Finish up with a few more files that didn't get updated. Hrmm..

git-svn-id: http://htmlpurifier.org/svnroot/htmlpurifier/branches/strict@1181 48356398-32a2-884e-a903-53898d9a118a
Tack on missing basic smoketests.
2025-08-06 14:16:32 +02:00 · 2007-06-21 00:53:09 +00:00 · 2007-06-21 00:42:00 +00:00 · 2007-06-21 00:36:12 +00:00 · 2007-05-05 20:49:49 +00:00 · 2007-04-02 03:09:23 +00:00
395 changed files with 3390 additions and 20157 deletions
--- a/1101
+++ b/1101
--- a/192
+++ b/192
@@ -1,58 +1,64 @@
-
 Install
    How to install HTML Purifier

-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 downloaded the wrong software!)
-
-While the impatient can get going immediately with some of the sample
-code at the bottom of this library, it's well worth performing some
-basic sanity checks to get the most out of this library.
+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.
+
+


---------------------------------------------------------------------------
 1.  Compatibility

-THIS IS A DEPRECATED PHP4 VERSION OF HTML PURIFIER.
+HTML Purifier works in both PHP 4 and PHP 5, from PHP 4.3.2 and up. It has no
+core dependencies with other libraries.

-If you are running PHP5, please go to http://htmlpurifier.org to download
-the latest version. This version of HTML Purifier is only actively tested
-from PHP 4.3.7 to PHP 5.0.5. Essential security will be released for this branch
-fixes will be issued for the PHP 4 version until August 8, 2008. 
-
-These optional extensions can enhance the capabilities of HTML Purifier:
-
-    * iconv  : Converts text to and from non-UTF-8 encodings
-    * bcmath : Used for unit conversion and imagecrash protection
-    * tidy   : Used for pretty-printing HTML
+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.


---------------------------------------------------------------------------
-2.  Reconnaissance

-A big plus of HTML Purifier is its inerrant support of standards, so
-your web-pages should be standards-compliant.  (They should also use
-semantic markup, but that's another issue altogether, one HTML Purifier
-cannot fix without reading your mind.)
+2.  Including the library

-HTML Purifier can process these doctypes:
+Simply use:
+
+    require_once '/path/to/library/HTMLPurifier.auto.php';
+
+...and you're good to go.  Since HTML Purifier's codebase is fairly
+large, I recommend only including HTML Purifier when you need it.
+
+If you don't like your include_path to be fiddled around with, simply set
+HTML Purifier's library/ directory to the include path yourself and then:
+
+    require_once 'HTMLPurifier.php';
+
+Only the contents in the library/ folder are necessary, so you can remove
+everything else when using HTML Purifier in a production environment.  
+
+
+
+3.  Preparing the proper output environment
+
+HTML Purifier is all about web-standards, so accordingly your webpages should
+be standards compliant.  HTML Purifier can deal with these doctypes:

 * XHTML 1.0 Transitional (default)
 * XHTML 1.0 Strict
 * HTML 4.01 Transitional
 * HTML 4.01 Strict
-* XHTML 1.1
+* XHTML 1.1 sans Ruby

 ...and these character encodings:

 * UTF-8 (default)
-* Any encoding iconv supports (with crippled internationalization support)
+* Any encoding iconv supports (support is crippled for i18n though)

-These defaults reflect what my choices where be if I were authoring an
-HTML document, however, what you choose depends on the nature of your
-codebase.  If you don't know what doctype you are using, you can determine
-the doctype from this identifier at the top of your source code:
+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">
@@ -61,34 +67,18 @@ the doctype from this identifier at the top of your source code:

    <meta http-equiv="Content-type" content="text/html;charset=ENCODING">

-If the character encoding declaration is missing, STOP NOW, and
-read 'docs/enduser-utf8.html' (web accessible at
-http://htmlpurifier.org/docs/enduser-utf8.html).  In fact, even if it is
-present, read this document anyway, as most websites specify character
-encoding incorrectly.
+For legacy codebases these declarations may be missing.  If that is the case,
+STOP, and read docs/enduser-utf8.html


---------------------------------------------------------------------------
-3.  Including the library
-
-The procedure is quite simple:
-
-    require_once '/path/to/library/HTMLPurifier.auto.php';
-
-I recommend only including HTML Purifier when you need it, because that
-call represents the inclusion of a lot of PHP files which constitute
-the bulk of HTML Purifier's memory usage.
-
-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';
-
-Only the contents in the library/ folder are necessary, so you can remove
-everything else when using HTML Purifier in a production environment. 


---------------------------------------------------------------------------
+
+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
@@ -105,6 +95,7 @@ object and read on:
    $config = HTMLPurifier_Config::createDefault();


+
 4.1. Setting a different character encoding

 You really shouldn't use any other encoding except UTF-8, especially if you
@@ -126,9 +117,12 @@ websites):
 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.  If you want to work around
-this, you are welcome to read docs/enduser-utf8.html for a fix,
-but please be cognizant of the issues the "solution" creates (for this
-reason, I do not include the solution in this document).
+this, you are welcome to read docs/enduser-utf8.html for a workaround,
+but please be cognizant of the issues the "solution" creates.
+
+
+
+


 4.2. Setting a different doctype
@@ -140,6 +134,7 @@ XHTML output like this:

 Other supported doctypes include:

+
    * HTML 4.01 Strict
    * HTML 4.01 Transitional
    * XHTML 1.0 Strict
@@ -147,71 +142,17 @@ Other supported doctypes include:
    * XHTML 1.1


+
 4.3. Other settings

 There are more configuration directives which can be read about
 here: <http://htmlpurifier.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.  Some of the more interesting ones are configurable at the
-demo <http://htmlpurifier.org/demo.php> and are well worth looking into
-for your own system.
-
-For example, you can fine tune allowed elements and attributes, convert
-relative URLs to absolute ones, and even autoparagraph input text! These
-are, respectively, %HTML.Allowed, %URI.MakeAbsolute and %URI.Base, and
-%AutoFormat.AutoParagraph. The %Namespace.Directive naming convention
-translates to:
-
-    $config->set('Namespace', 'Directive', $value);
-
-E.g.
-
-    $config->set('HTML', 'Allowed', 'p,b,a[href],i');
-    $config->set('URI', 'Base', 'http://www.example.com');
-    $config->set('URI', 'MakeAbsolute', true);
-    $config->set('AutoFormat', 'AutoParagraph', true);
+your code.


---------------------------------------------------------------------------
-5. Caching

-HTML Purifier generates some cache files (generally one or two) to speed up
-its execution. For maximum performance, make sure that
-library/HTMLPurifier/DefinitionCache/Serializer is writeable by the webserver.
-
-If you are in the library/ folder of HTML Purifier, you can set the
-appropriate permissions using:
-
-    chmod -R 0755 HTMLPurifier/DefinitionCache/Serializer
-
-If the above command doesn't work, you may need to assign write permissions
-to all. This may be necessary if your webserver runs as nobody, but is
-not recommended since it means any other user can write files in the
-directory. Use:
-
-    chmod -R 0777 HTMLPurifier/DefinitionCache/Serializer
-
-You can also chmod files via your FTP client; this option
-is usually accessible by right clicking the corresponding directory and
-then selecting "chmod" or "file permissions".
-
-Starting with 2.0.1, HTML Purifier will generate friendly error messages
-that will tell you exactly what you have to chmod the directory to, if in doubt,
-follow its advice.
-
-If you are unable or unwilling to give write permissions to the cache
-directory, you can either disable the cache (and suffer a performance
-hit):
-
-    $config->set('Core', 'DefinitionCache', null);
-
-Or move the cache directory somewhere else (no trailing slash):
-
-    $config->set('Cache', 'SerializerPath', '/home/user/absolute/path');
-
-
---------------------------------------------------------------------------
-6.   Using the code
+5.   Using the code

 The interface is mind-numbingly simple:

@@ -224,15 +165,13 @@ The interface is mind-numbingly simple:
    $clean_html = $purifier->purify( $dirty_html );

 That's it!  For more examples, check out docs/examples/ (they aren't very
-different though).  Also, docs/enduser-slow.html gives advice on what to
-do if HTML Purifier is slowing down your application.
+different though).  Also, SLOW gives advice on what to do if HTML Purifier
+is slowing down your application.


---------------------------------------------------------------------------
-7.   Quick install

-First, make sure library/HTMLPurifier/DefinitionCache/Serializer is
-writable by the webserver (see Section 5: Caching above for details).
+6.   Quick install
+
 If your website is in UTF-8 and XHTML Transitional, use this code:

 <?php
@@ -255,3 +194,10 @@ If your website is in a different encoding or doctype, use this code:
    $clean_html = $purifier->purify($dirty_html);
 ?>

+
+
+7. Caching
+
+HTML Purifier generates some cache files to speed up its execution. For
+maximum performance, make sure that library/HTMLPurifier/DefinitionCache/Serializer
+is writeable by the webserver.
--- a/245
+++ b/245
@@ -9,247 +9,6 @@ NEWS ( CHANGELOG and HISTORY )                                     HTMLPurifier
    . Internal change
 ==========================

-ERRATA
- PH5P is seriously broken here; it can result in fatal errors and exceptions. 
-  If you desire to use it, please use it with the latest, PHP5-only version of 
-  HTML Purifier.
-
-2.1.5, released 2008-06-19
-! More robust imagecrash protection with height/width CSS with %CSS.MaxImgLength,
-  and height/width HTML with %HTML.MaxImgLength.
- AttrValidator operations are now atomic; updates to attributes are not
-  manifest in token until end of operations. This prevents naughty internal
-  code from directly modifying CurrentToken when they're not supposed to.
- Percent encoding checks enabled for URI query and fragment
- Disable percent height/width attributes for img
- Fix stray backslashes in font-family; CSS Unicode character escapes are
-  now properly resolved (although *only* in font-family).
- Improve parseCDATA algorithm to take into account newline normalization
- Account for browser confusion between Yen character and backslash in
-  Shift_JIS encoding. This fix generalizes to any other encoding which is not
-  a strict superset of printable ASCII.
- Improved adherence to Unicode by checking for non-character codepoints.
-  Thanks Geoffrey Sneddon for reporting. This may result in degraded
-  performance for extremely large inputs.
- Allow CSS property-value pair ''text-decoration: none''
-. Added HTMLPurifier_UnitConverter and HTMLPurifier_Length for convenient
-  handling of CSS-style lengths. HTMLPurifier_AttrDef_CSS_Length now uses
-  this class.
-. API of HTMLPurifier_AttrDef_CSS_Length changed from __construct($disable_negative)
-  to __construct($min, $max). __construct(true) is equivalent to
-  __construct('0'). (replace __construct with HTMLPurifier_AttrDef_CSS_Length)
-. Added HTMLPurifier_AttrDef_Switch class
-. Rename HTMLPurifier_HTMLModule_Tidy->construct() to setup() and bubble method
-  up inheritance hierarchy to HTMLPurifier_HTMLModule. All HTMLModules
-  get this called with the configuration object.  All modules now
-  use this rather than __construct(), although legacy code using constructors
-  will still work--the new format, however, lets modules access the
-  configuration object for HTML namespace dependant tweaks.
-. AttrDef_HTML_Pixels now takes a single construction parameter, pixels.
-
-2.1.4, released 2008-05-18
-! DefinitionCacheFactory now can register new implementations
-! CSS properties are now case-insensitive
-! Encoder optimized with valid UTF-8 input
-! HTML Purifier's URI handling is a lot more robust, with much stricter
-  validation checks and better percent encoding handling.
- Colors missing # but in hex form will be corrected
- CSS Number algorithm improved
- Autoclose now operates iteratively, i.e. <span><span><div> now has
-  both span tags closed.
- Fix bug with trusted script handling in libxml versions later than 2.6.28.
- Fix bug in comment parsing with DirectLex
- Fix bug with rgb(0, 1, 2) color syntax with spaces inside shorthand syntax
- HTMLPurifier_HTMLDefinition->addAttribute can now be called multiple times
-  on the same element without emitting errors.
- Iconv uses set_error_handler instead of shut-up operator
- Add protection against imagecrash attack with CSS height/width
- HTMLPurifier::getInstance() renamed to HTMLPurifier::instance() for consistency
- Fixed bug with fallback languages in LanguageFactory
-
-2.1.3, released 2007-11-05
-! tests/multitest.php allows you to test multiple versions by running
-  tests/index.php through multiple interpreters using `phpv` shell
-  script (you must provide this script!)
- Fixed poor include ordering for Email URI AttrDefs, causes fatal errors
-  on some systems.
- Injector algorithm further refined: off-by-one error regarding skip 
-  counts for dormant injectors fixed
- Corrective blockquote definition now enabled for HTML 4.01 Strict
- Fatal error when <img> tag (or any other element with required attributes)
-  has 'id' attribute fixed, thanks NykO18 for reporting
- Fix warning emitted when a non-supported URI scheme is passed to the
-  MakeAbsolute URIFilter, thanks NykO18 (again)
- Further refine AutoParagraph injector. Behavior inside of elements
-  allowing paragraph tags clarified: only inline content delimeted by
-  double newlines (not block elements) are paragraphed.
- Buggy treatment of end tags of elements that have required attributes
-  fixed (does not manifest on default tag-set)
- Spurious internal content reorganization error suppressed
- HTMLDefinition->addElement now returns a reference to the created
-  element object, as implied by the documentation
- Phorum mod's HTML Purifier help message expanded (unreleased elsewhere)
- Fix a theoretical class of infinite loops from DirectLex reported
-  by Nate Abele
- Work around unnecessary DOMElement type-cast in PH5P that caused errors
-  in PHP 5.1
- Work around PHP 4 SimpleTest lack-of-error complaining for one-time-only
-  HTMLDefinition errors, this may indicate problems with error-collecting
-  facilities in PHP 5
- Make ErrorCollectorEMock work in both PHP 4 and PHP 5
- Make PH5P work with PHP 5.0 by removing unnecessary array parameter typedef
-. %Core.AcceptFullDocuments renamed to %Core.ConvertDocumentToFragment 
-  to better communicate its purpose
-. Error unit tests can now specify the expectation of no errors. Future
-  iterations of the harness will be extremely strict about what errors
-  are allowed
-. Extend Injector hooks to allow for more powerful injector routines
-. HTMLDefinition->addBlankElement created, as according to the HTMLModule
-  method
-. Doxygen configuration file updated, with minor improvements
-. Test runner now checks for similarly named files in conf/ directory too.
-. Minor cosmetic change to flush-definition-cache.php: trailing newline is
-  outputted
-. Maintenance script for generating PH5P patch added, original PH5P source
-  file also added under version control
-. Full unit test runner script title made more descriptive with PHP version
-. Updated INSTALL file to state that 4.3.7 is the earliest version we
-  are actively testing
-
-2.1.2, released 2007-09-03
-! Implemented Object module for trusted users
-! Implemented experimental HTML5 parsing mode using PH5P. To use, add
-  this to your code:
-        require_once 'HTMLPurifier/Lexer/PH5P.php';
-        $config->set('Core', 'LexerImpl', 'PH5P');
-  Note that this Lexer introduces some classes not in the HTMLPurifier
-  namespace.  Also, this is PHP5 only.
-! CSS property border-spacing implemented
- Fix non-visible parsing error in DirectLex with empty tags that have
-  slashes inside attribute values.
- Fix typo in CSS definition: border-collapse:seperate; was incorrectly
-  accepted as valid CSS. Usually non-visible, because this styling is the
-  default for tables in most browsers. Thanks Brett Zamir for pointing
-  this out.
- Fix validation errors in configuration form
- Hammer out a bunch of edge-case bugs in the standalone distribution
- Inclusion reflection removed from URISchemeRegistry; you must manually
-  include any new schema files you wish to use
- Numerous typo fixes in documentation thanks to Brett Zamir
-. Unit test refactoring for one logical test per test function
-. Config and context parameters in ComplexHarness deprecated: instead, edit
-  the $config and $context member variables
-. HTML wrapper in DOMLex now takes DTD identifiers into account; doesn't
-  really make a difference, but is good for completeness sake
-. merge-library.php script refactored for greater code reusability and
-  PHP4 compatibility
-
-2.1.1, released 2007-08-04
- Fix show-stopper bug in %URI.MakeAbsolute functionality
- Fix PHP4 syntax error in standalone version
-. Add prefix directory to include path for standalone, this prevents
-  other installations from clobbering the standalone's URI schemes
-. Single test methods can be invoked by prefixing with __only
-
-2.1.0, released 2007-08-02
-# flush-htmldefinition-cache.php superseded in favor of a generic
-  flush-definition-cache.php script, you can clear a specific cache
-  by passing its name as a parameter to the script
-! Phorum mod implemented for HTML Purifier
-! With %Core.AggressivelyFixLt, <3 and similar emoticons no longer
-  trigger HTML removal in PHP5 (DOMLex). This directive is not necessary
-  for PHP4 (DirectLex).
-! Standalone file now available, which greatly reduces the amount of
-  includes (although there are still a few files that reside in the
-  standalone folder)
-! Relative URIs can now be transformed into their absolute equivalents
-  using %URI.Base and %URI.MakeAbsolute
-! Ruby implemented for XHTML 1.1
-! You can now define custom URI filtering behavior, see enduser-uri-filter.html
-  for more details
-! UTF-8 font names now supported in CSS
- AutoFormatters emit friendly error messages if tags or attributes they
-  need are not allowed
- ConfigForm's compactification of directive names is now configurable
- AutoParagraph autoformatter algorithm refined after field-testing
- XHTML 1.1 now applies XHTML 1.0 Strict cleanup routines, namely
-  blockquote wrapping
- Contents of <style> tags removed by default when tags are removed
-. HTMLPurifier_Config->getSerial() implemented, this is extremely useful
-  for output cache invalidation
-. ConfigForm printer now can retrieve CSS and JS files as strings, in
-  case HTML Purifier's directory is not publically accessible
-. Introduce new text/itext configuration directive values: these represent
-  longer strings that would be more appropriately edited with a textarea
-. Allow newlines to act as separators for lists, hashes, lookups and
-  %HTML.Allowed
-. ConfigForm generates textareas instead of text inputs for lists, hashes,
-  lookups, text and itext fields
-. Hidden element content removal genericized: %Core.HiddenElements can
-  be used to customize this behavior, by default <script> and <style> are
-  hidden
-. Added HTMLPURIFIER_PREFIX constant, should be used instead of dirname(__FILE__)
-. Custom ChildDef added to default include list
-. URIScheme reflection improved: will not attempt to include file if class
-  already exists. May clobber autoload, so I need to keep an eye on it
-. ConfigSchema heavily optimized, will only collect information and validate
-  definitions when HTMLPURIFIER_SCHEMA_STRICT is true.
-. AttrDef_URI unit tests and implementation refactored
-. benchmarks/ directory now protected from public view with .htaccess file;
-  run the tests via command line
-. URI scheme is munged off if there is no authority and the scheme is the
-  default one
-. All unit tests inherit from HTMLPurifier_Harness, not UnitTestCase
-. Interface for URIScheme changed
-. Generic URI object to hold components of URI added, most systems involved
-  in URI validation have been migrated to use it
-. Custom filtering for URIs factored out to URIDefinition interface for
-  maximum extensibility
-
-2.0.1, released 2007-06-27
-! Tag auto-closing now based on a ChildDef heuristic rather than a
-  manually set auto_close array; some behavior may change
-! Experimental AutoFormat functionality added: auto-paragraph and
-  linkify your HTML input by setting %AutoFormat.AutoParagraph and
-  %AutoFormat.Linkify to true
-! Newlines normalized internally, and then converted back to the
-  value of PHP_EOL. If this is not desired, set your newline format
-  using %Output.Newline.
-! Beta error collection, messages are implemented for the most generic
-  cases involving Lexing or Strategies
- Clean up special case code for <script> tags
- Reorder includes for DefinitionCache decorators, fixes a possible
-  missing class error
- Fixed bug where manually modified definitions were not saved via cache
-  (mostly harmless, except for the fact that it would be a little slower)
- Configuration objects with different serials do not clobber each
-  others when revision numbers are unequal
- Improve Serializer DefinitionCache directory permissions checks
- DefinitionCache no longer throws errors when it encounters old
-  serial files that do not conform to the current style
- Stray xmlns attributes removed from configuration documentation
- configForm.php smoketest no longer has XSS vulnerability due to
-  unescaped print_r output
- Printer adheres to configuration's directives on output format
- Fix improperly named form field in ConfigForm printer
-. Rewire some test-cases to swallow errors rather than expect them
-. HTMLDefinition printer updated with some of the new attributes
-. DefinitionCache keys reordered to reflect precedence: version number,
-  hash, then revision number
-. %Core.DefinitionCache renamed to %Cache.DefinitionImpl
-. Interlinking in configuration documentation added using
-  Injector_PurifierLinkify
-. Directives now keep track of aliases to themselves
-. Error collector now requires a severity to be passed, use PHP's internal
-  error constants for this
-. HTMLPurifier_Config::getAllowedDirectivesForForm implemented, allows
-  much easier selective embedding of configuration values
-. Doctype objects now accept public and system DTD identifiers
-. %HTML.Doctype is now constrained by specific values, to specify a custom
-  doctype use new %HTML.CustomDoctype
-. ConfigForm truncates long directives to keep the form small, and does
-  not re-output namespaces
-
 2.0.0, released 2007-06-20
 # Completely refactored HTMLModuleManager, decentralizing safety
  information
@@ -356,6 +115,8 @@ ERRATA
  %Attr.IDBlacklistRegexp
 - Error messages are emitted when you attempt to "allow" elements or
  attributes that HTML Purifier does not support
+
+
 - Fix segfault in unit test. The problem is not very reproduceable and
  I don't know what causes it, but a six line patch fixed it.

