diff --git a/lib/common.lib.php b/lib/common.lib.php
index a9885c465..3674cfdcd 100644
--- a/lib/common.lib.php
+++ b/lib/common.lib.php
@@ -478,26 +478,6 @@ function conv_subject($subject, $len, $suffix='')
return cut_str(get_text($subject), $len, $suffix);
}
-// OBJECT 태그의 XSS 막기
-function bad120422($matches)
-{
- $tag = $matches['1'];
- $code = $matches['2'];
- if (preg_match("#\bscript\b#i", $code)) {
- return "$tag 태그에 스크립트는 사용 불가합니다.";
- } else if (preg_match("#\bbase64\b#i", $code)) {
- return "$tag 태그에 BASE64는 사용 불가합니다.";
- }
- return $matches['0'];
-}
-
-// tag 내의 주석문 무효화 하기
-function bad130128($matches)
-{
- $str = $matches[2];
- return '<'.$matches[1].preg_replace('#(\/\*|\*\/)#', '', $str).'>';
-}
-
// 내용을 변환
function conv_content($content, $html)
{
@@ -524,60 +504,8 @@ function conv_content($content, $html)
$content .= "";
}
- $content = preg_replace_callback("/<([^>]+)>/s", 'bad130128', $content);
-
$content = preg_replace($source, $target, $content);
-
- // XSS (Cross Site Script) 막기
- // 완벽한 XSS 방지는 없다.
-
- // 이런 경우를 방지함
- //$content = preg_replace("#\/\*.*\*\/#iU", "", $content);
- // 위의 정규식이 아래와 같은 내용을 통과시키므로 not greedy(비탐욕수량자?) 옵션을 제거함. ignore case 옵션도 필요 없으므로 제거
- //
- $content = preg_replace("#\/\*.*\*\/#", "", $content);
-
- // object, embed 태그에서 javascript 코드 막기
- $content = preg_replace_callback("#<(object|embed)([^>]+)>#i", "bad120422", $content);
-
- $content = preg_replace("/(on)([a-z]+)([^a-z]*)(\=)/i", "on$2$3$4", $content);
- $content = preg_replace("/(dy)(nsrc)/i", "dy$2", $content);
- $content = preg_replace("/(lo)(wsrc)/i", "lo$2", $content);
- $content = preg_replace("/(sc)(ript)/i", "sc$2", $content);
- $content = preg_replace_callback("#<([^>]+)#", create_function('$m', 'return "<".str_replace("<", "<", $m[1]);'), $content);
- //$content = preg_replace("/\<(\w|\s|\?)*(xml)/i", "", $content);
- $content = preg_replace("/\<(\w|\s|\?)*(xml)/i", "_$1$2_", $content);
-
- // 플래시의 액션스크립트와 자바스크립트의 연동을 차단하여 악의적인 사이트로의 이동을 막는다.
- // value="always" 를 value="never" 로, allowScriptaccess="always" 를 allowScriptaccess="never" 로 변환하는데 목적이 있다.
- $content = preg_replace("/((?<=\]+)(\s*=\s*[\'\"]?)always([\'\"]?)([^>]+(?=\>))/i", "$1$2never$3$4", $content);
-
- // 이미지 태그의 src 속성에 삭제등의 링크가 있는 경우 게시물을 확인하는 것만으로도 데이터의 위변조가 가능하므로 이것을 막음
- $content = preg_replace("/<(img[^>]+delete\.php[^>]+bo_table[^>]+)/i", "*** CSRF 감지 : <$1", $content);
- $content = preg_replace("/<(img[^>]+delete_comment\.php[^>]+bo_table[^>]+)/i", "*** CSRF 감지 : <$1", $content);
- $content = preg_replace("/<(img[^>]+logout\.php[^>]+)/i", "*** CSRF 감지 : <$1", $content);
- $content = preg_replace("/<(img[^>]+download\.php[^>]+bo_table[^>]+)/i", "*** CSRF 감지 : <$1", $content);
-
- $content = preg_replace_callback("#style\s*=\s*[\"\']?[^\"\']+[\"\']?#i",
- create_function('$matches', 'return str_replace("\\\\", "", stripslashes($matches[0]));'), $content);
-
- $pattern = "";
- $pattern .= "(e|(x65|101);?)";
- $pattern .= "(x|(x78|120);?)";
- $pattern .= "(p|(x70|112);?)";
- $pattern .= "(r|(x72|114);?)";
- $pattern .= "(e|(x65|101);?)";
- $pattern .= "(s|(x73|115);?)";
- $pattern .= "(s|(x73|115);?)";
- //$pattern .= "(i|(x6a|105);?)";
- $pattern .= "(i|(x69|105);?)";
- $pattern .= "(o|(x6f|111);?)";
- $pattern .= "(n|(x6e|110);?)";
- //$content = preg_replace("/".$pattern."/i", "__EXPRESSION__", $content);
- $content = preg_replace("/<[^>]*".$pattern."/i", "__EXPRESSION__", $content);
- // 와 같은 코드에 취약점이 있어 수정함. 121213
- $content = preg_replace("/(?<=style)(\s*=\s*[\"\']?xss\:)/i", '="__XSS__', $content);
- $content = bad_tag_convert($content);
+ $content = html_purifier($content);
}
else // text 이면
{
@@ -598,6 +526,40 @@ function conv_content($content, $html)
}
+// http://htmlpurifier.org/
+// Standards-Compliant HTML Filtering
+// Safe : HTML Purifier defeats XSS with an audited whitelist
+// Clean : HTML Purifier ensures standards-compliant output
+// Open : HTML Purifier is open-source and highly customizable
+function html_purifier($html)
+{
+ $f = file(G4_PLUGIN_PATH.'/htmlpurifier/safeiframe.txt');
+ $domains = array();
+ foreach($f as $domain){
+ // 첫행이 # 이면 주석 처리
+ if (!preg_match("/^#/", $domain)) {
+ $domain = trim($domain);
+ if ($domain)
+ array_push($domains, $domain);
+ }
+ }
+ // 내 도메인도 추가
+ array_push($domains, $_SERVER['HTTP_HOST'].'/');
+ $safeiframe = implode('|', $domains);
+
+ include_once(G4_PLUGIN_PATH.'/htmlpurifier/HTMLPurifier.standalone.php');
+ $config = HTMLPurifier_Config::createDefault();
+ // data/cache 디렉토리에 CSS, HTML, URI 디렉토리 등을 만든다.
+ $config->set('Cache.SerializerPath', G4_DATA_PATH.'/cache');
+ $config->set('HTML.SafeEmbed', true);
+ $config->set('HTML.SafeObject', true);
+ $config->set('HTML.SafeIframe', true);
+ $config->set('URI.SafeIframeRegexp','%^(https?:)?//('.$safeiframe.')%');
+ $purifier = new HTMLPurifier($config);
+ return $purifier->purify($html);
+}
+
+
// 검색 구문을 얻는다.
function get_sql_search($search_ca_name, $search_field, $search_text, $search_operator='and')
{
diff --git a/plugin/htmlpurifier/HTMLPurifier.standalone.php b/plugin/htmlpurifier/HTMLPurifier.standalone.php
new file mode 100644
index 000000000..86b4c884d
--- /dev/null
+++ b/plugin/htmlpurifier/HTMLPurifier.standalone.php
@@ -0,0 +1,17627 @@
+config = HTMLPurifier_Config::create($config);
+
+ $this->strategy = new HTMLPurifier_Strategy_Core();
+
+ }
+
+ /**
+ * Adds a filter to process the output. First come first serve
+ * @param $filter HTMLPurifier_Filter object
+ */
+ public function addFilter($filter) {
+ trigger_error('HTMLPurifier->addFilter() is deprecated, use configuration directives in the Filter namespace or Filter.Custom', E_USER_WARNING);
+ $this->filters[] = $filter;
+ }
+
+ /**
+ * Filters an HTML snippet/document to be XSS-free and standards-compliant.
+ *
+ * @param $html String of HTML to purify
+ * @param $config HTMLPurifier_Config object for this operation, if omitted,
+ * defaults to the config object specified during this
+ * object's construction. The parameter can also be any type
+ * that HTMLPurifier_Config::create() supports.
+ * @return Purified HTML
+ */
+ public function purify($html, $config = null) {
+
+ // :TODO: make the config merge in, instead of replace
+ $config = $config ? HTMLPurifier_Config::create($config) : $this->config;
+
+ // implementation is partially environment dependant, partially
+ // configuration dependant
+ $lexer = HTMLPurifier_Lexer::create($config);
+
+ $context = new HTMLPurifier_Context();
+
+ // setup HTML generator
+ $this->generator = new HTMLPurifier_Generator($config, $context);
+ $context->register('Generator', $this->generator);
+
+ // set up global context variables
+ if ($config->get('Core.CollectErrors')) {
+ // may get moved out if other facilities use it
+ $language_factory = HTMLPurifier_LanguageFactory::instance();
+ $language = $language_factory->create($config, $context);
+ $context->register('Locale', $language);
+
+ $error_collector = new HTMLPurifier_ErrorCollector($context);
+ $context->register('ErrorCollector', $error_collector);
+ }
+
+ // setup id_accumulator context, necessary due to the fact that
+ // AttrValidator can be called from many places
+ $id_accumulator = HTMLPurifier_IDAccumulator::build($config, $context);
+ $context->register('IDAccumulator', $id_accumulator);
+
+ $html = HTMLPurifier_Encoder::convertToUTF8($html, $config, $context);
+
+ // setup filters
+ $filter_flags = $config->getBatch('Filter');
+ $custom_filters = $filter_flags['Custom'];
+ unset($filter_flags['Custom']);
+ $filters = array();
+ foreach ($filter_flags as $filter => $flag) {
+ if (!$flag) continue;
+ if (strpos($filter, '.') !== false) continue;
+ $class = "HTMLPurifier_Filter_$filter";
+ $filters[] = new $class;
+ }
+ foreach ($custom_filters as $filter) {
+ // maybe "HTMLPurifier_Filter_$filter", but be consistent with AutoFormat
+ $filters[] = $filter;
+ }
+ $filters = array_merge($filters, $this->filters);
+ // maybe prepare(), but later
+
+ for ($i = 0, $filter_size = count($filters); $i < $filter_size; $i++) {
+ $html = $filters[$i]->preFilter($html, $config, $context);
+ }
+
+ // purified HTML
+ $html =
+ $this->generator->generateFromTokens(
+ // list of tokens
+ $this->strategy->execute(
+ // list of un-purified tokens
+ $lexer->tokenizeHTML(
+ // un-purified HTML
+ $html, $config, $context
+ ),
+ $config, $context
+ )
+ );
+
+ for ($i = $filter_size - 1; $i >= 0; $i--) {
+ $html = $filters[$i]->postFilter($html, $config, $context);
+ }
+
+ $html = HTMLPurifier_Encoder::convertFromUTF8($html, $config, $context);
+ $this->context =& $context;
+ return $html;
+ }
+
+ /**
+ * Filters an array of HTML snippets
+ * @param $config Optional HTMLPurifier_Config object for this operation.
+ * See HTMLPurifier::purify() for more details.
+ * @return Array of purified HTML
+ */
+ public function purifyArray($array_of_html, $config = null) {
+ $context_array = array();
+ foreach ($array_of_html as $key => $html) {
+ $array_of_html[$key] = $this->purify($html, $config);
+ $context_array[$key] = $this->context;
+ }
+ $this->context = $context_array;
+ return $array_of_html;
+ }
+
+ /**
+ * Singleton for enforcing just one HTML Purifier in your system
+ * @param $prototype Optional prototype HTMLPurifier instance to
+ * overload singleton with, or HTMLPurifier_Config
+ * instance to configure the generated version with.
+ */
+ public static function instance($prototype = null) {
+ if (!self::$instance || $prototype) {
+ if ($prototype instanceof HTMLPurifier) {
+ self::$instance = $prototype;
+ } elseif ($prototype) {
+ self::$instance = new HTMLPurifier($prototype);
+ } else {
+ self::$instance = new HTMLPurifier();
+ }
+ }
+ return self::$instance;
+ }
+
+ /**
+ * @note Backwards compatibility, see instance()
+ */
+ public static function getInstance($prototype = null) {
+ return HTMLPurifier::instance($prototype);
+ }
+
+}
+
+
+
+
+
+/**
+ * Defines common attribute collections that modules reference
+ */
+
+class HTMLPurifier_AttrCollections
+{
+
+ /**
+ * Associative array of attribute collections, indexed by name
+ */
+ public $info = array();
+
+ /**
+ * Performs all expansions on internal data for use by other inclusions
+ * It also collects all attribute collection extensions from
+ * modules
+ * @param $attr_types HTMLPurifier_AttrTypes instance
+ * @param $modules Hash array of HTMLPurifier_HTMLModule members
+ */
+ public function __construct($attr_types, $modules) {
+ // load extensions from the modules
+ foreach ($modules as $module) {
+ foreach ($module->attr_collections as $coll_i => $coll) {
+ if (!isset($this->info[$coll_i])) {
+ $this->info[$coll_i] = array();
+ }
+ foreach ($coll as $attr_i => $attr) {
+ if ($attr_i === 0 && isset($this->info[$coll_i][$attr_i])) {
+ // merge in includes
+ $this->info[$coll_i][$attr_i] = array_merge(
+ $this->info[$coll_i][$attr_i], $attr);
+ continue;
+ }
+ $this->info[$coll_i][$attr_i] = $attr;
+ }
+ }
+ }
+ // perform internal expansions and inclusions
+ foreach ($this->info as $name => $attr) {
+ // merge attribute collections that include others
+ $this->performInclusions($this->info[$name]);
+ // replace string identifiers with actual attribute objects
+ $this->expandIdentifiers($this->info[$name], $attr_types);
+ }
+ }
+
+ /**
+ * Takes a reference to an attribute associative array and performs
+ * all inclusions specified by the zero index.
+ * @param &$attr Reference to attribute array
+ */
+ public function performInclusions(&$attr) {
+ if (!isset($attr[0])) return;
+ $merge = $attr[0];
+ $seen = array(); // recursion guard
+ // loop through all the inclusions
+ for ($i = 0; isset($merge[$i]); $i++) {
+ if (isset($seen[$merge[$i]])) continue;
+ $seen[$merge[$i]] = true;
+ // foreach attribute of the inclusion, copy it over
+ if (!isset($this->info[$merge[$i]])) continue;
+ foreach ($this->info[$merge[$i]] as $key => $value) {
+ if (isset($attr[$key])) continue; // also catches more inclusions
+ $attr[$key] = $value;
+ }
+ if (isset($this->info[$merge[$i]][0])) {
+ // recursion
+ $merge = array_merge($merge, $this->info[$merge[$i]][0]);
+ }
+ }
+ unset($attr[0]);
+ }
+
+ /**
+ * Expands all string identifiers in an attribute array by replacing
+ * them with the appropriate values inside HTMLPurifier_AttrTypes
+ * @param &$attr Reference to attribute array
+ * @param $attr_types HTMLPurifier_AttrTypes instance
+ */
+ public function expandIdentifiers(&$attr, $attr_types) {
+
+ // because foreach will process new elements we add, make sure we
+ // skip duplicates
+ $processed = array();
+
+ foreach ($attr as $def_i => $def) {
+ // skip inclusions
+ if ($def_i === 0) continue;
+
+ if (isset($processed[$def_i])) continue;
+
+ // determine whether or not attribute is required
+ if ($required = (strpos($def_i, '*') !== false)) {
+ // rename the definition
+ unset($attr[$def_i]);
+ $def_i = trim($def_i, '*');
+ $attr[$def_i] = $def;
+ }
+
+ $processed[$def_i] = true;
+
+ // if we've already got a literal object, move on
+ if (is_object($def)) {
+ // preserve previous required
+ $attr[$def_i]->required = ($required || $attr[$def_i]->required);
+ continue;
+ }
+
+ if ($def === false) {
+ unset($attr[$def_i]);
+ continue;
+ }
+
+ if ($t = $attr_types->get($def)) {
+ $attr[$def_i] = $t;
+ $attr[$def_i]->required = $required;
+ } else {
+ unset($attr[$def_i]);
+ }
+ }
+
+ }
+
+}
+
+
+
+
+
+/**
+ * Base class for all validating attribute definitions.
+ *
+ * This family of classes forms the core for not only HTML attribute validation,
+ * but also any sort of string that needs to be validated or cleaned (which
+ * means CSS properties and composite definitions are defined here too).
+ * Besides defining (through code) what precisely makes the string valid,
+ * subclasses are also responsible for cleaning the code if possible.
+ */
+
+abstract class HTMLPurifier_AttrDef
+{
+
+ /**
+ * Tells us whether or not an HTML attribute is minimized. Has no
+ * meaning in other contexts.
+ */
+ public $minimized = false;
+
+ /**
+ * Tells us whether or not an HTML attribute is required. Has no
+ * meaning in other contexts
+ */
+ public $required = false;
+
+ /**
+ * Validates and cleans passed string according to a definition.
+ *
+ * @param $string String to be validated and cleaned.
+ * @param $config Mandatory HTMLPurifier_Config object.
+ * @param $context Mandatory HTMLPurifier_AttrContext object.
+ */
+ abstract public function validate($string, $config, $context);
+
+ /**
+ * Convenience method that parses a string as if it were CDATA.
+ *
+ * This method process a string in the manner specified at
+ * by removing
+ * leading and trailing whitespace, ignoring line feeds, and replacing
+ * carriage returns and tabs with spaces. While most useful for HTML
+ * attributes specified as CDATA, it can also be applied to most CSS
+ * values.
+ *
+ * @note This method is not entirely standards compliant, as trim() removes
+ * more types of whitespace than specified in the spec. In practice,
+ * this is rarely a problem, as those extra characters usually have
+ * already been removed by HTMLPurifier_Encoder.
+ *
+ * @warning This processing is inconsistent with XML's whitespace handling
+ * as specified by section 3.3.3 and referenced XHTML 1.0 section
+ * 4.7. However, note that we are NOT necessarily
+ * parsing XML, thus, this behavior may still be correct. We
+ * assume that newlines have been normalized.
+ */
+ public function parseCDATA($string) {
+ $string = trim($string);
+ $string = str_replace(array("\n", "\t", "\r"), ' ', $string);
+ return $string;
+ }
+
+ /**
+ * Factory method for creating this class from a string.
+ * @param $string String construction info
+ * @return Created AttrDef object corresponding to $string
+ */
+ public function make($string) {
+ // default implementation, return a flyweight of this object.
+ // If $string has an effect on the returned object (i.e. you
+ // need to overload this method), it is best
+ // to clone or instantiate new copies. (Instantiation is safer.)
+ return $this;
+ }
+
+ /**
+ * Removes spaces from rgb(0, 0, 0) so that shorthand CSS properties work
+ * properly. THIS IS A HACK!
+ */
+ protected function mungeRgb($string) {
+ return preg_replace('/rgb\((\d+)\s*,\s*(\d+)\s*,\s*(\d+)\)/', 'rgb(\1,\2,\3)', $string);
+ }
+
+ /**
+ * Parses a possibly escaped CSS string and returns the "pure"
+ * version of it.
+ */
+ protected function expandCSSEscape($string) {
+ // flexibly parse it
+ $ret = '';
+ for ($i = 0, $c = strlen($string); $i < $c; $i++) {
+ if ($string[$i] === '\\') {
+ $i++;
+ if ($i >= $c) {
+ $ret .= '\\';
+ break;
+ }
+ if (ctype_xdigit($string[$i])) {
+ $code = $string[$i];
+ for ($a = 1, $i++; $i < $c && $a < 6; $i++, $a++) {
+ if (!ctype_xdigit($string[$i])) break;
+ $code .= $string[$i];
+ }
+ // We have to be extremely careful when adding
+ // new characters, to make sure we're not breaking
+ // the encoding.
+ $char = HTMLPurifier_Encoder::unichr(hexdec($code));
+ if (HTMLPurifier_Encoder::cleanUTF8($char) === '') continue;
+ $ret .= $char;
+ if ($i < $c && trim($string[$i]) !== '') $i--;
+ continue;
+ }
+ if ($string[$i] === "\n") continue;
+ }
+ $ret .= $string[$i];
+ }
+ return $ret;
+ }
+
+}
+
+
+
+
+
+/**
+ * Processes an entire attribute array for corrections needing multiple values.
+ *
+ * Occasionally, a certain attribute will need to be removed and popped onto
+ * another value. Instead of creating a complex return syntax for
+ * HTMLPurifier_AttrDef, we just pass the whole attribute array to a
+ * specialized object and have that do the special work. That is the
+ * family of HTMLPurifier_AttrTransform.
+ *
+ * An attribute transformation can be assigned to run before or after
+ * HTMLPurifier_AttrDef validation. See HTMLPurifier_HTMLDefinition for
+ * more details.
+ */
+
+abstract class HTMLPurifier_AttrTransform
+{
+
+ /**
+ * Abstract: makes changes to the attributes dependent on multiple values.
+ *
+ * @param $attr Assoc array of attributes, usually from
+ * HTMLPurifier_Token_Tag::$attr
+ * @param $config Mandatory HTMLPurifier_Config object.
+ * @param $context Mandatory HTMLPurifier_Context object
+ * @returns Processed attribute array.
+ */
+ abstract public function transform($attr, $config, $context);
+
+ /**
+ * Prepends CSS properties to the style attribute, creating the
+ * attribute if it doesn't exist.
+ * @param $attr Attribute array to process (passed by reference)
+ * @param $css CSS to prepend
+ */
+ public function prependCSS(&$attr, $css) {
+ $attr['style'] = isset($attr['style']) ? $attr['style'] : '';
+ $attr['style'] = $css . $attr['style'];
+ }
+
+ /**
+ * Retrieves and removes an attribute
+ * @param $attr Attribute array to process (passed by reference)
+ * @param $key Key of attribute to confiscate
+ */
+ public function confiscateAttr(&$attr, $key) {
+ if (!isset($attr[$key])) return null;
+ $value = $attr[$key];
+ unset($attr[$key]);
+ return $value;
+ }
+
+}
+
+
+
+
+
+/**
+ * Provides lookup array of attribute types to HTMLPurifier_AttrDef objects
+ */
+class HTMLPurifier_AttrTypes
+{
+ /**
+ * Lookup array of attribute string identifiers to concrete implementations
+ */
+ protected $info = array();
+
+ /**
+ * Constructs the info array, supplying default implementations for attribute
+ * types.
+ */
+ public function __construct() {
+ // XXX This is kind of poor, since we don't actually /clone/
+ // instances; instead, we use the supplied make() attribute. So,
+ // the underlying class must know how to deal with arguments.
+ // With the old implementation of Enum, that ignored its
+ // arguments when handling a make dispatch, the IAlign
+ // definition wouldn't work.
+
+ // pseudo-types, must be instantiated via shorthand
+ $this->info['Enum'] = new HTMLPurifier_AttrDef_Enum();
+ $this->info['Bool'] = new HTMLPurifier_AttrDef_HTML_Bool();
+
+ $this->info['CDATA'] = new HTMLPurifier_AttrDef_Text();
+ $this->info['ID'] = new HTMLPurifier_AttrDef_HTML_ID();
+ $this->info['Length'] = new HTMLPurifier_AttrDef_HTML_Length();
+ $this->info['MultiLength'] = new HTMLPurifier_AttrDef_HTML_MultiLength();
+ $this->info['NMTOKENS'] = new HTMLPurifier_AttrDef_HTML_Nmtokens();
+ $this->info['Pixels'] = new HTMLPurifier_AttrDef_HTML_Pixels();
+ $this->info['Text'] = new HTMLPurifier_AttrDef_Text();
+ $this->info['URI'] = new HTMLPurifier_AttrDef_URI();
+ $this->info['LanguageCode'] = new HTMLPurifier_AttrDef_Lang();
+ $this->info['Color'] = new HTMLPurifier_AttrDef_HTML_Color();
+ $this->info['IAlign'] = self::makeEnum('top,middle,bottom,left,right');
+ $this->info['LAlign'] = self::makeEnum('top,bottom,left,right');
+ $this->info['FrameTarget'] = new HTMLPurifier_AttrDef_HTML_FrameTarget();
+
+ // unimplemented aliases
+ $this->info['ContentType'] = new HTMLPurifier_AttrDef_Text();
+ $this->info['ContentTypes'] = new HTMLPurifier_AttrDef_Text();
+ $this->info['Charsets'] = new HTMLPurifier_AttrDef_Text();
+ $this->info['Character'] = new HTMLPurifier_AttrDef_Text();
+
+ // "proprietary" types
+ $this->info['Class'] = new HTMLPurifier_AttrDef_HTML_Class();
+
+ // number is really a positive integer (one or more digits)
+ // FIXME: ^^ not always, see start and value of list items
+ $this->info['Number'] = new HTMLPurifier_AttrDef_Integer(false, false, true);
+ }
+
+ private static function makeEnum($in) {
+ return new HTMLPurifier_AttrDef_Clone(new HTMLPurifier_AttrDef_Enum(explode(',', $in)));
+ }
+
+ /**
+ * Retrieves a type
+ * @param $type String type name
+ * @return Object AttrDef for type
+ */
+ public function get($type) {
+
+ // determine if there is any extra info tacked on
+ if (strpos($type, '#') !== false) list($type, $string) = explode('#', $type, 2);
+ else $string = '';
+
+ if (!isset($this->info[$type])) {
+ trigger_error('Cannot retrieve undefined attribute type ' . $type, E_USER_ERROR);
+ return;
+ }
+
+ return $this->info[$type]->make($string);
+
+ }
+
+ /**
+ * Sets a new implementation for a type
+ * @param $type String type name
+ * @param $impl Object AttrDef for type
+ */
+ public function set($type, $impl) {
+ $this->info[$type] = $impl;
+ }
+}
+
+
+
+
+
+/**
+ * Validates the attributes of a token. Doesn't manage required attributes
+ * very well. The only reason we factored this out was because RemoveForeignElements
+ * also needed it besides ValidateAttributes.
+ */
+class HTMLPurifier_AttrValidator
+{
+
+ /**
+ * Validates the attributes of a token, returning a modified token
+ * that has valid tokens
+ * @param $token Reference to token to validate. We require a reference
+ * because the operation this class performs on the token are
+ * not atomic, so the context CurrentToken to be updated
+ * throughout
+ * @param $config Instance of HTMLPurifier_Config
+ * @param $context Instance of HTMLPurifier_Context
+ */
+ public function validateToken(&$token, &$config, $context) {
+
+ $definition = $config->getHTMLDefinition();
+ $e =& $context->get('ErrorCollector', true);
+
+ // initialize IDAccumulator if necessary
+ $ok =& $context->get('IDAccumulator', true);
+ if (!$ok) {
+ $id_accumulator = HTMLPurifier_IDAccumulator::build($config, $context);
+ $context->register('IDAccumulator', $id_accumulator);
+ }
+
+ // initialize CurrentToken if necessary
+ $current_token =& $context->get('CurrentToken', true);
+ if (!$current_token) $context->register('CurrentToken', $token);
+
+ if (
+ !$token instanceof HTMLPurifier_Token_Start &&
+ !$token instanceof HTMLPurifier_Token_Empty
+ ) return $token;
+
+ // create alias to global definition array, see also $defs
+ // DEFINITION CALL
+ $d_defs = $definition->info_global_attr;
+
+ // don't update token until the very end, to ensure an atomic update
+ $attr = $token->attr;
+
+ // do global transformations (pre)
+ // nothing currently utilizes this
+ foreach ($definition->info_attr_transform_pre as $transform) {
+ $attr = $transform->transform($o = $attr, $config, $context);
+ if ($e) {
+ if ($attr != $o) $e->send(E_NOTICE, 'AttrValidator: Attributes transformed', $o, $attr);
+ }
+ }
+
+ // do local transformations only applicable to this element (pre)
+ // ex.
to
+ foreach ($definition->info[$token->name]->attr_transform_pre as $transform) {
+ $attr = $transform->transform($o = $attr, $config, $context);
+ if ($e) {
+ if ($attr != $o) $e->send(E_NOTICE, 'AttrValidator: Attributes transformed', $o, $attr);
+ }
+ }
+
+ // create alias to this element's attribute definition array, see
+ // also $d_defs (global attribute definition array)
+ // 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 => $value) {
+
+ // call the definition
+ if ( isset($defs[$attr_key]) ) {
+ // there is a local definition defined
+ if ($defs[$attr_key] === false) {
+ // We've explicitly been told not to allow this element.
+ // This is usually when there's a global definition
+ // that must be overridden.
+ // Theoretically speaking, we could have a
+ // AttrDef_DenyAll, but this is faster!
+ $result = false;
+ } else {
+ // validate according to the element's definition
+ $result = $defs[$attr_key]->validate(
+ $value, $config, $context
+ );
+ }
+ } elseif ( isset($d_defs[$attr_key]) ) {
+ // there is a global definition defined, validate according
+ // to the global definition
+ $result = $d_defs[$attr_key]->validate(
+ $value, $config, $context
+ );
+ } else {
+ // system never heard of the attribute? DELETE!
+ $result = false;
+ }
+
+ // put the results into effect
+ if ($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;
+ } else {
+ // nothing happens
+ }
+
+ // we'd also want slightly more complicated substitution
+ // involving an array as the return value,
+ // although we're not sure how colliding attributes would
+ // resolve (certain ones would be completely overriden,
+ // others would prepend themselves).
+ }
+
+ $context->destroy('CurrentAttr');
+
+ // post transforms
+
+ // global (error reporting untested)
+ foreach ($definition->info_attr_transform_post as $transform) {
+ $attr = $transform->transform($o = $attr, $config, $context);
+ if ($e) {
+ if ($attr != $o) $e->send(E_NOTICE, 'AttrValidator: Attributes transformed', $o, $attr);
+ }
+ }
+
+ // local (error reporting untested)
+ foreach ($definition->info[$token->name]->attr_transform_post as $transform) {
+ $attr = $transform->transform($o = $attr, $config, $context);
+ if ($e) {
+ if ($attr != $o) $e->send(E_NOTICE, 'AttrValidator: Attributes transformed', $o, $attr);
+ }
+ }
+
+ $token->attr = $attr;
+
+ // destroy CurrentToken if we made it ourselves
+ if (!$current_token) $context->destroy('CurrentToken');
+
+ }
+
+
+}
+
+
+
+
+
+// constants are slow, so we use as few as possible
+if (!defined('HTMLPURIFIER_PREFIX')) {
+ define('HTMLPURIFIER_PREFIX', dirname(__FILE__) . '/standalone');
+ set_include_path(HTMLPURIFIER_PREFIX . PATH_SEPARATOR . get_include_path());
+}
+
+// accomodations for versions earlier than 5.0.2
+// borrowed from PHP_Compat, LGPL licensed, by Aidan Lister
+if (!defined('PHP_EOL')) {
+ switch (strtoupper(substr(PHP_OS, 0, 3))) {
+ case 'WIN':
+ define('PHP_EOL', "\r\n");
+ break;
+ case 'DAR':
+ define('PHP_EOL', "\r");
+ break;
+ default:
+ define('PHP_EOL', "\n");
+ }
+}
+
+/**
+ * Bootstrap class that contains meta-functionality for HTML Purifier such as
+ * the autoload function.
+ *
+ * @note
+ * This class may be used without any other files from HTML Purifier.
+ */
+class HTMLPurifier_Bootstrap
+{
+
+ /**
+ * Autoload function for HTML Purifier
+ * @param $class Class to load
+ */
+ public static function autoload($class) {
+ $file = HTMLPurifier_Bootstrap::getPath($class);
+ if (!$file) return false;
+ // Technically speaking, it should be ok and more efficient to
+ // just do 'require', but Antonio Parraga reports that with
+ // Zend extensions such as Zend debugger and APC, this invariant
+ // may be broken. Since we have efficient alternatives, pay
+ // the cost here and avoid the bug.
+ require_once HTMLPURIFIER_PREFIX . '/' . $file;
+ return true;
+ }
+
+ /**
+ * Returns the path for a specific class.
+ */
+ public static function getPath($class) {
+ if (strncmp('HTMLPurifier', $class, 12) !== 0) return false;
+ // Custom implementations
+ if (strncmp('HTMLPurifier_Language_', $class, 22) === 0) {
+ $code = str_replace('_', '-', substr($class, 22));
+ $file = 'HTMLPurifier/Language/classes/' . $code . '.php';
+ } else {
+ $file = str_replace('_', '/', $class) . '.php';
+ }
+ if (!file_exists(HTMLPURIFIER_PREFIX . '/' . $file)) return false;
+ return $file;
+ }
+
+ /**
+ * "Pre-registers" our autoloader on the SPL stack.
+ */
+ public static function registerAutoload() {
+ $autoload = array('HTMLPurifier_Bootstrap', 'autoload');
+ if ( ($funcs = spl_autoload_functions()) === false ) {
+ spl_autoload_register($autoload);
+ } elseif (function_exists('spl_autoload_unregister')) {
+ if (version_compare(PHP_VERSION, '5.3.0', '>=')) {
+ // prepend flag exists, no need for shenanigans
+ spl_autoload_register($autoload, true, true);
+ } else {
+ $buggy = version_compare(PHP_VERSION, '5.2.11', '<');
+ $compat = version_compare(PHP_VERSION, '5.1.2', '<=') &&
+ version_compare(PHP_VERSION, '5.1.0', '>=');
+ foreach ($funcs as $func) {
+ if ($buggy && is_array($func)) {
+ // :TRICKY: There are some compatibility issues and some
+ // places where we need to error out
+ $reflector = new ReflectionMethod($func[0], $func[1]);
+ if (!$reflector->isStatic()) {
+ throw new Exception('
+ HTML Purifier autoloader registrar is not compatible
+ with non-static object methods due to PHP Bug #44144;
+ Please do not use HTMLPurifier.autoload.php (or any
+ file that includes this file); instead, place the code:
+ spl_autoload_register(array(\'HTMLPurifier_Bootstrap\', \'autoload\'))
+ after your own autoloaders.
+ ');
+ }
+ // Suprisingly, spl_autoload_register supports the
+ // Class::staticMethod callback format, although call_user_func doesn't
+ if ($compat) $func = implode('::', $func);
+ }
+ spl_autoload_unregister($func);
+ }
+ spl_autoload_register($autoload);
+ foreach ($funcs as $func) spl_autoload_register($func);
+ }
+ }
+ }
+
+}
+
+
+
+
+
+/**
+ * Super-class for definition datatype objects, implements serialization
+ * functions for the class.
+ */
+abstract class HTMLPurifier_Definition
+{
+
+ /**
+ * Has setup() been called yet?
+ */
+ public $setup = false;
+
+ /**
+ * If true, write out the final definition object to the cache after
+ * setup. This will be true only if all invocations to get a raw
+ * definition object are also optimized. This does not cause file
+ * system thrashing because on subsequent calls the cached object
+ * is used and any writes to the raw definition object are short
+ * circuited. See enduser-customize.html for the high-level
+ * picture.
+ */
+ public $optimized = null;
+
+ /**
+ * What type of definition is it?
+ */
+ public $type;
+
+ /**
+ * Sets up the definition object into the final form, something
+ * not done by the constructor
+ * @param $config HTMLPurifier_Config instance
+ */
+ abstract protected function doSetup($config);
+
+ /**
+ * Setup function that aborts if already setup
+ * @param $config HTMLPurifier_Config instance
+ */
+ public function setup($config) {
+ if ($this->setup) return;
+ $this->setup = true;
+ $this->doSetup($config);
+ }
+
+}
+
+
+
+
+
+/**
+ * Defines allowed CSS attributes and what their values are.
+ * @see HTMLPurifier_HTMLDefinition
+ */
+class HTMLPurifier_CSSDefinition extends HTMLPurifier_Definition
+{
+
+ public $type = 'CSS';
+
+ /**
+ * Assoc array of attribute name to definition object.
+ */
+ public $info = array();
+
+ /**
+ * Constructs the info array. The meat of this class.
+ */
+ protected function doSetup($config) {
+
+ $this->info['text-align'] = new HTMLPurifier_AttrDef_Enum(
+ array('left', 'right', 'center', 'justify'), false);
+
+ $border_style =
+ $this->info['border-bottom-style'] =
+ $this->info['border-right-style'] =
+ $this->info['border-left-style'] =
+ $this->info['border-top-style'] = new HTMLPurifier_AttrDef_Enum(
+ array('none', 'hidden', 'dotted', 'dashed', 'solid', 'double',
+ 'groove', 'ridge', 'inset', 'outset'), false);
+
+ $this->info['border-style'] = new HTMLPurifier_AttrDef_CSS_Multiple($border_style);
+
+ $this->info['clear'] = new HTMLPurifier_AttrDef_Enum(
+ array('none', 'left', 'right', 'both'), false);
+ $this->info['float'] = new HTMLPurifier_AttrDef_Enum(
+ array('none', 'left', 'right'), false);
+ $this->info['font-style'] = new HTMLPurifier_AttrDef_Enum(
+ array('normal', 'italic', 'oblique'), false);
+ $this->info['font-variant'] = new HTMLPurifier_AttrDef_Enum(
+ array('normal', 'small-caps'), false);
+
+ $uri_or_none = new HTMLPurifier_AttrDef_CSS_Composite(
+ array(
+ new HTMLPurifier_AttrDef_Enum(array('none')),
+ new HTMLPurifier_AttrDef_CSS_URI()
+ )
+ );
+
+ $this->info['list-style-position'] = new HTMLPurifier_AttrDef_Enum(
+ array('inside', 'outside'), false);
+ $this->info['list-style-type'] = new HTMLPurifier_AttrDef_Enum(
+ array('disc', 'circle', 'square', 'decimal', 'lower-roman',
+ 'upper-roman', 'lower-alpha', 'upper-alpha', 'none'), false);
+ $this->info['list-style-image'] = $uri_or_none;
+
+ $this->info['list-style'] = new HTMLPurifier_AttrDef_CSS_ListStyle($config);
+
+ $this->info['text-transform'] = new HTMLPurifier_AttrDef_Enum(
+ array('capitalize', 'uppercase', 'lowercase', 'none'), false);
+ $this->info['color'] = new HTMLPurifier_AttrDef_CSS_Color();
+
+ $this->info['background-image'] = $uri_or_none;
+ $this->info['background-repeat'] = new HTMLPurifier_AttrDef_Enum(
+ array('repeat', 'repeat-x', 'repeat-y', 'no-repeat')
+ );
+ $this->info['background-attachment'] = new HTMLPurifier_AttrDef_Enum(
+ array('scroll', 'fixed')
+ );
+ $this->info['background-position'] = new HTMLPurifier_AttrDef_CSS_BackgroundPosition();
+
+ $border_color =
+ $this->info['border-top-color'] =
+ $this->info['border-bottom-color'] =
+ $this->info['border-left-color'] =
+ $this->info['border-right-color'] =
+ $this->info['background-color'] = new HTMLPurifier_AttrDef_CSS_Composite(array(
+ new HTMLPurifier_AttrDef_Enum(array('transparent')),
+ new HTMLPurifier_AttrDef_CSS_Color()
+ ));
+
+ $this->info['background'] = new HTMLPurifier_AttrDef_CSS_Background($config);
+
+ $this->info['border-color'] = new HTMLPurifier_AttrDef_CSS_Multiple($border_color);
+
+ $border_width =
+ $this->info['border-top-width'] =
+ $this->info['border-bottom-width'] =
+ $this->info['border-left-width'] =
+ $this->info['border-right-width'] = new HTMLPurifier_AttrDef_CSS_Composite(array(
+ new HTMLPurifier_AttrDef_Enum(array('thin', 'medium', 'thick')),
+ new HTMLPurifier_AttrDef_CSS_Length('0') //disallow negative
+ ));
+
+ $this->info['border-width'] = new HTMLPurifier_AttrDef_CSS_Multiple($border_width);
+
+ $this->info['letter-spacing'] = new HTMLPurifier_AttrDef_CSS_Composite(array(
+ new HTMLPurifier_AttrDef_Enum(array('normal')),
+ new HTMLPurifier_AttrDef_CSS_Length()
+ ));
+
+ $this->info['word-spacing'] = new HTMLPurifier_AttrDef_CSS_Composite(array(
+ new HTMLPurifier_AttrDef_Enum(array('normal')),
+ new HTMLPurifier_AttrDef_CSS_Length()
+ ));
+
+ $this->info['font-size'] = new HTMLPurifier_AttrDef_CSS_Composite(array(
+ new HTMLPurifier_AttrDef_Enum(array('xx-small', 'x-small',
+ 'small', 'medium', 'large', 'x-large', 'xx-large',
+ 'larger', 'smaller')),
+ new HTMLPurifier_AttrDef_CSS_Percentage(),
+ new HTMLPurifier_AttrDef_CSS_Length()
+ ));
+
+ $this->info['line-height'] = new HTMLPurifier_AttrDef_CSS_Composite(array(
+ new HTMLPurifier_AttrDef_Enum(array('normal')),
+ new HTMLPurifier_AttrDef_CSS_Number(true), // no negatives
+ new HTMLPurifier_AttrDef_CSS_Length('0'),
+ new HTMLPurifier_AttrDef_CSS_Percentage(true)
+ ));
+
+ $margin =
+ $this->info['margin-top'] =
+ $this->info['margin-bottom'] =
+ $this->info['margin-left'] =
+ $this->info['margin-right'] = new HTMLPurifier_AttrDef_CSS_Composite(array(
+ new HTMLPurifier_AttrDef_CSS_Length(),
+ new HTMLPurifier_AttrDef_CSS_Percentage(),
+ new HTMLPurifier_AttrDef_Enum(array('auto'))
+ ));
+
+ $this->info['margin'] = new HTMLPurifier_AttrDef_CSS_Multiple($margin);
+
+ // non-negative
+ $padding =
+ $this->info['padding-top'] =
+ $this->info['padding-bottom'] =
+ $this->info['padding-left'] =
+ $this->info['padding-right'] = new HTMLPurifier_AttrDef_CSS_Composite(array(
+ new HTMLPurifier_AttrDef_CSS_Length('0'),
+ new HTMLPurifier_AttrDef_CSS_Percentage(true)
+ ));
+
+ $this->info['padding'] = new HTMLPurifier_AttrDef_CSS_Multiple($padding);
+
+ $this->info['text-indent'] = new HTMLPurifier_AttrDef_CSS_Composite(array(
+ new HTMLPurifier_AttrDef_CSS_Length(),
+ new HTMLPurifier_AttrDef_CSS_Percentage()
+ ));
+
+ $trusted_wh = new HTMLPurifier_AttrDef_CSS_Composite(array(
+ new HTMLPurifier_AttrDef_CSS_Length('0'),
+ new HTMLPurifier_AttrDef_CSS_Percentage(true),
+ new HTMLPurifier_AttrDef_Enum(array('auto'))
+ ));
+ $max = $config->get('CSS.MaxImgLength');
+
+ $this->info['width'] =
+ $this->info['height'] =
+ $max === null ?
