContentSets.php

@@ -0,0 +1,148 @@
+<?php
+
+// common defs that we'll support by default
+require_once 'HTMLPurifier/ChildDef.php';
+require_once 'HTMLPurifier/ChildDef/Empty.php';
+require_once 'HTMLPurifier/ChildDef/Required.php';
+require_once 'HTMLPurifier/ChildDef/Optional.php';
+
+class HTMLPurifier_ContentSets
+{
+    
+    /**
+     * List of content set strings (pipe seperators) indexed by name.
+     * @public
+     */
+    var $info = array();
+    
+    /**
+     * List of content set lookups (element => true) indexed by name.
+     * @note This is in HTMLPurifier_HTMLDefinition->info_content_sets
+     * @public
+     */
+    var $lookup = array();
+    
+    /**
+     * Synchronized list of defined content sets (keys of info)
+     */
+    var $keys = array();
+    /**
+     * Synchronized list of defined content values (values of info)
+     */
+    var $values = array();
+    
+    /**
+     * Merges in module's content sets, expands identifiers in the content
+     * sets and populates the keys, values and lookup member variables.
+     * @param $modules List of HTMLPurifier_HTMLModule
+     */
+    function HTMLPurifier_ContentSets($modules) {
+        if (!is_array($modules)) $modules = array($modules);
+        // populate content_sets based on module hints
+        // sorry, no way of overloading
+        foreach ($modules as $module_i => $module) {
+            foreach ($module->content_sets as $key => $value) {
+                if (isset($this->info[$key])) {
+                    // add it into the existing content set
+                    $this->info[$key] = $this->info[$key] . ' | ' . $value;
+                } else {
+                    $this->info[$key] = $value;
+                }
+            }
+        }
+        // perform content_set expansions
+        $this->keys = array_keys($this->info);
+        foreach ($this->info as $i => $set) {
+            // only performed once, so infinite recursion is not
+            // a problem
+            $this->info[$i] =
+                str_replace(
+                    $this->keys,
+                    // must be recalculated each time due to
+                    // changing substitutions
+                    array_values($this->info),
+                $set);
+        }
+        $this->values = array_values($this->info);
+        
+        // generate lookup tables
+        foreach ($this->info as $name => $set) {
+            $this->lookup[$name] = $this->convertToLookup($set);
+        }
+    }
+    
+    /**
+     * Accepts a definition; generates and assigns a ChildDef for it
+     * @param $def HTMLPurifier_ElementDef reference
+     * @param $module Module that defined the ElementDef
+     */
+    function generateChildDef(&$def, $module) {
+        if (!empty($def->child)) return; // already done!
+        $content_model = $def->content_model;
+        if (is_string($content_model)) {
+            $def->content_model = str_replace(
+                $this->keys, $this->values, $content_model);
+        }
+        $def->child = $this->getChildDef($def, $module);
+    }
+    
+    /**
+     * Instantiates a ChildDef based on content_model and content_model_type
+     * member variables in HTMLPurifier_ElementDef
+     * @note This will also defer to modules for custom HTMLPurifier_ChildDef
+     *       subclasses that need content set expansion
+     * @param $def HTMLPurifier_ElementDef to have ChildDef extracted
+     * @return HTMLPurifier_ChildDef corresponding to ElementDef
+     */
+    function getChildDef($def, $module) {
+        $value = $def->content_model;
+        if (is_object($value)) {
+            trigger_error(
+                'Literal object child definitions should be stored in '.
+                'ElementDef->child not ElementDef->content_model',
+                E_USER_NOTICE
+            );
+            return $value;
+        }
+        switch ($def->content_model_type) {
+            case 'required':
+                return new HTMLPurifier_ChildDef_Required($value);
+            case 'optional':
+                return new HTMLPurifier_ChildDef_Optional($value);
+            case 'empty':
+                return new HTMLPurifier_ChildDef_Empty();
+            case 'custom':
+                return new HTMLPurifier_ChildDef_Custom($value);
+        }
+        // defer to its module
+        $return = false;
+        if ($module->defines_child_def) { // save a func call
+            $return = $module->getChildDef($def);
+        }
+        if ($return !== false) return $return;
+        // error-out
+        trigger_error(
+            'Could not determine which ChildDef class to instantiate',
+            E_USER_ERROR
+        );
+        return false;
+    }
+    
+    /**
+     * Converts a string list of elements separated by pipes into
+     * a lookup array.
+     * @param $string List of elements
+     * @return Lookup array of elements
+     */
+    function convertToLookup($string) {
+        $array = explode('|', str_replace(' ', '', $string));
+        $ret = array();
+        foreach ($array as $i => $k) {
+            $ret[$k] = true;
+        }
+        return $ret;
+    }
+    
+}
+
+?>

library/HTMLPurifier/ElementDef.php

@@ -0,0 +1,122 @@
+<?php
+
+/**
+ * Structure that stores an HTML element definition. Used by
+ * HTMLPurifier_HTMLDefinition and HTMLPurifier_HTMLModule.
+ */
+class HTMLPurifier_ElementDef
+{
+    
+    /**
+     * Does the definition work by itself, or is it created solely
+     * for the purpose of merging into another definition?
+     */
+    var $standalone = true;
+    
+    /**
+     * Associative array of attribute name to HTMLPurifier_AttrDef
+     * @note Before being processed by HTMLPurifier_AttrCollections
+     *       when modules are finalized during
+     *       HTMLPurifier_HTMLDefinition->setup(), this array may also
+     *       contain an array at index 0 that indicates which attribute
+     *       collections to load into the full array. It may also
+     *       contain string indentifiers in lieu of HTMLPurifier_AttrDef,
+     *       see HTMLPurifier_AttrTypes on how they are expanded during
+     *       HTMLPurifier_HTMLDefinition->setup() processing.
+     * @public
+     */
+    var $attr = array();
+    
+    /**
+     * Indexed list of tag's HTMLPurifier_AttrTransform to be done before validation
+     * @public
+     */
+    var $attr_transform_pre = array();
+    
+    /**
+     * Indexed list of tag's HTMLPurifier_AttrTransform to be done after validation
+     * @public
+     */
+    var $attr_transform_post = array();
+    
+    
+    
+    /**
+     * HTMLPurifier_ChildDef of this tag.
+     * @public
+     */
+    var $child;
+    
+    /**
+     * Abstract string representation of internal ChildDef rules. See
+     * HTMLPurifier_ContentSets for how this is parsed and then transformed
+     * into an HTMLPurifier_ChildDef.
+     * @public
+     */
+    var $content_model;
+    
+    /**
+     * Value of $child->type, used to determine which ChildDef to use,
+     * used in combination with $content_model.
+     * @public
+     */
+    var $content_model_type;
+    
+    
+    
+    /**
+     * Lookup table of tags that close this tag. Used during parsing
+     * to make sure we don't attempt to nest unclosed tags.
+     * @public
+     */
+    var $auto_close = array();
+    
+    /**
+     * Does the element have a content model (#PCDATA | Inline)*? This
+     * is important for chameleon ins and del processing in 
+     * HTMLPurifier_ChildDef_Chameleon. Dynamically set: modules don't
+     * have to worry about this one.
+     * @public
+     */
+    var $descendants_are_inline;
+    
+    /**
+     * Lookup table of tags excluded from all descendants of this tag.
+     * @public
+     */
+    var $excludes = array();
+    
+    /**
+     * Merges the values of another element definition into this one.
+     * Values from the new element def take precedence if a value is
+     * not mergeable.
+     */
+    function mergeIn($def) {
+        
+        // later keys takes precedence
+        foreach($def->attr as $k => $v) {
+            if ($k === 0) {
+                // merge in the includes
+                // sorry, no way to override an include
+                foreach ($v as $v2) {
+                    $def->attr[0][] = $v2;
+                }
+                continue;
+            }
+            $this->attr[$k] = $v;
+        }
+        foreach($def->attr_transform_pre    as $k => $v) $this->attr_transform_pre[$k]  = $v;
+        foreach($def->attr_transform_post   as $k => $v) $this->attr_transform_post[$k] = $v;
+        foreach($def->auto_close            as $k => $v) $this->auto_close[$k]          = $v;
+        foreach($def->excludes              as $k => $v) $this->excludes[$k]            = $v;
+        
+        if(!is_null($def->child)) $this->child = $def->child;
+        if(!empty($def->content_model)) $this->content_model .= ' | ' . $def->content_model;
+        if(!empty($def->content_model_type)) $this->content_model_type = $def->content_model_type;
+        if(!is_null($def->descendants_are_inline)) $this->descendants_are_inline = $def->descendants_are_inline;
+        
+    }
+    
+}
+
+?>

