Release 4.1.1.

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

.gitignore

@@ -1,5 +1,7 @@
+tags
 conf/
 test-settings.php
+config-schema.php
 library/HTMLPurifier/DefinitionCache/Serializer/*/
 library/standalone/
 library/HTMLPurifier.standalone.php

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         = 3.3.0
+PROJECT_NUMBER         = 4.1.1
 
 # The OUTPUT_DIRECTORY tag is used to specify the (relative or absolute)
 # base path where the generated documentation will be put.

FOCUS

@@ -1,4 +1,4 @@
-7 - Major bugfixes
+9 - Major security fixes
 
 [ Appendix A: Release focus IDs ]
 0 - N/A

INSTALL

@@ -231,12 +231,12 @@ HTML Purifier uses iconv to support other character encodings, as such,
 any encoding that iconv supports <http://www.gnu.org/software/libiconv/>
 HTML Purifier supports with this code:
 
-    $config->set('Core', 'Encoding', /* put your encoding here */);
+    $config->set('Core.Encoding', /* put your encoding here */);
 
 An example usage for Latin-1 websites (the most common encoding for English
 websites):
 
-    $config->set('Core', 'Encoding', 'ISO-8859-1');
+    $config->set('Core.Encoding', 'ISO-8859-1');
 
 Note that HTML Purifier's support for non-Unicode encodings is crippled by the
 fact that any character not supported by that encoding will be silently
@@ -251,7 +251,7 @@ reason, I do not include the solution in this document).
 For those of you using HTML 4.01 Transitional, you can disable
 XHTML output like this:
 
-    $config->set('HTML', 'Doctype', 'HTML 4.01 Transitional');
+    $config->set('HTML.Doctype', 'HTML 4.01 Transitional');
 
 Other supported doctypes include:
 
@@ -277,14 +277,14 @@ are, respectively, %HTML.Allowed, %URI.MakeAbsolute and %URI.Base, and
 %AutoFormat.AutoParagraph. The %Namespace.Directive naming convention
 translates to:
 
-    $config->set('Namespace', 'Directive', $value);
+    $config->set('Namespace.Directive', $value);
 
 E.g.
 
-    $config->set('HTML', 'Allowed', 'p,b,a[href],i');
+    $config->set('HTML.Allowed', 'p,b,a[href],i');
-    $config->set('URI', 'Base', 'http://www.example.com');
+    $config->set('URI.Base', 'http://www.example.com');
-    $config->set('URI', 'MakeAbsolute', true);
+    $config->set('URI.MakeAbsolute', true);
-    $config->set('AutoFormat', 'AutoParagraph', true);
+    $config->set('AutoFormat.AutoParagraph', true);
 
 
 ---------------------------------------------------------------------------
@@ -318,11 +318,11 @@ If you are unable or unwilling to give write permissions to the cache
 directory, you can either disable the cache (and suffer a performance
 hit):
 
-    $config->set('Core', 'DefinitionCache', null);
+    $config->set('Core.DefinitionCache', null);
 
 Or move the cache directory somewhere else (no trailing slash):
 
-    $config->set('Cache', 'SerializerPath', '/home/user/absolute/path');
+    $config->set('Cache.SerializerPath', '/home/user/absolute/path');
 
 
 ---------------------------------------------------------------------------
@@ -363,8 +363,8 @@ If your website is in a different encoding or doctype, use this code:
     require_once '/path/to/htmlpurifier/library/HTMLPurifier.auto.php';
 
     $config = HTMLPurifier_Config::createDefault();
-    $config->set('Core', 'Encoding', 'ISO-8859-1'); // replace with your encoding
+    $config->set('Core.Encoding', 'ISO-8859-1'); // replace with your encoding
-    $config->set('HTML', 'Doctype', 'HTML 4.01 Transitional'); // replace with your doctype
+    $config->set('HTML.Doctype', 'HTML 4.01 Transitional'); // replace with your doctype
     $purifier = new HTMLPurifier($config);
 
     $clean_html = $purifier->purify($dirty_html);

NEWS

@@ -9,6 +9,82 @@ NEWS ( CHANGELOG and HISTORY )                                     HTMLPurifier
     . Internal change
 ==========================
 
+4.1.1, released 2010-05-31
+- Fix undefined index warnings in maintenance scripts.
+- Fix bug in DirectLex for parsing elements with a single attribute
+  with entities.
+- Rewrite CSS output logic for font-family and url().  Thanks Mario
+  Heiderich <mario.heiderich@googlemail.com> for reporting and Takeshi
+  Terada <t-terada@violet.plala.or.jp> for suggesting the fix.
+- Emit an error for CollectErrors if a body is extracted
+- Fix bug where in background-position for center keyword handling.
+- Fix infinite loop when a wrapper element is inserted in a context
+  where it's not allowed.  Thanks Lars <lars@renoz.dk> for reporting.
+- Remove +x bit and shebang from index.php; only supported mode is to
+  explicitly call it with php.
+- Make test script less chatty when log_errors is on.
+
+4.1.0, released 2010-04-26
+! Support proprietary height attribute on table element
+! Support YouTube slideshows that contain /cp/ in their URL.
+! Support for data: URI scheme; not enabled by default, add it using
+  %URI.AllowedSchemes
+! Support flashvars when using %HTML.SafeObject and %HTML.SafeEmbed.
+! Support for Internet Explorer compatibility with %HTML.SafeObject
+  using %Output.FlashCompat.
+! Handle <ol><ol> properly, by inserting the necessary <li> tag.
+- Always quote the insides of url(...) in CSS.
+
+4.0.0, released 2009-07-07
+# APIs for ConfigSchema subsystem have substantially changed. See
+  docs/dev-config-bcbreaks.txt for details; in essence, anything that
+  had both namespace and directive now have a single unified key.
+# Some configuration directives were renamed, specifically:
+    %AutoFormatParam.PurifierLinkifyDocURL -> %AutoFormat.PurifierLinkify.DocURL
+    %FilterParam.ExtractStyleBlocksEscaping -> %Filter.ExtractStyleBlocks.Escaping
+    %FilterParam.ExtractStyleBlocksScope -> %Filter.ExtractStyleBlocks.Scope
+    %FilterParam.ExtractStyleBlocksTidyImpl -> %Filter.ExtractStyleBlocks.TidyImpl
+  As usual, the old directive names will still work, but will throw E_NOTICE
+  errors.
+# The allowed values for class have been relaxed to allow all of CDATA for
+  doctypes that are not XHTML 1.1 or XHTML 2.0.  For old behavior, set
+  %Attr.ClassUseCDATA to false.
+# Instead of appending the content model to an old content model, a blank
+  element will replace the old content model.  You can use #SUPER to get
+  the old content model.
+! More robust support for name="" and id=""
+! HTMLPurifier_Config::inherit($config) allows you to inherit one
+  configuration, and have changes to that configuration be propagated
+  to all of its children.
+! Implement %HTML.Attr.Name.UseCDATA, which relaxes validation rules on
+  the name attribute when set. Use with care. Thanks Ian Cook for
+  sponsoring.
+! Implement %AutoFormat.RemoveEmpty.RemoveNbsp, which removes empty
+  tags that contain non-breaking spaces as well other whitespace. You
+  can also modify which tags should have &nbsp; maintained with
+  %AutoFormat.RemoveEmpty.RemoveNbsp.Exceptions.
+! Implement %Attr.AllowedClasses, which allows administrators to restrict
+  classes users can use to a specified finite set of classes, and
+  %Attr.ForbiddenClasses, which is the logical inverse.
+! You can now maintain your own configuration schema directories by
+  creating a config-schema.php file or passing an extra argument. Check
+  docs/dev-config-schema.html for more details.
+! Added HTMLPurifier_Config->serialize() method, which lets you save away
+  your configuration in a compact serial file, which you can unserialize
+  and use directly without having to go through the overhead of setup.
+- Fix bug where URIDefinition would not get cleared if it's directives got
+  changed.
+- Fix fatal error in HTMLPurifier_Encoder on certain platforms (probably NetBSD 5.0)
+- Fix bug in Linkify autoformatter involving <a><span>http://foo</span></a>
+- Make %URI.Munge not apply to links that have the same host as your host.
+- Prevent stray </body> tag from truncating output, if a second </body>
+  is present.
+. Created script maintenance/rename-config.php for renaming a configuration
+  directive while maintaining its alias.  This script does not change source code.
+. Implement namespace locking for definition construction, to prevent
+  bugs where a directive is used for definition construction but is not
+  used to construct the cache hash.
+
 3.3.0, released 2009-02-16
 ! Implement CSS property 'overflow' when %CSS.AllowTricky is true.
 ! Implement generic property list classess

TODO

@@ -11,54 +11,60 @@ If no interest is expressed for a feature that may require a considerable
 amount of effort to implement, it may get endlessly delayed. Do not be
 afraid to cast your vote for the next feature to be implemented!
 
-- Investigate how early internal structures can be accessed; this would
+Things to do as soon as possible:
-  prevent structures from being parsed and serialized multiple times.
+
-- Built-in support for target="_blank" on all external links
+ - Think about allowing explicit order of operations hooks for transforms
-- Allow <a id="asdf" name="asdf">
+ - Inputs don't do the right thing with submit
-- Convert configuration to allow an arbitrary number of namespaces;
+ - Fix "<.<" bug (trailing < is removed if not EOD)
-  then rename as appropriate.
+ - Build in better internal state dumps and debugging tools for remote
+   debugging
+ - Allowed/Allowed* have strange interactions when both set
+ - Transform lone embeds into object tags
 
 FUTURE VERSIONS
 ---------------
 
-4.1 release [It's All About Trust] (floating)
+4.2 release [OMG CONFIG PONIES]
+ ! Fix Printer. It's from the old days when we didn't have decent XML classes
+ ! Factor demo.php into a set of Printer classes, and then create a stub
+   file for users here (inside the actual HTML Purifier library)
+ - Fix error handling with form construction
+ - Do encoding validation in Printers, or at least, where user data comes in
+ - Config: Add examples to everything (make built-in which also automatically
+   gives output)
+ - Add "register" field to config schemas to eliminate dependence on
+   naming conventions (try to remember why we ultimately decided on tihs)
+
+5.0 release [HTML 5]
+ # Swap out code to use html5lib tokenizer and tree-builder
+ ! Allow turning off of FixNesting and required attribute insertion
+
+5.1 release [It's All About Trust] (floating)
  # Implement untrusted, dangerous elements/attributes
  # Implement IDREF support (harder than it seems, since you cannot have
    IDREFs to non-existent IDs)
+     - Implement <area> (client and server side image maps are blocking
+       on IDREF support)
  # Frameset XHTML 1.0 and HTML 4.01 doctypes
- - Implement <area>
  - Figure out how to simultaneously set %CSS.Trusted and %HTML.Trusted (?)
 
-4.2 release [Error'ed]
+5.2 release [Error'ed]
  # Error logging for filtering/cleanup procedures
- - XSS-attempt detection--certain errors are flagged XSS-like
-
-4.3 release [Do What I Mean, Not What I Say]
  # Additional support for poorly written HTML
     - Microsoft Word HTML cleaning (i.e. MsoNormal, but research essential!)
     - Friendly strict handling of <address> (block -> <br>)
- ? Remove redundant tags, ex. <u><u>Underlined</u></u>. Implementation notes:
+ - XSS-attempt detection--certain errors are flagged XSS-like
-    1. Analyzing which tags to remove duplicants
-    2. Ensure attributes are merged into the parent tag
-    3. Extend the tag exclusion system to specify whether or not the
-    contents should be dropped or not (currently, there's code that could do
-    something like this if it didn't drop the inner text too.)
- - Remove <span> tags that don't do anything (no attributes)
  - 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
 
-5.0 release [Beyond HTML]
+6.0 release [Beyond HTML]
  # Legit token based CSS parsing (will require revamping almost every
-   AttrDef class). Probably will use CSSTidy class?
+   AttrDef class). Probably will use CSSTidy
  # More control over allowed CSS properties using a modularization
- # HTML 5 support
  # IRI support (this includes IDN)
  - Standardize token armor for all areas of processing
- - Convert RTL/LTR override characters to <bdo> tags, or vice versa on demand.
-   Also, enable disabling of directionality
 
-6.0 release [To XML and Beyond]
+7.0 release [To XML and Beyond]
  - Extended HTML capabilities based on namespacing and tag transforms (COMPLEX)
     - Hooks for adding custom processors to custom namespaced tags and
       attributes, offer default implementation
@@ -69,27 +75,14 @@ Ongoing
  - Refactor unit tests into lots of test methods
  - Plugins for major CMSes (COMPLEX)
     - phpBB
-    - Drupal needs loving!
+    - Also, a FAQ for extension writers with HTML Purifier
-    - Phorum need loving!
-    - more! (look for ones that use WYSIWYGs)
-    - Also, maybe a FAQ for extension writers with HTML Purifier
 
 AutoFormat
  - Smileys
  - Syntax highlighting (with GeSHi) with <pre> and possibly <?php
  - Look at http://drupal.org/project/Modules/category/63 for ideas
 
-Optimizations
- - Reduce size of internal data-structures (esp. HTMLDefinition)
- - Research memory usage of objects versus arrays
- - Combine multiple strategies into a single, single-pass strategy
- - Get PH5P working with the latest versions of DOM, which have much more
-   stringent error checking procedures. Maybe convert straight to tokens.
- - Get rid of set_include_path(). Save this for another major release.
-
 Neat feature related
- ! Factor demo.php into a set of Printer classes, and then create a stub
-   file for users here (inside the actual HTML Purifier library)
  ! Support exporting configuration, so users can easily tweak settings
    in the demo, and then copy-paste into their own setup
  - Advanced URI filtering schemes (see docs/proposal-new-directives.txt)
@@ -106,14 +99,28 @@ Neat feature related
  - Full set of color keywords. Also, a way to add onto them without
    finalizing the configuration object.
  - Write a var_export and memcached DefinitionCache - Denis
- - Allow restriction of allowed class values
+ - Built-in support for target="_blank" on all external links
+ - Convert RTL/LTR override characters to <bdo> tags, or vice versa on demand.
+   Also, enable disabling of directionality
+ ? Externalize inline CSS to promote clean HTML, proposed by Sander Tekelenburg
+ ? Remove redundant tags, ex. <u><u>Underlined</u></u>. Implementation notes:
+    1. Analyzing which tags to remove duplicants
+    2. Ensure attributes are merged into the parent tag
+    3. Extend the tag exclusion system to specify whether or not the
+    contents should be dropped or not (currently, there's code that could do
+    something like this if it didn't drop the inner text too.)
 
