Release 3.3.0.

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

.gitattributes

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

.gitignore

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

CREDITS

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

Doxyfile

@@ -31,7 +31,7 @@ PROJECT_NAME           = HTMLPurifier
 # This could be handy for archiving the generated documentation or
 # if some version control system is used.
 
-PROJECT_NUMBER         = 3.1.0
+PROJECT_NUMBER         = 3.3.0
 
 # The OUTPUT_DIRECTORY tag is used to specify the (relative or absolute)
 # base path where the generated documentation will be put.
@@ -1313,3 +1313,5 @@ DOT_CLEANUP            = YES
 # used. If set to NO the values of all tags below this one will be ignored.
 
 SEARCHENGINE           = NO
+
+# vim: et sw=4 sts=4

FOCUS

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

INSTALL

@@ -18,13 +18,12 @@ with these contents.
 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. 
 
 These optional extensions can enhance the capabilities of HTML Purifier:
 
-    * iconv : Converts text to and from non-UTF-8 encodings
-    * tidy  : Used for pretty-printing HTML
+    * iconv  : Converts text to and from non-UTF-8 encodings
+    * bcmath : Used for unit conversion and imagecrash protection
+    * tidy   : Used for pretty-printing HTML
 
 
 ---------------------------------------------------------------------------
@@ -371,3 +370,4 @@ If your website is in a different encoding or doctype, use this code:
     $clean_html = $purifier->purify($dirty_html);
 ?>
 
+    vim: et sw=4 sts=4

INSTALL.fr.utf8

@@ -65,3 +65,5 @@ Sinon, utilisez:
 
     $html_propre = $purificateur->purify($html_salle);
 ?>
+
+    vim: et sw=4 sts=4

LICENSE

@@ -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 +9,174 @@ NEWS ( CHANGELOG and HISTORY )                                     HTMLPurifier
     . Internal change
 ==========================
 
+3.3.0, released 2009-02-16
+! Implement CSS property 'overflow' when %CSS.AllowTricky is true.
+! Implement generic property list classess
+- Fix bug with testEncodingSupportsASCII() algorithm when iconv() implementation
+  does not do the "right thing" with characters not supported in the output
+  set.
+- Spellcheck UTF-8: The Secret To Character Encoding
+- Fix improper removal of the contents of elements with only whitespace. Thanks
+  Eric Wald for reporting.
+- Fix broken test suite in versions of PHP without spl_autoload_register()
+- Fix degenerate case with YouTube filter involving double hyphens.
+  Thanks Pierre Attar for reporting.
+- Fix YouTube rendering problem on certain versions of Firefox.
+- Fix CSSDefinition Printer problems with decorators
+- Add text parameter to unit tests, forces text output
+. Add verbose mode to command line test runner, use (--verbose)
+. Turn on unit tests for UnitConverter
+. Fix missing version number in configuration %Attr.DefaultImageAlt (added 3.2.0)
+. Fix newline errors that caused spurious failures when CRLF HTML Purifier was
+  tested on Linux.
+. Removed trailing whitespace from all text files, see
+  remote-trailing-whitespace.php maintenance script.
+. Convert configuration to use property list backend.
+
+3.2.0, released 2008-10-31
+# Using %Core.CollectErrors forces line number/column tracking on, whereas
+  previously you could theoretically turn it off.
+# HTMLPurifier_Injector->notifyEnd() is formally deprecated. Please
+  use handleEnd() instead.
+! %Output.AttrSort for when you need your attributes in alphabetical order to
+  deal with a bug in FCKEditor. Requested by frank farmer.
+! Enable HTML comments when %HTML.Trusted is on. Requested by Waldo Jaquith.
+! Proper support for name attribute. It is now allowed and equivalent to the id
+  attribute in a and img tags, and is only converted to id when %HTML.TidyLevel
+  is heavy (for all doctypes).
+! %AutoFormat.RemoveEmpty to remove some empty tags from documents. Please don't
+  use on hand-written HTML.
+! Add error-cases for unsupported elements in MakeWellFormed. This enables
+  the strategy to be used, standalone, on untrusted input.
+! %Core.AggressivelyFixLt is on by default. This causes more sensible
+  processing of left angled brackets in smileys and other whatnot.
+! Test scripts now have a 'type' parameter, which lets you say 'htmlpurifier',
+  'phpt', 'vtest', etc. in order to only execute those tests. This supercedes
+  the --only-phpt parameter, although for backwards-compatibility the flag
+  will still work.
+! AutoParagraph auto-formatter will now preserve double-newlines upon output.
+  Users who are not performing inbound filtering, this may seem a little
+  useless, but as a bonus, the test suite and handling of edge cases is also
+  improved.
+! Experimental implementation of forms for %HTML.Trusted
+! Track column numbers when maintain line numbers is on
+! Proprietary 'background' attribute on table-related elements converted into
+  corresponding CSS.  Thanks Fusemail for sponsoring this feature!
+! Add forward(), forwardUntilEndToken(), backward() and current() to Injector
+  supertype.
+! HTMLPurifier_Injector->handleEnd() permits modification to end tokens. The
+  time of operation varies slightly from notifyEnd() as *all* end tokens are
+  processed by the injector before they are subject to the well-formedness rules.
+! %Attr.DefaultImageAlt allows overriding default behavior of setting alt to
+  basename of image when not present.
+! %AutoFormat.DisplayLinkURI neuters <a> tags into plain text URLs.
+- Fix two bugs in %URI.MakeAbsolute; one involving empty paths in base URLs,
+  the other involving an undefined $is_folder error.
+- Throw error when %Core.Encoding is set to a spurious value. Previously,
+  this errored silently and returned false.
+- Redirected stderr to stdout for flush error output.
+- %URI.DisableExternal will now use the host in %URI.Base if %URI.Host is not
+  available.
+- Do not re-munge URL if the output URL has the same host as the input URL.
+  Requested by Chris.
+- Fix error in documentation regarding %Filter.ExtractStyleBlocks
+- Prevent <![CDATA[<body></body>]]> from triggering %Core.ConvertDocumentToFragment
+- Fix bug with inline elements in blockquotes conflicting with strict doctype
+- Detect if HTML support is disabled for DOM by checking for loadHTML() method.
+- Fix bug where dots and double-dots in absolute URLs without hostname were
+  not collapsed by URIFilter_MakeAbsolute.
+- Fix bug with anonymous modules operating on SafeEmbed or SafeObject elements
+  by reordering their addition.
+- Will now throw exception on many error conditions during lexer creation; also
+  throw an exception when MaintainLineNumbers is true, but a non-tracksLineNumbers
+  is being used.
+- Detect if domxml extension is loaded, and use DirectLEx accordingly.
+- Improve handling of big numbers with floating point arithmetic in UnitConverter.
+  Reported by David Morton.
+. Strategy_MakeWellFormed now operates in-place, saving memory and allowing
+  for more interesting filter-backtracking
+. New HTMLPurifier_Injector->rewind() functionality, allows injectors to rewind
+  index to reprocess tokens.
+. StringHashParser now allows for multiline sections with "empty" content;
+  previously the section would remain undefined.
+. Added --quick option to multitest.php, which tests only the most recent
+  release for each series.
+. Added --distro option to multitest.php, which accepts either 'normal' or
+  'standalone'. This supercedes --exclude-normal and --exclude-standalone
+
+3.1.1, released 2008-06-19
+# %URI.Munge now, by default, does not munge resources (for example, <img src="">)
+  In order to enable this again, please set %URI.MungeResources to true.
+! More robust imagecrash protection with height/width CSS with %CSS.MaxImgLength,
+  and height/width HTML with %HTML.MaxImgLength.
+! %URI.MungeSecretKey for secure URI munging. Thanks Chris
+  for sponsoring this feature. Check out the corresponding documentation
+  for details. (Att Nightly testers: The API for this feature changed before
+  the general release. Namely, rename your directives %URI.SecureMungeSecretKey =>
+  %URI.MungeSecretKey and and %URI.SecureMunge => %URI.Munge)
+! Implemented post URI filtering. Set member variable $post to true to set
+  a URIFilter as such.
+! Allow modules to define injectors via $info_injector. Injectors are
+  automatically disabled if injector's needed elements are not found.
+! Support for "safe" objects added, use %HTML.SafeObject and %HTML.SafeEmbed.
+  Thanks Chris for sponsoring. If you've been using ad hoc code from the
+  forums, PLEASE use this instead.
+! Added substitutions for %e, %n, %a and %p in %URI.Munge (in order,
+  embedded, tag name, attribute name, CSS property name). See %URI.Munge
+  for more details. Requested by Jochem Blok.
+- Disable percent height/width attributes for img.
+- AttrValidator operations are now atomic; updates to attributes are not
+  manifest in token until end of operations. This prevents naughty internal
+  code from directly modifying CurrentToken when they're not supposed to.
+  This semantics change was requested by frank farmer.
+- Percent encoding checks enabled for URI query and fragment
+- Fix stray backslashes in font-family; CSS Unicode character escapes are
+  now properly resolved (although *only* in font-family). Thanks Takeshi Terada
+  for reporting.
+- Improve parseCDATA algorithm to take into account newline normalization
+- Account for browser confusion between Yen character and backslash in
+  Shift_JIS encoding. This fix generalizes to any other encoding which is not
+  a strict superset of printable ASCII. Thanks Takeshi Terada for reporting.
+- Fix missing configuration parameter in Generator calls. Thanks vs for the
+  partial patch.
+- Improved adherence to Unicode by checking for non-character codepoints.
+  Thanks Geoffrey Sneddon for reporting. This may result in degraded
+  performance for extremely large inputs.
+- Allow CSS property-value pair ''text-decoration: none''. Thanks Jochem Blok
+  for reporting.
+. Added HTMLPurifier_UnitConverter and HTMLPurifier_Length for convenient
+  handling of CSS-style lengths. HTMLPurifier_AttrDef_CSS_Length now uses
+  this class.
+. API of HTMLPurifier_AttrDef_CSS_Length changed from __construct($disable_negative)
+  to __construct($min, $max). __construct(true) is equivalent to
+  __construct('0').
+. Added HTMLPurifier_AttrDef_Switch class
+. Rename HTMLPurifier_HTMLModule_Tidy->construct() to setup() and bubble method
+  up inheritance hierarchy to HTMLPurifier_HTMLModule. All HTMLModules
+  get this called with the configuration object.  All modules now
+  use this rather than __construct(), although legacy code using constructors
+  will still work--the new format, however, lets modules access the
+  configuration object for HTML namespace dependant tweaks.
+. AttrDef_HTML_Pixels now takes a single construction parameter, pixels.
+. ConfigSchema data-structure heavily optimized; on average it uses a third
+  the memory it did previously. The interface has changed accordingly,
+  consult changes to HTMLPurifier_Config for details.
+. Variable parsing types now are magic integers instead of strings
+. Added benchmark for ConfigSchema
+. HTMLPurifier_Generator requires $config and $context parameters. If you
+  don't know what they should be, use HTMLPurifier_Config::createDefault()
+  and new HTMLPurifier_Context().
+. Printers now properly distinguish between output configuration, and
+  target configuration. This is not applicable to scripts using
+  the Printers for HTML Purifier related tasks.
+. HTML/CSS Printers must be primed with prepareGenerator($gen_config), otherwise
+  fatal errors will ensue.
+. URIFilter->prepare can return false in order to abort loading of the filter
+. Factory for AttrDef_URI implemented, URI#embedded to indicate URI that embeds
+  an external resource.
+. %URI.Munge functionality factored out into a post-filter class.
+. Added CurrentCSSProperty context variable during CSS validation
+
 3.1.0, released 2008-05-18
 # Unnecessary references to objects (vestiges of PHP4) removed from method
   signatures.  The following methods do not need references when assigning from
@@ -33,7 +201,8 @@ NEWS ( CHANGELOG and HISTORY )                                     HTMLPurifier
   and allows for version numbers like "3.1.0-dev".
 ! %HTML.Allowed deals gracefully with whitespace anywhere, anytime!
 ! HTML Purifier's URI handling is a lot more robust, with much stricter
-  validation checks and better percent encoding handling.
+  validation checks and better percent encoding handling. Thanks Gareth Heyes
+  for indicating security vulnerabilities from lax percent encoding.
 ! Bootstrap autoloader deals more robustly with classes that don't exist,
   preventing class_exists($class, true) from barfing.
 - InterchangeBuilder now alphabetizes its lists
@@ -669,3 +838,5 @@ NEWS ( CHANGELOG and HISTORY )                                     HTMLPurifier
   + Shorthand CSS properties
   + Table CSS properties
   + Deprecated attribute transformations
+
+    vim: et sw=4 sts=4

