1.0.0beta release tag.

git-svn-id: http://htmlpurifier.org/svnroot/htmlpurifier/tags/1.0.0beta@285 48356398-32a2-884e-a903-53898d9a118a

Doxyfile

@@ -3,8 +3,8 @@
 #---------------------------------------------------------------------------
 # Project related configuration options
 #---------------------------------------------------------------------------
-PROJECT_NAME           = HTML Purifier
-PROJECT_NUMBER         = 1.1.2
+PROJECT_NAME           = HTMLPurifier
+PROJECT_NUMBER         = trunk
 OUTPUT_DIRECTORY       = "C:/Documents and Settings/Edward/My Documents/My Webs/htmlpurifier/docs/doxygen"
 CREATE_SUBDIRS         = NO
 OUTPUT_LANGUAGE        = English
@@ -88,13 +88,7 @@ RECURSIVE              = YES
 EXCLUDE                = 
 EXCLUDE_SYMLINKS       = NO
 EXCLUDE_PATTERNS       = */tests/* \
-                         */benchmarks/* \
-                         */docs/* \
-                         */test-settings.php \
-                         */configdoc/* \
-                         */test-settings.php \
-                         */maintenance/* \
-                         */smoketests/*
+                         */benchmarks/*
 EXAMPLE_PATH           = 
 EXAMPLE_PATTERNS       = *
 EXAMPLE_RECURSIVE      = NO

INSTALL

@@ -1,189 +1,61 @@
 
 Install
-    How to install HTML Purifier
+    How to install HTMLPurifier
 
-HTML Purifier is designed to run out of the box,  so actually using the library
-is extremely easy. (Although, if you were looking for a step-by-step
-installation GUI, you've come to the wrong place!)  The impatient can scroll
-down to the bottom of this INSTALL document to see the code, but you really
-should make sure a few things are properly done.
+Being a library, there's no fancy GUI that will take you step-by-step through
+configuring database credentials and other mumbo-jumbo.  HTMLPurifier is
+designed to run "out of the box."  Regardless, there are still a couple of
+things you should be mindful of.
 
 
 
-1.  Compatibility
+1.  Including the proper files
 
-HTML Purifier works in both PHP 4 and PHP 5, from PHP 4.3.9 and up. It has no
-core dependencies with other libraries. (Whoopee!)
+The library/ directory must be added to your path: HTMLPurifier will not be
+able to find the necessary includes otherwise.  This is as simple as:
 
-Optional extensions are iconv (usually installed) and tidy (also common).
-If you use UTF-8 and don't plan on pretty-printing HTML, you can get away with
-not having either of these extensions.
+set_include_path('/path/to/htmlpurifier/library' . PATH_SEPARATOR . get_include_path());
 
+...replacing /path/to/htmlpurifier with the actual location of the folder. Don't
+worry, HTMLPurifier is namespaced so unless you have another file named
+HTMLPurifier.php, the files won't collide with any of your includes.
 
+Then, it's a simple matter of including the base file:
 
-2.  Including the library
+require_once 'HTMLPurifier.php';
 
-Simply use:
+...and you're good to go.
 
-	require_once '/path/to/library/HTMLPurifier.auto.php';
 
-...and you're good to go.  Since HTML Purifier's codebase is fairly
-large, I recommend only including HTML Purifier when you need it.
 
-If you don't like your include_path to be fiddled around with, simply set
-HTML Purifier's library/ directory to the include path yourself and then:
+2.  Preparing the proper environment
 
-	require_once 'HTMLPurifier.php';
+While no configuration is necessary, you first should take precautions regarding
+the other output HTML that the filtered content will be going along with.  Here
+is a (short) checklist:
 
-Only the contents in the library/ folder are necessary, so you can remove
-everything else when using HTML Purifier in a production environment.  
+ * Have I specified XHTML 1.0 Transitional as the doctype?
+ * Have I specified UTF-8 as the character encoding?
 
+I cannot stress the importance of these two bullets enough.  Omitting either
+of them could have dire consequences not only for security but for plain
+old usability.  You can find a more in-depth discussion of why this is needed
+in docs/security.txt, in the meantime, try to change your output so this is
+the case.
 
+If, for some reason, you are unable to switch to UTF-8 immediately, you can
+use iconv to convert the output of HTMLPurifier to your desired encoding.
+We may integrate support for other encodings in later releases, but for now,
+UTF-8 is all you should need.  (If you're not using UTF-8, switch now!)
 
-3.  Preparing the proper output environment
 
-HTML Purifier is all about web-standards, so accordingly your webpages should
-be standards compliant.  HTML Purifier can deal with these doctypes:
 
-* XHTML 1.0 Transitional (default)
-* HTML 4.01 Transitional
+3.   Using the code
 
-...and these character encodings:
+The interface is mind-numbingly simple.
 
-* UTF-8 (default)
-* Any encoding iconv supports (support is crippled for i18n though)
+$purifier = new HTMLPurifier();
+$clean_html = $purifier->purify($dirty_html);
 
-The defaults are there for a reason: they are best-practice choices that
-should not be changed lightly.  For those of you in the dark, you can determine
-the doctype from this code in your HTML documents:
-
-    <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"
-        "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
-
-...and the character encoding from this code:
-
-    <meta http-equiv="Content-type" content="text/html;charset=ENCODING">
-
-For legacy codebases these declarations may be missing.  If that is the case,
-STOP, and read up on character encodings and doctypes (in that order).  Here
-are some links:
-
-* http://www.joelonsoftware.com/articles/Unicode.html
-* http://alistapart.com/stories/doctype/
-
-You may currently be vulnerable to XSS and other security threats, and HTML
-Purifier won't be able to fix that.
-
-
-
-4. Configuration
-
-HTML Purifier is designed to run out-of-the-box, but occasionally HTML
-Purifier needs to be told what to do.  If you answered no to any of these
-questions, read on, otherwise, you can skip to the next section (or, if you're
-into configuring things just for the heck of it, skip to 4.3).
-
-* Am I using UTF-8?
-* Am I using XHTML 1.0 Transitional?
-
-If you answered yes to any of these questions, instantiate a configuration
-object and read on:
-
-    $config = HTMLPurifier_Config::createDefault();
-
-
-
-4.1. Setting a different character encoding
-
-You really shouldn't use any other encoding except UTF-8, especially if you
-plan to support multilingual websites (read section three for more details).
-However, switching to UTF-8 is not always immediately feasible, so we can
-adapt.
-
-HTML Purifier uses iconv to support other character encodings, as such,
-any encoding that iconv supports <http://www.gnu.org/software/libiconv/>
-HTML Purifier supports with this code:
-
-    $config->set('Core', 'Encoding', /* put your encoding here */);
-
-An example usage for Latin-1 websites (the most common encoding for English
-websites):
-
-    $config->set('Core', 'Encoding', 'ISO-8859-1');
-
-Note that HTML Purifier's support for non-Unicode encodings is crippled by the
-fact that any character not supported by that encoding will be silently
-dropped, EVEN if it is ampersand escaped.  This is a current limitation of
-HTML Purifier that we are NOT actively working to fix.  Patches are welcome,
-but there are so many other gotchas and problems in I18N for non-Unicode
-encodings that this functionality is low priority.  See
-<http://ppewww.ph.gla.ac.uk/~flavell/charset/form-i18n.html> for a more
-detailed lowdown on the topic.
-
-
-
-4.2. Setting a different doctype
-
-For those of you stuck using HTML 4.01 Transitional, you can disable
-XHTML output like this:
-
-    $config->set('Core', 'XHTML', false);
-
-I recommend that you use XHTML, although not as much as I recommend UTF-8.  If
-your HTML 4.01 page validates, good for you!
-
-Currently, we can only guarantee transitional-complaint output, future
-versions will also allow strict-compliant output.
-
-
-
-4.3. Other settings
-
-There are more configuration directives which can be read about
-here: <http://hp.jpsband.org/live/configdoc/plain.html>  They're a bit boring,
-but they can help out for those of you who like to exert maximum control over
-your code.
-
-
-
-5.   Using the code
-
-The interface is mind-numbingly simple:
-
-    $purifier = new HTMLPurifier();
-    $clean_html = $purifier->purify( $dirty_html );
-
-...or, if you're using the configuration object:
-
-    $purifier = new HTMLPurifier($config);
-    $clean_html = $purifier->purify( $dirty_html );
-
-That's it!  For more examples, check out docs/examples/ (they aren't very
-different though).  Also, SLOW gives advice on what to do if HTML Purifier
-is slowing down your application.
-
-
-
-6.   Quick install
-
-If your website is in UTF-8 and XHTML Transitional, use this code:
-
-<?php
-    require_once '/path/to/htmlpurifier/library/HTMLPurifier.auto.php';
-    
-    $purifier = new HTMLPurifier();
-    $clean_html = $purifier->purify($dirty_html);
-?>
-
-If your website is in a different encoding or doctype, use this code:
-
-<?php
-    require_once '/path/to/htmlpurifier/library/HTMLPurifier.auto.php';
-    
-    $config = HTMLPurifier_Config::createDefault();
-    $config->set('Core', 'Encoding', 'ISO-8859-1'); //replace with your encoding
-    $config->set('Core', 'XHTML', true); //replace with false if HTML 4.01
-    $purifier = new HTMLPurifier($config);
-    
-    $clean_html = $purifier->purify($dirty_html);
-?>
+That's it.  For more examples, check out docs/examples/.  Also, SLOW gives
+advice on what to do if HTMLPurifier is slowing down your application.

NEWS

@@ -1,67 +1,9 @@
 NEWS ( CHANGELOG and HISTORY )                                     HTMLPurifier
 |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
 
-= KEY ====================
-    ! Feature
-    - Bugfix
-      + Sub-comment
-    . Internal change
-==========================
-
-1.1.2, released 2006-09-30
-! Add HTMLPurifier.auto.php stub file that configures include_path
-- Documentation updated
-  + INSTALL document rewritten
-  + TODO added semi-lossy conversion
-  + API Doxygen docs' file exclusions updated
-  + Added notes on HTML versus XML attribute whitespace handling
-  + Noted that HTMLPurifier_ChildDef_Custom isn't being used
-  + Noted that config object's definitions are cached versions
-- Fixed lack of attribute parsing in HTMLPurifier_Lexer_PEARSax3
-- ftp:// URIs now have their typecodes checked
-- Hooked up HTMLPurifier_ChildDef_Custom's unit tests (they weren't being run)
-. Line endings standardized throughout project (svn:eol-style standardized)
-. Refactored parseData() to general Lexer class
-. Tester named "HTML Purifier" not "HTMLPurifier"
-
-1.1.1, released 2006-09-24
-! Configuration option to optionally Tidy up output for indentation to make up
-  for dropped whitespace by DOMLex (pretty-printing for the entire application
-  should be done by a page-wide Tidy)
-- Various documentation updates
-- Fixed parse error in configuration documentation script
-- Fixed fatal error in benchmark scripts, slightly augmented
-- As far as possible, whitespace is preserved in-between table children
-- Sample test-settings.php file included
-
-1.1.0, released 2006-09-16
-! Directive documentation generation using XSLT
-! XHTML can now be turned off, output becomes <br>
-- Made URI validator more forgiving: will ignore leading and trailing
-  quotes, apostrophes and less than or greater than signs.
-- Enforce alphanumeric namespace and directive names for configuration.
-- Table child definition made more flexible, will fix up poorly ordered elements
-. Renamed ConfigDef to ConfigSchema
-
-1.0.1, released 2006-09-04
-- Fixed slight bug in DOMLex attribute parsing
-- Fixed rejection of case-insensitive configuration values when there is a
-  set of allowed values.  This manifested in %Core.Encoding.
-- Fixed rejection of inline style declarations that had lots of extra
-  space in them.  This manifested in TinyMCE.
-
-1.0.0, released 2006-09-01
-! Shorthand CSS properties implemented: font, border, background, list-style
-! Basic color keywords translated into hexadecimal values
-! Table CSS properties implemented
-! Support for charsets other than UTF-8 (defined by iconv)
-! Malformed UTF-8 and non-SGML character detection and cleaning implemented
-- Fixed broken numeric entity conversion
-- API documentation completed
-. (HTML|CSS)Definition de-singleton-ized
-
 1.0.0beta, released 2006-08-16
-! First public release, most functionality implemented. Notable omissions are:
-  + Shorthand CSS properties
-  + Table CSS properties
-  + Deprecated attribute transformations
+- First public release, most functionality implemented. Notable omissions are:
+  . Shorthand CSS properties
+  . Table CSS properties
+  . IPv6 validation
+  . Deprecated attribute transformations

README

@@ -1,13 +1,13 @@
+
+README
+    All about HTMLPurifier
 
-README
-    All about HTMLPurifier
-
-HTMLPurifier is an HTML filtering solution.  It uses a unique combination of
-robust whitelists and agressive parsing to ensure that not only are XSS
-attacks thwarted, but the resulting HTML is standards compliant.
-
-See INSTALL on how to use the library.  See docs/ for more developer-oriented
-documentation as well as some code examples.  Users of TinyMCE or FCKeditor
-may be especially interested in WYSIWYG.
-
-HTMLPurifier can be found on the web at: http://hp.jpsband.org/
+HTMLPurifier is an HTML filtering solution.  It uses a unique combination of
+robust whitelists and agressive parsing to ensure that not only are XSS
+attacks thwarted, but the resulting HTML is standards compliant.
+
+See INSTALL on how to use the library.  See docs/ for more developer-oriented
+documentation as well as some code examples.  Users of TinyMCE or FCKeditor
+may be especially interested in WYSIWYG.
+
+HTMLPurifier can be found on the web at: http://hp.jpsband.org/

SLOW

@@ -17,23 +17,18 @@ second tacked on to the load time probably isn't going to be that huge of
 a problem.  Then, displaying the content is a simple a manner of outputting
 it directly from your database/filesystem.  The trouble with this method is
 that your user loses the original text, and when doing edits, will be
-handling the filtered text.  While this may be a good thing, especially if
-you're using a WYSIWYG editor, it can also result in data-loss if a user
-expects a certain to be available but it doesn't.
+handling the filtered text.  Of course, maybe that's a good thing.  If you
+don't mind a little extra complexity, you can try...
 
 2. Caching the filtered output - accept the submitted text and put it
 unaltered into the database, but then also generate a filtered version and
 stash that in the database.  Serve the filtered version to readers, and the
 unaltered version to editors.  If need be, you can invalidate the cache and
 have the cached filtered version be regenerated on the first page view.  Pros?
-Full data retention.  Cons?  It's more complicated, and opens other editors
-up to XSS if they are using a WYSIWYG editor (to fix that, they'd have to
-be able to get their hands on the *really* original text served in plaintext
-mode).
+Full data retention.  Cons?  It's more complicated.
 
 In short, inbound filtering is almost as simple as outbound filtering, but
 it has some drawbacks which cannot be fixed unless you save both the original
 and the filtered versions.
 
-There is a third option: profile and optimize HTMLPurifier yourself.  Be sure
-to tell me if you decide to do that!  ;-)
+There is a third option: profile and optimize HTMLPurifier yourself.  ;-)

TODO

@@ -1,53 +1,19 @@
+Todo List
 
-TODO List
+Core:
+ - Finish table and shorthand CSS attributes
+ - Implement all non-essential attribute transforms
 
-Ongoing
- - Lots of profiling, make it faster!
- - Plugins for major CMSes (very tricky issue)
-
-1.2 release
+Code issues:
+ - Massive profiling, make it faster!
+ - Fix IPv6 issues
  - 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
+ - Factor out Host validation to its own AttrDef
+ - Rewrite table's child definition
+ - Silently drop content inbetween SCRIPT tags
 
-1.3 release
- - Add various "levels" of cleaning
-    - Related: Allow strict (X)HTML
-
-1.4 release
- - Additional support for poorly written HTML
-    - Implement all non-essential attribute transforms
-    - Microsoft Word HTML cleaning (i.e. MsoNormal)
-
-2.0 release
- - Formatters for plaintext
-    - Auto-paragraphing (be sure to leverage fact that we know when things
-      shouldn't be paragraphed, such as lists and tables).
-    - Linkify URLs
-    - Smileys
-
-3.0 release
- - Extended HTML capabilities based on namespacing and tag transforms
-    - Hooks for adding custom processors to custom namespaced tags and
-      attributes, offer default implementation
-    - Lots of documentation and samples
-
-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
- - 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
-
-Wontfix
- - Non-lossy smart alternate character encoding transformations
- - Pretty-printing HTML, users can use Tidy on the output on entire page
+Enhancements:
+ - Do fixes for Firefox's inability to handle COL alignment props (Bug 915)
+ - Pretty-printing HTML

WYSIWYG

@@ -1,6 +1,6 @@
 
 WYSIWYG - What You See Is What You Get
-    HTML Purifier: A Pretty Good Fit for TinyMCE and FCKeditor
+    HTMLPurifier: A Pretty Good Fit for TinyMCE and FCKeditor
 
 Javascript-based WYSIWYG editors, simply stated, are quite amazing.  But I've
 always been wary about using them due to security issues: they handle the
@@ -13,9 +13,6 @@ other markup languages still reign supreme.  Put simply: filtering HTML is
 hard work, and these WYSIWYG authors don't offer anything to alleviate that
 trouble.  Therein lies the solution:
 
-HTML Purifier is perfect for filtering pure-HTML input from WYSIWYG editors.
+HTMLPurifier is perfect for filtering pure-HTML input from WYSIWYG editors.
 
 Enough said.
-
-There is a proof-of-concept integration of HTML Purifier with the Mantis
-bugtracker at http://hp.jpsband.org/mantis/

benchmarks/Lexer.php

@@ -3,24 +3,15 @@
 // emulates inserting a dir called HTMLPurifier into your class dir
 set_include_path(get_include_path() . PATH_SEPARATOR . '../library/');
 
-@include_once '../test-settings.php';
-
-require_once 'HTMLPurifier/ConfigSchema.php';
+require_once 'HTMLPurifier/ConfigDef.php';
 require_once 'HTMLPurifier/Config.php';
-
-$LEXERS = array();
-$RUNS = isset($GLOBALS['HTMLPurifierTest']['Runs'])
-    ? $GLOBALS['HTMLPurifierTest']['Runs'] : 2; 
-
 require_once 'HTMLPurifier/Lexer/DirectLex.php';
-$LEXERS['DirectLex'] = new HTMLPurifier_Lexer_DirectLex();
+require_once 'HTMLPurifier/Lexer/PEARSax3.php';
 
-if (!empty($GLOBALS['HTMLPurifierTest']['PEAR'])) {
-    require_once 'HTMLPurifier/Lexer/PEARSax3.php';
-    $LEXERS['PEARSax3'] = new HTMLPurifier_Lexer_PEARSax3();
-} else {
-    exit('PEAR required to perform benchmark.');
-}
+$LEXERS = array(
+    'DirectLex' => new HTMLPurifier_Lexer_DirectLex(),
+    'PEARSax3'  => new HTMLPurifier_Lexer_PEARSax3()
+);
 
 if (version_compare(PHP_VERSION, '5', '>=')) {
     require_once 'HTMLPurifier/Lexer/DOMLex.php';
@@ -65,12 +56,9 @@ class RowTimer extends Benchmark_Timer
             if ($standard == false) $standard = $v['diff'];
             
             $perc = $v['diff'] * 100 / $standard;
-            $bad_run = ($v['diff'] < 0);
             
-            $out .= '<td align="right"'.
-                   ($bad_run ? ' style="color:#AAA;"' : '').
-                   '>' . number_format($perc, 2, '.', '') .
-                   '%</td><td>'.number_format($v['diff'],4,'.','').'</td>';
+            $out .= '<td align="right">' . number_format($perc, 2, '.', '') .
+                   '%</td>';
             
         }
         
@@ -91,13 +79,13 @@ function print_lexers() {
 }
 
 function do_benchmark($name, $document) {
-    global $LEXERS, $RUNS;
+    global $LEXERS;
     
     $timer = new RowTimer($name);
     $timer->start();
     
     foreach($LEXERS as $key => $lexer) {
-        for ($i=0; $i<$RUNS; $i++) $tokens = $lexer->tokenizeHTML($document);
+        $tokens = $lexer->tokenizeHTML($document);
         $timer->setMarker($key);
     }
     
@@ -115,7 +103,7 @@ function do_benchmark($name, $document) {
 <table border="1">
 <tr><th>Case</th><?php
 foreach ($LEXERS as $key => $value) {
-    echo '<th colspan="2">' . htmlspecialchars($key) . '</th>';
+    echo '<th>' . htmlspecialchars($key) . '</th>';
 }
 ?></tr>
 <?php

benchmarks/ProfileDirectLex.php

@@ -2,7 +2,7 @@
 
 set_include_path(get_include_path() . PATH_SEPARATOR . '../library/');
 
-require_once 'HTMLPurifier/ConfigSchema.php';
+require_once 'HTMLPurifier/ConfigDef.php';
 require_once 'HTMLPurifier/Config.php';
 require_once 'HTMLPurifier/Lexer/DirectLex.php';
 

configdoc/generate.php

@@ -1,214 +0,0 @@
-<?php
-
-/**
- * Generates XML and HTML documents describing configuration.
- */
-
-/*
-TODO:
-- make XML format richer (see below)
-- extend XSLT transformation (see the corresponding XSLT file)
-- allow generation of packaged docs that can be easily moved
-- multipage documentation
-- determine how to multilingualize
-- factor out code into classes
-- generate a table of contents
-*/
-
-
-// ---------------------------------------------------------------------------
-// Check and configure environment
-
-if (version_compare('5', PHP_VERSION, '>')) exit('Requires PHP 5 or higher.');
-error_reporting(E_ALL);
-
-
-// ---------------------------------------------------------------------------
-// Include HTML Purifier library
-
-set_include_path('../library' . PATH_SEPARATOR . get_include_path());
-require_once 'HTMLPurifier.php';
-
-
-// ---------------------------------------------------------------------------
-// Setup convenience functions
-
-function appendHTMLDiv($document, $node, $html) {
-    global $purifier;
-    $html = $purifier->purify($html);
-    $dom_html = $document->createDocumentFragment();
-    $dom_html->appendXML($html);
-    
-    $dom_div = $document->createElement('div');
-    $dom_div->setAttribute('xmlns', 'http://www.w3.org/1999/xhtml');
-    $dom_div->appendChild($dom_html);
-    
-    $node->appendChild($dom_div);
-}
-
-
-// ---------------------------------------------------------------------------
-// Load copies of HTMLPurifier_ConfigDef and HTMLPurifier
-
-$schema = HTMLPurifier_ConfigSchema::instance();
-$purifier = new HTMLPurifier();
-
-
-// ---------------------------------------------------------------------------
-// Generate types.xml, a document describing the constraint "type"
-
-$types_document = new DOMDocument('1.0', 'UTF-8');
-$types_root = $types_document->createElement('types');
-$types_document->appendChild($types_root);
-$types_document->formatOutput = true;
-foreach ($schema->types as $name => $expanded_name) {
-    $types_type = $types_document->createElement('type', $expanded_name);
-    $types_type->setAttribute('id', $name);
-    $types_root->appendChild($types_type);
-}
-$types_document->save('types.xml');
-
-
-// ---------------------------------------------------------------------------
-// Generate configdoc.xml, a document documenting configuration directives
-
-$dom_document = new DOMDocument('1.0', 'UTF-8');
-$dom_root = $dom_document->createElement('configdoc');
-$dom_document->appendChild($dom_root);
-$dom_document->formatOutput = true;
-
-// add the name of the application
-$dom_root->appendChild($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
-*/
-
-foreach($schema->info as $namespace_name => $namespace_info) {
-    
-    $dom_namespace = $dom_document->createElement('namespace');
-    $dom_root->appendChild($dom_namespace);
-    
-    $dom_namespace->setAttribute('id', $namespace_name);
-    $dom_namespace->appendChild(
-        $dom_document->createElement('name', $namespace_name)
-    );
-    $dom_namespace_description = $dom_document->createElement('description');
-    $dom_namespace->appendChild($dom_namespace_description);
-    appendHTMLDiv($dom_document, $dom_namespace_description,
-        $schema->info_namespace[$namespace_name]->description);
-    
-    foreach ($namespace_info as $name => $info) {
-        
-        $dom_directive = $dom_document->createElement('directive');
-        $dom_namespace->appendChild($dom_directive);
-        
-        $dom_directive->setAttribute('id', $namespace_name . '.' . $name);
-        $dom_directive->appendChild(
-            $dom_document->createElement('name', $name)
-        );
-        
-        $dom_constraints = $dom_document->createElement('constraints');
-        $dom_directive->appendChild($dom_constraints);
-        
-        $dom_constraints->appendChild(
-            $dom_document->createElement('type', $info->type)
-        );
-        if ($info->allowed !== true) {
-            $dom_allowed = $dom_document->createElement('allowed');
-            $dom_constraints->appendChild($dom_allowed);
-            foreach ($info->allowed as $allowed => $bool) {
-                $dom_allowed->appendChild(
-                    $dom_document->createElement('value', $allowed)
-                );
-            }
-        }
-        
-        $raw_default = $schema->defaults[$namespace_name][$name];
-        if (is_bool($raw_default)) {
-            $default = $raw_default ? 'true' : 'false';
-        } elseif (is_string($raw_default)) {
-            $default = "\"$raw_default\"";
-        } else {
-            $default = print_r(
-                    $schema->defaults[$namespace_name][$name], true
-                );
-        }
-        $dom_constraints->appendChild(
-            $dom_document->createElement('default', $default)
-        );
-        
-        $dom_descriptions = $dom_document->createElement('descriptions');
-        $dom_directive->appendChild($dom_descriptions);
-        
-        foreach ($info->descriptions as $file => $file_descriptions) {
-            foreach ($file_descriptions as $line => $description) {
-                $dom_description = $dom_document->createElement('description');
-                $dom_description->setAttribute('file', $file);
-                $dom_description->setAttribute('line', $line);
-                appendHTMLDiv($dom_document, $dom_description, $description);
-                $dom_descriptions->appendChild($dom_description);
-            }
-        }
-        
-    }
-    
-}
-
-// print_r($dom_document->saveXML());
-
-// save a copy of the raw XML
-$dom_document->save('configdoc.xml');
-
-
-// ---------------------------------------------------------------------------
-// Generate final output using XSLT
-
-// load the stylesheet
-$xsl_stylesheet_name = 'plain';
-$xsl_stylesheet = "styles/$xsl_stylesheet_name.xsl";
-$xsl_dom_stylesheet = new DOMDocument();
-$xsl_dom_stylesheet->load($xsl_stylesheet);
-
-// setup the XSLT processor
-$xsl_processor = new XSLTProcessor();
-
-// perform the transformation
-$xsl_processor->importStylesheet($xsl_dom_stylesheet);
-$html_output = $xsl_processor->transformToXML($dom_document);
-
-// some slight fudges to preserve backwards compatibility
-$html_output = str_replace('/>', ' />', $html_output); // <br /> not <br>
-$html_output = str_replace(' xmlns=""', '', $html_output); // rm unnecessary xmlns
-
-if (class_exists('Tidy')) {
-    // cleanup output
-    $config = array(
-        'indent'        => true,
-        'output-xhtml'  => true,
-        'wrap'          => 80
-    );
-    $tidy = new Tidy;
-    $tidy->parseString($html_output, $config, 'utf8');
-    $tidy->cleanRepair();
-    $html_output = (string) $tidy;
-}
-
-// write it to a file (todo: parse into seperate pages)
-file_put_contents("$xsl_stylesheet_name.html", $html_output);
-
-
-// ---------------------------------------------------------------------------
-// Output for instant feedback
-
-if (php_sapi_name() != 'cli') {
-    echo $html_output;
-} else {
-    echo 'Files generated successfully.';
-}
-
-?>

configdoc/styles/plain.css

@@ -1,7 +0,0 @@
-table {border-collapse:collapse;}
-table td, table th {padding:0.2em;}
-
-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;}

