Gusev's proposed patch

Signed-off-by: Edward Z. Yang <ezyang@mit.edu>

.gitignore

@@ -1,13 +1,24 @@
+tags
 conf/
 test-settings.php
+config-schema.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
+*.patch
+/*.php
+vendor
+composer.lock

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

@@ -1,4 +1,4 @@
-5 - Major feature enhancements
+4 - Minor feature enhancements
 
 [ Appendix A: Release focus IDs ]
 0 - N/A

INSTALL

@@ -2,8 +2,8 @@
 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
@@ -15,11 +15,10 @@ with these contents.
 ---------------------------------------------------------------------------
 1.  Compatibility
 
-HTML Purifier is PHP 5 only, and is actively tested from PHP 5.0.5 and 
-up. It has no core dependencies with other libraries. PHP 
-4 support was deprecated on December 31, 2007 with HTML Purifier 3.0.0. 
-Essential security fixes will be issued for the 2.1.x branch 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.
+HTML Purifier is not compatible with zend.ze1_compatibility_mode.
 
 These optional extensions can enhance the capabilities of HTML Purifier:
 
@@ -27,6 +26,10 @@ These optional extensions can enhance the capabilities of HTML Purifier:
     * bcmath : Used for unit conversion and imagecrash protection
     * tidy   : Used for pretty-printing HTML
 
+These optional libraries can enhance the capabilities of HTML Purifier:
+
+    * CSSTidy : Clean CSS stylesheets using %Core.ExtractStyleBlocks
+    * Net_IDNA2 (PEAR) : IRI support using %Core.EnableIDNA
 
 ---------------------------------------------------------------------------
 2.  Reconnaissance
@@ -96,32 +99,32 @@ 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
@@ -131,14 +134,14 @@ Autoload compatibility
         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
 ----------------------
@@ -147,18 +150,18 @@ For better performance
     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
@@ -169,22 +172,22 @@ Standalone version
     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
@@ -192,14 +195,14 @@ 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).
@@ -233,12 +236,12 @@ HTML Purifier uses iconv to support other character encodings, as such,
 any encoding that iconv supports <http://www.gnu.org/software/libiconv/>
 HTML Purifier supports with this code:
 
-    $config->set('Core', 'Encoding', /* put your encoding here */);
+    $config->set('Core.Encoding', /* put your encoding here */);
 
 An example usage for Latin-1 websites (the most common encoding for English
 websites):
 
-    $config->set('Core', 'Encoding', 'ISO-8859-1');
+    $config->set('Core.Encoding', 'ISO-8859-1');
 
 Note that HTML Purifier's support for non-Unicode encodings is crippled by the
 fact that any character not supported by that encoding will be silently
@@ -253,7 +256,7 @@ reason, I do not include the solution in this document).
 For those of you using HTML 4.01 Transitional, you can disable
 XHTML output like this:
 
-    $config->set('HTML', 'Doctype', 'HTML 4.01 Transitional');
+    $config->set('HTML.Doctype', 'HTML 4.01 Transitional');
 
 Other supported doctypes include:
 
@@ -279,14 +282,14 @@ are, respectively, %HTML.Allowed, %URI.MakeAbsolute and %URI.Base, and
 %AutoFormat.AutoParagraph. The %Namespace.Directive naming convention
 translates to:
 
-    $config->set('Namespace', 'Directive', $value);
+    $config->set('Namespace.Directive', $value);
 
 E.g.
 
-    $config->set('HTML', 'Allowed', 'p,b,a[href],i');
-    $config->set('URI', 'Base', 'http://www.example.com');
-    $config->set('URI', 'MakeAbsolute', true);
-    $config->set('AutoFormat', 'AutoParagraph', true);
+    $config->set('HTML.Allowed', 'p,b,a[href],i');
+    $config->set('URI.Base', 'http://www.example.com');
+    $config->set('URI.MakeAbsolute', true);
+    $config->set('AutoFormat.AutoParagraph', true);
 
 
 ---------------------------------------------------------------------------
@@ -320,11 +323,11 @@ If you are unable or unwilling to give write permissions to the cache
 directory, you can either disable the cache (and suffer a performance
 hit):
 
-    $config->set('Core', 'DefinitionCache', null);
+    $config->set('Core.DefinitionCache', null);
 
 Or move the cache directory somewhere else (no trailing slash):
 
-    $config->set('Cache', 'SerializerPath', '/home/user/absolute/path');
+    $config->set('Cache.SerializerPath', '/home/user/absolute/path');
 
 
 ---------------------------------------------------------------------------
@@ -332,11 +335,6 @@ Or move the cache directory somewhere else (no trailing slash):
 
 The interface is mind-numbingly simple:
 
-    $purifier = new HTMLPurifier();
-    $clean_html = $purifier->purify( $dirty_html );
-
-...or, if you're using the configuration object:
-
     $purifier = new HTMLPurifier($config);
     $clean_html = $purifier->purify( $dirty_html );
 
@@ -354,8 +352,9 @@ If your website is in UTF-8 and XHTML Transitional, use this code:
 
 <?php
     require_once '/path/to/htmlpurifier/library/HTMLPurifier.auto.php';
-    
-    $purifier = new HTMLPurifier();
+
+    $config = HTMLPurifier_Config::createDefault();
+    $purifier = new HTMLPurifier($config);
     $clean_html = $purifier->purify($dirty_html);
 ?>
 
@@ -363,12 +362,13 @@ 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
+    $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

@@ -20,7 +20,7 @@ ce document pour quelques choses.
 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.
 
@@ -48,7 +48,7 @@ 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);
 ?>
@@ -57,11 +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

@@ -9,6 +9,249 @@ NEWS ( CHANGELOG and HISTORY )                                     HTMLPurifier
     . Internal change
 ==========================
 
+4.6.0, unknown release date
+# URI parsing algorithm was made more strict, so only prefixes which
+  looks like schemes will actually be schemes.  Thanks
+  Michael Gusev <mgusev@sugarcrm.com> for fixing.
+
+4.5.0, released 2013-02-17
+# Fix bug where stacked attribute transforms clobber each other;
+  this also means it's no longer possible to override attribute
+  transforms in later modules.  No internal code was using this
+  but this may break some clients.
+# We now use SHA-1 to identify cached definitions, instead of MD5.
+! Support display:inline-block
+! Support for more white-space CSS values.
+! Permit underscores in font families
+! Support for page-break-* CSS3 properties when proprietary properties
+  are enabled.
+! New directive %Core.DisableExcludes; can be set to 'true' to turn off
+  SGML excludes checking.  If HTML Purifier is removing too much text
+  and you don't care about full standards compliance, try setting this to
+  'true'.
+- Use prepend for SPL autoloading on PHP 5.3 and later.
+- Fix bug with nofollow transform when pre-existing rel exists.
+- Fix bug where background:url() always gets lower-cased
+  (but not background-image:url())
+- Fix bug with non lower-case color names in HTML
+- Fix bug where data URI validation doesn't remove temporary files.
+  Thanks Javier Marín Ros <javiermarinros@gmail.com> for reporting.
+- Don't remove certain empty tags on RemoveEmpty.
+
+4.4.0, released 2012-01-18
+# Removed PEARSax3 handler.
+# URI.Munge now munges URIs inside the same host that go from https
+  to http.  Reported by Neike Taika-Tessaro.
+# Core.EscapeNonASCIICharacters now always transforms entities to
+  entities, even if target encoding is UTF-8.
+# Tighten up selector validation in ExtractStyleBlocks.
+  Non-syntactically valid selectors are now rejected, along with
+  some of the more obscure ones such as attribute selectors, the
+  :lang pseudoselector, and anything not in CSS2.1.  Furthermore,
+  ID and class selectors now work properly with the relevant
+  configuration attributes.  Also, mute errors when parsing CSS
+  with CSS Tidy.  Reported by Mario Heiderich and Norman Hippert.
+! Added support for 'scope' attribute on tables.
+! Added %HTML.TargetBlank, which adds target="blank" to all outgoing links.
+! Properly handle sub-lists directly nested inside of lists in
+  a standards compliant way, by moving them into the preceding <li>
+! Added %HTML.AllowedComments and %HTML.AllowedCommentsRegexp for
+  limited allowed comments in untrusted situations.
+! Implement iframes, and allow them to be used in untrusted mode with
+  %HTML.SafeIframe and %URI.SafeIframeRegexp.  Thanks Bradley M. Froehle
+  <brad.froehle@gmail.com> for submitting an initial version of the patch.
+! The Forms module now works properly for transitional doctypes.
+! Added support for internationalized domain names. You need the PEAR
+  Net_IDNA2 module to be in your path; if it is installed, ensure the
+  class can be loaded and then set %Core.EnableIDNA to true.
+- Color keywords are now case insensitive.  Thanks Yzmir Ramirez
+  <yramirez-htmlpurifier@adicio.com> for reporting.
+- Explicitly initialize anonModule variable to null.
+- Do not duplicate nofollow if already present.  Thanks 178
+  for reporting.
+- Do not add nofollow if hostname matches our current host.  Thanks 178
+  for reporting, and Neike Taika-Tessaro for helping diagnose.
+- Do not unset parser variable; this fixes intermittent serialization
+  problems.  Thanks Neike Taika-Tessaro for reporting, bill
+  <10010tiger@gmail.com> for diagnosing.
+- Fix iconv truncation bug, where non-UTF-8 target encodings see
+  output truncated after around 8000 characters.  Thanks Jörg Ludwig
+  <joerg.ludwig@iserv.eu> for reporting.
+- Fix broken table content model for XHTML1.1 (and also earlier
+  versions, although the W3C validator doesn't catch those violations).
+  Thanks GlitchMr <glitch.mr@gmail.com> for reporting.
+
+4.3.0, released 2011-03-27
+# Fixed broken caching of customized raw definitions, but requires an
+  API change.  The old API still works but will emit a warning,
+  see http://htmlpurifier.org/docs/enduser-customize.html#optimized
+  for how to upgrade your code.
+# Protect against Internet Explorer innerHTML behavior by specially
+  treating attributes with backticks but no angled brackets, quotes or
+  spaces.  This constitutes a slight semantic change, which can be
+  reverted using %Output.FixInnerHTML.  Reported by Neike Taika-Tessaro
+  and Mario Heiderich.
+# Protect against cssText/innerHTML by restricting allowed characters
+  used in fonts further than mandated by the specification and encoding
+  some extra special characters in URLs.  Reported by Neike
+  Taika-Tessaro and Mario Heiderich.
+! Added %HTML.Nofollow to add rel="nofollow" to external links.
+! More types of SPL autoloaders allowed on later versions of PHP.
+! Implementations for position, top, left, right, bottom, z-index
+  when %CSS.Trusted is on.
+! Add %Cache.SerializerPermissions option for custom serializer
+  directory/file permissions
+! Fix longstanding bug in Flash support for non-IE browsers, and
+  allow more wmode attributes.
+! Add %CSS.AllowedFonts to restrict permissible font names.
+- Switch to an iterative traversal of the DOM, which prevents us
+  from running out of stack space for deeply nested documents.
+  Thanks Maxim Krizhanovsky for contributing a patch.
+- Make removal of conditional IE comments ungreedy; thanks Bernd
+  for reporting.
+- Escape CDATA before removing Internet Explorer comments.
+- Fix removal of id attributes under certain conditions by ensuring
+  armor attributes are preserved when recreating tags.
+- Check if schema.ser was corrupted.
+- Check if zend.ze1_compatibility_mode is on, and error out if it is.
+  This safety check is only done for HTMLPurifier.auto.php; if you
+  are using standalone or the specialized includes files, you're
+  expected to know what you're doing.
+- Stop repeatedly writing the cache file after I'm done customizing a
+  raw definition.  Reported by ajh.
+- Switch to using require_once in the Bootstrap to work around bad
+  interaction with Zend Debugger and APC.  Reported by Antonio Parraga.
+- Fix URI handling when hostname is missing but scheme is present.
+  Reported by Neike Taika-Tessaro.
+- Fix missing numeric entities on DirectLex; thanks Neike Taika-Tessaro
+  for reporting.
+- Fix harmless notice from indexing into empty string.  Thanks Matthijs
+  Kooijman <matthijs@stdin.nl> for reporting.
+- Don't autoclose no parent elements are able to support the element
+  that triggered the autoclose.  In particular fixes strange behavior
+  of stray <li> tags.  Thanks pkuliga@gmail.com for reporting and
+  Neike Taika-Tessaro <pinkgothic@gmail.com> for debugging assistance.
+
+4.2.0, released 2010-09-15
+! Added %Core.RemoveProcessingInstructions, which lets you remove
+  <? ... ?> statements.
+! Added %URI.DisableResources functionality; the directive originally
+  did nothing.  Thanks David Rothstein for reporting.
+! Add documentation about configuration directive types.
+! Add %CSS.ForbiddenProperties configuration directive.
+! Add %HTML.FlashAllowFullScreen to permit embedded Flash objects
+  to utilize full-screen mode.
+! Add optional support for the <code>file</code> URI scheme, enable
+  by explicitly setting %URI.AllowedSchemes.
+! Add %Core.NormalizeNewlines options to allow turning off newline
+  normalization.
+- Fix improper handling of Internet Explorer conditional comments
+  by parser.  Thanks zmonteca for reporting.
+- Fix missing attributes bug when running on Mac Snow Leopard and APC.
+  Thanks sidepodcast for the fix.
+- Warn if an element is allowed, but an attribute it requires is
+  not allowed.
+
+4.1.1, released 2010-05-31
+- Fix undefined index warnings in maintenance scripts.
+- Fix bug in DirectLex for parsing elements with a single attribute
+  with entities.
+- Rewrite CSS output logic for font-family and url().  Thanks Mario
+  Heiderich <mario.heiderich@googlemail.com> for reporting and Takeshi
+  Terada <t-terada@violet.plala.or.jp> for suggesting the fix.
+- Emit an error for CollectErrors if a body is extracted
+- Fix bug where in background-position for center keyword handling.
+- Fix infinite loop when a wrapper element is inserted in a context
+  where it's not allowed.  Thanks Lars <lars@renoz.dk> for reporting.
+- Remove +x bit and shebang from index.php; only supported mode is to
+  explicitly call it with php.
+- Make test script less chatty when log_errors is on.
+
+4.1.0, released 2010-04-26
+! Support proprietary height attribute on table element
+! Support YouTube slideshows that contain /cp/ in their URL.
+! Support for data: URI scheme; not enabled by default, add it using
+  %URI.AllowedSchemes
+! Support flashvars when using %HTML.SafeObject and %HTML.SafeEmbed.
+! Support for Internet Explorer compatibility with %HTML.SafeObject
+  using %Output.FlashCompat.
+! Handle <ol><ol> properly, by inserting the necessary <li> tag.
+- Always quote the insides of url(...) in CSS.
+
+4.0.0, released 2009-07-07
+# APIs for ConfigSchema subsystem have substantially changed. See
+  docs/dev-config-bcbreaks.txt for details; in essence, anything that
+  had both namespace and directive now have a single unified key.
+# Some configuration directives were renamed, specifically:
+    %AutoFormatParam.PurifierLinkifyDocURL -> %AutoFormat.PurifierLinkify.DocURL
+    %FilterParam.ExtractStyleBlocksEscaping -> %Filter.ExtractStyleBlocks.Escaping
+    %FilterParam.ExtractStyleBlocksScope -> %Filter.ExtractStyleBlocks.Scope
+    %FilterParam.ExtractStyleBlocksTidyImpl -> %Filter.ExtractStyleBlocks.TidyImpl
+  As usual, the old directive names will still work, but will throw E_NOTICE
+  errors.
+# The allowed values for class have been relaxed to allow all of CDATA for
+  doctypes that are not XHTML 1.1 or XHTML 2.0.  For old behavior, set
+  %Attr.ClassUseCDATA to false.
+# Instead of appending the content model to an old content model, a blank
+  element will replace the old content model.  You can use #SUPER to get
+  the old content model.
+! More robust support for name="" and id=""
+! HTMLPurifier_Config::inherit($config) allows you to inherit one
+  configuration, and have changes to that configuration be propagated
+  to all of its children.
+! Implement %HTML.Attr.Name.UseCDATA, which relaxes validation rules on
+  the name attribute when set. Use with care. Thanks Ian Cook for
+  sponsoring.
+! Implement %AutoFormat.RemoveEmpty.RemoveNbsp, which removes empty
+  tags that contain non-breaking spaces as well other whitespace. You
+  can also modify which tags should have &nbsp; maintained with
+  %AutoFormat.RemoveEmpty.RemoveNbsp.Exceptions.
+! Implement %Attr.AllowedClasses, which allows administrators to restrict
+  classes users can use to a specified finite set of classes, and
+  %Attr.ForbiddenClasses, which is the logical inverse.
+! You can now maintain your own configuration schema directories by
+  creating a config-schema.php file or passing an extra argument. Check
+  docs/dev-config-schema.html for more details.
+! Added HTMLPurifier_Config->serialize() method, which lets you save away
+  your configuration in a compact serial file, which you can unserialize
+  and use directly without having to go through the overhead of setup.
+- Fix bug where URIDefinition would not get cleared if it's directives got
+  changed.
+- Fix fatal error in HTMLPurifier_Encoder on certain platforms (probably NetBSD 5.0)
+- Fix bug in Linkify autoformatter involving <a><span>http://foo</span></a>
+- Make %URI.Munge not apply to links that have the same host as your host.
+- Prevent stray </body> tag from truncating output, if a second </body>
+  is present.
+. Created script maintenance/rename-config.php for renaming a configuration
+  directive while maintaining its alias.  This script does not change source code.
+. Implement namespace locking for definition construction, to prevent
+  bugs where a directive is used for definition construction but is not
+  used to construct the cache hash.
+
+3.3.0, released 2009-02-16
+! Implement CSS property 'overflow' when %CSS.AllowTricky is true.
+! Implement generic property list classess
+- 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.
@@ -18,7 +261,7 @@ NEWS ( CHANGELOG and HISTORY )                                     HTMLPurifier
   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 
+  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.
@@ -29,7 +272,7 @@ NEWS ( CHANGELOG and HISTORY )                                     HTMLPurifier
 ! 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. 
+  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
@@ -73,7 +316,7 @@ NEWS ( CHANGELOG and HISTORY )                                     HTMLPurifier
   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; 
+. 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.
@@ -82,7 +325,7 @@ NEWS ( CHANGELOG and HISTORY )                                     HTMLPurifier
 
 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. 
+  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
@@ -92,7 +335,7 @@ NEWS ( CHANGELOG and HISTORY )                                     HTMLPurifier
   %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 
+! 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
@@ -139,10 +382,10 @@ NEWS ( CHANGELOG and HISTORY )                                     HTMLPurifier
   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 
+. HTMLPurifier_Generator requires $config and $context parameters. If you
   don't know what they should be, use HTMLPurifier_Config::createDefault()
   and new HTMLPurifier_Context().
-. Printers now properly distinguish between output configuration, and 
+. Printers now properly distinguish between output configuration, and
   target configuration. This is not applicable to scripts using
   the Printers for HTML Purifier related tasks.
 . HTML/CSS Printers must be primed with prepareGenerator($gen_config), otherwise
@@ -229,7 +472,7 @@ NEWS ( CHANGELOG and HISTORY )                                     HTMLPurifier
   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 
+  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.
@@ -269,7 +512,7 @@ NEWS ( CHANGELOG and HISTORY )                                     HTMLPurifier
 . 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* 
+. 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
@@ -290,7 +533,7 @@ NEWS ( CHANGELOG and HISTORY )                                     HTMLPurifier
 . 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 
+. 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
@@ -332,7 +575,7 @@ NEWS ( CHANGELOG and HISTORY )                                     HTMLPurifier
   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)
@@ -357,7 +600,7 @@ 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
@@ -516,7 +759,7 @@ 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()
@@ -600,7 +843,7 @@ 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
@@ -814,3 +1057,5 @@ 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

@@ -11,84 +11,86 @@ If no interest is expressed for a feature that may require a considerable
 amount of effort to implement, it may get endlessly delayed. Do not be
 afraid to cast your vote for the next feature to be implemented!
 
