Release 2.1.3, merged in 1404 to HEAD.

git-svn-id: http://htmlpurifier.org/svnroot/htmlpurifier/branches/strict@1444 48356398-32a2-884e-a903-53898d9a118a
Release 2.1.2, merged in 1368 to HEAD.
2025-08-03 12:47:56 +02:00 · 2007-11-06 04:34:33 +00:00 · 2007-09-03 15:40:43 +00:00 · 2007-08-05 02:02:46 +00:00 · 2007-08-05 01:42:52 +00:00
144 changed files with 14338 additions and 2105 deletions
--- a/1100
+++ b/1100
--- a/219
+++ b/219
@@ -1,64 +1,56 @@
+
 Install
    How to install HTML Purifier

-HTML Purifier is designed to run out of the box,  so actually using the library
-is extremely easy. (Although, if you were looking for a step-by-step
-installation GUI, you've come to the wrong place!)  The impatient can scroll
-down to the bottom of this INSTALL document to see the code, but you really
-should make sure a few things are properly done.
-
-
+HTML Purifier is designed to run out of the box, so actually using the 
+library is extremely easy.  (Although... if you were looking for a 
+step-by-step installation GUI, you've downloaded the wrong software!)
+
+While the impatient can get going immediately with some of the sample
+code at the bottom of this library, it's well worth performing some
+basic sanity checks to get the most out of this library.


+---------------------------------------------------------------------------
 1.  Compatibility

-HTML Purifier works in both PHP 4 and PHP 5, from PHP 4.3.2 and up. It has no
-core dependencies with other libraries.
+HTML Purifier works in both PHP 4 and PHP 5, and is actively tested from 
+PHP 4.3.7 and up (see tests/multitest.php for specific versions). It has 
+no core dependencies with other libraries. PHP 4 support will be 
+deprecated on December 31, 2007, at which time only essential security 
+fixes will be issued for the PHP 4 version until August 8, 2008. 

-Optional extensions are iconv (usually installed) and tidy (also common).
-If you use UTF-8 and don't plan on pretty-printing HTML, you can get away with
-not having either of these extensions.
+These optional extensions can enhance the capabilities of HTML Purifier:
+
+    * iconv : Converts text to and from non-UTF-8 encodings
+    * tidy  : Used for pretty-printing HTML


+---------------------------------------------------------------------------
+2.  Reconnaissance

-2.  Including the library
+A big plus of HTML Purifier is its inerrant support of standards, so
+your web-pages should be standards-compliant.  (They should also use
+semantic markup, but that's another issue altogether, one HTML Purifier
+cannot fix without reading your mind.)

-Simply use:
-
-    require_once '/path/to/library/HTMLPurifier.auto.php';
-
-...and you're good to go.  Since HTML Purifier's codebase is fairly
-large, I recommend only including HTML Purifier when you need it.
-
-If you don't like your include_path to be fiddled around with, simply set
-HTML Purifier's library/ directory to the include path yourself and then:
-
-    require_once 'HTMLPurifier.php';
-
-Only the contents in the library/ folder are necessary, so you can remove
-everything else when using HTML Purifier in a production environment.  
-
-
-
-3.  Preparing the proper output environment
-
-HTML Purifier is all about web-standards, so accordingly your webpages should
-be standards compliant.  HTML Purifier can deal with these doctypes:
+HTML Purifier can process these doctypes:

 * XHTML 1.0 Transitional (default)
 * XHTML 1.0 Strict
 * HTML 4.01 Transitional
 * HTML 4.01 Strict
-* XHTML 1.1 (sans Ruby)
+* XHTML 1.1

 ...and these character encodings:

 * UTF-8 (default)
-* Any encoding iconv supports (support is crippled for i18n though)
+* Any encoding iconv supports (with crippled internationalization support)

-The defaults are there for a reason: they are best-practice choices that
-should not be changed lightly.  For those of you in the dark, you can determine
-the doctype from this code in your HTML documents:
+These defaults reflect what my choices where be if I were authoring an
+HTML document, however, what you choose depends on the nature of your
+codebase.  If you don't know what doctype you are using, you can determine
+the doctype from this identifier at the top of your source code:

    <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"
        "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
@@ -67,18 +59,34 @@ the doctype from this code in your HTML documents:

    <meta http-equiv="Content-type" content="text/html;charset=ENCODING">

-For legacy codebases these declarations may be missing.  If that is the case,
-STOP, and read docs/enduser-utf8.html
+If the character encoding declaration is missing, STOP NOW, and
+read 'docs/enduser-utf8.html' (web accessible at
+http://htmlpurifier.org/docs/enduser-utf8.html).  In fact, even if it is
+present, read this document anyway, as most websites specify character
+encoding incorrectly.


+---------------------------------------------------------------------------
+3.  Including the library
+
+The procedure is quite simple:
+
+    require_once '/path/to/library/HTMLPurifier.auto.php';
+
+I recommend only including HTML Purifier when you need it, because that
+call represents the inclusion of a lot of PHP files which constitute
+the bulk of HTML Purifier's memory usage.
+
+If you don't like your include_path to be fiddled around with, simply set
+HTML Purifier's library/ directory to the include path yourself and then:
+
+    require_once 'HTMLPurifier.php';
+
+Only the contents in the library/ folder are necessary, so you can remove
+everything else when using HTML Purifier in a production environment. 


-
-You may currently be vulnerable to XSS and other security threats, and HTML
-Purifier won't be able to fix that.
-
-
-
+---------------------------------------------------------------------------
 4. Configuration

 HTML Purifier is designed to run out-of-the-box, but occasionally HTML
@@ -95,7 +103,6 @@ object and read on:
    $config = HTMLPurifier_Config::createDefault();


-
 4.1. Setting a different character encoding

 You really shouldn't use any other encoding except UTF-8, especially if you
@@ -122,10 +129,6 @@ but please be cognizant of the issues the "solution" creates (for this
 reason, I do not include the solution in this document).


-
-
-
-
 4.2. Setting a different doctype

 For those of you using HTML 4.01 Transitional, you can disable
@@ -135,7 +138,6 @@ XHTML output like this:

 Other supported doctypes include:

-
    * HTML 4.01 Strict
    * HTML 4.01 Transitional
    * XHTML 1.0 Strict
@@ -143,7 +145,6 @@ Other supported doctypes include:
    * XHTML 1.1


-
 4.3. Other settings

 There are more configuration directives which can be read about
@@ -153,55 +154,24 @@ your code.  Some of the more interesting ones are configurable at the
 demo <http://htmlpurifier.org/demo.php> and are well worth looking into
 for your own system.

+For example, you can fine tune allowed elements and attributes, convert
+relative URLs to absolute ones, and even autoparagraph input text! These
+are, respectively, %HTML.Allowed, %URI.MakeAbsolute and %URI.Base, and
+%AutoFormat.AutoParagraph. The %Namespace.Directive naming convention
+translates to:
+
+    $config->set('Namespace', 'Directive', $value);
+
+E.g.
+
+    $config->set('HTML', 'Allowed', 'p,b,a[href],i');
+    $config->set('URI', 'Base', 'http://www.example.com');
+    $config->set('URI', 'MakeAbsolute', true);
+    $config->set('AutoFormat', 'AutoParagraph', true);


-5.   Using the code
-
-The interface is mind-numbingly simple:
-
-    $purifier = new HTMLPurifier();
-    $clean_html = $purifier->purify( $dirty_html );
-
-...or, if you're using the configuration object:
-
-    $purifier = new HTMLPurifier($config);
-    $clean_html = $purifier->purify( $dirty_html );
-
-That's it!  For more examples, check out docs/examples/ (they aren't very
-different though).  Also, docs/enduser-slow.html gives advice on what to
-do if HTML Purifier is slowing down your application.
-
-
-
-6.   Quick install
-
-First, make sure library/HTMLPurifier/DefinitionCache/Serializer is
-writable by the webserver (see Section 7: Caching below for details).
-If your website is in UTF-8 and XHTML Transitional, use this code:
-
-<?php
-    require_once '/path/to/htmlpurifier/library/HTMLPurifier.auto.php';
-    
-    $purifier = new HTMLPurifier();
-    $clean_html = $purifier->purify($dirty_html);
-?>
-
-If your website is in a different encoding or doctype, use this code:
-
-<?php
-    require_once '/path/to/htmlpurifier/library/HTMLPurifier.auto.php';
-    
-    $config = HTMLPurifier_Config::createDefault();
-    $config->set('Core', 'Encoding', 'ISO-8859-1'); // replace with your encoding
-    $config->set('HTML', 'Doctype', 'HTML 4.01 Transitional'); // replace with your doctype
-    $purifier = new HTMLPurifier($config);
-    
-    $clean_html = $purifier->purify($dirty_html);
-?>
-
-
-
-7. Caching
+---------------------------------------------------------------------------
+5. Caching

 HTML Purifier generates some cache files (generally one or two) to speed up
 its execution. For maximum performance, make sure that
@@ -236,3 +206,50 @@ hit):
 Or move the cache directory somewhere else (no trailing slash):

    $config->set('Cache', 'SerializerPath', '/home/user/absolute/path');
+
+
+---------------------------------------------------------------------------
+6.   Using the code
+
+The interface is mind-numbingly simple:
+
+    $purifier = new HTMLPurifier();
+    $clean_html = $purifier->purify( $dirty_html );
+
+...or, if you're using the configuration object:
+
+    $purifier = new HTMLPurifier($config);
+    $clean_html = $purifier->purify( $dirty_html );
+
+That's it!  For more examples, check out docs/examples/ (they aren't very
+different though).  Also, docs/enduser-slow.html gives advice on what to
+do if HTML Purifier is slowing down your application.
+
+
+---------------------------------------------------------------------------
+7.   Quick install
+
+First, make sure library/HTMLPurifier/DefinitionCache/Serializer is
+writable by the webserver (see Section 5: Caching above for details).
+If your website is in UTF-8 and XHTML Transitional, use this code:
+
+<?php
+    require_once '/path/to/htmlpurifier/library/HTMLPurifier.auto.php';
+    
+    $purifier = new HTMLPurifier();
+    $clean_html = $purifier->purify($dirty_html);
+?>
+
+If your website is in a different encoding or doctype, use this code:
+
+<?php
+    require_once '/path/to/htmlpurifier/library/HTMLPurifier.auto.php';
+    
+    $config = HTMLPurifier_Config::createDefault();
+    $config->set('Core', 'Encoding', 'ISO-8859-1'); // replace with your encoding
+    $config->set('HTML', 'Doctype', 'HTML 4.01 Transitional'); // replace with your doctype
+    $purifier = new HTMLPurifier($config);
+    
+    $clean_html = $purifier->purify($dirty_html);
+?>
+
--- a/139
+++ b/139
@@ -9,6 +9,145 @@ NEWS ( CHANGELOG and HISTORY )                                     HTMLPurifier
    . Internal change
 ==========================

+2.1.3, released 2007-11-05
+! tests/multitest.php allows you to test multiple versions by running
+  tests/index.php through multiple interpreters using `phpv` shell
+  script (you must provide this script!)
+- Fixed poor include ordering for Email URI AttrDefs, causes fatal errors
+  on some systems.
+- Injector algorithm further refined: off-by-one error regarding skip 
+  counts for dormant injectors fixed
+- Corrective blockquote definition now enabled for HTML 4.01 Strict
+- Fatal error when <img> tag (or any other element with required attributes)
+  has 'id' attribute fixed, thanks NykO18 for reporting
+- Fix warning emitted when a non-supported URI scheme is passed to the
+  MakeAbsolute URIFilter, thanks NykO18 (again)
+- Further refine AutoParagraph injector. Behavior inside of elements
+  allowing paragraph tags clarified: only inline content delimeted by
+  double newlines (not block elements) are paragraphed.
+- Buggy treatment of end tags of elements that have required attributes
+  fixed (does not manifest on default tag-set)
+- Spurious internal content reorganization error suppressed
+- HTMLDefinition->addElement now returns a reference to the created
+  element object, as implied by the documentation
+- Phorum mod's HTML Purifier help message expanded (unreleased elsewhere)
+- Fix a theoretical class of infinite loops from DirectLex reported
+  by Nate Abele
+- Work around unnecessary DOMElement type-cast in PH5P that caused errors
+  in PHP 5.1
+- Work around PHP 4 SimpleTest lack-of-error complaining for one-time-only
+  HTMLDefinition errors, this may indicate problems with error-collecting
+  facilities in PHP 5
+- Make ErrorCollectorEMock work in both PHP 4 and PHP 5
+- Make PH5P work with PHP 5.0 by removing unnecessary array parameter typedef
+. %Core.AcceptFullDocuments renamed to %Core.ConvertDocumentToFragment 
+  to better communicate its purpose
+. Error unit tests can now specify the expectation of no errors. Future
+  iterations of the harness will be extremely strict about what errors
+  are allowed
+. Extend Injector hooks to allow for more powerful injector routines
+. HTMLDefinition->addBlankElement created, as according to the HTMLModule
+  method
+. Doxygen configuration file updated, with minor improvements
+. Test runner now checks for similarly named files in conf/ directory too.
+. Minor cosmetic change to flush-definition-cache.php: trailing newline is
+  outputted
+. Maintenance script for generating PH5P patch added, original PH5P source
+  file also added under version control
+. Full unit test runner script title made more descriptive with PHP version
+. Updated INSTALL file to state that 4.3.7 is the earliest version we
+  are actively testing
+
+2.1.2, released 2007-09-03
+! Implemented Object module for trusted users
+! Implemented experimental HTML5 parsing mode using PH5P. To use, add
+  this to your code:
+        require_once 'HTMLPurifier/Lexer/PH5P.php';
+        $config->set('Core', 'LexerImpl', 'PH5P');
+  Note that this Lexer introduces some classes not in the HTMLPurifier
+  namespace.  Also, this is PHP5 only.
+! CSS property border-spacing implemented
+- Fix non-visible parsing error in DirectLex with empty tags that have
+  slashes inside attribute values.
+- Fix typo in CSS definition: border-collapse:seperate; was incorrectly
+  accepted as valid CSS. Usually non-visible, because this styling is the
+  default for tables in most browsers. Thanks Brett Zamir for pointing
+  this out.
+- Fix validation errors in configuration form
+- Hammer out a bunch of edge-case bugs in the standalone distribution
+- Inclusion reflection removed from URISchemeRegistry; you must manually
+  include any new schema files you wish to use
+- Numerous typo fixes in documentation thanks to Brett Zamir
+. Unit test refactoring for one logical test per test function
+. Config and context parameters in ComplexHarness deprecated: instead, edit
+  the $config and $context member variables
+. HTML wrapper in DOMLex now takes DTD identifiers into account; doesn't
+  really make a difference, but is good for completeness sake
+. merge-library.php script refactored for greater code reusability and
+  PHP4 compatibility
+
+2.1.1, released 2007-08-04
+- Fix show-stopper bug in %URI.MakeAbsolute functionality
+- Fix PHP4 syntax error in standalone version
+. Add prefix directory to include path for standalone, this prevents
+  other installations from clobbering the standalone's URI schemes
+. Single test methods can be invoked by prefixing with __only
+
+2.1.0, released 2007-08-02
+# flush-htmldefinition-cache.php superseded in favor of a generic
+  flush-definition-cache.php script, you can clear a specific cache
+  by passing its name as a parameter to the script
+! Phorum mod implemented for HTML Purifier
+! With %Core.AggressivelyFixLt, <3 and similar emoticons no longer
+  trigger HTML removal in PHP5 (DOMLex). This directive is not necessary
+  for PHP4 (DirectLex).
+! Standalone file now available, which greatly reduces the amount of
+  includes (although there are still a few files that reside in the
+  standalone folder)
+! Relative URIs can now be transformed into their absolute equivalents
+  using %URI.Base and %URI.MakeAbsolute
+! Ruby implemented for XHTML 1.1
+! You can now define custom URI filtering behavior, see enduser-uri-filter.html
+  for more details
+! UTF-8 font names now supported in CSS
+- AutoFormatters emit friendly error messages if tags or attributes they
+  need are not allowed
+- ConfigForm's compactification of directive names is now configurable
+- AutoParagraph autoformatter algorithm refined after field-testing
+- XHTML 1.1 now applies XHTML 1.0 Strict cleanup routines, namely
+  blockquote wrapping
+- Contents of <style> tags removed by default when tags are removed
+. HTMLPurifier_Config->getSerial() implemented, this is extremely useful
+  for output cache invalidation
+. ConfigForm printer now can retrieve CSS and JS files as strings, in
+  case HTML Purifier's directory is not publically accessible
+. Introduce new text/itext configuration directive values: these represent
+  longer strings that would be more appropriately edited with a textarea
+. Allow newlines to act as separators for lists, hashes, lookups and
+  %HTML.Allowed
+. ConfigForm generates textareas instead of text inputs for lists, hashes,
+  lookups, text and itext fields
+. Hidden element content removal genericized: %Core.HiddenElements can
+  be used to customize this behavior, by default <script> and <style> are
+  hidden
+. Added HTMLPURIFIER_PREFIX constant, should be used instead of dirname(__FILE__)
+. Custom ChildDef added to default include list
+. URIScheme reflection improved: will not attempt to include file if class
+  already exists. May clobber autoload, so I need to keep an eye on it
+. ConfigSchema heavily optimized, will only collect information and validate
+  definitions when HTMLPURIFIER_SCHEMA_STRICT is true.
+. AttrDef_URI unit tests and implementation refactored
+. benchmarks/ directory now protected from public view with .htaccess file;
+  run the tests via command line
+. URI scheme is munged off if there is no authority and the scheme is the
+  default one
+. All unit tests inherit from HTMLPurifier_Harness, not UnitTestCase
+. Interface for URIScheme changed
+. Generic URI object to hold components of URI added, most systems involved
+  in URI validation have been migrated to use it
+. Custom filtering for URIs factored out to URIDefinition interface for
+  maximum extensibility
+
 2.0.1, released 2007-06-27
 ! Tag auto-closing now based on a ChildDef heuristic rather than a
  manually set auto_close array; some behavior may change
--- a/36
+++ b/36
@@ -6,14 +6,9 @@ TODO List
    ? Maybe I'll Do It
 ==========================

-2.1 release [Refactor, refactor!]
- # URI validation routines tighter (see docs/dev-code-quality.html) (COMPLEX)
- # Advanced URI filtering schemes (see docs/proposal-new-directives.txt)
- # Ruby support
- - Configuration profiles: predefined directives set with one func call
- - Implement IDREF support (harder than it seems, since you cannot have
-   IDREFs to non-existent IDs)
- - Allow non-ASCII characters in font names
+If no interest is expressed for a feature that may required a considerable
+amount of effort to implement, it may get endlessly delayed. Do not be
+afraid to cast your vote for the next feature to be implemented!

 2.2 release [Error'ed]
 # Error logging for filtering/cleanup procedures
@@ -33,21 +28,22 @@ TODO List
 - 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

 2.4 release [It's All About Trust] (floating)
 # Implement untrusted, dangerous elements/attributes
+ # Implement IDREF support (harder than it seems, since you cannot have
+   IDREFs to non-existent IDs)
+ # Frameset XHTML 1.0 and HTML 4.01 doctypes

 3.0 release [Beyond HTML]
 # Legit token based CSS parsing (will require revamping almost every
-   AttrDef class)
+   AttrDef class). Probably will use CSSTidy class
 # More control over allowed CSS properties (maybe modularize it in the
   same fashion!)
 # Formatters for plaintext
    - Smileys
 - Standardize token armor for all areas of processing
- - Fixes for Firefox's inability to handle COL alignment props (Bug 915)
- - Automatically add non-breaking spaces to empty table cells when
-   empty-cells:show is applied to have compatibility with Internet Explorer
 - Convert RTL/LTR override characters to <bdo> tags, or vice versa on demand.
   Also, enable disabling of directionality

@@ -60,31 +56,33 @@ TODO List
 Ongoing
 - Lots of profiling, make it faster!
 - Plugins for major CMSes (COMPLEX)
-    - WordPress (mostly written, needs beta-testing)
    - phpBB
-    - Phorum
    - eFiction
    - more! (look for ones that use WYSIWYGs)
 - Complete basic smoketests

 Unknown release (on a scratch-an-itch basis)
- ? Semi-lossy dumb alternate character encoding transfor
+ # CHMOD install script for PEAR installs
 ? Have 'lang' attribute be checked against official lists, achieved by
   encoding all characters that have string entity equivalents
- - Explain how to use HTML Purifier in non-PHP languages / create
-   a simple command line stub
 - Abstract ChildDef_BlockQuote to work with all elements that only
   allow blocks in them, required or optional
 - Reorganize Unit Tests
-    - Refactor loop tests (esp. AttrDef_URI)
 - Reorganize configuration directives (Create more namespaces! Get messy!)
+ - Advanced URI filtering schemes (see docs/proposal-new-directives.txt)
+ - Implement lenient <ruby> child validation
+ - Explain how to use HTML Purifier in non-PHP languages / create
+   a simple command line stub (or complicated?)
+ - Fixes for Firefox's inability to handle COL alignment props (Bug 915)
+ - Automatically add non-breaking spaces to empty table cells when
+   empty-cells:show is applied to have compatibility with Internet Explorer

 Requested

 Wontfix
 - Non-lossy smart alternate character encoding transformations (unless
   patch provided)
- - Pretty-printing HTML, users can use Tidy on the output on entire page
+ - Pretty-printing HTML: users can use Tidy on the output on entire page
 - Native content compression, whitespace stripping (don't rely on Tidy, make
   sure we don't remove from <pre> or related tags): use gzip if this is
   really important
--- a/2
+++ b/2
@@ -1 +1 @@
-2.1.0
+2.1.3
--- a/14
+++ b/14
@@ -1,8 +1,6 @@
-In version 2.1, HTML Purifier's URI validation and filtering handling
-system has been revamped with a new, extensible URIFilter system. Also
-notable features include preservation of emoticons in PHP5 with
-%Core.AggressivelyFixLt, standalone and lite download versions,
-transforming relative URIs to absolute URIs, Ruby in XHTML 1.1, a Phorum
-mod, and UTF-8 font names.  Notable bug-fixes include refinement of
-the auto-paragraphing algorithm (no longer experimental), better XHTML
-1.1 support and the removal of the contents of <style> elements.
+Stability release 2.1.3 fixes a slew of minor bugs found in HTML Purifier,
+and also includes some internal code enhancements and refactorings.
+Notably, tests/multitest.php automates testing in multiple versions, 
+fatal AttrDef_URI_Email error fixed, blockquote contents are more lenient
+in HTML 4.01 Strict and fatal errors involving ID tags in img tags were
+fixed.
--- a/benchmarks/.htaccess
+++ b/benchmarks/.htaccess
@@ -0,0 +1 @@
+Deny from all
--- a/benchmarks/Trace.php
+++ b/benchmarks/Trace.php
@@ -0,0 +1,12 @@
+<?php
+
+ini_set('xdebug.trace_format', 1);
+ini_set('xdebug.show_mem_delta', true);
+
+xdebug_start_trace(dirname(__FILE__) . '/Trace');
+require_once '../library/HTMLPurifier.auto.php';
+
+$purifier = new HTMLPurifier();
+
+$data = $purifier->purify(file_get_contents('samples/Lexer/4.html'));
+xdebug_stop_trace();
--- a/docs/dev-progress.html
+++ b/docs/dev-progress.html
@@ -39,7 +39,7 @@ thead th {text-align:left;padding:0.1em;background-color:#EEE;}
 <table cellspacing="0"><tbody>
 <tr><td class="impl-yes">Implemented</td></tr>
 <tr><td class="impl-partial">Partially implemented</td></tr>
-<tr><td class="impl-no">Will not implement</td></tr>
+<tr><td class="impl-no">Not priority to implement</td></tr>
 <tr><td class="danger">Dangerous attribute/property</td></tr>
 <tr><td class="css1">Present in CSS1</td></tr>
 <tr><td class="feature">Feature, requires extra work</td></tr>
@@ -118,6 +118,7 @@ thead th {text-align:left;padding:0.1em;background-color:#EEE;}
 <tbody>
 <tr><th colspan="2">Table</th></tr>
 <tr class="impl-yes"><td>border-collapse</td><td>ENUM(collapse, seperate)</td></tr>
+<tr class="impl-yes"><td>border-space</td><td>MULTIPLE</td></tr>
 <tr class="impl-yes"><td>caption-side</td><td>ENUM(top, bottom)</td></tr>
 <tr class="feature"><td>empty-cells</td><td>ENUM(show, hide), No IE support makes this useless,
    possible fix with &amp;nbsp;? Unknown release milestone.</td></tr>
--- a/docs/enduser-customize.html
+++ b/docs/enduser-customize.html
@@ -32,7 +32,7 @@
  Before we even write any code, it is paramount to consider whether or
  not the code we're writing is necessary or not. HTML Purifier, by default,
  contains a large set of elements and attributes: large enough so that
-  <em>any</em> element or attribute in XHTML 1.0 (and its HTML variant)
+  <em>any</em> element or attribute in XHTML 1.0 or 1.1 (and its HTML variants)
  that can be safely used by the general public is implemented.
 </p>

@@ -76,11 +76,12 @@
 <h3>XHTML 1.1</h3>

 <p>
-  We have not implemented the
+  As of HTMLPurifier 2.1.0, we have implemented the
  <a href="http://www.w3.org/TR/2001/REC-ruby-20010531/">Ruby module</a>,
  which defines a set of tags
  for publishing short annotations for text, used mostly in Japanese
-  and Chinese school texts.
+  and Chinese school texts, but applicable for positioning any text (not
+  limited to translations) above or below other corresponding text.
 </p>

 <h3>XHTML 2.0</h3>
@@ -492,10 +493,11 @@ $def =& $config->getHTMLDefinition(true);
 <p>
  The <code>(%flow;)*</code> indicates the allowed children of the
  <code>li</code> tag: <code>li</code> allows any number of flow
-  elements as its children. In HTML Purifier, we'd write it like
-  <code>Flow</code> (here's where the content sets we were
-  discussing earlier come into play). There are three shorthand content models you
-  can specify:
+  elements as its children. (The <code>- O</code> allows the closing tag to be 
+  omitted, though in XML this is not allowed.) In HTML Purifier, 
+  we'd write it like <code>Flow</code> (here's where the content sets 
+  we were discussing earlier come into play). There are three shorthand
+  content models you can specify:
 </p>

 <table class="table">
@@ -668,12 +670,22 @@ $def =& $config->getHTMLDefinition(true);
  Common is a combination of the above-mentioned collections.
 </p>

+<p class="aside">
+  Readers familiar with the modularization may have noticed that the Core
+  attribute collection differs from that specified by the <a
+  href="http://www.w3.org/TR/xhtml-modularization/abstract_modules.html#s_commonatts">abstract
+  modules of the XHTML Modularization 1.1</a>. We believe this section
+  to be in error, as <code>br</code> permits the use of the <code>style</code>
+  attribute even though it uses the <code>Core</code> collection, and 
+  the DTD and XML Schemas supplied by W3C support our interpretation.
+</p>
+
 <h3>Attributes</h3>

 <p>
-  If you didn't read the <a href="#addAttribute">previous section on
+  If you didn't read the <a href="#addAttribute">earlier section on
  adding attributes</a>, read it now.  The last parameter is simply
-  array of attribute names to attribute implementations, in the exact
+  an array of attribute names to attribute implementations, in the exact
  same format as <code>addAttribute()</code>.
 </p>

--- a/docs/enduser-id.html
+++ b/docs/enduser-id.html
@@ -58,7 +58,7 @@ appear elsewhere on the document.  The method is simple:</p>

 <pre>$config->set('HTML', 'EnableAttrID', true);
 $config->set('Attr', 'IDBlacklist' array(
-    'list', 'of', 'attributes', 'that', 'are', 'forbidden'
+    'list', 'of', 'attribute', 'values', 'that', 'are', 'forbidden'
 ));</pre>

 <p>That being said, there are some notable drawbacks.  First of all, you have to
@@ -71,9 +71,9 @@ to possible standards-compliance issues.</p>
 <p>Furthermore, this position becomes untenable when a single web page must hold
 multiple portions of user-submitted content.  Since there's obviously no way
 to find out before-hand what IDs users will use, the blacklist is helpless.
-And even since HTML Purifier validates each segment seperately, perhaps doing
+And since HTML Purifier validates each segment separately, perhaps doing
 so at different times, it would be extremely difficult to dynamically update
-the blacklist inbetween runs.</p>
+the blacklist in between runs.</p>

 <p>Finally, simply destroying the ID is extremely un-userfriendly behavior: after
 all, they might have simply specified a duplicate ID by accident.</p>
--- a/docs/enduser-tidy.html
+++ b/docs/enduser-tidy.html
@@ -22,7 +22,7 @@ out:</p>

 <p class="emphasis">This ain't HTML Tidy!</p>

-<p>Rather, Tidy stands for a cool set of Tidy-inspired in HTML Purifier
+<p>Rather, Tidy stands for a cool set of Tidy-inspired features in HTML Purifier
 that allows users to submit deprecated elements and attributes and get
 valid strict markup back. For example:</p>

@@ -33,8 +33,8 @@ valid strict markup back. For example:</p>
 <pre>&lt;div style=&quot;text-align:center;&quot;&gt;Centered&lt;/div&gt;</pre>

 <p>...when this particular fix is run on the HTML. This tutorial will give
-you down the lowdown of what exactly HTML Purifier will do when Tidy
-is on, and how to fine tune this behavior. Once again, <strong>you do
+you the lowdown of what exactly HTML Purifier will do when Tidy
+is on, and how to fine-tune this behavior. Once again, <strong>you do
 not need Tidy installed on your PHP to use these features!</strong></p>

 <h2>What does it do?</h2>
@@ -221,7 +221,7 @@ general syntax:</p>

 <p>The lowdown is, quite frankly, HTML Purifier's default settings are
 probably good enough. The next step is to bump the level up to heavy,
-and if that still doesn't satisfy your appetite, do some fine tuning.
+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>

--- a/docs/enduser-utf8.html
+++ b/docs/enduser-utf8.html
@@ -96,7 +96,7 @@ which can be a rewarding (but difficult) task.</p>
 <h2 id="findcharset">Finding the real encoding</h2>

 <p>In the beginning, there was ASCII, and things were simple. But they
-weren't good, for no one could write in Cryllic or Thai. So there
+weren't good, for no one could write in Cyrillic or Thai. So there
 exploded a proliferation of character encodings to remedy the problem
 by extending the characters ASCII could express. This ridiculously
 simplified version of the history of character encodings shows us that
@@ -138,7 +138,7 @@ browser:</p>
    <dd>View &gt; Encoding: bulleted item is unofficial name</dd>
 </dl>

-<p>Internet Explorer won't give you the mime (i.e. useful/real) name of the
+<p>Internet Explorer won't give you the MIME (i.e. useful/real) name of the
 character encoding, so you'll have to look it up using their description.
 Some common ones:</p>

@@ -216,6 +216,12 @@ if your <code>META</code> tag claims that either:</p>

 <h2 id="fixcharset">Fixing the encoding</h2>

+<p class="aside">The advice given here is for pages being served as
+vanilla <code>text/html</code>.  Different practices must be used
+for <code>application/xml</code> or <code>application/xml+xhtml</code>, see
+<a href="http://www.w3.org/TR/2002/NOTE-xhtml-media-types-20020430/">W3C's
+document on XHTML media types</a> for more information.</p>
+
 <p>If your <code>META</code> encoding and your real encoding match,
 savvy! You can skip this section. If they don't...</p>

@@ -231,7 +237,7 @@ of your real encoding.</p>
    why the character encoding should be explicitly stated. When the
    browser isn't told what the character encoding of a text is, it
    has to guess: and sometimes the guess is wrong. Hackers can manipulate
-    this guess in order to slip XSS pass filters and then fool the
+    this guess in order to slip XSS past filters and then fool the
    browser into executing it as active code. A great example of this
    is the <a href="http://shiflett.org/archive/177">Google UTF-7
    exploit</a>.</p>
@@ -302,7 +308,8 @@ languages</a>. The appropriate code is:</p>

 <p>...replacing UTF-8 with whatever your embedded encoding is.
 This code must come before any output, so be careful about
-stray whitespace in your application.</p>
+stray whitespace in your application (i.e., any whitespace before 
+output excluding whitespace within &lt;?php ?&gt; tags).</p>

 <h4 id="fixcharset-server-phpini">PHP ini directive</h4>

@@ -313,8 +320,8 @@ header call: <code><a href="http://php.net/ini.core#ini.default-charset">default

 <p>...will also do the trick. If PHP is running as an Apache module (and
 not as FastCGI, consult
-<a href="http://php.net/phpinfo">phpinfo</a>() for details), you can even use htaccess do apply this property
-globally:</p>
+<a href="http://php.net/phpinfo">phpinfo</a>() for details), you can even use htaccess to apply this property
+across many PHP files:</p>

 <pre><a href="http://php.net/configuration.changes#configuration.changes.apache">php_value</a> default_charset &quot;UTF-8&quot;</pre>

@@ -360,10 +367,11 @@ to send anything at all:</p>

 <pre><a href="http://httpd.apache.org/docs/1.3/mod/core.html#adddefaultcharset">AddDefaultCharset</a> Off</pre>

