Released 1.1.1.

git-svn-id: http://htmlpurifier.org/svnroot/htmlpurifier/branches/1.1@459 48356398-32a2-884e-a903-53898d9a118a
Merged 438:439, 440:441, and 442:457 from trunk/ to branches/1.1/, mostly major work done for 1.1.1 release.
2025-08-10 16:14:08 +02:00 · 2006-09-24 22:32:26 +00:00 · 2006-09-24 22:22:06 +00:00 · 2006-09-17 22:08:48 +00:00 · 2006-09-17 00:19:47 +00:00 · 2006-09-17 00:17:45 +00:00
51 changed files with 1127 additions and 533 deletions
--- a/2
+++ b/2
@@ -4,7 +4,7 @@
 # Project related configuration options
 #---------------------------------------------------------------------------
 PROJECT_NAME           = HTML Purifier
-PROJECT_NUMBER         = trunk
+PROJECT_NUMBER         = 1.0.0
 OUTPUT_DIRECTORY       = "C:/Documents and Settings/Edward/My Documents/My Webs/htmlpurifier/docs/doxygen"
 CREATE_SUBDIRS         = NO
 OUTPUT_LANGUAGE        = English
--- a/75
+++ b/75
@@ -17,7 +17,7 @@ these versions:
  - 4.3.9, 4.3.11
  - 4.4.0, 4.4.4
  - 5.0.0, 5.0.4
-  - 5.1.0, 5.1.5
+  - 5.1.0, 5.1.6
 And can confidently say that HTML Purifier should work in all versions
 between and afterwards.  HTML Purifier definitely does not support PHP 4.2,
@@ -26,7 +26,7 @@ any earlier versions.
 I have been unable to get PHP 5.0.5 working on my computer, so if someone
 wants to test that, be my guest.  All tests were done on Windows XP Home,
-but operating system is quite irrelevant in this particular case.
+but operating system should not be a major factor in the library.
@@ -35,7 +35,8 @@ but operating system is quite irrelevant in this particular case.
 The library/ directory must be added to your path: HTML Purifier will not be
 able to find the necessary includes otherwise.  This is as simple as:
-    set_include_path('/path/to/htmlpurifier/library' . PATH_SEPARATOR . get_include_path());
+    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, HTML Purifier is namespaced so unless you have another file named
@@ -45,7 +46,9 @@ Then, it's a simple matter of including the base file:
    require_once 'HTMLPurifier.php';
-...and you're good to go.
+...and you're good to go. The library/ folder contains all the files you need,
 so you can get rid of most of everything else when using the library in a
 production environment.
@@ -58,19 +61,47 @@ is a (short) checklist:
 * Have I specified XHTML 1.0 Transitional as the doctype?
 * Have I specified UTF-8 as the character encoding?
 To find out what these are, browse to your website and view its source code.
 You can figure out the doctype from the a declaration that looks like
    <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"
        "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
 or no doctype.  You can figure out the character encoding by looking for
    <meta http-equiv="Content-type" content="text/html;charset=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.
+the case.  If you can't, well, we might be able to accomodate you (read
 section 3).
 3. Configuring HTML Purifier
 HTML Purifier is designed to run out-of-the-box, but occasionally HTML
 Purifier needs to be told what to do.
 If, for some reason, you are unable to switch to UTF-8 immediately, you can
 switch HTML Purifier's encoding.  Note that the availability of encodings is
 dependent on iconv, and you'll be missing characters if the charset you
 choose doesn't have them.
-    $config = HTMLPurifier_Config::createDefault();
+    $config->set('Core', 'Encoding', /* put your encoding here */);
-    $config->set('Core', 'Encoding', $encoding);
+
 An example usage for Latin-1 websites:
    $config->set('Core', 'Encoding', 'ISO-8859-1');
 For those of you stuck using HTML 4.01 Transitional, you can disable
 XHTML output like this:
    $config->set('Core', 'XHTML', false);
 However, I strongly recommend that you use XHTML. Currently, we can only
 guarantee transitional-complaint output, future versions will also allow strict
 output. There are more configuration directives which can be read about
 here: http://hp.jpsband.org/live/configdoc/plain.html
@@ -88,3 +119,33 @@ Or, if you're using the configuration object:
 That's it.  For more examples, check out docs/examples/.  Also, SLOW gives
 advice on what to do if HTML Purifier is slowing down your application.
 4.   Quick install
 If your website is in UTF-8 and XHTML Transitional, use this code:
 <?php
    set_include_path('/path/to/htmlpurifier/library'
         . PATH_SEPARATOR . get_include_path() );
    require_once 'HTMLPurifier.php';
    $purifier = new HTMLPurifier();
    $clean_html = $purifier->purify($dirty_html);
 ?>
 If your website is in a different encoding or doctype, use this code:
 <?php
    set_include_path('/path/to/htmlpurifier/library'
         . PATH_SEPARATOR . get_include_path() );
    require_once 'HTMLPurifier.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);
 ?>
--- a/26
+++ b/26
@@ -1,6 +1,32 @@
 NEWS ( CHANGELOG and HISTORY )                                     HTMLPurifier
 |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
 1.1.1, released 2006-09-24
 - 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
 - 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)
 - Sample test-settings.php file included
 1.1.0, released 2006-09-16
 - 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.
 - Directive documentation generation using XSLT
 - Table child definition made more flexible, will fix up poorly ordered elements
 - XHTML generation can now be turned off, allowing things like <br>
 - 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
 - Fixed broken numeric entity conversion
 - Malformed UTF-8 and non-SGML character detection and cleaning implemented
--- a/13
+++ b/13
@@ -17,18 +17,23 @@ 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.  Of course, maybe that's a good thing.  If you
+handling the filtered text.  While this may be a good thing, especially if
-don't mind a little extra complexity, you can try...
+you're using a WYSIWYG editor, it can also result in data-loss if a user
 expects a certain to be available but it doesn't.
 2. Caching the filtered output - accept the submitted text and put it
 unaltered into the database, but then also generate a filtered version and
 stash that in the database.  Serve the filtered version to readers, and the
 unaltered version to editors.  If need be, you can invalidate the cache and
 have the cached filtered version be regenerated on the first page view.  Pros?
-Full data retention.  Cons?  It's more complicated.
+Full data retention.  Cons?  It's more complicated, and opens other editors
 up to XSS if they are using a WYSIWYG editor (to fix that, they'd have to
 be able to get their hands on the *really* original text served in plaintext
 mode).
 In short, inbound filtering is almost as simple as outbound filtering, but
 it has some drawbacks which cannot be fixed unless you save both the original
 and the filtered versions.
-There is a third option: profile and optimize HTMLPurifier yourself.  ;-)
+There is a third option: profile and optimize HTMLPurifier yourself.  Be sure
 to tell me if you decide to do that!  ;-)
--- a/29
+++ b/29
@@ -5,33 +5,34 @@ Ongoing
 - Lots of profiling, make it faster!
 - Plugins for major CMSes (very tricky issue)
 1.1 release
 - Directive documentation generation
 - Rewrite table's child definition to be faster, smart, and regexp free
 - Allow HTML 4.01 output (cosmetic changes to the generator)
 1.2 release
 - Additional support for poorly written HTML
    - Implement all non-essential attribute transforms
    - Microsoft Word HTML cleaning (i.e. MsoNormal)
 1.3 release
 - Make URI validation routines tighter (especially mailto)
 - More extensive URI filtering schemes
 - Allow for background-image and list-style-image (see above)
 - Distinguish between different types of URIs, for instance, a mailto URI
   in IMG SRC is nonsensical
 - Error logging for filtering/cleanup procedures
-2.0 release
+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
    - Auto-paragraphing (be sure to leverage fact that we know when things
      shouldn't be paragraphed, such as lists and tables).
    - Lots of documentation and samples
 Unknown release (on a scratch-an-itch basis)
@@ -42,9 +43,9 @@ Unknown release (on a scratch-an-itch basis)
 - 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
 - Pretty-printing HTML (adds dependency of Generator to HTMLDefinition)
 - Non-lossy dumb alternate character encoding transformations, achieved by
   numerically encoding all non-ASCII characters
 Wontfix
 - Non-lossy smart alternate character encoding transformations
 - Pretty-printing HTML, users can use Tidy on the output on entire page
--- a/3
+++ b/3
@@ -16,3 +16,6 @@ trouble.  Therein lies the solution:
 HTML Purifier is perfect for filtering pure-HTML input from WYSIWYG editors.
 Enough said.
 There is a proof-of-concept integration of HTML Purifier with the Mantis
 bugtracker at http://hp.jpsband.org/mantis/
--- a/benchmarks/Lexer.php
+++ b/benchmarks/Lexer.php
@@ -3,15 +3,24 @@
 // emulates inserting a dir called HTMLPurifier into your class dir
 set_include_path(get_include_path() . PATH_SEPARATOR . '../library/');
-require_once 'HTMLPurifier/ConfigDef.php';
+@include_once '../test-settings.php';
 require_once 'HTMLPurifier/Config.php';
 require_once 'HTMLPurifier/Lexer/DirectLex.php';
 require_once 'HTMLPurifier/Lexer/PEARSax3.php';
-$LEXERS = array(
+require_once 'HTMLPurifier/ConfigSchema.php';
-    'DirectLex' => new HTMLPurifier_Lexer_DirectLex(),
+require_once 'HTMLPurifier/Config.php';
-    'PEARSax3'  => new HTMLPurifier_Lexer_PEARSax3()
+
-);
+$LEXERS = array();
 $RUNS = isset($GLOBALS['HTMLPurifierTest']['Runs'])
    ? $GLOBALS['HTMLPurifierTest']['Runs'] : 2; 
 require_once 'HTMLPurifier/Lexer/DirectLex.php';
 $LEXERS['DirectLex'] = new HTMLPurifier_Lexer_DirectLex();
 if (!empty($GLOBALS['HTMLPurifierTest']['PEAR'])) {
    require_once 'HTMLPurifier/Lexer/PEARSax3.php';
    $LEXERS['PEARSax3'] = new HTMLPurifier_Lexer_PEARSax3();
 } else {
    exit('PEAR required to perform benchmark.');
 }
 if (version_compare(PHP_VERSION, '5', '>=')) {
    require_once 'HTMLPurifier/Lexer/DOMLex.php';
@@ -56,9 +65,12 @@ class RowTimer extends Benchmark_Timer
            if ($standard == false) $standard = $v['diff'];
            $perc = $v['diff'] * 100 / $standard;
            $bad_run = ($v['diff'] < 0);
-            $out .= '<td align="right">' . number_format($perc, 2, '.', '') .
