Finish up with a few more files that didn't get updated. Hrmm..

git-svn-id: http://htmlpurifier.org/svnroot/htmlpurifier/branches/strict@1181 48356398-32a2-884e-a903-53898d9a118a

Doxyfile

@@ -4,7 +4,7 @@
 # Project related configuration options
 #---------------------------------------------------------------------------
 PROJECT_NAME           = HTML Purifier
-PROJECT_NUMBER         = 1.5.0
+PROJECT_NUMBER         = 2.0.0
 OUTPUT_DIRECTORY       = "C:/Documents and Settings/Edward/My Documents/My Webs/htmlpurifier/docs/doxygen"
 CREATE_SUBDIRS         = NO
 OUTPUT_LANGUAGE        = English

INSTALL

@@ -1,4 +1,3 @@
-
 Install
     How to install HTML Purifier
 
@@ -8,13 +7,13 @@ installation GUI, you've come to the wrong place!)  The impatient can scroll
 down to the bottom of this INSTALL document to see the code, but you really
 should make sure a few things are properly done.
 
-Todo: Convert to using the array syntax for configuration.
+
 
 
 1.  Compatibility
 
-HTML Purifier works in both PHP 4 and PHP 5, from PHP 4.3.9 and up. It has no
-core dependencies with other libraries. (Whoopee!)
+HTML Purifier works in both PHP 4 and PHP 5, from PHP 4.3.2 and up. It has no
+core dependencies with other libraries.
 
 Optional extensions are iconv (usually installed) and tidy (also common).
 If you use UTF-8 and don't plan on pretty-printing HTML, you can get away with
@@ -47,7 +46,10 @@ 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
+* XHTML 1.1 sans Ruby
 
 ...and these character encodings:
 
@@ -66,11 +68,11 @@ the doctype from this code in your HTML documents:
     <meta http-equiv="Content-type" content="text/html;charset=ENCODING">
 
 For legacy codebases these declarations may be missing.  If that is the case,
-STOP, and read up on character encodings and doctypes (in that order).  Here
-are some links:
+STOP, and read docs/enduser-utf8.html
+
+
+
 
-* http://www.joelonsoftware.com/articles/Unicode.html
-* http://alistapart.com/stories/doctype/
 
 You may currently be vulnerable to XSS and other security threats, and HTML
 Purifier won't be able to fix that.
@@ -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();
@@ -114,34 +116,37 @@ websites):
 
 Note that HTML Purifier's support for non-Unicode encodings is crippled by the
 fact that any character not supported by that encoding will be silently
-dropped, EVEN if it is ampersand escaped.  This is a current limitation of
-HTML Purifier that we are NOT actively working to fix.  Patches are welcome,
-but there are so many other gotchas and problems in I18N for non-Unicode
-encodings that this functionality is low priority.  See
-<http://ppewww.ph.gla.ac.uk/~flavell/charset/form-i18n.html> for a more
-detailed lowdown on the topic.
+dropped, EVEN if it is ampersand escaped.  If you want to work around
+this, you are welcome to read docs/enduser-utf8.html for a workaround,
+but please be cognizant of the issues the "solution" creates.
+
+
+
 
 
 
 4.2. Setting a different doctype
 
-For those of you stuck using HTML 4.01 Transitional, you can disable
+For those of you using HTML 4.01 Transitional, you can disable
 XHTML output like this:
 
-    $config->set('Core', 'XHTML', false);
+    $config->set('HTML', 'Doctype', 'HTML 4.01 Transitional');
 
-I recommend that you use XHTML, although not as much as I recommend UTF-8.  If
-your HTML 4.01 page validates, good for you!
+Other supported doctypes include:
 
-Currently, we can only guarantee transitional-complaint output, future
-versions will also allow strict-compliant output.
+
+    * HTML 4.01 Strict
+    * HTML 4.01 Transitional
+    * XHTML 1.0 Strict
+    * XHTML 1.0 Transitional
+    * XHTML 1.1
 
 
 
 4.3. Other settings
 
 There are more configuration directives which can be read about
-here: <http://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.
 
@@ -182,9 +187,17 @@ If your website is in a different encoding or doctype, use this code:
     require_once '/path/to/htmlpurifier/library/HTMLPurifier.auto.php';
     
     $config = HTMLPurifier_Config::createDefault();
-    $config->set('Core', 'Encoding', 'ISO-8859-1'); //replace with your encoding
-    $config->set('Core', 'XHTML', true); //replace with false if HTML 4.01
+    $config->set('Core', 'Encoding', 'ISO-8859-1'); // replace with your encoding
+    $config->set('HTML', 'Doctype', 'HTML 4.01 Transitional'); // replace with your doctype
     $purifier = new HTMLPurifier($config);
     
     $clean_html = $purifier->purify($dirty_html);
-?>
+?>
+
+
+
+7. Caching
+
+HTML Purifier generates some cache files to speed up its execution. For
+maximum performance, make sure that library/HTMLPurifier/DefinitionCache/Serializer
+is writeable by the webserver.

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 4.3.2 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 +9,117 @@ NEWS ( CHANGELOG and HISTORY )                                     HTMLPurifier
     . Internal change
 ==========================
 
+2.0.0, released 2007-06-20
+# Completely refactored HTMLModuleManager, decentralizing safety
+  information
+# Transform modules changed to Tidy modules, which offer more flexibility
+  and better modularization
+# Configuration object now finalizes itself when a read operation is
+  performed on it, ensuring that its internal state stays consistent.
+  To revert this behavior, you can set the $autoFinalize member variable 
+  off, but it's not recommended.
+# New compact syntax for AttrDef objects that can be used to instantiate
+  new objects via make()
+# Definitions (esp. HTMLDefinition) are now cached for a significant
+  performance boost. You can disable caching by setting %Core.DefinitionCache
+  to null. You CANNOT edit raw definitions without setting the corresponding
+  DefinitionID directive (%HTML.DefinitionID for HTMLDefinition).
+# Contents between <script> tags are now completely removed if <script>
+  is not allowed
+# Prototype-declarations for Lexer removed in favor of configuration
+  determination of Lexer implementations.
+! HTML Purifier now works in PHP 4.3.2.
+! Configuration form-editing API makes tweaking HTMLPurifier_Config a
+  breeze!
+! Configuration directives that accept hashes now allow new string
+  format: key1:value1,key2:value2
+! ConfigDoc now factored into OOP design
+! All deprecated elements now natively supported
+! Implement TinyMCE styled whitelist specification format in
+  %HTML.Allowed
+! Config object gives more friendly error messages when things go wrong
+! Advanced API implemented: easy functions for creating elements (addElement)
+  and attributes (addAttribute) on HTMLDefinition
+! Add native support for required attributes
+- Deprecated and removed EnableRedundantUTF8Cleaning. It didn't even work!
+- DOMLex will not emit errors when a custom error handler that does not
+  honor error_reporting is used
+- StrictBlockquote child definition refrains from wrapping whitespace
+  in tags now.
+- Bug resulting from tag transforms to non-allowed elements fixed
+- ChildDef_Custom's regex generation has been improved, removing several
+  false positives
+. Unit test for ElementDef created, ElementDef behavior modified to
+  be more flexible
+. Added convenience functions for HTMLModule constructors
+. AttrTypes now has accessor functions that should be used instead
+  of directly manipulating info
+. TagTransform_Center deprecated in favor of generic TagTransform_Simple
+. Add extra protection in AttrDef_URI against phantom Schemes
+. Doctype object added to HTMLDefinition which describes certain aspects
+  of the operational document type
+. Lexer is now pre-emptively included, with a conditional include for the
+  PHP5 only version.
+. HTMLDefinition and CSSDefinition have a common parent class: Definition.
+. DirectLex can now track line-numbers
+. Preliminary error collector is in place, although no code actually reports
+  errors yet
+. Factor out most of ValidateAttributes to new AttrValidator class
+
+1.6.1, released 2007-05-05
+! Support for more deprecated attributes via transformations:
+  + hspace and vspace in img
+  + size and noshade in hr
+  + nowrap in td
+  + clear in br
+  + align in caption, table, img and hr
+  + type in ul, ol and li
+! DirectLex now preserves text in which a < bracket is followed by
+  a non-alphanumeric character. This means that certain emoticons
+  are now preserved.
+! %Core.RemoveInvalidImg is now operational, when set to false invalid
+  images will hang around with an empty src
+! target attribute in a tag supported, use %Attr.AllowedFrameTargets
+  to enable
+! CSS property white-space now allows nowrap (supported in all modern
+  browsers) but not others (which have spotty browser implementations)
+! XHTML 1.1 mode now sort-of works without any fatal errors, and
+  lang is now moved over to xml:lang.
+! Attribute transformation smoketest available at smoketests/attrTransform.php
+! Transformation of font's size attribute now handles super-large numbers
+- Possibly fatal bug with __autoload() fixed in module manager
+- Invert HTMLModuleManager->addModule() processing order to check
+  prefixes first and then the literal module
+- Empty strings get converted to empty arrays instead of arrays with
+  an empty string in them.
+- Merging in attribute lists now works.
+. Demo script removed: it has been added to the website's repository
+. Basic.php script modified to work out of the box
+. Refactor AttrTransform classes to reduce duplication
+. AttrTransform_TextAlign axed in favor of a more general
+  AttrTransform_EnumToCSS, refer to HTMLModule/TransformToStrict.php to
+  see how the new equivalent is implemented
+. Unit tests now use exclusively assertIdentical
+ 
+1.6.0, released 2007-04-01
+! Support for most common deprecated attributes via transformations:
+  + bgcolor in td, th, tr and table
+  + border in img
+  + name in a and img
+  + width in td, th and hr
+  + height in td, th
+! Support for CSS attribute 'height' added
+! Support for rel and rev attributes in a tags added, use %Attr.AllowedRel
+  and %Attr.AllowedRev to activate
+- You can define ID blacklists using regular expressions via
+  %Attr.IDBlacklistRegexp
+- Error messages are emitted when you attempt to "allow" elements or
+  attributes that HTML Purifier does not support
+
+
+- Fix segfault in unit test. The problem is not very reproduceable and
+  I don't know what causes it, but a six line patch fixed it.
+
 1.5.0, released 2007-03-23
 ! Added a rudimentary I18N and L10N system modeled off MediaWiki. It
   doesn't actually do anything yet, but keep your eyes peeled.
@@ -204,4 +315,4 @@ NEWS ( CHANGELOG and HISTORY )                                     HTMLPurifier
 ! First public release, most functionality implemented. Notable omissions are:
   + Shorthand CSS properties
   + Table CSS properties
-  + Deprecated attribute transformations
+  + Deprecated attribute transformations

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

@@ -1,36 +1,39 @@
-
 TODO List
 
 = KEY ====================
     # Flagship
     - Regular
-    ? At-risk
+    ? Maybe I'll Do It
 ==========================
 
-1.6 release
- # Implement all non-essential attribute transforms, configurable
+2.1 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
+ - Genericize special cases in RemoveForeignElements
+
+2.2 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
- - Implement IDREF support
-
-1.7 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
 
-1.8 release
+
+
+
+
+2.3 release [Do What I Mean, Not What I Say]
  # Additional support for poorly written HTML
     - Microsoft Word HTML cleaning (i.e. MsoNormal, but research essential!)
     - Friendly strict handling of <address> (block -> <br>)
@@ -45,41 +48,53 @@ 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
+2.4 release [It's All About Trust] (floating)
+ # Implement untrusted, dangerous elements/attributes
+
+3.0 release [Beyond HTML]
  # Legit token based CSS parsing (will require revamping almost every
    AttrDef class)
+ # More control over allowed CSS properties (maybe modularize it in the
+   same fashion!)
  # Formatters for plaintext (COMPLEX)
     - Auto-paragraphing (be sure to leverage fact that we know when things
       shouldn't be paragraphed, such as lists and tables).
     - 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
 
+4.0 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)
+ - Complete basic smoketests
 
 Unknown release (on a scratch-an-itch basis)
- - 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
+ - Abstract ChildDef_BlockQuote to work with all elements that only
+   allow blocks in them, required or optional
+ - Reorganize Unit Tests
+    - Refactor loop tests (esp. AttrDef_URI)
+ - Reorganize configuration directives (Create more namespaces! Get messy!)
 
 Requested
  ? Native content compression, whitespace stripping (don't rely on Tidy, make
@@ -88,4 +103,4 @@ Requested
 Wontfix
  - Non-lossy smart alternate character encoding transformations (unless
    patch provided)
- - Pretty-printing HTML, users can use Tidy on the output on entire page
+ - Pretty-printing HTML, users can use Tidy on the output on entire page

VERSION

@@ -0,0 +1 @@
+2.0.0

WHATSNEW

@@ -0,0 +1,7 @@
+HTML Purifier 2.0 is the culmination of two major architectural changes. 
+The first is Tidy, which enables HTML Purifier to both natively support 
+deprecated elements and also convert them to standards-compliant 
+alternatives. The second is the Advanced API, which enables users to 
+create new elements and attributes with ease. Keeping in line with a 
+commitment to high quality, there are also five esoteric bug-fixes and a 
+plethora of subtle improvements that enhance the library. 

WYSIWYG

@@ -16,7 +16,3 @@ trouble.  Therein lies the solution:
 HTML Purifier is perfect for filtering pure-HTML input from WYSIWYG editors.
 
 Enough said.
-
-There is a proof-of-concept integration of HTML Purifier with the Mantis
-bugtracker at http://hp.jpsband.org/mantis/ You can see notes on how
-this integration was acheived at http://hp.jpsband.org/mantis_notes.txt

configdoc/generate.php

@@ -2,217 +2,37 @@
 
 /**
  * Generates XML and HTML documents describing configuration.
+ * @note PHP 5 only!
  */
 
 /*
 TODO:
-- make XML format richer (see below)
+- make XML format richer (see XMLSerializer_ConfigSchema)
 - extend XSLT transformation (see the corresponding XSLT file)
 - allow generation of packaged docs that can be easily moved
 - multipage documentation
 - determine how to multilingualize
-- factor out code into classes
+- add blurbs to ToC
 */
 
-// ---------------------------------------------------------------------------
-// Check and configure environment
-
 if (version_compare('5', PHP_VERSION, '>')) exit('Requires PHP 5 or higher.');
-error_reporting(E_ALL);
+error_reporting(E_ALL); // probably not possible to use E_STRICT
 
-
-// ---------------------------------------------------------------------------
-// Include HTML Purifier library
-
-set_include_path('../library' . PATH_SEPARATOR . get_include_path());
-require_once 'HTMLPurifier.php';
-
-
-// ---------------------------------------------------------------------------
-// Setup convenience functions
-
-function appendHTMLDiv($document, $node, $html) {
-    global $purifier;
-    $html = $purifier->purify($html);
-    $dom_html = $document->createDocumentFragment();
-    $dom_html->appendXML($html);
-    
-    $dom_div = $document->createElement('div');
-    $dom_div->setAttribute('xmlns', 'http://www.w3.org/1999/xhtml');
-    $dom_div->appendChild($dom_html);
-    
-    $node->appendChild($dom_div);
-}
-
-
-// ---------------------------------------------------------------------------
-// Load copies of HTMLPurifier_ConfigDef and HTMLPurifier
+// load dual-libraries
+require_once '../library/HTMLPurifier.auto.php';
+require_once 'library/ConfigDoc.auto.php';
 
 $schema = HTMLPurifier_ConfigSchema::instance();
-$purifier = new HTMLPurifier();
+$style = 'plain'; // use $_GET in the future
+$configdoc = new ConfigDoc();
+$output = $configdoc->generate($schema, $style);
 
-
-// ---------------------------------------------------------------------------
-// Generate types.xml, a document describing the constraint "type"
-
-$types_document = new DOMDocument('1.0', 'UTF-8');
-$types_root = $types_document->createElement('types');
-$types_document->appendChild($types_root);
-$types_document->formatOutput = true;
-foreach ($schema->types as $name => $expanded_name) {
-    $types_type = $types_document->createElement('type', $expanded_name);
-    $types_type->setAttribute('id', $name);
-    $types_root->appendChild($types_type);
-}
-$types_document->save('types.xml');
-
-
-// ---------------------------------------------------------------------------
-// Generate configdoc.xml, a document documenting configuration directives
-
-$dom_document = new DOMDocument('1.0', 'UTF-8');
-$dom_root = $dom_document->createElement('configdoc');
-$dom_document->appendChild($dom_root);
-$dom_document->formatOutput = true;
-
-// add the name of the application
-$dom_root->appendChild($dom_document->createElement('title', 'HTML Purifier'));
-
-/*
-TODO for XML format:
-- create a definition (DTD or other) once interface stabilizes
-*/
-
-foreach($schema->info as $namespace_name => $namespace_info) {
-    
-    $dom_namespace = $dom_document->createElement('namespace');
-    $dom_root->appendChild($dom_namespace);
-    
-    $dom_namespace->setAttribute('id', $namespace_name);
-    $dom_namespace->appendChild(
-        $dom_document->createElement('name', $namespace_name)
-    );
-    $dom_namespace_description = $dom_document->createElement('description');
-    $dom_namespace->appendChild($dom_namespace_description);
-    appendHTMLDiv($dom_document, $dom_namespace_description,
-        $schema->info_namespace[$namespace_name]->description);
-    
-    foreach ($namespace_info as $name => $info) {
-        
-        if ($info->class == 'alias') continue;
-        
-        $dom_directive = $dom_document->createElement('directive');
-        $dom_namespace->appendChild($dom_directive);
-        
-        $dom_directive->setAttribute('id', $namespace_name . '.' . $name);
-        $dom_directive->appendChild(
-            $dom_document->createElement('name', $name)
-        );
-        
-        $dom_constraints = $dom_document->createElement('constraints');
-        $dom_directive->appendChild($dom_constraints);
-        
-        $dom_type = $dom_document->createElement('type', $info->type);
-        if ($info->allow_null) {
-            $dom_type->setAttribute('allow-null', 'yes');
-        }
-        $dom_constraints->appendChild($dom_type);
-        
-        if ($info->allowed !== true) {
-            $dom_allowed = $dom_document->createElement('allowed');
-            $dom_constraints->appendChild($dom_allowed);
-            foreach ($info->allowed as $allowed => $bool) {
-                $dom_allowed->appendChild(
-                    $dom_document->createElement('value', $allowed)
-                );
-            }
-        }
-        
-        $raw_default = $schema->defaults[$namespace_name][$name];
-        if (is_bool($raw_default)) {
-            $default = $raw_default ? 'true' : 'false';
-        } elseif (is_string($raw_default)) {
-            $default = "\"$raw_default\"";
-        } elseif (is_null($raw_default)) {
-            $default = 'null';
-        } else {
-            $default = print_r(
-                    $schema->defaults[$namespace_name][$name], true
-                );
-        }
-        
-        $dom_default = $dom_document->createElement('default', $default);
-        
-        // remove this once we get a DTD
-        $dom_default->setAttribute('xml:space', 'preserve');
-        
-        $dom_constraints->appendChild($dom_default);
-        
-        $dom_descriptions = $dom_document->createElement('descriptions');
-        $dom_directive->appendChild($dom_descriptions);
-        
-        foreach ($info->descriptions as $file => $file_descriptions) {
-            foreach ($file_descriptions as $line => $description) {
-                $dom_description = $dom_document->createElement('description');
-                $dom_description->setAttribute('file', $file);
-                $dom_description->setAttribute('line', $line);
-                appendHTMLDiv($dom_document, $dom_description, $description);
-                $dom_descriptions->appendChild($dom_description);
-            }
-        }
-        
-    }
-    
-}
-
-// print_r($dom_document->saveXML());
-
-// save a copy of the raw XML
-$dom_document->save('configdoc.xml');
-
-
-// ---------------------------------------------------------------------------
-// Generate final output using XSLT
-
-// load the stylesheet
-$xsl_stylesheet_name = 'plain';
-$xsl_stylesheet = "styles/$xsl_stylesheet_name.xsl";
-$xsl_dom_stylesheet = new DOMDocument();
-$xsl_dom_stylesheet->load($xsl_stylesheet);
-
-// setup the XSLT processor
-$xsl_processor = new XSLTProcessor();
-
-// perform the transformation
-$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(' xmlns=""', '', $html_output); // rm unnecessary xmlns
-
-if (class_exists('Tidy')) {
-    // cleanup output
-    $config = array(
-        'indent'        => true,
-        'output-xhtml'  => true,
-        'wrap'          => 80
-    );
-    $tidy = new Tidy;
-    $tidy->parseString($html_output, $config, 'utf8');
-    $tidy->cleanRepair();
-    $html_output = (string) $tidy;
-}
-
-// write it to a file (todo: parse into seperate pages)
-file_put_contents("$xsl_stylesheet_name.html", $html_output);
-
-
-// ---------------------------------------------------------------------------
-// Output for instant feedback
+// write out
+file_put_contents("$style.html", $output);
 
 if (php_sapi_name() != 'cli') {
-    echo $html_output;
+    // output = instant feedback
+    echo $output;
 } else {
     echo 'Files generated successfully.';
 }

configdoc/library/ConfigDoc.auto.php

@@ -0,0 +1,10 @@
+<?php
+
+/**
+ * This is a stub include that automatically configures the include path.
+ */
+
+set_include_path(dirname(__FILE__) . PATH_SEPARATOR . get_include_path() );
+require_once 'ConfigDoc.php';
+
+?>

configdoc/library/ConfigDoc.php

@@ -0,0 +1,39 @@
+<?php
+
+require_once 'ConfigDoc/HTMLXSLTProcessor.php';
+require_once 'ConfigDoc/XMLSerializer/Types.php';
+require_once 'ConfigDoc/XMLSerializer/ConfigSchema.php';
+
+class ConfigDoc
+{
+    
+    function generate($schema, $xsl_stylesheet_name = 'plain', $parameters = array()) {
+        // generate types document, describing type constraints
+        $types_serializer = new ConfigDoc_XMLSerializer_Types();
+        $types_document = $types_serializer->serialize($schema);
+        $types_document->save(dirname(__FILE__) . '/../types.xml'); // only ONE
+        
+        // generate configdoc.xml, documents configuration directives
+        $schema_serializer = new ConfigDoc_XMLSerializer_ConfigSchema();
+        $schema_document = $schema_serializer->serialize($schema);
+        $schema_document->save('configdoc.xml');
+        
+        // setup transformation
+        $xsl_stylesheet = dirname(__FILE__) . "/../styles/$xsl_stylesheet_name.xsl";
+        $xslt_processor = new ConfigDoc_HTMLXSLTProcessor();
+        $xslt_processor->setParameters($parameters);
+        $xslt_processor->importStylesheet($xsl_stylesheet);
+        
+        return $xslt_processor->transformToHTML($schema_document);
+    }
+    
+    /**
+     * Remove any generated files
+     */
+    function cleanup() {
+        unlink('configdoc.xml');
+    }
+    
+}
+
+?>

configdoc/library/ConfigDoc/HTMLXSLTProcessor.php

@@ -0,0 +1,62 @@
+<?php
+
+/**
+ * Special XSLTProcessor specifically for HTML documents. Loosely
+ * based off of XSLTProcessor, but not really
+ */
+class ConfigDoc_HTMLXSLTProcessor
+{
+    
+    protected $xsltProcessor;
+    
+    public function __construct() {
+        $this->xsltProcessor = new XSLTProcessor();
+    }
+    
+    /**
+     * Imports stylesheet for processor to use
+     * @param $xsl XSLT DOM tree, or filename of the XSL transformation
+     */
+    public function importStylesheet($xsl) {
+        if (is_string($xsl)) {
+            $xsl_file = $xsl;
+            $xsl = new DOMDocument();
+            $xsl->load($xsl_file);
+        }
+        return $this->xsltProcessor->importStylesheet($xsl);
+    }
+    
+    /**
+     * Transforms an XML file into HTML based on the stylesheet
+     * @param $xml XML DOM tree
+     */
+    public function transformToHTML($xml) {
+        $out = $this->xsltProcessor->transformToXML($xml);
+        
+        // fudges for HTML backwards compatibility
+        $out = str_replace('/>', ' />', $out); // <br /> not <br/>
+        $out = str_replace(' xmlns=""', '', $out); // rm unnecessary xmlns
+        if (class_exists('Tidy')) {
+            // cleanup output
+            $config = array(
+                'indent'        => true,
+                'output-xhtml'  => true,
+                'wrap'          => 80
+            );
+            $tidy = new Tidy;
+            $tidy->parseString($out, $config, 'utf8');
+            $tidy->cleanRepair();
+            $out = (string) $tidy;
+        }
+        return $out;
+    }
+    
+    public function setParameters($options) {
+        foreach ($options as $name => $value) {
+            $this->xsltProcessor->setParameter('', $name, $value);
+        }
+    }
+    
+}
+
+?>

configdoc/library/ConfigDoc/XMLSerializer.php

@@ -0,0 +1,26 @@
+<?php
+
+/**
+ * The XMLSerializer hierarchy of classes consist of classes that take
+ * objects and serialize them into XML, specifically DOM, form; this
+ * super-class contains convenience functions for those classes.
+ */
+class ConfigDoc_XMLSerializer
+{
+    
+    protected function appendHTMLDiv($document, $node, $html) {
+        $purifier = HTMLPurifier::getInstance();
+        $html = $purifier->purify($html);
+        $dom_html = $document->createDocumentFragment();
+        $dom_html->appendXML($html);
+        
+        $dom_div = $document->createElement('div');
+        $dom_div->setAttribute('xmlns', 'http://www.w3.org/1999/xhtml');
+        $dom_div->appendChild($dom_html);
+        
+        $node->appendChild($dom_div);
+    }
+    
+}
+
+?>

