MDL-19871 imported htmlpurifier 4.0.0

This commit is contained in:
skodak
2009-07-19 11:56:56 +00:00
parent 4c5e3bbe14
commit 97f973f922
84 changed files with 524 additions and 435 deletions
@@ -9,36 +9,28 @@ class HTMLPurifier_ConfigSchema_Builder_ConfigSchema
public function build($interchange) {
$schema = new HTMLPurifier_ConfigSchema();
foreach ($interchange->namespaces as $n) {
$schema->addNamespace($n->namespace);
}
foreach ($interchange->directives as $d) {
$schema->add(
$d->id->namespace,
$d->id->directive,
$d->id->key,
$d->default,
$d->type,
$d->typeAllowsNull
);
if ($d->allowed !== null) {
$schema->addAllowedValues(
$d->id->namespace,
$d->id->directive,
$d->id->key,
$d->allowed
);
}
foreach ($d->aliases as $alias) {
$schema->addAlias(
$alias->namespace,
$alias->directive,
$d->id->namespace,
$d->id->directive
$alias->key,
$d->id->key
);
}
if ($d->valueAliases !== null) {
$schema->addValueAliases(
$d->id->namespace,
$d->id->directive,
$d->id->key,
$d->valueAliases
);
}
@@ -8,6 +8,7 @@ class HTMLPurifier_ConfigSchema_Builder_Xml extends XMLWriter
{
protected $interchange;
private $namespace;
protected function writeHTMLDiv($html) {
$this->startElement('div');
@@ -34,36 +35,33 @@ class HTMLPurifier_ConfigSchema_Builder_Xml extends XMLWriter
$this->startElement('configdoc');
$this->writeElement('title', $interchange->name);
foreach ($interchange->namespaces as $namespace) {
$this->buildNamespace($namespace);
foreach ($interchange->directives as $directive) {
$this->buildDirective($directive);
}
if ($this->namespace) $this->endElement(); // namespace
$this->endElement(); // configdoc
$this->flush();
}
public function buildNamespace($namespace) {
$this->startElement('namespace');
$this->writeAttribute('id', $namespace->namespace);
public function buildDirective($directive) {
$this->writeElement('name', $namespace->namespace);
$this->startElement('description');
$this->writeHTMLDiv($namespace->description);
$this->endElement(); // description
foreach ($this->interchange->directives as $directive) {
if ($directive->id->namespace !== $namespace->namespace) continue;
$this->buildDirective($directive);
// Kludge, although I suppose having a notion of a "root namespace"
// certainly makes things look nicer when documentation is built.
// Depends on things being sorted.
if (!$this->namespace || $this->namespace !== $directive->id->getRootNamespace()) {
if ($this->namespace) $this->endElement(); // namespace
$this->namespace = $directive->id->getRootNamespace();
$this->startElement('namespace');
$this->writeAttribute('id', $this->namespace);
$this->writeElement('name', $this->namespace);
}
$this->endElement(); // namespace
}
public function buildDirective($directive) {
$this->startElement('directive');
$this->writeAttribute('id', $directive->id->toString());
$this->writeElement('name', $directive->id->directive);
$this->writeElement('name', $directive->id->getDirective());
$this->startElement('aliases');
foreach ($directive->aliases as $alias) $this->writeElement('alias', $alias->toString());
@@ -13,26 +13,11 @@ class HTMLPurifier_ConfigSchema_Interchange
*/
public $name;
/**
* Array of Namespace ID => array(namespace info)
*/
public $namespaces = array();
/**
* Array of Directive ID => array(directive info)
*/
public $directives = array();
/**
* Adds a namespace array to $namespaces
*/
public function addNamespace($namespace) {
if (isset($this->namespaces[$i = $namespace->namespace])) {
throw new HTMLPurifier_ConfigSchema_Exception("Cannot redefine namespace '$i'");
}
$this->namespaces[$i] = $namespace;
}
/**
* Adds a directive array to $directives
*/
@@ -6,11 +6,10 @@
class HTMLPurifier_ConfigSchema_Interchange_Id
{
public $namespace, $directive;
public $key;
public function __construct($namespace, $directive) {
$this->namespace = $namespace;
$this->directive = $directive;
public function __construct($key) {
$this->key = $key;
}
/**
@@ -18,12 +17,19 @@ class HTMLPurifier_ConfigSchema_Interchange_Id
* cause problems for PHP 5.0 support.
