Fix typo in NEWS item.

git-svn-id: http://htmlpurifier.org/svnroot/htmlpurifier/branches/1.1@477 48356398-32a2-884e-a903-53898d9a118a

CREDITS

@@ -2,6 +2,6 @@
 CREDITS
 
 Almost everything written by Edward Z. Yang (Ambush Commander).  Lots of thanks
-to the DevNetwork Community for their help (see docs/ref-devnetwork.html for
+to the DevNetwork Community for their help (see docs/devnetwork.html for more
-more details), Feyd especially (namely IPv6 and optimization).  Thanks to RSnake
+details), Feyd especially (namely IPv6 and optimization).  Thanks to RSnake for
-for letting me package his fantastic XSS cheatsheet for a smoketest.
+letting me package his fantastic XSS cheatsheet for a smoketest.

Doxyfile

@@ -4,7 +4,7 @@
 # Project related configuration options
 #---------------------------------------------------------------------------
 PROJECT_NAME           = HTML Purifier
-PROJECT_NUMBER         = 1.4.1
+PROJECT_NUMBER         = 1.1.2
 OUTPUT_DIRECTORY       = "C:/Documents and Settings/Edward/My Documents/My Webs/htmlpurifier/docs/doxygen"
 CREATE_SUBDIRS         = NO
 OUTPUT_LANGUAGE        = English

INSTALL

@@ -8,7 +8,6 @@ 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.
 
-Todo: Convert to using the array syntax for configuration.
 
 
 1.  Compatibility
@@ -26,7 +25,7 @@ not having either of these extensions.
 
 Simply use:
 
-    require_once '/path/to/library/HTMLPurifier.auto.php';
+	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.
@@ -34,7 +33,7 @@ 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';
+	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.  

NEWS

@@ -2,122 +2,12 @@ NEWS ( CHANGELOG and HISTORY )                                     HTMLPurifier
 |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
 
 = KEY ====================
-    # Breaks back-compat
     ! Feature
     - Bugfix
       + Sub-comment
     . Internal change
 ==========================
 
-1.4.1, released 2007-01-21
-! docs/enduser-youtube.html updated according to new functionality
-- YouTube IDs can have underscores and dashes
-
-1.4.0, released 2007-01-21
-! Implemented list-style-image, URIs now allowed in list-style
-! Implemented background-image, background-repeat, background-attachment
-  and background-position CSS properties. Shorthand property background
-  supports all of these properties.
-! Configuration documentation looks nicer
-! Added %Core.EscapeNonASCIICharacters to workaround loss of Unicode
-  characters while %Core.Encoding is set to a non-UTF-8 encoding.
-! Support for configuration directive aliases added
-! Config object can now be instantiated from ini files
-! YouTube preservation code added to the core, with two lines of code
-  you can add it as a filter to your code. See smoketests/preserveYouTube.php
-  for sample code.
-! Moved SLOW to docs/enduser-slow.html and added code examples
-- Replaced version check with functionality check for DOM (thanks Stephen
-  Khoo)
-. Added smoketest 'all.php', which loads all other smoketests via frames
-. Implemented AttrDef_CSSURI for url(http://google.com) style declarations
-. Added convenient single test selector form on test runner
-
-1.3.2, released 2006-12-25
-! HTMLPurifier object now accepts configuration arrays, no need to manually
-  instantiate a configuration object
-! Context object now accessible to outside
-! Added enduser-youtube.html, explains how to embed YouTube videos. See
-  also corresponding smoketest preserveYouTube.php.
-! Added purifyArray(), which takes a list of HTML and purifies it all
-! Added static member variable $version to HTML Purifier with PHP-compatible
-  version number string.
-- Fixed fatal error thrown by upper-cased language attributes
-- printDefinition.php: added labels, added better clarification
-. HTMLPurifier_Config::create() added, takes mixed variable and converts into
-  a HTMLPurifier_Config object.
-
-1.3.1, released 2006-12-06
-! Added HTMLPurifier.func.php stub for a convenient function to call the library
-- Fixed bug in RemoveInvalidImg code that caused all images to be dropped
-  (thanks to .mario for reporting this)
-. Standardized all attribute handling variables to attr, made it plural
-
-1.3.0, released 2006-11-26
-# Invalid images are now removed, rather than replaced with a dud
-  <img src="" alt="Invalid image" />. Previous behavior can be restored
-  with new directive %Core.RemoveInvalidImg set to false.
-! (X)HTML Strict now supported
-  + Transparently handles inline elements in block context (blockquote)
-! Added GET method to demo for easier validation, added 50kb max input size
-! New directive %HTML.BlockWrapper, for block-ifying inline elements
-! New directive %HTML.Parent, allows you to only allow inline content
-! New directives %HTML.AllowedElements and %HTML.AllowedAttributes to let
-  users narrow the set of allowed tags
-! <li value="4"> and <ul start="2"> now allowed in loose mode
-! New directives %URI.DisableExternalResources and %URI.DisableResources
-! New directive %Attr.DisableURI, which eliminates all hyperlinking
-! New directive %URI.Munge, munges URI so you can use some sort of redirector
-  service to avoid PageRank leaks or warn users that they are exiting your site.
-! Added spiffy new smoketest printDefinition.php, which lets you twiddle with
-  the configuration settings and see how the internal rules are affected.
-! New directive %URI.HostBlacklist for blocking links to bad hosts.
-  xssAttacks.php smoketest updated accordingly.
-- Added missing type to ChildDef_Chameleon
-- Remove Tidy option from demo if there is not Tidy available
-. ChildDef_Required guards against empty tags
-. Lookup table HTMLDefinition->info_flow_elements added
-. Added peace-of-mind variable initialization to Strategy_FixNesting
-. Added HTMLPurifier->info_parent_def, parent child processing made special
-. Added internal documents briefly summarizing future progression of HTML
-. HTMLPurifier_Config->getBatch($namespace) added
-. More lenient casting to bool from string in HTMLPurifier_ConfigSchema
-. Refactored ChildDef classes into their own files
-
-1.2.0, released 2006-11-19
-# ID attributes now disabled by default. New directives:
-  + %HTML.EnableAttrID - restores old behavior by allowing IDs
-  + %Attr.IDPrefix - %Attr.IDBlacklist alternative that munges all user IDs
-    so that they don't collide with your IDs
-  + %Attr.IDPrefixLocal - Same as above, but for when there are multiple
-    instances of user content on the page
-  + Profuse documentation on how to use these available in docs/enduser-id.txt
-! Added MODx plugin <http://modxcms.com/forums/index.php/topic,6604.0.html>
-! Added percent encoding normalization
-! XSS attacks smoketest given facelift
-! Configuration documentation now has table of contents
-! Added %URI.DisableExternal, which prevents links to external websites.  You
-  can also use %URI.Host to permit absolute linking to subdomains
-! Non-accessible resources (ex. mailto) blocked from embedded URIs (img src)
-- Type variable in HTMLDefinition was not being set properly, fixed
-- Documentation updated
-  + TODO added request Phalanger
-  + TODO added request Native compression
-  + TODO added request Remove redundant tags
-  + TODO added possible plaintext formatter for HTML Purifier documentation
-  + Updated ConfigDoc TODO
-  + Improved inline comments in AttrDef/Class.php, AttrDef/CSS.php
-    and AttrDef/Host.php
-  + Revamped documentation into HTML, along with misc updates
-- HTMLPurifier_Context doesn't throw a variable reference error if you attempt
-  to retrieve a non-existent variable
-. Switched to purify()-wide Context object registry
-. Refactored unit tests to minimize duplication
-. XSS attack sheet updated
-. configdoc.xml now has xml:space attached to default value nodes
-. Allow configuration directives to permit null values
-. Cleaned up test-cases to remove unnecessary swallowErrors()
-
 1.1.2, released 2006-09-30
 ! Add HTMLPurifier.auto.php stub file that configures include_path
 - Documentation updated

README

@@ -1,22 +1,13 @@
 
 README
-    All about HTML Purifier
+    All about HTMLPurifier
 
-HTML Purifier is an HTML filtering solution that uses a unique combination 
+HTMLPurifier is an HTML filtering solution.  It uses a unique combination of
-of robust whitelists and agressive parsing to ensure that not only are 
+robust whitelists and agressive parsing to ensure that not only are XSS
-XSS attacks thwarted, but the resulting HTML is standards compliant. 
+attacks thwarted, but the resulting HTML is standards compliant.
 
-HTML Purifier is oriented towards richly formatted documents from 
+See INSTALL on how to use the library.  See docs/ for more developer-oriented
-untrusted sources that require CSS and a full tag-set.  This library can 
+documentation as well as some code examples.  Users of TinyMCE or FCKeditor
-be configured to accept a more restrictive set of tags, but it won't be 
+may be especially interested in WYSIWYG.
-as efficient as more bare-bones parsers. It will, however, do the job 
-right, which may be more important. 
 
-Places to go:
+HTMLPurifier can be found on the web at: http://hp.jpsband.org/
-
-* See INSTALL for a quick installation guide
-* See docs/ for developer-oriented documentation, code examples and
-  an in-depth installation guide.
-* See WYSIWYG for information on editors like TinyMCE and FCKeditor
-
-HTML Purifier can be found on the web at: http://hp.jpsband.org/

SLOW

@@ -0,0 +1,39 @@
+
+SLOW
+  also known as the HELP ME LIBRARY IS TOO SLOW MY PAGE TAKE TOO LONG LOAD page
+
+HTMLPurifier is a very powerful library.  But with power comes great
+responsibility, or, at least, longer execution times.  Remember, this
+library isn't lightly grazing over submitted HTML: it's deconstructing
+the whole thing, rigorously checking the parts, and then putting it
+back together.
+
+So, if it so turns out that HTMLPurifier is kinda too slow for outbound
+filtering, you've got a few options:
+
+1. Inbound filtering - perform filtering of HTML when it's submitted by the
+user.  Since the user is already submitting something, an extra half a
+second tacked on to the load time probably isn't going to be that huge of
+a problem.  Then, displaying the content is a simple a manner of outputting
+it directly from your database/filesystem.  The trouble with this method is
+that your user loses the original text, and when doing edits, will be
+handling the filtered text.  While this may be a good thing, especially if
+you're using a WYSIWYG editor, it can also result in data-loss if a user
+expects a certain to be available but it doesn't.
+
+2. Caching the filtered output - accept the submitted text and put it
+unaltered into the database, but then also generate a filtered version and
+stash that in the database.  Serve the filtered version to readers, and the
+unaltered version to editors.  If need be, you can invalidate the cache and
+have the cached filtered version be regenerated on the first page view.  Pros?
+Full data retention.  Cons?  It's more complicated, and opens other editors
+up to XSS if they are using a WYSIWYG editor (to fix that, they'd have to
+be able to get their hands on the *really* original text served in plaintext
+mode).
+
+In short, inbound filtering is almost as simple as outbound filtering, but
+it has some drawbacks which cannot be fixed unless you save both the original
+and the filtered versions.
+
+There is a third option: profile and optimize HTMLPurifier yourself.  Be sure
+to tell me if you decide to do that!  ;-)

TODO

@@ -1,91 +1,53 @@
 
 TODO List
 
-= KEY ====================
+Ongoing
-    # Flagship
+ - Lots of profiling, make it faster!
-    - Regular
+ - Plugins for major CMSes (very tricky issue)
-    ? At-risk
-==========================
 
-1.5 release
+1.2 release
- # Implement all non-essential attribute transforms, configurable
+ - Make URI validation routines tighter (especially mailto)
- # URI validation routines tighter (see docs/dev-code-quality.html) (COMPLEX)
+ - More extensive URI filtering schemes
- # Advanced URI filtering schemes (see docs/proposal-new-directives.txt)
+ - Allow for background-image and list-style-image (see above)
- # Error logging for filtering/cleanup procedures
+ - Distinguish between different types of URIs, for instance, a mailto URI
-    - Requires I18N facilities to be created first (COMPLEX)
+   in IMG SRC is nonsensical
- ? Configuration profiles: sets of directives that get set with one func call
+ - Error logging for filtering/cleanup procedures
- - XSS-attempt detection
 
-1.6 release
+1.3 release
- # Add pre-packaged "levels" of cleaning (custom behavior already done)
+ - Add various "levels" of cleaning
- - More fine-grained control over escaping behavior
+    - Related: Allow strict (X)HTML
-    - Silently drop content inbetween SCRIPT tags (can be generalized to allow
-      specification of elements that, when detected as foreign, trigger removal
-      of children, although unbalanced tags could wreck havoc (or at least
-      delete the rest of the document)).
- - Allow specifying global attributes on a tag-by-tag basis in
-   %HTML.AllowAttributes
- ? More user-friendly warnings when %HTML.Allow* attempts to specify a
-   tag or attribute that is not supported
- - Parse TinyMCE whitelist into our %HTML.Allow* whitelists
 
-1.7 release
+1.4 release
- # Additional support for poorly written HTML
+ - Additional support for poorly written HTML
-    - Microsoft Word HTML cleaning (i.e. MsoNormal, but research essential!)
+    - Implement all non-essential attribute transforms
-    - Friendly strict handling of <address> (block -> <br>)
+    - Microsoft Word HTML cleaning (i.e. MsoNormal)
- - Remove redundant tags, ex. <u><u>Underlined</u></u>. Implementation notes:
-    1. Analyzing which tags to remove duplicants
-    2. Ensure attributes are merged into the parent tag
-    3. Extend the tag exclusion system to specify whether or not the
-    contents should be dropped or not (currently, there's code that could do
-    something like this if it didn't drop the inner text too.)
- - Remove <span> tags that don't do anything (no attributes)
- - 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)
 
 2.0 release
- # Legit token based CSS parsing (will require revamping almost every
+ - Formatters for plaintext
-   AttrDef class)
- # Formatters for plaintext (COMPLEX)
     - Auto-paragraphing (be sure to leverage fact that we know when things
       shouldn't be paragraphed, such as lists and tables).
     - Linkify URLs
     - Smileys
-    - Linkification for HTML Purifier docs: notably configuration and classes
 
 3.0 release
- - Extended HTML capabilities based on namespacing and tag transforms (COMPLEX)
+ - Extended HTML capabilities based on namespacing and tag transforms
     - Hooks for adding custom processors to custom namespaced tags and
       attributes, offer default implementation
     - Lots of documentation and samples
- - Allow tags to be "armored", an internal flag that protects them
+
-   from validation and passes them out unharmed
+Unknown release (on a scratch-an-itch basis)
- - XHTML 1.1 support
+ - Silently drop content inbetween SCRIPT tags (can be generalized to allow
+   specification of elements that, when detected as foreign, trigger removal
+   of children, although unbalanced tags could wreck havoc (or at least delete
+   the rest of the document)).
  - 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.
+ - Non-lossy dumb alternate character encoding transformations, achieved by
-   Also, enable disabling of directionality
+   numerically encoding all non-ASCII characters
-
+ - Semi-lossy dumb alternate character encoding transformations, achieved by
-Ongoing
- - Lots of profiling, make it faster!
- - Plugins for major CMSes (COMPLEX)
-    - WordPress
-    - eFiction
-    - more! (look for ones that use WYSIWYGs)
-
-Unknown release (on a scratch-an-itch basis)
- - Upgrade SimpleTest testing code to newest versions
- - Have 'lang' attribute be checked against official lists
- ? Semi-lossy dumb alternate character encoding transformations, achieved by
    encoding all characters that have string entity equivalents
 
-Requested
- ? Native content compression, whitespace stripping (don't rely on Tidy, make
-   sure we don't remove from <pre> or related tags)
-
 Wontfix
- - Non-lossy smart alternate character encoding transformations (unless
+ - Non-lossy smart alternate character encoding transformations
-   patch provided)
  - Pretty-printing HTML, users can use Tidy on the output on entire page

WYSIWYG

@@ -18,5 +18,4 @@ HTML Purifier is perfect for filtering pure-HTML input from WYSIWYG editors.
 Enough said.
 
 There is a proof-of-concept integration of HTML Purifier with the Mantis
-bugtracker at http://hp.jpsband.org/mantis/ You can see notes on how
+bugtracker at http://hp.jpsband.org/mantis/
-this integration was acheived at http://hp.jpsband.org/mantis_notes.txt

configdoc/generate.php

@@ -12,8 +12,10 @@ TODO:
 - multipage documentation
 - determine how to multilingualize
 - factor out code into classes
+- generate a table of contents
 */
 
+
 // ---------------------------------------------------------------------------
 // Check and configure environment
 
@@ -80,6 +82,9 @@ $dom_root->appendChild($dom_document->createElement('title', 'HTML Purifier'));
 
 /*
 TODO for XML format:
+- namespace descriptions
+- enumerated values
+- default values
 - create a definition (DTD or other) once interface stabilizes
 */
 
@@ -99,8 +104,6 @@ foreach($schema->info as $namespace_name => $namespace_info) {
     
     foreach ($namespace_info as $name => $info) {
         
-        if ($info->class == 'alias') continue;
-        
         $dom_directive = $dom_document->createElement('directive');
         $dom_namespace->appendChild($dom_directive);
         
@@ -112,12 +115,9 @@ foreach($schema->info as $namespace_name => $namespace_info) {
         $dom_constraints = $dom_document->createElement('constraints');
         $dom_directive->appendChild($dom_constraints);
         
-        $dom_type = $dom_document->createElement('type', $info->type);
+        $dom_constraints->appendChild(
-        if ($info->allow_null) {
+            $dom_document->createElement('type', $info->type)
-            $dom_type->setAttribute('allow-null', 'yes');
+        );
-        }
-        $dom_constraints->appendChild($dom_type);
-        
         if ($info->allowed !== true) {
             $dom_allowed = $dom_document->createElement('allowed');
             $dom_constraints->appendChild($dom_allowed);
@@ -133,20 +133,14 @@ foreach($schema->info as $namespace_name => $namespace_info) {
             $default = $raw_default ? 'true' : 'false';
         } elseif (is_string($raw_default)) {
             $default = "\"$raw_default\"";
-        } elseif (is_null($raw_default)) {
-            $default = 'null';
         } else {
             $default = print_r(
                     $schema->defaults[$namespace_name][$name], true
                 );
         }
-        
+        $dom_constraints->appendChild(
-        $dom_default = $dom_document->createElement('default', $default);
+            $dom_document->createElement('default', $default)
-        
+        );
-        // remove this once we get a DTD
-        $dom_default->setAttribute('xml:space', 'preserve');
-        
-        $dom_constraints->appendChild($dom_default);
         
         $dom_descriptions = $dom_document->createElement('descriptions');
         $dom_directive->appendChild($dom_descriptions);

configdoc/styles/plain.css

@@ -1,6 +1,3 @@
-
-body {margin:1em 4em;}
-
 table {border-collapse:collapse;}
 table td, table th {padding:0.2em;}
 
@@ -8,17 +5,3 @@ table.constraints {margin:0 0 1em;}
 table.constraints th {text-align:left;padding-left:0.4em;}
 table.constraints td {padding-right:0.4em;}
 table.constraints td pre {margin:0;}
-
-#toc {list-style-type:none; font-weight:bold;}
-#toc ul {list-style-type:disc; font-weight:normal;}
-
-.description p {margin-top:0;margin-bottom:1em;}
-
-#library, h1 {text-align:center; font-family:Garamond, serif;
-  font-variant:small-caps;}
-#library {font-size:1em;}
-h1 {margin-top:0;}
-h2 {border-bottom:1px solid #CCC; font-family:sans-serif; font-weight:normal;
-    font-size:1.3em;}
-h3 {font-family:sans-serif; font-size:1.1em; font-weight:bold; }
-h4 {font-family:sans-serif; font-size:0.9em; font-weight:bold; }

configdoc/styles/plain.xsl

@@ -18,47 +18,28 @@
     <xsl:template match="/">
         <html lang="en" xml:lang="en">
             <head>
-                <title>Configuration Documentation - <xsl:value-of select="/configdoc/title" /></title>
+                <title><xsl:value-of select="/configdoc/title" /> Configuration Documentation</title>
                 <meta http-equiv="Content-Type" content="text/html;charset=UTF-8" />
                 <link rel="stylesheet" type="text/css" href="styles/plain.css" />
             </head>
             <body>
-                <div id="library"><xsl:value-of select="/configdoc/title" /></div>
-                <h1>Configuration Documentation</h1>
-                <h2>Table of Contents</h2>
-                <ul id="toc">
-                    <xsl:apply-templates mode="toc" />
-                </ul>
                 <xsl:apply-templates />
             </body>
         </html>
     </xsl:template>
     
-    <xsl:template match="title" mode="toc" />
+    <xsl:template match="title">
-    <xsl:template match="namespace" mode="toc">
+        <h1><xsl:value-of select="/configdoc/title" /> Configuration Documentation</h1>
-        <xsl:if test="count(directive)&gt;0">
-            <li>
-                <a href="#{@id}"><xsl:value-of select="name" /></a>
-                <ul>
-                    <xsl:apply-templates select="directive" mode="toc" />
-                </ul>
-            </li>
-        </xsl:if>
     </xsl:template>
-    <xsl:template match="directive" mode="toc">
-        <li><a href="#{@id}"><xsl:value-of select="name" /></a></li>
-    </xsl:template>
-    
-    <xsl:template match="title" />
     
     <xsl:template match="namespace">
         <xsl:apply-templates />
-        <xsl:if test="count(directive)=0">
+        <xsl:if test="count(child::directive)=0">
             <p>No configuration directives defined for this namespace.</p>
         </xsl:if>
     </xsl:template>
     <xsl:template match="namespace/name">
-        <h2 id="{../@id}"><xsl:value-of select="." /></h2>
+        <h2 id="{../@id}"><xsl:value-of select="text()" /></h2>
     </xsl:template>
     <xsl:template match="namespace/description">
         <div class="description">
@@ -70,7 +51,7 @@
         <xsl:apply-templates />
     </xsl:template>
     <xsl:template match="directive/name">
-        <h3 id="{../@id}"><xsl:value-of select="../@id" /></h3>
+        <h3 id="{../@id}"><xsl:value-of select="text()" /></h3>
     </xsl:template>
     <xsl:template match="directive/constraints">
         <table class="constraints">
@@ -100,9 +81,6 @@
                 <xsl:variable name="type" select="text()" />
                 <xsl:attribute name="class">type type-<xsl:value-of select="$type" /></xsl:attribute>
                 <xsl:value-of select="$typeLookup/types/type[@id=$type]/text()" />
-                <xsl:if test="@allow-null='yes'">
-                    (or null)
-                </xsl:if>
             </td>
         </tr>
     </xsl:template>

docs/code-quality.txt

@@ -0,0 +1,39 @@
+
+Code Quality Issues
+
+Okay, face it.  Programmers can get lazy, cut corners, or make mistakes. They
+also can do quick prototypes, and then forget to rewrite them later.  Well,
+while I can't list mistakes in here, I can list prototype-like segments
+of code that should be aggressively refactored after the beta is released.
+This does not list optimization issues, that needs to be done after intense
+profiling.
+
+Here we go:
+
+AttrDef
+    Class - doesn't support Unicode characters (fringe); uses regular
+        expressions
+    Lang - code duplication; premature optimization; doesn't consult official
+        lists (fringe)
+    Length - easily mistaken for CSSLength
+    URI - multiple regular expressions; needs host validation routines factored
+        out for mailto scheme; missing validation for query; fragment and path,
+        no percent-encode fixing
+    CSS - parser doesn't accept advanced CSS (fringe)
+    Number - constructor interface is inconsistent with Integer
+AttrTransform - doesn't accept AttrContext
+Config - "load configuration" hooks missing, rich set* accessors missing
+ConfigSchema - redefinition is a mess
+Strategy
+    FixNesting - cannot bubble nodes out of structures
+    MakeWellFormed - insufficient automatic closing definitions (check HTML
+        spec for optional end tags, also, closing based on type (block/inline)
+        might be efficient).
+    RemoveForeignElements - should be run in parallel with MakeWellFormed
+URIScheme - needs to have callable generic checks
+    ftp - missing typecode check
+    mailto - doesn't validate emails
+    news - doesn't validate opaque path
+    nntp - doesn't constrain path
+EOL
+

docs/colors.txt

@@ -0,0 +1,23 @@
+
+Colors
+    Hammering some sense into those content-makers
+
+Your website probably has a color-scheme. Green on white, purple on yellow,
+whatever. When you give users the ability to style their content, you may
+want them to keep in line with your styling. If you're website is all
+about light colors, you don't want a user to come in and vandalize your
+page with a deep maroon.
+
+This is an extremely silly feature proposal, but I'm writing it down anyway.
+
+What if the user could constrain the colors specified in inline styles? You
+are only allowed to use these shades of dark green for text and these shades
+of light yellow for the background. At the very least, you could ensure
+that we did not have pale yellow on white text.
+
+Implementation issues:
+1. Requires the color attribute definition to know, currently, what the text
+and background colors are. This becomes difficult when classes are thrown
+into the mix.
+2. The user still has to define the permissible colors, how does one do
+something like that?

docs/config-ideas.txt

@@ -0,0 +1,46 @@
+
+Configuration Ideas
+
+Here are some theoretical configuration ideas that we could implement some
+time.  Note the naming convention: %Namespace.Directive
+
+%Attr.IDPrefix - prefix all ids with this
+
+%Attr.RewriteFragments - if there's %Attr.IDPrefix we may want to transparently
+    rewrite the URLs we parse too.  However, we can only do it when it's a pure
+    anchor link, so it's not foolproof
+
+%Attr.ClassBlacklist,
+%Attr.ClassWhitelist,
+%Attr.ClassListMode - determines what classes are allowed. When
+    %Attr.ClassListMode is set to Blacklist, only allow those not in
+    %Attr.ClassBlacklist. When it's Whitelist, only allow those in
+    %Attr.ClassWhitelist.
+
+%Attr.LangAlphaOnly - designate whether or not to allow numerals in language
+    code subtags
+    * RFC 1766, the current standard referenced by XML, does not permit
+        numbers, but,
+    * RFC 3066, the superseding best practice standard since January 2001,
+        permits them.
+    We allow numbers by default, but you generally never see them
+    at all, which makes this a little more sane.
+
+%Attr.MaxWidth, 
+%Attr.MaxHeight - caps for width and height related checks.
+    (a hack in Pixels for an image crashing attack could be replaced by this)
+
+%URI.Munge - will munge all URIs to a different URI, which should redirect
+    the user to the applicable page. A urlencoded version of the URI
+    will replace any instances of %s in the string. One possible
+    string is 'http://www.google.com/url?q=%s'. Useful for preventing
+    pagerank from being sent to other sites
+
+%URI.AddRelNofollow - will add rel="nofollow" to all links, preventing the
+    spread of ill-gotten pagerank
+
+%URI.Host - host of website, for external link checks
+
+%URI.RelativeToAbsolute - transforms all relative URIs to absolute form
+
+%URI.DisableExternal - disable external links

docs/config.txt

@@ -10,19 +10,22 @@ Directives are divided into namespaces, indicating the major portion of
 functionality they cover (although there may be overlaps.  Please consult
 the documentation in ConfigDef for more information on these namespaces.
 
-Since configuration is dependant on context, internal classes require a
+Since configuration is dependent on context, most of the internal classes
-configuration object to be passed as a parameter.  (They also require a
+require a configuration object to be passed as a parameter.  However, a few
-Context object).
+make this optional: they will supply a default configuration object if none
+are passed.  These classes are: HTMLPurifier::*, Generator::generateFromTokens
+and Lexer::tokenizeHTML.  However, whenever a valid configuration object
+is defined, that object should be used.
 
-In relation to HTMLDefinition and CSSDefinition, there could be a special class
+In relation to HTMLDefinition and CSSDefinition, there is a special class
 of directives that influence the *construction* of the Definition object.
-A theoretical call pattern would look like:
+A standard call pattern would look like:
 
 1. Client calls Config->getHTMLDefinition()
 2. Config calls HTMLDefinition->createNew(this)
 3. HTMLDefinition constructs itself with base configuration
-4. HTMLDefinition calls Config->get('HTML')
+4. HTMLDefinition calls Config->get('HTMLDefinition')
-5. Config returns array of directives
+5. Config returns array of directives that later construction
 6. HTMLDefinition performs operations and changes specified by directives
 7. HTMLPurifier returns constructed definition
 8. Config caches definition so it doesn't have to be generated again
@@ -33,7 +36,3 @@ custom copy, which OVERRIDES all directives.  Only the base, vanilla copy
 is the Singleton, the object actually interfaced with is a operated-upon
 clone of that object.  Also, if an update to the directives would update
 the definition, you'd have to force reconstruction.
-
-In practice, the pulling directives from the config object are
-solely need-based, and the flex points are littered throughout the
-setup() function.  Some sort of refactoring is likely in order.

docs/dev-code-quality.html

@@ -1,52 +0,0 @@
-<?xml version="1.0" encoding="UTF-8"?>
-<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN"
-    "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">
-<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en"><head>
-<meta http-equiv="Content-Type" content="text/html; charset=UTF-8" />
-<meta name="description" content="Discusses code quality issues and places that need to be refactored in HTML Purifier." />
-<link rel="stylesheet" type="text/css" href="./style.css" />
-
-<title>Code Quality Issues - HTML Purifier</title>
-
-</head><body>
-
-<h1>Code Quality Issues</h1>
-
-<div id="filing">Filed under Development</div>
-<div id="index">Return to the <a href="index.html">index</a>.</div>
-<div id="home"><a href="http://hp.jpsband.org/">HTML Purifier</a> End-User Documentation</div>
-
-<p>Okay, face it.  Programmers can get lazy, cut corners, or make mistakes. They
-also can do quick prototypes, and then forget to rewrite them later.  Well,
-while I can't list mistakes in here, I can list prototype-like segments
-of code that should be aggressively refactored.  This does not list
-optimization issues, that needs to be done after intense profiling.</p>
-
-<pre>
-docs/examples/demo.php - ad hoc HTML/PHP soup to the extreme
-
-AttrDef
-    Class - doesn't support Unicode characters (fringe); uses regular
-        expressions
-    Lang - code duplication; premature optimization
-    Length - easily mistaken for CSSLength
-    URI - multiple regular expressions; missing validation for parts (?)
-    CSS - parser doesn't accept advanced CSS (fringe)
-    Number - constructor interface inconsistent with Integer
-ConfigSchema - redefinition is a mess
-Strategy
-    FixNesting - cannot bubble nodes out of structures, duplicated checks
-        for special-case parent node
-    MakeWellFormed - insufficient automatic closing definitions (check HTML
-        spec for optional end tags, also, closing based on type (block/inline)
-        might be efficient).
-    RemoveForeignElements - should be run in parallel with MakeWellFormed
-URIScheme - needs to have callable generic checks
-    mailto - doesn't validate emails, doesn't validate querystring
-    news - doesn't validate opaque path
-    nntp - doesn't constrain path
-</pre>
-
-<div id="version">$Id$</div>
-
-</body></html>

docs/dev-naming.html

@@ -1,82 +0,0 @@
-<?xml version="1.0" encoding="UTF-8"?>
-<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN"
-    "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">
-<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en"><head>
-<meta http-equiv="Content-Type" content="text/html; charset=UTF-8" />
-<meta name="description" content="Defines class naming conventions in HTML Purifier." />
-<link rel="stylesheet" type="text/css" href="./style.css" />
-
-<title>Naming Conventions - HTML Purifier</title>
-
-</head><body>
-
-<h1>Naming Conventions</h1>
-
-<div id="filing">Filed under Development</div>
-<div id="index">Return to the <a href="index.html">index</a>.</div>
-<div id="home"><a href="http://hp.jpsband.org/">HTML Purifier</a> End-User Documentation</div>
-
-<p>The classes in this library follow a few naming conventions, which may
-help you find the correct functionality more quickly.  Here they are:</p>
-
-<dl>
-
-<dt>All classes occupy the HTMLPurifier pseudo-namespace.</dt>
-    <dd>This means that all classes are prefixed with HTMLPurifier_.  As such, all
-    names under HTMLPurifier_ are reserved.  I recommend that you use the name
-    HTMLPurifierX_YourName_ClassName, especially if you want to take advantage
-    of HTMLPurifier_ConfigDef.</dd>
-
-<dt>All classes correspond to their path if library/ was in the include path</dt>
-    <dd>HTMLPurifier_AttrDef is located at HTMLPurifier/AttrDef.php; replace
-    underscores with slashes and append .php and you'll have the location of
-    the class.</dd>
-
-<dt>Harness and Test are reserved class names for unit tests</dt>
-    <dd>The suffix <code>Test</code> indicates that the class is a subclass of UnitTestCase
-    (of the Simpletest library) and is testable. "Harness" indicates a subclass
-    of UnitTestCase that is not meant to be run but to be extended into 
-    concrete test cases and contains custom test methods (i.e. assert*())</dd>
-
-<dt>Class names do not necessarily represent inheritance hierarchies</dt>
-    <dd>While we try to reflect inheritance in naming to some extent, it is not
-    guaranteed (for instance, none of the classes inherit from HTMLPurifier,
-    the base class).  However, all class files have the require_once
-    declarations to whichever classes they are tightly coupled to.</dd>
-
-<dt>Strategy has a meaning different from the Gang of Four pattern</dt>
-    <dd>In Design Patterns, the Gang of Four describes a Strategy object as
-    encapsulating an algorithm so that they can be switched at run-time.  While
-    our strategies are indeed algorithms, they are not meant to be substituted:
-    all must be present in order for proper functioning.</dd>
-
-<dt>Abbreviations are avoided</dt>
-    <dd>We try to avoid abbreviations as much as possible, but in some cases, 
-    abbreviated version is more readable than the full version. Here, we
-    list common abbreviations:
-    <ul>
-        <li>Attr to Attributes (note that it is plural, i.e. <code>$attr = array()</code>)</li>
-        <li>Def to Definition</li>
-        <li><code>$ret</code> is the value to be returned in a function</li>
-    </ul>
-    </dd>
-
-<dt>Ambiguity concerning the definition of Def/Definition</dt>
-    <dd>While a definition normally defines the structure/acceptable values of
-    an entity, most of the definitions in this application also attempt
-    to validate and fix the value.  I am unsure of a better name, as
-    "Validator" would exclude fixing the value, "Fixer" doesn't invoke
-    the proper image of "fixing" something, and "ValidatorFixer" is too long!
-    Some other suggestions were "Handler", "Reference", "Check", "Fix",
-    "Repair" and "Heal".</dd>
-
-<dt>Transform not Transformer</dt>
-    <dd>Transform is both a noun and a verb, and thus we define a "Transform" as
-    something that "transforms," leaving "Transformer" (which sounds like an
-    electrical device/robot toy).</dd>
-
-</dl>
-
-<div id="version">$Id$</div>
-
-</body></html>

docs/dev-optimization.html

@@ -1,33 +0,0 @@
-<?xml version="1.0" encoding="UTF-8"?>
-<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN"
-    "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">
-<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en"><head>
-<meta http-equiv="Content-Type" content="text/html; charset=UTF-8" />
-<meta name="description" content="Discusses possible methods of optimizing HTML Purifier." />
-<link rel="stylesheet" type="text/css" href="./style.css" />
-
-<title>Optimization - HTML Purifier</title>
-
-</head><body>
-
-<h1>Optimization</h1>
-
-<div id="filing">Filed under Development</div>
-<div id="index">Return to the <a href="index.html">index</a>.</div>
-<div id="home"><a href="http://hp.jpsband.org/">HTML Purifier</a> End-User Documentation</div>
-
-<p>Here are some possible optimization techniques we can apply to code sections if
-they turn out to be slow.  Be sure not to prematurely optimize: if you get
-that itch, put it here!</p>
-
-<ul>
-    <li>Make Tokens Flyweights (may prove problematic, probably not worth it)</li>
-    <li>Rewrite regexps into PHP code</li>
-    <li>Serialize the Definition object</li>
-    <li>Batch regexp validation (do as many per function call as possible)</li>
-    <li>Parallelize strategies</li>
-</ul>
-
-<div id="version">$Id$</div>
-
-</body></html>

