[1.2.0] [merge] Bump TODO items.

git-svn-id: http://htmlpurifier.org/svnroot/htmlpurifier/branches/1.2@545 48356398-32a2-884e-a903-53898d9a118a

CREDITS

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

Doxyfile

@@ -3,8 +3,8 @@
 #---------------------------------------------------------------------------
 # Project related configuration options
 #---------------------------------------------------------------------------
-PROJECT_NAME           = HTMLPurifier
-PROJECT_NUMBER         = trunk
+PROJECT_NAME           = HTML Purifier
+PROJECT_NUMBER         = 1.2.0
 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

@@ -2,89 +2,188 @@
 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, 5.1.5
-
-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 is quite irrelevant in this particular case.
+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';
 
-...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
 
-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.
+...and these character encodings:
 
-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.
+* 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:
+
+    <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"
+        "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
+
+...and the character encoding from this code:
+
+    <meta http-equiv="Content-type" content="text/html;charset=ENCODING">
+
+For legacy codebases these declarations may be missing.  If that is the case,
+STOP, and read up on character encodings and doctypes (in that order).  Here
+are some links:
+
+* http://www.joelonsoftware.com/articles/Unicode.html
+* http://alistapart.com/stories/doctype/
+
+You may currently be vulnerable to XSS and other security threats, and HTML
+Purifier won't be able to fix that.
+
+
+
+4. Configuration
+
+HTML Purifier is designed to run out-of-the-box, but occasionally HTML
+Purifier needs to be told what to do.  If you answered no to any of these
+questions, read on, otherwise, you can skip to the next section (or, if you're
+into configuring things just for the heck of it, skip to 4.3).
+
+* Am I using UTF-8?
+* Am I using XHTML 1.0 Transitional?
+
+If you answered yes to any of these questions, instantiate a configuration
+object and read on:
 
     $config = HTMLPurifier_Config::createDefault();
-    $config->set('Core', 'Encoding', $encoding);
 
 
 
-3.   Using the code
+4.1. Setting a different character encoding
+
+You really shouldn't use any other encoding except UTF-8, especially if you
+plan to support multilingual websites (read section three for more details).
+However, switching to UTF-8 is not always immediately feasible, so we can
+adapt.
+
+HTML Purifier uses iconv to support other character encodings, as such,
+any encoding that iconv supports <http://www.gnu.org/software/libiconv/>
+HTML Purifier supports with this code:
+
+    $config->set('Core', 'Encoding', /* put your encoding here */);
+
+An example usage for Latin-1 websites (the most common encoding for English
+websites):
+
+    $config->set('Core', 'Encoding', 'ISO-8859-1');
+
+Note that HTML Purifier's support for non-Unicode encodings is crippled by the
+fact that any character not supported by that encoding will be silently
+dropped, EVEN if it is ampersand escaped.  This is a current limitation of
+HTML Purifier that we are NOT actively working to fix.  Patches are welcome,
+but there are so many other gotchas and problems in I18N for non-Unicode
+encodings that this functionality is low priority.  See
+<http://ppewww.ph.gla.ac.uk/~flavell/charset/form-i18n.html> for a more
+detailed lowdown on the topic.
+
+
+
+4.2. Setting a different doctype
+
+For those of you stuck using HTML 4.01 Transitional, you can disable
+XHTML output like this:
+
+    $config->set('Core', 'XHTML', false);
+
+I recommend that you use XHTML, although not as much as I recommend UTF-8.  If
+your HTML 4.01 page validates, good for you!
+
+Currently, we can only guarantee transitional-complaint output, future
+versions will also allow strict-compliant output.
+
+
+
+4.3. Other settings
+
+There are more configuration directives which can be read about
+here: <http://hp.jpsband.org/live/configdoc/plain.html>  They're a bit boring,
+but they can help out for those of you who like to exert maximum control over
+your code.
+
+
+
+5.   Using the code
 
 The interface is mind-numbingly simple:
 
     $purifier = new HTMLPurifier();
-    $clean_html = $purifier->purify($dirty_html);
+    $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.
+
+
+
+6.   Quick install
+
+If your website is in UTF-8 and XHTML Transitional, use this code:
+
+<?php
+    require_once '/path/to/htmlpurifier/library/HTMLPurifier.auto.php';
+    
+    $purifier = new HTMLPurifier();
+    $clean_html = $purifier->purify($dirty_html);
+?>
+
+If your website is in a different encoding or doctype, use this code:
+
+<?php
+    require_once '/path/to/htmlpurifier/library/HTMLPurifier.auto.php';
+    
+    $config = HTMLPurifier_Config::createDefault();
+    $config->set('Core', 'Encoding', 'ISO-8859-1'); //replace with your encoding
+    $config->set('Core', 'XHTML', true); //replace with false if HTML 4.01
+    $purifier = new HTMLPurifier($config);
+    
+    $clean_html = $purifier->purify($dirty_html);
+?>

NEWS

@@ -1,18 +1,102 @@
 NEWS ( CHANGELOG and HISTORY )                                     HTMLPurifier
 |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
 
+= KEY ====================
+    # Breaks back-compat
+    ! Feature
+    - Bugfix
+      + Sub-comment
+    . Internal change
+==========================
+
+1.2.0, released 2006-11-19
+# ID attributes now disabled by default. New directives:
+  + %HTML.EnableAttrID - restores old behavior by allowing IDs
+  + %Attr.IDPrefix - %Attr.IDBlacklist alternative that munges all user IDs
+    so that they don't collide with your IDs
+  + %Attr.IDPrefixLocal - Same as above, but for when there are multiple
+    instances of user content on the page
+  + Profuse documentation on how to use these available in docs/enduser-id.txt
+! Added MODx plugin <http://modxcms.com/forums/index.php/topic,6604.0.html>
+! Added percent encoding normalization
+! XSS attacks smoketest given facelift
+! Configuration documentation now has table of contents
+! Added %URI.DisableExternal, which prevents links to external websites.  You
+  can also use %URI.Host to permit absolute linking to subdomains
+! Non-accessible resources (ex. mailto) blocked from embedded URIs (img src)
+- Type variable in HTMLDefinition was not being set properly, fixed
+- Documentation updated
+  + TODO added request Phalanger
+  + TODO added request Native compression
+  + TODO added request Remove redundant tags
+  + TODO added possible plaintext formatter for HTML Purifier documentation
+  + Updated ConfigDoc TODO
+  + Improved inline comments in AttrDef/Class.php, AttrDef/CSS.php
+    and AttrDef/Host.php
+  + Revamped documentation into HTML, along with misc updates
+- HTMLPurifier_Context doesn't throw a variable reference error if you attempt
+  to retrieve a non-existent variable
+. Switched to purify()-wide Context object registry
+. Refactored unit tests to minimize duplication
+. XSS attack sheet updated
+. configdoc.xml now has xml:space attached to default value nodes
+. Allow configuration directives to permit null values
+. Cleaned up test-cases to remove unnecessary swallowErrors()
+
+1.1.2, released 2006-09-30
+! Add HTMLPurifier.auto.php stub file that configures include_path
+- Documentation updated
+  + INSTALL document rewritten
+  + TODO added semi-lossy conversion
+  + API Doxygen docs' file exclusions updated
+  + Added notes on HTML versus XML attribute whitespace handling
+  + Noted that HTMLPurifier_ChildDef_Custom isn't being used
+  + Noted that config object's definitions are cached versions
+- Fixed lack of attribute parsing in HTMLPurifier_Lexer_PEARSax3
+- ftp:// URIs now have their typecodes checked
+- Hooked up HTMLPurifier_ChildDef_Custom's unit tests (they weren't being run)
+. Line endings standardized throughout project (svn:eol-style standardized)
+. Refactored parseData() to general Lexer class
+. Tester named "HTML Purifier" not "HTMLPurifier"
+
+1.1.1, released 2006-09-24
+! Configuration option to optionally Tidy up output for indentation to make up
+  for dropped whitespace by DOMLex (pretty-printing for the entire application
+  should be done by a page-wide Tidy)
+- Various documentation updates
+- Fixed parse error in configuration documentation script
+- Fixed fatal error in benchmark scripts, slightly augmented
+- As far as possible, whitespace is preserved in-between table children
+- Sample test-settings.php file included
+
+1.1.0, released 2006-09-16
+! Directive documentation generation using XSLT
+! XHTML can now be turned off, output becomes <br>
+- Made URI validator more forgiving: will ignore leading and trailing
+  quotes, apostrophes and less than or greater than signs.
+- Enforce alphanumeric namespace and directive names for configuration.
+- Table child definition made more flexible, will fix up poorly ordered elements
+. Renamed ConfigDef to ConfigSchema
+
+1.0.1, released 2006-09-04
+- Fixed slight bug in DOMLex attribute parsing
+- Fixed rejection of case-insensitive configuration values when there is a
+  set of allowed values.  This manifested in %Core.Encoding.
+- Fixed rejection of inline style declarations that had lots of extra
+  space in them.  This manifested in TinyMCE.
+
 1.0.0, released 2006-09-01
+! Shorthand CSS properties implemented: font, border, background, list-style
+! Basic color keywords translated into hexadecimal values
+! Table CSS properties implemented
+! Support for charsets other than UTF-8 (defined by iconv)
+! Malformed UTF-8 and non-SGML character detection and cleaning implemented
 - Fixed broken numeric entity conversion
-- 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

@@ -2,13 +2,13 @@
 SLOW
   also known as the HELP ME LIBRARY IS TOO SLOW MY PAGE TAKE TOO LONG LOAD page
 
-HTMLPurifier is a very powerful library.  But with power comes great
+HTML Purifier is a very powerful library.  But with power comes great
 responsibility, or, at least, longer execution times.  Remember, this
 library isn't lightly grazing over submitted HTML: it's deconstructing
 the whole thing, rigorously checking the parts, and then putting it
 back together.
 
-So, if it so turns out that HTMLPurifier is kinda too slow for outbound
+So, if it so turns out that HTML Purifier is kinda too slow for outbound
 filtering, you've got a few options:
 
 1. Inbound filtering - perform filtering of HTML when it's submitted by the
@@ -17,18 +17,24 @@ 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
+makes a typo.
 
 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 report back your results if you decide to do that!  Especially if you
+port HTML Purifier to C++.  ;-)

TODO

@@ -1,50 +1,74 @@
 
 TODO List
 
-Ongoing
- - Lots of profiling, make it faster!
- - Plugins for major CMSes (very tricky issue)
+1.3 release
+ - Make URI validation routines tighter (especially mailto)
+ - More extensive URI filtering schemes (see docs/proposal-new-directives.txt)
+ - Allow for background-image and list-style-image (see above)
+ - Error logging for filtering/cleanup procedures
+ - Rich set* methods and config file loaders for HTMLPurifier_Config
 
-1.1 release
- - Directive documentation generation
- - Rewrite table's child definition to be faster, smart, and regexp free
- - Allow HTML 4.01 output (cosmetic changes to the generator)
+1.4 release
+ - Add various "levels" of cleaning
+    - Related: Allow strict (X)HTML
+ - More fine-grained control over escaping behavior
+    - Silently drop content inbetween SCRIPT tags (can be generalized to allow
+      specification of elements that, when detected as foreign, trigger removal
+      of children, although unbalanced tags could wreck havoc (or at least
+      delete the rest of the document)).
 
-1.2 release
+1.5 release
  - Additional support for poorly written HTML
     - Implement all non-essential attribute transforms
     - Microsoft Word HTML cleaning (i.e. MsoNormal)
 
-1.3 release
- - Make URI validation routines tighter (especially mailto)
- - More extensive URI filtering schemes
- - Allow for background-image and list-style-image (see above)
- - Distinguish between different types of URIs, for instance, a mailto URI
-   in IMG SRC is nonsensical
-
 2.0 release
- - Add various "levels" of cleaning
-    - Related: Allow strict (X)HTML
+ - 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
+    - Linkification for HTML Purifier docs: notably configuration and
+      class names
 
 3.0 release
  - Extended HTML capabilities based on namespacing and tag transforms
     - Hooks for adding custom processors to custom namespaced tags and
       attributes, offer default implementation
-    - Auto-paragraphing (be sure to leverage fact that we know when things
-      shouldn't be paragraphed, such as lists and tables).
     - Lots of documentation and samples
 
+Ongoing
+ - Lots of profiling, make it faster!
+ - Plugins for major CMSes (very tricky issue)
+
 Unknown release (on a scratch-an-itch basis)
- - Silently drop content inbetween SCRIPT tags (can be generalized to allow
-   specification of elements that, when detected as foreign, trigger removal
-   of children, although unbalanced tags could wreck havoc (or at least delete
-   the rest of the document)).
  - Fixes for Firefox's inability to handle COL alignment props (Bug 915)
  - Automatically add non-breaking spaces to empty table cells when
    empty-cells:show is applied to have compatibility with Internet Explorer
- - Pretty-printing HTML (adds dependency of Generator to HTMLDefinition)
+ - Convert RTL/LTR override characters to <bdo> tags, or vice versa on demand.
+   Also, enable disabling of directionality
+ - Append something to duplicate IDs so they're still usable (impl. note: the
+   dupe detector would also need to detect the suffix as well)
+ - Have 'lang' attribute be checked against official lists
+
+Encoding workarounds
  - Non-lossy dumb alternate character encoding transformations, achieved by
    numerically encoding all non-ASCII characters
+ - Semi-lossy dumb alternate character encoding transformations, achieved by
+   encoding all characters that have string entity equivalents
+
+Requested
+ - Native content compression, whitespace stripping (don't rely on Tidy, make
+   sure we don't remove from <pre> or related tags)
+ - Win32 Phalanger C# binaries (?)
+ - Remove redundant tags, ex. <u><u>Underlined</u></u>. Implementation notes:
+    1. Analyzing which tags to remove duplicants
+    2. Ensure attributes are merged into the parent tag
+    3. Extend the tag exclusion system to specify whether or not the
+    contents should be dropped or not (currently, there's code that could do
+    something like this if it didn't drop the inner text too.)
 
 Wontfix
- - Non-lossy smart alternate character encoding transformations
+ - Non-lossy smart alternate character encoding transformations (unless
+   patch provided)
+ - Pretty-printing HTML, users can use Tidy on the output on entire page