configdoc/library/ConfigDoc/XMLSerializer/ConfigSchema.php

@@ -0,0 +1,118 @@
+<?php
+
+require_once 'ConfigDoc/XMLSerializer.php';
+
+class ConfigDoc_XMLSerializer_ConfigSchema extends ConfigDoc_XMLSerializer
+{
+    
+    /**
+     * Serializes a schema into DOM form
+     * @todo Split into sub-serializers
+     * @param $schema HTMLPurifier_ConfigSchema to serialize
+     */
+    public function serialize($schema) {
+        $dom_document = new DOMDocument('1.0', 'UTF-8');
+        $dom_root = $dom_document->createElement('configdoc');
+        $dom_document->appendChild($dom_root);
+        $dom_document->formatOutput = true;
+        
+        // add the name of the application
+        $dom_root->appendChild($dom_document->createElement('title', 'HTML Purifier'));
+        
+        /*
+        TODO for XML format:
+        - create a definition (DTD or other) once interface stabilizes
+        */
+        
+        foreach($schema->info as $namespace_name => $namespace_info) {
+            
+            $dom_namespace = $dom_document->createElement('namespace');
+            $dom_root->appendChild($dom_namespace);
+            
+            $dom_namespace->setAttribute('id', $namespace_name);
+            $dom_namespace->appendChild(
+                $dom_document->createElement('name', $namespace_name)
+            );
+            $dom_namespace_description = $dom_document->createElement('description');
+            $dom_namespace->appendChild($dom_namespace_description);
+            $this->appendHTMLDiv($dom_document, $dom_namespace_description,
+                $schema->info_namespace[$namespace_name]->description);
+            
+            foreach ($namespace_info as $name => $info) {
+                
+                if ($info->class == 'alias') continue;
+                
+                $dom_directive = $dom_document->createElement('directive');
+                $dom_namespace->appendChild($dom_directive);
+                
+                $dom_directive->setAttribute('id', $namespace_name . '.' . $name);
+                $dom_directive->appendChild(
+                    $dom_document->createElement('name', $name)
+                );
+                
+                $dom_constraints = $dom_document->createElement('constraints');
+                $dom_directive->appendChild($dom_constraints);
+                
+                $dom_type = $dom_document->createElement('type', $info->type);
+                if ($info->allow_null) {
+                    $dom_type->setAttribute('allow-null', 'yes');
+                }
+                $dom_constraints->appendChild($dom_type);
+                
+                if ($info->allowed !== true) {
+                    $dom_allowed = $dom_document->createElement('allowed');
+                    $dom_constraints->appendChild($dom_allowed);
+                    foreach ($info->allowed as $allowed => $bool) {
+                        $dom_allowed->appendChild(
+                            $dom_document->createElement('value', $allowed)
+                        );
+                    }
+                }
+                
+                $raw_default = $schema->defaults[$namespace_name][$name];
+                if (is_bool($raw_default)) {
+                    $default = $raw_default ? 'true' : 'false';
+                } elseif (is_string($raw_default)) {
+                    $default = "\"$raw_default\"";
+                } elseif (is_null($raw_default)) {
+                    $default = 'null';
+                } else {
+                    $default = print_r(
+                            $schema->defaults[$namespace_name][$name], true
+                        );
+                }
+                
+                $dom_default = $dom_document->createElement('default', $default);
+                
+                // remove this once we get a DTD
+                $dom_default->setAttribute('xml:space', 'preserve');
+                
+                $dom_constraints->appendChild($dom_default);
+                
+                $dom_descriptions = $dom_document->createElement('descriptions');
+                $dom_directive->appendChild($dom_descriptions);
+                
+                foreach ($info->descriptions as $file => $file_descriptions) {
+                    foreach ($file_descriptions as $line => $description) {
+                        $dom_description = $dom_document->createElement('description');
+                        // refuse to write $file if it's a full path
+                        if (str_replace('\\', '/', realpath($file)) != $file) {
+                            $dom_description->setAttribute('file', $file);
+                            $dom_description->setAttribute('line', $line);
+                        }
+                        $this->appendHTMLDiv($dom_document, $dom_description, $description);
+                        $dom_descriptions->appendChild($dom_description);
+                    }
+                }
+                
+            }
+            
+        }
+        
+        return $dom_document;
+        
+    }
+    
+}
+
+?>

configdoc/library/ConfigDoc/XMLSerializer/Types.php

@@ -0,0 +1,27 @@
+<?php
+
+require_once 'ConfigDoc/XMLSerializer.php';
+
+class ConfigDoc_XMLSerializer_Types extends ConfigDoc_XMLSerializer
+{
+    
+    /**
+     * Serializes the types in a schema into DOM form
+     * @param $schema HTMLPurifier_ConfigSchema owner of types to serialize
+     */
+    public function serialize($schema) {
+        $types_document = new DOMDocument('1.0', 'UTF-8');
+        $types_root = $types_document->createElement('types');
+        $types_document->appendChild($types_root);
+        $types_document->formatOutput = true;
+        foreach ($schema->types as $name => $expanded_name) {
+            $types_type = $types_document->createElement('type', $expanded_name);
+            $types_type->setAttribute('id', $name);
+            $types_root->appendChild($types_type);
+        }
+        return $types_document;
+    }
+    
+}
+
+?>

configdoc/styles/plain.xsl

@@ -12,19 +12,21 @@
         indent = "no"
         media-type = "text/html"
     />
+    <xsl:param name="css" select="'styles/plain.css'"/>
+    <xsl:param name="title" select="'Configuration Documentation'"/>
     
     <xsl:variable name="typeLookup" select="document('../types.xml')" />
     
     <xsl:template match="/">
         <html lang="en" xml:lang="en">
             <head>
-                <title>Configuration Documentation - <xsl:value-of select="/configdoc/title" /></title>
+                <title><xsl:value-of select="$title" /> - <xsl:value-of select="/configdoc/title" /></title>
                 <meta http-equiv="Content-Type" content="text/html;charset=UTF-8" />
-                <link rel="stylesheet" type="text/css" href="styles/plain.css" />
+                <link rel="stylesheet" type="text/css" href="{$css}" />
             </head>
             <body>
                 <div id="library"><xsl:value-of select="/configdoc/title" /></div>
-                <h1>Configuration Documentation</h1>
+                <h1><xsl:value-of select="$title" /></h1>
                 <h2>Table of Contents</h2>
                 <ul id="toc">
                     <xsl:apply-templates mode="toc" />
@@ -76,15 +78,17 @@
         <table class="constraints">
             <xsl:apply-templates />
             <!-- Calculated other values -->
-            <tr>
-                <th>Used by:</th>
-                <td>
-                    <xsl:for-each select="../descriptions/description">
-                        <xsl:if test="position()&gt;1">, </xsl:if>
-                        <xsl:value-of select="@file" />
-                    </xsl:for-each>
-                </td>
-            </tr>
+            <xsl:if test="../descriptions/description[@file]">
+                <tr>
+                    <th>Used by:</th>
+                    <td>
+                        <xsl:for-each select="../descriptions/description">
+                            <xsl:if test="position()&gt;1">, </xsl:if>
+                            <xsl:value-of select="@file" />
+                        </xsl:for-each>
+                    </td>
+                </tr>
+            </xsl:if>
         </table>
     </xsl:template>
     <xsl:template match="directive//description">

docs/dev-advanced-api.html

@@ -14,11 +14,15 @@
 
 <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>It makes no sense to adopt a <q>one-size-fits-all</q> approach to
-filtersets: therefore, users must be able to define their own sets of
-<q>allowed</q> elements, as well as switch in-between doctypes of HTML.</p>
+<p>HTML Purifier currently natively supports only a subset of HTML's
+allowed elements, attributes, and behavior; specifically, this subset
+is the set of elements that are safe for untrusted users to use.
+However, HTML Purifier is often utilized to ensure standards-compliance
+from input that is trusted (making it a sort of Tidy substitute),
+and often users need to define new elements or attributes. The
+advanced API is oriented specifically for these use-cases.</p>
 
 <p>Our goals are to let the user:</p>
 
@@ -26,32 +30,28 @@ filtersets: therefore, users must be able to define their own sets of
     <dt>Select</dt>
     <dd><ul>
         <li>Doctype</li>
-        <li>Filtersets: Rich / Plain / Full ...</li>
-        <li>Mode: Lenient / Correctional</li>
-        <li>Collections (?): Safe / Unsafe</li>
-        <li>Modules / Tags / Attributes</li>
+        <!-- <li>Filterset</li> -->
+        <li>Elements / Attributes / Modules</li>
+        <li>Tidy</li>
     </ul></dd>
     <dt>Customize</dt>
     <dd><ul>
-        <li>Tags / Attributes / Attribute Types</li>
-        <li>Filtersets</li>
-        <li>Root Node</li>
-    </ul></dd>
-    <dt>Create</dt>
-    <dd><ul>
-        <li>Modules / Tags / Attributes / Attribute Types</li>
-        <li>Filtersets</li>
-        <li>Doctype</li>
+        <li>Attributes</li>
+        <li>Elements</li>
+        <!--<li>Doctypes</li>-->
     </ul></dd>
 </dl>
 
 <h2>Select</h2>
 
+<p>For basic use, the user will have to specify some basic parameters. This
+is not strictly necessary, as HTML Purifier's default setting will always
+output safe code, but is required for standards-compliant output.</p>
+
 <h3>Selecting a Doctype</h3>
 
-<p>By default, users will use a doctype-based, permissive but secure
-whitelist.  They must define a <strong>doctype</strong>, and this serves
-as the first method of determining a filterset.</p>
+<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>
@@ -61,127 +61,152 @@ the DTD identifier.</p>
 
 <pre>$config->set('HTML', 'Doctype', 'XHTML 1.0 Transitional');</pre>
 
-<h3>Selecting a Filterset</h3>
+<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>
 
-<p>However, selecting this doctype doesn't mean much, because if we
-adhered exactly to the definition we would be letting XSS and other
-nasties through. HTML Purifier must, in its filterset, allow a subset
-of the doctype, which we shall call a <strong>filterset</strong>.</p>
+<h3>Selecting Elements / Attributes / Modules</h3>
 
-<p>By default, HTML Purifier will use the <strong>Rich</strong>
-filterset, which allows as many elements as possible with untrusted
-sources. Other possible filtersets could be:</p>
+<p>HTML Purifier will, by default, allow as many elements and attributes
+as possible. However, a user may decide to roll their own filterset by
+selecting modules, elements and attributes to allow for their own
+specific use-case. This can be done using %HTML.Allowed:</p>
 
-<dl>
-    <dt>Full</dt>
-    <dd>Allows the full span of elements in the doctype, good if you want
-        HTML Purifier to work as a Tidy substitute but not to strip
-        anything out.</dd>
-    <dt>Plain</dt>
-    <dd>Provides a minimum set of tags for semantic markup of things
-        like blog comments.</dd>
-</dl>
+<pre>$config->set('HTML', 'Allowed', 'a[href|title],em,p,blockquote');</pre>
 
-<p>Extension-authors would be able to define custom filtersets for
-other users to use.</p>
+<p class="technical">The directive %HTML.Allowed is a convenience feature
+that may be fully expressed with the legacy interface.</p>
 
-<p>A possible call to select a filterset would be:</p>
+<p>We currently support another interface from older versions:</p>
 
-<pre>$config->set('HTML', 'Filterset', 'Rich');</pre>
+<pre>$config->set('HTML', 'AllowedElements', 'a,em,p,blockquote');
+$config->set('HTML', 'AllowedAttributes', 'a.href,a.title');</pre>
 
-<h3>Selecting Mode</h3>
+<p>A user may also choose to allow modules using a specialized
+directive:</p>
 
-<p>Within filtersets, there are various <strong>modes</strong> of operation.
-These indicate variant behaviors that, while not strictly changing the
-allowed set of elements and attributes, will definitely affect the output.
-Currently, we have two modes, which may be used together:</p>
+<pre>$config->set('HTML', 'AllowedModules', 'Hypertext,Text,Lists');</pre>
 
-<dl>
-    <dt>Lenient</dt>
-    <dd>Deprecated elements and attributes will be transformed into
-        standards-compliant alternatives when explicitly disallowed. For
-        example, in the XHTML 1.0 Strict doctype, a <code>center</code>
-        tag would be turned into a <code>div</code> with the CSS property
-        <code>text-align:center;</code>, but in XHTML 1.0 Transitional
-        the tag would be preserved. This mode is on by default.</dd>
-    <dt>Correctional</dt>
-    <dd>Deprecated elements and attributes will be transformed into
-        standards-compliant alternatives whenever possible. Referring
-        back to the previous example, the <code>center</code> tag would
-        be transformed in both cases. However, tags without a
-        reasonable standards-compliant alternative will be preserved
-        in their form. This mode is on by default. It may have
-        various levels of operation.</dd>
-</dl>
+<p>But it is not expected that this feature will be widely used.</p>
 
-<p>A possible call to select modes would be:</p>
+<p class="technical">Module selection will work slightly differently
+from the other AllowedElements and AllowedAttributes directives by
+directly modifying the doctype you are operating in, in the spirit of
+XHTML 1.1's modularization. We stop users from shooting themselves in the
+foot by mandating the modules in %HTML.CoreModules be used.</p>
 
-<pre>$config->set('HTML', 'Mode', array('correctional', 'lenient'));</pre>
+<p class="technical">Modules are distinguished from regular elements by the
+case of their first letter. While XML distinguishes between and allows
+lower and uppercase letters in element names, XHTML uses only lower-case
+element names for sake of consistency.</p>
 
-<p>If modes have extra parameters, a hash might work well:</p>
+<h3>Selecting Tidy</h3>
 
-<pre>$config->set('HTML', 'Mode', array(
-    'correctional' => 9, // strongest level
-    'lenient' => true // this one's just boolean
-));</pre>
+<p>The name of this segment of functionality is inspired off of Dave
+Ragget's program HTML Tidy, which purported to help clean up HTML. In
+HTML Purifier, Tidy functionality involves turning unsupported and
+deprecated elements into standards-compliant ones, maintaining
+backwards compatibility, and enforcing best practices.</p>
 
-<p>Modes may possibly be wrapped up with the filterset declaration:</p>
-
-<pre>$config->set('HTML', 'Filterset', 'Rich: correctional, lenient');</pre>
-
-<p>Further investigation in this field is necessary.</p>
-
-<h3>Selecting Modules / Tags / Attributes</h3>
-
-<p>If this cookie cutter approach doesn't appeal to a user, they may
-decide to roll their own filterset by selecting modules, tags and
-attributes to allow.</p>
-
-<p class="technical">This would make use of the same facilities
-as a filterset author would use, except that it would go under an
-<q>anonymous</q> filterset that would be auto-selected if any of the
-relevant module/tag/attribute selection configuration directives were
-non-null.</p>
-
-<p>On the highest level, a user will usually be most interested in
-directly specifying which elements and attributes are desired. For
-example:</p>
-
-<pre>$config->set('HTML', 'AllowedElements', 'a,b,em,p,blockquote,code,i');</pre>
-
-<p>Attribute declarations could be merged into this declaration as such:</p>
-
-<pre>$config->set('HTML', 'Allowed', 'a[href,title],b,em,p[class],blockquote[cite],code,i');</pre>
-
-<p>...or be kept separate:</p>
-
-<pre>$config->set('HTML', 'AllowedAttributes', 'a.href,a.title,p.class,blockquote.cite');</pre>
-
-<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>
-
-<p>A user may also specify a module to load a class of elements and attributes
-into their filterest:</p>
-
-<pre>$config->set('HTML', 'Allowed', 'Hypertext,Core');</pre>
-
-<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> tag to the not-so-safe <code>h1</code>
-tag). How do we make this still a viable solution?</p>
+<p>This is a complicated feature, and is explained more in depth at
+<a href="enduser-tidy.html">the Tidy documentation page</a>.</p>
 
+<!--
 <h3>Unified selector</h3>
 
 <p>Because selecting each and every one of these configuration options
 is a chore, we may wish to offer a specialized configuration method
 for selecting a filterset. Possibility:</p>
 
-<pre>function selectFilter($doctype, $filterset, $mode)</pre>
+<pre>function selectFilter($doctype, $filterset, $tidy)</pre>
 
 <p>...which is simply a light wrapper over the individual configuration
 calls. A custom config file format or text format could also be adopted.</p>
+-->
+
+<h2>Customize</h2>
+
+<p>By reviewing topic posts in the support forum, we determined that
+there were two primarily demanded customization features people wanted:
+to add an attribute to an existing element, and to add an element.
+Thus, we'll want to create convenience functions for these common
+use-cases.</p>
+
+<p>Note that the functions described here are only available if
+a raw copy of <code>HTMLPurifier_HTMLDefinition</code> was retrieved.
+Furthermore, caching may prevent your changes from immediately
+being seen: consult <a href="enduser-customize.html">enduser-customize.html</a> on how
+to work around this.</p>
+
+<h3>Attributes</h3>
+
+<p>An attribute is bound to an element by a name and has a specific
+<code>AttrDef</code> that validates it. The interface is therefore:</p>
+
+<pre>function addAttribute($element, $attribute, $attribute_def);</pre>
+
+<p>Example of the functionality in action:</p>
+
+<pre>$def->addAttribute('a', 'rel', 'Enum#nofollow');</pre>
+
+<p>The <code>$attribute_def</code> value is flexible,
+to make things simpler. It can be a literal object or:</p>
+
+<ul>
+    <!--<li>Class name: We'll instantiate it for you</li>
+    <li>Function name: We'll create an <code>HTMLPurifier_AttrDef_Anonymous</code>
+        class with that function registered as a callback.</li>-->
+    <li>String attribute type: We'll use <code>HTMLPurifier_AttrTypes</code>
+        to resolve it for you. Any data that follows a hash mark (#) will
+        be used to customize the attribute type: in the example above, 
+        we specify which values for Enum to allow.</li>
+</ul>
+
+<h3>Elements</h3>
+
+<p>An element requires certain information as specified by
+<code>HTMLPurifier_ElementDef</code>. However, not all of it is necessary,
+the usual things required are:</p>
+
+<ul>
+    <li>Attributes</li>
+    <li>Content model/type</li>
+    <li>Registration in a content set</li>
+</ul>
+
+<p>This suggests an API like this:</p>
+
+<pre>function addElement($element, $type, $contents,
+    $attr_collections = array(); $attributes = array());</pre>
+
+<p>Each parameter explained in depth:</p>
+
+<dl>
+    <dt><code>$element</code></dt>
+    <dd>Element name, ex. 'label'</dd>
+    <dt><code>$type</code></dt>
+    <dd>Content set to register in, ex. 'Inline' or 'Flow'</dd>
+    <dt><code>$contents</code></dt>
+    <dd>Description of allowed children. This is a merged form of
+        <code>HTMLPurifier_ElementDef</code>'s member variables
+        <code>$content_model</code> and <code>$content_model_type</code>,
+        where the form is <q>Type: Model</q>, ex. 'Optional: Inline'.
+        There are also a number of predefined templates one may use.</dd>
+    <dt><code>$attr_collections</code></dt>
+    <dd>Array (or string if only one) of attribute collection(s) to
+        merge into the attributes array.</dd>
+    <dt><code>$attributes</code></dt>
+    <dd>Array of attribute names to attribute definitions, much like
+        the above-described attribute customization.</dd>
+</dl>
+
+<p>A possible usage:</p>
+
+<pre>$def->addElement('font', 'Inline', 'Optional: Inline', 'Common',
+    array('color' => 'Color'));</pre>
+
+<p>See <code>HTMLPurifier/HTMLModule.php</code> for details.</p>
 
