Release 3.3.0.

Signed-off-by: Edward Z. Yang <edwardzyang@thewritingpot.com>

.gitattributes

@@ -0,0 +1 @@
+configdoc/usage.xml -crlf

.gitignore

@@ -0,0 +1,18 @@
+conf/
+test-settings.php
+library/HTMLPurifier/DefinitionCache/Serializer/*/
+library/standalone/
+library/HTMLPurifier.standalone.php
+library/HTMLPurifier*.tgz
+library/package*.xml
+smoketests/test-schema.html
+configdoc/*.html
+configdoc/configdoc.xml
+docs/doxygen*
+*.phpt.diff
+*.phpt.exp
+*.phpt.log
+*.phpt.out
+*.phpt.php
+*.phpt.skip.php
+*.htmlt.ini

CREDITS

@@ -5,3 +5,5 @@ Almost everything written by Edward Z. Yang (Ambush Commander).  Lots of thanks
 to the DevNetwork Community for their help (see docs/ref-devnetwork.html for
 more details), Feyd especially (namely IPv6 and optimization).  Thanks to RSnake
 for letting me package his fantastic XSS cheatsheet for a smoketest.
+
+    vim: et sw=4 sts=4

FOCUS

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

INSTALL

@@ -2,28 +2,28 @@
 Install
     How to install HTML Purifier
 
-HTML Purifier is designed to run out of the box, so actually using the 
-library is extremely easy.  (Although... if you were looking for a 
+HTML Purifier is designed to run out of the box, so actually using the
+library is extremely easy.  (Although... if you were looking for a
 step-by-step installation GUI, you've downloaded the wrong software!)
 
 While the impatient can get going immediately with some of the sample
-code at the bottom of this library, it's well worth performing some
-basic sanity checks to get the most out of this library.
+code at the bottom of this library, it's well worth reading this entire
+document--most of the other documentation assumes that you are familiar
+with these contents.
 
 
 ---------------------------------------------------------------------------
 1.  Compatibility
 
-HTML Purifier works in both PHP 4 and PHP 5, and is actively tested from 
-PHP 4.3.7 and up (see tests/multitest.php for specific versions). It has 
-no core dependencies with other libraries. PHP 4 support will be 
-deprecated on December 31, 2007, at which time only essential security 
-fixes will be issued for the PHP 4 version until August 8, 2008. 
+HTML Purifier is PHP 5 only, and is actively tested from PHP 5.0.5 and
+up. It has no core dependencies with other libraries. PHP
+4 support was deprecated on December 31, 2007 with HTML Purifier 3.0.0.
 
 These optional extensions can enhance the capabilities of HTML Purifier:
 
-    * iconv : Converts text to and from non-UTF-8 encodings
-    * tidy  : Used for pretty-printing HTML
+    * iconv  : Converts text to and from non-UTF-8 encodings
+    * bcmath : Used for unit conversion and imagecrash protection
+    * tidy   : Used for pretty-printing HTML
 
 
 ---------------------------------------------------------------------------
@@ -47,7 +47,7 @@ HTML Purifier can process these doctypes:
 * UTF-8 (default)
 * Any encoding iconv supports (with crippled internationalization support)
 
-These defaults reflect what my choices where be if I were authoring an
+These defaults reflect what my choices would be if I were authoring an
 HTML document, however, what you choose depends on the nature of your
 codebase.  If you don't know what doctype you are using, you can determine
 the doctype from this identifier at the top of your source code:
@@ -62,8 +62,8 @@ the doctype from this identifier at the top of your source code:
 If the character encoding declaration is missing, STOP NOW, and
 read 'docs/enduser-utf8.html' (web accessible at
 http://htmlpurifier.org/docs/enduser-utf8.html).  In fact, even if it is
-present, read this document anyway, as most websites specify character
-encoding incorrectly.
+present, read this document anyway, as many websites specify their
+document's character encoding incorrectly.
 
 
 ---------------------------------------------------------------------------
@@ -73,25 +73,142 @@ The procedure is quite simple:
 
     require_once '/path/to/library/HTMLPurifier.auto.php';
 
-I recommend only including HTML Purifier when you need it, because that
-call represents the inclusion of a lot of PHP files which constitute
-the bulk of HTML Purifier's memory usage.
-
-If you don't like your include_path to be fiddled around with, simply set
-HTML Purifier's library/ directory to the include path yourself and then:
-
-    require_once 'HTMLPurifier.php';
+This will setup an autoloader, so the library's files are only included
+when you use them.
 
 Only the contents in the library/ folder are necessary, so you can remove
-everything else when using HTML Purifier in a production environment. 
+everything else when using HTML Purifier in a production environment.
+
+If you installed HTML Purifier via PEAR, all you need to do is:
+
+    require_once 'HTMLPurifier.auto.php';
+
+Please note that the usual PEAR practice of including just the classes you
+want will not work with HTML Purifier's autoloading scheme.
+
+Advanced users, read on; other users can skip to section 4.
+
+Autoload compatibility
+----------------------
+
+    HTML Purifier attempts to be as smart as possible when registering an
+    autoloader, but there are some cases where you will need to change
+    your own code to accomodate HTML Purifier. These are those cases:
+
+    PHP VERSION IS LESS THAN 5.1.2, AND YOU'VE DEFINED __autoload
+        Because spl_autoload_register() doesn't exist in early versions
+        of PHP 5, HTML Purifier has no way of adding itself to the autoload
+        stack. Modify your __autoload function to test
+        HTMLPurifier_Bootstrap::autoload($class)
+
+        For example, suppose your autoload function looks like this:
+
+            function __autoload($class) {
+                require str_replace('_', '/', $class) . '.php';
+                return true;
+            }
+
+        A modified version with HTML Purifier would look like this:
+
+            function __autoload($class) {
+                if (HTMLPurifier_Bootstrap::autoload($class)) return true;
+                require str_replace('_', '/', $class) . '.php';
+                return true;
+            }
+
+        Note that there *is* some custom behavior in our autoloader; the
+        original autoloader in our example would work for 99% of the time,
+        but would fail when including language files.
+
+    AN __autoload FUNCTION IS DECLARED AFTER OUR AUTOLOADER IS REGISTERED
+        spl_autoload_register() has the curious behavior of disabling
+        the existing __autoload() handler. Users need to explicitly
+        spl_autoload_register('__autoload'). Because we use SPL when it
+        is available, __autoload() will ALWAYS be disabled. If __autoload()
+        is declared before HTML Purifier is loaded, this is not a problem:
+        HTML Purifier will register the function for you. But if it is
+        declared afterwards, it will mysteriously not work. This
+        snippet of code (after your autoloader is defined) will fix it:
+
+            spl_autoload_register('__autoload')
+
+    Users should also be on guard if they use a version of PHP previous
+    to 5.1.2 without an autoloader--HTML Purifier will define __autoload()
+    for you, which can collide with an autoloader that was added by *you*
+    later.
+
+
+For better performance
+----------------------
+
+    Opcode caches, which greatly speed up PHP initialization for scripts
+    with large amounts of code (HTML Purifier included), don't like
+    autoloaders. We offer an include file that includes all of HTML Purifier's
+    files in one go in an opcode cache friendly manner:
+
+        // If /path/to/library isn't already in your include path, uncomment
+        // the below line:
+        // require '/path/to/library/HTMLPurifier.path.php';
+
+        require 'HTMLPurifier.includes.php';
+
+    Optional components still need to be included--you'll know if you try to
+    use a feature and you get a class doesn't exists error! The autoloader
+    can be used in conjunction with this approach to catch classes that are
+    missing. Simply add this afterwards:
+
+        require 'HTMLPurifier.autoload.php';
+
+Standalone version
+------------------
+
+    HTML Purifier has a standalone distribution; you can also generate
+    a standalone file from the full version by running the script
+    maintenance/generate-standalone.php . The standalone version has the
+    benefit of having most of its code in one file, so parsing is much
+    faster and the library is easier to manage.
+
+    If HTMLPurifier.standalone.php exists in the library directory, you
+    can use it like this:
+
+        require '/path/to/HTMLPurifier.standalone.php';
+
+    This is equivalent to including HTMLPurifier.includes.php, except that
+    the contents of standalone/ will be added to your path. To override this
+    behavior, specify a new HTMLPURIFIER_PREFIX where standalone files can
+    be found (usually, this will be one directory up, the "true" library
+    directory in full distributions). Don't forget to set your path too!
+
+    The autoloader can be added to the end to ensure the classes are
+    loaded when necessary; otherwise you can manually include them.
+    To use the autoloader, use this:
+
+        require 'HTMLPurifier.autoload.php';
+
+For advanced users
+------------------
+
+    HTMLPurifier.auto.php performs a number of operations that can be done
+    individually. These are:
+
+        HTMLPurifier.path.php
+            Puts /path/to/library in the include path. For high performance,
+            this should be done in php.ini.
+
+        HTMLPurifier.autoload.php
+            Registers our autoload handler HTMLPurifier_Bootstrap::autoload($class).
+
+    You can do these operations by yourself--in fact, you must modify your own
+    autoload handler if you are using a version of PHP earlier than PHP 5.1.2
+    (See "Autoload compatibility" above).
 
 
 ---------------------------------------------------------------------------
 4. Configuration
 
 HTML Purifier is designed to run out-of-the-box, but occasionally HTML
-Purifier needs to be told what to do.  If you answered no to any of these
-questions, read on, otherwise, you can skip to the next section (or, if you're
+Purifier needs to be told what to do.  If you answer no to any of these
+questions, read on; otherwise, you can skip to the next section (or, if you're
 into configuring things just for the heck of it, skip to 4.3).
 
 * Am I using UTF-8?
@@ -235,7 +352,7 @@ If your website is in UTF-8 and XHTML Transitional, use this code:
 
 <?php
     require_once '/path/to/htmlpurifier/library/HTMLPurifier.auto.php';
-    
+
     $purifier = new HTMLPurifier();
     $clean_html = $purifier->purify($dirty_html);
 ?>
@@ -244,12 +361,13 @@ If your website is in a different encoding or doctype, use this code:
 
 <?php
     require_once '/path/to/htmlpurifier/library/HTMLPurifier.auto.php';
-    
+
     $config = HTMLPurifier_Config::createDefault();
     $config->set('Core', 'Encoding', 'ISO-8859-1'); // replace with your encoding
     $config->set('HTML', 'Doctype', 'HTML 4.01 Transitional'); // replace with your doctype
     $purifier = new HTMLPurifier($config);
-    
+
     $clean_html = $purifier->purify($dirty_html);
 ?>
 
+    vim: et sw=4 sts=4

INSTALL.fr.utf8

@@ -17,10 +17,10 @@ ce document pour quelques choses.
 
 1.  Compatibilité
 
-HTML Purifier fonctionne dans PHP 4 et PHP 5. PHP 4.3.2 est le dernier
+HTML Purifier fonctionne dans PHP 5. PHP 5.0.5 est le dernier
 version que je le testais.  Il ne dépend de les autre librairies.
 
-Les extensions optionnel est iconv (en général déjà installer) et 
+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.
 
@@ -34,25 +34,21 @@ Utilisez:
 ...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:
+HTML Purifier utilise 'autoload'. Si vous avez définu la fonction
+__autoload, vous doivez ajoute cet programme:
 
-    require_once 'HTMLPurifier.php';
+    spl_autoload_register('__autoload')
 
-Seuleument les contents dans library/ est essentiel; vous peut enlever
-les autre fichiers quand vous est dans une atmosphère professionnel.
+Plus d'information est dans le document 'INSTALL'.
 
 
-[En cours de construction]
-
-
-6.   Installation vite
+3.   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);
 ?>
@@ -61,11 +57,13 @@ 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);
-?>
+?>
+
+    vim: et sw=4 sts=4

LICENSE

@@ -146,7 +146,7 @@ such a program is covered only if its contents constitute a work based
 on the Library (independent of the use of the Library in a tool for
 writing it).  Whether that is true depends on what the Library does
 and what the program that uses the Library does.
-  
+
   1. You may copy and distribute verbatim copies of the Library's
 complete source code as you receive it, in any medium, provided that
 you conspicuously and appropriately publish on each copy an
@@ -501,4 +501,4 @@ necessary.  Here is a sample; alter the names:
 
 That's all there is to it!
 
-
+    vim: et sw=4 sts=4

NEWS

@@ -9,13 +9,354 @@ NEWS ( CHANGELOG and HISTORY )                                     HTMLPurifier
     . Internal change
 ==========================
 
+3.3.0, released 2009-02-16
+! Implement CSS property 'overflow' when %CSS.AllowTricky is true.
+! Implement generic property list classess
+- Fix bug with testEncodingSupportsASCII() algorithm when iconv() implementation
+  does not do the "right thing" with characters not supported in the output
+  set.
+- Spellcheck UTF-8: The Secret To Character Encoding
+- Fix improper removal of the contents of elements with only whitespace. Thanks
+  Eric Wald for reporting.
+- Fix broken test suite in versions of PHP without spl_autoload_register()
+- Fix degenerate case with YouTube filter involving double hyphens.
+  Thanks Pierre Attar for reporting.
+- Fix YouTube rendering problem on certain versions of Firefox.
+- Fix CSSDefinition Printer problems with decorators
+- Add text parameter to unit tests, forces text output
+. Add verbose mode to command line test runner, use (--verbose)
+. Turn on unit tests for UnitConverter
+. Fix missing version number in configuration %Attr.DefaultImageAlt (added 3.2.0)
+. Fix newline errors that caused spurious failures when CRLF HTML Purifier was
+  tested on Linux.
+. Removed trailing whitespace from all text files, see
+  remote-trailing-whitespace.php maintenance script.
+. Convert configuration to use property list backend.
+
+3.2.0, released 2008-10-31
+# Using %Core.CollectErrors forces line number/column tracking on, whereas
+  previously you could theoretically turn it off.
+# HTMLPurifier_Injector->notifyEnd() is formally deprecated. Please
+  use handleEnd() instead.
+! %Output.AttrSort for when you need your attributes in alphabetical order to
+  deal with a bug in FCKEditor. Requested by frank farmer.
+! Enable HTML comments when %HTML.Trusted is on. Requested by Waldo Jaquith.
+! Proper support for name attribute. It is now allowed and equivalent to the id
+  attribute in a and img tags, and is only converted to id when %HTML.TidyLevel
+  is heavy (for all doctypes).
+! %AutoFormat.RemoveEmpty to remove some empty tags from documents. Please don't
+  use on hand-written HTML.
+! Add error-cases for unsupported elements in MakeWellFormed. This enables
+  the strategy to be used, standalone, on untrusted input.
+! %Core.AggressivelyFixLt is on by default. This causes more sensible
+  processing of left angled brackets in smileys and other whatnot.
+! Test scripts now have a 'type' parameter, which lets you say 'htmlpurifier',
+  'phpt', 'vtest', etc. in order to only execute those tests. This supercedes
+  the --only-phpt parameter, although for backwards-compatibility the flag
+  will still work.
+! AutoParagraph auto-formatter will now preserve double-newlines upon output.
+  Users who are not performing inbound filtering, this may seem a little
+  useless, but as a bonus, the test suite and handling of edge cases is also
+  improved.
+! Experimental implementation of forms for %HTML.Trusted
+! Track column numbers when maintain line numbers is on
+! Proprietary 'background' attribute on table-related elements converted into
+  corresponding CSS.  Thanks Fusemail for sponsoring this feature!
+! Add forward(), forwardUntilEndToken(), backward() and current() to Injector
+  supertype.
+! HTMLPurifier_Injector->handleEnd() permits modification to end tokens. The
+  time of operation varies slightly from notifyEnd() as *all* end tokens are
+  processed by the injector before they are subject to the well-formedness rules.
+! %Attr.DefaultImageAlt allows overriding default behavior of setting alt to
+  basename of image when not present.
+! %AutoFormat.DisplayLinkURI neuters <a> tags into plain text URLs.
+- Fix two bugs in %URI.MakeAbsolute; one involving empty paths in base URLs,
+  the other involving an undefined $is_folder error.
+- Throw error when %Core.Encoding is set to a spurious value. Previously,
+  this errored silently and returned false.
+- Redirected stderr to stdout for flush error output.
+- %URI.DisableExternal will now use the host in %URI.Base if %URI.Host is not
+  available.
+- Do not re-munge URL if the output URL has the same host as the input URL.
+  Requested by Chris.
+- Fix error in documentation regarding %Filter.ExtractStyleBlocks
+- Prevent <![CDATA[<body></body>]]> from triggering %Core.ConvertDocumentToFragment
+- Fix bug with inline elements in blockquotes conflicting with strict doctype
+- Detect if HTML support is disabled for DOM by checking for loadHTML() method.
+- Fix bug where dots and double-dots in absolute URLs without hostname were
+  not collapsed by URIFilter_MakeAbsolute.
+- Fix bug with anonymous modules operating on SafeEmbed or SafeObject elements
+  by reordering their addition.
+- Will now throw exception on many error conditions during lexer creation; also
+  throw an exception when MaintainLineNumbers is true, but a non-tracksLineNumbers
+  is being used.
+- Detect if domxml extension is loaded, and use DirectLEx accordingly.
+- Improve handling of big numbers with floating point arithmetic in UnitConverter.
+  Reported by David Morton.
+. Strategy_MakeWellFormed now operates in-place, saving memory and allowing
+  for more interesting filter-backtracking
+. New HTMLPurifier_Injector->rewind() functionality, allows injectors to rewind
+  index to reprocess tokens.
+. StringHashParser now allows for multiline sections with "empty" content;
+  previously the section would remain undefined.
+. Added --quick option to multitest.php, which tests only the most recent
+  release for each series.
+. Added --distro option to multitest.php, which accepts either 'normal' or
+  'standalone'. This supercedes --exclude-normal and --exclude-standalone
+
+3.1.1, released 2008-06-19
+# %URI.Munge now, by default, does not munge resources (for example, <img src="">)
+  In order to enable this again, please set %URI.MungeResources to true.
+! More robust imagecrash protection with height/width CSS with %CSS.MaxImgLength,
+  and height/width HTML with %HTML.MaxImgLength.
+! %URI.MungeSecretKey for secure URI munging. Thanks Chris
+  for sponsoring this feature. Check out the corresponding documentation
+  for details. (Att Nightly testers: The API for this feature changed before
+  the general release. Namely, rename your directives %URI.SecureMungeSecretKey =>
+  %URI.MungeSecretKey and and %URI.SecureMunge => %URI.Munge)
+! Implemented post URI filtering. Set member variable $post to true to set
+  a URIFilter as such.
+! Allow modules to define injectors via $info_injector. Injectors are
+  automatically disabled if injector's needed elements are not found.
+! Support for "safe" objects added, use %HTML.SafeObject and %HTML.SafeEmbed.
+  Thanks Chris for sponsoring. If you've been using ad hoc code from the
+  forums, PLEASE use this instead.
+! Added substitutions for %e, %n, %a and %p in %URI.Munge (in order,
+  embedded, tag name, attribute name, CSS property name). See %URI.Munge
+  for more details. Requested by Jochem Blok.
+- Disable percent height/width attributes for img.
+- AttrValidator operations are now atomic; updates to attributes are not
+  manifest in token until end of operations. This prevents naughty internal
+  code from directly modifying CurrentToken when they're not supposed to.
+  This semantics change was requested by frank farmer.
+- Percent encoding checks enabled for URI query and fragment
+- Fix stray backslashes in font-family; CSS Unicode character escapes are
+  now properly resolved (although *only* in font-family). Thanks Takeshi Terada
+  for reporting.
+- Improve parseCDATA algorithm to take into account newline normalization
+- Account for browser confusion between Yen character and backslash in
+  Shift_JIS encoding. This fix generalizes to any other encoding which is not
+  a strict superset of printable ASCII. Thanks Takeshi Terada for reporting.
+- Fix missing configuration parameter in Generator calls. Thanks vs for the
+  partial patch.
+- Improved adherence to Unicode by checking for non-character codepoints.
+  Thanks Geoffrey Sneddon for reporting. This may result in degraded
+  performance for extremely large inputs.
+- Allow CSS property-value pair ''text-decoration: none''. Thanks Jochem Blok
+  for reporting.
+. Added HTMLPurifier_UnitConverter and HTMLPurifier_Length for convenient
+  handling of CSS-style lengths. HTMLPurifier_AttrDef_CSS_Length now uses
+  this class.
+. API of HTMLPurifier_AttrDef_CSS_Length changed from __construct($disable_negative)
+  to __construct($min, $max). __construct(true) is equivalent to
+  __construct('0').
+. Added HTMLPurifier_AttrDef_Switch class
+. Rename HTMLPurifier_HTMLModule_Tidy->construct() to setup() and bubble method
+  up inheritance hierarchy to HTMLPurifier_HTMLModule. All HTMLModules
+  get this called with the configuration object.  All modules now
+  use this rather than __construct(), although legacy code using constructors
+  will still work--the new format, however, lets modules access the
+  configuration object for HTML namespace dependant tweaks.
+. AttrDef_HTML_Pixels now takes a single construction parameter, pixels.
+. ConfigSchema data-structure heavily optimized; on average it uses a third
+  the memory it did previously. The interface has changed accordingly,
+  consult changes to HTMLPurifier_Config for details.
+. Variable parsing types now are magic integers instead of strings
+. Added benchmark for ConfigSchema
+. HTMLPurifier_Generator requires $config and $context parameters. If you
+  don't know what they should be, use HTMLPurifier_Config::createDefault()
+  and new HTMLPurifier_Context().
+. Printers now properly distinguish between output configuration, and
+  target configuration. This is not applicable to scripts using
+  the Printers for HTML Purifier related tasks.
+. HTML/CSS Printers must be primed with prepareGenerator($gen_config), otherwise
+  fatal errors will ensue.
+. URIFilter->prepare can return false in order to abort loading of the filter
+. Factory for AttrDef_URI implemented, URI#embedded to indicate URI that embeds
+  an external resource.
+. %URI.Munge functionality factored out into a post-filter class.
+. Added CurrentCSSProperty context variable during CSS validation
+
+3.1.0, released 2008-05-18
+# Unnecessary references to objects (vestiges of PHP4) removed from method
+  signatures.  The following methods do not need references when assigning from
+  them and will result in E_STRICT errors if you try:
+    + HTMLPurifier_Config->get*Definition() [* = HTML, CSS]
+    + HTMLPurifier_ConfigSchema::instance()
+    + HTMLPurifier_DefinitionCacheFactory::instance()
+    + HTMLPurifier_DefinitionCacheFactory->create()
+    + HTMLPurifier_DoctypeRegistry->register()
+    + HTMLPurifier_DoctypeRegistry->get()
+    + HTMLPurifier_HTMLModule->addElement()
+    + HTMLPurifier_HTMLModule->addBlankElement()
+    + HTMLPurifier_LanguageFactory::instance()
+# Printer_ConfigForm's get*() functions were static-ified
+# %HTML.ForbiddenAttributes requires attribute declarations to be in the
+  form of tag@attr, NOT tag.attr (which will throw an error and won't do
+  anything). This is for forwards compatibility with XML; you'd do best
+  to migrate an %HTML.AllowedAttributes directives to this syntax too.
+! Allow index to be false for config from form creation
+! Added HTMLPurifier::VERSION constant
+! Commas, not dashes, used for serializer IDs. This change is forwards-compatible
+  and allows for version numbers like "3.1.0-dev".
+! %HTML.Allowed deals gracefully with whitespace anywhere, anytime!
+! HTML Purifier's URI handling is a lot more robust, with much stricter
+  validation checks and better percent encoding handling. Thanks Gareth Heyes
+  for indicating security vulnerabilities from lax percent encoding.
+! Bootstrap autoloader deals more robustly with classes that don't exist,
+  preventing class_exists($class, true) from barfing.
+- InterchangeBuilder now alphabetizes its lists
+- Validation error in configdoc output fixed
+- Iconv and other encoding errors muted even with custom error handlers that
+  do not honor error_reporting
+- Add protection against imagecrash attack with CSS height/width
+- HTMLPurifier::instance() created for consistency, is equivalent to getInstance()
+- Fixed and revamped broken ConfigForm smoketest
+- Bug with bool/null fields in Printer_ConfigForm fixed
+- Bug with global forbidden attributes fixed
+- Improved error messages for allowed and forbidden HTML elements and attributes
+- Missing (or null) in configdoc documentation restored
+- If DOM throws and exception during parsing with PH5P (occurs in newer versions
+  of DOM), HTML Purifier punts to DirectLex
+- Fatal error with unserialization of ScriptRequired
+- Created directories are now chmod'ed properly
+- Fixed bug with fallback languages in LanguageFactory
+- Standalone testing setup properly with autoload
+. Out-of-date documentation revised
+. UTF-8 encoding check optimization as suggested by Diego
+. HTMLPurifier_Error removed in favor of exceptions
+. More copy() function removed; should use clone instead
+. More extensive unit tests for HTMLDefinition
+. assertPurification moved to central harness
+. HTMLPurifier_Generator accepts $config and $context parameters during
+  instantiation, not runtime
+. Double-quotes outside of attribute values are now unescaped
+
+3.1.0rc1, released 2008-04-22
+# Autoload support added. Internal require_once's removed in favor of an
+  explicit require list or autoloading. To use HTML Purifier,
+  you must now either use HTMLPurifier.auto.php
+  or HTMLPurifier.includes.php; setting the include path and including
+  HTMLPurifier.php is insufficient--in such cases include HTMLPurifier.autoload.php
+  as well to register our autoload handler (or modify your autoload function
+  to check HTMLPurifier_Bootstrap::getPath($class)). You can also use
+  HTMLPurifier.safe-includes.php for a less performance friendly but more
+  user-friendly library load.
+# HTMLPurifier_ConfigSchema static functions are officially deprecated. Schema
+  information is stored in the ConfigSchema directory, and the
+  maintenance/generate-schema-cache.php generates the schema.ser file, which
+  is now instantiated. Support for userland schema changes coming soon!
+# HTMLPurifier_Config will now throw E_USER_NOTICE when you use a directive
+  alias; to get rid of these errors just modify your configuration to use
+  the new directive name.
+# HTMLPurifier->addFilter is deprecated; built-in filters can now be
+  enabled using %Filter.$filter_name or by setting your own filters using
+  %Filter.Custom
+# Directive-level safety properties superceded in favor of module-level
+  safety. Internal method HTMLModule->addElement() has changed, although
+  the externally visible HTMLDefinition->addElement has *not* changed.
+! Extra utility classes for testing and non-library operations can
+  be found in extras/. Specifically, these are FSTools and ConfigDoc.
+  You may find a use for these in your own project, but right now they
+  are highly experimental and volatile.
+! Integration with PHPT allows for automated smoketests
+! Limited support for proprietary HTML elements, namely <marquee>, sponsored
+  by Chris. You can enable them with %HTML.Proprietary if your client
+  demands them.
+! Support for !important CSS cascade modifier. By default, this will be stripped
+  from CSS, but you can enable it using %CSS.AllowImportant
+! Support for display and visibility CSS properties added, set %CSS.AllowTricky
+  to true to use them.
+! HTML Purifier now has its own Exception hierarchy under HTMLPurifier_Exception.
+  Developer error (not enduser error) can cause these to be triggered.
+! Experimental kses() wrapper introduced with HTMLPurifier.kses.php
+! Finally %CSS.AllowedProperties for tweaking allowed CSS properties without
+  mucking around with HTMLPurifier_CSSDefinition
+! ConfigDoc output has been enhanced with version and deprecation info.
+! %HTML.ForbiddenAttributes and %HTML.ForbiddenElements implemented.
+- Autoclose now operates iteratively, i.e. <span><span><div> now has
+  both span tags closed.
+- Various HTMLPurifier_Config convenience functions now accept another parameter
+  $schema which defines what HTMLPurifier_ConfigSchema to use besides the
+  global default.
+- Fix bug with trusted script handling in libxml versions later than 2.6.28.
+- Fix bug in ExtractStyleBlocks with comments in style tags
+- Fix bug in comment parsing for DirectLex
+- Flush output now displayed when in command line mode for unit tester
+- Fix bug with rgb(0, 1, 2) color syntax with spaces inside shorthand syntax
+- HTMLPurifier_HTMLDefinition->addAttribute can now be called multiple times
+  on the same element without emitting errors.
+- Fixed fatal error in PH5P lexer with invalid tag names
+. Plugins now get their own changelogs according to project conventions.
+. Convert tokens to use instanceof, reducing memory footprint and
+  improving comparison speed.
+. Dry runs now supported in SimpleTest; testing facilities improved
+. Bootstrap class added for handling autoloading functionality
+. Implemented recursive glob at FSTools->globr
+. ConfigSchema now has instance methods for all corresponding define*
+  static methods.
+. A couple of new historical maintenance scripts were added.
+. HTMLPurifier/HTMLModule/Tidy/XHTMLAndHTML4.php split into two files
+. tests/index.php can now be run from any directory.
+. HTMLPurifier_Token subclasses split into seperate files
+. HTMLPURIFIER_PREFIX now is defined in Bootstrap.php, NOT HTMLPurifier.php
+. HTMLPURIFIER_PREFIX can now be defined outside of HTML Purifier
+. New --php=php flag added, allows PHP executable to be specified (command
+  line only!)
+. htmlpurifier_add_test() preferred method to translate test files in to
+  classes, because it handles PHPT files too.
+. Debugger class is deprecated and will be removed soon.
+. Command line argument parsing for testing scripts revamped, now --opt value
+  format is supported.
+. Smoketests now cleanup after magic quotes
+. Generator now can output comments (however, comments are still stripped
+  from HTML Purifier output)
+. HTMLPurifier_ConfigSchema->validate() deprecated in favor of
+  HTMLPurifier_VarParser->parse()
+. Integers auto-cast into float type by VarParser.
+. HTMLPURIFIER_STRICT removed; no validation is performed on runtime, only
+  during cache generation
+. Reordered script calls in maintenance/flush.php
+. Command line scripts now honor exit codes
+. When --flush fails in unit testers, abort tests and print message
+. Improved documentation in docs/dev-flush.html about the maintenance scripts
+. copy() methods removed in favor of clone keyword
+
+3.0.0, released 2008-01-06
+# HTML Purifier is PHP 5 only! The 2.1.x branch will be maintained
+  until PHP 4 is completely deprecated, but no new features will be added
+  to it.
+  + Visibility declarations added
+  + Constructor methods renamed to __construct()
+  + PHP4 reference cruft removed (in progress)
+! CSS properties are now case-insensitive
+! DefinitionCacheFactory now can register new implementations
+! New HTMLPurifier_Filter_ExtractStyleBlocks for extracting <style> from
+  documents and cleaning their contents up. Requires the CSSTidy library
+  <http://csstidy.sourceforge.net/>. You can access the blocks with the
+  'StyleBlocks' Context variable ($purifier->context->get('StyleBlocks')).
+  The output CSS can also be "scoped" for a specific element, use:
+  %Filter.ExtractStyleBlocksScope
+! Experimental support for some proprietary CSS attributes allowed:
+  opacity (and all of the browser-specific equivalents) and scrollbar colors.
+  Enable by setting %CSS.Proprietary to true.
+- Colors missing # but in hex form will be corrected
+- CSS Number algorithm improved
+- Unit testing and multi-testing now on steroids: command lines,
+  XML output, and other goodies now added.
+. Unit tests for Injector improved
+. New classes:
+  + HTMLPurifier_AttrDef_CSS_AlphaValue
+  + HTMLPurifier_AttrDef_CSS_Filter
+. Multitest now has a file docblock
+
 2.1.3, released 2007-11-05
 ! tests/multitest.php allows you to test multiple versions by running
   tests/index.php through multiple interpreters using `phpv` shell
   script (you must provide this script!)
 - Fixed poor include ordering for Email URI AttrDefs, causes fatal errors
   on some systems.
-- Injector algorithm further refined: off-by-one error regarding skip 
+- Injector algorithm further refined: off-by-one error regarding skip
   counts for dormant injectors fixed
 - Corrective blockquote definition now enabled for HTML 4.01 Strict
 - Fatal error when <img> tag (or any other element with required attributes)
@@ -40,7 +381,7 @@ NEWS ( CHANGELOG and HISTORY )                                     HTMLPurifier
   facilities in PHP 5
 - Make ErrorCollectorEMock work in both PHP 4 and PHP 5
 - Make PH5P work with PHP 5.0 by removing unnecessary array parameter typedef
-. %Core.AcceptFullDocuments renamed to %Core.ConvertDocumentToFragment 
+. %Core.AcceptFullDocuments renamed to %Core.ConvertDocumentToFragment
   to better communicate its purpose
 . Error unit tests can now specify the expectation of no errors. Future
   iterations of the harness will be extremely strict about what errors
@@ -199,7 +540,7 @@ NEWS ( CHANGELOG and HISTORY )                                     HTMLPurifier
   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 
+  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()
@@ -283,7 +624,7 @@ NEWS ( CHANGELOG and HISTORY )                                     HTMLPurifier
   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
@@ -497,3 +838,5 @@ NEWS ( CHANGELOG and HISTORY )                                     HTMLPurifier
   + Shorthand CSS properties
   + Table CSS properties
   + Deprecated attribute transformations
+
+    vim: et sw=4 sts=4

README

@@ -2,15 +2,15 @@
 README
     All about HTML Purifier
 
-HTML Purifier is an HTML filtering solution that uses a unique combination 
-of robust whitelists and agressive parsing to ensure that not only are 
-XSS attacks thwarted, but the resulting HTML is standards compliant. 
+HTML Purifier is an HTML filtering solution that uses a unique combination
+of robust whitelists and agressive parsing to ensure that not only are
+XSS attacks thwarted, but the resulting HTML is standards compliant.
 