configdoc/styles/plain.xsl

@@ -1,105 +0,0 @@
-<?xml version="1.0" encoding="UTF-8"?>
-<xsl:stylesheet
-    version     = "1.0"
-    xmlns       = "http://www.w3.org/1999/xhtml"
-    xmlns:xsl   = "http://www.w3.org/1999/XSL/Transform"
->
-    <xsl:output
-        method      = "xml"
-        encoding    = "UTF-8"
-        doctype-public = "-//W3C//DTD XHTML 1.0 Transitional//EN"
-        doctype-system = "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd"
-        indent = "no"
-        media-type = "text/html"
-    />
-    
-    <xsl:variable name="typeLookup" select="document('../types.xml')" />
-    
-    <xsl:template match="/">
-        <html lang="en" xml:lang="en">
-            <head>
-                <title><xsl:value-of select="/configdoc/title" /> Configuration Documentation</title>
-                <meta http-equiv="Content-Type" content="text/html;charset=UTF-8" />
-                <link rel="stylesheet" type="text/css" href="styles/plain.css" />
-            </head>
-            <body>
-                <xsl:apply-templates />
-            </body>
-        </html>
-    </xsl:template>
-    
-    <xsl:template match="title">
-        <h1><xsl:value-of select="/configdoc/title" /> Configuration Documentation</h1>
-    </xsl:template>
-    
-    <xsl:template match="namespace">
-        <xsl:apply-templates />
-        <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="text()" /></h2>
-    </xsl:template>
-    <xsl:template match="namespace/description">
-        <div class="description">
-            <xsl:copy-of select="div/node()" />
-        </div>
-    </xsl:template>
-    
-    <xsl:template match="directive">
-        <xsl:apply-templates />
-    </xsl:template>
-    <xsl:template match="directive/name">
-        <h3 id="{../@id}"><xsl:value-of select="text()" /></h3>
-    </xsl:template>
-    <xsl:template match="directive/constraints">
-        <table class="constraints">
-            <xsl:apply-templates />
-            <!-- Calculated other values -->
-            <tr>
-                <th>Used by:</th>
-                <td>
-                    <xsl:for-each select="../descriptions/description">
-                        <xsl:if test="position()&gt;1">, </xsl:if>
-                        <xsl:value-of select="@file" />
-                    </xsl:for-each>
-                </td>
-            </tr>
-        </table>
-    </xsl:template>
-    <xsl:template match="directive//description">
-        <div class="description">
-            <xsl:copy-of select="div/node()" />
-        </div>
-    </xsl:template>
-    
-    <xsl:template match="constraints/type">
-        <tr>
-            <th>Type:</th>
-            <td>
-                <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()" />
-            </td>
-        </tr>
-    </xsl:template>
-    <xsl:template match="constraints/allowed">
-        <tr>
-            <th>Allowed values:</th>
-            <td>
-                <xsl:for-each select="value"><!--
-                 --><xsl:if test="position()&gt;1">, </xsl:if>
-                    &quot;<xsl:value-of select="." />&quot;<!--
-             --></xsl:for-each>
-            </td>
-        </tr>
-    </xsl:template>
-    <xsl:template match="constraints/default">
-        <tr>
-            <th>Default:</th>
-            <td><pre><xsl:value-of select="." xml:space="preserve" /></pre></td>
-        </tr>
-    </xsl:template>
-    
-</xsl:stylesheet>

docs/code-quality.txt

@@ -11,24 +11,23 @@ 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,
+    Class - doesn't support Unicode characters, uses regular expressions
+    Lang - code duplication, premature optimization, doesn't consult official
+        lists
+    Pixels/Length/MultiLength - implemented according to HTML spec (excludes
+        code reuse in CSS)
+    URI - multiple regular expressions, needs host validation routines factored
+        out for mailto scheme, IPv6 validation is broken (fringe), unintuitive
+        variable overwriting, 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
+AttrTransform - doesn't accept AttrContext, non-validating
+    Lang - invalid xml:lang value can overwrite valid lang value (fringe)
+ChildDef - not-allowed nodes translated to text, likely invalid handling
 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).
+    MakeWellFormed - insufficient automatic closing definitions
     RemoveForeignElements - should be run in parallel with MakeWellFormed
 URIScheme - needs to have callable generic checks
     ftp - missing typecode check

docs/colors.txt

@@ -1,23 +0,0 @@
-
-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

@@ -28,7 +28,6 @@ time.  Note the naming convention: %Namespace.Directive
 
 %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

docs/config.txt

@@ -16,23 +16,3 @@ 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.
-A standard call pattern would look like:
-
-1. Client calls Config->getHTMLDefinition()
-2. Config calls HTMLDefinition->createNew(this)
-3. HTMLDefinition constructs itself with base configuration
-4. HTMLDefinition calls Config->get('HTMLDefinition')
-5. Config returns array of directives that later construction
-6. HTMLDefinition performs operations and changes specified by directives
-7. HTMLPurifier returns constructed definition
-8. Config caches definition so it doesn't have to be generated again
-9. Config returns definition
-
-You could also override Config's copy of the definition with your own
-custom copy, which OVERRIDES all directives.  Only the base, vanilla copy
-is the Singleton, the object actually interfaced with is a operated-upon
-clone of that object.  Also, if an update to the directives would update
-the definition, you'd have to force reconstruction.

docs/devnetwork.html

@@ -22,10 +22,7 @@ the development of this library in these forum threads:</p>
     <li><a href="http://forums.devnetwork.net/viewtopic.php?t=53539">http and ftp versus news and mailto</a></li>
     <li><a href="http://forums.devnetwork.net/viewtopic.php?t=53579">HTMLPurifier - Take your best shot</a></li>
     <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/dtd/xhtml1-purified.dtd

@@ -0,0 +1,272 @@
+<!-- Transform %TextAlign to align:value in style -->
+
+<!-- text alignment for p, div, h1-h6. The default is
+     align="left" for ltr headings, "right" for rtl
+     
+     Move to style! -->
+<!ENTITY % TextAlign "DEPRECATED align (left|center|right|justify) #IMPLIED">
+
+<!-- type and start should have CSS equivalents, but they'll need to
+be translated intelligently -->
+<!ENTITY % ULStyle "(disc|square|circle)">
+<!-- Ordered list numbering style
+
+    1   arabic numbers      1, 2, 3, ...
+    a   lower alpha         a, b, c, ...
+    A   upper alpha         A, B, C, ...
+    i   lower roman         i, ii, iii, ...
+    I   upper roman         I, II, III, ...
+
+    The style is applied to the sequence number which by default
+    is reset to 1 for the first list item in an ordered list.
+-->
+<!ENTITY % OLStyle "CDATA">
+<!-- LIStyle is constrained to: "(%ULStyle;|%OLStyle;)" -->
+<!ENTITY % LIStyle "CDATA">
+
+<!ATTLIST ol
+  %attrs;
+  DEPRECATED type        %OLStyle;      #IMPLIED
+  DEPRECATED start       %Number;       #IMPLIED
+  >
+
+<!ATTLIST li
+  %attrs;
+  DEPRECATED type        %LIStyle;      #IMPLIED
+  DEPRECATED value       %Number;       #IMPLIED
+  >
+
+<!ATTLIST hr
+  %attrs;
+  DEPRECATED align       (left|center|right) #IMPLIED
+  DEPRECATED size        %Pixels;       #IMPLIED
+  DEPRECATED width       %Length;       #IMPLIED
+  >
+
+<!ATTLIST pre
+  %attrs;
+  DEPRECATED width       %Number;      #IMPLIED
+  >
+
+<!ATTLIST blockquote
+  %attrs;
+  cite        %URI;          #IMPLIED
+  >
+
+<!ATTLIST ins
+  %attrs;
+  cite        %URI;          #IMPLIED
+  datetime    %Datetime;     #IMPLIED
+  >
+<!ATTLIST del
+  %attrs;
+  cite        %URI;          #IMPLIED
+  datetime    %Datetime;     #IMPLIED
+  >
+
+<!ATTLIST a
+  %attrs;
+  name        NMTOKEN        #IMPLIED // ID
+  href        %URI;          #IMPLIED
+  rel         %LinkTypes;    #IMPLIED // needs policing
+  rev         %LinkTypes;    #IMPLIED // see rel
+  target      %FrameTarget;  #IMPLIED // usually not used, but might be
+  >
+
+<!ATTLIST bdo
+  %coreattrs; // !#!
+  lang        %LanguageCode; #IMPLIED
+  xml:lang    %LanguageCode; #IMPLIED
+  dir         (ltr|rtl)      #REQUIRED
+  >
+
+<!ATTLIST br
+  %coreattrs; // !#!
+  DEPRECATED clear       (left|all|right|none) "none"
+  >
+
+<!ELEMENT q %Inline;>   <!-- inlined quote -->
+<!ATTLIST q
+  %attrs;
+  cite        %URI;          #IMPLIED
+  >
+
+<!ATTLIST img
+  %attrs;
+  src         %URI;          #REQUIRED
+  alt         %Text;         #REQUIRED
+  DEPRECATED name        NMTOKEN        #IMPLIED // ID
+  longdesc    %URI;          #IMPLIED
+  height      %Length;       #IMPLIED // dubious, but we'll allow
+  width       %Length;       #IMPLIED //
+  DEPRECATED align       %ImgAlign;     #IMPLIED
+  DEPRECATED border      %Length;       #IMPLIED
+  DEPRECATED hspace      %Pixels;       #IMPLIED // left/right margin
+  DEPRECATED vspace      %Pixels;       #IMPLIED // up/down margin
+  >
+
+<!--
+ The border attribute sets the thickness of the frame around the
+ table. The default units are screen pixels.
+
+ The frame attribute specifies which parts of the frame around
+ the table should be rendered. The values are not the same as
+ CALS to avoid a name clash with the valign attribute.
+-->
+<!ENTITY % TFrame "(void|above|below|hsides|lhs|rhs|vsides|box|border)">
+
+<!--
+ The rules attribute defines which rules to draw between cells:
+
+ If rules is absent then assume:
+     "none" if border is absent or border="0" otherwise "all"
+-->
+
+<!ENTITY % TRules "(none | groups | rows | cols | all)">
+  
+<!-- horizontal placement of table relative to document -->
+<!ENTITY % TAlign "(left|center|right)">
+
+<!-- horizontal alignment attributes for cell contents
+
+  char        alignment char, e.g. char=':'
+  charoff     offset for alignment char
+-->
+<!ENTITY % cellhalign
+  "align      (left|center|right|justify|char) #IMPLIED
+   char       %Character;    #IMPLIED
+   charoff    %Length;       #IMPLIED"
+  >
+
+<!-- vertical alignment attributes for cell contents -->
+<!ENTITY % cellvalign
+  "valign     (top|middle|bottom|baseline) #IMPLIED"
+  >
+
+<!-- we may want to convert some of these nonetheless -->
+<!ATTLIST table
+  %attrs;
+  summary     %Text;         #IMPLIED
+  width       %Length;       #IMPLIED
+  border      %Pixels;       #IMPLIED
+  frame       %TFrame;       #IMPLIED
+  rules       %TRules;       #IMPLIED
+  cellspacing %Length;       #IMPLIED
+  cellpadding %Length;       #IMPLIED
+  DEPRECATED align       %TAlign;       #IMPLIED
+  DEPRECATED bgcolor     %Color;        #IMPLIED
+  >
+
+<!ENTITY % CAlign "(top|bottom|left|right)">
+
+<!ATTLIST caption
+  %attrs;
+DEPRECATED  align       %CAlign;       #IMPLIED // watch, it's a special set
+  >
+
+<!--
+colgroup groups a set of col elements. It allows you to group
+several semantically related columns together.
+-->
+<!ATTLIST colgroup
+  %attrs;
+  span        %Number;       "1"
+  width       %MultiLength;  #IMPLIED
+  %cellhalign; // very interesting
+  %cellvalign;
+  >
+
+<!--
+ col elements define the alignment properties for cells in
+ one or more columns.
+
+ The width attribute specifies the width of the columns, e.g.
+
+     width=64        width in screen pixels
+     width=0.5*      relative width of 0.5
+
+ The span attribute causes the attributes of one
+ col element to apply to more than one column.
+-->
+<!ATTLIST col
+  %attrs;
+  span        %Number;       "1"
+  width       %MultiLength;  #IMPLIED
+  %cellhalign;
+  %cellvalign;
+  >
+
+<!--
+    Use thead to duplicate headers when breaking table
+    across page boundaries, or for static headers when
+    tbody sections are rendered in scrolling panel.
+
+    Use tfoot to duplicate footers when breaking table
+    across page boundaries, or for static footers when
+    tbody sections are rendered in scrolling panel.
+
+    Use multiple tbody sections when rules are needed
+    between groups of table rows.
+-->
+<!ATTLIST thead
+  %attrs;
+  %cellhalign;
+  %cellvalign;
+  >
+
+<!ATTLIST tfoot
+  %attrs;
+  %cellhalign;
+  %cellvalign;
+  >
+
+<!ATTLIST tbody
+  %attrs;
+  %cellhalign;
+  %cellvalign;
+  >
+
+<!ATTLIST tr
+  %attrs;
+  %cellhalign;
+  %cellvalign;
+DEPRECATED  bgcolor     %Color;        #IMPLIED
+  >
+
+<!-- Scope is simpler than headers attribute for common tables -->
+<!ENTITY % Scope "(row|col|rowgroup|colgroup)">
+
+<!-- th is for headers, td for data and for cells acting as both -->
+
+<!ATTLIST th
+  %attrs;
+  abbr        %Text;         #IMPLIED
+  axis        CDATA          #IMPLIED
+  headers     IDREFS         #IMPLIED
+  scope       %Scope;        #IMPLIED
+  rowspan     %Number;       "1"
+  colspan     %Number;       "1"
+  %cellhalign;
+  %cellvalign;
+DEPRECATED  nowrap      (nowrap)       #IMPLIED
+DEPRECATED  bgcolor     %Color;        #IMPLIED
+DEPRECATED  width       %Length;       #IMPLIED
+DEPRECATED  height      %Length;       #IMPLIED
+  >
+
+<!ATTLIST td
+  %attrs;
+  abbr        %Text;         #IMPLIED
+  axis        CDATA          #IMPLIED
+  headers     IDREFS         #IMPLIED
+  scope       %Scope;        #IMPLIED
+  rowspan     %Number;       "1"
+  colspan     %Number;       "1"
+  %cellhalign;
+  %cellvalign;
+DEPRECATED  nowrap      (nowrap)       #IMPLIED
+DEPRECATED  bgcolor     %Color;        #IMPLIED
+DEPRECATED  width       %Length;       #IMPLIED
+DEPRECATED  height      %Length;       #IMPLIED
+  >
+

docs/examples/demo.php

@@ -1,8 +1,4 @@
-<?php
-
-header('Content-type:text/html;charset=UTF-8');
-
-?><!DOCTYPE html 
+<!DOCTYPE html 
      PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"
      "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
 <html>
@@ -14,6 +10,8 @@ header('Content-type:text/html;charset=UTF-8');
 <h1>HTMLPurifier Live Demo</h1>
 <?php
 
+set_time_limit(120);
+
 set_include_path('../../library' . PATH_SEPARATOR . get_include_path());
 require_once 'HTMLPurifier.php';
 
@@ -21,9 +19,7 @@ if (!empty($_POST['html'])) {
     
     $html = get_magic_quotes_gpc() ? stripslashes($_POST['html']) : $_POST['html'];
     
-    $config = HTMLPurifier_Config::createDefault();
-    $config->set('Core', 'TidyFormat', !empty($_POST['tidy']));
-    $purifier = new HTMLPurifier($config);
+    $purifier = new HTMLPurifier();
     $pure_html = $purifier->purify($html);
     
 ?>
@@ -62,18 +58,13 @@ if (isset($_GET['profile']) || isset($_GET['XDEBUG_PROFILE'])) {
         <legend>HTML</legend>
         <textarea name="html" cols="60" rows="15"><?php
 
-if (isset($html)) {
-    echo htmlspecialchars(
-            HTMLPurifier_Encoder::cleanUTF8($html), ENT_COMPAT, 'UTF-8');
-}
+if (isset($html)) echo htmlspecialchars($html, ENT_COMPAT, 'UTF-8');
+
         ?></textarea>
-        <div>Nicely format output with Tidy? <input type="checkbox" value="1"
-        name="tidy"<?php if (!empty($_POST['tidy'])) echo ' checked="checked"'; ?> /></div>
         <div>
             <input type="submit" value="Submit" name="submit" class="button" />
         </div>
     </fieldset>
 </form>
-<p>Return to <a href="http://hp.jpsband.org/">HTMLPurifier's home page</a>.</p>
 </body>
 </html>

docs/filter-levels.txt

@@ -1,130 +0,0 @@
-
-Filter Levels
-    When one size *does not* fit all
-
-The more I think about it, the less sense it makes for maintaining one huge
-monolithic HTMLDefinition class.  There's simply so much variation that
-could go into this definition: the set of HTML good for blog entries is
-definitely too large for HTML that would be allowed in blog comments. Going
-from Transitional to Strict requires changes to the definition.
-
-However, allowing users to specify their own whitelists was an idea I
-rejected from the start.  Simply put, the typical programmer is too lazy
-to actually go through the trouble of investigating which tags, attributes
-and properties to allow.  HTMLDefinition makes a big part of what HTMLPurifier
-is.
-
-The idea, then, is to setup fundamentally different set of definitions, which
-can further be customized using simpler configuration options.
-
-Here are some fuzzy levels you could set:
-
-1. Comments - Wordpress recommends a, abbr, acronym, b, blockquote, cite,
-    code, em, i, strike, strong; however, you could get away with only a, em and
-    p; also having blockquote and pre tags would be helpful.
-2. BBCode - Emulate the usual tagset for forums: b, i, img, a, blockquote,
-    pre, div, span and h[2-6] (the last three are for specially formatted
-    posts, div and span require associated classes or inline styling enabled
-    to be useful)
-3. Pages - As permissive as possible without allowing XSS.  No protection
-    against bad design sense, unfortunantely.  Suitable for wiki and page
-    environments.
-4. Lint - Accept everything in the spec, a Tidy wannabe. (This probably won't
-    get implemented as it would require routines for things like <object>
-    and friends to be implemented, which is a lot of work for not a lot of
-    benefit)
-
-One final note: when you start axing tags that are more commonly used, you
-run the risk of accidentally destroying user data, especially if the data
-is incoming from a WYSIWYG eidtor that hasn't been synced accordingly. This may
-make forbidden element to text transformations desirable (for example, images).
-
-
-
-== Element Risk Analysis ==
-
-Legend:
-    [danger level] - regular tags / uncommon tags ~ deprecated tags
-    [danger level]* - rare tags
-
-1 - blockquote, code, em, i, p, tt / strong, sub, sup
-1* - abbr, acronym, bdo, cite, dfn, kbd, q, samp
-2 - b, br, del, div, pre, span / ins, s, strike ~ u
-3 - h2, h3, h4, h5, h6 ~ center
-4 - h1, big ~ font
-5 - a
-7 - area, map
-
-These are special use tags, they should be enabled on a blanket basis.
-
-Lists - dd, dl, dt, li, ol, ul ~ menu, dir
-Tables - caption, table, td, th, tr / col, colgroup, tbody, tfoot, thead
-
-Forms - fieldset, form, input, lable, legend, optgroup, option, select, textarea
-XSS - noscript, object, script ~ applet
-Meta - base, basefont, body, head, html, link, meta, style, title
-Frames - frame, frameset, iframe
-
-And tag specific notes:
-
-a   - general problems involving linkspam
-b   - too much bold is bad, typographically speaking bold is discouraged
-br  - often misused
-center - CSS, usually no legit use
-del - only useful in editing context
-div - little meaning in certain contexts i.e. blog comment
-h1  - usually no legit use, as header is already set by application
-h*  - not needed in blog comments
-hr  - usually not necessary in blog comments
-img - could be extremely undesirable if linking to external pics (CSRF, goatse)
-pre - could use formatting, only useful in code contexts
-q   - very little support
-s   - transform into span with styling or del?
-small - technically presentational
-span - depends on attribute allowances
-sub, sup - specialized
-u   - little legit use, prefer class with text-decoration
-
-Based on the riskiness of the items, we may want to offer %HTML.DisableImages
-attribute and put URI filtering higher up on the priority list.
-
-
-== Attribute Risk Analysis ==
-
-We actually have a suprisingly small assortment of allowed attributes (the
-rest are deprecated in strict, and thus we opted not to allow them, even
-though our output is XHTML Transitional by default.)
-
-Required URI - img.alt, img.src, a.href
-Medium risk - *.class, *.dir
-High risk - img.height, img.width, *.id, *.style
-
-Table - colgroup/col.span, td/th.rowspan, td/th.colspan
-Uncommon - *.title, *.lang, *.xml:lang
-Rare - td/th.abbr, table.summary, {table}.charoff
-Rare URI - del.cite, ins.cite, blockquote.cite, q.cite, img.longdesc
-Presentational - {table}.align, {table}.valign, table.frame, table.rules,
-    table.border
-Partially presentational - table.cellpadding, table.cellspacing,
-    table.width, col.width, colgroup.width
-
-
-== CSS Risk Analysis ==
-
-There are certain CSS elements that are extremely useful inline, but then
-as you get to more presentation oriented styling it may not always be
-appropriate to inline them.
-
-Useful - clear, float, border-collapse, caption-side
-
-These CSS properties can break layouts if used improperly. We have excluded
-any CSS properties that are not currently implemented (such as position).
-
-Dangerous, can go outside container - float
-Easy to abuse - font-size, font-family (font), width
-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 substnatially change the look of text in ways that should
-probably have been reserved to other areas.

docs/naming.txt

@@ -6,9 +6,8 @@ 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.
+    names under HTMLPurifier_ are reserved, and userspace extensions should
+    be registered in a different namespace (or the main namespace).
 
 All classes correspond to their path if library/ was in the include path
     HTMLPurifier_AttrDef is located at HTMLPurifier/AttrDef.php; replace

docs/optimization.txt

@@ -2,10 +2,9 @@
 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!
+they turn out to be slow.  Be sure not to prematurely optimize though!
 
- - Make Tokens Flyweights (may prove problematic, probably not worth it)
+ - Make Tokens Flyweights
  - Rewrite regexps into PHP code
  - Serialize the Definition object
  - Batch regexp validation (do as many per function call as possible)

docs/progress.html

@@ -12,14 +12,13 @@ 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-yes {background:#AFA;}
 .impl-partial {background:#FFA;}
-.impl-no {background:#CCC;}
+.impl-no {background:#FAA;}
 
-.danger {color:#600;}
+.danger {background:#FEE;}
 .css1 {color:#060;}
 .required {font-weight:bold;}
-.feature {color:#999;}
 
 </style>
 
@@ -35,9 +34,91 @@ thead th {text-align:left;padding:0.1em;background-color:#EEE;}
 <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>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-partial"><td>style</td><td>All</td><td>Needs CSS parser</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="impl-no"><td>axis</td><td>TD, TH</td><td>W3C only: No browser implementation</td></tr>
+<tr class="impl-no"><td>char</td><td>COL, COLGROUP, TBODY, TD, TFOOT, TH, THEAD, TR</td><td>W3C only: No browser implementation</td></tr>
+<tr class="impl-no"><td>headers</td><td>TD, TH</td><td>W3C only: No browser implementation</td></tr>
+<tr class="impl-no"><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</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</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>
+
 <h3>CSS</h3>
 
 <table cellspacing="0">
@@ -53,12 +134,12 @@ thead th {text-align:left;padding:0.1em;background-color:#EEE;}
 <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"><td>background</td><td>SHORTHAND</td></tr>
+<tr class="css1"><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="css1"><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>
@@ -67,7 +148,7 @@ thead th {text-align:left;padding:0.1em;background-color:#EEE;}
 <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"><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;,
@@ -86,7 +167,7 @@ thead th {text-align:left;padding:0.1em;background-color:#EEE;}
     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"><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>
@@ -110,18 +191,18 @@ thead th {text-align:left;padding:0.1em;background-color:#EEE;}
 
 <tbody>
 <tr><th colspan="2">Table</th></tr>
-<tr class="impl-yes"><td>border-collapse</td><td>ENUM(collapse, seperate)</td></tr>
-<tr class="impl-yes"><td>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,
+<tr><td>border-collapse</td><td>ENUM(collapse, seperate)</td></tr>
+<tr><td>caption-side</td><td>ENUM(top, bottom)</td></tr>
+<tr><td>empty-cells</td><td>ENUM(show, hide), No IE support, possible fix
+    with &amp;nbsp;?</td></tr>
+<tr><td>table-layout</td><td>ENUM(auto, fixed)</td></tr>
+<tr class="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><th colspan="2">Absolute positioning</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>
@@ -134,36 +215,36 @@ thead th {text-align:left;padding:0.1em;background-color:#EEE;}
 
 <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="danger css1"><td>background-image</td><td>Dangerous</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"><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>
+    for Mozilla.</td></tr>
+<tr><td class="css1">height</td><td>Interesting, why use it?</td></tr>
+<tr class="danger css1"><td>list-style-image</td><td>Dangerous?</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>overflow</td><td>ENUM, IE 5/6 almost (remove visible if set)</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>
+    IE 5.5/6 and Opera</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>
+    Mostly supported</td></tr>
+<tr><td>page-break-inside</td><td>ENUM(avoid, auto), Opera only</td></tr>
+<tr class="impl-no"><td>quotes</td><td>May be dropped from CSS2</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,
+<tr><td class="css1">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>
+    pre-wrap (only Opera), pre-line (no support). Fixable?</td></tr>
 </tbody>
 
 <tbody class="impl-no">
@@ -206,87 +287,4 @@ Mozilla on inside and needs -moz-outline, no IE support.</td></tr>
 
 </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/security.txt

@@ -6,43 +6,34 @@ through negligence of people. This class will do its job: no more, no less,
 and it's up to you to provide it the proper information and proper context
 to be effective. Things to remember:
 
-1. Character Encoding: UTF-8.
-Currently, the parser runs under the assumption that it is dealing
+1. UTF-8. Currently, the parser runs under the assumption that it is dealing
 with UTF-8. Not ISO-8859-1 or Windows-1252, UTF-8. And definitely not "no
 character encoding explicitly stated" or UTF-7. If you're not using UTF-8 as
-your character encoding, make sure you configure HTML Purifier or switch
-to UTF-8. Now. Also, make sure any input is properly converted to UTF-8, or
-the parser will mangle it badly (though it won't be a security risk if you're
-outputting it as UTF-8 though).  Character encoding is, in general, a knotty
-issue, but do yourself a favor and learn about it:
-<http://www.joelonsoftware.com/articles/Unicode.html>
+your character encoding, you should switch. Now. (in future versions, however,
+I may make the character encoding configurable, but there's only so much I
+can do). Make sure any input is properly converted to UTF-8, or the parser
+will mangle it badly (though it won't be a security risk if you're outputting
+it as UTF-8 though).
 
-2. Doctype: XHTML 1.0 Transitional
-This is what the parser is outputting. For the most
+2. XHTML 1.0 Transitional. This is what the parser is outputting. For the most
 part, it's compatible with HTML 4.01, but XHTML enforces some very nice things
 that all web developers should use. Regardless, NO DOCTYPE is a NO. Quirks mode
 has waaaay too many quirks for a little parser to handle.  We did not select
 strict in order to prevent ourselves from being too draconic on users, but
-this may be configurable in the future.  Do you want standards compliance?
-The doctype is a good place to start.
+this may be configurable in the future.
 
-3. IDs
-They need to be unique, but without some knowledge of the
-rest of the document, it's difficult to know what's unique. %Attr.IDBlacklist
-needs to be set: we may want to consider disallowing IDs by default to
-save lazy programmers.
+3. IDs. They need to be unique, but without some knowledge of the
+rest of the document, it's difficult to know what's unique. Without setting
+%Attr.IDBlacklist to the proper 
 
-4. [PROJECTED] Links
-We're not going to try for spam protection (although
+4. [PROJECTED] Links. We're not going to try for spam protection (although
 some hooks for such a module might be nice) but we may offer the ability to
 only accept relative URLs. Pick the one that's right for you.
 
