Release 2.1.2, merged in 1368 to HEAD.

git-svn-id: http://htmlpurifier.org/svnroot/htmlpurifier/branches/strict@1404 48356398-32a2-884e-a903-53898d9a118a

Doxyfile

@@ -4,7 +4,7 @@
 # Project related configuration options
 #---------------------------------------------------------------------------
 PROJECT_NAME           = HTML Purifier
-PROJECT_NUMBER         = 1.3.2
+PROJECT_NUMBER         = 2.1.2
 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
 
@@ -10,10 +9,11 @@ should make sure a few things are properly done.
 
 
 
+
 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
@@ -46,7 +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:
 
@@ -65,11 +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.
@@ -86,7 +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();
@@ -113,36 +116,42 @@ 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 fix,
+but please be cognizant of the issues the "solution" creates (for this
+reason, I do not include the solution in this document).
+
+
+
 
 
 
 4.2. Setting a different doctype
 
-For those of you 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.
+your code.  Some of the more interesting ones are configurable at the
+demo <http://htmlpurifier.org/demo.php> and are well worth looking into
+for your own system.
 
 
 
@@ -159,13 +168,15 @@ The interface is mind-numbingly simple:
     $clean_html = $purifier->purify( $dirty_html );
 
 That's it!  For more examples, check out docs/examples/ (they aren't very
-different though).  Also, SLOW gives advice on what to do if HTML Purifier
-is slowing down your application.
+different though).  Also, docs/enduser-slow.html gives advice on what to
+do if HTML Purifier is slowing down your application.
 
 
 
 6.   Quick install
 
+First, make sure library/HTMLPurifier/DefinitionCache/Serializer is
+writable by the webserver (see Section 7: Caching below for details).
 If your website is in UTF-8 and XHTML Transitional, use this code:
 
 <?php
@@ -181,9 +192,47 @@ 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 (generally one or two) to speed up
+its execution. For maximum performance, make sure that
+library/HTMLPurifier/DefinitionCache/Serializer is writeable by the webserver.
+
+If you are in the library/ folder of HTML Purifier, you can set the
+appropriate permissions using:
+
+    chmod -R 0755 HTMLPurifier/DefinitionCache/Serializer
+
+If the above command doesn't work, you may need to assign write permissions
+to all. This may be necessary if your webserver runs as nobody, but is
+not recommended since it means any other user can write files in the
+directory. Use:
+
+    chmod -R 0777 HTMLPurifier/DefinitionCache/Serializer
+
+You can also chmod files via your FTP client; this option
+is usually accessible by right clicking the corresponding directory and
+then selecting "chmod" or "file permissions".
+
+Starting with 2.0.1, HTML Purifier will generate friendly error messages
+that will tell you exactly what you have to chmod the directory to, if in doubt,
+follow its advice.
+
+If you are unable or unwilling to give write permissions to the cache
+directory, you can either disable the cache (and suffer a performance
+hit):
+
+    $config->set('Core', 'DefinitionCache', null);
+
+Or move the cache directory somewhere else (no trailing slash):
+
+    $config->set('Cache', 'SerializerPath', '/home/user/absolute/path');

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

@@ -9,11 +9,304 @@ NEWS ( CHANGELOG and HISTORY )                                     HTMLPurifier
     . Internal change
 ==========================
 
-1.4.0, unknown release date
-(major feature release)
+2.1.2, released 2007-09-03
+! Implemented Object module for trusted users
+! Implemented experimental HTML5 parsing mode using PH5P. To use, add
+  this to your code:
+        require_once 'HTMLPurifier/Lexer/PH5P.php';
+        $config->set('Core', 'LexerImpl', 'PH5P');
+  Note that this Lexer introduces some classes not in the HTMLPurifier
+  namespace.  Also, this is PHP5 only.
+! CSS property border-spacing implemented
+- Fix non-visible parsing error in DirectLex with empty tags that have
+  slashes inside attribute values.
+- Fix typo in CSS definition: border-collapse:seperate; was incorrectly
+  accepted as valid CSS. Usually non-visible, because this styling is the
+  default for tables in most browsers. Thanks Brett Zamir for pointing
+  this out.
+- Fix validation errors in configuration form
+- Hammer out a bunch of edge-case bugs in the standalone distribution
+- Inclusion reflection removed from URISchemeRegistry; you must manually
+  include any new schema files you wish to use
+- Numerous typo fixes in documentation thanks to Brett Zamir
+. Unit test refactoring for one logical test per test function
+. Config and context parameters in ComplexHarness deprecated: instead, edit
+  the $config and $context member variables
+. HTML wrapper in DOMLex now takes DTD identifiers into account; doesn't
+  really make a difference, but is good for completeness sake
+. merge-library.php script refactored for greater code reusability and
+  PHP4 compatibility
 
-1.3.3, unknown release date, may be dropped
-(security/bugfix/minor feature release)
+2.1.1, released 2007-08-04
+- Fix show-stopper bug in %URI.MakeAbsolute functionality
+- Fix PHP4 syntax error in standalone version
+. Add prefix directory to include path for standalone, this prevents
+  other installations from clobbering the standalone's URI schemes
+. Single test methods can be invoked by prefixing with __only
+
+2.1.0, released 2007-08-02
+# flush-htmldefinition-cache.php superseded in favor of a generic
+  flush-definition-cache.php script, you can clear a specific cache
+  by passing its name as a parameter to the script
+! Phorum mod implemented for HTML Purifier
+! With %Core.AggressivelyFixLt, <3 and similar emoticons no longer
+  trigger HTML removal in PHP5 (DOMLex). This directive is not necessary
+  for PHP4 (DirectLex).
+! Standalone file now available, which greatly reduces the amount of
+  includes (although there are still a few files that reside in the
+  standalone folder)
+! Relative URIs can now be transformed into their absolute equivalents
+  using %URI.Base and %URI.MakeAbsolute
+! Ruby implemented for XHTML 1.1
+! You can now define custom URI filtering behavior, see enduser-uri-filter.html
+  for more details
+! UTF-8 font names now supported in CSS
+- AutoFormatters emit friendly error messages if tags or attributes they
+  need are not allowed
+- ConfigForm's compactification of directive names is now configurable
+- AutoParagraph autoformatter algorithm refined after field-testing
+- XHTML 1.1 now applies XHTML 1.0 Strict cleanup routines, namely
+  blockquote wrapping
+- Contents of <style> tags removed by default when tags are removed
+. HTMLPurifier_Config->getSerial() implemented, this is extremely useful
+  for output cache invalidation
+. ConfigForm printer now can retrieve CSS and JS files as strings, in
+  case HTML Purifier's directory is not publically accessible
+. Introduce new text/itext configuration directive values: these represent
+  longer strings that would be more appropriately edited with a textarea
+. Allow newlines to act as separators for lists, hashes, lookups and
+  %HTML.Allowed
+. ConfigForm generates textareas instead of text inputs for lists, hashes,
+  lookups, text and itext fields
+. Hidden element content removal genericized: %Core.HiddenElements can
+  be used to customize this behavior, by default <script> and <style> are
+  hidden
+. Added HTMLPURIFIER_PREFIX constant, should be used instead of dirname(__FILE__)
+. Custom ChildDef added to default include list
+. URIScheme reflection improved: will not attempt to include file if class
+  already exists. May clobber autoload, so I need to keep an eye on it
+. ConfigSchema heavily optimized, will only collect information and validate
+  definitions when HTMLPURIFIER_SCHEMA_STRICT is true.
+. AttrDef_URI unit tests and implementation refactored
+. benchmarks/ directory now protected from public view with .htaccess file;
+  run the tests via command line
+. URI scheme is munged off if there is no authority and the scheme is the
+  default one
+. All unit tests inherit from HTMLPurifier_Harness, not UnitTestCase
+. Interface for URIScheme changed
+. Generic URI object to hold components of URI added, most systems involved
+  in URI validation have been migrated to use it
+. Custom filtering for URIs factored out to URIDefinition interface for
+  maximum extensibility
+
+2.0.1, released 2007-06-27
+! Tag auto-closing now based on a ChildDef heuristic rather than a
+  manually set auto_close array; some behavior may change
+! Experimental AutoFormat functionality added: auto-paragraph and
+  linkify your HTML input by setting %AutoFormat.AutoParagraph and
+  %AutoFormat.Linkify to true
+! Newlines normalized internally, and then converted back to the
+  value of PHP_EOL. If this is not desired, set your newline format
+  using %Output.Newline.
+! Beta error collection, messages are implemented for the most generic
+  cases involving Lexing or Strategies
+- Clean up special case code for <script> tags
+- Reorder includes for DefinitionCache decorators, fixes a possible
+  missing class error
+- Fixed bug where manually modified definitions were not saved via cache
+  (mostly harmless, except for the fact that it would be a little slower)
+- Configuration objects with different serials do not clobber each
+  others when revision numbers are unequal
+- Improve Serializer DefinitionCache directory permissions checks
+- DefinitionCache no longer throws errors when it encounters old
+  serial files that do not conform to the current style
+- Stray xmlns attributes removed from configuration documentation
+- configForm.php smoketest no longer has XSS vulnerability due to
+  unescaped print_r output
+- Printer adheres to configuration's directives on output format
+- Fix improperly named form field in ConfigForm printer
+. Rewire some test-cases to swallow errors rather than expect them
+. HTMLDefinition printer updated with some of the new attributes
+. DefinitionCache keys reordered to reflect precedence: version number,
+  hash, then revision number
+. %Core.DefinitionCache renamed to %Cache.DefinitionImpl
+. Interlinking in configuration documentation added using
+  Injector_PurifierLinkify
+. Directives now keep track of aliases to themselves
+. Error collector now requires a severity to be passed, use PHP's internal
+  error constants for this
+. HTMLPurifier_Config::getAllowedDirectivesForForm implemented, allows
+  much easier selective embedding of configuration values
+. Doctype objects now accept public and system DTD identifiers
+. %HTML.Doctype is now constrained by specific values, to specify a custom
+  doctype use new %HTML.CustomDoctype
+. ConfigForm truncates long directives to keep the form small, and does
+  not re-output namespaces
+
+2.0.0, released 2007-06-20
+# Completely refactored HTMLModuleManager, decentralizing safety
+  information
+# Transform modules changed to Tidy modules, which offer more flexibility
+  and better modularization
+# Configuration object now finalizes itself when a read operation is
+  performed on it, ensuring that its internal state stays consistent.
+  To revert this behavior, you can set the $autoFinalize member variable 
+  off, but it's not recommended.
+# New compact syntax for AttrDef objects that can be used to instantiate
+  new objects via make()
+# Definitions (esp. HTMLDefinition) are now cached for a significant
+  performance boost. You can disable caching by setting %Core.DefinitionCache
+  to null. You CANNOT edit raw definitions without setting the corresponding
+  DefinitionID directive (%HTML.DefinitionID for HTMLDefinition).
+# Contents between <script> tags are now completely removed if <script>
+  is not allowed
+# Prototype-declarations for Lexer removed in favor of configuration
+  determination of Lexer implementations.
+! HTML Purifier now works in PHP 4.3.2.
+! Configuration form-editing API makes tweaking HTMLPurifier_Config a
+  breeze!
+! Configuration directives that accept hashes now allow new string
+  format: key1:value1,key2:value2
+! ConfigDoc now factored into OOP design
+! All deprecated elements now natively supported
+! Implement TinyMCE styled whitelist specification format in
+  %HTML.Allowed
+! Config object gives more friendly error messages when things go wrong
+! Advanced API implemented: easy functions for creating elements (addElement)
+  and attributes (addAttribute) on HTMLDefinition
+! Add native support for required attributes
+- Deprecated and removed EnableRedundantUTF8Cleaning. It didn't even work!
+- DOMLex will not emit errors when a custom error handler that does not
+  honor error_reporting is used
+- StrictBlockquote child definition refrains from wrapping whitespace
+  in tags now.
+- Bug resulting from tag transforms to non-allowed elements fixed
+- ChildDef_Custom's regex generation has been improved, removing several
+  false positives
+. Unit test for ElementDef created, ElementDef behavior modified to
+  be more flexible
+. Added convenience functions for HTMLModule constructors
+. AttrTypes now has accessor functions that should be used instead
+  of directly manipulating info
+. TagTransform_Center deprecated in favor of generic TagTransform_Simple
+. Add extra protection in AttrDef_URI against phantom Schemes
+. Doctype object added to HTMLDefinition which describes certain aspects
+  of the operational document type
+. Lexer is now pre-emptively included, with a conditional include for the
+  PHP5 only version.
+. HTMLDefinition and CSSDefinition have a common parent class: Definition.
+. DirectLex can now track line-numbers
+. Preliminary error collector is in place, although no code actually reports
+  errors yet
+. Factor out most of ValidateAttributes to new AttrValidator class
+
+1.6.1, released 2007-05-05
+! Support for more deprecated attributes via transformations:
+  + hspace and vspace in img
+  + size and noshade in hr
+  + nowrap in td
+  + clear in br
+  + align in caption, table, img and hr
+  + type in ul, ol and li
+! DirectLex now preserves text in which a < bracket is followed by
+  a non-alphanumeric character. This means that certain emoticons
+  are now preserved.
+! %Core.RemoveInvalidImg is now operational, when set to false invalid
+  images will hang around with an empty src
+! target attribute in a tag supported, use %Attr.AllowedFrameTargets
+  to enable
+! CSS property white-space now allows nowrap (supported in all modern
+  browsers) but not others (which have spotty browser implementations)
+! XHTML 1.1 mode now sort-of works without any fatal errors, and
+  lang is now moved over to xml:lang.
+! Attribute transformation smoketest available at smoketests/attrTransform.php
+! Transformation of font's size attribute now handles super-large numbers
+- Possibly fatal bug with __autoload() fixed in module manager
+- Invert HTMLModuleManager->addModule() processing order to check
+  prefixes first and then the literal module
+- Empty strings get converted to empty arrays instead of arrays with
+  an empty string in them.
+- Merging in attribute lists now works.
+. Demo script removed: it has been added to the website's repository
+. Basic.php script modified to work out of the box
+. Refactor AttrTransform classes to reduce duplication
+. AttrTransform_TextAlign axed in favor of a more general
+  AttrTransform_EnumToCSS, refer to HTMLModule/TransformToStrict.php to
+  see how the new equivalent is implemented
+. Unit tests now use exclusively assertIdentical
+ 
+1.6.0, released 2007-04-01
+! Support for most common deprecated attributes via transformations:
+  + bgcolor in td, th, tr and table
+  + border in img
+  + name in a and img
+  + width in td, th and hr
+  + height in td, th
+! Support for CSS attribute 'height' added
+! Support for rel and rev attributes in a tags added, use %Attr.AllowedRel
+  and %Attr.AllowedRev to activate
+- You can define ID blacklists using regular expressions via
+  %Attr.IDBlacklistRegexp
+- Error messages are emitted when you attempt to "allow" elements or
+  attributes that HTML Purifier does not support
+
+
+- Fix segfault in unit test. The problem is not very reproduceable and
+  I don't know what causes it, but a six line patch fixed it.
+
+1.5.0, released 2007-03-23
+! Added a rudimentary I18N and L10N system modeled off MediaWiki. It
+  doesn't actually do anything yet, but keep your eyes peeled.
+! docs/enduser-utf8.html explains how to use UTF-8 and HTML Purifier
+! Newly structured HTMLDefinition modeled off of XHTML 1.1 modules.
+  I am loathe to release beta quality APIs, but this is exactly that;
+  don't use the internal interfaces if you're not willing to do migration
+  later on.
+- Allow 'x' subtag in language codes
+- Fixed buggy chameleon-support for ins and del
+. Added support for IDREF attributes (i.e. for)
+. Renamed HTMLPurifier_AttrDef_Class to HTMLPurifier_AttrDef_Nmtokens
+. Removed context variable ParentType, replaced with IsInline, which
+  is false when you're not inline and an integer of the parent that
+  caused you to become inline when you are (so possibly zero)
+. Removed ElementDef->type in favor of ElementDef->descendants_are_inline
+  and HTMLDefinition->content_sets
+. StrictBlockquote now reports what elements its supposed to allow,
+  rather than what it does allow
+. Removed HTMLDefinition->info_flow_elements in favor of
+  HTMLDefinition->content_sets['Flow']
+. Removed redundant "exclusionary" definitions from DTD roster
+. StrictBlockquote now requires a construction parameter as if it
+  were an Required ChildDef, this is the "real" set of allowed elements
+. AttrDef partitioned into HTML, CSS and URI segments
+. Modify Youtube filter regexp to be multiline
+. Require both PHP5 and DOM extension in order to use DOMLex, fixes
+  some edge cases where a DOMDocument class exists in a PHP4 environment
+  due to DOM XML extension.
+
+1.4.1, released 2007-01-21
+! docs/enduser-youtube.html updated according to new functionality
+- YouTube IDs can have underscores and dashes
+
+1.4.0, released 2007-01-21
+! Implemented list-style-image, URIs now allowed in list-style
+! Implemented background-image, background-repeat, background-attachment
+  and background-position CSS properties. Shorthand property background
+  supports all of these properties.
+! Configuration documentation looks nicer
+! Added %Core.EscapeNonASCIICharacters to workaround loss of Unicode
+  characters while %Core.Encoding is set to a non-UTF-8 encoding.
+! Support for configuration directive aliases added
+! Config object can now be instantiated from ini files
+! YouTube preservation code added to the core, with two lines of code
+  you can add it as a filter to your code. See smoketests/preserveYouTube.php
+  for sample code.
+! Moved SLOW to docs/enduser-slow.html and added code examples
+- Replaced version check with functionality check for DOM (thanks Stephen
+  Khoo)
+. Added smoketest 'all.php', which loads all other smoketests via frames
+. Implemented AttrDef_CSSURI for url(http://google.com) style declarations
+. Added convenient single test selector form on test runner
 
 1.3.2, released 2006-12-25
 ! HTMLPurifier object now accepts configuration arrays, no need to manually
@@ -156,4 +449,4 @@ 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

@@ -1,13 +1,22 @@
 
 README
-    All about HTMLPurifier
+    All about HTML Purifier
 
-HTMLPurifier is an HTML filtering solution.  It uses a unique combination of
-robust whitelists and agressive parsing to ensure that not only are XSS
-attacks thwarted, but the resulting HTML is standards compliant.
+HTML Purifier is an HTML filtering solution that uses a unique combination 
+of robust whitelists and agressive parsing to ensure that not only are 
+XSS attacks thwarted, but the resulting HTML is standards compliant. 
 
-See INSTALL on how to use the library.  See docs/ for more developer-oriented
-documentation as well as some code examples.  Users of TinyMCE or FCKeditor
-may be especially interested in WYSIWYG.
+HTML Purifier is oriented towards richly formatted documents from 
+untrusted sources that require CSS and a full tag-set.  This library can 
+be configured to accept a more restrictive set of tags, but it won't be 
+as efficient as more bare-bones parsers. It will, however, do the job 
+right, which may be more important. 
 
