1
0
mirror of https://github.com/ezyang/htmlpurifier.git synced 2025-08-05 05:37:49 +02:00

Compare commits

..

18 Commits

Author SHA1 Message Date
Edward Z. Yang
80c60bb9b5 Release 2.1.0, merged in 1255 to HEAD.
git-svn-id: http://htmlpurifier.org/svnroot/htmlpurifier/branches/strict@1368 48356398-32a2-884e-a903-53898d9a118a
2007-08-05 02:02:46 +00:00
Edward Z. Yang
503e76081b Revert to 2.0.1, it appears that the 2.1.0 merge was done improperly.
git-svn-id: http://htmlpurifier.org/svnroot/htmlpurifier/branches/strict@1367 48356398-32a2-884e-a903-53898d9a118a
2007-08-05 01:42:52 +00:00
Edward Z. Yang
678a593e62 Release 2.1.0, merged in 1313 to HEAD.
git-svn-id: http://htmlpurifier.org/svnroot/htmlpurifier/branches/strict@1352 48356398-32a2-884e-a903-53898d9a118a
2007-08-03 03:20:49 +00:00
Edward Z. Yang
495164e938 Release 2.0.1, merged in 1181 to HEAD.
git-svn-id: http://htmlpurifier.org/svnroot/htmlpurifier/branches/strict@1255 48356398-32a2-884e-a903-53898d9a118a
2007-06-27 14:30:45 +00:00
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
372 changed files with 7237 additions and 1924 deletions

View File

@@ -4,7 +4,7 @@
# Project related configuration options
#---------------------------------------------------------------------------
PROJECT_NAME = HTML Purifier
PROJECT_NUMBER = 2.0.0
PROJECT_NUMBER = 2.1.1
OUTPUT_DIRECTORY = "C:/Documents and Settings/Edward/My Documents/My Webs/htmlpurifier/docs/doxygen"
CREATE_SUBDIRS = NO
OUTPUT_LANGUAGE = English

64
INSTALL
View File

@@ -1,4 +1,3 @@
Install
How to install HTML Purifier
@@ -9,6 +8,8 @@ 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
HTML Purifier works in both PHP 4 and PHP 5, from PHP 4.3.2 and up. It has no
@@ -48,7 +49,7 @@ be standards compliant. HTML Purifier can deal with these doctypes:
* XHTML 1.0 Strict
* HTML 4.01 Transitional
* HTML 4.01 Strict
* XHTML 1.1 sans Ruby
* XHTML 1.1 (sans Ruby)
...and these character encodings:
@@ -69,6 +70,10 @@ the doctype from this code in your HTML documents:
For legacy codebases these declarations may be missing. If that is the case,
STOP, and read docs/enduser-utf8.html
You may currently be vulnerable to XSS and other security threats, and HTML
Purifier won't be able to fix that.
@@ -112,8 +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 workaround,
but please be cognizant of the issues the "solution" creates.
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).
@@ -126,6 +135,7 @@ XHTML output like this:
Other supported doctypes include:
* HTML 4.01 Strict
* HTML 4.01 Transitional
* XHTML 1.0 Strict
@@ -139,7 +149,9 @@ Other supported doctypes include:
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.
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.
@@ -156,13 +168,15 @@ 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, SLOW gives advice on what to do if HTML Purifier
is slowing down your application.
different though). Also, docs/enduser-slow.html gives advice on what to
do if HTML Purifier is slowing down your application.
6. Quick install
First, make sure library/HTMLPurifier/DefinitionCache/Serializer is
writable by the webserver (see Section 7: Caching below for details).
If your website is in UTF-8 and XHTML Transitional, use this code:
<?php
@@ -189,6 +203,36 @@ If your website is in a different encoding or doctype, use this code:
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.
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');

108
NEWS
View File

@@ -9,6 +9,112 @@ NEWS ( CHANGELOG and HISTORY ) HTMLPurifier
. Internal change
==========================
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
@@ -115,6 +221,8 @@ NEWS ( CHANGELOG and HISTORY ) HTMLPurifier
%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.

40
TODO
View File

@@ -1,4 +1,3 @@
TODO List
= KEY ====================
@@ -7,20 +6,13 @@ TODO List
? Maybe I'll Do It
==========================
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
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!
2.2 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
@@ -39,20 +31,17 @@ TODO List
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)
3.0 release [Beyond HTML]
# Legit token based CSS parsing (will require revamping almost every
AttrDef class)
# More control over allowed CSS properties (maybe modularize it in the
same fashion!)
# 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
# Formatters for plaintext
- Smileys
- 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
- Standardize token armor for all areas of processing
- 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
@@ -64,12 +53,11 @@ TODO List
- 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)
- WordPress (mostly written, needs beta-testing)
- phpBB
- eFiction
- more! (look for ones that use WYSIWYGs)
- Complete basic smoketests
@@ -78,18 +66,22 @@ Unknown release (on a scratch-an-itch basis)
? 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)
- Refactor loop tests: Lexer
- 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?)
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

View File

@@ -1 +1 @@
2.0.0
2.1.1

View File

@@ -1,7 +1,10 @@
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.
In version 2.1, HTML Purifier's URI validation and filtering handling
system has been revamped with a new, extensible URIFilter system. Also
notable features include preservation of emoticons in PHP5 with
%Core.AggressivelyFixLt, standalone and lite download versions,
transforming relative URIs to absolute URIs, Ruby in XHTML 1.1, a Phorum
mod, and UTF-8 font names. Notable bug-fixes include refinement of
the auto-paragraphing algorithm (no longer experimental), better XHTML
1.1 support and the removal of the contents of <style> elements. Version
2.1.1 amends a few bugs in some of newly introduced features, namely
running the standalone download version in PHP4 and %URI.MakeAbsolute.

BIN
art/100cases.png Normal file

Binary file not shown.

