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
-more details), Feyd especially (namely IPv6 and optimization).  Thanks to RSnake
-for letting me package his fantastic XSS cheatsheet for a smoketest.
+to the DevNetwork Community for their help (see docs/devnetwork.html for more
+details), Feyd especially (namely IPv6 and optimization).  Thanks to RSnake for
+letting me package his fantastic XSS cheatsheet for a smoketest.

Doxyfile

@@ -4,7 +4,7 @@
 # Project related configuration options
 #---------------------------------------------------------------------------
 PROJECT_NAME           = HTML Purifier
-PROJECT_NUMBER         = 1.2.0
+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

@@ -25,7 +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.
@@ -33,7 +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

@@ -2,47 +2,12 @@ NEWS ( CHANGELOG and HISTORY )                                     HTMLPurifier
 |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
 
 = KEY ====================
-    # Breaks back-compat
     ! Feature
     - Bugfix
       + Sub-comment
     . Internal change
 ==========================
 
-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

SLOW

@@ -2,13 +2,13 @@
 SLOW
   also known as the HELP ME LIBRARY IS TOO SLOW MY PAGE TAKE TOO LONG LOAD page
 
-HTML Purifier is a very powerful library.  But with power comes great
+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 HTML Purifier is kinda too slow for outbound
+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
@@ -19,7 +19,7 @@ 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.
+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
@@ -36,5 +36,4 @@ 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 report back your results if you decide to do that!  Especially if you
-port HTML Purifier to C++.  ;-)
+to tell me if you decide to do that!  ;-)

TODO

@@ -1,23 +1,23 @@
 
 TODO List
 
-1.3 release
- - Make URI validation routines tighter (especially mailto)
- - More extensive 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
- - Rich set* methods and config file loaders for HTMLPurifier_Config
+Ongoing
+ - Lots of profiling, make it faster!
+ - Plugins for major CMSes (very tricky issue)
 
-1.4 release
+1.2 release
+ - Make URI validation routines tighter (especially mailto)
+ - More extensive URI filtering schemes
+ - Allow for background-image and list-style-image (see above)
+ - Distinguish between different types of URIs, for instance, a mailto URI
+   in IMG SRC is nonsensical
+ - Error logging for filtering/cleanup procedures
+
+1.3 release
  - Add various "levels" of cleaning
     - Related: Allow strict (X)HTML
- - More fine-grained control over escaping behavior
-    - 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)).
 
-1.5 release
+1.4 release
  - Additional support for poorly written HTML
     - Implement all non-essential attribute transforms
     - Microsoft Word HTML cleaning (i.e. MsoNormal)
@@ -28,8 +28,6 @@ TODO List
       shouldn't be paragraphed, such as lists and tables).
     - Linkify URLs
     - Smileys
-    - Linkification for HTML Purifier docs: notably configuration and
-      class names
 
 3.0 release
  - Extended HTML capabilities based on namespacing and tag transforms
@@ -37,38 +35,19 @@ TODO List
       attributes, offer default implementation
     - Lots of documentation and samples
 
-Ongoing
- - Lots of profiling, make it faster!
- - Plugins for major CMSes (very tricky issue)
-
 Unknown release (on a scratch-an-itch basis)
+ - 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.
-   Also, enable disabling of directionality
- - Append something to duplicate IDs so they're still usable (impl. note: the
-   dupe detector would also need to detect the suffix as well)
- - Have 'lang' attribute be checked against official lists
-
-Encoding workarounds
  - Non-lossy dumb alternate character encoding transformations, achieved by
    numerically encoding all non-ASCII characters
  - 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)
- - Win32 Phalanger C# binaries (?)
- - 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.)
-
 Wontfix
- - Non-lossy smart alternate character encoding transformations (unless
-   patch provided)
+ - Non-lossy smart alternate character encoding transformations
  - Pretty-printing HTML, users can use Tidy on the output on entire page

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
 */
 
@@ -110,12 +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', $info->type);
-        if ($info->allow_null) {
-            $dom_type->setAttribute('allow-null', 'yes');
-        }
-        $dom_constraints->appendChild($dom_type);
-        
+        $dom_constraints->appendChild(
+            $dom_document->createElement('type', $info->type)
+        );
         if ($info->allowed !== true) {
             $dom_allowed = $dom_document->createElement('allowed');
             $dom_constraints->appendChild($dom_allowed);
@@ -131,20 +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_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_constraints->appendChild(
+            $dom_document->createElement('default', $default)
+        );
         
         $dom_descriptions = $dom_document->createElement('descriptions');
         $dom_directive->appendChild($dom_descriptions);

configdoc/styles/plain.css

@@ -5,6 +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;}

configdoc/styles/plain.xsl

@@ -23,41 +23,23 @@
                 <link rel="stylesheet" type="text/css" href="styles/plain.css" />
             </head>
             <body>
-                <h1><xsl:value-of select="/configdoc/title" /> 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="namespace" mode="toc">
-        <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 match="title">
+        <h1><xsl:value-of select="/configdoc/title" /> Configuration Documentation</h1>
     </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">
@@ -69,7 +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">
@@ -99,9 +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

@@ -10,9 +10,12 @@ 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
-configuration object to be passed as a parameter.  (They also require a
-Context object).
+Since configuration is dependent on context, most of the internal classes
+require a configuration object to be passed as a parameter.  However, a few
+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 is a special class
 of directives that influence the *construction* of the Definition object.

docs/dev-code-quality.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="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>
-
-<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>
-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
-    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

@@ -1,80 +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>
-
-<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(s) to Attribute(s)</li>
-        <li>Def to Definition</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

@@ -1,32 +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>
-
-<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

@@ -1,44 +1,31 @@
-<?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="Credits and links to DevNetwork forum topics on HTML Purifier." />
-<link rel="stylesheet" type="text/css" href="./style.css" />
-
-<title>DevNetwork Credits - HTML Purifier</title>
-
-</head>
-<body>
-
-<h1>DevNetwork Credits</h1>
-
-<div id="filing">Filed under Reference</div>
-<div id="index">Return to the <a href="index.html">index</a>.</div>
-
-<p>Many thanks to the DevNetwork community for answering questions,
-theorizing about design, and offering encouragement during
-the development of this library in these forum threads:</p>
-
-<ul>
-    <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=53056">How much of CSS to implement?</a></li>
-    <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>
-    <li><a href="http://forums.devnetwork.net/viewtopic.php?t=53415">How to document configuration directives</a></li>
-    <li><a href="http://forums.devnetwork.net/viewtopic.php?t=53479">IPv6</a></li>
-    <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>
+<?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>
+
+<title>DevNetwork Forums</title>
+
+</head>
+<body>
+
+<p>Many thanks to the DevNetwork community for answering questions,
+theorizing about design, and offering encouragement during
+the development of this library in these forum threads:</p>
+
+<ul>
+    <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=53056">How much of CSS to implement?</a></li>
+    <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>
+    <li><a href="http://forums.devnetwork.net/viewtopic.php?t=53415">How to document configuration directives</a></li>
+    <li><a href="http://forums.devnetwork.net/viewtopic.php?t=53479">IPv6</a></li>
+    <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><a href="http://forums.devnetwork.net/viewtopic.php?t=53861">Non-SGML characters</a>
+    <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=54478">Parameter Object vs. Parameter Array vs. Parameter Functions</a>
+    <li><a href="http://forums.devnetwork.net/viewtopic.php?t=54521">Convert encoding where output cannot represent characters</a>
+</ul>
+</body>
 </html>

docs/enduser-id.html

@@ -1,146 +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>
-
-<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/filter-levels.txt

@@ -126,5 +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

@@ -1,70 +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>HTML Purifier</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 in HTML Purifier.</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>
-
-<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