docs/devnetwork.html

@@ -1,45 +1,31 @@
-<?xml version="1.0" encoding="UTF-8"?>
+<?xml version="1.0" encoding="UTF-8"?>
-<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN"
+<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN"
-    "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">
+    "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">
-<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en"><head>
+<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en"><head>
-<meta http-equiv="Content-Type" content="text/html; charset=UTF-8" />
+
-<meta name="description" content="Credits and links to DevNetwork forum topics on HTML Purifier." />
+<title>DevNetwork Forums</title>
-<link rel="stylesheet" type="text/css" href="./style.css" />
+
-
+</head>
-<title>DevNetwork Credits - HTML Purifier</title>
+<body>
-
+
-</head>
+<p>Many thanks to the DevNetwork community for answering questions,
-<body>
+theorizing about design, and offering encouragement during
-
+the development of this library in these forum threads:</p>
-<h1>DevNetwork Credits</h1>
+
-
+<ul>
-<div id="filing">Filed under Reference</div>
+    <li><a href="http://forums.devnetwork.net/viewtopic.php?t=52905">HTMLPurifier PHP Library hompeage</a></li>
-<div id="index">Return to the <a href="index.html">index</a>.</div>
+    <li><a href="http://forums.devnetwork.net/viewtopic.php?t=53056">How much of CSS to implement?</a></li>
-<div id="home"><a href="http://hp.jpsband.org/">HTML Purifier</a> End-User Documentation</div>
+    <li><a href="http://forums.devnetwork.net/viewtopic.php?t=53083">Parsing URL only according to URI : Security Risk?</a></li>
-
+    <li><a href="http://forums.devnetwork.net/viewtopic.php?t=53096">Gimme a name : URI and friends</a></li>
-<p>Many thanks to the DevNetwork community for answering questions,
+    <li><a href="http://forums.devnetwork.net/viewtopic.php?t=53415">How to document configuration directives</a></li>
-theorizing about design, and offering encouragement during
+    <li><a href="http://forums.devnetwork.net/viewtopic.php?t=53479">IPv6</a></li>
-the development of this library in these forum threads:</p>
+    <li><a href="http://forums.devnetwork.net/viewtopic.php?t=53539">http and ftp versus news and mailto</a></li>
-
+    <li><a href="http://forums.devnetwork.net/viewtopic.php?t=53579">HTMLPurifier - Take your best shot</a></li>
-<ul>
+    <li><a href="http://forums.devnetwork.net/viewtopic.php?t=53664">Need help optimizing a block of code</a>
-    <li><a href="http://forums.devnetwork.net/viewtopic.php?t=52905">HTMLPurifier PHP Library hompeage</a></li>
+    <li><a href="http://forums.devnetwork.net/viewtopic.php?t=53861">Non-SGML characters</a>
-    <li><a href="http://forums.devnetwork.net/viewtopic.php?t=53056">How much of CSS to implement?</a></li>
+    <li><a href="http://forums.devnetwork.net/viewtopic.php?t=54283">Wordpress makes me cry</a>
-    <li><a href="http://forums.devnetwork.net/viewtopic.php?t=53083">Parsing URL only according to URI : Security Risk?</a></li>
+    <li><a href="http://forums.devnetwork.net/viewtopic.php?t=54478">Parameter Object vs. Parameter Array vs. Parameter Functions</a>
-    <li><a href="http://forums.devnetwork.net/viewtopic.php?t=53096">Gimme a name : URI and friends</a></li>
+    <li><a href="http://forums.devnetwork.net/viewtopic.php?t=54521">Convert encoding where output cannot represent characters</a>
-    <li><a href="http://forums.devnetwork.net/viewtopic.php?t=53415">How to document configuration directives</a></li>
+</ul>
-    <li><a href="http://forums.devnetwork.net/viewtopic.php?t=53479">IPv6</a></li>
+</body>
-    <li><a href="http://forums.devnetwork.net/viewtopic.php?t=53539">http and ftp versus news and mailto</a></li>
-    <li><a href="http://forums.devnetwork.net/viewtopic.php?t=53579">HTMLPurifier - Take your best shot</a></li>
-    <li><a href="http://forums.devnetwork.net/viewtopic.php?t=53664">Need help optimizing a block of code</a></li>
-    <li><a href="http://forums.devnetwork.net/viewtopic.php?t=53861">Non-SGML characters</a></li>
-    <li><a href="http://forums.devnetwork.net/viewtopic.php?t=54283">Wordpress makes me cry</a></li>
-    <li><a href="http://forums.devnetwork.net/viewtopic.php?t=54478">Parameter Object vs. Parameter Array vs. Parameter Functions</a></li>
-    <li><a href="http://forums.devnetwork.net/viewtopic.php?t=54521">Convert encoding where output cannot represent characters</a></li>
-    <li><a href="http://forums.devnetwork.net/viewtopic.php?t=56411">Reporting errors in a document without line numbers</a></li>
-</ul>
-
-<p>...as well as any I may have forgotten.</p>
-
-<div id="version">$Id$</div>
-</body>
 </html>

docs/enduser-id.html

@@ -1,147 +0,0 @@
-<?xml version="1.0" encoding="UTF-8"?>
-<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN"
-    "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">
-<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en"><head>
-<meta http-equiv="Content-Type" content="text/html; charset=UTF-8" />
-<meta name="description" content="Explains various methods for allowing IDs in documents safely in HTML Purifier." />
-<link rel="stylesheet" type="text/css" href="./style.css" />
-
-<title>IDs - HTML Purifier</title>
-
-</head><body>
-
-<h1 class="subtitled">IDs</h1>
-<div class="subtitle">What they are, why you should(n't) wear them, and how to deal with it</div>
-
-<div id="filing">Filed under End-User</div>
-<div id="index">Return to the <a href="index.html">index</a>.</div>
-<div id="home"><a href="http://hp.jpsband.org/">HTML Purifier</a> End-User Documentation</div>
-
-<p>Prior to HTML Purifier 1.2.0, this library blithely accepted user input that
-looked like this:</p>
-
-<pre>&lt;a id=&quot;fragment&quot;&gt;Anchor&lt;/a&gt;</pre>
-
-<p>...presenting an attractive vector for those that would destroy standards
-compliance: simply set the ID to one that is already used elsewhere in the
-document and voila: validation breaks.  There was a half-hearted attempt to
-prevent this by allowing users to blacklist IDs, but I suspect that no one
-really bothered, and thus, with the release of 1.2.0, IDs are now <em>removed</em>
-by default.</p>
-
-<p>IDs, however, are quite useful functionality to have, so if users start
-complaining about broken anchors you'll probably want to turn them back on
-with %HTML.EnableAttrID. But before you go mucking around with the config
-object, it's probably worth to take some precautions to keep your page
-validating. Why?</p>
-
-<ol>
-   <li>Standards-compliant pages are good</li>
-   <li>Duplicated IDs interfere with anchors.  If there are two id="foobar"s in a
-   document, which spot does a browser presented with the fragment #foobar go
-   to? Most browsers opt for the first appearing ID, making it impossible
-   to references the second section. Similarly, duplicated IDs can hijack
-   client-side scripting that relies on the IDs of elements.</li>
-</ol>
-
-<p>You have (currently) four ways of dealing with the problem.</p>
-
-
-
-<h2 class="subtitled">Blacklisting IDs</h2>
-<div class="subsubtitle">Good for pages with single content source and stable templates</div>
-
-<p>Keeping in terms with the
-<acronym title="Keep It Simple, Stupid">KISS</acronym> principle, let us
-deal with the most obvious solution: preventing users from using any IDs that
-appear elsewhere on the document.  The method is simple:</p>
-
-<pre>$config->set('HTML', 'EnableAttrID', true);
-$config->set('Attr', 'IDBlacklist' array(
-    'list', 'of', 'attributes', 'that', 'are', 'forbidden'
-));</pre>
-
-<p>That being said, there are some notable drawbacks.  First of all, you have to
-know precisely which IDs are being used by the HTML surrounding the user code.
-This is easier said than done: quite often the page designer and the system
-coder work separately, so the designer has to constantly be talking with the
-coder whenever he decides to add a new anchor.  Miss one and you open yourself
-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
-so at different times, it would be extremely difficult to dynamically update
-the blacklist inbetween 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>
-
-<p>Thus, we get to our second method.</p>
-
-
-
-<h2 class="subtitled">Namespacing IDs</h2>
-<div class="subsubtitle">Lazy developer's way, but needs user education</div>
-
-<p>This method, too, is quite simple: add a prefix to all user IDs. With this
-code:</p>
-
-<pre>$config->set('HTML', 'EnableAttrID', true);
-$config->set('Attr', 'IDPrefix', 'user_');</pre>
-
-<p>...this:</p>
-
-<pre>&lt;a id=&quot;foobar&quot;&gt;Anchor!&lt;/a&gt;</pre>
-
-<p>...turns into:</p>
-
-<pre>&lt;a id=&quot;user_foobar&quot;&gt;Anchor!&lt;/a&gt;</pre>
-
-<p>As long as you don't have any IDs that start with user_, collisions are
-guaranteed not to happen.  The drawback is obvious: if a user submits
-id=&quot;foobar&quot;, they probably expect to be able to reference their page with
-#foobar. You'll have to tell them, &quot;No, that doesn't work, you have to add
-user_ to the beginning.&quot;</p>
-
-<p>And yes, things get hairier.  Even with a nice prefix, we still have done
-nothing about multiple HTML Purifier outputs on one page.  Thus, we have
-a second configuration value to piggy-back off of: %Attr.IDPrefixLocal:</p>
-
-<pre>$config->set('Attr', 'IDPrefixLocal', 'comment' . $id . '_');</pre>
-
-<p>This new attributes does nothing but append on to regular IDPrefix, but is
-special in that it is volatile: it's value is determined at run-time and
-cannot possibly be cordoned into, say, a .ini config file.  As for what to
-put into the directive, is up to you, but I would recommend the ID number
-the text has been assigned in the database.  Whatever you pick, however, it
-has to be unique and stable for the text you are validating.  Note, however,
-that we require that %Attr.IDPrefix be set before you use this directive.</p>
-
-<p>And also remember: the user has to know what this prefix is too!</p>
-
-
-
-<h2>Abstinence</h2>
-
-<p>You may not want to bother. That's okay too, just don't enable IDs.</p>
-
-<p>Personally, I would take this road whenever user-submitted content would be
-possibly be shown together on one page.  Why a blog comment would need to use
-anchors is beyond me.</p>
-
-
-
-<h2>Denial</h2>
-
-<p>To revert back to pre-1.2.0 behavior, simply:</p>
-
-<pre>$config->set('HTML', 'EnableAttrID', true);</pre>
-
-<p>Don't come crying to me when your page mysteriously stops validating, though.</p>
-
-<div id="version">$Id$</div>
-
-</body>
-</html>

docs/enduser-slow.html

@@ -1,117 +0,0 @@
-<?xml version="1.0" encoding="UTF-8"?>
-<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN"
-    "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">
-<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en"><head>
-<meta http-equiv="Content-Type" content="text/html; charset=UTF-8" />
-<meta name="description" content="Explains how to speed up HTML Purifier through caching or inbound filtering." />
-<link rel="stylesheet" type="text/css" href="./style.css" />
-
-<title>Speeding up HTML Purifier - HTML Purifier</title>
-
-</head><body>
-
-<h1 class="subtitled">Speeding up HTML Purifier</h1>
-<div class="subtitle">...also known as the HELP ME LIBRARY IS TOO SLOW MY PAGE TAKE TOO LONG page</div>
-
-<div id="filing">Filed under End-User</div>
-<div id="index">Return to the <a href="index.html">index</a>.</div>
-<div id="home"><a href="http://hp.jpsband.org/">HTML Purifier</a> End-User Documentation</div>
-
-<p>HTML Purifier is a very powerful library. But with power comes great 
-responsibility, in the form of longer execution times.  Remember, this 
-library isn't lightly grazing over submitted HTML: it's deconstructing 
-the whole thing, rigorously checking the parts, and then putting it back 
-together. </p>
-
-<p>So, if it so turns out that HTML Purifier is kinda too slow for outbound 
-filtering, you've got a few options: </p>
-
-<h2>Inbound filtering</h2>
-
-<p>Perform filtering of HTML when it's submitted by the user. Since the 
-user is already submitting something, an extra half a second tacked on 
-to the load time probably isn't going to be that huge of a problem.  
-Then, displaying the content is a simple a manner of outputting it 
-directly from your database/filesystem. The trouble with this method is 
-that your user loses the original text, and when doing edits, will be 
-handling the filtered text.  While this may be a good thing, especially 
-if you're using a WYSIWYG editor, it can also result in data-loss if a 
-user makes a typo. </p>
-
-<p>Example (non-functional):</p>
-
-<pre>&lt;?php
-    /**
-     * FORM SUBMISSION PAGE
-     * display_error($message) : displays nice error page with message
-     * display_success() : displays a nice success page
-     * display_form() : displays the HTML submission form
-     * database_insert($html) : inserts data into database as new row
-     */
-    if (!empty($_POST)) {
-        require_once '/path/to/library/HTMLPurifier.auto.php';
-        require_once 'HTMLPurifier.func.php';
-        $dirty_html = isset($_POST['html']) ? $_POST['html'] : false;
-        if (!$dirty_html) {
-            display_error('You must write some HTML!');
-        }
-        $html = HTMLPurifier($dirty_html);
-        database_insert($html);
-        display_success();
-        // notice that $dirty_html is *not* saved
-    } else {
-        display_form();
-    }
-?&gt;</pre>
-
-<h2>Caching the filtered output</h2>
-
-<p>Accept the submitted text and put it unaltered into the database, but 
-then also generate a filtered version and stash that in the database.  
-Serve the filtered version to readers, and the unaltered version to 
-editors.  If need be, you can invalidate the cache and have the cached 
-filtered version be regenerated on the first page view.  Pros? Full data 
-retention. Cons? It's more complicated, and opens other editors up to 
-XSS if they are using a WYSIWYG editor (to fix that, they'd have to be 
-able to get their hands on the *really* original text served in 
-plaintext mode). </p>
-
-<p>Example (non-functional):</p>
-
-<pre>&lt;?php
-    /**
-     * VIEW PAGE
-     * display_error($message) : displays nice error page with message
-     * cache_get($id) : retrieves HTML from fast cache (db or file)
-     * cache_insert($id, $html) : inserts good HTML into cache system
-     * database_get($id) : retrieves raw HTML from database
-     */
-    $id = isset($_GET['id']) ? (int) $_GET['id'] : false;
-    if (!$id) {
-        display_error('Must specify ID.');
-        exit;
-    }
-    $html = cache_get($id); // filesystem or database
-    if ($html === false) {
-        // cache didn't have the HTML, generate it
-        $raw_html = database_get($id);
-        require_once '/path/to/library/HTMLPurifier.auto.php';
-        require_once 'HTMLPurifier.func.php';
-        $html = HTMLPurifier($raw_html);
-        cache_insert($id, $html);
-    }
-    echo $html;
-?&gt;</pre>
-
-<h2>Summary</h2>
-
-<p>In short, inbound filtering is the simple option and caching is the
-robust option (albeit with bigger storage requirements). </p>
-
-<p>There is a third option, independent of the two we've discussed: profile 
-and optimize HTMLPurifier yourself. Be sure to report back your results 
-if you decide to do that! Especially if you port HTML Purifier to C++. 
-<tt>;-)</tt></p>
-
-</body>
-</html>

docs/enduser-utf8.html

@@ -1,640 +0,0 @@
-<?xml version="1.0" encoding="UTF-8"?>
-<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN"
-    "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">
-<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en"><head>
-<meta http-equiv="Content-Type" content="text/html; charset=UTF-8" />
-<meta name="description" content="Describes the rationale for using UTF-8, the ramifications otherwise, and how to make the switch." />
-<link rel="stylesheet" type="text/css" href="./style.css" />
-<script defer="defer" type="text/javascript" src="./toc-gen.js"></script>
-<style type="text/css">
-    .minor td {font-style:italic;}
-</style>
-
-<title>UTF-8 - HTML Purifier</title>
-
-<!-- Note to users: this document, though professing to be UTF-8, attempts
-to use only ASCII characters, because most webservers are configured
-to send HTML as ISO-8859-1. So I will, many times, go against my
-own advice for sake of portability.  -->
-
-</head><body>
-
-<h1>UTF-8</h1>
-
-<div id="filing">Filed under End-User</div>
-<div id="index">Return to the <a href="index.html">index</a>.</div>
-<div id="home"><a href="http://hp.jpsband.org/">HTML Purifier</a> End-User Documentation</div>
-
-<p>Character encoding and character sets, in truth, are not that
-difficult to understand. But if you don't understand them, you are going
-to be caught by surprise by some of HTML Purifier's behavior, namely
-the fact that it operates UTF-8 or the limitations of the character
-encoding transformations it does. This document will walk you through
-determining the encoding of your system and how you should handle
-this information. It will stay away from excessive discussion on
-the internals of character encoding, but offer the information in
-asides that can easily be skipped.</p>
-
-<blockquote class="aside">
-<div class="label">Asides</div>
-    <p>Text in this formatting is an <strong>aside</strong>,
-    interesting tidbits for the curious but not strictly necessary material to
-    do the tutorial. If you read this text, you'll come out
-    with a greater understanding of the underlying issues.</p>
-</blockquote>
-
-<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
-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
-there are now many character encodings floating around.</p>
-
-<blockquote class="aside">
-    <p>A <strong>character encoding</strong> tells the computer how to
-    interpret raw zeroes and ones into real characters. It
-    usually does this by pairing numbers with characters.</p>
-    <p>There are many different types of character encodings floating
-    around, but the ones we deal most frequently with are ASCII, 
-    8-bit encodings, and Unicode-based encodings.</p>
-    <ul>
-        <li><strong>ASCII</strong> is a 7-bit encoding based on the
-            English alphabet.</li>
-        <li><strong>8-bit encodings</strong> are extensions to ASCII
-            that add a potpourri of useful, non-standard characters
-            like &eacute; and &aelig;. They can only add 127 characters,
-            so usually only support one script at a time. When you
-            see a page on the web, chances are it's encoded in one
-            of these encodings.</li>
-        <li><strong>Unicode-based encodings</strong> implement the
-            Unicode standard and include UTF-8, UCS-2 and UTF-16.
-            They go beyond 8-bits (the first two are variable length,
-            while the second one uses 16-bits), and support almost
-            every language in the world. UTF-8 is gaining traction
-            as the dominant international encoding of the web.</li>
-    </ul>
-</blockquote>
-
-<p>The first step of our journey is to find out what the encoding of
-your website is. The most reliable way is to ask your
-browser:</p>
-
-<dl>
-    <dt>Mozilla Firefox</dt>
-    <dd>Tools &gt; Page Info: Encoding</dd>
-    <dt>Internet Explorer</dt>
-    <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
-character encoding, so you'll have to look it up using their description.
-Some common ones:</p>
-
-<table class="table">
-    <thead><tr>
-        <th>IE's Description</th>
-        <th>Mime Name</th>
-    </tr></thead>
-    <tbody>
-        <tr><th colspan="2">Windows</th></tr>
-        <tr><td>Arabic (Windows)</td><td>Windows-1256</td></tr>
-        <tr><td>Baltic (Windows)</td><td>Windows-1257</td></tr>
-        <tr><td>Central European (Windows)</td><td>Windows-1250</td></tr>
-        <tr><td>Cyrillic (Windows)</td><td>Windows-1251</td></tr>
-        <tr><td>Greek (Windows)</td><td>Windows-1253</td></tr>
-        <tr><td>Hebrew (Windows)</td><td>Windows-1255</td></tr>
-        <tr><td>Thai (Windows)</td><td>TIS-620</td></tr>
-        <tr><td>Turkish (Windows)</td><td>Windows-1254</td></tr>
-        <tr><td>Vietnamese (Windows)</td><td>Windows-1258</td></tr>
-        <tr><td>Western European (Windows)</td><td>Windows-1252</td></tr>
-    </tbody>
-    <tbody>
-        <tr><th colspan="2">ISO</th></tr>
-        <tr><td>Arabic (ISO)</td><td>ISO-8859-6</td></tr>
-        <tr><td>Baltic (ISO)</td><td>ISO-8859-4</td></tr>
-        <tr><td>Central European (ISO)</td><td>ISO-8859-2</td></tr>
-        <tr><td>Cyrillic (ISO)</td><td>ISO-8859-5</td></tr>
-        <tr class="minor"><td>Estonian (ISO)</td><td>ISO-8859-13</td></tr>
-        <tr class="minor"><td>Greek (ISO)</td><td>ISO-8859-7</td></tr>
-        <tr><td>Hebrew (ISO-Logical)</td><td>ISO-8859-8-l</td></tr>
-        <tr><td>Hebrew (ISO-Visual)</td><td>ISO-8859-8</td></tr>
-        <tr class="minor"><td>Latin 9 (ISO)</td><td>ISO-8859-15</td></tr>
-        <tr class="minor"><td>Turkish (ISO)</td><td>ISO-8859-9</td></tr>
-        <tr><td>Western European (ISO)</td><td>ISO-8859-1</td></tr>
-    </tbody>
-    <tbody>
-        <tr><th colspan="2">Other</th></tr>
-        <tr><td>Chinese Simplified (GB18030)</td><td>GB18030</td></tr>
-        <tr><td>Chinese Simplified (GB2312)</td><td>GB2312</td></tr>
-        <tr><td>Chinese Simplified (HZ)</td><td>HZ</td></tr>
-        <tr><td>Chinese Traditional (Big5)</td><td>Big5</td></tr>
-        <tr><td>Japanese (Shift-JIS)</td><td>Shift_JIS</td></tr>
-        <tr><td>Japanese (EUC)</td><td>EUC-JP</td></tr>
-        <tr><td>Korean</td><td>EUC-KR</td></tr>
-        <tr><td>Unicode (UTF-8)</td><td>UTF-8</td></tr>
-    </tbody>
-</table>
-
-<p>Internet Explorer does not recognize some of the more obscure
-character encodings, and having to lookup the real names with a table
-is a pain, so I recommend using Mozilla Firefox to find out your
-character encoding.</p>
-
-<h2 id="findmetacharset">Finding the embedded encoding</h2>
-
-<p>At this point, you may be asking, &quot;Didn't we already find out our
-encoding?&quot; Well, as it turns out, there are multiple places where
-a web developer can specify a character encoding, and one such place
-is in a <code>META</code> tag:</p>
-
-<pre>&lt;meta http-equiv=&quot;Content-Type&quot; content=&quot;text/html; charset=UTF-8&quot; /&gt;</pre>
-
-<p>You'll find this in the <code>HEAD</code> section of an HTML document.
-The text to the right of <code>charset=</code> is the &quot;claimed&quot;
-encoding: the HTML claims to be this encoding, but whether or not this
-is actually the case depends on other factors. For now, take note
-if your <code>META</code> tag claims that either:</p>
-
-<ol>
-    <li>The character encoding is the same as the one reported by the
-        browser,</li>
-    <li>The character encoding is different from the browser's, or</li>
-    <li>There is no <code>META</code> tag at all! (horror, horror!)</li>
-</ol>
-
-<h2 id="fixcharset">Fixing the encoding</h2>
-
-<p>If your <code>META</code> encoding and your real encoding match,
-savvy! You can skip this section. If they don't...</p>
-
-<h3 id="fixcharset-none">No embedded encoding</h3>
-
-<p>If this is the case, you'll want to add in the appropriate
-<code>META</code> tag to your website. It's as simple as copy-pasting
-the code snippet above and replacing UTF-8 with whatever is the mime name
-of your real encoding.</p>
-
-<blockquote class="aside">
-    <p>For all those skeptics out there, there is a very good reason
-    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
-    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>
-    <p>You might be able to get away with not specifying a character
-    encoding with the <code>META</code> tag as long as your webserver
-    sends the right Content-Type header, but why risk it? Besides, if
-    the user downloads the HTML file, there is no longer any webserver
-    to define the character encoding.</p>
-</blockquote>
-
-<h3 id="fixcharset-diff">Embedded encoding disagrees</h3>
-
-<p>This is an extremely common mistake: another source is telling
-the browser what the
-character encoding is and is overriding the embedded encoding. This
-source usually is the Content-Type HTTP header that the webserver (i.e.
-Apache) sends. A usual Content-Type header sent with a page might
-look like this:</p>
-
-<pre>Content-Type: text/html; charset=ISO-8859-1</pre>
-
-<p>Notice how there is a charset parameter: this is the webserver's
-way of telling a browser what the character encoding is, much like
-the <code>META</code> tags we touched upon previously.</p>
-
-<blockquote class="aside"><p>In fact, the <code>META</code> tag is
-designed as a substitute for the HTTP header for contexts where
-sending headers is impossible (such as locally stored files without
-a webserver). Thus the name <code>http-equiv</code> (HTTP equivalent).
-</p></blockquote>
-
-<p>There are two ways to go about fixing this: changing the <code>META</code>
-tag to match the HTTP header, or changing the HTTP header to match
-the <code>META</code> tag. How do we know which to do? It depends
-on the website's content: after all, headers and tags are only ways of
-describing the actual characters on the web page.</p>
-
-<p>If your website:</p>
-
-<dl>
-    <dt>...only uses ASCII characters,</dt>
-    <dd>Either way is fine, but I recommend switching both to
-        UTF-8 (more on this later).</dd>
-    <dt>...uses special characters, and they display
-        properly,</dt>
-    <dd>Change the embedded encoding to the server encoding.</dd>
-    <dt>...uses special characters, but users often complain that
-        they come out garbled,</dt>
-    <dd>Change the server encoding to the embedded encoding.</dd>
-</dl>
-
-<p>Changing a META tag is easy: just swap out the old encoding
-for the new. Changing the server (HTTP header) encoding, however,
-is slightly more difficult.</p>
-
-<h3 id="fixcharset-server">Changing the server encoding</h3>
-
-<h4 id="fixcharset-server-php">PHP header() function</h4>
-
-<p>The simplest way to handle this problem is to send the encoding
-yourself, via your programming language. Since you're using HTML
-Purifier, I'll assume PHP, although it's not too difficult to do
-similar things in
-<a href="http://www.w3.org/International/O-HTTP-charset#scripting">other
-languages</a>. The appropriate code is:</p>
-
-<pre><a href="http://php.net/function.header">header</a>('Content-Type:text/html; charset=UTF-8');</pre>
-
-<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>
-
-<h4 id="fixcharset-server-phpini">PHP ini directive</h4>
-
-<p>PHP also has a neat little ini directive that can save you a
-header call: <code><a href="http://php.net/ini.core#ini.default-charset">default_charset</a></code>. Using this code:</p>
-
-<pre><a href="http://php.net/function.ini_set">ini_set</a>('default_charset', 'UTF-8');</pre>
-
-<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>
-
-<pre><a href="http://php.net/configuration.changes#configuration.changes.apache">php_value</a> default_charset &quot;UTF-8&quot;</pre>
-
-<blockquote class="aside"><p>As with all INI directives, this can
-also go in your php.ini file. Some hosting providers allow you to customize
-your own php.ini file, ask your support for details. Use:</p>
-<pre>default_charset = &quot;utf-8&quot;</pre></blockquote>
-
-<h4 id="fixcharset-server-nophp">Non-PHP</h4>
-
-<p>You may, for whatever reason, may need to set the character encoding
-on non-PHP files, usually plain ol' HTML files. Doing this
-is more of a hit-or-miss process: depending on the software being
-used as a webserver and the configuration of that software, certain
-techniques may work, or may not work.</p>
-
-<h4 id="fixcharset-server-htaccess">.htaccess</h4>
-
-<p>On Apache, you can use an .htaccess file to change the character
-encoding. I'll defer to
-<a href="http://www.w3.org/International/questions/qa-htaccess-charset">W3C</a>
-for the in-depth explanation, but it boils down to creating a file
-named .htaccess with the contents:</p>
-
-<pre><a href="http://httpd.apache.org/docs/1.3/mod/mod_mime.html#addcharset">AddCharset</a> UTF-8 .html</pre>
-
-<p>Where UTF-8 is replaced with the character encoding you want to
-use and .html is a file extension that this will be applied to. This
-character encoding will then be set for any file directly in
-or in the subdirectories of directory you place this file in.</p>
-
-<p>If you're feeling particularly courageous, you can use:</p>
-
-<pre><a href="http://httpd.apache.org/docs/1.3/mod/core.html#adddefaultcharset">AddDefaultCharset</a> UTF-8</pre>
-
-<p>...which changes the character set Apache adds to any document that
-doesn't have any Content-Type parameters. This directive, which the
-default configuration file sets to iso-8859-1 for security
-reasons, is probably why your headers mismatch
-with the <code>META</code> tag. If you would prefer Apache not to be
-butting in on your character encodings, you can tell it not
-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>
-
-<blockquote class="aside"><p>These directives can also be
-placed in httpd.conf file for Apache, but
-in most shared hosting situations you won't be able to edit this file.
-</p></blockquote>
-
-<h4 id="fixcharset-server-ext">File extensions</h4>
-
-<p>If you're not allowed to use .htaccess files, you can often
-piggy-back off of Apache's default AddCharset declarations to get
-your files in the proper extension. Here are Apache's default
-character set declarations:</p>
-
-<table class="table">
-    <thead><tr>
-        <th>Charset</th>
-        <th>File extension(s)</th>
-    </tr></thead>
-    <tbody>
-        <tr><td>ISO-8859-1</td><td>.iso8859-1 .latin1</td></tr>
-        <tr><td>ISO-8859-2</td><td>.iso8859-2 .latin2 .cen</td></tr>
-        <tr><td>ISO-8859-3</td><td>.iso8859-3 .latin3</td></tr>
-        <tr><td>ISO-8859-4</td><td>.iso8859-4 .latin4</td></tr>
-        <tr><td>ISO-8859-5</td><td>.iso8859-5 .latin5 .cyr .iso-ru</td></tr>
-        <tr><td>ISO-8859-6</td><td>.iso8859-6 .latin6 .arb</td></tr>
-        <tr><td>ISO-8859-7</td><td>.iso8859-7 .latin7 .grk</td></tr>
-        <tr><td>ISO-8859-8</td><td>.iso8859-8 .latin8 .heb</td></tr>
-        <tr><td>ISO-8859-9</td><td>.iso8859-9 .latin9 .trk</td></tr>
-        <tr><td>ISO-2022-JP</td><td>.iso2022-jp .jis</td></tr>
-        <tr><td>ISO-2022-KR</td><td>.iso2022-kr .kis</td></tr>
-        <tr><td>ISO-2022-CN</td><td>.iso2022-cn .cis</td></tr>
-        <tr><td>Big5</td><td>.Big5 .big5 .b5</td></tr>
-        <tr><td>WINDOWS-1251</td><td>.cp-1251 .win-1251</td></tr>
-        <tr><td>CP866</td><td>.cp866</td></tr>
-        <tr><td>KOI8-r</td><td>.koi8-r .koi8-ru</td></tr>
-        <tr><td>KOI8-ru</td><td>.koi8-uk .ua</td></tr>
-        <tr><td>ISO-10646-UCS-2</td><td>.ucs2</td></tr>
-        <tr><td>ISO-10646-UCS-4</td><td>.ucs4</td></tr>
-        <tr><td>UTF-8</td><td>.utf8</td></tr>
-        <tr><td>GB2312</td><td>.gb2312 .gb </td></tr>
-        <tr><td>utf-7</td><td>.utf7</td></tr>
-        <tr><td>EUC-TW</td><td>.euc-tw</td></tr>
-        <tr><td>EUC-JP</td><td>.euc-jp</td></tr>
-        <tr><td>EUC-KR</td><td>.euc-kr</td></tr>
-        <tr><td>shift_jis</td><td>.sjis</td></tr>
-    </tbody>
-</table>
-
-<p>So, for example, a file named <code>page.utf8.html</code> or
-<code>page.html.utf8</code> will probably be sent with the UTF-8 charset
-attached, the difference being that if there is an
-<code>AddCharset charset .html</code> declaration, it will override
-the .utf8 extension in <code>page.utf8.html</code> (precedence moves
-from right to left). By default, Apache has no such declaration.</p>
-
-<h4 id="fixcharset-server-iis">Microsoft IIS</h4>
-
-<p>If anyone can contribute information on how to configure Microsoft
-IIS to change character encodings, I'd be grateful.</p>
-
-<h3 id="fixcharset-xml">XML</h3>
-
-<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>
-
-<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
-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>
-
-<p>For XML, however, this processing instruction 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, be sure to make sure it jives
-with your <code>META</code> tags and HTTP headers.</p>
-
-<h3>Inside the process</h3>
-
-<p>This section is not required reading,
-but may answer some of your questions on what's going on in all
-this character encoding hocus pocus. If you're interested in
-moving on to the next phase, skip this section.</p>
-
-<p>A logical question that follows all of our wheeling and dealing
-with multiple sources of character encodings is &quot;Why are there
-so many options?&quot; To answer this question, we have to turn
-back our definition of character encodings: they allow a program
-to interpret bytes into human-readable characters.</p>
-
-<p>Thus, a chicken-egg problem: a character encoding
-is necessary to interpret the
-text of a document. A <code>META</code> tag is in the text of a document.
-The <code>META</code> tag gives the character encoding. How can we
-determine the contents of a <code>META</code> tag, inside the text,
-if we don't know it's character encoding? And how do we figure out
-the character encoding, if we don't know the contents of the
-<code>META</code> tag?</p>
-
-<p>Fortunantely for us, the characters we need to write the
-<code>META</code> are in ASCII, which is pretty much universal
-over every character encoding that is in common use today. So,
-all the web-browser has to do is parse all the way down until
-it gets to the Content-Type tag, extract the character encoding
-tag, then re-parse the document according to this new information.</p>
-
-<p>Obviously this is complicated, so browsers prefer the simpler
-and more efficient solution: get the character encoding from a 
-somewhere other than the document itself, i.e. the HTTP headers,
-much to the chagrin of HTML authors who can't set these headers.</p>
-
-<h2 id="whyutf8">Why UTF-8?</h2>
-
-<p>So, you've gone through all the trouble of ensuring that your
-server and embedded characters all line up properly and are
-present.  Good job: at
-this point, you could quit and rest easy knowing that your pages
-are not vulnerable to character encoding style XSS attacks.
-However, just as having a character encoding is better than
-having no character encoding at all, having UTF-8 as your
-character encoding is better than having some other random
-character encoding, and the next step is to convert to UTF-8.
-But why?</p>
-
-<h3 id="whyutf8-i18n">Internationalization</h3>
-
-<p>Many software projects, at one point or another, suddenly realize
-that they should be supporting more than one language. Even regular
-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
-zeal.</p>
-
-<p>UTF-8, however, obviates the need for any of these complicated
-measures. After getting the system to use UTF-8 and adjusting for
-sources that are outside the hand of the browser (more on this later),
-UTF-8 just works. You can use it for any language, even many languages
-at once, you don't have to worry about managing multiple encodings,
-you don't have to use those user-unfriendly entities.</p>
-
-<h3 id="whyutf8-user">User-friendly</h3>
-
-<p>Websites encoded in Latin-1 (ISO-8859-1) which ocassionally need
-a special character outside of their scope often will use a character
-entity 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>
-
-<pre>&amp;#28608;&amp;#20809;, &amp;#36889;&amp;#20841;&amp;#20491;&amp;#23383;&amp;#26159;&amp;#29978;&amp;#40636;&amp;#24847;&amp;#24605;</pre>
-
-<p>Extremely inconvenient for those of us who actually know what
-character entities are, totally unintelligible to poor users who don't!
-Even the slightly more user-friendly, &quot;intelligible&quot; character
-entities like <code>&amp;theta;</code> will leave users who are
-uninterested in learning HTML scratching their heads. On the other
-hand, if they see &theta; in an edit box, they'll know that it's a
-special character, and treat it accordingly, even if they don't know
-how to write that character themselves.</p>
-
-<blockquote class="aside"><p>Wikipedia is a great case study for
-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
-<a href="http://meta.wikimedia.org/wiki/Help:Special_characters">Meta's
-page on special characters</a> for more details.
-</p></blockquote>
-
-<h3 id="whyutf8-forms">Forms</h3>
-
-<p>While we're on the tack of users, how do non-UTF-8 web forms deal
-with characters that our outside of their character set? Rather than
-discuss what UTF-8 does right, we're going to show what could go wrong
-if you didn't use UTF-8 and people tried to use characters outside
-of your character encoding.</p>
-
-<p>The troubles are large, extensive, and extremely difficult to fix (or,
-at least, difficult enough that if you had the time and resources to invest
-in doing the fix, you would be probably better off migrating to UTF-8).
-There are two types of form submission: <code>application/x-www-form-urlencoded</code>
-which is used for GET and by default for POST, and <code>multipart/form-data</code>
-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">
-<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>
-
-<h4 id="whyutf8-forms-urlencoded"><code>application/x-www-form-urlencoded</code></h4>
-
-<p>This is the Content-Type that GET requests must use, and POST requests
-use by default. It involves the ubiquituous percent encoding format that
-looks something like: <code>%C3%86</code>. There is no official way of
-determining the character encoding of such a request, since the percent
-encoding operates on a byte level, so it is usually assumed that it
-is the same as the encoding the page containing the form was submitted
-in. You'll run into very few problems if you only use characters in
-the character encoding you chose.</p>
-
-<p>However, once you start adding characters outside of your encoding
-(and this is a lot more common than you may think: take curly
-&quot;smart&quot; quotes from Microsoft as an example),
-a whole manner of strange things start to happen. Depending on the
-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>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>
-</ul>
-
-<p>To properly guard against these behaviors, you'd have to sniff out
-the browser agent, compile a database of different behaviors, and
-take appropriate conversion action against the string (disregarding
-a spate of extremely mysterious, random and devastating bugs Internet
-Explorer manifests every once in a while). Or you could
-use UTF-8 and rest easy knowing that none of this could possibly happen
-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
-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>
-
-<p>There are two ways you go with this functionality: leave it
-unset and have the browser send in the same encoding as the page,
-or set it to UTF-8 and then do another conversion server-side.
-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 I18N 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?
-This route is more palatable, but there's a notable caveat: your data
-will come in as UTF-8, so you will have to explicitly convert it into
-your favored local character encoding.</p>
-
-<p>I object to this approach on idealogical grounds: you're
-digging yourself deeper into
-the hole when you could have been converting to UTF-8
-instead. And, of course, you can't use this method for GET requests.</p>
-
-<h3 id="whyutf8-support">Well supported</h3>
-
-<p>Almost every modern browser in the wild today has full UTF-8 and Unicode
-support: the number of troublesome cases can be counted with the
-fingers of one hand, and these browsers usually have trouble with
-other character encodings too. Problems users usually encounter stem
-from the lack of appropriate fonts to display the characters (once
-again, this applies to all character encodings and HTML entities) or
-Internet Explorer's lack of intelligent font picking (which can be
-worked around).</p>
-
-<p>We will go into more detail about how to deal with edge cases in
-the browser world in the Migration section, but rest assured that
-converting to UTF-8, if done correctly, will not result in users
-hounding you about broken pages.</p>
-
-<h3 id="whyutf8-htmlpurifier">HTML Purifier</h3>
-
-<p>And finally, we get to HTML Purifier.</p>
-
-<h2 id="migrate">Migrate to UTF-8</h2>
-
-<h3 id="migrate-editor">Text editor</h3>
-
-<h3 id="migrate-db">Configuring your database</h3>
-
-<h3 id="migrate-convert">Convert old text</h3>
-
-<h3 id="migrate-bom">Byte Order Mark (headers already sent!)</h3>
-
-<h3 id="migrate-variablewidth">Dealing with variable width in functions</h3>
-
-<h2 id="externallinks">Further Reading</h2>
-
-<p>Many other developers have already discussed the subject of Unicode,
-UTF-8 and internationalization, and I would like to defer to them for
-a more in-depth look into character sets and encodings.</p>
-
-<ul>
-    <li><a href="http://www.joelonsoftware.com/articles/Unicode.html">
-        The Absolute Minimum Every Software Developer Absolutely,
-        Positively Must Know About Unicode and Character Sets
-        (No Excuses!)</a> by Joel Spolsky, provides a <em>very</em>
-        good high-level look at Unicode and character sets in general.</li>
-    <li><a href="http://en.wikipedia.org/wiki/UTF-8">UTF-8 on Wikipedia</a>,
-        provides a lot of useful details into the innards of UTF-8, although
-        it may be a little off-putting to people who don't know much
-        about Unicode to begin with.</li>
-</ul>
-
-</body>
-</html>