+            $out .= '<td align="right"'.
-                   '%</td>';
+                   ($bad_run ? ' style="color:#AAA;"' : '').
                   '>' . number_format($perc, 2, '.', '') .
                   '%</td><td>'.number_format($v['diff'],4,'.','').'</td>';
        }
@@ -79,13 +91,13 @@ function print_lexers() {
 }
 function do_benchmark($name, $document) {
-    global $LEXERS;
+    global $LEXERS, $RUNS;
    $timer = new RowTimer($name);
    $timer->start();
    foreach($LEXERS as $key => $lexer) {
-        $tokens = $lexer->tokenizeHTML($document);
+        for ($i=0; $i<$RUNS; $i++) $tokens = $lexer->tokenizeHTML($document);
        $timer->setMarker($key);
    }
@@ -103,7 +115,7 @@ function do_benchmark($name, $document) {
 <table border="1">
 <tr><th>Case</th><?php
 foreach ($LEXERS as $key => $value) {
-    echo '<th>' . htmlspecialchars($key) . '</th>';
+    echo '<th colspan="2">' . htmlspecialchars($key) . '</th>';
 }
 ?></tr>
 <?php
--- a/benchmarks/ProfileDirectLex.php
+++ b/benchmarks/ProfileDirectLex.php
@@ -2,7 +2,7 @@
 set_include_path(get_include_path() . PATH_SEPARATOR . '../library/');
-require_once 'HTMLPurifier/ConfigDef.php';
+require_once 'HTMLPurifier/ConfigSchema.php';
 require_once 'HTMLPurifier/Config.php';
 require_once 'HTMLPurifier/Lexer/DirectLex.php';
--- a/configdoc/generate.php
+++ b/configdoc/generate.php
@@ -0,0 +1,214 @@
 <?php
 /**
 * Generates XML and HTML documents describing configuration.
 */
 /*
 TODO:
 - make XML format richer (see below)
 - extend XSLT transformation (see the corresponding XSLT file)
 - allow generation of packaged docs that can be easily moved
 - multipage documentation
 - determine how to multilingualize
 - factor out code into classes
 - generate a table of contents
 */
 // ---------------------------------------------------------------------------
 // Check and configure environment
 if (version_compare('5', PHP_VERSION, '>')) exit('Requires PHP 5 or higher.');
 error_reporting(E_ALL);
 // ---------------------------------------------------------------------------
 // Include HTML Purifier library
 set_include_path('../library' . PATH_SEPARATOR . get_include_path());
 require_once 'HTMLPurifier.php';
 // ---------------------------------------------------------------------------
 // Setup convenience functions
 function appendHTMLDiv($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.';
 }
 ?>
--- a/configdoc/styles/plain.css
+++ b/configdoc/styles/plain.css
@@ -0,0 +1,7 @@
 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;}
--- a/configdoc/styles/plain.xsl
+++ b/configdoc/styles/plain.xsl
@@ -0,0 +1,105 @@
 <?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>
--- a/docs/code-quality.txt
+++ b/docs/code-quality.txt
@@ -11,25 +11,24 @@ profiling.
 Here we go:
 AttrDef
-    Class - doesn't support Unicode characters, uses regular expressions
+    Class - doesn't support Unicode characters (fringe); uses regular
-    Lang - code duplication, premature optimization, doesn't consult official
+        expressions
-        lists
+    Lang - code duplication; premature optimization; doesn't consult official
-    Pixels/Length/MultiLength - implemented according to HTML spec (excludes
+        lists (fringe)
-        code reuse in CSS)
+    Length - easily mistaken for CSSLength
-    URI - multiple regular expressions, needs host validation routines factored
+    URI - multiple regular expressions; needs host validation routines factored
-        out for mailto scheme, IPv6 validation is broken (fringe), unintuitive
+        out for mailto scheme; missing validation for query; fragment and path,
        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, non-validating
+AttrTransform - doesn't accept AttrContext
-ChildDef - not-allowed nodes translated to text, likely invalid handling
+Config - "load configuration" hooks missing, rich set* accessors missing
-Config - "load configuration" hooks missing, rich set* accessors missing,
+ConfigSchema - redefinition is a mess
    needs redefined relationship with the definitions
 Strategy
    FixNesting - cannot bubble nodes out of structures
    MakeWellFormed - insufficient automatic closing definitions (check HTML
-        spec for optional end tags).
+        spec for optional end tags, also, closing based on type (block/inline)
        might be efficient).
    RemoveForeignElements - should be run in parallel with MakeWellFormed
 URIScheme - needs to have callable generic checks
    ftp - missing typecode check
--- a/docs/config.txt
+++ b/docs/config.txt
@@ -17,18 +17,9 @@ are passed.  These classes are: HTMLPurifier::*, Generator::generateFromTokens
 and Lexer::tokenizeHTML.  However, whenever a valid configuration object
 is defined, that object should be used.
-- the following is projected changes to the configuration system --
+In relation to HTMLDefinition and CSSDefinition, there is a special class
-
+of directives that influence the *construction* of the Definition object.
-In relation to HTMLDefinition and CSSDefinition, there are going to be some
+A standard call pattern would look like:
 major structural changes to enable the easy configuration of these objects.
 Due to the intricacy of these objects, it's not feasible to ask an average
 user to twiddle around with an element and its 20 other dependencies.  However,
 these objects are the only possible point where change could occur in the
 context of configuration.
 The solution is to introduce 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)
--- a/docs/dtd/xhtml1-purified.dtd
+++ b/docs/dtd/xhtml1-purified.dtd
@@ -1,272 +0,0 @@
 <!-- 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
  >
--- a/docs/examples/demo.php
+++ b/docs/examples/demo.php
@@ -21,7 +21,9 @@ if (!empty($_POST['html'])) {
    $html = get_magic_quotes_gpc() ? stripslashes($_POST['html']) : $_POST['html'];
-    $purifier = new HTMLPurifier();
+    $config = HTMLPurifier_Config::createDefault();
    $config->set('Core', 'TidyFormat', !empty($_POST['tidy']));
    $purifier = new HTMLPurifier($config);
    $pure_html = $purifier->purify($html);
 ?>
@@ -65,6 +67,8 @@ if (isset($html)) {
            HTMLPurifier_Encoder::cleanUTF8($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>
--- a/docs/optimization.txt
+++ b/docs/optimization.txt
@@ -2,9 +2,10 @@
 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 though!
+they turn out to be slow.  Be sure not to prematurely optimize: if you get
 that itch, put it here!
- - Make Tokens Flyweights
+ - Make Tokens Flyweights (may prove problematic, probably not worth it)
 - Rewrite regexps into PHP code
 - Serialize the Definition object
 - Batch regexp validation (do as many per function call as possible)
--- a/docs/progress.html
+++ b/docs/progress.html
@@ -86,7 +86,7 @@ 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, target milestone 1.0</td></tr>
+<tr class="css1 impl-yes"><td>list-style</td><td>SHORTHAND</td></tr>
 <tr class="css1 impl-yes"><td>margin</td><td>MULTIPLE</td></tr>
 <tr class="css1 impl-yes"><td>margin-*</td><td>COMPOSITE(&lt;length&gt;,
    &lt;percentage&gt;, auto)</td></tr>
@@ -134,7 +134,7 @@ 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 1.3</td></tr>
+<tr class="danger css1"><td>background-image</td><td>Dangerous, target milestone 1.2</td></tr>
 <tr class="css1"><td>background-attachment</td><td>ENUM(scroll, fixed),
    Depends on background-image</td></tr>
 <tr class="css1"><td>background-position</td><td>Depends on background-image</td></tr>
@@ -144,7 +144,7 @@ thead th {text-align:left;padding:0.1em;background-color:#EEE;}
    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 1.3</td></tr>
+<tr class="danger css1"><td>list-style-image</td><td>Dangerous? Target milestone 1.2</td></tr>
 <tr class="impl-no"><td>max-height</td><td rowspan="4">No IE 5/6</td></tr>
 <tr class="impl-no"><td>min-height</td></tr>
 <tr class="impl-no"><td>max-width</td></tr>
@@ -254,7 +254,7 @@ Mozilla on inside and needs -moz-outline, no IE support.</td></tr>
 </tbody>
 <tbody>
-<tr><th colspan="3">Transform, target milestone 1.2</th></tr>
+<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>
--- a/docs/security.txt
+++ b/docs/security.txt
@@ -6,35 +6,43 @@ 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. UTF-8. Currently, the parser runs under the assumption that it is dealing
+1. Character Encoding: 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, you should switch. Now. Make sure any input is
+your character encoding, make sure you configure HTML Purifier or switch
-properly converted to UTF-8, or the parser will mangle it badly
+to UTF-8. Now. Also, make sure any input is properly converted to UTF-8, or
-(though it won't be a security risk if you're outputting it as UTF-8 though).
+the parser will mangle it badly (though it won't be a security risk if you're
-We will be adding out-of-the-box support for the other major character
+outputting it as UTF-8 though).  Character encoding is, in general, a knotty
-encodings shortly.
+issue, but do yourself a favor and learn about it:
 <http://www.joelonsoftware.com/articles/Unicode.html>
-2. XHTML 1.0 Transitional. This is what the parser is outputting. For the most
+2. Doctype: 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.