-HTMLPurifier can be found on the web at: http://hp.jpsband.org/
+Places to go:
+
+* See INSTALL for a quick installation guide
+* See docs/ for developer-oriented documentation, code examples and
+  an in-depth installation guide.
+* See WYSIWYG for information on editors like TinyMCE and FCKeditor
+
+HTML Purifier can be found on the web at: http://htmlpurifier.org/

SLOW

@@ -1,40 +0,0 @@
-
-SLOW
-  also known as the HELP ME LIBRARY IS TOO SLOW MY PAGE TAKE TOO LONG LOAD page
-
-HTML Purifier is a very powerful library.  But with power comes great
-responsibility, or, at least, longer execution times.  Remember, this
-library isn't lightly grazing over submitted HTML: it's deconstructing
-the whole thing, rigorously checking the parts, and then putting it
-back together.
-
-So, if it so turns out that HTML Purifier is kinda too slow for outbound
-filtering, you've got a few options:
-
-1. Inbound filtering - perform filtering of HTML when it's submitted by the
-user.  Since the user is already submitting something, an extra half a
-second tacked on to the load time probably isn't going to be that huge of
-a problem.  Then, displaying the content is a simple a manner of outputting
-it directly from your database/filesystem.  The trouble with this method is
-that your user loses the original text, and when doing edits, will be
-handling the filtered text.  While this may be a good thing, especially if
-you're using a WYSIWYG editor, it can also result in data-loss if a user
-makes a typo.
-
-2. Caching the filtered output - accept the submitted text and put it
-unaltered into the database, but then also generate a filtered version and
-stash that in the database.  Serve the filtered version to readers, and the
-unaltered version to editors.  If need be, you can invalidate the cache and
-have the cached filtered version be regenerated on the first page view.  Pros?
-Full data retention.  Cons?  It's more complicated, and opens other editors
-up to XSS if they are using a WYSIWYG editor (to fix that, they'd have to
-be able to get their hands on the *really* original text served in plaintext
-mode).
-
-In short, inbound filtering is almost as simple as outbound filtering, but
-it has some drawbacks which cannot be fixed unless you save both the original
-and the filtered versions.
-
-There is a third option: profile and optimize HTMLPurifier yourself.  Be sure
-to report back your results if you decide to do that!  Especially if you
-port HTML Purifier to C++.  ;-)

TODO

@@ -1,97 +1,88 @@
-
 TODO List
 
 = KEY ====================
     # Flagship
     - Regular
-    ? At-risk
+    ? Maybe I'll Do It
 ==========================
 
-1.4 release
- # More extensive URI filtering schemes (see docs/proposal-new-directives.txt)
- # Allow for background-image and list-style-image (intrinsically tied to above)
- # Add hooks for custom behavior (for instance, YouTube preservation)
- - Aggressive caching
- ? Rich set* methods and config file loaders for HTMLPurifier_Config
- ? Configuration profiles: sets of directives that get set with one func call
- ? ConfigSchema directive aliases (so we can rename some of them)
- ? URI validation routines tighter (see docs/dev-code-quality.html) (COMPLEX)
+If no interest is expressed for a feature that may required a considerable
+amount of effort to implement, it may get endlessly delayed. Do not be
+afraid to cast your vote for the next feature to be implemented!
 
-1.5 release
+2.2 release [Error'ed]
  # Error logging for filtering/cleanup procedures
-    - Requires I18N facilities to be created first (COMPLEX)
+ - XSS-attempt detection
 
-1.6 release
- # Add pre-packaged "levels" of cleaning (custom behavior already done)
- - More fine-grained control over escaping behavior
-    - Silently drop content inbetween SCRIPT tags (can be generalized to allow
-      specification of elements that, when detected as foreign, trigger removal
-      of children, although unbalanced tags could wreck havoc (or at least
-      delete the rest of the document)).
-
-1.7 release
+2.3 release [Do What I Mean, Not What I Say]
  # Additional support for poorly written HTML
-    - Implement all non-essential attribute transforms (BIG!)
     - Microsoft Word HTML cleaning (i.e. MsoNormal, but research essential!)
     - Friendly strict handling of <address> (block -> <br>)
-
-2.0 release
- # 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
- - XHTML 1.1 support
-
-Ongoing
- - Lots of profiling, make it faster!
- - Plugins for major CMSes (COMPLEX)
-    - Drupal
-    - WordPress
-    - eFiction
-    - more! (look for ones that use WYSIWYGs)
-
-Unknown release (on a scratch-an-itch basis)
- - 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
- - Append something to duplicate IDs so they're still usable (impl. note: the
-   dupe detector would also need to detect the suffix as well)
- - Have 'lang' attribute be checked against official lists
-
-Encoding workarounds
- - Non-lossy dumb alternate character encoding transformations, achieved by
-   numerically encoding all non-ASCII characters
- - Semi-lossy dumb alternate character encoding transformations, achieved by
-   encoding all characters that have string entity equivalents
-
-Requested
- - Native content compression, whitespace stripping (don't rely on Tidy, make
-   sure we don't remove from <pre> or related tags)
- - Win32 Phalanger C# binaries (?)
  - Remove redundant tags, ex. <u><u>Underlined</u></u>. Implementation notes:
     1. Analyzing which tags to remove duplicants
     2. Ensure attributes are merged into the parent tag
     3. Extend the tag exclusion system to specify whether or not the
     contents should be dropped or not (currently, there's code that could do
     something like this if it didn't drop the inner text too.)
- - More user-friendly warnings when %HTML.Allow* attempts to specify a
-   tag or attribute that is not supported
- - Allow specifying global attributes on a tag-by-tag basis in
-   %HTML.AllowAttributes
- - Parse TinyMCE whitelist into our %HTML.Allow* whitelists
- - XSS-attempt detection
+ - Remove <span> tags that don't do anything (no attributes)
+ - Remove empty inline tags<i></i>
+ - Append something to duplicate IDs so they're still usable (impl. note: the
+   dupe detector would also need to detect the suffix as well)
+ - Externalize inline CSS to promote clean HTML
+
+2.4 release [It's All About Trust] (floating)
+ # Implement untrusted, dangerous elements/attributes
+ # Implement IDREF support (harder than it seems, since you cannot have
+   IDREFs to non-existent IDs)
+ # Frameset XHTML 1.0 and HTML 4.01 doctypes
+
+3.0 release [Beyond HTML]
+ # Legit token based CSS parsing (will require revamping almost every
+   AttrDef class). Probably will use CSSTidy class
+ # More control over allowed CSS properties (maybe modularize it in the
+   same fashion!)
+ # Formatters for plaintext
+    - Smileys
+ - Standardize token armor for all areas of processing
+ - Convert RTL/LTR override characters to <bdo> tags, or vice versa on demand.
+   Also, enable disabling of directionality
+
+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
+
+Ongoing
+ - Lots of profiling, make it faster!
+ - Plugins for major CMSes (COMPLEX)
+    - phpBB
+    - eFiction
+    - more! (look for ones that use WYSIWYGs)
+ - Complete basic smoketests
+
+Unknown release (on a scratch-an-itch basis)
+ # CHMOD install script for PEAR installs
+ ? Have 'lang' attribute be checked against official lists, achieved by
+   encoding all characters that have string entity equivalents
+ - Abstract ChildDef_BlockQuote to work with all elements that only
+   allow blocks in them, required or optional
+ - Reorganize Unit Tests
+ - Reorganize configuration directives (Create more namespaces! Get messy!)
+ - Advanced URI filtering schemes (see docs/proposal-new-directives.txt)
+ - Implement lenient <ruby> child validation
+ - Explain how to use HTML Purifier in non-PHP languages / create
+   a simple command line stub (or complicated?)
+ - Fixes for Firefox's inability to handle COL alignment props (Bug 915)
+ - Automatically add non-breaking spaces to empty table cells when
+   empty-cells:show is applied to have compatibility with Internet Explorer
+
+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
+ - Native content compression, whitespace stripping (don't rely on Tidy, make
+   sure we don't remove from <pre> or related tags): use gzip if this is
+   really important

VERSION

@@ -0,0 +1 @@
+2.1.2

WHATSNEW

@@ -0,0 +1,8 @@
+Version 2.1.2 is a mix of experimental features and stability updates.
+Among new features: an Object module for trusted users, support for the
+CSS property 'border-spacing', and HTML 5 style parsing using PH5P.
+Bug fixes ihave resolved a few obscure issues including border-collapse:seperate,
+a DirectLex parsing error, broken HTML in printDefinition.php, and problems
+with the experimental standalone distribution. Also, there were large
+amounts of behind-the-scenes refactoring and the removal of URIScheme
+inclusion reflection.

WYSIWYG

@@ -16,6 +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/

benchmarks/.htaccess

@@ -0,0 +1 @@
+Deny from all

benchmarks/Lexer.php

@@ -7,6 +7,7 @@ set_include_path(get_include_path() . PATH_SEPARATOR . '../library/');
 
 require_once 'HTMLPurifier/ConfigSchema.php';
 require_once 'HTMLPurifier/Config.php';
+require_once 'HTMLPurifier/Context.php';
 
 $LEXERS = array();
 $RUNS = isset($GLOBALS['HTMLPurifierTest']['Runs'])
@@ -93,11 +94,14 @@ function print_lexers() {
 function do_benchmark($name, $document) {
     global $LEXERS, $RUNS;
     
+    $config = HTMLPurifier_Config::createDefault();
+    $context = new HTMLPurifier_Context();
+    
     $timer = new RowTimer($name);
     $timer->start();
     
     foreach($LEXERS as $key => $lexer) {
-        for ($i=0; $i<$RUNS; $i++) $tokens = $lexer->tokenizeHTML($document);
+        for ($i=0; $i<$RUNS; $i++) $tokens = $lexer->tokenizeHTML($document, $config, $context);
         $timer->setMarker($key);
     }
     
@@ -161,4 +165,4 @@ echo '<div>Random input was: ' .
 ?>
 
 
-</body></html>
+</body></html>

benchmarks/ProfileDirectLex.php

@@ -5,12 +5,13 @@ set_include_path(get_include_path() . PATH_SEPARATOR . '../library/');
 require_once 'HTMLPurifier/ConfigSchema.php';
 require_once 'HTMLPurifier/Config.php';
 require_once 'HTMLPurifier/Lexer/DirectLex.php';
+require_once 'HTMLPurifier/Context.php';
 
 $input = file_get_contents('samples/Lexer/4.html');
 $lexer = new HTMLPurifier_Lexer_DirectLex();
+$config = HTMLPurifier_Config::createDefault();
+$context = new HTMLPurifier_Context();
 
 for ($i = 0; $i < 10; $i++) {
-    $tokens = $lexer->tokenizeHTML($input);
+    $tokens = $lexer->tokenizeHTML($input, $config, $context);
 }
-
-?>

benchmarks/Trace.php

@@ -0,0 +1,12 @@
+<?php
+
+ini_set('xdebug.trace_format', 1);
+ini_set('xdebug.show_mem_delta', true);
+
+xdebug_start_trace(dirname(__FILE__) . '/Trace');
+require_once '../library/HTMLPurifier.auto.php';
+
+$purifier = new HTMLPurifier();
+
+$data = $purifier->purify(file_get_contents('samples/Lexer/4.html'));
+xdebug_stop_trace();

configdoc/generate.php

@@ -2,217 +2,44 @@
 
 /**
  * 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
 
+define('HTMLPURIFIER_SCHEMA_STRICT', true); // description data needs to be collected
 
-// ---------------------------------------------------------------------------
-// Include HTML Purifier library
+// load dual-libraries
+require_once '../library/HTMLPurifier.auto.php';
+require_once 'library/ConfigDoc.auto.php';
 
-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
+$purifier = HTMLPurifier::getInstance(array(
+    'AutoFormat.PurifierLinkify' => true
+));
 
 $schema = HTMLPurifier_ConfigSchema::instance();
-$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) {
-        
-        $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 +1,9 @@
+<?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 +1,38 @@
+<?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
+        $out = str_replace(' xmlns="http://www.w3.org/1999/xhtml"', '', $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 +1,25 @@
+<?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 +1,123 @@
+<?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_aliases = $dom_document->createElement('aliases');
+                $dom_directive->appendChild($dom_aliases);
+                foreach ($info->directiveAliases as $alias) {
+                    $dom_aliases->appendChild($dom_document->createElement('alias', $alias));
+                }
+                
+                $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 +1,26 @@
+<?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.css

@@ -1,3 +1,6 @@
+
+body {margin:1em 4em;}
+
 table {border-collapse:collapse;}
 table td, table th {padding:0.2em;}
 
@@ -8,3 +11,14 @@ table.constraints td pre {margin:0;}
 
 #toc {list-style-type:none; font-weight:bold;}
 #toc ul {list-style-type:disc; font-weight:normal;}
+
+.description p {margin-top:0;margin-bottom:1em;}
+
+#library, h1 {text-align:center; font-family:Garamond, serif;
+  font-variant:small-caps;}
+#library {font-size:1em;}
+h1 {margin-top:0;}
+h2 {border-bottom:1px solid #CCC; font-family:sans-serif; font-weight:normal;
+    font-size:1.3em;}
+h3 {font-family:sans-serif; font-size:1.1em; font-weight:bold; }
+h4 {font-family:sans-serif; font-size:0.9em; font-weight:bold; }

configdoc/styles/plain.xsl

@@ -12,18 +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><xsl:value-of select="/configdoc/title" /> Configuration Documentation</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>
-                <h1><xsl:value-of select="/configdoc/title" /> Configuration Documentation</h1>
+                <div id="library"><xsl:value-of select="/configdoc/title" /></div>
+                <h1><xsl:value-of select="$title" /></h1>
                 <h2>Table of Contents</h2>
                 <ul id="toc">
                     <xsl:apply-templates mode="toc" />
@@ -69,23 +72,45 @@
         <xsl:apply-templates />
     </xsl:template>
     <xsl:template match="directive/name">
+        <xsl:apply-templates select="../aliases/alias" mode="anchor" />
         <h3 id="{../@id}"><xsl:value-of select="../@id" /></h3>
     </xsl:template>
+    <xsl:template match="alias" mode="anchor">
+        <a id="{.}"></a>
+    </xsl:template>
+    
+    <!-- Do not pass through -->
+    <xsl:template match="alias"></xsl:template>
+    
     <xsl:template match="directive/constraints">
         <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>
+            <xsl:if test="../aliases/alias">
+                <xsl:apply-templates select="../aliases" mode="constraints" />
+            </xsl:if>
         </table>
     </xsl:template>
+    <xsl:template match="directive/aliases" mode="constraints">
+        <th>Aliases:</th>
+        <td>
+            <xsl:for-each select="alias">
+                <xsl:if test="position()&gt;1">, </xsl:if>
+                <xsl:value-of select="." />
+            </xsl:for-each>
+        </td>
+    </xsl:template>
     <xsl:template match="directive//description">
         <div class="description">
             <xsl:copy-of select="div/node()" />
@@ -123,4 +148,4 @@
         </tr>
     </xsl:template>
     
