Release 3.2.0.

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

.gitattributes

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

.gitignore

@@ -0,0 +1,13 @@
+conf/
+test-settings.php
+library/HTMLPurifier/DefinitionCache/Serializer/*/
+library/standalone/
+library/HTMLPurifier.standalone.php
+configdoc/*.html
+configdoc/configdoc.xml
+*.phpt.diff
+*.phpt.exp
+*.phpt.log
+*.phpt.out
+*.phpt.php
+*.phpt.skip.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         = 3.1.0
+PROJECT_NUMBER         = 3.2.0
 
 # The OUTPUT_DIRECTORY tag is used to specify the (relative or absolute) 
 # base path where the generated documentation will be put. 

FOCUS

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

INSTALL

@@ -23,8 +23,9 @@ August 8, 2008.
 
 These optional extensions can enhance the capabilities of HTML Purifier:
 
-    * iconv : Converts text to and from non-UTF-8 encodings
+    * iconv  : Converts text to and from non-UTF-8 encodings
-    * tidy  : Used for pretty-printing HTML
+    * bcmath : Used for unit conversion and imagecrash protection
+    * tidy   : Used for pretty-printing HTML
 
 
 ---------------------------------------------------------------------------

NEWS

@@ -9,6 +9,150 @@ NEWS ( CHANGELOG and HISTORY )                                     HTMLPurifier
     . Internal change
 ==========================
 
+3.2.0, released 2008-10-31
+# Using %Core.CollectErrors forces line number/column tracking on, whereas
+  previously you could theoretically turn it off.
+# HTMLPurifier_Injector->notifyEnd() is formally deprecated. Please
+  use handleEnd() instead.
+! %Output.AttrSort for when you need your attributes in alphabetical order to
+  deal with a bug in FCKEditor. Requested by frank farmer.
+! Enable HTML comments when %HTML.Trusted is on. Requested by Waldo Jaquith.
+! Proper support for name attribute. It is now allowed and equivalent to the id
+  attribute in a and img tags, and is only converted to id when %HTML.TidyLevel 
+  is heavy (for all doctypes).
+! %AutoFormat.RemoveEmpty to remove some empty tags from documents. Please don't
+  use on hand-written HTML.
+! Add error-cases for unsupported elements in MakeWellFormed. This enables
+  the strategy to be used, standalone, on untrusted input.
+! %Core.AggressivelyFixLt is on by default. This causes more sensible
+  processing of left angled brackets in smileys and other whatnot.
+! Test scripts now have a 'type' parameter, which lets you say 'htmlpurifier',
+  'phpt', 'vtest', etc. in order to only execute those tests. This supercedes
+  the --only-phpt parameter, although for backwards-compatibility the flag
+  will still work. 
+! AutoParagraph auto-formatter will now preserve double-newlines upon output.
+  Users who are not performing inbound filtering, this may seem a little
+  useless, but as a bonus, the test suite and handling of edge cases is also
+  improved.
+! Experimental implementation of forms for %HTML.Trusted
+! Track column numbers when maintain line numbers is on
+! Proprietary 'background' attribute on table-related elements converted into
+  corresponding CSS.  Thanks Fusemail for sponsoring this feature!
+! Add forward(), forwardUntilEndToken(), backward() and current() to Injector
+  supertype.
+! HTMLPurifier_Injector->handleEnd() permits modification to end tokens. The
+  time of operation varies slightly from notifyEnd() as *all* end tokens are
+  processed by the injector before they are subject to the well-formedness rules.
+! %Attr.DefaultImageAlt allows overriding default behavior of setting alt to
+  basename of image when not present.
+! %AutoFormat.DisplayLinkURI neuters <a> tags into plain text URLs.
+- Fix two bugs in %URI.MakeAbsolute; one involving empty paths in base URLs,
+  the other involving an undefined $is_folder error.
+- Throw error when %Core.Encoding is set to a spurious value. Previously,
+  this errored silently and returned false.
+- Redirected stderr to stdout for flush error output.
+- %URI.DisableExternal will now use the host in %URI.Base if %URI.Host is not
+  available.
+- Do not re-munge URL if the output URL has the same host as the input URL.
+  Requested by Chris.
+- Fix error in documentation regarding %Filter.ExtractStyleBlocks
+- Prevent <![CDATA[<body></body>]]> from triggering %Core.ConvertDocumentToFragment
+- Fix bug with inline elements in blockquotes conflicting with strict doctype
+- Detect if HTML support is disabled for DOM by checking for loadHTML() method.
+- Fix bug where dots and double-dots in absolute URLs without hostname were
+  not collapsed by URIFilter_MakeAbsolute.
+- Fix bug with anonymous modules operating on SafeEmbed or SafeObject elements
+  by reordering their addition.
+- Will now throw exception on many error conditions during lexer creation; also
+  throw an exception when MaintainLineNumbers is true, but a non-tracksLineNumbers
+  is being used.
+- Detect if domxml extension is loaded, and use DirectLEx accordingly.
+- Improve handling of big numbers with floating point arithmetic in UnitConverter.
+  Reported by David Morton.
+. Strategy_MakeWellFormed now operates in-place, saving memory and allowing
+  for more interesting filter-backtracking
+. New HTMLPurifier_Injector->rewind() functionality, allows injectors to rewind
+  index to reprocess tokens.
+. StringHashParser now allows for multiline sections with "empty" content; 
+  previously the section would remain undefined.
+. Added --quick option to multitest.php, which tests only the most recent
+  release for each series.
+. Added --distro option to multitest.php, which accepts either 'normal' or
+  'standalone'. This supercedes --exclude-normal and --exclude-standalone
+
+3.1.1, released 2008-06-19
+# %URI.Munge now, by default, does not munge resources (for example, <img src="">)
+  In order to enable this again, please set %URI.MungeResources to true. 
+! More robust imagecrash protection with height/width CSS with %CSS.MaxImgLength,
+  and height/width HTML with %HTML.MaxImgLength.
+! %URI.MungeSecretKey for secure URI munging. Thanks Chris
+  for sponsoring this feature. Check out the corresponding documentation
+  for details. (Att Nightly testers: The API for this feature changed before
+  the general release. Namely, rename your directives %URI.SecureMungeSecretKey =>
+  %URI.MungeSecretKey and and %URI.SecureMunge => %URI.Munge)
+! Implemented post URI filtering. Set member variable $post to true to set
+  a URIFilter as such.
+! Allow modules to define injectors via $info_injector. Injectors are 
+  automatically disabled if injector's needed elements are not found.
+! Support for "safe" objects added, use %HTML.SafeObject and %HTML.SafeEmbed.
+  Thanks Chris for sponsoring. If you've been using ad hoc code from the
+  forums, PLEASE use this instead.
+! Added substitutions for %e, %n, %a and %p in %URI.Munge (in order,
+  embedded, tag name, attribute name, CSS property name). See %URI.Munge
+  for more details. Requested by Jochem Blok.
+- Disable percent height/width attributes for img.
+- AttrValidator operations are now atomic; updates to attributes are not
+  manifest in token until end of operations. This prevents naughty internal
+  code from directly modifying CurrentToken when they're not supposed to.
+  This semantics change was requested by frank farmer.
+- Percent encoding checks enabled for URI query and fragment
+- Fix stray backslashes in font-family; CSS Unicode character escapes are
+  now properly resolved (although *only* in font-family). Thanks Takeshi Terada
+  for reporting.
+- Improve parseCDATA algorithm to take into account newline normalization
+- Account for browser confusion between Yen character and backslash in
+  Shift_JIS encoding. This fix generalizes to any other encoding which is not
+  a strict superset of printable ASCII. Thanks Takeshi Terada for reporting.
+- Fix missing configuration parameter in Generator calls. Thanks vs for the
+  partial patch.
+- Improved adherence to Unicode by checking for non-character codepoints.
+  Thanks Geoffrey Sneddon for reporting. This may result in degraded
+  performance for extremely large inputs.
+- Allow CSS property-value pair ''text-decoration: none''. Thanks Jochem Blok
+  for reporting.
+. Added HTMLPurifier_UnitConverter and HTMLPurifier_Length for convenient
+  handling of CSS-style lengths. HTMLPurifier_AttrDef_CSS_Length now uses
+  this class.
+. API of HTMLPurifier_AttrDef_CSS_Length changed from __construct($disable_negative)
+  to __construct($min, $max). __construct(true) is equivalent to
+  __construct('0').
+. Added HTMLPurifier_AttrDef_Switch class
+. Rename HTMLPurifier_HTMLModule_Tidy->construct() to setup() and bubble method
+  up inheritance hierarchy to HTMLPurifier_HTMLModule. All HTMLModules
+  get this called with the configuration object.  All modules now
+  use this rather than __construct(), although legacy code using constructors
+  will still work--the new format, however, lets modules access the
+  configuration object for HTML namespace dependant tweaks.
+. AttrDef_HTML_Pixels now takes a single construction parameter, pixels.
+. ConfigSchema data-structure heavily optimized; on average it uses a third
+  the memory it did previously. The interface has changed accordingly,
+  consult changes to HTMLPurifier_Config for details.
+. Variable parsing types now are magic integers instead of strings
+. Added benchmark for ConfigSchema
+. HTMLPurifier_Generator requires $config and $context parameters. If you 
+  don't know what they should be, use HTMLPurifier_Config::createDefault()
+  and new HTMLPurifier_Context().
+. Printers now properly distinguish between output configuration, and 
+  target configuration. This is not applicable to scripts using
+  the Printers for HTML Purifier related tasks.
+. HTML/CSS Printers must be primed with prepareGenerator($gen_config), otherwise
+  fatal errors will ensue.
+. URIFilter->prepare can return false in order to abort loading of the filter
+. Factory for AttrDef_URI implemented, URI#embedded to indicate URI that embeds
+  an external resource.
+. %URI.Munge functionality factored out into a post-filter class.
+. Added CurrentCSSProperty context variable during CSS validation
+
 3.1.0, released 2008-05-18
 # Unnecessary references to objects (vestiges of PHP4) removed from method
   signatures.  The following methods do not need references when assigning from
@@ -33,7 +177,8 @@ NEWS ( CHANGELOG and HISTORY )                                     HTMLPurifier
   and allows for version numbers like "3.1.0-dev".
 ! %HTML.Allowed deals gracefully with whitespace anywhere, anytime!
 ! HTML Purifier's URI handling is a lot more robust, with much stricter
-  validation checks and better percent encoding handling.
+  validation checks and better percent encoding handling. Thanks Gareth Heyes
+  for indicating security vulnerabilities from lax percent encoding.
 ! Bootstrap autoloader deals more robustly with classes that don't exist,
   preventing class_exists($class, true) from barfing.
 - InterchangeBuilder now alphabetizes its lists

TODO

@@ -11,24 +11,28 @@ If no interest is expressed for a feature that may require a considerable
 amount of effort to implement, it may get endlessly delayed. Do not be
 afraid to cast your vote for the next feature to be implemented!
 
-- Implement validation for query and for fragment
+- Investigate how early internal structures can be accessed; this would
+  prevent structures from being parsed and serialized multiple times.
+- Built-in support for target="_blank" on all external links
+- Allow <a id="asdf" name="asdf">
+- Implement overflow CSS property (as per jlp09550)
 
 FUTURE VERSIONS
 ---------------
 
-3.2 release [It's All About Trust] (floating)
+3.3 release [It's All About Trust] (floating)
  # Implement untrusted, dangerous elements/attributes
-    - Objects and Forms are especially wanted
  # Implement IDREF support (harder than it seems, since you cannot have
    IDREFs to non-existent IDs)
  # Frameset XHTML 1.0 and HTML 4.01 doctypes
- - Research and implement a "safe" version of the Object module
+ - Implement <area>
+ - Figure out how to simultaneously set %CSS.Trusted and %HTML.Trusted (?)
 
-3.3 release [Error'ed]
+3.4 release [Error'ed]
  # Error logging for filtering/cleanup procedures
  - XSS-attempt detection--certain errors are flagged XSS-like
 
-3.4 release [Do What I Mean, Not What I Say]
+3.5 release [Do What I Mean, Not What I Say]
  # Additional support for poorly written HTML
     - Microsoft Word HTML cleaning (i.e. MsoNormal, but research essential!)
     - Friendly strict handling of <address> (block -> <br>)
@@ -39,7 +43,6 @@ FUTURE VERSIONS
     contents should be dropped or not (currently, there's code that could do
     something like this if it didn't drop the inner text too.)
  - Remove <span> tags that don't do anything (no attributes)
- - Remove empty inline tags<i></i>
  - Append something to duplicate IDs so they're still usable (impl. note: the
    dupe detector would also need to detect the suffix as well)
  - Externalize inline CSS to promote clean HTML, proposed by Sander Tekelenburg
@@ -49,14 +52,12 @@ FUTURE VERSIONS
    AttrDef class). Probably will use CSSTidy class?
  # More control over allowed CSS properties using a modularization
  # HTML 5 support
- # IRI support
+ # IRI support (this includes IDN)
  - Standardize token armor for all areas of processing
  - Convert RTL/LTR override characters to <bdo> tags, or vice versa on demand.
    Also, enable disabling of directionality
 
 5.0 release [To XML and Beyond]
- - AllowedAttributes and ForbiddenAttributes step on the toes of XML by
-   using periods; this needs to be changed.
  - Extended HTML capabilities based on namespacing and tag transforms (COMPLEX)
     - Hooks for adding custom processors to custom namespaced tags and
       attributes, offer default implementation
@@ -104,6 +105,7 @@ Neat feature related
  - Full set of color keywords. Also, a way to add onto them without
    finalizing the configuration object.
  - Write a var_export and memcached DefinitionCache - Denis
+ - Allow restriction of allowed class values
 
 Maintenance related (slightly boring)
  # CHMOD install script for PEAR installs

VERSION

@@ -1 +1 @@
-3.1.0
+3.2.0

WHATSNEW

@@ -1,10 +1,6 @@
-HTML Purifier 3.1.0 is the second release series for HTML Purifier on PHP 5
+HTML Purifier 3.2.0 is an amalgamation of new features and fixes that
-as well as a security update related to URIs. It shifts over to using
+have accumulated over a four month period.  Some notable features
-autoload, and also includes support for the !important CSS modifier,
+include %AutoFormat.RemoveEmpty, column tracking for tokens, 
-display and visibility CSS properties with %CSS.AllowTricky, marquee with
+%AutoFormat.DisplayLinkURI and %Attr.DefaultImageAlt.  There were also
-%HTML.Proprietary (had you scared for a moment, hmm?), a kses() wrapper,
+major improvements to the test suite interface, error collection output
-%CSS.AllowedProperties, %HTML.ForbiddenAttributes and
+and the auto-formatter framework.
-%HTML.ForbiddenElements and a totally revamped ConfigDoc system. Since the
-release candidate, there have also been a number of stability fixes such as
-improved URI escaping, a change in serializer ID format, and a relaxed
-format for %HTML.Allowed. And as always, numerous bugfixes.

benchmarks/ConfigSchema.php

@@ -0,0 +1,14 @@
+<?php
+
+chdir(dirname(__FILE__));
+
+//require_once '../library/HTMLPurifier.path.php';
+shell_exec('php ../maintenance/generate-schema-cache.php');
+require_once '../library/HTMLPurifier.path.php';
+require_once 'HTMLPurifier.includes.php';
+
+$begin = xdebug_memory_usage();
+
+$schema = HTMLPurifier_ConfigSchema::makeFromSerial();
+
+echo xdebug_memory_usage() - $begin;

configdoc/styles/plain.xsl

@@ -19,7 +19,7 @@
     <xsl:variable name="usageLookup" select="document('../usage.xml')/usage" />
     
     <!-- Twiddle this variable to get the columns as even as possible -->
-    <xsl:variable name="maxNumberAdjust" select="1" />
+    <xsl:variable name="maxNumberAdjust" select="2" />
     