-<p>...making your <code>META</code> tags the sole source of
-character encoding information. In these cases, it is
-<em>especially</em> important to make sure you have valid <code>META</code>
-tags on your pages and all the text before them is ASCII.</p>
+<p>...making your internal charset declaration (usually the <code>META</code> tags)
+the sole source of character encoding 
+information. In these cases, it is <em>especially</em> important to make 
+sure you have valid <code>META</code> tags on your pages and all the 
+text before them is ASCII.</p>

 <blockquote class="aside"><p>These directives can also be
 placed in httpd.conf file for Apache, but
@@ -428,28 +436,30 @@ IIS to change character encodings, I'd be grateful.</p>

 <p><code>META</code> tags are the most common source of embedded
 encodings, but they can also come from somewhere else: XML
-processing instructions. They look like:</p>
+Declarations. They look like:</p>

 <pre>&lt;?xml version=&quot;1.0&quot; encoding=&quot;UTF-8&quot;?&gt;</pre>

 <p>...and are most often found in XML documents (including XHTML).</p>

-<p>For XHTML, this processing instruction theoretically
+<p>For XHTML, this XML Declaration theoretically
 overrides the <code>META</code> tag. In reality, this happens only when the
 XHTML is actually served as legit XML and not HTML, which is almost always
 never due to Internet Explorer's lack of support for 
 <code>application/xhtml+xml</code> (even though doing so is often
-argued to be <a href="http://www.hixie.ch/advocacy/xhtml">good practice</a>).</p>
+argued to be <a href="http://www.hixie.ch/advocacy/xhtml">good 
+practice</a> and is required by the XHTML 1.1 specification).</p>

-<p>For XML, however, this processing instruction is extremely important.
+<p>For XML, however, this XML Declaration is extremely important.
 Since most webservers are not configured to send charsets for .xml files,
 this is the only thing a parser has to go on. Furthermore, the default
 for XML files is UTF-8, which often butts heads with more common
 ISO-8859-1 encoding (you see this in garbled RSS feeds).</p>

 <p>In short, if you use XHTML and have gone through the
-trouble of adding the XML header, make sure it jives
-with your <code>META</code> tags and HTTP headers.</p>
+trouble of adding the XML Declaration, make sure it jives
+with your <code>META</code> tags (which should only be present 
+if served in text/html) and HTTP headers.</p>

 <h3 id="fixcharset-internals">Inside the process</h3>

@@ -506,7 +516,7 @@ usage in one language sometimes requires the occasional special character
 that, without surprise, is not available in your character set. Sometimes
 developers get around this by adding support for multiple encodings: when
 using Chinese, use Big5, when using Japanese, use Shift-JIS, when
-using Greek, etc. Other times, they use character entities with great
+using Greek, etc. Other times, they use character references with great
 zeal.</p>

 <p>UTF-8, however, obviates the need for any of these complicated
@@ -520,14 +530,14 @@ you don't have to use those user-unfriendly entities.</p>

 <p>Websites encoded in Latin-1 (ISO-8859-1) which ocassionally need
 a special character outside of their scope often will use a character
-entity to achieve the desired effect. For instance, &theta; can be
+entity reference to achieve the desired effect. For instance, &theta; can be
 written <code>&amp;theta;</code>, regardless of the character encoding's
 support of Greek letters.</p>

 <p>This works nicely for limited use of special characters, but
 say you wanted this sentence of Chinese text: &#28608;&#20809;,
 &#36889;&#20841;&#20491;&#23383;&#26159;&#29978;&#40636;&#24847;&#24605;.
-The entity-ized version would look like this:</p>
+The ampersand encoded version would look like this:</p>

 <pre>&amp;#28608;&amp;#20809;, &amp;#36889;&amp;#20841;&amp;#20491;&amp;#23383;&amp;#26159;&amp;#29978;&amp;#40636;&amp;#24847;&amp;#24605;</pre>

@@ -545,7 +555,7 @@ an application that originally used ISO-8859-1 but switched to UTF-8
 when it became far to cumbersome to support foreign languages. Bots
 will now actually go through articles and convert character entities
 to their corresponding real characters for the sake of user-friendliness
-and searcheability. See
+and searchability. See
 <a href="http://meta.wikimedia.org/wiki/Help:Special_characters">Meta's
 page on special characters</a> for more details.
 </p></blockquote>
@@ -567,10 +577,11 @@ which may be used by POST, and is required when you want to upload
 files.</p>

 <p>The following is a summarization of notes from
-<a href="http://ppewww.physics.gla.ac.uk/~flavell/charset/form-i18n.html">
+<a href="http://web.archive.org/web/20060427015200/ppewww.ph.gla.ac.uk/~flavell/charset/form-i18n.html">
 <code>FORM</code> submission and i18n</a>. That document contains lots
 of useful information, but is written in a rambly manner, so
-here I try to get right to the point.</p>
+here I try to get right to the point. (Note: the original has 
+disappeared off the web, so I am linking to the Web Archive copy.)</p>

 <h4 id="whyutf8-forms-urlencoded"><code>application/x-www-form-urlencoded</code></h4>

@@ -592,7 +603,7 @@ browser you're using, they might:</p>
 <ul>
    <li>Replace the unsupported characters with useless question marks,</li>
    <li>Attempt to fix the characters (example: smart quotes to regular quotes),</li>
-    <li>Replace the character with a character entity, or</li>
+    <li>Replace the character with a character entity reference, or</li>
    <li>Send it anyway as a different character encoding mixed in
        with the original encoding (usually Windows-1252 rather than
        iso-8859-1 or UTF-8 interspersed in 8-bit)</li>
@@ -608,7 +619,7 @@ since UTF-8 supports every character.</p>

 <h4 id="whyutf8-forms-multipart"><code>multipart/form-data</code></h4>

-<p>Multipart form submission takes a way a lot of the ambiguity
+<p>Multipart form submission takes away a lot of the ambiguity
 that percent-encoding had: the server now can explicitly ask for
 certain encodings, and the client can explicitly tell the server
 during the form submission what encoding the fields are in.</p>
@@ -621,9 +632,9 @@ Each method has deficiencies, especially the former.</p>
 <p>If you tell the browser to send the form in the same encoding as
 the page, you still have the trouble of what to do with characters
 that are outside of the character encoding's range. The behavior, once
-again, varies: Firefox 2.0 entity-izes them while Internet Explorer
-7.0 mangles them beyond intelligibility. For serious internationalization purposes,
-this is not an option.</p>
+again, varies: Firefox 2.0 converts them to character entity references
+while Internet Explorer 7.0 mangles them beyond intelligibility. For
+serious internationalization purposes, this is not an option.</p>

 <p>The other possibility is to set Accept-Encoding to UTF-8, which
 begs the question: Why aren't you using UTF-8 for everything then?
@@ -663,12 +674,12 @@ it up to the module iconv to do the dirty work.</p>
 <p>This approach, however, is not perfect. iconv is blithely unaware
 of HTML character entities. HTML Purifier, in order to
 protect against sophisticated escaping schemes, normalizes all character
-and numeric entities before processing the text. This leads to
+and numeric entitie references before processing the text. This leads to
 one important ramification:</p>

 <p><strong>Any character that is not supported by the target character
 set, regardless of whether or not it is in the form of a character
-entity or a raw character, will be silently ignored.</strong></p>
+entity reference or a raw character, will be silently ignored.</strong></p>

 <p>Example of this principle at work: say you have <code>&amp;theta;</code>
 in your HTML, but the output is in Latin-1 (which, understandably,
@@ -677,7 +688,7 @@ set the encoding correctly using %Core.Encoding):</p>

 <ul>
    <li>The <code>Encoder</code> will transform the text from ISO 8859-1 to UTF-8
-        (note that theta is preserved since it doesn't actually use
+        (note that theta is preserved here since it doesn't actually use
        any non-ASCII characters): <code>&amp;theta;</code></li>
    <li>The <code>EntityParser</code> will transform all named and numeric
        character entities to their corresponding raw UTF-8 equivalents:
@@ -700,7 +711,7 @@ Purifier has provided a slightly more palatable workaround using
    <li>The <code>EntityParser</code> transforms entities: <code>&theta;</code></li>
    <li>HTML Purifier processes the code: <code>&theta;</code></li>
    <li>The <code>Encoder</code> replaces all non-ASCII characters
-        with numeric entities: <code>&amp;#952;</code></li>
+        with numeric entity reference: <code>&amp;#952;</code></li>
    <li>For good measure, <code>Encoder</code> transforms encoding back to
        original (which is strictly unnecessary for 99% of encodings
        out there): <code>&amp;#952;</code> (remember, it's all ASCII!)</li>
@@ -710,19 +721,19 @@ Purifier has provided a slightly more palatable workaround using
 the land of Unicode characters, and is totally unacceptable for Chinese
 or Japanese texts. The even bigger kicker is that, supposing the
 input encoding was actually ISO-8859-7, which <em>does</em> support
-theta, the character would get entity-ized anyway! (The Encoder does
-not discriminate).</p>
+theta, the character would get converted into a character entity reference
+anyway! (The Encoder does not discriminate).</p>

 <p>The current functionality is about where HTML Purifier will be for
 the rest of eternity. HTML Purifier could attempt to preserve the original
-form of the entities so that they could be substituted back in, only the
+form of the character references so that they could be substituted back in, only the
 DOM extension kills them off irreversibly. HTML Purifier could also attempt
 to be smart and only convert non-ASCII characters that weren't supported
 by the target encoding, but that would require reimplementing iconv
 with HTML awareness, something I will not do.</p>

 <p>So there: either it's UTF-8 or crippled international support. Your pick! (and I'm
-not being sarcastic here: some people could care less about other languages)</p>
+not being sarcastic here: some people could care less about other languages).</p>

 <h2 id="migrate">Migrate to UTF-8</h2>

@@ -984,7 +995,7 @@ and yes, it is variable width. Other traits:</p>
 in different ways. It is beyond the scope of this document to explain
 what precisely these implications are. PHPWact provides
 a very good <a href="http://www.phpwact.org/php/i18n/utf-8">reference document</a>
-on what to expect from each functions, although coverage is spotty in
+on what to expect from each function, although coverage is spotty in
 some areas. Their more general notes on
 <a href="http://www.phpwact.org/php/i18n/charsets">character sets</a>
 are also worth looking at for information on UTF-8. Some rules of thumb
@@ -998,7 +1009,7 @@ when dealing with Unicode text:</p>
    <li>Think twice before using functions that:<ul>
        <li>...count characters (strlen will return bytes, not characters;
            str_split and word_wrap may corrupt)</li>
-        <li>...entity-ize things (UTF-8 doesn't need entities)</li>
+        <li>...convert characters to entity references (UTF-8 doesn't need entities)</li>
        <li>...do very complex string processing (*printf)</li>
    </ul></li>
 </ul>
--- a/docs/ref-css-length.txt
+++ b/docs/ref-css-length.txt
@@ -0,0 +1,28 @@
+
+CSS Length Reference
+  To bound, or not to bound, that is the question
+
+It's quite a reasonable request, really, and it's already been implemented
+for HTML.  That is, length bounding.  It makes little sense to let users
+define text blocks that have a font-size of 63,360 inches (that's a mile,
+by the way) or a width of forty-fold the parent container.
+
+But it's a little more complicated then that. There are multiple units
+one can use, and we have to a little unit conversion to get things working.
+Here's what we have:
+
+Absolute:
+    1 in ~= 2.54 cm
+    1 cm = 10 mm
+    1 pt = 1/72 in
+    1 pc = 12 pt
+
+Relative:
+    1 em ~= 10.0667 px
+    1 ex ~= 0.5 em, though Mozilla Firefox says 1 ex = 6px
+    1 px ~= 1 pt
+
+Watch out: font-sizes can also be nested to get successively larger 
+(although I do not relish having to keep track of context font-sizes,
+this may be necessary, especially for some of the more advanced features
+for preventing things like white on white).
--- a/library/HTMLPurifier.php
+++ b/library/HTMLPurifier.php
@@ -22,8 +22,8 @@
 */

 /*
-    HTML Purifier 2.0.1 - Standards Compliant HTML Filtering
-    Copyright (C) 2006 Edward Z. Yang
+    HTML Purifier 2.1.3 - Standards Compliant HTML Filtering
+    Copyright (C) 2006-2007 Edward Z. Yang

    This library is free software; you can redistribute it and/or
    modify it under the terms of the GNU Lesser General Public
@@ -40,9 +40,11 @@
    Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301  USA
 */

-// almost every class has an undocumented dependency to these, so make sure
-// they get included
-require_once 'HTMLPurifier/ConfigSchema.php'; // important
+// constants are slow, but we'll make one exception
+define('HTMLPURIFIER_PREFIX', dirname(__FILE__));
+
+// every class has an undocumented dependency to these, must be included!
+require_once 'HTMLPurifier/ConfigSchema.php'; // fatal errors if not included
 require_once 'HTMLPurifier/Config.php';
 require_once 'HTMLPurifier/Context.php';

@@ -57,16 +59,23 @@ require_once 'HTMLPurifier/LanguageFactory.php';
 HTMLPurifier_ConfigSchema::define(
    'Core', 'CollectErrors', false, 'bool', '
 Whether or not to collect errors found while filtering the document. This
-is a useful way to give feedback to your users. CURRENTLY NOT IMPLEMENTED.
-This directive has been available since 2.0.0.
+is a useful way to give feedback to your users. <strong>Warning:</strong>
+Currently this feature is very patchy and experimental, with lots of
+possible error messages not yet implemented. It will not cause any problems,
+but it may not help your users either. This directive has been available
+since 2.0.0.
 ');

 /**
- * Main library execution class.
+ * Facade that coordinates HTML Purifier's subsystems in order to purify HTML.
 * 
- * Facade that performs calls to the HTMLPurifier_Lexer,
- * HTMLPurifier_Strategy and HTMLPurifier_Generator subsystems in order to
- * purify HTML.
+ * @note There are several points in which configuration can be specified 
+ *       for HTML Purifier.  The precedence of these (from lowest to
+ *       highest) is as follows:
+ *          -# Instance: new HTMLPurifier($config)
+ *          -# Invocation: purify($html, $config)
+ *       These configurations are entirely independent of each other and
+ *       are *not* merged.
 * 
 * @todo We need an easier way to inject strategies, it'll probably end
 *       up getting done through config though.
@@ -74,15 +83,16 @@ This directive has been available since 2.0.0.
 class HTMLPurifier
 {
    
-    var $version = '2.0.1';
+    var $version = '2.1.3';
    
    var $config;
-    var $filters;
+    var $filters = array();
    
    var $strategy, $generator;
    
    /**
-     * Final HTMLPurifier_Context of last run purification. Might be an array.
+     * Resultant HTMLPurifier_Context of last run purification. Is an array
+     * of contexts if the last called method was purifyArray().
     * @public
     */
    var $context;
@@ -147,6 +157,11 @@ class HTMLPurifier
            $context->register('ErrorCollector', $error_collector);
        }
        
+        // setup id_accumulator context, necessary due to the fact that
+        // AttrValidator can be called from many places
+        $id_accumulator = HTMLPurifier_IDAccumulator::build($config, $context);
+        $context->register('IDAccumulator', $id_accumulator);
+        
        $html = HTMLPurifier_Encoder::convertToUTF8($html, $config, $context);
        
        for ($i = 0, $size = count($this->filters); $i < $size; $i++) {
@@ -195,14 +210,16 @@ class HTMLPurifier
    
    /**
     * Singleton for enforcing just one HTML Purifier in your system
+     * @param $prototype Optional prototype HTMLPurifier instance to
+     *                   overload singleton with.
     */
-    function &getInstance($prototype = null) {
+    static function &getInstance($prototype = null) {
        static $htmlpurifier;
        if (!$htmlpurifier || $prototype) {
-            if (is_a($prototype, 'HTMLPurifier')) {
+            if ($prototype instanceof HTMLPurifier) {
                $htmlpurifier = $prototype;
            } elseif ($prototype) {
-                $htmlpurifier = new HTMLPurifier(HTMLPurifier_Config::create($prototype));
+                $htmlpurifier = new HTMLPurifier($prototype);
            } else {
                $htmlpurifier = new HTMLPurifier();
            }
--- a/library/HTMLPurifier/AttrDef/CSS/FontFamily.php
+++ b/library/HTMLPurifier/AttrDef/CSS/FontFamily.php
@@ -38,19 +38,24 @@ class HTMLPurifier_AttrDef_CSS_FontFamily extends HTMLPurifier_AttrDef
                $quote = $font[0];
                if ($font[$length - 1] !== $quote) continue;
                $font = substr($font, 1, $length - 2);
+                // double-backslash processing is buggy
+                $font = str_replace("\\$quote", $quote, $font); // de-escape quote
+                $font = str_replace("\\\n", "\n", $font);       // de-escape newlines
            }
-            // process font
+            // $font is a pure representation of the font name
+            
            if (ctype_alnum($font)) {
                // very simple font, allow it in unharmed
                $final .= $font . ', ';
                continue;
            }
-            $nospace = str_replace(array(' ', '.', '!'), '', $font);
-            if (ctype_alnum($nospace)) {
-                // font with spaces in it
-                $final .= "'$font', ";
-                continue;
-            }
+            
+            // complicated font, requires quoting
+            
+            // armor single quotes and new lines
+            $font = str_replace("'", "\\'", $font);
+            $font = str_replace("\n", "\\\n", $font);
+            $final .= "'$font', ";
        }
        $final = rtrim($final, ', ');
        if ($final === '') return false;
--- a/library/HTMLPurifier/AttrDef/CSS/URI.php
+++ b/library/HTMLPurifier/AttrDef/CSS/URI.php
@@ -15,7 +15,7 @@ class HTMLPurifier_AttrDef_CSS_URI extends HTMLPurifier_AttrDef_URI
 {
    
    function HTMLPurifier_AttrDef_CSS_URI() {
-        $this->HTMLPurifier_AttrDef_URI(true); // always embedded
+        parent::HTMLPurifier_AttrDef_URI(true); // always embedded
    }
    
    function validate($uri_string, $config, &$context) {
--- a/library/HTMLPurifier/AttrDef/URI.php
+++ b/library/HTMLPurifier/AttrDef/URI.php
@@ -1,90 +1,66 @@
 <?php

 require_once 'HTMLPurifier/AttrDef.php';
+require_once 'HTMLPurifier/URIParser.php';
 require_once 'HTMLPurifier/URIScheme.php';
 require_once 'HTMLPurifier/URISchemeRegistry.php';
 require_once 'HTMLPurifier/AttrDef/URI/Host.php';
 require_once 'HTMLPurifier/PercentEncoder.php';
+require_once 'HTMLPurifier/AttrDef/URI/Email.php';
+
+// special case filtering directives 

 HTMLPurifier_ConfigSchema::define(
-    'URI', 'DefaultScheme', 'http', 'string',
-    'Defines through what scheme the output will be served, in order to '.
-    'select the proper object validator when no scheme information is present.'
-);
+    'URI', 'Munge', null, 'string/null', '
+<p>
+    Munges all browsable (usually http, https and ftp)
+    absolute URI\'s 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>).
+</p>
+<p>
+    Uses for this directive:
+</p>
+<ul>
+    <li>
+        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 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 mandated
+        in corporate environments.
+    </li>
+</ul>
+<p>
+    This directive has been available since 1.3.0.
+</p>
+');
+
+// disabling directives

 HTMLPurifier_ConfigSchema::define(
-    'URI', 'Host', null, 'string/null',
-    'Defines the domain name of the server, so we can determine whether or '.
-    'an absolute URI is from your website or not.  Not strictly necessary, '.
-    'as users should be using relative URIs to reference resources on your '.
-    'website.  It will, however, let you use absolute URIs to link to '.
-    'subdomains of the domain you post here: i.e. example.com will allow '.
-    'sub.example.com.  However, higher up domains will still be excluded: '.
-    'if you set %URI.Host to sub.example.com, example.com will be blocked. '.
-    'This directive has been available since 1.2.0.'
-);
-
-HTMLPurifier_ConfigSchema::define(
-    'URI', 'DisableExternal', false, 'bool',
-    'Disables links to external websites.  This is a highly effective '.
-    'anti-spam and anti-pagerank-leech measure, but comes at a hefty price: no'.
-    'links or images outside of your domain will be allowed.  Non-linkified '.
-    'URIs will still be preserved.  If you want to be able to link to '.
-    'subdomains or use absolute URIs, specify %URI.Host for your website. '.
-    'This directive has been available since 1.2.0.'
-);
-
-HTMLPurifier_ConfigSchema::define(
-    'URI', 'DisableExternalResources', false, 'bool',
-    'Disables the embedding of external resources, preventing users from '.
-    'embedding things like images from other hosts. This prevents '.
-    'access tracking (good for email viewers), bandwidth leeching, '.
-    'cross-site request forging, goatse.cx posting, and '.
-    'other nasties, but also results in '.
-    'a loss of end-user functionality (they can\'t directly post a pic '.
-    'they posted from Flickr anymore). Use it if you don\'t have a '.
-    'robust user-content moderation team. This directive has been '.
-    'available since 1.3.0.'
-);
-
-HTMLPurifier_ConfigSchema::define(
-    'URI', 'DisableResources', false, 'bool',
-    'Disables embedding resources, essentially meaning no pictures. You can '.
-    'still link to them though. See %URI.DisableExternalResources for why '.
-    'this might be a good idea. This directive has been available since 1.3.0.'
-);
-
-HTMLPurifier_ConfigSchema::define(
-    'URI', 'Munge', null, 'string/null',
-    'Munges all browsable (usually http, https and ftp) URI\'s into some URL '.
-    'redirection service. Pass this directive a URI, with %s inserted where '.
-    'the url-encoded original URI should be inserted (sample: '.
-    '<code>http://www.google.com/url?q=%s</code>). '.
-    'This prevents PageRank leaks, while being as transparent as possible '.
-    'to users (you may also want to add some client side JavaScript to '.
-    'override the text in the statusbar). Warning: many security experts '.
-    'believe that this form of protection does not deter spam-bots. '.
-    'You can also use this directive to redirect users to a splash page '.
-    'telling them they are leaving your website. '.
-    'This directive has been available since 1.3.0.'
-);
-
-HTMLPurifier_ConfigSchema::define(
-    'URI', 'HostBlacklist', array(), 'list',
-    'List of strings that are forbidden in the host of any URI. Use it to '.
-    'kill domain names of spam, etc. Note that it will catch anything in '.
-    'the domain, so <tt>moo.com</tt> will catch <tt>moo.com.example.com</tt>. '.
-    'This directive has been available since 1.3.0.'
-);
-
-HTMLPurifier_ConfigSchema::define(
-    'URI', 'Disable', false, 'bool',
-    'Disables all URIs in all forms. Not sure why you\'d want to do that '.
-    '(after all, the Internet\'s founded on the notion of a hyperlink). '.
-    'This directive has been available since 1.3.0.'
-);
+    'URI', 'Disable', false, 'bool', '
+<p>
+    Disables all URIs in all forms. Not sure why you\'d want to do that 
+    (after all, the Internet\'s founded on the notion of a hyperlink). 
+    This directive has been available since 1.3.0.
+</p>
+');
 HTMLPurifier_ConfigSchema::defineAlias('Attr', 'DisableURI', 'URI', 'Disable');

+HTMLPurifier_ConfigSchema::define(
+    'URI', 'DisableResources', false, 'bool', '
+<p>
+    Disables embedding resources, essentially meaning no pictures. You can 
+    still link to them though. See %URI.DisableExternalResources for why 
+    this might be a good idea. This directive has been available since 1.3.0.
+</p>
+');
+
 /**
 * Validates a URI as defined by RFC 3986.
 * @note Scheme-specific mechanics deferred to HTMLPurifier_URIScheme
@@ -92,214 +68,83 @@ HTMLPurifier_ConfigSchema::defineAlias('Attr', 'DisableURI', 'URI', 'Disable');
 class HTMLPurifier_AttrDef_URI extends HTMLPurifier_AttrDef
 {
    
-    var $host;
-    var $embeds_resource;
+    var $parser, $percentEncoder;
+    var $embedsResource;
    
    /**
     * @param $embeds_resource_resource Does the URI here result in an extra HTTP request?
     */
    function HTMLPurifier_AttrDef_URI($embeds_resource = false) {
-        $this->host = new HTMLPurifier_AttrDef_URI_Host();
-        $this->embeds_resource = (bool) $embeds_resource;
+        $this->parser = new HTMLPurifier_URIParser();
+        $this->percentEncoder = new HTMLPurifier_PercentEncoder();
+        $this->embedsResource = (bool) $embeds_resource;
    }
    
    function validate($uri, $config, &$context) {
        
-        static $PercentEncoder = null;
-        if ($PercentEncoder === null) $PercentEncoder = new HTMLPurifier_PercentEncoder();
-        
-        // We'll write stack-based parsers later, for now, use regexps to
-        // get things working as fast as possible (irony)
-        
        if ($config->get('URI', 'Disable')) return false;
        
-        // parse as CDATA
+        // initial operations
        $uri = $this->parseCDATA($uri);
+        $uri = $this->percentEncoder->normalize($uri);
        
-        // fix up percent-encoding
-        $uri = $PercentEncoder->normalize($uri);
+        // parse the URI
+        $uri = $this->parser->parse($uri);
+        if ($uri === false) return false;
        
-        // while it would be nice to use parse_url(), that's specifically
-        // for HTTP and thus won't work for our generic URI parsing
+        // add embedded flag to context for validators
+        $context->register('EmbeddedURI', $this->embedsResource); 
        
-        // according to the RFC... (but this cuts corners, i.e. non-validating)
-        $r_URI = '!'.
-            '(([^:/?#<>\'"]+):)?'. // 2. Scheme
-            '(//([^/?#<>\'"]*))?'. // 4. Authority
-            '([^?#<>\'"]*)'.       // 5. Path
-            '(\?([^#<>\'"]*))?'.   // 7. Query
-            '(#([^<>\'"]*))?'.     // 8. Fragment
-            '!';
-        
-        $matches = array();
-        $result = preg_match($r_URI, $uri, $matches);
-        
-        if (!$result) return false; // invalid URI
-        
-        // seperate out parts
-        $scheme     = !empty($matches[1]) ? $matches[2] : null;
-        $authority  = !empty($matches[3]) ? $matches[4] : null;
-        $path       = $matches[5]; // always present, can be empty
-        $query      = !empty($matches[6]) ? $matches[7] : null;
-        $fragment   = !empty($matches[8]) ? $matches[9] : null;
-        
-        
-        
-        $registry =& HTMLPurifier_URISchemeRegistry::instance();
-        if ($scheme !== null) {
-            // no need to validate the scheme's fmt since we do that when we
-            // retrieve the specific scheme object from the registry
-            $scheme = ctype_lower($scheme) ? $scheme : strtolower($scheme);
-            $scheme_obj = $registry->getScheme($scheme, $config, $context);
-            if (!$scheme_obj) return false; // invalid scheme, clean it out
-        } else {
-            $scheme_obj = $registry->getScheme(
-                $config->get('URI', 'DefaultScheme'), $config, $context
-            );
-        }
-        
-        // something funky weird happened in the registry, abort!
-        if (!$scheme_obj) {
-            trigger_error(
-                'Default scheme object "' . $config->get('URI', 'DefaultScheme') . '" was not readable',
-                E_USER_WARNING
-            );
-            return false;
-        }
-        
-        // the URI we're processing embeds_resource a resource in the page, but the URI
-        // it references cannot be located
-        if ($this->embeds_resource && !$scheme_obj->browsable) {
-            return false;
-        }
-        
-        
-        if ($authority !== null) {
+        $ok = false;
+        do {
            
-            // remove URI if it's absolute and we disabled externals or
-            // if it's absolute and embedded and we disabled external resources
-            unset($our_host);
-            if (
-                $config->get('URI', 'DisableExternal') ||
-                (
-                    $config->get('URI', 'DisableExternalResources') &&
-                    $this->embeds_resource
-                )
-            ) {
-                $our_host = $config->get('URI', 'Host');
-                if ($our_host === null) return false;
+            // generic validation
+            $result = $uri->validate($config, $context);
+            if (!$result) break;
+            
+            // chained filtering
+            $uri_def =& $config->getDefinition('URI');
+            $result = $uri_def->filter($uri, $config, $context);
+            if (!$result) break;
+            
+            // scheme-specific validation 
+            $scheme_obj = $uri->getSchemeObj($config, $context);
+            if (!$scheme_obj) break;
+            if ($this->embedsResource && !$scheme_obj->browsable) break;
+            $result = $scheme_obj->validate($uri, $config, $context);
+            if (!$result) break;
+            
+            // survived gauntlet
+            $ok = true;
+            
+        } while (false);
+        
+        $context->destroy('EmbeddedURI');
+        if (!$ok) return false;
+        
+        // munge scheme off if necessary (this must be last)
+        if (!is_null($uri->scheme) && is_null($uri->host)) {
+            if ($uri_def->defaultScheme == $uri->scheme) {
+                $uri->scheme = null;
            }
-            
-            $HEXDIG = '[A-Fa-f0-9]';
-            $unreserved = 'A-Za-z0-9-._~'; // make sure you wrap with []
-            $sub_delims = '!$&\'()'; // needs []
-            $pct_encoded = "%$HEXDIG$HEXDIG";
-            $r_userinfo = "(?:[$unreserved$sub_delims:]|$pct_encoded)*";
-            $r_authority = "/^(($r_userinfo)@)?(\[[^\]]+\]|[^:]*)(:(\d*))?/";
-            $matches = array();
-            preg_match($r_authority, $authority, $matches);
-            // overloads regexp!
-            $userinfo   = !empty($matches[1]) ? $matches[2] : null;
-            $host       = !empty($matches[3]) ? $matches[3] : null;
-            $port       = !empty($matches[4]) ? $matches[5] : null;
-            
-            // validate port
-            if ($port !== null) {
-                $port = (int) $port;
-                if ($port < 1 || $port > 65535) $port = null;
-            }
-            
-            $host = $this->host->validate($host, $config, $context);
-            if ($host === false) $host = null;
-            
-            if ($this->checkBlacklist($host, $config, $context)) return false;
-            
-            // more lenient absolute checking
-            if (isset($our_host)) {
-                $host_parts = array_reverse(explode('.', $host));
-                // could be cached
-                $our_host_parts = array_reverse(explode('.', $our_host));
-                foreach ($our_host_parts as $i => $discard) {
-                    if (!isset($host_parts[$i])) return false;
-                    if ($host_parts[$i] != $our_host_parts[$i]) return false;
-                }
-            }
-            
-            // userinfo and host are validated within the regexp
-            
-        } else {
-            $port = $host = $userinfo = null;
        }
        
+        // back to string
+        $result = $uri->toString();
        
-        // query and fragment are quite simple in terms of definition:
-        // *( pchar / "/" / "?" ), so define their validation routines
-        // when we start fixing percent encoding
-        
-        
-        
-        // path gets to be validated against a hodge-podge of rules depending
-        // on the status of authority and scheme, but it's not that important,
-        // esp. since it won't be applicable to everyone
-        
-        
-        
-        // okay, now we defer execution to the subobject for more processing
-        // note that $fragment is omitted
-        list($userinfo, $host, $port, $path, $query) = 
-            $scheme_obj->validateComponents(
-                $userinfo, $host, $port, $path, $query, $config, $context
-            );
-        
-        
-        // reconstruct authority
-        $authority = null;
-        if (!is_null($userinfo) || !is_null($host) || !is_null($port)) {
-            $authority = '';
-            if($userinfo !== null) $authority .= $userinfo . '@';
-            $authority .= $host;
-            if($port !== null) $authority .= ':' . $port;
-        }
-        
-        // reconstruct the result
-        $result = '';
-        if ($scheme !== null) $result .= "$scheme:";
-        if ($authority !== null) $result .= "//$authority";
-        $result .= $path;
-        if ($query !== null) $result .= "?$query";
-        if ($fragment !== null) $result .= "#$fragment";
-        
-        // munge if necessary
-        $munge = $config->get('URI', 'Munge');
-        if (!empty($scheme_obj->browsable) && $munge !== null) {
-            if ($authority !== null) {
-                $result = str_replace('%s', rawurlencode($result), $munge);
-            }
+        // munge entire URI if necessary
+        if (
+            !is_null($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;
        
    }
    
-    /**
-     * Checks a host against an array blacklist
-     * @param $host Host to check
-     * @param $config HTMLPurifier_Config instance
-     * @param $context HTMLPurifier_Context instance
-     * @return bool Is spam?
-     */
-    function checkBlacklist($host, &$config, &$context) {
-        $blacklist = $config->get('URI', 'HostBlacklist');
-        if (!empty($blacklist)) {
-            foreach($blacklist as $blacklisted_host_fragment) {
-                if (strpos($host, $blacklisted_host_fragment) !== false) {
-                    return true;
-                }
-            }
-        }
-        return false;
-    }
-    
 }


--- a/library/HTMLPurifier/AttrDef/URI/Email.php
+++ b/library/HTMLPurifier/AttrDef/URI/Email.php
@@ -14,3 +14,5 @@ class HTMLPurifier_AttrDef_URI_Email extends HTMLPurifier_AttrDef
    