library/HTMLPurifier/Filter/YouTube.php

@@ -9,7 +9,7 @@ class HTMLPurifier_Filter_YouTube extends HTMLPurifier_Filter
     
     function preFilter($html, $config, &$context) {
         $pre_regex = '#<object[^>]+>.+?'.
-            'http://www.youtube.com/v/([A-Za-z0-9\-_]+).+?</object>#';
+            'http://www.youtube.com/v/([A-Za-z0-9\-_]+).+?</object>#s';
         $pre_replace = '<span class="youtube-embed">\1</span>';
         return preg_replace($pre_regex, $pre_replace, $html);
     }

library/HTMLPurifier/HTMLDefinition.php

@@ -1,46 +1,12 @@
 <?php
 
-require_once 'HTMLPurifier/AttrDef.php';
-    require_once 'HTMLPurifier/AttrDef/Enum.php';
-    require_once 'HTMLPurifier/AttrDef/ID.php';
-    require_once 'HTMLPurifier/AttrDef/Class.php';
-    require_once 'HTMLPurifier/AttrDef/Text.php';
-    require_once 'HTMLPurifier/AttrDef/Lang.php';
-    require_once 'HTMLPurifier/AttrDef/Pixels.php';
-    require_once 'HTMLPurifier/AttrDef/Length.php';
-    require_once 'HTMLPurifier/AttrDef/MultiLength.php';
-    require_once 'HTMLPurifier/AttrDef/Integer.php';
-    require_once 'HTMLPurifier/AttrDef/URI.php';
-    require_once 'HTMLPurifier/AttrDef/CSS.php';
-require_once 'HTMLPurifier/AttrTransform.php';
-    require_once 'HTMLPurifier/AttrTransform/Lang.php';
-    require_once 'HTMLPurifier/AttrTransform/TextAlign.php';
-    require_once 'HTMLPurifier/AttrTransform/BdoDir.php';
-    require_once 'HTMLPurifier/AttrTransform/ImgRequired.php';
-require_once 'HTMLPurifier/ChildDef.php';
-    require_once 'HTMLPurifier/ChildDef/Chameleon.php';
-    require_once 'HTMLPurifier/ChildDef/Empty.php';
-    require_once 'HTMLPurifier/ChildDef/Required.php';
-    require_once 'HTMLPurifier/ChildDef/Optional.php';
-    require_once 'HTMLPurifier/ChildDef/Table.php';
-    require_once 'HTMLPurifier/ChildDef/StrictBlockquote.php';
-require_once 'HTMLPurifier/Generator.php';
-require_once 'HTMLPurifier/Token.php';
-require_once 'HTMLPurifier/TagTransform.php';
+// components
+require_once 'HTMLPurifier/HTMLModuleManager.php';
 
-HTMLPurifier_ConfigSchema::define(
-    'HTML', 'EnableAttrID', false, 'bool',
-    'Allows the ID attribute in HTML.  This is disabled by default '.
-    'due to the fact that without proper configuration user input can '.
-    'easily break the validation of a webpage by specifying an ID that is '.
-    'already on the surrounding HTML.  If you don\'t mind throwing caution to '.
-    'the wind, enable this directive, but I strongly recommend you also '.
-    'consider blacklisting IDs you use (%Attr.IDBlacklist) or prefixing all '.
-    'user supplied IDs (%Attr.IDPrefix).  This directive has been available '.
-    'since 1.2.0, and when set to true reverts to the behavior of pre-1.2.0 '.
-    'versions.'
-);
+// this definition and its modules MUST NOT define configuration directives
+// outside of the HTML or Attr namespaces
 
+// will be superceded by more accurate doctype declaration schemes
 HTMLPurifier_ConfigSchema::define(
     'HTML', 'Strict', false, 'bool',
     'Determines whether or not to use Transitional (loose) or Strict rulesets. '.
@@ -91,33 +57,31 @@ HTMLPurifier_ConfigSchema::define(
     'IDs at all. This directive has been available since 1.3.0.'
 );
 
-HTMLPurifier_ConfigSchema::define(
-    'Attr', 'DisableURI', false, 'bool',
-    'Disables all URIs in all forms. Not sure why you\'d want to do that '.
-    '(after all, the Internet\'s founded on the notion of a hyperlink). '.
-    'This directive has been available since 1.3.0.'
-);
-
 /**
- * Defines the purified HTML type with large amounts of objects.
+ * Definition of the purified HTML that describes allowed children,
+ * attributes, and many other things.
  * 
- * The main function of this object is its $info array, which is an 
- * associative array of all the child and attribute definitions for
- * each allowed element. It also contains special use information (always
- * prefixed by info) for intelligent tag closing and global attributes.
+ * Conventions:
  * 
- * For optimization, the definition generation may be moved to
- * a maintenance script and stipulate that definition be created
- * by a factory method that unserializes a serialized version of Definition.
- * Customization would entail copying the maintenance script, making the
- * necessary changes, generating the serialized object, and then hooking it
- * in via the factory method. We would also offer a LiveDefinition for
- * automatic recompilation, suggesting that we would have a DefinitionGenerator.
+ * All member variables that are prefixed with info
+ * (including the main $info array) are used by HTML Purifier internals
+ * and should not be directly edited when customizing the HTMLDefinition.
+ * They can usually be set via configuration directives or custom
+ * modules.
+ * 
+ * On the other hand, member variables without the info prefix are used
+ * internally by the HTMLDefinition and MUST NOT be used by other HTML
+ * Purifier internals. Many of them, however, are public, and may be
+ * edited by userspace code to tweak the behavior of HTMLDefinition.
+ * 
+ * HTMLPurifier_Printer_HTMLDefinition is a notable exception to this
+ * rule: in the interest of comprehensiveness, it will sniff everything.
  */
-
 class HTMLPurifier_HTMLDefinition
 {
     