 Maintenance related (slightly boring)
  # CHMOD install script for PEAR installs
  ! Factor out command line parser into its own class, and unit test it
- ! Nested configuration namespaces
+ - Reduce size of internal data-structures (esp. HTMLDefinition)
- - Distinguish between default settings and explicitly set settings, so
+ - Allow merging configurations.  Thus,
-   configurations can be merged
+        a -> b -> default
+        c -> d -> default
+   becomes
+        a -> b -> c -> d -> default
+   Maybe allow more fine-grained tuning of this behavior. Alternatively,
+   encourage people to use short plist depths before building them up.
  - Time PHPT tests
 
 ChildDef related (very boring)

VERSION

@@ -1 +1 @@
-3.3.0
+4.1.1

WHATSNEW

@@ -1,6 +1,5 @@
-HTML Purifier 3.3.0 is fixes a number of obscure bugs reported and fixed
+HTML Purifier 4.1.1 is a major security and bugfix release that
-over a four month period.  It is probably the last release in the 3.x
+improves on 4.1's fix for an XSS vulnerability exploitable on Internet
-series.  Notable new features include support for the overflow CSS
+Explorer.  It also contains a number of important bugfixes, including
-property; notable bugfixes include fixed YouTube rendering in certain
+the removal of improper logic that could result in infinite loops and
-versions of Firefox, CSSDefinition Printer, improved early PHP support
+fixed parsing for single-attributes with entities with DirectLex.
-and bugs in iconv.

benchmarks/samples/Lexer/1.html

@@ -52,4 +52,5 @@
 </body>
 </html>
 
-<!-- vim: et sw=4 sts=4 -->
+<!-- vim: et sw=4 sts=4
+-->

benchmarks/samples/Lexer/2.html

@@ -16,4 +16,5 @@ function qs(el) {if (window.RegExp && window.encodeURIComponent) {var ue=el.href
 // -->
 </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 -->
+<!-- vim: et sw=4 sts=4
+-->

benchmarks/samples/Lexer/3.html

@@ -127,4 +127,5 @@ if (objAdMgr.isSlotAvailable("leaderboard")) {
 
 </html>
 
-<!-- vim: et sw=4 sts=4 -->
+<!-- vim: et sw=4 sts=4
+-->

benchmarks/samples/Lexer/4.html

@@ -539,4 +539,5 @@ 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 -->
+<!-- vim: et sw=4 sts=4
+-->

configdoc/generate.php

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

configdoc/styles/plain.xsl

@@ -232,4 +232,5 @@
 
 </xsl:stylesheet>
 
-<!-- vim: et sw=4 sts=4 -->
+<!-- vim: et sw=4 sts=4
+-->

configdoc/types.xml

@@ -13,4 +13,5 @@
   <type id="mixed">Mixed</type>
 </types>
 
-<!-- vim: et sw=4 sts=4 -->
+<!-- vim: et sw=4 sts=4
+-->

configdoc/usage.xml

@@ -6,6 +6,7 @@
   </file>
   <file name="HTMLPurifier/Lexer.php">
    <line>81</line>
+   <line>269</line>
   </file>
   <file name="HTMLPurifier/Lexer/DirectLex.php">
    <line>53</line>
@@ -85,22 +86,27 @@
  </directive>
  <directive id="Output.CommentScriptContents">
   <file name="HTMLPurifier/Generator.php">
-   <line>45</line>
+   <line>56</line>
   </file>
  </directive>
  <directive id="Output.SortAttr">
   <file name="HTMLPurifier/Generator.php">
-   <line>46</line>
+   <line>57</line>
+  </file>
+ </directive>
+ <directive id="Output.FlashCompat">
+  <file name="HTMLPurifier/Generator.php">
+   <line>58</line>
   </file>
  </directive>
  <directive id="Output.TidyFormat">
   <file name="HTMLPurifier/Generator.php">
-   <line>75</line>
+   <line>87</line>
   </file>
  </directive>
  <directive id="Output.Newline">
   <file name="HTMLPurifier/Generator.php">
-   <line>89</line>
+   <line>101</line>
   </file>
  </directive>
  <directive id="HTML.BlockWrapper">
@@ -208,6 +214,14 @@
    <line>267</line>
   </file>
  </directive>
+ <directive id="URI.">
+  <file name="HTMLPurifier/URIDefinition.php">
+   <line>55</line>
+  </file>
+  <file name="HTMLPurifier/URIFilter/Munge.php">
+   <line>12</line>
+  </file>
+ </directive>
  <directive id="URI.Host">
   <file name="HTMLPurifier/URIDefinition.php">
    <line>64</line>
@@ -225,12 +239,12 @@
  </directive>
  <directive id="URI.AllowedSchemes">
   <file name="HTMLPurifier/URISchemeRegistry.php">
-   <line>42</line>
+   <line>41</line>
   </file>
  </directive>
  <directive id="URI.OverrideAllowedSchemes">
   <file name="HTMLPurifier/URISchemeRegistry.php">
-   <line>43</line>
+   <line>42</line>
   </file>
  </directive>
  <directive id="URI.Disable">
@@ -246,6 +260,16 @@
    <line>12</line>
   </file>
  </directive>
+ <directive id="Attr.AllowedClasses">
+  <file name="HTMLPurifier/AttrDef/HTML/Class.php">
+   <line>18</line>
+  </file>
+ </directive>
+ <directive id="Attr.ForbiddenClasses">
+  <file name="HTMLPurifier/AttrDef/HTML/Class.php">
+   <line>19</line>
+  </file>
+ </directive>
  <directive id="Attr.AllowedFrameTargets">
   <file name="HTMLPurifier/AttrDef/HTML/FrameTarget.php">
    <line>15</line>
@@ -272,6 +296,11 @@
    <line>54</line>
   </file>
  </directive>
+ <directive id="Attr.">
+  <file name="HTMLPurifier/AttrDef/HTML/LinkTypes.php">
+   <line>30</line>
+  </file>
+ </directive>
  <directive id="Attr.DefaultTextDir">
   <file name="HTMLPurifier/AttrTransform/BdoDir.php">
    <line>13</line>
@@ -297,7 +326,15 @@
  </directive>
  <directive id="Attr.DefaultInvalidImageAlt">
   <file name="HTMLPurifier/AttrTransform/ImgRequired.php">
-   <line>32</line>
+   <line>33</line>
+  </file>
+ </directive>
+ <directive id="HTML.Attr.Name.UseCDATA">
+  <file name="HTMLPurifier/AttrTransform/Name.php">
+   <line>11</line>
+  </file>
+  <file name="HTMLPurifier/HTMLModule/Name.php">
+   <line>13</line>
   </file>
  </directive>
  <directive id="Core.EscapeInvalidChildren">
@@ -310,17 +347,17 @@
    <line>91</line>
   </file>
  </directive>
- <directive id="FilterParam.ExtractStyleBlocksTidyImpl">
+ <directive id="Filter.ExtractStyleBlocks.TidyImpl">
   <file name="HTMLPurifier/Filter/ExtractStyleBlocks.php">
    <line>41</line>
   </file>
  </directive>
- <directive id="FilterParam.ExtractStyleBlocksScope">
+ <directive id="Filter.ExtractStyleBlocks.Scope">
   <file name="HTMLPurifier/Filter/ExtractStyleBlocks.php">
    <line>65</line>
   </file>
  </directive>
- <directive id="FilterParam.ExtractStyleBlocksEscaping">
+ <directive id="Filter.ExtractStyleBlocks.Escaping">
   <file name="HTMLPurifier/Filter/ExtractStyleBlocks.php">
    <line>123</line>
   </file>
@@ -351,11 +388,21 @@
    <line>50</line>
   </file>
  </directive>
- <directive id="AutoFormatParam.PurifierLinkifyDocURL">
+ <directive id="AutoFormat.PurifierLinkify.DocURL">
   <file name="HTMLPurifier/Injector/PurifierLinkify.php">
    <line>15</line>
   </file>
  </directive>
+ <directive id="AutoFormat.RemoveEmpty.RemoveNbsp">
+  <file name="HTMLPurifier/Injector/RemoveEmpty.php">
+   <line>12</line>
+  </file>
+ </directive>
+ <directive id="AutoFormat.RemoveEmpty.RemoveNbsp.Exceptions">
+  <file name="HTMLPurifier/Injector/RemoveEmpty.php">
+   <line>13</line>
+  </file>
+ </directive>
  <directive id="Core.AggressivelyFixLt">
   <file name="HTMLPurifier/Lexer/DOMLex.php">
    <line>44</line>

docs/dev-advanced-api.html

@@ -17,202 +17,10 @@
 <div id="home"><a href="http://htmlpurifier.org/">HTML Purifier</a> End-User Documentation</div>
 
 <p>
-  <strong>Warning:</strong> This document may be out-of-date. When in doubt,
+  Please see <a href="enduser-customize.html">Customize!</a>
-  consult the source code documentation.
 </p>
 
-<p>HTML Purifier currently natively supports only a subset of HTML's
-allowed elements, attributes, and behavior; specifically, this subset
-is the set of elements that are safe for untrusted users to use.
-However, HTML Purifier is often utilized to ensure standards-compliance
-from input that is trusted (making it a sort of Tidy substitute),
-and often users need to define new elements or attributes. The
-advanced API is oriented specifically for these use-cases.</p>
-
-<p>Our goals are to let the user:</p>
-
-<dl>
-    <dt>Select</dt>
-    <dd><ul>
-        <li>Doctype</li>
-        <!-- <li>Filterset</li> -->
-        <li>Elements / Attributes / Modules</li>
-        <li>Tidy</li>
-    </ul></dd>
-    <dt>Customize</dt>
-    <dd><ul>
-        <li>Attributes</li>
-        <li>Elements</li>
-        <!--<li>Doctypes</li>-->
-    </ul></dd>
-</dl>
-
-<h2>Select</h2>
-
-<p>For basic use, the user will have to specify some basic parameters. This
-is not strictly necessary, as HTML Purifier's default setting will always
-output safe code, but is required for standards-compliant output.</p>
-
-<h3>Selecting a Doctype</h3>
-
-<p>The first thing to select is the <strong>doctype</strong>. This
-is essential for standards-compliant output.</p>
-
-<p class="technical">This identifier is based
-on the name the W3C has given to the document type and <em>not</em>
-the DTD identifier.</p>
-
-<p>This parameter is set via the configuration object:</p>
-
-<pre>$config->set('HTML', 'Doctype', 'XHTML 1.0 Transitional');</pre>
-
-<p>Due to historical reasons, the default doctype is XHTML 1.0
-Transitional, however, we really shouldn't be guessing what the user's
-doctype is. Fortunantely, people who can't be bothered to set this won't
-be bothered when their pages stop validating.</p>
-
-<h3>Selecting Elements / Attributes / Modules</h3>
-
-<p>HTML Purifier will, by default, allow as many elements and attributes
-as possible. However, a user may decide to roll their own filterset by
-selecting modules, elements and attributes to allow for their own
-specific use-case. This can be done using %HTML.Allowed:</p>
-
-<pre>$config->set('HTML', 'Allowed', 'a[href|title],em,p,blockquote');</pre>
-
-<p class="technical">The directive %HTML.Allowed is a convenience feature
-that may be fully expressed with the legacy interface.</p>
-
-<p>We currently support another interface from older versions:</p>
-
-<pre>$config->set('HTML', 'AllowedElements', 'a,em,p,blockquote');
-$config->set('HTML', 'AllowedAttributes', 'a.href,a.title');</pre>
-
-<p>A user may also choose to allow modules using a specialized
-directive:</p>
-
-<pre>$config->set('HTML', 'AllowedModules', 'Hypertext,Text,Lists');</pre>
-
-<p>But it is not expected that this feature will be widely used.</p>
-
-<p class="technical">Module selection will work slightly differently
-from the other AllowedElements and AllowedAttributes directives by
-directly modifying the doctype you are operating in, in the spirit of
-XHTML 1.1's modularization. We stop users from shooting themselves in the
-foot by mandating the modules in %HTML.CoreModules be used.</p>
-
-<p class="technical">Modules are distinguished from regular elements by the
-case of their first letter. While XML distinguishes between and allows
-lower and uppercase letters in element names, XHTML uses only lower-case
-element names for sake of consistency.</p>
-
-<h3>Selecting Tidy</h3>
-
-<p>The name of this segment of functionality is inspired off of Dave
-Ragget's program HTML Tidy, which purported to help clean up HTML. In
-HTML Purifier, Tidy functionality involves turning unsupported and
-deprecated elements into standards-compliant ones, maintaining
-backwards compatibility, and enforcing best practices.</p>
-
-<p>This is a complicated feature, and is explained more in depth at
-<a href="enduser-tidy.html">the Tidy documentation page</a>.</p>
-
-<!--
-<h3>Unified selector</h3>
-
-<p>Because selecting each and every one of these configuration options
-is a chore, we may wish to offer a specialized configuration method
-for selecting a filterset. Possibility:</p>
-
-<pre>function selectFilter($doctype, $filterset, $tidy)</pre>
-
-<p>...which is simply a light wrapper over the individual configuration
-calls. A custom config file format or text format could also be adopted.</p>
--->
-
-<h2>Customize</h2>
-
-<p>By reviewing topic posts in the support forum, we determined that
-there were two primarily demanded customization features people wanted:
-to add an attribute to an existing element, and to add an element.
-Thus, we'll want to create convenience functions for these common
-use-cases.</p>
-
-<p>Note that the functions described here are only available if
-a raw copy of <code>HTMLPurifier_HTMLDefinition</code> was retrieved.
-Furthermore, caching may prevent your changes from immediately
-being seen: consult <a href="enduser-customize.html">enduser-customize.html</a> on how
-to work around this.</p>
-
-<h3>Attributes</h3>
-
-<p>An attribute is bound to an element by a name and has a specific
-<code>AttrDef</code> that validates it. The interface is therefore:</p>
-
-<pre>function addAttribute($element, $attribute, $attribute_def);</pre>
-
-<p>Example of the functionality in action:</p>
-
-<pre>$def->addAttribute('a', 'rel', 'Enum#nofollow');</pre>
-
-<p>The <code>$attribute_def</code> value is flexible,
-to make things simpler. It can be a literal object or:</p>
-
-<ul>
-    <!--<li>Class name: We'll instantiate it for you</li>
-    <li>Function name: We'll create an <code>HTMLPurifier_AttrDef_Anonymous</code>
-        class with that function registered as a callback.</li>-->
-    <li>String attribute type: We'll use <code>HTMLPurifier_AttrTypes</code>
-        to resolve it for you. Any data that follows a hash mark (#) will
-        be used to customize the attribute type: in the example above,
-        we specify which values for Enum to allow.</li>
-</ul>
-
-<h3>Elements</h3>
-
-<p>An element requires certain information as specified by
-<code>HTMLPurifier_ElementDef</code>. However, not all of it is necessary,
-the usual things required are:</p>
-
-<ul>
-    <li>Attributes</li>
-    <li>Content model/type</li>
-    <li>Registration in a content set</li>
-</ul>
-
-<p>This suggests an API like this:</p>
-
-<pre>function addElement($element, $type, $contents,
-    $attr_collections = array(); $attributes = array());</pre>
-
-<p>Each parameter explained in depth:</p>
-
-<dl>
-    <dt><code>$element</code></dt>
-    <dd>Element name, ex. 'label'</dd>
-    <dt><code>$type</code></dt>
-    <dd>Content set to register in, ex. 'Inline' or 'Flow'</dd>
-    <dt><code>$contents</code></dt>
-    <dd>Description of allowed children. This is a merged form of
-        <code>HTMLPurifier_ElementDef</code>'s member variables
-        <code>$content_model</code> and <code>$content_model_type</code>,
-        where the form is <q>Type: Model</q>, ex. 'Optional: Inline'.
-        There are also a number of predefined templates one may use.</dd>
-    <dt><code>$attr_collections</code></dt>
-    <dd>Array (or string if only one) of attribute collection(s) to
-        merge into the attributes array.</dd>
-    <dt><code>$attributes</code></dt>
-    <dd>Array of attribute names to attribute definitions, much like
-        the above-described attribute customization.</dd>
-</dl>
-
-<p>A possible usage:</p>
-
-<pre>$def->addElement('font', 'Inline', 'Optional: Inline', 'Common',
-    array('color' => 'Color'));</pre>
-
-<p>See <code>HTMLPurifier/HTMLModule.php</code> for details.</p>
-
 </body></html>
 