+this may be configurable in the future.  Do you want standards compliance?
 The doctype is a good place to start.
-3. IDs. They need to be unique, but without some knowledge of the
+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.
-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.
+can be quite useful) can't mess up your layout. Once again, we may want to
 disable this by default to protect lazy developers.
--- a/docs/spec.txt
+++ b/docs/spec.txt
@@ -54,4 +54,4 @@ 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.
+be changing in the future with the addition of levels of filtering.
--- a/library/HTMLPurifier.php
+++ b/library/HTMLPurifier.php
@@ -18,7 +18,7 @@
 * 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_ConfigDef and HTMLPurifier_Config.
+ * HTMLPurifier_ConfigSchema and HTMLPurifier_Config.
 */
 /*
@@ -40,10 +40,12 @@
    Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301  USA
 */
-require_once 'HTMLPurifier/ConfigDef.php';
+// almost every class has an undocumented dependency to these, so make sure
 // they get included
 require_once 'HTMLPurifier/ConfigSchema.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';
--- a/library/HTMLPurifier/AttrContext.php
+++ b/library/HTMLPurifier/AttrContext.php
@@ -3,10 +3,10 @@
 /**
 * Internal data-structure used in attribute validation to accumulate state.
 * 
- * All it is is a data-structure that holds objects that accumulate state, like
+ * This is a data-structure that holds objects that accumulate state, like
- * HTMLPurifier_IDAccumulator.
+ * HTMLPurifier_IDAccumulator. It's better than using globals!
 * 
- * @param Many functions that accept this object have it as a mandatory
+ * @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
--- a/library/HTMLPurifier/AttrDef.php
+++ b/library/HTMLPurifier/AttrDef.php
@@ -15,6 +15,12 @@ require_once 'HTMLPurifier/AttrContext.php';
 class HTMLPurifier_AttrDef
 {
    /**
     * Tells us whether or not an HTML attribute is minimized. Only the
     * boolean attribute vapourware would use this.
     */
    var $minimized = false;
    /**
     * Abstract function defined for functions that validate and clean strings.
     * 
--- a/library/HTMLPurifier/AttrDef/CSS.php
+++ b/library/HTMLPurifier/AttrDef/CSS.php
@@ -28,6 +28,8 @@ class HTMLPurifier_AttrDef_CSS extends HTMLPurifier_AttrDef
            if (!$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
            if (strtolower(trim($value)) !== 'inherit') {
--- a/library/HTMLPurifier/AttrDef/Host.php
+++ b/library/HTMLPurifier/AttrDef/Host.php
@@ -11,9 +11,14 @@ class HTMLPurifier_AttrDef_Host extends HTMLPurifier_AttrDef
 {
    /**
-     * Instances of HTMLPurifier_AttrDef_IPv4 and HTMLPurifier_AttrDef_IPv6
+     * Instance of HTMLPurifier_AttrDef_IPv4 sub-validator
     */
-    var $ipv4, $ipv6;
+    var $ipv4;
    /**
     * Instance of HTMLPurifier_AttrDef_IPv6 sub-validator
     */
    var $ipv6;
    function HTMLPurifier_AttrDef_Host() {
        $this->ipv4 = new HTMLPurifier_AttrDef_IPv4();
--- a/library/HTMLPurifier/AttrDef/URI.php
+++ b/library/HTMLPurifier/AttrDef/URI.php
@@ -5,7 +5,7 @@ require_once 'HTMLPurifier/URIScheme.php';
 require_once 'HTMLPurifier/URISchemeRegistry.php';
 require_once 'HTMLPurifier/AttrDef/Host.php';
-HTMLPurifier_ConfigDef::define(
+HTMLPurifier_ConfigSchema::define(
    'URI', 'DefaultScheme', 'http', 'string',
    'Defines through what scheme the output will be served, in order to '.
    'select the proper object validator when no scheme information is present.'
@@ -36,13 +36,13 @@ 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 = '!^'.
+        $r_URI = '!'.
-            '(([^:/?#<>]+):)?'. // 2. Scheme
+            '(([^:/?#<>\'"]+):)?'. // 2. Scheme
-            '(//([^/?#<>]*))?'. // 4. Authority
+            '(//([^/?#<>\'"]*))?'. // 4. Authority
-            '([^?#<>]*)'.       // 5. Path
+            '([^?#<>\'"]*)'.       // 5. Path
-            '(\?([^#<>]*))?'.   // 7. Query
+            '(\?([^#<>\'"]*))?'.   // 7. Query
-            '(#([^<>]*))?'.     // 8. Fragment
+            '(#([^<>\'"]*))?'.     // 8. Fragment
-            '$!';
+            '!';
        $matches = array();
        $result = preg_match($r_URI, $uri, $matches);
--- a/library/HTMLPurifier/AttrTransform/BdoDir.php
+++ b/library/HTMLPurifier/AttrTransform/BdoDir.php
@@ -4,13 +4,13 @@ require_once 'HTMLPurifier/AttrTransform.php';
 // this MUST be placed in post, as it assumes that any value in dir is valid
-HTMLPurifier_ConfigDef::define(
+HTMLPurifier_ConfigSchema::define(
    'Attr', 'DefaultTextDir', 'ltr', 'string',
    '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_ConfigDef::defineAllowedValues(
+HTMLPurifier_ConfigSchema::defineAllowedValues(
    'Attr', 'DefaultTextDir', array( 'ltr', 'rtl' )
 );
--- a/library/HTMLPurifier/AttrTransform/ImgRequired.php
+++ b/library/HTMLPurifier/AttrTransform/ImgRequired.php
@@ -4,7 +4,7 @@ require_once 'HTMLPurifier/AttrTransform.php';
 // must be called POST validation
-HTMLPurifier_ConfigDef::define(
+HTMLPurifier_ConfigSchema::define(
    'Attr', 'DefaultInvalidImage', '', 'string',
    '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 '.
@@ -12,7 +12,7 @@ HTMLPurifier_ConfigDef::define(
    'not possible right now.'
 );
-HTMLPurifier_ConfigDef::define(
+HTMLPurifier_ConfigSchema::define(
    'Attr', 'DefaultInvalidImageAlt', 'Invalid image', 'string',
    '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 '.
--- a/library/HTMLPurifier/ChildDef.php
+++ b/library/HTMLPurifier/ChildDef.php
@@ -5,14 +5,7 @@
 // false = delete parent node and all children
 // array(...) = replace children nodes with these
-// this is the hardest one to implement. We'll use fancy regexp tricks
+HTMLPurifier_ConfigSchema::define(
 // 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, 'bool',
    '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 '.
@@ -62,9 +55,7 @@ class HTMLPurifier_ChildDef
 * 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.  Table is the only
+ *          it will only give a bool return value.
 *          child definition that uses this class, and we ought to give
 *          it a dedicated one.
 */
 class HTMLPurifier_ChildDef_Custom extends HTMLPurifier_ChildDef
 {
@@ -307,4 +298,141 @@ 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;
    }
 }
 ?>
--- a/library/HTMLPurifier/Config.php
+++ b/library/HTMLPurifier/Config.php
@@ -21,7 +21,7 @@ class HTMLPurifier_Config
    var $conf;
    /**
-     * Reference HTMLPurifier_ConfigDef for value checking
+     * Reference HTMLPurifier_ConfigSchema for value checking
     */
    var $def;
@@ -36,7 +36,7 @@ class HTMLPurifier_Config
    var $css_definition;
    /**
-     * @param $definition HTMLPurifier_ConfigDef that defines what directives
+     * @param $definition HTMLPurifier_ConfigSchema that defines what directives
     *                    are allowed.
     */
    function HTMLPurifier_Config(&$definition) {
@@ -49,7 +49,7 @@ class HTMLPurifier_Config
     * @return Default HTMLPurifier_Config object.
     */
    function createDefault() {
-        $definition =& HTMLPurifier_ConfigDef::instance();
+        $definition =& HTMLPurifier_ConfigSchema::instance();
        $config = new HTMLPurifier_Config($definition);
        return $config;
    }
@@ -80,6 +80,8 @@ class HTMLPurifier_Config
                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])) {
@@ -93,8 +95,6 @@ class HTMLPurifier_Config
                }
            }
        }
        $value = $this->def->validate($value,
                                      $this->def->info[$namespace][$key]->type);
        if ($value === null) {
            trigger_error('Value is of invalid type', E_USER_WARNING);
            return;
--- a/library/HTMLPurifier/ConfigSchema.php
+++ b/library/HTMLPurifier/ConfigSchema.php
@@ -2,9 +2,23 @@
 /**
 * Configuration definition, defines directives and their defaults.
- * @todo Build documentation generation capabilities.
+ * @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_ConfigDef {
+class HTMLPurifier_ConfigSchema {
    /**
     * Defaults of the directives and namespaces.
@@ -26,15 +40,15 @@ class HTMLPurifier_ConfigDef {
     * Lookup table of allowed types.
     */
    var $types = array(
-        'string'    => true,
+        'string'    => 'String',
-        'istring'   => true,
+        'istring'   => 'Case-insensitive string',
-        'int'       => true,
+        'int'       => 'Integer',
-        'float'     => true,
+        'float'     => 'Float',
-        'bool'      => true,
+        'bool'      => 'Boolean',
-        'lookup'    => true,
+        'lookup'    => 'Lookup array',
-        'list'      => true,
+        'list'      => 'Array list',
-        'hash'      => true,
+        'hash'      => 'Associative array',
-        'mixed'     => true
+        'mixed'     => 'Mixed'
    );
    /**
@@ -46,6 +60,7 @@ class HTMLPurifier_ConfigDef {
        $this->defineNamespace('URI', 'Features regarding Uniform Resource Identifiers.');
        $this->defineNamespace('HTML', 'Configuration regarding allowed HTML.');
        $this->defineNamespace('CSS', 'Configuration regarding allowed CSS.');
        $this->defineNamespace('Test', 'Developer testing configuration for our unit tests.');
    }
    /**
@@ -56,7 +71,7 @@ class HTMLPurifier_ConfigDef {
        if ($prototype !== null) {
            $instance = $prototype;
        } elseif ($instance === null || $prototype === true) {
-            $instance = new HTMLPurifier_ConfigDef();
+            $instance = new HTMLPurifier_ConfigSchema();
            $instance->initialize();
        }
        return $instance;
@@ -65,9 +80,6 @@ class HTMLPurifier_ConfigDef {
    /**
     * Defines a directive for configuration
     * @warning Will fail of directive's namespace is defined
     * @todo Collect information on description and allow redefinition
     *       so that multiple files can register a dependency on a
     *       configuration directive.
