Fix typo in NEWS item.

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

Doxyfile

@@ -4,7 +4,7 @@
 # Project related configuration options
 #---------------------------------------------------------------------------
 PROJECT_NAME           = HTML Purifier
-PROJECT_NUMBER         = 1.0.0
+PROJECT_NUMBER         = 1.1.2
 OUTPUT_DIRECTORY       = "C:/Documents and Settings/Edward/My Documents/My Webs/htmlpurifier/docs/doxygen"
 CREATE_SUBDIRS         = NO
 OUTPUT_LANGUAGE        = English
@@ -89,9 +89,12 @@ EXCLUDE                =
 EXCLUDE_SYMLINKS       = NO
 EXCLUDE_PATTERNS       = */tests/* \
                          */benchmarks/* \
-                         */docs/phpdoc/* \
-                         */docs/doxygen/* \
-                         */test-settings.php
+                         */docs/* \
+                         */test-settings.php \
+                         */configdoc/* \
+                         */test-settings.php \
+                         */maintenance/* \
+                         */smoketests/*
 EXAMPLE_PATH           = 
 EXAMPLE_PATTERNS       = *
 EXAMPLE_RECURSIVE      = NO

INSTALL

@@ -2,141 +2,183 @@
 Install
     How to install HTML Purifier
 
-Being a library, there's no fancy GUI that will take you step-by-step through
-configuring database credentials and other mumbo-jumbo.  HTML Purifier is
-designed to run "out of the box."  Regardless, there are still a couple of
-things you should be mindful of.
+HTML Purifier is designed to run out of the box,  so actually using the library
+is extremely easy. (Although, if you were looking for a step-by-step
+installation GUI, you've come to the wrong place!)  The impatient can scroll
+down to the bottom of this INSTALL document to see the code, but you really
+should make sure a few things are properly done.
 
 
 
-0.  Compatibility
+1.  Compatibility
 
-HTML Purifier works in both PHP 4 and PHP 5.  I have run the test suite on
-these versions:
+HTML Purifier works in both PHP 4 and PHP 5, from PHP 4.3.9 and up. It has no
+core dependencies with other libraries. (Whoopee!)
 
-  - 4.3.9, 4.3.11
-  - 4.4.0, 4.4.4
-  - 5.0.0, 5.0.4
-  - 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,
-and PHP 4.3 branch support may go further back than that, but I haven't tested
-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 should not be a major factor in the library.
+Optional extensions are iconv (usually installed) and tidy (also common).
+If you use UTF-8 and don't plan on pretty-printing HTML, you can get away with
+not having either of these extensions.
 
 
 
-1.  Including the proper files
+2.  Including the library
 
-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:
+Simply use:
 
-    set_include_path('/path/to/htmlpurifier/library' . PATH_SEPARATOR .
-        get_include_path() );
+	require_once '/path/to/library/HTMLPurifier.auto.php';
 
-...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
-HTMLPurifier.php, the files won't collide with any of your includes.
+...and you're good to go.  Since HTML Purifier's codebase is fairly
+large, I recommend only including HTML Purifier when you need it.
 
-Then, it's a simple matter of including the base file:
+If you don't like your include_path to be fiddled around with, simply set
+HTML Purifier's library/ directory to the include path yourself and then:
 
-    require_once 'HTMLPurifier.php';
+	require_once 'HTMLPurifier.php';
 
-...and you're good to go.
+Only the contents in the library/ folder are necessary, so you can remove
+everything else when using HTML Purifier in a production environment.  
 
 
 
-2.  Preparing the proper environment
+3.  Preparing the proper output environment
 
-While no configuration is necessary, you first should take precautions regarding
-the other output HTML that the filtered content will be going along with.  Here
-is a (short) checklist:
+HTML Purifier is all about web-standards, so accordingly your webpages should
+be standards compliant.  HTML Purifier can deal with these doctypes:
 
- * Have I specified XHTML 1.0 Transitional as the doctype?
- * Have I specified UTF-8 as the character encoding?
+* XHTML 1.0 Transitional (default)
+* HTML 4.01 Transitional
+
+...and these character encodings:
+
+* UTF-8 (default)
+* Any encoding iconv supports (support is crippled for i18n though)
+
+The defaults are there for a reason: they are best-practice choices that
+should not be changed lightly.  For those of you in the dark, you can determine
+the doctype from this code in your HTML documents:
 
-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
+
+...and the character encoding from this code:
+
     <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.  If you can't, well, we might be able to accomodate you (read
-section 3).
+For legacy codebases these declarations may be missing.  If that is the case,
+STOP, and read up on character encodings and doctypes (in that order).  Here
+are some links:
+
+* http://www.joelonsoftware.com/articles/Unicode.html
+* http://alistapart.com/stories/doctype/
+
+You may currently be vulnerable to XSS and other security threats, and HTML
+Purifier won't be able to fix that.
 
 
 
-3. Configuring HTML Purifier
+4. Configuration
 
 HTML Purifier is designed to run out-of-the-box, but occasionally HTML
-Purifier needs to be told what to do.
+Purifier needs to be told what to do.  If you answered no to any of these
+questions, read on, otherwise, you can skip to the next section (or, if you're
+into configuring things just for the heck of it, skip to 4.3).
 
-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.
+* Am I using UTF-8?
+* Am I using XHTML 1.0 Transitional?
+
+If you answered yes to any of these questions, instantiate a configuration
+object and read on:
+
+    $config = HTMLPurifier_Config::createDefault();
+
+
+
+4.1. Setting a different character encoding
+
+You really shouldn't use any other encoding except UTF-8, especially if you
+plan to support multilingual websites (read section three for more details).
+However, switching to UTF-8 is not always immediately feasible, so we can
+adapt.
+
+HTML Purifier uses iconv to support other character encodings, as such,
+any encoding that iconv supports <http://www.gnu.org/software/libiconv/>
+HTML Purifier supports with this code:
 
     $config->set('Core', 'Encoding', /* put your encoding here */);
 
-An example usage for Latin-1 websites:
+An example usage for Latin-1 websites (the most common encoding for English
+websites):
 
     $config->set('Core', 'Encoding', 'ISO-8859-1');
 
+Note that HTML Purifier's support for non-Unicode encodings is crippled by the
+fact that any character not supported by that encoding will be silently
+dropped, EVEN if it is ampersand escaped.  This is a current limitation of
+HTML Purifier that we are NOT actively working to fix.  Patches are welcome,
+but there are so many other gotchas and problems in I18N for non-Unicode
+encodings that this functionality is low priority.  See
+<http://ppewww.ph.gla.ac.uk/~flavell/charset/form-i18n.html> for a more
+detailed lowdown on the topic.
+
+
+
+4.2. Setting a different doctype
+
 For those of you stuck using HTML 4.01 Transitional, you can disable
 XHTML output like this:
 
     $config->set('Core', 'XHTML', false);
 
-However, I strongly recommend that you use XHTML. Currently, we can only
-guarantee transitional-complaint output, future versions will also allow strict
-output.
+I recommend that you use XHTML, although not as much as I recommend UTF-8.  If
+your HTML 4.01 page validates, good for you!
+
+Currently, we can only guarantee transitional-complaint output, future
+versions will also allow strict-compliant output.
 