WYSIWYG

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

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

@@ -0,0 +1,218 @@
+<?php
+
+/**
+ * Generates XML and HTML documents describing configuration.
+ */
+
+/*
+TODO:
+- make XML format richer (see below)
+- extend XSLT transformation (see the corresponding XSLT file)
+- allow generation of packaged docs that can be easily moved
+- multipage documentation
+- determine how to multilingualize
+- factor out code into classes
+*/
+
+// ---------------------------------------------------------------------------
+// Check and configure environment
+
+if (version_compare('5', PHP_VERSION, '>')) exit('Requires PHP 5 or higher.');
+error_reporting(E_ALL);
+
+
+// ---------------------------------------------------------------------------
+// Include HTML Purifier library
+
+set_include_path('../library' . PATH_SEPARATOR . get_include_path());
+require_once 'HTMLPurifier.php';
+
+
+// ---------------------------------------------------------------------------
+// Setup convenience functions
+
+function appendHTMLDiv($document, $node, $html) {
+    global $purifier;
+    $html = $purifier->purify($html);
+    $dom_html = $document->createDocumentFragment();
+    $dom_html->appendXML($html);
+    
+    $dom_div = $document->createElement('div');
+    $dom_div->setAttribute('xmlns', 'http://www.w3.org/1999/xhtml');
+    $dom_div->appendChild($dom_html);
+    
+    $node->appendChild($dom_div);
+}
+
+
+// ---------------------------------------------------------------------------
+// Load copies of HTMLPurifier_ConfigDef and HTMLPurifier
+
+$schema = HTMLPurifier_ConfigSchema::instance();
+$purifier = new HTMLPurifier();
+
+
+// ---------------------------------------------------------------------------
+// Generate types.xml, a document describing the constraint "type"
+
+$types_document = new DOMDocument('1.0', 'UTF-8');
+$types_root = $types_document->createElement('types');
+$types_document->appendChild($types_root);
+$types_document->formatOutput = true;
+foreach ($schema->types as $name => $expanded_name) {
+    $types_type = $types_document->createElement('type', $expanded_name);
+    $types_type->setAttribute('id', $name);
+    $types_root->appendChild($types_type);
+}
+$types_document->save('types.xml');
+
+
+// ---------------------------------------------------------------------------
+// Generate configdoc.xml, a document documenting configuration directives
+
+$dom_document = new DOMDocument('1.0', 'UTF-8');
+$dom_root = $dom_document->createElement('configdoc');
+$dom_document->appendChild($dom_root);
+$dom_document->formatOutput = true;
+
+// add the name of the application
+$dom_root->appendChild($dom_document->createElement('title', 'HTML Purifier'));
+
+/*
+TODO for XML format:
+- create a definition (DTD or other) once interface stabilizes
+*/
+
+foreach($schema->info as $namespace_name => $namespace_info) {
+    
+    $dom_namespace = $dom_document->createElement('namespace');
+    $dom_root->appendChild($dom_namespace);
+    
+    $dom_namespace->setAttribute('id', $namespace_name);
+    $dom_namespace->appendChild(
+        $dom_document->createElement('name', $namespace_name)
+    );
+    $dom_namespace_description = $dom_document->createElement('description');
+    $dom_namespace->appendChild($dom_namespace_description);
+    appendHTMLDiv($dom_document, $dom_namespace_description,
+        $schema->info_namespace[$namespace_name]->description);
+    
+    foreach ($namespace_info as $name => $info) {
+        
+        $dom_directive = $dom_document->createElement('directive');
+        $dom_namespace->appendChild($dom_directive);
+        
+        $dom_directive->setAttribute('id', $namespace_name . '.' . $name);
+        $dom_directive->appendChild(
+            $dom_document->createElement('name', $name)
+        );
+        
+        $dom_constraints = $dom_document->createElement('constraints');
+        $dom_directive->appendChild($dom_constraints);
+        
+        $dom_type = $dom_document->createElement('type', $info->type);
+        if ($info->allow_null) {
+            $dom_type->setAttribute('allow-null', 'yes');
+        }
+        $dom_constraints->appendChild($dom_type);
+        
+        if ($info->allowed !== true) {
+            $dom_allowed = $dom_document->createElement('allowed');
+            $dom_constraints->appendChild($dom_allowed);
+            foreach ($info->allowed as $allowed => $bool) {
+                $dom_allowed->appendChild(
+                    $dom_document->createElement('value', $allowed)
+                );
+            }
+        }
+        
+        $raw_default = $schema->defaults[$namespace_name][$name];
+        if (is_bool($raw_default)) {
+            $default = $raw_default ? 'true' : 'false';
+        } elseif (is_string($raw_default)) {
+            $default = "\"$raw_default\"";
+        } elseif (is_null($raw_default)) {
+            $default = 'null';
+        } else {
+            $default = print_r(
+                    $schema->defaults[$namespace_name][$name], true
+                );
+        }
+        
+        $dom_default = $dom_document->createElement('default', $default);
+        
+        // remove this once we get a DTD
+        $dom_default->setAttribute('xml:space', 'preserve');
+        
+        $dom_constraints->appendChild($dom_default);
+        
+        $dom_descriptions = $dom_document->createElement('descriptions');
+        $dom_directive->appendChild($dom_descriptions);
+        
+        foreach ($info->descriptions as $file => $file_descriptions) {
+            foreach ($file_descriptions as $line => $description) {
+                $dom_description = $dom_document->createElement('description');
+                $dom_description->setAttribute('file', $file);
+                $dom_description->setAttribute('line', $line);
+                appendHTMLDiv($dom_document, $dom_description, $description);
+                $dom_descriptions->appendChild($dom_description);
+            }
+        }
+        
+    }
+    
+}
+
+// print_r($dom_document->saveXML());
+
+// save a copy of the raw XML
+$dom_document->save('configdoc.xml');
+
+
+// ---------------------------------------------------------------------------
+// Generate final output using XSLT
+
+// load the stylesheet
+$xsl_stylesheet_name = 'plain';
+$xsl_stylesheet = "styles/$xsl_stylesheet_name.xsl";
+$xsl_dom_stylesheet = new DOMDocument();
+$xsl_dom_stylesheet->load($xsl_stylesheet);
+
+// setup the XSLT processor
+$xsl_processor = new XSLTProcessor();
+
+// perform the transformation
+$xsl_processor->importStylesheet($xsl_dom_stylesheet);
+$html_output = $xsl_processor->transformToXML($dom_document);
+
+// some slight fudges to preserve backwards compatibility
+$html_output = str_replace('/>', ' />', $html_output); // <br /> not <br>
+$html_output = str_replace(' xmlns=""', '', $html_output); // rm unnecessary xmlns
+
+if (class_exists('Tidy')) {
+    // cleanup output
+    $config = array(
+        'indent'        => true,
+        'output-xhtml'  => true,
+        'wrap'          => 80
+    );
+    $tidy = new Tidy;
+    $tidy->parseString($html_output, $config, 'utf8');
+    $tidy->cleanRepair();
+    $html_output = (string) $tidy;
+}
+
+// write it to a file (todo: parse into seperate pages)
+file_put_contents("$xsl_stylesheet_name.html", $html_output);
+
+
+// ---------------------------------------------------------------------------
+// Output for instant feedback
+
+if (php_sapi_name() != 'cli') {
+    echo $html_output;
+} else {
+    echo 'Files generated successfully.';
+}
+
+?>

configdoc/styles/plain.css

@@ -0,0 +1,10 @@
+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;}
+
+#toc {list-style-type:none; font-weight:bold;}
+#toc ul {list-style-type:disc; font-weight:normal;}

configdoc/styles/plain.xsl

@@ -0,0 +1,126 @@
+<?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>
+                <h1><xsl:value-of select="/configdoc/title" /> Configuration Documentation</h1>
+                <h2>Table of Contents</h2>
+                <ul id="toc">
+                    <xsl:apply-templates mode="toc" />
+                </ul>
+                <xsl:apply-templates />
+            </body>
+        </html>
+    </xsl:template>
+    
+    <xsl:template match="title" mode="toc" />
+    <xsl:template match="namespace" mode="toc">
+        <xsl:if test="count(directive)&gt;0">
+            <li>
+                <a href="#{@id}"><xsl:value-of select="name" /></a>
+                <ul>
+                    <xsl:apply-templates select="directive" mode="toc" />
+                </ul>
+            </li>
+        </xsl:if>
+    </xsl:template>
+    <xsl:template match="directive" mode="toc">
+        <li><a href="#{@id}"><xsl:value-of select="name" /></a></li>
+    </xsl:template>
+    
+    <xsl:template match="title" />
+    
+    <xsl:template match="namespace">
+        <xsl:apply-templates />
+        <xsl:if test="count(directive)=0">
+            <p>No configuration directives defined for this namespace.</p>
+        </xsl:if>
+    </xsl:template>
+    <xsl:template match="namespace/name">
+        <h2 id="{../@id}"><xsl:value-of select="." /></h2>
+    </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="../@id" /></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()" />
+                <xsl:if test="@allow-null='yes'">
+                    (or null)
+                </xsl:if>
+            </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

@@ -1,40 +0,0 @@
-
-Code Quality Issues
-
-Okay, face it.  Programmers can get lazy, cut corners, or make mistakes. They
-also can do quick prototypes, and then forget to rewrite them later.  Well,
-while I can't list mistakes in here, I can list prototype-like segments
-of code that should be aggressively refactored after the beta is released.
-This does not list optimization issues, that needs to be done after intense
-profiling.
-
-Here we go:
-
-AttrDef
-    Class - doesn't support Unicode characters, uses regular expressions
-    Lang - code duplication, premature optimization, doesn't consult official
-        lists
-    Pixels/Length/MultiLength - implemented according to HTML spec (excludes
-        code reuse in CSS)
-    URI - multiple regular expressions, needs host validation routines factored
-        out for mailto scheme, IPv6 validation is broken (fringe), unintuitive
-        variable overwriting, missing validation for query, fragment and path,
-        no percent-encode fixing
-    CSS - parser doesn't accept advanced CSS (fringe)
-    Number - constructor interface is inconsistent with Integer
-AttrTransform - doesn't accept AttrContext, non-validating
-ChildDef - not-allowed nodes translated to text, likely invalid handling
-Config - "load configuration" hooks missing, rich set* accessors missing,
-    needs redefined relationship with the definitions
-Strategy
-    FixNesting - cannot bubble nodes out of structures
-    MakeWellFormed - insufficient automatic closing definitions (check HTML
-        spec for optional end tags).
-    RemoveForeignElements - should be run in parallel with MakeWellFormed
-URIScheme - needs to have callable generic checks
-    ftp - missing typecode check
-    mailto - doesn't validate emails
-    news - doesn't validate opaque path
-    nntp - doesn't constrain path
-EOL
-

docs/config-ideas.txt

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

docs/dev-code-quality.html

@@ -0,0 +1,48 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN"
+    "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">
+<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en"><head>
+<meta http-equiv="Content-Type" content="text/html; charset=UTF-8" />
+<meta name="description" content="Discusses code quality issues and places that need to be refactored in HTML Purifier." />
+<link rel="stylesheet" type="text/css" href="./style.css" />
+
+<title>Code Quality Issues - HTML Purifier</title>
+
+</head><body>
+
+<h1>Code Quality Issues</h1>
+
+<div id="filing">Filed under Development</div>
+<div id="index">Return to the <a href="index.html">index</a>.</div>
+
+<p>Okay, face it.  Programmers can get lazy, cut corners, or make mistakes. They
+also can do quick prototypes, and then forget to rewrite them later.  Well,
+while I can't list mistakes in here, I can list prototype-like segments
+of code that should be aggressively refactored.  This does not list
+optimization issues, that needs to be done after intense profiling.</p>
+
+<pre>
+AttrDef
+    Class - doesn't support Unicode characters (fringe); uses regular
+        expressions
+    Lang - code duplication; premature optimization
+    Length - easily mistaken for CSSLength
+    URI - multiple regular expressions; missing validation for parts (?)
+    CSS - parser doesn't accept advanced CSS (fringe)
+    Number - constructor interface inconsistent with Integer
+ConfigSchema - redefinition is a mess
+Strategy
+    FixNesting - cannot bubble nodes out of structures
+    MakeWellFormed - insufficient automatic closing definitions (check HTML
+        spec for optional end tags, also, closing based on type (block/inline)
+        might be efficient).
+    RemoveForeignElements - should be run in parallel with MakeWellFormed
+URIScheme - needs to have callable generic checks
+    mailto - doesn't validate emails, doesn't validate querystring
+    news - doesn't validate opaque path
+    nntp - doesn't constrain path
+</pre>
+
+<div id="version">$Id$</div>
+
+</body></html>

docs/dev-naming.html

@@ -0,0 +1,80 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN"
+    "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">
+<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en"><head>
+<meta http-equiv="Content-Type" content="text/html; charset=UTF-8" />
+<meta name="description" content="Defines class naming conventions in HTML Purifier." />
+<link rel="stylesheet" type="text/css" href="./style.css" />
+
+<title>Naming Conventions - HTML Purifier</title>
+
+</head><body>
+
+<h1>Naming Conventions</h1>
+
+<div id="filing">Filed under Development</div>
+<div id="index">Return to the <a href="index.html">index</a>.</div>
+
+<p>The classes in this library follow a few naming conventions, which may
+help you find the correct functionality more quickly.  Here they are:</p>
+
+<dl>
+
+<dt>All classes occupy the HTMLPurifier pseudo-namespace.</dt>
+    <dd>This means that all classes are prefixed with HTMLPurifier_.  As such, all
+    names under HTMLPurifier_ are reserved.  I recommend that you use the name
+    HTMLPurifierX_YourName_ClassName, especially if you want to take advantage
+    of HTMLPurifier_ConfigDef.</dd>
+
+<dt>All classes correspond to their path if library/ was in the include path</dt>
+    <dd>HTMLPurifier_AttrDef is located at HTMLPurifier/AttrDef.php; replace
+    underscores with slashes and append .php and you'll have the location of
+    the class.</dd>
+
+<dt>Harness and Test are reserved class names for unit tests</dt>
+    <dd>The suffix <code>Test</code> indicates that the class is a subclass of UnitTestCase
+    (of the Simpletest library) and is testable. "Harness" indicates a subclass
+    of UnitTestCase that is not meant to be run but to be extended into 
+    concrete test cases and contains custom test methods (i.e. assert*())</dd>
+
+<dt>Class names do not necessarily represent inheritance hierarchies</dt>
+    <dd>While we try to reflect inheritance in naming to some extent, it is not
+    guaranteed (for instance, none of the classes inherit from HTMLPurifier,
+    the base class).  However, all class files have the require_once
+    declarations to whichever classes they are tightly coupled to.</dd>
+
+<dt>Strategy has a meaning different from the Gang of Four pattern</dt>
+    <dd>In Design Patterns, the Gang of Four describes a Strategy object as
+    encapsulating an algorithm so that they can be switched at run-time.  While
+    our strategies are indeed algorithms, they are not meant to be substituted:
+    all must be present in order for proper functioning.</dd>
+
+<dt>Abbreviations are avoided</dt>
+    <dd>We try to avoid abbreviations as much as possible, but in some cases, 
+    abbreviated version is more readable than the full version. Here, we
+    list common abbreviations:
+    <ul>
+        <li>Attr(s) to Attribute(s)</li>
+        <li>Def to Definition</li>
+    </ul>
+    </dd>
+
+<dt>Ambiguity concerning the definition of Def/Definition</dt>
+    <dd>While a definition normally defines the structure/acceptable values of
+    an entity, most of the definitions in this application also attempt
+    to validate and fix the value.  I am unsure of a better name, as
+    "Validator" would exclude fixing the value, "Fixer" doesn't invoke
+    the proper image of "fixing" something, and "ValidatorFixer" is too long!
+    Some other suggestions were "Handler", "Reference", "Check", "Fix",
+    "Repair" and "Heal".</dd>
+
+<dt>Transform not Transformer</dt>
+    <dd>Transform is both a noun and a verb, and thus we define a "Transform" as
+    something that "transforms," leaving "Transformer" (which sounds like an
+    electrical device/robot toy).</dd>
+
+</dl>
+
+<div id="version">$Id$</div>
+
+</body></html>

docs/dev-optimization.html

@@ -0,0 +1,32 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN"
+    "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">
+<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en"><head>
+<meta http-equiv="Content-Type" content="text/html; charset=UTF-8" />
+<meta name="description" content="Discusses possible methods of optimizing HTML Purifier." />
+<link rel="stylesheet" type="text/css" href="./style.css" />
+
+<title>Optimization - HTML Purifier</title>
+
+</head><body>
+
+<h1>Optimization</h1>
+
+<div id="filing">Filed under Development</div>
+<div id="index">Return to the <a href="index.html">index</a>.</div>
+
+<p>Here are some possible optimization techniques we can apply to code sections if
+they turn out to be slow.  Be sure not to prematurely optimize: if you get
+that itch, put it here!</p>
+
+<ul>
+    <li>Make Tokens Flyweights (may prove problematic, probably not worth it)</li>
+    <li>Rewrite regexps into PHP code</li>
+    <li>Serialize the Definition object</li>
+    <li>Batch regexp validation (do as many per function call as possible)</li>
+    <li>Parallelize strategies</li>
+</ul>
+
+<div id="version">$Id$</div>
+
+</body></html>