+    /** FULLY-PUBLIC VARIABLES */
+    
     /**
      * Associative array of element names to HTMLPurifier_ElementDef
      * @public
@@ -157,499 +121,169 @@ class HTMLPurifier_HTMLDefinition
     var $info_tag_transform = array();
     
     /**
-     * List of HTMLPurifier_AttrTransform to be performed before validation.
+     * Indexed list of HTMLPurifier_AttrTransform to be performed before validation.
      * @public
      */
     var $info_attr_transform_pre = array();
     
     /**
-     * List of HTMLPurifier_AttrTransform to be performed after validation/
+     * Indexed list of HTMLPurifier_AttrTransform to be performed after validation.
      * @public
      */
     var $info_attr_transform_post = array();
     
     /**
-     * Lookup table of flow elements
+     * Nested lookup array of content set name (Block, Inline) to
+     * element name to whether or not it belongs in that content set.
      * @public
      */
-    var $info_flow_elements = array();
+    var $info_content_sets = array();
+    
+    
+    
+    /** PUBLIC BUT INTERNAL VARIABLES */
+    
+    var $setup = false; /**< Has setup() been called yet? */
+    var $config; /**< Temporary instance of HTMLPurifier_Config */
+    
+    var $manager; /**< Instance of HTMLPurifier_HTMLModuleManager */
     
     /**
-     * Boolean is a strict definition?
-     * @public
+     * Performs low-cost, preliminary initialization.
+     * @param $config Instance of HTMLPurifier_Config
      */
-    var $strict;
+    function HTMLPurifier_HTMLDefinition(&$config) {
+        $this->config =& $config;
+        $this->manager = new HTMLPurifier_HTMLModuleManager();
+    }
     