 
 
-3.   Using the code
+4.3. Other settings
+
+There are more configuration directives which can be read about
+here: <http://hp.jpsband.org/live/configdoc/plain.html>  They're a bit boring,
+but they can help out for those of you who like to exert maximum control over
+your code.
+
+
+
+5.   Using the code
 
 The interface is mind-numbingly simple:
 
     $purifier = new HTMLPurifier();
-    $clean_html = $purifier->purify($dirty_html);
+    $clean_html = $purifier->purify( $dirty_html );
 
-Or, if you're using the configuration object:
+...or, if you're using the configuration object:
 
     $purifier = new HTMLPurifier($config);
-    $clean_html = $purifier->purify($dirty_html);
+    $clean_html = $purifier->purify( $dirty_html );
 
-That's it.  For more examples, check out docs/examples/.  Also, SLOW gives
-advice on what to do if HTML Purifier is slowing down your application.
+That's it!  For more examples, check out docs/examples/ (they aren't very
+different though).  Also, SLOW gives advice on what to do if HTML Purifier
+is slowing down your application.
 
 
 
-4.   Quick install
+6.   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();
+    require_once '/path/to/htmlpurifier/library/HTMLPurifier.auto.php';
     
+    $purifier = new HTMLPurifier();
     $clean_html = $purifier->purify($dirty_html);
+?>
 
 If your website is in a different encoding or doctype, use this code:
 
 <?php
-    set_include_path('/path/to/htmlpurifier/library'
-         . PATH_SEPARATOR . get_include_path() );
-    require_once 'HTMLPurifier.php';
+    require_once '/path/to/htmlpurifier/library/HTMLPurifier.auto.php';
     
     $config = HTMLPurifier_Config::createDefault();
     $config->set('Core', 'Encoding', 'ISO-8859-1'); //replace with your encoding

NEWS

@@ -1,20 +1,47 @@
 NEWS ( CHANGELOG and HISTORY )                                     HTMLPurifier
 |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
 
-1.2.0, unknown projected release date
-(major feature release)
+= KEY ====================
+    ! Feature
+    - Bugfix
+      + Sub-comment
+    . Internal change
+==========================
 
-1.1.1, unknown projected release date
-(bugfix release)
+1.1.2, released 2006-09-30
+! Add HTMLPurifier.auto.php stub file that configures include_path
+- Documentation updated
+  + INSTALL document rewritten
+  + TODO added semi-lossy conversion
+  + API Doxygen docs' file exclusions updated
+  + Added notes on HTML versus XML attribute whitespace handling
+  + Noted that HTMLPurifier_ChildDef_Custom isn't being used
+  + Noted that config object's definitions are cached versions
+- Fixed lack of attribute parsing in HTMLPurifier_Lexer_PEARSax3
+- ftp:// URIs now have their typecodes checked
+- Hooked up HTMLPurifier_ChildDef_Custom's unit tests (they weren't being run)
+. Line endings standardized throughout project (svn:eol-style standardized)
+. Refactored parseData() to general Lexer class
+. Tester named "HTML Purifier" not "HTMLPurifier"
+
+1.1.1, released 2006-09-24
+! Configuration option to optionally Tidy up output for indentation to make up
+  for dropped whitespace by DOMLex (pretty-printing for the entire application
+  should be done by a page-wide Tidy)
+- Various documentation updates
+- Fixed parse error in configuration documentation script
+- Fixed fatal error in benchmark scripts, slightly augmented
+- As far as possible, whitespace is preserved in-between table children
+- Sample test-settings.php file included
 
 1.1.0, released 2006-09-16
+! Directive documentation generation using XSLT
+! XHTML can now be turned off, output becomes <br>
 - Made URI validator more forgiving: will ignore leading and trailing
   quotes, apostrophes and less than or greater than signs.
 - Enforce alphanumeric namespace and directive names for configuration.
-- 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
+. Renamed ConfigDef to ConfigSchema
 
 1.0.1, released 2006-09-04
 - Fixed slight bug in DOMLex attribute parsing
@@ -24,17 +51,17 @@ NEWS ( CHANGELOG and HISTORY )                                     HTMLPurifier
   space in them.  This manifested in TinyMCE.
 
 1.0.0, released 2006-09-01
+! Shorthand CSS properties implemented: font, border, background, list-style
+! Basic color keywords translated into hexadecimal values
+! Table CSS properties implemented
+! Support for charsets other than UTF-8 (defined by iconv)
+! Malformed UTF-8 and non-SGML character detection and cleaning implemented
 - Fixed broken numeric entity conversion
-- Malformed UTF-8 and non-SGML character detection and cleaning implemented
 - API documentation completed
-- Shorthand CSS properties implemented: font, border, background, list-style
-- Basic color keywords translated into hexadecimal values
-- Table CSS properties implemented
-- (HTML|CSS)Definition de-singleton-ized
-- Support for charsets other than UTF-8 (defined by iconv)
+. (HTML|CSS)Definition de-singleton-ized
 
 1.0.0beta, released 2006-08-16
-- First public release, most functionality implemented. Notable omissions are:
-  . Shorthand CSS properties
-  . Table CSS properties
-  . Deprecated attribute transformations
+! First public release, most functionality implemented. Notable omissions are:
+  + Shorthand CSS properties
+  + Table CSS properties
+  + Deprecated attribute transformations

README

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

SLOW

@@ -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
-don't mind a little extra complexity, you can try...
+handling the filtered text.  While this may be a good thing, especially if
+you're using a WYSIWYG editor, it can also result in data-loss if a user
+expects a certain to be available but it doesn't.
 