-- Investigate how early internal structures can be accessed; this would
-  prevent structures from being parsed and serialized multiple times.
-- Built-in support for target="_blank" on all external links
-- Allow <a id="asdf" name="asdf">
-- Implement overflow CSS property (as per jlp09550)
+Things to do as soon as possible:
+
+ - http://htmlpurifier.org/phorum/read.php?3,5560,6307#msg-6307
+ - Think about allowing explicit order of operations hooks for transforms
+ - Fix "<.<" bug (trailing < is removed if not EOD)
+ - Build in better internal state dumps and debugging tools for remote
+   debugging
+ - Allowed/Allowed* have strange interactions when both set
+ ? Transform lone embeds into object tags
+ - Deprecated config options that emit warnings when you set them (with'
+   a way of muting the warning if you really want to)
+ - Make HTML.Trusted work with Output.FlashCompat
+ - HTML.Trusted and HTML.SafeObject have funny interaction; general
+   problem is what to do when a module "supersedes" another
+   (see also tables and basic tables.)  This is a little dicier
+   because HTML.SafeObject has some extra functionality that
+   trusted might find useful.  See http://htmlpurifier.org/phorum/read.php?3,5762,6100
 
 FUTURE VERSIONS
 ---------------
 
-3.3 release [It's All About Trust] (floating)
+4.6 release [OMG CONFIG PONIES]
+ ! Fix Printer. It's from the old days when we didn't have decent XML classes
+ ! Factor demo.php into a set of Printer classes, and then create a stub
+   file for users here (inside the actual HTML Purifier library)
+ - Fix error handling with form construction
+ - Do encoding validation in Printers, or at least, where user data comes in
+ - Config: Add examples to everything (make built-in which also automatically
+   gives output)
+ - Add "register" field to config schemas to eliminate dependence on
+   naming conventions (try to remember why we ultimately decided on tihs)
+
+5.0 release [HTML 5]
+ # Swap out code to use html5lib tokenizer and tree-builder
+ ! Allow turning off of FixNesting and required attribute insertion
+
+5.1 release [It's All About Trust] (floating)
  # Implement untrusted, dangerous elements/attributes
  # Implement IDREF support (harder than it seems, since you cannot have
    IDREFs to non-existent IDs)
+     - Implement <area> (client and server side image maps are blocking
+       on IDREF support)
  # Frameset XHTML 1.0 and HTML 4.01 doctypes
- - Implement <area>
  - Figure out how to simultaneously set %CSS.Trusted and %HTML.Trusted (?)
 
-3.4 release [Error'ed]
+5.2 release [Error'ed]
  # Error logging for filtering/cleanup procedures
- - XSS-attempt detection--certain errors are flagged XSS-like
-
-3.5 release [Do What I Mean, Not What I Say]
  # Additional support for poorly written HTML
     - Microsoft Word HTML cleaning (i.e. MsoNormal, but research essential!)
     - Friendly strict handling of <address> (block -> <br>)
- ? Remove redundant tags, ex. <u><u>Underlined</u></u>. Implementation notes:
-    1. Analyzing which tags to remove duplicants
-    2. Ensure attributes are merged into the parent tag
-    3. Extend the tag exclusion system to specify whether or not the
-    contents should be dropped or not (currently, there's code that could do
-    something like this if it didn't drop the inner text too.)
- - Remove <span> tags that don't do anything (no attributes)
+ - XSS-attempt detection--certain errors are flagged XSS-like
  - Append something to duplicate IDs so they're still usable (impl. note: the
    dupe detector would also need to detect the suffix as well)
- - Externalize inline CSS to promote clean HTML, proposed by Sander Tekelenburg
 
-4.0 release [Beyond HTML]
+6.0 release [Beyond HTML]
  # Legit token based CSS parsing (will require revamping almost every
-   AttrDef class). Probably will use CSSTidy class?
+   AttrDef class). Probably will use CSSTidy
  # More control over allowed CSS properties using a modularization
- # HTML 5 support
  # IRI support (this includes IDN)
  - Standardize token armor for all areas of processing
- - Convert RTL/LTR override characters to <bdo> tags, or vice versa on demand.
-   Also, enable disabling of directionality
 
-5.0 release [To XML and Beyond]
+7.0 release [To XML and Beyond]
  - Extended HTML capabilities based on namespacing and tag transforms (COMPLEX)
     - Hooks for adding custom processors to custom namespaced tags and
       attributes, offer default implementation
     - Lots of documentation and samples
 
 Ongoing
- - More refactoring to take advantage of PHP5's facilities 
+ - More refactoring to take advantage of PHP5's facilities
  - Refactor unit tests into lots of test methods
  - Plugins for major CMSes (COMPLEX)
     - phpBB
-    - Drupal needs loving!
-    - Phorum need loving!
-    - more! (look for ones that use WYSIWYGs)
-    - Also, maybe a FAQ for extension writers with HTML Purifier
+    - Also, a FAQ for extension writers with HTML Purifier
 
 AutoFormat
  - Smileys
  - Syntax highlighting (with GeSHi) with <pre> and possibly <?php
  - Look at http://drupal.org/project/Modules/category/63 for ideas
 
-Optimizations
- - Reduce size of internal data-structures (esp. HTMLDefinition)
- - Research memory usage of objects versus arrays
- - Combine multiple strategies into a single, single-pass strategy
- - Get PH5P working with the latest versions of DOM, which have much more
-   stringent error checking procedures. Maybe convert straight to tokens.
- - Get rid of set_include_path(). Save this for another major release.
-
 Neat feature related
- ! Factor demo.php into a set of Printer classes, and then create a stub
-   file for users here (inside the actual HTML Purifier library)
  ! Support exporting configuration, so users can easily tweak settings
    in the demo, and then copy-paste into their own setup
  - Advanced URI filtering schemes (see docs/proposal-new-directives.txt)
@@ -105,14 +107,32 @@ Neat feature related
  - Full set of color keywords. Also, a way to add onto them without
    finalizing the configuration object.
  - Write a var_export and memcached DefinitionCache - Denis
- - Allow restriction of allowed class values
+ - Built-in support for target="_blank" on all external links
+ - Convert RTL/LTR override characters to <bdo> tags, or vice versa on demand.
+   Also, enable disabling of directionality
+ ? Externalize inline CSS to promote clean HTML, proposed by Sander Tekelenburg
+ ? Remove redundant tags, ex. <u><u>Underlined</u></u>. Implementation notes:
+    1. Analyzing which tags to remove duplicants
+    2. Ensure attributes are merged into the parent tag
+    3. Extend the tag exclusion system to specify whether or not the
+    contents should be dropped or not (currently, there's code that could do
+    something like this if it didn't drop the inner text too.)
+ ? Make AutoParagraph also support paragraph-izing double <br> tags, and not
+   just double newlines.  This is kind of tough to do in the current framework,
+   though, and might be reasonably approximated by search replacing double <br>s
+   with newlines before running it through HTML Purifier.
 
 Maintenance related (slightly boring)
  # CHMOD install script for PEAR installs
  ! Factor out command line parser into its own class, and unit test it
- ! Nested configuration namespaces
- - Distinguish between default settings and explicitly set settings, so
-   configurations can be merged
+ - Reduce size of internal data-structures (esp. HTMLDefinition)
+ - Allow merging configurations.  Thus,
+        a -> b -> default
+        c -> d -> default
+   becomes
+        a -> b -> c -> d -> default
+   Maybe allow more fine-grained tuning of this behavior. Alternatively,
+   encourage people to use short plist depths before building them up.
  - Time PHPT tests
 
 ChildDef related (very boring)
@@ -126,3 +146,5 @@ Wontfix
  - Pretty-printing HTML: users can use Tidy on the output on entire page
  - Native content compression, whitespace stripping: use gzip if this is
    really important
+
+    vim: et sw=4 sts=4

VERSION

@@ -1 +1 @@
-3.2.0
+4.5.0

WHATSNEW

@@ -1,6 +1,6 @@
-HTML Purifier 3.2.0 is an amalgamation of new features and fixes that
-have accumulated over a four month period.  Some notable features
-include %AutoFormat.RemoveEmpty, column tracking for tokens, 
-%AutoFormat.DisplayLinkURI and %Attr.DefaultImageAlt.  There were also
-major improvements to the test suite interface, error collection output
-and the auto-formatter framework.
+HTML Purifier 4.5.0 is a minor bugfix and feature release, containing an
+accumulation of changes over a year.  CSS support has been extended to
+support display:inline-block, white-space, underscores in font families,
+page-break-* CSS3 properties (when proprietary is enabled.)  We now use
+SHA-1 to identify cached definitions, and the semantics of stacked
+attribute transforms has changed slightly.

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

@@ -12,3 +12,5 @@ $begin = xdebug_memory_usage();
 $schema = HTMLPurifier_ConfigSchema::makeFromSerial();
 
 echo xdebug_memory_usage() - $begin;
+
+// vim: et sw=4 sts=4

benchmarks/Lexer.php

@@ -9,7 +9,7 @@ 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();
@@ -22,48 +22,48 @@ if (version_compare(PHP_VERSION, '5', '>=')) {
 // 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;
     }
 }
@@ -80,18 +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();
     $timer->display();
 }
@@ -118,11 +118,11 @@ foreach ($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
@@ -153,3 +153,6 @@ echo '<div>Random input was: ' .
 
 
 </body></html>
+<?php
+
+// vim: et sw=4 sts=4

benchmarks/Trace.php

@@ -17,3 +17,5 @@ $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 +50,7 @@
 
 <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 +14,7 @@ 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 +126,6 @@ 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 +538,6 @@ 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

composer.json

@@ -0,0 +1,22 @@
+{
+    "name": "ezyang/htmlpurifier",
+    "description": "Standards compliant HTML filter written in PHP",
+    "type": "library",
+    "keywords": ["html"],
+    "homepage": "http://htmlpurifier.org/",
+    "license": "LGPL",
+    "authors": [
+        {
+            "name": "Edward Z. Yang",
+            "email": "admin@htmlpurifier.org",
+            "homepage": "http://ezyang.com"
+        }
+    ],
+    "require": {
+        "php": ">=5.2"
+    },
+    "autoload": {
+        "psr-0": { "HTMLPurifier": "library/" },
+        "files": ["library/HTMLPurifier.composer.php"]
+    }
+}

configdoc/generate.php

@@ -18,22 +18,24 @@ TODO:
 if (version_compare(PHP_VERSION, '5.2', '<')) exit('PHP 5.2+ required.');
 error_reporting(E_ALL | E_STRICT);
 
-chdir(dirname(__FILE__));
-
 // load dual-libraries
-require_once '../extras/HTMLPurifierExtras.auto.php';
-require_once '../library/HTMLPurifier.auto.php';
+require_once dirname(__FILE__) . '/../extras/HTMLPurifierExtras.auto.php';
+require_once dirname(__FILE__) . '/../library/HTMLPurifier.auto.php';
 
 // setup HTML Purifier singleton
 HTMLPurifier::getInstance(array(
     'AutoFormat.PurifierLinkify' => true
 ));
 
-$interchange = HTMLPurifier_ConfigSchema_InterchangeBuilder::buildFromDirectory();
+$builder = new HTMLPurifier_ConfigSchema_InterchangeBuilder();
+$interchange = new HTMLPurifier_ConfigSchema_Interchange();
+$builder->buildDir($interchange);
+$loader = dirname(__FILE__) . '/../config-schema.php';
+if (file_exists($loader)) include $loader;
 $interchange->validate();
 
 $style = 'plain'; // use $_GET in the future, careful to validate!
-$configdoc_xml = 'configdoc.xml';
+$configdoc_xml = dirname(__FILE__) . '/configdoc.xml';
 
 $xml_builder = new HTMLPurifier_ConfigSchema_Builder_Xml();
 $xml_builder->openURI($configdoc_xml);
@@ -50,12 +52,13 @@ if (!$output) {
 }
 
 // write out
-file_put_contents("$style.html", $output);
+file_put_contents(dirname(__FILE__) . "/$style.html", $output);
 
 if (php_sapi_name() != 'cli') {
     // output (instant feedback if it's a browser)
     echo $output;
 } else {
-    echo 'Files generated successfully.';
+    echo "Files generated successfully.\n";
 }
 
+// vim: et sw=4 sts=4

configdoc/styles/plain.css

@@ -40,3 +40,5 @@ 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

@@ -14,13 +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')/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>
@@ -40,12 +40,26 @@
                             </xsl:apply-templates>
                         </ul>
                     </div>
+                    <div id="typesContainer">
+                        <h2>Types</h2>
+                        <xsl:apply-templates select="$typeLookup" mode="types" />
+                    </div>
                     <xsl:apply-templates />
                 </div>
             </body>
         </html>
     </xsl:template>
-    
+
+    <xsl:template match="type" mode="types">
+        <div class="type-block">
+            <xsl:attribute name="id">type-<xsl:value-of select="@id" /></xsl:attribute>
+            <h3><code><xsl:value-of select="@id" /></code>: <xsl:value-of select="@name" /></h3>
+            <div class="type-description">
+                <xsl:copy-of xmlns:xhtml="http://www.w3.org/1999/xhtml" select="xhtml:div/node()" />
+            </div>
+        </div>
+    </xsl:template>
+
     <xsl:template match="title" mode="toc" />
     <xsl:template match="namespace" mode="toc">
         <xsl:param name="overflowNumber" />
@@ -83,9 +97,9 @@
             </li>
         </xsl:if>
     </xsl:template>
-    
+
     <xsl:template match="title" />
-    
+
     <xsl:template match="namespace">
         <div class="namespace">
             <xsl:apply-templates />
@@ -102,7 +116,7 @@
             <xsl:copy-of xmlns:xhtml="http://www.w3.org/1999/xhtml" select="xhtml:div/node()" />
         </div>
     </xsl:template>
-    
+
     <xsl:template match="directive">
         <div>
             <xsl:attribute name="class"><!--
@@ -122,10 +136,10 @@
     <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">
@@ -179,7 +193,7 @@
             </xsl:for-each>
         </li>
     </xsl:template>
-    
+
     <xsl:template match="constraints/version">
         <tr>
             <th>Version added</th>
@@ -192,10 +206,13 @@
             <td>
                 <xsl:variable name="type" select="text()" />
                 <xsl:attribute name="class">type type-<xsl:value-of select="$type" /></xsl:attribute>
-                <xsl:value-of select="$typeLookup/type[@id=$type]/text()" />
-                <xsl:if test="@allow-null='yes'">
-                    (or null)
-                </xsl:if>
+                <a>
+                    <xsl:attribute name="href">#type-<xsl:value-of select="$type" /></xsl:attribute>
+                    <xsl:value-of select="$typeLookup/type[@id=$type]/@name" />
+                    <xsl:if test="@allow-null='yes'">
+                        (or null)
+                    </xsl:if>
+                </a>
             </td>
         </tr>
     </xsl:template>
@@ -229,5 +246,8 @@
     <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