     /**
-     * Initializes the definition, the meat of the class.
+     * Processes internals into form usable by HTMLPurifier internals. 
+     * Modifying the definition after calling this function should not
+     * be done.
      */
-    function setup($config) {
-        
-        // some cached config values
-        $this->strict = $config->get('HTML', 'Strict');
-        
-        //////////////////////////////////////////////////////////////////////
-        // info[] : initializes the definition objects
-        
-        // if you attempt to define rules later on for a tag not in this array
-        // PHP will create an stdclass
-        
-        $allowed_tags =
-            array(
-                'ins', 'del', 'blockquote', 'dd', 'li', 'div', 'em', 'strong',
-                'dfn', 'code', 'samp', 'kbd', 'var', 'cite', 'abbr', 'acronym',
-                'q', 'sub', 'tt', 'sup', 'i', 'b', 'big', 'small',
-                'bdo', 'span', 'dt', 'p', 'h1', 'h2', 'h3', 'h4',
-                'h5', 'h6', 'ol', 'ul', 'dl', 'address', 'img', 'br', 'hr',
-                'pre', 'a', 'table', 'caption', 'thead', 'tfoot', 'tbody',
-                'colgroup', 'col', 'td', 'th', 'tr'
-            );
-        
-        if (!$this->strict) {
-            $allowed_tags[] = 'u';
-            $allowed_tags[] = 's';
-            $allowed_tags[] = 'strike';
-        }
-        
-        foreach ($allowed_tags as $tag) {
-            $this->info[$tag] = new HTMLPurifier_ElementDef();
-        }
-        
-        //////////////////////////////////////////////////////////////////////
-        // info[]->child : defines allowed children for elements
-        
-        // emulates the structure of the DTD
-        // however, these are condensed, with bad stuff taken out
-        // screening process was done by hand
-        
-        // entities: prefixed with e_ and _ replaces . from DTD
-        // double underlines are entities we made up
-        
-        // we don't use an array because that complicates interpolation
-        // strings are used instead of arrays because if you use arrays,
-        // you have to do some hideous manipulation with array_merge()
-        
-        // todo: determine whether or not having allowed children
-        //       that aren't allowed globally affects security (it shouldn't)
-        // if above works out, extend children definitions to include all
-        //       possible elements (allowed elements will dictate which ones
-        //       get dropped
-        
-        $e_special_extra = 'img';
-        $e_special_basic = 'br | span | bdo';
-        $e_special = "$e_special_basic | $e_special_extra";
-        $e_fontstyle_extra = 'big | small';
-        $e_fontstyle_basic = 'tt | i | b | u | s | strike';
-        $e_fontstyle = "$e_fontstyle_basic | $e_fontstyle_extra";
-        $e_phrase_extra = 'sub | sup';
-        $e_phrase_basic = 'em | strong | dfn | code | q | samp | kbd | var'.
-          ' | cite | abbr | acronym';
-        $e_phrase = "$e_phrase_basic | $e_phrase_extra";
-        $e_misc_inline = 'ins | del';
-        $e_misc = "$e_misc_inline";
-        $e_inline = "a | $e_special | $e_fontstyle | $e_phrase";
-        // pseudo-property we created for convenience, see later on
-        $e__inline = "#PCDATA | $e_inline | $e_misc_inline";
-        // note the casing
-        $e_Inline = new HTMLPurifier_ChildDef_Optional($e__inline);
-        $e_heading = 'h1|h2|h3|h4|h5|h6';
-        $e_lists = 'ul | ol | dl';
-        $e_blocktext = 'pre | hr | blockquote | address';
-        $e_block = "p | $e_heading | div | $e_lists | $e_blocktext | table";
-        $e_Block = new HTMLPurifier_ChildDef_Optional($e_block);
-        $e__flow = "#PCDATA | $e_block | $e_inline | $e_misc";
-        $e_Flow = new HTMLPurifier_ChildDef_Optional($e__flow);
-        $e_a_content = new HTMLPurifier_ChildDef_Optional("#PCDATA".
-          " | $e_special | $e_fontstyle | $e_phrase | $e_misc_inline");
-        $e_pre_content = new HTMLPurifier_ChildDef_Optional("#PCDATA | a".
-          " | $e_special_basic | $e_fontstyle_basic | $e_phrase_basic".
-          " | $e_misc_inline");
-        $e_form_content = new HTMLPurifier_ChildDef_Optional('');//unused
-        $e_form_button_content = new HTMLPurifier_ChildDef_Optional('');//unused
-        
-        $this->info['ins']->child =
-        $this->info['del']->child =
-            new HTMLPurifier_ChildDef_Chameleon($e__inline, $e__flow);
-        
-        $this->info['dd']->child  =
-        $this->info['li']->child  =
-        $this->info['div']->child = $e_Flow;
-        
-        if ($this->strict) {
-            $this->info['blockquote']->child = new HTMLPurifier_ChildDef_StrictBlockquote();
-        } else {
-            $this->info['blockquote']->child = $e_Flow;
-        }
-        
-        $this->info['caption']->child   = 
-        $this->info['em']->child   =
-        $this->info['strong']->child    =
-        $this->info['dfn']->child  =
-        $this->info['code']->child =
-        $this->info['samp']->child =
-        $this->info['kbd']->child  =
-        $this->info['var']->child  =
-        $this->info['cite']->child =
-        $this->info['abbr']->child =
-        $this->info['acronym']->child   =
-        $this->info['q']->child    =
-        $this->info['sub']->child  =
-        $this->info['tt']->child   =
-        $this->info['sup']->child  =
-        $this->info['i']->child    =
-        $this->info['b']->child    =
-        $this->info['big']->child  =
-        $this->info['small']->child=
-        $this->info['bdo']->child  =
-        $this->info['span']->child =
-        $this->info['dt']->child   =
-        $this->info['p']->child    = 
-        $this->info['h1']->child   = 
-        $this->info['h2']->child   = 
-        $this->info['h3']->child   = 
-        $this->info['h4']->child   = 
-        $this->info['h5']->child   = 
-        $this->info['h6']->child   = $e_Inline;
-        
-        if (!$this->strict) {
-            $this->info['u']->child    =
-            $this->info['s']->child    =
-            $this->info['strike']->child    = $e_Inline;
-        }
-        
-        // the only three required definitions, besides custom table code
-        $this->info['ol']->child   =
-        $this->info['ul']->child   = new HTMLPurifier_ChildDef_Required('li');
-        
-        $this->info['dl']->child   = new HTMLPurifier_ChildDef_Required('dt|dd');
-        
-        if ($this->strict) {
-            $this->info['address']->child = $e_Inline;
-        } else {
-            $this->info['address']->child =
-              new HTMLPurifier_ChildDef_Optional("#PCDATA | p | $e_inline".
-                  " | $e_misc_inline");
-        }
-        
-        $this->info['img']->child  =
-        $this->info['br']->child   =
-        $this->info['hr']->child   = new HTMLPurifier_ChildDef_Empty();
-        
-        $this->info['pre']->child  = $e_pre_content;
-        
-        $this->info['a']->child    = $e_a_content;
-        
-        $this->info['table']->child = new HTMLPurifier_ChildDef_Table();
-        
-        // not a real entity, watch the double underscore
-        $e__row = new HTMLPurifier_ChildDef_Required('tr');
-        $this->info['thead']->child = $e__row;
-        $this->info['tfoot']->child = $e__row;
-        $this->info['tbody']->child = $e__row;
-        $this->info['colgroup']->child = new HTMLPurifier_ChildDef_Optional('col');
-        $this->info['col']->child = new HTMLPurifier_ChildDef_Empty();
-        $this->info['tr']->child = new HTMLPurifier_ChildDef_Required('th | td');
-        $this->info['th']->child = $e_Flow;
-        $this->info['td']->child = $e_Flow;
-        
-        //////////////////////////////////////////////////////////////////////
-        // info[]->type : defines the type of the element (block or inline)
-        
-        // reuses $e_Inline and $e_Block
-        foreach ($e_Inline->elements as $name => $bool) {
-            if ($name == '#PCDATA') continue;
-            if (!isset($this->info[$name])) continue;
-            $this->info[$name]->type = 'inline';
-        }
-        
-        foreach ($e_Block->elements as $name => $bool) {
-            if (!isset($this->info[$name])) continue;
-            $this->info[$name]->type = 'block';
-        }
-        
-        foreach ($e_Flow->elements as $name => $bool) {
-            $this->info_flow_elements[$name] = true;
-        }
-        
-        //////////////////////////////////////////////////////////////////////
-        // info[]->excludes : defines elements that aren't allowed in here
-        
-        // make sure you test using isset() and not !empty()
-        
-        $this->info['a']->excludes = array('a' => true);
-        $this->info['pre']->excludes = array_flip(array('img', 'big', 'small',