+ $trusted_wh :
+ new HTMLPurifier_AttrDef_Switch('img',
+ // For img tags:
+ new HTMLPurifier_AttrDef_CSS_Composite(array(
+ new HTMLPurifier_AttrDef_CSS_Length('0', $max),
+ new HTMLPurifier_AttrDef_Enum(array('auto'))
+ )),
+ // For everyone else:
+ $trusted_wh
+ );
+
+ $this->info['text-decoration'] = new HTMLPurifier_AttrDef_CSS_TextDecoration();
+
+ $this->info['font-family'] = new HTMLPurifier_AttrDef_CSS_FontFamily();
+
+ // this could use specialized code
+ $this->info['font-weight'] = new HTMLPurifier_AttrDef_Enum(
+ array('normal', 'bold', 'bolder', 'lighter', '100', '200', '300',
+ '400', '500', '600', '700', '800', '900'), false);
+
+ // MUST be called after other font properties, as it references
+ // a CSSDefinition object
+ $this->info['font'] = new HTMLPurifier_AttrDef_CSS_Font($config);
+
+ // same here
+ $this->info['border'] =
+ $this->info['border-bottom'] =
+ $this->info['border-top'] =
+ $this->info['border-left'] =
+ $this->info['border-right'] = new HTMLPurifier_AttrDef_CSS_Border($config);
+
+ $this->info['border-collapse'] = new HTMLPurifier_AttrDef_Enum(array(
+ 'collapse', 'separate'));
+
+ $this->info['caption-side'] = new HTMLPurifier_AttrDef_Enum(array(
+ 'top', 'bottom'));
+
+ $this->info['table-layout'] = new HTMLPurifier_AttrDef_Enum(array(
+ 'auto', 'fixed'));
+
+ $this->info['vertical-align'] = new HTMLPurifier_AttrDef_CSS_Composite(array(
+ new HTMLPurifier_AttrDef_Enum(array('baseline', 'sub', 'super',
+ 'top', 'text-top', 'middle', 'bottom', 'text-bottom')),
+ new HTMLPurifier_AttrDef_CSS_Length(),
+ new HTMLPurifier_AttrDef_CSS_Percentage()
+ ));
+
+ $this->info['border-spacing'] = new HTMLPurifier_AttrDef_CSS_Multiple(new HTMLPurifier_AttrDef_CSS_Length(), 2);
+
+ // These CSS properties don't work on many browsers, but we live
+ // in THE FUTURE!
+ $this->info['white-space'] = new HTMLPurifier_AttrDef_Enum(array('nowrap', 'normal', 'pre', 'pre-wrap', 'pre-line'));
+
+ if ($config->get('CSS.Proprietary')) {
+ $this->doSetupProprietary($config);
+ }
+
+ if ($config->get('CSS.AllowTricky')) {
+ $this->doSetupTricky($config);
+ }
+
+ if ($config->get('CSS.Trusted')) {
+ $this->doSetupTrusted($config);
+ }
+
+ $allow_important = $config->get('CSS.AllowImportant');
+ // wrap all attr-defs with decorator that handles !important
+ foreach ($this->info as $k => $v) {
+ $this->info[$k] = new HTMLPurifier_AttrDef_CSS_ImportantDecorator($v, $allow_important);
+ }
+
+ $this->setupConfigStuff($config);
+ }
+
+ protected function doSetupProprietary($config) {
+ // Internet Explorer only scrollbar colors
+ $this->info['scrollbar-arrow-color'] = new HTMLPurifier_AttrDef_CSS_Color();
+ $this->info['scrollbar-base-color'] = new HTMLPurifier_AttrDef_CSS_Color();
+ $this->info['scrollbar-darkshadow-color'] = new HTMLPurifier_AttrDef_CSS_Color();
+ $this->info['scrollbar-face-color'] = new HTMLPurifier_AttrDef_CSS_Color();
+ $this->info['scrollbar-highlight-color'] = new HTMLPurifier_AttrDef_CSS_Color();
+ $this->info['scrollbar-shadow-color'] = new HTMLPurifier_AttrDef_CSS_Color();
+
+ // technically not proprietary, but CSS3, and no one supports it
+ $this->info['opacity'] = new HTMLPurifier_AttrDef_CSS_AlphaValue();
+ $this->info['-moz-opacity'] = new HTMLPurifier_AttrDef_CSS_AlphaValue();
+ $this->info['-khtml-opacity'] = new HTMLPurifier_AttrDef_CSS_AlphaValue();
+
+ // only opacity, for now
+ $this->info['filter'] = new HTMLPurifier_AttrDef_CSS_Filter();
+
+ // more CSS3
+ $this->info['page-break-after'] =
+ $this->info['page-break-before'] = new HTMLPurifier_AttrDef_Enum(array('auto','always','avoid','left','right'));
+ $this->info['page-break-inside'] = new HTMLPurifier_AttrDef_Enum(array('auto','avoid'));
+
+ }
+
+ protected function doSetupTricky($config) {
+ $this->info['display'] = new HTMLPurifier_AttrDef_Enum(array(
+ 'inline', 'block', 'list-item', 'run-in', 'compact',
+ 'marker', 'table', 'inline-block', 'inline-table', 'table-row-group',
+ 'table-header-group', 'table-footer-group', 'table-row',
+ 'table-column-group', 'table-column', 'table-cell', 'table-caption', 'none'
+ ));
+ $this->info['visibility'] = new HTMLPurifier_AttrDef_Enum(array(
+ 'visible', 'hidden', 'collapse'
+ ));
+ $this->info['overflow'] = new HTMLPurifier_AttrDef_Enum(array('visible', 'hidden', 'auto', 'scroll'));
+ }
+
+ protected function doSetupTrusted($config) {
+ $this->info['position'] = new HTMLPurifier_AttrDef_Enum(array(
+ 'static', 'relative', 'absolute', 'fixed'
+ ));
+ $this->info['top'] =
+ $this->info['left'] =
+ $this->info['right'] =
+ $this->info['bottom'] = new HTMLPurifier_AttrDef_CSS_Composite(array(
+ new HTMLPurifier_AttrDef_CSS_Length(),
+ new HTMLPurifier_AttrDef_CSS_Percentage(),
+ new HTMLPurifier_AttrDef_Enum(array('auto')),
+ ));
+ $this->info['z-index'] = new HTMLPurifier_AttrDef_CSS_Composite(array(
+ new HTMLPurifier_AttrDef_Integer(),
+ new HTMLPurifier_AttrDef_Enum(array('auto')),
+ ));
+ }
+
+ /**
+ * Performs extra config-based processing. Based off of
+ * HTMLPurifier_HTMLDefinition.
+ * @todo Refactor duplicate elements into common class (probably using
+ * composition, not inheritance).
+ */
+ protected function setupConfigStuff($config) {
+
+ // setup allowed elements
+ $support = "(for information on implementing this, see the ".
+ "support forums) ";
+ $allowed_properties = $config->get('CSS.AllowedProperties');
+ if ($allowed_properties !== null) {
+ foreach ($this->info as $name => $d) {
+ if(!isset($allowed_properties[$name])) unset($this->info[$name]);
+ unset($allowed_properties[$name]);
+ }
+ // emit errors
+ foreach ($allowed_properties as $name => $d) {
+ // :TODO: Is this htmlspecialchars() call really necessary?
+ $name = htmlspecialchars($name);
+ trigger_error("Style attribute '$name' is not supported $support", E_USER_WARNING);
+ }
+ }
+
+ $forbidden_properties = $config->get('CSS.ForbiddenProperties');
+ if ($forbidden_properties !== null) {
+ foreach ($this->info as $name => $d) {
+ if (isset($forbidden_properties[$name])) {
+ unset($this->info[$name]);
+ }
+ }
+ }
+
+ }
+}
+
+
+
+
+
+/**
+ * Defines allowed child nodes and validates tokens against it.
+ */
+abstract class HTMLPurifier_ChildDef
+{
+ /**
+ * Type of child definition, usually right-most part of class name lowercase.
+ * Used occasionally in terms of context.
+ */
+ public $type;
+
+ /**
+ * Bool that indicates whether or not an empty array of children is okay
+ *
+ * This is necessary for redundant checking when changes affecting
+ * a child node may cause a parent node to now be disallowed.
+ */
+ public $allow_empty;
+
+ /**
+ * Lookup array of all elements that this definition could possibly allow
+ */
+ public $elements = array();
+
+ /**
+ * Get lookup of tag names that should not close this element automatically.
+ * All other elements will do so.
+ */
+ public function getAllowedElements($config) {
+ return $this->elements;
+ }
+
+ /**
+ * Validates nodes according to definition and returns modification.
+ *
+ * @param $tokens_of_children Array of HTMLPurifier_Token
+ * @param $config HTMLPurifier_Config object
+ * @param $context HTMLPurifier_Context object
+ * @return bool true to leave nodes as is
+ * @return bool false to remove parent node
+ * @return array of replacement child tokens
+ */
+ abstract public function validateChildren($tokens_of_children, $config, $context);
+}
+
+
+
+
+
+/**
+ * Configuration object that triggers customizable behavior.
+ *
+ * @warning This class is strongly defined: that means that the class
+ * will fail if an undefined directive is retrieved or set.
+ *
+ * @note Many classes that could (although many times don't) use the
+ * configuration object make it a mandatory parameter. This is
+ * because a configuration object should always be forwarded,
+ * otherwise, you run the risk of missing a parameter and then
+ * being stumped when a configuration directive doesn't work.
+ *
+ * @todo Reconsider some of the public member variables
+ */
+class HTMLPurifier_Config
+{
+
+ /**
+ * HTML Purifier's version
+ */
+ public $version = '4.5.0';
+
+ /**
+ * Bool indicator whether or not to automatically finalize
+ * the object if a read operation is done
+ */
+ public $autoFinalize = true;
+
+ // protected member variables
+
+ /**
+ * Namespace indexed array of serials for specific namespaces (see
+ * getSerial() for more info).
+ */
+ protected $serials = array();
+
+ /**
+ * Serial for entire configuration object
+ */
+ protected $serial;
+
+ /**
+ * Parser for variables
+ */
+ protected $parser = null;
+
+ /**
+ * Reference HTMLPurifier_ConfigSchema for value checking
+ * @note This is public for introspective purposes. Please don't
+ * abuse!
+ */
+ public $def;
+
+ /**
+ * Indexed array of definitions
+ */
+ protected $definitions;
+
+ /**
+ * Bool indicator whether or not config is finalized
+ */
+ protected $finalized = false;
+
+ /**
+ * Property list containing configuration directives.
+ */
+ protected $plist;
+
+ /**
+ * Whether or not a set is taking place due to an
+ * alias lookup.
+ */
+ private $aliasMode;
+
+ /**
+ * Set to false if you do not want line and file numbers in errors
+ * (useful when unit testing). This will also compress some errors
+ * and exceptions.
+ */
+ public $chatty = true;
+
+ /**
+ * Current lock; only gets to this namespace are allowed.
+ */
+ private $lock;
+
+ /**
+ * @param $definition HTMLPurifier_ConfigSchema that defines what directives
+ * are allowed.
+ */
+ public function __construct($definition, $parent = null) {
+ $parent = $parent ? $parent : $definition->defaultPlist;
+ $this->plist = new HTMLPurifier_PropertyList($parent);
+ $this->def = $definition; // keep a copy around for checking
+ $this->parser = new HTMLPurifier_VarParser_Flexible();
+ }
+
+ /**
+ * Convenience constructor that creates a config object based on a mixed var
+ * @param mixed $config Variable that defines the state of the config
+ * object. Can be: a HTMLPurifier_Config() object,
+ * an array of directives based on loadArray(),
+ * or a string filename of an ini file.
+ * @param HTMLPurifier_ConfigSchema Schema object
+ * @return Configured HTMLPurifier_Config object
+ */
+ public static function create($config, $schema = null) {
+ if ($config instanceof HTMLPurifier_Config) {
+ // pass-through
+ return $config;
+ }
+ if (!$schema) {
+ $ret = HTMLPurifier_Config::createDefault();
+ } else {
+ $ret = new HTMLPurifier_Config($schema);
+ }
+ if (is_string($config)) $ret->loadIni($config);
+ elseif (is_array($config)) $ret->loadArray($config);
+ return $ret;
+ }
+
+ /**
+ * Creates a new config object that inherits from a previous one.
+ * @param HTMLPurifier_Config $config Configuration object to inherit
+ * from.
+ * @return HTMLPurifier_Config object with $config as its parent.
+ */
+ public static function inherit(HTMLPurifier_Config $config) {
+ return new HTMLPurifier_Config($config->def, $config->plist);
+ }
+
+ /**
+ * Convenience constructor that creates a default configuration object.
+ * @return Default HTMLPurifier_Config object.
+ */
+ public static function createDefault() {
+ $definition = HTMLPurifier_ConfigSchema::instance();
+ $config = new HTMLPurifier_Config($definition);
+ return $config;
+ }
+
+ /**
+ * Retreives a value from the configuration.
+ * @param $key String key
+ */
+ public function get($key, $a = null) {
+ if ($a !== null) {
+ $this->triggerError("Using deprecated API: use \$config->get('$key.$a') instead", E_USER_WARNING);
+ $key = "$key.$a";
+ }
+ if (!$this->finalized) $this->autoFinalize();
+ if (!isset($this->def->info[$key])) {
+ // can't add % due to SimpleTest bug
+ $this->triggerError('Cannot retrieve value of undefined directive ' . htmlspecialchars($key),
+ E_USER_WARNING);
+ return;
+ }
+ if (isset($this->def->info[$key]->isAlias)) {
+ $d = $this->def->info[$key];
+ $this->triggerError('Cannot get value from aliased directive, use real name ' . $d->key,
+ E_USER_ERROR);
+ return;
+ }
+ if ($this->lock) {
+ list($ns) = explode('.', $key);
+ if ($ns !== $this->lock) {
+ $this->triggerError('Cannot get value of namespace ' . $ns . ' when lock for ' . $this->lock . ' is active, this probably indicates a Definition setup method is accessing directives that are not within its namespace', E_USER_ERROR);
+ return;
+ }
+ }
+ return $this->plist->get($key);
+ }
+
+ /**
+ * Retreives an array of directives to values from a given namespace
+ * @param $namespace String namespace
+ */
+ public function getBatch($namespace) {
+ if (!$this->finalized) $this->autoFinalize();
+ $full = $this->getAll();
+ if (!isset($full[$namespace])) {
+ $this->triggerError('Cannot retrieve undefined namespace ' . htmlspecialchars($namespace),
+ E_USER_WARNING);
+ return;
+ }
+ return $full[$namespace];
+ }
+
+ /**
+ * Returns a SHA-1 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 $namespace Namespace to get serial for
+ */
+ public function getBatchSerial($namespace) {
+ if (empty($this->serials[$namespace])) {
+ $batch = $this->getBatch($namespace);
+ unset($batch['DefinitionRev']);
+ $this->serials[$namespace] = sha1(serialize($batch));
+ }
+ return $this->serials[$namespace];
+ }
+
+ /**
+ * Returns a SHA-1 signature for the entire configuration object
+ * that uniquely identifies that particular configuration
+ */
+ public function getSerial() {
+ if (empty($this->serial)) {
+ $this->serial = sha1(serialize($this->getAll()));
+ }
+ return $this->serial;
+ }
+
+ /**
+ * Retrieves all directives, organized by namespace
+ * @warning This is a pretty inefficient function, avoid if you can
+ */
+ public function getAll() {
+ if (!$this->finalized) $this->autoFinalize();
+ $ret = array();
+ foreach ($this->plist->squash() as $name => $value) {
+ list($ns, $key) = explode('.', $name, 2);
+ $ret[$ns][$key] = $value;
+ }
+ return $ret;
+ }
+
+ /**
+ * Sets a value to configuration.
+ * @param $key String key
+ * @param $value Mixed value
+ */
+ public function set($key, $value, $a = null) {
+ if (strpos($key, '.') === false) {
+ $namespace = $key;
+ $directive = $value;
+ $value = $a;
+ $key = "$key.$directive";
+ $this->triggerError("Using deprecated API: use \$config->set('$key', ...) instead", E_USER_NOTICE);
+ } else {
+ list($namespace) = explode('.', $key);
+ }
+ if ($this->isFinalized('Cannot set directive after finalization')) return;
+ if (!isset($this->def->info[$key])) {
+ $this->triggerError('Cannot set undefined directive ' . htmlspecialchars($key) . ' to value',
+ E_USER_WARNING);
+ return;
+ }
+ $def = $this->def->info[$key];
+
+ if (isset($def->isAlias)) {
+ if ($this->aliasMode) {
+ $this->triggerError('Double-aliases not allowed, please fix '.
+ 'ConfigSchema bug with' . $key, E_USER_ERROR);
+ return;
+ }
+ $this->aliasMode = true;
+ $this->set($def->key, $value);
+ $this->aliasMode = false;
+ $this->triggerError("$key is an alias, preferred directive name is {$def->key}", E_USER_NOTICE);
+ return;
+ }
+
+ // Raw type might be negative when using the fully optimized form
+ // of stdclass, which indicates allow_null == true
+ $rtype = is_int($def) ? $def : $def->type;
+ if ($rtype < 0) {
+ $type = -$rtype;
+ $allow_null = true;
+ } else {
+ $type = $rtype;
+ $allow_null = isset($def->allow_null);
+ }
+
+ try {
+ $value = $this->parser->parse($value, $type, $allow_null);
+ } catch (HTMLPurifier_VarParserException $e) {
+ $this->triggerError('Value for ' . $key . ' is of invalid type, should be ' . HTMLPurifier_VarParser::getTypeName($type), E_USER_WARNING);
+ return;
+ }
+ if (is_string($value) && is_object($def)) {
+ // resolve value alias if defined
+ if (isset($def->aliases[$value])) {
+ $value = $def->aliases[$value];
+ }
+ // check to see if the value is allowed
+ if (isset($def->allowed) && !isset($def->allowed[$value])) {
+ $this->triggerError('Value not supported, valid values are: ' .
+ $this->_listify($def->allowed), E_USER_WARNING);
+ return;
+ }
+ }
+ $this->plist->set($key, $value);
+
+ // reset definitions if the directives they depend on changed
+ // this is a very costly process, so it's discouraged
+ // with finalization
+ if ($namespace == 'HTML' || $namespace == 'CSS' || $namespace == 'URI') {
+ $this->definitions[$namespace] = null;
+ }
+
+ $this->serials[$namespace] = false;
+ }
+
+ /**
+ * Convenience function for error reporting
+ */
+ private function _listify($lookup) {
+ $list = array();
+ foreach ($lookup as $name => $b) $list[] = $name;
+ return implode(', ', $list);
+ }
+
+ /**
+ * Retrieves object reference to the HTML definition.
+ * @param $raw Return a copy that has not been setup yet. Must be
+ * called before it's been setup, otherwise won't work.
+ * @param $optimized If true, this method may return null, to
+ * indicate that a cached version of the modified
+ * definition object is available and no further edits
+ * are necessary. Consider using
+ * maybeGetRawHTMLDefinition, which is more explicitly
+ * named, instead.
+ */
+ public function getHTMLDefinition($raw = false, $optimized = false) {
+ return $this->getDefinition('HTML', $raw, $optimized);
+ }
+
+ /**
+ * Retrieves object reference to the CSS definition
+ * @param $raw Return a copy that has not been setup yet. Must be
+ * called before it's been setup, otherwise won't work.
+ * @param $optimized If true, this method may return null, to
+ * indicate that a cached version of the modified
+ * definition object is available and no further edits
+ * are necessary. Consider using
+ * maybeGetRawCSSDefinition, which is more explicitly
+ * named, instead.
+ */
+ public function getCSSDefinition($raw = false, $optimized = false) {
+ return $this->getDefinition('CSS', $raw, $optimized);
+ }
+
+ /**
+ * Retrieves object reference to the URI definition
+ * @param $raw Return a copy that has not been setup yet. Must be
+ * called before it's been setup, otherwise won't work.
+ * @param $optimized If true, this method may return null, to
+ * indicate that a cached version of the modified
+ * definition object is available and no further edits
+ * are necessary. Consider using
+ * maybeGetRawURIDefinition, which is more explicitly
+ * named, instead.
+ */
+ public function getURIDefinition($raw = false, $optimized = false) {
+ return $this->getDefinition('URI', $raw, $optimized);
+ }
+
+ /**
+ * Retrieves a definition
+ * @param $type Type of definition: HTML, CSS, etc
+ * @param $raw Whether or not definition should be returned raw
+ * @param $optimized Only has an effect when $raw is true. Whether
+ * or not to return null if the result is already present in
+ * the cache. This is off by default for backwards
+ * compatibility reasons, but you need to do things this
+ * way in order to ensure that caching is done properly.
+ * Check out enduser-customize.html for more details.
+ * We probably won't ever change this default, as much as the
+ * maybe semantics is the "right thing to do."
+ */
+ public function getDefinition($type, $raw = false, $optimized = false) {
+ if ($optimized && !$raw) {
+ throw new HTMLPurifier_Exception("Cannot set optimized = true when raw = false");
+ }
+ if (!$this->finalized) $this->autoFinalize();
+ // temporarily suspend locks, so we can handle recursive definition calls
+ $lock = $this->lock;
+ $this->lock = null;
+ $factory = HTMLPurifier_DefinitionCacheFactory::instance();
+ $cache = $factory->create($type, $this);
+ $this->lock = $lock;
+ if (!$raw) {
+ // full definition
+ // ---------------
+ // check if definition is in memory
+ if (!empty($this->definitions[$type])) {
+ $def = $this->definitions[$type];
+ // check if the definition is setup
+ if ($def->setup) {
+ return $def;
+ } else {
+ $def->setup($this);
+ if ($def->optimized) $cache->add($def, $this);
+ return $def;
+ }
+ }
+ // check if definition is in cache
+ $def = $cache->get($this);
+ if ($def) {
+ // definition in cache, save to memory and return it
+ $this->definitions[$type] = $def;
+ return $def;
+ }
+ // initialize it
+ $def = $this->initDefinition($type);
+ // set it up
+ $this->lock = $type;
+ $def->setup($this);
+ $this->lock = null;
+ // save in cache
+ $cache->add($def, $this);
+ // return it
+ return $def;
+ } else {
+ // raw definition
+ // --------------
+ // check preconditions
+ $def = null;
+ if ($optimized) {
+ if (is_null($this->get($type . '.DefinitionID'))) {
+ // fatally error out if definition ID not set
+ throw new HTMLPurifier_Exception("Cannot retrieve raw version without specifying %$type.DefinitionID");
+ }
+ }
+ if (!empty($this->definitions[$type])) {
+ $def = $this->definitions[$type];
+ if ($def->setup && !$optimized) {
+ $extra = $this->chatty ? " (try moving this code block earlier in your initialization)" : "";
+ throw new HTMLPurifier_Exception("Cannot retrieve raw definition after it has already been setup" . $extra);
+ }
+ if ($def->optimized === null) {
+ $extra = $this->chatty ? " (try flushing your cache)" : "";
+ throw new HTMLPurifier_Exception("Optimization status of definition is unknown" . $extra);
+ }
+ if ($def->optimized !== $optimized) {
+ $msg = $optimized ? "optimized" : "unoptimized";
+ $extra = $this->chatty ? " (this backtrace is for the first inconsistent call, which was for a $msg raw definition)" : "";
+ throw new HTMLPurifier_Exception("Inconsistent use of optimized and unoptimized raw definition retrievals" . $extra);
+ }
+ }
+ // check if definition was in memory
+ if ($def) {
+ if ($def->setup) {
+ // invariant: $optimized === true (checked above)
+ return null;
+ } else {
+ return $def;
+ }
+ }
+ // if optimized, check if definition was in cache
+ // (because we do the memory check first, this formulation
+ // is prone to cache slamming, but I think
+ // guaranteeing that either /all/ of the raw
+ // setup code or /none/ of it is run is more important.)
+ if ($optimized) {
+ // This code path only gets run once; once we put
+ // something in $definitions (which is guaranteed by the
+ // trailing code), we always short-circuit above.
+ $def = $cache->get($this);
+ if ($def) {
+ // save the full definition for later, but don't
+ // return it yet
+ $this->definitions[$type] = $def;
+ return null;
+ }
+ }
+ // check invariants for creation
+ if (!$optimized) {
+ if (!is_null($this->get($type . '.DefinitionID'))) {
+ if ($this->chatty) {
+ $this->triggerError("Due to a documentation error in previous version of HTML Purifier, your definitions are not being cached. If this is OK, you can remove the %$type.DefinitionRev and %$type.DefinitionID declaration. Otherwise, modify your code to use maybeGetRawDefinition, and test if the returned value is null before making any edits (if it is null, that means that a cached version is available, and no raw operations are necessary). See Customize for more details", E_USER_WARNING);
+ } else {
+ $this->triggerError("Useless DefinitionID declaration", E_USER_WARNING);
+ }
+ }
+ }
+ // initialize it
+ $def = $this->initDefinition($type);
+ $def->optimized = $optimized;
+ return $def;
+ }
+ throw new HTMLPurifier_Exception("The impossible happened!");
+ }
+
+ private function initDefinition($type) {
+ // quick checks failed, let's create the object
+ if ($type == 'HTML') {
+ $def = new HTMLPurifier_HTMLDefinition();
+ } elseif ($type == 'CSS') {
+ $def = new HTMLPurifier_CSSDefinition();
+ } elseif ($type == 'URI') {
+ $def = new HTMLPurifier_URIDefinition();
+ } else {
+ throw new HTMLPurifier_Exception("Definition of $type type not supported");
+ }
+ $this->definitions[$type] = $def;
+ return $def;
+ }
+
+ public function maybeGetRawDefinition($name) {
+ return $this->getDefinition($name, true, true);
+ }
+
+ public function maybeGetRawHTMLDefinition() {
+ return $this->getDefinition('HTML', true, true);
+ }
+
+ public function maybeGetRawCSSDefinition() {
+ return $this->getDefinition('CSS', true, true);
+ }
+
+ public function maybeGetRawURIDefinition() {
+ return $this->getDefinition('URI', true, true);
+ }
+
+ /**
+ * Loads configuration values from an array with the following structure:
+ * Namespace.Directive => Value
+ * @param $config_array Configuration associative array
+ */
+ public function loadArray($config_array) {
+ if ($this->isFinalized('Cannot load directives after finalization')) return;
+ foreach ($config_array as $key => $value) {
+ $key = str_replace('_', '.', $key);
+ if (strpos($key, '.') !== false) {
+ $this->set($key, $value);
+ } else {
+ $namespace = $key;
+ $namespace_values = $value;
+ foreach ($namespace_values as $directive => $value) {
+ $this->set($namespace .'.'. $directive, $value);
+ }
+ }
+ }
+ }
+
+ /**
+ * 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 $allowed List of allowed namespaces/directives
+ */
+ public static function getAllowedDirectivesForForm($allowed, $schema = null) {
+ if (!$schema) {
+ $schema = HTMLPurifier_ConfigSchema::instance();
+ }
+ if ($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 $key => $def) {
+ list($ns, $directive) = explode('.', $key, 2);
+ if ($allowed !== true) {
+ if (isset($blacklisted_directives["$ns.$directive"])) continue;
+ if (!isset($allowed_directives["$ns.$directive"]) && !isset($allowed_ns[$ns])) continue;
+ }
+ if (isset($def->isAlias)) continue;
+ if ($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
+ * @param $schema Instance of HTMLPurifier_ConfigSchema to use, if not global copy
+ */
+ public static function loadArrayFromForm($array, $index = false, $allowed = true, $mq_fix = true, $schema = null) {
+ $ret = HTMLPurifier_Config::prepareArrayFromForm($array, $index, $allowed, $mq_fix, $schema);
+ $config = HTMLPurifier_Config::create($ret, $schema);
+ return $config;
+ }
+
+ /**
+ * Merges in configuration values from $_GET/$_POST to object. NOT STATIC.
+ * @note Same parameters as loadArrayFromForm
+ */
+ public function mergeArrayFromForm($array, $index = false, $allowed = true, $mq_fix = true) {
+ $ret = HTMLPurifier_Config::prepareArrayFromForm($array, $index, $allowed, $mq_fix, $this->def);
+ $this->loadArray($ret);
+ }
+
+ /**
+ * Prepares an array from a form into something usable for the more
+ * strict parts of HTMLPurifier_Config
+ */
+ public static function prepareArrayFromForm($array, $index = false, $allowed = true, $mq_fix = true, $schema = null) {
+ if ($index !== false) $array = (isset($array[$index]) && is_array($array[$index])) ? $array[$index] : array();
+ $mq = $mq_fix && function_exists('get_magic_quotes_gpc') && get_magic_quotes_gpc();
+
+ $allowed = HTMLPurifier_Config::getAllowedDirectivesForForm($allowed, $schema);
+ $ret = array();
+ foreach ($allowed as $key) {
+ list($ns, $directive) = $key;
+ $skey = "$ns.$directive";
+ if (!empty($array["Null_$skey"])) {
+ $ret[$ns][$directive] = null;
+ continue;
+ }
+ if (!isset($array[$skey])) continue;
+ $value = $mq ? stripslashes($array[$skey]) : $array[$skey];
+ $ret[$ns][$directive] = $value;
+ }
+ return $ret;
+ }
+
+ /**
+ * Loads configuration values from an ini file
+ * @param $filename Name of ini file
+ */
+ public function loadIni($filename) {
+ if ($this->isFinalized('Cannot load directives after finalization')) return;
+ $array = parse_ini_file($filename, true);
+ $this->loadArray($array);
+ }
+
+ /**
+ * Checks whether or not the configuration object is finalized.
+ * @param $error String error message, or false for no error
+ */
+ public function isFinalized($error = false) {
+ if ($this->finalized && $error) {
+ $this->triggerError($error, E_USER_ERROR);
+ }
+ return $this->finalized;
+ }
+
+ /**
+ * Finalizes configuration only if auto finalize is on and not
+ * already finalized
+ */
+ public function autoFinalize() {
+ if ($this->autoFinalize) {
+ $this->finalize();
+ } else {
+ $this->plist->squash(true);
+ }
+ }
+
+ /**
+ * Finalizes a configuration object, prohibiting further change
+ */
+ public function finalize() {
+ $this->finalized = true;
+ $this->parser = null;
+ }
+
+ /**
+ * Produces a nicely formatted error message by supplying the
+ * stack frame information OUTSIDE of HTMLPurifier_Config.
+ */
+ protected function triggerError($msg, $no) {
+ // determine previous stack frame
+ $extra = '';
+ if ($this->chatty) {
+ $trace = debug_backtrace();
+ // zip(tail(trace), trace) -- but PHP is not Haskell har har
+ for ($i = 0, $c = count($trace); $i < $c - 1; $i++) {
+ // XXX this is not correct on some versions of HTML Purifier
+ if ($trace[$i + 1]['class'] === 'HTMLPurifier_Config') {
+ continue;
+ }
+ $frame = $trace[$i];
+ $extra = " invoked on line {$frame['line']} in file {$frame['file']}";
+ break;
+ }
+ }
+ trigger_error($msg . $extra, $no);
+ }
+
+ /**
+ * Returns a serialized form of the configuration object that can
+ * be reconstituted.
+ */
+ public function serialize() {
+ $this->getDefinition('HTML');
+ $this->getDefinition('CSS');
+ $this->getDefinition('URI');
+ return serialize($this);
+ }
+
+}
+
+
+
+
+
+/**
+ * Configuration definition, defines directives and their defaults.
+ */
+class HTMLPurifier_ConfigSchema {
+
+ /**
+ * Defaults of the directives and namespaces.
+ * @note This shares the exact same structure as HTMLPurifier_Config::$conf
+ */
+ public $defaults = array();
+
+ /**
+ * The default property list. Do not edit this property list.
+ */
+ public $defaultPlist;
+
+ /**
+ * Definition of the directives. The structure of this is:
+ *
+ * array(
+ * 'Namespace' => array(
+ * 'Directive' => new stdclass(),
+ * )
+ * )
+ *
+ * The stdclass may have the following properties:
+ *
+ * - If isAlias isn't set:
+ * - type: Integer type of directive, see HTMLPurifier_VarParser for definitions
+ * - allow_null: If set, this directive allows null values
+ * - aliases: If set, an associative array of value aliases to real values
+ * - allowed: If set, a lookup array of allowed (string) values
+ * - If isAlias is set:
+ * - namespace: Namespace this directive aliases to
+ * - name: Directive name this directive aliases to
+ *
+ * In certain degenerate cases, stdclass will actually be an integer. In
+ * that case, the value is equivalent to an stdclass with the type
+ * property set to the integer. If the integer is negative, type is
+ * equal to the absolute value of integer, and allow_null is true.
+ *
+ * This class is friendly with HTMLPurifier_Config. If you need introspection
+ * about the schema, you're better of using the ConfigSchema_Interchange,
+ * which uses more memory but has much richer information.
+ */
+ public $info = array();
+
+ /**
+ * Application-wide singleton
+ */
+ static protected $singleton;
+
+ public function __construct() {
+ $this->defaultPlist = new HTMLPurifier_PropertyList();
+ }
+
+ /**
+ * Unserializes the default ConfigSchema.
+ */
+ public static function makeFromSerial() {
+ $contents = file_get_contents(HTMLPURIFIER_PREFIX . '/HTMLPurifier/ConfigSchema/schema.ser');
+ $r = unserialize($contents);
+ if (!$r) {
+ $hash = sha1($contents);
+ trigger_error("Unserialization of configuration schema failed, sha1 of file was $hash", E_USER_ERROR);
+ }
+ return $r;
+ }
+
+ /**
+ * Retrieves an instance of the application-wide configuration definition.
+ */
+ public static function instance($prototype = null) {
+ if ($prototype !== null) {
+ HTMLPurifier_ConfigSchema::$singleton = $prototype;
+ } elseif (HTMLPurifier_ConfigSchema::$singleton === null || $prototype === true) {
+ HTMLPurifier_ConfigSchema::$singleton = HTMLPurifier_ConfigSchema::makeFromSerial();
+ }
+ return HTMLPurifier_ConfigSchema::$singleton;
+ }
+
+ /**
+ * Defines a directive for configuration
+ * @warning Will fail of directive's namespace is defined.
+ * @warning This method's signature is slightly different from the legacy
+ * define() static method! Beware!
+ * @param $namespace Namespace the directive is in
+ * @param $name Key of directive
+ * @param $default Default value of directive
+ * @param $type Allowed type of the directive. See
+ * HTMLPurifier_DirectiveDef::$type for allowed values
+ * @param $allow_null Whether or not to allow null values
+ */
+ public function add($key, $default, $type, $allow_null) {
+ $obj = new stdclass();
+ $obj->type = is_int($type) ? $type : HTMLPurifier_VarParser::$types[$type];
+ if ($allow_null) $obj->allow_null = true;
+ $this->info[$key] = $obj;
+ $this->defaults[$key] = $default;
+ $this->defaultPlist->set($key, $default);
+ }
+
+ /**
+ * Defines a directive value alias.
+ *
+ * Directive value aliases are convenient for developers because it lets
+ * them set a directive to several values and get the same result.
+ * @param $namespace Directive's namespace
+ * @param $name Name of Directive
+ * @param $aliases Hash of aliased values to the real alias
+ */
+ public function addValueAliases($key, $aliases) {
+ if (!isset($this->info[$key]->aliases)) {
+ $this->info[$key]->aliases = array();
+ }
+ foreach ($aliases as $alias => $real) {
+ $this->info[$key]->aliases[$alias] = $real;
+ }
+ }
+
+ /**
+ * Defines a set of allowed values for a directive.
+ * @warning This is slightly different from the corresponding static
+ * method definition.
+ * @param $namespace Namespace of directive
+ * @param $name Name of directive
+ * @param $allowed Lookup array of allowed values
+ */
+ public function addAllowedValues($key, $allowed) {
+ $this->info[$key]->allowed = $allowed;
+ }
+
+ /**
+ * Defines a directive alias for backwards compatibility
+ * @param $namespace
+ * @param $name Directive that will be aliased
+ * @param $new_namespace
+ * @param $new_name Directive that the alias will be to
+ */
+ public function addAlias($key, $new_key) {
+ $obj = new stdclass;
+ $obj->key = $new_key;
+ $obj->isAlias = true;
+ $this->info[$key] = $obj;
+ }
+
+ /**
+ * Replaces any stdclass that only has the type property with type integer.
+ */
+ public function postProcess() {
+ foreach ($this->info as $key => $v) {
+ if (count((array) $v) == 1) {
+ $this->info[$key] = $v->type;
+ } elseif (count((array) $v) == 2 && isset($v->allow_null)) {
+ $this->info[$key] = -$v->type;
+ }
+ }
+ }
+
+}
+
+
+
+
+
+/**
+ * @todo Unit test
+ */
+class HTMLPurifier_ContentSets
+{
+
+ /**
+ * List of content set strings (pipe seperators) indexed by name.
+ */
+ public $info = array();
+
+ /**
+ * List of content set lookups (element => true) indexed by name.
+ * @note This is in HTMLPurifier_HTMLDefinition->info_content_sets
+ */
+ public $lookup = array();
+
+ /**
+ * Synchronized list of defined content sets (keys of info)
+ */
+ protected $keys = array();
+ /**
+ * Synchronized list of defined content values (values of info)
+ */
+ protected $values = array();
+
+ /**
+ * Merges in module's content sets, expands identifiers in the content
+ * sets and populates the keys, values and lookup member variables.
+ * @param $modules List of HTMLPurifier_HTMLModule
+ */
+ public function __construct($modules) {
+ if (!is_array($modules)) $modules = array($modules);
+ // populate content_sets based on module hints
+ // sorry, no way of overloading
+ foreach ($modules as $module_i => $module) {
+ foreach ($module->content_sets as $key => $value) {
+ $temp = $this->convertToLookup($value);
+ if (isset($this->lookup[$key])) {
+ // add it into the existing content set
+ $this->lookup[$key] = array_merge($this->lookup[$key], $temp);
+ } else {
+ $this->lookup[$key] = $temp;
+ }
+ }
+ }
+ $old_lookup = false;
+ while ($old_lookup !== $this->lookup) {
+ $old_lookup = $this->lookup;
+ foreach ($this->lookup as $i => $set) {
+ $add = array();
+ foreach ($set as $element => $x) {
+ if (isset($this->lookup[$element])) {
+ $add += $this->lookup[$element];
+ unset($this->lookup[$i][$element]);
+ }
+ }
+ $this->lookup[$i] += $add;
+ }
+ }
+
+ foreach ($this->lookup as $key => $lookup) {
+ $this->info[$key] = implode(' | ', array_keys($lookup));
+ }
+ $this->keys = array_keys($this->info);
+ $this->values = array_values($this->info);
+ }
+
+ /**
+ * Accepts a definition; generates and assigns a ChildDef for it
+ * @param $def HTMLPurifier_ElementDef reference
+ * @param $module Module that defined the ElementDef
+ */
+ public function generateChildDef(&$def, $module) {
+ if (!empty($def->child)) return; // already done!