     * @param $namespace Namespace the directive is in
     * @param $name Key of directive
     * @param $default Default value of directive
@@ -79,12 +91,17 @@ class HTMLPurifier_ConfigDef {
        $namespace, $name, $default, $type, 
        $description
    ) {
-        $def =& HTMLPurifier_ConfigDef::instance();
+        $def =& HTMLPurifier_ConfigSchema::instance();
        if (!isset($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 ||
@@ -121,17 +138,19 @@ class HTMLPurifier_ConfigDef {
     * @param $description Description of the namespace
     */
    function defineNamespace($namespace, $description) {
-        $def =& HTMLPurifier_ConfigDef::instance();
+        $def =& HTMLPurifier_ConfigSchema::instance();
        if (isset($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();
-        $backtrace = debug_backtrace();
+        $def->info_namespace[$namespace]->description = $description;
        $file = $def->mungeFilename($backtrace[0]['file']);
        $line = $backtrace[0]['line'];
        $def->info_namespace[$namespace]->addDescription($file,$line,$description);
        $def->defaults[$namespace] = array();
    }
@@ -146,7 +165,7 @@ class HTMLPurifier_ConfigDef {
     * @param $real Value aliased value will be converted into
     */
    function defineValueAliases($namespace, $name, $aliases) {
-        $def =& HTMLPurifier_ConfigDef::instance();
+        $def =& HTMLPurifier_ConfigSchema::instance();
        if (!isset($def->info[$namespace][$name])) {
            trigger_error('Cannot set value alias for non-existant directive',
                E_USER_ERROR);
@@ -176,7 +195,7 @@ class HTMLPurifier_ConfigDef {
     * @param $allowed_values Arraylist of allowed values
     */
    function defineAllowedValues($namespace, $name, $allowed_values) {
-        $def =& HTMLPurifier_ConfigDef::instance();
+        $def =& HTMLPurifier_ConfigSchema::instance();
        if (!isset($def->info[$namespace][$name])) {
            trigger_error('Cannot define allowed values for undefined directive',
                E_USER_ERROR);
@@ -255,27 +274,19 @@ class HTMLPurifier_ConfigDef {
 /**
 * Base class for configuration entity
 */
-class HTMLPurifier_ConfigEntity
+class HTMLPurifier_ConfigEntity {}
 {
    /**
     * 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;
    }
 }
 /**
 * Structure object describing of a namespace
 */
-class HTMLPurifier_ConfigEntity_Namespace extends HTMLPurifier_ConfigEntity {}
+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.
@@ -307,6 +318,19 @@ class HTMLPurifier_ConfigEntity_Directive extends HTMLPurifier_ConfigEntity
     *      - mixed (anything goes)
     */
    var $type = 'mixed';
    /**
     * Plaintext descriptions of the configuration entity is. Organized by
     * file and line number, so multiple descriptions are allowed.
     */
    var $descriptions = array();
    /**
     * Adds a description to the array
     */
    function addDescription($file, $line, $description) {
        if (!isset($this->descriptions[$file])) $this->descriptions[$file] = array();
        $this->descriptions[$file][$line] = $description;
    }
 }
--- a/library/HTMLPurifier/Encoder.php
+++ b/library/HTMLPurifier/Encoder.php
@@ -2,7 +2,7 @@
 require_once 'HTMLPurifier/EntityLookup.php';
-HTMLPurifier_ConfigDef::define(
+HTMLPurifier_ConfigSchema::define(
    'Core', 'Encoding', 'utf-8', 'istring', 
    'If for some reason you are unable to convert all webpages to UTF-8, '. 
    'you can use this directive as a stop-gap compatibility change to '. 
@@ -17,14 +17,25 @@ HTMLPurifier_ConfigDef::define(
 if ( !function_exists('iconv') ) {
    // only encodings with native PHP support
-    HTMLPurifier_ConfigDef::defineAllowedValues(
+    HTMLPurifier_ConfigSchema::defineAllowedValues(
        'Core', 'Encoding', array(
            'utf-8',
            'iso-8859-1'
        )
    );
    HTMLPurifier_ConfigSchema::defineValueAliases(
        'Core', 'Encoding', array(
            'iso8859-1' => 'iso-8859-1'
        )
    );
 }
 HTMLPurifier_ConfigSchema::define(
    'Test', 'ForceNoIconv', false, 'bool', 
    'When set to true, HTMLPurifier_Encoder will act as if iconv does not '.
    'exist and use only pure PHP implementations.'
 );
 /**
 * A UTF-8 specific character encoder that handles cleaning and transforming.
 */
@@ -77,7 +88,7 @@ class HTMLPurifier_Encoder
        if ($iconv && !$force_php) {
            // do the shortcut way
            $str = @iconv('UTF-8', 'UTF-8//IGNORE', $str);
-            return strtr($str, $non_sgml_chars);;
+            return strtr($str, $non_sgml_chars);
        }
        $mState = 0; // cached expected number of octets after the current octet
@@ -260,9 +271,9 @@ class HTMLPurifier_Encoder
        if ($iconv === null) $iconv = function_exists('iconv');
        $encoding = $config->get('Core', 'Encoding');
        if ($encoding === 'utf-8') return $str;
-        if ($iconv) {
+        if ($iconv && !$config->get('Test', 'ForceNoIconv')) {
            return @iconv($encoding, 'utf-8//IGNORE', $str);
-        } elseif ($encoding === 'iso-8895-1') {
+        } elseif ($encoding === 'iso-8859-1') {
            return @utf8_encode($str);
        }
    }
@@ -277,10 +288,10 @@ class HTMLPurifier_Encoder
        if ($iconv === null) $iconv = function_exists('iconv');
        $encoding = $config->get('Core', 'Encoding');
        if ($encoding === 'utf-8') return $str;
-        if ($iconv) {
+        if ($iconv && !$config->get('Test', 'ForceNoIconv')) {
            return @iconv('utf-8', $encoding . '//IGNORE', $str);
-        } elseif ($encoding === 'iso-8895-1') {
+        } elseif ($encoding === 'iso-8859-1') {
-            return @utf8_encode($str);
+            return @utf8_decode($str);
        }
    }
--- a/library/HTMLPurifier/EntityParser.php
+++ b/library/HTMLPurifier/EntityParser.php
@@ -88,7 +88,6 @@ class HTMLPurifier_EntityParser
     *                  either index 1, 2 or 3 set with a hex value, dec value,
     *                  or string (respectively).
     * @returns Replacement string.
     * @todo Implement string translations
     */
    // +----------+----------+----------+----------+
--- a/library/HTMLPurifier/Generator.php
+++ b/library/HTMLPurifier/Generator.php
@@ -4,7 +4,7 @@
 require_once 'HTMLPurifier/Lexer.php';
-HTMLPurifier_ConfigDef::define(
+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. '.
@@ -15,6 +15,29 @@ HTMLPurifier_ConfigDef::define(
    '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.
 */
@@ -22,11 +45,16 @@ class HTMLPurifier_Generator
 {
    /**
-     * Bool cache of the CleanUTF8DuringGeneration directive.
+     * 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
@@ -38,10 +66,35 @@ class HTMLPurifier_Generator
        $html = '';
        if (!$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;
            }
        }
        return $html;
    }
@@ -61,7 +114,9 @@ class HTMLPurifier_Generator
        } elseif ($token->type == 'empty') {
            $attr = $this->generateAttributes($token->attributes);
-             return '<' . $token->name . ($attr ? ' ' : '') . $attr . ' />';
+             return '<' . $token->name . ($attr ? ' ' : '') . $attr .
                ( $this->_xhtml ? ' /': '' )
                . '>';
        } elseif ($token->type == 'text') {
            return $this->escape($token->data);
@@ -80,6 +135,11 @@ class HTMLPurifier_Generator
    function generateAttributes($assoc_array_of_attributes) {
        $html = '';
        foreach ($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($value).'" ';
        }
        return rtrim($html);
--- a/library/HTMLPurifier/HTMLDefinition.php
+++ b/library/HTMLPurifier/HTMLDefinition.php
@@ -209,8 +209,7 @@ class HTMLPurifier_HTMLDefinition
        $this->info['a']->child    = $e_a_content;
-        $this->info['table']->child = new HTMLPurifier_ChildDef_Custom(
+        $this->info['table']->child = new HTMLPurifier_ChildDef_Table();
            '(caption?, (col*|colgroup*), thead?, tfoot?, (tbody+|tr+))');
        // not a real entity, watch the double underscore
        $e__row = new HTMLPurifier_ChildDef_Required('tr');
--- a/library/HTMLPurifier/Lexer.php
+++ b/library/HTMLPurifier/Lexer.php
@@ -4,12 +4,11 @@ require_once 'HTMLPurifier/Token.php';
 require_once 'HTMLPurifier/Encoder.php';
 require_once 'HTMLPurifier/EntityParser.php';
-HTMLPurifier_ConfigDef::define(
+HTMLPurifier_ConfigSchema::define(
    'Core', 'AcceptFullDocuments', true, 'bool',
    'This parameter determines whether or not the filter should accept full '.
    'HTML documents, not just HTML fragments.  When on, it will '.
-    'drop all sections except the content between body.  Depending on '.