docs/dev-progress.html

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

docs/dtd/xhtml1-purified.dtd

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

docs/enduser-id.html

@@ -0,0 +1,146 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN"
+    "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">
+<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en"><head>
+<meta http-equiv="Content-Type" content="text/html; charset=UTF-8" />
+<meta name="description" content="Explains various methods for allowing IDs in documents safely in HTML Purifier." />
+<link rel="stylesheet" type="text/css" href="./style.css" />
+
+<title>IDs - HTML Purifier</title>
+
+</head><body>
+
+<h1 class="subtitled">IDs</h1>
+<div class="subtitle">What they are, why you should(n't) wear them, and how to deal with it</div>
+
+<div id="filing">Filed under End-User</div>
+<div id="index">Return to the <a href="index.html">index</a>.</div>
+
+<p>Prior to HTML Purifier 1.2.0, this library blithely accepted user input that
+looked like this:</p>
+
+<pre>&lt;a id=&quot;fragment&quot;&gt;Anchor&lt;/a&gt;</pre>
+
+<p>...presenting an attractive vector for those that would destroy standards
+compliance: simply set the ID to one that is already used elsewhere in the
+document and voila: validation breaks.  There was a half-hearted attempt to
+prevent this by allowing users to blacklist IDs, but I suspect that no one
+really bothered, and thus, with the release of 1.2.0, IDs are now <em>removed</em>
+by default.</p>
+
+<p>IDs, however, are quite useful functionality to have, so if users start
+complaining about broken anchors you'll probably want to turn them back on
+with %HTML.EnableAttrID. But before you go mucking around with the config
+object, it's probably worth to take some precautions to keep your page
+validating. Why?</p>
+
+<ol>
+   <li>Standards-compliant pages are good</li>
+   <li>Duplicated IDs interfere with anchors.  If there are two id="foobar"s in a
+   document, which spot does a browser presented with the fragment #foobar go
+   to? Most browsers opt for the first appearing ID, making it impossible
+   to references the second section. Similarly, duplicated IDs can hijack
+   client-side scripting that relies on the IDs of elements.</li>
+</ol>
+
+<p>You have (currently) four ways of dealing with the problem.</p>
+
+
+
+<h2 class="subtitled">Blacklisting IDs</h2>
+<div class="subsubtitle">Good for pages with single content source and stable templates</div>
+
+<p>Keeping in terms with the
+<acronym title="Keep It Simple, Stupid">KISS</acronym> principle, let us
+deal with the most obvious solution: preventing users from using any IDs that
+appear elsewhere on the document.  The method is simple:</p>
+
+<pre>$config->set('HTML', 'EnableAttrID', true);
+$config->set('Attr', 'IDBlacklist' array(
+    'list', 'of', 'attributes', 'that', 'are', 'forbidden'
+));</pre>
+
+<p>That being said, there are some notable drawbacks.  First of all, you have to
+know precisely which IDs are being used by the HTML surrounding the user code.
+This is easier said than done: quite often the page designer and the system
+coder work separately, so the designer has to constantly be talking with the
+coder whenever he decides to add a new anchor.  Miss one and you open yourself
+to possible standards-compliance issues.</p>
+
+<p>Furthermore, this position becomes untenable when a single web page must hold
+multiple portions of user-submitted content.  Since there's obviously no way
+to find out before-hand what IDs users will use, the blacklist is helpless.
+And even since HTML Purifier validates each segment seperately, perhaps doing
+so at different times, it would be extremely difficult to dynamically update
+the blacklist inbetween runs.</p>
+
+<p>Finally, simply destroying the ID is extremely un-userfriendly behavior: after
+all, they might have simply specified a duplicate ID by accident.</p>
+
+<p>Thus, we get to our second method.</p>
+
+
+
+<h2 class="subtitled">Namespacing IDs</h2>
+<div class="subsubtitle">Lazy developer's way, but needs user education</div>
+
+<p>This method, too, is quite simple: add a prefix to all user IDs. With this
+code:</p>
+
+<pre>$config->set('HTML', 'EnableAttrID', true);
+$config->set('Attr', 'IDPrefix', 'user_');</pre>
+
+<p>...this:</p>
+
+<pre>&lt;a id=&quot;foobar&quot;&gt;Anchor!&lt;/a&gt;</pre>
+
+<p>...turns into:</p>
+
+<pre>&lt;a id=&quot;user_foobar&quot;&gt;Anchor!&lt;/a&gt;</pre>
+
+<p>As long as you don't have any IDs that start with user_, collisions are
+guaranteed not to happen.  The drawback is obvious: if a user submits
+id=&quot;foobar&quot;, they probably expect to be able to reference their page with
+#foobar. You'll have to tell them, &quot;No, that doesn't work, you have to add
+user_ to the beginning.&quot;</p>
+
+<p>And yes, things get hairier.  Even with a nice prefix, we still have done
+nothing about multiple HTML Purifier outputs on one page.  Thus, we have
+a second configuration value to piggy-back off of: %Attr.IDPrefixLocal:</p>
+
+<pre>$config->set('Attr', 'IDPrefixLocal', 'comment' . $id . '_');</pre>
+
+<p>This new attributes does nothing but append on to regular IDPrefix, but is
+special in that it is volatile: it's value is determined at run-time and
+cannot possibly be cordoned into, say, a .ini config file.  As for what to
+put into the directive, is up to you, but I would recommend the ID number
+the text has been assigned in the database.  Whatever you pick, however, it
+has to be unique and stable for the text you are validating.  Note, however,
+that we require that %Attr.IDPrefix be set before you use this directive.</p>
+
+<p>And also remember: the user has to know what this prefix is too!</p>
+
+
+
+<h2>Abstinence</h2>
+
+<p>You may not want to bother. That's okay too, just don't enable IDs.</p>
+
+<p>Personally, I would take this road whenever user-submitted content would be
+possibly be shown together on one page.  Why a blog comment would need to use
+anchors is beyond me.</p>
+
+
+
+<h2>Denial</h2>
+
+<p>To revert back to pre-1.2.0 behavior, simply:</p>
+
+<pre>$config->set('HTML', 'EnableAttrID', true);</pre>
+
+<p>Don't come crying to me when your page mysteriously stops validating, though.</p>
+
+<div id="version">$Id$</div>
+
+</body>
+</html>

docs/enduser-overview.txt

@@ -54,4 +54,4 @@ HTML Purifier is best suited for documents that require a rich array of
 HTML tags.  Things like blog comments are, in all likelihood, most appropriately
 written in an extremely restrictive set of markup that doesn't require
 all this functionality (or not written in HTML at all), although this may
-be changing in the future.
+be changing in the future with the addition of levels of filtering.

docs/enduser-security.txt

@@ -6,35 +6,43 @@ through negligence of people. This class will do its job: no more, no less,
 and it's up to you to provide it the proper information and proper context
 to be effective. Things to remember:
 
-1. UTF-8. Currently, the parser runs under the assumption that it is dealing
+1. Character Encoding: UTF-8.
+Currently, the parser runs under the assumption that it is dealing
 with UTF-8. Not ISO-8859-1 or Windows-1252, UTF-8. And definitely not "no
 character encoding explicitly stated" or UTF-7. If you're not using UTF-8 as
-your character encoding, you should switch. Now. Make sure any input is
-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).
-We will be adding out-of-the-box support for the other major character
-encodings shortly.
+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
 in a document, but that's not likely to be implemented for a while.  In the
 meantime, be sure to make sure that floated elements (permitted, since they
-can be quite useful) can't mess up your layout.
+can be quite useful) can't mess up your layout. Once again, we may want to
+disable this by default to protect lazy developers.

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

@@ -1,67 +0,0 @@
-
-Filter Levels
-    When one size *does not* fit all
-
-The more I think about it, the less sense it makes for maintaining one huge
-monolithic HTMLDefinition class.  There's simply so much variation that
-could go into this definition: the set of HTML good for blog entries is
-definitely too large for HTML that would be allowed in blog comments. Going
-from Transitional to Strict requires changes to the definition.
-
-However, allowing users to specify their own whitelists was an idea I
-rejected from the start.  Simply put, the typical programmer is too lazy
-to actually go through the trouble of investigating which tags, attributes
-and properties to allow.  HTMLDefinition makes a big part of what HTMLPurifier
-is.
-
-The idea, then, is to setup fundamentally different set of definitions, which
-can further be customized using simpler configuration options.
-
-Here are some fuzzy levels you could set:
-
-1. Comments - Wordpress recommends a, abbr, acronym, b, blockquote, cite,
-    code, em, i, strike, strong; however, you could get away with only a, b and
-    i; also having p and pre tags would be helpful.
-2. 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.
-
-I've also decomposed tags into risk levels.  An asterisk indicates that no one
-really uses that tag, tilde indicates it's deprecated.
-
-1 - blockquote, code, em, i, p, tt / strong, sub, sup
-1* - abbr, acronym, bdo, cite, dfn, kbd, q, samp
-2 - b, br, del, div, pre, span / ins, s, strike ~ u
-3 - h2, h3, h4, h5, h6 ~ center
-4 - h1, big ~ font
-5 - a
-7 - area, map
-
-Lists - dd, dl, dt, li, ol, ul ~ menu, dir
-Tables - caption, table, td, th, tr / col, colgroup, tbody, tfoot, thead
-Forms - fieldset, form, input, lable, legend, optgroup, option, select, textarea
-XSS - noscript, object, script ~ applet
-
-Meta - base, basefont, body, head, html, link, meta, style, title
-Frames - frame, frameset, iframe
-
-And tag specific notes:
-
-a - general problems involving linkspam
-b - too much bold is bad, typographically speaking bold is discouraged
-br - often misused
-center - CSS, usually no legit use
-del - only useful in editing context
-div - little meaning in certain contexts i.e. blog comment
-h1 - usually no legit use, as header is already set by application
-h* - not needed in blog comments
-hr - usually not necessary in blog comments
-img - could be extremely undesirable if linking to external pics
-pre - could use formatting, only useful in code contexts
-q - very little support
-s - transform into span with styling or del?
-small - technically presentational
-span - depends on attribute allowances
-sub, sup - specialized
-u - little legit use, prefer class with text-decoration

docs/index.html

@@ -0,0 +1,70 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN"
+    "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">
+<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en"><head>
+<meta http-equiv="Content-Type" content="text/html; charset=UTF-8" />
+<meta name="description" content="Index to all HTML Purifier documentation." />
+<link rel="stylesheet" type="text/css" href="./style.css" />
+
+<title>Documentation - HTML Purifier</title>
+
+</head>
+<body>
+
+<h1>Documentation</h1>
+
+<p><strong>HTML Purifier</strong> has documentation for all types of people.
+Here is an index of all of them.</p>
+
+<h2>End-user</h2>
+<p>End-user documentation that contains articles, tutorials and useful
+information for casual developers using HTML Purifier.</p>
+
+<dl>
+
+<dt><a href="enduser-id.html">IDs</a></dt>
+<dd>Explains various methods for allowing IDs in documents safely in HTML Purifier.</dd>
+
+</dl>
+
+<h2>Development</h2>
+<p>Developer documentation detailing code issues, roadmaps and project
+conventions.</p>
+
+<dl>
+
+<dt><a href="dev-code-quality.html">Code Quality Issues</a></dt>
+<dd>Discusses code quality issues and places that need to be refactored.</dd>
+
+<dt><a href="dev-progress.html">Implementation Progress</a></dt>
+<dd>Tables detailing HTML element and CSS property implementation coverage.</dd>
+
+<dt><a href="dev-naming.html">Naming Conventions</a></dt>
+<dd>Defines class naming conventions.</dd>
+
+<dt><a href="dev-optimization.html">Optimization</a></dt>
+<dd>Discusses possible methods of optimizing HTML Purifier.</dd>
+
+</dl>
+
+<h2>Proposals</h2>
+<p>Proposed features, as well as the associated rambling to get a clear
+objective in place before attempted implementation.</p>
+
+<dl>
+<dt><a href="proposal-colors.html">Colors</a></dt>
+<dd>Proposal to allow for color constraints.</dd>
+</dl>
+
+<h2>Reference</h2>
+<p>Miscellaneous essays, research pieces and other reference type material
+that may not directly discuss HTML Purifier.</p>
+
+<dl>
+<dt><a href="ref-devnetwork.html">DevNetwork Credits</a></dt>
+<dd>Credits and links to DevNetwork forum topics.</dd>
+</dl>
+
+<div id="version">$Id$</div>
+</body>
+</html>

docs/naming.txt

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

docs/optimization.txt

@@ -1,11 +0,0 @@
-
-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!
-
- - Make Tokens Flyweights
- - Rewrite regexps into PHP code
- - Serialize the Definition object
- - Batch regexp validation (do as many per function call as possible)
- - Parallelize strategies

docs/proposal-colors.html

@@ -0,0 +1,47 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN"
+    "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">
+<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en"><head>
+<meta http-equiv="Content-Type" content="text/html; charset=UTF-8" />
+<meta name="description" content="Proposal to allow for color constraints in HTML Purifier." />
+<link rel="stylesheet" type="text/css" href="./style.css" />
+
+<title>Proposal: Colors - HTML Purifier</title>
+
+</head><body>
+
+<h1 class="subtitled">Colors</h1>
+<div class="subtitle">Hammering some sense into those color-blind newbies</div>
+
+<div id="filing">Filed under Proposals</div>
+<div id="index">Return to the <a href="index.html">index</a>.</div>
+
+<p>Your website probably has a color-scheme.
+<span style="color:#090; background:#FFF;">Green on white</span>,
+<span style="color:#A0F; background:#FF0;">purple on yellow</span>,
+whatever. When you give users the ability to style their content, you may
+want them to keep in line with your styling. If you're website is all
+about light colors, you don't want a user to come in and vandalize your
+page with a deep maroon.</p>
+
+<p>This is an extremely silly feature proposal, but I'm writing it down anyway.</p>
+
+<p>What if the user could constrain the colors specified in inline styles? You
+are only allowed to use these shades of dark green for text and these shades
+of light yellow for the background. At the very least, you could ensure
+that we did not have pale yellow on white text.</p>
+
+<h2>Implementation issues</h2>
+
+<ol>
+<li>Requires the color attribute definition to know, currently, what the text
+and background colors are. This becomes difficult when classes are thrown
+into the mix.</li>
+<li>The user still has to define the permissible colors, how does one do
+something like that?</li>
+</ol>
+
+<div id="version">$Id$</div>
+
+</body>
+</html>

docs/proposal-config.txt

@@ -10,25 +10,13 @@ Directives are divided into namespaces, indicating the major portion of
 functionality they cover (although there may be overlaps.  Please consult
 the documentation in ConfigDef for more information on these namespaces.
 
-Since configuration is dependent on context, most of the internal classes
-require a configuration object to be passed as a parameter.  However, a few
-make this optional: they will supply a default configuration object if none
-are passed.  These classes are: HTMLPurifier::*, Generator::generateFromTokens
-and Lexer::tokenizeHTML.  However, whenever a valid configuration object
-is defined, that object should be used.
+Since configuration is dependant on context, internal classes require a
+configuration object to be passed as a parameter.  (They also require a
+Context object).
 
--- the following is projected changes to the configuration system --
-
-In relation to HTMLDefinition and CSSDefinition, there are going to be some
-major structural changes to enable the easy configuration of these objects.
-Due to the intricacy of these objects, it's not feasible to ask an average
-user to twiddle around with an element and its 20 other dependencies.  However,
-these objects are the only possible point where change could occur in the
-context of configuration.
-
-The solution is to introduce a special class of directives that influence the
-*construction* of the Definition object.  A standard call pattern would look
-like:
+In relation to HTMLDefinition and CSSDefinition, there is a special class
+of directives that influence the *construction* of the Definition object.
+A standard call pattern would look like:
 
 1. Client calls Config->getHTMLDefinition()
 2. Config calls HTMLDefinition->createNew(this)

docs/proposal-filter-levels.txt

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

docs/proposal-language.txt

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

docs/proposal-new-directives.txt

@@ -0,0 +1,59 @@
+
+Configuration Ideas
+
+Here are some theoretical configuration ideas that we could implement some
+time.  Note the naming convention: %Namespace.Directive
+
+%Attr.IDPrefix - prefix all ids with this
+
+%Attr.RewriteFragments - if there's %Attr.IDPrefix we may want to transparently
+    rewrite the URLs we parse too.  However, we can only do it when it's a pure
+    anchor link, so it's not foolproof
+
+%Attr.ClassBlacklist,
+%Attr.ClassWhitelist,
+%Attr.ClassPolicy - determines what classes are allowed. When
+    %Attr.ClassPolicy is set to Blacklist, only allow those not in
+    %Attr.ClassBlacklist. When it's Whitelist, only allow those in
+    %Attr.ClassWhitelist.
+
+%Attr.MaxWidth, 
+%Attr.MaxHeight - caps for width and height related checks.
+    (the hack in Pixels for an image crashing attack could be replaced by this)
+
+%URI.Munge - will munge all external URIs to a different URI, which redirects
+    the user to the applicable page. A urlencoded version of the URI
+    will replace any instances of %s in the string. One possible
+    string is 'http://www.google.com/url?q=%s'. Useful for preventing
+    pagerank from being sent to other sites, but can also be used to
+    redirect to a splash page notifying user that they are leaving your
+    website.
+
+%URI.AddRelNofollow - will add rel="nofollow" to all links, preventing the
+    spread of ill-gotten pagerank
+
+%URI.RelativeToAbsolute - transforms all relative URIs to absolute form
+
+%URI.HostBlacklist - strings that if found in the host of a URI are disallowed
+%URI.HostBlacklistRegex - regexes that if matching the host are disallowed
+%URI.HostWhitelist - domain names that are excluded from the host blacklist
+%URI.HostPolicy - determines whether or not its reject all and then whitelist
+    or allow all in then do specific blacklists with whitelist intervening.
+    'DenyAll' or 'AllowAll' (default)
+
+%URI.DisableIPHosts - URIs that have IP addresses for hosts are disallowed.
+    Be sure to also grab unusual encodings (dword, hex and octal), which may
+    be currently be caught by regular DNS
+%URI.DisableIDN - Disallow raw internationalized domain names. Punycode
+    will still be permitted.
+
+%URI.ConvertUnusualIPHosts - transform dword/hex/octal IP addresses to the
+    regular form
+%URI.ConvertAbsoluteDNS - Remove extra dots after host names that trigger
+    absolute DNS.  While this is actually the preferred method according to
+    the RFC, most people opt to use a relative domain name relative to . (root).
+
+%URI.DisableExternalResources - disallow resource links (i.e. URIs that result
+    in immediate requests, such as src in IMG) to external websites
+
+%HTML.DisableImg - disables all images