docs/enduser-youtube.html

@@ -1,152 +0,0 @@
-<?xml version="1.0" encoding="UTF-8"?>
-<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN"
-    "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">
-<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en"><head>
-<meta http-equiv="Content-Type" content="text/html; charset=UTF-8" />
-<meta name="description" content="Explains how to safely allow the embedding of flash from trusted sites in HTML Purifier." />
-<link rel="stylesheet" type="text/css" href="./style.css" />
-
-<title>Embedding YouTube Videos - HTML Purifier</title>
-
-</head><body>
-
-<h1 class="subtitled">Embedding YouTube Videos</h1>
-<div class="subtitle">...as well as other dangerous active content</div>
-
-<div id="filing">Filed under End-User</div>
-<div id="index">Return to the <a href="index.html">index</a>.</div>
-<div id="home"><a href="http://hp.jpsband.org/">HTML Purifier</a> End-User Documentation</div>
-
-<p>Clients like their YouTube videos. It gives them a warm fuzzy feeling when
-they see a neat little embedded video player on their websites that can play
-the latest clips from their documentary &quot;Fido and the Bones of Spring&quot;.
-All joking aside, the ability to embed YouTube videos or other active
-content in their pages is something that a lot of people like.</p>
-
-<p>This is a <em>bad</em> idea. The moment you embed anything untrusted,
-you will definitely be slammed by a manner of nasties that can be
-embedded in things from your run of the mill Flash movie to
-<a href="http://blog.spywareguide.com/2006/12/myspace_phish_attack_leads_use.html">Quicktime movies</a>.
-Even <code>img</code> tags, which HTML Purifier allows by default, can be
-dangerous. Be distrustful of anything that tells a browser to load content
-from another website automatically.</p>
-
-<p>Luckily for us, however, whitelisting saves the day. Sure, letting users
-include any old random flash file could be dangerous, but if it's
-from a specific website, it probably is okay. If no amount of pleading will
-convince the people upstairs that they should just settle with just linking
-to their movies, you may find this technique very useful.</p>
-
-<h2>Looking in</h2>
-
-<p>Below is custom code that allows users to embed
-YouTube videos. This is not favoritism: this trick can easily be adapted for
-other forms of embeddable content.</p>
-
-<p>Usually, websites like YouTube give us boilerplate code that you can insert
-into your documents. YouTube's code goes like this:</p>
-
-<pre>
-&lt;object width=&quot;425&quot; height=&quot;350&quot;&gt;
-  &lt;param name=&quot;movie&quot; value=&quot;http://www.youtube.com/v/AyPzM5WK8ys&quot; /&gt;
-  &lt;param name=&quot;wmode&quot; value=&quot;transparent&quot; /&gt;
-  &lt;embed src=&quot;http://www.youtube.com/v/AyPzM5WK8ys&quot;
-         type=&quot;application/x-shockwave-flash&quot;
-         wmode=&quot;transparent&quot; width=&quot;425&quot; height=&quot;350&quot; /&gt;
-&lt;/object&gt;
-</pre>
-
-<p>There are two things to note about this code:</p>
-
-<ol>
-    <li><code>&lt;embed&gt;</code> is not recognized by W3C, so if you want
-        standards-compliant code, you'll have to get rid of it.</li>
-    <li>The code is exactly the same for all instances, except for the
-        identifier <tt>AyPzM5WK8ys</tt> which tells us which movie file
-        to retrieve.</li>
-</ol>
-
-<p>What point 2 means is that if we have code like <code>&lt;span
-class=&quot;embed-youtube&quot;&gt;AyPzM5WK8ys&lt;/span&gt;</code> your
-application can reconstruct the full object from this small snippet that
-passes through HTML Purifier <em>unharmed</em>.
-<a href="http://hp.jpsband.org/svnroot/htmlpurifier/trunk/library/HTMLPurifier/Filter/YouTube.php">Show me the code!</a></p>
-
-<p>And the corresponding usage:</p>
-
-<pre>&lt;?php
-    // assuming $purifier is an instance of HTMLPurifier
-    require_once 'HTMLPurifier/Filter/YouTube.php';
-    $purifier-&gt;addFilter(new HTMLPurifier_Filter_YouTube());
-?&gt;</pre>
-
-<p>There is a bit going in the two code snippets, so let's explain.</p>
-
-<ol>
-    <li>This is a Filter object, which intercepts the HTML that is
-        coming into and out of the purifier. You can add as many
-        filter objects as you like. <code>preFilter()</code>
-        processes the code before it gets purified, and <code>postFilter()</code>
-        processes the code afterwards. So, we'll use <code>preFilter()</code> to
-        replace the object tag with a <code>span</code>, and <code>postFilter()</code>
-        to restore it.</li>
-    <li>The first preg_replace call replaces any YouTube code users may have
-        embedded into the benign span tag. Span is used because it is inline,
-        and objects are inline too. We are very careful to be extremely
-        restrictive on what goes inside the span tag, as if an errant code
-        gets in there it could get messy.</li>
-    <li>The HTML is then purified as usual.</li>
-    <li>Then, another preg_replace replaces the span tag with a fully fledged
-        object. Note that the embed is removed, and, in its place, a data
-        attribute was added to the object. This makes the tag standards
-        compliant! It also breaks Internet Explorer, so we add in a bit of
-        conditional comments with the old embed code to make it work again.
-        It's all quite convoluted but works.</li>
-</ol>
-
-<h2>Warning</h2>
-
-<p>There are a number of possible problems with the code above, depending
-on how you look at it.</p>
-
-<h3>Cannot change width and height</h3>
-
-<p>The width and height of the final YouTube movie cannot be adjusted. This
-is because I am lazy. If you really insist on letting users change the size
-of the movie, what you need to do is package up the attributes inside the
-span tag (along with the movie ID). It gets complicated though: a malicious
-user can specify an outrageously large height and width and attempt to crash
-the user's operating system/browser. You need to either cap it by limiting
-the amount of digits allowed in the regex or using a callback to check the
-number.</p>
-
-<h3>Trusts media's host's security</h3>
-
-<p>By allowing this code onto our website, we are trusting that YouTube has
-tech-savvy enough people not to allow their users to inject malicious
-code into the Flash files.  An exploit on YouTube means an exploit on your
-site.  Even though YouTube is run by the reputable Google, it
-<a href="http://ha.ckers.org/blog/20061213/google-xss-vuln/">doesn't</a>
-mean they are
-<a href="http://ha.ckers.org/blog/20061208/xss-in-googles-orkut/">invulnerable.</a>
-You're putting a certain measure of the job on an external provider (just as
-you have by entrusting your user input to HTML Purifier), and
-it is important that you are cognizant of the risk.</p>
-
-<h3>Poorly written adaptations compromise security</h3>
-
-<p>This should go without saying, but if you're going to adapt this code
-for Google Video or the like, make sure you do it <em>right</em>. It's
-extremely easy to allow a character too many in <code>postFilter()</code> and
-suddenly you're introducing XSS into HTML Purifier's XSS free output. HTML
-Purifier may be well written, but it cannot guard against vulnerabilities
-introduced after it has finished.</p>
-
-<h2>Help out!</h2>
-
-<p>If you write a filter for your favorite video destination (or anything
-like that, for that matter), send it over and it might get included
-with the core!</p>
-
-</body>
-</html>

docs/examples/basic.php

@@ -1,14 +1,15 @@
-<?php exit;
+<?php
 
 // This file demonstrates basic usage of HTMLPurifier.
 
-require_once '/path/to/htmlpurifier/library/HTMLPurifier.auto.php';
+exit; // not to be called directly, it will fail fantastically!
+
+set_include_path('/path/to/htmlpurifier/library' . PATH_SEPARATOR . get_include_path());
+require_once 'HTMLPurifier.php';
 
 $purifier = new HTMLPurifier();
 $html = '<b>Simple and short';
 
 $pure_html = $purifier->purify($html);
 
-echo $pure_html;
-
 ?>

docs/examples/demo.php

@@ -1,66 +1,34 @@
 <?php
 
-// using _REQUEST because we accept GET and POST requests
+header('Content-type:text/html;charset=UTF-8');
 
-$content = empty($_REQUEST['xml']) ? 'text/html' : 'application/xhtml+xml';
+?><!DOCTYPE html 
-header("Content-type:$content;charset=UTF-8");
+     PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"
-
-// prevent PHP versions with shorttags from barfing
-echo '<?xml version="1.0" encoding="UTF-8" ?>
-';
-
-function getFormMethod() {
-    return (isset($_REQUEST['post'])) ? 'post' : 'get';
-}
-
-if (empty($_REQUEST['strict'])) {
-?><!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"
      "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
-<?php
+<html>
-} else {
-?>
-<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN"
-    "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">
-<?php
-}
-?>
-<html xmlns="http://www.w3.org/1999/xhtml" lang="en" xml:lang="en">
 <head>
-<title>HTML Purifier Live Demo</title>
+<title>HTMLPurifier Live Demo</title>
 <meta http-equiv="Content-Type" content="text/html; charset=UTF-8" />
 </head>
 <body>
-<h1>HTML Purifier Live Demo</h1>
+<h1>HTMLPurifier Live Demo</h1>
 <?php
 
-require_once '../../library/HTMLPurifier.auto.php';
+set_include_path('../../library' . PATH_SEPARATOR . get_include_path());
+require_once 'HTMLPurifier.php';
 
-if (!empty($_REQUEST['html'])) { // start result
+if (!empty($_POST['html'])) {
     
-    if (strlen($_REQUEST['html']) > 50000) {
+    $html = get_magic_quotes_gpc() ? stripslashes($_POST['html']) : $_POST['html'];
-        ?>
-        <p>Request exceeds maximum allowed text size of 50kb.</p>
-        <?php
-    } else { // start main processing
-    
-    $html = get_magic_quotes_gpc() ? stripslashes($_REQUEST['html']) : $_REQUEST['html'];
     
     $config = HTMLPurifier_Config::createDefault();
-    $config->set('Core', 'TidyFormat', !empty($_REQUEST['tidy']));
+    $config->set('Core', 'TidyFormat', !empty($_POST['tidy']));
-    $config->set('HTML', 'Strict',     !empty($_REQUEST['strict']));
     $purifier = new HTMLPurifier($config);
     $pure_html = $purifier->purify($html);
     
 ?>
 <p>Here is your purified HTML:</p>
 <div style="border:5px solid #CCC;margin:0 10%;padding:1em;">
-<?php if(getFormMethod() == 'get') { ?>
-<div style="float:right;">
-    <a href="http://validator.w3.org/check?uri=referer"><img
-        src="http://www.w3.org/Icons/valid-xhtml10"
-        alt="Valid XHTML 1.0 Transitional" height="31" width="88" style="border:0;" /></a>
-</div>
-<?php } ?>
 <?php
 
 echo $pure_html;
@@ -75,34 +43,23 @@ echo htmlspecialchars($pure_html, ENT_COMPAT, 'UTF-8');
 
 ?></pre>
 <?php
-if (getFormMethod() == 'post') { // start POST validation notice
+    
-?>
-<p>If you would like to validate the code with
-<a href="http://validator.w3.org/#validate-by-input">W3C's
-validator</a>, copy and paste the <em>entire</em> demo page's source.</p>
-<?php
-} // end POST validation notice
-
-} // end main processing
-
-// end result
 } else {
 
 ?>
-<p>Welcome to the live demo.  Enter some HTML and see how HTML Purifier
+<p>Welcome to the live demo.  Enter some HTML and see how HTMLPurifier
 will filter it.</p>
 <?php
 
 }
 
 ?>
-<form id="filter" action="demo.php<?php
+<form name="filter" action="demo.php<?php
-echo '?' . getFormMethod();
+if (isset($_GET['profile']) || isset($_GET['XDEBUG_PROFILE'])) {
-if (isset($_REQUEST['profile']) || isset($_REQUEST['XDEBUG_PROFILE'])) {
+    echo '?XDEBUG_PROFILE=1';
-    echo '&amp;XDEBUG_PROFILE=1';
+} ?>" method="post">
-} ?>" method="<?php echo getFormMethod();  ?>">
     <fieldset>
-        <legend>HTML Purifier Input (<?php echo getFormMethod(); ?>)</legend>
+        <legend>HTML</legend>
         <textarea name="html" cols="60" rows="15"><?php
 
 if (isset($html)) {
@@ -110,27 +67,13 @@ if (isset($html)) {
             HTMLPurifier_Encoder::cleanUTF8($html), ENT_COMPAT, 'UTF-8');
 }
         ?></textarea>
-        <?php if (getFormMethod() == 'get') { ?>
+        <div>Nicely format output with Tidy? <input type="checkbox" value="1"
-            <p><strong>Warning:</strong> GET request method can only hold
+        name="tidy"<?php if (!empty($_POST['tidy'])) echo ' checked="checked"'; ?> /></div>
-                8129 characters (probably less depending on your browser).
-                If you need to test anything
-                larger than that, try the <a href="demo.php?post">POST form</a>.</p>
-        <?php } ?>
-        <?php if (extension_loaded('tidy')) { ?>
-            <div>Nicely format output with Tidy? <input type="checkbox" value="1"
-            name="tidy"<?php if (!empty($_REQUEST['tidy'])) echo ' checked="checked"'; ?> /></div>
-        <?php } ?>
-        <div>XHTML 1.0 Strict output? <input type="checkbox" value="1"
-        name="strict"<?php if (!empty($_REQUEST['strict'])) echo ' checked="checked"'; ?> /></div>
-        <div>Serve as application/xhtml+xml? (not for IE) <input type="checkbox" value="1"
-        name="xml"<?php if (!empty($_REQUEST['xml'])) echo ' checked="checked"'; ?> /></div>
         <div>
             <input type="submit" value="Submit" name="submit" class="button" />
         </div>
     </fieldset>
 </form>
-<p>Return to <a href="http://hp.jpsband.org/">HTML Purifier's home page</a>.
+<p>Return to <a href="http://hp.jpsband.org/">HTMLPurifier's home page</a>.</p>
-Try the form in <a href="demo.php?get">GET</a> and <a href="demo.php?post">POST</a> request
-flavors (GET is easy to validate with W3C, but POST allows larger inputs).</p>
 </body>
 </html>

docs/filter-levels.txt

@@ -8,17 +8,14 @@ could go into this definition: the set of HTML good for blog entries is
 definitely too large for HTML that would be allowed in blog comments. Going
 from Transitional to Strict requires changes to the definition.
 
-Allowing users to specify their own whitelists is one step (implemented, btw), 
+However, allowing users to specify their own whitelists was an idea I
-but I have doubts on only doing this. Simply put, the typical programmer is too 
+rejected from the start.  Simply put, the typical programmer is too lazy
-lazy to actually go through the trouble of investigating which tags, attributes 
+to actually go through the trouble of investigating which tags, attributes
-and properties to allow. HTMLDefinition makes a big part of what HTMLPurifier 
+and properties to allow.  HTMLDefinition makes a big part of what HTMLPurifier
-is. 
+is.
 
 The idea, then, is to setup fundamentally different set of definitions, which
-can further be customized using simpler configuration options.  Alternatively,
+can further be customized using simpler configuration options.
-they could be implemented as configuration profiles, which simply load
-a set of recommended directives to acheive a desired affect (no simpler
-config options though).
 
 Here are some fuzzy levels you could set:
 
@@ -31,7 +28,7 @@ Here are some fuzzy levels you could set:
     to be useful)
 3. Pages - As permissive as possible without allowing XSS.  No protection
     against bad design sense, unfortunantely.  Suitable for wiki and page
-    environments. (probably what we have now)
+    environments.
 4. Lint - Accept everything in the spec, a Tidy wannabe. (This probably won't
     get implemented as it would require routines for things like <object>
     and friends to be implemented, which is a lot of work for not a lot of
@@ -129,5 +126,5 @@ Colored - background-color (background), border-color (border), color
 Dramatic - border, list-style-position (list-style), margin, padding,
     text-align, text-indent, text-transform, vertical-align, line-height
 
-Dramatic elements substantially change the look of text in ways that should
+Dramatic elements substnatially change the look of text in ways that should
 probably have been reserved to other areas.

docs/index.html

@@ -1,158 +0,0 @@
-<?xml version="1.0" encoding="UTF-8"?>
-<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN"
-    "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">
-<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en"><head>
-<meta http-equiv="Content-Type" content="text/html; charset=UTF-8" />
-<meta name="description" content="Index to all HTML Purifier documentation." />
-<link rel="stylesheet" type="text/css" href="./style.css" />
-
-<title>Documentation - HTML Purifier</title>
-
-</head>
-<body>
-
-<h1>Documentation</h1>
-
-<p><strong><a href="http://hp.jpsband.org/">HTML Purifier</a></strong> has documentation for all types of people.
-Here is an index of all of them.</p>
-
-<h2>End-user</h2>
-<p>End-user documentation that contains articles, tutorials and useful
-information for casual developers using HTML Purifier.</p>
-
-<dl>
-
-<dt><a href="enduser-id.html">IDs</a></dt>
-<dd>Explains various methods for allowing IDs in documents safely.</dd>
-
-<dt><a href="enduser-youtube.html">Embedding YouTube videos</a></dt>
-<dd>Explains how to safely allow the embedding of flash from trusted sites.</dd>
-
-<dt><a href="enduser-slow.html">Speeding up HTML Purifier</a></dt>
-<dd>Explains how to speed up HTML Purifier through caching or inbound filtering.</dd>
-
-<dt><a href="enduser-utf8.html">UTF-8</a></dt>
-<dd>Describes the rationale for using UTF-8, the ramifications otherwise, and how to make the switch.</dd>
-
-</dl>
-
-<h2>Development</h2>
-<p>Developer documentation detailing code issues, roadmaps and project
-conventions.</p>
-
-<dl>
-
-<dt><a href="dev-code-quality.html">Code Quality Issues</a></dt>
-<dd>Discusses code quality issues and places that need to be refactored.</dd>
-
-<dt><a href="dev-progress.html">Implementation Progress</a></dt>
-<dd>Tables detailing HTML element and CSS property implementation coverage.</dd>
-
-<dt><a href="dev-naming.html">Naming Conventions</a></dt>
-<dd>Defines class naming conventions.</dd>
-
-<dt><a href="dev-optimization.html">Optimization</a></dt>
-<dd>Discusses possible methods of optimizing HTML Purifier.</dd>
-
-</dl>
-
-<h2>Proposals</h2>
-<p>Proposed features, as well as the associated rambling to get a clear
-objective in place before attempted implementation.</p>
-
-<dl>
-<dt><a href="proposal-colors.html">Colors</a></dt>
-<dd>Proposal to allow for color constraints.</dd>
-</dl>
-
-<h2>Reference</h2>
-<p>Miscellaneous essays, research pieces and other reference type material
-that may not directly discuss HTML Purifier.</p>
-
-<dl>
-<dt><a href="ref-devnetwork.html">DevNetwork Credits</a></dt>
-<dd>Credits and links to DevNetwork forum topics.</dd>
-</dl>
-
-<h2>Internal memos</h2>
-
-<p>Plaintext documents that are more for use by active developers of
-the code. They may be upgraded to HTML files or stay as TXT scratchpads.</p>
-
-<table class="table">
-
-<thead><tr>
-    <th width="10%">Type</th>
-    <th width="20%">Name</th>
-    <th>Description</th>
-</tr></thead>
-
-<tbody>
-
-<tr>
-    <td>End-user</td>
-    <td><a href="enduser-overview.txt">Overview</a></td>
-    <td>High level overview of the general control flow (mostly obsolete).</td>
-</tr>
-
-<tr>
-    <td>End-user</td>
-    <td><a href="enduser-security.txt">Security</a></td>
-    <td>Common security issues that may still arise (half-baked).</td>
-</tr>
-
-<tr>
-    <td>Proposal</td>
-    <td><a href="proposal-filter-levels.txt">Filter levels</a></td>
-    <td>Outlines details of projected configurable level of filtering.</td>
-</tr>
-
-<tr>
-    <td>Proposal</td>
-    <td><a href="proposal-language.txt">Language</a></td>
-    <td>Specification of I18N for error messages derived from MediaWiki (half-baked).</td>
-</tr>
-
-<tr>
-    <td>Proposal</td>
-    <td><a href="proposal-new-directives.txt">New directives</a></td>
-    <td>Assorted configuration options that could be implemented.</td>
-</tr>
-
-<tr>
-    <td>Reference</td>
-    <td><a href="ref-loose-vs-strict.txt">Loose vs.Strict</a></td>
-    <td>Differences between HTML Strict and Transitional versions.</td>
-</tr>
-
-<tr>
-    <td>Reference</td>
-    <td><a href="ref-proprietary-tags.txt">Proprietary tags</a></td>
-    <td>List of vendor-specific tags we may want to transform to W3C compliant markup.</td>
-</tr>
-
-<tr>
-    <td>Reference</td>
-    <td><a href="ref-strictness.txt">Strictness</a></td>
-    <td>Short essay on how loose definition isn't really loose.</td>
-</tr>
-
-<tr>
-    <td>Reference</td>
-    <td><a href="ref-xhtml-1.1.txt">XHTML 1.1</a></td>
-    <td>What we'd have to do to support XHTML 1.1.</td>
-</tr>
-
-<tr>
-    <td>Reference</td>
-    <td><a href="ref-whatwg.txt">WHATWG</a></td>
-    <td>How WHATWG plays into what we need to do.</td>
-</tr>
-
-</tbody>
-
-</table>
-
-<div id="version">$Id$</div>
-</body>
-</html>

docs/naming.txt

@@ -0,0 +1,56 @@
+
+Naming
+
+The classes in this library follow a few naming conventions, which may
+help you find the correct functionality more quickly.  Here they are:
+
+All classes occupy the HTMLPurifier pseudo-namespace.
+    This means that all classes are prefixed with HTMLPurifier_.  As such, all
+    names under HTMLPurifier_ are reserved.  I recommend that you use the name
+    HTMLPurifierX_YourName_ClassName, especially if you want to take advantage
+    of HTMLPurifier_ConfigDef.
+
+All classes correspond to their path if library/ was in the include path
+    HTMLPurifier_AttrDef is located at HTMLPurifier/AttrDef.php; replace
+    underscores with slashes and append .php and you'll have the location of
+    the class.
+
+Harness and Test are reserved class names for unit tests
+    The suffix "Test" indicates that the class is a subclass of UnitTestCase
+    (of the Simpletest library) and is testable. "Harness" indicates a subclass
+    of UnitTestCase that is not meant to be run but to be extended into 
+    concrete test cases and contains custom test methods (i.e. assert*())
+
+Class names do not necessarily represent inheritance hierarchies
+    While we try to reflect inheritance in naming to some extent, it is not
+    guaranteed (for instance, none of the classes inherit from HTMLPurifier,
+    the base class).  However, all class files have the require_once
+    declarations to whichever classes they are tightly coupled to.
+
+Strategy has a meaning different from the Gang of Four pattern
+    In Design Patterns, the Gang of Four describes a Strategy object as
+    encapsulating an algorithm so that they can be switched at run-time.  While
+    our strategies are indeed algorithms, they are not meant to be substituted:
+    all must be present in order for proper functioning.
+
+Abbreviations are avoided
+    We try to avoid abbreviations as much as possible, but in some cases, 
+    abbreviated version is more readable than the full version. Here, we
+    list common abbreviations:
+        Attr(s) -> Attribute(s)
+        Def -> Definition
+
+Ambiguity concerning the definition of Def/Definition
+    While a definition normally defines the structure/acceptable values of
+    an entity, most of the definitions in this application also attempt
+    to validate and fix the value.  I am unsure of a better name, as
+    "Validator" would exclude fixing the value, "Fixer" doesn't invoke
+    the proper image of "fixing" something, and "ValidatorFixer" is too long!
+    Some other suggestions were "Handler", "Reference", "Check", "Fix",
+    "Repair" and "Heal".
+
+Transform not Transformer
+    Transform is both a noun and a verb, and thus we define a "Transform" as
+    something that "transforms," leaving "Transformer" (which sounds like an
+    electrical device/robot toy).
+

docs/optimization.txt

@@ -0,0 +1,12 @@
+
+Optimization
+
+Here are some possible optimization techniques we can apply to code sections if
+they turn out to be slow.  Be sure not to prematurely optimize: if you get
+that itch, put it here!
+
+ - Make Tokens Flyweights (may prove problematic, probably not worth it)
+ - Rewrite regexps into PHP code
+ - Serialize the Definition object
+ - Batch regexp validation (do as many per function call as possible)
+ - Parallelize strategies