-</xsl:stylesheet>
+</xsl:stylesheet>

docs/dev-advanced-api.html

@@ -0,0 +1,213 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN"
+    "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">
+<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en"><head>
+<meta http-equiv="Content-Type" content="text/html; charset=UTF-8" />
+<meta name="description" content="Functional specification for HTML Purifier's advanced API for defining custom filtering behavior." />
+<link rel="stylesheet" type="text/css" href="style.css" />
+
+<title>Advanced API - HTML Purifier</title>
+
+</head><body>
+
+<h1>Advanced API</h1>
+
+<div id="filing">Filed under Development</div>
+<div id="index">Return to the <a href="index.html">index</a>.</div>
+<div id="home"><a href="http://htmlpurifier.org/">HTML Purifier</a> End-User Documentation</div>
+
+<p>HTML Purifier currently natively supports only a subset of HTML's
+allowed elements, attributes, and behavior; specifically, this subset
+is the set of elements that are safe for untrusted users to use.
+However, HTML Purifier is often utilized to ensure standards-compliance
+from input that is trusted (making it a sort of Tidy substitute),
+and often users need to define new elements or attributes. The
+advanced API is oriented specifically for these use-cases.</p>
+
+<p>Our goals are to let the user:</p>
+
+<dl>
+    <dt>Select</dt>
+    <dd><ul>
+        <li>Doctype</li>
+        <!-- <li>Filterset</li> -->
+        <li>Elements / Attributes / Modules</li>
+        <li>Tidy</li>
+    </ul></dd>
+    <dt>Customize</dt>
+    <dd><ul>
+        <li>Attributes</li>
+        <li>Elements</li>
+        <!--<li>Doctypes</li>-->
+    </ul></dd>
+</dl>
+
+<h2>Select</h2>
+
+<p>For basic use, the user will have to specify some basic parameters. This
+is not strictly necessary, as HTML Purifier's default setting will always
+output safe code, but is required for standards-compliant output.</p>
+
+<h3>Selecting a Doctype</h3>
+
+<p>The first thing to select is the <strong>doctype</strong>. This
+is essential for standards-compliant output.</p>
+
+<p class="technical">This identifier is based
+on the name the W3C has given to the document type and <em>not</em>
+the DTD identifier.</p>
+
+<p>This parameter is set via the configuration object:</p>
+
+<pre>$config->set('HTML', 'Doctype', 'XHTML 1.0 Transitional');</pre>
+
+<p>Due to historical reasons, the default doctype is XHTML 1.0
+Transitional, however, we really shouldn't be guessing what the user's
+doctype is. Fortunantely, people who can't be bothered to set this won't
+be bothered when their pages stop validating.</p>
+
+<h3>Selecting Elements / Attributes / Modules</h3>
+
+<p>HTML Purifier will, by default, allow as many elements and attributes
+as possible. However, a user may decide to roll their own filterset by
+selecting modules, elements and attributes to allow for their own
+specific use-case. This can be done using %HTML.Allowed:</p>
+
+<pre>$config->set('HTML', 'Allowed', 'a[href|title],em,p,blockquote');</pre>
+
+<p class="technical">The directive %HTML.Allowed is a convenience feature
+that may be fully expressed with the legacy interface.</p>
+
+<p>We currently support another interface from older versions:</p>
+
+<pre>$config->set('HTML', 'AllowedElements', 'a,em,p,blockquote');
+$config->set('HTML', 'AllowedAttributes', 'a.href,a.title');</pre>
+
+<p>A user may also choose to allow modules using a specialized
+directive:</p>
+
+<pre>$config->set('HTML', 'AllowedModules', 'Hypertext,Text,Lists');</pre>
+
+<p>But it is not expected that this feature will be widely used.</p>
+
+<p class="technical">Module selection will work slightly differently
+from the other AllowedElements and AllowedAttributes directives by
+directly modifying the doctype you are operating in, in the spirit of
+XHTML 1.1's modularization. We stop users from shooting themselves in the
+foot by mandating the modules in %HTML.CoreModules be used.</p>
+
+<p class="technical">Modules are distinguished from regular elements by the
+case of their first letter. While XML distinguishes between and allows
+lower and uppercase letters in element names, XHTML uses only lower-case
+element names for sake of consistency.</p>
+
+<h3>Selecting Tidy</h3>
+
+<p>The name of this segment of functionality is inspired off of Dave
+Ragget's program HTML Tidy, which purported to help clean up HTML. In
+HTML Purifier, Tidy functionality involves turning unsupported and
+deprecated elements into standards-compliant ones, maintaining
+backwards compatibility, and enforcing best practices.</p>
+
+<p>This is a complicated feature, and is explained more in depth at
+<a href="enduser-tidy.html">the Tidy documentation page</a>.</p>
+
+<!--
+<h3>Unified selector</h3>
+
+<p>Because selecting each and every one of these configuration options
+is a chore, we may wish to offer a specialized configuration method
+for selecting a filterset. Possibility:</p>
+
+<pre>function selectFilter($doctype, $filterset, $tidy)</pre>
+
+<p>...which is simply a light wrapper over the individual configuration
+calls. A custom config file format or text format could also be adopted.</p>
+-->
+
+<h2>Customize</h2>
+
+<p>By reviewing topic posts in the support forum, we determined that
+there were two primarily demanded customization features people wanted:
+to add an attribute to an existing element, and to add an element.
+Thus, we'll want to create convenience functions for these common
+use-cases.</p>
+
+<p>Note that the functions described here are only available if
+a raw copy of <code>HTMLPurifier_HTMLDefinition</code> was retrieved.
+Furthermore, caching may prevent your changes from immediately
+being seen: consult <a href="enduser-customize.html">enduser-customize.html</a> on how
+to work around this.</p>
+
+<h3>Attributes</h3>
+
+<p>An attribute is bound to an element by a name and has a specific
+<code>AttrDef</code> that validates it. The interface is therefore:</p>
+
+<pre>function addAttribute($element, $attribute, $attribute_def);</pre>
+
+<p>Example of the functionality in action:</p>
+
+<pre>$def->addAttribute('a', 'rel', 'Enum#nofollow');</pre>
+
+<p>The <code>$attribute_def</code> value is flexible,
+to make things simpler. It can be a literal object or:</p>
+
+<ul>
+    <!--<li>Class name: We'll instantiate it for you</li>
+    <li>Function name: We'll create an <code>HTMLPurifier_AttrDef_Anonymous</code>
+        class with that function registered as a callback.</li>-->
+    <li>String attribute type: We'll use <code>HTMLPurifier_AttrTypes</code>
+        to resolve it for you. Any data that follows a hash mark (#) will
+        be used to customize the attribute type: in the example above, 
+        we specify which values for Enum to allow.</li>
+</ul>
+
+<h3>Elements</h3>
+
+<p>An element requires certain information as specified by
+<code>HTMLPurifier_ElementDef</code>. However, not all of it is necessary,
+the usual things required are:</p>
+
+<ul>
+    <li>Attributes</li>
+    <li>Content model/type</li>
+    <li>Registration in a content set</li>
+</ul>
+
+<p>This suggests an API like this:</p>
+
+<pre>function addElement($element, $type, $contents,
+    $attr_collections = array(); $attributes = array());</pre>
+
+<p>Each parameter explained in depth:</p>
+
+<dl>
+    <dt><code>$element</code></dt>
+    <dd>Element name, ex. 'label'</dd>
+    <dt><code>$type</code></dt>
+    <dd>Content set to register in, ex. 'Inline' or 'Flow'</dd>
+    <dt><code>$contents</code></dt>
+    <dd>Description of allowed children. This is a merged form of
+        <code>HTMLPurifier_ElementDef</code>'s member variables
+        <code>$content_model</code> and <code>$content_model_type</code>,
+        where the form is <q>Type: Model</q>, ex. 'Optional: Inline'.
+        There are also a number of predefined templates one may use.</dd>
+    <dt><code>$attr_collections</code></dt>
+    <dd>Array (or string if only one) of attribute collection(s) to
+        merge into the attributes array.</dd>
+    <dt><code>$attributes</code></dt>
+    <dd>Array of attribute names to attribute definitions, much like
+        the above-described attribute customization.</dd>
+</dl>
+
+<p>A possible usage:</p>
+
+<pre>$def->addElement('font', 'Inline', 'Optional: Inline', 'Common',
+    array('color' => 'Color'));</pre>
+
+<p>See <code>HTMLPurifier/HTMLModule.php</code> for details.</p>
+
+<div id="version">$Id$</div>
+
+</body></html>

docs/dev-code-quality.txt

@@ -1,32 +1,17 @@
-<?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>
-
-<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
-    Class - doesn't support Unicode characters (fringe); uses regular
-        expressions
+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
     Length - easily mistaken for CSSLength
     URI - multiple regular expressions; missing validation for parts (?)
@@ -36,16 +21,8 @@ ConfigSchema - redefinition is a mess
 Strategy
     FixNesting - cannot bubble nodes out of structures, duplicated checks
         for special-case parent node
-    MakeWellFormed - insufficient automatic closing definitions (check HTML
-        spec for optional end tags, also, closing based on type (block/inline)
-        might be efficient).
     RemoveForeignElements - should be run in parallel with MakeWellFormed
 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

@@ -14,6 +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://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>
@@ -78,4 +79,4 @@ help you find the correct functionality more quickly.  Here they are:</p>
 
 <div id="version">$Id$</div>
 
-</body></html>
+</body></html>

docs/dev-optimization.html

@@ -14,6 +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://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
@@ -29,4 +30,4 @@ that itch, put it here!</p>
 
 <div id="version">$Id$</div>
 
-</body></html>
+</body></html>

docs/dev-progress.html

@@ -32,13 +32,14 @@ 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://htmlpurifier.org/">HTML Purifier</a> End-User Documentation</div>
 
 <h2>Key</h2>
 
 <table cellspacing="0"><tbody>
 <tr><td class="impl-yes">Implemented</td></tr>
 <tr><td class="impl-partial">Partially implemented</td></tr>
-<tr><td class="impl-no">Will not implement</td></tr>
+<tr><td class="impl-no">Not priority to implement</td></tr>
 <tr><td class="danger">Dangerous attribute/property</td></tr>
 <tr><td class="css1">Present in CSS1</td></tr>
 <tr><td class="feature">Feature, requires extra work</td></tr>
@@ -59,7 +60,7 @@ thead th {text-align:left;padding:0.1em;background-color:#EEE;}
 <tbody>
 <tr><th colspan="2">Standard</th></tr>
 <tr class="css1 impl-yes"><td>background-color</td><td>COMPOSITE(&lt;color&gt;, transparent)</td></tr>
-<tr class="css1 impl-yes"><td>background</td><td>SHORTHAND, only for color, see below for info on background-image and friends</td></tr>
+<tr class="css1 impl-yes"><td>background</td><td>SHORTHAND, currently alias for background-color</td></tr>
 <tr class="css1 impl-yes"><td>border</td><td>SHORTHAND, MULTIPLE</td></tr>
 <tr class="css1 impl-yes"><td>border-color</td><td>MULTIPLE</td></tr>
 <tr class="css1 impl-yes"><td>border-style</td><td>MULTIPLE</td></tr>
@@ -117,6 +118,7 @@ thead th {text-align:left;padding:0.1em;background-color:#EEE;}
 <tbody>
 <tr><th colspan="2">Table</th></tr>
 <tr class="impl-yes"><td>border-collapse</td><td>ENUM(collapse, seperate)</td></tr>
+<tr class="impl-yes"><td>border-space</td><td>MULTIPLE</td></tr>
 <tr class="impl-yes"><td>caption-side</td><td>ENUM(top, bottom)</td></tr>
 <tr class="feature"><td>empty-cells</td><td>ENUM(show, hide), No IE support makes this useless,
     possible fix with &amp;nbsp;? Unknown release milestone.</td></tr>
@@ -141,17 +143,17 @@ thead th {text-align:left;padding:0.1em;background-color:#EEE;}
 
 <tbody>
 <tr><th colspan="2">Unknown</th></tr>
-<tr class="danger css1"><td>background-image</td><td>Dangerous, target milestone 1.3</td></tr>
-<tr class="css1"><td>background-attachment</td><td>ENUM(scroll, fixed),
+<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"><td>background-position</td><td>Depends on background-image</td></tr>
+<tr class="css1 impl-yes"><td>background-position</td><td>Depends on background-image</td></tr>
 <tr class="danger impl-no"><td>cursor</td><td>Dangerous but fluffy</td></tr>
 <tr class="danger css1"><td>display</td><td>ENUM(...), Dangerous but interesting;
     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><td class="css1">height</td><td>Interesting, why use it? Unknown target milestone.</td></tr>
-<tr class="danger css1"><td>list-style-image</td><td>Dangerous? Target milestone 1.3</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>
 <tr class="impl-no"><td>max-width</td></tr>
@@ -167,9 +169,9 @@ 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>
 
@@ -230,21 +232,21 @@ Mozilla on inside and needs -moz-outline, no IE support.</td></tr>
 
 <tbody>
 <tr><th colspan="3">CSS</th></tr>
-<tr class="impl-yes"><td>style</td><td>All</td><td>Not all properties may be implemented, parser is good though.</td></tr>
+<tr class="impl-yes"><td>style</td><td>All</td><td>Parser is reasonably functional. Status here doesn't count individual properties.</td></tr>
 </tbody>
 
 <tbody>
 <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>
@@ -261,41 +263,41 @@ 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>Equivalent style 'text-align' (IE tested)</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' (IE tested)</td></tr>
-    <tr><td>TR</td><td>Equivalent style 'background-color' (IE tested)</td></tr>
-    <tr><td>TD, TH</td><td>Equivalent style 'background-color'</td></tr>
-<tr><td>border</td><td>IMG</td><td>Equivalent style 'border-width', 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>
 
 <div id="version">$Id$</div>
 
-</body></html>
+</body></html>

docs/enduser-customize.html

@@ -0,0 +1,798 @@
+<?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>
+
+<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 or 1.1 (and its HTML variants)
+  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>
+  As of HTMLPurifier 2.1.0, we have 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, but applicable for positioning any text (not
+  limited to translations) above or below other corresponding text.
+</p>
+
+<h3>XHTML 2.0</h3>
+
+<p>
+  <a href="http://www.w3.org/TR/xhtml2/">XHTML 2.0</a> is still a
+  working draft, so any elements introduced in the
+  specification have not been implemented and will not be implemented
+  until we get a recommendation or proposal.  Because XHTML 2.0 is
+  an entirely new markup language, implementing rules for it will be
+  no easy task.
+</p>
+
+<h3>HTML 5</h3>
+
+<p>
+  <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. (The <code>- O</code> allows the closing tag to be 
+  omitted, though in XML this is not allowed.) 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>
+
+<p class="aside">
+  Readers familiar with the modularization may have noticed that the Core
+  attribute collection differs from that specified by the <a
+  href="http://www.w3.org/TR/xhtml-modularization/abstract_modules.html#s_commonatts">abstract
+  modules of the XHTML Modularization 1.1</a>. We believe this section
+  to be in error, as <code>br</code> permits the use of the <code>style</code>
+  attribute even though it uses the <code>Core</code> collection, and 
+  the DTD and XML Schemas supplied by W3C support our interpretation.
+</p>
+
+<h3>Attributes</h3>
+
+<p>
+  If you didn't read the <a href="#addAttribute">earlier section on
+  adding attributes</a>, read it now.  The last parameter is simply
+  an 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

@@ -15,6 +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://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>
@@ -57,7 +58,7 @@ appear elsewhere on the document.  The method is simple:</p>
 
 <pre>$config->set('HTML', 'EnableAttrID', true);
 $config->set('Attr', 'IDBlacklist' array(
-    'list', 'of', 'attributes', 'that', 'are', 'forbidden'
+    'list', 'of', 'attribute', 'values', 'that', 'are', 'forbidden'
 ));</pre>
 
 <p>That being said, there are some notable drawbacks.  First of all, you have to
@@ -70,9 +71,9 @@ to possible standards-compliance issues.</p>
 <p>Furthermore, this position becomes untenable when a single web page must hold
 multiple portions of user-submitted content.  Since there's obviously no way
 to find out before-hand what IDs users will use, the blacklist is helpless.
-And even since HTML Purifier validates each segment seperately, perhaps doing
+And since HTML Purifier validates each segment separately, perhaps doing
 so at different times, it would be extremely difficult to dynamically update
-the blacklist inbetween runs.</p>
+the blacklist in between runs.</p>
 
 <p>Finally, simply destroying the ID is extremely un-userfriendly behavior: after
 all, they might have simply specified a duplicate ID by accident.</p>
@@ -143,4 +144,4 @@ anchors is beyond me.</p>
 <div id="version">$Id$</div>
 
 </body>
-</html>
+</html>

docs/enduser-overview.txt

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

docs/enduser-security.txt

@@ -6,43 +6,11 @@ through negligence of people. This class will do its job: no more, no less,
 and it's up to you to provide it the proper information and proper context
 to be effective. Things to remember:
 
-1. Character Encoding: UTF-8.
-Currently, the parser runs under the assumption that it is dealing
-with UTF-8. Not ISO-8859-1 or Windows-1252, UTF-8. And definitely not "no
-character encoding explicitly stated" or UTF-7. If you're not using UTF-8 as
-your character encoding, make sure you configure HTML Purifier or switch
-to UTF-8. Now. Also, make sure any input is properly converted to UTF-8, or
-the parser will mangle it badly (though it won't be a security risk if you're
-outputting it as UTF-8 though).  Character encoding is, in general, a knotty
-issue, but do yourself a favor and learn about it:
-<http://www.joelonsoftware.com/articles/Unicode.html>
+1. Character Encoding: see enduser-utf8.html for more info.
 
-2. Doctype: XHTML 1.0 Transitional
-This is what the parser is outputting. For the most
-part, it's compatible with HTML 4.01, but XHTML enforces some very nice things
-that all web developers should use. Regardless, NO DOCTYPE is a NO. Quirks mode
-has waaaay too many quirks for a little parser to handle.  We did not select
-strict in order to prevent ourselves from being too draconic on users, but
-this may be configurable in the future.  Do you want standards compliance?
-The doctype is a good place to start.
+2. IDs: see enduser-id.html for more info
 
-3. IDs
-They need to be unique, but without some knowledge of the
-rest of the document, it's difficult to know what's unique. %Attr.IDBlacklist
-needs to be set: we may want to consider disallowing IDs by default to
-save lazy programmers.
+3. URIs: see enduser-uri-filter.html
 
-4. [PROJECTED] Links
-We're not going to try for spam protection (although
-some hooks for such a module might be nice) but we may offer the ability to
-only accept relative URLs. Pick the one that's right for you.
-
-5. CSS
-While we can prevent the most flagrant cases from affecting your
-layout (such as absolutely positioned elements), no amount of code is going
-to protect your pages from being attacked by garish colors and plain old
-bad taste.  A neat feature would be the ability to define acceptable colors
-in a document, but that's not likely to be implemented for a while.  In the
-meantime, be sure to make sure that floated elements (permitted, since they
-can be quite useful) can't mess up your layout. Once again, we may want to
-disable this by default to protect lazy developers.
+4. CSS: document pending
+Explain which CSS styles we blocked and why.

docs/enduser-slow.html

@@ -0,0 +1,117 @@
+<?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="Explains how to speed up HTML Purifier through caching or inbound filtering." />
+<link rel="stylesheet" type="text/css" href="./style.css" />
+
+<title>Speeding up HTML Purifier - HTML Purifier</title>
+
+</head><body>
+
+<h1 class="subtitled">Speeding up HTML Purifier</h1>
+<div class="subtitle">...also known as the HELP ME LIBRARY IS TOO SLOW MY PAGE TAKE TOO LONG page</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>
+
+<p>HTML Purifier is a very powerful library. But with power comes great 
+responsibility, in the form of longer execution times.  Remember, this 
+library isn't lightly grazing over submitted HTML: it's deconstructing 
+the whole thing, rigorously checking the parts, and then putting it back 
+together. </p>
+
+<p>So, if it so turns out that HTML Purifier is kinda too slow for outbound 
+filtering, you've got a few options: </p>
+
+<h2>Inbound filtering</h2>
+
+<p>Perform filtering of HTML when it's submitted by the user. Since the 
+user is already submitting something, an extra half a second tacked on 
+to the load time probably isn't going to be that huge of a problem.  
+Then, displaying the content is a simple a manner of outputting it 
+directly from your database/filesystem. The trouble with this method is 
+that your user loses the original text, and when doing edits, will be 
+handling the filtered text.  While this may be a good thing, especially 
+if you're using a WYSIWYG editor, it can also result in data-loss if a 
+user makes a typo. </p>
+
+<p>Example (non-functional):</p>
+
+<pre>&lt;?php
+    /**
+     * FORM SUBMISSION PAGE
+     * display_error($message) : displays nice error page with message
+     * display_success() : displays a nice success page
+     * display_form() : displays the HTML submission form
+     * database_insert($html) : inserts data into database as new row
+     */
+    if (!empty($_POST)) {
+        require_once '/path/to/library/HTMLPurifier.auto.php';
+        require_once 'HTMLPurifier.func.php';
+        $dirty_html = isset($_POST['html']) ? $_POST['html'] : false;
+        if (!$dirty_html) {
+            display_error('You must write some HTML!');
+        }
+        $html = HTMLPurifier($dirty_html);
+        database_insert($html);
+        display_success();
+        // notice that $dirty_html is *not* saved
+    } else {
+        display_form();
+    }
+?&gt;</pre>
+
+<h2>Caching the filtered output</h2>
+
+<p>Accept the submitted text and put it unaltered into the database, but 
+then also generate a filtered version and stash that in the database.  
+Serve the filtered version to readers, and the unaltered version to 
+editors.  If need be, you can invalidate the cache and have the cached 
+filtered version be regenerated on the first page view.  Pros? Full data 
+retention. Cons? It's more complicated, and opens other editors up to 
+XSS if they are using a WYSIWYG editor (to fix that, they'd have to be 
+able to get their hands on the *really* original text served in 
+plaintext mode). </p>
+
+<p>Example (non-functional):</p>
+
+<pre>&lt;?php
+    /**
+     * VIEW PAGE
+     * display_error($message) : displays nice error page with message
+     * cache_get($id) : retrieves HTML from fast cache (db or file)
+     * cache_insert($id, $html) : inserts good HTML into cache system
+     * database_get($id) : retrieves raw HTML from database
+     */
+    $id = isset($_GET['id']) ? (int) $_GET['id'] : false;
+    if (!$id) {
+        display_error('Must specify ID.');
+        exit;
+    }
+    $html = cache_get($id); // filesystem or database
+    if ($html === false) {
+        // cache didn't have the HTML, generate it
+        $raw_html = database_get($id);
+        require_once '/path/to/library/HTMLPurifier.auto.php';
+        require_once 'HTMLPurifier.func.php';
+        $html = HTMLPurifier($raw_html);
+        cache_insert($id, $html);
+    }
+    echo $html;
+?&gt;</pre>
+
+<h2>Summary</h2>
+
+<p>In short, inbound filtering is the simple option and caching is the
+robust option (albeit with bigger storage requirements). </p>
+
+<p>There is a third option, independent of the two we've discussed: profile 
+and optimize HTMLPurifier yourself. Be sure to report back your results 
+if you decide to do that! Especially if you port HTML Purifier to C++. 
+<tt>;-)</tt></p>
+
+</body>
+</html>

docs/enduser-tidy.html

@@ -0,0 +1,230 @@
+<?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>
+
+<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 features 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 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-uri-filter.html