After

Width:  |  Height:  |  Size: 2.7 KiB

1
benchmarks/.htaccess Normal file
View File

@@ -0,0 +1 @@
Deny from all

View File

@@ -15,5 +15,3 @@ $context = new HTMLPurifier_Context();
for ($i = 0; $i < 10; $i++) {
$tokens = $lexer->tokenizeHTML($input, $config, $context);
}
?>

12
benchmarks/Trace.php Normal file
View File

@@ -0,0 +1,12 @@
<?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();

View File

@@ -18,10 +18,16 @@ 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();
@@ -37,4 +43,3 @@ if (php_sapi_name() != 'cli') {
echo 'Files generated successfully.';
}
?>

View File

@@ -7,4 +7,3 @@
set_include_path(dirname(__FILE__) . PATH_SEPARATOR . get_include_path() );
require_once 'ConfigDoc.php';
?>

View File

@@ -36,4 +36,3 @@ class ConfigDoc
}
?>

View File

@@ -36,6 +36,7 @@ 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(
@@ -59,4 +60,3 @@ class ConfigDoc_HTMLXSLTProcessor
}
?>

View File

@@ -23,4 +23,3 @@ class ConfigDoc_XMLSerializer
}
?>

View File

@@ -50,6 +50,12 @@ 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);
@@ -115,4 +121,3 @@ class ConfigDoc_XMLSerializer_ConfigSchema extends ConfigDoc_XMLSerializer
}
?>

View File

@@ -24,4 +24,3 @@ class ConfigDoc_XMLSerializer_Types extends ConfigDoc_XMLSerializer
}
?>

View File

@@ -72,8 +72,16 @@
<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 />
@@ -89,8 +97,20 @@
</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()" />

View File

@@ -11,8 +11,7 @@ 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 (?)
@@ -22,9 +21,6 @@ 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

View File

@@ -17,11 +17,6 @@
<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

View File

@@ -10,9 +10,7 @@ to be effective. Things to remember:
2. IDs: see enduser-id.html for more info
3. Links: document pending feature completion
Rudimentary blacklisting, we should also allow only relative URIs. We
need a doc to explain the stuff.
3. URIs: see enduser-uri-filter.html
4. CSS: document pending
Explain which CSS styles we blocked and why.

View File

@@ -16,11 +16,6 @@
<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>

View File

@@ -0,0 +1,201 @@
<?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>

View File

@@ -231,7 +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 pass filters and then fool the
this guess in order to slip XSS past 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>
@@ -567,10 +567,11 @@ 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://ppewww.physics.gla.ac.uk/~flavell/charset/form-i18n.html">
<a href="http://web.archive.org/web/20060427015200/ppewww.ph.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.</p>
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>
<h4 id="whyutf8-forms-urlencoded"><code>application/x-www-form-urlencoded</code></h4>

View File

@@ -20,4 +20,3 @@ $pure_html = $purifier->purify($html);
echo '<pre>' . htmlspecialchars($pure_html) . '</pre>';
?>

View File

@@ -40,6 +40,9 @@ 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>

View File

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

View File

@@ -2,7 +2,8 @@
Configuration Ideas
Here are some theoretical configuration ideas that we could implement some
time. Note the naming convention: %Namespace.Directive
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.
%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
@@ -22,8 +23,6 @@ time. Note the naming convention: %Namespace.Directive
%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

28
docs/ref-css-length.txt Normal file
View File

@@ -0,0 +1,28 @@
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).

View File

@@ -33,6 +33,9 @@ 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; }

View File

@@ -7,4 +7,3 @@
set_include_path(dirname(__FILE__) . PATH_SEPARATOR . get_include_path() );
require_once 'HTMLPurifier.php';
?>

View File

@@ -18,4 +18,3 @@ function HTMLPurifier($html, $config = null) {
return $purifier->purify($html, $config);
}
?>

View File

@@ -22,7 +22,7 @@
*/
/*
HTML Purifier 2.0.0 - Standards Compliant HTML Filtering
HTML Purifier 2.1.1 - Standards Compliant HTML Filtering
Copyright (C) 2006 Edward Z. Yang
This library is free software; you can redistribute it and/or
@@ -40,6 +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__));
// almost every class has an undocumented dependency to these, so make sure
// they get included
require_once 'HTMLPurifier/ConfigSchema.php'; // important
@@ -51,16 +54,9 @@ 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
@@ -81,7 +77,7 @@ This directive has been available since 2.0.0.
class HTMLPurifier
{
var $version = '2.0.0';
var $version = '2.1.1';
var $config;
var $filters;
@@ -139,15 +135,19 @@ 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->get('Core', 'Language'));
$language = $language_factory->create($config, $context);
$context->register('Locale', $language);
$error_collector = new HTMLPurifier_ErrorCollector();
$context->register('ErrorCollector', $language);
$error_collector = new HTMLPurifier_ErrorCollector($context);
$context->register('ErrorCollector', $error_collector);
}
$html = HTMLPurifier_Encoder::convertToUTF8($html, $config, $context);
@@ -199,13 +199,13 @@ class HTMLPurifier
/**
* Singleton for enforcing just one HTML Purifier in your system
*/
function &getInstance($prototype = null) {
static function &getInstance($prototype = null) {
static $htmlpurifier;
if (!$htmlpurifier || $prototype) {
if (is_a($prototype, 'HTMLPurifier')) {
if ($prototype instanceof HTMLPurifier) {
$htmlpurifier = $prototype;
} elseif ($prototype) {
$htmlpurifier = new HTMLPurifier(HTMLPurifier_Config::create($prototype));
$htmlpurifier = new HTMLPurifier($prototype);
} else {
$htmlpurifier = new HTMLPurifier();
}
@@ -216,4 +216,3 @@ class HTMLPurifier
}
?>

View File

@@ -127,4 +127,3 @@ class HTMLPurifier_AttrCollections
}
?>

View File

@@ -84,4 +84,3 @@ class HTMLPurifier_AttrDef
}
?>

View File

@@ -66,4 +66,3 @@ class HTMLPurifier_AttrDef_CSS extends HTMLPurifier_AttrDef
}
?>

View File

@@ -84,4 +84,3 @@ class HTMLPurifier_AttrDef_CSS_Background extends HTMLPurifier_AttrDef
}
?>

View File

@@ -127,4 +127,3 @@ class HTMLPurifier_AttrDef_CSS_BackgroundPosition extends HTMLPurifier_AttrDef
}
?>

View File

@@ -42,4 +42,3 @@ class HTMLPurifier_AttrDef_CSS_Border extends HTMLPurifier_AttrDef
}
?>

View File

@@ -98,4 +98,3 @@ class HTMLPurifier_AttrDef_CSS_Color extends HTMLPurifier_AttrDef
}
?>