-5. CSS
-While we can prevent the most flagrant cases from affecting your
+5. CSS. While we can prevent the most flagrant cases from affecting your
 layout (such as absolutely positioned elements), no amount of code is going
 to protect your pages from being attacked by garish colors and plain old
 bad taste.  A neat feature would be the ability to define acceptable colors
 in a document, but that's not likely to be implemented for a while.  In the
 meantime, be sure to make sure that floated elements (permitted, since they
-can be quite useful) can't mess up your layout. Once again, we may want to
-disable this by default to protect lazy developers.
+can be quite useful) cna't mess up your layout.

docs/spec.txt

@@ -29,8 +29,7 @@ output is valid XHTML or send the HTML through a draconic XML parser (and yet
 still get the nesting wrong: SafeHtmlChecker.class.php does not prevent <a>
 tags from being nested within each other).
 
-This document no longer is a detailed description of how HTMLPurifier works,
-as those descriptions have been moved to the appropriate code.  The first
+This document seeks to detail the inner workings of HTML Purifier.  The first
 draft was drawn up after two rough code sketches and the implementation of a
 forgiving lexer.  You may also be interested in the unit tests located in the
 tests/ folder, which provide a living document on how exactly the filter deals
@@ -53,5 +52,4 @@ In summary:
 HTML Purifier is best suited for documents that require a rich array of
 HTML tags.  Things like blog comments are, in all likelihood, most appropriately
 written in an extremely restrictive set of markup that doesn't require
-all this functionality (or not written in HTML at all), although this may
-be changing in the future with the addition of levels of filtering.
+all this functionality (or not written in HTML at all).

docs/strictness.txt

@@ -1,25 +0,0 @@
-
-Is HTML Purifier Strict or Transitional?
-    A little bit of helpful guidance
-
-Despite the fact that HTML Purifier professes only to support transitional
-HTML, it rejects a lot of attributes and elements that are actually, indeed,
-valid. You can investigate progress.html to find out precisely what we
-are doing to these *deprecated* attributes.
-
-However, users have found that Strict HTML imposes some quite unreasonable
-restrictions on certain things. The start and value attributes in ol and
-li (respectively) perhaps are the most contested. There's is currently no
-widely supported browser method short of JavaScript that can replace these
-two deprecated elements. HTML Purifier does not currently support them, but
-it might behoove us to do so while our output is still transitional.
-
-Fortunantely, that's the only real bugger case. The others have near-perfect
-CSS equivalents, and were presentational anyway. However, the other question
-pops up: should we always convert these to the CSS forms when 1. the spec
-allows them anyway and 2. older browsers support them better? After all, the
-whole point about CSS is to seperate styling from content, so inline styling
-doesn't solve that problem.
-
-It's an icky question, and we'll have to deal with it as more and more 
-transforms get implemented.

library/HTMLPurifier.auto.php

@@ -1,10 +0,0 @@
-<?php
-
-/**
- * This is a stub include that automatically configures the include path.
- */
-
-set_include_path(dirname(__FILE__) . PATH_SEPARATOR . get_include_path() );
-require_once 'HTMLPurifier.php';
-
-?>

library/HTMLPurifier.php

@@ -3,7 +3,7 @@
 /*!
  * @mainpage
  * 
- * HTML Purifier is an HTML filter that will take an arbitrary snippet of
+ * HTMLPurifier is a purification class that will take an arbitrary snippet of
  * HTML and rigorously test, validate and filter it into a version that
  * is safe for output onto webpages. It achieves this by:
  * 
@@ -15,40 +15,15 @@
  *      -# Validating attributes of the nodes; and
  *  -# Generating HTML from the purified tokens.
  * 
- * However, most users will only need to interface with the HTMLPurifier
- * class, so this massive amount of infrastructure is usually concealed.
- * If you plan on working with the internals, be sure to include
- * HTMLPurifier_ConfigSchema and HTMLPurifier_Config.
+ * See /docs/spec.txt for more details.
  */
 
-/*
-    HTML Purifier - Standards Compliant HTML Filtering
-    Copyright (C) 2006 Edward Z. Yang
-
-    This library is free software; you can redistribute it and/or
-    modify it under the terms of the GNU Lesser General Public
-    License as published by the Free Software Foundation; either
-    version 2.1 of the License, or (at your option) any later version.
-
-    This library is distributed in the hope that it will be useful,
-    but WITHOUT ANY WARRANTY; without even the implied warranty of
-    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
-    Lesser General Public License for more details.
-
-    You should have received a copy of the GNU Lesser General Public
-    License along with this library; if not, write to the Free Software
-    Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301  USA
- */
-
-// almost every class has an undocumented dependency to these, so make sure
-// they get included
-require_once 'HTMLPurifier/ConfigSchema.php';
+require_once 'HTMLPurifier/ConfigDef.php';
 require_once 'HTMLPurifier/Config.php';
-
 require_once 'HTMLPurifier/Lexer.php';
+require_once 'HTMLPurifier/HTMLDefinition.php';
 require_once 'HTMLPurifier/Generator.php';
 require_once 'HTMLPurifier/Strategy/Core.php';
-require_once 'HTMLPurifier/Encoder.php';
 
 /**
  * Main library execution class.
@@ -56,56 +31,39 @@ require_once 'HTMLPurifier/Encoder.php';
  * Facade that performs calls to the HTMLPurifier_Lexer,
  * HTMLPurifier_Strategy and HTMLPurifier_Generator subsystems in order to
  * purify HTML.
- * 
- * @todo We need an easier way to inject strategies, it'll probably end
- *       up getting done through config though.
  */
 class HTMLPurifier
 {
     
     var $config;
     
-    var $lexer, $strategy, $generator;
-    
     /**
      * Initializes the purifier.
-     * @param $config Optional HTMLPurifier_Config object for all instances of
-     *                the purifier, if omitted, a default configuration is
-     *                supplied (which can be overridden on a per-use basis).
+     * @param $config Configuration for all instances of the purifier
      */
     function HTMLPurifier($config = null) {
-        
         $this->config = $config ? $config : HTMLPurifier_Config::createDefault();
-        
-        $this->lexer        = HTMLPurifier_Lexer::create();
-        $this->strategy     = new HTMLPurifier_Strategy_Core();
-        $this->generator    = new HTMLPurifier_Generator();
-        $this->encoder      = new HTMLPurifier_Encoder();
-        
     }
     
     /**
-     * Filters an HTML snippet/document to be XSS-free and standards-compliant.
+     * Purifies HTML.
      * 
      * @param $html String of HTML to purify
-     * @param $config HTMLPurifier_Config object for this operation, if omitted,
-     *                defaults to the config object specified during this
-     *                object's construction.
+     * @param $config HTMLPurifier_Config object for this specific round
      * @return Purified HTML
      */
     function purify($html, $config = null) {
         $config = $config ? $config : $this->config;
-        $html = $this->encoder->convertToUTF8($html, $config);
-        $html = 
-            $this->generator->generateFromTokens(
-                $this->strategy->execute(
-                    $this->lexer->tokenizeHTML($html, $config),
-                    $config
-                ),
+        $lexer = HTMLPurifier_Lexer::create();
+        $strategy = new HTMLPurifier_Strategy_Core();
+        $generator = new HTMLPurifier_Generator();
+        return $generator->generateFromTokens(
+            $strategy->execute(
+                $lexer->tokenizeHTML($html, $config),
                 $config
-            );
-        $html = $this->encoder->convertFromUTF8($html, $config);
-        return $html;
+            ),
+            $config
+        );
     }
     
 }

library/HTMLPurifier/AttrContext.php

@@ -3,23 +3,12 @@
 /**
  * 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).
+ * All it is is a data-structure that holds objects that accumulate state, like
+ * HTMLPurifier_IDAccumulator.
  */
 
 class HTMLPurifier_AttrContext
 {
-    /**
-     * Contains an HTMLPurifier_IDAccumulator, which keeps track of used IDs.
-     * @public
-     */
     var $id_accumulator;
 }
 

library/HTMLPurifier/AttrDef.php

@@ -2,65 +2,15 @@
 
 require_once 'HTMLPurifier/AttrContext.php';
 
-/**
- * Base class for all validating attribute definitions.
- * 
- * This family of classes forms the core for not only HTML attribute validation,
- * but also any sort of string that needs to be validated or cleaned (which
- * means CSS properties and composite definitions are defined here too).  
- * Besides defining (through code) what precisely makes the string valid,
- * subclasses are also responsible for cleaning the code if possible.
- */
-
+// AttrDef = Attribute Definition
 class HTMLPurifier_AttrDef
 {
+    function HTMLPurifier_AttrDef() {}
     
-    /**
-     * Tells us whether or not an HTML attribute is minimized. Only the
-     * boolean attribute vapourware would use this.
-     */
-    var $minimized = false;
-    
-    /**
-     * 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.
-     * @param $config Mandatory HTMLPurifier_Config object.
-     * @param $context Mandatory HTMLPurifier_AttrContext object.
-     */
     function validate($string, $config, &$context) {
         trigger_error('Cannot call abstract function', E_USER_ERROR);
     }
     
-    /**
-     * Convenience method that parses a string as if it were CDATA.
-     * 
-     * This method process a string in the manner specified at
-     * <http://www.w3.org/TR/html4/types.html#h-6.2> by removing
-     * leading and trailing whitespace, ignoring line feeds, and replacing
-     * carriage returns and tabs with spaces.  While most useful for HTML
-     * attributes specified as CDATA, it can also be applied to most CSS
-     * values.
-     * 
-     * @note This method is not entirely standards compliant, as trim() removes
-     *       more types of whitespace than specified in the spec. In practice,
-     *       this is rarely a problem, as those extra characters usually have
-     *       already been removed by HTMLPurifier_Encoder.
-     * 
-     * @warning This processing is inconsistent with XML's whitespace handling
-     *          as specified by section 3.3.3 and referenced XHTML 1.0 section
-     *          4.7.  Compliant processing requires all line breaks normalized
-     *          to "\n", so the fix is not as simple as fixing it in this
-     *          function.  Trim and whitespace collapsing are supposed to only
-     *          occur in NMTOKENs.  However, note that we are NOT necessarily
-     *          parsing XML, thus, this behavior may still be correct.
-     * 
-     * @public
-     */
     function parseCDATA($string) {
         $string = trim($string);
         $string = str_replace("\n", '', $string);

library/HTMLPurifier/AttrDef/Border.php

@@ -1,45 +0,0 @@
-<?php
-
-require_once 'HTMLPurifier/AttrDef.php';
-
-/**
- * Validates the border property as defined by CSS.
- */
-class HTMLPurifier_AttrDef_Border extends HTMLPurifier_AttrDef
-{
-    
-    /**
-     * Local copy of properties this property is shorthand for.
-     */
-    var $info = array();
-    
-    function HTMLPurifier_AttrDef_Border($config) {
-        $def = $config->getCSSDefinition();
-        $this->info['border-width'] = $def->info['border-width'];
-        $this->info['border-style'] = $def->info['border-style'];
-        $this->info['border-top-color'] = $def->info['border-top-color'];
-    }
-    
-    function validate($string, $config, &$context) {
-        $string = $this->parseCDATA($string);
-        // we specifically will not support rgb() syntax with spaces
-        $bits = explode(' ', $string);
-        $done = array(); // segments we've finished
-        $ret = ''; // return value
-        foreach ($bits as $bit) {
-            foreach ($this->info as $propname => $validator) {
-                if (isset($done[$propname])) continue;
-                $r = $validator->validate($bit, $config, $context);
-                if ($r !== false) {
-                    $ret .= $r . ' ';
-                    $done[$propname] = true;
-                    break;
-                }
-            }
-        }
-        return rtrim($ret);
-    }
-    
-}
-
-?>

library/HTMLPurifier/AttrDef/CSS.php

@@ -3,12 +3,6 @@
 require_once 'HTMLPurifier/AttrDef.php';
 require_once 'HTMLPurifier/CSSDefinition.php';
 
-/**
- * Validates the HTML attribute style, otherwise known as CSS.
- * @note We don't implement the whole CSS specification, so it might be
- *       difficult to reuse this component in the context of validating
- *       actual stylesheet declarations.
- */
 class HTMLPurifier_AttrDef_CSS extends HTMLPurifier_AttrDef
 {
     
@@ -16,7 +10,7 @@ class HTMLPurifier_AttrDef_CSS extends HTMLPurifier_AttrDef
         
         $css = $this->parseCDATA($css);
         
-        $definition = $config->getCSSDefinition();
+        $definition = HTMLPurifier_CSSDefinition::instance();
         
         // we're going to break the spec and explode by semicolons.
         // This is because semicolon rarely appears in escaped form
@@ -28,12 +22,10 @@ class HTMLPurifier_AttrDef_CSS extends HTMLPurifier_AttrDef
             if (!$declaration) continue;
             if (!strpos($declaration, ':')) continue;
             list($property, $value) = explode(':', $declaration, 2);
-            $property = trim($property);
-            $value    = trim($value);
             if (!isset($definition->info[$property])) continue;
             // inefficient call, since the validator will do this again
+            // inherit works for everything
             if (strtolower(trim($value)) !== 'inherit') {
-                // inherit works for everything (but only on the base property)
                 $result = $definition->info[$property]->validate(
                     $value, $config, $context );
             } else {

library/HTMLPurifier/AttrDef/CSSLength.php

@@ -3,29 +3,13 @@
 require_once 'HTMLPurifier/AttrDef.php';
 require_once 'HTMLPurifier/AttrDef/Number.php';
 
-/**
- * Represents a Length as defined by CSS.
- * @warning Be sure not to confuse this with HTMLPurifier_AttrDef_Length!
- */
 class HTMLPurifier_AttrDef_CSSLength extends HTMLPurifier_AttrDef
 {
     
-    /**
-     * Valid unit lookup table.
-     * @warning The code assumes all units are two characters long.  Be careful
-     *          if we have to change this behavior!
-     */
     var $units = array('em' => true, 'ex' => true, 'px' => true, 'in' => true,
          'cm' => true, 'mm' => true, 'pt' => true, 'pc' => true);
-    /**
-     * Instance of HTMLPurifier_AttrDef_Number to defer number validation to
-     */
     var $number_def;
     
-    /**
-     * @param $non_negative Bool indication whether or not negative values are
-     *                      allowed.
-     */
     function HTMLPurifier_AttrDef_CSSLength($non_negative = false) {
         $this->number_def = new HTMLPurifier_AttrDef_Number($non_negative);
     }

library/HTMLPurifier/AttrDef/Class.php

@@ -3,9 +3,6 @@
 require_once 'HTMLPurifier/AttrDef.php';
 require_once 'HTMLPurifier/Config.php';
 
-/**
- * Validates the contents of the global HTML attribute class.
- */
 class HTMLPurifier_AttrDef_Class extends HTMLPurifier_AttrDef
 {
     

library/HTMLPurifier/AttrDef/Color.php

@@ -2,44 +2,14 @@
 
 require_once 'HTMLPurifier/AttrDef.php';
 
-/**
- * Validates Color as defined by CSS.
- */
-class HTMLPurifier_AttrDef_Color extends HTMLPurifier_AttrDef
+class HTMLPurifier_AttrDef_Color
 {
     
-    /**
-     * Color keyword lookup table.
-     * @todo Extend it to include all usually allowed colors.
-     */
-    var $colors = array(
-        'maroon'    => '#800000',
-        'red'       => '#F00',
-        'orange'    => '#FFA500',
-        'yellow'    => '#FF0',
-        'olive'     => '#808000',
-        'purple'    => '#800080',
-        'fuchsia'   => '#F0F',
-        'white'     => '#FFF',
-        'lime'      => '#0F0',
-        'green'     => '#008000',
-        'navy'      => '#000080',
-        'blue'      => '#00F',
-        'aqua'      => '#0FF',
-        'teal'      => '#008080',
-        'black'     => '#000',
-        'silver'    => '#C0C0C0',
-        'gray'      => '#808080'
-    );
-    
     function validate($color, $config, &$context) {
         
         $color = trim($color);
         if (!$color) return false;
         
-        $lower = strtolower($color);
-        if (isset($this->colors[$lower])) return $this->colors[$lower];
-        
         if ($color[0] === '#') {
             // hexadecimal handling
             $hex = substr($color, 1);

library/HTMLPurifier/AttrDef/Composite.php

@@ -1,26 +1,10 @@
 <?php
 
-/**
- * Allows multiple validators to attempt to validate attribute.
- * 
- * Composite is just what it sounds like: a composite of many validators.
- * This means that multiple HTMLPurifier_AttrDef objects will have a whack
- * at the string.  If one of them passes, that's what is returned.  This is
- * especially useful for CSS values, which often are a choice between
- * an enumerated set of predefined values or a flexible data type.
- */
 class HTMLPurifier_AttrDef_Composite extends HTMLPurifier_AttrDef
 {
     
-    /**
-     * List of HTMLPurifier_AttrDef objects that may process strings
-     * @protected
-     */
     var $defs;
     
-    /**
-     * @param $defs List of HTMLPurifier_AttrDef objects
-     */
     function HTMLPurifier_AttrDef_Composite($defs) {
         $this->defs = $defs;
     }

library/HTMLPurifier/AttrDef/Enum.php

@@ -3,27 +3,12 @@
 require_once 'HTMLPurifier/AttrDef.php';
 
 // Enum = Enumerated
-/**
- * Validates a keyword against a list of valid values.
- */
 class HTMLPurifier_AttrDef_Enum extends HTMLPurifier_AttrDef
 {
     
-    /**
-     * Lookup table of valid values.
-     */
     var $valid_values   = array();
-    
-    /**
-     * Bool indicating whether or not enumeration is case sensitive.
-     * @note In general this is always case insensitive.
-     */
     var $case_sensitive = false; // values according to W3C spec
     
-    /**
-     * @param $valid_values List of valid values
-     * @param $case_sensitive Bool indicating whether or not case sensitive
-     */
     function HTMLPurifier_AttrDef_Enum(
         $valid_values = array(), $case_sensitive = false) {
         

library/HTMLPurifier/AttrDef/Font.php

@@ -1,154 +0,0 @@
-<?php
-
-require_once 'HTMLPurifier/AttrDef.php';
-
-/**
- * Validates shorthand CSS property font.
- */
-class HTMLPurifier_AttrDef_Font extends HTMLPurifier_AttrDef
-{
-    
-    /**
-     * Local copy of component validators.
-     * 
-     * @note If we moved specific CSS property definitions to their own
-     *       classes instead of having them be assembled at run time by
-     *       CSSDefinition, this wouldn't be necessary.  We'd instantiate
-     *       our own copies.
-     */
-    var $info = array();
-    
-    /**
-     * System font keywords.
-     */
-    var $system_fonts = array(
-        'caption' => true,
-        'icon' => true,
-        'menu' => true,
-        'message-box' => true,
-        'small-caption' => true,
-        'status-bar' => true
-    );
-    
-    function HTMLPurifier_AttrDef_Font($config) {
-        $def = $config->getCSSDefinition();
-        $this->info['font-style']   = $def->info['font-style'];
-        $this->info['font-variant'] = $def->info['font-variant'];
-        $this->info['font-weight']  = $def->info['font-weight'];
-        $this->info['font-size']    = $def->info['font-size'];
-        $this->info['line-height']  = $def->info['line-height'];
-        $this->info['font-family']  = $def->info['font-family'];
-    }
-    
-    function validate($string, $config, &$context) {
-        
-        // regular pre-processing
-        $string = $this->parseCDATA($string);
-        if ($string === '') return false;
-        
-        // check if it's one of the keywords
-        $lowercase_string = strtolower($string);
-        if (isset($this->system_fonts[$lowercase_string])) {
-            return $lowercase_string;
-        }
-        
-        $bits = explode(' ', $string); // bits to process
-        $stage = 0; // this indicates what we're looking for
-        $caught = array(); // which stage 0 properties have we caught?
-        $stage_1 = array('font-style', 'font-variant', 'font-weight');
-        $final = ''; // output
-        
-        for ($i = 0, $size = count($bits); $i < $size; $i++) {
-            if ($bits[$i] === '') continue;
-            switch ($stage) {
-                
-                // attempting to catch font-style, font-variant or font-weight
-                case 0:
-                    foreach ($stage_1 as $validator_name) {
-                        if (isset($caught[$validator_name])) continue;
-                        $r = $this->info[$validator_name]->validate(
-                                                $bits[$i], $config, $context);
-                        if ($r !== false) {
-                            $final .= $r . ' ';
-                            $caught[$validator_name] = true;
-                            break;
-                        }
-                    }
-                    // all three caught, continue on
-                    if (count($caught) >= 3) $stage = 1;
-                    if ($r !== false) break;
-                
-                // attempting to catch font-size and perhaps line-height
-                case 1:
-                    $found_slash = false;
-                    if (strpos($bits[$i], '/') !== false) {
-                        list($font_size, $line_height) =
-                                                    explode('/', $bits[$i]);
-                        if ($line_height === '') {
-                            // ooh, there's a space after the slash!
-                            $line_height = false;
-                            $found_slash = true;
-                        }
-                    } else {
-                        $font_size = $bits[$i];
-                        $line_height = false;
-                    }
-                    $r = $this->info['font-size']->validate(
-                                              $font_size, $config, $context);
-                    if ($r !== false) {
-                        $final .= $r;
-                        // attempt to catch line-height
-                        if ($line_height === false) {
-                            // we need to scroll forward
-                            for ($j = $i + 1; $j < $size; $j++) {
-                                if ($bits[$j] === '') continue;
-                                if ($bits[$j] === '/') {
-                                    if ($found_slash) {
-                                        return false;
-                                    } else {
-                                        $found_slash = true;
-                                        continue;
-                                    }
-                                }
-                                $line_height = $bits[$j];
-                                break;
-                            }
-                        } else {
-                            // slash already found
-                            $found_slash = true;
-                            $j = $i;
-                        }
-                        if ($found_slash) {
-                            $i = $j;
-                            $r = $this->info['line-height']->validate(
-                                              $line_height, $config, $context);
-                            if ($r !== false) {
-                                $final .= '/' . $r;
-                            }
-                        }
-                        $final .= ' ';
-                        $stage = 2;
-                        break;
-                    }
-                    return false;
-                
-                // attempting to catch font-family
-                case 2:
-                    $font_family =
-                        implode(' ', array_slice($bits, $i, $size - $i));
-                    $r = $this->info['font-family']->validate(
-                                              $font_family, $config, $context);
-                    if ($r !== false) {
-                        $final .= $r . ' ';
-                        // processing completed successfully
-                        return rtrim($final);
-                    }
-                    return false;
-            }
-        }
-        return false;
-    }
-    
-}
-
-?>

library/HTMLPurifier/AttrDef/FontFamily.php

@@ -4,16 +4,9 @@ require_once 'HTMLPurifier/AttrDef.php';
 
 // whitelisting allowed fonts would be nice
 
-/**
- * Validates a font family list according to CSS spec
- */
 class HTMLPurifier_AttrDef_FontFamily extends HTMLPurifier_AttrDef
 {
     
-    /**
-     * Generic font family keywords.
-     * @protected
-     */
     var $generic_names = array(
         'serif' => true,
         'sans-serif' => true,

library/HTMLPurifier/AttrDef/Host.php

@@ -4,21 +4,10 @@ require_once 'HTMLPurifier/AttrDef.php';
 require_once 'HTMLPurifier/AttrDef/IPv4.php';
 require_once 'HTMLPurifier/AttrDef/IPv6.php';
 
-/**
- * Validates a host according to the IPv4, IPv6 and DNS specifications.
- */
 class HTMLPurifier_AttrDef_Host extends HTMLPurifier_AttrDef
 {
     
-    /**
-     * Instance of HTMLPurifier_AttrDef_IPv4 sub-validator
-     */
-    var $ipv4;
-    
-    /**
-     * Instance of HTMLPurifier_AttrDef_IPv6 sub-validator
-     */
-    var $ipv6;
+    var $ipv4, $ipv6;
     
     function HTMLPurifier_AttrDef_Host() {
         $this->ipv4 = new HTMLPurifier_AttrDef_IPv4();

library/HTMLPurifier/AttrDef/ID.php

@@ -2,15 +2,12 @@
 
 require_once 'HTMLPurifier/AttrDef.php';
 require_once 'HTMLPurifier/IDAccumulator.php';
-
-/**
- * Validates the HTML attribute ID.
- * @warning Even though this is the id processor, it
- *          will ignore the directive Attr:IDBlacklist, since it will only
- *          go according to the ID accumulator. Since the accumulator is
- *          automatically generated, it will have already absorbed the
- *          blacklist. If you're hacking around, make sure you use load()!
- */
+        
+// NOTE QUIRKY BEHAVIOR: even though this is the id processor, it
+// will ignore directive Attr:IDBlacklist, since it will only
+// go according to the ID accumulator. Since the accumulator is
+// automatically generated, it will have already absorbed the
+// blacklist. If you're hacking around, make sure you use load()!
 
 class HTMLPurifier_AttrDef_ID extends HTMLPurifier_AttrDef
 {

library/HTMLPurifier/AttrDef/IPv4.php

@@ -2,17 +2,12 @@
 
 require_once 'HTMLPurifier/AttrDef.php';
 
-/**
- * Validates an IPv4 address
- * @author Feyd @ forums.devnetwork.net (public domain)
- */
+// spliced from Feyd's IPv6 function (pd)
+
 class HTMLPurifier_AttrDef_IPv4 extends HTMLPurifier_AttrDef
 {
     
-    /**
-     * IPv4 regex, protected so that IPv6 can reuse it
-     * @protected
-     */
+    // regex is public so that IPv6 can reuse it
     var $ip4;
     
     function HTMLPurifier_AttrDef_IPv4() {

library/HTMLPurifier/AttrDef/IPv6.php

@@ -2,12 +2,11 @@
 
 require_once 'HTMLPurifier/AttrDef/IPv4.php';
 
-/**
- * Validates an IPv6 address.
- * @author Feyd @ forums.devnetwork.net (public domain)
- * @note This function requires brackets to have been removed from address
- *       in URI.
- */
+// IPv6 by Feyd, source is in public domain
+
+// note that this expects the brackets to be removed from IPv6 addresses
+// extends from the IPv4 impl. so we can borrow its regex
+
 class HTMLPurifier_AttrDef_IPv6 extends HTMLPurifier_AttrDef_IPv4
 {
     

library/HTMLPurifier/AttrDef/Integer.php

@@ -2,42 +2,16 @@
 
 require_once 'HTMLPurifier/AttrDef.php';
 
-/**
- * Validates an integer.
- * @note While this class was modeled off the CSS definition, no currently
- *       allowed CSS uses this type.  The properties that do are: widows,
- *       orphans, z-index, counter-increment, counter-reset.  Some of the
- *       HTML attributes, however, find use for a non-negative version of this.
- */
+// appears to be a dud class: no currently allowed CSS uses this type
+// Uses this: widows, orphans, z-index, counter-increment, counter-reset
+
 class HTMLPurifier_AttrDef_Integer extends HTMLPurifier_AttrDef
 {
     
-    /**
-     * Bool indicating whether or not negative values are allowed
-     */
-    var $negative = true;
+    var $non_negative = false;
     
-    /**
-     * Bool indicating whether or not zero is allowed
-     */
-    var $zero = true;
-    
-    /**
-     * Bool indicating whether or not positive values are allowed
-     */
-    var $positive = true;
-    
-    /**
-     * @param $negative Bool indicating whether or not negative values are allowed
-     * @param $zero Bool indicating whether or not zero is allowed
-     * @param $positive Bool indicating whether or not positive values are allowed
-     */
-    function HTMLPurifier_AttrDef_Integer(
-        $negative = true, $zero = true, $positive = true
-    ) {
-        $this->negative = $negative;
-        $this->zero     = $zero;
-        $this->positive = $positive;
+    function HTMLPurifier_AttrDef_Integer($non_negative = false) {
+        $this->non_negative = $non_negative;
     }
     
     function validate($integer, $config, &$context) {
@@ -45,27 +19,15 @@ class HTMLPurifier_AttrDef_Integer extends HTMLPurifier_AttrDef
         $integer = $this->parseCDATA($integer);
         if ($integer === '') return false;
         