@@ -1,14 +1,69 @@
 <?xml version="1.0" encoding="UTF-8"?>
 <types>
-  <type id="string">String</type>
-  <type id="istring">Case-insensitive string</type>
-  <type id="text">Text</type>
-  <type id="itext">Case-insensitive text</type>
-  <type id="int">Integer</type>
-  <type id="float">Float</type>
-  <type id="bool">Boolean</type>
-  <type id="lookup">Lookup array</type>
-  <type id="list">Array list</type>
-  <type id="hash">Associative array</type>
-  <type id="mixed">Mixed</type>
+  <type id="string" name="String"><div xmlns="http://www.w3.org/1999/xhtml">
+    A <a
+    href="http://docs.php.net/manual/en/language.types.string.php">sequence
+    of characters</a>.
+  </div></type>
+  <type id="istring" name="Case-insensitive string"><div xmlns="http://www.w3.org/1999/xhtml">
+    A series of case-insensitive characters.  Internally, upper-case
+    ASCII characters will be converted to lower-case.
+  </div></type>
+  <type id="text" name="Text"><div xmlns="http://www.w3.org/1999/xhtml">
+    A series of characters that may contain newlines.  Text tends to
+    indicate human-oriented text, as opposed to a machine format.
+  </div></type>
+  <type id="itext" name="Case-insensitive text"><div xmlns="http://www.w3.org/1999/xhtml">
+    A series of case-insensitive characters that may contain newlines.
+  </div></type>
+  <type id="int" name="Integer"><div xmlns="http://www.w3.org/1999/xhtml">
+    An <a
+      href="http://docs.php.net/manual/en/language.types.integer.php">
+      integer</a>.  You are alternatively permitted to pass a string of
+    digits instead, which will be cast to an integer using
+    <code>(int)</code>.
+  </div></type>
+  <type id="float" name="Float"><div xmlns="http://www.w3.org/1999/xhtml">
+    A <a href="http://docs.php.net/manual/en/language.types.float.php">
+      floating point number</a>.  You are alternatively permitted to
+    pass a numeric string (as defined by <code>is_numeric()</code>),
+    which will be cast to a float using <code>(float)</code>.
+  </div></type>
+  <type id="bool" name="Boolean"><div xmlns="http://www.w3.org/1999/xhtml">
+    A <a
+      href="http://docs.php.net/manual/en/language.types.boolean.php">boolean</a>.
+    You are alternatively permitted to pass an integer <code>0</code> or
+    <code>1</code> (other integers are not permitted) or a string
+    <code>"on"</code>, <code>"true"</code> or <code>"1"</code> for
+    <code>true</code>, and <code>"off"</code>, <code>"false"</code> or
+    <code>"0"</code> for <code>false</code>.
+  </div></type>
+  <type id="lookup" name="Lookup array"><div xmlns="http://www.w3.org/1999/xhtml">
+    An array whose values are <code>true</code>, e.g. <code>array('key'
+      => true, 'key2' => true)</code>.  You are alternatively permitted
+    to pass an array list of the keys <code>array('key', 'key2')</code>
+    or a comma-separated string of keys <code>"key, key2"</code>.  If
+    you pass an array list of values, ensure that your values are
+    strictly numerically indexed: <code>array('key1', 2 =>
+      'key2')</code> will not do what you expect and emits a warning.
+  </div></type>
+  <type id="list" name="Array list"><div xmlns="http://www.w3.org/1999/xhtml">
+    An array which has consecutive integer indexes, e.g.
+    <code>array('val1', 'val2')</code>.  You are alternatively permitted
+    to pass a comma-separated string of keys <code>"val1, val2"</code>.
+    If your array is not in this form, <code>array_values</code> is run
+    on the array and a warning is emitted.
+  </div></type>
+  <type id="hash" name="Associative array"><div xmlns="http://www.w3.org/1999/xhtml">
+    An array which is a mapping of keys to values, e.g.
+    <code>array('key1' => 'val1', 'key2' => 'val2')</code>.  You are
+    alternatively permitted to pass a comma-separated string of
+    key-colon-value strings, e.g. <code>"key1: val1, key2: val2"</code>.
+  </div></type>
+  <type id="mixed" name="Mixed"><div xmlns="http://www.w3.org/1999/xhtml">
+    An arbitrary PHP value of any type.
+  </div></type>
 </types>
+
+<!-- vim: et sw=4 sts=4
+-->

configdoc/usage.xml

@@ -6,6 +6,7 @@
   </file>
   <file name="HTMLPurifier/Lexer.php">
    <line>81</line>
+   <line>284</line>
   </file>
   <file name="HTMLPurifier/Lexer/DirectLex.php">
    <line>53</line>
@@ -13,7 +14,7 @@
    <line>348</line>
   </file>
   <file name="HTMLPurifier/Strategy/RemoveForeignElements.php">
-   <line>47</line>
+   <line>50</line>
   </file>
  </directive>
  <directive id="CSS.MaxImgLength">
@@ -23,22 +24,32 @@
  </directive>
  <directive id="CSS.Proprietary">
   <file name="HTMLPurifier/CSSDefinition.php">
-   <line>214</line>
+   <line>215</line>
   </file>
  </directive>
  <directive id="CSS.AllowTricky">
   <file name="HTMLPurifier/CSSDefinition.php">
-   <line>218</line>
+   <line>219</line>
+  </file>
+ </directive>
+ <directive id="CSS.Trusted">
+  <file name="HTMLPurifier/CSSDefinition.php">
+   <line>223</line>
   </file>
  </directive>
  <directive id="CSS.AllowImportant">
   <file name="HTMLPurifier/CSSDefinition.php">
-   <line>222</line>
+   <line>227</line>
   </file>
  </directive>
  <directive id="CSS.AllowedProperties">
   <file name="HTMLPurifier/CSSDefinition.php">
-   <line>274</line>
+   <line>302</line>
+  </file>
+ </directive>
+ <directive id="CSS.ForbiddenProperties">
+  <file name="HTMLPurifier/CSSDefinition.php">
+   <line>316</line>
   </file>
  </directive>
  <directive id="Cache.DefinitionImpl">
@@ -68,39 +79,57 @@
  </directive>
  <directive id="Core.Encoding">
   <file name="HTMLPurifier/Encoder.php">
-   <line>267</line>
-   <line>300</line>
+   <line>337</line>
+   <line>372</line>
   </file>
  </directive>
  <directive id="Test.ForceNoIconv">
   <file name="HTMLPurifier/Encoder.php">
-   <line>272</line>
-   <line>308</line>
+   <line>341</line>
+   <line>379</line>
   </file>
  </directive>
  <directive id="Core.EscapeNonASCIICharacters">
   <file name="HTMLPurifier/Encoder.php">
-   <line>304</line>
+   <line>373</line>
   </file>
  </directive>
  <directive id="Output.CommentScriptContents">
   <file name="HTMLPurifier/Generator.php">
-   <line>45</line>
+   <line>61</line>
+  </file>
+ </directive>
+ <directive id="Output.FixInnerHTML">
+  <file name="HTMLPurifier/Generator.php">
+   <line>62</line>
   </file>
  </directive>
  <directive id="Output.SortAttr">
   <file name="HTMLPurifier/Generator.php">
-   <line>46</line>
+   <line>63</line>
+  </file>
+ </directive>
+ <directive id="Output.FlashCompat">
+  <file name="HTMLPurifier/Generator.php">
+   <line>64</line>
   </file>
  </directive>
  <directive id="Output.TidyFormat">
   <file name="HTMLPurifier/Generator.php">
-   <line>75</line>
+   <line>93</line>
+  </file>
+ </directive>
+ <directive id="Core.NormalizeNewlines">
+  <file name="HTMLPurifier/Generator.php">
+   <line>107</line>
+  </file>
+  <file name="HTMLPurifier/Lexer.php">
+   <line>266</line>
   </file>
  </directive>
  <directive id="Output.Newline">
   <file name="HTMLPurifier/Generator.php">
-   <line>89</line>
+   <line>108</line>
   </file>
  </directive>
  <directive id="HTML.BlockWrapper">
@@ -130,20 +159,20 @@
  </directive>
  <directive id="HTML.ForbiddenElements">
   <file name="HTMLPurifier/HTMLDefinition.php">
-   <line>337</line>
+   <line>342</line>
   </file>
  </directive>
  <directive id="HTML.ForbiddenAttributes">
   <file name="HTMLPurifier/HTMLDefinition.php">
-   <line>338</line>
+   <line>343</line>
   </file>
  </directive>
  <directive id="HTML.Trusted">
   <file name="HTMLPurifier/HTMLModuleManager.php">
-   <line>202</line>
+   <line>204</line>
   </file>
   <file name="HTMLPurifier/Lexer.php">
-   <line>258</line>
+   <line>271</line>
   </file>
   <file name="HTMLPurifier/HTMLModule/Image.php">
    <line>27</line>
@@ -157,27 +186,45 @@
  </directive>
  <directive id="HTML.AllowedModules">
   <file name="HTMLPurifier/HTMLModuleManager.php">
-   <line>209</line>
+   <line>211</line>
   </file>
  </directive>
  <directive id="HTML.CoreModules">
   <file name="HTMLPurifier/HTMLModuleManager.php">
-   <line>210</line>
+   <line>212</line>
   </file>
  </directive>
  <directive id="HTML.Proprietary">
   <file name="HTMLPurifier/HTMLModuleManager.php">
-   <line>221</line>
+   <line>222</line>
   </file>
  </directive>
  <directive id="HTML.SafeObject">
   <file name="HTMLPurifier/HTMLModuleManager.php">
-   <line>226</line>
+   <line>225</line>
   </file>
  </directive>
  <directive id="HTML.SafeEmbed">
   <file name="HTMLPurifier/HTMLModuleManager.php">
-   <line>229</line>
+   <line>228</line>
+  </file>
+ </directive>
+ <directive id="HTML.SafeScripting">
+  <file name="HTMLPurifier/HTMLModuleManager.php">
+   <line>231</line>
+  </file>
+  <file name="HTMLPurifier/HTMLModule/SafeScripting.php">
+   <line>17</line>
+  </file>
+ </directive>
+ <directive id="HTML.Nofollow">
+  <file name="HTMLPurifier/HTMLModuleManager.php">
+   <line>234</line>
+  </file>
+ </directive>
+ <directive id="HTML.TargetBlank">
+  <file name="HTMLPurifier/HTMLModuleManager.php">
+   <line>237</line>
   </file>
  </directive>
  <directive id="Attr.IDBlacklist">
@@ -205,32 +252,48 @@
  </directive>
  <directive id="Core.ConvertDocumentToFragment">
   <file name="HTMLPurifier/Lexer.php">
-   <line>267</line>
+   <line>282</line>
+  </file>
+ </directive>
+ <directive id="Core.RemoveProcessingInstructions">
+  <file name="HTMLPurifier/Lexer.php">
+   <line>303</line>
+  </file>
+ </directive>
+ <directive id="URI.">
+  <file name="HTMLPurifier/URIDefinition.php">
+   <line>60</line>
+  </file>
+  <file name="HTMLPurifier/URIFilter/Munge.php">
+   <line>12</line>
   </file>
  </directive>
  <directive id="URI.Host">
   <file name="HTMLPurifier/URIDefinition.php">
-   <line>64</line>
+   <line>70</line>
+  </file>
+  <file name="HTMLPurifier/URIScheme.php">
+   <line>81</line>
   </file>
  </directive>
  <directive id="URI.Base">
   <file name="HTMLPurifier/URIDefinition.php">
-   <line>65</line>
+   <line>71</line>
   </file>
  </directive>
  <directive id="URI.DefaultScheme">
   <file name="HTMLPurifier/URIDefinition.php">
-   <line>72</line>
+   <line>78</line>
   </file>
  </directive>
  <directive id="URI.AllowedSchemes">
   <file name="HTMLPurifier/URISchemeRegistry.php">
-   <line>42</line>
+   <line>41</line>
   </file>
  </directive>
  <directive id="URI.OverrideAllowedSchemes">
   <file name="HTMLPurifier/URISchemeRegistry.php">
-   <line>43</line>
+   <line>42</line>
   </file>
  </directive>
  <directive id="URI.Disable">
@@ -246,6 +309,21 @@
    <line>12</line>
   </file>
  </directive>
+ <directive id="CSS.AllowedFonts">
+  <file name="HTMLPurifier/AttrDef/CSS/FontFamily.php">
+   <line>50</line>
+  </file>
+ </directive>
+ <directive id="Attr.AllowedClasses">
+  <file name="HTMLPurifier/AttrDef/HTML/Class.php">
+   <line>18</line>
+  </file>
+ </directive>
+ <directive id="Attr.ForbiddenClasses">
+  <file name="HTMLPurifier/AttrDef/HTML/Class.php">
+   <line>19</line>
+  </file>
+ </directive>
  <directive id="Attr.AllowedFrameTargets">
   <file name="HTMLPurifier/AttrDef/HTML/FrameTarget.php">
    <line>15</line>
@@ -253,23 +331,33 @@
  </directive>
  <directive id="Attr.EnableID">
   <file name="HTMLPurifier/AttrDef/HTML/ID.php">
-   <line>20</line>
+   <line>30</line>
   </file>
  </directive>
  <directive id="Attr.IDPrefix">
   <file name="HTMLPurifier/AttrDef/HTML/ID.php">
-   <line>26</line>
+   <line>36</line>
   </file>
  </directive>
  <directive id="Attr.IDPrefixLocal">
   <file name="HTMLPurifier/AttrDef/HTML/ID.php">
-   <line>28</line>
-   <line>31</line>
+   <line>38</line>
+   <line>41</line>
   </file>
  </directive>
  <directive id="Attr.IDBlacklistRegexp">
   <file name="HTMLPurifier/AttrDef/HTML/ID.php">
-   <line>54</line>
+   <line>64</line>
+  </file>
+ </directive>
+ <directive id="Attr.">
+  <file name="HTMLPurifier/AttrDef/HTML/LinkTypes.php">
+   <line>30</line>
+  </file>
+ </directive>
+ <directive id="Core.EnableIDNA">
+  <file name="HTMLPurifier/AttrDef/URI/Host.php">
+   <line>67</line>
   </file>
  </directive>
  <directive id="Attr.DefaultTextDir">
@@ -297,12 +385,25 @@
  </directive>
  <directive id="Attr.DefaultInvalidImageAlt">
   <file name="HTMLPurifier/AttrTransform/ImgRequired.php">
-   <line>32</line>
+   <line>33</line>
+  </file>
+ </directive>
+ <directive id="HTML.Attr.Name.UseCDATA">
+  <file name="HTMLPurifier/AttrTransform/Name.php">
+   <line>11</line>
+  </file>
+  <file name="HTMLPurifier/HTMLModule/Name.php">
+   <line>13</line>
+  </file>
+ </directive>
+ <directive id="HTML.FlashAllowFullScreen">
+  <file name="HTMLPurifier/AttrTransform/SafeParam.php">
+   <line>38</line>
   </file>
  </directive>
  <directive id="Core.EscapeInvalidChildren">
   <file name="HTMLPurifier/ChildDef/Required.php">
-   <line>55</line>
+   <line>62</line>
   </file>
  </directive>
  <directive id="Cache.SerializerPath">
@@ -310,19 +411,33 @@
    <line>91</line>
   </file>
  </directive>
- <directive id="FilterParam.ExtractStyleBlocksTidyImpl">
-  <file name="HTMLPurifier/Filter/ExtractStyleBlocks.php">
-   <line>41</line>
+ <directive id="Cache.SerializerPermissions">
+  <file name="HTMLPurifier/DefinitionCache/Serializer.php">
+   <line>107</line>
+   <line>124</line>
   </file>
  </directive>
- <directive id="FilterParam.ExtractStyleBlocksScope">
+ <directive id="Filter.ExtractStyleBlocks.TidyImpl">
   <file name="HTMLPurifier/Filter/ExtractStyleBlocks.php">
-   <line>65</line>
+   <line>55</line>
   </file>
  </directive>
- <directive id="FilterParam.ExtractStyleBlocksEscaping">
+ <directive id="Filter.ExtractStyleBlocks.Scope">
   <file name="HTMLPurifier/Filter/ExtractStyleBlocks.php">
-   <line>123</line>
+   <line>79</line>
+  </file>
+ </directive>
+ <directive id="Filter.ExtractStyleBlocks.Escaping">
+  <file name="HTMLPurifier/Filter/ExtractStyleBlocks.php">
+   <line>277</line>
+  </file>
+ </directive>
+ <directive id="HTML.SafeIframe">
+  <file name="HTMLPurifier/HTMLModule/Iframe.php">
+   <line>17</line>
+  </file>
+  <file name="HTMLPurifier/URIFilter/SafeIframe.php">
+   <line>23</line>
   </file>
  </directive>
  <directive id="HTML.MaxImgLength">
@@ -351,11 +466,21 @@
    <line>50</line>
   </file>
  </directive>
- <directive id="AutoFormatParam.PurifierLinkifyDocURL">
+ <directive id="AutoFormat.PurifierLinkify.DocURL">
   <file name="HTMLPurifier/Injector/PurifierLinkify.php">
    <line>15</line>
   </file>
  </directive>
+ <directive id="AutoFormat.RemoveEmpty.RemoveNbsp">
+  <file name="HTMLPurifier/Injector/RemoveEmpty.php">
+   <line>15</line>
+  </file>
+ </directive>
+ <directive id="AutoFormat.RemoveEmpty.RemoveNbsp.Exceptions">
+  <file name="HTMLPurifier/Injector/RemoveEmpty.php">
+   <line>16</line>
+  </file>
+ </directive>
  <directive id="Core.AggressivelyFixLt">
   <file name="HTMLPurifier/Lexer/DOMLex.php">
    <line>44</line>
@@ -366,27 +491,42 @@
    <line>70</line>
   </file>
  </directive>
+ <directive id="Core.DisableExcludes">
+  <file name="HTMLPurifier/Strategy/FixNesting.php">
+   <line>57</line>
+  </file>
+ </directive>
  <directive id="Core.EscapeInvalidTags">
   <file name="HTMLPurifier/Strategy/MakeWellFormed.php">
-   <line>45</line>
+   <line>53</line>
   </file>
   <file name="HTMLPurifier/Strategy/RemoveForeignElements.php">
    <line>19</line>
   </file>
  </directive>
- <directive id="Core.RemoveScriptContents">
+ <directive id="HTML.AllowedComments">
+  <file name="HTMLPurifier/Strategy/RemoveForeignElements.php">
+   <line>24</line>
+  </file>
+ </directive>
+ <directive id="HTML.AllowedCommentsRegexp">
   <file name="HTMLPurifier/Strategy/RemoveForeignElements.php">
    <line>25</line>
   </file>
  </directive>
+ <directive id="Core.RemoveScriptContents">
+  <file name="HTMLPurifier/Strategy/RemoveForeignElements.php">
+   <line>28</line>
+  </file>
+ </directive>
  <directive id="Core.HiddenElements">
   <file name="HTMLPurifier/Strategy/RemoveForeignElements.php">
-   <line>26</line>
+   <line>29</line>
   </file>
  </directive>
  <directive id="URI.HostBlacklist">
   <file name="HTMLPurifier/URIFilter/HostBlacklist.php">
-   <line>8</line>
+   <line>12</line>
   </file>
  </directive>
  <directive id="URI.MungeResources">
@@ -399,4 +539,9 @@
    <line>15</line>
   </file>
  </directive>
+ <directive id="URI.SafeIframeRegexp">
+  <file name="HTMLPurifier/URIFilter/SafeIframe.php">
+   <line>18</line>
+  </file>
+ </directive>
 </usage>

docs/dev-advanced-api.html

@@ -17,200 +17,10 @@
 <div id="home"><a href="http://htmlpurifier.org/">HTML Purifier</a> End-User Documentation</div>
 
 <p>
-  <strong>Warning:</strong> This document may be out-of-date. When in doubt,
-  consult the source code documentation.
+  Please see <a href="enduser-customize.html">Customize!</a>
 </p>
 