docs/progress.html

@@ -1,302 +1,292 @@
-<?xml version="1.0" encoding="UTF-8"?>
+<?xml version="1.0" encoding="UTF-8"?>
-<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN"
+<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN"
-    "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">
+    "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">
-<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en"><head>
+<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en"><head>
-<meta http-equiv="Content-Type" content="text/html; charset=UTF-8" />
+
-<meta name="description" content="Tables detailing HTML element and CSS property implementation coverage in HTML Purifier." />
+<title>HTMLPurifier Progress</title>
-<link rel="stylesheet" type="text/css" href="./style.css" />
+
-
+<style type="text/css">
-<title>Implementation Progress - HTML Purifier</title>
+
-
+td {padding-right:1em;border-bottom:1px solid #000;padding-left:0.5em;}
-<style type="text/css">
+th {text-align:left;padding-top:1.4em;font-size:13pt;
-
+    border-bottom:2px solid #000;background:#FFF;}
-td {padding-right:1em;border-bottom:1px solid #000;padding-left:0.5em;}
+thead th {text-align:left;padding:0.1em;background-color:#EEE;}
-th {text-align:left;padding-top:1.4em;font-size:13pt;
+
-    border-bottom:2px solid #000;background:#FFF;}
+.impl-yes {background:#9D9;}
-thead th {text-align:left;padding:0.1em;background-color:#EEE;}
+.impl-partial {background:#FFA;}
-
+.impl-no {background:#CCC;}
-.impl-yes {background:#9D9;}
+
-.impl-partial {background:#FFA;}
+.danger {color:#600;}
-.impl-no {background:#CCC;}
+.css1 {color:#060;}
-
+.required {font-weight:bold;}
-.danger {color:#600;}
+.feature {color:#999;}
-.css1 {color:#060;}
+
-.required {font-weight:bold;}
+</style>
-.feature {color:#999;}
+
-
+</head><body>
-</style>
+
-
+<h1>HTMLPurifier Progress</h1>
-</head><body>
+
-
+<h2>Key</h2>
-<h1>Implementation Progress</h1>
+
-
+<table cellspacing="0"><tbody>
-<div id="filing">Filed under Development</div>
+<tr><td class="impl-yes">Implemented</td></tr>
-<div id="index">Return to the <a href="index.html">index</a>.</div>
+<tr><td class="impl-partial">Partially implemented</td></tr>
-<div id="home"><a href="http://hp.jpsband.org/">HTML Purifier</a> End-User Documentation</div>
+<tr><td class="impl-no">Will not implement</td></tr>
-
+<tr><td class="danger">Dangerous attribute/property</td></tr>
-<h2>Key</h2>
+<tr><td class="css1">Present in CSS1</td></tr>
-
+<tr><td class="feature">Feature, requires extra work</td></tr>
-<table cellspacing="0"><tbody>
+</tbody></table>
-<tr><td class="impl-yes">Implemented</td></tr>
+
-<tr><td class="impl-partial">Partially implemented</td></tr>
+<h3>CSS</h3>
-<tr><td class="impl-no">Will not implement</td></tr>
+
-<tr><td class="danger">Dangerous attribute/property</td></tr>
+<table cellspacing="0">
-<tr><td class="css1">Present in CSS1</td></tr>
+
-<tr><td class="feature">Feature, requires extra work</td></tr>
+<thead>
-</tbody></table>
+<tr><th>Name</th><th>Notes</th></tr>
-
+</thead>
-<h2>CSS</h2>
+
-
+<!--
-<table cellspacing="0">
+<tr><td>-</td><td>-</td></tr>
-
+-->
-<thead>
+
-<tr><th>Name</th><th>Notes</th></tr>
+<tbody>
-</thead>
+<tr><th colspan="2">Standard</th></tr>
-
+<tr class="css1 impl-yes"><td>background-color</td><td>COMPOSITE(&lt;color&gt;, transparent)</td></tr>
-<!--
+<tr class="css1 impl-yes"><td>background</td><td>SHORTHAND, only for color, see below for info on background-image and friends</td></tr>
-<tr><td>-</td><td>-</td></tr>
+<tr class="css1 impl-yes"><td>border</td><td>SHORTHAND, MULTIPLE</td></tr>
--->
+<tr class="css1 impl-yes"><td>border-color</td><td>MULTIPLE</td></tr>
-
+<tr class="css1 impl-yes"><td>border-style</td><td>MULTIPLE</td></tr>
-<tbody>
+<tr class="css1 impl-yes"><td>border-width</td><td>MULTIPLE</td></tr>
-<tr><th colspan="2">Standard</th></tr>
+<tr class="css1 impl-yes"><td>border-*</td><td>SHORTHAND</td></tr>
-<tr class="css1 impl-yes"><td>background-color</td><td>COMPOSITE(&lt;color&gt;, transparent)</td></tr>
+<tr class="impl-yes"><td>border-*-color</td><td>COMPOSITE(&lt;color&gt;, transparent)</td></tr>
-<tr class="css1 impl-yes"><td>background</td><td>SHORTHAND, currently alias for background-color</td></tr>
+<tr class="impl-yes"><td>border-*-style</td><td>ENUM(none, hidden, dotted, dashed,
-<tr class="css1 impl-yes"><td>border</td><td>SHORTHAND, MULTIPLE</td></tr>
+    solid, double, groove, ridge, inset, outset)</td></tr>
-<tr class="css1 impl-yes"><td>border-color</td><td>MULTIPLE</td></tr>
+<tr class="css1 impl-yes"><td>border-*-width</td><td>COMPOSITE(&lt;length&gt;, thin, medium, thick)</td></tr>
-<tr class="css1 impl-yes"><td>border-style</td><td>MULTIPLE</td></tr>
+<tr class="css1 impl-yes"><td>clear</td><td>ENUM(none, left, right, both)</td></tr>
-<tr class="css1 impl-yes"><td>border-width</td><td>MULTIPLE</td></tr>
+<tr class="css1 impl-yes"><td>color</td><td>&lt;color&gt;</td></tr>
-<tr class="css1 impl-yes"><td>border-*</td><td>SHORTHAND</td></tr>
+<tr class="css1 impl-yes"><td>float</td><td>ENUM(left, right, none), May require layout
-<tr class="impl-yes"><td>border-*-color</td><td>COMPOSITE(&lt;color&gt;, transparent)</td></tr>
+    precautions with clear</td></tr>
-<tr class="impl-yes"><td>border-*-style</td><td>ENUM(none, hidden, dotted, dashed,
+<tr class="css1 impl-yes"><td>font</td><td>SHORTHAND</td></tr>
-    solid, double, groove, ridge, inset, outset)</td></tr>
+<tr class="css1 impl-yes"><td>font-family</td><td>CSS validator may complain if fallback font
-<tr class="css1 impl-yes"><td>border-*-width</td><td>COMPOSITE(&lt;length&gt;, thin, medium, thick)</td></tr>
+    family not specified</td></tr>
-<tr class="css1 impl-yes"><td>clear</td><td>ENUM(none, left, right, both)</td></tr>
+<tr class="css1 impl-yes"><td>font-size</td><td>COMPOSITE(&lt;absolute-size&gt;,
-<tr class="css1 impl-yes"><td>color</td><td>&lt;color&gt;</td></tr>
+    &lt;relative-size&gt;, &lt;length&gt;, &lt;percentage&gt;)</td></tr>
-<tr class="css1 impl-yes"><td>float</td><td>ENUM(left, right, none), May require layout
+<tr class="css1 impl-yes"><td>font-style</td><td>ENUM(normal, italic, oblique)</td></tr>
-    precautions with clear</td></tr>
+<tr class="css1 impl-yes"><td>font-variant</td><td>ENUM(normal, small-caps)</td></tr>
-<tr class="css1 impl-yes"><td>font</td><td>SHORTHAND</td></tr>
+<tr class="css1 impl-yes"><td>font-weight</td><td>ENUM(normal, bold, bolder, lighter,
-<tr class="css1 impl-yes"><td>font-family</td><td>CSS validator may complain if fallback font
+    100, 200, 300, 400, 500, 600, 700, 800, 900), maybe special code for
-    family not specified</td></tr>
+    in-between integers</td></tr>
-<tr class="css1 impl-yes"><td>font-size</td><td>COMPOSITE(&lt;absolute-size&gt;,
+<tr class="css1 impl-yes"><td>letter-spacing</td><td>COMPOSITE(&lt;length&gt;, normal)</td></tr>
-    &lt;relative-size&gt;, &lt;length&gt;, &lt;percentage&gt;)</td></tr>
+<tr class="css1 impl-yes"><td>line-height</td><td>COMPOSITE(&lt;number&gt;,
-<tr class="css1 impl-yes"><td>font-style</td><td>ENUM(normal, italic, oblique)</td></tr>
+    &lt;length&gt;, &lt;percentage&gt;, normal)</td></tr>
-<tr class="css1 impl-yes"><td>font-variant</td><td>ENUM(normal, small-caps)</td></tr>
+<tr class="css1 impl-yes"><td>list-style-position</td><td>ENUM(inside, outside),
-<tr class="css1 impl-yes"><td>font-weight</td><td>ENUM(normal, bold, bolder, lighter,
+    Strange behavior in browsers</td></tr>
-    100, 200, 300, 400, 500, 600, 700, 800, 900), maybe special code for
+<tr class="css1 impl-yes"><td>list-style-type</td><td>ENUM(...),
-    in-between integers</td></tr>
+    Well-supported values are: disc, circle, square,
-<tr class="css1 impl-yes"><td>letter-spacing</td><td>COMPOSITE(&lt;length&gt;, normal)</td></tr>
+    decimal, lower-roman, upper-roman, lower-alpha and upper-alpha. See also
-<tr class="css1 impl-yes"><td>line-height</td><td>COMPOSITE(&lt;number&gt;,
+    CSS 3. Mostly IE lack of support.</td></tr>
-    &lt;length&gt;, &lt;percentage&gt;, normal)</td></tr>
+<tr class="css1 impl-yes"><td>list-style</td><td>SHORTHAND</td></tr>
-<tr class="css1 impl-yes"><td>list-style-position</td><td>ENUM(inside, outside),
+<tr class="css1 impl-yes"><td>margin</td><td>MULTIPLE</td></tr>
-    Strange behavior in browsers</td></tr>
+<tr class="css1 impl-yes"><td>margin-*</td><td>COMPOSITE(&lt;length&gt;,
-<tr class="css1 impl-yes"><td>list-style-type</td><td>ENUM(...),
+    &lt;percentage&gt;, auto)</td></tr>
-    Well-supported values are: disc, circle, square,
+<tr class="css1 impl-yes"><td>padding</td><td>MULTIPLE</td></tr>
-    decimal, lower-roman, upper-roman, lower-alpha and upper-alpha. See also
+<tr class="css1 impl-yes"><td>padding-*</td><td>COMPOSITE(&lt;length&gt;(positive),
-    CSS 3. Mostly IE lack of support.</td></tr>
+    &lt;percentage&gt;(positive))</td></tr>
-<tr class="css1 impl-yes"><td>list-style</td><td>SHORTHAND</td></tr>
+<tr class="css1 impl-yes"><td>text-align</td><td>ENUM(left, right,
-<tr class="css1 impl-yes"><td>margin</td><td>MULTIPLE</td></tr>
+    center, justify)</td></tr>
-<tr class="css1 impl-yes"><td>margin-*</td><td>COMPOSITE(&lt;length&gt;,
+<tr class="css1 impl-yes"><td>text-decoration</td><td>No blink (argh my eyes), not
-    &lt;percentage&gt;, auto)</td></tr>
+    enum, can be combined (composite sorta): underline, overline,
-<tr class="css1 impl-yes"><td>padding</td><td>MULTIPLE</td></tr>
+    line-through</td></tr>
-<tr class="css1 impl-yes"><td>padding-*</td><td>COMPOSITE(&lt;length&gt;(positive),
+<tr class="css1 impl-yes"><td>text-indent</td><td>COMPOSITE(&lt;length&gt;,
-    &lt;percentage&gt;(positive))</td></tr>
+    &lt;percentage&gt;)</td></tr>
-<tr class="css1 impl-yes"><td>text-align</td><td>ENUM(left, right,
+<tr class="css1 impl-yes"><td>text-transform</td><td>ENUM(capitalize, uppercase,
-    center, justify)</td></tr>
+    lowercase, none)</td></tr>
-<tr class="css1 impl-yes"><td>text-decoration</td><td>No blink (argh my eyes), not
+<tr class="css1 impl-yes"><td>width</td><td>COMPOSITE(&lt;length&gt;,
-    enum, can be combined (composite sorta): underline, overline,
+    &lt;percentage&gt;, auto), Interesting</td></tr>
-    line-through</td></tr>
+<tr class="css1 impl-yes"><td>word-spacing</td><td>COMPOSITE(&lt;length&gt;, auto),
-<tr class="css1 impl-yes"><td>text-indent</td><td>COMPOSITE(&lt;length&gt;,
+    IE 5 no support</td></tr>
-    &lt;percentage&gt;)</td></tr>
+</tbody>
-<tr class="css1 impl-yes"><td>text-transform</td><td>ENUM(capitalize, uppercase,
+
-    lowercase, none)</td></tr>
+<tbody>
-<tr class="css1 impl-yes"><td>width</td><td>COMPOSITE(&lt;length&gt;,
+<tr><th colspan="2">Table</th></tr>
-    &lt;percentage&gt;, auto), Interesting</td></tr>
+<tr class="impl-yes"><td>border-collapse</td><td>ENUM(collapse, seperate)</td></tr>
-<tr class="css1 impl-yes"><td>word-spacing</td><td>COMPOSITE(&lt;length&gt;, auto),
+<tr class="impl-yes"><td>caption-side</td><td>ENUM(top, bottom)</td></tr>
-    IE 5 no support</td></tr>
+<tr class="feature"><td>empty-cells</td><td>ENUM(show, hide), No IE support makes this useless,
-</tbody>
+    possible fix with &amp;nbsp;? Unknown release milestone.</td></tr>
-
+<tr class="impl-yes"><td>table-layout</td><td>ENUM(auto, fixed)</td></tr>
-<tbody>
+<tr class="impl-yes css1"><td>vertical-align</td><td>COMPOSITE(ENUM(baseline, sub,
-<tr><th colspan="2">Table</th></tr>
+    super, top, text-top, middle, bottom, text-bottom), &lt;percentage&gt;,
-<tr class="impl-yes"><td>border-collapse</td><td>ENUM(collapse, seperate)</td></tr>
+    &lt;length&gt;) Also applies to others with explicit height</td></tr>
-<tr class="impl-yes"><td>caption-side</td><td>ENUM(top, bottom)</td></tr>
+</tbody>
-<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>
+<tbody>
-<tr class="impl-yes"><td>table-layout</td><td>ENUM(auto, fixed)</td></tr>
+<tr><th colspan="2">Absolute positioning, unknown release milestone</th></tr>
-<tr class="impl-yes css1"><td>vertical-align</td><td>COMPOSITE(ENUM(baseline, sub,
+<tr class="danger"><td>bottom</td><td rowspan="4">Dangerous, must be non-negative</td></tr>
-    super, top, text-top, middle, bottom, text-bottom), &lt;percentage&gt;,
+<tr class="danger"><td>left</td></tr>
-    &lt;length&gt;) Also applies to others with explicit height</td></tr>
+<tr class="danger"><td>right</td></tr>
-</tbody>
+<tr class="danger"><td>top</td></tr>
-
+<tr><td>clip</td><td>-</td></tr>
-<tbody>
+<tr class="danger"><td>position</td><td>ENUM(static, relative, absolute, fixed), permit
-<tr><th colspan="2">Absolute positioning, unknown release milestone</th></tr>
+    relative not absolute?</td></tr>
-<tr class="danger impl-no"><td>bottom</td><td rowspan="4">Dangerous, must be non-negative to even be considered,
+<tr class="danger"><td>z-index</td><td>Dangerous</td></tr>
-    but it's still possible to arbitrarily position by running over.</td></tr>
+</tbody>
-<tr class="danger impl-no"><td>left</td></tr>
+
-<tr class="danger impl-no"><td>right</td></tr>
+<tbody>
-<tr class="danger impl-no"><td>top</td></tr>
+<tr><th colspan="2">Unknown</th></tr>
-<tr class="impl-no"><td>clip</td><td>-</td></tr>
+<tr class="danger css1"><td>background-image</td><td>Dangerous, target milestone 1.2</td></tr>
-<tr class="danger impl-no"><td>position</td><td>ENUM(static, relative, absolute, fixed)
+<tr class="css1"><td>background-attachment</td><td>ENUM(scroll, fixed),
-    relative not absolute?</td></tr>
+    Depends on background-image</td></tr>
-<tr class="danger impl-no"><td>z-index</td><td>Dangerous</td></tr>
+<tr class="css1"><td>background-position</td><td>Depends on background-image</td></tr>
-</tbody>
+<tr class="danger impl-no"><td>cursor</td><td>Dangerous but fluffy</td></tr>
-
+<tr class="danger css1"><td>display</td><td>ENUM(...), Dangerous but interesting;
-<tbody>
+    will not implement list-item, run-in (Opera only) or table (no IE);
-<tr><th colspan="2">Unknown</th></tr>
+    inline-block has incomplete IE6 support and requires -moz-inline-box
-<tr class="danger css1 impl-yes"><td>background-image</td><td>Dangerous, target milestone 1.3</td></tr>
+    for Mozilla. Unknown target milestone.</td></tr>
-<tr class="css1 impl-yes"><td>background-attachment</td><td>ENUM(scroll, fixed),
+<tr><td class="css1">height</td><td>Interesting, why use it? Unknown target milestone.</td></tr>
-    Depends on background-image</td></tr>
+<tr class="danger css1"><td>list-style-image</td><td>Dangerous? Target milestone 1.2</td></tr>
-<tr class="css1 impl-yes"><td>background-position</td><td>Depends on background-image</td></tr>
+<tr class="impl-no"><td>max-height</td><td rowspan="4">No IE 5/6</td></tr>
-<tr class="danger impl-no"><td>cursor</td><td>Dangerous but fluffy</td></tr>
+<tr class="impl-no"><td>min-height</td></tr>
-<tr class="danger css1"><td>display</td><td>ENUM(...), Dangerous but interesting;
+<tr class="impl-no"><td>max-width</td></tr>
-    will not implement list-item, run-in (Opera only) or table (no IE);
+<tr class="impl-no"><td>min-width</td></tr>
-    inline-block has incomplete IE6 support and requires -moz-inline-box
+<tr class="impl-no"><td>orphans</td><td>No IE support</td></tr>
-    for Mozilla. Unknown target milestone.</td></tr>
+<tr class="impl-no"><td>widows</td><td>No IE support</td></tr>
-<tr class="css1"><td>height</td><td>Interesting, why use it? Unknown target milestone.</td></tr>
+<tr><td>overflow</td><td>ENUM, IE 5/6 almost (remove visible if set). Unknown target milestone.</td></tr>
-<tr class="danger css1 impl-yes"><td>list-style-image</td><td>Dangerous?</td></tr>
+<tr><td>page-break-after</td><td>ENUM(auto, always, avoid, left, right),
-<tr class="impl-no"><td>max-height</td><td rowspan="4">No IE 5/6</td></tr>
+    IE 5.5/6 and Opera. Unknown target milestone.</td></tr>
-<tr class="impl-no"><td>min-height</td></tr>
+<tr><td>page-break-before</td><td>ENUM(auto, always, avoid, left, right),
-<tr class="impl-no"><td>max-width</td></tr>
+    Mostly supported. Unknown target milestone.</td></tr>
-<tr class="impl-no"><td>min-width</td></tr>
+<tr><td>page-break-inside</td><td>ENUM(avoid, auto), Opera only. Unknown target milestone.</td></tr>
-<tr class="impl-no"><td>orphans</td><td>No IE support</td></tr>
+<tr class="impl-no"><td>quotes</td><td>May be dropped from CSS2, fairly useless for inline context</td></tr>
-<tr class="impl-no"><td>widows</td><td>No IE support</td></tr>
+<tr class="impl-no"><td>visibility</td><td>ENUM(visible, hidden, collapse),
-<tr><td>overflow</td><td>ENUM, IE 5/6 almost (remove visible if set). Unknown target milestone.</td></tr>
+    Dangerous</td></tr>
-<tr><td>page-break-after</td><td>ENUM(auto, always, avoid, left, right),
+<tr class="css1 feature"><td>white-space</td><td>ENUM(normal, pre, nowrap, pre-wrap,
-    IE 5.5/6 and Opera. Unknown target milestone.</td></tr>
+    pre-line), Spotty implementation:
-<tr><td>page-break-before</td><td>ENUM(auto, always, avoid, left, right),
+    pre (no IE 5/6), nowrap (no IE 5),
-    Mostly supported. Unknown target milestone.</td></tr>
+    pre-wrap (only Opera), pre-line (no support). Fixable? Unknown target milestone.</td></tr>
-<tr><td>page-break-inside</td><td>ENUM(avoid, auto), Opera only. Unknown target milestone.</td></tr>
+</tbody>
-<tr class="impl-no"><td>quotes</td><td>May be dropped from CSS2, fairly useless for inline context</td></tr>
+
-<tr class="impl-no"><td>visibility</td><td>ENUM(visible, hidden, collapse),
+<tbody class="impl-no">
-    Dangerous</td></tr>
+<tr><th colspan="2">Aural</th></tr>
-<tr class="css1 feature"><td>white-space</td><td>ENUM(normal, pre, nowrap, pre-wrap,
+<tr><td>azimuth</td><td>-</td></tr>
-    pre-line), Spotty implementation:
+<tr><td>cue</td><td>-</td></tr>
-    pre (no IE 5/6), nowrap (no IE 5),
+<tr><td>cue-after</td><td>-</td></tr>
-    pre-wrap (only Opera), pre-line (no support). Fixable? Unknown target milestone.</td></tr>
+<tr><td>cue-before</td><td>-</td></tr>
-</tbody>
+<tr><td>elevation</td><td>-</td></tr>
-
+<tr><td>pause-after</td><td>-</td></tr>
-<tbody class="impl-no">
+<tr><td>pause-before</td><td>-</td></tr>
-<tr><th colspan="2">Aural</th></tr>
+<tr><td>pause</td><td>-</td></tr>
-<tr><td>azimuth</td><td>-</td></tr>
+<tr><td>pitch-range</td><td>-</td></tr>
-<tr><td>cue</td><td>-</td></tr>
+<tr><td>pitch</td><td>-</td></tr>
-<tr><td>cue-after</td><td>-</td></tr>
+<tr><td>play-during</td><td>-</td></tr>
-<tr><td>cue-before</td><td>-</td></tr>
+<tr><td>richness</td><td>-</td></tr>
-<tr><td>elevation</td><td>-</td></tr>
+<tr><td>speak-header</td><td>Table related</td></tr>
-<tr><td>pause-after</td><td>-</td></tr>
+<tr><td>speak-numeral</td><td>-</td></tr>
-<tr><td>pause-before</td><td>-</td></tr>
+<tr><td>speak-punctuation</td><td>-</td></tr>
-<tr><td>pause</td><td>-</td></tr>
+<tr><td>speak</td><td>-</td></tr>
-<tr><td>pitch-range</td><td>-</td></tr>
+<tr><td>speech-rate</td><td>-</td></tr>
-<tr><td>pitch</td><td>-</td></tr>
+<tr><td>stress</td><td>-</td></tr>
-<tr><td>play-during</td><td>-</td></tr>
+<tr><td>voice-family</td><td>-</td></tr>
-<tr><td>richness</td><td>-</td></tr>
+<tr><td>volume</td><td>-</td></tr>
-<tr><td>speak-header</td><td>Table related</td></tr>
+</tbody>
-<tr><td>speak-numeral</td><td>-</td></tr>
+
-<tr><td>speak-punctuation</td><td>-</td></tr>
+<tbody class="impl-no">
-<tr><td>speak</td><td>-</td></tr>
+<tr><th colspan="2">Will not implement</th></tr>
-<tr><td>speech-rate</td><td>-</td></tr>
+<tr><td>content</td><td>Not applicable for inline styles</td></tr>
-<tr><td>stress</td><td>-</td></tr>
+<tr><td>counter-increment</td><td>Needs content, Opera only</td></tr>
-<tr><td>voice-family</td><td>-</td></tr>
+<tr><td>counter-reset</td><td>Needs content, Opera only</td></tr>
-<tr><td>volume</td><td>-</td></tr>
+<tr><td>direction</td><td>No support</td></tr>
-</tbody>
+<tr><td>outline-color</td><td rowspan="4">IE Mac and Opera on outside,
-
+Mozilla on inside and needs -moz-outline, no IE support.</td></tr>
-<tbody class="impl-no">
+    <tr><td>outline-style</td></tr>
-<tr><th colspan="2">Will not implement</th></tr>
+    <tr><td>outline-width</td></tr>
-<tr><td>content</td><td>Not applicable for inline styles</td></tr>
+    <tr><td>outline</td></tr>
-<tr><td>counter-increment</td><td>Needs content, Opera only</td></tr>
+<tr><td>unicode-bidi</td><td>No support</td></tr>
-<tr><td>counter-reset</td><td>Needs content, Opera only</td></tr>
+</tbody>
-<tr><td>direction</td><td>No support</td></tr>
+
-<tr><td>outline-color</td><td rowspan="4">IE Mac and Opera on outside,
+</table>
-Mozilla on inside and needs -moz-outline, no IE support.</td></tr>
+
-    <tr><td>outline-style</td></tr>
+<h2>Interesting Attributes</h2>
-    <tr><td>outline-width</td></tr>
+
-    <tr><td>outline</td></tr>
+<table cellspacing="0">
-<tr><td>unicode-bidi</td><td>No support</td></tr>
+
-</tbody>
+<thead>
-
+<tr><th>Attribute</th><th>Tags</th><th>Notes</th></tr>
-</table>
+</thead>
-
+
-<h2>Interesting Attributes</h2>
+<!--
-
+<tr><th></th></tr>
-<table cellspacing="0">
+<tbody>
-
+<tr><td>-</td><td>-</td><td>-</td></tr>
-<thead>
+</tbody>
-<tr><th>Attribute</th><th>Tags</th><th>Notes</th></tr>
+-->
-</thead>
+
-
+<tbody>
-<!--
+<tr><th colspan="3">CSS</th></tr>
-<tr><th></th></tr>
+<tr class="impl-yes"><td>style</td><td>All</td><td>Not all properties may be implemented, parser is good though.</td></tr>
-<tbody>
+</tbody>
-<tr><td>-</td><td>-</td><td>-</td></tr>
+
-</tbody>
+<tbody>
--->
+<tr><th colspan="3">Questionable</th></tr>
-
+<tr class="impl-no"><td>accesskey</td><td>A</td><td>May interfere with main interface</td></tr>
-<tbody>
+<tr class="impl-no"><td>tabindex</td><td>A</td><td>May interfere with main interface</td></tr>
-<tr><th colspan="3">CSS</th></tr>
+<tr><td>target</td><td>A</td><td>Config enabled, only useful for frame layouts</td></tr>
-<tr class="impl-yes"><td>style</td><td>All</td><td>Parser is reasonably functional. Status here doesn't count individual properties.</td></tr>
+</tbody>
-</tbody>
+
-
+<tbody>
-<tbody>
+<tr><th colspan="3">Miscellaneous</th></tr>
-<tr><th colspan="3">Questionable</th></tr>
+<tr><td>datetime</td><td>DEL, INS</td><td>No visible effect, ISO format</td></tr>
-<tr class="impl-no"><td>accesskey</td><td>A</td><td>May interfere with main interface</td></tr>
+<tr><td>rel</td><td>A</td><td>Largely user-defined: nofollow, tag (see microformats)</td></tr>
-<tr class="impl-no"><td>tabindex</td><td>A</td><td>May interfere with main interface</td></tr>
+<tr><td>rev</td><td>A</td><td>Largely user-defined: vote-*</td></tr>
-<tr><td>target</td><td>A</td><td>Config enabled, only useful for frame layouts, disallowed in strict</td></tr>
+<tr class="feature"><td>axis</td><td>TD, TH</td><td>W3C only: No browser implementation</td></tr>
-</tbody>
+<tr class="feature"><td>char</td><td>COL, COLGROUP, TBODY, TD, TFOOT, TH, THEAD, TR</td><td>W3C only: No browser implementation</td></tr>
-
+<tr class="feature"><td>headers</td><td>TD, TH</td><td>W3C only: No browser implementation</td></tr>
-<tbody>
+<tr class="feature"><td>scope</td><td>TD, TH</td><td>W3C only: No browser implementation</td></tr>
-<tr><th colspan="3">Miscellaneous</th></tr>
+</tbody>
-<tr><td>datetime</td><td>DEL, INS</td><td>No visible effect, ISO format</td></tr>
+
-<tr><td>rel</td><td>A</td><td>Largely user-defined: nofollow, tag (see microformats)</td></tr>
+<tbody class="impl-yes">
-<tr><td>rev</td><td>A</td><td>Largely user-defined: vote-*</td></tr>
+<tr><th colspan="3">URI</th></tr>
-<tr class="feature"><td>axis</td><td>TD, TH</td><td>W3C only: No browser implementation</td></tr>
+<tr><td rowspan="2">cite</td><td>BLOCKQUOTE, Q</td><td>For attribution</td></tr>
-<tr class="feature"><td>char</td><td>COL, COLGROUP, TBODY, TD, TFOOT, TH, THEAD, TR</td><td>W3C only: No browser implementation</td></tr>
+    <tr><td>DEL, INS</td><td>Link to explanation why it changed</td></tr>
-<tr class="feature"><td>headers</td><td>TD, TH</td><td>W3C only: No browser implementation</td></tr>
+<tr><td>href</td><td>A</td><td>-</td></tr>
-<tr class="feature"><td>scope</td><td>TD, TH</td><td>W3C only: No browser implementation</td></tr>
+<tr><td>longdesc</td><td>IMG</td><td>-</td></tr>
-</tbody>
+<tr class="required"><td>src</td><td>IMG</td><td>Required</td></tr>
-
+</tbody>
-<tbody class="impl-yes">
+
-<tr><th colspan="3">URI</th></tr>
+<tbody>
-<tr><td rowspan="2">cite</td><td>BLOCKQUOTE, Q</td><td>For attribution</td></tr>
+<tr><th colspan="3">Transform, target milestone 1.4</th></tr>
-    <tr><td>DEL, INS</td><td>Link to explanation why it changed</td></tr>
+<tr><td rowspan="5">align</td><td>CAPTION</td><td>Near-equiv style 'caption-side', drop left and right</td></tr>
-<tr><td>href</td><td>A</td><td>-</td></tr>
+    <tr><td>IMG</td><td rowspan="2">Margin-left and margin-right = auto or parent div</td></tr>
-<tr><td>longdesc</td><td>IMG</td><td>-</td></tr>
+    <tr><td>TABLE</td></tr>
-<tr class="required"><td>src</td><td>IMG</td><td>Required</td></tr>
+    <tr><td>HR</td><td>Equivalent style 'text-align' (IE tested)</td></tr>
-</tbody>
+    <tr class="impl-yes"><td>H1, H2, H3, H4, H5, H6, P</td><td>Equivalent style 'text-align'</td></tr>
-
+<tr class="required impl-yes"><td>alt</td><td>IMG</td><td>Required, insert image filename if src is present or default invalid image text</td></tr>
-<tbody>
+<tr><td rowspan="3">bgcolor</td><td>TABLE</td><td>Equivalent style 'background-color' (IE tested)</td></tr>
-<tr><th colspan="3">Transform, target milestone 1.4</th></tr>
+    <tr><td>TR</td><td>Equivalent style 'background-color' (IE tested)</td></tr>
-<tr><td rowspan="5">align</td><td>CAPTION</td><td>Near-equiv style 'caption-side', drop left and right</td></tr>
+    <tr><td>TD, TH</td><td>Equivalent style 'background-color'</td></tr>
-    <tr><td>IMG</td><td rowspan="2">Margin-left and margin-right = auto or parent div</td></tr>
+<tr><td>border</td><td>IMG</td><td>Equivalent style 'border-width', only applies when link present</td></tr>
-    <tr><td>TABLE</td></tr>
+<tr><td>clear</td><td>BR</td><td>Near-equiv style 'clear', transform 'all' into 'both'</td></tr>
-    <tr><td>HR</td><td>Near-equivalent style 'text-align' (Works for IE and Opera, but not Firefox). Also try <code>margin-right:auto; margin-left:0;</code> for left or <code>margin-right:0; margin-left:auto;</code> for right (optionally replacing 0 with the original margin for that side)</td></tr>
+<tr class="impl-no"><td>compact</td><td>DL, OL, UL</td><td>Boolean, needs custom CSS class; rarely used anyway</td></tr>
-    <tr class="impl-yes"><td>H1, H2, H3, H4, H5, H6, P</td><td>Equivalent style 'text-align'</td></tr>
+<tr class="required impl-yes"><td>dir</td><td>BDO</td><td>Required, insert ltr (or configuration value) if none</td></tr>
-<tr class="required impl-yes"><td>alt</td><td>IMG</td><td>Required, insert image filename if src is present or default invalid image text</td></tr>
+<tr><td>height</td><td>TD, TH</td><td>Near-equiv style 'height', needs px suffix if original was in pixels</td></tr>
-<tr><td rowspan="3">bgcolor</td><td>TABLE</td><td>Equivalent style 'background-color'</td></tr>
+<tr><td>hspace</td><td>IMG</td><td>Near-equiv styles 'margin-top' and 'margin-bottom', needs px suffix</td></tr>
-    <tr><td>TR</td><td>Equivalent style 'background-color'</td></tr>
+<tr class="impl-yes"><td>lang</td><td>*</td><td>Copy value to xml:lang</td></tr>
-    <tr><td>TD, TH</td><td>Equivalent style 'background-color'</td></tr>
+<tr><td rowspan="2">name</td><td>IMG</td><td>Turn into ID</td></tr>
-<tr><td>border</td><td>IMG</td><td>Near equivalent style 'border-width', as it only applies when link present</td></tr>
+    <tr><td>A</td><td>Turn into ID? (not deprecated, though in which specs?)</td></tr>
-<tr><td>clear</td><td>BR</td><td>Near-equiv style 'clear', transform 'all' into 'both'</td></tr>
+<tr><td>noshade</td><td>HR</td><td>Boolean, style 'border-style:solid;'</td></tr>
-<tr class="impl-no"><td>compact</td><td>DL, OL, UL</td><td>Boolean, needs custom CSS class; rarely used anyway</td></tr>
+<tr><td>nowrap</td><td>TD, TH</td><td>Boolean, style 'white-space:nowrap;' (not compat with IE5)</td></tr>
-<tr class="required impl-yes"><td>dir</td><td>BDO</td><td>Required, insert ltr (or configuration value) if none</td></tr>
+<tr><td>size</td><td>HR</td><td>Near-equiv 'width', needs px suffix if original was pixels</td></tr>
-<tr><td>height</td><td>TD, TH</td><td>Near-equiv style 'height', needs px suffix if original was in pixels</td></tr>
+<tr class="required impl-yes"><td>src</td><td>IMG</td><td>Required, insert blank or default img if not set</td></tr>
-<tr><td>hspace</td><td>IMG</td><td>Near-equiv styles 'margin-top' and 'margin-bottom', needs px suffix</td></tr>
+<tr><td>start</td><td>OL</td><td>Poorly supported 'counter-reset', transform may not be desirable</td></tr>
-<tr class="impl-yes"><td>lang</td><td>*</td><td>Copy value to xml:lang</td></tr>
+<tr><td rowspan="3">type</td><td>LI</td><td rowspan="3">Equivalent style 'list-style-type', different allowed values though. (needs testing)</td></tr>
-<tr><td rowspan="2">name</td><td>IMG</td><td>Turn into ID</td></tr>
+    <tr><td>OL</td></tr>
-    <tr><td>A</td><td>Turn into ID? (not deprecated, though in which specs?)</td></tr>
+    <tr><td>UL</td></tr>
-<tr><td>noshade</td><td>HR</td><td>Boolean, style 'border-style:solid;'</td></tr>
+<tr><td>value</td><td>LI</td><td>Poorly supported 'counter-reset', transform may not be desirable, see ol.start. Configurable.</td></tr>
-<tr><td>nowrap</td><td>TD, TH</td><td>Boolean, style 'white-space:nowrap;' (not compat with IE5)</td></tr>
+<tr><td>vspace</td><td>IMG</td><td>Near-equiv styles 'margin-left' and 'margin-right', needs px suffix, see hspace</td></tr>
-<tr><td>size</td><td>HR</td><td>Near-equiv 'width', needs px suffix if original was pixels</td></tr>
+<tr><td rowspan="2">width</td><td>HR</td><td rowspan="2">Near-equiv style 'width', needs px suffix if original was pixels</td></tr>
-<tr class="required impl-yes"><td>src</td><td>IMG</td><td>Required, insert blank or default img if not set</td></tr>
+    <tr><td>TD, TH</td></tr>
-<tr class="impl-yes"><td>start</td><td>OL</td><td>Poorly supported 'counter-reset', allowed in loose, dropped in strict</td></tr>
+</tbody>
-<tr><td rowspan="3">type</td><td>LI</td><td rowspan="3">Equivalent style 'list-style-type', different allowed values though. (needs testing)</td></tr>
+
-    <tr><td>OL</td></tr>
+</table>
-    <tr><td>UL</td></tr>
+
-<tr class="impl-yes"><td>value</td><td>LI</td><td>Poorly supported 'counter-reset', allowed in loose, dropped in strict</td></tr>
-<tr><td>vspace</td><td>IMG</td><td>Near-equiv styles 'margin-left' and 'margin-right', needs px suffix, see hspace</td></tr>
-<tr><td rowspan="2">width</td><td>HR</td><td rowspan="2">Near-equiv style 'width', needs px suffix if original was pixels</td></tr>
-    <tr><td>TD, TH</td></tr>
-</tbody>
-
-</table>
-
-<div id="version">$Id$</div>
-
 </body></html>

docs/proposal-colors.html

@@ -1,48 +0,0 @@
-<?xml version="1.0" encoding="UTF-8"?>
-<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN"
-    "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">
-<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en"><head>
-<meta http-equiv="Content-Type" content="text/html; charset=UTF-8" />
-<meta name="description" content="Proposal to allow for color constraints in HTML Purifier." />
-<link rel="stylesheet" type="text/css" href="./style.css" />
-
-<title>Proposal: Colors - HTML Purifier</title>
-
-</head><body>
-
-<h1 class="subtitled">Colors</h1>
-<div class="subtitle">Hammering some sense into those color-blind newbies</div>
-
-<div id="filing">Filed under Proposals</div>
-<div id="index">Return to the <a href="index.html">index</a>.</div>
-<div id="home"><a href="http://hp.jpsband.org/">HTML Purifier</a> End-User Documentation</div>
-
-<p>Your website probably has a color-scheme.
-<span style="color:#090; background:#FFF;">Green on white</span>,
-<span style="color:#A0F; background:#FF0;">purple on yellow</span>,
-whatever. When you give users the ability to style their content, you may
-want them to keep in line with your styling. If you're website is all
-about light colors, you don't want a user to come in and vandalize your
-page with a deep maroon.</p>
-
-<p>This is an extremely silly feature proposal, but I'm writing it down anyway.</p>
-
-<p>What if the user could constrain the colors specified in inline styles? You
-are only allowed to use these shades of dark green for text and these shades
-of light yellow for the background. At the very least, you could ensure
-that we did not have pale yellow on white text.</p>
-
-<h2>Implementation issues</h2>
-
-<ol>
-<li>Requires the color attribute definition to know, currently, what the text
-and background colors are. This becomes difficult when classes are thrown
-into the mix.</li>
-<li>The user still has to define the permissible colors, how does one do
-something like that?</li>
-</ol>
-
-<div id="version">$Id$</div>
-
-</body>
-</html>

docs/proposal-language.txt

@@ -1,98 +0,0 @@
-We are going to model our I18N/L10N off of MediaWiki's system.  Their's is
-obviously quite complicated, so we're going to simplify it a bit for our needs.
-
-== Structure ==
-
-First, you have a Language object.  This object contains all the localisable
-message strings, as well as other important language-specific settings and
-custom behavior (uppercasing, lowercasing, printing dates, formatting
-numbers, etc.)
-
-The object is constructed from two sources: subclassed versions of itself
-(classes) and Message files (messages).
-
-== General use ==
-
-You load a language object by calling the Language::factory() function. 
-This function the class file for the object (taking in account fallback 
-languages by using the fallback langauge's object but overloading the 
-language key) and returns that object. Nothing else happens.
-
-When a message/etc is requested, a lazy load initializor is called.  Now the
-real work starts.  We're first going to take the scenario that the language
-is not cached.  The system loads the Messages file by:
-
-    require( $filename );
-    $cache = compact( self::$mLocalisationKeys );	
-
-...where self::$mLocalisationKeys is the name of variables that could be used
-in the localization file. This lets you use things like:
-
-    $fallback = false;
-    $rtl = false;
-
-...and easily siphon them into arrays.
-
-Then, we load the $fallback language (if not set, English) to fill in the gaps in
-the messages.  There is specialized behavior for certain keys, as they can be
-mergeable maps, lists or alias lists (not sure what the last one is).
-
-== Caching ==
-
-MediaWiki has lots of caching mechanisms built in, which make the code somewhat
-more difficult to understand.  Before doing any loading, MediaWiki will check
-the following places to see if we can be lazy:
-
-1. $mLocalisationCache[$code] -  just a variable where it may have been stashed
-2. serialized/$code.ser -  compiled serialized language file
-3. Memcached version of file (with expiration checking)
-
-Expiration checking consists of by ensuring all dependencies have filemtime
-that match the ones bundled with the cached copy. Similar checking could be
-implemented for serialized versions, as it seems that they are not updated
-until manually recompiled.
-
-== Behavior ==
-
-Things that are localizable:
-
--  Weekdays (and abbrev)
--  Months (and abbrev)
--  Bookstores
--  Skin names
--  Date preferences / Custom date format
--  Default date format
--  Default user option overrides
--+ Language names
--  Timezones
--+ Character encoding conversion via iconv
--  UpperLowerCase first (needs casemaps for some)
--  UpperLowerCase
--  Uppercase words
--  Uppercase word breaks
--  Case folding
--  Strip punctuation for MySQL search
--  Get first character
--+ Alternate encoding
--+ Recoding for edit (and then recode input)
--+ RTL
--+ Direction mark character depending on RTL
--? Arrow depending on RTL
--  Languages where italics cannot be used
--+ Number formatting (commafy, transform digits, transform separators)
--  Truncate (multibyte)
--  Grammar conversions for inflected languages
--  Plural transformations
--  Formatting expiry times
--  Segmenting for diffs (Chinese)
--  Convert to variants of language
--  Language specific user preference options
--  Link trails [[foo]]bar
--+ Language code (RFC 3066)
-
-Neat functionality:
-
--  I18N sprintfDate
--  Roman numeral formatting
-
-Items marked with a + likely need to be addressed by HTML Purifier

docs/proposal-new-directives.txt

@@ -1,44 +0,0 @@
-
-Configuration Ideas
-
-Here are some theoretical configuration ideas that we could implement some
-time.  Note the naming convention: %Namespace.Directive
-
-%Attr.RewriteFragments - if there's %Attr.IDPrefix we may want to transparently
-    rewrite the URLs we parse too.  However, we can only do it when it's a pure
-    anchor link, so it's not foolproof
-
-%Attr.ClassBlacklist,
-%Attr.ClassWhitelist,
-%Attr.ClassPolicy - determines what classes are allowed. When
-    %Attr.ClassPolicy is set to Blacklist, only allow those not in
-    %Attr.ClassBlacklist. When it's Whitelist, only allow those in
-    %Attr.ClassWhitelist.
-
-%Attr.MaxWidth, 
-%Attr.MaxHeight - caps for width and height related checks.
-    (the hack in Pixels for an image crashing attack could be replaced by this)
-
-%URI.AddRelNofollow - will add rel="nofollow" to all links, preventing the
-    spread of ill-gotten pagerank
-
-%URI.RelativeToAbsolute - transforms all relative URIs to absolute form
-
-%URI.HostBlacklistRegex - regexes that if matching the host are disallowed
-%URI.HostWhitelist - domain names that are excluded from the host blacklist
-%URI.HostPolicy - determines whether or not its reject all and then whitelist
-    or allow all in then do specific blacklists with whitelist intervening.
-    'DenyAll' or 'AllowAll' (default)
-
-%URI.DisableIPHosts - URIs that have IP addresses for hosts are disallowed.
-    Be sure to also grab unusual encodings (dword, hex and octal), which may
-    be currently be caught by regular DNS
-%URI.DisableIDN - Disallow raw internationalized domain names. Punycode
-    will still be permitted.
-
-%URI.ConvertUnusualIPHosts - transform dword/hex/octal IP addresses to the
-    regular form
-%URI.ConvertAbsoluteDNS - Remove extra dots after host names that trigger
-    absolute DNS.  While this is actually the preferred method according to
-    the RFC, most people opt to use a relative domain name relative to . (root).
-

docs/ref-loose-vs-strict.txt

@@ -1,37 +0,0 @@
-
-Loose versus Strict
-    Changes from one doctype to another
-
-There are changes.  Wow, how insightful.  Not everything changed is relevant
-to HTML Purifier, though, so let's take a look:
-
-== Major incompatibilities ==
-
-[done] BLOCKQUOTE changes from 'flow' to 'block'
-    current behavior: inline inner contents should not be nuked, block-ify as necessary
-[partially-done] U, S, STRIKE cut
-    current behavior: removed completely
-    projected behavior: replace with appropriate inline span + CSS
-[done] ADDRESS from potpourri to Inline (removes p tags)
-    current behavior: block tags silently dropped
-    ideal behavior: replace tags with something like <br>. (not high priority)
-
-== Things we can loosen up ==
-
-Tags DIR, MENU, CENTER, ISINDEX, FONT, BASEFONT? allowed in loose
-    current behavior: transform to strict-valid forms
-Attributes allowed in loose (see attribute transforms in 'dev-progress.html')
-    current behavior: projected to transform into strict-valid forms
-
-== Periphery issues ==
-
-A tag's attribute 'target' (for selecting frames) cut
-    current behavior: not allowed at all
-    projected behavior: use loose doctype if needed, needs valid values
-[done] OL/LI tag's attribute 'start'/'value' (for renumbering lists) cut
-    current behavior: no substitute, just delete when in strict, allow in loose
-Attribute 'name' deprecated in favor of 'id'
-    current behavior: dropped silently
-    projected behavior: create proper AttrTransform (currently not allowed at all)
-[done] PRE tag allows SUB/SUP? (strict dtd comment vs syntax, loose disallows)
-    current behavior: disallow as usual

docs/ref-proprietary-tags.txt

@@ -1,22 +0,0 @@
-
-Proprietary Tags
-    <nobr> and friends
-
-Here are some proprietary tags that W3C does not define but occasionally show
-up in the wild.  We have only included tags that would make sense in an
-HTML Purifier context.
-
-<align>, block element that aligns (extremely rare)
-<blackface>, inline that double-bolds text (extremely rare)
-<comment>, hidden comment for IE and WebTV
-<multicol cols=number gutter=pixels width=pixels>, multiple columns
-<nobr>, no linebreaks
-<spacer align=* type="vertical|horizontal|block">, whitespace in doc,
-    use width/height for block and size for vertical/horizontal (attributes)
-    (extremely rare)
-<wbr>, potential word break point: allows linebreaks. Only works in <nobr>
-
-<listing>, monospace pre-variant (extremely rare)
-<plaintext>, escapes all tags to the end of document
-<ruby> and friends, (more research needed, appears to be XHTML 1.1 markup)
-<xmp>, monospace, replace with pre

docs/ref-whatwg.txt

@@ -1,9 +0,0 @@
-
-Web Hypertext Application Technology Working Group
-    WHATWG
-
-I don't think we need to worry about them.  Untrusted users shouldn't be
-submitting applications, eh?  But if some interesting attribute pops up in
-their spec, and might be worth supporting, stick it here.
-
-(none so far, as you can see)

docs/ref-xhtml-1.1.txt

@@ -1,21 +0,0 @@
-
-Getting XHTML 1.1 Working
-
-It's quite simple, according to <http://www.w3.org/TR/xhtml11/changes.html>
-
-1. Scratch lang entirely in favor of xml:lang
-2. Scratch name entirely in favor of id (partially-done)
-3. Support Ruby <http://www.w3.org/TR/2001/REC-ruby-20010531/>
-
-...but that's only an informative section. More things to do:
-
-1. Scratch style attribute (it's deprecated)
-2. Be module-aware (this might entail intelligent grouping in the definition
-   and allowing users to specifically remove certain modules (see 5))
-3. Cross-reference minimal content models with existing DTDs and determine
-   changes (todo)
-4. Watch out for the Legacy Module
-<http://www.w3.org/TR/2001/REC-xhtml-modularization-20010410/abstract_modules.html#s_legacymodule>
-5. Let users specify their own custom modules
-6. Study Modularization document
-<http://www.w3.org/TR/2001/REC-xhtml-modularization-20010410/>

docs/security.txt

@@ -7,7 +7,6 @@ and it's up to you to provide it the proper information and proper context
 to be effective. Things to remember:
 
 1. Character Encoding: UTF-8.
-    This segment will soon be obsoleted by enduser-utf8.html
 Currently, the parser runs under the assumption that it is dealing
 with UTF-8. Not ISO-8859-1 or Windows-1252, UTF-8. And definitely not "no
 character encoding explicitly stated" or UTF-7. If you're not using UTF-8 as
@@ -28,7 +27,6 @@ this may be configurable in the future.  Do you want standards compliance?
 The doctype is a good place to start.
 
 3. IDs
-    This segment is obsoleted by enduser-id.html
 They need to be unique, but without some knowledge of the
 rest of the document, it's difficult to know what's unique. %Attr.IDBlacklist
 needs to be set: we may want to consider disallowing IDs by default to

docs/strictness.txt

@@ -2,8 +2,8 @@
 Is HTML Purifier Strict or Transitional?
     A little bit of helpful guidance
 
-Despite the fact that HTML Purifier professes to support both transitional and
+Despite the fact that HTML Purifier professes only to support transitional
-strict HTML, it rejects a lot of attributes and elements that are actually, indeed,
+HTML, it rejects a lot of attributes and elements that are actually, indeed,
 valid. You can investigate progress.html to find out precisely what we
 are doing to these *deprecated* attributes.
 
@@ -11,8 +11,8 @@ However, users have found that Strict HTML imposes some quite unreasonable
 restrictions on certain things. The start and value attributes in ol and
 li (respectively) perhaps are the most contested. There's is currently no
 widely supported browser method short of JavaScript that can replace these
-two deprecated elements. It behooves us to allow these deprecated
+two deprecated elements. HTML Purifier does not currently support them, but
-attributes when the output is transitional.
+it might behoove us to do so while our output is still transitional.
 
 Fortunantely, that's the only real bugger case. The others have near-perfect
 CSS equivalents, and were presentational anyway. However, the other question
@@ -22,16 +22,4 @@ whole point about CSS is to seperate styling from content, so inline styling
 doesn't solve that problem.
 