View File

@@ -35,4 +35,3 @@ class HTMLPurifier_AttrDef_CSS_Composite extends HTMLPurifier_AttrDef
}
?>

View File

@@ -148,4 +148,3 @@ class HTMLPurifier_AttrDef_CSS_Font extends HTMLPurifier_AttrDef
}
?>

View File

@@ -38,19 +38,24 @@ class HTMLPurifier_AttrDef_CSS_FontFamily extends HTMLPurifier_AttrDef
$quote = $font[0];
if ($font[$length - 1] !== $quote) continue;
$font = substr($font, 1, $length - 2);
// double-backslash processing is buggy
$font = str_replace("\\$quote", $quote, $font); // de-escape quote
$font = str_replace("\\\n", "\n", $font); // de-escape newlines
}
// process font
// $font is a pure representation of the font name
if (ctype_alnum($font)) {
// very simple font, allow it in unharmed
$final .= $font . ', ';
continue;
}
$nospace = str_replace(array(' ', '.', '!'), '', $font);
if (ctype_alnum($nospace)) {
// font with spaces in it
// complicated font, requires quoting
// armor single quotes and new lines
$font = str_replace("'", "\\'", $font);
$font = str_replace("\n", "\\\n", $font);
$final .= "'$font', ";
continue;
}
}
$final = rtrim($final, ', ');
if ($final === '') return false;
@@ -59,4 +64,3 @@ class HTMLPurifier_AttrDef_CSS_FontFamily extends HTMLPurifier_AttrDef
}
?>

View File

@@ -53,4 +53,3 @@ class HTMLPurifier_AttrDef_CSS_Length extends HTMLPurifier_AttrDef
}
?>

View File

@@ -77,4 +77,3 @@ class HTMLPurifier_AttrDef_CSS_ListStyle extends HTMLPurifier_AttrDef
}
?>

View File

@@ -55,4 +55,3 @@ class HTMLPurifier_AttrDef_CSS_Multiple extends HTMLPurifier_AttrDef
}
?>

View File

@@ -58,4 +58,3 @@ class HTMLPurifier_AttrDef_CSS_Number extends HTMLPurifier_AttrDef
}
?>

View File

@@ -40,4 +40,3 @@ class HTMLPurifier_AttrDef_CSS_Percentage extends HTMLPurifier_AttrDef
}
?>

View File

@@ -34,4 +34,3 @@ class HTMLPurifier_AttrDef_CSS_TextDecoration extends HTMLPurifier_AttrDef
}
?>

View File

@@ -15,7 +15,7 @@ class HTMLPurifier_AttrDef_CSS_URI extends HTMLPurifier_AttrDef_URI
{
function HTMLPurifier_AttrDef_CSS_URI() {
$this->HTMLPurifier_AttrDef_URI(true); // always embedded
parent::HTMLPurifier_AttrDef_URI(true); // always embedded
}
function validate($uri_string, $config, &$context) {
@@ -55,4 +55,3 @@ class HTMLPurifier_AttrDef_CSS_URI extends HTMLPurifier_AttrDef_URI
}
?>

View File

@@ -63,4 +63,3 @@ class HTMLPurifier_AttrDef_Enum extends HTMLPurifier_AttrDef
}
?>

View File

@@ -27,4 +27,3 @@ class HTMLPurifier_AttrDef_HTML_Bool extends HTMLPurifier_AttrDef
}
?>

View File

@@ -32,4 +32,3 @@ class HTMLPurifier_AttrDef_HTML_Color extends HTMLPurifier_AttrDef
}
?>

View File

@@ -31,4 +31,3 @@ class HTMLPurifier_AttrDef_HTML_FrameTarget extends HTMLPurifier_AttrDef_Enum
}
?>

View File

@@ -118,4 +118,3 @@ class HTMLPurifier_AttrDef_HTML_ID extends HTMLPurifier_AttrDef
}
?>

View File

@@ -41,4 +41,3 @@ class HTMLPurifier_AttrDef_HTML_Length extends HTMLPurifier_AttrDef_HTML_Pixels
}
?>

View File

@@ -70,4 +70,3 @@ class HTMLPurifier_AttrDef_HTML_LinkTypes extends HTMLPurifier_AttrDef
}
?>

View File

@@ -41,4 +41,3 @@ class HTMLPurifier_AttrDef_HTML_MultiLength extends HTMLPurifier_AttrDef_HTML_Le
}
?>

View File

@@ -48,4 +48,3 @@ class HTMLPurifier_AttrDef_HTML_Nmtokens extends HTMLPurifier_AttrDef
}
?>

View File

@@ -34,4 +34,3 @@ class HTMLPurifier_AttrDef_HTML_Pixels extends HTMLPurifier_AttrDef
}
?>

View File

@@ -72,4 +72,3 @@ class HTMLPurifier_AttrDef_Integer extends HTMLPurifier_AttrDef
}
?>

View File

@@ -72,4 +72,3 @@ class HTMLPurifier_AttrDef_Lang extends HTMLPurifier_AttrDef
}
?>

View File

@@ -14,4 +14,3 @@ class HTMLPurifier_AttrDef_Text extends HTMLPurifier_AttrDef
}
?>