-<p>HTML Purifier currently natively supports only a subset of HTML's
-allowed elements, attributes, and behavior; specifically, this subset
-is the set of elements that are safe for untrusted users to use.
-However, HTML Purifier is often utilized to ensure standards-compliance
-from input that is trusted (making it a sort of Tidy substitute),
-and often users need to define new elements or attributes. The
-advanced API is oriented specifically for these use-cases.</p>
-
-<p>Our goals are to let the user:</p>
-
-<dl>
-    <dt>Select</dt>
-    <dd><ul>
-        <li>Doctype</li>
-        <!-- <li>Filterset</li> -->
-        <li>Elements / Attributes / Modules</li>
-        <li>Tidy</li>
-    </ul></dd>
-    <dt>Customize</dt>
-    <dd><ul>
-        <li>Attributes</li>
-        <li>Elements</li>
-        <!--<li>Doctypes</li>-->
-    </ul></dd>
-</dl>
-
-<h2>Select</h2>
-
-<p>For basic use, the user will have to specify some basic parameters. This
-is not strictly necessary, as HTML Purifier's default setting will always
-output safe code, but is required for standards-compliant output.</p>
-
-<h3>Selecting a Doctype</h3>
-
-<p>The first thing to select is the <strong>doctype</strong>. This
-is essential for standards-compliant output.</p>
-
-<p class="technical">This identifier is based
-on the name the W3C has given to the document type and <em>not</em>
-the DTD identifier.</p>
-
-<p>This parameter is set via the configuration object:</p>
-
-<pre>$config->set('HTML', 'Doctype', 'XHTML 1.0 Transitional');</pre>
-
-<p>Due to historical reasons, the default doctype is XHTML 1.0
-Transitional, however, we really shouldn't be guessing what the user's
-doctype is. Fortunantely, people who can't be bothered to set this won't
-be bothered when their pages stop validating.</p>
-
-<h3>Selecting Elements / Attributes / Modules</h3>
-
-<p>HTML Purifier will, by default, allow as many elements and attributes
-as possible. However, a user may decide to roll their own filterset by
-selecting modules, elements and attributes to allow for their own
-specific use-case. This can be done using %HTML.Allowed:</p>
-
-<pre>$config->set('HTML', 'Allowed', 'a[href|title],em,p,blockquote');</pre>
-
-<p class="technical">The directive %HTML.Allowed is a convenience feature
-that may be fully expressed with the legacy interface.</p>
-
-<p>We currently support another interface from older versions:</p>
-
-<pre>$config->set('HTML', 'AllowedElements', 'a,em,p,blockquote');
-$config->set('HTML', 'AllowedAttributes', 'a.href,a.title');</pre>
-
-<p>A user may also choose to allow modules using a specialized
-directive:</p>
-
-<pre>$config->set('HTML', 'AllowedModules', 'Hypertext,Text,Lists');</pre>
-
-<p>But it is not expected that this feature will be widely used.</p>
-
-<p class="technical">Module selection will work slightly differently
-from the other AllowedElements and AllowedAttributes directives by
-directly modifying the doctype you are operating in, in the spirit of
-XHTML 1.1's modularization. We stop users from shooting themselves in the
-foot by mandating the modules in %HTML.CoreModules be used.</p>
-
-<p class="technical">Modules are distinguished from regular elements by the
-case of their first letter. While XML distinguishes between and allows
-lower and uppercase letters in element names, XHTML uses only lower-case
-element names for sake of consistency.</p>
-
-<h3>Selecting Tidy</h3>
-
-<p>The name of this segment of functionality is inspired off of Dave
-Ragget's program HTML Tidy, which purported to help clean up HTML. In
-HTML Purifier, Tidy functionality involves turning unsupported and
-deprecated elements into standards-compliant ones, maintaining
-backwards compatibility, and enforcing best practices.</p>
-
-<p>This is a complicated feature, and is explained more in depth at
-<a href="enduser-tidy.html">the Tidy documentation page</a>.</p>
-
-<!--
-<h3>Unified selector</h3>
-
-<p>Because selecting each and every one of these configuration options
-is a chore, we may wish to offer a specialized configuration method
-for selecting a filterset. Possibility:</p>
-
-<pre>function selectFilter($doctype, $filterset, $tidy)</pre>
-
-<p>...which is simply a light wrapper over the individual configuration
-calls. A custom config file format or text format could also be adopted.</p>
--->
-
-<h2>Customize</h2>
-
-<p>By reviewing topic posts in the support forum, we determined that
-there were two primarily demanded customization features people wanted:
-to add an attribute to an existing element, and to add an element.
-Thus, we'll want to create convenience functions for these common
-use-cases.</p>
-
-<p>Note that the functions described here are only available if
-a raw copy of <code>HTMLPurifier_HTMLDefinition</code> was retrieved.
-Furthermore, caching may prevent your changes from immediately
-being seen: consult <a href="enduser-customize.html">enduser-customize.html</a> on how
-to work around this.</p>
-
-<h3>Attributes</h3>
-
-<p>An attribute is bound to an element by a name and has a specific
-<code>AttrDef</code> that validates it. The interface is therefore:</p>
-
-<pre>function addAttribute($element, $attribute, $attribute_def);</pre>
-
-<p>Example of the functionality in action:</p>
-
-<pre>$def->addAttribute('a', 'rel', 'Enum#nofollow');</pre>
-
-<p>The <code>$attribute_def</code> value is flexible,
-to make things simpler. It can be a literal object or:</p>
-
-<ul>
-    <!--<li>Class name: We'll instantiate it for you</li>
-    <li>Function name: We'll create an <code>HTMLPurifier_AttrDef_Anonymous</code>
-        class with that function registered as a callback.</li>-->
-    <li>String attribute type: We'll use <code>HTMLPurifier_AttrTypes</code>
-        to resolve it for you. Any data that follows a hash mark (#) will
-        be used to customize the attribute type: in the example above, 
-        we specify which values for Enum to allow.</li>
-</ul>
-
-<h3>Elements</h3>
-
-<p>An element requires certain information as specified by
-<code>HTMLPurifier_ElementDef</code>. However, not all of it is necessary,
-the usual things required are:</p>
-
-<ul>
-    <li>Attributes</li>
-    <li>Content model/type</li>
-    <li>Registration in a content set</li>
-</ul>
-
-<p>This suggests an API like this:</p>
-
-<pre>function addElement($element, $type, $contents,
-    $attr_collections = array(); $attributes = array());</pre>
-
-<p>Each parameter explained in depth:</p>
-
-<dl>
-    <dt><code>$element</code></dt>
-    <dd>Element name, ex. 'label'</dd>
-    <dt><code>$type</code></dt>
-    <dd>Content set to register in, ex. 'Inline' or 'Flow'</dd>
-    <dt><code>$contents</code></dt>
-    <dd>Description of allowed children. This is a merged form of
-        <code>HTMLPurifier_ElementDef</code>'s member variables
-        <code>$content_model</code> and <code>$content_model_type</code>,
-        where the form is <q>Type: Model</q>, ex. 'Optional: Inline'.
-        There are also a number of predefined templates one may use.</dd>
-    <dt><code>$attr_collections</code></dt>
-    <dd>Array (or string if only one) of attribute collection(s) to
-        merge into the attributes array.</dd>
-    <dt><code>$attributes</code></dt>
-    <dd>Array of attribute names to attribute definitions, much like
-        the above-described attribute customization.</dd>
-</dl>
-
-<p>A possible usage:</p>
-
-<pre>$def->addElement('font', 'Inline', 'Optional: Inline', 'Common',
-    array('color' => 'Color'));</pre>
-
-<p>See <code>HTMLPurifier/HTMLModule.php</code> for details.</p>
-
 </body></html>
+
+<!-- vim: et sw=4 sts=4
+-->

docs/dev-code-quality.txt

@@ -25,3 +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-bcbreaks.txt

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

docs/dev-config-naming.txt

@@ -0,0 +1,164 @@
+Configuration naming
+
+HTML Purifier 4.0.0 features a new configuration naming system that
+allows arbitrary nesting of namespaces.  While there are certain cases
+in which using two namespaces is obviously better (the canonical example
+is where we were using AutoFormatParam to contain directives for AutoFormat
+parameters), it is unclear whether or not a general migration to highly
+namespaced directives is a good idea or not.
+
+== Case studies ==
+
+=== Attr.* ===
+
+We have a dead duck HTML.Attr.Name.UseCDATA which migrated before we decided
+to think this out thoroughly.
+
+We currently have a large number of directives in the Attr.* namespace.
+These directives tweak the behavior of some HTML attributes.  They have
+the properties:
+
+* While they apply to only one attribute at a time, the attribute can
+  span over multiple elements (not necessarily all attributes, either).
+  The information of which elements it impacts is either omitted or
+  informally stated (EnableID applies to all elements, DefaultImageAlt
+  applies to <img> tags, AllowedRev doesn't say but only applies to a tags).
+
+* There is a certain degree of clustering that could be applied, especially
+  to the ID directives.  The clustering could be done with respect to
+  what element/attribute was used, i.e.
+
+    *.id -> EnableID, IDBlacklistRegexp, IDBlacklist, IDPrefixLocal, IDPrefix
+    img.src -> DefaultInvalidImage
+    img.alt -> DefaultImageAlt, DefaultInvalidImageAlt
+    bdo.dir -> DefaultTextDir
+    a.rel -> AllowedRel
+    a.rev -> AllowedRev
+    a.target -> AllowedFrameTargets
+    a.name -> Name.UseCDATA
+
+* The directives often reference generic attribute types that were specified
+  in the DTD/specification.  However, some of the behavior specifically relies
+  on the fact that other use cases of the attribute are not, at current,
+  supported by HTML Purifier.
+
+    AllowedRel, AllowedRev -> heavily <a> specific; if <link> ends up being
+        allowed, we will also have to give users specificity there (we also
+        want to preserve generality) DTD %Linktypes, HTML5 distinguishes
+        between <link> and <a>/<area>
+    AllowedFrameTargets -> heavily <a> specific, but also used by <area>
+        and <form>. Transitional DTD %FrameTarget, not present in strict,
+        HTML5 calls them "browsing contexts"
+    Default*Image* -> as a default parameter, is almost entirely exlcusive
+        to <img>
+    EnableID -> global attribute
+    Name.UseCDATA -> heavily <a> specific, but has heavy other usage by
+        many things
+
+== AutoFormat.* ==
+
+These have the fairly normal pluggable architecture that lends itself to
+large amounts of namespaces (pluggability may be the key to figuring
+out when gratuitous namespacing is good.)  Properties:
+
+* Boolean directives are fair game for being namespaced: for example,
+  RemoveEmpty.RemoveNbsp triggers RemoveEmpty.RemoveNbsp.Exceptions,
+  the latter of which only makes sense when RemoveEmpty.RemoveNbsp
+  is set to true. (The same applies to RemoveNbsp too)
+
+The AutoFormat string is a bit long, but is the only bit of repeated
+context.
+
+== Core.* ==
+
+Core is the potpourri of directives, mostly regarding some minor behavioral
+tweaks for HTML handling abilities.
+
+    AggressivelyFixLt
+    ConvertDocumentToFragment
+    DirectLexLineNumberSyncInterval
+    LexerImpl
+    MaintainLineNumbers
+        Lexer
+    CollectErrors
+    Language
+        Error handling (Language is ostensibly a little more general, but
+        it's only used for error handling right now)
+    ColorKeywords
+        CSS and HTML
+    Encoding
+    EscapeNonASCIICharacters
+        Character encoding
+    EscapeInvalidChildren
+    EscapeInvalidTags
+    HiddenElements
+    RemoveInvalidImg
+        Lexing/Output
+    RemoveScriptContents
+        Deprecated
+
+== HTML.* ==
+
+    AllowedAttributes
+    AllowedElements
+    AllowedModules
+    Allowed
+    ForbiddenAttributes
+    ForbiddenElements
+        Element set tuning
+    BlockWrapper
+        Child def advanced twiddle
+    CoreModules
+    CustomDoctype
+        Advanced HTMLModuleManager twiddles
+    DefinitionID
+    DefinitionRev
+        Caching
+    Doctype
+    Parent
+    Strict
+    XHTML
+        Global environment
+    MaxImgLength
+        Attribute twiddle? (applies to two attributes)
+    Proprietary
+    SafeEmbed
+    SafeObject
+    Trusted
+        Extra functionality/tagsets
+    TidyAdd
+    TidyLevel
+    TidyRemove
+        Tidy
+
+== Output.* ==
+
+These directly affect the output of Generator. These are all advanced
+twiddles.
+
+== URI.* ==
+
+    AllowedSchemes
+    OverrideAllowedSchemes
+        Scheme tuning
+    Base
+    DefaultScheme
+    Host
+        Global environment
+    DefinitionID
+    DefinitionRev
+        Caching
+    DisableExternalResources
+    DisableExternal
+    DisableResources
+    Disable
+        Contextual/authority tuning
+    HostBlacklist
+        Authority tuning
+    MakeAbsolute
+    MungeResources
+    MungeSecretKey
+    Munge
+        Transformation behavior (munge can be grouped)
+
+

docs/dev-config-schema.html

@@ -9,29 +9,29 @@
     <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>
@@ -42,7 +42,7 @@
       <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
@@ -54,11 +54,11 @@ 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>
@@ -114,7 +114,7 @@ Test.Example</pre>
         </tr>
         <tr>
           <td>VALUE-ALIASES</td>
-          <td>'baz' => 'bar'</td>
+          <td>'baz' =&gt; 'bar'</td>
           <td><em>Optional</em>. Mapping of one value to another, and
           should be a comma separated list of keypair duples. This
           is only allowed string, istring, text and itext TYPEs.</td>
@@ -143,11 +143,11 @@ Test.Example</pre>
         </tr>
       </tbody>
     </table>
-    
+
     <p>
       Some notes on format and style:
     </p>
-    
+
     <ul>
       <li>
         Each of these keys can be expressed in the short format
@@ -162,11 +162,11 @@ Test.Example</pre>
         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>
@@ -213,7 +213,7 @@ Test.Example</pre>
         </tr>
         <tr>
           <td>lookup</td>
-          <td>array('key' => true)</td>
+          <td>array('key' =&gt; true)</td>
           <td>Lookup array, used with <code>isset($var[$key])</code></td>
         </tr>
         <tr>
@@ -223,7 +223,7 @@ Test.Example</pre>
         </tr>
         <tr>
           <td>hash</td>
-          <td>array('key' => 'val')</td>
+          <td>array('key' =&gt; 'val')</td>
           <td>Associative array of keys to values</td>
         </tr>
         <tr>
@@ -233,7 +233,7 @@ Test.Example</pre>
         </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
@@ -242,7 +242,7 @@ Test.Example</pre>
       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">
@@ -251,9 +251,9 @@ Test.Example</pre>
       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
@@ -262,14 +262,49 @@ Test.Example</pre>
       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>Adding in-house schema definitions</h2>
+
+    <p>
+      Placing stuff directly in HTML Purifier's source tree is generally not a
+      good idea, so HTML Purifier 4.0.0+ has some facilities in place to make your
+      life easier.
+    </p>
+
+    <p>
+      The first is to pass an extra parameter to <code>maintenance/generate-schema-cache.php</code>
+      with the location of your directory (relative or absolute path will do). For example,
+      if I'm storing my custom definitions in <em>/var/htmlpurifier/myschema</em>, run:
+      <code>php maintenance/generate-schema-cache.php /var/htmlpurifier/myschema</code>.
+    </p>
+
+    <p>
+      Alternatively, you can create a small loader PHP file in the HTML Purifier base
+      directory named <code>config-schema.php</code> (this is the same directory
+      you would place a <code>test-settings.php</code> file).  In this file, add
+      the following line for each directory you want to load:
+    </p>
+
+<pre>$builder-&gt;buildDir($interchange, '/var/htmlpurifier/myschema');</pre>
+
+    <p>You can even load a single file using:</p>
+
+<pre>$builder-&gt;buildFile($interchange, '/var/htmlpurifier/myschema/MyApp.Directive.txt');</pre>
+
+    <p>Storing custom definitions that you don't plan on sending back upstream in
+    a separate directory is <em>definitely</em> a good idea! Additionally, picking
+    a good namespace can go a long way to saving you grief if you want to use
+    someone else's change, but they picked the same name, or if HTML Purifier
+    decides to add support for a configuration directive that has the same name.</p>
+
+    <!-- TODO: how to name directives that rely on naming conventions -->
+
     <h2>Errors</h2>
-    
+
     <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">
@@ -279,16 +314,16 @@ Test.Example</pre>
       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
@@ -298,28 +333,28 @@ Test.Example</pre>
       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>
@@ -329,12 +364,12 @@ Test.Example</pre>
       <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
@@ -342,9 +377,9 @@ Test.Example</pre>
       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
@@ -352,7 +387,7 @@ Test.Example</pre>
       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>
@@ -360,7 +395,7 @@ Test.Example</pre>
       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.
@@ -372,3 +407,6 @@ Test.Example</pre>
 
   </body>
 </html>
+
+<!-- vim: et sw=4 sts=4
+-->

docs/dev-flush.html

@@ -63,3 +63,6 @@
 </p>
 
 </body></html>
+
+<!-- vim: et sw=4 sts=4
+-->

docs/dev-includes.txt

@@ -91,14 +91,14 @@ use the stub for all cases (which might not be a bad idea).
     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 
+    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.
@@ -193,7 +193,7 @@ configuration directives would be used to generate our key (meta-directives!)
     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
@@ -277,3 +277,5 @@ 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>
@@ -78,3 +78,6 @@ help you find the correct functionality more quickly.  Here they are:</p>
 </dl>
 
 </body></html>
+
+<!-- vim: et sw=4 sts=4
+-->

docs/dev-optimization.html

@@ -28,3 +28,6 @@ that itch, put it here!</p>
 </ul>
 
 </body></html>
+
+<!-- vim: et sw=4 sts=4
+-->

docs/dev-progress.html

@@ -255,7 +255,7 @@ Mozilla on inside and needs -moz-outline, no IE support.</td></tr>
 <tr class="feature"><td>axis</td><td>TD, TH</td><td>W3C only: No browser implementation</td></tr>
 <tr class="feature"><td>char</td><td>COL, COLGROUP, TBODY, TD, TFOOT, TH, THEAD, TR</td><td>W3C only: No browser implementation</td></tr>
 <tr class="feature"><td>headers</td><td>TD, TH</td><td>W3C only: No browser implementation</td></tr>
-<tr class="feature"><td>scope</td><td>TD, TH</td><td>W3C only: No browser implementation</td></tr>
+<tr class="impl-yes"><td>scope</td><td>TD, TH</td><td>W3C only: No browser implementation</td></tr>
 </tbody>
 
 <tbody class="impl-yes">
@@ -304,3 +304,6 @@ Mozilla on inside and needs -moz-outline, no IE support.</td></tr>
 </table>
 
 </body></html>
+
+<!-- vim: et sw=4 sts=4
+-->

docs/enduser-customize.html

@@ -18,12 +18,11 @@
 <div id="home"><a href="http://htmlpurifier.org/">HTML Purifier</a> End-User Documentation</div>
 
 <p>
-  You may have heard of the <a href="dev-advanced-api.html">Advanced API</a>.
-  If you're interested in reading dry prose and boring functional
-  specifications, feel free to click that link to get a no-nonsense overview
-  on the Advanced API. For the rest of us, there's this tutorial. By the time
-  you're finished reading this, you should have a pretty good idea on
-  how to implement custom tags and attributes that HTML Purifier may not have.
+  HTML Purifier has this quirk where if you try to allow certain elements or
+  attributes, HTML Purifier will tell you that it's not supported, and that
+  you should go to the forums to find out how to implement it. Well, this
+  document is how to implement elements and attributes which HTML Purifier
+  doesn't support out of the box.
 </p>
 
 <h2>Is it necessary?</h2>
@@ -84,17 +83,6 @@
   limited to translations) above or below other corresponding text.
 </p>
 
-<h3>XHTML 2.0</h3>
-
-<p>
-  <a href="http://www.w3.org/TR/xhtml2/">XHTML 2.0</a> is still a
-  working draft, so any elements introduced in the
-  specification have not been implemented and will not be implemented
-  until we get a recommendation or proposal.  Because XHTML 2.0 is
-  an entirely new markup language, implementing rules for it will be
-  no easy task.
-</p>
-
 <h3>HTML 5</h3>
 