README

@@ -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

@@ -11,24 +11,29 @@ 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!
 
-- Implement validation for query and for fragment
+- Investigate how early internal structures can be accessed; this would
+  prevent structures from being parsed and serialized multiple times.
+- Built-in support for target="_blank" on all external links
+- Allow <a id="asdf" name="asdf">
+- Convert configuration to allow an arbitrary number of namespaces;
+  then rename as appropriate.
 
 FUTURE VERSIONS
 ---------------
 
-3.2 release [It's All About Trust] (floating)
+4.1 release [It's All About Trust] (floating)
  # Implement untrusted, dangerous elements/attributes
-    - Objects and Forms are especially wanted
  # Implement IDREF support (harder than it seems, since you cannot have
    IDREFs to non-existent IDs)
  # Frameset XHTML 1.0 and HTML 4.01 doctypes
- - Research and implement a "safe" version of the Object module
+ - Implement <area>
+ - Figure out how to simultaneously set %CSS.Trusted and %HTML.Trusted (?)
 
-3.3 release [Error'ed]
+4.2 release [Error'ed]
  # Error logging for filtering/cleanup procedures
  - XSS-attempt detection--certain errors are flagged XSS-like
 
-3.4 release [Do What I Mean, Not What I Say]
+4.3 release [Do What I Mean, Not What I Say]
  # Additional support for poorly written HTML
     - Microsoft Word HTML cleaning (i.e. MsoNormal, but research essential!)
     - Friendly strict handling of <address> (block -> <br>)
@@ -39,24 +44,21 @@ FUTURE VERSIONS
     contents should be dropped or not (currently, there's code that could do
     something like this if it didn't drop the inner text too.)
  - Remove <span> tags that don't do anything (no attributes)
- - Remove empty inline tags<i></i>
  - Append something to duplicate IDs so they're still usable (impl. note: the
    dupe detector would also need to detect the suffix as well)
  - Externalize inline CSS to promote clean HTML, proposed by Sander Tekelenburg
 
-4.0 release [Beyond HTML]
+5.0 release [Beyond HTML]
  # Legit token based CSS parsing (will require revamping almost every
    AttrDef class). Probably will use CSSTidy class?
  # More control over allowed CSS properties using a modularization
  # HTML 5 support
- # IRI 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]
- - AllowedAttributes and ForbiddenAttributes step on the toes of XML by
-   using periods; this needs to be changed.
+6.0 release [To XML and Beyond]
  - Extended HTML capabilities based on namespacing and tag transforms (COMPLEX)
     - Hooks for adding custom processors to custom namespaced tags and
       attributes, offer default implementation
@@ -104,6 +106,7 @@ 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
 
 Maintenance related (slightly boring)
  # CHMOD install script for PEAR installs
@@ -124,3 +127,5 @@ 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 @@
-3.1.0
+3.3.0

WHATSNEW

@@ -1,10 +1,6 @@
-HTML Purifier 3.1.0 is the second release series for HTML Purifier on PHP 5
-as well as a security update related to URIs. It shifts over to using
-autoload, and also includes support for the !important CSS modifier,
-display and visibility CSS properties with %CSS.AllowTricky, marquee with
-%HTML.Proprietary (had you scared for a moment, hmm?), a kses() wrapper,
-%CSS.AllowedProperties, %HTML.ForbiddenAttributes and
-%HTML.ForbiddenElements and a totally revamped ConfigDoc system. Since the
-release candidate, there have also been a number of stability fixes such as
-improved URI escaping, a change in serializer ID format, and a relaxed
-format for %HTML.Allowed. And as always, numerous bugfixes.
+HTML Purifier 3.3.0 is fixes a number of obscure bugs reported and fixed
+over a four month period.  It is probably the last release in the 3.x
+series.  Notable new features include support for the overflow CSS
+property; notable bugfixes include fixed YouTube rendering in certain
+versions of Firefox, CSSDefinition Printer, improved early PHP support
+and bugs in iconv.

WYSIWYG

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

benchmarks/ConfigSchema.php

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

benchmarks/Lexer.php

@@ -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

@@ -51,3 +51,5 @@
 <div style="text-align:center;">Click on photo to see HR version</div></div>
 </body>
 </html>
+
+<!-- vim: et sw=4 sts=4 -->

benchmarks/samples/Lexer/2.html

@@ -15,3 +15,5 @@ function rwt(el,ct,cd,sg){var e = window.encodeURIComponent ? encodeURIComponent
 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>
+
+<!-- vim: et sw=4 sts=4 -->

benchmarks/samples/Lexer/3.html

@@ -126,3 +126,5 @@ if (objAdMgr.isSlotAvailable("leaderboard")) {
 </body>
 
 </html>
+
+<!-- vim: et sw=4 sts=4 -->

benchmarks/samples/Lexer/4.html

@@ -538,3 +538,5 @@ Retrieved from "<a href="http://en.wikipedia.org/wiki/Tai_Chi_Chuan">http://en.w
 
 <!-- Served by srv25 in 0.089 secs. -->
 </body></html>
+
+<!-- vim: et sw=4 sts=4 -->

benchmarks/samples/Lexer/DISCLAIMER.txt

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

configdoc/generate.php

@@ -59,3 +59,4 @@ if (php_sapi_name() != 'cli') {
     echo 'Files generated successfully.';
 }
 
+// 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

@@ -19,7 +19,7 @@
     <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="1" />
+    <xsl:variable name="maxNumberAdjust" select="2" />
 
     <xsl:template match="/">
         <html lang="en" xml:lang="en">
@@ -231,3 +231,5 @@
     </xsl:template>
 
 </xsl:stylesheet>
+
+<!-- vim: et sw=4 sts=4 -->

configdoc/types.xml

@@ -12,3 +12,5 @@
   <type id="hash">Associative array</type>
   <type id="mixed">Mixed</type>
 </types>
+
+<!-- vim: et sw=4 sts=4 -->