View File

@@ -1,90 +1,65 @@
<?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';
HTMLPurifier_ConfigSchema::define(
'URI', 'DefaultScheme', 'http', 'string',
'Defines through what scheme the output will be served, in order to '.
'select the proper object validator when no scheme information is present.'
);
// special case filtering directives
HTMLPurifier_ConfigSchema::define(
'URI', 'Host', null, 'string/null',
'Defines the domain name of the server, so we can determine whether or '.
'an absolute URI is from your website or not. Not strictly necessary, '.
'as users should be using relative URIs to reference resources on your '.
'website. It will, however, let you use absolute URIs to link to '.
'subdomains of the domain you post here: i.e. example.com will allow '.
'sub.example.com. However, higher up domains will still be excluded: '.
'if you set %URI.Host to sub.example.com, example.com will be blocked. '.
'This directive has been available since 1.2.0.'
);
'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
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.'
);
'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>
');
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
@@ -92,214 +67,83 @@ HTMLPurifier_ConfigSchema::defineAlias('Attr', 'DisableURI', 'URI', 'Disable');
class HTMLPurifier_AttrDef_URI extends HTMLPurifier_AttrDef
{
var $host;
var $embeds_resource;
var $parser, $percentEncoder;
var $embedsResource;
/**
* @param $embeds_resource_resource Does the URI here result in an extra HTTP request?
*/
function HTMLPurifier_AttrDef_URI($embeds_resource = false) {
$this->host = new HTMLPurifier_AttrDef_URI_Host();
$this->embeds_resource = (bool) $embeds_resource;
$this->parser = new HTMLPurifier_URIParser();
$this->percentEncoder = new HTMLPurifier_PercentEncoder();
$this->embedsResource = (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
// initial operations
$uri = $this->parseCDATA($uri);
$uri = $this->percentEncoder->normalize($uri);
// fix up percent-encoding
$uri = $PercentEncoder->normalize($uri);
// parse the URI
$uri = $this->parser->parse($uri);
if ($uri === false) return false;
// while it would be nice to use parse_url(), that's specifically
// for HTTP and thus won't work for our generic URI parsing
// add embedded flag to context for validators
$context->register('EmbeddedURI', $this->embedsResource);
// according to the RFC... (but this cuts corners, i.e. non-validating)
$r_URI = '!'.
'(([^:/?#<>\'"]+):)?'. // 2. Scheme
'(//([^/?#<>\'"]*))?'. // 4. Authority
'([^?#<>\'"]*)'. // 5. Path
'(\?([^#<>\'"]*))?'. // 7. Query
'(#([^<>\'"]*))?'. // 8. Fragment
'!';
$ok = false;
do {
$matches = array();
$result = preg_match($r_URI, $uri, $matches);
// generic validation
$result = $uri->validate($config, $context);
if (!$result) break;
if (!$result) return false; // invalid URI
// chained validation
$uri_def =& $config->getDefinition('URI');
$result = $uri_def->filter($uri, $config, $context);
if (!$result) break;
// 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;
// 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);
$registry =& HTMLPurifier_URISchemeRegistry::instance();
if ($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
);
$context->destroy('EmbeddedURI');
if (!$ok) return false;
// munge scheme off if necessary (this must be last)
if (!is_null($uri->scheme) && is_null($uri->host)) {
if ($uri_def->defaultScheme == $uri->scheme) {
$uri->scheme = null;
}
}
// something funky weird happened in the registry, abort!
if (!$scheme_obj) {
trigger_error(
'Default scheme object "' . $config->get('URI', 'DefaultScheme') . '" was not readable',
E_USER_WARNING
);
return false;
}
// back to string
$result = $uri->toString();
// the URI we're processing embeds_resource a resource in the page, but the URI
// it references cannot be located
if ($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);
// munge entire URI if necessary
if (
$config->get('URI', 'DisableExternal') ||
(
$config->get('URI', 'DisableExternalResources') &&
$this->embeds_resource
)
!is_null($uri->host) && // indicator for authority
!empty($scheme_obj->browsable) &&
!is_null($munge = $config->get('URI', 'Munge'))
) {
$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;
}
}
?>

View File

@@ -14,4 +14,3 @@ class HTMLPurifier_AttrDef_URI_Email extends HTMLPurifier_AttrDef
}
?>

View File

@@ -20,4 +20,3 @@ class HTMLPurifier_AttrDef_URI_Email_SimpleCheck extends HTMLPurifier_AttrDef_UR
}
?>

View File

@@ -51,4 +51,3 @@ class HTMLPurifier_AttrDef_URI_Host extends HTMLPurifier_AttrDef
}
?>

View File

@@ -39,4 +39,3 @@ class HTMLPurifier_AttrDef_URI_IPv4 extends HTMLPurifier_AttrDef
}
?>

View File

@@ -98,4 +98,3 @@ class HTMLPurifier_AttrDef_URI_IPv6 extends HTMLPurifier_AttrDef_URI_IPv4
}
?>

View File

@@ -55,4 +55,3 @@ class HTMLPurifier_AttrTransform
}
?>

View File

@@ -28,4 +28,3 @@ class HTMLPurifier_AttrTransform_BdoDir extends HTMLPurifier_AttrTransform
}
?>

View File

@@ -23,4 +23,3 @@ extends HTMLPurifier_AttrTransform {
}
?>

View File

@@ -36,4 +36,3 @@ extends HTMLPurifier_AttrTransform {
}
?>

View File

@@ -17,4 +17,3 @@ class HTMLPurifier_AttrTransform_Border extends HTMLPurifier_AttrTransform {
}
?>

View File

@@ -57,4 +57,3 @@ class HTMLPurifier_AttrTransform_EnumToCSS extends HTMLPurifier_AttrTransform {
}
?>

View File

@@ -51,4 +51,3 @@ class HTMLPurifier_AttrTransform_ImgRequired extends HTMLPurifier_AttrTransform
}
?>

View File

@@ -44,4 +44,3 @@ extends HTMLPurifier_AttrTransform {
}
?>

View File

@@ -27,4 +27,3 @@ class HTMLPurifier_AttrTransform_Lang extends HTMLPurifier_AttrTransform
}
?>

View File

@@ -26,4 +26,3 @@ class HTMLPurifier_AttrTransform_Length extends HTMLPurifier_AttrTransform
}
?>

View File

@@ -18,4 +18,3 @@ class HTMLPurifier_AttrTransform_Name extends HTMLPurifier_AttrTransform
}
?>