     <xsl:template match="/">
         <html lang="en" xml:lang="en">

configdoc/usage.xml

@@ -5,35 +5,40 @@
    <line>131</line>
   </file>
   <file name="HTMLPurifier/Lexer.php">
-   <line>85</line>
+   <line>81</line>
   </file>
   <file name="HTMLPurifier/Lexer/DirectLex.php">
-   <line>50</line>
+   <line>53</line>
-   <line>62</line>
+   <line>73</line>
-   <line>327</line>
+   <line>348</line>
   </file>
   <file name="HTMLPurifier/Strategy/RemoveForeignElements.php">
-   <line>44</line>
+   <line>47</line>
+  </file>
+ </directive>
+ <directive id="CSS.MaxImgLength">
+  <file name="HTMLPurifier/CSSDefinition.php">
+   <line>157</line>
   </file>
  </directive>
  <directive id="CSS.Proprietary">
   <file name="HTMLPurifier/CSSDefinition.php">
-   <line>202</line>
+   <line>214</line>
   </file>
  </directive>
  <directive id="CSS.AllowTricky">
   <file name="HTMLPurifier/CSSDefinition.php">
-   <line>206</line>
+   <line>218</line>
   </file>
  </directive>
  <directive id="CSS.AllowImportant">
   <file name="HTMLPurifier/CSSDefinition.php">
-   <line>210</line>
+   <line>222</line>
   </file>
  </directive>
  <directive id="CSS.AllowedProperties">
   <file name="HTMLPurifier/CSSDefinition.php">
-   <line>262</line>
+   <line>274</line>
   </file>
  </directive>
  <directive id="Cache.DefinitionImpl">
@@ -63,106 +68,116 @@
  </directive>
  <directive id="Core.Encoding">
   <file name="HTMLPurifier/Encoder.php">
-   <line>281</line>
+   <line>267</line>
-   <line>305</line>
+   <line>300</line>
   </file>
  </directive>
  <directive id="Test.ForceNoIconv">
   <file name="HTMLPurifier/Encoder.php">
-   <line>283</line>
+   <line>272</line>
-   <line>310</line>
+   <line>308</line>
   </file>
  </directive>
  <directive id="Core.EscapeNonASCIICharacters">
   <file name="HTMLPurifier/Encoder.php">
-   <line>307</line>
+   <line>304</line>
-  </file>
- </directive>
- <directive id="Core.MaintainLineNumbers">
-  <file name="HTMLPurifier/ErrorCollector.php">
-   <line>81</line>
-  </file>
-  <file name="HTMLPurifier/Lexer.php">
-   <line>82</line>
-  </file>
-  <file name="HTMLPurifier/Lexer/DirectLex.php">
-   <line>45</line>
   </file>
  </directive>
  <directive id="Output.CommentScriptContents">
   <file name="HTMLPurifier/Generator.php">
-   <line>41</line>
+   <line>45</line>
+  </file>
+ </directive>
+ <directive id="Output.SortAttr">
+  <file name="HTMLPurifier/Generator.php">
+   <line>46</line>
   </file>
  </directive>
  <directive id="Output.TidyFormat">
   <file name="HTMLPurifier/Generator.php">
-   <line>70</line>
+   <line>75</line>
   </file>
  </directive>
  <directive id="Output.Newline">
   <file name="HTMLPurifier/Generator.php">
-   <line>84</line>
+   <line>89</line>
   </file>
  </directive>
  <directive id="HTML.BlockWrapper">
   <file name="HTMLPurifier/HTMLDefinition.php">
-   <line>213</line>
+   <line>222</line>
   </file>
  </directive>
  <directive id="HTML.Parent">
   <file name="HTMLPurifier/HTMLDefinition.php">
-   <line>221</line>
+   <line>230</line>
   </file>
  </directive>
  <directive id="HTML.AllowedElements">
   <file name="HTMLPurifier/HTMLDefinition.php">
-   <line>238</line>
+   <line>247</line>
   </file>
  </directive>
  <directive id="HTML.AllowedAttributes">
   <file name="HTMLPurifier/HTMLDefinition.php">
-   <line>239</line>
+   <line>248</line>
   </file>
  </directive>
  <directive id="HTML.Allowed">
   <file name="HTMLPurifier/HTMLDefinition.php">
-   <line>242</line>
+   <line>251</line>
   </file>
  </directive>
  <directive id="HTML.ForbiddenElements">
   <file name="HTMLPurifier/HTMLDefinition.php">
-   <line>328</line>
+   <line>337</line>
   </file>
  </directive>
  <directive id="HTML.ForbiddenAttributes">
   <file name="HTMLPurifier/HTMLDefinition.php">
-   <line>329</line>
+   <line>338</line>
   </file>
  </directive>
  <directive id="HTML.Trusted">
   <file name="HTMLPurifier/HTMLModuleManager.php">
-   <line>198</line>
+   <line>202</line>
   </file>
   <file name="HTMLPurifier/Lexer.php">
-   <line>238</line>
+   <line>258</line>
+  </file>
+  <file name="HTMLPurifier/HTMLModule/Image.php">
+   <line>27</line>
   </file>
   <file name="HTMLPurifier/Lexer/DirectLex.php">
-   <line>34</line>
+   <line>36</line>
+  </file>
+  <file name="HTMLPurifier/Strategy/RemoveForeignElements.php">
+   <line>23</line>
   </file>
  </directive>
  <directive id="HTML.AllowedModules">
   <file name="HTMLPurifier/HTMLModuleManager.php">
-   <line>205</line>
+   <line>209</line>
   </file>
  </directive>
  <directive id="HTML.CoreModules">
   <file name="HTMLPurifier/HTMLModuleManager.php">
-   <line>206</line>
+   <line>210</line>
   </file>
  </directive>
  <directive id="HTML.Proprietary">
   <file name="HTMLPurifier/HTMLModuleManager.php">
-   <line>220</line>
+   <line>221</line>
+  </file>
+ </directive>
+ <directive id="HTML.SafeObject">
+  <file name="HTMLPurifier/HTMLModuleManager.php">
+   <line>226</line>
+  </file>
+ </directive>
+ <directive id="HTML.SafeEmbed">
+  <file name="HTMLPurifier/HTMLModuleManager.php">
+   <line>229</line>
   </file>
  </directive>
  <directive id="Attr.IDBlacklist">
@@ -177,30 +192,35 @@
  </directive>
  <directive id="Core.LexerImpl">
   <file name="HTMLPurifier/Lexer.php">
-   <line>70</line>
+   <line>76</line>
+  </file>
+ </directive>
+ <directive id="Core.MaintainLineNumbers">
+  <file name="HTMLPurifier/Lexer.php">
+   <line>80</line>
+  </file>
+  <file name="HTMLPurifier/Lexer/DirectLex.php">
+   <line>48</line>
   </file>
  </directive>
  <directive id="Core.ConvertDocumentToFragment">
   <file name="HTMLPurifier/Lexer.php">
-   <line>230</line>
+   <line>267</line>
   </file>
  </directive>
  <directive id="URI.Host">
   <file name="HTMLPurifier/URIDefinition.php">
-   <line>57</line>
+   <line>64</line>
-  </file>
-  <file name="HTMLPurifier/URIFilter/DisableExternal.php">
-   <line>8</line>
   </file>
  </directive>
  <directive id="URI.Base">
   <file name="HTMLPurifier/URIDefinition.php">
-   <line>58</line>
+   <line>65</line>
   </file>
  </directive>
  <directive id="URI.DefaultScheme">
   <file name="HTMLPurifier/URIDefinition.php">
-   <line>65</line>
+   <line>72</line>
   </file>
  </directive>
  <directive id="URI.AllowedSchemes">
@@ -215,12 +235,7 @@
  </directive>
  <directive id="URI.Disable">
   <file name="HTMLPurifier/AttrDef/URI.php">
-   <line>23</line>
+   <line>28</line>
-  </file>
- </directive>
- <directive id="URI.Munge">
-  <file name="HTMLPurifier/AttrDef/URI.php">
-   <line>68</line>
   </file>
  </directive>
  <directive id="Core.ColorKeywords">
@@ -275,9 +290,14 @@
    <line>19</line>
   </file>
  </directive>
+ <directive id="Attr.DefaultImageAlt">
+  <file name="HTMLPurifier/AttrTransform/ImgRequired.php">
+   <line>25</line>
+  </file>
+ </directive>
  <directive id="Attr.DefaultInvalidImageAlt">
   <file name="HTMLPurifier/AttrTransform/ImgRequired.php">
-   <line>27</line>
+   <line>32</line>
   </file>
  </directive>
  <directive id="Core.EscapeInvalidChildren">
@@ -305,6 +325,17 @@
    <line>123</line>
   </file>
  </directive>
+ <directive id="HTML.MaxImgLength">
+  <file name="HTMLPurifier/HTMLModule/Image.php">
+   <line>14</line>
+  </file>
+  <file name="HTMLPurifier/HTMLModule/SafeEmbed.php">
+   <line>13</line>
+  </file>
+  <file name="HTMLPurifier/HTMLModule/SafeObject.php">
+   <line>19</line>
+  </file>
+ </directive>
  <directive id="HTML.TidyLevel">
   <file name="HTMLPurifier/HTMLModule/Tidy.php">
    <line>45</line>
@@ -332,12 +363,12 @@
  </directive>
  <directive id="Core.DirectLexLineNumberSyncInterval">
   <file name="HTMLPurifier/Lexer/DirectLex.php">
-   <line>59</line>
+   <line>70</line>
   </file>
  </directive>
  <directive id="Core.EscapeInvalidTags">
   <file name="HTMLPurifier/Strategy/MakeWellFormed.php">
-   <line>22</line>
+   <line>45</line>
   </file>
   <file name="HTMLPurifier/Strategy/RemoveForeignElements.php">
    <line>19</line>
@@ -345,12 +376,12 @@
  </directive>
  <directive id="Core.RemoveScriptContents">
   <file name="HTMLPurifier/Strategy/RemoveForeignElements.php">
-   <line>22</line>
+   <line>25</line>
   </file>
  </directive>
  <directive id="Core.HiddenElements">
   <file name="HTMLPurifier/Strategy/RemoveForeignElements.php">
-   <line>23</line>
+   <line>26</line>
   </file>
  </directive>
  <directive id="URI.HostBlacklist">
@@ -358,4 +389,14 @@
    <line>8</line>
   </file>
  </directive>
+ <directive id="URI.MungeResources">
+  <file name="HTMLPurifier/URIFilter/Munge.php">
+   <line>14</line>
+  </file>
+ </directive>
+ <directive id="URI.MungeSecretKey">
+  <file name="HTMLPurifier/URIFilter/Munge.php">
+   <line>15</line>
+  </file>
+ </directive>
 </usage>

docs/dev-advanced-api.html

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

docs/dev-config-schema.html

@@ -239,15 +239,15 @@ Test.Example</pre>
       object; users have a little bit of leeway when setting configuration
       values (for example, a lookup value can be specified as a list;
       HTML Purifier will flip it as necessary.) These types are defined
-      in <a href="http://htmlpurifier.org/svnroot/htmlpurifier/trunk/library/HTMLPurifier/VarParser.php">
+      in <a href="http://repo.or.cz/w/htmlpurifier.git?a=blob;hb=HEAD;f=library/HTMLPurifier/VarParser.php">
       library/HTMLPurifier/VarParser.php</a>.
     </p>
     
     <p>
       For more information on what values are allowed, and how they are parsed,
-      consult <a href="http://htmlpurifier.org/svnroot/htmlpurifier/trunk/library/HTMLPurifier/ConfigSchema/InterchangeBuilder.php">
+      consult <a href="http://repo.or.cz/w/htmlpurifier.git?a=blob;hb=HEAD;f=library/HTMLPurifier/ConfigSchema/InterchangeBuilder.php">
       library/HTMLPurifier/ConfigSchema/InterchangeBuilder.php</a>, as well
-      as <a href="http://htmlpurifier.org/svnroot/htmlpurifier/trunk/library/HTMLPurifier/ConfigSchema/Interchange/Directive.php">
+      as <a href="http://repo.or.cz/w/htmlpurifier.git?a=blob;hb=HEAD;f=library/HTMLPurifier/ConfigSchema/Interchange/Directive.php">
       library/HTMLPurifier/ConfigSchema/Interchange/Directive.php</a> for
       the semantics of the parsed values.
     </p>
@@ -272,7 +272,7 @@ Test.Example</pre>
     
     <p>
       All directive files go through a rigorous validation process
-      through <a href="http://htmlpurifier.org/svnroot/htmlpurifier/trunk/library/HTMLPurifier/ConfigSchema/">
+      through <a href="http://repo.or.cz/w/htmlpurifier.git?a=blob;hb=HEAD;f=library/HTMLPurifier/ConfigSchema/Validator.php">
       library/HTMLPurifier/ConfigSchema/Validator.php</a>, as well
       as some basic checks during building. While
       listing every error out here is out-of-scope for this document, we
@@ -339,7 +339,7 @@ Test.Example</pre>
       The most difficult part is translating the Interchange member variable (valueAliases)
       into a directive file key (VALUE-ALIASES), but there's a one-to-one
       correspondence currently. If the two formats diverge, any discrepancies
-      will be described in <a href="http://htmlpurifier.org/svnroot/htmlpurifier/trunk/library/HTMLPurifier/ConfigSchema/InterchangeBuilder.php">
+      will be described in <a href="http://repo.or.cz/w/htmlpurifier.git?a=blob;hb=HEAD;f=library/HTMLPurifier/ConfigSchema/InterchangeBuilder.php">
       library/HTMLPurifier/ConfigSchema/InterchangeBuilder.php</a>.
     </p>
     
@@ -370,7 +370,5 @@ Test.Example</pre>
       data. There is also an XML serializer, which is used to build documentation.
     </p>
 
-    <div id="version">$Id$</div>
-
   </body>
 </html>

docs/dev-flush.html

@@ -62,6 +62,4 @@
     do.
 </p>
 
-<div id="version">$Id$</div>
-
 </body></html>

docs/dev-naming.html

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

docs/dev-optimization.html

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

docs/dev-progress.html

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

docs/enduser-customize.html

@@ -213,7 +213,7 @@ $def = $config->getHTMLDefinition(true);</pre>
 <pre>$config = HTMLPurifier_Config::createDefault();
 $config->set('HTML', 'DefinitionID', 'enduser-customize.html tutorial');
 $config->set('HTML', 'DefinitionRev', 1);
-<strong>$config->set('Core', 'DefinitionCache', null); // remove this later!</strong>
+<strong>$config->set('Cache', 'DefinitionImpl', null); // remove this later!</strong>
 $def = $config->getHTMLDefinition(true);</pre>
 
 <p>
@@ -269,7 +269,7 @@ $def = $config->getHTMLDefinition(true);</pre>
 <pre>$config = HTMLPurifier_Config::createDefault();
 $config->set('HTML', 'DefinitionID', 'enduser-customize.html tutorial');
 $config->set('HTML', 'DefinitionRev', 1);
-$config->set('Core', 'DefinitionCache', null); // remove this later!
+$config->set('Cache', 'DefinitionImpl', null); // remove this later!
 $def = $config->getHTMLDefinition(true);
 <strong>$def->addAttribute('a', 'target', 'Enum#_blank,_self,_target,_top');</strong></pre>
 
@@ -372,10 +372,10 @@ $def = $config->getHTMLDefinition(true);
 
 <p>
   For a complete list, consult
-  <a href="http://htmlpurifier.org/svnroot/htmlpurifier/trunk/library/HTMLPurifier/AttrTypes.php"><code>library/HTMLPurifier/AttrTypes.php</code></a>;
+  <a href="http://repo.or.cz/w/htmlpurifier.git?a=blob;hb=HEAD;f=library/HTMLPurifier/AttrTypes.php"><code>library/HTMLPurifier/AttrTypes.php</code></a>;
   more information on attributes that accept parameters can be found on their
   respective includes in
-  <a href="http://htmlpurifier.org/svnroot/htmlpurifier/trunk/library/HTMLPurifier/AttrDef/"><code>library/HTMLPurifier/AttrDef</code></a>.
+  <a href="http://repo.or.cz/w/htmlpurifier.git?a=tree;hb=HEAD;f=library/HTMLPurifier/AttrDef"><code>library/HTMLPurifier/AttrDef</code></a>.
 </p>
 
 <p>
@@ -387,7 +387,7 @@ $def = $config->getHTMLDefinition(true);
 <pre>$config = HTMLPurifier_Config::createDefault();
 $config->set('HTML', 'DefinitionID', 'enduser-customize.html tutorial');
 $config->set('HTML', 'DefinitionRev', 1);
-$config->set('Core', 'DefinitionCache', null); // remove this later!
+$config->set('Cache', 'DefinitionImpl', null); // remove this later!
 $def = $config->getHTMLDefinition(true);
 <strong>$def->addAttribute('a', 'target', new HTMLPurifier_AttrDef_Enum(
   array('_blank','_self','_target','_top')
@@ -734,7 +734,7 @@ $def = $config->getHTMLDefinition(true);
 <pre>$config = HTMLPurifier_Config::createDefault();
 $config->set('HTML', 'DefinitionID', 'enduser-customize.html tutorial');
 $config->set('HTML', 'DefinitionRev', 1);
-$config->set('Core', 'DefinitionCache', null); // remove this later!
+$config->set('Cache', 'DefinitionImpl', null); // remove this later!
 $def = $config->getHTMLDefinition(true);
 $def->addAttribute('a', 'target', new HTMLPurifier_AttrDef_Enum(
   array('_blank','_self','_target','_top')
@@ -764,7 +764,7 @@ $form->excludes = array('form' => true);</strong></pre>
 <p>
   And that's all there is to it! Implementing the rest of the form
   module is left as an exercise to the user; to see more examples
-  check the <a href="http://htmlpurifier.org/svnroot/htmlpurifier/trunk/library/HTMLPurifier/HTMLModule/"><code>library/HTMLPurifier/HTMLModule/</code></a> directory
+  check the <a href="http://repo.or.cz/w/htmlpurifier.git?a=tree;hb=HEAD;f=library/HTMLPurifier/HTMLModule"><code>library/HTMLPurifier/HTMLModule/</code></a> directory
   in your local HTML Purifier installation.
 </p>
 
@@ -789,10 +789,8 @@ $form->excludes = array('form' => true);</strong></pre>
 </p>
 
 <ul>
-  <li><a href="http://htmlpurifier.org/svnroot/htmlpurifier/trunk/library/HTMLPurifier/HTMLModule.php"><code>library/HTMLPurifier/HTMLModule.php</code></a></li>
+  <li><a href="http://repo.or.cz/w/htmlpurifier.git?a=blob;hb=HEAD;f=library/HTMLPurifier/HTMLModule.php"><code>library/HTMLPurifier/HTMLModule.php</code></a></li>
-  <li><a href="http://htmlpurifier.org/svnroot/htmlpurifier/trunk/library/HTMLPurifier/ElementDef.php"><code>library/HTMLPurifier/ElementDef.php</code></a></li>
+  <li><a href="http://repo.or.cz/w/htmlpurifier.git?a=blob;hb=HEAD;f=library/HTMLPurifier/ElementDef.php"><code>library/HTMLPurifier/ElementDef.php</code></a></li>
 </ul>
 
-<div id="version">$Id: enduser-tidy.html 1158 2007-06-18 19:26:29Z Edward $</div>
-
 </body></html>

docs/enduser-id.html

@@ -141,7 +141,5 @@ anchors is beyond me.</p>
 
 <p>Don't come crying to me when your page mysteriously stops validating, though.</p>
 
-<div id="version">$Id$</div>
-
 </body>
 </html>

docs/enduser-tidy.html

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

docs/enduser-uri-filter.html

@@ -130,30 +130,26 @@
 </p>
 
 <p>
-  Let's suppose I wanted to write a filter that de-internationalized domain
+  Let's suppose I wanted to write a filter that converted links with a
-  names by converting them to <a href="http://en.wikipedia.org/wiki/Punycode">Punycode</a>.
+  custom <code>image</code> scheme to its corresponding real path on
-  Assuming that <code>punycode_encode($input)</code> converts <code>$input</code> to
+  our website:
-  Punycode and returns <code>false</code> on failure:
 </p>
 
-<pre>class HTMLPurifier_URIFilter_ConvertIDNToPunycode extends HTMLPurifier_URIFilter
+<pre>class HTMLPurifier_URIFilter_TransformImageScheme extends HTMLPurifier_URIFilter
 {
-    public $name = 'ConvertIDNToPunycode';
+    public $name = 'TransformImageScheme';
     public function filter(&$uri, $config, $context) {
-        if (is_null($uri->host)) return true;
+        if ($uri->scheme !== 'image') return true;
-        if ($uri->host == utf8_decode($uri->host)) {
+        $img_name = $uri->path;
-            // is ASCII, abort
+        // Overwrite the previous URI object
-            return true;
+        $uri = new HTMLPurifier_URI('http', null, null, null, '/img/' . $img_name . '.png', null, null);
-        }
-        $host = punycode_encode($uri->host);
-        if ($host === false) return false;
-        $uri->host = $host;
         return true;
     }
 }</pre>
 
 <p>
-  Notice I did not <code>return $uri;</code>.
+  Notice I did not <code>return $uri;</code>. This filter would turn
+  <code>image:Foo</code> into <code>/img/Foo.png</code>.
 </p>
 
 <h2>Activating your filter</h2>
@@ -186,16 +182,33 @@ $uri->registerFilter(new HTMLPurifier_URIFilter_<strong>NameOfFilter</strong>())
   is set to true.
 </p>
 
+<h2>Post-filter</h2>
+
+<p>
+    Remember our TransformImageScheme filter? That filter acted before we had
+    performed scheme validation; otherwise, the URI would have been filtered
+    out when it was discovered that there was no image scheme. Well, a post-filter
+    is run after scheme specific validation, so it's ideal for bulk
+    post-processing of URIs, including munging. To specify a URI as a post-filter,
+    set the <code>$post</code> member variable to TRUE.
+</p>
+
+<pre>class HTMLPurifier_URIFilter_MyPostFilter extends HTMLPurifier_URIFilter
+{
+    public $name = 'MyPostFilter';
+    public $post = true;
+    // ... extra code here
+}
+</pre>
+
 <h2>Examples</h2>
 
 <p>
   Check the
-  <a href="http://htmlpurifier.org/svnroot/htmlpurifier/trunk/library/HTMLPurifier/URIFilter/">URIFilter</a>
+  <a href="http://repo.or.cz/w/htmlpurifier.git?a=tree;hb=HEAD;f=library/HTMLPurifier/URIFilter">URIFilter</a>
-  directory for more implementation examples, and see <a href="http://htmlpurifier.org/svnroot/htmlpurifier/trunk/docs/proposal-new-directives.txt">the
+  directory for more implementation examples, and see <a href="proposal-new-directives.txt">the
   new directives proposal document</a> for ideas on what could be implemented
   as a filter.
 </p>
 
-<div id="version">$Id$</div>
-
 </body></html>

docs/enduser-utf8.html

@@ -118,9 +118,8 @@ there are now many character encodings floating around.</p>
             see a page on the web, chances are it's encoded in one
             of these encodings.</li>
         <li><strong>Unicode-based encodings</strong> implement the
-            Unicode standard and include UTF-8, UCS-2 and UTF-16.
+            Unicode standard and include UTF-8, UTF-16 and UTF-32/UCS-4.
-            They go beyond 8-bits (the first two are variable length,
+            They go beyond 8-bits and support almost
-            while the second one uses 16-bits), and support almost
             every language in the world. UTF-8 is gaining traction
             as the dominant international encoding of the web.</li>
     </ul>
@@ -590,8 +589,10 @@ looks something like: <code>%C3%86</code>. There is no official way of
 determining the character encoding of such a request, since the percent
 encoding operates on a byte level, so it is usually assumed that it
 is the same as the encoding the page containing the form was submitted
-in. You'll run into very few problems if you only use characters in
+in. (<a href="http://tools.ietf.org/html/rfc3986#section-2.5">RFC 3986</a>
-the character encoding you chose.</p>
+recommends that textual identifiers be translated to UTF-8; however, browser
+compliance is spotty.) You'll run into very few problems
+if you only use characters in the character encoding you chose.</p>
 
 <p>However, once you start adding characters outside of your encoding
 (and this is a lot more common than you may think: take curly

docs/enduser-youtube.html

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

docs/index.html

@@ -98,8 +98,8 @@ the code. They may be upgraded to HTML files or stay as TXT scratchpads.</p>
 <table class="table">
 
 <thead><tr>
-    <th width="10%">Type</th>
+    <th style="width:10%">Type</th>
-    <th width="20%">Name</th>
+    <th style="width:20%">Name</th>
     <th>Description</th>
 </tr></thead>
 
@@ -175,6 +175,5 @@ the code. They may be upgraded to HTML files or stay as TXT scratchpads.</p>
 