 2. Caching the filtered output - accept the submitted text and put it
 unaltered into the database, but then also generate a filtered version and
 stash that in the database.  Serve the filtered version to readers, and the
 unaltered version to editors.  If need be, you can invalidate the cache and
 have the cached filtered version be regenerated on the first page view.  Pros?
-Full data retention.  Cons?  It's more complicated.
+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!  ;-)

TODO

@@ -6,24 +6,29 @@ Ongoing
  - Plugins for major CMSes (very tricky issue)
 
 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
- - Formatters for plaintext
-    - Auto-paragraphing (be sure to leverage fact that we know when things
-      shouldn't be paragraphed, such as lists and tables).
  - 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
@@ -38,9 +43,11 @@ 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
+ - Semi-lossy dumb alternate character encoding transformations, achieved by
+   encoding all characters that have string entity equivalents
 
 Wontfix
  - Non-lossy smart alternate character encoding transformations
+ - Pretty-printing HTML, users can use Tidy on the output on entire page

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';
-require_once 'HTMLPurifier/Config.php';
-require_once 'HTMLPurifier/Lexer/DirectLex.php';
-require_once 'HTMLPurifier/Lexer/PEARSax3.php';
+@include_once '../test-settings.php';
 
-$LEXERS = array(
-    'DirectLex' => new HTMLPurifier_Lexer_DirectLex(),
-    'PEARSax3'  => new HTMLPurifier_Lexer_PEARSax3()
-);
+require_once 'HTMLPurifier/ConfigSchema.php';
+require_once 'HTMLPurifier/Config.php';
+
+$LEXERS = array();
+$RUNS = isset($GLOBALS['HTMLPurifierTest']['Runs'])
+    ? $GLOBALS['HTMLPurifierTest']['Runs'] : 2; 
+
+require_once 'HTMLPurifier/Lexer/DirectLex.php';
+$LEXERS['DirectLex'] = new HTMLPurifier_Lexer_DirectLex();
+
+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, '.', '') .
-                   '%</td>';
+            $out .= '<td align="right"'.
+                   ($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

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';
 

configdoc/generate.php

@@ -50,7 +50,7 @@ function appendHTMLDiv($document, $node, $html) {
 // ---------------------------------------------------------------------------
 // Load copies of HTMLPurifier_ConfigDef and HTMLPurifier
 
-$definition = HTMLPurifier_ConfigDef::instance();
+$schema = HTMLPurifier_ConfigSchema::instance();
 $purifier = new HTMLPurifier();
 
 
@@ -61,7 +61,7 @@ $types_document = new DOMDocument('1.0', 'UTF-8');
 $types_root = $types_document->createElement('types');
 $types_document->appendChild($types_root);
 $types_document->formatOutput = true;
-foreach ($definition->types as $name => $expanded_name) {
+foreach ($schema->types as $name => $expanded_name) {
     $types_type = $types_document->createElement('type', $expanded_name);
     $types_type->setAttribute('id', $name);
     $types_root->appendChild($types_type);
@@ -88,7 +88,7 @@ TODO for XML format:
 - create a definition (DTD or other) once interface stabilizes
 */
 
-foreach($definition->info as $namespace_name => $namespace_info) {
+foreach($schema->info as $namespace_name => $namespace_info) {
     
     $dom_namespace = $dom_document->createElement('namespace');
     $dom_root->appendChild($dom_namespace);
@@ -100,7 +100,7 @@ foreach($definition->info as $namespace_name => $namespace_info) {
     $dom_namespace_description = $dom_document->createElement('description');
     $dom_namespace->appendChild($dom_namespace_description);
     appendHTMLDiv($dom_document, $dom_namespace_description,
-        $definition->info_namespace[$namespace_name]->description);
+        $schema->info_namespace[$namespace_name]->description);
     
     foreach ($namespace_info as $name => $info) {
         
@@ -128,14 +128,14 @@ foreach($definition->info as $namespace_name => $namespace_info) {
             }
         }
         
-        $raw_default = $definition->defaults[$namespace_name][$name];
+        $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(
-                    $definition->defaults[$namespace_name][$name], true
+                    $schema->defaults[$namespace_name][$name], true
                 );
         }
         $dom_constraints->appendChild(

configdoc/styles/plain.css

@@ -1,7 +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;}
+table {border-collapse:collapse;}
+table td, table th {padding:0.2em;}
+
+table.constraints {margin:0 0 1em;}
+table.constraints th {text-align:left;padding-left:0.4em;}
+table.constraints td {padding-right:0.4em;}
+table.constraints td pre {margin:0;}

configdoc/styles/plain.xsl

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

docs/code-quality.txt

@@ -11,24 +11,24 @@ profiling.
 Here we go:
 
 AttrDef
-    Class - doesn't support Unicode characters, uses regular expressions
-    Lang - code duplication, premature optimization, doesn't consult official
-        lists
-    Pixels/Length/MultiLength - implemented according to HTML spec (excludes
-        code reuse in CSS)
-    URI - multiple regular expressions, needs host validation routines factored
-        out for mailto scheme, IPv6 validation is broken (fringe), unintuitive
-        variable overwriting, missing validation for query, fragment and path,
+    Class - doesn't support Unicode characters (fringe); uses regular
+        expressions
+    Lang - code duplication; premature optimization; doesn't consult official
+        lists (fringe)
+    Length - easily mistaken for CSSLength
+    URI - multiple regular expressions; needs host validation routines factored
+        out for mailto scheme; missing validation for query; fragment and path,
         no percent-encode fixing
     CSS - parser doesn't accept advanced CSS (fringe)
     Number - constructor interface is inconsistent with Integer
-AttrTransform - doesn't accept AttrContext, non-validating
-ChildDef - not-allowed nodes translated to text, likely invalid handling
+AttrTransform - doesn't accept AttrContext
 Config - "load configuration" hooks missing, rich set* accessors missing
+ConfigSchema - redefinition is a mess
 Strategy
     FixNesting - cannot bubble nodes out of structures
     MakeWellFormed - insufficient automatic closing definitions (check HTML
-        spec for optional end tags).
+        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

docs/colors.txt

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

docs/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>

docs/filter-levels.txt

@@ -20,15 +20,32 @@ can further be customized using simpler configuration options.
 Here are some fuzzy levels you could set:
 
 1. Comments - Wordpress recommends a, abbr, acronym, b, blockquote, cite,
-    code, em, i, strike, strong; however, you could get away with only a, b and
-    i; also having p and pre tags would be helpful.
-2. Pages - As permissive as possible without allowing XSS.  No protection
+    code, em, i, strike, strong; however, you could get away with only a, em and
+    p; also having blockquote and pre tags would be helpful.
+2. BBCode - Emulate the usual tagset for forums: b, i, img, a, blockquote,
+    pre, div, span and h[2-6] (the last three are for specially formatted
+    posts, div and span require associated classes or inline styling enabled
+    to be useful)
+3. Pages - As permissive as possible without allowing XSS.  No protection
     against bad design sense, unfortunantely.  Suitable for wiki and page
     environments.
-3. Lint - Accept everything in the spec, a Tidy wannabe.
+4. Lint - Accept everything in the spec, a Tidy wannabe. (This probably won't
+    get implemented as it would require routines for things like <object>
+    and friends to be implemented, which is a lot of work for not a lot of
+    benefit)
 