 It's an icky question, and we'll have to deal with it as more and more 
-transforms get implemented.  As of right now, however, we currently support
+transforms get implemented.
-these loose-only constructs in loose mode:
-
-- <ul start="1">, <li value="1"> attributes
-- <u>, <strike>, <s> tags
-- flow children in <blockquote>
-- mixed children in <address>
-
-The changed child definitions as well as the ul.start li.value are the most
-compelling reasons why loose should be used.  We may want offer disabling <u>,
-<strike> and <s> by themselves. We may also want to offer no pre-emptive
-deprecated conversions. This all must be unified.
-

docs/style.css

@@ -1,44 +0,0 @@
-html {font-size:1em; font-family:serif; }
-body {margin-left:4em; margin-right:4em; }
-
-dt {font-weight:bold; }
-pre {margin-left:2em; }
-pre, code, tt {font-family:monospace; font-size:1em; }
-
-h1 {text-align:center; font-family:Garamond, serif;
-  font-variant:small-caps;}
-h2 {border-bottom:1px solid #CCC; font-family:sans-serif; font-weight:normal;
-    font-size:1.3em;}
-h3 {font-family:sans-serif; font-size:1.1em; font-weight:bold; }
-h4 {font-family:sans-serif; font-size:0.9em; font-weight:bold; }
-
-/* For witty quips */
-.subtitled {margin-bottom:0em;}
-.subtitle , .subsubtitle {font-size:.8em; margin-bottom:1em;
-    font-style:italic; margin-top:-.2em;text-align:center;}
-.subsubtitle {text-align:left;margin-left:2em;}
-
-/* Used for special "See also" links. */
-.reference {font-style:italic;margin-left:2em;}
-
-/* Marks off asides, discussions on why something is the way it is */
-.aside {margin-left:2em; font-family:sans-serif; font-size:0.9em; }
-blockquote .label {font-weight:bold; font-size:1em; margin:0 0 .1em;
-    border-bottom:1px solid #CCC;}
-
-/* A regular table */
-.table {border-collapse:collapse; border-bottom:2px solid #888; margin-left:2em; }
-.table thead th {margin:0; background:#888; color:#FFF; }
-.table thead th:first-child {-moz-border-radius-topleft:1em;}
-.table tbody td {border-bottom:1px solid #CCC; padding-right:0.6em;padding-left:0.6em;}
-
-/* Category of the file */
-#filing {font-weight:bold; font-size:smaller; }
-
-/* Contains, without exception, Return to index. */
-#index {font-size:smaller; }
-
-#home {font-size:smaller;}
-
-/* Contains, without exception, $Id$, for SVN version info. */
-#version {text-align:right; font-style:italic; margin:2em 0;}

library/HTMLPurifier.func.php

@@ -1,21 +0,0 @@
-<?php
-
-/**
- * Function wrapper for HTML Purifier for quick use.
- * @note This function only includes the library when it is called. While
- *       this is efficient for instances when you only use HTML Purifier
- *       on a few of your pages, it murders bytecode caching. You still
- *       need to add HTML Purifier to your path.
- * @note ''HTMLPurifier()'' is NOT the same as ''new HTMLPurifier()''
- */
-
-function HTMLPurifier($html, $config = null) {
-    static $purifier = false;
-    if (!$purifier) {
-        require_once 'HTMLPurifier.php';
-        $purifier = new HTMLPurifier();
-    }
-    return $purifier->purify($html, $config);
-}
-
-?>

library/HTMLPurifier.php

@@ -22,7 +22,7 @@
  */
 
 /*
-    HTML Purifier 1.4.1 - Standards Compliant HTML Filtering
+    HTML Purifier - Standards Compliant HTML Filtering
     Copyright (C) 2006 Edward Z. Yang
 
     This library is free software; you can redistribute it and/or
@@ -44,7 +44,6 @@
 // they get included
 require_once 'HTMLPurifier/ConfigSchema.php';
 require_once 'HTMLPurifier/Config.php';
-require_once 'HTMLPurifier/Context.php';
 
 require_once 'HTMLPurifier/Lexer.php';
 require_once 'HTMLPurifier/Generator.php';
@@ -64,107 +63,51 @@ require_once 'HTMLPurifier/Encoder.php';
 class HTMLPurifier
 {
     
-    var $version = '1.4.1';
-    
     var $config;
-    var $filters;
     
     var $lexer, $strategy, $generator;
     
-    /**
-     * Final HTMLPurifier_Context of last run purification. Might be an array.
-     * @public
-     */
-    var $context;
-    
     /**
      * Initializes the purifier.
      * @param $config Optional HTMLPurifier_Config object for all instances of
      *                the purifier, if omitted, a default configuration is
      *                supplied (which can be overridden on a per-use basis).
-     *                The parameter can also be any type that
-     *                HTMLPurifier_Config::create() supports.
      */
     function HTMLPurifier($config = null) {
         
-        $this->config = HTMLPurifier_Config::create($config);
+        $this->config = $config ? $config : HTMLPurifier_Config::createDefault();
         
         $this->lexer        = HTMLPurifier_Lexer::create();
         $this->strategy     = new HTMLPurifier_Strategy_Core();
         $this->generator    = new HTMLPurifier_Generator();
+        $this->encoder      = new HTMLPurifier_Encoder();
         
     }
     
-    /**
-     * Adds a filter to process the output. First come first serve
-     * @param $filter HTMLPurifier_Filter object
-     */
-    function addFilter($filter) {
-        $this->filters[] = $filter;
-    }
-    
     /**
      * Filters an HTML snippet/document to be XSS-free and standards-compliant.
      * 
      * @param $html String of HTML to purify
      * @param $config HTMLPurifier_Config object for this operation, if omitted,
      *                defaults to the config object specified during this
-     *                object's construction. The parameter can also be any type
+     *                object's construction.
-     *                that HTMLPurifier_Config::create() supports.
      * @return Purified HTML
      */
     function purify($html, $config = null) {
-        
+        $config = $config ? $config : $this->config;
-        $config = $config ? HTMLPurifier_Config::create($config) : $this->config;
+        $html = $this->encoder->convertToUTF8($html, $config);
-        
-        $context = new HTMLPurifier_Context();
-        $html = HTMLPurifier_Encoder::convertToUTF8($html, $config, $context);
-        
-        for ($i = 0, $size = count($this->filters); $i < $size; $i++) {
-            $html = $this->filters[$i]->preFilter($html, $config, $context);
-        }
-        
-        // purified HTML
         $html = 
             $this->generator->generateFromTokens(
-                // list of tokens
                 $this->strategy->execute(
-                    // list of un-purified tokens
+                    $this->lexer->tokenizeHTML($html, $config),
-                    $this->lexer->tokenizeHTML(
+                    $config
-                        // un-purified HTML
-                        $html, $config, $context
-                    ),
-                    $config, $context
                 ),
-                $config, $context
+                $config
             );
-        
+        $html = $this->encoder->convertFromUTF8($html, $config);
-        for ($i = $size - 1; $i >= 0; $i--) {
-            $html = $this->filters[$i]->postFilter($html, $config, $context);
-        }
-        
-        $html = HTMLPurifier_Encoder::convertFromUTF8($html, $config, $context);
-        $this->context =& $context;
         return $html;
     }
     
-    /**
-     * Filters an array of HTML snippets
-     * @param $config Optional HTMLPurifier_Config object for this operation.
-     *                See HTMLPurifier::purify() for more details.
-     * @return Array of purified HTML
-     */
-    function purifyArray($array_of_html, $config = null) {
-        $context_array = array();
-        foreach ($array_of_html as $key => $html) {
-            $array_of_html[$key] = $this->purify($html, $config);
-            $context_array[$key] = $this->context;
-        }
-        $this->context = $context_array;
-        return $array_of_html;
-    }
-    
-    
 }
 
 ?>

library/HTMLPurifier/AttrContext.php

@@ -0,0 +1,26 @@
+<?php
+
+/**
+ * Internal data-structure used in attribute validation to accumulate state.
+ * 
+ * This is a data-structure that holds objects that accumulate state, like
+ * HTMLPurifier_IDAccumulator. It's better than using globals!
+ * 
+ * @note Many functions that accept this object have it as a mandatory
+ *       parameter, even when there is no use for it.  Though this is
+ *       for the same reasons as why HTMLPurifier_Config is a mandatory
+ *       parameter, it is also because you cannot assign a default value
+ *       to a parameter passed by reference (passing by reference is essential
+ *       for context to work in PHP 4).
+ */
+
+class HTMLPurifier_AttrContext
+{
+    /**
+     * Contains an HTMLPurifier_IDAccumulator, which keeps track of used IDs.
+     * @public
+     */
+    var $id_accumulator;
+}
+
+?>

library/HTMLPurifier/AttrDef.php

@@ -1,5 +1,7 @@
 <?php
 
+require_once 'HTMLPurifier/AttrContext.php';
+
 /**
  * Base class for all validating attribute definitions.
  * 
@@ -20,7 +22,10 @@ class HTMLPurifier_AttrDef
     var $minimized = false;
     
     /**
-     * Validates and cleans passed string according to a definition.
+     * Abstract function defined for functions that validate and clean strings.
+     * 
+     * This function forms the basis for all the subclasses: they must
+     * define this method.
      * 
      * @public
      * @param $string String to be validated and cleaned.

library/HTMLPurifier/AttrDef/Background.php

@@ -1,87 +0,0 @@
-<?php
-
-require_once 'HTMLPurifier/AttrDef.php';
-require_once 'HTMLPurifier/CSSDefinition.php';
-
-/**
- * Validates shorthand CSS property background.
- * @warning Does not support url tokens that have internal spaces.
- */
-class HTMLPurifier_AttrDef_Background extends HTMLPurifier_AttrDef
-{
-    
-    /**
-     * Local copy of component validators.
-     * @note See HTMLPurifier_AttrDef_Font::$info for a similar impl.
-     */
-    var $info;
-    
-    function HTMLPurifier_AttrDef_Background($config) {
-        $def = $config->getCSSDefinition();
-        $this->info['background-color'] = $def->info['background-color'];
-        $this->info['background-image'] = $def->info['background-image'];
-        $this->info['background-repeat'] = $def->info['background-repeat'];
-        $this->info['background-attachment'] = $def->info['background-attachment'];
-        $this->info['background-position'] = $def->info['background-position'];
-    }
-    
-    function validate($string, $config, &$context) {
-        
-        // regular pre-processing
-        $string = $this->parseCDATA($string);
-        if ($string === '') return false;
-        
-        // assumes URI doesn't have spaces in it
-        $bits = explode(' ', strtolower($string)); // bits to process
-        
-        $caught = array();
-        $caught['color']    = false;
-        $caught['image']    = false;
-        $caught['repeat']   = false;
-        $caught['attachment'] = false;
-        $caught['position'] = false;
-        
-        $i = 0; // number of catches
-        $none = false;
-        
-        foreach ($bits as $bit) {
-            if ($bit === '') continue;
-            foreach ($caught as $key => $status) {
-                if ($key != 'position') {
-                    if ($status !== false) continue;
-                    $r = $this->info['background-' . $key]->validate($bit, $config, $context);
-                } else {
-                    $r = $bit;
-                }
-                if ($r === false) continue;
-                if ($key == 'position') {
-                    if ($caught[$key] === false) $caught[$key] = '';
-                    $caught[$key] .= $r . ' ';
-                } else {
-                    $caught[$key] = $r;
-                }
-                $i++;
-                break;
-            }
-        }
-        
-        if (!$i) return false;
-        if ($caught['position'] !== false) {
-            $caught['position'] = $this->info['background-position']->
-                validate($caught['position'], $config, $context);
-        }
-        
-        $ret = array();
-        foreach ($caught as $value) {
-            if ($value === false) continue;
-            $ret[] = $value;
-        }
-        
-        if (empty($ret)) return false;
-        return implode(' ', $ret);
-        
-    }
-    
-}
-
-?>

library/HTMLPurifier/AttrDef/BackgroundPosition.php

@@ -1,130 +0,0 @@
-<?php
-
-require_once 'HTMLPurifier/AttrDef.php';
-require_once 'HTMLPurifier/AttrDef/CSSLength.php';
-require_once 'HTMLPurifier/AttrDef/Percentage.php';
-
-/* W3C says:
-    [ // adjective and number must be in correct order, even if
-      // you could switch them without introducing ambiguity.
-      // some browsers support that syntax
-        [
-            <percentage> | <length> | left | center | right
-        ]
-        [ 
-            <percentage> | <length> | top | center | bottom
-        ]?
-    ] |
-    [ // this signifies that the vertical and horizontal adjectives
-      // can be arbitrarily ordered, however, there can only be two,
-      // one of each, or none at all
-        [
-            left | center | right
-        ] ||
-        [
-            top | center | bottom
-        ]
-    ]
-    top, left = 0%
-    center, (none) = 50%
-    bottom, right = 100%
-*/
-
-/* QuirksMode says:
-    keyword + length/percentage must be ordered correctly, as per W3C
-    
-    Internet Explorer and Opera, however, support arbitrary ordering. We
-    should fix it up.
-    
-    Minor issue though, not strictly necessary.
-*/
-
-// control freaks may appreciate the ability to convert these to
-// percentages or something, but it's not necessary
-
-/**
- * Validates the value of background-position.
- */
-class HTMLPurifier_AttrDef_BackgroundPosition extends HTMLPurifier_AttrDef
-{
-    
-    var $length;
-    var $percentage;
-    
-    function HTMLPurifier_AttrDef_BackgroundPosition() {
-        $this->length     = new HTMLPurifier_AttrDef_CSSLength();
-        $this->percentage = new HTMLPurifier_AttrDef_Percentage();
-    }
-    
-    function validate($string, $config, &$context) {
-        $string = $this->parseCDATA($string);
-        $bits = explode(' ', $string);
-        
-        $keywords = array();
-        $keywords['h'] = false; // left, right
-        $keywords['v'] = false; // top, bottom
-        $keywords['c'] = false; // center
-        $measures = array();
-        
-        $i = 0;
-        
-        $lookup = array(
-            'top' => 'v',
-            'bottom' => 'v',
-            'left' => 'h',
-            'right' => 'h',
-            'center' => 'c'
-        );
-        
-        foreach ($bits as $bit) {
-            if ($bit === '') continue;
-            
-            // test for keyword
-            $lbit = ctype_lower($bit) ? $bit : strtolower($bit);
-            if (isset($lookup[$lbit])) {
-                $status = $lookup[$lbit];
-                $keywords[$status] = $lbit;
-                $i++;
-            }
-            
-            // test for length
-            $r = $this->length->validate($bit, $config, $context);
-            if ($r !== false) {
-                $measures[] = $r;
-                $i++;
-            }
-            
-            // test for percentage
-            $r = $this->percentage->validate($bit, $config, $context);
-            if ($r !== false) {
-                $measures[] = $r;
-                $i++;
-            }
-            
-        }
-        
-        if (!$i) return false; // no valid values were caught
-        
-        
-        $ret = array();
-        
-        // first keyword
-        if     ($keywords['h'])     $ret[] = $keywords['h'];
-        elseif (count($measures))   $ret[] = array_shift($measures);
-        elseif ($keywords['c']) {
-            $ret[] = $keywords['c'];
-            $keywords['c'] = false; // prevent re-use: center = center center
-        }
-        
-        if     ($keywords['v'])     $ret[] = $keywords['v'];
-        elseif (count($measures))   $ret[] = array_shift($measures);
-        elseif ($keywords['c'])     $ret[] = $keywords['c'];
-        
-        if (empty($ret)) return false;
-        return implode(' ', $ret);
-        
-    }
-    
-}
-
-?>

library/HTMLPurifier/AttrDef/CSS.php

@@ -8,11 +8,6 @@ require_once 'HTMLPurifier/CSSDefinition.php';
  * @note We don't implement the whole CSS specification, so it might be
  *       difficult to reuse this component in the context of validating
  *       actual stylesheet declarations.
- * @note If we were really serious about validating the CSS, we would
- *       tokenize the styles and then parse the tokens. Obviously, we
- *       are not doing that. Doing that could seriously harm performance,
- *       but would make these components a lot more viable for a CSS
- *       filtering solution.
  */
 class HTMLPurifier_AttrDef_CSS extends HTMLPurifier_AttrDef
 {
@@ -25,9 +20,6 @@ class HTMLPurifier_AttrDef_CSS extends HTMLPurifier_AttrDef
         
         // we're going to break the spec and explode by semicolons.
         // This is because semicolon rarely appears in escaped form
-        // Doing this is generally flaky but fast
-        // IT MIGHT APPEAR IN URIs, see HTMLPurifier_AttrDef_CSSURI
-        // for details
         
         $declarations = explode(';', $css);
         $propvalues = array();
@@ -51,7 +43,6 @@ class HTMLPurifier_AttrDef_CSS extends HTMLPurifier_AttrDef
             $propvalues[$property] = $result;
         }
         
-        // procedure does not write the new CSS simultaneously, so it's
         // slightly inefficient, but it's the only way of getting rid of
         // duplicates. Perhaps config to optimize it, but not now.
         

library/HTMLPurifier/AttrDef/CSSLength.php

@@ -40,7 +40,6 @@ class HTMLPurifier_AttrDef_CSSLength extends HTMLPurifier_AttrDef
         
         // we assume all units are two characters
         $unit = substr($length, $strlen - 2);
-        if (!ctype_lower($unit)) $unit = strtolower($unit);
         $number = substr($length, 0, $strlen - 2);
         
         if (!isset($this->units[$unit])) return false;

library/HTMLPurifier/AttrDef/CSSURI.php

@@ -1,58 +0,0 @@
-<?php
-
-require_once 'HTMLPurifier/AttrDef/URI.php';
-
-/**
- * Validates a URI in CSS syntax, which uses url('http://example.com')
- * @note While theoretically speaking we a URI in a CSS document could
- *       be non-embedded, as of CSS2 there is no such usage so we're
- *       generalizing it. This may need to be changed in the future.
- * @warning Since HTMLPurifier_AttrDef_CSS blindly uses semicolons as
- *          the separator, you cannot put a literal semicolon in
- *          in the URI. Try percent encoding it, in that case.
- */
-class HTMLPurifier_AttrDef_CSSURI extends HTMLPurifier_AttrDef_URI
-{
-    
-    function HTMLPurifier_AttrDef_CSSURI() {
-        $this->HTMLPurifier_AttrDef_URI(true); // always embedded
-    }
-    
-    function validate($uri_string, $config, &$context) {
-        // parse the URI out of the string and then pass it onto
-        // the parent object
-        
-        $uri_string = $this->parseCDATA($uri_string);
-        if (strpos($uri_string, 'url(') !== 0) return false;
-        $uri_string = substr($uri_string, 4);
-        $new_length = strlen($uri_string) - 1;
-        if ($uri_string[$new_length] != ')') return false;
-        $uri = trim(substr($uri_string, 0, $new_length));
-        
-        if (isset($uri[0]) && ($uri[0] == "'" || $uri[0] == '"')) {
-            $quote = $uri[0];
-            $new_length = strlen($uri) - 1;
-            if ($uri[$new_length] !== $quote) return false;
-            $uri = substr($uri, 1, $new_length - 1);
-        }
-        
-        $keys   = array(  '(',   ')',   ',',   ' ',   '"',   "'");
-        $values = array('\\(', '\\)', '\\,', '\\ ', '\\"', "\\'");
-        $uri = str_replace($values, $keys, $uri);
-        
-        $result = parent::validate($uri, $config, $context);
-        
-        if ($result === false) return false;
-        
-        // escape necessary characters according to CSS spec
-        // except for the comma, none of these should appear in the
-        // URI at all
-        $result = str_replace($keys, $values, $result);
-        
-        return "url($result)";
-        
-    }
-    
-}
-
-?>

library/HTMLPurifier/AttrDef/Class.php

@@ -24,14 +24,13 @@ class HTMLPurifier_AttrDef_Class extends HTMLPurifier_AttrDef
         // and plus it would complicate optimization efforts (you never
         // see that anyway).
         $matches = array();
-        $pattern = '/(?:(?<=\s)|\A)'. // look behind for space or string start
+        $pattern = '/(?:(?<=\s)|\A)'.
                    '((?:--|-?[A-Za-z_])[A-Za-z_\-0-9]*)'.
-                   '(?:(?=\s)|\z)/'; // look ahead for space or string end
+                   '(?:(?=\s)|\z)/';
         preg_match_all($pattern, $string, $matches);
         
         if (empty($matches[1])) return false;
         
-        // reconstruct class string
         $new_string = '';
         foreach ($matches[1] as $class_names) {
             $new_string .= $class_names . ' ';

library/HTMLPurifier/AttrDef/Email.php

@@ -1,17 +0,0 @@
-<?php
-
-require_once 'HTMLPurifier/AttrDef.php';
-
-class HTMLPurifier_AttrDef_Email extends HTMLPurifier_AttrDef
-{
-    
-    /**
-     * Unpacks a mailbox into its display-name and address
-     */
-    function unpack($string) {
-        // needs to be implemented
-    }
-    
-}
-
-?>

library/HTMLPurifier/AttrDef/Email/SimpleCheck.php

@@ -1,23 +0,0 @@
-<?php
-
-require_once 'HTMLPurifier/AttrDef/Email.php';
-
-/**
- * Primitive email validation class based on the regexp found at 
- * http://www.regular-expressions.info/email.html
- */
-class HTMLPurifier_AttrDef_Email_SimpleCheck extends HTMLPurifier_AttrDef_Email
-{
-    
-    function validate($string, $config, &$context) {
-        // no support for named mailboxes i.e. "Bob <bob@example.com>"
-        // that needs more percent encoding to be done
-        if ($string == '') return false;
-        $string = trim($string);
-        $result = preg_match('/^[A-Z0-9._%-]+@[A-Z0-9.-]+\.[A-Z]{2,4}$/i', $string);
-        return $result ? $string : false;
-    }
-    
-}
-
-?>

library/HTMLPurifier/AttrDef/Host.php

@@ -5,7 +5,7 @@ require_once 'HTMLPurifier/AttrDef/IPv4.php';
 require_once 'HTMLPurifier/AttrDef/IPv6.php';
 
 /**
- * Validates a host according to the IPv4, IPv6 and DNS (future) specifications.
+ * Validates a host according to the IPv4, IPv6 and DNS specifications.
  */
 class HTMLPurifier_AttrDef_Host extends HTMLPurifier_AttrDef
 {
@@ -35,8 +35,6 @@ class HTMLPurifier_AttrDef_Host extends HTMLPurifier_AttrDef
             if ($valid === false) return false;
             return '['. $valid . ']';
         }
-        
-        // need to do checks on unusual encodings too
         $ipv4 = $this->ipv4->validate($string, $config, $context);
         if ($ipv4 !== false) return $ipv4;
         

library/HTMLPurifier/AttrDef/ID.php

@@ -3,30 +3,6 @@
 require_once 'HTMLPurifier/AttrDef.php';
 require_once 'HTMLPurifier/IDAccumulator.php';
 
-HTMLPurifier_ConfigSchema::define(
-    'Attr', 'IDPrefix', '', 'string',
-    'String to prefix to IDs.  If you have no idea what IDs your pages '.
-    'may use, you may opt to simply add a prefix to all user-submitted ID '.
-    'attributes so that they are still usable, but will not conflict with '.
-    'core page IDs. Example: setting the directive to \'user_\' will result in '.
-    'a user submitted \'foo\' to become \'user_foo\'  Be sure to set '.
-    '%HTML.EnableAttrID to true before using '.
-    'this.  This directive was available since 1.2.0.'
-);
-
-HTMLPurifier_ConfigSchema::define(
-    'Attr', 'IDPrefixLocal', '', 'string',
-    'Temporary prefix for IDs used in conjunction with %Attr.IDPrefix.  If '.
-    'you need to allow multiple sets of '.
-    'user content on web page, you may need to have a seperate prefix that '.
-    'changes with each iteration.  This way, seperately submitted user content '.
-    'displayed on the same page doesn\'t clobber each other. Ideal values '.
-    'are unique identifiers for the content it represents (i.e. the id of '.
-    'the row in the database). Be sure to add a seperator (like an underscore) '.
-    'at the end.  Warning: this directive will not work unless %Attr.IDPrefix '.
-    'is set to a non-empty value! This directive was available since 1.2.0.'
-);
-
 /**
  * Validates the HTML attribute ID.
  * @warning Even though this is the id processor, it
@@ -44,19 +20,7 @@ class HTMLPurifier_AttrDef_ID extends HTMLPurifier_AttrDef
         $id = trim($id); // trim it first
         
         if ($id === '') return false;
-        
+        if (isset($context->id_accumulator->ids[$id])) return false;
-        $prefix = $config->get('Attr', 'IDPrefix');
-        if ($prefix !== '') {
-            $prefix .= $config->get('Attr', 'IDPrefixLocal');
-            // prevent re-appending the prefix
-            if (strpos($id, $prefix) !== 0) $id = $prefix . $id;
-        } elseif ($config->get('Attr', 'IDPrefixLocal') !== '') {
-            trigger_error('%Attr.IDPrefixLocal cannot be used unless '.
-                '%Attr.IDPrefix is set', E_USER_WARNING);
-        }
-        
-        $id_accumulator =& $context->get('IDAccumulator');
-        if (isset($id_accumulator->ids[$id])) return false;
         
         // we purposely avoid using regex, hopefully this is faster
         
@@ -71,7 +35,7 @@ class HTMLPurifier_AttrDef_ID extends HTMLPurifier_AttrDef
             $result = ($trim === '');
         }
         
-        if ($result) $id_accumulator->add($id);
+        if ($result) $context->id_accumulator->add($id);
         
         // if no change was made to the ID, return the result
         // else, return the new id if stripping whitespace made it

library/HTMLPurifier/AttrDef/Lang.php

@@ -49,7 +49,7 @@ class HTMLPurifier_AttrDef_Lang extends HTMLPurifier_AttrDef
         if ($length == 0 || $length == 1 || $length > 8 || !ctype_alnum($subtags[1])) {
             return $new_string;
         }
-        if (!ctype_lower($subtags[1])) $subtags[1] = strtolower($subtags[1]);
+        if (!ctype_lower($subtags[1])) $subtags[1] = strotolower($subtags[1]);
         
         $new_string .= '-' . $subtags[1];
         if ($num_subtags == 2) return $new_string;
@@ -61,7 +61,7 @@ class HTMLPurifier_AttrDef_Lang extends HTMLPurifier_AttrDef
                 return $new_string;
             }
             if (!ctype_lower($subtags[$i])) {
-                $subtags[$i] = strtolower($subtags[$i]);
+                $subtags[$i] = strotolower($subtags[$i]);
             }
             $new_string .= '-' . $subtags[$i];
         }

library/HTMLPurifier/AttrDef/ListStyle.php

@@ -4,7 +4,8 @@ require_once 'HTMLPurifier/AttrDef.php';
 
 /**
  * Validates shorthand CSS property list-style.
- * @warning Does not support url tokens that have internal spaces.
+ * @note This currently does not support list-style-image, as that functionality
+ *       is not implemented yet elsewhere.
  */
 class HTMLPurifier_AttrDef_ListStyle extends HTMLPurifier_AttrDef
 {
@@ -19,7 +20,6 @@ class HTMLPurifier_AttrDef_ListStyle extends HTMLPurifier_AttrDef
         $def = $config->getCSSDefinition();
         $this->info['list-style-type']     = $def->info['list-style-type'];
         $this->info['list-style-position'] = $def->info['list-style-position'];
-        $this->info['list-style-image'] = $def->info['list-style-image'];
     }
     
     function validate($string, $config, &$context) {
@@ -28,50 +28,48 @@ class HTMLPurifier_AttrDef_ListStyle extends HTMLPurifier_AttrDef
         $string = $this->parseCDATA($string);
         if ($string === '') return false;
         
-        // assumes URI doesn't have spaces in it
         $bits = explode(' ', strtolower($string)); // bits to process
         
-        $caught = array();
+        $caught_type = false;
-        $caught['type']     = false;
+        $caught_position = false;
-        $caught['position'] = false;
+        $caught_none = false; // as in keyword none, which is in all of them
-        $caught['image']    = false;
         
-        $i = 0; // number of catches
+        $ret = '';
-        $none = false;
         
         foreach ($bits as $bit) {
-            if ($i >= 3) return; // optimization bit
+            if ($caught_none && ($caught_type || $caught_position)) break;
+            if ($caught_type && $caught_position) break;
+            
             if ($bit === '') continue;
-            foreach ($caught as $key => $status) {
+            
-                if ($status !== false) continue;
+            if ($bit === 'none') {
-                $r = $this->info['list-style-' . $key]->validate($bit, $config, $context);
+                if ($caught_none) continue;
-                if ($r === false) continue;
+                $caught_none = true;
-                if ($r === 'none') {
+                $ret .= 'none ';
-                    if ($none) continue;
+                continue;
-                    else $none = true;
+            }
-                    if ($key == 'image') continue;
+            
-                }
+            // if we add anymore, roll it into a loop
-                $caught[$key] = $r;
+            
-                $i++;
+            $r = $this->info['list-style-type']->validate($bit, $config, $context);
-                break;
+            if ($r !== false) {
+                if ($caught_type) continue;
+                $caught_type = true;
+                $ret .= $r . ' ';
+                continue;
+            }
+            
+            $r = $this->info['list-style-position']->validate($bit, $config, $context);
+            if ($r !== false) {
+                if ($caught_position) continue;
+                $caught_position = true;
+                $ret .= $r . ' ';
+                continue;
             }
         }
         
-        if (!$i) return false;
+        $ret = rtrim($ret);
-        
+        return $ret ? $ret : false;
-        $ret = array();
-        
-        // construct type
-        if ($caught['type']) $ret[] = $caught['type'];
-        
-        // construct image
-        if ($caught['image']) $ret[] = $caught['image'];
-        
-        // construct position
-        if ($caught['position']) $ret[] = $caught['position'];
-        
-        if (empty($ret)) return false;
-        return implode(' ', $ret);
         
     }
     

library/HTMLPurifier/AttrDef/Percentage.php

@@ -4,13 +4,14 @@ require_once 'HTMLPurifier/AttrDef.php';
 require_once 'HTMLPurifier/AttrDef/Number.php';
 
 /**
- * Validates a Percentage as defined by the CSS spec.
+ * Validates a Percentage as defined by the HTML spec.
+ * @note This also allows integer pixel values.
  */
 class HTMLPurifier_AttrDef_Percentage extends HTMLPurifier_AttrDef
 {
     
     /**
-     * Instance of HTMLPurifier_AttrDef_Number to defer number validation
+     * Instance of HTMLPurifier_AttrDef_Number to defer pixel validation
      */
     var $number_def;
     

library/HTMLPurifier/AttrDef/URI.php

@@ -4,7 +4,6 @@ require_once 'HTMLPurifier/AttrDef.php';
 require_once 'HTMLPurifier/URIScheme.php';
 require_once 'HTMLPurifier/URISchemeRegistry.php';
 require_once 'HTMLPurifier/AttrDef/Host.php';
-require_once 'HTMLPurifier/PercentEncoder.php';
 
 HTMLPurifier_ConfigSchema::define(
     'URI', 'DefaultScheme', 'http', 'string',
@@ -12,71 +11,6 @@ HTMLPurifier_ConfigSchema::define(
     'select the proper object validator when no scheme information is present.'
 );
 
-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.'
-);
-
 /**
  * Validates a URI as defined by RFC 3986.
  * @note Scheme-specific mechanics deferred to HTMLPurifier_URIScheme
@@ -85,16 +19,9 @@ class HTMLPurifier_AttrDef_URI extends HTMLPurifier_AttrDef
 {
     
     var $host;
-    var $PercentEncoder;
-    var $embeds_resource;
     
-    /**
+    function HTMLPurifier_AttrDef_URI() {
-     * @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_Host();
-        $this->PercentEncoder = new HTMLPurifier_PercentEncoder();
-        $this->embeds_resource = (bool) $embeds_resource;
     }
     
     function validate($uri, $config, &$context) {
@@ -105,9 +32,6 @@ class HTMLPurifier_AttrDef_URI extends HTMLPurifier_AttrDef
         // parse as CDATA
         $uri = $this->parseCDATA($uri);
         
-        // fix up percent-encoding
-        $uri = $this->PercentEncoder->normalize($uri);
-        
         // while it would be nice to use parse_url(), that's specifically
         // for HTTP and thus won't work for our generic URI parsing
         
@@ -139,38 +63,18 @@ class HTMLPurifier_AttrDef_URI extends HTMLPurifier_AttrDef
             // 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);
+            $scheme_obj =& $registry->getScheme($scheme, $config);
             if (!$scheme_obj) return false; // invalid scheme, clean it out
         } else {
-            $scheme_obj = $registry->getScheme(
+            $scheme_obj =& $registry->getScheme(
-                $config->get('URI', 'DefaultScheme'), $config, $context
+                $config->get('URI', 'DefaultScheme'), $config
             );
         }
         
         
-        // 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) {
             
-            // 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;
-            }
-            
             $HEXDIG = '[A-Fa-f0-9]';
             $unreserved = 'A-Za-z0-9-._~'; // make sure you wrap with []
             $sub_delims = '!$&\'()'; // needs []
@@ -193,19 +97,6 @@ class HTMLPurifier_AttrDef_URI extends HTMLPurifier_AttrDef
             $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 {
@@ -229,7 +120,7 @@ class HTMLPurifier_AttrDef_URI extends HTMLPurifier_AttrDef
         // note that $fragment is omitted
         list($userinfo, $host, $port, $path, $query) = 
             $scheme_obj->validateComponents(
-                $userinfo, $host, $port, $path, $query, $config, $context
+                $userinfo, $host, $port, $path, $query, $config
             );
         
         
@@ -250,37 +141,10 @@ class HTMLPurifier_AttrDef_URI extends HTMLPurifier_AttrDef
         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);
-            }
-        }
-        
         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;
-    }
-    
 }
 
 ?>

library/HTMLPurifier/AttrTransform.php

@@ -21,12 +21,11 @@ class HTMLPurifier_AttrTransform
      * Abstract: makes changes to the attributes dependent on multiple values.
      * 
      * @param $attr Assoc array of attributes, usually from
-     *              HTMLPurifier_Token_Tag::$attr
+     *              HTMLPurifier_Token_Tag::$attributes
      * @param $config Mandatory HTMLPurifier_Config object.
-     * @param $context Mandatory HTMLPurifier_Context object
      * @returns Processed attribute array.
      */
-    function transform($attr, $config, &$context) {
+    function transform($attr, $config) {
         trigger_error('Cannot call abstract function', E_USER_ERROR);
     }
 }

library/HTMLPurifier/AttrTransform/BdoDir.php

@@ -20,7 +20,7 @@ HTMLPurifier_ConfigSchema::defineAllowedValues(
 class HTMLPurifier_AttrTransform_BdoDir extends HTMLPurifier_AttrTransform
 {
     
-    function transform($attr, $config, &$context) {
+    function transform($attr, $config) {
         if (isset($attr['dir'])) return $attr;
         $attr['dir'] = $config->get('Attr', 'DefaultTextDir');
         return $attr;

library/HTMLPurifier/AttrTransform/ImgRequired.php

@@ -25,7 +25,7 @@ HTMLPurifier_ConfigSchema::define(
 class HTMLPurifier_AttrTransform_ImgRequired extends HTMLPurifier_AttrTransform
 {
     
-    function transform($attr, $config, &$context) {
+    function transform($attr, $config) {
         
         $src = true;
         if (!isset($attr['src'])) {

library/HTMLPurifier/AttrTransform/Lang.php

@@ -10,7 +10,7 @@ require_once 'HTMLPurifier/AttrTransform.php';
 class HTMLPurifier_AttrTransform_Lang extends HTMLPurifier_AttrTransform
 {
     
-    function transform($attr, $config, &$context) {
+    function transform($attr, $config) {
         
         $lang     = isset($attr['lang']) ? $attr['lang'] : false;
         $xml_lang = isset($attr['xml:lang']) ? $attr['xml:lang'] : false;

library/HTMLPurifier/AttrTransform/TextAlign.php

@@ -8,7 +8,7 @@ require_once 'HTMLPurifier/AttrTransform.php';
 class HTMLPurifier_AttrTransform_TextAlign
     extends HTMLPurifier_AttrTransform {
 
-    function transform($attr, $config, &$context) {
+    function transform($attr, $config) {
         
         if (!isset($attr['align'])) return $attr;
         

library/HTMLPurifier/CSSDefinition.php

@@ -11,9 +11,6 @@ require_once 'HTMLPurifier/AttrDef/FontFamily.php';
 require_once 'HTMLPurifier/AttrDef/Font.php';
 require_once 'HTMLPurifier/AttrDef/Border.php';
 require_once 'HTMLPurifier/AttrDef/ListStyle.php';
-require_once 'HTMLPurifier/AttrDef/CSSURI.php';
-require_once 'HTMLPurifier/AttrDef/BackgroundPosition.php';
-require_once 'HTMLPurifier/AttrDef/Background.php';
 
 /**
  * Defines allowed CSS attributes and what their values are.
@@ -54,19 +51,11 @@ class HTMLPurifier_CSSDefinition
         $this->info['font-variant'] = new HTMLPurifier_AttrDef_Enum(
             array('normal', 'small-caps'), false);
         
-        $uri_or_none = new HTMLPurifier_AttrDef_Composite(
-            array(
-                new HTMLPurifier_AttrDef_Enum(array('none')),
-                new HTMLPurifier_AttrDef_CSSURI()
-            )
-        );
-        
         $this->info['list-style-position'] = new HTMLPurifier_AttrDef_Enum(
             array('inside', 'outside'), false);
         $this->info['list-style-type'] = new HTMLPurifier_AttrDef_Enum(
             array('disc', 'circle', 'square', 'decimal', 'lower-roman',
-            'upper-roman', 'lower-alpha', 'upper-alpha', 'none'), false);
+            'upper-roman', 'lower-alpha', 'upper-alpha'), false);
-        $this->info['list-style-image'] = $uri_or_none;
         
         $this->info['list-style'] = new HTMLPurifier_AttrDef_ListStyle($config);
         
@@ -74,14 +63,14 @@ class HTMLPurifier_CSSDefinition
             array('capitalize', 'uppercase', 'lowercase', 'none'), false);
         $this->info['color'] = new HTMLPurifier_AttrDef_Color();
         