-        // we could possibly simply typecast it to integer, but there are
-        // certain fringe cases that must not return an integer.
-        
-        // clip leading sign
-        if ( $this->negative && $integer[0] === '-' ) {
+        if ( !$this->non_negative && $integer[0] === '-' ) {
             $digits = substr($integer, 1);
-            if ($digits === '0') $integer = '0'; // rm minus sign for zero
-        } elseif( $this->positive && $integer[0] === '+' ) {
-            $digits = $integer = substr($integer, 1); // rm unnecessary plus
+        } elseif( $integer[0] === '+' ) {
+            $digits = $integer = substr($integer, 1);
         } else {
             $digits = $integer;
         }
         
-        // test if it's numeric
         if (!ctype_digit($digits)) return false;
-        
-        // perform scope tests
-        if (!$this->zero     && $integer == 0) return false;
-        if (!$this->positive && $integer > 0) return false;
-        if (!$this->negative && $integer < 0) return false;
-        
         return $integer;
         
     }

library/HTMLPurifier/AttrDef/Lang.php

@@ -2,10 +2,8 @@
 
 require_once 'HTMLPurifier/AttrDef.php';
 
-/**
- * Validates the HTML attribute lang, effectively a language code.
- * @note Built according to RFC 3066, which obsoleted RFC 1766
- */
+// built according to RFC 3066, which obsoleted RFC 1766
+
 class HTMLPurifier_AttrDef_Lang extends HTMLPurifier_AttrDef
 {
     

library/HTMLPurifier/AttrDef/ListStyle.php

@@ -1,78 +0,0 @@
-<?php
-
-require_once 'HTMLPurifier/AttrDef.php';
-
-/**
- * Validates shorthand CSS property list-style.
- * @note This currently does not support list-style-image, as that functionality
- *       is not implemented yet elsewhere.
- */
-class HTMLPurifier_AttrDef_ListStyle extends HTMLPurifier_AttrDef
-{
-    
-    /**
-     * Local copy of component validators.
-     * @note See HTMLPurifier_AttrDef_Font::$info for a similar impl.
-     */
-    var $info;
-    
-    function HTMLPurifier_AttrDef_ListStyle($config) {
-        $def = $config->getCSSDefinition();
-        $this->info['list-style-type']     = $def->info['list-style-type'];
-        $this->info['list-style-position'] = $def->info['list-style-position'];
-    }
-    
-    function validate($string, $config, &$context) {
-        
-        // regular pre-processing
-        $string = $this->parseCDATA($string);
-        if ($string === '') return false;
-        
-        $bits = explode(' ', strtolower($string)); // bits to process
-        
-        $caught_type = false;
-        $caught_position = false;
-        $caught_none = false; // as in keyword none, which is in all of them
-        
-        $ret = '';
-        
-        foreach ($bits as $bit) {
-            if ($caught_none && ($caught_type || $caught_position)) break;
-            if ($caught_type && $caught_position) break;
-            
-            if ($bit === '') continue;
-            
-            if ($bit === 'none') {
-                if ($caught_none) continue;
-                $caught_none = true;
-                $ret .= 'none ';
-                continue;
-            }
-            
-            // if we add anymore, roll it into a loop
-            
-            $r = $this->info['list-style-type']->validate($bit, $config, $context);
-            if ($r !== false) {
-                if ($caught_type) continue;
-                $caught_type = true;
-                $ret .= $r . ' ';
-                continue;
-            }
-            
-            $r = $this->info['list-style-position']->validate($bit, $config, $context);
-            if ($r !== false) {
-                if ($caught_position) continue;
-                $caught_position = true;
-                $ret .= $r . ' ';
-                continue;
-            }
-        }
-        
-        $ret = rtrim($ret);
-        return $ret ? $ret : false;
-        
-    }
-    
-}
-
-?>

library/HTMLPurifier/AttrDef/MultiLength.php

@@ -3,12 +3,6 @@
 require_once 'HTMLPurifier/AttrDef.php';
 require_once 'HTMLPurifier/AttrDef/Length.php';
 
-/**
- * Validates a MultiLength as defined by the HTML spec.
- * 
- * A multilength is either a integer (pixel count), a percentage, or
- * a relative number.
- */
 class HTMLPurifier_AttrDef_MultiLength extends HTMLPurifier_AttrDef_Length
 {
     

library/HTMLPurifier/AttrDef/Multiple.php

@@ -2,34 +2,12 @@
 
 require_once 'HTMLPurifier/AttrDef.php';
 
-/**
- * Framework class for strings that involve multiple values.
- * 
- * Certain CSS properties such as border-width and margin allow multiple
- * lengths to be specified.  This class can take a vanilla border-width
- * definition and multiply it, usually into a max of four.
- * 
- * @note Even though the CSS specification isn't clear about it, inherit
- *       can only be used alone: it will never manifest as part of a multi
- *       shorthand declaration.  Thus, this class does not allow inherit.
- */
 class HTMLPurifier_AttrDef_Multiple extends HTMLPurifier_AttrDef
 {
     
-    /**
-     * Instance of component definition to defer validation to.
-     */
     var $single;
-    
-    /**
-     * Max number of values allowed.
-     */
     var $max;
     
-    /**
-     * @param $single HTMLPurifier_AttrDef to multiply
-     * @param $max Max number of values allowed (usually four)
-     */
     function HTMLPurifier_AttrDef_Multiple($single, $max = 4) {
         $this->single = $single;
         $this->max = $max;

library/HTMLPurifier/AttrDef/Number.php

@@ -1,19 +1,10 @@
 <?php
 
-/**
- * Validates a number as defined by the CSS spec.
- */
 class HTMLPurifier_AttrDef_Number extends HTMLPurifier_AttrDef
 {
     
-    /**
-     * Bool indicating whether or not only positive values allowed.
-     */
     var $non_negative = false;
     
-    /**
-     * @param $non_negative Bool indicating whether negatives are forbidden
-     */
     function HTMLPurifier_AttrDef_Number($non_negative = false) {
         $this->non_negative = $non_negative;
     }

library/HTMLPurifier/AttrDef/NumberSpan.php

@@ -0,0 +1,23 @@
+<?php
+
+require_once 'HTMLPurifier/AttrDef.php';
+
+// for col and row spans, essentially, a positive integer
+class HTMLPurifier_AttrDef_NumberSpan extends HTMLPurifier_AttrDef
+{
+    
+    function validate($string, $config, &$context) {
+        
+        $string = trim($string);
+        if ($string === '') return false;
+        if ($string === '1') return false; // this is the default value
+        if (!is_numeric($string)) return false;
+        $int = (int) $string;
+        if ($int <= 0) return false;
+        return (string) $int;
+        
+    }
+    
+}
+
+?>

library/HTMLPurifier/AttrDef/Percentage.php

@@ -3,21 +3,11 @@
 require_once 'HTMLPurifier/AttrDef.php';
 require_once 'HTMLPurifier/AttrDef/Number.php';
 
-/**
- * Validates a Percentage as defined by the HTML spec.
- * @note This also allows integer pixel values.
- */
 class HTMLPurifier_AttrDef_Percentage extends HTMLPurifier_AttrDef
 {
     
-    /**
-     * Instance of HTMLPurifier_AttrDef_Number to defer pixel validation
-     */
     var $number_def;
     
-    /**
-     * @param Bool indicating whether to forbid negative values
-     */
     function HTMLPurifier_AttrDef_Percentage($non_negative = false) {
         $this->number_def = new HTMLPurifier_AttrDef_Number($non_negative);
     }

library/HTMLPurifier/AttrDef/Pixels.php

@@ -2,9 +2,6 @@
 
 require_once 'HTMLPurifier/AttrDef.php';
 
-/**
- * Validates an integer representation of pixels according to the HTML spec.
- */
 class HTMLPurifier_AttrDef_Pixels extends HTMLPurifier_AttrDef
 {
     

library/HTMLPurifier/AttrDef/Text.php

@@ -2,9 +2,6 @@
 
 require_once 'HTMLPurifier/AttrDef.php';
 
-/**
- * Validates arbitrary text according to the HTML spec.
- */
 class HTMLPurifier_AttrDef_Text extends HTMLPurifier_AttrDef
 {
     

library/HTMLPurifier/AttrDef/TextDecoration.php

@@ -2,18 +2,9 @@
 
 require_once 'HTMLPurifier/AttrDef.php';
 
-/**
- * Validates the value for the CSS property text-decoration
- * @note This class could be generalized into a version that acts sort of
- *       like Enum except you can compound the allowed values.
- */
 class HTMLPurifier_AttrDef_TextDecoration extends HTMLPurifier_AttrDef
 {
     
-    /**
-     * Lookup table of allowed values.
-     * @protected
-     */
     var $allowed_values = array(
         'line-through' => true,
         'overline' => true,

library/HTMLPurifier/AttrDef/URI.php

@@ -5,16 +5,12 @@ require_once 'HTMLPurifier/URIScheme.php';
 require_once 'HTMLPurifier/URISchemeRegistry.php';
 require_once 'HTMLPurifier/AttrDef/Host.php';
 
-HTMLPurifier_ConfigSchema::define(
-    'URI', 'DefaultScheme', 'http', 'string',
+HTMLPurifier_ConfigDef::define(
+    'URI', 'DefaultScheme', 'http',
     'Defines through what scheme the output will be served, in order to '.
     'select the proper object validator when no scheme information is present.'
 );
 
-/**
- * Validates a URI as defined by RFC 3986.
- * @note Scheme-specific mechanics deferred to HTMLPurifier_URIScheme
- */
 class HTMLPurifier_AttrDef_URI extends HTMLPurifier_AttrDef
 {
     
@@ -36,13 +32,13 @@ class HTMLPurifier_AttrDef_URI extends HTMLPurifier_AttrDef
         // for HTTP and thus won't work for our generic URI parsing
         
         // according to the RFC... (but this cuts corners, i.e. non-validating)
-        $r_URI = '!'.
-            '(([^:/?#<>\'"]+):)?'. // 2. Scheme
-            '(//([^/?#<>\'"]*))?'. // 4. Authority
-            '([^?#<>\'"]*)'.       // 5. Path
-            '(\?([^#<>\'"]*))?'.   // 7. Query
-            '(#([^<>\'"]*))?'.     // 8. Fragment
-            '!';
+        $r_URI = '!^'.
+            '(([^:/?#<>]+):)?'. // 2. Scheme
+            '(//([^/?#<>]*))?'. // 4. Authority
+            '([^?#<>]*)'.       // 5. Path
+            '(\?([^#<>]*))?'.   // 7. Query
+            '(#([^<>]*))?'.     // 8. Fragment
+            '$!';
         
         $matches = array();
         $result = preg_match($r_URI, $uri, $matches);

library/HTMLPurifier/AttrTransform.php

@@ -1,31 +1,12 @@
 <?php
 
-/**
- * Processes an entire attribute array for corrections needing multiple values.
- * 
- * Occasionally, a certain attribute will need to be removed and popped onto
- * another value.  Instead of creating a complex return syntax for
- * HTMLPurifier_AttrDef, we just pass the whole attribute array to a
- * specialized object and have that do the special work.  That is the
- * family of HTMLPurifier_AttrTransform.
- * 
- * An attribute transformation can be assigned to run before or after
- * HTMLPurifier_AttrDef validation.  See HTMLPurifier_HTMLDefinition for
- * more details.
- */
-
+// AttrTransform = Attribute Transformation, when handling one attribute
+//                 isn't enough
 class HTMLPurifier_AttrTransform
 {
+    function HTMLPurifier_AttrTransform() {}
     
-    /**
-     * Abstract: makes changes to the attributes dependent on multiple values.
-     * 
-     * @param $attr Assoc array of attributes, usually from
-     *              HTMLPurifier_Token_Tag::$attributes
-     * @param $config Mandatory HTMLPurifier_Config object.
-     * @returns Processed attribute array.
-     */
-    function transform($attr, $config) {
+    function transform($token, $config = null) {
         trigger_error('Cannot call abstract function', E_USER_ERROR);
     }
 }

library/HTMLPurifier/AttrTransform/BdoDir.php

@@ -4,26 +4,20 @@ require_once 'HTMLPurifier/AttrTransform.php';
 
 // this MUST be placed in post, as it assumes that any value in dir is valid
 
-HTMLPurifier_ConfigSchema::define(
-    'Attr', 'DefaultTextDir', 'ltr', 'string',
+HTMLPurifier_ConfigDef::define(
+    'Attr', 'DefaultTextDir', 'ltr',
     'Defines the default text direction (ltr or rtl) of the document '.
     'being parsed.  This generally is the same as the value of the dir '.
     'attribute in HTML, or ltr if that is not specified.'
 );
-HTMLPurifier_ConfigSchema::defineAllowedValues(
-    'Attr', 'DefaultTextDir', array( 'ltr', 'rtl' )
-);
 
-/**
- * Post-trasnform that ensures that bdo tags have the dir attribute set.
- */
 class HTMLPurifier_AttrTransform_BdoDir extends HTMLPurifier_AttrTransform
 {
     
-    function transform($attr, $config) {
-        if (isset($attr['dir'])) return $attr;
-        $attr['dir'] = $config->get('Attr', 'DefaultTextDir');
-        return $attr;
+    function transform($attributes, $config) {
+        if (isset($attributes['dir'])) return $attributes;
+        $attributes['dir'] = $config->get('Attr', 'DefaultTextDir');
+        return $attributes;
     }
     
 }

library/HTMLPurifier/AttrTransform/ImgRequired.php

@@ -4,44 +4,41 @@ require_once 'HTMLPurifier/AttrTransform.php';
 
 // must be called POST validation
 
-HTMLPurifier_ConfigSchema::define(
-    'Attr', 'DefaultInvalidImage', '', 'string',
+HTMLPurifier_ConfigDef::define(
+    'Attr', 'DefaultInvalidImage', '',
     'This is the default image an img tag will be pointed to if it does '.
     'not have a valid src attribute.  In future versions, we may allow the '.
     'image tag to be removed completely, but due to design issues, this is '.
     'not possible right now.'
 );
 
-HTMLPurifier_ConfigSchema::define(
-    'Attr', 'DefaultInvalidImageAlt', 'Invalid image', 'string',
+HTMLPurifier_ConfigDef::define(
+    'Attr', 'DefaultInvalidImageAlt', 'Invalid image',
     'This is the content of the alt tag of an invalid image if the user '.
     'had not previously specified an alt attribute.  It has no effect when the '.
     'image is valid but there was no alt attribute present.'
 );
 
-/**
- * Post-transform that ensures the required attrs of img (alt and src) are set
- */
 class HTMLPurifier_AttrTransform_ImgRequired extends HTMLPurifier_AttrTransform
 {
     
-    function transform($attr, $config) {
+    function transform($attributes, $config) {
         
         $src = true;
-        if (!isset($attr['src'])) {
-            $attr['src'] = $config->get('Attr', 'DefaultInvalidImage');
+        if (!isset($attributes['src'])) {
+            $attributes['src'] = $config->get('Attr', 'DefaultInvalidImage');
             $src = false;
         }
         
-        if (!isset($attr['alt'])) {
+        if (!isset($attributes['alt'])) {
             if ($src) {
-                $attr['alt'] = basename($attr['src']);
+                $attributes['alt'] = basename($attributes['src']);
             } else {
-                $attr['alt'] = $config->get('Attr', 'DefaultInvalidImageAlt');
+                $attributes['alt'] = $config->get('Attr', 'DefaultInvalidImageAlt');
             }
         }
         
-        return $attr;
+        return $attributes;
         
     }
     

library/HTMLPurifier/AttrTransform/Lang.php

@@ -2,11 +2,9 @@
 
 require_once 'HTMLPurifier/AttrTransform.php';
 
-/**
- * Post-transform that copies lang's value to xml:lang (and vice-versa)
- * @note Theoretically speaking, this could be a pre-transform, but putting
- *       post is more efficient.
- */
+// this transformation may be done pre or post validation, but post is
+// preferred, since invalid languages then will have been dropped.
+
 class HTMLPurifier_AttrTransform_Lang extends HTMLPurifier_AttrTransform
 {
     

library/HTMLPurifier/AttrTransform/TextAlign.php

@@ -2,9 +2,6 @@
 
 require_once 'HTMLPurifier/AttrTransform.php';
 
-/**
- * Pre-transform that changes deprecated align attribute to text-align.
- */
 class HTMLPurifier_AttrTransform_TextAlign
     extends HTMLPurifier_AttrTransform {
 

library/HTMLPurifier/CSSDefinition.php

@@ -8,26 +8,26 @@ require_once 'HTMLPurifier/AttrDef/Percentage.php';
 require_once 'HTMLPurifier/AttrDef/Multiple.php';
 require_once 'HTMLPurifier/AttrDef/TextDecoration.php';
 require_once 'HTMLPurifier/AttrDef/FontFamily.php';
-require_once 'HTMLPurifier/AttrDef/Font.php';
-require_once 'HTMLPurifier/AttrDef/Border.php';
-require_once 'HTMLPurifier/AttrDef/ListStyle.php';
 
-/**
- * Defines allowed CSS attributes and what their values are.
- * @see HTMLPurifier_HTMLDefinition
- */
 class HTMLPurifier_CSSDefinition
 {
     
-    /**
-     * Assoc array of attribute name to definition object.
-     */
     var $info = array();
     
-    /**
-     * Constructs the info array.  The meat of this class.
-     */
-    function setup($config) {
+    function &instance($prototype = null) {
+        static $instance = null;
+        if ($prototype) {
+            $instance = $prototype;
+        } elseif (!$instance) {
+            $instance = new HTMLPurifier_CSSDefinition();
+            $instance->setup();
+        }
+        return $instance;
+    }
+    
+    function HTMLPurifier_CSSDefinition() {}
+    
+    function setup() {
         
         $this->info['text-align'] = new HTMLPurifier_AttrDef_Enum(
             array('left', 'right', 'center', 'justify'), false);
@@ -50,28 +50,15 @@ class HTMLPurifier_CSSDefinition
             array('normal', 'italic', 'oblique'), false);
         $this->info['font-variant'] = new HTMLPurifier_AttrDef_Enum(
             array('normal', 'small-caps'), false);
-        
         $this->info['list-style-position'] = new HTMLPurifier_AttrDef_Enum(
             array('inside', 'outside'), false);
         $this->info['list-style-type'] = new HTMLPurifier_AttrDef_Enum(
             array('disc', 'circle', 'square', 'decimal', 'lower-roman',
             'upper-roman', 'lower-alpha', 'upper-alpha'), false);
-        
-        $this->info['list-style'] = new HTMLPurifier_AttrDef_ListStyle($config);
-        
         $this->info['text-transform'] = new HTMLPurifier_AttrDef_Enum(
             array('capitalize', 'uppercase', 'lowercase', 'none'), false);
         $this->info['color'] = new HTMLPurifier_AttrDef_Color();
         
-        // technically speaking, this one should get its own validator, but
-        // since we don't support background images, it effectively is
-        // equivalent to color.  The only trouble is that if the author
-        // specifies an image and a color, they'll both end up getting dropped,
-        // even though we ought to implement it and just discard the image
-        // info.  This will be fixed in a later version (see TODO) when
-        // better URI filtering is implemented.
-        $this->info['background'] = 
-        
         $border_color = 
         $this->info['border-top-color'] = 
         $this->info['border-bottom-color'] = 
@@ -164,33 +151,6 @@ class HTMLPurifier_CSSDefinition
             array('normal', 'bold', 'bolder', 'lighter', '100', '200', '300',
             '400', '500', '600', '700', '800', '900'), false);
         
-        // MUST be called after other font properties, as it references
-        // a CSSDefinition object
-        $this->info['font'] = new HTMLPurifier_AttrDef_Font($config);
-        
-        // same here
-        $this->info['border'] =
-        $this->info['border-bottom'] = 
-        $this->info['border-top'] = 
-        $this->info['border-left'] = 
-        $this->info['border-right'] = new HTMLPurifier_AttrDef_Border($config);
-        
-        $this->info['border-collapse'] = new HTMLPurifier_AttrDef_Enum(array(
-            'collapse', 'seperate'));
-        
-        $this->info['caption-side'] = new HTMLPurifier_AttrDef_Enum(array(
-            'top', 'bottom'));
-        
-        $this->info['table-layout'] = new HTMLPurifier_AttrDef_Enum(array(
-            'auto', 'fixed'));
-        
-        $this->info['vertical-align'] = new HTMLPurifier_AttrDef_Composite(array(
-            new HTMLPurifier_AttrDef_Enum(array('baseline', 'sub', 'super',
-                'top', 'text-top', 'middle', 'bottom', 'text-bottom')),
-            new HTMLPurifier_AttrDef_CSSLength(),
-            new HTMLPurifier_AttrDef_Percentage()
-        ));
-        
     }
     
 }

library/HTMLPurifier/ChildDef.php

@@ -5,8 +5,15 @@
 // false = delete parent node and all children
 // array(...) = replace children nodes with these
 
-HTMLPurifier_ConfigSchema::define(
-    'Core', 'EscapeInvalidChildren', false, 'bool',
+// this is the hardest one to implement. We'll use fancy regexp tricks
+// right now, we only expect it to return TRUE or FALSE (it won't attempt
+// to fix the tree)
+
+// we may end up writing custom code for each HTML case
+// in order to make it self correcting
+
+HTMLPurifier_ConfigDef::define(
+    'Core', 'EscapeInvalidChildren', false,
     'When true, a child is found that is not allowed in the context of the '.
     'parent element will be transformed into text as if it were ASCII. When '.
     'false, that element and all internal tags will be dropped, though text '.
@@ -14,74 +21,25 @@ HTMLPurifier_ConfigSchema::define(
     'preserving child nodes.'
 );
 
-/**
- * Defines allowed child nodes and validates tokens against it.
- */
 class HTMLPurifier_ChildDef
 {
-    /**
-     * Type of child definition, usually right-most part of class name lowercase
-     * 
-     * Used occasionally in terms of context.  Possible values include
-     * custom, required, optional and empty.
-     */
     var $type;
-    
-    /**
-     * Bool that indicates whether or not an empty array of children is okay
-     * 
-     * This is necessary for redundant checking when changes affecting
-     * a child node may cause a parent node to now be disallowed.
-     */
     var $allow_empty;
-    
-    /**
-     * 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 $context String context indicating inline, block or unknown
-     * @return bool true to leave nodes as is
-     * @return bool false to remove parent node
-     * @return array of replacement child tokens
-     */
-    function validateChildren($tokens_of_children, $config, $context) {
+    function validateChildren($tokens_of_children) {
         trigger_error('Call to abstract function', E_USER_ERROR);
     }
 }
 
-/**
- * Custom validation class, accepts DTD child definitions
- * 
- * @warning Currently this class is an all or nothing proposition, that is,
- *          it will only give a bool return value.
- * @note This class is currently not used by any code, although it is unit
- *       tested.
- */
 class HTMLPurifier_ChildDef_Custom extends HTMLPurifier_ChildDef
 {
     var $type = 'custom';
     var $allow_empty = false;
-    /**
-     * Allowed child pattern as defined by the DTD
-     */
     var $dtd_regex;
-    /**
-     * PCRE regex derived from $dtd_regex
-     * @private
-     */
     var $_pcre_regex;
-    /**
-     * @param $dtd_regex Allowed child pattern from the DTD
-     */
     function HTMLPurifier_ChildDef_Custom($dtd_regex) {
         $this->dtd_regex = $dtd_regex;
         $this->_compileRegex();
     }
-    /**
-     * Compiles the PCRE regex from a DTD regex ($dtd_regex to $_pcre_regex)
-     */
     function _compileRegex() {
         $raw = str_replace(' ', '', $this->dtd_regex);
         if ($raw{0} != '(') {
@@ -121,18 +79,9 @@ class HTMLPurifier_ChildDef_Custom extends HTMLPurifier_ChildDef
     }
 }
 
-/**
- * Definition that allows a set of elements, but disallows empty children.
- */
 class HTMLPurifier_ChildDef_Required extends HTMLPurifier_ChildDef
 {
-    /**
-     * Lookup table of allowed elements.
-     */
     var $elements = array();
-    /**
-     * @param $elements List of allowed element names (lowercase).
-     */
     function HTMLPurifier_ChildDef_Required($elements) {
         if (is_string($elements)) {
             $elements = str_replace(' ', '', $elements);
@@ -216,13 +165,8 @@ class HTMLPurifier_ChildDef_Required extends HTMLPurifier_ChildDef
     }
 }
 
-/**
- * Definition that allows a set of elements, and allows no children.
- * @note This is a hack to reuse code from HTMLPurifier_ChildDef_Required,
- *       really, one shouldn't inherit from the other.  Only altered behavior
- *       is to overload a returned false with an array.  Thus, it will never
- *       return false.
- */
+// only altered behavior is that it returns an empty array
+// instead of a false (to delete the node)
 class HTMLPurifier_ChildDef_Optional extends HTMLPurifier_ChildDef_Required
 {
     var $allow_empty = true;
@@ -234,48 +178,23 @@ class HTMLPurifier_ChildDef_Optional extends HTMLPurifier_ChildDef_Required
     }
 }
 
-/**
- * Definition that disallows all elements.
- * @warning validateChildren() in this class is actually never called, because
- *          empty elements are corrected in HTMLPurifier_Strategy_MakeWellFormed
- *          before child definitions are parsed in earnest by
- *          HTMLPurifier_Strategy_FixNesting.
- */
+// placeholder
 class HTMLPurifier_ChildDef_Empty extends HTMLPurifier_ChildDef
 {
     var $allow_empty = true;
     var $type = 'empty';
     function HTMLPurifier_ChildDef_Empty() {}
     function validateChildren($tokens_of_children, $config, $context) {
-        return array();
+        return false;
     }
 }
 
-/**
- * Definition that uses different definitions depending on context.
- * 
- * The del and ins tags are notable because they allow different types of
- * elements depending on whether or not they're in a block or inline context.
- * Chameleon allows this behavior to happen by using two different
- * definitions depending on context.  While this somewhat generalized,
- * it is specifically intended for those two tags.
- */
 class HTMLPurifier_ChildDef_Chameleon extends HTMLPurifier_ChildDef
 {
     
-    /**
-     * Instance of the definition object to use when inline. Usually stricter.
-     */
     var $inline;
-    /**
-     * Instance of the definition object to use when block.
-     */
     var $block;
     
-    /**
-     * @param $inline List of elements to allow when inline.
-     * @param $block List of elements to allow when block.
-     */
     function HTMLPurifier_ChildDef_Chameleon($inline, $block) {
         $this->inline = new HTMLPurifier_ChildDef_Optional($inline);
         $this->block  = new HTMLPurifier_ChildDef_Optional($block);
@@ -300,141 +219,4 @@ class HTMLPurifier_ChildDef_Chameleon extends HTMLPurifier_ChildDef
     }
 }
 