*/
public function toString() {
return $this->namespace . '.' . $this->directive;
return $this->key;
}
public function getRootNamespace() {
return substr($this->key, 0, strpos($this->key, "."));
}
public function getDirective() {
return substr($this->key, strpos($this->key, ".") + 1);
}
public static function make($id) {
list($namespace, $directive) = explode('.', $id);
return new HTMLPurifier_ConfigSchema_Interchange_Id($namespace, $directive);
return new HTMLPurifier_ConfigSchema_Interchange_Id($id);
}
}
@@ -1,21 +0,0 @@
<?php
/**
* Interchange component class describing namespaces.
*/
class HTMLPurifier_ConfigSchema_Interchange_Namespace
{
/**
* Name of namespace defined.
*/
public $namespace;
/**
* HTML description.
*/
public $description;
}
// vim: et sw=4 sts=4
@@ -13,13 +13,17 @@ class HTMLPurifier_ConfigSchema_InterchangeBuilder
}
public static function buildFromDirectory($dir = null) {
$parser = new HTMLPurifier_StringHashParser();
$builder = new HTMLPurifier_ConfigSchema_InterchangeBuilder();
$interchange = new HTMLPurifier_ConfigSchema_Interchange();
return $builder->buildDir($interchange, $dir);
}
if (!$dir) $dir = HTMLPURIFIER_PREFIX . '/HTMLPurifier/ConfigSchema/schema/';
$info = parse_ini_file($dir . 'info.ini');
$interchange->name = $info['name'];
public function buildDir($interchange, $dir = null) {
if (!$dir) $dir = HTMLPURIFIER_PREFIX . '/HTMLPurifier/ConfigSchema/schema';
if (file_exists($dir . '/info.ini')) {
$info = parse_ini_file($dir . '/info.ini');
$interchange->name = $info['name'];
}
$files = array();
$dh = opendir($dir);
@@ -33,15 +37,20 @@ class HTMLPurifier_ConfigSchema_InterchangeBuilder
sort($files);
foreach ($files as $file) {
$builder->build(
$interchange,
new HTMLPurifier_StringHash( $parser->parseFile($dir . $file) )
);
$this->buildFile($interchange, $dir . '/' . $file);
}
return $interchange;
}
public function buildFile($interchange, $file) {
$parser = new HTMLPurifier_StringHashParser();
$this->build(
$interchange,
new HTMLPurifier_StringHash( $parser->parseFile($file) )
);
}
/**
* Builds an interchange object based on a hash.
* @param $interchange HTMLPurifier_ConfigSchema_Interchange object to build
@@ -55,22 +64,17 @@ class HTMLPurifier_ConfigSchema_InterchangeBuilder
throw new HTMLPurifier_ConfigSchema_Exception('Hash does not have any ID');
}
if (strpos($hash['ID'], '.') === false) {
$this->buildNamespace($interchange, $hash);
if (count($hash) == 2 && isset($hash['DESCRIPTION'])) {
$hash->offsetGet('DESCRIPTION'); // prevent complaining
} else {
throw new HTMLPurifier_ConfigSchema_Exception('All directives must have a namespace');
}
} else {
$this->buildDirective($interchange, $hash);
}
$this->_findUnused($hash);
}
public function buildNamespace($interchange, $hash) {
$namespace = new HTMLPurifier_ConfigSchema_Interchange_Namespace();
$namespace->namespace = $hash->offsetGet('ID');
if (isset($hash['DESCRIPTION'])) {
$namespace->description = $hash->offsetGet('DESCRIPTION');
}
$interchange->addNamespace($namespace);
}
public function buildDirective($interchange, $hash) {
$directive = new HTMLPurifier_ConfigSchema_Interchange_Directive();
@@ -39,10 +39,6 @@ class HTMLPurifier_ConfigSchema_Validator
$this->aliases = array();
// PHP is a bit lax with integer <=> string conversions in
// arrays, so we don't use the identical !== comparison
foreach ($interchange->namespaces as $i => $namespace) {
if ($i != $namespace->namespace) $this->error(false, "Integrity violation: key '$i' does not match internal id '{$namespace->namespace}'");
$this->validateNamespace($namespace);
}
foreach ($interchange->directives as $i => $directive) {
$id = $directive->id->toString();
if ($i != $id) $this->error(false, "Integrity violation: key '$i' does not match internal id '$id'");
@@ -51,20 +47,6 @@ class HTMLPurifier_ConfigSchema_Validator
return true;
}
/**
* Validates a HTMLPurifier_ConfigSchema_Interchange_Namespace object.