configdoc/usage.xml

@@ -5,35 +5,40 @@
    <line>131</line>
   </file>
   <file name="HTMLPurifier/Lexer.php">
-   <line>85</line>
+   <line>81</line>
   </file>
   <file name="HTMLPurifier/Lexer/DirectLex.php">
-   <line>50</line>
-   <line>62</line>
-   <line>327</line>
+   <line>53</line>
+   <line>73</line>
+   <line>348</line>
   </file>
   <file name="HTMLPurifier/Strategy/RemoveForeignElements.php">
-   <line>44</line>
+   <line>47</line>
+  </file>
+ </directive>
+ <directive id="CSS.MaxImgLength">
+  <file name="HTMLPurifier/CSSDefinition.php">
+   <line>157</line>
   </file>
  </directive>
  <directive id="CSS.Proprietary">
   <file name="HTMLPurifier/CSSDefinition.php">
-   <line>202</line>
+   <line>214</line>
   </file>
  </directive>
  <directive id="CSS.AllowTricky">
   <file name="HTMLPurifier/CSSDefinition.php">
-   <line>206</line>
+   <line>218</line>
   </file>
  </directive>
  <directive id="CSS.AllowImportant">
   <file name="HTMLPurifier/CSSDefinition.php">
-   <line>210</line>
+   <line>222</line>
   </file>
  </directive>
  <directive id="CSS.AllowedProperties">
   <file name="HTMLPurifier/CSSDefinition.php">
-   <line>262</line>
+   <line>275</line>
   </file>
  </directive>
  <directive id="Cache.DefinitionImpl">
@@ -63,106 +68,116 @@
  </directive>
  <directive id="Core.Encoding">
   <file name="HTMLPurifier/Encoder.php">
-   <line>281</line>
-   <line>305</line>
+   <line>267</line>
+   <line>300</line>
   </file>
  </directive>
  <directive id="Test.ForceNoIconv">
   <file name="HTMLPurifier/Encoder.php">
-   <line>283</line>
-   <line>310</line>
+   <line>272</line>
+   <line>308</line>
   </file>
  </directive>
  <directive id="Core.EscapeNonASCIICharacters">
   <file name="HTMLPurifier/Encoder.php">
-   <line>307</line>
-  </file>
- </directive>
- <directive id="Core.MaintainLineNumbers">
-  <file name="HTMLPurifier/ErrorCollector.php">
-   <line>81</line>
-  </file>
-  <file name="HTMLPurifier/Lexer.php">
-   <line>82</line>
-  </file>
-  <file name="HTMLPurifier/Lexer/DirectLex.php">
-   <line>45</line>
+   <line>304</line>
   </file>
  </directive>
  <directive id="Output.CommentScriptContents">
   <file name="HTMLPurifier/Generator.php">
-   <line>41</line>
+   <line>45</line>
+  </file>
+ </directive>
+ <directive id="Output.SortAttr">
+  <file name="HTMLPurifier/Generator.php">
+   <line>46</line>
   </file>
  </directive>
  <directive id="Output.TidyFormat">
   <file name="HTMLPurifier/Generator.php">
-   <line>70</line>
+   <line>75</line>
   </file>
  </directive>
  <directive id="Output.Newline">
   <file name="HTMLPurifier/Generator.php">
-   <line>84</line>
+   <line>89</line>
   </file>
  </directive>
  <directive id="HTML.BlockWrapper">
   <file name="HTMLPurifier/HTMLDefinition.php">
-   <line>213</line>
+   <line>222</line>
   </file>
  </directive>
  <directive id="HTML.Parent">
   <file name="HTMLPurifier/HTMLDefinition.php">
-   <line>221</line>
+   <line>230</line>
   </file>
  </directive>
  <directive id="HTML.AllowedElements">
   <file name="HTMLPurifier/HTMLDefinition.php">
-   <line>238</line>
+   <line>247</line>
   </file>
  </directive>
  <directive id="HTML.AllowedAttributes">
   <file name="HTMLPurifier/HTMLDefinition.php">
-   <line>239</line>
+   <line>248</line>
   </file>
  </directive>
  <directive id="HTML.Allowed">
   <file name="HTMLPurifier/HTMLDefinition.php">
-   <line>242</line>
+   <line>251</line>
   </file>
  </directive>
  <directive id="HTML.ForbiddenElements">
   <file name="HTMLPurifier/HTMLDefinition.php">
-   <line>328</line>
+   <line>337</line>
   </file>
  </directive>
  <directive id="HTML.ForbiddenAttributes">
   <file name="HTMLPurifier/HTMLDefinition.php">
-   <line>329</line>
+   <line>338</line>
   </file>
  </directive>
  <directive id="HTML.Trusted">
   <file name="HTMLPurifier/HTMLModuleManager.php">
-   <line>198</line>
+   <line>202</line>
   </file>
   <file name="HTMLPurifier/Lexer.php">
-   <line>238</line>
+   <line>258</line>
+  </file>
+  <file name="HTMLPurifier/HTMLModule/Image.php">
+   <line>27</line>
   </file>
   <file name="HTMLPurifier/Lexer/DirectLex.php">
-   <line>34</line>
+   <line>36</line>
+  </file>
+  <file name="HTMLPurifier/Strategy/RemoveForeignElements.php">
+   <line>23</line>
   </file>
  </directive>
  <directive id="HTML.AllowedModules">
   <file name="HTMLPurifier/HTMLModuleManager.php">
-   <line>205</line>
+   <line>209</line>
   </file>
  </directive>
  <directive id="HTML.CoreModules">
   <file name="HTMLPurifier/HTMLModuleManager.php">
-   <line>206</line>
+   <line>210</line>
   </file>
  </directive>
  <directive id="HTML.Proprietary">
   <file name="HTMLPurifier/HTMLModuleManager.php">
-   <line>220</line>
+   <line>221</line>
+  </file>
+ </directive>
+ <directive id="HTML.SafeObject">
+  <file name="HTMLPurifier/HTMLModuleManager.php">
+   <line>226</line>
+  </file>
+ </directive>
+ <directive id="HTML.SafeEmbed">
+  <file name="HTMLPurifier/HTMLModuleManager.php">
+   <line>229</line>
   </file>
  </directive>
  <directive id="Attr.IDBlacklist">
@@ -177,30 +192,35 @@
  </directive>
  <directive id="Core.LexerImpl">
   <file name="HTMLPurifier/Lexer.php">
-   <line>70</line>
+   <line>76</line>
+  </file>
+ </directive>
+ <directive id="Core.MaintainLineNumbers">
+  <file name="HTMLPurifier/Lexer.php">
+   <line>80</line>
+  </file>
+  <file name="HTMLPurifier/Lexer/DirectLex.php">
+   <line>48</line>
   </file>
  </directive>
  <directive id="Core.ConvertDocumentToFragment">
   <file name="HTMLPurifier/Lexer.php">
-   <line>230</line>
+   <line>267</line>
   </file>
  </directive>
  <directive id="URI.Host">
   <file name="HTMLPurifier/URIDefinition.php">
-   <line>57</line>
-  </file>
-  <file name="HTMLPurifier/URIFilter/DisableExternal.php">
-   <line>8</line>
+   <line>64</line>
   </file>
  </directive>
  <directive id="URI.Base">
   <file name="HTMLPurifier/URIDefinition.php">
-   <line>58</line>
+   <line>65</line>
   </file>
  </directive>
  <directive id="URI.DefaultScheme">
   <file name="HTMLPurifier/URIDefinition.php">
-   <line>65</line>
+   <line>72</line>
   </file>
  </directive>
  <directive id="URI.AllowedSchemes">
@@ -215,12 +235,7 @@
  </directive>
  <directive id="URI.Disable">
   <file name="HTMLPurifier/AttrDef/URI.php">
-   <line>23</line>
-  </file>
- </directive>
- <directive id="URI.Munge">
-  <file name="HTMLPurifier/AttrDef/URI.php">
-   <line>68</line>
+   <line>28</line>
   </file>
  </directive>
  <directive id="Core.ColorKeywords">
@@ -275,14 +290,19 @@
    <line>19</line>
   </file>
  </directive>
+ <directive id="Attr.DefaultImageAlt">
+  <file name="HTMLPurifier/AttrTransform/ImgRequired.php">
+   <line>25</line>
+  </file>
+ </directive>
  <directive id="Attr.DefaultInvalidImageAlt">
   <file name="HTMLPurifier/AttrTransform/ImgRequired.php">
-   <line>27</line>
+   <line>32</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">
@@ -305,6 +325,17 @@
    <line>123</line>
   </file>
  </directive>
+ <directive id="HTML.MaxImgLength">
+  <file name="HTMLPurifier/HTMLModule/Image.php">
+   <line>14</line>
+  </file>
+  <file name="HTMLPurifier/HTMLModule/SafeEmbed.php">
+   <line>13</line>
+  </file>
+  <file name="HTMLPurifier/HTMLModule/SafeObject.php">
+   <line>19</line>
+  </file>
+ </directive>
  <directive id="HTML.TidyLevel">
   <file name="HTMLPurifier/HTMLModule/Tidy.php">
    <line>45</line>
@@ -332,12 +363,12 @@
  </directive>
  <directive id="Core.DirectLexLineNumberSyncInterval">
   <file name="HTMLPurifier/Lexer/DirectLex.php">
-   <line>59</line>
+   <line>70</line>
   </file>
  </directive>
  <directive id="Core.EscapeInvalidTags">
   <file name="HTMLPurifier/Strategy/MakeWellFormed.php">
-   <line>22</line>
+   <line>45</line>
   </file>
   <file name="HTMLPurifier/Strategy/RemoveForeignElements.php">
    <line>19</line>
@@ -345,12 +376,12 @@
  </directive>
  <directive id="Core.RemoveScriptContents">
   <file name="HTMLPurifier/Strategy/RemoveForeignElements.php">
-   <line>22</line>
+   <line>25</line>
   </file>
  </directive>
  <directive id="Core.HiddenElements">
   <file name="HTMLPurifier/Strategy/RemoveForeignElements.php">
-   <line>23</line>
+   <line>26</line>
   </file>
  </directive>
  <directive id="URI.HostBlacklist">
@@ -358,4 +389,14 @@
    <line>8</line>
   </file>
  </directive>
+ <directive id="URI.MungeResources">
+  <file name="HTMLPurifier/URIFilter/Munge.php">
+   <line>14</line>
+  </file>
+ </directive>
+ <directive id="URI.MungeSecretKey">
+  <file name="HTMLPurifier/URIFilter/Munge.php">
+   <line>15</line>
+  </file>
+ </directive>
 </usage>

docs/dev-advanced-api.html

@@ -213,6 +213,6 @@ the usual things required are:</p>
 
 <p>See <code>HTMLPurifier/HTMLModule.php</code> for details.</p>
 
-<div id="version">$Id$</div>
-
 </body></html>
+
+<!-- vim: et sw=4 sts=4 -->

docs/dev-code-quality.txt

@@ -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-schema.html

@@ -239,15 +239,15 @@ Test.Example</pre>
       object; users have a little bit of leeway when setting configuration
       values (for example, a lookup value can be specified as a list;
       HTML Purifier will flip it as necessary.) These types are defined
-      in <a href="http://htmlpurifier.org/svnroot/htmlpurifier/trunk/library/HTMLPurifier/VarParser.php">
+      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://htmlpurifier.org/svnroot/htmlpurifier/trunk/library/HTMLPurifier/ConfigSchema/InterchangeBuilder.php">
+      consult <a href="http://repo.or.cz/w/htmlpurifier.git?a=blob;hb=HEAD;f=library/HTMLPurifier/ConfigSchema/InterchangeBuilder.php">
       library/HTMLPurifier/ConfigSchema/InterchangeBuilder.php</a>, as well
-      as <a href="http://htmlpurifier.org/svnroot/htmlpurifier/trunk/library/HTMLPurifier/ConfigSchema/Interchange/Directive.php">
+      as <a href="http://repo.or.cz/w/htmlpurifier.git?a=blob;hb=HEAD;f=library/HTMLPurifier/ConfigSchema/Interchange/Directive.php">
       library/HTMLPurifier/ConfigSchema/Interchange/Directive.php</a> for
       the semantics of the parsed values.
     </p>
@@ -272,7 +272,7 @@ Test.Example</pre>
 