-/**
- * Definition for tables
- */
-class HTMLPurifier_ChildDef_Table extends HTMLPurifier_ChildDef
-{
-    var $allow_empty = false;
-    var $type = 'table';
-    function HTMLPurifier_ChildDef_Table() {}
-    function validateChildren($tokens_of_children, $config, $context) {
-        if (empty($tokens_of_children)) return false;
-        
-        // this ensures that the loop gets run one last time before closing
-        // up. It's a little bit of a hack, but it works! Just make sure you
-        // get rid of the token later.
-        $tokens_of_children[] = false;
-        
-        // only one of these elements is allowed in a table
-        $caption = false;
-        $thead   = false;
-        $tfoot   = false;
-        
-        // as many of these as you want
-        $cols    = array();
-        $content = array();
-        
-        $nesting = 0; // current depth so we can determine nodes
-        $is_collecting = false; // are we globbing together tokens to package
-                                // into one of the collectors?
-        $collection = array(); // collected nodes
-        $tag_index = 0; // the first node might be whitespace,
-                            // so this tells us where the start tag is
-        
-        foreach ($tokens_of_children as $token) {
-            $is_child = ($nesting == 0);
-            
-            if ($token === false) {
-                // terminating sequence started
-            } elseif ($token->type == 'start') {
-                $nesting++;
-            } elseif ($token->type == 'end') {
-                $nesting--;
-            }
-            
-            // handle node collection
-            if ($is_collecting) {
-                if ($is_child) {
-                    // okay, let's stash the tokens away
-                    // first token tells us the type of the collection
-                    switch ($collection[$tag_index]->name) {
-                        case 'tr':
-                        case 'tbody':
-                            $content[] = $collection;
-                            break;
-                        case 'caption':
-                            if ($caption !== false) break;
-                            $caption = $collection;
-                            break;
-                        case 'thead':
-                        case 'tfoot':
-                            // access the appropriate variable, $thead or $tfoot
-                            $var = $collection[$tag_index]->name;
-                            if ($$var === false) {
-                                $$var = $collection;
-                            } else {
-                                // transmutate the first and less entries into
-                                // tbody tags, and then put into content
-                                $collection[$tag_index]->name = 'tbody';
-                                $collection[count($collection)-1]->name = 'tbody';
-                                $content[] = $collection;
-                            }
-                            break;
-                         case 'colgroup':
-                            $cols[] = $collection;
-                            break;
-                    }
-                    $collection = array();
-                    $is_collecting = false;
-                    $tag_index = 0;
-                } else {
-                    // add the node to the collection
-                    $collection[] = $token;
-                }
-            }
-            
-            // terminate
-            if ($token === false) break;
-            
-            if ($is_child) {
-                // determine what we're dealing with
-                if ($token->name == 'col') {
-                    // the only empty tag in the possie, we can handle it
-                    // immediately
-                    $cols[] = array_merge($collection, array($token));
-                    $collection = array();
-                    $tag_index = 0;
-                    continue;
-                }
-                switch($token->name) {
-                    case 'caption':
-                    case 'colgroup':
-                    case 'thead':
-                    case 'tfoot':
-                    case 'tbody':
-                    case 'tr':
-                        $is_collecting = true;
-                        $collection[] = $token;
-                        continue;
-                    default:
-                        if ($token->type == 'text' && $token->is_whitespace) {
-                            $collection[] = $token;
-                            $tag_index++;
-                        }
-                        continue;
-                }
-            }
-        }
-        
-        if (empty($content)) return false;
-        
-        $ret = array();
-        if ($caption !== false) $ret = array_merge($ret, $caption);
-        if ($cols !== false)    foreach ($cols as $token_array) $ret = array_merge($ret, $token_array);
-        if ($thead !== false)   $ret = array_merge($ret, $thead);
-        if ($tfoot !== false)   $ret = array_merge($ret, $tfoot);
-        foreach ($content as $token_array) $ret = array_merge($ret, $token_array);
-        if (!empty($collection) && $is_collecting == false){
-            // grab the trailing space
-            $ret = array_merge($ret, $collection);
-        }
-        
-        array_pop($tokens_of_children); // remove phantom token
-        
-        return ($ret === $tokens_of_children) ? true : $ret;
-        
-    }
-}
-
-?>
+?>

library/HTMLPurifier/Config.php

@@ -1,129 +1,39 @@
 <?php
 
-/**
- * Configuration object that triggers customizable behavior.
- *
- * @warning This class is strongly defined: that means that the class
- *          will fail if an undefined directive is retrieved or set.
- * 
- * @note Many classes that could (although many times don't) use the
- *       configuration object make it a mandatory parameter.  This is
- *       because a configuration object should always be forwarded,
- *       otherwise, you run the risk of missing a parameter and then
- *       being stumped when a configuration directive doesn't work.
- */
+// subclass this to add custom settings
 class HTMLPurifier_Config
 {
     
-    /**
-     * Two-level associative array of configuration directives
-     */
     var $conf;
     
-    /**
-     * Reference HTMLPurifier_ConfigSchema for value checking
-     */
-    var $def;
-    
-    /**
-     * Cached instance of HTMLPurifier_HTMLDefinition
-     */
-    var $html_definition;
-    
-    /**
-     * Cached instance of HTMLPurifier_CSSDefinition
-     */
-    var $css_definition;
-    
-    /**
-     * @param $definition HTMLPurifier_ConfigSchema that defines what directives
-     *                    are allowed.
-     */
     function HTMLPurifier_Config(&$definition) {
-        $this->conf = $definition->defaults; // set up, copy in defaults
-        $this->def  = $definition; // keep a copy around for checking
+        $this->conf = $definition->info; // set up the defaults
     }
     
-    /**
-     * Convenience constructor that creates a default configuration object.
-     * @return Default HTMLPurifier_Config object.
-     */
     function createDefault() {
-        $definition =& HTMLPurifier_ConfigSchema::instance();
+        $definition =& HTMLPurifier_ConfigDef::instance();
         $config = new HTMLPurifier_Config($definition);
         return $config;
     }
     
-    /**
-     * Retreives a value from the configuration.
-     * @param $namespace String namespace
-     * @param $key String key
-     */
     function get($namespace, $key) {
         if (!isset($this->conf[$namespace][$key])) {
             trigger_error('Cannot retrieve value of undefined directive',
-                E_USER_WARNING);
+                E_USER_ERROR);
             return;
         }
         return $this->conf[$namespace][$key];
     }
     
-    /**
-     * Sets a value to configuration.
-     * @param $namespace String namespace
-     * @param $key String key
-     * @param $value Mixed value
-     */
     function set($namespace, $key, $value) {
         if (!isset($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][$key]->type);
-        if (is_string($value)) {
-            // resolve value alias if defined
-            if (isset($this->def->info[$namespace][$key]->aliases[$value])) {
-                $value = $this->def->info[$namespace][$key]->aliases[$value];
-            }
-            if ($this->def->info[$namespace][$key]->allowed !== true) {
-                // check to see if the value is allowed
-                if (!isset($this->def->info[$namespace][$key]->allowed[$value])) {
-                    trigger_error('Value not supported', E_USER_WARNING);
-                    return;
-                }
-            }
-        }
-        if ($value === null) {
-            trigger_error('Value is of invalid type', E_USER_WARNING);
+                E_USER_ERROR);
             return;
         }
         $this->conf[$namespace][$key] = $value;
     }
     
-    /**
-     * Retrieves a copy of the HTML definition.
-     */
-    function getHTMLDefinition() {
-        if ($this->html_definition === null) {
-            $this->html_definition = new HTMLPurifier_HTMLDefinition();
-            $this->html_definition->setup($this);
-        }
-        return $this->html_definition;
-    }
-    
-    /**
-     * Retrieves a copy of the CSS definition
-     */
-    function getCSSDefinition() {
-        if ($this->css_definition === null) {
-            $this->css_definition = new HTMLPurifier_CSSDefinition();
-            $this->css_definition->setup($this);
-        }
-        return $this->css_definition;
-    }
-    
 }
 
 ?>

library/HTMLPurifier/ConfigDef.php

@@ -0,0 +1,50 @@
+<?php
+
+class HTMLPurifier_ConfigDef {
+    
+    var $info = array();
+    
+    function initialize() {
+        $this->defineNamespace('Core', 'Core features that are always available.');
+        $this->defineNamespace('Attr', 'Features regarding attribute validation.');
+        $this->defineNamespace('URI', 'Features regarding Uniform Resource Identifiers.');
+    }
+    
+    function &instance($prototype = null) {
+        static $instance;
+        if ($prototype !== null) {
+            $instance = $prototype;
+        } elseif ($instance === null || $prototype === true) {
+            $instance = new HTMLPurifier_ConfigDef();
+            $instance->initialize();
+        }
+        return $instance;
+    }
+    
+    function define($namespace, $name, $default, $description) {
+        $def =& HTMLPurifier_ConfigDef::instance();
+        if (!isset($def->info[$namespace])) {
+            trigger_error('Cannot define directive for undefined namespace',
+                E_USER_ERROR);
+            return;
+        }
+        if (isset($def->info[$namespace][$name])) {
+            // this behavior is at risk of change
+            trigger_error('Cannot redefine directive', E_USER_ERROR);
+            return;
+        }
+        $def->info[$namespace][$name] = $default;
+    }
+    
+    function defineNamespace($namespace, $description) {
+        $def =& HTMLPurifier_ConfigDef::instance();
+        if (isset($def->info[$namespace])) {
+            trigger_error('Cannot redefine namespace', E_USER_ERROR);
+            return;
+        }
+        $def->info[$namespace] = array();
+    }
+    
+}
+
+?>

library/HTMLPurifier/ConfigSchema.php

@@ -1,337 +0,0 @@
-<?php
-
-/**
- * Configuration definition, defines directives and their defaults.
- * @todo The ability to define things multiple times is confusing and should
- *       be factored out to its own function named registerDependency() or 
- *       addNote(), where only the namespace.name and an extra descriptions
- *       documenting the nature of the dependency are needed.  Since it's
- *       possible that the dependency is registered before the configuration
- *       is defined, deferring it to some sort of cache until it actually
- *       gets defined would be wise, keeping it opaque until it does get
- *       defined. We could add a finalize() method which would cause it to
- *       error out if we get a dangling dependency.  It's difficult, however,
- *       to know whether or not it's a dependency, or a codependency, that is
- *       neither of them fully depends on it. Where does the configuration go
- *       then?  This could be partially resolved by allowing blanket definitions
- *       and then splitting them up into finer-grained versions, however, there
- *       might be implementation difficulties in ini files regarding order of
- *       execution.
- */
-class HTMLPurifier_ConfigSchema {
-    
-    /**
-     * Defaults of the directives and namespaces.
-     * @note This shares the exact same structure as HTMLPurifier_Config::$conf
-     */
-    var $defaults = array();
-    
-    /**
-     * Definition of the directives.
-     */
-    var $info = array();
-    
-    /**
-     * Definition of namespaces.
-     */
-    var $info_namespace = array();
-    
-    /**
-     * Lookup table of allowed types.
-     */
-    var $types = array(
-        'string'    => 'String',
-        'istring'   => 'Case-insensitive string',
-        'int'       => 'Integer',
-        'float'     => 'Float',
-        'bool'      => 'Boolean',
-        'lookup'    => 'Lookup array',
-        'list'      => 'Array list',
-        'hash'      => 'Associative array',
-        'mixed'     => 'Mixed'
-    );
-    
-    /**
-     * Initializes the default namespaces.
-     */
-    function initialize() {
-        $this->defineNamespace('Core', 'Core features that are always available.');
-        $this->defineNamespace('Attr', 'Features regarding attribute validation.');
-        $this->defineNamespace('URI', 'Features regarding Uniform Resource Identifiers.');
-        $this->defineNamespace('HTML', 'Configuration regarding allowed HTML.');
-        $this->defineNamespace('CSS', 'Configuration regarding allowed CSS.');
-        $this->defineNamespace('Test', 'Developer testing configuration for our unit tests.');
-    }
-    
-    /**
-     * Retrieves an instance of the application-wide configuration definition.
-     */
-    function &instance($prototype = null) {
-        static $instance;
-        if ($prototype !== null) {
-            $instance = $prototype;
-        } elseif ($instance === null || $prototype === true) {
-            $instance = new HTMLPurifier_ConfigSchema();
-            $instance->initialize();
-        }
-        return $instance;
-    }
-    
-    /**
-     * Defines a directive for configuration
-     * @warning Will fail of directive's namespace is defined
-     * @param $namespace Namespace the directive is in
-     * @param $name Key of directive
-     * @param $default Default value of directive
-     * @param $type Allowed type of the directive. See
-     *      HTMLPurifier_DirectiveDef::$type for allowed values
-     * @param $description Description of directive for documentation
-     */
-    function define(
-        $namespace, $name, $default, $type, 
-        $description
-    ) {
-        $def =& HTMLPurifier_ConfigSchema::instance();
-        if (!isset($def->info[$namespace])) {
-            trigger_error('Cannot define directive for undefined namespace',
-                E_USER_ERROR);
-            return;
-        }
-        if (!ctype_alnum($name)) {
-            trigger_error('Directive name must be alphanumeric',
-                E_USER_ERROR);
-            return;
-        }
-        if (isset($def->info[$namespace][$name])) {
-            if (
-                $def->info[$namespace][$name]->type !== $type ||
-                $def->defaults[$namespace][$name]   !== $default
-            ) {
-                trigger_error('Inconsistent default or type, cannot redefine');
-                return;
-            }
-        } else {
-            if (!isset($def->types[$type])) {
-                trigger_error('Invalid type for configuration directive',
-                    E_USER_ERROR);
-                return;
-            }
-            if ($def->validate($default, $type) === null) {
-                trigger_error('Default value does not match directive type',
-                    E_USER_ERROR);
-                return;
-            }
-            $def->info[$namespace][$name] =
-                new HTMLPurifier_ConfigEntity_Directive();
-            $def->info[$namespace][$name]->type = $type;
-            $def->defaults[$namespace][$name]   = $default;
-        }
-        $backtrace = debug_backtrace();
-        $file = $def->mungeFilename($backtrace[0]['file']);
-        $line = $backtrace[0]['line'];
-        $def->info[$namespace][$name]->addDescription($file,$line,$description);
-    }
-    
-    /**
-     * Defines a namespace for directives to be put into.
-     * @param $namespace Namespace's name
-     * @param $description Description of the namespace
-     */
-    function defineNamespace($namespace, $description) {
-        $def =& HTMLPurifier_ConfigSchema::instance();
-        if (isset($def->info[$namespace])) {
-            trigger_error('Cannot redefine namespace', E_USER_ERROR);
-            return;
-        }
-        if (!ctype_alnum($namespace)) {
-            trigger_error('Namespace name must be alphanumeric',
-                E_USER_ERROR);
-            return;
-        }
-        $def->info[$namespace] = array();
-        $def->info_namespace[$namespace] = new HTMLPurifier_ConfigEntity_Namespace();
-        $def->info_namespace[$namespace]->description = $description;
-        $def->defaults[$namespace] = array();
-    }
-    
-    /**
-     * Defines a directive value alias.
-     * 
-     * Directive value aliases are convenient for developers because it lets
-     * them set a directive to several values and get the same result.
-     * @param $namespace Directive's namespace
-     * @param $name Name of Directive
-     * @param $alias Name of aliased value
-     * @param $real Value aliased value will be converted into
-     */
-    function defineValueAliases($namespace, $name, $aliases) {
-        $def =& HTMLPurifier_ConfigSchema::instance();
-        if (!isset($def->info[$namespace][$name])) {
-            trigger_error('Cannot set value alias for non-existant directive',
-                E_USER_ERROR);
-            return;
-        }
-        foreach ($aliases as $alias => $real) {
-            if (!$def->info[$namespace][$name] !== true &&
-                !isset($def->info[$namespace][$name]->allowed[$real])
-            ) {
-                trigger_error('Cannot define alias to value that is not allowed',
-                    E_USER_ERROR);
-                return;
-            }
-            if (isset($def->info[$namespace][$name]->allowed[$alias])) {
-                trigger_error('Cannot define alias over allowed value',
-                    E_USER_ERROR);
-                return;
-            }
-            $def->info[$namespace][$name]->aliases[$alias] = $real;
-        }
-    }
-    
-    /**
-     * Defines a set of allowed values for a directive.
-     * @param $namespace Namespace of directive
-     * @param $name Name of directive
-     * @param $allowed_values Arraylist of allowed values
-     */
-    function defineAllowedValues($namespace, $name, $allowed_values) {
-        $def =& HTMLPurifier_ConfigSchema::instance();
-        if (!isset($def->info[$namespace][$name])) {
-            trigger_error('Cannot define allowed values for undefined directive',
-                E_USER_ERROR);
-            return;
-        }
-        if ($def->info[$namespace][$name]->allowed === true) {
-            $def->info[$namespace][$name]->allowed = array();
-        }
-        foreach ($allowed_values as $value) {
-            $def->info[$namespace][$name]->allowed[$value] = true;
-        }
-    }
-    
-    /**
-     * Validate a variable according to type. Return null if invalid.
-     */
-    function validate($var, $type) {
-        if (!isset($this->types[$type])) {
-            trigger_error('Invalid type', E_USER_ERROR);
-            return;
-        }
-        switch ($type) {
-            case 'mixed':
-                return $var;
-            case 'istring':
-            case 'string':
-                if (!is_string($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)) return;
-                return $var;
-            case 'float':
-                if (is_string($var) && is_numeric($var)) $var = (float) $var;
-                elseif (!is_float($var)) return;
-                return $var;
-            case 'bool':
-                if (is_int($var) && ($var === 0 || $var === 1)) {
-                    $var = (bool) $var;
-                } elseif (!is_bool($var)) return;
-                return $var;
-            case 'list':
-            case 'hash':
-            case 'lookup':
-                if (!is_array($var)) return;
-                $keys = array_keys($var);
-                if ($keys === array_keys($keys)) {
-                    if ($type == 'list') return $var;
-                    elseif ($type == 'lookup') {
-                        $new = array();
-                        foreach ($var as $key) {
-                            $new[$key] = true;
-                        }
-                        return $new;
-                    } else return;
-                }
-                if ($type === 'lookup') {
-                    foreach ($var as $key => $value) {
-                        $var[$key] = true;
-                    }
-                }
-                return $var;
-        }
-    }
-    
-    function mungeFilename($filename) {
-        $offset = strrpos($filename, 'HTMLPurifier');
-        $filename = substr($filename, $offset);
-        $filename = str_replace('\\', '/', $filename);
-        return $filename;
-    }
-    
-}
-
-/**
- * Base class for configuration entity
- */
-class HTMLPurifier_ConfigEntity {}
-
-/**
- * Structure object describing of a namespace
- */
-class HTMLPurifier_ConfigEntity_Namespace extends HTMLPurifier_ConfigEntity {
-    
-    /**
-     * String description of what kinds of directives go in this namespace.
-     */
-    var $description;
-    
-}
-
-/**
- * Structure object containing definition of a directive.
- * @note This structure does not contain default values
- */
-class HTMLPurifier_ConfigEntity_Directive extends HTMLPurifier_ConfigEntity
-{
-    
-    /**
-     * Hash of value aliases, i.e. values that are equivalent.
-     */
-    var $aliases = array();
-    
-    /**
-     * Lookup table of allowed values of the element, bool true if all allowed.
-     */
-    var $allowed = true;
-    
-    /**
-     * Allowed type of the directive. Values are:
-     *      - string
-     *      - istring (case insensitive string)
-     *      - int
-     *      - float
-     *      - bool
-     *      - lookup (array of value => true)
-     *      - list (regular numbered index array)
-     *      - hash (array of key => value)
-     *      - mixed (anything goes)
-     */
-    var $type = 'mixed';
-    /**
-     * Plaintext descriptions of the configuration entity is. Organized by
-     * file and line number, so multiple descriptions are allowed.
-     */
-    var $descriptions = array();
-    
-    /**
-     * Adds a description to the array
-     */
-    function addDescription($file, $line, $description) {
-        if (!isset($this->descriptions[$file])) $this->descriptions[$file] = array();
-        $this->descriptions[$file][$line] = $description;
-    }
-    
-}
-
-?>

library/HTMLPurifier/Encoder.php

@@ -1,301 +0,0 @@
-<?php
-
-require_once 'HTMLPurifier/EntityLookup.php';
-
-HTMLPurifier_ConfigSchema::define(
-    'Core', 'Encoding', 'utf-8', 'istring', 
-    'If for some reason you are unable to convert all webpages to UTF-8, '. 
-    'you can use this directive as a stop-gap compatibility change to '. 
-    'let HTMLPurifier deal with non UTF-8 input.  This technique has '. 
-    'notable deficiencies: absolutely no characters outside of the selected '. 
-    'character encoding will be preserved, not even the ones that have '. 
-    'been ampersand escaped (this is due to a UTF-8 specific <em>feature</em> '.
-    'that automatically resolves all entities), making it pretty useless '.
-    'for anything except the most I18N-blind applications.  This directive '.
-    'only accepts ISO-8859-1 if iconv is not enabled.'
-);
-
-if ( !function_exists('iconv') ) {
-    // only encodings with native PHP support
-    HTMLPurifier_ConfigSchema::defineAllowedValues(
-        'Core', 'Encoding', array(
-            'utf-8',
-            'iso-8859-1'
-        )
-    );
-    HTMLPurifier_ConfigSchema::defineValueAliases(
-        'Core', 'Encoding', array(
-            'iso8859-1' => 'iso-8859-1'
-        )
-    );
-}
-
-HTMLPurifier_ConfigSchema::define(
-    'Test', 'ForceNoIconv', false, 'bool', 
-    'When set to true, HTMLPurifier_Encoder will act as if iconv does not '.
-    'exist and use only pure PHP implementations.'
-);
-
-/**
- * A UTF-8 specific character encoder that handles cleaning and transforming.
- */
-class HTMLPurifier_Encoder
-{
-    
-    /**
-     * Cleans a UTF-8 string for well-formedness and SGML validity
-     * 
-     * It will parse according to UTF-8 and return a valid UTF8 string, with
-     * non-SGML codepoints excluded.
-     * 
-     * @note Just for reference, the non-SGML code points are 0 to 31 and
-     *       127 to 159, inclusive.  However, we allow code points 9, 10
-     *       and 13, which are the tab, line feed and carriage return
-     *       respectively. 128 and above the code points map to multibyte
-     *       UTF-8 representations.
-     * 
-     * @note Fallback code adapted from utf8ToUnicode by Henri Sivonen and
-     *       hsivonen@iki.fi at <http://iki.fi/hsivonen/php-utf8/> under the
-     *       LGPL license.  Notes on what changed are inside, but in general,
-     *       the original code transformed UTF-8 text into an array of integer
-     *       Unicode codepoints. Understandably, transforming that back to
-     *       a string would be somewhat expensive, so the function was modded to
-     *       directly operate on the string.  However, this discourages code
-     *       reuse, and the logic enumerated here would be useful for any
-     *       function that needs to be able to understand UTF-8 characters.
-     *       As of right now, only smart lossless character encoding converters
-     *       would need that, and I'm probably not going to implement them.
-     *       Once again, PHP 6 should solve all our problems.
-     */
-    function cleanUTF8($str, $force_php = false) {
-        
-        static $non_sgml_chars = array();
-        if (empty($non_sgml_chars)) {
-            for ($i = 0; $i <= 31; $i++) {
-                // non-SGML ASCII chars
-                // save \r, \t and \n
-                if ($i == 9 || $i == 13 || $i == 10) continue;
-                $non_sgml_chars[chr($i)] = '';
-            }
-            for ($i = 127; $i <= 159; $i++) {
-                $non_sgml_chars[HTMLPurifier_Encoder::unichr($i)] = '';
-            }
-        }
-        
-        static $iconv = null;
-        if ($iconv === null) $iconv = function_exists('iconv');
-        
-        if ($iconv && !$force_php) {
-            // do the shortcut way
-            $str = @iconv('UTF-8', 'UTF-8//IGNORE', $str);
-            return strtr($str, $non_sgml_chars);
-        }
-        
-        $mState = 0; // cached expected number of octets after the current octet
-                     // until the beginning of the next UTF8 character sequence
-        $mUcs4  = 0; // cached Unicode character
-        $mBytes = 1; // cached expected number of octets in the current sequence
-        
-        // original code involved an $out that was an array of Unicode
-        // codepoints.  Instead of having to convert back into UTF-8, we've
-        // decided to directly append valid UTF-8 characters onto a string
-        // $out once they're done.  $char accumulates raw bytes, while $mUcs4
-        // turns into the Unicode code point, so there's some redundancy.
-        
-        $out = '';
-        $char = '';
-        
-        $len = strlen($str);
-        for($i = 0; $i < $len; $i++) {
-            $in = ord($str{$i});
-            $char .= $str[$i]; // append byte to char
-            if (0 == $mState) {
-                // When mState is zero we expect either a US-ASCII character 
-                // or a multi-octet sequence.
-                if (0 == (0x80 & ($in))) {
-                    // US-ASCII, pass straight through.
-                    if (($in <= 31 || $in == 127) && 
-                        !($in == 9 || $in == 13 || $in == 10) // save \r\t\n
-                    ) {
-                        // control characters, remove
-                    } else {
-                        $out .= $char;
-                    }
-                    // reset
-                    $char = '';
-                    $mBytes = 1;
-                } elseif (0xC0 == (0xE0 & ($in))) {
-                    // First octet of 2 octet sequence
-                    $mUcs4 = ($in);
-                    $mUcs4 = ($mUcs4 & 0x1F) << 6;
-                    $mState = 1;
-                    $mBytes = 2;
-                } elseif (0xE0 == (0xF0 & ($in))) {
-                    // First octet of 3 octet sequence
-                    $mUcs4 = ($in);
-                    $mUcs4 = ($mUcs4 & 0x0F) << 12;
-                    $mState = 2;
-                    $mBytes = 3;
-                } elseif (0xF0 == (0xF8 & ($in))) {
-                    // First octet of 4 octet sequence
-                    $mUcs4 = ($in);
-                    $mUcs4 = ($mUcs4 & 0x07) << 18;
-                    $mState = 3;
-                    $mBytes = 4;
-                } elseif (0xF8 == (0xFC & ($in))) {
-                    // First octet of 5 octet sequence.
-                    // 
-                    // This is illegal because the encoded codepoint must be 
-                    // either:
-                    // (a) not the shortest form or
-                    // (b) outside the Unicode range of 0-0x10FFFF.
-                    // Rather than trying to resynchronize, we will carry on 
-                    // until the end of the sequence and let the later error
-                    // handling code catch it.
-                    $mUcs4 = ($in);
-                    $mUcs4 = ($mUcs4 & 0x03) << 24;
-                    $mState = 4;
-                    $mBytes = 5;
-                } elseif (0xFC == (0xFE & ($in))) {
-                    // First octet of 6 octet sequence, see comments for 5
-                    // octet sequence.
-                    $mUcs4 = ($in);
-                    $mUcs4 = ($mUcs4 & 1) << 30;
-                    $mState = 5;
-                    $mBytes = 6;
-                } else {
-                    // Current octet is neither in the US-ASCII range nor a 
-                    // legal first octet of a multi-octet sequence.
-                    $mState = 0;
-                    $mUcs4  = 0;
-                    $mBytes = 1;
-                    $char = '';
-                }
-            } else {
-                // When mState is non-zero, we expect a continuation of the
-                // multi-octet sequence
-                if (0x80 == (0xC0 & ($in))) {
-                    // Legal continuation.
-                    $shift = ($mState - 1) * 6;
-                    $tmp = $in;
-                    $tmp = ($tmp & 0x0000003F) << $shift;
-                    $mUcs4 |= $tmp;
-                    
-                    if (0 == --$mState) {
-                        // End of the multi-octet sequence. mUcs4 now contains
-                        // the final Unicode codepoint to be output
-                        
-                        // Check for illegal sequences and codepoints.
-                        
-                        // From Unicode 3.1, non-shortest form is illegal
-                        if (((2 == $mBytes) && ($mUcs4 < 0x0080)) ||
-                            ((3 == $mBytes) && ($mUcs4 < 0x0800)) ||
-                            ((4 == $mBytes) && ($mUcs4 < 0x10000)) ||
-                            (4 < $mBytes) ||
-                            // From Unicode 3.2, surrogate characters = illegal
-                            (($mUcs4 & 0xFFFFF800) == 0xD800) ||
-                            // Codepoints outside the Unicode range are illegal
-                            ($mUcs4 > 0x10FFFF)
-                        ) {
-                            
-                        } elseif (0xFEFF != $mUcs4 && // omit BOM
-                            !($mUcs4 >= 128 && $mUcs4 <= 159) // omit non-SGML
-                        ) {
-                            $out .= $char;
-                        }
-                        // initialize UTF8 cache (reset)
-                        $mState = 0;
-                        $mUcs4  = 0;
-                        $mBytes = 1;
-                        $char = '';
-                    }
-                } else {
-                    // ((0xC0 & (*in) != 0x80) && (mState != 0))
-                    // Incomplete multi-octet sequence.
-                    // used to result in complete fail, but we'll reset
-                    $mState = 0;
-                    $mUcs4  = 0;
-                    $mBytes = 1;
-                    $char ='';
-                }
-            }
-        }
-        return $out;
-    }
-    
-    /**
-     * Translates a Unicode codepoint into its corresponding UTF-8 character.
-     */
-    function unichr($code) {
-        if($code > 1114111 or $code < 0 or
-          ($code >= 55296 and $code <= 57343) ) {
-            // bits are set outside the "valid" range as defined
-            // by UNICODE 4.1.0 
-            return '';
-        }
-        
-        $x = $y = $z = $w = 0; 
-        if ($code < 128) {
-            // regular ASCII character
-            $x = $code;
-        } else {
-            // set up bits for UTF-8
-            $x = ($code & 63) | 128;
-            if ($code < 2048) {
-                $y = (($code & 2047) >> 6) | 192;
-            } else {
-                $y = (($code & 4032) >> 6) | 128;
-                if($code < 65536) {
-                    $z = (($code >> 12) & 15) | 224;
-                } else {
-                    $z = (($code >> 12) & 63) | 128;
-                    $w = (($code >> 18) & 7)  | 240;
-                }
-            } 
-        }
-        // set up the actual character
-        $ret = '';
-        if($w) $ret .= chr($w);
-        if($z) $ret .= chr($z);
-        if($y) $ret .= chr($y);
-        $ret .= chr($x); 
-        
-        return $ret;
-    }
-    
-    /**
-     * Converts a string to UTF-8 based on configuration.
-     */
-    function convertToUTF8($str, $config) {
-        static $iconv = null;
-        if ($iconv === null) $iconv = function_exists('iconv');
-        $encoding = $config->get('Core', 'Encoding');
-        if ($encoding === 'utf-8') return $str;
-        if ($iconv && !$config->get('Test', 'ForceNoIconv')) {
-            return @iconv($encoding, 'utf-8//IGNORE', $str);
-        } elseif ($encoding === 'iso-8859-1') {
-            return @utf8_encode($str);
-        }
-    }
-    
-    /**
-     * Converts a string from UTF-8 based on configuration.
-     * @note Currently, this is a lossy conversion, with unexpressable
-     *       characters being omitted.
-     */
-    function convertFromUTF8($str, $config) {
-        static $iconv = null;
-        if ($iconv === null) $iconv = function_exists('iconv');
-        $encoding = $config->get('Core', 'Encoding');
-        if ($encoding === 'utf-8') return $str;
-        if ($iconv && !$config->get('Test', 'ForceNoIconv')) {
-            return @iconv('utf-8', $encoding . '//IGNORE', $str);
-        } elseif ($encoding === 'iso-8859-1') {
-            return @utf8_decode($str);
-        }
-    }
-    
-    
-}
-
-?>

library/HTMLPurifier/EntityLookup.php

@@ -1,22 +1,12 @@
 <?php
 
-/**
- * Object that provides entity lookup table from entity name to character
- */
 class HTMLPurifier_EntityLookup {
     