+ $content_model = $def->content_model;
+ if (is_string($content_model)) {
+ // Assume that $this->keys is alphanumeric
+ $def->content_model = preg_replace_callback(
+ '/\b(' . implode('|', $this->keys) . ')\b/',
+ array($this, 'generateChildDefCallback'),
+ $content_model
+ );
+ //$def->content_model = str_replace(
+ // $this->keys, $this->values, $content_model);
+ }
+ $def->child = $this->getChildDef($def, $module);
+ }
+
+ public function generateChildDefCallback($matches) {
+ return $this->info[$matches[0]];
+ }
+
+ /**
+ * Instantiates a ChildDef based on content_model and content_model_type
+ * member variables in HTMLPurifier_ElementDef
+ * @note This will also defer to modules for custom HTMLPurifier_ChildDef
+ * subclasses that need content set expansion
+ * @param $def HTMLPurifier_ElementDef to have ChildDef extracted
+ * @return HTMLPurifier_ChildDef corresponding to ElementDef
+ */
+ public function getChildDef($def, $module) {
+ $value = $def->content_model;
+ if (is_object($value)) {
+ trigger_error(
+ 'Literal object child definitions should be stored in '.
+ 'ElementDef->child not ElementDef->content_model',
+ E_USER_NOTICE
+ );
+ return $value;
+ }
+ switch ($def->content_model_type) {
+ case 'required':
+ return new HTMLPurifier_ChildDef_Required($value);
+ case 'optional':
+ return new HTMLPurifier_ChildDef_Optional($value);
+ case 'empty':
+ return new HTMLPurifier_ChildDef_Empty();
+ case 'custom':
+ return new HTMLPurifier_ChildDef_Custom($value);
+ }
+ // defer to its module
+ $return = false;
+ if ($module->defines_child_def) { // save a func call
+ $return = $module->getChildDef($def);
+ }
+ if ($return !== false) return $return;
+ // error-out
+ trigger_error(
+ 'Could not determine which ChildDef class to instantiate',
+ E_USER_ERROR
+ );
+ return false;
+ }
+
+ /**
+ * Converts a string list of elements separated by pipes into
+ * a lookup array.
+ * @param $string List of elements
+ * @return Lookup array of elements
+ */
+ protected function convertToLookup($string) {
+ $array = explode('|', str_replace(' ', '', $string));
+ $ret = array();
+ foreach ($array as $i => $k) {
+ $ret[$k] = true;
+ }
+ return $ret;
+ }
+
+}
+
+
+
+
+
+/**
+ * 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.
+ * @note Since the variables Context deals with may not be objects,
+ * references are very important here! Do not remove!
+ */
+class HTMLPurifier_Context
+{
+
+ /**
+ * Private array that stores the references.
+ */
+ private $_storage = array();
+
+ /**
+ * Registers a variable into the context.
+ * @param $name String name
+ * @param $ref Reference to variable to be registered
+ */
+ public function register($name, &$ref) {
+ if (isset($this->_storage[$name])) {
+ trigger_error("Name $name produces collision, cannot re-register",
+ E_USER_ERROR);
+ return;
+ }
+ $this->_storage[$name] =& $ref;
+ }
+
+ /**
+ * Retrieves a variable reference from the context.
+ * @param $name String name
+ * @param $ignore_error Boolean whether or not to ignore error
+ */
+ public function &get($name, $ignore_error = false) {
+ if (!isset($this->_storage[$name])) {
+ if (!$ignore_error) {
+ trigger_error("Attempted to retrieve non-existent variable $name",
+ E_USER_ERROR);
+ }
+ $var = null; // so we can return by reference
+ return $var;
+ }
+ return $this->_storage[$name];
+ }
+
+ /**
+ * Destorys a variable in the context.
+ * @param $name String name
+ */
+ public function destroy($name) {
+ if (!isset($this->_storage[$name])) {
+ trigger_error("Attempted to destroy non-existent variable $name",
+ E_USER_ERROR);
+ return;
+ }
+ unset($this->_storage[$name]);
+ }
+
+ /**
+ * Checks whether or not the variable exists.
+ * @param $name String name
+ */
+ public function exists($name) {
+ return isset($this->_storage[$name]);
+ }
+
+ /**
+ * Loads a series of variables from an associative array
+ * @param $context_array Assoc array of variables to load
+ */
+ public function loadArray($context_array) {
+ foreach ($context_array as $key => $discard) {
+ $this->register($key, $context_array[$key]);
+ }
+ }
+
+}
+
+
+
+
+
+/**
+ * Abstract class representing Definition cache managers that implements
+ * useful common methods and is a factory.
+ * @todo Create a separate maintenance file advanced users can use to
+ * cache their custom HTMLDefinition, which can be loaded
+ * via a configuration directive
+ * @todo Implement memcached
+ */
+abstract class HTMLPurifier_DefinitionCache
+{
+
+ public $type;
+
+ /**
+ * @param $name Type of definition objects this instance of the
+ * cache will handle.
+ */
+ public function __construct($type) {
+ $this->type = $type;
+ }
+
+ /**
+ * Generates a unique identifier for a particular configuration
+ * @param Instance of HTMLPurifier_Config
+ */
+ public function generateKey($config) {
+ return $config->version . ',' . // possibly replace with function calls
+ $config->getBatchSerial($this->type) . ',' .
+ $config->get($this->type . '.DefinitionRev');
+ }
+
+ /**
+ * Tests whether or not a key is old with respect to the configuration's
+ * version and revision number.
+ * @param $key Key to test
+ * @param $config Instance of HTMLPurifier_Config to test against
+ */
+ public function isOld($key, $config) {
+ if (substr_count($key, ',') < 2) return true;
+ list($version, $hash, $revision) = explode(',', $key, 3);
+ $compare = version_compare($version, $config->version);
+ // version mismatch, is always old
+ if ($compare != 0) return true;
+ // versions match, ids match, check revision number
+ if (
+ $hash == $config->getBatchSerial($this->type) &&
+ $revision < $config->get($this->type . '.DefinitionRev')
+ ) return true;
+ return false;
+ }
+
+ /**
+ * Checks if a definition's type jives with the cache's type
+ * @note Throws an error on failure
+ * @param $def Definition object to check
+ * @return Boolean true if good, false if not
+ */
+ public function checkDefType($def) {
+ if ($def->type !== $this->type) {
+ trigger_error("Cannot use definition of type {$def->type} in cache for {$this->type}");
+ return false;
+ }
+ return true;
+ }
+
+ /**
+ * Adds a definition object to the cache
+ */
+ abstract public function add($def, $config);
+
+ /**
+ * Unconditionally saves a definition object to the cache
+ */
+ abstract public function set($def, $config);
+
+ /**
+ * Replace an object in the cache
+ */
+ abstract public function replace($def, $config);
+
+ /**
+ * Retrieves a definition object from the cache
+ */
+ abstract public function get($config);
+
+ /**
+ * Removes a definition object to the cache
+ */
+ abstract public function remove($config);
+
+ /**
+ * Clears all objects from cache
+ */
+ abstract public function flush($config);
+
+ /**
+ * Clears all expired (older version or revision) objects from cache
+ * @note Be carefuly implementing this method as flush. Flush must
+ * not interfere with other Definition types, and cleanup()
+ * should not be repeatedly called by userland code.
+ */
+ abstract public function cleanup($config);
+
+}
+
+
+
+
+
+/**
+ * Responsible for creating definition caches.
+ */
+class HTMLPurifier_DefinitionCacheFactory
+{
+
+ protected $caches = array('Serializer' => array());
+ protected $implementations = array();
+ protected $decorators = array();
+
+ /**
+ * Initialize default decorators
+ */
+ public function setup() {
+ $this->addDecorator('Cleanup');
+ }
+
+ /**
+ * Retrieves an instance of global definition cache factory.
+ */
+ public static function instance($prototype = null) {
+ static $instance;
+ if ($prototype !== null) {
+ $instance = $prototype;
+ } elseif ($instance === null || $prototype === true) {
+ $instance = new HTMLPurifier_DefinitionCacheFactory();
+ $instance->setup();
+ }
+ return $instance;
+ }
+
+ /**
+ * Registers a new definition cache object
+ * @param $short Short name of cache object, for reference
+ * @param $long Full class name of cache object, for construction
+ */
+ public function register($short, $long) {
+ $this->implementations[$short] = $long;
+ }
+
+ /**
+ * Factory method that creates a cache object based on configuration
+ * @param $name Name of definitions handled by cache
+ * @param $config Instance of HTMLPurifier_Config
+ */
+ public function create($type, $config) {
+ $method = $config->get('Cache.DefinitionImpl');
+ if ($method === null) {
+ return new HTMLPurifier_DefinitionCache_Null($type);
+ }
+ if (!empty($this->caches[$method][$type])) {
+ return $this->caches[$method][$type];
+ }
+ if (
+ isset($this->implementations[$method]) &&
+ class_exists($class = $this->implementations[$method], false)
+ ) {
+ $cache = new $class($type);
+ } else {
+ if ($method != 'Serializer') {
+ trigger_error("Unrecognized DefinitionCache $method, using Serializer instead", E_USER_WARNING);
+ }
+ $cache = new HTMLPurifier_DefinitionCache_Serializer($type);
+ }
+ foreach ($this->decorators as $decorator) {
+ $new_cache = $decorator->decorate($cache);
+ // prevent infinite recursion in PHP 4
+ unset($cache);
+ $cache = $new_cache;
+ }
+ $this->caches[$method][$type] = $cache;
+ return $this->caches[$method][$type];
+ }
+
+ /**
+ * Registers a decorator to add to all new cache objects
+ * @param
+ */
+ public function addDecorator($decorator) {
+ if (is_string($decorator)) {
+ $class = "HTMLPurifier_DefinitionCache_Decorator_$decorator";
+ $decorator = new $class;
+ }
+ $this->decorators[$decorator->name] = $decorator;
+ }
+
+}
+
+
+
+
+
+/**
+ * Represents a document type, contains information on which modules
+ * need to be loaded.
+ * @note This class is inspected by Printer_HTMLDefinition->renderDoctype.
+ * If structure changes, please update that function.
+ */
+class HTMLPurifier_Doctype
+{
+ /**
+ * Full name of doctype
+ */
+ public $name;
+
+ /**
+ * List of standard modules (string identifiers or literal objects)
+ * that this doctype uses
+ */
+ public $modules = array();
+
+ /**
+ * List of modules to use for tidying up code
+ */
+ public $tidyModules = array();
+
+ /**
+ * Is the language derived from XML (i.e. XHTML)?
+ */
+ public $xml = true;
+
+ /**
+ * List of aliases for this doctype
+ */
+ public $aliases = array();
+
+ /**
+ * Public DTD identifier
+ */
+ public $dtdPublic;
+
+ /**
+ * System DTD identifier
+ */
+ public $dtdSystem;
+
+ public function __construct($name = null, $xml = true, $modules = array(),
+ $tidyModules = array(), $aliases = array(), $dtd_public = null, $dtd_system = null
+ ) {
+ $this->name = $name;
+ $this->xml = $xml;
+ $this->modules = $modules;
+ $this->tidyModules = $tidyModules;
+ $this->aliases = $aliases;
+ $this->dtdPublic = $dtd_public;
+ $this->dtdSystem = $dtd_system;
+ }
+}
+
+
+
+
+
+class HTMLPurifier_DoctypeRegistry
+{
+
+ /**
+ * Hash of doctype names to doctype objects
+ */
+ protected $doctypes;
+
+ /**
+ * Lookup table of aliases to real doctype names
+ */
+ protected $aliases;
+
+ /**
+ * Registers a doctype to the registry
+ * @note Accepts a fully-formed doctype object, or the
+ * parameters for constructing a doctype object
+ * @param $doctype Name of doctype or literal doctype object
+ * @param $modules Modules doctype will load
+ * @param $modules_for_modes Modules doctype will load for certain modes
+ * @param $aliases Alias names for doctype
+ * @return Editable registered doctype
+ */
+ public function register($doctype, $xml = true, $modules = array(),
+ $tidy_modules = array(), $aliases = array(), $dtd_public = null, $dtd_system = null
+ ) {
+ if (!is_array($modules)) $modules = array($modules);
+ if (!is_array($tidy_modules)) $tidy_modules = array($tidy_modules);
+ if (!is_array($aliases)) $aliases = array($aliases);
+ if (!is_object($doctype)) {
+ $doctype = new HTMLPurifier_Doctype(
+ $doctype, $xml, $modules, $tidy_modules, $aliases, $dtd_public, $dtd_system
+ );
+ }
+ $this->doctypes[$doctype->name] = $doctype;
+ $name = $doctype->name;
+ // hookup aliases
+ foreach ($doctype->aliases as $alias) {
+ if (isset($this->doctypes[$alias])) continue;
+ $this->aliases[$alias] = $name;
+ }
+ // remove old aliases
+ if (isset($this->aliases[$name])) unset($this->aliases[$name]);
+ return $doctype;
+ }
+
+ /**
+ * Retrieves reference to a doctype of a certain name
+ * @note This function resolves aliases
+ * @note When possible, use the more fully-featured make()
+ * @param $doctype Name of doctype
+ * @return Editable doctype object
+ */
+ public function get($doctype) {
+ if (isset($this->aliases[$doctype])) $doctype = $this->aliases[$doctype];
+ if (!isset($this->doctypes[$doctype])) {
+ trigger_error('Doctype ' . htmlspecialchars($doctype) . ' does not exist', E_USER_ERROR);
+ $anon = new HTMLPurifier_Doctype($doctype);
+ return $anon;
+ }
+ return $this->doctypes[$doctype];
+ }
+
+ /**
+ * Creates a doctype based on a configuration object,
+ * will perform initialization on the doctype
+ * @note Use this function to get a copy of doctype that config
+ * can hold on to (this is necessary in order to tell
+ * Generator whether or not the current document is XML
+ * based or not).
+ */
+ public function make($config) {
+ return clone $this->get($this->getDoctypeFromConfig($config));
+ }
+
+ /**
+ * Retrieves the doctype from the configuration object
+ */
+ public function getDoctypeFromConfig($config) {
+ // recommended test
+ $doctype = $config->get('HTML.Doctype');
+ if (!empty($doctype)) return $doctype;
+ $doctype = $config->get('HTML.CustomDoctype');
+ if (!empty($doctype)) return $doctype;
+ // backwards-compatibility
+ if ($config->get('HTML.XHTML')) {
+ $doctype = 'XHTML 1.0';
+ } else {
+ $doctype = 'HTML 4.01';
+ }
+ if ($config->get('HTML.Strict')) {
+ $doctype .= ' Strict';
+ } else {
+ $doctype .= ' Transitional';
+ }
+ return $doctype;
+ }
+
+}
+
+
+
+
+
+/**
+ * Structure that stores an HTML element definition. Used by
+ * HTMLPurifier_HTMLDefinition and HTMLPurifier_HTMLModule.
+ * @note This class is inspected by HTMLPurifier_Printer_HTMLDefinition.
+ * Please update that class too.
+ * @warning If you add new properties to this class, you MUST update
+ * the mergeIn() method.
+ */
+class HTMLPurifier_ElementDef
+{
+
+ /**
+ * Does the definition work by itself, or is it created solely
+ * for the purpose of merging into another definition?
+ */
+ public $standalone = true;
+
+ /**
+ * Associative array of attribute name to HTMLPurifier_AttrDef
+ * @note Before being processed by HTMLPurifier_AttrCollections
+ * when modules are finalized during
+ * HTMLPurifier_HTMLDefinition->setup(), this array may also
+ * contain an array at index 0 that indicates which attribute
+ * collections to load into the full array. It may also
+ * contain string indentifiers in lieu of HTMLPurifier_AttrDef,
+ * see HTMLPurifier_AttrTypes on how they are expanded during
+ * HTMLPurifier_HTMLDefinition->setup() processing.
+ */
+ public $attr = array();
+
+ // XXX: Design note: currently, it's not possible to override
+ // previously defined AttrTransforms without messing around with
+ // the final generated config. This is by design; a previous version
+ // used an associated list of attr_transform, but it was extremely
+ // easy to accidentally override other attribute transforms by
+ // forgetting to specify an index (and just using 0.) While we
+ // could check this by checking the index number and complaining,
+ // there is a second problem which is that it is not at all easy to
+ // tell when something is getting overridden. Combine this with a
+ // codebase where this isn't really being used, and it's perfect for
+ // nuking.
+
+ /**
+ * List of tags HTMLPurifier_AttrTransform to be done before validation
+ */
+ public $attr_transform_pre = array();
+
+ /**
+ * List of tags HTMLPurifier_AttrTransform to be done after validation
+ */
+ public $attr_transform_post = array();
+
+ /**
+ * HTMLPurifier_ChildDef of this tag.
+ */
+ public $child;
+
+ /**
+ * Abstract string representation of internal ChildDef rules. See
+ * HTMLPurifier_ContentSets for how this is parsed and then transformed
+ * into an HTMLPurifier_ChildDef.
+ * @warning This is a temporary variable that is not available after
+ * being processed by HTMLDefinition
+ */
+ public $content_model;
+
+ /**
+ * Value of $child->type, used to determine which ChildDef to use,
+ * used in combination with $content_model.
+ * @warning This must be lowercase
+ * @warning This is a temporary variable that is not available after
+ * being processed by HTMLDefinition
+ */
+ public $content_model_type;
+
+
+
+ /**
+ * Does the element have a content model (#PCDATA | Inline)*? This
+ * is important for chameleon ins and del processing in
+ * HTMLPurifier_ChildDef_Chameleon. Dynamically set: modules don't
+ * have to worry about this one.
+ */
+ public $descendants_are_inline = false;
+
+ /**
+ * List of the names of required attributes this element has. Dynamically
+ * populated by HTMLPurifier_HTMLDefinition::getElement
+ */
+ public $required_attr = array();
+
+ /**
+ * Lookup table of tags excluded from all descendants of this tag.
+ * @note SGML permits exclusions for all descendants, but this is
+ * not possible with DTDs or XML Schemas. W3C has elected to
+ * use complicated compositions of content_models to simulate
+ * exclusion for children, but we go the simpler, SGML-style
+ * route of flat-out exclusions, which correctly apply to
+ * all descendants and not just children. Note that the XHTML
+ * Modularization Abstract Modules are blithely unaware of such
+ * distinctions.
+ */
+ public $excludes = array();
+
+ /**
+ * This tag is explicitly auto-closed by the following tags.
+ */
+ public $autoclose = array();
+
+ /**
+ * If a foreign element is found in this element, test if it is
+ * allowed by this sub-element; if it is, instead of closing the
+ * current element, place it inside this element.
+ */
+ public $wrap;
+
+ /**
+ * Whether or not this is a formatting element affected by the
+ * "Active Formatting Elements" algorithm.
+ */
+ public $formatting;
+
+ /**
+ * Low-level factory constructor for creating new standalone element defs
+ */
+ public static function create($content_model, $content_model_type, $attr) {
+ $def = new HTMLPurifier_ElementDef();
+ $def->content_model = $content_model;
+ $def->content_model_type = $content_model_type;
+ $def->attr = $attr;
+ return $def;
+ }
+
+ /**
+ * Merges the values of another element definition into this one.
+ * Values from the new element def take precedence if a value is
+ * not mergeable.
+ */
+ public function mergeIn($def) {
+
+ // later keys takes precedence
+ foreach($def->attr as $k => $v) {
+ if ($k === 0) {
+ // merge in the includes
+ // sorry, no way to override an include
+ foreach ($v as $v2) {
+ $this->attr[0][] = $v2;
+ }
+ continue;
+ }
+ if ($v === false) {
+ if (isset($this->attr[$k])) unset($this->attr[$k]);
+ continue;
+ }
+ $this->attr[$k] = $v;
+ }
+ $this->_mergeAssocArray($this->excludes, $def->excludes);
+ $this->attr_transform_pre = array_merge($this->attr_transform_pre, $def->attr_transform_pre);
+ $this->attr_transform_post = array_merge($this->attr_transform_post, $def->attr_transform_post);
+
+ if(!empty($def->content_model)) {
+ $this->content_model =
+ str_replace("#SUPER", $this->content_model, $def->content_model);
+ $this->child = false;
+ }
+ if(!empty($def->content_model_type)) {
+ $this->content_model_type = $def->content_model_type;
+ $this->child = false;
+ }
+ if(!is_null($def->child)) $this->child = $def->child;
+ if(!is_null($def->formatting)) $this->formatting = $def->formatting;
+ if($def->descendants_are_inline) $this->descendants_are_inline = $def->descendants_are_inline;
+
+ }
+
+ /**
+ * Merges one array into another, removes values which equal false
+ * @param $a1 Array by reference that is merged into
+ * @param $a2 Array that merges into $a1
+ */
+ private function _mergeAssocArray(&$a1, $a2) {
+ foreach ($a2 as $k => $v) {
+ if ($v === false) {
+ if (isset($a1[$k])) unset($a1[$k]);
+ continue;
+ }
+ $a1[$k] = $v;
+ }
+ }
+
+}
+
+
+
+
+
+/**
+ * A UTF-8 specific character encoder that handles cleaning and transforming.
+ * @note All functions in this class should be static.
+ */
+class HTMLPurifier_Encoder
+{
+
+ /**
+ * Constructor throws fatal error if you attempt to instantiate class
+ */
+ private function __construct() {
+ trigger_error('Cannot instantiate encoder, call methods statically', E_USER_ERROR);
+ }
+
+ /**
+ * Error-handler that mutes errors, alternative to shut-up operator.
+ */
+ public static function muteErrorHandler() {}
+
+ /**
+ * iconv wrapper which mutes errors, but doesn't work around bugs.
+ */
+ public static function unsafeIconv($in, $out, $text) {
+ set_error_handler(array('HTMLPurifier_Encoder', 'muteErrorHandler'));
+ $r = iconv($in, $out, $text);
+ restore_error_handler();
+ return $r;
+ }
+
+ /**
+ * iconv wrapper which mutes errors and works around bugs.
+ */
+ public static function iconv($in, $out, $text, $max_chunk_size = 8000) {
+ $code = self::testIconvTruncateBug();
+ if ($code == self::ICONV_OK) {
+ return self::unsafeIconv($in, $out, $text);
+ } elseif ($code == self::ICONV_TRUNCATES) {
+ // we can only work around this if the input character set
+ // is utf-8
+ if ($in == 'utf-8') {
+ if ($max_chunk_size < 4) {
+ trigger_error('max_chunk_size is too small', E_USER_WARNING);
+ return false;
+ }
+ // split into 8000 byte chunks, but be careful to handle
+ // multibyte boundaries properly
+ if (($c = strlen($text)) <= $max_chunk_size) {
+ return self::unsafeIconv($in, $out, $text);
+ }
+ $r = '';
+ $i = 0;
+ while (true) {
+ if ($i + $max_chunk_size >= $c) {
+ $r .= self::unsafeIconv($in, $out, substr($text, $i));
+ break;
+ }
+ // wibble the boundary
+ if (0x80 != (0xC0 & ord($text[$i + $max_chunk_size]))) {
+ $chunk_size = $max_chunk_size;
+ } elseif (0x80 != (0xC0 & ord($text[$i + $max_chunk_size - 1]))) {
+ $chunk_size = $max_chunk_size - 1;
+ } elseif (0x80 != (0xC0 & ord($text[$i + $max_chunk_size - 2]))) {
+ $chunk_size = $max_chunk_size - 2;
+ } elseif (0x80 != (0xC0 & ord($text[$i + $max_chunk_size - 3]))) {
+ $chunk_size = $max_chunk_size - 3;
+ } else {
+ return false; // rather confusing UTF-8...
+ }
+ $chunk = substr($text, $i, $chunk_size); // substr doesn't mind overlong lengths
+ $r .= self::unsafeIconv($in, $out, $chunk);
+ $i += $chunk_size;
+ }
+ return $r;
+ } else {
+ return false;
+ }
+ } else {
+ return false;
+ }
+ }
+
+ /**
+ * Cleans a UTF-8 string for well-formedness and SGML validity
+ *
+ * It will parse according to UTF-8 and return a valid UTF8 string, with
+ * non-SGML codepoints excluded.
+ *
+ * @note Just for reference, the non-SGML code points are 0 to 31 and
+ * 127 to 159, inclusive. However, we allow code points 9, 10
+ * and 13, which are the tab, line feed and carriage return
+ * respectively. 128 and above the code points map to multibyte
+ * UTF-8 representations.
+ *
+ * @note Fallback code adapted from utf8ToUnicode by Henri Sivonen and
+ * hsivonen@iki.fi at under the
+ * LGPL license. Notes on what changed are inside, but in general,
+ * the original code transformed UTF-8 text into an array of integer
+ * Unicode codepoints. Understandably, transforming that back to
+ * a string would be somewhat expensive, so the function was modded to
+ * directly operate on the string. However, this discourages code
+ * reuse, and the logic enumerated here would be useful for any
+ * function that needs to be able to understand UTF-8 characters.
+ * As of right now, only smart lossless character encoding converters
+ * would need that, and I'm probably not going to implement them.
+ * Once again, PHP 6 should solve all our problems.
+ */
+ public static function cleanUTF8($str, $force_php = false) {
+
+ // UTF-8 validity is checked since PHP 4.3.5
+ // This is an optimization: if the string is already valid UTF-8, no
+ // need to do PHP stuff. 99% of the time, this will be the case.
+ // The regexp matches the XML char production, as well as well as excluding
+ // non-SGML codepoints U+007F to U+009F
+ if (preg_match('/^[\x{9}\x{A}\x{D}\x{20}-\x{7E}\x{A0}-\x{D7FF}\x{E000}-\x{FFFD}\x{10000}-\x{10FFFF}]*$/Du', $str)) {
+ return $str;
+ }
+
+ $mState = 0; // cached expected number of octets after the current octet
+ // until the beginning of the next UTF8 character sequence
+ $mUcs4 = 0; // cached Unicode character
+ $mBytes = 1; // cached expected number of octets in the current sequence
+
+ // original code involved an $out that was an array of Unicode
+ // codepoints. Instead of having to convert back into UTF-8, we've
+ // decided to directly append valid UTF-8 characters onto a string
+ // $out once they're done. $char accumulates raw bytes, while $mUcs4
+ // turns into the Unicode code point, so there's some redundancy.
+
+ $out = '';
+ $char = '';
+
+ $len = strlen($str);
+ for($i = 0; $i < $len; $i++) {
+ $in = ord($str{$i});
+ $char .= $str[$i]; // append byte to char
+ if (0 == $mState) {
+ // When mState is zero we expect either a US-ASCII character
+ // or a multi-octet sequence.
+ if (0 == (0x80 & ($in))) {
+ // US-ASCII, pass straight through.
+ if (($in <= 31 || $in == 127) &&
+ !($in == 9 || $in == 13 || $in == 10) // save \r\t\n
+ ) {
+ // control characters, remove
+ } else {
+ $out .= $char;
+ }
+ // reset
+ $char = '';
+ $mBytes = 1;
+ } elseif (0xC0 == (0xE0 & ($in))) {
+ // First octet of 2 octet sequence
+ $mUcs4 = ($in);
+ $mUcs4 = ($mUcs4 & 0x1F) << 6;
+ $mState = 1;
+ $mBytes = 2;
+ } elseif (0xE0 == (0xF0 & ($in))) {
+ // First octet of 3 octet sequence
+ $mUcs4 = ($in);
+ $mUcs4 = ($mUcs4 & 0x0F) << 12;
+ $mState = 2;
+ $mBytes = 3;
+ } elseif (0xF0 == (0xF8 & ($in))) {
+ // First octet of 4 octet sequence
+ $mUcs4 = ($in);
+ $mUcs4 = ($mUcs4 & 0x07) << 18;
+ $mState = 3;
+ $mBytes = 4;
+ } elseif (0xF8 == (0xFC & ($in))) {
+ // First octet of 5 octet sequence.
+ //
+ // This is illegal because the encoded codepoint must be
+ // either:
+ // (a) not the shortest form or
+ // (b) outside the Unicode range of 0-0x10FFFF.
+ // Rather than trying to resynchronize, we will carry on
+ // until the end of the sequence and let the later error
+ // handling code catch it.
+ $mUcs4 = ($in);
+ $mUcs4 = ($mUcs4 & 0x03) << 24;
+ $mState = 4;
+ $mBytes = 5;
+ } elseif (0xFC == (0xFE & ($in))) {
+ // First octet of 6 octet sequence, see comments for 5
+ // octet sequence.
+ $mUcs4 = ($in);
+ $mUcs4 = ($mUcs4 & 1) << 30;
+ $mState = 5;
+ $mBytes = 6;
+ } else {
+ // Current octet is neither in the US-ASCII range nor a
+ // legal first octet of a multi-octet sequence.
+ $mState = 0;
+ $mUcs4 = 0;
+ $mBytes = 1;
+ $char = '';
+ }
+ } else {
+ // When mState is non-zero, we expect a continuation of the
+ // multi-octet sequence
+ if (0x80 == (0xC0 & ($in))) {
+ // Legal continuation.
+ $shift = ($mState - 1) * 6;
+ $tmp = $in;
+ $tmp = ($tmp & 0x0000003F) << $shift;
+ $mUcs4 |= $tmp;
+
+ if (0 == --$mState) {
+ // End of the multi-octet sequence. mUcs4 now contains
+ // the final Unicode codepoint to be output
+
+ // Check for illegal sequences and codepoints.
+
+ // From Unicode 3.1, non-shortest form is illegal
+ if (((2 == $mBytes) && ($mUcs4 < 0x0080)) ||
+ ((3 == $mBytes) && ($mUcs4 < 0x0800)) ||
+ ((4 == $mBytes) && ($mUcs4 < 0x10000)) ||
+ (4 < $mBytes) ||
+ // From Unicode 3.2, surrogate characters = illegal
+ (($mUcs4 & 0xFFFFF800) == 0xD800) ||
+ // Codepoints outside the Unicode range are illegal
+ ($mUcs4 > 0x10FFFF)
+ ) {
+
+ } elseif (0xFEFF != $mUcs4 && // omit BOM
+ // check for valid Char unicode codepoints
+ (
+ 0x9 == $mUcs4 ||
+ 0xA == $mUcs4 ||
+ 0xD == $mUcs4 ||
+ (0x20 <= $mUcs4 && 0x7E >= $mUcs4) ||
+ // 7F-9F is not strictly prohibited by XML,
+ // but it is non-SGML, and thus we don't allow it
+ (0xA0 <= $mUcs4 && 0xD7FF >= $mUcs4) ||
+ (0x10000 <= $mUcs4 && 0x10FFFF >= $mUcs4)
+ )
+ ) {
+ $out .= $char;
+ }
+ // initialize UTF8 cache (reset)
+ $mState = 0;
+ $mUcs4 = 0;
+ $mBytes = 1;
+ $char = '';
+ }
+ } else {
+ // ((0xC0 & (*in) != 0x80) && (mState != 0))
+ // Incomplete multi-octet sequence.
+ // used to result in complete fail, but we'll reset
+ $mState = 0;
+ $mUcs4 = 0;
+ $mBytes = 1;
+ $char ='';
+ }
+ }
+ }
+ return $out;
+ }
+
+ /**
+ * Translates a Unicode codepoint into its corresponding UTF-8 character.
+ * @note Based on Feyd's function at
+ * ,
+ * which is in public domain.
+ * @note While we're going to do code point parsing anyway, a good
+ * optimization would be to refuse to translate code points that
+ * are non-SGML characters. However, this could lead to duplication.
+ * @note This is very similar to the unichr function in
+ * maintenance/generate-entity-file.php (although this is superior,
+ * due to its sanity checks).
+ */
+
+ // +----------+----------+----------+----------+
+ // | 33222222 | 22221111 | 111111 | |
+ // | 10987654 | 32109876 | 54321098 | 76543210 | bit
+ // +----------+----------+----------+----------+
+ // | | | | 0xxxxxxx | 1 byte 0x00000000..0x0000007F
+ // | | | 110yyyyy | 10xxxxxx | 2 byte 0x00000080..0x000007FF
+ // | | 1110zzzz | 10yyyyyy | 10xxxxxx | 3 byte 0x00000800..0x0000FFFF
+ // | 11110www | 10wwzzzz | 10yyyyyy | 10xxxxxx | 4 byte 0x00010000..0x0010FFFF
+ // +----------+----------+----------+----------+
+ // | 00000000 | 00011111 | 11111111 | 11111111 | Theoretical upper limit of legal scalars: 2097151 (0x001FFFFF)
+ // | 00000000 | 00010000 | 11111111 | 11111111 | Defined upper limit of legal scalar codes
+ // +----------+----------+----------+----------+
+
+ public static function unichr($code) {
+ if($code > 1114111 or $code < 0 or
+ ($code >= 55296 and $code <= 57343) ) {
+ // bits are set outside the "valid" range as defined
+ // by UNICODE 4.1.0
+ return '';
+ }
+
+ $x = $y = $z = $w = 0;
+ if ($code < 128) {
+ // regular ASCII character
+ $x = $code;
+ } else {
+ // set up bits for UTF-8
+ $x = ($code & 63) | 128;
+ if ($code < 2048) {
+ $y = (($code & 2047) >> 6) | 192;
+ } else {
+ $y = (($code & 4032) >> 6) | 128;
+ if($code < 65536) {
+ $z = (($code >> 12) & 15) | 224;
+ } else {
+ $z = (($code >> 12) & 63) | 128;
+ $w = (($code >> 18) & 7) | 240;
+ }
+ }
+ }
+ // set up the actual character
+ $ret = '';
+ if($w) $ret .= chr($w);
+ if($z) $ret .= chr($z);
+ if($y) $ret .= chr($y);
+ $ret .= chr($x);
+
+ return $ret;
+ }
+
+ public static function iconvAvailable() {
+ static $iconv = null;
+ if ($iconv === null) {
+ $iconv = function_exists('iconv') && self::testIconvTruncateBug() != self::ICONV_UNUSABLE;
+ }
+ return $iconv;
+ }
+
+ /**
+ * Converts a string to UTF-8 based on configuration.
+ */
+ public static function convertToUTF8($str, $config, $context) {
+ $encoding = $config->get('Core.Encoding');
+ if ($encoding === 'utf-8') return $str;
+ static $iconv = null;
+ if ($iconv === null) $iconv = self::iconvAvailable();
+ if ($iconv && !$config->get('Test.ForceNoIconv')) {
+ // unaffected by bugs, since UTF-8 support all characters
+ $str = self::unsafeIconv($encoding, 'utf-8//IGNORE', $str);
+ if ($str === false) {
+ // $encoding is not a valid encoding
+ trigger_error('Invalid encoding ' . $encoding, E_USER_ERROR);
+ return '';
+ }
+ // If the string is bjorked by Shift_JIS or a similar encoding
+ // that doesn't support all of ASCII, convert the naughty
+ // characters to their true byte-wise ASCII/UTF-8 equivalents.
+ $str = strtr($str, self::testEncodingSupportsASCII($encoding));
+ return $str;
+ } elseif ($encoding === 'iso-8859-1') {
+ $str = utf8_encode($str);
+ return $str;
+ }
+ $bug = HTMLPurifier_Encoder::testIconvTruncateBug();
+ if ($bug == self::ICONV_OK) {
+ trigger_error('Encoding not supported, please install iconv', E_USER_ERROR);
+ } else {
+ trigger_error('You have a buggy version of iconv, see https://bugs.php.net/bug.php?id=48147 and http://sourceware.org/bugzilla/show_bug.cgi?id=13541', E_USER_ERROR);
+ }
+ }
+
+ /**
+ * Converts a string from UTF-8 based on configuration.
+ * @note Currently, this is a lossy conversion, with unexpressable
+ * characters being omitted.
+ */
+ public static function convertFromUTF8($str, $config, $context) {
+ $encoding = $config->get('Core.Encoding');
+ if ($escape = $config->get('Core.EscapeNonASCIICharacters')) {
+ $str = self::convertToASCIIDumbLossless($str);
+ }
+ if ($encoding === 'utf-8') return $str;
+ static $iconv = null;
+ if ($iconv === null) $iconv = self::iconvAvailable();
+ if ($iconv && !$config->get('Test.ForceNoIconv')) {
+ // Undo our previous fix in convertToUTF8, otherwise iconv will barf
+ $ascii_fix = self::testEncodingSupportsASCII($encoding);
+ if (!$escape && !empty($ascii_fix)) {
+ $clear_fix = array();
+ foreach ($ascii_fix as $utf8 => $native) $clear_fix[$utf8] = '';
+ $str = strtr($str, $clear_fix);
+ }
+ $str = strtr($str, array_flip($ascii_fix));
+ // Normal stuff
+ $str = self::iconv('utf-8', $encoding . '//IGNORE', $str);
+ return $str;
+ } elseif ($encoding === 'iso-8859-1') {
+ $str = utf8_decode($str);
+ return $str;
+ }
+ trigger_error('Encoding not supported', E_USER_ERROR);
+ // You might be tempted to assume that the ASCII representation
+ // might be OK, however, this is *not* universally true over all
+ // encodings. So we take the conservative route here, rather
+ // than forcibly turn on %Core.EscapeNonASCIICharacters
+ }
+
+ /**
+ * Lossless (character-wise) conversion of HTML to ASCII
+ * @param $str UTF-8 string to be converted to ASCII
+ * @returns ASCII encoded string with non-ASCII character entity-ized
+ * @warning Adapted from MediaWiki, claiming fair use: this is a common
+ * algorithm. If you disagree with this license fudgery,
+ * implement it yourself.
+ * @note Uses decimal numeric entities since they are best supported.
+ * @note This is a DUMB function: it has no concept of keeping
+ * character entities that the projected character encoding
+ * can allow. We could possibly implement a smart version
+ * but that would require it to also know which Unicode
+ * codepoints the charset supported (not an easy task).
+ * @note Sort of with cleanUTF8() but it assumes that $str is
+ * well-formed UTF-8
+ */
+ public static function convertToASCIIDumbLossless($str) {
+ $bytesleft = 0;
+ $result = '';
+ $working = 0;
+ $len = strlen($str);
+ for( $i = 0; $i < $len; $i++ ) {
+ $bytevalue = ord( $str[$i] );
+ if( $bytevalue <= 0x7F ) { //0xxx xxxx
+ $result .= chr( $bytevalue );
+ $bytesleft = 0;
+ } elseif( $bytevalue <= 0xBF ) { //10xx xxxx
+ $working = $working << 6;
+ $working += ($bytevalue & 0x3F);
+ $bytesleft--;
+ if( $bytesleft <= 0 ) {
+ $result .= "" . $working . ";";
+ }
+ } elseif( $bytevalue <= 0xDF ) { //110x xxxx
+ $working = $bytevalue & 0x1F;
+ $bytesleft = 1;
+ } elseif( $bytevalue <= 0xEF ) { //1110 xxxx
+ $working = $bytevalue & 0x0F;
+ $bytesleft = 2;
+ } else { //1111 0xxx
+ $working = $bytevalue & 0x07;
+ $bytesleft = 3;
+ }
+ }
+ return $result;
+ }
+
+ /** No bugs detected in iconv. */
+ const ICONV_OK = 0;
+
+ /** Iconv truncates output if converting from UTF-8 to another
+ * character set with //IGNORE, and a non-encodable character is found */
+ const ICONV_TRUNCATES = 1;
+
+ /** Iconv does not support //IGNORE, making it unusable for
+ * transcoding purposes */
+ const ICONV_UNUSABLE = 2;
+
+ /**
+ * glibc iconv has a known bug where it doesn't handle the magic
+ * //IGNORE stanza correctly. In particular, rather than ignore
+ * characters, it will return an EILSEQ after consuming some number
+ * of characters, and expect you to restart iconv as if it were
+ * an E2BIG. Old versions of PHP did not respect the errno, and
+ * returned the fragment, so as a result you would see iconv
+ * mysteriously truncating output. We can work around this by
+ * manually chopping our input into segments of about 8000
+ * characters, as long as PHP ignores the error code. If PHP starts
+ * paying attention to the error code, iconv becomes unusable.
+ *
+ * @returns Error code indicating severity of bug.
+ */
+ public static function testIconvTruncateBug() {
+ static $code = null;
+ if ($code === null) {
+ // better not use iconv, otherwise infinite loop!
+ $r = self::unsafeIconv('utf-8', 'ascii//IGNORE', "\xCE\xB1" . str_repeat('a', 9000));
+ if ($r === false) {
+ $code = self::ICONV_UNUSABLE;
+ } elseif (($c = strlen($r)) < 9000) {
+ $code = self::ICONV_TRUNCATES;
+ } elseif ($c > 9000) {
+ trigger_error('Your copy of iconv is extremely buggy. Please notify HTML Purifier maintainers: include your iconv version as per phpversion()', E_USER_ERROR);
+ } else {
+ $code = self::ICONV_OK;
+ }
+ }
+ return $code;
+ }
+
+ /**
+ * This expensive function tests whether or not a given character
+ * encoding supports ASCII. 7/8-bit encodings like Shift_JIS will
+ * fail this test, and require special processing. Variable width
+ * encodings shouldn't ever fail.
+ *
+ * @param string $encoding Encoding name to test, as per iconv format
+ * @param bool $bypass Whether or not to bypass the precompiled arrays.
+ * @return Array of UTF-8 characters to their corresponding ASCII,
+ * which can be used to "undo" any overzealous iconv action.
+ */
+ public static function testEncodingSupportsASCII($encoding, $bypass = false) {
+ // All calls to iconv here are unsafe, proof by case analysis:
+ // If ICONV_OK, no difference.
+ // If ICONV_TRUNCATE, all calls involve one character inputs,
+ // so bug is not triggered.