 <div id="version">$Id$</div>
 

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-customize.html

@@ -0,0 +1,791 @@
+<?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="Tutorial for customizing HTML Purifier's tag and attribute sets." />
+<link rel="stylesheet" type="text/css" href="style.css" />
+
+<title>Customize - HTML Purifier</title>
+
+</head><body>
+
+<h1 class="subtitled">Customize!</h1>
+<div class="subtitle">HTML Purifier is a Swiss-Army Knife</div>
+
+<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://htmlpurifier.org/">HTML Purifier</a> End-User Documentation</div>
+
+<div id="applicability">
+  This document covers currently unreleased functionality and
+  only applies to recent SVN checkouts.
+</div>
+
+<p>
+  You may have heard of the <a href="dev-advanced-api.html">Advanced API</a>.
+  If you're interested in reading dry prose and boring functional
+  specifications, feel free to click that link to get a no-nonsense overview
+  on the Advanced API. For the rest of us, there's this tutorial. By the time
+  you're finished reading this, you should have a pretty good idea on
+  how to implement custom tags and attributes that HTML Purifier may not have.
+</p>
+
+<h2>Is it necessary?</h2>
+
+<p>
+  Before we even write any code, it is paramount to consider whether or
+  not the code we're writing is necessary or not. HTML Purifier, by default,
+  contains a large set of elements and attributes: large enough so that
+  <em>any</em> element or attribute in XHTML 1.0 (and its HTML variant)
+  that can be safely used by the general public is implemented.
+</p>
+
+<p>
+  So what needs to be implemented? (Feel free to skip this section if
+  you know what you want).
+</p>
+
+<h3>XHTML 1.0</h3>
+
+<p>
+  All of the modules listed below are based off of the
+  <a href="http://www.w3.org/TR/2001/REC-xhtml-modularization-20010410/abstract_modules.html#sec_5.2.">modularization of
+  XHTML</a>, which, while technically for XHTML 1.1, is quite a useful
+  resource.
+</p>
+
+<ul>
+  <li>Structure</li>
+  <li>Frames</li>
+  <li>Applets (deprecated)</li>
+  <li>Forms</li>
+  <li>Image maps</li>
+  <li>Objects</li>
+  <li>Frames</li>
+  <li>Events</li>
+  <li>Meta-information</li>
+  <li>Style sheets</li>
+  <li>Link (not hypertext)</li>
+  <li>Base</li>
+  <li>Name</li>
+</ul>
+
+<p>
+  If you don't recognize it, you probably don't need it. But the curious
+  can look all of these modules up in the above-mentioned document.  Note
+  that inline scripting comes packaged with HTML Purifier (more on this
+  later).
+</p>
+
+<h3>XHTML 1.1</h3>
+
+<p>
+  We have not implemented the
+  <a href="http://www.w3.org/TR/2001/REC-ruby-20010531/">Ruby module</a>,
+  which defines a set of tags
+  for publishing short annotations for text, used mostly in Japanese
+  and Chinese school texts.
+</p>
+
+<h3>XHTML 2.0</h3>
+
+<p>
+  <a href="http://www.w3.org/TR/xhtml2/">XHTML 2.0</a> is still a
+  working draft, so any elements introduced in the
+  specification have not been implemented and will not be implemented
+  until we get a recommendation or proposal.  Because XHTML 2.0 is
+  an entirely new markup language, implementing rules for it will be
+  no easy task.
+</p>
+
+<h3>HTML 5</h3>
+
+<p>
+  <a href="http://www.whatwg.org/specs/web-apps/current-work/">HTML 5</a>
+  is a fork of HTML 4.01 by WHATWG, who believed that XHTML 2.0 was headed
+  in the wrong direction.  It too is a working draft, and may change
+  drastically before publication, but it should be noted that the
+  <code>canvas</code> tag has been implemented by many browser vendors.
+</p>
+
+<h3>Proprietary</h3>
+
+<p>
+  There are a number of proprietary tags still in the wild. Many of them
+  have been documented in <a href="ref-proprietary-tags.txt">ref-proprietary-tags.txt</a>,
+  but there is currently no implementation for any of them.
+</p>
+
+<h3>Extensions</h3>
+
+<p>
+  There are also a number of other XML languages out there that can
+  be embedded in HTML documents: two of the most popular are MathML and
+  SVG, and I frequently get requests to implement these.  But they are
+  expansive, comprehensive specifications, and it would take far too long
+  to implement them <em>correctly</em> (most systems I've seen go as far
+  as whitelisting tags and no further; come on, what about nesting!)
+</p>
+
+<p>
+  Word of warning: HTML Purifier is currently <em>not</em> namespace
+  aware.
+</p>
+
+<h2>Giving back</h2>
+
+<p>
+  As you may imagine from the details above (don't be abashed if you didn't
+  read it all: a glance over would have done), there's quite a bit that
+  HTML Purifier doesn't implement.  Recent architectural changes have
+  allowed HTML Purifier to implement elements and attributes that are not
+  safe!  Don't worry, they won't be activated unless you set %HTML.Trusted
+  to true, but they certainly help out users who need to put, say, forms
+  on their page and don't want to go through the trouble of reading this
+  and implementing it themself.
+</p>
+
+<p>
+  So any of the above that you implement for your own application could
+  help out some other poor sap on the other side of the globe.  Help us
+  out, and send back code so that it can be hammered into a module and
+  released with the core.  Any code would be greatly appreciated!
+</p>
+
+<h2>And now...</h2>
+
+<p>
+  Enough philosophical talk, time for some code:
+</p>
+
+<pre>$config = HTMLPurifier_Config::createDefault();
+$config->set('HTML', 'DefinitionID', 'enduser-customize.html tutorial');
+$config->set('HTML', 'DefinitionRev', 1);
+$def =& $config->getHTMLDefinition(true);</pre>
+
+<p>
+  Assuming that HTML Purifier has already been properly loaded (hint:
+  include <code>HTMLPurifier.auto.php</code>), this code will set up
+  the environment that you need to start customizing the HTML definition.
+  What's going on?
+</p>
+
+<ul>
+  <li>
+    The first three lines are regular configuration code:
+    <ul>
+      <li>
+        %HTML.DefinitionID is set to a unique identifier for your
+        custom HTML definition.  This prevents it from clobbering
+        other custom definitions on the same installation.
+      </li>
+      <li>
+        %HTML.DefinitionRev is a revision integer of your HTML
+        definition.  Because HTML definitions are cached, you'll need
+        to increment this whenever you make a change in order to flush
+        the cache.
+      </li>
+    </ul>
+  </li>
+  <li>
+    The fourth line retrieves a raw <code>HTMLPurifier_HTMLDefinition</code>
+    object that we will be tweaking. If the parameter was removed, we
+    would be retrieving a fully formed definition object, which is somewhat
+    useless for customization purposes.
+  </li>
+</ul>
+
+<h3>Broken backwards-compatibility</h3>
+
+<p>
+  Those of you who have already been twiddling around with the raw
+  HTML definition object, you'll be noticing that you're getting an error
+  when you attempt to retrieve the raw definition object without specifying
+  a DefinitionID.  It is vital to caching (see below) that you make a unique
+  name for your customized definition, so make up something right now and
+  things will operate again.
+</p>
+
+<h2>Turn off caching</h2>
+
+<p>
+  To make development easier, we're going to temporarily turn off 
+  definition caching:
+</p>
+
+<pre>$config = HTMLPurifier_Config::createDefault();
+$config->set('HTML', 'DefinitionID', 'enduser-customize.html tutorial');
+$config->set('HTML', 'DefinitionRev', 1);
+<strong>$config->set('Core', 'DefinitionCache', null); // remove this later!</strong>
+$def =& $config->getHTMLDefinition(true);</pre>
+
+<p>
+  A few things should be mentioned about the caching mechanism before
+  we move on.  For performance reasons, HTML Purifier caches generated
+  <code>HTMLPurifier_Definition</code> objects in serialized files
+  stored (by default) in <code>library/HTMLPurifier/DefinitionCache/Serializer</code>.
+  A lot of processing is done in order to create these objects, so it
+  makes little sense to repeat the same processing over and over again
+  whenever HTML Purifier is called.
+</p>
+
+<p>
+  In order to identify a cache entry, HTML Purifier uses three variables:
+  the library's version number, the value of %HTML.DefinitionRev and
+  a serial of relevant configuration.  Whenever any of these changes,
+  a new HTML definition is generated.  Notice that there is no way
+  for the definition object to track changes to customizations: here, it
+  is up to you to supply appropriate information to DefinitionID and
+  DefinitionRev.
+</p>
+
+<h2 id="addAttribute">Add an attribute</h2>
+
+<p>
+  For this example, we're going to implement the <code>target</code> attribute found
+  on <code>a</code> elements.  To implement an attribute, we have to
+  ask a few questions:
+</p>
+
+<ol>
+  <li>What element is it found on?</li>
+  <li>What is its name?</li>
+  <li>Is it required or optional?</li>
+  <li>What are valid values for it?</li>
+</ol>
+
+<p>
+  The first three are easy: the element is <code>a</code>, the attribute
+  is <code>target</code>, and it is not a required attribute. (If it
+  was required, we'd need to append an asterisk to the attribute name,
+  you'll see an example of this in the addElement() example).
+</p>
+
+<p>
+  The last question is a little trickier.
+  Lets allow the special values: _blank, _self, _target and _top.
+  The form of this is called an <strong>enumeration</strong>, a list of
+  valid values, although only one can be used at a time.  To translate
+  this into code form, we write:
+</p>
+
+<pre>$config = HTMLPurifier_Config::createDefault();
+$config->set('HTML', 'DefinitionID', 'enduser-customize.html tutorial');
+$config->set('HTML', 'DefinitionRev', 1);
+$config->set('Core', 'DefinitionCache', null); // remove this later!
+$def =& $config->getHTMLDefinition(true);
+<strong>$def->addAttribute('a', 'target', 'Enum#_blank,_self,_target,_top');</strong></pre>
+
+<p>
+  The <code>Enum#_blank,_self,_target,_top</code> does all the magic.
+  The string is split into two parts, separated by a hash mark (#):
+</p>
+
+<ol>
+  <li>The first part is the name of what we call an <code>AttrDef</code></li>
+  <li>The second part is the parameter of the above-mentioned <code>AttrDef</code></li>
+</ol>
+
+<p>
+  If that sounds vague and generic, it's because it is!  HTML Purifier defines
+  an assortment of different attribute types one can use, and each of these
+  has their own specialized parameter format.  Here are some of the more useful
+  ones:
+</p>
+
+<table class="table">
+  <thead>
+    <tr>
+      <th>Type</th>
+      <th>Format</th>
+      <th>Description</th>
+    </tr>
+  </thead>
+  <tbody>
+    <tr>
+      <th>Enum</th>
+      <td><em>[s:]</em>value1,value2,...</td>
+      <td>
+        Attribute with a number of valid values, one of which may be used. When
+        s: is present, the enumeration is case sensitive.
+      </td>
+    </tr>
+    <tr>
+      <th>Bool</th>
+      <td>attribute_name</td>
+      <td>
+        Boolean attribute, with only one valid value: the name
+        of the attribute.
+      </td>
+    </tr>
+    <tr>
+      <th>CDATA</th>
+      <td></td>
+      <td>
+        Attribute of arbitrary text. Can also be referred to as <strong>Text</strong>
+        (the specification makes a semantic distinction between the two).
+      </td>
+    </tr>
+    <tr>
+      <th>ID</th>
+      <td></td>
+      <td>
+        Attribute that specifies a unique ID
+      </td>
+    </tr>
+    <tr>
+      <th>Pixels</th>
+      <td></td>
+      <td>
+        Attribute that specifies an integer pixel length
+      </td>
+    </tr>
+    <tr>
+      <th>Length</th>
+      <td></td>
+      <td>
+        Attribute that specifies a pixel or percentage length
+      </td>
+    </tr>
+    <tr>
+      <th>NMTOKENS</th>
+      <td></td>
+      <td>
+        Attribute that specifies a number of name tokens, example: the
+        <code>class</code> attribute
+      </td>
+    </tr>
+    <tr>
+      <th>URI</th>
+      <td></td>
+      <td>
+        Attribute that specifies a URI, example: the <code>href</code>
+        attribute
+      </td>
+    </tr>
+    <tr>
+      <th>Number</th>
+      <td></td>
+      <td>
+        Attribute that specifies an positive integer number
+      </td>
+    </tr>
+  </tbody>
+</table>
+
+<p>
+  For a complete list, consult
+  <a href="http://htmlpurifier.org/svnroot/htmlpurifier/trunk/library/HTMLPurifier/AttrTypes.php"><code>library/HTMLPurifier/AttrTypes.php</code></a>;
+  more information on attributes that accept parameters can be found on their
+  respective includes in
+  <a href="http://htmlpurifier.org/svnroot/htmlpurifier/trunk/library/HTMLPurifier/AttrDef/"><code>library/HTMLPurifier/AttrDef</code></a>.
+</p>
+
+<p>
+  Sometimes, the restrictive list in AttrTypes just doesn't cut it. Don't
+  sweat: you can also use a fully instantiated object as the value. The
+  equivalent, verbose form of the above example is:
+</p>
+
+<pre>$config = HTMLPurifier_Config::createDefault();
+$config->set('HTML', 'DefinitionID', 'enduser-customize.html tutorial');
+$config->set('HTML', 'DefinitionRev', 1);
+$config->set('Core', 'DefinitionCache', null); // remove this later!
+$def =& $config->getHTMLDefinition(true);
+<strong>$def->addAttribute('a', 'target', new HTMLPurifier_AttrDef_Enum(
+  array('_blank','_self','_target','_top')
+));</strong></pre>
+
+<p>
+  Trust me, you'll learn to love the shorthand.
+</p>
+
+<h2>Add an element</h2>
+
+<p>
+  Adding attributes is really small-fry stuff, though, and it was possible
+  to add them (albeit a bit more wordy) prior to 2.0. The real gem of 
+  the Advanced API is adding elements. There are five questions to 
+  ask when adding a new element:
+</p>
+
+<ol>
+  <li>What is the element's name?</li>
+  <li>What content set does this element belong to?</li>
+  <li>What are the allowed children of this element?</li>
+  <li>What attributes does the element allow that are general?</li>
+  <li>What attributes does the element allow that are specific to this element?</li>
+</ol>
+
+<p>
+  It's a mouthful, and you'll be slightly lost if your not familiar with
+  the HTML specification, so let's explain them step by step.
+</p>
+
+<h3>Content set</h3>
+
+<p>
+  The HTML specification defines two major content sets: Inline
+  and Block.  Each of these
+  content sets contain a list of elements: Inline contains things like
+  <code>span</code> and <code>b</code> while Block contains things like
+  <code>div</code> and <code>blockquote</code>.
+</p>
+
+<p>
+  These content sets amount to a macro mechanism for HTML definition. Most
+  elements in HTML are organized into one of these two sets, and most
+  elements in HTML allow elements from one of these sets.  If we had
+  to write each element verbatim into each other element's allowed
+  children, we would have ridiculously large lists; instead we use
+  content sets to compactify the declaration.
+</p>
+
+<p>
+  Practically speaking, there are several useful values you can use here:
+</p>
+
+<table class="table">
+  <thead>
+    <tr>
+      <th>Content set</th>
+      <th>Description</th>
+    </tr>
+  </thead>
+  <tbody>
+    <tr>
+      <th>Inline</th>
+      <td>Character level elements, text</td>
+    </tr>
+    <tr>
+      <th>Block</th>
+      <td>Block-like elements, like paragraphs and lists</td>
+    </tr>
+    <tr>
+      <th><em>false</em></th>
+      <td>
+        Any element that doesn't fit into the mold, for example <code>li</code>
+        or <code>tr</code>
+      </td>
+    </tr>
+  </tbody>
+</table>
+
+<p>
+  By specifying a valid value here, all other elements that use that
+  content set will also allow your element, without you having to do
+  anything. If you specify <em>false</em>, you'll have to register
+  your element manually.
+</p>
+
+<h3>Allowed children</h3>
+
+<p>
+  Allowed children defines the elements that this element can contain.
+  The allowed values may range from none to a complex regexp depending on
+  your element.
+</p>
+
+<p>
+  If you've ever taken a look at the HTML DTD's before, you may have
+  noticed declarations like this:
+</p>
+
+<pre>&lt;!ELEMENT LI - O (%flow;)*             -- list item --&gt;</pre>
+
+<p>
+  The <code>(%flow;)*</code> indicates the allowed children of the
+  <code>li</code> tag: <code>li</code> allows any number of flow
+  elements as its children. In HTML Purifier, we'd write it like
+  <code>Flow</code> (here's where the content sets we were
+  discussing earlier come into play). There are three shorthand content models you
+  can specify:
+</p>
+
+<table class="table">
+  <thead>
+    <tr>
+      <th>Content model</th>
+      <th>Description</th>
+    </tr>
+  </thead>
+  <tbody>
+    <tr>
+      <th>Empty</th>
+      <td>No children allowed, like <code>br</code> or <code>hr</code></td>
+    </tr>
+    <tr>
+      <th>Inline</th>
+      <td>Any number of inline elements and text, like <code>span</code></td>
+    </tr>
+    <tr>
+      <th>Flow</th>
+      <td>Any number of inline elements, block elements and text, like <code>div</code></td>
+    </tr>
+  </tbody>
+</table>
+
+<p>
+  This covers 90% of all the cases out there, but what about elements that
+  break the mold like <code>ul</code>? This guy requires at least one
+  child, and the only valid children for it are <code>li</code>. The
+  content model is: <code>Required: li</code>. There are two parts: the
+  first type determines what <code>ChildDef</code> will be used to validate
+  content models. The most common values are:
+</p>
+
+<table class="table">
+  <thead>
+    <tr>
+      <th>Type</th>
+      <th>Description</th>
+    </tr>
+  </thead>
+  <tbody>
+    <tr>
+      <th>Required</th>
+      <td>Children must be one or more of the valid elements</td>
+    </tr>
+    <tr>
+      <th>Optional</th>
+      <td>Children can be any number of the valid elements</td>
+    </tr>
+    <tr>
+      <th>Custom</th>
+      <td>Children must follow the DTD-style regex</td>
+    </tr>
+  </tbody>
+</table>
+
+<p>
+  You can also implement your own <code>ChildDef</code>: this was done
+  for a few special cases in HTML Purifier such as <code>Chameleon</code>
+  (for <code>ins</code> and <code>del</code>), <code>StrictBlockquote</code>
+  and <code>Table</code>.
+</p>
+
+<p>
+  The second part specifies either valid elements or a regular expression.
+  Valid elements are separated with horizontal bars (|), i.e.
+  "<code>a | b | c</code>".  Use #PCDATA to represent plain text.
+  Regular expressions are based off of DTD's style:
+</p>
+
+<ul>
+  <li>Parentheses () are used for grouping</li>
+  <li>Commas (,) separate elements that should come one after another</li>
+  <li>Horizontal bars (|) indicate one or the other elements should be used</li>
+  <li>Plus signs (+) are used for a one or more match</li>
+  <li>Asterisks (*) are used for a zero or more match</li>
+  <li>Question marks (?) are used for a zero or one match</li>
+</ul>
+
+<p>
+  For example, "<code>a, b?, (c | d), e+, f*</code>" means "In this order,
+  one <code>a</code> element, at most one <code>b</code> element,
+  one <code>c</code> or <code>d</code> element (but not both), one or more
+  <code>e</code> elements, and any number of <code>f</code> elements."
+  Regex veterans should be able to jump right in, and those not so savvy
+  can always copy-paste W3C's content model definitions into HTML Purifier
+  and hope for the best.
+</p>
+
+<p>
+  A word of warning: while the regex format is extremely flexible on
+  the developer's side, it is
+  quite unforgiving on the user's side.  If the user input does not <em>exactly</em>
+  match the specification, the entire contents of the element will
+  be nuked.  This is why there is are specific content model types like
+  Optional and Required: while they could be implemented as <code>Custom:
+  (valid | elements)*</code>, the custom classes contain special recovery
+  measures that make sure as much of the user's original content gets 
+  through. HTML Purifier's core, as a rule, does not use Custom.
+</p>
+
+<p>
+  One final note: you can also use Content Sets inside your valid elements
+  lists or regular expressions. In fact, the three shorthand content models
+  mentioned above are just that: abbreviations:
+</p>
+
+<table class="table">
+  <thead>
+    <tr>
+      <th>Content model</th>
+      <th>Implementation</th>
+    </tr>
+  </thead>
+  <tbody>
+    <tr>
+      <th>Inline</th>
+      <td>Optional: Inline | #PCDATA</td>
+    </tr>
+    <tr>
+      <th>Flow</th>
+      <td>Optional: Flow | #PCDATA</td>
+    </tr>
+  </tbody>
+</table>
+
+<p>
+  When the definition is compiled, Inline will be replaced with a
+  horizontal-bar separated list of inline elements. Also, notice that
+  it does not contain text: you have to specify that yourself.
+</p>
+
+<h3>Common attributes</h3>
+
+<p>
+  Congratulations: you have just gotten over the proverbial hump (Allowed
+  children). Common attributes is much simpler, and boils down to
+  one question: does your element have the <code>id</code>, <code>style</code>,
+  <code>class</code>, <code>title</code> and <code>lang</code> attributes?
+  If so, you'll want to specify the <code>Common</code> attribute collection,
+  which contains these five attributes that are found on almost every
+  HTML element in the specification.
+</p>
+
+<p>
+  There are a few more collections, but they're really edge cases:
+</p>
+
+<table class="table">
+  <thead>
+    <tr>
+      <th>Collection</th>
+      <th>Attributes</th>
+    </tr>
+  </thead>
+  <tbody>
+    <tr>
+      <th>I18N</th>
+      <td><code>lang</code>, possibly <code>xml:lang</code></td>
+    </tr>
+    <tr>
+      <th>Core</th>
+      <td><code>style</code>, <code>class</code>, <code>id</code> and <code>title</code></td>
+    </tr>
+  </tbody>
+</table>
+
+<p>
+  Common is a combination of the above-mentioned collections.
+</p>
+
+<h3>Attributes</h3>
+
+<p>
+  If you didn't read the <a href="#addAttribute">previous section on
+  adding attributes</a>, read it now.  The last parameter is simply
+  array of attribute names to attribute implementations, in the exact
+  same format as <code>addAttribute()</code>.
+</p>
+
+<h3>Putting it all together</h3>
+
+<p>
+  We're going to implement <code>form</code>. Before we embark, lets
+  grab a reference implementation from over at the
+  <a href="http://www.w3.org/TR/html4/sgml/loosedtd.html">transitional DTD</a>:
+</p>
+
+<pre>&lt;!ELEMENT FORM - - (%flow;)* -(FORM)   -- interactive form --&gt;
+&lt;!ATTLIST FORM
+  %attrs;                              -- %coreattrs, %i18n, %events --
+  action      %URI;          #REQUIRED -- server-side form handler --
+  method      (GET|POST)     GET       -- HTTP method used to submit the form--
+  enctype     %ContentType;  &quot;application/x-www-form-urlencoded&quot;
+  accept      %ContentTypes; #IMPLIED  -- list of MIME types for file upload --
+  name        CDATA          #IMPLIED  -- name of form for scripting --
+  onsubmit    %Script;       #IMPLIED  -- the form was submitted --
+  onreset     %Script;       #IMPLIED  -- the form was reset --
+  target      %FrameTarget;  #IMPLIED  -- render in this frame --
+  accept-charset %Charsets;  #IMPLIED  -- list of supported charsets --
+  &gt;</pre>
+
+<p>
+  Juicy! With just this, we can answer four of our five questions:
+</p>
+
+<ol>
+  <li>What is the element's name? <strong>form</strong></li>
+  <li>What content set does this element belong to? <strong>Block</strong>
+    (this needs a little sleuthing, I find the easiest way is to search
+    the DTD for <code>FORM</code> and determine which set it is in.)</li>
+  <li>What are the allowed children of this element? <strong>One
+    or more flow elements, but no nested <code>form</code>s</strong></li>
+  <li>What attributes does the element allow that are general? <strong>Common</strong></li>
+  <li>What attributes does the element allow that are specific to this element? <strong>A whole bunch, see ATTLIST;
+    we're going to the vital ones: <code>action</code>, <code>method</code> and <code>name</code></strong></li>
+</ol>
+
+<p>
+  Time for some code:
+</p>
+
+<pre>$config = HTMLPurifier_Config::createDefault();
+$config->set('HTML', 'DefinitionID', 'enduser-customize.html tutorial');
+$config->set('HTML', 'DefinitionRev', 1);
+$config->set('Core', 'DefinitionCache', null); // remove this later!
+$def =& $config->getHTMLDefinition(true);
+$def->addAttribute('a', 'target', new HTMLPurifier_AttrDef_Enum(
+  array('_blank','_self','_target','_top')
+));
+<strong>$form =& $def->addElement(
+  'form',   // name
+  'Block',  // content set
+  'Flow', // allowed children
+  'Common', // attribute collection
+  array( // attributes
+    'action*' => 'URI',
+    'method' => 'Enum#get|post',
+    'name' => 'ID'
+  )
+);
+$form->excludes = array('form' => true);</strong></pre>
+
+<p>
+  Each of the parameters corresponds to one of the questions we asked.
+  Notice that we added an asterisk to the end of the <code>action</code>
+  attribute to indicate that it is required. If someone specifies a
+  <code>form</code> without that attribute, the tag will be axed.
+  Also, the extra line at the end is a special extra declaration that
+  prevents forms from being nested within each other.
+</p>
+
+<p>
+  And that's all there is to it! Implementing the rest of the form
+  module is left as an exercise to the user; to see more examples
+  check the <a href="http://htmlpurifier.org/svnroot/htmlpurifier/trunk/library/HTMLPurifier/HTMLModule/"><code>library/HTMLPurifier/HTMLModule/</code></a> directory
+  in your local HTML Purifier installation.
+</p>
+
+<h2>And beyond...</h2>
+
+<p>
+  Perceptive users may have realized that, to a certain extent, we
+  have simply re-implemented the facilities of XML Schema or the
+  Document Type Definition.  What you are seeing here, however, is
+  not just an XML Schema or Document Type Definition: it is a fully
+  expressive method of specifying the definition of HTML that is
+  a portable superset of the capabilities of the two above-mentioned schema
+  languages.  What makes HTMLDefinition so powerful is the fact that
+  if we don't have an implementation for a content model or an attribute
+  definition, you can supply it yourself by writing a PHP class.
+</p>
+
+<p>
+  There are many facets of HTMLDefinition beyond the Advanced API I have
+  walked you through today.  To find out more about these, you can
+  check out these source files:
+</p>
+
+<ul>
+  <li><a href="http://htmlpurifier.org/svnroot/htmlpurifier/trunk/library/HTMLPurifier/HTMLModule.php"><code>library/HTMLPurifier/HTMLModule.php</code></a></li>
+  <li><a href="http://htmlpurifier.org/svnroot/htmlpurifier/trunk/library/HTMLPurifier/ElementDef.php"><code>library/HTMLPurifier/ElementDef.php</code></a></li>
+</ul>
+
+<div id="version">$Id: enduser-tidy.html 1158 2007-06-18 19:26:29Z Edward $</div>
+
+</body></html>

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-security.txt

@@ -8,15 +8,11 @@ to be effective. Things to remember:
 
 1. Character Encoding: see enduser-utf8.html for more info.
 
-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.
+2. IDs: see enduser-id.html for more info
 
-3. IDs: see enduser-id.html for more info
-
-4. Links: document pending feature completion
+3. Links: document pending feature completion
 Rudimentary blacklisting, we should also allow only relative URIs. We
 need a doc to explain the stuff.
 
-5. CSS: document pending
+4. 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-tidy.html

@@ -0,0 +1,235 @@
+<?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="Tutorial for tweaking HTML Purifier's Tidy-like behavior." />
+<link rel="stylesheet" type="text/css" href="style.css" />
+
+<title>Tidy - HTML Purifier</title>
+
+</head><body>
+
+<h1>Tidy</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>
+
+<div id="applicability">
+  This document covers currently unreleased functionality and
+  only applies to recent SVN checkouts.
+</div>
+
+<p>You've probably heard of HTML Tidy, Dave Raggett's little piece
+of software that cleans up poorly written HTML.  Let me say it straight
+out:</p>
+
+<p class="emphasis">This ain't HTML Tidy!</p>
+
+<p>Rather, Tidy stands for a cool set of Tidy-inspired in HTML Purifier
+that allows users to submit deprecated elements and attributes and get
+valid strict markup back. For example:</p>
+
+<pre>&lt;center&gt;Centered&lt;/center&gt;</pre>
+
+<p>...becomes:</p>
+
+<pre>&lt;div style=&quot;text-align:center;&quot;&gt;Centered&lt;/div&gt;</pre>
+
+<p>...when this particular fix is run on the HTML. This tutorial will give
+you down the lowdown of what exactly HTML Purifier will do when Tidy
+is on, and how to fine tune this behavior. Once again, <strong>you do
+not need Tidy installed on your PHP to use these features!</strong></p>
+
+<h2>What does it do?</h2>
+
+<p>Tidy will do several things to your HTML:</p>
+
+<ul>
+    <li>Convert deprecated elements and attributes to standards-compliant
+        alternatives</li>
+    <li>Enforce XHTML compatibility guidelines and other best practices</li>
+    <li>Preserve data that would normally be removed as per W3C</li>
+</ul>
+
+<h2>What are levels?</h2>
+
+<p>Levels describe how aggressive the Tidy module should be when 
+cleaning up HTML. There are four levels to pick: none, light, medium
+and heavy. Each of these levels has a well-defined set of behavior
+associated with it, although it may change depending on your doctype.</p>
+
+<dl>
+    <dt>light</dt>
+    <dd>This is the <strong>lenient</strong> level. If a tag or attribute
+        is about to be removed because it isn't supported by the
+        doctype, Tidy will step in and change into an alternative that
+        is supported.</dd>
+    <dt>medium</dt>
+    <dd>This is the <strong>correctional</strong> level. At this level,
+        all the functions of light are performed, as well as some extra,
+        non-essential best practices enforcement. Changes made on this
+        level are very benign and are unlikely to cause problems.</dd>
+    <dt>heavy</dt>
+    <dd>This is the <strong>aggressive</strong> level. If a tag or
+        attribute is deprecated, it will be converted into a non-deprecated
+        version, no ifs ands or buts.</dd>
+</dl>
+
+<p>By default, Tidy operates on the <strong>medium</strong> level. You can
+change the level of cleaning by setting the %HTML.TidyLevel configuration
+directive:</p>
+
+<pre>$config->set('HTML', 'TidyLevel', 'heavy'); // burn baby burn!</pre>
+
+<h2>Is the light level really light?</h2>
+
+<p>It depends on what doctype you're using. If your documents are HTML
+4.01 <em>Transitional</em>, HTML Purifier will be lazy
+and won't clean up your <code>center</code>
+or <code>font</code> tags. But if you're using HTML 4.01 <em>Strict</em>,
+HTML Purifier has no choice: it has to convert them, or they will
+be nuked out of existence. So while light on Transitional will result
+in little to no changes, light on Strict will still result in quite
+a lot of fixes.</p>
+
+<p>This is different behavior from 1.6 or before, where deprecated
+tags in transitional documents would
+always be cleaned up regardless. This is also better behavior.</p>
+
+<h2>My pages look different!</h2>
+
+<p>HTML Purifier is tasked with converting deprecated tags and
+attributes to standards-compliant alternatives, which usually
+need copious amounts of CSS. It's also not foolproof: sometimes
+things do get lost in the translation. This is why when HTML Purifier
+can get away with not doing cleaning, it won't; this is why
+the default value is <strong>medium</strong> and not heavy.</p>
+
+<p>Fortunately, only a few attributes have problems with the switch
+over. They are described below:</p>
+
+<table class="table">
+    <thead><tr>
+        <th>Element@Attr</th>
+        <th>Changes</th>
+    </tr></thead>
+    <tbody>
+        <tr>
+            <td>caption@align</td>
+            <td>Firefox supports stuffing the caption on the
+                left and right side of the table, a feature that
+                Internet Explorer, understandably, does not have.
+                When align equals right or left, the text will simply
+                be aligned on the left or right side.</td>
+        </tr>
+        <tr>
+            <td>img@align</td>
+            <td>The implementation for align bottom is good, but not
+            perfect. There are a few pixel differences.</td>
+        </tr>
+        <tr>
+            <td>br@clear</td>
+            <td>Clear both gets a little wonky in Internet Explorer. Haven't
+                really been able to figure out why.</td>
+        </tr>
+        <tr>
+            <td>hr@noshade</td>
+            <td>All browsers implement this slightly differently: we've
+                chosen to make noshade horizontal rules gray.</td>
+        </tr>
+    </tbody>
+</table>
+
+<p>There are a few more minor, although irritating, bugs.
+Some older browsers support deprecated attributes,
+but not CSS. Transformed elements and attributes will look unstyled
+to said browsers. Also, CSS precedence is slightly different for
+inline styles versus presentational markup. In increasing precedence:</p>
+
+<ol>
+    <li>Presentational attributes</li>
+    <li>External style sheets</li>
+    <li>Inline styling</li>
+</ol>
+
+<p>This means that styling that may have been masked by external CSS
+declarations will start showing up (a good thing, perhaps). Finally,
+if you've turned off the style attribute, almost all of
+these transformations will not work. Sorry mates.</p>
+
+<p>You can review the rendering before and after of these transformations
+by consulting the <a
+href="http://htmlpurifier.org/live/smoketests/attrTransform.php">attrTransform.php
+smoketest</a>.</p>
+
+<h2>I like the general idea, but the specifics bug me!</h2>
+
+<p>So you want HTML Purifier to clean up your HTML, but you're not
+so happy about the br@clear implementation. That's perfectly fine!
+HTML Purifier will make accomodations:</p>
+
+<pre>$config->set('HTML', 'Doctype', 'XHTML 1.0 Transitional');
+$config->set('HTML', 'TidyLevel', 'heavy'); // all changes, minus...
+<strong>$config->set('HTML', 'TidyRemove', 'br@clear');</strong></pre>
+
+<p>That third line does the magic, removing the br@clear fix
+from the module, ensuring that <code>&lt;br clear="both" /&gt;</code>
+will pass through unharmed. The reverse is possible too:</p>
+
+<pre>$config->set('HTML', 'Doctype', 'XHTML 1.0 Transitional');
+$config->set('HTML', 'TidyLevel', 'none'); // no changes, plus...
+<strong>$config->set('HTML', 'TidyAdd', 'p@align');</strong></pre>
+
+<p>In this case, all transformations are shut off, except for the p@align
+one, which you found handy.</p>
+
+<p>To find out what the names of fixes you want to turn on or off are,
+you'll have to consult the source code, specifically the files in
+<code>HTMLPurifier/HTMLModule/Tidy/</code>. There is, however, a
+general syntax:</p>
+
+<table class="table">
+    <thead>
+        <tr>
+            <th>Name</th>
+            <th>Example</th>
+            <th>Interpretation</th>
+        </tr>
+    </thead>
+    <tbody>
+        <tr>
+            <td>element</td>
+            <td>font</td>
+            <td>Tag transform for <em>element</em></td>
+        </tr>
+        <tr>
+            <td>element@attr</td>
+            <td>br@clear</td>
+            <td>Attribute transform for <em>attr</em> on <em>element</em></td>
+        </tr>
+        <tr>
+            <td>@attr</td>
+            <td>@lang</td>
+            <td>Global attribute transform for <em>attr</em></td>
+        </tr>
+        <tr>
+            <td>e#content_model_type</td>
+            <td>blockquote#content_model_type</td>
+            <td>Change of child processing implementation for <em>e</em></td>
+        </tr>
+    </tbody>
+</table>
+
+<h2>So... what's the lowdown?</h2>
+
+<p>The lowdown is, quite frankly, HTML Purifier's default settings are
+probably good enough. The next step is to bump the level up to heavy,
+and if that still doesn't satisfy your appetite, do some fine tuning.
+Other than that, don't worry about it: this all works silently and
+effectively in the background.</p>
+
+<div id="version">$Id$</div>
+
+</body></html>

docs/enduser-utf8.html

@@ -23,7 +23,7 @@ own advice for sake of portability.  -->
 
 <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 are not that
 difficult to understand, but so many people blithely stumble
@@ -1003,7 +1003,11 @@ when dealing with Unicode text:</p>
     </ul></li>
 </ul>
 