-<!-- vim: et sw=4 sts=4 -->
+<!-- vim: et sw=4 sts=4
+-->

docs/dev-config-bcbreaks.txt

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

docs/dev-config-naming.txt

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

docs/dev-config-schema.html

@@ -114,7 +114,7 @@ Test.Example</pre>
         </tr>
         <tr>
           <td>VALUE-ALIASES</td>
-          <td>'baz' => 'bar'</td>
+          <td>'baz' =&gt; 'bar'</td>
           <td><em>Optional</em>. Mapping of one value to another, and
           should be a comma separated list of keypair duples. This
           is only allowed string, istring, text and itext TYPEs.</td>
@@ -213,7 +213,7 @@ Test.Example</pre>
         </tr>
         <tr>
           <td>lookup</td>
-          <td>array('key' => true)</td>
+          <td>array('key' =&gt; true)</td>
           <td>Lookup array, used with <code>isset($var[$key])</code></td>
         </tr>
         <tr>
@@ -223,7 +223,7 @@ Test.Example</pre>
         </tr>
         <tr>
           <td>hash</td>
-          <td>array('key' => 'val')</td>
+          <td>array('key' =&gt; 'val')</td>
           <td>Associative array of keys to values</td>
         </tr>
         <tr>
@@ -267,6 +267,41 @@ Test.Example</pre>
       If you ever make changes to your configuration directives, you
       will need to run this script again.
     </p>
+    <h2>Adding in-house schema definitions</h2>
+
+    <p>
+      Placing stuff directly in HTML Purifier's source tree is generally not a
+      good idea, so HTML Purifier 4.0.0+ has some facilities in place to make your
+      life easier.
+    </p>
+
+    <p>
+      The first is to pass an extra parameter to <code>maintenance/generate-schema-cache.php</code>
+      with the location of your directory (relative or absolute path will do). For example,
+      if I'm storing my custom definitions in <em>/var/htmlpurifier/myschema</em>, run:
+      <code>php maintenance/generate-schema-cache.php /var/htmlpurifier/myschema</code>.
+    </p>
+
+    <p>
+      Alternatively, you can create a small loader PHP file in the HTML Purifier base
+      directory named <code>config-schema.php</code> (this is the same directory
+      you would place a <code>test-settings.php</code> file).  In this file, add
+      the following line for each directory you want to load:
+    </p>
+
+<pre>$builder-&gt;buildDir($interchange, '/var/htmlpurifier/myschema');</pre>
+
+    <p>You can even load a single file using:</p>
+
+<pre>$builder-&gt;buildFile($interchange, '/var/htmlpurifier/myschema/MyApp.Directive.txt');</pre>
+
+    <p>Storing custom definitions that you don't plan on sending back upstream in
+    a separate directory is <em>definitely</em> a good idea! Additionally, picking
+    a good namespace can go a long way to saving you grief if you want to use
+    someone else's change, but they picked the same name, or if HTML Purifier
+    decides to add support for a configuration directive that has the same name.</p>
+
+    <!-- TODO: how to name directives that rely on naming conventions -->
 
     <h2>Errors</h2>
 
@@ -373,4 +408,5 @@ Test.Example</pre>
   </body>
 </html>
 
-<!-- vim: et sw=4 sts=4 -->
+<!-- vim: et sw=4 sts=4
+-->

docs/dev-flush.html

@@ -64,4 +64,5 @@
 
 </body></html>
 
-<!-- vim: et sw=4 sts=4 -->
+<!-- vim: et sw=4 sts=4
+-->

docs/dev-naming.html

@@ -79,4 +79,5 @@ help you find the correct functionality more quickly.  Here they are:</p>
 
 </body></html>
 
-<!-- vim: et sw=4 sts=4 -->
+<!-- vim: et sw=4 sts=4
+-->

docs/dev-optimization.html

@@ -29,4 +29,5 @@ that itch, put it here!</p>
 
 </body></html>
 
-<!-- vim: et sw=4 sts=4 -->
+<!-- vim: et sw=4 sts=4
+-->

docs/dev-progress.html

@@ -305,4 +305,5 @@ Mozilla on inside and needs -moz-outline, no IE support.</td></tr>
 
 </body></html>
 
-<!-- vim: et sw=4 sts=4 -->
+<!-- vim: et sw=4 sts=4
+-->

docs/enduser-customize.html

@@ -18,12 +18,11 @@
 <div id="home"><a href="http://htmlpurifier.org/">HTML Purifier</a> End-User Documentation</div>
 
 <p>
-  You may have heard of the <a href="dev-advanced-api.html">Advanced API</a>.
+  HTML Purifier has this quirk where if you try to allow certain elements or
-  If you're interested in reading dry prose and boring functional
+  attributes, HTML Purifier will tell you that it's not supported, and that
-  specifications, feel free to click that link to get a no-nonsense overview
+  you should go to the forums to find out how to implement it. Well, this
-  on the Advanced API. For the rest of us, there's this tutorial. By the time
+  document is how to implement elements and attributes which HTML Purifier
-  you're finished reading this, you should have a pretty good idea on
+  doesn't support out of the box.
-  how to implement custom tags and attributes that HTML Purifier may not have.
 </p>
 
 <h2>Is it necessary?</h2>
@@ -84,17 +83,6 @@
   limited to translations) above or below other corresponding text.
 </p>
 
-<h3>XHTML 2.0</h3>
-
-<p>
-  <a href="http://www.w3.org/TR/xhtml2/">XHTML 2.0</a> is still a
-  working draft, so any elements introduced in the
-  specification have not been implemented and will not be implemented
-  until we get a recommendation or proposal.  Because XHTML 2.0 is
-  an entirely new markup language, implementing rules for it will be
-  no easy task.
-</p>
-
 <h3>HTML 5</h3>
 
 <p>
@@ -156,9 +144,9 @@
 </p>
 
 <pre>$config = HTMLPurifier_Config::createDefault();
-$config->set('HTML', 'DefinitionID', 'enduser-customize.html tutorial');
+$config-&gt;set('HTML.DefinitionID', 'enduser-customize.html tutorial');
-$config->set('HTML', 'DefinitionRev', 1);
+$config-&gt;set('HTML.DefinitionRev', 1);
-$def = $config->getHTMLDefinition(true);</pre>
+$def = $config-&gt;getHTMLDefinition(true);</pre>
 
 <p>
   Assuming that HTML Purifier has already been properly loaded (hint:
@@ -211,10 +199,10 @@ $def = $config->getHTMLDefinition(true);</pre>
 </p>
 
 <pre>$config = HTMLPurifier_Config::createDefault();
-$config->set('HTML', 'DefinitionID', 'enduser-customize.html tutorial');
+$config-&gt;set('HTML.DefinitionID', 'enduser-customize.html tutorial');
-$config->set('HTML', 'DefinitionRev', 1);
+$config-&gt;set('HTML.DefinitionRev', 1);
-<strong>$config->set('Cache', 'DefinitionImpl', null); // remove this later!</strong>
+<strong>$config-&gt;set('Cache.DefinitionImpl', null); // TODO: remove this later!</strong>
-$def = $config->getHTMLDefinition(true);</pre>
+$def = $config-&gt;getHTMLDefinition(true);</pre>
 
 <p>
   A few things should be mentioned about the caching mechanism before
@@ -267,10 +255,10 @@ $def = $config->getHTMLDefinition(true);</pre>
 </p>
 
 <pre>$config = HTMLPurifier_Config::createDefault();
-$config->set('HTML', 'DefinitionID', 'enduser-customize.html tutorial');
+$config-&gt;set('HTML.DefinitionID', 'enduser-customize.html tutorial');
-$config->set('HTML', 'DefinitionRev', 1);
+$config-&gt;set('HTML.DefinitionRev', 1);
-$config->set('Cache', 'DefinitionImpl', null); // remove this later!
+$config-&gt;set('Cache.DefinitionImpl', null); // remove this later!
-$def = $config->getHTMLDefinition(true);
+$def = $config-&gt;getHTMLDefinition(true);
 <strong>$def->addAttribute('a', 'target', 'Enum#_blank,_self,_target,_top');</strong></pre>
 
 <p>
@@ -385,11 +373,11 @@ $def = $config->getHTMLDefinition(true);
 </p>
 
 <pre>$config = HTMLPurifier_Config::createDefault();
-$config->set('HTML', 'DefinitionID', 'enduser-customize.html tutorial');
+$config-&gt;set('HTML.DefinitionID', 'enduser-customize.html tutorial');
-$config->set('HTML', 'DefinitionRev', 1);
+$config-&gt;set('HTML.DefinitionRev', 1);
-$config->set('Cache', 'DefinitionImpl', null); // remove this later!
+$config-&gt;set('Cache.DefinitionImpl', null); // remove this later!
-$def = $config->getHTMLDefinition(true);
+$def = $config-&gt;getHTMLDefinition(true);
-<strong>$def->addAttribute('a', 'target', new HTMLPurifier_AttrDef_Enum(
+<strong>$def-&gt;addAttribute('a', 'target', new HTMLPurifier_AttrDef_Enum(
   array('_blank','_self','_target','_top')
 ));</strong></pre>
 
@@ -724,7 +712,7 @@ $def = $config->getHTMLDefinition(true);
     or more flow elements, but no nested <code>form</code>s</strong></li>
   <li>What attributes does the element allow that are general? <strong>Common</strong></li>
   <li>What attributes does the element allow that are specific to this element? <strong>A whole bunch, see ATTLIST;
-    we're going to the vital ones: <code>action</code>, <code>method</code> and <code>name</code></strong></li>
+    we're going to do the vital ones: <code>action</code>, <code>method</code> and <code>name</code></strong></li>
 </ol>
 
 <p>
@@ -732,14 +720,14 @@ $def = $config->getHTMLDefinition(true);
 </p>
 
 <pre>$config = HTMLPurifier_Config::createDefault();
-$config->set('HTML', 'DefinitionID', 'enduser-customize.html tutorial');
+$config-&gt;set('HTML.DefinitionID', 'enduser-customize.html tutorial');
-$config->set('HTML', 'DefinitionRev', 1);
+$config-&gt;set('HTML.DefinitionRev', 1);
-$config->set('Cache', 'DefinitionImpl', null); // remove this later!
+$config-&gt;set('Cache.DefinitionImpl', null); // remove this later!
-$def = $config->getHTMLDefinition(true);
+$def = $config-&gt;getHTMLDefinition(true);
-$def->addAttribute('a', 'target', new HTMLPurifier_AttrDef_Enum(
+$def-&gt;addAttribute('a', 'target', new HTMLPurifier_AttrDef_Enum(
   array('_blank','_self','_target','_top')
 ));
-<strong>$form = $def->addElement(
+<strong>$form = $def-&gt;addElement(
   'form',   // name
   'Block',  // content set
   'Flow', // allowed children
@@ -750,7 +738,7 @@ $def->addAttribute('a', 'target', new HTMLPurifier_AttrDef_Enum(
     'name' => 'ID'
   )
 );
-$form->excludes = array('form' => true);</strong></pre>
+$form-&gt;excludes = array('form' => true);</strong></pre>
 
 <p>
   Each of the parameters corresponds to one of the questions we asked.
@@ -795,4 +783,5 @@ $form->excludes = array('form' => true);</strong></pre>
 
 </body></html>
 
-<!-- vim: et sw=4 sts=4 -->
+<!-- vim: et sw=4 sts=4
+-->

docs/enduser-id.html

@@ -31,7 +31,7 @@ by default.</p>
 
 <p>IDs, however, are quite useful functionality to have, so if users start
 complaining about broken anchors you'll probably want to turn them back on
-with %HTML.EnableAttrID. But before you go mucking around with the config
+with %Attr.EnableID. But before you go mucking around with the config
 object, it's probably worth to take some precautions to keep your page
 validating. Why?</p>
 
@@ -56,8 +56,8 @@ validating. Why?</p>
 deal with the most obvious solution: preventing users from using any IDs that
 appear elsewhere on the document.  The method is simple:</p>
 
-<pre>$config->set('HTML', 'EnableAttrID', true);
+<pre>$config-&gt;set('Attr.EnableID', true);
-$config->set('Attr', 'IDBlacklist' array(
+$config-&gt;set('Attr.IDBlacklist' array(
     'list', 'of', 'attribute', 'values', 'that', 'are', 'forbidden'
 ));</pre>
 
@@ -88,8 +88,8 @@ all, they might have simply specified a duplicate ID by accident.</p>
 <p>This method, too, is quite simple: add a prefix to all user IDs. With this
 code:</p>
 
-<pre>$config->set('HTML', 'EnableAttrID', true);
+<pre>$config-&gt;set('Attr.EnableID', true);
-$config->set('Attr', 'IDPrefix', 'user_');</pre>
+$config-&gt;set('Attr.IDPrefix', 'user_');</pre>
 
 <p>...this:</p>
 
@@ -109,7 +109,7 @@ user_ to the beginning.&quot;</p>
 nothing about multiple HTML Purifier outputs on one page.  Thus, we have
 a second configuration value to piggy-back off of: %Attr.IDPrefixLocal:</p>
 
-<pre>$config->set('Attr', 'IDPrefixLocal', 'comment' . $id . '_');</pre>
+<pre>$config-&gt;set('Attr.IDPrefixLocal', 'comment' . $id . '_');</pre>
 
 <p>This new attributes does nothing but append on to regular IDPrefix, but is
 special in that it is volatile: it's value is determined at run-time and
@@ -137,11 +137,12 @@ anchors is beyond me.</p>
 
 <p>To revert back to pre-1.2.0 behavior, simply:</p>
 
-<pre>$config->set('HTML', 'EnableAttrID', true);</pre>
+<pre>$config-&gt;set('Attr.EnableID', true);</pre>
 
 <p>Don't come crying to me when your page mysteriously stops validating, though.</p>
 
 </body>
 </html>
 
-<!-- vim: et sw=4 sts=4 -->
+<!-- vim: et sw=4 sts=4
+-->

docs/enduser-slow.html

@@ -116,4 +116,5 @@ if you decide to do that! Especially if you port HTML Purifier to C++.
 </body>
 </html>
 
-<!-- vim: et sw=4 sts=4 -->
+<!-- vim: et sw=4 sts=4
+-->

docs/enduser-tidy.html

@@ -76,7 +76,7 @@ associated with it, although it may change depending on your doctype.</p>
 change the level of cleaning by setting the %HTML.TidyLevel configuration
 directive:</p>
 
-<pre>$config->set('HTML', 'TidyLevel', 'heavy'); // burn baby burn!</pre>
+<pre>$config-&gt;set('HTML.TidyLevel', 'heavy'); // burn baby burn!</pre>
 
 <h2>Is the light level really light?</h2>
 
@@ -165,17 +165,17 @@ smoketest</a>.</p>
 so happy about the br@clear implementation. That's perfectly fine!
 HTML Purifier will make accomodations:</p>
 
-<pre>$config->set('HTML', 'Doctype', 'XHTML 1.0 Transitional');
+<pre>$config-&gt;set('HTML.Doctype', 'XHTML 1.0 Transitional');
-$config->set('HTML', 'TidyLevel', 'heavy'); // all changes, minus...
+$config-&gt;set('HTML.TidyLevel', 'heavy'); // all changes, minus...
-<strong>$config->set('HTML', 'TidyRemove', 'br@clear');</strong></pre>
+<strong>$config-&gt;set('HTML.TidyRemove', 'br@clear');</strong></pre>
 
 <p>That third line does the magic, removing the br@clear fix
 from the module, ensuring that <code>&lt;br clear="both" /&gt;</code>
 will pass through unharmed. The reverse is possible too:</p>
 
-<pre>$config->set('HTML', 'Doctype', 'XHTML 1.0 Transitional');
+<pre>$config-&gt;set('HTML.Doctype', 'XHTML 1.0 Transitional');
-$config->set('HTML', 'TidyLevel', 'none'); // no changes, plus...
+$config-&gt;set('HTML.TidyLevel', 'none'); // no changes, plus...
-<strong>$config->set('HTML', 'TidyAdd', 'p@align');</strong></pre>
+<strong>$config-&gt;set('HTML.TidyAdd', 'p@align');</strong></pre>
 
 <p>In this case, all transformations are shut off, except for the p@align
 one, which you found handy.</p>
@@ -227,4 +227,5 @@ effectively in the background.</p>
 
 </body></html>
 
-<!-- vim: et sw=4 sts=4 -->
+<!-- vim: et sw=4 sts=4
+-->

docs/enduser-uri-filter.html

@@ -160,27 +160,14 @@
 </p>
 
 <pre>$uri = $config->getDefinition('URI');
-$uri->addFilter(new HTMLPurifier_URIFilter_<strong>NameOfFilter</strong>());</pre>
+$uri->addFilter(new HTMLPurifier_URIFilter_<strong>NameOfFilter</strong>(), $config);</pre>
 