@@ -1,300 +1,292 @@
-<?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="Tables detailing HTML element and CSS property implementation coverage in HTML Purifier." />
-<link rel="stylesheet" type="text/css" href="./style.css" />
-
-<title>Implementation Progress - HTML Purifier</title>
-
-<style type="text/css">
-
-td {padding-right:1em;border-bottom:1px solid #000;padding-left:0.5em;}
-th {text-align:left;padding-top:1.4em;font-size:13pt;
-    border-bottom:2px solid #000;background:#FFF;}
-thead th {text-align:left;padding:0.1em;background-color:#EEE;}
-
-.impl-yes {background:#9D9;}
-.impl-partial {background:#FFA;}
-.impl-no {background:#CCC;}
-
-.danger {color:#600;}
-.css1 {color:#060;}
-.required {font-weight:bold;}
-.feature {color:#999;}
-
-</style>
-
-</head><body>
-
-<h1>Implementation Progress</h1>
-
-<div id="filing">Filed under Development</div>
-<div id="index">Return to the <a href="index.html">index</a>.</div>
-
-<h2>Key</h2>
-
-<table cellspacing="0"><tbody>
-<tr><td class="impl-yes">Implemented</td></tr>
-<tr><td class="impl-partial">Partially implemented</td></tr>
-<tr><td class="impl-no">Will not implement</td></tr>
-<tr><td class="danger">Dangerous attribute/property</td></tr>
-<tr><td class="css1">Present in CSS1</td></tr>
-<tr><td class="feature">Feature, requires extra work</td></tr>
-</tbody></table>
-
-<h2>CSS</h2>
-
-<table cellspacing="0">
-
-<thead>
-<tr><th>Name</th><th>Notes</th></tr>
-</thead>
-
-<!--
-<tr><td>-</td><td>-</td></tr>
--->
-
-<tbody>
-<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 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>
-<tr class="css1 impl-yes"><td>border-width</td><td>MULTIPLE</td></tr>
-<tr class="css1 impl-yes"><td>border-*</td><td>SHORTHAND</td></tr>
-<tr class="impl-yes"><td>border-*-color</td><td>COMPOSITE(&lt;color&gt;, transparent)</td></tr>
-<tr class="impl-yes"><td>border-*-style</td><td>ENUM(none, hidden, dotted, dashed,
-    solid, double, groove, ridge, inset, outset)</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>clear</td><td>ENUM(none, left, right, both)</td></tr>
-<tr class="css1 impl-yes"><td>color</td><td>&lt;color&gt;</td></tr>
-<tr class="css1 impl-yes"><td>float</td><td>ENUM(left, right, none), May require layout
-    precautions with clear</td></tr>
-<tr class="css1 impl-yes"><td>font</td><td>SHORTHAND</td></tr>
-<tr class="css1 impl-yes"><td>font-family</td><td>CSS validator may complain if fallback font
-    family not specified</td></tr>
-<tr class="css1 impl-yes"><td>font-size</td><td>COMPOSITE(&lt;absolute-size&gt;,
-    &lt;relative-size&gt;, &lt;length&gt;, &lt;percentage&gt;)</td></tr>
-<tr class="css1 impl-yes"><td>font-style</td><td>ENUM(normal, italic, oblique)</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-weight</td><td>ENUM(normal, bold, bolder, lighter,
-    100, 200, 300, 400, 500, 600, 700, 800, 900), maybe special code for
-    in-between integers</td></tr>
-<tr class="css1 impl-yes"><td>letter-spacing</td><td>COMPOSITE(&lt;length&gt;, normal)</td></tr>
-<tr class="css1 impl-yes"><td>line-height</td><td>COMPOSITE(&lt;number&gt;,
-    &lt;length&gt;, &lt;percentage&gt;, normal)</td></tr>
-<tr class="css1 impl-yes"><td>list-style-position</td><td>ENUM(inside, outside),
-    Strange behavior in browsers</td></tr>
-<tr class="css1 impl-yes"><td>list-style-type</td><td>ENUM(...),
-    Well-supported values are: disc, circle, square,
-    decimal, lower-roman, upper-roman, lower-alpha and upper-alpha. See also
-    CSS 3. Mostly IE lack of support.</td></tr>
-<tr class="css1 impl-yes"><td>list-style</td><td>SHORTHAND</td></tr>
-<tr class="css1 impl-yes"><td>margin</td><td>MULTIPLE</td></tr>
-<tr class="css1 impl-yes"><td>margin-*</td><td>COMPOSITE(&lt;length&gt;,
-    &lt;percentage&gt;, auto)</td></tr>
-<tr class="css1 impl-yes"><td>padding</td><td>MULTIPLE</td></tr>
-<tr class="css1 impl-yes"><td>padding-*</td><td>COMPOSITE(&lt;length&gt;(positive),
-    &lt;percentage&gt;(positive))</td></tr>
-<tr class="css1 impl-yes"><td>text-align</td><td>ENUM(left, right,
-    center, justify)</td></tr>
-<tr class="css1 impl-yes"><td>text-decoration</td><td>No blink (argh my eyes), not
-    enum, can be combined (composite sorta): underline, overline,
-    line-through</td></tr>
-<tr class="css1 impl-yes"><td>text-indent</td><td>COMPOSITE(&lt;length&gt;,
-    &lt;percentage&gt;)</td></tr>
-<tr class="css1 impl-yes"><td>text-transform</td><td>ENUM(capitalize, uppercase,
-    lowercase, none)</td></tr>
-<tr class="css1 impl-yes"><td>width</td><td>COMPOSITE(&lt;length&gt;,
-    &lt;percentage&gt;, auto), Interesting</td></tr>
-<tr class="css1 impl-yes"><td>word-spacing</td><td>COMPOSITE(&lt;length&gt;, auto),
-    IE 5 no support</td></tr>
-</tbody>
-
-<tbody>
-<tr><th colspan="2">Table</th></tr>
-<tr class="impl-yes"><td>border-collapse</td><td>ENUM(collapse, seperate)</td></tr>
-<tr class="impl-yes"><td>caption-side</td><td>ENUM(top, bottom)</td></tr>
-<tr class="feature"><td>empty-cells</td><td>ENUM(show, hide), No IE support makes this useless,
-    possible fix with &amp;nbsp;? Unknown release milestone.</td></tr>
-<tr class="impl-yes"><td>table-layout</td><td>ENUM(auto, fixed)</td></tr>
-<tr class="impl-yes css1"><td>vertical-align</td><td>COMPOSITE(ENUM(baseline, sub,
-    super, top, text-top, middle, bottom, text-bottom), &lt;percentage&gt;,
-    &lt;length&gt;) Also applies to others with explicit height</td></tr>
-</tbody>
-
-<tbody>
-<tr><th colspan="2">Absolute positioning, unknown release milestone</th></tr>
-<tr class="danger"><td>bottom</td><td rowspan="4">Dangerous, must be non-negative</td></tr>
-<tr class="danger"><td>left</td></tr>
-<tr class="danger"><td>right</td></tr>
-<tr class="danger"><td>top</td></tr>
-<tr><td>clip</td><td>-</td></tr>
-<tr class="danger"><td>position</td><td>ENUM(static, relative, absolute, fixed), permit
-    relative not absolute?</td></tr>
-<tr class="danger"><td>z-index</td><td>Dangerous</td></tr>
-</tbody>
-
-<tbody>
-<tr><th colspan="2">Unknown</th></tr>
-<tr class="danger css1"><td>background-image</td><td>Dangerous, target milestone 1.2</td></tr>
-<tr class="css1"><td>background-attachment</td><td>ENUM(scroll, fixed),
-    Depends on background-image</td></tr>
-<tr class="css1"><td>background-position</td><td>Depends on background-image</td></tr>
-<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;
-    will not implement list-item, run-in (Opera only) or table (no IE);
-    inline-block has incomplete IE6 support and requires -moz-inline-box
-    for Mozilla. Unknown target milestone.</td></tr>
-<tr><td class="css1">height</td><td>Interesting, why use it? Unknown target milestone.</td></tr>
-<tr class="danger css1"><td>list-style-image</td><td>Dangerous? Target milestone 1.2</td></tr>
-<tr class="impl-no"><td>max-height</td><td rowspan="4">No IE 5/6</td></tr>
-<tr class="impl-no"><td>min-height</td></tr>
-<tr class="impl-no"><td>max-width</td></tr>
-<tr class="impl-no"><td>min-width</td></tr>
-<tr class="impl-no"><td>orphans</td><td>No IE support</td></tr>
-<tr class="impl-no"><td>widows</td><td>No IE support</td></tr>
-<tr><td>overflow</td><td>ENUM, IE 5/6 almost (remove visible if set). Unknown target milestone.</td></tr>
-<tr><td>page-break-after</td><td>ENUM(auto, always, avoid, left, right),
-    IE 5.5/6 and Opera. Unknown target milestone.</td></tr>
-<tr><td>page-break-before</td><td>ENUM(auto, always, avoid, left, right),
-    Mostly supported. Unknown target milestone.</td></tr>
-<tr><td>page-break-inside</td><td>ENUM(avoid, auto), Opera only. Unknown target milestone.</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>visibility</td><td>ENUM(visible, hidden, collapse),
-    Dangerous</td></tr>
-<tr class="css1 feature"><td>white-space</td><td>ENUM(normal, pre, nowrap, pre-wrap,
-    pre-line), Spotty implementation:
-    pre (no IE 5/6), nowrap (no IE 5),
-    pre-wrap (only Opera), pre-line (no support). Fixable? Unknown target milestone.</td></tr>
-</tbody>
-
-<tbody class="impl-no">
-<tr><th colspan="2">Aural</th></tr>
-<tr><td>azimuth</td><td>-</td></tr>
-<tr><td>cue</td><td>-</td></tr>
-<tr><td>cue-after</td><td>-</td></tr>
-<tr><td>cue-before</td><td>-</td></tr>
-<tr><td>elevation</td><td>-</td></tr>
-<tr><td>pause-after</td><td>-</td></tr>
-<tr><td>pause-before</td><td>-</td></tr>
-<tr><td>pause</td><td>-</td></tr>
-<tr><td>pitch-range</td><td>-</td></tr>
-<tr><td>pitch</td><td>-</td></tr>
-<tr><td>play-during</td><td>-</td></tr>
-<tr><td>richness</td><td>-</td></tr>
-<tr><td>speak-header</td><td>Table related</td></tr>
-<tr><td>speak-numeral</td><td>-</td></tr>
-<tr><td>speak-punctuation</td><td>-</td></tr>
-<tr><td>speak</td><td>-</td></tr>
-<tr><td>speech-rate</td><td>-</td></tr>
-<tr><td>stress</td><td>-</td></tr>
-<tr><td>voice-family</td><td>-</td></tr>
-<tr><td>volume</td><td>-</td></tr>
-</tbody>
-
-<tbody class="impl-no">
-<tr><th colspan="2">Will not implement</th></tr>
-<tr><td>content</td><td>Not applicable for inline styles</td></tr>
-<tr><td>counter-increment</td><td>Needs content, Opera only</td></tr>
-<tr><td>counter-reset</td><td>Needs content, Opera only</td></tr>
-<tr><td>direction</td><td>No support</td></tr>
-<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>
-    <tr><td>outline-style</td></tr>
-    <tr><td>outline-width</td></tr>
-    <tr><td>outline</td></tr>
-<tr><td>unicode-bidi</td><td>No support</td></tr>
-</tbody>
-
-</table>
-
-<h2>Interesting Attributes</h2>
-
-<table cellspacing="0">
-
-<thead>
-<tr><th>Attribute</th><th>Tags</th><th>Notes</th></tr>
-</thead>
-
-<!--
-<tr><th></th></tr>
-<tbody>
-<tr><td>-</td><td>-</td><td>-</td></tr>
-</tbody>
--->
-
-<tbody>
-<tr><th colspan="3">CSS</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><th colspan="3">Questionable</th></tr>
-<tr class="impl-no"><td>accesskey</td><td>A</td><td>May interfere with main interface</td></tr>
-<tr class="impl-no"><td>tabindex</td><td>A</td><td>May interfere with main interface</td></tr>
-<tr><td>target</td><td>A</td><td>Config enabled, only useful for frame layouts</td></tr>
-</tbody>
-
-<tbody>
-<tr><th colspan="3">Miscellaneous</th></tr>
-<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>
-<tr><td>rev</td><td>A</td><td>Largely user-defined: vote-*</td></tr>
-<tr class="feature"><td>axis</td><td>TD, TH</td><td>W3C only: No browser implementation</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 class="feature"><td>headers</td><td>TD, TH</td><td>W3C only: No browser implementation</td></tr>
-<tr class="feature"><td>scope</td><td>TD, TH</td><td>W3C only: No browser implementation</td></tr>
-</tbody>
-
-<tbody class="impl-yes">
-<tr><th colspan="3">URI</th></tr>
-<tr><td rowspan="2">cite</td><td>BLOCKQUOTE, Q</td><td>For attribution</td></tr>
-    <tr><td>DEL, INS</td><td>Link to explanation why it changed</td></tr>
-<tr><td>href</td><td>A</td><td>-</td></tr>
-<tr><td>longdesc</td><td>IMG</td><td>-</td></tr>
-<tr class="required"><td>src</td><td>IMG</td><td>Required</td></tr>
-</tbody>
-
-<tbody>
-<tr><th colspan="3">Transform, target milestone 1.4</th></tr>
-<tr><td rowspan="5">align</td><td>CAPTION</td><td>Near-equiv style 'caption-side', drop left and right</td></tr>
-    <tr><td>IMG</td><td rowspan="2">Margin-left and margin-right = auto or parent div</td></tr>
-    <tr><td>TABLE</td></tr>
-    <tr><td>HR</td><td>Equivalent style 'text-align' (IE tested)</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>alt</td><td>IMG</td><td>Required, insert image filename if src is present or default invalid image text</td></tr>
-<tr><td rowspan="3">bgcolor</td><td>TABLE</td><td>Equivalent style 'background-color' (IE tested)</td></tr>
-    <tr><td>TR</td><td>Equivalent style 'background-color' (IE tested)</td></tr>
-    <tr><td>TD, TH</td><td>Equivalent style 'background-color'</td></tr>
-<tr><td>border</td><td>IMG</td><td>Equivalent style 'border-width', only applies when link present</td></tr>
-<tr><td>clear</td><td>BR</td><td>Near-equiv style 'clear', transform 'all' into 'both'</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="required impl-yes"><td>dir</td><td>BDO</td><td>Required, insert ltr (or configuration value) if none</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>hspace</td><td>IMG</td><td>Near-equiv styles 'margin-top' and 'margin-bottom', needs px suffix</td></tr>
-<tr class="impl-yes"><td>lang</td><td>*</td><td>Copy value to xml:lang</td></tr>
-<tr><td rowspan="2">name</td><td>IMG</td><td>Turn into ID</td></tr>
-    <tr><td>A</td><td>Turn into ID? (not deprecated, though in which specs?)</td></tr>
-<tr><td>noshade</td><td>HR</td><td>Boolean, style 'border-style:solid;'</td></tr>
-<tr><td>nowrap</td><td>TD, TH</td><td>Boolean, style 'white-space:nowrap;' (not compat with IE5)</td></tr>
-<tr><td>size</td><td>HR</td><td>Near-equiv '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>start</td><td>OL</td><td>Poorly supported 'counter-reset', transform may not be desirable</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>OL</td></tr>
-    <tr><td>UL</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>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>
-
+<?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>
+
+<title>HTMLPurifier Progress</title>
+
+<style type="text/css">
+
+td {padding-right:1em;border-bottom:1px solid #000;padding-left:0.5em;}
+th {text-align:left;padding-top:1.4em;font-size:13pt;
+    border-bottom:2px solid #000;background:#FFF;}
+thead th {text-align:left;padding:0.1em;background-color:#EEE;}
+
+.impl-yes {background:#9D9;}
+.impl-partial {background:#FFA;}
+.impl-no {background:#CCC;}
+
+.danger {color:#600;}
+.css1 {color:#060;}
+.required {font-weight:bold;}
+.feature {color:#999;}
+
+</style>
+
+</head><body>
+
+<h1>HTMLPurifier Progress</h1>
+
+<h2>Key</h2>
+
+<table cellspacing="0"><tbody>
+<tr><td class="impl-yes">Implemented</td></tr>
+<tr><td class="impl-partial">Partially implemented</td></tr>
+<tr><td class="impl-no">Will not implement</td></tr>
+<tr><td class="danger">Dangerous attribute/property</td></tr>
+<tr><td class="css1">Present in CSS1</td></tr>
+<tr><td class="feature">Feature, requires extra work</td></tr>
+</tbody></table>
+
+<h3>CSS</h3>
+
+<table cellspacing="0">
+
+<thead>
+<tr><th>Name</th><th>Notes</th></tr>
+</thead>
+
+<!--
+<tr><td>-</td><td>-</td></tr>
+-->
+
+<tbody>
+<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 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>
+<tr class="css1 impl-yes"><td>border-width</td><td>MULTIPLE</td></tr>
+<tr class="css1 impl-yes"><td>border-*</td><td>SHORTHAND</td></tr>
+<tr class="impl-yes"><td>border-*-color</td><td>COMPOSITE(&lt;color&gt;, transparent)</td></tr>
+<tr class="impl-yes"><td>border-*-style</td><td>ENUM(none, hidden, dotted, dashed,
+    solid, double, groove, ridge, inset, outset)</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>clear</td><td>ENUM(none, left, right, both)</td></tr>
+<tr class="css1 impl-yes"><td>color</td><td>&lt;color&gt;</td></tr>
+<tr class="css1 impl-yes"><td>float</td><td>ENUM(left, right, none), May require layout
+    precautions with clear</td></tr>
+<tr class="css1 impl-yes"><td>font</td><td>SHORTHAND</td></tr>
+<tr class="css1 impl-yes"><td>font-family</td><td>CSS validator may complain if fallback font
+    family not specified</td></tr>
+<tr class="css1 impl-yes"><td>font-size</td><td>COMPOSITE(&lt;absolute-size&gt;,
+    &lt;relative-size&gt;, &lt;length&gt;, &lt;percentage&gt;)</td></tr>
+<tr class="css1 impl-yes"><td>font-style</td><td>ENUM(normal, italic, oblique)</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-weight</td><td>ENUM(normal, bold, bolder, lighter,
+    100, 200, 300, 400, 500, 600, 700, 800, 900), maybe special code for
+    in-between integers</td></tr>
+<tr class="css1 impl-yes"><td>letter-spacing</td><td>COMPOSITE(&lt;length&gt;, normal)</td></tr>
+<tr class="css1 impl-yes"><td>line-height</td><td>COMPOSITE(&lt;number&gt;,
+    &lt;length&gt;, &lt;percentage&gt;, normal)</td></tr>
+<tr class="css1 impl-yes"><td>list-style-position</td><td>ENUM(inside, outside),
+    Strange behavior in browsers</td></tr>
+<tr class="css1 impl-yes"><td>list-style-type</td><td>ENUM(...),
+    Well-supported values are: disc, circle, square,
+    decimal, lower-roman, upper-roman, lower-alpha and upper-alpha. See also
+    CSS 3. Mostly IE lack of support.</td></tr>
+<tr class="css1 impl-yes"><td>list-style</td><td>SHORTHAND</td></tr>
+<tr class="css1 impl-yes"><td>margin</td><td>MULTIPLE</td></tr>
+<tr class="css1 impl-yes"><td>margin-*</td><td>COMPOSITE(&lt;length&gt;,
+    &lt;percentage&gt;, auto)</td></tr>
+<tr class="css1 impl-yes"><td>padding</td><td>MULTIPLE</td></tr>
+<tr class="css1 impl-yes"><td>padding-*</td><td>COMPOSITE(&lt;length&gt;(positive),
+    &lt;percentage&gt;(positive))</td></tr>
+<tr class="css1 impl-yes"><td>text-align</td><td>ENUM(left, right,
+    center, justify)</td></tr>
+<tr class="css1 impl-yes"><td>text-decoration</td><td>No blink (argh my eyes), not
+    enum, can be combined (composite sorta): underline, overline,
+    line-through</td></tr>
+<tr class="css1 impl-yes"><td>text-indent</td><td>COMPOSITE(&lt;length&gt;,
+    &lt;percentage&gt;)</td></tr>
+<tr class="css1 impl-yes"><td>text-transform</td><td>ENUM(capitalize, uppercase,
+    lowercase, none)</td></tr>
+<tr class="css1 impl-yes"><td>width</td><td>COMPOSITE(&lt;length&gt;,
+    &lt;percentage&gt;, auto), Interesting</td></tr>
+<tr class="css1 impl-yes"><td>word-spacing</td><td>COMPOSITE(&lt;length&gt;, auto),
+    IE 5 no support</td></tr>
+</tbody>
+
+<tbody>
+<tr><th colspan="2">Table</th></tr>
+<tr class="impl-yes"><td>border-collapse</td><td>ENUM(collapse, seperate)</td></tr>
+<tr class="impl-yes"><td>caption-side</td><td>ENUM(top, bottom)</td></tr>
+<tr class="feature"><td>empty-cells</td><td>ENUM(show, hide), No IE support makes this useless,
+    possible fix with &amp;nbsp;? Unknown release milestone.</td></tr>
+<tr class="impl-yes"><td>table-layout</td><td>ENUM(auto, fixed)</td></tr>
+<tr class="impl-yes css1"><td>vertical-align</td><td>COMPOSITE(ENUM(baseline, sub,
+    super, top, text-top, middle, bottom, text-bottom), &lt;percentage&gt;,
+    &lt;length&gt;) Also applies to others with explicit height</td></tr>
+</tbody>
+
+<tbody>
+<tr><th colspan="2">Absolute positioning, unknown release milestone</th></tr>
+<tr class="danger"><td>bottom</td><td rowspan="4">Dangerous, must be non-negative</td></tr>
+<tr class="danger"><td>left</td></tr>
+<tr class="danger"><td>right</td></tr>
+<tr class="danger"><td>top</td></tr>
+<tr><td>clip</td><td>-</td></tr>
+<tr class="danger"><td>position</td><td>ENUM(static, relative, absolute, fixed), permit
+    relative not absolute?</td></tr>
+<tr class="danger"><td>z-index</td><td>Dangerous</td></tr>
+</tbody>
+
+<tbody>
+<tr><th colspan="2">Unknown</th></tr>
+<tr class="danger css1"><td>background-image</td><td>Dangerous, target milestone 1.2</td></tr>
+<tr class="css1"><td>background-attachment</td><td>ENUM(scroll, fixed),
+    Depends on background-image</td></tr>
+<tr class="css1"><td>background-position</td><td>Depends on background-image</td></tr>
+<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;
+    will not implement list-item, run-in (Opera only) or table (no IE);
+    inline-block has incomplete IE6 support and requires -moz-inline-box
+    for Mozilla. Unknown target milestone.</td></tr>
+<tr><td class="css1">height</td><td>Interesting, why use it? Unknown target milestone.</td></tr>
+<tr class="danger css1"><td>list-style-image</td><td>Dangerous? Target milestone 1.2</td></tr>
+<tr class="impl-no"><td>max-height</td><td rowspan="4">No IE 5/6</td></tr>
+<tr class="impl-no"><td>min-height</td></tr>
+<tr class="impl-no"><td>max-width</td></tr>
+<tr class="impl-no"><td>min-width</td></tr>
+<tr class="impl-no"><td>orphans</td><td>No IE support</td></tr>
+<tr class="impl-no"><td>widows</td><td>No IE support</td></tr>
+<tr><td>overflow</td><td>ENUM, IE 5/6 almost (remove visible if set). Unknown target milestone.</td></tr>
+<tr><td>page-break-after</td><td>ENUM(auto, always, avoid, left, right),
+    IE 5.5/6 and Opera. Unknown target milestone.</td></tr>
+<tr><td>page-break-before</td><td>ENUM(auto, always, avoid, left, right),
+    Mostly supported. Unknown target milestone.</td></tr>
+<tr><td>page-break-inside</td><td>ENUM(avoid, auto), Opera only. Unknown target milestone.</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>visibility</td><td>ENUM(visible, hidden, collapse),
+    Dangerous</td></tr>
+<tr class="css1 feature"><td>white-space</td><td>ENUM(normal, pre, nowrap, pre-wrap,
+    pre-line), Spotty implementation:
+    pre (no IE 5/6), nowrap (no IE 5),
+    pre-wrap (only Opera), pre-line (no support). Fixable? Unknown target milestone.</td></tr>
+</tbody>
+
+<tbody class="impl-no">
+<tr><th colspan="2">Aural</th></tr>
+<tr><td>azimuth</td><td>-</td></tr>
+<tr><td>cue</td><td>-</td></tr>
+<tr><td>cue-after</td><td>-</td></tr>
+<tr><td>cue-before</td><td>-</td></tr>
+<tr><td>elevation</td><td>-</td></tr>
+<tr><td>pause-after</td><td>-</td></tr>
+<tr><td>pause-before</td><td>-</td></tr>
+<tr><td>pause</td><td>-</td></tr>
+<tr><td>pitch-range</td><td>-</td></tr>
+<tr><td>pitch</td><td>-</td></tr>
+<tr><td>play-during</td><td>-</td></tr>
+<tr><td>richness</td><td>-</td></tr>
+<tr><td>speak-header</td><td>Table related</td></tr>
+<tr><td>speak-numeral</td><td>-</td></tr>
+<tr><td>speak-punctuation</td><td>-</td></tr>
+<tr><td>speak</td><td>-</td></tr>
+<tr><td>speech-rate</td><td>-</td></tr>
+<tr><td>stress</td><td>-</td></tr>
+<tr><td>voice-family</td><td>-</td></tr>
+<tr><td>volume</td><td>-</td></tr>
+</tbody>
+
+<tbody class="impl-no">
+<tr><th colspan="2">Will not implement</th></tr>
+<tr><td>content</td><td>Not applicable for inline styles</td></tr>
+<tr><td>counter-increment</td><td>Needs content, Opera only</td></tr>
+<tr><td>counter-reset</td><td>Needs content, Opera only</td></tr>
+<tr><td>direction</td><td>No support</td></tr>
+<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>
+    <tr><td>outline-style</td></tr>
+    <tr><td>outline-width</td></tr>
+    <tr><td>outline</td></tr>
+<tr><td>unicode-bidi</td><td>No support</td></tr>
+</tbody>
+
+</table>
+
+<h2>Interesting Attributes</h2>
+
+<table cellspacing="0">
+
+<thead>
+<tr><th>Attribute</th><th>Tags</th><th>Notes</th></tr>
+</thead>
+
+<!--
+<tr><th></th></tr>
+<tbody>
+<tr><td>-</td><td>-</td><td>-</td></tr>
+</tbody>
+-->
+
+<tbody>
+<tr><th colspan="3">CSS</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><th colspan="3">Questionable</th></tr>
+<tr class="impl-no"><td>accesskey</td><td>A</td><td>May interfere with main interface</td></tr>
+<tr class="impl-no"><td>tabindex</td><td>A</td><td>May interfere with main interface</td></tr>
+<tr><td>target</td><td>A</td><td>Config enabled, only useful for frame layouts</td></tr>
+</tbody>
+
+<tbody>
+<tr><th colspan="3">Miscellaneous</th></tr>
+<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>
+<tr><td>rev</td><td>A</td><td>Largely user-defined: vote-*</td></tr>
+<tr class="feature"><td>axis</td><td>TD, TH</td><td>W3C only: No browser implementation</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 class="feature"><td>headers</td><td>TD, TH</td><td>W3C only: No browser implementation</td></tr>
+<tr class="feature"><td>scope</td><td>TD, TH</td><td>W3C only: No browser implementation</td></tr>
+</tbody>
+
+<tbody class="impl-yes">
+<tr><th colspan="3">URI</th></tr>
+<tr><td rowspan="2">cite</td><td>BLOCKQUOTE, Q</td><td>For attribution</td></tr>
+    <tr><td>DEL, INS</td><td>Link to explanation why it changed</td></tr>
+<tr><td>href</td><td>A</td><td>-</td></tr>
+<tr><td>longdesc</td><td>IMG</td><td>-</td></tr>
+<tr class="required"><td>src</td><td>IMG</td><td>Required</td></tr>
+</tbody>
+
+<tbody>
+<tr><th colspan="3">Transform, target milestone 1.4</th></tr>
+<tr><td rowspan="5">align</td><td>CAPTION</td><td>Near-equiv style 'caption-side', drop left and right</td></tr>
+    <tr><td>IMG</td><td rowspan="2">Margin-left and margin-right = auto or parent div</td></tr>
+    <tr><td>TABLE</td></tr>
+    <tr><td>HR</td><td>Equivalent style 'text-align' (IE tested)</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>alt</td><td>IMG</td><td>Required, insert image filename if src is present or default invalid image text</td></tr>
+<tr><td rowspan="3">bgcolor</td><td>TABLE</td><td>Equivalent style 'background-color' (IE tested)</td></tr>
+    <tr><td>TR</td><td>Equivalent style 'background-color' (IE tested)</td></tr>
+    <tr><td>TD, TH</td><td>Equivalent style 'background-color'</td></tr>
+<tr><td>border</td><td>IMG</td><td>Equivalent style 'border-width', only applies when link present</td></tr>
+<tr><td>clear</td><td>BR</td><td>Near-equiv style 'clear', transform 'all' into 'both'</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="required impl-yes"><td>dir</td><td>BDO</td><td>Required, insert ltr (or configuration value) if none</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>hspace</td><td>IMG</td><td>Near-equiv styles 'margin-top' and 'margin-bottom', needs px suffix</td></tr>
+<tr class="impl-yes"><td>lang</td><td>*</td><td>Copy value to xml:lang</td></tr>
+<tr><td rowspan="2">name</td><td>IMG</td><td>Turn into ID</td></tr>
+    <tr><td>A</td><td>Turn into ID? (not deprecated, though in which specs?)</td></tr>
+<tr><td>noshade</td><td>HR</td><td>Boolean, style 'border-style:solid;'</td></tr>
+<tr><td>nowrap</td><td>TD, TH</td><td>Boolean, style 'white-space:nowrap;' (not compat with IE5)</td></tr>
+<tr><td>size</td><td>HR</td><td>Near-equiv '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>start</td><td>OL</td><td>Poorly supported 'counter-reset', transform may not be desirable</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>OL</td></tr>
+    <tr><td>UL</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>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>
+
 </body></html>