-HTML Purifier is oriented towards richly formatted documents from 
-untrusted sources that require CSS and a full tag-set.  This library can 
-be configured to accept a more restrictive set of tags, but it won't be 
-as efficient as more bare-bones parsers. It will, however, do the job 
-right, which may be more important. 
+HTML Purifier is oriented towards richly formatted documents from
+untrusted sources that require CSS and a full tag-set.  This library can
+be configured to accept a more restrictive set of tags, but it won't be
+as efficient as more bare-bones parsers. It will, however, do the job
+right, which may be more important.
 
 Places to go:
 
@@ -20,3 +20,5 @@ Places to go:
 * See WYSIWYG for information on editors like TinyMCE and FCKeditor
 
 HTML Purifier can be found on the web at: http://htmlpurifier.org/
+
+    vim: et sw=4 sts=4

TODO

@@ -7,83 +7,125 @@ TODO List
     ? Maybe I'll Do It
 ==========================
 
-If no interest is expressed for a feature that may required a considerable
+If no interest is expressed for a feature that may require a considerable
 amount of effort to implement, it may get endlessly delayed. Do not be
 afraid to cast your vote for the next feature to be implemented!
 
-2.2 release [Error'ed]
- # Error logging for filtering/cleanup procedures
- - XSS-attempt detection
+- Investigate how early internal structures can be accessed; this would
+  prevent structures from being parsed and serialized multiple times.
+- Built-in support for target="_blank" on all external links
+- Allow <a id="asdf" name="asdf">
+- Convert configuration to allow an arbitrary number of namespaces;
+  then rename as appropriate.
 
-2.3 release [Do What I Mean, Not What I Say]
+FUTURE VERSIONS
+---------------
+
+4.1 release [It's All About Trust] (floating)
+ # Implement untrusted, dangerous elements/attributes
+ # Implement IDREF support (harder than it seems, since you cannot have
+   IDREFs to non-existent IDs)
+ # Frameset XHTML 1.0 and HTML 4.01 doctypes
+ - Implement <area>
+ - Figure out how to simultaneously set %CSS.Trusted and %HTML.Trusted (?)
+
+4.2 release [Error'ed]
+ # Error logging for filtering/cleanup procedures
+ - XSS-attempt detection--certain errors are flagged XSS-like
+
+4.3 release [Do What I Mean, Not What I Say]
  # Additional support for poorly written HTML
     - Microsoft Word HTML cleaning (i.e. MsoNormal, but research essential!)
     - Friendly strict handling of <address> (block -> <br>)
- - Remove redundant tags, ex. <u><u>Underlined</u></u>. Implementation notes:
+ ? Remove redundant tags, ex. <u><u>Underlined</u></u>. Implementation notes:
     1. Analyzing which tags to remove duplicants
     2. Ensure attributes are merged into the parent tag
     3. Extend the tag exclusion system to specify whether or not the
     contents should be dropped or not (currently, there's code that could do
     something like this if it didn't drop the inner text too.)
  - Remove <span> tags that don't do anything (no attributes)
- - 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
+ - Externalize inline CSS to promote clean HTML, proposed by Sander Tekelenburg
 
-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]
+5.0 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
+   AttrDef class). Probably will use CSSTidy class?
+ # More control over allowed CSS properties using a modularization
+ # HTML 5 support
+ # IRI support (this includes IDN)
  - Standardize token armor for all areas of processing
  - Convert RTL/LTR override characters to <bdo> tags, or vice versa on demand.
    Also, enable disabling of directionality
 
-4.0 release [To XML and Beyond]
+6.0 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!
+ - More refactoring to take advantage of PHP5's facilities
+ - Refactor unit tests into lots of test methods
  - Plugins for major CMSes (COMPLEX)
     - phpBB
-    - eFiction
+    - Drupal needs loving!
+    - Phorum need loving!
     - more! (look for ones that use WYSIWYGs)
- - Complete basic smoketests
+    - Also, maybe a FAQ for extension writers with HTML Purifier
 
-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!)
+AutoFormat
+ - Smileys
+ - Syntax highlighting (with GeSHi) with <pre> and possibly <?php
+ - Look at http://drupal.org/project/Modules/category/63 for ideas
+
+Optimizations
+ - Reduce size of internal data-structures (esp. HTMLDefinition)
+ - Research memory usage of objects versus arrays
+ - Combine multiple strategies into a single, single-pass strategy
+ - Get PH5P working with the latest versions of DOM, which have much more
+   stringent error checking procedures. Maybe convert straight to tokens.
+ - Get rid of set_include_path(). Save this for another major release.
+
+Neat feature related
+ ! Factor demo.php into a set of Printer classes, and then create a stub
+   file for users here (inside the actual HTML Purifier library)
+ ! Support exporting configuration, so users can easily tweak settings
+   in the demo, and then copy-paste into their own setup
  - Advanced URI filtering schemes (see docs/proposal-new-directives.txt)
- - Implement lenient <ruby> child validation
+ - Allow scoped="scoped" attribute in <style> tags; may be troublesome
+   because regular CSS has no way of uniquely identifying nodes, so we'd
+   have to generate IDs
  - Explain how to use HTML Purifier in non-PHP languages / create
    a simple command line stub (or complicated?)
  - Fixes for Firefox's inability to handle COL alignment props (Bug 915)
  - Automatically add non-breaking spaces to empty table cells when
    empty-cells:show is applied to have compatibility with Internet Explorer
+ - Table of Contents generation (XHTML Compiler might be reusable). May also
+   be out-of-band information.
+ - Full set of color keywords. Also, a way to add onto them without
+   finalizing the configuration object.
+ - Write a var_export and memcached DefinitionCache - Denis
+ - Allow restriction of allowed class values
 
-Requested
+Maintenance related (slightly boring)
+ # CHMOD install script for PEAR installs
+ ! Factor out command line parser into its own class, and unit test it
+ ! Nested configuration namespaces
+ - Distinguish between default settings and explicitly set settings, so
+   configurations can be merged
+ - Time PHPT tests
+
+ChildDef related (very boring)
+ - Abstract ChildDef_BlockQuote to work with all elements that only
+   allow blocks in them, required or optional
+ - Implement lenient <ruby> child validation
 
 Wontfix
  - Non-lossy smart alternate character encoding transformations (unless
    patch provided)
  - Pretty-printing HTML: users can use Tidy on the output on entire page
- - Native content compression, whitespace stripping (don't rely on Tidy, make
-   sure we don't remove from <pre> or related tags): use gzip if this is
+ - Native content compression, whitespace stripping: use gzip if this is
    really important
+
+    vim: et sw=4 sts=4

VERSION

@@ -1 +1 @@
-2.1.3
+3.3.0

WHATSNEW

@@ -1,6 +1,6 @@
-Stability release 2.1.3 fixes a slew of minor bugs found in HTML Purifier,
-and also includes some internal code enhancements and refactorings.
-Notably, tests/multitest.php automates testing in multiple versions, 
-fatal AttrDef_URI_Email error fixed, blockquote contents are more lenient
-in HTML 4.01 Strict and fatal errors involving ID tags in img tags were
-fixed.
+HTML Purifier 3.3.0 is fixes a number of obscure bugs reported and fixed
+over a four month period.  It is probably the last release in the 3.x
+series.  Notable new features include support for the overflow CSS
+property; notable bugfixes include fixed YouTube rendering in certain
+versions of Firefox, CSSDefinition Printer, improved early PHP support
+and bugs in iconv.

WYSIWYG

@@ -16,3 +16,5 @@ trouble.  Therein lies the solution:
 HTML Purifier is perfect for filtering pure-HTML input from WYSIWYG editors.
 
 Enough said.
+
+    vim: et sw=4 sts=4

benchmarks/ConfigSchema.php

@@ -0,0 +1,16 @@
+<?php
+
+chdir(dirname(__FILE__));
+
+//require_once '../library/HTMLPurifier.path.php';
+shell_exec('php ../maintenance/generate-schema-cache.php');
+require_once '../library/HTMLPurifier.path.php';
+require_once 'HTMLPurifier.includes.php';
+
+$begin = xdebug_memory_usage();
+
+$schema = HTMLPurifier_ConfigSchema::makeFromSerial();
+
+echo xdebug_memory_usage() - $begin;
+
+// vim: et sw=4 sts=4

benchmarks/Lexer.php

@@ -1,82 +1,69 @@
 <?php
 
-// emulates inserting a dir called HTMLPurifier into your class dir
-set_include_path(get_include_path() . PATH_SEPARATOR . '../library/');
-
+require_once '../library/HTMLPurifier.auto.php';
 @include_once '../test-settings.php';
 
-require_once 'HTMLPurifier/ConfigSchema.php';
-require_once 'HTMLPurifier/Config.php';
-require_once 'HTMLPurifier/Context.php';
+// PEAR
+require_once 'Benchmark/Timer.php'; // to do the timing
+require_once 'Text/Password.php'; // for generating random input
 
 $LEXERS = array();
 $RUNS = isset($GLOBALS['HTMLPurifierTest']['Runs'])
-    ? $GLOBALS['HTMLPurifierTest']['Runs'] : 2; 
+    ? $GLOBALS['HTMLPurifierTest']['Runs'] : 2;
 
 require_once 'HTMLPurifier/Lexer/DirectLex.php';
 $LEXERS['DirectLex'] = new HTMLPurifier_Lexer_DirectLex();
 
-if (!empty($GLOBALS['HTMLPurifierTest']['PEAR'])) {
-    require_once 'HTMLPurifier/Lexer/PEARSax3.php';
-    $LEXERS['PEARSax3'] = new HTMLPurifier_Lexer_PEARSax3();
-} else {
-    exit('PEAR required to perform benchmark.');
-}
-
 if (version_compare(PHP_VERSION, '5', '>=')) {
     require_once 'HTMLPurifier/Lexer/DOMLex.php';
     $LEXERS['DOMLex'] = new HTMLPurifier_Lexer_DOMLex();
 }
 
-// PEAR
-require_once 'Benchmark/Timer.php'; // to do the timing
-require_once 'Text/Password.php'; // for generating random input
-
 // custom class to aid unit testing
 class RowTimer extends Benchmark_Timer
 {
-    
+
     var $name;
-    
+
     function RowTimer($name, $auto = false) {
         $this->name = htmlentities($name);
         $this->Benchmark_Timer($auto);
     }
-    
+
     function getOutput() {
 
         $total  = $this->TimeElapsed();
         $result = $this->getProfiling();
         $dashes = '';
-        
+
         $out = '<tr>';
-        
+
         $out .= "<td>{$this->name}</td>";
-        
+
         $standard = false;
-        
+
         foreach ($result as $k => $v) {
             if ($v['name'] == 'Start' || $v['name'] == 'Stop') continue;
-            
+
             //$perc = (($v['diff'] * 100) / $total);
             //$tperc = (($v['total'] * 100) / $total);
-            
+
             //$out .= '<td align="right">' . $v['diff'] . '</td>';
-            
+
             if ($standard == false) $standard = $v['diff'];
-            
+
             $perc = $v['diff'] * 100 / $standard;
             $bad_run = ($v['diff'] < 0);
-            
+
             $out .= '<td align="right"'.
                    ($bad_run ? ' style="color:#AAA;"' : '').
                    '>' . number_format($perc, 2, '.', '') .
                    '%</td><td>'.number_format($v['diff'],4,'.','').'</td>';
-            
+
         }
-        
+
         $out .= '</tr>';
-        
+
         return $out;
     }
 }
@@ -93,18 +80,18 @@ 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, $config, $context);
         $timer->setMarker($key);
     }
-    
+
     $timer->stop();
     $timer->display();
 }
@@ -131,11 +118,11 @@ foreach ($LEXERS as $key => $value) {
 $dir = 'samples/Lexer';
 $dh  = opendir($dir);
 while (false !== ($filename = readdir($dh))) {
-    
+
     if (strpos($filename, '.html') !== strlen($filename) - 5) continue;
     $document = file_get_contents($dir . '/' . $filename);
     do_benchmark("File: $filename", $document);
-    
+
 }
 
 // crashers, caused infinite loops before
@@ -166,3 +153,6 @@ echo '<div>Random input was: ' .
 
 
 </body></html>
+<?php
+
+// vim: et sw=4 sts=4

benchmarks/ProfileDirectLex.php

@@ -1,17 +0,0 @@
-<?php
-
-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, $config, $context);
-}

benchmarks/Trace.php

@@ -3,6 +3,11 @@
 ini_set('xdebug.trace_format', 1);
 ini_set('xdebug.show_mem_delta', true);
 
+if (file_exists('Trace.xt')) {
+    echo "Previous trace Trace.xt must be removed before this script can be run.";
+    exit;
+}
+
 xdebug_start_trace(dirname(__FILE__) . '/Trace');
 require_once '../library/HTMLPurifier.auto.php';
 
@@ -10,3 +15,7 @@ $purifier = new HTMLPurifier();
 
 $data = $purifier->purify(file_get_contents('samples/Lexer/4.html'));
 xdebug_stop_trace();
+
+echo "Trace finished.";
+
+// vim: et sw=4 sts=4

benchmarks/samples/Lexer/1.html

@@ -28,7 +28,7 @@
 
  <li>HX Edison Taiji Club <a href="http://www.taijiclub.org/downloads/Taiji_club_regulation_.pdf">by-law</a>  effective 3/28/2006</li>
  <li>A new email account for our club: HXEdisontaijiclub@yahoo.com</li>
- 
+
  <li>Workshop conducted by <a href="http://www.taijiclub.org/ch/Digest/LiDeyin">?????</a> Li Deyin is set on June 4, 2006 at Clarion Hotel in Edison from 9:30am-12pm; <a href="http://www.taijiclub.org/en/Registration">Registration</a></li>
 
 </ul>
@@ -36,7 +36,7 @@
 
 
 
-<p><i>Taiji</i> is an ancient Chinese tradition of movement systems that is associated with philosophy, physiology, psychology, geometry and dynamics. It is the slowest form of martial arts and is meant to improve the internal spirit.   It is soothing to the soul and extremely invigorating. </p> 
+<p><i>Taiji</i> is an ancient Chinese tradition of movement systems that is associated with philosophy, physiology, psychology, geometry and dynamics. It is the slowest form of martial arts and is meant to improve the internal spirit.   It is soothing to the soul and extremely invigorating. </p>
 
 <p>The founder of Taiji was Zhang Sanfeng (Chang San-feng), who was a monk of the Wu Dang (Wu Tang) Monastery and lived in the period from 1391 to 1459. His exercises stressed suppleness and elasticity as opposed to the hardness and force of other martial art styles. Several centuries old, Taiji was originally developed as a form of self-defense, emphasizing strength, balance, flexibility and speed. Tai Chi also differs from other martial arts in that it is based on the Taoist religion and aims to avoid aggressive forces. </p>
 
@@ -50,4 +50,6 @@
 
 <div style="text-align:center;">Click on photo to see HR version</div></div>
 </body>
-</html>
+</html>
+
+<!-- vim: et sw=4 sts=4 -->

benchmarks/samples/Lexer/2.html

@@ -14,4 +14,6 @@ function rwt(el,ct,cd,sg){var e = window.encodeURIComponent ? encodeURIComponent
 <form action=/search name=f><script><!--
 function qs(el) {if (window.RegExp && window.encodeURIComponent) {var ue=el.href;var qe=encodeURIComponent(document.f.q.value);if(ue.indexOf("q=")!=-1){el.href=ue.replace(new RegExp("q=[^&$]*"),"q="+qe);}else{el.href=ue+"&q="+qe;}}return 1;}
 // -->
-</script><table border=0 cellspacing=0 cellpadding=4><tr><td nowrap><font size=-1><b>Web</b>&nbsp;&nbsp;&nbsp;&nbsp;<a id=1a class=q href="/imghp?hl=en&tab=wi" onClick="return qs(this);">Images</a>&nbsp;&nbsp;&nbsp;&nbsp;<a id=2a class=q href="http://groups.google.com/grphp?hl=en&tab=wg" onClick="return qs(this);">Groups</a>&nbsp;&nbsp;&nbsp;&nbsp;<a id=4a class=q href="http://news.google.com/nwshp?hl=en&tab=wn" onClick="return qs(this);">News</a>&nbsp;&nbsp;&nbsp;&nbsp;<a id=5a class=q href="http://froogle.google.com/frghp?hl=en&tab=wf" onClick="return qs(this);">Froogle</a>&nbsp;&nbsp;&nbsp;&nbsp;<a id=8a class=q href="/lochp?hl=en&tab=wl" onClick="return qs(this);">Local</a>&nbsp;&nbsp;&nbsp;&nbsp;<b><a href="/intl/en/options/" class=q>more&nbsp;&raquo;</a></b></font></td></tr></table><table cellspacing=0 cellpadding=0><tr><td width=25%>&nbsp;</td><td align=center><input type=hidden name=hl value=en><input maxlength=2048 size=55 name=q value="" title="Google Search"><br><input type=submit value="Google Search" name=btnG><input type=submit value="I'm Feeling Lucky" name=btnI></td><td valign=top nowrap width=25%><font size=-2>&nbsp;&nbsp;<a href=/advanced_search?hl=en>Advanced Search</a><br>&nbsp;&nbsp;<a href=/preferences?hl=en>Preferences</a><br>&nbsp;&nbsp;<a href=/language_tools?hl=en>Language Tools</a></font></td></tr></table></form><br><br><font size=-1><a href="/ads/">Advertising&nbsp;Programs</a> - <a href=/services/>Business Solutions</a> - <a href=/about.html>About Google</a></font><p><font size=-2>&copy;2006 Google</font></p></center></body></html>
+</script><table border=0 cellspacing=0 cellpadding=4><tr><td nowrap><font size=-1><b>Web</b>&nbsp;&nbsp;&nbsp;&nbsp;<a id=1a class=q href="/imghp?hl=en&tab=wi" onClick="return qs(this);">Images</a>&nbsp;&nbsp;&nbsp;&nbsp;<a id=2a class=q href="http://groups.google.com/grphp?hl=en&tab=wg" onClick="return qs(this);">Groups</a>&nbsp;&nbsp;&nbsp;&nbsp;<a id=4a class=q href="http://news.google.com/nwshp?hl=en&tab=wn" onClick="return qs(this);">News</a>&nbsp;&nbsp;&nbsp;&nbsp;<a id=5a class=q href="http://froogle.google.com/frghp?hl=en&tab=wf" onClick="return qs(this);">Froogle</a>&nbsp;&nbsp;&nbsp;&nbsp;<a id=8a class=q href="/lochp?hl=en&tab=wl" onClick="return qs(this);">Local</a>&nbsp;&nbsp;&nbsp;&nbsp;<b><a href="/intl/en/options/" class=q>more&nbsp;&raquo;</a></b></font></td></tr></table><table cellspacing=0 cellpadding=0><tr><td width=25%>&nbsp;</td><td align=center><input type=hidden name=hl value=en><input maxlength=2048 size=55 name=q value="" title="Google Search"><br><input type=submit value="Google Search" name=btnG><input type=submit value="I'm Feeling Lucky" name=btnI></td><td valign=top nowrap width=25%><font size=-2>&nbsp;&nbsp;<a href=/advanced_search?hl=en>Advanced Search</a><br>&nbsp;&nbsp;<a href=/preferences?hl=en>Preferences</a><br>&nbsp;&nbsp;<a href=/language_tools?hl=en>Language Tools</a></font></td></tr></table></form><br><br><font size=-1><a href="/ads/">Advertising&nbsp;Programs</a> - <a href=/services/>Business Solutions</a> - <a href=/about.html>About Google</a></font><p><font size=-2>&copy;2006 Google</font></p></center></body></html>
+
+<!-- vim: et sw=4 sts=4 -->

benchmarks/samples/Lexer/3.html

@@ -67,21 +67,21 @@ if (objAdMgr.isSlotAvailable("leaderboard")) {
 </table>
 <table width="86%" border="0" cellspacing="0" cellpadding="2">
   <tr>
-    <td height="388" width="19%" bgcolor="#FFCCFF" valign="top"> 
+    <td height="388" width="19%" bgcolor="#FFCCFF" valign="top">
       <p>May 1, 2000</p>
       <p><b>Pop Culture</b> </p>
       <p>by. H. Finkelstein</p>
 
     </td>
-    <td height="388" width="52%" valign="top"> 
-      <p>Welcome to the <b>Anime Digi-Lib</b>, a virtual index to anime on the 
-        internet. This site strives to house a comprehensive index to both personal 
-        and commercial websites and provides reviews to these sites. We hope to 
-        be a gateway for people who've never imagined they'd ever be interested 
+    <td height="388" width="52%" valign="top">
+      <p>Welcome to the <b>Anime Digi-Lib</b>, a virtual index to anime on the
+        internet. This site strives to house a comprehensive index to both personal
+        and commercial websites and provides reviews to these sites. We hope to
+        be a gateway for people who've never imagined they'd ever be interested
         in Japanese Animation. </p>
       <table width="99%" border="1" cellspacing="0" cellpadding="2" height="320" name="Searchnservices">
         <tr>
-          <td height="263" valign="top" width="58%"> 
+          <td height="263" valign="top" width="58%">
             <p>&nbsp; </p>
             <p>&nbsp;</p>
 
@@ -107,15 +107,15 @@ if (objAdMgr.isSlotAvailable("leaderboard")) {
 </form>
 
 
-            <td> 
+            <td>
               <table border="0" cellpadding="0" cellspacing="0" width="100%">
 <tr><td><font face="verdana,geneva" color="#000011" size="1">What is better, subtitled or dubbed anime?</font></td></tr>
 <tr><td><input type="radio" name="rd" value="1"><font face="verdana" size="2" color="#000011">Subtitled</font></td></tr>
 
 <tr><td align="middle"><font face="verdana" size="1"><a href="http://pub.alxnet.com/poll?id=2079873&q=view">Current results</a></font></td></tr>
 </table></td></tr>
-          <tr> 
-            <td><font face="verdana" size="1"><a href="http://www.alxnet.com/services/poll/">Free 
+          <tr>
+            <td><font face="verdana" size="1"><a href="http://www.alxnet.com/services/poll/">Free
               Web Polls</a></font></td>
           </tr>
 </table></form>
@@ -126,3 +126,5 @@ if (objAdMgr.isSlotAvailable("leaderboard")) {
 </body>
 
 </html>
+
+<!-- vim: et sw=4 sts=4 -->

benchmarks/samples/Lexer/4.html

@@ -138,7 +138,7 @@
 </table>
 <p><script type="text/javascript">
 //<![CDATA[
- if (window.showTocToggle) { var tocShowText = "show"; var tocHideText = "hide"; showTocToggle(); } 
+ if (window.showTocToggle) { var tocShowText = "show"; var tocHideText = "hide"; showTocToggle(); }
 //]]>
 </script></p>
 <div class="editsection" style="float:right;margin-left:5px;">[<a href="/w/index.php?title=Tai_Chi_Chuan&amp;action=edit&amp;section=1" title="Edit section: Overview">edit</a>]</div>
@@ -279,19 +279,19 @@ Yang Small Frame                     |                             <a href="/wik
 
    |                                                                          |
 <a href="/w/index.php?title=Wu_Ta-kuei&amp;action=edit" class="new" title="Wu Ta-kuei">Wu Ta-kuei</a>                                                                  <a href="/w/index.php?title=Sun_Hsing-i&amp;action=edit" class="new" title="Sun Hsing-i">Sun Hsing-i</a>
-1923-1970                                                                   1891-1929                  
-                           
-<b>MODERN FORMS</b>        
-                                      
-from Yang Ch`eng-fu                     
-        |               
-        |              
-        |                         
-        +--------------+      
-        |              |       
-  <a href="/wiki/Cheng_Man-ch%27ing" title="Cheng Man-ch'ing">Cheng Man-ch'ing</a>     |   
-  1901-1975            |    
-  Short (37) Form      |     
+1923-1970                                                                   1891-1929
+
+<b>MODERN FORMS</b>
+
+from Yang Ch`eng-fu
+        |
+        |
+        |
+        +--------------+
+        |              |
+  <a href="/wiki/Cheng_Man-ch%27ing" title="Cheng Man-ch'ing">Cheng Man-ch'ing</a>     |
+  1901-1975            |
+  Short (37) Form      |
                        |
               Chinese Sports Commission
               1956
@@ -538,3 +538,5 @@ Retrieved from "<a href="http://en.wikipedia.org/wiki/Tai_Chi_Chuan">http://en.w
 
 <!-- Served by srv25 in 0.089 secs. -->
 </body></html>
+
+<!-- vim: et sw=4 sts=4 -->

benchmarks/samples/Lexer/DISCLAIMER.txt

@@ -2,4 +2,6 @@ Disclaimer:
 
 The HTML used in these samples are taken from random websites.  I claim
 no copyright over these and assert that I may use them like this under
-fair use.
+fair use.
+
+    vim: et sw=4 sts=4

configdoc/generate.php

@@ -2,12 +2,12 @@
 
 /**
  * Generates XML and HTML documents describing configuration.
- * @note PHP 5 only!
+ * @note PHP 5.2+ only!
  */
 
 /*
 TODO:
-- make XML format richer (see XMLSerializer_ConfigSchema)
+- make XML format richer
 - extend XSLT transformation (see the corresponding XSLT file)
 - allow generation of packaged docs that can be easily moved
 - multipage documentation
@@ -15,31 +15,48 @@ TODO:
 - add blurbs to ToC
 */
 
-if (version_compare('5', PHP_VERSION, '>')) exit('Requires PHP 5 or higher.');
-error_reporting(E_ALL); // probably not possible to use E_STRICT
+if (version_compare(PHP_VERSION, '5.2', '<')) exit('PHP 5.2+ required.');
+error_reporting(E_ALL | E_STRICT);
 
-define('HTMLPURIFIER_SCHEMA_STRICT', true); // description data needs to be collected
+chdir(dirname(__FILE__));
 
 // load dual-libraries
+require_once '../extras/HTMLPurifierExtras.auto.php';
 require_once '../library/HTMLPurifier.auto.php';
-require_once 'library/ConfigDoc.auto.php';
 
-$purifier = HTMLPurifier::getInstance(array(
+// setup HTML Purifier singleton
+HTMLPurifier::getInstance(array(
     'AutoFormat.PurifierLinkify' => true
 ));
 
-$schema = HTMLPurifier_ConfigSchema::instance();
-$style = 'plain'; // use $_GET in the future
-$configdoc = new ConfigDoc();
-$output = $configdoc->generate($schema, $style);
+$interchange = HTMLPurifier_ConfigSchema_InterchangeBuilder::buildFromDirectory();
+$interchange->validate();
+
+$style = 'plain'; // use $_GET in the future, careful to validate!
+$configdoc_xml = 'configdoc.xml';
+
+$xml_builder = new HTMLPurifier_ConfigSchema_Builder_Xml();
+$xml_builder->openURI($configdoc_xml);
+$xml_builder->build($interchange);
+unset($xml_builder); // free handle
+
+$xslt = new ConfigDoc_HTMLXSLTProcessor();
+$xslt->importStylesheet(dirname(__FILE__) . "/styles/$style.xsl");
+$output = $xslt->transformToHTML($configdoc_xml);
+
+if (!$output) {
+    echo "Error in generating files\n";
+    exit(1);
+}
 
 // write out
 file_put_contents("$style.html", $output);
 
 if (php_sapi_name() != 'cli') {
-    // output = instant feedback
+    // output (instant feedback if it's a browser)
     echo $output;
 } else {
     echo 'Files generated successfully.';
 }
 
+// vim: et sw=4 sts=4

configdoc/library/ConfigDoc.php

@@ -1,38 +0,0 @@
-<?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/XMLSerializer.php

@@ -1,25 +0,0 @@
-<?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

@@ -1,123 +0,0 @@
-<?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

@@ -1,26 +0,0 @@
-<?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

@@ -1,16 +1,30 @@
 
-body {margin:1em 4em;}
+body {margin:0;padding:0;}
+#content {
+  margin:1em auto;
+  max-width: 47em;
+  width: expression(document.body.clientWidth >
+    85 * parseInt(document.body.currentStyle.fontSize) ?
+    "54em": "auto");
+}
 
 table {border-collapse:collapse;}
 table td, table th {padding:0.2em;}
 
 table.constraints {margin:0 0 1em;}
-table.constraints th {text-align:left;padding-left:0.4em;}
-table.constraints td {padding-right:0.4em;}
+table.constraints th {
+  text-align:right;padding-left:0.4em;padding-right:0.4em;background:#EEE;
+  width:8em;vertical-align:top;}
+table.constraints td {padding-right:0.4em; padding-left: 1em;}
+table.constraints td ul {padding:0; margin:0; list-style:none;}
 table.constraints td pre {margin:0;}
 