 <p>
@@ -156,9 +144,11 @@
 </p>
 
 <pre>$config = HTMLPurifier_Config::createDefault();
-$config->set('HTML', 'DefinitionID', 'enduser-customize.html tutorial');
-$config->set('HTML', 'DefinitionRev', 1);
-$def = $config->getHTMLDefinition(true);</pre>
+$config-&gt;set('HTML.DefinitionID', 'enduser-customize.html tutorial');
+$config-&gt;set('HTML.DefinitionRev', 1);
+if ($def = $config-&gt;maybeGetRawHTMLDefinition()) {
+    // our code will go here
+}</pre>
 
 <p>
   Assuming that HTML Purifier has already been properly loaded (hint:
@@ -186,35 +176,27 @@ $def = $config->getHTMLDefinition(true);</pre>
   </li>
   <li>
     The fourth line retrieves a raw <code>HTMLPurifier_HTMLDefinition</code>
-    object that we will be tweaking. If the parameter was removed, we
-    would be retrieving a fully formed definition object, which is somewhat
-    useless for customization purposes.
+    object that we will be tweaking.  Interestingly enough, we have
+    placed it in an if block: this is because
+    <code>maybeGetRawHTMLDefinition</code>, as its name suggests, may
+    return a NULL, in which case we should skip doing any
+    initialization.  This, in fact, will correspond to when our fully
+    customized object is already in the cache.
   </li>
 </ul>
 
-<h3>Broken backwards-compatibility</h3>
-
-<p>
-  Those of you who have already been twiddling around with the raw
-  HTML definition object, you'll be noticing that you're getting an error
-  when you attempt to retrieve the raw definition object without specifying
-  a DefinitionID.  It is vital to caching (see below) that you make a unique
-  name for your customized definition, so make up something right now and
-  things will operate again.
-</p>
-
 <h2>Turn off caching</h2>
 
 <p>
-  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('Cache', 'DefinitionImpl', null); // remove this later!</strong>
-$def = $config->getHTMLDefinition(true);</pre>
+$config-&gt;set('HTML.DefinitionID', 'enduser-customize.html tutorial');
+$config-&gt;set('HTML.DefinitionRev', 1);
+<strong>$config-&gt;set('Cache.DefinitionImpl', null); // TODO: remove this later!</strong>
+$def = $config-&gt;getHTMLDefinition(true);</pre>
 
 <p>
   A few things should be mentioned about the caching mechanism before
@@ -267,10 +249,10 @@ $def = $config->getHTMLDefinition(true);</pre>
 </p>
 
 <pre>$config = HTMLPurifier_Config::createDefault();
-$config->set('HTML', 'DefinitionID', 'enduser-customize.html tutorial');
-$config->set('HTML', 'DefinitionRev', 1);
-$config->set('Cache', 'DefinitionImpl', null); // remove this later!
-$def = $config->getHTMLDefinition(true);
+$config-&gt;set('HTML.DefinitionID', 'enduser-customize.html tutorial');
+$config-&gt;set('HTML.DefinitionRev', 1);
+$config-&gt;set('Cache.DefinitionImpl', null); // remove this later!
+$def = $config-&gt;getHTMLDefinition(true);
 <strong>$def->addAttribute('a', 'target', 'Enum#_blank,_self,_target,_top');</strong></pre>
 
 <p>
@@ -385,11 +367,11 @@ $def = $config->getHTMLDefinition(true);
 </p>
 
 <pre>$config = HTMLPurifier_Config::createDefault();
-$config->set('HTML', 'DefinitionID', 'enduser-customize.html tutorial');
-$config->set('HTML', 'DefinitionRev', 1);
-$config->set('Cache', 'DefinitionImpl', null); // remove this later!
-$def = $config->getHTMLDefinition(true);
-<strong>$def->addAttribute('a', 'target', new HTMLPurifier_AttrDef_Enum(
+$config-&gt;set('HTML.DefinitionID', 'enduser-customize.html tutorial');
+$config-&gt;set('HTML.DefinitionRev', 1);
+$config-&gt;set('Cache.DefinitionImpl', null); // remove this later!
+$def = $config-&gt;getHTMLDefinition(true);
+<strong>$def-&gt;addAttribute('a', 'target', new HTMLPurifier_AttrDef_Enum(
   array('_blank','_self','_target','_top')
 ));</strong></pre>
 
@@ -401,8 +383,8 @@ $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 +475,9 @@ $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 +578,7 @@ $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 +658,7 @@ $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>
 
@@ -724,7 +706,7 @@ $def = $config->getHTMLDefinition(true);
     or more flow elements, but no nested <code>form</code>s</strong></li>
   <li>What attributes does the element allow that are general? <strong>Common</strong></li>
   <li>What attributes does the element allow that are specific to this element? <strong>A whole bunch, see ATTLIST;
-    we're going to the vital ones: <code>action</code>, <code>method</code> and <code>name</code></strong></li>
+    we're going to do the vital ones: <code>action</code>, <code>method</code> and <code>name</code></strong></li>
 </ol>
 
 <p>
@@ -732,14 +714,14 @@ $def = $config->getHTMLDefinition(true);
 </p>
 
 <pre>$config = HTMLPurifier_Config::createDefault();
-$config->set('HTML', 'DefinitionID', 'enduser-customize.html tutorial');
-$config->set('HTML', 'DefinitionRev', 1);
-$config->set('Cache', 'DefinitionImpl', null); // remove this later!
-$def = $config->getHTMLDefinition(true);
-$def->addAttribute('a', 'target', new HTMLPurifier_AttrDef_Enum(
+$config-&gt;set('HTML.DefinitionID', 'enduser-customize.html tutorial');
+$config-&gt;set('HTML.DefinitionRev', 1);
+$config-&gt;set('Cache.DefinitionImpl', null); // remove this later!
+$def = $config-&gt;getHTMLDefinition(true);
+$def-&gt;addAttribute('a', 'target', new HTMLPurifier_AttrDef_Enum(
   array('_blank','_self','_target','_top')
 ));
-<strong>$form = $def->addElement(
+<strong>$form = $def-&gt;addElement(
   'form',   // name
   'Block',  // content set
   'Flow', // allowed children
@@ -750,7 +732,7 @@ $def->addAttribute('a', 'target', new HTMLPurifier_AttrDef_Enum(
     'name' => 'ID'
   )
 );
-$form->excludes = array('form' => true);</strong></pre>
+$form-&gt;excludes = array('form' => true);</strong></pre>
 
 <p>
   Each of the parameters corresponds to one of the questions we asked.
@@ -793,4 +775,76 @@ $form->excludes = array('form' => true);</strong></pre>
   <li><a href="http://repo.or.cz/w/htmlpurifier.git?a=blob;hb=HEAD;f=library/HTMLPurifier/ElementDef.php"><code>library/HTMLPurifier/ElementDef.php</code></a></li>
 </ul>
 
+<h2 id="optimized">Notes for HTML Purifier 4.2.0 and earlier</h3>
+
+<p>
+    Previously, this tutorial gave some incorrect template code for
+    editing raw definitions, and that template code will now produce the
+    error <q>Due to a documentation error in previous version of HTML
+    Purifier...</q>  Here is how to mechanically transform old-style
+    code into new-style code.
+</p>
+
+<p>
+    First, identify all code that edits the raw definition object, and
+    put it together.  Ensure none of this code must be run on every
+    request; if some sub-part needs to always be run, move it outside
+    this block.  Here is an example below, with the raw definition
+    object code bolded.
+</p>
+
+<pre>$config = HTMLPurifier_Config::createDefault();
+$config-&gt;set('HTML.DefinitionID', 'enduser-customize.html tutorial');
+$config-&gt;set('HTML.DefinitionRev', 1);
+$def = $config-&gt;getHTMLDefinition(true);
+<strong>$def->addAttribute('a', 'target', 'Enum#_blank,_self,_target,_top');</strong>
+$purifier = new HTMLPurifier($config);</pre>
+
+<p>
+    Next, replace the raw definition retrieval with a
+    maybeGetRawHTMLDefinition method call inside an if conditional, and
+    place the editing code inside that if block.
+</p>
+
+<pre>$config = HTMLPurifier_Config::createDefault();
+$config-&gt;set('HTML.DefinitionID', 'enduser-customize.html tutorial');
+$config-&gt;set('HTML.DefinitionRev', 1);
+<strong>if ($def = $config-&gt;maybeGetRawHTMLDefinition()) {
+    $def->addAttribute('a', 'target', 'Enum#_blank,_self,_target,_top');
+}</strong>
+$purifier = new HTMLPurifier($config);</pre>
+
+<p>
+    And you're done!  Alternatively, if you're OK with not ever caching
+    your code, the following will still work and not emit warnings.
+</p>
+
+<pre>$config = HTMLPurifier_Config::createDefault();
+$def = $config-&gt;getHTMLDefinition(true);
+$def->addAttribute('a', 'target', 'Enum#_blank,_self,_target,_top');
+$purifier = new HTMLPurifier($config);</pre>
+
+<p>
+    A slightly less efficient version of this was what was going on with
+    old versions of HTML Purifier.
+</p>
+
+<p>
+    <em>Technical notes:</em> ajh pointed out on <a
+        href="http://htmlpurifier.org/phorum/read.php?5,5164,5169#msg-5169">in a forum topic</a> that
+    HTML Purifier appeared to be repeatedly writing to the cache even
+    when a cache entry already existed.  Investigation lead to the
+    discovery of the following infelicity: caching of customized
+    definitions didn't actually work!  The problem was that even though
+    a cache file would be written out at the end of the process, there
+    was no way for HTML Purifier to say, <q>Actually, I've already got a
+        copy of your work, no need to reconfigure your
+        customizations</q>.  This required the API to change: placing
+    all of the customizations to the raw definition object in a
+    conditional which could be skipped.
+</p>
+
 </body></html>
+
+<!-- vim: et sw=4 sts=4
+-->

docs/enduser-id.html

@@ -31,7 +31,7 @@ by default.</p>
 
 <p>IDs, however, are quite useful functionality to have, so if users start
 complaining about broken anchors you'll probably want to turn them back on
-with %HTML.EnableAttrID. But before you go mucking around with the config
+with %Attr.EnableID. But before you go mucking around with the config
 object, it's probably worth to take some precautions to keep your page
 validating. Why?</p>
 
@@ -56,8 +56,8 @@ validating. Why?</p>
 deal with the most obvious solution: preventing users from using any IDs that
 appear elsewhere on the document.  The method is simple:</p>
 
-<pre>$config->set('HTML', 'EnableAttrID', true);
-$config->set('Attr', 'IDBlacklist' array(
+<pre>$config-&gt;set('Attr.EnableID', true);
+$config-&gt;set('Attr.IDBlacklist' array(
     'list', 'of', 'attribute', 'values', 'that', 'are', 'forbidden'
 ));</pre>
 
@@ -88,8 +88,8 @@ all, they might have simply specified a duplicate ID by accident.</p>
 <p>This method, too, is quite simple: add a prefix to all user IDs. With this
 code:</p>
 
-<pre>$config->set('HTML', 'EnableAttrID', true);
-$config->set('Attr', 'IDPrefix', 'user_');</pre>
+<pre>$config-&gt;set('Attr.EnableID', true);
+$config-&gt;set('Attr.IDPrefix', 'user_');</pre>
 
 <p>...this:</p>
 
@@ -109,7 +109,7 @@ user_ to the beginning.&quot;</p>
 nothing about multiple HTML Purifier outputs on one page.  Thus, we have
 a second configuration value to piggy-back off of: %Attr.IDPrefixLocal:</p>
 
-<pre>$config->set('Attr', 'IDPrefixLocal', 'comment' . $id . '_');</pre>
+<pre>$config-&gt;set('Attr.IDPrefixLocal', 'comment' . $id . '_');</pre>
 
 <p>This new attributes does nothing but append on to regular IDPrefix, but is
 special in that it is volatile: it's value is determined at run-time and
@@ -137,9 +137,12 @@ anchors is beyond me.</p>
 
 <p>To revert back to pre-1.2.0 behavior, simply:</p>
 
-<pre>$config->set('HTML', 'EnableAttrID', true);</pre>
+<pre>$config-&gt;set('Attr.EnableID', true);</pre>
 
 <p>Don't come crying to me when your page mysteriously stops validating, though.</p>
 
 </body>
 </html>
+
+<!-- vim: et sw=4 sts=4
+-->

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 +108,13 @@ 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>
@@ -76,7 +76,7 @@ associated with it, although it may change depending on your doctype.</p>
 change the level of cleaning by setting the %HTML.TidyLevel configuration
 directive:</p>
 
-<pre>$config->set('HTML', 'TidyLevel', 'heavy'); // burn baby burn!</pre>
+<pre>$config-&gt;set('HTML.TidyLevel', 'heavy'); // burn baby burn!</pre>
 
 <h2>Is the light level really light?</h2>
 
@@ -165,17 +165,17 @@ smoketest</a>.</p>
 so happy about the br@clear implementation. That's perfectly fine!
 HTML Purifier will make accomodations:</p>
 
-<pre>$config->set('HTML', 'Doctype', 'XHTML 1.0 Transitional');
-$config->set('HTML', 'TidyLevel', 'heavy'); // all changes, minus...
-<strong>$config->set('HTML', 'TidyRemove', 'br@clear');</strong></pre>
+<pre>$config-&gt;set('HTML.Doctype', 'XHTML 1.0 Transitional');
+$config-&gt;set('HTML.TidyLevel', 'heavy'); // all changes, minus...
+<strong>$config-&gt;set('HTML.TidyRemove', 'br@clear');</strong></pre>
 
 <p>That third line does the magic, removing the br@clear fix
 from the module, ensuring that <code>&lt;br clear="both" /&gt;</code>
 will pass through unharmed. The reverse is possible too:</p>
 
-<pre>$config->set('HTML', 'Doctype', 'XHTML 1.0 Transitional');
-$config->set('HTML', 'TidyLevel', 'none'); // no changes, plus...
-<strong>$config->set('HTML', 'TidyAdd', 'p@align');</strong></pre>
+<pre>$config-&gt;set('HTML.Doctype', 'XHTML 1.0 Transitional');
+$config-&gt;set('HTML.TidyLevel', 'none'); // no changes, plus...
+<strong>$config-&gt;set('HTML.TidyAdd', 'p@align');</strong></pre>
 
 <p>In this case, all transformations are shut off, except for the p@align
 one, which you found handy.</p>
@@ -226,3 +226,6 @@ Other than that, don't worry about it: this all works silently and
 effectively in the background.</p>
 
 </body></html>
+
+<!-- vim: et sw=4 sts=4
+-->

docs/enduser-uri-filter.html

@@ -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:
@@ -160,27 +160,14 @@
 </p>
 
 <pre>$uri = $config->getDefinition('URI');
-$uri->addFilter(new HTMLPurifier_URIFilter_<strong>NameOfFilter</strong>());</pre>
+$uri->addFilter(new HTMLPurifier_URIFilter_<strong>NameOfFilter</strong>(), $config);</pre>
 
 <p>
-  If you want to be really fancy, you can define a configuration directive
-  for your filter and have HTML Purifier automatically manage whether or
-  not your filter gets loaded or not (this is how internal filters manage
-  things):
+    After adding a filter, you won't be able to set configuration directives.
+    Structure your code accordingly.
 </p>
 
-<pre>HTMLPurifier_ConfigSchema::define(
-    'URI', '<strong>NameOfFilter</strong>', false, 'bool',
-    '<strong>What your filter does.</strong>'
-);
-$uri = $config->getDefinition('URI', true);
-$uri->registerFilter(new HTMLPurifier_URIFilter_<strong>NameOfFilter</strong>());
-</pre>
-
-<p>
-  Now, your filter will only be called when %URI.<strong>NameOfFilter</strong>
-  is set to true.
-</p>
+<!-- XXX: link to new documentation system -->
 
 <h2>Post-filter</h2>
 
@@ -212,3 +199,6 @@ $uri->registerFilter(new HTMLPurifier_URIFilter_<strong>NameOfFilter</strong>())
 </p>
 
 </body></html>
+
+<!-- vim: et sw=4 sts=4
+-->

docs/enduser-utf8.html

@@ -106,7 +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
@@ -306,7 +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>
@@ -366,9 +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
@@ -443,9 +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.
@@ -456,7 +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>
@@ -481,7 +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
@@ -489,7 +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>
 
@@ -526,7 +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
@@ -561,7 +561,7 @@ page on special characters</a> for more details.
 <h3 id="whyutf8-forms">Forms</h3>
 
 <p>While we're on the tack of users, how do non-UTF-8 web forms deal
-with characters that our outside of their character set? Rather than
+with characters that are outside of their character set? Rather than
 discuss what UTF-8 does right, we're going to show what could go wrong
 if you didn't use UTF-8 and people tried to use characters outside
 of your character encoding.</p>
@@ -578,13 +578,13 @@ 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
@@ -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 +1055,6 @@ a more in-depth look into character sets and encodings.</p>
 
 </body>
 </html>
+
+<!-- vim: et sw=4 sts=4
+-->

docs/enduser-youtube.html

@@ -67,7 +67,7 @@ into your documents. YouTube's code goes like this:</p>
 </ol>
 
 <p>What point 2 means is that if we have code like <code>&lt;span
-class=&quot;embed-youtube&quot;&gt;AyPzM5WK8ys&lt;/span&gt;</code> your
+class=&quot;youtube-embed&quot;&gt;AyPzM5WK8ys&lt;/span&gt;</code> your
 application can reconstruct the full object from this small snippet that
 passes through HTML Purifier <em>unharmed</em>.
 <a href="http://repo.or.cz/w/htmlpurifier.git?a=blob;hb=HEAD;f=library/HTMLPurifier/Filter/YouTube.php">Show me the code!</a></p>
@@ -75,7 +75,7 @@ passes through HTML Purifier <em>unharmed</em>.
 <p>And the corresponding usage:</p>
 
 <pre>&lt;?php
-    $config->set('Filter', 'YouTube', true);
+    $config-&gt;set('Filter.YouTube', true);
 ?&gt;</pre>
 
 <p>There is a bit going in the two code snippets, so let's explain.</p>
@@ -148,3 +148,6 @@ with the core!</p>
 
 </body>
 </html>
+
+<!-- vim: et sw=4 sts=4
+-->

docs/examples/basic.php

@@ -8,8 +8,8 @@ require_once '../../library/HTMLPurifier.auto.php';
 $config = HTMLPurifier_Config::createDefault();
 
 // configuration goes here:
-$config->set('Core', 'Encoding', 'UTF-8'); // replace with your encoding
-$config->set('HTML', 'Doctype', 'XHTML 1.0 Transitional'); // replace with your doctype
+$config->set('Core.Encoding', 'UTF-8'); // replace with your encoding
+$config->set('HTML.Doctype', 'XHTML 1.0 Transitional'); // replace with your doctype
 
 $purifier = new HTMLPurifier($config);
 
@@ -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 +4,6 @@ function init() {
   element.innerHTML = '“'+element.innerHTML+'”';
 }
 </script>
+
+<!-- vim: et sw=4 sts=4
+-->

docs/index.html

@@ -117,6 +117,12 @@ the code. They may be upgraded to HTML files or stay as TXT scratchpads.</p>
     <td>Common security issues that may still arise (half-baked).</td>
 </tr>
 
+<tr>
+    <td>Development</td>
+    <td><a href="dev-config-bcbreaks.txt">Config BC Breaks</a></td>
+    <td>Backwards-incompatible changes in HTML Purifier 4.0.0</td>
+</tr>
+
 <tr>
     <td>Development</td>
     <td><a href="dev-code-quality.txt">Code Quality Issues</a></td>
@@ -177,3 +183,6 @@ the code. They may be upgraded to HTML files or stay as TXT scratchpads.</p>
 
 </body>
 </html>
+
+<!-- vim: et sw=4 sts=4
+-->

docs/proposal-colors.html

@@ -44,3 +44,6 @@ something like that?</li>
 
 </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

@@ -30,3 +30,5 @@ 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

@@ -2,7 +2,7 @@ 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 
+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.
 