-        $this->info['background-image'] = $uri_or_none;
+        // technically speaking, this one should get its own validator, but
-        $this->info['background-repeat'] = new HTMLPurifier_AttrDef_Enum(
+        // since we don't support background images, it effectively is
-            array('repeat', 'repeat-x', 'repeat-y', 'no-repeat')
+        // equivalent to color.  The only trouble is that if the author
-        );
+        // specifies an image and a color, they'll both end up getting dropped,
-        $this->info['background-attachment'] = new HTMLPurifier_AttrDef_Enum(
+        // even though we ought to implement it and just discard the image
-            array('scroll', 'fixed')
+        // info.  This will be fixed in a later version (see TODO) when
-        );
+        // better URI filtering is implemented.
-        $this->info['background-position'] = new HTMLPurifier_AttrDef_BackgroundPosition();
+        $this->info['background'] = 
         
         $border_color = 
         $this->info['border-top-color'] = 
@@ -93,8 +82,6 @@ class HTMLPurifier_CSSDefinition
             new HTMLPurifier_AttrDef_Color()
         ));
         
-        $this->info['background'] = new HTMLPurifier_AttrDef_Background($config);
-        
         $this->info['border-color'] = new HTMLPurifier_AttrDef_Multiple($border_color);
         
         $border_width = 

library/HTMLPurifier/ChildDef.php

@@ -20,9 +20,10 @@ HTMLPurifier_ConfigSchema::define(
 class HTMLPurifier_ChildDef
 {
     /**
-     * Type of child definition, usually right-most part of class name lowercase.
+     * Type of child definition, usually right-most part of class name lowercase
-     * Used occasionally in terms of context.
+     * 
-     * @public
+     * Used occasionally in terms of context.  Possible values include
+     * custom, required, optional and empty.
      */
     var $type;
     
@@ -31,25 +32,409 @@ class HTMLPurifier_ChildDef
      * 
      * This is necessary for redundant checking when changes affecting
      * a child node may cause a parent node to now be disallowed.
-     * 
-     * @public
      */
     var $allow_empty;
     
     /**
      * Validates nodes according to definition and returns modification.
      * 
-     * @public
+     * @warning $context is NOT HTMLPurifier_AttrContext
      * @param $tokens_of_children Array of HTMLPurifier_Token
      * @param $config HTMLPurifier_Config object
-     * @param $context HTMLPurifier_Context object
+     * @param $context String context indicating inline, block or unknown
      * @return bool true to leave nodes as is
      * @return bool false to remove parent node
      * @return array of replacement child tokens
      */
-    function validateChildren($tokens_of_children, $config, &$context) {
+    function validateChildren($tokens_of_children, $config, $context) {
         trigger_error('Call to abstract function', E_USER_ERROR);
     }
 }
 
+/**
+ * Custom validation class, accepts DTD child definitions
+ * 
+ * @warning Currently this class is an all or nothing proposition, that is,
+ *          it will only give a bool return value.
+ * @note This class is currently not used by any code, although it is unit
+ *       tested.
+ */
+class HTMLPurifier_ChildDef_Custom extends HTMLPurifier_ChildDef
+{
+    var $type = 'custom';
+    var $allow_empty = false;
+    /**
+     * Allowed child pattern as defined by the DTD
+     */
+    var $dtd_regex;
+    /**
+     * PCRE regex derived from $dtd_regex
+     * @private
+     */
+    var $_pcre_regex;
+    /**
+     * @param $dtd_regex Allowed child pattern from the DTD
+     */
+    function HTMLPurifier_ChildDef_Custom($dtd_regex) {
+        $this->dtd_regex = $dtd_regex;
+        $this->_compileRegex();
+    }
+    /**
+     * Compiles the PCRE regex from a DTD regex ($dtd_regex to $_pcre_regex)
+     */
+    function _compileRegex() {
+        $raw = str_replace(' ', '', $this->dtd_regex);
+        if ($raw{0} != '(') {
+            $raw = "($raw)";
+        }
+        $reg = str_replace(',', ',?', $raw);
+        $reg = preg_replace('/([#a-zA-Z0-9_.-]+)/', '(,?\\0)', $reg);
+        $this->_pcre_regex = $reg;
+    }
+    function validateChildren($tokens_of_children, $config, $context) {
+        $list_of_children = '';
+        $nesting = 0; // depth into the nest
+        foreach ($tokens_of_children as $token) {
+            if (!empty($token->is_whitespace)) continue;
+            
+            $is_child = ($nesting == 0); // direct
+            
+            if ($token->type == 'start') {
+                $nesting++;
+            } elseif ($token->type == 'end') {
+                $nesting--;
+            }
+            
+            if ($is_child) {
+                $list_of_children .= $token->name . ',';
+            }
+        }
+        $list_of_children = rtrim($list_of_children, ',');
+        
+        $okay =
+            preg_match(
+                '/^'.$this->_pcre_regex.'$/',
+                $list_of_children
+            );
+        
+        return (bool) $okay;
+    }
+}
+
+/**
+ * Definition that allows a set of elements, but disallows empty children.
+ */
+class HTMLPurifier_ChildDef_Required extends HTMLPurifier_ChildDef
+{
+    /**
+     * Lookup table of allowed elements.
+     */
+    var $elements = array();
+    /**
+     * @param $elements List of allowed element names (lowercase).
+     */
+    function HTMLPurifier_ChildDef_Required($elements) {
+        if (is_string($elements)) {
+            $elements = str_replace(' ', '', $elements);
+            $elements = explode('|', $elements);
+        }
+        $elements = array_flip($elements);
+        foreach ($elements as $i => $x) $elements[$i] = true;
+        $this->elements = $elements;
+        $this->gen = new HTMLPurifier_Generator();
+    }
+    var $allow_empty = false;
+    var $type = 'required';
+    function validateChildren($tokens_of_children, $config, $context) {
+        // if there are no tokens, delete parent node
+        if (empty($tokens_of_children)) return false;
+        
+        // the new set of children
+        $result = array();
+        
+        // current depth into the nest
+        $nesting = 0;
+        
+        // whether or not we're deleting a node
+        $is_deleting = false;
+        
+        // whether or not parsed character data is allowed
+        // this controls whether or not we silently drop a tag
+        // or generate escaped HTML from it
+        $pcdata_allowed = isset($this->elements['#PCDATA']);
+        
+        // a little sanity check to make sure it's not ALL whitespace
+        $all_whitespace = true;
+        
+        // some configuration
+        $escape_invalid_children = $config->get('Core', 'EscapeInvalidChildren');
+        
+        foreach ($tokens_of_children as $token) {
+            if (!empty($token->is_whitespace)) {
+                $result[] = $token;
+                continue;
+            }
+            $all_whitespace = false; // phew, we're not talking about whitespace
+            
+            $is_child = ($nesting == 0);
+            
+            if ($token->type == 'start') {
+                $nesting++;
+            } elseif ($token->type == 'end') {
+                $nesting--;
+            }
+            
+            if ($is_child) {
+                $is_deleting = false;
+                if (!isset($this->elements[$token->name])) {
+                    $is_deleting = true;
+                    if ($pcdata_allowed && $token->type == 'text') {
+                        $result[] = $token;
+                    } elseif ($pcdata_allowed && $escape_invalid_children) {
+                        $result[] = new HTMLPurifier_Token_Text(
+                            $this->gen->generateFromToken($token, $config)
+                        );
+                    }
+                    continue;
+                }
+            }
+            if (!$is_deleting || ($pcdata_allowed && $token->type == 'text')) {
+                $result[] = $token;
+            } elseif ($pcdata_allowed && $escape_invalid_children) {
+                $result[] =
+                    new HTMLPurifier_Token_Text(
+                        $this->gen->generateFromToken( $token, $config )
+                    );
+            } else {
+                // drop silently
+            }
+        }
+        if (empty($result)) return false;
+        if ($all_whitespace) return false;
+        if ($tokens_of_children == $result) return true;
+        return $result;
+    }
+}
+
+/**
+ * Definition that allows a set of elements, and allows no children.
+ * @note This is a hack to reuse code from HTMLPurifier_ChildDef_Required,
+ *       really, one shouldn't inherit from the other.  Only altered behavior
+ *       is to overload a returned false with an array.  Thus, it will never
+ *       return false.
+ */
+class HTMLPurifier_ChildDef_Optional extends HTMLPurifier_ChildDef_Required
+{
+    var $allow_empty = true;
+    var $type = 'optional';
+    function validateChildren($tokens_of_children, $config, $context) {
+        $result = parent::validateChildren($tokens_of_children, $config, $context);
+        if ($result === false) return array();
+        return $result;
+    }
+}
+
+/**
+ * Definition that disallows all elements.
+ * @warning validateChildren() in this class is actually never called, because
+ *          empty elements are corrected in HTMLPurifier_Strategy_MakeWellFormed
+ *          before child definitions are parsed in earnest by
+ *          HTMLPurifier_Strategy_FixNesting.
+ */
+class HTMLPurifier_ChildDef_Empty extends HTMLPurifier_ChildDef
+{
+    var $allow_empty = true;
+    var $type = 'empty';
+    function HTMLPurifier_ChildDef_Empty() {}
+    function validateChildren($tokens_of_children, $config, $context) {
+        return array();
+    }
+}
+
+/**
+ * Definition that uses different definitions depending on context.
+ * 
+ * The del and ins tags are notable because they allow different types of
+ * elements depending on whether or not they're in a block or inline context.
+ * Chameleon allows this behavior to happen by using two different
+ * definitions depending on context.  While this somewhat generalized,
+ * it is specifically intended for those two tags.
+ */
+class HTMLPurifier_ChildDef_Chameleon extends HTMLPurifier_ChildDef
+{
+    
+    /**
+     * Instance of the definition object to use when inline. Usually stricter.
+     */
+    var $inline;
+    /**
+     * Instance of the definition object to use when block.
+     */
+    var $block;
+    
+    /**
+     * @param $inline List of elements to allow when inline.
+     * @param $block List of elements to allow when block.
+     */
+    function HTMLPurifier_ChildDef_Chameleon($inline, $block) {
+        $this->inline = new HTMLPurifier_ChildDef_Optional($inline);
+        $this->block  = new HTMLPurifier_ChildDef_Optional($block);
+    }
+    
+    function validateChildren($tokens_of_children, $config, $context) {
+        switch ($context) {
+            case 'unknown':
+            case 'inline':
+                $result = $this->inline->validateChildren(
+                    $tokens_of_children, $config, $context);
+                break;
+            case 'block':
+                $result = $this->block->validateChildren(
+                    $tokens_of_children, $config, $context);
+                break;
+            default:
+                trigger_error('Invalid context', E_USER_ERROR);
+                return false;
+        }
+        return $result;
+    }
+}
+
+/**
+ * Definition for tables
+ */
+class HTMLPurifier_ChildDef_Table extends HTMLPurifier_ChildDef
+{
+    var $allow_empty = false;
+    var $type = 'table';
+    function HTMLPurifier_ChildDef_Table() {}
+    function validateChildren($tokens_of_children, $config, $context) {
+        if (empty($tokens_of_children)) return false;
+        
+        // this ensures that the loop gets run one last time before closing
+        // up. It's a little bit of a hack, but it works! Just make sure you
+        // get rid of the token later.
+        $tokens_of_children[] = false;
+        
+        // only one of these elements is allowed in a table
+        $caption = false;
+        $thead   = false;
+        $tfoot   = false;
+        
+        // as many of these as you want
+        $cols    = array();
+        $content = array();
+        
+        $nesting = 0; // current depth so we can determine nodes
+        $is_collecting = false; // are we globbing together tokens to package
+                                // into one of the collectors?
+        $collection = array(); // collected nodes
+        $tag_index = 0; // the first node might be whitespace,
+                            // so this tells us where the start tag is
+        
+        foreach ($tokens_of_children as $token) {
+            $is_child = ($nesting == 0);
+            
+            if ($token === false) {
+                // terminating sequence started
+            } elseif ($token->type == 'start') {
+                $nesting++;
+            } elseif ($token->type == 'end') {
+                $nesting--;
+            }
+            
+            // handle node collection
+            if ($is_collecting) {
+                if ($is_child) {
+                    // okay, let's stash the tokens away
+                    // first token tells us the type of the collection
+                    switch ($collection[$tag_index]->name) {
+                        case 'tr':
+                        case 'tbody':
+                            $content[] = $collection;
+                            break;
+                        case 'caption':
+                            if ($caption !== false) break;
+                            $caption = $collection;
+                            break;
+                        case 'thead':
+                        case 'tfoot':
+                            // access the appropriate variable, $thead or $tfoot
+                            $var = $collection[$tag_index]->name;
+                            if ($$var === false) {
+                                $$var = $collection;
+                            } else {
+                                // transmutate the first and less entries into
+                                // tbody tags, and then put into content
+                                $collection[$tag_index]->name = 'tbody';
+                                $collection[count($collection)-1]->name = 'tbody';
+                                $content[] = $collection;
+                            }
+                            break;
+                         case 'colgroup':
+                            $cols[] = $collection;
+                            break;
+                    }
+                    $collection = array();
+                    $is_collecting = false;
+                    $tag_index = 0;
+                } else {
+                    // add the node to the collection
+                    $collection[] = $token;
+                }
+            }
+            
+            // terminate
+            if ($token === false) break;
+            
+            if ($is_child) {
+                // determine what we're dealing with
+                if ($token->name == 'col') {
+                    // the only empty tag in the possie, we can handle it
+                    // immediately
+                    $cols[] = array_merge($collection, array($token));
+                    $collection = array();
+                    $tag_index = 0;
+                    continue;
+                }
+                switch($token->name) {
+                    case 'caption':
+                    case 'colgroup':
+                    case 'thead':
+                    case 'tfoot':
+                    case 'tbody':
+                    case 'tr':
+                        $is_collecting = true;
+                        $collection[] = $token;
+                        continue;
+                    default:
+                        if ($token->type == 'text' && $token->is_whitespace) {
+                            $collection[] = $token;
+                            $tag_index++;
+                        }
+                        continue;
+                }
+            }
+        }
+        
+        if (empty($content)) return false;
+        
+        $ret = array();
+        if ($caption !== false) $ret = array_merge($ret, $caption);
+        if ($cols !== false)    foreach ($cols as $token_array) $ret = array_merge($ret, $token_array);
+        if ($thead !== false)   $ret = array_merge($ret, $thead);
+        if ($tfoot !== false)   $ret = array_merge($ret, $tfoot);
+        foreach ($content as $token_array) $ret = array_merge($ret, $token_array);
+        if (!empty($collection) && $is_collecting == false){
+            // grab the trailing space
+            $ret = array_merge($ret, $collection);
+        }
+        
+        array_pop($tokens_of_children); // remove phantom token
+        
+        return ($ret === $tokens_of_children) ? true : $ret;
+        
+    }
+}
+
 ?>

library/HTMLPurifier/ChildDef/Chameleon.php

@@ -1,60 +0,0 @@
-<?php
-
-require_once 'HTMLPurifier/ChildDef.php';
-
-/**
- * Definition that uses different definitions depending on context.
- * 
- * The del and ins tags are notable because they allow different types of
- * elements depending on whether or not they're in a block or inline context.
- * Chameleon allows this behavior to happen by using two different
- * definitions depending on context.  While this somewhat generalized,
- * it is specifically intended for those two tags.
- */
-class HTMLPurifier_ChildDef_Chameleon extends HTMLPurifier_ChildDef
-{
-    
-    /**
-     * Instance of the definition object to use when inline. Usually stricter.
-     * @public
-     */
-    var $inline;
-    
-    /**
-     * Instance of the definition object to use when block.
-     * @public
-     */
-    var $block;
-    
-    var $type = 'chameleon';
-    
-    /**
-     * @param $inline List of elements to allow when inline.
-     * @param $block List of elements to allow when block.
-     */
-    function HTMLPurifier_ChildDef_Chameleon($inline, $block) {
-        $this->inline = new HTMLPurifier_ChildDef_Optional($inline);
-        $this->block  = new HTMLPurifier_ChildDef_Optional($block);
-    }
-    
-    function validateChildren($tokens_of_children, $config, &$context) {
-        $parent_type = $context->get('ParentType');
-        switch ($parent_type) {
-            case 'unknown':
-            case 'inline':
-                $result = $this->inline->validateChildren(
-                    $tokens_of_children, $config, $context);
-                break;
-            case 'block':
-                $result = $this->block->validateChildren(
-                    $tokens_of_children, $config, $context);
-                break;
-            default:
-                trigger_error('Invalid context', E_USER_ERROR);
-                return false;
-        }
-        return $result;
-    }
-}
-
-?>

library/HTMLPurifier/ChildDef/Custom.php

@@ -1,75 +0,0 @@
-<?php
-
-require_once 'HTMLPurifier/ChildDef.php';
-
-/**
- * Custom validation class, accepts DTD child definitions
- * 
- * @warning Currently this class is an all or nothing proposition, that is,
- *          it will only give a bool return value.
- * @note This class is currently not used by any code, although it is unit
- *       tested.
- */
-class HTMLPurifier_ChildDef_Custom extends HTMLPurifier_ChildDef
-{
-    var $type = 'custom';
-    var $allow_empty = false;
-    /**
-     * Allowed child pattern as defined by the DTD
-     */
-    var $dtd_regex;
-    /**
-     * PCRE regex derived from $dtd_regex
-     * @private
-     */
-    var $_pcre_regex;
-    /**
-     * @param $dtd_regex Allowed child pattern from the DTD
-     */
-    function HTMLPurifier_ChildDef_Custom($dtd_regex) {
-        $this->dtd_regex = $dtd_regex;
-        $this->_compileRegex();
-    }
-    /**
-     * Compiles the PCRE regex from a DTD regex ($dtd_regex to $_pcre_regex)
-     */
-    function _compileRegex() {
-        $raw = str_replace(' ', '', $this->dtd_regex);
-        if ($raw{0} != '(') {
-            $raw = "($raw)";
-        }
-        $reg = str_replace(',', ',?', $raw);
-        $reg = preg_replace('/([#a-zA-Z0-9_.-]+)/', '(,?\\0)', $reg);
-        $this->_pcre_regex = $reg;
-    }
-    function validateChildren($tokens_of_children, $config, &$context) {
-        $list_of_children = '';
-        $nesting = 0; // depth into the nest
-        foreach ($tokens_of_children as $token) {
-            if (!empty($token->is_whitespace)) continue;
-            
-            $is_child = ($nesting == 0); // direct
-            
-            if ($token->type == 'start') {
-                $nesting++;
-            } elseif ($token->type == 'end') {
-                $nesting--;
-            }
-            
-            if ($is_child) {
-                $list_of_children .= $token->name . ',';
-            }
-        }
-        $list_of_children = rtrim($list_of_children, ',');
-        
-        $okay =
-            preg_match(
-                '/^'.$this->_pcre_regex.'$/',
-                $list_of_children
-            );
-        
-        return (bool) $okay;
-    }
-}
-
-?>

library/HTMLPurifier/ChildDef/Empty.php

@@ -1,22 +0,0 @@
-<?php
-
-require_once 'HTMLPurifier/ChildDef.php';
-
-/**
- * Definition that disallows all elements.
- * @warning validateChildren() in this class is actually never called, because
- *          empty elements are corrected in HTMLPurifier_Strategy_MakeWellFormed
- *          before child definitions are parsed in earnest by
- *          HTMLPurifier_Strategy_FixNesting.
- */
-class HTMLPurifier_ChildDef_Empty extends HTMLPurifier_ChildDef
-{
-    var $allow_empty = true;
-    var $type = 'empty';
-    function HTMLPurifier_ChildDef_Empty() {}
-    function validateChildren($tokens_of_children, $config, &$context) {
-        return array();
-    }
-}
-
-?>

library/HTMLPurifier/ChildDef/Optional.php

@@ -1,23 +0,0 @@
-<?php
-
-require_once 'HTMLPurifier/ChildDef/Required.php';
-
-/**
- * Definition that allows a set of elements, and allows no children.
- * @note This is a hack to reuse code from HTMLPurifier_ChildDef_Required,
- *       really, one shouldn't inherit from the other.  Only altered behavior
- *       is to overload a returned false with an array.  Thus, it will never
- *       return false.
- */
-class HTMLPurifier_ChildDef_Optional extends HTMLPurifier_ChildDef_Required
-{
-    var $allow_empty = true;
-    var $type = 'optional';
-    function validateChildren($tokens_of_children, $config, &$context) {
-        $result = parent::validateChildren($tokens_of_children, $config, $context);
-        if ($result === false) return array();
-        return $result;
-    }
-}
-
-?>

library/HTMLPurifier/ChildDef/Required.php

@@ -1,104 +0,0 @@
-<?php
-
-require_once 'HTMLPurifier/ChildDef.php';
-
-/**
- * Definition that allows a set of elements, but disallows empty children.
- */
-class HTMLPurifier_ChildDef_Required extends HTMLPurifier_ChildDef
-{
-    /**
-     * Lookup table of allowed elements.
-     * @public
-     */
-    var $elements = array();
-    /**
-     * @param $elements List of allowed element names (lowercase).
-     */
-    function HTMLPurifier_ChildDef_Required($elements) {
-        if (is_string($elements)) {
-            $elements = str_replace(' ', '', $elements);
-            $elements = explode('|', $elements);
-        }
-        $elements = array_flip($elements);
-        foreach ($elements as $i => $x) {
-            $elements[$i] = true;
-            if (empty($i)) unset($elements[$i]);
-        }
-        $this->elements = $elements;
-        $this->gen = new HTMLPurifier_Generator();
-    }
-    var $allow_empty = false;
-    var $type = 'required';
-    function validateChildren($tokens_of_children, $config, &$context) {
-        // if there are no tokens, delete parent node
-        if (empty($tokens_of_children)) return false;
-        
-        // the new set of children
-        $result = array();
-        
-        // current depth into the nest
-        $nesting = 0;
-        
-        // whether or not we're deleting a node
-        $is_deleting = false;
-        
-        // whether or not parsed character data is allowed
-        // this controls whether or not we silently drop a tag
-        // or generate escaped HTML from it
-        $pcdata_allowed = isset($this->elements['#PCDATA']);
-        
-        // a little sanity check to make sure it's not ALL whitespace
-        $all_whitespace = true;
-        
-        // some configuration
-        $escape_invalid_children = $config->get('Core', 'EscapeInvalidChildren');
-        
-        foreach ($tokens_of_children as $token) {
-            if (!empty($token->is_whitespace)) {
-                $result[] = $token;
-                continue;
-            }
-            $all_whitespace = false; // phew, we're not talking about whitespace
-            
-            $is_child = ($nesting == 0);
-            
-            if ($token->type == 'start') {
-                $nesting++;
-            } elseif ($token->type == 'end') {
-                $nesting--;
-            }
-            
-            if ($is_child) {
-                $is_deleting = false;
-                if (!isset($this->elements[$token->name])) {
-                    $is_deleting = true;
-                    if ($pcdata_allowed && $token->type == 'text') {
-                        $result[] = $token;
-                    } elseif ($pcdata_allowed && $escape_invalid_children) {
-                        $result[] = new HTMLPurifier_Token_Text(
-                            $this->gen->generateFromToken($token, $config)
-                        );
-                    }
-                    continue;
-                }
-            }
-            if (!$is_deleting || ($pcdata_allowed && $token->type == 'text')) {
-                $result[] = $token;
-            } elseif ($pcdata_allowed && $escape_invalid_children) {
-                $result[] =
-                    new HTMLPurifier_Token_Text(
-                        $this->gen->generateFromToken( $token, $config )
-                    );
-            } else {
-                // drop silently
-            }
-        }
-        if (empty($result)) return false;
-        if ($all_whitespace) return false;
-        if ($tokens_of_children == $result) return true;
-        return $result;
-    }
-}
-
-?>

library/HTMLPurifier/ChildDef/StrictBlockquote.php

@@ -1,70 +0,0 @@
-<?php
-
-require_once 'HTMLPurifier/ChildDef/Required.php';
-
-/**
- * Takes the contents of blockquote when in strict and reformats for validation.
- * 
- * From XHTML 1.0 Transitional to Strict, there is a notable change where 
- */
-class   HTMLPurifier_ChildDef_StrictBlockquote
-extends HTMLPurifier_ChildDef_Required
-{
-    var $allow_empty = true;
-    var $type = 'strictblockquote';
-    var $init = false;
-    function HTMLPurifier_ChildDef_StrictBlockquote() {}
-    function validateChildren($tokens_of_children, $config, &$context) {
-        
-        $def = $config->getHTMLDefinition();
-        if (!$this->init) {
-            // allow all inline elements
-            $this->elements = $def->info_flow_elements;
-            $this->elements['#PCDATA'] = true;
-            $this->init = true;
-        }
-        
-        $result = parent::validateChildren($tokens_of_children, $config, $context);
-        if ($result === false) return array();
-        if ($result === true) $result = $tokens_of_children;
-        
-        $block_wrap_start = new HTMLPurifier_Token_Start($def->info_block_wrapper);
-        $block_wrap_end   = new HTMLPurifier_Token_End(  $def->info_block_wrapper);
-        $is_inline = false;
-        $depth = 0;
-        $ret = array();
-        
-        // assuming that there are no comment tokens
-        foreach ($result as $i => $token) {
-            $token = $result[$i];
-            // ifs are nested for readability
-            if (!$is_inline) {
-                if (!$depth) {
-                     if (($token->type == 'text') ||
-                         ($def->info[$token->name]->type == 'inline')) {
-                        $is_inline = true;
-                        $ret[] = $block_wrap_start;
-                     }
-                }
-            } else {
-                if (!$depth) {
-                    // starting tokens have been inline text / empty
-                    if ($token->type == 'start' || $token->type == 'empty') {
-                        if ($def->info[$token->name]->type == 'block') {
-                            // ended
-                            $ret[] = $block_wrap_end;
-                            $is_inline = false;
-                        }
-                    }
-                }
-            }
-            $ret[] = $token;
-            if ($token->type == 'start') $depth++;
-            if ($token->type == 'end')   $depth--;
-        }
-        if ($is_inline) $ret[] = $block_wrap_end;
-        return $ret;
-    }
-}
-
-?>

library/HTMLPurifier/ChildDef/Table.php

@@ -1,142 +0,0 @@
-<?php
-
-require_once 'HTMLPurifier/ChildDef.php';
-
-/**
- * Definition for tables
- */
-class HTMLPurifier_ChildDef_Table extends HTMLPurifier_ChildDef
-{
-    var $allow_empty = false;
-    var $type = 'table';
-    function HTMLPurifier_ChildDef_Table() {}
-    function validateChildren($tokens_of_children, $config, &$context) {
-        if (empty($tokens_of_children)) return false;
-        
-        // this ensures that the loop gets run one last time before closing
-        // up. It's a little bit of a hack, but it works! Just make sure you
-        // get rid of the token later.
-        $tokens_of_children[] = false;
-        
-        // only one of these elements is allowed in a table
-        $caption = false;
-        $thead   = false;
-        $tfoot   = false;
-        
-        // as many of these as you want
-        $cols    = array();
-        $content = array();
-        
-        $nesting = 0; // current depth so we can determine nodes
-        $is_collecting = false; // are we globbing together tokens to package
-                                // into one of the collectors?
-        $collection = array(); // collected nodes
-        $tag_index = 0; // the first node might be whitespace,
-                            // so this tells us where the start tag is
-        
-        foreach ($tokens_of_children as $token) {
-            $is_child = ($nesting == 0);
-            
-            if ($token === false) {
-                // terminating sequence started
-            } elseif ($token->type == 'start') {
-                $nesting++;
-            } elseif ($token->type == 'end') {
-                $nesting--;
-            }
-            
-            // handle node collection
-            if ($is_collecting) {
-                if ($is_child) {
-                    // okay, let's stash the tokens away
-                    // first token tells us the type of the collection
-                    switch ($collection[$tag_index]->name) {
-                        case 'tr':
-                        case 'tbody':
-                            $content[] = $collection;
-                            break;
-                        case 'caption':
-                            if ($caption !== false) break;
-                            $caption = $collection;
-                            break;
-                        case 'thead':
-                        case 'tfoot':
-                            // access the appropriate variable, $thead or $tfoot
-                            $var = $collection[$tag_index]->name;
-                            if ($$var === false) {
-                                $$var = $collection;
-                            } else {
-                                // transmutate the first and less entries into
-                                // tbody tags, and then put into content
-                                $collection[$tag_index]->name = 'tbody';
-                                $collection[count($collection)-1]->name = 'tbody';
-                                $content[] = $collection;
-                            }
-                            break;
-                         case 'colgroup':
-                            $cols[] = $collection;
-                            break;
-                    }
-                    $collection = array();
-                    $is_collecting = false;
-                    $tag_index = 0;
-                } else {
-                    // add the node to the collection
-                    $collection[] = $token;
-                }
-            }
-            
-            // terminate
-            if ($token === false) break;
-            
-            if ($is_child) {
-                // determine what we're dealing with
-                if ($token->name == 'col') {
-                    // the only empty tag in the possie, we can handle it
-                    // immediately
-                    $cols[] = array_merge($collection, array($token));
-                    $collection = array();
-                    $tag_index = 0;
-                    continue;
-                }
-                switch($token->name) {
-                    case 'caption':
-                    case 'colgroup':
-                    case 'thead':
-                    case 'tfoot':
-                    case 'tbody':
-                    case 'tr':
-                        $is_collecting = true;
-                        $collection[] = $token;
-                        continue;
-                    default:
-                        if ($token->type == 'text' && $token->is_whitespace) {
-                            $collection[] = $token;
-                            $tag_index++;
-                        }
-                        continue;
-                }
-            }
-        }
-        
-        if (empty($content)) return false;
-        
-        $ret = array();
-        if ($caption !== false) $ret = array_merge($ret, $caption);
-        if ($cols !== false)    foreach ($cols as $token_array) $ret = array_merge($ret, $token_array);
-        if ($thead !== false)   $ret = array_merge($ret, $thead);
-        if ($tfoot !== false)   $ret = array_merge($ret, $tfoot);
-        foreach ($content as $token_array) $ret = array_merge($ret, $token_array);
-        if (!empty($collection) && $is_collecting == false){
-            // grab the trailing space
-            $ret = array_merge($ret, $collection);
-        }
-        
-        array_pop($tokens_of_children); // remove phantom token
-        
-        return ($ret === $tokens_of_children) ? true : $ret;
-        
-    }
-}
-
-?>

library/HTMLPurifier/Config.php

@@ -44,29 +44,11 @@ class HTMLPurifier_Config
         $this->def  = $definition; // keep a copy around for checking
     }
     
-    /**
-     * Convenience constructor that creates a config object based on a mixed var
-     * @static
-     * @param mixed $config Variable that defines the state of the config
-     *                      object. Can be: a HTMLPurifier_Config() object,
-     *                      an array of directives based on loadArray(),
-     *                      or a string filename of an ini file.
-     * @return Configured HTMLPurifier_Config object
-     */
-    static function create($config) {
-        if ($config instanceof HTMLPurifier_Config) return $config;
-        $ret = HTMLPurifier_Config::createDefault();
-        if (is_string($config)) $ret->loadIni($config);
-        elseif (is_array($config)) $ret->loadArray($config);
-        return $ret;
-    }
-    
     /**
      * Convenience constructor that creates a default configuration object.
-     * @static
      * @return Default HTMLPurifier_Config object.
      */
-    static function createDefault() {
+    function createDefault() {
         $definition =& HTMLPurifier_ConfigSchema::instance();
         $config = new HTMLPurifier_Config($definition);
         return $config;
@@ -77,60 +59,29 @@ class HTMLPurifier_Config
      * @param $namespace String namespace
      * @param $key String key
      */
-    function get($namespace, $key, $from_alias = false) {
+    function get($namespace, $key) {
-        if (!isset($this->def->info[$namespace][$key])) {
+        if (!isset($this->conf[$namespace][$key])) {
             trigger_error('Cannot retrieve value of undefined directive',
                 E_USER_WARNING);
             return;
         }
-        if ($this->def->info[$namespace][$key]->class == 'alias') {
-            trigger_error('Cannot get value from aliased directive, use real name',
-                E_USER_ERROR);
-            return;
-        }
         return $this->conf[$namespace][$key];
     }
     
-    /**
-     * Retreives an array of directives to values from a given namespace
-     * @param $namespace String namespace
-     */
-    function getBatch($namespace) {
-        if (!isset($this->def->info[$namespace])) {
-            trigger_error('Cannot retrieve undefined namespace',
-                E_USER_WARNING);
-            return;
-        }
-        return $this->conf[$namespace];
-    }
-    
     /**
      * Sets a value to configuration.
      * @param $namespace String namespace
      * @param $key String key
      * @param $value Mixed value
      */
-    function set($namespace, $key, $value, $from_alias = false) {
+    function set($namespace, $key, $value) {
-        if (!isset($this->def->info[$namespace][$key])) {
+        if (!isset($this->conf[$namespace][$key])) {
             trigger_error('Cannot set undefined directive to value',
                 E_USER_WARNING);
             return;
         }
-        if ($this->def->info[$namespace][$key]->class == 'alias') {
+        $value = $this->def->validate($value,
-            if ($from_alias) {
+                                      $this->def->info[$namespace][$key]->type);
-                trigger_error('Double-aliases not allowed, please fix '.
-                    'ConfigSchema bug');
-            }
-            $this->set($this->def->info[$namespace][$key]->namespace,
-                       $this->def->info[$namespace][$key]->name,
-                       $value, true);
-            return;
-        }
-        $value = $this->def->validate(
-                    $value,
-                    $this->def->info[$namespace][$key]->type,
-                    $this->def->info[$namespace][$key]->allow_null
-                 );
         if (is_string($value)) {
             // resolve value alias if defined
             if (isset($this->def->info[$namespace][$key]->aliases[$value])) {
@@ -144,7 +95,7 @@ class HTMLPurifier_Config
                 }
             }
         }
-        if ($this->def->isError($value)) {
+        if ($value === null) {
             trigger_error('Value is of invalid type', E_USER_WARNING);
             return;
         }
@@ -173,37 +124,6 @@ class HTMLPurifier_Config
         return $this->css_definition;
     }
     
-    /**
-     * Loads configuration values from an array with the following structure:
-     * Namespace.Directive => Value
-     * @param $config_array Configuration associative array
-     */
-    function loadArray($config_array) {
-        foreach ($config_array as $key => $value) {
-            $key = str_replace('_', '.', $key);
-            if (strpos($key, '.') !== false) {
-                // condensed form
-                list($namespace, $directive) = explode('.', $key);
-                $this->set($namespace, $directive, $value);
-            } else {
-                $namespace = $key;
-                $namespace_values = $value;
-                foreach ($namespace_values as $directive => $value) {
-                    $this->set($namespace, $directive, $value);
-                }
-            }
-        }
-    }
-    
-    /**
-     * Loads configuration values from an ini file
-     * @param $filename Name of ini file
-     */
-    function loadIni($filename) {
-        $array = parse_ini_file($filename, true);
-        $this->loadArray($array);
-    }
-    
 }
 
-?>
+?>

library/HTMLPurifier/ConfigSchema.php

@@ -1,7 +1,5 @@
 <?php
 
-require_once 'HTMLPurifier/Error.php';
-
 /**
  * Configuration definition, defines directives and their defaults.
  * @todo The ability to define things multiple times is confusing and should
@@ -67,9 +65,8 @@ class HTMLPurifier_ConfigSchema {
     
     /**
      * Retrieves an instance of the application-wide configuration definition.
-     * @static
      */
-    static function &instance($prototype = null) {
+    function &instance($prototype = null) {
         static $instance;
         if ($prototype !== null) {
             $instance = $prototype;
@@ -82,7 +79,6 @@ class HTMLPurifier_ConfigSchema {
     
     /**
      * Defines a directive for configuration
-     * @static
      * @warning Will fail of directive's namespace is defined
      * @param $namespace Namespace the directive is in
      * @param $name Key of directive
@@ -91,7 +87,7 @@ class HTMLPurifier_ConfigSchema {
      *      HTMLPurifier_DirectiveDef::$type for allowed values
      * @param $description Description of directive for documentation
      */
-    static function define(
+    function define(
         $namespace, $name, $default, $type, 
         $description
     ) {
@@ -106,11 +102,6 @@ class HTMLPurifier_ConfigSchema {
                 E_USER_ERROR);
             return;
         }
-        if (empty($description)) {
-            trigger_error('Description must be non-empty',
-                E_USER_ERROR);
-            return;
-        }
         if (isset($def->info[$namespace][$name])) {
             if (
                 $def->info[$namespace][$name]->type !== $type ||
@@ -120,19 +111,12 @@ class HTMLPurifier_ConfigSchema {
                 return;
             }
         } else {
-            // process modifiers
-            $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->validate($default, $type) === null) {
-            if ($def->isError($default)) {
                 trigger_error('Default value does not match directive type',
                     E_USER_ERROR);
                 return;
@@ -140,7 +124,6 @@ class HTMLPurifier_ConfigSchema {
             $def->info[$namespace][$name] =
                 new HTMLPurifier_ConfigEntity_Directive();
             $def->info[$namespace][$name]->type = $type;
-            $def->info[$namespace][$name]->allow_null = $allow_null;
             $def->defaults[$namespace][$name]   = $default;
         }
         $backtrace = debug_backtrace();
@@ -151,11 +134,10 @@ class HTMLPurifier_ConfigSchema {
     