@@ -554,4 +315,4 @@ ERRATA
 ! First public release, most functionality implemented. Notable omissions are:
  + Shorthand CSS properties
  + Table CSS properties
-  + Deprecated attribute transformations
+  + Deprecated attribute transformations
--- a/65
+++ b/65
@@ -1,4 +1,3 @@
-
 TODO List

 = KEY ====================
@@ -7,13 +6,32 @@ TODO List
    ? Maybe I'll Do It
 ==========================

-If no interest is expressed for a feature that may required a considerable
-amount of effort to implement, it may get endlessly delayed. Do not be
-afraid to cast your vote for the next feature to be implemented!
+2.1 release [Refactor, refactor!]
+
+
+
+
+
+
+
+
+ # URI validation routines tighter (see docs/dev-code-quality.html) (COMPLEX)
+ # Advanced URI filtering schemes (see docs/proposal-new-directives.txt)
+ - Configuration profiles: predefined directives set with one func call
+ - Implement IDREF support (harder than it seems, since you cannot have
+   IDREFs to non-existent IDs)
+ - Allow non-ASCII characters in font names
+ - Genericize special cases in RemoveForeignElements

 2.2 release [Error'ed]
 # Error logging for filtering/cleanup procedures
+    - Requires I18N facilities to be created first (COMPLEX)
 - XSS-attempt detection
+ - More fine-grained control over escaping behavior
+
+
+
+

 2.3 release [Do What I Mean, Not What I Say]
 # Additional support for poorly written HTML
@@ -29,22 +47,26 @@ afraid to cast your vote for the next feature to be implemented!
 - Remove empty inline tags<i></i>
 - Append something to duplicate IDs so they're still usable (impl. note: the
   dupe detector would also need to detect the suffix as well)
- - Externalize inline CSS to promote clean HTML

 2.4 release [It's All About Trust] (floating)
 # Implement untrusted, dangerous elements/attributes
- # Implement IDREF support (harder than it seems, since you cannot have
-   IDREFs to non-existent IDs)
- # Frameset XHTML 1.0 and HTML 4.01 doctypes

 3.0 release [Beyond HTML]
 # Legit token based CSS parsing (will require revamping almost every
-   AttrDef class). Probably will use CSSTidy class
+   AttrDef class)
 # More control over allowed CSS properties (maybe modularize it in the
   same fashion!)
- # Formatters for plaintext
+ # Formatters for plaintext (COMPLEX)
+    - Auto-paragraphing (be sure to leverage fact that we know when things
+      shouldn't be paragraphed, such as lists and tables).
+    - Linkify URLs
    - Smileys
- - Standardize token armor for all areas of processing
+    - Linkification for HTML Purifier docs: notably configuration and classes
+ - Allow tags to be "armored", an internal flag that protects them
+   from validation and passes them out unharmed
+ - Fixes for Firefox's inability to handle COL alignment props (Bug 915)
+ - Automatically add non-breaking spaces to empty table cells when
+   empty-cells:show is applied to have compatibility with Internet Explorer
 - Convert RTL/LTR override characters to <bdo> tags, or vice versa on demand.
   Also, enable disabling of directionality

@@ -53,37 +75,32 @@ afraid to cast your vote for the next feature to be implemented!
    - Hooks for adding custom processors to custom namespaced tags and
      attributes, offer default implementation
    - Lots of documentation and samples
+ - XHTML 1.1 support

 Ongoing
 - Lots of profiling, make it faster!
 - Plugins for major CMSes (COMPLEX)
-    - phpBB
+    - WordPress (mostly written, needs beta-testing)
    - eFiction
    - more! (look for ones that use WYSIWYGs)
 - Complete basic smoketests

 Unknown release (on a scratch-an-itch basis)
- # CHMOD install script for PEAR installs
+ ? Semi-lossy dumb alternate character encoding transfor
 ? Have 'lang' attribute be checked against official lists, achieved by
   encoding all characters that have string entity equivalents
+ - Explain how to use HTML Purifier in non-PHP languages
 - Abstract ChildDef_BlockQuote to work with all elements that only
   allow blocks in them, required or optional
 - Reorganize Unit Tests
+    - Refactor loop tests (esp. AttrDef_URI)
 - Reorganize configuration directives (Create more namespaces! Get messy!)
- - Advanced URI filtering schemes (see docs/proposal-new-directives.txt)
- - Implement lenient <ruby> child validation
- - Explain how to use HTML Purifier in non-PHP languages / create
-   a simple command line stub (or complicated?)
- - 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

 Requested
+ ? Native content compression, whitespace stripping (don't rely on Tidy, make
+   sure we don't remove from <pre> or related tags)

 Wontfix
 - Non-lossy smart alternate character encoding transformations (unless
   patch provided)
- - Pretty-printing HTML: users can use Tidy on the output on entire page
- - Native content compression, whitespace stripping (don't rely on Tidy, make
-   sure we don't remove from <pre> or related tags): use gzip if this is
-   really important
+ - Pretty-printing HTML, users can use Tidy on the output on entire page
--- a/2
+++ b/2
@@ -1 +1 @@
-2.1.5
+2.0.0
--- a/14
+++ b/14
@@ -1,7 +1,7 @@
-Security and bugfix release 2.1.5 is a backport that fixes two vulnerabilities
-related to CSS, one of which only occurs under Shift_JIS. It also improves
-imagecrash protection (percent CSS width and height is now disabled for
-images, and you can control the bounds with %CSS.MaxImgLength and
-%HTML.MaxImgLength). Finally, there are number of bug fixes, most notably 
-support for text-decoration: none, improved adherence to Unicode and increased
-percent encoding checks.
+HTML Purifier 2.0 is the culmination of two major architectural changes. 
+The first is Tidy, which enables HTML Purifier to both natively support 
+deprecated elements and also convert them to standards-compliant 
+alternatives. The second is the Advanced API, which enables users to 
+create new elements and attributes with ease. Keeping in line with a 
+commitment to high quality, there are also five esoteric bug-fixes and a 
+plethora of subtle improvements that enhance the library. 
--- a/art/100cases.png
+++ b/art/100cases.png
--- a/benchmarks/.htaccess
+++ b/benchmarks/.htaccess
@@ -1 +0,0 @@
-Deny from all
--- a/benchmarks/Lexer.php
+++ b/benchmarks/Lexer.php
@@ -165,4 +165,4 @@ echo '<div>Random input was: ' .
 ?>


-</body></html>
+</body></html>
--- a/benchmarks/ProfileDirectLex.php
+++ b/benchmarks/ProfileDirectLex.php
@@ -15,3 +15,5 @@ $context = new HTMLPurifier_Context();
 for ($i = 0; $i < 10; $i++) {
    $tokens = $lexer->tokenizeHTML($input, $config, $context);
 }
+
+?>
--- a/benchmarks/Trace.php
+++ b/benchmarks/Trace.php
@@ -1,12 +0,0 @@
-<?php
-
-ini_set('xdebug.trace_format', 1);
-ini_set('xdebug.show_mem_delta', true);
-
-xdebug_start_trace(dirname(__FILE__) . '/Trace');
-require_once '../library/HTMLPurifier.auto.php';
-
-$purifier = new HTMLPurifier();
-
-$data = $purifier->purify(file_get_contents('samples/Lexer/4.html'));
-xdebug_stop_trace();
--- a/configdoc/generate.php
+++ b/configdoc/generate.php
@@ -18,16 +18,10 @@ TODO:
 if (version_compare('5', PHP_VERSION, '>')) exit('Requires PHP 5 or higher.');
 error_reporting(E_ALL); // probably not possible to use E_STRICT

-define('HTMLPURIFIER_SCHEMA_STRICT', true); // description data needs to be collected
-
 // load dual-libraries
 require_once '../library/HTMLPurifier.auto.php';
 require_once 'library/ConfigDoc.auto.php';

-$purifier = HTMLPurifier::getInstance(array(
-    'AutoFormat.PurifierLinkify' => true
-));
-
 $schema = HTMLPurifier_ConfigSchema::instance();
 $style = 'plain'; // use $_GET in the future
 $configdoc = new ConfigDoc();
@@ -43,3 +37,4 @@ if (php_sapi_name() != 'cli') {
    echo 'Files generated successfully.';
 }

+?>
--- a/configdoc/library/ConfigDoc.auto.php
+++ b/configdoc/library/ConfigDoc.auto.php
@@ -7,3 +7,4 @@
 set_include_path(dirname(__FILE__) . PATH_SEPARATOR . get_include_path() );
 require_once 'ConfigDoc.php';

+?>
--- a/configdoc/library/ConfigDoc.php
+++ b/configdoc/library/ConfigDoc.php
@@ -36,3 +36,4 @@ class ConfigDoc
    
 }

+?>
--- a/configdoc/library/ConfigDoc/HTMLXSLTProcessor.php
+++ b/configdoc/library/ConfigDoc/HTMLXSLTProcessor.php
@@ -36,7 +36,6 @@ class ConfigDoc_HTMLXSLTProcessor
        // fudges for HTML backwards compatibility
        $out = str_replace('/>', ' />', $out); // <br /> not <br/>
        $out = str_replace(' xmlns=""', '', $out); // rm unnecessary xmlns
-        $out = str_replace(' xmlns="http://www.w3.org/1999/xhtml"', '', $out); // rm unnecessary xmlns
        if (class_exists('Tidy')) {
            // cleanup output
            $config = array(
@@ -60,3 +59,4 @@ class ConfigDoc_HTMLXSLTProcessor
    
 }

+?>
--- a/configdoc/library/ConfigDoc/XMLSerializer.php
+++ b/configdoc/library/ConfigDoc/XMLSerializer.php
@@ -23,3 +23,4 @@ class ConfigDoc_XMLSerializer
    
 }

+?>
--- a/configdoc/library/ConfigDoc/XMLSerializer/ConfigSchema.php
+++ b/configdoc/library/ConfigDoc/XMLSerializer/ConfigSchema.php
@@ -50,12 +50,6 @@ class ConfigDoc_XMLSerializer_ConfigSchema extends ConfigDoc_XMLSerializer
                    $dom_document->createElement('name', $name)
                );
                
-                $dom_aliases = $dom_document->createElement('aliases');
-                $dom_directive->appendChild($dom_aliases);
-                foreach ($info->directiveAliases as $alias) {
-                    $dom_aliases->appendChild($dom_document->createElement('alias', $alias));
-                }
-                
                $dom_constraints = $dom_document->createElement('constraints');
                $dom_directive->appendChild($dom_constraints);
                
@@ -121,3 +115,4 @@ class ConfigDoc_XMLSerializer_ConfigSchema extends ConfigDoc_XMLSerializer
    
 }

+?>
--- a/configdoc/library/ConfigDoc/XMLSerializer/Types.php
+++ b/configdoc/library/ConfigDoc/XMLSerializer/Types.php
@@ -24,3 +24,4 @@ class ConfigDoc_XMLSerializer_Types extends ConfigDoc_XMLSerializer
    
 }

+?>
--- a/configdoc/styles/plain.xsl
+++ b/configdoc/styles/plain.xsl
@@ -72,16 +72,8 @@
        <xsl:apply-templates />
    </xsl:template>
    <xsl:template match="directive/name">
-        <xsl:apply-templates select="../aliases/alias" mode="anchor" />
        <h3 id="{../@id}"><xsl:value-of select="../@id" /></h3>
    </xsl:template>
-    <xsl:template match="alias" mode="anchor">
-        <a id="{.}"></a>
-    </xsl:template>
-    
-    <!-- Do not pass through -->
-    <xsl:template match="alias"></xsl:template>
-    
    <xsl:template match="directive/constraints">
        <table class="constraints">
            <xsl:apply-templates />
@@ -97,20 +89,8 @@
                    </td>
                </tr>
            </xsl:if>
-            <xsl:if test="../aliases/alias">
-                <xsl:apply-templates select="../aliases" mode="constraints" />
-            </xsl:if>
        </table>
    </xsl:template>
-    <xsl:template match="directive/aliases" mode="constraints">
-        <th>Aliases:</th>
-        <td>
-            <xsl:for-each select="alias">
-                <xsl:if test="position()&gt;1">, </xsl:if>
-                <xsl:value-of select="." />
-            </xsl:for-each>
-        </td>
-    </xsl:template>
    <xsl:template match="directive//description">
        <div class="description">
            <xsl:copy-of select="div/node()" />
@@ -148,4 +128,4 @@
        </tr>
    </xsl:template>
    
-</xsl:stylesheet>
+</xsl:stylesheet>
--- a/docs/dev-advanced-api.html
+++ b/docs/dev-advanced-api.html
@@ -210,4 +210,4 @@ the usual things required are:</p>

 <div id="version">$Id$</div>

-</body></html>
+</body></html>
--- a/docs/dev-code-quality.txt
+++ b/docs/dev-code-quality.txt
@@ -11,7 +11,8 @@ docs/examples/demo.php - ad hoc HTML/PHP soup to the extreme