 }

+// sub-implementations
+require_once 'HTMLPurifier/AttrDef/URI/Email/SimpleCheck.php';
--- a/library/HTMLPurifier/AttrTypes.php
+++ b/library/HTMLPurifier/AttrTypes.php
@@ -44,6 +44,9 @@ class HTMLPurifier_AttrTypes
        $this->info['LanguageCode'] = new HTMLPurifier_AttrDef_Lang();
        $this->info['Color']    = new HTMLPurifier_AttrDef_HTML_Color();
        
+        // unimplemented aliases
+        $this->info['ContentType'] = new HTMLPurifier_AttrDef_Text();
+        
        // number is really a positive integer (one or more digits)
        // FIXME: ^^ not always, see start and value of list items
        $this->info['Number']   = new HTMLPurifier_AttrDef_Integer(false, false, true);
--- a/library/HTMLPurifier/AttrValidator.php
+++ b/library/HTMLPurifier/AttrValidator.php
@@ -23,6 +23,13 @@ class HTMLPurifier_AttrValidator
        $definition = $config->getHTMLDefinition();
        $e =& $context->get('ErrorCollector', true);
        
+        // initialize IDAccumulator if necessary
+        $ok =& $context->get('IDAccumulator', true);
+        if (!$ok) {
+            $id_accumulator = HTMLPurifier_IDAccumulator::build($config, $context);
+            $context->register('IDAccumulator', $id_accumulator);
+        }
+        
        // initialize CurrentToken if necessary
        $current_token =& $context->get('CurrentToken', true);
        if (!$current_token) $context->register('CurrentToken', $token);
--- a/library/HTMLPurifier/CSSDefinition.php
+++ b/library/HTMLPurifier/CSSDefinition.php
@@ -204,7 +204,7 @@ class HTMLPurifier_CSSDefinition extends HTMLPurifier_Definition
        $this->info['border-right'] = new HTMLPurifier_AttrDef_CSS_Border($config);
        
        $this->info['border-collapse'] = new HTMLPurifier_AttrDef_Enum(array(
-            'collapse', 'seperate'));
+            'collapse', 'separate'));
        
        $this->info['caption-side'] = new HTMLPurifier_AttrDef_Enum(array(
            'top', 'bottom'));
@@ -219,6 +219,8 @@ class HTMLPurifier_CSSDefinition extends HTMLPurifier_Definition
            new HTMLPurifier_AttrDef_CSS_Percentage()
        ));
        
+        $this->info['border-spacing'] = new HTMLPurifier_AttrDef_CSS_Multiple(new HTMLPurifier_AttrDef_CSS_Length(), 2);
+        
        // partial support
        $this->info['white-space'] = new HTMLPurifier_AttrDef_Enum(array('nowrap'));
        
--- a/library/HTMLPurifier/ChildDef/Optional.php
+++ b/library/HTMLPurifier/ChildDef/Optional.php
@@ -15,7 +15,10 @@ class HTMLPurifier_ChildDef_Optional extends HTMLPurifier_ChildDef_Required
    var $type = 'optional';
    function validateChildren($tokens_of_children, $config, &$context) {
        $result = parent::validateChildren($tokens_of_children, $config, $context);
-        if ($result === false) return array();
+        if ($result === false) {
+            if (empty($tokens_of_children)) return true;
+            else return array();
+        }
        return $result;
    }
 }
--- a/library/HTMLPurifier/Config.php
+++ b/library/HTMLPurifier/Config.php
@@ -5,6 +5,7 @@ require_once 'HTMLPurifier/ConfigSchema.php';
 // member variables
 require_once 'HTMLPurifier/HTMLDefinition.php';
 require_once 'HTMLPurifier/CSSDefinition.php';
+require_once 'HTMLPurifier/URIDefinition.php';
 require_once 'HTMLPurifier/Doctype.php';
 require_once 'HTMLPurifier/DefinitionCacheFactory.php';

@@ -41,7 +42,7 @@ class HTMLPurifier_Config
    /**
     * HTML Purifier's version
     */
-    var $version = '2.0.1';
+    var $version = '2.1.3';
    
    /**
     * Two-level associative array of configuration directives
@@ -75,6 +76,11 @@ class HTMLPurifier_Config
     */
    var $serials = array();
    
+    /**
+     * Serial for entire configuration object
+     */
+    var $serial;
+    
    /**
     * @param $definition HTMLPurifier_ConfigSchema that defines what directives
     *                    are allowed.
@@ -98,7 +104,6 @@ class HTMLPurifier_Config
        $ret = HTMLPurifier_Config::createDefault();
        if (is_string($config)) $ret->loadIni($config);
        elseif (is_array($config)) $ret->loadArray($config);
-        if (isset($revision)) $ret->revision = $revision;
        return $ret;
    }
    
@@ -165,6 +170,17 @@ class HTMLPurifier_Config
        return $this->serials[$namespace];
    }
    
+    /**
+     * Returns a md5 signature for the entire configuration object
+     * that uniquely identifies that particular configuration
+     */
+    function getSerial() {
+        if (empty($this->serial)) {
+            $this->serial = md5(serialize($this->getAll()));
+        }
+        return $this->serial;
+    }
+    
    /**
     * Retrieves all directives, organized by namespace
     */
@@ -295,6 +311,8 @@ class HTMLPurifier_Config
            $this->definitions[$type] = new HTMLPurifier_HTMLDefinition();
        } elseif ($type == 'CSS') {
            $this->definitions[$type] = new HTMLPurifier_CSSDefinition();
+        } elseif ($type == 'URI') {
+            $this->definitions[$type] = new HTMLPurifier_URIDefinition();
        } else {
            trigger_error("Definition of $type type not supported");
            $false = false;
@@ -393,6 +411,26 @@ class HTMLPurifier_Config
     * @static
     */
    static function loadArrayFromForm($array, $index, $allowed = true, $mq_fix = true) {
+        $ret = HTMLPurifier_Config::prepareArrayFromForm($array, $index, $allowed, $mq_fix);
+        $config = HTMLPurifier_Config::create($ret);
+        return $config;
+    }
+    
+    /**
+     * Merges in configuration values from $_GET/$_POST to object. NOT STATIC.
+     * @note Same parameters as loadArrayFromForm
+     */
+    function mergeArrayFromForm($array, $index, $allowed = true, $mq_fix = true) {
+         $ret = HTMLPurifier_Config::prepareArrayFromForm($array, $index, $allowed, $mq_fix);
+         $this->loadArray($ret);
+    }
+    
+    /**
+     * Prepares an array from a form into something usable for the more
+     * strict parts of HTMLPurifier_Config
+     * @static
+     */
+    static function prepareArrayFromForm($array, $index, $allowed = true, $mq_fix = true) {
        $array = (isset($array[$index]) && is_array($array[$index])) ? $array[$index] : array();
        $mq = get_magic_quotes_gpc() && $mq_fix;
        
@@ -409,9 +447,7 @@ class HTMLPurifier_Config
            $value = $mq ? stripslashes($array[$skey]) : $array[$skey];
            $ret[$ns][$directive] = $value;
        }
-        
-        $config = HTMLPurifier_Config::create($ret);
-        return $config;
+        return $ret;
    }
    
    /**
--- a/library/HTMLPurifier/ConfigSchema.php
+++ b/library/HTMLPurifier/ConfigSchema.php
@@ -6,6 +6,8 @@ require_once 'HTMLPurifier/ConfigDef/Namespace.php';
 require_once 'HTMLPurifier/ConfigDef/Directive.php';
 require_once 'HTMLPurifier/ConfigDef/DirectiveAlias.php';

+if (!defined('HTMLPURIFIER_SCHEMA_STRICT')) define('HTMLPURIFIER_SCHEMA_STRICT', false);
+
 /**
 * Configuration definition, defines directives and their defaults.
 * @note If you update this, please update Printer_ConfigForm
@@ -49,6 +51,8 @@ class HTMLPurifier_ConfigSchema {
    var $types = array(
        'string'    => 'String',
        'istring'   => 'Case-insensitive string',
+        'text'      => 'Text',
+        'itext'      => 'Case-insensitive text',
        'int'       => 'Integer',
        'float'     => 'Float',
        'bool'      => 'Boolean',
@@ -100,27 +104,30 @@ class HTMLPurifier_ConfigSchema {
     *      HTMLPurifier_DirectiveDef::$type for allowed values
     * @param $description Description of directive for documentation
     */
-    static function define(
-        $namespace, $name, $default, $type, 
-        $description
-    ) {
+    static function define($namespace, $name, $default, $type, $description) {
        $def =& HTMLPurifier_ConfigSchema::instance();
-        if (!isset($def->info[$namespace])) {
-            trigger_error('Cannot define directive for undefined namespace',
-                E_USER_ERROR);
-            return;
-        }
-        if (!ctype_alnum($name)) {
-            trigger_error('Directive name must be alphanumeric',
-                E_USER_ERROR);
-            return;
-        }
-        if (empty($description)) {
-            trigger_error('Description must be non-empty',
-                E_USER_ERROR);
-            return;
+        
+        // basic sanity checks
+        if (HTMLPURIFIER_SCHEMA_STRICT) {
+            if (!isset($def->info[$namespace])) {
+                trigger_error('Cannot define directive for undefined namespace',
+                    E_USER_ERROR);
+                return;
+            }
+            if (!ctype_alnum($name)) {
+                trigger_error('Directive name must be alphanumeric',
+                    E_USER_ERROR);
+                return;
+            }
+            if (empty($description)) {
+                trigger_error('Description must be non-empty',
+                    E_USER_ERROR);
+                return;
+            }
        }
+        
        if (isset($def->info[$namespace][$name])) {
+            // already defined
            if (
                $def->info[$namespace][$name]->type !== $type ||
                $def->defaults[$namespace][$name]   !== $default
@@ -129,29 +136,35 @@ class HTMLPurifier_ConfigSchema {
                return;
            }
        } else {
-            // process modifiers
+            // needs defining
+            
+            // process modifiers (OPTIMIZE!)
            $type_values = explode('/', $type, 2);
            $type = $type_values[0];
            $modifier = isset($type_values[1]) ? $type_values[1] : false;
            $allow_null = ($modifier === 'null');
            
-            if (!isset($def->types[$type])) {
-                trigger_error('Invalid type for configuration directive',
-                    E_USER_ERROR);
-                return;
-            }
-            $default = $def->validate($default, $type, $allow_null);
-            if ($def->isError($default)) {
-                trigger_error('Default value does not match directive type',
-                    E_USER_ERROR);
-                return;
+            if (HTMLPURIFIER_SCHEMA_STRICT) {
+                if (!isset($def->types[$type])) {
+                    trigger_error('Invalid type for configuration directive',
+                        E_USER_ERROR);
+                    return;
+                }
+                $default = $def->validate($default, $type, $allow_null);
+                if ($def->isError($default)) {
+                    trigger_error('Default value does not match directive type',
+                        E_USER_ERROR);
+                    return;
+                }
            }
+            
            $def->info[$namespace][$name] =
                new HTMLPurifier_ConfigDef_Directive();
            $def->info[$namespace][$name]->type = $type;
            $def->info[$namespace][$name]->allow_null = $allow_null;
            $def->defaults[$namespace][$name]   = $default;
        }
+        if (!HTMLPURIFIER_SCHEMA_STRICT) return;
        $backtrace = debug_backtrace();
        $file = $def->mungeFilename($backtrace[0]['file']);
        $line = $backtrace[0]['line'];
@@ -166,19 +179,21 @@ class HTMLPurifier_ConfigSchema {
     */
    static function defineNamespace($namespace, $description) {
        $def =& HTMLPurifier_ConfigSchema::instance();
-        if (isset($def->info[$namespace])) {
-            trigger_error('Cannot redefine namespace', E_USER_ERROR);
-            return;
-        }
-        if (!ctype_alnum($namespace)) {
-            trigger_error('Namespace name must be alphanumeric',
-                E_USER_ERROR);
-            return;
-        }
-        if (empty($description)) {
-            trigger_error('Description must be non-empty',
-                E_USER_ERROR);
-            return;
+        if (HTMLPURIFIER_SCHEMA_STRICT) {
+            if (isset($def->info[$namespace])) {
+                trigger_error('Cannot redefine namespace', E_USER_ERROR);
+                return;
+            }
+            if (!ctype_alnum($namespace)) {
+                trigger_error('Namespace name must be alphanumeric',
+                    E_USER_ERROR);
+                return;
+            }
+            if (empty($description)) {
+                trigger_error('Description must be non-empty',
+                    E_USER_ERROR);
+                return;
+            }
        }
        $def->info[$namespace] = array();
        $def->info_namespace[$namespace] = new HTMLPurifier_ConfigDef_Namespace();
@@ -199,23 +214,25 @@ class HTMLPurifier_ConfigSchema {
     */
    static function defineValueAliases($namespace, $name, $aliases) {
        $def =& HTMLPurifier_ConfigSchema::instance();
-        if (!isset($def->info[$namespace][$name])) {
+        if (HTMLPURIFIER_SCHEMA_STRICT && !isset($def->info[$namespace][$name])) {
            trigger_error('Cannot set value alias for non-existant directive',
                E_USER_ERROR);
            return;
        }
        foreach ($aliases as $alias => $real) {
-            if (!$def->info[$namespace][$name] !== true &&
-                !isset($def->info[$namespace][$name]->allowed[$real])
-            ) {
-                trigger_error('Cannot define alias to value that is not allowed',
-                    E_USER_ERROR);
-                return;
-            }
-            if (isset($def->info[$namespace][$name]->allowed[$alias])) {
-                trigger_error('Cannot define alias over allowed value',
-                    E_USER_ERROR);
-                return;
+            if (HTMLPURIFIER_SCHEMA_STRICT) {
+                if (!$def->info[$namespace][$name] !== true &&
+                    !isset($def->info[$namespace][$name]->allowed[$real])
+                ) {
+                    trigger_error('Cannot define alias to value that is not allowed',
+                        E_USER_ERROR);
+                    return;
+                }
+                if (isset($def->info[$namespace][$name]->allowed[$alias])) {
+                    trigger_error('Cannot define alias over allowed value',
+                        E_USER_ERROR);
+                    return;
+                }
            }
            $def->info[$namespace][$name]->aliases[$alias] = $real;
        }
@@ -230,14 +247,14 @@ class HTMLPurifier_ConfigSchema {
     */
    static function defineAllowedValues($namespace, $name, $allowed_values) {
        $def =& HTMLPurifier_ConfigSchema::instance();
-        if (!isset($def->info[$namespace][$name])) {
+        if (HTMLPURIFIER_SCHEMA_STRICT && !isset($def->info[$namespace][$name])) {
            trigger_error('Cannot define allowed values for undefined directive',
                E_USER_ERROR);
            return;
        }
        $directive =& $def->info[$namespace][$name];
        $type = $directive->type;
-        if ($type != 'string' && $type != 'istring') {
+        if (HTMLPURIFIER_SCHEMA_STRICT && $type != 'string' && $type != 'istring') {
            trigger_error('Cannot define allowed values for directive whose type is not string',
                E_USER_ERROR);
            return;
@@ -248,8 +265,11 @@ class HTMLPurifier_ConfigSchema {
        foreach ($allowed_values as $value) {
            $directive->allowed[$value] = true;
        }
-        if ($def->defaults[$namespace][$name] !== null &&
-            !isset($directive->allowed[$def->defaults[$namespace][$name]])) {
+        if (
+            HTMLPURIFIER_SCHEMA_STRICT &&
+            $def->defaults[$namespace][$name] !== null &&
+            !isset($directive->allowed[$def->defaults[$namespace][$name]])
+        ) {
            trigger_error('Default value must be in allowed range of variables',
                E_USER_ERROR);
            $directive->allowed = true; // undo undo!
@@ -267,30 +287,32 @@ class HTMLPurifier_ConfigSchema {
     */
    static function defineAlias($namespace, $name, $new_namespace, $new_name) {
        $def =& HTMLPurifier_ConfigSchema::instance();
-        if (!isset($def->info[$namespace])) {
-            trigger_error('Cannot define directive alias in undefined namespace',
-                E_USER_ERROR);
-            return;
-        }
-        if (!ctype_alnum($name)) {
-            trigger_error('Directive name must be alphanumeric',
-                E_USER_ERROR);
-            return;
-        }
-        if (isset($def->info[$namespace][$name])) {
-            trigger_error('Cannot define alias over directive',
-                E_USER_ERROR);
-            return;
-        }
-        if (!isset($def->info[$new_namespace][$new_name])) {
-            trigger_error('Cannot define alias to undefined directive',
-                E_USER_ERROR);
-            return;
-        }
-        if ($def->info[$new_namespace][$new_name]->class == 'alias') {
-            trigger_error('Cannot define alias to alias',
-                E_USER_ERROR);
-            return;
+        if (HTMLPURIFIER_SCHEMA_STRICT) {
+            if (!isset($def->info[$namespace])) {
+                trigger_error('Cannot define directive alias in undefined namespace',
+                    E_USER_ERROR);
+                return;
+            }
+            if (!ctype_alnum($name)) {
+                trigger_error('Directive name must be alphanumeric',
+                    E_USER_ERROR);
+                return;
+            }
+            if (isset($def->info[$namespace][$name])) {
+                trigger_error('Cannot define alias over directive',
+                    E_USER_ERROR);
+                return;
+            }
+            if (!isset($def->info[$new_namespace][$new_name])) {
+                trigger_error('Cannot define alias to undefined directive',
+                    E_USER_ERROR);
+                return;
+            }
+            if ($def->info[$new_namespace][$new_name]->class == 'alias') {
+                trigger_error('Cannot define alias to alias',
+                    E_USER_ERROR);
+                return;
+            }
        }
        $def->info[$namespace][$name] =
            new HTMLPurifier_ConfigDef_DirectiveAlias(
@@ -313,8 +335,10 @@ class HTMLPurifier_ConfigSchema {
                return $var;
            case 'istring':
            case 'string':
+            case 'text': // no difference, just is longer/multiple line string
+            case 'itext':
                if (!is_string($var)) break;
-                if ($type === 'istring') $var = strtolower($var);
+                if ($type === 'istring' || $type === 'itext') $var = strtolower($var);
                return $var;
            case 'int':
                if (is_string($var) && ctype_digit($var)) $var = (int) $var;
@@ -345,9 +369,13 @@ class HTMLPurifier_ConfigSchema {
                    // a single empty string item, but having an empty
                    // array is more intuitive
                    if ($var == '') return array();
-                    // simplistic string to array method that only works
-                    // for simple lists of tag names or alphanumeric characters
-                    $var = explode(',',$var);
+                    if (strpos($var, "\n") === false && strpos($var, "\r") === false) {
+                        // simplistic string to array method that only works
+                        // for simple lists of tag names or alphanumeric characters
+                        $var = explode(',',$var);
+                    } else {
+                        $var = preg_split('/(,|[\n\r]+)/', $var);
+                    }
                    // remove spaces
                    foreach ($var as $i => $j) $var[$i] = trim($j);
                    if ($type === 'hash') {
@@ -388,6 +416,7 @@ class HTMLPurifier_ConfigSchema {
     * Takes an absolute path and munges it into a more manageable relative path
     */
    function mungeFilename($filename) {
+        if (!HTMLPURIFIER_SCHEMA_STRICT) return $filename;
        $offset = strrpos($filename, 'HTMLPurifier');
        $filename = substr($filename, $offset);
        $filename = str_replace('\\', '/', $filename);
--- a/library/HTMLPurifier/ContentSets.php
+++ b/library/HTMLPurifier/ContentSets.php
@@ -5,6 +5,7 @@ require_once 'HTMLPurifier/ChildDef.php';
 require_once 'HTMLPurifier/ChildDef/Empty.php';
 require_once 'HTMLPurifier/ChildDef/Required.php';
 require_once 'HTMLPurifier/ChildDef/Optional.php';
+require_once 'HTMLPurifier/ChildDef/Custom.php';

 // NOT UNIT TESTED!!!

--- a/library/HTMLPurifier/DefinitionCache/Serializer.php
+++ b/library/HTMLPurifier/DefinitionCache/Serializer.php
@@ -99,7 +99,7 @@ class HTMLPurifier_DefinitionCache_Serializer extends
     */
    function generateBaseDirectoryPath($config) {
        $base = $config->get('Cache', 'SerializerPath');
-        $base = is_null($base) ? dirname(__FILE__) . '/Serializer' : $base;
+        $base = is_null($base) ? HTMLPURIFIER_PREFIX . '/HTMLPurifier/DefinitionCache/Serializer' : $base;
        return $base;
    }
    
--- a/library/HTMLPurifier/EntityLookup.php
+++ b/library/HTMLPurifier/EntityLookup.php
@@ -19,7 +19,7 @@ class HTMLPurifier_EntityLookup {
     */
    function setup($file = false) {
        if (!$file) {
-            $file = dirname(__FILE__) . '/EntityLookup/entities.ser';
+            $file = HTMLPURIFIER_PREFIX . '/HTMLPurifier/EntityLookup/entities.ser';
        }
        $this->table = unserialize(file_get_contents($file));
    }
--- a/library/HTMLPurifier/HTMLDefinition.php
+++ b/library/HTMLPurifier/HTMLDefinition.php
@@ -110,12 +110,13 @@ HTMLPurifier_ConfigSchema::define(
 ');

 HTMLPurifier_ConfigSchema::define(
-    'HTML', 'Allowed', null, 'string/null', '
+    'HTML', 'Allowed', null, 'itext/null', '
 <p>
    This is a convenience directive that rolls the functionality of
    %HTML.AllowedElements and %HTML.AllowedAttributes into one directive.
    Specify elements and attributes that are allowed using:
-    <code>element1[attr1|attr2],element2...</code>.
+    <code>element1[attr1|attr2],element2...</code>. You can also use
+    newlines instead of commas to separate elements.
 </p>
 <p>
    <strong>Warning</strong>:
@@ -235,13 +236,26 @@ class HTMLPurifier_HTMLDefinition extends HTMLPurifier_Definition
    /**
     * Adds a custom element to your HTML definition
     * @note See HTMLPurifier_HTMLModule::addElement for detailed 
-     *       parameter descriptions.
+     *       parameter and return value descriptions.
     */
-    function addElement($element_name, $type, $contents, $attr_collections, $attributes) {
+    function &addElement($element_name, $type, $contents, $attr_collections, $attributes) {
        $module =& $this->getAnonymousModule();
        // assume that if the user is calling this, the element
        // is safe. This may not be a good idea
-        $module->addElement($element_name, true, $type, $contents, $attr_collections, $attributes);
+        $element =& $module->addElement($element_name, true, $type, $contents, $attr_collections, $attributes);
+        return $element;
+    }
+    
+    /**
+     * Adds a blank element to your HTML definition, for overriding
+     * existing behavior
+     * @note See HTMLPurifier_HTMLModule::addBlankElement for detailed
+     *       parameter and return value descriptions.
+     */
+    function &addBlankElement($element_name) {
+        $module  =& $this->getAnonymousModule();
+        $element =& $module->addBlankElement($element_name);
+        return $element;
    }
    
    /**
@@ -329,7 +343,7 @@ class HTMLPurifier_HTMLDefinition extends HTMLPurifier_Definition
        if (isset($this->info_content_sets['Block'][$block_wrapper])) {
            $this->info_block_wrapper = $block_wrapper;
        } else {
-            trigger_error('Cannot use non-block element as block wrapper.',
+            trigger_error('Cannot use non-block element as block wrapper',
                E_USER_ERROR);
        }
        
@@ -339,7 +353,7 @@ class HTMLPurifier_HTMLDefinition extends HTMLPurifier_Definition
            $this->info_parent = $parent;
            $this->info_parent_def = $def;
        } else {
-            trigger_error('Cannot use unrecognized element as parent.',
+            trigger_error('Cannot use unrecognized element as parent',
                E_USER_ERROR);
            $this->info_parent_def = $this->manager->getElement($this->info_parent, true);
        }
@@ -426,8 +440,9 @@ class HTMLPurifier_HTMLDefinition extends HTMLPurifier_Definition
        $elements = array();
        $attributes = array();
        
-        $chunks = explode(',', $list);
+        $chunks = preg_split('/(,|[\n\r]+)/', $list);
        foreach ($chunks as $chunk) {
+            if (empty($chunk)) continue;
            // remove TinyMCE element control characters
            if (!strpos($chunk, '[')) {
                $element = $chunk;
--- a/library/HTMLPurifier/HTMLModule/Object.php
+++ b/library/HTMLPurifier/HTMLModule/Object.php
@@ -0,0 +1,47 @@
+<?php
+
+require_once 'HTMLPurifier/HTMLModule.php';
+
+/**
+ * XHTML 1.1 Object Module, defines elements for generic object inclusion
+ * @warning Users will commonly use <embed> to cater to legacy browsers: this
+ *      module does not allow this sort of behavior
+ */
+class HTMLPurifier_HTMLModule_Object extends HTMLPurifier_HTMLModule
+{
+    
+    var $name = 'Object';
+    
+    function HTMLPurifier_HTMLModule_Object() {
+        
+        $this->addElement('object', false, 'Inline', 'Optional: #PCDATA | Flow | param', 'Common', 
+            array(
+                'archive' => 'URI',
+                'classid' => 'URI',
+                'codebase' => 'URI',
+                'codetype' => 'Text',
+                'data' => 'URI',
+                'declare' => 'Bool#declare',
+                'height' => 'Length',
+                'name' => 'CDATA',
+                'standby' => 'Text',
+                'tabindex' => 'Number',
+                'type' => 'ContentType',
+                'width' => 'Length'
+            )
+        );
+
+        $this->addElement('param', false, false, 'Empty', false,
+            array(
+                'id' => 'ID',
+                'name*' => 'Text',
+                'type' => 'Text',
+                'value' => 'Text',
+                'valuetype' => 'Enum#data,ref,object'
+           )
+        );
+    
+    }
+    
+}
+
--- a/library/HTMLPurifier/HTMLModule/Ruby.php
+++ b/library/HTMLPurifier/HTMLModule/Ruby.php
@@ -0,0 +1,28 @@
+<?php
+
+require_once 'HTMLPurifier/HTMLModule.php';
+
+/**
+ * XHTML 1.1 Ruby Annotation Module, defines elements that indicate
+ * short runs of text alongside base text for annotation or pronounciation.
+ */
+class HTMLPurifier_HTMLModule_Ruby extends HTMLPurifier_HTMLModule
+{
+    
+    var $name = 'Ruby';
+    
+    function HTMLPurifier_HTMLModule_Ruby() {
+        $this->addElement('ruby', true, 'Inline',
+            'Custom: ((rb, (rt | (rp, rt, rp))) | (rbc, rtc, rtc?))',
+            'Common');
+        $this->addElement('rbc', true, false, 'Required: rb', 'Common');
+        $this->addElement('rtc', true, false, 'Required: rt', 'Common');
+        $rb =& $this->addElement('rb', true, false, 'Inline', 'Common');
+        $rb->excludes = array('ruby' => true);
+        $rt =& $this->addElement('rt', true, false, 'Inline', 'Common', array('rbspan' => 'Number'));
+        $rt->excludes = array('ruby' => true);
+        $this->addElement('rp', true, false, 'Optional: #PCDATA', 'Common');
+    }
+    
+}
+
--- a/library/HTMLPurifier/HTMLModule/Tidy/XHTMLAndHTML4.php
+++ b/library/HTMLPurifier/HTMLModule/Tidy/XHTMLAndHTML4.php
@@ -13,6 +13,8 @@ require_once 'HTMLPurifier/AttrTransform/Length.php';
 require_once 'HTMLPurifier/AttrTransform/ImgSpace.php';
 require_once 'HTMLPurifier/AttrTransform/EnumToCSS.php';

+require_once 'HTMLPurifier/ChildDef/StrictBlockquote.php';
+
 class HTMLPurifier_HTMLModule_Tidy_XHTMLAndHTML4 extends
      HTMLPurifier_HTMLModule_Tidy
 {
@@ -188,5 +190,17 @@ class HTMLPurifier_HTMLModule_Tidy_Strict extends
 {
    var $name = 'Tidy_Strict';
    var $defaultLevel = 'light';
+    
+    function makeFixes() {
+        $r = parent::makeFixes();
+        $r['blockquote#content_model_type'] = 'strictblockquote';
+        return $r;
+    }
+    
+    var $defines_child_def = true;
+    function getChildDef($def) {
+        if ($def->content_model_type != 'strictblockquote') return parent::getChildDef($def);
+        return new HTMLPurifier_ChildDef_StrictBlockquote($def->content_model);
+    }
 }

--- a/library/HTMLPurifier/HTMLModule/Tidy/XHTMLStrict.php
+++ b/library/HTMLPurifier/HTMLModule/Tidy/XHTMLStrict.php
@@ -1,26 +0,0 @@
-<?php
-
-require_once 'HTMLPurifier/HTMLModule/Tidy.php';
-require_once 'HTMLPurifier/ChildDef/StrictBlockquote.php';
-
-class HTMLPurifier_HTMLModule_Tidy_XHTMLStrict extends
-      HTMLPurifier_HTMLModule_Tidy
-{
-    
-    var $name = 'Tidy_XHTMLStrict';
-    var $defaultLevel = 'light';
-    
-    function makeFixes() {
-        $r = array();
-        $r['blockquote#content_model_type'] = 'strictblockquote';
-        return $r;
-    }
-    
-    var $defines_child_def = true;
-    function getChildDef($def) {
-        if ($def->content_model_type != 'strictblockquote') return false;
-        return new HTMLPurifier_ChildDef_StrictBlockquote($def->content_model);
-    }
-    
-}
-
--- a/library/HTMLPurifier/HTMLModuleManager.php
+++ b/library/HTMLPurifier/HTMLModuleManager.php
@@ -28,12 +28,13 @@ require_once 'HTMLPurifier/HTMLModule/Target.php';
 require_once 'HTMLPurifier/HTMLModule/Scripting.php';
 require_once 'HTMLPurifier/HTMLModule/XMLCommonAttributes.php';
 require_once 'HTMLPurifier/HTMLModule/NonXMLCommonAttributes.php';
+require_once 'HTMLPurifier/HTMLModule/Ruby.php';
+require_once 'HTMLPurifier/HTMLModule/Object.php';

 // tidy modules
 require_once 'HTMLPurifier/HTMLModule/Tidy.php';
 require_once 'HTMLPurifier/HTMLModule/Tidy/XHTMLAndHTML4.php';
 require_once 'HTMLPurifier/HTMLModule/Tidy/XHTML.php';
-require_once 'HTMLPurifier/HTMLModule/Tidy/XHTMLStrict.php';
 require_once 'HTMLPurifier/HTMLModule/Tidy/Proprietary.php';

 HTMLPurifier_ConfigSchema::define(
@@ -171,7 +172,7 @@ class HTMLPurifier_HTMLModuleManager
        $common = array(
            'CommonAttributes', 'Text', 'Hypertext', 'List',
            'Presentation', 'Edit', 'Bdo', 'Tables', 'Image',
-            'StyleAttribute', 'Scripting'
+            'StyleAttribute', 'Scripting', 'Object'
        );
        $transitional = array('Legacy', 'Target');
        $xml = array('XMLCommonAttributes');
@@ -207,7 +208,7 @@ class HTMLPurifier_HTMLModuleManager
        $this->doctypes->register(
            'XHTML 1.0 Strict', true,
            array_merge($common, $xml, $non_xml),
-            array('Tidy_Strict', 'Tidy_XHTML', 'Tidy_XHTMLStrict', 'Tidy_Proprietary'),
+            array('Tidy_Strict', 'Tidy_XHTML', 'Tidy_Strict', 'Tidy_Proprietary'),
            array(),
            '-//W3C//DTD XHTML 1.0 Strict//EN',
            'http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd'
@@ -215,8 +216,8 @@ class HTMLPurifier_HTMLModuleManager
        
        $this->doctypes->register(
            'XHTML 1.1', true,
-            array_merge($common, $xml),
-            array('Tidy_Strict', 'Tidy_XHTML', 'Tidy_Proprietary'), // Tidy_XHTML1_1
+            array_merge($common, $xml, array('Ruby')),
+            array('Tidy_Strict', 'Tidy_XHTML', 'Tidy_Proprietary', 'Tidy_Strict'), // Tidy_XHTML1_1
            array(),
            '-//W3C//DTD XHTML 1.1//EN',
            'http://www.w3.org/TR/xhtml11/DTD/xhtml11.dtd'
--- a/library/HTMLPurifier/IDAccumulator.php
+++ b/library/HTMLPurifier/IDAccumulator.php
@@ -1,11 +1,15 @@
 <?php

+HTMLPurifier_ConfigSchema::define(
+    'Attr', 'IDBlacklist', array(), 'list',
+    'Array of IDs not allowed in the document.'
+);
+
 /**
 * Component of HTMLPurifier_AttrContext that accumulates IDs to prevent dupes
 * @note In Slashdot-speak, dupe means duplicate.
- * @note This class does not accept $config or $context, thus, it is the
- *       burden of the callee to register the appropriate errors or
- *       configuration.
+ * @note The default constructor does not accept $config or $context objects:
+ *       use must use the static build() factory method to perform initialization.
 */
 class HTMLPurifier_IDAccumulator
 {
@@ -16,6 +20,19 @@ class HTMLPurifier_IDAccumulator
     */
    var $ids = array();
    