-            // technically useless, but good to be indepth
-            'object', 'applet', 'font', 'basefont'));
-        
-        //////////////////////////////////////////////////////////////////////
-        // info[]->attr : defines allowed attributes for elements
-        
-        // this doesn't include REQUIRED declarations, those are handled
-        // by the transform classes. It will, however, do simple and slightly
-        // complex attribute value substitution
-        
-        // the question of varying allowed attributes is more entangling.
-        
-        $e_Text = new HTMLPurifier_AttrDef_Text();
-        
-        // attrs, included in almost every single one except for a few,
-        // which manually override these in their local definitions
-        $this->info_global_attr = array(
-            // core attrs
-            'class' => new HTMLPurifier_AttrDef_Class(),
-            'title' => $e_Text,
-            'style' => new HTMLPurifier_AttrDef_CSS(),
-            // i18n
-            'dir'   => new HTMLPurifier_AttrDef_Enum(array('ltr','rtl'), false),
-            'lang'  => new HTMLPurifier_AttrDef_Lang(),
-            'xml:lang' => new HTMLPurifier_AttrDef_Lang(),
-            );
-        
-        if ($config->get('HTML', 'EnableAttrID')) {
-            $this->info_global_attr['id'] = new HTMLPurifier_AttrDef_ID();
-        }
-        
-        // required attribute stipulation handled in attribute transformation
-        $this->info['bdo']->attr = array(); // nothing else
-        
-        $this->info['br']->attr['dir'] = false;
-        $this->info['br']->attr['lang'] = false;
-        $this->info['br']->attr['xml:lang'] = false;
-        
-        $this->info['td']->attr['abbr'] = $e_Text;
-        $this->info['th']->attr['abbr'] = $e_Text;
-        
-        $this->setAttrForTableElements('align', new HTMLPurifier_AttrDef_Enum(
-            array('left', 'center', 'right', 'justify', 'char'), false));
-        
-        $this->setAttrForTableElements('valign', new HTMLPurifier_AttrDef_Enum(
-            array('top', 'middle', 'bottom', 'baseline'), false));
-        
-        $this->info['img']->attr['alt'] = $e_Text;
-        
-        $e_TFrame = new HTMLPurifier_AttrDef_Enum(array('void', 'above',
-            'below', 'hsides', 'lhs', 'rhs', 'vsides', 'box', 'border'), false);
-        $this->info['table']->attr['frame'] = $e_TFrame;
-        
-        $e_TRules = new HTMLPurifier_AttrDef_Enum(array('none', 'groups',
-            'rows', 'cols', 'all'), false);
-        $this->info['table']->attr['rules'] = $e_TRules;
-        
-        $this->info['table']->attr['summary'] = $e_Text;
-        
-        $this->info['table']->attr['border'] =
-            new HTMLPurifier_AttrDef_Pixels();
-        
-        $e_Length = new HTMLPurifier_AttrDef_Length();
-        $this->info['table']->attr['cellpadding'] =
-        $this->info['table']->attr['cellspacing'] =
-        $this->info['table']->attr['width'] =
-        $this->info['img']->attr['height'] =
-        $this->info['img']->attr['width'] = $e_Length;
-        $this->setAttrForTableElements('charoff', $e_Length);
-        
-        $e_MultiLength = new HTMLPurifier_AttrDef_MultiLength();
-        $this->info['col']->attr['width'] =
-        $this->info['colgroup']->attr['width'] = $e_MultiLength;
-        
-        $e__NumberSpan = new HTMLPurifier_AttrDef_Integer(false, false, true);
-        $this->info['colgroup']->attr['span'] =
-        $this->info['col']->attr['span']   =
-        $this->info['td']->attr['rowspan'] =
-        $this->info['th']->attr['rowspan'] = 
-        $this->info['td']->attr['colspan'] =
-        $this->info['th']->attr['colspan'] = $e__NumberSpan;
-        
-        if (!$config->get('Attr', 'DisableURI')) {
-            $e_URI = new HTMLPurifier_AttrDef_URI();
-            $this->info['a']->attr['href'] =
-            $this->info['img']->attr['longdesc'] =
-            $this->info['del']->attr['cite'] =
-            $this->info['ins']->attr['cite'] =
-            $this->info['blockquote']->attr['cite'] =
-            $this->info['q']->attr['cite'] = $e_URI;
-            
-            // URI that causes HTTP request
-            $this->info['img']->attr['src'] = new HTMLPurifier_AttrDef_URI(true);
-        }
-        
-        if (!$this->strict) {
-            $this->info['li']->attr['value'] = new HTMLPurifier_AttrDef_Integer();
-            $this->info['ol']->attr['start'] = new HTMLPurifier_AttrDef_Integer();
-        }
-        
-        //////////////////////////////////////////////////////////////////////
-        // info_tag_transform : transformations of tags
-        
-        $this->info_tag_transform['font']   = new HTMLPurifier_TagTransform_Font();
-        $this->info_tag_transform['menu']   = new HTMLPurifier_TagTransform_Simple('ul');
-        $this->info_tag_transform['dir']    = new HTMLPurifier_TagTransform_Simple('ul');
-        $this->info_tag_transform['center'] = new HTMLPurifier_TagTransform_Center();
-        
-        //////////////////////////////////////////////////////////////////////
-        // info[]->auto_close : tags that automatically close another
-        
-        // todo: determine whether or not SGML-like modeling based on
-        // mandatory/optional end tags would be a better policy
-        
-        // make sure you test using isset() not !empty()
-        
-        // these are all block elements: blocks aren't allowed in P
-        $this->info['p']->auto_close = array_flip(array(
-                'address', 'blockquote', 'dd', 'dir', 'div', 'dl', 'dt',
-                'h1', 'h2', 'h3', 'h4', 'h5', 'h6', 'hr', 'ol', 'p', 'pre',
-                'table', 'ul'
-            ));
-        
-        $this->info['li']->auto_close = array('li' => true);
-        
-        // we need TABLE and heading mismatch code
-        // we may need to make this more flexible for heading mismatch,
-        // or we can just create another info
-        
-        //////////////////////////////////////////////////////////////////////
-        // info[]->attr_transform_* : attribute transformations in elements
-        // pre is applied before any validation is done, post is done after
-        
-        $this->info['h1']->attr_transform_pre[] =
-        $this->info['h2']->attr_transform_pre[] =
-        $this->info['h3']->attr_transform_pre[] =
-        $this->info['h4']->attr_transform_pre[] =
-        $this->info['h5']->attr_transform_pre[] =
-        $this->info['h6']->attr_transform_pre[] =
-        $this->info['p'] ->attr_transform_pre[] = 
-                    new HTMLPurifier_AttrTransform_TextAlign();
-        
-        $this->info['bdo']->attr_transform_post[] =
-                    new HTMLPurifier_AttrTransform_BdoDir();
-        
-        $this->info['img']->attr_transform_post[] =
-                    new HTMLPurifier_AttrTransform_ImgRequired();
-        
-        //////////////////////////////////////////////////////////////////////
-        // info_attr_transform_* : global attribute transformation that is
-        // unconditionally called. Good for transformations that have complex
-        // start conditions
-        // pre is applied before any validation is done, post is done after
-        
-        $this->info_attr_transform_post[] = new HTMLPurifier_AttrTransform_Lang();
-        
-        // protect against stdclasses floating around
-        foreach ($this->info as $key => $obj) {
-            if ($obj instanceof stdClass) {
-                unset($this->info[$key]);
+    function setup() {
+        
+        // multiple call guard
+        if ($this->setup) {return;} else {$this->setup = true;}
+        
+        $this->processModules();
+        $this->setupConfigStuff();
+        
+        unset($this->config);
+        unset($this->manager);
+        
+    }
+    
+    /**
+     * Extract out the information from the manager
+     */
+    function processModules() {
+        
+        $this->manager->setup($this->config);
+        
+        foreach ($this->manager->activeModules as $module) {
+            foreach($module->info_tag_transform         as $k => $v) {
+                if ($v === false) unset($this->info_tag_transform[$k]);
+                else $this->info_tag_transform[$k] = $v;
+            }
+            foreach($module->info_attr_transform_pre    as $k => $v) {
+                if ($v === false) unset($this->info_attr_transform_pre[$k]);
+                else $this->info_attr_transform_pre[$k] = $v;
+            }
+            foreach($module->info_attr_transform_post   as $k => $v) {
+                if ($v === false) unset($this->info_attr_transform_post[$k]);
+                else $this->info_attr_transform_post[$k] = $v;
             }
         }
         