 AttrDef - a lot of duplication, more generic classes need to be created;
 a lot of strtolower() calls, no legit casing
-    Class - doesn't support Unicode characters (fringe); uses regular expressions
+    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 (?)
@@ -21,6 +22,9 @@ ConfigSchema - redefinition is a mess
 Strategy
    FixNesting - cannot bubble nodes out of structures, duplicated checks
        for special-case parent node
+    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
--- a/docs/dev-naming.html
+++ b/docs/dev-naming.html
@@ -79,4 +79,4 @@ help you find the correct functionality more quickly.  Here they are:</p>

 <div id="version">$Id$</div>

-</body></html>
+</body></html>
--- a/docs/dev-optimization.html
+++ b/docs/dev-optimization.html
@@ -30,4 +30,4 @@ that itch, put it here!</p>

 <div id="version">$Id$</div>

-</body></html>
+</body></html>
--- a/docs/dev-progress.html
+++ b/docs/dev-progress.html
@@ -39,7 +39,7 @@ thead th {text-align:left;padding:0.1em;background-color:#EEE;}
 <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">Not priority to implement</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>
@@ -118,7 +118,6 @@ thead th {text-align:left;padding:0.1em;background-color:#EEE;}
 <tbody>
 <tr><th colspan="2">Table</th></tr>
 <tr class="impl-yes"><td>border-collapse</td><td>ENUM(collapse, seperate)</td></tr>
-<tr class="impl-yes"><td>border-space</td><td>MULTIPLE</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>
@@ -300,4 +299,4 @@ Mozilla on inside and needs -moz-outline, no IE support.</td></tr>

 <div id="version">$Id$</div>

-</body></html>
+</body></html>
--- a/docs/enduser-customize.html
+++ b/docs/enduser-customize.html
@@ -17,6 +17,11 @@
 <div id="index">Return to the <a href="index.html">index</a>.</div>
 <div id="home"><a href="http://htmlpurifier.org/">HTML Purifier</a> End-User Documentation</div>

+<div id="applicability">
+  This document covers currently unreleased functionality and
+  only applies to recent SVN checkouts.
+</div>
+
 <p>
  You may have heard of the <a href="dev-advanced-api.html">Advanced API</a>.
  If you're interested in reading dry prose and boring functional
@@ -32,7 +37,7 @@
  Before we even write any code, it is paramount to consider whether or
  not the code we're writing is necessary or not. HTML Purifier, by default,
  contains a large set of elements and attributes: large enough so that
-  <em>any</em> element or attribute in XHTML 1.0 or 1.1 (and its HTML variants)
+  <em>any</em> element or attribute in XHTML 1.0 (and its HTML variant)
  that can be safely used by the general public is implemented.
 </p>

@@ -76,12 +81,11 @@
 <h3>XHTML 1.1</h3>

 <p>
-  As of HTMLPurifier 2.1.0, we have implemented the
+  We have not implemented the
  <a href="http://www.w3.org/TR/2001/REC-ruby-20010531/">Ruby module</a>,
  which defines a set of tags
  for publishing short annotations for text, used mostly in Japanese
-  and Chinese school texts, but applicable for positioning any text (not
-  limited to translations) above or below other corresponding text.
+  and Chinese school texts.
 </p>

 <h3>XHTML 2.0</h3>
@@ -493,11 +497,10 @@ $def =& $config->getHTMLDefinition(true);
 <p>
  The <code>(%flow;)*</code> indicates the allowed children of the
  <code>li</code> tag: <code>li</code> allows any number of flow
-  elements as its children. (The <code>- O</code> allows the closing tag to be 
-  omitted, though in XML this is not allowed.) In HTML Purifier, 
-  we'd write it like <code>Flow</code> (here's where the content sets 
-  we were discussing earlier come into play). There are three shorthand
-  content models you can specify:
+  elements as its children. In HTML Purifier, we'd write it like
+  <code>Flow</code> (here's where the content sets we were
+  discussing earlier come into play). There are three shorthand content models you
+  can specify:
 </p>

 <table class="table">
@@ -670,22 +673,12 @@ $def =& $config->getHTMLDefinition(true);
  Common is a combination of the above-mentioned collections.
 </p>

-<p class="aside">
-  Readers familiar with the modularization may have noticed that the Core
-  attribute collection differs from that specified by the <a
-  href="http://www.w3.org/TR/xhtml-modularization/abstract_modules.html#s_commonatts">abstract
-  modules of the XHTML Modularization 1.1</a>. We believe this section
-  to be in error, as <code>br</code> permits the use of the <code>style</code>
-  attribute even though it uses the <code>Core</code> collection, and 
-  the DTD and XML Schemas supplied by W3C support our interpretation.
-</p>
-
 <h3>Attributes</h3>

 <p>
-  If you didn't read the <a href="#addAttribute">earlier section on
+  If you didn't read the <a href="#addAttribute">previous section on
  adding attributes</a>, read it now.  The last parameter is simply
-  an array of attribute names to attribute implementations, in the exact
+  array of attribute names to attribute implementations, in the exact
  same format as <code>addAttribute()</code>.
 </p>

@@ -795,4 +788,4 @@ $form->excludes = array('form' => true);</strong></pre>

 <div id="version">$Id: enduser-tidy.html 1158 2007-06-18 19:26:29Z Edward $</div>

-</body></html>
+</body></html>
--- a/docs/enduser-id.html
+++ b/docs/enduser-id.html
@@ -58,7 +58,7 @@ appear elsewhere on the document.  The method is simple:</p>

 <pre>$config->set('HTML', 'EnableAttrID', true);
 $config->set('Attr', 'IDBlacklist' array(
-    'list', 'of', 'attribute', 'values', 'that', 'are', 'forbidden'
+    'list', 'of', 'attributes', 'that', 'are', 'forbidden'
 ));</pre>

 <p>That being said, there are some notable drawbacks.  First of all, you have to
@@ -71,9 +71,9 @@ 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 since HTML Purifier validates each segment separately, perhaps doing
+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 in between runs.</p>
+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>
@@ -144,4 +144,4 @@ anchors is beyond me.</p>
 <div id="version">$Id$</div>

 </body>
-</html>
+</html>
--- a/docs/enduser-security.txt
+++ b/docs/enduser-security.txt
@@ -10,7 +10,9 @@ to be effective. Things to remember:

 2. IDs: see enduser-id.html for more info

-3. URIs: see enduser-uri-filter.html
+3. Links: document pending feature completion
+Rudimentary blacklisting, we should also allow only relative URIs. We
+need a doc to explain the stuff.

 4. CSS: document pending
 Explain which CSS styles we blocked and why.
--- a/docs/enduser-slow.html
+++ b/docs/enduser-slow.html
@@ -114,4 +114,4 @@ if you decide to do that! Especially if you port HTML Purifier to C++.
 <tt>;-)</tt></p>

 </body>
-</html>
+</html>
--- a/docs/enduser-tidy.html
+++ b/docs/enduser-tidy.html
@@ -16,13 +16,18 @@
 <div id="index">Return to the <a href="index.html">index</a>.</div>
 <div id="home"><a href="http://htmlpurifier.org/">HTML Purifier</a> End-User Documentation</div>

+<div id="applicability">
+  This document covers currently unreleased functionality and
+  only applies to recent SVN checkouts.
+</div>
+
 <p>You've probably heard of HTML Tidy, Dave Raggett's little piece
 of software that cleans up poorly written HTML.  Let me say it straight
 out:</p>

 <p class="emphasis">This ain't HTML Tidy!</p>

-<p>Rather, Tidy stands for a cool set of Tidy-inspired features in HTML Purifier
+<p>Rather, Tidy stands for a cool set of Tidy-inspired in HTML Purifier
 that allows users to submit deprecated elements and attributes and get
 valid strict markup back. For example:</p>

@@ -33,8 +38,8 @@ valid strict markup back. For example:</p>
 <pre>&lt;div style=&quot;text-align:center;&quot;&gt;Centered&lt;/div&gt;</pre>

 <p>...when this particular fix is run on the HTML. This tutorial will give
-you the lowdown of what exactly HTML Purifier will do when Tidy
-is on, and how to fine-tune this behavior. Once again, <strong>you do
+you down the lowdown of what exactly HTML Purifier will do when Tidy
+is on, and how to fine tune this behavior. Once again, <strong>you do
 not need Tidy installed on your PHP to use these features!</strong></p>

 <h2>What does it do?</h2>
@@ -221,10 +226,10 @@ general syntax:</p>

 <p>The lowdown is, quite frankly, HTML Purifier's default settings are
 probably good enough. The next step is to bump the level up to heavy,
-and if that still doesn't satisfy your appetite, do some fine-tuning.
+and if that still doesn't satisfy your appetite, do some fine tuning.
 Other than that, don't worry about it: this all works silently and
 effectively in the background.</p>

 <div id="version">$Id$</div>

-</body></html>
+</body></html>
--- a/docs/enduser-uri-filter.html
+++ b/docs/enduser-uri-filter.html
@@ -1,201 +0,0 @@
-<?xml version="1.0" encoding="UTF-8"?>
-<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN"
-    "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">
-<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en"><head>
-<meta http-equiv="Content-Type" content="text/html; charset=UTF-8" />
-<meta name="description" content="Tutorial for creating custom URI filters." />
-<link rel="stylesheet" type="text/css" href="style.css" />
-
-<title>URI Filters - HTML Purifier</title>
-
-</head><body>
-
-<h1>URI Filters</h1>
-
-<div id="filing">Filed under End-User</div>
-<div id="index">Return to the <a href="index.html">index</a>.</div>
-<div id="home"><a href="http://htmlpurifier.org/">HTML Purifier</a> End-User Documentation</div>
-
-<p>
-  This is a quick and dirty document to get you on your way to writing
-  custom URI filters for your own URL filtering needs.  Why would you
-  want to write a URI filter?  If you need URIs your users put into
-  HTML to magically change into a different URI, this is
-  exactly what you need!
-</p>
-
-<h2>Creating the class</h2>
-
-<p>
-  Any URI filter you make will be a subclass of <code>HTMLPurifier_URIFilter</code>.
-  The scaffolding is thus:
-</p>
-
-<pre>class HTMLPurifier_URIFilter_<strong>NameOfFilter</strong> extends HTMLPurifier_URIFilter
-{
-    var $name = '<strong>NameOfFilter</strong>';
-    function prepare($config) {}
-    function filter(&$uri, $config, &$context) {}
-}</pre>
-
-<p>
-  Fill in the variable <code>$name</code> with the name of your filter, and
-  take a look at the two methods. <code>prepare()</code> is an initialization
-  method that is called only once, before any filtering has been done of the
-  HTML. Use it to perform any costly setup work that only needs to be done
-  once. <code>filter()</code> is the guts and innards of our filter:
-  it takes the URI and does whatever needs to be done to it.
-</p>
-
-<p>
-  If you've worked with HTML Purifier, you'll recognize the <code>$config</code>
-  and <code>$context</code> parameters.  On the other hand, <code>$uri</code>
-  is something unique to this section of the application: it's a
-  <code>HTMLPurifier_URI</code> object. The interface is thus:
-</p>
-
-<pre>class HTMLPurifier_URI
-{
-    var $scheme, $userinfo, $host, $port, $path, $query, $fragment;
-    function HTMLPurifier_URI($scheme, $userinfo, $host, $port, $path, $query, $fragment);
-    function toString();
-    function copy();
-    function getSchemeObj($config, &$context);
-    function validate($config, &$context);
-}</pre>
-
-<p>
-  The first three methods are fairly self-explanatory: you have a constructor,
-  a serializer, and a cloner.  Generally, you won't be using them when
-  you are manipulating the URI objects themselves.
-  <code>getSchemeObj()</code> is a special purpose method that returns
-  a <code>HTMLPurifier_URIScheme</code> object corresponding to the specific
-  URI at hand. <code>validate()</code> performs general-purpose validation
-  on the internal components of a URI. Once again, you don't need to
-  worry about these: they've already been handled for you.
-</p>
-
-<h2>URI format</h2>
-
-<p>
-  As a URIFilter, we're interested in the member variables of the URI object.
-</p>
-
-<table class="quick"><tbody>
-  <tr><th>Scheme</th>   <td>The protocol for identifying (and possibly locating) a resource (http, ftp, https)</td></tr>
-  <tr><th>Userinfo</th> <td>User information such as a username (bob)</td></tr>
-  <tr><th>Host</th>     <td>Domain name or IP address of the server (example.com, 127.0.0.1)</td></tr>
-  <tr><th>Port</th>     <td>Network port number for the server (80, 12345)</td></tr>
-  <tr><th>Path</th>     <td>Data that identifies the resource, possibly hierarchical (/path/to, ed@example.com)</td></tr>
-  <tr><th>Query</th>    <td>String of information to be interpreted by the resource (?q=search-term)</td></tr>
-  <tr><th>Fragment</th> <td>Additional information for the resource after retrieval (#bookmark)</td></tr>
-</tbody></table>
-
-<p>
-  Because the URI is presented to us in this form, and not 
-  <code>http://bob@example.com:8080/foo.php?q=string#hash</code>, it saves us
-  a lot of trouble in having to parse the URI every time we want to filter
-  it. For the record, the above URI has the following components:
-</p>
-
-<table class="quick"><tbody>
-  <tr><th>Scheme</th>   <td>http</td></tr>
-  <tr><th>Userinfo</th> <td>bob</td></tr>
-  <tr><th>Host</th>     <td>example.com</td></tr>
-  <tr><th>Port</th>     <td>8080</td></tr>
-  <tr><th>Path</th>     <td>/foo.php</td></tr>
-  <tr><th>Query</th>    <td>q=string</td></tr>
-  <tr><th>Fragment</th> <td>hash</td></tr>
-</tbody></table>
-
-<p>
-  Note that there is no question mark or octothorpe in the query or
-  fragment: these get removed during parsing.
-</p>
-
-<p>
-  With this information, you can get straight to implementing your
-  <code>filter()</code> method. But one more thing...
-</p>
-
-<h2>Return value: Boolean, not URI</h2>
-
-<p>
-  You may have noticed that the URI is being passed in by reference.
-  This means that whatever changes you make to it, those changes will
-  be reflected in the URI object the callee had.  <strong>Do not
-  return the URI object: it is unnecessary and will cause bugs.</strong>
-  Instead, return a boolean value, true if the filtering was successful,
-  or false if the URI is beyond repair and needs to be axed.
-</p>
-
-<p>
-  Let's suppose I wanted to write a filter that de-internationalized domain
-  names by converting them to <a href="http://en.wikipedia.org/wiki/Punycode">Punycode</a>.
-  Assuming that <code>punycode_encode($input)</code> converts <code>$input</code> to
-  Punycode and returns <code>false</code> on failure:
-</p>
-
-<pre>class HTMLPurifier_URIFilter_ConvertIDNToPunycode extends HTMLPurifier_URIFilter
-{
-    var $name = 'ConvertIDNToPunycode';
-    function filter(&$uri, $config, &$context) {
-        if (is_null($uri->host)) return true;
-        if ($uri->host == utf8_decode($uri->host)) {
-            // is ASCII, abort
-            return true;
-        }
-        $host = punycode_encode($uri->host);
-        if ($host === false) return false;
-        $uri->host = $host;
-        return true;
-    }
-}</pre>
-
-<p>
-  Notice I did not <code>return $uri;</code>.
-</p>
-
-<h2>Activating your filter</h2>
-
-<p>
-  Having a filter is all well and good, but you need to tell HTML Purifier
-  to use it. Fortunately, this part's simple:
-</p>
-
-<pre>$uri =& $config->getDefinition('URI');
-$uri->addFilter(new HTMLPurifier_URIFilter_<strong>NameOfFilter</strong>());</pre>
-
-<p>
-  If you want to be really fancy, you can define a configuration directive
-  for your filter and have HTML Purifier automatically manage whether or
-  not your filter gets loaded or not (this is how internal filters manage
-  things):
-</p>
-
-<pre>HTMLPurifier_ConfigSchema::define(
-    'URI', '<strong>NameOfFilter</strong>', false, 'bool',
-    '<strong>What your filter does.</strong>'
-);
-$uri =& $config->getDefinition('URI', true);
-$uri->registerFilter(new HTMLPurifier_URIFilter_<strong>NameOfFilter</strong>());
-</pre>
-
-<p>
-  Now, your filter will only be called when %URI.<strong>NameOfFilter</strong>
-  is set to true.
-</p>
-
-<h2>Examples</h2>
-
-<p>
-  Check the
-  <a href="http://htmlpurifier.org/svnroot/htmlpurifier/trunk/library/HTMLPurifier/URIFilter/">URIFilter</a>
-  directory for more implementation examples, and see <a href="http://htmlpurifier.org/svnroot/htmlpurifier/trunk/docs/proposal-new-directives.txt">the
-  new directives proposal document</a> for ideas on what could be implemented
-  as a filter.
-</p>
-
-<div id="version">$Id$</div>
-
-</body></html>
--- a/docs/enduser-utf8.html
+++ b/docs/enduser-utf8.html
@@ -96,7 +96,7 @@ which can be a rewarding (but difficult) task.</p>
 <h2 id="findcharset">Finding the real encoding</h2>