docs/ref-devnetwork.html

@@ -1,31 +1,44 @@
-<?xml version="1.0" encoding="UTF-8"?>
-<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN"
-    "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">
-<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en"><head>
-
-<title>DevNetwork Forums</title>
-
-</head>
-<body>
-
-<p>Many thanks to the DevNetwork community for answering questions,
-theorizing about design, and offering encouragement during
-the development of this library in these forum threads:</p>
-
-<ul>
-    <li><a href="http://forums.devnetwork.net/viewtopic.php?t=52905">HTMLPurifier PHP Library hompeage</a></li>
-    <li><a href="http://forums.devnetwork.net/viewtopic.php?t=53056">How much of CSS to implement?</a></li>
-    <li><a href="http://forums.devnetwork.net/viewtopic.php?t=53083">Parsing URL only according to URI : Security Risk?</a></li>
-    <li><a href="http://forums.devnetwork.net/viewtopic.php?t=53096">Gimme a name : URI and friends</a></li>
-    <li><a href="http://forums.devnetwork.net/viewtopic.php?t=53415">How to document configuration directives</a></li>
-    <li><a href="http://forums.devnetwork.net/viewtopic.php?t=53479">IPv6</a></li>
-    <li><a href="http://forums.devnetwork.net/viewtopic.php?t=53539">http and ftp versus news and mailto</a></li>
-    <li><a href="http://forums.devnetwork.net/viewtopic.php?t=53579">HTMLPurifier - Take your best shot</a></li>
-    <li><a href="http://forums.devnetwork.net/viewtopic.php?t=53664">Need help optimizing a block of code</a>
-    <li><a href="http://forums.devnetwork.net/viewtopic.php?t=53861">Non-SGML characters</a>
-    <li><a href="http://forums.devnetwork.net/viewtopic.php?t=54283">Wordpress makes me cry</a>
-    <li><a href="http://forums.devnetwork.net/viewtopic.php?t=54478">Parameter Object vs. Parameter Array vs. Parameter Functions</a>
-    <li><a href="http://forums.devnetwork.net/viewtopic.php?t=54521">Convert encoding where output cannot represent characters</a>
-</ul>
-</body>
+<?xml version="1.0" encoding="UTF-8"?>
+<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN"
+    "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">
+<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en"><head>
+<meta http-equiv="Content-Type" content="text/html; charset=UTF-8" />
+<meta name="description" content="Credits and links to DevNetwork forum topics on HTML Purifier." />
+<link rel="stylesheet" type="text/css" href="./style.css" />
+
+<title>DevNetwork Credits - HTML Purifier</title>
+
+</head>
+<body>
+
+<h1>DevNetwork Credits</h1>
+
+<div id="filing">Filed under Reference</div>
+<div id="index">Return to the <a href="index.html">index</a>.</div>
+
+<p>Many thanks to the DevNetwork community for answering questions,
+theorizing about design, and offering encouragement during
+the development of this library in these forum threads:</p>
+
+<ul>
+    <li><a href="http://forums.devnetwork.net/viewtopic.php?t=52905">HTMLPurifier PHP Library hompeage</a></li>
+    <li><a href="http://forums.devnetwork.net/viewtopic.php?t=53056">How much of CSS to implement?</a></li>
+    <li><a href="http://forums.devnetwork.net/viewtopic.php?t=53083">Parsing URL only according to URI : Security Risk?</a></li>
+    <li><a href="http://forums.devnetwork.net/viewtopic.php?t=53096">Gimme a name : URI and friends</a></li>
+    <li><a href="http://forums.devnetwork.net/viewtopic.php?t=53415">How to document configuration directives</a></li>
+    <li><a href="http://forums.devnetwork.net/viewtopic.php?t=53479">IPv6</a></li>
+    <li><a href="http://forums.devnetwork.net/viewtopic.php?t=53539">http and ftp versus news and mailto</a></li>
+    <li><a href="http://forums.devnetwork.net/viewtopic.php?t=53579">HTMLPurifier - Take your best shot</a></li>
+    <li><a href="http://forums.devnetwork.net/viewtopic.php?t=53664">Need help optimizing a block of code</a></li>
+    <li><a href="http://forums.devnetwork.net/viewtopic.php?t=53861">Non-SGML characters</a></li>
+    <li><a href="http://forums.devnetwork.net/viewtopic.php?t=54283">Wordpress makes me cry</a></li>
+    <li><a href="http://forums.devnetwork.net/viewtopic.php?t=54478">Parameter Object vs. Parameter Array vs. Parameter Functions</a></li>
+    <li><a href="http://forums.devnetwork.net/viewtopic.php?t=54521">Convert encoding where output cannot represent characters</a></li>
+    <li><a href="http://forums.devnetwork.net/viewtopic.php?t=56411">Reporting errors in a document without line numbers</a></li>
+</ul>
+
+<p>...as well as any I may have forgotten.</p>
+
+<div id="version">$Id$</div>
+</body>
 </html>

docs/ref-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.

docs/style.css

@@ -0,0 +1,40 @@
+html {font-size:1em; font-family:serif; }
+body {margin-left:4em; margin-right:4em; }
+
+dt {font-weight:bold; }
+pre {margin-left:2em; }
+pre, code, tt {font-family:monospace; font-size:1em; }
+
+h1 {text-align:center; font-family:Garamond, serif;
+  font-variant:small-caps;}
+h2 {border-bottom:1px solid #CCC; font-family:sans-serif; font-weight:normal;
+    font-size:1.3em;}
+h3 {font-family:sans-serif; font-size:1.1em; font-weight:bold; }
+h4 {font-family:sans-serif; font-size:0.9em; font-weight:bold; }
+
+/* For witty quips */
+.subtitled {margin-bottom:0em;}
+.subtitle , .subsubtitle {font-size:.8em; margin-bottom:1em;
+    font-style:italic; margin-top:-.2em;text-align:center;}
+.subsubtitle {text-align:left;margin-left:2em;}
+
+/* Used for special "See also" links. */
+.reference {font-style:italic;margin-left:2em;}
+
+/* Marks off asides, discussions on why something is the way it is */
+.aside {margin-left:2em; font-family:sans-serif; font-size:0.9em; }
+
+/* A regular table */
+.table {border-collapse:collapse; border-bottom:2px solid #888; margin-left:2em; }
+.table thead th {margin:0; background:#888; color:#FFF; }
+.table thead th:first-child {-moz-border-radius-topleft:1em;}
+.table tbody td {border-bottom:1px solid #CCC; padding-right:0.6em;padding-left:0.6em;}
+
+/* Category of the file */
+#filing {font-weight:bold; font-size:smaller; }
+
+/* Contains, without exception, Return to index. */
+#index {font-size:smaller; }
+
+/* Contains, without exception, $Id$, for SVN version info. */
+#version {text-align:right; font-style:italic; margin:2em 0;}

library/HTMLPurifier.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:
  * 
@@ -18,11 +18,11 @@
  * However, most users will only need to interface with the HTMLPurifier
  * class, so this massive amount of infrastructure is usually concealed.
  * If you plan on working with the internals, be sure to include
- * HTMLPurifier_ConfigDef and HTMLPurifier_Config.
+ * HTMLPurifier_ConfigSchema and HTMLPurifier_Config.
  */
 
 /*
-    HTMLPurifier - Standards Compliant HTML Filtering
+    HTML Purifier 1.2.0 - Standards Compliant HTML Filtering
     Copyright (C) 2006 Edward Z. Yang
 
     This library is free software; you can redistribute it and/or
@@ -39,11 +39,14 @@
     License along with this library; if not, write to the Free Software
     Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301  USA
  */
- 
-require_once 'HTMLPurifier/ConfigDef.php';
+
+// almost every class has an undocumented dependency to these, so make sure
+// they get included
+require_once 'HTMLPurifier/ConfigSchema.php';
 require_once 'HTMLPurifier/Config.php';
+require_once 'HTMLPurifier/Context.php';
+
 require_once 'HTMLPurifier/Lexer.php';
-require_once 'HTMLPurifier/HTMLDefinition.php';
 require_once 'HTMLPurifier/Generator.php';
 require_once 'HTMLPurifier/Strategy/Core.php';
 require_once 'HTMLPurifier/Encoder.php';
@@ -93,16 +96,17 @@ class HTMLPurifier
      */
     function purify($html, $config = null) {
         $config = $config ? $config : $this->config;
-        $html = $this->encoder->convertToUTF8($html, $config);
+        $context =& new HTMLPurifier_Context();
+        $html = $this->encoder->convertToUTF8($html, $config, $context);
         $html = 
             $this->generator->generateFromTokens(
                 $this->strategy->execute(
-                    $this->lexer->tokenizeHTML($html, $config),
-                    $config
+                    $this->lexer->tokenizeHTML($html, $config, $context),
+                    $config, $context
                 ),
-                $config
+                $config, $context
             );
-        $html = $this->encoder->convertFromUTF8($html, $config);
+        $html = $this->encoder->convertFromUTF8($html, $config, $context);
         return $html;
     }
     

library/HTMLPurifier/AttrContext.php

@@ -1,26 +0,0 @@
-<?php
-
-/**
- * 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.
- * 
- * @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).
- */
-
-class HTMLPurifier_AttrContext
-{
-    /**
-     * Contains an HTMLPurifier_IDAccumulator, which keeps track of used IDs.
-     * @public
-     */
-    var $id_accumulator;
-}
-
-?>

library/HTMLPurifier/AttrDef.php

@@ -1,7 +1,5 @@
 <?php
 
-require_once 'HTMLPurifier/AttrContext.php';
-
 /**
  * Base class for all validating attribute definitions.
  * 
@@ -16,10 +14,13 @@ class HTMLPurifier_AttrDef
 {
     
     /**
-     * Abstract function defined for functions that validate and clean strings.
-     * 
-     * This function forms the basis for all the subclasses: they must
-     * define this method.
+     * Tells us whether or not an HTML attribute is minimized. Only the
+     * boolean attribute vapourware would use this.
+     */
+    var $minimized = false;
+    
+    /**
+     * Validates and cleans passed string according to a definition.
      * 
      * @public
      * @param $string String to be validated and cleaned.
@@ -42,7 +43,16 @@ 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/CSS.php

@@ -28,6 +28,8 @@ class HTMLPurifier_AttrDef_CSS extends HTMLPurifier_AttrDef
             if (!$declaration) continue;
             if (!strpos($declaration, ':')) continue;
             list($property, $value) = explode(':', $declaration, 2);
+            $property = trim($property);
+            $value    = trim($value);
             if (!isset($definition->info[$property])) continue;
             // inefficient call, since the validator will do this again
             if (strtolower(trim($value)) !== 'inherit') {
@@ -41,6 +43,7 @@ class HTMLPurifier_AttrDef_CSS extends HTMLPurifier_AttrDef
             $propvalues[$property] = $result;
         }
         
+        // procedure does not write the new CSS simultaneously, so it's
         // slightly inefficient, but it's the only way of getting rid of
         // duplicates. Perhaps config to optimize it, but not now.
         

library/HTMLPurifier/AttrDef/Class.php

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

library/HTMLPurifier/AttrDef/Email.php

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

library/HTMLPurifier/AttrDef/Email/SimpleCheck.php

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

library/HTMLPurifier/AttrDef/Host.php

@@ -5,15 +5,20 @@ require_once 'HTMLPurifier/AttrDef/IPv4.php';
 require_once 'HTMLPurifier/AttrDef/IPv6.php';
 
 /**
- * Validates a host according to the IPv4, IPv6 and DNS specifications.
+ * Validates a host according to the IPv4, IPv6 and DNS (future) specifications.
  */
 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() {
         $this->ipv4 = new HTMLPurifier_AttrDef_IPv4();
@@ -30,6 +35,8 @@ class HTMLPurifier_AttrDef_Host extends HTMLPurifier_AttrDef
             if ($valid === false) return false;
             return '['. $valid . ']';
         }
+        
+        // need to do checks on unusual encodings too
         $ipv4 = $this->ipv4->validate($string, $config, $context);
         if ($ipv4 !== false) return $ipv4;
         

library/HTMLPurifier/AttrDef/ID.php

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

library/HTMLPurifier/AttrDef/URI.php

@@ -4,13 +4,36 @@ require_once 'HTMLPurifier/AttrDef.php';
 require_once 'HTMLPurifier/URIScheme.php';
 require_once 'HTMLPurifier/URISchemeRegistry.php';
 require_once 'HTMLPurifier/AttrDef/Host.php';
+require_once 'HTMLPurifier/PercentEncoder.php';
 
-HTMLPurifier_ConfigDef::define(
+HTMLPurifier_ConfigSchema::define(
     'URI', 'DefaultScheme', 'http', 'string',
     'Defines through what scheme the output will be served, in order to '.
     'select the proper object validator when no scheme information is present.'
 );
 
+HTMLPurifier_ConfigSchema::define(
+    'URI', 'Host', null, 'string/null',
+    'Defines the domain name of the server, so we can determine whether or '.
+    'an absolute URI is from your website or not.  Not strictly necessary, '.
+    'as users should be using relative URIs to reference resources on your '.
+    'website.  It will, however, let you use absolute URIs to link to '.
+    'subdomains of the domain you post here: i.e. example.com will allow '.
+    'sub.example.com.  However, higher up domains will still be excluded: '.
+    'if you set %URI.Host to sub.example.com, example.com will be blocked. '.
+    'This directive has been available since 1.2.0.'
+);
+
+HTMLPurifier_ConfigSchema::Define(
+    'URI', 'DisableExternal', false, 'bool',
+    'Disables links to external websites.  This is a highly effective '.
+    'anti-spam and anti-pagerank-leech measure, but comes at a hefty price: no'.
+    'links or images outside of your domain will be allowed.  Non-linkified '.
+    'URIs will still be preserved.  If you want to be able to link to '.
+    'subdomains or use absolute URIs, specify %URI.Host for your website. '.
+    'This directive has been available since 1.2.0.'
+);
+
 /**
  * Validates a URI as defined by RFC 3986.
  * @note Scheme-specific mechanics deferred to HTMLPurifier_URIScheme
@@ -19,9 +42,16 @@ class HTMLPurifier_AttrDef_URI extends HTMLPurifier_AttrDef
 {
     
     var $host;
+    var $PercentEncoder;
+    var $embeds;
     
-    function HTMLPurifier_AttrDef_URI() {
+    /**
+     * @param $embeds Does the URI here result in an extra HTTP request?
+     */
+    function HTMLPurifier_AttrDef_URI($embeds = false) {
         $this->host = new HTMLPurifier_AttrDef_Host();
+        $this->PercentEncoder = new HTMLPurifier_PercentEncoder();
+        $this->embeds = (bool) $embeds;
     }
     
     function validate($uri, $config, &$context) {
@@ -32,17 +62,20 @@ class HTMLPurifier_AttrDef_URI extends HTMLPurifier_AttrDef
         // parse as CDATA
         $uri = $this->parseCDATA($uri);
         
+        // fix up percent-encoding
+        $uri = $this->PercentEncoder->normalize($uri);
+        
         // while it would be nice to use parse_url(), that's specifically
         // for HTTP and thus won't work for our generic URI parsing
         
         // according to the RFC... (but this cuts corners, i.e. non-validating)
-        $r_URI = '!^'.
-            '(([^:/?#<>]+):)?'. // 2. Scheme
-            '(//([^/?#<>]*))?'. // 4. Authority
-            '([^?#<>]*)'.       // 5. Path
-            '(\?([^#<>]*))?'.   // 7. Query
-            '(#([^<>]*))?'.     // 8. Fragment
-            '$!';
+        $r_URI = '!'.
+            '(([^:/?#<>\'"]+):)?'. // 2. Scheme
+            '(//([^/?#<>\'"]*))?'. // 4. Authority
+            '([^?#<>\'"]*)'.       // 5. Path
+            '(\?([^#<>\'"]*))?'.   // 7. Query
+            '(#([^<>\'"]*))?'.     // 8. Fragment
+            '!';
         
         $matches = array();
         $result = preg_match($r_URI, $uri, $matches);
@@ -63,18 +96,31 @@ class HTMLPurifier_AttrDef_URI extends HTMLPurifier_AttrDef
             // no need to validate the scheme's fmt since we do that when we
             // retrieve the specific scheme object from the registry
             $scheme = ctype_lower($scheme) ? $scheme : strtolower($scheme);
-            $scheme_obj =& $registry->getScheme($scheme, $config);
+            $scheme_obj =& $registry->getScheme($scheme, $config, $context);
             if (!$scheme_obj) return false; // invalid scheme, clean it out
         } else {
             $scheme_obj =& $registry->getScheme(
-                $config->get('URI', 'DefaultScheme'), $config
+                $config->get('URI', 'DefaultScheme'), $config, $context
             );
         }
         
         
+        // the URI we're processing embeds a resource in the page, but the URI
+        // it references cannot be located
+        if ($this->embeds && !$scheme_obj->browsable) {
+            return false;
+        }
+        
         
         if ($authority !== null) {
             
+            // remove URI if it's absolute and we disallow externals
+            unset($our_host);
+            if ($config->get('URI', 'DisableExternal')) {
+                $our_host = $config->get('URI', 'Host');
+                if ($our_host === null) return false;
+            }
+            
             $HEXDIG = '[A-Fa-f0-9]';
             $unreserved = 'A-Za-z0-9-._~'; // make sure you wrap with []
             $sub_delims = '!$&\'()'; // needs []
@@ -97,6 +143,17 @@ class HTMLPurifier_AttrDef_URI extends HTMLPurifier_AttrDef
             $host = $this->host->validate($host, $config, $context);
             if ($host === false) $host = null;
             