-        //////////////////////////////////////////////////////////////////////
-        // info_block_wrapper : wraps inline elements in block context
+        $this->info = $this->manager->getElements($this->config);
+        $this->info_content_sets = $this->manager->contentSets->lookup;
         
-        $block_wrapper = $config->get('HTML', 'BlockWrapper');
-        if (isset($e_Block->elements[$block_wrapper])) {
+    }
+    
+    /**
+     * Sets up stuff based on config. We need a better way of doing this.
+     */
+    function setupConfigStuff() {
+        
+        $block_wrapper = $this->config->get('HTML', 'BlockWrapper');
+        if (isset($this->info_content_sets['Block'][$block_wrapper])) {
             $this->info_block_wrapper = $block_wrapper;
         } else {
             trigger_error('Cannot use non-block element as block wrapper.',
                 E_USER_ERROR);
         }
         
-        //////////////////////////////////////////////////////////////////////
-        // info_parent : parent element of the HTML fragment
-        
-        $parent = $config->get('HTML', 'Parent');
-        if (isset($this->info[$parent])) {
+        $parent = $this->config->get('HTML', 'Parent');
+        $def = $this->manager->getElement($parent, $this->config);
+        if ($def) {
             $this->info_parent = $parent;
+            $this->info_parent_def = $def;
         } else {
             trigger_error('Cannot use unrecognized element as parent.',
                 E_USER_ERROR);
+            $this->info_parent_def = $this->manager->getElement(
+                $this->info_parent, $this->config);
         }
-        $this->info_parent_def = $this->info[$this->info_parent];
         
-        //////////////////////////////////////////////////////////////////////
-        // %HTML.Allowed(Elements|Attributes) : cut non-allowed elements
+        // support template text
+        $support = "(for information on implementing this, see the ".
+                   "support forums) ";
         
-        $allowed_elements = $config->get('HTML', 'AllowedElements');
+        // setup allowed elements, SubtractiveWhitelist module
+        $allowed_elements = $this->config->get('HTML', 'AllowedElements');
         if (is_array($allowed_elements)) {
             foreach ($this->info as $name => $d) {
                 if(!isset($allowed_elements[$name])) unset($this->info[$name]);
+                unset($allowed_elements[$name]);
+            }
+            // emit errors
+            foreach ($allowed_elements as $element => $d) {
+                trigger_error("Element '$element' is not supported $support", E_USER_WARNING);
             }
         }
-        $allowed_attributes = $config->get('HTML', 'AllowedAttributes');
+        
+        $allowed_attributes = $this->config->get('HTML', 'AllowedAttributes');
+        $allowed_attributes_mutable = $allowed_attributes; // by copy!
         if (is_array($allowed_attributes)) {
             foreach ($this->info_global_attr as $attr_key => $info) {
                 if (!isset($allowed_attributes["*.$attr_key"])) {
                     unset($this->info_global_attr[$attr_key]);
+                } elseif (isset($allowed_attributes_mutable["*.$attr_key"])) {
+                    unset($allowed_attributes_mutable["*.$attr_key"]);
                 }
             }
             foreach ($this->info as $tag => $info) {
                 foreach ($info->attr as $attr => $attr_info) {
-                    if (!isset($allowed_attributes["$tag.$attr"])) {
+                    if (!isset($allowed_attributes["$tag.$attr"]) &&
+                        !isset($allowed_attributes["*.$attr"])) {
                         unset($this->info[$tag]->attr[$attr]);
+                    } else {
+                        if (isset($allowed_attributes_mutable["$tag.$attr"])) {
+                            unset($allowed_attributes_mutable["$tag.$attr"]);
+                        } elseif (isset($allowed_attributes_mutable["*.$attr"])) {
+                            unset($allowed_attributes_mutable["*.$attr"]);
+                        }
                     }
                 }
             }
+            // emit errors
+            foreach ($allowed_attributes_mutable as $elattr => $d) {
+                list($element, $attribute) = explode('.', $elattr);
+                if ($element == '*') {
+                    trigger_error("Global attribute '$attribute' is not ".
+                        "supported in any elements $support",
+                        E_USER_WARNING);
+                } else {
+                    trigger_error("Attribute '$attribute' in element '$element' not supported $support",
+                        E_USER_WARNING);
+                }
+            }
         }
+        
     }
     
-    function setAttrForTableElements($attr, $def) {
-        $this->info['col']->attr[$attr] = 
-        $this->info['colgroup']->attr[$attr] = 
-        $this->info['tbody']->attr[$attr] = 
-        $this->info['td']->attr[$attr] = 
-        $this->info['tfoot']->attr[$attr] = 
-        $this->info['th']->attr[$attr] = 
-        $this->info['thead']->attr[$attr] = 
-        $this->info['tr']->attr[$attr] = $def;
-    }
-    
-}
-
-/**
- * Structure that stores an element definition.
- */
-class HTMLPurifier_ElementDef
-{
-    
-    /**
-     * Associative array of attribute name to HTMLPurifier_AttrDef
-     * @public
-     */
-    var $attr = array();
-    
-    /**
-     * List of tag's HTMLPurifier_AttrTransform to be done before validation
-     * @public
-     */
-    var $attr_transform_pre = array();
-    
-    /**
-     * List of tag's HTMLPurifier_AttrTransform to be done after validation
-     * @public
-     */
-    var $attr_transform_post = array();
-    
-    /**
-     * Lookup table of tags that close this tag.
-     * @public
-     */
-    var $auto_close = array();
-    
-    /**
-     * HTMLPurifier_ChildDef of this tag.
-     * @public
-     */
-    var $child;
-    
-    /**
-     * Type of the tag: inline or block or unknown?
-     * @public
-     */
-    var $type = 'unknown';
-    
-    /**
-     * Lookup table of tags excluded from all descendants of this tag.
-     * @public
-     */
-    var $excludes = array();
     
 }
 

library/HTMLPurifier/HTMLModule.php

@@ -0,0 +1,125 @@
+<?php
+
+/**
+ * Represents an XHTML 1.1 module, with information on elements, tags
+ * and attributes.
+ * @note Even though this is technically XHTML 1.1, it is also used for
+ *       regular HTML parsing. We are using modulization as a convenient
+ *       way to represent the internals of HTMLDefinition, and our
+ *       implementation is by no means conforming and does not directly
+ *       use the normative DTDs or XML schemas.
+ * @note The public variables in a module should almost directly
+ *       correspond to the variables in HTMLPurifier_HTMLDefinition.
+ *       However, the prefix info carries no special meaning in these
+ *       objects (include it anyway if that's the correspondence though).
+ */
+
+class HTMLPurifier_HTMLModule
+{
+    /**
+     * Short unique string identifier of the module
+     */
+    var $name;
+    
+    /**
+     * Dynamically set integer that specifies when the module was loaded in.
+     */
+    var $order;
+    
+    /**
+     * Informally, a list of elements this module changes. Not used in
+     * any significant way.
+     * @protected
+     */
+    var $elements = array();
+    
+    /**
+     * Associative array of element names to element definitions.
+     * Some definitions may be incomplete, to be merged in later
+     * with the full definition.
+     * @public
+     */
+    var $info = array();
+    
+    /**
+     * Associative array of content set names to content set additions.
+     * This is commonly used to, say, add an A element to the Inline
+     * content set. This corresponds to an internal variable $content_sets
+     * and NOT info_content_sets member variable of HTMLDefinition.
+     * @public
+     */
+    var $content_sets = array();
+    
+    /**
+     * Associative array of attribute collection names to attribute
+     * collection additions. More rarely used for adding attributes to
+     * the global collections. Example is the StyleAttribute module adding
+     * the style attribute to the Core. Corresponds to HTMLDefinition's
+     * attr_collections->info, since the object's data is only info,
+     * with extra behavior associated with it.
+     * @public
+     */
+    var $attr_collections = array();
+    
+    /**
+     * Associative array of deprecated tag name to HTMLPurifier_TagTransform
+     * @public
+     */
+    var $info_tag_transform = array();
+    
+    /**
+     * List of HTMLPurifier_AttrTransform to be performed before validation.
+     * @public
+     */
+    var $info_attr_transform_pre = array();
+    
+    /**
+     * List of HTMLPurifier_AttrTransform to be performed after validation.
+     * @public
+     */
+    var $info_attr_transform_post = array();
+    
+    /**
+     * Boolean flag that indicates whether or not getChildDef is implemented.
+     * For optimization reasons: may save a call to a function. Be sure
+     * to set it if you do implement getChildDef(), otherwise it will have
+     * no effect!
+     * @public
+     */
+    var $defines_child_def = false;
+    
+    /**
+     * Retrieves a proper HTMLPurifier_ChildDef subclass based on 
+     * content_model and content_model_type member variables of
+     * the HTMLPurifier_ElementDef class. There is a similar function
+     * in HTMLPurifier_HTMLDefinition.
+     * @param $def HTMLPurifier_ElementDef instance
+     * @return HTMLPurifier_ChildDef subclass
+     * @public
+     */
+    function getChildDef($def) {return false;}
+    
+    /**
+     * Hook method that lets module perform arbitrary operations on
+     * HTMLPurifier_HTMLDefinition before the module gets processed.
+     * @param $definition Reference to HTMLDefinition being setup
+     */
+    function preProcess(&$definition) {}
+    
+    /**
+     * Hook method that lets module perform arbitrary operations
+     * on HTMLPurifier_HTMLDefinition after the module gets processed.
+     * @param $definition Reference to HTMLDefinition being setup
+     */
+    function postProcess(&$definition) {}
+    
+    /**
+     * Hook method that is called when a module gets registered to
+     * the definition.
+     * @param $definition Reference to HTMLDefinition being setup
+     */
+    function setup(&$definition) {}
+    
+}
+
+?>