+    'drop all sections except the content between body.'
    'the implementation in use, this may speed up document parse times.'
 );
 /**
--- a/library/HTMLPurifier/Lexer/DOMLex.php
+++ b/library/HTMLPurifier/Lexer/DOMLex.php
@@ -12,15 +12,19 @@ require_once 'HTMLPurifier/TokenFactory.php';
 * documents, it performs twenty times faster than
 * HTMLPurifier_Lexer_DirectLex,and is the default choice for PHP 5. 
 * 
- * @notice
+ * @note Any empty elements will have empty tokens associated with them, even if
 * 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.
 * 
- * @todo Determine DOM's entity parsing behavior, point to local entity files
+ * @note PHP's DOM extension does not actually parse any entities, we use
- *       if necessary.
+ *       our own function to do that.
- * @todo Make div access less fragile, and refrain from preprocessing when
+ * 
- *       HTML tag and friends are already present.
+ * @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
 */
 class HTMLPurifier_Lexer_DOMLex extends HTMLPurifier_Lexer
@@ -87,19 +91,20 @@ class HTMLPurifier_Lexer_DOMLex extends HTMLPurifier_Lexer
            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(
+                $tokens[] = $this->factory->createEmpty($node->tagName, $attr);
                    $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
-                    $this->transformAttrToAssoc($node->attributes)
+                    $attr
                );
            }
            foreach ($node->childNodes as $node) {
--- a/library/HTMLPurifier/Strategy.php
+++ b/library/HTMLPurifier/Strategy.php
@@ -8,7 +8,7 @@
 * features, such as custom tags, custom parsing of text, etc.
 */
-HTMLPurifier_ConfigDef::define(
+HTMLPurifier_ConfigSchema::define(
    'Core', 'EscapeInvalidTags', false, 'bool',
    'When true, invalid tags will be written back to the document as plain '.
    'text.  Otherwise, they are silently dropped.'
--- a/library/HTMLPurifier/Strategy/FixNesting.php
+++ b/library/HTMLPurifier/Strategy/FixNesting.php
@@ -187,6 +187,7 @@ class HTMLPurifier_Strategy_FixNesting extends HTMLPurifier_Strategy
                if (!$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
--- a/library/HTMLPurifier/Strategy/ValidateAttributes.php
+++ b/library/HTMLPurifier/Strategy/ValidateAttributes.php
@@ -3,10 +3,10 @@
 require_once 'HTMLPurifier/Strategy.php';
 require_once 'HTMLPurifier/HTMLDefinition.php';
 require_once 'HTMLPurifier/IDAccumulator.php';
-require_once 'HTMLPurifier/ConfigDef.php';
+require_once 'HTMLPurifier/ConfigSchema.php';
 require_once 'HTMLPurifier/AttrContext.php';
-HTMLPurifier_ConfigDef::define(
+HTMLPurifier_ConfigSchema::define(
    'Attr', 'IDBlacklist', array(), 'list',
    'Array of IDs not allowed in the document.');
--- a/library/HTMLPurifier/URISchemeRegistry.php
+++ b/library/HTMLPurifier/URISchemeRegistry.php
@@ -1,6 +1,6 @@
 <?php
-HTMLPurifier_ConfigDef::define(
+HTMLPurifier_ConfigSchema::define(
    'URI', 'AllowedSchemes', array(
        'http'  => true, // "Hypertext Transfer Protocol", nuf' said
        'https' => true, // HTTP over SSL (Secure Socket Layer)
@@ -16,7 +16,7 @@ HTMLPurifier_ConfigDef::define(
    'prevents XSS attacks from using pseudo-schemes like javascript or mocha.'
 );
-HTMLPurifier_ConfigDef::define(
+HTMLPurifier_ConfigSchema::define(
    'URI', 'OverrideAllowedSchemes', true, 'bool',
    'If this is set to true (which it is by default), you can override '.
    '%URI.AllowedSchemes by simply registering a HTMLPurifier_URIScheme '.
--- a/test-settings.sample.php
+++ b/test-settings.sample.php
@@ -0,0 +1,17 @@
 <?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/';
 ?>
--- a/tests/HTMLPurifier/AttrDef/CSSTest.php
+++ b/tests/HTMLPurifier/AttrDef/CSSTest.php
@@ -92,6 +92,10 @@ class HTMLPurifier_AttrDef_CSSTest extends HTMLPurifier_AttrDefHarness
        $this->assertDef('position:absolute;', false);
        $this->assertDef('background-image:url(javascript:alert\(\));', false);
        // airy input
        $this->assertDef(' font-weight : bold; color : #ff0000',
                         'font-weight:bold;color:#ff0000;');
    }
 }
--- a/tests/HTMLPurifier/AttrDef/URITest.php
+++ b/tests/HTMLPurifier/AttrDef/URITest.php
@@ -158,9 +158,15 @@ class HTMLPurifier_AttrDef_URITest extends HTMLPurifier_AttrDefHarness
        $uri[18] = '/a/b';
        $components[18] = array(null, null, null, '/a/b', null);
-        // it's not allowed, so generic URI should get it
+        // result of malformed tag, gracefully handle error
-        $uri[19] = '<';
+        $uri[19] = 'http://www.google.com/\'>"';
-        $expect_uri[19] = false;
+        $components[19] = array(null, 'www.google.com', null, '/', null);
        $expect_uri[19] = 'http://www.google.com/';
        // test empty
        $uri[20] = '';
        $components[20] = array(null, null, null, '', null);
        $expect_uri[20] = '';
        foreach ($uri as $i => $value) {
--- a/tests/HTMLPurifier/ChildDefTest.php
+++ b/tests/HTMLPurifier/ChildDefTest.php
@@ -1,7 +1,7 @@
 <?php
 require_once 'HTMLPurifier/ChildDef.php';
-require_once 'HTMLPurifier/Lexer.php';
+require_once 'HTMLPurifier/Lexer/DirectLex.php';
 require_once 'HTMLPurifier/Generator.php';
 class HTMLPurifier_ChildDefTest extends UnitTestCase
@@ -12,7 +12,8 @@ class HTMLPurifier_ChildDefTest extends UnitTestCase
    var $gen;
    function HTMLPurifier_ChildDefTest() {
-        $this->lex = HTMLPurifier_Lexer::create();
+        // it is vital that the tags be treated as literally as possible
        $this->lex = new HTMLPurifier_Lexer_DirectLex();
        $this->gen = new HTMLPurifier_Generator();
        parent::UnitTestCase();
    }
@@ -42,28 +43,70 @@ class HTMLPurifier_ChildDefTest extends UnitTestCase
    function test_custom() {
        // the table definition
        $this->def = new HTMLPurifier_ChildDef_Custom(
-            '(caption?, (col*|colgroup*), thead?, tfoot?, (tbody+|tr+))');
+            '(a, b?, c*, d+, (a, b)*)');
        $inputs[0] = '';
        $expect[0] = false;
        $inputs[1] = '<a /><b /><c /><d /><a /><b />';
        $expect[1] = true;
        $inputs[2] = '<a /><d>Dob</d><a /><b>foo</b><a href="moo"><b>foo</b>';
        $expect[2] = true;
        $inputs[3] = '<a /><a />';
        $expect[3] = false;
    }
    function test_table() {
        // currently inactive, awaiting augmentation
        // the table definition
        $this->def = new HTMLPurifier_ChildDef_Table();
        $inputs = $expect = $config = array();
        $inputs[0] = '';
        $expect[0] = false;
-        // we really don't care what's inside, because if it turns out
+        // we're using empty tags to compact the tests: under real circumstances
-        // this tr is illegal, we'll end up re-evaluating the parent node
+        // there would be contents in them
-        // anyway.
+        
-        $inputs[1] = '<tr></tr>';
+        $inputs[1] = '<tr />';
        $expect[1] = true;
-        $inputs[2] = '<caption></caption><col></col><thead></thead>' .
+        $inputs[2] = '<caption /><col /><thead /><tfoot /><tbody>'.
-                     '<tfoot></tfoot><tbody></tbody>';
+            '<tr><td>asdf</td></tr></tbody>';
        $expect[2] = true;
-        $inputs[3] = '<col></col><col></col><col></col><tr></tr>';
+        $inputs[3] = '<col /><col /><col /><tr />';
        $expect[3] = true;
        // mixed up order
        $inputs[4] = '<col /><colgroup /><tbody /><tfoot /><thead /><tr>1</tr><caption /><tr />';
        $expect[4] = '<caption /><col /><colgroup /><thead /><tfoot /><tbody /><tr>1</tr><tr />';
        // duplicates of singles
        // - first caption serves
        // - trailing tfoots/theads get turned into tbodys
        $inputs[5] = '<caption>1</caption><caption /><tbody /><tbody /><tfoot>1</tfoot><tfoot />';
        $expect[5] = '<caption>1</caption><tfoot>1</tfoot><tbody /><tbody /><tbody />';
        // errant text dropped (until bubbling is implemented)
        $inputs[6] = 'foo';
        $expect[6] = false;
        // whitespace sticks to the previous element, last whitespace is
        // stationary
        $inputs[7] = "\n   <tr />\n  <tr />\n ";
        $expect[7] = true;
        $inputs[8] = "\n\t<tbody />\n\t\t<tfoot />\n\t\t\t";
        $expect[8] = "\n\t\t<tfoot />\n\t<tbody />\n\t\t\t";
        $this->assertSeries($inputs, $expect, $config);
    }
--- a/tests/HTMLPurifier/ConfigSchemaTest.php
+++ b/tests/HTMLPurifier/ConfigSchemaTest.php
@@ -1,8 +1,8 @@
 <?php
-require_once 'HTMLPurifier/ConfigDef.php';
+require_once 'HTMLPurifier/ConfigSchema.php';
-class HTMLPurifier_ConfigDefTest extends UnitTestCase
+class HTMLPurifier_ConfigSchemaTest extends UnitTestCase
 {
    var $old_copy;
@@ -13,16 +13,16 @@ class HTMLPurifier_ConfigDefTest extends UnitTestCase
        // you pay for using Singletons. Good thing we can overload it.