-I've also decomposed tags into risk levels.  An asterisk indicates that no one
-really uses that tag, tilde indicates it's deprecated.
+One final note: when you start axing tags that are more commonly used, you
+run the risk of accidentally destroying user data, especially if the data
+is incoming from a WYSIWYG eidtor that hasn't been synced accordingly. This may
+make forbidden element to text transformations desirable (for example, images).
+
+
+
+== Element Risk Analysis ==
+
+Legend:
+    [danger level] - regular tags / uncommon tags ~ deprecated tags
+    [danger level]* - rare tags
 
 1 - blockquote, code, em, i, p, tt / strong, sub, sup
 1* - abbr, acronym, bdo, cite, dfn, kbd, q, samp
@@ -38,30 +55,76 @@ really uses that tag, tilde indicates it's deprecated.
 5 - a
 7 - area, map
 
+These are special use tags, they should be enabled on a blanket basis.
+
 Lists - dd, dl, dt, li, ol, ul ~ menu, dir
 Tables - caption, table, td, th, tr / col, colgroup, tbody, tfoot, thead
+
 Forms - fieldset, form, input, lable, legend, optgroup, option, select, textarea
 XSS - noscript, object, script ~ applet
-
 Meta - base, basefont, body, head, html, link, meta, style, title
 Frames - frame, frameset, iframe
 
 And tag specific notes:
 
-a - general problems involving linkspam
-b - too much bold is bad, typographically speaking bold is discouraged
-br - often misused
+a   - general problems involving linkspam
+b   - too much bold is bad, typographically speaking bold is discouraged
+br  - often misused
 center - CSS, usually no legit use
 del - only useful in editing context
 div - little meaning in certain contexts i.e. blog comment
-h1 - usually no legit use, as header is already set by application
-h* - not needed in blog comments
-hr - usually not necessary in blog comments
-img - could be extremely undesirable if linking to external pics
+h1  - usually no legit use, as header is already set by application
+h*  - not needed in blog comments
+hr  - usually not necessary in blog comments
+img - could be extremely undesirable if linking to external pics (CSRF, goatse)
 pre - could use formatting, only useful in code contexts
-q - very little support
-s - transform into span with styling or del?
+q   - very little support
+s   - transform into span with styling or del?
 small - technically presentational
 span - depends on attribute allowances
 sub, sup - specialized
-u - little legit use, prefer class with text-decoration
+u   - little legit use, prefer class with text-decoration
+
+Based on the riskiness of the items, we may want to offer %HTML.DisableImages
+attribute and put URI filtering higher up on the priority list.
+
+
+== Attribute Risk Analysis ==
+
+We actually have a suprisingly small assortment of allowed attributes (the
+rest are deprecated in strict, and thus we opted not to allow them, even
+though our output is XHTML Transitional by default.)
+
+Required URI - img.alt, img.src, a.href
+Medium risk - *.class, *.dir
+High risk - img.height, img.width, *.id, *.style
+
+Table - colgroup/col.span, td/th.rowspan, td/th.colspan
+Uncommon - *.title, *.lang, *.xml:lang
+Rare - td/th.abbr, table.summary, {table}.charoff
+Rare URI - del.cite, ins.cite, blockquote.cite, q.cite, img.longdesc
+Presentational - {table}.align, {table}.valign, table.frame, table.rules,
+    table.border
+Partially presentational - table.cellpadding, table.cellspacing,
+    table.width, col.width, colgroup.width
+
+
+== CSS Risk Analysis ==
+
+There are certain CSS elements that are extremely useful inline, but then
+as you get to more presentation oriented styling it may not always be
+appropriate to inline them.
+
+Useful - clear, float, border-collapse, caption-side
+
+These CSS properties can break layouts if used improperly. We have excluded
+any CSS properties that are not currently implemented (such as position).
+
+Dangerous, can go outside container - float
+Easy to abuse - font-size, font-family (font), width
+Colored - background-color (background), border-color (border), color
+Dramatic - border, list-style-position (list-style), margin, padding,
+    text-align, text-indent, text-transform, vertical-align, line-height
+
+Dramatic elements substnatially change the look of text in ways that should
+probably have been reserved to other areas.

docs/optimization.txt

@@ -2,7 +2,8 @@
 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 (may prove problematic, probably not worth it)
  - Rewrite regexps into PHP code

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>

docs/security.txt

@@ -6,30 +6,39 @@ 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
-properly converted to UTF-8, or the parser will mangle it badly
-(though it won't be a security risk if you're outputting it as UTF-8 though).
+your character encoding, make sure you configure HTML Purifier or switch
+to UTF-8. Now. Also, make sure any input is properly converted to UTF-8, or
+the parser will mangle it badly (though it won't be a security risk if you're
+outputting it as UTF-8 though).  Character encoding is, in general, a knotty
+issue, but do yourself a favor and learn about it:
+<http://www.joelonsoftware.com/articles/Unicode.html>
 
-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

docs/strictness.txt

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

library/HTMLPurifier.auto.php

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

library/HTMLPurifier.php

@@ -3,7 +3,7 @@
 /*!
  * @mainpage
  * 
- * HTMLPurifier is an HTML filter that will take an arbitrary snippet of
+ * HTML Purifier is an HTML filter that will take an arbitrary snippet of
  * HTML and rigorously test, validate and filter it into a version that
  * is safe for output onto webpages. It achieves this by:
  * 
@@ -22,7 +22,7 @@
  */
 
 /*
-    HTMLPurifier - Standards Compliant HTML Filtering
+    HTML Purifier - Standards Compliant HTML Filtering
     Copyright (C) 2006 Edward Z. Yang
 
     This library is free software; you can redistribute it and/or

library/HTMLPurifier/AttrContext.php

@@ -3,15 +3,15 @@
 /**
  * Internal data-structure used in attribute validation to accumulate state.
  * 
- * All it is is a data-structure that holds objects that accumulate state, like
- * HTMLPurifier_IDAccumulator.
+ * This is a data-structure that holds objects that accumulate state, like
+ * HTMLPurifier_IDAccumulator. It's better than using globals!
  * 
- * @param Many functions that accept this object have it as a mandatory
- *        parameter, even when there is no use for it.  Though this is
- *        for the same reasons as why HTMLPurifier_Config is a mandatory
- *        parameter, it is also because you cannot assign a default value
- *        to a parameter passed by reference (passing by reference is essential
- *        for context to work in PHP 4).
+ * @note Many functions that accept this object have it as a mandatory
+ *       parameter, even when there is no use for it.  Though this is
+ *       for the same reasons as why HTMLPurifier_Config is a mandatory
+ *       parameter, it is also because you cannot assign a default value
+ *       to a parameter passed by reference (passing by reference is essential
+ *       for context to work in PHP 4).
  */
 
 class HTMLPurifier_AttrContext

library/HTMLPurifier/AttrDef.php

@@ -48,7 +48,16 @@ class HTMLPurifier_AttrDef
      * 
      * @note This method is not entirely standards compliant, as trim() removes
      *       more types of whitespace than specified in the spec. In practice,
-     *       this is rarely a problem.
+     *       this is rarely a problem, as those extra characters usually have
+     *       already been removed by HTMLPurifier_Encoder.
+     * 
+     * @warning This processing is inconsistent with XML's whitespace handling
+     *          as specified by section 3.3.3 and referenced XHTML 1.0 section
+     *          4.7.  Compliant processing requires all line breaks normalized
+     *          to "\n", so the fix is not as simple as fixing it in this
+     *          function.  Trim and whitespace collapsing are supposed to only
+     *          occur in NMTOKENs.  However, note that we are NOT necessarily
+     *          parsing XML, thus, this behavior may still be correct.
      * 
      * @public
      */