 <p>In the beginning, there was ASCII, and things were simple. But they
-weren't good, for no one could write in Cyrillic or Thai. So there
+weren't good, for no one could write in Cryllic or Thai. So there
 exploded a proliferation of character encodings to remedy the problem
 by extending the characters ASCII could express. This ridiculously
 simplified version of the history of character encodings shows us that
@@ -138,7 +138,7 @@ browser:</p>
    <dd>View &gt; Encoding: bulleted item is unofficial name</dd>
 </dl>

-<p>Internet Explorer won't give you the MIME (i.e. useful/real) name of the
+<p>Internet Explorer won't give you the mime (i.e. useful/real) name of the
 character encoding, so you'll have to look it up using their description.
 Some common ones:</p>

@@ -216,12 +216,6 @@ if your <code>META</code> tag claims that either:</p>

 <h2 id="fixcharset">Fixing the encoding</h2>

-<p class="aside">The advice given here is for pages being served as
-vanilla <code>text/html</code>.  Different practices must be used
-for <code>application/xml</code> or <code>application/xml+xhtml</code>, see
-<a href="http://www.w3.org/TR/2002/NOTE-xhtml-media-types-20020430/">W3C's
-document on XHTML media types</a> for more information.</p>
-
 <p>If your <code>META</code> encoding and your real encoding match,
 savvy! You can skip this section. If they don't...</p>

@@ -237,7 +231,7 @@ of your real encoding.</p>
    why the character encoding should be explicitly stated. When the
    browser isn't told what the character encoding of a text is, it
    has to guess: and sometimes the guess is wrong. Hackers can manipulate
-    this guess in order to slip XSS past filters and then fool the
+    this guess in order to slip XSS pass filters and then fool the
    browser into executing it as active code. A great example of this
    is the <a href="http://shiflett.org/archive/177">Google UTF-7
    exploit</a>.</p>
@@ -308,8 +302,7 @@ languages</a>. The appropriate code is:</p>

 <p>...replacing UTF-8 with whatever your embedded encoding is.
 This code must come before any output, so be careful about
-stray whitespace in your application (i.e., any whitespace before 
-output excluding whitespace within &lt;?php ?&gt; tags).</p>
+stray whitespace in your application.</p>

 <h4 id="fixcharset-server-phpini">PHP ini directive</h4>

@@ -320,8 +313,8 @@ header call: <code><a href="http://php.net/ini.core#ini.default-charset">default

 <p>...will also do the trick. If PHP is running as an Apache module (and
 not as FastCGI, consult
-<a href="http://php.net/phpinfo">phpinfo</a>() for details), you can even use htaccess to apply this property
-across many PHP files:</p>
+<a href="http://php.net/phpinfo">phpinfo</a>() for details), you can even use htaccess do apply this property
+globally:</p>

 <pre><a href="http://php.net/configuration.changes#configuration.changes.apache">php_value</a> default_charset &quot;UTF-8&quot;</pre>

@@ -367,11 +360,10 @@ to send anything at all:</p>

 <pre><a href="http://httpd.apache.org/docs/1.3/mod/core.html#adddefaultcharset">AddDefaultCharset</a> Off</pre>

-<p>...making your internal charset declaration (usually the <code>META</code> tags)
-the sole source of character encoding 
-information. In these cases, it is <em>especially</em> important to make 
-sure you have valid <code>META</code> tags on your pages and all the 
-text before them is ASCII.</p>
+<p>...making your <code>META</code> tags the sole source of
+character encoding information. In these cases, it is
+<em>especially</em> important to make sure you have valid <code>META</code>
+tags on your pages and all the text before them is ASCII.</p>

 <blockquote class="aside"><p>These directives can also be
 placed in httpd.conf file for Apache, but
@@ -436,30 +428,28 @@ IIS to change character encodings, I'd be grateful.</p>

 <p><code>META</code> tags are the most common source of embedded
 encodings, but they can also come from somewhere else: XML
-Declarations. They look like:</p>
+processing instructions. They look like:</p>

 <pre>&lt;?xml version=&quot;1.0&quot; encoding=&quot;UTF-8&quot;?&gt;</pre>

 <p>...and are most often found in XML documents (including XHTML).</p>

-<p>For XHTML, this XML Declaration theoretically
+<p>For XHTML, this processing instruction theoretically
 overrides the <code>META</code> tag. In reality, this happens only when the
 XHTML is actually served as legit XML and not HTML, which is almost always
 never due to Internet Explorer's lack of support for 
 <code>application/xhtml+xml</code> (even though doing so is often
-argued to be <a href="http://www.hixie.ch/advocacy/xhtml">good 
-practice</a> and is required by the XHTML 1.1 specification).</p>
+argued to be <a href="http://www.hixie.ch/advocacy/xhtml">good practice</a>).</p>

-<p>For XML, however, this XML Declaration is extremely important.
+<p>For XML, however, this processing instruction is extremely important.
 Since most webservers are not configured to send charsets for .xml files,
 this is the only thing a parser has to go on. Furthermore, the default
 for XML files is UTF-8, which often butts heads with more common
 ISO-8859-1 encoding (you see this in garbled RSS feeds).</p>

 <p>In short, if you use XHTML and have gone through the
-trouble of adding the XML Declaration, make sure it jives
-with your <code>META</code> tags (which should only be present 
-if served in text/html) and HTTP headers.</p>
+trouble of adding the XML header, make sure it jives
+with your <code>META</code> tags and HTTP headers.</p>

 <h3 id="fixcharset-internals">Inside the process</h3>

@@ -516,7 +506,7 @@ usage in one language sometimes requires the occasional special character
 that, without surprise, is not available in your character set. Sometimes
 developers get around this by adding support for multiple encodings: when
 using Chinese, use Big5, when using Japanese, use Shift-JIS, when
-using Greek, etc. Other times, they use character references with great
+using Greek, etc. Other times, they use character entities with great
 zeal.</p>

 <p>UTF-8, however, obviates the need for any of these complicated
@@ -530,14 +520,14 @@ you don't have to use those user-unfriendly entities.</p>

 <p>Websites encoded in Latin-1 (ISO-8859-1) which ocassionally need
 a special character outside of their scope often will use a character
-entity reference to achieve the desired effect. For instance, &theta; can be
+entity to achieve the desired effect. For instance, &theta; can be
 written <code>&amp;theta;</code>, regardless of the character encoding's
 support of Greek letters.</p>

 <p>This works nicely for limited use of special characters, but
 say you wanted this sentence of Chinese text: &#28608;&#20809;,
 &#36889;&#20841;&#20491;&#23383;&#26159;&#29978;&#40636;&#24847;&#24605;.
-The ampersand encoded version would look like this:</p>
+The entity-ized version would look like this:</p>

 <pre>&amp;#28608;&amp;#20809;, &amp;#36889;&amp;#20841;&amp;#20491;&amp;#23383;&amp;#26159;&amp;#29978;&amp;#40636;&amp;#24847;&amp;#24605;</pre>

@@ -555,7 +545,7 @@ an application that originally used ISO-8859-1 but switched to UTF-8
 when it became far to cumbersome to support foreign languages. Bots
 will now actually go through articles and convert character entities
 to their corresponding real characters for the sake of user-friendliness
-and searchability. See
+and searcheability. See
 <a href="http://meta.wikimedia.org/wiki/Help:Special_characters">Meta's
 page on special characters</a> for more details.
 </p></blockquote>
@@ -577,11 +567,10 @@ which may be used by POST, and is required when you want to upload
 files.</p>

 <p>The following is a summarization of notes from
-<a href="http://web.archive.org/web/20060427015200/ppewww.ph.gla.ac.uk/~flavell/charset/form-i18n.html">
+<a href="http://ppewww.physics.gla.ac.uk/~flavell/charset/form-i18n.html">
 <code>FORM</code> submission and i18n</a>. That document contains lots
 of useful information, but is written in a rambly manner, so
-here I try to get right to the point. (Note: the original has 
-disappeared off the web, so I am linking to the Web Archive copy.)</p>
+here I try to get right to the point.</p>

 <h4 id="whyutf8-forms-urlencoded"><code>application/x-www-form-urlencoded</code></h4>

@@ -603,7 +592,7 @@ browser you're using, they might:</p>
 <ul>
    <li>Replace the unsupported characters with useless question marks,</li>
    <li>Attempt to fix the characters (example: smart quotes to regular quotes),</li>
-    <li>Replace the character with a character entity reference, or</li>
+    <li>Replace the character with a character entity, or</li>
    <li>Send it anyway as a different character encoding mixed in
        with the original encoding (usually Windows-1252 rather than
        iso-8859-1 or UTF-8 interspersed in 8-bit)</li>
@@ -619,7 +608,7 @@ since UTF-8 supports every character.</p>

 <h4 id="whyutf8-forms-multipart"><code>multipart/form-data</code></h4>

-<p>Multipart form submission takes away a lot of the ambiguity
+<p>Multipart form submission takes a way a lot of the ambiguity
 that percent-encoding had: the server now can explicitly ask for
 certain encodings, and the client can explicitly tell the server
 during the form submission what encoding the fields are in.</p>
@@ -632,9 +621,9 @@ Each method has deficiencies, especially the former.</p>
 <p>If you tell the browser to send the form in the same encoding as
 the page, you still have the trouble of what to do with characters
 that are outside of the character encoding's range. The behavior, once
-again, varies: Firefox 2.0 converts them to character entity references
-while Internet Explorer 7.0 mangles them beyond intelligibility. For
-serious internationalization purposes, this is not an option.</p>
+again, varies: Firefox 2.0 entity-izes them while Internet Explorer
+7.0 mangles them beyond intelligibility. For serious internationalization purposes,
+this is not an option.</p>

 <p>The other possibility is to set Accept-Encoding to UTF-8, which
 begs the question: Why aren't you using UTF-8 for everything then?
@@ -674,12 +663,12 @@ it up to the module iconv to do the dirty work.</p>
 <p>This approach, however, is not perfect. iconv is blithely unaware
 of HTML character entities. HTML Purifier, in order to
 protect against sophisticated escaping schemes, normalizes all character
-and numeric entitie references before processing the text. This leads to
+and numeric entities before processing the text. This leads to
 one important ramification:</p>

 <p><strong>Any character that is not supported by the target character
 set, regardless of whether or not it is in the form of a character
-entity reference or a raw character, will be silently ignored.</strong></p>
+entity or a raw character, will be silently ignored.</strong></p>

 <p>Example of this principle at work: say you have <code>&amp;theta;</code>
 in your HTML, but the output is in Latin-1 (which, understandably,
@@ -688,7 +677,7 @@ set the encoding correctly using %Core.Encoding):</p>

 <ul>
    <li>The <code>Encoder</code> will transform the text from ISO 8859-1 to UTF-8
-        (note that theta is preserved here since it doesn't actually use
+        (note that theta is preserved since it doesn't actually use
        any non-ASCII characters): <code>&amp;theta;</code></li>
    <li>The <code>EntityParser</code> will transform all named and numeric
        character entities to their corresponding raw UTF-8 equivalents:
@@ -711,7 +700,7 @@ Purifier has provided a slightly more palatable workaround using
    <li>The <code>EntityParser</code> transforms entities: <code>&theta;</code></li>
    <li>HTML Purifier processes the code: <code>&theta;</code></li>
    <li>The <code>Encoder</code> replaces all non-ASCII characters
-        with numeric entity reference: <code>&amp;#952;</code></li>
+        with numeric entities: <code>&amp;#952;</code></li>
    <li>For good measure, <code>Encoder</code> transforms encoding back to
        original (which is strictly unnecessary for 99% of encodings
        out there): <code>&amp;#952;</code> (remember, it's all ASCII!)</li>
@@ -721,19 +710,19 @@ Purifier has provided a slightly more palatable workaround using
 the land of Unicode characters, and is totally unacceptable for Chinese
 or Japanese texts. The even bigger kicker is that, supposing the
 input encoding was actually ISO-8859-7, which <em>does</em> support
-theta, the character would get converted into a character entity reference
-anyway! (The Encoder does not discriminate).</p>
+theta, the character would get entity-ized anyway! (The Encoder does
+not discriminate).</p>

 <p>The current functionality is about where HTML Purifier will be for
 the rest of eternity. HTML Purifier could attempt to preserve the original
-form of the character references so that they could be substituted back in, only the
+form of the entities so that they could be substituted back in, only the
 DOM extension kills them off irreversibly. HTML Purifier could also attempt
 to be smart and only convert non-ASCII characters that weren't supported
 by the target encoding, but that would require reimplementing iconv
 with HTML awareness, something I will not do.</p>

 <p>So there: either it's UTF-8 or crippled international support. Your pick! (and I'm
-not being sarcastic here: some people could care less about other languages).</p>
+not being sarcastic here: some people could care less about other languages)</p>

 <h2 id="migrate">Migrate to UTF-8</h2>

@@ -995,7 +984,7 @@ and yes, it is variable width. Other traits:</p>
 in different ways. It is beyond the scope of this document to explain
 what precisely these implications are. PHPWact provides
 a very good <a href="http://www.phpwact.org/php/i18n/utf-8">reference document</a>
-on what to expect from each function, although coverage is spotty in
+on what to expect from each functions, although coverage is spotty in
 some areas. Their more general notes on
 <a href="http://www.phpwact.org/php/i18n/charsets">character sets</a>
 are also worth looking at for information on UTF-8. Some rules of thumb
@@ -1009,7 +998,7 @@ when dealing with Unicode text:</p>
    <li>Think twice before using functions that:<ul>
        <li>...count characters (strlen will return bytes, not characters;
            str_split and word_wrap may corrupt)</li>
-        <li>...convert characters to entity references (UTF-8 doesn't need entities)</li>
+        <li>...entity-ize things (UTF-8 doesn't need entities)</li>
        <li>...do very complex string processing (*printf)</li>
    </ul></li>
 </ul>
@@ -1054,4 +1043,4 @@ a more in-depth look into character sets and encodings.</p>
 </ul>

 </body>
-</html>
+</html>
--- a/docs/enduser-youtube.html
+++ b/docs/enduser-youtube.html
@@ -149,4 +149,4 @@ like that, for that matter), send it over and it might get included
 with the core!</p>

 </body>
-</html>
+</html>
--- a/docs/examples/basic.php
+++ b/docs/examples/basic.php
@@ -20,3 +20,4 @@ $pure_html = $purifier->purify($html);

 echo '<pre>' . htmlspecialchars($pure_html) . '</pre>';

+?>
--- a/docs/index.html
+++ b/docs/index.html
@@ -40,9 +40,6 @@ information for casual developers using HTML Purifier.</p>
 <dt><a href="enduser-customize.html">Customize</a></dt>
 <dd>Tutorial for customizing HTML Purifier's tag and attribute sets.</dd>

-<dt><a href="enduser-uri-filter.html">URI Filters</a></dt>
-<dd>Tutorial for creating custom URI filters.</dd>
-
 </dl>

 <h2>Development</h2>
@@ -165,4 +162,4 @@ the code. They may be upgraded to HTML files or stay as TXT scratchpads.</p>

 <div id="version">$Id$</div>
 </body>
-</html>
+</html>
--- a/docs/proposal-filter-levels.txt
+++ b/docs/proposal-filter-levels.txt
@@ -32,7 +32,7 @@ Here are some fuzzy levels you could set:

 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 editor that hasn't been synced accordingly. This may
+is incoming from a WYSIWYG eidtor that hasn't been synced accordingly. This may
 make forbidden element to text transformations desirable (for example, images).