View File

@@ -79,4 +79,4 @@ class HTMLPurifier_AttrTypes
}
}
?>

View File

@@ -1,32 +1,53 @@
<?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
{
function validateToken($token, &$config, &$context) {
/**
* 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) {
$definition = $config->getHTMLDefinition();
$e =& $context->get('ErrorCollector', true);
// 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;
// copy out attributes for easy manipulation
$attr = $token->attr;
// reference attributes for easy manipulation
$attr =& $token->attr;
// do global transformations (pre)
// nothing currently utilizes this
foreach ($definition->info_attr_transform_pre as $transform) {
$attr = $transform->transform($attr, $config, $context);
$attr = $transform->transform($o = $attr, $config, $context);
if ($e && ($attr != $o)) $e->send(E_NOTICE, 'AttrValidator: Attributes transformed', $o, $attr);
}
// do local transformations only applicable to this element (pre)
// ex. <p align="right"> to <p style="text-align:right;">
foreach ($definition->info[$token->name]->attr_transform_pre
as $transform
) {
$attr = $transform->transform($attr, $config, $context);
foreach ($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);
}
// create alias to this element's attribute definition array, see
@@ -34,6 +55,9 @@ 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 => $value) {
@@ -67,9 +91,17 @@ class HTMLPurifier_AttrValidator
// put the results into effect
if ($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;
}
@@ -81,25 +113,27 @@ class HTMLPurifier_AttrValidator
// others would prepend themselves).
}
$context->destroy('CurrentAttr');
// post transforms
// ex. <x lang="fr"> to <x lang="fr" xml:lang="fr">
// global (error reporting untested)
foreach ($definition->info_attr_transform_post as $transform) {
$attr = $transform->transform($attr, $config, $context);
$attr = $transform->transform($o = $attr, $config, $context);
if ($e && ($attr != $o)) $e->send(E_NOTICE, 'AttrValidator: Attributes transformed', $o, $attr);
}
// ex. <bdo> to <bdo dir="ltr">
// local (error reporting untested)
foreach ($definition->info[$token->name]->attr_transform_post as $transform) {
$attr = $transform->transform($attr, $config, $context);
$attr = $transform->transform($o = $attr, $config, $context);
if ($e && ($attr != $o)) $e->send(E_NOTICE, 'AttrValidator: Attributes transformed', $o, $attr);
}
// commit changes
$token->attr = $attr;
return $token;
// destroy CurrentToken if we made it ourselves
if (!$current_token) $context->destroy('CurrentToken');
}
}
?>

View File

@@ -226,4 +226,3 @@ class HTMLPurifier_CSSDefinition extends HTMLPurifier_Definition
}
?>

View File

@@ -36,6 +36,11 @@ 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.
*
@@ -52,4 +57,4 @@ class HTMLPurifier_ChildDef
}
}
?>

View File

@@ -35,6 +35,7 @@ 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) {
@@ -48,4 +49,3 @@ class HTMLPurifier_ChildDef_Chameleon extends HTMLPurifier_ChildDef
}
}
?>

View File

@@ -44,6 +44,12 @@ 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);
@@ -85,4 +91,3 @@ class HTMLPurifier_ChildDef_Custom extends HTMLPurifier_ChildDef
}
}
?>

View File

@@ -19,4 +19,3 @@ class HTMLPurifier_ChildDef_Empty extends HTMLPurifier_ChildDef
}
}
?>

View File

@@ -20,4 +20,3 @@ class HTMLPurifier_ChildDef_Optional extends HTMLPurifier_ChildDef_Required
}
}
?>

View File

@@ -25,7 +25,7 @@ class HTMLPurifier_ChildDef_Required extends HTMLPurifier_ChildDef
$elements = array_flip($elements);
foreach ($elements as $i => $x) {
$elements[$i] = true;
if (empty($i)) unset($elements[$i]);
if (empty($i)) unset($elements[$i]); // remove blank
}
}
$this->elements = $elements;
@@ -109,4 +109,3 @@ class HTMLPurifier_ChildDef_Required extends HTMLPurifier_ChildDef
}
}
?>

View File

@@ -73,4 +73,3 @@ extends HTMLPurifier_ChildDef_Required
}
}
?>

View File

@@ -9,6 +9,8 @@ class HTMLPurifier_ChildDef_Table extends HTMLPurifier_ChildDef
{
var $allow_empty = false;
var $type = 'table';
var $elements = array('tr' => true, 'tbody' => true, 'thead' => true,
'tfoot' => true, 'caption' => true, 'colgroup' => true, 'col' => true);
function HTMLPurifier_ChildDef_Table() {}
function validateChildren($tokens_of_children, $config, &$context) {
if (empty($tokens_of_children)) return false;
@@ -139,4 +141,3 @@ class HTMLPurifier_ChildDef_Table extends HTMLPurifier_ChildDef
}
}
?>