-<p>...and always think in bytes, not characters. If you use strpos()
+<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>
 

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:
+$config->set('Core', 'Encoding', 'UTF-8'); // replace with your encoding
+$config->set('HTML', 'Doctype', 'XHTML 1.0 Transitional'); // replace with your doctype
+
+$purifier = new HTMLPurifier($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/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>
@@ -34,6 +34,12 @@ information for casual developers using HTML Purifier.</p>
 <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>
 
+<dt><a href="enduser-tidy.html">Tidy</a></dt>
+<dd>Tutorial for tweaking HTML Purifier's Tidy-like behavior.</dd>
+
+<dt><a href="enduser-customize.html">Customize</a></dt>
+<dd>Tutorial for customizing HTML Purifier's tag and attribute sets.</dd>
+
 </dl>
 
 <h2>Development</h2>
@@ -42,9 +48,6 @@ 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>
 
@@ -105,6 +108,12 @@ 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>
@@ -125,8 +134,8 @@ the code. They may be upgraded to HTML files or stay as TXT scratchpads.</p>
 
 <tr>
     <td>Reference</td>
-    <td><a href="ref-loose-vs-strict.txt">Loose vs.Strict</a></td>
-    <td>Differences between HTML Strict and Transitional versions.</td>
+    <td><a href="ref-content-models.txt">Handling Content Model Changes</a></td>
+    <td>Discusses how to tidy up content model changes using custom ChildDef classes.</td>
 </tr>
 
 <tr>
@@ -137,14 +146,8 @@ the code. They may be upgraded to HTML files or stay as TXT scratchpads.</p>
 
 <tr>
     <td>Reference</td>
-    <td><a href="ref-strictness.txt">Strictness</a></td>
-    <td>Short essay on how loose definition isn't really loose.</td>
-</tr>
-
-<tr>
-    <td>Reference</td>
-    <td><a href="ref-xhtml-1.1.txt">XHTML 1.1</a></td>
-    <td>What we'd have to do to support XHTML 1.1.</td>
+    <td><a href="ref-html-modularization.txt">Modularization of HTMLDefinition</a></td>
+    <td>Provides a high-level overview of the concepts behind HTMLModules.</td>
 </tr>
 
 <tr>

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

@@ -12,29 +12,10 @@ the documentation in ConfigDef for more information on these namespaces.
 
 Since configuration is dependant on context, internal classes require a
 configuration object to be passed as a parameter.  (They also require a
-Context object).
+Context object). A majority of classes do not need the config object,
+but for those who do, it is a lifesaver.
 
-In relation to HTMLDefinition and CSSDefinition, there could be a special class
-of directives that influence the *construction* of the Definition object.
-A theoretical call pattern would look like:
-
-1. Client calls Config->getHTMLDefinition()
-2. Config calls HTMLDefinition->createNew(this)
-3. HTMLDefinition constructs itself with base configuration
-4. HTMLDefinition calls Config->get('HTML')
-5. Config returns array of directives
-6. HTMLDefinition performs operations and changes specified by directives
-7. HTMLPurifier returns constructed definition
-8. Config caches definition so it doesn't have to be generated again
-9. Config returns definition
-
-You could also override Config's copy of the definition with your own
-custom copy, which OVERRIDES all directives.  Only the base, vanilla copy
-is the Singleton, the object actually interfaced with is a operated-upon
-clone of that object.  Also, if an update to the directives would update
-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. See
-ref-xhtml-1.1.txt for more info.
+Definition objects are complex datatypes influenced by their respective
+directive namespaces (HTMLDefinition with HTML and CSSDefinition with CSS).
+If any of these directives is updated, HTML Purifier forces the definition
+to be regenerated.

docs/proposal-filter-levels.txt

@@ -2,23 +2,16 @@
 Filter Levels
     When one size *does not* fit all
 
-The more I think about it, the less sense it makes for maintaining one huge
-monolithic HTMLDefinition class.  There's simply so much variation that
-could go into this definition: the set of HTML good for blog entries is
-definitely too large for HTML that would be allowed in blog comments. Going
-from Transitional to Strict requires changes to the definition.
+It makes little sense to constrain users to one set of HTML elements and
+attributes and tell them that they are not allowed to mold this in
+any fashion.  Many users demand to be able to custom-select which elements
+and attributes they want.  This is fine: because HTML Purifier keeps close
+track of what elements are safe to use, there is no way for them to
+accidently allow an XSS-able tag.
 
-Allowing users to specify their own whitelists is one step (implemented, btw), 
-but I have doubts on only doing this. Simply put, the typical programmer is too 
-lazy to actually go through the trouble of investigating which tags, attributes 
-and properties to allow. HTMLDefinition makes a big part of what HTMLPurifier 
-is. 
-
-The idea, then, is to setup fundamentally different set of definitions, which
-can further be customized using simpler configuration options.  Alternatively,
-they could be implemented as configuration profiles, which simply load
-a set of recommended directives to acheive a desired affect (no simpler
-config options though).
+However, combing through the HTML spec to make your own whitelist can
+be a daunting task.  HTML Purifier ought to offer pre-canned filter levels
+that amateur users can select based on what they think is their use-case.
 
 Here are some fuzzy levels you could set:
 
@@ -46,6 +39,10 @@ make forbidden element to text transformations desirable (for example, images).
 
 == Element Risk Analysis ==
 
+Although none of the currently supported elements presents a security
+threat per-say, some can cause problems for page layouts or be
+extremely complicated.
+
 Legend:
     [danger level] - regular tags / uncommon tags ~ deprecated tags
     [danger level]* - rare tags
@@ -114,6 +111,10 @@ Partially presentational - table.cellpadding, table.cellspacing,
 
 == CSS Risk Analysis ==
 
+Currently, there is no support for fine-grained "allowed CSS" specification,
+mainly because I'm lazy, partially because no one has asked for it. However,
+this will be added eventually.
+
 There are certain CSS elements that are extremely useful inline, but then
 as you get to more presentation oriented styling it may not always be
 appropriate to inline them.
@@ -126,6 +127,7 @@ any CSS properties that are not currently implemented (such as position).
 Dangerous, can go outside container - float
 Easy to abuse - font-size, font-family (font), width
 Colored - background-color (background), border-color (border), color
+    (see proposal-colors.html)
 Dramatic - border, list-style-position (list-style), margin, padding,
     text-align, text-indent, text-transform, vertical-align, line-height
 

docs/ref-content-models.txt

@@ -0,0 +1,48 @@
+
+Handling Content Model Changes
+
+
+1. Context
+
+The distinction between Transitional and Strict document types is somewhat
+of an anomaly in the lineage of XHTML document types (following 1.0, no
+doctypes do not have flavors: instead, modularization is used to let
+document authors vary their elements).  This transition is usually quite
+straight-forward, as W3C usually deprecates attributes or elements, which
+are quite easily handled using tag and attribute transforms.
+
+However, for two elements, <blockquote>, <body> and <address>, W3C elected
+to also change the content model.  <blockquote> and <body> originally
+accepted both inline and block elements, but in the strict doctype they
+only allow block elements.  With <address>, the situation is inverted:
+<p> tags were now forbidden from appearing within this tag.
+
+
+2. Current situation
+
+Currently, HTML Purifier treats <blockquote> specially during Tidy mode
+using a custom ChildDef class StrictBlockquote.  StrictBlockquote
+operates similarly to Required, except that when it encounters an inline
+element, it will wrap it in a block tag (as specified by
+%HTML.BlockWrapper, the default is <p>).  The naming suggests it can
+only be used for <blockquote>s, although it may be possible to
+genericize it to work on other cases of this nature (this would be of
+little practical application, as no other element in XHTML 1.1 or earlier
+has a block-only content model).
+
+Tidy currently contains no custom, lenient implementation for <address>.
+If one were to be written, it would likely operate on the principle that,
+when a <p> tag were to be encountered, it would be replaced with a
+leading and trailing <br /> tag (the contents of <p>, being inline, are
+not an issue).  There is no prior work with this sort of operation.
+
+
+3. Outside applicability
+
+There are a number of other elements that contain restrictive content
+models, such as <ul> or <span> (the latter is restrictive in that it
+does not allow block elements).  In the former case, an errant node
+is eliminated completely, in the latter case, the text of the node
+would is preserved (as the parent node does allow PCDATA).  Custom
+content model implementations probably are not the best way of handling
+these cases, instead, node bubbling should be implemented instead.

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-html-modularization.txt

@@ -1,10 +1,8 @@
 
-XHTML 1.1 and HTML Purifier
+The Modularization of HTMLDefinition in 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/>
+1. Support Ruby <http://www.w3.org/TR/2001/REC-ruby-20010531/>
 
 HTML Purifier uses the modularization of XHTML
 <http://www.w3.org/TR/xhtml-modularization/> to organize the internals
@@ -12,25 +10,10 @@ 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).
+/library/HTMLPurifier/HTMLModule.php's docblock comments). These modules
+are managed by HTMLModuleManager.
 
-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:
+Modules that we don't support but could support are:
 
     * 5.6. Table Modules
           o 5.6.1. Basic Tables Module [?]
@@ -38,10 +21,8 @@ Modules that we don't support but coul support are:
     * 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:
+These modules would be implemented as "unsafe":
 
     * 5.2. Core Modules
           o 5.2.1. Structure Module
@@ -64,11 +45,7 @@ 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.
+This system may be generalized and ported over for CSS.
 
 == General Use-Case ==
 
@@ -91,7 +68,7 @@ like this:
 <?php
     $config = HTMLPurifier_Config::createDefault();
     $def =& $config->getHTMLDefinition(true); // reference to raw
-    unset($def->modules['Hypertext']); // rm ''a'' link
+    $def->addElement('marquee', 'Block', 'Flow', 'Common');
     $purifier = new HTMLPurifier($config);
     $purifier->purify($html); // now the definition is finalized
 ?>
@@ -184,4 +161,4 @@ 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.
+created. They are substituted into content_model.

docs/ref-loose-vs-strict.txt

@@ -1,37 +0,0 @@
-
-Loose versus Strict
-    Changes from one doctype to another
-
-There are changes.  Wow, how insightful.  Not everything changed is relevant
-to HTML Purifier, though, so let's take a look:
-
-== Major incompatibilities ==
-
-[done] BLOCKQUOTE changes from 'flow' to 'block'
-    current behavior: inline inner contents should not be nuked, block-ify as necessary
-[partially-done] U, S, STRIKE cut
-    current behavior: removed completely
-    projected behavior: replace with appropriate inline span + CSS
-[done] ADDRESS from potpourri to Inline (removes p tags)
-    current behavior: block tags silently dropped
-    ideal behavior: replace tags with something like <br>. (not high priority)
-
-== Things we can loosen up ==
-
-Tags DIR, MENU, CENTER, ISINDEX, FONT, BASEFONT? allowed in loose
-    current behavior: transform to strict-valid forms
-Attributes allowed in loose (see attribute transforms in 'dev-progress.html')
-    current behavior: projected to transform into strict-valid forms
-
-== Periphery issues ==
-
-A tag's attribute 'target' (for selecting frames) cut
-    current behavior: not allowed at all
-    projected behavior: use loose doctype if needed, needs valid values
-[done] OL/LI tag's attribute 'start'/'value' (for renumbering lists) 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
-[done] PRE tag allows SUB/SUP? (strict dtd comment vs syntax, loose disallows)
-    current behavior: disallow as usual

docs/ref-proprietary-tags.txt

@@ -18,5 +18,7 @@ HTML Purifier context.
 
 <listing>, monospace pre-variant (extremely rare)
 <plaintext>, escapes all tags to the end of document
-<ruby> and friends, (more research needed, appears to be XHTML 1.1 markup)
 <xmp>, monospace, replace with pre
+
+These should be put into their own Tidy module, not loaded by default(?). These
+all qualify as "lenient" transforms.

docs/ref-strictness.txt

@@ -1,37 +0,0 @@
-
-Is HTML Purifier Strict or Transitional?
-    A little bit of helpful guidance
-
-Despite the fact that HTML Purifier professes to support both transitional and
-strict HTML, it rejects a lot of attributes and elements that are actually, indeed,
-valid. You can investigate progress.html to find out precisely what we
-are doing to these *deprecated* attributes.
-
-However, users have found that Strict HTML imposes some quite unreasonable
-restrictions on certain things. The start and value attributes in ol and
-li (respectively) perhaps are the most contested. There's is currently no
-widely supported browser method short of JavaScript that can replace these
-two deprecated elements. It behooves us to allow these deprecated
-attributes when the output is transitional.
-
-Fortunantely, that's the only real bugger case. The others have near-perfect
-CSS equivalents, and were presentational anyway. However, the other question
-pops up: should we always convert these to the CSS forms when 1. the spec
-allows them anyway and 2. older browsers support them better? After all, the
-whole point about CSS is to seperate styling from content, so inline styling
-doesn't solve that problem.
-
-It's an icky question, and we'll have to deal with it as more and more 
-transforms get implemented.  As of right now, however, we currently support
-these loose-only constructs in loose mode:
-
-- <ul start="1">, <li value="1"> attributes
-- <u>, <strike>, <s> tags
-- flow children in <blockquote>
-- mixed children in <address>
-
-The changed child definitions as well as the ul.start li.value are the most
-compelling reasons why loose should be used.  We may want offer disabling <u>,
-<strike> and <s> by themselves. We may also want to offer no pre-emptive
-deprecated conversions. This all must be unified.
-

docs/ref-whatwg.txt

@@ -2,8 +2,23 @@
 Web Hypertext Application Technology Working Group
     WHATWG
 
-I don't think we need to worry about them.  Untrusted users shouldn't be
-submitting applications, eh?  But if some interesting attribute pops up in
-their spec, and might be worth supporting, stick it here.
+== HTML 5 ==
 
-(none so far, as you can see)
+URL: http://www.whatwg.org/specs/web-apps/current-work/
+
+HTML 5 defines a kaboodle of new elements and attributes, as well as
+some well-defined, "quirks mode" HTML parsing.  Although WHATWG professes
+to be targeted towards web applications, many of their semantic additions
+would be quite useful in regular documents. Eventually, HTML
+Purifier will need to audit their lists and figure out what changes need
+to be made.  This process is complicated by the fact that the WHATWG
+doesn't buy into W3C's modularization of XHTML 1.1: we may need
+to remodularize HTML 5 (probably done by section name). No sense in
+committing ourselves till the spec stabilizes, though.
+
+More immediately speaking though, however, is the well-defined parsing
+behavior that HTML 5 adds. While I have little interest in writing
+another DirectLex parser, other parsers like ph5p 
+<http://jero.net/lab/ph5p/> can be adapted to DOMLex to support much more
+flexible HTML parsing (a cool feature I've seen is how they resolve
+<b>bold<i>both</b>italic</i>).

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

@@ -25,6 +25,7 @@ h4 {font-family:sans-serif; font-size:0.9em; font-weight:bold; }
 .aside {margin-left:2em; font-family:sans-serif; font-size:0.9em; }
 blockquote .label {font-weight:bold; font-size:1em; margin:0 0 .1em;
     border-bottom:1px solid #CCC;}
+.emphasis {font-weight:bold; text-align:center; font-size:1.3em;}
 
 /* A regular table */
 .table {border-collapse:collapse; border-bottom:2px solid #888; margin-left:2em; }
@@ -66,3 +67,5 @@ q:after {
 /* Marks off sections that are lacking. */
 .fixme {margin-left:2em; }
 .fixme:before {content:"Fix me: "; font-weight:bold; color:#C00; }
+
+#applicability {margin: 1em 5%; font-style:italic;}

library/HTMLPurifier.php

@@ -22,7 +22,7 @@
  */
 
 /*
-    HTML Purifier 1.4.1 - Standards Compliant HTML Filtering
+    HTML Purifier 2.0.0 - Standards Compliant HTML Filtering
     Copyright (C) 2006 Edward Z. Yang
 
     This library is free software; you can redistribute it and/or
@@ -42,7 +42,7 @@
 
 // almost every class has an undocumented dependency to these, so make sure
 // they get included
-require_once 'HTMLPurifier/ConfigSchema.php';
+require_once 'HTMLPurifier/ConfigSchema.php'; // important
 require_once 'HTMLPurifier/Config.php';
 require_once 'HTMLPurifier/Context.php';
 
@@ -51,6 +51,23 @@ require_once 'HTMLPurifier/Generator.php';
 require_once 'HTMLPurifier/Strategy/Core.php';
 require_once 'HTMLPurifier/Encoder.php';
 
+require_once 'HTMLPurifier/LanguageFactory.php';
+
+HTMLPurifier_ConfigSchema::define(
+    'Core', 'Language', 'en', 'string', '
+ISO 639 language code for localizable things in HTML Purifier to use,
+which is mainly error reporting. There is currently only an English (en)
+translation, so this directive is currently useless.
+This directive has been available since 2.0.0.
+');
+
+HTMLPurifier_ConfigSchema::define(
+    'Core', 'CollectErrors', false, 'bool', '
+Whether or not to collect errors found while filtering the document. This
+is a useful way to give feedback to your users. CURRENTLY NOT IMPLEMENTED.
+This directive has been available since 2.0.0.
+');
+
 /**
  * Main library execution class.
  * 
@@ -64,12 +81,12 @@ require_once 'HTMLPurifier/Encoder.php';
 class HTMLPurifier
 {
     
-    var $version = '1.4.1';
+    var $version = '2.0.0';
     
     var $config;
     var $filters;
     
-    var $lexer, $strategy, $generator;
+    var $strategy, $generator;
     
     /**
      * Final HTMLPurifier_Context of last run purification. Might be an array.
@@ -89,7 +106,6 @@ class HTMLPurifier
         
         $this->config = HTMLPurifier_Config::create($config);
         
-        $this->lexer        = HTMLPurifier_Lexer::create();
         $this->strategy     = new HTMLPurifier_Strategy_Core();
         $this->generator    = new HTMLPurifier_Generator();
         
@@ -117,7 +133,23 @@ class HTMLPurifier
         
         $config = $config ? HTMLPurifier_Config::create($config) : $this->config;
         
+        // implementation is partially environment dependant, partially
+        // configuration dependant
+        $lexer = HTMLPurifier_Lexer::create($config);
+        
         $context = new HTMLPurifier_Context();
+        
+        // set up global context variables
+        if ($config->get('Core', 'CollectErrors')) {
+            // may get moved out if other facilities use it
+            $language_factory = HTMLPurifier_LanguageFactory::instance();
+            $language = $language_factory->create($config->get('Core', 'Language'));
+            $context->register('Locale', $language);
+            
+            $error_collector = new HTMLPurifier_ErrorCollector();
+            $context->register('ErrorCollector', $language);
+        }
+        
         $html = HTMLPurifier_Encoder::convertToUTF8($html, $config, $context);
         
         for ($i = 0, $size = count($this->filters); $i < $size; $i++) {
@@ -130,7 +162,7 @@ class HTMLPurifier
                 // list of tokens
                 $this->strategy->execute(
                     // list of un-purified tokens
-                    $this->lexer->tokenizeHTML(
+                    $lexer->tokenizeHTML(
                         // un-purified HTML
                         $html, $config, $context
                     ),
@@ -164,6 +196,23 @@ class HTMLPurifier
         return $array_of_html;
     }
     
+    /**
+     * Singleton for enforcing just one HTML Purifier in your system
+     */
+    function &getInstance($prototype = null) {
+        static $htmlpurifier;
+        if (!$htmlpurifier || $prototype) {
+            if (is_a($prototype, 'HTMLPurifier')) {
+                $htmlpurifier = $prototype;
+            } elseif ($prototype) {
+                $htmlpurifier = new HTMLPurifier(HTMLPurifier_Config::create($prototype));
+            } else {
+                $htmlpurifier = new HTMLPurifier();
+            }
+        }
+        return $htmlpurifier;
+    }
+    
     
 }
 

library/HTMLPurifier/AttrCollections.php

@@ -1,7 +1,6 @@
 <?php
 
 require_once 'HTMLPurifier/AttrTypes.php';
-require_once 'HTMLPurifier/AttrDef/Lang.php';
 
 /**
  * Defines common attribute collections that modules reference
@@ -12,8 +11,6 @@ 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();
     
@@ -25,27 +22,29 @@ class HTMLPurifier_AttrCollections
      * @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 => $coll) {
+                if (!isset($this->info[$coll_i])) {
+                    $this->info[$coll_i] = array();
+                }
                 foreach ($coll as $attr_i => $attr) {
-                    if ($attr_i === 0 && isset($info[$coll_i][$attr_i])) {
+                    if ($attr_i === 0 && isset($this->info[$coll_i][$attr_i])) {
                         // merge in includes
-                        $info[$coll_i][$attr_i] = array_merge(
-                            $info[$coll_i][$attr_i], $attr);
+                        $this->info[$coll_i][$attr_i] = array_merge(
+                            $this->info[$coll_i][$attr_i], $attr);
                         continue;
                     }
-                    $info[$coll_i][$attr_i] = $attr;
+                    $this->info[$coll_i][$attr_i] = $attr;
                 }
             }
         }
         // perform internal expansions and inclusions
-        foreach ($info as $name => $attr) {
+        foreach ($this->info as $name => $attr) {
             // merge attribute collections that include others
-            $this->performInclusions($info[$name]);
+            $this->performInclusions($this->info[$name]);
             // replace string identifiers with actual attribute objects
-            $this->expandIdentifiers($info[$name], $attr_types);
+            $this->expandIdentifiers($this->info[$name], $attr_types);
         }
     }
     