     <p>
       All directive files go through a rigorous validation process
-      through <a href="http://htmlpurifier.org/svnroot/htmlpurifier/trunk/library/HTMLPurifier/ConfigSchema/">
+      through <a href="http://repo.or.cz/w/htmlpurifier.git?a=blob;hb=HEAD;f=library/HTMLPurifier/ConfigSchema/Validator.php">
       library/HTMLPurifier/ConfigSchema/Validator.php</a>, as well
       as some basic checks during building. While
       listing every error out here is out-of-scope for this document, we
@@ -339,7 +339,7 @@ Test.Example</pre>
       The most difficult part is translating the Interchange member variable (valueAliases)
       into a directive file key (VALUE-ALIASES), but there's a one-to-one
       correspondence currently. If the two formats diverge, any discrepancies
-      will be described in <a href="http://htmlpurifier.org/svnroot/htmlpurifier/trunk/library/HTMLPurifier/ConfigSchema/InterchangeBuilder.php">
+      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>
 
@@ -370,7 +370,7 @@ Test.Example</pre>
       data. There is also an XML serializer, which is used to build documentation.
     </p>
 
-    <div id="version">$Id$</div>
-
   </body>
 </html>
+
+<!-- vim: et sw=4 sts=4 -->

docs/dev-flush.html

@@ -62,6 +62,6 @@
     do.
 </p>
 
-<div id="version">$Id$</div>
-
 </body></html>
+
+<!-- vim: et sw=4 sts=4 -->

docs/dev-includes.txt

@@ -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

@@ -77,6 +77,6 @@ help you find the correct functionality more quickly.  Here they are:</p>
 
 </dl>
 
-<div id="version">$Id$</div>
-
 </body></html>
+
+<!-- vim: et sw=4 sts=4 -->

docs/dev-optimization.html

@@ -27,6 +27,6 @@ that itch, put it here!</p>
     <li>Parallelize strategies</li>
 </ul>
 
-<div id="version">$Id$</div>
-
 </body></html>
+
+<!-- vim: et sw=4 sts=4 -->

docs/dev-progress.html

@@ -303,6 +303,6 @@ Mozilla on inside and needs -moz-outline, no IE support.</td></tr>
 
 </table>
 
-<div id="version">$Id$</div>
-
 </body></html>
+
+<!-- vim: et sw=4 sts=4 -->

docs/enduser-customize.html

@@ -213,7 +213,7 @@ $def = $config->getHTMLDefinition(true);</pre>
 <pre>$config = HTMLPurifier_Config::createDefault();
 $config->set('HTML', 'DefinitionID', 'enduser-customize.html tutorial');
 $config->set('HTML', 'DefinitionRev', 1);
-<strong>$config->set('Core', 'DefinitionCache', null); // remove this later!</strong>
+<strong>$config->set('Cache', 'DefinitionImpl', null); // remove this later!</strong>
 $def = $config->getHTMLDefinition(true);</pre>
 
 <p>
@@ -269,7 +269,7 @@ $def = $config->getHTMLDefinition(true);</pre>
 <pre>$config = HTMLPurifier_Config::createDefault();
 $config->set('HTML', 'DefinitionID', 'enduser-customize.html tutorial');
 $config->set('HTML', 'DefinitionRev', 1);
-$config->set('Core', 'DefinitionCache', null); // remove this later!
+$config->set('Cache', 'DefinitionImpl', null); // remove this later!
 $def = $config->getHTMLDefinition(true);
 <strong>$def->addAttribute('a', 'target', 'Enum#_blank,_self,_target,_top');</strong></pre>
 
@@ -372,10 +372,10 @@ $def = $config->getHTMLDefinition(true);
 
 <p>
   For a complete list, consult
-  <a href="http://htmlpurifier.org/svnroot/htmlpurifier/trunk/library/HTMLPurifier/AttrTypes.php"><code>library/HTMLPurifier/AttrTypes.php</code></a>;
+  <a href="http://repo.or.cz/w/htmlpurifier.git?a=blob;hb=HEAD;f=library/HTMLPurifier/AttrTypes.php"><code>library/HTMLPurifier/AttrTypes.php</code></a>;
   more information on attributes that accept parameters can be found on their
   respective includes in
-  <a href="http://htmlpurifier.org/svnroot/htmlpurifier/trunk/library/HTMLPurifier/AttrDef/"><code>library/HTMLPurifier/AttrDef</code></a>.
+  <a href="http://repo.or.cz/w/htmlpurifier.git?a=tree;hb=HEAD;f=library/HTMLPurifier/AttrDef"><code>library/HTMLPurifier/AttrDef</code></a>.
 </p>
 
 <p>
@@ -387,7 +387,7 @@ $def = $config->getHTMLDefinition(true);
 <pre>$config = HTMLPurifier_Config::createDefault();
 $config->set('HTML', 'DefinitionID', 'enduser-customize.html tutorial');
 $config->set('HTML', 'DefinitionRev', 1);
-$config->set('Core', 'DefinitionCache', null); // remove this later!
+$config->set('Cache', 'DefinitionImpl', null); // remove this later!
 $def = $config->getHTMLDefinition(true);
 <strong>$def->addAttribute('a', 'target', new HTMLPurifier_AttrDef_Enum(
   array('_blank','_self','_target','_top')
@@ -734,7 +734,7 @@ $def = $config->getHTMLDefinition(true);
 <pre>$config = HTMLPurifier_Config::createDefault();
 $config->set('HTML', 'DefinitionID', 'enduser-customize.html tutorial');
 $config->set('HTML', 'DefinitionRev', 1);
-$config->set('Core', 'DefinitionCache', null); // remove this later!
+$config->set('Cache', 'DefinitionImpl', null); // remove this later!
 $def = $config->getHTMLDefinition(true);
 $def->addAttribute('a', 'target', new HTMLPurifier_AttrDef_Enum(
   array('_blank','_self','_target','_top')
@@ -764,7 +764,7 @@ $form->excludes = array('form' => true);</strong></pre>
 <p>
   And that's all there is to it! Implementing the rest of the form
   module is left as an exercise to the user; to see more examples
-  check the <a href="http://htmlpurifier.org/svnroot/htmlpurifier/trunk/library/HTMLPurifier/HTMLModule/"><code>library/HTMLPurifier/HTMLModule/</code></a> directory
+  check the <a href="http://repo.or.cz/w/htmlpurifier.git?a=tree;hb=HEAD;f=library/HTMLPurifier/HTMLModule"><code>library/HTMLPurifier/HTMLModule/</code></a> directory
   in your local HTML Purifier installation.
 </p>
 
@@ -789,10 +789,10 @@ $form->excludes = array('form' => true);</strong></pre>
 </p>
 
 <ul>
-  <li><a href="http://htmlpurifier.org/svnroot/htmlpurifier/trunk/library/HTMLPurifier/HTMLModule.php"><code>library/HTMLPurifier/HTMLModule.php</code></a></li>
-  <li><a href="http://htmlpurifier.org/svnroot/htmlpurifier/trunk/library/HTMLPurifier/ElementDef.php"><code>library/HTMLPurifier/ElementDef.php</code></a></li>
+  <li><a href="http://repo.or.cz/w/htmlpurifier.git?a=blob;hb=HEAD;f=library/HTMLPurifier/HTMLModule.php"><code>library/HTMLPurifier/HTMLModule.php</code></a></li>
+  <li><a href="http://repo.or.cz/w/htmlpurifier.git?a=blob;hb=HEAD;f=library/HTMLPurifier/ElementDef.php"><code>library/HTMLPurifier/ElementDef.php</code></a></li>
 </ul>
 
-<div id="version">$Id: enduser-tidy.html 1158 2007-06-18 19:26:29Z Edward $</div>
-
 </body></html>
+
+<!-- vim: et sw=4 sts=4 -->

docs/enduser-id.html

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

docs/enduser-overview.txt

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

docs/enduser-security.txt

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

docs/enduser-slow.html

@@ -115,3 +115,5 @@ if you decide to do that! Especially if you port HTML Purifier to C++.
 
 </body>
 </html>
+
+<!-- vim: et sw=4 sts=4 -->

docs/enduser-tidy.html

@@ -225,6 +225,6 @@ and if that still doesn't satisfy your appetite, do some fine-tuning.
 Other than that, don't worry about it: this all works silently and
 effectively in the background.</p>
 
-<div id="version">$Id$</div>
-
 </body></html>
+
+<!-- vim: et sw=4 sts=4 -->

docs/enduser-uri-filter.html

@@ -130,30 +130,26 @@
 </p>
 
 <p>
-  Let's suppose I wanted to write a filter that de-internationalized domain
-  names by converting them to <a href="http://en.wikipedia.org/wiki/Punycode">Punycode</a>.
-  Assuming that <code>punycode_encode($input)</code> converts <code>$input</code> to
-  Punycode and returns <code>false</code> on failure:
+  Let's suppose I wanted to write a filter that converted links with a
+  custom <code>image</code> scheme to its corresponding real path on
+  our website:
 </p>
 
-<pre>class HTMLPurifier_URIFilter_ConvertIDNToPunycode extends HTMLPurifier_URIFilter
+<pre>class HTMLPurifier_URIFilter_TransformImageScheme extends HTMLPurifier_URIFilter
 {
-    public $name = 'ConvertIDNToPunycode';
+    public $name = 'TransformImageScheme';
     public function filter(&$uri, $config, $context) {
-        if (is_null($uri->host)) return true;
-        if ($uri->host == utf8_decode($uri->host)) {
-            // is ASCII, abort
-            return true;
-        }
-        $host = punycode_encode($uri->host);
-        if ($host === false) return false;
-        $uri->host = $host;
+        if ($uri->scheme !== 'image') return true;
+        $img_name = $uri->path;
+        // Overwrite the previous URI object
+        $uri = new HTMLPurifier_URI('http', null, null, null, '/img/' . $img_name . '.png', null, null);
         return true;
     }
 }</pre>
 
 <p>
-  Notice I did not <code>return $uri;</code>.
+  Notice I did not <code>return $uri;</code>. This filter would turn
+  <code>image:Foo</code> into <code>/img/Foo.png</code>.
 </p>
 
 <h2>Activating your filter</h2>
@@ -186,16 +182,35 @@ $uri->registerFilter(new HTMLPurifier_URIFilter_<strong>NameOfFilter</strong>())
   is set to true.
 </p>
 