@@ -13,7 +13,7 @@ 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 
+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."
@@ -56,7 +56,7 @@ 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 
+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.
 
@@ -80,12 +80,12 @@ cases).
     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)
@@ -95,50 +95,50 @@ cases).
             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.
 
@@ -173,7 +173,7 @@ 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.
@@ -187,7 +187,7 @@ 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 
+  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
@@ -204,6 +204,8 @@ 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/proposal-plists.txt

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

docs/ref-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

@@ -42,3 +42,6 @@ the development of this library in these forum threads:</p>
 
 </body>
 </html>
+
+<!-- vim: et sw=4 sts=4
+-->

docs/ref-html-modularization.txt

@@ -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

@@ -6,3 +6,5 @@ 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 +162,4 @@ div.segment {width:250px; float:left; margin-top:1em;}
 </div>
 
 </body>
-</html>
+</html>

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

@@ -4,71 +4,71 @@
 <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>

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

@@ -5,17 +5,17 @@
  */
 class ConfigDoc_HTMLXSLTProcessor
 {
-    
+
     /**
      * 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
      */
@@ -27,7 +27,7 @@ class ConfigDoc_HTMLXSLTProcessor
         }
         return $this->xsltProcessor->importStylesheet($xsl);
     }
-    
+
     /**
      * Transforms an XML file into compatible XHTML based on the stylesheet
      * @param $xml XML DOM tree, or string filename
@@ -42,12 +42,12 @@ class ConfigDoc_HTMLXSLTProcessor
             $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
-        
+
         if (class_exists('Tidy')) {
             // cleanup output
             $config = array(
@@ -60,10 +60,10 @@ 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
@@ -73,13 +73,14 @@ class ConfigDoc_HTMLXSLTProcessor
             $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

@@ -3,15 +3,15 @@
 /**
  * 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 $singleton;
-    
+
     /**
      * Returns a global instance of FSTools
      */
@@ -19,7 +19,7 @@ class FSTools
         if (empty(FSTools::$singleton)) FSTools::$singleton = new FSTools();
         return FSTools::$singleton;
     }
-    
+
     /**
      * Sets our global singleton to something else; useful for overloading
      * functions.
@@ -27,7 +27,7 @@ class FSTools
     static public function setSingleton($singleton) {
         FSTools::$singleton = $singleton;
     }
-    
+
     /**
      * Recursively creates a directory
      * @param string $folder Name of folder to create
@@ -51,7 +51,7 @@ class FSTools
             $base .= DIRECTORY_SEPARATOR;
         }
     }
-    
+
     /**
      * Copy a file, or recursively copy a folder and its contents; modified
      * so that copied files, if PHP, have includes removed
@@ -85,17 +85,17 @@ class FSTools
         $dir->close();
         return true;
     }
-    
+
     /**
      * Overloadable function that tests a filename for copyability. By
      * default, everything should be copied; you can restrict things to
-     * ignore hidden files, unreadable files, etc. This function 
+     * ignore hidden files, unreadable files, etc. This function
      * applies to copyr().
      */
     public function copyable($file) {
         return true;
     }
-    
+
     /**
      * Delete a file, or a folder and its contents
      * @note Adapted from http://aidanlister.com/repos/v/function.rmdirr.php
@@ -106,12 +106,12 @@ class FSTools
         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()) {
@@ -122,12 +122,12 @@ class FSTools
             // Recurse
             $this->rmdirr($dirname . DIRECTORY_SEPARATOR . $entry);
         }
-     
+
         // Clean up
         $dir->close();
         return $this->rmdir($dirname);
     }
-    
+
     /**
      * Recursively globs a directory.
      */
@@ -140,9 +140,9 @@ class FSTools
             $sub_files = $this->globr($sub_dir, $pattern, $flags);
             $files = array_merge($files, $sub_files);
         }
-        return $files; 
+        return $files;
     }
-    
+
     /**
      * Allows for PHP functions to be called and be stubbed.
      * @warning This function will not work for functions that need
@@ -151,5 +151,7 @@ class FSTools
     public function __call($name, $args) {
         return call_user_func_array($name, $args);
     }
-    
+
 }
+
+// vim: et sw=4 sts=4

extras/FSTools/File.php

@@ -9,16 +9,16 @@
  */
 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
@@ -27,13 +27,13 @@ class FSTools_File
         $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
@@ -41,27 +41,27 @@ class FSTools_File
     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
@@ -70,14 +70,14 @@ class FSTools_File
     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;
@@ -85,40 +85,42 @@ class FSTools_File
         $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

@@ -7,3 +7,5 @@
 set_include_path(dirname(__FILE__) . PATH_SEPARATOR . get_include_path() );
 require_once 'HTMLPurifierExtras.php';
 require_once 'HTMLPurifierExtras.autoload.php';
+
+// vim: et sw=4 sts=4

extras/HTMLPurifierExtras.autoload.php

@@ -3,7 +3,7 @@
 /**
  * @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
@@ -21,3 +21,5 @@ if (function_exists('spl_autoload_register')) {
         return HTMLPurifierExtras::autoload($class);
     }
 }
+
+// vim: et sw=4 sts=4

extras/HTMLPurifierExtras.php

@@ -6,14 +6,14 @@
  */
 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 &&
@@ -23,5 +23,7 @@ class HTMLPurifierExtras
         // Standard implementation:
         return str_replace('_', '/', $class) . '.php';
     }
-    
+
 }
+
+// vim: et sw=4 sts=4

extras/README

@@ -24,7 +24,9 @@ the filesystem. It currently consists of two classes:
   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 
+- 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

@@ -7,3 +7,5 @@
 set_include_path(dirname(__FILE__) . PATH_SEPARATOR . get_include_path() );
 require_once 'HTMLPurifier/Bootstrap.php';
 require_once 'HTMLPurifier.autoload.php';
+
+// vim: et sw=4 sts=4

library/HTMLPurifier.autoload.php

@@ -3,6 +3,7 @@
 /**
  * @file
  * Convenience file that registers autoload handler for HTML Purifier.
+ * It also does some sanity checks.
  */
 
 if (function_exists('spl_autoload_register') && function_exists('spl_autoload_unregister')) {
@@ -17,3 +18,9 @@ if (function_exists('spl_autoload_register') && function_exists('spl_autoload_un
         return HTMLPurifier_Bootstrap::autoload($class);
     }
 }
+
+if (ini_get('zend.ze1_compatibility_mode')) {
+    trigger_error("HTML Purifier is not compatible with zend.ze1_compatibility_mode; please turn it off", E_USER_ERROR);
+}
+
+// vim: et sw=4 sts=4

library/HTMLPurifier.composer.php

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

library/HTMLPurifier.func.php

@@ -20,3 +20,4 @@ function HTMLPurifier($html, $config = null) {
     return $purifier->purify($html, $config);
 }
 
+// vim: et sw=4 sts=4

library/HTMLPurifier.includes.php

@@ -6,19 +6,21 @@
  * 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 3.2.0
- * 
+ *
+ * @version 4.5.0
+ *
  * @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/Array.php';
+require 'HTMLPurifier/ArrayNode.php';
 require 'HTMLPurifier/AttrCollections.php';
 require 'HTMLPurifier/AttrDef.php';
 require 'HTMLPurifier/AttrTransform.php';
@@ -36,6 +38,7 @@ require 'HTMLPurifier/DefinitionCache.php';
 require 'HTMLPurifier/DefinitionCacheFactory.php';
 require 'HTMLPurifier/Doctype.php';
 require 'HTMLPurifier/DoctypeRegistry.php';
+require 'HTMLPurifier/DoublyLinkedList.php';
 require 'HTMLPurifier/ElementDef.php';
 require 'HTMLPurifier/Encoder.php';
 require 'HTMLPurifier/EntityLookup.php';
@@ -55,6 +58,8 @@ 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';
@@ -71,6 +76,7 @@ require 'HTMLPurifier/UnitConverter.php';
 require 'HTMLPurifier/VarParser.php';
 require 'HTMLPurifier/VarParserException.php';
 require 'HTMLPurifier/AttrDef/CSS.php';
+require 'HTMLPurifier/AttrDef/Clone.php';
 require 'HTMLPurifier/AttrDef/Enum.php';
 require 'HTMLPurifier/AttrDef/Integer.php';
 require 'HTMLPurifier/AttrDef/Lang.php';
@@ -88,6 +94,7 @@ require 'HTMLPurifier/AttrDef/CSS/DenyElementDecorator.php';
 require 'HTMLPurifier/AttrDef/CSS/Filter.php';
 require 'HTMLPurifier/AttrDef/CSS/Font.php';
 require 'HTMLPurifier/AttrDef/CSS/FontFamily.php';
+require 'HTMLPurifier/AttrDef/CSS/Ident.php';
 require 'HTMLPurifier/AttrDef/CSS/ImportantDecorator.php';
 require 'HTMLPurifier/AttrDef/CSS/Length.php';
 require 'HTMLPurifier/AttrDef/CSS/ListStyle.php';
@@ -96,6 +103,8 @@ 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/Nmtokens.php';
+require 'HTMLPurifier/AttrDef/HTML/Class.php';
 require 'HTMLPurifier/AttrDef/HTML/Color.php';
 require 'HTMLPurifier/AttrDef/HTML/FrameTarget.php';
 require 'HTMLPurifier/AttrDef/HTML/ID.php';
@@ -103,7 +112,6 @@ 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';
@@ -121,14 +129,18 @@ require 'HTMLPurifier/AttrTransform/Input.php';
 require 'HTMLPurifier/AttrTransform/Lang.php';
 require 'HTMLPurifier/AttrTransform/Length.php';
 require 'HTMLPurifier/AttrTransform/Name.php';
+require 'HTMLPurifier/AttrTransform/NameSync.php';
+require 'HTMLPurifier/AttrTransform/Nofollow.php';
 require 'HTMLPurifier/AttrTransform/SafeEmbed.php';
 require 'HTMLPurifier/AttrTransform/SafeObject.php';
 require 'HTMLPurifier/AttrTransform/SafeParam.php';
 require 'HTMLPurifier/AttrTransform/ScriptRequired.php';
+require 'HTMLPurifier/AttrTransform/TargetBlank.php';
 require 'HTMLPurifier/AttrTransform/Textarea.php';
 require 'HTMLPurifier/ChildDef/Chameleon.php';
 require 'HTMLPurifier/ChildDef/Custom.php';
 require 'HTMLPurifier/ChildDef/Empty.php';
+require 'HTMLPurifier/ChildDef/List.php';
 require 'HTMLPurifier/ChildDef/Required.php';
 require 'HTMLPurifier/ChildDef/Optional.php';
 require 'HTMLPurifier/ChildDef/StrictBlockquote.php';
@@ -143,10 +155,12 @@ require 'HTMLPurifier/HTMLModule/CommonAttributes.php';
 require 'HTMLPurifier/HTMLModule/Edit.php';
 require 'HTMLPurifier/HTMLModule/Forms.php';
 require 'HTMLPurifier/HTMLModule/Hypertext.php';
+require 'HTMLPurifier/HTMLModule/Iframe.php';
 require 'HTMLPurifier/HTMLModule/Image.php';
 require 'HTMLPurifier/HTMLModule/Legacy.php';
 require 'HTMLPurifier/HTMLModule/List.php';
 require 'HTMLPurifier/HTMLModule/Name.php';
+require 'HTMLPurifier/HTMLModule/Nofollow.php';
 require 'HTMLPurifier/HTMLModule/NonXMLCommonAttributes.php';
 require 'HTMLPurifier/HTMLModule/Object.php';
 require 'HTMLPurifier/HTMLModule/Presentation.php';
@@ -154,10 +168,12 @@ require 'HTMLPurifier/HTMLModule/Proprietary.php';
 require 'HTMLPurifier/HTMLModule/Ruby.php';
 require 'HTMLPurifier/HTMLModule/SafeEmbed.php';
 require 'HTMLPurifier/HTMLModule/SafeObject.php';
+require 'HTMLPurifier/HTMLModule/SafeScripting.php';
 require 'HTMLPurifier/HTMLModule/Scripting.php';
 require 'HTMLPurifier/HTMLModule/StyleAttribute.php';
 require 'HTMLPurifier/HTMLModule/Tables.php';
 require 'HTMLPurifier/HTMLModule/Target.php';
+require 'HTMLPurifier/HTMLModule/TargetBlank.php';
 require 'HTMLPurifier/HTMLModule/Text.php';
 require 'HTMLPurifier/HTMLModule/Tidy.php';
 require 'HTMLPurifier/HTMLModule/XMLCommonAttributes.php';
@@ -172,6 +188,7 @@ require 'HTMLPurifier/Injector/DisplayLinkURI.php';
 require 'HTMLPurifier/Injector/Linkify.php';
 require 'HTMLPurifier/Injector/PurifierLinkify.php';
 require 'HTMLPurifier/Injector/RemoveEmpty.php';
+require 'HTMLPurifier/Injector/RemoveSpansWithoutAttributes.php';
 require 'HTMLPurifier/Injector/SafeObject.php';
 require 'HTMLPurifier/Lexer/DOMLex.php';
 require 'HTMLPurifier/Lexer/DirectLex.php';
@@ -191,9 +208,13 @@ require 'HTMLPurifier/Token/Start.php';
 require 'HTMLPurifier/Token/Text.php';
 require 'HTMLPurifier/URIFilter/DisableExternal.php';
 require 'HTMLPurifier/URIFilter/DisableExternalResources.php';
+require 'HTMLPurifier/URIFilter/DisableResources.php';
 require 'HTMLPurifier/URIFilter/HostBlacklist.php';
 require 'HTMLPurifier/URIFilter/MakeAbsolute.php';
 require 'HTMLPurifier/URIFilter/Munge.php';
+require 'HTMLPurifier/URIFilter/SafeIframe.php';
+require 'HTMLPurifier/URIScheme/data.php';
+require 'HTMLPurifier/URIScheme/file.php';
 require 'HTMLPurifier/URIScheme/ftp.php';
 require 'HTMLPurifier/URIScheme/http.php';
 require 'HTMLPurifier/URIScheme/https.php';

library/HTMLPurifier.kses.php

@@ -17,12 +17,14 @@ function kses($string, $allowed_html, $allowed_protocols = null) {
             $allowed_attributes["$element.$attribute"] = true;
         }
     }
-    $config->set('HTML', 'AllowedElements', $allowed_elements);
-    $config->set('HTML', 'AllowedAttributes', $allowed_attributes);
+    $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);
+        $config->set('URI.AllowedSchemes', $allowed_protocols);
     }
     $purifier = new HTMLPurifier($config);
     return $purifier->purify($string);
 }
+
+// vim: et sw=4 sts=4

library/HTMLPurifier.path.php

@@ -7,3 +7,5 @@
  */
 
 set_include_path(dirname(__FILE__) . PATH_SEPARATOR . get_include_path() );
+
+// vim: et sw=4 sts=4

library/HTMLPurifier.php

@@ -1,11 +1,11 @@
 <?php
 
 /*! @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,
@@ -13,13 +13,13 @@
  *      -# 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
  * and HTMLPurifier_Config.
  */
 
 /*
-    HTML Purifier 3.2.0 - Standards Compliant HTML Filtering
+    HTML Purifier 4.5.0 - Standards Compliant HTML Filtering
     Copyright (C) 2006-2008 Edward Z. Yang
 
     This library is free software; you can redistribute it and/or
@@ -39,44 +39,44 @@
 
 /**
  * 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 (this behavior may change in the future).
- * 
+ *
  * @todo We need an easier way to inject strategies using the configuration
  *       object.
  */
 class HTMLPurifier
 {
-    
+
     /** Version of HTML Purifier */
-    public $version = '3.2.0';
-    
+    public $version = '4.5.0';
+
     /** Constant with version of HTML Purifier */
-    const VERSION = '3.2.0';
-    
+    const VERSION = '4.5.0';
+
     /** 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 $context;
-    
+
     /**
      * Initializes the purifier.
      * @param $config Optional HTMLPurifier_Config object for all instances of
@@ -86,13 +86,13 @@ class HTMLPurifier
      *                HTMLPurifier_Config::create() supports.
      */
     public function __construct($config = null) {
-        
+
         $this->config = HTMLPurifier_Config::create($config);
-        
+
         $this->strategy     = new HTMLPurifier_Strategy_Core();
-        
+
     }
-    
+
     /**
      * Adds a filter to process the output. First come first serve
      * @param $filter HTMLPurifier_Filter object
@@ -101,10 +101,10 @@ class HTMLPurifier
         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 $config HTMLPurifier_Config object for this operation, if omitted,
      *                defaults to the config object specified during this
@@ -113,38 +113,38 @@ class HTMLPurifier
      * @return Purified HTML
      */
     public function purify($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();
-        
+
         // 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')) {
+        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);
-        
+
         // setup filters
         $filter_flags = $config->getBatch('Filter');
         $custom_filters = $filter_flags['Custom'];
@@ -152,6 +152,7 @@ class HTMLPurifier
         $filters = array();
         foreach ($filter_flags as $filter => $flag) {
             if (!$flag) continue;
+            if (strpos($filter, '.') !== false) continue;
             $class = "HTMLPurifier_Filter_$filter";
             $filters[] = new $class;
         }
@@ -161,13 +162,13 @@ class HTMLPurifier
         }
         $filters = array_merge($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(
@@ -179,16 +180,16 @@ class HTMLPurifier
                     $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.
@@ -204,7 +205,7 @@ class HTMLPurifier
         $this->context = $context_array;
         return $array_of_html;
     }
-    
+
     /**
      * Singleton for enforcing just one HTML Purifier in your system
      * @param $prototype Optional prototype HTMLPurifier instance to
@@ -223,12 +224,14 @@ class HTMLPurifier
         }
         return self::$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