        // first, let's get a clean copy to do tests
-        $our_copy = new HTMLPurifier_ConfigDef();
+        $our_copy = new HTMLPurifier_ConfigSchema();
        // get the old copy
-        $this->old_copy = HTMLPurifier_ConfigDef::instance();
+        $this->old_copy = HTMLPurifier_ConfigSchema::instance();
        // put in our copy, and reassign to the REAL reference
-        $this->our_copy =& HTMLPurifier_ConfigDef::instance($our_copy);
+        $this->our_copy =& HTMLPurifier_ConfigSchema::instance($our_copy);
    }
    function tearDown() {
        // testing is done, restore the old copy
-        HTMLPurifier_ConfigDef::instance($this->old_copy);
+        HTMLPurifier_ConfigSchema::instance($this->old_copy);
    }
    function testNormal() {
@@ -31,9 +31,9 @@ class HTMLPurifier_ConfigDefTest extends UnitTestCase
        // define a namespace
        $description = 'Configuration that is always available.';
-        HTMLPurifier_ConfigDef::defineNamespace(
+        HTMLPurifier_ConfigSchema::defineNamespace(
            'Core', $description
-        ); $line = __LINE__;
+        );
        $this->assertIdentical($this->our_copy->defaults, array(
            'Core' => array()
        ));
@@ -41,7 +41,7 @@ class HTMLPurifier_ConfigDefTest extends UnitTestCase
            'Core' => array()
        ));
        $namespace = new HTMLPurifier_ConfigEntity_Namespace();
-        $namespace->addDescription($file, $line, $description);
+        $namespace->description = $description;
        $this->assertIdentical($this->our_copy->info_namespace, array(
            'Core' => $namespace
        ));
@@ -50,7 +50,7 @@ class HTMLPurifier_ConfigDefTest extends UnitTestCase
        // define a directive
        $description = 'This is a description of the directive.';
-        HTMLPurifier_ConfigDef::define(
+        HTMLPurifier_ConfigSchema::define(
            'Core', 'Name', 'default value', 'string',
            $description
        ); $line = __LINE__;
@@ -71,7 +71,7 @@ class HTMLPurifier_ConfigDefTest extends UnitTestCase
        // define a directive in an undefined namespace
-        HTMLPurifier_ConfigDef::define(
+        HTMLPurifier_ConfigSchema::define(
            'Extension', 'Name', false, 'bool',
            'This is for an extension, but we have not defined its namespace!'
        );
@@ -83,7 +83,7 @@ class HTMLPurifier_ConfigDefTest extends UnitTestCase
        // redefine a value in a valid manner
        $description = 'Alternative configuration definition';
-        HTMLPurifier_ConfigDef::define(
+        HTMLPurifier_ConfigSchema::define(
            'Core', 'Name', 'default value', 'string',
            $description
        ); $line = __LINE__;
@@ -98,7 +98,7 @@ class HTMLPurifier_ConfigDefTest extends UnitTestCase
        // redefine a directive in an invalid manner
-        HTMLPurifier_ConfigDef::define(
+        HTMLPurifier_ConfigSchema::define(
            'Core', 'Name', 'different default', 'string',
            'Inconsistent default or type, cannot redefine'
        );
@@ -109,7 +109,7 @@ class HTMLPurifier_ConfigDefTest extends UnitTestCase
        // make an enumeration
-        HTMLPurifier_ConfigDef::defineAllowedValues(
+        HTMLPurifier_ConfigSchema::defineAllowedValues(
            'Core', 'Name', array(
                'Real Value',
                'Real Value 2'
@@ -128,7 +128,7 @@ class HTMLPurifier_ConfigDefTest extends UnitTestCase
        // redefinition of enumeration is cumulative
-        HTMLPurifier_ConfigDef::defineAllowedValues(
+        HTMLPurifier_ConfigSchema::defineAllowedValues(
            'Core', 'Name', array(
                'Real Value 3',
            )
@@ -143,7 +143,7 @@ class HTMLPurifier_ConfigDefTest extends UnitTestCase
        // cannot define enumeration for undefined directive
-        HTMLPurifier_ConfigDef::defineAllowedValues(
+        HTMLPurifier_ConfigSchema::defineAllowedValues(
            'Core', 'Foobar', array(
                'Real Value 9',
            )
@@ -155,7 +155,7 @@ class HTMLPurifier_ConfigDefTest extends UnitTestCase
        // test defining value aliases for an enumerated value
-        HTMLPurifier_ConfigDef::defineValueAliases(
+        HTMLPurifier_ConfigSchema::defineValueAliases(
            'Core', 'Name', array(
                'Aliased Value' => 'Real Value'
            )
@@ -170,7 +170,7 @@ class HTMLPurifier_ConfigDefTest extends UnitTestCase
        // redefine should be cumulative
-        HTMLPurifier_ConfigDef::defineValueAliases(
+        HTMLPurifier_ConfigSchema::defineValueAliases(
            'Core', 'Name', array(
                'Aliased Value 2' => 'Real Value 2'
            )
@@ -185,7 +185,7 @@ class HTMLPurifier_ConfigDefTest extends UnitTestCase
        // cannot create alias to not-allowed value
-        HTMLPurifier_ConfigDef::defineValueAliases(
+        HTMLPurifier_ConfigSchema::defineValueAliases(
            'Core', 'Name', array(
                'Aliased Value 3' => 'Invalid Value'
            )
@@ -197,7 +197,7 @@ class HTMLPurifier_ConfigDefTest extends UnitTestCase
        // cannot create alias for already allowed value
-        HTMLPurifier_ConfigDef::defineValueAliases(
+        HTMLPurifier_ConfigSchema::defineValueAliases(
            'Core', 'Name', array(
                'Real Value' => 'Real Value 2'
            )
@@ -209,7 +209,7 @@ class HTMLPurifier_ConfigDefTest extends UnitTestCase
        // define a directive with an invalid type
-        HTMLPurifier_ConfigDef::define(
+        HTMLPurifier_ConfigSchema::define(
            'Core', 'Foobar', false, 'omen',
            'Omen is not a valid type, so we reject this.'
        );
@@ -221,7 +221,7 @@ class HTMLPurifier_ConfigDefTest extends UnitTestCase
        // define a directive with inconsistent type
-        HTMLPurifier_ConfigDef::define(
+        HTMLPurifier_ConfigSchema::define(
            'Core', 'Foobaz', 10, 'string',
            'If we say string, we should mean it, not integer 10.'
        );
@@ -231,6 +231,24 @@ class HTMLPurifier_ConfigDefTest extends UnitTestCase
        $this->swallowErrors();
        // define a directive with bad characters
        HTMLPurifier_ConfigSchema::define(
            'Core', 'Core.Attr', 10, 'int',
            'No periods! >:-('
        );
        $this->assertError('Directive name must be alphanumeric');
        $this->assertNoErrors();
        $this->swallowErrors();
        // define a namespace with bad characters
        HTMLPurifier_ConfigSchema::defineNamespace(
            'Foobar&Gromit', $description
        );
        $this->assertError('Namespace name must be alphanumeric');
        $this->assertNoErrors();
        $this->swallowErrors();
    }
--- a/tests/HTMLPurifier/ConfigTest.php
+++ b/tests/HTMLPurifier/ConfigTest.php
@@ -8,37 +8,43 @@ class HTMLPurifier_ConfigTest extends UnitTestCase
    var $our_copy, $old_copy;
    function setUp() {
-        $our_copy = new HTMLPurifier_ConfigDef();
+        $our_copy = new HTMLPurifier_ConfigSchema();
-        $this->old_copy = HTMLPurifier_ConfigDef::instance();
+        $this->old_copy = HTMLPurifier_ConfigSchema::instance();
-        $this->our_copy =& HTMLPurifier_ConfigDef::instance($our_copy);
+        $this->our_copy =& HTMLPurifier_ConfigSchema::instance($our_copy);
    }
    function tearDown() {
-        HTMLPurifier_ConfigDef::instance($this->old_copy);
+        HTMLPurifier_ConfigSchema::instance($this->old_copy);
    }
    function test() {
-        HTMLPurifier_ConfigDef::defineNamespace('Core', 'Corestuff');
+        HTMLPurifier_ConfigSchema::defineNamespace('Core', 'Corestuff');
-        HTMLPurifier_ConfigDef::defineNamespace('Attr', 'Attributes');
+        HTMLPurifier_ConfigSchema::defineNamespace('Attr', 'Attributes');
-        HTMLPurifier_ConfigDef::defineNamespace('Extension', 'Extensible');
+        HTMLPurifier_ConfigSchema::defineNamespace('Extension', 'Extensible');
-        HTMLPurifier_ConfigDef::define(
+        HTMLPurifier_ConfigSchema::define(
            'Core', 'Key', false, 'bool', 'A boolean directive.'
        );
-        HTMLPurifier_ConfigDef::define(
+        HTMLPurifier_ConfigSchema::define(
            'Attr', 'Key', 42, 'int', 'An integer directive.'
        );
-        HTMLPurifier_ConfigDef::define(
+        HTMLPurifier_ConfigSchema::define(
            'Extension', 'Pert', 'foo', 'string', 'A string directive.'
        );
        HTMLPurifier_ConfigSchema::define(
            'Core', 'Encoding', 'utf-8', 'istring', 'Case insensitivity!'