@@ -57,16 +56,20 @@ class HTMLPurifier_AttrCollections
     function performInclusions(&$attr) {
         if (!isset($attr[0])) return;
         $merge = $attr[0];
+        $seen  = array(); // recursion guard
         // loop through all the inclusions
         for ($i = 0; isset($merge[$i]); $i++) {
+            if (isset($seen[$merge[$i]])) continue;
+            $seen[$merge[$i]] = true;
             // foreach attribute of the inclusion, copy it over
+            if (!isset($this->info[$merge[$i]])) continue;
             foreach ($this->info[$merge[$i]] as $key => $value) {
                 if (isset($attr[$key])) continue; // also catches more inclusions
                 $attr[$key] = $value;
             }
-            if (isset($info[$merge[$i]][0])) {
+            if (isset($this->info[$merge[$i]][0])) {
                 // recursion
-                $merge = array_merge($merge, isset($info[$merge[$i]][0]));
+                $merge = array_merge($merge, $this->info[$merge[$i]][0]);
             }
         }
         unset($attr[0]);
@@ -79,20 +82,47 @@ class HTMLPurifier_AttrCollections
      * @param $attr_types HTMLPurifier_AttrTypes instance
      */
     function expandIdentifiers(&$attr, $attr_types) {
+        
+        // because foreach will process new elements we add, make sure we
+        // skip duplicates
+        $processed = array();
+        
         foreach ($attr as $def_i => $def) {
+            // skip inclusions
             if ($def_i === 0) continue;
-            if (!is_string($def)) continue;
+            
+            if (isset($processed[$def_i])) continue;
+            
+            // determine whether or not attribute is required
+            if ($required = (strpos($def_i, '*') !== false)) {
+                // rename the definition
+                unset($attr[$def_i]);
+                $def_i = trim($def_i, '*');
+                $attr[$def_i] = $def;
+            }
+            
+            $processed[$def_i] = true;
+            
+            // if we've already got a literal object, move on
+            if (is_object($def)) {
+                // preserve previous required
+                $attr[$def_i]->required = ($required || $attr[$def_i]->required);
+                continue;
+            }
+            
             if ($def === false) {
                 unset($attr[$def_i]);
                 continue;
             }
-            if (isset($attr_types->info[$def])) {
-                $attr[$def_i] = $attr_types->info[$def];
+            
+            if ($t = $attr_types->get($def)) {
+                $attr[$def_i] = $t;
+                $attr[$def_i]->required = $required;
             } else {
-                trigger_error('Attempted to reference undefined attribute type', E_USER_ERROR);
                 unset($attr[$def_i]);
             }
         }
+        
     }
     
 }

library/HTMLPurifier/AttrDef.php

@@ -14,11 +14,17 @@ class HTMLPurifier_AttrDef
 {
     
     /**
-     * Tells us whether or not an HTML attribute is minimized. Only the
-     * boolean attribute vapourware would use this.
+     * Tells us whether or not an HTML attribute is minimized. Has no
+     * meaning in other contexts.
      */
     var $minimized = false;
     
+    /**
+     * Tells us whether or not an HTML attribute is required. Has no
+     * meaning in other contexts
+     */
+    var $required = false;
+    
     /**
      * Validates and cleans passed string according to a definition.
      * 
@@ -62,6 +68,20 @@ class HTMLPurifier_AttrDef
         $string = str_replace(array("\r", "\t"), ' ', $string);
         return $string;
     }
+    
+    /**
+     * Factory method for creating this class from a string.
+     * @param $string String construction info
+     * @return Created AttrDef object corresponding to $string
+     * @public
+     */
+    function make($string) {
+        // default implementation, return flyweight of this object
+        // if overloaded, it is *necessary* for you to clone the
+        // object (usually by instantiating a new copy) and return that
+        return $this;
+    }
+    
 }
 
 ?>

library/HTMLPurifier/AttrDef/CSS/Color.php

@@ -2,43 +2,47 @@
 
 require_once 'HTMLPurifier/AttrDef.php';
 
+HTMLPurifier_ConfigSchema::define(
+    'Core', 'ColorKeywords', array(
+        'maroon'    => '#800000',
+        'red'       => '#FF0000',
+        'orange'    => '#FFA500',
+        'yellow'    => '#FFFF00',
+        'olive'     => '#808000',
+        'purple'    => '#800080',
+        'fuchsia'   => '#FF00FF',
+        'white'     => '#FFFFFF',
+        'lime'      => '#00FF00',
+        'green'     => '#008000',
+        'navy'      => '#000080',
+        'blue'      => '#0000FF',
+        'aqua'      => '#00FFFF',
+        'teal'      => '#008080',
+        'black'     => '#000000',
+        'silver'    => '#C0C0C0',
+        'gray'      => '#808080'
+    ), 'hash', '
+Lookup array of color names to six digit hexadecimal number corresponding
+to color, with preceding hash mark. Used when parsing colors.
+This directive has been available since 2.0.0.
+');
+
 /**
  * Validates Color as defined by CSS.
  */
 class HTMLPurifier_AttrDef_CSS_Color extends HTMLPurifier_AttrDef
 {
     
-    /**
-     * Color keyword lookup table.
-     * @todo Extend it to include all usually allowed colors.
-     */
-    var $colors = array(
-        'maroon'    => '#800000',
-        'red'       => '#F00',
-        'orange'    => '#FFA500',
-        'yellow'    => '#FF0',
-        'olive'     => '#808000',
-        'purple'    => '#800080',
-        'fuchsia'   => '#F0F',
-        'white'     => '#FFF',
-        'lime'      => '#0F0',
-        'green'     => '#008000',
-        'navy'      => '#000080',
-        'blue'      => '#00F',
-        'aqua'      => '#0FF',
-        'teal'      => '#008080',
-        'black'     => '#000',
-        'silver'    => '#C0C0C0',
-        'gray'      => '#808080'
-    );
-    
     function validate($color, $config, &$context) {
         
+        static $colors = null;
+        if ($colors === null) $colors = $config->get('Core', 'ColorKeywords');
+        
         $color = trim($color);
         if (!$color) return false;
         
         $lower = strtolower($color);
-        if (isset($this->colors[$lower])) return $this->colors[$lower];
+        if (isset($colors[$lower])) return $colors[$lower];
         
         if ($color[0] === '#') {
             // hexadecimal handling

library/HTMLPurifier/AttrDef/CSS/Font.php

@@ -18,18 +18,6 @@ class HTMLPurifier_AttrDef_CSS_Font extends HTMLPurifier_AttrDef
      */
     var $info = array();
     
-    /**
-     * System font keywords.
-     */
-    var $system_fonts = array(
-        'caption' => true,
-        'icon' => true,
-        'menu' => true,
-        'message-box' => true,
-        'small-caption' => true,
-        'status-bar' => true
-    );
-    
     function HTMLPurifier_AttrDef_CSS_Font($config) {
         $def = $config->getCSSDefinition();
         $this->info['font-style']   = $def->info['font-style'];
@@ -42,13 +30,22 @@ class HTMLPurifier_AttrDef_CSS_Font extends HTMLPurifier_AttrDef
     
     function validate($string, $config, &$context) {
         
+        static $system_fonts = array(
+            'caption' => true,
+            'icon' => true,
+            'menu' => true,
+            'message-box' => true,
+            'small-caption' => true,
+            'status-bar' => true
+        );
+        
         // regular pre-processing
         $string = $this->parseCDATA($string);
         if ($string === '') return false;
         
         // check if it's one of the keywords
         $lowercase_string = strtolower($string);
-        if (isset($this->system_fonts[$lowercase_string])) {
+        if (isset($system_fonts[$lowercase_string])) {
             return $lowercase_string;
         }
         

library/HTMLPurifier/AttrDef/CSS/FontFamily.php

@@ -10,19 +10,15 @@ require_once 'HTMLPurifier/AttrDef.php';
 class HTMLPurifier_AttrDef_CSS_FontFamily extends HTMLPurifier_AttrDef
 {
     
-    /**
-     * Generic font family keywords.
-     * @protected
-     */
-    var $generic_names = array(
-        'serif' => true,
-        'sans-serif' => true,
-        'monospace' => true,
-        'fantasy' => true,
-        'cursive' => true
-    );
-    
     function validate($string, $config, &$context) {
+        static $generic_names = array(
+            'serif' => true,
+            'sans-serif' => true,
+            'monospace' => true,
+            'fantasy' => true,
+            'cursive' => true
+        );
+        
         $string = $this->parseCDATA($string);
         // assume that no font names contain commas in them
         $fonts = explode(',', $string);
@@ -31,7 +27,7 @@ class HTMLPurifier_AttrDef_CSS_FontFamily extends HTMLPurifier_AttrDef
             $font = trim($font);
             if ($font === '') continue;
             // match a generic name
-            if (isset($this->generic_names[$font])) {
+            if (isset($generic_names[$font])) {
                 $final .= $font . ', ';
                 continue;
             }

library/HTMLPurifier/AttrDef/CSS/TextDecoration.php

@@ -10,23 +10,19 @@ require_once 'HTMLPurifier/AttrDef.php';
 class HTMLPurifier_AttrDef_CSS_TextDecoration extends HTMLPurifier_AttrDef
 {
     
-    /**
-     * Lookup table of allowed values.
-     * @protected
-     */
-    var $allowed_values = array(
-        'line-through' => true,
-        'overline' => true,
-        'underline' => true
-    );
-    
     function validate($string, $config, &$context) {
         
+        static $allowed_values = array(
+            'line-through' => true,
+            'overline' => true,
+            'underline' => true
+        );
+        
         $string = strtolower($this->parseCDATA($string));
         $parts = explode(' ', $string);
         $final = '';
         foreach ($parts as $part) {
-            if (isset($this->allowed_values[$part])) {
+            if (isset($allowed_values[$part])) {
                 $final .= $part . ' ';
             }
         }

library/HTMLPurifier/AttrDef/CSS/URI.php

@@ -29,7 +29,7 @@ class HTMLPurifier_AttrDef_CSS_URI extends HTMLPurifier_AttrDef_URI
         if ($uri_string[$new_length] != ')') return false;
         $uri = trim(substr($uri_string, 0, $new_length));
         
-        if (isset($uri[0]) && ($uri[0] == "'" || $uri[0] == '"')) {
+        if (!empty($uri) && ($uri[0] == "'" || $uri[0] == '"')) {
             $quote = $uri[0];
             $new_length = strlen($uri) - 1;
             if ($uri[$new_length] !== $quote) return false;

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
 {
@@ -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]);
@@ -41,6 +45,22 @@ class HTMLPurifier_AttrDef_Enum extends HTMLPurifier_AttrDef
         return $result ? $string : false;
     }
     
+    /**
+     * @param $string In form of comma-delimited list of case-insensitive
+     *      valid values. Example: "foo,bar,baz". Prepend "s:" to make
+     *      case sensitive
+     */
+    function make($string) {
+        if (strlen($string) > 2 && $string[0] == 's' && $string[1] == ':') {
+            $string = substr($string, 2);
+            $sensitive = true;
+        } else {
+            $sensitive = false;
+        }
+        $values = explode(',', $string);
+        return new HTMLPurifier_AttrDef_Enum($values, $sensitive);
+    }
+    
 }
 
 ?>

library/HTMLPurifier/AttrDef/HTML/Bool.php

@@ -0,0 +1,30 @@
+<?php
+
+require_once 'HTMLPurifier/AttrDef.php';
+
+/**
+ * Validates a boolean attribute
+ */
+class HTMLPurifier_AttrDef_HTML_Bool extends HTMLPurifier_AttrDef
+{
+    
+    var $name;
+    var $minimized = true;
+    
+    function HTMLPurifier_AttrDef_HTML_Bool($name = false) {$this->name = $name;}
+    
+    function validate($string, $config, &$context) {
+        if (empty($string)) return false;
+        return $this->name;
+    }
+    
+    /**
+     * @param $string Name of attribute
+     */
+    function make($string) {
+        return new HTMLPurifier_AttrDef_HTML_Bool($string);
+    }
+    
+}
+
+?>

library/HTMLPurifier/AttrDef/HTML/Color.php

@@ -0,0 +1,35 @@
+<?php
+
+require_once 'HTMLPurifier/AttrDef.php';
+require_once 'HTMLPurifier/AttrDef/CSS/Color.php'; // for %Core.ColorKeywords
+
+/**
+ * Validates a color according to the HTML spec.
+ */
+class HTMLPurifier_AttrDef_HTML_Color extends HTMLPurifier_AttrDef
+{
+    
+    function validate($string, $config, &$context) {
+        
+        static $colors = null;
+        if ($colors === null) $colors = $config->get('Core', 'ColorKeywords');
+        
+        $string = trim($string);
+        
+        if (empty($string)) return false;
+        if (isset($colors[$string])) return $colors[$string];
+        if ($string[0] === '#') $hex = substr($string, 1);
+        else $hex = $string;
+        
+        $length = strlen($hex);
+        if ($length !== 3 && $length !== 6) return false;
+        if (!ctype_xdigit($hex)) return false;
+        if ($length === 3) $hex = $hex[0].$hex[0].$hex[1].$hex[1].$hex[2].$hex[2];
+        
+        return "#$hex";
+        
+    }
+    
+}
+
+?>

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

@@ -43,6 +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
@@ -94,6 +102,11 @@ class HTMLPurifier_AttrDef_HTML_ID extends HTMLPurifier_AttrDef
             $result = ($trim === '');
         }
         
+        $regexp = $config->get('Attr', 'IDBlacklistRegexp');
+        if ($regexp && preg_match($regexp, $id)) {
+            return false;
+        }
+        
         if (/*!$this->ref && */$result) $id_accumulator->add($id);
         
         // if no change was made to the ID, return the result

library/HTMLPurifier/AttrDef/HTML/LinkTypes.php

@@ -0,0 +1,73 @@
+<?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
+{
+    
+    /** Name config attribute to pull. */
+    var $name;
+    
+    function HTMLPurifier_AttrDef_HTML_LinkTypes($name) {
+        $configLookup = array(
+            'rel' => 'AllowedRel',
+            'rev' => 'AllowedRev'
+        );
+        if (!isset($configLookup[$name])) {
+            trigger_error('Unrecognized attribute name for link '.
+                'relationship.', E_USER_ERROR);
+            return;
+        }
+        $this->name = $configLookup[$name];
+    }
+    
+    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/URI.php

@@ -93,7 +93,6 @@ class HTMLPurifier_AttrDef_URI extends HTMLPurifier_AttrDef
 {
     
     var $host;
-    var $PercentEncoder;
     var $embeds_resource;
     
     /**
@@ -101,12 +100,14 @@ class HTMLPurifier_AttrDef_URI extends HTMLPurifier_AttrDef
      */
     function HTMLPurifier_AttrDef_URI($embeds_resource = false) {
         $this->host = new HTMLPurifier_AttrDef_URI_Host();
-        $this->PercentEncoder = new HTMLPurifier_PercentEncoder();
         $this->embeds_resource = (bool) $embeds_resource;
     }
     
     function validate($uri, $config, &$context) {
         
+        static $PercentEncoder = null;
+        if ($PercentEncoder === null) $PercentEncoder = new HTMLPurifier_PercentEncoder();
+        
         // We'll write stack-based parsers later, for now, use regexps to
         // get things working as fast as possible (irony)
         
@@ -116,7 +117,7 @@ class HTMLPurifier_AttrDef_URI extends HTMLPurifier_AttrDef
         $uri = $this->parseCDATA($uri);
         
         // fix up percent-encoding
-        $uri = $this->PercentEncoder->normalize($uri);
+        $uri = $PercentEncoder->normalize($uri);
         
         // while it would be nice to use parse_url(), that's specifically
         // for HTTP and thus won't work for our generic URI parsing
@@ -157,6 +158,14 @@ class HTMLPurifier_AttrDef_URI extends HTMLPurifier_AttrDef
             );
         }
         
+        // something funky weird happened in the registry, abort!
+        if (!$scheme_obj) {
+            trigger_error(
+                'Default scheme object "' . $config->get('URI', 'DefaultScheme') . '" was not readable',
+                E_USER_WARNING
+            );
+            return false;
+        }
         
         // the URI we're processing embeds_resource a resource in the page, but the URI
         // it references cannot be located

library/HTMLPurifier/AttrDef/URI/IPv4.php

@@ -15,13 +15,10 @@ class HTMLPurifier_AttrDef_URI_IPv4 extends HTMLPurifier_AttrDef
      */
     var $ip4;
     
-    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}\\.{$oct})";
-    }
-    
     function validate($aIP, $config, &$context) {
         
+        if (!$this->ip4) $this->_loadRegex();
+        
         if (preg_match('#^' . $this->ip4 . '$#s', $aIP))
         {
                 return $aIP;
@@ -31,6 +28,15 @@ class HTMLPurifier_AttrDef_URI_IPv4 extends HTMLPurifier_AttrDef
         
     }
     
+    /**
+     * Lazy load function to prevent regex from being stuffed in
+     * cache.
+     */
+    function _loadRegex() {
+        $oct = '(?:25[0-5]|2[0-4][0-9]|1[0-9]{2}|[1-9][0-9]|[0-9])'; // 0-255
+        $this->ip4 = "(?:{$oct}\\.{$oct}\\.{$oct}\\.{$oct})";
+    }
+    
 }
 
 ?>

library/HTMLPurifier/AttrDef/URI/IPv6.php

@@ -13,6 +13,8 @@ class HTMLPurifier_AttrDef_URI_IPv6 extends HTMLPurifier_AttrDef_URI_IPv4
     
     function validate($aIP, $config, &$context) {
         
+        if (!$this->ip4) $this->_loadRegex();
+        
         $original = $aIP;
         
         $hex = '[0-9a-fA-F]';

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/ImgRequired.php

@@ -20,7 +20,10 @@ HTMLPurifier_ConfigSchema::define(
 );
 
 /**
- * Post-transform that ensures the required attrs of img (alt and src) are set
+ * Transform that supplies default values for the src and alt attributes
+ * in img tags, as well as prevents the img tag from being removed
+ * because of a missing alt tag. This needs to be registered as both
+ * a pre and post attribute transform.
  */
 class HTMLPurifier_AttrTransform_ImgRequired extends HTMLPurifier_AttrTransform
 {
@@ -29,6 +32,7 @@ class HTMLPurifier_AttrTransform_ImgRequired extends HTMLPurifier_AttrTransform
         
         $src = true;
         if (!isset($attr['src'])) {
+            if ($config->get('Core', 'RemoveInvalidImg')) return $attr;
             $attr['src'] = $config->get('Attr', 'DefaultInvalidImage');
             $src = false;
         }

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

@@ -1,10 +1,14 @@
 <?php
 
+require_once 'HTMLPurifier/AttrDef/Lang.php';
+require_once 'HTMLPurifier/AttrDef/Enum.php';
+require_once 'HTMLPurifier/AttrDef/HTML/Bool.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/HTML/Color.php';
 require_once 'HTMLPurifier/AttrDef/Integer.php';
 require_once 'HTMLPurifier/AttrDef/Text.php';
 require_once 'HTMLPurifier/AttrDef/URI.php';
@@ -16,14 +20,19 @@ class HTMLPurifier_AttrTypes
 {
     /**
      * Lookup array of attribute string identifiers to concrete implementations
-     * @public
+     * @protected
      */
     var $info = array();
     
     /**
-     * Constructs the info array
+     * Constructs the info array, supplying default implementations for attribute
+     * types.
      */
     function HTMLPurifier_AttrTypes() {
+        // pseudo-types, must be instantiated via shorthand
+        $this->info['Enum']    = new HTMLPurifier_AttrDef_Enum();
+        $this->info['Bool']    = new HTMLPurifier_AttrDef_HTML_Bool();
+        
         $this->info['CDATA']    = new HTMLPurifier_AttrDef_Text();
         $this->info['ID']       = new HTMLPurifier_AttrDef_HTML_ID();
         $this->info['Length']   = new HTMLPurifier_AttrDef_HTML_Length();
@@ -32,10 +41,42 @@ class HTMLPurifier_AttrTypes
         $this->info['Pixels']   = new HTMLPurifier_AttrDef_HTML_Pixels();
         $this->info['Text']     = new HTMLPurifier_AttrDef_Text();
         $this->info['URI']      = new HTMLPurifier_AttrDef_URI();
+        $this->info['LanguageCode'] = new HTMLPurifier_AttrDef_Lang();
+        $this->info['Color']    = new HTMLPurifier_AttrDef_HTML_Color();
         
         // number is really a positive integer (one or more digits)
+        // FIXME: ^^ not always, see start and value of list items
         $this->info['Number']   = new HTMLPurifier_AttrDef_Integer(false, false, true);
     }
+    
+    /**
+     * Retrieves a type
+     * @param $type String type name
+     * @return Object AttrDef for type
+     */
+    function get($type) {
+        
+        // determine if there is any extra info tacked on
+        if (strpos($type, '#') !== false) list($type, $string) = explode('#', $type, 2);
+        else $string = '';
+        
+        if (!isset($this->info[$type])) {
+            trigger_error('Cannot retrieve undefined attribute type ' . $type, E_USER_ERROR);
+            return;
+        }
+        
+        return $this->info[$type]->make($string);
+        
+    }
+    
+    /**
+     * Sets a new implementation for a type
+     * @param $type String type name
+     * @param $impl Object AttrDef for type
+     */
+    function set($type, $impl) {
+        $this->info[$type] = $impl;
+    }
 }
 
 ?>

library/HTMLPurifier/AttrValidator.php

@@ -0,0 +1,105 @@
+<?php
+
+class HTMLPurifier_AttrValidator
+{
+    
+    
+    function validateToken($token, &$config, &$context) {
+            
+        $definition = $config->getHTMLDefinition();
+        
+        // create alias to global definition array, see also $defs
+        // DEFINITION CALL
+        $d_defs = $definition->info_global_attr;
+        
+        // copy out attributes for easy manipulation
+        $attr = $token->attr;
+        
+        // do global transformations (pre)
+        // nothing currently utilizes this
+        foreach ($definition->info_attr_transform_pre as $transform) {
+            $attr = $transform->transform($attr, $config, $context);
+        }
+        
+        // do local transformations only applicable to this element (pre)
+        // ex. <p align="right"> to <p style="text-align:right;">
+        foreach ($definition->info[$token->name]->attr_transform_pre
+            as $transform
+        ) {
+            $attr = $transform->transform($attr, $config, $context);
+        }
+        
+        // create alias to this element's attribute definition array, see
+        // also $d_defs (global attribute definition array)
+        // DEFINITION CALL
+        $defs = $definition->info[$token->name]->attr;
+        
+        // iterate through all the attribute keypairs
+        // Watch out for name collisions: $key has previously been used
+        foreach ($attr as $attr_key => $value) {
+            
+            // call the definition
+            if ( isset($defs[$attr_key]) ) {
+                // there is a local definition defined
+                if ($defs[$attr_key] === false) {
+                    // We've explicitly been told not to allow this element.
+                    // This is usually when there's a global definition
+                    // that must be overridden.
+                    // Theoretically speaking, we could have a
+                    // AttrDef_DenyAll, but this is faster!
+                    $result = false;
+                } else {
+                    // validate according to the element's definition
+                    $result = $defs[$attr_key]->validate(
+                                    $value, $config, $context
+                               );
+                }
+            } elseif ( isset($d_defs[$attr_key]) ) {
+                // there is a global definition defined, validate according
+                // to the global definition
+                $result = $d_defs[$attr_key]->validate(
+                                $value, $config, $context
+                           );
+            } else {
+                // system never heard of the attribute? DELETE!
+                $result = false;
+            }
+            
+            // put the results into effect
+            if ($result === false || $result === null) {
+                // remove the attribute
+                unset($attr[$attr_key]);
+            } elseif (is_string($result)) {
+                // simple substitution
+                $attr[$attr_key] = $result;
+            }
+            
+            // we'd also want slightly more complicated substitution
+            // involving an array as the return value,
+            // although we're not sure how colliding attributes would
+            // resolve (certain ones would be completely overriden,
+            // others would prepend themselves).
+        }
+        
+        // post transforms
+        
+        // ex. <x lang="fr"> to <x lang="fr" xml:lang="fr">
+        foreach ($definition->info_attr_transform_post as $transform) {
+            $attr = $transform->transform($attr, $config, $context);
+        }
+        
+        // ex. <bdo> to <bdo dir="ltr">
+        foreach ($definition->info[$token->name]->attr_transform_post as $transform) {
+            $attr = $transform->transform($attr, $config, $context);
+        }
+        
+        // commit changes
+        $token->attr = $attr;
+        return $token;
+        
+    }
+    
+    
+}
+
+?>

library/HTMLPurifier/CSSDefinition.php

@@ -1,5 +1,7 @@
 <?php
 
+require_once 'HTMLPurifier/Definition.php';
+
 require_once 'HTMLPurifier/AttrDef/CSS/Background.php';
 require_once 'HTMLPurifier/AttrDef/CSS/BackgroundPosition.php';
 require_once 'HTMLPurifier/AttrDef/CSS/Border.php';
@@ -15,13 +17,24 @@ require_once 'HTMLPurifier/AttrDef/CSS/TextDecoration.php';
 require_once 'HTMLPurifier/AttrDef/CSS/URI.php';
 require_once 'HTMLPurifier/AttrDef/Enum.php';
 
+HTMLPurifier_ConfigSchema::define(
+    'CSS', 'DefinitionRev', 1, 'int', '
+<p>
+    Revision identifier for your custom definition. See
+    %HTML.DefinitionRev for details. This directive has been available
+    since 2.0.0.
+</p>
+');
+
 /**
  * Defines allowed CSS attributes and what their values are.
  * @see HTMLPurifier_HTMLDefinition
  */
-class HTMLPurifier_CSSDefinition
+class HTMLPurifier_CSSDefinition extends HTMLPurifier_Definition
 {
     
+    var $type = 'CSS';
+    
     /**
      * Assoc array of attribute name to definition object.
      */
@@ -30,7 +43,7 @@ class HTMLPurifier_CSSDefinition
     /**
      * Constructs the info array.  The meat of this class.
      */
-    function setup($config) {
+    function doSetup($config) {
         
         $this->info['text-align'] = new HTMLPurifier_AttrDef_Enum(
             array('left', 'right', 'center', 'justify'), false);
@@ -162,7 +175,9 @@ class HTMLPurifier_CSSDefinition
             new HTMLPurifier_AttrDef_CSS_Percentage()
         ));
         
-        $this->info['width'] = new HTMLPurifier_AttrDef_CSS_Composite(array(
+        $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'))
@@ -204,6 +219,9 @@ class HTMLPurifier_CSSDefinition
             new HTMLPurifier_AttrDef_CSS_Percentage()
         ));
         
+        // partial support
+        $this->info['white-space'] = new HTMLPurifier_AttrDef_Enum(array('nowrap'));
+        
     }
     