docs/proposal-colors.html

@@ -1,47 +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>
-
-<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

@@ -1,59 +0,0 @@
-
-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.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.Munge - will munge all external URIs to a different URI, which redirects
-    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, but can also be used to
-    redirect to a splash page notifying user that they are leaving your
-    website.
-
-%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.HostBlacklist - strings that if found in the host of a URI are disallowed
-%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).
-
-%URI.DisableExternalResources - disallow resource links (i.e. URIs that result
-    in immediate requests, such as src in IMG) to external websites
-
-%HTML.DisableImg - disables all images

docs/style.css

@@ -1,40 +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; }
-
-/* 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; }
-
-/* Contains, without exception, $Id$, for SVN version info. */
-#version {text-align:right; font-style:italic; margin:2em 0;}

library/HTMLPurifier.php

@@ -22,7 +22,7 @@
  */
 
 /*
-    HTML Purifier 1.2.0 - 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';
@@ -96,17 +95,16 @@ class HTMLPurifier
      */
     function purify($html, $config = null) {
         $config = $config ? $config : $this->config;
-        $context =& new HTMLPurifier_Context();
-        $html = $this->encoder->convertToUTF8($html, $config, $context);
+        $html = $this->encoder->convertToUTF8($html, $config);
         $html = 
             $this->generator->generateFromTokens(
                 $this->strategy->execute(
-                    $this->lexer->tokenizeHTML($html, $config, $context),
-                    $config, $context
+                    $this->lexer->tokenizeHTML($html, $config),
+                    $config
                 ),
-                $config, $context
+                $config
             );
-        $html = $this->encoder->convertFromUTF8($html, $config, $context);
+        $html = $this->encoder->convertFromUTF8($html, $config);
         return $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/CSS.php

@@ -43,7 +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/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;
-        
-        $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[$id])) return false;
+        if (isset($context->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/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',
@@ -12,28 +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.'
-);
-
 /**
  * Validates a URI as defined by RFC 3986.
  * @note Scheme-specific mechanics deferred to HTMLPurifier_URIScheme
@@ -42,16 +19,9 @@ class HTMLPurifier_AttrDef_URI extends HTMLPurifier_AttrDef
 {
     
     var $host;
-    var $PercentEncoder;
-    var $embeds;
     
-    /**
-     * @param $embeds Does the URI here result in an extra HTTP request?
-     */
-    function HTMLPurifier_AttrDef_URI($embeds = false) {
+    function HTMLPurifier_AttrDef_URI() {
         $this->host = new HTMLPurifier_AttrDef_Host();
-        $this->PercentEncoder = new HTMLPurifier_PercentEncoder();
-        $this->embeds = (bool) $embeds;
     }
     
     function validate($uri, $config, &$context) {
@@ -62,9 +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
         
@@ -96,31 +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(
-                $config->get('URI', 'DefaultScheme'), $config, $context
+                $config->get('URI', 'DefaultScheme'), $config
             );
         }
         
         
-        // the URI we're processing embeds a resource in the page, but the URI
-        // it references cannot be located
-        if ($this->embeds && !$scheme_obj->browsable) {
-            return false;
-        }
-        
         
         if ($authority !== null) {
             
-            // remove URI if it's absolute and we disallow externals
-            unset($our_host);
-            if ($config->get('URI', 'DisableExternal')) {
-                $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 []
@@ -143,17 +97,6 @@ class HTMLPurifier_AttrDef_URI extends HTMLPurifier_AttrDef
             $host = $this->host->validate($host, $config, $context);
             if ($host === false) $host = null;
             
-            // 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 {
@@ -177,7 +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
             );
         
         

library/HTMLPurifier/AttrTransform.php

@@ -23,10 +23,9 @@ class HTMLPurifier_AttrTransform
      * @param $attr Assoc array of attributes, usually from
      *              HTMLPurifier_Token_Tag::$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/ChildDef.php

@@ -38,14 +38,15 @@ class HTMLPurifier_ChildDef
     /**
      * Validates nodes according to definition and returns modification.
      * 
+     * @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);
     }
 }
@@ -90,7 +91,7 @@ class HTMLPurifier_ChildDef_Custom extends HTMLPurifier_ChildDef
         $reg = preg_replace('/([#a-zA-Z0-9_.-]+)/', '(,?\\0)', $reg);
         $this->_pcre_regex = $reg;
     }
-    function validateChildren($tokens_of_children, $config, &$context) {
+    function validateChildren($tokens_of_children, $config, $context) {
         $list_of_children = '';
         $nesting = 0; // depth into the nest
         foreach ($tokens_of_children as $token) {
@@ -144,7 +145,7 @@ class HTMLPurifier_ChildDef_Required extends HTMLPurifier_ChildDef
     }
     var $allow_empty = false;
     var $type = 'required';
-    function validateChildren($tokens_of_children, $config, &$context) {
+    function validateChildren($tokens_of_children, $config, $context) {
         // if there are no tokens, delete parent node
         if (empty($tokens_of_children)) return false;
         
@@ -226,7 +227,7 @@ class HTMLPurifier_ChildDef_Optional extends HTMLPurifier_ChildDef_Required
 {
     var $allow_empty = true;
     var $type = 'optional';
-    function validateChildren($tokens_of_children, $config, &$context) {
+    function validateChildren($tokens_of_children, $config, $context) {
         $result = parent::validateChildren($tokens_of_children, $config, $context);
         if ($result === false) return array();
         return $result;
@@ -245,7 +246,7 @@ 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) {
+    function validateChildren($tokens_of_children, $config, $context) {
         return array();
     }
 }
@@ -280,9 +281,8 @@ class HTMLPurifier_ChildDef_Chameleon extends HTMLPurifier_ChildDef
         $this->block  = new HTMLPurifier_ChildDef_Optional($block);
     }
     
-    function validateChildren($tokens_of_children, $config, &$context) {
-        $parent_type = $context->get('ParentType');
-        switch ($parent_type) {
+    function validateChildren($tokens_of_children, $config, $context) {
+        switch ($context) {
             case 'unknown':
             case 'inline':
                 $result = $this->inline->validateChildren(
@@ -308,7 +308,7 @@ 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) {
+    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

library/HTMLPurifier/Config.php

@@ -60,7 +60,7 @@ class HTMLPurifier_Config
      * @param $key String key
      */
     function get($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;
@@ -75,16 +75,13 @@ class HTMLPurifier_Config
      * @param $value Mixed value
      */
     function set($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;
         }
-        $value = $this->def->validate(
-                    $value,
-                    $this->def->info[$namespace][$key]->type,
-                    $this->def->info[$namespace][$key]->allow_null
-                 );
+        $value = $this->def->validate($value,
+                                      $this->def->info[$namespace][$key]->type);
         if (is_string($value)) {
             // resolve value alias if defined
             if (isset($this->def->info[$namespace][$key]->aliases[$value])) {
@@ -98,7 +95,7 @@ class HTMLPurifier_Config
                 }
             }
         }
-        if ($this->def->isError($value)) {
+        if ($value === null) {
             trigger_error('Value is of invalid type', E_USER_WARNING);
             return;
         }
@@ -127,27 +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 => $value) {
-            if (strpos($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);
-                }
-            }
-        }
-    }
-    
 }
 
 ?>

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
@@ -113,19 +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->isError($default)) {
+            if ($def->validate($default, $type) === null) {
                 trigger_error('Default value does not match directive type',
                     E_USER_ERROR);
                 return;
@@ -133,7 +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;
         }
         $backtrace = debug_backtrace();
@@ -222,37 +212,36 @@ class HTMLPurifier_ConfigSchema {
     /**
      * Validate a variable according to type. Return null if invalid.
      */
-    function validate($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) $var;
-                } elseif (!is_bool($var)) break;
+                } elseif (!is_bool($var)) return;
                 return $var;
             case 'list':
             case 'hash':
             case 'lookup':
-                if (!is_array($var)) break;
+                if (!is_array($var)) return;
                 $keys = array_keys($var);
                 if ($keys === array_keys($keys)) {
                     if ($type == 'list') return $var;
@@ -262,7 +251,7 @@ class HTMLPurifier_ConfigSchema {
                             $new[$key] = true;
                         }
                         return $new;
-                    } else break;
+                    } else return;
                 }
                 if ($type === 'lookup') {
                     foreach ($var as $key => $value) {
@@ -271,13 +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);
@@ -285,14 +269,6 @@ class HTMLPurifier_ConfigSchema {
         return $filename;
     }
     
-    /**
-     * Checks if var is an HTMLPurifier_Error object
-     */
-    function isError($var) {
-        if (!is_object($var)) return false;
-        if (!is_a($var, 'HTMLPurifier_Error')) return false;
-        return true;
-    }
 }
 
 /**
@@ -342,13 +318,6 @@ class HTMLPurifier_ConfigEntity_Directive extends HTMLPurifier_ConfigEntity
      *      - mixed (anything goes)
      */
     var $type = 'mixed';
-    
-    /**
-     * Is null allowed? Has no affect for mixed type.
-     * @bool
-     */
-    var $allow_null = false;
-    
     /**
      * Plaintext descriptions of the configuration entity is. Organized by
      * file and line number, so multiple descriptions are allowed.