        );
-        HTMLPurifier_ConfigDef::defineAllowedValues(
+        HTMLPurifier_ConfigSchema::defineAllowedValues(
            'Extension', 'Pert', array('foo', 'moo')
        );
-        HTMLPurifier_ConfigDef::defineValueAliases(
+        HTMLPurifier_ConfigSchema::defineValueAliases(
            'Extension', 'Pert', array('cow' => 'moo')
        );
        HTMLPurifier_ConfigSchema::defineAllowedValues(
            'Core', 'Encoding', array('utf-8', 'iso-8859-1')
        );
        $config = HTMLPurifier_Config::createDefault();
@@ -80,6 +86,11 @@ class HTMLPurifier_ConfigTest extends UnitTestCase
        $this->assertNoErrors();
        $this->assertIdentical($config->get('Extension', 'Pert'), 'moo');
        // case-insensitive attempt to set value that is allowed
        $config->set('Core', 'Encoding', 'ISO-8859-1');
        $this->assertNoErrors();
        $this->assertIdentical($config->get('Core', 'Encoding'), 'iso-8859-1');
    }
 }
--- a/tests/HTMLPurifier/EncoderTest.php
+++ b/tests/HTMLPurifier/EncoderTest.php
@@ -14,8 +14,8 @@ class HTMLPurifier_EncoderTest extends UnitTestCase
    function assertCleanUTF8($string, $expect = null) {
        if ($expect === null) $expect = $string;
-        $this->assertIdentical($this->Encoder->cleanUTF8($string), $expect);
+        $this->assertIdentical($this->Encoder->cleanUTF8($string), $expect, 'iconv: %s');
-        $this->assertIdentical($this->Encoder->cleanUTF8($string, true), $expect);
+        $this->assertIdentical($this->Encoder->cleanUTF8($string, true), $expect, 'PHP: %s');
    }
    function test_cleanUTF8() {
@@ -46,6 +46,14 @@ class HTMLPurifier_EncoderTest extends UnitTestCase
            $this->Encoder->convertToUTF8("\xF6", $config),
            "\xC3\xB6"
        );
        $config->set('Test', 'ForceNoIconv', true);
        $this->assertIdentical(
            $this->Encoder->convertToUTF8("\xF6", $config),
            "\xC3\xB6"
        );
    }
    function test_convertFromUTF8() {
@@ -64,6 +72,14 @@ class HTMLPurifier_EncoderTest extends UnitTestCase
            $this->Encoder->convertFromUTF8("\xC3\xB6", $config),
            "\xF6"
        );
        $config->set('Test', 'ForceNoIconv', true);
        $this->assertIdentical(
            $this->Encoder->convertFromUTF8("\xC3\xB6", $config),
            "\xF6"
        );
    }
 }
--- a/tests/HTMLPurifier/GeneratorTest.php
+++ b/tests/HTMLPurifier/GeneratorTest.php
@@ -52,10 +52,8 @@ class HTMLPurifier_GeneratorTest extends UnitTestCase
        $inputs[7] = new HTMLPurifier_Token_Text($theta_char);
        $expect[7] = $theta_char;
        $default_config = HTMLPurifier_Config::createDefault();
        foreach ($inputs as $i => $input) {
-            if (!isset($config[$i])) $config[$i] = $default_config;
+            $result = $this->gen->generateFromToken($input);
            $result = $this->gen->generateFromToken($input, $config[$i]);
            $this->assertEqual($result, $expect[$i]);
            paintIf($result, $result != $expect[$i]);
        }
@@ -122,6 +120,56 @@ class HTMLPurifier_GeneratorTest extends UnitTestCase
    }
    var $config;
    function assertGeneration($tokens, $expect) {
        $result = $this->gen->generateFromTokens($tokens, $this->config);
        // normalized newlines, this probably should be put somewhere else
        $result = str_replace("\r\n", "\n", $result);
        $result = str_replace("\r", "\n", $result);
        $this->assertEqual($expect, $result);
    }
    function test_generateFromTokens_XHTMLoff() {
        $this->config = HTMLPurifier_Config::createDefault();
        $this->config->set('Core', 'XHTML', false);
        // omit trailing slash
        $this->assertGeneration(
            array( new HTMLPurifier_Token_Empty('br') ),
            '<br>'
        );
        // there should be a test for attribute minimization, but it is
        // impossible for something like that to happen due to our current
        // definitions! fix it later
        // namespaced attributes must be dropped
        $this->assertGeneration(
            array( new HTMLPurifier_Token_Start('p', array('xml:lang'=>'fr')) ),
            '<p>'
        );
    }
    function test_generateFromTokens_TidyFormat() {
        // abort test if tidy isn't loaded
        if (!extension_loaded('tidy')) return;
        $this->config = HTMLPurifier_Config::createDefault();
        $this->config->set('Core', 'TidyFormat', true);
        // nice wrapping please
        $this->assertGeneration(
            array(
                new HTMLPurifier_Token_Start('div'),
                new HTMLPurifier_Token_Text('Text'),
                new HTMLPurifier_Token_End('div')
            ),
            "<div>\n  Text\n</div>\n"
        );
    }
 }
 ?>
--- a/tests/HTMLPurifier/Test.php
+++ b/tests/HTMLPurifier/Test.php
@@ -0,0 +1,24 @@
 <?php
 require_once 'HTMLPurifier.php';
 // integration test
 class HTMLPurifier_Test extends UnitTestCase
 {
    var $purifier;
    function assertPurification($input, $expect = null) {
        if ($expect === null) $expect = $input;
        $result = $this->purifier->purify($input);
        $this->assertIdentical($expect, $result);
    }
    function test() {
        $config = HTMLPurifier_Config::createDefault();
        $this->purifier = new HTMLPurifier($config);
        $this->assertPurification("Null byte\0", "Null byte");
    }
 }
 ?>
--- a/tests/index.php
+++ b/tests/index.php
@@ -40,7 +40,7 @@ require_once 'HTMLPurifier.php';
 // define callable test files
 $test_files = array();
 $test_files[] = 'ConfigTest.php';
-$test_files[] = 'ConfigDefTest.php';
+$test_files[] = 'ConfigSchemaTest.php';
 $test_files[] = 'LexerTest.php';
 $test_files[] = 'Lexer/DirectLexTest.php';
 $test_files[] = 'TokenTest.php';
@@ -88,6 +88,7 @@ $test_files[] = 'URISchemeRegistryTest.php';
 $test_files[] = 'URISchemeTest.php';
 $test_files[] = 'EncoderTest.php';
 $test_files[] = 'EntityParserTest.php';
 $test_files[] = 'Test.php';
 if (version_compare(PHP_VERSION, '5', '>=')) {
    $test_files[] = 'TokenFactoryTest.php';
Author	SHA1	Message	Date
Edward Z. Yang	6ef8abd04f	Released 1.1.1. git-svn-id: http://htmlpurifier.org/svnroot/htmlpurifier/branches/1.1@459 48356398-32a2-884e-a903-53898d9a118a	2006-09-24 22:32:26 +00:00
Edward Z. Yang	bc5871f389	Merged 438:439, 440:441, and 442:457 from trunk/ to branches/1.1/, mostly major work done for 1.1.1 release. - Various documentation updates - Fixed fatal error in benchmark scripts, slightly augmented - As far as possible, whitespace is preserved in-between table children - 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) - Sample test-settings.php file included Unrelated unmerged edit: removed irrelevant 1.2.0 release notes, those only exist in the trunk. git-svn-id: http://htmlpurifier.org/svnroot/htmlpurifier/branches/1.1@458 48356398-32a2-884e-a903-53898d9a118a	2006-09-24 22:22:06 +00:00
Edward Z. Yang	30d75c999d	Merged r434:436 from trunk/ to branches/1.1 - Update documentation. - Update TODO. git-svn-id: http://htmlpurifier.org/svnroot/htmlpurifier/branches/1.1@437 48356398-32a2-884e-a903-53898d9a118a	2006-09-17 22:08:48 +00:00
Edward Z. Yang	64d8ca9831	Branch out 1.1 release set. git-svn-id: http://htmlpurifier.org/svnroot/htmlpurifier/branches/1.1@426 48356398-32a2-884e-a903-53898d9a118a	2006-09-17 00:19:47 +00:00
Edward Z. Yang	d7642b8c70	Bump release dates. git-svn-id: http://htmlpurifier.org/svnroot/htmlpurifier/trunk@425 48356398-32a2-884e-a903-53898d9a118a	2006-09-17 00:17:45 +00:00
Edward Z. Yang	3b30c2ca5b	Renamed ConfigDef to ConfigSchema. (Required major internal restructuring but should not affect end-users) git-svn-id: http://htmlpurifier.org/svnroot/htmlpurifier/trunk@424 48356398-32a2-884e-a903-53898d9a118a	2006-09-16 22:36:58 +00:00
Edward Z. Yang	f43616f72d	Add default value information. git-svn-id: http://htmlpurifier.org/svnroot/htmlpurifier/trunk@423 48356398-32a2-884e-a903-53898d9a118a	2006-09-16 01:53:13 +00:00
Edward Z. Yang	6740ba61af	- XHTML generation can now be turned off, allowing things like <br> - Docs updated in preparation for 1.1 release git-svn-id: http://htmlpurifier.org/svnroot/htmlpurifier/trunk@422 48356398-32a2-884e-a903-53898d9a118a	2006-09-16 00:37:33 +00:00