+<h2>Post-filter</h2>
+
+<p>
+    Remember our TransformImageScheme filter? That filter acted before we had
+    performed scheme validation; otherwise, the URI would have been filtered
+    out when it was discovered that there was no image scheme. Well, a post-filter
+    is run after scheme specific validation, so it's ideal for bulk
+    post-processing of URIs, including munging. To specify a URI as a post-filter,
+    set the <code>$post</code> member variable to TRUE.
+</p>
+
+<pre>class HTMLPurifier_URIFilter_MyPostFilter extends HTMLPurifier_URIFilter
+{
+    public $name = 'MyPostFilter';
+    public $post = true;
+    // ... extra code here
+}
+</pre>
+
 <h2>Examples</h2>
 
 <p>
   Check the
-  <a href="http://htmlpurifier.org/svnroot/htmlpurifier/trunk/library/HTMLPurifier/URIFilter/">URIFilter</a>
-  directory for more implementation examples, and see <a href="http://htmlpurifier.org/svnroot/htmlpurifier/trunk/docs/proposal-new-directives.txt">the
+  <a href="http://repo.or.cz/w/htmlpurifier.git?a=tree;hb=HEAD;f=library/HTMLPurifier/URIFilter">URIFilter</a>
+  directory for more implementation examples, and see <a href="proposal-new-directives.txt">the
   new directives proposal document</a> for ideas on what could be implemented
   as a filter.
 </p>
 
-<div id="version">$Id$</div>
-
 </body></html>
+
+<!-- vim: et sw=4 sts=4 -->

docs/enduser-utf8.html

@@ -118,9 +118,8 @@ there are now many character encodings floating around.</p>
             see a page on the web, chances are it's encoded in one
             of these encodings.</li>
         <li><strong>Unicode-based encodings</strong> implement the
-            Unicode standard and include UTF-8, UCS-2 and UTF-16.
-            They go beyond 8-bits (the first two are variable length,
-            while the second one uses 16-bits), and support almost
+            Unicode standard and include UTF-8, UTF-16 and UTF-32/UCS-4.
+            They go beyond 8-bits and support almost
             every language in the world. UTF-8 is gaining traction
             as the dominant international encoding of the web.</li>
     </ul>
@@ -482,7 +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
@@ -527,7 +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
@@ -585,13 +584,15 @@ disappeared off the web, so I am linking to the Web Archive copy.)</p>
 <h4 id="whyutf8-forms-urlencoded"><code>application/x-www-form-urlencoded</code></h4>
 
 <p>This is the Content-Type that GET requests must use, and POST requests
-use by default. It involves the ubiquituous percent encoding format that
+use by default. It involves the ubiquitous percent encoding format that
 looks something like: <code>%C3%86</code>. There is no official way of
 determining the character encoding of such a request, since the percent
 encoding operates on a byte level, so it is usually assumed that it
 is the same as the encoding the page containing the form was submitted
-in. You'll run into very few problems if you only use characters in
-the character encoding you chose.</p>
+in. (<a href="http://tools.ietf.org/html/rfc3986#section-2.5">RFC 3986</a>
+recommends that textual identifiers be translated to UTF-8; however, browser
+compliance is spotty.) You'll run into very few problems
+if you only use characters in the character encoding you chose.</p>
 
 <p>However, once you start adding characters outside of your encoding
 (and this is a lot more common than you may think: take curly
@@ -673,7 +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
@@ -769,7 +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
@@ -789,7 +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>.
@@ -916,8 +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>
 
@@ -927,7 +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).
@@ -940,11 +941,11 @@ 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
@@ -971,7 +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>
 
@@ -1034,7 +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
@@ -1054,3 +1055,5 @@ a more in-depth look into character sets and encodings.</p>
 
 </body>
 </html>
+
+<!-- vim: et sw=4 sts=4 -->

docs/enduser-youtube.html

@@ -70,7 +70,7 @@ into your documents. YouTube's code goes like this:</p>
 class=&quot;embed-youtube&quot;&gt;AyPzM5WK8ys&lt;/span&gt;</code> your
 application can reconstruct the full object from this small snippet that
 passes through HTML Purifier <em>unharmed</em>.
-<a href="http://htmlpurifier.org/svnroot/htmlpurifier/trunk/library/HTMLPurifier/Filter/YouTube.php">Show me the code!</a></p>
+<a href="http://repo.or.cz/w/htmlpurifier.git?a=blob;hb=HEAD;f=library/HTMLPurifier/Filter/YouTube.php">Show me the code!</a></p>
 
 <p>And the corresponding usage:</p>
 
@@ -148,3 +148,5 @@ with the core!</p>
 
 </body>
 </html>
+
+<!-- vim: et sw=4 sts=4 -->

docs/examples/basic.php

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

docs/fixquotes.htc

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

docs/index.html

@@ -98,8 +98,8 @@ the code. They may be upgraded to HTML files or stay as TXT scratchpads.</p>
 <table class="table">
 
 <thead><tr>
-    <th width="10%">Type</th>
-    <th width="20%">Name</th>
+    <th style="width:10%">Type</th>
+    <th style="width:20%">Name</th>
     <th>Description</th>
 </tr></thead>
 
@@ -175,6 +175,7 @@ the code. They may be upgraded to HTML files or stay as TXT scratchpads.</p>
 
 </table>
 
-<div id="version">$Id$</div>
 </body>
 </html>
+
+<!-- vim: et sw=4 sts=4 -->

docs/proposal-colors.html

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

docs/proposal-config.txt

@@ -19,3 +19,5 @@ Definition objects are complex datatypes influenced by their respective
 directive namespaces (HTMLDefinition with HTML and CSSDefinition with CSS).
 If any of these directives is updated, HTML Purifier forces the definition
 to be regenerated.
+
+    vim: et sw=4 sts=4

docs/proposal-css-extraction.txt

@@ -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

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

docs/proposal-filter-levels.txt

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

docs/proposal-language.txt

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

docs/proposal-new-directives.txt

@@ -41,3 +41,4 @@ implemented, give us a ring, and we'll move it up the priority chain.
     absolute DNS.  While this is actually the preferred method according to
     the RFC, most people opt to use a relative domain name relative to . (root).
 
+    vim: et sw=4 sts=4

docs/ref-content-models.txt

@@ -46,3 +46,5 @@ is eliminated completely, in the latter case, the text of the node
 would is preserved (as the parent node does allow PCDATA).  Custom
 content model implementations probably are not the best way of handling
 these cases, instead, node bubbling should be implemented instead.
+
+    vim: et sw=4 sts=4

docs/ref-css-length.txt

@@ -26,3 +26,5 @@ Watch out: font-sizes can also be nested to get successively larger
 (although I do not relish having to keep track of context font-sizes,
 this may be necessary, especially for some of the more advanced features
 for preventing things like white on white).
+
+    vim: et sw=4 sts=4

docs/ref-devnetwork.html

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

docs/ref-html-modularization.txt

@@ -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

@@ -22,3 +22,5 @@ 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

@@ -163,3 +163,5 @@ div.segment {width:250px; float:left; margin-top:1em;}
 
 </body>
 </html>
+
+<!-- vim: et sw=4 sts=4 -->

docs/specimens/jochem-blok-word.html

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

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

@@ -72,3 +72,5 @@ title="Join Windows Live to share photos using Windows Live Photo E-mail.">Onlin
 pictures are available for 30 days. <A style="COLOR: #0088e4"
 href="http://g.msn.com/5meen_us/175">Get Windows Live Mail desktop to create
 your own photo e-mails. </A></SPAN></NOBR></DIV></BODY></HTML>
+
+<!-- vim: et sw=4 sts=4 -->

docs/style.css

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

extras/ConfigDoc/HTMLXSLTProcessor.php

@@ -83,3 +83,4 @@ class ConfigDoc_HTMLXSLTProcessor
 
 }
 
+// vim: et sw=4 sts=4

extras/FSTools.php

@@ -153,3 +153,5 @@ class FSTools
     }
 
 }
+
+// vim: et sw=4 sts=4

extras/FSTools/File.php

@@ -122,3 +122,5 @@ class FSTools_File
     }
 
 }
+
+// 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

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

extras/HTMLPurifierExtras.php

@@ -25,3 +25,5 @@ class HTMLPurifierExtras
     }
 
 }
+
+// vim: et sw=4 sts=4

extras/README

@@ -28,3 +28,5 @@ the filesystem. It currently consists of two classes:
   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

@@ -17,3 +17,5 @@ if (function_exists('spl_autoload_register') && function_exists('spl_autoload_un
         return HTMLPurifier_Bootstrap::autoload($class);
     }
 }
+
+// vim: et sw=4 sts=4