@@ -0,0 +1,201 @@
+<?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 creating custom URI filters." />
+<link rel="stylesheet" type="text/css" href="style.css" />
+
+<title>URI Filters - HTML Purifier</title>
+
+</head><body>
+
+<h1>URI Filters</h1>
+
+<div id="filing">Filed under End-User</div>
+<div id="index">Return to the <a href="index.html">index</a>.</div>
+<div id="home"><a href="http://htmlpurifier.org/">HTML Purifier</a> End-User Documentation</div>
+
+<p>
+  This is a quick and dirty document to get you on your way to writing
+  custom URI filters for your own URL filtering needs.  Why would you
+  want to write a URI filter?  If you need URIs your users put into
+  HTML to magically change into a different URI, this is
+  exactly what you need!
+</p>
+
+<h2>Creating the class</h2>
+
+<p>
+  Any URI filter you make will be a subclass of <code>HTMLPurifier_URIFilter</code>.
+  The scaffolding is thus:
+</p>
+
+<pre>class HTMLPurifier_URIFilter_<strong>NameOfFilter</strong> extends HTMLPurifier_URIFilter
+{
+    var $name = '<strong>NameOfFilter</strong>';
+    function prepare($config) {}
+    function filter(&$uri, $config, &$context) {}
+}</pre>
+
+<p>
+  Fill in the variable <code>$name</code> with the name of your filter, and
+  take a look at the two methods. <code>prepare()</code> is an initialization
+  method that is called only once, before any filtering has been done of the
+  HTML. Use it to perform any costly setup work that only needs to be done
+  once. <code>filter()</code> is the guts and innards of our filter:
+  it takes the URI and does whatever needs to be done to it.
+</p>
+
+<p>
+  If you've worked with HTML Purifier, you'll recognize the <code>$config</code>
+  and <code>$context</code> parameters.  On the other hand, <code>$uri</code>
+  is something unique to this section of the application: it's a
+  <code>HTMLPurifier_URI</code> object. The interface is thus:
+</p>
+
+<pre>class HTMLPurifier_URI
+{
+    var $scheme, $userinfo, $host, $port, $path, $query, $fragment;
+    function HTMLPurifier_URI($scheme, $userinfo, $host, $port, $path, $query, $fragment);
+    function toString();
+    function copy();
+    function getSchemeObj($config, &$context);
+    function validate($config, &$context);
+}</pre>
+
+<p>
+  The first three methods are fairly self-explanatory: you have a constructor,
+  a serializer, and a cloner.  Generally, you won't be using them when
+  you are manipulating the URI objects themselves.
+  <code>getSchemeObj()</code> is a special purpose method that returns
+  a <code>HTMLPurifier_URIScheme</code> object corresponding to the specific
+  URI at hand. <code>validate()</code> performs general-purpose validation
+  on the internal components of a URI. Once again, you don't need to
+  worry about these: they've already been handled for you.
+</p>
+
+<h2>URI format</h2>
+
+<p>
+  As a URIFilter, we're interested in the member variables of the URI object.
+</p>
+
+<table class="quick"><tbody>
+  <tr><th>Scheme</th>   <td>The protocol for identifying (and possibly locating) a resource (http, ftp, https)</td></tr>
+  <tr><th>Userinfo</th> <td>User information such as a username (bob)</td></tr>
+  <tr><th>Host</th>     <td>Domain name or IP address of the server (example.com, 127.0.0.1)</td></tr>
+  <tr><th>Port</th>     <td>Network port number for the server (80, 12345)</td></tr>
+  <tr><th>Path</th>     <td>Data that identifies the resource, possibly hierarchical (/path/to, ed@example.com)</td></tr>
+  <tr><th>Query</th>    <td>String of information to be interpreted by the resource (?q=search-term)</td></tr>
+  <tr><th>Fragment</th> <td>Additional information for the resource after retrieval (#bookmark)</td></tr>
+</tbody></table>
+
+<p>
+  Because the URI is presented to us in this form, and not 
+  <code>http://bob@example.com:8080/foo.php?q=string#hash</code>, it saves us
+  a lot of trouble in having to parse the URI every time we want to filter
+  it. For the record, the above URI has the following components:
+</p>
+
+<table class="quick"><tbody>
+  <tr><th>Scheme</th>   <td>http</td></tr>
+  <tr><th>Userinfo</th> <td>bob</td></tr>
+  <tr><th>Host</th>     <td>example.com</td></tr>
+  <tr><th>Port</th>     <td>8080</td></tr>
+  <tr><th>Path</th>     <td>/foo.php</td></tr>
+  <tr><th>Query</th>    <td>q=string</td></tr>
+  <tr><th>Fragment</th> <td>hash</td></tr>
+</tbody></table>
+
+<p>
+  Note that there is no question mark or octothorpe in the query or
+  fragment: these get removed during parsing.
+</p>
+
+<p>
+  With this information, you can get straight to implementing your
+  <code>filter()</code> method. But one more thing...
+</p>
+
+<h2>Return value: Boolean, not URI</h2>
+
+<p>
+  You may have noticed that the URI is being passed in by reference.
+  This means that whatever changes you make to it, those changes will
+  be reflected in the URI object the callee had.  <strong>Do not
+  return the URI object: it is unnecessary and will cause bugs.</strong>
+  Instead, return a boolean value, true if the filtering was successful,
+  or false if the URI is beyond repair and needs to be axed.
+</p>
+
+<p>
+  Let's suppose I wanted to write a filter that de-internationalized domain
+  names by converting them to <a href="http://en.wikipedia.org/wiki/Punycode">Punycode</a>.
+  Assuming that <code>punycode_encode($input)</code> converts <code>$input</code> to
+  Punycode and returns <code>false</code> on failure:
+</p>
+
+<pre>class HTMLPurifier_URIFilter_ConvertIDNToPunycode extends HTMLPurifier_URIFilter
+{
+    var $name = 'ConvertIDNToPunycode';
+    function filter(&$uri, $config, &$context) {
+        if (is_null($uri->host)) return true;
+        if ($uri->host == utf8_decode($uri->host)) {
+            // is ASCII, abort
+            return true;
+        }
+        $host = punycode_encode($uri->host);
+        if ($host === false) return false;
+        $uri->host = $host;
+        return true;
+    }
+}</pre>
+
+<p>
+  Notice I did not <code>return $uri;</code>.
+</p>
+
+<h2>Activating your filter</h2>
+
+<p>
+  Having a filter is all well and good, but you need to tell HTML Purifier
+  to use it. Fortunately, this part's simple:
+</p>
+
+<pre>$uri =& $config->getDefinition('URI');
+$uri->addFilter(new HTMLPurifier_URIFilter_<strong>NameOfFilter</strong>());</pre>
+
+<p>
+  If you want to be really fancy, you can define a configuration directive
+  for your filter and have HTML Purifier automatically manage whether or
+  not your filter gets loaded or not (this is how internal filters manage
+  things):
+</p>
+
+<pre>HTMLPurifier_ConfigSchema::define(
+    'URI', '<strong>NameOfFilter</strong>', false, 'bool',
+    '<strong>What your filter does.</strong>'
+);
+$uri =& $config->getDefinition('URI', true);
+$uri->registerFilter(new HTMLPurifier_URIFilter_<strong>NameOfFilter</strong>());
+</pre>
+
+<p>
+  Now, your filter will only be called when %URI.<strong>NameOfFilter</strong>
+  is set to true.
+</p>
+
+<h2>Examples</h2>
+
+<p>
+  Check the
+  <a href="http://htmlpurifier.org/svnroot/htmlpurifier/trunk/library/HTMLPurifier/URIFilter/">URIFilter</a>
+  directory for more implementation examples, and see <a href="http://htmlpurifier.org/svnroot/htmlpurifier/trunk/docs/proposal-new-directives.txt">the
+  new directives proposal document</a> for ideas on what could be implemented
+  as a filter.
+</p>
+
+<div id="version">$Id$</div>
+
+</body></html>

docs/enduser-youtube.html

@@ -15,6 +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://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
@@ -36,7 +37,7 @@ from a specific website, it probably is okay. If no amount of pleading will
 convince the people upstairs that they should just settle with just linking
 to their movies, you may find this technique very useful.</p>
 
-<h2>Sample</h2>
+<h2>Looking in</h2>
 
 <p>Below is custom code that allows users to embed
 YouTube videos. This is not favoritism: this trick can easily be adapted for
@@ -68,55 +69,27 @@ into your documents. YouTube's code goes like this:</p>
 <p>What point 2 means is that if we have code like <code>&lt;span
 class=&quot;embed-youtube&quot;&gt;AyPzM5WK8ys&lt;/span&gt;</code> your
 application can reconstruct the full object from this small snippet that
-passes through HTML Purifier <em>unharmed</em>.</p>
+passes through HTML Purifier <em>unharmed</em>.
+<a href="http://htmlpurifier.org/svnroot/htmlpurifier/trunk/library/HTMLPurifier/Filter/YouTube.php">Show me the code!</a></p>
 
-<pre>
-&lt;?php
+<p>And the corresponding usage:</p>
 
-class HTMLPurifierX_PreserveYouTube extends HTMLPurifier
-{
-    function purify($html, $config = null) {
-        $pre_regex = '#&lt;object[^&gt;]+&gt;.+?'.
-            'http://www.youtube.com/v/([A-Za-z0-9]+).+?&lt;/object&gt;#';
-        $pre_replace = '&lt;span class=&quot;youtube-embed&quot;&gt;\1&lt;/span&gt;';
-        $html = preg_replace($pre_regex, $pre_replace, $html);
-        $html = parent::purify($html, $config);
-        $post_regex = '#&lt;span class=&quot;youtube-embed&quot;&gt;([A-Za-z0-9]+)&lt;/span&gt;#';
-        $post_replace = '&lt;object width=&quot;425&quot; height=&quot;350&quot; '.
-            'data=&quot;http://www.youtube.com/v/\1&quot;&gt;'.
-            '&lt;param name=&quot;movie&quot; value=&quot;http://www.youtube.com/v/\1&quot;&gt;&lt;/param&gt;'.
-            '&lt;param name=&quot;wmode&quot; value=&quot;transparent&quot;&gt;&lt;/param&gt;'.
-            '&lt;!--[if IE]&gt;'.
-            '&lt;embed src=&quot;http://www.youtube.com/v/\1&quot;'.
-            'type=&quot;application/x-shockwave-flash&quot;'.
-            'wmode=&quot;transparent&quot; width=&quot;425&quot; height=&quot;350&quot; /&gt;'.
-            '&lt;![endif]--&gt;'.
-            '&lt;/object&gt;';
-        $html = preg_replace($post_regex, $post_replace, $html);
-        return $html;
-    }
-}
+<pre>&lt;?php
+    // assuming $purifier is an instance of HTMLPurifier
+    require_once 'HTMLPurifier/Filter/YouTube.php';
+    $purifier-&gt;addFilter(new HTMLPurifier_Filter_YouTube());
+?&gt;</pre>
 
-$purifier = new HTMLPurifierX_PreserveYouTube();
-$html_still_with_youtube = $purifier->purify($html_with_youtube);
-
-?&gt;
-</pre>
-
-<p>There is a bit going on here, so let's explain.</p>
+<p>There is a bit going in the two code snippets, so let's explain.</p>
 
 <ol>
-    <li>The class uses the prefix <code>HTMLPurifierX</code> because it's
-        userspace code. Don't use <code>HTMLPurifier</code> in front of your
-        class, since it might clobber another class in the library.</li>
-    <li>In order to keep the interface compatible, we've extended HTMLPurifier
-        into a new class that preserves the YouTube videos. This means that
-        all you have to do is replace all instances of
-        <code>new HTMLPurifier</code> to <code>new
-        HTMLPurifierX_PreserveYouTube</code>. There's other ways to go about
-        doing this: if you were calling a function that wrapped HTML Purifier,
-        you could paste the PHP right there. If you wanted to be really
-        fancy, you could make a decorator for HTMLPurifier.</li>
+    <li>This is a Filter object, which intercepts the HTML that is
+        coming into and out of the purifier. You can add as many
+        filter objects as you like. <code>preFilter()</code>
+        processes the code before it gets purified, and <code>postFilter()</code>
+        processes the code afterwards. So, we'll use <code>preFilter()</code> to
+        replace the object tag with a <code>span</code>, and <code>postFilter()</code>
+        to restore it.</li>
     <li>The first preg_replace call replaces any YouTube code users may have
         embedded into the benign span tag. Span is used because it is inline,
         and objects are inline too. We are very careful to be extremely
@@ -164,16 +137,16 @@ it is important that you are cognizant of the risk.</p>
 
 <p>This should go without saying, but if you're going to adapt this code
 for Google Video or the like, make sure you do it <em>right</em>. It's
-extremely easy to allow a character too many in the final section and
+extremely easy to allow a character too many in <code>postFilter()</code> and
 suddenly you're introducing XSS into HTML Purifier's XSS free output. HTML
 Purifier may be well written, but it cannot guard against vulnerabilities
 introduced after it has finished.</p>
 
-<h2>Future plans</h2>
+<h2>Help out!</h2>
 
-<p>It would probably be a good idea if this code was added to the core
-library. Look out for the inclusion of this into the core as a decorator
-or the like.</p>
+<p>If you write a filter for your favorite video destination (or anything
+like that, for that matter), send it over and it might get included
+with the core!</p>
 
 </body>
-</html>
+</html>

docs/examples/basic.php

@@ -2,14 +2,21 @@
 
 // This file demonstrates basic usage of HTMLPurifier.
 
-exit; // not to be called directly, it will fail fantastically!
+// replace this with the path to the HTML Purifier library
+require_once '../../library/HTMLPurifier.auto.php';
 
-set_include_path('/path/to/htmlpurifier/library' . PATH_SEPARATOR . get_include_path());
-require_once 'HTMLPurifier.php';
+$config = HTMLPurifier_Config::createDefault();
 
-$purifier = new HTMLPurifier();
+// configuration goes here:
+$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 '<pre>' . htmlspecialchars($pure_html) . '</pre>';
+

docs/examples/demo.php

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

docs/fixquotes.htc

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

docs/index.html

@@ -13,7 +13,7 @@
 
 <h1>Documentation</h1>
 
-<p><strong>HTML Purifier</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>
@@ -28,6 +28,21 @@ information for casual developers using HTML Purifier.</p>
 <dt><a href="enduser-youtube.html">Embedding YouTube videos</a></dt>
 <dd>Explains how to safely allow the embedding of flash from trusted sites.</dd>
 
+<dt><a href="enduser-slow.html">Speeding up HTML Purifier</a></dt>
+<dd>Explains how to speed up HTML Purifier through caching or inbound filtering.</dd>
+
+<dt><a href="enduser-utf8.html">UTF-8: 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>
+
+<dt><a href="enduser-uri-filter.html">URI Filters</a></dt>
+<dd>Tutorial for creating custom URI filters.</dd>
+
 </dl>
 
 <h2>Development</h2>
@@ -36,9 +51,6 @@ 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>
 
@@ -48,6 +60,10 @@ conventions.</p>
 <dt><a href="dev-optimization.html">Optimization</a></dt>
 <dd>Discusses possible methods of optimizing HTML Purifier.</dd>
 
+<dt><a href="dev-advanced-api.html">Advanced API</a></dt>
+<dd>Functional specification for HTML Purifier's advanced API for defining
+custom filtering behavior.</dd>
+
 </dl>
 
 <h2>Proposals</h2>
@@ -95,6 +111,12 @@ 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>
@@ -115,8 +137,8 @@ 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>
@@ -127,14 +149,8 @@ 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>
@@ -149,4 +165,4 @@ the code. They may be upgraded to HTML files or stay as TXT scratchpads.</p>
 
 <div id="version">$Id$</div>
 </body>
-</html>
+</html>

docs/proposal-colors.html

@@ -15,6 +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://htmlpurifier.org/">HTML Purifier</a> End-User Documentation</div>
 
 <p>Your website probably has a color-scheme.
 <span style="color:#090; background:#FFF;">Green on white</span>,

docs/proposal-config.txt

@@ -7,29 +7,15 @@ value is used for.  This means decentralized configuration declarations that
 are nevertheless error checking and a centralized configuration object.
 
 Directives are divided into namespaces, indicating the major portion of
-functionality they cover (although there may be overlaps.  Please consult
+functionality they cover (although there may be overlaps).  Please consult
 the documentation in ConfigDef for more information on these namespaces.
 
 Since configuration is dependant on context, internal classes require a
 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 is a special class
-of directives that influence the *construction* of the Definition object.
-A standard 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('HTMLDefinition')
-5. Config returns array of directives that later construction
-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.
+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

@@ -2,20 +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.
+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:
 
@@ -36,13 +32,17 @@ Here are some fuzzy levels you could set:
 
 One final note: when you start axing tags that are more commonly used, you
 run the risk of accidentally destroying user data, especially if the data
-is incoming from a WYSIWYG eidtor that hasn't been synced accordingly. This may
+is incoming from a WYSIWYG editor that hasn't been synced accordingly. This may
 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
@@ -111,6 +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.
@@ -123,6 +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/proposal-language.txt

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

docs/proposal-new-directives.txt

@@ -2,9 +2,8 @@
 Configuration Ideas
 
 Here are some theoretical configuration ideas that we could implement some
-time.  Note the naming convention: %Namespace.Directive
-
-%Attr.IDPrefix - prefix all ids with this
+time.  Note the naming convention: %Namespace.Directive. If you want one
+implemented, give us a ring, and we'll move it up the priority chain.
 