 }

library/HTMLPurifier/ChildDef/Custom.php

@@ -38,8 +38,21 @@ class HTMLPurifier_ChildDef_Custom extends HTMLPurifier_ChildDef
         if ($raw{0} != '(') {
             $raw = "($raw)";
         }
-        $reg = str_replace(',', ',?', $raw);
-        $reg = preg_replace('/([#a-zA-Z0-9_.-]+)/', '(,?\\0)', $reg);
+        $el = '[#a-zA-Z0-9_.-]+';
+        $reg = $raw;
+        
+        // COMPLICATED! AND MIGHT BE BUGGY! I HAVE NO CLUE WHAT I'M
+        // DOING! Seriously: if there's problems, please report them.
+        
+        // setup all elements as parentheticals with leading commas
+        $reg = preg_replace("/$el/", '(,\\0)', $reg);
+        
+        // remove commas when they were not solicited
+        $reg = preg_replace("/([^,(|]\(+),/", '\\1', $reg);
+        
+        // remove all non-paranthetical commas: they are handled by first regex
+        $reg = preg_replace("/,\(/", '(', $reg);
+        
         $this->_pcre_regex = $reg;
     }
     function validateChildren($tokens_of_children, $config, &$context) {
@@ -60,11 +73,11 @@ class HTMLPurifier_ChildDef_Custom extends HTMLPurifier_ChildDef
                 $list_of_children .= $token->name . ',';
             }
         }
-        $list_of_children = rtrim($list_of_children, ',');
-        
+        // add leading comma to deal with stray comma declarations
+        $list_of_children = ',' . rtrim($list_of_children, ',');
         $okay =
             preg_match(
-                '/^'.$this->_pcre_regex.'$/',
+                '/^,?'.$this->_pcre_regex.'$/',
                 $list_of_children
             );
         

library/HTMLPurifier/ChildDef/Required.php

@@ -29,7 +29,6 @@ class HTMLPurifier_ChildDef_Required extends HTMLPurifier_ChildDef
             }
         }
         $this->elements = $elements;
-        $this->gen = new HTMLPurifier_Generator();
     }
     var $allow_empty = false;
     var $type = 'required';
@@ -57,6 +56,12 @@ class HTMLPurifier_ChildDef_Required extends HTMLPurifier_ChildDef
         // some configuration
         $escape_invalid_children = $config->get('Core', 'EscapeInvalidChildren');
         
+        // generator
+        static $gen = null;
+        if ($gen === null) {
+            $gen = new HTMLPurifier_Generator();
+        }
+        
         foreach ($tokens_of_children as $token) {
             if (!empty($token->is_whitespace)) {
                 $result[] = $token;
@@ -80,7 +85,7 @@ class HTMLPurifier_ChildDef_Required extends HTMLPurifier_ChildDef
                         $result[] = $token;
                     } elseif ($pcdata_allowed && $escape_invalid_children) {
                         $result[] = new HTMLPurifier_Token_Text(
-                            $this->gen->generateFromToken($token, $config)
+                            $gen->generateFromToken($token, $config)
                         );
                     }
                     continue;
@@ -91,7 +96,7 @@ class HTMLPurifier_ChildDef_Required extends HTMLPurifier_ChildDef
             } elseif ($pcdata_allowed && $escape_invalid_children) {
                 $result[] =
                     new HTMLPurifier_Token_Text(
-                        $this->gen->generateFromToken( $token, $config )
+                        $gen->generateFromToken( $token, $config )
                     );
             } else {
                 // drop silently

library/HTMLPurifier/ChildDef/StrictBlockquote.php

@@ -45,8 +45,8 @@ extends HTMLPurifier_ChildDef_Required
             if (!$is_inline) {
                 if (!$depth) {
                      if (
-                        $token->type == 'text' ||
-                        !isset($this->elements[$token->name])
+                        ($token->type == 'text' && !$token->is_whitespace) ||
+                        ($token->type != 'text' && !isset($this->elements[$token->name]))
                      ) {
                         $is_inline = true;
                         $ret[] = $block_wrap_start;

library/HTMLPurifier/Config.php

@@ -1,5 +1,28 @@
 <?php
 
+require_once 'HTMLPurifier/ConfigSchema.php';
+
+// member variables
+require_once 'HTMLPurifier/HTMLDefinition.php';
+require_once 'HTMLPurifier/CSSDefinition.php';
+require_once 'HTMLPurifier/Doctype.php';
+require_once 'HTMLPurifier/DefinitionCacheFactory.php';
+
+// accomodations for versions earlier than 4.3.10 and 5.0.2
+// borrowed from PHP_Compat, LGPL licensed, by Aidan Lister <aidan@php.net>
+if (!defined('PHP_EOL')) {
+    switch (strtoupper(substr(PHP_OS, 0, 3))) {
+        case 'WIN':
+            define('PHP_EOL', "\r\n");
+            break;
+        case 'DAR':
+            define('PHP_EOL', "\r");
+            break;
+        default:
+            define('PHP_EOL', "\n");
+    }
+}
+
 /**
  * Configuration object that triggers customizable behavior.
  *
@@ -15,6 +38,11 @@
 class HTMLPurifier_Config
 {
     
+    /**
+     * HTML Purifier's version
+     */
+    var $version = '2.0.0';
+    
     /**
      * Two-level associative array of configuration directives
      */
@@ -26,14 +54,26 @@ class HTMLPurifier_Config
     var $def;
     
     /**
-     * Cached instance of HTMLPurifier_HTMLDefinition
+     * Indexed array of definitions
      */
-    var $html_definition;
+    var $definitions;
     
     /**
-     * Cached instance of HTMLPurifier_CSSDefinition
+     * Bool indicator whether or not config is finalized
      */
-    var $css_definition;
+    var $finalized = false;
+    
+    /**
+     * Bool indicator whether or not to automatically finalize 
+     * the object if a read operation is done
+     */
+    var $autoFinalize = true;
+    
+    /**
+     * Namespace indexed array of serials for specific namespaces (see
+     * getSerial for more info).
+     */
+    var $serials = array();
     
     /**
      * @param $definition HTMLPurifier_ConfigSchema that defines what directives
@@ -58,6 +98,7 @@ class HTMLPurifier_Config
         $ret = HTMLPurifier_Config::createDefault();
         if (is_string($config)) $ret->loadIni($config);
         elseif (is_array($config)) $ret->loadArray($config);
+        if (isset($revision)) $ret->revision = $revision;
         return $ret;
     }
     
@@ -78,13 +119,16 @@ class HTMLPurifier_Config
      * @param $key String key
      */
     function get($namespace, $key, $from_alias = false) {
+        if (!$this->finalized && $this->autoFinalize) $this->finalize();
         if (!isset($this->def->info[$namespace][$key])) {
-            trigger_error('Cannot retrieve value of undefined directive',
+            // can't add % due to SimpleTest bug
+            trigger_error('Cannot retrieve value of undefined directive ' . htmlspecialchars("$namespace.$key"),
                 E_USER_WARNING);
             return;
         }
         if ($this->def->info[$namespace][$key]->class == 'alias') {
-            trigger_error('Cannot get value from aliased directive, use real name',
+            $d = $this->def->info[$namespace][$key];
+            trigger_error('Cannot get value from aliased directive, use real name ' . $d->namespace . '.' . $d->name,
                 E_USER_ERROR);
             return;
         }
@@ -96,14 +140,35 @@ class HTMLPurifier_Config
      * @param $namespace String namespace
      */
     function getBatch($namespace) {
+        if (!$this->finalized && $this->autoFinalize) $this->finalize();
         if (!isset($this->def->info[$namespace])) {
-            trigger_error('Cannot retrieve undefined namespace',
+            trigger_error('Cannot retrieve undefined namespace ' . htmlspecialchars($namespace),
                 E_USER_WARNING);
             return;
         }
         return $this->conf[$namespace];
     }
     
+    /**
+     * Returns a md5 signature of a segment of the configuration object
+     * that uniquely identifies that particular configuration
+     * @param $namespace Namespace to get serial for
+     */
+    function getBatchSerial($namespace) {
+        if (empty($this->serials[$namespace])) {
+            $this->serials[$namespace] = md5(serialize($this->getBatch($namespace)));
+        }
+        return $this->serials[$namespace];
+    }
+    
+    /**
+     * Retrieves all directives, organized by namespace
+     */
+    function getAll() {
+        if (!$this->finalized && $this->autoFinalize) $this->finalize();
+        return $this->conf;
+    }
+    
     /**
      * Sets a value to configuration.
      * @param $namespace String namespace
@@ -111,15 +176,16 @@ class HTMLPurifier_Config
      * @param $value Mixed value
      */
     function set($namespace, $key, $value, $from_alias = false) {
+        if ($this->isFinalized('Cannot set directive after finalization')) return;
         if (!isset($this->def->info[$namespace][$key])) {
-            trigger_error('Cannot set undefined directive to value',
+            trigger_error('Cannot set undefined directive ' . htmlspecialchars("$namespace.$key") . ' to value',
                 E_USER_WARNING);
             return;
         }
         if ($this->def->info[$namespace][$key]->class == 'alias') {
             if ($from_alias) {
                 trigger_error('Double-aliases not allowed, please fix '.
-                    'ConfigSchema bug');
+                    'ConfigSchema bug with' . "$namespace.$key");
             }
             $this->set($this->def->info[$namespace][$key]->namespace,
                        $this->def->info[$namespace][$key]->name,
@@ -128,7 +194,7 @@ class HTMLPurifier_Config
         }
         $value = $this->def->validate(
                     $value,
-                    $this->def->info[$namespace][$key]->type,
+                    $type = $this->def->info[$namespace][$key]->type,
                     $this->def->info[$namespace][$key]->allow_null
                  );
         if (is_string($value)) {
@@ -139,23 +205,36 @@ class HTMLPurifier_Config
             if ($this->def->info[$namespace][$key]->allowed !== true) {
                 // check to see if the value is allowed
                 if (!isset($this->def->info[$namespace][$key]->allowed[$value])) {
-                    trigger_error('Value not supported', E_USER_WARNING);
+                    trigger_error('Value not supported, valid values are: ' .
+                        $this->_listify($this->def->info[$namespace][$key]->allowed), E_USER_WARNING);
                     return;
                 }
             }
         }
         if ($this->def->isError($value)) {
-            trigger_error('Value is of invalid type', E_USER_WARNING);
+            trigger_error('Value for ' . "$namespace.$key" . ' is of invalid type, should be ' . $type, E_USER_WARNING);
             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') {
-            $this->css_definition = null;
+        
+        // reset definitions if the directives they depend on changed
+        // this is a very costly process, so it's discouraged 
+        // with finalization
+        if ($namespace == 'HTML' || $namespace == 'CSS') {
+            $this->definitions[$namespace] = null;
         }
+        
+        $this->serials[$namespace] = false;
+    }
+    
+    /**
+     * Convenience function for error reporting
+     * @private
+     */
+    function _listify($lookup) {
+        $list = array();
+        foreach ($lookup as $name => $b) $list[] = $name;
+        return implode(', ', $list);
     }
     
     /**
@@ -164,26 +243,71 @@ class HTMLPurifier_Config
      *             called before it's been setup, otherwise won't work.
      */
     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;
+        return $this->getDefinition('HTML', $raw);
     }
     
     /**
      * Retrieves reference to the CSS definition
      */
-    function &getCSSDefinition() {
-        if ($this->css_definition === null) {
-            $this->css_definition = new HTMLPurifier_CSSDefinition();
-            $this->css_definition->setup($this);
+    function &getCSSDefinition($raw = false) {
+        return $this->getDefinition('CSS', $raw);
+    }
+    
+    /**
+     * Retrieves a definition
+     * @param $type Type of definition: HTML, CSS, etc
+     * @param $raw  Whether or not definition should be returned raw
+     */
+    function &getDefinition($type, $raw = false) {
+        if (!$this->finalized && $this->autoFinalize) $this->finalize();
+        $factory = HTMLPurifier_DefinitionCacheFactory::instance();
+        $cache = $factory->create($type, $this);
+        if (!$raw) {
+            // see if we can quickly supply a definition
+            if (!empty($this->definitions[$type])) {
+                if (!$this->definitions[$type]->setup) {
+                    $this->definitions[$type]->setup($this);
+                }
+                return $this->definitions[$type];
+            }
+            // memory check missed, try cache
+            $this->definitions[$type] = $cache->get($this);
+            if ($this->definitions[$type]) {
+                // definition in cache, return it
+                return $this->definitions[$type];
+            }
+        } elseif (
+            !empty($this->definitions[$type]) &&
+            !$this->definitions[$type]->setup
+        ) {
+            // raw requested, raw in memory, quick return
+            return $this->definitions[$type];
         }
-        return $this->css_definition;
+        // quick checks failed, let's create the object
+        if ($type == 'HTML') {
+            $this->definitions[$type] = new HTMLPurifier_HTMLDefinition();
+        } elseif ($type == 'CSS') {
+            $this->definitions[$type] = new HTMLPurifier_CSSDefinition();
+        } else {
+            trigger_error("Definition of $type type not supported");
+            $false = false;
+            return $false;
+        }
+        // quick abort if raw
+        if ($raw) {
+            if (is_null($this->get($type, 'DefinitionID'))) {
+                // fatally error out if definition ID not set
+                trigger_error("Cannot retrieve raw version without specifying %$type.DefinitionID", E_USER_ERROR);
+                $false = false;
+                return $false;
+            }
+            return $this->definitions[$type];
+        }
+        // set it up
+        $this->definitions[$type]->setup($this);
+        // save in cache
+        $cache->set($this->definitions[$type], $this);
+        return $this->definitions[$type];
     }
     
     /**
@@ -192,6 +316,7 @@ class HTMLPurifier_Config
      * @param $config_array Configuration associative array
      */
     function loadArray($config_array) {
+        if ($this->isFinalized('Cannot load directives after finalization')) return;
         foreach ($config_array as $key => $value) {
             $key = str_replace('_', '.', $key);
             if (strpos($key, '.') !== false) {
@@ -208,15 +333,63 @@ class HTMLPurifier_Config
         }
     }
     
+    /**
+     * Loads configuration values from $_GET/$_POST that were posted
+     * via ConfigForm
+     * @param $array $_GET or $_POST array to import
+     * @param $index Index/name that the config variables are in
+     * @param $mq_fix Boolean whether or not to enable magic quotes fix
+     * @static
+     */
+    function loadArrayFromForm($array, $index, $mq_fix = true) {
+        $array = (isset($array[$index]) && is_array($array[$index])) ? $array[$index] : array();
+        $mq = get_magic_quotes_gpc() && $mq_fix;
+        foreach ($array as $key => $value) {
+            if (!strncmp($key, 'Null_', 5) && !empty($value)) {
+                unset($array[substr($key, 5)]);
+                unset($array[$key]);
+            }
+            if ($mq) $array[$key] = stripslashes($value);
+        }
+        return @HTMLPurifier_Config::create($array);
+    }
+    
     /**
      * Loads configuration values from an ini file
      * @param $filename Name of ini file
      */
     function loadIni($filename) {
+        if ($this->isFinalized('Cannot load directives after finalization')) return;
         $array = parse_ini_file($filename, true);
         $this->loadArray($array);
     }
     
+    /**
+     * Checks whether or not the configuration object is finalized.
+     * @param $error String error message, or false for no error
+     */
+    function isFinalized($error = false) {
+        if ($this->finalized && $error) {
+            trigger_error($error, E_USER_ERROR);
+        }
+        return $this->finalized;
+    }
+    
+    /**
+     * Finalizes configuration only if auto finalize is on and not
+     * already finalized
+     */
+    function autoFinalize() {
+        if (!$this->finalized && $this->autoFinalize) $this->finalize();
+    }
+    
+    /**
+     * Finalizes a configuration object, prohibiting further change
+     */
+    function finalize() {
+        $this->finalized = true;
+    }
+    
 }
 
 ?>

library/HTMLPurifier/ConfigSchema.php

@@ -8,6 +8,7 @@ require_once 'HTMLPurifier/ConfigDef/DirectiveAlias.php';
 
 /**
  * Configuration definition, defines directives and their defaults.
+ * @note If you update this, please update Printer_ConfigForm
  * @todo The ability to define things multiple times is confusing and should
  *       be factored out to its own function named registerDependency() or 
  *       addNote(), where only the namespace.name and an extra descriptions
@@ -66,6 +67,8 @@ class HTMLPurifier_ConfigSchema {
         $this->defineNamespace('URI', 'Features regarding Uniform Resource Identifiers.');
         $this->defineNamespace('HTML', 'Configuration regarding allowed HTML.');
         $this->defineNamespace('CSS', 'Configuration regarding allowed CSS.');
+        $this->defineNamespace('Output', 'Configuration relating to the generation of (X)HTML.');
+        $this->defineNamespace('Cache', 'Configuration for DefinitionCache and related subclasses.');
         $this->defineNamespace('Test', 'Developer testing configuration for our unit tests.');
     }
     
@@ -303,6 +306,7 @@ class HTMLPurifier_ConfigSchema {
         if ($allow_null && $var === null) return null;
         switch ($type) {
             case 'mixed':
+                //if (is_string($var)) $var = unserialize($var);
                 return $var;
             case 'istring':
             case 'string':
@@ -334,11 +338,25 @@ class HTMLPurifier_ConfigSchema {
             case 'hash':
             case 'lookup':
                 if (is_string($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);
                     // remove spaces
                     foreach ($var as $i => $j) $var[$i] = trim($j);
+                    if ($type === 'hash') {
+                        // key:value,key2:value2
+                        $nvar = array();
+                        foreach ($var as $keypair) {
+                            $c = explode(':', $keypair, 2);
+                            if (!isset($c[1])) continue;
+                            $nvar[$c[0]] = $c[1];
+                        }
+                        $var = $nvar;
+                    }
                 }
                 if (!is_array($var)) break;
                 $keys = array_keys($var);

library/HTMLPurifier/ContentSets.php

@@ -6,6 +6,8 @@ require_once 'HTMLPurifier/ChildDef/Empty.php';
 require_once 'HTMLPurifier/ChildDef/Required.php';
 require_once 'HTMLPurifier/ChildDef/Optional.php';
 
+// NOT UNIT TESTED!!!
+
 class HTMLPurifier_ContentSets
 {
     

library/HTMLPurifier/Definition.php

@@ -0,0 +1,41 @@
+<?php
+
+/**
+ * Super-class for definition datatype objects, implements serialization
+ * functions for the class.
+ */
+class HTMLPurifier_Definition
+{
+    
+    /**
+     * Has setup() been called yet?
+     */
+    var $setup = false;
+    
+    /**
+     * What type of definition is it?
+     */
+    var $type;
+    
+    /**
+     * Sets up the definition object into the final form, something
+     * not done by the constructor
+     * @param $config HTMLPurifier_Config instance
+     */
+    function doSetup($config) {
+        trigger_error('Cannot call abstract method', E_USER_ERROR);
+    }
+    
+    /**
+     * Setup function that aborts if already setup
+     * @param $config HTMLPurifier_Config instance
+     */
+    function setup($config) {
+        if ($this->setup) return;
+        $this->setup = true;
+        $this->doSetup($config);
+    }
+    
+}
+
+?>

library/HTMLPurifier/DefinitionCache.php

@@ -0,0 +1,121 @@
+<?php
+
+require_once 'HTMLPurifier/DefinitionCache/Serializer.php';
+require_once 'HTMLPurifier/DefinitionCache/Null.php';
+
+require_once 'HTMLPurifier/DefinitionCache/Decorator.php';
+
+/**
+ * Abstract class representing Definition cache managers that implements
+ * useful common methods and is a factory.
+ * @todo Get some sort of versioning variable so the library can easily
+ *       invalidate the cache with a new version
+ * @todo Make the test runner cache aware and allow the user to easily
+ *       flush the cache
+ * @todo Create a separate maintenance file advanced users can use to
+ *       cache their custom HTMLDefinition, which can be loaded
+ *       via a configuration directive
+ * @todo Implement memcached
+ */
+class HTMLPurifier_DefinitionCache
+{
+    
+    var $type;
+    
+    /**
+     * @param $name Type of definition objects this instance of the
+     *      cache will handle.
+     */
+    function HTMLPurifier_DefinitionCache($type) {
+        $this->type = $type;
+    }
+    
+    /**
+     * Generates a unique identifier for a particular configuration
+     * @param Instance of HTMLPurifier_Config
+     */
+    function generateKey($config) {
+        return $config->version . '-' . // possibly replace with function calls
+               $config->get($this->type, 'DefinitionRev') . '-' .
+               $config->getBatchSerial($this->type);
+    }
+    
+    /**
+     * Tests whether or not a key is old with respect to the configuration's
+     * version and revision number.
+     * @param $key Key to test
+     * @param $config Instance of HTMLPurifier_Config to test against
+     */
+    function isOld($key, $config) {
+        list($version, $revision, $hash) = explode('-', $key, 3);
+        $compare = version_compare($version, $config->version);
+        if ($compare > 0) return false;
+        if ($compare == 0 && $revision >= $config->get($this->type, 'DefinitionRev')) return false;
+        return true;
+    }
+    
+    /**
+     * Checks if a definition's type jives with the cache's type
+     * @note Throws an error on failure
+     * @param $def Definition object to check
+     * @return Boolean true if good, false if not
+     */
+    function checkDefType($def) {
+        if ($def->type !== $this->type) {
+            trigger_error("Cannot use definition of type {$def->type} in cache for {$this->type}");
+            return false;
+        }
+        return true;
+    }
+    
+    /**
+     * Adds a definition object to the cache
+     */
+    function add($def, $config) {
+        trigger_error('Cannot call abstract method', E_USER_ERROR);
+    }
+    
+    /**
+     * Unconditionally saves a definition object to the cache
+     */
+    function set($def, $config) {
+        trigger_error('Cannot call abstract method', E_USER_ERROR);
+    }
+    
+    /**
+     * Replace an object in the cache
+     */
+    function replace($def, $config) {
+        trigger_error('Cannot call abstract method', E_USER_ERROR);
+    }
+    
+    /**
+     * Retrieves a definition object from the cache
+     */
+    function get($config) {
+        trigger_error('Cannot call abstract method', E_USER_ERROR);
+    }
+    
+    /**
+     * Removes a definition object to the cache
+     */
+    function remove($config) {
+        trigger_error('Cannot call abstract method', E_USER_ERROR);
+    }
+    
+    /**
+     * Clears all objects from cache
+     */
+    function flush($config) {
+        trigger_error('Cannot call abstract method', E_USER_ERROR);
+    }
+    
+    /**
+     * Clears all expired (older version or revision) objects from cache
+     */
+    function cleanup($config) {
+        trigger_error('Cannot call abstract method', E_USER_ERROR);
+    }
+}
+
+?>

library/HTMLPurifier/DefinitionCache/Decorator.php

@@ -0,0 +1,63 @@
+<?php
+
+require_once 'HTMLPurifier/DefinitionCache.php';
+
+require_once 'HTMLPurifier/DefinitionCache/Decorator/Memory.php';
+require_once 'HTMLPurifier/DefinitionCache/Decorator/Cleanup.php';
+
+class HTMLPurifier_DefinitionCache_Decorator extends HTMLPurifier_DefinitionCache
+{
+    
+    /**
+     * Cache object we are decorating
+     */
+    var $cache;
+    
+    function HTMLPurifier_DefinitionCache_Decorator() {}
+    
+    /**
+     * Lazy decorator function
+     * @param $cache Reference to cache object to decorate
+     */
+    function decorate(&$cache) {
+        $decorator = $this->copy();
+        // reference is necessary for mocks in PHP 4
+        $decorator->cache =& $cache;
+        $decorator->type  = $cache->type;
+        return $decorator;
+    }
+    
+    /**
+     * Cross-compatible clone substitute
+     */
+    function copy() {
+        return new HTMLPurifier_DefinitionCache_Decorator();
+    }
+    
+    function add($def, $config) {
+        return $this->cache->add($def, $config);
+    }
+    
+    function set($def, $config) {
+        return $this->cache->set($def, $config);
+    }
+    
+    function replace($def, $config) {
+        return $this->cache->replace($def, $config);
+    }
+    
+    function get($config) {
+        return $this->cache->get($config);
+    }
+    
+    function flush($config) {
+        return $this->cache->flush($config);
+    }
+    
+    function cleanup($config) {
+        return $this->cache->cleanup($config);
+    }
+    
+}
+
+?>

library/HTMLPurifier/DefinitionCache/Decorator/Cleanup.php

@@ -0,0 +1,45 @@
+<?php
+
+require_once 'HTMLPurifier/DefinitionCache/Decorator.php';
+
+/**
+ * Definition cache decorator class that cleans up the cache
+ * whenever there is a cache miss.
+ */
+class HTMLPurifier_DefinitionCache_Decorator_Cleanup extends
+      HTMLPurifier_DefinitionCache_Decorator
+{
+    
+    var $name = 'Cleanup';
+    
+    function copy() {
+        return new HTMLPurifier_DefinitionCache_Decorator_Cleanup();
+    }
+    
+    function add($def, $config) {
+        $status = parent::add($def, $config);
+        if (!$status) parent::cleanup($config);
+        return $status;
+    }
+    
+    function set($def, $config) {
+        $status = parent::set($def, $config);
+        if (!$status) parent::cleanup($config);
+        return $status;
+    }
+    
+    function replace($def, $config) {
+        $status = parent::replace($def, $config);
+        if (!$status) parent::cleanup($config);
+        return $status;
+    }
+    
+    function get($config) {
+        $ret = parent::get($config);
+        if (!$ret) parent::cleanup($config);
+        return $ret;
+    }
+    
+}
+
+?>