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();

library/HTMLPurifier/ChildDef.php

@@ -56,6 +56,8 @@ class HTMLPurifier_ChildDef
  * 
  * @warning Currently this class is an all or nothing proposition, that is,
  *          it will only give a bool return value.
+ * @note This class is currently not used by any code, although it is unit
+ *       tested.
  */
 class HTMLPurifier_ChildDef_Custom extends HTMLPurifier_ChildDef
 {
@@ -327,6 +329,8 @@ class HTMLPurifier_ChildDef_Table extends HTMLPurifier_ChildDef
         $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);
@@ -344,7 +348,7 @@ class HTMLPurifier_ChildDef_Table extends HTMLPurifier_ChildDef
                 if ($is_child) {
                     // okay, let's stash the tokens away
                     // first token tells us the type of the collection
-                    switch ($collection[0]->name) {
+                    switch ($collection[$tag_index]->name) {
                         case 'tr':
                         case 'tbody':
                             $content[] = $collection;
@@ -356,13 +360,13 @@ class HTMLPurifier_ChildDef_Table extends HTMLPurifier_ChildDef
                         case 'thead':
                         case 'tfoot':
                             // access the appropriate variable, $thead or $tfoot
-                            $var = $collection[0]->name;
+                            $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[0]->name = 'tbody';
+                                $collection[$tag_index]->name = 'tbody';
                                 $collection[count($collection)-1]->name = 'tbody';
                                 $content[] = $collection;
                             }
@@ -373,6 +377,7 @@ class HTMLPurifier_ChildDef_Table extends HTMLPurifier_ChildDef
                     }
                     $collection = array();
                     $is_collecting = false;
+                    $tag_index = 0;
                 } else {
                     // add the node to the collection
                     $collection[] = $token;
@@ -387,7 +392,9 @@ class HTMLPurifier_ChildDef_Table extends HTMLPurifier_ChildDef
                 if ($token->name == 'col') {
                     // the only empty tag in the possie, we can handle it
                     // immediately
-                    $cols[] = array($token);
+                    $cols[] = array_merge($collection, array($token));
+                    $collection = array();
+                    $tag_index = 0;
                     continue;
                 }
                 switch($token->name) {
@@ -401,7 +408,10 @@ class HTMLPurifier_ChildDef_Table extends HTMLPurifier_ChildDef
                         $collection[] = $token;
                         continue;
                     default:
-                        // unrecognized, drop silently
+                        if ($token->type == 'text' && $token->is_whitespace) {
+                            $collection[] = $token;
+                            $tag_index++;
+                        }
                         continue;
                 }
             }
@@ -415,6 +425,10 @@ class HTMLPurifier_ChildDef_Table extends HTMLPurifier_ChildDef
         if ($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
         
@@ -423,4 +437,4 @@ class HTMLPurifier_ChildDef_Table extends HTMLPurifier_ChildDef
     }
 }
 
-?>
+?>

library/HTMLPurifier/Config.php

@@ -26,12 +26,12 @@ class HTMLPurifier_Config
     var $def;
     
     /**
-     * Instance of HTMLPurifier_HTMLDefinition
+     * Cached instance of HTMLPurifier_HTMLDefinition
      */
     var $html_definition;
     
     /**
-     * Instance of HTMLPurifier_CSSDefinition
+     * Cached instance of HTMLPurifier_CSSDefinition
      */
     var $css_definition;
     

library/HTMLPurifier/ConfigSchema.php

@@ -2,7 +2,6 @@
 
 /**
  * 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
@@ -39,7 +38,6 @@ class HTMLPurifier_ConfigSchema {
     
     /**
      * Lookup table of allowed types.
-     * @todo Add descriptions
      */
     var $types = array(
         'string'    => 'String',
@@ -82,9 +80,6 @@ class HTMLPurifier_ConfigSchema {
     /**
      * 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

library/HTMLPurifier/Encoder.php

@@ -88,7 +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

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
      */
     
     // +----------+----------+----------+----------+

library/HTMLPurifier/Generator.php

@@ -23,6 +23,21 @@ HTMLPurifier_ConfigSchema::define(
     '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.
  */
@@ -56,6 +71,30 @@ class HTMLPurifier_Generator
         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;
     }
     

library/HTMLPurifier/HTMLDefinition.php

@@ -56,6 +56,7 @@ class HTMLPurifier_HTMLDefinition
     
     /**
      * String name of parent element HTML will be going into.
+     * @todo Allow this to be overloaded by user config
      * @public
      */
     var $info_parent = 'div';
@@ -111,12 +112,19 @@ class HTMLPurifier_HTMLDefinition
         //////////////////////////////////////////////////////////////////////
         // info[]->child : defines allowed children for elements
         
-        // entities: prefixed with e_ and _ replaces .
+        // entities: prefixed with e_ and _ replaces . from DTD
+        // double underlines are entities we made up
         
         // we don't use an array because that complicates interpolation
         // strings are used instead of arrays because if you use arrays,
         // you have to do some hideous manipulation with array_merge()
         