-    /**
-     * Assoc array of entity name to character represented.
-     * @public
-     */
     var $table;
     
-    /**
-     * Sets up the entity lookup table from the serialized file contents.
-     * @note The serialized contents are versioned, but were generated
-     *       using the maintenance script generate_entity_file.php
-     * @warning This is not in constructor to help enforce the Singleton
-     */
+    function HTMLPurifier_EntityLookup() {}
+    
+    // to enforce Singleton-ness
     function setup($file = false) {
         if (!$file) {
             $file = dirname(__FILE__) . '/EntityLookup/data.txt';
@@ -24,10 +14,6 @@ class HTMLPurifier_EntityLookup {
         $this->table = unserialize(file_get_contents($file));
     }
     
-    /**
-     * Retrieves sole instance of the object.
-     * @param Optional prototype of custom lookup table to overload with.
-     */
     function instance($prototype = false) {
         // no references, since PHP doesn't copy unless modified
         static $instance = null;

library/HTMLPurifier/EntityParser.php

@@ -1,179 +0,0 @@
-<?php
-
-require_once 'HTMLPurifier/EntityLookup.php';
-require_once 'HTMLPurifier/Encoder.php';
-
-/**
- * Handles referencing and derefencing character entities
- */
-class HTMLPurifier_EntityParser
-{
-    
-    /**
-     * Reference to entity lookup table.
-     * @protected
-     */
-    var $_entity_lookup;
-    
-    /**
-     * Callback regex string for parsing entities.
-     * @protected
-     */                             
-    var $_substituteEntitiesRegex =
-'/&(?:[#]x([a-fA-F0-9]+)|[#]0*(\d+)|([A-Za-z]+));?/';
-//     1. hex             2. dec      3. string
-    
-    
-    /**
-     * Decimal to parsed string conversion table for special entities.
-     * @protected
-     */
-    var $_special_dec2str =
-            array(
-                    34 => '"',
-                    38 => '&',
-                    39 => "'",
-                    60 => '<',
-                    62 => '>'
-            );
-    
-    /**
-     * Stripped entity names to decimal conversion table for special entities.
-     * @protected
-     */
-    var $_special_ent2dec =
-            array(
-                    'quot' => 34,
-                    'amp'  => 38,
-                    'lt'   => 60,
-                    'gt'   => 62
-            );
-    
-    /**
-     * Substitutes non-special entities with their parsed equivalents. Since
-     * running this whenever you have parsed character is t3h 5uck, we run
-     * it before everything else.
-     * 
-     * @protected
-     * @param $string String to have non-special entities parsed.
-     * @returns Parsed string.
-     */
-    function substituteNonSpecialEntities($string) {
-        // it will try to detect missing semicolons, but don't rely on it
-        return preg_replace_callback(
-            $this->_substituteEntitiesRegex,
-            array($this, 'nonSpecialEntityCallback'),
-            $string
-            );
-    }
-    
-    /**
-     * Callback function for substituteNonSpecialEntities() that does the work.
-     * 
-     * @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];
-        $is_num = (@$matches[0][1] === '#');
-        if ($is_num) {
-            $is_hex = (@$entity[2] === 'x');
-            $code = $is_hex ? hexdec($matches[1]) : (int) $matches[2];
-            
-            // abort for special characters
-            if (isset($this->_special_dec2str[$code]))  return $entity;
-            
-            return HTMLPurifier_Encoder::unichr($code);
-        } else {
-            if (isset($this->_special_ent2dec[$matches[3]])) return $entity;
-            if (!$this->_entity_lookup) {
-                require_once 'HTMLPurifier/EntityLookup.php';
-                $this->_entity_lookup = HTMLPurifier_EntityLookup::instance();
-            }
-            if (isset($this->_entity_lookup->table[$matches[3]])) {
-                return $this->_entity_lookup->table[$matches[3]];
-            } else {
-                return $entity;
-            }
-        }
-    }
-    
-    /**
-     * Substitutes only special entities with their parsed equivalents.
-     * 
-     * @notice We try to avoid calling this function because otherwise, it
-     * would have to be called a lot (for every parsed section).
-     * 
-     * @protected
-     * @param $string String to have non-special entities parsed.
-     * @returns Parsed string.
-     */
-    function substituteSpecialEntities($string) {
-        return preg_replace_callback(
-            $this->_substituteEntitiesRegex,
-            array($this, 'specialEntityCallback'),
-            $string);
-    }
-    
-    /**
-     * Callback function for substituteSpecialEntities() that does the work.
-     * 
-     * This callback has same syntax as nonSpecialEntityCallback().
-     * 
-     * @warning Though this is public in order to let the callback happen,
-     *          calling it directly is not recommended.
-     * @param $matches  PCRE-style matches array, with 0 the entire match, and
-     *                  either index 1, 2 or 3 set with a hex value, dec value,
-     *                  or string (respectively).
-     * @returns Replacement string.
-     */
-    function specialEntityCallback($matches) {
-        $entity = $matches[0];
-        $is_num = (@$matches[0][1] === '#');
-        if ($is_num) {
-            $is_hex = (@$entity[2] === 'x');
-            $int = $is_hex ? hexdec($matches[1]) : (int) $matches[2];
-            return isset($this->_special_dec2str[$int]) ?
-                $this->_special_dec2str[$int] :
-                $entity;
-        } else {
-            return isset($this->_special_ent2dec[$matches[3]]) ?
-                $this->_special_ent2dec[$matches[3]] :
-                $entity;
-        }
-    }
-    
-}
-
-?>

library/HTMLPurifier/Generator.php

@@ -2,124 +2,35 @@
 
 // pretty-printing with indentation would be pretty cool
 
-require_once 'HTMLPurifier/Lexer.php';
-
-HTMLPurifier_ConfigSchema::define(
-    'Core', 'CleanUTF8DuringGeneration', false, 'bool',
-    'When true, HTMLPurifier_Generator will also check all strings it '.
-    'escapes for UTF-8 well-formedness as a defense in depth measure. '.
-    'This could cause a considerable performance impact, and is not '.
-    'strictly necessary due to the fact that the Lexers should have '.
-    'ensured that all the UTF-8 strings were well-formed.  Note that '.
-    'the configuration value is only read at the beginning of '.
-    'generateFromTokens.'
-);
-
-HTMLPurifier_ConfigSchema::define(
-    'Core', 'XHTML', true, 'bool',
-    'Determines whether or not output is XHTML or not.  When disabled, HTML '.
-    'Purifier goes into HTML 4.01 removes XHTML-specific markup constructs, '.
-    'such as boolean attribute expansion and trailing slashes in empty tags. '.
-    'This directive was available since 1.1.'
-);
-
-// extension constraints could be factored into ConfigSchema
-HTMLPurifier_ConfigSchema::define(
-    'Core', 'TidyFormat', false, 'bool',
-    '<p>Determines whether or not to run Tidy on the final output for pretty '.
-    'formatting reasons, such as indentation and wrap.</p><p>This can greatly '.
-    'improve readability for editors who are hand-editing the HTML, but is '.
-    'by no means necessary as HTML Purifier has already fixed all major '.
-    'errors the HTML may have had. Tidy is a non-default extension, and this directive '.
-    'will silently fail if Tidy is not available.</p><p>If you are looking to make '.
-    'the overall look of your page\'s source better, I recommend running Tidy '.
-    'on the entire page rather than just user-content (after all, the '.
-    'indentation relative to the containing blocks will be incorrect).</p><p>This '.
-    'directive was available since 1.1.1.</p>'
-);
-
-/**
- * Generates HTML from tokens.
- */
 class HTMLPurifier_Generator
 {
     
-    /**
-     * Bool cache of %Core.CleanUTF8DuringGeneration
-     * @private
-     */
-    var $_clean_utf8 = false;
-    
-    /**
-     * Bool cache of %Core.XHTML
-     */
-    var $_xhtml = true;
-    
-    /**
-     * Generates HTML from an array of tokens.
-     * @param $tokens Array of HTMLPurifier_Token
-     * @param $config HTMLPurifier_Config object
-     * @return Generated HTML
-     * @note Only unit tests may omit configuration: internals MUST pass config
-     */
+    // only unit tests may omit configuration: internals MUST pass config
     function generateFromTokens($tokens, $config = null) {
         $html = '';
         if (!$config) $config = HTMLPurifier_Config::createDefault();
-        $this->_clean_utf8 = $config->get('Core', 'CleanUTF8DuringGeneration');
-        $this->_xhtml = $config->get('Core', 'XHTML');
         if (!$tokens) return '';
         foreach ($tokens as $token) {
-            $html .= $this->generateFromToken($token);
-        }
-        if ($config->get('Core', 'TidyFormat') && extension_loaded('tidy')) {
-            
-            $tidy_options = array(
-               'indent'=> true,
-               'output-xhtml' => $this->_xhtml,
-               'show-body-only' => true,
-               'indent-spaces' => 2,
-               'wrap' => 68,
-            );
-            if (version_compare(PHP_VERSION, '5', '<')) {
-                tidy_set_encoding('utf8');
-                foreach ($tidy_options as $key => $value) {
-                    tidy_setopt($key, $value);
-                }
-                tidy_parse_string($html);
-                tidy_clean_repair();
-                $html = tidy_get_output();
-            } else {
-                $tidy = new Tidy;
-                $tidy->parseString($html, $tidy_options, 'utf8');
-                $tidy->cleanRepair();
-                $html = (string) $tidy;
-            }
+            $html .= $this->generateFromToken($token, $config);
         }
         return $html;
     }
     
-    /**
-     * Generates HTML from a single token.
-     * @param $token HTMLPurifier_Token object.
-     * @return Generated HTML
-     */
-    function generateFromToken($token) {
+    function generateFromToken($token, $config) {
         if (!isset($token->type)) return '';
         if ($token->type == 'start') {
-            $attr = $this->generateAttributes($token->attributes);
+            $attr = $this->generateAttributes($token->attributes, $config);
             return '<' . $token->name . ($attr ? ' ' : '') . $attr . '>';
             
         } elseif ($token->type == 'end') {
             return '</' . $token->name . '>';
             
         } elseif ($token->type == 'empty') {
-            $attr = $this->generateAttributes($token->attributes);
-             return '<' . $token->name . ($attr ? ' ' : '') . $attr .
-                ( $this->_xhtml ? ' /': '' )
-                . '>';
+            $attr = $this->generateAttributes($token->attributes, $config);
+             return '<' . $token->name . ($attr ? ' ' : '') . $attr . ' />';
             
         } elseif ($token->type == 'text') {
-            return $this->escape($token->data);
+            return htmlspecialchars($token->data, ENT_COMPAT, 'UTF-8');
             
         } else {
             return '';
@@ -127,34 +38,14 @@ class HTMLPurifier_Generator
         }
     }
     
-    /**
-     * Generates attribute declarations from attribute array.
-     * @param $assoc_array_of_attributes Attribute array
-     * @return Generate HTML fragment for insertion.
-     */
-    function generateAttributes($assoc_array_of_attributes) {
+    function generateAttributes($assoc_array_of_attributes, $config) {
         $html = '';
         foreach ($assoc_array_of_attributes as $key => $value) {
-            if (!$this->_xhtml) {
-                // remove namespaced attributes
-                if (strpos($key, ':') !== false) continue;
-                // also needed: check for attribute minimization
-            }
-            $html .= $key.'="'.$this->escape($value).'" ';
+            $html .= $key.'="'.htmlspecialchars($value, ENT_COMPAT, 'UTF-8').'" ';
         }
         return rtrim($html);
     }
     
-    /**
-     * Escapes raw text data.
-     * @param $string String data to escape for HTML.
-     * @return String escaped data.
-     */
-    function escape($string) {
-        if ($this->_clean_utf8) $string = HTMLPurifier_Lexer::cleanUTF8($string);
-        return htmlspecialchars($string, ENT_COMPAT, 'UTF-8');
-    }
-    
 }
 
 ?>

library/HTMLPurifier/HTMLDefinition.php

@@ -9,7 +9,7 @@ require_once 'HTMLPurifier/AttrDef.php';
     require_once 'HTMLPurifier/AttrDef/Pixels.php';
     require_once 'HTMLPurifier/AttrDef/Length.php';
     require_once 'HTMLPurifier/AttrDef/MultiLength.php';
-    require_once 'HTMLPurifier/AttrDef/Integer.php';
+    require_once 'HTMLPurifier/AttrDef/NumberSpan.php';
     require_once 'HTMLPurifier/AttrDef/URI.php';
     require_once 'HTMLPurifier/AttrDef/CSS.php';
 require_once 'HTMLPurifier/AttrTransform.php';
@@ -30,8 +30,12 @@ require_once 'HTMLPurifier/TagTransform.php';
  * each allowed element. It also contains special use information (always
  * prefixed by info) for intelligent tag closing and global attributes.
  * 
- * For optimization, the definition generation may be moved to
- * a maintenance script and stipulate that definition be created
+ * Planned improvements include attribute transformation objects as well as
+ * migration of auto-tag-closing from HTMLPurifier_Strategy_MakeWellFormed
+ * (these can likely just be extensions of ElementDef).
+ * 
+ * After development drops off, the definition generation will be moved to
+ * a maintenance script and we will stipulate that definition be created
  * by a factory method that unserializes a serialized version of Definition.
  * Customization would entail copying the maintenance script, making the
  * necessary changes, generating the serialized object, and then hooking it
@@ -42,47 +46,40 @@ require_once 'HTMLPurifier/TagTransform.php';
 class HTMLPurifier_HTMLDefinition
 {
     
-    /**
-     * Associative array of element names to HTMLPurifier_ElementDef
-     * @public
-     */
     var $info = array();
     
-    /**
-     * Associative array of global attribute name to attribute definition.
-     * @public
-     */
+    // used solely by HTMLPurifier_Strategy_ValidateAttributes
     var $info_global_attr = array();
     
-    /**
-     * String name of parent element HTML will be going into.
-     * @todo Allow this to be overloaded by user config
-     * @public
-     */
+    // used solely by HTMLPurifier_Strategy_FixNesting
     var $info_parent = 'div';
     
-    /**
-     * Associative array of deprecated tag name to HTMLPurifier_TagTransform
-     * @public
-     */
+    // used solely by HTMLPurifier_Strategy_RemoveForeignElements
     var $info_tag_transform = array();
     
-    /**
-     * List of HTMLPurifier_AttrTransform to be performed before validation.
-     * @public
-     */
+    // used solely by HTMLPurifier_Strategy_ValidateAttributes
     var $info_attr_transform_pre = array();
-    
-    /**
-     * List of HTMLPurifier_AttrTransform to be performed after validation/
-     * @public
-     */
     var $info_attr_transform_post = array();
     
-    /**
-     * Initializes the definition, the meat of the class.
-     */
-    function setup($config) {
+    // WARNING! Prototype is not passed by reference, so in order to get
+    // a copy of the real one, you'll have to destroy your copy and
+    // use instance() to get it.
+    // Usually, however, modifying the returned definition (reference) should be
+    // sufficient
+    function &instance($prototype = null) {
+        static $instance = null;
+        if ($prototype) {
+            $instance = $prototype;
+        } elseif (!$instance) {
+            $instance = new HTMLPurifier_HTMLDefinition();
+            $instance->setup();
+        }
+        return $instance;
+    }
+    
+    function HTMLPurifier_HTMLDefinition() {}
+    
+    function setup() {
         
         // emulates the structure of the DTD
         // these are condensed, however, with bad stuff taken out
@@ -112,19 +109,12 @@ class HTMLPurifier_HTMLDefinition
         //////////////////////////////////////////////////////////////////////
         // info[]->child : defines allowed children for elements
         
-        // entities: prefixed with e_ and _ replaces . from DTD
-        // double underlines are entities we made up
+        // entities: prefixed with e_ and _ replaces .
         
         // we don't use an array because that complicates interpolation
         // strings are used instead of arrays because if you use arrays,
         // you have to do some hideous manipulation with array_merge()
         
-        // todo: determine whether or not having allowed children
-        //       that aren't allowed globally affects security (it shouldn't)
-        // if above works out, extend children definitions to include all
-        //       possible elements (allowed elements will dictate which ones
-        //       get dropped
-        
         $e_special_extra = 'img';
         $e_special_basic = 'br | span | bdo';
         $e_special = "$e_special_basic | $e_special_extra";
@@ -140,7 +130,6 @@ class HTMLPurifier_HTMLDefinition
         $e_misc = "$e_misc_inline";
         $e_inline = "a | $e_special | $e_fontstyle | $e_phrase".
           " | $e_inline_forms";
-        // pseudo-property we created for convenience, see later on
         $e__inline = "#PCDATA | $e_inline | $e_misc_inline";
         // note the casing
         $e_Inline = new HTMLPurifier_ChildDef_Optional($e__inline);
@@ -150,18 +139,16 @@ class HTMLPurifier_HTMLDefinition
         $e_block = "p | $e_heading | div | $e_lists | $e_blocktext | table";
         $e__flow = "#PCDATA | $e_block | $e_inline | $e_misc";
         $e_Flow = new HTMLPurifier_ChildDef_Optional($e__flow);
-        $e_a_content = new HTMLPurifier_ChildDef_Optional("#PCDATA".
-          " | $e_special | $e_fontstyle | $e_phrase | $e_inline_forms".
-          " | $e_misc_inline");
+        $e_a_content = new HTMLPurifier_ChildDef_Optional("#PCDATA | $e_special".
+          " | $e_fontstyle | $e_phrase | $e_inline_forms | $e_misc_inline");
         $e_pre_content = new HTMLPurifier_ChildDef_Optional("#PCDATA | a".
           " | $e_special_basic | $e_fontstyle_basic | $e_phrase_basic".
           " | $e_inline_forms | $e_misc_inline");
-        $e_form_content = new HTMLPurifier_ChildDef_Optional('');//unused
-        $e_form_button_content = new HTMLPurifier_ChildDef_Optional('');//unused
+        $e_form_content = new HTMLPurifier_ChildDef_Optional(''); //unused
+        $e_form_button_content = new HTMLPurifier_ChildDef_Optional(''); // unused
         
         $this->info['ins']->child =
-        $this->info['del']->child =
-            new HTMLPurifier_ChildDef_Chameleon($e__inline, $e__flow);
+        $this->info['del']->child = new HTMLPurifier_ChildDef_Chameleon($e__inline, $e__flow);
         
         $this->info['blockquote']->child=
         $this->info['dd']->child  =
@@ -219,7 +206,8 @@ class HTMLPurifier_HTMLDefinition
         
         $this->info['a']->child    = $e_a_content;
         
-        $this->info['table']->child = new HTMLPurifier_ChildDef_Table();
+        $this->info['table']->child = new HTMLPurifier_ChildDef_Custom(
+            '(caption?, (col*|colgroup*), thead?, tfoot?, (tbody+|tr+))');
         
         // not a real entity, watch the double underscore
         $e__row = new HTMLPurifier_ChildDef_Required('tr');
@@ -235,7 +223,7 @@ class HTMLPurifier_HTMLDefinition
         //////////////////////////////////////////////////////////////////////
         // info[]->type : defines the type of the element (block or inline)
         
-        // reuses $e_Inline and $e_Block
+        // reuses $e_Inline and $e_block
         
         foreach ($e_Inline->elements as $name) {
             $this->info[$name]->type = 'inline';
@@ -253,7 +241,7 @@ class HTMLPurifier_HTMLDefinition
         
         $this->info['a']->excludes = array('a' => true);
         $this->info['pre']->excludes = array_flip(array('img', 'big', 'small',
-            // technically useless, but good to be indepth
+            // technically in spec, but we don't allow em anyway
             'object', 'applet', 'font', 'basefont'));
         
         //////////////////////////////////////////////////////////////////////
@@ -263,8 +251,6 @@ class HTMLPurifier_HTMLDefinition
         // by the transform classes. It will, however, do simple and slightly
         // complex attribute value substitution
         
-        // the question of varying allowed attributes is more entangling.
-        
         $e_Text = new HTMLPurifier_AttrDef_Text();
         
         // attrs, included in almost every single one except for a few,
@@ -309,8 +295,7 @@ class HTMLPurifier_HTMLDefinition
         
         $this->info['table']->attr['summary'] = $e_Text;
         
-        $this->info['table']->attr['border'] =
-            new HTMLPurifier_AttrDef_Pixels();
+        $this->info['table']->attr['border'] = new HTMLPurifier_AttrDef_Pixels();
         
         $e_Length = new HTMLPurifier_AttrDef_Length();
         $this->info['table']->attr['cellpadding'] =
@@ -324,7 +309,7 @@ class HTMLPurifier_HTMLDefinition
         $this->info['col']->attr['width'] =
         $this->info['colgroup']->attr['width'] = $e_MultiLength;
         
-        $e__NumberSpan = new HTMLPurifier_AttrDef_Integer(false, false, true);
+        $e__NumberSpan = new HTMLPurifier_AttrDef_NumberSpan();
         $this->info['colgroup']->attr['span'] =
         $this->info['col']->attr['span']   =
         $this->info['td']->attr['rowspan'] =
@@ -342,7 +327,7 @@ class HTMLPurifier_HTMLDefinition
         $this->info['q']->attr['cite'] = $e_URI;
         
         //////////////////////////////////////////////////////////////////////
-        // info_tag_transform : transformations of tags
+        // UNIMP : info_tag_transform : transformations of tags
         
         $this->info_tag_transform['font']   = new HTMLPurifier_TagTransform_Font();
         $this->info_tag_transform['menu']   = new HTMLPurifier_TagTransform_Simple('ul');
@@ -352,9 +337,6 @@ class HTMLPurifier_HTMLDefinition
         //////////////////////////////////////////////////////////////////////
         // info[]->auto_close : tags that automatically close another
         
-        // todo: determine whether or not SGML-like modeling based on
-        // mandatory/optional end tags would be a better policy
-        
         // make sure you test using isset() not !empty()
         
         // these are all block elements: blocks aren't allowed in P
@@ -412,52 +394,15 @@ class HTMLPurifier_HTMLDefinition
     
 }
 
-/**
- * Structure that stores an element definition.
- */
 class HTMLPurifier_ElementDef
 {
     
-    /**
-     * Associative array of attribute name to HTMLPurifier_AttrDef
-     * @public
-     */
     var $attr = array();
-    
-    /**
-     * List of tag's HTMLPurifier_AttrTransform to be done before validation
-     * @public
-     */
     var $attr_transform_pre = array();
-    
-    /**
-     * List of tag's HTMLPurifier_AttrTransform to be done after validation
-     * @public
-     */
     var $attr_transform_post = array();
-    
-    /**
-     * Lookup table of tags that close this tag.
-     * @public
-     */
     var $auto_close = array();
-    
-    /**
-     * HTMLPurifier_ChildDef of this tag.
-     * @public
-     */
     var $child;
-    
-    /**
-     * Type of the tag: inline or block or unknown?
-     * @public
-     */
     var $type = 'unknown';
-    
-    /**
-     * Lookup table of tags excluded from all descendants of this tag.
-     * @public
-     */
     var $excludes = array();
     
 }

library/HTMLPurifier/IDAccumulator.php

@@ -1,33 +1,15 @@
 <?php
 
-/**
- * Component of HTMLPurifier_AttrContext that accumulates IDs to prevent dupes
- * @note In Slashdot-speak, dupe means duplicate.
- */
 class HTMLPurifier_IDAccumulator
 {
     
-    /**
-     * Lookup table of IDs we've accumulated.
-     * @public
-     */
     var $ids = array();
     
-    /**
-     * Add an ID to the lookup table.
-     * @param $id ID to be added.
-     * @return Bool status, true if success, false if there's a dupe
-     */
     function add($id) {
         if (isset($this->ids[$id])) return false;
         return $this->ids[$id] = true;
     }
     
-    /**
-     * Load a list of IDs into the lookup table
-     * @param $array_of_ids Array of IDs to load
-     * @note This function doesn't care about duplicates
-     */
     function load($array_of_ids) {
         foreach ($array_of_ids as $id) {
             $this->ids[$id] = true;

library/HTMLPurifier/Lexer.php

@@ -1,14 +1,13 @@
 <?php
 
 require_once 'HTMLPurifier/Token.php';
-require_once 'HTMLPurifier/Encoder.php';
-require_once 'HTMLPurifier/EntityParser.php';
 
-HTMLPurifier_ConfigSchema::define(
-    'Core', 'AcceptFullDocuments', true, 'bool',
+HTMLPurifier_ConfigDef::define(
+    'Core', 'AcceptFullDocuments', true,
     'This parameter determines whether or not the filter should accept full '.
     'HTML documents, not just HTML fragments.  When on, it will '.
-    'drop all sections except the content between body.'
+    'drop all sections except the content between body.  Depending on '.
+    'the implementation in use, this may speed up document parse times.'
 );
 
 /**
@@ -55,67 +54,6 @@ HTMLPurifier_ConfigSchema::define(
 class HTMLPurifier_Lexer
 {
     