*/
public function validateNamespace($n) {
$this->context[] = "namespace '{$n->namespace}'";
$this->with($n, 'namespace')
->assertNotEmpty()
->assertAlnum(); // implicit assertIsString handled by InterchangeBuilder
$this->with($n, 'description')
->assertNotEmpty()
->assertIsString(); // handled by InterchangeBuilder
array_pop($this->context);
}
/**
* Validates a HTMLPurifier_ConfigSchema_Interchange_Id object.
*/
@@ -75,12 +57,11 @@ class HTMLPurifier_ConfigSchema_Validator
// handled by InterchangeBuilder
$this->error(false, 'is not an instance of HTMLPurifier_ConfigSchema_Interchange_Id');
}
if (!isset($this->interchange->namespaces[$id->namespace])) {
$this->error('namespace', 'does not exist'); // assumes that the namespace was validated already
}
$this->with($id, 'directive')
// keys are now unconstrained (we might want to narrow down to A-Za-z0-9.)
// we probably should check that it has at least one namespace
$this->with($id, 'key')
->assertNotEmpty()
->assertAlnum(); // implicit assertIsString handled by InterchangeBuilder
->assertIsString(); // implicit assertIsString handled by InterchangeBuilder
array_pop($this->context);
}
@@ -0,0 +1,8 @@
Attr.AllowedClasses
TYPE: lookup/null
VERSION: 4.0.0
DEFAULT: null
--DESCRIPTION--
List of allowed class values in the class attribute. By default, this is null,
which means all classes are allowed.
--# vim: et sw=4 sts=4
@@ -0,0 +1,19 @@
Attr.ClassUseCDATA
TYPE: bool/null
DEFAULT: null
VERSION: 4.0.0
--DESCRIPTION--
If null, class will auto-detect the doctype and, if matching XHTML 1.1 or
XHTML 2.0, will use the restrictive NMTOKENS specification of class. Otherwise,
it will use a relaxed CDATA definition. If true, the relaxed CDATA definition
is forced; if false, the NMTOKENS definition is forced. To get behavior
of HTML Purifier prior to 4.0.0, set this directive to false.
Some rational behind the auto-detection:
in previous versions of HTML Purifier, it was assumed that the form of
class was NMTOKENS, as specified by the XHTML Modularization (representing
XHTML 1.1 and XHTML 2.0). The DTDs for HTML 4.01 and XHTML 1.0, however
specify class as CDATA. HTML 5 effectively defines it as CDATA, but
with the additional constraint that each name should be unique (this is not
explicitly outlined in previous specifications).
--# vim: et sw=4 sts=4
@@ -0,0 +1,8 @@
Attr.ForbiddenClasses
TYPE: lookup
VERSION: 4.0.0
DEFAULT: array()
--DESCRIPTION--
List of forbidden class values in the class attribute. By default, this is
empty, which means that no classes are forbidden. See also %Attr.AllowedClasses.
--# vim: et sw=4 sts=4
@@ -1,3 +0,0 @@
Attr
DESCRIPTION: Features regarding attribute validation.
--# vim: et sw=4 sts=4
@@ -1,9 +1,9 @@
AutoFormatParam.PurifierLinkifyDocURL
AutoFormat.PurifierLinkify.DocURL
TYPE: string
VERSION: 2.0.1
DEFAULT: '#%s'
ALIASES: AutoFormatParam.PurifierLinkifyDocURL
--DESCRIPTION--
<p>
Location of configuration documentation to link to, let %s substitute
into the configuration's namespace and directive names sans the percent
@@ -0,0 +1,11 @@
AutoFormat.RemoveEmpty.RemoveNbsp.Exceptions
TYPE: lookup
VERSION: 4.0.0
DEFAULT: array('td' => true, 'th' => true)
--DESCRIPTION--
<p>
When %AutoFormat.RemoveEmpty and %AutoFormat.RemoveEmpty.RemoveNbsp
are enabled, this directive defines what HTML elements should not be
removede if they have only a non-breaking space in them.
</p>
--# vim: et sw=4 sts=4
@@ -0,0 +1,15 @@
AutoFormat.RemoveEmpty.RemoveNbsp
TYPE: bool
VERSION: 4.0.0
DEFAULT: false
--DESCRIPTION--
<p>
When enabled, HTML Purifier will treat any elements that contain only
non-breaking spaces as well as regular whitespace as empty, and remove
them when %AutoForamt.RemoveEmpty is enabled.
</p>
<p>
See %AutoFormat.RemoveEmpty.RemoveNbsp.Exceptions for a list of elements
that don't have this behavior applied to them.