+ // If ICONV_UNUSABLE, this call is irrelevant
+ static $encodings = array();
+ if (!$bypass) {
+ if (isset($encodings[$encoding])) return $encodings[$encoding];
+ $lenc = strtolower($encoding);
+ switch ($lenc) {
+ case 'shift_jis':
+ return array("\xC2\xA5" => '\\', "\xE2\x80\xBE" => '~');
+ case 'johab':
+ return array("\xE2\x82\xA9" => '\\');
+ }
+ if (strpos($lenc, 'iso-8859-') === 0) return array();
+ }
+ $ret = array();
+ if (self::unsafeIconv('UTF-8', $encoding, 'a') === false) return false;
+ for ($i = 0x20; $i <= 0x7E; $i++) { // all printable ASCII chars
+ $c = chr($i); // UTF-8 char
+ $r = self::unsafeIconv('UTF-8', "$encoding//IGNORE", $c); // initial conversion
+ if (
+ $r === '' ||
+ // This line is needed for iconv implementations that do not
+ // omit characters that do not exist in the target character set
+ ($r === $c && self::unsafeIconv($encoding, 'UTF-8//IGNORE', $r) !== $c)
+ ) {
+ // Reverse engineer: what's the UTF-8 equiv of this byte
+ // sequence? This assumes that there's no variable width
+ // encoding that doesn't support ASCII.
+ $ret[self::unsafeIconv($encoding, 'UTF-8//IGNORE', $c)] = $c;
+ }
+ }
+ $encodings[$encoding] = $ret;
+ return $ret;
+ }
+
+
+}
+
+
+
+
+
+/**
+ * Object that provides entity lookup table from entity name to character
+ */
+class HTMLPurifier_EntityLookup {
+
+ /**
+ * Assoc array of entity name to character represented.
+ */
+ public $table;
+
+ /**
+ * Sets up the entity lookup table from the serialized file contents.
+ * @note The serialized contents are versioned, but were generated
+ * using the maintenance script generate_entity_file.php
+ * @warning This is not in constructor to help enforce the Singleton
+ */
+ public function setup($file = false) {
+ if (!$file) {
+ $file = HTMLPURIFIER_PREFIX . '/HTMLPurifier/EntityLookup/entities.ser';
+ }
+ $this->table = unserialize(file_get_contents($file));
+ }
+
+ /**
+ * Retrieves sole instance of the object.
+ * @param Optional prototype of custom lookup table to overload with.
+ */
+ public static function instance($prototype = false) {
+ // no references, since PHP doesn't copy unless modified
+ static $instance = null;
+ if ($prototype) {
+ $instance = $prototype;
+ } elseif (!$instance) {
+ $instance = new HTMLPurifier_EntityLookup();
+ $instance->setup();
+ }
+ return $instance;
+ }
+
+}
+
+
+
+
+
+// if want to implement error collecting here, we'll need to use some sort
+// of global data (probably trigger_error) because it's impossible to pass
+// $config or $context to the callback functions.
+
+/**
+ * Handles referencing and derefencing character entities
+ */
+class HTMLPurifier_EntityParser
+{
+
+ /**
+ * Reference to entity lookup table.
+ */
+ protected $_entity_lookup;
+
+ /**
+ * Callback regex string for parsing entities.
+ */
+ protected $_substituteEntitiesRegex =
+'/&(?:[#]x([a-fA-F0-9]+)|[#]0*(\d+)|([A-Za-z_:][A-Za-z0-9.\-_:]*));?/';
+// 1. hex 2. dec 3. string (XML style)
+
+
+ /**
+ * Decimal to parsed string conversion table for special entities.
+ */
+ protected $_special_dec2str =
+ array(
+ 34 => '"',
+ 38 => '&',
+ 39 => "'",
+ 60 => '<',
+ 62 => '>'
+ );
+
+ /**
+ * Stripped entity names to decimal conversion table for special entities.
+ */
+ protected $_special_ent2dec =
+ array(
+ 'quot' => 34,
+ 'amp' => 38,
+ 'lt' => 60,
+ 'gt' => 62
+ );
+
+ /**
+ * Substitutes non-special entities with their parsed equivalents. Since
+ * running this whenever you have parsed character is t3h 5uck, we run
+ * it before everything else.
+ *
+ * @param $string String to have non-special entities parsed.
+ * @returns Parsed string.
+ */
+ public function substituteNonSpecialEntities($string) {
+ // it will try to detect missing semicolons, but don't rely on it
+ return preg_replace_callback(
+ $this->_substituteEntitiesRegex,
+ array($this, 'nonSpecialEntityCallback'),
+ $string
+ );
+ }
+
+ /**
+ * Callback function for substituteNonSpecialEntities() that does the work.
+ *
+ * @param $matches PCRE matches array, with 0 the entire match, and
+ * either index 1, 2 or 3 set with a hex value, dec value,
+ * or string (respectively).
+ * @returns Replacement string.
+ */
+
+ protected function nonSpecialEntityCallback($matches) {
+ // replaces all but big five
+ $entity = $matches[0];
+ $is_num = (@$matches[0][1] === '#');
+ if ($is_num) {
+ $is_hex = (@$entity[2] === 'x');
+ $code = $is_hex ? hexdec($matches[1]) : (int) $matches[2];
+
+ // abort for special characters
+ if (isset($this->_special_dec2str[$code])) return $entity;
+
+ return HTMLPurifier_Encoder::unichr($code);
+ } else {
+ if (isset($this->_special_ent2dec[$matches[3]])) return $entity;
+ if (!$this->_entity_lookup) {
+ $this->_entity_lookup = HTMLPurifier_EntityLookup::instance();
+ }
+ if (isset($this->_entity_lookup->table[$matches[3]])) {
+ return $this->_entity_lookup->table[$matches[3]];
+ } else {
+ return $entity;
+ }
+ }
+ }
+
+ /**
+ * Substitutes only special entities with their parsed equivalents.
+ *
+ * @notice We try to avoid calling this function because otherwise, it
+ * would have to be called a lot (for every parsed section).
+ *
+ * @param $string String to have non-special entities parsed.
+ * @returns Parsed string.
+ */
+ public function substituteSpecialEntities($string) {
+ return preg_replace_callback(
+ $this->_substituteEntitiesRegex,
+ array($this, 'specialEntityCallback'),
+ $string);
+ }
+
+ /**
+ * Callback function for substituteSpecialEntities() that does the work.
+ *
+ * This callback has same syntax as nonSpecialEntityCallback().
+ *
+ * @param $matches PCRE-style matches array, with 0 the entire match, and
+ * either index 1, 2 or 3 set with a hex value, dec value,
+ * or string (respectively).
+ * @returns Replacement string.
+ */
+ protected function specialEntityCallback($matches) {
+ $entity = $matches[0];
+ $is_num = (@$matches[0][1] === '#');
+ if ($is_num) {
+ $is_hex = (@$entity[2] === 'x');
+ $int = $is_hex ? hexdec($matches[1]) : (int) $matches[2];
+ return isset($this->_special_dec2str[$int]) ?
+ $this->_special_dec2str[$int] :
+ $entity;
+ } else {
+ return isset($this->_special_ent2dec[$matches[3]]) ?
+ $this->_special_ent2dec[$matches[3]] :
+ $entity;
+ }
+ }
+
+}
+
+
+
+
+
+/**
+ * Error collection class that enables HTML Purifier to report HTML
+ * problems back to the user
+ */
+class HTMLPurifier_ErrorCollector
+{
+
+ /**
+ * Identifiers for the returned error array. These are purposely numeric
+ * so list() can be used.
+ */
+ const LINENO = 0;
+ const SEVERITY = 1;
+ const MESSAGE = 2;
+ const CHILDREN = 3;
+
+ protected $errors;
+ protected $_current;
+ protected $_stacks = array(array());
+ protected $locale;
+ protected $generator;
+ protected $context;
+
+ protected $lines = array();
+
+ public function __construct($context) {
+ $this->locale =& $context->get('Locale');
+ $this->context = $context;
+ $this->_current =& $this->_stacks[0];
+ $this->errors =& $this->_stacks[0];
+ }
+
+ /**
+ * Sends an error message to the collector for later use
+ * @param $severity int Error severity, PHP error style (don't use E_USER_)
+ * @param $msg string Error message text
+ * @param $subst1 string First substitution for $msg
+ * @param $subst2 string ...
+ */
+ public function send($severity, $msg) {
+
+ $args = array();
+ if (func_num_args() > 2) {
+ $args = func_get_args();
+ array_shift($args);
+ unset($args[0]);
+ }
+
+ $token = $this->context->get('CurrentToken', true);
+ $line = $token ? $token->line : $this->context->get('CurrentLine', true);
+ $col = $token ? $token->col : $this->context->get('CurrentCol', true);
+ $attr = $this->context->get('CurrentAttr', true);
+
+ // perform special substitutions, also add custom parameters
+ $subst = array();
+ if (!is_null($token)) {
+ $args['CurrentToken'] = $token;
+ }
+ if (!is_null($attr)) {
+ $subst['$CurrentAttr.Name'] = $attr;
+ if (isset($token->attr[$attr])) $subst['$CurrentAttr.Value'] = $token->attr[$attr];
+ }
+
+ if (empty($args)) {
+ $msg = $this->locale->getMessage($msg);
+ } else {
+ $msg = $this->locale->formatMessage($msg, $args);
+ }
+
+ if (!empty($subst)) $msg = strtr($msg, $subst);
+
+ // (numerically indexed)
+ $error = array(
+ self::LINENO => $line,
+ self::SEVERITY => $severity,
+ self::MESSAGE => $msg,
+ self::CHILDREN => array()
+ );
+ $this->_current[] = $error;
+
+
+ // NEW CODE BELOW ...
+
+ $struct = null;
+ // Top-level errors are either:
+ // TOKEN type, if $value is set appropriately, or
+ // "syntax" type, if $value is null
+ $new_struct = new HTMLPurifier_ErrorStruct();
+ $new_struct->type = HTMLPurifier_ErrorStruct::TOKEN;
+ if ($token) $new_struct->value = clone $token;
+ if (is_int($line) && is_int($col)) {
+ if (isset($this->lines[$line][$col])) {
+ $struct = $this->lines[$line][$col];
+ } else {
+ $struct = $this->lines[$line][$col] = $new_struct;
+ }
+ // These ksorts may present a performance problem
+ ksort($this->lines[$line], SORT_NUMERIC);
+ } else {
+ if (isset($this->lines[-1])) {
+ $struct = $this->lines[-1];
+ } else {
+ $struct = $this->lines[-1] = $new_struct;
+ }
+ }
+ ksort($this->lines, SORT_NUMERIC);
+
+ // Now, check if we need to operate on a lower structure
+ if (!empty($attr)) {
+ $struct = $struct->getChild(HTMLPurifier_ErrorStruct::ATTR, $attr);
+ if (!$struct->value) {
+ $struct->value = array($attr, 'PUT VALUE HERE');
+ }
+ }
+ if (!empty($cssprop)) {
+ $struct = $struct->getChild(HTMLPurifier_ErrorStruct::CSSPROP, $cssprop);
+ if (!$struct->value) {
+ // if we tokenize CSS this might be a little more difficult to do
+ $struct->value = array($cssprop, 'PUT VALUE HERE');
+ }
+ }
+
+ // Ok, structs are all setup, now time to register the error
+ $struct->addError($severity, $msg);
+ }
+
+ /**
+ * Retrieves raw error data for custom formatter to use
+ * @param List of arrays in format of array(line of error,
+ * error severity, error message,
+ * recursive sub-errors array)
+ */
+ public function getRaw() {
+ return $this->errors;
+ }
+
+ /**
+ * Default HTML formatting implementation for error messages
+ * @param $config Configuration array, vital for HTML output nature
+ * @param $errors Errors array to display; used for recursion.
+ */
+ public function getHTMLFormatted($config, $errors = null) {
+ $ret = array();
+
+ $this->generator = new HTMLPurifier_Generator($config, $this->context);
+ if ($errors === null) $errors = $this->errors;
+
+ // 'At line' message needs to be removed
+
+ // generation code for new structure goes here. It needs to be recursive.
+ foreach ($this->lines as $line => $col_array) {
+ if ($line == -1) continue;
+ foreach ($col_array as $col => $struct) {
+ $this->_renderStruct($ret, $struct, $line, $col);
+ }
+ }
+ if (isset($this->lines[-1])) {
+ $this->_renderStruct($ret, $this->lines[-1]);
+ }
+
+ if (empty($errors)) {
+ return '
' . $this->locale->getMessage('ErrorCollector: No errors') . '
';
+ // W3C uses an icon to indicate the severity of the error.
+ $error = $this->locale->getErrorName($severity);
+ $string .= "$error ";
+ if (!is_null($line) && !is_null($col)) {
+ $string .= "Line $line, Column $col: ";
+ } else {
+ $string .= 'End of Document: ';
+ }
+ $string .= '' . $this->generator->escape($msg) . ' ';
+ $string .= '
';
+ // Here, have a marker for the character on the column appropriate.
+ // Be sure to clip extremely long lines.
+ //$string .= '
';
+ //$string .= '';
+ //$string .= '
';
+ $ret[] = $string;
+ }
+ foreach ($current->children as $type => $array) {
+ $context[] = $current;
+ $stack = array_merge($stack, array_reverse($array, true));
+ for ($i = count($array); $i > 0; $i--) {
+ $context_stack[] = $context;
+ }
+ }
+ }
+ }
+
+}
+
+
+
+
+
+/**
+ * Records errors for particular segments of an HTML document such as tokens,
+ * attributes or CSS properties. They can contain error structs (which apply
+ * to components of what they represent), but their main purpose is to hold
+ * errors applying to whatever struct is being used.
+ */
+class HTMLPurifier_ErrorStruct
+{
+
+ /**
+ * Possible values for $children first-key. Note that top-level structures
+ * are automatically token-level.
+ */
+ const TOKEN = 0;
+ const ATTR = 1;
+ const CSSPROP = 2;
+
+ /**
+ * Type of this struct.
+ */
+ public $type;
+
+ /**
+ * Value of the struct we are recording errors for. There are various
+ * values for this:
+ * - TOKEN: Instance of HTMLPurifier_Token
+ * - ATTR: array('attr-name', 'value')
+ * - CSSPROP: array('prop-name', 'value')
+ */
+ public $value;
+
+ /**
+ * Errors registered for this structure.
+ */
+ public $errors = array();
+
+ /**
+ * Child ErrorStructs that are from this structure. For example, a TOKEN
+ * ErrorStruct would contain ATTR ErrorStructs. This is a multi-dimensional
+ * array in structure: [TYPE]['identifier']
+ */
+ public $children = array();
+
+ public function getChild($type, $id) {
+ if (!isset($this->children[$type][$id])) {
+ $this->children[$type][$id] = new HTMLPurifier_ErrorStruct();
+ $this->children[$type][$id]->type = $type;
+ }
+ return $this->children[$type][$id];
+ }
+
+ public function addError($severity, $message) {
+ $this->errors[] = array($severity, $message);
+ }
+
+}
+
+
+
+
+
+/**
+ * Global exception class for HTML Purifier; any exceptions we throw
+ * are from here.
+ */
+class HTMLPurifier_Exception extends Exception
+{
+
+}
+
+
+
+
+
+/**
+ * Represents a pre or post processing filter on HTML Purifier's output
+ *
+ * Sometimes, a little ad-hoc fixing of HTML has to be done before
+ * it gets sent through HTML Purifier: you can use filters to acheive
+ * this effect. For instance, YouTube videos can be preserved using
+ * this manner. You could have used a decorator for this task, but
+ * PHP's support for them is not terribly robust, so we're going
+ * to just loop through the filters.
+ *
+ * Filters should be exited first in, last out. If there are three filters,
+ * named 1, 2 and 3, the order of execution should go 1->preFilter,
+ * 2->preFilter, 3->preFilter, purify, 3->postFilter, 2->postFilter,
+ * 1->postFilter.
+ *
+ * @note Methods are not declared abstract as it is perfectly legitimate
+ * for an implementation not to want anything to happen on a step
+ */
+
+class HTMLPurifier_Filter
+{
+
+ /**
+ * Name of the filter for identification purposes
+ */
+ public $name;
+
+ /**
+ * Pre-processor function, handles HTML before HTML Purifier
+ */
+ public function preFilter($html, $config, $context) {
+ return $html;
+ }
+
+ /**
+ * Post-processor function, handles HTML after HTML Purifier
+ */
+ public function postFilter($html, $config, $context) {
+ return $html;
+ }
+
+}
+
+
+
+
+
+/**
+ * Generates HTML from tokens.
+ * @todo Refactor interface so that configuration/context is determined
+ * upon instantiation, no need for messy generateFromTokens() calls
+ * @todo Make some of the more internal functions protected, and have
+ * unit tests work around that
+ */
+class HTMLPurifier_Generator
+{
+
+ /**
+ * Whether or not generator should produce XML output
+ */
+ private $_xhtml = true;
+
+ /**
+ * :HACK: Whether or not generator should comment the insides of )#si',
+ array($this, 'scriptCallback'), $html);
+ }
+
+ $html = $this->normalize($html, $config, $context);
+
+ $cursor = 0; // our location in the text
+ $inside_tag = false; // whether or not we're parsing the inside of a tag
+ $array = array(); // result array
+
+ // This is also treated to mean maintain *column* numbers too
+ $maintain_line_numbers = $config->get('Core.MaintainLineNumbers');
+
+ if ($maintain_line_numbers === null) {
+ // automatically determine line numbering by checking
+ // if error collection is on
+ $maintain_line_numbers = $config->get('Core.CollectErrors');
+ }
+
+ if ($maintain_line_numbers) {
+ $current_line = 1;
+ $current_col = 0;
+ $length = strlen($html);
+ } else {
+ $current_line = false;
+ $current_col = false;
+ $length = false;
+ }
+ $context->register('CurrentLine', $current_line);
+ $context->register('CurrentCol', $current_col);
+ $nl = "\n";
+ // how often to manually recalculate. This will ALWAYS be right,
+ // but it's pretty wasteful. Set to 0 to turn off
+ $synchronize_interval = $config->get('Core.DirectLexLineNumberSyncInterval');
+
+ $e = false;
+ if ($config->get('Core.CollectErrors')) {
+ $e =& $context->get('ErrorCollector');
+ }
+
+ // for testing synchronization
+ $loops = 0;
+
+ while(++$loops) {
+
+ // $cursor is either at the start of a token, or inside of
+ // a tag (i.e. there was a < immediately before it), as indicated
+ // by $inside_tag
+
+ if ($maintain_line_numbers) {
+
+ // $rcursor, however, is always at the start of a token.
+ $rcursor = $cursor - (int) $inside_tag;
+
+ // Column number is cheap, so we calculate it every round.
+ // We're interested at the *end* of the newline string, so
+ // we need to add strlen($nl) == 1 to $nl_pos before subtracting it
+ // from our "rcursor" position.
+ $nl_pos = strrpos($html, $nl, $rcursor - $length);
+ $current_col = $rcursor - (is_bool($nl_pos) ? 0 : $nl_pos + 1);
+
+ // recalculate lines
+ if (
+ $synchronize_interval && // synchronization is on
+ $cursor > 0 && // cursor is further than zero
+ $loops % $synchronize_interval === 0 // time to synchronize!
+ ) {
+ $current_line = 1 + $this->substrCount($html, $nl, 0, $cursor);
+ }
+
+ }
+
+ $position_next_lt = strpos($html, '<', $cursor);
+ $position_next_gt = strpos($html, '>', $cursor);
+
+ // triggers on "asdf" but not "asdf "
+ // special case to set up context
+ if ($position_next_lt === $cursor) {
+ $inside_tag = true;
+ $cursor++;
+ }
+
+ if (!$inside_tag && $position_next_lt !== false) {
+ // We are not inside tag and there still is another tag to parse
+ $token = new
+ HTMLPurifier_Token_Text(
+ $this->parseData(
+ substr(
+ $html, $cursor, $position_next_lt - $cursor
+ )
+ )
+ );
+ if ($maintain_line_numbers) {
+ $token->rawPosition($current_line, $current_col);
+ $current_line += $this->substrCount($html, $nl, $cursor, $position_next_lt - $cursor);
+ }
+ $array[] = $token;
+ $cursor = $position_next_lt + 1;
+ $inside_tag = true;
+ continue;
+ } elseif (!$inside_tag) {
+ // We are not inside tag but there are no more tags
+ // If we're already at the end, break
+ if ($cursor === strlen($html)) break;
+ // Create Text of rest of string
+ $token = new
+ HTMLPurifier_Token_Text(
+ $this->parseData(
+ substr(
+ $html, $cursor
+ )
+ )
+ );
+ if ($maintain_line_numbers) $token->rawPosition($current_line, $current_col);
+ $array[] = $token;
+ break;
+ } elseif ($inside_tag && $position_next_gt !== false) {
+ // We are in tag and it is well formed
+ // Grab the internals of the tag
+ $strlen_segment = $position_next_gt - $cursor;
+
+ if ($strlen_segment < 1) {
+ // there's nothing to process!
+ $token = new HTMLPurifier_Token_Text('<');
+ $cursor++;
+ continue;
+ }
+
+ $segment = substr($html, $cursor, $strlen_segment);
+
+ if ($segment === false) {
+ // somehow, we attempted to access beyond the end of
+ // the string, defense-in-depth, reported by Nate Abele
+ break;
+ }
+
+ // Check if it's a comment
+ if (
+ substr($segment, 0, 3) === '!--'
+ ) {
+ // re-determine segment length, looking for -->
+ $position_comment_end = strpos($html, '-->', $cursor);
+ if ($position_comment_end === false) {
+ // uh oh, we have a comment that extends to
+ // infinity. Can't be helped: set comment
+ // end position to end of string
+ if ($e) $e->send(E_WARNING, 'Lexer: Unclosed comment');
+ $position_comment_end = strlen($html);
+ $end = true;
+ } else {
+ $end = false;
+ }
+ $strlen_segment = $position_comment_end - $cursor;
+ $segment = substr($html, $cursor, $strlen_segment);
+ $token = new
+ HTMLPurifier_Token_Comment(
+ substr(
+ $segment, 3, $strlen_segment - 3
+ )
+ );
+ if ($maintain_line_numbers) {
+ $token->rawPosition($current_line, $current_col);
+ $current_line += $this->substrCount($html, $nl, $cursor, $strlen_segment);
+ }
+ $array[] = $token;
+ $cursor = $end ? $position_comment_end : $position_comment_end + 3;
+ $inside_tag = false;
+ continue;
+ }
+
+ // Check if it's an end tag
+ $is_end_tag = (strpos($segment,'/') === 0);
+ if ($is_end_tag) {
+ $type = substr($segment, 1);
+ $token = new HTMLPurifier_Token_End($type);
+ if ($maintain_line_numbers) {
+ $token->rawPosition($current_line, $current_col);
+ $current_line += $this->substrCount($html, $nl, $cursor, $position_next_gt - $cursor);
+ }
+ $array[] = $token;
+ $inside_tag = false;
+ $cursor = $position_next_gt + 1;
+ continue;
+ }
+
+ // Check leading character is alnum, if not, we may
+ // have accidently grabbed an emoticon. Translate into
+ // text and go our merry way
+ if (!ctype_alpha($segment[0])) {
+ // XML: $segment[0] !== '_' && $segment[0] !== ':'
+ if ($e) $e->send(E_NOTICE, 'Lexer: Unescaped lt');
+ $token = new HTMLPurifier_Token_Text('<');
+ if ($maintain_line_numbers) {
+ $token->rawPosition($current_line, $current_col);
+ $current_line += $this->substrCount($html, $nl, $cursor, $position_next_gt - $cursor);
+ }
+ $array[] = $token;
+ $inside_tag = false;
+ continue;
+ }
+
+ // Check if it is explicitly self closing, if so, remove
+ // trailing slash. Remember, we could have a tag like , so
+ // any later token processing scripts must convert improperly
+ // classified EmptyTags from StartTags.
+ $is_self_closing = (strrpos($segment,'/') === $strlen_segment-1);
+ if ($is_self_closing) {
+ $strlen_segment--;
+ $segment = substr($segment, 0, $strlen_segment);
+ }
+
+ // Check if there are any attributes
+ $position_first_space = strcspn($segment, $this->_whitespace);
+
+ if ($position_first_space >= $strlen_segment) {
+ if ($is_self_closing) {
+ $token = new HTMLPurifier_Token_Empty($segment);
+ } else {
+ $token = new HTMLPurifier_Token_Start($segment);
+ }
+ if ($maintain_line_numbers) {
+ $token->rawPosition($current_line, $current_col);
+ $current_line += $this->substrCount($html, $nl, $cursor, $position_next_gt - $cursor);
+ }
+ $array[] = $token;
+ $inside_tag = false;
+ $cursor = $position_next_gt + 1;
+ continue;
+ }
+
+ // Grab out all the data
+ $type = substr($segment, 0, $position_first_space);
+ $attribute_string =
+ trim(
+ substr(
+ $segment, $position_first_space
+ )
+ );
+ if ($attribute_string) {
+ $attr = $this->parseAttributeString(
+ $attribute_string
+ , $config, $context
+ );
+ } else {
+ $attr = array();
+ }
+
+ if ($is_self_closing) {
+ $token = new HTMLPurifier_Token_Empty($type, $attr);
+ } else {
+ $token = new HTMLPurifier_Token_Start($type, $attr);
+ }
+ if ($maintain_line_numbers) {
+ $token->rawPosition($current_line, $current_col);
+ $current_line += $this->substrCount($html, $nl, $cursor, $position_next_gt - $cursor);
+ }
+ $array[] = $token;
+ $cursor = $position_next_gt + 1;
+ $inside_tag = false;
+ continue;
+ } else {
+ // inside tag, but there's no ending > sign
+ if ($e) $e->send(E_WARNING, 'Lexer: Missing gt');
+ $token = new
+ HTMLPurifier_Token_Text(
+ '<' .
+ $this->parseData(
+ substr($html, $cursor)
+ )
+ );
+ if ($maintain_line_numbers) $token->rawPosition($current_line, $current_col);
+ // no cursor scroll? Hmm...
+ $array[] = $token;
+ break;
+ }
+ break;
+ }
+
+ $context->destroy('CurrentLine');
+ $context->destroy('CurrentCol');
+ return $array;
+ }
+
+ /**
+ * PHP 5.0.x compatible substr_count that implements offset and length
+ */
+ protected function substrCount($haystack, $needle, $offset, $length) {
+ static $oldVersion;
+ if ($oldVersion === null) {
+ $oldVersion = version_compare(PHP_VERSION, '5.1', '<');
+ }
+ if ($oldVersion) {
+ $haystack = substr($haystack, $offset, $length);
+ return substr_count($haystack, $needle);
+ } else {
+ return substr_count($haystack, $needle, $offset, $length);
+ }
+ }
+
+ /**
+ * Takes the inside of an HTML tag and makes an assoc array of attributes.
+ *
+ * @param $string Inside of tag excluding name.
+ * @returns Assoc array of attributes.
+ */
+ public function parseAttributeString($string, $config, $context) {
+ $string = (string) $string; // quick typecast
+
+ if ($string == '') return array(); // no attributes
+
+ $e = false;
+ if ($config->get('Core.CollectErrors')) {
+ $e =& $context->get('ErrorCollector');
+ }
+
+ // let's see if we can abort as quickly as possible
+ // one equal sign, no spaces => one attribute
+ $num_equal = substr_count($string, '=');
+ $has_space = strpos($string, ' ');
+ if ($num_equal === 0 && !$has_space) {
+ // bool attribute
+ return array($string => $string);
+ } elseif ($num_equal === 1 && !$has_space) {
+ // only one attribute
+ list($key, $quoted_value) = explode('=', $string);
+ $quoted_value = trim($quoted_value);
+ if (!$key) {
+ if ($e) $e->send(E_ERROR, 'Lexer: Missing attribute key');
+ return array();
+ }
+ if (!$quoted_value) return array($key => '');
+ $first_char = @$quoted_value[0];
+ $last_char = @$quoted_value[strlen($quoted_value)-1];
+
+ $same_quote = ($first_char == $last_char);
+ $open_quote = ($first_char == '"' || $first_char == "'");
+
+ if ( $same_quote && $open_quote) {
+ // well behaved
+ $value = substr($quoted_value, 1, strlen($quoted_value) - 2);
+ } else {
+ // not well behaved
+ if ($open_quote) {
+ if ($e) $e->send(E_ERROR, 'Lexer: Missing end quote');
+ $value = substr($quoted_value, 1);
+ } else {
+ $value = $quoted_value;
+ }
+ }
+ if ($value === false) $value = '';
+ return array($key => $this->parseData($value));
+ }
+
+ // setup loop environment
+ $array = array(); // return assoc array of attributes
+ $cursor = 0; // current position in string (moves forward)
+ $size = strlen($string); // size of the string (stays the same)
+
+ // if we have unquoted attributes, the parser expects a terminating
+ // space, so let's guarantee that there's always a terminating space.
+ $string .= ' ';
+
+ while(true) {
+
+ if ($cursor >= $size) {
+ break;
+ }
+
+ $cursor += ($value = strspn($string, $this->_whitespace, $cursor));
+ // grab the key
+
+ $key_begin = $cursor; //we're currently at the start of the key
+
+ // scroll past all characters that are the key (not whitespace or =)
+ $cursor += strcspn($string, $this->_whitespace . '=', $cursor);
+
+ $key_end = $cursor; // now at the end of the key
+
+ $key = substr($string, $key_begin, $key_end - $key_begin);
+
+ if (!$key) {
+ if ($e) $e->send(E_ERROR, 'Lexer: Missing attribute key');
+ $cursor += strcspn($string, $this->_whitespace, $cursor + 1); // prevent infinite loop
+ continue; // empty key
+ }
+
+ // scroll past all whitespace
+ $cursor += strspn($string, $this->_whitespace, $cursor);
+
+ if ($cursor >= $size) {
+ $array[$key] = $key;
+ break;
+ }
+
+ // if the next character is an equal sign, we've got a regular
+ // pair, otherwise, it's a bool attribute
+ $first_char = @$string[$cursor];
+
+ if ($first_char == '=') {
+ // key="value"
+
+ $cursor++;
+ $cursor += strspn($string, $this->_whitespace, $cursor);
+
+ if ($cursor === false) {
+ $array[$key] = '';
+ break;
+ }
+
+ // we might be in front of a quote right now
+
+ $char = @$string[$cursor];
+
+ if ($char == '"' || $char == "'") {
+ // it's quoted, end bound is $char
+ $cursor++;
+ $value_begin = $cursor;
+ $cursor = strpos($string, $char, $cursor);
+ $value_end = $cursor;
+ } else {
+ // it's not quoted, end bound is whitespace
+ $value_begin = $cursor;
+ $cursor += strcspn($string, $this->_whitespace, $cursor);
+ $value_end = $cursor;
+ }
+
+ // we reached a premature end
+ if ($cursor === false) {
+ $cursor = $size;
+ $value_end = $cursor;
+ }
+
+ $value = substr($string, $value_begin, $value_end - $value_begin);
+ if ($value === false) $value = '';
+ $array[$key] = $this->parseData($value);
+ $cursor++;
+
+ } else {
+ // boolattr
+ if ($key !== '') {
+ $array[$key] = $key;
+ } else {
+ // purely theoretical
+ if ($e) $e->send(E_ERROR, 'Lexer: Missing attribute key');
+ }
+
+ }
+ }
+ return $array;
+ }
+
+}
+
+
+
+
+
+/**
+ * Composite strategy that runs multiple strategies on tokens.
+ */
+abstract class HTMLPurifier_Strategy_Composite extends HTMLPurifier_Strategy
+{
+
+ /**
+ * List of strategies to run tokens through.
+ */
+ protected $strategies = array();
+
+ public function execute($tokens, $config, $context) {
+ foreach ($this->strategies as $strategy) {
+ $tokens = $strategy->execute($tokens, $config, $context);
+ }
+ return $tokens;
+ }
+
+}
+
+
+
+
+
+/**
+ * Core strategy composed of the big four strategies.
+ */
+class HTMLPurifier_Strategy_Core extends HTMLPurifier_Strategy_Composite
+{
+
+ public function __construct() {
+ $this->strategies[] = new HTMLPurifier_Strategy_RemoveForeignElements();
+ $this->strategies[] = new HTMLPurifier_Strategy_MakeWellFormed();
+ $this->strategies[] = new HTMLPurifier_Strategy_FixNesting();
+ $this->strategies[] = new HTMLPurifier_Strategy_ValidateAttributes();
+ }
+
+}
+
+
+
+
+
+/**
+ * Takes a well formed list of tokens and fixes their nesting.
+ *
+ * HTML elements dictate which elements are allowed to be their children,
+ * for example, you can't have a p tag in a span tag. Other elements have
+ * much more rigorous definitions: tables, for instance, require a specific
+ * order for their elements. There are also constraints not expressible by
+ * document type definitions, such as the chameleon nature of ins/del
+ * tags and global child exclusions.
+ *
+ * The first major objective of this strategy is to iterate through all the
+ * nodes (not tokens) of the list of tokens and determine whether or not
+ * their children conform to the element's definition. If they do not, the
+ * child definition may optionally supply an amended list of elements that
+ * is valid or require that the entire node be deleted (and the previous
+ * node rescanned).
+ *
+ * The second objective is to ensure that explicitly excluded elements of
+ * an element do not appear in its children. Code that accomplishes this
+ * task is pervasive through the strategy, though the two are distinct tasks
+ * and could, theoretically, be seperated (although it's not recommended).
+ *
+ * @note Whether or not unrecognized children are silently dropped or
+ * translated into text depends on the child definitions.
+ *
+ * @todo Enable nodes to be bubbled out of the structure.
+ *
+ * @warning This algorithm (though it may be hard to see) proceeds from
+ * a top-down fashion. Thus, parents are processed before
+ * children. This is easy to implement and has a nice effiency
+ * benefit, in that if a node is removed, we never waste any
+ * time processing it, but it also means that if a child
+ * changes in a non-encapsulated way (e.g. it is removed), we
+ * need to go back and reprocess the parent to see if those
+ * changes resulted in problems for the parent. See
+ * [BACKTRACK] for an example of this. In the current
+ * implementation, this backtracking can only be triggered when
+ * a node is removed and if that node was the sole node, the
+ * parent would need to be removed. As such, it is easy to see
+ * that backtracking only incurs constant overhead. If more
+ * sophisticated backtracking is implemented, care must be
+ * taken to avoid nontermination or exponential blowup.
+ */
+
+class HTMLPurifier_Strategy_FixNesting extends HTMLPurifier_Strategy
+{
+
+ public function execute($tokens, $config, $context) {
+ //####################################################################//
+ // Pre-processing
+
+ // get a copy of the HTML definition
+ $definition = $config->getHTMLDefinition();
+
+ $excludes_enabled = !$config->get('Core.DisableExcludes');
+
+ // insert implicit "parent" node, will be removed at end.
+ // DEFINITION CALL
+ $parent_name = $definition->info_parent;
+ array_unshift($tokens, new HTMLPurifier_Token_Start($parent_name));
+ $tokens[] = new HTMLPurifier_Token_End($parent_name);
+
+ // setup the context variable 'IsInline', for chameleon processing
+ // is 'false' when we are not inline, 'true' when it must always
+ // be inline, and an integer when it is inline for a certain
+ // branch of the document tree
+ $is_inline = $definition->info_parent_def->descendants_are_inline;
+ $context->register('IsInline', $is_inline);
+
+ // setup error collector
+ $e =& $context->get('ErrorCollector', true);
+
+ //####################################################################//
+ // Loop initialization
+
+ // stack that contains the indexes of all parents,
+ // $stack[count($stack)-1] being the current parent
+ $stack = array();
+
+ // stack that contains all elements that are excluded
+ // it is organized by parent elements, similar to $stack,
+ // but it is only populated when an element with exclusions is
+ // processed, i.e. there won't be empty exclusions.
+ $exclude_stack = array();
+
+ // variable that contains the start token while we are processing
+ // nodes. This enables error reporting to do its job
+ $start_token = false;
+ $context->register('CurrentToken', $start_token);
+
+ //####################################################################//
+ // Loop
+
+ // iterate through all start nodes. Determining the start node
+ // is complicated so it has been omitted from the loop construct
+ for ($i = 0, $size = count($tokens) ; $i < $size; ) {
+
+ //################################################################//
+ // Gather information on children
+
+ // child token accumulator
+ $child_tokens = array();
+
+ // scroll to the end of this node, report number, and collect
+ // all children
+ for ($j = $i, $depth = 0; ; $j++) {
+ if ($tokens[$j] instanceof HTMLPurifier_Token_Start) {
+ $depth++;
+ // skip token assignment on first iteration, this is the
+ // token we currently are on
+ if ($depth == 1) continue;
+ } elseif ($tokens[$j] instanceof HTMLPurifier_Token_End) {
+ $depth--;
+ // skip token assignment on last iteration, this is the
+ // end token of the token we're currently on
+ if ($depth == 0) break;
+ }
+ $child_tokens[] = $tokens[$j];
+ }
+
+ // $i is index of start token
+ // $j is index of end token
+
+ $start_token = $tokens[$i]; // to make token available via CurrentToken
+
+ //################################################################//
+ // Gather information on parent
+
+ // calculate parent information
+ if ($count = count($stack)) {
+ $parent_index = $stack[$count-1];
+ $parent_name = $tokens[$parent_index]->name;
+ if ($parent_index == 0) {
+ $parent_def = $definition->info_parent_def;
+ } else {
+ $parent_def = $definition->info[$parent_name];
+ }
+ } else {
+ // processing as if the parent were the "root" node
+ // unknown info, it won't be used anyway, in the future,
+ // we may want to enforce one element only (this is
+ // necessary for HTML Purifier to clean entire documents
+ $parent_index = $parent_name = $parent_def = null;
+ }
+
+ // calculate context
+ if ($is_inline === false) {
+ // check if conditions make it inline
+ if (!empty($parent_def) && $parent_def->descendants_are_inline) {
+ $is_inline = $count - 1;
+ }
+ } else {
+ // check if we're out of inline
+ if ($count === $is_inline) {
+ $is_inline = false;
+ }
+ }
+
+ //################################################################//
+ // Determine whether element is explicitly excluded SGML-style
+
+ // determine whether or not element is excluded by checking all
+ // parent exclusions. The array should not be very large, two
+ // elements at most.
+ $excluded = false;
+ if (!empty($exclude_stack) && $excludes_enabled) {
+ foreach ($exclude_stack as $lookup) {
+ if (isset($lookup[$tokens[$i]->name])) {
+ $excluded = true;
+ // no need to continue processing
+ break;
+ }
+ }
+ }
+
+ //################################################################//
+ // Perform child validation
+
+ if ($excluded) {
+ // there is an exclusion, remove the entire node
+ $result = false;
+ $excludes = array(); // not used, but good to initialize anyway
+ } else {
+ // DEFINITION CALL
+ if ($i === 0) {
+ // special processing for the first node
+ $def = $definition->info_parent_def;
+ } else {
+ $def = $definition->info[$tokens[$i]->name];
+
+ }
+
+ if (!empty($def->child)) {
+ // have DTD child def validate children
+ $result = $def->child->validateChildren(
+ $child_tokens, $config, $context);
+ } else {
+ // weird, no child definition, get rid of everything
+ $result = false;
+ }
+
+ // determine whether or not this element has any exclusions
+ $excludes = $def->excludes;
+ }
+
+ // $result is now a bool or array
+
+ //################################################################//
+ // Process result by interpreting $result
+
+ if ($result === true || $child_tokens === $result) {
+ // leave the node as is
+
+ // register start token as a parental node start
+ $stack[] = $i;
+
+ // register exclusions if there are any
+ if (!empty($excludes)) $exclude_stack[] = $excludes;
+
+ // move cursor to next possible start node
+ $i++;
+
+ } elseif($result === false) {
+ // remove entire node
+
+ if ($e) {
+ if ($excluded) {
+ $e->send(E_ERROR, 'Strategy_FixNesting: Node excluded');
+ } else {
+ $e->send(E_ERROR, 'Strategy_FixNesting: Node removed');
+ }
+ }
+
+ // calculate length of inner tokens and current tokens
+ $length = $j - $i + 1;
+
+ // perform removal
+ array_splice($tokens, $i, $length);
+
+ // update size
+ $size -= $length;
+
+ // there is no start token to register,
+ // current node is now the next possible start node
+ // unless it turns out that we need to do a double-check
+
+ // this is a rought heuristic that covers 100% of HTML's
+ // cases and 99% of all other cases. A child definition
+ // that would be tricked by this would be something like:
+ // ( | a b c) where it's all or nothing. Fortunately,
+ // our current implementation claims that that case would
+ // not allow empty, even if it did
+ if (!$parent_def->child->allow_empty) {
+ // we need to do a double-check [BACKTRACK]
+ $i = $parent_index;
+ array_pop($stack);
+ }
+
+ // PROJECTED OPTIMIZATION: Process all children elements before
+ // reprocessing parent node.