 </table>
 
-<div id="version">$Id$</div>
 </body>
 </html>

docs/proposal-colors.html

@@ -42,7 +42,5 @@ into the mix.</li>
 something like that?</li>
 </ol>
 
-<div id="version">$Id$</div>
-
 </body>
 </html>

docs/proposal-errors.txt

@@ -0,0 +1,209 @@
+Considerations for ErrorCollection
+
+Presently, HTML Purifier takes a code-execution centric approach to handling
+errors. Errors are organized and grouped according to which segment of the
+code triggers them, not necessarily the portion of the input document that 
+triggered the error. This means that errors are pseudo-sorted by category,
+rather than location in the document.
+
+One easy way to "fix" this problem would be to re-sort according to line number.
+However, the "category" style information we derive from naively following
+program execution is still useful. After all, each of the strategies which
+can report errors still process the document mostly linearly. Furthermore,
+not only do they process linearly, but the way they pass off operations to
+sub-systems mirrors that of the document. For example, AttrValidator will
+linearly proceed through elements, and on each element will use AttrDef to
+validate those contents. From there, the attribute might have more 
+sub-components, which have execution passed off accordingly.
+
+In fact, each strategy handles a very specific class of "error."
+
+RemoveForeignElements   - element tokens
+MakeWellFormed          - element token ordering
+FixNesting              - element token ordering
+ValidateAttributes      - attributes of elements
+
+The crucial point is that while we care about the hierarchy governing these
+different errors, we *don't* care about any other information about what actually
+happens to the elements. This brings up another point: if HTML Purifier fixes
+something, this is not really a notice/warning/error; it's really a suggestion
+of a way to fix the aforementioned defects.
+
+In short, the refactoring to take this into account kinda sucks.
+
+Errors should not be recorded in order that they are reported. Instead, they
+should be bound to the line (and preferably element) in which they were found.
+This means we need some way to uniquely identify every element in the document,
+which doesn't presently exist. An easy way of adding this would be to track
+line columns. An important ramification of this is that we *must* use the
+DirectLex implementation.
+
+    1. Implement column numbers for DirectLex [DONE!]
+    2. Disable error collection when not using DirectLex [DONE!]
+
+Next, we need to re-orient all of the error declarations to place CurrentToken
+at utmost important. Since this is passed via Context, it's not always clear
+if that's available. ErrorCollector should complain HARD if it isn't available.
+There are some locations when we don't have a token available. These include:
+
+    * Lexing - this can actually have a row and column, but NOT correspond to
+      a token
+    * End of document errors - bump this to the end
+
+Actually, we *don't* have to complain if CurrentToken isn't available; we just
+set it as a document-wide error. And actually, nothing needs to be done here.
+
+Something interesting to consider is whether or not we care about the locations
+of attributes and CSS properties, i.e. the sub-objects that compose these things.
+In terms of consistency, at the very least attributes should have column/line
+numbers attached to them. However, this may be overkill, as attributes are 
+uniquely identifiable. You could go even further, with CSS, but they are also
+uniquely identifiable.
+
+Bottom-line is, however, this information must be available, in form of the
+CurrentAttribute and CurrentCssProperty (theoretical) context variables, and
+it must be used to organize the errors that the sub-processes may throw.
+There is also a hierarchy of sorts that may make merging this into one context
+variable more sense, if it hadn't been for HTML's reasonably rigid structure.
+A CSS property will never contain an HTML attribute. So we won't ever get
+recursive relations, and having multiple depths won't ever make sense. Leave
+this be.
+
+We already have this information, and consequently, using start and end is
+*unnecessary*, so long as the context variables are set appropriately. We don't
+care if an error was thrown by an attribute transform or an attribute definition;
+to the end user these are the same (for a developer, they are different, but
+they're better off with a stack trace (which we should add support for) in such
+cases).
+
+    3. Remove start()/end() code. Don't get rid of recursion, though [DONE]
+    4. Setup ErrorCollector to use context information to setup hierarchies.
+       This may require a different internal format. Use objects if it gets
+       complex. [DONE]
+       
+       ASIDE
+            More on this topic: since we are now binding errors to lines
+            and columns, a particular error can have three relationships to that
+            specific location:
+            
+            1. The token at that location directly
+                RemoveForeignElements
+                AttrValidator (transforms)
+                MakeWellFormed
+            2. A "component" of that token (i.e. attribute)
+                AttrValidator (removals)
+            3. A modification to that node (i.e. contents from start to end
+               token) as a whole
+                FixNesting
+            
+            This needs to be marked accordingly. In the presentation, it might
+            make sense keep (3) separate, have (2) a sublist of (1). (1) can
+            be a closing tag, in which case (3) makes no sense at all, OR it
+            should be related with its opening tag (this may not necessarily
+            be possible before MakeWellFormed is run).
+            
+            So, the line and column counts as our identifier, so:
+            
+            $errors[$line][$col] = ...
+            
+            Then, we need to identify case 1, 2 or 3. They are identified as
+            such:
+            
+            1. Need some sort of semaphore in RemoveForeignElements, etc.
+            2. If CurrentAttr/CurrentCssProperty is non-null
+            3. Default (FixNesting, MakeWellFormed)
+            
+            One consideration about (1) is that it usually is actually a
+            (3) modification, but we have no way of knowing about that because
+            of various optimizations. However, they can probably be treated
+            the same. The other difficulty is that (3) is never a line and
+            column; rather, it is a range (i.e. a duple) and telling the user
+            the very start of the range may confuse them. For example,
+            
+            <b>Foo<div>bar</div></b>
+            ^     ^
+            
+            The node being operated on is <b>, so the error would be assigned
+            to the first caret, with a "node reorganized" error. Then, the
+            ChildDef would have submitted its own suggestions and errors with
+            regard to what's going in the internals.  So I suppose this is
+            ok. :-)
+            
+            Now, the structure of the earlier mentioned ... would be something
+            like this:
+            
+            object {
+                type = (token|attr|property),
+                value, // appropriate for type
+                errors => array(),
+                sub-errors = [recursive],
+            }
+            
+            This helps us keep things agnostic. It is also sufficiently complex
+            enough to warrant an object.
+
+So, more wanking about the object format is in order. The way HTML Purifier is
+currently setup, the only possible hierarchy is:
+
+    token -> attr -> css property
+
+These relations do not exist all of the time; a comment or end token would not
+ever have any attributes, and non-style attributes would never have CSS properties
+associated with them.
+
+I believe that it is worth supporting multiple paths. At some point, we might
+have a hierarchy like:
+
+    * -> syntax
+      -> token -> attr -> css property
+                       -> url
+               -> css stylesheet <style>
+
+et cetera. Now, one of the practical implications of this is that every "node"
+on our tree is well-defined, so in theory it should be possible to either 1.
+create a separate class for each error struct, or 2. embed this information
+directly into HTML Purifier's token stream.  Embedding the information in the
+token stream is not a terribly good idea, since tokens can be removed, etc.
+So that leaves us with 1... and if we use a generic interface we can cut down
+on a lot of code we might need. So let's leave it like this.
+
+~~~~
+
+Then we setup suggestions.
+
+    5. Setup a separate error class which tells the user any modifications
+       HTML Purifier made.
+       
+Some information about this:
+
+Our current paradigm is to tell the user what HTML Purifier did to the HTML.
+This is the most natural mode of operation, since that's what HTML Purifier
+is all about; it was not meant to be a validator.
+
+However, most other people have experience dealing with a validator. In cases
+where HTML Purifier unambiguously does the right thing, simply giving the user
+the correct version isn't a bad idea, but problems arise when:
+
+- The user has such bad HTML we do something odd, when we should have just
+  flagged the HTML as an error. Such examples are when we do things like
+  remove text from directly inside a <table> tag. It was probably meant to
+  be in a <td> tag or be outside the table, but we're not smart enough to 
+  realize this so we just remove it. In such a case, we should tell the user
+  that there was foreign data in the table, but then we shouldn't "demand"
+  the user remove the data; it's more of a "here's a possible way of
+  rectifying the problem"
+
+- Giving line context for input is hard enough, but feasible; giving output
+  line context will be extremely difficult due to shifting lines; we'd probably
+  have to track what the tokens are and then find the appropriate out context
+  and it's not guaranteed to work etc etc etc.
+
+````````````
+
+Don't forget to spruce up output.
+
+    6. Output needs to automatically give line and column numbers, basically
+       "at line" on steroids. Look at W3C's output; it's ok. [PARTIALLY DONE]
+       
+       - We need a standard CSS to apply (check demo.css for some starting
+         styling; some buttons would also be hip)

docs/ref-devnetwork.html

@@ -40,6 +40,5 @@ the development of this library in these forum threads:</p>
 
 <p>...as well as any I may have forgotten.</p>
 
-<div id="version">$Id$</div>
 </body>
 </html>

docs/specimens/jochem-blok-word.html

@@ -0,0 +1,129 @@
+<html xmlns:v="urn:schemas-microsoft-com:vml" xmlns:o="urn:schemas-microsoft-com:office:office" xmlns:w="urn:schemas-microsoft-com:office:word" xmlns:m="http://schemas.microsoft.com/office/2004/12/omml" xmlns="http://www.w3.org/TR/REC-html40">
+
+<head>
+<META HTTP-EQUIV="Content-Type" CONTENT="text/html; charset=us-ascii">
+<meta name=Generator content="Microsoft Word 12 (filtered medium)">
+<!--[if !mso]>
+<style>
+v\:* {behavior:url(#default#VML);}
+o\:* {behavior:url(#default#VML);}
+w\:* {behavior:url(#default#VML);}
+..shape {behavior:url(#default#VML);}
+</style>
+<![endif]-->
+<style>
+<!--
+ /* Font Definitions */
+ @font-face
+	{font-family:"Cambria Math";
+	panose-1:2 4 5 3 5 4 6 3 2 4;}
+@font-face
+	{font-family:Calibri;
+	panose-1:2 15 5 2 2 2 4 3 2 4;}
+@font-face
+	{font-family:Tahoma;
+	panose-1:2 11 6 4 3 5 4 4 2 4;}
+@font-face
+	{font-family:Verdana;
+	panose-1:2 11 6 4 3 5 4 4 2 4;}
+ /* Style Definitions */
+ p.MsoNormal, li.MsoNormal, div.MsoNormal
+	{margin:0cm;
+	margin-bottom:.0001pt;
+	font-size:10.0pt;
+	font-family:"Verdana","sans-serif";}
+a:link, span.MsoHyperlink
+	{mso-style-priority:99;
+	color:blue;
+	text-decoration:underline;}
+a:visited, span.MsoHyperlinkFollowed
+	{mso-style-priority:99;
+	color:purple;
+	text-decoration:underline;}
+p.MsoAcetate, li.MsoAcetate, div.MsoAcetate
+	{mso-style-priority:99;
+	mso-style-link:"Balloon Text Char";
+	margin:0cm;
+	margin-bottom:.0001pt;
+	font-size:8.0pt;
+	font-family:"Tahoma","sans-serif";}
+span.EmailStyle17
+	{mso-style-type:personal-compose;
+	font-family:"Verdana","sans-serif";
+	color:windowtext;}
+span.BalloonTextChar
+	{mso-style-name:"Balloon Text Char";
+	mso-style-priority:99;
+	mso-style-link:"Balloon Text";
+	font-family:"Tahoma","sans-serif";}
+..MsoChpDefault
+	{mso-style-type:export-only;}
+@page Section1
+	{size:612.0pt 792.0pt;
+	margin:70.85pt 70.85pt 70.85pt 70.85pt;}
+div.Section1
+	{page:Section1;}
+-->
+</style>
+<!--[if gte mso 9]><xml>
+ <o:shapedefaults v:ext="edit" spidmax="2050" />
+</xml><![endif]--><!--[if gte mso 9]><xml>
+ <o:shapelayout v:ext="edit">
+  <o:idmap v:ext="edit" data="1" />
+ </o:shapelayout></xml><![endif]-->
+</head>
+
+<body lang=NL link=blue vlink=purple>
+
+<div class=Section1>
+
+<p class=MsoNormal><img width=1277 height=994 id="Picture_x0020_1"
+src="cid:image001.png@01C8CBDF.5D1BAEE0"><o:p></o:p></p>
+
+<p class=MsoNormal><o:p>&nbsp;</o:p></p>
+
+<p class=MsoNormal><b>Name<o:p></o:p></b></p>
+
+<p class=MsoNormal>E-mail : <a href="mailto:mail@example.com"><span
+style='color:windowtext'>mail@example.com</span></a><o:p></o:p></p>
+
+<p class=MsoNormal><o:p>&nbsp;</o:p></p>
+
+<p class=MsoNormal><b>Company<o:p></o:p></b></p>
+
+<p class=MsoNormal>Address 1<o:p></o:p></p>
+
+<p class=MsoNormal>Address 2<o:p></o:p></p>
+
+<p class=MsoNormal><o:p>&nbsp;</o:p></p>
+
+<p class=MsoNormal>Telefoon&nbsp; : +xx xx xxx xxx xx <span style='color:black'><o:p></o:p></span></p>
+
+<p class=MsoNormal><span lang=EN-US style='color:black'>Fax&nbsp; : +xx xx xxx xx xx<o:p></o:p></span></p>
+
+<p class=MsoNormal><span lang=EN-US style='color:black'>Internet : </span><span
+style='color:black'><a href="http://www.example.com/"><span lang=EN-US
+style='color:black'>http://www.example.com</span></a></span><span
+lang=EN-US style='color:black'><o:p></o:p></span></p>
+
+<p class=MsoNormal><span lang=EN-US style='color:black'>Kamer van koophandel
+xxxxxxxxx<o:p></o:p></span></p>
+
+<p class=MsoNormal><span lang=EN-US style='color:black'><o:p>&nbsp;</o:p></span></p>
+
+<p class=MsoNormal><span lang=EN-US style='font-size:7.5pt;color:black'>Op deze
+e-mail is een disclaimer van toepassing, ga naar </span><span lang=EN-US
+style='font-size:7.5pt'><a
+href="http://www.example.com/disclaimer"><span
+style='color:black'>www.example.com/disclaimer</span></a><br>
+<span style='color:black'>A disclaimer is applicable to this email, please
+refer to </span><a href="http://www.example.com/disclaimer"><span
+style='color:black'>www.example.com/disclaimer</span></a><o:p></o:p></span></p>
+
+<p class=MsoNormal><span lang=EN-US><o:p>&nbsp;</o:p></span></p>
+
+</div>
+
+</body>
+
+</html>

library/HTMLPurifier.includes.php

@@ -7,7 +7,7 @@
  * primary concern and you are using an opcode cache. PLEASE DO NOT EDIT THIS
  * FILE, changes will be overwritten the next time the script is run.
  * 
- * @version 3.1.0
+ * @version 3.2.0
  * 
  * @warning
  *      You must *not* include any other HTML Purifier files before this file,
@@ -29,7 +29,6 @@ require 'HTMLPurifier/Definition.php';
 require 'HTMLPurifier/CSSDefinition.php';
 require 'HTMLPurifier/ChildDef.php';
 require 'HTMLPurifier/Config.php';
-require 'HTMLPurifier/ConfigDef.php';
 require 'HTMLPurifier/ConfigSchema.php';
 require 'HTMLPurifier/ContentSets.php';
 require 'HTMLPurifier/Context.php';
@@ -42,6 +41,7 @@ require 'HTMLPurifier/Encoder.php';
 require 'HTMLPurifier/EntityLookup.php';
 require 'HTMLPurifier/EntityParser.php';
 require 'HTMLPurifier/ErrorCollector.php';
+require 'HTMLPurifier/ErrorStruct.php';
 require 'HTMLPurifier/Exception.php';
 require 'HTMLPurifier/Filter.php';
 require 'HTMLPurifier/Generator.php';
@@ -52,6 +52,7 @@ require 'HTMLPurifier/IDAccumulator.php';
 require 'HTMLPurifier/Injector.php';
 require 'HTMLPurifier/Language.php';
 require 'HTMLPurifier/LanguageFactory.php';
+require 'HTMLPurifier/Length.php';
 require 'HTMLPurifier/Lexer.php';
 require 'HTMLPurifier/PercentEncoder.php';
 require 'HTMLPurifier/Strategy.php';
@@ -66,12 +67,14 @@ require 'HTMLPurifier/URIFilter.php';
 require 'HTMLPurifier/URIParser.php';
 require 'HTMLPurifier/URIScheme.php';
 require 'HTMLPurifier/URISchemeRegistry.php';
+require 'HTMLPurifier/UnitConverter.php';
 require 'HTMLPurifier/VarParser.php';
 require 'HTMLPurifier/VarParserException.php';
 require 'HTMLPurifier/AttrDef/CSS.php';
 require 'HTMLPurifier/AttrDef/Enum.php';
 require 'HTMLPurifier/AttrDef/Integer.php';
 require 'HTMLPurifier/AttrDef/Lang.php';
+require 'HTMLPurifier/AttrDef/Switch.php';
 require 'HTMLPurifier/AttrDef/Text.php';
 require 'HTMLPurifier/AttrDef/URI.php';
 require 'HTMLPurifier/AttrDef/CSS/Number.php';
@@ -106,6 +109,7 @@ require 'HTMLPurifier/AttrDef/URI/Host.php';
 require 'HTMLPurifier/AttrDef/URI/IPv4.php';
 require 'HTMLPurifier/AttrDef/URI/IPv6.php';
 require 'HTMLPurifier/AttrDef/URI/Email/SimpleCheck.php';
+require 'HTMLPurifier/AttrTransform/Background.php';
 require 'HTMLPurifier/AttrTransform/BdoDir.php';
 require 'HTMLPurifier/AttrTransform/BgColor.php';
 require 'HTMLPurifier/AttrTransform/BoolToCSS.php';
@@ -113,10 +117,15 @@ require 'HTMLPurifier/AttrTransform/Border.php';
 require 'HTMLPurifier/AttrTransform/EnumToCSS.php';
 require 'HTMLPurifier/AttrTransform/ImgRequired.php';
 require 'HTMLPurifier/AttrTransform/ImgSpace.php';
+require 'HTMLPurifier/AttrTransform/Input.php';
 require 'HTMLPurifier/AttrTransform/Lang.php';
 require 'HTMLPurifier/AttrTransform/Length.php';
 require 'HTMLPurifier/AttrTransform/Name.php';
+require 'HTMLPurifier/AttrTransform/SafeEmbed.php';
+require 'HTMLPurifier/AttrTransform/SafeObject.php';
+require 'HTMLPurifier/AttrTransform/SafeParam.php';
 require 'HTMLPurifier/AttrTransform/ScriptRequired.php';
+require 'HTMLPurifier/AttrTransform/Textarea.php';
 require 'HTMLPurifier/ChildDef/Chameleon.php';
 require 'HTMLPurifier/ChildDef/Custom.php';
 require 'HTMLPurifier/ChildDef/Empty.php';
@@ -124,9 +133,6 @@ require 'HTMLPurifier/ChildDef/Required.php';
 require 'HTMLPurifier/ChildDef/Optional.php';
 require 'HTMLPurifier/ChildDef/StrictBlockquote.php';
 require 'HTMLPurifier/ChildDef/Table.php';
-require 'HTMLPurifier/ConfigDef/Directive.php';
-require 'HTMLPurifier/ConfigDef/DirectiveAlias.php';
-require 'HTMLPurifier/ConfigDef/Namespace.php';
 require 'HTMLPurifier/DefinitionCache/Decorator.php';
 require 'HTMLPurifier/DefinitionCache/Null.php';
 require 'HTMLPurifier/DefinitionCache/Serializer.php';
@@ -135,15 +141,19 @@ require 'HTMLPurifier/DefinitionCache/Decorator/Memory.php';
 require 'HTMLPurifier/HTMLModule/Bdo.php';
 require 'HTMLPurifier/HTMLModule/CommonAttributes.php';
 require 'HTMLPurifier/HTMLModule/Edit.php';
+require 'HTMLPurifier/HTMLModule/Forms.php';
 require 'HTMLPurifier/HTMLModule/Hypertext.php';
 require 'HTMLPurifier/HTMLModule/Image.php';
 require 'HTMLPurifier/HTMLModule/Legacy.php';
 require 'HTMLPurifier/HTMLModule/List.php';
+require 'HTMLPurifier/HTMLModule/Name.php';
 require 'HTMLPurifier/HTMLModule/NonXMLCommonAttributes.php';
 require 'HTMLPurifier/HTMLModule/Object.php';
 require 'HTMLPurifier/HTMLModule/Presentation.php';
 require 'HTMLPurifier/HTMLModule/Proprietary.php';
 require 'HTMLPurifier/HTMLModule/Ruby.php';
+require 'HTMLPurifier/HTMLModule/SafeEmbed.php';
+require 'HTMLPurifier/HTMLModule/SafeObject.php';
 require 'HTMLPurifier/HTMLModule/Scripting.php';
 require 'HTMLPurifier/HTMLModule/StyleAttribute.php';
 require 'HTMLPurifier/HTMLModule/Tables.php';
@@ -151,14 +161,18 @@ require 'HTMLPurifier/HTMLModule/Target.php';
 require 'HTMLPurifier/HTMLModule/Text.php';
 require 'HTMLPurifier/HTMLModule/Tidy.php';
 require 'HTMLPurifier/HTMLModule/XMLCommonAttributes.php';
+require 'HTMLPurifier/HTMLModule/Tidy/Name.php';
 require 'HTMLPurifier/HTMLModule/Tidy/Proprietary.php';
 require 'HTMLPurifier/HTMLModule/Tidy/XHTMLAndHTML4.php';
 require 'HTMLPurifier/HTMLModule/Tidy/Strict.php';
 require 'HTMLPurifier/HTMLModule/Tidy/Transitional.php';
 require 'HTMLPurifier/HTMLModule/Tidy/XHTML.php';
 require 'HTMLPurifier/Injector/AutoParagraph.php';
+require 'HTMLPurifier/Injector/DisplayLinkURI.php';
 require 'HTMLPurifier/Injector/Linkify.php';
 require 'HTMLPurifier/Injector/PurifierLinkify.php';
+require 'HTMLPurifier/Injector/RemoveEmpty.php';
+require 'HTMLPurifier/Injector/SafeObject.php';
 require 'HTMLPurifier/Lexer/DOMLex.php';
 require 'HTMLPurifier/Lexer/DirectLex.php';
 require 'HTMLPurifier/Strategy/Composite.php';
@@ -179,6 +193,7 @@ require 'HTMLPurifier/URIFilter/DisableExternal.php';
 require 'HTMLPurifier/URIFilter/DisableExternalResources.php';
 require 'HTMLPurifier/URIFilter/HostBlacklist.php';
 require 'HTMLPurifier/URIFilter/MakeAbsolute.php';
+require 'HTMLPurifier/URIFilter/Munge.php';
 require 'HTMLPurifier/URIScheme/ftp.php';
 require 'HTMLPurifier/URIScheme/http.php';
 require 'HTMLPurifier/URIScheme/https.php';

library/HTMLPurifier.php

@@ -19,7 +19,7 @@
  */
 
 /*
-    HTML Purifier 3.1.0 - Standards Compliant HTML Filtering
+    HTML Purifier 3.2.0 - Standards Compliant HTML Filtering
     Copyright (C) 2006-2008 Edward Z. Yang
 