 <p>
-  If you want to be really fancy, you can define a configuration directive
+    After adding a filter, you won't be able to set configuration directives.
-  for your filter and have HTML Purifier automatically manage whether or
+    Structure your code accordingly.
-  not your filter gets loaded or not (this is how internal filters manage
-  things):
 </p>
 
-<pre>HTMLPurifier_ConfigSchema::define(
+<!-- XXX: link to new documentation system -->
-    'URI', '<strong>NameOfFilter</strong>', false, 'bool',
-    '<strong>What your filter does.</strong>'
-);
-$uri = $config->getDefinition('URI', true);
-$uri->registerFilter(new HTMLPurifier_URIFilter_<strong>NameOfFilter</strong>());
-</pre>
-
-<p>
-  Now, your filter will only be called when %URI.<strong>NameOfFilter</strong>
-  is set to true.
-</p>
 
 <h2>Post-filter</h2>
 
@@ -213,4 +200,5 @@ $uri->registerFilter(new HTMLPurifier_URIFilter_<strong>NameOfFilter</strong>())
 
 </body></html>
 
-<!-- vim: et sw=4 sts=4 -->
+<!-- vim: et sw=4 sts=4
+-->

docs/enduser-utf8.html

@@ -1056,4 +1056,5 @@ a more in-depth look into character sets and encodings.</p>
 </body>
 </html>
 
-<!-- vim: et sw=4 sts=4 -->
+<!-- vim: et sw=4 sts=4
+-->

docs/enduser-youtube.html

@@ -67,7 +67,7 @@ into your documents. YouTube's code goes like this:</p>
 </ol>
 
 <p>What point 2 means is that if we have code like <code>&lt;span
-class=&quot;embed-youtube&quot;&gt;AyPzM5WK8ys&lt;/span&gt;</code> your
+class=&quot;youtube-embed&quot;&gt;AyPzM5WK8ys&lt;/span&gt;</code> your
 application can reconstruct the full object from this small snippet that
 passes through HTML Purifier <em>unharmed</em>.
 <a href="http://repo.or.cz/w/htmlpurifier.git?a=blob;hb=HEAD;f=library/HTMLPurifier/Filter/YouTube.php">Show me the code!</a></p>
@@ -75,7 +75,7 @@ passes through HTML Purifier <em>unharmed</em>.
 <p>And the corresponding usage:</p>
 
 <pre>&lt;?php
-    $config->set('Filter', 'YouTube', true);
+    $config-&gt;set('Filter.YouTube', true);
 ?&gt;</pre>
 
 <p>There is a bit going in the two code snippets, so let's explain.</p>
@@ -149,4 +149,5 @@ with the core!</p>
 </body>
 </html>
 
-<!-- vim: et sw=4 sts=4 -->
+<!-- vim: et sw=4 sts=4
+-->

docs/examples/basic.php

@@ -8,8 +8,8 @@ require_once '../../library/HTMLPurifier.auto.php';
 $config = HTMLPurifier_Config::createDefault();
 
 // configuration goes here:
-$config->set('Core', 'Encoding', 'UTF-8'); // replace with your encoding
+$config->set('Core.Encoding', 'UTF-8'); // replace with your encoding
-$config->set('HTML', 'Doctype', 'XHTML 1.0 Transitional'); // replace with your doctype
+$config->set('HTML.Doctype', 'XHTML 1.0 Transitional'); // replace with your doctype
 
 $purifier = new HTMLPurifier($config);
 

docs/fixquotes.htc

@@ -5,4 +5,5 @@ function init() {
 }
 </script>
 
-<!-- vim: et sw=4 sts=4 -->
+<!-- vim: et sw=4 sts=4
+-->

docs/index.html

@@ -117,6 +117,12 @@ the code. They may be upgraded to HTML files or stay as TXT scratchpads.</p>
     <td>Common security issues that may still arise (half-baked).</td>
 </tr>
 
+<tr>
+    <td>Development</td>
+    <td><a href="dev-config-bcbreaks.txt">Config BC Breaks</a></td>
+    <td>Backwards-incompatible changes in HTML Purifier 4.0.0</td>
+</tr>
+
 <tr>
     <td>Development</td>
     <td><a href="dev-code-quality.txt">Code Quality Issues</a></td>
@@ -178,4 +184,5 @@ the code. They may be upgraded to HTML files or stay as TXT scratchpads.</p>
 </body>
 </html>
 
-<!-- vim: et sw=4 sts=4 -->
+<!-- vim: et sw=4 sts=4
+-->

docs/proposal-colors.html

@@ -45,4 +45,5 @@ something like that?</li>
 </body>
 </html>
 
-<!-- vim: et sw=4 sts=4 -->
+<!-- vim: et sw=4 sts=4
+-->

docs/proposal-plists.txt

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

docs/ref-devnetwork.html

@@ -43,4 +43,5 @@ the development of this library in these forum threads:</p>
 </body>
 </html>
 
-<!-- vim: et sw=4 sts=4 -->
+<!-- vim: et sw=4 sts=4
+-->

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

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

docs/specimens/jochem-blok-word.html

@@ -127,5 +127,3 @@ style='color:black'>www.example.com/disclaimer</span></a><o:p></o:p></span></p>
 </body>
 
 </html>
-
-<!-- vim: et sw=4 sts=4 -->

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

@@ -72,5 +72,3 @@ 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 -->

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 3.3.0
+ * @version 4.1.1
  *
  * @warning
  *      You must *not* include any other HTML Purifier files before this file,
@@ -98,6 +98,8 @@ require 'HTMLPurifier/AttrDef/CSS/Percentage.php';
 require 'HTMLPurifier/AttrDef/CSS/TextDecoration.php';
 require 'HTMLPurifier/AttrDef/CSS/URI.php';
 require 'HTMLPurifier/AttrDef/HTML/Bool.php';
+require 'HTMLPurifier/AttrDef/HTML/Nmtokens.php';
+require 'HTMLPurifier/AttrDef/HTML/Class.php';
 require 'HTMLPurifier/AttrDef/HTML/Color.php';
 require 'HTMLPurifier/AttrDef/HTML/FrameTarget.php';
 require 'HTMLPurifier/AttrDef/HTML/ID.php';
@@ -105,7 +107,6 @@ require 'HTMLPurifier/AttrDef/HTML/Pixels.php';
 require 'HTMLPurifier/AttrDef/HTML/Length.php';
 require 'HTMLPurifier/AttrDef/HTML/LinkTypes.php';
 require 'HTMLPurifier/AttrDef/HTML/MultiLength.php';
-require 'HTMLPurifier/AttrDef/HTML/Nmtokens.php';
 require 'HTMLPurifier/AttrDef/URI/Email.php';
 require 'HTMLPurifier/AttrDef/URI/Host.php';
 require 'HTMLPurifier/AttrDef/URI/IPv4.php';
@@ -123,6 +124,7 @@ require 'HTMLPurifier/AttrTransform/Input.php';
 require 'HTMLPurifier/AttrTransform/Lang.php';
 require 'HTMLPurifier/AttrTransform/Length.php';
 require 'HTMLPurifier/AttrTransform/Name.php';
+require 'HTMLPurifier/AttrTransform/NameSync.php';
 require 'HTMLPurifier/AttrTransform/SafeEmbed.php';
 require 'HTMLPurifier/AttrTransform/SafeObject.php';
 require 'HTMLPurifier/AttrTransform/SafeParam.php';
@@ -174,6 +176,7 @@ require 'HTMLPurifier/Injector/DisplayLinkURI.php';
 require 'HTMLPurifier/Injector/Linkify.php';
 require 'HTMLPurifier/Injector/PurifierLinkify.php';
 require 'HTMLPurifier/Injector/RemoveEmpty.php';
+require 'HTMLPurifier/Injector/RemoveSpansWithoutAttributes.php';
 require 'HTMLPurifier/Injector/SafeObject.php';
 require 'HTMLPurifier/Lexer/DOMLex.php';
 require 'HTMLPurifier/Lexer/DirectLex.php';
@@ -196,6 +199,7 @@ require 'HTMLPurifier/URIFilter/DisableExternalResources.php';
 require 'HTMLPurifier/URIFilter/HostBlacklist.php';
 require 'HTMLPurifier/URIFilter/MakeAbsolute.php';
 require 'HTMLPurifier/URIFilter/Munge.php';
+require 'HTMLPurifier/URIScheme/data.php';
 require 'HTMLPurifier/URIScheme/ftp.php';
 require 'HTMLPurifier/URIScheme/http.php';
 require 'HTMLPurifier/URIScheme/https.php';

library/HTMLPurifier.kses.php

@@ -17,11 +17,11 @@ function kses($string, $allowed_html, $allowed_protocols = null) {
             $allowed_attributes["$element.$attribute"] = true;
         }
     }
-    $config->set('HTML', 'AllowedElements', $allowed_elements);
+    $config->set('HTML.AllowedElements', $allowed_elements);
-    $config->set('HTML', 'AllowedAttributes', $allowed_attributes);
+    $config->set('HTML.AllowedAttributes', $allowed_attributes);
     $allowed_schemes = array();
     if ($allowed_protocols !== null) {
-        $config->set('URI', 'AllowedSchemes', $allowed_protocols);
+        $config->set('URI.AllowedSchemes', $allowed_protocols);
     }
     $purifier = new HTMLPurifier($config);
     return $purifier->purify($string);

library/HTMLPurifier.php

@@ -19,7 +19,7 @@
  */
 
 /*
-    HTML Purifier 3.3.0 - Standards Compliant HTML Filtering
+    HTML Purifier 4.1.1 - 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 = '3.3.0';
+    public $version = '4.1.1';
 
     /** Constant with version of HTML Purifier */
-    const VERSION = '3.3.0';
+    const VERSION = '4.1.1';
 
     /** Global configuration object */
     public $config;
@@ -128,7 +128,7 @@ class HTMLPurifier
         $context->register('Generator', $this->generator);
 
         // set up global context variables
-        if ($config->get('Core', 'CollectErrors')) {
+        if ($config->get('Core.CollectErrors')) {
             // may get moved out if other facilities use it
             $language_factory = HTMLPurifier_LanguageFactory::instance();
             $language = $language_factory->create($config, $context);
@@ -152,6 +152,7 @@ class HTMLPurifier
         $filters = array();
         foreach ($filter_flags as $filter => $flag) {
             if (!$flag) continue;
+            if (strpos($filter, '.') !== false) continue;
             $class = "HTMLPurifier_Filter_$filter";
             $filters[] = new $class;
         }

library/HTMLPurifier.safe-includes.php

@@ -92,6 +92,8 @@ require_once $__dir . '/HTMLPurifier/AttrDef/CSS/Percentage.php';
 require_once $__dir . '/HTMLPurifier/AttrDef/CSS/TextDecoration.php';
 require_once $__dir . '/HTMLPurifier/AttrDef/CSS/URI.php';
 require_once $__dir . '/HTMLPurifier/AttrDef/HTML/Bool.php';
+require_once $__dir . '/HTMLPurifier/AttrDef/HTML/Nmtokens.php';
+require_once $__dir . '/HTMLPurifier/AttrDef/HTML/Class.php';
 require_once $__dir . '/HTMLPurifier/AttrDef/HTML/Color.php';
 require_once $__dir . '/HTMLPurifier/AttrDef/HTML/FrameTarget.php';
 require_once $__dir . '/HTMLPurifier/AttrDef/HTML/ID.php';
@@ -99,7 +101,6 @@ require_once $__dir . '/HTMLPurifier/AttrDef/HTML/Pixels.php';
 require_once $__dir . '/HTMLPurifier/AttrDef/HTML/Length.php';
 require_once $__dir . '/HTMLPurifier/AttrDef/HTML/LinkTypes.php';
 require_once $__dir . '/HTMLPurifier/AttrDef/HTML/MultiLength.php';
-require_once $__dir . '/HTMLPurifier/AttrDef/HTML/Nmtokens.php';
 require_once $__dir . '/HTMLPurifier/AttrDef/URI/Email.php';
 require_once $__dir . '/HTMLPurifier/AttrDef/URI/Host.php';
 require_once $__dir . '/HTMLPurifier/AttrDef/URI/IPv4.php';
@@ -117,6 +118,7 @@ require_once $__dir . '/HTMLPurifier/AttrTransform/Input.php';
 require_once $__dir . '/HTMLPurifier/AttrTransform/Lang.php';
 require_once $__dir . '/HTMLPurifier/AttrTransform/Length.php';
 require_once $__dir . '/HTMLPurifier/AttrTransform/Name.php';
+require_once $__dir . '/HTMLPurifier/AttrTransform/NameSync.php';
 require_once $__dir . '/HTMLPurifier/AttrTransform/SafeEmbed.php';
 require_once $__dir . '/HTMLPurifier/AttrTransform/SafeObject.php';
 require_once $__dir . '/HTMLPurifier/AttrTransform/SafeParam.php';
@@ -168,6 +170,7 @@ require_once $__dir . '/HTMLPurifier/Injector/DisplayLinkURI.php';
 require_once $__dir . '/HTMLPurifier/Injector/Linkify.php';
 require_once $__dir . '/HTMLPurifier/Injector/PurifierLinkify.php';
 require_once $__dir . '/HTMLPurifier/Injector/RemoveEmpty.php';
+require_once $__dir . '/HTMLPurifier/Injector/RemoveSpansWithoutAttributes.php';
 require_once $__dir . '/HTMLPurifier/Injector/SafeObject.php';
 require_once $__dir . '/HTMLPurifier/Lexer/DOMLex.php';
 require_once $__dir . '/HTMLPurifier/Lexer/DirectLex.php';
@@ -190,6 +193,7 @@ 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/data.php';
 require_once $__dir . '/HTMLPurifier/URIScheme/ftp.php';
 require_once $__dir . '/HTMLPurifier/URIScheme/http.php';
 require_once $__dir . '/HTMLPurifier/URIScheme/https.php';

library/HTMLPurifier/AttrDef.php

@@ -82,6 +82,42 @@ abstract class HTMLPurifier_AttrDef
         return preg_replace('/rgb\((\d+)\s*,\s*(\d+)\s*,\s*(\d+)\)/', 'rgb(\1,\2,\3)', $string);
     }
 
+    /**
+     * Parses a possibly escaped CSS string and returns the "pure" 
+     * version of it.
+     */
+    protected function expandCSSEscape($string) {
+        // flexibly parse it
+        $ret = '';
+        for ($i = 0, $c = strlen($string); $i < $c; $i++) {
+            if ($string[$i] === '\\') {
+                $i++;
+                if ($i >= $c) {
+                    $ret .= '\\';
+                    break;
+                }
+                if (ctype_xdigit($string[$i])) {
+                    $code = $string[$i];
+                    for ($a = 1, $i++; $i < $c && $a < 6; $i++, $a++) {
+                        if (!ctype_xdigit($string[$i])) break;
+                        $code .= $string[$i];
+                    }
+                    // We have to be extremely careful when adding
+                    // new characters, to make sure we're not breaking
+                    // the encoding.
+                    $char = HTMLPurifier_Encoder::unichr(hexdec($code));
+                    if (HTMLPurifier_Encoder::cleanUTF8($char) === '') continue;
+                    $ret .= $char;
+                    if ($i < $c && trim($string[$i]) !== '') $i--;
+                    continue;
+                }
+                if ($string[$i] === "\n") continue;
+            }
+            $ret .= $string[$i];
+        }
+        return $ret;
+    }
+
 }
 
 // vim: et sw=4 sts=4

library/HTMLPurifier/AttrDef/CSS/BackgroundPosition.php

@@ -59,7 +59,8 @@ class HTMLPurifier_AttrDef_CSS_BackgroundPosition extends HTMLPurifier_AttrDef
         $keywords = array();
         $keywords['h'] = false; // left, right
         $keywords['v'] = false; // top, bottom
-        $keywords['c'] = false; // center
+        $keywords['ch'] = false; // center (first word)
+        $keywords['cv'] = false; // center (second word)
         $measures = array();
 