-#toc {list-style-type:none; font-weight:bold;}
-#toc ul {list-style-type:disc; font-weight:normal;}
+#tocContainer {position:relative;}
+#toc {list-style-type:none; font-weight:bold; font-size:1em; margin-bottom:1em;}
+#toc li {position:relative; line-height: 1.2em;}
+#toc .col-2 {margin-left:50%;}
+#toc .col-l {float:left;}
+#toc ul {list-style-type:disc; font-weight:normal; padding-bottom:1.2em;}
 
 .description p {margin-top:0;margin-bottom:1em;}
 
@@ -19,6 +33,12 @@ table.constraints td pre {margin:0;}
 #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;}
+    font-size:1.3em; clear:both;}
 h3 {font-family:sans-serif; font-size:1.1em; font-weight:bold; }
 h4 {font-family:sans-serif; font-size:0.9em; font-weight:bold; }
+
+.deprecated {color: #CCC;}
+.deprecated table.constraints th {background:#FFF;}
+.deprecated-notice {color: #000; text-align:center; margin-bottom: 1em;}
+
+/* vim: et sw=4 sts=4 */

configdoc/styles/plain.xsl

@@ -14,9 +14,13 @@
     />
     <xsl:param name="css" select="'styles/plain.css'"/>
     <xsl:param name="title" select="'Configuration Documentation'"/>
-    
-    <xsl:variable name="typeLookup" select="document('../types.xml')" />
-    
+
+    <xsl:variable name="typeLookup"  select="document('../types.xml')/types" />
+    <xsl:variable name="usageLookup" select="document('../usage.xml')/usage" />
+
+    <!-- Twiddle this variable to get the columns as even as possible -->
+    <xsl:variable name="maxNumberAdjust" select="2" />
+
     <xsl:template match="/">
         <html lang="en" xml:lang="en">
             <head>
@@ -25,105 +29,170 @@
                 <link rel="stylesheet" type="text/css" href="{$css}" />
             </head>
             <body>
-                <div id="library"><xsl:value-of select="/configdoc/title" /></div>
-                <h1><xsl:value-of select="$title" /></h1>
-                <h2>Table of Contents</h2>
-                <ul id="toc">
-                    <xsl:apply-templates mode="toc" />
-                </ul>
-                <xsl:apply-templates />
+                <div id="content">
+                    <div id="library"><xsl:value-of select="/configdoc/title" /></div>
+                    <h1><xsl:value-of select="$title" /></h1>
+                    <div id="tocContainer">
+                        <h2>Table of Contents</h2>
+                        <ul id="toc">
+                            <xsl:apply-templates mode="toc">
+                                <xsl:with-param name="overflowNumber" select="round(count(/configdoc/namespace) div 2) + $maxNumberAdjust" />
+                            </xsl:apply-templates>
+                        </ul>
+                    </div>
+                    <xsl:apply-templates />
+                </div>
             </body>
         </html>
     </xsl:template>
-    
+
     <xsl:template match="title" mode="toc" />
     <xsl:template match="namespace" mode="toc">
+        <xsl:param name="overflowNumber" />
+        <xsl:variable name="number"><xsl:number level="single" /></xsl:variable>
+        <xsl:variable name="directiveNumber"><xsl:number level="any" count="directive" /></xsl:variable>
         <xsl:if test="count(directive)&gt;0">
             <li>
+                <!-- BEGIN multicolumn code -->
+                <xsl:if test="$number &gt;= $overflowNumber">
+                    <xsl:attribute name="class">col-2</xsl:attribute>
+                </xsl:if>
+                <xsl:if test="$number = $overflowNumber">
+                    <xsl:attribute name="style">margin-top:-<xsl:value-of select="($number * 2 + $directiveNumber - 3) * 1.2" />em</xsl:attribute>
+                </xsl:if>
+                <!-- END multicolumn code -->
                 <a href="#{@id}"><xsl:value-of select="name" /></a>
                 <ul>
-                    <xsl:apply-templates select="directive" mode="toc" />
+                    <xsl:apply-templates select="directive" mode="toc">
+                        <xsl:with-param name="overflowNumber" select="$overflowNumber" />
+                    </xsl:apply-templates>
                 </ul>
+                <xsl:if test="$number + 1 = $overflowNumber">
+                    <div class="col-l" />
+                </xsl:if>
             </li>
         </xsl:if>
     </xsl:template>
     <xsl:template match="directive" mode="toc">
-        <li><a href="#{@id}"><xsl:value-of select="name" /></a></li>
-    </xsl:template>
-    
-    <xsl:template match="title" />
-    
-    <xsl:template match="namespace">
-        <xsl:apply-templates />
-        <xsl:if test="count(directive)=0">
-            <p>No configuration directives defined for this namespace.</p>
+        <xsl:variable name="number">
+            <xsl:number level="any" count="directive|namespace" />
+        </xsl:variable>
+        <xsl:if test="not(deprecated)">
+            <li>
+                <a href="#{@id}"><xsl:value-of select="name" /></a>
+            </li>
         </xsl:if>
     </xsl:template>
+
+    <xsl:template match="title" />
+
+    <xsl:template match="namespace">
+        <div class="namespace">
+            <xsl:apply-templates />
+            <xsl:if test="count(directive)=0">
+                <p>No configuration directives defined for this namespace.</p>
+            </xsl:if>
+        </div>
+    </xsl:template>
     <xsl:template match="namespace/name">
         <h2 id="{../@id}"><xsl:value-of select="." /></h2>
     </xsl:template>
     <xsl:template match="namespace/description">
         <div class="description">
-            <xsl:copy-of select="div/node()" />
+            <xsl:copy-of xmlns:xhtml="http://www.w3.org/1999/xhtml" select="xhtml:div/node()" />
         </div>
     </xsl:template>
-    
+
     <xsl:template match="directive">
-        <xsl:apply-templates />
+        <div>
+            <xsl:attribute name="class"><!--
+                -->directive<!--
+                --><xsl:if test="deprecated"> deprecated</xsl:if><!--
+            --></xsl:attribute>
+            <xsl:apply-templates>
+                <xsl:with-param name="id" select="@id" />
+            </xsl:apply-templates>
+        </div>
     </xsl:template>
     <xsl:template match="directive/name">
+        <xsl:param name="id" />
         <xsl:apply-templates select="../aliases/alias" mode="anchor" />
-        <h3 id="{../@id}"><xsl:value-of select="../@id" /></h3>
+        <h3 id="{$id}"><xsl:value-of select="$id" /></h3>
     </xsl:template>
     <xsl:template match="alias" mode="anchor">
         <a id="{.}"></a>
     </xsl:template>
-    
+
     <!-- Do not pass through -->
     <xsl:template match="alias"></xsl:template>
-    
+
     <xsl:template match="directive/constraints">
+        <xsl:param name="id" />
         <table class="constraints">
             <xsl:apply-templates />
-            <!-- Calculated other values -->
-            <xsl:if test="../descriptions/description[@file]">
-                <tr>
-                    <th>Used by:</th>
-                    <td>
-                        <xsl:for-each select="../descriptions/description">
-                            <xsl:if test="position()&gt;1">, </xsl:if>
-                            <xsl:value-of select="@file" />
-                        </xsl:for-each>
-                    </td>
-                </tr>
-            </xsl:if>
             <xsl:if test="../aliases/alias">
                 <xsl:apply-templates select="../aliases" mode="constraints" />
             </xsl:if>
+            <xsl:apply-templates select="$usageLookup/directive[@id=$id]" />
         </table>
     </xsl:template>
     <xsl:template match="directive/aliases" mode="constraints">
-        <th>Aliases:</th>
-        <td>
-            <xsl:for-each select="alias">
+        <tr>
+            <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>
+        </tr>
+    </xsl:template>
+    <xsl:template match="directive/description">
+        <div class="description">
+            <xsl:copy-of xmlns:xhtml="http://www.w3.org/1999/xhtml" select="xhtml:div/node()" />
+        </div>
+    </xsl:template>
+    <xsl:template match="directive/deprecated">
+        <div class="deprecated-notice">
+            <strong>Warning:</strong>
+            This directive was deprecated in version <xsl:value-of select="version" />.
+            <a href="#{use}">%<xsl:value-of select="use" /></a> should be used instead.
+        </div>
+    </xsl:template>
+    <xsl:template match="usage/directive">
+        <tr>
+            <th>Used in</th>
+            <td>
+                <ul>
+                    <xsl:apply-templates />
+                </ul>
+            </td>
+        </tr>
+    </xsl:template>
+    <xsl:template match="usage/directive/file">
+        <li>
+            <em><xsl:value-of select="@name" /></em> on line<xsl:if test="count(line)&gt;1">s</xsl:if>
+            <xsl:text> </xsl:text>
+            <xsl:for-each select="line">
                 <xsl:if test="position()&gt;1">, </xsl:if>
                 <xsl:value-of select="." />
             </xsl:for-each>
-        </td>
+        </li>
     </xsl:template>
-    <xsl:template match="directive//description">
-        <div class="description">
-            <xsl:copy-of select="div/node()" />
-        </div>
+
+    <xsl:template match="constraints/version">
+        <tr>
+            <th>Version added</th>
+            <td><xsl:value-of select="." /></td>
+        </tr>
     </xsl:template>
-    
     <xsl:template match="constraints/type">
         <tr>
-            <th>Type:</th>
+            <th>Type</th>
             <td>
                 <xsl:variable name="type" select="text()" />
                 <xsl:attribute name="class">type type-<xsl:value-of select="$type" /></xsl:attribute>
-                <xsl:value-of select="$typeLookup/types/type[@id=$type]/text()" />
+                <xsl:value-of select="$typeLookup/type[@id=$type]/text()" />
                 <xsl:if test="@allow-null='yes'">
                     (or null)
                 </xsl:if>
@@ -132,7 +201,7 @@
     </xsl:template>
     <xsl:template match="constraints/allowed">
         <tr>
-            <th>Allowed values:</th>
+            <th>Allowed values</th>
             <td>
                 <xsl:for-each select="value"><!--
                  --><xsl:if test="position()&gt;1">, </xsl:if>
@@ -143,9 +212,24 @@
     </xsl:template>
     <xsl:template match="constraints/default">
         <tr>
-            <th>Default:</th>
+            <th>Default</th>
             <td><pre><xsl:value-of select="." xml:space="preserve" /></pre></td>
         </tr>
     </xsl:template>
-    
+    <xsl:template match="constraints/external">
+        <tr>
+            <th>External deps</th>
+            <td>
+                <ul>
+                    <xsl:apply-templates />
+                </ul>
+            </td>
+        </tr>
+    </xsl:template>
+    <xsl:template match="constraints/external/project">
+        <li><xsl:value-of select="." /></li>
+    </xsl:template>
+
 </xsl:stylesheet>
+
+<!-- vim: et sw=4 sts=4 -->

configdoc/types.xml

@@ -0,0 +1,16 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<types>
+  <type id="string">String</type>
+  <type id="istring">Case-insensitive string</type>
+  <type id="text">Text</type>
+  <type id="itext">Case-insensitive text</type>
+  <type id="int">Integer</type>
+  <type id="float">Float</type>
+  <type id="bool">Boolean</type>
+  <type id="lookup">Lookup array</type>
+  <type id="list">Array list</type>
+  <type id="hash">Associative array</type>
+  <type id="mixed">Mixed</type>
+</types>
+
+<!-- vim: et sw=4 sts=4 -->

configdoc/usage.xml

@@ -0,0 +1,402 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<usage>
+ <directive id="Core.CollectErrors">
+  <file name="HTMLPurifier.php">
+   <line>131</line>
+  </file>
+  <file name="HTMLPurifier/Lexer.php">
+   <line>81</line>
+  </file>
+  <file name="HTMLPurifier/Lexer/DirectLex.php">
+   <line>53</line>
+   <line>73</line>
+   <line>348</line>
+  </file>
+  <file name="HTMLPurifier/Strategy/RemoveForeignElements.php">
+   <line>47</line>
+  </file>
+ </directive>
+ <directive id="CSS.MaxImgLength">
+  <file name="HTMLPurifier/CSSDefinition.php">
+   <line>157</line>
+  </file>
+ </directive>
+ <directive id="CSS.Proprietary">
+  <file name="HTMLPurifier/CSSDefinition.php">
+   <line>214</line>
+  </file>
+ </directive>
+ <directive id="CSS.AllowTricky">
+  <file name="HTMLPurifier/CSSDefinition.php">
+   <line>218</line>
+  </file>
+ </directive>
+ <directive id="CSS.AllowImportant">
+  <file name="HTMLPurifier/CSSDefinition.php">
+   <line>222</line>
+  </file>
+ </directive>
+ <directive id="CSS.AllowedProperties">
+  <file name="HTMLPurifier/CSSDefinition.php">
+   <line>275</line>
+  </file>
+ </directive>
+ <directive id="Cache.DefinitionImpl">
+  <file name="HTMLPurifier/DefinitionCacheFactory.php">
+   <line>49</line>
+  </file>
+ </directive>
+ <directive id="HTML.Doctype">
+  <file name="HTMLPurifier/DoctypeRegistry.php">
+   <line>83</line>
+  </file>
+ </directive>
+ <directive id="HTML.CustomDoctype">
+  <file name="HTMLPurifier/DoctypeRegistry.php">
+   <line>85</line>
+  </file>
+ </directive>
+ <directive id="HTML.XHTML">
+  <file name="HTMLPurifier/DoctypeRegistry.php">
+   <line>88</line>
+  </file>
+ </directive>
+ <directive id="HTML.Strict">
+  <file name="HTMLPurifier/DoctypeRegistry.php">
+   <line>93</line>
+  </file>
+ </directive>
+ <directive id="Core.Encoding">
+  <file name="HTMLPurifier/Encoder.php">
+   <line>267</line>
+   <line>300</line>
+  </file>
+ </directive>
+ <directive id="Test.ForceNoIconv">
+  <file name="HTMLPurifier/Encoder.php">
+   <line>272</line>
+   <line>308</line>
+  </file>
+ </directive>
+ <directive id="Core.EscapeNonASCIICharacters">
+  <file name="HTMLPurifier/Encoder.php">
+   <line>304</line>
+  </file>
+ </directive>
+ <directive id="Output.CommentScriptContents">
+  <file name="HTMLPurifier/Generator.php">
+   <line>45</line>
+  </file>
+ </directive>
+ <directive id="Output.SortAttr">
+  <file name="HTMLPurifier/Generator.php">
+   <line>46</line>
+  </file>
+ </directive>
+ <directive id="Output.TidyFormat">
+  <file name="HTMLPurifier/Generator.php">
+   <line>75</line>
+  </file>
+ </directive>
+ <directive id="Output.Newline">
+  <file name="HTMLPurifier/Generator.php">
+   <line>89</line>
+  </file>
+ </directive>
+ <directive id="HTML.BlockWrapper">
+  <file name="HTMLPurifier/HTMLDefinition.php">
+   <line>222</line>
+  </file>
+ </directive>
+ <directive id="HTML.Parent">
+  <file name="HTMLPurifier/HTMLDefinition.php">
+   <line>230</line>
+  </file>
+ </directive>
+ <directive id="HTML.AllowedElements">
+  <file name="HTMLPurifier/HTMLDefinition.php">
+   <line>247</line>
+  </file>
+ </directive>
+ <directive id="HTML.AllowedAttributes">
+  <file name="HTMLPurifier/HTMLDefinition.php">
+   <line>248</line>
+  </file>
+ </directive>
+ <directive id="HTML.Allowed">
+  <file name="HTMLPurifier/HTMLDefinition.php">
+   <line>251</line>
+  </file>
+ </directive>
+ <directive id="HTML.ForbiddenElements">
+  <file name="HTMLPurifier/HTMLDefinition.php">
+   <line>337</line>
+  </file>
+ </directive>
+ <directive id="HTML.ForbiddenAttributes">
+  <file name="HTMLPurifier/HTMLDefinition.php">
+   <line>338</line>
+  </file>
+ </directive>
+ <directive id="HTML.Trusted">
+  <file name="HTMLPurifier/HTMLModuleManager.php">
+   <line>202</line>
+  </file>
+  <file name="HTMLPurifier/Lexer.php">
+   <line>258</line>
+  </file>
+  <file name="HTMLPurifier/HTMLModule/Image.php">
+   <line>27</line>
+  </file>
+  <file name="HTMLPurifier/Lexer/DirectLex.php">
+   <line>36</line>
+  </file>
+  <file name="HTMLPurifier/Strategy/RemoveForeignElements.php">
+   <line>23</line>
+  </file>
+ </directive>
+ <directive id="HTML.AllowedModules">
+  <file name="HTMLPurifier/HTMLModuleManager.php">
+   <line>209</line>
+  </file>
+ </directive>
+ <directive id="HTML.CoreModules">
+  <file name="HTMLPurifier/HTMLModuleManager.php">
+   <line>210</line>
+  </file>
+ </directive>
+ <directive id="HTML.Proprietary">
+  <file name="HTMLPurifier/HTMLModuleManager.php">
+   <line>221</line>
+  </file>
+ </directive>
+ <directive id="HTML.SafeObject">
+  <file name="HTMLPurifier/HTMLModuleManager.php">
+   <line>226</line>
+  </file>
+ </directive>
+ <directive id="HTML.SafeEmbed">
+  <file name="HTMLPurifier/HTMLModuleManager.php">
+   <line>229</line>
+  </file>
+ </directive>
+ <directive id="Attr.IDBlacklist">
+  <file name="HTMLPurifier/IDAccumulator.php">
+   <line>26</line>
+  </file>
+ </directive>
+ <directive id="Core.Language">
+  <file name="HTMLPurifier/LanguageFactory.php">
+   <line>88</line>
+  </file>
+ </directive>
+ <directive id="Core.LexerImpl">
+  <file name="HTMLPurifier/Lexer.php">
+   <line>76</line>
+  </file>
+ </directive>
+ <directive id="Core.MaintainLineNumbers">
+  <file name="HTMLPurifier/Lexer.php">
+   <line>80</line>
+  </file>
+  <file name="HTMLPurifier/Lexer/DirectLex.php">
+   <line>48</line>
+  </file>
+ </directive>
+ <directive id="Core.ConvertDocumentToFragment">
+  <file name="HTMLPurifier/Lexer.php">
+   <line>267</line>
+  </file>
+ </directive>
+ <directive id="URI.Host">
+  <file name="HTMLPurifier/URIDefinition.php">
+   <line>64</line>
+  </file>
+ </directive>
+ <directive id="URI.Base">
+  <file name="HTMLPurifier/URIDefinition.php">
+   <line>65</line>
+  </file>
+ </directive>
+ <directive id="URI.DefaultScheme">
+  <file name="HTMLPurifier/URIDefinition.php">
+   <line>72</line>
+  </file>
+ </directive>
+ <directive id="URI.AllowedSchemes">
+  <file name="HTMLPurifier/URISchemeRegistry.php">
+   <line>42</line>
+  </file>
+ </directive>
+ <directive id="URI.OverrideAllowedSchemes">
+  <file name="HTMLPurifier/URISchemeRegistry.php">
+   <line>43</line>
+  </file>
+ </directive>
+ <directive id="URI.Disable">
+  <file name="HTMLPurifier/AttrDef/URI.php">
+   <line>28</line>
+  </file>
+ </directive>
+ <directive id="Core.ColorKeywords">
+  <file name="HTMLPurifier/AttrDef/CSS/Color.php">
+   <line>12</line>
+  </file>
+  <file name="HTMLPurifier/AttrDef/HTML/Color.php">
+   <line>12</line>
+  </file>
+ </directive>
+ <directive id="Attr.AllowedFrameTargets">
+  <file name="HTMLPurifier/AttrDef/HTML/FrameTarget.php">
+   <line>15</line>
+  </file>
+ </directive>
+ <directive id="Attr.EnableID">
+  <file name="HTMLPurifier/AttrDef/HTML/ID.php">
+   <line>20</line>
+  </file>
+ </directive>
+ <directive id="Attr.IDPrefix">
+  <file name="HTMLPurifier/AttrDef/HTML/ID.php">
+   <line>26</line>
+  </file>
+ </directive>
+ <directive id="Attr.IDPrefixLocal">
+  <file name="HTMLPurifier/AttrDef/HTML/ID.php">
+   <line>28</line>
+   <line>31</line>
+  </file>
+ </directive>
+ <directive id="Attr.IDBlacklistRegexp">
+  <file name="HTMLPurifier/AttrDef/HTML/ID.php">
+   <line>54</line>
+  </file>
+ </directive>
+ <directive id="Attr.DefaultTextDir">
+  <file name="HTMLPurifier/AttrTransform/BdoDir.php">
+   <line>13</line>
+  </file>
+ </directive>
+ <directive id="Core.RemoveInvalidImg">
+  <file name="HTMLPurifier/AttrTransform/ImgRequired.php">
+   <line>18</line>
+  </file>
+  <file name="HTMLPurifier/Strategy/RemoveForeignElements.php">
+   <line>20</line>
+  </file>
+ </directive>
+ <directive id="Attr.DefaultInvalidImage">
+  <file name="HTMLPurifier/AttrTransform/ImgRequired.php">
+   <line>19</line>
+  </file>
+ </directive>
+ <directive id="Attr.DefaultImageAlt">
+  <file name="HTMLPurifier/AttrTransform/ImgRequired.php">
+   <line>25</line>
+  </file>
+ </directive>
+ <directive id="Attr.DefaultInvalidImageAlt">
+  <file name="HTMLPurifier/AttrTransform/ImgRequired.php">
+   <line>32</line>
+  </file>
+ </directive>
+ <directive id="Core.EscapeInvalidChildren">
+  <file name="HTMLPurifier/ChildDef/Required.php">
+   <line>62</line>
+  </file>
+ </directive>
+ <directive id="Cache.SerializerPath">
+  <file name="HTMLPurifier/DefinitionCache/Serializer.php">
+   <line>91</line>
+  </file>
+ </directive>
+ <directive id="FilterParam.ExtractStyleBlocksTidyImpl">
+  <file name="HTMLPurifier/Filter/ExtractStyleBlocks.php">
+   <line>41</line>
+  </file>
+ </directive>
+ <directive id="FilterParam.ExtractStyleBlocksScope">
+  <file name="HTMLPurifier/Filter/ExtractStyleBlocks.php">
+   <line>65</line>
+  </file>
+ </directive>
+ <directive id="FilterParam.ExtractStyleBlocksEscaping">
+  <file name="HTMLPurifier/Filter/ExtractStyleBlocks.php">
+   <line>123</line>
+  </file>
+ </directive>
+ <directive id="HTML.MaxImgLength">
+  <file name="HTMLPurifier/HTMLModule/Image.php">
+   <line>14</line>
+  </file>
+  <file name="HTMLPurifier/HTMLModule/SafeEmbed.php">
+   <line>13</line>
+  </file>
+  <file name="HTMLPurifier/HTMLModule/SafeObject.php">
+   <line>19</line>
+  </file>
+ </directive>
+ <directive id="HTML.TidyLevel">
+  <file name="HTMLPurifier/HTMLModule/Tidy.php">
+   <line>45</line>
+  </file>
+ </directive>
+ <directive id="HTML.TidyAdd">
+  <file name="HTMLPurifier/HTMLModule/Tidy.php">
+   <line>49</line>
+  </file>
+ </directive>
+ <directive id="HTML.TidyRemove">
+  <file name="HTMLPurifier/HTMLModule/Tidy.php">
+   <line>50</line>
+  </file>
+ </directive>
+ <directive id="AutoFormatParam.PurifierLinkifyDocURL">
+  <file name="HTMLPurifier/Injector/PurifierLinkify.php">
+   <line>15</line>
+  </file>
+ </directive>
+ <directive id="Core.AggressivelyFixLt">
+  <file name="HTMLPurifier/Lexer/DOMLex.php">
+   <line>44</line>
+  </file>
+ </directive>
+ <directive id="Core.DirectLexLineNumberSyncInterval">
+  <file name="HTMLPurifier/Lexer/DirectLex.php">
+   <line>70</line>
+  </file>
+ </directive>
+ <directive id="Core.EscapeInvalidTags">
+  <file name="HTMLPurifier/Strategy/MakeWellFormed.php">
+   <line>45</line>
+  </file>
+  <file name="HTMLPurifier/Strategy/RemoveForeignElements.php">
+   <line>19</line>
+  </file>
+ </directive>
+ <directive id="Core.RemoveScriptContents">
+  <file name="HTMLPurifier/Strategy/RemoveForeignElements.php">
+   <line>25</line>
+  </file>
+ </directive>
+ <directive id="Core.HiddenElements">
+  <file name="HTMLPurifier/Strategy/RemoveForeignElements.php">
+   <line>26</line>
+  </file>
+ </directive>
+ <directive id="URI.HostBlacklist">
+  <file name="HTMLPurifier/URIFilter/HostBlacklist.php">
+   <line>8</line>
+  </file>
+ </directive>
+ <directive id="URI.MungeResources">
+  <file name="HTMLPurifier/URIFilter/Munge.php">
+   <line>14</line>
+  </file>
+ </directive>
+ <directive id="URI.MungeSecretKey">
+  <file name="HTMLPurifier/URIFilter/Munge.php">
+   <line>15</line>
+  </file>
+ </directive>
+</usage>

docs/dev-advanced-api.html

@@ -3,7 +3,7 @@
     "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." />
+<meta name="description" content="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>
@@ -16,6 +16,11 @@
 <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>
+  <strong>Warning:</strong> This document may be out-of-date. When in doubt,
+  consult the source code documentation.
+</p>
+
 <p>HTML Purifier currently natively supports only a subset of HTML's
 allowed elements, attributes, and behavior; specifically, this subset
 is the set of elements that are safe for untrusted users to use.
@@ -159,7 +164,7 @@ to make things simpler. It can be a literal object or:</p>
         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, 
+        be used to customize the attribute type: in the example above,
         we specify which values for Enum to allow.</li>
 </ul>
 
@@ -208,6 +213,6 @@ the usual things required are:</p>
 
 <p>See <code>HTMLPurifier/HTMLModule.php</code> for details.</p>
 
-<div id="version">$Id$</div>
-
 </body></html>
+
+<!-- vim: et sw=4 sts=4 -->

docs/dev-code-quality.txt

@@ -17,7 +17,6 @@ a lot of strtolower() calls, no legit casing
     URI - multiple regular expressions; missing validation for parts (?)
     CSS - parser doesn't accept advanced CSS (fringe)
     Number - constructor interface inconsistent with Integer
-ConfigSchema - redefinition is a mess
 Strategy
     FixNesting - cannot bubble nodes out of structures, duplicated checks
         for special-case parent node
@@ -26,3 +25,5 @@ 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
+
+    vim: et sw=4 sts=4