     This library is free software; you can redistribute it and/or
@@ -55,10 +55,10 @@ class HTMLPurifier
 {
     
     /** Version of HTML Purifier */
-    public $version = '3.1.0';
+    public $version = '3.2.0';
     
     /** Constant with version of HTML Purifier */
-    const VERSION = '3.1.0';
+    const VERSION = '3.2.0';
     
     /** Global configuration object */
     public $config;

library/HTMLPurifier.safe-includes.php

@@ -23,7 +23,6 @@ require_once $__dir . '/HTMLPurifier/Definition.php';
 require_once $__dir . '/HTMLPurifier/CSSDefinition.php';
 require_once $__dir . '/HTMLPurifier/ChildDef.php';
 require_once $__dir . '/HTMLPurifier/Config.php';
-require_once $__dir . '/HTMLPurifier/ConfigDef.php';
 require_once $__dir . '/HTMLPurifier/ConfigSchema.php';
 require_once $__dir . '/HTMLPurifier/ContentSets.php';
 require_once $__dir . '/HTMLPurifier/Context.php';
@@ -36,6 +35,7 @@ require_once $__dir . '/HTMLPurifier/Encoder.php';
 require_once $__dir . '/HTMLPurifier/EntityLookup.php';
 require_once $__dir . '/HTMLPurifier/EntityParser.php';
 require_once $__dir . '/HTMLPurifier/ErrorCollector.php';
+require_once $__dir . '/HTMLPurifier/ErrorStruct.php';
 require_once $__dir . '/HTMLPurifier/Exception.php';
 require_once $__dir . '/HTMLPurifier/Filter.php';
 require_once $__dir . '/HTMLPurifier/Generator.php';
@@ -46,6 +46,7 @@ require_once $__dir . '/HTMLPurifier/IDAccumulator.php';
 require_once $__dir . '/HTMLPurifier/Injector.php';
 require_once $__dir . '/HTMLPurifier/Language.php';
 require_once $__dir . '/HTMLPurifier/LanguageFactory.php';
+require_once $__dir . '/HTMLPurifier/Length.php';
 require_once $__dir . '/HTMLPurifier/Lexer.php';
 require_once $__dir . '/HTMLPurifier/PercentEncoder.php';
 require_once $__dir . '/HTMLPurifier/Strategy.php';
@@ -60,12 +61,14 @@ require_once $__dir . '/HTMLPurifier/URIFilter.php';
 require_once $__dir . '/HTMLPurifier/URIParser.php';
 require_once $__dir . '/HTMLPurifier/URIScheme.php';
 require_once $__dir . '/HTMLPurifier/URISchemeRegistry.php';
+require_once $__dir . '/HTMLPurifier/UnitConverter.php';
 require_once $__dir . '/HTMLPurifier/VarParser.php';
 require_once $__dir . '/HTMLPurifier/VarParserException.php';
 require_once $__dir . '/HTMLPurifier/AttrDef/CSS.php';
 require_once $__dir . '/HTMLPurifier/AttrDef/Enum.php';
 require_once $__dir . '/HTMLPurifier/AttrDef/Integer.php';
 require_once $__dir . '/HTMLPurifier/AttrDef/Lang.php';
+require_once $__dir . '/HTMLPurifier/AttrDef/Switch.php';
 require_once $__dir . '/HTMLPurifier/AttrDef/Text.php';
 require_once $__dir . '/HTMLPurifier/AttrDef/URI.php';
 require_once $__dir . '/HTMLPurifier/AttrDef/CSS/Number.php';
@@ -100,6 +103,7 @@ require_once $__dir . '/HTMLPurifier/AttrDef/URI/Host.php';
 require_once $__dir . '/HTMLPurifier/AttrDef/URI/IPv4.php';
 require_once $__dir . '/HTMLPurifier/AttrDef/URI/IPv6.php';
 require_once $__dir . '/HTMLPurifier/AttrDef/URI/Email/SimpleCheck.php';
+require_once $__dir . '/HTMLPurifier/AttrTransform/Background.php';
 require_once $__dir . '/HTMLPurifier/AttrTransform/BdoDir.php';
 require_once $__dir . '/HTMLPurifier/AttrTransform/BgColor.php';
 require_once $__dir . '/HTMLPurifier/AttrTransform/BoolToCSS.php';
@@ -107,10 +111,15 @@ require_once $__dir . '/HTMLPurifier/AttrTransform/Border.php';
 require_once $__dir . '/HTMLPurifier/AttrTransform/EnumToCSS.php';
 require_once $__dir . '/HTMLPurifier/AttrTransform/ImgRequired.php';
 require_once $__dir . '/HTMLPurifier/AttrTransform/ImgSpace.php';
+require_once $__dir . '/HTMLPurifier/AttrTransform/Input.php';
 require_once $__dir . '/HTMLPurifier/AttrTransform/Lang.php';
 require_once $__dir . '/HTMLPurifier/AttrTransform/Length.php';
 require_once $__dir . '/HTMLPurifier/AttrTransform/Name.php';
+require_once $__dir . '/HTMLPurifier/AttrTransform/SafeEmbed.php';
+require_once $__dir . '/HTMLPurifier/AttrTransform/SafeObject.php';
+require_once $__dir . '/HTMLPurifier/AttrTransform/SafeParam.php';
 require_once $__dir . '/HTMLPurifier/AttrTransform/ScriptRequired.php';
+require_once $__dir . '/HTMLPurifier/AttrTransform/Textarea.php';
 require_once $__dir . '/HTMLPurifier/ChildDef/Chameleon.php';
 require_once $__dir . '/HTMLPurifier/ChildDef/Custom.php';
 require_once $__dir . '/HTMLPurifier/ChildDef/Empty.php';
@@ -118,9 +127,6 @@ require_once $__dir . '/HTMLPurifier/ChildDef/Required.php';
 require_once $__dir . '/HTMLPurifier/ChildDef/Optional.php';
 require_once $__dir . '/HTMLPurifier/ChildDef/StrictBlockquote.php';
 require_once $__dir . '/HTMLPurifier/ChildDef/Table.php';
-require_once $__dir . '/HTMLPurifier/ConfigDef/Directive.php';
-require_once $__dir . '/HTMLPurifier/ConfigDef/DirectiveAlias.php';
-require_once $__dir . '/HTMLPurifier/ConfigDef/Namespace.php';
 require_once $__dir . '/HTMLPurifier/DefinitionCache/Decorator.php';
 require_once $__dir . '/HTMLPurifier/DefinitionCache/Null.php';
 require_once $__dir . '/HTMLPurifier/DefinitionCache/Serializer.php';
@@ -129,15 +135,19 @@ require_once $__dir . '/HTMLPurifier/DefinitionCache/Decorator/Memory.php';
 require_once $__dir . '/HTMLPurifier/HTMLModule/Bdo.php';
 require_once $__dir . '/HTMLPurifier/HTMLModule/CommonAttributes.php';
 require_once $__dir . '/HTMLPurifier/HTMLModule/Edit.php';
+require_once $__dir . '/HTMLPurifier/HTMLModule/Forms.php';
 require_once $__dir . '/HTMLPurifier/HTMLModule/Hypertext.php';
 require_once $__dir . '/HTMLPurifier/HTMLModule/Image.php';
 require_once $__dir . '/HTMLPurifier/HTMLModule/Legacy.php';
 require_once $__dir . '/HTMLPurifier/HTMLModule/List.php';
+require_once $__dir . '/HTMLPurifier/HTMLModule/Name.php';
 require_once $__dir . '/HTMLPurifier/HTMLModule/NonXMLCommonAttributes.php';
 require_once $__dir . '/HTMLPurifier/HTMLModule/Object.php';
 require_once $__dir . '/HTMLPurifier/HTMLModule/Presentation.php';
 require_once $__dir . '/HTMLPurifier/HTMLModule/Proprietary.php';
 require_once $__dir . '/HTMLPurifier/HTMLModule/Ruby.php';
+require_once $__dir . '/HTMLPurifier/HTMLModule/SafeEmbed.php';
+require_once $__dir . '/HTMLPurifier/HTMLModule/SafeObject.php';
 require_once $__dir . '/HTMLPurifier/HTMLModule/Scripting.php';
 require_once $__dir . '/HTMLPurifier/HTMLModule/StyleAttribute.php';
 require_once $__dir . '/HTMLPurifier/HTMLModule/Tables.php';
@@ -145,14 +155,18 @@ require_once $__dir . '/HTMLPurifier/HTMLModule/Target.php';
 require_once $__dir . '/HTMLPurifier/HTMLModule/Text.php';
 require_once $__dir . '/HTMLPurifier/HTMLModule/Tidy.php';
 require_once $__dir . '/HTMLPurifier/HTMLModule/XMLCommonAttributes.php';
+require_once $__dir . '/HTMLPurifier/HTMLModule/Tidy/Name.php';
 require_once $__dir . '/HTMLPurifier/HTMLModule/Tidy/Proprietary.php';
 require_once $__dir . '/HTMLPurifier/HTMLModule/Tidy/XHTMLAndHTML4.php';
 require_once $__dir . '/HTMLPurifier/HTMLModule/Tidy/Strict.php';
 require_once $__dir . '/HTMLPurifier/HTMLModule/Tidy/Transitional.php';
 require_once $__dir . '/HTMLPurifier/HTMLModule/Tidy/XHTML.php';
 require_once $__dir . '/HTMLPurifier/Injector/AutoParagraph.php';
+require_once $__dir . '/HTMLPurifier/Injector/DisplayLinkURI.php';
 require_once $__dir . '/HTMLPurifier/Injector/Linkify.php';
 require_once $__dir . '/HTMLPurifier/Injector/PurifierLinkify.php';
+require_once $__dir . '/HTMLPurifier/Injector/RemoveEmpty.php';
+require_once $__dir . '/HTMLPurifier/Injector/SafeObject.php';
 require_once $__dir . '/HTMLPurifier/Lexer/DOMLex.php';
 require_once $__dir . '/HTMLPurifier/Lexer/DirectLex.php';
 require_once $__dir . '/HTMLPurifier/Strategy/Composite.php';
@@ -173,6 +187,7 @@ require_once $__dir . '/HTMLPurifier/URIFilter/DisableExternal.php';
 require_once $__dir . '/HTMLPurifier/URIFilter/DisableExternalResources.php';
 require_once $__dir . '/HTMLPurifier/URIFilter/HostBlacklist.php';
 require_once $__dir . '/HTMLPurifier/URIFilter/MakeAbsolute.php';
+require_once $__dir . '/HTMLPurifier/URIFilter/Munge.php';
 require_once $__dir . '/HTMLPurifier/URIScheme/ftp.php';
 require_once $__dir . '/HTMLPurifier/URIScheme/http.php';
 require_once $__dir . '/HTMLPurifier/URIScheme/https.php';

library/HTMLPurifier/AttrDef.php

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

library/HTMLPurifier/AttrDef/CSS.php

@@ -29,6 +29,12 @@ class HTMLPurifier_AttrDef_CSS extends HTMLPurifier_AttrDef
         $declarations = explode(';', $css);
         $propvalues = array();
         
+        /**
+         * Name of the current CSS property being validated.
+         */
+        $property = false;
+        $context->register('CurrentCSSProperty', $property);
+        
         foreach ($declarations as $declaration) {
             if (!$declaration) continue;
             if (!strpos($declaration, ':')) continue;
@@ -61,6 +67,8 @@ class HTMLPurifier_AttrDef_CSS extends HTMLPurifier_AttrDef
             $propvalues[$property] = $result;
         }
         
+        $context->destroy('CurrentCSSProperty');
+        
         // procedure does not write the new CSS simultaneously, so it's
         // slightly inefficient, but it's the only way of getting rid of
         // duplicates. Perhaps config to optimize it, but not now.

library/HTMLPurifier/AttrDef/CSS/FontFamily.php

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

library/HTMLPurifier/AttrDef/CSS/Length.php

@@ -6,46 +6,40 @@
 class HTMLPurifier_AttrDef_CSS_Length extends HTMLPurifier_AttrDef
 {
     
-    /**
+    protected $min, $max;
-     * Valid unit lookup table.
-     * @warning The code assumes all units are two characters long.  Be careful
-     *          if we have to change this behavior!
-     */
-    protected $units = array('em' => true, 'ex' => true, 'px' => true, 'in' => true,
-         'cm' => true, 'mm' => true, 'pt' => true, 'pc' => true);
-    /**
-     * Instance of HTMLPurifier_AttrDef_Number to defer number validation to
-     */
-    protected $number_def;
     
     /**
-     * @param $non_negative Bool indication whether or not negative values are
+     * @param HTMLPurifier_Length $max Minimum length, or null for no bound. String is also acceptable.
-     *                      allowed.
+     * @param HTMLPurifier_Length $max Maximum length, or null for no bound. String is also acceptable.
      */
-    public function __construct($non_negative = false) {
+    public function __construct($min = null, $max = null) {
-        $this->number_def = new HTMLPurifier_AttrDef_CSS_Number($non_negative);
+        $this->min = $min !== null ? HTMLPurifier_Length::make($min) : null;
+        $this->max = $max !== null ? HTMLPurifier_Length::make($max) : null;
     }
     
-    public function validate($length, $config, $context) {
+    public function validate($string, $config, $context) {
+        $string = $this->parseCDATA($string);
         
-        $length = $this->parseCDATA($length);
+        // Optimizations
-        if ($length === '') return false;
+        if ($string === '') return false;
-        if ($length === '0') return '0';
+        if ($string === '0') return '0';
-        $strlen = strlen($length);
+        if (strlen($string) === 1) return false;
-        if ($strlen === 1) return false; // impossible!
         
-        // we assume all units are two characters
+        $length = HTMLPurifier_Length::make($string);
-        $unit = substr($length, $strlen - 2);
+        if (!$length->isValid()) return false;
-        if (!ctype_lower($unit)) $unit = strtolower($unit);
-        $number = substr($length, 0, $strlen - 2);
         
-        if (!isset($this->units[$unit])) return false;
+        if ($this->min) {
-        
+            $c = $length->compareTo($this->min);
-        $number = $this->number_def->validate($number, $config, $context);
+            if ($c === false) return false;
-        if ($number === false) return false;
+            if ($c < 0) return false;
-        
+        }
-        return $number . $unit;
+        if ($this->max) {
+            $c = $length->compareTo($this->max);
+            if ($c === false) return false;
+            if ($c > 0) return false;
+        }
         
+        return $length->toString();
     }
     
 }

library/HTMLPurifier/AttrDef/CSS/Number.php

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

library/HTMLPurifier/AttrDef/CSS/TextDecoration.php

@@ -13,10 +13,13 @@ class HTMLPurifier_AttrDef_CSS_TextDecoration extends HTMLPurifier_AttrDef
         static $allowed_values = array(
             'line-through' => true,
             'overline' => true,
-            'underline' => true
+            'underline' => true,
         );
         
         $string = strtolower($this->parseCDATA($string));
+        
+        if ($string === 'none') return $string;
+        
         $parts = explode(' ', $string);
         $final = '';
         foreach ($parts as $part) {

library/HTMLPurifier/AttrDef/HTML/LinkTypes.php

@@ -42,10 +42,7 @@ class HTMLPurifier_AttrDef_HTML_LinkTypes extends HTMLPurifier_AttrDef
         }
         
         if (empty($ret_lookup)) return false;
-        
+        $string = implode(' ', array_keys($ret_lookup));
-        $ret_array = array();
-        foreach ($ret_lookup as $part => $bool) $ret_array[] = $part;
-        $string = implode(' ', $ret_array);
         
         return $string;
         

library/HTMLPurifier/AttrDef/HTML/Pixels.php

@@ -6,6 +6,12 @@
 class HTMLPurifier_AttrDef_HTML_Pixels extends HTMLPurifier_AttrDef
 {
     
+    protected $max;
+    
+    public function __construct($max = null) {
+        $this->max = $max;
+    }
+    
     public function validate($string, $config, $context) {
         
         $string = trim($string);
@@ -24,11 +30,18 @@ class HTMLPurifier_AttrDef_HTML_Pixels extends HTMLPurifier_AttrDef
         // crash operating systems, see <http://ha.ckers.org/imagecrash.html>
         // WARNING, above link WILL crash you if you're using Windows
         
-        if ($int > 1200) return '1200';
+        if ($this->max !== null && $int > $this->max) return (string) $this->max;
         
         return (string) $int;
         
     }
     
+    public function make($string) {
+        if ($string === '') $max = null;
+        else $max = (int) $string;
+        $class = get_class($this);
+        return new $class($max);
+    }
+    
 }
 

library/HTMLPurifier/AttrDef/Switch.php

@@ -0,0 +1,32 @@
+<?php
+
+/**
+ * Decorator that, depending on a token, switches between two definitions.
+ */
+class HTMLPurifier_AttrDef_Switch
+{
+    
+    protected $tag;
+    protected $withTag, $withoutTag;
+    
+    /**
+     * @param string $tag Tag name to switch upon
+     * @param HTMLPurifier_AttrDef $with_tag Call if token matches tag
+     * @param HTMLPurifier_AttrDef $without_tag Call if token doesn't match, or there is no token
+     */
+    public function __construct($tag, $with_tag, $without_tag) {
+        $this->tag = $tag;
+        $this->withTag = $with_tag;
+        $this->withoutTag = $without_tag;
+    }
+    
+    public function validate($string, $config, $context) {
+        $token = $context->get('CurrentToken', true);
+        if (!$token || $token->name !== $this->tag) {
+            return $this->withoutTag->validate($string, $config, $context);
+        } else {
+            return $this->withTag->validate($string, $config, $context);
+        }
+    }
+    
+}

library/HTMLPurifier/AttrDef/URI.php

@@ -18,6 +18,11 @@ class HTMLPurifier_AttrDef_URI extends HTMLPurifier_AttrDef
         $this->embedsResource = (bool) $embeds_resource;
     }
     
+    public function make($string) {
+        $embeds = (bool) $string;
+        return new HTMLPurifier_AttrDef_URI($embeds);
+    }
+    
     public function validate($uri, $config, $context) {
         
         if ($config->get('URI', 'Disable')) return false;
@@ -50,6 +55,10 @@ class HTMLPurifier_AttrDef_URI extends HTMLPurifier_AttrDef
             $result = $scheme_obj->validate($uri, $config, $context);
             if (!$result) break;
             