@@ -6,13 +6,15 @@
  * 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/Array.php';
+require_once $__dir . '/HTMLPurifier/ArrayNode.php';
 require_once $__dir . '/HTMLPurifier/AttrCollections.php';
 require_once $__dir . '/HTMLPurifier/AttrDef.php';
 require_once $__dir . '/HTMLPurifier/AttrTransform.php';
@@ -30,6 +32,7 @@ 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/DoublyLinkedList.php';
 require_once $__dir . '/HTMLPurifier/ElementDef.php';
 require_once $__dir . '/HTMLPurifier/Encoder.php';
 require_once $__dir . '/HTMLPurifier/EntityLookup.php';
@@ -49,6 +52,8 @@ 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';
@@ -65,6 +70,7 @@ 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/Clone.php';
 require_once $__dir . '/HTMLPurifier/AttrDef/Enum.php';
 require_once $__dir . '/HTMLPurifier/AttrDef/Integer.php';
 require_once $__dir . '/HTMLPurifier/AttrDef/Lang.php';
@@ -82,6 +88,7 @@ require_once $__dir . '/HTMLPurifier/AttrDef/CSS/DenyElementDecorator.php';
 require_once $__dir . '/HTMLPurifier/AttrDef/CSS/Filter.php';
 require_once $__dir . '/HTMLPurifier/AttrDef/CSS/Font.php';
 require_once $__dir . '/HTMLPurifier/AttrDef/CSS/FontFamily.php';
+require_once $__dir . '/HTMLPurifier/AttrDef/CSS/Ident.php';
 require_once $__dir . '/HTMLPurifier/AttrDef/CSS/ImportantDecorator.php';
 require_once $__dir . '/HTMLPurifier/AttrDef/CSS/Length.php';
 require_once $__dir . '/HTMLPurifier/AttrDef/CSS/ListStyle.php';
@@ -90,6 +97,8 @@ 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/Nmtokens.php';
+require_once $__dir . '/HTMLPurifier/AttrDef/HTML/Class.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';
@@ -97,7 +106,6 @@ 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';
@@ -115,14 +123,18 @@ require_once $__dir . '/HTMLPurifier/AttrTransform/Input.php';
 require_once $__dir . '/HTMLPurifier/AttrTransform/Lang.php';
 require_once $__dir . '/HTMLPurifier/AttrTransform/Length.php';
 require_once $__dir . '/HTMLPurifier/AttrTransform/Name.php';
+require_once $__dir . '/HTMLPurifier/AttrTransform/NameSync.php';
+require_once $__dir . '/HTMLPurifier/AttrTransform/Nofollow.php';
 require_once $__dir . '/HTMLPurifier/AttrTransform/SafeEmbed.php';
 require_once $__dir . '/HTMLPurifier/AttrTransform/SafeObject.php';
 require_once $__dir . '/HTMLPurifier/AttrTransform/SafeParam.php';
 require_once $__dir . '/HTMLPurifier/AttrTransform/ScriptRequired.php';
+require_once $__dir . '/HTMLPurifier/AttrTransform/TargetBlank.php';
 require_once $__dir . '/HTMLPurifier/AttrTransform/Textarea.php';
 require_once $__dir . '/HTMLPurifier/ChildDef/Chameleon.php';
 require_once $__dir . '/HTMLPurifier/ChildDef/Custom.php';
 require_once $__dir . '/HTMLPurifier/ChildDef/Empty.php';
+require_once $__dir . '/HTMLPurifier/ChildDef/List.php';
 require_once $__dir . '/HTMLPurifier/ChildDef/Required.php';
 require_once $__dir . '/HTMLPurifier/ChildDef/Optional.php';
 require_once $__dir . '/HTMLPurifier/ChildDef/StrictBlockquote.php';
@@ -137,10 +149,12 @@ require_once $__dir . '/HTMLPurifier/HTMLModule/CommonAttributes.php';
 require_once $__dir . '/HTMLPurifier/HTMLModule/Edit.php';
 require_once $__dir . '/HTMLPurifier/HTMLModule/Forms.php';
 require_once $__dir . '/HTMLPurifier/HTMLModule/Hypertext.php';
+require_once $__dir . '/HTMLPurifier/HTMLModule/Iframe.php';
 require_once $__dir . '/HTMLPurifier/HTMLModule/Image.php';
 require_once $__dir . '/HTMLPurifier/HTMLModule/Legacy.php';
 require_once $__dir . '/HTMLPurifier/HTMLModule/List.php';
 require_once $__dir . '/HTMLPurifier/HTMLModule/Name.php';
+require_once $__dir . '/HTMLPurifier/HTMLModule/Nofollow.php';
 require_once $__dir . '/HTMLPurifier/HTMLModule/NonXMLCommonAttributes.php';
 require_once $__dir . '/HTMLPurifier/HTMLModule/Object.php';
 require_once $__dir . '/HTMLPurifier/HTMLModule/Presentation.php';
@@ -148,10 +162,12 @@ require_once $__dir . '/HTMLPurifier/HTMLModule/Proprietary.php';
 require_once $__dir . '/HTMLPurifier/HTMLModule/Ruby.php';
 require_once $__dir . '/HTMLPurifier/HTMLModule/SafeEmbed.php';
 require_once $__dir . '/HTMLPurifier/HTMLModule/SafeObject.php';
+require_once $__dir . '/HTMLPurifier/HTMLModule/SafeScripting.php';
 require_once $__dir . '/HTMLPurifier/HTMLModule/Scripting.php';
 require_once $__dir . '/HTMLPurifier/HTMLModule/StyleAttribute.php';
 require_once $__dir . '/HTMLPurifier/HTMLModule/Tables.php';
 require_once $__dir . '/HTMLPurifier/HTMLModule/Target.php';
+require_once $__dir . '/HTMLPurifier/HTMLModule/TargetBlank.php';
 require_once $__dir . '/HTMLPurifier/HTMLModule/Text.php';
 require_once $__dir . '/HTMLPurifier/HTMLModule/Tidy.php';
 require_once $__dir . '/HTMLPurifier/HTMLModule/XMLCommonAttributes.php';
@@ -166,6 +182,7 @@ require_once $__dir . '/HTMLPurifier/Injector/DisplayLinkURI.php';
 require_once $__dir . '/HTMLPurifier/Injector/Linkify.php';
 require_once $__dir . '/HTMLPurifier/Injector/PurifierLinkify.php';
 require_once $__dir . '/HTMLPurifier/Injector/RemoveEmpty.php';
+require_once $__dir . '/HTMLPurifier/Injector/RemoveSpansWithoutAttributes.php';
 require_once $__dir . '/HTMLPurifier/Injector/SafeObject.php';
 require_once $__dir . '/HTMLPurifier/Lexer/DOMLex.php';
 require_once $__dir . '/HTMLPurifier/Lexer/DirectLex.php';
@@ -185,9 +202,13 @@ require_once $__dir . '/HTMLPurifier/Token/Start.php';
 require_once $__dir . '/HTMLPurifier/Token/Text.php';
 require_once $__dir . '/HTMLPurifier/URIFilter/DisableExternal.php';
 require_once $__dir . '/HTMLPurifier/URIFilter/DisableExternalResources.php';
+require_once $__dir . '/HTMLPurifier/URIFilter/DisableResources.php';
 require_once $__dir . '/HTMLPurifier/URIFilter/HostBlacklist.php';
 require_once $__dir . '/HTMLPurifier/URIFilter/MakeAbsolute.php';
 require_once $__dir . '/HTMLPurifier/URIFilter/Munge.php';
+require_once $__dir . '/HTMLPurifier/URIFilter/SafeIframe.php';
+require_once $__dir . '/HTMLPurifier/URIScheme/data.php';
+require_once $__dir . '/HTMLPurifier/URIScheme/file.php';
 require_once $__dir . '/HTMLPurifier/URIScheme/ftp.php';
 require_once $__dir . '/HTMLPurifier/URIScheme/http.php';
 require_once $__dir . '/HTMLPurifier/URIScheme/https.php';

library/HTMLPurifier/Array.php

@@ -0,0 +1,184 @@
+<?php
+
+class HTMLPurifier_Array implements ArrayAccess
+{
+    /**
+     * @param HTMLPurifier_ArrayNode
+     */
+    public $head = null;
+
+    /**
+     * @var int
+     */
+    protected $count = 0;
+
+    /**
+     * @var int
+     */
+    protected $offset = 0;
+
+    /**
+     * @var HTMLPurifier_ArrayNode
+     */
+    protected $offsetItem = null;
+
+
+    public function __construct(array $array = array())
+    {
+        /**
+         * @var HTMLPurifier_ArrayNode $temp
+         */
+        $temp = null;
+        $i = 0;
+
+        foreach ($array as &$v) {
+            $item = new HTMLPurifier_ArrayNode($v);
+
+            if ($this->head == null) {
+                $this->head = &$item;
+            }
+            if ($temp instanceof HTMLPurifier_ArrayNode) {
+                $item->prev = &$temp;
+                $temp->next = &$item;
+            }
+            unset($temp);
+            $temp = &$item;
+
+            $i ++;
+
+            unset($item, $v);
+        }
+        $this->count = $i;
+        $this->offset = 0;
+        $this->offsetItem = &$this->head;
+    }
+
+    protected function findIndex($offset)
+    {
+        if ($this->head == null) {
+            return array(
+                'correct' => false,
+                'value' => null
+            );
+        }
+
+        $current = &$this->head;
+        $index = 0;
+
+        if ($this->offset <= $offset && $this->offsetItem instanceof HTMLPurifier_ArrayNode) {
+            $current = &$this->offsetItem;
+            $index = $this->offset;
+        }
+
+        while ($current->next instanceof HTMLPurifier_ArrayNode && $index != $offset) {
+            $current = &$current->next;
+            $index ++;
+        }
+
+        if ($index == $offset) {
+            $this->offset = $offset;
+            $this->offsetItem = &$current;
+            return array(
+                'correct' => true,
+                'value' => &$current
+            );
+        }
+
+        return array(
+            'correct' => false,
+            'value' => &$current
+        );
+    }
+
+    public function insertBefore($offset, $value)
+    {
+        $result = $this->findIndex($offset);
+
+        $this->count ++;
+        $item = new HTMLPurifier_ArrayNode($value);
+        if ($result['correct'] == false) {
+            if ($result['value'] instanceof HTMLPurifier_ArrayNode) {
+                $result['value']->next = &$item;
+                $item->prev = &$result['value'];
+            }
+        } else {
+            if ($result['value'] instanceof HTMLPurifier_ArrayNode) {
+                $item->prev = &$result['value']->prev;
+                $item->next = &$result['value'];
+            }
+            if ($item->prev instanceof HTMLPurifier_ArrayNode) {
+                $item->prev->next = &$item;
+            }
+            if ($result['value'] instanceof HTMLPurifier_ArrayNode) {
+                $result['value']->prev = &$item;
+            }
+        }
+        if ($offset == 0) {
+            $this->head = &$item;
+        }
+        if ($offset <= $this->offset && $this->offsetItem instanceof HTMLPurifier_ArrayNode) {
+            $this->offsetItem = &$this->offsetItem->prev;
+        }
+    }
+
+    public function remove($offset)
+    {
+        $result = $this->findIndex($offset);
+
+        if ($result['correct']) {
+            $this->count --;
+            $item = $result['value'];
+            $item->prev->next = &$result['value']->next;
+            $item->next->prev = &$result['value']->prev;
+            if ($offset == 0) {
+                $this->head = &$item->next;
+            }
+            if ($offset < $this->offset) {
+                $this->offset --;
+            } elseif ($offset == $this->offset) {
+                $this->offsetItem = &$item->next;
+            }
+        }
+    }
+
+    public function getArray()
+    {
+        $return = array();
+        $head = $this->head;
+
+        while ($head instanceof HTMLPurifier_ArrayNode) {
+            $return[] = $head->value;
+            $head = &$head->next;
+        }
+
+        return $return;
+    }
+
+    public function offsetExists($offset)
+    {
+        return $offset >= 0 && $offset < $this->count;
+    }
+
+    public function offsetGet($offset)
+    {
+        $result = $this->findIndex($offset);
+        if ($result['correct']) {
+            return $result['value']->value;
+        }
+
+        return null;
+    }
+
+    public function offsetSet($offset, $value)
+    {
+        $result = $this->findIndex($offset);
+        if ($result['correct']) {
+            $result['value']->value = &$value;
+        }
+    }
+
+    public function offsetUnset($offset)
+    {
+        $this->remove($offset);
+    }
+}

library/HTMLPurifier/ArrayNode.php

@@ -0,0 +1,24 @@
+<?php
+
+class HTMLPurifier_ArrayNode
+{
+    public function __construct(&$value)
+    {
+        $this->value = &$value;
+    }
+
+    /**
+     * @var HTMLPurifier_ArrayNode
+     */
+    public $prev = null;
+
+    /**
+     * @var HTMLPurifier_ArrayNode
+     */
+    public $next = null;
+
+    /**
+     * @var mixed
+     */
+    public $value = null;
+}

library/HTMLPurifier/AttrCollections.php

@@ -6,12 +6,12 @@
 
 class HTMLPurifier_AttrCollections
 {
-    
+
     /**
      * Associative array of attribute collections, indexed by name
      */
     public $info = array();
-    
+
     /**
      * Performs all expansions on internal data for use by other inclusions
      * It also collects all attribute collection extensions from
@@ -45,7 +45,7 @@ class HTMLPurifier_AttrCollections
             $this->expandIdentifiers($this->info[$name], $attr_types);
         }
     }
-    
+
     /**
      * Takes a reference to an attribute associative array and performs
      * all inclusions specified by the zero index.
@@ -72,7 +72,7 @@ class HTMLPurifier_AttrCollections
         }
         unset($attr[0]);
     }
-    
+
     /**
      * Expands all string identifiers in an attribute array by replacing
      * them with the appropriate values inside HTMLPurifier_AttrTypes
@@ -80,17 +80,17 @@ class HTMLPurifier_AttrCollections
      * @param $attr_types HTMLPurifier_AttrTypes instance
      */
     public function expandIdentifiers(&$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
@@ -98,21 +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 = $required;
@@ -120,8 +120,9 @@ class HTMLPurifier_AttrCollections
                 unset($attr[$def_i]);
             }
         }
-        
+
     }
-    
+
 }
 
+// vim: et sw=4 sts=4

library/HTMLPurifier/AttrDef.php

@@ -2,53 +2,53 @@
 
 /**
  * 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.
  */
 
 abstract class HTMLPurifier_AttrDef
 {
-    
+
     /**
      * Tells us whether or not an HTML attribute is minimized. Has no
      * meaning in other contexts.
      */
     public $minimized = false;
-    
+
     /**
      * Tells us whether or not an HTML attribute is required. Has no
      * meaning in other contexts
      */
     public $required = false;
-    
+
     /**
      * Validates and cleans passed string according to a definition.
-     * 
+     *
      * @param $string String to be validated and cleaned.
      * @param $config Mandatory HTMLPurifier_Config object.
      * @param $context Mandatory HTMLPurifier_AttrContext object.
      */
     abstract public function validate($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.  However, note that we are NOT necessarily
@@ -60,7 +60,7 @@ abstract class HTMLPurifier_AttrDef
         $string = str_replace(array("\n", "\t", "\r"), ' ', $string);
         return $string;
     }
-    
+
     /**
      * Factory method for creating this class from a string.
      * @param $string String construction info
@@ -73,7 +73,7 @@ abstract class HTMLPurifier_AttrDef
         // to clone or instantiate new copies. (Instantiation is safer.)
         return $this;
     }
-    
+
     /**
      * Removes spaces from rgb(0, 0, 0) so that shorthand CSS properties work
      * properly. THIS IS A HACK!
@@ -81,6 +81,43 @@ abstract class HTMLPurifier_AttrDef
     protected function mungeRgb($string) {
         return preg_replace('/rgb\((\d+)\s*,\s*(\d+)\s*,\s*(\d+)\)/', 'rgb(\1,\2,\3)', $string);
     }
-    
+
+    /**
+     * Parses a possibly escaped CSS string and returns the "pure" 
+     * version of it.
+     */
+    protected function expandCSSEscape($string) {
+        // flexibly parse it
+        $ret = '';
+        for ($i = 0, $c = strlen($string); $i < $c; $i++) {
+            if ($string[$i] === '\\') {
+                $i++;
+                if ($i >= $c) {
+                    $ret .= '\\';
+                    break;
+                }
+                if (ctype_xdigit($string[$i])) {
+                    $code = $string[$i];
+                    for ($a = 1, $i++; $i < $c && $a < 6; $i++, $a++) {
+                        if (!ctype_xdigit($string[$i])) break;
+                        $code .= $string[$i];
+                    }
+                    // We have to be extremely careful when adding
+                    // new characters, to make sure we're not breaking
+                    // the encoding.
+                    $char = HTMLPurifier_Encoder::unichr(hexdec($code));
+                    if (HTMLPurifier_Encoder::cleanUTF8($char) === '') continue;
+                    $ret .= $char;
+                    if ($i < $c && trim($string[$i]) !== '') $i--;
+                    continue;
+                }
+                if ($string[$i] === "\n") continue;
+            }
+            $ret .= $string[$i];
+        }
+        return $ret;
+    }
+
 }
 
+// vim: et sw=4 sts=4

library/HTMLPurifier/AttrDef/CSS.php

@@ -13,28 +13,28 @@
  */
 class HTMLPurifier_AttrDef_CSS extends HTMLPurifier_AttrDef
 {
-    
+
     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($declaration, ':')) continue;
@@ -66,21 +66,22 @@ class HTMLPurifier_AttrDef_CSS extends HTMLPurifier_AttrDef
             if ($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

@@ -2,11 +2,11 @@
 
 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 $result;
@@ -15,5 +15,7 @@ class HTMLPurifier_AttrDef_CSS_AlphaValue extends HTMLPurifier_AttrDef_CSS_Numbe
         if ($float > 1.0) $result = '1';
         return $result;
     }
-    
+
 }
+
+// vim: et sw=4 sts=4

library/HTMLPurifier/AttrDef/CSS/Background.php

@@ -6,13 +6,13 @@
  */
 class HTMLPurifier_AttrDef_CSS_Background extends HTMLPurifier_AttrDef
 {
-    
+
     /**
      * Local copy of component validators.
      * @note See HTMLPurifier_AttrDef_Font::$info for a similar impl.
      */
     protected $info;
-    
+
     public function __construct($config) {
         $def = $config->getCSSDefinition();
         $this->info['background-color'] = $def->info['background-color'];
@@ -21,29 +21,29 @@ class HTMLPurifier_AttrDef_CSS_Background extends HTMLPurifier_AttrDef
         $this->info['background-attachment'] = $def->info['background-attachment'];
         $this->info['background-position'] = $def->info['background-position'];
     }
-    
+
     public function validate($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
-        
+        $bits = explode(' ', $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