+            // more lenient absolute checking
+            if (isset($our_host)) {
+                $host_parts = array_reverse(explode('.', $host));
+                // could be cached
+                $our_host_parts = array_reverse(explode('.', $our_host));
+                foreach ($our_host_parts as $i => $discard) {
+                    if (!isset($host_parts[$i])) return false;
+                    if ($host_parts[$i] != $our_host_parts[$i]) return false;
+                }
+            }
+            
             // userinfo and host are validated within the regexp
             
         } else {
@@ -120,7 +177,7 @@ class HTMLPurifier_AttrDef_URI extends HTMLPurifier_AttrDef
         // note that $fragment is omitted
         list($userinfo, $host, $port, $path, $query) = 
             $scheme_obj->validateComponents(
-                $userinfo, $host, $port, $path, $query, $config
+                $userinfo, $host, $port, $path, $query, $config, $context
             );
         
         

library/HTMLPurifier/AttrTransform.php

@@ -23,9 +23,10 @@ class HTMLPurifier_AttrTransform
      * @param $attr Assoc array of attributes, usually from
      *              HTMLPurifier_Token_Tag::$attributes
      * @param $config Mandatory HTMLPurifier_Config object.
+     * @param $context Mandatory HTMLPurifier_Context object
      * @returns Processed attribute array.
      */
-    function transform($attr, $config) {
+    function transform($attr, $config, &$context) {
         trigger_error('Cannot call abstract function', E_USER_ERROR);
     }
 }

library/HTMLPurifier/AttrTransform/BdoDir.php

@@ -4,13 +4,13 @@ require_once 'HTMLPurifier/AttrTransform.php';
 
 // this MUST be placed in post, as it assumes that any value in dir is valid
 
-HTMLPurifier_ConfigDef::define(
+HTMLPurifier_ConfigSchema::define(
     'Attr', 'DefaultTextDir', 'ltr', 'string',
     'Defines the default text direction (ltr or rtl) of the document '.
     'being parsed.  This generally is the same as the value of the dir '.
     'attribute in HTML, or ltr if that is not specified.'
 );
-HTMLPurifier_ConfigDef::defineAllowedValues(
+HTMLPurifier_ConfigSchema::defineAllowedValues(
     'Attr', 'DefaultTextDir', array( 'ltr', 'rtl' )
 );
 
@@ -20,7 +20,7 @@ HTMLPurifier_ConfigDef::defineAllowedValues(
 class HTMLPurifier_AttrTransform_BdoDir extends HTMLPurifier_AttrTransform
 {
     
-    function transform($attr, $config) {
+    function transform($attr, $config, $context) {
         if (isset($attr['dir'])) return $attr;
         $attr['dir'] = $config->get('Attr', 'DefaultTextDir');
         return $attr;

library/HTMLPurifier/AttrTransform/ImgRequired.php

@@ -4,7 +4,7 @@ require_once 'HTMLPurifier/AttrTransform.php';
 
 // must be called POST validation
 
-HTMLPurifier_ConfigDef::define(
+HTMLPurifier_ConfigSchema::define(
     'Attr', 'DefaultInvalidImage', '', 'string',
     'This is the default image an img tag will be pointed to if it does '.
     'not have a valid src attribute.  In future versions, we may allow the '.
@@ -12,7 +12,7 @@ HTMLPurifier_ConfigDef::define(
     'not possible right now.'
 );
 
-HTMLPurifier_ConfigDef::define(
+HTMLPurifier_ConfigSchema::define(
     'Attr', 'DefaultInvalidImageAlt', 'Invalid image', 'string',
     'This is the content of the alt tag of an invalid image if the user '.
     'had not previously specified an alt attribute.  It has no effect when the '.
@@ -25,7 +25,7 @@ HTMLPurifier_ConfigDef::define(
 class HTMLPurifier_AttrTransform_ImgRequired extends HTMLPurifier_AttrTransform
 {
     
-    function transform($attr, $config) {
+    function transform($attr, $config, $context) {
         
         $src = true;
         if (!isset($attr['src'])) {

library/HTMLPurifier/AttrTransform/Lang.php

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

library/HTMLPurifier/AttrTransform/TextAlign.php

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

library/HTMLPurifier/ChildDef.php

@@ -5,14 +5,7 @@
 // false = delete parent node and all children
 // array(...) = replace children nodes with these
 
-// this is the hardest one to implement. We'll use fancy regexp tricks
-// right now, we only expect it to return TRUE or FALSE (it won't attempt
-// to fix the tree)
-
-// we may end up writing custom code for each HTML case
-// in order to make it self correcting
-
-HTMLPurifier_ConfigDef::define(
+HTMLPurifier_ConfigSchema::define(
     'Core', 'EscapeInvalidChildren', false, 'bool',
     'When true, a child is found that is not allowed in the context of the '.
     'parent element will be transformed into text as if it were ASCII. When '.
@@ -45,15 +38,14 @@ class HTMLPurifier_ChildDef
     /**
      * Validates nodes according to definition and returns modification.
      * 
-     * @warning $context is NOT HTMLPurifier_AttrContext
      * @param $tokens_of_children Array of HTMLPurifier_Token
      * @param $config HTMLPurifier_Config object
-     * @param $context String context indicating inline, block or unknown
+     * @param $context HTMLPurifier_Context object
      * @return bool true to leave nodes as is
      * @return bool false to remove parent node
      * @return array of replacement child tokens
      */
-    function validateChildren($tokens_of_children, $config, $context) {
+    function validateChildren($tokens_of_children, $config, &$context) {
         trigger_error('Call to abstract function', E_USER_ERROR);
     }
 }
@@ -62,9 +54,9 @@ class HTMLPurifier_ChildDef
  * Custom validation class, accepts DTD child definitions
  * 
  * @warning Currently this class is an all or nothing proposition, that is,
- *          it will only give a bool return value.  Table is the only
- *          child definition that uses this class, and we ought to give
- *          it a dedicated one.
+ *          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
 {
@@ -98,7 +90,7 @@ class HTMLPurifier_ChildDef_Custom extends HTMLPurifier_ChildDef
         $reg = preg_replace('/([#a-zA-Z0-9_.-]+)/', '(,?\\0)', $reg);
         $this->_pcre_regex = $reg;
     }
-    function validateChildren($tokens_of_children, $config, $context) {
+    function validateChildren($tokens_of_children, $config, &$context) {
         $list_of_children = '';
         $nesting = 0; // depth into the nest
         foreach ($tokens_of_children as $token) {
@@ -152,7 +144,7 @@ class HTMLPurifier_ChildDef_Required extends HTMLPurifier_ChildDef
     }
     var $allow_empty = false;
     var $type = 'required';
-    function validateChildren($tokens_of_children, $config, $context) {
+    function validateChildren($tokens_of_children, $config, &$context) {
         // if there are no tokens, delete parent node
         if (empty($tokens_of_children)) return false;
         
@@ -234,7 +226,7 @@ class HTMLPurifier_ChildDef_Optional extends HTMLPurifier_ChildDef_Required
 {
     var $allow_empty = true;
     var $type = 'optional';
-    function validateChildren($tokens_of_children, $config, $context) {
+    function validateChildren($tokens_of_children, $config, &$context) {
         $result = parent::validateChildren($tokens_of_children, $config, $context);
         if ($result === false) return array();
         return $result;
@@ -253,7 +245,7 @@ class HTMLPurifier_ChildDef_Empty extends HTMLPurifier_ChildDef
     var $allow_empty = true;
     var $type = 'empty';
     function HTMLPurifier_ChildDef_Empty() {}
-    function validateChildren($tokens_of_children, $config, $context) {
+    function validateChildren($tokens_of_children, $config, &$context) {
         return array();
     }
 }
@@ -288,8 +280,9 @@ class HTMLPurifier_ChildDef_Chameleon extends HTMLPurifier_ChildDef
         $this->block  = new HTMLPurifier_ChildDef_Optional($block);
     }
     
-    function validateChildren($tokens_of_children, $config, $context) {
-        switch ($context) {
+    function validateChildren($tokens_of_children, $config, &$context) {
+        $parent_type = $context->get('ParentType');
+        switch ($parent_type) {
             case 'unknown':
             case 'inline':
                 $result = $this->inline->validateChildren(
@@ -307,4 +300,141 @@ class HTMLPurifier_ChildDef_Chameleon extends HTMLPurifier_ChildDef
     }
 }
 
-?>
+/**
+ * Definition for tables
+ */
+class HTMLPurifier_ChildDef_Table extends HTMLPurifier_ChildDef
+{
+    var $allow_empty = false;
+    var $type = 'table';
+    function HTMLPurifier_ChildDef_Table() {}
+    function validateChildren($tokens_of_children, $config, &$context) {
+        if (empty($tokens_of_children)) return false;
+        
+        // this ensures that the loop gets run one last time before closing
+        // up. It's a little bit of a hack, but it works! Just make sure you
+        // get rid of the token later.
+        $tokens_of_children[] = false;
+        
+        // only one of these elements is allowed in a table
+        $caption = false;
+        $thead   = false;
+        $tfoot   = false;
+        
+        // as many of these as you want
+        $cols    = array();
+        $content = array();
+        
+        $nesting = 0; // current depth so we can determine nodes
+        $is_collecting = false; // are we globbing together tokens to package
+                                // into one of the collectors?
+        $collection = array(); // collected nodes
+        $tag_index = 0; // the first node might be whitespace,
+                            // so this tells us where the start tag is
+        
+        foreach ($tokens_of_children as $token) {
+            $is_child = ($nesting == 0);
+            
+            if ($token === false) {
+                // terminating sequence started
+            } elseif ($token->type == 'start') {
+                $nesting++;
+            } elseif ($token->type == 'end') {
+                $nesting--;
+            }
+            
+            // handle node collection
+            if ($is_collecting) {
+                if ($is_child) {
+                    // okay, let's stash the tokens away
+                    // first token tells us the type of the collection
+                    switch ($collection[$tag_index]->name) {
+                        case 'tr':
+                        case 'tbody':
+                            $content[] = $collection;
+                            break;
+                        case 'caption':
+                            if ($caption !== false) break;
+                            $caption = $collection;
+                            break;
+                        case 'thead':
+                        case 'tfoot':
+                            // access the appropriate variable, $thead or $tfoot
+                            $var = $collection[$tag_index]->name;
+                            if ($$var === false) {
+                                $$var = $collection;
+                            } else {
+                                // transmutate the first and less entries into
+                                // tbody tags, and then put into content
+                                $collection[$tag_index]->name = 'tbody';
+                                $collection[count($collection)-1]->name = 'tbody';
+                                $content[] = $collection;
+                            }
+                            break;
+                         case 'colgroup':
+                            $cols[] = $collection;
+                            break;
+                    }
+                    $collection = array();
+                    $is_collecting = false;
+                    $tag_index = 0;
+                } else {
+                    // add the node to the collection
+                    $collection[] = $token;
+                }
+            }
+            
+            // terminate
+            if ($token === false) break;
+            
+            if ($is_child) {
+                // determine what we're dealing with
+                if ($token->name == 'col') {
+                    // the only empty tag in the possie, we can handle it
+                    // immediately
+                    $cols[] = array_merge($collection, array($token));
+                    $collection = array();
+                    $tag_index = 0;
+                    continue;
+                }
+                switch($token->name) {
+                    case 'caption':
+                    case 'colgroup':
+                    case 'thead':
+                    case 'tfoot':
+                    case 'tbody':
+                    case 'tr':
+                        $is_collecting = true;
+                        $collection[] = $token;
+                        continue;
+                    default:
+                        if ($token->type == 'text' && $token->is_whitespace) {
+                            $collection[] = $token;
+                            $tag_index++;
+                        }
+                        continue;
+                }
+            }
+        }
+        
+        if (empty($content)) return false;
+        
+        $ret = array();
+        if ($caption !== false) $ret = array_merge($ret, $caption);
+        if ($cols !== false)    foreach ($cols as $token_array) $ret = array_merge($ret, $token_array);
+        if ($thead !== false)   $ret = array_merge($ret, $thead);
+        if ($tfoot !== false)   $ret = array_merge($ret, $tfoot);
+        foreach ($content as $token_array) $ret = array_merge($ret, $token_array);
+        if (!empty($collection) && $is_collecting == false){
+            // grab the trailing space
+            $ret = array_merge($ret, $collection);
+        }
+        
+        array_pop($tokens_of_children); // remove phantom token
+        
+        return ($ret === $tokens_of_children) ? true : $ret;
+        
+    }
+}
+
+?>

library/HTMLPurifier/Config.php

@@ -21,22 +21,22 @@ class HTMLPurifier_Config
     var $conf;
     
     /**
-     * Reference HTMLPurifier_ConfigDef for value checking
+     * Reference HTMLPurifier_ConfigSchema for value checking
      */
     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;
     
     /**
-     * @param $definition HTMLPurifier_ConfigDef that defines what directives
+     * @param $definition HTMLPurifier_ConfigSchema that defines what directives
      *                    are allowed.
      */
     function HTMLPurifier_Config(&$definition) {
@@ -49,7 +49,7 @@ class HTMLPurifier_Config
      * @return Default HTMLPurifier_Config object.
      */
     function createDefault() {
-        $definition =& HTMLPurifier_ConfigDef::instance();
+        $definition =& HTMLPurifier_ConfigSchema::instance();
         $config = new HTMLPurifier_Config($definition);
         return $config;
     }
@@ -60,7 +60,7 @@ class HTMLPurifier_Config
      * @param $key String key
      */
     function get($namespace, $key) {
-        if (!isset($this->conf[$namespace][$key])) {
+        if (!isset($this->def->info[$namespace][$key])) {
             trigger_error('Cannot retrieve value of undefined directive',
                 E_USER_WARNING);
             return;
@@ -75,11 +75,16 @@ class HTMLPurifier_Config
      * @param $value Mixed value
      */
     function set($namespace, $key, $value) {
-        if (!isset($this->conf[$namespace][$key])) {
+        if (!isset($this->def->info[$namespace][$key])) {
             trigger_error('Cannot set undefined directive to value',
                 E_USER_WARNING);
             return;
         }
+        $value = $this->def->validate(
+                    $value,
+                    $this->def->info[$namespace][$key]->type,
+                    $this->def->info[$namespace][$key]->allow_null
+                 );
         if (is_string($value)) {
             // resolve value alias if defined
             if (isset($this->def->info[$namespace][$key]->aliases[$value])) {
@@ -93,9 +98,7 @@ class HTMLPurifier_Config
                 }
             }
         }
-        $value = $this->def->validate($value,
-                                      $this->def->info[$namespace][$key]->type);
-        if ($value === null) {
+        if ($this->def->isError($value)) {
             trigger_error('Value is of invalid type', E_USER_WARNING);
             return;
         }
@@ -124,6 +127,27 @@ class HTMLPurifier_Config
         return $this->css_definition;
     }
     
+    /**
+     * Loads configuration values from an array with the following structure:
+     * Namespace.Directive => Value
+     * @param $config_array Configuration associative array
+     */
+    function loadArray($config_array) {
+        foreach ($config_array as $key => $value) {
+            if (strpos($key, '.') !== false) {
+                // condensed form
+                list($namespace, $directive) = explode('.', $key);
+                $this->set($namespace, $directive, $value);
+            } else {
+                $namespace = $key;
+                $namespace_values = $value;
+                foreach ($namespace_values as $directive => $value) {
+                    $this->set($namespace, $directive, $value);
+                }
+            }
+        }
+    }
+    
 }
 
 ?>

library/HTMLPurifier/ConfigSchema.php

@@ -1,10 +1,26 @@
 <?php
 
+require_once 'HTMLPurifier/Error.php';
+
 /**
  * Configuration definition, defines directives and their defaults.
- * @todo Build documentation generation capabilities.
+ * @todo The ability to define things multiple times is confusing and should
+ *       be factored out to its own function named registerDependency() or 
+ *       addNote(), where only the namespace.name and an extra descriptions
+ *       documenting the nature of the dependency are needed.  Since it's
+ *       possible that the dependency is registered before the configuration
+ *       is defined, deferring it to some sort of cache until it actually
+ *       gets defined would be wise, keeping it opaque until it does get
+ *       defined. We could add a finalize() method which would cause it to
+ *       error out if we get a dangling dependency.  It's difficult, however,
+ *       to know whether or not it's a dependency, or a codependency, that is
+ *       neither of them fully depends on it. Where does the configuration go
+ *       then?  This could be partially resolved by allowing blanket definitions
+ *       and then splitting them up into finer-grained versions, however, there
+ *       might be implementation difficulties in ini files regarding order of
+ *       execution.
  */
-class HTMLPurifier_ConfigDef {
+class HTMLPurifier_ConfigSchema {
     
     /**
      * Defaults of the directives and namespaces.
@@ -26,15 +42,15 @@ class HTMLPurifier_ConfigDef {
      * Lookup table of allowed types.
      */
     var $types = array(
-        'string'    => true,
-        'istring'   => true,
-        'int'       => true,
-        'float'     => true,
-        'bool'      => true,
-        'lookup'    => true,
-        'list'      => true,
-        'hash'      => true,
-        'mixed'     => true
+        'string'    => 'String',
+        'istring'   => 'Case-insensitive string',
+        'int'       => 'Integer',
+        'float'     => 'Float',
+        'bool'      => 'Boolean',
+        'lookup'    => 'Lookup array',
+        'list'      => 'Array list',
+        'hash'      => 'Associative array',
+        'mixed'     => 'Mixed'
     );
     