+            // Post chained filtering
+            $result = $uri_def->postFilter($uri, $config, $context);
+            if (!$result) break;
+            
             // survived gauntlet
             $ok = true;
             
@@ -59,18 +68,7 @@ class HTMLPurifier_AttrDef_URI extends HTMLPurifier_AttrDef
         if (!$ok) return false;
         
         // back to string
-        $result = $uri->toString();
+        return $uri->toString();
-        
-        // munge entire URI if necessary
-        if (
-            !is_null($uri->host) && // indicator for authority
-            !empty($scheme_obj->browsable) &&
-            !is_null($munge = $config->get('URI', 'Munge'))
-        ) {
-            $result = str_replace('%s', rawurlencode($result), $munge);
-        }
-        
-        return $result;
         
     }
     

library/HTMLPurifier/AttrTransform/Background.php

@@ -0,0 +1,22 @@
+<?php
+
+/**
+ * Pre-transform that changes proprietary background attribute to CSS.
+ */
+class HTMLPurifier_AttrTransform_Background extends HTMLPurifier_AttrTransform {
+
+    public function transform($attr, $config, $context) {
+        
+        if (!isset($attr['background'])) return $attr;
+        
+        $background = $this->confiscateAttr($attr, 'background');
+        // some validation should happen here
+        
+        $this->prependCSS($attr, "background-image:url($background);");
+        
+        return $attr;
+        
+    }
+    
+}
+

library/HTMLPurifier/AttrTransform/ImgRequired.php

@@ -22,7 +22,12 @@ class HTMLPurifier_AttrTransform_ImgRequired extends HTMLPurifier_AttrTransform
         
         if (!isset($attr['alt'])) {
             if ($src) {
-                $attr['alt'] = basename($attr['src']);
+                $alt = $config->get('Attr', 'DefaultImageAlt');
+                if ($alt === null) {
+                    $attr['alt'] = basename($attr['src']);
+                } else {
+                    $attr['alt'] = $alt;
+                }
             } else {
                 $attr['alt'] = $config->get('Attr', 'DefaultInvalidImageAlt');
             }

library/HTMLPurifier/AttrTransform/Input.php

@@ -0,0 +1,39 @@
+<?php
+
+/**
+ * Performs miscellaneous cross attribute validation and filtering for
+ * input elements. This is meant to be a post-transform.
+ */
+class HTMLPurifier_AttrTransform_Input extends HTMLPurifier_AttrTransform {
+    
+    protected $pixels;
+    
+    public function __construct() {
+        $this->pixels = new HTMLPurifier_AttrDef_HTML_Pixels();
+    }
+    
+    public function transform($attr, $config, $context) {
+        if (!isset($attr['type'])) $t = 'text';
+        else $t = strtolower($attr['type']);
+        if (isset($attr['checked']) && $t !== 'radio' && $t !== 'checkbox') {
+            unset($attr['checked']);
+        }
+        if (isset($attr['maxlength']) && $t !== 'text' && $t !== 'password') {
+            unset($attr['maxlength']);
+        }
+        if (isset($attr['size']) && $t !== 'text' && $t !== 'password') {
+            $result = $this->pixels->validate($attr['size'], $config, $context);
+            if ($result === false) unset($attr['size']);
+            else $attr['size'] = $result;
+        }
+        if (isset($attr['src']) && $t !== 'image') {
+            unset($attr['src']);
+        }
+        if (!isset($attr['value']) && ($t === 'radio' || $t === 'checkbox')) {
+            $attr['value'] = '';
+        }
+        return $attr;
+    }
+    
+}
+

library/HTMLPurifier/AttrTransform/SafeEmbed.php

@@ -0,0 +1,13 @@
+<?php
+
+class HTMLPurifier_AttrTransform_SafeEmbed extends HTMLPurifier_AttrTransform 
+{
+    public $name = "SafeEmbed";
+
+    public function transform($attr, $config, $context) {
+        $attr['allowscriptaccess'] = 'never';
+        $attr['allownetworking'] = 'internal';
+        $attr['type'] = 'application/x-shockwave-flash';
+        return $attr;
+    }
+}

library/HTMLPurifier/AttrTransform/SafeObject.php

@@ -0,0 +1,14 @@
+<?php
+
+/**
+ * Writes default type for all objects. Currently only supports flash.
+ */
+class HTMLPurifier_AttrTransform_SafeObject extends HTMLPurifier_AttrTransform
+{
+    public $name = "SafeObject";
+
+    function transform($attr, $config, $context) {
+        if (!isset($attr['type'])) $attr['type'] = 'application/x-shockwave-flash';
+        return $attr;
+    }
+}

library/HTMLPurifier/AttrTransform/SafeParam.php

@@ -0,0 +1,48 @@
+<?php
+
+/**
+ * Validates name/value pairs in param tags to be used in safe objects. This
+ * will only allow name values it recognizes, and pre-fill certain attributes
+ * with required values.
+ * 
+ * @note
+ *      This class only supports Flash. In the future, Quicktime support
+ *      may be added.
+ * 
+ * @warning
+ *      This class expects an injector to add the necessary parameters tags.
+ */
+class HTMLPurifier_AttrTransform_SafeParam extends HTMLPurifier_AttrTransform 
+{
+    public $name = "SafeParam";
+    private $uri;
+    
+    public function __construct() {
+        $this->uri = new HTMLPurifier_AttrDef_URI(true); // embedded
+    }
+    
+    public function transform($attr, $config, $context) {
+        // If we add support for other objects, we'll need to alter the
+        // transforms.
+        switch ($attr['name']) {
+            // application/x-shockwave-flash
+            // Keep this synchronized with Injector/SafeObject.php
+            case 'allowScriptAccess':
+                $attr['value'] = 'never';
+                break;
+            case 'allowNetworking':
+                $attr['value'] = 'internal';
+                break;
+            case 'wmode':
+                $attr['value'] = 'window';
+                break;
+            case 'movie':
+                $attr['value'] = $this->uri->validate($attr['value'], $config, $context);
+                break;
+            // add other cases to support other param name/value pairs
+            default:
+                $attr['name'] = $attr['value'] = null;
+        }
+        return $attr;
+    }
+}

library/HTMLPurifier/AttrTransform/Textarea.php

@@ -0,0 +1,16 @@
+<?php
+
+/**
+ * Sets height/width defaults for <textarea>
+ */
+class HTMLPurifier_AttrTransform_Textarea extends HTMLPurifier_AttrTransform
+{
+    
+    public function transform($attr, $config, $context) {
+        // Calculated from Firefox
+        if (!isset($attr['cols'])) $attr['cols'] = '22';
+        if (!isset($attr['rows'])) $attr['rows'] = '3';
+        return $attr;
+    }
+    
+}

library/HTMLPurifier/AttrTypes.php

@@ -32,6 +32,9 @@ class HTMLPurifier_AttrTypes
         
         // unimplemented aliases
         $this->info['ContentType'] = new HTMLPurifier_AttrDef_Text();
+        $this->info['ContentTypes'] = new HTMLPurifier_AttrDef_Text();
+        $this->info['Charsets'] = new HTMLPurifier_AttrDef_Text();
+        $this->info['Character'] = new HTMLPurifier_AttrDef_Text();
         
         // number is really a positive integer (one or more digits)
         // FIXME: ^^ not always, see start and value of list items

library/HTMLPurifier/AttrValidator.php

@@ -35,29 +35,33 @@ class HTMLPurifier_AttrValidator
         if (!$current_token) $context->register('CurrentToken', $token);
         
         if (
-          !$token instanceof HTMLPurifier_Token_Start &&
+            !$token instanceof HTMLPurifier_Token_Start &&
-          !$token instanceof HTMLPurifier_Token_Empty
+            !$token instanceof HTMLPurifier_Token_Empty
         ) return $token;
         
         // create alias to global definition array, see also $defs
         // DEFINITION CALL
         $d_defs = $definition->info_global_attr;
         
-        // reference attributes for easy manipulation
+        // don't update token until the very end, to ensure an atomic update
-        $attr =& $token->attr;
+        $attr = $token->attr;
         
         // do global transformations (pre)
         // nothing currently utilizes this
         foreach ($definition->info_attr_transform_pre as $transform) {
             $attr = $transform->transform($o = $attr, $config, $context);
-            if ($e && ($attr != $o)) $e->send(E_NOTICE, 'AttrValidator: Attributes transformed', $o, $attr);
+            if ($e) {
+                if ($attr != $o) $e->send(E_NOTICE, 'AttrValidator: Attributes transformed', $o, $attr);
+            }
         }
         
         // do local transformations only applicable to this element (pre)
         // ex. <p align="right"> to <p style="text-align:right;">
         foreach ($definition->info[$token->name]->attr_transform_pre as $transform) {
             $attr = $transform->transform($o = $attr, $config, $context);
-            if ($e && ($attr != $o)) $e->send(E_NOTICE, 'AttrValidator: Attributes transformed', $o, $attr);
+            if ($e) {
+                if ($attr != $o) $e->send(E_NOTICE, 'AttrValidator: Attributes transformed', $o, $attr);
+            }
         }
         
         // create alias to this element's attribute definition array, see
@@ -114,6 +118,8 @@ class HTMLPurifier_AttrValidator
                 
                 // simple substitution
                 $attr[$attr_key] = $result;
+            } else {
+                // nothing happens
             }
             
             // we'd also want slightly more complicated substitution
@@ -130,15 +136,21 @@ class HTMLPurifier_AttrValidator
         // global (error reporting untested)
         foreach ($definition->info_attr_transform_post as $transform) {
             $attr = $transform->transform($o = $attr, $config, $context);
-            if ($e && ($attr != $o)) $e->send(E_NOTICE, 'AttrValidator: Attributes transformed', $o, $attr);
+            if ($e) {
+                if ($attr != $o) $e->send(E_NOTICE, 'AttrValidator: Attributes transformed', $o, $attr);
+            }
         }
         
         // local (error reporting untested)
         foreach ($definition->info[$token->name]->attr_transform_post as $transform) {
             $attr = $transform->transform($o = $attr, $config, $context);
-            if ($e && ($attr != $o)) $e->send(E_NOTICE, 'AttrValidator: Attributes transformed', $o, $attr);
+            if ($e) {
+                if ($attr != $o) $e->send(E_NOTICE, 'AttrValidator: Attributes transformed', $o, $attr);
+            }
         }
         
+        $token->attr = $attr;
+        
         // destroy CurrentToken if we made it ourselves
         if (!$current_token) $context->destroy('CurrentToken');
         

library/HTMLPurifier/CSSDefinition.php

@@ -90,7 +90,7 @@ class HTMLPurifier_CSSDefinition extends HTMLPurifier_Definition
         $this->info['border-left-width'] = 
         $this->info['border-right-width'] = new HTMLPurifier_AttrDef_CSS_Composite(array(
             new HTMLPurifier_AttrDef_Enum(array('thin', 'medium', 'thick')),
-            new HTMLPurifier_AttrDef_CSS_Length(true) //disallow negative
+            new HTMLPurifier_AttrDef_CSS_Length('0') //disallow negative
         ));
         
         $this->info['border-width'] = new HTMLPurifier_AttrDef_CSS_Multiple($border_width);
@@ -116,7 +116,7 @@ class HTMLPurifier_CSSDefinition extends HTMLPurifier_Definition
         $this->info['line-height'] = new HTMLPurifier_AttrDef_CSS_Composite(array(
             new HTMLPurifier_AttrDef_Enum(array('normal')),
             new HTMLPurifier_AttrDef_CSS_Number(true), // no negatives
-            new HTMLPurifier_AttrDef_CSS_Length(true),
+            new HTMLPurifier_AttrDef_CSS_Length('0'),
             new HTMLPurifier_AttrDef_CSS_Percentage(true)
         ));
         
@@ -138,7 +138,7 @@ class HTMLPurifier_CSSDefinition extends HTMLPurifier_Definition
         $this->info['padding-bottom'] = 
         $this->info['padding-left'] = 
         $this->info['padding-right'] = new HTMLPurifier_AttrDef_CSS_Composite(array(
-            new HTMLPurifier_AttrDef_CSS_Length(true),
+            new HTMLPurifier_AttrDef_CSS_Length('0'),
             new HTMLPurifier_AttrDef_CSS_Percentage(true)
         ));
         
@@ -149,14 +149,26 @@ class HTMLPurifier_CSSDefinition extends HTMLPurifier_Definition
             new HTMLPurifier_AttrDef_CSS_Percentage()
         ));
         
-        $this->info['width'] =
+        $trusted_wh = new HTMLPurifier_AttrDef_CSS_Composite(array(
-        $this->info['height'] =
+            new HTMLPurifier_AttrDef_CSS_Length('0'),
-        new HTMLPurifier_AttrDef_CSS_DenyElementDecorator(
-        new HTMLPurifier_AttrDef_CSS_Composite(array(
-            new HTMLPurifier_AttrDef_CSS_Length(true),
             new HTMLPurifier_AttrDef_CSS_Percentage(true),
             new HTMLPurifier_AttrDef_Enum(array('auto'))
-        )), 'img');
+        ));
+        $max = $config->get('CSS', 'MaxImgLength');
+        
+        $this->info['width'] =
+        $this->info['height'] =
+            $max === null ?
+            $trusted_wh : 
+            new HTMLPurifier_AttrDef_Switch('img',
+                // For img tags:
+                new HTMLPurifier_AttrDef_CSS_Composite(array(
+                    new HTMLPurifier_AttrDef_CSS_Length('0', $max),
+                    new HTMLPurifier_AttrDef_Enum(array('auto'))
+                )),
+                // For everyone else:
+                $trusted_wh
+            );
         
         $this->info['text-decoration'] = new HTMLPurifier_AttrDef_CSS_TextDecoration();
         

library/HTMLPurifier/ChildDef.php

@@ -24,6 +24,14 @@ abstract class HTMLPurifier_ChildDef
      */
     public $elements = array();
     
+    /**
+     * Get lookup of tag names that should not close this element automatically.
+     * All other elements will do so.
+     */
+    public function getNonAutoCloseElements($config) {
+        return $this->elements;
+    }
+    
     /**
      * Validates nodes according to definition and returns modification.
      * 

library/HTMLPurifier/ChildDef/Custom.php

@@ -5,8 +5,6 @@
  * 
  * @warning Currently this class is an all or nothing proposition, that is,
  *          it will only give a bool return value.
- * @note This class is currently not used by any code, although it is unit
- *       tested.
  */
 class HTMLPurifier_ChildDef_Custom extends HTMLPurifier_ChildDef
 {

library/HTMLPurifier/ChildDef/Required.php

@@ -55,10 +55,7 @@ class HTMLPurifier_ChildDef_Required extends HTMLPurifier_ChildDef
         $escape_invalid_children = $config->get('Core', 'EscapeInvalidChildren');
         
         // generator
-        static $gen = null;
+        $gen = new HTMLPurifier_Generator($config, $context);
-        if ($gen === null) {
-            $gen = new HTMLPurifier_Generator();
-        }
         
         foreach ($tokens_of_children as $token) {
             if (!empty($token->is_whitespace)) {
@@ -83,7 +80,7 @@ class HTMLPurifier_ChildDef_Required extends HTMLPurifier_ChildDef
                         $result[] = $token;
                     } elseif ($pcdata_allowed && $escape_invalid_children) {
                         $result[] = new HTMLPurifier_Token_Text(
-                            $gen->generateFromToken($token, $config)
+                            $gen->generateFromToken($token)
                         );
                     }
                     continue;
@@ -94,7 +91,7 @@ class HTMLPurifier_ChildDef_Required extends HTMLPurifier_ChildDef
             } elseif ($pcdata_allowed && $escape_invalid_children) {
                 $result[] =
                     new HTMLPurifier_Token_Text(
-                        $gen->generateFromToken( $token, $config )
+                        $gen->generateFromToken($token)
                     );
             } else {
                 // drop silently

library/HTMLPurifier/ChildDef/StrictBlockquote.php

@@ -10,16 +10,19 @@ class HTMLPurifier_ChildDef_StrictBlockquote extends HTMLPurifier_ChildDef_Requi
     public $allow_empty = true;
     public $type = 'strictblockquote';
     protected $init = false;
+    
+    /**
+     * @note We don't want MakeWellFormed to auto-close inline elements since
+     *       they might be allowed.
+     */
+    public function getNonAutoCloseElements($config) {
+        $this->init($config);
+        return $this->fake_elements;
+    }
+    
     public function validateChildren($tokens_of_children, $config, $context) {
         
-        $def = $config->getHTMLDefinition();
+        $this->init($config);
-        if (!$this->init) {
-            // allow all inline elements
-            $this->real_elements = $this->elements;
-            $this->fake_elements = $def->info_content_sets['Flow'];
-            $this->fake_elements['#PCDATA'] = true;
-            $this->init = true;
-        }
         
         // trick the parent class into thinking it allows more
         $this->elements = $this->fake_elements;
@@ -29,6 +32,7 @@ class HTMLPurifier_ChildDef_StrictBlockquote extends HTMLPurifier_ChildDef_Requi
         if ($result === false) return array();
         if ($result === true) $result = $tokens_of_children;
         
+        $def = $config->getHTMLDefinition();
         $block_wrap_start = new HTMLPurifier_Token_Start($def->info_block_wrapper);
         $block_wrap_end   = new HTMLPurifier_Token_End(  $def->info_block_wrapper);
         $is_inline = false;
@@ -68,5 +72,16 @@ class HTMLPurifier_ChildDef_StrictBlockquote extends HTMLPurifier_ChildDef_Requi
         if ($is_inline) $ret[] = $block_wrap_end;
         return $ret;
     }
+    
+    private function init($config) {
+        if (!$this->init) {
+            $def = $config->getHTMLDefinition();
+            // allow all inline elements
+            $this->real_elements = $this->elements;
+            $this->fake_elements = $def->info_content_sets['Flow'];
+            $this->fake_elements['#PCDATA'] = true;
+            $this->init = true;
+        }
+    }
 }
 

library/HTMLPurifier/Config.php

@@ -20,7 +20,7 @@ class HTMLPurifier_Config
     /**
      * HTML Purifier's version
      */
-    public $version = '3.1.0';
+    public $version = '3.2.0';
     