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

@@ -225,30 +225,7 @@ class HTMLPurifier_Encoder
     
     /**
      * Translates a Unicode codepoint into its corresponding UTF-8 character.
-     * @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).
      */
-    
-    // +----------+----------+----------+----------+
-    // | 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 unichr($code) {
         if($code > 1114111 or $code < 0 or
           ($code >= 55296 and $code <= 57343) ) {
@@ -289,7 +266,7 @@ class HTMLPurifier_Encoder
     /**
      * Converts a string to UTF-8 based on configuration.
      */
-    function convertToUTF8($str, $config, &$context) {
+    function convertToUTF8($str, $config) {
         static $iconv = null;
         if ($iconv === null) $iconv = function_exists('iconv');
         $encoding = $config->get('Core', 'Encoding');
@@ -306,7 +283,7 @@ class HTMLPurifier_Encoder
      * @note Currently, this is a lossy conversion, with unexpressable
      *       characters being omitted.
      */
-    function convertFromUTF8($str, $config, &$context) {
+    function convertFromUTF8($str, $config) {
         static $iconv = null;
         if ($iconv === null) $iconv = function_exists('iconv');
         $encoding = $config->get('Core', 'Encoding');

library/HTMLPurifier/EntityLookup.php

@@ -19,7 +19,7 @@ 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));
     }

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/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');

library/HTMLPurifier/HTMLDefinition.php

@@ -22,19 +22,6 @@ 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.'
-);
-
 /**
  * Defines the purified HTML type with large amounts of objects.
  * 
@@ -249,13 +236,13 @@ 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' || $name == '') continue;
+        
+        foreach ($e_Inline->elements as $name) {
             $this->info[$name]->type = 'inline';
         }
         
         $e_Block = new HTMLPurifier_ChildDef_Optional($e_block);
-        foreach ($e_Block->elements as $name => $bool) {
+        foreach ($e_Block->elements as $name) {
             $this->info[$name]->type = 'block';
         }
         
@@ -284,6 +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(),
@@ -293,10 +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
         
@@ -351,14 +335,12 @@ class HTMLPurifier_HTMLDefinition
         $e_URI = new HTMLPurifier_AttrDef_URI();
         $this->info['a']->attr['href'] =
         $this->info['img']->attr['longdesc'] =
+        $this->info['img']->attr['src'] =
         $this->info['del']->attr['cite'] =
         $this->info['ins']->attr['cite'] =
         $this->info['blockquote']->attr['cite'] =
         $this->info['q']->attr['cite'] = $e_URI;
         
-        // URI that causes HTTP request
-        $this->info['img']->attr['src'] = new HTMLPurifier_AttrDef_URI(true);
-        
         //////////////////////////////////////////////////////////////////////
         // info_tag_transform : transformations of tags
         
@@ -415,13 +397,6 @@ class HTMLPurifier_HTMLDefinition
         
         $this->info_attr_transform_post[] = new HTMLPurifier_AttrTransform_Lang();
         
-        // protect against stdclasses floating around
-        foreach ($this->info as $key => $obj) {
-            if (is_a($obj, 'stdclass')) {
-                unset($this->info[$key]);
-            }
-        }
-        
     }
     
     function setAttrForTableElements($attr, $def) {

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

@@ -122,7 +122,7 @@ class HTMLPurifier_Lexer
      * @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);
     }
     
@@ -196,7 +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')) {

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 =

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
         $inside_tag = false; // whether or not we're parsing the inside of a tag
@@ -145,7 +147,6 @@ class HTMLPurifier_Lexer_DirectLex extends HTMLPurifier_Lexer
                 if ($attribute_string) {
                     $attributes = $this->parseAttributeString(
                                         $attribute_string
-                                      , $config, $context
                                   );
                 } else {
                     $attributes = array();
@@ -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

@@ -31,11 +31,12 @@ 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();
         $parser->set_object($this);

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/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
         
@@ -112,10 +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';
             }
             
             //################################################################//
@@ -148,7 +145,7 @@ class HTMLPurifier_Strategy_FixNesting extends HTMLPurifier_Strategy
                 
                 // have DTD child def validate children
                 $result = $child_def->validateChildren(
-                    $child_tokens, $config, $context);
+                    $child_tokens, $config,$context);
                 
                 // determine whether or not this element has any exclusions
                 $excludes = $def->excludes;
@@ -250,9 +247,6 @@ class HTMLPurifier_Strategy_FixNesting extends HTMLPurifier_Strategy
         array_shift($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();
         $result = array();
@@ -86,7 +86,7 @@ class HTMLPurifier_Strategy_MakeWellFormed extends HTMLPurifier_Strategy
             if (empty($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

@@ -16,7 +16,7 @@ require_once 'HTMLPurifier/TagTransform.php';
 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();
@@ -33,11 +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;

library/HTMLPurifier/Strategy/ValidateAttributes.php

@@ -3,6 +3,8 @@
 require_once 'HTMLPurifier/Strategy.php';
 require_once 'HTMLPurifier/HTMLDefinition.php';
 require_once 'HTMLPurifier/IDAccumulator.php';
+require_once 'HTMLPurifier/ConfigSchema.php';
+require_once 'HTMLPurifier/AttrContext.php';
 
 HTMLPurifier_ConfigSchema::define(
     'Attr', 'IDBlacklist', array(), 'list',
@@ -15,14 +17,18 @@ HTMLPurifier_ConfigSchema::define(
 class HTMLPurifier_Strategy_ValidateAttributes extends HTMLPurifier_Strategy
 {
     
-    function execute($tokens, $config, &$context) {
+    function execute($tokens, $config) {
         
         $definition = $config->getHTMLDefinition();
         
-        // setup id_accumulator context
-        $id_accumulator = new HTMLPurifier_IDAccumulator();
-        $id_accumulator->load($config->get('Attr', 'IDBlacklist'));
-        $context->register('IDAccumulator', $id_accumulator);
+        // setup StrategyContext
+        $context = new HTMLPurifier_AttrContext();
+        
+        // setup ID accumulator and load it with blacklisted IDs
+        //     eventually, we'll have a dedicated context object to hold
+        //     all these accumulators and caches. For now, just an IDAccumulator
+        $context->id_accumulator = new HTMLPurifier_IDAccumulator();
+        $context->id_accumulator->load($config->get('Attr', 'IDBlacklist'));
         
         // create alias to global definition array, see also $defs
         // DEFINITION CALL
@@ -38,17 +44,19 @@ class HTMLPurifier_Strategy_ValidateAttributes extends HTMLPurifier_Strategy
             $attr = $token->attributes;
             
             // do global transformations (pre)
-            // nothing currently utilizes this
+            // ex. <ELEMENT lang="fr"> to <ELEMENT lang="fr" xml:lang="fr">
+            // DEFINITION CALL
             foreach ($definition->info_attr_transform_pre as $transform) {
-                $attr = $transform->transform($attr, $config, $context);
+                $attr = $transform->transform($attr, $config);
             }
             
             // do local transformations only applicable to this element (pre)
             // ex. <p align="right"> to <p style="text-align:right;">
+            // DEFINITION CALL
             foreach ($definition->info[$token->name]->attr_transform_pre
                 as $transform
             ) {
-                $attr = $transform->transform($attr, $config, $context);
+                $attr = $transform->transform($attr, $config);
             }
             
             // create alias to this element's attribute definition array, see
@@ -104,23 +112,17 @@ class HTMLPurifier_Strategy_ValidateAttributes extends HTMLPurifier_Strategy
             }
             
             // post transforms
-            
-            // ex. <x lang="fr"> to <x lang="fr" xml:lang="fr">
             foreach ($definition->info_attr_transform_post as $transform) {
-                $attr = $transform->transform($attr, $config, $context);
+                $attr = $transform->transform($attr, $config);
             }
-            
-            // ex. <bdo> to <bdo dir="ltr">
             foreach ($definition->info[$token->name]->attr_transform_post as $transform) {
-                $attr = $transform->transform($attr, $config, $context);
+                $attr = $transform->transform($attr, $config);
             }
             
             // commit changes
             // could interfere with flyweight implementation
             $tokens[$key]->attributes = $attr;
         }
-        $context->destroy('IDAccumulator');
-        
         return $tokens;
     }
     

library/HTMLPurifier/TagTransform.php

@@ -17,10 +17,8 @@ class HTMLPurifier_TagTransform
     /**
      * Transforms the obsolete tag into the valid tag.
      * @param $tag Tag to be transformed.
-     * @param $config Mandatory HTMLPurifier_Config object
-     * @param $context Mandatory HTMLPurifier_Context object
      */
-    function transform($tag, $config, &$context) {
+    function transform($tag) {
         trigger_error('Call to abstract function', E_USER_ERROR);
     }
     
@@ -39,7 +37,7 @@ class HTMLPurifier_TagTransform_Simple extends HTMLPurifier_TagTransform
         $this->transform_to = $transform_to;
     }
     
-    function transform($tag, $config, &$context) {
+    function transform($tag) {
         $new_tag = $tag->copy();
         $new_tag->name = $this->transform_to;
         return $new_tag;
@@ -57,7 +55,7 @@ class HTMLPurifier_TagTransform_Center extends HTMLPurifier_TagTransform
 {
     var $transform_to = 'div';
     
-    function transform($tag, $config, &$context) {
+    function transform($tag) {
         if ($tag->type == 'end') {
             $new_tag = new HTMLPurifier_Token_End($this->transform_to);
             return $new_tag;
@@ -108,7 +106,7 @@ class HTMLPurifier_TagTransform_Font extends HTMLPurifier_TagTransform
         '+4' => '300%'
     );
     
-    function transform($tag, $config, &$context) {
+    function transform($tag) {
         
         if ($tag->type == 'end') {
             $new_tag = new HTMLPurifier_Token_End($this->transform_to);

library/HTMLPurifier/URIScheme.php

@@ -12,13 +12,6 @@ class HTMLPurifier_URIScheme
      */
     var $default_port = null;
     
-    /**
-     * Whether or not URIs of this schem are locatable by a browser
-     * http and ftp are accessible, while mailto and news are not.
-     * @public
-     */
-    var $browsable = false;
-    
     /**
      * Validates the components of a URI
      * @note This implementation should be called by children if they define
@@ -30,10 +23,9 @@ class HTMLPurifier_URIScheme
      * @param $path Path of URI
      * @param $query Query of URI, found after question mark
      * @param $config HTMLPurifier_Config object
-     * @param $context HTMLPurifier_Context object
      */
     function validateComponents(
-        $userinfo, $host, $port, $path, $query, $config, &$context
+        $userinfo, $host, $port, $path, $query, $config
     ) {
         if ($this->default_port == $port) $port = null;
         return array($userinfo, $host, $port, $path, $query);

library/HTMLPurifier/URIScheme/ftp.php

@@ -8,14 +8,13 @@ require_once 'HTMLPurifier/URIScheme.php';
 class HTMLPurifier_URIScheme_ftp extends HTMLPurifier_URIScheme {
     
     var $default_port = 21;
-    var $browsable = true; // usually
     
     function validateComponents(
-        $userinfo, $host, $port, $path, $query, $config, &$context
+        $userinfo, $host, $port, $path, $query, $config
     ) {
         list($userinfo, $host, $port, $path, $query) = 
             parent::validateComponents(
-                $userinfo, $host, $port, $path, $query, $config, $context );
+                $userinfo, $host, $port, $path, $query, $config );
         $semicolon_pos = strrpos($path, ';'); // reverse
         if ($semicolon_pos !== false) {
             // typecode check

library/HTMLPurifier/URIScheme/http.php

@@ -8,14 +8,13 @@ require_once 'HTMLPurifier/URIScheme.php';
 class HTMLPurifier_URIScheme_http extends HTMLPurifier_URIScheme {
     
     var $default_port = 80;
-    var $browsable = true;
     
     function validateComponents(
-        $userinfo, $host, $port, $path, $query, $config, &$context
+        $userinfo, $host, $port, $path, $query, $config
     ) {
         list($userinfo, $host, $port, $path, $query) = 
             parent::validateComponents(
-                $userinfo, $host, $port, $path, $query, $config, $context );
+                $userinfo, $host, $port, $path, $query, $config );
         return array(null, $host, $port, $path, $query);
     }
     

library/HTMLPurifier/URIScheme/mailto.php

@@ -13,14 +13,12 @@ require_once 'HTMLPurifier/URIScheme.php';
 
 class HTMLPurifier_URIScheme_mailto extends HTMLPurifier_URIScheme {
     
-    var $browsable = false;
-    
     function validateComponents(
-        $userinfo, $host, $port, $path, $query, $config, &$context
+        $userinfo, $host, $port, $path, $query, $config
     ) {
         list($userinfo, $host, $port, $path, $query) = 
             parent::validateComponents(
-                $userinfo, $host, $port, $path, $query, $config, $context );
+                $userinfo, $host, $port, $path, $query, $config );
         // we need to validate path against RFC 2368's addr-spec
         return array(null, null, null, $path, $query);
     }

library/HTMLPurifier/URIScheme/news.php

@@ -7,14 +7,12 @@ require_once 'HTMLPurifier/URIScheme.php';
  */
 class HTMLPurifier_URIScheme_news extends HTMLPurifier_URIScheme {
     
-    var $browsable = false;
-    
     function validateComponents(
-        $userinfo, $host, $port, $path, $query, $config, &$context
+        $userinfo, $host, $port, $path, $query, $config
     ) {
         list($userinfo, $host, $port, $path, $query) = 
             parent::validateComponents(
-                $userinfo, $host, $port, $path, $query, $config, $context );
+                $userinfo, $host, $port, $path, $query, $config );
         // typecode check needed on path
         return array(null, null, null, $path, null);
     }

library/HTMLPurifier/URIScheme/nntp.php

@@ -8,14 +8,13 @@ require_once 'HTMLPurifier/URIScheme.php';
 class HTMLPurifier_URIScheme_nntp extends HTMLPurifier_URIScheme {
     
     var $default_port = 119;
-    var $browsable = false;
     
     function validateComponents(
-        $userinfo, $host, $port, $path, $query, $config, &$context
+        $userinfo, $host, $port, $path, $query, $config
     ) {
         list($userinfo, $host, $port, $path, $query) = 
             parent::validateComponents(
-                $userinfo, $host, $port, $path, $query, $config, $context );
+                $userinfo, $host, $port, $path, $query, $config );
         return array(null, $host, $port, $path, null);
     }
     

library/HTMLPurifier/URISchemeRegistry.php

@@ -63,9 +63,8 @@ class HTMLPurifier_URISchemeRegistry
      * Retrieves a scheme validator object
      * @param $scheme String scheme name like http or mailto
      * @param $config HTMLPurifier_Config object
-     * @param $config HTMLPurifier_Context object
      */
-    function &getScheme($scheme, $config, &$context) {
+    function &getScheme($scheme, $config = null) {
         if (!$config) $config = HTMLPurifier_Config::createDefault();
         $null = null; // for the sake of passing by reference
         

maintenance/generate-entity-file.php

@@ -13,7 +13,7 @@ chdir( dirname(__FILE__) );
 $entity_dir = '../docs/entities/';
 
 // defines the output file for the serialized content.
-$output_file = '../library/HTMLPurifier/EntityLookup/entities.ser';
+$output_file = '../library/HTMLPurifier/EntityLookup/data.txt';
 