+    /**
+     * Builds an IDAccumulator, also initializing the default blacklist
+     * @param $config Instance of HTMLPurifier_Config
+     * @param $context Instance of HTMLPurifier_Context
+     * @return Fully initialized HTMLPurifier_IDAccumulator
+     * @static
+     */
+    static function build($config, &$context) {
+        $id_accumulator = new HTMLPurifier_IDAccumulator();
+        $id_accumulator->load($config->get('Attr', 'IDBlacklist'));
+        return $id_accumulator;
+    }
+    
    /**
     * Add an ID to the lookup table.
     * @param $id ID to be added.
--- a/library/HTMLPurifier/Injector.php
+++ b/library/HTMLPurifier/Injector.php
@@ -4,10 +4,18 @@
 * Injects tokens into the document while parsing for well-formedness.
 * This enables "formatter-like" functionality such as auto-paragraphing,
 * smiley-ification and linkification to take place.
+ * 
+ * @todo Allow injectors to request a re-run on their output. This 
+ *       would help if an operation is recursive.
 */
 class HTMLPurifier_Injector
 {
    
+    /**
+     * Advisory name of injector, this is for friendly error messages
+     */
+    var $name;
+    
    /**
     * Amount of tokens the injector needs to skip + 1. Because
     * the decrement is the first thing that happens, this needs to
@@ -40,16 +48,37 @@ class HTMLPurifier_Injector
    var $inputIndex;
    
    /**
-     * Prepares the injector by giving it the config and context objects,
-     * so that important variables can be extracted and not passed via
-     * parameter constantly. Remember: always instantiate a new injector
-     * when handling a set of HTML.
+     * Array of elements and attributes this injector creates and therefore
+     * need to be allowed by the definition. Takes form of
+     * array('element' => array('attr', 'attr2'), 'element2')
+     */
+    var $needed = array();
+    
+    /**
+     * Prepares the injector by giving it the config and context objects:
+     * this allows references to important variables to be made within
+     * the injector. This function also checks if the HTML environment
+     * will work with the Injector: if p tags are not allowed, the
+     * Auto-Paragraphing injector should not be enabled.
+     * @param $config Instance of HTMLPurifier_Config
+     * @param $context Instance of HTMLPurifier_Context
+     * @return Boolean false if success, string of missing needed element/attribute if failure
     */
    function prepare($config, &$context) {
        $this->htmlDefinition = $config->getHTMLDefinition();
+        // perform $needed checks
+        foreach ($this->needed as $element => $attributes) {
+            if (is_int($element)) $element = $attributes;
+            if (!isset($this->htmlDefinition->info[$element])) return $element;
+            if (!is_array($attributes)) continue;
+            foreach ($attributes as $name) {
+                if (!isset($this->htmlDefinition->info[$element]->attr[$name])) return "$element.$name";
+            }
+        }
        $this->currentNesting =& $context->get('CurrentNesting');
        $this->inputTokens    =& $context->get('InputTokens');
        $this->inputIndex     =& $context->get('InputIndex');
+        return false;
    }
    
    /**
@@ -74,12 +103,19 @@ class HTMLPurifier_Injector
    /**
     * Handler that is called when a text token is processed
     */
-    function handleText(&$token, $config, &$context) {}
+    function handleText(&$token) {}
    
    /**
-     * Handler that is called when a start token is processed
+     * Handler that is called when a start or empty token is processed
     */
-    function handleStart(&$token, $config, &$context) {}
+    function handleElement(&$token) {}
+    
+    /**
+     * Notifier that is called when an end token is processed
+     * @note This differs from handlers in that the token is read-only
+     */
+    function notifyEnd($token) {}
+    
    
 }

--- a/library/HTMLPurifier/Injector/AutoParagraph.php
+++ b/library/HTMLPurifier/Injector/AutoParagraph.php
@@ -6,15 +6,28 @@ HTMLPurifier_ConfigSchema::define(
    'AutoFormat', 'AutoParagraph', false, 'bool', '
 <p>
  This directive turns on auto-paragraphing, where double newlines are
-  converted in to paragraphs whenever possible. Auto-paragraphing
-  applies when:
+  converted in to paragraphs whenever possible. Auto-paragraphing:
 </p>
 <ul>
-  <li>There are inline elements or text in the root node</li>
-  <li>There are inline elements or text with double newlines or
-      block elements in nodes that allow paragraph tags</li>
-  <li>There are double newlines in paragraph tags</li>
+  <li>Always applies to inline elements or text in the root node,</li>
+  <li>Applies to inline elements or text with double newlines in nodes
+      that allow paragraph tags,</li>
+  <li>Applies to double newlines in paragraph tags</li>
 </ul>
+<p>
+  <code>p</code> tags must be allowed for this directive to take effect.
+  We do not use <code>br</code> tags for paragraphing, as that is
+  semantically incorrect.
+</p>
+<p>
+  To prevent auto-paragraphing as a content-producer, refrain from using
+  double-newlines except to specify a new paragraph or in contexts where
+  it has special meaning (whitespace usually has no meaning except in
+  tags like <code>pre</code>, so this should not be difficult.) To prevent
+  the paragraphing of inline text adjacent to block elements, wrap them
+  in <code>div</code> tags (the behavior is slightly different outside of
+  the root node.)
+</p>
 <p>
  This directive has been available since 2.0.1.
 </p>
@@ -27,13 +40,16 @@ HTMLPurifier_ConfigSchema::define(
 class HTMLPurifier_Injector_AutoParagraph extends HTMLPurifier_Injector
 {
    
+    var $name = 'AutoParagraph';
+    var $needed = array('p');
+    
    function _pStart() {
        $par = new HTMLPurifier_Token_Start('p');
        $par->armor['MakeWellFormed_TagClosedError'] = true;
        return $par;
    }
    
-    function handleText(&$token, $config, &$context) {
+    function handleText(&$token) {
        $text = $token->data;
        if (empty($this->currentNesting)) {
            if (!$this->allowsElement('p')) return;
@@ -54,19 +70,27 @@ class HTMLPurifier_Injector_AutoParagraph extends HTMLPurifier_Injector
                $ok = false;
                // test if up-coming tokens are either block or have
                // a double newline in them
+                $nesting = 0;
                for ($i = $this->inputIndex + 1; isset($this->inputTokens[$i]); $i++) {
                    if ($this->inputTokens[$i]->type == 'start'){
                        if (!$this->_isInline($this->inputTokens[$i])) {
-                            $ok = true;
+                            // we haven't found a double-newline, and
+                            // we've hit a block element, so don't paragraph
+                            $ok = false;
+                            break;
                        }
-                        break;
+                        $nesting++;
+                    }
+                    if ($this->inputTokens[$i]->type == 'end') {
+                        if ($nesting <= 0) break;
+                        $nesting--;
                    }
-                    if ($this->inputTokens[$i]->type == 'end') break;
                    if ($this->inputTokens[$i]->type == 'text') {
+                        // found it!
                        if (strpos($this->inputTokens[$i]->data, "\n\n") !== false) {
                            $ok = true;
+                            break;
                        }
-                        if (!$this->inputTokens[$i]->is_whitespace) break;
                    }
                }
                if ($ok) {
@@ -79,7 +103,7 @@ class HTMLPurifier_Injector_AutoParagraph extends HTMLPurifier_Injector
        
    }
    
-    function handleStart(&$token, $config, &$context) {
+    function handleElement(&$token) {
        // check if we're inside a tag already
        if (!empty($this->currentNesting)) {
            if ($this->allowsElement('p')) {
@@ -88,11 +112,19 @@ class HTMLPurifier_Injector_AutoParagraph extends HTMLPurifier_Injector
                // this token is already paragraph, abort
                if ($token->name == 'p') return;
                
-                // check if this token is adjacent to the parent
-                if ($this->inputTokens[$this->inputIndex - 1]->type != 'start') {
+                // this token is a block level, abort
+                if (!$this->_isInline($token)) return;
+                
+                // check if this token is adjacent to the parent token
+                $prev = $this->inputTokens[$this->inputIndex - 1];
+                if ($prev->type != 'start') {
                    // not adjacent, we can abort early
                    // add lead paragraph tag if our token is inline
-                    if ($this->_isInline($token)) {
+                    // and the previous tag was an end paragraph
+                    if (
+                        $prev->name == 'p' && $prev->type == 'end' &&
+                        $this->_isInline($token)
+                    ) {
                        $token = array($this->_pStart(), $token);
                    }
                    return;
@@ -105,8 +137,8 @@ class HTMLPurifier_Injector_AutoParagraph extends HTMLPurifier_Injector
                $ok = false;
                // maintain a mini-nesting counter, this lets us bail out
                // early if possible
-                $j = 2; // current nesting, is two due to parent and this start
-                for ($i = $this->inputIndex + 1; isset($this->inputTokens[$i]); $i++) {
+                $j = 1; // current nesting, one is due to parent (we recalculate current token)
+                for ($i = $this->inputIndex; isset($this->inputTokens[$i]); $i++) {
                    if ($this->inputTokens[$i]->type == 'start') $j++;
                    if ($this->inputTokens[$i]->type == 'end') $j--;
                    if ($this->inputTokens[$i]->type == 'text') {
@@ -150,7 +182,14 @@ class HTMLPurifier_Injector_AutoParagraph extends HTMLPurifier_Injector
        $needs_start = false;
        $needs_end   = false;
        
-        for ($i = 0, $c = count($raw_paragraphs); $i < $c; $i++) {
+        $c = count($raw_paragraphs);
+        if ($c == 1) {
+            // there were no double-newlines, abort quickly
+            $result[] = new HTMLPurifier_Token_Text($data);
+            return;
+        }
+        
+        for ($i = 0; $i < $c; $i++) {
            $par = $raw_paragraphs[$i];
            if (trim($par) !== '') {
                $paragraphs[] = $par;
--- a/library/HTMLPurifier/Injector/Linkify.php
+++ b/library/HTMLPurifier/Injector/Linkify.php
@@ -6,7 +6,8 @@ HTMLPurifier_ConfigSchema::define(
    'AutoFormat', 'Linkify', false, 'bool', '
 <p>
  This directive turns on linkification, auto-linking http, ftp and
-  https URLs. This directive has been available since 2.0.1.
+  https URLs. <code>a</code> tags with the <code>href</code> attribute
+  must be allowed. This directive has been available since 2.0.1.
 </p>
 ');

@@ -16,7 +17,10 @@ HTMLPurifier_ConfigSchema::define(
 class HTMLPurifier_Injector_Linkify extends HTMLPurifier_Injector
 {
    
-    function handleText(&$token, $config, &$context) {
+    var $name = 'Linkify';
+    var $needed = array('a' => array('href'));
+    
+    function handleText(&$token) {
        if (!$this->allowsElement('a')) return;
        
        if (strpos($token->data, '://') === false) {
--- a/library/HTMLPurifier/Injector/PurifierLinkify.php
+++ b/library/HTMLPurifier/Injector/PurifierLinkify.php
@@ -6,8 +6,9 @@ HTMLPurifier_ConfigSchema::define(
    'AutoFormat', 'PurifierLinkify', false, 'bool', '
 <p>
  Internal auto-formatter that converts configuration directives in
-  syntax <a>%Namespace.Directive</a> to links. This directive has been available
-  since 2.0.1.
+  syntax <a>%Namespace.Directive</a> to links. <code>a</code> tags
+  with the <code>href</code> attribute must be allowed.
+  This directive has been available since 2.0.1.
 </p>
 ');

@@ -27,14 +28,16 @@ HTMLPurifier_ConfigSchema::define(
 class HTMLPurifier_Injector_PurifierLinkify extends HTMLPurifier_Injector
 {
    
+    var $name = 'PurifierLinkify';
    var $docURL;
+    var $needed = array('a' => array('href'));
    
    function prepare($config, &$context) {
-        parent::prepare($config, $context);
        $this->docURL = $config->get('AutoFormatParam', 'PurifierLinkifyDocURL');
+        return parent::prepare($config, $context);
    }
    
-    function handleText(&$token, $config, &$context) {
+    function handleText(&$token) {
        if (!$this->allowsElement('a')) return;
        if (strpos($token->data, '%') === false) return;
        
--- a/library/HTMLPurifier/Language/messages/en.php
+++ b/library/HTMLPurifier/Language/messages/en.php
@@ -28,7 +28,7 @@ $messages = array(
 'Strategy_RemoveForeignElements: Foreign element to text'    => 'Unrecognized $CurrentToken.Serialized tag converted to text',
 'Strategy_RemoveForeignElements: Foreign element removed'    => 'Unrecognized $CurrentToken.Serialized tag removed',
 'Strategy_RemoveForeignElements: Comment removed'            => 'Comment containing "$CurrentToken.Data" removed',
-'Strategy_RemoveForeignElements: Script removed'             => 'Script removed',
+'Strategy_RemoveForeignElements: Foreign meta element removed' => 'Unrecognized $CurrentToken.Serialized meta tag and all descendants removed',
 'Strategy_RemoveForeignElements: Token removed to end'       => 'Tags and text starting from $1 element where removed to end',

 'Strategy_MakeWellFormed: Unnecessary end tag removed' => 'Unnecessary $CurrentToken.Serialized tag removed',
--- a/library/HTMLPurifier/LanguageFactory.php
+++ b/library/HTMLPurifier/LanguageFactory.php
@@ -82,7 +82,7 @@ class HTMLPurifier_LanguageFactory
     */
    function setup() {
        $this->validator = new HTMLPurifier_AttrDef_Lang();
-        $this->dir = dirname(__FILE__);
+        $this->dir = HTMLPURIFIER_PREFIX . '/HTMLPurifier';
    }
    
    /**
--- a/library/HTMLPurifier/Lexer.php
+++ b/library/HTMLPurifier/Lexer.php
@@ -13,11 +13,14 @@ if (version_compare(PHP_VERSION, "5", ">=")) {
 }

 HTMLPurifier_ConfigSchema::define(
-    'Core', 'AcceptFullDocuments', true, 'bool',
-    'This parameter determines whether or not the filter should accept full '.
-    'HTML documents, not just HTML fragments.  When on, it will '.
-    'drop all sections except the content between body.'
-);
+    'Core', 'ConvertDocumentToFragment', true, 'bool', '
+This parameter determines whether or not the filter should convert
+input that is a full document with html and body tags to a fragment
+of just the contents of a body tag. This parameter is simply something
+HTML Purifier can do during an edge-case: for most inputs, this
+processing is not necessary.
+');
+HTMLPurifier_ConfigSchema::defineAlias('Core', 'AcceptFullDocuments', 'Core', 'ConvertDocumentToFragment');

 HTMLPurifier_ConfigSchema::define(
    'Core', 'LexerImpl', null, 'mixed/null', '
@@ -66,6 +69,16 @@ HTMLPurifier_ConfigSchema::define(
 </p>
 ');

+HTMLPurifier_ConfigSchema::define(
+    'Core', 'AggressivelyFixLt', false, 'bool', '
+This directive enables aggressive pre-filter fixes HTML Purifier can
+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
+calls and one preg_replace call for every bit of HTML passed through here.
+It is not necessary and will have no effect for PHP 4.
+This directive has been available since 2.1.0.
+');
+
 /**
 * Forgivingly lexes HTML (SGML-style) markup into tokens.
 * 
@@ -179,6 +192,9 @@ class HTMLPurifier_Lexer
                return new HTMLPurifier_Lexer_DOMLex();
            case 'DirectLex':
                return new HTMLPurifier_Lexer_DirectLex();
+            case 'PH5P':
+                // experimental Lexer that must be manually included
+                return new HTMLPurifier_Lexer_PH5P();
            default:
                trigger_error("Cannot instantiate unrecognized Lexer type " . htmlspecialchars($lexer), E_USER_ERROR);
        }
@@ -303,7 +319,7 @@ class HTMLPurifier_Lexer
    function normalize($html, $config, &$context) {
        
        // extract body from document if applicable
-        if ($config->get('Core', 'AcceptFullDocuments')) {
+        if ($config->get('Core', 'ConvertDocumentToFragment')) {
            $html = $this->extractBody($html);
        }
        
--- a/library/HTMLPurifier/Lexer/DOMLex.php
+++ b/library/HTMLPurifier/Lexer/DOMLex.php
@@ -42,15 +42,18 @@ class HTMLPurifier_Lexer_DOMLex extends HTMLPurifier_Lexer
        
        $html = $this->normalize($html, $config, $context);
        
+        // attempt to armor stray angled brackets that cannot possibly
+        // form tags and thus are probably being used as emoticons
+        if ($config->get('Core', 'AggressivelyFixLt')) {
+            $char = '[^a-z!\/]';
+            $comment = "/<!--(.*?)(-->|\z)/is";
+            $html = preg_replace_callback($comment, array('HTMLPurifier_Lexer_DOMLex', 'callbackArmorCommentEntities'), $html);
+            $html = preg_replace("/<($char)/i", '&lt;\\1', $html);
+            $html = preg_replace_callback($comment, array('HTMLPurifier_Lexer_DOMLex', 'callbackUndoCommentSubst'), $html); // fix comments
+        }
+        
        // preprocess html, essential for UTF-8
-        $html =
-            '<!DOCTYPE html '.
-                'PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"'.
-                '"http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">'.
-            '<html><head>'.
-            '<meta http-equiv="Content-Type" content="text/html;'.
-                ' charset=utf-8" />'.
-            '</head><body><div>'.$html.'</div></body></html>';
+        $html = $this->wrapHTML($html, $config, $context);
        
        $doc = new DOMDocument();
        $doc->encoding = 'UTF-8'; // theoretically, the above has this covered
@@ -151,5 +154,41 @@ class HTMLPurifier_Lexer_DOMLex extends HTMLPurifier_Lexer
     */
    public function muteErrorHandler($errno, $errstr) {}
    
+    /**
+     * Callback function for undoing escaping of stray angled brackets
+     * in comments
+     */
+    static public function callbackUndoCommentSubst($matches) {
+        return '<!--' . strtr($matches[1], array('&amp;'=>'&','&lt;'=>'<')) . $matches[2];
+    }
+    
+    /**
+     * Callback function that entity-izes ampersands in comments so that
+     * callbackUndoCommentSubst doesn't clobber them
+     */
+    static public function callbackArmorCommentEntities($matches) {
+        return '<!--' . str_replace('&', '&amp;', $matches[1]) . $matches[2];
+    }
+    
+    /**
+     * Wraps an HTML fragment in the necessary HTML
+     */
+    function wrapHTML($html, $config, &$context) {
+        $def = $config->getDefinition('HTML');
+        $ret = '';
+        
+        if (!empty($def->doctype->dtdPublic) || !empty($def->doctype->dtdSystem)) {
+            $ret .= '<!DOCTYPE html ';
+            if (!empty($def->doctype->dtdPublic)) $ret .= 'PUBLIC "' . $def->doctype->dtdPublic . '" ';
+            if (!empty($def->doctype->dtdSystem)) $ret .= '"' . $def->doctype->dtdSystem . '" ';
+            $ret .= '>';
+        }
+        
+        $ret .= '<html><head>';
+        $ret .= '<meta http-equiv="Content-Type" content="text/html; charset=utf-8" />';
+        $ret .= '</head><body><div>'.$html.'</div></body></html>';
+        return $ret;
+    }
+    
 }

--- a/library/HTMLPurifier/Lexer/DirectLex.php
+++ b/library/HTMLPurifier/Lexer/DirectLex.php
@@ -150,11 +150,25 @@ class HTMLPurifier_Lexer_DirectLex extends HTMLPurifier_Lexer
                // We are in tag and it is well formed
                // Grab the internals of the tag
                $strlen_segment = $position_next_gt - $cursor;
+                
+                if ($strlen_segment < 1) {
+                    // there's nothing to process!
+                    $token = new HTMLPurifier_Token_Text('<');
+                    $cursor++;
+                    continue;
+                }
+                
                $segment = substr($html, $cursor, $strlen_segment);
                
+                if ($segment === false) {
+                    // somehow, we attempted to access beyond the end of
+                    // the string, defense-in-depth, reported by Nate Abele
+                    break;
+                }
+                
                // Check if it's a comment
                if (
-                    substr($segment, 0, 3) == '!--'
+                    substr($segment, 0, 3) === '!--'
                ) {
                    // re-determine segment length, looking for -->
                    $position_comment_end = strpos($html, '-->', $cursor);
@@ -204,7 +218,8 @@ class HTMLPurifier_Lexer_DirectLex extends HTMLPurifier_Lexer
                // Check leading character is alnum, if not, we may
                // have accidently grabbed an emoticon. Translate into
                // text and go our merry way
-                if (!ctype_alnum($segment[0])) {
+                if (!ctype_alpha($segment[0])) {
+                    // XML:  $segment[0] !== '_' && $segment[0] !== ':'
                    if ($e) $e->send(E_NOTICE, 'Lexer: Unescaped lt');
                    $token = new
                        HTMLPurifier_Token_Text(
@@ -228,7 +243,7 @@ class HTMLPurifier_Lexer_DirectLex extends HTMLPurifier_Lexer
                // trailing slash. Remember, we could have a tag like <br>, so
                // any later token processing scripts must convert improperly
                // classified EmptyTags from StartTags.
-                $is_self_closing= (strpos($segment,'/') === $strlen_segment-1);
+                $is_self_closing = (strrpos($segment,'/') === $strlen_segment-1);
                if ($is_self_closing) {
                    $strlen_segment--;
                    $segment = substr($segment, 0, $strlen_segment);
@@ -371,6 +386,7 @@ class HTMLPurifier_Lexer_DirectLex extends HTMLPurifier_Lexer
                    $value = $quoted_value;
                }
            }
+            if ($value === false) $value = '';
            return array($key => $value);
        }
        
@@ -385,7 +401,6 @@ class HTMLPurifier_Lexer_DirectLex extends HTMLPurifier_Lexer
        
        // infinite loop protection
        $loops = 0;
-        
        while(true) {
            
            // infinite loop protection
@@ -399,7 +414,6 @@ class HTMLPurifier_Lexer_DirectLex extends HTMLPurifier_Lexer
            }
            
            $cursor += ($value = strspn($string, $this->_whitespace, $cursor));
-            
            // grab the key
            
            $key_begin = $cursor; //we're currently at the start of the key
@@ -435,6 +449,11 @@ class HTMLPurifier_Lexer_DirectLex extends HTMLPurifier_Lexer
                $cursor++;
                $cursor += strspn($string, $this->_whitespace, $cursor);
                
+                if ($cursor === false) {
+                    $array[$key] = '';
+                    break;
+                }
+                
                // we might be in front of a quote right now
                
                $char = @$string[$cursor];
@@ -452,7 +471,14 @@ class HTMLPurifier_Lexer_DirectLex extends HTMLPurifier_Lexer
                    $value_end = $cursor;
                }
                
+                // we reached a premature end
+                if ($cursor === false) {
+                    $cursor = $size;
+                    $value_end = $cursor;
+                }
+                
                $value = substr($string, $value_begin, $value_end - $value_begin);
+                if ($value === false) $value = '';
                $array[$key] = $this->parseData($value);
                $cursor++;
                
--- a/library/HTMLPurifier/Lexer/PH5P.php
+++ b/library/HTMLPurifier/Lexer/PH5P.php
--- a/library/HTMLPurifier/Printer/ConfigForm.css
+++ b/library/HTMLPurifier/Printer/ConfigForm.css
@@ -1,7 +1,7 @@

 .hp-config {}

-.hp-config tbody th {text-align:right;}
+.hp-config tbody th {text-align:right; padding-right:0.5em;}
 .hp-config thead, .hp-config .namespace {background:#3C578C; color:#FFF;}
 .hp-config .namespace th {text-align:center;}
 .hp-config .verbose {display:none;}
--- a/library/HTMLPurifier/Printer/ConfigForm.php
+++ b/library/HTMLPurifier/Printer/ConfigForm.php
@@ -23,18 +23,55 @@ class HTMLPurifier_Printer_ConfigForm extends HTMLPurifier_Printer
     */
    var $name;
    
+    /**
+     * Whether or not to compress directive names, clipping them off
+     * after a certain amount of letters. False to disable or integer letters
+     * before clipping.
+     * @protected
+     */
+    var $compress = false;
+    
    /**
     * @param $name Form element name for directives to be stuffed into
     * @param $doc_url String documentation URL, will have fragment tagged on
+     * @param $compress Integer max length before compressing a directive name, set to false to turn off
     */
-    function HTMLPurifier_Printer_ConfigForm($name, $doc_url = null) {
+    function HTMLPurifier_Printer_ConfigForm(
+        $name, $doc_url = null, $compress = false
+    ) {
        parent::HTMLPurifier_Printer();
        $this->docURL = $doc_url;
        $this->name   = $name;
+        $this->compress = $compress;
+        // initialize sub-printers
        $this->fields['default']    = new HTMLPurifier_Printer_ConfigForm_default();
        $this->fields['bool']       = new HTMLPurifier_Printer_ConfigForm_bool();
    }
    
+    /**
+     * Sets default column and row size for textareas in sub-printers
+     * @param $cols Integer columns of textarea, null to use default
+     * @param $rows Integer rows of textarea, null to use default
+     */
+    function setTextareaDimensions($cols = null, $rows = null) {
+        if ($cols) $this->fields['default']->cols = $cols;
+        if ($rows) $this->fields['default']->rows = $rows;
+    }
+    
+    /**
+     * Retrieves styling, in case it is not accessible by webserver
+     */
+    function getCSS() {
+        return file_get_contents(HTMLPURIFIER_PREFIX . '/HTMLPurifier/Printer/ConfigForm.css');
+    }
+    
+    /**
+     * Retrieves JavaScript, in case it is not accessible by webserver
+     */
+    function getJavaScript() {
+        return file_get_contents(HTMLPURIFIER_PREFIX . '/HTMLPurifier/Printer/ConfigForm.js');
+    }
+    
    /**
     * Returns HTML output for a configuration form
     * @param $config Configuration object of current form state
@@ -63,14 +100,14 @@ class HTMLPurifier_Printer_ConfigForm extends HTMLPurifier_Printer
            $ret .= $this->renderNamespace($ns, $directives);
        }
        if ($render_controls) {
-             $ret .= $this->start('tfoot');
+             $ret .= $this->start('tbody');
             $ret .= $this->start('tr');
                 $ret .= $this->start('td', array('colspan' => 2, 'class' => 'controls'));
-                     $ret .= $this->elementEmpty('input', array('type' => 'Submit', 'value' => 'Submit'));
+                     $ret .= $this->elementEmpty('input', array('type' => 'submit', 'value' => 'Submit'));
                     $ret .= '[<a href="?">Reset</a>]';
                 $ret .= $this->end('td');
             $ret .= $this->end('tr');
-             $ret .= $this->end('tfoot');
+             $ret .= $this->end('tbody');
        }
        $ret .= $this->end('table');
        return $ret;
@@ -98,11 +135,12 @@ class HTMLPurifier_Printer_ConfigForm extends HTMLPurifier_Printer
                $ret .= $this->start('a', array('href' => $url));
            }
                $attr = array('for' => "{$this->name}:$ns.$directive");
+                
                // crop directive name if it's too long
-                if (strlen($directive) < 14) {
+                if (!$this->compress || (strlen($directive) < $this->compress)) {
                    $directive_disp = $directive;
                } else {
-                    $directive_disp = substr($directive, 0, 12) . '...';
+                    $directive_disp = substr($directive, 0, $this->compress - 2) . '...';
                    $attr['title'] = $directive;
                }
                
@@ -176,6 +214,8 @@ class HTMLPurifier_Printer_ConfigForm_NullDecorator extends HTMLPurifier_Printer
 * Swiss-army knife configuration form field printer
 */
 class HTMLPurifier_Printer_ConfigForm_default extends HTMLPurifier_Printer {
+    var $cols = 18;
+    var $rows = 5;
    function render($ns, $directive, $value, $name, $config) {
        $this->prepareGenerator($config);
        // this should probably be split up a little
@@ -190,12 +230,12 @@ class HTMLPurifier_Printer_ConfigForm_default extends HTMLPurifier_Printer {
                        $value[] = $val;
                    }
                case 'list':
-                    $value = implode(',', $value);
+                    $value = implode(PHP_EOL, $value);
                    break;
                case 'hash':
                    $nvalue = '';
                    foreach ($value as $i => $v) {
-                        $nvalue .= "$i:$v,";
+                        $nvalue .= "$i:$v" . PHP_EOL;
                    }
                    $value = $nvalue;
                    break;
@@ -220,6 +260,15 @@ class HTMLPurifier_Printer_ConfigForm_default extends HTMLPurifier_Printer {
                $ret .= $this->element('option', $val, $attr);
            }
            $ret .= $this->end('select');
+        } elseif (
+            $def->type == 'text' || $def->type == 'itext' ||
+            $def->type == 'list' || $def->type == 'hash' || $def->type == 'lookup'
+        ) {
+            $attr['cols'] = $this->cols;
+            $attr['rows'] = $this->rows;
+            $ret .= $this->start('textarea', $attr);
+            $ret .= $this->text($value);
+            $ret .= $this->end('textarea');
        } else {
            $attr['value'] = $value;
            $attr['type'] = 'text';
--- a/library/HTMLPurifier/Printer/HTMLDefinition.php
+++ b/library/HTMLPurifier/Printer/HTMLDefinition.php
@@ -102,6 +102,7 @@ class HTMLPurifier_Printer_HTMLDefinition extends HTMLPurifier_Printer
            $ret .= $this->element('td', $this->listifyTagLookup($lookup));
            $ret .= $this->end('tr');
        }
+        $ret .= $this->end('table');
        return $ret;
    }
    
@@ -179,7 +180,8 @@ class HTMLPurifier_Printer_HTMLDefinition extends HTMLPurifier_Printer
                    $def->validateChildren(array(), $this->config, $context);
                }
                $elements = $def->elements;
-            } elseif ($def->type == 'chameleon') {
+            }
+            if ($def->type == 'chameleon') {
                $attr['rowspan'] = 2;
            } elseif ($def->type == 'empty') {
                $elements = array();
--- a/library/HTMLPurifier/Strategy/FixNesting.php
+++ b/library/HTMLPurifier/Strategy/FixNesting.php
@@ -195,7 +195,7 @@ class HTMLPurifier_Strategy_FixNesting extends HTMLPurifier_Strategy
            //################################################################//
            // Process result by interpreting $result
            
-            if ($result === true) {
+            if ($result === true || $child_tokens === $result) {
                // leave the node as is
                
                // register start token as a parental node start
--- a/library/HTMLPurifier/Strategy/MakeWellFormed.php
+++ b/library/HTMLPurifier/Strategy/MakeWellFormed.php
@@ -36,28 +36,23 @@ class HTMLPurifier_Strategy_MakeWellFormed extends HTMLPurifier_Strategy
        
        $definition = $config->getHTMLDefinition();
        
-        // CurrentNesting
-        $this->currentNesting = array();
-        $context->register('CurrentNesting', $this->currentNesting);
-        
-        // InputIndex
-        $this->inputIndex = false;
-        $context->register('InputIndex', $this->inputIndex);
-        
-        // InputTokens
-        $context->register('InputTokens', $tokens);
-        $this->inputTokens =& $tokens;
-        
-        // OutputTokens
+        // local variables
        $result = array();
-        $this->outputTokens =& $result;
-        
-        // %Core.EscapeInvalidTags
-        $escape_invalid_tags = $config->get('Core', 'EscapeInvalidTags');
        $generator = new HTMLPurifier_Generator();
-        
+        $escape_invalid_tags = $config->get('Core', 'EscapeInvalidTags');
        $e =& $context->get('ErrorCollector', true);
        
+        // member variables
+        $this->currentNesting = array();
+        $this->inputIndex     = false;
+        $this->inputTokens    =& $tokens;
+        $this->outputTokens   =& $result;
+        
+        // context variables
+        $context->register('CurrentNesting', $this->currentNesting);
+        $context->register('InputIndex', $this->inputIndex);
+        $context->register('InputTokens', $tokens);
+        
        // -- begin INJECTOR --
        
        $this->injectors = array();
@@ -67,7 +62,8 @@ class HTMLPurifier_Strategy_MakeWellFormed extends HTMLPurifier_Strategy
        unset($injectors['Custom']); // special case
        foreach ($injectors as $injector => $b) {
            $injector = "HTMLPurifier_Injector_$injector";
-            if ($b) $this->injectors[] = new $injector;
+            if (!$b) continue;
+            $this->injectors[] = new $injector;
        }
        foreach ($custom_injectors as $injector) {
            if (is_string($injector)) {
@@ -87,9 +83,17 @@ class HTMLPurifier_Strategy_MakeWellFormed extends HTMLPurifier_Strategy
        // give the injectors references to the definition and context
        // variables for performance reasons
        foreach ($this->injectors as $i => $x) {
-            $this->injectors[$i]->prepare($config, $context);
+            $error = $this->injectors[$i]->prepare($config, $context);
+            if (!$error) continue;
+            list($injector) = array_splice($this->injectors, $i, 1);
+            $name = $injector->name;
+            trigger_error("Cannot enable $name injector because $error is not allowed", E_USER_WARNING);
        }
        
+        // warning: most foreach loops follow the convention $i => $x.
+        // be sure, for PHP4 compatibility, to only perform write operations
+        // directly referencing the object using $i: $x is only safe for reads
+        
        // -- end INJECTOR --
        