     /**
      * Bool indicator whether or not to automatically finalize 
@@ -125,7 +125,7 @@ class HTMLPurifier_Config
                 E_USER_WARNING);
             return;
         }
-        if ($this->def->info[$namespace][$key]->class == 'alias') {
+        if (isset($this->def->info[$namespace][$key]->isAlias)) {
             $d = $this->def->info[$namespace][$key];
             trigger_error('Cannot get value from aliased directive, use real name ' . $d->namespace . '.' . $d->name,
                 E_USER_ERROR);
@@ -196,40 +196,48 @@ class HTMLPurifier_Config
                 E_USER_WARNING);
             return;
         }
-        if ($this->def->info[$namespace][$key]->class == 'alias') {
+        $def = $this->def->info[$namespace][$key];
+        
+        if (isset($def->isAlias)) {
             if ($from_alias) {
                 trigger_error('Double-aliases not allowed, please fix '.
                     'ConfigSchema bug with' . "$namespace.$key", E_USER_ERROR);
                 return;
             }
-            $this->set($new_ns = $this->def->info[$namespace][$key]->namespace,
+            $this->set($new_ns  = $def->namespace,
-                       $new_dir = $this->def->info[$namespace][$key]->name,
+                       $new_dir = $def->name,
                        $value, true);
             trigger_error("$namespace.$key is an alias, preferred directive name is $new_ns.$new_dir", E_USER_NOTICE);
             return;
         }
+        
+        // Raw type might be negative when using the fully optimized form
+        // of stdclass, which indicates allow_null == true
+        $rtype = is_int($def) ? $def : $def->type;
+        if ($rtype < 0) {
+            $type = -$rtype;
+            $allow_null = true;
+        } else {
+            $type = $rtype;
+            $allow_null = isset($def->allow_null);
+        }
+        
         try {
-            $value = $this->parser->parse(
+            $value = $this->parser->parse($value, $type, $allow_null);
-                        $value,
-                        $type = $this->def->info[$namespace][$key]->type,
-                        $this->def->info[$namespace][$key]->allow_null
-                     );
         } catch (HTMLPurifier_VarParserException $e) {
-            trigger_error('Value for ' . "$namespace.$key" . ' is of invalid type, should be ' . $type, E_USER_WARNING);
+            trigger_error('Value for ' . "$namespace.$key" . ' is of invalid type, should be ' . HTMLPurifier_VarParser::getTypeName($type), E_USER_WARNING);
             return;
         }
-        if (is_string($value)) {
+        if (is_string($value) && is_object($def)) {
             // resolve value alias if defined
-            if (isset($this->def->info[$namespace][$key]->aliases[$value])) {
+            if (isset($def->aliases[$value])) {
-                $value = $this->def->info[$namespace][$key]->aliases[$value];
+                $value = $def->aliases[$value];
             }
-            if ($this->def->info[$namespace][$key]->allowed !== true) {
+            // check to see if the value is allowed
-                // check to see if the value is allowed
+            if (isset($def->allowed) && !isset($def->allowed[$value])) {
-                if (!isset($this->def->info[$namespace][$key]->allowed[$value])) {
+                trigger_error('Value not supported, valid values are: ' .
-                    trigger_error('Value not supported, valid values are: ' .
+                    $this->_listify($def->allowed), E_USER_WARNING);
-                        $this->_listify($this->def->info[$namespace][$key]->allowed), E_USER_WARNING);
+                return;
-                    return;
-                }
             }
         }
         $this->conf[$namespace][$key] = $value;
@@ -386,7 +394,7 @@ class HTMLPurifier_Config
                     if (isset($blacklisted_directives["$ns.$directive"])) continue;
                     if (!isset($allowed_directives["$ns.$directive"]) && !isset($allowed_ns[$ns])) continue;
                 }
-                if ($def->class == 'alias') continue;
+                if (isset($def->isAlias)) continue;
                 if ($directive == 'DefinitionID' || $directive == 'DefinitionRev') continue;
                 $ret[] = array($ns, $directive);
             }

library/HTMLPurifier/ConfigDef.php

@@ -1,9 +0,0 @@
-<?php
-
-/**
- * Base class for configuration entity
- */
-abstract class HTMLPurifier_ConfigDef {
-    public $class = false;
-}
-

library/HTMLPurifier/ConfigDef/Directive.php

@@ -1,55 +0,0 @@
-<?php
-
-/**
- * Structure object containing definition of a directive.
- * @note This structure does not contain default values
- */
-class HTMLPurifier_ConfigDef_Directive extends HTMLPurifier_ConfigDef
-{
-    
-    public $class = 'directive';
-    
-    public function __construct(
-        $type = null,
-        $allow_null = null,
-        $allowed = null,
-        $aliases = null
-    ) {
-        if (       $type !== null)        $this->type = $type;
-        if ( $allow_null !== null)  $this->allow_null = $allow_null;
-        if (    $allowed !== null)     $this->allowed = $allowed;
-        if (    $aliases !== null)     $this->aliases = $aliases;
-    }
-    
-    /**
-     * Allowed type of the directive. Values are:
-     *      - string
-     *      - istring (case insensitive string)
-     *      - int
-     *      - float
-     *      - bool
-     *      - lookup (array of value => true)
-     *      - list (regular numbered index array)
-     *      - hash (array of key => value)
-     *      - mixed (anything goes)
-     */
-    public $type = 'mixed';
-    
-    /**
-     * Is null allowed? Has no effect for mixed type.
-     * @bool
-     */
-    public $allow_null = false;
-    
-    /**
-     * Lookup table of allowed values of the element, bool true if all allowed.
-     */
-    public $allowed = true;
-    
-    /**
-     * Hash of value aliases, i.e. values that are equivalent.
-     */
-    public $aliases = array();
-    
-}
-

library/HTMLPurifier/ConfigDef/DirectiveAlias.php

@@ -1,24 +0,0 @@
-<?php
-
-/**
- * Structure object describing a directive alias
- */
-class HTMLPurifier_ConfigDef_DirectiveAlias extends HTMLPurifier_ConfigDef
-{
-    public $class = 'alias';
-    
-    /**
-     * Namespace being aliased to
-     */
-    public $namespace;
-    /**
-     * Directive being aliased to
-     */
-    public $name;
-    
-    public function __construct($namespace, $name) {
-        $this->namespace = $namespace;
-        $this->name = $name;
-    }
-}
-

library/HTMLPurifier/ConfigDef/Namespace.php

@@ -1,10 +0,0 @@
-<?php
-
-/**
- * Structure object describing of a namespace
- */
-class HTMLPurifier_ConfigDef_Namespace extends HTMLPurifier_ConfigDef
-{
-    public $class = 'namespace';
-}
-

library/HTMLPurifier/ConfigSchema.php

@@ -12,7 +12,33 @@ class HTMLPurifier_ConfigSchema {
     public $defaults = array();
     
     /**
-     * Definition of the directives.
+     * Definition of the directives. The structure of this is:
+     * 
+     *  array(
+     *      'Namespace' => array(
+     *          'Directive' => new stdclass(),
+     *      )
+     *  )
+     * 
+     * The stdclass may have the following properties:
+     * 
+     *  - If isAlias isn't set:
+     *      - type: Integer type of directive, see HTMLPurifier_VarParser for definitions
+     *      - allow_null: If set, this directive allows null values
+     *      - aliases: If set, an associative array of value aliases to real values
+     *      - allowed: If set, a lookup array of allowed (string) values
+     *  - If isAlias is set:
+     *      - namespace: Namespace this directive aliases to
+     *      - name: Directive name this directive aliases to
+     * 
+     * In certain degenerate cases, stdclass will actually be an integer. In
+     * that case, the value is equivalent to an stdclass with the type
+     * property set to the integer. If the integer is negative, type is
+     * equal to the absolute value of integer, and allow_null is true.
+     * 
+     * This class is friendly with HTMLPurifier_Config. If you need introspection
+     * about the schema, you're better of using the ConfigSchema_Interchange,
+     * which uses more memory but has much richer information.
      */
     public $info = array();
     
@@ -21,15 +47,6 @@ class HTMLPurifier_ConfigSchema {
      */
     static protected $singleton;
     
-    /**
-     * Variable parser.
-     */
-    protected $parser;
-    
-    public function __construct() {
-        $this->parser = new HTMLPurifier_VarParser_Flexible();
-    }
-    
     /**
      * Unserializes the default ConfigSchema.
      */
@@ -62,11 +79,11 @@ class HTMLPurifier_ConfigSchema {
      * @param $allow_null Whether or not to allow null values
      */
     public function add($namespace, $name, $default, $type, $allow_null) {
-        $default = $this->parser->parse($default, $type, $allow_null);
+        $obj = new stdclass();
-        $this->info[$namespace][$name] = new HTMLPurifier_ConfigDef_Directive();
+        $obj->type = is_int($type) ? $type : HTMLPurifier_VarParser::$types[$type];
-        $this->info[$namespace][$name]->type = $type;
+        if ($allow_null) $obj->allow_null = true;
-        $this->info[$namespace][$name]->allow_null = $allow_null;
+        $this->info[$namespace][$name] = $obj;
-        $this->defaults[$namespace][$name]   = $default;
+        $this->defaults[$namespace][$name] = $default;
     }
     
     /**
@@ -90,6 +107,9 @@ class HTMLPurifier_ConfigSchema {
      * @param $aliases Hash of aliased values to the real alias
      */
     public function addValueAliases($namespace, $name, $aliases) {
+        if (!isset($this->info[$namespace][$name]->aliases)) {
+            $this->info[$namespace][$name]->aliases = array();
+        }
         foreach ($aliases as $alias => $real) {
             $this->info[$namespace][$name]->aliases[$alias] = $real;
         }
@@ -104,7 +124,6 @@ class HTMLPurifier_ConfigSchema {
      * @param $allowed Lookup array of allowed values
      */
     public function addAllowedValues($namespace, $name, $allowed) {
-        $type = $this->info[$namespace][$name]->type;
         $this->info[$namespace][$name]->allowed = $allowed;
     }
     
@@ -116,7 +135,26 @@ class HTMLPurifier_ConfigSchema {
      * @param $new_name Directive that the alias will be to
      */
     public function addAlias($namespace, $name, $new_namespace, $new_name) {
-        $this->info[$namespace][$name] = new HTMLPurifier_ConfigDef_DirectiveAlias($new_namespace, $new_name);
+        $obj = new stdclass;
+        $obj->namespace = $new_namespace;
+        $obj->name = $new_name;
+        $obj->isAlias = true;
+        $this->info[$namespace][$name] = $obj;
+    }
+    
+    /**
+     * Replaces any stdclass that only has the type property with type integer.
+     */
+    public function postProcess() {
+        foreach ($this->info as $namespace => $info) {
+            foreach ($info as $directive => $v) {
+                if (count((array) $v) == 1) {
+                    $this->info[$namespace][$directive] = $v->type;
+                } elseif (count((array) $v) == 2 && isset($v->allow_null)) {
+                    $this->info[$namespace][$directive] = -$v->type;
+                }
+            }
+        }
     }
     
     // DEPRECATED METHODS
@@ -124,7 +162,6 @@ class HTMLPurifier_ConfigSchema {
     /** @see HTMLPurifier_ConfigSchema->set() */
     public static function define($namespace, $name, $default, $type, $description) {
         HTMLPurifier_ConfigSchema::deprecated(__METHOD__);
-        // process modifiers (OPTIMIZE!)
         $type_values = explode('/', $type, 2);
         $type = $type_values[0];
         $modifier = isset($type_values[1]) ? $type_values[1] : false;
@@ -168,7 +205,8 @@ class HTMLPurifier_ConfigSchema {
     /** @deprecated, use HTMLPurifier_VarParser->parse() */
     public function validate($a, $b, $c = false) {
         trigger_error("HTMLPurifier_ConfigSchema->validate deprecated, use HTMLPurifier_VarParser->parse instead", E_USER_NOTICE);
-        return $this->parser->parse($a, $b, $c);
+        $parser = new HTMLPurifier_VarParser();
+        return $parser->parse($a, $b, $c);
     }
     
     /**

library/HTMLPurifier/ConfigSchema/Builder/ConfigSchema.php

@@ -43,6 +43,7 @@ class HTMLPurifier_ConfigSchema_Builder_ConfigSchema
                 );
             }
         }
+        $schema->postProcess();
         return $schema;
     }
     

library/HTMLPurifier/ConfigSchema/Validator.php

@@ -111,7 +111,8 @@ class HTMLPurifier_ConfigSchema_Validator
         if (!is_null($d->allowed) || !empty($d->valueAliases)) {
             // allowed and valueAliases require that we be dealing with
             // strings, so check for that early.
-            if (!isset(HTMLPurifier_VarParser::$stringTypes[$d->type])) {
+            $d_int = HTMLPurifier_VarParser::$types[$d->type];
+            if (!isset(HTMLPurifier_VarParser::$stringTypes[$d_int])) {
                 $this->error('type', 'must be a string type when used with allowed or value aliases');
             }
         }

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

@@ -0,0 +1,9 @@
+Attr.DefaultImageAlt
+TYPE: string/null
+DEFAULT: null
+--DESCRIPTION--
+This is the content of the alt tag of an image if the user had not
+previously specified an alt attribute.  This applies to all images without
+a valid alt attribute, as opposed to %Attr.DefaultInvalidImageAlt, which
+only applies to invalid images, and overrides in the case of an invalid image.
+Default behavior with null is to use the basename of the src tag for the alt.

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

@@ -0,0 +1,10 @@
+AutoFormat.DisplayLinkURI
+TYPE: bool
+VERSION: 3.2.0
+DEFAULT: false
+--DESCRIPTION--
+<p>
+  This directive turns on the in-text display of URIs in &lt;a&gt; tags, and disables
+  those links. For example, <a href="http://example.com">example</a> becomes
+  example (<a>http://example.com</a>).
+</p>

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

@@ -0,0 +1,44 @@
+AutoFormat.RemoveEmpty
+TYPE: bool
+VERSION: 3.2.0
+DEFAULT: false
+--DESCRIPTION--
+<p>
+  When enabled, HTML Purifier will attempt to remove empty elements that
+  contribute no semantic information to the document. The following types
+  of nodes will be removed:
+</p>
+<ul><li>
+    Tags with no attributes and no content, and that are not empty
+    elements (remove <code>&lt;a&gt;&lt;/a&gt;</code> but not
+    <code>&lt;br /&gt;</code>), and
+  </li>
+  <li>
+    Tags with no content, except for:<ul>
+      <li>The <code>colgroup</code> element, or</li>
+      <li>
+        Elements with the <code>id</code> or <code>name</code> attribute,
+        when those attributes are permitted on those elements.
+      </li>
+    </ul></li>
+</ul>
+<p>
+  Please be very careful when using this functionality; while it may not
+  seem that empty elements contain useful information, they can alter the
+  layout of a document given appropriate styling. This directive is most
+  useful when you are processing machine-generated HTML, please avoid using
+  it on regular user HTML.
+</p>
+<p>
+  Elements that contain only whitespace will be treated as empty. Non-breaking
+  spaces, however, do not count as whitespace.
+</p>
+<p>
+  This algorithm is not perfect; you may still notice some empty tags,
+  particularly if a node had elements, but those elements were later removed
+  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
+  made it empty, it will stay.
+</p>

library/HTMLPurifier/ConfigSchema/schema/CSS.MaxImgLength.txt

@@ -0,0 +1,15 @@
+CSS.MaxImgLength
+TYPE: string/null
+DEFAULT: '1200px'
+VERSION: 3.1.1
+--DESCRIPTION--
+<p>
+ This parameter sets the maximum allowed length on <code>img</code> tags,
+ effectively the <code>width</code> and <code>height</code> properties.
+ Only absolute units of measurement (in, pt, pc, mm, cm) and pixels (px) are allowed. This is
+ in place to prevent imagecrash attacks, disable with null at your own risk.
+ This directive is similar to %HTML.MaxImgLength, and both should be
+ concurrently edited, although there are
+ subtle differences in the input format (the CSS max is a number with
+ a unit).
+</p>

library/HTMLPurifier/ConfigSchema/schema/Core.AggressivelyFixLt.txt

@@ -1,13 +1,17 @@
 Core.AggressivelyFixLt
 TYPE: bool
 VERSION: 2.1.0
-DEFAULT: false
+DEFAULT: true
 --DESCRIPTION--
-
+<p>
-This directive enables aggressive pre-filter fixes HTML Purifier can
+    This directive enables aggressive pre-filter fixes HTML Purifier can
-perform in order to ensure that open angled-brackets do not get killed
+    perform in order to ensure that open angled-brackets do not get killed
-during parsing stage. Enabling this will result in two preg_replace_callback
+    during parsing stage. Enabling this will result in two preg_replace_callback
-calls and one preg_replace call for every bit of HTML passed through here.
+    calls and at least two preg_replace calls for every HTML document parsed;
-It is not necessary and will have no effect for PHP 4.
+    if your users make very well-formed HTML, you can set this directive false.
-
+    This has no effect when DirectLex is used.
-
+</p>
+<p>
+    <strong>Notice:</strong> This directive's default turned from false to true
+    in HTML Purifier 3.2.0.
+</p>

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

@@ -14,13 +14,49 @@ EXTERNAL: CSSTidy
 <p>
   Sample usage:
 </p>
-<pre><![CDATA[$config = HTMLPurifier_Config::createDefault();
+<pre><![CDATA[
-$config->set('Filter', 'ExtractStyleBlocks', true);
+<?php
-$purifier = new HTMLPurifier($config);
+    header('Content-type: text/html; charset=utf-8');
-$styles = $purifier->context->get('StyleBlocks');
+    echo '<?xml version="1.0" encoding="UTF-8"?>';
-foreach ($styles as $style) {
+?>
-    echo '<style type="text/css">' . $style . "</style>\n";
+<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"
-}]]></pre>
+  "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
+<html xmlns="http://www.w3.org/1999/xhtml" lang="en" xml:lang="en">
+<head>
+  <title>Filter.ExtractStyleBlocks</title>
+<?php
+    require_once '/path/to/library/HTMLPurifier.auto.php';
+    require_once '/path/to/csstidy.class.php';
+    
+    $dirty = '<style>body {color:#F00;}</style> Some text';
+
+    $config = HTMLPurifier_Config::createDefault();
+    $config->set('Filter', 'ExtractStyleBlocks', true);
+    $purifier = new HTMLPurifier($config);
+    
+    $html = $purifier->purify($dirty);
+    
+    // This implementation writes the stylesheets to the styles/ directory.
+    // You can also echo the styles inside the document, but it's a bit
+    // more difficult to make sure they get interpreted properly by
+    // browsers; try the usual CSS armoring techniques.
+    $styles = $purifier->context->get('StyleBlocks');
+    $dir = 'styles/';
+    if (!is_dir($dir)) mkdir($dir);
+    $hash = sha1($_GET['html']);
+    foreach ($styles as $i => $style) {
+        file_put_contents($name = $dir . $hash . "_$i");
+        echo '<link rel="stylesheet" type="text/css" href="'.$name.'" />';
+    }
+?>
+</head>
+<body>
+  <div>
+    <?php echo $html; ?>
+  </div>
+</b]]><![CDATA[ody>
+</html>
+]]></pre>
 <p>
   <strong>Warning:</strong> It is possible for a user to mount an
   imagecrash attack using this CSS. Counter-measures are difficult;

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

@@ -0,0 +1,13 @@
+HTML.MaxImgLength
+TYPE: int/null
+DEFAULT: 1200
+VERSION: 3.1.1
+--DESCRIPTION--
+<p>
+ This directive controls the maximum number of pixels in the width and
+ height attributes in <code>img</code> tags. This is
+ in place to prevent imagecrash attacks, disable with null at your own risk.
+ This directive is similar to %CSS.MaxImgLength, and both should be
+ concurrently edited, although there are
+ subtle differences in the input format (the HTML max is an integer).
+</p>

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

@@ -0,0 +1,13 @@
+HTML.SafeEmbed
+TYPE: bool
+VERSION: 3.1.1
+DEFAULT: false
+--DESCRIPTION--
+<p>
+    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
+    to enable this with %HTML.SafeObject.
+    <strong>Highly experimental.</strong>
+</p>

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

@@ -0,0 +1,13 @@
+HTML.SafeObject
+TYPE: bool
+VERSION: 3.1.1
+DEFAULT: false
+--DESCRIPTION--
+<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 
+    enable %HTML.SafeEmbed for maximum interoperability with Internet Explorer,
+    although embed tags will cause your website to stop validating.
+    <strong>Highly experimental.</strong>
+</p>