 // courtesy of a PHP manual comment
 function unichr($dec) {

plugins/modx.txt

@@ -1,91 +0,0 @@
-
-MODx Plugin
-
-MODx <http://www.modxcms.com/> is an open source PHP application framework.  
-I first came across them in my referrer logs when tillda asked if anyone
-could implement an HTML Purifier plugin.  This forum thread
-<http://modxcms.com/forums/index.php/topic,6604.0.html> eventually resulted
-in the fruition of this plugin that davidm says, "is on top of my favorite
-list."  HTML Purifier goes great with WYSIWYG editors!
-
-
-
-1. Credits
-
-PaulGregory wrote the overall structure of the code.  I added the
-slashes hack.
-
-
-
-2. Install
-
-First, you need to place HTML Purifier library somewhere.  The code here
-assumes that you've placed in MODx's assets/plugins/htmlpurifier (no version
-number).
-
-Log into the manager, and navigate:
-
-Resources > Manage Resources > Plugins tab > New Plugin
-
-Type in a name (probably HTML Purifier), and copy paste this code into the
-textarea:
-
---------------------------------------------------------------------------------
-$e = &$modx->Event;
-if ($e->name == 'OnBeforeDocFormSave') {
-    global $content;
-    
-    set_include_path('../assets/plugins/htmlpurifier/library/'
-       . PATH_SEPARATOR . get_include_path());
-    include_once 'HTMLPurifier.php';
-    $purifier = new HTMLPurifier();
-    
-    static $magic_quotes = null;
-    if ($magic_quotes === null) {
-        // this is an ugly hack because this hook hasn't
-        // had the backslashes removed yet when magic_quotes_gpc is on,
-        // but HTMLPurifier must not have the quotes slashed.
-        $magic_quotes = get_magic_quotes_gpc();
-    }
-    
-    if ($magic_quotes) $content = stripslashes($content);
-    $content = $purifier->purify($content);
-    if ($magic_quotes) $content = addslashes($content);
-}
---------------------------------------------------------------------------------
-
-Then navigate to the System Events tab and check "OnBeforeDocFormSave".
-Save the plugin.  HTML Purifier now is integrated!
-
-
-
-3. Making sure it works
-
-You can test HTML Purifier by deliberately putting in crappy HTML and seeing
-whether or not it gets fixed.  A better way is to put in something like this:
-
-<p lang="fr">Il est bon</p>
-
-...and seeing whether or not the content comes out as:
-
-<p lang="fr" xml:lang="fr">Il est bon</p>
-
-(lang to xml:lang synchronization is one of the many features HTML Purifier
-has).
-
-
-
-4. Caveat Emptor
-
-This code does not intercept save requests from the QuickEdit plugin, this may
-be added in a later version.  It also modifies things on save, so there's a
-slight chance that HTML Purifier may make a boo-boo and accidently mess things
-up (the original version is not saved).
-
-Finally, make sure that MODx is using UTF-8.  If you are using, say, a French
-localisation, you may be using Latin-1, if that's the case, configure
-HTML Purifier properly like this:
-
-$config = HTMLPurifier_Config::createDefault();
-$config->set('Core', 'Encoding', 'ISO-8859-1'); // or whatever encoding
-$purifier = new HTMLPurifier($config);

smoketests/xssAttacks.php

@@ -2,19 +2,6 @@
 
 require_once('common.php');
 
-function formatCode($string) {
-    return 
-        str_replace(
-            array("\t", '»', '\0(null)'),
-            array('<strong>\t</strong>', '<span class="linebreak">»</span>', '<strong>\0</strong>'),
-            escapeHTML(
-                str_replace("\0", '\0(null)',
-                    wordwrap($string, 28, " »\n", true)
-                )
-            )
-        );
-}
-
 ?><!DOCTYPE html 
      PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"
      "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
@@ -22,26 +9,15 @@ function formatCode($string) {
 <head>
     <title>HTMLPurifier XSS Attacks Smoketest</title>
     <meta http-equiv="Content-Type" content="text/html; charset=UTF-8" />
-    <style type="text/css">
-        .scroll {overflow:auto; width:100%;}
-        .even {background:#EAEAEA;}
-        thead th {border-bottom:1px solid #000;}
-        pre strong {color:#00C;}
-        pre .linebreak {color:#AAA;font-weight:100;}
-    </style>
 </head>
 <body>
 <h1>HTMLPurifier XSS Attacks Smoketest</h1>
 <p>XSS attacks are from
 <a href="http://ha.ckers.org/xss.html">http://ha.ckers.org/xss.html</a>.</p>
-<p><strong>Caveats:</strong>
-The last segment of tests regarding blacklisted websites is not
+<p>The last segment of tests regarding blacklisted websites is not
 applicable at the moment, but when we add that functionality they'll be
-relevant. Most XSS broadcasts its presence by spawning an alert dialogue.
-The displayed code is not strictly correct, as linebreaks have been forced for
-readability. Linewraps have been marked with <tt>»</tt>.  Some tests are
-omitted for your convenience. Not all control characters are displayed.</p>
-
+relevant.</p>
+<p>Most of the XSS broadcasts its presence by spawning an alert dialogue.</p>
 <h2>Test</h2>
 <?php
 
@@ -51,35 +27,24 @@ $xml = simplexml_load_file('xssAttacks.xml');
 $purifier = new HTMLPurifier();
 
 ?>
-<table cellspacing="0" cellpadding="2">
+<!-- form is used so that we can use textareas and stay valid -->
+<form method="post" action="xssAttacks.php">
+<table>
 <thead><tr><th>Name</th><th width="30%">Raw</th><th>Output</th><th>Render</th></tr></thead>
 <tbody>
 <?php
 
-$i = 0;
 foreach ($xml->attack as $attack) {
     $code = $attack->code;
-    
-    // custom code for null byte injection tests
-    if (substr($code, 0, 7) == 'perl -e') {
-        $code = substr($code, $i=strpos($code, '"')+1, strrpos($code, '"') - $i);
-        $code = str_replace('\0', "\0", $code);
-    }
-    
-    // disable vectors we cannot test in any meaningful way
-    if ($code == 'See Below') continue; // event handlers, whitelist defeats
-    if ($attack->name == 'OBJECT w/Flash 2') continue; // requires ActionScript
-    if ($attack->name == 'IMG Embedded commands 2') continue; // is an HTTP response
-    
     // custom code for US-ASCII, which couldn't be expressed in XML without encoding
     if ($attack->name == 'US-ASCII encoding') $code = urldecode($code);
 ?>
-    <tr<?php if ($i++ % 2) {echo ' class="even"';} ?>>
+    <tr>
         <td><?php echo escapeHTML($attack->name); ?></td>
-        <td><pre><?php echo formatCode($code); ?></pre></td>
+        <td><textarea readonly="readonly" cols="20" rows="2"><?php echo escapeHTML($code); ?></textarea></td>
         <?php $pure_html = $purifier->purify($code); ?>
-        <td><pre><?php echo formatCode($pure_html); ?></pre></td>
-        <td><div class="scroll"><?php echo $pure_html ?></div></td>
+        <td><textarea readonly="readonly" cols="20" rows="2"><?php echo escapeHTML($pure_html); ?></textarea></td>
+        <td><?php echo $pure_html ?></td>
     </tr>
 <?php
 }
@@ -87,5 +52,6 @@ foreach ($xml->attack as $attack) {
 ?>
 </tbody>
 </table>
+</form>
 </body>
 </html>

tests/HTMLPurifier/AttrDef/CompositeTest.php

@@ -23,7 +23,7 @@ class HTMLPurifier_AttrDef_CompositeTest extends HTMLPurifier_AttrDefHarness
         generate_mock_once('HTMLPurifier_AttrDef');
         
         $config = HTMLPurifier_Config::createDefault();
-        $context = new HTMLPurifier_Context();
+        $context = new HTMLPurifier_AttrContext();
         
         // first test: value properly validates on first definition
         // so second def is never called

tests/HTMLPurifier/AttrDef/Email/SimpleCheckTest.php

@@ -1,16 +0,0 @@
-<?php
-
-require_once 'HTMLPurifier/AttrDef/Email/SimpleCheck.php';
-require_once 'HTMLPurifier/AttrDef/EmailHarness.php';
-
-class HTMLPurifier_AttrDef_Email_SimpleCheckTest
-    extends HTMLPurifier_AttrDef_EmailHarness
-{
-    
-    function setUp() {
-        $this->def = new HTMLPurifier_AttrDef_Email_SimpleCheck();
-    }
-    
-}
-
-?>

tests/HTMLPurifier/AttrDef/EmailHarness.php

@@ -1,33 +0,0 @@
-<?php
-
-require_once 'HTMLPurifier/AttrDef/Email.php';
-
-class HTMLPurifier_AttrDef_EmailHarness extends HTMLPurifier_AttrDefHarness
-{
-    
-    /**
-     * Tests common email strings that are obviously pass/fail
-     */
-    function testCore() {
-        $this->assertDef('bob@example.com');
-        $this->assertDef('  bob@example.com  ', 'bob@example.com');
-        $this->assertDef('bob.thebuilder@example.net');
-        $this->assertDef('Bob_the_Builder-the-2nd@example.org');
-        $this->assertDef('Bob%20the%20Builder@white-space.test');
-        
-        // extended format, with real name
-        //$this->assertDef('Bob%20Builder%20%3Cbobby.bob.bob@it.is.example.com%3E');
-        //$this->assertDef('Bob Builder <bobby.bob.bob@it.is.example.com>');
-        
-        // time to fail
-        $this->assertDef('bob', false);
-        $this->assertDef('bob@home@work', false);
-        $this->assertDef('@example.com', false);
-        $this->assertDef('bob@', false);
-        $this->assertDef('', false);
-        
-    }
-    
-}
-
-?>

tests/HTMLPurifier/AttrDef/IDTest.php

@@ -7,17 +7,12 @@ require_once 'HTMLPurifier/IDAccumulator.php';
 class HTMLPurifier_AttrDef_IDTest extends HTMLPurifier_AttrDefHarness
 {
     
-    function setUp() {
-        parent::setUp();
-        
-        $id_accumulator = new HTMLPurifier_IDAccumulator();
-        $this->context->register('IDAccumulator', $id_accumulator);
-        $this->def = new HTMLPurifier_AttrDef_ID();
-        
-    }
-    
     function test() {
         
+        $this->context = new HTMLPurifier_AttrContext();
+        $this->context->id_accumulator = new HTMLPurifier_IDAccumulator();
+        $this->def = new HTMLPurifier_AttrDef_ID();
+        
         // valid ID names
         $this->assertDef('alpha');
         $this->assertDef('al_ha');
@@ -30,52 +25,13 @@ class HTMLPurifier_AttrDef_IDTest extends HTMLPurifier_AttrDefHarness
         $this->assertDef('.asa', false);
         
         // test duplicate detection
-        $this->assertDef('once');
-        $this->assertDef('once', false);
+        $this->assertDef('a', false);
         
         // valid once whitespace stripped, but needs to be amended
         $this->assertDef(' whee ', 'whee');
         
     }
     
-    function testPrefix() {
-        
-        $this->config->set('Attr', 'IDPrefix', 'user_');
-        
-        $this->assertDef('alpha', 'user_alpha');
-        $this->assertDef('<asa', false);
-        $this->assertDef('once', 'user_once');
-        $this->assertDef('once', false);
-        
-        // if already prefixed, leave alone
-        $this->assertDef('user_alas');
-        $this->assertDef('user_user_alas'); // how to bypass
-        
-    }
-    
-    function testTwoPrefixes() {
-        
-        $this->config->set('Attr', 'IDPrefix', 'user_');
-        $this->config->set('Attr', 'IDPrefixLocal', 'story95_');
-        
-        $this->assertDef('alpha', 'user_story95_alpha');
-        $this->assertDef('<asa', false);
-        $this->assertDef('once', 'user_story95_once');
-        $this->assertDef('once', false);
-        
-        $this->assertDef('user_story95_alas');
-        $this->assertDef('user_alas', 'user_story95_user_alas'); // !
-        
-        $this->config->set('Attr', 'IDPrefix', '');
-        $this->assertDef('amherst'); // no affect when IDPrefix isn't set
-        $this->assertError('%Attr.IDPrefixLocal cannot be used unless '.
-            '%Attr.IDPrefix is set');
-        // SimpleTest has a bug and throws a sprintf error
-        // $this->assertNoErrors();
-        $this->swallowErrors();
-        
-    }
-    
 }
 
 ?>

tests/HTMLPurifier/AttrDef/URITest.php

@@ -4,6 +4,7 @@ require_once 'HTMLPurifier/AttrDefHarness.php';
 require_once 'HTMLPurifier/AttrDef/URI.php';
 
 // WARNING: INCOMPLETE UNIT TESTS!
+// we are currently abstaining percent-encode fixing unit tests
 // we also need to test all the configuration directives defined by this class
 
 // http: is returned quite often when a URL is invalid. We have to change
@@ -82,11 +83,10 @@ class HTMLPurifier_AttrDef_URITest extends HTMLPurifier_AttrDefHarness
         // %5 - prematurely terminated, encode %
         // %FC - u with umlaut, correct
         // note that Apache doesn't do such fixing, rather, it just claims
-        // that the browser sent a "Bad Request".  See PercentEncoder.php
-        // for more details
-        $uri[6] = 'http://www.example.com/%56%fc%GJ%5%FC';
-        $components[6] = array(null, 'www.example.com', null, '/V%FC%25GJ%255%FC', null);
-        $expect_uri[6] = 'http://www.example.com/V%FC%25GJ%255%FC';
+        // that the browser sent a "Bad Request".
+        //$uri[6] = 'http://www.example.com/%56%fc%GJ%5%FC';
+        //$components[6] = array('www.example.com', '/V%FC%25GJ%255%FC', null, null);
+        //$expect_uri[6] = 'http://www.example.com/V%FC%25GJ%255%FC';
         
         // test IPv4 address (behavior may vary with configuration)
         $uri[7] = 'http://192.0.34.166/';
@@ -152,7 +152,9 @@ class HTMLPurifier_AttrDef_URITest extends HTMLPurifier_AttrDefHarness
         $uri[17] = 'javascript:alert("moo");';
         $expect_uri[17] = false;
         
-        // relative URIs - basic case
+        // relative URIs
+        
+        // test basic case
         $uri[18] = '/a/b';
         $components[18] = array(null, null, null, '/a/b', null);
         
@@ -168,10 +170,6 @@ class HTMLPurifier_AttrDef_URITest extends HTMLPurifier_AttrDefHarness
         
         foreach ($uri as $i => $value) {
             
-            // the read in values
-            $this->config  = isset($config[$i])  ? $config[$i]  : HTMLPurifier_Config::createDefault();
-            $this->context = isset($context[$i]) ? $context[$i] : new HTMLPurifier_Context();
-            
             // setUpAssertDef
             if ( isset($components[$i]) ) {
                 $this->components = $components[$i];
@@ -189,6 +187,10 @@ class HTMLPurifier_AttrDef_URITest extends HTMLPurifier_AttrDefHarness
                 $expect_uri[$i] = $value; // untouched
             }
             
+            // the read in values
+            $this->config  = isset($config[$i])  ? $config[$i]  : null;
+            $this->context = isset($context[$i]) ? $context[$i] : null;
+            
             $this->assertDef($value, $expect_uri[$i], true, "Test $i: %s");
             
         }
@@ -205,21 +207,20 @@ class HTMLPurifier_AttrDef_URITest extends HTMLPurifier_AttrDefHarness
         $fake_registry = new HTMLPurifier_URISchemeRegistryMock($this);
         $registry =& HTMLPurifier_URISchemeRegistry::instance($fake_registry);
         
-        // now, let's add a pseudo-scheme to the registry
+        // now, let's at a pseudo-scheme to the registry
         $this->scheme =& new HTMLPurifier_URISchemeMock($this);
         
         // here are the schemes we will support with overloaded mocks
-        $registry->setReturnReference('getScheme', $this->scheme, array('http', $this->config, $this->context));
-        $registry->setReturnReference('getScheme', $this->scheme, array('mailto', $this->config, $this->context));
+        $registry->setReturnReference('getScheme', $this->scheme, array('http', $this->config));
+        $registry->setReturnReference('getScheme', $this->scheme, array('mailto', $this->config));
         