         $i = 0;
@@ -79,6 +80,13 @@ class HTMLPurifier_AttrDef_CSS_BackgroundPosition extends HTMLPurifier_AttrDef
             $lbit = ctype_lower($bit) ? $bit : strtolower($bit);
             if (isset($lookup[$lbit])) {
                 $status = $lookup[$lbit];
+                if ($status == 'c') {
+                    if ($i == 0) {
+                        $status = 'ch';
+                    } else {
+                        $status = 'cv';
+                    }
+                }
                 $keywords[$status] = $lbit;
                 $i++;
             }
@@ -101,20 +109,19 @@ class HTMLPurifier_AttrDef_CSS_BackgroundPosition extends HTMLPurifier_AttrDef
 
         if (!$i) return false; // no valid values were caught
 
-
         $ret = array();
 
         // first keyword
         if     ($keywords['h'])     $ret[] = $keywords['h'];
-        elseif (count($measures))   $ret[] = array_shift($measures);
+        elseif ($keywords['ch']) {
-        elseif ($keywords['c']) {
+            $ret[] = $keywords['ch'];
-            $ret[] = $keywords['c'];
+            $keywords['cv'] = false; // prevent re-use: center = center center
-            $keywords['c'] = false; // prevent re-use: center = center center
         }
+        elseif (count($measures))   $ret[] = array_shift($measures);
 
         if     ($keywords['v'])     $ret[] = $keywords['v'];
+        elseif ($keywords['cv'])    $ret[] = $keywords['cv'];
         elseif (count($measures))   $ret[] = array_shift($measures);
-        elseif ($keywords['c'])     $ret[] = $keywords['c'];
 
         if (empty($ret)) return false;
         return implode(' ', $ret);

library/HTMLPurifier/AttrDef/CSS/Color.php

@@ -9,7 +9,7 @@ class HTMLPurifier_AttrDef_CSS_Color extends HTMLPurifier_AttrDef
     public function validate($color, $config, $context) {
 
         static $colors = null;
-        if ($colors === null) $colors = $config->get('Core', 'ColorKeywords');
+        if ($colors === null) $colors = $config->get('Core.ColorKeywords');
 
         $color = trim($color);
         if ($color === '') return false;

library/HTMLPurifier/AttrDef/CSS/FontFamily.php

@@ -34,37 +34,10 @@ class HTMLPurifier_AttrDef_CSS_FontFamily extends HTMLPurifier_AttrDef
                 $quote = $font[0];
                 if ($font[$length - 1] !== $quote) continue;
                 $font = substr($font, 1, $length - 2);
-
-                $new_font = '';
-                for ($i = 0, $c = strlen($font); $i < $c; $i++) {
-                    if ($font[$i] === '\\') {
-                        $i++;
-                        if ($i >= $c) {
-                            $new_font .= '\\';
-                            break;
-                        }
-                        if (ctype_xdigit($font[$i])) {
-                            $code = $font[$i];
-                            for ($a = 1, $i++; $i < $c && $a < 6; $i++, $a++) {
-                                if (!ctype_xdigit($font[$i])) break;
-                                $code .= $font[$i];
-                            }
-                            // We have to be extremely careful when adding
-                            // new characters, to make sure we're not breaking
-                            // the encoding.
-                            $char = HTMLPurifier_Encoder::unichr(hexdec($code));
-                            if (HTMLPurifier_Encoder::cleanUTF8($char) === '') continue;
-                            $new_font .= $char;
-                            if ($i < $c && trim($font[$i]) !== '') $i--;
-                            continue;
-                        }
-                        if ($font[$i] === "\n") continue;
-                    }
-                    $new_font .= $font[$i];
-                }
-
-                $font = $new_font;
             }
+
+            $font = $this->expandCSSEscape($font);
+
             // $font is a pure representation of the font name
 
             if (ctype_alnum($font) && $font !== '') {
@@ -73,12 +46,21 @@ class HTMLPurifier_AttrDef_CSS_FontFamily extends HTMLPurifier_AttrDef
                 continue;
             }
 
-            // complicated font, requires quoting
+            // bugger out on whitespace.  form feed (0C) really
+            // shouldn't show up regardless
+            $font = str_replace(array("\n", "\t", "\r", "\x0C"), ' ', $font);
 
-            // armor single quotes and new lines
+            // These ugly transforms don't pose a security
-            $font = str_replace("\\", "\\\\", $font);
+            // risk (as \\ and \" might).  We could try to be clever and
-            $font = str_replace("'", "\\'", $font);
+            // use single-quote wrapping when there is a double quote
-            $final .= "'$font', ";
+            // present, but I have choosen not to implement that.
+            // (warning: this code relies on the selection of quotation
+            // mark below)
+            $font = str_replace('\\', '\\5C ', $font);
+            $font = str_replace('"',  '\\22 ', $font);
+
+            // complicated font, requires quoting
+            $final .= "\"$font\", "; // note that this will later get turned into &quot;
         }
         $final = rtrim($final, ', ');
         if ($final === '') return false;

library/HTMLPurifier/AttrDef/CSS/URI.php

@@ -34,20 +34,16 @@ class HTMLPurifier_AttrDef_CSS_URI extends HTMLPurifier_AttrDef_URI
             $uri = substr($uri, 1, $new_length - 1);
         }
 
-        $keys   = array(  '(',   ')',   ',',   ' ',   '"',   "'");
+        $uri = $this->expandCSSEscape($uri);
-        $values = array('\\(', '\\)', '\\,', '\\ ', '\\"', "\\'");
-        $uri = str_replace($values, $keys, $uri);
 
         $result = parent::validate($uri, $config, $context);
 
         if ($result === false) return false;
 
-        // escape necessary characters according to CSS spec
+        // extra sanity check; should have been done by URI
-        // except for the comma, none of these should appear in the
+        $result = str_replace(array('"', "\\", "\n", "\x0c", "\r"), "", $result);
-        // URI at all
-        $result = str_replace($keys, $values, $result);
 
-        return "url($result)";
+        return "url(\"$result\")";
 
     }
 

library/HTMLPurifier/AttrDef/HTML/Class.php

@@ -0,0 +1,34 @@
+<?php
+
+/**
+ * Implements special behavior for class attribute (normally NMTOKENS)
+ */
+class HTMLPurifier_AttrDef_HTML_Class extends HTMLPurifier_AttrDef_HTML_Nmtokens
+{
+    protected function split($string, $config, $context) {
+        // really, this twiddle should be lazy loaded
+        $name = $config->getDefinition('HTML')->doctype->name;
+        if ($name == "XHTML 1.1" || $name == "XHTML 2.0") {
+            return parent::split($string, $config, $context);
+        } else {
+            return preg_split('/\s+/', $string);
+        }
+    }
+    protected function filter($tokens, $config, $context) {
+        $allowed = $config->get('Attr.AllowedClasses');
+        $forbidden = $config->get('Attr.ForbiddenClasses');
+        $ret = array();
+        foreach ($tokens as $token) {
+            if (
+                ($allowed === null || isset($allowed[$token])) &&
+                !isset($forbidden[$token]) &&
+                // We need this O(n) check because of PHP's array
+                // implementation that casts -0 to 0.
+                !in_array($token, $ret, true)
+            ) {
+                $ret[] = $token;
+            }
+        }
+        return $ret;
+    }
+}

library/HTMLPurifier/AttrDef/HTML/Color.php

@@ -9,7 +9,7 @@ class HTMLPurifier_AttrDef_HTML_Color extends HTMLPurifier_AttrDef
     public function validate($string, $config, $context) {
 
         static $colors = null;
-        if ($colors === null) $colors = $config->get('Core', 'ColorKeywords');
+        if ($colors === null) $colors = $config->get('Core.ColorKeywords');
 
         $string = trim($string);
 

library/HTMLPurifier/AttrDef/HTML/FrameTarget.php

@@ -12,7 +12,7 @@ class HTMLPurifier_AttrDef_HTML_FrameTarget extends HTMLPurifier_AttrDef_Enum
     public function __construct() {}
 
     public function validate($string, $config, $context) {
-        if ($this->valid_values === false) $this->valid_values = $config->get('Attr', 'AllowedFrameTargets');
+        if ($this->valid_values === false) $this->valid_values = $config->get('Attr.AllowedFrameTargets');
         return parent::validate($string, $config, $context);
     }
 

library/HTMLPurifier/AttrDef/HTML/ID.php

@@ -17,18 +17,18 @@ class HTMLPurifier_AttrDef_HTML_ID extends HTMLPurifier_AttrDef
 
     public function validate($id, $config, $context) {
 
-        if (!$config->get('Attr', 'EnableID')) return false;
+        if (!$config->get('Attr.EnableID')) return false;
 
         $id = trim($id); // trim it first
 
         if ($id === '') return false;
 
-        $prefix = $config->get('Attr', 'IDPrefix');
+        $prefix = $config->get('Attr.IDPrefix');
         if ($prefix !== '') {
-            $prefix .= $config->get('Attr', 'IDPrefixLocal');
+            $prefix .= $config->get('Attr.IDPrefixLocal');
             // prevent re-appending the prefix
             if (strpos($id, $prefix) !== 0) $id = $prefix . $id;
-        } elseif ($config->get('Attr', 'IDPrefixLocal') !== '') {
+        } elseif ($config->get('Attr.IDPrefixLocal') !== '') {
             trigger_error('%Attr.IDPrefixLocal cannot be used unless '.
                 '%Attr.IDPrefix is set', E_USER_WARNING);
         }
@@ -51,7 +51,7 @@ class HTMLPurifier_AttrDef_HTML_ID extends HTMLPurifier_AttrDef
             $result = ($trim === '');
         }
 
-        $regexp = $config->get('Attr', 'IDBlacklistRegexp');
+        $regexp = $config->get('Attr.IDBlacklistRegexp');
         if ($regexp && preg_match($regexp, $id)) {
             return false;
         }

library/HTMLPurifier/AttrDef/HTML/LinkTypes.php

@@ -27,7 +27,7 @@ class HTMLPurifier_AttrDef_HTML_LinkTypes extends HTMLPurifier_AttrDef
 
     public function validate($string, $config, $context) {
 
-        $allowed = $config->get('Attr', $this->name);
+        $allowed = $config->get('Attr.' . $this->name);
         if (empty($allowed)) return false;
 
         $string = $this->parseCDATA($string);

library/HTMLPurifier/AttrDef/HTML/Nmtokens.php

@@ -2,10 +2,6 @@
 
 /**
  * Validates contents based on NMTOKENS attribute type.
- * @note The only current use for this is the class attribute in HTML
- * @note Could have some functionality factored out into Nmtoken class
- * @warning We cannot assume this class will be used only for 'class'
- *          attributes. Not sure how to hook in magic behavior, then.
  */
 class HTMLPurifier_AttrDef_HTML_Nmtokens extends HTMLPurifier_AttrDef
 {
@@ -17,6 +13,17 @@ class HTMLPurifier_AttrDef_HTML_Nmtokens extends HTMLPurifier_AttrDef
         // early abort: '' and '0' (strings that convert to false) are invalid
         if (!$string) return false;
 
+        $tokens = $this->split($string, $config, $context);
+        $tokens = $this->filter($tokens, $config, $context);
+        if (empty($tokens)) return false;
+        return implode(' ', $tokens);
+
+    }
+
+    /**
+     * Splits a space separated list of tokens into its constituent parts.
+     */
+    protected function split($string, $config, $context) {
         // OPTIMIZABLE!
         // do the preg_match, capture all subpatterns for reformulation
 
@@ -24,23 +31,20 @@ class HTMLPurifier_AttrDef_HTML_Nmtokens extends HTMLPurifier_AttrDef
         // escaping because I don't know how to do that with regexps
         // and plus it would complicate optimization efforts (you never
         // see that anyway).
-        $matches = array();
         $pattern = '/(?:(?<=\s)|\A)'. // look behind for space or string start
                    '((?:--|-?[A-Za-z_])[A-Za-z_\-0-9]*)'.
                    '(?:(?=\s)|\z)/'; // look ahead for space or string end
         preg_match_all($pattern, $string, $matches);
+        return $matches[1];
+    }
 
-        if (empty($matches[1])) return false;
+    /**
-
+     * Template method for removing certain tokens based on arbitrary criteria.
-        // reconstruct string
+     * @note If we wanted to be really functional, we'd do an array_filter
-        $new_string = '';
+     *       with a callback. But... we're not.
-        foreach ($matches[1] as $token) {
+     */
-            $new_string .= $token . ' ';
+    protected function filter($tokens, $config, $context) {
-        }
+        return $tokens;
-        $new_string = rtrim($new_string);
-
-        return $new_string;
-
     }
 
 }

library/HTMLPurifier/AttrDef/URI.php

@@ -25,7 +25,7 @@ class HTMLPurifier_AttrDef_URI extends HTMLPurifier_AttrDef
 
     public function validate($uri, $config, $context) {
 
-        if ($config->get('URI', 'Disable')) return false;
+        if ($config->get('URI.Disable')) return false;
 
         $uri = $this->parseCDATA($uri);
 

library/HTMLPurifier/AttrTransform/BdoDir.php

@@ -10,7 +10,7 @@ class HTMLPurifier_AttrTransform_BdoDir extends HTMLPurifier_AttrTransform
 
     public function transform($attr, $config, $context) {
         if (isset($attr['dir'])) return $attr;
-        $attr['dir'] = $config->get('Attr', 'DefaultTextDir');
+        $attr['dir'] = $config->get('Attr.DefaultTextDir');
         return $attr;
     }
 

library/HTMLPurifier/AttrTransform/ImgRequired.php

@@ -15,21 +15,22 @@ class HTMLPurifier_AttrTransform_ImgRequired extends HTMLPurifier_AttrTransform
 
         $src = true;
         if (!isset($attr['src'])) {
-            if ($config->get('Core', 'RemoveInvalidImg')) return $attr;
+            if ($config->get('Core.RemoveInvalidImg')) return $attr;
-            $attr['src'] = $config->get('Attr', 'DefaultInvalidImage');
+            $attr['src'] = $config->get('Attr.DefaultInvalidImage');
             $src = false;
         }
 
         if (!isset($attr['alt'])) {
             if ($src) {
-                $alt = $config->get('Attr', 'DefaultImageAlt');
+                $alt = $config->get('Attr.DefaultImageAlt');
                 if ($alt === null) {
-                    $attr['alt'] = basename($attr['src']);
+                    // truncate if the alt is too long
+                    $attr['alt'] = substr(basename($attr['src']),0,40);
                 } else {
                     $attr['alt'] = $alt;
                 }
             } else {
-                $attr['alt'] = $config->get('Attr', 'DefaultInvalidImageAlt');
+                $attr['alt'] = $config->get('Attr.DefaultInvalidImageAlt');
             }
         }
 

library/HTMLPurifier/AttrTransform/Name.php

@@ -7,6 +7,8 @@ class HTMLPurifier_AttrTransform_Name extends HTMLPurifier_AttrTransform
 {
 
     public function transform($attr, $config, $context) {
+        // Abort early if we're using relaxed definition of name
+        if ($config->get('HTML.Attr.Name.UseCDATA')) return $attr;
         if (!isset($attr['name'])) return $attr;
         $id = $this->confiscateAttr($attr, 'name');
         if ( isset($attr['id']))   return $attr;

library/HTMLPurifier/AttrTransform/NameSync.php

@@ -0,0 +1,27 @@
+<?php
+
+/**
+ * Post-transform that performs validation to the name attribute; if
+ * it is present with an equivalent id attribute, it is passed through;
+ * otherwise validation is performed.
+ */
+class HTMLPurifier_AttrTransform_NameSync extends HTMLPurifier_AttrTransform
+{
+
+    public function __construct() {
+        $this->idDef = new HTMLPurifier_AttrDef_HTML_ID();
+    }
+
+    public function transform($attr, $config, $context) {
+        if (!isset($attr['name'])) return $attr;
+        $name = $attr['name'];
+        if (isset($attr['id']) && $attr['id'] === $name) return $attr;
+        $result = $this->idDef->validate($name, $config, $context);
+        if ($result === false) unset($attr['name']);
+        else $attr['name'] = $result;
+        return $attr;
+    }
+
+}
+
+// vim: et sw=4 sts=4

library/HTMLPurifier/AttrTransform/SafeParam.php

@@ -37,8 +37,14 @@ class HTMLPurifier_AttrTransform_SafeParam extends HTMLPurifier_AttrTransform
                 $attr['value'] = 'window';
                 break;
             case 'movie':
+            case 'src':
+                $attr['name'] = "movie";
                 $attr['value'] = $this->uri->validate($attr['value'], $config, $context);
                 break;
+            case 'flashvars':
+                // we're going to allow arbitrary inputs to the SWF, on
+                // the reasoning that it could only hack the SWF, not us.
+                break;
             // add other cases to support other param name/value pairs
             default:
                 $attr['name'] = $attr['value'] = null;

library/HTMLPurifier/AttrTypes.php

@@ -36,6 +36,9 @@ class HTMLPurifier_AttrTypes
         $this->info['Charsets'] = new HTMLPurifier_AttrDef_Text();
         $this->info['Character'] = new HTMLPurifier_AttrDef_Text();
 