     /**
      * Defines a namespace for directives to be put into.
-     * @static
      * @param $namespace Namespace's name
      * @param $description Description of the namespace
      */
-    static function defineNamespace($namespace, $description) {
+    function defineNamespace($namespace, $description) {
         $def =& HTMLPurifier_ConfigSchema::instance();
         if (isset($def->info[$namespace])) {
             trigger_error('Cannot redefine namespace', E_USER_ERROR);
@@ -166,11 +148,6 @@ class HTMLPurifier_ConfigSchema {
                 E_USER_ERROR);
             return;
         }
-        if (empty($description)) {
-            trigger_error('Description must be non-empty',
-                E_USER_ERROR);
-            return;
-        }
         $def->info[$namespace] = array();
         $def->info_namespace[$namespace] = new HTMLPurifier_ConfigEntity_Namespace();
         $def->info_namespace[$namespace]->description = $description;
@@ -182,13 +159,12 @@ class HTMLPurifier_ConfigSchema {
      * 
      * Directive value aliases are convenient for developers because it lets
      * them set a directive to several values and get the same result.
-     * @static
      * @param $namespace Directive's namespace
      * @param $name Name of Directive
      * @param $alias Name of aliased value
      * @param $real Value aliased value will be converted into
      */
-    static function defineValueAliases($namespace, $name, $aliases) {
+    function defineValueAliases($namespace, $name, $aliases) {
         $def =& HTMLPurifier_ConfigSchema::instance();
         if (!isset($def->info[$namespace][$name])) {
             trigger_error('Cannot set value alias for non-existant directive',
@@ -214,129 +190,58 @@ class HTMLPurifier_ConfigSchema {
     
     /**
      * Defines a set of allowed values for a directive.
-     * @static
      * @param $namespace Namespace of directive
      * @param $name Name of directive
      * @param $allowed_values Arraylist of allowed values
      */
-    static function defineAllowedValues($namespace, $name, $allowed_values) {
+    function defineAllowedValues($namespace, $name, $allowed_values) {
         $def =& HTMLPurifier_ConfigSchema::instance();
         if (!isset($def->info[$namespace][$name])) {
             trigger_error('Cannot define allowed values for undefined directive',
                 E_USER_ERROR);
             return;
         }
-        $directive =& $def->info[$namespace][$name];
+        if ($def->info[$namespace][$name]->allowed === true) {
-        $type = $directive->type;
+            $def->info[$namespace][$name]->allowed = array();
-        if ($type != 'string' && $type != 'istring') {
-            trigger_error('Cannot define allowed values for directive whose type is not string',
-                E_USER_ERROR);
-            return;
-        }
-        if ($directive->allowed === true) {
-            $directive->allowed = array();
         }
         foreach ($allowed_values as $value) {
-            $directive->allowed[$value] = true;
+            $def->info[$namespace][$name]->allowed[$value] = true;
         }
-        if ($def->defaults[$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!
-            return;
-        }
-    }
-    
-    /**
-     * Defines a directive alias for backwards compatibility
-     * @static
-     * @param $namespace
-     * @param $name Directive that will be aliased
-     * @param $new_namespace
-     * @param $new_name Directive that the alias will be to
-     */
-    static function defineAlias($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;
-        }
-        $def->info[$namespace][$name] =
-            new HTMLPurifier_ConfigEntity_DirectiveAlias(
-                $new_namespace, $new_name);
     }
     
     /**
      * Validate a variable according to type. Return null if invalid.
      */
-    function validate($var, $type, $allow_null = false) {
+    function validate($var, $type) {
         if (!isset($this->types[$type])) {
             trigger_error('Invalid type', E_USER_ERROR);
             return;
         }
-        if ($allow_null && $var === null) return null;
         switch ($type) {
             case 'mixed':
                 return $var;
             case 'istring':
             case 'string':
-                if (!is_string($var)) break;
+                if (!is_string($var)) return;
                 if ($type === 'istring') $var = strtolower($var);
                 return $var;
             case 'int':
                 if (is_string($var) && ctype_digit($var)) $var = (int) $var;
-                elseif (!is_int($var)) break;
+                elseif (!is_int($var)) return;
                 return $var;
             case 'float':
                 if (is_string($var) && is_numeric($var)) $var = (float) $var;
-                elseif (!is_float($var)) break;
+                elseif (!is_float($var)) return;
                 return $var;
             case 'bool':
                 if (is_int($var) && ($var === 0 || $var === 1)) {
                     $var = (bool) $var;
-                } elseif (is_string($var)) {
+                } elseif (!is_bool($var)) return;
-                    if ($var == 'on' || $var == 'true' || $var == '1') {
-                        $var = true;
-                    } elseif ($var == 'off' || $var == 'false' || $var == '0') {
-                        $var = false;
-                    } else {
-                        break;
-                    }
-                } elseif (!is_bool($var)) break;
                 return $var;
             case 'list':
             case 'hash':
             case 'lookup':
-                if (is_string($var)) {
+                if (!is_array($var)) return;
-                    // simplistic string to array method that only works
-                    // for simple lists of tag names or alphanumeric characters
-                    $var = explode(',',$var);
-                    // remove spaces
-                    foreach ($var as $i => $j) $var[$i] = trim($j);
-                }
-                if (!is_array($var)) break;
                 $keys = array_keys($var);
                 if ($keys === array_keys($keys)) {
                     if ($type == 'list') return $var;
@@ -346,7 +251,7 @@ class HTMLPurifier_ConfigSchema {
                             $new[$key] = true;
                         }
                         return $new;
-                    } else break;
+                    } else return;
                 }
                 if ($type === 'lookup') {
                     foreach ($var as $key => $value) {
@@ -355,13 +260,8 @@ class HTMLPurifier_ConfigSchema {
                 }
                 return $var;
         }
-        $error = new HTMLPurifier_Error();
-        return $error;
     }
     
-    /**
-     * Takes an absolute path and munges it into a more manageable relative path
-     */
     function mungeFilename($filename) {
         $offset = strrpos($filename, 'HTMLPurifier');
         $filename = substr($filename, $offset);
@@ -369,34 +269,18 @@ class HTMLPurifier_ConfigSchema {
         return $filename;
     }
     
-    /**
-     * Checks if var is an HTMLPurifier_Error object
-     */
-    function isError($var) {
-        if (!is_object($var)) return false;
-        if (!($var instanceof HTMLPurifier_Error)) return false;
-        return true;
-    }
 }
 
 /**
  * Base class for configuration entity
  */
-class HTMLPurifier_ConfigEntity {
+class HTMLPurifier_ConfigEntity {}
-    var $class = false;
-}
 
 /**
  * Structure object describing of a namespace
  */
 class HTMLPurifier_ConfigEntity_Namespace extends HTMLPurifier_ConfigEntity {
     
-    function HTMLPurifier_ConfigEntity_Namespace($description = null) {
-        $this->description = $description;
-    }
-    
-    var $class = 'namespace';
-    
     /**
      * String description of what kinds of directives go in this namespace.
      */
@@ -411,21 +295,15 @@ class HTMLPurifier_ConfigEntity_Namespace extends HTMLPurifier_ConfigEntity {
 class HTMLPurifier_ConfigEntity_Directive extends HTMLPurifier_ConfigEntity
 {
     
-    var $class = 'directive';
+    /**
+     * Hash of value aliases, i.e. values that are equivalent.
+     */
+    var $aliases = array();
     
-    function HTMLPurifier_ConfigEntity_Directive(
+    /**
-        $type = null,
+     * Lookup table of allowed values of the element, bool true if all allowed.
-        $descriptions = null,
+     */
-        $allow_null = null,
+    var $allowed = true;
-        $allowed = null,
-        $aliases = null
-    ) {
-        if (        $type !== null)         $this->type = $type;
-        if ($descriptions !== null) $this->descriptions = $descriptions;
-        if (  $allow_null !== null)   $this->allow_null = $allow_null;
-        if (     $allowed !== null)      $this->allowed = $allowed;
-        if (     $aliases !== null)      $this->aliases = $aliases;
-    }
     
     /**
      * Allowed type of the directive. Values are:
@@ -440,29 +318,12 @@ class HTMLPurifier_ConfigEntity_Directive extends HTMLPurifier_ConfigEntity
      *      - mixed (anything goes)
      */
     var $type = 'mixed';
-    
     /**
      * Plaintext descriptions of the configuration entity is. Organized by
      * file and line number, so multiple descriptions are allowed.
      */
     var $descriptions = array();
     
-    /**
-     * Is null allowed? Has no effect for mixed type.
-     * @bool
-     */
-    var $allow_null = false;
-    
-    /**
-     * Lookup table of allowed values of the element, bool true if all allowed.
-     */
-    var $allowed = true;
-    
-    /**
-     * Hash of value aliases, i.e. values that are equivalent.
-     */
-    var $aliases = array();
-    
     /**
      * Adds a description to the array
      */
@@ -473,26 +334,4 @@ class HTMLPurifier_ConfigEntity_Directive extends HTMLPurifier_ConfigEntity
     
 }
 
-/**
+?>
- * Structure object describing a directive alias
- */
-class HTMLPurifier_ConfigEntity_DirectiveAlias extends HTMLPurifier_ConfigEntity
-{
-    var $class = 'alias';
-    
-    /**
-     * Namespace being aliased to
-     */
-    var $namespace;
-    /**
-     * Directive being aliased to
-     */
-    var $name;
-    
-    function HTMLPurifier_ConfigEntity_DirectiveAlias($namespace, $name) {
-        $this->namespace = $namespace;
-        $this->name = $name;
-    }
-}
-
-?>

library/HTMLPurifier/Context.php

@@ -1,76 +0,0 @@
-<?php
-
-/**
- * Registry object that contains information about the current context.
- */
-class HTMLPurifier_Context
-{
-    
-    /**
-     * Private array that stores the references.
-     * @private
-     */
-    var $_storage = array();
-    
-    /**
-     * Registers a variable into the context.
-     * @param $name String name
-     * @param $ref Variable to be registered
-     */
-    function register($name, &$ref) {
-        if (isset($this->_storage[$name])) {
-            trigger_error('Name collision, cannot re-register',
-                          E_USER_ERROR);
-            return;
-        }
-        $this->_storage[$name] =& $ref;
-    }
-    
-    /**
-     * Retrieves a variable reference from the context.
-     * @param $name String name
-     */
-    function &get($name) {
-        if (!isset($this->_storage[$name])) {
-            trigger_error('Attempted to retrieve non-existent variable',
-                          E_USER_ERROR);
-            $var = null; // so we can return by reference
-            return $var;
-        }
-        return $this->_storage[$name];
-    }
-    
-    /**
-     * Destorys a variable in the context.
-     * @param $name String name
-     */
-    function destroy($name) {
-        if (!isset($this->_storage[$name])) {
-            trigger_error('Attempted to destroy non-existent variable',
-                          E_USER_ERROR);
-            return;
-        }
-        unset($this->_storage[$name]);
-    }
-    
-    /**
-     * Checks whether or not the variable exists.
-     * @param $name String name
-     */
-    function exists($name) {
-        return isset($this->_storage[$name]);
-    }
-    
-    /**
-     * Loads a series of variables from an associative array
-     * @param $context_array Assoc array of variables to load
-     */
-    function loadArray(&$context_array) {
-        foreach ($context_array as $key => $discard) {
-            $this->register($key, $context_array[$key]);
-        }
-    }
-    
-}
-
-?>

library/HTMLPurifier/Encoder.php

@@ -6,29 +6,15 @@ HTMLPurifier_ConfigSchema::define(
     'Core', 'Encoding', 'utf-8', 'istring', 
     'If for some reason you are unable to convert all webpages to UTF-8, '. 
     'you can use this directive as a stop-gap compatibility change to '. 
-    'let HTML Purifier deal with non UTF-8 input.  This technique has '. 
+    'let HTMLPurifier deal with non UTF-8 input.  This technique has '. 
     'notable deficiencies: absolutely no characters outside of the selected '. 
     'character encoding will be preserved, not even the ones that have '. 
     'been ampersand escaped (this is due to a UTF-8 specific <em>feature</em> '.
     'that automatically resolves all entities), making it pretty useless '.
-    'for anything except the most I18N-blind applications, although '.
+    'for anything except the most I18N-blind applications.  This directive '.
-    '%Core.EscapeNonASCIICharacters offers fixes this trouble with '.
-    'another tradeoff. This directive '.
     'only accepts ISO-8859-1 if iconv is not enabled.'
 );
 
-HTMLPurifier_ConfigSchema::define(
-    'Core', 'EscapeNonASCIICharacters', false, 'bool',
-    'This directive overcomes a deficiency in %Core.Encoding by blindly '.
-    'converting all non-ASCII characters into decimal numeric entities before '.
-    'converting it to its native encoding. This means that even '.
-    'characters that can be expressed in the non-UTF-8 encoding will '.
-    'be entity-ized, which can be a real downer for encodings like Big5. '.
-    'It also assumes that the ASCII repetoire is available, although '.
-    'this is the case for almost all encodings. Anyway, use UTF-8! This '.
-    'directive has been available since 1.4.0.'
-);
-
 if ( !function_exists('iconv') ) {
     // only encodings with native PHP support
     HTMLPurifier_ConfigSchema::defineAllowedValues(
@@ -52,25 +38,16 @@ HTMLPurifier_ConfigSchema::define(
 
 /**
  * A UTF-8 specific character encoder that handles cleaning and transforming.
- * @note All functions in this class should be static.
  */
 class HTMLPurifier_Encoder
 {
     
-    /**
-     * Constructor throws fatal error if you attempt to instantiate class
-     */
-    function HTMLPurifier_Encoder() {
-        trigger_error('Cannot instantiate encoder, call methods statically', E_USER_ERROR);
-    }
-    
     /**
      * Cleans a UTF-8 string for well-formedness and SGML validity
      * 
      * It will parse according to UTF-8 and return a valid UTF8 string, with
      * non-SGML codepoints excluded.
      * 
-     * @static
      * @note Just for reference, the non-SGML code points are 0 to 31 and
      *       127 to 159, inclusive.  However, we allow code points 9, 10
      *       and 13, which are the tab, line feed and carriage return
@@ -90,7 +67,7 @@ class HTMLPurifier_Encoder
      *       would need that, and I'm probably not going to implement them.
      *       Once again, PHP 6 should solve all our problems.
      */
-    static function cleanUTF8($str, $force_php = false) {
+    function cleanUTF8($str, $force_php = false) {
         
         static $non_sgml_chars = array();
         if (empty($non_sgml_chars)) {
@@ -248,32 +225,8 @@ class HTMLPurifier_Encoder
     
     /**
      * Translates a Unicode codepoint into its corresponding UTF-8 character.
-     * @static
-     * @note Based on Feyd's function at
-     *       <http://forums.devnetwork.net/viewtopic.php?p=191404#191404>,
-     *       which is in public domain.
-     * @note While we're going to do code point parsing anyway, a good
-     *       optimization would be to refuse to translate code points that
-     *       are non-SGML characters.  However, this could lead to duplication.
-     * @note This is very similar to the unichr function in
-     *       maintenance/generate-entity-file.php (although this is superior,
-     *       due to its sanity checks).
      */
-    
+    function unichr($code) {
-    // +----------+----------+----------+----------+
-    // | 33222222 | 22221111 | 111111   |          |
-    // | 10987654 | 32109876 | 54321098 | 76543210 | bit
-    // +----------+----------+----------+----------+
-    // |          |          |          | 0xxxxxxx | 1 byte 0x00000000..0x0000007F
-    // |          |          | 110yyyyy | 10xxxxxx | 2 byte 0x00000080..0x000007FF
-    // |          | 1110zzzz | 10yyyyyy | 10xxxxxx | 3 byte 0x00000800..0x0000FFFF
-    // | 11110www | 10wwzzzz | 10yyyyyy | 10xxxxxx | 4 byte 0x00010000..0x0010FFFF
-    // +----------+----------+----------+----------+
-    // | 00000000 | 00011111 | 11111111 | 11111111 | Theoretical upper limit of legal scalars: 2097151 (0x001FFFFF)
-    // | 00000000 | 00010000 | 11111111 | 11111111 | Defined upper limit of legal scalar codes
-    // +----------+----------+----------+----------+ 
-    
-    static function unichr($code) {
         if($code > 1114111 or $code < 0 or
           ($code >= 55296 and $code <= 57343) ) {
             // bits are set outside the "valid" range as defined
@@ -312,9 +265,8 @@ class HTMLPurifier_Encoder
     
     /**
      * Converts a string to UTF-8 based on configuration.
-     * @static
      */
-    static function convertToUTF8($str, $config, &$context) {
+    function convertToUTF8($str, $config) {
         static $iconv = null;
         if ($iconv === null) $iconv = function_exists('iconv');
         $encoding = $config->get('Core', 'Encoding');
@@ -324,77 +276,23 @@ class HTMLPurifier_Encoder
         } elseif ($encoding === 'iso-8859-1') {
             return @utf8_encode($str);
         }
-        trigger_error('Encoding not supported', E_USER_ERROR);
     }
     
     /**
      * Converts a string from UTF-8 based on configuration.
-     * @static
      * @note Currently, this is a lossy conversion, with unexpressable
      *       characters being omitted.
      */
-    static function convertFromUTF8($str, $config, &$context) {
+    function convertFromUTF8($str, $config) {
         static $iconv = null;
         if ($iconv === null) $iconv = function_exists('iconv');
         $encoding = $config->get('Core', 'Encoding');
         if ($encoding === 'utf-8') return $str;
-        if ($config->get('Core', 'EscapeNonASCIICharacters')) {
-            $str = HTMLPurifier_Encoder::convertToASCIIDumbLossless($str);
-        }
         if ($iconv && !$config->get('Test', 'ForceNoIconv')) {
             return @iconv('utf-8', $encoding . '//IGNORE', $str);
         } elseif ($encoding === 'iso-8859-1') {
             return @utf8_decode($str);
         }
-        trigger_error('Encoding not supported', E_USER_ERROR);
-    }
-    
-    /**
-     * Lossless (character-wise) conversion of HTML to ASCII
-     * @static
-     * @param $str UTF-8 string to be converted to ASCII
-     * @returns ASCII encoded string with non-ASCII character entity-ized
-     * @warning Adapted from MediaWiki, claiming fair use: this is a common
-     *       algorithm. If you disagree with this license fudgery,
-     *       implement it yourself.
-     * @note Uses decimal numeric entities since they are best supported.
-     * @note This is a DUMB function: it has no concept of keeping
-     *       character entities that the projected character encoding
-     *       can allow. We could possibly implement a smart version
-     *       but that would require it to also know which Unicode
-     *       codepoints the charset supported (not an easy task).
-     * @note Sort of with cleanUTF8() but it assumes that $str is
-     *       well-formed UTF-8
-     */
-    static function convertToASCIIDumbLossless($str) {
-        $bytesleft = 0;
-        $result = '';
-        $working = 0;
-        $len = strlen($str);
-        for( $i = 0; $i < $len; $i++ ) {
-            $bytevalue = ord( $str[$i] );
-            if( $bytevalue <= 0x7F ) { //0xxx xxxx
-                $result .= chr( $bytevalue );
-                $bytesleft = 0;
-            } elseif( $bytevalue <= 0xBF ) { //10xx xxxx
-                $working = $working << 6;
-                $working += ($bytevalue & 0x3F);
-                $bytesleft--;
-                if( $bytesleft <= 0 ) {
-                    $result .= "&#" . $working . ";";
-                }
-            } elseif( $bytevalue <= 0xDF ) { //110x xxxx
-                $working = $bytevalue & 0x1F;
-                $bytesleft = 1;
-            } elseif( $bytevalue <= 0xEF ) { //1110 xxxx
-                $working = $bytevalue & 0x0F;
-                $bytesleft = 2;
-            } else { //1111 0xxx
-                $working = $bytevalue & 0x07;
-                $bytesleft = 3;
-            }
-        }
-        return $result;
     }
     
     

library/HTMLPurifier/EntityLookup.php

@@ -19,17 +19,16 @@ class HTMLPurifier_EntityLookup {
      */
     function setup($file = false) {
         if (!$file) {
-            $file = dirname(__FILE__) . '/EntityLookup/entities.ser';
+            $file = dirname(__FILE__) . '/EntityLookup/data.txt';
         }
         $this->table = unserialize(file_get_contents($file));
     }
     
     /**
      * Retrieves sole instance of the object.
-     * @static
      * @param Optional prototype of custom lookup table to overload with.
      */
-    static function instance($prototype = false) {
+    function instance($prototype = false) {
         // no references, since PHP doesn't copy unless modified
         static $instance = null;
         if ($prototype) {

library/HTMLPurifier/EntityParser.php

@@ -3,10 +3,6 @@
 require_once 'HTMLPurifier/EntityLookup.php';
 require_once 'HTMLPurifier/Encoder.php';
 
-// if want to implement error collecting here, we'll need to use some sort
-// of global data (probably trigger_error) because it's impossible to pass
-// $config or $context to the callback functions.
-
 /**
  * Handles referencing and derefencing character entities
  */
@@ -76,12 +72,37 @@ class HTMLPurifier_EntityParser
      * 
      * @warning Though this is public in order to let the callback happen,
      *          calling it directly is not recommended.
+     * @note Based on Feyd's function at
+     *       <http://forums.devnetwork.net/viewtopic.php?p=191404#191404>,
+     *       which is in public domain.
+     * @note While we're going to do code point parsing anyway, a good
+     *       optimization would be to refuse to translate code points that
+     *       are non-SGML characters.  However, this could lead to duplication.
+     * @note This function is heavily intimate with the inner workings of
+     *       UTF-8 and would also be well suited in the Encoder class (or at
+     *       least deferring some processing to it).  This is also very
+     *       similar to the unichr function in
+     *       maintenance/generate-entity-file.php (although this is superior,
+     *       due to its sanity checks).
      * @param $matches  PCRE matches array, with 0 the entire match, and
      *                  either index 1, 2 or 3 set with a hex value, dec value,
      *                  or string (respectively).
      * @returns Replacement string.
      */
     
+    // +----------+----------+----------+----------+
+    // | 33222222 | 22221111 | 111111   |          |
+    // | 10987654 | 32109876 | 54321098 | 76543210 | bit
+    // +----------+----------+----------+----------+
+    // |          |          |          | 0xxxxxxx | 1 byte 0x00000000..0x0000007F
+    // |          |          | 110yyyyy | 10xxxxxx | 2 byte 0x00000080..0x000007FF
+    // |          | 1110zzzz | 10yyyyyy | 10xxxxxx | 3 byte 0x00000800..0x0000FFFF
+    // | 11110www | 10wwzzzz | 10yyyyyy | 10xxxxxx | 4 byte 0x00010000..0x0010FFFF
+    // +----------+----------+----------+----------+
+    // | 00000000 | 00011111 | 11111111 | 11111111 | Theoretical upper limit of legal scalars: 2097151 (0x001FFFFF)
+    // | 00000000 | 00010000 | 11111111 | 11111111 | Defined upper limit of legal scalar codes
+    // +----------+----------+----------+----------+ 
+    
     function nonSpecialEntityCallback($matches) {
         // replaces all but big five
         $entity = $matches[0];

library/HTMLPurifier/Error.php

@@ -1,8 +0,0 @@
-<?php
-
-/**
- * Return object from functions that signifies error when null doesn't cut it
- */
-class HTMLPurifier_Error {}
-
-?>

library/HTMLPurifier/Filter.php

@@ -1,39 +0,0 @@
-<?php
-
-/**
- * Represents a pre or post processing filter on HTML Purifier's output
- * 
- * Sometimes, a little ad-hoc fixing of HTML has to be done before
- * it gets sent through HTML Purifier: you can use filters to acheive
- * this effect. For instance, YouTube videos can be preserved using
- * this manner. You could have used a decorator for this task, but
- * PHP's support for them is not terribly robust, so we're going
- * to just loop through the filters.
- * 
- * Filters should be exited first in, last out. If there are three filters,
- * named 1, 2 and 3, the order of execution should go 1->preFilter,
- * 2->preFilter, 3->preFilter, purify, 3->postFilter, 2->postFilter,
- * 1->postFilter.
- */
-
-class HTMLPurifier_Filter
-{
-    
-    /**
-     * Name of the filter for identification purposes
-     */
-    var $name;
-    
-    /**
-     * Pre-processor function, handles HTML before HTML Purifier 
-     */
-    function preFilter($html, $config, &$context) {}
-    
-    /**
-     * Post-processor function, handles HTML after HTML Purifier
-     */
-    function postFilter($html, $config, &$context) {}
-    
-}
-
-?>

library/HTMLPurifier/Filter/YouTube.php

@@ -1,34 +0,0 @@
-<?php
-
-require_once 'HTMLPurifier/Filter.php';
-
-class HTMLPurifier_Filter_YouTube extends HTMLPurifier_Filter
-{
-    
-    var $name = 'YouTube preservation';
-    
-    function preFilter($html, $config, &$context) {
-        $pre_regex = '#<object[^>]+>.+?'.
-            'http://www.youtube.com/v/([A-Za-z0-9\-_]+).+?</object>#';
-        $pre_replace = '<span class="youtube-embed">\1</span>';
-        return preg_replace($pre_regex, $pre_replace, $html);
-    }
-    
-    function postFilter($html, $config, &$context) {
-        $post_regex = '#<span class="youtube-embed">([A-Za-z0-9\-_]+)</span>#';
-        $post_replace = '<object width="425" height="350" '.
-            'data="http://www.youtube.com/v/\1">'.
-            '<param name="movie" value="http://www.youtube.com/v/\1"></param>'.
-            '<param name="wmode" value="transparent"></param>'.
-            '<!--[if IE]>'.
-            '<embed src="http://www.youtube.com/v/\1"'.
-            'type="application/x-shockwave-flash"'.
-            'wmode="transparent" width="425" height="350" />'.
-            '<![endif]-->'.
-            '</object>';
-        return preg_replace($post_regex, $post_replace, $html);
-    }
-    
-}
-
-?>

library/HTMLPurifier/Generator.php

@@ -1,5 +1,7 @@
 <?php
 
+// pretty-printing with indentation would be pretty cool
+
 require_once 'HTMLPurifier/Lexer.php';
 
 HTMLPurifier_ConfigSchema::define(
@@ -50,7 +52,6 @@ class HTMLPurifier_Generator
     
     /**
      * Bool cache of %Core.XHTML
-     * @private
      */
     var $_xhtml = true;
     
@@ -59,8 +60,9 @@ class HTMLPurifier_Generator
      * @param $tokens Array of HTMLPurifier_Token
      * @param $config HTMLPurifier_Config object
      * @return Generated HTML
+     * @note Only unit tests may omit configuration: internals MUST pass config
      */
-    function generateFromTokens($tokens, $config, &$context) {
+    function generateFromTokens($tokens, $config = null) {
         $html = '';
         if (!$config) $config = HTMLPurifier_Config::createDefault();
         $this->_clean_utf8 = $config->get('Core', 'CleanUTF8DuringGeneration');
@@ -104,14 +106,14 @@ class HTMLPurifier_Generator
     function generateFromToken($token) {
         if (!isset($token->type)) return '';
         if ($token->type == 'start') {
-            $attr = $this->generateAttributes($token->attr);
+            $attr = $this->generateAttributes($token->attributes);
             return '<' . $token->name . ($attr ? ' ' : '') . $attr . '>';
             
         } elseif ($token->type == 'end') {
             return '</' . $token->name . '>';
             
         } elseif ($token->type == 'empty') {
-            $attr = $this->generateAttributes($token->attr);
+            $attr = $this->generateAttributes($token->attributes);
              return '<' . $token->name . ($attr ? ' ' : '') . $attr .
                 ( $this->_xhtml ? ' /': '' )
                 . '>';

library/HTMLPurifier/HTMLDefinition.php

@@ -18,86 +18,10 @@ require_once 'HTMLPurifier/AttrTransform.php';
     require_once 'HTMLPurifier/AttrTransform/BdoDir.php';
     require_once 'HTMLPurifier/AttrTransform/ImgRequired.php';
 require_once 'HTMLPurifier/ChildDef.php';
-    require_once 'HTMLPurifier/ChildDef/Chameleon.php';
-    require_once 'HTMLPurifier/ChildDef/Empty.php';
-    require_once 'HTMLPurifier/ChildDef/Required.php';
-    require_once 'HTMLPurifier/ChildDef/Optional.php';
-    require_once 'HTMLPurifier/ChildDef/Table.php';
-    require_once 'HTMLPurifier/ChildDef/StrictBlockquote.php';
 require_once 'HTMLPurifier/Generator.php';
 require_once 'HTMLPurifier/Token.php';
 require_once 'HTMLPurifier/TagTransform.php';
 
-HTMLPurifier_ConfigSchema::define(
-    'HTML', 'EnableAttrID', false, 'bool',
-    'Allows the ID attribute in HTML.  This is disabled by default '.
-    'due to the fact that without proper configuration user input can '.
-    'easily break the validation of a webpage by specifying an ID that is '.
-    'already on the surrounding HTML.  If you don\'t mind throwing caution to '.
-    'the wind, enable this directive, but I strongly recommend you also '.
-    'consider blacklisting IDs you use (%Attr.IDBlacklist) or prefixing all '.
-    'user supplied IDs (%Attr.IDPrefix).  This directive has been available '.
-    'since 1.2.0, and when set to true reverts to the behavior of pre-1.2.0 '.
-    'versions.'
-);
-
-HTMLPurifier_ConfigSchema::define(
-    'HTML', 'Strict', false, 'bool',
-    'Determines whether or not to use Transitional (loose) or Strict rulesets. '.
-    'This directive has been available since 1.3.0.'
-);
-
-HTMLPurifier_ConfigSchema::define(
-    'HTML', 'BlockWrapper', 'p', 'string',
-    'String name of element to wrap inline elements that are inside a block '.
-    'context.  This only occurs in the children of blockquote in strict mode. '.
-    'Example: by default value, <code>&lt;blockquote&gt;Foo&lt;/blockquote&gt;</code> '.
-    'would become <code>&lt;blockquote&gt;&lt;p&gt;Foo&lt;/p&gt;&lt;/blockquote&gt;</code>. The '.
-    '<code>&lt;p&gt;</code> tags can be replaced '.
-    'with whatever you desire, as long as it is a block level element. '.
-    'This directive has been available since 1.3.0.'
-);
-
-HTMLPurifier_ConfigSchema::define(
-    'HTML', 'Parent', 'div', 'string',
-    'String name of element that HTML fragment passed to library will be '.
-    'inserted in.  An interesting variation would be using span as the '.
-    'parent element, meaning that only inline tags would be allowed. '.
-    'This directive has been available since 1.3.0.'
-);
-
-HTMLPurifier_ConfigSchema::define(
-    'HTML', 'AllowedElements', null, 'lookup/null',
-    'If HTML Purifier\'s tag set is unsatisfactory for your needs, you '.
-    'can overload it with your own list of tags to allow.  Note that this '.
-    'method is subtractive: it does its job by taking away from HTML Purifier '.
-    'usual feature set, so you cannot add a tag that HTML Purifier never '.
-    'supported in the first place (like embed, form or head).  If you change this, you '.
-    'probably also want to change %HTML.AllowedAttributes. '.
-    '<strong>Warning:</strong> If another directive conflicts with the '.
-    'elements here, <em>that</em> directive will win and override. '.
-    'This directive has been available since 1.3.0.'
-);
-
-HTMLPurifier_ConfigSchema::define(
-    'HTML', 'AllowedAttributes', null, 'lookup/null',
-    'IF HTML Purifier\'s attribute set is unsatisfactory, overload it! '.
-    'The syntax is \'tag.attr\' or \'*.attr\' for the global attributes '.
-    '(style, id, class, dir, lang, xml:lang).'.
-    '<strong>Warning:</strong> If another directive conflicts with the '.
-    'elements here, <em>that</em> directive will win and override. For '.
-    'example, %HTML.EnableAttrID will take precedence over *.id in this '.
-    'directive.  You must set that directive to true before you can use '.
-    'IDs at all. This directive has been available since 1.3.0.'
-);
-
-HTMLPurifier_ConfigSchema::define(
-    'Attr', 'DisableURI', 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.'
-);
-
 /**
  * Defines the purified HTML type with large amounts of objects.
  * 
@@ -132,24 +56,11 @@ class HTMLPurifier_HTMLDefinition
     
     /**
      * String name of parent element HTML will be going into.
+     * @todo Allow this to be overloaded by user config
      * @public
      */
     var $info_parent = 'div';
     
-    /**
-     * Definition for parent element, allows parent element to be a
-     * tag that's not allowed inside the HTML fragment.
-     * @public
-     */
-    var $info_parent_def;
-    
-    /**
-     * String name of element used to wrap inline elements in block context
-     * @note This is rarely used except for BLOCKQUOTEs in strict mode
-     * @public
-     */
-    var $info_block_wrapper = 'p';
-    
     /**
      * Associative array of deprecated tag name to HTMLPurifier_TagTransform
      * @public
@@ -168,25 +79,14 @@ class HTMLPurifier_HTMLDefinition
      */
     var $info_attr_transform_post = array();
     
-    /**
-     * Lookup table of flow elements
-     * @public
-     */
-    var $info_flow_elements = array();
-    
-    /**
-     * Boolean is a strict definition?
-     * @public
-     */
-    var $strict;
-    
     /**
      * Initializes the definition, the meat of the class.
      */
     function setup($config) {
         
-        // some cached config values
+        // emulates the structure of the DTD
-        $this->strict = $config->get('HTML', 'Strict');
+        // these are condensed, however, with bad stuff taken out
+        // screening process was done by hand
         
         //////////////////////////////////////////////////////////////////////
         // info[] : initializes the definition objects
@@ -198,19 +98,13 @@ class HTMLPurifier_HTMLDefinition
             array(
                 'ins', 'del', 'blockquote', 'dd', 'li', 'div', 'em', 'strong',
                 'dfn', 'code', 'samp', 'kbd', 'var', 'cite', 'abbr', 'acronym',
-                'q', 'sub', 'tt', 'sup', 'i', 'b', 'big', 'small',
+                'q', 'sub', 'tt', 'sup', 'i', 'b', 'big', 'small', 'u', 's',
-                'bdo', 'span', 'dt', 'p', 'h1', 'h2', 'h3', 'h4',
+                'strike', 'bdo', 'span', 'dt', 'p', 'h1', 'h2', 'h3', 'h4',
                 'h5', 'h6', 'ol', 'ul', 'dl', 'address', 'img', 'br', 'hr',
                 'pre', 'a', 'table', 'caption', 'thead', 'tfoot', 'tbody',
                 'colgroup', 'col', 'td', 'th', 'tr'
             );
         
-        if (!$this->strict) {
-            $allowed_tags[] = 'u';
-            $allowed_tags[] = 's';
-            $allowed_tags[] = 'strike';
-        }
-        
         foreach ($allowed_tags as $tag) {
             $this->info[$tag] = new HTMLPurifier_ElementDef();
         }
@@ -218,10 +112,6 @@ class HTMLPurifier_HTMLDefinition
         //////////////////////////////////////////////////////////////////////
         // info[]->child : defines allowed children for elements
         
-        // emulates the structure of the DTD
-        // however, these are condensed, with bad stuff taken out
-        // screening process was done by hand
-        
         // entities: prefixed with e_ and _ replaces . from DTD
         // double underlines are entities we made up
         
@@ -245,9 +135,11 @@ class HTMLPurifier_HTMLDefinition
         $e_phrase_basic = 'em | strong | dfn | code | q | samp | kbd | var'.
           ' | cite | abbr | acronym';
         $e_phrase = "$e_phrase_basic | $e_phrase_extra";
+        $e_inline_forms = ''; // humor the dtd
         $e_misc_inline = 'ins | del';
         $e_misc = "$e_misc_inline";
-        $e_inline = "a | $e_special | $e_fontstyle | $e_phrase";
+        $e_inline = "a | $e_special | $e_fontstyle | $e_phrase".
+          " | $e_inline_forms";
         // pseudo-property we created for convenience, see later on
         $e__inline = "#PCDATA | $e_inline | $e_misc_inline";
         // note the casing
@@ -256,14 +148,14 @@ class HTMLPurifier_HTMLDefinition
         $e_lists = 'ul | ol | dl';
         $e_blocktext = 'pre | hr | blockquote | address';
         $e_block = "p | $e_heading | div | $e_lists | $e_blocktext | table";
-        $e_Block = new HTMLPurifier_ChildDef_Optional($e_block);
         $e__flow = "#PCDATA | $e_block | $e_inline | $e_misc";
         $e_Flow = new HTMLPurifier_ChildDef_Optional($e__flow);
         $e_a_content = new HTMLPurifier_ChildDef_Optional("#PCDATA".
-          " | $e_special | $e_fontstyle | $e_phrase | $e_misc_inline");
+          " | $e_special | $e_fontstyle | $e_phrase | $e_inline_forms".
+          " | $e_misc_inline");
         $e_pre_content = new HTMLPurifier_ChildDef_Optional("#PCDATA | a".
           " | $e_special_basic | $e_fontstyle_basic | $e_phrase_basic".
-          " | $e_misc_inline");
+          " | $e_inline_forms | $e_misc_inline");
         $e_form_content = new HTMLPurifier_ChildDef_Optional('');//unused
         $e_form_button_content = new HTMLPurifier_ChildDef_Optional('');//unused
         
@@ -271,16 +163,11 @@ class HTMLPurifier_HTMLDefinition
         $this->info['del']->child =
             new HTMLPurifier_ChildDef_Chameleon($e__inline, $e__flow);
         
+        $this->info['blockquote']->child=
         $this->info['dd']->child  =
         $this->info['li']->child  =
         $this->info['div']->child = $e_Flow;
         
-        if ($this->strict) {
-            $this->info['blockquote']->child = new HTMLPurifier_ChildDef_StrictBlockquote();
-        } else {
-            $this->info['blockquote']->child = $e_Flow;
-        }
-        
         $this->info['caption']->child   = 
         $this->info['em']->child   =
         $this->info['strong']->child    =
@@ -300,6 +187,9 @@ class HTMLPurifier_HTMLDefinition
         $this->info['b']->child    =
         $this->info['big']->child  =
         $this->info['small']->child=
+        $this->info['u']->child    =
+        $this->info['s']->child    =
+        $this->info['strike']->child    =
         $this->info['bdo']->child  =
         $this->info['span']->child =
         $this->info['dt']->child   =
@@ -311,25 +201,15 @@ class HTMLPurifier_HTMLDefinition
         $this->info['h5']->child   = 
         $this->info['h6']->child   = $e_Inline;
         
-        if (!$this->strict) {
-            $this->info['u']->child    =
-            $this->info['s']->child    =
-            $this->info['strike']->child    = $e_Inline;
-        }
-        
         // the only three required definitions, besides custom table code
         $this->info['ol']->child   =
         $this->info['ul']->child   = new HTMLPurifier_ChildDef_Required('li');
         