View File

@@ -5,6 +5,7 @@ require_once 'HTMLPurifier/ConfigSchema.php';
// member variables
require_once 'HTMLPurifier/HTMLDefinition.php';
require_once 'HTMLPurifier/CSSDefinition.php';
require_once 'HTMLPurifier/URIDefinition.php';
require_once 'HTMLPurifier/Doctype.php';
require_once 'HTMLPurifier/DefinitionCacheFactory.php';
@@ -41,7 +42,7 @@ class HTMLPurifier_Config
/**
* HTML Purifier's version
*/
var $version = '2.0.0';
var $version = '2.1.1';
/**
* Two-level associative array of configuration directives
@@ -75,6 +76,11 @@ class HTMLPurifier_Config
*/
var $serials = array();
/**
* Serial for entire configuration object
*/
var $serial;
/**
* @param $definition HTMLPurifier_ConfigSchema that defines what directives
* are allowed.
@@ -93,15 +99,11 @@ class HTMLPurifier_Config
* or a string filename of an ini file.
* @return Configured HTMLPurifier_Config object
*/
function create($config) {
if (is_a($config, 'HTMLPurifier_Config')) {
// pass-through
return $config;
}
static function create($config) {
if ($config instanceof HTMLPurifier_Config) return $config;
$ret = HTMLPurifier_Config::createDefault();
if (is_string($config)) $ret->loadIni($config);
elseif (is_array($config)) $ret->loadArray($config);
if (isset($revision)) $ret->revision = $revision;
return $ret;
}
@@ -110,7 +112,7 @@ class HTMLPurifier_Config
* @static
* @return Default HTMLPurifier_Config object.
*/
function createDefault() {
static function createDefault() {
$definition =& HTMLPurifier_ConfigSchema::instance();
$config = new HTMLPurifier_Config($definition);
return $config;
@@ -155,15 +157,30 @@ class HTMLPurifier_Config
/**
* Returns a md5 signature of a segment of the configuration object
* that uniquely identifies that particular configuration
* @note Revision is handled specially and is removed from the batch
* before processing!
* @param $namespace Namespace to get serial for
*/
function getBatchSerial($namespace) {
if (empty($this->serials[$namespace])) {
$this->serials[$namespace] = md5(serialize($this->getBatch($namespace)));
$batch = $this->getBatch($namespace);
unset($batch['DefinitionRev']);
$this->serials[$namespace] = md5(serialize($batch));
}
return $this->serials[$namespace];
}
/**
* Returns a md5 signature for the entire configuration object
* that uniquely identifies that particular configuration
*/
function getSerial() {
if (empty($this->serial)) {
$this->serial = md5(serialize($this->getAll()));
}
return $this->serial;
}
/**
* Retrieves all directives, organized by namespace
*/
@@ -246,14 +263,16 @@ class HTMLPurifier_Config
* called before it's been setup, otherwise won't work.
*/
function &getHTMLDefinition($raw = false) {
return $this->getDefinition('HTML', $raw);
$def =& $this->getDefinition('HTML', $raw);
return $def; // prevent PHP 4.4.0 from complaining
}
/**
* Retrieves reference to the CSS definition
*/
function &getCSSDefinition($raw = false) {
return $this->getDefinition('CSS', $raw);
$def =& $this->getDefinition('CSS', $raw);
return $def;
}
/**
@@ -270,6 +289,7 @@ class HTMLPurifier_Config
if (!empty($this->definitions[$type])) {
if (!$this->definitions[$type]->setup) {
$this->definitions[$type]->setup($this);
$cache->set($this->definitions[$type], $this);
}
return $this->definitions[$type];
}
@@ -291,6 +311,8 @@ class HTMLPurifier_Config
$this->definitions[$type] = new HTMLPurifier_HTMLDefinition();
} elseif ($type == 'CSS') {
$this->definitions[$type] = new HTMLPurifier_CSSDefinition();
} elseif ($type == 'URI') {
$this->definitions[$type] = new HTMLPurifier_URIDefinition();
} else {
trigger_error("Definition of $type type not supported");
$false = false;
@@ -301,7 +323,7 @@ class HTMLPurifier_Config
if (is_null($this->get($type, 'DefinitionID'))) {
// fatally error out if definition ID not set
trigger_error("Cannot retrieve raw version without specifying %$type.DefinitionID", E_USER_ERROR);
$false = false;
$false = new HTMLPurifier_Error();
return $false;
}
return $this->definitions[$type];
@@ -336,25 +358,96 @@ class HTMLPurifier_Config
}
}
/**
* Returns a list of array(namespace, directive) for all directives
* that are allowed in a web-form context as per an allowed
* namespaces/directives list.
* @param $allowed List of allowed namespaces/directives
* @static
*/
static function getAllowedDirectivesForForm($allowed) {
$schema = HTMLPurifier_ConfigSchema::instance();
if ($allowed !== true) {
if (is_string($allowed)) $allowed = array($allowed);
$allowed_ns = array();
$allowed_directives = array();
$blacklisted_directives = array();
foreach ($allowed as $ns_or_directive) {
if (strpos($ns_or_directive, '.') !== false) {
// directive
if ($ns_or_directive[0] == '-') {
$blacklisted_directives[substr($ns_or_directive, 1)] = true;
} else {
$allowed_directives[$ns_or_directive] = true;
}
} else {
// namespace
$allowed_ns[$ns_or_directive] = true;
}
}
}
$ret = array();
foreach ($schema->info as $ns => $keypairs) {
foreach ($keypairs as $directive => $def) {
if ($allowed !== true) {
if (isset($blacklisted_directives["$ns.$directive"])) continue;
if (!isset($allowed_directives["$ns.$directive"]) && !isset($allowed_ns[$ns])) continue;
}
if ($def->class == 'alias') continue;
if ($directive == 'DefinitionID' || $directive == 'DefinitionRev') continue;
$ret[] = array($ns, $directive);
}
}
return $ret;
}
/**
* Loads configuration values from $_GET/$_POST that were posted
* via ConfigForm
* @param $array $_GET or $_POST array to import
* @param $index Index/name that the config variables are in
* @param $allowed List of allowed namespaces/directives
* @param $mq_fix Boolean whether or not to enable magic quotes fix
* @static
*/
function loadArrayFromForm($array, $index, $mq_fix = true) {
static function loadArrayFromForm($array, $index, $allowed = true, $mq_fix = true) {
$ret = HTMLPurifier_Config::prepareArrayFromForm($array, $index, $allowed, $mq_fix);
$config = HTMLPurifier_Config::create($ret);
return $config;
}
/**
* Merges in configuration values from $_GET/$_POST to object. NOT STATIC.
* @note Same parameters as loadArrayFromForm
*/
function mergeArrayFromForm($array, $index, $allowed = true, $mq_fix = true) {
$ret = HTMLPurifier_Config::prepareArrayFromForm($array, $index, $allowed, $mq_fix);
$this->loadArray($ret);
}
/**
* Prepares an array from a form into something usable for the more
* strict parts of HTMLPurifier_Config
* @static
*/
static function prepareArrayFromForm($array, $index, $allowed = true, $mq_fix = true) {
$array = (isset($array[$index]) && is_array($array[$index])) ? $array[$index] : array();
$mq = get_magic_quotes_gpc() && $mq_fix;
foreach ($array as $key => $value) {
if (!strncmp($key, 'Null_', 5) && !empty($value)) {
unset($array[substr($key, 5)]);
unset($array[$key]);
$allowed = HTMLPurifier_Config::getAllowedDirectivesForForm($allowed);
$ret = array();
foreach ($allowed as $key) {
list($ns, $directive) = $key;
$skey = "$ns.$directive";
if (!empty($array["Null_$skey"])) {
$ret[$ns][$directive] = null;
continue;
}
if ($mq) $array[$key] = stripslashes($value);
if (!isset($array[$skey])) continue;
$value = $mq ? stripslashes($array[$skey]) : $array[$skey];
$ret[$ns][$directive] = $value;
}
return @HTMLPurifier_Config::create($array);
return $ret;
}
/**
@@ -395,4 +488,4 @@ class HTMLPurifier_Config
}
?>

View File

@@ -7,4 +7,3 @@ class HTMLPurifier_ConfigDef {
var $class = false;
}
?>

View File

@@ -61,6 +61,12 @@ class HTMLPurifier_ConfigDef_Directive extends HTMLPurifier_ConfigDef
*/
var $aliases = array();
/**
* Advisory list of directive aliases, i.e. other directives that
* redirect here
*/
var $directiveAliases = array();
/**
* Adds a description to the array
*/
@@ -71,4 +77,3 @@ class HTMLPurifier_ConfigDef_Directive extends HTMLPurifier_ConfigDef
}
?>