+
+ } else {
+ // replace node with $result
+
+ // calculate length of inner tokens
+ $length = $j - $i - 1;
+
+ if ($e) {
+ if (empty($result) && $length) {
+ $e->send(E_ERROR, 'Strategy_FixNesting: Node contents removed');
+ } else {
+ $e->send(E_WARNING, 'Strategy_FixNesting: Node reorganized');
+ }
+ }
+
+ // perform replacement
+ array_splice($tokens, $i + 1, $length, $result);
+
+ // update size
+ $size -= $length;
+ $size += count($result);
+
+ // register start token as a parental node start
+ $stack[] = $i;
+
+ // register exclusions if there are any
+ if (!empty($excludes)) $exclude_stack[] = $excludes;
+
+ // move cursor to next possible start node
+ $i++;
+
+ }
+
+ //################################################################//
+ // Scroll to next start node
+
+ // We assume, at this point, that $i is the index of the token
+ // that is the first possible new start point for a node.
+
+ // Test if the token indeed is a start tag, if not, move forward
+ // and test again.
+ $size = count($tokens);
+ while ($i < $size and !$tokens[$i] instanceof HTMLPurifier_Token_Start) {
+ if ($tokens[$i] instanceof HTMLPurifier_Token_End) {
+ // pop a token index off the stack if we ended a node
+ array_pop($stack);
+ // pop an exclusion lookup off exclusion stack if
+ // we ended node and that node had exclusions
+ if ($i == 0 || $i == $size - 1) {
+ // use specialized var if it's the super-parent
+ $s_excludes = $definition->info_parent_def->excludes;
+ } else {
+ $s_excludes = $definition->info[$tokens[$i]->name]->excludes;
+ }
+ if ($s_excludes) {
+ array_pop($exclude_stack);
+ }
+ }
+ $i++;
+ }
+
+ }
+
+ //####################################################################//
+ // Post-processing
+
+ // remove implicit parent tokens at the beginning and end
+ array_shift($tokens);
+ array_pop($tokens);
+
+ // remove context variables
+ $context->destroy('IsInline');
+ $context->destroy('CurrentToken');
+
+ //####################################################################//
+ // Return
+
+ return $tokens;
+
+ }
+
+}
+
+
+
+
+
+/**
+ * Takes tokens makes them well-formed (balance end tags, etc.)
+ *
+ * Specification of the armor attributes this strategy uses:
+ *
+ * - MakeWellFormed_TagClosedError: This armor field is used to
+ * suppress tag closed errors for certain tokens [TagClosedSuppress],
+ * in particular, if a tag was generated automatically by HTML
+ * Purifier, we may rely on our infrastructure to close it for us
+ * and shouldn't report an error to the user [TagClosedAuto].
+ */
+class HTMLPurifier_Strategy_MakeWellFormed extends HTMLPurifier_Strategy
+{
+
+ /**
+ * Array stream of tokens being processed.
+ */
+ protected $tokens;
+
+ /**
+ * Current index in $tokens.
+ */
+ protected $t;
+
+ /**
+ * Current nesting of elements.
+ */
+ protected $stack;
+
+ /**
+ * Injectors active in this stream processing.
+ */
+ protected $injectors;
+
+ /**
+ * Current instance of HTMLPurifier_Config.
+ */
+ protected $config;
+
+ /**
+ * Current instance of HTMLPurifier_Context.
+ */
+ protected $context;
+
+ public function execute($tokens, $config, $context) {
+
+ $definition = $config->getHTMLDefinition();
+
+ // local variables
+ $generator = new HTMLPurifier_Generator($config, $context);
+ $escape_invalid_tags = $config->get('Core.EscapeInvalidTags');
+ // used for autoclose early abortion
+ $global_parent_allowed_elements = array();
+ if (isset($definition->info[$definition->info_parent])) {
+ // may be unset under testing circumstances
+ $global_parent_allowed_elements = $definition->info[$definition->info_parent]->child->getAllowedElements($config);
+ }
+ $e = $context->get('ErrorCollector', true);
+ $t = false; // token index
+ $i = false; // injector index
+ $token = false; // the current token
+ $reprocess = false; // whether or not to reprocess the same token
+ $stack = array();
+
+ // member variables
+ $this->stack =& $stack;
+ $this->t =& $t;
+ $this->tokens =& $tokens;
+ $this->config = $config;
+ $this->context = $context;
+
+ // context variables
+ $context->register('CurrentNesting', $stack);
+ $context->register('InputIndex', $t);
+ $context->register('InputTokens', $tokens);
+ $context->register('CurrentToken', $token);
+
+ // -- begin INJECTOR --
+
+ $this->injectors = array();
+
+ $injectors = $config->getBatch('AutoFormat');
+ $def_injectors = $definition->info_injector;
+ $custom_injectors = $injectors['Custom'];
+ unset($injectors['Custom']); // special case
+ foreach ($injectors as $injector => $b) {
+ // XXX: Fix with a legitimate lookup table of enabled filters
+ if (strpos($injector, '.') !== false) continue;
+ $injector = "HTMLPurifier_Injector_$injector";
+ if (!$b) continue;
+ $this->injectors[] = new $injector;
+ }
+ foreach ($def_injectors as $injector) {
+ // assumed to be objects
+ $this->injectors[] = $injector;
+ }
+ foreach ($custom_injectors as $injector) {
+ if (!$injector) continue;
+ if (is_string($injector)) {
+ $injector = "HTMLPurifier_Injector_$injector";
+ $injector = new $injector;
+ }
+ $this->injectors[] = $injector;
+ }
+
+ // give the injectors references to the definition and context
+ // variables for performance reasons
+ foreach ($this->injectors as $ix => $injector) {
+ $error = $injector->prepare($config, $context);
+ if (!$error) continue;
+ array_splice($this->injectors, $ix, 1); // rm the injector
+ trigger_error("Cannot enable {$injector->name} injector because $error is not allowed", E_USER_WARNING);
+ }
+
+ // -- end INJECTOR --
+
+ // a note on reprocessing:
+ // In order to reduce code duplication, whenever some code needs
+ // to make HTML changes in order to make things "correct", the
+ // new HTML gets sent through the purifier, regardless of its
+ // status. This means that if we add a start token, because it
+ // was totally necessary, we don't have to update nesting; we just
+ // punt ($reprocess = true; continue;) and it does that for us.
+
+ // isset is in loop because $tokens size changes during loop exec
+ for (
+ $t = 0;
+ $t == 0 || isset($tokens[$t - 1]);
+ // only increment if we don't need to reprocess
+ $reprocess ? $reprocess = false : $t++
+ ) {
+
+ // check for a rewind
+ if (is_int($i) && $i >= 0) {
+ // possibility: disable rewinding if the current token has a
+ // rewind set on it already. This would offer protection from
+ // infinite loop, but might hinder some advanced rewinding.
+ $rewind_to = $this->injectors[$i]->getRewind();
+ if (is_int($rewind_to) && $rewind_to < $t) {
+ if ($rewind_to < 0) $rewind_to = 0;
+ while ($t > $rewind_to) {
+ $t--;
+ $prev = $tokens[$t];
+ // indicate that other injectors should not process this token,
+ // but we need to reprocess it
+ unset($prev->skip[$i]);
+ $prev->rewind = $i;
+ if ($prev instanceof HTMLPurifier_Token_Start) array_pop($this->stack);
+ elseif ($prev instanceof HTMLPurifier_Token_End) $this->stack[] = $prev->start;
+ }
+ }
+ $i = false;
+ }
+
+ // handle case of document end
+ if (!isset($tokens[$t])) {
+ // kill processing if stack is empty
+ if (empty($this->stack)) break;
+
+ // peek
+ $top_nesting = array_pop($this->stack);
+ $this->stack[] = $top_nesting;
+
+ // send error [TagClosedSuppress]
+ if ($e && !isset($top_nesting->armor['MakeWellFormed_TagClosedError'])) {
+ $e->send(E_NOTICE, 'Strategy_MakeWellFormed: Tag closed by document end', $top_nesting);
+ }
+
+ // append, don't splice, since this is the end
+ $tokens[] = new HTMLPurifier_Token_End($top_nesting->name);
+
+ // punt!
+ $reprocess = true;
+ continue;
+ }
+
+ $token = $tokens[$t];
+
+ //echo ' '; printTokens($tokens, $t); printTokens($this->stack);
+ //flush();
+
+ // quick-check: if it's not a tag, no need to process
+ if (empty($token->is_tag)) {
+ if ($token instanceof HTMLPurifier_Token_Text) {
+ foreach ($this->injectors as $i => $injector) {
+ if (isset($token->skip[$i])) continue;
+ if ($token->rewind !== null && $token->rewind !== $i) continue;
+ $injector->handleText($token);
+ $this->processToken($token, $i);
+ $reprocess = true;
+ break;
+ }
+ }
+ // another possibility is a comment
+ continue;
+ }
+
+ if (isset($definition->info[$token->name])) {
+ $type = $definition->info[$token->name]->child->type;
+ } else {
+ $type = false; // Type is unknown, treat accordingly
+ }
+
+ // quick tag checks: anything that's *not* an end tag
+ $ok = false;
+ if ($type === 'empty' && $token instanceof HTMLPurifier_Token_Start) {
+ // claims to be a start tag but is empty
+ $token = new HTMLPurifier_Token_Empty($token->name, $token->attr, $token->line, $token->col, $token->armor);
+ $ok = true;
+ } elseif ($type && $type !== 'empty' && $token instanceof HTMLPurifier_Token_Empty) {
+ // claims to be empty but really is a start tag
+ $this->swap(new HTMLPurifier_Token_End($token->name));
+ $this->insertBefore(new HTMLPurifier_Token_Start($token->name, $token->attr, $token->line, $token->col, $token->armor));
+ // punt (since we had to modify the input stream in a non-trivial way)
+ $reprocess = true;
+ continue;
+ } elseif ($token instanceof HTMLPurifier_Token_Empty) {
+ // real empty token
+ $ok = true;
+ } elseif ($token instanceof HTMLPurifier_Token_Start) {
+ // start tag
+
+ // ...unless they also have to close their parent
+ if (!empty($this->stack)) {
+
+ // Performance note: you might think that it's rather
+ // inefficient, recalculating the autoclose information
+ // for every tag that a token closes (since when we
+ // do an autoclose, we push a new token into the
+ // stream and then /process/ that, before
+ // re-processing this token.) But this is
+ // necessary, because an injector can make an
+ // arbitrary transformations to the autoclosing
+ // tokens we introduce, so things may have changed
+ // in the meantime. Also, doing the inefficient thing is
+ // "easy" to reason about (for certain perverse definitions
+ // of "easy")
+
+ $parent = array_pop($this->stack);
+ $this->stack[] = $parent;
+
+ if (isset($definition->info[$parent->name])) {
+ $elements = $definition->info[$parent->name]->child->getAllowedElements($config);
+ $autoclose = !isset($elements[$token->name]);
+ } else {
+ $autoclose = false;
+ }
+
+ if ($autoclose && $definition->info[$token->name]->wrap) {
+ // Check if an element can be wrapped by another
+ // element to make it valid in a context (for
+ // example,
needs a
in between)
+ $wrapname = $definition->info[$token->name]->wrap;
+ $wrapdef = $definition->info[$wrapname];
+ $elements = $wrapdef->child->getAllowedElements($config);
+ $parent_elements = $definition->info[$parent->name]->child->getAllowedElements($config);
+ if (isset($elements[$token->name]) && isset($parent_elements[$wrapname])) {
+ $newtoken = new HTMLPurifier_Token_Start($wrapname);
+ $this->insertBefore($newtoken);
+ $reprocess = true;
+ continue;
+ }
+ }
+
+ $carryover = false;
+ if ($autoclose && $definition->info[$parent->name]->formatting) {
+ $carryover = true;
+ }
+
+ if ($autoclose) {
+ // check if this autoclose is doomed to fail
+ // (this rechecks $parent, which his harmless)
+ $autoclose_ok = isset($global_parent_allowed_elements[$token->name]);
+ if (!$autoclose_ok) {
+ foreach ($this->stack as $ancestor) {
+ $elements = $definition->info[$ancestor->name]->child->getAllowedElements($config);
+ if (isset($elements[$token->name])) {
+ $autoclose_ok = true;
+ break;
+ }
+ if ($definition->info[$token->name]->wrap) {
+ $wrapname = $definition->info[$token->name]->wrap;
+ $wrapdef = $definition->info[$wrapname];
+ $wrap_elements = $wrapdef->child->getAllowedElements($config);
+ if (isset($wrap_elements[$token->name]) && isset($elements[$wrapname])) {
+ $autoclose_ok = true;
+ break;
+ }
+ }
+ }
+ }
+ if ($autoclose_ok) {
+ // errors need to be updated
+ $new_token = new HTMLPurifier_Token_End($parent->name);
+ $new_token->start = $parent;
+ if ($carryover) {
+ $element = clone $parent;
+ // [TagClosedAuto]
+ $element->armor['MakeWellFormed_TagClosedError'] = true;
+ $element->carryover = true;
+ $this->processToken(array($new_token, $token, $element));
+ } else {
+ $this->insertBefore($new_token);
+ }
+ // [TagClosedSuppress]
+ if ($e && !isset($parent->armor['MakeWellFormed_TagClosedError'])) {
+ if (!$carryover) {
+ $e->send(E_NOTICE, 'Strategy_MakeWellFormed: Tag auto closed', $parent);
+ } else {
+ $e->send(E_NOTICE, 'Strategy_MakeWellFormed: Tag carryover', $parent);
+ }
+ }
+ } else {
+ $this->remove();
+ }
+ $reprocess = true;
+ continue;
+ }
+
+ }
+ $ok = true;
+ }
+
+ if ($ok) {
+ foreach ($this->injectors as $i => $injector) {
+ if (isset($token->skip[$i])) continue;
+ if ($token->rewind !== null && $token->rewind !== $i) continue;
+ $injector->handleElement($token);
+ $this->processToken($token, $i);
+ $reprocess = true;
+ break;
+ }
+ if (!$reprocess) {
+ // ah, nothing interesting happened; do normal processing
+ $this->swap($token);
+ if ($token instanceof HTMLPurifier_Token_Start) {
+ $this->stack[] = $token;
+ } elseif ($token instanceof HTMLPurifier_Token_End) {
+ throw new HTMLPurifier_Exception('Improper handling of end tag in start code; possible error in MakeWellFormed');
+ }
+ }
+ continue;
+ }
+
+ // sanity check: we should be dealing with a closing tag
+ if (!$token instanceof HTMLPurifier_Token_End) {
+ throw new HTMLPurifier_Exception('Unaccounted for tag token in input stream, bug in HTML Purifier');
+ }
+
+ // make sure that we have something open
+ if (empty($this->stack)) {
+ if ($escape_invalid_tags) {
+ if ($e) $e->send(E_WARNING, 'Strategy_MakeWellFormed: Unnecessary end tag to text');
+ $this->swap(new HTMLPurifier_Token_Text(
+ $generator->generateFromToken($token)
+ ));
+ } else {
+ $this->remove();
+ if ($e) $e->send(E_WARNING, 'Strategy_MakeWellFormed: Unnecessary end tag removed');
+ }
+ $reprocess = true;
+ continue;
+ }
+
+ // first, check for the simplest case: everything closes neatly.
+ // Eventually, everything passes through here; if there are problems
+ // we modify the input stream accordingly and then punt, so that
+ // the tokens get processed again.
+ $current_parent = array_pop($this->stack);
+ if ($current_parent->name == $token->name) {
+ $token->start = $current_parent;
+ foreach ($this->injectors as $i => $injector) {
+ if (isset($token->skip[$i])) continue;
+ if ($token->rewind !== null && $token->rewind !== $i) continue;
+ $injector->handleEnd($token);
+ $this->processToken($token, $i);
+ $this->stack[] = $current_parent;
+ $reprocess = true;
+ break;
+ }
+ continue;
+ }
+
+ // okay, so we're trying to close the wrong tag
+
+ // undo the pop previous pop
+ $this->stack[] = $current_parent;
+
+ // scroll back the entire nest, trying to find our tag.
+ // (feature could be to specify how far you'd like to go)
+ $size = count($this->stack);
+ // -2 because -1 is the last element, but we already checked that
+ $skipped_tags = false;
+ for ($j = $size - 2; $j >= 0; $j--) {
+ if ($this->stack[$j]->name == $token->name) {
+ $skipped_tags = array_slice($this->stack, $j);
+ break;
+ }
+ }
+
+ // we didn't find the tag, so remove
+ if ($skipped_tags === false) {
+ if ($escape_invalid_tags) {
+ $this->swap(new HTMLPurifier_Token_Text(
+ $generator->generateFromToken($token)
+ ));
+ if ($e) $e->send(E_WARNING, 'Strategy_MakeWellFormed: Stray end tag to text');
+ } else {
+ $this->remove();
+ if ($e) $e->send(E_WARNING, 'Strategy_MakeWellFormed: Stray end tag removed');
+ }
+ $reprocess = true;
+ continue;
+ }
+
+ // do errors, in REVERSE $j order: a,b,c with
+ $c = count($skipped_tags);
+ if ($e) {
+ for ($j = $c - 1; $j > 0; $j--) {
+ // notice we exclude $j == 0, i.e. the current ending tag, from
+ // the errors... [TagClosedSuppress]
+ if (!isset($skipped_tags[$j]->armor['MakeWellFormed_TagClosedError'])) {
+ $e->send(E_NOTICE, 'Strategy_MakeWellFormed: Tag closed by element end', $skipped_tags[$j]);
+ }
+ }
+ }
+
+ // insert tags, in FORWARD $j order: c,b,a with
+ $replace = array($token);
+ for ($j = 1; $j < $c; $j++) {
+ // ...as well as from the insertions
+ $new_token = new HTMLPurifier_Token_End($skipped_tags[$j]->name);
+ $new_token->start = $skipped_tags[$j];
+ array_unshift($replace, $new_token);
+ if (isset($definition->info[$new_token->name]) && $definition->info[$new_token->name]->formatting) {
+ // [TagClosedAuto]
+ $element = clone $skipped_tags[$j];
+ $element->carryover = true;
+ $element->armor['MakeWellFormed_TagClosedError'] = true;
+ $replace[] = $element;
+ }
+ }
+ $this->processToken($replace);
+ $reprocess = true;
+ continue;
+ }
+
+ $context->destroy('CurrentNesting');
+ $context->destroy('InputTokens');
+ $context->destroy('InputIndex');
+ $context->destroy('CurrentToken');
+
+ unset($this->injectors, $this->stack, $this->tokens, $this->t);
+ return $tokens;
+ }
+
+ /**
+ * Processes arbitrary token values for complicated substitution patterns.
+ * In general:
+ *
+ * If $token is an array, it is a list of tokens to substitute for the
+ * current token. These tokens then get individually processed. If there
+ * is a leading integer in the list, that integer determines how many
+ * tokens from the stream should be removed.
+ *
+ * If $token is a regular token, it is swapped with the current token.
+ *
+ * If $token is false, the current token is deleted.
+ *
+ * If $token is an integer, that number of tokens (with the first token
+ * being the current one) will be deleted.
+ *
+ * @param $token Token substitution value
+ * @param $injector Injector that performed the substitution; default is if
+ * this is not an injector related operation.
+ */
+ protected function processToken($token, $injector = -1) {
+
+ // normalize forms of token
+ if (is_object($token)) $token = array(1, $token);
+ if (is_int($token)) $token = array($token);
+ if ($token === false) $token = array(1);
+ if (!is_array($token)) throw new HTMLPurifier_Exception('Invalid token type from injector');
+ if (!is_int($token[0])) array_unshift($token, 1);
+ if ($token[0] === 0) throw new HTMLPurifier_Exception('Deleting zero tokens is not valid');
+
+ // $token is now an array with the following form:
+ // array(number nodes to delete, new node 1, new node 2, ...)
+
+ $delete = array_shift($token);
+ $old = array_splice($this->tokens, $this->t, $delete, $token);
+
+ if ($injector > -1) {
+ // determine appropriate skips
+ $oldskip = isset($old[0]) ? $old[0]->skip : array();
+ foreach ($token as $object) {
+ $object->skip = $oldskip;
+ $object->skip[$injector] = true;
+ }
+ }
+
+ }
+
+ /**
+ * Inserts a token before the current token. Cursor now points to
+ * this token. You must reprocess after this.
+ */
+ private function insertBefore($token) {
+ array_splice($this->tokens, $this->t, 0, array($token));
+ }
+
+ /**
+ * Removes current token. Cursor now points to new token occupying previously
+ * occupied space. You must reprocess after this.
+ */
+ private function remove() {
+ array_splice($this->tokens, $this->t, 1);
+ }
+
+ /**
+ * Swap current token with new token. Cursor points to new token (no
+ * change). You must reprocess after this.
+ */
+ private function swap($token) {
+ $this->tokens[$this->t] = $token;
+ }
+
+}
+
+
+
+
+
+/**
+ * Removes all unrecognized tags from the list of tokens.
+ *
+ * This strategy iterates through all the tokens and removes unrecognized
+ * tokens. If a token is not recognized but a TagTransform is defined for
+ * that element, the element will be transformed accordingly.
+ */
+
+class HTMLPurifier_Strategy_RemoveForeignElements extends HTMLPurifier_Strategy
+{
+
+ public function execute($tokens, $config, $context) {
+ $definition = $config->getHTMLDefinition();
+ $generator = new HTMLPurifier_Generator($config, $context);
+ $result = array();
+
+ $escape_invalid_tags = $config->get('Core.EscapeInvalidTags');
+ $remove_invalid_img = $config->get('Core.RemoveInvalidImg');
+
+ // currently only used to determine if comments should be kept
+ $trusted = $config->get('HTML.Trusted');
+ $comment_lookup = $config->get('HTML.AllowedComments');
+ $comment_regexp = $config->get('HTML.AllowedCommentsRegexp');
+ $check_comments = $comment_lookup !== array() || $comment_regexp !== null;
+
+ $remove_script_contents = $config->get('Core.RemoveScriptContents');
+ $hidden_elements = $config->get('Core.HiddenElements');
+
+ // remove script contents compatibility
+ if ($remove_script_contents === true) {
+ $hidden_elements['script'] = true;
+ } elseif ($remove_script_contents === false && isset($hidden_elements['script'])) {
+ unset($hidden_elements['script']);
+ }
+
+ $attr_validator = new HTMLPurifier_AttrValidator();
+
+ // removes tokens until it reaches a closing tag with its value
+ $remove_until = false;
+
+ // converts comments into text tokens when this is equal to a tag name
+ $textify_comments = false;
+
+ $token = false;
+ $context->register('CurrentToken', $token);
+
+ $e = false;
+ if ($config->get('Core.CollectErrors')) {
+ $e =& $context->get('ErrorCollector');
+ }
+
+ foreach($tokens as $token) {
+ if ($remove_until) {
+ if (empty($token->is_tag) || $token->name !== $remove_until) {
+ continue;
+ }
+ }
+ if (!empty( $token->is_tag )) {
+ // DEFINITION CALL
+
+ // before any processing, try to transform the element
+ if (
+ isset($definition->info_tag_transform[$token->name])
+ ) {
+ $original_name = $token->name;
+ // there is a transformation for this tag
+ // DEFINITION CALL
+ $token = $definition->
+ info_tag_transform[$token->name]->
+ transform($token, $config, $context);
+ if ($e) $e->send(E_NOTICE, 'Strategy_RemoveForeignElements: Tag transform', $original_name);
+ }
+
+ if (isset($definition->info[$token->name])) {
+
+ // mostly everything's good, but
+ // we need to make sure required attributes are in order
+ if (
+ ($token instanceof HTMLPurifier_Token_Start || $token instanceof HTMLPurifier_Token_Empty) &&
+ $definition->info[$token->name]->required_attr &&
+ ($token->name != 'img' || $remove_invalid_img) // ensure config option still works
+ ) {
+ $attr_validator->validateToken($token, $config, $context);
+ $ok = true;
+ foreach ($definition->info[$token->name]->required_attr as $name) {
+ if (!isset($token->attr[$name])) {
+ $ok = false;
+ break;
+ }
+ }
+ if (!$ok) {
+ if ($e) $e->send(E_ERROR, 'Strategy_RemoveForeignElements: Missing required attribute', $name);
+ continue;
+ }
+ $token->armor['ValidateAttributes'] = true;
+ }
+
+ if (isset($hidden_elements[$token->name]) && $token instanceof HTMLPurifier_Token_Start) {
+ $textify_comments = $token->name;
+ } elseif ($token->name === $textify_comments && $token instanceof HTMLPurifier_Token_End) {
+ $textify_comments = false;
+ }
+
+ } elseif ($escape_invalid_tags) {
+ // invalid tag, generate HTML representation and insert in
+ if ($e) $e->send(E_WARNING, 'Strategy_RemoveForeignElements: Foreign element to text');
+ $token = new HTMLPurifier_Token_Text(
+ $generator->generateFromToken($token)
+ );
+ } else {
+ // check if we need to destroy all of the tag's children
+ // CAN BE GENERICIZED
+ if (isset($hidden_elements[$token->name])) {
+ if ($token instanceof HTMLPurifier_Token_Start) {
+ $remove_until = $token->name;
+ } elseif ($token instanceof HTMLPurifier_Token_Empty) {
+ // do nothing: we're still looking
+ } else {
+ $remove_until = false;
+ }
+ if ($e) $e->send(E_ERROR, 'Strategy_RemoveForeignElements: Foreign meta element removed');
+ } else {
+ if ($e) $e->send(E_ERROR, 'Strategy_RemoveForeignElements: Foreign element removed');
+ }
+ continue;
+ }
+ } elseif ($token instanceof HTMLPurifier_Token_Comment) {
+ // textify comments in script tags when they are allowed
+ if ($textify_comments !== false) {
+ $data = $token->data;
+ $token = new HTMLPurifier_Token_Text($data);
+ } elseif ($trusted || $check_comments) {
+ // always cleanup comments
+ $trailing_hyphen = false;
+ if ($e) {
+ // perform check whether or not there's a trailing hyphen
+ if (substr($token->data, -1) == '-') {
+ $trailing_hyphen = true;
+ }
+ }
+ $token->data = rtrim($token->data, '-');
+ $found_double_hyphen = false;
+ while (strpos($token->data, '--') !== false) {
+ $found_double_hyphen = true;
+ $token->data = str_replace('--', '-', $token->data);
+ }
+ if ($trusted || !empty($comment_lookup[trim($token->data)]) || ($comment_regexp !== NULL && preg_match($comment_regexp, trim($token->data)))) {
+ // OK good
+ if ($e) {
+ if ($trailing_hyphen) {
+ $e->send(E_NOTICE, 'Strategy_RemoveForeignElements: Trailing hyphen in comment removed');
+ }
+ if ($found_double_hyphen) {
+ $e->send(E_NOTICE, 'Strategy_RemoveForeignElements: Hyphens in comment collapsed');
+ }
+ }
+ } else {
+ if ($e) {
+ $e->send(E_NOTICE, 'Strategy_RemoveForeignElements: Comment removed');
+ }
+ continue;
+ }
+ } else {
+ // strip comments
+ if ($e) $e->send(E_NOTICE, 'Strategy_RemoveForeignElements: Comment removed');
+ continue;
+ }
+ } elseif ($token instanceof HTMLPurifier_Token_Text) {
+ } else {
+ continue;
+ }
+ $result[] = $token;
+ }
+ if ($remove_until && $e) {
+ // we removed tokens until the end, throw error
+ $e->send(E_ERROR, 'Strategy_RemoveForeignElements: Token removed to end', $remove_until);
+ }
+
+ $context->destroy('CurrentToken');
+
+ return $result;
+ }
+
+}
+
+
+
+
+
+/**
+ * Validate all attributes in the tokens.
+ */
+
+class HTMLPurifier_Strategy_ValidateAttributes extends HTMLPurifier_Strategy
+{
+
+ public function execute($tokens, $config, $context) {
+
+ // setup validator
+ $validator = new HTMLPurifier_AttrValidator();
+
+ $token = false;
+ $context->register('CurrentToken', $token);
+
+ foreach ($tokens as $key => $token) {
+
+ // only process tokens that have attributes,
+ // namely start and empty tags
+ if (!$token instanceof HTMLPurifier_Token_Start && !$token instanceof HTMLPurifier_Token_Empty) continue;
+
+ // skip tokens that are armored
+ if (!empty($token->armor['ValidateAttributes'])) continue;
+
+ // note that we have no facilities here for removing tokens
+ $validator->validateToken($token, $config, $context);
+
+ $tokens[$key] = $token; // for PHP 4
+ }
+ $context->destroy('CurrentToken');
+
+ return $tokens;
+ }
+
+}
+
+
+
+
+
+/**
+ * Transforms FONT tags to the proper form (SPAN with CSS styling)
+ *
+ * This transformation takes the three proprietary attributes of FONT and
+ * transforms them into their corresponding CSS attributes. These are color,
+ * face, and size.
+ *
+ * @note Size is an interesting case because it doesn't map cleanly to CSS.
+ * Thanks to
+ * http://style.cleverchimp.com/font_size_intervals/altintervals.html
+ * for reasonable mappings.
+ * @warning This doesn't work completely correctly; specifically, this
+ * TagTransform operates before well-formedness is enforced, so
+ * the "active formatting elements" algorithm doesn't get applied.
+ */
+class HTMLPurifier_TagTransform_Font extends HTMLPurifier_TagTransform
+{
+
+ public $transform_to = 'span';
+
+ protected $_size_lookup = array(
+ '0' => 'xx-small',
+ '1' => 'xx-small',
+ '2' => 'small',
+ '3' => 'medium',
+ '4' => 'large',
+ '5' => 'x-large',
+ '6' => 'xx-large',
+ '7' => '300%',
+ '-1' => 'smaller',
+ '-2' => '60%',
+ '+1' => 'larger',
+ '+2' => '150%',
+ '+3' => '200%',
+ '+4' => '300%'
+ );
+
+ public function transform($tag, $config, $context) {
+
+ if ($tag instanceof HTMLPurifier_Token_End) {
+ $new_tag = clone $tag;
+ $new_tag->name = $this->transform_to;
+ return $new_tag;
+ }
+
+ $attr = $tag->attr;
+ $prepend_style = '';
+
+ // handle color transform
+ if (isset($attr['color'])) {
+ $prepend_style .= 'color:' . $attr['color'] . ';';
+ unset($attr['color']);
+ }
+
+ // handle face transform
+ if (isset($attr['face'])) {
+ $prepend_style .= 'font-family:' . $attr['face'] . ';';
+ unset($attr['face']);
+ }
+
+ // handle size transform
+ if (isset($attr['size'])) {
+ // normalize large numbers
+ if ($attr['size'] !== '') {
+ if ($attr['size']{0} == '+' || $attr['size']{0} == '-') {
+ $size = (int) $attr['size'];
+ if ($size < -2) $attr['size'] = '-2';
+ if ($size > 4) $attr['size'] = '+4';
+ } else {
+ $size = (int) $attr['size'];
+ if ($size > 7) $attr['size'] = '7';
+ }
+ }
+ if (isset($this->_size_lookup[$attr['size']])) {
+ $prepend_style .= 'font-size:' .
+ $this->_size_lookup[$attr['size']] . ';';
+ }
+ unset($attr['size']);
+ }
+
+ if ($prepend_style) {
+ $attr['style'] = isset($attr['style']) ?
+ $prepend_style . $attr['style'] :
+ $prepend_style;
+ }
+
+ $new_tag = clone $tag;
+ $new_tag->name = $this->transform_to;
+ $new_tag->attr = $attr;
+
+ return $new_tag;
+
+ }
+}
+
+
+
+
+
+/**
+ * Simple transformation, just change tag name to something else,
+ * and possibly add some styling. This will cover most of the deprecated
+ * tag cases.
+ */
+class HTMLPurifier_TagTransform_Simple extends HTMLPurifier_TagTransform
+{
+
+ protected $style;
+
+ /**
+ * @param $transform_to Tag name to transform to.
+ * @param $style CSS style to add to the tag
+ */
+ public function __construct($transform_to, $style = null) {
+ $this->transform_to = $transform_to;
+ $this->style = $style;
+ }
+
+ public function transform($tag, $config, $context) {
+ $new_tag = clone $tag;
+ $new_tag->name = $this->transform_to;
+ if (!is_null($this->style) &&
+ ($new_tag instanceof HTMLPurifier_Token_Start || $new_tag instanceof HTMLPurifier_Token_Empty)
+ ) {
+ $this->prependCSS($new_tag->attr, $this->style);
+ }
+ return $new_tag;
+ }
+
+}
+
+
+
+
+
+/**
+ * Concrete comment token class. Generally will be ignored.
+ */
+class HTMLPurifier_Token_Comment extends HTMLPurifier_Token
+{
+ public $data; /**< Character data within comment. */
+ public $is_whitespace = true;
+ /**
+ * Transparent constructor.
+ *
+ * @param $data String comment data.
+ */
+ public function __construct($data, $line = null, $col = null) {
+ $this->data = $data;
+ $this->line = $line;
+ $this->col = $col;
+ }
+}
+
+
+
+
+
+/**
+ * Abstract class of a tag token (start, end or empty), and its behavior.
+ */
+class HTMLPurifier_Token_Tag extends HTMLPurifier_Token
+{
+ /**
+ * Static bool marker that indicates the class is a tag.
+ *
+ * This allows us to check objects with !empty($obj->is_tag)
+ * without having to use a function call is_a().
+ */
+ public $is_tag = true;
+
+ /**
+ * The lower-case name of the tag, like 'a', 'b' or 'blockquote'.
+ *
+ * @note Strictly speaking, XML tags are case sensitive, so we shouldn't
+ * be lower-casing them, but these tokens cater to HTML tags, which are
+ * insensitive.
+ */
+ public $name;
+
+ /**
+ * Associative array of the tag's attributes.
+ */
+ public $attr = array();
+
+ /**
+ * Non-overloaded constructor, which lower-cases passed tag name.
+ *
+ * @param $name String name.
+ * @param $attr Associative array of attributes.
+ */
+ public function __construct($name, $attr = array(), $line = null, $col = null, $armor = array()) {
+ $this->name = ctype_lower($name) ? $name : strtolower($name);
+ foreach ($attr as $key => $value) {
+ // normalization only necessary when key is not lowercase
+ if (!ctype_lower($key)) {
+ $new_key = strtolower($key);
+ if (!isset($attr[$new_key])) {
+ $attr[$new_key] = $attr[$key];
+ }
+ if ($new_key !== $key) {
+ unset($attr[$key]);
+ }
+ }
+ }
+ $this->attr = $attr;
+ $this->line = $line;
+ $this->col = $col;
+ $this->armor = $armor;
+ }
+}
+
+
+
+
+
+/**
+ * Concrete empty token class.
+ */
+class HTMLPurifier_Token_Empty extends HTMLPurifier_Token_Tag
+{
+
+}
+
+
+
+
+
+/**
+ * Concrete end token class.
+ *
+ * @warning This class accepts attributes even though end tags cannot. This
+ * is for optimization reasons, as under normal circumstances, the Lexers
+ * do not pass attributes.
+ */
+class HTMLPurifier_Token_End extends HTMLPurifier_Token_Tag
+{
+ /**
+ * Token that started this node. Added by MakeWellFormed. Please
+ * do not edit this!
+ */
+ public $start;
+}
+
+
+
+
+
+/**
+ * Concrete start token class.
+ */
+class HTMLPurifier_Token_Start extends HTMLPurifier_Token_Tag
+{
+
+}
+
+
+
+
+
+/**
+ * Concrete text token class.
+ *
+ * Text tokens comprise of regular parsed character data (PCDATA) and raw
+ * character data (from the CDATA sections). Internally, their
+ * data is parsed with all entities expanded. Surprisingly, the text token
+ * does have a "tag name" called #PCDATA, which is how the DTD represents it
+ * in permissible child nodes.
+ */
+class HTMLPurifier_Token_Text extends HTMLPurifier_Token
+{
+
+ public $name = '#PCDATA'; /**< PCDATA tag name compatible with DTD. */
+ public $data; /**< Parsed character data of text. */
+ public $is_whitespace; /**< Bool indicating if node is whitespace. */
+
+ /**
+ * Constructor, accepts data and determines if it is whitespace.
+ *
+ * @param $data String parsed character data.
+ */
+ public function __construct($data, $line = null, $col = null) {
+ $this->data = $data;
+ $this->is_whitespace = ctype_space($data);
+ $this->line = $line;
+ $this->col = $col;
+ }
+
+}
+
+
+
+
+
+class HTMLPurifier_URIFilter_DisableExternal extends HTMLPurifier_URIFilter
+{
+ public $name = 'DisableExternal';
+ protected $ourHostParts = false;
+ public function prepare($config) {
+ $our_host = $config->getDefinition('URI')->host;
+ if ($our_host !== null) $this->ourHostParts = array_reverse(explode('.', $our_host));
+ }
+ public function filter(&$uri, $config, $context) {
+ if (is_null($uri->host)) return true;
+ if ($this->ourHostParts === false) return false;
+ $host_parts = array_reverse(explode('.', $uri->host));
+ foreach ($this->ourHostParts as $i => $x) {
+ if (!isset($host_parts[$i])) return false;
+ if ($host_parts[$i] != $this->ourHostParts[$i]) return false;
+ }
+ return true;
+ }
+}
+
+
+
+
+
+class HTMLPurifier_URIFilter_DisableExternalResources extends HTMLPurifier_URIFilter_DisableExternal
+{
+ public $name = 'DisableExternalResources';
+ public function filter(&$uri, $config, $context) {
+ if (!$context->get('EmbeddedURI', true)) return true;
+ return parent::filter($uri, $config, $context);
+ }
+}
+
+
+
+
+
+class HTMLPurifier_URIFilter_DisableResources extends HTMLPurifier_URIFilter
+{
+ public $name = 'DisableResources';
+ public function filter(&$uri, $config, $context) {
+ return !$context->get('EmbeddedURI', true);
+ }
+}
+
+
+
+
+
+// It's not clear to me whether or not Punycode means that hostnames
+// do not have canonical forms anymore. As far as I can tell, it's
+// not a problem (punycoding should be identity when no Unicode
+// points are involved), but I'm not 100% sure
+class HTMLPurifier_URIFilter_HostBlacklist extends HTMLPurifier_URIFilter
+{
+ public $name = 'HostBlacklist';
+ protected $blacklist = array();
+ public function prepare($config) {
+ $this->blacklist = $config->get('URI.HostBlacklist');
+ return true;
+ }
+ public function filter(&$uri, $config, $context) {
+ foreach($this->blacklist as $blacklisted_host_fragment) {
+ if (strpos($uri->host, $blacklisted_host_fragment) !== false) {
+ return false;
+ }
+ }
+ return true;
+ }
+}
+
+
+
+
+
+// does not support network paths
+
+class HTMLPurifier_URIFilter_MakeAbsolute extends HTMLPurifier_URIFilter
+{
+ public $name = 'MakeAbsolute';
+ protected $base;
+ protected $basePathStack = array();
+ public function prepare($config) {
+ $def = $config->getDefinition('URI');
+ $this->base = $def->base;
+ if (is_null($this->base)) {
+ trigger_error('URI.MakeAbsolute is being ignored due to lack of value for URI.Base configuration', E_USER_WARNING);
+ return false;
+ }
+ $this->base->fragment = null; // fragment is invalid for base URI
+ $stack = explode('/', $this->base->path);
+ array_pop($stack); // discard last segment
+ $stack = $this->_collapseStack($stack); // do pre-parsing
+ $this->basePathStack = $stack;
+ return true;
+ }
+ public function filter(&$uri, $config, $context) {
+ if (is_null($this->base)) return true; // abort early
+ if (
+ $uri->path === '' && is_null($uri->scheme) &&
+ is_null($uri->host) && is_null($uri->query) && is_null($uri->fragment)
+ ) {
+ // reference to current document
+ $uri = clone $this->base;
+ return true;
+ }
+ if (!is_null($uri->scheme)) {
+ // absolute URI already: don't change
+ if (!is_null($uri->host)) return true;
+ $scheme_obj = $uri->getSchemeObj($config, $context);
+ if (!$scheme_obj) {
+ // scheme not recognized
+ return false;
+ }
+ if (!$scheme_obj->hierarchical) {
+ // non-hierarchal URI with explicit scheme, don't change
+ return true;
+ }
+ // special case: had a scheme but always is hierarchical and had no authority
+ }
+ if (!is_null($uri->host)) {
+ // network path, don't bother
+ return true;
+ }
+ if ($uri->path === '') {
+ $uri->path = $this->base->path;
+ } elseif ($uri->path[0] !== '/') {
+ // relative path, needs more complicated processing
+ $stack = explode('/', $uri->path);
+ $new_stack = array_merge($this->basePathStack, $stack);
+ if ($new_stack[0] !== '' && !is_null($this->base->host)) {
+ array_unshift($new_stack, '');
+ }
+ $new_stack = $this->_collapseStack($new_stack);
+ $uri->path = implode('/', $new_stack);
+ } else {
+ // absolute path, but still we should collapse
+ $uri->path = implode('/', $this->_collapseStack(explode('/', $uri->path)));
+ }
+ // re-combine
+ $uri->scheme = $this->base->scheme;
+ if (is_null($uri->userinfo)) $uri->userinfo = $this->base->userinfo;
+ if (is_null($uri->host)) $uri->host = $this->base->host;
+ if (is_null($uri->port)) $uri->port = $this->base->port;
+ return true;
+ }
+
+ /**
+ * Resolve dots and double-dots in a path stack
+ */
+ private function _collapseStack($stack) {
+ $result = array();
+ $is_folder = false;
+ for ($i = 0; isset($stack[$i]); $i++) {
+ $is_folder = false;
+ // absorb an internally duplicated slash
+ if ($stack[$i] == '' && $i && isset($stack[$i+1])) continue;
+ if ($stack[$i] == '..') {
+ if (!empty($result)) {
+ $segment = array_pop($result);
+ if ($segment === '' && empty($result)) {
+ // error case: attempted to back out too far:
+ // restore the leading slash
+ $result[] = '';
+ } elseif ($segment === '..') {
+ $result[] = '..'; // cannot remove .. with ..