     /**
@@ -46,6 +62,7 @@ class HTMLPurifier_ConfigDef {
         $this->defineNamespace('URI', 'Features regarding Uniform Resource Identifiers.');
         $this->defineNamespace('HTML', 'Configuration regarding allowed HTML.');
         $this->defineNamespace('CSS', 'Configuration regarding allowed CSS.');
+        $this->defineNamespace('Test', 'Developer testing configuration for our unit tests.');
     }
     
     /**
@@ -56,7 +73,7 @@ class HTMLPurifier_ConfigDef {
         if ($prototype !== null) {
             $instance = $prototype;
         } elseif ($instance === null || $prototype === true) {
-            $instance = new HTMLPurifier_ConfigDef();
+            $instance = new HTMLPurifier_ConfigSchema();
             $instance->initialize();
         }
         return $instance;
@@ -65,9 +82,6 @@ class HTMLPurifier_ConfigDef {
     /**
      * Defines a directive for configuration
      * @warning Will fail of directive's namespace is defined
-     * @todo Collect information on description and allow redefinition
-     *       so that multiple files can register a dependency on a
-     *       configuration directive.
      * @param $namespace Namespace the directive is in
      * @param $name Key of directive
      * @param $default Default value of directive
@@ -79,12 +93,17 @@ class HTMLPurifier_ConfigDef {
         $namespace, $name, $default, $type, 
         $description
     ) {
-        $def =& HTMLPurifier_ConfigDef::instance();
+        $def =& HTMLPurifier_ConfigSchema::instance();
         if (!isset($def->info[$namespace])) {
             trigger_error('Cannot define directive for undefined namespace',
                 E_USER_ERROR);
             return;
         }
+        if (!ctype_alnum($name)) {
+            trigger_error('Directive name must be alphanumeric',
+                E_USER_ERROR);
+            return;
+        }
         if (isset($def->info[$namespace][$name])) {
             if (
                 $def->info[$namespace][$name]->type !== $type ||
@@ -94,12 +113,19 @@ class HTMLPurifier_ConfigDef {
                 return;
             }
         } else {
+            // process modifiers
+            $type_values = explode('/', $type, 2);
+            $type = $type_values[0];
+            $modifier = isset($type_values[1]) ? $type_values[1] : false;
+            $allow_null = ($modifier === 'null');
+            
             if (!isset($def->types[$type])) {
                 trigger_error('Invalid type for configuration directive',
                     E_USER_ERROR);
                 return;
             }
-            if ($def->validate($default, $type) === null) {
+            $default = $def->validate($default, $type, $allow_null);
+            if ($def->isError($default)) {
                 trigger_error('Default value does not match directive type',
                     E_USER_ERROR);
                 return;
@@ -107,6 +133,7 @@ class HTMLPurifier_ConfigDef {
             $def->info[$namespace][$name] =
                 new HTMLPurifier_ConfigEntity_Directive();
             $def->info[$namespace][$name]->type = $type;
+            $def->info[$namespace][$name]->allow_null = $allow_null;
             $def->defaults[$namespace][$name]   = $default;
         }
         $backtrace = debug_backtrace();
@@ -121,17 +148,19 @@ class HTMLPurifier_ConfigDef {
      * @param $description Description of the namespace
      */
     function defineNamespace($namespace, $description) {
-        $def =& HTMLPurifier_ConfigDef::instance();
+        $def =& HTMLPurifier_ConfigSchema::instance();
         if (isset($def->info[$namespace])) {
             trigger_error('Cannot redefine namespace', E_USER_ERROR);
             return;
         }
+        if (!ctype_alnum($namespace)) {
+            trigger_error('Namespace name must be alphanumeric',
+                E_USER_ERROR);
+            return;
+        }
         $def->info[$namespace] = array();
         $def->info_namespace[$namespace] = new HTMLPurifier_ConfigEntity_Namespace();
-        $backtrace = debug_backtrace();
-        $file = $def->mungeFilename($backtrace[0]['file']);
-        $line = $backtrace[0]['line'];
-        $def->info_namespace[$namespace]->addDescription($file,$line,$description);
+        $def->info_namespace[$namespace]->description = $description;
         $def->defaults[$namespace] = array();
     }
     
@@ -146,7 +175,7 @@ class HTMLPurifier_ConfigDef {
      * @param $real Value aliased value will be converted into
      */
     function defineValueAliases($namespace, $name, $aliases) {
-        $def =& HTMLPurifier_ConfigDef::instance();
+        $def =& HTMLPurifier_ConfigSchema::instance();
         if (!isset($def->info[$namespace][$name])) {
             trigger_error('Cannot set value alias for non-existant directive',
                 E_USER_ERROR);
@@ -176,7 +205,7 @@ class HTMLPurifier_ConfigDef {
      * @param $allowed_values Arraylist of allowed values
      */
     function defineAllowedValues($namespace, $name, $allowed_values) {
-        $def =& HTMLPurifier_ConfigDef::instance();
+        $def =& HTMLPurifier_ConfigSchema::instance();
         if (!isset($def->info[$namespace][$name])) {
             trigger_error('Cannot define allowed values for undefined directive',
                 E_USER_ERROR);
@@ -193,36 +222,37 @@ class HTMLPurifier_ConfigDef {
     /**
      * Validate a variable according to type. Return null if invalid.
      */
-    function validate($var, $type) {
+    function validate($var, $type, $allow_null = false) {
         if (!isset($this->types[$type])) {
             trigger_error('Invalid type', E_USER_ERROR);
             return;
         }
+        if ($allow_null && $var === null) return null;
         switch ($type) {
             case 'mixed':
                 return $var;
             case 'istring':
             case 'string':
-                if (!is_string($var)) return;
+                if (!is_string($var)) break;
                 if ($type === 'istring') $var = strtolower($var);
                 return $var;
             case 'int':
                 if (is_string($var) && ctype_digit($var)) $var = (int) $var;
-                elseif (!is_int($var)) return;
+                elseif (!is_int($var)) break;
                 return $var;
             case 'float':
                 if (is_string($var) && is_numeric($var)) $var = (float) $var;
-                elseif (!is_float($var)) return;
+                elseif (!is_float($var)) break;
                 return $var;
             case 'bool':
                 if (is_int($var) && ($var === 0 || $var === 1)) {
                     $var = (bool) $var;
-                } elseif (!is_bool($var)) return;
+                } elseif (!is_bool($var)) break;
                 return $var;
             case 'list':
             case 'hash':
             case 'lookup':
-                if (!is_array($var)) return;
+                if (!is_array($var)) break;
                 $keys = array_keys($var);
                 if ($keys === array_keys($keys)) {
                     if ($type == 'list') return $var;
@@ -232,7 +262,7 @@ class HTMLPurifier_ConfigDef {
                             $new[$key] = true;
                         }
                         return $new;
-                    } else return;
+                    } else break;
                 }
                 if ($type === 'lookup') {
                     foreach ($var as $key => $value) {
@@ -241,8 +271,13 @@ class HTMLPurifier_ConfigDef {
                 }
                 return $var;
         }
+        $error = new HTMLPurifier_Error();
+        return $error;
     }
     
+    /**
+     * Takes an absolute path and munges it into a more manageable relative path
+     */
     function mungeFilename($filename) {
         $offset = strrpos($filename, 'HTMLPurifier');
         $filename = substr($filename, $offset);
@@ -250,32 +285,32 @@ class HTMLPurifier_ConfigDef {
         return $filename;
     }
     
+    /**
+     * Checks if var is an HTMLPurifier_Error object
+     */
+    function isError($var) {
+        if (!is_object($var)) return false;
+        if (!is_a($var, 'HTMLPurifier_Error')) return false;
+        return true;
+    }
 }
 
 /**
  * Base class for configuration entity
  */
-class HTMLPurifier_ConfigEntity
-{
-    /**
-     * Plaintext descriptions of the configuration entity is. Organized by
-     * file and line number, so multiple descriptions are allowed.
-     */
-    var $descriptions = array();
-    
-    /**
-     * Adds a description to the array
-     */
-    function addDescription($file, $line, $description) {
-        if (!isset($this->descriptions[$file])) $this->descriptions[$file] = array();
-        $this->descriptions[$file][$line] = $description;
-    }
-}
+class HTMLPurifier_ConfigEntity {}
 
 /**
  * Structure object describing of a namespace
  */
-class HTMLPurifier_ConfigEntity_Namespace extends HTMLPurifier_ConfigEntity {}
+class HTMLPurifier_ConfigEntity_Namespace extends HTMLPurifier_ConfigEntity {
+    
+    /**
+     * String description of what kinds of directives go in this namespace.
+     */
+    var $description;
+    
+}
 
 /**
  * Structure object containing definition of a directive.
@@ -308,6 +343,26 @@ class HTMLPurifier_ConfigEntity_Directive extends HTMLPurifier_ConfigEntity
      */
     var $type = 'mixed';
     
+    /**
+     * Is null allowed? Has no affect for mixed type.
+     * @bool
+     */
+    var $allow_null = false;
+    
+    /**
+     * Plaintext descriptions of the configuration entity is. Organized by
+     * file and line number, so multiple descriptions are allowed.
+     */
+    var $descriptions = array();
+    
+    /**
+     * Adds a description to the array
+     */
+    function addDescription($file, $line, $description) {
+        if (!isset($this->descriptions[$file])) $this->descriptions[$file] = array();
+        $this->descriptions[$file][$line] = $description;
+    }
+    
 }
 
 ?>

library/HTMLPurifier/Context.php

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

library/HTMLPurifier/Encoder.php

@@ -2,7 +2,7 @@
 
 require_once 'HTMLPurifier/EntityLookup.php';
 
-HTMLPurifier_ConfigDef::define(
+HTMLPurifier_ConfigSchema::define(
     'Core', 'Encoding', 'utf-8', 'istring', 
     'If for some reason you are unable to convert all webpages to UTF-8, '. 
     'you can use this directive as a stop-gap compatibility change to '. 
@@ -17,14 +17,25 @@ HTMLPurifier_ConfigDef::define(
 
 if ( !function_exists('iconv') ) {
     // only encodings with native PHP support
-    HTMLPurifier_ConfigDef::defineAllowedValues(
+    HTMLPurifier_ConfigSchema::defineAllowedValues(
         'Core', 'Encoding', array(
             'utf-8',
             'iso-8859-1'
         )
     );
+    HTMLPurifier_ConfigSchema::defineValueAliases(
+        'Core', 'Encoding', array(
+            'iso8859-1' => 'iso-8859-1'
+        )
+    );
 }
 
+HTMLPurifier_ConfigSchema::define(
+    'Test', 'ForceNoIconv', false, 'bool', 
+    'When set to true, HTMLPurifier_Encoder will act as if iconv does not '.
+    'exist and use only pure PHP implementations.'
+);
+
 /**
  * A UTF-8 specific character encoder that handles cleaning and transforming.
  */
@@ -77,7 +88,7 @@ class HTMLPurifier_Encoder
         if ($iconv && !$force_php) {
             // do the shortcut way
             $str = @iconv('UTF-8', 'UTF-8//IGNORE', $str);
-            return strtr($str, $non_sgml_chars);;
+            return strtr($str, $non_sgml_chars);
         }
         
         $mState = 0; // cached expected number of octets after the current octet
@@ -214,7 +225,30 @@ class HTMLPurifier_Encoder
     
     /**
      * Translates a Unicode codepoint into its corresponding UTF-8 character.
+     * @note Based on Feyd's function at
+     *       <http://forums.devnetwork.net/viewtopic.php?p=191404#191404>,
+     *       which is in public domain.
+     * @note While we're going to do code point parsing anyway, a good
+     *       optimization would be to refuse to translate code points that
+     *       are non-SGML characters.  However, this could lead to duplication.
+     * @note This is very similar to the unichr function in
+     *       maintenance/generate-entity-file.php (although this is superior,
+     *       due to its sanity checks).
      */
+    
+    // +----------+----------+----------+----------+
+    // | 33222222 | 22221111 | 111111   |          |
+    // | 10987654 | 32109876 | 54321098 | 76543210 | bit
+    // +----------+----------+----------+----------+
+    // |          |          |          | 0xxxxxxx | 1 byte 0x00000000..0x0000007F
+    // |          |          | 110yyyyy | 10xxxxxx | 2 byte 0x00000080..0x000007FF
+    // |          | 1110zzzz | 10yyyyyy | 10xxxxxx | 3 byte 0x00000800..0x0000FFFF
+    // | 11110www | 10wwzzzz | 10yyyyyy | 10xxxxxx | 4 byte 0x00010000..0x0010FFFF
+    // +----------+----------+----------+----------+
+    // | 00000000 | 00011111 | 11111111 | 11111111 | Theoretical upper limit of legal scalars: 2097151 (0x001FFFFF)
+    // | 00000000 | 00010000 | 11111111 | 11111111 | Defined upper limit of legal scalar codes
+    // +----------+----------+----------+----------+ 
+    
     function unichr($code) {
         if($code > 1114111 or $code < 0 or
           ($code >= 55296 and $code <= 57343) ) {
@@ -255,14 +289,14 @@ class HTMLPurifier_Encoder
     /**
      * Converts a string to UTF-8 based on configuration.
      */
-    function convertToUTF8($str, $config) {
+    function convertToUTF8($str, $config, &$context) {
         static $iconv = null;
         if ($iconv === null) $iconv = function_exists('iconv');
         $encoding = $config->get('Core', 'Encoding');
         if ($encoding === 'utf-8') return $str;
-        if ($iconv) {
+        if ($iconv && !$config->get('Test', 'ForceNoIconv')) {
             return @iconv($encoding, 'utf-8//IGNORE', $str);
-        } elseif ($encoding === 'iso-8895-1') {
+        } elseif ($encoding === 'iso-8859-1') {
             return @utf8_encode($str);
         }
     }
@@ -272,15 +306,15 @@ class HTMLPurifier_Encoder
      * @note Currently, this is a lossy conversion, with unexpressable
      *       characters being omitted.
      */
-    function convertFromUTF8($str, $config) {
+    function convertFromUTF8($str, $config, &$context) {
         static $iconv = null;
         if ($iconv === null) $iconv = function_exists('iconv');
         $encoding = $config->get('Core', 'Encoding');
         if ($encoding === 'utf-8') return $str;
-        if ($iconv) {
+        if ($iconv && !$config->get('Test', 'ForceNoIconv')) {
             return @iconv('utf-8', $encoding . '//IGNORE', $str);
-        } elseif ($encoding === 'iso-8895-1') {
-            return @utf8_encode($str);
+        } elseif ($encoding === 'iso-8859-1') {
+            return @utf8_decode($str);
         }
     }
     

library/HTMLPurifier/EntityLookup.php

@@ -19,7 +19,7 @@ class HTMLPurifier_EntityLookup {
      */
     function setup($file = false) {
         if (!$file) {
-            $file = dirname(__FILE__) . '/EntityLookup/data.txt';
+            $file = dirname(__FILE__) . '/EntityLookup/entities.ser';
         }
         $this->table = unserialize(file_get_contents($file));
     }

library/HTMLPurifier/EntityParser.php

@@ -3,6 +3,10 @@
 require_once 'HTMLPurifier/EntityLookup.php';
 require_once 'HTMLPurifier/Encoder.php';
 
+// if want to implement error collecting here, we'll need to use some sort
+// of global data (probably trigger_error) because it's impossible to pass
+// $config or $context to the callback functions.
+
 /**
  * Handles referencing and derefencing character entities
  */
@@ -72,38 +76,12 @@ class HTMLPurifier_EntityParser
      * 
      * @warning Though this is public in order to let the callback happen,
      *          calling it directly is not recommended.
-     * @note Based on Feyd's function at
-     *       <http://forums.devnetwork.net/viewtopic.php?p=191404#191404>,
-     *       which is in public domain.
-     * @note While we're going to do code point parsing anyway, a good
-     *       optimization would be to refuse to translate code points that
-     *       are non-SGML characters.  However, this could lead to duplication.
-     * @note This function is heavily intimate with the inner workings of
-     *       UTF-8 and would also be well suited in the Encoder class (or at
-     *       least deferring some processing to it).  This is also very
-     *       similar to the unichr function in
-     *       maintenance/generate-entity-file.php (although this is superior,
-     *       due to its sanity checks).
      * @param $matches  PCRE matches array, with 0 the entire match, and
      *                  either index 1, 2 or 3 set with a hex value, dec value,
      *                  or string (respectively).
      * @returns Replacement string.
-     * @todo Implement string translations
      */
     