Edward Z. Yang	6a33945499	Update Test namespace description noting that it is developer-only. git-svn-id: http://htmlpurifier.org/svnroot/htmlpurifier/trunk@421 48356398-32a2-884e-a903-53898d9a118a	2006-09-16 00:00:17 +00:00
Edward Z. Yang	4660791682	Bump plaintext formatters to 1.3, they'll be difficult to implement. git-svn-id: http://htmlpurifier.org/svnroot/htmlpurifier/trunk@420 48356398-32a2-884e-a903-53898d9a118a	2006-09-15 23:33:35 +00:00
Edward Z. Yang	b5c69d8ca5	Update documentation. git-svn-id: http://htmlpurifier.org/svnroot/htmlpurifier/trunk@418 48356398-32a2-884e-a903-53898d9a118a	2006-09-15 01:59:43 +00:00
Edward Z. Yang	e440f25bce	[1.1] Table child definition made more flexible, will fix up poorly ordered elements git-svn-id: http://htmlpurifier.org/svnroot/htmlpurifier/trunk@417 48356398-32a2-884e-a903-53898d9a118a	2006-09-15 01:52:22 +00:00
Edward Z. Yang	665e80d223	Remove outdated and misleading DTD. git-svn-id: http://htmlpurifier.org/svnroot/htmlpurifier/trunk@416 48356398-32a2-884e-a903-53898d9a118a	2006-09-15 00:28:49 +00:00
Edward Z. Yang	69747ede8a	Generalize custom test to use non-existent items. Table unit test was disabled (to be reused for table test). git-svn-id: http://htmlpurifier.org/svnroot/htmlpurifier/trunk@415 48356398-32a2-884e-a903-53898d9a118a	2006-09-13 02:11:09 +00:00
Edward Z. Yang	49b3832ebf	Add ToC todo to configdoc. git-svn-id: http://htmlpurifier.org/svnroot/htmlpurifier/trunk@414 48356398-32a2-884e-a903-53898d9a118a	2006-09-13 01:02:17 +00:00
Edward Z. Yang	a365d4c688	- Finished documentation generation. - Modified namespace definitions so that they cannot be redefined git-svn-id: http://htmlpurifier.org/svnroot/htmlpurifier/trunk@413 48356398-32a2-884e-a903-53898d9a118a	2006-09-13 00:59:20 +00:00
Edward Z. Yang	7038fad788	Add nicer comments to configdoc/generate.php. We may want to factor things out into classes. git-svn-id: http://htmlpurifier.org/svnroot/htmlpurifier/trunk@412 48356398-32a2-884e-a903-53898d9a118a	2006-09-11 02:52:47 +00:00
Edward Z. Yang	50b272d75e	Fix up the NEWS document that was missing release dates. git-svn-id: http://htmlpurifier.org/svnroot/htmlpurifier/trunk@409 48356398-32a2-884e-a903-53898d9a118a	2006-09-11 02:20:33 +00:00
Edward Z. Yang	bfb642d32c	Ehh... I liked 80-char linewrap better. git-svn-id: http://htmlpurifier.org/svnroot/htmlpurifier/trunk@408 48356398-32a2-884e-a903-53898d9a118a	2006-09-10 23:02:36 +00:00
Edward Z. Yang	edb39601c7	Increase wrap slightly. git-svn-id: http://htmlpurifier.org/svnroot/htmlpurifier/trunk@407 48356398-32a2-884e-a903-53898d9a118a	2006-09-10 22:55:58 +00:00
Edward Z. Yang	694139d3bb	Fix parse error. git-svn-id: http://htmlpurifier.org/svnroot/htmlpurifier/trunk@406 48356398-32a2-884e-a903-53898d9a118a	2006-09-10 22:53:40 +00:00
Edward Z. Yang	81721ded5c	Disable HTML output when run from cli. git-svn-id: http://htmlpurifier.org/svnroot/htmlpurifier/trunk@405 48356398-32a2-884e-a903-53898d9a118a	2006-09-10 22:47:27 +00:00
Edward Z. Yang	371fb7c3d2	Remove cli conditional code. git-svn-id: http://htmlpurifier.org/svnroot/htmlpurifier/trunk@404 48356398-32a2-884e-a903-53898d9a118a	2006-09-10 22:40:18 +00:00
Edward Z. Yang	9e6953e619	Massive augmentation of ConfigDoc. - Generate name to expanded name for types - Change XML format so that constraints are grouped together - Table-ize constraints - Enable HTML output in descriptions - Run output through Tidy to make it easier to read - Load stylesheet git-svn-id: http://htmlpurifier.org/svnroot/htmlpurifier/trunk@403 48356398-32a2-884e-a903-53898d9a118a	2006-09-10 22:17:22 +00:00
Edward Z. Yang	2299f0c831	Add todo items to the files. git-svn-id: http://htmlpurifier.org/svnroot/htmlpurifier/trunk@402 48356398-32a2-884e-a903-53898d9a118a	2006-09-10 20:21:19 +00:00
Edward Z. Yang	9dd4dcb27a	Restructure directory to make it more amenable to CSS by merging output with ./ git-svn-id: http://htmlpurifier.org/svnroot/htmlpurifier/trunk@400 48356398-32a2-884e-a903-53898d9a118a	2006-09-10 20:16:19 +00:00
Edward Z. Yang	aa0838492e	Remove an outdated piece of information from Lexer's configuration documentation. git-svn-id: http://htmlpurifier.org/svnroot/htmlpurifier/trunk@399 48356398-32a2-884e-a903-53898d9a118a	2006-09-10 19:56:49 +00:00
Edward Z. Yang	df075c96e0	Rename default skin to plain skin to allow directory browsing. git-svn-id: http://htmlpurifier.org/svnroot/htmlpurifier/trunk@397 48356398-32a2-884e-a903-53898d9a118a	2006-09-10 19:48:40 +00:00
Edward Z. Yang	fbaa909d25	[1.1.0] Initial commit of ConfigDoc code, still needs cleanup, but basic proof-of-concept is there. git-svn-id: http://htmlpurifier.org/svnroot/htmlpurifier/trunk@394 48356398-32a2-884e-a903-53898d9a118a	2006-09-10 02:02:40 +00:00
Edward Z. Yang	967f40fc11	Make install docs more comprehensive about encoding. Prompted by http://hp.jpsband.org/vanilla/comments.php?DiscussionID=2 git-svn-id: http://htmlpurifier.org/svnroot/htmlpurifier/trunk@392 48356398-32a2-884e-a903-53898d9a118a	2006-09-09 21:10:04 +00:00
Edward Z. Yang	5ee6ffe20f	Defer HTMLDefinition include to the classes that are actually tightly coupled to it. git-svn-id: http://htmlpurifier.org/svnroot/htmlpurifier/trunk@391 48356398-32a2-884e-a903-53898d9a118a	2006-09-07 02:13:17 +00:00
Edward Z. Yang	10d41d7130	Add notes on redefinition, what to do next? git-svn-id: http://htmlpurifier.org/svnroot/htmlpurifier/trunk@390 48356398-32a2-884e-a903-53898d9a118a	2006-09-06 02:20:32 +00:00
Edward Z. Yang	65a628bcb7	[1.1.0] Enforce alphanumeric namespace and directive names for configuration. git-svn-id: http://htmlpurifier.org/svnroot/htmlpurifier/trunk@389 48356398-32a2-884e-a903-53898d9a118a	2006-09-06 02:07:46 +00:00
Edward Z. Yang	a5b4ed2126	[1.0.1] Fixed rejection of inline style declarations that had lots of extra space in them. This manifested in TinyMCE. git-svn-id: http://htmlpurifier.org/svnroot/htmlpurifier/trunk@382 48356398-32a2-884e-a903-53898d9a118a	2006-09-04 23:01:47 +00:00
Edward Z. Yang	d20bbd8db3	[1.0.1] Disambiguate between iconv and PHP test runs for cleanUTF8. git-svn-id: http://htmlpurifier.org/svnroot/htmlpurifier/trunk@381 48356398-32a2-884e-a903-53898d9a118a	2006-09-04 20:18:10 +00:00
Edward Z. Yang	b99573223d	[1.1.0] Made URI validator more forgiving: will ignore leading and trailing quotes, apostrophes and less than or greater than signs. git-svn-id: http://htmlpurifier.org/svnroot/htmlpurifier/trunk@380 48356398-32a2-884e-a903-53898d9a118a	2006-09-04 02:31:27 +00:00
Edward Z. Yang	c6cfb68713	Bump formatting features release date to 1.1 git-svn-id: http://htmlpurifier.org/svnroot/htmlpurifier/trunk@376 48356398-32a2-884e-a903-53898d9a118a	2006-09-03 20:50:45 +00:00
Edward Z. Yang	2259bfa40e	Merged 371:372 from branches/1.0/ to trunk/ - Add integration test. git-svn-id: http://htmlpurifier.org/svnroot/htmlpurifier/trunk@374 48356398-32a2-884e-a903-53898d9a118a	2006-09-01 17:56:55 +00:00
Edward Z. Yang	de3b2b70fb	Bump tested in version number. git-svn-id: http://htmlpurifier.org/svnroot/htmlpurifier/trunk@370 48356398-32a2-884e-a903-53898d9a118a	2006-09-01 17:18:49 +00:00
Edward Z. Yang	4f0a5c0e22	- Add Test namespace - Further fix the no iconv problem, and extend test cases to cover that case. git-svn-id: http://htmlpurifier.org/svnroot/htmlpurifier/trunk@368 48356398-32a2-884e-a903-53898d9a118a	2006-09-01 16:54:23 +00:00
Edward Z. Yang	fdd583253c	Fixed rejection of case-insensitive configuration values when there is a set of allowed values. This manifested in %Core.Encoding. git-svn-id: http://htmlpurifier.org/svnroot/htmlpurifier/trunk@367 48356398-32a2-884e-a903-53898d9a118a	2006-09-01 16:40:14 +00:00
Edward Z. Yang	a4be6ffe4d	Fix slight bug in DOMLex's attribute parsing. git-svn-id: http://htmlpurifier.org/svnroot/htmlpurifier/trunk@365 48356398-32a2-884e-a903-53898d9a118a	2006-09-01 16:19:21 +00:00
Edward Z. Yang	6de42d8d1d	Attempt to fix strange foreach troubles. git-svn-id: http://htmlpurifier.org/svnroot/htmlpurifier/trunk@364 48356398-32a2-884e-a903-53898d9a118a	2006-09-01 16:17:56 +00:00
Edward Z. Yang	e9a519e589	Bump Doxyfile version number, add spaces in-between HTML Purifier. git-svn-id: http://htmlpurifier.org/svnroot/htmlpurifier/trunk@360 48356398-32a2-884e-a903-53898d9a118a	2006-09-01 15:28:05 +00:00