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

@@ -0,0 +1,13 @@
+Output.SortAttr
+TYPE: bool
+VERSION: 3.2.0
+DEFAULT: false
+--DESCRIPTION--
+<p>
+  If true, HTML Purifier will sort attributes by name before writing them back
+  to the document, converting a tag like: <code>&lt;el b="" a="" c="" /&gt;</code>
+  to <code>&lt;el a="" b="" c="" /&gt;</code>. This is a workaround for
+  a bug in FCKeditor which causes it to swap attributes order, adding noise
+  to text diffs. If you're not seeing this bug, chances are, you don't need
+  this directive.
+</p>

library/HTMLPurifier/ConfigSchema/schema/URI.Munge.txt

@@ -6,7 +6,7 @@ DEFAULT: NULL
 
 <p>
     Munges all browsable (usually http, https and ftp)
-    absolute URI's into another URI, usually a URI redirection service.
+    absolute URIs into another URI, usually a URI redirection service.
     This directive accepts a URI, formatted with a <code>%s</code> where 
     the url-encoded original URI should be inserted (sample: 
     <code>http://www.google.com/url?q=%s</code>).
@@ -19,13 +19,64 @@ DEFAULT: NULL
         Prevent PageRank leaks, while being fairly transparent 
         to users (you may also want to add some client side JavaScript to 
         override the text in the statusbar). <strong>Notice</strong>:
-        Many security experts believe that this form of protection does
+        Many security experts believe that this form of protection does not deter spam-bots. 
-not deter spam-bots. 
     </li>
     <li>
         Redirect users to a splash page telling them they are leaving your
-        website. While this is poor usability practice, it is often
+        website. While this is poor usability practice, it is often mandated
-mandated
         in corporate environments.
     </li>
 </ul>
+<p>
+    Prior to HTML Purifier 3.1.1, this directive also enabled the munging
+    of browsable external resources, which could break things if your redirection
+    script was a splash page or used <code>meta</code> tags. To revert to
+    previous behavior, please use %URI.MungeResources.
+</p>
+<p>
+    You may want to also use %URI.MungeSecretKey along with this directive
+    in order to enforce what URIs your redirector script allows. Open
+    redirector scripts can be a security risk and negatively affect the
+    reputation of your domain name.
+</p>
+<p>
+    Starting with HTML Purifier 3.1.1, there is also these substitutions:
+</p>
+<table>
+    <thead>
+        <tr>
+            <th>Key</th>
+            <th>Description</th>
+            <th>Example <code>&lt;a href=""&gt;</code></th>
+        </tr>
+    </thead>
+    <tbody>
+        <tr>
+            <td>%r</td>
+            <td>1 - The URI embeds a resource<br />(blank) - The URI is merely a link</td>
+            <td></td>
+        </tr>
+        <tr>
+            <td>%n</td>
+            <td>The name of the tag this URI came from</td>
+            <td>a</td>
+        </tr>
+        <tr>
+            <td>%m</td>
+            <td>The name of the attribute this URI came from</td>
+            <td>href</td>
+        </tr>
+        <tr>
+            <td>%p</td>
+            <td>The name of the CSS property this URI came from, or blank if irrelevant</td>
+            <td></td>
+        </tr>
+    </tbody>
+</table>
+<p>
+    Admittedly, these letters are somewhat arbitrary; the only stipulation
+    was that they couldn't be a through f. r is for resource (I would have preferred
+    e, but you take what you can get), n is for name, m
+    was picked because it came after n (and I couldn't use a), p is for
+    property.
+</p>

library/HTMLPurifier/ConfigSchema/schema/URI.MungeResources.txt

@@ -0,0 +1,16 @@
+URI.MungeResources
+TYPE: bool
+VERSION: 3.1.1
+DEFAULT: false
+--DESCRIPTION--
+<p>
+    If true, any URI munging directives like %URI.Munge
+    will also apply to embedded resources, such as <code>&lt;img src=""&gt;</code>.
+    Be careful enabling this directive if you have a redirector script
+    that does not use the <code>Location</code> HTTP header; all of your images
+    and other embedded resources will break.
+</p>
+<p>
+    <strong>Warning:</strong> It is strongly advised you use this in conjunction
+    %URI.MungeSecretKey to mitigate the security risk of an open redirector.
+</p>

library/HTMLPurifier/ConfigSchema/schema/URI.MungeSecretKey.txt

@@ -0,0 +1,29 @@
+URI.MungeSecretKey
+TYPE: string/null
+VERSION: 3.1.1
+DEFAULT: NULL
+--DESCRIPTION--
+<p>
+    This directive enables secure checksum generation along with %URI.Munge.
+    It should be set to a secure key that is not shared with anyone else.
+    The checksum can be placed in the URI using %t. Use of this checksum
+    affords an additional level of protection by allowing a redirector
+    to check if a URI has passed through HTML Purifier with this line:
+</p>
+
+<pre>$checksum === sha1($secret_key . ':' . $url)</pre>
+
+<p>
+    If the output is TRUE, the redirector script should accept the URI.
+</p>
+
+<p>
+    Please note that it would still be possible for an attacker to procure
+    secure hashes en-mass by abusing your website's Preview feature or the
+    like, but this service affords an additional level of protection
+    that should be combined with website blacklisting.
+</p>
+
+<p>
+    Remember this has no effect if %URI.Munge is not on.
+</p>

library/HTMLPurifier/ContentSets.php

@@ -37,33 +37,35 @@ class HTMLPurifier_ContentSets
         // sorry, no way of overloading
         foreach ($modules as $module_i => $module) {
             foreach ($module->content_sets as $key => $value) {
-                if (isset($this->info[$key])) {
+                $temp = $this->convertToLookup($value);
+                if (isset($this->lookup[$key])) {
                     // add it into the existing content set
-                    $this->info[$key] = $this->info[$key] . ' | ' . $value;
+                    $this->lookup[$key] = array_merge($this->lookup[$key], $temp);
                 } else {
-                    $this->info[$key] = $value;
+                    $this->lookup[$key] = $temp;
                 }
             }
         }
-        // perform content_set expansions
+        $old_lookup = false;
-        $this->keys = array_keys($this->info);
+        while ($old_lookup !== $this->lookup) {
-        foreach ($this->info as $i => $set) {
+            $old_lookup = $this->lookup;
-            // only performed once, so infinite recursion is not
+            foreach ($this->lookup as $i => $set) {
-            // a problem
+                $add = array();
-            $this->info[$i] =
+                foreach ($set as $element => $x) {
-                str_replace(
+                    if (isset($this->lookup[$element])) {
-                    $this->keys,
+                        $add += $this->lookup[$element];
-                    // must be recalculated each time due to
+                        unset($this->lookup[$i][$element]);
-                    // changing substitutions
+                    }
-                    array_values($this->info),
+                }
-                $set);
+                $this->lookup[$i] += $add;
+            }
         }
-        $this->values = array_values($this->info);
         
-        // generate lookup tables
+        foreach ($this->lookup as $key => $lookup) {
-        foreach ($this->info as $name => $set) {
+            $this->info[$key] = implode(' | ', array_keys($lookup));
-            $this->lookup[$name] = $this->convertToLookup($set);
         }
+        $this->keys   = array_keys($this->info);
+        $this->values = array_values($this->info);
     }
     
     /**
@@ -75,12 +77,22 @@ class HTMLPurifier_ContentSets
         if (!empty($def->child)) return; // already done!
         $content_model = $def->content_model;
         if (is_string($content_model)) {
-            $def->content_model = str_replace(
+            // Assume that $this->keys is alphanumeric
-                $this->keys, $this->values, $content_model);
+            $def->content_model = preg_replace_callback(
+                '/\b(' . implode('|', $this->keys) . ')\b/',
+                array($this, 'generateChildDefCallback'),
+                $content_model
+            );
+            //$def->content_model = str_replace(
+            //    $this->keys, $this->values, $content_model);
         }
         $def->child = $this->getChildDef($def, $module);
     }
     
+    public function generateChildDefCallback($matches) {
+        return $this->info[$matches[0]];
+    }
+    
     /**
      * Instantiates a ChildDef based on content_model and content_model_type
      * member variables in HTMLPurifier_ElementDef

library/HTMLPurifier/DefinitionCache/Serializer/README

@@ -0,0 +1 @@
+This is a dummy file to prevent Git from ignoring this empty directory.

library/HTMLPurifier/Encoder.php

@@ -46,35 +46,13 @@ class HTMLPurifier_Encoder
      */
     public static function cleanUTF8($str, $force_php = false) {
         
-        static $non_sgml_chars = array();
-        if (empty($non_sgml_chars)) {
-            for ($i = 0; $i <= 31; $i++) {
-                // non-SGML ASCII chars
-                // save \r, \t and \n
-                if ($i == 9 || $i == 13 || $i == 10) continue;
-                $non_sgml_chars[chr($i)] = '';
-            }
-            for ($i = 127; $i <= 159; $i++) {
-                $non_sgml_chars[HTMLPurifier_Encoder::unichr($i)] = '';
-            }
-        }
-        
-        static $iconv = null;
-        if ($iconv === null) $iconv = function_exists('iconv');
-        
         // UTF-8 validity is checked since PHP 4.3.5
         // This is an optimization: if the string is already valid UTF-8, no
-        // need to do iconv/php stuff. 99% of the time, this will be the case.
+        // need to do PHP stuff. 99% of the time, this will be the case.
-        if (preg_match('/^.{1}/us', $str)) {
+        // The regexp matches the XML char production, as well as well as excluding
-            return strtr($str, $non_sgml_chars);
+        // non-SGML codepoints U+007F to U+009F
-        }
+        if (preg_match('/^[\x{9}\x{A}\x{D}\x{20}-\x{7E}\x{A0}-\x{D7FF}\x{E000}-\x{FFFD}\x{10000}-\x{10FFFF}]*$/Du', $str)) {
-        
+            return $str;
-        if ($iconv && !$force_php) {
-            // do the shortcut way
-            set_error_handler(array('HTMLPurifier_Encoder', 'muteErrorHandler'));
-            $str = iconv('UTF-8', 'UTF-8//IGNORE', $str);
-            restore_error_handler();
-            return strtr($str, $non_sgml_chars);
         }
         
         $mState = 0; // cached expected number of octets after the current octet
@@ -185,7 +163,17 @@ class HTMLPurifier_Encoder
                         ) {
                             
                         } elseif (0xFEFF != $mUcs4 && // omit BOM
-                            !($mUcs4 >= 128 && $mUcs4 <= 159) // omit non-SGML
+                            // check for valid Char unicode codepoints
+                            (
+                                0x9 == $mUcs4 ||
+                                0xA == $mUcs4 ||
+                                0xD == $mUcs4 ||
+                                (0x20 <= $mUcs4 && 0x7E >= $mUcs4) ||
+                                // 7F-9F is not strictly prohibited by XML,
+                                // but it is non-SGML, and thus we don't allow it
+                                (0xA0 <= $mUcs4 && 0xD7FF >= $mUcs4) ||
+                                (0x10000 <= $mUcs4 && 0x10FFFF >= $mUcs4)
+                            )
                         ) {
                             $out .= $char;
                         }
@@ -276,22 +264,31 @@ class HTMLPurifier_Encoder
      * Converts a string to UTF-8 based on configuration.
      */
     public static function convertToUTF8($str, $config, $context) {
-        static $iconv = null;
-        if ($iconv === null) $iconv = function_exists('iconv');
         $encoding = $config->get('Core', 'Encoding');
         if ($encoding === 'utf-8') return $str;
+        static $iconv = null;
+        if ($iconv === null) $iconv = function_exists('iconv');
+        set_error_handler(array('HTMLPurifier_Encoder', 'muteErrorHandler'));
         if ($iconv && !$config->get('Test', 'ForceNoIconv')) {
-            set_error_handler(array('HTMLPurifier_Encoder', 'muteErrorHandler'));
             $str = iconv($encoding, 'utf-8//IGNORE', $str);
+            if ($str === false) {
+                // $encoding is not a valid encoding
+                restore_error_handler();
+                trigger_error('Invalid encoding ' . $encoding, E_USER_ERROR);
+                return '';
+            }
+            // If the string is bjorked by Shift_JIS or a similar encoding
+            // that doesn't support all of ASCII, convert the naughty
+            // characters to their true byte-wise ASCII/UTF-8 equivalents.
+            $str = strtr($str, HTMLPurifier_Encoder::testEncodingSupportsASCII($encoding));
             restore_error_handler();
             return $str;
         } elseif ($encoding === 'iso-8859-1') {
-            set_error_handler(array('HTMLPurifier_Encoder', 'muteErrorHandler'));
             $str = utf8_encode($str);
             restore_error_handler();
             return $str;
         }
-        trigger_error('Encoding not supported', E_USER_ERROR);
+        trigger_error('Encoding not supported, please install iconv', E_USER_ERROR);
     }
     
     /**
@@ -300,20 +297,28 @@ class HTMLPurifier_Encoder
      *       characters being omitted.
      */
     public static function convertFromUTF8($str, $config, $context) {
-        static $iconv = null;
-        if ($iconv === null) $iconv = function_exists('iconv');
         $encoding = $config->get('Core', 'Encoding');
         if ($encoding === 'utf-8') return $str;
-        if ($config->get('Core', 'EscapeNonASCIICharacters')) {
+        static $iconv = null;
+        if ($iconv === null) $iconv = function_exists('iconv');
+        if ($escape = $config->get('Core', 'EscapeNonASCIICharacters')) {
             $str = HTMLPurifier_Encoder::convertToASCIIDumbLossless($str);
         }
+        set_error_handler(array('HTMLPurifier_Encoder', 'muteErrorHandler'));
         if ($iconv && !$config->get('Test', 'ForceNoIconv')) {
-            set_error_handler(array('HTMLPurifier_Encoder', 'muteErrorHandler'));
+            // Undo our previous fix in convertToUTF8, otherwise iconv will barf
+            $ascii_fix = HTMLPurifier_Encoder::testEncodingSupportsASCII($encoding);
+            if (!$escape && !empty($ascii_fix)) {
+                $clear_fix = array();
+                foreach ($ascii_fix as $utf8 => $native) $clear_fix[$utf8] = '';
+                $str = strtr($str, $clear_fix);
+            }
+            $str = strtr($str, array_flip($ascii_fix));
+            // Normal stuff
             $str = iconv('utf-8', $encoding . '//IGNORE', $str);
             restore_error_handler();
             return $str;
         } elseif ($encoding === 'iso-8859-1') {
-            set_error_handler(array('HTMLPurifier_Encoder', 'muteErrorHandler'));
             $str = utf8_decode($str);
             restore_error_handler();
             return $str;
@@ -368,6 +373,47 @@ class HTMLPurifier_Encoder
         return $result;
     }
     
+    /**
+     * This expensive function tests whether or not a given character
+     * encoding supports ASCII. 7/8-bit encodings like Shift_JIS will
+     * fail this test, and require special processing. Variable width
+     * encodings shouldn't ever fail.
+     * 
+     * @param string $encoding Encoding name to test, as per iconv format
+     * @param bool $bypass Whether or not to bypass the precompiled arrays.
+     * @return Array of UTF-8 characters to their corresponding ASCII,
+     *      which can be used to "undo" any overzealous iconv action.
+     */
+    public static function testEncodingSupportsASCII($encoding, $bypass = false) {
+        static $encodings = array();
+        if (!$bypass) {
+            if (isset($encodings[$encoding])) return $encodings[$encoding];
+            $lenc = strtolower($encoding);
+            switch ($lenc) {
+                case 'shift_jis':
+                    return array("\xC2\xA5" => '\\', "\xE2\x80\xBE" => '~');
+                case 'johab':
+                    return array("\xE2\x82\xA9" => '\\');
+            }
+            if (strpos($lenc, 'iso-8859-') === 0) return array();
+        }
+        $ret = array();
+        set_error_handler(array('HTMLPurifier_Encoder', 'muteErrorHandler'));
+        if (iconv('UTF-8', $encoding, 'a') === false) return false;
+        for ($i = 0x20; $i <= 0x7E; $i++) { // all printable ASCII chars
+            $c = chr($i);
+            if (iconv('UTF-8', "$encoding//IGNORE", $c) === '') {
+                // Reverse engineer: what's the UTF-8 equiv of this byte
+                // sequence? This assumes that there's no variable width
+                // encoding that doesn't support ASCII.
+                $ret[iconv($encoding, 'UTF-8//IGNORE', $c)] = $c;
+            }
+        }
+        restore_error_handler();
+        $encodings[$encoding] = $ret;
+        return $ret;
+    }
+    
     
 }
 

library/HTMLPurifier/ErrorCollector.php

@@ -7,22 +7,37 @@
 class HTMLPurifier_ErrorCollector
 {
     
-    protected $errors = array();
+    /**
+     * Identifiers for the returned error array. These are purposely numeric
+     * so list() can be used.
+     */
+    const LINENO   = 0;
+    const SEVERITY = 1;
+    const MESSAGE  = 2;
+    const CHILDREN = 3;
+    
+    protected $errors;
+    protected $_current;
+    protected $_stacks = array(array());
     protected $locale;
     protected $generator;
     protected $context;
     
+    protected $lines = array();
+    
     public function __construct($context) {
         $this->locale    =& $context->get('Locale');
-        $this->generator =& $context->get('Generator');
         $this->context   = $context;
+        $this->_current  =& $this->_stacks[0];
+        $this->errors    =& $this->_stacks[0];
     }
     
     /**
      * Sends an error message to the collector for later use
-     * @param $line Integer line number, or HTMLPurifier_Token that caused error
      * @param $severity int Error severity, PHP error style (don't use E_USER_)
      * @param $msg string Error message text
+     * @param $subst1 string First substitution for $msg
+     * @param $subst2 string ...
      */
     public function send($severity, $msg) {
         
@@ -35,6 +50,7 @@ class HTMLPurifier_ErrorCollector
         
         $token = $this->context->get('CurrentToken', true);
         $line  = $token ? $token->line : $this->context->get('CurrentLine', true);
+        $col   = $token ? $token->col  : $this->context->get('CurrentCol',  true);
         $attr  = $this->context->get('CurrentAttr', true);
         
         // perform special substitutions, also add custom parameters
@@ -55,13 +71,66 @@ class HTMLPurifier_ErrorCollector
         
         if (!empty($subst)) $msg = strtr($msg, $subst);
         
-        $this->errors[] = array($line, $severity, $msg);
+        // (numerically indexed)
+        $error = array(
+            self::LINENO   => $line,
+            self::SEVERITY => $severity,
+            self::MESSAGE  => $msg,
+            self::CHILDREN => array()
+        );
+        $this->_current[] = $error;
+        
+        
+        // NEW CODE BELOW ...
+        
+        $struct = null;
+        // Top-level errors are either:
+        //  TOKEN type, if $value is set appropriately, or
+        //  "syntax" type, if $value is null
+        $new_struct = new HTMLPurifier_ErrorStruct();
+        $new_struct->type = HTMLPurifier_ErrorStruct::TOKEN;
+        if ($token) $new_struct->value = clone $token;
+        if (is_int($line) && is_int($col)) {
+            if (isset($this->lines[$line][$col])) {
+                $struct = $this->lines[$line][$col];
+            } else {
+                $struct = $this->lines[$line][$col] = $new_struct;
+            }
+            // These ksorts may present a performance problem
+            ksort($this->lines[$line], SORT_NUMERIC);
+        } else {
+            if (isset($this->lines[-1])) {
+                $struct = $this->lines[-1];
+            } else {
+                $struct = $this->lines[-1] = $new_struct;
+            }
+        }
+        ksort($this->lines, SORT_NUMERIC);
+        
+        // Now, check if we need to operate on a lower structure
+        if (!empty($attr)) {
+            $struct = $struct->getChild(HTMLPurifier_ErrorStruct::ATTR, $attr);
+            if (!$struct->value) {
+                $struct->value = array($attr, 'PUT VALUE HERE');
+            }
+        }
+        if (!empty($cssprop)) {
+            $struct = $struct->getChild(HTMLPurifier_ErrorStruct::CSSPROP, $cssprop);
+            if (!$struct->value) {
+                // if we tokenize CSS this might be a little more difficult to do
+                $struct->value = array($cssprop, 'PUT VALUE HERE');
+            }
+        }
+        
+        // Ok, structs are all setup, now time to register the error
+        $struct->addError($severity, $msg);
     }
     
     /**
      * Retrieves raw error data for custom formatter to use
-     * @param List of arrays in format of array(Error message text,
+     * @param List of arrays in format of array(line of error,
-     *        token that caused error, tokens surrounding token)
+     *        error severity, error message,
+     *        recursive sub-errors array)
      */
     public function getRaw() {
         return $this->errors;
@@ -70,38 +139,25 @@ class HTMLPurifier_ErrorCollector
     /**
      * Default HTML formatting implementation for error messages
      * @param $config Configuration array, vital for HTML output nature
+     * @param $errors Errors array to display; used for recursion.
      */
-    public function getHTMLFormatted($config) {
+    public function getHTMLFormatted($config, $errors = null) {
         $ret = array();
         
-        $errors = $this->errors;
+        $this->generator = new HTMLPurifier_Generator($config, $this->context);
+        if ($errors === null) $errors = $this->errors;
         