-    // +----------+----------+----------+----------+
-    // | 33222222 | 22221111 | 111111   |          |
-    // | 10987654 | 32109876 | 54321098 | 76543210 | bit
-    // +----------+----------+----------+----------+
-    // |          |          |          | 0xxxxxxx | 1 byte 0x00000000..0x0000007F
-    // |          |          | 110yyyyy | 10xxxxxx | 2 byte 0x00000080..0x000007FF
-    // |          | 1110zzzz | 10yyyyyy | 10xxxxxx | 3 byte 0x00000800..0x0000FFFF
-    // | 11110www | 10wwzzzz | 10yyyyyy | 10xxxxxx | 4 byte 0x00010000..0x0010FFFF
-    // +----------+----------+----------+----------+
-    // | 00000000 | 00011111 | 11111111 | 11111111 | Theoretical upper limit of legal scalars: 2097151 (0x001FFFFF)
-    // | 00000000 | 00010000 | 11111111 | 11111111 | Defined upper limit of legal scalar codes
-    // +----------+----------+----------+----------+ 
-    
     function nonSpecialEntityCallback($matches) {
         // replaces all but big five
         $entity = $matches[0];

library/HTMLPurifier/Error.php

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

library/HTMLPurifier/Generator.php

@@ -1,10 +1,8 @@
 <?php
 
-// pretty-printing with indentation would be pretty cool
-
 require_once 'HTMLPurifier/Lexer.php';
 
-HTMLPurifier_ConfigDef::define(
+HTMLPurifier_ConfigSchema::define(
     'Core', 'CleanUTF8DuringGeneration', false, 'bool',
     'When true, HTMLPurifier_Generator will also check all strings it '.
     'escapes for UTF-8 well-formedness as a defense in depth measure. '.
@@ -15,6 +13,29 @@ HTMLPurifier_ConfigDef::define(
     'generateFromTokens.'
 );
 
+HTMLPurifier_ConfigSchema::define(
+    'Core', 'XHTML', true, 'bool',
+    'Determines whether or not output is XHTML or not.  When disabled, HTML '.
+    'Purifier goes into HTML 4.01 removes XHTML-specific markup constructs, '.
+    'such as boolean attribute expansion and trailing slashes in empty tags. '.
+    'This directive was available since 1.1.'
+);
+
+// extension constraints could be factored into ConfigSchema
+HTMLPurifier_ConfigSchema::define(
+    'Core', 'TidyFormat', false, 'bool',
+    '<p>Determines whether or not to run Tidy on the final output for pretty '.
+    'formatting reasons, such as indentation and wrap.</p><p>This can greatly '.
+    'improve readability for editors who are hand-editing the HTML, but is '.
+    'by no means necessary as HTML Purifier has already fixed all major '.
+    'errors the HTML may have had. Tidy is a non-default extension, and this directive '.
+    'will silently fail if Tidy is not available.</p><p>If you are looking to make '.
+    'the overall look of your page\'s source better, I recommend running Tidy '.
+    'on the entire page rather than just user-content (after all, the '.
+    'indentation relative to the containing blocks will be incorrect).</p><p>This '.
+    'directive was available since 1.1.1.</p>'
+);
+
 /**
  * Generates HTML from tokens.
  */
@@ -22,26 +43,56 @@ class HTMLPurifier_Generator
 {
     
     /**
-     * Bool cache of the CleanUTF8DuringGeneration directive.
+     * Bool cache of %Core.CleanUTF8DuringGeneration
      * @private
      */
     var $_clean_utf8 = false;
     
+    /**
+     * Bool cache of %Core.XHTML
+     * @private
+     */
+    var $_xhtml = true;
+    
     /**
      * Generates HTML from an array of tokens.
      * @param $tokens Array of HTMLPurifier_Token
      * @param $config HTMLPurifier_Config object
      * @return Generated HTML
-     * @note Only unit tests may omit configuration: internals MUST pass config
      */
-    function generateFromTokens($tokens, $config = null) {
+    function generateFromTokens($tokens, $config, &$context) {
         $html = '';
         if (!$config) $config = HTMLPurifier_Config::createDefault();
         $this->_clean_utf8 = $config->get('Core', 'CleanUTF8DuringGeneration');
+        $this->_xhtml = $config->get('Core', 'XHTML');
         if (!$tokens) return '';
         foreach ($tokens as $token) {
             $html .= $this->generateFromToken($token);
         }
+        if ($config->get('Core', 'TidyFormat') && extension_loaded('tidy')) {
+            
+            $tidy_options = array(
+               'indent'=> true,
+               'output-xhtml' => $this->_xhtml,
+               'show-body-only' => true,
+               'indent-spaces' => 2,
+               'wrap' => 68,
+            );
+            if (version_compare(PHP_VERSION, '5', '<')) {
+                tidy_set_encoding('utf8');
+                foreach ($tidy_options as $key => $value) {
+                    tidy_setopt($key, $value);
+                }
+                tidy_parse_string($html);
+                tidy_clean_repair();
+                $html = tidy_get_output();
+            } else {
+                $tidy = new Tidy;
+                $tidy->parseString($html, $tidy_options, 'utf8');
+                $tidy->cleanRepair();
+                $html = (string) $tidy;
+            }
+        }
         return $html;
     }
     
@@ -61,7 +112,9 @@ class HTMLPurifier_Generator
             
         } elseif ($token->type == 'empty') {
             $attr = $this->generateAttributes($token->attributes);
-             return '<' . $token->name . ($attr ? ' ' : '') . $attr . ' />';
+             return '<' . $token->name . ($attr ? ' ' : '') . $attr .
+                ( $this->_xhtml ? ' /': '' )
+                . '>';
             
         } elseif ($token->type == 'text') {
             return $this->escape($token->data);
@@ -80,6 +133,11 @@ class HTMLPurifier_Generator
     function generateAttributes($assoc_array_of_attributes) {
         $html = '';
         foreach ($assoc_array_of_attributes as $key => $value) {
+            if (!$this->_xhtml) {
+                // remove namespaced attributes
+                if (strpos($key, ':') !== false) continue;
+                // also needed: check for attribute minimization
+            }
             $html .= $key.'="'.$this->escape($value).'" ';
         }
         return rtrim($html);

library/HTMLPurifier/HTMLDefinition.php

@@ -22,6 +22,19 @@ require_once 'HTMLPurifier/Generator.php';
 require_once 'HTMLPurifier/Token.php';
 require_once 'HTMLPurifier/TagTransform.php';
 
+HTMLPurifier_ConfigSchema::define(
+    'HTML', 'EnableAttrID', false, 'bool',
+    'Allows the ID attribute in HTML.  This is disabled by default '.
+    'due to the fact that without proper configuration user input can '.
+    'easily break the validation of a webpage by specifying an ID that is '.
+    'already on the surrounding HTML.  If you don\'t mind throwing caution to '.
+    'the wind, enable this directive, but I strongly recommend you also '.
+    'consider blacklisting IDs you use (%Attr.IDBlacklist) or prefixing all '.
+    'user supplied IDs (%Attr.IDPrefix).  This directive has been available '.
+    'since 1.2.0, and when set to true reverts to the behavior of pre-1.2.0 '.
+    'versions.'
+);
+
 /**
  * Defines the purified HTML type with large amounts of objects.
  * 
@@ -56,6 +69,7 @@ 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 +125,19 @@ 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 +163,18 @@ 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  =
@@ -209,8 +232,7 @@ class HTMLPurifier_HTMLDefinition
         
         $this->info['a']->child    = $e_a_content;
         
-        $this->info['table']->child = new HTMLPurifier_ChildDef_Custom(
-            '(caption?, (col*|colgroup*), thead?, tfoot?, (tbody+|tr+))');
+        $this->info['table']->child = new HTMLPurifier_ChildDef_Table();
         
         // not a real entity, watch the double underscore
         $e__row = new HTMLPurifier_ChildDef_Required('tr');
@@ -226,14 +248,14 @@ class HTMLPurifier_HTMLDefinition
         //////////////////////////////////////////////////////////////////////
         // info[]->type : defines the type of the element (block or inline)
         
-        // reuses $e_Inline and $e_block
-        
-        foreach ($e_Inline->elements as $name) {
+        // reuses $e_Inline and $e_Block
+        foreach ($e_Inline->elements as $name => $bool) {
+            if ($name == '#PCDATA' || $name == '') continue;
             $this->info[$name]->type = 'inline';
         }
         
         $e_Block = new HTMLPurifier_ChildDef_Optional($e_block);
-        foreach ($e_Block->elements as $name) {
+        foreach ($e_Block->elements as $name => $bool) {
             $this->info[$name]->type = 'block';
         }
         
@@ -244,7 +266,7 @@ 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'));
         
         //////////////////////////////////////////////////////////////////////
@@ -254,13 +276,14 @@ 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,
         // which manually override these in their local definitions
         $this->info_global_attr = array(
             // core attrs
-            'id'    => new HTMLPurifier_AttrDef_ID(),
             'class' => new HTMLPurifier_AttrDef_Class(),
             'title' => $e_Text,
             'style' => new HTMLPurifier_AttrDef_CSS(),
@@ -270,6 +293,10 @@ class HTMLPurifier_HTMLDefinition
             'xml:lang' => new HTMLPurifier_AttrDef_Lang(),
             );
         
+        if ($config->get('HTML', 'EnableAttrID')) {
+            $this->info_global_attr['id'] = new HTMLPurifier_AttrDef_ID();
+        }
+        
         // required attribute stipulation handled in attribute transformation
         $this->info['bdo']->attr = array(); // nothing else
         
@@ -298,7 +325,8 @@ 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'] =
@@ -323,14 +351,16 @@ class HTMLPurifier_HTMLDefinition
         $e_URI = new HTMLPurifier_AttrDef_URI();
         $this->info['a']->attr['href'] =
         $this->info['img']->attr['longdesc'] =
-        $this->info['img']->attr['src'] =
         $this->info['del']->attr['cite'] =
         $this->info['ins']->attr['cite'] =
         $this->info['blockquote']->attr['cite'] =
         $this->info['q']->attr['cite'] = $e_URI;
         
+        // URI that causes HTTP request
+        $this->info['img']->attr['src'] = new HTMLPurifier_AttrDef_URI(true);
+        
         //////////////////////////////////////////////////////////////////////
-        // 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');
@@ -340,6 +370,9 @@ 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
@@ -382,6 +415,13 @@ class HTMLPurifier_HTMLDefinition
         
         $this->info_attr_transform_post[] = new HTMLPurifier_AttrTransform_Lang();
         
+        // protect against stdclasses floating around
+        foreach ($this->info as $key => $obj) {
+            if (is_a($obj, 'stdclass')) {
+                unset($this->info[$key]);
+            }
+        }
+        
     }
     
     function setAttrForTableElements($attr, $def) {

library/HTMLPurifier/IDAccumulator.php

@@ -3,6 +3,9 @@
 /**
  * Component of HTMLPurifier_AttrContext that accumulates IDs to prevent dupes
  * @note In Slashdot-speak, dupe means duplicate.
+ * @note This class does not accept $config or $context, thus, it is the
+ *       burden of the callee to register the appropriate errors or
+ *       configuration.
  */
 class HTMLPurifier_IDAccumulator
 {

library/HTMLPurifier/Lexer.php

@@ -4,12 +4,11 @@ require_once 'HTMLPurifier/Token.php';
 require_once 'HTMLPurifier/Encoder.php';
 require_once 'HTMLPurifier/EntityParser.php';
 
-HTMLPurifier_ConfigDef::define(
+HTMLPurifier_ConfigSchema::define(
     'Core', 'AcceptFullDocuments', true, 'bool',
     'This parameter determines whether or not the filter should accept full '.
     'HTML documents, not just HTML fragments.  When on, it will '.
-    'drop all sections except the content between body.  Depending on '.
-    'the implementation in use, this may speed up document parse times.'
+    'drop all sections except the content between body.'
 );
 
 /**
@@ -61,6 +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;
     
     /**
@@ -69,7 +122,7 @@ class HTMLPurifier_Lexer
      * @param $string String HTML.
      * @return HTMLPurifier_Token array representation of HTML.
      */
-    function tokenizeHTML($string, $config = null) {
+    function tokenizeHTML($string, $config, &$context) {
         trigger_error('Call to abstract class', E_USER_ERROR);
     }
     
@@ -143,7 +196,7 @@ class HTMLPurifier_Lexer
      * Takes a piece of HTML and normalizes it by converting entities, fixing
      * encoding, extracting bits, and other good stuff.
      */
-    function normalize($html, $config) {
+    function normalize($html, $config, &$context) {
         
         // extract body from document if applicable
         if ($config->get('Core', 'AcceptFullDocuments')) {

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
@@ -34,10 +38,9 @@ class HTMLPurifier_Lexer_DOMLex extends HTMLPurifier_Lexer
         $this->factory = new HTMLPurifier_TokenFactory();
     }
     
-    public function tokenizeHTML($string, $config = null) {
-        if (!$config) $config = HTMLPurifier_Config::createDefault();
+    public function tokenizeHTML($string, $config, &$context) {
         
-        $string = $this->normalize($string, $config);
+        $string = $this->normalize($string, $config, $context);
         
         // preprocess string, essential for UTF-8
         $string =
@@ -87,19 +90,20 @@ class HTMLPurifier_Lexer_DOMLex extends HTMLPurifier_Lexer
             return;
         }
         
+        $attr = $node->hasAttributes() ?
+            $this->transformAttrToAssoc($node->attributes) :
+            array();
+        
         // We still have to make sure that the element actually IS empty
         if (!$node->childNodes->length) {
             if ($collect) {
-                $tokens[] = $this->factory->createEmpty(
-                    $node->tagName,
-                    $this->transformAttrToAssoc($node->attributes)
-                );
+                $tokens[] = $this->factory->createEmpty($node->tagName, $attr);
             }
         } else {
             if ($collect) { // don't wrap on first iteration
                 $tokens[] = $this->factory->createStart(
                     $tag_name = $node->tagName, // somehow, it get's dropped
-                    $this->transformAttrToAssoc($node->attributes)
+                    $attr
                 );
             }
             foreach ($node->childNodes as $node) {

library/HTMLPurifier/Lexer/DirectLex.php

@@ -12,75 +12,21 @@ 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
      */
     var $_whitespace = "\x20\x09\x0D\x0A";
     
-    function tokenizeHTML($html, $config = null) {
+    function tokenizeHTML($html, $config, &$context) {
         
-        if (!$config) $config = HTMLPurifier_Config::createDefault();
-        
-        $html = $this->normalize($html, $config);
+        $html = $this->normalize($html, $config, $context);
         
         $cursor = 0; // our location in the text
         $inside_tag = false; // whether or not we're parsing the inside of a tag
@@ -199,6 +145,7 @@ class HTMLPurifier_Lexer_DirectLex extends HTMLPurifier_Lexer
                 if ($attribute_string) {
                     $attributes = $this->parseAttributeString(
                                         $attribute_string
+                                      , $config, $context
                                   );
                 } else {
                     $attributes = array();
@@ -233,7 +180,7 @@ class HTMLPurifier_Lexer_DirectLex extends HTMLPurifier_Lexer
      * @param $string Inside of tag excluding name.
      * @returns Assoc array of attributes.
      */
-    function parseAttributeString($string) {
+    function parseAttributeString($string, $config, &$context) {
         $string = (string) $string; // quick typecast
         
         if ($string == '') return array(); // no attributes

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
@@ -29,18 +31,19 @@ class HTMLPurifier_Lexer_PEARSax3 extends HTMLPurifier_Lexer
      */
     var $tokens = array();
     
-    function tokenizeHTML($string, $config = null) {
+    function tokenizeHTML($string, $config, &$context) {
         
         $this->tokens = array();
         
-        if (!$config) $config = HTMLPurifier_Config::createDefault();
-        $string = $this->normalize($string, $config);
+        $string = $this->normalize($string, $config, $context);
         
         $parser=& new XML_HTMLSax3();
         $parser->set_object($this);
         $parser->set_element_handler('openHandler','closeHandler');
         $parser->set_data_handler('dataHandler');
         $parser->set_escape_handler('escapeHandler');
+        
+        // doesn't seem to work correctly for attributes
         $parser->set_option('XML_OPTION_ENTITIES_PARSED', 1);
         
         $parser->parse($string);
@@ -53,6 +56,10 @@ 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/PercentEncoder.php

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

library/HTMLPurifier/Strategy.php

@@ -8,7 +8,7 @@
  * features, such as custom tags, custom parsing of text, etc.
  */
 
-HTMLPurifier_ConfigDef::define(
+HTMLPurifier_ConfigSchema::define(
     'Core', 'EscapeInvalidTags', false, 'bool',
     'When true, invalid tags will be written back to the document as plain '.
     'text.  Otherwise, they are silently dropped.'
@@ -24,7 +24,7 @@ class HTMLPurifier_Strategy
      * @param $config Configuration options
      * @returns Processed array of token objects.
      */
-    function execute($tokens, $config = null) {
+    function execute($tokens, $config, &$context) {
         trigger_error('Cannot call abstract function', E_USER_ERROR);
     }
     

library/HTMLPurifier/Strategy/Composite.php

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

library/HTMLPurifier/Strategy/FixNesting.php

@@ -34,8 +34,7 @@ require_once 'HTMLPurifier/HTMLDefinition.php';
 class HTMLPurifier_Strategy_FixNesting extends HTMLPurifier_Strategy
 {
     