 %Attr.RewriteFragments - if there's %Attr.IDPrefix we may want to transparently
     rewrite the URLs we parse too.  However, we can only do it when it's a pure
@@ -24,8 +23,6 @@ time.  Note the naming convention: %Namespace.Directive
 %URI.AddRelNofollow - will add rel="nofollow" to all links, preventing the
     spread of ill-gotten pagerank
 
-%URI.RelativeToAbsolute - transforms all relative URIs to absolute form
-
 %URI.HostBlacklistRegex - regexes that if matching the host are disallowed
 %URI.HostWhitelist - domain names that are excluded from the host blacklist
 %URI.HostPolicy - determines whether or not its reject all and then whitelist

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-css-length.txt

@@ -0,0 +1,28 @@
+
+CSS Length Reference
+  To bound, or not to bound, that is the question
+
+It's quite a reasonable request, really, and it's already been implemented
+for HTML.  That is, length bounding.  It makes little sense to let users
+define text blocks that have a font-size of 63,360 inches (that's a mile,
+by the way) or a width of forty-fold the parent container.
+
+But it's a little more complicated then that. There are multiple units
+one can use, and we have to a little unit conversion to get things working.
+Here's what we have:
+
+Absolute:
+    1 in ~= 2.54 cm
+    1 cm = 10 mm
+    1 pt = 1/72 in
+    1 pc = 12 pt
+
+Relative:
+    1 em ~= 10.0667 px
+    1 ex ~= 0.5 em, though Mozilla Firefox says 1 ex = 6px
+    1 px ~= 1 pt
+
+Watch out: font-sizes can also be nested to get successively larger 
+(although I do not relish having to keep track of context font-sizes,
+this may be necessary, especially for some of the more advanced features
+for preventing things like white on white).

docs/ref-devnetwork.html

@@ -15,6 +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://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
@@ -41,4 +42,4 @@ the development of this library in these forum threads:</p>
 
 <div id="version">$Id$</div>
 </body>
-</html>
+</html>

docs/ref-html-modularization.txt

@@ -0,0 +1,164 @@
+
+The Modularization of HTMLDefinition in HTML Purifier
+
+Todo for XHTML 1.1 support <http://www.w3.org/TR/xhtml11/changes.html>
+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
+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). These modules
+are managed by HTMLModuleManager.
+
+Modules that we don't support but could support are:
+
+    * 5.6. Table Modules
+          o 5.6.1. Basic Tables Module [?]
+    * 5.8. Client-side Image Map Module [?]
+    * 5.9. Server-side Image Map Module [?]
+    * 5.12. Target Module [?]
+    * 5.21. Name Identification Module [deprecated]
+
+These modules would be implemented as "unsafe":
+
+    * 5.2. Core Modules
+          o 5.2.1. Structure Module
+    * 5.3. Applet Module
+    * 5.5. Forms Modules
+          o 5.5.1. Basic Forms Module
+          o 5.5.2. Forms Module
+    * 5.10. Object Module
+    * 5.11. Frames Module
+    * 5.13. Iframe Module
+    * 5.14. Intrinsic Events Module
+    * 5.15. Metainformation Module
+    * 5.16. Scripting Module
+    * 5.17. Style Sheet Module
+    * 5.19. Link Module
+    * 5.20. Base Module
+
+We will not be using W3C's XML Schemas or DTDs directly due to the lack
+of robust tools for handling them (the main problem is that all the
+current parsers are usually PHP 5 only and solely-validating, not
+correcting).
+
+This system may be generalized and ported over for CSS.
+
+== General Use-Case ==
+
+The outwards API of HTMLDefinition has been largely preserved, not
+only for backwards-compatibility but also by design. Instead,
+HTMLDefinition can be retrieved "raw", in which it loads a structure
+that closely resembles the modules of XHTML 1.1. This structure is very
+dynamic, making it easy to make cascading changes to global content
+sets or remove elements in bulk.
+
+However, once HTML Purifier needs the actual definition, it retrieves
+a finalized version of HTMLDefinition. The finalized definition involves
+processing the modules into a form that it is optimized for multiple
+calls. This final version is immutable and, even if editable, would
+be extremely hard to change.
+
+So, some code taking advantage of the XHTML modularization may look
+like this:
+
+<?php
+    $config = HTMLPurifier_Config::createDefault();
+    $def =& $config->getHTMLDefinition(true); // reference to raw
+    $def->addElement('marquee', 'Block', 'Flow', 'Common');
+    $purifier = new HTMLPurifier($config);
+    $purifier->purify($html); // now the definition is finalized
+?>
+
+== Inclusions ==
+
+One of the nice features of HTMLDefinition is that piggy-backing off
+of global attribute and content sets is extremely easy to do.
+
+=== Attributes ===
+
+HTMLModule->elements[$element]->attr stores attribute information for the
+specific attributes of $element. This is quite close to the final
+API that HTML Purifier interfaces with, but there's an important
+extra feature: attr may also contain a array with a member index zero.
+
+<?php
+    HTMLModule->elements[$element]->attr[0] = array('AttrSet');
+?>
+
+Rather than map the attribute key 0 to an array (which should be
+an AttrDef), it defines a number of attribute collections that should
+be merged into this elements attribute array.
+
+Furthermore, the value of an attribute key, attribute value pair need
+not be a fully fledged AttrDef object. They can also be a string, which
+signifies a AttrDef that is looked up from a centralized registry
+AttrTypes. This allows more concise attribute definitions that look
+more like W3C's declarations, as well as offering a centralized point
+for modifying the behavior of one attribute type. And, of course, the
+old method of manually instantiating an AttrDef still works.
+
+=== Attribute Collections ===
+
+Attribute collections are stored and processed in the AttrCollections
+object, which is responsible for performing the inclusions signified
+by the 0 index. These attribute collections, too, are mutable, by
+using HTMLModule->attr_collections. You may add new attributes
+to a collection or define an entirely new collection for your module's
+use. Inclusions can also be cumulative.
+
+Attribute collections allow us to get rid of so called "global attributes"
+(which actually aren't so global).
+
+=== Content Models and ChildDef ===
+
+An implementation of the above-mentioned attributes and attribute
+collections was applied to the ChildDef system. HTML Purifier uses
+a proprietary system called ChildDef for performance and flexibility
+reasons, but this does not line up very well with W3C's notion of
+regexps for defining the allowed children of an element.
+
+HTMLPurifier->elements[$element]->content_model and 
+HTMLPurifier->elements[$element]->content_model_type store information
+about the final ChildDef that will be stored in
+HTMLPurifier->elements[$element]->child (we use a different variable
+because the two forms are sufficiently different).
+
+$content_model is an abstract, string representation of the internal
+state of ChildDef, while $content_model_type is a string identifier
+of which ChildDef subclass to instantiate. $content_model is processed
+by substituting all content set identifiers (capitalized element names)
+with their contents. It is then parsed and passed into the appropriate
+ChildDef class, as defined by the ContentSets->getChildDef() or the
+custom fallback HTMLModule->getChildDef() for custom child definitions
+not in the core.
+
+You'll need to use these facilities if you plan on referencing a content
+set like "Inline" or "Block", and using them is recommended even if you're
+not due to their conciseness.
+
+A few notes on $content_model: it's structure can be as complicated
+as you want, but the pipe symbol (|) is reserved for defining possible
+choices, due to the content sets implementation. For example, a content
+model that looks like:
+
+"Inline -> Block -> a"
+
+...when the Inline content set is defined as "span | b" and the Block
+content set is defined as "div | blockquote", will expand into:
+
+"span | b -> div | blockquote -> a"
+
+The custom HTMLModule->getChildDef() function will need to be able to
+then feed this information to ChildDef in a usable manner.
+
+=== Content Sets ===
+
+Content sets can be altered using HTMLModule->content_sets, an associative
+array of content set names to content set contents. If the content set
+already exists, your values are appended on to it (great for, say,
+registering the font tag as an inline element), otherwise it is
+created. They are substituted into content_model.

docs/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 (currently not allowed at all)
-[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

@@ -1,36 +0,0 @@
-
-Is HTML Purifier Strict or Transitional?
-    A little bit of helpful guidance
-
-Despite the fact that HTML Purifier professes only to support transitional
-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. HTML Purifier does not currently support them, but
-it might behoove us to do so while our output is still 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.
-

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/ref-xhtml-1.1.txt

@@ -1,21 +0,0 @@
-
-Getting XHTML 1.1 Working
-
-It's quite simple, according to <http://www.w3.org/TR/xhtml11/changes.html>
-
-1. Scratch lang entirely in favor of xml:lang
-2. Scratch name entirely in favor of id (partially-done)
-3. Support Ruby <http://www.w3.org/TR/2001/REC-ruby-20010531/>
-
-...but that's only an informative section. More things to do:
-
-1. Scratch style attribute (it's deprecated)
-2. Be module-aware (this might entail intelligent grouping in the definition
-   and allowing users to specifically remove certain modules (see 5))
-3. Cross-reference minimal content models with existing DTDs and determine
-   changes (todo)
-4. Watch out for the Legacy Module
-<http://www.w3.org/TR/2001/REC-xhtml-modularization-20010410/abstract_modules.html#s_legacymodule>
-5. Let users specify their own custom modules
-6. Study Modularization document
-<http://www.w3.org/TR/2001/REC-xhtml-modularization-20010410/>

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

@@ -23,6 +23,9 @@ h4 {font-family:sans-serif; font-size:0.9em; font-weight:bold; }
 
 /* Marks off asides, discussions on why something is the way it is */
 .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; }
@@ -30,11 +33,42 @@ h4 {font-family:sans-serif; font-size:0.9em; font-weight:bold; }
 .table thead th:first-child {-moz-border-radius-topleft:1em;}
 .table tbody td {border-bottom:1px solid #CCC; padding-right:0.6em;padding-left:0.6em;}
 
+/* A quick table*/
+table.quick tbody th {text-align:right; padding-right:1em;}
+
 /* Category of the file */
 #filing {font-weight:bold; font-size:smaller; }
 
 /* Contains, without exception, Return to index. */
 #index {font-size:smaller; }
 
+#home {font-size:smaller;}
+
 /* Contains, without exception, $Id$, for SVN version info. */
-#version {text-align:right; font-style:italic; margin:2em 0;}
+#version {text-align:right; font-style:italic; margin:2em 0;}
+
+#toc ol ol {list-style-type:lower-roman;}
+#toc ol {list-style-type:decimal;}
+#toc {list-style-type:upper-alpha;}
+
+q {
+  behavior: url(fixquotes.htc); /* IE fix */
+  quotes: '\201C' '\201D' '\2018' '\2019';
+}
+q:before {
+  content: open-quote;
+}
+q:after {
+  content: close-quote;
+}
+
+/* Marks off implementation details interesting only to the person writing
+   the class described in the spec. */
+.technical {margin-left:2em; }
+.technical:before {content:"Technical note: "; font-weight:bold; color:#061; }
+
+/* Marks off sections that are lacking. */
+.fixme {margin-left:2em; }
+.fixme:before {content:"Fix me: "; font-weight:bold; color:#C00; }
+
+#applicability {margin: 1em 5%; font-style:italic;}

library/HTMLPurifier.auto.php

@@ -7,4 +7,3 @@
 set_include_path(dirname(__FILE__) . PATH_SEPARATOR . get_include_path() );
 require_once 'HTMLPurifier.php';
 
-?>

library/HTMLPurifier.func.php

@@ -6,16 +6,15 @@
  *       this is efficient for instances when you only use HTML Purifier
  *       on a few of your pages, it murders bytecode caching. You still
  *       need to add HTML Purifier to your path.
+ * @note ''HTMLPurifier()'' is NOT the same as ''new HTMLPurifier()''
  */
 
 function HTMLPurifier($html, $config = null) {
     static $purifier = false;
     if (!$purifier) {
-        $init = true;
         require_once 'HTMLPurifier.php';
         $purifier = new HTMLPurifier();
     }
     return $purifier->purify($html, $config);
 }
 
-?>

library/HTMLPurifier.php

@@ -22,7 +22,7 @@
  */
 
 /*
-    HTML Purifier 1.3.2 - Standards Compliant HTML Filtering
+    HTML Purifier 2.1.2 - Standards Compliant HTML Filtering
     Copyright (C) 2006 Edward Z. Yang
 
     This library is free software; you can redistribute it and/or
@@ -40,9 +40,12 @@
     Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301  USA
  */
 
+// constants are slow, but we'll make one exception
+define('HTMLPURIFIER_PREFIX', dirname(__FILE__));
+
 // 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 +54,16 @@ require_once 'HTMLPurifier/Generator.php';
 require_once 'HTMLPurifier/Strategy/Core.php';
 require_once 'HTMLPurifier/Encoder.php';
 
+require_once 'HTMLPurifier/ErrorCollector.php';
+require_once 'HTMLPurifier/LanguageFactory.php';
+
+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.
  * 
@@ -64,11 +77,12 @@ require_once 'HTMLPurifier/Encoder.php';
 class HTMLPurifier
 {
     
-    var $version = '1.3.2';
+    var $version = '2.1.2';
     
     var $config;
+    var $filters;
     
-    var $lexer, $strategy, $generator;
+    var $strategy, $generator;
     
     /**
      * Final HTMLPurifier_Context of last run purification. Might be an array.
@@ -88,13 +102,19 @@ class HTMLPurifier
         
         $this->config = HTMLPurifier_Config::create($config);
         
-        $this->lexer        = HTMLPurifier_Lexer::create();
         $this->strategy     = new HTMLPurifier_Strategy_Core();
         $this->generator    = new HTMLPurifier_Generator();
-        $this->encoder      = new HTMLPurifier_Encoder();
         
     }
     
+    /**
+     * Adds a filter to process the output. First come first serve
+     * @param $filter HTMLPurifier_Filter object
+     */
+    function addFilter($filter) {
+        $this->filters[] = $filter;
+    }
+    
     /**
      * Filters an HTML snippet/document to be XSS-free and standards-compliant.
      * 
@@ -109,8 +129,32 @@ class HTMLPurifier
         
         $config = $config ? HTMLPurifier_Config::create($config) : $this->config;
         
-        $context =& new HTMLPurifier_Context();
-        $html = $this->encoder->convertToUTF8($html, $config, $context);
+        // implementation is partially environment dependant, partially
+        // configuration dependant
+        $lexer = HTMLPurifier_Lexer::create($config);
+        
+        $context = new HTMLPurifier_Context();
+        
+        // our friendly neighborhood generator, all primed with configuration too!
+        $this->generator->generateFromTokens(array(), $config, $context);
+        $context->register('Generator', $this->generator);
+        
+        // set up global context variables
+        if ($config->get('Core', 'CollectErrors')) {
+            // may get moved out if other facilities use it
+            $language_factory = HTMLPurifier_LanguageFactory::instance();
+            $language = $language_factory->create($config, $context);
+            $context->register('Locale', $language);
+            
+            $error_collector = new HTMLPurifier_ErrorCollector($context);
+            $context->register('ErrorCollector', $error_collector);
+        }
+        
+        $html = HTMLPurifier_Encoder::convertToUTF8($html, $config, $context);
+        
+        for ($i = 0, $size = count($this->filters); $i < $size; $i++) {
+            $html = $this->filters[$i]->preFilter($html, $config, $context);
+        }
         
         // purified HTML
         $html = 
@@ -118,7 +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
                     ),
@@ -127,7 +171,11 @@ class HTMLPurifier
                 $config, $context
             );
         
-        $html = $this->encoder->convertFromUTF8($html, $config, $context);
+        for ($i = $size - 1; $i >= 0; $i--) {
+            $html = $this->filters[$i]->postFilter($html, $config, $context);
+        }
+        
+        $html = HTMLPurifier_Encoder::convertFromUTF8($html, $config, $context);
         $this->context =& $context;
         return $html;
     }
@@ -148,7 +196,23 @@ class HTMLPurifier
         return $array_of_html;
     }
     
+    /**
+     * Singleton for enforcing just one HTML Purifier in your system
+     */
+    static function &getInstance($prototype = null) {
+        static $htmlpurifier;
+        if (!$htmlpurifier || $prototype) {
+            if ($prototype instanceof HTMLPurifier) {
+                $htmlpurifier = $prototype;
+            } elseif ($prototype) {
+                $htmlpurifier = new HTMLPurifier($prototype);
+            } else {
+                $htmlpurifier = new HTMLPurifier();
+            }
+        }
+        return $htmlpurifier;
+    }
+    
     
 }
 
-?>

library/HTMLPurifier/AttrCollections.php

@@ -0,0 +1,129 @@
+<?php
+
+require_once 'HTMLPurifier/AttrTypes.php';
+
+/**
+ * Defines common attribute collections that modules reference
+ */
+
+class HTMLPurifier_AttrCollections
+{
+    
+    /**
+     * Associative array of attribute collections, indexed by name
+     */
+    var $info = array();
+    
+    /**
+     * Performs all expansions on internal data for use by other inclusions
+     * It also collects all attribute collection extensions from
+     * modules
+     * @param $attr_types HTMLPurifier_AttrTypes instance
+     * @param $modules Hash array of HTMLPurifier_HTMLModule members
+     */
+    function HTMLPurifier_AttrCollections($attr_types, $modules) {
+        // load extensions from the modules
+        foreach ($modules as $module) {
+            foreach ($module->attr_collections as $coll_i => $coll) {
+                if (!isset($this->info[$coll_i])) {
+                    $this->info[$coll_i] = array();
+                }
+                foreach ($coll as $attr_i => $attr) {
+                    if ($attr_i === 0 && isset($this->info[$coll_i][$attr_i])) {
+                        // merge in includes
+                        $this->info[$coll_i][$attr_i] = array_merge(
+                            $this->info[$coll_i][$attr_i], $attr);
+                        continue;
+                    }
+                    $this->info[$coll_i][$attr_i] = $attr;
+                }
+            }
+        }
+        // perform internal expansions and inclusions
+        foreach ($this->info as $name => $attr) {
+            // merge attribute collections that include others
+            $this->performInclusions($this->info[$name]);
+            // replace string identifiers with actual attribute objects
+            $this->expandIdentifiers($this->info[$name], $attr_types);
+        }
+    }
+    
+    /**
+     * Takes a reference to an attribute associative array and performs
+     * all inclusions specified by the zero index.
+     * @param &$attr Reference to attribute array
+     */
+    function performInclusions(&$attr) {
+        if (!isset($attr[0])) return;
+        $merge = $attr[0];
+        $seen  = array(); // recursion guard
+        // loop through all the inclusions
+        for ($i = 0; isset($merge[$i]); $i++) {
+            if (isset($seen[$merge[$i]])) continue;
+            $seen[$merge[$i]] = true;
+            // foreach attribute of the inclusion, copy it over
+            if (!isset($this->info[$merge[$i]])) continue;
+            foreach ($this->info[$merge[$i]] as $key => $value) {
+                if (isset($attr[$key])) continue; // also catches more inclusions
+                $attr[$key] = $value;
+            }
+            if (isset($this->info[$merge[$i]][0])) {
+                // recursion
+                $merge = array_merge($merge, $this->info[$merge[$i]][0]);
+            }
+        }
+        unset($attr[0]);
+    }
+    
+    /**
+     * Expands all string identifiers in an attribute array by replacing
+     * them with the appropriate values inside HTMLPurifier_AttrTypes
+     * @param &$attr Reference to attribute array
+     * @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 (isset($processed[$def_i])) continue;
+            
+            // determine whether or not attribute is required
+            if ($required = (strpos($def_i, '*') !== false)) {
+                // rename the definition
+                unset($attr[$def_i]);
+                $def_i = trim($def_i, '*');
+                $attr[$def_i] = $def;
+            }
+            
+            $processed[$def_i] = true;
+            
+            // if we've already got a literal object, move on
+            if (is_object($def)) {
+                // preserve previous required
+                $attr[$def_i]->required = ($required || $attr[$def_i]->required);
+                continue;
+            }
+            
+            if ($def === false) {
+                unset($attr[$def_i]);
+                continue;
+            }
+            
+            if ($t = $attr_types->get($def)) {
+                $attr[$def_i] = $t;
+                $attr[$def_i]->required = $required;
+            } else {
+                unset($attr[$def_i]);
+            }
+        }
+        
+    }
+    
+}
+