+ }
+ } else {
+ // relative path, preserve the double-dots
+ $result[] = '..';
+ }
+ $is_folder = true;
+ continue;
+ }
+ if ($stack[$i] == '.') {
+ // silently absorb
+ $is_folder = true;
+ continue;
+ }
+ $result[] = $stack[$i];
+ }
+ if ($is_folder) $result[] = '';
+ return $result;
+ }
+}
+
+
+
+
+
+class HTMLPurifier_URIFilter_Munge extends HTMLPurifier_URIFilter
+{
+ public $name = 'Munge';
+ public $post = true;
+ private $target, $parser, $doEmbed, $secretKey;
+
+ protected $replace = array();
+
+ public function prepare($config) {
+ $this->target = $config->get('URI.' . $this->name);
+ $this->parser = new HTMLPurifier_URIParser();
+ $this->doEmbed = $config->get('URI.MungeResources');
+ $this->secretKey = $config->get('URI.MungeSecretKey');
+ return true;
+ }
+ public function filter(&$uri, $config, $context) {
+ if ($context->get('EmbeddedURI', true) && !$this->doEmbed) return true;
+
+ $scheme_obj = $uri->getSchemeObj($config, $context);
+ if (!$scheme_obj) return true; // ignore unknown schemes, maybe another postfilter did it
+ if (!$scheme_obj->browsable) return true; // ignore non-browseable schemes, since we can't munge those in a reasonable way
+ if ($uri->isBenign($config, $context)) return true; // don't redirect if a benign URL
+
+ $this->makeReplace($uri, $config, $context);
+ $this->replace = array_map('rawurlencode', $this->replace);
+
+ $new_uri = strtr($this->target, $this->replace);
+ $new_uri = $this->parser->parse($new_uri);
+ // don't redirect if the target host is the same as the
+ // starting host
+ if ($uri->host === $new_uri->host) return true;
+ $uri = $new_uri; // overwrite
+ return true;
+ }
+
+ protected function makeReplace($uri, $config, $context) {
+ $string = $uri->toString();
+ // always available
+ $this->replace['%s'] = $string;
+ $this->replace['%r'] = $context->get('EmbeddedURI', true);
+ $token = $context->get('CurrentToken', true);
+ $this->replace['%n'] = $token ? $token->name : null;
+ $this->replace['%m'] = $context->get('CurrentAttr', true);
+ $this->replace['%p'] = $context->get('CurrentCSSProperty', true);
+ // not always available
+ if ($this->secretKey) $this->replace['%t'] = sha1($this->secretKey . ':' . $string);
+ }
+
+}
+
+
+
+
+
+/**
+ * Implements safety checks for safe iframes.
+ *
+ * @warning This filter is *critical* for ensuring that %HTML.SafeIframe
+ * works safely.
+ */
+class HTMLPurifier_URIFilter_SafeIframe extends HTMLPurifier_URIFilter
+{
+ public $name = 'SafeIframe';
+ public $always_load = true;
+ protected $regexp = NULL;
+ // XXX: The not so good bit about how this is all setup now is we
+ // can't check HTML.SafeIframe in the 'prepare' step: we have to
+ // defer till the actual filtering.
+ public function prepare($config) {
+ $this->regexp = $config->get('URI.SafeIframeRegexp');
+ return true;
+ }
+ public function filter(&$uri, $config, $context) {
+ // check if filter not applicable
+ if (!$config->get('HTML.SafeIframe')) return true;
+ // check if the filter should actually trigger
+ if (!$context->get('EmbeddedURI', true)) return true;
+ $token = $context->get('CurrentToken', true);
+ if (!($token && $token->name == 'iframe')) return true;
+ // check if we actually have some whitelists enabled
+ if ($this->regexp === null) return false;
+ // actually check the whitelists
+ return preg_match($this->regexp, $uri->toString());
+ }
+}
+
+
+
+
+
+/**
+ * Implements data: URI for base64 encoded images supported by GD.
+ */
+class HTMLPurifier_URIScheme_data extends HTMLPurifier_URIScheme {
+
+ public $browsable = true;
+ public $allowed_types = array(
+ // you better write validation code for other types if you
+ // decide to allow them
+ 'image/jpeg' => true,
+ 'image/gif' => true,
+ 'image/png' => true,
+ );
+ // this is actually irrelevant since we only write out the path
+ // component
+ public $may_omit_host = true;
+
+ public function doValidate(&$uri, $config, $context) {
+ $result = explode(',', $uri->path, 2);
+ $is_base64 = false;
+ $charset = null;
+ $content_type = null;
+ if (count($result) == 2) {
+ list($metadata, $data) = $result;
+ // do some legwork on the metadata
+ $metas = explode(';', $metadata);
+ while(!empty($metas)) {
+ $cur = array_shift($metas);
+ if ($cur == 'base64') {
+ $is_base64 = true;
+ break;
+ }
+ if (substr($cur, 0, 8) == 'charset=') {
+ // doesn't match if there are arbitrary spaces, but
+ // whatever dude
+ if ($charset !== null) continue; // garbage
+ $charset = substr($cur, 8); // not used
+ } else {
+ if ($content_type !== null) continue; // garbage
+ $content_type = $cur;
+ }
+ }
+ } else {
+ $data = $result[0];
+ }
+ if ($content_type !== null && empty($this->allowed_types[$content_type])) {
+ return false;
+ }
+ if ($charset !== null) {
+ // error; we don't allow plaintext stuff
+ $charset = null;
+ }
+ $data = rawurldecode($data);
+ if ($is_base64) {
+ $raw_data = base64_decode($data);
+ } else {
+ $raw_data = $data;
+ }
+ // XXX probably want to refactor this into a general mechanism
+ // for filtering arbitrary content types
+ $file = tempnam("/tmp", "");
+ file_put_contents($file, $raw_data);
+ if (function_exists('exif_imagetype')) {
+ $image_code = exif_imagetype($file);
+ unlink($file);
+ } elseif (function_exists('getimagesize')) {
+ set_error_handler(array($this, 'muteErrorHandler'));
+ $info = getimagesize($file);
+ restore_error_handler();
+ unlink($file);
+ if ($info == false) return false;
+ $image_code = $info[2];
+ } else {
+ trigger_error("could not find exif_imagetype or getimagesize functions", E_USER_ERROR);
+ }
+ $real_content_type = image_type_to_mime_type($image_code);
+ if ($real_content_type != $content_type) {
+ // we're nice guys; if the content type is something else we
+ // support, change it over
+ if (empty($this->allowed_types[$real_content_type])) return false;
+ $content_type = $real_content_type;
+ }
+ // ok, it's kosher, rewrite what we need
+ $uri->userinfo = null;
+ $uri->host = null;
+ $uri->port = null;
+ $uri->fragment = null;
+ $uri->query = null;
+ $uri->path = "$content_type;base64," . base64_encode($raw_data);
+ return true;
+ }
+
+ public function muteErrorHandler($errno, $errstr) {}
+
+}
+
+
+
+
+/**
+ * Validates file as defined by RFC 1630 and RFC 1738.
+ */
+class HTMLPurifier_URIScheme_file extends HTMLPurifier_URIScheme {
+
+ // Generally file:// URLs are not accessible from most
+ // machines, so placing them as an img src is incorrect.
+ public $browsable = false;
+
+ // Basically the *only* URI scheme for which this is true, since
+ // accessing files on the local machine is very common. In fact,
+ // browsers on some operating systems don't understand the
+ // authority, though I hear it is used on Windows to refer to
+ // network shares.
+ public $may_omit_host = true;
+
+ public function doValidate(&$uri, $config, $context) {
+ // Authentication method is not supported
+ $uri->userinfo = null;
+ // file:// makes no provisions for accessing the resource
+ $uri->port = null;
+ // While it seems to work on Firefox, the querystring has
+ // no possible effect and is thus stripped.
+ $uri->query = null;
+ return true;
+ }
+
+}
+
+
+
+
+
+/**
+ * Validates ftp (File Transfer Protocol) URIs as defined by generic RFC 1738.
+ */
+class HTMLPurifier_URIScheme_ftp extends HTMLPurifier_URIScheme {
+
+ public $default_port = 21;
+ public $browsable = true; // usually
+ public $hierarchical = true;
+
+ public function doValidate(&$uri, $config, $context) {
+ $uri->query = null;
+
+ // typecode check
+ $semicolon_pos = strrpos($uri->path, ';'); // reverse
+ if ($semicolon_pos !== false) {
+ $type = substr($uri->path, $semicolon_pos + 1); // no semicolon
+ $uri->path = substr($uri->path, 0, $semicolon_pos);
+ $type_ret = '';
+ if (strpos($type, '=') !== false) {
+ // figure out whether or not the declaration is correct
+ list($key, $typecode) = explode('=', $type, 2);
+ if ($key !== 'type') {
+ // invalid key, tack it back on encoded
+ $uri->path .= '%3B' . $type;
+ } elseif ($typecode === 'a' || $typecode === 'i' || $typecode === 'd') {
+ $type_ret = ";type=$typecode";
+ }
+ } else {
+ $uri->path .= '%3B' . $type;
+ }
+ $uri->path = str_replace(';', '%3B', $uri->path);
+ $uri->path .= $type_ret;
+ }
+
+ return true;
+ }
+
+}
+
+
+
+
+
+/**
+ * Validates http (HyperText Transfer Protocol) as defined by RFC 2616
+ */
+class HTMLPurifier_URIScheme_http extends HTMLPurifier_URIScheme {
+
+ public $default_port = 80;
+ public $browsable = true;
+ public $hierarchical = true;
+
+ public function doValidate(&$uri, $config, $context) {
+ $uri->userinfo = null;
+ return true;
+ }
+
+}
+
+
+
+
+
+/**
+ * Validates https (Secure HTTP) according to http scheme.
+ */
+class HTMLPurifier_URIScheme_https extends HTMLPurifier_URIScheme_http {
+
+ public $default_port = 443;
+ public $secure = true;
+
+}
+
+
+
+
+
+// VERY RELAXED! Shouldn't cause problems, not even Firefox checks if the
+// email is valid, but be careful!
+
+/**
+ * Validates mailto (for E-mail) according to RFC 2368
+ * @todo Validate the email address
+ * @todo Filter allowed query parameters
+ */
+
+class HTMLPurifier_URIScheme_mailto extends HTMLPurifier_URIScheme {
+
+ public $browsable = false;
+ public $may_omit_host = true;
+
+ public function doValidate(&$uri, $config, $context) {
+ $uri->userinfo = null;
+ $uri->host = null;
+ $uri->port = null;
+ // we need to validate path against RFC 2368's addr-spec
+ return true;
+ }
+
+}
+
+
+
+
+
+/**
+ * Validates news (Usenet) as defined by generic RFC 1738
+ */
+class HTMLPurifier_URIScheme_news extends HTMLPurifier_URIScheme {
+
+ public $browsable = false;
+ public $may_omit_host = true;
+
+ public function doValidate(&$uri, $config, $context) {
+ $uri->userinfo = null;
+ $uri->host = null;
+ $uri->port = null;
+ $uri->query = null;
+ // typecode check needed on path
+ return true;
+ }
+
+}
+
+
+
+
+
+/**
+ * Validates nntp (Network News Transfer Protocol) as defined by generic RFC 1738
+ */
+class HTMLPurifier_URIScheme_nntp extends HTMLPurifier_URIScheme {
+
+ public $default_port = 119;
+ public $browsable = false;
+
+ public function doValidate(&$uri, $config, $context) {
+ $uri->userinfo = null;
+ $uri->query = null;
+ return true;
+ }
+
+}
+
+
+
+
+
+/**
+ * Performs safe variable parsing based on types which can be used by
+ * users. This may not be able to represent all possible data inputs,
+ * however.
+ */
+class HTMLPurifier_VarParser_Flexible extends HTMLPurifier_VarParser
+{
+
+ protected function parseImplementation($var, $type, $allow_null) {
+ if ($allow_null && $var === null) return null;
+ switch ($type) {
+ // Note: if code "breaks" from the switch, it triggers a generic
+ // exception to be thrown. Specific errors can be specifically
+ // done here.
+ case self::MIXED :
+ case self::ISTRING :
+ case self::STRING :
+ case self::TEXT :
+ case self::ITEXT :
+ return $var;
+ case self::INT :
+ if (is_string($var) && ctype_digit($var)) $var = (int) $var;
+ return $var;
+ case self::FLOAT :
+ if ((is_string($var) && is_numeric($var)) || is_int($var)) $var = (float) $var;
+ return $var;
+ case self::BOOL :
+ if (is_int($var) && ($var === 0 || $var === 1)) {
+ $var = (bool) $var;
+ } elseif (is_string($var)) {
+ if ($var == 'on' || $var == 'true' || $var == '1') {
+ $var = true;
+ } elseif ($var == 'off' || $var == 'false' || $var == '0') {
+ $var = false;
+ } else {
+ throw new HTMLPurifier_VarParserException("Unrecognized value '$var' for $type");
+ }
+ }
+ return $var;
+ case self::ALIST :
+ case self::HASH :
+ case self::LOOKUP :
+ if (is_string($var)) {
+ // special case: technically, this is an array with
+ // 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 === self::HASH) {
+ // key:value,key2:value2
+ $nvar = array();
+ foreach ($var as $keypair) {
+ $c = explode(':', $keypair, 2);
+ if (!isset($c[1])) continue;
+ $nvar[trim($c[0])] = trim($c[1]);
+ }
+ $var = $nvar;
+ }
+ }
+ if (!is_array($var)) break;
+ $keys = array_keys($var);
+ if ($keys === array_keys($keys)) {
+ if ($type == self::ALIST) return $var;
+ elseif ($type == self::LOOKUP) {
+ $new = array();
+ foreach ($var as $key) {
+ $new[$key] = true;
+ }
+ return $new;
+ } else break;
+ }
+ if ($type === self::ALIST) {
+ trigger_error("Array list did not have consecutive integer indexes", E_USER_WARNING);
+ return array_values($var);
+ }
+ if ($type === self::LOOKUP) {
+ foreach ($var as $key => $value) {
+ if ($value !== true) {
+ trigger_error("Lookup array has non-true value at key '$key'; maybe your input array was not indexed numerically", E_USER_WARNING);
+ }
+ $var[$key] = true;
+ }
+ }
+ return $var;
+ default:
+ $this->errorInconsistent(__CLASS__, $type);
+ }
+ $this->errorGeneric($var, $type);
+ }
+
+}
+
+
+
+
+
+/**
+ * This variable parser uses PHP's internal code engine. Because it does
+ * this, it can represent all inputs; however, it is dangerous and cannot
+ * be used by users.
+ */
+class HTMLPurifier_VarParser_Native extends HTMLPurifier_VarParser
+{
+
+ protected function parseImplementation($var, $type, $allow_null) {
+ return $this->evalExpression($var);
+ }
+
+ protected function evalExpression($expr) {
+ $var = null;
+ $result = eval("\$var = $expr;");
+ if ($result === false) {
+ throw new HTMLPurifier_VarParserException("Fatal error in evaluated code");
+ }
+ return $var;
+ }
+
+}
+
+
+
diff --git a/plugin/htmlpurifier/safeiframe.txt b/plugin/htmlpurifier/safeiframe.txt
new file mode 100644
index 000000000..6484f4ccf
--- /dev/null
+++ b/plugin/htmlpurifier/safeiframe.txt
@@ -0,0 +1,6 @@
+# iframe 허용 도메인을 한줄에 하나씩만 적으세요.
+# 도메인 뒤에 가급적 / 를 붙여주세요.
+www.youtube(?:-nocookie)?.com/
+serviceapi.rmcnmv.naver.com/
+videofarm.daum.net/
+player.vimeo.com/
diff --git a/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/Builder/ConfigSchema.php b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/Builder/ConfigSchema.php
new file mode 100644
index 000000000..c05668a70
--- /dev/null
+++ b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/Builder/ConfigSchema.php
@@ -0,0 +1,44 @@
+directives as $d) {
+ $schema->add(
+ $d->id->key,
+ $d->default,
+ $d->type,
+ $d->typeAllowsNull
+ );
+ if ($d->allowed !== null) {
+ $schema->addAllowedValues(
+ $d->id->key,
+ $d->allowed
+ );
+ }
+ foreach ($d->aliases as $alias) {
+ $schema->addAlias(
+ $alias->key,
+ $d->id->key
+ );
+ }
+ if ($d->valueAliases !== null) {
+ $schema->addValueAliases(
+ $d->id->key,
+ $d->valueAliases
+ );
+ }
+ }
+ $schema->postProcess();
+ return $schema;
+ }
+
+}
+
+// vim: et sw=4 sts=4
diff --git a/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/Builder/Xml.php b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/Builder/Xml.php
new file mode 100644
index 000000000..244561a37
--- /dev/null
+++ b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/Builder/Xml.php
@@ -0,0 +1,106 @@
+startElement('div');
+
+ $purifier = HTMLPurifier::getInstance();
+ $html = $purifier->purify($html);
+ $this->writeAttribute('xmlns', 'http://www.w3.org/1999/xhtml');
+ $this->writeRaw($html);
+
+ $this->endElement(); // div
+ }
+
+ protected function export($var) {
+ if ($var === array()) return 'array()';
+ return var_export($var, true);
+ }
+
+ public function build($interchange) {
+ // global access, only use as last resort
+ $this->interchange = $interchange;
+
+ $this->setIndent(true);
+ $this->startDocument('1.0', 'UTF-8');
+ $this->startElement('configdoc');
+ $this->writeElement('title', $interchange->name);
+
+ foreach ($interchange->directives as $directive) {
+ $this->buildDirective($directive);
+ }
+
+ if ($this->namespace) $this->endElement(); // namespace
+
+ $this->endElement(); // configdoc
+ $this->flush();
+ }
+
+ public function buildDirective($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->startElement('directive');
+ $this->writeAttribute('id', $directive->id->toString());
+
+ $this->writeElement('name', $directive->id->getDirective());
+
+ $this->startElement('aliases');
+ foreach ($directive->aliases as $alias) $this->writeElement('alias', $alias->toString());
+ $this->endElement(); // aliases
+
+ $this->startElement('constraints');
+ if ($directive->version) $this->writeElement('version', $directive->version);
+ $this->startElement('type');
+ if ($directive->typeAllowsNull) $this->writeAttribute('allow-null', 'yes');
+ $this->text($directive->type);
+ $this->endElement(); // type
+ if ($directive->allowed) {
+ $this->startElement('allowed');
+ foreach ($directive->allowed as $value => $x) $this->writeElement('value', $value);
+ $this->endElement(); // allowed
+ }
+ $this->writeElement('default', $this->export($directive->default));
+ $this->writeAttribute('xml:space', 'preserve');
+ if ($directive->external) {
+ $this->startElement('external');
+ foreach ($directive->external as $project) $this->writeElement('project', $project);
+ $this->endElement();
+ }
+ $this->endElement(); // constraints
+
+ if ($directive->deprecatedVersion) {
+ $this->startElement('deprecated');
+ $this->writeElement('version', $directive->deprecatedVersion);
+ $this->writeElement('use', $directive->deprecatedUse->toString());
+ $this->endElement(); // deprecated
+ }
+
+ $this->startElement('description');
+ $this->writeHTMLDiv($directive->description);
+ $this->endElement(); // description
+
+ $this->endElement(); // directive
+ }
+
+}
+
+// vim: et sw=4 sts=4
diff --git a/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/Exception.php b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/Exception.php
new file mode 100644
index 000000000..2671516c5
--- /dev/null
+++ b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/Exception.php
@@ -0,0 +1,11 @@
+ array(directive info)
+ */
+ public $directives = array();
+
+ /**
+ * Adds a directive array to $directives
+ */
+ public function addDirective($directive) {
+ if (isset($this->directives[$i = $directive->id->toString()])) {
+ throw new HTMLPurifier_ConfigSchema_Exception("Cannot redefine directive '$i'");
+ }
+ $this->directives[$i] = $directive;
+ }
+
+ /**
+ * Convenience function to perform standard validation. Throws exception
+ * on failed validation.
+ */
+ public function validate() {
+ $validator = new HTMLPurifier_ConfigSchema_Validator();
+ return $validator->validate($this);
+ }
+
+}
+
+// vim: et sw=4 sts=4
diff --git a/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/Interchange/Directive.php b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/Interchange/Directive.php
new file mode 100644
index 000000000..ac8be0d97
--- /dev/null
+++ b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/Interchange/Directive.php
@@ -0,0 +1,77 @@
+ true).
+ * Null if all values are allowed.
+ */
+ public $allowed;
+
+ /**
+ * List of aliases for the directive,
+ * e.g. array(new HTMLPurifier_ConfigSchema_Interchange_Id('Ns', 'Dir'))).
+ */
+ public $aliases = array();
+
+ /**
+ * Hash of value aliases, e.g. array('alt' => 'real'). Null if value
+ * aliasing is disabled (necessary for non-scalar types).
+ */
+ public $valueAliases;
+
+ /**
+ * Version of HTML Purifier the directive was introduced, e.g. '1.3.1'.
+ * Null if the directive has always existed.
+ */
+ public $version;
+
+ /**
+ * ID of directive that supercedes this old directive, is an instance
+ * of HTMLPurifier_ConfigSchema_Interchange_Id. Null if not deprecated.
+ */
+ public $deprecatedUse;
+
+ /**
+ * Version of HTML Purifier this directive was deprecated. Null if not
+ * deprecated.
+ */
+ public $deprecatedVersion;
+
+ /**
+ * List of external projects this directive depends on, e.g. array('CSSTidy').
+ */
+ public $external = array();
+
+}
+
+// vim: et sw=4 sts=4
diff --git a/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/Interchange/Id.php b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/Interchange/Id.php
new file mode 100644
index 000000000..b9b3c6f5c
--- /dev/null
+++ b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/Interchange/Id.php
@@ -0,0 +1,37 @@
+key = $key;
+ }
+
+ /**
+ * @warning This is NOT magic, to ensure that people don't abuse SPL and
+ * cause problems for PHP 5.0 support.
+ */
+ public function toString() {
+ 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) {
+ return new HTMLPurifier_ConfigSchema_Interchange_Id($id);
+ }
+
+}
+
+// vim: et sw=4 sts=4
diff --git a/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/InterchangeBuilder.php b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/InterchangeBuilder.php
new file mode 100644
index 000000000..785b72ce8
--- /dev/null
+++ b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/InterchangeBuilder.php
@@ -0,0 +1,180 @@
+varParser = $varParser ? $varParser : new HTMLPurifier_VarParser_Native();
+ }
+
+ public static function buildFromDirectory($dir = null) {
+ $builder = new HTMLPurifier_ConfigSchema_InterchangeBuilder();
+ $interchange = new HTMLPurifier_ConfigSchema_Interchange();
+ return $builder->buildDir($interchange, $dir);
+ }
+
+ public function buildDir($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);
+ while (false !== ($file = readdir($dh))) {
+ if (!$file || $file[0] == '.' || strrchr($file, '.') !== '.txt') {
+ continue;
+ }
+ $files[] = $file;
+ }
+ closedir($dh);
+
+ sort($files);
+ foreach ($files as $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
+ * @param $hash HTMLPurifier_ConfigSchema_StringHash source data
+ */
+ public function build($interchange, $hash) {
+ if (!$hash instanceof HTMLPurifier_StringHash) {
+ $hash = new HTMLPurifier_StringHash($hash);
+ }
+ if (!isset($hash['ID'])) {
+ throw new HTMLPurifier_ConfigSchema_Exception('Hash does not have any ID');
+ }
+ if (strpos($hash['ID'], '.') === false) {
+ 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 buildDirective($interchange, $hash) {
+ $directive = new HTMLPurifier_ConfigSchema_Interchange_Directive();
+
+ // These are required elements:
+ $directive->id = $this->id($hash->offsetGet('ID'));
+ $id = $directive->id->toString(); // convenience
+
+ if (isset($hash['TYPE'])) {
+ $type = explode('/', $hash->offsetGet('TYPE'));
+ if (isset($type[1])) $directive->typeAllowsNull = true;
+ $directive->type = $type[0];
+ } else {
+ throw new HTMLPurifier_ConfigSchema_Exception("TYPE in directive hash '$id' not defined");
+ }
+
+ if (isset($hash['DEFAULT'])) {
+ try {
+ $directive->default = $this->varParser->parse($hash->offsetGet('DEFAULT'), $directive->type, $directive->typeAllowsNull);
+ } catch (HTMLPurifier_VarParserException $e) {
+ throw new HTMLPurifier_ConfigSchema_Exception($e->getMessage() . " in DEFAULT in directive hash '$id'");
+ }
+ }
+
+ if (isset($hash['DESCRIPTION'])) {
+ $directive->description = $hash->offsetGet('DESCRIPTION');
+ }
+
+ if (isset($hash['ALLOWED'])) {
+ $directive->allowed = $this->lookup($this->evalArray($hash->offsetGet('ALLOWED')));
+ }
+
+ if (isset($hash['VALUE-ALIASES'])) {
+ $directive->valueAliases = $this->evalArray($hash->offsetGet('VALUE-ALIASES'));
+ }
+
+ if (isset($hash['ALIASES'])) {
+ $raw_aliases = trim($hash->offsetGet('ALIASES'));
+ $aliases = preg_split('/\s*,\s*/', $raw_aliases);
+ foreach ($aliases as $alias) {
+ $directive->aliases[] = $this->id($alias);
+ }
+ }
+
+ if (isset($hash['VERSION'])) {
+ $directive->version = $hash->offsetGet('VERSION');
+ }
+
+ if (isset($hash['DEPRECATED-USE'])) {
+ $directive->deprecatedUse = $this->id($hash->offsetGet('DEPRECATED-USE'));
+ }
+
+ if (isset($hash['DEPRECATED-VERSION'])) {
+ $directive->deprecatedVersion = $hash->offsetGet('DEPRECATED-VERSION');
+ }
+
+ if (isset($hash['EXTERNAL'])) {
+ $directive->external = preg_split('/\s*,\s*/', trim($hash->offsetGet('EXTERNAL')));
+ }
+
+ $interchange->addDirective($directive);
+ }
+
+ /**
+ * Evaluates an array PHP code string without array() wrapper
+ */
+ protected function evalArray($contents) {
+ return eval('return array('. $contents .');');
+ }
+
+ /**
+ * Converts an array list into a lookup array.
+ */
+ protected function lookup($array) {
+ $ret = array();
+ foreach ($array as $val) $ret[$val] = true;
+ return $ret;
+ }
+
+ /**
+ * Convenience function that creates an HTMLPurifier_ConfigSchema_Interchange_Id
+ * object based on a string Id.
+ */
+ protected function id($id) {
+ return HTMLPurifier_ConfigSchema_Interchange_Id::make($id);
+ }
+
+ /**
+ * Triggers errors for any unused keys passed in the hash; such keys
+ * may indicate typos, missing values, etc.
+ * @param $hash Instance of ConfigSchema_StringHash to check.
+ */
+ protected function _findUnused($hash) {
+ $accessed = $hash->getAccessed();
+ foreach ($hash as $k => $v) {
+ if (!isset($accessed[$k])) {
+ trigger_error("String hash key '$k' not used by builder", E_USER_NOTICE);
+ }
+ }
+ }
+
+}
+
+// vim: et sw=4 sts=4
diff --git a/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/Validator.php b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/Validator.php
new file mode 100644
index 000000000..f374f6a02
--- /dev/null
+++ b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/Validator.php
@@ -0,0 +1,206 @@
+parser = new HTMLPurifier_VarParser();
+ }
+
+ /**
+ * Validates a fully-formed interchange object. Throws an
+ * HTMLPurifier_ConfigSchema_Exception if there's a problem.
+ */
+ public function validate($interchange) {
+ $this->interchange = $interchange;
+ $this->aliases = array();
+ // PHP is a bit lax with integer <=> string conversions in
+ // arrays, so we don't use the identical !== comparison
+ foreach ($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'");
+ $this->validateDirective($directive);
+ }
+ return true;
+ }
+
+ /**
+ * Validates a HTMLPurifier_ConfigSchema_Interchange_Id object.
+ */
+ public function validateId($id) {
+ $id_string = $id->toString();
+ $this->context[] = "id '$id_string'";
+ if (!$id instanceof HTMLPurifier_ConfigSchema_Interchange_Id) {
+ // handled by InterchangeBuilder
+ $this->error(false, 'is not an instance of HTMLPurifier_ConfigSchema_Interchange_Id');
+ }
+ // 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()
+ ->assertIsString(); // implicit assertIsString handled by InterchangeBuilder
+ array_pop($this->context);
+ }
+
+ /**
+ * Validates a HTMLPurifier_ConfigSchema_Interchange_Directive object.
+ */
+ public function validateDirective($d) {
+ $id = $d->id->toString();
+ $this->context[] = "directive '$id'";
+ $this->validateId($d->id);
+
+ $this->with($d, 'description')
+ ->assertNotEmpty();
+
+ // BEGIN - handled by InterchangeBuilder
+ $this->with($d, 'type')
+ ->assertNotEmpty();
+ $this->with($d, 'typeAllowsNull')
+ ->assertIsBool();
+ try {
+ // This also tests validity of $d->type
+ $this->parser->parse($d->default, $d->type, $d->typeAllowsNull);
+ } catch (HTMLPurifier_VarParserException $e) {
+ $this->error('default', 'had error: ' . $e->getMessage());
+ }
+ // END - handled by InterchangeBuilder
+
+ if (!is_null($d->allowed) || !empty($d->valueAliases)) {
+ // allowed and valueAliases require that we be dealing with
+ // strings, so check for that early.
+ $d_int = HTMLPurifier_VarParser::$types[$d->type];
+ if (!isset(HTMLPurifier_VarParser::$stringTypes[$d_int])) {
+ $this->error('type', 'must be a string type when used with allowed or value aliases');
+ }
+ }
+
+ $this->validateDirectiveAllowed($d);
+ $this->validateDirectiveValueAliases($d);
+ $this->validateDirectiveAliases($d);
+
+ array_pop($this->context);
+ }
+
+ /**
+ * Extra validation if $allowed member variable of
+ * HTMLPurifier_ConfigSchema_Interchange_Directive is defined.
+ */
+ public function validateDirectiveAllowed($d) {
+ if (is_null($d->allowed)) return;
+ $this->with($d, 'allowed')
+ ->assertNotEmpty()
+ ->assertIsLookup(); // handled by InterchangeBuilder
+ if (is_string($d->default) && !isset($d->allowed[$d->default])) {
+ $this->error('default', 'must be an allowed value');
+ }
+ $this->context[] = 'allowed';
+ foreach ($d->allowed as $val => $x) {
+ if (!is_string($val)) $this->error("value $val", 'must be a string');
+ }
+ array_pop($this->context);
+ }
+
+ /**
+ * Extra validation if $valueAliases member variable of
+ * HTMLPurifier_ConfigSchema_Interchange_Directive is defined.
+ */
+ public function validateDirectiveValueAliases($d) {
+ if (is_null($d->valueAliases)) return;
+ $this->with($d, 'valueAliases')
+ ->assertIsArray(); // handled by InterchangeBuilder
+ $this->context[] = 'valueAliases';
+ foreach ($d->valueAliases as $alias => $real) {
+ if (!is_string($alias)) $this->error("alias $alias", 'must be a string');
+ if (!is_string($real)) $this->error("alias target $real from alias '$alias'", 'must be a string');
+ if ($alias === $real) {
+ $this->error("alias '$alias'", "must not be an alias to itself");
+ }
+ }
+ if (!is_null($d->allowed)) {
+ foreach ($d->valueAliases as $alias => $real) {
+ if (isset($d->allowed[$alias])) {
+ $this->error("alias '$alias'", 'must not be an allowed value');
+ } elseif (!isset($d->allowed[$real])) {
+ $this->error("alias '$alias'", 'must be an alias to an allowed value');
+ }
+ }
+ }
+ array_pop($this->context);
+ }
+
+ /**
+ * Extra validation if $aliases member variable of
+ * HTMLPurifier_ConfigSchema_Interchange_Directive is defined.
+ */
+ public function validateDirectiveAliases($d) {
+ $this->with($d, 'aliases')
+ ->assertIsArray(); // handled by InterchangeBuilder
+ $this->context[] = 'aliases';
+ foreach ($d->aliases as $alias) {
+ $this->validateId($alias);
+ $s = $alias->toString();
+ if (isset($this->interchange->directives[$s])) {
+ $this->error("alias '$s'", 'collides with another directive');
+ }
+ if (isset($this->aliases[$s])) {
+ $other_directive = $this->aliases[$s];
+ $this->error("alias '$s'", "collides with alias for directive '$other_directive'");
+ }
+ $this->aliases[$s] = $d->id->toString();
+ }
+ array_pop($this->context);
+ }
+
+ // protected helper functions
+
+ /**
+ * Convenience function for generating HTMLPurifier_ConfigSchema_ValidatorAtom
+ * for validating simple member variables of objects.
+ */
+ protected function with($obj, $member) {
+ return new HTMLPurifier_ConfigSchema_ValidatorAtom($this->getFormattedContext(), $obj, $member);
+ }
+
+ /**
+ * Emits an error, providing helpful context.
+ */
+ protected function error($target, $msg) {
+ if ($target !== false) $prefix = ucfirst($target) . ' in ' . $this->getFormattedContext();
+ else $prefix = ucfirst($this->getFormattedContext());
+ throw new HTMLPurifier_ConfigSchema_Exception(trim($prefix . ' ' . $msg));
+ }
+
+ /**
+ * Returns a formatted context string.
+ */
+ protected function getFormattedContext() {
+ return implode(' in ', array_reverse($this->context));
+ }
+
+}
+
+// vim: et sw=4 sts=4
diff --git a/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/ValidatorAtom.php b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/ValidatorAtom.php
new file mode 100644
index 000000000..b95aea18c
--- /dev/null
+++ b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/ValidatorAtom.php
@@ -0,0 +1,66 @@
+context = $context;
+ $this->obj = $obj;
+ $this->member = $member;
+ $this->contents =& $obj->$member;
+ }
+
+ public function assertIsString() {
+ if (!is_string($this->contents)) $this->error('must be a string');
+ return $this;
+ }
+
+ public function assertIsBool() {
+ if (!is_bool($this->contents)) $this->error('must be a boolean');
+ return $this;
+ }
+
+ public function assertIsArray() {
+ if (!is_array($this->contents)) $this->error('must be an array');
+ return $this;
+ }
+
+ public function assertNotNull() {
+ if ($this->contents === null) $this->error('must not be null');
+ return $this;
+ }
+
+ public function assertAlnum() {
+ $this->assertIsString();
+ if (!ctype_alnum($this->contents)) $this->error('must be alphanumeric');
+ return $this;
+ }
+
+ public function assertNotEmpty() {
+ if (empty($this->contents)) $this->error('must not be empty');
+ return $this;
+ }
+
+ public function assertIsLookup() {
+ $this->assertIsArray();
+ foreach ($this->contents as $v) {
+ if ($v !== true) $this->error('must be a lookup array');
+ }
+ return $this;
+ }
+
+ protected function error($msg) {
+ throw new HTMLPurifier_ConfigSchema_Exception(ucfirst($this->member) . ' in ' . $this->context . ' ' . $msg);
+ }
+
+}
+
+// vim: et sw=4 sts=4
diff --git a/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema.ser b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema.ser
new file mode 100644
index 000000000..fa0bacb94
Binary files /dev/null and b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema.ser differ
diff --git a/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/Attr.AllowedClasses.txt b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/Attr.AllowedClasses.txt
new file mode 100644
index 000000000..0517fed0a
--- /dev/null
+++ b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/Attr.AllowedClasses.txt
@@ -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
diff --git a/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/Attr.AllowedFrameTargets.txt b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/Attr.AllowedFrameTargets.txt
new file mode 100644
index 000000000..249edd647
--- /dev/null
+++ b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/Attr.AllowedFrameTargets.txt
@@ -0,0 +1,12 @@
+Attr.AllowedFrameTargets
+TYPE: lookup
+DEFAULT: array()
+--DESCRIPTION--
+Lookup table of all allowed link frame targets. Some commonly used link
+targets include _blank, _self, _parent and _top. Values should be
+lowercase, as validation will be done in a case-sensitive manner despite
+W3C's recommendation. XHTML 1.0 Strict does not permit the target attribute
+so this directive will have no effect in that doctype. XHTML 1.1 does not
+enable the Target module by default, you will have to manually enable it
+(see the module documentation for more details.)
+--# vim: et sw=4 sts=4
diff --git a/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/Attr.AllowedRel.txt b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/Attr.AllowedRel.txt
new file mode 100644
index 000000000..9a8fa6a2e
--- /dev/null
+++ b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/Attr.AllowedRel.txt
@@ -0,0 +1,9 @@
+Attr.AllowedRel
+TYPE: lookup
+VERSION: 1.6.0
+DEFAULT: array()
+--DESCRIPTION--
+List of allowed forward document relationships in the rel attribute. Common
+values may be nofollow or print. By default, this is empty, meaning that no
+document relationships are allowed.
+--# vim: et sw=4 sts=4
diff --git a/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/Attr.AllowedRev.txt b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/Attr.AllowedRev.txt
new file mode 100644
index 000000000..b01788348
--- /dev/null
+++ b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/Attr.AllowedRev.txt
@@ -0,0 +1,9 @@
+Attr.AllowedRev
+TYPE: lookup
+VERSION: 1.6.0
+DEFAULT: array()
+--DESCRIPTION--
+List of allowed reverse document relationships in the rev attribute. This
+attribute is a bit of an edge-case; if you don't know what it is for, stay
+away.
+--# vim: et sw=4 sts=4
diff --git a/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/Attr.ClassUseCDATA.txt b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/Attr.ClassUseCDATA.txt
new file mode 100644
index 000000000..e774b823b
--- /dev/null
+++ b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/Attr.ClassUseCDATA.txt
@@ -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
diff --git a/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/Attr.DefaultImageAlt.txt b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/Attr.DefaultImageAlt.txt
new file mode 100644
index 000000000..533165e17
--- /dev/null
+++ b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/Attr.DefaultImageAlt.txt
@@ -0,0 +1,11 @@
+Attr.DefaultImageAlt
+TYPE: string/null
+DEFAULT: null
+VERSION: 3.2.0
+--DESCRIPTION--
+This is the content of the alt tag of an image if the user had not
+previously specified an alt attribute. This applies to all images without
+a valid alt attribute, as opposed to %Attr.DefaultInvalidImageAlt, which
+only applies to invalid images, and overrides in the case of an invalid image.
+Default behavior with null is to use the basename of the src tag for the alt.
+--# vim: et sw=4 sts=4
diff --git a/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/Attr.DefaultInvalidImage.txt b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/Attr.DefaultInvalidImage.txt
new file mode 100644
index 000000000..9eb7e3846
--- /dev/null
+++ b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/Attr.DefaultInvalidImage.txt
@@ -0,0 +1,9 @@
+Attr.DefaultInvalidImage
+TYPE: string
+DEFAULT: ''
+--DESCRIPTION--
+This is the default image an img tag will be pointed to if it does not have
+a valid src attribute. In future versions, we may allow the image tag to
+be removed completely, but due to design issues, this is not possible right
+now.
+--# vim: et sw=4 sts=4
diff --git a/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/Attr.DefaultInvalidImageAlt.txt b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/Attr.DefaultInvalidImageAlt.txt
new file mode 100644
index 000000000..2f17bf477
--- /dev/null
+++ b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/Attr.DefaultInvalidImageAlt.txt
@@ -0,0 +1,8 @@
+Attr.DefaultInvalidImageAlt
+TYPE: string
+DEFAULT: 'Invalid image'
+--DESCRIPTION--
+This is the content of the alt tag of an invalid image if the user had not
+previously specified an alt attribute. It has no effect when the image is
+valid but there was no alt attribute present.
+--# vim: et sw=4 sts=4
diff --git a/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/Attr.DefaultTextDir.txt b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/Attr.DefaultTextDir.txt
new file mode 100644
index 000000000..52654b53a
--- /dev/null
+++ b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/Attr.DefaultTextDir.txt
@@ -0,0 +1,10 @@
+Attr.DefaultTextDir
+TYPE: string
+DEFAULT: 'ltr'
+--DESCRIPTION--
+Defines the default text direction (ltr or rtl) of the document being
+parsed. This generally is the same as the value of the dir attribute in
+HTML, or ltr if that is not specified.