+        // "proprietary" types
+        $this->info['Class'] = new HTMLPurifier_AttrDef_HTML_Class();
+
         // number is really a positive integer (one or more digits)
         // FIXME: ^^ not always, see start and value of list items
         $this->info['Number']   = new HTMLPurifier_AttrDef_Integer(false, false, true);

library/HTMLPurifier/CSSDefinition.php

@@ -154,7 +154,7 @@ class HTMLPurifier_CSSDefinition extends HTMLPurifier_Definition
             new HTMLPurifier_AttrDef_CSS_Percentage(true),
             new HTMLPurifier_AttrDef_Enum(array('auto'))
         ));
-        $max = $config->get('CSS', 'MaxImgLength');
+        $max = $config->get('CSS.MaxImgLength');
 
         $this->info['width'] =
         $this->info['height'] =
@@ -211,15 +211,15 @@ class HTMLPurifier_CSSDefinition extends HTMLPurifier_Definition
         // partial support
         $this->info['white-space'] = new HTMLPurifier_AttrDef_Enum(array('nowrap'));
 
-        if ($config->get('CSS', 'Proprietary')) {
+        if ($config->get('CSS.Proprietary')) {
             $this->doSetupProprietary($config);
         }
 
-        if ($config->get('CSS', 'AllowTricky')) {
+        if ($config->get('CSS.AllowTricky')) {
             $this->doSetupTricky($config);
         }
 
-        $allow_important = $config->get('CSS', 'AllowImportant');
+        $allow_important = $config->get('CSS.AllowImportant');
         // wrap all attr-defs with decorator that handles !important
         foreach ($this->info as $k => $v) {
             $this->info[$k] = new HTMLPurifier_AttrDef_CSS_ImportantDecorator($v, $allow_important);
@@ -272,7 +272,7 @@ class HTMLPurifier_CSSDefinition extends HTMLPurifier_Definition
         // setup allowed elements
         $support = "(for information on implementing this, see the ".
                    "support forums) ";
-        $allowed_attributes = $config->get('CSS', 'AllowedProperties');
+        $allowed_attributes = $config->get('CSS.AllowedProperties');
         if ($allowed_attributes !== null) {
             foreach ($this->info as $name => $d) {
                 if(!isset($allowed_attributes[$name])) unset($this->info[$name]);

library/HTMLPurifier/ChildDef/Required.php

@@ -59,7 +59,7 @@ class HTMLPurifier_ChildDef_Required extends HTMLPurifier_ChildDef
         $all_whitespace = true;
 
         // some configuration
-        $escape_invalid_children = $config->get('Core', 'EscapeInvalidChildren');
+        $escape_invalid_children = $config->get('Core.EscapeInvalidChildren');
 
         // generator
         $gen = new HTMLPurifier_Generator($config, $context);

library/HTMLPurifier/Config.php

@@ -20,7 +20,7 @@ class HTMLPurifier_Config
     /**
      * HTML Purifier's version
      */
-    public $version = '3.3.0';
+    public $version = '4.1.1';
 
     /**
      * Bool indicator whether or not to automatically finalize
@@ -68,12 +68,30 @@ class HTMLPurifier_Config
      */
     protected $plist;
 
+    /**
+     * Whether or not a set is taking place due to an
+     * alias lookup.
+     */
+    private $aliasMode;
+
+    /**
+     * Set to false if you do not want line and file numbers in errors
+     * (useful when unit testing)
+     */
+    public $chatty = true;
+
+    /**
+     * Current lock; only gets to this namespace are allowed.
+     */
+    private $lock;
+
     /**
      * @param $definition HTMLPurifier_ConfigSchema that defines what directives
      *                    are allowed.
      */
-    public function __construct($definition) {
+    public function __construct($definition, $parent = null) {
-        $this->plist = new HTMLPurifier_PropertyList($definition->defaultPlist);
+        $parent = $parent ? $parent : $definition->defaultPlist;
+        $this->plist = new HTMLPurifier_PropertyList($parent);
         $this->def = $definition; // keep a copy around for checking
         $this->parser = new HTMLPurifier_VarParser_Flexible();
     }
@@ -102,6 +120,16 @@ class HTMLPurifier_Config
         return $ret;
     }
 
+    /**
+     * Creates a new config object that inherits from a previous one.
+     * @param HTMLPurifier_Config $config Configuration object to inherit
+     *        from.
+     * @return HTMLPurifier_Config object with $config as its parent.
+     */
+    public static function inherit(HTMLPurifier_Config $config) {
+        return new HTMLPurifier_Config($config->def, $config->plist);
+    }
+
     /**
      * Convenience constructor that creates a default configuration object.
      * @return Default HTMLPurifier_Config object.
@@ -114,24 +142,34 @@ class HTMLPurifier_Config
 
     /**
      * Retreives a value from the configuration.
-     * @param $namespace String namespace
      * @param $key String key
      */
-    public function get($namespace, $key) {
+    public function get($key, $a = null) {
-        if (!$this->finalized) $this->autoFinalize ? $this->finalize() : $this->plist->squash(true);
+        if ($a !== null) {
-        if (!isset($this->def->info[$namespace][$key])) {
+            $this->triggerError("Using deprecated API: use \$config->get('$key.$a') instead", E_USER_WARNING);
+            $key = "$key.$a";
+        }
+        if (!$this->finalized) $this->autoFinalize();
+        if (!isset($this->def->info[$key])) {
             // can't add % due to SimpleTest bug
-            trigger_error('Cannot retrieve value of undefined directive ' . htmlspecialchars("$namespace.$key"),
+            $this->triggerError('Cannot retrieve value of undefined directive ' . htmlspecialchars($key),
                 E_USER_WARNING);
             return;
         }
-        if (isset($this->def->info[$namespace][$key]->isAlias)) {
+        if (isset($this->def->info[$key]->isAlias)) {
-            $d = $this->def->info[$namespace][$key];
+            $d = $this->def->info[$key];
-            trigger_error('Cannot get value from aliased directive, use real name ' . $d->namespace . '.' . $d->name,
+            $this->triggerError('Cannot get value from aliased directive, use real name ' . $d->key,
                 E_USER_ERROR);
             return;
         }
-        return $this->plist->get("$namespace.$key");
+        if ($this->lock) {
+            list($ns) = explode('.', $key);
+            if ($ns !== $this->lock) {
+                $this->triggerError('Cannot get value of namespace ' . $ns . ' when lock for ' . $this->lock . ' is active, this probably indicates a Definition setup method is accessing directives that are not within its namespace', E_USER_ERROR);
+                return;
+            }
+        }
+        return $this->plist->get($key);
     }
 
     /**
@@ -139,13 +177,13 @@ class HTMLPurifier_Config
      * @param $namespace String namespace
      */
     public function getBatch($namespace) {
-        if (!$this->finalized) $this->autoFinalize ? $this->finalize() : $this->plist->squash(true);
+        if (!$this->finalized) $this->autoFinalize();
-        if (!isset($this->def->info[$namespace])) {
+        $full = $this->getAll();
-            trigger_error('Cannot retrieve undefined namespace ' . htmlspecialchars($namespace),
+        if (!isset($full[$namespace])) {
+            $this->triggerError('Cannot retrieve undefined namespace ' . htmlspecialchars($namespace),
                 E_USER_WARNING);
             return;
         }
-        $full = $this->getAll();
         return $full[$namespace];
     }
 
@@ -178,9 +216,10 @@ class HTMLPurifier_Config
 
     /**
      * Retrieves all directives, organized by namespace
+     * @warning This is a pretty inefficient function, avoid if you can
      */
     public function getAll() {
-        if (!$this->finalized) $this->autoFinalize ? $this->finalize() : $this->plist->squash(true);
+        if (!$this->finalized) $this->autoFinalize();
         $ret = array();
         foreach ($this->plist->squash() as $name => $value) {
             list($ns, $key) = explode('.', $name, 2);
@@ -191,29 +230,37 @@ class HTMLPurifier_Config
 
     /**
      * Sets a value to configuration.
-     * @param $namespace String namespace
      * @param $key String key
      * @param $value Mixed value
      */
-    public function set($namespace, $key, $value, $from_alias = false) {
+    public function set($key, $value, $a = null) {
+        if (strpos($key, '.') === false) {
+            $namespace = $key;
+            $directive = $value;
+            $value = $a;
+            $key = "$key.$directive";
+            $this->triggerError("Using deprecated API: use \$config->set('$key', ...) instead", E_USER_NOTICE);
+        } else {
+            list($namespace) = explode('.', $key);
+        }
         if ($this->isFinalized('Cannot set directive after finalization')) return;
-        if (!isset($this->def->info[$namespace][$key])) {
+        if (!isset($this->def->info[$key])) {
-            trigger_error('Cannot set undefined directive ' . htmlspecialchars("$namespace.$key") . ' to value',
+            $this->triggerError('Cannot set undefined directive ' . htmlspecialchars($key) . ' to value',
                 E_USER_WARNING);
             return;
         }
-        $def = $this->def->info[$namespace][$key];
+        $def = $this->def->info[$key];
 
         if (isset($def->isAlias)) {
-            if ($from_alias) {
+            if ($this->aliasMode) {
-                trigger_error('Double-aliases not allowed, please fix '.
+                $this->triggerError('Double-aliases not allowed, please fix '.
-                    'ConfigSchema bug with' . "$namespace.$key", E_USER_ERROR);
+                    'ConfigSchema bug with' . $key, E_USER_ERROR);
                 return;
             }
-            $this->set($new_ns  = $def->namespace,
+            $this->aliasMode = true;
-                       $new_dir = $def->name,
+            $this->set($def->key, $value);
-                       $value, true);
+            $this->aliasMode = false;
-            trigger_error("$namespace.$key is an alias, preferred directive name is $new_ns.$new_dir", E_USER_NOTICE);
+            $this->triggerError("$key is an alias, preferred directive name is {$def->key}", E_USER_NOTICE);
             return;
         }
 
@@ -231,7 +278,7 @@ class HTMLPurifier_Config
         try {
             $value = $this->parser->parse($value, $type, $allow_null);
         } catch (HTMLPurifier_VarParserException $e) {
-            trigger_error('Value for ' . "$namespace.$key" . ' is of invalid type, should be ' . HTMLPurifier_VarParser::getTypeName($type), E_USER_WARNING);
+            $this->triggerError('Value for ' . $key . ' is of invalid type, should be ' . HTMLPurifier_VarParser::getTypeName($type), E_USER_WARNING);
             return;
         }
         if (is_string($value) && is_object($def)) {
@@ -241,17 +288,17 @@ class HTMLPurifier_Config
             }
             // check to see if the value is allowed
             if (isset($def->allowed) && !isset($def->allowed[$value])) {
-                trigger_error('Value not supported, valid values are: ' .
+                $this->triggerError('Value not supported, valid values are: ' .
                     $this->_listify($def->allowed), E_USER_WARNING);
                 return;
             }
         }
-        $this->plist->set("$namespace.$key", $value);
+        $this->plist->set($key, $value);
 
         // reset definitions if the directives they depend on changed
         // this is a very costly process, so it's discouraged
         // with finalization
-        if ($namespace == 'HTML' || $namespace == 'CSS') {
+        if ($namespace == 'HTML' || $namespace == 'CSS' || $namespace == 'URI') {
             $this->definitions[$namespace] = null;
         }
 
@@ -291,9 +338,13 @@ class HTMLPurifier_Config
      * @param $raw  Whether or not definition should be returned raw
      */
     public function getDefinition($type, $raw = false) {
-        if (!$this->finalized) $this->autoFinalize ? $this->finalize() : $this->plist->squash(true);
+        if (!$this->finalized) $this->autoFinalize();
+        // temporarily suspend locks, so we can handle recursive definition calls
+        $lock = $this->lock;
+        $this->lock = null;
         $factory = HTMLPurifier_DefinitionCacheFactory::instance();
         $cache = $factory->create($type, $this);
+        $this->lock = $lock;
         if (!$raw) {
             // see if we can quickly supply a definition
             if (!empty($this->definitions[$type])) {
@@ -328,14 +379,16 @@ class HTMLPurifier_Config
         }
         // quick abort if raw
         if ($raw) {
-            if (is_null($this->get($type, 'DefinitionID'))) {
+            if (is_null($this->get($type . '.DefinitionID'))) {
                 // fatally error out if definition ID not set
                 throw new HTMLPurifier_Exception("Cannot retrieve raw version without specifying %$type.DefinitionID");
             }
             return $this->definitions[$type];
         }
         // set it up
+        $this->lock = $type;
         $this->definitions[$type]->setup($this);
+        $this->lock = null;
         // save in cache
         $cache->set($this->definitions[$type], $this);
         return $this->definitions[$type];
@@ -351,14 +404,12 @@ class HTMLPurifier_Config
         foreach ($config_array as $key => $value) {
             $key = str_replace('_', '.', $key);
             if (strpos($key, '.') !== false) {
-                // condensed form
+                $this->set($key, $value);
-                list($namespace, $directive) = explode('.', $key);
-                $this->set($namespace, $directive, $value);
             } else {
                 $namespace = $key;
                 $namespace_values = $value;
                 foreach ($namespace_values as $directive => $value) {
-                    $this->set($namespace, $directive, $value);
+                    $this->set($namespace .'.'. $directive, $value);
                 }
             }
         }
@@ -394,16 +445,15 @@ class HTMLPurifier_Config
              }
         }
         $ret = array();
-        foreach ($schema->info as $ns => $keypairs) {
+        foreach ($schema->info as $key => $def) {
-            foreach ($keypairs as $directive => $def) {
+            list($ns, $directive) = explode('.', $key, 2);
-                if ($allowed !== true) {
+            if ($allowed !== true) {
-                    if (isset($blacklisted_directives["$ns.$directive"])) continue;
+                if (isset($blacklisted_directives["$ns.$directive"])) continue;
-                    if (!isset($allowed_directives["$ns.$directive"]) && !isset($allowed_ns[$ns])) continue;
+                if (!isset($allowed_directives["$ns.$directive"]) && !isset($allowed_ns[$ns])) continue;
-                }
-                if (isset($def->isAlias)) continue;
-                if ($directive == 'DefinitionID' || $directive == 'DefinitionRev') continue;
-                $ret[] = array($ns, $directive);
             }
+            if (isset($def->isAlias)) continue;
+            if ($directive == 'DefinitionID' || $directive == 'DefinitionRev') continue;
+            $ret[] = array($ns, $directive);
         }
         return $ret;
     }
@@ -472,7 +522,7 @@ class HTMLPurifier_Config
      */
     public function isFinalized($error = false) {
         if ($this->finalized && $error) {
-            trigger_error($error, E_USER_ERROR);
+            $this->triggerError($error, E_USER_ERROR);
         }
         return $this->finalized;
     }
@@ -482,7 +532,11 @@ class HTMLPurifier_Config
      * already finalized
      */
     public function autoFinalize() {
-        if (!$this->finalized && $this->autoFinalize) $this->finalize();
+        if ($this->autoFinalize) {
+            $this->finalize();
+        } else {
+            $this->plist->squash(true);
+        }
     }
 