         // default return value is false (meaning no scheme defined: reject)
-        $registry->setReturnValue('getScheme', false, array('*', $this->config, $this->context));
+        $registry->setReturnValue('getScheme', false, array('*', $this->config));
         
         if ($this->components === false) {
             $this->scheme->expectNever('validateComponents');
         } else {
             $this->components[] = $this->config; // append the configuration
-            $this->components[] =& $this->context; // append context
             $this->scheme->setReturnValue(
                 'validateComponents', $this->return_components, $this->components);
             $this->scheme->expectOnce('validateComponents', $this->components);
@@ -233,6 +234,7 @@ class HTMLPurifier_AttrDef_URITest extends HTMLPurifier_AttrDefHarness
     function testIntegration() {
         
         $this->def = new HTMLPurifier_AttrDef_URI();
+        $this->config = $this->context = null;
         
         $this->assertDef('http://www.google.com/');
         $this->assertDef('javascript:bad_stuff();', false);
@@ -243,34 +245,6 @@ class HTMLPurifier_AttrDef_URITest extends HTMLPurifier_AttrDefHarness
         
     }
     
-    function testDisableExternal() {
-        
-        $this->def = new HTMLPurifier_AttrDef_URI();
-        $this->config->set('URI', 'DisableExternal', true);
-        
-        $this->assertDef('/foobar.txt');
-        $this->assertDef('http://google.com/', false);
-        $this->assertDef('http://sub.example.com/alas?foo=asd', false);
-        
-        $this->config->set('URI', 'Host', 'sub.example.com');
-        
-        $this->assertDef('http://sub.example.com/alas?foo=asd');
-        $this->assertDef('http://example.com/teehee', false);
-        $this->assertDef('http://www.example.com/#man', false);
-        $this->assertDef('http://go.sub.example.com/perhaps?p=foo');
-        
-    }
-    
-    function testEmbeds() {
-        
-        // embedded URI
-        $this->def = new HTMLPurifier_AttrDef_URI(true);
-        
-        $this->assertDef('http://sub.example.com/alas?foo=asd');
-        $this->assertDef('mailto:foo@example.com', false);
-        
-    }
-    
 }
 
 ?>

tests/HTMLPurifier/AttrDefHarness.php

@@ -7,14 +7,11 @@ class HTMLPurifier_AttrDefHarness extends UnitTestCase
     var $context;
     var $config;
     
-    function setUp() {
-        $this->config = HTMLPurifier_Config::createDefault();
-        $this->context = new HTMLPurifier_Context();
-    }
-    
     // cannot be used for accumulator
     function assertDef($string, $expect = true, $ini = false, $message = '%s') {
         // $expect can be a string or bool
+        if (!$this->config) $this->config = HTMLPurifier_Config::createDefault();
+        if (!$this->context) $this->context = new HTMLPurifier_AttrContext();
         if ($ini) $this->setUpAssertDef();
         $result = $this->def->validate($string, $this->config, $this->context);
         if ($expect === true) {

tests/HTMLPurifier/AttrTransform/BdoDirTest.php

@@ -5,24 +5,29 @@ require_once 'HTMLPurifier/AttrTransform/BdoDir.php';
 class HTMLPurifier_AttrTransform_BdoDirTest extends HTMLPurifier_AttrTransformHarness
 {
     
-    function setUp() {
-        parent::setUp();
-        $this->obj = new HTMLPurifier_AttrTransform_BdoDir();
-    }
-    
     function test() {
         
-        $this->assertResult( array(), array('dir' => 'ltr') );
+        $this->transform = new HTMLPurifier_AttrTransform_BdoDir();
+        
+        $inputs = array();
+        $expect = array();
+        $config = array();
+        
+        // add dir
+        $inputs[0] = array();
+        $expect[0] = array('dir' => 'ltr');
         
         // leave existing dir alone
-        $this->assertResult( array('dir' => 'rtl') );
+        $inputs[1] = array('dir' => 'rtl');
+        $expect[1] = array('dir' => 'rtl');
         
-        // use a different default
-        $this->assertResult(
-            array(),
-            array('dir' => 'rtl'),
-            array('Attr.DefaultTextDir' => 'rtl')
-        );
+        $config_rtl = HTMLPurifier_Config::createDefault();
+        $config_rtl->set('Attr', 'DefaultTextDir', 'rtl');
+        $inputs[2] = array();
+        $expect[2] = array('dir' => 'rtl');
+        $config[2] = $config_rtl;
+        
+        $this->assertTransform($inputs, $expect, $config);
         
     }
     

tests/HTMLPurifier/AttrTransform/ImgRequiredTest.php

@@ -5,36 +5,28 @@ require_once 'HTMLPurifier/AttrTransform/ImgRequired.php';
 class HTMLPurifier_AttrTransform_ImgRequiredTest extends HTMLPurifier_AttrTransformHarness
 {
     
-    function setUp() {
-        parent::setUp();
-        $this->obj = new HTMLPurifier_AttrTransform_ImgRequired();
-    }
-    
     function test() {
         
-        $this->assertResult(
-            array(),
-            array('src' => '', 'alt' => 'Invalid image')
-        );
+        $this->transform = new HTMLPurifier_AttrTransform_ImgRequired();
         
-        $this->assertResult(
-            array(),
-            array('src' => 'blank.png', 'alt' => 'Pawned!'),
-            array(
-                'Attr.DefaultInvalidImage' => 'blank.png',
-                'Attr.DefaultInvalidImageAlt' => 'Pawned!'
-            )
-        );
+        $inputs = $expect = $config = array();
         
-        $this->assertResult(
-            array('src' => '/path/to/foobar.png'),
-            array('src' => '/path/to/foobar.png', 'alt' => 'foobar.png')
-        );
+        $inputs[0] = array();
+        $expect[0] = array('src' => '', 'alt' => 'Invalid image');
         
-        $this->assertResult(
-            array('alt' => 'intrigue'),
-            array('src' => '', 'alt' => 'intrigue')
-        );
+        $inputs[1] = array();
+        $expect[1] = array('src' => 'blank.png', 'alt' => 'Pawned!');
+        $config[1] = HTMLPurifier_Config::createDefault();
+        $config[1]->set('Attr', 'DefaultInvalidImage', 'blank.png');
+        $config[1]->set('Attr', 'DefaultInvalidImageAlt', 'Pawned!');
+        
+        $inputs[2] = array('src' => '/path/to/foobar.png');
+        $expect[2] = array('src' => '/path/to/foobar.png', 'alt' => 'foobar.png');
+        
+        $inputs[3] = array('alt' => 'intrigue');
+        $expect[3] = array('src' => '', 'alt' => 'intrigue');
+        
+        $this->assertTransform($inputs, $expect, $config);
         
     }
     

tests/HTMLPurifier/AttrTransform/LangTest.php

@@ -8,39 +8,34 @@ class HTMLPurifier_AttrTransform_LangTest
     extends HTMLPurifier_AttrTransformHarness
 {
     
-    function setUp() {
-        parent::setUp();
-        $this->obj = new HTMLPurifier_AttrTransform_Lang();
-    }
-    
     function test() {
         
+        $this->transform = new HTMLPurifier_AttrTransform_Lang();
+        
+        $inputs = array();
+        $expect = array();
+        
         // leave non-lang'ed elements alone
-        $this->assertResult(array(), true);
+        $inputs[0] = array();
+        $expect[0] = true;
         
         // copy lang to xml:lang
-        $this->assertResult(
-            array('lang' => 'en'),
-            array('lang' => 'en', 'xml:lang' => 'en')
-        );
+        $inputs[1] = array('lang' => 'en');
+        $expect[1] = array('lang' => 'en', 'xml:lang' => 'en');
         
         // preserve attributes
-        $this->assertResult(
-            array('src' => 'vert.png', 'lang' => 'fr'),
-            array('src' => 'vert.png', 'lang' => 'fr', 'xml:lang' => 'fr')
-        );
+        $inputs[2] = array('src' => 'vert.png', 'lang' => 'fr');
+        $expect[2] = array('src' => 'vert.png', 'lang' => 'fr', 'xml:lang' => 'fr');
         
         // copy xml:lang to lang
-        $this->assertResult(
-            array('xml:lang' => 'en'),
-            array('lang' => 'en', 'xml:lang' => 'en')
-        );
+        $inputs[3] = array('xml:lang' => 'en');
+        $expect[3] = array('lang' => 'en', 'xml:lang' => 'en');
         
         // both set, override lang with xml:lang
-        $this->assertResult(
-            array('lang' => 'fr', 'xml:lang' => 'de'),
-            array('lang' => 'de', 'xml:lang' => 'de')
-        );
+        $inputs[4] = array('lang' => 'fr', 'xml:lang' => 'de');
+        $expect[4] = array('lang' => 'de', 'xml:lang' => 'de');
+        
+        $this->assertTransform($inputs, $expect);
         
     }
     

tests/HTMLPurifier/AttrTransform/TextAlignTest.php

@@ -5,58 +5,48 @@ require_once 'HTMLPurifier/AttrTransform/TextAlign.php';
 class HTMLPurifier_AttrTransform_TextAlignTest extends HTMLPurifier_AttrTransformHarness
 {
     
-    function setUp() {
-        parent::setUp();
-        $this->obj = new HTMLPurifier_AttrTransform_TextAlign();
-    }
-    
     function test() {
         
+        $this->transform = new HTMLPurifier_AttrTransform_TextAlign();
+        
+        $inputs = array();
+        $expect = array();
+        
         // leave empty arrays alone
-        $this->assertResult( array() );
+        $inputs[0] = array();
+        $expect[0] = true;
         
         // leave arrays without interesting stuff alone
-        $this->assertResult( array('style' => 'font-weight:bold;') );
+        $inputs[1] = array('style' => 'font-weight:bold;');
+        $expect[1] = true;
         
         // test each of the conversions
         
-        $this->assertResult(
-            array('align' => 'left'),
-            array('style' => 'text-align:left;')
-        );
+        $inputs[2] = array('align' => 'left');
+        $expect[2] = array('style' => 'text-align:left;');
         
-        $this->assertResult(
-            array('align' => 'right'),
-            array('style' => 'text-align:right;')
-        );
+        $inputs[3] = array('align' => 'right');
+        $expect[3] = array('style' => 'text-align:right;');
         
-        $this->assertResult(
-            array('align' => 'center'),
-            array('style' => 'text-align:center;')
-        );
+        $inputs[4] = array('align' => 'center');
+        $expect[4] = array('style' => 'text-align:center;');
         
-        $this->assertResult(
-            array('align' => 'justify'),
-            array('style' => 'text-align:justify;')
-        );
+        $inputs[5] = array('align' => 'justify');
+        $expect[5] = array('style' => 'text-align:justify;');
         
         // drop garbage value
-        $this->assertResult(
-            array('align' => 'invalid'),
-            array()
-        );
+        $inputs[6] = array('align' => 'invalid');
+        $expect[6] = array();
         
         // test CSS munging
-        $this->assertResult(
-            array('align' => 'left', 'style' => 'font-weight:bold;'),
-            array('style' => 'text-align:left;font-weight:bold;')
-        );
+        $inputs[7] = array('align' => 'left', 'style' => 'font-weight:bold;');
+        $expect[7] = array('style' => 'text-align:left;font-weight:bold;');
         
         // test case insensitivity
-        $this->assertResult(
-            array('align' => 'CENTER'),
-            array('style' => 'text-align:center;')
-        );
+        $inputs[8] = array('align' => 'CENTER');
+        $expect[8] = array('style' => 'text-align:center;');
+        
+        $this->assertTransform($inputs, $expect);
         
     }
     

tests/HTMLPurifier/AttrTransformHarness.php

@@ -1,12 +1,18 @@
 <?php
 
-require_once 'HTMLPurifier/Harness.php';
-
-class HTMLPurifier_AttrTransformHarness extends HTMLPurifier_Harness
+class HTMLPurifier_AttrTransformHarness extends UnitTestCase
 {
     
-    function setUp() {
-        $this->func = 'transform';
+    var $transform;
+    
+    function assertTransform($inputs, $expect, $config = array()) {
+        $default_config = HTMLPurifier_Config::createDefault();
+        foreach ($inputs as $i => $input) {
+            if (!isset($config[$i])) $config[$i] = $default_config;
+            $result = $this->transform->transform($input, $config[$i]);
+            if ($expect[$i] === true) $expect[$i] = $input;
+            $this->assertEqual($expect[$i], $result, "Test $i: %s");
+        }
     }
     
 }

tests/HTMLPurifier/ChildDefTest.php

@@ -1,78 +1,122 @@
 <?php
 
-require_once 'HTMLPurifier/Harness.php';
-
 require_once 'HTMLPurifier/ChildDef.php';
 require_once 'HTMLPurifier/Lexer/DirectLex.php';
 require_once 'HTMLPurifier/Generator.php';
 
-class HTMLPurifier_ChildDefTest extends HTMLPurifier_Harness
+class HTMLPurifier_ChildDefTest extends UnitTestCase
 {
     
-    function setUp() {
-        $this->obj       = null;
-        $this->func      = 'validateChildren';
-        $this->to_tokens = true;
-        $this->to_html   = true;
+    var $def;
+    var $lex;
+    var $gen;
+    
+    function HTMLPurifier_ChildDefTest() {
+        // it is vital that the tags be treated as literally as possible
+        $this->lex = new HTMLPurifier_Lexer_DirectLex();
+        $this->gen = new HTMLPurifier_Generator();
+        parent::UnitTestCase();
+    }
+    
+    function assertSeries($inputs, $expect, $config, $context = array()) {
+        foreach ($inputs as $i => $input) {
+            
+            if (!isset($context[$i])) {
+                $context[$i] = null;
+            }
+            if (!isset($config[$i])) {
+                $config[$i] = HTMLPurifier_Config::createDefault();
+            }
+            
+            $tokens = $this->lex->tokenizeHTML($input, $config[$i]);
+            $result = $this->def->validateChildren($tokens, $config[$i], $context[$i]);
+            
+            if (is_bool($expect[$i])) {
+                $this->assertIdentical($expect[$i], $result, "Test $i: %s");
+            } else {
+                $result_html = $this->gen->generateFromTokens($result, $config[$i]);
+                $this->assertIdentical($expect[$i], $result_html, "Test $i: %s");
+                paintIf($result_html, $result_html != $expect[$i]);
+            }
+        }
     }
     
     function test_custom() {
         
-        $this->obj = new HTMLPurifier_ChildDef_Custom('(a,b?,c*,d+,(a,b)*)');
+        $this->def = new HTMLPurifier_ChildDef_Custom(
+            '(a, b?, c*, d+, (a, b)*)');
         
-        $this->assertResult('', false);
-        $this->assertResult('<a /><a />', false);
+        $inputs = array();
+        $expect = array();
+        $config = array();
         
-        $this->assertResult('<a /><b /><c /><d /><a /><b />');
-        $this->assertResult('<a /><d>Dob</d><a /><b>foo</b>'.
-          '<a href="moo" /><b>foo</b>');
+        $inputs[0] = '';
+        $expect[0] = false;
         
+        $inputs[1] = '<a /><b /><c /><d /><a /><b />';
+        $expect[1] = true;
+        
+        $inputs[2] = '<a /><d>Dob</d><a /><b>foo</b><a href="moo" /><b>foo</b>';
+        $expect[2] = true;
+        
+        $inputs[3] = '<a /><a />';
+        $expect[3] = false;
+        
+        $this->assertSeries($inputs, $expect, $config);
     }
     
     function test_table() {
         
+        // currently inactive, awaiting augmentation
+        
         // the table definition
-        $this->obj = new HTMLPurifier_ChildDef_Table();
+        $this->def = new HTMLPurifier_ChildDef_Table();
         
         $inputs = $expect = $config = array();
         
-        $this->assertResult('', false);
+        $inputs[0] = '';
+        $expect[0] = false;
         