+        // todo: determine whether or not having allowed children
+        //       that aren't allowed globally affects security (it shouldn't)
+        // if above works out, extend children definitions to include all
+        //       possible elements (allowed elements will dictate which ones
+        //       get dropped
+        
         $e_special_extra = 'img';
         $e_special_basic = 'br | span | bdo';
         $e_special = "$e_special_basic | $e_special_extra";
@@ -142,16 +150,18 @@ class HTMLPurifier_HTMLDefinition
         $e_block = "p | $e_heading | div | $e_lists | $e_blocktext | table";
         $e__flow = "#PCDATA | $e_block | $e_inline | $e_misc";
         $e_Flow = new HTMLPurifier_ChildDef_Optional($e__flow);
-        $e_a_content = new HTMLPurifier_ChildDef_Optional("#PCDATA | $e_special".
-          " | $e_fontstyle | $e_phrase | $e_inline_forms | $e_misc_inline");
+        $e_a_content = new HTMLPurifier_ChildDef_Optional("#PCDATA".
+          " | $e_special | $e_fontstyle | $e_phrase | $e_inline_forms".
+          " | $e_misc_inline");
         $e_pre_content = new HTMLPurifier_ChildDef_Optional("#PCDATA | a".
           " | $e_special_basic | $e_fontstyle_basic | $e_phrase_basic".
           " | $e_inline_forms | $e_misc_inline");
-        $e_form_content = new HTMLPurifier_ChildDef_Optional(''); //unused
-        $e_form_button_content = new HTMLPurifier_ChildDef_Optional(''); // unused
+        $e_form_content = new HTMLPurifier_ChildDef_Optional('');//unused
+        $e_form_button_content = new HTMLPurifier_ChildDef_Optional('');//unused
         
         $this->info['ins']->child =
-        $this->info['del']->child = new HTMLPurifier_ChildDef_Chameleon($e__inline, $e__flow);
+        $this->info['del']->child =
+            new HTMLPurifier_ChildDef_Chameleon($e__inline, $e__flow);
         
         $this->info['blockquote']->child=
         $this->info['dd']->child  =
@@ -225,7 +235,7 @@ class HTMLPurifier_HTMLDefinition
         //////////////////////////////////////////////////////////////////////
         // info[]->type : defines the type of the element (block or inline)
         
-        // reuses $e_Inline and $e_block
+        // reuses $e_Inline and $e_Block
         
         foreach ($e_Inline->elements as $name) {
             $this->info[$name]->type = 'inline';
@@ -243,7 +253,7 @@ class HTMLPurifier_HTMLDefinition
         
         $this->info['a']->excludes = array('a' => true);
         $this->info['pre']->excludes = array_flip(array('img', 'big', 'small',
-            // technically in spec, but we don't allow em anyway
+            // technically useless, but good to be indepth
             'object', 'applet', 'font', 'basefont'));
         
         //////////////////////////////////////////////////////////////////////
@@ -253,6 +263,8 @@ class HTMLPurifier_HTMLDefinition
         // by the transform classes. It will, however, do simple and slightly
         // complex attribute value substitution
         
+        // the question of varying allowed attributes is more entangling.
+        
         $e_Text = new HTMLPurifier_AttrDef_Text();
         
         // attrs, included in almost every single one except for a few,
@@ -297,7 +309,8 @@ class HTMLPurifier_HTMLDefinition
         
         $this->info['table']->attr['summary'] = $e_Text;
         
-        $this->info['table']->attr['border'] = new HTMLPurifier_AttrDef_Pixels();
+        $this->info['table']->attr['border'] =
+            new HTMLPurifier_AttrDef_Pixels();
         
         $e_Length = new HTMLPurifier_AttrDef_Length();
         $this->info['table']->attr['cellpadding'] =
@@ -329,7 +342,7 @@ class HTMLPurifier_HTMLDefinition
         $this->info['q']->attr['cite'] = $e_URI;
         
         //////////////////////////////////////////////////////////////////////
-        // UNIMP : info_tag_transform : transformations of tags
+        // info_tag_transform : transformations of tags
         
         $this->info_tag_transform['font']   = new HTMLPurifier_TagTransform_Font();
         $this->info_tag_transform['menu']   = new HTMLPurifier_TagTransform_Simple('ul');
@@ -339,6 +352,9 @@ class HTMLPurifier_HTMLDefinition
         //////////////////////////////////////////////////////////////////////
         // info[]->auto_close : tags that automatically close another
         
+        // todo: determine whether or not SGML-like modeling based on
+        // mandatory/optional end tags would be a better policy
+        
         // make sure you test using isset() not !empty()
         
         // these are all block elements: blocks aren't allowed in P

library/HTMLPurifier/Lexer.php

@@ -60,6 +60,60 @@ class HTMLPurifier_Lexer
         $this->_entity_parser = new HTMLPurifier_EntityParser();
     }
     
+    
+    /**
+     * Most common entity to raw value conversion table for special entities.
+     * @protected
+     */
+    var $_special_entity2str =
+            array(
+                    '"' => '"',
+                    '&'  => '&',
+                    '&lt;'   => '<',
+                    '&gt;'   => '>',
+                    '&#39;'  => "'",
+                    '&#039;' => "'",
+                    '&#x27;' => "'"
+            );
+    
+    /**
+     * Parses special entities into the proper characters.
+     * 
+     * This string will translate escaped versions of the special characters
+     * into the correct ones.
+     * 
+     * @warning
+     * You should be able to treat the output of this function as
+     * completely parsed, but that's only because all other entities should
+     * have been handled previously in substituteNonSpecialEntities()
+     * 
+     * @param $string String character data to be parsed.
+     * @returns Parsed character data.
+     */
+    function parseData($string) {
+        
+        // following functions require at least one character
+        if ($string === '') return '';
+        
+        // subtracts amps that cannot possibly be escaped
+        $num_amp = substr_count($string, '&') - substr_count($string, '& ') -
+            ($string[strlen($string)-1] === '&' ? 1 : 0);
+        
+        if (!$num_amp) return $string; // abort if no entities
+        $num_esc_amp = substr_count($string, '&amp;');
+        $string = strtr($string, $this->_special_entity2str);
+        
+        // code duplication for sake of optimization, see above
+        $num_amp_2 = substr_count($string, '&') - substr_count($string, '& ') -
+            ($string[strlen($string)-1] === '&' ? 1 : 0);
+        
+        if ($num_amp_2 <= $num_esc_amp) return $string;
+        
+        // hmm... now we have some uncommon entities. Use the callback.
+        $string = $this->_entity_parser->substituteSpecialEntities($string);
+        return $string;
+    }
+    
     var $_encoder;
     
     /**

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
- * Any empty elements will have empty tokens associated with them, even if
+ * @note 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
- *       if necessary.
- * @todo Make div access less fragile, and refrain from preprocessing when
- *       HTML tag and friends are already present.
+ * @note PHP's DOM extension does not actually parse any entities, we use
+ *       our own function to do that.
+ * 
+ * @warning DOM tends to drop whitespace, which may wreak havoc on indenting.
+ *          If this is a huge problem, due to the fact that HTML is hand
+ *          edited and youa re unable to get a parser cache that caches the
+ *          the output of HTML Purifier while keeping the original HTML lying
+ *          around, you may want to run Tidy on the resulting output or use
+ *          HTMLPurifier_DirectLex
  */
 
 class HTMLPurifier_Lexer_DOMLex extends HTMLPurifier_Lexer

library/HTMLPurifier/Lexer/DirectLex.php

@@ -12,64 +12,12 @@ require_once 'HTMLPurifier/Lexer.php';
  * completely eventually.
  * 
  * @todo Reread XML spec and document differences.
- * @todo Add support for CDATA sections.
- * @todo Determine correct behavior in outputting comment data. (preserve dashes?)
- * @todo Optimize main function tokenizeHTML().
- * @todo Less than sign (<) being prohibited (even as entity) in attr-values?
+ * 
+ * @todo Determine correct behavior in transforming comment data. (preserve dashes?)
  */
 class HTMLPurifier_Lexer_DirectLex extends HTMLPurifier_Lexer
 {
     