     /**
@@ -490,6 +544,35 @@ class HTMLPurifier_Config
      */
     public function finalize() {
         $this->finalized = true;
+        unset($this->parser);
+    }
+
+    /**
+     * Produces a nicely formatted error message by supplying the
+     * stack frame information from two levels up and OUTSIDE of
+     * HTMLPurifier_Config.
+     */
+    protected function triggerError($msg, $no) {
+        // determine previous stack frame
+        $backtrace = debug_backtrace();
+        if ($this->chatty && isset($backtrace[1])) {
+            $frame = $backtrace[1];
+            $extra = " on line {$frame['line']} in file {$frame['file']}";
+        } else {
+            $extra = '';
+        }
+        trigger_error($msg . $extra, $no);
+    }
+
+    /**
+     * Returns a serialized form of the configuration object that can
+     * be reconstituted.
+     */
+    public function serialize() {
+        $this->getDefinition('HTML');
+        $this->getDefinition('CSS');
+        $this->getDefinition('URI');
+        return serialize($this);
     }
 
 }

library/HTMLPurifier/ConfigSchema.php

@@ -87,24 +87,13 @@ class HTMLPurifier_ConfigSchema {
      *      HTMLPurifier_DirectiveDef::$type for allowed values
      * @param $allow_null Whether or not to allow null values
      */
-    public function add($namespace, $name, $default, $type, $allow_null) {
+    public function add($key, $default, $type, $allow_null) {
         $obj = new stdclass();
         $obj->type = is_int($type) ? $type : HTMLPurifier_VarParser::$types[$type];
         if ($allow_null) $obj->allow_null = true;
-        $this->info[$namespace][$name] = $obj;
+        $this->info[$key] = $obj;
-        $this->defaults[$namespace][$name] = $default;
+        $this->defaults[$key] = $default;
-        $this->defaultPlist->set("$namespace.$name", $default);
+        $this->defaultPlist->set($key, $default);
-    }
-
-    /**
-     * Defines a namespace for directives to be put into.
-     * @warning This is slightly different from the corresponding static
-     *          method.
-     * @param $namespace Namespace's name
-     */
-    public function addNamespace($namespace) {
-        $this->info[$namespace] = array();
-        $this->defaults[$namespace] = array();
     }
 
     /**
@@ -116,12 +105,12 @@ class HTMLPurifier_ConfigSchema {
      * @param $name Name of Directive
      * @param $aliases Hash of aliased values to the real alias
      */
-    public function addValueAliases($namespace, $name, $aliases) {
+    public function addValueAliases($key, $aliases) {
-        if (!isset($this->info[$namespace][$name]->aliases)) {
+        if (!isset($this->info[$key]->aliases)) {
-            $this->info[$namespace][$name]->aliases = array();
+            $this->info[$key]->aliases = array();
         }
         foreach ($aliases as $alias => $real) {
-            $this->info[$namespace][$name]->aliases[$alias] = $real;
+            $this->info[$key]->aliases[$alias] = $real;
         }
     }
 
@@ -133,8 +122,8 @@ class HTMLPurifier_ConfigSchema {
      * @param $name Name of directive
      * @param $allowed Lookup array of allowed values
      */
-    public function addAllowedValues($namespace, $name, $allowed) {
+    public function addAllowedValues($key, $allowed) {
-        $this->info[$namespace][$name]->allowed = $allowed;
+        $this->info[$key]->allowed = $allowed;
     }
 
     /**
@@ -144,88 +133,26 @@ class HTMLPurifier_ConfigSchema {
      * @param $new_namespace
      * @param $new_name Directive that the alias will be to
      */
-    public function addAlias($namespace, $name, $new_namespace, $new_name) {
+    public function addAlias($key, $new_key) {
         $obj = new stdclass;
-        $obj->namespace = $new_namespace;
+        $obj->key = $new_key;
-        $obj->name = $new_name;
         $obj->isAlias = true;
-        $this->info[$namespace][$name] = $obj;
+        $this->info[$key] = $obj;
     }
 
     /**
      * Replaces any stdclass that only has the type property with type integer.
      */
     public function postProcess() {
-        foreach ($this->info as $namespace => $info) {
+        foreach ($this->info as $key => $v) {
-            foreach ($info as $directive => $v) {
+            if (count((array) $v) == 1) {
-                if (count((array) $v) == 1) {
+                $this->info[$key] = $v->type;
-                    $this->info[$namespace][$directive] = $v->type;
+            } elseif (count((array) $v) == 2 && isset($v->allow_null)) {
-                } elseif (count((array) $v) == 2 && isset($v->allow_null)) {
+                $this->info[$key] = -$v->type;
-                    $this->info[$namespace][$directive] = -$v->type;
-                }
             }
         }
     }
 
-    // DEPRECATED METHODS
-
-    /** @see HTMLPurifier_ConfigSchema->set() */
-    public static function define($namespace, $name, $default, $type, $description) {
-        HTMLPurifier_ConfigSchema::deprecated(__METHOD__);
-        $type_values = explode('/', $type, 2);
-        $type = $type_values[0];
-        $modifier = isset($type_values[1]) ? $type_values[1] : false;
-        $allow_null = ($modifier === 'null');
-        $def = HTMLPurifier_ConfigSchema::instance();
-        $def->add($namespace, $name, $default, $type, $allow_null);
-    }
-
-    /** @see HTMLPurifier_ConfigSchema->addNamespace() */
-    public static function defineNamespace($namespace, $description) {
-        HTMLPurifier_ConfigSchema::deprecated(__METHOD__);
-        $def = HTMLPurifier_ConfigSchema::instance();
-        $def->addNamespace($namespace);
-    }
-
-    /** @see HTMLPurifier_ConfigSchema->addValueAliases() */
-    public static function defineValueAliases($namespace, $name, $aliases) {
-        HTMLPurifier_ConfigSchema::deprecated(__METHOD__);
-        $def = HTMLPurifier_ConfigSchema::instance();
-        $def->addValueAliases($namespace, $name, $aliases);
-    }
-
-    /** @see HTMLPurifier_ConfigSchema->addAllowedValues() */
-    public static function defineAllowedValues($namespace, $name, $allowed_values) {
-        HTMLPurifier_ConfigSchema::deprecated(__METHOD__);
-        $allowed = array();
-        foreach ($allowed_values as $value) {
-            $allowed[$value] = true;
-        }
-        $def = HTMLPurifier_ConfigSchema::instance();
-        $def->addAllowedValues($namespace, $name, $allowed);
-    }
-
-    /** @see HTMLPurifier_ConfigSchema->addAlias() */
-    public static function defineAlias($namespace, $name, $new_namespace, $new_name) {
-        HTMLPurifier_ConfigSchema::deprecated(__METHOD__);
-        $def = HTMLPurifier_ConfigSchema::instance();
-        $def->addAlias($namespace, $name, $new_namespace, $new_name);
-    }
-
-    /** @deprecated, use HTMLPurifier_VarParser->parse() */
-    public function validate($a, $b, $c = false) {
-        trigger_error("HTMLPurifier_ConfigSchema->validate deprecated, use HTMLPurifier_VarParser->parse instead", E_USER_NOTICE);
-        $parser = new HTMLPurifier_VarParser();
-        return $parser->parse($a, $b, $c);
-    }
-
-    /**
-     * Throws an E_USER_NOTICE stating that a method is deprecated.
-     */
-    private static function deprecated($method) {
-        trigger_error("Static HTMLPurifier_ConfigSchema::$method deprecated, use add*() method instead", E_USER_NOTICE);
-    }
-
 }
 
 // vim: et sw=4 sts=4

library/HTMLPurifier/ConfigSchema/Builder/ConfigSchema.php

@@ -9,36 +9,28 @@ class HTMLPurifier_ConfigSchema_Builder_ConfigSchema
 
     public function build($interchange) {
         $schema = new HTMLPurifier_ConfigSchema();
-        foreach ($interchange->namespaces as $n) {
-            $schema->addNamespace($n->namespace);
-        }
         foreach ($interchange->directives as $d) {
             $schema->add(
-                $d->id->namespace,
+                $d->id->key,
-                $d->id->directive,
                 $d->default,
                 $d->type,
                 $d->typeAllowsNull
             );
             if ($d->allowed !== null) {
                 $schema->addAllowedValues(
-                    $d->id->namespace,
+                    $d->id->key,
-                    $d->id->directive,
                     $d->allowed
                 );
             }
             foreach ($d->aliases as $alias) {
                 $schema->addAlias(
-                    $alias->namespace,
+                    $alias->key,
-                    $alias->directive,
+                    $d->id->key
-                    $d->id->namespace,
-                    $d->id->directive
                 );
             }
             if ($d->valueAliases !== null) {
                 $schema->addValueAliases(
-                    $d->id->namespace,
+                    $d->id->key,
-                    $d->id->directive,
                     $d->valueAliases
                 );
             }

library/HTMLPurifier/ConfigSchema/Builder/Xml.php

@@ -8,6 +8,7 @@ class HTMLPurifier_ConfigSchema_Builder_Xml extends XMLWriter
 {
 
     protected $interchange;
+    private $namespace;
 
     protected function writeHTMLDiv($html) {
         $this->startElement('div');
@@ -34,36 +35,33 @@ class HTMLPurifier_ConfigSchema_Builder_Xml extends XMLWriter
         $this->startElement('configdoc');
         $this->writeElement('title', $interchange->name);
 
-        foreach ($interchange->namespaces as $namespace) {
+        foreach ($interchange->directives as $directive) {
-            $this->buildNamespace($namespace);
+            $this->buildDirective($directive);
         }
 
+        if ($this->namespace) $this->endElement(); // namespace
+
         $this->endElement(); // configdoc
         $this->flush();
     }
 
-    public function buildNamespace($namespace) {
+    public function buildDirective($directive) {
-        $this->startElement('namespace');
-        $this->writeAttribute('id', $namespace->namespace);
 
-        $this->writeElement('name', $namespace->namespace);
+        // Kludge, although I suppose having a notion of a "root namespace"
-        $this->startElement('description');
+        // certainly makes things look nicer when documentation is built.
-            $this->writeHTMLDiv($namespace->description);
+        // Depends on things being sorted.
-        $this->endElement(); // description
+        if (!$this->namespace || $this->namespace !== $directive->id->getRootNamespace()) {
-
+            if ($this->namespace) $this->endElement(); // namespace
-        foreach ($this->interchange->directives as $directive) {
+            $this->namespace = $directive->id->getRootNamespace();
-            if ($directive->id->namespace !== $namespace->namespace) continue;
+            $this->startElement('namespace');
-            $this->buildDirective($directive);
+            $this->writeAttribute('id', $this->namespace);
+            $this->writeElement('name', $this->namespace);
         }
 
-        $this->endElement(); // namespace
-    }
-
-    public function buildDirective($directive) {
         $this->startElement('directive');
         $this->writeAttribute('id', $directive->id->toString());
 
-        $this->writeElement('name', $directive->id->directive);
+        $this->writeElement('name', $directive->id->getDirective());
 
         $this->startElement('aliases');
             foreach ($directive->aliases as $alias) $this->writeElement('alias', $alias->toString());

library/HTMLPurifier/ConfigSchema/Interchange.php

@@ -13,26 +13,11 @@ class HTMLPurifier_ConfigSchema_Interchange
      */
     public $name;
 
-    /**
-     * Array of Namespace ID => array(namespace info)
-     */
-    public $namespaces = array();
-
     /**
      * Array of Directive ID => array(directive info)
      */
     public $directives = array();
 
-    /**
-     * Adds a namespace array to $namespaces
-     */
-    public function addNamespace($namespace) {
-        if (isset($this->namespaces[$i = $namespace->namespace])) {
-            throw new HTMLPurifier_ConfigSchema_Exception("Cannot redefine namespace '$i'");
-        }
-        $this->namespaces[$i] = $namespace;
-    }
-
     /**
      * Adds a directive array to $directives
      */

library/HTMLPurifier/ConfigSchema/Interchange/Id.php

@@ -6,11 +6,10 @@
 class HTMLPurifier_ConfigSchema_Interchange_Id
 {
 
-    public $namespace, $directive;
+    public $key;
 
-    public function __construct($namespace, $directive) {
+    public function __construct($key) {
-        $this->namespace = $namespace;
+        $this->key = $key;
-        $this->directive = $directive;
     }
 
     /**
@@ -18,12 +17,19 @@ class HTMLPurifier_ConfigSchema_Interchange_Id
      *          cause problems for PHP 5.0 support.
      */
     public function toString() {
-        return $this->namespace . '.' . $this->directive;
+        return $this->key;
+    }
+
+    public function getRootNamespace() {
+        return substr($this->key, 0, strpos($this->key, "."));
+    }
+
+    public function getDirective() {
+        return substr($this->key, strpos($this->key, ".") + 1);
     }
 
     public static function make($id) {
-        list($namespace, $directive) = explode('.', $id);
+        return new HTMLPurifier_ConfigSchema_Interchange_Id($id);
-        return new HTMLPurifier_ConfigSchema_Interchange_Id($namespace, $directive);
     }
 
 }

library/HTMLPurifier/ConfigSchema/Interchange/Namespace.php

@@ -1,21 +0,0 @@
-<?php
-
-/**
- * Interchange component class describing namespaces.
- */
-class HTMLPurifier_ConfigSchema_Interchange_Namespace
-{
-
-    /**
-     * Name of namespace defined.
-     */
-    public $namespace;
-
-    /**
-     * HTML description.
-     */
-    public $description;
-
-}
-
-// vim: et sw=4 sts=4

library/HTMLPurifier/ConfigSchema/InterchangeBuilder.php

@@ -13,13 +13,17 @@ class HTMLPurifier_ConfigSchema_InterchangeBuilder
     }
 
     public static function buildFromDirectory($dir = null) {
-        $parser      = new HTMLPurifier_StringHashParser();
         $builder     = new HTMLPurifier_ConfigSchema_InterchangeBuilder();
         $interchange = new HTMLPurifier_ConfigSchema_Interchange();
+        return $builder->buildDir($interchange, $dir);
+    }
 
-        if (!$dir) $dir = HTMLPURIFIER_PREFIX . '/HTMLPurifier/ConfigSchema/schema/';
+    public function buildDir($interchange, $dir = null) {
-        $info = parse_ini_file($dir . 'info.ini');
+        if (!$dir) $dir = HTMLPURIFIER_PREFIX . '/HTMLPurifier/ConfigSchema/schema';
-        $interchange->name = $info['name'];
+        if (file_exists($dir . '/info.ini')) {
+            $info = parse_ini_file($dir . '/info.ini');
+            $interchange->name = $info['name'];
+        }
 