+--ALLOWED--
+'ltr', 'rtl'
+--# vim: et sw=4 sts=4
diff --git a/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/Attr.EnableID.txt b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/Attr.EnableID.txt
new file mode 100644
index 000000000..6440d2103
--- /dev/null
+++ b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/Attr.EnableID.txt
@@ -0,0 +1,16 @@
+Attr.EnableID
+TYPE: bool
+DEFAULT: false
+VERSION: 1.2.0
+--DESCRIPTION--
+Allows the ID attribute in HTML. This is disabled by default due to the
+fact that without proper configuration user input can easily break the
+validation of a webpage by specifying an ID that is already on the
+surrounding HTML. If you don't mind throwing caution to the wind, enable
+this directive, but I strongly recommend you also consider blacklisting IDs
+you use (%Attr.IDBlacklist) or prefixing all user supplied IDs
+(%Attr.IDPrefix). When set to true HTML Purifier reverts to the behavior of
+pre-1.2.0 versions.
+--ALIASES--
+HTML.EnableAttrID
+--# vim: et sw=4 sts=4
diff --git a/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/Attr.ForbiddenClasses.txt b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/Attr.ForbiddenClasses.txt
new file mode 100644
index 000000000..f31d226f5
--- /dev/null
+++ b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/Attr.ForbiddenClasses.txt
@@ -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
diff --git a/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/Attr.IDBlacklist.txt b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/Attr.IDBlacklist.txt
new file mode 100644
index 000000000..5f2b5e3d2
--- /dev/null
+++ b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/Attr.IDBlacklist.txt
@@ -0,0 +1,5 @@
+Attr.IDBlacklist
+TYPE: list
+DEFAULT: array()
+DESCRIPTION: Array of IDs not allowed in the document.
+--# vim: et sw=4 sts=4
diff --git a/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/Attr.IDBlacklistRegexp.txt b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/Attr.IDBlacklistRegexp.txt
new file mode 100644
index 000000000..6f5824586
--- /dev/null
+++ b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/Attr.IDBlacklistRegexp.txt
@@ -0,0 +1,9 @@
+Attr.IDBlacklistRegexp
+TYPE: string/null
+VERSION: 1.6.0
+DEFAULT: NULL
+--DESCRIPTION--
+PCRE regular expression to be matched against all IDs. If the expression is
+matches, the ID is rejected. Use this with care: may cause significant
+degradation. ID matching is done after all other validation.
+--# vim: et sw=4 sts=4
diff --git a/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/Attr.IDPrefix.txt b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/Attr.IDPrefix.txt
new file mode 100644
index 000000000..cc49d43fd
--- /dev/null
+++ b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/Attr.IDPrefix.txt
@@ -0,0 +1,12 @@
+Attr.IDPrefix
+TYPE: string
+VERSION: 1.2.0
+DEFAULT: ''
+--DESCRIPTION--
+String to prefix to IDs. If you have no idea what IDs your pages may use,
+you may opt to simply add a prefix to all user-submitted ID attributes so
+that they are still usable, but will not conflict with core page IDs.
+Example: setting the directive to 'user_' will result in a user submitted
+'foo' to become 'user_foo' Be sure to set %HTML.EnableAttrID to true
+before using this.
+--# vim: et sw=4 sts=4
diff --git a/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/Attr.IDPrefixLocal.txt b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/Attr.IDPrefixLocal.txt
new file mode 100644
index 000000000..2c5924a7a
--- /dev/null
+++ b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/Attr.IDPrefixLocal.txt
@@ -0,0 +1,14 @@
+Attr.IDPrefixLocal
+TYPE: string
+VERSION: 1.2.0
+DEFAULT: ''
+--DESCRIPTION--
+Temporary prefix for IDs used in conjunction with %Attr.IDPrefix. If you
+need to allow multiple sets of user content on web page, you may need to
+have a seperate prefix that changes with each iteration. This way,
+seperately submitted user content displayed on the same page doesn't
+clobber each other. Ideal values are unique identifiers for the content it
+represents (i.e. the id of the row in the database). Be sure to add a
+seperator (like an underscore) at the end. Warning: this directive will
+not work unless %Attr.IDPrefix is set to a non-empty value!
+--# vim: et sw=4 sts=4
diff --git a/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/AutoFormat.AutoParagraph.txt b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/AutoFormat.AutoParagraph.txt
new file mode 100644
index 000000000..d5caa1bb9
--- /dev/null
+++ b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/AutoFormat.AutoParagraph.txt
@@ -0,0 +1,31 @@
+AutoFormat.AutoParagraph
+TYPE: bool
+VERSION: 2.0.1
+DEFAULT: false
+--DESCRIPTION--
+
+
+ This directive turns on auto-paragraphing, where double newlines are
+ converted in to paragraphs whenever possible. Auto-paragraphing:
+
+
+
Always applies to inline elements or text in the root node,
+
Applies to inline elements or text with double newlines in nodes
+ that allow paragraph tags,
+
Applies to double newlines in paragraph tags
+
+
+ p tags must be allowed for this directive to take effect.
+ We do not use br tags for paragraphing, as that is
+ semantically incorrect.
+
+
+ To prevent auto-paragraphing as a content-producer, refrain from using
+ double-newlines except to specify a new paragraph or in contexts where
+ it has special meaning (whitespace usually has no meaning except in
+ tags like pre, so this should not be difficult.) To prevent
+ the paragraphing of inline text adjacent to block elements, wrap them
+ in div tags (the behavior is slightly different outside of
+ the root node.)
+
+--# vim: et sw=4 sts=4
diff --git a/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/AutoFormat.Custom.txt b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/AutoFormat.Custom.txt
new file mode 100644
index 000000000..2a476481a
--- /dev/null
+++ b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/AutoFormat.Custom.txt
@@ -0,0 +1,12 @@
+AutoFormat.Custom
+TYPE: list
+VERSION: 2.0.1
+DEFAULT: array()
+--DESCRIPTION--
+
+
+ This directive can be used to add custom auto-format injectors.
+ Specify an array of injector names (class name minus the prefix)
+ or concrete implementations. Injector class must exist.
+
+ This directive turns on the in-text display of URIs in <a> tags, and disables
+ those links. For example, example becomes
+ example (http://example.com).
+
+ Location of configuration documentation to link to, let %s substitute
+ into the configuration's namespace and directive names sans the percent
+ sign.
+
+ Internal auto-formatter that converts configuration directives in
+ syntax %Namespace.Directive to links. a tags
+ with the href attribute must be allowed.
+
+ 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.
+
+ 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.
+
+
+ See %AutoFormat.RemoveEmpty.RemoveNbsp.Exceptions for a list of elements
+ that don't have this behavior applied to them.
+
+ When enabled, HTML Purifier will attempt to remove empty elements that
+ contribute no semantic information to the document. The following types
+ of nodes will be removed:
+
+
+ Tags with no attributes and no content, and that are not empty
+ elements (remove <a></a> but not
+ <br />), and
+
+
+ Tags with no content, except for:
+
The colgroup element, or
+
+ Elements with the id or name attribute,
+ when those attributes are permitted on those elements.
+
+
+
+
+ Please be very careful when using this functionality; while it may not
+ seem that empty elements contain useful information, they can alter the
+ layout of a document given appropriate styling. This directive is most
+ useful when you are processing machine-generated HTML, please avoid using
+ it on regular user HTML.
+
+
+ Elements that contain only whitespace will be treated as empty. Non-breaking
+ spaces, however, do not count as whitespace. See
+ %AutoFormat.RemoveEmpty.RemoveNbsp for alternate behavior.
+
+
+ This algorithm is not perfect; you may still notice some empty tags,
+ particularly if a node had elements, but those elements were later removed
+ 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 in, it will get removed; if HTML Purifier
+ made it empty, it will stay.
+
+ This directive causes span tags without any attributes
+ to be removed. It will also remove spans that had all attributes
+ removed during processing.
+
+--# vim: et sw=4 sts=4
diff --git a/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/CSS.AllowImportant.txt b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/CSS.AllowImportant.txt
new file mode 100644
index 000000000..b324608f7
--- /dev/null
+++ b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/CSS.AllowImportant.txt
@@ -0,0 +1,8 @@
+CSS.AllowImportant
+TYPE: bool
+DEFAULT: false
+VERSION: 3.1.0
+--DESCRIPTION--
+This parameter determines whether or not !important cascade modifiers should
+be allowed in user CSS. If false, !important will stripped.
+--# vim: et sw=4 sts=4
diff --git a/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/CSS.AllowTricky.txt b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/CSS.AllowTricky.txt
new file mode 100644
index 000000000..748be0eec
--- /dev/null
+++ b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/CSS.AllowTricky.txt
@@ -0,0 +1,11 @@
+CSS.AllowTricky
+TYPE: bool
+DEFAULT: false
+VERSION: 3.1.0
+--DESCRIPTION--
+This parameter determines whether or not to allow "tricky" CSS properties and
+values. Tricky CSS properties/values can drastically modify page layout or
+be used for deceptive practices but do not directly constitute a security risk.
+For example, display:none; is considered a tricky property that
+will only be allowed if this directive is set to true.
+--# vim: et sw=4 sts=4
diff --git a/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/CSS.AllowedFonts.txt b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/CSS.AllowedFonts.txt
new file mode 100644
index 000000000..3fd465406
--- /dev/null
+++ b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/CSS.AllowedFonts.txt
@@ -0,0 +1,12 @@
+CSS.AllowedFonts
+TYPE: lookup/null
+VERSION: 4.3.0
+DEFAULT: NULL
+--DESCRIPTION--
+
+ Allows you to manually specify a set of allowed fonts. If
+ NULL, all fonts are allowed. This directive
+ affects generic names (serif, sans-serif, monospace, cursive,
+ fantasy) as well as specific font families.
+
+ If HTML Purifier's style attributes set is unsatisfactory for your needs,
+ you can overload it with your own list of tags to allow. Note that this
+ method is subtractive: it does its job by taking away from HTML Purifier
+ usual feature set, so you cannot add an attribute that HTML Purifier never
+ supported in the first place.
+
+
+ Warning: If another directive conflicts with the
+ elements here, that directive will win and override.
+
+--# vim: et sw=4 sts=4
diff --git a/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/CSS.DefinitionRev.txt b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/CSS.DefinitionRev.txt
new file mode 100644
index 000000000..5cb7dda3b
--- /dev/null
+++ b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/CSS.DefinitionRev.txt
@@ -0,0 +1,11 @@
+CSS.DefinitionRev
+TYPE: int
+VERSION: 2.0.0
+DEFAULT: 1
+--DESCRIPTION--
+
+
+ Revision identifier for your custom definition. See
+ %HTML.DefinitionRev for details.
+
+ This is the logical inverse of %CSS.AllowedProperties, and it will
+ override that directive or any other directive. If possible,
+ %CSS.AllowedProperties is recommended over this directive,
+ because it can sometimes be difficult to tell whether or not you've
+ forbidden all of the CSS properties you truly would like to disallow.
+
+ This parameter sets the maximum allowed length on img tags,
+ effectively the width and height properties.
+ Only absolute units of measurement (in, pt, pc, mm, cm) and pixels (px) are allowed. This is
+ in place to prevent imagecrash attacks, disable with null at your own risk.
+ This directive is similar to %HTML.MaxImgLength, and both should be
+ concurrently edited, although there are
+ subtle differences in the input format (the CSS max is a number with
+ a unit).
+
+ Whether or not to allow safe, proprietary CSS values.
+
+--# vim: et sw=4 sts=4
diff --git a/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/CSS.Trusted.txt b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/CSS.Trusted.txt
new file mode 100644
index 000000000..e733a61e8
--- /dev/null
+++ b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/CSS.Trusted.txt
@@ -0,0 +1,9 @@
+CSS.Trusted
+TYPE: bool
+VERSION: 4.2.1
+DEFAULT: false
+--DESCRIPTION--
+Indicates whether or not the user's CSS input is trusted or not. If the
+input is trusted, a more expansive set of allowed properties. See
+also %HTML.Trusted.
+--# vim: et sw=4 sts=4
diff --git a/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/Cache.DefinitionImpl.txt b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/Cache.DefinitionImpl.txt
new file mode 100644
index 000000000..c486724c8
--- /dev/null
+++ b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/Cache.DefinitionImpl.txt
@@ -0,0 +1,14 @@
+Cache.DefinitionImpl
+TYPE: string/null
+VERSION: 2.0.0
+DEFAULT: 'Serializer'
+--DESCRIPTION--
+
+This directive defines which method to use when caching definitions,
+the complex data-type that makes HTML Purifier tick. Set to null
+to disable caching (not recommended, as you will see a definite
+performance degradation).
+
+--ALIASES--
+Core.DefinitionCache
+--# vim: et sw=4 sts=4
diff --git a/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/Cache.SerializerPath.txt b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/Cache.SerializerPath.txt
new file mode 100644
index 000000000..54036507d
--- /dev/null
+++ b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/Cache.SerializerPath.txt
@@ -0,0 +1,13 @@
+Cache.SerializerPath
+TYPE: string/null
+VERSION: 2.0.0
+DEFAULT: NULL
+--DESCRIPTION--
+
+
+ Absolute path with no trailing slash to store serialized definitions in.
+ Default is within the
+ HTML Purifier library inside DefinitionCache/Serializer. This
+ path must be writable by the webserver.
+
+--# vim: et sw=4 sts=4
diff --git a/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/Cache.SerializerPermissions.txt b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/Cache.SerializerPermissions.txt
new file mode 100644
index 000000000..b2b83d9ab
--- /dev/null
+++ b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/Cache.SerializerPermissions.txt
@@ -0,0 +1,11 @@
+Cache.SerializerPermissions
+TYPE: int
+VERSION: 4.3.0
+DEFAULT: 0755
+--DESCRIPTION--
+
+
+ Directory permissions of the files and directories created inside
+ the DefinitionCache/Serializer or other custom serializer path.
+
+ This directive enables aggressive pre-filter fixes HTML Purifier can
+ perform in order to ensure that open angled-brackets do not get killed
+ during parsing stage. Enabling this will result in two preg_replace_callback
+ calls and at least two preg_replace calls for every HTML document parsed;
+ if your users make very well-formed HTML, you can set this directive false.
+ This has no effect when DirectLex is used.
+
+
+ Notice: This directive's default turned from false to true
+ in HTML Purifier 3.2.0.
+
+--# vim: et sw=4 sts=4
diff --git a/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/Core.CollectErrors.txt b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/Core.CollectErrors.txt
new file mode 100644
index 000000000..d7317911f
--- /dev/null
+++ b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/Core.CollectErrors.txt
@@ -0,0 +1,12 @@
+Core.CollectErrors
+TYPE: bool
+VERSION: 2.0.0
+DEFAULT: false
+--DESCRIPTION--
+
+Whether or not to collect errors found while filtering the document. This
+is a useful way to give feedback to your users. Warning:
+Currently this feature is very patchy and experimental, with lots of
+possible error messages not yet implemented. It will not cause any
+problems, but it may not help your users either.
+--# vim: et sw=4 sts=4
diff --git a/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/Core.ColorKeywords.txt b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/Core.ColorKeywords.txt
new file mode 100644
index 000000000..c572c14ec
--- /dev/null
+++ b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/Core.ColorKeywords.txt
@@ -0,0 +1,29 @@
+Core.ColorKeywords
+TYPE: hash
+VERSION: 2.0.0
+--DEFAULT--
+array (
+ 'maroon' => '#800000',
+ 'red' => '#FF0000',
+ 'orange' => '#FFA500',
+ 'yellow' => '#FFFF00',
+ 'olive' => '#808000',
+ 'purple' => '#800080',
+ 'fuchsia' => '#FF00FF',
+ 'white' => '#FFFFFF',
+ 'lime' => '#00FF00',
+ 'green' => '#008000',
+ 'navy' => '#000080',
+ 'blue' => '#0000FF',
+ 'aqua' => '#00FFFF',
+ 'teal' => '#008080',
+ 'black' => '#000000',
+ 'silver' => '#C0C0C0',
+ 'gray' => '#808080',
+)
+--DESCRIPTION--
+
+Lookup array of color names to six digit hexadecimal number corresponding
+to color, with preceding hash mark. Used when parsing colors. The lookup
+is done in a case-insensitive manner.
+--# vim: et sw=4 sts=4
diff --git a/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/Core.ConvertDocumentToFragment.txt b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/Core.ConvertDocumentToFragment.txt
new file mode 100644
index 000000000..64b114fce
--- /dev/null
+++ b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/Core.ConvertDocumentToFragment.txt
@@ -0,0 +1,14 @@
+Core.ConvertDocumentToFragment
+TYPE: bool
+DEFAULT: true
+--DESCRIPTION--
+
+This parameter determines whether or not the filter should convert
+input that is a full document with html and body tags to a fragment
+of just the contents of a body tag. This parameter is simply something
+HTML Purifier can do during an edge-case: for most inputs, this
+processing is not necessary.
+
+--ALIASES--
+Core.AcceptFullDocuments
+--# vim: et sw=4 sts=4
diff --git a/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/Core.DirectLexLineNumberSyncInterval.txt b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/Core.DirectLexLineNumberSyncInterval.txt
new file mode 100644
index 000000000..36f16e07e
--- /dev/null
+++ b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/Core.DirectLexLineNumberSyncInterval.txt
@@ -0,0 +1,17 @@
+Core.DirectLexLineNumberSyncInterval
+TYPE: int
+VERSION: 2.0.0
+DEFAULT: 0
+--DESCRIPTION--
+
+
+ Specifies the number of tokens the DirectLex line number tracking
+ implementations should process before attempting to resyncronize the
+ current line count by manually counting all previous new-lines. When
+ at 0, this functionality is disabled. Lower values will decrease
+ performance, and this is only strictly necessary if the counting
+ algorithm is buggy (in which case you should report it as a bug).
+ This has no effect when %Core.MaintainLineNumbers is disabled or DirectLex is
+ not being used.
+
+ This directive disables SGML-style exclusions, e.g. the exclusion of
+ <object> in any descendant of a
+ <pre> tag. Disabling excludes will allow some
+ invalid documents to pass through HTML Purifier, but HTML Purifier
+ will also be less likely to accidentally remove large documents during
+ processing.
+
+--# vim: et sw=4 sts=4
diff --git a/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/Core.EnableIDNA.txt b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/Core.EnableIDNA.txt
new file mode 100644
index 000000000..ce243c35d
--- /dev/null
+++ b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/Core.EnableIDNA.txt
@@ -0,0 +1,9 @@
+Core.EnableIDNA
+TYPE: bool
+DEFAULT: false
+VERSION: 4.4.0
+--DESCRIPTION--
+Allows international domain names in URLs. This configuration option
+requires the PEAR Net_IDNA2 module to be installed. It operates by
+punycoding any internationalized host names for maximum portability.
+--# vim: et sw=4 sts=4
diff --git a/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/Core.Encoding.txt b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/Core.Encoding.txt
new file mode 100644
index 000000000..8bfb47c3a
--- /dev/null
+++ b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/Core.Encoding.txt
@@ -0,0 +1,15 @@
+Core.Encoding
+TYPE: istring
+DEFAULT: 'utf-8'
+--DESCRIPTION--
+If for some reason you are unable to convert all webpages to UTF-8, you can
+use this directive as a stop-gap compatibility change to let HTML Purifier
+deal with non UTF-8 input. This technique has notable deficiencies:
+absolutely no characters outside of the selected character encoding will be
+preserved, not even the ones that have been ampersand escaped (this is due
+to a UTF-8 specific feature that automatically resolves all
+entities), making it pretty useless for anything except the most I18N-blind
+applications, although %Core.EscapeNonASCIICharacters offers fixes this
+trouble with another tradeoff. This directive only accepts ISO-8859-1 if
+iconv is not enabled.
+--# vim: et sw=4 sts=4
diff --git a/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/Core.EscapeInvalidChildren.txt b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/Core.EscapeInvalidChildren.txt
new file mode 100644
index 000000000..4d5b5055c
--- /dev/null
+++ b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/Core.EscapeInvalidChildren.txt
@@ -0,0 +1,10 @@
+Core.EscapeInvalidChildren
+TYPE: bool
+DEFAULT: false
+--DESCRIPTION--
+When true, a child is found that is not allowed in the context of the
+parent element will be transformed into text as if it were ASCII. When
+false, that element and all internal tags will be dropped, though text will
+be preserved. There is no option for dropping the element but preserving
+child nodes.
+--# vim: et sw=4 sts=4
diff --git a/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/Core.EscapeInvalidTags.txt b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/Core.EscapeInvalidTags.txt
new file mode 100644
index 000000000..a7a5b249b
--- /dev/null
+++ b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/Core.EscapeInvalidTags.txt
@@ -0,0 +1,7 @@
+Core.EscapeInvalidTags
+TYPE: bool
+DEFAULT: false
+--DESCRIPTION--
+When true, invalid tags will be written back to the document as plain text.
+Otherwise, they are silently dropped.
+--# vim: et sw=4 sts=4
diff --git a/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/Core.EscapeNonASCIICharacters.txt b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/Core.EscapeNonASCIICharacters.txt
new file mode 100644
index 000000000..abb499948
--- /dev/null
+++ b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/Core.EscapeNonASCIICharacters.txt
@@ -0,0 +1,13 @@
+Core.EscapeNonASCIICharacters
+TYPE: bool
+VERSION: 1.4.0
+DEFAULT: false
+--DESCRIPTION--
+This directive overcomes a deficiency in %Core.Encoding by blindly
+converting all non-ASCII characters into decimal numeric entities before
+converting it to its native encoding. This means that even characters that
+can be expressed in the non-UTF-8 encoding will be entity-ized, which can
+be a real downer for encodings like Big5. It also assumes that the ASCII
+repetoire is available, although this is the case for almost all encodings.
+Anyway, use UTF-8!
+--# vim: et sw=4 sts=4
diff --git a/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/Core.HiddenElements.txt b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/Core.HiddenElements.txt
new file mode 100644
index 000000000..915391edb
--- /dev/null
+++ b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/Core.HiddenElements.txt
@@ -0,0 +1,19 @@
+Core.HiddenElements
+TYPE: lookup
+--DEFAULT--
+array (
+ 'script' => true,
+ 'style' => true,
+)
+--DESCRIPTION--
+
+
+ This directive is a lookup array of elements which should have their
+ contents removed when they are not allowed by the HTML definition.
+ For example, the contents of a script tag are not
+ normally shown in a document, so if script tags are to be removed,
+ their contents should be removed to. This is opposed to a b
+ tag, which defines some presentational changes but does not hide its
+ contents.
+
+--# vim: et sw=4 sts=4
diff --git a/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/Core.Language.txt b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/Core.Language.txt
new file mode 100644
index 000000000..233fca14f
--- /dev/null
+++ b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/Core.Language.txt
@@ -0,0 +1,10 @@
+Core.Language
+TYPE: string
+VERSION: 2.0.0
+DEFAULT: 'en'
+--DESCRIPTION--
+
+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.
+--# vim: et sw=4 sts=4
diff --git a/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/Core.LexerImpl.txt b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/Core.LexerImpl.txt
new file mode 100644
index 000000000..8983e2cca
--- /dev/null
+++ b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/Core.LexerImpl.txt
@@ -0,0 +1,34 @@
+Core.LexerImpl
+TYPE: mixed/null
+VERSION: 2.0.0
+DEFAULT: NULL
+--DESCRIPTION--
+
+
+ This parameter determines what lexer implementation can be used. The
+ valid values are:
+
+
+
null
+
+ Recommended, the lexer implementation will be auto-detected based on
+ your PHP-version and configuration.
+
+
string lexer identifier
+
+ This is a slim way of manually overridding the implementation.
+ Currently recognized values are: DOMLex (the default PHP5
+implementation)
+ and DirectLex (the default PHP4 implementation). Only use this if
+ you know what you are doing: usually, the auto-detection will
+ manage things for cases you aren't even aware of.
+
+
object lexer instance
+
+ Super-advanced: you can specify your own, custom, implementation that
+ implements the interface defined by HTMLPurifier_Lexer.
+ I may remove this option simply because I don't expect anyone
+ to use it.
+
+ If true, HTML Purifier will add line number information to all tokens.
+ This is useful when error reporting is turned on, but can result in
+ significant performance degradation and should not be used when
+ unnecessary. This directive must be used with the DirectLex lexer,
+ as the DOMLex lexer does not (yet) support this functionality.
+ If the value is null, an appropriate value will be selected based
+ on other configuration.
+
+ This directive enables pre-emptive URI checking in img
+ tags, as the attribute validation strategy is not authorized to
+ remove elements from the document. Revert to pre-1.3.0 behavior by setting to false.
+
+--# vim: et sw=4 sts=4
diff --git a/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/Core.RemoveProcessingInstructions.txt b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/Core.RemoveProcessingInstructions.txt
new file mode 100644
index 000000000..3397d9f71
--- /dev/null
+++ b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/Core.RemoveProcessingInstructions.txt
@@ -0,0 +1,11 @@
+Core.RemoveProcessingInstructions
+TYPE: bool
+VERSION: 4.2.0
+DEFAULT: false
+--DESCRIPTION--
+Instead of escaping processing instructions in the form <? ...
+?>, remove it out-right. This may be useful if the HTML
+you are validating contains XML processing instruction gunk, however,
+it can also be user-unfriendly for people attempting to post PHP
+snippets.
+--# vim: et sw=4 sts=4
diff --git a/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/Core.RemoveScriptContents.txt b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/Core.RemoveScriptContents.txt
new file mode 100644
index 000000000..a4cd966df
--- /dev/null
+++ b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/Core.RemoveScriptContents.txt
@@ -0,0 +1,12 @@
+Core.RemoveScriptContents
+TYPE: bool/null
+DEFAULT: NULL
+VERSION: 2.0.0
+DEPRECATED-VERSION: 2.1.0
+DEPRECATED-USE: Core.HiddenElements
+--DESCRIPTION--
+
+ This directive enables HTML Purifier to remove not only script tags
+ but all of their contents.
+
+--# vim: et sw=4 sts=4
diff --git a/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/Filter.Custom.txt b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/Filter.Custom.txt
new file mode 100644
index 000000000..3db50ef20
--- /dev/null
+++ b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/Filter.Custom.txt
@@ -0,0 +1,11 @@
+Filter.Custom
+TYPE: list
+VERSION: 3.1.0
+DEFAULT: array()
+--DESCRIPTION--
+
+ This directive can be used to add custom filters; it is nearly the
+ equivalent of the now deprecated HTMLPurifier->addFilter()
+ method. Specify an array of concrete implementations.
+
+ Whether or not to escape the dangerous characters <, > and &
+ as \3C, \3E and \26, respectively. This is can be safely set to false
+ if the contents of StyleBlocks will be placed in an external stylesheet,
+ where there is no risk of it being interpreted as HTML.
+
+ If you would like users to be able to define external stylesheets, but
+ only allow them to specify CSS declarations for a specific node and
+ prevent them from fiddling with other elements, use this directive.
+ It accepts any valid CSS selector, and will prepend this to any
+ CSS declaration extracted from the document. For example, if this
+ directive is set to #user-content and a user uses the
+ selector a:hover, the final selector will be
+ #user-content a:hover.
+
+
+ The comma shorthand may be used; consider the above example, with
+ #user-content, #user-content2, the final selector will
+ be #user-content a:hover, #user-content2 a:hover.
+
+
+ Warning: It is possible for users to bypass this measure
+ using a naughty + selector. This is a bug in CSS Tidy 1.3, not HTML
+ Purifier, and I am working to get it fixed. Until then, HTML Purifier
+ performs a basic check to prevent this.
+
+ If left NULL, HTML Purifier will attempt to instantiate a csstidy
+ class to use for internal cleaning. This will usually be good enough.
+
+
+ However, for trusted user input, you can set this to false to
+ disable cleaning. In addition, you can supply your own concrete implementation
+ of Tidy's interface to use, although I don't know why you'd want to do that.
+
+ This directive turns on the style block extraction filter, which removes
+ style blocks from input HTML, cleans them up with CSSTidy,
+ and places them in the StyleBlocks context variable, for further
+ use by you, usually to be placed in an external stylesheet, or a
+ style block in the head of your document.
+
+
+ Sample usage:
+
+
';
+?>
+
+
+
+ Filter.ExtractStyleBlocks
+body {color:#F00;} Some text';
+
+ $config = HTMLPurifier_Config::createDefault();
+ $config->set('Filter', 'ExtractStyleBlocks', true);
+ $purifier = new HTMLPurifier($config);
+
+ $html = $purifier->purify($dirty);
+
+ // This implementation writes the stylesheets to the styles/ directory.
+ // You can also echo the styles inside the document, but it's a bit
+ // more difficult to make sure they get interpreted properly by
+ // browsers; try the usual CSS armoring techniques.
+ $styles = $purifier->context->get('StyleBlocks');
+ $dir = 'styles/';
+ if (!is_dir($dir)) mkdir($dir);
+ $hash = sha1($_GET['html']);
+ foreach ($styles as $i => $style) {
+ file_put_contents($name = $dir . $hash . "_$i");
+ echo '';
+ }
+?>
+
+
+
+
+
+
+
+]]>
+
+ Warning: It is possible for a user to mount an
+ imagecrash attack using this CSS. Counter-measures are difficult;
+ it is not simply enough to limit the range of CSS lengths (using
+ relative lengths with many nesting levels allows for large values
+ to be attained without actually specifying them in the stylesheet),
+ and the flexible nature of selectors makes it difficult to selectively
+ disable lengths on image tags (HTML Purifier, however, does disable
+ CSS width and height in inline styling). There are probably two effective
+ counter measures: an explicit width and height set to auto in all
+ images in your document (unlikely) or the disabling of width and
+ height (somewhat reasonable). Whether or not these measures should be
+ used is left to the reader.
+
+ Warning: Deprecated in favor of %HTML.SafeObject and
+ %Output.FlashCompat (turn both on to allow YouTube videos and other
+ Flash content).
+
+
+ This directive enables YouTube video embedding in HTML Purifier. Check
+ this document
+ on embedding videos for more information on what this filter does.
+
+ This is a preferred convenience directive that combines
+ %HTML.AllowedElements and %HTML.AllowedAttributes.
+ Specify elements and attributes that are allowed using:
+ element1[attr1|attr2],element2.... For example,
+ if you would like to only allow paragraphs and links, specify
+ a[href],p. You can specify attributes that apply
+ to all elements using an asterisk, e.g. *[lang].
+ You can also use newlines instead of commas to separate elements.
+
+
+ Warning:
+ All of the constraints on the component directives are still enforced.
+ The syntax is a subset of TinyMCE's valid_elements
+ whitelist: directly copy-pasting it here will probably result in
+ broken whitelists. If %HTML.AllowedElements or %HTML.AllowedAttributes
+ are set, this directive has no effect.
+
+ If HTML Purifier's attribute set is unsatisfactory, overload it!
+ The syntax is "tag.attr" or "*.attr" for the global attributes
+ (style, id, class, dir, lang, xml:lang).
+
+
+ Warning: If another directive conflicts with the
+ elements here, that directive will win and override. For
+ example, %HTML.EnableAttrID will take precedence over *.id in this
+ directive. You must set that directive to true before you can use
+ IDs at all.
+
+--# vim: et sw=4 sts=4
diff --git a/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/HTML.AllowedComments.txt b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/HTML.AllowedComments.txt
new file mode 100644
index 000000000..140e21423
--- /dev/null
+++ b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/HTML.AllowedComments.txt
@@ -0,0 +1,10 @@
+HTML.AllowedComments
+TYPE: lookup
+VERSION: 4.4.0
+DEFAULT: array()
+--DESCRIPTION--
+A whitelist which indicates what explicit comment bodies should be
+allowed, modulo leading and trailing whitespace. See also %HTML.AllowedCommentsRegexp
+(these directives are union'ed together, so a comment is considered
+valid if any directive deems it valid.)
+--# vim: et sw=4 sts=4
diff --git a/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/HTML.AllowedCommentsRegexp.txt b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/HTML.AllowedCommentsRegexp.txt
new file mode 100644
index 000000000..f22e977d4
--- /dev/null
+++ b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/HTML.AllowedCommentsRegexp.txt
@@ -0,0 +1,15 @@
+HTML.AllowedCommentsRegexp
+TYPE: string/null
+VERSION: 4.4.0
+DEFAULT: NULL
+--DESCRIPTION--
+A regexp, which if it matches the body of a comment, indicates that
+it should be allowed. Trailing and leading spaces are removed prior
+to running this regular expression.
+Warning: Make sure you specify
+correct anchor metacharacters ^regex$, otherwise you may accept
+comments that you did not mean to! In particular, the regex /foo|bar/
+is probably not sufficiently strict, since it also allows foobar.
+See also %HTML.AllowedComments (these directives are union'ed together,
+so a comment is considered valid if any directive deems it valid.)
+--# vim: et sw=4 sts=4
diff --git a/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/HTML.AllowedElements.txt b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/HTML.AllowedElements.txt
new file mode 100644
index 000000000..1d3fa7907
--- /dev/null
+++ b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/HTML.AllowedElements.txt
@@ -0,0 +1,23 @@
+HTML.AllowedElements
+TYPE: lookup/null
+VERSION: 1.3.0
+DEFAULT: NULL
+--DESCRIPTION--
+
+ If HTML Purifier's tag set is unsatisfactory for your needs, you can
+ overload it with your own list of tags to allow. If you change
+ this, you probably also want to change %HTML.AllowedAttributes; see
+ also %HTML.Allowed which lets you set allowed elements and
+ attributes at the same time.
+
+
+ If you attempt to allow an element that HTML Purifier does not know
+ about, HTML Purifier will raise an error. You will need to manually
+ tell HTML Purifier about this element by using the
+ advanced customization features.
+
+
+ Warning: If another directive conflicts with the
+ elements here, that directive will win and override.
+
+ A doctype comes with a set of usual modules to use. Without having
+ to mucking about with the doctypes, you can quickly activate or
+ disable these modules by specifying which modules you wish to allow
+ with this directive. This is most useful for unit testing specific
+ modules, although end users may find it useful for their own ends.
+
+
+ If you specify a module that does not exist, the manager will silently
+ fail to use it, so be careful! User-defined modules are not affected
+ by this directive. Modules defined in %HTML.CoreModules are not
+ affected by this directive.
+
+--# vim: et sw=4 sts=4
diff --git a/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/HTML.Attr.Name.UseCDATA.txt b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/HTML.Attr.Name.UseCDATA.txt
new file mode 100644
index 000000000..151fb7b82
--- /dev/null
+++ b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/HTML.Attr.Name.UseCDATA.txt
@@ -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
diff --git a/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/HTML.BlockWrapper.txt b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/HTML.BlockWrapper.txt
new file mode 100644
index 000000000..45ae469ec
--- /dev/null
+++ b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/HTML.BlockWrapper.txt
@@ -0,0 +1,18 @@
+HTML.BlockWrapper
+TYPE: string
+VERSION: 1.3.0
+DEFAULT: 'p'
+--DESCRIPTION--
+
+
+ String name of element to wrap inline elements that are inside a block
+ context. This only occurs in the children of blockquote in strict mode.
+
+
+ Example: by default value,
+ <blockquote>Foo</blockquote> would become
+ <blockquote><p>Foo</p></blockquote>.
+ The <p> tags can be replaced with whatever you desire,
+ as long as it is a block level element.
+
+ Certain modularized doctypes (XHTML, namely), have certain modules
+ that must be included for the doctype to be an conforming document
+ type: put those modules here. By default, XHTML's core modules
+ are used. You can set this to a blank array to disable core module
+ protection, but this is not recommended.
+
+--# vim: et sw=4 sts=4
diff --git a/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/HTML.CustomDoctype.txt b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/HTML.CustomDoctype.txt
new file mode 100644
index 000000000..a64e3d7c3
--- /dev/null
+++ b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/HTML.CustomDoctype.txt
@@ -0,0 +1,9 @@
+HTML.CustomDoctype
+TYPE: string/null
+VERSION: 2.0.1
+DEFAULT: NULL
+--DESCRIPTION--
+
+A custom doctype for power-users who defined there own document
+type. This directive only applies when %HTML.Doctype is blank.
+--# vim: et sw=4 sts=4
diff --git a/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/HTML.DefinitionID.txt b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/HTML.DefinitionID.txt
new file mode 100644
index 000000000..103db754a
--- /dev/null
+++ b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/HTML.DefinitionID.txt
@@ -0,0 +1,33 @@
+HTML.DefinitionID
+TYPE: string/null
+DEFAULT: NULL
+VERSION: 2.0.0
+--DESCRIPTION--
+
+
+ Unique identifier for a custom-built HTML definition. If you edit
+ the raw version of the HTMLDefinition, introducing changes that the
+ configuration object does not reflect, you must specify this variable.
+ If you change your custom edits, you should change this directive, or
+ clear your cache. Example:
+
+ In the above example, the configuration is still at the defaults, but
+ using the advanced API, an extra attribute has been added. The
+ configuration object normally has no way of knowing that this change
+ has taken place, so it needs an extra directive: %HTML.DefinitionID.
+ If someone else attempts to use the default configuration, these two
+ pieces of code will not clobber each other in the cache, since one has
+ an extra directive attached to it.
+
+
+ You must specify a value to this directive to use the
+ advanced API features.
+
+--# vim: et sw=4 sts=4
diff --git a/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/HTML.DefinitionRev.txt b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/HTML.DefinitionRev.txt
new file mode 100644
index 000000000..229ae0267
--- /dev/null
+++ b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/HTML.DefinitionRev.txt
@@ -0,0 +1,16 @@
+HTML.DefinitionRev
+TYPE: int
+VERSION: 2.0.0
+DEFAULT: 1
+--DESCRIPTION--
+
+
+ Revision identifier for your custom definition specified in
+ %HTML.DefinitionID. This serves the same purpose: uniquely identifying
+ your custom definition, but this one does so in a chronological
+ context: revision 3 is more up-to-date then revision 2. Thus, when
+ this gets incremented, the cache handling is smart enough to clean
+ up any older revisions of your definition as well as flush the
+ cache.
+
+--# vim: et sw=4 sts=4
diff --git a/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/HTML.Doctype.txt b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/HTML.Doctype.txt
new file mode 100644
index 000000000..9dab497f2
--- /dev/null
+++ b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/HTML.Doctype.txt
@@ -0,0 +1,11 @@
+HTML.Doctype
+TYPE: string/null
+DEFAULT: NULL
+--DESCRIPTION--
+Doctype to use during filtering. Technically speaking this is not actually
+a doctype (as it does not identify a corresponding DTD), but we are using
+this name for sake of simplicity. When non-blank, this will override any
+older directives like %HTML.XHTML or %HTML.Strict.
+--ALLOWED--
+'HTML 4.01 Transitional', 'HTML 4.01 Strict', 'XHTML 1.0 Transitional', 'XHTML 1.0 Strict', 'XHTML 1.1'
+--# vim: et sw=4 sts=4
diff --git a/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/HTML.FlashAllowFullScreen.txt b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/HTML.FlashAllowFullScreen.txt
new file mode 100644
index 000000000..7878dc0bf
--- /dev/null
+++ b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/HTML.FlashAllowFullScreen.txt
@@ -0,0 +1,11 @@
+HTML.FlashAllowFullScreen
+TYPE: bool
+VERSION: 4.2.0
+DEFAULT: false
+--DESCRIPTION--
+
+ Whether or not to permit embedded Flash content from
+ %HTML.SafeObject to expand to the full screen. Corresponds to
+ the allowFullScreen parameter.
+
+ While this directive is similar to %HTML.AllowedAttributes, for
+ forwards-compatibility with XML, this attribute has a different syntax. Instead of
+ tag.attr, use tag@attr. To disallow href
+ attributes in a tags, set this directive to
+ a@href. You can also disallow an attribute globally with
+ attr or *@attr (either syntax is fine; the latter
+ is provided for consistency with %HTML.AllowedAttributes).
+
+
+ Warning: This directive complements %HTML.ForbiddenElements,
+ accordingly, check
+ out that directive for a discussion of why you
+ should think twice before using this directive.
+
+ This was, perhaps, the most requested feature ever in HTML
+ Purifier. Please don't abuse it! This is the logical inverse of
+ %HTML.AllowedElements, and it will override that directive, or any
+ other directive.
+
+
+ If possible, %HTML.Allowed is recommended over this directive, because it
+ can sometimes be difficult to tell whether or not you've forbidden all of
+ the behavior you would like to disallow. If you forbid img
+ with the expectation of preventing images on your site, you'll be in for
+ a nasty surprise when people start using the background-image
+ CSS property.
+
+ This directive controls the maximum number of pixels in the width and
+ height attributes in img tags. This is
+ in place to prevent imagecrash attacks, disable with null at your own risk.
+ This directive is similar to %CSS.MaxImgLength, and both should be
+ concurrently edited, although there are
+ subtle differences in the input format (the HTML max is an integer).
+
+--# vim: et sw=4 sts=4
diff --git a/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/HTML.Nofollow.txt b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/HTML.Nofollow.txt
new file mode 100644
index 000000000..700b30924
--- /dev/null
+++ b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/HTML.Nofollow.txt
@@ -0,0 +1,7 @@
+HTML.Nofollow
+TYPE: bool
+VERSION: 4.3.0
+DEFAULT: FALSE
+--DESCRIPTION--
+If enabled, nofollow rel attributes are added to all outgoing links.