</p>
--# vim: et sw=4 sts=4
@@ -31,7 +31,8 @@ DEFAULT: false
</p>
<p>
Elements that contain only whitespace will be treated as empty. Non-breaking
spaces, however, do not count as whitespace.
spaces, however, do not count as whitespace. See
%AutoFormat.RemoveEmpty.RemoveNbsp for alternate behavior.
</p>
<p>
This algorithm is not perfect; you may still notice some empty tags,
@@ -39,7 +40,7 @@ DEFAULT: false
because they were not permitted in that context, or tags that, after
being auto-closed by another tag, where empty. This is for safety reasons
to prevent clever code from breaking validation. The general rule of thumb:
if a tag looked empty on the way end, it will get removed; if HTML Purifier
if a tag looked empty on the way in, it will get removed; if HTML Purifier
made it empty, it will stay.
</p>
--# vim: et sw=4 sts=4
@@ -1,3 +0,0 @@
AutoFormat
DESCRIPTION: Configuration for activating auto-formatting functionality (also known as <code>Injector</code>s)
--# vim: et sw=4 sts=4
@@ -1,3 +0,0 @@
AutoFormatParam
DESCRIPTION: Configuration for customizing auto-formatting functionality
--# vim: et sw=4 sts=4
@@ -1,3 +0,0 @@
CSS
DESCRIPTION: Configuration regarding allowed CSS.
--# vim: et sw=4 sts=4
@@ -1,3 +0,0 @@
Cache
DESCRIPTION: Configuration for DefinitionCache and related subclasses.
--# vim: et sw=4 sts=4
@@ -1,3 +0,0 @@
Core
DESCRIPTION: Core features that are always available.
--# vim: et sw=4 sts=4
@@ -1,8 +1,8 @@
FilterParam.ExtractStyleBlocksEscaping
Filter.ExtractStyleBlocks.Escaping
TYPE: bool
VERSION: 3.0.0
DEFAULT: true
ALIASES: Filter.ExtractStyleBlocksEscaping
ALIASES: Filter.ExtractStyleBlocksEscaping, FilterParam.ExtractStyleBlocksEscaping
--DESCRIPTION--
<p>
@@ -1,8 +1,8 @@
FilterParam.ExtractStyleBlocksScope
Filter.ExtractStyleBlocks.Scope
TYPE: string/null
VERSION: 3.0.0
DEFAULT: NULL
ALIASES: Filter.ExtractStyleBlocksScope
ALIASES: Filter.ExtractStyleBlocksScope, FilterParam.ExtractStyleBlocksScope
--DESCRIPTION--
<p>
@@ -1,7 +1,8 @@
FilterParam.ExtractStyleBlocksTidyImpl
Filter.ExtractStyleBlocks.TidyImpl
TYPE: mixed/null
VERSION: 3.1.0
DEFAULT: NULL
ALIASES: FilterParam.ExtractStyleBlocksTidyImpl
--DESCRIPTION--
<p>
If left NULL, HTML Purifier will attempt to instantiate a <code>csstidy</code>
@@ -1,3 +0,0 @@
Filter
DESCRIPTION: Directives for turning filters on and off, or specifying custom filters.
--# vim: et sw=4 sts=4
@@ -1,3 +0,0 @@
FilterParam
DESCRIPTION: Configuration for filters.
--# vim: et sw=4 sts=4
@@ -0,0 +1,11 @@
HTML.Attr.Name.UseCDATA
TYPE: bool
DEFAULT: false
VERSION: 4.0.0
--DESCRIPTION--
The W3C specification DTD defines the name attribute to be CDATA, not ID, due
to limitations of DTD. In certain documents, this relaxed behavior is desired,
whether it is to specify duplicate names, or to specify names that would be
illegal IDs (for example, names that begin with a digit.) Set this configuration
directive to true to use the relaxed parsing rules.
--# vim: et sw=4 sts=4
@@ -1,3 +0,0 @@
HTML
DESCRIPTION: Configuration regarding allowed HTML.
--# vim: et sw=4 sts=4
@@ -1,3 +0,0 @@
Output
DESCRIPTION: Configuration relating to the generation of (X)HTML.
--# vim: et sw=4 sts=4
@@ -1,3 +0,0 @@
Test
DESCRIPTION: Developer testing configuration for our unit tests.
--# vim: et sw=4 sts=4
@@ -1,3 +0,0 @@
URI
DESCRIPTION: Features regarding Uniform Resource Identifiers.
--# vim: et sw=4 sts=4