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 +68,19 @@ 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.php

@@ -8,6 +8,11 @@ require_once 'HTMLPurifier/CSSDefinition.php';
  * @note We don't implement the whole CSS specification, so it might be
  *       difficult to reuse this component in the context of validating
  *       actual stylesheet declarations.
+ * @note If we were really serious about validating the CSS, we would
+ *       tokenize the styles and then parse the tokens. Obviously, we
+ *       are not doing that. Doing that could seriously harm performance,
+ *       but would make these components a lot more viable for a CSS
+ *       filtering solution.
  */
 class HTMLPurifier_AttrDef_CSS extends HTMLPurifier_AttrDef
 {
@@ -20,6 +25,9 @@ class HTMLPurifier_AttrDef_CSS extends HTMLPurifier_AttrDef
         
         // we're going to break the spec and explode by semicolons.
         // This is because semicolon rarely appears in escaped form
+        // Doing this is generally flaky but fast
+        // IT MIGHT APPEAR IN URIs, see HTMLPurifier_AttrDef_CSSURI
+        // for details
         
         $declarations = explode(';', $css);
         $propvalues = array();
@@ -58,4 +66,3 @@ class HTMLPurifier_AttrDef_CSS extends HTMLPurifier_AttrDef
     
 }
 
-?>

library/HTMLPurifier/AttrDef/CSS/Background.php

@@ -0,0 +1,86 @@
+<?php
+
+require_once 'HTMLPurifier/AttrDef.php';
+require_once 'HTMLPurifier/CSSDefinition.php';
+
+/**
+ * Validates shorthand CSS property background.
+ * @warning Does not support url tokens that have internal spaces.
+ */
+class HTMLPurifier_AttrDef_CSS_Background extends HTMLPurifier_AttrDef
+{
+    
+    /**
+     * Local copy of component validators.
+     * @note See HTMLPurifier_AttrDef_Font::$info for a similar impl.
+     */
+    var $info;
+    
+    function HTMLPurifier_AttrDef_CSS_Background($config) {
+        $def = $config->getCSSDefinition();
+        $this->info['background-color'] = $def->info['background-color'];
+        $this->info['background-image'] = $def->info['background-image'];
+        $this->info['background-repeat'] = $def->info['background-repeat'];
+        $this->info['background-attachment'] = $def->info['background-attachment'];
+        $this->info['background-position'] = $def->info['background-position'];
+    }
+    
+    function validate($string, $config, &$context) {
+        
+        // regular pre-processing
+        $string = $this->parseCDATA($string);
+        if ($string === '') return false;
+        
+        // assumes URI doesn't have spaces in it
+        $bits = explode(' ', strtolower($string)); // bits to process
+        
+        $caught = array();
+        $caught['color']    = false;
+        $caught['image']    = false;
+        $caught['repeat']   = false;
+        $caught['attachment'] = false;
+        $caught['position'] = false;
+        
+        $i = 0; // number of catches
+        $none = false;
+        
+        foreach ($bits as $bit) {
+            if ($bit === '') continue;
+            foreach ($caught as $key => $status) {
+                if ($key != 'position') {
+                    if ($status !== false) continue;
+                    $r = $this->info['background-' . $key]->validate($bit, $config, $context);
+                } else {
+                    $r = $bit;
+                }
+                if ($r === false) continue;
+                if ($key == 'position') {
+                    if ($caught[$key] === false) $caught[$key] = '';
+                    $caught[$key] .= $r . ' ';
+                } else {
+                    $caught[$key] = $r;
+                }
+                $i++;
+                break;
+            }
+        }
+        
+        if (!$i) return false;
+        if ($caught['position'] !== false) {
+            $caught['position'] = $this->info['background-position']->
+                validate($caught['position'], $config, $context);
+        }
+        
+        $ret = array();
+        foreach ($caught as $value) {
+            if ($value === false) continue;
+            $ret[] = $value;
+        }
+        
+        if (empty($ret)) return false;
+        return implode(' ', $ret);
+        
+    }
+    
+}
+

library/HTMLPurifier/AttrDef/CSS/BackgroundPosition.php

@@ -0,0 +1,129 @@
+<?php
+
+require_once 'HTMLPurifier/AttrDef.php';
+require_once 'HTMLPurifier/AttrDef/CSS/Length.php';
+require_once 'HTMLPurifier/AttrDef/CSS/Percentage.php';
+
+/* W3C says:
+    [ // adjective and number must be in correct order, even if
+      // you could switch them without introducing ambiguity.
+      // some browsers support that syntax
+        [
+            <percentage> | <length> | left | center | right
+        ]
+        [ 
+            <percentage> | <length> | top | center | bottom
+        ]?
+    ] |
+    [ // this signifies that the vertical and horizontal adjectives
+      // can be arbitrarily ordered, however, there can only be two,
+      // one of each, or none at all
+        [
+            left | center | right
+        ] ||
+        [
+            top | center | bottom
+        ]
+    ]
+    top, left = 0%
+    center, (none) = 50%
+    bottom, right = 100%
+*/
+
+/* QuirksMode says:
+    keyword + length/percentage must be ordered correctly, as per W3C
+    
+    Internet Explorer and Opera, however, support arbitrary ordering. We
+    should fix it up.
+    
+    Minor issue though, not strictly necessary.
+*/
+
+// control freaks may appreciate the ability to convert these to
+// percentages or something, but it's not necessary
+
+/**
+ * Validates the value of background-position.
+ */
+class HTMLPurifier_AttrDef_CSS_BackgroundPosition extends HTMLPurifier_AttrDef
+{
+    
+    var $length;
+    var $percentage;
+    
+    function HTMLPurifier_AttrDef_CSS_BackgroundPosition() {
+        $this->length     = new HTMLPurifier_AttrDef_CSS_Length();
+        $this->percentage = new HTMLPurifier_AttrDef_CSS_Percentage();
+    }
+    
+    function validate($string, $config, &$context) {
+        $string = $this->parseCDATA($string);
+        $bits = explode(' ', $string);
+        
+        $keywords = array();
+        $keywords['h'] = false; // left, right
+        $keywords['v'] = false; // top, bottom
+        $keywords['c'] = false; // center
+        $measures = array();
+        
+        $i = 0;
+        
+        $lookup = array(
+            'top' => 'v',
+            'bottom' => 'v',
+            'left' => 'h',
+            'right' => 'h',
+            'center' => 'c'
+        );
+        
+        foreach ($bits as $bit) {
+            if ($bit === '') continue;
+            
+            // test for keyword
+            $lbit = ctype_lower($bit) ? $bit : strtolower($bit);
+            if (isset($lookup[$lbit])) {
+                $status = $lookup[$lbit];
+                $keywords[$status] = $lbit;
+                $i++;
+            }
+            
+            // test for length
+            $r = $this->length->validate($bit, $config, $context);
+            if ($r !== false) {
+                $measures[] = $r;
+                $i++;
+            }
+            
+            // test for percentage
+            $r = $this->percentage->validate($bit, $config, $context);
+            if ($r !== false) {
+                $measures[] = $r;
+                $i++;
+            }
+            
+        }
+        
+        if (!$i) return false; // no valid values were caught
+        
+        
+        $ret = array();
+        
+        // first keyword
+        if     ($keywords['h'])     $ret[] = $keywords['h'];
+        elseif (count($measures))   $ret[] = array_shift($measures);
+        elseif ($keywords['c']) {
+            $ret[] = $keywords['c'];
+            $keywords['c'] = false; // prevent re-use: center = center center
+        }
+        
+        if     ($keywords['v'])     $ret[] = $keywords['v'];
+        elseif (count($measures))   $ret[] = array_shift($measures);
+        elseif ($keywords['c'])     $ret[] = $keywords['c'];
+        
+        if (empty($ret)) return false;
+        return implode(' ', $ret);
+        
+    }
+    
+}
+

library/HTMLPurifier/AttrDef/CSS/Border.php

@@ -5,7 +5,7 @@ require_once 'HTMLPurifier/AttrDef.php';
 /**
  * Validates the border property as defined by CSS.
  */
-class HTMLPurifier_AttrDef_Border extends HTMLPurifier_AttrDef
+class HTMLPurifier_AttrDef_CSS_Border extends HTMLPurifier_AttrDef
 {
     
     /**
@@ -13,7 +13,7 @@ class HTMLPurifier_AttrDef_Border extends HTMLPurifier_AttrDef
      */
     var $info = array();
     
-    function HTMLPurifier_AttrDef_Border($config) {
+    function HTMLPurifier_AttrDef_CSS_Border($config) {
         $def = $config->getCSSDefinition();
         $this->info['border-width'] = $def->info['border-width'];
         $this->info['border-style'] = $def->info['border-style'];
@@ -42,4 +42,3 @@ class HTMLPurifier_AttrDef_Border extends HTMLPurifier_AttrDef
     
 }
 
-?>

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_Color extends HTMLPurifier_AttrDef
+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
@@ -94,4 +98,3 @@ class HTMLPurifier_AttrDef_Color extends HTMLPurifier_AttrDef
     
 }
 
-?>

library/HTMLPurifier/AttrDef/CSS/Composite.php

@@ -9,7 +9,7 @@
  * especially useful for CSS values, which often are a choice between
  * an enumerated set of predefined values or a flexible data type.
  */
-class HTMLPurifier_AttrDef_Composite extends HTMLPurifier_AttrDef
+class HTMLPurifier_AttrDef_CSS_Composite extends HTMLPurifier_AttrDef
 {
     
     /**
@@ -21,7 +21,7 @@ class HTMLPurifier_AttrDef_Composite extends HTMLPurifier_AttrDef
     /**
      * @param $defs List of HTMLPurifier_AttrDef objects
      */
-    function HTMLPurifier_AttrDef_Composite($defs) {
+    function HTMLPurifier_AttrDef_CSS_Composite($defs) {
         $this->defs = $defs;
     }
     
@@ -35,4 +35,3 @@ class HTMLPurifier_AttrDef_Composite extends HTMLPurifier_AttrDef
     
 }
 
-?>

library/HTMLPurifier/AttrDef/CSS/Font.php

@@ -5,7 +5,7 @@ require_once 'HTMLPurifier/AttrDef.php';
 /**
  * Validates shorthand CSS property font.
  */
-class HTMLPurifier_AttrDef_Font extends HTMLPurifier_AttrDef
+class HTMLPurifier_AttrDef_CSS_Font extends HTMLPurifier_AttrDef
 {
     
     /**
@@ -18,19 +18,7 @@ class HTMLPurifier_AttrDef_Font extends HTMLPurifier_AttrDef
      */
     var $info = array();
     
-    /**
-     * System font keywords.
-     */
-    var $system_fonts = array(
-        'caption' => true,
-        'icon' => true,
-        'menu' => true,
-        'message-box' => true,
-        'small-caption' => true,
-        'status-bar' => true
-    );
-    
-    function HTMLPurifier_AttrDef_Font($config) {
+    function HTMLPurifier_AttrDef_CSS_Font($config) {
         $def = $config->getCSSDefinition();
         $this->info['font-style']   = $def->info['font-style'];
         $this->info['font-variant'] = $def->info['font-variant'];
@@ -42,13 +30,22 @@ class HTMLPurifier_AttrDef_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;
         }
         
@@ -151,4 +148,3 @@ class HTMLPurifier_AttrDef_Font extends HTMLPurifier_AttrDef
     
 }
 
-?>

library/HTMLPurifier/AttrDef/CSS/FontFamily.php

@@ -7,22 +7,18 @@ require_once 'HTMLPurifier/AttrDef.php';
 /**
  * Validates a font family list according to CSS spec
  */
-class HTMLPurifier_AttrDef_FontFamily extends HTMLPurifier_AttrDef
+class HTMLPurifier_AttrDef_CSS_FontFamily extends HTMLPurifier_AttrDef
 {
     
-    /**
-     * 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_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;
             }
@@ -42,19 +38,24 @@ class HTMLPurifier_AttrDef_FontFamily extends HTMLPurifier_AttrDef
                 $quote = $font[0];
                 if ($font[$length - 1] !== $quote) continue;
                 $font = substr($font, 1, $length - 2);
+                // double-backslash processing is buggy
+                $font = str_replace("\\$quote", $quote, $font); // de-escape quote
+                $font = str_replace("\\\n", "\n", $font);       // de-escape newlines
             }
-            // process font
+            // $font is a pure representation of the font name
+            
             if (ctype_alnum($font)) {
                 // very simple font, allow it in unharmed
                 $final .= $font . ', ';
                 continue;
             }
-            $nospace = str_replace(array(' ', '.', '!'), '', $font);
-            if (ctype_alnum($nospace)) {
-                // font with spaces in it
-                $final .= "'$font', ";
-                continue;
-            }
+            
+            // complicated font, requires quoting
+            
+            // armor single quotes and new lines
+            $font = str_replace("'", "\\'", $font);
+            $font = str_replace("\n", "\\\n", $font);
+            $final .= "'$font', ";
         }
         $final = rtrim($final, ', ');
         if ($final === '') return false;
@@ -63,4 +64,3 @@ class HTMLPurifier_AttrDef_FontFamily extends HTMLPurifier_AttrDef
     
 }
 
-?>

library/HTMLPurifier/AttrDef/CSS/Length.php

@@ -1,13 +1,12 @@
 <?php
 
 require_once 'HTMLPurifier/AttrDef.php';
-require_once 'HTMLPurifier/AttrDef/Number.php';
+require_once 'HTMLPurifier/AttrDef/CSS/Number.php';
 
 /**
  * Represents a Length as defined by CSS.
- * @warning Be sure not to confuse this with HTMLPurifier_AttrDef_Length!
  */
-class HTMLPurifier_AttrDef_CSSLength extends HTMLPurifier_AttrDef
+class HTMLPurifier_AttrDef_CSS_Length extends HTMLPurifier_AttrDef
 {
     
     /**
@@ -26,8 +25,8 @@ class HTMLPurifier_AttrDef_CSSLength extends HTMLPurifier_AttrDef
      * @param $non_negative Bool indication whether or not negative values are
      *                      allowed.
      */
-    function HTMLPurifier_AttrDef_CSSLength($non_negative = false) {
-        $this->number_def = new HTMLPurifier_AttrDef_Number($non_negative);
+    function HTMLPurifier_AttrDef_CSS_Length($non_negative = false) {
+        $this->number_def = new HTMLPurifier_AttrDef_CSS_Number($non_negative);
     }
     
     function validate($length, $config, &$context) {
@@ -40,6 +39,7 @@ class HTMLPurifier_AttrDef_CSSLength extends HTMLPurifier_AttrDef
         
         // we assume all units are two characters
         $unit = substr($length, $strlen - 2);
+        if (!ctype_lower($unit)) $unit = strtolower($unit);
         $number = substr($length, 0, $strlen - 2);
         
         if (!isset($this->units[$unit])) return false;
@@ -53,4 +53,3 @@ class HTMLPurifier_AttrDef_CSSLength extends HTMLPurifier_AttrDef
     
 }
 
-?>

library/HTMLPurifier/AttrDef/CSS/ListStyle.php

@@ -0,0 +1,79 @@
+<?php
+
+require_once 'HTMLPurifier/AttrDef.php';
+
+/**
+ * Validates shorthand CSS property list-style.
+ * @warning Does not support url tokens that have internal spaces.
+ */
+class HTMLPurifier_AttrDef_CSS_ListStyle extends HTMLPurifier_AttrDef
+{
+    
+    /**
+     * Local copy of component validators.
+     * @note See HTMLPurifier_AttrDef_CSS_Font::$info for a similar impl.
+     */
+    var $info;
+    
+    function HTMLPurifier_AttrDef_CSS_ListStyle($config) {
+        $def = $config->getCSSDefinition();
+        $this->info['list-style-type']     = $def->info['list-style-type'];
+        $this->info['list-style-position'] = $def->info['list-style-position'];
+        $this->info['list-style-image'] = $def->info['list-style-image'];
+    }
+    
+    function validate($string, $config, &$context) {
+        
+        // regular pre-processing
+        $string = $this->parseCDATA($string);
+        if ($string === '') return false;
+        
+        // assumes URI doesn't have spaces in it
+        $bits = explode(' ', strtolower($string)); // bits to process
+        
+        $caught = array();
+        $caught['type']     = false;
+        $caught['position'] = false;
+        $caught['image']    = false;
+        
+        $i = 0; // number of catches
+        $none = false;
+        
+        foreach ($bits as $bit) {
+            if ($i >= 3) return; // optimization bit
+            if ($bit === '') continue;
+            foreach ($caught as $key => $status) {
+                if ($status !== false) continue;
+                $r = $this->info['list-style-' . $key]->validate($bit, $config, $context);
+                if ($r === false) continue;
+                if ($r === 'none') {
+                    if ($none) continue;
+                    else $none = true;
+                    if ($key == 'image') continue;
+                }
+                $caught[$key] = $r;
+                $i++;
+                break;
+            }
+        }
+        
+        if (!$i) return false;
+        
+        $ret = array();
+        
+        // construct type
+        if ($caught['type']) $ret[] = $caught['type'];
+        
+        // construct image
+        if ($caught['image']) $ret[] = $caught['image'];
+        
+        // construct position
+        if ($caught['position']) $ret[] = $caught['position'];
+        
+        if (empty($ret)) return false;
+        return implode(' ', $ret);
+        
+    }
+    
+}
+

library/HTMLPurifier/AttrDef/CSS/Multiple.php

@@ -13,7 +13,7 @@ require_once 'HTMLPurifier/AttrDef.php';
  *       can only be used alone: it will never manifest as part of a multi
  *       shorthand declaration.  Thus, this class does not allow inherit.
  */
-class HTMLPurifier_AttrDef_Multiple extends HTMLPurifier_AttrDef
+class HTMLPurifier_AttrDef_CSS_Multiple extends HTMLPurifier_AttrDef
 {
     
     /**
@@ -30,7 +30,7 @@ class HTMLPurifier_AttrDef_Multiple extends HTMLPurifier_AttrDef
      * @param $single HTMLPurifier_AttrDef to multiply
      * @param $max Max number of values allowed (usually four)
      */
-    function HTMLPurifier_AttrDef_Multiple($single, $max = 4) {
+    function HTMLPurifier_AttrDef_CSS_Multiple($single, $max = 4) {
         $this->single = $single;
         $this->max = $max;
     }
@@ -55,4 +55,3 @@ class HTMLPurifier_AttrDef_Multiple extends HTMLPurifier_AttrDef
     
 }
 
-?>

library/HTMLPurifier/AttrDef/CSS/Number.php

@@ -3,7 +3,7 @@
 /**
  * Validates a number as defined by the CSS spec.
  */
-class HTMLPurifier_AttrDef_Number extends HTMLPurifier_AttrDef
+class HTMLPurifier_AttrDef_CSS_Number extends HTMLPurifier_AttrDef
 {
     