docs/dev-config-schema.html

@@ -0,0 +1,376 @@
+<?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="Describes config schema framework in HTML Purifier." />
+    <link rel="stylesheet" type="text/css" href="./style.css" />
+    <title>Config Schema - HTML Purifier</title>
+  </head>
+  <body>
+
+    <h1>Config Schema</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 has a fairly complex system for configuration. Users
+      interact with a <code>HTMLPurifier_Config</code> object to
+      set configuration directives. The values they set are validated according
+      to a configuration schema, <code>HTMLPurifier_ConfigSchema</code>.
+    </p>
+
+    <p>
+      The schema is mostly transparent to end-users, but if you're doing development
+      work for HTML Purifier and need to define a new configuration directive,
+      you'll need to interact with it. We'll also talk about how to define
+      userspace configuration directives at the very end.
+    </p>
+
+    <h2>Write a directive file</h2>
+
+    <p>
+      Directive files define configuration directives to be used by
+      HTML Purifier. They are placed in <code>library/HTMLPurifier/ConfigSchema/schema/</code>
+      in the form <code><em>Namespace</em>.<em>Directive</em>.txt</code> (I
+      couldn't think of a more descriptive file extension.)
+      Directive files are actually what we call <code>StringHash</code>es,
+      i.e. associative arrays represented in a string form reminiscent of
+      <a href="http://qa.php.net/write-test.php">PHPT</a> tests. Here's a
+      sample directive file, <code>Test.Sample.txt</code>:
+    </p>
+
+    <pre>Test.Sample
+TYPE: string/null
+DEFAULT: NULL
+ALLOWED: 'foo', 'bar'
+VALUE-ALIASES: 'baz' => 'bar'
+VERSION: 3.1.0
+--DESCRIPTION--
+This is a sample configuration directive for the purposes of the
+&lt;code&gt;dev-config-schema.html&lt;code&gt; documentation.
+--ALIASES--
+Test.Example</pre>
+
+    <p>
+      Each of these segments has a specific meaning:
+    </p>
+
+    <table class="table">
+      <thead>
+        <tr>
+          <th>Key</th>
+          <th>Example</th>
+          <th>Description</th>
+        </tr>
+      </thead>
+      <tbody>
+        <tr>
+          <td>ID</td>
+          <td>Test.Sample</td>
+          <td>The name of the directive, in the form Namespace.Directive
+          (implicitly the first line)</td>
+        </tr>
+        <tr>
+          <td>TYPE</td>
+          <td>string/null</td>
+          <td>The type of variable this directive accepts. See below for
+          details. You can also add <code>/null</code> to the end of
+          any basic type to allow null values too.</td>
+        </tr>
+        <tr>
+          <td>DEFAULT</td>
+          <td>NULL</td>
+          <td>A parseable PHP expression of the default value.</td>
+        </tr>
+        <tr>
+          <td>DESCRIPTION</td>
+          <td>This is a...</td>
+          <td>An HTML description of what this directive does.</td>
+        </tr>
+        <tr>
+          <td>VERSION</td>
+          <td>3.1.0</td>
+          <td><em>Recommended</em>. The version of HTML Purifier this directive was added.
+          Directives that have been around since 1.0.0 don't have this,
+          but any new ones should.</td>
+        </tr>
+        <tr>
+          <td>ALIASES</td>
+          <td>Test.Example</td>
+          <td><em>Optional</em>. A comma separated list of aliases for this directive.
+          This is most useful for backwards compatibility and should
+          not be used otherwise.</td>
+        </tr>
+        <tr>
+          <td>ALLOWED</td>
+          <td>'foo', 'bar'</td>
+          <td><em>Optional</em>. Set of allowed value for a directive,
+          a comma separated list of parseable PHP expressions. This
+          is only allowed string, istring, text and itext TYPEs.</td>
+        </tr>
+        <tr>
+          <td>VALUE-ALIASES</td>
+          <td>'baz' => 'bar'</td>
+          <td><em>Optional</em>. Mapping of one value to another, and
+          should be a comma separated list of keypair duples. This
+          is only allowed string, istring, text and itext TYPEs.</td>
+        </tr>
+        <tr>
+          <td>DEPRECATED-VERSION</td>
+          <td>3.1.0</td>
+          <td><em>Not shown</em>. Indicates that the directive was
+          deprecated this version.</td>
+        </tr>
+        <tr>
+          <td>DEPRECATED-USE</td>
+          <td>Test.NewDirective</td>
+          <td><em>Not shown</em>. Indicates what new directive should be
+          used instead. Note that the directives will functionally be
+          different, although they should offer the same functionality.
+          If they are identical, use an alias instead.</td>
+        </tr>
+        <tr>
+          <td>EXTERNAL</td>
+          <td>CSSTidy</td>
+          <td><em>Not shown</em>. Indicates if there is an external library
+          the user will need to download and install to use this configuration
+          directive. As of right now, this is merely a Google-able name; future
+          versions may also provide links and instructions.</td>
+        </tr>
+      </tbody>
+    </table>
+
+    <p>
+      Some notes on format and style:
+    </p>
+
+    <ul>
+      <li>
+        Each of these keys can be expressed in the short format
+        (<code>KEY: Value</code>) or the long format
+        (<code>--KEY--</code> with value beneath). You must use the
+        long format if multiple lines are needed, or if a long format
+        has been used already (that's why <code>ALIASES</code> in our
+        example is in the long format); otherwise, it's user preference.
+      </li>
+      <li>
+        The HTML descriptions should be wrapped at about 80 columns; do
+        not rely on editor word-wrapping.
+      </li>
+    </ul>
+
+    <p>
+      Also, as promised, here is the set of possible types:
+    </p>
+
+    <table class="table">
+      <thead>
+        <tr>
+          <th>Type</th>
+          <th>Example</th>
+          <th>Description</th>
+        </tr>
+      </thead>
+      <tbody>
+        <tr>
+          <td>string</td>
+          <td>'Foo'</td>
+          <td><a href="http://docs.php.net/manual/en/language.types.string.php">String</a> without newlines</td>
+        </tr>
+        <tr>
+          <td>istring</td>
+          <td>'foo'</td>
+          <td>Case insensitive ASCII string without newlines</td>
+        </tr>
+        <tr>
+          <td>text</td>
+          <td>"A<em>\n</em>b"</td>
+          <td>String with newlines</td>
+        </tr>
+        <tr>
+          <td>itext</td>
+          <td>"a<em>\n</em>b"</td>
+          <td>Case insensitive ASCII string without newlines</td>
+        </tr>
+        <tr>
+          <td>int</td>
+          <td>23</td>
+          <td>Integer</td>
+        </tr>
+        <tr>
+          <td>float</td>
+          <td>3.0</td>
+          <td>Floating point number</td>
+        </tr>
+        <tr>
+          <td>bool</td>
+          <td>true</td>
+          <td>Boolean</td>
+        </tr>
+        <tr>
+          <td>lookup</td>
+          <td>array('key' => true)</td>
+          <td>Lookup array, used with <code>isset($var[$key])</code></td>
+        </tr>
+        <tr>
+          <td>list</td>
+          <td>array('f', 'b')</td>
+          <td>List array, with ordered numerical indexes</td>
+        </tr>
+        <tr>
+          <td>hash</td>
+          <td>array('key' => 'val')</td>
+          <td>Associative array of keys to values</td>
+        </tr>
+        <tr>
+          <td>mixed</td>
+          <td>new stdclass</td>
+          <td>Any PHP variable is fine</td>
+        </tr>
+      </tbody>
+    </table>
+
+    <p>
+      The examples represent what will be returned out of the configuration
+      object; users have a little bit of leeway when setting configuration
+      values (for example, a lookup value can be specified as a list;
+      HTML Purifier will flip it as necessary.) These types are defined
+      in <a href="http://repo.or.cz/w/htmlpurifier.git?a=blob;hb=HEAD;f=library/HTMLPurifier/VarParser.php">
+      library/HTMLPurifier/VarParser.php</a>.
+    </p>
+
+    <p>
+      For more information on what values are allowed, and how they are parsed,
+      consult <a href="http://repo.or.cz/w/htmlpurifier.git?a=blob;hb=HEAD;f=library/HTMLPurifier/ConfigSchema/InterchangeBuilder.php">
+      library/HTMLPurifier/ConfigSchema/InterchangeBuilder.php</a>, as well
+      as <a href="http://repo.or.cz/w/htmlpurifier.git?a=blob;hb=HEAD;f=library/HTMLPurifier/ConfigSchema/Interchange/Directive.php">
+      library/HTMLPurifier/ConfigSchema/Interchange/Directive.php</a> for
+      the semantics of the parsed values.
+    </p>
+
+    <h2>Refreshing the cache</h2>
+
+    <p>
+      You may have noticed that your directive file isn't doing anything
+      yet. That's because it hasn't been added to the runtime
+      <code>HTMLPurifier_ConfigSchema</code> instance. Run
+      <code>maintenance/generate-schema-cache.php</code> to fix this.
+      If there were no errors, you're good to go! Don't forget to add
+      some unit tests for your functionality!
+    </p>
+
+    <p>
+      If you ever make changes to your configuration directives, you
+      will need to run this script again.
+    </p>
+
+    <h2>Errors</h2>
+
+    <p>
+      All directive files go through a rigorous validation process
+      through <a href="http://repo.or.cz/w/htmlpurifier.git?a=blob;hb=HEAD;f=library/HTMLPurifier/ConfigSchema/Validator.php">
+      library/HTMLPurifier/ConfigSchema/Validator.php</a>, as well
+      as some basic checks during building. While
+      listing every error out here is out-of-scope for this document, we
+      can give some general tips for interpreting error messages.
+      There are two types of errors: builder errors and validation errors.
+    </p>
+
+    <h3>Builder errors</h3>
+
+    <blockquote>
+      <p>
+        <strong>Exception:</strong> Expected type string, got
+        integer in DEFAULT in directive hash 'Ns.Dir'
+      </p>
+    </blockquote>
+
+    <p>
+      You can identify a builder error by the keyword "directive hash."
+      These are the easiest to deal with, because they directly correspond
+      with your directive file. Find the offending directive file (which
+      is the directive hash plus the .txt extension), find the
+      offending index ("in DEFAULT" means the DEFAULT key) and fix the error.
+      This particular error would occur if your default value is not the same
+      type as TYPE.
+    </p>
+
+    <h3>Validation errors</h3>
+
+    <blockquote>
+      <p>
+        <strong>Exception:</strong> Alias 3 in valueAliases in directive
+        'Ns.Dir' must be a string
+      </p>
+    </blockquote>
+
+    <p>
+      These are a little trickier, because we're not actually validating
+      your directive file, or even the direct string hash representation.
+      We're validating an Interchange object, and the error messages do
+      not mention any string hash keys.
+    </p>
+
+    <p>
+      Nevertheless, it's not difficult to figure out what went wrong.
+      Read the "context" statements in reverse:
+    </p>
+
+    <dl>
+      <dt>in directive 'Ns.Dir'</dt>
+        <dd>This means we need to look at the directive file <code>Ns.Dir.txt</code></dd>
+      <dt>in valueAliases</dt>
+        <dd>There's no key actually called this, but there's one that's close:
+          VALUE-ALIASES. Indeed, that's where to look.</dd>
+      <dt>Alias 3</dt>
+        <dd>The value alias that is equal to 3 is the culprit.</dd>
+    </dl>
+
+    <p>
+      In this particular case, you're not allowed to alias integers values to
+      strings values.
+    </p>
+
+    <p>
+      The most difficult part is translating the Interchange member variable (valueAliases)
+      into a directive file key (VALUE-ALIASES), but there's a one-to-one
+      correspondence currently. If the two formats diverge, any discrepancies
+      will be described in <a href="http://repo.or.cz/w/htmlpurifier.git?a=blob;hb=HEAD;f=library/HTMLPurifier/ConfigSchema/InterchangeBuilder.php">
+      library/HTMLPurifier/ConfigSchema/InterchangeBuilder.php</a>.
+    </p>
+
+    <h2>Internals</h2>
+
+    <p>
+      Much of the configuration schema framework's codebase deals with
+      shuffling data from one format to another, and doing validation on this
+      data.
+      The keystone of all of this is the <code>HTMLPurifier_ConfigSchema_Interchange</code>
+      class, which represents the purest, parsed representation of the schema.
+    </p>
+
+    <p>
+      Hand-writing this data is unwieldy, however, so we write directive files.
+      These directive files are parsed by <code>HTMLPurifier_StringHashParser</code>
+      into <code>HTMLPurifier_StringHash</code>es, which then
+      are run through <code>HTMLPurifier_ConfigSchema_InterchangeBuilder</code>
+      to construct the interchange object.
+    </p>
+
+    <p>
+      From the interchange object, the data can be siphoned into other forms
+      using <code>HTMLPurifier_ConfigSchema_Builder</code> subclasses.
+      For example, <code>HTMLPurifier_ConfigSchema_Builder_ConfigSchema</code>
+      generates a runtime <code>HTMLPurifier_ConfigSchema</code> object,
+      which <code>HTMLPurifier_Config</code> uses to validate its incoming
+      data. There is also an XML serializer, which is used to build documentation.
+    </p>
+
+  </body>
+</html>
+
+<!-- vim: et sw=4 sts=4 -->

docs/dev-flush.html

@@ -0,0 +1,67 @@
+<?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 when to flush HTML Purifier's various caches." />
+    <link rel="stylesheet" type="text/css" href="./style.css" />
+    <title>Flushing the Purifier - HTML Purifier</title>
+</head>
+<body>
+
+<h1>Flushing the Purifier</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>
+    If you've been poking around the various folders in HTML Purifier,
+    you may have noticed the <code>maintenance</code> directory.  Almost
+    all of these scripts are devoted to flushing out the various caches
+    HTML Purifier uses.  Normal users don't have to worry about this:
+    regular library usage is transparent.  However, when doing development
+    work on HTML Purifier, you may find you have to flush one of the
+    caches.
+</p>
+
+<p>
+    As a general rule of thumb, run <code>flush.php</code> whenever you make
+    any <em>major</em> changes, or when tests start mysteriously failing.
+    In more detail, run this script if:
+</p>
+
+<ul>
+    <li>
+        You added new source files to HTML Purifier's main library.
+        (see <code>generate-includes.php</code>)
+    </li>
+    <li>
+        You modified the configuration schema (see
+        <code>generate-schema-cache.php</code>). This usually means
+        adding or modifying files in <code>HTMLPurifier/ConfigSchema/schema/</code>,
+        although in rare cases modifying <code>HTMLPurifier/ConfigSchema.php</code>
+        will also require this.
+    </li>
+    <li>
+        You modified a Definition, or its subsystems. The most usual candidate
+        is <code>HTMLPurifier/HTMLDefinition.php</code>, which also encompasses
+        the files in <code>HTMLPurifier/HTMLModule/</code> as well as if you've
+        <a href="enduser-customize.html">customizing definitions</a> without
+        the cache disabled. (see <code>flush-generation-cache.php</code>)
+    </li>
+    <li>
+        You modified source files, and have been using the standalone
+        version from the full installation. (see <code>generate-standalone.php</code>)
+    </li>
+</ul>
+
+<p>
+    You can check out the corresponding scripts for more information on what they
+    do.
+</p>
+
+</body></html>
+
+<!-- vim: et sw=4 sts=4 -->

docs/dev-includes.txt

@@ -0,0 +1,281 @@
+
+INCLUDES, AUTOLOAD, BYTECODE CACHES and OPTIMIZATION
+
+The Problem
+-----------
+
+HTML Purifier contains a number of extra components that are not used all
+of the time, only if the user explicitly specifies that we should use
+them.
+
+Some of these optional components are optionally included (Filter,
+Language, Lexer, Printer), while others are included all the time
+(Injector, URIFilter, HTMLModule, URIScheme). We will stipulate that these
+are all developer specified: it is conceivable that certain Tokens are not
+used, but this is user-dependent and should not be trusted.
+
+We should come up with a consistent way to handle these things and ensure
+that we get the maximum performance when there is bytecode caches and
+when there are not. Unfortunately, these two goals seem contrary to each
+other.
+
+A peripheral issue is the performance of ConfigSchema, which has been
+shown take a large, constant amount of initialization time, and is
+intricately linked to the issue of includes due to its pervasive use
+in our plugin architecture.
+
+Pros and Cons
+-------------
+
+We will assume that user-based extensions will be included by them.
+
+Conditional includes:
+  Pros:
+    - User management is simplified; only a single directive needs to be set
+    - Only necessary code is included
+  Cons:
+    - Doesn't play nicely with opcode caches
+    - Adds complexity to standalone version
+    - Optional configuration directives are not exposed without a little
+      extra coaxing (not implemented yet)
+
+Include it all:
+  Pros:
+    - User management is still simple
+    - Plays nicely with opcode caches and standalone version
+    - All configuration directives are present
+  Cons:
+    - Lots of (how much?) extra code is included
+    - Classes that inherit from external libraries will cause compile
+      errors
+
+Build an include stub (Let's do this!):
+  Pros:
+    - Only necessary code is included
+    - Plays nicely with opcode caches and standalone version
+    - require (without once) can be used, see above
+    - Could further extend as a compilation to one file
+  Cons:
+    - Not implemented yet
+    - Requires user intervention and use of a command line script
+    - Standalone script must be chained to this
+    - More complex and compiled-language-like
+    - Requires a whole new class of system-wide configuration directives,
+      as configuration objects can be reused
+    - Determining what needs to be included can be complex (see above)
+    - No way of autodetecting dynamically instantiated classes
+    - Might be slow
+
+Include stubs
+-------------
+
+This solution may be "just right" for users who are heavily oriented
+towards performance. However, there are a number of picky implementation
+details to work out beforehand.
+
+The number one concern is how to make the HTML Purifier files "work
+out of the box", while still being able to easily get them into a form
+that works with this setup. As the codebase stands right now, it would
+be necessary to strip out all of the require_once calls. The only way
+we could get rid of the require_once calls is to use __autoload or
+use the stub for all cases (which might not be a bad idea).
+
+    Aside
+    -----
+    An important thing to remember, however, is that these require_once's
+    are valuable data about what classes a file needs. Unfortunately, there's
+    no distinction between whether or not the file is needed all the time,
+    or whether or not it is one of our "optional" files. Thus, it is
+    effectively useless.
+
+    Deprecated
+    ----------
+    One of the things I'd like to do is have the code search for any classes
+    that are explicitly mentioned in the code. If a class isn't mentioned, I
+    get to assume that it is "optional," i.e. included via introspection.
+    The choice is either to use PHP's tokenizer or use regexps; regexps would
+    be faster but a tokenizer would be more correct. If this ends up being
+    unfeasible, adding dependency comments isn't a bad idea. (This could
+    even be done automatically by search/replacing require_once, although
+    we'd have to manually inspect the results for the optional requires.)
+
+    NOTE: This ends up not being necessary, as we're going to make the user
+    figure out all the extra classes they need, and only include the core
+    which is predetermined.
+
+Using the autoload framework with include stubs works nicely with
+introspective classes: instead of having to have require_once inside
+the function, we can let autoload do the work; we simply need to
+new $class or accept the object straight from the caller. Handling filters
+becomes a simple matter of ticking off configuration directives, and
+if ConfigSchema spits out errors, adding the necessary includes. We could
+also use the autoload framework as a fallback, in case the user forgets
+to make the include, but doesn't really care about performance.
+
+    Insight
+    -------
+    All of this talk is merely a natural extension of what our current
+    standalone functionality does. However, instead of having our code
+    perform the includes, or attempting to inline everything that possibly
+    could be used, we boot the issue to the user, making them include
+    everything or setup the fallback autoload handler.
+
+Configuration Schema
+--------------------
+
+A common deficiency for all of the conditional include setups (including
+the dynamically built include PHP stub) is that if one of this
+conditionally included files includes a configuration directive, it
+is not accessible to configdoc. A stopgap solution for this problem is
+to have it piggy-back off of the data in the merge-library.php script
+to figure out what extra files it needs to include, but if the file also
+inherits classes that don't exist, we're in big trouble.
+
+I think it's high time we centralized the configuration documentation.
+However, the type checking has been a great boon for the library, and
+I'd like to keep that. The compromise is to use some other source, and
+then parse it into the ConfigSchema internal format (sans all of those
+nasty documentation strings which we really don't need at runtime) and
+serialize that for future use.
+
+The next question is that of format. XML is very verbose, and the prospect
+of setting defaults in it gives me willies. However, this may be necessary.
+Splitting up the file into manageable chunks may alleviate this trouble,
+and we may be even want to create our own format optimized for specifying
+configuration. It might look like (based off the PHPT format, which is
+nicely compact yet unambiguous and human-readable):
+
+Core.HiddenElements
+TYPE:    lookup
+DEFAULT: array('script', 'style') // auto-converted during processing
+--ALIASES--
+Core.InvisibleElements, Core.StupidElements
+--DESCRIPTION--
+<p>
+  Blah blah
+</p>
+
+The first line is the directive name, the lines after that prior to the
+first --HEADER-- block are single-line values, and then after that
+the multiline values are there. No value is restricted to a particular
+format: DEFAULT could very well be multiline if that would be easier.
+This would make it insanely easy, also, to add arbitrary extra parameters,
+like:
+
+VERSION:  3.0.0
+ALLOWED:  'none', 'light', 'medium', 'heavy' // this is wrapped in array()
+EXTERNAL: CSSTidy // this would be documented somewhere else with a URL
+
+The final loss would be that you wouldn't know what file the directive
+was used in; with some clever regexps it should be possible to
+figure out where $config->get($ns, $d); occurs. Reflective calls to
+the configuration object is mitigated by the fact that getBatch is
+used, so we can simply talk about that in the namespace definition page.
+This might be slow, but it would only happen when we are creating
+the documentation for consumption, and is sugar.
+
+We can put this in a schema/ directory, outside of HTML Purifier. The serialized
+data gets treated like entities.ser.
+
+The final thing that needs to be handled is user defined configurations.
+They can be added at runtime using ConfigSchema::registerDirectory()
+which globs the directory and grabs all of the directives to be incorporated
+in. Then, the result is saved. We may want to take advantage of the
+DefinitionCache framework, although it is not altogether certain what
+configuration directives would be used to generate our key (meta-directives!)
+
+    Further thoughts
+    ----------------
+    Our master configuration schema will only need to be updated once
+    every new version, so it's easily versionable. User specified
+    schema files are far more volatile, but it's far too expensive
+    to check the filemtimes of all the files, so a DefinitionRev style
+    mechanism works better. However, we can uniquely identify the
+    schema based on the directories they loaded, so there's no need
+    for a DefinitionId until we give them full programmatic control.
+
+    These variables should be directly incorporated into ConfigSchema,
+    and ConfigSchema should handle serialization. Some refactoring will be
+    necessary for the DefinitionCache classes, as they are built with
+    Config in mind. If the user changes something, the cache file gets
+    rebuilt. If the version changes, the cache file gets rebuilt. Since
+    our unit tests flush the caches before we start, and the operation is
+    pretty fast, this will not negatively impact unit testing.
+
+One last thing: certain configuration directives require that files
+get added. They may even be specified dynamically. It is not a good idea
+for the HTMLPurifier_Config object to be used directly for such matters.
+Instead, the userland code should explicitly perform the includes. We may
+put in something like:
+
+REQUIRES: HTMLPurifier_Filter_ExtractStyleBlocks
+
+To indicate that if that class doesn't exist, and the user is attempting
+to use the directive, we should fatally error out. The stub includes the core files,
+and the user includes everything else. Any reflective things like new
+$class would be required to tie in with the configuration.
+
+It would work very well with rarely used configuration options, but it
+wouldn't be so good for "core" parts that can be disabled. In such cases
+the core include file would need to be modified, and the only way
+to properly do this is use the configuration object. Once again, our
+ability to create cache keys saves the day again: we can create arbitrary
+stub files for arbitrary configurations and include those. They could
+even be the single file affairs. The only thing we'd need to include,
+then, would be HTMLPurifier_Config! Then, the configuration object would
+load the library.
+
+    An aside...
+    -----------
+    One questions, however, the wisdom of letting PHP files write other PHP
+    files. It seems like a recipe for disaster, or at least lots of headaches
+    in highly secured setups, where PHP does not have the ability to write
+    to its root. In such cases, we could use sticky bits or tell the user
+    to manually generate the file.
+
+    The other troublesome bit is actually doing the calculations necessary.
+    For certain cases, it's simple (such as URIScheme), but for AttrDef
+    and HTMLModule the dependency trees are very complex in relation to
+    %HTML.Allowed and friends. I think that this idea should be shelved
+    and looked at a later, less insane date.
+
+An interesting dilemma presents itself when a configuration form is offered
+to the user. Normally, the configuration object is not accessible without
+editing PHP code; this facility changes thing. The sensible thing to do
+is stipulate that all classes required by the directives you allow must
+be included.
+
+Unit testing
+------------
+
+Setting up the parsing and translation into our existing format would not
+be difficult to do. It might represent a good time for us to rethink our
+tests for these facilities; as creative as they are, they are often hacky
+and require public visibility for things that ought to be protected.
+This is especially applicable for our DefinitionCache tests.
+
+Migration
+---------
+
+Because we are not *adding* anything essentially new, it should be trivial
+to write a script to take our existing data and dump it into the new format.
+Well, not trivial, but fairly easy to accomplish. Primary implementation
+difficulties would probably involve formatting the file nicely.
+
+Backwards-compatibility
+-----------------------
+
+I expect that the ConfigSchema methods should stick around for a little bit,
+but display E_USER_NOTICE warnings that they are deprecated. This will
+require documentation!
+
+New stuff
+---------
+
+VERSION: Version number directive was introduced
+DEPRECATED-VERSION: If the directive was deprecated, when was it deprecated?
+DEPRECATED-USE: If the directive was deprecated, what should the user use now?
+REQUIRES: What classes does this configuration directive require, but are
+    not part of the HTML Purifier core?
+
+    vim: et sw=4 sts=4

docs/dev-naming.html

@@ -35,7 +35,7 @@ help you find the correct functionality more quickly.  Here they are:</p>
 <dt>Harness and Test are reserved class names for unit tests</dt>
     <dd>The suffix <code>Test</code> indicates that the class is a subclass of UnitTestCase
     (of the Simpletest library) and is testable. "Harness" indicates a subclass
-    of UnitTestCase that is not meant to be run but to be extended into 
+    of UnitTestCase that is not meant to be run but to be extended into
     concrete test cases and contains custom test methods (i.e. assert*())</dd>
 
 <dt>Class names do not necessarily represent inheritance hierarchies</dt>
@@ -51,7 +51,7 @@ help you find the correct functionality more quickly.  Here they are:</p>
     all must be present in order for proper functioning.</dd>
 
 <dt>Abbreviations are avoided</dt>
-    <dd>We try to avoid abbreviations as much as possible, but in some cases, 
+    <dd>We try to avoid abbreviations as much as possible, but in some cases,
     abbreviated version is more readable than the full version. Here, we
     list common abbreviations:
     <ul>
@@ -77,6 +77,6 @@ help you find the correct functionality more quickly.  Here they are:</p>
 
 </dl>
 
-<div id="version">$Id$</div>
-
 </body></html>
+
+<!-- vim: et sw=4 sts=4 -->

docs/dev-optimization.html

@@ -23,11 +23,10 @@ that itch, put it here!</p>
 <ul>
     <li>Make Tokens Flyweights (may prove problematic, probably not worth it)</li>
     <li>Rewrite regexps into PHP code</li>
-    <li>Serialize the Definition object</li>
     <li>Batch regexp validation (do as many per function call as possible)</li>
     <li>Parallelize strategies</li>
 </ul>
 
-<div id="version">$Id$</div>
-
 </body></html>
+
+<!-- vim: et sw=4 sts=4 -->

docs/dev-progress.html

@@ -34,6 +34,11 @@ thead th {text-align:left;padding:0.1em;background-color:#EEE;}
 <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>
+  <strong>Warning:</strong> This table is kept for historical purposes and
+  is not being actively updated.
+</p>
+
 <h2>Key</h2>
 
 <table cellspacing="0"><tbody>
@@ -148,7 +153,7 @@ thead th {text-align:left;padding:0.1em;background-color:#EEE;}
     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;
+<tr class="danger impl-yes"><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>
@@ -167,7 +172,7 @@ thead th {text-align:left;padding:0.1em;background-color:#EEE;}
     Mostly supported. Unknown target milestone.</td></tr>
 <tr><td>page-break-inside</td><td>ENUM(avoid, auto), Opera only. Unknown target milestone.</td></tr>
 <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),
+<tr class="danger impl-yes"><td>visibility</td><td>ENUM(visible, hidden, collapse),
     Dangerous</td></tr>
 <tr class="css1 feature impl-partial"><td>white-space</td><td>ENUM(normal, pre, nowrap, pre-wrap,
     pre-line), Spotty implementation:
@@ -298,6 +303,6 @@ Mozilla on inside and needs -moz-outline, no IE support.</td></tr>
 
 </table>
 
-<div id="version">$Id$</div>
-
 </body></html>
+
+<!-- vim: et sw=4 sts=4 -->

docs/enduser-customize.html

@@ -158,7 +158,7 @@
 <pre>$config = HTMLPurifier_Config::createDefault();
 $config->set('HTML', 'DefinitionID', 'enduser-customize.html tutorial');
 $config->set('HTML', 'DefinitionRev', 1);
-$def =& $config->getHTMLDefinition(true);</pre>
+$def = $config->getHTMLDefinition(true);</pre>
 
 <p>
   Assuming that HTML Purifier has already been properly loaded (hint:
@@ -206,15 +206,15 @@ $def =& $config->getHTMLDefinition(true);</pre>
 <h2>Turn off caching</h2>
 
 <p>
-  To make development easier, we're going to temporarily turn off 
+  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 =& $config->getHTMLDefinition(true);</pre>
+<strong>$config->set('Cache', 'DefinitionImpl', null); // remove this later!</strong>
+$def = $config->getHTMLDefinition(true);</pre>
 
 <p>
   A few things should be mentioned about the caching mechanism before
@@ -269,8 +269,8 @@ $def =& $config->getHTMLDefinition(true);</pre>
 <pre>$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 =& $config->getHTMLDefinition(true);
+$config->set('Cache', 'DefinitionImpl', null); // remove this later!
+$def = $config->getHTMLDefinition(true);
 <strong>$def->addAttribute('a', 'target', 'Enum#_blank,_self,_target,_top');</strong></pre>
 
 <p>
@@ -372,10 +372,10 @@ $def =& $config->getHTMLDefinition(true);
 
 <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>;
+  <a href="http://repo.or.cz/w/htmlpurifier.git?a=blob;hb=HEAD;f=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>.
+  <a href="http://repo.or.cz/w/htmlpurifier.git?a=tree;hb=HEAD;f=library/HTMLPurifier/AttrDef"><code>library/HTMLPurifier/AttrDef</code></a>.
 </p>
 
 <p>
@@ -387,8 +387,8 @@ $def =& $config->getHTMLDefinition(true);
 <pre>$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 =& $config->getHTMLDefinition(true);
+$config->set('Cache', 'DefinitionImpl', null); // remove this later!
+$def = $config->getHTMLDefinition(true);
 <strong>$def->addAttribute('a', 'target', new HTMLPurifier_AttrDef_Enum(
   array('_blank','_self','_target','_top')
 ));</strong></pre>
@@ -401,8 +401,8 @@ $def =& $config->getHTMLDefinition(true);
 
 <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 
+  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>
 
@@ -493,9 +493,9 @@ $def =& $config->getHTMLDefinition(true);
 <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 
+  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>
@@ -596,7 +596,7 @@ $def =& $config->getHTMLDefinition(true);
   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 
+  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>
 
@@ -676,7 +676,7 @@ $def =& $config->getHTMLDefinition(true);
   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 
+  attribute even though it uses the <code>Core</code> collection, and
   the DTD and XML Schemas supplied by W3C support our interpretation.
 </p>
 
@@ -734,12 +734,12 @@ $def =& $config->getHTMLDefinition(true);
 <pre>$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 =& $config->getHTMLDefinition(true);
+$config->set('Cache', 'DefinitionImpl', null); // remove this later!
+$def = $config->getHTMLDefinition(true);
 $def->addAttribute('a', 'target', new HTMLPurifier_AttrDef_Enum(
   array('_blank','_self','_target','_top')
 ));
-<strong>$form =& $def->addElement(
+<strong>$form = $def->addElement(
   'form',   // name
   'Block',  // content set
   'Flow', // allowed children
@@ -764,7 +764,7 @@ $form->excludes = array('form' => true);</strong></pre>
 <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
+  check the <a href="http://repo.or.cz/w/htmlpurifier.git?a=tree;hb=HEAD;f=library/HTMLPurifier/HTMLModule"><code>library/HTMLPurifier/HTMLModule/</code></a> directory
   in your local HTML Purifier installation.
 </p>
 
@@ -789,10 +789,10 @@ $form->excludes = array('form' => true);</strong></pre>
 </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>
+  <li><a href="http://repo.or.cz/w/htmlpurifier.git?a=blob;hb=HEAD;f=library/HTMLPurifier/HTMLModule.php"><code>library/HTMLPurifier/HTMLModule.php</code></a></li>
+  <li><a href="http://repo.or.cz/w/htmlpurifier.git?a=blob;hb=HEAD;f=library/HTMLPurifier/ElementDef.php"><code>library/HTMLPurifier/ElementDef.php</code></a></li>
 </ul>
 
-<div id="version">$Id: enduser-tidy.html 1158 2007-06-18 19:26:29Z Edward $</div>
-
 </body></html>
+
+<!-- vim: et sw=4 sts=4 -->

docs/enduser-id.html

@@ -141,7 +141,7 @@ anchors is beyond me.</p>
 
 <p>Don't come crying to me when your page mysteriously stops validating, though.</p>
 
-<div id="version">$Id$</div>
-
 </body>
 </html>
+
+<!-- vim: et sw=4 sts=4 -->

docs/enduser-overview.txt

@@ -55,3 +55,5 @@ HTML tags.  Things like blog comments are, in all likelihood, most appropriately
 written in an extremely restrictive set of markup that doesn't require
 all this functionality (or not written in HTML at all), although this may
 be changing in the future with the addition of levels of filtering.
+
+    vim: et sw=4 sts=4

docs/enduser-security.txt

@@ -14,3 +14,5 @@ to be effective. Things to remember:
 
 4. CSS: document pending
 Explain which CSS styles we blocked and why.
+
+    vim: et sw=4 sts=4

docs/enduser-slow.html

@@ -17,25 +17,25 @@
 <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 
+<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 
+<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 
+<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>
@@ -66,14 +66,14 @@ user makes a typo. </p>
 
 <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 
+<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>
@@ -108,10 +108,12 @@ plaintext mode). </p>
 <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++. 
+<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>
+
+<!-- vim: et sw=4 sts=4 -->

docs/enduser-tidy.html

@@ -50,7 +50,7 @@ not need Tidy installed on your PHP to use these features!</strong></p>
 
 <h2>What are levels?</h2>
 
-<p>Levels describe how aggressive the Tidy module should be when 
+<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>
@@ -225,6 +225,6 @@ 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>
+
+<!-- vim: et sw=4 sts=4 -->

docs/enduser-uri-filter.html

@@ -33,9 +33,9 @@
 
 <pre>class HTMLPurifier_URIFilter_<strong>NameOfFilter</strong> extends HTMLPurifier_URIFilter
 {
-    var $name = '<strong>NameOfFilter</strong>';
-    function prepare($config) {}
-    function filter(&$uri, $config, &$context) {}
+    public $name = '<strong>NameOfFilter</strong>';
+    public function prepare($config) {}
+    public function filter(&$uri, $config, $context) {}
 }</pre>
 
 <p>
@@ -56,12 +56,12 @@
 
 <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);
+    public $scheme, $userinfo, $host, $port, $path, $query, $fragment;
+    public function HTMLPurifier_URI($scheme, $userinfo, $host, $port, $path, $query, $fragment);
+    public function toString();
+    public function copy();
+    public function getSchemeObj($config, $context);
+    public function validate($config, $context);
 }</pre>
 