         $files = array();
         $dh = opendir($dir);
@@ -33,15 +37,20 @@ class HTMLPurifier_ConfigSchema_InterchangeBuilder
 
         sort($files);
         foreach ($files as $file) {
-            $builder->build(
+            $this->buildFile($interchange, $dir . '/' . $file);
-                $interchange,
-                new HTMLPurifier_StringHash( $parser->parseFile($dir . $file) )
-            );
         }
 
         return $interchange;
     }
 
+    public function buildFile($interchange, $file) {
+        $parser = new HTMLPurifier_StringHashParser();
+        $this->build(
+            $interchange,
+            new HTMLPurifier_StringHash( $parser->parseFile($file) )
+        );
+    }
+
     /**
      * Builds an interchange object based on a hash.
      * @param $interchange HTMLPurifier_ConfigSchema_Interchange object to build
@@ -55,22 +64,17 @@ class HTMLPurifier_ConfigSchema_InterchangeBuilder
             throw new HTMLPurifier_ConfigSchema_Exception('Hash does not have any ID');
         }
         if (strpos($hash['ID'], '.') === false) {
-            $this->buildNamespace($interchange, $hash);
+            if (count($hash) == 2 && isset($hash['DESCRIPTION'])) {
+                $hash->offsetGet('DESCRIPTION'); // prevent complaining
+            } else {
+                throw new HTMLPurifier_ConfigSchema_Exception('All directives must have a namespace');
+            }
         } else {
             $this->buildDirective($interchange, $hash);
         }
         $this->_findUnused($hash);
     }
 
-    public function buildNamespace($interchange, $hash) {
-        $namespace = new HTMLPurifier_ConfigSchema_Interchange_Namespace();
-        $namespace->namespace   = $hash->offsetGet('ID');
-        if (isset($hash['DESCRIPTION'])) {
-            $namespace->description = $hash->offsetGet('DESCRIPTION');
-        }
-        $interchange->addNamespace($namespace);
-    }
-
     public function buildDirective($interchange, $hash) {
         $directive = new HTMLPurifier_ConfigSchema_Interchange_Directive();
 

library/HTMLPurifier/ConfigSchema/Validator.php

@@ -39,10 +39,6 @@ class HTMLPurifier_ConfigSchema_Validator
         $this->aliases = array();
         // PHP is a bit lax with integer <=> string conversions in
         // arrays, so we don't use the identical !== comparison
-        foreach ($interchange->namespaces as $i => $namespace) {
-            if ($i != $namespace->namespace) $this->error(false, "Integrity violation: key '$i' does not match internal id '{$namespace->namespace}'");
-            $this->validateNamespace($namespace);
-        }
         foreach ($interchange->directives as $i => $directive) {
             $id = $directive->id->toString();
             if ($i != $id) $this->error(false, "Integrity violation: key '$i' does not match internal id '$id'");
@@ -51,20 +47,6 @@ class HTMLPurifier_ConfigSchema_Validator
         return true;
     }
 
-    /**
-     * Validates a HTMLPurifier_ConfigSchema_Interchange_Namespace object.
-     */
-    public function validateNamespace($n) {
-        $this->context[] = "namespace '{$n->namespace}'";
-        $this->with($n, 'namespace')
-            ->assertNotEmpty()
-            ->assertAlnum(); // implicit assertIsString handled by InterchangeBuilder
-        $this->with($n, 'description')
-            ->assertNotEmpty()
-            ->assertIsString(); // handled by InterchangeBuilder
-        array_pop($this->context);
-    }
-
     /**
      * Validates a HTMLPurifier_ConfigSchema_Interchange_Id object.
      */
@@ -75,12 +57,11 @@ class HTMLPurifier_ConfigSchema_Validator
             // handled by InterchangeBuilder
             $this->error(false, 'is not an instance of HTMLPurifier_ConfigSchema_Interchange_Id');
         }
-        if (!isset($this->interchange->namespaces[$id->namespace])) {
+        // keys are now unconstrained (we might want to narrow down to A-Za-z0-9.)
-            $this->error('namespace', 'does not exist'); // assumes that the namespace was validated already
+        // we probably should check that it has at least one namespace
-        }
+        $this->with($id, 'key')
-        $this->with($id, 'directive')
             ->assertNotEmpty()
-            ->assertAlnum(); // implicit assertIsString handled by InterchangeBuilder
+            ->assertIsString(); // implicit assertIsString handled by InterchangeBuilder
         array_pop($this->context);
     }
 

library/HTMLPurifier/ConfigSchema/schema/Attr.AllowedClasses.txt

@@ -0,0 +1,8 @@
+Attr.AllowedClasses
+TYPE: lookup/null
+VERSION: 4.0.0
+DEFAULT: null
+--DESCRIPTION--
+List of allowed class values in the class attribute. By default, this is null,
+which means all classes are allowed.
+--# vim: et sw=4 sts=4

library/HTMLPurifier/ConfigSchema/schema/Attr.ClassUseCDATA.txt

@@ -0,0 +1,19 @@
+Attr.ClassUseCDATA
+TYPE: bool/null
+DEFAULT: null
+VERSION: 4.0.0
+--DESCRIPTION--
+If null, class will auto-detect the doctype and, if matching XHTML 1.1 or
+XHTML 2.0, will use the restrictive NMTOKENS specification of class. Otherwise,
+it will use a relaxed CDATA definition.  If true, the relaxed CDATA definition
+is forced; if false, the NMTOKENS definition is forced.  To get behavior
+of HTML Purifier prior to 4.0.0, set this directive to false.
+
+Some rational behind the auto-detection:
+in previous versions of HTML Purifier, it was assumed that the form of
+class was NMTOKENS, as specified by the XHTML Modularization (representing
+XHTML 1.1 and XHTML 2.0).  The DTDs for HTML 4.01 and XHTML 1.0, however
+specify class as CDATA.  HTML 5 effectively defines it as CDATA, but
+with the additional constraint that each name should be unique (this is not
+explicitly outlined in previous specifications).
+--# vim: et sw=4 sts=4

library/HTMLPurifier/ConfigSchema/schema/Attr.ForbiddenClasses.txt

@@ -0,0 +1,8 @@
+Attr.ForbiddenClasses
+TYPE: lookup
+VERSION: 4.0.0
+DEFAULT: array()
+--DESCRIPTION--
+List of forbidden class values in the class attribute. By default, this is
+empty, which means that no classes are forbidden. See also %Attr.AllowedClasses.
+--# vim: et sw=4 sts=4

library/HTMLPurifier/ConfigSchema/schema/Attr.txt

@@ -1,3 +0,0 @@
-Attr
-DESCRIPTION: Features regarding attribute validation.
---# vim: et sw=4 sts=4

library/HTMLPurifier/ConfigSchema/schema/AutoFormat.PurifierLinkify.DocURL.txt

@@ -1,9 +1,9 @@
-AutoFormatParam.PurifierLinkifyDocURL
+AutoFormat.PurifierLinkify.DocURL
 TYPE: string
 VERSION: 2.0.1
 DEFAULT: '#%s'
+ALIASES: AutoFormatParam.PurifierLinkifyDocURL
 --DESCRIPTION--
-
 <p>
   Location of configuration documentation to link to, let %s substitute
   into the configuration's namespace and directive names sans the percent

library/HTMLPurifier/ConfigSchema/schema/AutoFormat.RemoveEmpty.RemoveNbsp.Exceptions.txt

@@ -0,0 +1,11 @@
+AutoFormat.RemoveEmpty.RemoveNbsp.Exceptions
+TYPE: lookup
+VERSION: 4.0.0
+DEFAULT: array('td' => true, 'th' => true)
+--DESCRIPTION--
+<p>
+  When %AutoFormat.RemoveEmpty and %AutoFormat.RemoveEmpty.RemoveNbsp
+  are enabled, this directive defines what HTML elements should not be
+  removede if they have only a non-breaking space in them.
+</p>
+--# vim: et sw=4 sts=4

library/HTMLPurifier/ConfigSchema/schema/AutoFormat.RemoveEmpty.RemoveNbsp.txt

@@ -0,0 +1,15 @@
+AutoFormat.RemoveEmpty.RemoveNbsp
+TYPE: bool
+VERSION: 4.0.0
+DEFAULT: false
+--DESCRIPTION--
+<p>
+  When enabled, HTML Purifier will treat any elements that contain only
+  non-breaking spaces as well as regular whitespace as empty, and remove
+  them when %AutoForamt.RemoveEmpty is enabled.
+</p>
+<p>
+  See %AutoFormat.RemoveEmpty.RemoveNbsp.Exceptions for a list of elements
+  that don't have this behavior applied to them.
+</p>
+--# vim: et sw=4 sts=4

library/HTMLPurifier/ConfigSchema/schema/AutoFormat.RemoveEmpty.txt

@@ -31,7 +31,8 @@ DEFAULT: false
 </p>
 <p>
   Elements that contain only whitespace will be treated as empty. Non-breaking
-  spaces, however, do not count as whitespace.
+  spaces, however, do not count as whitespace. See
+  %AutoFormat.RemoveEmpty.RemoveNbsp for alternate behavior.
 </p>
 <p>
   This algorithm is not perfect; you may still notice some empty tags,
@@ -39,7 +40,7 @@ DEFAULT: false
   because they were not permitted in that context, or tags that, after
   being auto-closed by another tag, where empty. This is for safety reasons
   to prevent clever code from breaking validation. The general rule of thumb:
-  if a tag looked empty on the way end, it will get removed; if HTML Purifier
+  if a tag looked empty on the way in, it will get removed; if HTML Purifier
   made it empty, it will stay.
 </p>
 --# vim: et sw=4 sts=4

library/HTMLPurifier/ConfigSchema/schema/AutoFormat.RemoveSpansWithoutAttributes.txt

@@ -0,0 +1,11 @@
+AutoFormat.RemoveSpansWithoutAttributes
+TYPE: bool
+VERSION: 4.0.1
+DEFAULT: false
+--DESCRIPTION--
+<p>
+  This directive causes <code>span</code> tags without any attributes
+  to be removed. It will also remove spans that had all attributes
+  removed during processing.
+</p>
+--# vim: et sw=4 sts=4

library/HTMLPurifier/ConfigSchema/schema/AutoFormat.txt

@@ -1,3 +0,0 @@
-AutoFormat
-DESCRIPTION: Configuration for activating auto-formatting functionality (also known as <code>Injector</code>s)
---# vim: et sw=4 sts=4

library/HTMLPurifier/ConfigSchema/schema/AutoFormatParam.txt

@@ -1,3 +0,0 @@
-AutoFormatParam
-DESCRIPTION: Configuration for customizing auto-formatting functionality
---# vim: et sw=4 sts=4

library/HTMLPurifier/ConfigSchema/schema/CSS.txt

@@ -1,3 +0,0 @@
-CSS
-DESCRIPTION: Configuration regarding allowed CSS.
---# vim: et sw=4 sts=4

library/HTMLPurifier/ConfigSchema/schema/Cache.txt

@@ -1,3 +0,0 @@
-Cache
-DESCRIPTION: Configuration for DefinitionCache and related subclasses.
---# vim: et sw=4 sts=4

library/HTMLPurifier/ConfigSchema/schema/Core.txt

@@ -1,3 +0,0 @@
-Core
-DESCRIPTION: Core features that are always available.
---# vim: et sw=4 sts=4

library/HTMLPurifier/ConfigSchema/schema/Filter.ExtractStyleBlocks.Escaping.txt

@@ -1,8 +1,8 @@
-FilterParam.ExtractStyleBlocksEscaping
+Filter.ExtractStyleBlocks.Escaping
 TYPE: bool
 VERSION: 3.0.0
 DEFAULT: true
-ALIASES: Filter.ExtractStyleBlocksEscaping
+ALIASES: Filter.ExtractStyleBlocksEscaping, FilterParam.ExtractStyleBlocksEscaping
 --DESCRIPTION--
 
 <p>

library/HTMLPurifier/ConfigSchema/schema/Filter.ExtractStyleBlocks.Scope.txt

@@ -1,8 +1,8 @@
-FilterParam.ExtractStyleBlocksScope
+Filter.ExtractStyleBlocks.Scope
 TYPE: string/null
 VERSION: 3.0.0
 DEFAULT: NULL
-ALIASES: Filter.ExtractStyleBlocksScope
+ALIASES: Filter.ExtractStyleBlocksScope, FilterParam.ExtractStyleBlocksScope
 --DESCRIPTION--
 
 <p>

library/HTMLPurifier/ConfigSchema/schema/Filter.ExtractStyleBlocks.TidyImpl.txt

@@ -1,7 +1,8 @@
-FilterParam.ExtractStyleBlocksTidyImpl
+Filter.ExtractStyleBlocks.TidyImpl
 TYPE: mixed/null
 VERSION: 3.1.0
 DEFAULT: NULL
+ALIASES: FilterParam.ExtractStyleBlocksTidyImpl
 --DESCRIPTION--
 <p>
   If left NULL, HTML Purifier will attempt to instantiate a <code>csstidy</code>

library/HTMLPurifier/ConfigSchema/schema/Filter.txt

@@ -1,3 +0,0 @@
-Filter
-DESCRIPTION: Directives for turning filters on and off, or specifying custom filters.
---# vim: et sw=4 sts=4

library/HTMLPurifier/ConfigSchema/schema/FilterParam.txt

@@ -1,3 +0,0 @@
-FilterParam
-DESCRIPTION: Configuration for filters.
---# vim: et sw=4 sts=4

library/HTMLPurifier/ConfigSchema/schema/HTML.Attr.Name.UseCDATA.txt

@@ -0,0 +1,11 @@
+HTML.Attr.Name.UseCDATA
+TYPE: bool
+DEFAULT: false
+VERSION: 4.0.0
+--DESCRIPTION--
+The W3C specification DTD defines the name attribute to be CDATA, not ID, due
+to limitations of DTD.  In certain documents, this relaxed behavior is desired,
+whether it is to specify duplicate names, or to specify names that would be
+illegal IDs (for example, names that begin with a digit.) Set this configuration
+directive to true to use the relaxed parsing rules.
+--# vim: et sw=4 sts=4

library/HTMLPurifier/ConfigSchema/schema/HTML.SafeEmbed.txt

@@ -7,8 +7,7 @@ DEFAULT: false
     Whether or not to permit embed tags in documents, with a number of extra
     security features added to prevent script execution. This is similar to
     what websites like MySpace do to embed tags. Embed is a proprietary
-    element and will cause your website to stop validating. You probably want
+    element and will cause your website to stop validating; you should
-    to enable this with %HTML.SafeObject.
+    see if you can use %Output.FlashCompat with %HTML.SafeObject instead
-    <strong>Highly experimental.</strong>
+    first.</p>
-</p>
 --# vim: et sw=4 sts=4

library/HTMLPurifier/ConfigSchema/schema/HTML.SafeObject.txt

@@ -6,9 +6,8 @@ DEFAULT: false
 <p>
     Whether or not to permit object tags in documents, with a number of extra
     security features added to prevent script execution. This is similar to
-    what websites like MySpace do to object tags. You may also want to
+    what websites like MySpace do to object tags.  You should also enable
-    enable %HTML.SafeEmbed for maximum interoperability with Internet Explorer,
+    %Output.FlashCompat in order to generate Internet Explorer
-    although embed tags will cause your website to stop validating.
+    compatibility code for your object tags.
-    <strong>Highly experimental.</strong>
 </p>
 --# vim: et sw=4 sts=4

library/HTMLPurifier/ConfigSchema/schema/HTML.txt

@@ -1,3 +0,0 @@
-HTML
-DESCRIPTION: Configuration regarding allowed HTML.
---# vim: et sw=4 sts=4

library/HTMLPurifier/ConfigSchema/schema/Output.FlashCompat.txt

@@ -0,0 +1,11 @@
+Output.FlashCompat
+TYPE: bool
+VERSION: 4.1.0
+DEFAULT: false
+--DESCRIPTION--
+<p>
+  If true, HTML Purifier will generate Internet Explorer compatibility
+  code for all object code.  This is highly recommended if you enable
+  %HTML.SafeObject.
+</p>
+--# vim: et sw=4 sts=4

library/HTMLPurifier/ConfigSchema/schema/Output.txt

@@ -1,3 +0,0 @@
-Output
-DESCRIPTION: Configuration relating to the generation of (X)HTML.
---# vim: et sw=4 sts=4

library/HTMLPurifier/ConfigSchema/schema/Test.txt

@@ -1,3 +0,0 @@
-Test
-DESCRIPTION: Developer testing configuration for our unit tests.
---# vim: et sw=4 sts=4