     /**
@@ -14,7 +14,7 @@ class HTMLPurifier_AttrDef_Number extends HTMLPurifier_AttrDef
     /**
      * @param $non_negative Bool indicating whether negatives are forbidden
      */
-    function HTMLPurifier_AttrDef_Number($non_negative = false) {
+    function HTMLPurifier_AttrDef_CSS_Number($non_negative = false) {
         $this->non_negative = $non_negative;
     }
     
@@ -58,4 +58,3 @@ class HTMLPurifier_AttrDef_Number extends HTMLPurifier_AttrDef
     
 }
 
-?>

library/HTMLPurifier/AttrDef/CSS/Percentage.php

@@ -1,25 +1,24 @@
 <?php
 
 require_once 'HTMLPurifier/AttrDef.php';
-require_once 'HTMLPurifier/AttrDef/Number.php';
+require_once 'HTMLPurifier/AttrDef/CSS/Number.php';
 
 /**
- * Validates a Percentage as defined by the HTML spec.
- * @note This also allows integer pixel values.
+ * Validates a Percentage as defined by the CSS spec.
  */
-class HTMLPurifier_AttrDef_Percentage extends HTMLPurifier_AttrDef
+class HTMLPurifier_AttrDef_CSS_Percentage extends HTMLPurifier_AttrDef
 {
     
     /**
-     * Instance of HTMLPurifier_AttrDef_Number to defer pixel validation
+     * Instance of HTMLPurifier_AttrDef_CSS_Number to defer number validation
      */
     var $number_def;
     
     /**
      * @param Bool indicating whether to forbid negative values
      */
-    function HTMLPurifier_AttrDef_Percentage($non_negative = false) {
-        $this->number_def = new HTMLPurifier_AttrDef_Number($non_negative);
+    function HTMLPurifier_AttrDef_CSS_Percentage($non_negative = false) {
+        $this->number_def = new HTMLPurifier_AttrDef_CSS_Number($non_negative);
     }
     
     function validate($string, $config, &$context) {
@@ -41,4 +40,3 @@ class HTMLPurifier_AttrDef_Percentage extends HTMLPurifier_AttrDef
     
 }
 
-?>

library/HTMLPurifier/AttrDef/CSS/TextDecoration.php

@@ -7,26 +7,22 @@ require_once 'HTMLPurifier/AttrDef.php';
  * @note This class could be generalized into a version that acts sort of
  *       like Enum except you can compound the allowed values.
  */
-class HTMLPurifier_AttrDef_TextDecoration extends HTMLPurifier_AttrDef
+class HTMLPurifier_AttrDef_CSS_TextDecoration extends HTMLPurifier_AttrDef
 {
     
-    /**
-     * 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 . ' ';
             }
         }
@@ -38,4 +34,3 @@ class HTMLPurifier_AttrDef_TextDecoration extends HTMLPurifier_AttrDef
     
 }
 
-?>

library/HTMLPurifier/AttrDef/CSS/URI.php

@@ -0,0 +1,57 @@
+<?php
+
+require_once 'HTMLPurifier/AttrDef/URI.php';
+
+/**
+ * Validates a URI in CSS syntax, which uses url('http://example.com')
+ * @note While theoretically speaking a URI in a CSS document could
+ *       be non-embedded, as of CSS2 there is no such usage so we're
+ *       generalizing it. This may need to be changed in the future.
+ * @warning Since HTMLPurifier_AttrDef_CSS blindly uses semicolons as
+ *          the separator, you cannot put a literal semicolon in
+ *          in the URI. Try percent encoding it, in that case.
+ */
+class HTMLPurifier_AttrDef_CSS_URI extends HTMLPurifier_AttrDef_URI
+{
+    
+    function HTMLPurifier_AttrDef_CSS_URI() {
+        parent::HTMLPurifier_AttrDef_URI(true); // always embedded
+    }
+    
+    function validate($uri_string, $config, &$context) {
+        // parse the URI out of the string and then pass it onto
+        // the parent object
+        
+        $uri_string = $this->parseCDATA($uri_string);
+        if (strpos($uri_string, 'url(') !== 0) return false;
+        $uri_string = substr($uri_string, 4);
+        $new_length = strlen($uri_string) - 1;
+        if ($uri_string[$new_length] != ')') return false;
+        $uri = trim(substr($uri_string, 0, $new_length));
+        
+        if (!empty($uri) && ($uri[0] == "'" || $uri[0] == '"')) {
+            $quote = $uri[0];
+            $new_length = strlen($uri) - 1;
+            if ($uri[$new_length] !== $quote) return false;
+            $uri = substr($uri, 1, $new_length - 1);
+        }
+        
+        $keys   = array(  '(',   ')',   ',',   ' ',   '"',   "'");
+        $values = array('\\(', '\\)', '\\,', '\\ ', '\\"', "\\'");
+        $uri = str_replace($values, $keys, $uri);
+        
+        $result = parent::validate($uri, $config, $context);
+        
+        if ($result === false) return false;
+        
+        // escape necessary characters according to CSS spec
+        // except for the comma, none of these should appear in the
+        // URI at all
+        $result = str_replace($keys, $values, $result);
+        
+        return "url($result)";
+        
+    }
+    
+}
+

library/HTMLPurifier/AttrDef/Enum.php

@@ -5,6 +5,9 @@ require_once 'HTMLPurifier/AttrDef.php';
 // Enum = Enumerated
 /**
  * Validates a keyword against a list of valid values.
+ * @warning The case-insensitive compare of this function uses PHP's
+ *          built-in strtolower and ctype_lower functions, which may
+ *          cause problems with international comparisons
  */
 class HTMLPurifier_AttrDef_Enum extends HTMLPurifier_AttrDef
 {
@@ -25,8 +28,8 @@ class HTMLPurifier_AttrDef_Enum extends HTMLPurifier_AttrDef
      * @param $case_sensitive Bool indicating whether or not case sensitive
      */
     function HTMLPurifier_AttrDef_Enum(
-        $valid_values = array(), $case_sensitive = false) {
-        
+        $valid_values = array(), $case_sensitive = false
+    ) {
         $this->valid_values = array_flip($valid_values);
         $this->case_sensitive = $case_sensitive;
     }
@@ -34,6 +37,7 @@ class HTMLPurifier_AttrDef_Enum extends HTMLPurifier_AttrDef
     function validate($string, $config, &$context) {
         $string = trim($string);
         if (!$this->case_sensitive) {
+            // we may want to do full case-insensitive libraries
             $string = ctype_lower($string) ? $string : strtolower($string);
         }
         $result = isset($this->valid_values[$string]);
@@ -41,6 +45,21 @@ 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 +1,29 @@
+<?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 +1,34 @@
+<?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 +1,33 @@
+<?php
+
+HTMLPurifier_ConfigSchema::define(
+    'Attr', 'AllowedFrameTargets', array(), 'lookup',
+    'Lookup table of all allowed link frame targets.  Some commonly used '.
+    'link targets include _blank, _self, _parent and _top. Values should '.
+    'be lowercase, as validation will be done in a case-sensitive manner '.
+    'despite W3C\'s recommendation. XHTML 1.0 Strict does not permit '.
+    'the target attribute so this directive will have no effect in that '.
+    'doctype. XHTML 1.1 does not enable the Target module by default, you '.
+    'will have to manually enable it (see the module documentation for more details.)'
+);
+
+require_once 'HTMLPurifier/AttrDef/Enum.php';
+
+/**
+ * Special-case enum attribute definition that lazy loads allowed frame targets
+ */
+class HTMLPurifier_AttrDef_HTML_FrameTarget extends HTMLPurifier_AttrDef_Enum
+{
+    
+    var $valid_values = false; // uninitialized value
+    var $case_sensitive = false;
+    
+    function HTMLPurifier_AttrDef_HTML_FrameTarget() {}
+    
+    function validate($string, $config, &$context) {
+        if ($this->valid_values === false) $this->valid_values = $config->get('Attr', 'AllowedFrameTargets');
+        return parent::validate($string, $config, $context);
+    }
+    
+}
+

library/HTMLPurifier/AttrDef/HTML/ID.php

@@ -3,6 +3,22 @@
 require_once 'HTMLPurifier/AttrDef.php';
 require_once 'HTMLPurifier/IDAccumulator.php';
 
+HTMLPurifier_ConfigSchema::define(
+    'Attr', 'EnableID', false, 'bool',
+    'Allows the ID attribute in HTML.  This is disabled by default '.
+    'due to the fact that without proper configuration user input can '.
+    'easily break the validation of a webpage by specifying an ID that is '.
+    'already on the surrounding HTML.  If you don\'t mind throwing caution to '.
+    'the wind, enable this directive, but I strongly recommend you also '.
+    'consider blacklisting IDs you use (%Attr.IDBlacklist) or prefixing all '.
+    'user supplied IDs (%Attr.IDPrefix).  This directive has been available '.
+    'since 1.2.0, and when set to true reverts to the behavior of pre-1.2.0 '.
+    'versions.'
+);
+HTMLPurifier_ConfigSchema::defineAlias(
+    'HTML', 'EnableAttrID', 'Attr', 'EnableID'
+);
+
 HTMLPurifier_ConfigSchema::define(
     'Attr', 'IDPrefix', '', 'string',
     'String to prefix to IDs.  If you have no idea what IDs your pages '.
@@ -27,6 +43,14 @@ HTMLPurifier_ConfigSchema::define(
     'is set to a non-empty value! This directive was available since 1.2.0.'
 );
 
+HTMLPurifier_ConfigSchema::define(
+    'Attr', 'IDBlacklistRegexp', null, 'string/null',
+    'PCRE regular expression to be matched against all IDs. If the expression '.
+    'is matches, the ID is rejected. Use this with care: may cause '.
+    'significant degradation. ID matching is done after all other '.
+    'validation. This directive was available since 1.6.0.'
+);
+
 /**
  * Validates the HTML attribute ID.
  * @warning Even though this is the id processor, it
@@ -36,11 +60,16 @@ HTMLPurifier_ConfigSchema::define(
  *          blacklist. If you're hacking around, make sure you use load()!
  */
 
-class HTMLPurifier_AttrDef_ID extends HTMLPurifier_AttrDef
+class HTMLPurifier_AttrDef_HTML_ID extends HTMLPurifier_AttrDef
 {
     
+    // ref functionality disabled, since we also have to verify
+    // whether or not the ID it refers to exists
+    
     function validate($id, $config, &$context) {
         
+        if (!$config->get('Attr', 'EnableID')) return false;
+        
         $id = trim($id); // trim it first
         
         if ($id === '') return false;
@@ -55,8 +84,10 @@ class HTMLPurifier_AttrDef_ID extends HTMLPurifier_AttrDef
                 '%Attr.IDPrefix is set', E_USER_WARNING);
         }
         
-        $id_accumulator =& $context->get('IDAccumulator');
-        if (isset($id_accumulator->ids[$id])) return false;
+        //if (!$this->ref) {
+            $id_accumulator =& $context->get('IDAccumulator');
+            if (isset($id_accumulator->ids[$id])) return false;
+        //}
         
         // we purposely avoid using regex, hopefully this is faster
         
@@ -71,7 +102,12 @@ class HTMLPurifier_AttrDef_ID extends HTMLPurifier_AttrDef
             $result = ($trim === '');
         }
         
-        if ($result) $id_accumulator->add($id);
+        $regexp = $config->get('Attr', 'IDBlacklistRegexp');
+        if ($regexp && preg_match($regexp, $id)) {
+            return false;
+        }
+        
+        if (/*!$this->ref && */$result) $id_accumulator->add($id);
         
         // if no change was made to the ID, return the result
         // else, return the new id if stripping whitespace made it
@@ -82,4 +118,3 @@ class HTMLPurifier_AttrDef_ID extends HTMLPurifier_AttrDef
     
 }
 
-?>

library/HTMLPurifier/AttrDef/HTML/Length.php

@@ -1,18 +1,16 @@
 <?php
 
 require_once 'HTMLPurifier/AttrDef.php';
-require_once 'HTMLPurifier/AttrDef/Pixels.php';
+require_once 'HTMLPurifier/AttrDef/HTML/Pixels.php';
 
 /**
  * Validates the HTML type length (not to be confused with CSS's length).
  * 
  * This accepts integer pixels or percentages as lengths for certain
- * HTML attributes. Don't use this for CSS: that's
- * HTMLPurifier_AttrDef_CSSLength which requires prefixes and allows a lot
- * more different types.
+ * HTML attributes.
  */
 
-class HTMLPurifier_AttrDef_Length extends HTMLPurifier_AttrDef_Pixels
+class HTMLPurifier_AttrDef_HTML_Length extends HTMLPurifier_AttrDef_HTML_Pixels
 {
     
     function validate($string, $config, &$context) {
@@ -43,4 +41,3 @@ class HTMLPurifier_AttrDef_Length extends HTMLPurifier_AttrDef_Pixels
     
 }
 
-?>

library/HTMLPurifier/AttrDef/HTML/LinkTypes.php

@@ -0,0 +1,72 @@
+<?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/HTML/MultiLength.php

@@ -1,7 +1,7 @@
 <?php
 
 require_once 'HTMLPurifier/AttrDef.php';
-require_once 'HTMLPurifier/AttrDef/Length.php';
+require_once 'HTMLPurifier/AttrDef/HTML/Length.php';
 
 /**
  * Validates a MultiLength as defined by the HTML spec.
@@ -9,7 +9,7 @@ require_once 'HTMLPurifier/AttrDef/Length.php';
  * A multilength is either a integer (pixel count), a percentage, or
  * a relative number.
  */
-class HTMLPurifier_AttrDef_MultiLength extends HTMLPurifier_AttrDef_Length
+class HTMLPurifier_AttrDef_HTML_MultiLength extends HTMLPurifier_AttrDef_HTML_Length
 {
     
     function validate($string, $config, &$context) {
@@ -27,16 +27,17 @@ class HTMLPurifier_AttrDef_MultiLength extends HTMLPurifier_AttrDef_Length
         
         $int = substr($string, 0, $length - 1);
         
+        if ($int == '') return '*';
         if (!is_numeric($int)) return false;
         
         $int = (int) $int;
         
-        if ($int < 0) return '0*';
-        
+        if ($int < 0) return false;
+        if ($int == 0) return '0';
+        if ($int == 1) return '*';
         return ((string) $int) . '*';
         
     }
     
 }
 
-?>

library/HTMLPurifier/AttrDef/HTML/Nmtokens.php

@@ -4,9 +4,13 @@ require_once 'HTMLPurifier/AttrDef.php';
 require_once 'HTMLPurifier/Config.php';
 
 /**
- * Validates the contents of the global HTML attribute class.
+ * Validates contents based on NMTOKENS attribute type.
+ * @note The only current use for this is the class attribute in HTML
+ * @note Could have some functionality factored out into Nmtoken class
+ * @warning We cannot assume this class will be used only for 'class'
+ *          attributes. Not sure how to hook in magic behavior, then.
  */
-class HTMLPurifier_AttrDef_Class extends HTMLPurifier_AttrDef
+class HTMLPurifier_AttrDef_HTML_Nmtokens extends HTMLPurifier_AttrDef
 {
     
     function validate($string, $config, &$context) {
@@ -31,10 +35,10 @@ class HTMLPurifier_AttrDef_Class extends HTMLPurifier_AttrDef
         
         if (empty($matches[1])) return false;
         
-        // reconstruct class string
+        // reconstruct string
         $new_string = '';
-        foreach ($matches[1] as $class_names) {
-            $new_string .= $class_names . ' ';
+        foreach ($matches[1] as $token) {
+            $new_string .= $token . ' ';
         }
         $new_string = rtrim($new_string);
         
@@ -44,4 +48,3 @@ class HTMLPurifier_AttrDef_Class extends HTMLPurifier_AttrDef
     
 }
 
-?>

library/HTMLPurifier/AttrDef/HTML/Pixels.php

@@ -5,7 +5,7 @@ require_once 'HTMLPurifier/AttrDef.php';
 /**
  * Validates an integer representation of pixels according to the HTML spec.
  */
-class HTMLPurifier_AttrDef_Pixels extends HTMLPurifier_AttrDef
+class HTMLPurifier_AttrDef_HTML_Pixels extends HTMLPurifier_AttrDef
 {
     
     function validate($string, $config, &$context) {
@@ -34,4 +34,3 @@ class HTMLPurifier_AttrDef_Pixels extends HTMLPurifier_AttrDef
     
 }
 
-?>

library/HTMLPurifier/AttrDef/Integer.php

@@ -72,4 +72,3 @@ class HTMLPurifier_AttrDef_Integer extends HTMLPurifier_AttrDef
     
 }
 
-?>

library/HTMLPurifier/AttrDef/Lang.php

@@ -46,7 +46,7 @@ class HTMLPurifier_AttrDef_Lang extends HTMLPurifier_AttrDef
         
         // process second subtag : $subtags[1]
         $length = strlen($subtags[1]);
-        if ($length == 0 || $length == 1 || $length > 8 || !ctype_alnum($subtags[1])) {
+        if ($length == 0 || ($length == 1 && $subtags[1] != 'x') || $length > 8 || !ctype_alnum($subtags[1])) {
             return $new_string;
         }
         if (!ctype_lower($subtags[1])) $subtags[1] = strtolower($subtags[1]);
@@ -72,4 +72,3 @@ class HTMLPurifier_AttrDef_Lang extends HTMLPurifier_AttrDef
     
 }
 
-?>

library/HTMLPurifier/AttrDef/ListStyle.php

@@ -1,78 +0,0 @@
-<?php
-
-require_once 'HTMLPurifier/AttrDef.php';
-
-/**
- * Validates shorthand CSS property list-style.
- * @note This currently does not support list-style-image, as that functionality
- *       is not implemented yet elsewhere.
- */
-class HTMLPurifier_AttrDef_ListStyle extends HTMLPurifier_AttrDef
-{
-    
-    /**
-     * Local copy of component validators.
-     * @note See HTMLPurifier_AttrDef_Font::$info for a similar impl.
-     */
-    var $info;
-    
-    function HTMLPurifier_AttrDef_ListStyle($config) {
-        $def = $config->getCSSDefinition();
-        $this->info['list-style-type']     = $def->info['list-style-type'];
-        $this->info['list-style-position'] = $def->info['list-style-position'];
-    }
-    
-    function validate($string, $config, &$context) {
-        
-        // regular pre-processing
-        $string = $this->parseCDATA($string);
-        if ($string === '') return false;
-        
-        $bits = explode(' ', strtolower($string)); // bits to process
-        
-        $caught_type = false;
-        $caught_position = false;
-        $caught_none = false; // as in keyword none, which is in all of them
-        
-        $ret = '';
-        
-        foreach ($bits as $bit) {
-            if ($caught_none && ($caught_type || $caught_position)) break;
-            if ($caught_type && $caught_position) break;
-            
-            if ($bit === '') continue;
-            
-            if ($bit === 'none') {
-                if ($caught_none) continue;
-                $caught_none = true;
-                $ret .= 'none ';
-                continue;
-            }
-            
-            // if we add anymore, roll it into a loop
-            
-            $r = $this->info['list-style-type']->validate($bit, $config, $context);
-            if ($r !== false) {
-                if ($caught_type) continue;
-                $caught_type = true;
-                $ret .= $r . ' ';
-                continue;
-            }
-            
-            $r = $this->info['list-style-position']->validate($bit, $config, $context);
-            if ($r !== false) {
-                if ($caught_position) continue;
-                $caught_position = true;
-                $ret .= $r . ' ';
-                continue;
-            }
-        }
-        
-        $ret = rtrim($ret);
-        return $ret ? $ret : false;
-        
-    }
-    
-}
-
-?>

library/HTMLPurifier/AttrDef/Text.php

@@ -14,4 +14,3 @@ class HTMLPurifier_AttrDef_Text extends HTMLPurifier_AttrDef
     
 }
 
-?>

library/HTMLPurifier/AttrDef/URI.php

@@ -1,81 +1,65 @@
 <?php
 
 require_once 'HTMLPurifier/AttrDef.php';
+require_once 'HTMLPurifier/URIParser.php';
 require_once 'HTMLPurifier/URIScheme.php';
 require_once 'HTMLPurifier/URISchemeRegistry.php';
-require_once 'HTMLPurifier/AttrDef/Host.php';
+require_once 'HTMLPurifier/AttrDef/URI/Host.php';
 require_once 'HTMLPurifier/PercentEncoder.php';
+require_once 'HTMLPurifier/AttrDef/URI/Email.php';
+
+// special case filtering directives 
 