library/HTMLPurifier/HTMLModule/Bdo.php

@@ -0,0 +1,42 @@
+<?php
+
+require_once 'HTMLPurifier/HTMLModule.php';
+require_once 'HTMLPurifier/AttrTransform/BdoDir.php';
+
+/**
+ * XHTML 1.1 Bi-directional Text Module, defines elements that
+ * declare directionality of content. Text Extension Module.
+ */
+class HTMLPurifier_HTMLModule_Bdo extends HTMLPurifier_HTMLModule
+{
+    
+    var $name = 'Bdo';
+    var $elements = array('bdo');
+    var $content_sets = array('Inline' => 'bdo');
+    var $attr_collections = array(
+        'I18N' => array('dir' => false)
+    );
+    
+    function HTMLPurifier_HTMLModule_Bdo() {
+        $dir = new HTMLPurifier_AttrDef_Enum(array('ltr','rtl'), false);
+        $this->attr_collections['I18N']['dir'] = $dir;
+        $this->info['bdo'] = new HTMLPurifier_ElementDef();
+        $this->info['bdo']->attr = array(
+            0 => array('Core', 'Lang'),
+            'dir' => $dir, // required
+            // The Abstract Module specification has the attribute
+            // inclusions wrong for bdo: bdo allows
+            // xml:lang too (and we'll toss in lang for good measure,
+            // though it is not allowed for XHTML 1.1, this will
+            // be managed with a global attribute transform)
+        );
+        $this->info['bdo']->content_model = '#PCDATA | Inline';
+        $this->info['bdo']->content_model_type = 'optional';
+        // provides fallback behavior if dir's missing (dir is required)
+        $this->info['bdo']->attr_transform_post['required-dir'] =
+            new HTMLPurifier_AttrTransform_BdoDir();
+    }
+    
+}
+
+?>

library/HTMLPurifier/HTMLModule/CommonAttributes.php

@@ -0,0 +1,31 @@
+<?php
+
+class HTMLPurifier_HTMLModule_CommonAttributes extends HTMLPurifier_HTMLModule
+{
+    var $name = 'CommonAttributes';
+    
+    var $attr_collections = array(
+        'Core' => array(
+            0 => array('Style'),
+            // 'xml:space' => false,
+            'class' => 'NMTOKENS',
+            'id' => 'ID',
+            'title' => 'CDATA',
+        ),
+        'Lang' => array(
+            'xml:lang' => false, // see constructor
+        ),
+        'I18N' => array(
+            0 => array('Lang'), // proprietary, for xml:lang/lang
+        ),
+        'Common' => array(
+            0 => array('Core', 'I18N')
+        )
+    );
+    
+    function HTMLPurifier_HTMLModule_CommonAttributes() {
+        $this->attr_collections['Lang']['xml:lang'] = new HTMLPurifier_AttrDef_Lang();
+    }
+}
+
+?>

library/HTMLPurifier/HTMLModule/Edit.php

@@ -0,0 +1,45 @@
+<?php
+
+require_once 'HTMLPurifier/HTMLModule.php';
+require_once 'HTMLPurifier/ChildDef/Chameleon.php';
+
+/**
+ * XHTML 1.1 Edit Module, defines editing-related elements. Text Extension
+ * Module.
+ */
+class HTMLPurifier_HTMLModule_Edit extends HTMLPurifier_HTMLModule
+{
+    
+    var $name = 'Edit';
+    var $elements = array('del', 'ins');
+    var $content_sets = array('Inline' => 'del | ins');
+    
+    function HTMLPurifier_HTMLModule_Edit() {
+        foreach ($this->elements as $element) {
+            $this->info[$element] = new HTMLPurifier_ElementDef();
+            $this->info[$element]->attr = array(
+                0 => array('Common'),
+                'cite' => 'URI',
+                // 'datetime' => 'Datetime' // Datetime not implemented
+            );
+            // Inline context ! Block context (exclamation mark is
+            // separator, see getChildDef for parsing)
+            $this->info[$element]->content_model =
+                '#PCDATA | Inline ! #PCDATA | Flow';
+            // HTML 4.01 specifies that ins/del must not contain block
+            // elements when used in an inline context, chameleon is
+            // a complicated workaround to acheive this effect
+            $this->info[$element]->content_model_type = 'chameleon';
+        }
+    }
+    
+    var $defines_child_def = true;
+    function getChildDef($def) {
+        if ($def->content_model_type != 'chameleon') return false;
+        $value = explode('!', $def->content_model);
+        return new HTMLPurifier_ChildDef_Chameleon($value[0], $value[1]);
+    }
+    
+}
+
+?>