--- a/docs/proposal-new-directives.txt
+++ b/docs/proposal-new-directives.txt
@@ -2,8 +2,7 @@
 Configuration Ideas

 Here are some theoretical configuration ideas that we could implement some
-time.  Note the naming convention: %Namespace.Directive. If you want one
-implemented, give us a ring, and we'll move it up the priority chain.
+time.  Note the naming convention: %Namespace.Directive

 %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
@@ -23,6 +22,8 @@ implemented, give us a ring, and we'll move it up the priority chain.
 %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.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
--- a/docs/ref-css-length.txt
+++ b/docs/ref-css-length.txt
@@ -1,28 +0,0 @@
-
-CSS Length Reference
-  To bound, or not to bound, that is the question
-
-It's quite a reasonable request, really, and it's already been implemented
-for HTML.  That is, length bounding.  It makes little sense to let users
-define text blocks that have a font-size of 63,360 inches (that's a mile,
-by the way) or a width of forty-fold the parent container.
-
-But it's a little more complicated then that. There are multiple units
-one can use, and we have to a little unit conversion to get things working.
-Here's what we have:
-
-Absolute:
-    1 in ~= 2.54 cm
-    1 cm = 10 mm
-    1 pt = 1/72 in
-    1 pc = 12 pt
-
-Relative:
-    1 em ~= 10.0667 px
-    1 ex ~= 0.5 em, though Mozilla Firefox says 1 ex = 6px
-    1 px ~= 1 pt
-
-Watch out: font-sizes can also be nested to get successively larger 
-(although I do not relish having to keep track of context font-sizes,
-this may be necessary, especially for some of the more advanced features
-for preventing things like white on white).
--- a/docs/ref-devnetwork.html
+++ b/docs/ref-devnetwork.html
@@ -42,4 +42,4 @@ the development of this library in these forum threads:</p>

 <div id="version">$Id$</div>
 </body>
-</html>
+</html>
--- a/docs/ref-proprietary-tags.txt
+++ b/docs/ref-proprietary-tags.txt
@@ -21,4 +21,4 @@ HTML Purifier context.
 <xmp>, monospace, replace with pre

 These should be put into their own Tidy module, not loaded by default(?). These
-all qualify as "lenient" transforms.
+all qualify as "lenient" transforms.
--- a/docs/style.css
+++ b/docs/style.css
@@ -33,9 +33,6 @@ blockquote .label {font-weight:bold; font-size:1em; margin:0 0 .1em;
 .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;}

-/* A quick table*/
-table.quick tbody th {text-align:right; padding-right:1em;}
-
 /* Category of the file */
 #filing {font-weight:bold; font-size:smaller; }

--- a/library/HTMLPurifier.auto.php
+++ b/library/HTMLPurifier.auto.php
@@ -7,3 +7,4 @@
 set_include_path(dirname(__FILE__) . PATH_SEPARATOR . get_include_path() );
 require_once 'HTMLPurifier.php';

+?>
--- a/library/HTMLPurifier.func.php
+++ b/library/HTMLPurifier.func.php
@@ -18,3 +18,4 @@ function HTMLPurifier($html, $config = null) {
    return $purifier->purify($html, $config);
 }

+?>
--- a/library/HTMLPurifier.php
+++ b/library/HTMLPurifier.php
@@ -22,8 +22,8 @@
 */

 /*
-    HTML Purifier 2.1.5 - Standards Compliant HTML Filtering
-    Copyright (C) 2006-2007 Edward Z. Yang
+    HTML Purifier 2.0.0 - Standards Compliant HTML Filtering
+    Copyright (C) 2006 Edward Z. Yang

    This library is free software; you can redistribute it and/or
    modify it under the terms of the GNU Lesser General Public
@@ -40,11 +40,9 @@
    Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301  USA
 */

-// constants are slow, but we'll make one exception
-define('HTMLPURIFIER_PREFIX', dirname(__FILE__));
-
-// every class has an undocumented dependency to these, must be included!
-require_once 'HTMLPurifier/ConfigSchema.php'; // fatal errors if not included
+// almost every class has an undocumented dependency to these, so make sure
+// they get included
+require_once 'HTMLPurifier/ConfigSchema.php'; // important
 require_once 'HTMLPurifier/Config.php';
 require_once 'HTMLPurifier/Context.php';

@@ -53,29 +51,29 @@ require_once 'HTMLPurifier/Generator.php';
 require_once 'HTMLPurifier/Strategy/Core.php';
 require_once 'HTMLPurifier/Encoder.php';

-require_once 'HTMLPurifier/ErrorCollector.php';
 require_once 'HTMLPurifier/LanguageFactory.php';

+HTMLPurifier_ConfigSchema::define(
+    'Core', 'Language', 'en', 'string', '
+ISO 639 language code for localizable things in HTML Purifier to use,
+which is mainly error reporting. There is currently only an English (en)
+translation, so this directive is currently useless.
+This directive has been available since 2.0.0.
+');
+
 HTMLPurifier_ConfigSchema::define(
    'Core', 'CollectErrors', false, 'bool', '
 Whether or not to collect errors found while filtering the document. This
-is a useful way to give feedback to your users. <strong>Warning:</strong>
-Currently this feature is very patchy and experimental, with lots of
-possible error messages not yet implemented. It will not cause any problems,
-but it may not help your users either. This directive has been available
-since 2.0.0.
+is a useful way to give feedback to your users. CURRENTLY NOT IMPLEMENTED.
+This directive has been available since 2.0.0.
 ');

 /**
- * Facade that coordinates HTML Purifier's subsystems in order to purify HTML.
+ * Main library execution class.
 * 
- * @note There are several points in which configuration can be specified 
- *       for HTML Purifier.  The precedence of these (from lowest to
- *       highest) is as follows:
- *          -# Instance: new HTMLPurifier($config)
- *          -# Invocation: purify($html, $config)
- *       These configurations are entirely independent of each other and
- *       are *not* merged.
+ * Facade that performs calls to the HTMLPurifier_Lexer,
+ * HTMLPurifier_Strategy and HTMLPurifier_Generator subsystems in order to
+ * purify HTML.
 * 
 * @todo We need an easier way to inject strategies, it'll probably end
 *       up getting done through config though.
@@ -83,16 +81,15 @@ since 2.0.0.
 class HTMLPurifier
 {
    
-    var $version = '2.1.5';
+    var $version = '2.0.0';
    
    var $config;
-    var $filters = array();
+    var $filters;
    
    var $strategy, $generator;
    
    /**
-     * Resultant HTMLPurifier_Context of last run purification. Is an array
-     * of contexts if the last called method was purifyArray().
+     * Final HTMLPurifier_Context of last run purification. Might be an array.
     * @public
     */
    var $context;
@@ -142,26 +139,17 @@ class HTMLPurifier
        
        $context = new HTMLPurifier_Context();
        
-        // our friendly neighborhood generator, all primed with configuration too!
-        $this->generator->generateFromTokens(array(), $config, $context);
-        $context->register('Generator', $this->generator);
-        
        // set up global context variables
        if ($config->get('Core', 'CollectErrors')) {
            // may get moved out if other facilities use it
            $language_factory = HTMLPurifier_LanguageFactory::instance();
-            $language = $language_factory->create($config, $context);
+            $language = $language_factory->create($config->get('Core', 'Language'));
            $context->register('Locale', $language);
            
-            $error_collector = new HTMLPurifier_ErrorCollector($context);
-            $context->register('ErrorCollector', $error_collector);
+            $error_collector = new HTMLPurifier_ErrorCollector();
+            $context->register('ErrorCollector', $language);
        }
        
-        // setup id_accumulator context, necessary due to the fact that
-        // AttrValidator can be called from many places
-        $id_accumulator = HTMLPurifier_IDAccumulator::build($config, $context);
-        $context->register('IDAccumulator', $id_accumulator);
-        
        $html = HTMLPurifier_Encoder::convertToUTF8($html, $config, $context);
        
        for ($i = 0, $size = count($this->filters); $i < $size; $i++) {
@@ -210,16 +198,14 @@ class HTMLPurifier
    
    /**
     * Singleton for enforcing just one HTML Purifier in your system
-     * @param $prototype Optional prototype HTMLPurifier instance to
-     *                   overload singleton with.
     */
-    function &instance($prototype = null) {
+    function &getInstance($prototype = null) {
        static $htmlpurifier;
        if (!$htmlpurifier || $prototype) {
            if (is_a($prototype, 'HTMLPurifier')) {
                $htmlpurifier = $prototype;
            } elseif ($prototype) {
-                $htmlpurifier = new HTMLPurifier($prototype);
+                $htmlpurifier = new HTMLPurifier(HTMLPurifier_Config::create($prototype));
            } else {
                $htmlpurifier = new HTMLPurifier();
            }
@@ -227,9 +213,7 @@ class HTMLPurifier
        return $htmlpurifier;
    }
    
-    function &getInstance($prototype = null) {
-        return HTMLPurifier::instance($prototype);
-    }
    
 }

+?>
--- a/library/HTMLPurifier/AttrCollections.php
+++ b/library/HTMLPurifier/AttrCollections.php
@@ -127,3 +127,4 @@ class HTMLPurifier_AttrCollections
    
 }

+?>
--- a/library/HTMLPurifier/AttrDef.php
+++ b/library/HTMLPurifier/AttrDef.php
@@ -54,15 +54,18 @@ class HTMLPurifier_AttrDef
     * 
     * @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.  However, note that we are NOT necessarily
-     *          parsing XML, thus, this behavior may still be correct. We
-     *          assume that newlines have been normalized.
+     *          4.7.  Compliant processing requires all line breaks normalized
+     *          to "\n", so the fix is not as simple as fixing it in this
+     *          function.  Trim and whitespace collapsing are supposed to only
+     *          occur in NMTOKENs.  However, note that we are NOT necessarily
+     *          parsing XML, thus, this behavior may still be correct.
     * 
     * @public
     */
    function parseCDATA($string) {
        $string = trim($string);
-        $string = str_replace(array("\n", "\t", "\r"), ' ', $string);
+        $string = str_replace("\n", '', $string);
+        $string = str_replace(array("\r", "\t"), ' ', $string);
        return $string;
    }
    
@@ -79,13 +82,6 @@ class HTMLPurifier_AttrDef
        return $this;
    }
    
-    /**
-     * Removes spaces from rgb(0, 0, 0) so that shorthand CSS properties work
-     * properly. THIS IS A HACK!
-     */
-    function mungeRgb($string) {
-        return preg_replace('/rgb\((\d+)\s*,\s*(\d+)\s*,\s*(\d+)\)/', 'rgb(\1,\2,\3)', $string);
-    }
-    
 }

+?>
--- a/library/HTMLPurifier/AttrDef/CSS.php
+++ b/library/HTMLPurifier/AttrDef/CSS.php
@@ -38,20 +38,7 @@ class HTMLPurifier_AttrDef_CSS extends HTMLPurifier_AttrDef
            list($property, $value) = explode(':', $declaration, 2);
            $property = trim($property);
            $value    = trim($value);
-            $ok = false;
-            do {
-                if (isset($definition->info[$property])) {
-                    $ok = true;
-                    break;
-                }
-                if (ctype_lower($property)) break;
-                $property = strtolower($property);
-                if (isset($definition->info[$property])) {
-                    $ok = true;
-                    break;
-                }
-            } while(0);
-            if (!$ok) continue;
+            if (!isset($definition->info[$property])) continue;
            // inefficient call, since the validator will do this again
            if (strtolower(trim($value)) !== 'inherit') {
                // inherit works for everything (but only on the base property)
@@ -79,3 +66,4 @@ class HTMLPurifier_AttrDef_CSS extends HTMLPurifier_AttrDef
    
 }

+?>
--- a/library/HTMLPurifier/AttrDef/CSS/Background.php
+++ b/library/HTMLPurifier/AttrDef/CSS/Background.php
@@ -31,9 +31,6 @@ class HTMLPurifier_AttrDef_CSS_Background extends HTMLPurifier_AttrDef
        $string = $this->parseCDATA($string);
        if ($string === '') return false;
        
-        // munge rgb() decl if necessary
-        $string = $this->mungeRgb($string);
-        
        // assumes URI doesn't have spaces in it
        $bits = explode(' ', strtolower($string)); // bits to process
        
@@ -87,3 +84,4 @@ class HTMLPurifier_AttrDef_CSS_Background extends HTMLPurifier_AttrDef
    
 }

+?>
--- a/library/HTMLPurifier/AttrDef/CSS/BackgroundPosition.php
+++ b/library/HTMLPurifier/AttrDef/CSS/BackgroundPosition.php
@@ -127,3 +127,4 @@ class HTMLPurifier_AttrDef_CSS_BackgroundPosition extends HTMLPurifier_AttrDef
    
 }

+?>
--- a/library/HTMLPurifier/AttrDef/CSS/Border.php
+++ b/library/HTMLPurifier/AttrDef/CSS/Border.php
@@ -22,7 +22,7 @@ class HTMLPurifier_AttrDef_CSS_Border extends HTMLPurifier_AttrDef
    
    function validate($string, $config, &$context) {
        $string = $this->parseCDATA($string);
-        $string = $this->mungeRgb($string);
+        // we specifically will not support rgb() syntax with spaces
        $bits = explode(' ', $string);
        $done = array(); // segments we've finished
        $ret = ''; // return value
@@ -42,3 +42,4 @@ class HTMLPurifier_AttrDef_CSS_Border extends HTMLPurifier_AttrDef
    
 }

+?>
--- a/library/HTMLPurifier/AttrDef/CSS/Color.php
+++ b/library/HTMLPurifier/AttrDef/CSS/Color.php
@@ -39,13 +39,20 @@ class HTMLPurifier_AttrDef_CSS_Color extends HTMLPurifier_AttrDef
        if ($colors === null) $colors = $config->get('Core', 'ColorKeywords');
        
        $color = trim($color);
-        if ($color === '') return false;
+        if (!$color) return false;
        
        $lower = strtolower($color);
        if (isset($colors[$lower])) return $colors[$lower];
        
-        if (strpos($color, 'rgb(') !== false) {
+        if ($color[0] === '#') {
+            // hexadecimal handling
+            $hex = substr($color, 1);
+            $length = strlen($hex);
+            if ($length !== 3 && $length !== 6) return false;
+            if (!ctype_xdigit($hex)) return false;
+        } else {
            // rgb literal handling
+            if (strpos($color, 'rgb(')) return false;
            $length = strlen($color);
            if (strpos($color, ')') !== $length - 1) return false;
            $triad = substr($color, 4, $length - 4 - 1);
@@ -83,17 +90,6 @@ class HTMLPurifier_AttrDef_CSS_Color extends HTMLPurifier_AttrDef
            }
            $new_triad = implode(',', $new_parts);
            $color = "rgb($new_triad)";
-        } else {
-            // hexadecimal handling
-            if ($color[0] === '#') {
-                $hex = substr($color, 1);
-            } else {
-                $hex = $color;
-                $color = '#' . $color;
-            }
-            $length = strlen($hex);
-            if ($length !== 3 && $length !== 6) return false;
-            if (!ctype_xdigit($hex)) return false;
        }
        
        return $color;
@@ -102,3 +98,4 @@ class HTMLPurifier_AttrDef_CSS_Color extends HTMLPurifier_AttrDef
    
 }

+?>
--- a/library/HTMLPurifier/AttrDef/CSS/Composite.php
+++ b/library/HTMLPurifier/AttrDef/CSS/Composite.php
@@ -35,3 +35,4 @@ class HTMLPurifier_AttrDef_CSS_Composite extends HTMLPurifier_AttrDef
    
 }

+?>
--- a/library/HTMLPurifier/AttrDef/CSS/DenyElementDecorator.php
+++ b/library/HTMLPurifier/AttrDef/CSS/DenyElementDecorator.php
@@ -1,26 +0,0 @@
-<?php
-
-/**
- * Decorator which enables CSS properties to be disabled for specific elements.
- */
-class HTMLPurifier_AttrDef_CSS_DenyElementDecorator extends HTMLPurifier_AttrDef
-{
-    var $def, $element;
-    
-    /**
-     * @param $def Definition to wrap
-     * @param $element Element to deny
-     */
-    function HTMLPurifier_AttrDef_CSS_DenyElementDecorator(&$def, $element) {
-        $this->def =& $def;
-        $this->element = $element;
-    }
-    /**
-     * Checks if CurrentToken is set and equal to $this->element
-     */
-    function validate($string, $config, $context) {
-        $token = $context->get('CurrentToken', true);
-        if ($token && $token->name == $this->element) return false;
-        return $this->def->validate($string, $config, $context);
-    }
-}
--- a/library/HTMLPurifier/AttrDef/CSS/Font.php
+++ b/library/HTMLPurifier/AttrDef/CSS/Font.php
@@ -148,3 +148,4 @@ class HTMLPurifier_AttrDef_CSS_Font extends HTMLPurifier_AttrDef
    
 }

+?>
--- a/library/HTMLPurifier/AttrDef/CSS/FontFamily.php
+++ b/library/HTMLPurifier/AttrDef/CSS/FontFamily.php
@@ -19,6 +19,7 @@ class HTMLPurifier_AttrDef_CSS_FontFamily extends HTMLPurifier_AttrDef
            'cursive' => true
        );
        
+        $string = $this->parseCDATA($string);
        // assume that no font names contain commas in them
        $fonts = explode(',', $string);
        $final = '';
@@ -37,51 +38,19 @@ class HTMLPurifier_AttrDef_CSS_FontFamily extends HTMLPurifier_AttrDef
                $quote = $font[0];
                if ($font[$length - 1] !== $quote) continue;
                $font = substr($font, 1, $length - 2);
-                
-                $new_font = '';
-                for ($i = 0, $c = strlen($font); $i < $c; $i++) {
-                    if ($font[$i] === '\\') {
-                        $i++;
-                        if ($i >= $c) {
-                            $new_font .= '\\';
-                            break;
-                        }
-                        if (ctype_xdigit($font[$i])) {
-                            $code = $font[$i];
-                            for ($a = 1, $i++; $i < $c && $a < 6; $i++, $a++) {
-                                if (!ctype_xdigit($font[$i])) break;
-                                $code .= $font[$i];
-                            }
-                            // We have to be extremely careful when adding
-                            // new characters, to make sure we're not breaking
-                            // the encoding.
-                            $char = HTMLPurifier_Encoder::unichr(hexdec($code));
-                            if (HTMLPurifier_Encoder::cleanUTF8($char) === '') continue;
-                            $new_font .= $char;
-                            if ($i < $c && trim($font[$i]) !== '') $i--;
-                            continue;
-                        }
-                        if ($font[$i] === "\n") continue;
-                    }
-                    $new_font .= $font[$i];
-                }
-                
-                $font = $new_font;
            }
-            // $font is a pure representation of the font name
-            
-            if (ctype_alnum($font) && $font !== '') {
+            // process font
+            if (ctype_alnum($font)) {
                // very simple font, allow it in unharmed
                $final .= $font . ', ';
                continue;
            }
-            
-            // complicated font, requires quoting
-            
-            // armor single quotes and new lines
-            $font = str_replace("\\", "\\\\", $font);
-            $font = str_replace("'", "\\'", $font);
-            $final .= "'$font', ";
+            $nospace = str_replace(array(' ', '.', '!'), '', $font);
+            if (ctype_alnum($nospace)) {
+                // font with spaces in it
+                $final .= "'$font', ";
+                continue;
+            }
        }
        $final = rtrim($final, ', ');
        if ($final === '') return false;
@@ -90,3 +59,4 @@ class HTMLPurifier_AttrDef_CSS_FontFamily extends HTMLPurifier_AttrDef
    