library/HTMLPurifier/DefinitionCache/Decorator/Memory.php

@@ -0,0 +1,48 @@
+<?php
+
+require_once 'HTMLPurifier/DefinitionCache/Decorator.php';
+
+/**
+ * Definition cache decorator class that saves all cache retrievals
+ * to PHP's memory; good for unit tests or circumstances where 
+ * there are lots of configuration objects floating around.
+ */
+class HTMLPurifier_DefinitionCache_Decorator_Memory extends
+      HTMLPurifier_DefinitionCache_Decorator
+{
+    
+    var $definitions;
+    var $name = 'Memory';
+    
+    function copy() {
+        return new HTMLPurifier_DefinitionCache_Decorator_Memory();
+    }
+    
+    function add($def, $config) {
+        $status = parent::add($def, $config);
+        if ($status) $this->definitions[$this->generateKey($config)] = $def;
+        return $status;
+    }
+    
+    function set($def, $config) {
+        $status = parent::set($def, $config);
+        if ($status) $this->definitions[$this->generateKey($config)] = $def;
+        return $status;
+    }
+    
+    function replace($def, $config) {
+        $status = parent::replace($def, $config);
+        if ($status) $this->definitions[$this->generateKey($config)] = $def;
+        return $status;
+    }
+    
+    function get($config) {
+        $key = $this->generateKey($config);
+        if (isset($this->definitions[$key])) return $this->definitions[$key];
+        $this->definitions[$key] = parent::get($config);
+        return $this->definitions[$key];
+    }
+    
+}
+
+?>

library/HTMLPurifier/DefinitionCache/Decorator/Template.php.in

@@ -0,0 +1,47 @@
+<?php
+
+require_once 'HTMLPurifier/DefinitionCache/Decorator.php';
+
+/**
+ * Definition cache decorator template.
+ */
+class HTMLPurifier_DefinitionCache_Decorator_Template extends
+      HTMLPurifier_DefinitionCache_Decorator
+{
+    
+    var $name = 'Template'; // replace this
+    
+    function copy() {
+        // replace class name with yours
+        return new HTMLPurifier_DefinitionCache_Decorator_Template();
+    }
+    
+    // remove methods you don't need
+    
+    function add($def, $config) {
+        return parent::add($def, $config);
+    }
+    
+    function set($def, $config) {
+        return parent::set($def, $config);
+    }
+    
+    function replace($def, $config) {
+        return parent::replace($def, $config);
+    }
+    
+    function get($config) {
+        return parent::get($config);
+    }
+    
+    function flush() {
+        return parent::flush();
+    }
+    
+    function cleanup($config) {
+        return parent::cleanup($config);
+    }
+    
+}
+
+?>

library/HTMLPurifier/DefinitionCache/Null.php

@@ -0,0 +1,37 @@
+<?php
+
+require_once 'HTMLPurifier/DefinitionCache.php';
+
+/**
+ * Null cache object to use when no caching is on.
+ */
+class HTMLPurifier_DefinitionCache_Null extends HTMLPurifier_DefinitionCache
+{
+    
+    function add($def, $config) {
+        return false;
+    }
+    
+    function set($def, $config) {
+        return false;
+    }
+    
+    function replace($def, $config) {
+        return false;
+    }
+    
+    function get($config) {
+        return false;
+    }
+    
+    function flush($config) {
+        return false;
+    }
+    
+    function cleanup($config) {
+        return false;
+    }
+    
+}
+
+?>

library/HTMLPurifier/DefinitionCache/Serializer.php

@@ -0,0 +1,129 @@
+<?php
+
+require_once 'HTMLPurifier/DefinitionCache.php';
+
+HTMLPurifier_ConfigSchema::define(
+    'Cache', 'SerializerPath', null, 'string/null', '
+<p>
+    Absolute path with no trailing slash to store serialized definitions in.
+    Default is within the
+    HTML Purifier library inside DefinitionCache/Serializer. This
+    path must be writable by the webserver. This directive has been
+    available since 2.0.0.
+</p>
+');
+
+class HTMLPurifier_DefinitionCache_Serializer extends
+      HTMLPurifier_DefinitionCache
+{
+    
+    function add($def, $config) {
+        if (!$this->checkDefType($def)) return;
+        $file = $this->generateFilePath($config);
+        if (file_exists($file)) return false;
+        $this->_prepareDir($config);
+        return $this->_write($file, serialize($def));
+    }
+    
+    function set($def, $config) {
+        if (!$this->checkDefType($def)) return;
+        $file = $this->generateFilePath($config);
+        $this->_prepareDir($config);
+        return $this->_write($file, serialize($def));
+    }
+    
+    function replace($def, $config) {
+        if (!$this->checkDefType($def)) return;
+        $file = $this->generateFilePath($config);
+        if (!file_exists($file)) return false;
+        $this->_prepareDir($config);
+        return $this->_write($file, serialize($def));
+    }
+    
+    function get($config) {
+        $file = $this->generateFilePath($config);
+        if (!file_exists($file)) return false;
+        return unserialize(file_get_contents($file));
+    }
+    
+    function remove($config) {
+        $file = $this->generateFilePath($config);
+        if (!file_exists($file)) return false;
+        return unlink($file);
+    }
+    
+    function flush($config) {
+        $dir = $this->generateDirectoryPath($config);
+        $dh  = opendir($dir);
+        while (false !== ($filename = readdir($dh))) {
+            if (empty($filename)) continue;
+            if ($filename[0] === '.') continue;
+            unlink($dir . '/' . $filename);
+        }
+    }
+    
+    function cleanup($config) {
+        $this->_prepareDir($config);
+        $dir = $this->generateDirectoryPath($config);
+        $dh  = opendir($dir);
+        while (false !== ($filename = readdir($dh))) {
+            if (empty($filename)) continue;
+            if ($filename[0] === '.') continue;
+            $key = substr($filename, 0, strlen($filename) - 4);
+            if ($this->isOld($key, $config)) unlink($dir . '/' . $filename);
+        }
+    }
+    
+    /**
+     * Generates the file path to the serial file corresponding to
+     * the configuration and definition name
+     */
+    function generateFilePath($config) {
+        $key = $this->generateKey($config);
+        return $this->generateDirectoryPath($config) . '/' . $key . '.ser';
+    }
+    
+    /**
+     * Generates the path to the directory contain this cache's serial files
+     * @note No trailing slash
+     */
+    function generateDirectoryPath($config) {
+        $base = $config->get('Cache', 'SerializerPath');
+        $base = is_null($base) ? dirname(__FILE__) . '/Serializer' : $base;
+        return $base . '/' . $this->type;
+    }
+    
+    /**
+     * Convenience wrapper function for file_put_contents
+     * @param $file File name to write to
+     * @param $data Data to write into file
+     * @return Number of bytes written if success, or false if failure.
+     */
+    function _write($file, $data) {
+        static $file_put_contents;
+        if ($file_put_contents === null) {
+            $file_put_contents = function_exists('file_put_contents');
+        }
+        if ($file_put_contents) {
+            return file_put_contents($file, $data);
+        }
+        $fh = fopen($file, 'w');
+        if (!$fh) return false;
+        $status = fwrite($fh, $data);
+        fclose($fh);
+        return $status;
+    }
+    
+    /**
+     * Prepares the directory that this type stores the serials in
+     */
+    function _prepareDir($config) {
+        $directory = $this->generateDirectoryPath($config);
+        if (!is_dir($directory)) {
+            mkdir($directory);
+        }
+    }
+    
+}
+
+?>

library/HTMLPurifier/DefinitionCacheFactory.php

@@ -0,0 +1,90 @@
+<?php
+
+require_once 'HTMLPurifier/DefinitionCache.php';
+
+HTMLPurifier_ConfigSchema::define(
+    'Core', 'DefinitionCache', 'Serializer', 'string/null', '
+This directive defines which method to use when caching definitions,
+the complex data-type that makes HTML Purifier tick. Set to null
+to disable caching (not recommended, as you will see a definite
+performance degradation). This directive has been available since 2.0.0.
+');
+
+HTMLPurifier_ConfigSchema::defineAllowedValues(
+    'Core', 'DefinitionCache', array('Serializer')
+);
+
+
+/**
+ * Responsible for creating definition caches.
+ */
+class HTMLPurifier_DefinitionCacheFactory
+{
+    
+    var $caches = array('Serializer' => array());
+    var $decorators = array();
+    
+    /**
+     * Initialize default decorators
+     */
+    function setup() {
+        $this->addDecorator('Cleanup');
+    }
+    
+    /**
+     * Retrieves an instance of global definition cache factory.
+     * @static
+     */
+    static function &instance($prototype = null) {
+        static $instance;
+        if ($prototype !== null) {
+            $instance = $prototype;
+        } elseif ($instance === null || $prototype === true) {
+            $instance = new HTMLPurifier_DefinitionCacheFactory();
+            $instance->setup();
+        }
+        return $instance;
+    }
+    
+    /**
+     * Factory method that creates a cache object based on configuration
+     * @param $name Name of definitions handled by cache
+     * @param $config Instance of HTMLPurifier_Config
+     */
+    function &create($type, $config) {
+        // only one implementation as for right now, $config will
+        // be used to determine implementation
+        $method = $config->get('Core', 'DefinitionCache');
+        if ($method === null) {
+            $null = new HTMLPurifier_DefinitionCache_Null($type);
+            return $null;
+        }
+        if (!empty($this->caches[$method][$type])) {
+            return $this->caches[$method][$type];
+        }
+        $cache = new HTMLPurifier_DefinitionCache_Serializer($type);
+        foreach ($this->decorators as $decorator) {
+            $new_cache = $decorator->decorate($cache);
+            // prevent infinite recursion in PHP 4
+            unset($cache);
+            $cache = $new_cache;
+        }
+        $this->caches[$method][$type] = $cache;
+        return $this->caches[$method][$type];
+    }
+    
+    /**
+     * Registers a decorator to add to all new cache objects
+     * @param 
+     */
+    function addDecorator($decorator) {
+        if (is_string($decorator)) {
+            $class = "HTMLPurifier_DefinitionCache_Decorator_$decorator";
+            $decorator = new $class;
+        }
+        $this->decorators[$decorator->name] = $decorator;
+    }
+    
+}
+
+?>

library/HTMLPurifier/Doctype.php

@@ -0,0 +1,55 @@
+<?php
+
+/**
+ * Represents a document type, contains information on which modules
+ * need to be loaded.
+ */
+class HTMLPurifier_Doctype
+{
+    /**
+     * Full name of doctype
+     */
+    var $name;
+    
+    /**
+     * List of standard modules (string identifiers or literal objects)
+     * that this doctype uses
+     */
+    var $modules = array();
+    
+    /**
+     * List of modules to use for tidying up code
+     */
+    var $tidyModules = array();
+    
+    /**
+     * Is the language derived from XML (i.e. XHTML)?
+     */
+    var $xml = true;
+    
+    /**
+     * List of aliases for this doctype
+     */
+    var $aliases = array();
+    
+    function HTMLPurifier_Doctype($name = null, $xml = true, $modules = array(),
+        $tidyModules = array(), $aliases = array()
+    ) {
+        $this->name         = $name;
+        $this->xml          = $xml;
+        $this->modules      = $modules;
+        $this->tidyModules  = $tidyModules;
+        $this->aliases      = $aliases;
+    }
+    
+    /**
+     * Clones the doctype, use before resolving modes and the like
+     */
+    function copy() {
+        return new HTMLPurifier_Doctype(
+            $this->name, $this->xml, $this->modules, $this->tidyModules, $this->aliases
+        );
+    }
+}
+
+?>

library/HTMLPurifier/DoctypeRegistry.php

@@ -0,0 +1,125 @@
+<?php
+
+require_once 'HTMLPurifier/Doctype.php';
+
+// Legacy directives for doctype specification
+HTMLPurifier_ConfigSchema::define(
+    'HTML', 'Strict', false, 'bool',
+    'Determines whether or not to use Transitional (loose) or Strict rulesets. '.
+    'This directive is deprecated in favor of %HTML.Doctype. '.
+    'This directive has been available since 1.3.0.'
+);
+
+HTMLPurifier_ConfigSchema::define(
+    'HTML', 'XHTML', true, 'bool',
+    'Determines whether or not output is XHTML 1.0 or HTML 4.01 flavor. '.
+    'This directive is deprecated in favor of %HTML.Doctype. '.
+    'This directive was available since 1.1.'
+);
+HTMLPurifier_ConfigSchema::defineAlias('Core', 'XHTML', 'HTML', 'XHTML');
+
+class HTMLPurifier_DoctypeRegistry
+{
+    
+    /**
+     * Hash of doctype names to doctype objects
+     * @protected
+     */
+    var $doctypes;
+    
+    /**
+     * Lookup table of aliases to real doctype names
+     * @protected
+     */
+    var $aliases;
+    
+    /**
+     * Registers a doctype to the registry
+     * @note Accepts a fully-formed doctype object, or the
+     *       parameters for constructing a doctype object
+     * @param $doctype Name of doctype or literal doctype object
+     * @param $modules Modules doctype will load
+     * @param $modules_for_modes Modules doctype will load for certain modes
+     * @param $aliases Alias names for doctype
+     * @return Reference to registered doctype (usable for further editing)
+     */
+    function &register($doctype, $xml = true, $modules = array(),
+        $tidy_modules = array(), $aliases = array()
+    ) {
+        if (!is_array($modules)) $modules = array($modules);
+        if (!is_array($tidy_modules)) $tidy_modules = array($tidy_modules);
+        if (!is_array($aliases)) $aliases = array($aliases);
+        if (!is_object($doctype)) {
+            $doctype = new HTMLPurifier_Doctype(
+                $doctype, $xml, $modules, $tidy_modules, $aliases
+            );
+        }
+        $this->doctypes[$doctype->name] =& $doctype;
+        $name = $doctype->name;
+        // hookup aliases
+        foreach ($doctype->aliases as $alias) {
+            if (isset($this->doctypes[$alias])) continue;
+            $this->aliases[$alias] = $name;
+        }
+        // remove old aliases
+        if (isset($this->aliases[$name])) unset($this->aliases[$name]);
+        return $doctype;
+    }
+    
+    /**
+     * Retrieves reference to a doctype of a certain name
+     * @note This function resolves aliases
+     * @note When possible, use the more fully-featured make()
+     * @param $doctype Name of doctype
+     * @return Reference to doctype object
+     */
+    function &get($doctype) {
+        if (isset($this->aliases[$doctype])) $doctype = $this->aliases[$doctype];
+        if (!isset($this->doctypes[$doctype])) {
+            trigger_error('Doctype ' . htmlspecialchars($doctype) . ' does not exist');
+            $anon = new HTMLPurifier_Doctype($doctype);
+            return $anon;
+        }
+        return $this->doctypes[$doctype];
+    }
+    
+    /**
+     * Creates a doctype based on a configuration object,
+     * will perform initialization on the doctype
+     * @note Use this function to get a copy of doctype that config
+     *       can hold on to (this is necessary in order to tell
+     *       Generator whether or not the current document is XML
+     *       based or not).
+     */
+    function make($config) {
+        $original_doctype = $this->get($this->getDoctypeFromConfig($config));
+        $doctype = $original_doctype->copy();
+        return $doctype;
+    }
+    
+    /**
+     * Retrieves the doctype from the configuration object
+     */
+    function getDoctypeFromConfig($config) {
+        // recommended test
+        $doctype = $config->get('HTML', 'Doctype');
+        if ($doctype !== null) {
+            return $doctype;
+        }
+        // backwards-compatibility
+        if ($config->get('HTML', 'XHTML')) {
+            $doctype = 'XHTML 1.0';
+        } else {
+            $doctype = 'HTML 4.01';
+        }
+        if ($config->get('HTML', 'Strict')) {
+            $doctype .= ' Strict';
+        } else {
+            $doctype .= ' Transitional';
+        }
+        return $doctype;
+    }
+    
+}
+
+?>

library/HTMLPurifier/ElementDef.php

@@ -51,6 +51,8 @@ class HTMLPurifier_ElementDef
      * Abstract string representation of internal ChildDef rules. See
      * HTMLPurifier_ContentSets for how this is parsed and then transformed
      * into an HTMLPurifier_ChildDef.
+     * @warning This is a temporary variable that is not available after
+     *      being processed by HTMLDefinition
      * @public
      */
     var $content_model;
@@ -58,6 +60,9 @@ class HTMLPurifier_ElementDef
     /**
      * Value of $child->type, used to determine which ChildDef to use,
      * used in combination with $content_model.
+     * @warning This must be lowercase
+     * @warning This is a temporary variable that is not available after
+     *      being processed by HTMLDefinition
      * @public
      */
     var $content_model_type;
@@ -78,14 +83,47 @@ class HTMLPurifier_ElementDef
      * have to worry about this one.
      * @public
      */
-    var $descendants_are_inline;
+    var $descendants_are_inline = false;
+    
+    /**
+     * List of the names of required attributes this element has. Dynamically
+     * populated.
+     * @public
+     */
+    var $required_attr = array();
     
     /**
      * Lookup table of tags excluded from all descendants of this tag.
+     * @note SGML permits exclusions for all descendants, but this is
+     *       not possible with DTDs or XML Schemas. W3C has elected to
+     *       use complicated compositions of content_models to simulate
+     *       exclusion for children, but we go the simpler, SGML-style
+     *       route of flat-out exclusions, which correctly apply to
+     *       all descendants and not just children. Note that the XHTML
+     *       Modularization Abstract Modules are blithely unaware of such
+     *       distinctions.
      * @public
      */
     var $excludes = array();
     
+    /**
+     * Is this element safe for untrusted users to use?
+     */
+    var $safe;
+    
+    /**
+     * Low-level factory constructor for creating new standalone element defs
+     * @static
+     */
+    static function create($safe, $content_model, $content_model_type, $attr) {
+        $def = new HTMLPurifier_ElementDef();
+        $def->safe = (bool) $safe;
+        $def->content_model = $content_model;
+        $def->content_model_type = $content_model_type;
+        $def->attr = $attr;
+        return $def;
+    }
+    
     /**
      * Merges the values of another element definition into this one.
      * Values from the new element def take precedence if a value is
@@ -95,28 +133,61 @@ class HTMLPurifier_ElementDef
         
         // later keys takes precedence
         foreach($def->attr as $k => $v) {
-            if ($k == 0) {
+            if ($k === 0) {
                 // merge in the includes
                 // sorry, no way to override an include
                 foreach ($v as $v2) {
-                    $def->attr[0][] = $v2;
+                    $this->attr[0][] = $v2;
                 }
                 continue;
             }
+            if ($v === false) {
+                if (isset($this->attr[$k])) unset($this->attr[$k]);
+                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;
+        $this->_mergeAssocArray($this->attr_transform_pre, $def->attr_transform_pre);
+        $this->_mergeAssocArray($this->attr_transform_post, $def->attr_transform_post);
+        $this->_mergeAssocArray($this->auto_close, $def->auto_close);
+        $this->_mergeAssocArray($this->excludes, $def->excludes);
         
+        if(!empty($def->content_model)) {
+            $this->content_model .= ' | ' . $def->content_model;
+            $this->child = false;
+        }
+        if(!empty($def->content_model_type)) {
+            $this->content_model_type = $def->content_model_type;
+            $this->child = false;
+        }
         if(!is_null($def->child)) $this->child = $def->child;
-        if(!empty($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 = $def->descendants_are_inline;
+        if($def->descendants_are_inline) $this->descendants_are_inline = $def->descendants_are_inline;
+        if(!is_null($def->safe)) $this->safe = $def->safe;
         
     }
     
+    /**
+     * Merges one array into another, removes values which equal false
+     * @param $a1 Array by reference that is merged into
+     * @param $a2 Array that merges into $a1
+     */
+    function _mergeAssocArray(&$a1, $a2) {
+        foreach ($a2 as $k => $v) {
+            if ($v === false) {
+                if (isset($a1[$k])) unset($a1[$k]);
+                continue;
+            }
+            $a1[$k] = $v;
+        }
+    }
+    
+    /**
+     * Retrieves a copy of the element definition
+     */
+    function copy() {
+        return unserialize(serialize($this));
+    }
+    
 }
 
 ?>

library/HTMLPurifier/Encoder.php

@@ -1,7 +1,5 @@
 <?php
 
-require_once 'HTMLPurifier/EntityLookup.php';
-
 HTMLPurifier_ConfigSchema::define(
     'Core', 'Encoding', 'utf-8', 'istring', 
     'If for some reason you are unable to convert all webpages to UTF-8, '. 

library/HTMLPurifier/EntityParser.php

@@ -24,8 +24,8 @@ class HTMLPurifier_EntityParser
      * @protected
      */                             
     var $_substituteEntitiesRegex =
-'/&(?:[#]x([a-fA-F0-9]+)|[#]0*(\d+)|([A-Za-z]+));?/';
-//     1. hex             2. dec      3. string
+'/&(?:[#]x([a-fA-F0-9]+)|[#]0*(\d+)|([A-Za-z_:][A-Za-z0-9.\-_:]*));?/';
+//     1. hex             2. dec      3. string (XML style)
     
     
     /**
@@ -97,7 +97,6 @@ class HTMLPurifier_EntityParser
         } else {
             if (isset($this->_special_ent2dec[$matches[3]])) return $entity;
             if (!$this->_entity_lookup) {
-                require_once 'HTMLPurifier/EntityLookup.php';
                 $this->_entity_lookup = HTMLPurifier_EntityLookup::instance();
             }
             if (isset($this->_entity_lookup->table[$matches[3]])) {

library/HTMLPurifier/ErrorCollector.php

@@ -0,0 +1,73 @@
+<?php
+
+require_once 'HTMLPurifier/Generator.php';
+
+/**
+ * Error collection class that enables HTML Purifier to report HTML
+ * problems back to the user
+ */
+class HTMLPurifier_ErrorCollector
+{
+    
+    var $errors = array();
+    
+    /**
+     * Sends an error message to the collector for later use
+     * @param string Error message text
+     * @param HTMLPurifier_Token Token that caused error
+     * @param array Tokens surrounding the offending token above, use true as placeholder
+     */
+    function send($msg, $token, $context_tokens = array(true)) {
+        $this->errors[] = array($msg, $token, $context_tokens);
+    }
+    
+    /**
+     * Retrieves raw error data for custom formatter to use
+     * @param List of arrays in format of array(Error message text,
+     *        token that caused error, tokens surrounding token)
+     */
+    function getRaw() {
+        return $this->errors;
+    }
+    
+    /**
+     * Default HTML formatting implementation for error messages
+     * @param $config Configuration array, vital for HTML output nature
+     */
+    function getHTMLFormatted($config) {
+        $generator = new HTMLPurifier_Generator();
+        $context = new HTMLPurifier_Context();
+        $generator->generateFromTokens(array(), $config, $context); // initialize
+        $ret = array();
+        
+        $errors = $this->errors;
+        
+        // sort error array by line
+        if ($config->get('Core', 'MaintainLineNumbers')) {
+            $lines  = array();
+            foreach ($errors as $error) $lines[] = $error[1]->line;
+            array_multisort($lines, SORT_ASC, $errors);
+        }
+        
+        foreach ($errors as $error) {
+            $string = $generator->escape($error[0]); // message
+            if (!empty($error[1]->line)) {
+                $string .= ' at line ' . $error[1]->line;
+            }
+            $string .= ' (<code>';
+            foreach ($error[2] as $token) {
+                if ($token !== true) {
+                    $string .= $generator->escape($generator->generateFromToken($token));
+                } else {
+                    $string .= '<strong>' . $generator->escape($generator->generateFromToken($error[1])) . '</strong>';
+                }
+            }
+            $string .= '</code>)';
+            $ret[] = $string;
+        }
+        return $ret;
+    }
+    
+}
+
+?>

library/HTMLPurifier/Generator.php

@@ -1,59 +1,65 @@
 <?php
 
-require_once 'HTMLPurifier/Lexer.php';
-
 HTMLPurifier_ConfigSchema::define(
-    'Core', 'CleanUTF8DuringGeneration', false, 'bool',
-    'When true, HTMLPurifier_Generator will also check all strings it '.
-    'escapes for UTF-8 well-formedness as a defense in depth measure. '.
-    'This could cause a considerable performance impact, and is not '.
-    'strictly necessary due to the fact that the Lexers should have '.
-    'ensured that all the UTF-8 strings were well-formed.  Note that '.
-    'the configuration value is only read at the beginning of '.
-    'generateFromTokens.'
-);
-
-HTMLPurifier_ConfigSchema::define(
-    'Core', 'XHTML', true, 'bool',
-    'Determines whether or not output is XHTML or not.  When disabled, HTML '.
-    'Purifier goes into HTML 4.01 removes XHTML-specific markup constructs, '.
-    'such as boolean attribute expansion and trailing slashes in empty tags. '.
-    'This directive was available since 1.1.'
+    'Output', 'CommentScriptContents', true, 'bool',
+    'Determines whether or not HTML Purifier should attempt to fix up '.
+    'the contents of script tags for legacy browsers with comments. This '.
+    'directive was available since 1.7.'
 );
+HTMLPurifier_ConfigSchema::defineAlias('Core', 'CommentScriptContents', 'Output', 'CommentScriptContents');
 
 // extension constraints could be factored into ConfigSchema
 HTMLPurifier_ConfigSchema::define(
-    'Core', 'TidyFormat', false, 'bool',
-    '<p>Determines whether or not to run Tidy on the final output for pretty '.
-    'formatting reasons, such as indentation and wrap.</p><p>This can greatly '.
-    'improve readability for editors who are hand-editing the HTML, but is '.
-    'by no means necessary as HTML Purifier has already fixed all major '.
-    'errors the HTML may have had. Tidy is a non-default extension, and this directive '.
-    'will silently fail if Tidy is not available.</p><p>If you are looking to make '.
-    'the overall look of your page\'s source better, I recommend running Tidy '.
-    'on the entire page rather than just user-content (after all, the '.
-    'indentation relative to the containing blocks will be incorrect).</p><p>This '.
-    'directive was available since 1.1.1.</p>'
+    'Output', 'TidyFormat', false, 'bool', <<<HTML
+<p>
+    Determines whether or not to run Tidy on the final output for pretty 
+    formatting reasons, such as indentation and wrap.
+</p>
+<p>
+    This can greatly improve readability for editors who are hand-editing
+    the HTML, but is by no means necessary as HTML Purifier has already
+    fixed all major errors the HTML may have had. Tidy is a non-default
+    extension, and this directive will silently fail if Tidy is not
+    available.
+</p>
+<p>
+    If you are looking to make the overall look of your page's source
+    better, I recommend running Tidy on the entire page rather than just
+    user-content (after all, the indentation relative to the containing
+    blocks will be incorrect).
+</p>
+<p>
+    This directive was available since 1.1.1.
+</p>
+HTML
 );
+HTMLPurifier_ConfigSchema::defineAlias('Core', 'TidyFormat', 'Output', 'TidyFormat');
 