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

@@ -7,7 +7,7 @@
  * 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 3.1.0
+ * @version 3.3.0
  *
  * @warning
  *      You must *not* include any other HTML Purifier files before this file,
@@ -29,7 +29,6 @@ require 'HTMLPurifier/Definition.php';
 require 'HTMLPurifier/CSSDefinition.php';
 require 'HTMLPurifier/ChildDef.php';
 require 'HTMLPurifier/Config.php';
-require 'HTMLPurifier/ConfigDef.php';
 require 'HTMLPurifier/ConfigSchema.php';
 require 'HTMLPurifier/ContentSets.php';
 require 'HTMLPurifier/Context.php';
@@ -42,6 +41,7 @@ require 'HTMLPurifier/Encoder.php';
 require 'HTMLPurifier/EntityLookup.php';
 require 'HTMLPurifier/EntityParser.php';
 require 'HTMLPurifier/ErrorCollector.php';
+require 'HTMLPurifier/ErrorStruct.php';
 require 'HTMLPurifier/Exception.php';
 require 'HTMLPurifier/Filter.php';
 require 'HTMLPurifier/Generator.php';
@@ -52,8 +52,11 @@ require 'HTMLPurifier/IDAccumulator.php';
 require 'HTMLPurifier/Injector.php';
 require 'HTMLPurifier/Language.php';
 require 'HTMLPurifier/LanguageFactory.php';
+require 'HTMLPurifier/Length.php';
 require 'HTMLPurifier/Lexer.php';
 require 'HTMLPurifier/PercentEncoder.php';
+require 'HTMLPurifier/PropertyList.php';
+require 'HTMLPurifier/PropertyListIterator.php';
 require 'HTMLPurifier/Strategy.php';
 require 'HTMLPurifier/StringHash.php';
 require 'HTMLPurifier/StringHashParser.php';
@@ -66,12 +69,14 @@ require 'HTMLPurifier/URIFilter.php';
 require 'HTMLPurifier/URIParser.php';
 require 'HTMLPurifier/URIScheme.php';
 require 'HTMLPurifier/URISchemeRegistry.php';
+require 'HTMLPurifier/UnitConverter.php';
 require 'HTMLPurifier/VarParser.php';
 require 'HTMLPurifier/VarParserException.php';
 require 'HTMLPurifier/AttrDef/CSS.php';
 require 'HTMLPurifier/AttrDef/Enum.php';
 require 'HTMLPurifier/AttrDef/Integer.php';
 require 'HTMLPurifier/AttrDef/Lang.php';
+require 'HTMLPurifier/AttrDef/Switch.php';
 require 'HTMLPurifier/AttrDef/Text.php';
 require 'HTMLPurifier/AttrDef/URI.php';
 require 'HTMLPurifier/AttrDef/CSS/Number.php';
@@ -106,6 +111,7 @@ require 'HTMLPurifier/AttrDef/URI/Host.php';
 require 'HTMLPurifier/AttrDef/URI/IPv4.php';
 require 'HTMLPurifier/AttrDef/URI/IPv6.php';
 require 'HTMLPurifier/AttrDef/URI/Email/SimpleCheck.php';
+require 'HTMLPurifier/AttrTransform/Background.php';
 require 'HTMLPurifier/AttrTransform/BdoDir.php';
 require 'HTMLPurifier/AttrTransform/BgColor.php';
 require 'HTMLPurifier/AttrTransform/BoolToCSS.php';
@@ -113,10 +119,15 @@ require 'HTMLPurifier/AttrTransform/Border.php';
 require 'HTMLPurifier/AttrTransform/EnumToCSS.php';
 require 'HTMLPurifier/AttrTransform/ImgRequired.php';
 require 'HTMLPurifier/AttrTransform/ImgSpace.php';
+require 'HTMLPurifier/AttrTransform/Input.php';
 require 'HTMLPurifier/AttrTransform/Lang.php';
 require 'HTMLPurifier/AttrTransform/Length.php';
 require 'HTMLPurifier/AttrTransform/Name.php';
+require 'HTMLPurifier/AttrTransform/SafeEmbed.php';
+require 'HTMLPurifier/AttrTransform/SafeObject.php';
+require 'HTMLPurifier/AttrTransform/SafeParam.php';
 require 'HTMLPurifier/AttrTransform/ScriptRequired.php';
+require 'HTMLPurifier/AttrTransform/Textarea.php';
 require 'HTMLPurifier/ChildDef/Chameleon.php';
 require 'HTMLPurifier/ChildDef/Custom.php';
 require 'HTMLPurifier/ChildDef/Empty.php';
@@ -124,9 +135,6 @@ require 'HTMLPurifier/ChildDef/Required.php';
 require 'HTMLPurifier/ChildDef/Optional.php';
 require 'HTMLPurifier/ChildDef/StrictBlockquote.php';
 require 'HTMLPurifier/ChildDef/Table.php';
-require 'HTMLPurifier/ConfigDef/Directive.php';
-require 'HTMLPurifier/ConfigDef/DirectiveAlias.php';
-require 'HTMLPurifier/ConfigDef/Namespace.php';
 require 'HTMLPurifier/DefinitionCache/Decorator.php';
 require 'HTMLPurifier/DefinitionCache/Null.php';
 require 'HTMLPurifier/DefinitionCache/Serializer.php';
@@ -135,15 +143,19 @@ require 'HTMLPurifier/DefinitionCache/Decorator/Memory.php';
 require 'HTMLPurifier/HTMLModule/Bdo.php';
 require 'HTMLPurifier/HTMLModule/CommonAttributes.php';
 require 'HTMLPurifier/HTMLModule/Edit.php';
+require 'HTMLPurifier/HTMLModule/Forms.php';
 require 'HTMLPurifier/HTMLModule/Hypertext.php';
 require 'HTMLPurifier/HTMLModule/Image.php';
 require 'HTMLPurifier/HTMLModule/Legacy.php';
 require 'HTMLPurifier/HTMLModule/List.php';
+require 'HTMLPurifier/HTMLModule/Name.php';
 require 'HTMLPurifier/HTMLModule/NonXMLCommonAttributes.php';
 require 'HTMLPurifier/HTMLModule/Object.php';
 require 'HTMLPurifier/HTMLModule/Presentation.php';
 require 'HTMLPurifier/HTMLModule/Proprietary.php';
 require 'HTMLPurifier/HTMLModule/Ruby.php';
+require 'HTMLPurifier/HTMLModule/SafeEmbed.php';
+require 'HTMLPurifier/HTMLModule/SafeObject.php';
 require 'HTMLPurifier/HTMLModule/Scripting.php';
 require 'HTMLPurifier/HTMLModule/StyleAttribute.php';
 require 'HTMLPurifier/HTMLModule/Tables.php';
@@ -151,14 +163,18 @@ require 'HTMLPurifier/HTMLModule/Target.php';
 require 'HTMLPurifier/HTMLModule/Text.php';
 require 'HTMLPurifier/HTMLModule/Tidy.php';
 require 'HTMLPurifier/HTMLModule/XMLCommonAttributes.php';
+require 'HTMLPurifier/HTMLModule/Tidy/Name.php';
 require 'HTMLPurifier/HTMLModule/Tidy/Proprietary.php';
 require 'HTMLPurifier/HTMLModule/Tidy/XHTMLAndHTML4.php';
 require 'HTMLPurifier/HTMLModule/Tidy/Strict.php';
 require 'HTMLPurifier/HTMLModule/Tidy/Transitional.php';
 require 'HTMLPurifier/HTMLModule/Tidy/XHTML.php';
 require 'HTMLPurifier/Injector/AutoParagraph.php';
+require 'HTMLPurifier/Injector/DisplayLinkURI.php';
 require 'HTMLPurifier/Injector/Linkify.php';
 require 'HTMLPurifier/Injector/PurifierLinkify.php';
+require 'HTMLPurifier/Injector/RemoveEmpty.php';
+require 'HTMLPurifier/Injector/SafeObject.php';
 require 'HTMLPurifier/Lexer/DOMLex.php';
 require 'HTMLPurifier/Lexer/DirectLex.php';
 require 'HTMLPurifier/Strategy/Composite.php';
@@ -179,6 +195,7 @@ require 'HTMLPurifier/URIFilter/DisableExternal.php';
 require 'HTMLPurifier/URIFilter/DisableExternalResources.php';
 require 'HTMLPurifier/URIFilter/HostBlacklist.php';
 require 'HTMLPurifier/URIFilter/MakeAbsolute.php';
+require 'HTMLPurifier/URIFilter/Munge.php';
 require 'HTMLPurifier/URIScheme/ftp.php';
 require 'HTMLPurifier/URIScheme/http.php';
 require 'HTMLPurifier/URIScheme/https.php';

library/HTMLPurifier.kses.php

@@ -26,3 +26,5 @@ function kses($string, $allowed_html, $allowed_protocols = null) {
     $purifier = new HTMLPurifier($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

@@ -19,7 +19,7 @@
  */
 
 /*
-    HTML Purifier 3.1.0 - Standards Compliant HTML Filtering
+    HTML Purifier 3.3.0 - Standards Compliant HTML Filtering
     Copyright (C) 2006-2008 Edward Z. Yang
 
     This library is free software; you can redistribute it and/or
@@ -55,10 +55,10 @@ class HTMLPurifier
 {
 
     /** Version of HTML Purifier */
-    public $version = '3.1.0';
+    public $version = '3.3.0';
 
     /** Constant with version of HTML Purifier */
-    const VERSION = '3.1.0';
+    const VERSION = '3.3.0';
 
     /** Global configuration object */
     public $config;
@@ -232,3 +232,5 @@ class HTMLPurifier
     }
 