 <p>
@@ -92,7 +92,7 @@
 </tbody></table>
 
 <p>
-  Because the URI is presented to us in this form, and not 
+  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:
@@ -130,30 +130,26 @@
 </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:
+  Let's suppose I wanted to write a filter that converted links with a
+  custom <code>image</code> scheme to its corresponding real path on
+  our website:
 </p>
 
-<pre>class HTMLPurifier_URIFilter_ConvertIDNToPunycode extends HTMLPurifier_URIFilter
+<pre>class HTMLPurifier_URIFilter_TransformImageScheme 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;
+    public $name = 'TransformImageScheme';
+    public function filter(&$uri, $config, $context) {
+        if ($uri->scheme !== 'image') return true;
+        $img_name = $uri->path;
+        // Overwrite the previous URI object
+        $uri = new HTMLPurifier_URI('http', null, null, null, '/img/' . $img_name . '.png', null, null);
         return true;
     }
 }</pre>
 
 <p>
-  Notice I did not <code>return $uri;</code>.
+  Notice I did not <code>return $uri;</code>. This filter would turn
+  <code>image:Foo</code> into <code>/img/Foo.png</code>.
 </p>
 
 <h2>Activating your filter</h2>
@@ -163,7 +159,7 @@
   to use it. Fortunately, this part's simple:
 </p>
 
-<pre>$uri =& $config->getDefinition('URI');
+<pre>$uri = $config->getDefinition('URI');
 $uri->addFilter(new HTMLPurifier_URIFilter_<strong>NameOfFilter</strong>());</pre>
 
 <p>
@@ -177,7 +173,7 @@ $uri->addFilter(new HTMLPurifier_URIFilter_<strong>NameOfFilter</strong>());</pr
     'URI', '<strong>NameOfFilter</strong>', false, 'bool',
     '<strong>What your filter does.</strong>'
 );
-$uri =& $config->getDefinition('URI', true);
+$uri = $config->getDefinition('URI', true);
 $uri->registerFilter(new HTMLPurifier_URIFilter_<strong>NameOfFilter</strong>());
 </pre>
 
@@ -186,16 +182,35 @@ $uri->registerFilter(new HTMLPurifier_URIFilter_<strong>NameOfFilter</strong>())
   is set to true.
 </p>
 
+<h2>Post-filter</h2>
+
+<p>
+    Remember our TransformImageScheme filter? That filter acted before we had
+    performed scheme validation; otherwise, the URI would have been filtered
+    out when it was discovered that there was no image scheme. Well, a post-filter
+    is run after scheme specific validation, so it's ideal for bulk
+    post-processing of URIs, including munging. To specify a URI as a post-filter,
+    set the <code>$post</code> member variable to TRUE.
+</p>
+
+<pre>class HTMLPurifier_URIFilter_MyPostFilter extends HTMLPurifier_URIFilter
+{
+    public $name = 'MyPostFilter';
+    public $post = true;
+    // ... extra code here
+}
+</pre>
+
 <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
+  <a href="http://repo.or.cz/w/htmlpurifier.git?a=tree;hb=HEAD;f=library/HTMLPurifier/URIFilter">URIFilter</a>
+  directory for more implementation examples, and see <a href="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>
+
+<!-- vim: et sw=4 sts=4 -->

docs/enduser-utf8.html

@@ -5,7 +5,6 @@
 <meta http-equiv="Content-Type" content="text/html; charset=UTF-8" />
 <meta name="description" content="Describes the rationale for using UTF-8, the ramifications otherwise, and how to make the switch." />
 <link rel="stylesheet" type="text/css" href="./style.css" />
-<script defer="defer" type="text/javascript" src="./toc-gen.js"></script>
 <style type="text/css">
     .minor td {font-style:italic;}
 </style>
@@ -107,7 +106,7 @@ there are now many character encodings floating around.</p>
     interpret raw zeroes and ones into real characters. It
     usually does this by pairing numbers with characters.</p>
     <p>There are many different types of character encodings floating
-    around, but the ones we deal most frequently with are ASCII, 
+    around, but the ones we deal most frequently with are ASCII,
     8-bit encodings, and Unicode-based encodings.</p>
     <ul>
         <li><strong>ASCII</strong> is a 7-bit encoding based on the
@@ -119,9 +118,8 @@ there are now many character encodings floating around.</p>
             see a page on the web, chances are it's encoded in one
             of these encodings.</li>
         <li><strong>Unicode-based encodings</strong> implement the
-            Unicode standard and include UTF-8, UCS-2 and UTF-16.
-            They go beyond 8-bits (the first two are variable length,
-            while the second one uses 16-bits), and support almost
+            Unicode standard and include UTF-8, UTF-16 and UTF-32/UCS-4.
+            They go beyond 8-bits and support almost
             every language in the world. UTF-8 is gaining traction
             as the dominant international encoding of the web.</li>
     </ul>
@@ -308,7 +306,7 @@ languages</a>. The appropriate code is:</p>
 
 <p>...replacing UTF-8 with whatever your embedded encoding is.
 This code must come before any output, so be careful about
-stray whitespace in your application (i.e., any whitespace before 
+stray whitespace in your application (i.e., any whitespace before
 output excluding whitespace within &lt;?php ?&gt; tags).</p>
 
 <h4 id="fixcharset-server-phpini">PHP ini directive</h4>
@@ -368,9 +366,9 @@ to send anything at all:</p>
 <pre><a href="http://httpd.apache.org/docs/1.3/mod/core.html#adddefaultcharset">AddDefaultCharset</a> Off</pre>
 
 <p>...making your internal charset declaration (usually the <code>META</code> tags)
-the sole source of character encoding 
-information. In these cases, it is <em>especially</em> important to make 
-sure you have valid <code>META</code> tags on your pages and all the 
+the sole source of character encoding
+information. In these cases, it is <em>especially</em> important to make
+sure you have valid <code>META</code> tags on your pages and all the
 text before them is ASCII.</p>
 
 <blockquote class="aside"><p>These directives can also be
@@ -445,9 +443,9 @@ Declarations. They look like:</p>
 <p>For XHTML, this XML Declaration theoretically
 overrides the <code>META</code> tag. In reality, this happens only when the
 XHTML is actually served as legit XML and not HTML, which is almost always
-never due to Internet Explorer's lack of support for 
+never due to Internet Explorer's lack of support for
 <code>application/xhtml+xml</code> (even though doing so is often
-argued to be <a href="http://www.hixie.ch/advocacy/xhtml">good 
+argued to be <a href="http://www.hixie.ch/advocacy/xhtml">good
 practice</a> and is required by the XHTML 1.1 specification).</p>
 
 <p>For XML, however, this XML Declaration is extremely important.
@@ -458,7 +456,7 @@ ISO-8859-1 encoding (you see this in garbled RSS feeds).</p>
 
 <p>In short, if you use XHTML and have gone through the
 trouble of adding the XML Declaration, make sure it jives
-with your <code>META</code> tags (which should only be present 
+with your <code>META</code> tags (which should only be present
 if served in text/html) and HTTP headers.</p>
 
 <h3 id="fixcharset-internals">Inside the process</h3>
@@ -483,7 +481,7 @@ if we don't know it's character encoding? And how do we figure out
 the character encoding, if we don't know the contents of the
 <code>META</code> tag?</p>
 
-<p>Fortunantely for us, the characters we need to write the
+<p>Fortunately for us, the characters we need to write the
 <code>META</code> are in ASCII, which is pretty much universal
 over every character encoding that is in common use today. So,
 all the web-browser has to do is parse all the way down until
@@ -491,7 +489,7 @@ it gets to the Content-Type tag, extract the character encoding
 tag, then re-parse the document according to this new information.</p>
 
 <p>Obviously this is complicated, so browsers prefer the simpler
-and more efficient solution: get the character encoding from a 
+and more efficient solution: get the character encoding from a
 somewhere other than the document itself, i.e. the HTTP headers,
 much to the chagrin of HTML authors who can't set these headers.</p>
 
@@ -528,7 +526,7 @@ you don't have to use those user-unfriendly entities.</p>
 
 <h3 id="whyutf8-user">User-friendly</h3>
 
-<p>Websites encoded in Latin-1 (ISO-8859-1) which ocassionally need
+<p>Websites encoded in Latin-1 (ISO-8859-1) which occasionally need
 a special character outside of their scope often will use a character
 entity reference to achieve the desired effect. For instance, &theta; can be
 written <code>&amp;theta;</code>, regardless of the character encoding's
@@ -580,19 +578,21 @@ files.</p>
 <a href="http://web.archive.org/web/20060427015200/ppewww.ph.gla.ac.uk/~flavell/charset/form-i18n.html">
 <code>FORM</code> submission and i18n</a>. That document contains lots
 of useful information, but is written in a rambly manner, so
-here I try to get right to the point. (Note: the original has 
+here I try to get right to the point. (Note: the original has
 disappeared off the web, so I am linking to the Web Archive copy.)</p>
 
 <h4 id="whyutf8-forms-urlencoded"><code>application/x-www-form-urlencoded</code></h4>
 
 <p>This is the Content-Type that GET requests must use, and POST requests
-use by default. It involves the ubiquituous percent encoding format that
+use by default. It involves the ubiquitous percent encoding format that
 looks something like: <code>%C3%86</code>. There is no official way of
 determining the character encoding of such a request, since the percent
 encoding operates on a byte level, so it is usually assumed that it
 is the same as the encoding the page containing the form was submitted
-in. You'll run into very few problems if you only use characters in
-the character encoding you chose.</p>
+in. (<a href="http://tools.ietf.org/html/rfc3986#section-2.5">RFC 3986</a>
+recommends that textual identifiers be translated to UTF-8; however, browser
+compliance is spotty.) You'll run into very few problems
+if you only use characters in the character encoding you chose.</p>
 
 <p>However, once you start adding characters outside of your encoding
 (and this is a lot more common than you may think: take curly
@@ -674,7 +674,7 @@ it up to the module iconv to do the dirty work.</p>
 <p>This approach, however, is not perfect. iconv is blithely unaware
 of HTML character entities. HTML Purifier, in order to
 protect against sophisticated escaping schemes, normalizes all character
-and numeric entitie references before processing the text. This leads to
+and numeric entity references before processing the text. This leads to
 one important ramification:</p>
 
 <p><strong>Any character that is not supported by the target character
@@ -770,7 +770,7 @@ the text when you try to convert it to UTF-8. You'll have to convert
 it to a binary field, convert it to a Shift-JIS field (the real encoding),
 and then finally to UTF-8. Many a website had pages irreversibly mangled
 because they didn't realize that they'd been deluding themselves about
-the character encoding all along, don't become the next victim.</p>
+the character encoding all along; don't become the next victim.</p>
 
 <p>For <a href="http://www.postgresql.org/docs/8.2/static/multibyte.html">PostgreSQL</a>, there appears to be no direct way to change the
 encoding of a database (as of 8.2). You will have to dump the data, and then reimport
@@ -790,7 +790,7 @@ usually supported).</p>
 
 <h4 id="migrate-db-binary">Binary</h4>
 
-<p>Due to the abovementioned compatibility issues, a more interoperable
+<p>Due to the aforementioned compatibility issues, a more interoperable
 way of storing UTF-8 text is to stuff it in a binary datatype.
 <code>CHAR</code> becomes <code>BINARY</code>, <code>VARCHAR</code> becomes
 <code>VARBINARY</code> and <code>TEXT</code> becomes <code>BLOB</code>.
@@ -886,7 +886,7 @@ sure the page is saved WITHOUT the BOM.</p>
 </blockquote>
 
 <p>If you are reading in text files to insert into the middle of another
-page, it is strongly advised (but not strictly necessary) that you replace out the UTF-8 byte 
+page, it is strongly advised (but not strictly necessary) that you replace out the UTF-8 byte
 sequence for BOM <code>&quot;\xEF\xBB\xBF&quot;</code> before inserting it in,
 via:</p>
 
@@ -917,8 +917,8 @@ anyway. So we'll deal with the other two edge cases.</p>
 would like to read your website but get heaps of question marks or
 other meaningless characters. Fixing this problem requires the
 installation of a font or language pack which is often highly
-dependent on what the language is. <a href="http://bn.wikipedia.org/wiki/%E0%A6%89%E0%A6%87%E0%A6%95%E0%A6%BF%E0%A6%AA%E0%A7%87%E0%A6%A1%E0%A6%BF%E0%A6%AF%E0%A6%BC%E0%A6%BE:Bangla_script_display_help">Here is an example</a>
-of such a help file for the Bengali language, I am sure there are
+dependent on what the language is. <a href="http://bn.wikipedia.org/wiki/%E0%A6%89%E0%A6%87%E0%A6%95%E0%A6%BF%E0%A6%AA%E0%A7%87%E0%A6%A1%E0%A6%BF%E0%A6%AF%E0%A6%BC%E0%A6%BE:Bangla_script_display_and_input_help">Here is an example</a>
+of such a help file for the Bengali language; I am sure there are
 others out there too. You just have to point users to the appropriate
 help file.</p>
 
@@ -928,7 +928,7 @@ help file.</p>
 characters embedded in what otherwise would be very bland ASCII are
 letters of the
 <a href="http://en.wikipedia.org/wiki/International_Phonetic_Alphabet">International
-Phonetic Alphabet (IPA)</a>, use to designate pronounciations in a very standard
+Phonetic Alphabet (IPA)</a>, use to designate pronunciations in a very standard
 manner (you probably see them all the time in your dictionary). Your
 average font probably won't have support for all of the IPA characters
 like &#664; (bilabial click) or &#658; (voiced postalveolar fricative).
@@ -941,15 +941,15 @@ most widely used browser in the entire world? Microsoft IE 6
 is not smart enough to borrow from other fonts when a character isn't
 present, so more often than not you'll be slapped with a nice big &#65533;.
 To get things to work, MSIE 6 needs a little nudge. You could configure it
-to use a different font to render the text, but you can acheive the same
+to use a different font to render the text, but you can achieve the same
 effect by selectively changing the font for blocks of special characters
 to known good Unicode fonts.</p>
 
-<p>Fortunantely, the folks over at Wikipedia have already done all the
+<p>Fortunately, the folks over at Wikipedia have already done all the
 heavy lifting for you. Get the CSS from the horses mouth here:
 <a href="http://en.wikipedia.org/wiki/MediaWiki:Common.css">Common.css</a>,
 and search for &quot;.IPA&quot; There are also a smattering of
-other classes you can use for other purposes, check out 
+other classes you can use for other purposes, check out
 <a href="http://meta.wikimedia.org/wiki/Help:Special_characters#Displaying_Special_Characters">this page</a>
 for more details. For you lazy ones, this should work:</p>
 
@@ -972,7 +972,7 @@ users.</p>
 <h3 id="migrate-variablewidth">Dealing with variable width in functions</h3>
 
 <p>When people claim that PHP6 will solve all our Unicode problems, they're
-misinformed. It will not fix any of the abovementioned troubles. It will,
+misinformed. It will not fix any of the aforementioned troubles. It will,
 however, fix the problem we are about to discuss: processing UTF-8 text
 in PHP.</p>
 
@@ -1035,7 +1035,7 @@ directory.</p>
 <p>Well, that's it. Hopefully this document has served as a very
 practical springboard into knowledge of how UTF-8 works.  You may have
 decided that you don't want to migrate yet: that's fine, just know
-what will happen to your output and what bug reports you may recieve.</p>
+what will happen to your output and what bug reports you may receive.</p>
 
 <p>Many other developers have already discussed the subject of Unicode,
 UTF-8 and internationalization, and I would like to defer to them for
@@ -1055,3 +1055,5 @@ a more in-depth look into character sets and encodings.</p>
 
 </body>
 </html>
+
+<!-- vim: et sw=4 sts=4 -->

docs/enduser-youtube.html

@@ -70,14 +70,12 @@ into your documents. YouTube's code goes like this:</p>
 class=&quot;embed-youtube&quot;&gt;AyPzM5WK8ys&lt;/span&gt;</code> your
 application can reconstruct the full object from this small snippet that
 passes through HTML Purifier <em>unharmed</em>.
-<a href="http://htmlpurifier.org/svnroot/htmlpurifier/trunk/library/HTMLPurifier/Filter/YouTube.php">Show me the code!</a></p>
+<a href="http://repo.or.cz/w/htmlpurifier.git?a=blob;hb=HEAD;f=library/HTMLPurifier/Filter/YouTube.php">Show me the code!</a></p>
 
 <p>And the corresponding usage:</p>
 
 <pre>&lt;?php
-    // assuming $purifier is an instance of HTMLPurifier
-    require_once 'HTMLPurifier/Filter/YouTube.php';
-    $purifier-&gt;addFilter(new HTMLPurifier_Filter_YouTube());
+    $config->set('Filter', 'YouTube', true);
 ?&gt;</pre>
 
 <p>There is a bit going in the two code snippets, so let's explain.</p>
@@ -150,3 +148,5 @@ with the core!</p>
 
 </body>
 </html>
+
+<!-- vim: et sw=4 sts=4 -->

docs/examples/basic.php

@@ -20,3 +20,4 @@ $pure_html = $purifier->purify($html);
 
 echo '<pre>' . htmlspecialchars($pure_html) . '</pre>';
 
+// vim: et sw=4 sts=4

docs/fixquotes.htc

@@ -4,3 +4,5 @@ function init() {
   element.innerHTML = '“'+element.innerHTML+'”';
 }
 </script>
+
+<!-- vim: et sw=4 sts=4 -->

docs/index.html

@@ -60,10 +60,16 @@ conventions.</p>
 <dt><a href="dev-optimization.html">Optimization</a></dt>
 <dd>Discusses possible methods of optimizing HTML Purifier.</dd>
 
+<dt><a href="dev-flush.html">Flushing the Purifier</a></dt>
+<dd>Discusses when to flush HTML Purifier's various caches.</dd>
+
 <dt><a href="dev-advanced-api.html">Advanced API</a></dt>
-<dd>Functional specification for HTML Purifier's advanced API for defining
+<dd>Specification for HTML Purifier's advanced API for defining
 custom filtering behavior.</dd>
 
+<dt><a href="dev-config-schema.html">Config Schema</a></dt>
+<dd>Describes config schema framework in HTML Purifier.</dd>
+
 </dl>
 
 <h2>Proposals</h2>
@@ -92,8 +98,8 @@ the code. They may be upgraded to HTML files or stay as TXT scratchpads.</p>
 <table class="table">
 
 <thead><tr>
-    <th width="10%">Type</th>
-    <th width="20%">Name</th>
+    <th style="width:10%">Type</th>
+    <th style="width:20%">Name</th>
     <th>Description</th>
 </tr></thead>
 
@@ -113,7 +119,7 @@ the code. They may be upgraded to HTML files or stay as TXT scratchpads.</p>
 
 <tr>
     <td>Development</td>
-    <td><a href="enduser-code-quality.txt">Code Quality Issues</a></td>
+    <td><a href="dev-code-quality.txt">Code Quality Issues</a></td>
     <td>Enumerates code quality issues and places that need to be refactored.</td>
 </tr>
 
@@ -135,6 +141,12 @@ the code. They may be upgraded to HTML files or stay as TXT scratchpads.</p>
     <td>Assorted configuration options that could be implemented.</td>
 </tr>
 
+<tr>
+    <td>Proposal</td>
+    <td><a href="proposal-css-extraction.txt">CSS extraction</a></td>
+    <td>Taking the inline CSS out of documents and into <code>style</code>.</td>
+</tr>
+
 <tr>
     <td>Reference</td>
     <td><a href="ref-content-models.txt">Handling Content Model Changes</a></td>
@@ -163,6 +175,7 @@ the code. They may be upgraded to HTML files or stay as TXT scratchpads.</p>
 
 </table>
 
-<div id="version">$Id$</div>
 </body>
 </html>
+
+<!-- vim: et sw=4 sts=4 -->

docs/proposal-colors.html

@@ -42,7 +42,7 @@ into the mix.</li>
 something like that?</li>
 </ol>
 
-<div id="version">$Id$</div>
-
 </body>
 </html>
+
+<!-- vim: et sw=4 sts=4 -->

docs/proposal-config.txt

@@ -19,3 +19,5 @@ 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.
+
+    vim: et sw=4 sts=4

docs/proposal-css-extraction.txt

@@ -0,0 +1,34 @@
+
+Extracting inline CSS from HTML Purifier
+    voodoofied: Assigning semantics to elements
+
+Sander Tekelenburg brought to my attention the poor programming style of
+inline CSS in HTML documents.  In an ideal world, we wouldn't be using inline
+CSS at all: everything would be assigned using semantic class attributes
+from an external stylesheet.
+
+With ExtractStyleBlocks and CSSTidy, this is now possible (when allowed, users
+can specify a style element which gets extracted from the user-submitted HTML, which
+the application can place in the head of the HTML document).  But there still
+is the issue of inline CSS that refuses to go away.
+
+The basic idea behind this feature is assign every element a unique identifier,
+and then move all of the CSS data to a style-sheet. This HTML:
+
+<div style="text-align:center">Big <span style="color:red;">things</span>!</div>
+
+into
+
+<div id="hp-12345">Big <span id="hp-12346">things</span>!</div>
+
+and a stylesheet that is:
+
+#hp-12345 {text-align:center;}
+#hp-12346 {color:red;}
+
+Beyond that, HTML Purifier can magically merge common CSS values together,
+and a whole manner of other heuristic things.  HTML Purifier should also
+make it easy for an admin to re-style the HTML semantically. Speed is not
+an issue. Also, better WYSIWYG editors are needed.
+
+    vim: et sw=4 sts=4

docs/proposal-errors.txt

@@ -0,0 +1,211 @@
+Considerations for ErrorCollection
+
+Presently, HTML Purifier takes a code-execution centric approach to handling
+errors. Errors are organized and grouped according to which segment of the
+code triggers them, not necessarily the portion of the input document that
+triggered the error. This means that errors are pseudo-sorted by category,
+rather than location in the document.
+
+One easy way to "fix" this problem would be to re-sort according to line number.
+However, the "category" style information we derive from naively following
+program execution is still useful. After all, each of the strategies which
+can report errors still process the document mostly linearly. Furthermore,
+not only do they process linearly, but the way they pass off operations to
+sub-systems mirrors that of the document. For example, AttrValidator will
+linearly proceed through elements, and on each element will use AttrDef to
+validate those contents. From there, the attribute might have more
+sub-components, which have execution passed off accordingly.
+
+In fact, each strategy handles a very specific class of "error."
+
+RemoveForeignElements   - element tokens
+MakeWellFormed          - element token ordering
+FixNesting              - element token ordering
+ValidateAttributes      - attributes of elements
+
+The crucial point is that while we care about the hierarchy governing these
+different errors, we *don't* care about any other information about what actually
+happens to the elements. This brings up another point: if HTML Purifier fixes
+something, this is not really a notice/warning/error; it's really a suggestion
+of a way to fix the aforementioned defects.
+
+In short, the refactoring to take this into account kinda sucks.
+
+Errors should not be recorded in order that they are reported. Instead, they
+should be bound to the line (and preferably element) in which they were found.
+This means we need some way to uniquely identify every element in the document,
+which doesn't presently exist. An easy way of adding this would be to track
+line columns. An important ramification of this is that we *must* use the
+DirectLex implementation.
+
+    1. Implement column numbers for DirectLex [DONE!]
+    2. Disable error collection when not using DirectLex [DONE!]
+
+Next, we need to re-orient all of the error declarations to place CurrentToken
+at utmost important. Since this is passed via Context, it's not always clear
+if that's available. ErrorCollector should complain HARD if it isn't available.
+There are some locations when we don't have a token available. These include:
+
+    * Lexing - this can actually have a row and column, but NOT correspond to
+      a token
+    * End of document errors - bump this to the end
+
+Actually, we *don't* have to complain if CurrentToken isn't available; we just
+set it as a document-wide error. And actually, nothing needs to be done here.
+
+Something interesting to consider is whether or not we care about the locations
+of attributes and CSS properties, i.e. the sub-objects that compose these things.
+In terms of consistency, at the very least attributes should have column/line
+numbers attached to them. However, this may be overkill, as attributes are
+uniquely identifiable. You could go even further, with CSS, but they are also
+uniquely identifiable.
+
+Bottom-line is, however, this information must be available, in form of the
+CurrentAttribute and CurrentCssProperty (theoretical) context variables, and
+it must be used to organize the errors that the sub-processes may throw.
+There is also a hierarchy of sorts that may make merging this into one context
+variable more sense, if it hadn't been for HTML's reasonably rigid structure.
+A CSS property will never contain an HTML attribute. So we won't ever get
+recursive relations, and having multiple depths won't ever make sense. Leave
+this be.
+
+We already have this information, and consequently, using start and end is
+*unnecessary*, so long as the context variables are set appropriately. We don't
+care if an error was thrown by an attribute transform or an attribute definition;
+to the end user these are the same (for a developer, they are different, but
+they're better off with a stack trace (which we should add support for) in such
+cases).
+
+    3. Remove start()/end() code. Don't get rid of recursion, though [DONE]
+    4. Setup ErrorCollector to use context information to setup hierarchies.
+       This may require a different internal format. Use objects if it gets
+       complex. [DONE]
+
+       ASIDE
+            More on this topic: since we are now binding errors to lines
+            and columns, a particular error can have three relationships to that
+            specific location:
+
+            1. The token at that location directly
+                RemoveForeignElements
+                AttrValidator (transforms)
+                MakeWellFormed
+            2. A "component" of that token (i.e. attribute)
+                AttrValidator (removals)
+            3. A modification to that node (i.e. contents from start to end
+               token) as a whole
+                FixNesting
+
+            This needs to be marked accordingly. In the presentation, it might
+            make sense keep (3) separate, have (2) a sublist of (1). (1) can
+            be a closing tag, in which case (3) makes no sense at all, OR it
+            should be related with its opening tag (this may not necessarily
+            be possible before MakeWellFormed is run).
+
+            So, the line and column counts as our identifier, so:
+
+            $errors[$line][$col] = ...
+
+            Then, we need to identify case 1, 2 or 3. They are identified as
+            such:
+
+            1. Need some sort of semaphore in RemoveForeignElements, etc.
+            2. If CurrentAttr/CurrentCssProperty is non-null
+            3. Default (FixNesting, MakeWellFormed)
+
+            One consideration about (1) is that it usually is actually a
+            (3) modification, but we have no way of knowing about that because
+            of various optimizations. However, they can probably be treated
+            the same. The other difficulty is that (3) is never a line and
+            column; rather, it is a range (i.e. a duple) and telling the user
+            the very start of the range may confuse them. For example,
+
+            <b>Foo<div>bar</div></b>
+            ^     ^
+
+            The node being operated on is <b>, so the error would be assigned
+            to the first caret, with a "node reorganized" error. Then, the
+            ChildDef would have submitted its own suggestions and errors with
+            regard to what's going in the internals.  So I suppose this is
+            ok. :-)
+
+            Now, the structure of the earlier mentioned ... would be something
+            like this:
+
+            object {
+                type = (token|attr|property),
+                value, // appropriate for type
+                errors => array(),
+                sub-errors = [recursive],
+            }
+
+            This helps us keep things agnostic. It is also sufficiently complex
+            enough to warrant an object.
+
+So, more wanking about the object format is in order. The way HTML Purifier is
+currently setup, the only possible hierarchy is:
+
+    token -> attr -> css property
+
+These relations do not exist all of the time; a comment or end token would not
+ever have any attributes, and non-style attributes would never have CSS properties
+associated with them.
+
+I believe that it is worth supporting multiple paths. At some point, we might
+have a hierarchy like:
+
+    * -> syntax
+      -> token -> attr -> css property
+                       -> url
+               -> css stylesheet <style>
+
+et cetera. Now, one of the practical implications of this is that every "node"
+on our tree is well-defined, so in theory it should be possible to either 1.
+create a separate class for each error struct, or 2. embed this information
+directly into HTML Purifier's token stream.  Embedding the information in the
+token stream is not a terribly good idea, since tokens can be removed, etc.
+So that leaves us with 1... and if we use a generic interface we can cut down
+on a lot of code we might need. So let's leave it like this.
+
+~~~~
+
+Then we setup suggestions.
+
+    5. Setup a separate error class which tells the user any modifications
+       HTML Purifier made.
+
+Some information about this:
+
+Our current paradigm is to tell the user what HTML Purifier did to the HTML.
+This is the most natural mode of operation, since that's what HTML Purifier
+is all about; it was not meant to be a validator.
+
+However, most other people have experience dealing with a validator. In cases
+where HTML Purifier unambiguously does the right thing, simply giving the user
+the correct version isn't a bad idea, but problems arise when:
+
+- The user has such bad HTML we do something odd, when we should have just
+  flagged the HTML as an error. Such examples are when we do things like
+  remove text from directly inside a <table> tag. It was probably meant to
+  be in a <td> tag or be outside the table, but we're not smart enough to
+  realize this so we just remove it. In such a case, we should tell the user
+  that there was foreign data in the table, but then we shouldn't "demand"
+  the user remove the data; it's more of a "here's a possible way of
+  rectifying the problem"
+
+- Giving line context for input is hard enough, but feasible; giving output
+  line context will be extremely difficult due to shifting lines; we'd probably
+  have to track what the tokens are and then find the appropriate out context
+  and it's not guaranteed to work etc etc etc.
+
+````````````
+
+Don't forget to spruce up output.
+
+    6. Output needs to automatically give line and column numbers, basically
+       "at line" on steroids. Look at W3C's output; it's ok. [PARTIALLY DONE]
+
+       - We need a standard CSS to apply (check demo.css for some starting
+         styling; some buttons would also be hip)
+
+    vim: et sw=4 sts=4

docs/proposal-filter-levels.txt

@@ -133,3 +133,5 @@ Dramatic - border, list-style-position (list-style), margin, padding,
 
 Dramatic elements substantially change the look of text in ways that should
 probably have been reserved to other areas.
+
+    vim: et sw=4 sts=4

docs/proposal-language.txt

@@ -60,3 +60,5 @@ Neat functionality:
 -  Roman numeral formatting
 
 Items marked with a + likely need to be addressed by HTML Purifier
+
+    vim: et sw=4 sts=4

docs/proposal-new-directives.txt

@@ -16,7 +16,7 @@ implemented, give us a ring, and we'll move it up the priority chain.
     %Attr.ClassBlacklist. When it's Whitelist, only allow those in
     %Attr.ClassWhitelist.
 
-%Attr.MaxWidth, 
+%Attr.MaxWidth,
 %Attr.MaxHeight - caps for width and height related checks.
     (the hack in Pixels for an image crashing attack could be replaced by this)
 
@@ -41,3 +41,4 @@ implemented, give us a ring, and we'll move it up the priority chain.
     absolute DNS.  While this is actually the preferred method according to
     the RFC, most people opt to use a relative domain name relative to . (root).
 
+    vim: et sw=4 sts=4

docs/ref-content-models.txt

@@ -46,3 +46,5 @@ 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.
+
+    vim: et sw=4 sts=4

docs/ref-css-length.txt

@@ -22,7 +22,9 @@ Relative:
     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 
+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).
+
+    vim: et sw=4 sts=4

docs/ref-devnetwork.html

@@ -40,6 +40,7 @@ the development of this library in these forum threads:</p>
 
 <p>...as well as any I may have forgotten.</p>
 
-<div id="version">$Id$</div>
 </body>
 </html>
+
+<!-- vim: et sw=4 sts=4 -->

docs/ref-html-modularization.txt

@@ -1,8 +1,8 @@
 
 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/>
+WARNING: This document was drafted before the implementation of this
+    system, and some implementation details may have evolved over time.
 