View File

@@ -24,4 +24,3 @@ class HTMLPurifier_ConfigDef_DirectiveAlias extends HTMLPurifier_ConfigDef
}
}
?>

View File

@@ -20,4 +20,3 @@ class HTMLPurifier_ConfigDef_Namespace extends HTMLPurifier_ConfigDef {
}
?>

View File

@@ -6,6 +6,8 @@ require_once 'HTMLPurifier/ConfigDef/Namespace.php';
require_once 'HTMLPurifier/ConfigDef/Directive.php';
require_once 'HTMLPurifier/ConfigDef/DirectiveAlias.php';
if (!defined('HTMLPURIFIER_SCHEMA_STRICT')) define('HTMLPURIFIER_SCHEMA_STRICT', false);
/**
* Configuration definition, defines directives and their defaults.
* @note If you update this, please update Printer_ConfigForm
@@ -49,6 +51,8 @@ class HTMLPurifier_ConfigSchema {
var $types = array(
'string' => 'String',
'istring' => 'Case-insensitive string',
'text' => 'Text',
'itext' => 'Case-insensitive text',
'int' => 'Integer',
'float' => 'Float',
'bool' => 'Boolean',
@@ -67,6 +71,8 @@ class HTMLPurifier_ConfigSchema {
$this->defineNamespace('URI', 'Features regarding Uniform Resource Identifiers.');
$this->defineNamespace('HTML', 'Configuration regarding allowed HTML.');
$this->defineNamespace('CSS', 'Configuration regarding allowed CSS.');
$this->defineNamespace('AutoFormat', 'Configuration for activating auto-formatting functionality (also known as <code>Injector</code>s)');
$this->defineNamespace('AutoFormatParam', 'Configuration for customizing auto-formatting functionality');
$this->defineNamespace('Output', 'Configuration relating to the generation of (X)HTML.');
$this->defineNamespace('Cache', 'Configuration for DefinitionCache and related subclasses.');
$this->defineNamespace('Test', 'Developer testing configuration for our unit tests.');
@@ -76,7 +82,7 @@ class HTMLPurifier_ConfigSchema {
* Retrieves an instance of the application-wide configuration definition.
* @static
*/
function &instance($prototype = null) {
static function &instance($prototype = null) {
static $instance;
if ($prototype !== null) {
$instance = $prototype;
@@ -98,11 +104,11 @@ class HTMLPurifier_ConfigSchema {
* HTMLPurifier_DirectiveDef::$type for allowed values
* @param $description Description of directive for documentation
*/
function define(
$namespace, $name, $default, $type,
$description
) {
static function define($namespace, $name, $default, $type, $description) {
$def =& HTMLPurifier_ConfigSchema::instance();
// basic sanity checks
if (HTMLPURIFIER_SCHEMA_STRICT) {
if (!isset($def->info[$namespace])) {
trigger_error('Cannot define directive for undefined namespace',
E_USER_ERROR);
@@ -118,7 +124,10 @@ class HTMLPurifier_ConfigSchema {
E_USER_ERROR);
return;
}
}
if (isset($def->info[$namespace][$name])) {
// already defined
if (
$def->info[$namespace][$name]->type !== $type ||
$def->defaults[$namespace][$name] !== $default
@@ -127,12 +136,15 @@ class HTMLPurifier_ConfigSchema {
return;
}
} else {
// process modifiers
// needs defining
// process modifiers (OPTIMIZE!)
$type_values = explode('/', $type, 2);
$type = $type_values[0];
$modifier = isset($type_values[1]) ? $type_values[1] : false;
$allow_null = ($modifier === 'null');
if (HTMLPURIFIER_SCHEMA_STRICT) {
if (!isset($def->types[$type])) {
trigger_error('Invalid type for configuration directive',
E_USER_ERROR);
@@ -144,12 +156,15 @@ class HTMLPurifier_ConfigSchema {
E_USER_ERROR);
return;
}
}
$def->info[$namespace][$name] =
new HTMLPurifier_ConfigDef_Directive();
$def->info[$namespace][$name]->type = $type;
$def->info[$namespace][$name]->allow_null = $allow_null;
$def->defaults[$namespace][$name] = $default;
}
if (!HTMLPURIFIER_SCHEMA_STRICT) return;
$backtrace = debug_backtrace();
$file = $def->mungeFilename($backtrace[0]['file']);
$line = $backtrace[0]['line'];
@@ -162,8 +177,9 @@ class HTMLPurifier_ConfigSchema {
* @param $namespace Namespace's name
* @param $description Description of the namespace
*/
function defineNamespace($namespace, $description) {
static function defineNamespace($namespace, $description) {
$def =& HTMLPurifier_ConfigSchema::instance();
if (HTMLPURIFIER_SCHEMA_STRICT) {
if (isset($def->info[$namespace])) {
trigger_error('Cannot redefine namespace', E_USER_ERROR);
return;
@@ -178,6 +194,7 @@ class HTMLPurifier_ConfigSchema {
E_USER_ERROR);
return;
}
}
$def->info[$namespace] = array();
$def->info_namespace[$namespace] = new HTMLPurifier_ConfigDef_Namespace();
$def->info_namespace[$namespace]->description = $description;
@@ -195,14 +212,15 @@ class HTMLPurifier_ConfigSchema {
* @param $alias Name of aliased value
* @param $real Value aliased value will be converted into
*/
function defineValueAliases($namespace, $name, $aliases) {
static function defineValueAliases($namespace, $name, $aliases) {
$def =& HTMLPurifier_ConfigSchema::instance();
if (!isset($def->info[$namespace][$name])) {
if (HTMLPURIFIER_SCHEMA_STRICT && !isset($def->info[$namespace][$name])) {
trigger_error('Cannot set value alias for non-existant directive',
E_USER_ERROR);
return;
}
foreach ($aliases as $alias => $real) {
if (HTMLPURIFIER_SCHEMA_STRICT) {
if (!$def->info[$namespace][$name] !== true &&
!isset($def->info[$namespace][$name]->allowed[$real])
) {
@@ -215,6 +233,7 @@ class HTMLPurifier_ConfigSchema {
E_USER_ERROR);
return;
}
}
$def->info[$namespace][$name]->aliases[$alias] = $real;
}
}
@@ -226,16 +245,16 @@ class HTMLPurifier_ConfigSchema {
* @param $name Name of directive
* @param $allowed_values Arraylist of allowed values
*/
function defineAllowedValues($namespace, $name, $allowed_values) {
static function defineAllowedValues($namespace, $name, $allowed_values) {
$def =& HTMLPurifier_ConfigSchema::instance();
if (!isset($def->info[$namespace][$name])) {
if (HTMLPURIFIER_SCHEMA_STRICT && !isset($def->info[$namespace][$name])) {
trigger_error('Cannot define allowed values for undefined directive',
E_USER_ERROR);
return;
}
$directive =& $def->info[$namespace][$name];
$type = $directive->type;
if ($type != 'string' && $type != 'istring') {
if (HTMLPURIFIER_SCHEMA_STRICT && $type != 'string' && $type != 'istring') {
trigger_error('Cannot define allowed values for directive whose type is not string',
E_USER_ERROR);
return;
@@ -246,8 +265,11 @@ class HTMLPurifier_ConfigSchema {
foreach ($allowed_values as $value) {
$directive->allowed[$value] = true;
}
if ($def->defaults[$namespace][$name] !== null &&
!isset($directive->allowed[$def->defaults[$namespace][$name]])) {
if (
HTMLPURIFIER_SCHEMA_STRICT &&
$def->defaults[$namespace][$name] !== null &&
!isset($directive->allowed[$def->defaults[$namespace][$name]])
) {
trigger_error('Default value must be in allowed range of variables',
E_USER_ERROR);
$directive->allowed = true; // undo undo!
@@ -263,8 +285,9 @@ class HTMLPurifier_ConfigSchema {
* @param $new_namespace
* @param $new_name Directive that the alias will be to
*/
function defineAlias($namespace, $name, $new_namespace, $new_name) {
static function defineAlias($namespace, $name, $new_namespace, $new_name) {
$def =& HTMLPurifier_ConfigSchema::instance();
if (HTMLPURIFIER_SCHEMA_STRICT) {
if (!isset($def->info[$namespace])) {
trigger_error('Cannot define directive alias in undefined namespace',
E_USER_ERROR);
@@ -290,9 +313,11 @@ class HTMLPurifier_ConfigSchema {
E_USER_ERROR);
return;
}
}
$def->info[$namespace][$name] =
new HTMLPurifier_ConfigDef_DirectiveAlias(
$new_namespace, $new_name);
$def->info[$new_namespace][$new_name]->directiveAliases[] = "$namespace.$name";
}
/**
@@ -310,8 +335,10 @@ class HTMLPurifier_ConfigSchema {
return $var;
case 'istring':
case 'string':
case 'text': // no difference, just is longer/multiple line string
case 'itext':
if (!is_string($var)) break;
if ($type === 'istring') $var = strtolower($var);
if ($type === 'istring' || $type === 'itext') $var = strtolower($var);
return $var;
case 'int':
if (is_string($var) && ctype_digit($var)) $var = (int) $var;
@@ -342,9 +369,13 @@ class HTMLPurifier_ConfigSchema {
// a single empty string item, but having an empty
// array is more intuitive
if ($var == '') return array();
if (strpos($var, "\n") === false && strpos($var, "\r") === false) {
// simplistic string to array method that only works
// for simple lists of tag names or alphanumeric characters
$var = explode(',',$var);
} else {
$var = preg_split('/(,|[\n\r]+)/', $var);
}
// remove spaces
foreach ($var as $i => $j) $var[$i] = trim($j);
if ($type === 'hash') {
@@ -385,6 +416,7 @@ class HTMLPurifier_ConfigSchema {
* Takes an absolute path and munges it into a more manageable relative path
*/
function mungeFilename($filename) {
if (!HTMLPURIFIER_SCHEMA_STRICT) return $filename;
$offset = strrpos($filename, 'HTMLPurifier');
$filename = substr($filename, $offset);
$filename = str_replace('\\', '/', $filename);
@@ -396,9 +428,9 @@ class HTMLPurifier_ConfigSchema {
*/
function isError($var) {
if (!is_object($var)) return false;
if (!is_a($var, 'HTMLPurifier_Error')) return false;
if (!($var instanceof HTMLPurifier_Error)) return false;
return true;
}
}
?>