-    /**
-     * Most common entity to raw value conversion table for special entities.
-     * @protected
-     */
-    var $_special_entity2str =
-            array(
-                    '&quot;' => '"',
-                    '&amp;'  => '&',
-                    '&lt;'   => '<',
-                    '&gt;'   => '>',
-                    '&#39;'  => "'",
-                    '&#039;' => "'",
-                    '&#x27;' => "'"
-            );
-    
-    /**
-     * Parses special entities into the proper characters.
-     * 
-     * This string will translate escaped versions of the special characters
-     * into the correct ones.
-     * 
-     * @warning
-     * You should be able to treat the output of this function as
-     * completely parsed, but that's only because all other entities should
-     * have been handled previously in substituteNonSpecialEntities()
-     * 
-     * @param $string String character data to be parsed.
-     * @returns Parsed character data.
-     */
-    function parseData($string) {
-        
-        // subtracts amps that cannot possibly be escaped
-        $num_amp = substr_count($string, '&') - substr_count($string, '& ') -
-            ($string[strlen($string)-1] === '&' ? 1 : 0);
-        
-        if (!$num_amp) return $string; // abort if no entities
-        $num_esc_amp = substr_count($string, '&amp;');
-        $string = strtr($string, $this->_special_entity2str);
-        
-        // code duplication for sake of optimization, see above
-        $num_amp_2 = substr_count($string, '&') - substr_count($string, '& ') -
-            ($string[strlen($string)-1] === '&' ? 1 : 0);
-        
-        if ($num_amp_2 <= $num_esc_amp) return $string;
-        
-        // hmm... now we have some uncommon entities. Use the callback.
-        $string = $this->_entity_parser->substituteSpecialEntities($string);
-        return $string;
-    }
-    
     /**
      * Whitespace characters for str(c)spn.
      * @protected

library/HTMLPurifier/Lexer/PEARSax3.php

@@ -18,6 +18,8 @@ require_once 'HTMLPurifier/Lexer.php';
  * whatever it does for poorly formed HTML is up to it.
  * 
  * @todo Generalize so that XML_HTMLSax is also supported.
+ * 
+ * @warning Entity-resolution inside attributes is broken.
  */
 
 class HTMLPurifier_Lexer_PEARSax3 extends HTMLPurifier_Lexer
@@ -41,6 +43,8 @@ class HTMLPurifier_Lexer_PEARSax3 extends HTMLPurifier_Lexer
         $parser->set_element_handler('openHandler','closeHandler');
         $parser->set_data_handler('dataHandler');
         $parser->set_escape_handler('escapeHandler');
+        
+        // doesn't seem to work correctly for attributes
         $parser->set_option('XML_OPTION_ENTITIES_PARSED', 1);
         
         $parser->parse($string);
@@ -53,6 +57,10 @@ class HTMLPurifier_Lexer_PEARSax3 extends HTMLPurifier_Lexer
      * Open tag event handler, interface is defined by PEAR package.
      */
     function openHandler(&$parser, $name, $attrs, $closed) {
+        // entities are not resolved in attrs
+        foreach ($attrs as $key => $attr) {
+            $attrs[$key] = $this->parseData($attr);
+        }
         if ($closed) {
             $this->tokens[] = new HTMLPurifier_Token_Empty($name, $attrs);
         } else {

library/HTMLPurifier/URIScheme/ftp.php

@@ -4,7 +4,6 @@ require_once 'HTMLPurifier/URIScheme.php';
 
 /**
  * Validates ftp (File Transfer Protocol) URIs as defined by generic RFC 1738.
- * @todo Typecode check on path
  */
 class HTMLPurifier_URIScheme_ftp extends HTMLPurifier_URIScheme {
     
@@ -16,7 +15,27 @@ class HTMLPurifier_URIScheme_ftp extends HTMLPurifier_URIScheme {
         list($userinfo, $host, $port, $path, $query) = 
             parent::validateComponents(
                 $userinfo, $host, $port, $path, $query, $config );
-        // typecode check needed on path
+        $semicolon_pos = strrpos($path, ';'); // reverse
+        if ($semicolon_pos !== false) {
+            // typecode check
+            $type = substr($path, $semicolon_pos + 1); // no semicolon
+            $path = substr($path, 0, $semicolon_pos);
+            $type_ret = '';
+            if (strpos($type, '=') !== false) {
+                // figure out whether or not the declaration is correct
+                list($key, $typecode) = explode('=', $type, 2);
+                if ($key !== 'type') {
+                    // invalid key, tack it back on encoded
+                    $path .= '%3B' . $type;
+                } elseif ($typecode === 'a' || $typecode === 'i' || $typecode === 'd') {
+                    $type_ret = ";type=$typecode";
+                }
+            } else {
+                $path .= '%3B' . $type;
+            }
+            $path = str_replace(';', '%3B', $path);
+            $path .= $type_ret;
+        }
         return array($userinfo, $host, $port, $path, null);
     }
     

maintenance/.htaccess

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

phpdoc.ini

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

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/';
+
+?>

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();
     }
@@ -45,18 +46,23 @@ class HTMLPurifier_ChildDefTest extends UnitTestCase
         $this->def = new HTMLPurifier_ChildDef_Custom(
             '(a, b?, c*, d+, (a, b)*)');
         
+        $inputs = array();
+        $expect = array();
+        $config = array();
+        
         $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>';
+        $inputs[2] = '<a /><d>Dob</d><a /><b>foo</b><a href="moo" /><b>foo</b>';
         $expect[2] = true;
         
         $inputs[3] = '<a /><a />';
         $expect[3] = false;
         
+        $this->assertSeries($inputs, $expect, $config);
     }
     
     function test_table() {
@@ -98,6 +104,14 @@ class HTMLPurifier_ChildDefTest extends UnitTestCase
         $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);
         