 HTML Purifier uses the modularization of XHTML
 <http://www.w3.org/TR/xhtml-modularization/> to organize the internals
@@ -121,7 +121,7 @@ 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 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
@@ -162,3 +162,5 @@ 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.
+
+    vim: et sw=4 sts=4

docs/ref-proprietary-tags.txt

@@ -22,3 +22,5 @@ HTML Purifier context.
 
 These should be put into their own Tidy module, not loaded by default(?). These
 all qualify as "lenient" transforms.
+
+    vim: et sw=4 sts=4

docs/ref-whatwg.txt

@@ -18,7 +18,9 @@ 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 
+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>).
+
+    vim: et sw=4 sts=4

docs/specimens/LICENSE

@@ -1,8 +1,10 @@
-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.
+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.
+
+    vim: et sw=4 sts=4

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

@@ -162,4 +162,6 @@ div.segment {width:250px; float:left; margin-top:1em;}
 </div>
 
 </body>
-</html>
+</html>
+
+<!-- vim: et sw=4 sts=4 -->

docs/specimens/jochem-blok-word.html

@@ -0,0 +1,131 @@
+<html xmlns:v="urn:schemas-microsoft-com:vml" xmlns:o="urn:schemas-microsoft-com:office:office" xmlns:w="urn:schemas-microsoft-com:office:word" xmlns:m="http://schemas.microsoft.com/office/2004/12/omml" xmlns="http://www.w3.org/TR/REC-html40">
+
+<head>
+<META HTTP-EQUIV="Content-Type" CONTENT="text/html; charset=us-ascii">
+<meta name=Generator content="Microsoft Word 12 (filtered medium)">
+<!--[if !mso]>
+<style>
+v\:* {behavior:url(#default#VML);}
+o\:* {behavior:url(#default#VML);}
+w\:* {behavior:url(#default#VML);}
+..shape {behavior:url(#default#VML);}
+</style>
+<![endif]-->
+<style>
+<!--
+ /* Font Definitions */
+ @font-face
+	{font-family:"Cambria Math";
+	panose-1:2 4 5 3 5 4 6 3 2 4;}
+@font-face
+	{font-family:Calibri;
+	panose-1:2 15 5 2 2 2 4 3 2 4;}
+@font-face
+	{font-family:Tahoma;
+	panose-1:2 11 6 4 3 5 4 4 2 4;}
+@font-face
+	{font-family:Verdana;
+	panose-1:2 11 6 4 3 5 4 4 2 4;}
+ /* Style Definitions */
+ p.MsoNormal, li.MsoNormal, div.MsoNormal
+	{margin:0cm;
+	margin-bottom:.0001pt;
+	font-size:10.0pt;
+	font-family:"Verdana","sans-serif";}
+a:link, span.MsoHyperlink
+	{mso-style-priority:99;
+	color:blue;
+	text-decoration:underline;}
+a:visited, span.MsoHyperlinkFollowed
+	{mso-style-priority:99;
+	color:purple;
+	text-decoration:underline;}
+p.MsoAcetate, li.MsoAcetate, div.MsoAcetate
+	{mso-style-priority:99;
+	mso-style-link:"Balloon Text Char";
+	margin:0cm;
+	margin-bottom:.0001pt;
+	font-size:8.0pt;
+	font-family:"Tahoma","sans-serif";}
+span.EmailStyle17
+	{mso-style-type:personal-compose;
+	font-family:"Verdana","sans-serif";
+	color:windowtext;}
+span.BalloonTextChar
+	{mso-style-name:"Balloon Text Char";
+	mso-style-priority:99;
+	mso-style-link:"Balloon Text";
+	font-family:"Tahoma","sans-serif";}
+..MsoChpDefault
+	{mso-style-type:export-only;}
+@page Section1
+	{size:612.0pt 792.0pt;
+	margin:70.85pt 70.85pt 70.85pt 70.85pt;}
+div.Section1
+	{page:Section1;}
+-->
+</style>
+<!--[if gte mso 9]><xml>
+ <o:shapedefaults v:ext="edit" spidmax="2050" />
+</xml><![endif]--><!--[if gte mso 9]><xml>
+ <o:shapelayout v:ext="edit">
+  <o:idmap v:ext="edit" data="1" />
+ </o:shapelayout></xml><![endif]-->
+</head>
+
+<body lang=NL link=blue vlink=purple>
+
+<div class=Section1>
+
+<p class=MsoNormal><img width=1277 height=994 id="Picture_x0020_1"
+src="cid:image001.png@01C8CBDF.5D1BAEE0"><o:p></o:p></p>
+
+<p class=MsoNormal><o:p>&nbsp;</o:p></p>
+
+<p class=MsoNormal><b>Name<o:p></o:p></b></p>
+
+<p class=MsoNormal>E-mail : <a href="mailto:mail@example.com"><span
+style='color:windowtext'>mail@example.com</span></a><o:p></o:p></p>
+
+<p class=MsoNormal><o:p>&nbsp;</o:p></p>
+
+<p class=MsoNormal><b>Company<o:p></o:p></b></p>
+
+<p class=MsoNormal>Address 1<o:p></o:p></p>
+
+<p class=MsoNormal>Address 2<o:p></o:p></p>
+
+<p class=MsoNormal><o:p>&nbsp;</o:p></p>
+
+<p class=MsoNormal>Telefoon&nbsp; : +xx xx xxx xxx xx <span style='color:black'><o:p></o:p></span></p>
+
+<p class=MsoNormal><span lang=EN-US style='color:black'>Fax&nbsp; : +xx xx xxx xx xx<o:p></o:p></span></p>
+
+<p class=MsoNormal><span lang=EN-US style='color:black'>Internet : </span><span
+style='color:black'><a href="http://www.example.com/"><span lang=EN-US
+style='color:black'>http://www.example.com</span></a></span><span
+lang=EN-US style='color:black'><o:p></o:p></span></p>
+
+<p class=MsoNormal><span lang=EN-US style='color:black'>Kamer van koophandel
+xxxxxxxxx<o:p></o:p></span></p>
+
+<p class=MsoNormal><span lang=EN-US style='color:black'><o:p>&nbsp;</o:p></span></p>
+
+<p class=MsoNormal><span lang=EN-US style='font-size:7.5pt;color:black'>Op deze
+e-mail is een disclaimer van toepassing, ga naar </span><span lang=EN-US
+style='font-size:7.5pt'><a
+href="http://www.example.com/disclaimer"><span
+style='color:black'>www.example.com/disclaimer</span></a><br>
+<span style='color:black'>A disclaimer is applicable to this email, please
+refer to </span><a href="http://www.example.com/disclaimer"><span
+style='color:black'>www.example.com/disclaimer</span></a><o:p></o:p></span></p>
+
+<p class=MsoNormal><span lang=EN-US><o:p>&nbsp;</o:p></span></p>
+
+</div>
+
+</body>
+
+</html>
+
+<!-- vim: et sw=4 sts=4 -->

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

@@ -4,71 +4,73 @@
 <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 
+<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 
+<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 
+<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><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>Buletets
   <LI>
-  <DIV align=justify><A title=http://laacz.lv/blog/ 
-  href="http://laacz.lv/blog/">http://laacz.lv/blog/</A> un <A 
+  <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 
+  <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" 
+      <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 
+      <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 
+      <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 
+<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>
+<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>
+
+<!-- vim: et sw=4 sts=4 -->

docs/style.css

@@ -72,3 +72,5 @@ q:after {
 .fixme:before {content:"Fix me: "; font-weight:bold; color:#C00; }
 
 #applicability {margin: 1em 5%; font-style:italic;}
+
+/* vim: et sw=4 sts=4 */

extras/ConfigDoc/HTMLXSLTProcessor.php

@@ -1,21 +1,23 @@
 <?php
 
 /**
- * Special XSLTProcessor specifically for HTML documents. Loosely
- * based off of XSLTProcessor, but not really
+ * Decorator/extender XSLT processor specifically for HTML documents.
  */
 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
+     * Instance of XSLTProcessor
+     */
+    protected $xsltProcessor;
+
+    public function __construct($proc = false) {
+        if ($proc === false) $proc = new XSLTProcessor();
+        $this->xsltProcessor = $proc;
+    }
+
+    /**
+     * @note Allows a string $xsl filename to be passed
      */
     public function importStylesheet($xsl) {
         if (is_string($xsl)) {
@@ -25,18 +27,27 @@ class ConfigDoc_HTMLXSLTProcessor
         }
         return $this->xsltProcessor->importStylesheet($xsl);
     }
-    
+
     /**
-     * Transforms an XML file into HTML based on the stylesheet
-     * @param $xml XML DOM tree
+     * Transforms an XML file into compatible XHTML based on the stylesheet
+     * @param $xml XML DOM tree, or string filename
+     * @return string HTML output
+     * @todo Rename to transformToXHTML, as transformToHTML is misleading
      */
     public function transformToHTML($xml) {
-        $out = $this->xsltProcessor->transformToXML($xml);
-        
+        if (is_string($xml)) {
+            $dom = new DOMDocument();
+            $dom->load($xml);
+        } else {
+            $dom = $xml;
+        }
+        $out = $this->xsltProcessor->transformToXML($dom);
+
         // fudges for HTML backwards compatibility
+        // assumes that document is XHTML
         $out = str_replace('/>', ' />', $out); // <br /> not <br/>
         $out = str_replace(' xmlns=""', '', $out); // rm unnecessary xmlns
-        $out = str_replace(' xmlns="http://www.w3.org/1999/xhtml"', '', $out); // rm unnecessary xmlns
+
         if (class_exists('Tidy')) {
             // cleanup output
             $config = array(
@@ -49,14 +60,27 @@ class ConfigDoc_HTMLXSLTProcessor
             $tidy->cleanRepair();
             $out = (string) $tidy;
         }
+
         return $out;
     }
-    
+
+    /**
+     * Bulk sets parameters for the XSL stylesheet
+     * @param array $options Associative array of options to set
+     */
     public function setParameters($options) {
         foreach ($options as $name => $value) {
             $this->xsltProcessor->setParameter('', $name, $value);
         }
     }
-    
+
+    /**
+     * Forward any other calls to the XSLT processor
+     */
+    public function __call($name, $arguments) {
+        call_user_func_array(array($this->xsltProcessor, $name), $arguments);
+    }
+
 }
 
+// vim: et sw=4 sts=4

extras/FSTools.php

@@ -0,0 +1,157 @@
+<?php
+
+/**
+ * Filesystem tools not provided by default; can recursively create, copy
+ * and delete folders. Some template methods are provided for extensibility.
+ *
+ * @note This class must be instantiated to be used, although it does
+ *       not maintain state.
+ */
+class FSTools
+{
+
+    private static $singleton;
+
+    /**
+     * Returns a global instance of FSTools
+     */
+    static public function singleton() {
+        if (empty(FSTools::$singleton)) FSTools::$singleton = new FSTools();
+        return FSTools::$singleton;
+    }
+
+    /**
+     * Sets our global singleton to something else; useful for overloading
+     * functions.
+     */
+    static public function setSingleton($singleton) {
+        FSTools::$singleton = $singleton;
+    }
+
+    /**
+     * Recursively creates a directory
+     * @param string $folder Name of folder to create
+     * @note Adapted from the PHP manual comment 76612
+     */
+    public function mkdirr($folder) {
+        $folders = preg_split("#[\\\\/]#", $folder);
+        $base = '';
+        for($i = 0, $c = count($folders); $i < $c; $i++) {
+            if(empty($folders[$i])) {
+                if (!$i) {
+                    // special case for root level
+                    $base .= DIRECTORY_SEPARATOR;
+                }
+                continue;
+            }
+            $base .= $folders[$i];
+            if(!is_dir($base)){
+                $this->mkdir($base);
+            }
+            $base .= DIRECTORY_SEPARATOR;
+        }
+    }
+
+    /**
+     * Copy a file, or recursively copy a folder and its contents; modified
+     * so that copied files, if PHP, have includes removed
+     * @note Adapted from http://aidanlister.com/repos/v/function.copyr.php
+     */
+    public function copyr($source, $dest) {
+        // Simple copy for a file
+        if (is_file($source)) {
+            return $this->copy($source, $dest);
+        }
+        // Make destination directory
+        if (!is_dir($dest)) {
+            $this->mkdir($dest);
+        }
+        // Loop through the folder
+        $dir = $this->dir($source);
+        while ( false !== ($entry = $dir->read()) ) {
+            // Skip pointers
+            if ($entry == '.' || $entry == '..') {
+                continue;
+            }
+            if (!$this->copyable($entry)) {
+                continue;
+            }
+            // Deep copy directories
+            if ($dest !== "$source/$entry") {
+                $this->copyr("$source/$entry", "$dest/$entry");
+            }
+        }
+        // Clean up
+        $dir->close();
+        return true;
+    }
+
+    /**
+     * Overloadable function that tests a filename for copyability. By
+     * default, everything should be copied; you can restrict things to
+     * ignore hidden files, unreadable files, etc. This function
+     * applies to copyr().
+     */
+    public function copyable($file) {
+        return true;
+    }
+
+    /**
+     * Delete a file, or a folder and its contents
+     * @note Adapted from http://aidanlister.com/repos/v/function.rmdirr.php
+     */
+    public function rmdirr($dirname)
+    {
+        // Sanity check
+        if (!$this->file_exists($dirname)) {
+            return false;
+        }
+
+        // Simple delete for a file
+        if ($this->is_file($dirname) || $this->is_link($dirname)) {
+            return $this->unlink($dirname);
+        }
+
+        // Loop through the folder
+        $dir = $this->dir($dirname);
+        while (false !== $entry = $dir->read()) {
+            // Skip pointers
+            if ($entry == '.' || $entry == '..') {
+                continue;
+            }
+            // Recurse
+            $this->rmdirr($dirname . DIRECTORY_SEPARATOR . $entry);
+        }
+
+        // Clean up
+        $dir->close();
+        return $this->rmdir($dirname);
+    }
+
+    /**
+     * Recursively globs a directory.
+     */
+    public function globr($dir, $pattern, $flags = NULL) {
+        $files = $this->glob("$dir/$pattern", $flags);
+        if ($files === false) $files = array();
+        $sub_dirs = $this->glob("$dir/*", GLOB_ONLYDIR);
+        if ($sub_dirs === false) $sub_dirs = array();
+        foreach ($sub_dirs as $sub_dir) {
+            $sub_files = $this->globr($sub_dir, $pattern, $flags);
+            $files = array_merge($files, $sub_files);
+        }
+        return $files;
+    }
+
+    /**
+     * Allows for PHP functions to be called and be stubbed.
+     * @warning This function will not work for functions that need
+     *      to pass references; manually define a stub function for those.
+     */
+    public function __call($name, $args) {
+        return call_user_func_array($name, $args);
+    }
+
+}
+
+// vim: et sw=4 sts=4

extras/FSTools/File.php

@@ -0,0 +1,126 @@
+<?php
+
+/**
+ * Represents a file in the filesystem
+ *
+ * @warning Be sure to distinguish between get() and write() versus
+ *      read() and put(), the former operates on the entire file, while
+ *      the latter operates on a handle.
+ */
+class FSTools_File
+{
+
+    /** Filename of file this object represents */
+    protected $name;
+
+    /** Handle for the file */
+    protected $handle = false;
+
+    /** Instance of FSTools for interfacing with filesystem */
+    protected $fs;
+
+    /**
+     * Filename of file you wish to instantiate.
+     * @note This file need not exist
+     */
+    public function __construct($name, $fs = false) {
+        $this->name = $name;
+        $this->fs = $fs ? $fs : FSTools::singleton();
+    }
+
+    /** Returns the filename of the file. */
+    public function getName() {return $this->name;}
+
+    /** Returns directory of the file without trailing slash */
+    public function getDirectory() {return $this->fs->dirname($this->name);}
+
+    /**
+     * Retrieves the contents of a file
+     * @todo Throw an exception if file doesn't exist
+     */
+    public function get() {
+        return $this->fs->file_get_contents($this->name);
+    }
+
+    /** Writes contents to a file, creates new file if necessary */
+    public function write($contents) {
+        return $this->fs->file_put_contents($this->name, $contents);
+    }
+
+    /** Deletes the file */
+    public function delete() {
+        return $this->fs->unlink($this->name);
+    }
+
+    /** Returns true if file exists and is a file. */
+    public function exists() {
+        return $this->fs->is_file($this->name);
+    }
+
+    /** Returns last file modification time */
+    public function getMTime() {
+        return $this->fs->filemtime($this->name);
+    }
+
+    /**
+     * Chmod a file
+     * @note We ignore errors because of some weird owner trickery due
+     *       to SVN duality
+     */
+    public function chmod($octal_code) {
+        return @$this->fs->chmod($this->name, $octal_code);
+    }
+
+    /** Opens file's handle */
+    public function open($mode) {
+        if ($this->handle) $this->close();
+        $this->handle = $this->fs->fopen($this->name, $mode);
+        return true;
+    }
+
+    /** Closes file's handle */
+    public function close() {
+        if (!$this->handle) return false;
+        $status = $this->fs->fclose($this->handle);
+        $this->handle = false;
+        return $status;
+    }
+
+    /** Retrieves a line from an open file, with optional max length $length */
+    public function getLine($length = null) {
+        if (!$this->handle) $this->open('r');
+        if ($length === null) return $this->fs->fgets($this->handle);
+        else return $this->fs->fgets($this->handle, $length);
+    }
+
+    /** Retrieves a character from an open file */
+    public function getChar() {
+        if (!$this->handle) $this->open('r');
+        return $this->fs->fgetc($this->handle);
+    }
+
+    /** Retrieves an $length bytes of data from an open data */
+    public function read($length) {
+        if (!$this->handle) $this->open('r');
+        return $this->fs->fread($this->handle, $length);
+    }
+
+    /** Writes to an open file */
+    public function put($string) {
+        if (!$this->handle) $this->open('a');
+        return $this->fs->fwrite($this->handle, $string);
+    }
+
+    /** Returns TRUE if the end of the file has been reached */
+    public function eof() {
+        if (!$this->handle) return true;
+        return $this->fs->feof($this->handle);
+    }
+
+    public function __destruct() {
+        if ($this->handle) $this->close();
+    }
+
+}
+
+// vim: et sw=4 sts=4

extras/HTMLPurifierExtras.auto.php

@@ -5,5 +5,7 @@
  */
 
 set_include_path(dirname(__FILE__) . PATH_SEPARATOR . get_include_path() );
-require_once 'ConfigDoc.php';
+require_once 'HTMLPurifierExtras.php';
+require_once 'HTMLPurifierExtras.autoload.php';
 
+// vim: et sw=4 sts=4

extras/HTMLPurifierExtras.autoload.php

@@ -0,0 +1,25 @@
+<?php
+
+/**
+ * @file
+ * Convenience file that registers autoload handler for HTML Purifier.
+ *
+ * @warning
+ *      This autoloader does not contain the compatibility code seen in
+ *      HTMLPurifier_Bootstrap; the user is expected to make any necessary
+ *      changes to use this library.
+ */
+
+if (function_exists('spl_autoload_register')) {
+    spl_autoload_register(array('HTMLPurifierExtras', 'autoload'));
+    if (function_exists('__autoload')) {
+        // Be polite and ensure that userland autoload gets retained
+        spl_autoload_register('__autoload');
+    }
+} elseif (!function_exists('__autoload')) {
+    function __autoload($class) {
+        return HTMLPurifierExtras::autoload($class);
+    }
+}
+
+// vim: et sw=4 sts=4

extras/HTMLPurifierExtras.php

@@ -0,0 +1,29 @@
+<?php
+
+/**
+ * Meta-class for HTML Purifier's extra class hierarchies, similar to
+ * HTMLPurifier_Bootstrap.
+ */
+class HTMLPurifierExtras
+{
+
+    public static function autoload($class) {
+        $path = HTMLPurifierExtras::getPath($class);
+        if (!$path) return false;
+        require $path;
+        return true;
+    }
+
+    public static function getPath($class) {
+        if (
+            strncmp('FSTools', $class, 7) !== 0 &&
+            strncmp('ConfigDoc', $class, 9) !== 0
+        ) return false;
+        // Custom implementations can go here
+        // Standard implementation:
+        return str_replace('_', '/', $class) . '.php';
+    }
+
+}
+
+// vim: et sw=4 sts=4

extras/README

@@ -0,0 +1,32 @@
+
+HTML Purifier Extras
+    The Method Behind The Madness!
+
+The extras/ folder in HTML Purifier contains--you guessed it--extra things
+for HTML Purifier.  Specifically, these are two extra libraries called
+FSTools and ConfigSchema.  They're extra for a reason: you don't need them
+if you're using HTML Purifier for normal usage: filtering HTML.  However,
+if you're a developer, and would like to test HTML Purifier, or need to
+use one of HTML Purifier's maintenance scripts, chances are they'll need
+these libraries. Who knows: maybe you'll find them useful too!
+
+Here are the libraries:
+
+
+FSTools
+-------
+
+Short for File System Tools, this is a poor-man's object-oriented wrapper for
+the filesystem. It currently consists of two classes:
+
+- FSTools: This is a singleton that contains a manner of useful functions
+  such as recursive glob, directory removal, etc, as well as the ability
+  to call arbitrary native PHP functions through it like $FS->fopen(...).
+  This makes it a lot simpler to mock these filesystem calls for unit testing.
+
+- FSTools_File: This object represents a single file, and has almost any
+  method imaginable one would need.
+
+Check the files themselves for more information.
+
+    vim: et sw=4 sts=4

library/HTMLPurifier.auto.php

@@ -5,5 +5,7 @@
  */
 
 set_include_path(dirname(__FILE__) . PATH_SEPARATOR . get_include_path() );
-require_once 'HTMLPurifier.php';
+require_once 'HTMLPurifier/Bootstrap.php';
+require_once 'HTMLPurifier.autoload.php';
 
+// vim: et sw=4 sts=4

library/HTMLPurifier.autoload.php

@@ -0,0 +1,21 @@
+<?php
+
+/**
+ * @file
+ * Convenience file that registers autoload handler for HTML Purifier.
+ */
+
+if (function_exists('spl_autoload_register') && function_exists('spl_autoload_unregister')) {
+    // We need unregister for our pre-registering functionality
+    HTMLPurifier_Bootstrap::registerAutoload();
+    if (function_exists('__autoload')) {
+        // Be polite and ensure that userland autoload gets retained
+        spl_autoload_register('__autoload');
+    }
+} elseif (!function_exists('__autoload')) {
+    function __autoload($class) {
+        return HTMLPurifier_Bootstrap::autoload($class);
+    }
+}
+
+// vim: et sw=4 sts=4

library/HTMLPurifier.func.php

@@ -1,20 +1,23 @@
 <?php
 
 /**
- * Function wrapper for HTML Purifier for quick use.
- * @note This function only includes the library when it is called. While
- *       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.
+ * @file
+ * Defines a function wrapper for HTML Purifier for quick use.
  * @note ''HTMLPurifier()'' is NOT the same as ''new HTMLPurifier()''
  */
 
+/**
+ * Purify HTML.
+ * @param $html String HTML to purify
+ * @param $config Configuration to use, can be any value accepted by
+ *        HTMLPurifier_Config::create()
+ */
 function HTMLPurifier($html, $config = null) {
     static $purifier = false;
     if (!$purifier) {
-        require_once 'HTMLPurifier.php';
         $purifier = new HTMLPurifier();
     }
     return $purifier->purify($html, $config);
 }
 
+// vim: et sw=4 sts=4

library/HTMLPurifier.includes.php

@@ -0,0 +1,206 @@
+<?php
+
+/**
+ * @file
+ * This file was auto-generated by generate-includes.php and includes all of
+ * the core files required by HTML Purifier. Use this if performance is a
+ * primary concern and you are using an opcode cache. PLEASE DO NOT EDIT THIS
+ * FILE, changes will be overwritten the next time the script is run.
+ *
+ * @version 3.3.0
+ *
+ * @warning
+ *      You must *not* include any other HTML Purifier files before this file,
+ *      because 'require' not 'require_once' is used.
+ *
+ * @warning
+ *      This file requires that the include path contains the HTML Purifier
+ *      library directory; this is not auto-set.
+ */
+
+require 'HTMLPurifier.php';
+require 'HTMLPurifier/AttrCollections.php';
+require 'HTMLPurifier/AttrDef.php';
+require 'HTMLPurifier/AttrTransform.php';
+require 'HTMLPurifier/AttrTypes.php';
+require 'HTMLPurifier/AttrValidator.php';
+require 'HTMLPurifier/Bootstrap.php';
+require 'HTMLPurifier/Definition.php';
+require 'HTMLPurifier/CSSDefinition.php';
+require 'HTMLPurifier/ChildDef.php';
+require 'HTMLPurifier/Config.php';
+require 'HTMLPurifier/ConfigSchema.php';
+require 'HTMLPurifier/ContentSets.php';
+require 'HTMLPurifier/Context.php';
+require 'HTMLPurifier/DefinitionCache.php';
+require 'HTMLPurifier/DefinitionCacheFactory.php';
+require 'HTMLPurifier/Doctype.php';
+require 'HTMLPurifier/DoctypeRegistry.php';
+require 'HTMLPurifier/ElementDef.php';
+require 'HTMLPurifier/Encoder.php';
+require 'HTMLPurifier/EntityLookup.php';
+require 'HTMLPurifier/EntityParser.php';
+require 'HTMLPurifier/ErrorCollector.php';
+require 'HTMLPurifier/ErrorStruct.php';
+require 'HTMLPurifier/Exception.php';
+require 'HTMLPurifier/Filter.php';
+require 'HTMLPurifier/Generator.php';
+require 'HTMLPurifier/HTMLDefinition.php';
+require 'HTMLPurifier/HTMLModule.php';
+require 'HTMLPurifier/HTMLModuleManager.php';
+require 'HTMLPurifier/IDAccumulator.php';
+require 'HTMLPurifier/Injector.php';
+require 'HTMLPurifier/Language.php';
+require 'HTMLPurifier/LanguageFactory.php';
+require 'HTMLPurifier/Length.php';
+require 'HTMLPurifier/Lexer.php';
+require 'HTMLPurifier/PercentEncoder.php';
+require 'HTMLPurifier/PropertyList.php';
+require 'HTMLPurifier/PropertyListIterator.php';
+require 'HTMLPurifier/Strategy.php';
+require 'HTMLPurifier/StringHash.php';
+require 'HTMLPurifier/StringHashParser.php';
+require 'HTMLPurifier/TagTransform.php';
+require 'HTMLPurifier/Token.php';
+require 'HTMLPurifier/TokenFactory.php';
+require 'HTMLPurifier/URI.php';
+require 'HTMLPurifier/URIDefinition.php';
+require 'HTMLPurifier/URIFilter.php';
+require 'HTMLPurifier/URIParser.php';
+require 'HTMLPurifier/URIScheme.php';
+require 'HTMLPurifier/URISchemeRegistry.php';
+require 'HTMLPurifier/UnitConverter.php';
+require 'HTMLPurifier/VarParser.php';
+require 'HTMLPurifier/VarParserException.php';
+require 'HTMLPurifier/AttrDef/CSS.php';
+require 'HTMLPurifier/AttrDef/Enum.php';
+require 'HTMLPurifier/AttrDef/Integer.php';
+require 'HTMLPurifier/AttrDef/Lang.php';
+require 'HTMLPurifier/AttrDef/Switch.php';
+require 'HTMLPurifier/AttrDef/Text.php';
+require 'HTMLPurifier/AttrDef/URI.php';
+require 'HTMLPurifier/AttrDef/CSS/Number.php';
+require 'HTMLPurifier/AttrDef/CSS/AlphaValue.php';
+require 'HTMLPurifier/AttrDef/CSS/Background.php';
+require 'HTMLPurifier/AttrDef/CSS/BackgroundPosition.php';
+require 'HTMLPurifier/AttrDef/CSS/Border.php';
+require 'HTMLPurifier/AttrDef/CSS/Color.php';
+require 'HTMLPurifier/AttrDef/CSS/Composite.php';
+require 'HTMLPurifier/AttrDef/CSS/DenyElementDecorator.php';
+require 'HTMLPurifier/AttrDef/CSS/Filter.php';
+require 'HTMLPurifier/AttrDef/CSS/Font.php';
+require 'HTMLPurifier/AttrDef/CSS/FontFamily.php';
+require 'HTMLPurifier/AttrDef/CSS/ImportantDecorator.php';
+require 'HTMLPurifier/AttrDef/CSS/Length.php';
+require 'HTMLPurifier/AttrDef/CSS/ListStyle.php';
+require 'HTMLPurifier/AttrDef/CSS/Multiple.php';
+require 'HTMLPurifier/AttrDef/CSS/Percentage.php';
+require 'HTMLPurifier/AttrDef/CSS/TextDecoration.php';
+require 'HTMLPurifier/AttrDef/CSS/URI.php';
+require 'HTMLPurifier/AttrDef/HTML/Bool.php';
+require 'HTMLPurifier/AttrDef/HTML/Color.php';
+require 'HTMLPurifier/AttrDef/HTML/FrameTarget.php';
+require 'HTMLPurifier/AttrDef/HTML/ID.php';
+require 'HTMLPurifier/AttrDef/HTML/Pixels.php';
+require 'HTMLPurifier/AttrDef/HTML/Length.php';
+require 'HTMLPurifier/AttrDef/HTML/LinkTypes.php';
+require 'HTMLPurifier/AttrDef/HTML/MultiLength.php';
+require 'HTMLPurifier/AttrDef/HTML/Nmtokens.php';
+require 'HTMLPurifier/AttrDef/URI/Email.php';
+require 'HTMLPurifier/AttrDef/URI/Host.php';
+require 'HTMLPurifier/AttrDef/URI/IPv4.php';
+require 'HTMLPurifier/AttrDef/URI/IPv6.php';
+require 'HTMLPurifier/AttrDef/URI/Email/SimpleCheck.php';
+require 'HTMLPurifier/AttrTransform/Background.php';
+require 'HTMLPurifier/AttrTransform/BdoDir.php';
+require 'HTMLPurifier/AttrTransform/BgColor.php';
+require 'HTMLPurifier/AttrTransform/BoolToCSS.php';
+require 'HTMLPurifier/AttrTransform/Border.php';
+require 'HTMLPurifier/AttrTransform/EnumToCSS.php';
+require 'HTMLPurifier/AttrTransform/ImgRequired.php';
+require 'HTMLPurifier/AttrTransform/ImgSpace.php';
+require 'HTMLPurifier/AttrTransform/Input.php';
+require 'HTMLPurifier/AttrTransform/Lang.php';
+require 'HTMLPurifier/AttrTransform/Length.php';
+require 'HTMLPurifier/AttrTransform/Name.php';
+require 'HTMLPurifier/AttrTransform/SafeEmbed.php';
+require 'HTMLPurifier/AttrTransform/SafeObject.php';
+require 'HTMLPurifier/AttrTransform/SafeParam.php';
+require 'HTMLPurifier/AttrTransform/ScriptRequired.php';
+require 'HTMLPurifier/AttrTransform/Textarea.php';
+require 'HTMLPurifier/ChildDef/Chameleon.php';
+require 'HTMLPurifier/ChildDef/Custom.php';
+require 'HTMLPurifier/ChildDef/Empty.php';
+require 'HTMLPurifier/ChildDef/Required.php';
+require 'HTMLPurifier/ChildDef/Optional.php';
+require 'HTMLPurifier/ChildDef/StrictBlockquote.php';
+require 'HTMLPurifier/ChildDef/Table.php';
+require 'HTMLPurifier/DefinitionCache/Decorator.php';
+require 'HTMLPurifier/DefinitionCache/Null.php';
+require 'HTMLPurifier/DefinitionCache/Serializer.php';
+require 'HTMLPurifier/DefinitionCache/Decorator/Cleanup.php';
+require 'HTMLPurifier/DefinitionCache/Decorator/Memory.php';
+require 'HTMLPurifier/HTMLModule/Bdo.php';
+require 'HTMLPurifier/HTMLModule/CommonAttributes.php';
+require 'HTMLPurifier/HTMLModule/Edit.php';
+require 'HTMLPurifier/HTMLModule/Forms.php';
+require 'HTMLPurifier/HTMLModule/Hypertext.php';
+require 'HTMLPurifier/HTMLModule/Image.php';
+require 'HTMLPurifier/HTMLModule/Legacy.php';
+require 'HTMLPurifier/HTMLModule/List.php';
+require 'HTMLPurifier/HTMLModule/Name.php';
+require 'HTMLPurifier/HTMLModule/NonXMLCommonAttributes.php';
+require 'HTMLPurifier/HTMLModule/Object.php';
+require 'HTMLPurifier/HTMLModule/Presentation.php';
+require 'HTMLPurifier/HTMLModule/Proprietary.php';
+require 'HTMLPurifier/HTMLModule/Ruby.php';
+require 'HTMLPurifier/HTMLModule/SafeEmbed.php';
+require 'HTMLPurifier/HTMLModule/SafeObject.php';
+require 'HTMLPurifier/HTMLModule/Scripting.php';
+require 'HTMLPurifier/HTMLModule/StyleAttribute.php';
+require 'HTMLPurifier/HTMLModule/Tables.php';
+require 'HTMLPurifier/HTMLModule/Target.php';
+require 'HTMLPurifier/HTMLModule/Text.php';
+require 'HTMLPurifier/HTMLModule/Tidy.php';
+require 'HTMLPurifier/HTMLModule/XMLCommonAttributes.php';
+require 'HTMLPurifier/HTMLModule/Tidy/Name.php';
+require 'HTMLPurifier/HTMLModule/Tidy/Proprietary.php';
+require 'HTMLPurifier/HTMLModule/Tidy/XHTMLAndHTML4.php';
+require 'HTMLPurifier/HTMLModule/Tidy/Strict.php';
+require 'HTMLPurifier/HTMLModule/Tidy/Transitional.php';
+require 'HTMLPurifier/HTMLModule/Tidy/XHTML.php';
+require 'HTMLPurifier/Injector/AutoParagraph.php';
+require 'HTMLPurifier/Injector/DisplayLinkURI.php';
+require 'HTMLPurifier/Injector/Linkify.php';
+require 'HTMLPurifier/Injector/PurifierLinkify.php';
+require 'HTMLPurifier/Injector/RemoveEmpty.php';
+require 'HTMLPurifier/Injector/SafeObject.php';
+require 'HTMLPurifier/Lexer/DOMLex.php';
+require 'HTMLPurifier/Lexer/DirectLex.php';
+require 'HTMLPurifier/Strategy/Composite.php';
+require 'HTMLPurifier/Strategy/Core.php';
+require 'HTMLPurifier/Strategy/FixNesting.php';
+require 'HTMLPurifier/Strategy/MakeWellFormed.php';
+require 'HTMLPurifier/Strategy/RemoveForeignElements.php';
+require 'HTMLPurifier/Strategy/ValidateAttributes.php';
+require 'HTMLPurifier/TagTransform/Font.php';
+require 'HTMLPurifier/TagTransform/Simple.php';
+require 'HTMLPurifier/Token/Comment.php';
+require 'HTMLPurifier/Token/Tag.php';
+require 'HTMLPurifier/Token/Empty.php';
+require 'HTMLPurifier/Token/End.php';
+require 'HTMLPurifier/Token/Start.php';
+require 'HTMLPurifier/Token/Text.php';
+require 'HTMLPurifier/URIFilter/DisableExternal.php';
+require 'HTMLPurifier/URIFilter/DisableExternalResources.php';
+require 'HTMLPurifier/URIFilter/HostBlacklist.php';
+require 'HTMLPurifier/URIFilter/MakeAbsolute.php';
+require 'HTMLPurifier/URIFilter/Munge.php';
+require 'HTMLPurifier/URIScheme/ftp.php';
+require 'HTMLPurifier/URIScheme/http.php';
+require 'HTMLPurifier/URIScheme/https.php';
+require 'HTMLPurifier/URIScheme/mailto.php';
+require 'HTMLPurifier/URIScheme/news.php';
+require 'HTMLPurifier/URIScheme/nntp.php';
+require 'HTMLPurifier/VarParser/Flexible.php';
+require 'HTMLPurifier/VarParser/Native.php';