-    function HTMLPurifier_Lexer() {
-        $this->_encoder = new HTMLPurifier_Encoder();
-        $this->_entity_parser = new HTMLPurifier_EntityParser();
-    }
-    
-    
-    /**
-     * Most common entity to raw value conversion table for special entities.
-     * @protected
-     */
-    var $_special_entity2str =
-            array(
-                    '&quot;' => '"',
-                    '&amp;'  => '&',
-                    '&lt;'   => '<',
-                    '&gt;'   => '>',
-                    '&#39;'  => "'",
-                    '&#039;' => "'",
-                    '&#x27;' => "'"
-            );
-    
-    /**
-     * Parses special entities into the proper characters.
-     * 
-     * This string will translate escaped versions of the special characters
-     * into the correct ones.
-     * 
-     * @warning
-     * You should be able to treat the output of this function as
-     * completely parsed, but that's only because all other entities should
-     * have been handled previously in substituteNonSpecialEntities()
-     * 
-     * @param $string String character data to be parsed.
-     * @returns Parsed character data.
-     */
-    function parseData($string) {
-        
-        // following functions require at least one character
-        if ($string === '') return '';
-        
-        // subtracts amps that cannot possibly be escaped
-        $num_amp = substr_count($string, '&') - substr_count($string, '& ') -
-            ($string[strlen($string)-1] === '&' ? 1 : 0);
-        
-        if (!$num_amp) return $string; // abort if no entities
-        $num_esc_amp = substr_count($string, '&amp;');
-        $string = strtr($string, $this->_special_entity2str);
-        
-        // code duplication for sake of optimization, see above
-        $num_amp_2 = substr_count($string, '&') - substr_count($string, '& ') -
-            ($string[strlen($string)-1] === '&' ? 1 : 0);
-        
-        if ($num_amp_2 <= $num_esc_amp) return $string;
-        
-        // hmm... now we have some uncommon entities. Use the callback.
-        $string = $this->_entity_parser->substituteSpecialEntities($string);
-        return $string;
-    }
-    
-    var $_encoder;
-    
     /**
      * Lexes an HTML string into tokens.
      * 
@@ -163,6 +101,112 @@ class HTMLPurifier_Lexer
         return $lexer;
     }
     
+    /**
+     * Decimal to parsed string conversion table for special entities.
+     * @protected
+     */
+    var $_special_dec2str =
+            array(
+                    34 => '"',
+                    38 => '&',
+                    39 => "'",
+                    60 => '<',
+                    62 => '>'
+            );
+    
+    /**
+     * Stripped entity names to decimal conversion table for special entities.
+     * @protected
+     */
+    var $_special_ent2dec =
+            array(
+                    'quot' => 34,
+                    'amp'  => 38,
+                    'lt'   => 60,
+                    'gt'   => 62
+            );
+    
+    /**
+     * Most common entity to raw value conversion table for special entities.
+     * @protected
+     */
+    var $_special_entity2str =
+            array(
+                    '&quot;' => '"',
+                    '&amp;'  => '&',
+                    '&lt;'   => '<',
+                    '&gt;'   => '>',
+                    '&#39;'  => "'",
+                    '&#039;' => "'",
+                    '&#x27;' => "'"
+            );
+    
+    /**
+     * Callback regex string for parsing entities.
+     * @protected
+     */                             
+    var $_substituteEntitiesRegex =
+'/&(?:[#]x([a-fA-F0-9]+)|[#]0*(\d+)|([A-Za-z]+));?/';
+//     1. hex             2. dec      3. string
+    
+    /**
+     * Substitutes non-special entities with their parsed equivalents. Since
+     * running this whenever you have parsed character is t3h 5uck, we run
+     * it before everything else.
+     * 
+     * @protected
+     * @param $string String to have non-special entities parsed.
+     * @returns Parsed string.
+     */
+    function substituteNonSpecialEntities($string) {
+        // it will try to detect missing semicolons, but don't rely on it
+        return preg_replace_callback(
+            $this->_substituteEntitiesRegex,
+            array($this, 'nonSpecialEntityCallback'),
+            $string
+            );
+    }
+    
+    /**
+     * Callback function for substituteNonSpecialEntities() that does the work.
+     * 
+     * @warning Though this is public in order to let the callback happen,
+     *          calling it directly is not recommended.
+     * @param $matches  PCRE matches array, with 0 the entire match, and
+     *                  either index 1, 2 or 3 set with a hex value, dec value,
+     *                  or string (respectively).
+     * @returns Replacement string.
+     * @todo Implement string translations
+     */
+    function nonSpecialEntityCallback($matches) {
+        // replaces all but big five
+        $entity = $matches[0];
+        $is_num = (@$matches[0][1] === '#');
+        if ($is_num) {
+            $is_hex = (@$entity[2] === 'x');
+            $int = $is_hex ? hexdec($matches[1]) : (int) $matches[2];
+            if (isset($this->_special_dec2str[$int]))  return $entity;
+            return chr($int);
+        } else {
+            if (isset($this->_special_ent2dec[$matches[3]])) return $entity;
+            if (!$this->_entity_lookup) {
+                require_once 'HTMLPurifier/EntityLookup.php';
+                $this->_entity_lookup = HTMLPurifier_EntityLookup::instance();
+            }
+            if (isset($this->_entity_lookup->table[$matches[3]])) {
+                return $this->_entity_lookup->table[$matches[3]];
+            } else {
+                return $entity;
+            }
+        }
+    }
+    
+    /**
+     * Contains a copy of the EntityLookup table.
+     * @protected
+     */
+    var $_entity_lookup;
+    
     /**
      * Translates CDATA sections into regular sections (through escaping).
      * 
@@ -192,37 +236,13 @@ class HTMLPurifier_Lexer
         return htmlspecialchars($matches[1], ENT_COMPAT, 'UTF-8');
     }
     
-    /**
-     * Takes a piece of HTML and normalizes it by converting entities, fixing
-     * encoding, extracting bits, and other good stuff.
-     */
-    function normalize($html, $config) {
-        
-        // extract body from document if applicable
-        if ($config->get('Core', 'AcceptFullDocuments')) {
-            $html = $this->extractBody($html);
-        }
-        
-        // escape CDATA
-        $html = $this->escapeCDATA($html);
-        
-        // expand entities that aren't the big five
-        $html = $this->_entity_parser->substituteNonSpecialEntities($html);
-        
-        // clean into wellformed UTF-8 string for an SGML context: this has
-        // to be done after entity expansion because the entities sometimes
-        // represent non-SGML characters (horror, horror!)
-        $html = $this->_encoder->cleanUTF8($html);
-        
-        return $html;
-    }
-    
     /**
      * Takes a string of HTML (fragment or document) and returns the content
      */
-    function extractBody($html) {
+    function extractBody($html, $return_bool = false) {
         $matches = array();
         $result = preg_match('!<body[^>]*>(.+?)</body>!is', $html, $matches);
+        if ($return_bool) return $result;
         if ($result) {
             return $matches[1];
         } else {

library/HTMLPurifier/Lexer/DOMLex.php

@@ -12,19 +12,15 @@ require_once 'HTMLPurifier/TokenFactory.php';
  * documents, it performs twenty times faster than
  * HTMLPurifier_Lexer_DirectLex,and is the default choice for PHP 5. 
  * 
- * @note Any empty elements will have empty tokens associated with them, even if
+ * @notice
+ * Any empty elements will have empty tokens associated with them, even if
  * this is prohibited by the spec. This is cannot be fixed until the spec
  * comes into play.
  * 
- * @note PHP's DOM extension does not actually parse any entities, we use
- *       our own function to do that.
- * 
- * @warning DOM tends to drop whitespace, which may wreak havoc on indenting.
- *          If this is a huge problem, due to the fact that HTML is hand
- *          edited and youa re unable to get a parser cache that caches the
- *          the output of HTML Purifier while keeping the original HTML lying
- *          around, you may want to run Tidy on the resulting output or use
- *          HTMLPurifier_DirectLex
+ * @todo Determine DOM's entity parsing behavior, point to local entity files
+ *       if necessary.
+ * @todo Make div access less fragile, and refrain from preprocessing when
+ *       HTML tag and friends are already present.
  */
 
 class HTMLPurifier_Lexer_DOMLex extends HTMLPurifier_Lexer
@@ -34,34 +30,38 @@ class HTMLPurifier_Lexer_DOMLex extends HTMLPurifier_Lexer
     
     public function __construct() {
         // setup the factory
-        parent::HTMLPurifier_Lexer();
         $this->factory = new HTMLPurifier_TokenFactory();
     }
     
     public function tokenizeHTML($string, $config = null) {
         if (!$config) $config = HTMLPurifier_Config::createDefault();
         
-        $string = $this->normalize($string, $config);
-        
-        // preprocess string, essential for UTF-8
-        $string =
-            '<!DOCTYPE html '.
-                'PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"'.
-                '"http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">'.
-            '<html><head>'.
-            '<meta http-equiv="Content-Type" content="text/html;'.
-                ' charset=utf-8" />'.
-            '</head><body><div>'.$string.'</div></body></html>';
+        if ($config->get('Core', 'AcceptFullDocuments')) {
+            $is_full = $this->extractBody($string, true);
+        }
         
         $doc = new DOMDocument();
         $doc->encoding = 'UTF-8'; // technically does nothing, but whatever
+        
+        // replace and escape the CDATA sections, since parsing under HTML
+        // mode won't get 'em.
+        $string = $this->escapeCDATA($string);
+        
+        if (!$is_full) {
+        // preprocess string, essential for UTF-8
+        $string =
+            '<html><head>'.
+            '<meta http-equiv="Content-Type" content="text/html;'.
+                ' charset=utf-8" />'.
+            '</head><body>'.$string.'</body></html>';
+        }
+        
         @$doc->loadHTML($string); // mute all errors, handle it transparently
         
         $tokens = array();
         $this->tokenizeDOM(
-            $doc->getElementsByTagName('html')->item(0)-> // html
-                  getElementsByTagName('body')->item(0)-> // body
-                  getElementsByTagName('div')->item(0) // div
+            $doc->childNodes->item(1)-> // html
+                  getElementsByTagName('body')->item(0) // body
             , $tokens);
         return $tokens;
     }
@@ -79,32 +79,32 @@ class HTMLPurifier_Lexer_DOMLex extends HTMLPurifier_Lexer
     protected function tokenizeDOM($node, &$tokens, $collect = false) {
         // recursive goodness!
         
-        // intercept non element nodes. WE MUST catch all of them,
-        // but we're not getting the character reference nodes because
-        // those should have been preprocessed
-        if ($node->nodeType === XML_TEXT_NODE ||
-                  $node->nodeType === XML_CDATA_SECTION_NODE) {
-            $tokens[] = $this->factory->createText($node->data);
-            return;
-        } elseif ($node->nodeType === XML_COMMENT_NODE) {
-            $tokens[] = $this->factory->createComment($node->data);
+        // intercept non element nodes
+        
+        if ( isset($node->data) ) {
+            if ($node->nodeType === XML_TEXT_NODE ||
+                      $node->nodeType === XML_CDATA_SECTION_NODE) {
+                $tokens[] = $this->factory->createText($node->data);
+            } elseif ($node->nodeType === XML_COMMENT_NODE) {
+                $tokens[] = $this->factory->createComment($node->data);
+            }
+            // quite possibly, the object wasn't handled, that's fine
             return;
         }
         
-        $attr = $node->hasAttributes() ?
-            $this->transformAttrToAssoc($node->attributes) :
-            array();
-        
         // We still have to make sure that the element actually IS empty
         if (!$node->childNodes->length) {
             if ($collect) {
-                $tokens[] = $this->factory->createEmpty($node->tagName, $attr);
+                $tokens[] = $this->factory->createEmpty(
+                    $node->tagName,
+                    $this->transformAttrToAssoc($node->attributes)
+                );
             }
         } else {
             if ($collect) { // don't wrap on first iteration
                 $tokens[] = $this->factory->createStart(
                     $tag_name = $node->tagName, // somehow, it get's dropped
-                    $attr
+                    $this->transformAttrToAssoc($node->attributes)
                 );
             }
             foreach ($node->childNodes as $node) {

library/HTMLPurifier/Lexer/DirectLex.php

@@ -12,28 +12,122 @@ require_once 'HTMLPurifier/Lexer.php';
  * completely eventually.
  * 
  * @todo Reread XML spec and document differences.
- * 
- * @todo Determine correct behavior in transforming comment data. (preserve dashes?)
+ * @todo Add support for CDATA sections.
+ * @todo Determine correct behavior in outputting comment data. (preserve dashes?)
+ * @todo Optimize main function tokenizeHTML().
+ * @todo Less than sign (<) being prohibited (even as entity) in attr-values?
  */
 class HTMLPurifier_Lexer_DirectLex extends HTMLPurifier_Lexer
 {
     
+    /**
+     * Parses special entities into the proper characters.
+     * 
+     * This string will translate escaped versions of the special characters
+     * into the correct ones.
+     * 
+     * @warning
+     * You should be able to treat the output of this function as
+     * completely parsed, but that's only because all other entities should
+     * have been handled previously in substituteNonSpecialEntities()
+     * 
+     * @param $string String character data to be parsed.
+     * @returns Parsed character data.
+     */
+    function parseData($string) {
+        
+        // subtracts amps that cannot possibly be escaped
+        $num_amp = substr_count($string, '&') - substr_count($string, '& ') -
+            ($string[strlen($string)-1] === '&' ? 1 : 0);
+        
+        if (!$num_amp) return $string; // abort if no entities
+        $num_esc_amp = substr_count($string, '&amp;');
+        $string = strtr($string, $this->_special_entity2str);
+        
+        // code duplication for sake of optimization, see above
+        $num_amp_2 = substr_count($string, '&') - substr_count($string, '& ') -
+            ($string[strlen($string)-1] === '&' ? 1 : 0);
+        
+        if ($num_amp_2 <= $num_esc_amp) return $string;
+        
+        // hmm... now we have some uncommon entities. Use the callback.
+        $string = $this->substituteSpecialEntities($string);
+        return $string;
+    }
+    
     /**
      * Whitespace characters for str(c)spn.
      * @protected
      */
     var $_whitespace = "\x20\x09\x0D\x0A";
     
-    function tokenizeHTML($html, $config = null) {
+    /**
+     * Substitutes only special entities with their parsed equivalents.
+     * 
+     * @notice We try to avoid calling this function because otherwise, it
+     * would have to be called a lot (for every parsed section).
+     * 
+     * @protected
+     * @param $string String to have non-special entities parsed.
+     * @returns Parsed string.
+     */
+    function substituteSpecialEntities($string) {
+        return preg_replace_callback(
+            $this->_substituteEntitiesRegex,
+            array('HTMLPurifier_Lexer_DirectLex', 'specialEntityCallback'),
+            $string);
+    }
+    
+    /**
+     * Callback function for substituteSpecialEntities() that does the work.
+     * 
+     * This callback has same syntax as nonSpecialEntityCallback().
+     * 
+     * @warning Though this is public in order to let the callback happen,
+     *          calling it directly is not recommended.
+     * @param $matches  PCRE-style matches array, with 0 the entire match, and
+     *                  either index 1, 2 or 3 set with a hex value, dec value,
+     *                  or string (respectively).
+     * @returns Replacement string.
+     */
+    function specialEntityCallback($matches) {
+        $entity = $matches[0];
+        $is_num = (@$matches[0][1] === '#');
+        if ($is_num) {
+            $is_hex = (@$entity[2] === 'x');
+            $int = $is_hex ? hexdec($matches[1]) : (int) $matches[2];
+            return isset($this->_special_dec2str[$int]) ?
+                $this->_special_dec2str[$int] :
+                $entity;
+        } else {
+            return isset($this->_special_ent2dec[$matches[3]]) ?
+                $this->_special_ent2dec[$matches[3]] :
+                $entity;
+        }
+    }
+    
+    function tokenizeHTML($string, $config = null) {
         
         if (!$config) $config = HTMLPurifier_Config::createDefault();
         
-        $html = $this->normalize($html, $config);
+        // some quick checking (if empty, return empty)
+        $string = @ (string) $string;
+        if ($string == '') return array();
+        
+        if ($config->get('Core', 'AcceptFullDocuments')) {
+            $string = $this->extractBody($string);
+        }
         
         $cursor = 0; // our location in the text
         $inside_tag = false; // whether or not we're parsing the inside of a tag
         $array = array(); // result array
         
+        // escape CDATA
+        $string = $this->escapeCDATA($string);
+        
+        // expand entities THAT AREN'T THE BIG FIVE
+        $string = $this->substituteNonSpecialEntities($string);
+        
         // infinite loop protection
         // has to be pretty big, since html docs can be big
         // we're allow two hundred thousand tags... more than enough?
@@ -44,8 +138,8 @@ class HTMLPurifier_Lexer_DirectLex extends HTMLPurifier_Lexer
             // infinite loop protection
             if (++$loops > 200000) return array();
             
-            $position_next_lt = strpos($html, '<', $cursor);
-            $position_next_gt = strpos($html, '>', $cursor);
+            $position_next_lt = strpos($string, '<', $cursor);
+            $position_next_gt = strpos($string, '>', $cursor);
             
             // triggers on "<b>asdf</b>" but not "asdf <b></b>"
             if ($position_next_lt === $cursor) {
@@ -59,7 +153,7 @@ class HTMLPurifier_Lexer_DirectLex extends HTMLPurifier_Lexer
                     HTMLPurifier_Token_Text(
                         $this->parseData(
                             substr(
-                                $html, $cursor, $position_next_lt - $cursor
+                                $string, $cursor, $position_next_lt - $cursor
                             )
                         )
                     );
@@ -69,13 +163,13 @@ class HTMLPurifier_Lexer_DirectLex extends HTMLPurifier_Lexer
             } elseif (!$inside_tag) {
                 // We are not inside tag but there are no more tags
                 // If we're already at the end, break
-                if ($cursor === strlen($html)) break;
+                if ($cursor === strlen($string)) break;
                 // Create Text of rest of string
                 $array[] = new
                     HTMLPurifier_Token_Text(
                         $this->parseData(
                             substr(
-                                $html, $cursor
+                                $string, $cursor
                             )
                         )
                     );
@@ -84,7 +178,7 @@ class HTMLPurifier_Lexer_DirectLex extends HTMLPurifier_Lexer
                 // We are in tag and it is well formed
                 // Grab the internals of the tag
                 $strlen_segment = $position_next_gt - $cursor;
-                $segment = substr($html, $cursor, $strlen_segment);
+                $segment = substr($string, $cursor, $strlen_segment);
                 
                 // Check if it's a comment
                 if (
@@ -165,7 +259,7 @@ class HTMLPurifier_Lexer_DirectLex extends HTMLPurifier_Lexer
                     HTMLPurifier_Token_Text(
                         '<' .
                         $this->parseData(
-                            substr($html, $cursor)
+                            substr($string, $cursor)
                         )
                     );
                 break;

library/HTMLPurifier/Lexer/PEARSax3.php

@@ -18,8 +18,6 @@ require_once 'HTMLPurifier/Lexer.php';
  * whatever it does for poorly formed HTML is up to it.
  * 
  * @todo Generalize so that XML_HTMLSax is also supported.
- * 
- * @warning Entity-resolution inside attributes is broken.
  */
 
 class HTMLPurifier_Lexer_PEARSax3 extends HTMLPurifier_Lexer
@@ -31,36 +29,29 @@ class HTMLPurifier_Lexer_PEARSax3 extends HTMLPurifier_Lexer
      */
     var $tokens = array();
     
-    function tokenizeHTML($string, $config = null) {
-        
-        $this->tokens = array();
-        
+    function tokenizeHTML($html, $config = null) {
         if (!$config) $config = HTMLPurifier_Config::createDefault();
-        $string = $this->normalize($string, $config);
-        
+        $html = $this->escapeCDATA($html);
+        if ($config->get('Core', 'AcceptFullDocuments')) {
+            $html = $this->extractBody($html);
+        }
+        $html = $this->substituteNonSpecialEntities($html);
         $parser=& new XML_HTMLSax3();
         $parser->set_object($this);
         $parser->set_element_handler('openHandler','closeHandler');
         $parser->set_data_handler('dataHandler');
         $parser->set_escape_handler('escapeHandler');
-        
-        // doesn't seem to work correctly for attributes
         $parser->set_option('XML_OPTION_ENTITIES_PARSED', 1);
-        
-        $parser->parse($string);
-        
-        return $this->tokens;
-        
+        $parser->parse($html);
+        $tokens = $this->tokens;
+        $this->tokens = array();
+        return $tokens;
     }
     
     /**
      * Open tag event handler, interface is defined by PEAR package.
      */
     function openHandler(&$parser, $name, $attrs, $closed) {
-        // entities are not resolved in attrs
-        foreach ($attrs as $key => $attr) {
-            $attrs[$key] = $this->parseData($attr);
-        }
         if ($closed) {
             $this->tokens[] = new HTMLPurifier_Token_Empty($name, $attrs);
         } else {

library/HTMLPurifier/Strategy.php

@@ -8,8 +8,8 @@
  * features, such as custom tags, custom parsing of text, etc.
  */
 
-HTMLPurifier_ConfigSchema::define(
-    'Core', 'EscapeInvalidTags', false, 'bool',
+HTMLPurifier_ConfigDef::define(
+    'Core', 'EscapeInvalidTags', false,
     'When true, invalid tags will be written back to the document as plain '.
     'text.  Otherwise, they are silently dropped.'
 );

library/HTMLPurifier/Strategy/Composite.php

@@ -3,15 +3,9 @@
 require_once 'HTMLPurifier/Strategy.php';
 require_once 'HTMLPurifier/Config.php';
 
-/**
- * Composite strategy that runs multiple strategies on tokens.
- */
-class HTMLPurifier_Strategy_Composite extends HTMLPurifier_Strategy
+class HTMLPurifier_Strategy_Composite
 {
     
-    /**
-     * List of strategies to run tokens through.
-     */
     var $strategies = array();
     
     function HTMLPurifier_Strategy_Composite() {

library/HTMLPurifier/Strategy/Core.php

@@ -7,9 +7,6 @@ require_once 'HTMLPurifier/Strategy/MakeWellFormed.php';
 require_once 'HTMLPurifier/Strategy/FixNesting.php';
 require_once 'HTMLPurifier/Strategy/ValidateAttributes.php';
 
-/**
- * Core strategy composed of the big four strategies.
- */
 class HTMLPurifier_Strategy_Core extends HTMLPurifier_Strategy_Composite
 {
     

library/HTMLPurifier/Strategy/FixNesting.php

@@ -34,18 +34,21 @@ require_once 'HTMLPurifier/HTMLDefinition.php';
 class HTMLPurifier_Strategy_FixNesting extends HTMLPurifier_Strategy
 {
     
+    var $definition;
+    
+    function HTMLPurifier_Strategy_FixNesting() {
+        $this->definition = HTMLPurifier_HTMLDefinition::instance();
+    }
+    
     function execute($tokens, $config) {
         
         //####################################################################//
         // Pre-processing
         
-        // get a copy of the HTML definition
-        $definition = $config->getHTMLDefinition();
-        
         // insert implicit "parent" node, will be removed at end.
         // ! we might want to move this to configuration
         // DEFINITION CALL
-        $parent_name = $definition->info_parent;
+        $parent_name = $this->definition->info_parent;
         array_unshift($tokens, new HTMLPurifier_Token_Start($parent_name));
         $tokens[] = new HTMLPurifier_Token_End($parent_name);
         
@@ -101,7 +104,7 @@ class HTMLPurifier_Strategy_FixNesting extends HTMLPurifier_Strategy
             if ($count = count($stack)) {
                 $parent_index = $stack[$count-1];
                 $parent_name  = $tokens[$parent_index]->name;
-                $parent_def   = $definition->info[$parent_name];
+                $parent_def   = $this->definition->info[$parent_name];
             } else {
                 // unknown info, it won't be used anyway
                 $parent_index = $parent_name = $parent_def = null;
@@ -140,7 +143,7 @@ class HTMLPurifier_Strategy_FixNesting extends HTMLPurifier_Strategy
                 $result = false;
             } else {
                 // DEFINITION CALL
-                $def = $definition->info[$tokens[$i]->name];
+                $def = $this->definition->info[$tokens[$i]->name];
                 $child_def = $def->child;
                 
                 // have DTD child def validate children
@@ -187,7 +190,6 @@ class HTMLPurifier_Strategy_FixNesting extends HTMLPurifier_Strategy
                 if (!$parent_def->child->allow_empty) {
                     // we need to do a double-check
                     $i = $parent_index;
-                    array_pop($stack);
                 }
                 
                 // PROJECTED OPTIMIZATION: Process all children elements before
@@ -231,7 +233,7 @@ class HTMLPurifier_Strategy_FixNesting extends HTMLPurifier_Strategy
                     array_pop($stack);
                     // pop an exclusion lookup off exclusion stack if
                     // we ended node and that node had exclusions
-                    if ($definition->info[$tokens[$i]->name]->excludes) {
+                    if ($this->definition->info[$tokens[$i]->name]->excludes) {
                         array_pop($exclude_stack);
                     }
                 }
@@ -256,4 +258,4 @@ class HTMLPurifier_Strategy_FixNesting extends HTMLPurifier_Strategy
     
 }
 
-?>
+?>

library/HTMLPurifier/Strategy/MakeWellFormed.php

@@ -4,15 +4,18 @@ require_once 'HTMLPurifier/Strategy.php';
 require_once 'HTMLPurifier/HTMLDefinition.php';
 require_once 'HTMLPurifier/Generator.php';
 
-/**
- * Takes tokens makes them well-formed (balance end tags, etc.)
- */
 class HTMLPurifier_Strategy_MakeWellFormed extends HTMLPurifier_Strategy
 {
     
+    var $generator;
+    var $definition;
+    
+    function HTMLPurifier_Strategy_MakeWellFormed() {
+        $this->generator = new HTMLPurifier_Generator();
+        $this->definition = HTMLPurifier_HTMLDefinition::instance();
+    }
+    
     function execute($tokens, $config) {
-        $definition = $config->getHTMLDefinition();
-        $generator = new HTMLPurifier_Generator();
         $result = array();
         $current_nesting = array();
         $escape_invalid_tags = $config->get('Core', 'EscapeInvalidTags');
@@ -23,7 +26,7 @@ class HTMLPurifier_Strategy_MakeWellFormed extends HTMLPurifier_Strategy
             }
             
             // DEFINITION CALL
-            $info = $definition->info[$token->name]->child;
+            $info = $this->definition->info[$token->name]->child;
             
             // test if it claims to be a start tag but is empty
             if ($info->type == 'empty' &&
@@ -60,7 +63,7 @@ class HTMLPurifier_Strategy_MakeWellFormed extends HTMLPurifier_Strategy
                     
                     $parent = array_pop($current_nesting);
                     $parent_name = $parent->name;
-                    $parent_info = $definition->info[$parent_name];
+                    $parent_info = $this->definition->info[$parent_name];
                     
                     if (isset($parent_info->auto_close[$token->name])) {
                         $result[] = new HTMLPurifier_Token_End($parent_name);
@@ -86,7 +89,7 @@ class HTMLPurifier_Strategy_MakeWellFormed extends HTMLPurifier_Strategy
             if (empty($current_nesting)) {
                 if ($escape_invalid_tags) {
                     $result[] = new HTMLPurifier_Token_Text(
-                        $generator->generateFromToken($token, $config)
+                        $this->generator->generateFromToken($token, $config)
                     );
                 }
                 continue;
@@ -123,7 +126,7 @@ class HTMLPurifier_Strategy_MakeWellFormed extends HTMLPurifier_Strategy
             if ($skipped_tags === false) {
                 if ($escape_invalid_tags) {
                     $result[] = new HTMLPurifier_Token_Text(
-                        $generator->generateFromToken($token, $config)
+                        $this->generator->generateFromToken($token, $config)
                     );
                 }
                 continue;

library/HTMLPurifier/Strategy/RemoveForeignElements.php

@@ -16,28 +16,35 @@ require_once 'HTMLPurifier/TagTransform.php';
 class HTMLPurifier_Strategy_RemoveForeignElements extends HTMLPurifier_Strategy
 {
     