     }
@@ -209,4 +223,4 @@ class HTMLPurifier_ChildDefTest extends UnitTestCase
     
 }
 
-?>
+?>

tests/HTMLPurifier/ConfigTest.php

@@ -8,6 +8,7 @@ class HTMLPurifier_ConfigTest extends UnitTestCase
     var $our_copy, $old_copy;
     
     function setUp() {
+        // set up a dummy schema object for testing
         $our_copy = new HTMLPurifier_ConfigSchema();
         $this->old_copy = HTMLPurifier_ConfigSchema::instance();
         $this->our_copy =& HTMLPurifier_ConfigSchema::instance($our_copy);
@@ -93,6 +94,17 @@ class HTMLPurifier_ConfigTest extends UnitTestCase
         
     }
     
+    function test_getDefinition() {
+        
+        $config = HTMLPurifier_Config::createDefault();
+        $def = $config->getHTMLDefinition();
+        $this->assertIsA($def, 'HTMLPurifier_HTMLDefinition');
+        
+        $def = $config->getCSSDefinition();
+        $this->assertIsA($def, 'HTMLPurifier_CSSDefinition');
+        
+    }
+    
 }
 
 ?>

tests/HTMLPurifier/GeneratorTest.php

@@ -123,6 +123,9 @@ 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);
     }
     
@@ -148,6 +151,25 @@ class HTMLPurifier_GeneratorTest extends UnitTestCase
         
     }
     
+    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"
+        );
+        
+    }
+    
 }
 
 ?>

tests/HTMLPurifier/Lexer/DirectLexTest.php

@@ -11,24 +11,6 @@ class HTMLPurifier_Lexer_DirectLexTest extends UnitTestCase
         $this->DirectLex = new HTMLPurifier_Lexer_DirectLex();
     }
     
-    function test_parseData() {
-        $HP =& $this->DirectLex;
-        
-        $this->assertIdentical('asdf', $HP->parseData('asdf'));
-        $this->assertIdentical('&', $HP->parseData('&'));
-        $this->assertIdentical('"', $HP->parseData('"'));
-        $this->assertIdentical("'", $HP->parseData('''));
-        $this->assertIdentical("'", $HP->parseData('''));
-        $this->assertIdentical('&&&', $HP->parseData('&&&'));
-        $this->assertIdentical('&&', $HP->parseData('&&')); // [INVALID]
-        $this->assertIdentical('Procter & Gamble',
-                $HP->parseData('Procter & Gamble')); // [INVALID]
-        
-        // This is not special, thus not converted. Test of fault tolerance,
-        // realistically speaking, this should never happen
-        $this->assertIdentical('-', $HP->parseData('-'));
-    }
-    
     // internals testing
     function test_parseAttributeString() {
         

tests/HTMLPurifier/LexerTest.php

@@ -38,6 +38,25 @@ class HTMLPurifier_LexerTest extends UnitTestCase
         $this->assertIdentical($extract, $result);
     }
     
+    function test_parseData() {
+        $HP =& $this->Lexer;
+        
+        $this->assertIdentical('asdf', $HP->parseData('asdf'));
+        $this->assertIdentical('&', $HP->parseData('&'));
+        $this->assertIdentical('"', $HP->parseData('"'));
+        $this->assertIdentical("'", $HP->parseData('''));
+        $this->assertIdentical("'", $HP->parseData('''));
+        $this->assertIdentical('&&&', $HP->parseData('&&&'));
+        $this->assertIdentical('&&', $HP->parseData('&&')); // [INVALID]
+        $this->assertIdentical('Procter & Gamble',
+                $HP->parseData('Procter & Gamble')); // [INVALID]
+        
+        // This is not special, thus not converted. Test of fault tolerance,
+        // realistically speaking, this should never happen
+        $this->assertIdentical('-', $HP->parseData('-'));
+    }
+    
+    
     function test_extractBody() {
         $this->assertExtractBody('<b>Bold</b>');
         $this->assertExtractBody('<html><body><b>Bold</b></body></html>', '<b>Bold</b>');
@@ -249,13 +268,16 @@ class HTMLPurifier_LexerTest extends UnitTestCase
                ,new HTMLPurifier_Token_Text('Link')
                ,new HTMLPurifier_Token_End('a')
             );
-        $sax_expect[16] = false; // PEARSax doesn't support it!
         
         // test that UTF-8 is preserved
         $char_hearts = $this->_entity_lookup->table['hearts'];
         $input[17] = $char_hearts;
         $expect[17] = array( new HTMLPurifier_Token_Text($char_hearts) );
         
+        // test weird characters in attributes
+        $input[18] = '<br test="x &lt; 6" />';
+        $expect[18] = array( new HTMLPurifier_Token_Empty('br', array('test' => 'x < 6')) );
+        
         $default_config = HTMLPurifier_Config::createDefault();
         foreach($input as $i => $discard) {
             if (!isset($config[$i])) $config[$i] = $default_config;

tests/HTMLPurifier/URISchemeTest.php

@@ -54,12 +54,34 @@ class HTMLPurifier_URISchemeTest extends UnitTestCase
         
         $scheme = new HTMLPurifier_URIScheme_ftp();
         $config = HTMLPurifier_Config::createDefault();
+        
         $this->assertIdentical(
           $scheme->validateComponents(
                 'user', 'www.example.com', 21, '/', 's=foobar', $config),
           array('user', 'www.example.com', null, '/', null)
         );
         
+        // valid typecode
+        $this->assertIdentical(
+          $scheme->validateComponents(
+                null, 'www.example.com', null, '/file.txt;type=a', null, $config),
+          array(null, 'www.example.com', null, '/file.txt;type=a', null)
+        );
+        
+        // remove invalid typecode
+        $this->assertIdentical(
+          $scheme->validateComponents(
+                null, 'www.example.com', null, '/file.txt;type=z', null, $config),
+          array(null, 'www.example.com', null, '/file.txt', null)
+        );
+        
+        // encode errant semicolons
+        $this->assertIdentical(
+          $scheme->validateComponents(
+                null, 'www.example.com', null, '/too;many;semicolons=1', null, $config),
+          array(null, 'www.example.com', null, '/too%3Bmany%3Bsemicolons=1', null)
+        );
+        
     }
     
     function test_news() {

tests/index.php

@@ -114,14 +114,14 @@ if (isset($_GET['file']) && isset($test_file_lookup[$_GET['file']])) {
     // execute only one test
     $test_file = $_GET['file'];
     
-    $test = new GroupTest('HTMLPurifier - ' . $test_file);
+    $test = new GroupTest('HTML Purifier - ' . $test_file);
     $path = 'HTMLPurifier/' . $test_file;
     require_once $path;
     $test->addTestClass(htmlpurifier_path2class($path));
     
 } else {
     
-    $test = new GroupTest('HTMLPurifier');
+    $test = new GroupTest('HTML Purifier');
 
     foreach ($test_files as $test_file) {
         $path = 'HTMLPurifier/' . $test_file;