library/HTMLPurifier/HTMLModule/Hypertext.php

@@ -0,0 +1,36 @@
+<?php
+
+require_once 'HTMLPurifier/HTMLModule.php';
+require_once 'HTMLPurifier/AttrDef/HTML/LinkTypes.php';
+
+/**
+ * XHTML 1.1 Hypertext Module, defines hypertext links. Core Module.
+ */
+class HTMLPurifier_HTMLModule_Hypertext extends HTMLPurifier_HTMLModule
+{
+    
+    var $name = 'Hypertext';
+    var $elements = array('a');
+    var $content_sets = array('Inline' => 'a');
+    
+    function HTMLPurifier_HTMLModule_Hypertext() {
+        $this->info['a'] = new HTMLPurifier_ElementDef();
+        $this->info['a']->attr = array(
+            0 => array('Common'),
+            // 'accesskey' => 'Character',
+            // 'charset' => 'Charset',
+            'href' => 'URI',
+            //'hreflang' => 'LanguageCode',
+            'rel' => new HTMLPurifier_AttrDef_HTML_LinkTypes('rel'),
+            'rev' => new HTMLPurifier_AttrDef_HTML_LinkTypes('rev'),
+            //'tabindex' => 'Number',
+            //'type' => 'ContentType',
+        );
+        $this->info['a']->content_model = '#PCDATA | Inline';
+        $this->info['a']->content_model_type = 'optional';
+        $this->info['a']->excludes = array('a' => true);
+    }
+    
+}
+
+?>

library/HTMLPurifier/HTMLModule/Image.php

@@ -0,0 +1,37 @@
+<?php
+
+require_once 'HTMLPurifier/HTMLModule.php';
+
+require_once 'HTMLPurifier/AttrDef/URI.php';
+require_once 'HTMLPurifier/AttrTransform/ImgRequired.php';
+
+/**
+ * XHTML 1.1 Image Module provides basic image embedding.
+ * @note There is specialized code for removing empty images in
+ *       HTMLPurifier_Strategy_RemoveForeignElements
+ */
+class HTMLPurifier_HTMLModule_Image extends HTMLPurifier_HTMLModule
+{
+    
+    var $name = 'Image';
+    var $elements = array('img');
+    var $content_sets = array('Inline' => 'img');
+    
+    function HTMLPurifier_HTMLModule_Image() {
+        $this->info['img'] = new HTMLPurifier_ElementDef();
+        $this->info['img']->attr = array(
+            0 => array('Common'),
+            'alt' => 'Text',
+            'height' => 'Length',
+            'longdesc' => 'URI', 
+            'src' => new HTMLPurifier_AttrDef_URI(true), // embedded
+            'width' => 'Length'
+        );
+        $this->info['img']->content_model_type = 'empty';
+        $this->info['img']->attr_transform_post[] =
+            new HTMLPurifier_AttrTransform_ImgRequired();
+    }
+    
+}
+
+?>

library/HTMLPurifier/HTMLModule/Legacy.php

@@ -0,0 +1,60 @@
+<?php
+
+/**
+ * XHTML 1.1 Legacy module defines elements that were previously 
+ * deprecated.
+ * 
+ * @note Not all legacy elements have been implemented yet, which
+ *       is a bit of a reverse problem as compared to browsers! In
+ *       addition, this legacy module may implement a bit more than
+ *       mandated by XHTML 1.1.
+ * 
+ * This module can be used in combination with TransformToStrict in order
+ * to transform as many deprecated elements as possible, but retain
+ * questionably deprecated elements that do not have good alternatives
+ * as well as transform elements that don't have an implementation.
+ * See docs/ref-strictness.txt for more details.
+ */
+
+class HTMLPurifier_HTMLModule_Legacy extends HTMLPurifier_HTMLModule
+{
+    
+    // incomplete
+    
+    var $name = 'Legacy';
+    var $elements = array('u', 's', 'strike');
+    var $non_standalone_elements = array('li', 'ol', 'address', 'blockquote');
+    
+    function HTMLPurifier_HTMLModule_Legacy() {
+        // setup new elements
+        foreach ($this->elements as $name) {
+            $this->info[$name] = new HTMLPurifier_ElementDef();
+            // for u, s, strike, as more elements get added, add
+            // conditionals as necessary
+            $this->info[$name]->content_model = 'Inline | #PCDATA';
+            $this->info[$name]->content_model_type = 'optional';
+            $this->info[$name]->attr[0] = array('Common');
+        }
+        
+        // setup modifications to old elements
+        foreach ($this->non_standalone_elements as $name) {
+            $this->info[$name] = new HTMLPurifier_ElementDef();
+            $this->info[$name]->standalone = false;
+        }
+        
+        $this->info['li']->attr['value'] = new HTMLPurifier_AttrDef_Integer();
+        $this->info['ol']->attr['start'] = new HTMLPurifier_AttrDef_Integer();
+        
+        $this->info['address']->content_model = 'Inline | #PCDATA | p';
+        $this->info['address']->content_model_type = 'optional';
+        $this->info['address']->child = false;
+        
+        $this->info['blockquote']->content_model = 'Flow | #PCDATA';
+        $this->info['blockquote']->content_model_type = 'optional';
+        $this->info['blockquote']->child = false;
+        
+    }
+    
+}
+
+?>

library/HTMLPurifier/HTMLModule/List.php

@@ -0,0 +1,46 @@
+<?php
+
+require_once 'HTMLPurifier/HTMLModule.php';
+
+/**
+ * XHTML 1.1 List Module, defines list-oriented elements. Core Module.
+ */
+class HTMLPurifier_HTMLModule_List extends HTMLPurifier_HTMLModule
+{
+    
+    var $name = 'List';
+    var $elements = array('dl', 'dt', 'dd', 'ol', 'ul', 'li');
+    
+    // According to the abstract schema, the List content set is a fully formed
+    // one or more expr, but it invariably occurs in an optional declaration
+    // so we're not going to do that subtlety. It might cause trouble
+    // if a user defines "List" and expects that multiple lists are
+    // allowed to be specified, but then again, that's not very intuitive.
+    // Furthermore, the actual XML Schema may disagree. Regardless,
+    // we don't have support for such nested expressions without using
+    // the incredibly inefficient and draconic Custom ChildDef.
+    var $content_sets = array('List' => 'dl | ol | ul', 'Flow' => 'List');
+    
+    function HTMLPurifier_HTMLModule_List() {
+        foreach ($this->elements as $element) {
+            $this->info[$element] = new HTMLPurifier_ElementDef();
+            $this->info[$element]->attr = array(0 => array('Common'));
+            if ($element == 'li' || $element == 'dd') {
+                $this->info[$element]->content_model = '#PCDATA | Flow';
+                $this->info[$element]->content_model_type = 'optional';
+            } elseif ($element == 'ol' || $element == 'ul') {
+                $this->info[$element]->content_model = 'li';
+                $this->info[$element]->content_model_type = 'required';
+            }
+        }
+        $this->info['dt']->content_model = '#PCDATA | Inline';
+        $this->info['dt']->content_model_type = 'optional';
+        $this->info['dl']->content_model = 'dt | dd';
+        $this->info['dl']->content_model_type = 'required';
+        // this could be a LOT more robust
+        $this->info['li']->auto_close = array('li' => true);
+    }
+    
+}
+
+?>