library/HTMLPurifier.kses.php

@@ -0,0 +1,30 @@
+<?php
+
+/**
+ * @file
+ * Emulation layer for code that used kses(), substituting in HTML Purifier.
+ */
+
+require_once dirname(__FILE__) . '/HTMLPurifier.auto.php';
+
+function kses($string, $allowed_html, $allowed_protocols = null) {
+    $config = HTMLPurifier_Config::createDefault();
+    $allowed_elements = array();
+    $allowed_attributes = array();
+    foreach ($allowed_html as $element => $attributes) {
+        $allowed_elements[$element] = true;
+        foreach ($attributes as $attribute => $x) {
+            $allowed_attributes["$element.$attribute"] = true;
+        }
+    }
+    $config->set('HTML', 'AllowedElements', $allowed_elements);
+    $config->set('HTML', 'AllowedAttributes', $allowed_attributes);
+    $allowed_schemes = array();
+    if ($allowed_protocols !== null) {
+        $config->set('URI', 'AllowedSchemes', $allowed_protocols);
+    }
+    $purifier = new HTMLPurifier($config);
+    return $purifier->purify($string);
+}
+
+// vim: et sw=4 sts=4

library/HTMLPurifier.path.php

@@ -0,0 +1,11 @@
+<?php
+
+/**
+ * @file
+ * Convenience stub file that adds HTML Purifier's library file to the path
+ * without any other side-effects.
+ */
+
+set_include_path(dirname(__FILE__) . PATH_SEPARATOR . get_include_path() );
+
+// vim: et sw=4 sts=4

library/HTMLPurifier.php

@@ -1,12 +1,11 @@
 <?php
 
-/*!
- * @mainpage
- * 
+/*! @mainpage
+ *
  * HTML Purifier is an HTML filter that will take an arbitrary snippet of
  * HTML and rigorously test, validate and filter it into a version that
  * is safe for output onto webpages. It achieves this by:
- * 
+ *
  *  -# Lexing (parsing into tokens) the document,
  *  -# Executing various strategies on the tokens:
  *      -# Removing all elements not in the whitelist,
@@ -14,16 +13,14 @@
  *      -# Fixing the nesting of the nodes, and
  *      -# Validating attributes of the nodes; and
  *  -# Generating HTML from the purified tokens.
- * 
+ *
  * However, most users will only need to interface with the HTMLPurifier
- * class, so this massive amount of infrastructure is usually concealed.
- * If you plan on working with the internals, be sure to include
- * HTMLPurifier_ConfigSchema and HTMLPurifier_Config.
+ * and HTMLPurifier_Config.
  */
 
 /*
-    HTML Purifier 2.1.3 - Standards Compliant HTML Filtering
-    Copyright (C) 2006-2007 Edward Z. Yang
+    HTML Purifier 3.3.0 - Standards Compliant HTML Filtering
+    Copyright (C) 2006-2008 Edward Z. Yang
 
     This library is free software; you can redistribute it and/or
     modify it under the terms of the GNU Lesser General Public
@@ -40,63 +37,46 @@
     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__));
-
-// every class has an undocumented dependency to these, must be included!
-require_once 'HTMLPurifier/ConfigSchema.php'; // fatal errors if not included
-require_once 'HTMLPurifier/Config.php';
-require_once 'HTMLPurifier/Context.php';
-
-require_once 'HTMLPurifier/Lexer.php';
-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. <strong>Warning:</strong>
-Currently this feature is very patchy and experimental, with lots of
-possible error messages not yet implemented. It will not cause any problems,
-but it may not help your users either. This directive has been available
-since 2.0.0.
-');
-
 /**
  * Facade that coordinates HTML Purifier's subsystems in order to purify HTML.
- * 
- * @note There are several points in which configuration can be specified 
+ *
+ * @note There are several points in which configuration can be specified
  *       for HTML Purifier.  The precedence of these (from lowest to
  *       highest) is as follows:
  *          -# Instance: new HTMLPurifier($config)
  *          -# Invocation: purify($html, $config)
  *       These configurations are entirely independent of each other and
- *       are *not* merged.
- * 
- * @todo We need an easier way to inject strategies, it'll probably end
- *       up getting done through config though.
+ *       are *not* merged (this behavior may change in the future).
+ *
+ * @todo We need an easier way to inject strategies using the configuration
+ *       object.
  */
 class HTMLPurifier
 {
-    
-    var $version = '2.1.3';
-    
-    var $config;
-    var $filters = array();
-    
-    var $strategy, $generator;
-    
+
+    /** Version of HTML Purifier */
+    public $version = '3.3.0';
+
+    /** Constant with version of HTML Purifier */
+    const VERSION = '3.3.0';
+
+    /** Global configuration object */
+    public $config;
+
+    /** Array of extra HTMLPurifier_Filter objects to run on HTML, for backwards compatibility */
+    private $filters = array();
+
+    /** Single instance of HTML Purifier */
+    private static $instance;
+
+    protected $strategy, $generator;
+
     /**
      * Resultant HTMLPurifier_Context of last run purification. Is an array
      * of contexts if the last called method was purifyArray().
-     * @public
      */
-    var $context;
-    
+    public $context;
+
     /**
      * Initializes the purifier.
      * @param $config Optional HTMLPurifier_Config object for all instances of
@@ -105,26 +85,26 @@ class HTMLPurifier
      *                The parameter can also be any type that
      *                HTMLPurifier_Config::create() supports.
      */
-    function HTMLPurifier($config = null) {
-        
+    public function __construct($config = null) {
+
         $this->config = HTMLPurifier_Config::create($config);
-        
+
         $this->strategy     = new HTMLPurifier_Strategy_Core();
-        $this->generator    = new HTMLPurifier_Generator();
-        
+
     }
-    
+
     /**
      * Adds a filter to process the output. First come first serve
      * @param $filter HTMLPurifier_Filter object
      */
-    function addFilter($filter) {
+    public function addFilter($filter) {
+        trigger_error('HTMLPurifier->addFilter() is deprecated, use configuration directives in the Filter namespace or Filter.Custom', E_USER_WARNING);
         $this->filters[] = $filter;
     }
-    
+
     /**
      * Filters an HTML snippet/document to be XSS-free and standards-compliant.
-     * 
+     *
      * @param $html String of HTML to purify
      * @param $config HTMLPurifier_Config object for this operation, if omitted,
      *                defaults to the config object specified during this
@@ -132,44 +112,62 @@ class HTMLPurifier
      *                that HTMLPurifier_Config::create() supports.
      * @return Purified HTML
      */
-    function purify($html, $config = null) {
-        
+    public function purify($html, $config = null) {
+
+        // :TODO: make the config merge in, instead of replace
         $config = $config ? HTMLPurifier_Config::create($config) : $this->config;
-        
+
         // 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);
+
+        // setup HTML generator
+        $this->generator = new HTMLPurifier_Generator($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);
         }
-        
+
         // setup id_accumulator context, necessary due to the fact that
         // AttrValidator can be called from many places
         $id_accumulator = HTMLPurifier_IDAccumulator::build($config, $context);
         $context->register('IDAccumulator', $id_accumulator);
-        
+
         $html = HTMLPurifier_Encoder::convertToUTF8($html, $config, $context);
-        
-        for ($i = 0, $size = count($this->filters); $i < $size; $i++) {
-            $html = $this->filters[$i]->preFilter($html, $config, $context);
+
+        // setup filters
+        $filter_flags = $config->getBatch('Filter');
+        $custom_filters = $filter_flags['Custom'];
+        unset($filter_flags['Custom']);
+        $filters = array();
+        foreach ($filter_flags as $filter => $flag) {
+            if (!$flag) continue;
+            $class = "HTMLPurifier_Filter_$filter";
+            $filters[] = new $class;
         }
-        
+        foreach ($custom_filters as $filter) {
+            // maybe "HTMLPurifier_Filter_$filter", but be consistent with AutoFormat
+            $filters[] = $filter;
+        }
+        $filters = array_merge($filters, $this->filters);
+        // maybe prepare(), but later
+
+        for ($i = 0, $filter_size = count($filters); $i < $filter_size; $i++) {
+            $html = $filters[$i]->preFilter($html, $config, $context);
+        }
+
         // purified HTML
-        $html = 
+        $html =
             $this->generator->generateFromTokens(
                 // list of tokens
                 $this->strategy->execute(
@@ -179,26 +177,25 @@ class HTMLPurifier
                         $html, $config, $context
                     ),
                     $config, $context
-                ),
-                $config, $context
+                )
             );
-        
-        for ($i = $size - 1; $i >= 0; $i--) {
-            $html = $this->filters[$i]->postFilter($html, $config, $context);
+
+        for ($i = $filter_size - 1; $i >= 0; $i--) {
+            $html = $filters[$i]->postFilter($html, $config, $context);
         }
-        
+
         $html = HTMLPurifier_Encoder::convertFromUTF8($html, $config, $context);
         $this->context =& $context;
         return $html;
     }
-    
+
     /**
      * Filters an array of HTML snippets
      * @param $config Optional HTMLPurifier_Config object for this operation.
      *                See HTMLPurifier::purify() for more details.
      * @return Array of purified HTML
      */
-    function purifyArray($array_of_html, $config = null) {
+    public function purifyArray($array_of_html, $config = null) {
         $context_array = array();
         foreach ($array_of_html as $key => $html) {
             $array_of_html[$key] = $this->purify($html, $config);
@@ -207,26 +204,33 @@ class HTMLPurifier
         $this->context = $context_array;
         return $array_of_html;
     }
-    
+
     /**
      * Singleton for enforcing just one HTML Purifier in your system
      * @param $prototype Optional prototype HTMLPurifier instance to
-     *                   overload singleton with.
+     *                   overload singleton with, or HTMLPurifier_Config
+     *                   instance to configure the generated version with.
      */
-    function &getInstance($prototype = null) {
-        static $htmlpurifier;
-        if (!$htmlpurifier || $prototype) {
-            if (is_a($prototype, 'HTMLPurifier')) {
-                $htmlpurifier = $prototype;
+    public static function instance($prototype = null) {
+        if (!self::$instance || $prototype) {
+            if ($prototype instanceof HTMLPurifier) {
+                self::$instance = $prototype;
             } elseif ($prototype) {
-                $htmlpurifier = new HTMLPurifier($prototype);
+                self::$instance = new HTMLPurifier($prototype);
             } else {
-                $htmlpurifier = new HTMLPurifier();
+                self::$instance = new HTMLPurifier();
             }
         }
-        return $htmlpurifier;
+        return self::$instance;
     }
-    
-    
+
+    /**
+     * @note Backwards compatibility, see instance()
+     */
+    public static function getInstance($prototype = null) {
+        return HTMLPurifier::instance($prototype);
+    }
+
 }
 
+// vim: et sw=4 sts=4

library/HTMLPurifier.safe-includes.php

@@ -0,0 +1,200 @@
+<?php
+
+/**
+ * @file
+ * This file was auto-generated by generate-includes.php and includes all of
+ * the core files required by HTML Purifier. This is a convenience stub that
+ * includes all files using dirname(__FILE__) and require_once. PLEASE DO NOT
+ * EDIT THIS FILE, changes will be overwritten the next time the script is run.
+ *
+ * Changes to include_path are not necessary.
+ */
+
+$__dir = dirname(__FILE__);
+
+require_once $__dir . '/HTMLPurifier.php';
+require_once $__dir . '/HTMLPurifier/AttrCollections.php';
+require_once $__dir . '/HTMLPurifier/AttrDef.php';
+require_once $__dir . '/HTMLPurifier/AttrTransform.php';
+require_once $__dir . '/HTMLPurifier/AttrTypes.php';
+require_once $__dir . '/HTMLPurifier/AttrValidator.php';
+require_once $__dir . '/HTMLPurifier/Bootstrap.php';
+require_once $__dir . '/HTMLPurifier/Definition.php';
+require_once $__dir . '/HTMLPurifier/CSSDefinition.php';
+require_once $__dir . '/HTMLPurifier/ChildDef.php';
+require_once $__dir . '/HTMLPurifier/Config.php';
+require_once $__dir . '/HTMLPurifier/ConfigSchema.php';
+require_once $__dir . '/HTMLPurifier/ContentSets.php';
+require_once $__dir . '/HTMLPurifier/Context.php';
+require_once $__dir . '/HTMLPurifier/DefinitionCache.php';
+require_once $__dir . '/HTMLPurifier/DefinitionCacheFactory.php';
+require_once $__dir . '/HTMLPurifier/Doctype.php';
+require_once $__dir . '/HTMLPurifier/DoctypeRegistry.php';
+require_once $__dir . '/HTMLPurifier/ElementDef.php';
+require_once $__dir . '/HTMLPurifier/Encoder.php';
+require_once $__dir . '/HTMLPurifier/EntityLookup.php';
+require_once $__dir . '/HTMLPurifier/EntityParser.php';
+require_once $__dir . '/HTMLPurifier/ErrorCollector.php';
+require_once $__dir . '/HTMLPurifier/ErrorStruct.php';
+require_once $__dir . '/HTMLPurifier/Exception.php';
+require_once $__dir . '/HTMLPurifier/Filter.php';
+require_once $__dir . '/HTMLPurifier/Generator.php';
+require_once $__dir . '/HTMLPurifier/HTMLDefinition.php';
+require_once $__dir . '/HTMLPurifier/HTMLModule.php';
+require_once $__dir . '/HTMLPurifier/HTMLModuleManager.php';
+require_once $__dir . '/HTMLPurifier/IDAccumulator.php';
+require_once $__dir . '/HTMLPurifier/Injector.php';
+require_once $__dir . '/HTMLPurifier/Language.php';
+require_once $__dir . '/HTMLPurifier/LanguageFactory.php';
+require_once $__dir . '/HTMLPurifier/Length.php';
+require_once $__dir . '/HTMLPurifier/Lexer.php';
+require_once $__dir . '/HTMLPurifier/PercentEncoder.php';
+require_once $__dir . '/HTMLPurifier/PropertyList.php';
+require_once $__dir . '/HTMLPurifier/PropertyListIterator.php';
+require_once $__dir . '/HTMLPurifier/Strategy.php';
+require_once $__dir . '/HTMLPurifier/StringHash.php';
+require_once $__dir . '/HTMLPurifier/StringHashParser.php';
+require_once $__dir . '/HTMLPurifier/TagTransform.php';
+require_once $__dir . '/HTMLPurifier/Token.php';
+require_once $__dir . '/HTMLPurifier/TokenFactory.php';
+require_once $__dir . '/HTMLPurifier/URI.php';
+require_once $__dir . '/HTMLPurifier/URIDefinition.php';
+require_once $__dir . '/HTMLPurifier/URIFilter.php';
+require_once $__dir . '/HTMLPurifier/URIParser.php';
+require_once $__dir . '/HTMLPurifier/URIScheme.php';
+require_once $__dir . '/HTMLPurifier/URISchemeRegistry.php';
+require_once $__dir . '/HTMLPurifier/UnitConverter.php';
+require_once $__dir . '/HTMLPurifier/VarParser.php';
+require_once $__dir . '/HTMLPurifier/VarParserException.php';
+require_once $__dir . '/HTMLPurifier/AttrDef/CSS.php';
+require_once $__dir . '/HTMLPurifier/AttrDef/Enum.php';
+require_once $__dir . '/HTMLPurifier/AttrDef/Integer.php';
+require_once $__dir . '/HTMLPurifier/AttrDef/Lang.php';
+require_once $__dir . '/HTMLPurifier/AttrDef/Switch.php';
+require_once $__dir . '/HTMLPurifier/AttrDef/Text.php';
+require_once $__dir . '/HTMLPurifier/AttrDef/URI.php';
+require_once $__dir . '/HTMLPurifier/AttrDef/CSS/Number.php';
+require_once $__dir . '/HTMLPurifier/AttrDef/CSS/AlphaValue.php';
+require_once $__dir . '/HTMLPurifier/AttrDef/CSS/Background.php';
+require_once $__dir . '/HTMLPurifier/AttrDef/CSS/BackgroundPosition.php';
+require_once $__dir . '/HTMLPurifier/AttrDef/CSS/Border.php';
+require_once $__dir . '/HTMLPurifier/AttrDef/CSS/Color.php';
+require_once $__dir . '/HTMLPurifier/AttrDef/CSS/Composite.php';
+require_once $__dir . '/HTMLPurifier/AttrDef/CSS/DenyElementDecorator.php';
+require_once $__dir . '/HTMLPurifier/AttrDef/CSS/Filter.php';
+require_once $__dir . '/HTMLPurifier/AttrDef/CSS/Font.php';
+require_once $__dir . '/HTMLPurifier/AttrDef/CSS/FontFamily.php';
+require_once $__dir . '/HTMLPurifier/AttrDef/CSS/ImportantDecorator.php';
+require_once $__dir . '/HTMLPurifier/AttrDef/CSS/Length.php';
+require_once $__dir . '/HTMLPurifier/AttrDef/CSS/ListStyle.php';
+require_once $__dir . '/HTMLPurifier/AttrDef/CSS/Multiple.php';
+require_once $__dir . '/HTMLPurifier/AttrDef/CSS/Percentage.php';
+require_once $__dir . '/HTMLPurifier/AttrDef/CSS/TextDecoration.php';
+require_once $__dir . '/HTMLPurifier/AttrDef/CSS/URI.php';
+require_once $__dir . '/HTMLPurifier/AttrDef/HTML/Bool.php';
+require_once $__dir . '/HTMLPurifier/AttrDef/HTML/Color.php';
+require_once $__dir . '/HTMLPurifier/AttrDef/HTML/FrameTarget.php';
+require_once $__dir . '/HTMLPurifier/AttrDef/HTML/ID.php';
+require_once $__dir . '/HTMLPurifier/AttrDef/HTML/Pixels.php';
+require_once $__dir . '/HTMLPurifier/AttrDef/HTML/Length.php';
+require_once $__dir . '/HTMLPurifier/AttrDef/HTML/LinkTypes.php';
+require_once $__dir . '/HTMLPurifier/AttrDef/HTML/MultiLength.php';
+require_once $__dir . '/HTMLPurifier/AttrDef/HTML/Nmtokens.php';
+require_once $__dir . '/HTMLPurifier/AttrDef/URI/Email.php';
+require_once $__dir . '/HTMLPurifier/AttrDef/URI/Host.php';
+require_once $__dir . '/HTMLPurifier/AttrDef/URI/IPv4.php';
+require_once $__dir . '/HTMLPurifier/AttrDef/URI/IPv6.php';
+require_once $__dir . '/HTMLPurifier/AttrDef/URI/Email/SimpleCheck.php';
+require_once $__dir . '/HTMLPurifier/AttrTransform/Background.php';
+require_once $__dir . '/HTMLPurifier/AttrTransform/BdoDir.php';
+require_once $__dir . '/HTMLPurifier/AttrTransform/BgColor.php';
+require_once $__dir . '/HTMLPurifier/AttrTransform/BoolToCSS.php';
+require_once $__dir . '/HTMLPurifier/AttrTransform/Border.php';
+require_once $__dir . '/HTMLPurifier/AttrTransform/EnumToCSS.php';
+require_once $__dir . '/HTMLPurifier/AttrTransform/ImgRequired.php';
+require_once $__dir . '/HTMLPurifier/AttrTransform/ImgSpace.php';
+require_once $__dir . '/HTMLPurifier/AttrTransform/Input.php';
+require_once $__dir . '/HTMLPurifier/AttrTransform/Lang.php';
+require_once $__dir . '/HTMLPurifier/AttrTransform/Length.php';
+require_once $__dir . '/HTMLPurifier/AttrTransform/Name.php';
+require_once $__dir . '/HTMLPurifier/AttrTransform/SafeEmbed.php';
+require_once $__dir . '/HTMLPurifier/AttrTransform/SafeObject.php';
+require_once $__dir . '/HTMLPurifier/AttrTransform/SafeParam.php';
+require_once $__dir . '/HTMLPurifier/AttrTransform/ScriptRequired.php';
+require_once $__dir . '/HTMLPurifier/AttrTransform/Textarea.php';
+require_once $__dir . '/HTMLPurifier/ChildDef/Chameleon.php';
+require_once $__dir . '/HTMLPurifier/ChildDef/Custom.php';
+require_once $__dir . '/HTMLPurifier/ChildDef/Empty.php';
+require_once $__dir . '/HTMLPurifier/ChildDef/Required.php';
+require_once $__dir . '/HTMLPurifier/ChildDef/Optional.php';
+require_once $__dir . '/HTMLPurifier/ChildDef/StrictBlockquote.php';
+require_once $__dir . '/HTMLPurifier/ChildDef/Table.php';
+require_once $__dir . '/HTMLPurifier/DefinitionCache/Decorator.php';
+require_once $__dir . '/HTMLPurifier/DefinitionCache/Null.php';
+require_once $__dir . '/HTMLPurifier/DefinitionCache/Serializer.php';
+require_once $__dir . '/HTMLPurifier/DefinitionCache/Decorator/Cleanup.php';
+require_once $__dir . '/HTMLPurifier/DefinitionCache/Decorator/Memory.php';
+require_once $__dir . '/HTMLPurifier/HTMLModule/Bdo.php';
+require_once $__dir . '/HTMLPurifier/HTMLModule/CommonAttributes.php';
+require_once $__dir . '/HTMLPurifier/HTMLModule/Edit.php';
+require_once $__dir . '/HTMLPurifier/HTMLModule/Forms.php';
+require_once $__dir . '/HTMLPurifier/HTMLModule/Hypertext.php';
+require_once $__dir . '/HTMLPurifier/HTMLModule/Image.php';
+require_once $__dir . '/HTMLPurifier/HTMLModule/Legacy.php';
+require_once $__dir . '/HTMLPurifier/HTMLModule/List.php';
+require_once $__dir . '/HTMLPurifier/HTMLModule/Name.php';
+require_once $__dir . '/HTMLPurifier/HTMLModule/NonXMLCommonAttributes.php';
+require_once $__dir . '/HTMLPurifier/HTMLModule/Object.php';
+require_once $__dir . '/HTMLPurifier/HTMLModule/Presentation.php';
+require_once $__dir . '/HTMLPurifier/HTMLModule/Proprietary.php';
+require_once $__dir . '/HTMLPurifier/HTMLModule/Ruby.php';
+require_once $__dir . '/HTMLPurifier/HTMLModule/SafeEmbed.php';
+require_once $__dir . '/HTMLPurifier/HTMLModule/SafeObject.php';
+require_once $__dir . '/HTMLPurifier/HTMLModule/Scripting.php';
+require_once $__dir . '/HTMLPurifier/HTMLModule/StyleAttribute.php';
+require_once $__dir . '/HTMLPurifier/HTMLModule/Tables.php';
+require_once $__dir . '/HTMLPurifier/HTMLModule/Target.php';
+require_once $__dir . '/HTMLPurifier/HTMLModule/Text.php';
+require_once $__dir . '/HTMLPurifier/HTMLModule/Tidy.php';
+require_once $__dir . '/HTMLPurifier/HTMLModule/XMLCommonAttributes.php';
+require_once $__dir . '/HTMLPurifier/HTMLModule/Tidy/Name.php';
+require_once $__dir . '/HTMLPurifier/HTMLModule/Tidy/Proprietary.php';
+require_once $__dir . '/HTMLPurifier/HTMLModule/Tidy/XHTMLAndHTML4.php';
+require_once $__dir . '/HTMLPurifier/HTMLModule/Tidy/Strict.php';
+require_once $__dir . '/HTMLPurifier/HTMLModule/Tidy/Transitional.php';
+require_once $__dir . '/HTMLPurifier/HTMLModule/Tidy/XHTML.php';
+require_once $__dir . '/HTMLPurifier/Injector/AutoParagraph.php';
+require_once $__dir . '/HTMLPurifier/Injector/DisplayLinkURI.php';
+require_once $__dir . '/HTMLPurifier/Injector/Linkify.php';
+require_once $__dir . '/HTMLPurifier/Injector/PurifierLinkify.php';
+require_once $__dir . '/HTMLPurifier/Injector/RemoveEmpty.php';
+require_once $__dir . '/HTMLPurifier/Injector/SafeObject.php';
+require_once $__dir . '/HTMLPurifier/Lexer/DOMLex.php';
+require_once $__dir . '/HTMLPurifier/Lexer/DirectLex.php';
+require_once $__dir . '/HTMLPurifier/Strategy/Composite.php';
+require_once $__dir . '/HTMLPurifier/Strategy/Core.php';
+require_once $__dir . '/HTMLPurifier/Strategy/FixNesting.php';
+require_once $__dir . '/HTMLPurifier/Strategy/MakeWellFormed.php';
+require_once $__dir . '/HTMLPurifier/Strategy/RemoveForeignElements.php';
+require_once $__dir . '/HTMLPurifier/Strategy/ValidateAttributes.php';
+require_once $__dir . '/HTMLPurifier/TagTransform/Font.php';
+require_once $__dir . '/HTMLPurifier/TagTransform/Simple.php';
+require_once $__dir . '/HTMLPurifier/Token/Comment.php';
+require_once $__dir . '/HTMLPurifier/Token/Tag.php';
+require_once $__dir . '/HTMLPurifier/Token/Empty.php';
+require_once $__dir . '/HTMLPurifier/Token/End.php';
+require_once $__dir . '/HTMLPurifier/Token/Start.php';
+require_once $__dir . '/HTMLPurifier/Token/Text.php';
+require_once $__dir . '/HTMLPurifier/URIFilter/DisableExternal.php';
+require_once $__dir . '/HTMLPurifier/URIFilter/DisableExternalResources.php';
+require_once $__dir . '/HTMLPurifier/URIFilter/HostBlacklist.php';
+require_once $__dir . '/HTMLPurifier/URIFilter/MakeAbsolute.php';
+require_once $__dir . '/HTMLPurifier/URIFilter/Munge.php';
+require_once $__dir . '/HTMLPurifier/URIScheme/ftp.php';
+require_once $__dir . '/HTMLPurifier/URIScheme/http.php';
+require_once $__dir . '/HTMLPurifier/URIScheme/https.php';
+require_once $__dir . '/HTMLPurifier/URIScheme/mailto.php';
+require_once $__dir . '/HTMLPurifier/URIScheme/news.php';
+require_once $__dir . '/HTMLPurifier/URIScheme/nntp.php';
+require_once $__dir . '/HTMLPurifier/VarParser/Flexible.php';
+require_once $__dir . '/HTMLPurifier/VarParser/Native.php';

library/HTMLPurifier/AttrCollections.php

@@ -1,19 +1,17 @@
 <?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();
-    
+    public $info = array();
+
     /**
      * Performs all expansions on internal data for use by other inclusions
      * It also collects all attribute collection extensions from
@@ -21,7 +19,7 @@ class HTMLPurifier_AttrCollections
      * @param $attr_types HTMLPurifier_AttrTypes instance
      * @param $modules Hash array of HTMLPurifier_HTMLModule members
      */
-    function HTMLPurifier_AttrCollections($attr_types, $modules) {
+    public function __construct($attr_types, $modules) {
         // load extensions from the modules
         foreach ($modules as $module) {
             foreach ($module->attr_collections as $coll_i => $coll) {
@@ -47,13 +45,13 @@ class HTMLPurifier_AttrCollections
             $this->expandIdentifiers($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(&$attr) {
+    public function performInclusions(&$attr) {
         if (!isset($attr[0])) return;
         $merge = $attr[0];
         $seen  = array(); // recursion guard
@@ -74,25 +72,25 @@ class HTMLPurifier_AttrCollections
         }
         unset($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, $attr_types) {
-        
+    public function expandIdentifiers(&$attr, $attr_types) {
+
         // because foreach will process new elements we add, make sure we
         // skip duplicates
         $processed = array();
-        
+
         foreach ($attr as $def_i => $def) {
             // skip inclusions
             if ($def_i === 0) continue;
-            
+
             if (isset($processed[$def_i])) continue;
-            
+
             // determine whether or not attribute is required
             if ($required = (strpos($def_i, '*') !== false)) {
                 // rename the definition
@@ -100,21 +98,21 @@ class HTMLPurifier_AttrCollections
                 $def_i = trim($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 = $required;
@@ -122,8 +120,9 @@ class HTMLPurifier_AttrCollections
                 unset($attr[$def_i]);
             }
         }
-        
+
     }
-    
+
 }
 