 }

+?>
--- a/library/HTMLPurifier/AttrDef/CSS/Length.php
+++ b/library/HTMLPurifier/AttrDef/CSS/Length.php
@@ -1,7 +1,7 @@
 <?php

-require_once 'HTMLPurifier/Length.php';
-require_once 'HTMLPurifier/UnitConverter.php';
+require_once 'HTMLPurifier/AttrDef.php';
+require_once 'HTMLPurifier/AttrDef/CSS/Number.php';

 /**
 * Represents a Length as defined by CSS.
@@ -9,41 +9,48 @@ require_once 'HTMLPurifier/UnitConverter.php';
 class HTMLPurifier_AttrDef_CSS_Length extends HTMLPurifier_AttrDef
 {
    
-    var $min, $max;
+    /**
+     * Valid unit lookup table.
+     * @warning The code assumes all units are two characters long.  Be careful
+     *          if we have to change this behavior!
+     */
+    var $units = array('em' => true, 'ex' => true, 'px' => true, 'in' => true,
+         'cm' => true, 'mm' => true, 'pt' => true, 'pc' => true);
+    /**
+     * Instance of HTMLPurifier_AttrDef_Number to defer number validation to
+     */
+    var $number_def;
    
    /**
-     * @param HTMLPurifier_Length $max Minimum length, or null for no bound. String is also acceptable.
-     * @param HTMLPurifier_Length $max Maximum length, or null for no bound. String is also acceptable.
+     * @param $non_negative Bool indication whether or not negative values are
+     *                      allowed.
     */
-    function HTMLPurifier_AttrDef_CSS_Length($min = null, $max = null) {
-        $this->min = $min !== null ? HTMLPurifier_Length::make($min) : null;
-        $this->max = $max !== null ? HTMLPurifier_Length::make($max) : null;
+    function HTMLPurifier_AttrDef_CSS_Length($non_negative = false) {
+        $this->number_def = new HTMLPurifier_AttrDef_CSS_Number($non_negative);
    }
    
-    function validate($string, $config, $context) {
-        $string = $this->parseCDATA($string);
+    function validate($length, $config, &$context) {
        
-        // Optimizations
-        if ($string === '') return false;
-        if ($string === '0') return '0';
-        if (strlen($string) === 1) return false;
+        $length = $this->parseCDATA($length);
+        if ($length === '') return false;
+        if ($length === '0') return '0';
+        $strlen = strlen($length);
+        if ($strlen === 1) return false; // impossible!
        
-        $length = HTMLPurifier_Length::make($string);
-        if (!$length->isValid()) return false;
+        // we assume all units are two characters
+        $unit = substr($length, $strlen - 2);
+        if (!ctype_lower($unit)) $unit = strtolower($unit);
+        $number = substr($length, 0, $strlen - 2);
        
-        if ($this->min) {
-            $c = $length->compareTo($this->min);
-            if ($c === false) return false;
-            if ($c < 0) return false;
-        }
-        if ($this->max) {
-            $c = $length->compareTo($this->max);
-            if ($c === false) return false;
-            if ($c > 0) return false;
-        }
+        if (!isset($this->units[$unit])) return false;
+        
+        $number = $this->number_def->validate($number, $config, $context);
+        if ($number === false) return false;
+        
+        return $number . $unit;
        
-        return $length->toString();
    }
    
 }

+?>
--- a/library/HTMLPurifier/AttrDef/CSS/ListStyle.php
+++ b/library/HTMLPurifier/AttrDef/CSS/ListStyle.php
@@ -77,3 +77,4 @@ class HTMLPurifier_AttrDef_CSS_ListStyle extends HTMLPurifier_AttrDef
    
 }

+?>
--- a/library/HTMLPurifier/AttrDef/CSS/Multiple.php
+++ b/library/HTMLPurifier/AttrDef/CSS/Multiple.php
@@ -55,3 +55,4 @@ class HTMLPurifier_AttrDef_CSS_Multiple extends HTMLPurifier_AttrDef
    
 }

+?>
--- a/library/HTMLPurifier/AttrDef/CSS/Number.php
+++ b/library/HTMLPurifier/AttrDef/CSS/Number.php
@@ -18,11 +18,6 @@ class HTMLPurifier_AttrDef_CSS_Number extends HTMLPurifier_AttrDef
        $this->non_negative = $non_negative;
    }
    
-    /**
-     * @warning Some contexts do not pass $config, $context. These
-     *          variables should not be used without checking HTMLPurifier_Length.
-     *          This might not work properly in PHP4.
-     */
    function validate($number, $config, &$context) {
        
        $number = $this->parseCDATA($number);
@@ -63,3 +58,4 @@ class HTMLPurifier_AttrDef_CSS_Number extends HTMLPurifier_AttrDef
    
 }

+?>
--- a/library/HTMLPurifier/AttrDef/CSS/Percentage.php
+++ b/library/HTMLPurifier/AttrDef/CSS/Percentage.php
@@ -40,3 +40,4 @@ class HTMLPurifier_AttrDef_CSS_Percentage extends HTMLPurifier_AttrDef
    
 }

+?>
--- a/library/HTMLPurifier/AttrDef/CSS/TextDecoration.php
+++ b/library/HTMLPurifier/AttrDef/CSS/TextDecoration.php
@@ -15,13 +15,10 @@ class HTMLPurifier_AttrDef_CSS_TextDecoration extends HTMLPurifier_AttrDef
        static $allowed_values = array(
            'line-through' => true,
            'overline' => true,
-            'underline' => true,
+            'underline' => true
        );
        
        $string = strtolower($this->parseCDATA($string));
-        
-        if ($string === 'none') return $string;
-        
        $parts = explode(' ', $string);
        $final = '';
        foreach ($parts as $part) {
@@ -37,3 +34,4 @@ class HTMLPurifier_AttrDef_CSS_TextDecoration extends HTMLPurifier_AttrDef
    
 }

+?>
--- a/library/HTMLPurifier/AttrDef/CSS/URI.php
+++ b/library/HTMLPurifier/AttrDef/CSS/URI.php
@@ -15,7 +15,7 @@ class HTMLPurifier_AttrDef_CSS_URI extends HTMLPurifier_AttrDef_URI
 {
    
    function HTMLPurifier_AttrDef_CSS_URI() {
-        parent::HTMLPurifier_AttrDef_URI(true); // always embedded
+        $this->HTMLPurifier_AttrDef_URI(true); // always embedded
    }
    
    function validate($uri_string, $config, &$context) {
@@ -55,3 +55,4 @@ class HTMLPurifier_AttrDef_CSS_URI extends HTMLPurifier_AttrDef_URI
    
 }

+?>
--- a/library/HTMLPurifier/AttrDef/Enum.php
+++ b/library/HTMLPurifier/AttrDef/Enum.php
@@ -63,3 +63,4 @@ class HTMLPurifier_AttrDef_Enum extends HTMLPurifier_AttrDef
    
 }

+?>
--- a/library/HTMLPurifier/AttrDef/HTML/Bool.php
+++ b/library/HTMLPurifier/AttrDef/HTML/Bool.php
@@ -27,3 +27,4 @@ class HTMLPurifier_AttrDef_HTML_Bool extends HTMLPurifier_AttrDef
    
 }

+?>
--- a/library/HTMLPurifier/AttrDef/HTML/Color.php
+++ b/library/HTMLPurifier/AttrDef/HTML/Color.php
@@ -32,3 +32,4 @@ class HTMLPurifier_AttrDef_HTML_Color extends HTMLPurifier_AttrDef
    
 }

+?>
--- a/library/HTMLPurifier/AttrDef/HTML/FrameTarget.php
+++ b/library/HTMLPurifier/AttrDef/HTML/FrameTarget.php
@@ -31,3 +31,4 @@ class HTMLPurifier_AttrDef_HTML_FrameTarget extends HTMLPurifier_AttrDef_Enum
    
 }

+?>
--- a/library/HTMLPurifier/AttrDef/HTML/ID.php
+++ b/library/HTMLPurifier/AttrDef/HTML/ID.php
@@ -118,3 +118,4 @@ class HTMLPurifier_AttrDef_HTML_ID extends HTMLPurifier_AttrDef
    
 }

+?>
--- a/library/HTMLPurifier/AttrDef/HTML/Length.php
+++ b/library/HTMLPurifier/AttrDef/HTML/Length.php
@@ -41,3 +41,4 @@ class HTMLPurifier_AttrDef_HTML_Length extends HTMLPurifier_AttrDef_HTML_Pixels
    
 }

+?>
--- a/library/HTMLPurifier/AttrDef/HTML/LinkTypes.php
+++ b/library/HTMLPurifier/AttrDef/HTML/LinkTypes.php
@@ -70,3 +70,4 @@ class HTMLPurifier_AttrDef_HTML_LinkTypes extends HTMLPurifier_AttrDef
    
 }

+?>
--- a/library/HTMLPurifier/AttrDef/HTML/MultiLength.php
+++ b/library/HTMLPurifier/AttrDef/HTML/MultiLength.php
@@ -41,3 +41,4 @@ class HTMLPurifier_AttrDef_HTML_MultiLength extends HTMLPurifier_AttrDef_HTML_Le
    
 }

+?>
--- a/library/HTMLPurifier/AttrDef/HTML/Nmtokens.php
+++ b/library/HTMLPurifier/AttrDef/HTML/Nmtokens.php
@@ -48,3 +48,4 @@ class HTMLPurifier_AttrDef_HTML_Nmtokens extends HTMLPurifier_AttrDef
    
 }

+?>
--- a/library/HTMLPurifier/AttrDef/HTML/Pixels.php
+++ b/library/HTMLPurifier/AttrDef/HTML/Pixels.php
@@ -8,12 +8,6 @@ require_once 'HTMLPurifier/AttrDef.php';
 class HTMLPurifier_AttrDef_HTML_Pixels extends HTMLPurifier_AttrDef
 {
    
-    var $max;
-    
-    function HTMLPurifier_AttrDef_HTML_Pixels($max = null) {
-        $this->max = $max;
-    }
-    
    function validate($string, $config, &$context) {
        
        $string = trim($string);
@@ -32,18 +26,12 @@ class HTMLPurifier_AttrDef_HTML_Pixels extends HTMLPurifier_AttrDef
        // crash operating systems, see <http://ha.ckers.org/imagecrash.html>
        // WARNING, above link WILL crash you if you're using Windows
        
-        if ($this->max !== null && $int > $this->max) return (string) $this->max;
+        if ($int > 1200) return '1200';
        
        return (string) $int;
        
    }
    
-    function make($string) {
-        if ($string === '') $max = null;
-        else $max = (int) $string;
-        $class = get_class($this);
-        return new $class($max);
-    }
-    
 }

+?>
--- a/library/HTMLPurifier/AttrDef/Integer.php
+++ b/library/HTMLPurifier/AttrDef/Integer.php
@@ -72,3 +72,4 @@ class HTMLPurifier_AttrDef_Integer extends HTMLPurifier_AttrDef
    
 }

+?>
--- a/library/HTMLPurifier/AttrDef/Lang.php
+++ b/library/HTMLPurifier/AttrDef/Lang.php
@@ -72,3 +72,4 @@ class HTMLPurifier_AttrDef_Lang extends HTMLPurifier_AttrDef
    
 }

+?>
--- a/library/HTMLPurifier/AttrDef/Switch.php
+++ b/library/HTMLPurifier/AttrDef/Switch.php
@@ -1,32 +0,0 @@
-<?php
-
-/**
- * Decorator that, depending on a token, switches between two definitions.
- */
-class HTMLPurifier_AttrDef_Switch
-{
-    
-    var $tag;
-    var $withTag, $withoutTag;
-    
-    /**
-     * @param string $tag Tag name to switch upon
-     * @param HTMLPurifier_AttrDef $with_tag Call if token matches tag
-     * @param HTMLPurifier_AttrDef $without_tag Call if token doesn't match, or there is no token
-     */
-    function HTMLPurifier_AttrDef_Switch($tag, $with_tag, $without_tag) {
-        $this->tag = $tag;
-        $this->withTag = $with_tag;
-        $this->withoutTag = $without_tag;
-    }
-    
-    function validate($string, $config, $context) {
-        $token = $context->get('CurrentToken', true);
-        if (!$token || $token->name !== $this->tag) {
-            return $this->withoutTag->validate($string, $config, $context);
-        } else {
-            return $this->withTag->validate($string, $config, $context);
-        }
-    }
-    
-}
--- a/library/HTMLPurifier/AttrDef/Text.php
+++ b/library/HTMLPurifier/AttrDef/Text.php
@@ -14,3 +14,4 @@ class HTMLPurifier_AttrDef_Text extends HTMLPurifier_AttrDef
    
 }

+?>
--- a/library/HTMLPurifier/AttrDef/URI.php
+++ b/library/HTMLPurifier/AttrDef/URI.php
@@ -1,66 +1,90 @@
 <?php

 require_once 'HTMLPurifier/AttrDef.php';
-require_once 'HTMLPurifier/URIParser.php';
 require_once 'HTMLPurifier/URIScheme.php';
 require_once 'HTMLPurifier/URISchemeRegistry.php';
 require_once 'HTMLPurifier/AttrDef/URI/Host.php';
 require_once 'HTMLPurifier/PercentEncoder.php';
-require_once 'HTMLPurifier/AttrDef/URI/Email.php';
-
-// special case filtering directives 

 HTMLPurifier_ConfigSchema::define(
-    'URI', 'Munge', null, 'string/null', '
-<p>
-    Munges all browsable (usually http, https and ftp)
-    absolute URI\'s into another URI, usually a URI redirection service.
-    This directive accepts a URI, formatted with a <code>%s</code> where 
-    the url-encoded original URI should be inserted (sample: 
-    <code>http://www.google.com/url?q=%s</code>).
-</p>
-<p>
-    Uses for this directive:
-</p>
-<ul>
-    <li>
-        Prevent PageRank leaks, while being fairly transparent 
-        to users (you may also want to add some client side JavaScript to 
-        override the text in the statusbar). <strong>Notice</strong>:
-        Many security experts believe that this form of protection does not deter spam-bots. 
-    </li>
-    <li>
-        Redirect users to a splash page telling them they are leaving your
-        website. While this is poor usability practice, it is often mandated
-        in corporate environments.
-    </li>
-</ul>
-<p>
-    This directive has been available since 1.3.0.
-</p>
-');
-
-// disabling directives
+    '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', 'Disable', false, 'bool', '
-<p>
-    Disables all URIs in all forms. Not sure why you\'d want to do that 
-    (after all, the Internet\'s founded on the notion of a hyperlink). 
-    This directive has been available since 1.3.0.
-</p>
-');
+    '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.'
+);
+
+HTMLPurifier_ConfigSchema::define(
+    'URI', 'DisableExternalResources', false, 'bool',
+    'Disables the embedding of external resources, preventing users from '.
+    'embedding things like images from other hosts. This prevents '.
+    'access tracking (good for email viewers), bandwidth leeching, '.
+    'cross-site request forging, goatse.cx posting, and '.
+    'other nasties, but also results in '.
+    'a loss of end-user functionality (they can\'t directly post a pic '.
+    'they posted from Flickr anymore). Use it if you don\'t have a '.
+    'robust user-content moderation team. This directive has been '.
+    'available since 1.3.0.'
+);
+
+HTMLPurifier_ConfigSchema::define(
+    'URI', 'DisableResources', false, 'bool',
+    'Disables embedding resources, essentially meaning no pictures. You can '.
+    'still link to them though. See %URI.DisableExternalResources for why '.
+    'this might be a good idea. This directive has been available since 1.3.0.'
+);
+
+HTMLPurifier_ConfigSchema::define(
+    'URI', 'Munge', null, 'string/null',
+    'Munges all browsable (usually http, https and ftp) URI\'s into some URL '.
+    'redirection service. Pass this directive a URI, with %s inserted where '.
+    'the url-encoded original URI should be inserted (sample: '.
+    '<code>http://www.google.com/url?q=%s</code>). '.
+    'This prevents PageRank leaks, while being as transparent as possible '.
+    'to users (you may also want to add some client side JavaScript to '.
+    'override the text in the statusbar). Warning: many security experts '.
+    'believe that this form of protection does not deter spam-bots. '.
+    'You can also use this directive to redirect users to a splash page '.
+    'telling them they are leaving your website. '.
+    'This directive has been available since 1.3.0.'
+);
+
+HTMLPurifier_ConfigSchema::define(
+    'URI', 'HostBlacklist', array(), 'list',
+    'List of strings that are forbidden in the host of any URI. Use it to '.
+    'kill domain names of spam, etc. Note that it will catch anything in '.
+    'the domain, so <tt>moo.com</tt> will catch <tt>moo.com.example.com</tt>. '.
+    'This directive has been available since 1.3.0.'
+);
+
+HTMLPurifier_ConfigSchema::define(
+    'URI', 'Disable', false, 'bool',
+    'Disables all URIs in all forms. Not sure why you\'d want to do that '.
+    '(after all, the Internet\'s founded on the notion of a hyperlink). '.
+    'This directive has been available since 1.3.0.'
+);
 HTMLPurifier_ConfigSchema::defineAlias('Attr', 'DisableURI', 'URI', 'Disable');