         $this->info['dl']->child   = new HTMLPurifier_ChildDef_Required('dt|dd');
         
-        if ($this->strict) {
+        $this->info['address']->child =
-            $this->info['address']->child = $e_Inline;
+          new HTMLPurifier_ChildDef_Optional("#PCDATA | p | $e_inline".
-        } else {
+              " | $e_misc_inline");
-            $this->info['address']->child =
-              new HTMLPurifier_ChildDef_Optional("#PCDATA | p | $e_inline".
-                  " | $e_misc_inline");
-        }
         
         $this->info['img']->child  =
         $this->info['br']->child   =
@@ -356,21 +236,16 @@ class HTMLPurifier_HTMLDefinition
         // info[]->type : defines the type of the element (block or inline)
         
         // reuses $e_Inline and $e_Block
-        foreach ($e_Inline->elements as $name => $bool) {
+        
-            if ($name == '#PCDATA') continue;
+        foreach ($e_Inline->elements as $name) {
-            if (!isset($this->info[$name])) continue;
             $this->info[$name]->type = 'inline';
         }
         
-        foreach ($e_Block->elements as $name => $bool) {
+        $e_Block = new HTMLPurifier_ChildDef_Optional($e_block);
-            if (!isset($this->info[$name])) continue;
+        foreach ($e_Block->elements as $name) {
             $this->info[$name]->type = 'block';
         }
         
-        foreach ($e_Flow->elements as $name => $bool) {
-            $this->info_flow_elements[$name] = true;
-        }
-        
         //////////////////////////////////////////////////////////////////////
         // info[]->excludes : defines elements that aren't allowed in here
         
@@ -396,6 +271,7 @@ class HTMLPurifier_HTMLDefinition
         // which manually override these in their local definitions
         $this->info_global_attr = array(
             // core attrs
+            'id'    => new HTMLPurifier_AttrDef_ID(),
             'class' => new HTMLPurifier_AttrDef_Class(),
             'title' => $e_Text,
             'style' => new HTMLPurifier_AttrDef_CSS(),
@@ -405,10 +281,6 @@ class HTMLPurifier_HTMLDefinition
             'xml:lang' => new HTMLPurifier_AttrDef_Lang(),
             );
         
-        if ($config->get('HTML', 'EnableAttrID')) {
-            $this->info_global_attr['id'] = new HTMLPurifier_AttrDef_ID();
-        }
-        
         // required attribute stipulation handled in attribute transformation
         $this->info['bdo']->attr = array(); // nothing else
         
@@ -460,23 +332,14 @@ class HTMLPurifier_HTMLDefinition
         $this->info['td']->attr['colspan'] =
         $this->info['th']->attr['colspan'] = $e__NumberSpan;
         
-        if (!$config->get('Attr', 'DisableURI')) {
+        $e_URI = new HTMLPurifier_AttrDef_URI();
-            $e_URI = new HTMLPurifier_AttrDef_URI();
+        $this->info['a']->attr['href'] =
-            $this->info['a']->attr['href'] =
+        $this->info['img']->attr['longdesc'] =
-            $this->info['img']->attr['longdesc'] =
+        $this->info['img']->attr['src'] =
-            $this->info['del']->attr['cite'] =
+        $this->info['del']->attr['cite'] =
-            $this->info['ins']->attr['cite'] =
+        $this->info['ins']->attr['cite'] =
-            $this->info['blockquote']->attr['cite'] =
+        $this->info['blockquote']->attr['cite'] =
-            $this->info['q']->attr['cite'] = $e_URI;
+        $this->info['q']->attr['cite'] = $e_URI;
-            
-            // URI that causes HTTP request
-            $this->info['img']->attr['src'] = new HTMLPurifier_AttrDef_URI(true);
-        }
-        
-        if (!$this->strict) {
-            $this->info['li']->attr['value'] = new HTMLPurifier_AttrDef_Integer();
-            $this->info['ol']->attr['start'] = new HTMLPurifier_AttrDef_Integer();
-        }
         
         //////////////////////////////////////////////////////////////////////
         // info_tag_transform : transformations of tags
@@ -534,60 +397,6 @@ class HTMLPurifier_HTMLDefinition
         
         $this->info_attr_transform_post[] = new HTMLPurifier_AttrTransform_Lang();
         
-        // protect against stdclasses floating around
-        foreach ($this->info as $key => $obj) {
-            if ($obj instanceof stdClass) {
-                unset($this->info[$key]);
-            }
-        }
-        
-        //////////////////////////////////////////////////////////////////////
-        // info_block_wrapper : wraps inline elements in block context
-        
-        $block_wrapper = $config->get('HTML', 'BlockWrapper');
-        if (isset($e_Block->elements[$block_wrapper])) {
-            $this->info_block_wrapper = $block_wrapper;
-        } else {
-            trigger_error('Cannot use non-block element as block wrapper.',
-                E_USER_ERROR);
-        }
-        
-        //////////////////////////////////////////////////////////////////////
-        // info_parent : parent element of the HTML fragment
-        
-        $parent = $config->get('HTML', 'Parent');
-        if (isset($this->info[$parent])) {
-            $this->info_parent = $parent;
-        } else {
-            trigger_error('Cannot use unrecognized element as parent.',
-                E_USER_ERROR);
-        }
-        $this->info_parent_def = $this->info[$this->info_parent];
-        
-        //////////////////////////////////////////////////////////////////////
-        // %HTML.Allowed(Elements|Attributes) : cut non-allowed elements
-        
-        $allowed_elements = $config->get('HTML', 'AllowedElements');
-        if (is_array($allowed_elements)) {
-            foreach ($this->info as $name => $d) {
-                if(!isset($allowed_elements[$name])) unset($this->info[$name]);
-            }
-        }
-        $allowed_attributes = $config->get('HTML', 'AllowedAttributes');
-        if (is_array($allowed_attributes)) {
-            foreach ($this->info_global_attr as $attr_key => $info) {
-                if (!isset($allowed_attributes["*.$attr_key"])) {
-                    unset($this->info_global_attr[$attr_key]);
-                }
-            }
-            foreach ($this->info as $tag => $info) {
-                foreach ($info->attr as $attr => $attr_info) {
-                    if (!isset($allowed_attributes["$tag.$attr"])) {
-                        unset($this->info[$tag]->attr[$attr]);
-                    }
-                }
-            }
-        }
     }
     
     function setAttrForTableElements($attr, $def) {
@@ -653,4 +462,4 @@ class HTMLPurifier_ElementDef
     
 }
 
-?>
+?>

library/HTMLPurifier/IDAccumulator.php

@@ -3,9 +3,6 @@
 /**
  * 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.
  */
 class HTMLPurifier_IDAccumulator
 {

library/HTMLPurifier/Lexer.php

@@ -56,6 +56,7 @@ class HTMLPurifier_Lexer
 {
     
     function HTMLPurifier_Lexer() {
+        $this->_encoder = new HTMLPurifier_Encoder();
         $this->_entity_parser = new HTMLPurifier_EntityParser();
     }
     
@@ -113,13 +114,15 @@ class HTMLPurifier_Lexer
         return $string;
     }
     
+    var $_encoder;
+    
     /**
      * Lexes an HTML string into tokens.
      * 
      * @param $string String HTML.
      * @return HTMLPurifier_Token array representation of HTML.
      */
-    function tokenizeHTML($string, $config, &$context) {
+    function tokenizeHTML($string, $config = null) {
         trigger_error('Call to abstract class', E_USER_ERROR);
     }
     
@@ -135,8 +138,6 @@ class HTMLPurifier_Lexer
      * default with your own implementation.  A copy/reference of the prototype
      * lexer will now be returned when you request a new lexer.
      * 
-     * @static
-     * 
      * @note
      * Though it is possible to call this factory method from subclasses,
      * such usage is not recommended.
@@ -144,14 +145,14 @@ class HTMLPurifier_Lexer
      * @param $prototype Optional prototype lexer.
      * @return Concrete lexer.
      */
-    static function create($prototype = null) {
+    function create($prototype = null) {
         // we don't really care if it's a reference or a copy
         static $lexer = null;
         if ($prototype) {
             $lexer = $prototype;
         }
         if (empty($lexer)) {
-            if (class_exists('DOMDocument')) { // check for DOM support
+            if (version_compare(PHP_VERSION, '5', '>=')) {
                 require_once 'HTMLPurifier/Lexer/DOMLex.php';
                 $lexer = new HTMLPurifier_Lexer_DOMLex();
             } else {
@@ -165,12 +166,11 @@ class HTMLPurifier_Lexer
     /**
      * Translates CDATA sections into regular sections (through escaping).
      * 
-     * @static
      * @protected
      * @param $string HTML string to process.
      * @returns HTML with CDATA sections escaped.
      */
-    static function escapeCDATA($string) {
+    function escapeCDATA($string) {
         return preg_replace_callback(
             '/<!\[CDATA\[(.+?)\]\]>/',
             array('HTMLPurifier_Lexer', 'CDATACallback'),
@@ -181,14 +181,13 @@ class HTMLPurifier_Lexer
     /**
      * Callback function for escapeCDATA() that does the work.
      * 
-     * @static
      * @warning Though this is public in order to let the callback happen,
      *          calling it directly is not recommended.
      * @params $matches PCRE matches array, with index 0 the entire match
      *                  and 1 the inside of the CDATA section.
      * @returns Escaped internals of the CDATA section.
      */
-    static function CDATACallback($matches) {
+    function CDATACallback($matches) {
         // not exactly sure why the character set is needed, but whatever
         return htmlspecialchars($matches[1], ENT_COMPAT, 'UTF-8');
     }
@@ -197,7 +196,7 @@ class HTMLPurifier_Lexer
      * Takes a piece of HTML and normalizes it by converting entities, fixing
      * encoding, extracting bits, and other good stuff.
      */
-    function normalize($html, $config, &$context) {
+    function normalize($html, $config) {
         
         // extract body from document if applicable
         if ($config->get('Core', 'AcceptFullDocuments')) {
@@ -213,7 +212,7 @@ class HTMLPurifier_Lexer
         // clean into wellformed UTF-8 string for an SGML context: this has
         // to be done after entity expansion because the entities sometimes
         // represent non-SGML characters (horror, horror!)
-        $html = HTMLPurifier_Encoder::cleanUTF8($html);
+        $html = $this->_encoder->cleanUTF8($html);
         
         return $html;
     }

library/HTMLPurifier/Lexer/DOMLex.php

@@ -38,9 +38,10 @@ class HTMLPurifier_Lexer_DOMLex extends HTMLPurifier_Lexer
         $this->factory = new HTMLPurifier_TokenFactory();
     }
     
-    public function tokenizeHTML($string, $config, &$context) {
+    public function tokenizeHTML($string, $config = null) {
+        if (!$config) $config = HTMLPurifier_Config::createDefault();
         
-        $string = $this->normalize($string, $config, $context);
+        $string = $this->normalize($string, $config);
         
         // preprocess string, essential for UTF-8
         $string =
@@ -88,11 +89,6 @@ class HTMLPurifier_Lexer_DOMLex extends HTMLPurifier_Lexer
         } elseif ($node->nodeType === XML_COMMENT_NODE) {
             $tokens[] = $this->factory->createComment($node->data);
             return;
-        } elseif (
-            // not-well tested: there may be other nodes we have to grab
-            $node->nodeType !== XML_ELEMENT_NODE
-        ) {
-            return;
         }
         
         $attr = $node->hasAttributes() ?

library/HTMLPurifier/Lexer/DirectLex.php

@@ -24,9 +24,11 @@ class HTMLPurifier_Lexer_DirectLex extends HTMLPurifier_Lexer
      */
     var $_whitespace = "\x20\x09\x0D\x0A";
     
-    function tokenizeHTML($html, $config, &$context) {
+    function tokenizeHTML($html, $config = null) {
         
-        $html = $this->normalize($html, $config, $context);
+        if (!$config) $config = HTMLPurifier_Config::createDefault();
+        
+        $html = $this->normalize($html, $config);
         
         $cursor = 0; // our location in the text
         $inside_tag = false; // whether or not we're parsing the inside of a tag
@@ -143,18 +145,17 @@ class HTMLPurifier_Lexer_DirectLex extends HTMLPurifier_Lexer
                         )
                     );
                 if ($attribute_string) {
-                    $attr = $this->parseAttributeString(
+                    $attributes = $this->parseAttributeString(
-                                    $attribute_string
+                                        $attribute_string
-                                  , $config, $context
+                                  );
-                              );
                 } else {
-                    $attr = array();
+                    $attributes = array();
                 }
                 
                 if ($is_self_closing) {
-                    $array[] = new HTMLPurifier_Token_Empty($type, $attr);
+                    $array[] = new HTMLPurifier_Token_Empty($type, $attributes);
                 } else {
-                    $array[] = new HTMLPurifier_Token_Start($type, $attr);
+                    $array[] = new HTMLPurifier_Token_Start($type, $attributes);
                 }
                 $cursor = $position_next_gt + 1;
                 $inside_tag = false;
@@ -180,7 +181,7 @@ class HTMLPurifier_Lexer_DirectLex extends HTMLPurifier_Lexer
      * @param $string Inside of tag excluding name.
      * @returns Assoc array of attributes.
      */
-    function parseAttributeString($string, $config, &$context) {
+    function parseAttributeString($string) {
         $string = (string) $string; // quick typecast
         
         if ($string == '') return array(); // no attributes

library/HTMLPurifier/Lexer/PEARSax3.php

@@ -31,13 +31,14 @@ class HTMLPurifier_Lexer_PEARSax3 extends HTMLPurifier_Lexer
      */
     var $tokens = array();
     
-    function tokenizeHTML($string, $config, &$context) {
+    function tokenizeHTML($string, $config = null) {
         
         $this->tokens = array();
         
-        $string = $this->normalize($string, $config, $context);
+        if (!$config) $config = HTMLPurifier_Config::createDefault();
+        $string = $this->normalize($string, $config);
         
-        $parser = new XML_HTMLSax3();
+        $parser=& new XML_HTMLSax3();
         $parser->set_object($this);
         $parser->set_element_handler('openHandler','closeHandler');
         $parser->set_data_handler('dataHandler');

library/HTMLPurifier/PercentEncoder.php

@@ -1,47 +0,0 @@
-<?php
-
-/**
- * Class that handles operations involving percent-encoding in URIs.
- */
-class HTMLPurifier_PercentEncoder
-{
-    
-    /**
-     * Fix up percent-encoding by decoding unreserved characters and normalizing
-     * @param $string String to normalize
-     */
-    function normalize($string) {
-        if ($string == '') return '';
-        $parts = explode('%', $string);
-        $ret = array_shift($parts);
-        foreach ($parts as $part) {
-            $length = strlen($part);
-            if ($length < 2) {
-                $ret .= '%25' . $part;
-                continue;
-            }
-            $encoding = substr($part, 0, 2);
-            $text     = substr($part, 2);
-            if (!ctype_xdigit($encoding)) {
-                $ret .= '%25' . $part;
-                continue;
-            }
-            $int = hexdec($encoding);
-            if (
-                ($int >= 48 && $int <= 57) || // digits
-                ($int >= 65 && $int <= 90) || // uppercase letters
-                ($int >= 97 && $int <= 122) || // lowercase letters
-                $int == 126 || $int == 45 || $int == 46 || $int == 95 // ~-._
-            ) {
-                $ret .= chr($int) . $text;
-                continue;
-            }
-            $encoding = strtoupper($encoding);
-            $ret .= '%' . $encoding . $text;
-        }
-        return $ret;
-    }
-    
-}
-
-?>

library/HTMLPurifier/Printer.php

@@ -1,149 +0,0 @@
-<?php
-
-require_once 'HTMLPurifier/Generator.php';
-require_once 'HTMLPurifier/Token.php';
-require_once 'HTMLPurifier/Encoder.php';
-
-class HTMLPurifier_Printer
-{
-    
-    /**
-     * Instance of HTMLPurifier_Generator for HTML generation convenience funcs
-     */
-    var $generator;
-    
-    /**
-     * Instance of HTMLPurifier_Config, for easy access
-     */
-    var $config;
-    
-    /**
-     * Initialize $generator.
-     */
-    function HTMLPurifier_Printer() {
-        $this->generator = new HTMLPurifier_Generator();
-    }
-    
-    /**
-     * Main function that renders object or aspect of that object
-     * @param $config Configuration object
-     */
-    function render($config) {}
-    
-    /**
-     * Returns a start tag
-     * @param $tag Tag name
-     * @param $attr Attribute array
-     */
-    function start($tag, $attr = array()) {
-        return $this->generator->generateFromToken(
-                    new HTMLPurifier_Token_Start($tag, $attr ? $attr : array())
-               );
-    }
-    
-    /**
-     * Returns an end teg
-     * @param $tag Tag name
-     */
-    function end($tag) {
-        return $this->generator->generateFromToken(
-                    new HTMLPurifier_Token_End($tag)
-               );
-    }
-    
-    /**
-     * Prints a complete element with content inside
-     * @param $tag Tag name
-     * @param $contents Element contents
-     * @param $attr Tag attributes
-     * @param $escape Bool whether or not to escape contents
-     */
-    function element($tag, $contents, $attr = array(), $escape = true) {
-        return $this->start($tag, $attr) .
-               ($escape ? $this->escape($contents) : $contents) .
-               $this->end($tag);
-    }
-    
-    /**
-     * Prints a simple key/value row in a table.
-     * @param $name Key
-     * @param $value Value
-     */
-    function row($name, $value) {
-        if (is_bool($value)) $value = $value ? 'On' : 'Off';
-        return
-            $this->start('tr') . "\n" .
-                $this->element('th', $name) . "\n" .
-                $this->element('td', $value) . "\n" .
-            $this->end('tr')
-        ;
-    }
-    
-    /**
-     * Escapes a string for HTML output.
-     * @param $string String to escape
-     */
-    function escape($string) {
-        $string = HTMLPurifier_Encoder::cleanUTF8($string);
-        $string = htmlspecialchars($string, ENT_COMPAT, 'UTF-8');
-        return $string;
-    }
-    
-    /**
-     * Takes a list of strings and turns them into a single list
-     * @param $array List of strings
-     * @param $polite Bool whether or not to add an end before the last
-     */
-    function listify($array, $polite = false) {
-        if (empty($array)) return 'None';
-        $ret = '';
-        $i = count($array);
-        foreach ($array as $value) {
-            $i--;
-            $ret .= $value;
-            if ($i > 0 && !($polite && $i == 1)) $ret .= ', ';
-            if ($polite && $i == 1) $ret .= 'and ';
-        }
-        return $ret;
-    }
-    
-    /**
-     * Retrieves the class of an object without prefixes, as well as metadata
-     * @param $obj Object to determine class of
-     * @param $prefix Further prefix to remove
-     */
-    function getClass($obj, $sec_prefix = '') {
-        static $five = null;
-        if ($five === null) $five = version_compare(PHP_VERSION, '5', '>=');
-        $prefix = 'HTMLPurifier_' . $sec_prefix;
-        if (!$five) $prefix = strtolower($prefix);
-        $class = str_replace($prefix, '', get_class($obj));
-        $lclass = strtolower($class);
-        $class .= '(';
-        switch ($lclass) {
-            case 'enum':
-                $values = array();
-                foreach ($obj->valid_values as $value => $bool) {
-                    $values[] = $value;
-                }
-                $class .= implode(', ', $values);
-                break;
-            case 'composite':
-                $values = array();
-                foreach ($obj->defs as $def) {
-                    $values[] = $this->getClass($def, $sec_prefix);
-                }
-                $class .= implode(', ', $values);
-                break;
-            case 'multiple':
-                $class .= $this->getClass($obj->single, $sec_prefix) . ', ';
-                $class .= $obj->max;
-                break;
-        }
-        $class .= ')';
-        return $class;
-    }
-    
-}
-
-?>

library/HTMLPurifier/Printer/CSSDefinition.php

@@ -1,40 +0,0 @@
-<?php
-
-require_once 'HTMLPurifier/Printer.php';
-
-class HTMLPurifier_Printer_CSSDefinition extends HTMLPurifier_Printer
-{
-    
-    var $def;
-    
-    function render($config) {
-        $this->def = $config->getCSSDefinition();
-        $ret = '';
-        
-        $ret .= $this->start('div', array('class' => 'HTMLPurifier_Printer'));
-        $ret .= $this->start('table');
-        
-        $ret .= $this->element('caption', 'Properties ($info)');
-        
-        $ret .= $this->start('thead');
-        $ret .= $this->start('tr');
-        $ret .= $this->element('th', 'Property', array('class' => 'heavy'));
-        $ret .= $this->element('th', 'Definition', array('class' => 'heavy', 'style' => 'width:auto;'));
-        $ret .= $this->end('tr');
-        $ret .= $this->end('thead');
-        
-        ksort($this->def->info);
-        foreach ($this->def->info as $property => $obj) {
-            $name = $this->getClass($obj, 'AttrDef_');
-            $ret .= $this->row($property, $name);
-        }
-        
-        $ret .= $this->end('table');
-        $ret .= $this->end('div');
-        
-        return $ret;
-    }
-    
-}
-
-?>

library/HTMLPurifier/Printer/HTMLDefinition.php

@@ -1,206 +0,0 @@
-<?php
-
-require_once 'HTMLPurifier/Printer.php';
-
-class HTMLPurifier_Printer_HTMLDefinition extends HTMLPurifier_Printer
-{
-    
-    /**
-     * Instance of HTMLPurifier_HTMLDefinition, for easy access
-     */
-    var $def;
-    
-    function render($config) {
-        $ret = '';
-        $this->config =& $config;
-        $this->def = $config->getHTMLDefinition();
-        $def =& $this->def;
-        
-        $ret .= $this->start('div', array('class' => 'HTMLPurifier_Printer'));
-        $ret .= $this->start('table');
-        $ret .= $this->element('caption', 'Environment');
-        
-        $ret .= $this->row('Parent of fragment', $def->info_parent);
-        $ret .= $this->row('Strict mode', $def->strict);
-        if ($def->strict) $ret .= $this->row('Block wrap name', $def->info_block_wrapper);
-        
-        $ret .= $this->start('tr');
-            $ret .= $this->element('th', 'Global attributes');
-            $ret .= $this->element('td', $this->listifyAttr($def->info_global_attr),0,0);
-        $ret .= $this->end('tr');
-        
-        $ret .= $this->renderChildren($def->info_parent_def->child);
-        
-        $ret .= $this->start('tr');
-            $ret .= $this->element('th', 'Tag transforms');
-            $list = array();
-            foreach ($def->info_tag_transform as $old => $new) {
-                $new = $this->getClass($new, 'TagTransform_');
-                $list[] = "<$old> with $new";
-            }
-            $ret .= $this->element('td', $this->listify($list));
-        $ret .= $this->end('tr');
-        
-        $ret .= $this->start('tr');
-            $ret .= $this->element('th', 'Pre-AttrTransform');
-            $ret .= $this->element('td', $this->listifyObjectList($def->info_attr_transform_pre));
-        $ret .= $this->end('tr');
-        
-        $ret .= $this->start('tr');
-            $ret .= $this->element('th', 'Post-AttrTransform');
-            $ret .= $this->element('td', $this->listifyObjectList($def->info_attr_transform_post));
-        $ret .= $this->end('tr');
-        
-        $ret .= $this->end('table');
-        
-        
-        $ret .= $this->renderInfo();
-        
-        
-        $ret .= $this->end('div');
-        
-        return $ret;
-    }
-    
-    /**
-     * Renders the Elements ($info) table
-     */
-    function renderInfo() {
-        $ret = '';
-        $ret .= $this->start('table');
-        $ret .= $this->element('caption', 'Elements ($info)');
-        ksort($this->def->info);
-        $ret .= $this->start('tr');
-        $ret .= $this->element('th', 'Allowed tags', array('colspan' => 2, 'class' => 'heavy'));
-        $ret .= $this->end('tr');
-        $ret .= $this->start('tr');
-        $ret .= $this->element('td', $this->listifyTagLookup($this->def->info), array('colspan' => 2));
-        $ret .= $this->end('tr');
-        foreach ($this->def->info as $name => $def) {
-            $ret .= $this->start('tr');
-                $ret .= $this->element('th', "<$name>", array('class'=>'heavy', 'colspan' => 2));
-            $ret .= $this->end('tr');
-            $ret .= $this->start('tr');
-                $ret .= $this->element('th', 'Type');
-                $ret .= $this->element('td', ucfirst($def->type));
-            $ret .= $this->end('tr');
-            if (!empty($def->excludes)) {
-                $ret .= $this->start('tr');
-                    $ret .= $this->element('th', 'Excludes');
-                    $ret .= $this->element('td', $this->listifyTagLookup($def->excludes));
-                $ret .= $this->end('tr');
-            }
-            if (!empty($def->attr_transform_pre)) {
-                $ret .= $this->start('tr');
-                    $ret .= $this->element('th', 'Pre-AttrTransform');
-                    $ret .= $this->element('td', $this->listifyObjectList($def->attr_transform_pre));
-                $ret .= $this->end('tr');
-            }
-            if (!empty($def->attr_transform_post)) {
-                $ret .= $this->start('tr');
-                    $ret .= $this->element('th', 'Post-AttrTransform');
-                    $ret .= $this->element('td', $this->listifyObjectList($def->attr_transform_post));
-                $ret .= $this->end('tr');
-            }
-            if (!empty($def->auto_close)) {
-                $ret .= $this->start('tr');
-                    $ret .= $this->element('th', 'Auto closed by');
-                    $ret .= $this->element('td', $this->listifyTagLookup($def->auto_close));
-                $ret .= $this->end('tr');
-            }
-            $ret .= $this->start('tr');
-                $ret .= $this->element('th', 'Allowed attributes');
-                $ret .= $this->element('td',$this->listifyAttr($def->attr),0,0);
-            $ret .= $this->end('tr');
-            
-            $ret .= $this->renderChildren($def->child);
-        }
-        $ret .= $this->end('table');
-        return $ret;
-    }
-    
-    /** 
-     * Renders a row describing the allowed children of an element
-     * @param $def HTMLPurifier_ChildDef of pertinent element
-     */
-    function renderChildren($def) {
-        $context = new HTMLPurifier_Context();
-        $ret = '';
-        $ret .= $this->start('tr');
-            $elements = array();
-            $attr = array();
-            if (isset($def->elements)) {
-                if ($def->type == 'strictblockquote') $def->validateChildren(array(), $this->config, $context);
-                $elements = $def->elements;
-            } elseif ($def->type == 'chameleon') {
-                $attr['rowspan'] = 2;
-            } elseif ($def->type == 'empty') {
-                $elements = array();
-            } elseif ($def->type == 'table') {
-                $elements = array('col', 'caption', 'colgroup', 'thead',
-                    'tfoot', 'tbody', 'tr');
-            }
-            $ret .= $this->element('th', 'Allowed children', $attr);
-            
-            if ($def->type == 'chameleon') {
-                
-                $ret .= $this->element('td',
-                    '<em>Block</em>: ' .
-                    $this->escape($this->listifyTagLookup($def->block->elements)),0,0);
-                $ret .= $this->end('tr');
-                $ret .= $this->start('tr');
-                $ret .= $this->element('td',
-                    '<em>Inline</em>: ' .
-                    $this->escape($this->listifyTagLookup($def->inline->elements)),0,0);
-                
-            } else {
-                $ret .= $this->element('td',
-                    '<em>'.ucfirst($def->type).'</em>: ' .
-                    $this->escape($this->listifyTagLookup($elements)),0,0);
-            }
-        $ret .= $this->end('tr');
-        return $ret;
-    }
-    
-    /** 
-     * Listifies a tag lookup table.
-     * @param $array Tag lookup array in form of array('tagname' => true)
-     */
-    function listifyTagLookup($array) {
-        $list = array();
-        foreach ($array as $name => $discard) {
-            if ($name !== '#PCDATA' && !isset($this->def->info[$name])) continue;
-            $list[] = $name;
-        }
-        return $this->listify($list);
-    }
-    
-    /**
-     * Listifies a list of objects by retrieving class names and internal state
-     * @param $array List of objects
-     * @todo Also add information about internal state
-     */
-    function listifyObjectList($array) {
-        $list = array();
-        foreach ($array as $discard => $obj) {
-            $list[] = $this->getClass($obj, 'AttrTransform_');
-        }
-        return $this->listify($list);
-    }
-    
-    /**
-     * Listifies a hash of attributes to AttrDef classes
-     * @param $array Array hash in form of array('attrname' => HTMLPurifier_AttrDef)
-     */
-    function listifyAttr($array) {
-        $list = array();
-        foreach ($array as $name => $obj) {
-            if ($obj === false) continue;
-            $list[] = "$name&nbsp;=&nbsp;<i>" . $this->getClass($obj, 'AttrDef_') . '</i>';
-        }
-        return $this->listify($list);
-    }
-    
-}
-
-?>

library/HTMLPurifier/Strategy.php

@@ -24,7 +24,7 @@ class HTMLPurifier_Strategy
      * @param $config Configuration options
      * @returns Processed array of token objects.
      */
-    function execute($tokens, $config, &$context) {
+    function execute($tokens, $config = null) {
         trigger_error('Cannot call abstract function', E_USER_ERROR);
     }
     

library/HTMLPurifier/Strategy/Composite.php

@@ -18,9 +18,9 @@ class HTMLPurifier_Strategy_Composite extends HTMLPurifier_Strategy
         trigger_error('Attempt to instantiate abstract object', E_USER_ERROR);
     }
     
-    function execute($tokens, $config, &$context) {
+    function execute($tokens, $config) {
         foreach ($this->strategies as $strategy) {
-            $tokens = $strategy->execute($tokens, $config, $context);
+            $tokens = $strategy->execute($tokens, $config);
         }
         return $tokens;
     }

library/HTMLPurifier/Strategy/FixNesting.php

@@ -34,7 +34,8 @@ require_once 'HTMLPurifier/HTMLDefinition.php';
 class HTMLPurifier_Strategy_FixNesting extends HTMLPurifier_Strategy
 {
     
-    function execute($tokens, $config, &$context) {
+    function execute($tokens, $config) {
+        
         //####################################################################//
         // Pre-processing
         
@@ -48,10 +49,6 @@ class HTMLPurifier_Strategy_FixNesting extends HTMLPurifier_Strategy
         array_unshift($tokens, new HTMLPurifier_Token_Start($parent_name));
         $tokens[] = new HTMLPurifier_Token_End($parent_name);
         
-        // setup the context variables
-        $parent_type = 'unknown'; // reference var that we alter
-        $context->register('ParentType', $parent_type);
-        
         //####################################################################//
         // Loop initialization
         
@@ -104,11 +101,7 @@ class HTMLPurifier_Strategy_FixNesting extends HTMLPurifier_Strategy
             if ($count = count($stack)) {
                 $parent_index = $stack[$count-1];
                 $parent_name  = $tokens[$parent_index]->name;
-                if ($parent_index == 0) {
+                $parent_def   = $definition->info[$parent_name];
-                    $parent_def   = $definition->info_parent_def;
-                } else {
-                    $parent_def   = $definition->info[$parent_name];
-                }
             } else {
                 // unknown info, it won't be used anyway
                 $parent_index = $parent_name = $parent_def = null;
@@ -116,10 +109,10 @@ class HTMLPurifier_Strategy_FixNesting extends HTMLPurifier_Strategy
             
             // calculate context
             if (isset($parent_def)) {
-                $parent_type = $parent_def->type;
+                $context = $parent_def->type;
             } else {
                 // generally found in specialized elements like UL
-                $parent_type = 'unknown';
+                $context = 'unknown';
             }
             
             //################################################################//
@@ -145,25 +138,14 @@ class HTMLPurifier_Strategy_FixNesting extends HTMLPurifier_Strategy
             if ($excluded) {
                 // there is an exclusion, remove the entire node
                 $result = false;
-                $excludes = array(); // not used, but good to initialize anyway
             } else {
                 // DEFINITION CALL
-                if ($i === 0) {
+                $def = $definition->info[$tokens[$i]->name];
-                    // special processing for the first node
+                $child_def = $def->child;
-                    $def = $definition->info_parent_def;
-                } else {
-                    $def = $definition->info[$tokens[$i]->name];
-                    
-                }
                 
-                if (!empty($def->child)) {
+                // have DTD child def validate children
-                    // have DTD child def validate children
+                $result = $child_def->validateChildren(
-                    $result = $def->child->validateChildren(
+                    $child_tokens, $config,$context);
-                        $child_tokens, $config, $context);
-                } else {
-                    // weird, no child definition, get rid of everything
-                    $result = false;
-                }
                 
                 // determine whether or not this element has any exclusions
                 $excludes = $def->excludes;
@@ -243,20 +225,13 @@ class HTMLPurifier_Strategy_FixNesting extends HTMLPurifier_Strategy
             
             // Test if the token indeed is a start tag, if not, move forward
             // and test again.
-            $size = count($tokens);
             while ($i < $size and $tokens[$i]->type != 'start') {
                 if ($tokens[$i]->type == 'end') {
                     // pop a token index off the stack if we ended a node
                     array_pop($stack);
                     // pop an exclusion lookup off exclusion stack if
                     // we ended node and that node had exclusions
-                    if ($i == 0 || $i == $size - 1) {
+                    if ($definition->info[$tokens[$i]->name]->excludes) {
-                        // use specialized var if it's the super-parent
-                        $s_excludes = $definition->info_parent_def->excludes;
-                    } else {
-                        $s_excludes = $definition->info[$tokens[$i]->name]->excludes;
-                    }
-                    if ($s_excludes) {
                         array_pop($exclude_stack);
                     }
                 }
@@ -272,9 +247,6 @@ class HTMLPurifier_Strategy_FixNesting extends HTMLPurifier_Strategy
         array_shift($tokens);
         array_pop($tokens);
         
-        // remove context variables
-        $context->destroy('ParentType');
-        
         //####################################################################//
         // Return
         

library/HTMLPurifier/Strategy/MakeWellFormed.php

@@ -10,7 +10,7 @@ require_once 'HTMLPurifier/Generator.php';
 class HTMLPurifier_Strategy_MakeWellFormed extends HTMLPurifier_Strategy
 {
     
-    function execute($tokens, $config, &$context) {
+    function execute($tokens, $config) {
         $definition = $config->getHTMLDefinition();
         $generator = new HTMLPurifier_Generator();
         $result = array();
@@ -30,7 +30,7 @@ class HTMLPurifier_Strategy_MakeWellFormed extends HTMLPurifier_Strategy
                 $token->type == 'start' ) {
                 
                 $result[] = new HTMLPurifier_Token_Empty($token->name,
-                                                         $token->attr);
+                                                         $token->attributes);
                 continue;
             }
             
@@ -39,7 +39,7 @@ class HTMLPurifier_Strategy_MakeWellFormed extends HTMLPurifier_Strategy
                 $token->type == 'empty' ) {
                 
                 $result[] = new HTMLPurifier_Token_Start($token->name,
-                                                         $token->attr);
+                                                         $token->attributes);
                 $result[] = new HTMLPurifier_Token_End($token->name);
                 
                 continue;
@@ -86,7 +86,7 @@ class HTMLPurifier_Strategy_MakeWellFormed extends HTMLPurifier_Strategy
             if (empty($current_nesting)) {
                 if ($escape_invalid_tags) {
                     $result[] = new HTMLPurifier_Token_Text(
-                        $generator->generateFromToken($token, $config, $context)
+                        $generator->generateFromToken($token, $config)
                     );
                 }
                 continue;
@@ -123,7 +123,7 @@ class HTMLPurifier_Strategy_MakeWellFormed extends HTMLPurifier_Strategy
             if ($skipped_tags === false) {
                 if ($escape_invalid_tags) {
                     $result[] = new HTMLPurifier_Token_Text(
-                        $generator->generateFromToken($token, $config, $context)
+                        $generator->generateFromToken($token, $config)
                     );
                 }
                 continue;

library/HTMLPurifier/Strategy/RemoveForeignElements.php

@@ -5,14 +5,6 @@ require_once 'HTMLPurifier/HTMLDefinition.php';
 require_once 'HTMLPurifier/Generator.php';
 require_once 'HTMLPurifier/TagTransform.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.'
-);
-
 /**
  * Removes all unrecognized tags from the list of tokens.
  * 
@@ -24,7 +16,7 @@ HTMLPurifier_ConfigSchema::define(
 class HTMLPurifier_Strategy_RemoveForeignElements extends HTMLPurifier_Strategy
 {
     
-    function execute($tokens, $config, &$context) {
+    function execute($tokens, $config) {
         $definition = $config->getHTMLDefinition();
         $generator = new HTMLPurifier_Generator();
         $result = array();
@@ -33,26 +25,7 @@ class HTMLPurifier_Strategy_RemoveForeignElements extends HTMLPurifier_Strategy
             if (!empty( $token->is_tag )) {
                 // DEFINITION CALL
                 if (isset($definition->info[$token->name])) {
-                    // leave untouched, except for a few special cases:
+                    // leave untouched
-                    
-                    // hard-coded image special case, pre-emptively drop
-                    // if not available. Probably not abstract-able
-                    if ( $token->name == 'img' ) {
-                        if (!isset($token->attr['src'])) {
-                            continue;
-                        }
-                        if (!isset($definition->info['img']->attr['src'])) {
-                            continue;
-                        }
-                        $token->attr['src'] =
-                            $definition->
-                                info['img']->
-                                    attr['src']->
-                                        validate($token->attr['src'],
-                                            $config, $context);
-                        if ($token->attr['src'] === false) continue;
-                    }
-                    
                 } elseif (
                     isset($definition->info_tag_transform[$token->name])
                 ) {
@@ -60,11 +33,11 @@ class HTMLPurifier_Strategy_RemoveForeignElements extends HTMLPurifier_Strategy
                     // DEFINITION CALL
                     $token = $definition->
                                 info_tag_transform[$token->name]->
-                                    transform($token, $config, $context);
+                                    transform($token);
                 } elseif ($escape_invalid_tags) {
                     // invalid tag, generate HTML and insert in
                     $token = new HTMLPurifier_Token_Text(
-                        $generator->generateFromToken($token, $config, $context)
+                        $generator->generateFromToken($token, $config)
                     );
                 } else {
                     continue;