 HTMLPurifier_ConfigSchema::define(
-    'URI', 'DefaultScheme', 'http', 'string',
-    'Defines through what scheme the output will be served, in order to '.
-    'select the proper object validator when no scheme information is present.'
-);
+    'URI', 'Munge', null, 'string/null', '
+<p>
+    Munges all browsable (usually http, https and ftp)
+    absolute URI\'s into another URI, usually a URI redirection service.
+    This directive accepts a URI, formatted with a <code>%s</code> where 
+    the url-encoded original URI should be inserted (sample: 
+    <code>http://www.google.com/url?q=%s</code>).
+</p>
+<p>
+    Uses for this directive:
+</p>
+<ul>
+    <li>
+        Prevent PageRank leaks, while being fairly transparent 
+        to users (you may also want to add some client side JavaScript to 
+        override the text in the statusbar). <strong>Notice</strong>:
+        Many security experts believe that this form of protection does not deter spam-bots. 
+    </li>
+    <li>
+        Redirect users to a splash page telling them they are leaving your
+        website. While this is poor usability practice, it is often mandated
+        in corporate environments.
+    </li>
+</ul>
+<p>
+    This directive has been available since 1.3.0.
+</p>
+');
+
+// disabling directives
 
 HTMLPurifier_ConfigSchema::define(
-    'URI', 'Host', null, 'string/null',
-    'Defines the domain name of the server, so we can determine whether or '.
-    'an absolute URI is from your website or not.  Not strictly necessary, '.
-    'as users should be using relative URIs to reference resources on your '.
-    'website.  It will, however, let you use absolute URIs to link to '.
-    'subdomains of the domain you post here: i.e. example.com will allow '.
-    'sub.example.com.  However, higher up domains will still be excluded: '.
-    'if you set %URI.Host to sub.example.com, example.com will be blocked. '.
-    'This directive has been available since 1.2.0.'
-);
+    'URI', 'Disable', false, 'bool', '
+<p>
+    Disables all URIs in all forms. Not sure why you\'d want to do that 
+    (after all, the Internet\'s founded on the notion of a hyperlink). 
+    This directive has been available since 1.3.0.
+</p>
+');
+HTMLPurifier_ConfigSchema::defineAlias('Attr', 'DisableURI', 'URI', 'Disable');
 
 HTMLPurifier_ConfigSchema::define(
-    'URI', 'DisableExternal', false, 'bool',
-    'Disables links to external websites.  This is a highly effective '.
-    'anti-spam and anti-pagerank-leech measure, but comes at a hefty price: no'.
-    'links or images outside of your domain will be allowed.  Non-linkified '.
-    'URIs will still be preserved.  If you want to be able to link to '.
-    'subdomains or use absolute URIs, specify %URI.Host for your website. '.
-    'This directive has been available since 1.2.0.'
-);
-
-HTMLPurifier_ConfigSchema::define(
-    'URI', 'DisableExternalResources', false, 'bool',
-    'Disables the embedding of external resources, preventing users from '.
-    'embedding things like images from other hosts. This prevents '.
-    'access tracking (good for email viewers), bandwidth leeching, '.
-    'cross-site request forging, goatse.cx posting, and '.
-    'other nasties, but also results in '.
-    'a loss of end-user functionality (they can\'t directly post a pic '.
-    'they posted from Flickr anymore). Use it if you don\'t have a '.
-    'robust user-content moderation team. This directive has been '.
-    'available since 1.3.0.'
-);
-
-HTMLPurifier_ConfigSchema::define(
-    'URI', 'DisableResources', false, 'bool',
-    'Disables embedding resources, essentially meaning no pictures. You can '.
-    'still link to them though. See %URI.DisableExternalResources for why '.
-    'this might be a good idea. This directive has been available since 1.3.0.'
-);
-
-HTMLPurifier_ConfigSchema::define(
-    'URI', 'Munge', null, 'string/null',
-    'Munges all browsable (usually http, https and ftp) URI\'s into some URL '.
-    'redirection service. Pass this directive a URI, with %s inserted where '.
-    'the url-encoded original URI should be inserted (sample: '.
-    '<code>http://www.google.com/url?q=%s</code>). '.
-    'This prevents PageRank leaks, while being as transparent as possible '.
-    'to users (you may also want to add some client side JavaScript to '.
-    'override the text in the statusbar). Warning: many security experts '.
-    'believe that this form of protection does not deter spam-bots. '.
-    'You can also use this directive to redirect users to a splash page '.
-    'telling them they are leaving your website. '.
-    'This directive has been available since 1.3.0.'
-);
-
-HTMLPurifier_ConfigSchema::define(
-    'URI', 'HostBlacklist', array(), 'list',
-    'List of strings that are forbidden in the host of any URI. Use it to '.
-    'kill domain names of spam, etc. Note that it will catch anything in '.
-    'the domain, so <tt>moo.com</tt> will catch <tt>moo.com.example.com</tt>. '.
-    'This directive has been available since 1.3.0.'
-);
+    'URI', 'DisableResources', false, 'bool', '
+<p>
+    Disables embedding resources, essentially meaning no pictures. You can 
+    still link to them though. See %URI.DisableExternalResources for why 
+    this might be a good idea. This directive has been available since 1.3.0.
+</p>
+');
 
 /**
  * Validates a URI as defined by RFC 3986.
@@ -84,203 +68,83 @@ HTMLPurifier_ConfigSchema::define(
 class HTMLPurifier_AttrDef_URI extends HTMLPurifier_AttrDef
 {
     
-    var $host;
-    var $PercentEncoder;
-    var $embeds_resource;
+    var $parser, $percentEncoder;
+    var $embedsResource;
     
     /**
      * @param $embeds_resource_resource Does the URI here result in an extra HTTP request?
      */
     function HTMLPurifier_AttrDef_URI($embeds_resource = false) {
-        $this->host = new HTMLPurifier_AttrDef_Host();
-        $this->PercentEncoder = new HTMLPurifier_PercentEncoder();
-        $this->embeds_resource = (bool) $embeds_resource;
+        $this->parser = new HTMLPurifier_URIParser();
+        $this->percentEncoder = new HTMLPurifier_PercentEncoder();
+        $this->embedsResource = (bool) $embeds_resource;
     }
     
     function validate($uri, $config, &$context) {
         
-        // We'll write stack-based parsers later, for now, use regexps to
-        // get things working as fast as possible (irony)
+        if ($config->get('URI', 'Disable')) return false;
         
-        // parse as CDATA
+        // initial operations
         $uri = $this->parseCDATA($uri);
+        $uri = $this->percentEncoder->normalize($uri);
         
-        // fix up percent-encoding
-        $uri = $this->PercentEncoder->normalize($uri);
+        // parse the URI
+        $uri = $this->parser->parse($uri);
+        if ($uri === false) return false;
         
-        // while it would be nice to use parse_url(), that's specifically
-        // for HTTP and thus won't work for our generic URI parsing
+        // add embedded flag to context for validators
+        $context->register('EmbeddedURI', $this->embedsResource); 
         
-        // according to the RFC... (but this cuts corners, i.e. non-validating)
-        $r_URI = '!'.
-            '(([^:/?#<>\'"]+):)?'. // 2. Scheme
-            '(//([^/?#<>\'"]*))?'. // 4. Authority
-            '([^?#<>\'"]*)'.       // 5. Path
-            '(\?([^#<>\'"]*))?'.   // 7. Query
-            '(#([^<>\'"]*))?'.     // 8. Fragment
-            '!';
+        $ok = false;
+        do {
+            
+            // generic validation
+            $result = $uri->validate($config, $context);
+            if (!$result) break;
+            
+            // chained validation
+            $uri_def =& $config->getDefinition('URI');
+            $result = $uri_def->filter($uri, $config, $context);
+            if (!$result) break;
+            
+            // scheme-specific validation 
+            $scheme_obj = $uri->getSchemeObj($config, $context);
+            if (!$scheme_obj) break;
+            if ($this->embedsResource && !$scheme_obj->browsable) break;
+            $result = $scheme_obj->validate($uri, $config, $context);
+            if (!$result) break;
+            
+            // survived gauntlet
+            $ok = true;
+            
+        } while (false);
         
-        $matches = array();
-        $result = preg_match($r_URI, $uri, $matches);
+        $context->destroy('EmbeddedURI');
+        if (!$ok) return false;
         
-        if (!$result) return false; // invalid URI
-        
-        // seperate out parts
-        $scheme     = !empty($matches[1]) ? $matches[2] : null;
-        $authority  = !empty($matches[3]) ? $matches[4] : null;
-        $path       = $matches[5]; // always present, can be empty
-        $query      = !empty($matches[6]) ? $matches[7] : null;
-        $fragment   = !empty($matches[8]) ? $matches[9] : null;
-        
-        
-        
-        $registry =& HTMLPurifier_URISchemeRegistry::instance();
-        if ($scheme !== null) {
-            // no need to validate the scheme's fmt since we do that when we
-            // retrieve the specific scheme object from the registry
-            $scheme = ctype_lower($scheme) ? $scheme : strtolower($scheme);
-            $scheme_obj =& $registry->getScheme($scheme, $config, $context);
-            if (!$scheme_obj) return false; // invalid scheme, clean it out
-        } else {
-            $scheme_obj =& $registry->getScheme(
-                $config->get('URI', 'DefaultScheme'), $config, $context
-            );
+        // munge scheme off if necessary (this must be last)
+        if (!is_null($uri->scheme) && is_null($uri->host)) {
+            if ($uri_def->defaultScheme == $uri->scheme) {
+                $uri->scheme = null;
+            }
         }
         
+        // back to string
+        $result = $uri->toString();
         
-        // the URI we're processing embeds_resource a resource in the page, but the URI
-        // it references cannot be located
-        if ($this->embeds_resource && !$scheme_obj->browsable) {
-            return false;
-        }
-        
-        
-        if ($authority !== null) {
-            
-            // remove URI if it's absolute and we disabled externals or
-            // if it's absolute and embedded and we disabled external resources
-            unset($our_host);
-            if (
-                $config->get('URI', 'DisableExternal') ||
-                (
-                    $config->get('URI', 'DisableExternalResources') &&
-                    $this->embeds_resource
-                )
-            ) {
-                $our_host = $config->get('URI', 'Host');
-                if ($our_host === null) return false;
-            }
-            
-            $HEXDIG = '[A-Fa-f0-9]';
-            $unreserved = 'A-Za-z0-9-._~'; // make sure you wrap with []
-            $sub_delims = '!$&\'()'; // needs []
-            $pct_encoded = "%$HEXDIG$HEXDIG";
-            $r_userinfo = "(?:[$unreserved$sub_delims:]|$pct_encoded)*";
-            $r_authority = "/^(($r_userinfo)@)?(\[[^\]]+\]|[^:]*)(:(\d*))?/";
-            $matches = array();
-            preg_match($r_authority, $authority, $matches);
-            // overloads regexp!
-            $userinfo   = !empty($matches[1]) ? $matches[2] : null;
-            $host       = !empty($matches[3]) ? $matches[3] : null;
-            $port       = !empty($matches[4]) ? $matches[5] : null;
-            
-            // validate port
-            if ($port !== null) {
-                $port = (int) $port;
-                if ($port < 1 || $port > 65535) $port = null;
-            }
-            
-            $host = $this->host->validate($host, $config, $context);
-            if ($host === false) $host = null;
-            
-            if ($this->checkBlacklist($host, $config, $context)) return false;
-            
-            // more lenient absolute checking
-            if (isset($our_host)) {
-                $host_parts = array_reverse(explode('.', $host));
-                // could be cached
-                $our_host_parts = array_reverse(explode('.', $our_host));
-                foreach ($our_host_parts as $i => $discard) {
-                    if (!isset($host_parts[$i])) return false;
-                    if ($host_parts[$i] != $our_host_parts[$i]) return false;
-                }
-            }
-            
-            // userinfo and host are validated within the regexp
-            
-        } else {
-            $port = $host = $userinfo = null;
-        }
-        
-        
-        // query and fragment are quite simple in terms of definition:
-        // *( pchar / "/" / "?" ), so define their validation routines
-        // when we start fixing percent encoding
-        
-        
-        
-        // path gets to be validated against a hodge-podge of rules depending
-        // on the status of authority and scheme, but it's not that important,
-        // esp. since it won't be applicable to everyone
-        
-        
-        
-        // okay, now we defer execution to the subobject for more processing
-        // note that $fragment is omitted
-        list($userinfo, $host, $port, $path, $query) = 
-            $scheme_obj->validateComponents(
-                $userinfo, $host, $port, $path, $query, $config, $context
-            );
-        
-        
-        // reconstruct authority
-        $authority = null;
-        if (!is_null($userinfo) || !is_null($host) || !is_null($port)) {
-            $authority = '';
-            if($userinfo !== null) $authority .= $userinfo . '@';
-            $authority .= $host;
-            if($port !== null) $authority .= ':' . $port;
-        }
-        
-        // reconstruct the result
-        $result = '';
-        if ($scheme !== null) $result .= "$scheme:";
-        if ($authority !== null) $result .= "//$authority";
-        $result .= $path;
-        if ($query !== null) $result .= "?$query";
-        if ($fragment !== null) $result .= "#$fragment";
-        
-        // munge if necessary
-        $munge = $config->get('URI', 'Munge');
-        if (!empty($scheme_obj->browsable) && $munge !== null) {
-            if ($authority !== null) {
-                $result = str_replace('%s', rawurlencode($result), $munge);
-            }
+        // munge entire URI if necessary
+        if (
+            !is_null($uri->host) && // indicator for authority
+            !empty($scheme_obj->browsable) &&
+            !is_null($munge = $config->get('URI', 'Munge'))
+        ) {
+            $result = str_replace('%s', rawurlencode($result), $munge);
         }
         
         return $result;
         
     }
     
-    /**
-     * Checks a host against an array blacklist
-     * @param $host Host to check
-     * @param $config HTMLPurifier_Config instance
-     * @param $context HTMLPurifier_Context instance
-     * @return bool Is spam?
-     */
-    function checkBlacklist($host, &$config, &$context) {
-        $blacklist = $config->get('URI', 'HostBlacklist');
-        if (!empty($blacklist)) {
-            foreach($blacklist as $blacklisted_host_fragment) {
-                if (strpos($host, $blacklisted_host_fragment) !== false) {
-                    return true;
-                }
-            }
-        }
-        return false;
-    }
-    
 }
 
-?>
+

library/HTMLPurifier/AttrDef/URI/Email.php

@@ -1,8 +1,9 @@
 <?php
 
 require_once 'HTMLPurifier/AttrDef.php';
+require_once 'HTMLPurifier/AttrDef/URI/Email/SimpleCheck.php';
 
-class HTMLPurifier_AttrDef_Email extends HTMLPurifier_AttrDef
+class HTMLPurifier_AttrDef_URI_Email extends HTMLPurifier_AttrDef
 {
     
     /**
@@ -14,4 +15,3 @@ class HTMLPurifier_AttrDef_Email extends HTMLPurifier_AttrDef
     
 }
 
-?>

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

@@ -1,12 +1,12 @@
 <?php
 
-require_once 'HTMLPurifier/AttrDef/Email.php';
+require_once 'HTMLPurifier/AttrDef/URI/Email.php';
 
 /**
  * Primitive email validation class based on the regexp found at 
  * http://www.regular-expressions.info/email.html
  */
-class HTMLPurifier_AttrDef_Email_SimpleCheck extends HTMLPurifier_AttrDef_Email
+class HTMLPurifier_AttrDef_URI_Email_SimpleCheck extends HTMLPurifier_AttrDef_URI_Email
 {
     
     function validate($string, $config, &$context) {
@@ -20,4 +20,3 @@ class HTMLPurifier_AttrDef_Email_SimpleCheck extends HTMLPurifier_AttrDef_Email
     
 }
 
-?>

library/HTMLPurifier/AttrDef/URI/Host.php

@@ -1,28 +1,28 @@
 <?php
 
 require_once 'HTMLPurifier/AttrDef.php';
-require_once 'HTMLPurifier/AttrDef/IPv4.php';
-require_once 'HTMLPurifier/AttrDef/IPv6.php';
+require_once 'HTMLPurifier/AttrDef/URI/IPv4.php';
+require_once 'HTMLPurifier/AttrDef/URI/IPv6.php';
 
 /**
  * Validates a host according to the IPv4, IPv6 and DNS (future) specifications.
  */
-class HTMLPurifier_AttrDef_Host extends HTMLPurifier_AttrDef
+class HTMLPurifier_AttrDef_URI_Host extends HTMLPurifier_AttrDef
 {
     
     /**
-     * Instance of HTMLPurifier_AttrDef_IPv4 sub-validator
+     * Instance of HTMLPurifier_AttrDef_URI_IPv4 sub-validator
      */
     var $ipv4;
     
     /**
-     * Instance of HTMLPurifier_AttrDef_IPv6 sub-validator
+     * Instance of HTMLPurifier_AttrDef_URI_IPv6 sub-validator
      */
     var $ipv6;
     
-    function HTMLPurifier_AttrDef_Host() {
-        $this->ipv4 = new HTMLPurifier_AttrDef_IPv4();
-        $this->ipv6 = new HTMLPurifier_AttrDef_IPv6();
+    function HTMLPurifier_AttrDef_URI_Host() {
+        $this->ipv4 = new HTMLPurifier_AttrDef_URI_IPv4();
+        $this->ipv6 = new HTMLPurifier_AttrDef_URI_IPv6();
     }
     
     function validate($string, $config, &$context) {
@@ -51,4 +51,3 @@ class HTMLPurifier_AttrDef_Host extends HTMLPurifier_AttrDef
     
 }
 
-?>