        $token = false;
@@ -100,6 +104,8 @@ class HTMLPurifier_Strategy_MakeWellFormed extends HTMLPurifier_Strategy
            // if all goes well, this token will be passed through unharmed
            $token = $tokens[$this->inputIndex];
            
+            //printTokens($tokens, $this->inputIndex);
+            
            foreach ($this->injectors as $i => $x) {
                if ($x->skip > 0) $this->injectors[$i]->skip--;
            }
@@ -109,7 +115,7 @@ class HTMLPurifier_Strategy_MakeWellFormed extends HTMLPurifier_Strategy
                if ($token->type === 'text') {
                     // injector handler code; duplicated for performance reasons
                     foreach ($this->injectors as $i => $x) {
-                         if (!$x->skip) $x->handleText($token, $config, $context);
+                         if (!$x->skip) $this->injectors[$i]->handleText($token);
                         if (is_array($token)) {
                             $this->currentInjector = $i;
                             break;
@@ -122,26 +128,24 @@ class HTMLPurifier_Strategy_MakeWellFormed extends HTMLPurifier_Strategy
            
            $info = $definition->info[$token->name]->child;
            
-            // quick checks:
-            // test if it claims to be a start tag but is empty
+            // quick tag checks: anything that's *not* an end tag
+            $ok = false;
            if ($info->type == 'empty' && $token->type == 'start') {
-                $result[] = new HTMLPurifier_Token_Empty($token->name, $token->attr);
-                continue;
-            }
-            // test if it claims to be empty but really is a start tag
-            if ($info->type != 'empty' && $token->type == 'empty' ) {
-                $result[] = new HTMLPurifier_Token_Start($token->name, $token->attr);
-                $result[] = new HTMLPurifier_Token_End($token->name);
-                continue;
-            }
-            // automatically insert empty tags
-            if ($token->type == 'empty') {
-                $result[] = $token;
-                continue;
-            }
-            
-            // start tags have precedence, so they get passed through...
-            if ($token->type == 'start') {
+                // test if it claims to be a start tag but is empty
+                $token = new HTMLPurifier_Token_Empty($token->name, $token->attr);
+                $ok = true;
+            } elseif ($info->type != 'empty' && $token->type == 'empty' ) {
+                // claims to be empty but really is a start tag
+                $token = array(
+                    new HTMLPurifier_Token_Start($token->name, $token->attr),
+                    new HTMLPurifier_Token_End($token->name)
+                );
+                $ok = true;
+            } elseif ($token->type == 'empty') {
+                // real empty token
+                $ok = true;
+            } elseif ($token->type == 'start') {
+                // start tag
                
                // ...unless they also have to close their parent
                if (!empty($this->currentNesting)) {
@@ -163,16 +167,18 @@ class HTMLPurifier_Strategy_MakeWellFormed extends HTMLPurifier_Strategy
                    
                    $this->currentNesting[] = $parent; // undo the pop
                }
-                
-                // injector handler code; duplicated for performance reasons
+                $ok = true;
+            }
+            
+            // injector handler code; duplicated for performance reasons
+            if ($ok) {
                foreach ($this->injectors as $i => $x) {
-                    if (!$x->skip) $x->handleStart($token, $config, $context);
+                    if (!$x->skip) $this->injectors[$i]->handleElement($token);
                    if (is_array($token)) {
                        $this->currentInjector = $i;
                        break;
                    }
                }
-                
                $this->processToken($token, $config, $context);
                continue;
            }
@@ -197,6 +203,9 @@ class HTMLPurifier_Strategy_MakeWellFormed extends HTMLPurifier_Strategy
            $current_parent = array_pop($this->currentNesting);
            if ($current_parent->name == $token->name) {
                $result[] = $token;
+                foreach ($this->injectors as $i => $x) {
+                    $this->injectors[$i]->notifyEnd($token);
+                }
                continue;
            }
            
@@ -233,16 +242,16 @@ class HTMLPurifier_Strategy_MakeWellFormed extends HTMLPurifier_Strategy
            
            // okay, we found it, close all the skipped tags
            // note that skipped tags contains the element we need closed
-            $size = count($skipped_tags);
-            for ($i = $size - 1; $i > 0; $i--) {
-                if ($e && !isset($skipped_tags[$i]->armor['MakeWellFormed_TagClosedError'])) {
+            for ($i = count($skipped_tags) - 1; $i >= 0; $i--) {
+                if ($i && $e && !isset($skipped_tags[$i]->armor['MakeWellFormed_TagClosedError'])) {
                    $e->send(E_NOTICE, 'Strategy_MakeWellFormed: Tag closed by element end', $skipped_tags[$i]);
                }
-                $result[] = new HTMLPurifier_Token_End($skipped_tags[$i]->name);
+                $result[] = $new_token = new HTMLPurifier_Token_End($skipped_tags[$i]->name);
+                foreach ($this->injectors as $j => $x) { // $j, not $i!!!
+                    $this->injectors[$j]->notifyEnd($new_token);
+                }
            }
            
-            $result[] = new HTMLPurifier_Token_End($skipped_tags[$i]->name);
-            
        }
        
        $context->destroy('CurrentNesting');
@@ -250,17 +259,18 @@ class HTMLPurifier_Strategy_MakeWellFormed extends HTMLPurifier_Strategy
        $context->destroy('InputIndex');
        $context->destroy('CurrentToken');
        
-        // we're at the end now, fix all still unclosed tags
-        // not using processToken() because at this point we don't
-        // care about current nesting
+        // we're at the end now, fix all still unclosed tags (this is
+        // duplicated from the end of the loop with some slight modifications)
+        // not using $skipped_tags since it would invariably be all of them
        if (!empty($this->currentNesting)) {
-            $size = count($this->currentNesting);
-            for ($i = $size - 1; $i >= 0; $i--) {
+            for ($i = count($this->currentNesting) - 1; $i >= 0; $i--) {
                if ($e && !isset($this->currentNesting[$i]->armor['MakeWellFormed_TagClosedError'])) {
                    $e->send(E_NOTICE, 'Strategy_MakeWellFormed: Tag closed by document end', $this->currentNesting[$i]);
                }
-                $result[] =
-                    new HTMLPurifier_Token_End($this->currentNesting[$i]->name);
+                $result[] = $new_token = new HTMLPurifier_Token_End($this->currentNesting[$i]->name);
+                foreach ($this->injectors as $j => $x) { // $j, not $i!!!
+                    $this->injectors[$j]->notifyEnd($new_token);
+                }
            }
        }
        
@@ -280,9 +290,17 @@ class HTMLPurifier_Strategy_MakeWellFormed extends HTMLPurifier_Strategy
            array_splice($this->inputTokens, $this->inputIndex--, 1, $token);
            
            // adjust the injector skips based on the array substitution
-            $offset = count($token) + 1;
-            for ($i = 0; $i <= $this->currentInjector; $i++) {
-                $this->injectors[$i]->skip += $offset;
+            if ($this->injectors) {
+                $offset = count($token);
+                for ($i = 0; $i <= $this->currentInjector; $i++) {
+                    // because of the skip back, we need to add one more
+                    // for uninitialized injectors. I'm not exactly
+                    // sure why this is the case, but I think it has to
+                    // do with the fact that we're decrementing skips
+                    // before re-checking text
+                    if (!$this->injectors[$i]->skip) $this->injectors[$i]->skip++;
+                    $this->injectors[$i]->skip += $offset;
+                }
            }
        } elseif ($token) {
            // regular case
--- a/library/HTMLPurifier/Strategy/RemoveForeignElements.php
+++ b/library/HTMLPurifier/Strategy/RemoveForeignElements.php
@@ -8,19 +8,38 @@ require_once 'HTMLPurifier/TagTransform.php';
 require_once 'HTMLPurifier/AttrValidator.php';

 HTMLPurifier_ConfigSchema::define(
-    'Core', 'RemoveInvalidImg', true, 'bool',
-    'This directive enables pre-emptive URI checking in <code>img</code> '.
-    'tags, as the attribute validation strategy is not authorized to '.
-    'remove elements from the document.  This directive has been available '.
-    'since 1.3.0, revert to pre-1.3.0 behavior by setting to false.'
+    'Core', 'RemoveInvalidImg', true, 'bool', '
+<p>
+  This directive enables pre-emptive URI checking in <code>img</code> 
+  tags, as the attribute validation strategy is not authorized to 
+  remove elements from the document.  This directive has been available 
+  since 1.3.0, revert to pre-1.3.0 behavior by setting to false.
+</p>
+'
 );

 HTMLPurifier_ConfigSchema::define(
-    'Core', 'RemoveScriptContents', true, 'bool', '
+    'Core', 'RemoveScriptContents', null, 'bool/null', '
 <p>
  This directive enables HTML Purifier to remove not only script tags
-  but all of their contents. This directive has been available since 2.0.0,
-  revert to pre-2.0.0 behavior by setting to false.
+  but all of their contents. This directive has been deprecated since 2.1.0,
+  and when not set the value of %Core.HiddenElements will take
+  precedence. This directive has been available since 2.0.0, and can be used to 
+  revert to pre-2.0.0 behavior by setting it to false.
+</p>
+'
+);
+
+HTMLPurifier_ConfigSchema::define(
+    'Core', 'HiddenElements', array('script' => true, 'style' => true), 'lookup', '
+<p>
+  This directive is a lookup array of elements which should have their
+  contents removed when they are not allowed by the HTML definition.
+  For example, the contents of a <code>script</code> tag are not 
+  normally shown in a document, so if script tags are to be removed,
+  their contents should be removed to. This is opposed to a <code>b</code>
+  tag, which defines some presentational changes but does not hide its
+  contents.
 </p>
 '
 );
@@ -43,7 +62,16 @@ class HTMLPurifier_Strategy_RemoveForeignElements extends HTMLPurifier_Strategy
        
        $escape_invalid_tags = $config->get('Core', 'EscapeInvalidTags');
        $remove_invalid_img  = $config->get('Core', 'RemoveInvalidImg');
+        
        $remove_script_contents = $config->get('Core', 'RemoveScriptContents');
+        $hidden_elements     = $config->get('Core', 'HiddenElements');
+        
+        // remove script contents compatibility
+        if ($remove_script_contents === true) {
+            $hidden_elements['script'] = true;
+        } elseif ($remove_script_contents === false && isset($hidden_elements['script'])) {
+            unset($hidden_elements['script']);
+        }
        
        $attr_validator = new HTMLPurifier_AttrValidator();
        
@@ -88,6 +116,7 @@ class HTMLPurifier_Strategy_RemoveForeignElements extends HTMLPurifier_Strategy
                    // mostly everything's good, but
                    // we need to make sure required attributes are in order
                    if (
+                        ($token->type === 'start' || $token->type === 'empty') &&
                        $definition->info[$token->name]->required_attr &&
                        ($token->name != 'img' || $remove_invalid_img) // ensure config option still works
                    ) {
@@ -106,8 +135,7 @@ class HTMLPurifier_Strategy_RemoveForeignElements extends HTMLPurifier_Strategy
                        $token->armor['ValidateAttributes'] = true;
                    }
                    
-                    // CAN BE GENERICIZED
-                    if ($token->name == 'script' && $token->type == 'start') {
+                    if (isset($hidden_elements[$token->name]) && $token->type == 'start') {
                        $textify_comments = $token->name;
                    } elseif ($token->name === $textify_comments && $token->type == 'end') {
                        $textify_comments = false;
@@ -122,7 +150,7 @@ class HTMLPurifier_Strategy_RemoveForeignElements extends HTMLPurifier_Strategy
                } else {
                    // check if we need to destroy all of the tag's children
                    // CAN BE GENERICIZED
-                    if ($token->name == 'script' && $remove_script_contents) {
+                    if (isset($hidden_elements[$token->name])) {
                        if ($token->type == 'start') {
                            $remove_until = $token->name;
                        } elseif ($token->type == 'empty') {
@@ -130,7 +158,7 @@ class HTMLPurifier_Strategy_RemoveForeignElements extends HTMLPurifier_Strategy
                        } else {
                            $remove_until = false;
                        }
-                        if ($e) $e->send(E_ERROR, 'Strategy_RemoveForeignElements: Script removed');
+                        if ($e) $e->send(E_ERROR, 'Strategy_RemoveForeignElements: Foreign meta element removed');
                    } else {
                        if ($e) $e->send(E_ERROR, 'Strategy_RemoveForeignElements: Foreign element removed');
                    }
--- a/library/HTMLPurifier/Strategy/ValidateAttributes.php
+++ b/library/HTMLPurifier/Strategy/ValidateAttributes.php
@@ -6,10 +6,6 @@ require_once 'HTMLPurifier/IDAccumulator.php';

 require_once 'HTMLPurifier/AttrValidator.php';

-HTMLPurifier_ConfigSchema::define(
-    'Attr', 'IDBlacklist', array(), 'list',
-    'Array of IDs not allowed in the document.');
-
 /**
 * Validate all attributes in the tokens.
 */
@@ -19,11 +15,6 @@ class HTMLPurifier_Strategy_ValidateAttributes extends HTMLPurifier_Strategy
    
    function execute($tokens, $config, &$context) {
        
-        // setup id_accumulator context
-        $id_accumulator = new HTMLPurifier_IDAccumulator();
-        $id_accumulator->load($config->get('Attr', 'IDBlacklist'));
-        $context->register('IDAccumulator', $id_accumulator);
-        
        // setup validator
        $validator = new HTMLPurifier_AttrValidator();
        
@@ -44,8 +35,7 @@ class HTMLPurifier_Strategy_ValidateAttributes extends HTMLPurifier_Strategy
            
            $tokens[$key] = $token; // for PHP 4
        }
-        
-        $context->destroy('IDAccumulator');
+        $context->destroy('CurrentToken');
        
        return $tokens;
    }
--- a/library/HTMLPurifier/URI.php
+++ b/library/HTMLPurifier/URI.php
@@ -0,0 +1,119 @@
+<?php
+
+require_once 'HTMLPurifier/URIParser.php';
+require_once 'HTMLPurifier/URIFilter.php';
+
+/**
+ * HTML Purifier's internal representation of a URI
+ */
+class HTMLPurifier_URI
+{
+    
+    var $scheme, $userinfo, $host, $port, $path, $query, $fragment;
+    
+    /**
+     * @note Automatically normalizes scheme and port
+     */
+    function HTMLPurifier_URI($scheme, $userinfo, $host, $port, $path, $query, $fragment) {
+        $this->scheme = is_null($scheme) || ctype_lower($scheme) ? $scheme : strtolower($scheme);
+        $this->userinfo = $userinfo;
+        $this->host = $host;
+        $this->port = is_null($port) ? $port : (int) $port;
+        $this->path = $path;
+        $this->query = $query;
+        $this->fragment = $fragment;
+    }
+    
+    /**
+     * Retrieves a scheme object corresponding to the URI's scheme/default
+     * @param $config Instance of HTMLPurifier_Config
+     * @param $context Instance of HTMLPurifier_Context
+     * @return Scheme object appropriate for validating this URI
+     */
+    function getSchemeObj($config, &$context) {
+        $registry =& HTMLPurifier_URISchemeRegistry::instance();
+        if ($this->scheme !== null) {
+            $scheme_obj = $registry->getScheme($this->scheme, $config, $context);
+            if (!$scheme_obj) return false; // invalid scheme, clean it out
+        } else {
+            // no scheme: retrieve the default one
+            $def = $config->getDefinition('URI');
+            $scheme_obj = $registry->getScheme($def->defaultScheme, $config, $context);
+            if (!$scheme_obj) {
+                // something funky happened to the default scheme object
+                trigger_error(
+                    'Default scheme object "' . $def->defaultScheme . '" was not readable',
+                    E_USER_WARNING
+                );
+                return false;
+            }
+        }
+        return $scheme_obj;
+    }
+    
+    /**
+     * Generic validation method applicable for all schemes
+     * @param $config Instance of HTMLPurifier_Config
+     * @param $context Instance of HTMLPurifier_Context
+     * @return True if validation/filtering succeeds, false if failure
+     */
+    function validate($config, &$context) {
+        
+        // validate host
+        if (!is_null($this->host)) {
+            $host_def = new HTMLPurifier_AttrDef_URI_Host();
+            $this->host = $host_def->validate($this->host, $config, $context);
+            if ($this->host === false) $this->host = null;
+        }
+        
+        // validate port
+        if (!is_null($this->port)) {
+            if ($this->port < 1 || $this->port > 65535) $this->port = null;
+        }
+        
+        // query and fragment are quite simple in terms of definition:
+        // *( pchar / "/" / "?" ), so define their validation routines
+        // when we start fixing percent encoding
+        
+        // path gets to be validated against a hodge-podge of rules depending
+        // on the status of authority and scheme, but it's not that important,
+        // esp. since it won't be applicable to everyone
+        
+        return true;
+        
+    }
+    
+    /**
+     * Convert URI back to string
+     * @return String URI appropriate for output
+     */
+    function toString() {
+        // reconstruct authority
+        $authority = null;
+        if (!is_null($this->host)) {
+            $authority = '';
+            if(!is_null($this->userinfo)) $authority .= $this->userinfo . '@';
+            $authority .= $this->host;
+            if(!is_null($this->port))     $authority .= ':' . $this->port;
+        }
+        
+        // reconstruct the result
+        $result = '';
+        if (!is_null($this->scheme))    $result .= $this->scheme . ':';
+        if (!is_null($authority))       $result .=  '//' . $authority;
+        $result .= $this->path;
+        if (!is_null($this->query))     $result .= '?' . $this->query;
+        if (!is_null($this->fragment))  $result .= '#' . $this->fragment;
+        
+        return $result;
+    }
+    
+    /**
+     * Returns a copy of the URI object
+     */
+    function copy() {
+        return unserialize(serialize($this));
+    }
+    
+}
+
--- a/library/HTMLPurifier/URIDefinition.php
+++ b/library/HTMLPurifier/URIDefinition.php
@@ -0,0 +1,145 @@
+<?php
+
+require_once 'HTMLPurifier/Definition.php';
+require_once 'HTMLPurifier/URIFilter.php';
+require_once 'HTMLPurifier/URIParser.php';
+
+require_once 'HTMLPurifier/URIFilter/DisableExternal.php';
+require_once 'HTMLPurifier/URIFilter/DisableExternalResources.php';
+require_once 'HTMLPurifier/URIFilter/HostBlacklist.php';
+require_once 'HTMLPurifier/URIFilter/MakeAbsolute.php';
+
+HTMLPurifier_ConfigSchema::define(
+    'URI', 'DefinitionID', null, 'string/null', '
+<p>
+    Unique identifier for a custom-built URI definition. If you  want
+    to add custom URIFilters, you must specify this value.
+    This directive has been available since 2.1.0.
+</p>
+');
+
+HTMLPurifier_ConfigSchema::define(
+    'URI', 'DefinitionRev', 1, 'int', '
+<p>
+    Revision identifier for your custom definition. See
+    %HTML.DefinitionRev for details. This directive has been available
+    since 2.1.0.
+</p>
+');
+
+// informative URI directives
+
+HTMLPurifier_ConfigSchema::define(
+    'URI', 'DefaultScheme', 'http', 'string', '
+<p>
+    Defines through what scheme the output will be served, in order to 
+    select the proper object validator when no scheme information is present.
+</p>
+');
+
+HTMLPurifier_ConfigSchema::define(
+    'URI', 'Host', null, 'string/null', '
+<p>
+    Defines the domain name of the server, so we can determine whether or 
+    an absolute URI is from your website or not.  Not strictly necessary, 
+    as users should be using relative URIs to reference resources on your 
+    website.  It will, however, let you use absolute URIs to link to 
+    subdomains of the domain you post here: i.e. example.com will allow 
+    sub.example.com.  However, higher up domains will still be excluded: 
+    if you set %URI.Host to sub.example.com, example.com will be blocked. 
+    <strong>Note:</strong> This directive overrides %URI.Base because
+    a given page may be on a sub-domain, but you wish HTML Purifier to be
+    more relaxed and allow some of the parent domains too.
+    This directive has been available since 1.2.0.
+</p>
+');
+
+HTMLPurifier_ConfigSchema::define(
+    'URI', 'Base', null, 'string/null', '
+<p>
+    The base URI is the URI of the document this purified HTML will be
+    inserted into.  This information is important if HTML Purifier needs
+    to calculate absolute URIs from relative URIs, such as when %URI.MakeAbsolute
+    is on.  You may use a non-absolute URI for this value, but behavior
+    may vary (%URI.MakeAbsolute deals nicely with both absolute and 
+    relative paths, but forwards-compatibility is not guaranteed).
+    <strong>Warning:</strong> If set, the scheme on this URI
+    overrides the one specified by %URI.DefaultScheme. This directive has
+    been available since 2.1.0.
+</p>
+');
+
+class HTMLPurifier_URIDefinition extends HTMLPurifier_Definition
+{
+    
+    var $type = 'URI';
+    var $filters = array();
+    var $registeredFilters = array();
+    
+    /**
+     * HTMLPurifier_URI object of the base specified at %URI.Base
+     */
+    var $base;
+    
+    /**
+     * String host to consider "home" base
+     */
+    var $host;
+    
+    /**
+     * Name of default scheme based on %URI.DefaultScheme and %URI.Base
+     */
+    var $defaultScheme;
+    
+    function HTMLPurifier_URIDefinition() {
+        $this->registerFilter(new HTMLPurifier_URIFilter_DisableExternal());
+        $this->registerFilter(new HTMLPurifier_URIFilter_DisableExternalResources());
+        $this->registerFilter(new HTMLPurifier_URIFilter_HostBlacklist());
+        $this->registerFilter(new HTMLPurifier_URIFilter_MakeAbsolute());
+    }
+    
+    function registerFilter($filter) {
+        $this->registeredFilters[$filter->name] = $filter;
+    }
+    
+    function addFilter($filter, $config) {
+        $filter->prepare($config);
+        $this->filters[$filter->name] = $filter;
+    }
+    
+    function doSetup($config) {
+        $this->setupMemberVariables($config);
+        $this->setupFilters($config);
+    }
+    
+    function setupFilters($config) {
+        foreach ($this->registeredFilters as $name => $filter) {
+            $conf = $config->get('URI', $name);
+            if ($conf !== false && $conf !== null) {
+                $this->addFilter($filter, $config);
+            }
+        }
+        unset($this->registeredFilters);
+    }
+    
+    function setupMemberVariables($config) {
+        $this->host = $config->get('URI', 'Host');
+        $base_uri = $config->get('URI', 'Base');
+        if (!is_null($base_uri)) {
+            $parser = new HTMLPurifier_URIParser();
+            $this->base = $parser->parse($base_uri);
+            $this->defaultScheme = $this->base->scheme;
+            if (is_null($this->host)) $this->host = $this->base->host;
+        }
+        if (is_null($this->defaultScheme)) $this->defaultScheme = $config->get('URI', 'DefaultScheme');
+    }
+    
+    function filter(&$uri, $config, &$context) {
+        foreach ($this->filters as $name => $x) {
+            $result = $this->filters[$name]->filter($uri, $config, $context);
+            if (!$result) return false;
+        }
+        return true;
+    }
+    
+}
--- a/library/HTMLPurifier/URIFilter.php
+++ b/library/HTMLPurifier/URIFilter.php
@@ -0,0 +1,40 @@
+<?php
+
+/**
+ * Chainable filters for custom URI processing.
+ * 
+ * These filters can perform custom actions on a URI filter object,
+ * including transformation or blacklisting.
+ * 
+ * @warning This filter is called before scheme object validation occurs.
+ *          Make sure, if you require a specific scheme object, you
+ *          you check that it exists. This allows filters to convert
+ *          proprietary URI schemes into regular ones.
+ */
+class HTMLPurifier_URIFilter
+{
+    
+    /**
+     * Unique identifier of filter
+     */
+    var $name;
+    
+    /**
+     * Performs initialization for the filter
+     */
+    function prepare($config) {}
+    
+    /**
+     * Filter a URI object
+     * @param &$uri Reference to URI object
+     * @param $config Instance of HTMLPurifier_Config
+     * @param &$context Instance of HTMLPurifier_Context
+     * @return bool Whether or not to continue processing: false indicates
+     *         URL is no good, true indicates continue processing. Note that
+     *         all changes are committed directly on the URI object
+     */
+    function filter(&$uri, $config, &$context) {
+        trigger_error('Cannot call abstract function', E_USER_ERROR);
+    }
+    
+}
--- a/library/HTMLPurifier/URIFilter/DisableExternal.php
+++ b/library/HTMLPurifier/URIFilter/DisableExternal.php
@@ -0,0 +1,34 @@
+<?php
+
+require_once 'HTMLPurifier/URIFilter.php';
+
+HTMLPurifier_ConfigSchema::define(
+    'URI', 'DisableExternal', false, 'bool',
+    'Disables links to external websites.  This is a highly effective '.
+    'anti-spam and anti-pagerank-leech measure, but comes at a hefty price: no'.
+    'links or images outside of your domain will be allowed.  Non-linkified '.
+    'URIs will still be preserved.  If you want to be able to link to '.
+    'subdomains or use absolute URIs, specify %URI.Host for your website. '.
+    'This directive has been available since 1.2.0.'
+);
+
+class HTMLPurifier_URIFilter_DisableExternal extends HTMLPurifier_URIFilter
+{
+    var $name = 'DisableExternal';
+    var $ourHostParts = false;
+    function prepare($config) {
+        $our_host = $config->get('URI', 'Host');
+        if ($our_host !== null) $this->ourHostParts = array_reverse(explode('.', $our_host));
+    }
+    function filter(&$uri, $config, &$context) {
+        if (is_null($uri->host)) return true;
+        if ($this->ourHostParts === false) return false;
+        $host_parts = array_reverse(explode('.', $uri->host));
+        foreach ($this->ourHostParts as $i => $x) {
+            if (!isset($host_parts[$i])) return false;
+            if ($host_parts[$i] != $this->ourHostParts[$i]) return false;
+        }
+        return true;
+    }
+}
+
--- a/library/HTMLPurifier/URIFilter/DisableExternalResources.php
+++ b/library/HTMLPurifier/URIFilter/DisableExternalResources.php
@@ -0,0 +1,26 @@
+<?php
+
+require_once 'HTMLPurifier/URIFilter/DisableExternal.php';
+
+HTMLPurifier_ConfigSchema::define(
+    'URI', 'DisableExternalResources', false, 'bool',
+    'Disables the embedding of external resources, preventing users from '.
+    'embedding things like images from other hosts. This prevents '.
+    'access tracking (good for email viewers), bandwidth leeching, '.
+    'cross-site request forging, goatse.cx posting, and '.
+    'other nasties, but also results in '.
+    'a loss of end-user functionality (they can\'t directly post a pic '.
+    'they posted from Flickr anymore). Use it if you don\'t have a '.
+    'robust user-content moderation team. This directive has been '.
+    'available since 1.3.0.'
+);
+
+class HTMLPurifier_URIFilter_DisableExternalResources extends HTMLPurifier_URIFilter_DisableExternal
+{
+    var $name = 'DisableExternalResources';
+    function filter(&$uri, $config, &$context) {
+        if (!$context->get('EmbeddedURI', true)) return true;
+        return parent::filter($uri, $config, $context);
+    }
+}
+
--- a/library/HTMLPurifier/URIFilter/HostBlacklist.php
+++ b/library/HTMLPurifier/URIFilter/HostBlacklist.php
@@ -0,0 +1,28 @@
+<?php
+
+require_once 'HTMLPurifier/URIFilter.php';
+
+HTMLPurifier_ConfigSchema::define(
+    'URI', 'HostBlacklist', array(), 'list',
+    'List of strings that are forbidden in the host of any URI. Use it to '.
+    'kill domain names of spam, etc. Note that it will catch anything in '.
+    'the domain, so <tt>moo.com</tt> will catch <tt>moo.com.example.com</tt>. '.
+    'This directive has been available since 1.3.0.'
+);
+
+class HTMLPurifier_URIFilter_HostBlacklist extends HTMLPurifier_URIFilter
+{
+    var $name = 'HostBlacklist';
+    var $blacklist = array();
+    function prepare($config) {
+        $this->blacklist = $config->get('URI', 'HostBlacklist');
+    }
+    function filter(&$uri, $config, &$context) {
+        foreach($this->blacklist as $blacklisted_host_fragment) {
+            if (strpos($uri->host, $blacklisted_host_fragment) !== false) {
+                return false;
+            }
+        }
+        return true;
+    }
+}
--- a/library/HTMLPurifier/URIFilter/MakeAbsolute.php
+++ b/library/HTMLPurifier/URIFilter/MakeAbsolute.php
@@ -0,0 +1,119 @@
+<?php
+
+// does not support network paths
+
+require_once 'HTMLPurifier/URIFilter.php';
+
+HTMLPurifier_ConfigSchema::define(
+    'URI', 'MakeAbsolute', false, 'bool', '
+<p>
+    Converts all URIs into absolute forms. This is useful when the HTML
+    being filtered assumes a specific base path, but will actually be
+    viewed in a different context (and setting an alternate base URI is
+    not possible). %URI.Base must be set for this directive to work.
+    This directive has been available since 2.1.0.
+</p>
+');
+
+class HTMLPurifier_URIFilter_MakeAbsolute extends HTMLPurifier_URIFilter
+{
+    var $name = 'MakeAbsolute';
+    var $base;
+    var $basePathStack = array();
+    function prepare($config) {
+        $def = $config->getDefinition('URI');
+        $this->base = $def->base;
+        if (is_null($this->base)) {
+            trigger_error('URI.MakeAbsolute is being ignored due to lack of value for URI.Base configuration', E_USER_ERROR);
+            return;
+        }
+        $this->base->fragment = null; // fragment is invalid for base URI
+        $stack = explode('/', $this->base->path);
+        array_pop($stack); // discard last segment
+        $stack = $this->_collapseStack($stack); // do pre-parsing
+        $this->basePathStack = $stack;
+    }
+    function filter(&$uri, $config, &$context) {
+        if (is_null($this->base)) return true; // abort early
+        if (
+            $uri->path === '' && is_null($uri->scheme) &&
+            is_null($uri->host) && is_null($uri->query) && is_null($uri->fragment)
+        ) {
+            // reference to current document
+            $uri = $this->base->copy();
+            return true;
+        }
+        if (!is_null($uri->scheme)) {
+            // absolute URI already: don't change
+            if (!is_null($uri->host)) return true;
+            $scheme_obj = $uri->getSchemeObj($config, $context);
+            if (!$scheme_obj) {
+                // scheme not recognized
+                return false;
+            }
+            if (!$scheme_obj->hierarchical) {
+                // non-hierarchal URI with explicit scheme, don't change
+                return true;
+            }
+            // special case: had a scheme but always is hierarchical and had no authority
+        }
+        if (!is_null($uri->host)) {
+            // network path, don't bother
+            return true;
+        }
+        if ($uri->path === '') {
+            $uri->path = $this->base->path;
+        }elseif ($uri->path[0] !== '/') {
+            // relative path, needs more complicated processing
+            $stack = explode('/', $uri->path);
+            $new_stack = array_merge($this->basePathStack, $stack);
+            $new_stack = $this->_collapseStack($new_stack);
+            $uri->path = implode('/', $new_stack);
+        }
+        // re-combine
+        $uri->scheme = $this->base->scheme;
+        if (is_null($uri->userinfo)) $uri->userinfo = $this->base->userinfo;
+        if (is_null($uri->host))     $uri->host     = $this->base->host;
+        if (is_null($uri->port))     $uri->port     = $this->base->port;
+        return true;
+    }
+    
+    /**
+     * Resolve dots and double-dots in a path stack
+     * @private
+     */
+    function _collapseStack($stack) {
+        $result = array();
+        for ($i = 0; isset($stack[$i]); $i++) {
+            $is_folder = false;
+            // absorb an internally duplicated slash
+            if ($stack[$i] == '' && $i && isset($stack[$i+1])) continue;
+            if ($stack[$i] == '..') {
+                if (!empty($result)) {
+                    $segment = array_pop($result);
+                    if ($segment === '' && empty($result)) {
+                        // error case: attempted to back out too far:
+                        // restore the leading slash
+                        $result[] = '';
+                    } elseif ($segment === '..') {
+                        $result[] = '..'; // cannot remove .. with ..
+                    }
+                } else {
+                    // relative path, preserve the double-dots
+                    $result[] = '..';
+                }
+                $is_folder = true;
+                continue;
+            }
+            if ($stack[$i] == '.') {
+                // silently absorb
+                $is_folder = true;
+                continue;
+            }
+            $result[] = $stack[$i];
+        }
+        if ($is_folder) $result[] = '';
+        return $result;
+    }
+}
+
--- a/library/HTMLPurifier/URIParser.php
+++ b/library/HTMLPurifier/URIParser.php
@@ -0,0 +1,62 @@
+<?php
+
+require_once 'HTMLPurifier/URI.php';
+
+/**
+ * Parses a URI into the components and fragment identifier as specified
+ * by RFC 2396.
+ * @todo Replace regexps with a native PHP parser
+ */
+class HTMLPurifier_URIParser
+{
+    
+    /**
+     * Parses a URI
+     * @param $uri string URI to parse
+     * @return HTMLPurifier_URI representation of URI
+     */
+    function parse($uri) {
+        $r_URI = '!'.
+            '(([^:/?#<>\'"]+):)?'. // 2. Scheme
+            '(//([^/?#<>\'"]*))?'. // 4. Authority
+            '([^?#<>\'"]*)'.       // 5. Path
+            '(\?([^#<>\'"]*))?'.   // 7. Query
+            '(#([^<>\'"]*))?'.     // 8. Fragment
+            '!';
+        
+        $matches = array();
+        $result = preg_match($r_URI, $uri, $matches);
+        
+        if (!$result) return false; // *really* invalid URI
+        
+        // seperate out parts
+        $scheme     = !empty($matches[1]) ? $matches[2] : null;
+        $authority  = !empty($matches[3]) ? $matches[4] : null;
+        $path       = $matches[5]; // always present, can be empty
+        $query      = !empty($matches[6]) ? $matches[7] : null;
+        $fragment   = !empty($matches[8]) ? $matches[9] : null;
+        
+        // further parse authority
+        if ($authority !== null) {
+            // ridiculously inefficient: it's a stacked regex!
+            $HEXDIG = '[A-Fa-f0-9]';
+            $unreserved = 'A-Za-z0-9-._~'; // make sure you wrap with []
+            $sub_delims = '!$&\'()'; // needs []
+            $pct_encoded = "%$HEXDIG$HEXDIG";
+            $r_userinfo = "(?:[$unreserved$sub_delims:]|$pct_encoded)*";
+            $r_authority = "/^(($r_userinfo)@)?(\[[^\]]+\]|[^:]*)(:(\d*))?/";
+            $matches = array();
+            preg_match($r_authority, $authority, $matches);
+            $userinfo   = !empty($matches[1]) ? $matches[2] : null;
+            $host       = !empty($matches[3]) ? $matches[3] : '';
+            $port       = !empty($matches[4]) ? (int) $matches[5] : null;
+        } else {
+            $port = $host = $userinfo = null;
+        }
+        
+        return new HTMLPurifier_URI(
+            $scheme, $userinfo, $host, $port, $path, $query, $fragment);
+    }
+    
+}
+
--- a/library/HTMLPurifier/URIScheme.php
+++ b/library/HTMLPurifier/URIScheme.php
@@ -19,24 +19,24 @@ class HTMLPurifier_URIScheme
     */
    var $browsable = false;
    