 }
+
+// vim: et sw=4 sts=4

library/HTMLPurifier.safe-includes.php

@@ -23,7 +23,6 @@ require_once $__dir . '/HTMLPurifier/Definition.php';
 require_once $__dir . '/HTMLPurifier/CSSDefinition.php';
 require_once $__dir . '/HTMLPurifier/ChildDef.php';
 require_once $__dir . '/HTMLPurifier/Config.php';
-require_once $__dir . '/HTMLPurifier/ConfigDef.php';
 require_once $__dir . '/HTMLPurifier/ConfigSchema.php';
 require_once $__dir . '/HTMLPurifier/ContentSets.php';
 require_once $__dir . '/HTMLPurifier/Context.php';
@@ -36,6 +35,7 @@ require_once $__dir . '/HTMLPurifier/Encoder.php';
 require_once $__dir . '/HTMLPurifier/EntityLookup.php';
 require_once $__dir . '/HTMLPurifier/EntityParser.php';
 require_once $__dir . '/HTMLPurifier/ErrorCollector.php';
+require_once $__dir . '/HTMLPurifier/ErrorStruct.php';
 require_once $__dir . '/HTMLPurifier/Exception.php';
 require_once $__dir . '/HTMLPurifier/Filter.php';
 require_once $__dir . '/HTMLPurifier/Generator.php';
@@ -46,8 +46,11 @@ require_once $__dir . '/HTMLPurifier/IDAccumulator.php';
 require_once $__dir . '/HTMLPurifier/Injector.php';
 require_once $__dir . '/HTMLPurifier/Language.php';
 require_once $__dir . '/HTMLPurifier/LanguageFactory.php';
+require_once $__dir . '/HTMLPurifier/Length.php';
 require_once $__dir . '/HTMLPurifier/Lexer.php';
 require_once $__dir . '/HTMLPurifier/PercentEncoder.php';
+require_once $__dir . '/HTMLPurifier/PropertyList.php';
+require_once $__dir . '/HTMLPurifier/PropertyListIterator.php';
 require_once $__dir . '/HTMLPurifier/Strategy.php';
 require_once $__dir . '/HTMLPurifier/StringHash.php';
 require_once $__dir . '/HTMLPurifier/StringHashParser.php';
@@ -60,12 +63,14 @@ require_once $__dir . '/HTMLPurifier/URIFilter.php';
 require_once $__dir . '/HTMLPurifier/URIParser.php';
 require_once $__dir . '/HTMLPurifier/URIScheme.php';
 require_once $__dir . '/HTMLPurifier/URISchemeRegistry.php';
+require_once $__dir . '/HTMLPurifier/UnitConverter.php';
 require_once $__dir . '/HTMLPurifier/VarParser.php';
 require_once $__dir . '/HTMLPurifier/VarParserException.php';
 require_once $__dir . '/HTMLPurifier/AttrDef/CSS.php';
 require_once $__dir . '/HTMLPurifier/AttrDef/Enum.php';
 require_once $__dir . '/HTMLPurifier/AttrDef/Integer.php';
 require_once $__dir . '/HTMLPurifier/AttrDef/Lang.php';
+require_once $__dir . '/HTMLPurifier/AttrDef/Switch.php';
 require_once $__dir . '/HTMLPurifier/AttrDef/Text.php';
 require_once $__dir . '/HTMLPurifier/AttrDef/URI.php';
 require_once $__dir . '/HTMLPurifier/AttrDef/CSS/Number.php';
@@ -100,6 +105,7 @@ require_once $__dir . '/HTMLPurifier/AttrDef/URI/Host.php';
 require_once $__dir . '/HTMLPurifier/AttrDef/URI/IPv4.php';
 require_once $__dir . '/HTMLPurifier/AttrDef/URI/IPv6.php';
 require_once $__dir . '/HTMLPurifier/AttrDef/URI/Email/SimpleCheck.php';
+require_once $__dir . '/HTMLPurifier/AttrTransform/Background.php';
 require_once $__dir . '/HTMLPurifier/AttrTransform/BdoDir.php';
 require_once $__dir . '/HTMLPurifier/AttrTransform/BgColor.php';
 require_once $__dir . '/HTMLPurifier/AttrTransform/BoolToCSS.php';
@@ -107,10 +113,15 @@ require_once $__dir . '/HTMLPurifier/AttrTransform/Border.php';
 require_once $__dir . '/HTMLPurifier/AttrTransform/EnumToCSS.php';
 require_once $__dir . '/HTMLPurifier/AttrTransform/ImgRequired.php';
 require_once $__dir . '/HTMLPurifier/AttrTransform/ImgSpace.php';
+require_once $__dir . '/HTMLPurifier/AttrTransform/Input.php';
 require_once $__dir . '/HTMLPurifier/AttrTransform/Lang.php';
 require_once $__dir . '/HTMLPurifier/AttrTransform/Length.php';
 require_once $__dir . '/HTMLPurifier/AttrTransform/Name.php';
+require_once $__dir . '/HTMLPurifier/AttrTransform/SafeEmbed.php';
+require_once $__dir . '/HTMLPurifier/AttrTransform/SafeObject.php';
+require_once $__dir . '/HTMLPurifier/AttrTransform/SafeParam.php';
 require_once $__dir . '/HTMLPurifier/AttrTransform/ScriptRequired.php';
+require_once $__dir . '/HTMLPurifier/AttrTransform/Textarea.php';
 require_once $__dir . '/HTMLPurifier/ChildDef/Chameleon.php';
 require_once $__dir . '/HTMLPurifier/ChildDef/Custom.php';
 require_once $__dir . '/HTMLPurifier/ChildDef/Empty.php';
@@ -118,9 +129,6 @@ require_once $__dir . '/HTMLPurifier/ChildDef/Required.php';
 require_once $__dir . '/HTMLPurifier/ChildDef/Optional.php';
 require_once $__dir . '/HTMLPurifier/ChildDef/StrictBlockquote.php';
 require_once $__dir . '/HTMLPurifier/ChildDef/Table.php';
-require_once $__dir . '/HTMLPurifier/ConfigDef/Directive.php';
-require_once $__dir . '/HTMLPurifier/ConfigDef/DirectiveAlias.php';
-require_once $__dir . '/HTMLPurifier/ConfigDef/Namespace.php';
 require_once $__dir . '/HTMLPurifier/DefinitionCache/Decorator.php';
 require_once $__dir . '/HTMLPurifier/DefinitionCache/Null.php';
 require_once $__dir . '/HTMLPurifier/DefinitionCache/Serializer.php';
@@ -129,15 +137,19 @@ require_once $__dir . '/HTMLPurifier/DefinitionCache/Decorator/Memory.php';
 require_once $__dir . '/HTMLPurifier/HTMLModule/Bdo.php';
 require_once $__dir . '/HTMLPurifier/HTMLModule/CommonAttributes.php';
 require_once $__dir . '/HTMLPurifier/HTMLModule/Edit.php';
+require_once $__dir . '/HTMLPurifier/HTMLModule/Forms.php';
 require_once $__dir . '/HTMLPurifier/HTMLModule/Hypertext.php';
 require_once $__dir . '/HTMLPurifier/HTMLModule/Image.php';
 require_once $__dir . '/HTMLPurifier/HTMLModule/Legacy.php';
 require_once $__dir . '/HTMLPurifier/HTMLModule/List.php';
+require_once $__dir . '/HTMLPurifier/HTMLModule/Name.php';
 require_once $__dir . '/HTMLPurifier/HTMLModule/NonXMLCommonAttributes.php';
 require_once $__dir . '/HTMLPurifier/HTMLModule/Object.php';
 require_once $__dir . '/HTMLPurifier/HTMLModule/Presentation.php';
 require_once $__dir . '/HTMLPurifier/HTMLModule/Proprietary.php';
 require_once $__dir . '/HTMLPurifier/HTMLModule/Ruby.php';
+require_once $__dir . '/HTMLPurifier/HTMLModule/SafeEmbed.php';
+require_once $__dir . '/HTMLPurifier/HTMLModule/SafeObject.php';
 require_once $__dir . '/HTMLPurifier/HTMLModule/Scripting.php';
 require_once $__dir . '/HTMLPurifier/HTMLModule/StyleAttribute.php';
 require_once $__dir . '/HTMLPurifier/HTMLModule/Tables.php';
@@ -145,14 +157,18 @@ require_once $__dir . '/HTMLPurifier/HTMLModule/Target.php';
 require_once $__dir . '/HTMLPurifier/HTMLModule/Text.php';
 require_once $__dir . '/HTMLPurifier/HTMLModule/Tidy.php';
 require_once $__dir . '/HTMLPurifier/HTMLModule/XMLCommonAttributes.php';
+require_once $__dir . '/HTMLPurifier/HTMLModule/Tidy/Name.php';
 require_once $__dir . '/HTMLPurifier/HTMLModule/Tidy/Proprietary.php';
 require_once $__dir . '/HTMLPurifier/HTMLModule/Tidy/XHTMLAndHTML4.php';
 require_once $__dir . '/HTMLPurifier/HTMLModule/Tidy/Strict.php';
 require_once $__dir . '/HTMLPurifier/HTMLModule/Tidy/Transitional.php';
 require_once $__dir . '/HTMLPurifier/HTMLModule/Tidy/XHTML.php';
 require_once $__dir . '/HTMLPurifier/Injector/AutoParagraph.php';
+require_once $__dir . '/HTMLPurifier/Injector/DisplayLinkURI.php';
 require_once $__dir . '/HTMLPurifier/Injector/Linkify.php';
 require_once $__dir . '/HTMLPurifier/Injector/PurifierLinkify.php';
+require_once $__dir . '/HTMLPurifier/Injector/RemoveEmpty.php';
+require_once $__dir . '/HTMLPurifier/Injector/SafeObject.php';
 require_once $__dir . '/HTMLPurifier/Lexer/DOMLex.php';
 require_once $__dir . '/HTMLPurifier/Lexer/DirectLex.php';
 require_once $__dir . '/HTMLPurifier/Strategy/Composite.php';
@@ -173,6 +189,7 @@ require_once $__dir . '/HTMLPurifier/URIFilter/DisableExternal.php';
 require_once $__dir . '/HTMLPurifier/URIFilter/DisableExternalResources.php';
 require_once $__dir . '/HTMLPurifier/URIFilter/HostBlacklist.php';
 require_once $__dir . '/HTMLPurifier/URIFilter/MakeAbsolute.php';
+require_once $__dir . '/HTMLPurifier/URIFilter/Munge.php';
 require_once $__dir . '/HTMLPurifier/URIScheme/ftp.php';
 require_once $__dir . '/HTMLPurifier/URIScheme/http.php';
 require_once $__dir . '/HTMLPurifier/URIScheme/https.php';

library/HTMLPurifier/AttrCollections.php

@@ -125,3 +125,4 @@ class HTMLPurifier_AttrCollections
 
 }
 
+// vim: et sw=4 sts=4

library/HTMLPurifier/AttrDef.php

@@ -51,16 +51,13 @@ abstract class HTMLPurifier_AttrDef
      *
      * @warning This processing is inconsistent with XML's whitespace handling
      *          as specified by section 3.3.3 and referenced XHTML 1.0 section
-     *          4.7.  Compliant processing requires all line breaks normalized
-     *          to "\n", so the fix is not as simple as fixing it in this
-     *          function.  Trim and whitespace collapsing are supposed to only
-     *          occur in NMTOKENs.  However, note that we are NOT necessarily
-     *          parsing XML, thus, this behavior may still be correct.
+     *          4.7.  However, note that we are NOT necessarily
+     *          parsing XML, thus, this behavior may still be correct. We
+     *          assume that newlines have been normalized.
      */
     public function parseCDATA($string) {
         $string = trim($string);
-        $string = str_replace("\n", '', $string);
-        $string = str_replace(array("\r", "\t"), ' ', $string);
+        $string = str_replace(array("\n", "\t", "\r"), ' ', $string);
         return $string;
     }
 
@@ -87,3 +84,4 @@ abstract class HTMLPurifier_AttrDef
 
 }
 
+// vim: et sw=4 sts=4

library/HTMLPurifier/AttrDef/CSS.php

@@ -29,6 +29,12 @@ class HTMLPurifier_AttrDef_CSS extends HTMLPurifier_AttrDef
         $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;
@@ -61,6 +67,8 @@ class HTMLPurifier_AttrDef_CSS extends HTMLPurifier_AttrDef
             $propvalues[$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.
@@ -76,3 +84,4 @@ class HTMLPurifier_AttrDef_CSS extends HTMLPurifier_AttrDef
 
 }
 
+// vim: et sw=4 sts=4

library/HTMLPurifier/AttrDef/CSS/AlphaValue.php

@@ -17,3 +17,5 @@ class HTMLPurifier_AttrDef_CSS_AlphaValue extends HTMLPurifier_AttrDef_CSS_Numbe
     }
 
 }
+
+// vim: et sw=4 sts=4

library/HTMLPurifier/AttrDef/CSS/Background.php

@@ -84,3 +84,4 @@ class HTMLPurifier_AttrDef_CSS_Background extends HTMLPurifier_AttrDef
 