View File

@@ -5,6 +5,7 @@ require_once 'HTMLPurifier/ChildDef.php';
require_once 'HTMLPurifier/ChildDef/Empty.php';
require_once 'HTMLPurifier/ChildDef/Required.php';
require_once 'HTMLPurifier/ChildDef/Optional.php';
require_once 'HTMLPurifier/ChildDef/Custom.php';
// NOT UNIT TESTED!!!
@@ -147,4 +148,3 @@ class HTMLPurifier_ContentSets
}
?>

View File

@@ -2,6 +2,8 @@
/**
* Registry object that contains information about the current context.
* @warning Is a bit buggy when variables are set to null: it thinks
* they don't exist! So use false instead, please.
*/
class HTMLPurifier_Context
{
@@ -19,7 +21,7 @@ class HTMLPurifier_Context
*/
function register($name, &$ref) {
if (isset($this->_storage[$name])) {
trigger_error('Name collision, cannot re-register',
trigger_error("Name $name produces collision, cannot re-register",
E_USER_ERROR);
return;
}
@@ -29,11 +31,14 @@ class HTMLPurifier_Context
/**
* Retrieves a variable reference from the context.
* @param $name String name
* @param $ignore_error Boolean whether or not to ignore error
*/
function &get($name) {
function &get($name, $ignore_error = false) {
if (!isset($this->_storage[$name])) {
trigger_error('Attempted to retrieve non-existent variable',
if (!$ignore_error) {
trigger_error("Attempted to retrieve non-existent variable $name",
E_USER_ERROR);
}
$var = null; // so we can return by reference
return $var;
}
@@ -46,7 +51,7 @@ class HTMLPurifier_Context
*/
function destroy($name) {
if (!isset($this->_storage[$name])) {
trigger_error('Attempted to destroy non-existent variable',
trigger_error("Attempted to destroy non-existent variable $name",
E_USER_ERROR);
return;
}
@@ -73,4 +78,3 @@ class HTMLPurifier_Context
}
?>

View File

@@ -38,4 +38,3 @@ class HTMLPurifier_Definition
}
?>

Some files were not shown because too many files have changed in this diff Show More