+    /**
+     * Whether or not the URI always uses <hier_part>, resolves edge cases
+     * with making relative URIs absolute
+     */
+    var $hierarchical = false;
+    
    /**
     * Validates the components of a URI
     * @note This implementation should be called by children if they define
     *       a default port, as it does port processing.
-     * @note Fragment is omitted as that is scheme independent
-     * @param $userinfo User info found before at sign in authority
-     * @param $host Hostname in authority
-     * @param $port Port found after colon in authority
-     * @param $path Path of URI
-     * @param $query Query of URI, found after question mark
+     * @param $uri Instance of HTMLPurifier_URI
     * @param $config HTMLPurifier_Config object
     * @param $context HTMLPurifier_Context object
+     * @return Bool success or failure
     */
-    function validateComponents(
-        $userinfo, $host, $port, $path, $query, $config, &$context
-    ) {
-        if ($this->default_port == $port) $port = null;
-        return array($userinfo, $host, $port, $path, $query);
+    function validate(&$uri, $config, &$context) {
+        if ($this->default_port == $uri->port) $uri->port = null;
+        return true;
    }
    
 }
--- a/library/HTMLPurifier/URIScheme/ftp.php
+++ b/library/HTMLPurifier/URIScheme/ftp.php
@@ -9,35 +9,35 @@ class HTMLPurifier_URIScheme_ftp extends HTMLPurifier_URIScheme {
    
    var $default_port = 21;
    var $browsable = true; // usually
+    var $hierarchical = true;
    
-    function validateComponents(
-        $userinfo, $host, $port, $path, $query, $config, &$context
-    ) {
-        list($userinfo, $host, $port, $path, $query) = 
-            parent::validateComponents(
-                $userinfo, $host, $port, $path, $query, $config, $context );
-        $semicolon_pos = strrpos($path, ';'); // reverse
+    function validate(&$uri, $config, &$context) {
+        parent::validate($uri, $config, $context);
+        $uri->query    = null;
+        
+        // typecode check
+        $semicolon_pos = strrpos($uri->path, ';'); // reverse
        if ($semicolon_pos !== false) {
-            // typecode check
-            $type = substr($path, $semicolon_pos + 1); // no semicolon
-            $path = substr($path, 0, $semicolon_pos);
+            $type = substr($uri->path, $semicolon_pos + 1); // no semicolon
+            $uri->path = substr($uri->path, 0, $semicolon_pos);
            $type_ret = '';
            if (strpos($type, '=') !== false) {
                // figure out whether or not the declaration is correct
                list($key, $typecode) = explode('=', $type, 2);
                if ($key !== 'type') {
                    // invalid key, tack it back on encoded
-                    $path .= '%3B' . $type;
+                    $uri->path .= '%3B' . $type;
                } elseif ($typecode === 'a' || $typecode === 'i' || $typecode === 'd') {
                    $type_ret = ";type=$typecode";
                }
            } else {
-                $path .= '%3B' . $type;
+                $uri->path .= '%3B' . $type;
            }
-            $path = str_replace(';', '%3B', $path);
-            $path .= $type_ret;
+            $uri->path = str_replace(';', '%3B', $uri->path);
+            $uri->path .= $type_ret;
        }
-        return array($userinfo, $host, $port, $path, null);
+        
+        return true;
    }
    
 }
--- a/library/HTMLPurifier/URIScheme/http.php
+++ b/library/HTMLPurifier/URIScheme/http.php
@@ -9,14 +9,12 @@ class HTMLPurifier_URIScheme_http extends HTMLPurifier_URIScheme {
    
    var $default_port = 80;
    var $browsable = true;
+    var $hierarchical = true;
    
-    function validateComponents(
-        $userinfo, $host, $port, $path, $query, $config, &$context
-    ) {
-        list($userinfo, $host, $port, $path, $query) = 
-            parent::validateComponents(
-                $userinfo, $host, $port, $path, $query, $config, $context );
-        return array(null, $host, $port, $path, $query);
+    function validate(&$uri, $config, &$context) {
+        parent::validate($uri, $config, $context);
+        $uri->userinfo = null;
+        return true;
    }
    
 }
--- a/library/HTMLPurifier/URIScheme/mailto.php
+++ b/library/HTMLPurifier/URIScheme/mailto.php
@@ -15,14 +15,13 @@ class HTMLPurifier_URIScheme_mailto extends HTMLPurifier_URIScheme {
    
    var $browsable = false;
    
-    function validateComponents(
-        $userinfo, $host, $port, $path, $query, $config, &$context
-    ) {
-        list($userinfo, $host, $port, $path, $query) = 
-            parent::validateComponents(
-                $userinfo, $host, $port, $path, $query, $config, $context );
+    function validate(&$uri, $config, &$context) {
+        parent::validate($uri, $config, $context);
+        $uri->userinfo = null;
+        $uri->host     = null;
+        $uri->port     = null;
        // we need to validate path against RFC 2368's addr-spec
-        return array(null, null, null, $path, $query);
+        return true;
    }
    
 }
--- a/library/HTMLPurifier/URIScheme/news.php
+++ b/library/HTMLPurifier/URIScheme/news.php
@@ -9,14 +9,14 @@ class HTMLPurifier_URIScheme_news extends HTMLPurifier_URIScheme {
    
    var $browsable = false;
    
-    function validateComponents(
-        $userinfo, $host, $port, $path, $query, $config, &$context
-    ) {
-        list($userinfo, $host, $port, $path, $query) = 
-            parent::validateComponents(
-                $userinfo, $host, $port, $path, $query, $config, $context );
+    function validate(&$uri, $config, &$context) {
+        parent::validate($uri, $config, $context);
+        $uri->userinfo = null;
+        $uri->host     = null;
+        $uri->port     = null;
+        $uri->query    = null;
        // typecode check needed on path
-        return array(null, null, null, $path, null);
+        return true;
    }
    
 }
--- a/library/HTMLPurifier/URIScheme/nntp.php
+++ b/library/HTMLPurifier/URIScheme/nntp.php
@@ -10,13 +10,11 @@ class HTMLPurifier_URIScheme_nntp extends HTMLPurifier_URIScheme {
    var $default_port = 119;
    var $browsable = false;
    
-    function validateComponents(
-        $userinfo, $host, $port, $path, $query, $config, &$context
-    ) {
-        list($userinfo, $host, $port, $path, $query) = 
-            parent::validateComponents(
-                $userinfo, $host, $port, $path, $query, $config, $context );
-        return array(null, $host, $port, $path, null);
+    function validate(&$uri, $config, &$context) {
+        parent::validate($uri, $config, $context);
+        $uri->userinfo = null;
+        $uri->query    = null;
+        return true;
    }
    
 }
--- a/library/HTMLPurifier/URISchemeRegistry.php
+++ b/library/HTMLPurifier/URISchemeRegistry.php
@@ -1,5 +1,12 @@
 <?php

+require_once 'HTMLPurifier/URIScheme/http.php';
+require_once 'HTMLPurifier/URIScheme/https.php';
+require_once 'HTMLPurifier/URIScheme/mailto.php';
+require_once 'HTMLPurifier/URIScheme/ftp.php';
+require_once 'HTMLPurifier/URIScheme/nntp.php';
+require_once 'HTMLPurifier/URIScheme/news.php';
+
 HTMLPurifier_ConfigSchema::define(
    'URI', 'AllowedSchemes', array(
        'http'  => true, // "Hypertext Transfer Protocol", nuf' said
@@ -7,7 +14,6 @@ HTMLPurifier_ConfigSchema::define(
        // quite useful, but not necessary
        'mailto' => true,// Email
        'ftp'   => true, // "File Transfer Protocol"
-        'irc'   => true, // "Internet Relay Chat", usually needs another app
        // for Usenet, these two are similar, but distinct
        'nntp'  => true, // individual Netnews articles
        'news'  => true  // newsgroup or individual Netnews articles
@@ -54,12 +60,6 @@ class HTMLPurifier_URISchemeRegistry
     */
    var $schemes = array();
    
-    /**
-     * Directory where scheme objects can be found
-     * @private
-     */
-    var $_scheme_dir = null;
-    
    /**
     * Retrieves a scheme validator object
     * @param $scheme String scheme name like http or mailto
@@ -79,11 +79,8 @@ class HTMLPurifier_URISchemeRegistry
        }
        
        if (isset($this->schemes[$scheme])) return $this->schemes[$scheme];
-        if (empty($this->_dir)) $this->_dir = dirname(__FILE__) . '/URIScheme/';
-        
        if (!isset($allowed_schemes[$scheme])) return $null;
        
-        @include_once $this->_dir . $scheme . '.php';
        $class = 'HTMLPurifier_URIScheme_' . $scheme;
        if (!class_exists($class)) return $null;
        $this->schemes[$scheme] = new $class();
@@ -91,7 +88,7 @@ class HTMLPurifier_URISchemeRegistry
    }
    
    /**
-     * Registers a custom scheme to the cache.
+     * Registers a custom scheme to the cache, bypassing reflection.
     * @param $scheme Scheme name
     * @param $scheme_obj HTMLPurifier_URIScheme object
     */
--- a/maintenance/PH5P.patch
+++ b/maintenance/PH5P.patch
@@ -0,0 +1,64 @@
+--- C:\Users\Edward\Webs\htmlpurifier\maintenance\PH5P.php	2007-11-04 23:41:49.074543700 -0500
+++ C:\Users\Edward\Webs\htmlpurifier\maintenance/PH5P.new.php	2007-11-05 00:23:52.839543700 -0500
+@@ -211,7 +211,10 @@
+         // If nothing is returned, emit a U+0026 AMPERSAND character token.
+         // Otherwise, emit the character token that was returned.
+         $char = (!$entity) ? '&' : $entity;
+-        $this->emitToken($char);
+        $this->emitToken(array(
+            'type' => self::CHARACTR,
+            'data' => $char
+        ));
+ 
+         // Finally, switch to the data state.
+         $this->state = 'data';
+@@ -708,7 +711,7 @@
+         } elseif($char === '&') {
+             /* U+0026 AMPERSAND (&)
+             Switch to the entity in attribute value state. */
+-            $this->entityInAttributeValueState('non');
+            $this->entityInAttributeValueState();
+ 
+         } elseif($char === '>') {
+             /* U+003E GREATER-THAN SIGN (>)
+@@ -738,7 +741,8 @@
+             ? '&'
+             : $entity;
+ 
+-        $this->emitToken($char);
+        $last = count($this->token['attr']) - 1;
+        $this->token['attr'][$last]['value'] .= $char;
+     }
+ 
+     private function bogusCommentState() {
+@@ -1066,6 +1070,11 @@
+                     $this->char++;
+ 
+                     if(in_array($id, $this->entities)) {
+                        if ($e_name[$c-1] !== ';') {
+                            if ($c < $len && $e_name[$c] == ';') {
+                                $this->char++; // consume extra semicolon
+                            }
+                        }
+                         $entity = $id;
+                         break;
+                     }
+@@ -3659,7 +3668,7 @@
+         }
+     }
+ 
+-    private function generateImpliedEndTags(array $exclude = array()) {
+    private function generateImpliedEndTags($exclude = array()) {
+         /* When the steps below require the UA to generate implied end tags,
+         then, if the current node is a dd element, a dt element, an li element,
+         a p element, a td element, a th  element, or a tr element, the UA must
+@@ -3673,7 +3682,8 @@
+         }
+     }
+ 
+-    private function getElementCategory($name) {
+    private function getElementCategory($node) {
+        $name = $node->tagName;
+         if(in_array($name, $this->special))
+             return self::SPECIAL;
+ 
--- a/maintenance/PH5P.php
+++ b/maintenance/PH5P.php
--- a/maintenance/common.php
+++ b/maintenance/common.php
@@ -1,5 +1,7 @@
 <?php

+require_once 'compat-function-file-put-contents.php';
+
 function assertCli() {
    if (php_sapi_name() != 'cli' && !getenv('PHP_IS_CLI')) {
        echo 'Script cannot be called from web-browser (if you are calling via cli,
@@ -7,3 +9,135 @@ set environment variable PHP_IS_CLI to work around this).';
        exit;
    }
 }
+
+/**
+ * Filesystem tools not provided by default; can recursively create, copy
+ * and delete folders. Some template methods are provided for extensibility.
+ * @note This class must be instantiated to be used, although it does
+ *       not maintain state.
+ */
+class FSTools
+{
+    
+    /**
+     * Recursively creates a directory
+     * @param string $folder Name of folder to create
+     * @note Adapted from the PHP manual comment 76612
+     */
+    function mkdir($folder) {
+        $folders = preg_split("#[\\\\/]#", $folder);
+        $base = '';
+        for($i = 0, $c = count($folders); $i < $c; $i++) {
+            if(empty($folders[$i])) {
+                if (!$i) {
+                    // special case for root level
+                    $base .= DIRECTORY_SEPARATOR;
+                }
+                continue;
+            }
+            $base .= $folders[$i];
+            if(!is_dir($base)){
+                mkdir($base);
+            }
+            $base .= DIRECTORY_SEPARATOR;
+        }
+    }
+    
+    /**
+     * Copy a file, or recursively copy a folder and its contents; modified
+     * so that copied files, if PHP, have includes removed
+     *
+     * @author      Aidan Lister <aidan@php.net>
+     * @version     1.0.1-modified
+     * @link        http://aidanlister.com/repos/v/function.copyr.php
+     * @param       string   $source    Source path
+     * @param       string   $dest      Destination path
+     * @return      bool     Returns TRUE on success, FALSE on failure
+     */
+    function copyr($source, $dest) {
+        // Simple copy for a file
+        if (is_file($source)) {
+            return $this->copy($source, $dest);
+        }
+        // Make destination directory
+        if (!is_dir($dest)) {
+            mkdir($dest);
+        }
+        // Loop through the folder
+        $dir = dir($source);
+        while (false !== $entry = $dir->read()) {
+            // Skip pointers
+            if ($entry == '.' || $entry == '..') {
+                continue;
+            }
+            if (!$this->copyable($entry)) {
+                continue;
+            }
+            // Deep copy directories
+            if ($dest !== "$source/$entry") {
+                $this->copyr("$source/$entry", "$dest/$entry");
+            }
+        }
+        // Clean up
+        $dir->close();
+        return true;
+    }
+    
+    /**
+     * Stub for PHP's built-in copy function, can be used to overload
+     * functionality
+     */
+    function copy($source, $dest) {
+        return copy($source, $dest);
+    }
+    
+    /**
+     * Overloadable function that tests a filename for copyability. By
+     * default, everything should be copied; you can restrict things to
+     * ignore hidden files, unreadable files, etc.
+     */
+    function copyable($file) {
+        return true;
+    }
+    
+    /**
+     * Delete a file, or a folder and its contents
+     *
+     * @author      Aidan Lister <aidan@php.net>
+     * @version     1.0.3
+     * @link        http://aidanlister.com/repos/v/function.rmdirr.php
+     * @param       string   $dirname    Directory to delete
+     * @return      bool     Returns TRUE on success, FALSE on failure
+     */
+    function rmdirr($dirname)
+    {
+        // Sanity check
+        if (!file_exists($dirname)) {
+            return false;
+        }
+     
+        // Simple delete for a file
+        if (is_file($dirname) || is_link($dirname)) {
+            return unlink($dirname);
+        }
+     
+        // Loop through the folder
+        $dir = dir($dirname);
+        while (false !== $entry = $dir->read()) {
+            // Skip pointers
+            if ($entry == '.' || $entry == '..') {
+                continue;
+            }
+            // Recurse
+            $this->rmdirr($dirname . DIRECTORY_SEPARATOR . $entry);
+        }
+     
+        // Clean up
+        $dir->close();
+        return rmdir($dirname);
+    }
+    
+    
+}
+
+
--- a/maintenance/compat-function-file-put-contents.php
+++ b/maintenance/compat-function-file-put-contents.php
@@ -0,0 +1,107 @@
+<?php
+// $Id: file_put_contents.php,v 1.27 2007/04/17 10:09:56 arpad Exp $
+
+
+if (!defined('FILE_USE_INCLUDE_PATH')) {
+    define('FILE_USE_INCLUDE_PATH', 1);
+}
+
+if (!defined('LOCK_EX')) {
+    define('LOCK_EX', 2);
+}
+
+if (!defined('FILE_APPEND')) {
+    define('FILE_APPEND', 8);
+}
+
+
+/**
+ * Replace file_put_contents()
+ *
+ * @category    PHP
+ * @package     PHP_Compat
+ * @license     LGPL - http://www.gnu.org/licenses/lgpl.html
+ * @copyright   2004-2007 Aidan Lister <aidan@php.net>, Arpad Ray <arpad@php.net>
+ * @link        http://php.net/function.file_put_contents
+ * @author      Aidan Lister <aidan@php.net>
+ * @version     $Revision: 1.27 $
+ * @internal    resource_context is not supported
+ * @since       PHP 5
+ * @require     PHP 4.0.0 (user_error)
+ */
+function php_compat_file_put_contents($filename, $content, $flags = null, $resource_context = null)
+{
+    // If $content is an array, convert it to a string
+    if (is_array($content)) {
+        $content = implode('', $content);
+    }
+
+    // If we don't have a string, throw an error
+    if (!is_scalar($content)) {
+        user_error('file_put_contents() The 2nd parameter should be either a string or an array',
+            E_USER_WARNING);
+        return false;
+    }
+
+    // Get the length of data to write
+    $length = strlen($content);
+
+    // Check what mode we are using
+    $mode = ($flags & FILE_APPEND) ?
+                'a' :
+                'wb';
+
+    // Check if we're using the include path
+    $use_inc_path = ($flags & FILE_USE_INCLUDE_PATH) ?
+                true :
+                false;
+
+    // Open the file for writing
+    if (($fh = @fopen($filename, $mode, $use_inc_path)) === false) {
+        user_error('file_put_contents() failed to open stream: Permission denied',
+            E_USER_WARNING);
+        return false;
+    }
+
+    // Attempt to get an exclusive lock
+    $use_lock = ($flags & LOCK_EX) ? true : false ;
+    if ($use_lock === true) {
+        if (!flock($fh, LOCK_EX)) {
+            return false;
+        }
+    }
+
+    // Write to the file
+    $bytes = 0;
+    if (($bytes = @fwrite($fh, $content)) === false) {
+        $errormsg = sprintf('file_put_contents() Failed to write %d bytes to %s',
+                        $length,
+                        $filename);
+        user_error($errormsg, E_USER_WARNING);
+        return false;
+    }
+
+    // Close the handle
+    @fclose($fh);
+
+    // Check all the data was written
+    if ($bytes != $length) {
+        $errormsg = sprintf('file_put_contents() Only %d of %d bytes written, possibly out of free disk space.',
+                        $bytes,
+                        $length);
+        user_error($errormsg, E_USER_WARNING);
+        return false;
+    }
+
+    // Return length
+    return $bytes;
+}
+
+
+// Define
+if (!function_exists('file_put_contents')) {
+    function file_put_contents($filename, $content, $flags = null, $resource_context = null)
+    {
+        return php_compat_file_put_contents($filename, $content, $flags, $resource_context);
+    }
+}
--- a/maintenance/flush-definition-cache.php
+++ b/maintenance/flush-definition-cache.php
@@ -32,5 +32,5 @@ foreach ($names as $name) {
    $cache->flush($config);
 }

-echo 'Cache flushed successfully.';
+echo "Cache flushed successfully.\n";

--- a/maintenance/generate-ph5p-patch.php
+++ b/maintenance/generate-ph5p-patch.php
@@ -0,0 +1,13 @@
+<?php
+
+$orig = realpath(dirname(__FILE__) . '/PH5P.php');
+$new  = realpath(dirname(__FILE__) . '/../library/HTMLPurifier/Lexer/PH5P.php');
+$newt = dirname(__FILE__) . '/PH5P.new.php'; // temporary file
+
+// minor text-processing of new file to get into same format as original
+$new_src = file_get_contents($new);
+$new_src = '<?php' . PHP_EOL . substr($new_src, strpos($new_src, 'class HTML5 {'));
+
+file_put_contents($newt, $new_src);
+shell_exec("diff -u \"$orig\" \"$newt\" > PH5P.patch");
+unlink($newt);
--- a/maintenance/merge-library.php
+++ b/maintenance/merge-library.php
@@ -6,20 +6,38 @@ assertCli();

 /**
 * Compiles all of HTML Purifier's library files into one big file
- * named HTMLPurifier.standalone.php. Operates recursively, and will
- * barf if there are conditional includes.
- * 
- * Details: also creates blank "include" files in the test/blank directory
- * in order to simulate require_once's inside the test files.
+ * named HTMLPurifier.standalone.php.
 */

 /**
- * Global array that tracks already loaded includes
+ * Global hash that tracks already loaded includes
 */
 $GLOBALS['loaded'] = array('HTMLPurifier.php' => true);

 /**
- * @param $text Text to replace includes from
+ * Custom FSTools for this script that overloads some behavior
+ * @warning The overloading of copy() is not necessarily global for
+ *          this script. Watch out!
+ */
+class MergeLibraryFSTools extends FSTools
+{
+    function copyable($entry) {
+        // Skip hidden files
+        if ($entry[0] == '.') {
+            return false;
+        }
+        return true;
+    }
+    function copy($source, $dest) {
+        copy_and_remove_includes($source, $dest);
+    }
+}
+$FS = new MergeLibraryFSTools();
+
+/**
+ * Replaces the includes inside PHP source code with the corresponding
+ * source.
+ * @param string $text PHP source code to replace includes from
 */
 function replace_includes($text) {
    return preg_replace_callback(
@@ -32,6 +50,8 @@ function replace_includes($text) {
 /**
 * Removes leading PHP tags from included files. Assumes that there is
 * no trailing tag.
+ * @note This is safe for files that have internal <?php
+ * @param string $text Text to have leading PHP tag from
 */
 function remove_php_tags($text) {
    return substr($text, 5);
@@ -40,125 +60,48 @@ function remove_php_tags($text) {
 /**
 * Creates an appropriate blank file, recursively generating directories
 * if necessary
+ * @param string $file Filename to create blank for
 */
 function create_blank($file) {
+    global $FS;
    $dir = dirname($file);
    $base = realpath('../tests/blanks/') . DIRECTORY_SEPARATOR ;
-    if ($dir != '.') mkdir_deep($base . $dir);
+    if ($dir != '.') {
+        $FS->mkdir($base . $dir);
+    }
    file_put_contents($base . $file, '');
 }

 /**
- * Recursively creates a directory
- * @note Adapted from the PHP manual comment 76612
+ * Copies the contents of a directory to the standalone directory
+ * @param string $dir Directory to copy
 */
-function mkdir_deep($folder) {
-    $folders = preg_split("#[\\\\/]#", $folder);
-    $base = '';
-    for($i = 0, $c = count($folders); $i < $c; $i++) {
-        if(empty($folders[$i])) {
-            if (!$i) {
-                // special case for root level
-                $base .= DIRECTORY_SEPARATOR;
-            }
-            continue;
-        }
-        $base .= $folders[$i];
-        if(!is_dir($base)){
-            mkdir($base);
-        }
-        $base .= DIRECTORY_SEPARATOR;
-    }
+function make_dir_standalone($dir) {
+    global $FS;
+    return $FS->copyr($dir, 'standalone/' . $dir);
 }

 /**
- * Copy a file, or recursively copy a folder and its contents
- *
- * @author      Aidan Lister <aidan@php.net>
- * @version     1.0.1
- * @link        http://aidanlister.com/repos/v/function.copyr.php
- * @param       string   $source    Source path
- * @param       string   $dest      Destination path
- * @return      bool     Returns TRUE on success, FALSE on failure
+ * Copies the contents of a file to the standalone directory
+ * @param string $file File to copy
 */
-function copyr($source, $dest) {
-    // Simple copy for a file
-    if (is_file($source)) {
-        return copy($source, $dest);
-    }
-    // Make destination directory
-    if (!is_dir($dest)) {
-        mkdir($dest);
-    }
-    // Loop through the folder
-    $dir = dir($source);
-    while (false !== $entry = $dir->read()) {
-        // Skip pointers
-        if ($entry == '.' || $entry == '..') {
-            continue;
-        }
-        // Skip hidden files
-        if ($entry[0] == '.') {
-            continue;
-        }
-        // Deep copy directories
-        if ($dest !== "$source/$entry") {
-            copyr("$source/$entry", "$dest/$entry");
-        }
-    }
-    // Clean up
-    $dir->close();
+function make_file_standalone($file) {
+    global $FS;
+    $FS->mkdir('standalone/' . dirname($file));
+    copy_and_remove_includes($file, 'standalone/' . $file);
    return true;
 }

 /**
- * Delete a file, or a folder and its contents
- *
- * @author      Aidan Lister <aidan@php.net>
- * @version     1.0.3
- * @link        http://aidanlister.com/repos/v/function.rmdirr.php
- * @param       string   $dirname    Directory to delete
- * @return      bool     Returns TRUE on success, FALSE on failure
+ * Copies a file to another location recursively, if it is a PHP file
+ * remove includes
+ * @param string $file Original file
+ * @param string $sfile New location of file
 */
-function rmdirr($dirname)
-{
-    // Sanity check
-    if (!file_exists($dirname)) {
-        return false;
-    }
- 
-    // Simple delete for a file
-    if (is_file($dirname) || is_link($dirname)) {
-        return unlink($dirname);
-    }
- 
-    // Loop through the folder
-    $dir = dir($dirname);
-    while (false !== $entry = $dir->read()) {
-        // Skip pointers
-        if ($entry == '.' || $entry == '..') {
-            continue;
-        }
- 
-        // Recurse
-        rmdirr($dirname . DIRECTORY_SEPARATOR . $entry);
-    }
- 
-    // Clean up
-    $dir->close();
-    return rmdir($dirname);
-}
-
-/**
- * Copies the contents of a directory to the standalone directory
- */
-function make_dir_standalone($dir) {
-    return copyr($dir, 'standalone/' . $dir);
-}
-
-function make_file_standalone($file) {
-    mkdir_deep('standalone/' . dirname($file));
-    return copy($file, 'standalone/' . $file);
+function copy_and_remove_includes($file, $sfile) {
+    $contents = file_get_contents($file);
+    if (strrchr($file, '.') === '.php') $contents = replace_includes($contents);
+    return file_put_contents($sfile, $contents);
 }

 /**
@@ -167,6 +110,16 @@ function make_file_standalone($file) {
 */
 function replace_includes_callback($matches) {
    $file = $matches[1];
+    $preserve = array(
+      // PHP 5 only
+      'HTMLPurifier/Lexer/DOMLex.php' => 1,
+      'HTMLPurifier/Printer.php' => 1,
+      // PEAR (external)
+      'XML/HTMLSax3.php' => 1
+    );
+    if (isset($preserve[$file])) {
+        return $matches[0];
+    }
    if (isset($GLOBALS['loaded'][$file])) return '';
    $GLOBALS['loaded'][$file] = true;
    create_blank($file);
@@ -180,19 +133,30 @@ echo 'Creating full file...';
 $contents = replace_includes(file_get_contents('HTMLPurifier.php'));
 $contents = str_replace(
    "define('HTMLPURIFIER_PREFIX', dirname(__FILE__));",
-    "define('HTMLPURIFIER_PREFIX', dirname(__FILE__) . '/standalone');",
+    "define('HTMLPURIFIER_PREFIX', dirname(__FILE__) . '/standalone');
+set_include_path(HTMLPURIFIER_PREFIX . PATH_SEPARATOR . get_include_path());",
    $contents
 );
 file_put_contents('HTMLPurifier.standalone.php', $contents);
 echo ' done!' . PHP_EOL;

 echo 'Creating standalone directory...';
-rmdirr('standalone'); // ensure a clean copy
-mkdir_deep('standalone/HTMLPurifier/DefinitionCache/Serializer');
-make_dir_standalone('HTMLPurifier/EntityLookup');
-make_dir_standalone('HTMLPurifier/Language');
-make_file_standalone('HTMLPurifier/Printer/ConfigForm.js');
-make_file_standalone('HTMLPurifier/Printer/ConfigForm.css');
-make_dir_standalone('HTMLPurifier/URIScheme');
-echo ' done!' . PHP_EOL;
+$FS->rmdirr('standalone'); // ensure a clean copy