         // we're using empty tags to compact the tests: under real circumstances
         // there would be contents in them
         
-        $this->assertResult('<tr />');
-        $this->assertResult('<caption /><col /><thead /><tfoot /><tbody>'.
-            '<tr><td>asdf</td></tr></tbody>');
-        $this->assertResult('<col /><col /><col /><tr />');
+        $inputs[1] = '<tr />';
+        $expect[1] = true;
+        
+        $inputs[2] = '<caption /><col /><thead /><tfoot /><tbody>'.
+            '<tr><td>asdf</td></tr></tbody>';
+        $expect[2] = true;
+        
+        $inputs[3] = '<col /><col /><col /><tr />';
+        $expect[3] = true;
         
         // mixed up order
-        $this->assertResult(
-          '<col /><colgroup /><tbody /><tfoot /><thead /><tr>1</tr><caption /><tr />',
-          '<caption /><col /><colgroup /><thead /><tfoot /><tbody /><tr>1</tr><tr />');
+        $inputs[4] = '<col /><colgroup /><tbody /><tfoot /><thead /><tr>1</tr><caption /><tr />';
+        $expect[4] = '<caption /><col /><colgroup /><thead /><tfoot /><tbody /><tr>1</tr><tr />';
         
         // duplicates of singles
         // - first caption serves
         // - trailing tfoots/theads get turned into tbodys
-        $this->assertResult(
-          '<caption>1</caption><caption /><tbody /><tbody /><tfoot>1</tfoot><tfoot />',
-          '<caption>1</caption><tfoot>1</tfoot><tbody /><tbody /><tbody />'
-        );
+        $inputs[5] = '<caption>1</caption><caption /><tbody /><tbody /><tfoot>1</tfoot><tfoot />';
+        $expect[5] = '<caption>1</caption><tfoot>1</tfoot><tbody /><tbody /><tbody />';
         
         // errant text dropped (until bubbling is implemented)
-        $this->assertResult('foo', false);
+        $inputs[6] = 'foo';
+        $expect[6] = false;
         
         // whitespace sticks to the previous element, last whitespace is
         // stationary
-        $this->assertResult("\n   <tr />\n  <tr />\n ");
-        $this->assertResult(
-          "\n\t<tbody />\n\t\t<tfoot />\n\t\t\t",
-          "\n\t\t<tfoot />\n\t<tbody />\n\t\t\t"
-        );
+        $inputs[7] = "\n   <tr />\n  <tr />\n ";
+        $expect[7] = true;
+        
+        $inputs[8] = "\n\t<tbody />\n\t\t<tfoot />\n\t\t\t";
+        $expect[8] = "\n\t\t<tfoot />\n\t<tbody />\n\t\t\t";
+        
+        $this->assertSeries($inputs, $expect, $config);
         
     }
     
-    function testParsing() {
+    function test_parsing() {
         
         $def = new HTMLPurifier_ChildDef_Required('foobar | bang |gizmo');
         $this->assertEqual($def->elements,
@@ -88,78 +132,92 @@ class HTMLPurifier_ChildDefTest extends HTMLPurifier_Harness
             'href' => true
            ,'src'  => true
           ));
-        
     }
     
     function test_required_pcdata_forbidden() {
         
-        $this->obj = new HTMLPurifier_ChildDef_Required('dt | dd');
+        $this->def = new HTMLPurifier_ChildDef_Required('dt | dd');
+        $inputs = $expect = $config = array();
         
-        $this->assertResult('', false);
-        $this->assertResult(
-          '<dt>Term</dt>Text in an illegal location'.
-             '<dd>Definition</dd><b>Illegal tag</b>',
-          '<dt>Term</dt><dd>Definition</dd>');
-        $this->assertResult('How do you do!', false);
+        $inputs[0] = '';
+        $expect[0] = false;
+        
+        $inputs[1] = '<dt>Term</dt>Text in an illegal location'.
+                     '<dd>Definition</dd><b>Illegal tag</b>';
+        
+        $expect[1] = '<dt>Term</dt><dd>Definition</dd>';
+        
+        $inputs[2] = 'How do you do!';
+        $expect[2] = false;
         
         // whitespace shouldn't trigger it
-        $this->assertResult("\n<dd>Definition</dd>       ");
+        $inputs[3] = "\n<dd>Definition</dd>       ";
+        $expect[3] = true;
         
-        $this->assertResult(
-          '<dd>Definition</dd>       <b></b>       ',
-          '<dd>Definition</dd>              '
-        );
-        $this->assertResult("\t      ", false);
+        $inputs[4] ='<dd>Definition</dd>       <b></b>       ';
+        $expect[4] = '<dd>Definition</dd>              ';
+        
+        $inputs[5] = "\t      ";
+        $expect[5] = false;
+        
+        $this->assertSeries($inputs, $expect, $config);
         
     }
     
     function test_required_pcdata_allowed() {
+        $this->def = new HTMLPurifier_ChildDef_Required('#PCDATA | b');
         
-        $this->obj = new HTMLPurifier_ChildDef_Required('#PCDATA | b');
+        $inputs = $expect = $config = array();
         
-        $this->assertResult('<b>Bold text</b><img />', '<b>Bold text</b>');
+        $inputs[0] = '<b>Bold text</b><img />';
+        $expect[0] = '<b>Bold text</b>';
         
         // with child escaping on
-        $this->assertResult(
-            '<b>Bold text</b><img />',
-            '<b>Bold text</b>&lt;img /&gt;',
-            array(
-              'Core.EscapeInvalidChildren' => true
-            )
-        );
+        $inputs[1] = '<b>Bold text</b><img />';
+        $expect[1] = '<b>Bold text</b>&lt;img /&gt;';
+        $config[1] = HTMLPurifier_Config::createDefault();
+        $config[1]->set('Core', 'EscapeInvalidChildren', true);
         
+        $this->assertSeries($inputs, $expect, $config);
     }
     
     function test_optional() {
+        $this->def = new HTMLPurifier_ChildDef_Optional('b | i');
         
-        $this->obj = new HTMLPurifier_ChildDef_Optional('b | i');
+        $inputs = $expect = $config = array();
         
-        $this->assertResult('<b>Bold text</b><img />', '<b>Bold text</b>');
-        $this->assertResult('Not allowed text', '');
+        $inputs[0] = '<b>Bold text</b><img />';
+        $expect[0] = '<b>Bold text</b>';
         
+        $inputs[1] = 'Not allowed text';
+        $expect[1] = '';
+        
+        $this->assertSeries($inputs, $expect, $config);
     }
     
     function test_chameleon() {
         
-        $this->obj = new HTMLPurifier_ChildDef_Chameleon(
-            'b | i',      // allowed only when in inline context
+        $this->def = new HTMLPurifier_ChildDef_Chameleon(
+            'b | i', // allowed only when in inline context
             'b | i | div' // allowed only when in block context
         );
         
-        $this->assertResult(
-            '<b>Allowed.</b>', true,
-            array(), array('ParentType' => 'inline')
-        );
+        $inputs = $expect = $config = array();
+        $context = array();
         
-        $this->assertResult(
-            '<div>Not allowed.</div>', '',
-            array(), array('ParentType' => 'inline')
-        );
+        $inputs[0] = '<b>Allowed.</b>';
+        $expect[0] = true;
+        $context[0] = 'inline';
         
-        $this->assertResult(
-            '<div>Allowed.</div>', true,
-            array(), array('ParentType' => 'block')
-        );
+        $inputs[1] = '<div>Not allowed.</div>';
+        $expect[1] = '';
+        $context[1] = 'inline';
+        
+        $inputs[2] = '<div>Allowed.</div>';
+        $expect[2] = true;
+        $context[2] = 'block';
+        
+        $this->assertSeries($inputs, $expect, $config, $context);
         
     }
     

tests/HTMLPurifier/ConfigSchemaTest.php

@@ -77,6 +77,7 @@ class HTMLPurifier_ConfigSchemaTest extends UnitTestCase
         );
         $this->assertError('Cannot define directive for undefined namespace');
         $this->assertNoErrors();
+        $this->swallowErrors();
         
         
         
@@ -103,6 +104,7 @@ class HTMLPurifier_ConfigSchemaTest extends UnitTestCase
         );
         $this->assertError('Inconsistent default or type, cannot redefine');
         $this->assertNoErrors();
+        $this->swallowErrors();
         
         
         
@@ -148,6 +150,7 @@ class HTMLPurifier_ConfigSchemaTest extends UnitTestCase
         );
         $this->assertError('Cannot define allowed values for undefined directive');
         $this->assertNoErrors();
+        $this->swallowErrors();
         
         
         
@@ -189,6 +192,7 @@ class HTMLPurifier_ConfigSchemaTest extends UnitTestCase
         );
         $this->assertError('Cannot define alias to value that is not allowed');
         $this->assertNoErrors();
+        $this->swallowErrors();
         
         
         
@@ -200,6 +204,7 @@ class HTMLPurifier_ConfigSchemaTest extends UnitTestCase
         );
         $this->assertError('Cannot define alias over allowed value');
         $this->assertNoErrors();
+        $this->swallowErrors();
         
         
         
@@ -211,6 +216,7 @@ class HTMLPurifier_ConfigSchemaTest extends UnitTestCase
         
         $this->assertError('Invalid type for configuration directive');
         $this->assertNoErrors();
+        $this->swallowErrors();
         
         
         
@@ -222,16 +228,7 @@ class HTMLPurifier_ConfigSchemaTest extends UnitTestCase
         
         $this->assertError('Default value does not match directive type');
         $this->assertNoErrors();
-        
-        
-        
-        // define a directive that allows null
-        HTMLPurifier_ConfigSchema::define(
-            'Core', 'Foobaz', null, 'string/null',
-            'Nulls are allowed if you add on /null, cool huh?'
-        );
-        
-        $this->assertNoErrors();
+        $this->swallowErrors();
         
         
         // define a directive with bad characters
@@ -242,6 +239,7 @@ class HTMLPurifier_ConfigSchemaTest extends UnitTestCase
         
         $this->assertError('Directive name must be alphanumeric');
         $this->assertNoErrors();
+        $this->swallowErrors();
         
         // define a namespace with bad characters
         HTMLPurifier_ConfigSchema::defineNamespace(
@@ -250,6 +248,7 @@ class HTMLPurifier_ConfigSchemaTest extends UnitTestCase
         
         $this->assertError('Namespace name must be alphanumeric');
         $this->assertNoErrors();
+        $this->swallowErrors();
         
     }
     
@@ -259,11 +258,7 @@ class HTMLPurifier_ConfigSchemaTest extends UnitTestCase
     }
     
     function assertInvalid($var, $type) {
-        $this->assertTrue(
-            $this->our_copy->isError(
-                $this->our_copy->validate($var, $type)
-            )
-        );
+        $this->assertIdentical($this->our_copy->validate($var, $type), null);
     }
     
     function testValidate() {
@@ -276,7 +271,6 @@ class HTMLPurifier_ConfigSchemaTest extends UnitTestCase
         $this->assertValid(0, 'bool', false);
         $this->assertValid(1, 'bool', true);
         $this->assertInvalid(34, 'bool');
-        $this->assertInvalid(null, 'bool');
         $this->assertValid(array('1', '2', '3'), 'list');
         $this->assertValid(array('1' => true, '2' => true), 'lookup');
         $this->assertValid(array('1', '2'), 'lookup', array('1' => true, '2' => true));
@@ -287,22 +281,6 @@ class HTMLPurifier_ConfigSchemaTest extends UnitTestCase
         
     }
     
-    function testValidate_null() {
-        
-        $this->assertTrue(
-            $this->our_copy->isError(
-                $this->our_copy->validate(null, 'string', false)
-            )
-        );
-        
-        $this->assertFalse(
-            $this->our_copy->isError(
-                $this->our_copy->validate(null, 'string', true)
-            )
-        );
-        
-    }
-    
     function assertMungeFilename($oldname, $newname) {
         $this->assertIdentical(
             $this->our_copy->mungeFilename($oldname),

tests/HTMLPurifier/ConfigTest.php

@@ -37,10 +37,6 @@ class HTMLPurifier_ConfigTest extends UnitTestCase
             'Core', 'Encoding', 'utf-8', 'istring', 'Case insensitivity!'
         );
         
-        HTMLPurifier_ConfigSchema::define(
-            'Extension', 'CanBeNull', null, 'string/null', 'Null or string!'
-        );
-        
         HTMLPurifier_ConfigSchema::defineAllowedValues(
             'Extension', 'Pert', array('foo', 'moo')
         );
@@ -66,21 +62,25 @@ class HTMLPurifier_ConfigTest extends UnitTestCase
         $config->get('Core', 'NotDefined');
         $this->assertError('Cannot retrieve value of undefined directive');
         $this->assertNoErrors();
+        $this->swallowErrors();
         
         // try to set undefined value
         $config->set('Foobar', 'Key', 'foobar');
         $this->assertError('Cannot set undefined directive to value');
         $this->assertNoErrors();
+        $this->swallowErrors();
         
         // try to set not allowed value
         $config->set('Extension', 'Pert', 'wizard');
         $this->assertError('Value not supported');
         $this->assertNoErrors();
+        $this->swallowErrors();
         
         // try to set not allowed value
         $config->set('Extension', 'Pert', 34);
         $this->assertError('Value is of invalid type');
         $this->assertNoErrors();
+        $this->swallowErrors();
         
         // set aliased value
         $config->set('Extension', 'Pert', 'cow');
@@ -92,29 +92,10 @@ class HTMLPurifier_ConfigTest extends UnitTestCase
         $this->assertNoErrors();
         $this->assertIdentical($config->get('Core', 'Encoding'), 'iso-8859-1');
         
-        // set null to directive that allows null
-        $config->set('Extension', 'CanBeNull', null);
-        $this->assertNoErrors();
-        $this->assertIdentical($config->get('Extension', 'CanBeNull'), null);
-        
-        $config->set('Extension', 'CanBeNull', 'foobar');
-        $this->assertNoErrors();
-        $this->assertIdentical($config->get('Extension', 'CanBeNull'), 'foobar');
-        
-        // set null to directive that doesn't allow null
-        $config->set('Extension', 'Pert', null);
-        $this->assertError('Value is of invalid type');
-        $this->assertNoErrors();
-        
     }
     
     function test_getDefinition() {
         
-        // we actually want to use the old copy, because the definition
-        // generation routines have dependencies on configuration values
-        
-        $this->old_copy = HTMLPurifier_ConfigSchema::instance($this->old_copy);
-        
         $config = HTMLPurifier_Config::createDefault();
         $def = $config->getHTMLDefinition();
         $this->assertIsA($def, 'HTMLPurifier_HTMLDefinition');
@@ -124,48 +105,6 @@ class HTMLPurifier_ConfigTest extends UnitTestCase
         
     }
     
-    function test_loadArray() {
-        // setup a few dummy namespaces/directives for our testing
-        HTMLPurifier_ConfigSchema::defineNamespace('Zoo', 'Animals we have.');
-        HTMLPurifier_ConfigSchema::define('Zoo', 'Aadvark', 0, 'int', 'Have?');
-        HTMLPurifier_ConfigSchema::define('Zoo', 'Boar',    0, 'int', 'Have?');
-        HTMLPurifier_ConfigSchema::define('Zoo', 'Camel',   0, 'int', 'Have?');
-        HTMLPurifier_ConfigSchema::define(
-            'Zoo', 'Others', array(), 'list', 'Other animals we have one of.'
-        );
-        
-        $config_manual = HTMLPurifier_Config::createDefault();
-        $config_loadabbr = HTMLPurifier_Config::createDefault();
-        $config_loadfull = HTMLPurifier_Config::createDefault();
-        
-        $config_manual->set('Zoo', 'Aadvark', 3);
-        $config_manual->set('Zoo', 'Boar', 5);
-        $config_manual->set('Zoo', 'Camel', 2000); // that's a lotta camels!
-        $config_manual->set('Zoo', 'Others', array('Peacock', 'Dodo')); // wtf!
-        
-        // condensed form
-        $config_loadabbr->loadArray(array(
-            'Zoo.Aadvark' => 3,
-            'Zoo.Boar' => 5,
-            'Zoo.Camel' => 2000,
-            'Zoo.Others' => array('Peacock', 'Dodo')
-        ));
-        
-        // fully expanded form
-        $config_loadfull->loadArray(array(
-            'Zoo' => array(
-                'Aadvark' => 3,
-                'Boar' => 5,
-                'Camel' => 2000,
-                'Others' => array('Peacock', 'Dodo')
-            )
-        ));
-        
-        $this->assertEqual($config_manual, $config_loadabbr);
-        $this->assertEqual($config_manual, $config_loadfull);
-        
-    }
-    
 }
 