+// vim: et sw=4 sts=4

library/HTMLPurifier/AttrDef.php

@@ -2,85 +2,86 @@
 
 /**
  * Base class for all validating attribute definitions.
- * 
+ *
  * This family of classes forms the core for not only HTML attribute validation,
  * but also any sort of string that needs to be validated or cleaned (which
- * means CSS properties and composite definitions are defined here too).  
+ * means CSS properties and composite definitions are defined here too).
  * Besides defining (through code) what precisely makes the string valid,
  * subclasses are also responsible for cleaning the code if possible.
  */
 
-class HTMLPurifier_AttrDef
+abstract class HTMLPurifier_AttrDef
 {
-    
+
     /**
      * Tells us whether or not an HTML attribute is minimized. Has no
      * meaning in other contexts.
      */
-    var $minimized = false;
-    
+    public $minimized = false;
+
     /**
      * Tells us whether or not an HTML attribute is required. Has no
      * meaning in other contexts
      */
-    var $required = false;
-    
+    public $required = false;
+
     /**
      * Validates and cleans passed string according to a definition.
-     * 
-     * @public
+     *
      * @param $string String to be validated and cleaned.
      * @param $config Mandatory HTMLPurifier_Config object.
      * @param $context Mandatory HTMLPurifier_AttrContext object.
      */
-    function validate($string, $config, &$context) {
-        trigger_error('Cannot call abstract function', E_USER_ERROR);
-    }
-    
+    abstract public function validate($string, $config, $context);
+
     /**
      * Convenience method that parses a string as if it were CDATA.
-     * 
+     *
      * This method process a string in the manner specified at
      * <http://www.w3.org/TR/html4/types.html#h-6.2> by removing
      * leading and trailing whitespace, ignoring line feeds, and replacing
      * carriage returns and tabs with spaces.  While most useful for HTML
      * attributes specified as CDATA, it can also be applied to most CSS
      * values.
-     * 
+     *
      * @note This method is not entirely standards compliant, as trim() removes
      *       more types of whitespace than specified in the spec. In practice,
      *       this is rarely a problem, as those extra characters usually have
      *       already been removed by HTMLPurifier_Encoder.
-     * 
+     *
      * @warning This processing is inconsistent with XML's whitespace handling
      *          as specified by section 3.3.3 and referenced XHTML 1.0 section
-     *          4.7.  Compliant processing requires all line breaks normalized
-     *          to "\n", so the fix is not as simple as fixing it in this
-     *          function.  Trim and whitespace collapsing are supposed to only
-     *          occur in NMTOKENs.  However, note that we are NOT necessarily
-     *          parsing XML, thus, this behavior may still be correct.
-     * 
-     * @public
+     *          4.7.  However, note that we are NOT necessarily
+     *          parsing XML, thus, this behavior may still be correct. We
+     *          assume that newlines have been normalized.
      */
-    function parseCDATA($string) {
+    public function parseCDATA($string) {
         $string = trim($string);
-        $string = str_replace("\n", '', $string);
-        $string = str_replace(array("\r", "\t"), ' ', $string);
+        $string = str_replace(array("\n", "\t", "\r"), ' ', $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
+    public function make($string) {
+        // default implementation, return a flyweight of this object.
+        // If $string has an effect on the returned object (i.e. you
+        // need to overload this method), it is best
+        // to clone or instantiate new copies. (Instantiation is safer.)
         return $this;
     }
-    
+
+    /**
+     * Removes spaces from rgb(0, 0, 0) so that shorthand CSS properties work
+     * properly. THIS IS A HACK!
+     */
+    protected function mungeRgb($string) {
+        return preg_replace('/rgb\((\d+)\s*,\s*(\d+)\s*,\s*(\d+)\)/', 'rgb(\1,\2,\3)', $string);
+    }
+
 }
 
+// vim: et sw=4 sts=4

library/HTMLPurifier/AttrDef/CSS.php

@@ -1,8 +1,5 @@
 <?php
 
-require_once 'HTMLPurifier/AttrDef.php';
-require_once 'HTMLPurifier/CSSDefinition.php';
-
 /**
  * Validates the HTML attribute style, otherwise known as CSS.
  * @note We don't implement the whole CSS specification, so it might be
@@ -16,29 +13,48 @@ require_once 'HTMLPurifier/CSSDefinition.php';
  */
 class HTMLPurifier_AttrDef_CSS extends HTMLPurifier_AttrDef
 {
-    
-    function validate($css, $config, &$context) {
-        
+
+    public function validate($css, $config, $context) {
+
         $css = $this->parseCDATA($css);
-        
+
         $definition = $config->getCSSDefinition();
-        
+
         // 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();
-        
+
+        /**
+         * Name of the current CSS property being validated.
+         */
+        $property = false;
+        $context->register('CurrentCSSProperty', $property);
+
         foreach ($declarations as $declaration) {
             if (!$declaration) continue;
             if (!strpos($declaration, ':')) continue;
             list($property, $value) = explode(':', $declaration, 2);
             $property = trim($property);
             $value    = trim($value);
-            if (!isset($definition->info[$property])) continue;
+            $ok = false;
+            do {
+                if (isset($definition->info[$property])) {
+                    $ok = true;
+                    break;
+                }
+                if (ctype_lower($property)) break;
+                $property = strtolower($property);
+                if (isset($definition->info[$property])) {
+                    $ok = true;
+                    break;
+                }
+            } while(0);
+            if (!$ok) continue;
             // inefficient call, since the validator will do this again
             if (strtolower(trim($value)) !== 'inherit') {
                 // inherit works for everything (but only on the base property)
@@ -50,19 +66,22 @@ class HTMLPurifier_AttrDef_CSS extends HTMLPurifier_AttrDef
             if ($result === false) continue;
             $propvalues[$property] = $result;
         }
-        
+
+        $context->destroy('CurrentCSSProperty');
+
         // procedure does not write the new CSS simultaneously, so it's
         // slightly inefficient, but it's the only way of getting rid of
         // duplicates. Perhaps config to optimize it, but not now.
-        
+
         $new_declarations = '';
         foreach ($propvalues as $prop => $value) {
             $new_declarations .= "$prop:$value;";
         }
-        
+
         return $new_declarations ? $new_declarations : false;
-        
+
     }
-    
+
 }
 
+// vim: et sw=4 sts=4

library/HTMLPurifier/AttrDef/CSS/AlphaValue.php

@@ -0,0 +1,21 @@
+<?php
+
+class HTMLPurifier_AttrDef_CSS_AlphaValue extends HTMLPurifier_AttrDef_CSS_Number
+{
+
+    public function __construct() {
+        parent::__construct(false); // opacity is non-negative, but we will clamp it
+    }
+
+    public function validate($number, $config, $context) {
+        $result = parent::validate($number, $config, $context);
+        if ($result === false) return $result;
+        $float = (float) $result;
+        if ($float < 0.0) $result = '0';
+        if ($float > 1.0) $result = '1';
+        return $result;
+    }
+
+}
+
+// vim: et sw=4 sts=4

library/HTMLPurifier/AttrDef/CSS/Background.php

@@ -1,22 +1,19 @@
 <?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) {
+    protected $info;
+
+    public function __construct($config) {
         $def = $config->getCSSDefinition();
         $this->info['background-color'] = $def->info['background-color'];
         $this->info['background-image'] = $def->info['background-image'];
@@ -24,26 +21,29 @@ class HTMLPurifier_AttrDef_CSS_Background extends HTMLPurifier_AttrDef
         $this->info['background-attachment'] = $def->info['background-attachment'];
         $this->info['background-position'] = $def->info['background-position'];
     }
-    
-    function validate($string, $config, &$context) {
-        
+
+    public function validate($string, $config, $context) {
+
         // regular pre-processing
         $string = $this->parseCDATA($string);
         if ($string === '') return false;
-        
+
+        // munge rgb() decl if necessary
+        $string = $this->mungeRgb($string);
+
         // assumes URI doesn't have spaces in it
         $bits = explode(' ', strtolower($string)); // bits to process
-        
+
         $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 => $status) {
@@ -64,23 +64,24 @@ class HTMLPurifier_AttrDef_CSS_Background extends HTMLPurifier_AttrDef
                 break;
             }
         }
-        
+
         if (!$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);
-        
+
     }
-    
+
 }
 
+// vim: et sw=4 sts=4

library/HTMLPurifier/AttrDef/CSS/BackgroundPosition.php

@@ -1,9 +1,5 @@
 <?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.
@@ -11,7 +7,7 @@ require_once 'HTMLPurifier/AttrDef/CSS/Percentage.php';
         [
             <percentage> | <length> | left | center | right
         ]
-        [ 
+        [
             <percentage> | <length> | top | center | bottom
         ]?
     ] |
@@ -32,10 +28,10 @@ require_once 'HTMLPurifier/AttrDef/CSS/Percentage.php';
 
 /* 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.
 */
 
@@ -47,27 +43,27 @@ require_once 'HTMLPurifier/AttrDef/CSS/Percentage.php';
  */
 class HTMLPurifier_AttrDef_CSS_BackgroundPosition extends HTMLPurifier_AttrDef
 {
-    
-    var $length;
-    var $percentage;
-    
-    function HTMLPurifier_AttrDef_CSS_BackgroundPosition() {
+
+    protected $length;
+    protected $percentage;
+
+    public function __construct() {
         $this->length     = new HTMLPurifier_AttrDef_CSS_Length();
         $this->percentage = new HTMLPurifier_AttrDef_CSS_Percentage();
     }
-    
-    function validate($string, $config, &$context) {
+
+    public function validate($string, $config, $context) {
         $string = $this->parseCDATA($string);
         $bits = explode(' ', $string);
-        
+
         $keywords = array();
         $keywords['h'] = false; // left, right
         $keywords['v'] = false; // top, bottom
         $keywords['c'] = false; // center
         $measures = array();
-        
+
         $i = 0;
-        
+
         $lookup = array(
             'top' => 'v',
             'bottom' => 'v',
@@ -75,10 +71,10 @@ class HTMLPurifier_AttrDef_CSS_BackgroundPosition extends HTMLPurifier_AttrDef
             'right' => 'h',
             'center' => 'c'
         );
-        
+
         foreach ($bits as $bit) {
             if ($bit === '') continue;
-            
+
             // test for keyword
             $lbit = ctype_lower($bit) ? $bit : strtolower($bit);
             if (isset($lookup[$lbit])) {
@@ -86,28 +82,28 @@ class HTMLPurifier_AttrDef_CSS_BackgroundPosition extends HTMLPurifier_AttrDef
                 $keywords[$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);
@@ -115,15 +111,16 @@ class HTMLPurifier_AttrDef_CSS_BackgroundPosition extends HTMLPurifier_AttrDef
             $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);
-        
+
     }
-    
+
 }
 
+// vim: et sw=4 sts=4

library/HTMLPurifier/AttrDef/CSS/Border.php

@@ -1,28 +1,26 @@
 <?php
 
-require_once 'HTMLPurifier/AttrDef.php';
-
 /**
  * Validates the border property as defined by CSS.
  */
 class HTMLPurifier_AttrDef_CSS_Border extends HTMLPurifier_AttrDef
 {
-    
+
     /**
      * Local copy of properties this property is shorthand for.
      */
-    var $info = array();
-    
-    function HTMLPurifier_AttrDef_CSS_Border($config) {
+    protected $info = array();
+
+    public function __construct($config) {
         $def = $config->getCSSDefinition();
         $this->info['border-width'] = $def->info['border-width'];
         $this->info['border-style'] = $def->info['border-style'];
         $this->info['border-top-color'] = $def->info['border-top-color'];
     }
-    
-    function validate($string, $config, &$context) {
+
+    public function validate($string, $config, $context) {
         $string = $this->parseCDATA($string);
-        // we specifically will not support rgb() syntax with spaces
+        $string = $this->mungeRgb($string);
         $bits = explode(' ', $string);
         $done = array(); // segments we've finished
         $ret = ''; // return value
@@ -39,6 +37,7 @@ class HTMLPurifier_AttrDef_CSS_Border extends HTMLPurifier_AttrDef
         }
         return rtrim($ret);
     }
-    
+
 }
 
+// vim: et sw=4 sts=4

library/HTMLPurifier/AttrDef/CSS/Color.php

@@ -1,58 +1,24 @@
 <?php
 
-require_once 'HTMLPurifier/AttrDef.php';
-
-HTMLPurifier_ConfigSchema::define(
-    'Core', 'ColorKeywords', array(
-        'maroon'    => '#800000',
-        'red'       => '#FF0000',
-        'orange'    => '#FFA500',
-        'yellow'    => '#FFFF00',
-        'olive'     => '#808000',
-        'purple'    => '#800080',
-        'fuchsia'   => '#FF00FF',
-        'white'     => '#FFFFFF',
-        'lime'      => '#00FF00',
-        'green'     => '#008000',
-        'navy'      => '#000080',
-        'blue'      => '#0000FF',
-        'aqua'      => '#00FFFF',
-        'teal'      => '#008080',
-        'black'     => '#000000',
-        'silver'    => '#C0C0C0',
-        'gray'      => '#808080'
-    ), 'hash', '
-Lookup array of color names to six digit hexadecimal number corresponding
-to color, with preceding hash mark. Used when parsing colors.
-This directive has been available since 2.0.0.
-');
-
 /**
  * Validates Color as defined by CSS.
  */
 class HTMLPurifier_AttrDef_CSS_Color extends HTMLPurifier_AttrDef
 {
-    
-    function validate($color, $config, &$context) {
-        
+
+    public function validate($color, $config, $context) {
+
         static $colors = null;
         if ($colors === null) $colors = $config->get('Core', 'ColorKeywords');
-        
+
         $color = trim($color);
-        if (!$color) return false;
-        
+        if ($color === '') return false;
+
         $lower = strtolower($color);
         if (isset($colors[$lower])) return $colors[$lower];
-        
-        if ($color[0] === '#') {
-            // hexadecimal handling
-            $hex = substr($color, 1);
-            $length = strlen($hex);
-            if ($length !== 3 && $length !== 6) return false;
-            if (!ctype_xdigit($hex)) return false;
-        } else {
+
+        if (strpos($color, 'rgb(') !== false) {
             // rgb literal handling
-            if (strpos($color, 'rgb(')) return false;
             $length = strlen($color);
             if (strpos($color, ')') !== $length - 1) return false;
             $triad = substr($color, 4, $length - 4 - 1);
@@ -90,11 +56,23 @@ class HTMLPurifier_AttrDef_CSS_Color extends HTMLPurifier_AttrDef
             }
             $new_triad = implode(',', $new_parts);
             $color = "rgb($new_triad)";
+        } else {
+            // hexadecimal handling
+            if ($color[0] === '#') {
+                $hex = substr($color, 1);
+            } else {
+                $hex = $color;
+                $color = '#' . $color;
+            }
+            $length = strlen($hex);
+            if ($length !== 3 && $length !== 6) return false;
+            if (!ctype_xdigit($hex)) return false;
         }
-        
+
         return $color;
-        
+
     }
-    
+
 }
 
+// vim: et sw=4 sts=4

library/HTMLPurifier/AttrDef/CSS/Composite.php

@@ -2,7 +2,7 @@
 
 /**
  * Allows multiple validators to attempt to validate attribute.
- * 
+ *
  * Composite is just what it sounds like: a composite of many validators.
  * This means that multiple HTMLPurifier_AttrDef objects will have a whack
  * at the string.  If one of them passes, that's what is returned.  This is
@@ -11,27 +11,28 @@
  */
 class HTMLPurifier_AttrDef_CSS_Composite extends HTMLPurifier_AttrDef
 {
-    
+
     /**
      * List of HTMLPurifier_AttrDef objects that may process strings
-     * @protected
+     * @todo Make protected
      */
-    var $defs;
-    
+    public $defs;
+
     /**
      * @param $defs List of HTMLPurifier_AttrDef objects
      */
-    function HTMLPurifier_AttrDef_CSS_Composite($defs) {
+    public function __construct($defs) {
         $this->defs = $defs;
     }
-    
-    function validate($string, $config, &$context) {
+
+    public function validate($string, $config, $context) {
         foreach ($this->defs as $i => $def) {
             $result = $this->defs[$i]->validate($string, $config, $context);
             if ($result !== false) return $result;
         }
         return false;
     }
-    
+
 }
 
+// vim: et sw=4 sts=4

library/HTMLPurifier/AttrDef/CSS/DenyElementDecorator.php

@@ -0,0 +1,28 @@
+<?php
+
+/**
+ * Decorator which enables CSS properties to be disabled for specific elements.
+ */
+class HTMLPurifier_AttrDef_CSS_DenyElementDecorator extends HTMLPurifier_AttrDef
+{
+    public $def, $element;
+
+    /**
+     * @param $def Definition to wrap
+     * @param $element Element to deny
+     */
+    public function __construct($def, $element) {
+        $this->def = $def;
+        $this->element = $element;
+    }
+    /**
+     * Checks if CurrentToken is set and equal to $this->element
+     */
+    public function validate($string, $config, $context) {
+        $token = $context->get('CurrentToken', true);
+        if ($token && $token->name == $this->element) return false;
+        return $this->def->validate($string, $config, $context);
+    }
+}
+
+// vim: et sw=4 sts=4

library/HTMLPurifier/AttrDef/CSS/Filter.php

@@ -0,0 +1,54 @@
+<?php
+
+/**
+ * Microsoft's proprietary filter: CSS property
+ * @note Currently supports the alpha filter. In the future, this will
+ *       probably need an extensible framework
+ */
+class HTMLPurifier_AttrDef_CSS_Filter extends HTMLPurifier_AttrDef
+{
+
+    protected $intValidator;
+
+    public function __construct() {
+        $this->intValidator = new HTMLPurifier_AttrDef_Integer();
+    }
+
+    public function validate($value, $config, $context) {
+        $value = $this->parseCDATA($value);
+        if ($value === 'none') return $value;
+        // if we looped this we could support multiple filters
+        $function_length = strcspn($value, '(');
+        $function = trim(substr($value, 0, $function_length));
+        if ($function !== 'alpha' &&
+            $function !== 'Alpha' &&
+            $function !== 'progid:DXImageTransform.Microsoft.Alpha'
+            ) return false;
+        $cursor = $function_length + 1;
+        $parameters_length = strcspn($value, ')', $cursor);
+        $parameters = substr($value, $cursor, $parameters_length);
+        $params = explode(',', $parameters);
+        $ret_params = array();
+        $lookup = array();
+        foreach ($params as $param) {
+            list($key, $value) = explode('=', $param);
+            $key   = trim($key);
+            $value = trim($value);
+            if (isset($lookup[$key])) continue;
+            if ($key !== 'opacity') continue;
+            $value = $this->intValidator->validate($value, $config, $context);
+            if ($value === false) continue;
+            $int = (int) $value;
+            if ($int > 100) $value = '100';
+            if ($int < 0) $value = '0';
+            $ret_params[] = "$key=$value";
+            $lookup[$key] = true;
+        }
+        $ret_parameters = implode(',', $ret_params);
+        $ret_function = "$function($ret_parameters)";
+        return $ret_function;
+    }
+
+}
+
+// vim: et sw=4 sts=4

library/HTMLPurifier/AttrDef/CSS/Font.php

@@ -1,24 +1,22 @@
 <?php
 
-require_once 'HTMLPurifier/AttrDef.php';
-
 /**
  * Validates shorthand CSS property font.
  */
 class HTMLPurifier_AttrDef_CSS_Font extends HTMLPurifier_AttrDef
 {
-    
+
     /**
      * Local copy of component validators.
-     * 
+     *
      * @note If we moved specific CSS property definitions to their own
      *       classes instead of having them be assembled at run time by
      *       CSSDefinition, this wouldn't be necessary.  We'd instantiate
      *       our own copies.
      */
-    var $info = array();
-    
-    function HTMLPurifier_AttrDef_CSS_Font($config) {
+    protected $info = array();
+
+    public function __construct($config) {
         $def = $config->getCSSDefinition();
         $this->info['font-style']   = $def->info['font-style'];
         $this->info['font-variant'] = $def->info['font-variant'];
@@ -27,9 +25,9 @@ class HTMLPurifier_AttrDef_CSS_Font extends HTMLPurifier_AttrDef
         $this->info['line-height']  = $def->info['line-height'];
         $this->info['font-family']  = $def->info['font-family'];
     }
-    
-    function validate($string, $config, &$context) {
-        
+
+    public function validate($string, $config, $context) {
+
         static $system_fonts = array(
             'caption' => true,
             'icon' => true,
@@ -38,27 +36,27 @@ class HTMLPurifier_AttrDef_CSS_Font extends HTMLPurifier_AttrDef
             '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($system_fonts[$lowercase_string])) {
             return $lowercase_string;
         }
-        
+
         $bits = explode(' ', $string); // bits to process
         $stage = 0; // this indicates what we're looking for
         $caught = array(); // which stage 0 properties have we caught?
         $stage_1 = array('font-style', 'font-variant', 'font-weight');
         $final = ''; // output
-        
+
         for ($i = 0, $size = count($bits); $i < $size; $i++) {
             if ($bits[$i] === '') continue;
             switch ($stage) {
-                
+
                 // attempting to catch font-style, font-variant or font-weight
                 case 0:
                     foreach ($stage_1 as $validator_name) {
@@ -74,7 +72,7 @@ class HTMLPurifier_AttrDef_CSS_Font extends HTMLPurifier_AttrDef
                     // all three caught, continue on
                     if (count($caught) >= 3) $stage = 1;
                     if ($r !== false) break;
-                
+
                 // attempting to catch font-size and perhaps line-height
                 case 1:
                     $found_slash = false;
@@ -128,7 +126,7 @@ class HTMLPurifier_AttrDef_CSS_Font extends HTMLPurifier_AttrDef
                         break;
                     }
                     return false;
-                
+
                 // attempting to catch font-family
                 case 2:
                     $font_family =
@@ -145,6 +143,7 @@ class HTMLPurifier_AttrDef_CSS_Font extends HTMLPurifier_AttrDef
         }
         return false;
     }
-    
+
 }
 
+// vim: et sw=4 sts=4

library/HTMLPurifier/AttrDef/CSS/FontFamily.php

@@ -1,16 +1,13 @@
 <?php
 
-require_once 'HTMLPurifier/AttrDef.php';
-
-// whitelisting allowed fonts would be nice
-
 /**
  * Validates a font family list according to CSS spec
+ * @todo whitelisting allowed fonts would be nice
  */
 class HTMLPurifier_AttrDef_CSS_FontFamily extends HTMLPurifier_AttrDef
 {
-    
-    function validate($string, $config, &$context) {
+
+    public function validate($string, $config, $context) {
         static $generic_names = array(
             'serif' => true,
             'sans-serif' => true,
@@ -18,8 +15,7 @@ class HTMLPurifier_AttrDef_CSS_FontFamily extends HTMLPurifier_AttrDef
             'fantasy' => true,
             'cursive' => true
         );
-        
-        $string = $this->parseCDATA($string);
+
         // assume that no font names contain commas in them
         $fonts = explode(',', $string);
         $final = '';
@@ -38,29 +34,57 @@ class HTMLPurifier_AttrDef_CSS_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
+
+                $new_font = '';
+                for ($i = 0, $c = strlen($font); $i < $c; $i++) {
+                    if ($font[$i] === '\\') {
+                        $i++;
+                        if ($i >= $c) {
+                            $new_font .= '\\';
+                            break;
+                        }
+                        if (ctype_xdigit($font[$i])) {
+                            $code = $font[$i];
+                            for ($a = 1, $i++; $i < $c && $a < 6; $i++, $a++) {
+                                if (!ctype_xdigit($font[$i])) break;
+                                $code .= $font[$i];
+                            }
+                            // We have to be extremely careful when adding
+                            // new characters, to make sure we're not breaking
+                            // the encoding.
+                            $char = HTMLPurifier_Encoder::unichr(hexdec($code));
+                            if (HTMLPurifier_Encoder::cleanUTF8($char) === '') continue;
+                            $new_font .= $char;
+                            if ($i < $c && trim($font[$i]) !== '') $i--;
+                            continue;
+                        }
+                        if ($font[$i] === "\n") continue;
+                    }
+                    $new_font .= $font[$i];
+                }
+
+                $font = $new_font;
             }
             // $font is a pure representation of the font name
-            
-            if (ctype_alnum($font)) {
+
+            if (ctype_alnum($font) && $font !== '') {
                 // very simple font, allow it in unharmed
                 $final .= $font . ', ';
                 continue;
             }
-            
+
             // complicated font, requires quoting
-            
+
             // armor single quotes and new lines
+            $font = str_replace("\\", "\\\\", $font);
             $font = str_replace("'", "\\'", $font);
-            $font = str_replace("\n", "\\\n", $font);
             $final .= "'$font', ";
         }
         $final = rtrim($final, ', ');
         if ($final === '') return false;
         return $final;
     }
-    
+
 }
 
+// vim: et sw=4 sts=4

library/HTMLPurifier/AttrDef/CSS/ImportantDecorator.php

@@ -0,0 +1,40 @@
+<?php
+
+/**
+ * Decorator which enables !important to be used in CSS values.
+ */
+class HTMLPurifier_AttrDef_CSS_ImportantDecorator extends HTMLPurifier_AttrDef
+{
+    public $def, $allow;
+
+    /**
+     * @param $def Definition to wrap
+     * @param $allow Whether or not to allow !important
+     */
+    public function __construct($def, $allow = false) {
+        $this->def = $def;
+        $this->allow = $allow;
+    }
+    /**
+     * Intercepts and removes !important if necessary
+     */
+    public function validate($string, $config, $context) {
+        // test for ! and important tokens
+        $string = trim($string);
+        $is_important = false;
+        // :TODO: optimization: test directly for !important and ! important
+        if (strlen($string) >= 9 && substr($string, -9) === 'important') {
+            $temp = rtrim(substr($string, 0, -9));
+            // use a temp, because we might want to restore important
+            if (strlen($temp) >= 1 && substr($temp, -1) === '!') {
+                $string = rtrim(substr($temp, 0, -1));
+                $is_important = true;
+            }
+        }
+        $string = $this->def->validate($string, $config, $context);
+        if ($this->allow && $is_important) $string .= ' !important';
+        return $string;
+    }
+}
+
+// vim: et sw=4 sts=4

library/HTMLPurifier/AttrDef/CSS/Length.php

@@ -1,55 +1,47 @@
 <?php
 
-require_once 'HTMLPurifier/AttrDef.php';
-require_once 'HTMLPurifier/AttrDef/CSS/Number.php';
-
 /**
  * Represents a Length as defined by CSS.
  */
 class HTMLPurifier_AttrDef_CSS_Length extends HTMLPurifier_AttrDef
 {
-    
+
+    protected $min, $max;
+
     /**
-     * Valid unit lookup table.
-     * @warning The code assumes all units are two characters long.  Be careful
-     *          if we have to change this behavior!
+     * @param HTMLPurifier_Length $max Minimum length, or null for no bound. String is also acceptable.
+     * @param HTMLPurifier_Length $max Maximum length, or null for no bound. String is also acceptable.
      */
-    var $units = array('em' => true, 'ex' => true, 'px' => true, 'in' => true,
-         'cm' => true, 'mm' => true, 'pt' => true, 'pc' => true);
-    /**
-     * Instance of HTMLPurifier_AttrDef_Number to defer number validation to
-     */
-    var $number_def;
-    
-    /**
-     * @param $non_negative Bool indication whether or not negative values are
-     *                      allowed.
-     */
-    function HTMLPurifier_AttrDef_CSS_Length($non_negative = false) {
-        $this->number_def = new HTMLPurifier_AttrDef_CSS_Number($non_negative);
+    public function __construct($min = null, $max = null) {
+        $this->min = $min !== null ? HTMLPurifier_Length::make($min) : null;
+        $this->max = $max !== null ? HTMLPurifier_Length::make($max) : null;
     }
-    
-    function validate($length, $config, &$context) {
-        
-        $length = $this->parseCDATA($length);
-        if ($length === '') return false;
-        if ($length === '0') return '0';
-        $strlen = strlen($length);
-        if ($strlen === 1) return false; // impossible!
-        
-        // 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;
-        
-        $number = $this->number_def->validate($number, $config, $context);
-        if ($number === false) return false;
-        
-        return $number . $unit;
-        
+
+    public function validate($string, $config, $context) {
+        $string = $this->parseCDATA($string);
+
+        // Optimizations
+        if ($string === '') return false;
+        if ($string === '0') return '0';
+        if (strlen($string) === 1) return false;
+
+        $length = HTMLPurifier_Length::make($string);
+        if (!$length->isValid()) return false;
+
+        if ($this->min) {
+            $c = $length->compareTo($this->min);
+            if ($c === false) return false;
+            if ($c < 0) return false;
+        }
+        if ($this->max) {
+            $c = $length->compareTo($this->max);
+            if ($c === false) return false;
+            if ($c > 0) return false;
+        }
+
+        return $length->toString();
     }
-    
+
 }
 
+// vim: et sw=4 sts=4