-        // sort error array by line
+        // 'At line' message needs to be removed
-        // line numbers are enabled if they aren't explicitly disabled
+        
-        if ($config->get('Core', 'MaintainLineNumbers') !== false) {
+        // generation code for new structure goes here. It needs to be recursive.
-            $has_line       = array();
+        foreach ($this->lines as $line => $col_array) {
-            $lines          = array();
+            if ($line == -1) continue;
-            $original_order = array();
+            foreach ($col_array as $col => $struct) {
-            foreach ($errors as $i => $error) {
+                $this->_renderStruct($ret, $struct, $line, $col);
-                $has_line[] = (int) (bool) $error[0];
-                $lines[] = $error[0];
-                $original_order[] = $i;
             }
-            array_multisort($has_line, SORT_DESC, $lines, SORT_ASC, $original_order, SORT_ASC, $errors);
         }
-        
+        if (isset($this->lines[-1])) {
-        foreach ($errors as $error) {
+            $this->_renderStruct($ret, $this->lines[-1]);
-            list($line, $severity, $msg) = $error;
-            $string = '';
-            $string .= '<strong>' . $this->locale->getErrorName($severity) . '</strong>: ';
-            $string .= $this->generator->escape($msg); 
-            if ($line) {
-                // have javascript link generation that causes 
-                // textarea to skip to the specified line
-                $string .= $this->locale->formatMessage(
-                    'ErrorCollector: At line', array('line' => $line));
-            }
-            $ret[] = $string;
         }
         
         if (empty($errors)) {
@@ -112,5 +168,41 @@ class HTMLPurifier_ErrorCollector
         
     }
     
+    private function _renderStruct(&$ret, $struct, $line = null, $col = null) {
+        $stack = array($struct);
+        $context_stack = array(array());
+        while ($current = array_pop($stack)) {
+            $context = array_pop($context_stack);
+            foreach ($current->errors as $error) {
+                list($severity, $msg) = $error;
+                $string = '';
+                $string .= '<div>';
+                // W3C uses an icon to indicate the severity of the error.
+                $error = $this->locale->getErrorName($severity);
+                $string .= "<span class=\"error e$severity\"><strong>$error</strong></span> ";
+                if (!is_null($line) && !is_null($col)) {
+                    $string .= "<em class=\"location\">Line $line, Column $col: </em> ";
+                } else {
+                    $string .= '<em class="location">End of Document: </em> ';
+                }
+                $string .= '<strong class="description">' . $this->generator->escape($msg) . '</strong> ';
+                $string .= '</div>';
+                // Here, have a marker for the character on the column appropriate.
+                // Be sure to clip extremely long lines.
+                //$string .= '<pre>';
+                //$string .= '';
+                //$string .= '</pre>';
+                $ret[] = $string;
+            }
+            foreach ($current->children as $type => $array) {
+                $context[] = $current;
+                $stack = array_merge($stack, array_reverse($array, true));
+                for ($i = count($array); $i > 0; $i--) {
+                    $context_stack[] = $context;
+                }
+            }
+        }
+    }
+    
 }
 

library/HTMLPurifier/ErrorStruct.php

@@ -0,0 +1,58 @@
+<?php
+
+/**
+ * Records errors for particular segments of an HTML document such as tokens,
+ * attributes or CSS properties. They can contain error structs (which apply
+ * to components of what they represent), but their main purpose is to hold
+ * errors applying to whatever struct is being used.
+ */
+class HTMLPurifier_ErrorStruct
+{
+    
+    /**
+     * Possible values for $children first-key. Note that top-level structures
+     * are automatically token-level.
+     */
+    const TOKEN     = 0;
+    const ATTR      = 1;
+    const CSSPROP   = 2;
+    
+    /**
+     * Type of this struct.
+     */
+    public $type;
+    
+    /**
+     * Value of the struct we are recording errors for. There are various
+     * values for this:
+     *  - TOKEN: Instance of HTMLPurifier_Token
+     *  - ATTR: array('attr-name', 'value')
+     *  - CSSPROP: array('prop-name', 'value')
+     */
+    public $value;
+    
+    /**
+     * Errors registered for this structure.
+     */
+    public $errors = array();
+    
+    /**
+     * Child ErrorStructs that are from this structure. For example, a TOKEN
+     * ErrorStruct would contain ATTR ErrorStructs. This is a multi-dimensional
+     * array in structure: [TYPE]['identifier']
+     */
+    public $children = array();
+    
+    public function getChild($type, $id) {
+        if (!isset($this->children[$type][$id])) {
+            $this->children[$type][$id] = new HTMLPurifier_ErrorStruct();
+            $this->children[$type][$id]->type = $type;
+        }
+        return $this->children[$type][$id];
+    }
+    
+    public function addError($severity, $message) {
+        $this->errors[] = array($severity, $message);
+    }
+    
+}

library/HTMLPurifier/Generator.php

@@ -26,6 +26,11 @@ class HTMLPurifier_Generator
      */
     private $_def;
     
+    /**
+     * Cache of %Output.SortAttr
+     */
+    private $_sortAttr;
+    
     /**
      * Configuration for the generator
      */
@@ -35,10 +40,10 @@ class HTMLPurifier_Generator
      * @param $config Instance of HTMLPurifier_Config
      * @param $context Instance of HTMLPurifier_Context
      */
-    public function __construct($config = null, $context = null) {
+    public function __construct($config, $context) {
-        if (!$config) $config = HTMLPurifier_Config::createDefault();
         $this->config = $config;
         $this->_scriptFix = $config->get('Output', 'CommentScriptContents');
+        $this->_sortAttr = $config->get('Output', 'SortAttr');
         $this->_def = $config->getHTMLDefinition();
         $this->_xhtml = $this->_def->doctype->xml;
     }
@@ -143,6 +148,7 @@ class HTMLPurifier_Generator
      */
     public function generateAttributes($assoc_array_of_attributes, $element = false) {
         $html = '';
+        if ($this->_sortAttr) ksort($assoc_array_of_attributes);
         foreach ($assoc_array_of_attributes as $key => $value) {
             if (!$this->_xhtml) {
                 // Remove namespaced attributes

library/HTMLPurifier/HTMLDefinition.php

@@ -76,6 +76,11 @@ class HTMLPurifier_HTMLDefinition extends HTMLPurifier_Definition
      */
     public $info_content_sets = array();
     
+    /**
+     * Indexed list of HTMLPurifier_Injector to be used.
+     */
+    public $info_injector = array();
+    
     /**
      * Doctype object
      */
@@ -186,18 +191,22 @@ class HTMLPurifier_HTMLDefinition extends HTMLPurifier_Definition
         $this->doctype = $this->manager->doctype;
         
         foreach ($this->manager->modules as $module) {
-            foreach($module->info_tag_transform         as $k => $v) {
+            foreach($module->info_tag_transform as $k => $v) {
                 if ($v === false) unset($this->info_tag_transform[$k]);
                 else $this->info_tag_transform[$k] = $v;
             }
-            foreach($module->info_attr_transform_pre    as $k => $v) {
+            foreach($module->info_attr_transform_pre as $k => $v) {
                 if ($v === false) unset($this->info_attr_transform_pre[$k]);
                 else $this->info_attr_transform_pre[$k] = $v;
             }
-            foreach($module->info_attr_transform_post   as $k => $v) {
+            foreach($module->info_attr_transform_post as $k => $v) {
                 if ($v === false) unset($this->info_attr_transform_post[$k]);
                 else $this->info_attr_transform_post[$k] = $v;
             }
+            foreach ($module->info_injector as $k => $v) {
+                if ($v === false) unset($this->info_injector[$k]);
+                else $this->info_injector[$k] = $v;
+            }
         }
         
         $this->info = $this->manager->getElements();
@@ -356,6 +365,14 @@ class HTMLPurifier_HTMLDefinition extends HTMLPurifier_Definition
             }
         }
         
+        // setup injectors -----------------------------------------------------
+        foreach ($this->info_injector as $i => $injector) {
+            if ($injector->checkNeeded($config) !== false) {
+                // remove injector that does not have it's required
+                // elements/attributes present, and is thus not needed.
+                unset($this->info_injector[$i]);
+            }
+        }
     }
     
     /**

library/HTMLPurifier/HTMLModule.php

@@ -71,6 +71,14 @@ class HTMLPurifier_HTMLModule
      */
     public $info_attr_transform_post = array();
     
+    /**
+     * List of HTMLPurifier_Injector to be performed during well-formedness fixing.
+     * An injector will only be invoked if all of it's pre-requisites are met;
+     * if an injector fails setup, there will be no error; it will simply be
+     * silently disabled.
+     */
+    public $info_injector = array();
+    
     /**
      * Boolean flag that indicates whether or not getChildDef is implemented.
      * For optimization reasons: may save a call to a function. Be sure
@@ -222,5 +230,14 @@ class HTMLPurifier_HTMLModule
         }
         return $ret;
     }
+    
+    /**
+     * Lazy load construction of the module after determining whether
+     * or not it's needed, and also when a finalized configuration object
+     * is available.
+     * @param $config Instance of HTMLPurifier_Config
+     */
+    public function setup($config) {}
+    
 }
 

library/HTMLPurifier/HTMLModule/Bdo.php

@@ -12,7 +12,7 @@ class HTMLPurifier_HTMLModule_Bdo extends HTMLPurifier_HTMLModule
         'I18N' => array('dir' => false)
     );
     
-    public function __construct() {
+    public function setup($config) {
         $bdo = $this->addElement(
             'bdo', 'Inline', 'Inline', array('Core', 'Lang'),
             array(

library/HTMLPurifier/HTMLModule/Edit.php

@@ -9,7 +9,7 @@ class HTMLPurifier_HTMLModule_Edit extends HTMLPurifier_HTMLModule
     
     public $name = 'Edit';
     
-    public function __construct() {
+    public function setup($config) {
         $contents = 'Chameleon: #PCDATA | Inline ! #PCDATA | Flow';
         $attr = array(
             'cite' => 'URI',

library/HTMLPurifier/HTMLModule/Forms.php

@@ -0,0 +1,117 @@
+<?php
+
+/**
+ * XHTML 1.1 Forms module, defines all form-related elements found in HTML 4.
+ */
+class HTMLPurifier_HTMLModule_Forms extends HTMLPurifier_HTMLModule
+{
+    public $name = 'Forms';
+    public $safe = false;
+    
+    public $content_sets = array(
+        'Block' => 'Form',
+        'Inline' => 'Formctrl',
+    );
+    
+    public function setup($config) {
+        $form = $this->addElement('form', 'Form',
+          'Required: Heading | List | Block | fieldset', 'Common', array(
+            'accept' => 'ContentTypes',
+            'accept-charset' => 'Charsets',
+            'action*' => 'URI',
+            'method' => 'Enum#get,post',
+            // really ContentType, but these two are the only ones used today
+            'enctype' => 'Enum#application/x-www-form-urlencoded,multipart/form-data',
+        ));
+        $form->excludes = array('form' => true);
+        
+        $input = $this->addElement('input', 'Formctrl', 'Empty', 'Common', array(
+            'accept' => 'ContentTypes',
+            'accesskey' => 'Character',
+            'alt' => 'Text',
+            'checked' => 'Bool#checked',
+            'disabled' => 'Bool#disabled',
+            'maxlength' => 'Number',
+            'name' => 'CDATA',
+            'readonly' => 'Bool#readonly',
+            'size' => 'Number',
+            'src' => 'URI#embeds',
+            'tabindex' => 'Number',
+            'type' => 'Enum#text,password,checkbox,button,radio,submit,reset,file,hidden,image',
+            'value' => 'CDATA',
+        ));
+        $input->attr_transform_post[] = new HTMLPurifier_AttrTransform_Input();
+        
+        $this->addElement('select', 'Formctrl', 'Required: optgroup | option', 'Common', array(
+            'disabled' => 'Bool#disabled',
+            'multiple' => 'Bool#multiple',
+            'name' => 'CDATA',
+            'size' => 'Number',
+            'tabindex' => 'Number',
+        ));
+        
+        $this->addElement('option', false, 'Optional: #PCDATA', 'Common', array(
+            'disabled' => 'Bool#disabled',
+            'label' => 'Text',
+            'selected' => 'Bool#selected',
+            'value' => 'CDATA',
+        ));
+        // It's illegal for there to be more than one selected, but not
+        // be multiple. Also, no selected means undefined behavior. This might
+        // be difficult to implement; perhaps an injector, or a context variable.
+        
+        $textarea = $this->addElement('textarea', 'Formctrl', 'Optional: #PCDATA', 'Common', array(
+            'accesskey' => 'Character',
+            'cols*' => 'Number',
+            'disabled' => 'Bool#disabled',
+            'name' => 'CDATA',
+            'readonly' => 'Bool#readonly',
+            'rows*' => 'Number',
+            'tabindex' => 'Number',
+        ));
+        $textarea->attr_transform_pre[] = new HTMLPurifier_AttrTransform_Textarea();
+        
+        $button = $this->addElement('button', 'Formctrl', 'Optional: #PCDATA | Heading | List | Block | Inline', 'Common', array(
+            'accesskey' => 'Character',
+            'disabled' => 'Bool#disabled',
+            'name' => 'CDATA',
+            'tabindex' => 'Number',
+            'type' => 'Enum#button,submit,reset',
+            'value' => 'CDATA',
+        ));
+        
+        // For exclusions, ideally we'd specify content sets, not literal elements
+        $button->excludes = $this->makeLookup(
+            'form', 'fieldset', // Form
+            'input', 'select', 'textarea', 'label', 'button', // Formctrl
+            'a' // as per HTML 4.01 spec, this is omitted by modularization
+        );
+        
+        // Extra exclusion: img usemap="" is not permitted within this element.
+        // We'll omit this for now, since we don't have any good way of
+        // indicating it yet.
+        
+        // This is HIGHLY user-unfriendly; we need a custom child-def for this
+        $this->addElement('fieldset', 'Form', 'Custom: (#WS?,legend,(Flow|#PCDATA)*)', 'Common');
+        
+        $label = $this->addElement('label', 'Formctrl', 'Optional: #PCDATA | Inline', 'Common', array(
+            'accesskey' => 'Character',
+            // 'for' => 'IDREF', // IDREF not implemented, cannot allow
+        ));
+        $label->excludes = array('label' => true);
+        
+        $this->addElement('legend', false, 'Optional: #PCDATA | Inline', 'Common', array(
+            'accesskey' => 'Character',
+        ));
+        
+        $this->addElement('optgroup', false, 'Required: option', 'Common', array(
+            'disabled' => 'Bool#disabled',
+            'label*' => 'Text',
+        ));
+        
+        // Don't forget an injector for <isindex>. This one's a little complex
+        // because it maps to multiple elements.
+        
+    }
+}
+

library/HTMLPurifier/HTMLModule/Hypertext.php

@@ -8,7 +8,7 @@ class HTMLPurifier_HTMLModule_Hypertext extends HTMLPurifier_HTMLModule
     
     public $name = 'Hypertext';
     
-    public function __construct() {
+    public function setup($config) {
         $a = $this->addElement(
             'a', 'Inline', 'Inline', 'Common',
             array(

library/HTMLPurifier/HTMLModule/Image.php

@@ -10,17 +10,25 @@ class HTMLPurifier_HTMLModule_Image extends HTMLPurifier_HTMLModule
     
     public $name = 'Image';
     
-    public function __construct() {
+    public function setup($config) {
+        $max = $config->get('HTML', 'MaxImgLength');
         $img = $this->addElement(
             'img', 'Inline', 'Empty', 'Common',
             array(
                 'alt*' => 'Text',
-                'height' => 'Length',
+                // According to the spec, it's Length, but percents can
+                // be abused, so we allow only Pixels.
+                'height' => 'Pixels#' . $max,
+                'width'  => 'Pixels#' . $max,
                 'longdesc' => 'URI', 
                 'src*' => new HTMLPurifier_AttrDef_URI(true), // embedded
-                'width' => 'Length'
             )
         );
+        if ($max === null || $config->get('HTML', 'Trusted')) {
+            $img->attr['height'] =
+            $img->attr['width'] = 'Length';
+        }
+        
         // kind of strange, but splitting things up would be inefficient
         $img->attr_transform_pre[] =
         $img->attr_transform_post[] =

library/HTMLPurifier/HTMLModule/Legacy.php

@@ -21,7 +21,7 @@ class HTMLPurifier_HTMLModule_Legacy extends HTMLPurifier_HTMLModule
     
     public $name = 'Legacy';
     
-    public function __construct() {
+    public function setup($config) {
         
         $this->addElement('basefont', 'Inline', 'Empty', false, array(
             'color' => 'Color',

library/HTMLPurifier/HTMLModule/List.php

@@ -19,7 +19,7 @@ class HTMLPurifier_HTMLModule_List extends HTMLPurifier_HTMLModule
     
     public $content_sets = array('Flow' => 'List');
     
-    public function __construct() {
+    public function setup($config) {
         $this->addElement('ol', 'List', 'Required: li', 'Common');
         $this->addElement('ul', 'List', 'Required: li', 'Common');
         $this->addElement('dl', 'List', 'Required: dt | dd', 'Common');

library/HTMLPurifier/HTMLModule/Name.php

@@ -0,0 +1,16 @@
+<?php
+
+class HTMLPurifier_HTMLModule_Name extends HTMLPurifier_HTMLModule
+{
+    
+    public $name = 'Name';
+    
+    public function setup($config) {
+        $elements = array('a', 'applet', 'form', 'frame', 'iframe', 'img', 'map');
+        foreach ($elements as $name) {
+            $element = $this->addBlankElement($name);
+            $element->attr['name'] = 'ID';
+        }
+    }
+    
+}

library/HTMLPurifier/HTMLModule/Object.php

@@ -11,7 +11,7 @@ class HTMLPurifier_HTMLModule_Object extends HTMLPurifier_HTMLModule
     public $name = 'Object';
     public $safe = false;
     
-    public function __construct() {
+    public function setup($config) {
         
         $this->addElement('object', 'Inline', 'Optional: #PCDATA | Flow | param', 'Common', 
             array(

library/HTMLPurifier/HTMLModule/Presentation.php

@@ -15,7 +15,7 @@ class HTMLPurifier_HTMLModule_Presentation extends HTMLPurifier_HTMLModule
     
     public $name = 'Presentation';
     
-    public function __construct() {
+    public function setup($config) {
         $this->addElement('b',      'Inline', 'Inline', 'Common');
         $this->addElement('big',    'Inline', 'Inline', 'Common');
         $this->addElement('hr',     'Block',  'Empty',  'Common');

library/HTMLPurifier/HTMLModule/Proprietary.php

@@ -9,7 +9,7 @@ class HTMLPurifier_HTMLModule_Proprietary extends HTMLPurifier_HTMLModule
     
     public $name = 'Proprietary';
     
-    public function __construct() {
+    public function setup($config) {
         
         $this->addElement('marquee', 'Inline', 'Flow', 'Common', 
             array(

library/HTMLPurifier/HTMLModule/Ruby.php

@@ -9,7 +9,7 @@ class HTMLPurifier_HTMLModule_Ruby extends HTMLPurifier_HTMLModule
     
     public $name = 'Ruby';
     
-    public function __construct() {
+    public function setup($config) {
         $this->addElement('ruby', 'Inline',
             'Custom: ((rb, (rt | (rp, rt, rp))) | (rbc, rtc, rtc?))',
             'Common');

library/HTMLPurifier/HTMLModule/SafeEmbed.php

@@ -0,0 +1,31 @@
+<?php
+
+/**
+ * A "safe" embed module. See SafeObject. This is a proprietary element.
+ */
+class HTMLPurifier_HTMLModule_SafeEmbed extends HTMLPurifier_HTMLModule
+{
+    
+    public $name = 'SafeEmbed';
+    
+    public function setup($config) {
+        
+        $max = $config->get('HTML', 'MaxImgLength');
+        $embed = $this->addElement(
+            'embed', 'Inline', 'Empty', 'Common',
+            array(
+                'src*' => 'URI#embedded',
+                'type' => 'Enum#application/x-shockwave-flash',
+                'width' => 'Pixels#' . $max,
+                'height' => 'Pixels#' . $max,
+                'allowscriptaccess' => 'Enum#never',
+                'allownetworking' => 'Enum#internal',
+                'wmode' => 'Enum#window',
+                'name' => 'ID',
+            )
+        );
+        $embed->attr_transform_post[] = new HTMLPurifier_AttrTransform_SafeEmbed();
+        
+    }
+    
+}

library/HTMLPurifier/HTMLModule/SafeObject.php

@@ -0,0 +1,48 @@
+<?php
+
+/**
+ * A "safe" object module. In theory, objects permitted by this module will
+ * be safe, and untrusted users can be allowed to embed arbitrary flash objects
+ * (maybe other types too, but only Flash is supported as of right now).
+ * Highly experimental.
+ */
+class HTMLPurifier_HTMLModule_SafeObject extends HTMLPurifier_HTMLModule
+{
+    
+    public $name = 'SafeObject';
+    
+    public function setup($config) {
+        
+        // These definitions are not intrinsically safe: the attribute transforms
+        // are a vital part of ensuring safety.
+        
+        $max = $config->get('HTML', 'MaxImgLength');
+        $object = $this->addElement(
+            'object',
+            'Inline',
+            'Optional: param | Flow | #PCDATA',
+            'Common',
+            array(
+                // While technically not required by the spec, we're forcing
+                // it to this value.
+                'type'   => 'Enum#application/x-shockwave-flash',
+                'width'  => 'Pixels#' . $max,
+                'height' => 'Pixels#' . $max,
+                'data'   => 'URI#embedded'
+            )
+        );
+        $object->attr_transform_post[] = new HTMLPurifier_AttrTransform_SafeObject();
+
+        $param = $this->addElement('param', false, 'Empty', false,
+            array(
+                'id' => 'ID',
+                'name*' => 'Text', 
+                'value' => 'Text'
+            )
+        );
+        $param->attr_transform_post[] = new HTMLPurifier_AttrTransform_SafeParam();
+        $this->info_injector[] = 'SafeObject';
+    
+    }
+    
+}