 ?>

tests/HTMLPurifier/ContextTest.php

@@ -1,89 +0,0 @@
-<?php
-
-require_once 'HTMLPurifier/Context.php';
-
-// mocks
-require_once 'HTMLPurifier/IDAccumulator.php';
-
-class HTMLPurifier_ContextTest extends UnitTestCase
-{
-    
-    var $context;
-    
-    function setUp() {
-        $this->context = new HTMLPurifier_Context();
-    }
-    
-    function testStandardUsage() {
-        
-        generate_mock_once('HTMLPurifier_IDAccumulator');
-        
-        $this->assertFalse($this->context->exists('IDAccumulator'));
-        
-        $accumulator =& new HTMLPurifier_IDAccumulatorMock($this);
-        $this->context->register('IDAccumulator', $accumulator);
-        $this->assertTrue($this->context->exists('IDAccumulator'));
-        
-        $accumulator_2 =& $this->context->get('IDAccumulator');
-        $this->assertReference($accumulator, $accumulator_2);
-        
-        $this->context->destroy('IDAccumulator');
-        $this->assertFalse($this->context->exists('IDAccumulator'));
-        $accumulator_3 =& $this->context->get('IDAccumulator');
-        $this->assertError('Attempted to retrieve non-existent variable');
-        $this->assertNull($accumulator_3);
-        
-        $this->context->destroy('IDAccumulator');
-        $this->assertError('Attempted to destroy non-existent variable');
-        
-    }
-    
-    function testReRegister() {
-        
-        $var = true;
-        $this->context->register('OnceOnly', $var);
-        $this->assertNoErrors();
-        
-        $this->context->register('OnceOnly', $var);
-        $this->assertError('Name collision, cannot re-register');
-        
-        // destroy it, now registration is okay
-        $this->context->destroy('OnceOnly');
-        $this->context->register('OnceOnly', $var);
-        $this->assertNoErrors();
-        
-    }
-    
-    function test_loadArray() {
-        
-        // references can be *really* wonky!
-        
-        $context_manual = new HTMLPurifier_Context();
-        $context_load   = new HTMLPurifier_Context();
-        
-        $var1 = 1;
-        $var2 = 2;
-        
-        $context_manual->register('var1', $var1);
-        $context_manual->register('var2', $var2);
-        
-        // you MUST set up the references when constructing the array,
-        // otherwise the registered version will be a copy
-        $array = array(
-            'var1' => &$var1,
-            'var2' => &$var2
-        );
-        
-        $context_load->loadArray($array);
-        $this->assertIdentical($context_manual, $context_load);
-        
-        $var1 = 10;
-        $var2 = 20;
-        
-        $this->assertIdentical($context_manual, $context_load);
-        
-    }
-    
-}
-
-?>

tests/HTMLPurifier/EncoderTest.php

@@ -31,11 +31,10 @@ class HTMLPurifier_EncoderTest extends UnitTestCase
     
     function test_convertToUTF8() {
         $config = HTMLPurifier_Config::createDefault();
-        $context = new HTMLPurifier_Context();
         
         // UTF-8 means that we don't touch it
         $this->assertIdentical(
-            $this->Encoder->convertToUTF8("\xF6", $config, $context),
+            $this->Encoder->convertToUTF8("\xF6", $config),
             "\xF6" // this is invalid
         );
         $this->assertNoErrors();
@@ -44,14 +43,14 @@ class HTMLPurifier_EncoderTest extends UnitTestCase
         
         // Now it gets converted
         $this->assertIdentical(
-            $this->Encoder->convertToUTF8("\xF6", $config, $context),
+            $this->Encoder->convertToUTF8("\xF6", $config),
             "\xC3\xB6"
         );
         
         $config->set('Test', 'ForceNoIconv', true);
         
         $this->assertIdentical(
-            $this->Encoder->convertToUTF8("\xF6", $config, $context),
+            $this->Encoder->convertToUTF8("\xF6", $config),
             "\xC3\xB6"
         );
         
@@ -59,11 +58,10 @@ class HTMLPurifier_EncoderTest extends UnitTestCase
     
     function test_convertFromUTF8() {
         $config = HTMLPurifier_Config::createDefault();
-        $context = new HTMLPurifier_Context();
         
         // UTF-8 means that we don't touch it
         $this->assertIdentical(
-            $this->Encoder->convertFromUTF8("\xC3\xB6", $config, $context),
+            $this->Encoder->convertFromUTF8("\xC3\xB6", $config),
             "\xC3\xB6"
         );
         
@@ -71,14 +69,14 @@ class HTMLPurifier_EncoderTest extends UnitTestCase
         
         // Now it gets converted
         $this->assertIdentical(
-            $this->Encoder->convertFromUTF8("\xC3\xB6", $config, $context),
+            $this->Encoder->convertFromUTF8("\xC3\xB6", $config),
             "\xF6"
         );
         
         $config->set('Test', 'ForceNoIconv', true);
         
         $this->assertIdentical(
-            $this->Encoder->convertFromUTF8("\xC3\xB6", $config, $context),
+            $this->Encoder->convertFromUTF8("\xC3\xB6", $config),
             "\xF6"
         );
         

tests/HTMLPurifier/GeneratorTest.php

@@ -3,9 +3,7 @@
 require_once 'HTMLPurifier/Generator.php';
 require_once 'HTMLPurifier/EntityLookup.php';
 
-require_once 'HTMLPurifier/Harness.php';
-
-class HTMLPurifier_GeneratorTest extends HTMLPurifier_Harness
+class HTMLPurifier_GeneratorTest extends UnitTestCase
 {
     
     var $gen;
@@ -17,16 +15,11 @@ class HTMLPurifier_GeneratorTest extends HTMLPurifier_Harness
         $this->_entity_lookup = HTMLPurifier_EntityLookup::instance();
     }
     
-    function setUp() {
-        $this->obj       = new HTMLPurifier_Generator();
-        $this->func      = null;
-        $this->to_tokens = false;
-        $this->to_html   = false;
-    }
-    
     function test_generateFromToken() {
         
-        $inputs = $expect = array();
+        $inputs = array();
+        $expect = array();
+        $config = array();
         
         $inputs[0] = new HTMLPurifier_Token_Text('Foobar.<>');
         $expect[0] = 'Foobar.&lt;&gt;';
@@ -60,7 +53,7 @@ class HTMLPurifier_GeneratorTest extends HTMLPurifier_Harness
         $expect[7] = $theta_char;
         
         foreach ($inputs as $i => $input) {
-            $result = $this->obj->generateFromToken($input);
+            $result = $this->gen->generateFromToken($input);
             $this->assertEqual($result, $expect[$i]);
             paintIf($result, $result != $expect[$i]);
         }
@@ -69,7 +62,9 @@ class HTMLPurifier_GeneratorTest extends HTMLPurifier_Harness
     
     function test_generateAttributes() {
         
-        $inputs = $expect = array();
+        $inputs = array();
+        $expect = array();
+        $config = array();
         
         $inputs[0] = array();
         $expect[0] = '';
@@ -88,8 +83,10 @@ class HTMLPurifier_GeneratorTest extends HTMLPurifier_Harness
         $inputs[4] = array('title' => 'Theta is ' . $theta_char);
         $expect[4] = 'title="Theta is ' . $theta_char . '"';
         
+        $default_config = HTMLPurifier_Config::createDefault();
         foreach ($inputs as $i => $input) {
-            $result = $this->obj->generateAttributes($input);
+            if (!isset($config[$i])) $config[$i] = $default_config;
+            $result = $this->gen->generateAttributes($input, $config[$i]);
             $this->assertEqual($result, $expect[$i]);
             paintIf($result, $result != $expect[$i]);
         }
@@ -98,26 +95,34 @@ class HTMLPurifier_GeneratorTest extends HTMLPurifier_Harness
     
     function test_generateFromTokens() {
         
-        $this->func = 'generateFromTokens';
+        $inputs = array();
+        $expect = array();
+        $config = array();
         
-        $this->assertResult(
-            array(
-                new HTMLPurifier_Token_Start('b'),
-                new HTMLPurifier_Token_Text('Foobar!'),
-                new HTMLPurifier_Token_End('b')
-            ),
-            '<b>Foobar!</b>'
-        );
+        $inputs[0] = array(
+            new HTMLPurifier_Token_Start('b'),
+            new HTMLPurifier_Token_Text('Foobar!'),
+            new HTMLPurifier_Token_End('b')
+            );
+        $expect[0] = '<b>Foobar!</b>';
+        
+        $inputs[1] = array();
+        $expect[1] = '';
+        
+        $default_config = HTMLPurifier_Config::createDefault();
+        foreach ($inputs as $i => $input) {
+            if (!isset($config[$i])) $config[$i] = $default_config;
+            $result = $this->gen->generateFromTokens($input, $config[$i]);
+            $this->assertEqual($expect[$i], $result);
+            paintIf($result, $result != $expect[$i]);
+        }
         
-        $this->assertResult(array(), '');
         
     }
     
     var $config;
     function assertGeneration($tokens, $expect) {
-        $context = new HTMLPurifier_Context();
-        $result = $this->gen->generateFromTokens(
-          $tokens, $this->config, $context);
+        $result = $this->gen->generateFromTokens($tokens, $this->config);
         // normalized newlines, this probably should be put somewhere else
         $result = str_replace("\r\n", "\n", $result);
         $result = str_replace("\r", "\n", $result);

tests/HTMLPurifier/Harness.php

@@ -1,106 +0,0 @@
-<?php
-
-require_once 'HTMLPurifier/Lexer/DirectLex.php';
-
-/**
- * General-purpose test-harness that makes testing functions that require
- * configuration and context objects easier when those two parameters are
- * meaningless.  See HTMLPurifier_ChildDefTest for a good example of usage.
- */
-class HTMLPurifier_Harness extends UnitTestCase
-{
-    
-    /**
-     * Instance of the object that will execute the method
-     */
-    var $obj;
-    
-    /**
-     * Name of the function to be executed
-     */
-    var $func;
-    
-    /**
-     * Whether or not the method deals in tokens. If set to true, assertResult()
-     * will transparently convert HTML to and back from tokens.
-     */
-    var $to_tokens = false;
-    
-    /**
-     * Whether or not to convert tokens back into HTML before performing
-     * equality check, has no effect on bools.
-     */
-    var $to_html = false;
-    
-    /**
-     * Instance of an HTMLPurifier_Lexer implementation.
-     */
-    var $lexer;
-    
-    /**
-     * Instance of HTMLPurifier_Generator
-     */
-    var $generator;
-    
-    function HTMLPurifier_Harness() {
-        $this->lexer     = new HTMLPurifier_Lexer_DirectLex();
-        $this->generator = new HTMLPurifier_Generator();
-        parent::UnitTestCase();
-    }
-    
-    /**
-     * Asserts a specific result from a one parameter + config/context function
-     * @param $input Input parameter
-     * @param $expect Expectation
-     * @param $config_array Configuration array in form of
-     *                      Namespace.Directive => Value or an actual config
-     *                      object.
-     * @param $context_array Context array in form of Key => Value or an actual
-     *                       context object.
-     */
-    function assertResult($input, $expect = true,
-        $config_array = array(), $context_array = array()
-    ) {
-        
-        // setup config object
-        $config  = HTMLPurifier_Config::createDefault();
-        $config->loadArray($config_array);
-        
-        // setup context object. Note that we are operating on a copy of it!
-        // We will extend the test harness to allow you to do post-tests
-        // on the context object
-        $context = new HTMLPurifier_Context();
-        $context->loadArray($context_array);
-        
-        if ($this->to_tokens && is_string($input)) {
-            $input = $this->lexer->tokenizeHTML($input, $config, $context);
-        }
-        
-        // call the function
-        $func = $this->func;
-        $result = $this->obj->$func($input, $config, $context);
-        
-        // test a bool result
-        if (is_bool($result)) {
-            $this->assertIdentical($expect, $result);
-            return;
-        } elseif (is_bool($expect)) {
-            $expect = $input;
-        }
-        
-        if ($this->to_html) {
-            $result = $this->generator->
-              generateFromTokens($result, $config, $context);
-            if (is_array($expect)) {
-                $expect = $this->generator->
-                  generateFromTokens($expect, $config, $context);
-            }
-        }
-        
-        $this->assertEqual($expect, $result);
-        
-    }
-    
-}
-
-?>

tests/HTMLPurifier/Lexer/DirectLexTest.php

@@ -53,11 +53,9 @@ class HTMLPurifier_Lexer_DirectLexTest extends UnitTestCase
         $input[10] = 'name="input" selected';
         $expect[10] = array('name' => 'input', 'selected' => 'selected');
         
-        $config = HTMLPurifier_Config::createDefault();
-        $context = new HTMLPurifier_Context();
         $size = count($input);
         for($i = 0; $i < $size; $i++) {
-            $result = $this->DirectLex->parseAttributeString($input[$i], $config, $context);
+            $result = $this->DirectLex->parseAttributeString($input[$i]);
             $this->assertEqual($expect[$i], $result, 'Test ' . $i . ': %s');
             paintIf($result, $expect[$i] != $result);
         }

tests/HTMLPurifier/LexerTest.php

@@ -279,17 +279,16 @@ class HTMLPurifier_LexerTest extends UnitTestCase
         $expect[18] = array( new HTMLPurifier_Token_Empty('br', array('test' => 'x < 6')) );
         
         $default_config = HTMLPurifier_Config::createDefault();
-        $default_context = new HTMLPurifier_Context();
         foreach($input as $i => $discard) {
             if (!isset($config[$i])) $config[$i] = $default_config;
             
-            $result = $this->DirectLex->tokenizeHTML($input[$i], $config[$i], $default_context);
+            $result = $this->DirectLex->tokenizeHTML($input[$i], $config[$i]);
             $this->assertEqual($expect[$i], $result, 'DirectLexTest '.$i.': %s');
             paintIf($result, $expect[$i] != $result);
             
             if ($this->_has_pear) {
                 // assert unless I say otherwise
-                $sax_result = $this->PEARSax3->tokenizeHTML($input[$i], $config[$i], $default_context);
+                $sax_result = $this->PEARSax3->tokenizeHTML($input[$i], $config[$i]);
                 if (!isset($sax_expect[$i])) {
                     // by default, assert with normal result
                     $this->assertEqual($expect[$i], $sax_result, 'PEARSax3Test '.$i.': %s');
@@ -305,7 +304,7 @@ class HTMLPurifier_LexerTest extends UnitTestCase
             }
             
             if ($this->_has_dom) {
-                $dom_result = $this->DOMLex->tokenizeHTML($input[$i], $config[$i], $default_context);
+                $dom_result = $this->DOMLex->tokenizeHTML($input[$i], $config[$i]);
                 // same structure as SAX
                 if (!isset($dom_expect[$i])) {
                     $this->assertEqual($expect[$i], $dom_result, 'DOMLexTest '.$i.': %s');