@@ -7,7 +7,7 @@
         [
             <percentage> | <length> | left | center | right
         ]
-        [ 
+        [
             <percentage> | <length> | top | center | bottom
         ]?
     ] |
@@ -28,10 +28,10 @@
 
 /* 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.
 */
 
@@ -43,27 +43,28 @@
  */
 class HTMLPurifier_AttrDef_CSS_BackgroundPosition extends HTMLPurifier_AttrDef
 {
-    
+
     protected $length;
     protected $percentage;
-    
+
     public function __construct() {
         $this->length     = new HTMLPurifier_AttrDef_CSS_Length();
         $this->percentage = new HTMLPurifier_AttrDef_CSS_Percentage();
     }
-    
+
     public function validate($string, $config, $context) {
         $string = $this->parseCDATA($string);
         $bits = explode(' ', $string);
-        
+
         $keywords = array();
         $keywords['h'] = false; // left, right
         $keywords['v'] = false; // top, bottom
-        $keywords['c'] = false; // center
+        $keywords['ch'] = false; // center (first word)
+        $keywords['cv'] = false; // center (second word)
         $measures = array();
-        
+
         $i = 0;
-        
+
         $lookup = array(
             'top' => 'v',
             'bottom' => 'v',
@@ -71,55 +72,62 @@ class HTMLPurifier_AttrDef_CSS_BackgroundPosition extends HTMLPurifier_AttrDef
             'right' => 'h',
             'center' => 'c'
         );
-        
+
         foreach ($bits as $bit) {
             if ($bit === '') continue;
-            
+
             // test for keyword
             $lbit = ctype_lower($bit) ? $bit : strtolower($bit);
             if (isset($lookup[$lbit])) {
                 $status = $lookup[$lbit];
+                if ($status == 'c') {
+                    if ($i == 0) {
+                        $status = 'ch';
+                    } else {
+                        $status = 'cv';
+                    }
+                }
                 $keywords[$status] = $lbit;
                 $i++;
             }
-            
+
             // test for length
             $r = $this->length->validate($bit, $config, $context);
             if ($r !== false) {
                 $measures[] = $r;
                 $i++;
             }
-            
+
             // test for percentage
             $r = $this->percentage->validate($bit, $config, $context);
             if ($r !== false) {
                 $measures[] = $r;
                 $i++;
             }
-            
+
         }
-        
+
         if (!$i) return false; // no valid values were caught
-        
-        
+
         $ret = array();
-        
+
         // first keyword
         if     ($keywords['h'])     $ret[] = $keywords['h'];
-        elseif (count($measures))   $ret[] = array_shift($measures);
-        elseif ($keywords['c']) {
-            $ret[] = $keywords['c'];
-            $keywords['c'] = false; // prevent re-use: center = center center
+        elseif ($keywords['ch']) {
+            $ret[] = $keywords['ch'];
+            $keywords['cv'] = false; // prevent re-use: center = center center
         }
-        
-        if     ($keywords['v'])     $ret[] = $keywords['v'];
         elseif (count($measures))   $ret[] = array_shift($measures);
-        elseif ($keywords['c'])     $ret[] = $keywords['c'];
-        
+
+        if     ($keywords['v'])     $ret[] = $keywords['v'];
+        elseif ($keywords['cv'])    $ret[] = $keywords['cv'];
+        elseif (count($measures))   $ret[] = array_shift($measures);
+
         if (empty($ret)) return false;
         return implode(' ', $ret);
-        
+
     }
-    
+
 }
 
+// vim: et sw=4 sts=4

library/HTMLPurifier/AttrDef/CSS/Border.php

@@ -5,19 +5,19 @@
  */
 class HTMLPurifier_AttrDef_CSS_Border extends HTMLPurifier_AttrDef
 {
-    
+
     /**
      * Local copy of properties this property is shorthand for.
      */
     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'] = $def->info['border-top-color'];
     }
-    
+
     public function validate($string, $config, $context) {
         $string = $this->parseCDATA($string);
         $string = $this->mungeRgb($string);
@@ -37,6 +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

@@ -5,18 +5,18 @@
  */
 class HTMLPurifier_AttrDef_CSS_Color extends HTMLPurifier_AttrDef
 {
-    
+
     public function validate($color, $config, $context) {
-        
+
         static $colors = null;
-        if ($colors === null) $colors = $config->get('Core', 'ColorKeywords');
-        
+        if ($colors === null) $colors = $config->get('Core.ColorKeywords');
+
         $color = trim($color);
         if ($color === '') return false;
-        
+
         $lower = strtolower($color);
         if (isset($colors[$lower])) return $colors[$lower];
-        
+
         if (strpos($color, 'rgb(') !== false) {
             // rgb literal handling
             $length = strlen($color);
@@ -68,10 +68,11 @@ class HTMLPurifier_AttrDef_CSS_Color extends HTMLPurifier_AttrDef
             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
@@ -11,20 +11,20 @@
  */
 class HTMLPurifier_AttrDef_CSS_Composite extends HTMLPurifier_AttrDef
 {
-    
+
     /**
      * List of HTMLPurifier_AttrDef objects that may process strings
      * @todo Make protected
      */
     public $defs;
-    
+
     /**
      * @param $defs List of HTMLPurifier_AttrDef objects
      */
     public function __construct($defs) {
         $this->defs = $defs;
     }
-    
+
     public function validate($string, $config, $context) {
         foreach ($this->defs as $i => $def) {
             $result = $this->defs[$i]->validate($string, $config, $context);
@@ -32,6 +32,7 @@ class HTMLPurifier_AttrDef_CSS_Composite extends HTMLPurifier_AttrDef
         }
         return false;
     }
-    
+
 }
 
+// vim: et sw=4 sts=4

library/HTMLPurifier/AttrDef/CSS/DenyElementDecorator.php

@@ -5,8 +5,8 @@
  */
 class HTMLPurifier_AttrDef_CSS_DenyElementDecorator extends HTMLPurifier_AttrDef
 {
-    protected $def, $element;
-    
+    public $def, $element;
+
     /**
      * @param $def Definition to wrap
      * @param $element Element to deny
@@ -24,3 +24,5 @@ class HTMLPurifier_AttrDef_CSS_DenyElementDecorator extends HTMLPurifier_AttrDef
         return $this->def->validate($string, $config, $context);
     }
 }
+
+// vim: et sw=4 sts=4

library/HTMLPurifier/AttrDef/CSS/Filter.php

@@ -7,13 +7,13 @@
  */
 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;
@@ -48,5 +48,7 @@ class HTMLPurifier_AttrDef_CSS_Filter extends HTMLPurifier_AttrDef
         $ret_function = "$function($ret_parameters)";
         return $ret_function;
     }
-    
+
 }
+
+// vim: et sw=4 sts=4

library/HTMLPurifier/AttrDef/CSS/Font.php

@@ -5,17 +5,17 @@
  */
 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.
      */
     protected $info = array();
-    
+
     public function __construct($config) {
         $def = $config->getCSSDefinition();
         $this->info['font-style']   = $def->info['font-style'];
@@ -25,9 +25,9 @@ class HTMLPurifier_AttrDef_CSS_Font extends HTMLPurifier_AttrDef
         $this->info['line-height']  = $def->info['line-height'];
         $this->info['font-family']  = $def->info['font-family'];
     }
-    
+
     public function validate($string, $config, $context) {
-        
+
         static $system_fonts = array(
             'caption' => true,
             'icon' => true,
@@ -36,27 +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 $validator_name) {
@@ -72,7 +72,7 @@ class HTMLPurifier_AttrDef_CSS_Font extends HTMLPurifier_AttrDef
                     // all three caught, continue on
                     if (count($caught) >= 3) $stage = 1;
                     if ($r !== false) break;
-                
+
                 // attempting to catch font-size and perhaps line-height
                 case 1:
                     $found_slash = false;
@@ -126,7 +126,7 @@ class HTMLPurifier_AttrDef_CSS_Font extends HTMLPurifier_AttrDef
                         break;
                     }
                     return false;
-                
+
                 // attempting to catch font-family
                 case 2:
                     $font_family =
@@ -143,6 +143,7 @@ class HTMLPurifier_AttrDef_CSS_Font extends HTMLPurifier_AttrDef
         }
         return false;
     }
-    
+
 }
 
+// vim: et sw=4 sts=4

library/HTMLPurifier/AttrDef/CSS/FontFamily.php

@@ -2,11 +2,43 @@
 
 /**
  * Validates a font family list according to CSS spec
- * @todo whitelisting allowed fonts would be nice
  */
 class HTMLPurifier_AttrDef_CSS_FontFamily extends HTMLPurifier_AttrDef
 {
-    
+
+    protected $mask = null;
+
+    public function __construct() {
+        $this->mask = '_- ';
+        for ($c = 'a'; $c <= 'z'; $c++) $this->mask .= $c;
+        for ($c = 'A'; $c <= 'Z'; $c++) $this->mask .= $c;
+        for ($c = '0'; $c <= '9'; $c++) $this->mask .= $c; // cast-y, but should be fine
+        // special bytes used by UTF-8
+        for ($i = 0x80; $i <= 0xFF; $i++) {
+            // We don't bother excluding invalid bytes in this range,
+            // because the our restriction of well-formed UTF-8 will
+            // prevent these from ever occurring.
+            $this->mask .= chr($i);
+        }
+
+        /*
+            PHP's internal strcspn implementation is
+            O(length of string * length of mask), making it inefficient
+            for large masks.  However, it's still faster than
+            preg_match 8)
+          for (p = s1;;) {
+            spanp = s2;
+            do {
+              if (*spanp == c || p == s1_end) {
+                return p - s1;
+              }
+            } while (spanp++ < (s2_end - 1));
+            c = *++p;
+          }
+         */
+        // possible optimization: invert the mask.
+    }
+
     public function validate($string, $config, $context) {
         static $generic_names = array(
             'serif' => true,
@@ -15,7 +47,8 @@ class HTMLPurifier_AttrDef_CSS_FontFamily extends HTMLPurifier_AttrDef
             'fantasy' => true,
             'cursive' => true
         );
-        
+        $allowed_fonts = $config->get('CSS.AllowedFonts');
+
         // assume that no font names contain commas in them
         $fonts = explode(',', $string);
         $final = '';
@@ -24,7 +57,9 @@ class HTMLPurifier_AttrDef_CSS_FontFamily extends HTMLPurifier_AttrDef
             if ($font === '') continue;
             // match a generic name
             if (isset($generic_names[$font])) {
-                $final .= $font . ', ';
+                if ($allowed_fonts === null || isset($allowed_fonts[$font])) {
+                    $final .= $font . ', ';
+                }
                 continue;
             }
             // match a quoted name
@@ -34,56 +69,129 @@ class HTMLPurifier_AttrDef_CSS_FontFamily extends HTMLPurifier_AttrDef
                 $quote = $font[0];
                 if ($font[$length - 1] !== $quote) continue;
                 $font = substr($font, 1, $length - 2);
-                
-                $new_font = '';
-                for ($i = 0, $c = strlen($font); $i < $c; $i++) {
-                    if ($font[$i] === '\\') {
-                        $i++;
-                        if ($i >= $c) {
-                            $new_font .= '\\';
-                            break;
-                        }
-                        if (ctype_xdigit($font[$i])) {
-                            $code = $font[$i];
-                            for ($a = 1, $i++; $i < $c && $a < 6; $i++, $a++) {
-                                if (!ctype_xdigit($font[$i])) break;
-                                $code .= $font[$i];
-                            }
-                            // We have to be extremely careful when adding
-                            // new characters, to make sure we're not breaking
-                            // the encoding.
-                            $char = HTMLPurifier_Encoder::unichr(hexdec($code));
-                            if (HTMLPurifier_Encoder::cleanUTF8($char) === '') continue;
-                            $new_font .= $char;
-                            if ($i < $c && trim($font[$i]) !== '') $i--;
-                            continue;
-                        }
-                        if ($font[$i] === "\n") continue;
-                    }
-                    $new_font .= $font[$i];
-                }
-                
-                $font = $new_font;
             }
+
+            $font = $this->expandCSSEscape($font);
+
             // $font is a pure representation of the font name
-            
+
+            if ($allowed_fonts !== null && !isset($allowed_fonts[$font])) {
+                continue;
+            }
+
             if (ctype_alnum($font) && $font !== '') {
                 // very simple font, allow it in unharmed
                 $final .= $font . ', ';
                 continue;
             }
-            
-            // complicated font, requires quoting
-            
-            // armor single quotes and new lines
-            $font = str_replace("\\", "\\\\", $font);
-            $font = str_replace("'", "\\'", $font);
+
+            // bugger out on whitespace.  form feed (0C) really
+            // shouldn't show up regardless
+            $font = str_replace(array("\n", "\t", "\r", "\x0C"), ' ', $font);
+
+            // Here, there are various classes of characters which need
+            // to be treated differently:
+            //  - Alphanumeric characters are essentially safe.  We
+            //    handled these above.
+            //  - Spaces require quoting, though most parsers will do
+            //    the right thing if there aren't any characters that
+            //    can be misinterpreted
+            //  - Dashes rarely occur, but they fairly unproblematic
+            //    for parsing/rendering purposes.
+            //  The above characters cover the majority of Western font
+            //  names.
+            //  - Arbitrary Unicode characters not in ASCII.  Because
+            //    most parsers give little thought to Unicode, treatment
+            //    of these codepoints is basically uniform, even for
+            //    punctuation-like codepoints.  These characters can
+            //    show up in non-Western pages and are supported by most
+            //    major browsers, for example: "ＭＳ 明朝" is a
+            //    legitimate font-name
+            //    <http://ja.wikipedia.org/wiki/MS_明朝>.  See
+            //    the CSS3 spec for more examples:
+            //    <http://www.w3.org/TR/2011/WD-css3-fonts-20110324/localizedfamilynames.png>
+            //    You can see live samples of these on the Internet:
+            //    <http://www.google.co.jp/search?q=font-family+ＭＳ+明朝|ゴシック>
+            //    However, most of these fonts have ASCII equivalents:
+            //    for example, 'MS Mincho', and it's considered
+            //    professional to use ASCII font names instead of
+            //    Unicode font names.  Thanks Takeshi Terada for
+            //    providing this information.
+            //  The following characters, to my knowledge, have not been
+            //  used to name font names.
+            //  - Single quote.  While theoretically you might find a
+            //    font name that has a single quote in its name (serving
+            //    as an apostrophe, e.g. Dave's Scribble), I haven't
+            //    been able to find any actual examples of this.
+            //    Internet Explorer's cssText translation (which I
+            //    believe is invoked by innerHTML) normalizes any
+            //    quoting to single quotes, and fails to escape single
+            //    quotes.  (Note that this is not IE's behavior for all
+            //    CSS properties, just some sort of special casing for
+            //    font-family).  So a single quote *cannot* be used
+            //    safely in the font-family context if there will be an
+            //    innerHTML/cssText translation.  Note that Firefox 3.x
+            //    does this too.
+            //  - Double quote.  In IE, these get normalized to
+            //    single-quotes, no matter what the encoding.  (Fun
+            //    fact, in IE8, the 'content' CSS property gained
+            //    support, where they special cased to preserve encoded
+            //    double quotes, but still translate unadorned double
+            //    quotes into single quotes.)  So, because their
+            //    fixpoint behavior is identical to single quotes, they
+            //    cannot be allowed either.  Firefox 3.x displays
+            //    single-quote style behavior.
+            //  - Backslashes are reduced by one (so \\ -> \) every
+            //    iteration, so they cannot be used safely.  This shows
+            //    up in IE7, IE8 and FF3
+            //  - Semicolons, commas and backticks are handled properly.
+            //  - The rest of the ASCII punctuation is handled properly.
+            // We haven't checked what browsers do to unadorned
+            // versions, but this is not important as long as the
+            // browser doesn't /remove/ surrounding quotes (as IE does
+            // for HTML).
+            //
+            // With these results in hand, we conclude that there are
+            // various levels of safety:
+            //  - Paranoid: alphanumeric, spaces and dashes(?)
+            //  - International: Paranoid + non-ASCII Unicode
+            //  - Edgy: Everything except quotes, backslashes
+            //  - NoJS: Standards compliance, e.g. sod IE. Note that
+            //    with some judicious character escaping (since certain
+            //    types of escaping doesn't work) this is theoretically
+            //    OK as long as innerHTML/cssText is not called.
+            // We believe that international is a reasonable default
+            // (that we will implement now), and once we do more
+            // extensive research, we may feel comfortable with dropping
+            // it down to edgy.
+
+            // Edgy: alphanumeric, spaces, dashes, underscores and Unicode.  Use of
+            // str(c)spn assumes that the string was already well formed
+            // Unicode (which of course it is).
+            if (strspn($font, $this->mask) !== strlen($font)) {
+                continue;
+            }
+
+            // Historical:
+            // In the absence of innerHTML/cssText, these ugly
+            // transforms don't pose a security risk (as \\ and \"
+            // might--these escapes are not supported by most browsers).
+            // We could try to be clever and use single-quote wrapping
+            // when there is a double quote present, but I have choosen
+            // not to implement that.  (NOTE: you can reduce the amount
+            // of escapes by one depending on what quoting style you use)
+            // $font = str_replace('\\', '\\5C ', $font);
+            // $font = str_replace('"',  '\\22 ', $font);
+            // $font = str_replace("'",  '\\27 ', $font);
+
+            // font possibly with spaces, requires quoting
             $final .= "'$font', ";
         }
         $final = rtrim($final, ', ');
         if ($final === '') return false;
         return $final;
     }
-    
+
 }
 
+// vim: et sw=4 sts=4

library/HTMLPurifier/AttrDef/CSS/Ident.php

@@ -0,0 +1,24 @@
+<?php
+
+/**
+ * Validates based on {ident} CSS grammar production
+ */
+class HTMLPurifier_AttrDef_CSS_Ident extends HTMLPurifier_AttrDef
+{
+
+    public function validate($string, $config, $context) {
+
+        $string = trim($string);
+
+        // early abort: '' and '0' (strings that convert to false) are invalid
+        if (!$string) return false;
+
+        $pattern = '/^(-?[A-Za-z_][A-Za-z_\-0-9]*)$/';
+        if (!preg_match($pattern, $string)) return false;
+        return $string;
+
+    }
+
+}
+
+// vim: et sw=4 sts=4

library/HTMLPurifier/AttrDef/CSS/ImportantDecorator.php

@@ -5,8 +5,8 @@
  */
 class HTMLPurifier_AttrDef_CSS_ImportantDecorator extends HTMLPurifier_AttrDef
 {
-    protected $def, $allow;
-    
+    public $def, $allow;
+
     /**
      * @param $def Definition to wrap
      * @param $allow Whether or not to allow !important
@@ -36,3 +36,5 @@ class HTMLPurifier_AttrDef_CSS_ImportantDecorator extends HTMLPurifier_AttrDef
         return $string;
     }
 }
+
+// vim: et sw=4 sts=4