 /**
  * Generates HTML from tokens.
+ * @todo Create a configuration-wide instance that all objects retrieve
  */
 class HTMLPurifier_Generator
 {
     
     /**
-     * Bool cache of %Core.CleanUTF8DuringGeneration
-     * @private
-     */
-    var $_clean_utf8 = false;
-    
-    /**
-     * Bool cache of %Core.XHTML
+     * Bool cache of %HTML.XHTML
      * @private
      */
     var $_xhtml = true;
     
+    /**
+     * Bool cache of %Output.CommentScriptContents
+     * @private
+     */
+    var $_scriptFix = false;
+    
+    /**
+     * Cache of HTMLDefinition
+     * @private
+     */
+    var $_def;
+    
     /**
      * Generates HTML from an array of tokens.
      * @param $tokens Array of HTMLPurifier_Token
@@ -63,13 +69,24 @@ class HTMLPurifier_Generator
     function generateFromTokens($tokens, $config, &$context) {
         $html = '';
         if (!$config) $config = HTMLPurifier_Config::createDefault();
-        $this->_clean_utf8 = $config->get('Core', 'CleanUTF8DuringGeneration');
-        $this->_xhtml = $config->get('Core', 'XHTML');
+        $this->_scriptFix   = $config->get('Output', 'CommentScriptContents');
+        
+        $this->_def = $config->getHTMLDefinition();
+        $this->_xhtml = $this->_def->doctype->xml;
+        
         if (!$tokens) return '';
-        foreach ($tokens as $token) {
-            $html .= $this->generateFromToken($token);
+        for ($i = 0, $size = count($tokens); $i < $size; $i++) {
+            if ($this->_scriptFix && $tokens[$i]->name === 'script') {
+                // script special case
+                $html .= $this->generateFromToken($tokens[$i++]);
+                $html .= $this->generateScriptFromToken($tokens[$i++]);
+                while ($tokens[$i]->name != 'script') {
+                    $html .= $this->generateScriptFromToken($tokens[$i++]);
+                }
+            }
+            $html .= $this->generateFromToken($tokens[$i]);
         }
-        if ($config->get('Core', 'TidyFormat') && extension_loaded('tidy')) {
+        if ($config->get('Output', 'TidyFormat') && extension_loaded('tidy')) {
             
             $tidy_options = array(
                'indent'=> true,
@@ -104,14 +121,14 @@ class HTMLPurifier_Generator
     function generateFromToken($token) {
         if (!isset($token->type)) return '';
         if ($token->type == 'start') {
-            $attr = $this->generateAttributes($token->attr);
+            $attr = $this->generateAttributes($token->attr, $token->name);
             return '<' . $token->name . ($attr ? ' ' : '') . $attr . '>';
             
         } elseif ($token->type == 'end') {
             return '</' . $token->name . '>';
             
         } elseif ($token->type == 'empty') {
-            $attr = $this->generateAttributes($token->attr);
+            $attr = $this->generateAttributes($token->attr, $token->name);
              return '<' . $token->name . ($attr ? ' ' : '') . $attr .
                 ( $this->_xhtml ? ' /': '' )
                 . '>';
@@ -125,18 +142,33 @@ class HTMLPurifier_Generator
         }
     }
     
+    /**
+     * Special case processor for the contents of script tags
+     * @warning This runs into problems if there's already a literal
+     *          --> somewhere inside the script contents.
+     */
+    function generateScriptFromToken($token) {
+        if (!$token->type == 'text') return $this->generateFromToken($token);
+        return '<!--' . PHP_EOL . $token->data . PHP_EOL . '// -->';
+        // more advanced version:
+        // return '<!--//--><![CDATA[//><!--' . PHP_EOL . $token->data . PHP_EOL . '//--><!]]>';
+    }
+    
     /**
      * Generates attribute declarations from attribute array.
      * @param $assoc_array_of_attributes Attribute array
      * @return Generate HTML fragment for insertion.
      */
-    function generateAttributes($assoc_array_of_attributes) {
+    function generateAttributes($assoc_array_of_attributes, $element) {
         $html = '';
         foreach ($assoc_array_of_attributes as $key => $value) {
             if (!$this->_xhtml) {
                 // remove namespaced attributes
                 if (strpos($key, ':') !== false) continue;
-                // also needed: check for attribute minimization
+                if (!empty($this->_def->info[$element]->attr[$key]->minimized)) {
+                    $html .= $key . ' ';
+                    continue;
+                }
             }
             $html .= $key.'="'.$this->escape($value).'" ';
         }
@@ -149,7 +181,6 @@ class HTMLPurifier_Generator
      * @return String escaped data.
      */
     function escape($string) {
-        if ($this->_clean_utf8) $string = HTMLPurifier_Lexer::cleanUTF8($string);
         return htmlspecialchars($string, ENT_COMPAT, 'UTF-8');
     }
     

library/HTMLPurifier/HTMLDefinition.php

@@ -1,250 +1,454 @@
-<?php
-
-// components
-require_once 'HTMLPurifier/HTMLModuleManager.php';
-
-// 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. '.
-    'This directive has been available since 1.3.0.'
-);
-
-HTMLPurifier_ConfigSchema::define(
-    'HTML', 'BlockWrapper', 'p', 'string',
-    'String name of element to wrap inline elements that are inside a block '.
-    'context.  This only occurs in the children of blockquote in strict mode. '.
-    'Example: by default value, <code>&lt;blockquote&gt;Foo&lt;/blockquote&gt;</code> '.
-    'would become <code>&lt;blockquote&gt;&lt;p&gt;Foo&lt;/p&gt;&lt;/blockquote&gt;</code>. The '.
-    '<code>&lt;p&gt;</code> tags can be replaced '.
-    'with whatever you desire, as long as it is a block level element. '.
-    'This directive has been available since 1.3.0.'
-);
-
-HTMLPurifier_ConfigSchema::define(
-    'HTML', 'Parent', 'div', 'string',
-    'String name of element that HTML fragment passed to library will be '.
-    'inserted in.  An interesting variation would be using span as the '.
-    'parent element, meaning that only inline tags would be allowed. '.
-    'This directive has been available since 1.3.0.'
-);
-
-HTMLPurifier_ConfigSchema::define(
-    'HTML', 'AllowedElements', null, 'lookup/null',
-    'If HTML Purifier\'s tag set is unsatisfactory for your needs, you '.
-    'can overload it with your own list of tags to allow.  Note that this '.
-    'method is subtractive: it does its job by taking away from HTML Purifier '.
-    'usual feature set, so you cannot add a tag that HTML Purifier never '.
-    'supported in the first place (like embed, form or head).  If you change this, you '.
-    'probably also want to change %HTML.AllowedAttributes. '.
-    '<strong>Warning:</strong> If another directive conflicts with the '.
-    'elements here, <em>that</em> directive will win and override. '.
-    'This directive has been available since 1.3.0.'
-);
-
-HTMLPurifier_ConfigSchema::define(
-    'HTML', 'AllowedAttributes', null, 'lookup/null',
-    'IF HTML Purifier\'s attribute set is unsatisfactory, overload it! '.
-    'The syntax is \'tag.attr\' or \'*.attr\' for the global attributes '.
-    '(style, id, class, dir, lang, xml:lang).'.
-    '<strong>Warning:</strong> If another directive conflicts with the '.
-    'elements here, <em>that</em> directive will win and override. For '.
-    'example, %HTML.EnableAttrID will take precedence over *.id in this '.
-    'directive.  You must set that directive to true before you can use '.
-    'IDs at all. This directive has been available since 1.3.0.'
-);
-
-/**
- * Definition of the purified HTML that describes allowed children,
- * attributes, and many other things.
- * 
- * Conventions:
- * 
- * All member variables that are prefixed with info
- * (including the main $info array) are used by HTML Purifier internals
- * and should not be directly edited when customizing the HTMLDefinition.
- * They can usually be set via configuration directives or custom
- * modules.
- * 
- * On the other hand, member variables without the info prefix are used
- * internally by the HTMLDefinition and MUST NOT be used by other HTML
- * Purifier internals. Many of them, however, are public, and may be
- * edited by userspace code to tweak the behavior of HTMLDefinition.
- * 
- * 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
-     */
-    var $info = array();
-    
-    /**
-     * Associative array of global attribute name to attribute definition.
-     * @public
-     */
-    var $info_global_attr = array();
-    
-    /**
-     * String name of parent element HTML will be going into.
-     * @public
-     */
-    var $info_parent = 'div';
-    
-    /**
-     * Definition for parent element, allows parent element to be a
-     * tag that's not allowed inside the HTML fragment.
-     * @public
-     */
-    var $info_parent_def;
-    
-    /**
-     * String name of element used to wrap inline elements in block context
-     * @note This is rarely used except for BLOCKQUOTEs in strict mode
-     * @public
-     */
-    var $info_block_wrapper = 'p';
-    
-    /**
-     * Associative array of deprecated tag name to HTMLPurifier_TagTransform
-     * @public
-     */
-    var $info_tag_transform = array();
-    
-    /**
-     * Indexed list of HTMLPurifier_AttrTransform to be performed before validation.
-     * @public
-     */
-    var $info_attr_transform_pre = array();
-    
-    /**
-     * Indexed list of HTMLPurifier_AttrTransform to be performed after validation.
-     * @public
-     */
-    var $info_attr_transform_post = array();
-    
-    /**
-     * Nested lookup array of content set name (Block, Inline) to
-     * element name to whether or not it belongs in that content set.
-     * @public
-     */
-    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 */
-    
-    /**
-     * Performs low-cost, preliminary initialization.
-     * @param $config Instance of HTMLPurifier_Config
-     */
-    function HTMLPurifier_HTMLDefinition(&$config) {
-        $this->config =& $config;
-        $this->manager = new HTMLPurifier_HTMLModuleManager();
-    }
-    
-    /**
-     * Processes internals into form usable by HTMLPurifier internals. 
-     * Modifying the definition after calling this function should not
-     * be done.
-     */
-    function setup() {
-        
-        // multiple call guard
-        if ($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) $this->info_tag_transform[$k]      = $v;
-            foreach($module->info_attr_transform_pre    as $k => $v) $this->info_attr_transform_pre[$k] = $v;
-            foreach($module->info_attr_transform_post   as $k => $v) $this->info_attr_transform_post[$k]= $v;
-        }
-        
-        $this->info = $this->manager->getElements($this->config);
-        $this->info_content_sets = $this->manager->contentSets->lookup;
-        
-    }
-    
-    /**
-     * 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);
-        }
-        
-        $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);
-        }
-        
-        // 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]);
-            }
-        }
-        $allowed_attributes = $this->config->get('HTML', 'AllowedAttributes');
-        if (is_array($allowed_attributes)) {
-            foreach ($this->info_global_attr as $attr_key => $info) {
-                if (!isset($allowed_attributes["*.$attr_key"])) {
-                    unset($this->info_global_attr[$attr_key]);
-                }
-            }
-            foreach ($this->info as $tag => $info) {
-                foreach ($info->attr as $attr => $attr_info) {
-                    if (!isset($allowed_attributes["$tag.$attr"]) &&
-                        !isset($allowed_attributes["*.$attr"])) {
-                        unset($this->info[$tag]->attr[$attr]);
-                    }
-                }
-            }
-        }
-        
-    }
-    
-    
-}
-
-?>
+<?php
+
+require_once 'HTMLPurifier/Definition.php';
+require_once 'HTMLPurifier/HTMLModuleManager.php';
+
+// this definition and its modules MUST NOT define configuration directives
+// outside of the HTML or Attr namespaces
+
+HTMLPurifier_ConfigSchema::define(
+    'HTML', 'DefinitionID', null, 'string/null', '
+<p>
+    Unique identifier for a custom-built HTML definition. If you edit
+    the raw version of the HTMLDefinition, introducing changes that the
+    configuration object does not reflect, you must specify this variable.
+    If you change your custom edits, you should change this directive, or
+    clear your cache. Example:
+</p>
+<pre>
+$config = HTMLPurifier_Config::createDefault();
+$config->set(\'HTML\', \'DefinitionID\', \'1\');
+$def = $config->getHTMLDefinition();
+$def->addAttribute(\'a\', \'tabindex\', \'Number\');
+</pre>
+<p>
+    In the above example, the configuration is still at the defaults, but
+    using the advanced API, an extra attribute has been added. The
+    configuration object normally has no way of knowing that this change
+    has taken place, so it needs an extra directive: %HTML.DefinitionID.
+    If someone else attempts to use the default configuration, these two
+    pieces of code will not clobber each other in the cache, since one has
+    an extra directive attached to it.
+</p>
+<p>
+    This directive has been available since 2.0.0, and in that version or
+    later you <em>must</em> specify a value to this directive to use the
+    advanced API features.
+</p>
+');
+
+HTMLPurifier_ConfigSchema::define(
+    'HTML', 'DefinitionRev', 1, 'int', '
+<p>
+    Revision identifier for your custom definition specified in
+    %HTML.DefinitionID.  This serves the same purpose: uniquely identifying
+    your custom definition, but this one does so in a chronological
+    context: revision 3 is more up-to-date then revision 2.  Thus, when
+    this gets incremented, the cache handling is smart enough to clean
+    up any older revisions of your definition as well as flush the
+    cache.  This directive has been available since 2.0.0.
+</p>
+');
+
+HTMLPurifier_ConfigSchema::define(
+    'HTML', 'BlockWrapper', 'p', 'string', '
+<p>
+    String name of element to wrap inline elements that are inside a block
+    context.  This only occurs in the children of blockquote in strict mode.
+</p>
+<p>
+    Example: by default value,
+    <code>&lt;blockquote&gt;Foo&lt;/blockquote&gt;</code> would become
+    <code>&lt;blockquote&gt;&lt;p&gt;Foo&lt;/p&gt;&lt;/blockquote&gt;</code>.
+    The <code>&lt;p&gt;</code> tags can be replaced with whatever you desire,
+    as long as it is a block level element. This directive has been available
+    since 1.3.0.
+</p>
+');
+
+HTMLPurifier_ConfigSchema::define(
+    'HTML', 'Parent', 'div', 'string', '
+<p>
+    String name of element that HTML fragment passed to library will be 
+    inserted in.  An interesting variation would be using span as the 
+    parent element, meaning that only inline tags would be allowed. 
+    This directive has been available since 1.3.0.
+</p>
+');
+
+HTMLPurifier_ConfigSchema::define(
+    'HTML', 'AllowedElements', null, 'lookup/null', '
+<p>
+    If HTML Purifier\'s tag set is unsatisfactory for your needs, you 
+    can overload it with your own list of tags to allow.  Note that this 
+    method is subtractive: it does its job by taking away from HTML Purifier 
+    usual feature set, so you cannot add a tag that HTML Purifier never 
+    supported in the first place (like embed, form or head).  If you 
+    change this, you probably also want to change %HTML.AllowedAttributes. 
+</p>
+<p>
+    <strong>Warning:</strong> If another directive conflicts with the 
+    elements here, <em>that</em> directive will win and override. 
+    This directive has been available since 1.3.0.
+</p>
+');
+
+HTMLPurifier_ConfigSchema::define(
+    'HTML', 'AllowedAttributes', null, 'lookup/null', '
+<p>
+    If HTML Purifier\'s attribute set is unsatisfactory, overload it! 
+    The syntax is "tag.attr" or "*.attr" for the global attributes 
+    (style, id, class, dir, lang, xml:lang).
+</p>
+<p>
+    <strong>Warning:</strong> If another directive conflicts with the 
+    elements here, <em>that</em> directive will win and override. For 
+    example, %HTML.EnableAttrID will take precedence over *.id in this 
+    directive.  You must set that directive to true before you can use 
+    IDs at all. This directive has been available since 1.3.0.
+</p>
+');
+
+HTMLPurifier_ConfigSchema::define(
+    'HTML', 'Allowed', null, 'string/null', '
+<p>
+    This is a convenience directive that rolls the functionality of
+    %HTML.AllowedElements and %HTML.AllowedAttributes into one directive.
+    Specify elements and attributes that are allowed using:
+    <code>element1[attr1|attr2],element2...</code>.
+</p>
+<p>
+    <strong>Warning</strong>:
+    All of the constraints on the component directives are still enforced.
+    The syntax is a <em>subset</em> of TinyMCE\'s <code>valid_elements</code>
+    whitelist: directly copy-pasting it here will probably result in
+    broken whitelists. If %HTML.AllowedElements or %HTML.AllowedAttributes
+    are set, this directive has no effect.
+    This directive has been available since 2.0.0.
+</p>
+');
+
+/**
+ * Definition of the purified HTML that describes allowed children,
+ * attributes, and many other things.
+ * 
+ * Conventions:
+ * 
+ * All member variables that are prefixed with info
+ * (including the main $info array) are used by HTML Purifier internals
+ * and should not be directly edited when customizing the HTMLDefinition.
+ * They can usually be set via configuration directives or custom
+ * modules.
+ * 
+ * On the other hand, member variables without the info prefix are used
+ * internally by the HTMLDefinition and MUST NOT be used by other HTML
+ * Purifier internals. Many of them, however, are public, and may be
+ * edited by userspace code to tweak the behavior of HTMLDefinition.
+ * 
+ * HTMLPurifier_Printer_HTMLDefinition is a notable exception to this
+ * rule: in the interest of comprehensiveness, it will sniff everything.
+ */
+class HTMLPurifier_HTMLDefinition extends HTMLPurifier_Definition
+{
+    
+    // FULLY-PUBLIC VARIABLES ---------------------------------------------
+    
+    /**
+     * Associative array of element names to HTMLPurifier_ElementDef
+     * @public
+     */
+    var $info = array();
+    
+    /**
+     * Associative array of global attribute name to attribute definition.
+     * @public
+     */
+    var $info_global_attr = array();
+    
+    /**
+     * String name of parent element HTML will be going into.
+     * @public
+     */
+    var $info_parent = 'div';
+    
+    /**
+     * Definition for parent element, allows parent element to be a
+     * tag that's not allowed inside the HTML fragment.
+     * @public
+     */
+    var $info_parent_def;
+    
+    /**
+     * String name of element used to wrap inline elements in block context
+     * @note This is rarely used except for BLOCKQUOTEs in strict mode
+     * @public
+     */
+    var $info_block_wrapper = 'p';
+    
+    /**
+     * Associative array of deprecated tag name to HTMLPurifier_TagTransform
+     * @public
+     */
+    var $info_tag_transform = array();
+    
+    /**
+     * Indexed list of HTMLPurifier_AttrTransform to be performed before validation.
+     * @public
+     */
+    var $info_attr_transform_pre = array();
+    
+    /**
+     * Indexed list of HTMLPurifier_AttrTransform to be performed after validation.
+     * @public
+     */
+    var $info_attr_transform_post = array();
+    
+    /**
+     * Nested lookup array of content set name (Block, Inline) to
+     * element name to whether or not it belongs in that content set.
+     * @public
+     */
+    var $info_content_sets = array();
+    
+    /**
+     * Doctype object
+     */
+    var $doctype;
+    
+    
+    
+    // RAW CUSTOMIZATION STUFF --------------------------------------------
+    
+    /**
+     * Adds a custom attribute to a pre-existing element
+     * @param $element_name String element name to add attribute to
+     * @param $attr_name String name of attribute
+     * @param $def Attribute definition, can be string or object, see
+     *             HTMLPurifier_AttrTypes for details
+     */
+    function addAttribute($element_name, $attr_name, $def) {
+        $module =& $this->getAnonymousModule();
+        $element =& $module->addBlankElement($element_name);
+        $element->attr[$attr_name] = $def;
+    }
+    
+    /**
+     * Adds a custom element to your HTML definition
+     * @note See HTMLPurifier_HTMLModule::addElement for detailed 
+     *       parameter descriptions.
+     */
+    function addElement($element_name, $type, $contents, $attr_collections, $attributes) {
+        $module =& $this->getAnonymousModule();
+        // assume that if the user is calling this, the element
+        // is safe. This may not be a good idea
+        $module->addElement($element_name, true, $type, $contents, $attr_collections, $attributes);
+    }
+    
+    /**
+     * Retrieves a reference to the anonymous module, so you can
+     * bust out advanced features without having to make your own
+     * module.
+     */
+    function &getAnonymousModule() {
+        if (!$this->_anonModule) {
+            $this->_anonModule = new HTMLPurifier_HTMLModule();
+            $this->_anonModule->name = 'Anonymous';
+        }
+        return $this->_anonModule;
+    }
+    
+    var $_anonModule;
+    
+    
+    // PUBLIC BUT INTERNAL VARIABLES --------------------------------------
+    
+    var $type = 'HTML';
+    var $manager; /**< Instance of HTMLPurifier_HTMLModuleManager */
+    
+    /**
+     * Performs low-cost, preliminary initialization.
+     */
+    function HTMLPurifier_HTMLDefinition() {
+        $this->manager = new HTMLPurifier_HTMLModuleManager();
+    }
+    
+    function doSetup($config) {
+        $this->processModules($config);
+        $this->setupConfigStuff($config);
+        unset($this->manager);
+        
+        // cleanup some of the element definitions
+        foreach ($this->info as $k => $v) {
+            unset($this->info[$k]->content_model);
+            unset($this->info[$k]->content_model_type);
+        }
+    }
+    
+    /**
+     * Extract out the information from the manager
+     */
+    function processModules($config) {
+        
+        if ($this->_anonModule) {
+            // for user specific changes
+            // this is late-loaded so we don't have to deal with PHP4
+            // reference wonky-ness
+            $this->manager->addModule($this->_anonModule);
+            unset($this->_anonModule);
+        }
+        
+        $this->manager->setup($config);
+        $this->doctype = $this->manager->doctype;
+        
+        foreach ($this->manager->modules as $module) {
+            foreach($module->info_tag_transform         as $k => $v) {
+                if ($v === false) unset($this->info_tag_transform[$k]);
+                else $this->info_tag_transform[$k] = $v;
+            }
+            foreach($module->info_attr_transform_pre    as $k => $v) {
+                if ($v === false) unset($this->info_attr_transform_pre[$k]);
+                else $this->info_attr_transform_pre[$k] = $v;
+            }
+            foreach($module->info_attr_transform_post   as $k => $v) {
+                if ($v === false) unset($this->info_attr_transform_post[$k]);
+                else $this->info_attr_transform_post[$k] = $v;
+            }
+        }
+        
+        $this->info = $this->manager->getElements();
+        $this->info_content_sets = $this->manager->contentSets->lookup;
+        
+    }
+    
+    /**
+     * Sets up stuff based on config. We need a better way of doing this.
+     */
+    function setupConfigStuff($config) {
+        
+        $block_wrapper = $config->get('HTML', 'BlockWrapper');
+        if (isset($this->info_content_sets['Block'][$block_wrapper])) {
+            $this->info_block_wrapper = $block_wrapper;
+        } else {
+            trigger_error('Cannot use non-block element as block wrapper.',
+                E_USER_ERROR);
+        }
+        
+        $parent = $config->get('HTML', 'Parent');
+        $def = $this->manager->getElement($parent, true);
+        if ($def) {
+            $this->info_parent = $parent;
+            $this->info_parent_def = $def;
+        } else {
+            trigger_error('Cannot use unrecognized element as parent.',
+                E_USER_ERROR);
+            $this->info_parent_def = $this->manager->getElement($this->info_parent, true);
+        }
+        
+        // support template text
+        $support = "(for information on implementing this, see the ".
+                   "support forums) ";
+        
+        // setup allowed elements
+        
+        $allowed_elements = $config->get('HTML', 'AllowedElements');
+        $allowed_attributes = $config->get('HTML', 'AllowedAttributes');
+        
+        if (!is_array($allowed_elements) && !is_array($allowed_attributes)) {
+            $allowed = $config->get('HTML', 'Allowed');
+            if (is_string($allowed)) {
+                list($allowed_elements, $allowed_attributes) = $this->parseTinyMCEAllowedList($allowed);
+            }
+        }
+        
+        if (is_array($allowed_elements)) {
+            foreach ($this->info as $name => $d) {
+                if(!isset($allowed_elements[$name])) unset($this->info[$name]);
+                unset($allowed_elements[$name]);
+            }
+            // emit errors
+            foreach ($allowed_elements as $element => $d) {
+                $element = htmlspecialchars($element);
+                trigger_error("Element '$element' is not supported $support", E_USER_WARNING);
+            }
+        }
+        
+        $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"]) &&
+                        !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);
+                $element = htmlspecialchars($element);
+                $attribute = htmlspecialchars($attribute);
+                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);
+                }
+            }
+        }
+        
+    }
+    
+    /**
+     * Parses a TinyMCE-flavored Allowed Elements and Attributes list into
+     * separate lists for processing. Format is element[attr1|attr2],element2...
+     * @warning Although it's largely drawn from TinyMCE's implementation,
+     *      it is different, and you'll probably have to modify your lists
+     * @param $list String list to parse
+     * @param array($allowed_elements, $allowed_attributes)
+     */
+    function parseTinyMCEAllowedList($list) {
+        
+        $elements = array();
+        $attributes = array();
+        
+        $chunks = explode(',', $list);
+        foreach ($chunks as $chunk) {
+            // remove TinyMCE element control characters
+            if (!strpos($chunk, '[')) {
+                $element = $chunk;
+                $attr = false;
+            } else {
+                list($element, $attr) = explode('[', $chunk);
+            }
+            if ($element !== '*') $elements[$element] = true;
+            if (!$attr) continue;
+            $attr = substr($attr, 0, strlen($attr) - 1); // remove trailing ]
+            $attr = explode('|', $attr);
+            foreach ($attr as $key) {
+                $attributes["$element.$key"] = true;
+            }
+        }
+        
+        return array($elements, $attributes);
+        
+    }
+    
+    
+}
+
+?>