+// data files
+$FS->mkdir('standalone/HTMLPurifier/DefinitionCache/Serializer');
+make_dir_standalone('HTMLPurifier/EntityLookup');
+
+// non-standard inclusion setup
+make_dir_standalone('HTMLPurifier/Language');
+
+// optional components
+make_file_standalone('HTMLPurifier/Printer.php'); 
+make_dir_standalone('HTMLPurifier/Printer');
+make_dir_standalone('HTMLPurifier/Filter');
+make_file_standalone('HTMLPurifier/Lexer/PEARSax3.php');
+
+// PHP 5 only files
+make_file_standalone('HTMLPurifier/Lexer/DOMLex.php');
+make_file_standalone('HTMLPurifier/Lexer/PH5P.php');
+echo ' done!' . PHP_EOL;
--- a/plugins/phorum/config.default.php
+++ b/plugins/phorum/config.default.php
@@ -0,0 +1,56 @@
+<?php
+
+if(!defined("PHORUM")) exit;
+
+// default HTML Purifier configuration settings
+$config->set('HTML', 'Allowed',
+  // alphabetically sorted
+'a[href|title]
+abbr[title]
+acronym[title]
+b
+blockquote[cite]
+br
+caption
+cite
+code
+dd
+del
+dfn
+div
+dl
+dt
+em
+i
+img[src|alt|title|class]
+ins
+kbd
+li
+ol
+p
+pre
+s
+strike
+strong
+sub
+sup
+table
+tbody
+td
+tfoot
+th
+thead
+tr
+tt
+u
+ul
+var');
+$config->set('AutoFormat', 'AutoParagraph', true);
+$config->set('AutoFormat', 'Linkify', true);
+$config->set('HTML', 'Doctype', 'XHTML 1.0 Transitional');
+$config->set('Core', 'AggressivelyFixLt', true);
+$config->set('Core', 'Encoding', $GLOBALS['PHORUM']['DATA']['CHARSET']); // we'll change this eventually
+if (strtolower($GLOBALS['PHORUM']['DATA']['CHARSET']) !== 'utf-8') {
+  $config->set('Core', 'EscapeNonASCIICharacters', true);
+}
+
--- a/plugins/phorum/htmlpurifier.php
+++ b/plugins/phorum/htmlpurifier.php
@@ -0,0 +1,302 @@
+<?php
+
+/**
+ * HTML Purifier Phorum Mod. Filter your HTML the Standards-Compliant Way!
+ * 
+ * This Phorum mod enables users to post raw HTML into Phorum.  But never
+ * fear: with the help of HTML Purifier, this HTML will be beat into
+ * de-XSSed and standards-compliant form, safe for general consumption.
+ * It is not recommended, but possible to run this mod in parallel
+ * with other formatters (in short, please DISABLE the BBcode mod).
+ * 
+ * For help migrating from your previous markup language to pure HTML
+ * please check the migrate.bbcode.php file.
+ * 
+ * If you'd like to use this with a WYSIWYG editor, make sure that
+ * editor sets $PHORUM['mod_htmlpurifier']['wysiwyg'] to true. Otherwise,
+ * administrators who need to edit other people's comments may be at
+ * risk for some nasty attacks.
+ * 
+ * Tested with Phorum 5.1.22. This module will almost definitely need
+ * to be upgraded when Phorum 6 rolls around.
+ */
+
+// Note: Cache data is base64 encoded because Phorum insists on flinging
+// to the user and expecting it to come back unharmed, newlines and
+// all, which ain't happening. It's slower, it takes up more space, but
+// at least it won't get mutilated
+
+/**
+ * Purifies a data array
+ */
+function phorum_htmlpurifier_format($data)
+{
+    $PHORUM = $GLOBALS["PHORUM"];
+    
+    $purifier =& HTMLPurifier::getInstance();
+    $cache_serial = $PHORUM['mod_htmlpurifier']['body_cache_serial'];
+    
+    foreach($data as $message_id => $message){
+        if(isset($message['body'])) {
+            
+            if ($message_id) {
+                // we're dealing with a real message, not a fake, so
+                // there a number of shortcuts that can be taken
+                
+                if (isset($message['meta']['htmlpurifier_light'])) {
+                    // format hook was called outside of Phorum's normal
+                    // functions, do the abridged purification
+                    $data[$message_id]['body'] = $purifier->purify($message['body']);
+                    continue;
+                }
+                
+                if (!empty($PHORUM['args']['purge'])) {
+                    // purge the cache, must be below the following if
+                    unset($message['meta']['body_cache']);
+                }
+                
+                if (
+                    isset($message['meta']['body_cache']) &&
+                    isset($message['meta']['body_cache_serial']) &&
+                    $message['meta']['body_cache_serial'] == $cache_serial
+                ) {
+                    // cached version is present, bail out early
+                    $data[$message_id]['body'] = base64_decode($message['meta']['body_cache']);
+                    continue;
+                }
+            }
+            
+            // migration might edit this array, that's why it's defined
+            // so early
+            $updated_message = array();
+            
+            // create the $body variable
+            if (
+                $message_id && // message must be real to migrate
+                !isset($message['meta']['body_cache_serial'])
+            ) {
+                // perform migration
+                $fake_data = array();
+                list($signature, $edit_message) = phorum_htmlpurifier_remove_sig_and_editmessage($message);
+                $fake_data[$message_id] = $message;
+                $fake_data = phorum_htmlpurifier_migrate($fake_data);
+                $body = $fake_data[$message_id]['body'];
+                $body = str_replace("<phorum break>", '', $body);
+                $updated_message['body'] = $body; // save it in
+                $body .= $signature . $edit_message; // add it back in
+            } else {
+                // reverse Phorum's pre-processing
+                $body = $message['body'];
+                // order is important
+                $body = str_replace("<phorum break>\n", "\n", $body);
+                $body = str_replace(array('&lt;','&gt;','&amp;'), array('<','>','&'), $body);
+                if (!$message_id && defined('PHORUM_CONTROL_CENTER')) {
+                    // we're in control.php, so it was double-escaped
+                    $body = str_replace(array('&lt;','&gt;','&amp;', '&quot;'), array('<','>','&','"'), $body);
+                }
+            }
+            
+            $body = $purifier->purify($body);
+            
+            // dynamically update the cache (MUST BE DONE HERE!)
+            // this is inefficient because it's one db call per
+            // cache miss, but once the cache is in place things are
+            // a lot zippier.
+            
+            if ($message_id) { // make sure it's not a fake id
+                $updated_message['meta'] = $message['meta'];
+                $updated_message['meta']['body_cache'] = base64_encode($body);
+                $updated_message['meta']['body_cache_serial'] = $cache_serial;
+                phorum_db_update_message($message_id, $updated_message);
+            }
+            
+            // must not get overloaded until after we cache it, otherwise
+            // we'll inadvertently change the original text
+            $data[$message_id]['body'] = $body;
+            
+        }
+    }
+    
+    return $data;
+}
+
+// -----------------------------------------------------------------------
+// This is fragile code, copied from read.php:359. It will break if
+// that is changed
+
+/**
+ * Generates a signature based on a message array
+ */
+function phorum_htmlpurifier_generate_sig($row) {
+    $phorum_sig = '';
+    if(isset($row["user"]["signature"])
+       && isset($row['meta']['show_signature']) && $row['meta']['show_signature']==1){
+           $phorum_sig=trim($row["user"]["signature"]);
+           if(!empty($phorum_sig)){
+               $phorum_sig="\n\n$phorum_sig";
+           }
+    }
+    return $phorum_sig;
+}
+
+/**
+ * Generates an edit message based on a message array
+ */
+function phorum_htmlpurifier_generate_editmessage($row) {
+    $PHORUM = $GLOBALS['PHORUM'];
+    $editmessage = '';
+    if(isset($row['meta']['edit_count']) && $row['meta']['edit_count'] > 0) {
+        $editmessage = str_replace ("%count%", $row['meta']['edit_count'], $PHORUM["DATA"]["LANG"]["EditedMessage"]);
+        $editmessage = str_replace ("%lastedit%", phorum_date($PHORUM["short_date"],$row['meta']['edit_date']),  $editmessage);
+        $editmessage = str_replace ("%lastuser%", $row['meta']['edit_username'],  $editmessage);
+        $editmessage="\n\n\n\n$editmessage";
+    }
+    return $editmessage;
+}
+
+// End fragile code
+// -----------------------------------------------------------------------
+
+/**
+ * Removes the signature and edit message from a message
+ * @param $row Message passed by reference
+ */
+function phorum_htmlpurifier_remove_sig_and_editmessage(&$row) {
+    // attempt to remove the Phorum's pre-processing:
+    // we must not process the signature or editmessage
+    $signature = phorum_htmlpurifier_generate_sig($row);
+    $editmessage = phorum_htmlpurifier_generate_editmessage($row);
+    $row['body'] = strtr($row['body'], array($signature => '', $editmessage => ''));
+    return array($signature, $editmessage);
+}
+
+/**
+ * Indicate that data is fully HTML and not from migration, invalidate
+ * previous caches
+ * @note This function used to generate the actual cache entries, but
+ * since there's data missing that must be deferred to the first read
+ */
+function phorum_htmlpurifier_posting($message) {
+    $PHORUM = $GLOBALS["PHORUM"];
+    unset($message['meta']['body_cache']); // invalidate the cache
+    $message['meta']['body_cache_serial'] = $PHORUM['mod_htmlpurifier']['body_cache_serial'];
+    return $message;
+}
+
+/**
+ * Overload quoting mechanism to prevent default, mail-style quote from happening
+ */
+function phorum_htmlpurifier_quote($array) {
+    $PHORUM = $GLOBALS["PHORUM"];
+    $purifier =& HTMLPurifier::getInstance();
+    $text = $purifier->purify($array[1]);
+    return "<blockquote cite=\"$array[0]\">\n$text\n</blockquote>";
+}
+
+/**
+ * Ensure that our format hook is processed last. Also, loads the library.
+ * @credits <http://secretsauce.phorum.org/snippets/make_bbcode_last_formatter.php.txt>
+ */
+function phorum_htmlpurifier_common() {
+    
+    require_once(dirname(__FILE__).'/htmlpurifier/HTMLPurifier.auto.php');
+    require(dirname(__FILE__).'/init-config.php');
+    
+    $config = phorum_htmlpurifier_get_config();
+    HTMLPurifier::getInstance($config);
+    
+    // increment revision.txt if you want to invalidate the cache
+    $GLOBALS['PHORUM']['mod_htmlpurifier']['body_cache_serial'] = $config->getSerial();
+    
+    // load migration
+    if (file_exists(dirname(__FILE__) . '/migrate.php')) {
+        include(dirname(__FILE__) . '/migrate.php');
+    } else {
+        echo '<strong>Error:</strong> No migration path specified for HTML Purifier, please check
+        <tt>modes/htmlpurifier/migrate.bbcode.php</tt> for instructions on
+        how to migrate from your previous markup language.';
+        exit;
+    }
+    
+    // see if our hooks need to be bubbled to the end
+    phorum_htmlpurifier_bubble_hook('format');
+    
+}
+
+function phorum_htmlpurifier_bubble_hook($hook) {
+    global $PHORUM;
+    $our_idx = null;
+    $last_idx = null;
+    if (!isset($PHORUM['hooks'][$hook]['mods'])) return;
+    foreach ($PHORUM['hooks'][$hook]['mods'] as $idx => $mod) {
+        if ($mod == 'htmlpurifier') $our_idx = $idx;
+        $last_idx = $idx;
+    }
+    list($mod) = array_splice($PHORUM['hooks'][$hook]['mods'], $our_idx, 1);
+    $PHORUM['hooks'][$hook]['mods'][] = $mod;
+    list($func) = array_splice($PHORUM['hooks'][$hook]['funcs'], $our_idx, 1);
+    $PHORUM['hooks'][$hook]['funcs'][] = $func;
+}
+
+/**
+ * Pre-emptively performs purification if it looks like a WYSIWYG editor
+ * is being used
+ */
+function phorum_htmlpurifier_before_editor($message) {
+    if (!empty($GLOBALS['PHORUM']['mod_htmlpurifier']['wysiwyg'])) {
+        if (!empty($message['body'])) {
+            $body = $message['body'];
+            // de-entity-ize contents
+            $body = str_replace(array('&lt;','&gt;','&amp;'), array('<','>','&'), $body);
+            $purifier =& HTMLPurifier::getInstance();
+            $body = $purifier->purify($message['body']);
+            // re-entity-ize contents
+            $body = htmlspecialchars($body, ENT_QUOTES, $GLOBALS['PHORUM']['DATA']['CHARSET']);
+        }
+    }
+    return $message;
+}
+
+function phorum_htmlpurifier_editor_after_subject() {
+    // don't show this message if it's a WYSIWYG editor, since it will
+    // then be handled automatically
+    if (!empty($GLOBALS['PHORUM']['mod_htmlpurifier']['wysiwyg'])) return;
+    ?><tr><td colspan="2" style="padding:1em 0.3em;" class="htmlpurifier-help">
+    <p>
+        <strong>HTML input</strong> is enabled. Make sure you escape all HTML and
+        angled brackets with <code>&amp;lt;</code> and <code>&amp;gt;</code>.
+    </p><?php
+            $purifier =& HTMLPurifier::getInstance();
+            $config = $purifier->config;
+            if ($config->get('AutoFormat', 'AutoParagraph')) {
+                ?><p>
+                    <strong>Auto-paragraphing</strong> is enabled. Double
+                    newlines will be converted to paragraphs; for single
+                    newlines, use the <code>pre</code> tag.
+                </p><?php
+            }
+            $html_definition = $config->getDefinition('HTML');
+            $allowed = array();
+            foreach ($html_definition->info as $name => $x) $allowed[] = "<code>$name</code>";
+            sort($allowed);
+            $allowed_text = implode(', ', $allowed);
+            ?><p><strong>Allowed tags:</strong> <?php
+            echo $allowed_text;
+            ?>.</p><?php
+        ?>
+    </p>
+    <p>
+        For inputting literal code such as HTML and PHP for display, use
+        CDATA tags to auto-escape your angled brackets, and <code>pre</code>
+        to preserve newlines:
+    </p>
+    <pre>&lt;pre&gt;&lt;![CDATA[
+<em>Place code here</em>
+]]&gt;&lt;/pre&gt;</pre>
+    <p>
+        Power users, you can hide this notice with:
+        <pre>.htmlpurifier-help {display:none;}</pre>
+    </p>
+    </td></tr><?php
+}
+
--- a/plugins/phorum/htmlpurifier/LICENSE
+++ b/plugins/phorum/htmlpurifier/LICENSE
@@ -0,0 +1,504 @@
+		  GNU LESSER GENERAL PUBLIC LICENSE
+		       Version 2.1, February 1999
+
+ Copyright (C) 1991, 1999 Free Software Foundation, Inc.
+ 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301  USA
+ Everyone is permitted to copy and distribute verbatim copies
+ of this license document, but changing it is not allowed.
+
+[This is the first released version of the Lesser GPL.  It also counts
+ as the successor of the GNU Library Public License, version 2, hence
+ the version number 2.1.]
+
+			    Preamble
+
+  The licenses for most software are designed to take away your
+freedom to share and change it.  By contrast, the GNU General Public
+Licenses are intended to guarantee your freedom to share and change
+free software--to make sure the software is free for all its users.
+
+  This license, the Lesser General Public License, applies to some
+specially designated software packages--typically libraries--of the
+Free Software Foundation and other authors who decide to use it.  You
+can use it too, but we suggest you first think carefully about whether
+this license or the ordinary General Public License is the better
+strategy to use in any particular case, based on the explanations below.
+
+  When we speak of free software, we are referring to freedom of use,
+not price.  Our General Public Licenses are designed to make sure that
+you have the freedom to distribute copies of free software (and charge
+for this service if you wish); that you receive source code or can get
+it if you want it; that you can change the software and use pieces of
+it in new free programs; and that you are informed that you can do
+these things.
+
+  To protect your rights, we need to make restrictions that forbid
+distributors to deny you these rights or to ask you to surrender these
+rights.  These restrictions translate to certain responsibilities for
+you if you distribute copies of the library or if you modify it.
+
+  For example, if you distribute copies of the library, whether gratis
+or for a fee, you must give the recipients all the rights that we gave
+you.  You must make sure that they, too, receive or can get the source
+code.  If you link other code with the library, you must provide
+complete object files to the recipients, so that they can relink them
+with the library after making changes to the library and recompiling
+it.  And you must show them these terms so they know their rights.
+
+  We protect your rights with a two-step method: (1) we copyright the
+library, and (2) we offer you this license, which gives you legal
+permission to copy, distribute and/or modify the library.
+
+  To protect each distributor, we want to make it very clear that
+there is no warranty for the free library.  Also, if the library is
+modified by someone else and passed on, the recipients should know
+that what they have is not the original version, so that the original
+author's reputation will not be affected by problems that might be
+introduced by others.
+
+  Finally, software patents pose a constant threat to the existence of
+any free program.  We wish to make sure that a company cannot
+effectively restrict the users of a free program by obtaining a
+restrictive license from a patent holder.  Therefore, we insist that
+any patent license obtained for a version of the library must be
+consistent with the full freedom of use specified in this license.
+
+  Most GNU software, including some libraries, is covered by the
+ordinary GNU General Public License.  This license, the GNU Lesser
+General Public License, applies to certain designated libraries, and
+is quite different from the ordinary General Public License.  We use
+this license for certain libraries in order to permit linking those
+libraries into non-free programs.
+
+  When a program is linked with a library, whether statically or using
+a shared library, the combination of the two is legally speaking a
+combined work, a derivative of the original library.  The ordinary
+General Public License therefore permits such linking only if the
+entire combination fits its criteria of freedom.  The Lesser General
+Public License permits more lax criteria for linking other code with
+the library.
+
+  We call this license the "Lesser" General Public License because it
+does Less to protect the user's freedom than the ordinary General
+Public License.  It also provides other free software developers Less
+of an advantage over competing non-free programs.  These disadvantages
+are the reason we use the ordinary General Public License for many
+libraries.  However, the Lesser license provides advantages in certain
+special circumstances.
+
+  For example, on rare occasions, there may be a special need to
+encourage the widest possible use of a certain library, so that it becomes
+a de-facto standard.  To achieve this, non-free programs must be
+allowed to use the library.  A more frequent case is that a free
+library does the same job as widely used non-free libraries.  In this
+case, there is little to gain by limiting the free library to free
+software only, so we use the Lesser General Public License.
+
+  In other cases, permission to use a particular library in non-free
+programs enables a greater number of people to use a large body of
+free software.  For example, permission to use the GNU C Library in
+non-free programs enables many more people to use the whole GNU
+operating system, as well as its variant, the GNU/Linux operating
+system.
+
+  Although the Lesser General Public License is Less protective of the
+users' freedom, it does ensure that the user of a program that is
+linked with the Library has the freedom and the wherewithal to run
+that program using a modified version of the Library.
+
+  The precise terms and conditions for copying, distribution and
+modification follow.  Pay close attention to the difference between a
+"work based on the library" and a "work that uses the library".  The
+former contains code derived from the library, whereas the latter must
+be combined with the library in order to run.
+
+		  GNU LESSER GENERAL PUBLIC LICENSE
+   TERMS AND CONDITIONS FOR COPYING, DISTRIBUTION AND MODIFICATION
+
+  0. This License Agreement applies to any software library or other
+program which contains a notice placed by the copyright holder or
+other authorized party saying it may be distributed under the terms of
+this Lesser General Public License (also called "this License").
+Each licensee is addressed as "you".
+
+  A "library" means a collection of software functions and/or data
+prepared so as to be conveniently linked with application programs
+(which use some of those functions and data) to form executables.
+
+  The "Library", below, refers to any such software library or work
+which has been distributed under these terms.  A "work based on the
+Library" means either the Library or any derivative work under
+copyright law: that is to say, a work containing the Library or a
+portion of it, either verbatim or with modifications and/or translated
+straightforwardly into another language.  (Hereinafter, translation is
+included without limitation in the term "modification".)
+
+  "Source code" for a work means the preferred form of the work for
+making modifications to it.  For a library, complete source code means
+all the source code for all modules it contains, plus any associated
+interface definition files, plus the scripts used to control compilation
+and installation of the library.
+
+  Activities other than copying, distribution and modification are not
+covered by this License; they are outside its scope.  The act of
+running a program using the Library is not restricted, and output from
+such a program is covered only if its contents constitute a work based
+on the Library (independent of the use of the Library in a tool for
+writing it).  Whether that is true depends on what the Library does
+and what the program that uses the Library does.
+  
+  1. You may copy and distribute verbatim copies of the Library's
+complete source code as you receive it, in any medium, provided that
+you conspicuously and appropriately publish on each copy an
+appropriate copyright notice and disclaimer of warranty; keep intact
+all the notices that refer to this License and to the absence of any
+warranty; and distribute a copy of this License along with the
+Library.
+
+  You may charge a fee for the physical act of transferring a copy,
+and you may at your option offer warranty protection in exchange for a
+fee.
+
+  2. You may modify your copy or copies of the Library or any portion
+of it, thus forming a work based on the Library, and copy and
+distribute such modifications or work under the terms of Section 1
+above, provided that you also meet all of these conditions:
+
+    a) The modified work must itself be a software library.
+
+    b) You must cause the files modified to carry prominent notices
+    stating that you changed the files and the date of any change.
+
+    c) You must cause the whole of the work to be licensed at no
+    charge to all third parties under the terms of this License.
+
+    d) If a facility in the modified Library refers to a function or a
+    table of data to be supplied by an application program that uses
+    the facility, other than as an argument passed when the facility
+    is invoked, then you must make a good faith effort to ensure that,
+    in the event an application does not supply such function or
+    table, the facility still operates, and performs whatever part of
+    its purpose remains meaningful.
+
+    (For example, a function in a library to compute square roots has
+    a purpose that is entirely well-defined independent of the
+    application.  Therefore, Subsection 2d requires that any
+    application-supplied function or table used by this function must
+    be optional: if the application does not supply it, the square
+    root function must still compute square roots.)
+
+These requirements apply to the modified work as a whole.  If
+identifiable sections of that work are not derived from the Library,
+and can be reasonably considered independent and separate works in
+themselves, then this License, and its terms, do not apply to those
+sections when you distribute them as separate works.  But when you
+distribute the same sections as part of a whole which is a work based
+on the Library, the distribution of the whole must be on the terms of
+this License, whose permissions for other licensees extend to the
+entire whole, and thus to each and every part regardless of who wrote
+it.
+
+Thus, it is not the intent of this section to claim rights or contest
+your rights to work written entirely by you; rather, the intent is to
+exercise the right to control the distribution of derivative or
+collective works based on the Library.
+
+In addition, mere aggregation of another work not based on the Library
+with the Library (or with a work based on the Library) on a volume of
+a storage or distribution medium does not bring the other work under
+the scope of this License.
+
+  3. You may opt to apply the terms of the ordinary GNU General Public
+License instead of this License to a given copy of the Library.  To do
+this, you must alter all the notices that refer to this License, so
+that they refer to the ordinary GNU General Public License, version 2,
+instead of to this License.  (If a newer version than version 2 of the
+ordinary GNU General Public License has appeared, then you can specify
+that version instead if you wish.)  Do not make any other change in
+these notices.
+
+  Once this change is made in a given copy, it is irreversible for
+that copy, so the ordinary GNU General Public License applies to all
+subsequent copies and derivative works made from that copy.
+
+  This option is useful when you wish to copy part of the code of
+the Library into a program that is not a library.
+
+  4. You may copy and distribute the Library (or a portion or
+derivative of it, under Section 2) in object code or executable form
+under the terms of Sections 1 and 2 above provided that you accompany
+it with the complete corresponding machine-readable source code, which
+must be distributed under the terms of Sections 1 and 2 above on a
+medium customarily used for software interchange.
+
+  If distribution of object code is made by offering access to copy
+from a designated place, then offering equivalent access to copy the
+source code from the same place satisfies the requirement to
+distribute the source code, even though third parties are not
+compelled to copy the source along with the object code.
+
+  5. A program that contains no derivative of any portion of the
+Library, but is designed to work with the Library by being compiled or
+linked with it, is called a "work that uses the Library".  Such a
+work, in isolation, is not a derivative work of the Library, and
+therefore falls outside the scope of this License.
+
+  However, linking a "work that uses the Library" with the Library
+creates an executable that is a derivative of the Library (because it
+contains portions of the Library), rather than a "work that uses the
+library".  The executable is therefore covered by this License.
+Section 6 states terms for distribution of such executables.
+
+  When a "work that uses the Library" uses material from a header file
+that is part of the Library, the object code for the work may be a
+derivative work of the Library even though the source code is not.
+Whether this is true is especially significant if the work can be
+linked without the Library, or if the work is itself a library.  The
+threshold for this to be true is not precisely defined by law.
+
+  If such an object file uses only numerical parameters, data
+structure layouts and accessors, and small macros and small inline
+functions (ten lines or less in length), then the use of the object
+file is unrestricted, regardless of whether it is legally a derivative
+work.  (Executables containing this object code plus portions of the
+Library will still fall under Section 6.)
+
+  Otherwise, if the work is a derivative of the Library, you may
+distribute the object code for the work under the terms of Section 6.
+Any executables containing that work also fall under Section 6,
+whether or not they are linked directly with the Library itself.
+
+  6. As an exception to the Sections above, you may also combine or
+link a "work that uses the Library" with the Library to produce a
+work containing portions of the Library, and distribute that work
+under terms of your choice, provided that the terms permit
+modification of the work for the customer's own use and reverse
+engineering for debugging such modifications.
+
+  You must give prominent notice with each copy of the work that the
+Library is used in it and that the Library and its use are covered by
+this License.  You must supply a copy of this License.  If the work
+during execution displays copyright notices, you must include the
+copyright notice for the Library among them, as well as a reference
+directing the user to the copy of this License.  Also, you must do one
+of these things:
+
+    a) Accompany the work with the complete corresponding
+    machine-readable source code for the Library including whatever
+    changes were used in the work (which must be distributed under
+    Sections 1 and 2 above); and, if the work is an executable linked
+    with the Library, with the complete machine-readable "work that
+    uses the Library", as object code and/or source code, so that the
+    user can modify the Library and then relink to produce a modified
+    executable containing the modified Library.  (It is understood
+    that the user who changes the contents of definitions files in the
+    Library will not necessarily be able to recompile the application
+    to use the modified definitions.)
+
+    b) Use a suitable shared library mechanism for linking with the
+    Library.  A suitable mechanism is one that (1) uses at run time a
+    copy of the library already present on the user's computer system,
+    rather than copying library functions into the executable, and (2)
+    will operate properly with a modified version of the library, if
+    the user installs one, as long as the modified version is
+    interface-compatible with the version that the work was made with.
+
+    c) Accompany the work with a written offer, valid for at
+    least three years, to give the same user the materials
+    specified in Subsection 6a, above, for a charge no more
+    than the cost of performing this distribution.
+
+    d) If distribution of the work is made by offering access to copy
+    from a designated place, offer equivalent access to copy the above
+    specified materials from the same place.
+
+    e) Verify that the user has already received a copy of these
+    materials or that you have already sent this user a copy.
+
+  For an executable, the required form of the "work that uses the
+Library" must include any data and utility programs needed for
+reproducing the executable from it.  However, as a special exception,
+the materials to be distributed need not include anything that is
+normally distributed (in either source or binary form) with the major
+components (compiler, kernel, and so on) of the operating system on
+which the executable runs, unless that component itself accompanies
+the executable.
+
+  It may happen that this requirement contradicts the license
+restrictions of other proprietary libraries that do not normally
+accompany the operating system.  Such a contradiction means you cannot
+use both them and the Library together in an executable that you
+distribute.
+
+  7. You may place library facilities that are a work based on the
+Library side-by-side in a single library together with other library
+facilities not covered by this License, and distribute such a combined
+library, provided that the separate distribution of the work based on
+the Library and of the other library facilities is otherwise
+permitted, and provided that you do these two things:
+
+    a) Accompany the combined library with a copy of the same work
+    based on the Library, uncombined with any other library
+    facilities.  This must be distributed under the terms of the
+    Sections above.
+
+    b) Give prominent notice with the combined library of the fact
+    that part of it is a work based on the Library, and explaining
+    where to find the accompanying uncombined form of the same work.
+
+  8. You may not copy, modify, sublicense, link with, or distribute
+the Library except as expressly provided under this License.  Any
+attempt otherwise to copy, modify, sublicense, link with, or
+distribute the Library is void, and will automatically terminate your
+rights under this License.  However, parties who have received copies,
+or rights, from you under this License will not have their licenses
+terminated so long as such parties remain in full compliance.
+
+  9. You are not required to accept this License, since you have not
+signed it.  However, nothing else grants you permission to modify or
+distribute the Library or its derivative works.  These actions are
+prohibited by law if you do not accept this License.  Therefore, by
+modifying or distributing the Library (or any work based on the
+Library), you indicate your acceptance of this License to do so, and
+all its terms and conditions for copying, distributing or modifying
+the Library or works based on it.
+
+  10. Each time you redistribute the Library (or any work based on the
+Library), the recipient automatically receives a license from the
+original licensor to copy, distribute, link with or modify the Library
+subject to these terms and conditions.  You may not impose any further
+restrictions on the recipients' exercise of the rights granted herein.
+You are not responsible for enforcing compliance by third parties with
+this License.
+
+  11. If, as a consequence of a court judgment or allegation of patent
+infringement or for any other reason (not limited to patent issues),
+conditions are imposed on you (whether by court order, agreement or
+otherwise) that contradict the conditions of this License, they do not
+excuse you from the conditions of this License.  If you cannot
+distribute so as to satisfy simultaneously your obligations under this
+License and any other pertinent obligations, then as a consequence you
+may not distribute the Library at all.  For example, if a patent
+license would not permit royalty-free redistribution of the Library by
+all those who receive copies directly or indirectly through you, then
+the only way you could satisfy both it and this License would be to
+refrain entirely from distribution of the Library.
+
+If any portion of this section is held invalid or unenforceable under any
+particular circumstance, the balance of the section is intended to apply,
+and the section as a whole is intended to apply in other circumstances.
+
+It is not the purpose of this section to induce you to infringe any
+patents or other property right claims or to contest validity of any
+such claims; this section has the sole purpose of protecting the
+integrity of the free software distribution system which is
+implemented by public license practices.  Many people have made
+generous contributions to the wide range of software distributed
+through that system in reliance on consistent application of that
+system; it is up to the author/donor to decide if he or she is willing
+to distribute software through any other system and a licensee cannot
+impose that choice.
+
+This section is intended to make thoroughly clear what is believed to
+be a consequence of the rest of this License.
+
+  12. If the distribution and/or use of the Library is restricted in
+certain countries either by patents or by copyrighted interfaces, the
+original copyright holder who places the Library under this License may add
+an explicit geographical distribution limitation excluding those countries,
+so that distribution is permitted only in or among countries not thus
+excluded.  In such case, this License incorporates the limitation as if
+written in the body of this License.
+
+  13. The Free Software Foundation may publish revised and/or new
+versions of the Lesser General Public License from time to time.
+Such new versions will be similar in spirit to the present version,
+but may differ in detail to address new problems or concerns.
+
+Each version is given a distinguishing version number.  If the Library
+specifies a version number of this License which applies to it and
+"any later version", you have the option of following the terms and
+conditions either of that version or of any later version published by
+the Free Software Foundation.  If the Library does not specify a
+license version number, you may choose any version ever published by
+the Free Software Foundation.
+
+  14. If you wish to incorporate parts of the Library into other free
+programs whose distribution conditions are incompatible with these,
+write to the author to ask for permission.  For software which is
+copyrighted by the Free Software Foundation, write to the Free
+Software Foundation; we sometimes make exceptions for this.  Our
+decision will be guided by the two goals of preserving the free status
+of all derivatives of our free software and of promoting the sharing
+and reuse of software generally.
+
+			    NO WARRANTY
+
+  15. BECAUSE THE LIBRARY IS LICENSED FREE OF CHARGE, THERE IS NO
+WARRANTY FOR THE LIBRARY, TO THE EXTENT PERMITTED BY APPLICABLE LAW.
+EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT HOLDERS AND/OR
+OTHER PARTIES PROVIDE THE LIBRARY "AS IS" WITHOUT WARRANTY OF ANY
+KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, THE
+IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
+PURPOSE.  THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE
+LIBRARY IS WITH YOU.  SHOULD THE LIBRARY PROVE DEFECTIVE, YOU ASSUME
+THE COST OF ALL NECESSARY SERVICING, REPAIR OR CORRECTION.
+
+  16. IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN
+WRITING WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MAY MODIFY
+AND/OR REDISTRIBUTE THE LIBRARY AS PERMITTED ABOVE, BE LIABLE TO YOU
+FOR DAMAGES, INCLUDING ANY GENERAL, SPECIAL, INCIDENTAL OR
+CONSEQUENTIAL DAMAGES ARISING OUT OF THE USE OR INABILITY TO USE THE
+LIBRARY (INCLUDING BUT NOT LIMITED TO LOSS OF DATA OR DATA BEING
+RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD PARTIES OR A
+FAILURE OF THE LIBRARY TO OPERATE WITH ANY OTHER SOFTWARE), EVEN IF
+SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF SUCH
+DAMAGES.
+
+		     END OF TERMS AND CONDITIONS
+
+           How to Apply These Terms to Your New Libraries
+
+  If you develop a new library, and you want it to be of the greatest
+possible use to the public, we recommend making it free software that
+everyone can redistribute and change.  You can do so by permitting
+redistribution under these terms (or, alternatively, under the terms of the
+ordinary General Public License).
+
+  To apply these terms, attach the following notices to the library.  It is
+safest to attach them to the start of each source file to most effectively
+convey the exclusion of warranty; and each file should have at least the
+"copyright" line and a pointer to where the full notice is found.
+
+    <one line to give the library's name and a brief idea of what it does.>
+    Copyright (C) <year>  <name of author>
+
+    This library is free software; you can redistribute it and/or
+    modify it under the terms of the GNU Lesser General Public
+    License as published by the Free Software Foundation; either
+    version 2.1 of the License, or (at your option) any later version.
+
+    This library is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+    Lesser General Public License for more details.
+
+    You should have received a copy of the GNU Lesser General Public
+    License along with this library; if not, write to the Free Software
+    Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301  USA
+
+Also add information on how to contact you by electronic and paper mail.
+
+You should also get your employer (if you work as a programmer) or your
+school, if any, to sign a "copyright disclaimer" for the library, if
+necessary.  Here is a sample; alter the names:
+
+  Yoyodyne, Inc., hereby disclaims all copyright interest in the
+  library `Frob' (a library for tweaking knobs) written by James Random Hacker.
+
+  <signature of Ty Coon>, 1 April 1990
+  Ty Coon, President of Vice
+
+That's all there is to it!
+
+
--- a/plugins/phorum/htmlpurifier/README
+++ b/plugins/phorum/htmlpurifier/README
@@ -0,0 +1 @@
+The contents of the library/ folder should be here.
--- a/plugins/phorum/info.txt
+++ b/plugins/phorum/info.txt
@@ -0,0 +1,8 @@
+hook:  format|phorum_htmlpurifier_format
+hook:  quote|phorum_htmlpurifier_quote
+hook:  posting_custom_action|phorum_htmlpurifier_posting
+hook:  common|phorum_htmlpurifier_common
+hook:  before_editor|phorum_htmlpurifier_before_editor
+hook:  tpl_editor_after_subject|phorum_htmlpurifier_editor_after_subject
+title: HTML Purifier Phorum Mod
+desc:  This module enables standards-compliant HTML filtering on Phorum. Please check migrate.bbcode.php before enabling this mod.
--- a/plugins/phorum/init-config.php
+++ b/plugins/phorum/init-config.php
@@ -0,0 +1,27 @@
+<?php
+
+/**
+ * Initializes the appropriate configuration from either a PHP file
+ * or a module configuration value
+ * @return Instance of HTMLPurifier_Config
+ */
+function phorum_htmlpurifier_get_config() {
+    global $PHORUM;
+    $config_exists = phorum_htmlpurifier_config_file_exists();
+    if ($config_exists || !isset($PHORUM['mod_htmlpurifier']['config'])) {
+        $config = HTMLPurifier_Config::createDefault();
+        include(dirname(__FILE__) . '/config.default.php');
+        if ($config_exists) {
+            include(dirname(__FILE__) . '/config.php');
+        }
+        unset($PHORUM['mod_htmlpurifier']['config']); // unnecessary
+    } else {
+        $config = HTMLPurifier_Config::create($PHORUM['mod_htmlpurifier']['config']);
+    }
+    return $config;
+}
+
+function phorum_htmlpurifier_config_file_exists() {
+    return file_exists(dirname(__FILE__) . '/config.php');
+}
+
--- a/plugins/phorum/install.txt
+++ b/plugins/phorum/install.txt
@@ -0,0 +1,33 @@
+
+HTML Purifier Phorum Mod - Filter your HTML the Standards-Compliant Way!
+
+This Phorum mod enables HTML posting on Phorum.  Under normal circumstances,
+this would cause a huge security risk, but because we are running
+HTML through HTML Purifier, output is guaranteed to be XSS free and
+standards-compliant.
+
+This mod requires HTML input, and previous markup languages need to be
+converted accordingly.  Thus, it is vital that you create a 'migrate.php'
+file that works with your installation. If you're using the built-in
+BBCode formatting, simply move migrate.bbcode.php to that place; for
+other markup languages, consult said file for instructions on how
+to adapt it to your needs.
+
+This module will not work if 'migrate.php' is not created, and an improperly
+made migration file may *CORRUPT* Phorum, so please take your time to
+do this correctly. It should go without saying to *BACKUP YOUR DATABASE*
+before attempting anything here.
+
+This module will not automatically migrate user signatures, because this
+process may take a long time. After installing the HTML Purifier module and
+then configuring 'migrate.php', navigate to Settings and click 'Migrate
+Signatures' to migrate all user signatures.
+
+The version of HTML Purifier bundled with is a custom modified 2.0.1.
+Do not attempt to replace it with a version equal to or less than
+downloaded from the HTML Purifier website: the module will combust
+spectacularly. (Greater versions, however, are okay, because the changes
+made to accomodate this module have been committed to the trunk).
+
+Visit HTML Purifier at <http://htmlpurifier.org/>. May the force
+be with you.
--- a/plugins/phorum/migrate.bbcode.php
+++ b/plugins/phorum/migrate.bbcode.php
@@ -0,0 +1,28 @@
+<?php
+
+/**
+ * This file is responsible for migrating from a specific markup language
+ * like BBCode or Markdown to HTML. WARNING: THIS PROCESS IS NOT REVERSIBLE
+ * 
+ * Copy this file to 'migrate.php' and it will automatically work for
+ * BBCode; you may need to tweak this a little to get it to work for other
+ * languages (usually, just replace the include name and the function name).
+ * 
+ * If you do NOT want to have any migration performed (for instance, you
+ * are installing the module on a new forum with no posts), simply remove
+ * phorum_htmlpurifier_migrate() function. You still need migrate.php
+ * present, otherwise the module won't work.
+ */
+
+if(!defined("PHORUM")) exit;
+
+require_once(dirname(__FILE__) . "/../bbcode/bbcode.php");
+
+/**
+ * 'format' hook style function that will be called to convert
+ * legacy markup into HTML.
+ */
+function phorum_htmlpurifier_migrate($data) {
+    return phorum_bb_code($data); // bbcode's 'format' hook
+}
+
--- a/plugins/phorum/settings.php
+++ b/plugins/phorum/settings.php
@@ -0,0 +1,63 @@
+<?php
+
+// based off of BBCode's settings file
+
+/**
+ * HTML Purifier Phorum mod settings configuration. This provides
+ * a convenient web-interface for editing the most common HTML Purifier
+ * configuration directives. You can also specify custom configuration
+ * by creating a 'config.php' file.
+ */
+
+if(!defined("PHORUM_ADMIN")) exit;
+
+// error reporting is good!
+error_reporting(E_ALL ^ E_NOTICE);
+
+// load library and other paraphenalia
+require_once './include/admin/PhorumInputForm.php';
+require_once (dirname(__FILE__) . '/htmlpurifier/HTMLPurifier.auto.php');
+require_once (dirname(__FILE__) . '/init-config.php');
+require_once (dirname(__FILE__) . '/settings/migrate-sigs-form.php');
+require_once (dirname(__FILE__) . '/settings/migrate-sigs.php');
+require_once (dirname(__FILE__) . '/settings/form.php');
+require_once (dirname(__FILE__) . '/settings/save.php');
+
+// define friendly configuration directives. you can expand this array
+// to get more web-definable directives
+$PHORUM['mod_htmlpurifier']['directives'] = array(
+    'URI.Host', // auto-detectable
+    'URI.DisableExternal',
+    'URI.DisableExternalResources',
+    'URI.DisableResources',
+    'URI.Munge',
+    'URI.HostBlacklist',
+    'URI.Disable',
+    'HTML.TidyLevel',
+    'HTML.Doctype', // auto-detectable
+    'HTML.Allowed',
+    'AutoFormat',
+    '-AutoFormat.Custom',
+    '-AutoFormat.PurifierLinkify',
+    'Output.TidyFormat',
+);
+
+// lower this setting if you're getting time outs/out of memory
+$PHORUM['mod_htmlpurifier']['migrate-sigs-increment'] = 100;
+
+if (isset($_POST['reset'])) {
+    unset($PHORUM['mod_htmlpurifier']['config']);
+}
+
+if ($offset = phorum_htmlpurifier_migrate_sigs_check()) {
+    // migrate signatures
+    phorum_htmlpurifier_migrate_sigs($offset);
+} elseif(!empty($_POST)){
+    // save settings
+    phorum_htmlpurifier_save_settings();
+}
+
+phorum_htmlpurifier_show_migrate_sigs_form();
+echo '<br />';
+phorum_htmlpurifier_show_form();
+
--- a/plugins/phorum/settings/form.php
+++ b/plugins/phorum/settings/form.php
@@ -0,0 +1,79 @@
+<?php
+
+function phorum_htmlpurifier_show_form() {
+    if (phorum_htmlpurifier_config_file_exists()) {
+        phorum_htmlpurifier_show_config_info();
+        return;
+    }
+    
+    global $PHORUM;
+    
+    $config = phorum_htmlpurifier_get_config();
+    
+    $frm = new PhorumInputForm ("", "post", "Save");
+    $frm->hidden("module", "modsettings");
+    $frm->hidden("mod", "htmlpurifier"); // this is the directory name that the Settings file lives in
+
+    if (!empty($error)){
+        echo "$error<br />";
+    }
+
+    $frm->addbreak("Edit settings for the HTML Purifier module");
+    
+    $frm->addMessage('<p>Click on directive links to read what each option does
+    (links do not open in new windows).</p>
+    <p>For more flexibility (for instance, you want to edit the full
+    range of configuration directives), you can create a <tt>config.php</tt>
+    file in your <tt>mods/htmlpurifier/</tt> directory. Doing so will,
+    however, make the web configuration interface unavailable.</p>');
+    
+    require_once 'HTMLPurifier/Printer/ConfigForm.php';
+    $htmlpurifier_form = new HTMLPurifier_Printer_ConfigForm('config', 'http://htmlpurifier.org/live/configdoc/plain.html#%s');
+    $htmlpurifier_form->setTextareaDimensions(23, 7); // widen a little, since we have space
+    
+    $frm->addMessage($htmlpurifier_form->render(
+        $config, $PHORUM['mod_htmlpurifier']['directives'], false));
+
+    $frm->addMessage("<strong>Warning: Changing HTML Purifier's configuration will invalidate
+      the cache. Expect to see a flurry of database activity after you change
+      any of these settings.</strong>");
+    
+    $frm->addrow('Reset to defaults:', $frm->checkbox("reset", "1", "", false));
+
+    // hack to include extra styling
+    echo '<style type="text/css">' . $htmlpurifier_form->getCSS() . '
+    .hp-config {margin-left:auto;margin-right:auto;}
+    </style>';
+    $js = $htmlpurifier_form->getJavaScript();
+    echo '<script type="text/javascript">'."<!--\n$js\n//-->".'</script>';
+    
+    $frm->show();
+}
+
+function phorum_htmlpurifier_show_config_info() {
+    global $PHORUM;
+    
+    // update mod_htmlpurifier for housekeeping
+    phorum_htmlpurifier_commit_settings();
+    
+    // politely tell user how to edit settings manually
+?>
+        <div class="input-form-td-break">How to edit settings for HTML Purifier module</div>
+        <p>
+          A <tt>config.php</tt> file exists in your <tt>mods/htmlpurifier/</tt>
+          directory. This file contains your custom configuration: in order to
+          change it, please navigate to that file and edit it accordingly.
+        </p>
+        <p>
+          To use the web interface, delete <tt>config.php</tt> (or rename it to
+          <tt>config.php.bak</tt>).
+        </p>
+        <p>
+          <strong>Warning: Changing HTML Purifier's configuration will invalidate
+          the cache. Expect to see a flurry of database activity after you change
+          any of these settings.</strong>
+        </p>
+<?php
+
+}
+
--- a/plugins/phorum/settings/migrate-sigs-form.php
+++ b/plugins/phorum/settings/migrate-sigs-form.php
@@ -0,0 +1,21 @@
+<?php
+
+function phorum_htmlpurifier_show_migrate_sigs_form() {
+    
+    $frm = new PhorumInputForm ('', "post", "Migrate");
+    $frm->hidden("module", "modsettings");
+    $frm->hidden("mod", "htmlpurifier");
+    $frm->hidden("migrate-sigs", "1");
+    $frm->addbreak("Migrate user signatures to HTML");
+    $frm->addMessage('This operation will migrate your users signatures
+        to HTML. <strong>This process is irreversible and must only be performed once.</strong>
+        Type in yes in the confirmation field to migrate.');
+    if (!file_exists(dirname(__FILE__) . '/../migrate.php')) {
+        $frm->addMessage('Migration file does not exist, cannot migrate signatures.
+            Please check <tt>migrate.bbcode.php</tt> on how to create an appropriate file.');
+    } else {
+        $frm->addrow('Confirm:', $frm->text_box("confirmation", ""));
+    }
+    $frm->show();
+}
+
--- a/plugins/phorum/settings/migrate-sigs.php
+++ b/plugins/phorum/settings/migrate-sigs.php
@@ -0,0 +1,85 @@
+<?php
+
+function phorum_htmlpurifier_migrate_sigs_check() {
+    global $PHORUM;
+    $offset = 0;
+    if (!empty($_POST['migrate-sigs'])) {
+        if (!isset($_POST['confirmation']) || strtolower($_POST['confirmation']) !== 'yes') {
+            echo 'Invalid confirmation code.';
+            exit;
+        }
+        $PHORUM['mod_htmlpurifier']['migrate-sigs'] = true;
+        phorum_db_update_settings(array("mod_htmlpurifier"=>$PHORUM["mod_htmlpurifier"]));
+        $offset = 1;
+    } elseif (!empty($_GET['migrate-sigs']) && $PHORUM['mod_htmlpurifier']['migrate-sigs']) {
+        $offset = (int) $_GET['migrate-sigs'];
+    }
+    return $offset;
+}
+
+function phorum_htmlpurifier_migrate_sigs($offset) {
+    global $PHORUM;
+    
+    if(!$offset) return; // bail out quick if $offset == 0
+    
+    // theoretically, we could get rid of this multi-request
+    // doo-hickery if safe mode is off
+    @set_time_limit(0); // attempt to let this run
+    $increment = $PHORUM['mod_htmlpurifier']['migrate-sigs-increment'];
+    
+    require_once(dirname(__FILE__) . '/../migrate.php');
+    // migrate signatures
+    // do this in batches so we don't run out of time/space
+    $end = $offset + $increment;
+    $user_ids = array();
+    for ($i = $offset; $i < $end; $i++) {
+        $user_ids[] = $i;
+    }
+    $userinfos = phorum_db_user_get_fields($user_ids, 'signature');
+    foreach ($userinfos as $i => $user) {
+        if (empty($user['signature'])) continue;
+        $sig = $user['signature'];
+        // perform standard Phorum processing on the sig
+        $sig = str_replace(array("&","<",">"), array("&amp;","&lt;","&gt;"), $sig);
+        $sig = preg_replace("/<((http|https|ftp):\/\/[a-z0-9;\/\?:@=\&\$\-_\.\+!*'\(\),~%]+?)>/i", "$1", $sig);
+        // prepare fake data to pass to migration function
+        $fake_data = array(array("author"=>"", "email"=>"", "subject"=>"", 'body' => $sig));
+        list($fake_message) = phorum_htmlpurifier_migrate($fake_data);
+        $user['signature'] = $fake_message['body'];
+        if (!phorum_user_save($user)) {
+            exit('Error while saving user data');
+        }
+    }
+    unset($userinfos); // free up memory
+    
+    // query for highest ID in database
+    $type = $PHORUM['DBCONFIG']['type'];
+    $sql = "select MAX(user_id) from {$PHORUM['user_table']}";
+    if ($type == 'mysql') {
+        $conn = phorum_db_mysql_connect();
+        $res = mysql_query($sql, $conn);
+        $row = mysql_fetch_row($res);
+    } elseif ($type == 'mysqli') {
+        $conn = phorum_db_mysqli_connect();
+        $res = mysqli_query($conn, $sql);
+        $row = mysqli_fetch_row($res);
+    } else {
+        exit('Unrecognized database!');
+    }
+    $top_id = (int) $row[0];
+    
+    $offset += $increment;
+    if ($offset > $top_id) { // test for end condition
+        echo 'Migration finished';
+        $PHORUM['mod_htmlpurifier']['migrate-sigs'] = false;
+        phorum_htmlpurifier_commit_settings();
+        return true;
+    }
+    $host  = $_SERVER['HTTP_HOST'];
+    $uri   = rtrim(dirname($_SERVER['PHP_SELF']), '/\\');
+    $extra = 'admin.php?module=modsettings&mod=htmlpurifier&migrate-sigs=' . $offset;
+    // relies on output buffering to work
+    header("Location: http://$host$uri/$extra");
+    exit;
+    
+}
--- a/plugins/phorum/settings/save.php
+++ b/plugins/phorum/settings/save.php
@@ -0,0 +1,23 @@
+<?php
+
+function phorum_htmlpurifier_save_settings() {
+    global $PHORUM;
+    if (phorum_htmlpurifier_config_file_exists()) {
+        echo "Cannot update settings, <code>mods/htmlpurifier/config.php</code> already exists. To change
+        settings, edit that file. To use the web form, delete that file.<br />";
+    } else {
+        $config = phorum_htmlpurifier_get_config();
+        if (!isset($_POST['reset'])) $config->mergeArrayFromForm($_POST, 'config', $PHORUM['mod_htmlpurifier']['directives']);
+        $PHORUM['mod_htmlpurifier']['config'] = $config->getAll();
+        if(!phorum_htmlpurifier_commit_settings()){
+            $error="Database error while updating settings.";
+        } else {
+            echo "Settings Updated<br />";
+        }
+    }
+}
+
+function phorum_htmlpurifier_commit_settings() {
+    global $PHORUM;
+    return phorum_db_update_settings(array("mod_htmlpurifier"=>$PHORUM["mod_htmlpurifier"]));
+}
--- a/smoketests/all.php
+++ b/smoketests/all.php
@@ -31,7 +31,7 @@ while (false !== ($filename = readdir($dh))) {
    if ($filename == 'all.php') continue;
    if ($filename == 'testSchema.php') continue;
    ?>
-    <iframe src="<?php echo escapeHTML($filename); ?>"></iframe>
+    <iframe src="<?php echo escapeHTML($filename); if (isset($_GET['standalone'])) {echo '?standalone';} ?>"></iframe>
    <?php
 }