-HTMLPurifier_ConfigSchema::define(
-    'URI', 'DisableResources', false, 'bool', '
-<p>
-    Disables embedding resources, essentially meaning no pictures. You can 
-    still link to them though. See %URI.DisableExternalResources for why 
-    this might be a good idea. This directive has been available since 1.3.0.
-</p>
-');
-
 /**
 * Validates a URI as defined by RFC 3986.
 * @note Scheme-specific mechanics deferred to HTMLPurifier_URIScheme
@@ -68,73 +92,214 @@ HTMLPurifier_ConfigSchema::define(
 class HTMLPurifier_AttrDef_URI extends HTMLPurifier_AttrDef
 {
    
-    var $parser;
-    var $embedsResource;
+    var $host;
+    var $embeds_resource;
    
    /**
     * @param $embeds_resource_resource Does the URI here result in an extra HTTP request?
     */
    function HTMLPurifier_AttrDef_URI($embeds_resource = false) {
-        $this->parser = new HTMLPurifier_URIParser();
-        $this->embedsResource = (bool) $embeds_resource;
+        $this->host = new HTMLPurifier_AttrDef_URI_Host();
+        $this->embeds_resource = (bool) $embeds_resource;
    }
    
    function validate($uri, $config, &$context) {
        
+        static $PercentEncoder = null;
+        if ($PercentEncoder === null) $PercentEncoder = new HTMLPurifier_PercentEncoder();
+        
+        // We'll write stack-based parsers later, for now, use regexps to
+        // get things working as fast as possible (irony)
+        
        if ($config->get('URI', 'Disable')) return false;
        
+        // parse as CDATA
        $uri = $this->parseCDATA($uri);
        
-        // parse the URI
-        $uri = $this->parser->parse($uri);
-        if ($uri === false) return false;
+        // fix up percent-encoding
+        $uri = $PercentEncoder->normalize($uri);
        
-        // add embedded flag to context for validators
-        $context->register('EmbeddedURI', $this->embedsResource); 
+        // while it would be nice to use parse_url(), that's specifically
+        // for HTTP and thus won't work for our generic URI parsing
        
-        $ok = false;
-        do {
-            
-            // generic validation
-            $result = $uri->validate($config, $context);
-            if (!$result) break;
-            
-            // chained filtering
-            $uri_def =& $config->getDefinition('URI');
-            $result = $uri_def->filter($uri, $config, $context);
-            if (!$result) break;
-            
-            // scheme-specific validation 
-            $scheme_obj = $uri->getSchemeObj($config, $context);
-            if (!$scheme_obj) break;
-            if ($this->embedsResource && !$scheme_obj->browsable) break;
-            $result = $scheme_obj->validate($uri, $config, $context);
-            if (!$result) break;
-            
-            // survived gauntlet
-            $ok = true;
-            
-        } while (false);
+        // according to the RFC... (but this cuts corners, i.e. non-validating)
+        $r_URI = '!'.
+            '(([^:/?#<>\'"]+):)?'. // 2. Scheme
+            '(//([^/?#<>\'"]*))?'. // 4. Authority
+            '([^?#<>\'"]*)'.       // 5. Path
+            '(\?([^#<>\'"]*))?'.   // 7. Query
+            '(#([^<>\'"]*))?'.     // 8. Fragment
+            '!';
        
-        $context->destroy('EmbeddedURI');
-        if (!$ok) return false;
+        $matches = array();
+        $result = preg_match($r_URI, $uri, $matches);
        
-        // back to string
-        $result = $uri->toString();
+        if (!$result) return false; // invalid URI
        
-        // munge entire URI if necessary
-        if (
-            !is_null($uri->host) && // indicator for authority
-            !empty($scheme_obj->browsable) &&
-            !is_null($munge = $config->get('URI', 'Munge'))
-        ) {
-            $result = str_replace('%s', rawurlencode($result), $munge);
+        // seperate out parts
+        $scheme     = !empty($matches[1]) ? $matches[2] : null;
+        $authority  = !empty($matches[3]) ? $matches[4] : null;
+        $path       = $matches[5]; // always present, can be empty
+        $query      = !empty($matches[6]) ? $matches[7] : null;
+        $fragment   = !empty($matches[8]) ? $matches[9] : null;
+        
+        
+        
+        $registry =& HTMLPurifier_URISchemeRegistry::instance();
+        if ($scheme !== null) {
+            // no need to validate the scheme's fmt since we do that when we
+            // retrieve the specific scheme object from the registry
+            $scheme = ctype_lower($scheme) ? $scheme : strtolower($scheme);
+            $scheme_obj = $registry->getScheme($scheme, $config, $context);
+            if (!$scheme_obj) return false; // invalid scheme, clean it out
+        } else {
+            $scheme_obj = $registry->getScheme(
+                $config->get('URI', 'DefaultScheme'), $config, $context
+            );
+        }
+        
+        // something funky weird happened in the registry, abort!
+        if (!$scheme_obj) {
+            trigger_error(
+                'Default scheme object "' . $config->get('URI', 'DefaultScheme') . '" was not readable',
+                E_USER_WARNING
+            );
+            return false;
+        }
+        
+        // the URI we're processing embeds_resource a resource in the page, but the URI
+        // it references cannot be located
+        if ($this->embeds_resource && !$scheme_obj->browsable) {
+            return false;
+        }
+        
+        
+        if ($authority !== null) {
+            
+            // remove URI if it's absolute and we disabled externals or
+            // if it's absolute and embedded and we disabled external resources
+            unset($our_host);
+            if (
+                $config->get('URI', 'DisableExternal') ||
+                (
+                    $config->get('URI', 'DisableExternalResources') &&
+                    $this->embeds_resource
+                )
+            ) {
+                $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 []
+            $pct_encoded = "%$HEXDIG$HEXDIG";
+            $r_userinfo = "(?:[$unreserved$sub_delims:]|$pct_encoded)*";
+            $r_authority = "/^(($r_userinfo)@)?(\[[^\]]+\]|[^:]*)(:(\d*))?/";
+            $matches = array();
+            preg_match($r_authority, $authority, $matches);
+            // overloads regexp!
+            $userinfo   = !empty($matches[1]) ? $matches[2] : null;
+            $host       = !empty($matches[3]) ? $matches[3] : null;
+            $port       = !empty($matches[4]) ? $matches[5] : null;
+            
+            // validate port
+            if ($port !== null) {
+                $port = (int) $port;
+                if ($port < 1 || $port > 65535) $port = null;
+            }
+            
+            $host = $this->host->validate($host, $config, $context);
+            if ($host === false) $host = null;
+            
+            if ($this->checkBlacklist($host, $config, $context)) return false;
+            
+            // more lenient absolute checking
+            if (isset($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 {
+            $port = $host = $userinfo = null;
+        }
+        
+        
+        // query and fragment are quite simple in terms of definition:
+        // *( pchar / "/" / "?" ), so define their validation routines
+        // when we start fixing percent encoding
+        
+        
+        
+        // path gets to be validated against a hodge-podge of rules depending
+        // on the status of authority and scheme, but it's not that important,
+        // esp. since it won't be applicable to everyone
+        
+        
+        
+        // okay, now we defer execution to the subobject for more processing
+        // note that $fragment is omitted
+        list($userinfo, $host, $port, $path, $query) = 
+            $scheme_obj->validateComponents(
+                $userinfo, $host, $port, $path, $query, $config, $context
+            );
+        
+        
+        // reconstruct authority
+        $authority = null;
+        if (!is_null($userinfo) || !is_null($host) || !is_null($port)) {
+            $authority = '';
+            if($userinfo !== null) $authority .= $userinfo . '@';
+            $authority .= $host;
+            if($port !== null) $authority .= ':' . $port;
+        }
+        
+        // reconstruct the result
+        $result = '';
+        if ($scheme !== null) $result .= "$scheme:";
+        if ($authority !== null) $result .= "//$authority";
+        $result .= $path;
+        if ($query !== null) $result .= "?$query";
+        if ($fragment !== null) $result .= "#$fragment";
+        
+        // munge if necessary
+        $munge = $config->get('URI', 'Munge');
+        if (!empty($scheme_obj->browsable) && $munge !== null) {
+            if ($authority !== null) {
+                $result = str_replace('%s', rawurlencode($result), $munge);
+            }
        }
        
        return $result;
        
    }
    
+    /**
+     * Checks a host against an array blacklist
+     * @param $host Host to check
+     * @param $config HTMLPurifier_Config instance
+     * @param $context HTMLPurifier_Context instance
+     * @return bool Is spam?
+     */
+    function checkBlacklist($host, &$config, &$context) {
+        $blacklist = $config->get('URI', 'HostBlacklist');
+        if (!empty($blacklist)) {
+            foreach($blacklist as $blacklisted_host_fragment) {
+                if (strpos($host, $blacklisted_host_fragment) !== false) {
+                    return true;
+                }
+            }
+        }
+        return false;
+    }
+    
 }

-
+?>
--- a/library/HTMLPurifier/AttrDef/URI/Email.php
+++ b/library/HTMLPurifier/AttrDef/URI/Email.php
@@ -14,5 +14,4 @@ class HTMLPurifier_AttrDef_URI_Email extends HTMLPurifier_AttrDef
    
 }

-// sub-implementations
-require_once 'HTMLPurifier/AttrDef/URI/Email/SimpleCheck.php';
+?>
--- a/library/HTMLPurifier/AttrDef/URI/Email/SimpleCheck.php
+++ b/library/HTMLPurifier/AttrDef/URI/Email/SimpleCheck.php
@@ -20,3 +20,4 @@ class HTMLPurifier_AttrDef_URI_Email_SimpleCheck extends HTMLPurifier_AttrDef_UR
    
 }

+?>
--- a/library/HTMLPurifier/AttrDef/URI/Host.php
+++ b/library/HTMLPurifier/AttrDef/URI/Host.php
@@ -40,26 +40,15 @@ class HTMLPurifier_AttrDef_URI_Host extends HTMLPurifier_AttrDef
        $ipv4 = $this->ipv4->validate($string, $config, $context);
        if ($ipv4 !== false) return $ipv4;
        
-        // A regular domain name.
+        // validate a domain name here, do filtering, etc etc etc
        
-        // This breaks I18N domain names, but we don't have proper IRI support,
-        // so force users to insert Punycode. If there's complaining we'll 
-        // try to fix things into an international friendly form.
-        
-        // The productions describing this are:
-        $a   = '[a-z]';     // alpha
-        $an  = '[a-z0-9]';  // alphanum
-        $and = '[a-z0-9-]'; // alphanum | "-"
-        // domainlabel = alphanum | alphanum *( alphanum | "-" ) alphanum
-        $domainlabel   = "$an($and*$an)?";
-        // toplabel    = alpha | alpha *( alphanum | "-" ) alphanum
-        $toplabel      = "$a($and*$an)?";
-        // hostname    = *( domainlabel "." ) toplabel [ "." ]
-        $match = preg_match("/^($domainlabel\.)*$toplabel\.?$/i", $string);
-        if (!$match) return false;
+        // We could use this, but it would break I18N domain names
+        //$match = preg_match('/^[a-z0-9][\w\-\.]*[a-z0-9]$/i', $string);
+        //if (!$match) return false;
        
        return $string;
    }
    
 }

+?>
--- a/library/HTMLPurifier/AttrDef/URI/IPv4.php
+++ b/library/HTMLPurifier/AttrDef/URI/IPv4.php
@@ -39,3 +39,4 @@ class HTMLPurifier_AttrDef_URI_IPv4 extends HTMLPurifier_AttrDef
    
 }

+?>
--- a/library/HTMLPurifier/AttrDef/URI/IPv6.php
+++ b/library/HTMLPurifier/AttrDef/URI/IPv6.php
@@ -98,3 +98,4 @@ class HTMLPurifier_AttrDef_URI_IPv6 extends HTMLPurifier_AttrDef_URI_IPv4
    
 }

+?>
--- a/library/HTMLPurifier/AttrTransform.php
+++ b/library/HTMLPurifier/AttrTransform.php
@@ -55,3 +55,4 @@ class HTMLPurifier_AttrTransform
    
 }

+?>
--- a/library/HTMLPurifier/AttrTransform/BdoDir.php
+++ b/library/HTMLPurifier/AttrTransform/BdoDir.php
@@ -28,3 +28,4 @@ class HTMLPurifier_AttrTransform_BdoDir extends HTMLPurifier_AttrTransform
    
 }

+?>
--- a/library/HTMLPurifier/AttrTransform/BgColor.php
+++ b/library/HTMLPurifier/AttrTransform/BgColor.php
@@ -23,3 +23,4 @@ extends HTMLPurifier_AttrTransform {
    
 }

+?>
--- a/library/HTMLPurifier/AttrTransform/BoolToCSS.php
+++ b/library/HTMLPurifier/AttrTransform/BoolToCSS.php
@@ -36,3 +36,4 @@ extends HTMLPurifier_AttrTransform {
    
 }

+?>
--- a/library/HTMLPurifier/AttrTransform/Border.php
+++ b/library/HTMLPurifier/AttrTransform/Border.php
@@ -17,3 +17,4 @@ class HTMLPurifier_AttrTransform_Border extends HTMLPurifier_AttrTransform {
    
 }

+?>
--- a/library/HTMLPurifier/AttrTransform/EnumToCSS.php
+++ b/library/HTMLPurifier/AttrTransform/EnumToCSS.php
@@ -57,3 +57,4 @@ class HTMLPurifier_AttrTransform_EnumToCSS extends HTMLPurifier_AttrTransform {
    
 }

+?>
--- a/library/HTMLPurifier/AttrTransform/ImgRequired.php
+++ b/library/HTMLPurifier/AttrTransform/ImgRequired.php
@@ -51,3 +51,4 @@ class HTMLPurifier_AttrTransform_ImgRequired extends HTMLPurifier_AttrTransform
    
 }

+?>
--- a/library/HTMLPurifier/AttrTransform/ImgSpace.php
+++ b/library/HTMLPurifier/AttrTransform/ImgSpace.php
@@ -44,3 +44,4 @@ extends HTMLPurifier_AttrTransform {
    
 }

+?>
--- a/library/HTMLPurifier/AttrTransform/Lang.php
+++ b/library/HTMLPurifier/AttrTransform/Lang.php
@@ -27,3 +27,4 @@ class HTMLPurifier_AttrTransform_Lang extends HTMLPurifier_AttrTransform
    
 }

+?>
--- a/library/HTMLPurifier/AttrTransform/Length.php
+++ b/library/HTMLPurifier/AttrTransform/Length.php
@@ -26,3 +26,4 @@ class HTMLPurifier_AttrTransform_Length extends HTMLPurifier_AttrTransform
    
 }

+?>
--- a/library/HTMLPurifier/AttrTransform/Name.php
+++ b/library/HTMLPurifier/AttrTransform/Name.php
@@ -18,3 +18,4 @@ class HTMLPurifier_AttrTransform_Name extends HTMLPurifier_AttrTransform
    
 }

+?>
--- a/library/HTMLPurifier/AttrTypes.php
+++ b/library/HTMLPurifier/AttrTypes.php
@@ -44,9 +44,6 @@ class HTMLPurifier_AttrTypes
        $this->info['LanguageCode'] = new HTMLPurifier_AttrDef_Lang();
        $this->info['Color']    = new HTMLPurifier_AttrDef_HTML_Color();
        
-        // unimplemented aliases
-        $this->info['ContentType'] = new HTMLPurifier_AttrDef_Text();
-        
        // number is really a positive integer (one or more digits)
        // FIXME: ^^ not always, see start and value of list items
        $this->info['Number']   = new HTMLPurifier_AttrDef_Integer(false, false, true);
@@ -82,4 +79,4 @@ class HTMLPurifier_AttrTypes
    }
 }

-
+?>
--- a/library/HTMLPurifier/AttrValidator.php
+++ b/library/HTMLPurifier/AttrValidator.php
@@ -1,60 +1,32 @@
 <?php

-/**
- * Validates the attributes of a token. Doesn't manage required attributes
- * very well. The only reason we factored this out was because RemoveForeignElements
- * also needed it besides ValidateAttributes.
- */
 class HTMLPurifier_AttrValidator
 {
    
-    /**
-     * Validates the attributes of a token, returning a modified token
-     * that has valid tokens
-     * @param $token Reference to token to validate. We require a reference
-     *     because the operation this class performs on the token are
-     *     not atomic, so the context CurrentToken to be updated
-     *     throughout
-     * @param $config Instance of HTMLPurifier_Config
-     * @param $context Instance of HTMLPurifier_Context
-     */
-    function validateToken(&$token, &$config, &$context) {
+    
+    function validateToken($token, &$config, &$context) {
            
        $definition = $config->getHTMLDefinition();
-        $e =& $context->get('ErrorCollector', true);
-        
-        // initialize IDAccumulator if necessary
-        $ok =& $context->get('IDAccumulator', true);
-        if (!$ok) {
-            $id_accumulator = HTMLPurifier_IDAccumulator::build($config, $context);
-            $context->register('IDAccumulator', $id_accumulator);
-        }
-        
-        // initialize CurrentToken if necessary
-        $current_token =& $context->get('CurrentToken', true);
-        if (!$current_token) $context->register('CurrentToken', $token);
-        
-        if ($token->type !== 'start' && $token->type !== 'empty') return $token;
        