 }
 
+// vim: et sw=4 sts=4

library/HTMLPurifier/AttrDef/CSS/BackgroundPosition.php

@@ -123,3 +123,4 @@ class HTMLPurifier_AttrDef_CSS_BackgroundPosition extends HTMLPurifier_AttrDef
 
 }
 
+// vim: et sw=4 sts=4

library/HTMLPurifier/AttrDef/CSS/Border.php

@@ -40,3 +40,4 @@ class HTMLPurifier_AttrDef_CSS_Border extends HTMLPurifier_AttrDef
 
 }
 
+// vim: et sw=4 sts=4

library/HTMLPurifier/AttrDef/CSS/Color.php

@@ -75,3 +75,4 @@ class HTMLPurifier_AttrDef_CSS_Color extends HTMLPurifier_AttrDef
 
 }
 
+// vim: et sw=4 sts=4

library/HTMLPurifier/AttrDef/CSS/Composite.php

@@ -35,3 +35,4 @@ class HTMLPurifier_AttrDef_CSS_Composite extends HTMLPurifier_AttrDef
 
 }
 
+// vim: et sw=4 sts=4

library/HTMLPurifier/AttrDef/CSS/DenyElementDecorator.php

@@ -5,7 +5,7 @@
  */
 class HTMLPurifier_AttrDef_CSS_DenyElementDecorator extends HTMLPurifier_AttrDef
 {
-    protected $def, $element;
+    public $def, $element;
 
     /**
      * @param $def Definition to wrap
@@ -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

@@ -50,3 +50,5 @@ class HTMLPurifier_AttrDef_CSS_Filter extends HTMLPurifier_AttrDef
     }
 
 }
+
+// vim: et sw=4 sts=4

library/HTMLPurifier/AttrDef/CSS/Font.php

@@ -146,3 +146,4 @@ class HTMLPurifier_AttrDef_CSS_Font extends HTMLPurifier_AttrDef
 
 }
 
+// vim: et sw=4 sts=4

library/HTMLPurifier/AttrDef/CSS/FontFamily.php

@@ -16,7 +16,6 @@ class HTMLPurifier_AttrDef_CSS_FontFamily extends HTMLPurifier_AttrDef
             'cursive' => true
         );
 
-        $string = $this->parseCDATA($string);
         // assume that no font names contain commas in them
         $fonts = explode(',', $string);
         $final = '';
@@ -35,13 +34,40 @@ class HTMLPurifier_AttrDef_CSS_FontFamily extends HTMLPurifier_AttrDef
                 $quote = $font[0];
                 if ($font[$length - 1] !== $quote) continue;
                 $font = substr($font, 1, $length - 2);
-                // double-backslash processing is buggy
-                $font = str_replace("\\$quote", $quote, $font); // de-escape quote
-                $font = str_replace("\\\n", "\n", $font);       // de-escape newlines
+
+                $new_font = '';
+                for ($i = 0, $c = strlen($font); $i < $c; $i++) {
+                    if ($font[$i] === '\\') {
+                        $i++;
+                        if ($i >= $c) {
+                            $new_font .= '\\';
+                            break;
+                        }
+                        if (ctype_xdigit($font[$i])) {
+                            $code = $font[$i];
+                            for ($a = 1, $i++; $i < $c && $a < 6; $i++, $a++) {
+                                if (!ctype_xdigit($font[$i])) break;
+                                $code .= $font[$i];
+                            }
+                            // We have to be extremely careful when adding
+                            // new characters, to make sure we're not breaking
+                            // the encoding.
+                            $char = HTMLPurifier_Encoder::unichr(hexdec($code));
+                            if (HTMLPurifier_Encoder::cleanUTF8($char) === '') continue;
+                            $new_font .= $char;
+                            if ($i < $c && trim($font[$i]) !== '') $i--;
+                            continue;
+                        }
+                        if ($font[$i] === "\n") continue;
+                    }
+                    $new_font .= $font[$i];
+                }
+
+                $font = $new_font;
             }
             // $font is a pure representation of the font name
 
-            if (ctype_alnum($font)) {
+            if (ctype_alnum($font) && $font !== '') {
                 // very simple font, allow it in unharmed
                 $final .= $font . ', ';
                 continue;
@@ -50,8 +76,8 @@ class HTMLPurifier_AttrDef_CSS_FontFamily extends HTMLPurifier_AttrDef
             // complicated font, requires quoting
 
             // armor single quotes and new lines
+            $font = str_replace("\\", "\\\\", $font);
             $font = str_replace("'", "\\'", $font);
-            $font = str_replace("\n", "\\\n", $font);
             $final .= "'$font', ";
         }
         $final = rtrim($final, ', ');
@@ -61,3 +87,4 @@ class HTMLPurifier_AttrDef_CSS_FontFamily extends HTMLPurifier_AttrDef
 
 }
 
+// vim: et sw=4 sts=4

library/HTMLPurifier/AttrDef/CSS/ImportantDecorator.php

@@ -5,7 +5,7 @@
  */
 class HTMLPurifier_AttrDef_CSS_ImportantDecorator extends HTMLPurifier_AttrDef
 {
-    protected $def, $allow;
+    public $def, $allow;
 
     /**
      * @param $def Definition to wrap
@@ -36,3 +36,5 @@ class HTMLPurifier_AttrDef_CSS_ImportantDecorator extends HTMLPurifier_AttrDef
         return $string;
     }
 }
+
+// vim: et sw=4 sts=4

library/HTMLPurifier/AttrDef/CSS/Length.php

@@ -6,47 +6,42 @@
 class HTMLPurifier_AttrDef_CSS_Length extends HTMLPurifier_AttrDef
 {
 
-    /**
-     * Valid unit lookup table.
-     * @warning The code assumes all units are two characters long.  Be careful
-     *          if we have to change this behavior!
-     */
-    protected $units = array('em' => true, 'ex' => true, 'px' => true, 'in' => true,
-         'cm' => true, 'mm' => true, 'pt' => true, 'pc' => true);
-    /**
-     * Instance of HTMLPurifier_AttrDef_Number to defer number validation to
-     */
-    protected $number_def;
+    protected $min, $max;
 
     /**
-     * @param $non_negative Bool indication whether or not negative values are
-     *                      allowed.
+     * @param HTMLPurifier_Length $max Minimum length, or null for no bound. String is also acceptable.
+     * @param HTMLPurifier_Length $max Maximum length, or null for no bound. String is also acceptable.
      */
-    public function __construct($non_negative = false) {
-        $this->number_def = new HTMLPurifier_AttrDef_CSS_Number($non_negative);
+    public function __construct($min = null, $max = null) {
+        $this->min = $min !== null ? HTMLPurifier_Length::make($min) : null;
+        $this->max = $max !== null ? HTMLPurifier_Length::make($max) : null;
     }
 
-    public function validate($length, $config, $context) {
+    public function validate($string, $config, $context) {
+        $string = $this->parseCDATA($string);
 
-        $length = $this->parseCDATA($length);
-        if ($length === '') return false;
-        if ($length === '0') return '0';
-        $strlen = strlen($length);
-        if ($strlen === 1) return false; // impossible!
+        // Optimizations
+        if ($string === '') return false;
+        if ($string === '0') return '0';
+        if (strlen($string) === 1) return false;
 
-        // we assume all units are two characters
-        $unit = substr($length, $strlen - 2);
-        if (!ctype_lower($unit)) $unit = strtolower($unit);
-        $number = substr($length, 0, $strlen - 2);
+        $length = HTMLPurifier_Length::make($string);
+        if (!$length->isValid()) return false;
 
-        if (!isset($this->units[$unit])) return false;
-        
-        $number = $this->number_def->validate($number, $config, $context);
-        if ($number === false) return false;
-        
-        return $number . $unit;
+        if ($this->min) {
+            $c = $length->compareTo($this->min);
+            if ($c === false) return false;
+            if ($c < 0) return false;
+        }
+        if ($this->max) {
+            $c = $length->compareTo($this->max);
+            if ($c === false) return false;
+            if ($c > 0) return false;
+        }
 
+        return $length->toString();
     }
 
 }
 
+// vim: et sw=4 sts=4

library/HTMLPurifier/AttrDef/CSS/ListStyle.php

@@ -75,3 +75,4 @@ class HTMLPurifier_AttrDef_CSS_ListStyle extends HTMLPurifier_AttrDef
 
 }
 
+// vim: et sw=4 sts=4

library/HTMLPurifier/AttrDef/CSS/Multiple.php

@@ -55,3 +55,4 @@ class HTMLPurifier_AttrDef_CSS_Multiple extends HTMLPurifier_AttrDef
 
 }
 
+// vim: et sw=4 sts=4

library/HTMLPurifier/AttrDef/CSS/Number.php

@@ -18,6 +18,10 @@ class HTMLPurifier_AttrDef_CSS_Number extends HTMLPurifier_AttrDef
         $this->non_negative = $non_negative;
     }
 
+    /**
+     * @warning Some contexts do not pass $config, $context. These
+     *          variables should not be used without checking HTMLPurifier_Length
+     */
     public function validate($number, $config, $context) {
 
         $number = $this->parseCDATA($number);
@@ -62,3 +66,4 @@ class HTMLPurifier_AttrDef_CSS_Number extends HTMLPurifier_AttrDef
 
 }
 
+// vim: et sw=4 sts=4

library/HTMLPurifier/AttrDef/CSS/Percentage.php

@@ -37,3 +37,4 @@ class HTMLPurifier_AttrDef_CSS_Percentage extends HTMLPurifier_AttrDef
 
 }
 
+// vim: et sw=4 sts=4

library/HTMLPurifier/AttrDef/CSS/TextDecoration.php

@@ -13,10 +13,13 @@ class HTMLPurifier_AttrDef_CSS_TextDecoration extends HTMLPurifier_AttrDef
         static $allowed_values = array(
             'line-through' => true,
             'overline' => true,
-            'underline' => true
+            'underline' => true,
         );
 
         $string = strtolower($this->parseCDATA($string));
+
+        if ($string === 'none') return $string;
+
         $parts = explode(' ', $string);
         $final = '';
         foreach ($parts as $part) {
@@ -32,3 +35,4 @@ class HTMLPurifier_AttrDef_CSS_TextDecoration extends HTMLPurifier_AttrDef
 
 }
 
+// vim: et sw=4 sts=4