+    var $generator;
+    var $definition;
+    
+    function HTMLPurifier_Strategy_RemoveForeignElements() {
+        $this->generator = new HTMLPurifier_Generator();
+        $this->definition = HTMLPurifier_HTMLDefinition::instance();
+    }
+    
     function execute($tokens, $config) {
-        $definition = $config->getHTMLDefinition();
-        $generator = new HTMLPurifier_Generator();
         $result = array();
         $escape_invalid_tags = $config->get('Core', 'EscapeInvalidTags');
         foreach($tokens as $token) {
             if (!empty( $token->is_tag )) {
                 // DEFINITION CALL
-                if (isset($definition->info[$token->name])) {
+                if (isset($this->definition->info[$token->name])) {
                     // leave untouched
                 } elseif (
-                    isset($definition->info_tag_transform[$token->name])
+                    isset($this->definition->info_tag_transform[$token->name])
                 ) {
                     // there is a transformation for this tag
                     // DEFINITION CALL
-                    $token = $definition->
-                                info_tag_transform[$token->name]->
-                                    transform($token);
+                    $token = $this->
+                                definition->
+                                    info_tag_transform[$token->name]->
+                                        transform($token);
                 } elseif ($escape_invalid_tags) {
                     // invalid tag, generate HTML and insert in
                     $token = new HTMLPurifier_Token_Text(
-                        $generator->generateFromToken($token, $config)
+                        $this->generator->generateFromToken($token, $config)
                     );
                 } else {
                     continue;

library/HTMLPurifier/Strategy/ValidateAttributes.php

@@ -3,11 +3,11 @@
 require_once 'HTMLPurifier/Strategy.php';
 require_once 'HTMLPurifier/HTMLDefinition.php';
 require_once 'HTMLPurifier/IDAccumulator.php';
-require_once 'HTMLPurifier/ConfigSchema.php';
+require_once 'HTMLPurifier/ConfigDef.php';
 require_once 'HTMLPurifier/AttrContext.php';
 
-HTMLPurifier_ConfigSchema::define(
-    'Attr', 'IDBlacklist', array(), 'list',
+HTMLPurifier_ConfigDef::define(
+    'Attr', 'IDBlacklist', array(),
     'Array of IDs not allowed in the document.');
 
 /**
@@ -17,10 +17,14 @@ HTMLPurifier_ConfigSchema::define(
 class HTMLPurifier_Strategy_ValidateAttributes extends HTMLPurifier_Strategy
 {
     
+    var $definition;
+    
+    function HTMLPurifier_Strategy_ValidateAttributes() {
+        $this->definition = HTMLPurifier_HTMLDefinition::instance();
+    }
+    
     function execute($tokens, $config) {
         
-        $definition = $config->getHTMLDefinition();
-        
         // setup StrategyContext
         $context = new HTMLPurifier_AttrContext();
         
@@ -32,7 +36,7 @@ class HTMLPurifier_Strategy_ValidateAttributes extends HTMLPurifier_Strategy
         
         // create alias to global definition array, see also $defs
         // DEFINITION CALL
-        $d_defs = $definition->info_global_attr;
+        $d_defs = $this->definition->info_global_attr;
         
         foreach ($tokens as $key => $token) {
             
@@ -46,14 +50,14 @@ class HTMLPurifier_Strategy_ValidateAttributes extends HTMLPurifier_Strategy
             // do global transformations (pre)
             // ex. <ELEMENT lang="fr"> to <ELEMENT lang="fr" xml:lang="fr">
             // DEFINITION CALL
-            foreach ($definition->info_attr_transform_pre as $transform) {
+            foreach ($this->definition->info_attr_transform_pre as $transform) {
                 $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
+            foreach ($this->definition->info[$token->name]->attr_transform_pre
                 as $transform
             ) {
                 $attr = $transform->transform($attr, $config);
@@ -62,7 +66,7 @@ class HTMLPurifier_Strategy_ValidateAttributes extends HTMLPurifier_Strategy
             // create alias to this element's attribute definition array, see
             // also $d_defs (global attribute definition array)
             // DEFINITION CALL
-            $defs = $definition->info[$token->name]->attr;
+            $defs = $this->definition->info[$token->name]->attr;
             
             // iterate through all the attribute keypairs
             // Watch out for name collisions: $key has previously been used
@@ -112,10 +116,10 @@ class HTMLPurifier_Strategy_ValidateAttributes extends HTMLPurifier_Strategy
             }
             
             // post transforms
-            foreach ($definition->info_attr_transform_post as $transform) {
+            foreach ($this->definition->info_attr_transform_post as $transform) {
                 $attr = $transform->transform($attr, $config);
             }
-            foreach ($definition->info[$token->name]->attr_transform_post as $transform) {
+            foreach ($this->definition->info[$token->name]->attr_transform_post as $transform) {
                 $attr = $transform->transform($attr, $config);
             }
             

library/HTMLPurifier/TagTransform.php

@@ -2,37 +2,20 @@
 
 require_once('HTMLPurifier/Token.php');
 
-/**
- * Defines a mutation of an obsolete tag into a valid tag.
- */
 class HTMLPurifier_TagTransform
 {
     
-    /**
-     * Tag name to transform the tag to.
-     * @public
-     */
-    var $transform_to;
-    
-    /**
-     * Transforms the obsolete tag into the valid tag.
-     * @param $tag Tag to be transformed.
-     */
     function transform($tag) {
         trigger_error('Call to abstract function', E_USER_ERROR);
     }
     
 }
 
-/**
- * Simple transformation, just change tag name to something else.
- */
 class HTMLPurifier_TagTransform_Simple extends HTMLPurifier_TagTransform
 {
     
-    /**
-     * @param $transform_to Tag name to transform to.
-     */
+    var $transform_to;
+    
     function HTMLPurifier_TagTransform_Simple($transform_to) {
         $this->transform_to = $transform_to;
     }
@@ -45,12 +28,6 @@ class HTMLPurifier_TagTransform_Simple extends HTMLPurifier_TagTransform
     
 }
 
-/**
- * Transforms CENTER tags into proper version (DIV with text-align CSS)
- * 
- * Takes a CENTER tag, parses the align attribute, and then if it's valid
- * assigns it to the CSS property text-align.
- */
 class HTMLPurifier_TagTransform_Center extends HTMLPurifier_TagTransform
 {
     var $transform_to = 'div';
@@ -74,18 +51,6 @@ class HTMLPurifier_TagTransform_Center extends HTMLPurifier_TagTransform
     }
 }
 
-/**
- * Transforms FONT tags to the proper form (SPAN with CSS styling)
- * 
- * This transformation takes the three proprietary attributes of FONT and
- * transforms them into their corresponding CSS attributes.  These are color,
- * face, and size.
- * 
- * @note Size is an interesting case because it doesn't map cleanly to CSS.
- *       Thanks to
- *       http://style.cleverchimp.com/font_size_intervals/altintervals.html
- *       for reasonable mappings.
- */
 class HTMLPurifier_TagTransform_Font extends HTMLPurifier_TagTransform
 {
     
@@ -113,6 +78,8 @@ class HTMLPurifier_TagTransform_Font extends HTMLPurifier_TagTransform
             return $new_tag;
         }
         
+        // font size lookup table based off of:
+        //  http://style.cleverchimp.com/font_size_intervals/altintervals.html
         $attributes = $tag->attributes;
         $prepend_style = '';
         

library/HTMLPurifier/Token.php

@@ -11,14 +11,6 @@
  */
 class HTMLPurifier_Token {
     var $type; /**< Type of node to bypass <tt>is_a()</tt>. @public */
-    
-    /**
-     * Copies the tag into a new one (clone substitute).
-     * @return Copied token
-     */
-    function copy() {
-        trigger_error('Cannot copy abstract class', E_USER_ERROR);
-    }
 }
 
 /**

library/HTMLPurifier/TokenFactory.php

@@ -2,30 +2,12 @@
 
 require_once 'HTMLPurifier/Token.php';
 
-/**
- * Factory for token generation (PHP 5 only).
- * 
- * @note Doing some benchmarking indicates that the new operator is much
- *       slower than the clone operator (even discounting the cost of the
- *       constructor).  This class is for that optimization.  We may want to
- *       consider porting this to PHP 4 by virtue of the fact it makes the code
- *       easier to read.  Other then that, there's not much point as we don't
- *       maintain parallel HTMLPurifier_Token hierarchies (the main reason why
- *       you'd want to use an abstract factory).
- */
 class HTMLPurifier_TokenFactory
 {
     
-    /**
-     * Prototypes that will be cloned.
-     * @private
-     */
     // p stands for prototype
     private $p_start, $p_end, $p_empty, $p_text, $p_comment;
     
-    /**
-     * Generates blank prototypes for cloning.
-     */
     public function __construct() {
         $this->p_start  = new HTMLPurifier_Token_Start('', array());
         $this->p_end    = new HTMLPurifier_Token_End('');
@@ -34,57 +16,30 @@ class HTMLPurifier_TokenFactory
         $this->p_comment= new HTMLPurifier_Token_Comment('');
     }
     
-    /**
-     * Creates a HTMLPurifier_Token_Start.
-     * @param $name Tag name
-     * @param $attribute Associative array of attributes
-     * @return Generated HTMLPurifier_Token_Start
-     */
     public function createStart($name, $attributes = array()) {
         $p = clone $this->p_start;
         $p->HTMLPurifier_Token_Tag($name, $attributes);
         return $p;
     }
     
-    /**
-     * Creates a HTMLPurifier_Token_End.
-     * @param $name Tag name
-     * @return Generated HTMLPurifier_Token_End
-     */
     public function createEnd($name) {
         $p = clone $this->p_end;
         $p->HTMLPurifier_Token_Tag($name);
         return $p;
     }
     
-    /**
-     * Creates a HTMLPurifier_Token_Empty.
-     * @param $name Tag name
-     * @param $attribute Associative array of attributes
-     * @return Generated HTMLPurifier_Token_Empty
-     */
     public function createEmpty($name, $attributes = array()) {
         $p = clone $this->p_empty;
         $p->HTMLPurifier_Token_Tag($name, $attributes);
         return $p;
     }
     
-    /**
-     * Creates a HTMLPurifier_Token_Text.
-     * @param $data Data of text token
-     * @return Generated HTMLPurifier_Token_Text
-     */
     public function createText($data) {
         $p = clone $this->p_text;
         $p->HTMLPurifier_Token_Text($data);
         return $p;
     }
     
-    /**
-     * Creates a HTMLPurifier_Token_Comment.
-     * @param $data Data of comment token
-     * @return Generated HTMLPurifier_Token_Comment
-     */
     public function createComment($data) {
         $p = clone $this->p_comment;
         $p->HTMLPurifier_Token_Comment($data);

library/HTMLPurifier/URIScheme.php

@@ -1,29 +1,10 @@
 <?php
 
-/**
- * Validator for the components of a URI for a specific scheme
- */
 class HTMLPurifier_URIScheme
 {
     
-    /**
-     * Scheme's default port (integer)
-     * @public
-     */
     var $default_port = null;
     
-    /**
-     * Validates the components of a URI
-     * @note This implementation should be called by children if they define
-     *       a default port, as it does port processing.
-     * @note Fragment is omitted as that is scheme independent
-     * @param $userinfo User info found before at sign in authority
-     * @param $host Hostname in authority
-     * @param $port Port found after colon in authority
-     * @param $path Path of URI
-     * @param $query Query of URI, found after question mark
-     * @param $config HTMLPurifier_Config object
-     */
     function validateComponents(
         $userinfo, $host, $port, $path, $query, $config
     ) {

library/HTMLPurifier/URIScheme/ftp.php

@@ -2,9 +2,6 @@
 
 require_once 'HTMLPurifier/URIScheme.php';
 
-/**
- * Validates ftp (File Transfer Protocol) URIs as defined by generic RFC 1738.
- */
 class HTMLPurifier_URIScheme_ftp extends HTMLPurifier_URIScheme {
     
     var $default_port = 21;
@@ -15,27 +12,7 @@ class HTMLPurifier_URIScheme_ftp extends HTMLPurifier_URIScheme {
         list($userinfo, $host, $port, $path, $query) = 
             parent::validateComponents(
                 $userinfo, $host, $port, $path, $query, $config );
-        $semicolon_pos = strrpos($path, ';'); // reverse
-        if ($semicolon_pos !== false) {
-            // typecode check
-            $type = substr($path, $semicolon_pos + 1); // no semicolon
-            $path = substr($path, 0, $semicolon_pos);
-            $type_ret = '';
-            if (strpos($type, '=') !== false) {
-                // figure out whether or not the declaration is correct
-                list($key, $typecode) = explode('=', $type, 2);
-                if ($key !== 'type') {
-                    // invalid key, tack it back on encoded
-                    $path .= '%3B' . $type;
-                } elseif ($typecode === 'a' || $typecode === 'i' || $typecode === 'd') {
-                    $type_ret = ";type=$typecode";
-                }
-            } else {
-                $path .= '%3B' . $type;
-            }
-            $path = str_replace(';', '%3B', $path);
-            $path .= $type_ret;
-        }
+        // typecode check needed on path
         return array($userinfo, $host, $port, $path, null);
     }
     

library/HTMLPurifier/URIScheme/http.php

@@ -2,9 +2,6 @@
 
 require_once 'HTMLPurifier/URIScheme.php';
 
-/**
- * Validates http (HyperText Transfer Protocol) as defined by RFC 2616
- */
 class HTMLPurifier_URIScheme_http extends HTMLPurifier_URIScheme {
     
     var $default_port = 80;

library/HTMLPurifier/URIScheme/https.php

@@ -2,9 +2,6 @@
 
 require_once 'HTMLPurifier/URIScheme/http.php';
 
-/**
- * Validates https (Secure HTTP) according to http scheme.
- */
 class HTMLPurifier_URIScheme_https extends HTMLPurifier_URIScheme_http {
     
     var $default_port = 443;

library/HTMLPurifier/URIScheme/mailto.php

@@ -5,12 +5,6 @@ require_once 'HTMLPurifier/URIScheme.php';
 // VERY RELAXED! Shouldn't cause problems, not even Firefox checks if the
 // email is valid, but be careful!
 
-/**
- * Validates mailto (for E-mail) according to RFC 2368
- * @todo Validate the email address
- * @todo Filter allowed query parameters
- */
-
 class HTMLPurifier_URIScheme_mailto extends HTMLPurifier_URIScheme {
     
     function validateComponents(

library/HTMLPurifier/URIScheme/news.php

@@ -2,9 +2,6 @@
 
 require_once 'HTMLPurifier/URIScheme.php';
 
-/**
- * Validates news (Usenet) as defined by generic RFC 1738
- */
 class HTMLPurifier_URIScheme_news extends HTMLPurifier_URIScheme {
     
     function validateComponents(

library/HTMLPurifier/URIScheme/nntp.php

@@ -2,9 +2,6 @@
 
 require_once 'HTMLPurifier/URIScheme.php';
 
-/**
- * Validates nntp (Network News Transfer Protocol) as defined by generic RFC 1738
- */
 class HTMLPurifier_URIScheme_nntp extends HTMLPurifier_URIScheme {
     
     var $default_port = 119;

library/HTMLPurifier/URISchemeRegistry.php

@@ -1,6 +1,6 @@
 <?php
 
-HTMLPurifier_ConfigSchema::define(
+HTMLPurifier_ConfigDef::define(
     'URI', 'AllowedSchemes', array(
         'http'  => true, // "Hypertext Transfer Protocol", nuf' said
         'https' => true, // HTTP over SSL (Secure Socket Layer)
@@ -11,32 +11,25 @@ HTMLPurifier_ConfigSchema::define(
         // for Usenet, these two are similar, but distinct
         'nntp'  => true, // individual Netnews articles
         'news'  => true  // newsgroup or individual Netnews articles),
-    ), 'lookup',
+    ),
     'Whitelist that defines the schemes that a URI is allowed to have.  This '.
     'prevents XSS attacks from using pseudo-schemes like javascript or mocha.'
 );
 
-HTMLPurifier_ConfigSchema::define(
-    'URI', 'OverrideAllowedSchemes', true, 'bool',
+HTMLPurifier_ConfigDef::define(
+    'URI', 'OverrideAllowedSchemes', true,
     'If this is set to true (which it is by default), you can override '.
     '%URI.AllowedSchemes by simply registering a HTMLPurifier_URIScheme '.
     'to the registry.  If false, you will also have to update that directive '.
     'in order to add more schemes.'
 );
 
-/**
- * Registry for retrieving specific URI scheme validator objects.
- */
 class HTMLPurifier_URISchemeRegistry
 {
     
-    /**
-     * Retrieve sole instance of the registry.
-     * @param $prototype Optional prototype to overload sole instance with,
-     *                   or bool true to reset to default registry.
-     * @note Pass a registry object $prototype with a compatible interface and
-     *       the function will copy it and return it all further times.
-     */
+    // pass a registry object $prototype with a compatible interface and
+    // the function will copy it and return it all further times.
+    // pass bool true to reset to the default registry
     function &instance($prototype = null) {
         static $instance = null;
         if ($prototype !== null) {
@@ -47,23 +40,9 @@ class HTMLPurifier_URISchemeRegistry
         return $instance;
     }
     
-    /**
-     * Cache of retrieved schemes.
-     * @protected
-     */
     var $schemes = array();
-    
-    /**
-     * Directory where scheme objects can be found
-     * @private
-     */
     var $_scheme_dir = null;
     
-    /**
-     * Retrieves a scheme validator object
-     * @param $scheme String scheme name like http or mailto
-     * @param $config HTMLPurifier_Config object
-     */
     function &getScheme($scheme, $config = null) {
         if (!$config) $config = HTMLPurifier_Config::createDefault();
         $null = null; // for the sake of passing by reference
@@ -88,11 +67,6 @@ class HTMLPurifier_URISchemeRegistry
         return $this->schemes[$scheme];
     }
     
-    /**
-     * Registers a custom scheme to the cache.
-     * @param $scheme Scheme name
-     * @param $scheme_obj HTMLPurifier_URIScheme object
-     */
     function register($scheme, &$scheme_obj) {
         $this->schemes[$scheme] =& $scheme_obj;
     }

maintenance/.htaccess

@@ -1 +1 @@
-Deny from all
+Deny from all

phpdoc.ini

@@ -1,100 +0,0 @@
-;; phpDocumentor parse configuration file
-;;
-;; This file is designed to cut down on repetitive typing on the command-line or web interface
-;; You can copy this file to create a number of configuration files that can be used with the
-;; command-line switch -c, as in phpdoc -c default.ini or phpdoc -c myini.ini.  The web
-;; interface will automatically generate a list of .ini files that can be used.
-;;
-;; default.ini is used to generate the online manual at http://www.phpdoc.org/docs
-;;
-;; ALL .ini files must be in the user subdirectory of phpDocumentor with an extension of .ini
-;;
-;; Copyright 2002, Greg Beaver <cellog@users.sourceforge.net>
-;;
-;; WARNING: do not change the name of any command-line parameters, phpDocumentor will ignore them
-
-[Parse Data]
-;; title of all the documentation
-;; legal values: any string
-title = HTML Purifier API Documentation
-
-;; parse files that start with a . like .bash_profile
-;; legal values: true, false
-hidden = false
-
-;; show elements marked @access private in documentation by setting this to on
-;; legal values: on, off
-parseprivate = off
-
-;; parse with javadoc-like description (first sentence is always the short description)
-;; legal values: on, off
-javadocdesc = on
-
-;; add any custom @tags separated by commas here
-;; legal values: any legal tagname separated by commas.
-;customtags = mytag1,mytag2
-
-;; This is only used by the XML:DocBook/peardoc2 converter
-defaultcategoryname = Documentation
-
-;; what is the main package?
-;; legal values: alphanumeric string plus - and _
-defaultpackagename = HTMLPurifier
-
-;; output any parsing information?  set to on for cron jobs
-;; legal values: on
-;quiet = on
-
-;; parse a PEAR-style repository.  Do not turn this on if your project does
-;; not have a parent directory named "pear"
-;; legal values: on/off
-;pear = on
-
-;; where should the documentation be written?
-;; legal values: a legal path
-target = docs/phpdoc
-
-;; Which files should be parsed out as special documentation files, such as README,
-;; INSTALL and CHANGELOG?  This overrides the default files found in
-;; phpDocumentor.ini (this file is not a user .ini file, but the global file)
-readmeinstallchangelog = README, INSTALL, NEWS, WYSIWYG, SLOW, LICENSE, CREDITS
-
-;; limit output to the specified packages, even if others are parsed
-;; legal values: package names separated by commas
-;packageoutput = package1,package2
-
-;; comma-separated list of files to parse
-;; legal values: paths separated by commas
-;filename = /path/to/file1,/path/to/file2,fileincurrentdirectory
-
-;; comma-separated list of directories to parse
-;; legal values: directory paths separated by commas
-;directory = /path1,/path2,.,..,subdirectory
-;directory = /home/jeichorn/cvs/pear
-directory = ./
-
-;; template base directory (the equivalent directory of <installdir>/phpDocumentor)
-;templatebase = /path/to/my/templates
-
-;; directory to find any example files in through @example and {@example} tags
-;examplesdir = /path/to/my/templates
-
-;; comma-separated list of files, directories or wildcards ? and * (any wildcard) to ignore
-;; legal values: any wildcard strings separated by commas
-;ignore = /path/to/ignore*,*list.php,myfile.php,subdirectory/
-ignore = pear-*,templates/,Documentation/,test*.php,Lexer.inc
-
-sourcecode = on
-
-;; comma-separated list of Converters to use in outputformat:Convertername:templatedirectory format
-;; legal values: HTML:frames:default,HTML:frames:l0l33t,HTML:frames:phpdoc.de,HTML:frames:phphtmllib,
-;;               HTML:frames:earthli,
-;;               HTML:frames:DOM/default,HTML:frames:DOM/l0l33t,HTML:frames:DOM/phpdoc.de,
-;;               HTML:frames:DOM/phphtmllib,HTML:frames:DOM/earthli
-;;               HTML:Smarty:default,HTML:Smarty:PHP,HTML:Smarty:HandS
-;;               PDF:default:default,CHM:default:default,XML:DocBook/peardoc2:default
-output=HTML:frames:default
-
-;; turn this option on if you want highlighted source code for every file
-;; legal values: on/off
-sourcecode = on

smoketests/common.php

@@ -1,14 +0,0 @@
-<?php
-
-header('Content-type: text/html; charset=UTF-8');
-
-set_include_path('../library' . PATH_SEPARATOR . get_include_path());
-require_once 'HTMLPurifier.php';
-
-function escapeHTML($string) {
-    $string = HTMLPurifier_Encoder::cleanUTF8($string);
-    $string = htmlspecialchars($string, ENT_COMPAT, 'UTF-8');
-    return $string;
-}
-
-?>

smoketests/utf8.php

@@ -1,8 +1,4 @@
-<?php
-
-require_once 'common.php';
-
-?><!DOCTYPE html 
+<!DOCTYPE html 
      PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"
      "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
 <html>
@@ -14,6 +10,9 @@ require_once 'common.php';
 <h1>HTMLPurifier UTF-8 Smoketest</h1>
 <?php
 
+set_include_path('../library' . PATH_SEPARATOR . get_include_path());
+require_once 'HTMLPurifier.php';
+
 $purifier = new HTMLPurifier();
 $string = '
 <ul>
@@ -28,10 +27,5 @@ $string = '
 <?php echo $string; ?>
 <h2>Purified</h2>
 <?php echo $purifier->purify($string); ?>
-<h2>Analysis</h2>
-<p>The content in <strong>Raw</strong> should be equivalent to the content
-in <strong>Purified</strong>.  If <strong>Purified</strong> is mangled, there
-is likely trouble a-brewing in the library. If
-both are mangled, check to see that this file was not corrupted.</p>
 </body>
 </html>

smoketests/variableWidthAttack.php

@@ -1,53 +0,0 @@
-<?php
-
-require_once 'common.php';
-
-?><!DOCTYPE html 
-     PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"
-     "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
-<html>
-<head>
-<title>HTMLPurifier Variable Width Attack Smoketest</title>
-<meta http-equiv="Content-Type" content="text/html; charset=UTF-8" />
-</head>
-<body>
-<h1>HTMLPurifier Variable Width Attack Smoketest</h1>
-<p>For more information, see
-<a href="http://applesoup.googlepages.com/bypass_filter.txt">Cheng Peng Su's
-original advisory.</a>  This particular exploit code appears only to work
-in Internet Explorer, if it works at all.</p>
-<h2>Test</h2>
-<?php
-
-$purifier = new HTMLPurifier();
-
-?>
-<table>
-<thead><tr><th>ASCII</th><th width="30%">Raw</th><th>Output</th><th>Render</th></tr></thead>
-<tbody>
-<?php
-
-for ($i = 0; $i < 256; $i++) {
-    $c = chr($i);
-    $html = '<img src="" alt="X' . $c . '"';
-    $html .= '>A"'; // in our out the attribute? ;-)
-    $html .= "onerror=alert('$i')>O";
-    $pure_html = $purifier->purify($html);
-?>
-<tr>
-    <td><?php echo $i; ?></td>
-    <td style="font-size:8pt;"><?php echo escapeHTML($html); ?></td>
-    <td style="font-size:8pt;"><?php echo escapeHTML($pure_html); ?></td>
-    <td><?php echo $pure_html; ?></td>
-</tr>
-<?php } ?>
-</tbody>
-</table>
-
-<h2>Analysis</h2>
-
-<p>By making sure that UTF-8 is well formed and non-SGML codepoints are
-removed, as well as escaping quotes outside of tags, this is a non-threat.</p>
-
-</body>
-</html>

smoketests/xssAttacks.php

@@ -1,14 +1,10 @@
-<?php
-
-require_once('common.php');
-
-?><!DOCTYPE html 
+<!DOCTYPE html 
      PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"
      "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
 <html>
 <head>
-    <title>HTMLPurifier XSS Attacks Smoketest</title>
-    <meta http-equiv="Content-Type" content="text/html; charset=UTF-8" />
+<title>HTMLPurifier XSS Attacks Smoketest</title>
+<meta http-equiv="Content-Type" content="text/html; charset=UTF-8" />
 </head>
 <body>
 <h1>HTMLPurifier XSS Attacks Smoketest</h1>
@@ -17,17 +13,17 @@ require_once('common.php');
 <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.</p>
-<p>Most of the XSS broadcasts its presence by spawning an alert dialogue.</p>
-<h2>Test</h2>
 <?php
 
 if (version_compare(PHP_VERSION, '5', '<')) exit('<p>Requires PHP 5.</p>');
 
+set_include_path('../library' . PATH_SEPARATOR . get_include_path());
+require_once 'HTMLPurifier.php';
+
 $xml = simplexml_load_file('xssAttacks.xml');
 $purifier = new HTMLPurifier();
 
 ?>
-<!-- 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>
@@ -40,10 +36,10 @@ foreach ($xml->attack as $attack) {
     if ($attack->name == 'US-ASCII encoding') $code = urldecode($code);
 ?>
     <tr>
-        <td><?php echo escapeHTML($attack->name); ?></td>
-        <td><textarea readonly="readonly" cols="20" rows="2"><?php echo escapeHTML($code); ?></textarea></td>
+        <td><?php echo htmlspecialchars($attack->name); ?></td>
+        <td><textarea readonly="readonly" cols="20" rows="2"><?php echo htmlspecialchars($code); ?></textarea></td>
         <?php $pure_html = $purifier->purify($code); ?>
-        <td><textarea readonly="readonly" cols="20" rows="2"><?php echo escapeHTML($pure_html); ?></textarea></td>
+        <td><textarea readonly="readonly" cols="20" rows="2"><?php echo htmlspecialchars($pure_html); ?></textarea></td>
         <td><?php echo $pure_html ?></td>
     </tr>
 <?php

test-settings.sample.php

@@ -1,17 +0,0 @@
-<?php
-
-// This file is necessary to run the unit tests and profiling
-// scripts.
-
-// Is PEAR available on your system? If it isn't, set to false. If PEAR
-// is not part of the default include_path, add it.
-$GLOBALS['HTMLPurifierTest']['PEAR'] = true;
-
-// How many times should profiling scripts iterate over the function? More runs 
-// means more accurate results, but they'll take longer to perform.
-$GLOBALS['HTMLPurifierTest']['Runs'] = 2;
-
-// Where is SimpleTest located?
-$simpletest_location = '/path/to/simpletest/';
-
-?>