--- a/smoketests/common.php
+++ b/smoketests/common.php
@@ -2,7 +2,11 @@

 header('Content-type: text/html; charset=UTF-8');

-require_once '../library/HTMLPurifier.auto.php';
+if (!isset($_GET['standalone'])) {
+    require_once '../library/HTMLPurifier.auto.php';
+} else {
+    require_once '../library/HTMLPurifier.standalone.php';
+}
 error_reporting(E_ALL | E_STRICT);

 function escapeHTML($string) {
--- a/smoketests/testSchema.php
+++ b/smoketests/testSchema.php
@@ -37,3 +37,7 @@ HTMLPurifier_ConfigSchema::defineNamespace('ReportCard', 'It is for grades.');
 HTMLPurifier_ConfigSchema::define('ReportCard', 'English', null, 'string/null', 'Grade from English class.');
 HTMLPurifier_ConfigSchema::define('ReportCard', 'Absences', 0, 'int', 'How many times missing from school?');

+HTMLPurifier_ConfigSchema::defineNamespace('Text', 'This stuff is long, boring, and English.');
+HTMLPurifier_ConfigSchema::define('Text', 'AboutUs', 'Nothing much, but this should be decently long so that a textarea would be better', 'text', 'Who are we? What are we up to?');
+HTMLPurifier_ConfigSchema::define('Text', 'Hash', "not-case-sensitive\nstill-not-case-sensitive\nsuper-not-case-sensitive", 'itext', 'This is of limited utility, but of course it ends up being used.');
+
--- a/test-settings.sample.php
+++ b/test-settings.sample.php
@@ -1,16 +1,20 @@
 <?php

-// This file is necessary to run the unit tests and profiling
-// scripts.
+// ATTENTION! DO NOT EDIT THIS FILE!
+// This file is necessary to run the unit tests and profiling scripts.
+// Please copy it to 'test-settings.php' and make the necessary edits.

-// Is PEAR available on your system? If it isn't, set to false. If PEAR
-// is not part of the default include_path, add it.
-$GLOBALS['HTMLPurifierTest']['PEAR'] = true;
+// Some of these scripts run a long time, so it is recommended that you
+// turn off the time limit
+set_time_limit(0);
+
+// Turning off output buffering will prevent mysterious errors from core dumps
+@ob_end_flush();
+
+// Where is SimpleTest located?
+$simpletest_location = '/path/to/simpletest/';

 // How many times should profiling scripts iterate over the function? More runs 
 // means more accurate results, but they'll take longer to perform.
 $GLOBALS['HTMLPurifierTest']['Runs'] = 2;

-// Where is SimpleTest located?
-$simpletest_location = '/path/to/simpletest/';
-
--- a/tests/Debugger.php
+++ b/tests/Debugger.php
@@ -54,14 +54,14 @@ function isInScopes($array = array()) {
 }
 /**#@-*/

-function printTokens($tokens, $index) {
+function printTokens($tokens, $index = null) {
    $string = '<pre>';
    $generator = new HTMLPurifier_Generator();
    foreach ($tokens as $i => $token) {
-        if ($index == $i) $string .= '[<strong>';
+        if ($index === $i) $string .= '[<strong>';
        $string .= "<sup>$i</sup>";
        $string .= $generator->escape($generator->generateFromToken($token));
-        if ($index == $i) $string .= '</strong>]';
+        if ($index === $i) $string .= '</strong>]';
    }
    $string .= '</pre>';
    echo $string;
--- a/tests/HTMLPurifier/AttrDef/CSSTest.php
+++ b/tests/HTMLPurifier/AttrDef/CSSTest.php
@@ -67,6 +67,7 @@ class HTMLPurifier_AttrDef_CSSTest extends HTMLPurifier_AttrDefHarness
        $this->assertDef('border:1px solid #000;');
        $this->assertDef('border-bottom:2em double #FF00FA;');
        $this->assertDef('border-collapse:collapse;');
+        $this->assertDef('border-collapse:separate;');
        $this->assertDef('caption-side:top;');
        $this->assertDef('vertical-align:middle;');
        $this->assertDef('vertical-align:12px;');
@@ -79,6 +80,8 @@ class HTMLPurifier_AttrDef_CSSTest extends HTMLPurifier_AttrDefHarness
        $this->assertDef('background-repeat:repeat-y;');
        $this->assertDef('background-attachment:fixed;');
        $this->assertDef('background-position:left 90%;');
+        $this->assertDef('border-spacing:1em;');
+        $this->assertDef('border-spacing:1em 2em;');
        
        // duplicates
        $this->assertDef('text-align:right;text-align:left;',
--- a/tests/HTMLPurifier/AttrTransform/BdoDirTest.php
+++ b/tests/HTMLPurifier/AttrTransform/BdoDirTest.php
@@ -11,18 +11,19 @@ class HTMLPurifier_AttrTransform_BdoDirTest extends HTMLPurifier_AttrTransformHa
        $this->obj = new HTMLPurifier_AttrTransform_BdoDir();
    }
    
-    function test() {
-        
+    function testAddDefaultDir() {
        $this->assertResult( array(), array('dir' => 'ltr') );
-        
-        // leave existing dir alone
+    }
+    
+    function testPreserveExistingDir() {
        $this->assertResult( array('dir' => 'rtl') );
-        
-        // use a different default
+    }
+    
+    function testAlternateDefault() {
+        $this->config->set('Attr', 'DefaultTextDir', 'rtl');
        $this->assertResult(
            array(),
-            array('dir' => 'rtl'),
-            array('Attr.DefaultTextDir' => 'rtl')
+            array('dir' => 'rtl')
        );
        
    }
--- a/tests/HTMLPurifier/AttrTransform/BgColorTest.php
+++ b/tests/HTMLPurifier/AttrTransform/BgColorTest.php
@@ -3,6 +3,10 @@
 require_once 'HTMLPurifier/AttrTransform/BgColor.php';
 require_once 'HTMLPurifier/AttrTransformHarness.php';

+// we currently rely on the CSS validator to fix any problems.
+// This means that this transform, strictly speaking, supports
+// a superset of the functionality.
+
 class HTMLPurifier_AttrTransform_BgColorTest extends HTMLPurifier_AttrTransformHarness
 {
    
@@ -11,31 +15,31 @@ class HTMLPurifier_AttrTransform_BgColorTest extends HTMLPurifier_AttrTransformH
        $this->obj = new HTMLPurifier_AttrTransform_BgColor();
    }
    
-    function test() {
-        
+    function testEmptyInput() {
        $this->assertResult( array() );
-        
-        // we currently rely on the CSS validator to fix any problems.
-        // This means that this transform, strictly speaking, supports
-        // a superset of the functionality.
-        
+    }
+    
+    function testBasicTransform() {
        $this->assertResult(
            array('bgcolor' => '#000000'),
            array('style' => 'background-color:#000000;')
        );
-        
+    }
+    
+    function testPrependNewCSS() {
        $this->assertResult(
            array('bgcolor' => '#000000', 'style' => 'font-weight:bold'),
            array('style' => 'background-color:#000000;font-weight:bold')
        );
-        
+    }
+    
+    function testLenientTreatmentOfInvalidInput() {
        // this may change when we natively support the datatype and
        // validate its contents before forwarding it on
        $this->assertResult(
            array('bgcolor' => '#F00'),
            array('style' => 'background-color:#F00;')
        );
-        
    }
    
 }
--- a/tests/HTMLPurifier/AttrTransform/BoolToCSSTest.php
+++ b/tests/HTMLPurifier/AttrTransform/BoolToCSSTest.php
@@ -11,27 +11,29 @@ class HTMLPurifier_AttrTransform_BoolToCSSTest extends HTMLPurifier_AttrTransfor
        $this->obj = new HTMLPurifier_AttrTransform_BoolToCSS('foo', 'bar:3in;');
    }
    
-    function test() {
-        
+    function testEmptyInput() {
        $this->assertResult( array() );
-        
+    }
+    
+    function testBasicTransform() {
        $this->assertResult(
            array('foo' => 'foo'),
            array('style' => 'bar:3in;')
        );
-        
-        // boolean attribute just has to be set: we don't care about
-        // anything else
+    }
+    
+    function testIgnoreValueOfBooleanAttribute() {
        $this->assertResult(
            array('foo' => 'no'),
            array('style' => 'bar:3in;')
        );
-        
+    }
+    
+    function testPrependCSS() {
        $this->assertResult(
            array('foo' => 'foo', 'style' => 'background-color:#F00;'),
            array('style' => 'bar:3in;background-color:#F00;')
        );
-        
    }
    
 }
--- a/tests/HTMLPurifier/AttrTransform/BorderTest.php
+++ b/tests/HTMLPurifier/AttrTransform/BorderTest.php
@@ -12,27 +12,29 @@ class HTMLPurifier_AttrTransform_BorderTest extends HTMLPurifier_AttrTransformHa
        $this->obj = new HTMLPurifier_AttrTransform_Border();
    }
    
-    function test() {
-        
+    function testEmptyInput() {
        $this->assertResult( array() );
-        
+    }
+    
+    function testBasicTransform() {
        $this->assertResult(
            array('border' => '1'),
            array('style' => 'border:1px solid;')
        );
-        
-        // once again, no validation done here, we expect CSS validator
-        // to catch it
+    }
+    
+    function testLenientTreatmentOfInvalidInput() {
        $this->assertResult(
            array('border' => '10%'),
            array('style' => 'border:10%px solid;')
        );
-        
+    }
+    
+    function testPrependNewCSS() {
        $this->assertResult(
            array('border' => '23', 'style' => 'font-weight:bold;'),
            array('style' => 'border:23px solid;font-weight:bold;')
        );
-        
    }
    
 }
--- a/tests/HTMLPurifier/AttrTransform/EnumToCSSTest.php
+++ b/tests/HTMLPurifier/AttrTransform/EnumToCSSTest.php
@@ -6,38 +6,44 @@ require_once 'HTMLPurifier/AttrTransformHarness.php';
 class HTMLPurifier_AttrTransform_EnumToCSSTest extends HTMLPurifier_AttrTransformHarness
 {
    
-    function testRegular() {
-        
+    function setUp() {
+        parent::setUp();
        $this->obj = new HTMLPurifier_AttrTransform_EnumToCSS('align', array(
            'left'  => 'text-align:left;',
            'right' => 'text-align:right;'
        ));
-        
-        // leave empty arrays alone
+    }
+    
+    function testEmptyInput() {
        $this->assertResult( array() );
-        
-        // leave arrays without interesting stuff alone
+    }
+    
+    function testPreserveArraysWithoutInterestingAttributes() {
        $this->assertResult( array('style' => 'font-weight:bold;') );
-        
-        // test each of the conversions
-        
+    }
+    
+    function testConvertAlignLeft() {
        $this->assertResult(
            array('align' => 'left'),
            array('style' => 'text-align:left;')
        );
-        
+    }
+    
+    function testConvertAlignRight() {
        $this->assertResult(
            array('align' => 'right'),
            array('style' => 'text-align:right;')
        );
-        
-        // drop garbage value
+    }
+    
+    function testRemoveInvalidAlign() {
        $this->assertResult(
            array('align' => 'invalid'),
            array()
        );
-        
-        // test CSS munging
+    }
+    
+    function testPrependNewCSS() {
        $this->assertResult(
            array('align' => 'left', 'style' => 'font-weight:bold;'),
            array('style' => 'text-align:left;font-weight:bold;')
@@ -46,31 +52,23 @@ class HTMLPurifier_AttrTransform_EnumToCSSTest extends HTMLPurifier_AttrTransfor
    }
    
    function testCaseInsensitive() {
-        
        $this->obj = new HTMLPurifier_AttrTransform_EnumToCSS('align', array(
            'right' => 'text-align:right;'
        ));
-        
-        // test case insensitivity
        $this->assertResult(
            array('align' => 'RIGHT'),
            array('style' => 'text-align:right;')
        );
-        
    }
    
    function testCaseSensitive() {
-        
        $this->obj = new HTMLPurifier_AttrTransform_EnumToCSS('align', array(
            'right' => 'text-align:right;'
        ), true);
-        
-        // test case insensitivity
        $this->assertResult(
            array('align' => 'RIGHT'),
            array()
        );
-        
    }
    
 }
--- a/tests/HTMLPurifier/AttrTransform/ImgRequiredTest.php
+++ b/tests/HTMLPurifier/AttrTransform/ImgRequiredTest.php
@@ -11,39 +11,37 @@ class HTMLPurifier_AttrTransform_ImgRequiredTest extends HTMLPurifier_AttrTransf
        $this->obj = new HTMLPurifier_AttrTransform_ImgRequired();
    }
    
-    function test() {
-        
+    function testAddMissingAttr() {
+        $this->config->set('Core', 'RemoveInvalidImg', false);
        $this->assertResult(
            array(),
-            array('src' => '', 'alt' => 'Invalid image'),
-            array(
-                'Core.RemoveInvalidImg' => false
-            )
+            array('src' => '', 'alt' => 'Invalid image')
        );
-        
+    }
+    
+    function testAlternateDefaults() {
+        $this->config->set('Attr', 'DefaultInvalidImage', 'blank.png');
+        $this->config->set('Attr', 'DefaultInvalidImageAlt', 'Pawned!');
+        $this->config->set('Core', 'RemoveInvalidImg', false);
        $this->assertResult(
            array(),
-            array('src' => 'blank.png', 'alt' => 'Pawned!'),
-            array(
-                'Attr.DefaultInvalidImage' => 'blank.png',
-                'Attr.DefaultInvalidImageAlt' => 'Pawned!',
-                'Core.RemoveInvalidImg' => false
-            )
+            array('src' => 'blank.png', 'alt' => 'Pawned!')
        );
-        
+    }
+    
+    function testGenerateAlt() {
        $this->assertResult(
            array('src' => '/path/to/foobar.png'),
            array('src' => '/path/to/foobar.png', 'alt' => 'foobar.png')
        );
-        
+    }
+    
+    function testAddDefaultSrc() {
+        $this->config->set('Core', 'RemoveInvalidImg', false);
        $this->assertResult(
            array('alt' => 'intrigue'),
-            array('alt' => 'intrigue', 'src' => ''),
-            array(
-                'Core.RemoveInvalidImg' => false
-            )
+            array('alt' => 'intrigue', 'src' => '')
        );
-        
    }
    
 }
--- a/tests/HTMLPurifier/AttrTransform/ImgSpaceTest.php
+++ b/tests/HTMLPurifier/AttrTransform/ImgSpaceTest.php
@@ -9,33 +9,35 @@ class HTMLPurifier_AttrTransform_ImgSpaceTest extends HTMLPurifier_AttrTransform
    
    function setUp() {
        parent::setUp();
+        $this->obj = new HTMLPurifier_AttrTransform_ImgSpace('vspace');
    }
    
-    function testVertical() {
-        
-        $this->obj = new HTMLPurifier_AttrTransform_ImgSpace('vspace');
-        
+    function testEmptyInput() {
        $this->assertResult( array() );
-        
+    }
+    
+    function testVerticalBasicUsage() {
        $this->assertResult(
            array('vspace' => '1'),
            array('style' => 'margin-top:1px;margin-bottom:1px;')
        );
-        
-        // no validation done here, we expect CSS validator to catch it
+    }
+    
+    function testLenientHandlingOfInvalidInput() {
        $this->assertResult(
            array('vspace' => '10%'),
            array('style' => 'margin-top:10%px;margin-bottom:10%px;')
        );
-        
+    }
+    
+    function testPrependNewCSS() {
        $this->assertResult(
            array('vspace' => '23', 'style' => 'font-weight:bold;'),
            array('style' => 'margin-top:23px;margin-bottom:23px;font-weight:bold;')
        );
-        
    }
    
-    function testHorizontal() {
+    function testHorizontalBasicUsage() {
        $this->obj = new HTMLPurifier_AttrTransform_ImgSpace('hspace');
        $this->assertResult(
            array('hspace' => '1'),
@@ -43,7 +45,7 @@ class HTMLPurifier_AttrTransform_ImgSpaceTest extends HTMLPurifier_AttrTransform
        );
    }
    
-    function testInvalid() {
+    function testInvalidConstructionParameter() {
        $this->expectError('ispace is not valid space attribute');
        $this->obj = new HTMLPurifier_AttrTransform_ImgSpace('ispace');
        $this->assertResult(
--- a/Show More
+++ b/Show More
Author	SHA1	Message	Date
Edward Z. Yang	9db861e356	Release 2.1.3, merged in 1404 to HEAD. git-svn-id: http://htmlpurifier.org/svnroot/htmlpurifier/branches/strict@1444 48356398-32a2-884e-a903-53898d9a118a	2007-11-06 04:34:33 +00:00
Edward Z. Yang	b3f0e6c86c	Release 2.1.2, merged in 1368 to HEAD. git-svn-id: http://htmlpurifier.org/svnroot/htmlpurifier/branches/strict@1404 48356398-32a2-884e-a903-53898d9a118a	2007-09-03 15:40:43 +00:00
Edward Z. Yang	80c60bb9b5	Release 2.1.0, merged in 1255 to HEAD. git-svn-id: http://htmlpurifier.org/svnroot/htmlpurifier/branches/strict@1368 48356398-32a2-884e-a903-53898d9a118a	2007-08-05 02:02:46 +00:00
Edward Z. Yang	503e76081b	Revert to 2.0.1, it appears that the 2.1.0 merge was done improperly. git-svn-id: http://htmlpurifier.org/svnroot/htmlpurifier/branches/strict@1367 48356398-32a2-884e-a903-53898d9a118a	2007-08-05 01:42:52 +00:00
@@ -1 +1 @@
 .1.0
 .1.3
				`@@ -0,0 +1 @@`
				`The contents of the library/ folder should be here.`