-    function execute($tokens, $config) {
-        
+    function execute($tokens, $config, &$context) {
         //####################################################################//
         // Pre-processing
         
@@ -49,6 +48,10 @@ class HTMLPurifier_Strategy_FixNesting extends HTMLPurifier_Strategy
         array_unshift($tokens, new HTMLPurifier_Token_Start($parent_name));
         $tokens[] = new HTMLPurifier_Token_End($parent_name);
         
+        // setup the context variables
+        $parent_type = 'unknown'; // reference var that we alter
+        $context->register('ParentType', $parent_type);
+        
         //####################################################################//
         // Loop initialization
         
@@ -109,10 +112,10 @@ class HTMLPurifier_Strategy_FixNesting extends HTMLPurifier_Strategy
             
             // calculate context
             if (isset($parent_def)) {
-                $context = $parent_def->type;
+                $parent_type = $parent_def->type;
             } else {
                 // generally found in specialized elements like UL
-                $context = 'unknown';
+                $parent_type = 'unknown';
             }
             
             //################################################################//
@@ -145,7 +148,7 @@ class HTMLPurifier_Strategy_FixNesting extends HTMLPurifier_Strategy
                 
                 // have DTD child def validate children
                 $result = $child_def->validateChildren(
-                    $child_tokens, $config,$context);
+                    $child_tokens, $config, $context);
                 
                 // determine whether or not this element has any exclusions
                 $excludes = $def->excludes;
@@ -187,6 +190,7 @@ class HTMLPurifier_Strategy_FixNesting extends HTMLPurifier_Strategy
                 if (!$parent_def->child->allow_empty) {
                     // we need to do a double-check
                     $i = $parent_index;
+                    array_pop($stack);
                 }
                 
                 // PROJECTED OPTIMIZATION: Process all children elements before
@@ -246,6 +250,9 @@ class HTMLPurifier_Strategy_FixNesting extends HTMLPurifier_Strategy
         array_shift($tokens);
         array_pop($tokens);
         
+        // remove context variables
+        $context->destroy('ParentType');
+        
         //####################################################################//
         // Return
         
@@ -255,4 +262,4 @@ class HTMLPurifier_Strategy_FixNesting extends HTMLPurifier_Strategy
     
 }
 
-?>
+?>

library/HTMLPurifier/Strategy/MakeWellFormed.php

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

library/HTMLPurifier/Strategy/RemoveForeignElements.php

@@ -16,7 +16,7 @@ require_once 'HTMLPurifier/TagTransform.php';
 class HTMLPurifier_Strategy_RemoveForeignElements extends HTMLPurifier_Strategy
 {
     
-    function execute($tokens, $config) {
+    function execute($tokens, $config, &$context) {
         $definition = $config->getHTMLDefinition();
         $generator = new HTMLPurifier_Generator();
         $result = array();
@@ -33,11 +33,11 @@ class HTMLPurifier_Strategy_RemoveForeignElements extends HTMLPurifier_Strategy
                     // DEFINITION CALL
                     $token = $definition->
                                 info_tag_transform[$token->name]->
-                                    transform($token);
+                                    transform($token, $config, $context);
                 } elseif ($escape_invalid_tags) {
                     // invalid tag, generate HTML and insert in
                     $token = new HTMLPurifier_Token_Text(
-                        $generator->generateFromToken($token, $config)
+                        $generator->generateFromToken($token, $config, $context)
                     );
                 } else {
                     continue;

library/HTMLPurifier/Strategy/ValidateAttributes.php

@@ -3,10 +3,8 @@
 require_once 'HTMLPurifier/Strategy.php';
 require_once 'HTMLPurifier/HTMLDefinition.php';
 require_once 'HTMLPurifier/IDAccumulator.php';
-require_once 'HTMLPurifier/ConfigDef.php';
-require_once 'HTMLPurifier/AttrContext.php';
 
-HTMLPurifier_ConfigDef::define(
+HTMLPurifier_ConfigSchema::define(
     'Attr', 'IDBlacklist', array(), 'list',
     'Array of IDs not allowed in the document.');
 
@@ -17,18 +15,14 @@ HTMLPurifier_ConfigDef::define(
 class HTMLPurifier_Strategy_ValidateAttributes extends HTMLPurifier_Strategy
 {
     
-    function execute($tokens, $config) {
+    function execute($tokens, $config, &$context) {
         
         $definition = $config->getHTMLDefinition();
         
-        // setup StrategyContext
-        $context = new HTMLPurifier_AttrContext();
-        
-        // setup ID accumulator and load it with blacklisted IDs
-        //     eventually, we'll have a dedicated context object to hold
-        //     all these accumulators and caches. For now, just an IDAccumulator
-        $context->id_accumulator = new HTMLPurifier_IDAccumulator();
-        $context->id_accumulator->load($config->get('Attr', 'IDBlacklist'));
+        // setup id_accumulator context
+        $id_accumulator = new HTMLPurifier_IDAccumulator();
+        $id_accumulator->load($config->get('Attr', 'IDBlacklist'));
+        $context->register('IDAccumulator', $id_accumulator);
         
         // create alias to global definition array, see also $defs
         // DEFINITION CALL
@@ -44,19 +38,17 @@ class HTMLPurifier_Strategy_ValidateAttributes extends HTMLPurifier_Strategy
             $attr = $token->attributes;
             
             // do global transformations (pre)
-            // ex. <ELEMENT lang="fr"> to <ELEMENT lang="fr" xml:lang="fr">
-            // DEFINITION CALL
+            // nothing currently utilizes this
             foreach ($definition->info_attr_transform_pre as $transform) {
-                $attr = $transform->transform($attr, $config);
+                $attr = $transform->transform($attr, $config, $context);
             }
             
             // do local transformations only applicable to this element (pre)
             // ex. <p align="right"> to <p style="text-align:right;">
-            // DEFINITION CALL
             foreach ($definition->info[$token->name]->attr_transform_pre
                 as $transform
             ) {
-                $attr = $transform->transform($attr, $config);
+                $attr = $transform->transform($attr, $config, $context);
             }
             
             // create alias to this element's attribute definition array, see
@@ -112,17 +104,23 @@ class HTMLPurifier_Strategy_ValidateAttributes extends HTMLPurifier_Strategy
             }
             
             // post transforms
+            
+            // ex. <x lang="fr"> to <x lang="fr" xml:lang="fr">
             foreach ($definition->info_attr_transform_post as $transform) {
-                $attr = $transform->transform($attr, $config);
+                $attr = $transform->transform($attr, $config, $context);
             }
+            
+            // ex. <bdo> to <bdo dir="ltr">
             foreach ($definition->info[$token->name]->attr_transform_post as $transform) {
-                $attr = $transform->transform($attr, $config);
+                $attr = $transform->transform($attr, $config, $context);
             }
             
             // commit changes
             // could interfere with flyweight implementation
             $tokens[$key]->attributes = $attr;
         }
+        $context->destroy('IDAccumulator');
+        
         return $tokens;
     }
     

library/HTMLPurifier/TagTransform.php

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

library/HTMLPurifier/URIScheme.php

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

library/HTMLPurifier/URIScheme/ftp.php

@@ -4,19 +4,39 @@ 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 {
     
     var $default_port = 21;
+    var $browsable = true; // usually
     
     function validateComponents(
-        $userinfo, $host, $port, $path, $query, $config
+        $userinfo, $host, $port, $path, $query, $config, &$context
     ) {
         list($userinfo, $host, $port, $path, $query) = 
             parent::validateComponents(
-                $userinfo, $host, $port, $path, $query, $config );
-        // typecode check needed on path
+                $userinfo, $host, $port, $path, $query, $config, $context );
+        $semicolon_pos = strrpos($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);
     }
     

library/HTMLPurifier/URIScheme/http.php

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

library/HTMLPurifier/URIScheme/mailto.php

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

library/HTMLPurifier/URIScheme/news.php

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

library/HTMLPurifier/URIScheme/nntp.php

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

library/HTMLPurifier/URISchemeRegistry.php

@@ -1,6 +1,6 @@
 <?php
 
-HTMLPurifier_ConfigDef::define(
+HTMLPurifier_ConfigSchema::define(
     'URI', 'AllowedSchemes', array(
         'http'  => true, // "Hypertext Transfer Protocol", nuf' said
         'https' => true, // HTTP over SSL (Secure Socket Layer)
@@ -16,7 +16,7 @@ HTMLPurifier_ConfigDef::define(
     'prevents XSS attacks from using pseudo-schemes like javascript or mocha.'
 );
 
-HTMLPurifier_ConfigDef::define(
+HTMLPurifier_ConfigSchema::define(
     'URI', 'OverrideAllowedSchemes', true, 'bool',
     'If this is set to true (which it is by default), you can override '.
     '%URI.AllowedSchemes by simply registering a HTMLPurifier_URIScheme '.
@@ -63,8 +63,9 @@ class HTMLPurifier_URISchemeRegistry
      * Retrieves a scheme validator object
      * @param $scheme String scheme name like http or mailto
      * @param $config HTMLPurifier_Config object
+     * @param $config HTMLPurifier_Context object
      */
-    function &getScheme($scheme, $config = null) {
+    function &getScheme($scheme, $config, &$context) {
         if (!$config) $config = HTMLPurifier_Config::createDefault();
         $null = null; // for the sake of passing by reference
         

maintenance/.htaccess

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

maintenance/generate-entity-file.php

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

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 = HTMLPurifier 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

plugins/modx.txt

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

smoketests/xssAttacks.php

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

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/AttrDef/CSSTest.php

@@ -92,6 +92,10 @@ class HTMLPurifier_AttrDef_CSSTest extends HTMLPurifier_AttrDefHarness
         $this->assertDef('position:absolute;', false);
         $this->assertDef('background-image:url(javascript:alert\(\));', false);
         
+        // airy input
+        $this->assertDef(' font-weight : bold; color : #ff0000',
+                         'font-weight:bold;color:#ff0000;');
+        
     }
     
 }

tests/HTMLPurifier/AttrDef/CompositeTest.php

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

tests/HTMLPurifier/AttrDef/Email/SimpleCheckTest.php

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

tests/HTMLPurifier/AttrDef/EmailHarness.php

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

tests/HTMLPurifier/AttrDef/IDTest.php

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

tests/HTMLPurifier/AttrDef/URITest.php

@@ -4,7 +4,6 @@ require_once 'HTMLPurifier/AttrDefHarness.php';
 require_once 'HTMLPurifier/AttrDef/URI.php';
 
 // WARNING: INCOMPLETE UNIT TESTS!
-// we are currently abstaining percent-encode fixing unit tests
 // we also need to test all the configuration directives defined by this class
 
 // http: is returned quite often when a URL is invalid. We have to change
@@ -83,10 +82,11 @@ class HTMLPurifier_AttrDef_URITest extends HTMLPurifier_AttrDefHarness
         // %5 - prematurely terminated, encode %
         // %FC - u with umlaut, correct
         // note that Apache doesn't do such fixing, rather, it just claims
-        // that the browser sent a "Bad Request".
-        //$uri[6] = 'http://www.example.com/%56%fc%GJ%5%FC';
-        //$components[6] = array('www.example.com', '/V%FC%25GJ%255%FC', null, null);
-        //$expect_uri[6] = 'http://www.example.com/V%FC%25GJ%255%FC';
+        // that the browser sent a "Bad Request".  See PercentEncoder.php
+        // for more details
+        $uri[6] = 'http://www.example.com/%56%fc%GJ%5%FC';
+        $components[6] = array(null, 'www.example.com', null, '/V%FC%25GJ%255%FC', null);
+        $expect_uri[6] = 'http://www.example.com/V%FC%25GJ%255%FC';
         
         // test IPv4 address (behavior may vary with configuration)
         $uri[7] = 'http://192.0.34.166/';
@@ -152,18 +152,26 @@ class HTMLPurifier_AttrDef_URITest extends HTMLPurifier_AttrDefHarness
         $uri[17] = 'javascript:alert("moo");';
         $expect_uri[17] = false;
         
-        // relative URIs
-        
-        // test basic case
+        // relative URIs - basic case
         $uri[18] = '/a/b';
         $components[18] = array(null, null, null, '/a/b', null);
         
-        // it's not allowed, so generic URI should get it
-        $uri[19] = '<';
-        $expect_uri[19] = false;
+        // result of malformed tag, gracefully handle error
+        $uri[19] = 'http://www.google.com/\'>"';
+        $components[19] = array(null, 'www.google.com', null, '/', null);
+        $expect_uri[19] = 'http://www.google.com/';
+        
+        // test empty
+        $uri[20] = '';
+        $components[20] = array(null, null, null, '', null);
+        $expect_uri[20] = '';
         
         foreach ($uri as $i => $value) {
             
+            // the read in values
+            $this->config  = isset($config[$i])  ? $config[$i]  : HTMLPurifier_Config::createDefault();
+            $this->context = isset($context[$i]) ? $context[$i] : new HTMLPurifier_Context();
+            
             // setUpAssertDef
             if ( isset($components[$i]) ) {
                 $this->components = $components[$i];
@@ -181,10 +189,6 @@ class HTMLPurifier_AttrDef_URITest extends HTMLPurifier_AttrDefHarness
                 $expect_uri[$i] = $value; // untouched
             }
             
-            // the read in values
-            $this->config  = isset($config[$i])  ? $config[$i]  : null;
-            $this->context = isset($context[$i]) ? $context[$i] : null;
-            
             $this->assertDef($value, $expect_uri[$i], true, "Test $i: %s");
             
         }
@@ -201,20 +205,21 @@ class HTMLPurifier_AttrDef_URITest extends HTMLPurifier_AttrDefHarness
         $fake_registry = new HTMLPurifier_URISchemeRegistryMock($this);
         $registry =& HTMLPurifier_URISchemeRegistry::instance($fake_registry);
         
-        // now, let's at a pseudo-scheme to the registry
+        // now, let's add a pseudo-scheme to the registry
         $this->scheme =& new HTMLPurifier_URISchemeMock($this);
         
         // here are the schemes we will support with overloaded mocks
-        $registry->setReturnReference('getScheme', $this->scheme, array('http', $this->config));
-        $registry->setReturnReference('getScheme', $this->scheme, array('mailto', $this->config));
+        $registry->setReturnReference('getScheme', $this->scheme, array('http', $this->config, $this->context));
+        $registry->setReturnReference('getScheme', $this->scheme, array('mailto', $this->config, $this->context));
         
         // default return value is false (meaning no scheme defined: reject)
-        $registry->setReturnValue('getScheme', false, array('*', $this->config));
+        $registry->setReturnValue('getScheme', false, array('*', $this->config, $this->context));
         
         if ($this->components === false) {
             $this->scheme->expectNever('validateComponents');
         } else {
             $this->components[] = $this->config; // append the configuration
+            $this->components[] =& $this->context; // append context
             $this->scheme->setReturnValue(
                 'validateComponents', $this->return_components, $this->components);
             $this->scheme->expectOnce('validateComponents', $this->components);
@@ -228,7 +233,6 @@ class HTMLPurifier_AttrDef_URITest extends HTMLPurifier_AttrDefHarness
     function testIntegration() {
         
         $this->def = new HTMLPurifier_AttrDef_URI();
-        $this->config = $this->context = null;
         
         $this->assertDef('http://www.google.com/');
         $this->assertDef('javascript:bad_stuff();', false);
@@ -239,6 +243,34 @@ class HTMLPurifier_AttrDef_URITest extends HTMLPurifier_AttrDefHarness
         
     }
     
+    function testDisableExternal() {
+        
+        $this->def = new HTMLPurifier_AttrDef_URI();
+        $this->config->set('URI', 'DisableExternal', true);
+        
+        $this->assertDef('/foobar.txt');
+        $this->assertDef('http://google.com/', false);
+        $this->assertDef('http://sub.example.com/alas?foo=asd', false);
+        
+        $this->config->set('URI', 'Host', 'sub.example.com');
+        
+        $this->assertDef('http://sub.example.com/alas?foo=asd');
+        $this->assertDef('http://example.com/teehee', false);
+        $this->assertDef('http://www.example.com/#man', false);
+        $this->assertDef('http://go.sub.example.com/perhaps?p=foo');
+        
+    }
+    
+    function testEmbeds() {
+        
+        // embedded URI
+        $this->def = new HTMLPurifier_AttrDef_URI(true);
+        
+        $this->assertDef('http://sub.example.com/alas?foo=asd');
+        $this->assertDef('mailto:foo@example.com', false);
+        
+    }
+    
 }
 
 ?>

tests/HTMLPurifier/AttrDefHarness.php

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

tests/HTMLPurifier/AttrTransform/BdoDirTest.php

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

tests/HTMLPurifier/AttrTransform/ImgRequiredTest.php

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

tests/HTMLPurifier/AttrTransform/LangTest.php

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