        // create alias to global definition array, see also $defs
        // DEFINITION CALL
        $d_defs = $definition->info_global_attr;
        
-        // don't update token until the very end, to ensure an atomic update
+        // copy out attributes for easy manipulation
        $attr = $token->attr;
        
        // do global transformations (pre)
        // nothing currently utilizes this
        foreach ($definition->info_attr_transform_pre as $transform) {
-            $attr = $transform->transform($o = $attr, $config, $context);
-            if ($e && ($attr != $o)) $e->send(E_NOTICE, 'AttrValidator: Attributes transformed', $o, $attr);
+            $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;">
-        foreach ($definition->info[$token->name]->attr_transform_pre as $transform) {
-            $attr = $transform->transform($o = $attr, $config, $context);
-            if ($e && ($attr != $o)) $e->send(E_NOTICE, 'AttrValidator: Attributes transformed', $o, $attr);
+        foreach ($definition->info[$token->name]->attr_transform_pre
+            as $transform
+        ) {
+            $attr = $transform->transform($attr, $config, $context);
        }
        
        // create alias to this element's attribute definition array, see
@@ -62,9 +34,6 @@ class HTMLPurifier_AttrValidator
        // DEFINITION CALL
        $defs = $definition->info[$token->name]->attr;
        
-        $attr_key = false;
-        $context->register('CurrentAttr', $attr_key);
-        
        // iterate through all the attribute keypairs
        // Watch out for name collisions: $key has previously been used
        foreach ($attr as $attr_key => $value) {
@@ -98,17 +67,9 @@ class HTMLPurifier_AttrValidator
            
            // put the results into effect
            if ($result === false || $result === null) {
-                // this is a generic error message that should replaced
-                // with more specific ones when possible
-                if ($e) $e->send(E_ERROR, 'AttrValidator: Attribute removed');
-                
                // remove the attribute
                unset($attr[$attr_key]);
            } elseif (is_string($result)) {
-                // generally, if a substitution is happening, there
-                // was some sort of implicit correction going on. We'll
-                // delegate it to the attribute classes to say exactly what.
-                
                // simple substitution
                $attr[$attr_key] = $result;
            }
@@ -120,29 +81,25 @@ class HTMLPurifier_AttrValidator
            // others would prepend themselves).
        }
        
-        $context->destroy('CurrentAttr');
-        
        // post transforms
        
-        // global (error reporting untested)
+        // ex. <x lang="fr"> to <x lang="fr" xml:lang="fr">
        foreach ($definition->info_attr_transform_post as $transform) {
-            $attr = $transform->transform($o = $attr, $config, $context);
-            if ($e && ($attr != $o)) $e->send(E_NOTICE, 'AttrValidator: Attributes transformed', $o, $attr);
+            $attr = $transform->transform($attr, $config, $context);
        }
        
-        // local (error reporting untested)
+        // ex. <bdo> to <bdo dir="ltr">
        foreach ($definition->info[$token->name]->attr_transform_post as $transform) {
-            $attr = $transform->transform($o = $attr, $config, $context);
-            if ($e && ($attr != $o)) $e->send(E_NOTICE, 'AttrValidator: Attributes transformed', $o, $attr);
+            $attr = $transform->transform($attr, $config, $context);
        }
        
+        // commit changes
        $token->attr = $attr;
-        
-        // destroy CurrentToken if we made it ourselves
-        if (!$current_token) $context->destroy('CurrentToken');
+        return $token;
        
    }
    
    
 }

+?>
--- a/library/HTMLPurifier/CSSDefinition.php
+++ b/library/HTMLPurifier/CSSDefinition.php
@@ -7,7 +7,6 @@ require_once 'HTMLPurifier/AttrDef/CSS/BackgroundPosition.php';
 require_once 'HTMLPurifier/AttrDef/CSS/Border.php';
 require_once 'HTMLPurifier/AttrDef/CSS/Color.php';
 require_once 'HTMLPurifier/AttrDef/CSS/Composite.php';
-require_once 'HTMLPurifier/AttrDef/CSS/DenyElementDecorator.php';
 require_once 'HTMLPurifier/AttrDef/CSS/Font.php';
 require_once 'HTMLPurifier/AttrDef/CSS/FontFamily.php';
 require_once 'HTMLPurifier/AttrDef/CSS/Length.php';
@@ -17,7 +16,6 @@ require_once 'HTMLPurifier/AttrDef/CSS/Percentage.php';
 require_once 'HTMLPurifier/AttrDef/CSS/TextDecoration.php';
 require_once 'HTMLPurifier/AttrDef/CSS/URI.php';
 require_once 'HTMLPurifier/AttrDef/Enum.php';
-require_once 'HTMLPurifier/AttrDef/Switch.php';

 HTMLPurifier_ConfigSchema::define(
    'CSS', 'DefinitionRev', 1, 'int', '
@@ -28,20 +26,6 @@ HTMLPurifier_ConfigSchema::define(
 </p>
 ');

-HTMLPurifier_ConfigSchema::define(
-    'CSS', 'MaxImgLength', '1200px', 'string/null', '
-<p>
- This parameter sets the maximum allowed length on <code>img</code> tags,
- effectively the <code>width</code> and <code>height</code> properties.
- Only absolute units of measurement (in, pt, pc, mm, cm) and pixels (px) are allowed. This is
- in place to prevent imagecrash attacks, disable with null at your own risk.
- This directive is similar to %HTML.MaxImgLength, and both should be
- concurrently edited, although there are
- subtle differences in the input format (the CSS max is a number with
- a unit).
-</p>
-');
-
 /**
 * Defines allowed CSS attributes and what their values are.
 * @see HTMLPurifier_HTMLDefinition
@@ -132,7 +116,7 @@ class HTMLPurifier_CSSDefinition extends HTMLPurifier_Definition
        $this->info['border-left-width'] = 
        $this->info['border-right-width'] = new HTMLPurifier_AttrDef_CSS_Composite(array(
            new HTMLPurifier_AttrDef_Enum(array('thin', 'medium', 'thick')),
-            new HTMLPurifier_AttrDef_CSS_Length('0') //disallow negative
+            new HTMLPurifier_AttrDef_CSS_Length(true) //disallow negative
        ));
        
        $this->info['border-width'] = new HTMLPurifier_AttrDef_CSS_Multiple($border_width);
@@ -158,7 +142,7 @@ class HTMLPurifier_CSSDefinition extends HTMLPurifier_Definition
        $this->info['line-height'] = new HTMLPurifier_AttrDef_CSS_Composite(array(
            new HTMLPurifier_AttrDef_Enum(array('normal')),
            new HTMLPurifier_AttrDef_CSS_Number(true), // no negatives
-            new HTMLPurifier_AttrDef_CSS_Length('0'),
+            new HTMLPurifier_AttrDef_CSS_Length(true),
            new HTMLPurifier_AttrDef_CSS_Percentage(true)
        ));
        
@@ -180,7 +164,7 @@ class HTMLPurifier_CSSDefinition extends HTMLPurifier_Definition
        $this->info['padding-bottom'] = 
        $this->info['padding-left'] = 
        $this->info['padding-right'] = new HTMLPurifier_AttrDef_CSS_Composite(array(
-            new HTMLPurifier_AttrDef_CSS_Length('0'),
+            new HTMLPurifier_AttrDef_CSS_Length(true),
            new HTMLPurifier_AttrDef_CSS_Percentage(true)
        ));
        
@@ -191,25 +175,13 @@ class HTMLPurifier_CSSDefinition extends HTMLPurifier_Definition
            new HTMLPurifier_AttrDef_CSS_Percentage()
        ));
        
-        $trusted_wh = new HTMLPurifier_AttrDef_CSS_Composite(array(
-            new HTMLPurifier_AttrDef_CSS_Length('0'),
+        $this->info['width'] =
+        $this->info['height'] = 
+        new HTMLPurifier_AttrDef_CSS_Composite(array(
+            new HTMLPurifier_AttrDef_CSS_Length(true),
            new HTMLPurifier_AttrDef_CSS_Percentage(true),
            new HTMLPurifier_AttrDef_Enum(array('auto'))
        ));
-        $max = $config->get('CSS', 'MaxImgLength');
-        $this->info['width'] =
-        $this->info['height'] =
-            $max === null ?
-            $trusted_wh : 
-            new HTMLPurifier_AttrDef_Switch('img',
-                // For img tags:
-                new HTMLPurifier_AttrDef_CSS_Composite(array(
-                    new HTMLPurifier_AttrDef_CSS_Length('0', $max),
-                    new HTMLPurifier_AttrDef_Enum(array('auto'))
-                )),
-                // For everyone else:
-                $trusted_wh
-            );
        
        $this->info['text-decoration'] = new HTMLPurifier_AttrDef_CSS_TextDecoration();
        
@@ -232,7 +204,7 @@ class HTMLPurifier_CSSDefinition extends HTMLPurifier_Definition
        $this->info['border-right'] = new HTMLPurifier_AttrDef_CSS_Border($config);
        
        $this->info['border-collapse'] = new HTMLPurifier_AttrDef_Enum(array(
-            'collapse', 'separate'));
+            'collapse', 'seperate'));
        
        $this->info['caption-side'] = new HTMLPurifier_AttrDef_Enum(array(
            'top', 'bottom'));
@@ -247,8 +219,6 @@ class HTMLPurifier_CSSDefinition extends HTMLPurifier_Definition
            new HTMLPurifier_AttrDef_CSS_Percentage()
        ));
        
-        $this->info['border-spacing'] = new HTMLPurifier_AttrDef_CSS_Multiple(new HTMLPurifier_AttrDef_CSS_Length(), 2);
-        
        // partial support
        $this->info['white-space'] = new HTMLPurifier_AttrDef_Enum(array('nowrap'));
        
@@ -256,3 +226,4 @@ class HTMLPurifier_CSSDefinition extends HTMLPurifier_Definition
    
 }

+?>
--- a/library/HTMLPurifier/ChildDef.php
+++ b/library/HTMLPurifier/ChildDef.php
@@ -36,11 +36,6 @@ class HTMLPurifier_ChildDef
     */
    var $allow_empty;
    
-    /**
-     * Lookup array of all elements that this definition could possibly allow
-     */
-    var $elements = array();
-    
    /**
     * Validates nodes according to definition and returns modification.
     * 
@@ -57,4 +52,4 @@ class HTMLPurifier_ChildDef
    }
 }

-
+?>
--- a/library/HTMLPurifier/ChildDef/Chameleon.php
+++ b/library/HTMLPurifier/ChildDef/Chameleon.php
@@ -35,7 +35,6 @@ class HTMLPurifier_ChildDef_Chameleon extends HTMLPurifier_ChildDef
    function HTMLPurifier_ChildDef_Chameleon($inline, $block) {
        $this->inline = new HTMLPurifier_ChildDef_Optional($inline);
        $this->block  = new HTMLPurifier_ChildDef_Optional($block);
-        $this->elements = $this->block->elements;
    }
    
    function validateChildren($tokens_of_children, $config, &$context) {
@@ -49,3 +48,4 @@ class HTMLPurifier_ChildDef_Chameleon extends HTMLPurifier_ChildDef
    }
 }

+?>
--- a/library/HTMLPurifier/ChildDef/Custom.php
+++ b/library/HTMLPurifier/ChildDef/Custom.php
@@ -44,12 +44,6 @@ class HTMLPurifier_ChildDef_Custom extends HTMLPurifier_ChildDef
        // COMPLICATED! AND MIGHT BE BUGGY! I HAVE NO CLUE WHAT I'M
        // DOING! Seriously: if there's problems, please report them.
        
-        // collect all elements into the $elements array
-        preg_match_all("/$el/", $reg, $matches);
-        foreach ($matches[0] as $match) {
-            $this->elements[$match] = true;
-        }
-        
        // setup all elements as parentheticals with leading commas
        $reg = preg_replace("/$el/", '(,\\0)', $reg);
        
@@ -91,3 +85,4 @@ class HTMLPurifier_ChildDef_Custom extends HTMLPurifier_ChildDef
    }
 }

+?>
--- a/library/HTMLPurifier/ChildDef/Empty.php
+++ b/library/HTMLPurifier/ChildDef/Empty.php
@@ -19,3 +19,4 @@ class HTMLPurifier_ChildDef_Empty extends HTMLPurifier_ChildDef
    }
 }

+?>
--- a/library/HTMLPurifier/ChildDef/Optional.php
+++ b/library/HTMLPurifier/ChildDef/Optional.php
@@ -15,11 +15,9 @@ class HTMLPurifier_ChildDef_Optional extends HTMLPurifier_ChildDef_Required
    var $type = 'optional';
    function validateChildren($tokens_of_children, $config, &$context) {
        $result = parent::validateChildren($tokens_of_children, $config, $context);
-        if ($result === false) {
-            if (empty($tokens_of_children)) return true;
-            else return array();
-        }
+        if ($result === false) return array();
        return $result;
    }
 }

+?>
--- a/Show More
+++ b/Show More
Author	SHA1	Message	Date
Edward Z. Yang	42858ad594	Finish up with a few more files that didn't get updated. Hrmm.. git-svn-id: http://htmlpurifier.org/svnroot/htmlpurifier/branches/strict@1181 48356398-32a2-884e-a903-53898d9a118a	2007-06-21 00:53:09 +00:00
Edward Z. Yang	5ecb11f19a	Tack on missing basic smoketests. git-svn-id: http://htmlpurifier.org/svnroot/htmlpurifier/branches/strict@1180 48356398-32a2-884e-a903-53898d9a118a	2007-06-21 00:42:00 +00:00
Edward Z. Yang	0101311193	Release 2.0.0, merged in 1026 to HEAD. git-svn-id: http://htmlpurifier.org/svnroot/htmlpurifier/branches/strict@1179 48356398-32a2-884e-a903-53898d9a118a	2007-06-21 00:36:12 +00:00
Edward Z. Yang	c35eb3e95f	Release 1.6.1, merged in 931 to HEAD. git-svn-id: http://htmlpurifier.org/svnroot/htmlpurifier/branches/strict@1026 48356398-32a2-884e-a903-53898d9a118a	2007-05-05 20:49:49 +00:00
Edward Z. Yang	b829e76bbf	Release 1.6.0, merged in r875-930. git-svn-id: http://htmlpurifier.org/svnroot/htmlpurifier/branches/strict@931 48356398-32a2-884e-a903-53898d9a118a	2007-04-02 03:09:23 +00:00
Edward Z. Yang	e967680250	Really release 1.5.0. git-svn-id: http://htmlpurifier.org/svnroot/htmlpurifier/branches/strict@876 48356398-32a2-884e-a903-53898d9a118a	2007-03-24 02:19:11 +00:00
Edward Z. Yang	dd2fd06591	Release 1.5.0, merged in r688-867. - LanguageFactory::instance() declared static - HTMLModuleManagerTest pass by reference bug fixed, merge back into trunk scheduled git-svn-id: http://htmlpurifier.org/svnroot/htmlpurifier/branches/strict@869 48356398-32a2-884e-a903-53898d9a118a	2007-03-24 01:04:06 +00:00
Edward Z. Yang	cec7a1c087	Release 1.4.1, merged in 685-687. git-svn-id: http://htmlpurifier.org/svnroot/htmlpurifier/branches/strict@689 48356398-32a2-884e-a903-53898d9a118a	2007-01-21 21:54:03 +00:00
Edward Z. Yang	c2d3d5b859	Release 1.4.0. git-svn-id: http://htmlpurifier.org/svnroot/htmlpurifier/branches/strict@682 48356398-32a2-884e-a903-53898d9a118a	2007-01-21 17:45:33 +00:00
Edward Z. Yang	9a84e11f34	Merge in r657-674, prompted by near release of 1.4.0. git-svn-id: http://htmlpurifier.org/svnroot/htmlpurifier/branches/strict@675 48356398-32a2-884e-a903-53898d9a118a	2007-01-21 16:07:36 +00:00
Edward Z. Yang	37ea1673dd	Merge in r649-656, prompted by changing two of Encoder's functions to static. git-svn-id: http://htmlpurifier.org/svnroot/htmlpurifier/branches/strict@657 48356398-32a2-884e-a903-53898d9a118a	2007-01-19 02:28:53 +00:00
Edward Z. Yang	5395d8b4bd	Renamed remotely git-svn-id: http://htmlpurifier.org/svnroot/htmlpurifier/branches/strict@649 48356398-32a2-884e-a903-53898d9a118a	2007-01-16 22:03:54 +00:00
Edward Z. Yang	c980e76197	Moved remotely git-svn-id: http://htmlpurifier.org/svnroot/htmlpurifier/branches/trunk-strict@648 48356398-32a2-884e-a903-53898d9a118a	2007-01-16 22:03:00 +00:00
Edward Z. Yang	2bf912d528	Commit strict version of HTML Purifier. git-svn-id: http://htmlpurifier.org/svnroot/htmlpurifier/trunk-strict@647 48356398-32a2-884e-a903-53898d9a118a	2007-01-16 21:59:29 +00:00
@@ -1 +1 @@
 .1.5
 .0.0