+--# vim: et sw=4 sts=4
diff --git a/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/HTML.Parent.txt b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/HTML.Parent.txt
new file mode 100644
index 000000000..62e8e160c
--- /dev/null
+++ b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/HTML.Parent.txt
@@ -0,0 +1,12 @@
+HTML.Parent
+TYPE: string
+VERSION: 1.3.0
+DEFAULT: 'div'
+--DESCRIPTION--
+
+
+ String name of element that HTML fragment passed to library will be
+ inserted in. An interesting variation would be using span as the
+ parent element, meaning that only inline tags would be allowed.
+
+ Whether or not to allow proprietary elements and attributes in your
+ documents, as per HTMLPurifier_HTMLModule_Proprietary.
+ Warning: This can cause your documents to stop
+ validating!
+
+ Whether or not to permit embed tags in documents, with a number of extra
+ security features added to prevent script execution. This is similar to
+ what websites like MySpace do to embed tags. Embed is a proprietary
+ element and will cause your website to stop validating; you should
+ see if you can use %Output.FlashCompat with %HTML.SafeObject instead
+ first.
+ Whether or not to permit iframe tags in untrusted documents. This
+ directive must be accompanied by a whitelist of permitted iframes,
+ such as %URI.SafeIframeRegexp, otherwise it will fatally error.
+ This directive has no effect on strict doctypes, as iframes are not
+ valid.
+
+ Whether or not to permit object tags in documents, with a number of extra
+ security features added to prevent script execution. This is similar to
+ what websites like MySpace do to object tags. You should also enable
+ %Output.FlashCompat in order to generate Internet Explorer
+ compatibility code for your object tags.
+
+ Whether or not to permit script tags to external scripts in documents.
+ Inline scripting is not allowed, and the script must match an explicit whitelist.
+
+--# vim: et sw=4 sts=4
diff --git a/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/HTML.Strict.txt b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/HTML.Strict.txt
new file mode 100644
index 000000000..a8b1de56b
--- /dev/null
+++ b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/HTML.Strict.txt
@@ -0,0 +1,9 @@
+HTML.Strict
+TYPE: bool
+VERSION: 1.3.0
+DEFAULT: false
+DEPRECATED-VERSION: 1.7.0
+DEPRECATED-USE: HTML.Doctype
+--DESCRIPTION--
+Determines whether or not to use Transitional (loose) or Strict rulesets.
+--# vim: et sw=4 sts=4
diff --git a/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/HTML.TargetBlank.txt b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/HTML.TargetBlank.txt
new file mode 100644
index 000000000..587a16778
--- /dev/null
+++ b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/HTML.TargetBlank.txt
@@ -0,0 +1,8 @@
+HTML.TargetBlank
+TYPE: bool
+VERSION: 4.4.0
+DEFAULT: FALSE
+--DESCRIPTION--
+If enabled, target=blank attributes are added to all outgoing links.
+(This includes links from an HTTPS version of a page to an HTTP version.)
+--# vim: et sw=4 sts=4
diff --git a/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/HTML.TidyAdd.txt b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/HTML.TidyAdd.txt
new file mode 100644
index 000000000..b4c271b7f
--- /dev/null
+++ b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/HTML.TidyAdd.txt
@@ -0,0 +1,8 @@
+HTML.TidyAdd
+TYPE: lookup
+VERSION: 2.0.0
+DEFAULT: array()
+--DESCRIPTION--
+
+Fixes to add to the default set of Tidy fixes as per your level.
+--# vim: et sw=4 sts=4
diff --git a/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/HTML.TidyLevel.txt b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/HTML.TidyLevel.txt
new file mode 100644
index 000000000..4186ccd0d
--- /dev/null
+++ b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/HTML.TidyLevel.txt
@@ -0,0 +1,24 @@
+HTML.TidyLevel
+TYPE: string
+VERSION: 2.0.0
+DEFAULT: 'medium'
+--DESCRIPTION--
+
+
General level of cleanliness the Tidy module should enforce.
+There are four allowed values:
+
+
none
+
No extra tidying should be done
+
light
+
Only fix elements that would be discarded otherwise due to
+ lack of support in doctype
+
medium
+
Enforce best practices
+
heavy
+
Transform all deprecated elements and attributes to standards
+ compliant equivalents
+
+
+--ALLOWED--
+'none', 'light', 'medium', 'heavy'
+--# vim: et sw=4 sts=4
diff --git a/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/HTML.TidyRemove.txt b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/HTML.TidyRemove.txt
new file mode 100644
index 000000000..996762bd1
--- /dev/null
+++ b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/HTML.TidyRemove.txt
@@ -0,0 +1,8 @@
+HTML.TidyRemove
+TYPE: lookup
+VERSION: 2.0.0
+DEFAULT: array()
+--DESCRIPTION--
+
+Fixes to remove from the default set of Tidy fixes as per your level.
+--# vim: et sw=4 sts=4
diff --git a/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/HTML.Trusted.txt b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/HTML.Trusted.txt
new file mode 100644
index 000000000..1db9237e9
--- /dev/null
+++ b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/HTML.Trusted.txt
@@ -0,0 +1,9 @@
+HTML.Trusted
+TYPE: bool
+VERSION: 2.0.0
+DEFAULT: false
+--DESCRIPTION--
+Indicates whether or not the user input is trusted or not. If the input is
+trusted, a more expansive set of allowed tags and attributes will be used.
+See also %CSS.Trusted.
+--# vim: et sw=4 sts=4
diff --git a/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/HTML.XHTML.txt b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/HTML.XHTML.txt
new file mode 100644
index 000000000..2a47e384f
--- /dev/null
+++ b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/HTML.XHTML.txt
@@ -0,0 +1,11 @@
+HTML.XHTML
+TYPE: bool
+DEFAULT: true
+VERSION: 1.1.0
+DEPRECATED-VERSION: 1.7.0
+DEPRECATED-USE: HTML.Doctype
+--DESCRIPTION--
+Determines whether or not output is XHTML 1.0 or HTML 4.01 flavor.
+--ALIASES--
+Core.XHTML
+--# vim: et sw=4 sts=4
diff --git a/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/Output.CommentScriptContents.txt b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/Output.CommentScriptContents.txt
new file mode 100644
index 000000000..08921fde7
--- /dev/null
+++ b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/Output.CommentScriptContents.txt
@@ -0,0 +1,10 @@
+Output.CommentScriptContents
+TYPE: bool
+VERSION: 2.0.0
+DEFAULT: true
+--DESCRIPTION--
+Determines whether or not HTML Purifier should attempt to fix up the
+contents of script tags for legacy browsers with comments.
+--ALIASES--
+Core.CommentScriptContents
+--# vim: et sw=4 sts=4
diff --git a/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/Output.FixInnerHTML.txt b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/Output.FixInnerHTML.txt
new file mode 100644
index 000000000..d6f0d9f29
--- /dev/null
+++ b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/Output.FixInnerHTML.txt
@@ -0,0 +1,15 @@
+Output.FixInnerHTML
+TYPE: bool
+VERSION: 4.3.0
+DEFAULT: true
+--DESCRIPTION--
+
+ If true, HTML Purifier will protect against Internet Explorer's
+ mishandling of the innerHTML attribute by appending
+ a space to any attribute that does not contain angled brackets, spaces
+ or quotes, but contains a backtick. This slightly changes the
+ semantics of any given attribute, so if this is unacceptable and
+ you do not use innerHTML on any of your pages, you can
+ turn this directive off.
+
+ If true, HTML Purifier will generate Internet Explorer compatibility
+ code for all object code. This is highly recommended if you enable
+ %HTML.SafeObject.
+
+ Newline string to format final output with. If left null, HTML Purifier
+ will auto-detect the default newline type of the system and use that;
+ you can manually override it here. Remember, \r\n is Windows, \r
+ is Mac, and \n is Unix.
+
+ If true, HTML Purifier will sort attributes by name before writing them back
+ to the document, converting a tag like: <el b="" a="" c="" />
+ to <el a="" b="" c="" />. This is a workaround for
+ a bug in FCKeditor which causes it to swap attributes order, adding noise
+ to text diffs. If you're not seeing this bug, chances are, you don't need
+ this directive.
+
+ Determines whether or not to run Tidy on the final output for pretty
+ formatting reasons, such as indentation and wrap.
+
+
+ This can greatly improve readability for editors who are hand-editing
+ the HTML, but is by no means necessary as HTML Purifier has already
+ fixed all major errors the HTML may have had. Tidy is a non-default
+ extension, and this directive will silently fail if Tidy is not
+ available.
+
+
+ If you are looking to make the overall look of your page's source
+ better, I recommend running Tidy on the entire page rather than just
+ user-content (after all, the indentation relative to the containing
+ blocks will be incorrect).
+
+--ALIASES--
+Core.TidyFormat
+--# vim: et sw=4 sts=4
diff --git a/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/Test.ForceNoIconv.txt b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/Test.ForceNoIconv.txt
new file mode 100644
index 000000000..071bc0295
--- /dev/null
+++ b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/Test.ForceNoIconv.txt
@@ -0,0 +1,7 @@
+Test.ForceNoIconv
+TYPE: bool
+DEFAULT: false
+--DESCRIPTION--
+When set to true, HTMLPurifier_Encoder will act as if iconv does not exist
+and use only pure PHP implementations.
+--# vim: et sw=4 sts=4
diff --git a/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/URI.AllowedSchemes.txt b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/URI.AllowedSchemes.txt
new file mode 100644
index 000000000..666635a5f
--- /dev/null
+++ b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/URI.AllowedSchemes.txt
@@ -0,0 +1,17 @@
+URI.AllowedSchemes
+TYPE: lookup
+--DEFAULT--
+array (
+ 'http' => true,
+ 'https' => true,
+ 'mailto' => true,
+ 'ftp' => true,
+ 'nntp' => true,
+ 'news' => true,
+)
+--DESCRIPTION--
+Whitelist that defines the schemes that a URI is allowed to have. This
+prevents XSS attacks from using pseudo-schemes like javascript or mocha.
+There is also support for the data and file
+URI schemes, but they are not enabled by default.
+--# vim: et sw=4 sts=4
diff --git a/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/URI.Base.txt b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/URI.Base.txt
new file mode 100644
index 000000000..876f0680c
--- /dev/null
+++ b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/URI.Base.txt
@@ -0,0 +1,17 @@
+URI.Base
+TYPE: string/null
+VERSION: 2.1.0
+DEFAULT: NULL
+--DESCRIPTION--
+
+
+ The base URI is the URI of the document this purified HTML will be
+ inserted into. This information is important if HTML Purifier needs
+ to calculate absolute URIs from relative URIs, such as when %URI.MakeAbsolute
+ is on. You may use a non-absolute URI for this value, but behavior
+ may vary (%URI.MakeAbsolute deals nicely with both absolute and
+ relative paths, but forwards-compatibility is not guaranteed).
+ Warning: If set, the scheme on this URI
+ overrides the one specified by %URI.DefaultScheme.
+
+ 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).
+
+
+--ALIASES--
+Attr.DisableURI
+--# vim: et sw=4 sts=4
diff --git a/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/URI.DisableExternal.txt b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/URI.DisableExternal.txt
new file mode 100644
index 000000000..13c122c8c
--- /dev/null
+++ b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/URI.DisableExternal.txt
@@ -0,0 +1,11 @@
+URI.DisableExternal
+TYPE: bool
+VERSION: 1.2.0
+DEFAULT: false
+--DESCRIPTION--
+Disables links to external websites. This is a highly effective anti-spam
+and anti-pagerank-leech measure, but comes at a hefty price: nolinks 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.
+--# vim: et sw=4 sts=4
diff --git a/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/URI.DisableExternalResources.txt b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/URI.DisableExternalResources.txt
new file mode 100644
index 000000000..abcc1efd6
--- /dev/null
+++ b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/URI.DisableExternalResources.txt
@@ -0,0 +1,13 @@
+URI.DisableExternalResources
+TYPE: bool
+VERSION: 1.3.0
+DEFAULT: false
+--DESCRIPTION--
+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.
+--# vim: et sw=4 sts=4
diff --git a/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/URI.DisableResources.txt b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/URI.DisableResources.txt
new file mode 100644
index 000000000..f891de499
--- /dev/null
+++ b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/URI.DisableResources.txt
@@ -0,0 +1,15 @@
+URI.DisableResources
+TYPE: bool
+VERSION: 4.2.0
+DEFAULT: false
+--DESCRIPTION--
+
+ 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.
+
+
+ Note: While this directive has been available since 1.3.0,
+ it didn't actually start doing anything until 4.2.0.
+
+ 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.
+ Note: This directive overrides %URI.Base because
+ a given page may be on a sub-domain, but you wish HTML Purifier to be
+ more relaxed and allow some of the parent domains too.
+
+--# vim: et sw=4 sts=4
diff --git a/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/URI.HostBlacklist.txt b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/URI.HostBlacklist.txt
new file mode 100644
index 000000000..0b6df7625
--- /dev/null
+++ b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/URI.HostBlacklist.txt
@@ -0,0 +1,9 @@
+URI.HostBlacklist
+TYPE: list
+VERSION: 1.3.0
+DEFAULT: array()
+--DESCRIPTION--
+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 moo.com will catch moo.com.example.com.
+--# vim: et sw=4 sts=4
diff --git a/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/URI.MakeAbsolute.txt b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/URI.MakeAbsolute.txt
new file mode 100644
index 000000000..4214900a5
--- /dev/null
+++ b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/URI.MakeAbsolute.txt
@@ -0,0 +1,13 @@
+URI.MakeAbsolute
+TYPE: bool
+VERSION: 2.1.0
+DEFAULT: false
+--DESCRIPTION--
+
+
+ Converts all URIs into absolute forms. This is useful when the HTML
+ being filtered assumes a specific base path, but will actually be
+ viewed in a different context (and setting an alternate base URI is
+ not possible). %URI.Base must be set for this directive to work.
+
+ Munges all browsable (usually http, https and ftp)
+ absolute URIs into another URI, usually a URI redirection service.
+ This directive accepts a URI, formatted with a %s where
+ the url-encoded original URI should be inserted (sample:
+ http://www.google.com/url?q=%s).
+
+
+ Uses for this directive:
+
+
+
+ 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). Notice:
+ Many security experts believe that this form of protection does not deter spam-bots.
+
+
+ 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.
+
+
+
+ Prior to HTML Purifier 3.1.1, this directive also enabled the munging
+ of browsable external resources, which could break things if your redirection
+ script was a splash page or used meta tags. To revert to
+ previous behavior, please use %URI.MungeResources.
+
+
+ You may want to also use %URI.MungeSecretKey along with this directive
+ in order to enforce what URIs your redirector script allows. Open
+ redirector scripts can be a security risk and negatively affect the
+ reputation of your domain name.
+
+
+ Starting with HTML Purifier 3.1.1, there is also these substitutions:
+
+
+
+
+
Key
+
Description
+
Example <a href="">
+
+
+
+
+
%r
+
1 - The URI embeds a resource (blank) - The URI is merely a link
+
+
+
+
%n
+
The name of the tag this URI came from
+
a
+
+
+
%m
+
The name of the attribute this URI came from
+
href
+
+
+
%p
+
The name of the CSS property this URI came from, or blank if irrelevant
+
+
+
+
+
+ Admittedly, these letters are somewhat arbitrary; the only stipulation
+ was that they couldn't be a through f. r is for resource (I would have preferred
+ e, but you take what you can get), n is for name, m
+ was picked because it came after n (and I couldn't use a), p is for
+ property.
+
+ If true, any URI munging directives like %URI.Munge
+ will also apply to embedded resources, such as <img src="">.
+ Be careful enabling this directive if you have a redirector script
+ that does not use the Location HTTP header; all of your images
+ and other embedded resources will break.
+
+
+ Warning: It is strongly advised you use this in conjunction
+ %URI.MungeSecretKey to mitigate the security risk of an open redirector.
+
+ This directive enables secure checksum generation along with %URI.Munge.
+ It should be set to a secure key that is not shared with anyone else.
+ The checksum can be placed in the URI using %t. Use of this checksum
+ affords an additional level of protection by allowing a redirector
+ to check if a URI has passed through HTML Purifier with this line:
+
+
+
$checksum === sha1($secret_key . ':' . $url)
+
+
+ If the output is TRUE, the redirector script should accept the URI.
+
+
+
+ Please note that it would still be possible for an attacker to procure
+ secure hashes en-mass by abusing your website's Preview feature or the
+ like, but this service affords an additional level of protection
+ that should be combined with website blacklisting.
+
+
+
+ Remember this has no effect if %URI.Munge is not on.
+
+--# vim: et sw=4 sts=4
diff --git a/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/URI.OverrideAllowedSchemes.txt b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/URI.OverrideAllowedSchemes.txt
new file mode 100644
index 000000000..23331a4e7
--- /dev/null
+++ b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/URI.OverrideAllowedSchemes.txt
@@ -0,0 +1,9 @@
+URI.OverrideAllowedSchemes
+TYPE: bool
+DEFAULT: true
+--DESCRIPTION--
+If this is set to true (which it is by default), you can override
+%URI.AllowedSchemes by simply registering a HTMLPurifier_URIScheme to the
+registry. If false, you will also have to update that directive in order
+to add more schemes.
+--# vim: et sw=4 sts=4
diff --git a/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/URI.SafeIframeRegexp.txt b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/URI.SafeIframeRegexp.txt
new file mode 100644
index 000000000..79084832b
--- /dev/null
+++ b/plugin/htmlpurifier/standalone/HTMLPurifier/ConfigSchema/schema/URI.SafeIframeRegexp.txt
@@ -0,0 +1,22 @@
+URI.SafeIframeRegexp
+TYPE: string/null
+VERSION: 4.4.0
+DEFAULT: NULL
+--DESCRIPTION--
+
+ A PCRE regular expression that will be matched against an iframe URI. This is
+ a relatively inflexible scheme, but works well enough for the most common
+ use-case of iframes: embedded video. This directive only has an effect if
+ %HTML.SafeIframe is enabled. Here are some example values:
+
%^http://(www.youtube.com/embed/|player.vimeo.com/video/)% - Allow both
+
+
+ Note that this directive does not give you enough granularity to, say, disable
+ all autoplay videos. Pipe up on the HTML Purifier forums if this
+ is a capability you want.
+
+ , $tokens);
+ return $tokens;
+ }
+
+}
+
+/*
+
+Copyright 2007 Jeroen van der Meer
+
+Permission is hereby granted, free of charge, to any person obtaining a
+copy of this software and associated documentation files (the
+"Software"), to deal in the Software without restriction, including
+without limitation the rights to use, copy, modify, merge, publish,
+distribute, sublicense, and/or sell copies of the Software, and to
+permit persons to whom the Software is furnished to do so, subject to
+the following conditions:
+
+The above copyright notice and this permission notice shall be included
+in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
+OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
+IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY
+CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT,
+TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
+SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
+
+*/
+
+class HTML5 {
+ private $data;
+ private $char;
+ private $EOF;
+ private $state;
+ private $tree;
+ private $token;
+ private $content_model;
+ private $escape = false;
+ private $entities = array('AElig;','AElig','AMP;','AMP','Aacute;','Aacute',
+ 'Acirc;','Acirc','Agrave;','Agrave','Alpha;','Aring;','Aring','Atilde;',
+ 'Atilde','Auml;','Auml','Beta;','COPY;','COPY','Ccedil;','Ccedil','Chi;',
+ 'Dagger;','Delta;','ETH;','ETH','Eacute;','Eacute','Ecirc;','Ecirc','Egrave;',
+ 'Egrave','Epsilon;','Eta;','Euml;','Euml','GT;','GT','Gamma;','Iacute;',
+ 'Iacute','Icirc;','Icirc','Igrave;','Igrave','Iota;','Iuml;','Iuml','Kappa;',
+ 'LT;','LT','Lambda;','Mu;','Ntilde;','Ntilde','Nu;','OElig;','Oacute;',
+ 'Oacute','Ocirc;','Ocirc','Ograve;','Ograve','Omega;','Omicron;','Oslash;',
+ 'Oslash','Otilde;','Otilde','Ouml;','Ouml','Phi;','Pi;','Prime;','Psi;',
+ 'QUOT;','QUOT','REG;','REG','Rho;','Scaron;','Sigma;','THORN;','THORN',
+ 'TRADE;','Tau;','Theta;','Uacute;','Uacute','Ucirc;','Ucirc','Ugrave;',
+ 'Ugrave','Upsilon;','Uuml;','Uuml','Xi;','Yacute;','Yacute','Yuml;','Zeta;',
+ 'aacute;','aacute','acirc;','acirc','acute;','acute','aelig;','aelig',
+ 'agrave;','agrave','alefsym;','alpha;','amp;','amp','and;','ang;','apos;',
+ 'aring;','aring','asymp;','atilde;','atilde','auml;','auml','bdquo;','beta;',
+ 'brvbar;','brvbar','bull;','cap;','ccedil;','ccedil','cedil;','cedil',
+ 'cent;','cent','chi;','circ;','clubs;','cong;','copy;','copy','crarr;',
+ 'cup;','curren;','curren','dArr;','dagger;','darr;','deg;','deg','delta;',
+ 'diams;','divide;','divide','eacute;','eacute','ecirc;','ecirc','egrave;',
+ 'egrave','empty;','emsp;','ensp;','epsilon;','equiv;','eta;','eth;','eth',
+ 'euml;','euml','euro;','exist;','fnof;','forall;','frac12;','frac12',
+ 'frac14;','frac14','frac34;','frac34','frasl;','gamma;','ge;','gt;','gt',
+ 'hArr;','harr;','hearts;','hellip;','iacute;','iacute','icirc;','icirc',
+ 'iexcl;','iexcl','igrave;','igrave','image;','infin;','int;','iota;',
+ 'iquest;','iquest','isin;','iuml;','iuml','kappa;','lArr;','lambda;','lang;',
+ 'laquo;','laquo','larr;','lceil;','ldquo;','le;','lfloor;','lowast;','loz;',
+ 'lrm;','lsaquo;','lsquo;','lt;','lt','macr;','macr','mdash;','micro;','micro',
+ 'middot;','middot','minus;','mu;','nabla;','nbsp;','nbsp','ndash;','ne;',
+ 'ni;','not;','not','notin;','nsub;','ntilde;','ntilde','nu;','oacute;',
+ 'oacute','ocirc;','ocirc','oelig;','ograve;','ograve','oline;','omega;',
+ 'omicron;','oplus;','or;','ordf;','ordf','ordm;','ordm','oslash;','oslash',
+ 'otilde;','otilde','otimes;','ouml;','ouml','para;','para','part;','permil;',
+ 'perp;','phi;','pi;','piv;','plusmn;','plusmn','pound;','pound','prime;',
+ 'prod;','prop;','psi;','quot;','quot','rArr;','radic;','rang;','raquo;',
+ 'raquo','rarr;','rceil;','rdquo;','real;','reg;','reg','rfloor;','rho;',
+ 'rlm;','rsaquo;','rsquo;','sbquo;','scaron;','sdot;','sect;','sect','shy;',
+ 'shy','sigma;','sigmaf;','sim;','spades;','sub;','sube;','sum;','sup1;',
+ 'sup1','sup2;','sup2','sup3;','sup3','sup;','supe;','szlig;','szlig','tau;',
+ 'there4;','theta;','thetasym;','thinsp;','thorn;','thorn','tilde;','times;',
+ 'times','trade;','uArr;','uacute;','uacute','uarr;','ucirc;','ucirc',
+ 'ugrave;','ugrave','uml;','uml','upsih;','upsilon;','uuml;','uuml','weierp;',
+ 'xi;','yacute;','yacute','yen;','yen','yuml;','yuml','zeta;','zwj;','zwnj;');
+
+ const PCDATA = 0;
+ const RCDATA = 1;
+ const CDATA = 2;
+ const PLAINTEXT = 3;
+
+ const DOCTYPE = 0;
+ const STARTTAG = 1;
+ const ENDTAG = 2;
+ const COMMENT = 3;
+ const CHARACTR = 4;
+ const EOF = 5;
+
+ public function __construct($data) {
+
+ $this->data = $data;
+ $this->char = -1;
+ $this->EOF = strlen($data);
+ $this->tree = new HTML5TreeConstructer;
+ $this->content_model = self::PCDATA;
+
+ $this->state = 'data';
+
+ while($this->state !== null) {
+ $this->{$this->state.'State'}();
+ }
+ }
+
+ public function save() {
+ return $this->tree->save();
+ }
+
+ private function char() {
+ return ($this->char < $this->EOF)
+ ? $this->data[$this->char]
+ : false;
+ }
+
+ private function character($s, $l = 0) {
+ if($s + $l < $this->EOF) {
+ if($l === 0) {
+ return $this->data[$s];
+ } else {
+ return substr($this->data, $s, $l);
+ }
+ }
+ }
+
+ private function characters($char_class, $start) {
+ return preg_replace('#^(['.$char_class.']+).*#s', '\\1', substr($this->data, $start));
+ }
+
+ private function dataState() {
+ // Consume the next input character
+ $this->char++;
+ $char = $this->char();
+
+ if($char === '&' && ($this->content_model === self::PCDATA || $this->content_model === self::RCDATA)) {
+ /* U+0026 AMPERSAND (&)
+ When the content model flag is set to one of the PCDATA or RCDATA
+ states: switch to the entity data state. Otherwise: treat it as per
+ the "anything else" entry below. */
+ $this->state = 'entityData';
+
+ } elseif($char === '-') {
+ /* If the content model flag is set to either the RCDATA state or
+ the CDATA state, and the escape flag is false, and there are at
+ least three characters before this one in the input stream, and the
+ last four characters in the input stream, including this one, are
+ U+003C LESS-THAN SIGN, U+0021 EXCLAMATION MARK, U+002D HYPHEN-MINUS,
+ and U+002D HYPHEN-MINUS (""),
+ set the escape flag to false. */
+ if(($this->content_model === self::RCDATA ||
+ $this->content_model === self::CDATA) && $this->escape === true &&
+ $this->character($this->char, 3) === '-->') {
+ $this->escape = false;
+ }
+
+ /* In any case, emit the input character as a character token.
+ Stay in the data state. */
+ $this->emitToken(array(
+ 'type' => self::CHARACTR,
+ 'data' => $char
+ ));
+
+ } elseif($this->char === $this->EOF) {
+ /* EOF
+ Emit an end-of-file token. */
+ $this->EOF();
+
+ } elseif($this->content_model === self::PLAINTEXT) {
+ /* When the content model flag is set to the PLAINTEXT state
+ THIS DIFFERS GREATLY FROM THE SPEC: Get the remaining characters of
+ the text and emit it as a character token. */
+ $this->emitToken(array(
+ 'type' => self::CHARACTR,
+ 'data' => substr($this->data, $this->char)
+ ));
+
+ $this->EOF();
+
+ } else {
+ /* Anything else
+ THIS DIFFERS GREATLY FROM THE SPEC: Get as many character that
+ otherwise would also be treated as a character token and emit it
+ as a single character token. Stay in the data state. */
+ $len = strcspn($this->data, '<&', $this->char);
+ $char = substr($this->data, $this->char, $len);
+ $this->char += $len - 1;
+
+ $this->emitToken(array(
+ 'type' => self::CHARACTR,
+ 'data' => $char
+ ));
+
+ $this->state = 'data';
+ }
+ }
+
+ private function entityDataState() {
+ // Attempt to consume an entity.
+ $entity = $this->entity();
+
+ // If nothing is returned, emit a U+0026 AMPERSAND character token.
+ // Otherwise, emit the character token that was returned.
+ $char = (!$entity) ? '&' : $entity;
+ $this->emitToken(array(
+ 'type' => self::CHARACTR,
+ 'data' => $char
+ ));
+
+ // Finally, switch to the data state.
+ $this->state = 'data';
+ }
+
+ private function tagOpenState() {
+ switch($this->content_model) {
+ case self::RCDATA:
+ case self::CDATA:
+ /* If the next input character is a U+002F SOLIDUS (/) character,
+ consume it and switch to the close tag open state. If the next
+ input character is not a U+002F SOLIDUS (/) character, emit a
+ U+003C LESS-THAN SIGN character token and switch to the data
+ state to process the next input character. */
+ if($this->character($this->char + 1) === '/') {
+ $this->char++;
+ $this->state = 'closeTagOpen';
+
+ } else {
+ $this->emitToken(array(
+ 'type' => self::CHARACTR,
+ 'data' => '<'
+ ));
+
+ $this->state = 'data';
+ }
+ break;
+
+ case self::PCDATA:
+ // If the content model flag is set to the PCDATA state
+ // Consume the next input character:
+ $this->char++;
+ $char = $this->char();
+
+ if($char === '!') {
+ /* U+0021 EXCLAMATION MARK (!)
+ Switch to the markup declaration open state. */
+ $this->state = 'markupDeclarationOpen';
+
+ } elseif($char === '/') {
+ /* U+002F SOLIDUS (/)
+ Switch to the close tag open state. */
+ $this->state = 'closeTagOpen';
+
+ } elseif(preg_match('/^[A-Za-z]$/', $char)) {
+ /* U+0041 LATIN LETTER A through to U+005A LATIN LETTER Z
+ Create a new start tag token, set its tag name to the lowercase
+ version of the input character (add 0x0020 to the character's code
+ point), then switch to the tag name state. (Don't emit the token
+ yet; further details will be filled in before it is emitted.) */
+ $this->token = array(
+ 'name' => strtolower($char),
+ 'type' => self::STARTTAG,
+ 'attr' => array()
+ );
+
+ $this->state = 'tagName';
+
+ } elseif($char === '>') {
+ /* U+003E GREATER-THAN SIGN (>)
+ Parse error. Emit a U+003C LESS-THAN SIGN character token and a
+ U+003E GREATER-THAN SIGN character token. Switch to the data state. */
+ $this->emitToken(array(
+ 'type' => self::CHARACTR,
+ 'data' => '<>'
+ ));
+
+ $this->state = 'data';
+
+ } elseif($char === '?') {
+ /* U+003F QUESTION MARK (?)
+ Parse error. Switch to the bogus comment state. */
+ $this->state = 'bogusComment';
+
+ } else {
+ /* Anything else
+ Parse error. Emit a U+003C LESS-THAN SIGN character token and
+ reconsume the current input character in the data state. */
+ $this->emitToken(array(
+ 'type' => self::CHARACTR,
+ 'data' => '<'
+ ));
+
+ $this->char--;
+ $this->state = 'data';
+ }
+ break;
+ }
+ }
+
+ private function closeTagOpenState() {
+ $next_node = strtolower($this->characters('A-Za-z', $this->char + 1));
+ $the_same = count($this->tree->stack) > 0 && $next_node === end($this->tree->stack)->nodeName;
+
+ if(($this->content_model === self::RCDATA || $this->content_model === self::CDATA) &&
+ (!$the_same || ($the_same && (!preg_match('/[\t\n\x0b\x0c >\/]/',
+ $this->character($this->char + 1 + strlen($next_node))) || $this->EOF === $this->char)))) {
+ /* If the content model flag is set to the RCDATA or CDATA states then
+ examine the next few characters. If they do not match the tag name of
+ the last start tag token emitted (case insensitively), or if they do but
+ they are not immediately followed by one of the following characters:
+ * U+0009 CHARACTER TABULATION
+ * U+000A LINE FEED (LF)
+ * U+000B LINE TABULATION
+ * U+000C FORM FEED (FF)
+ * U+0020 SPACE
+ * U+003E GREATER-THAN SIGN (>)
+ * U+002F SOLIDUS (/)
+ * EOF
+ ...then there is a parse error. Emit a U+003C LESS-THAN SIGN character
+ token, a U+002F SOLIDUS character token, and switch to the data state
+ to process the next input character. */
+ $this->emitToken(array(
+ 'type' => self::CHARACTR,
+ 'data' => ''
+ ));
+
+ $this->state = 'data';
+
+ } else {
+ /* Otherwise, if the content model flag is set to the PCDATA state,
+ or if the next few characters do match that tag name, consume the
+ next input character: */
+ $this->char++;
+ $char = $this->char();
+
+ if(preg_match('/^[A-Za-z]$/', $char)) {
+ /* U+0041 LATIN LETTER A through to U+005A LATIN LETTER Z
+ Create a new end tag token, set its tag name to the lowercase version
+ of the input character (add 0x0020 to the character's code point), then
+ switch to the tag name state. (Don't emit the token yet; further details
+ will be filled in before it is emitted.) */
+ $this->token = array(
+ 'name' => strtolower($char),
+ 'type' => self::ENDTAG
+ );
+
+ $this->state = 'tagName';
+
+ } elseif($char === '>') {
+ /* U+003E GREATER-THAN SIGN (>)
+ Parse error. Switch to the data state. */
+ $this->state = 'data';
+
+ } elseif($this->char === $this->EOF) {
+ /* EOF
+ Parse error. Emit a U+003C LESS-THAN SIGN character token and a U+002F
+ SOLIDUS character token. Reconsume the EOF character in the data state. */
+ $this->emitToken(array(
+ 'type' => self::CHARACTR,
+ 'data' => ''
+ ));
+
+ $this->char--;
+ $this->state = 'data';
+
+ } else {
+ /* Parse error. Switch to the bogus comment state. */
+ $this->state = 'bogusComment';
+ }
+ }
+ }
+
+ private function tagNameState() {
+ // Consume the next input character:
+ $this->char++;
+ $char = $this->character($this->char);
+
+ if(preg_match('/^[\t\n\x0b\x0c ]$/', $char)) {
+ /* U+0009 CHARACTER TABULATION
+ U+000A LINE FEED (LF)
+ U+000B LINE TABULATION
+ U+000C FORM FEED (FF)
+ U+0020 SPACE
+ Switch to the before attribute name state. */
+ $this->state = 'beforeAttributeName';
+
+ } elseif($char === '>') {
+ /* U+003E GREATER-THAN SIGN (>)
+ Emit the current tag token. Switch to the data state. */
+ $this->emitToken($this->token);
+ $this->state = 'data';
+
+ } elseif($this->char === $this->EOF) {
+ /* EOF
+ Parse error. Emit the current tag token. Reconsume the EOF
+ character in the data state. */
+ $this->emitToken($this->token);
+
+ $this->char--;
+ $this->state = 'data';
+
+ } elseif($char === '/') {
+ /* U+002F SOLIDUS (/)
+ Parse error unless this is a permitted slash. Switch to the before
+ attribute name state. */
+ $this->state = 'beforeAttributeName';
+
+ } else {
+ /* Anything else
+ Append the current input character to the current tag token's tag name.
+ Stay in the tag name state. */
+ $this->token['name'] .= strtolower($char);
+ $this->state = 'tagName';
+ }
+ }
+
+ private function beforeAttributeNameState() {
+ // Consume the next input character:
+ $this->char++;
+ $char = $this->character($this->char);
+
+ if(preg_match('/^[\t\n\x0b\x0c ]$/', $char)) {
+ /* U+0009 CHARACTER TABULATION
+ U+000A LINE FEED (LF)
+ U+000B LINE TABULATION
+ U+000C FORM FEED (FF)
+ U+0020 SPACE
+ Stay in the before attribute name state. */
+ $this->state = 'beforeAttributeName';
+
+ } elseif($char === '>') {
+ /* U+003E GREATER-THAN SIGN (>)
+ Emit the current tag token. Switch to the data state. */
+ $this->emitToken($this->token);
+ $this->state = 'data';
+
+ } elseif($char === '/') {
+ /* U+002F SOLIDUS (/)
+ Parse error unless this is a permitted slash. Stay in the before
+ attribute name state. */
+ $this->state = 'beforeAttributeName';
+
+ } elseif($this->char === $this->EOF) {
+ /* EOF
+ Parse error. Emit the current tag token. Reconsume the EOF
+ character in the data state. */
+ $this->emitToken($this->token);
+
+ $this->char--;
+ $this->state = 'data';
+
+ } else {
+ /* Anything else
+ Start a new attribute in the current tag token. Set that attribute's
+ name to the current input character, and its value to the empty string.
+ Switch to the attribute name state. */
+ $this->token['attr'][] = array(
+ 'name' => strtolower($char),
+ 'value' => null
+ );
+
+ $this->state = 'attributeName';
+ }
+ }
+
+ private function attributeNameState() {
+ // Consume the next input character:
+ $this->char++;
+ $char = $this->character($this->char);
+
+ if(preg_match('/^[\t\n\x0b\x0c ]$/', $char)) {
+ /* U+0009 CHARACTER TABULATION
+ U+000A LINE FEED (LF)
+ U+000B LINE TABULATION
+ U+000C FORM FEED (FF)
+ U+0020 SPACE
+ Stay in the before attribute name state. */
+ $this->state = 'afterAttributeName';
+
+ } elseif($char === '=') {
+ /* U+003D EQUALS SIGN (=)
+ Switch to the before attribute value state. */
+ $this->state = 'beforeAttributeValue';
+
+ } elseif($char === '>') {
+ /* U+003E GREATER-THAN SIGN (>)
+ Emit the current tag token. Switch to the data state. */
+ $this->emitToken($this->token);
+ $this->state = 'data';
+
+ } elseif($char === '/' && $this->character($this->char + 1) !== '>') {
+ /* U+002F SOLIDUS (/)
+ Parse error unless this is a permitted slash. Switch to the before
+ attribute name state. */
+ $this->state = 'beforeAttributeName';
+
+ } elseif($this->char === $this->EOF) {
+ /* EOF
+ Parse error. Emit the current tag token. Reconsume the EOF
+ character in the data state. */
+ $this->emitToken($this->token);
+
+ $this->char--;
+ $this->state = 'data';
+
+ } else {
+ /* Anything else
+ Append the current input character to the current attribute's name.
+ Stay in the attribute name state. */
+ $last = count($this->token['attr']) - 1;
+ $this->token['attr'][$last]['name'] .= strtolower($char);
+
+ $this->state = 'attributeName';
+ }
+ }
+
+ private function afterAttributeNameState() {
+ // Consume the next input character:
+ $this->char++;
+ $char = $this->character($this->char);
+
+ if(preg_match('/^[\t\n\x0b\x0c ]$/', $char)) {
+ /* U+0009 CHARACTER TABULATION
+ U+000A LINE FEED (LF)
+ U+000B LINE TABULATION
+ U+000C FORM FEED (FF)
+ U+0020 SPACE
+ Stay in the after attribute name state. */
+ $this->state = 'afterAttributeName';
+
+ } elseif($char === '=') {
+ /* U+003D EQUALS SIGN (=)
+ Switch to the before attribute value state. */
+ $this->state = 'beforeAttributeValue';
+
+ } elseif($char === '>') {
+ /* U+003E GREATER-THAN SIGN (>)
+ Emit the current tag token. Switch to the data state. */
+ $this->emitToken($this->token);
+ $this->state = 'data';
+
+ } elseif($char === '/' && $this->character($this->char + 1) !== '>') {
+ /* U+002F SOLIDUS (/)
+ Parse error unless this is a permitted slash. Switch to the
+ before attribute name state. */
+ $this->state = 'beforeAttributeName';
+
+ } elseif($this->char === $this->EOF) {
+ /* EOF
+ Parse error. Emit the current tag token. Reconsume the EOF
+ character in the data state. */
+ $this->emitToken($this->token);
+
+ $this->char--;
+ $this->state = 'data';
+
+ } else {
+ /* Anything else
+ Start a new attribute in the current tag token. Set that attribute's
+ name to the current input character, and its value to the empty string.
+ Switch to the attribute name state. */
+ $this->token['attr'][] = array(
+ 'name' => strtolower($char),
+ 'value' => null
+ );
+
+ $this->state = 'attributeName';
+ }
+ }
+
+ private function beforeAttributeValueState() {
+ // Consume the next input character:
+ $this->char++;
+ $char = $this->character($this->char);
+
+ if(preg_match('/^[\t\n\x0b\x0c ]$/', $char)) {
+ /* U+0009 CHARACTER TABULATION
+ U+000A LINE FEED (LF)
+ U+000B LINE TABULATION
+ U+000C FORM FEED (FF)
+ U+0020 SPACE
+ Stay in the before attribute value state. */
+ $this->state = 'beforeAttributeValue';
+
+ } elseif($char === '"') {
+ /* U+0022 QUOTATION MARK (")
+ Switch to the attribute value (double-quoted) state. */
+ $this->state = 'attributeValueDoubleQuoted';
+
+ } elseif($char === '&') {
+ /* U+0026 AMPERSAND (&)
+ Switch to the attribute value (unquoted) state and reconsume
+ this input character. */
+ $this->char--;
+ $this->state = 'attributeValueUnquoted';
+
+ } elseif($char === '\'') {
+ /* U+0027 APOSTROPHE (')
+ Switch to the attribute value (single-quoted) state. */
+ $this->state = 'attributeValueSingleQuoted';
+
+ } elseif($char === '>') {
+ /* U+003E GREATER-THAN SIGN (>)
+ Emit the current tag token. Switch to the data state. */
+ $this->emitToken($this->token);
+ $this->state = 'data';
+
+ } else {
+ /* Anything else
+ Append the current input character to the current attribute's value.
+ Switch to the attribute value (unquoted) state. */
+ $last = count($this->token['attr']) - 1;
+ $this->token['attr'][$last]['value'] .= $char;
+
+ $this->state = 'attributeValueUnquoted';
+ }
+ }
+
+ private function attributeValueDoubleQuotedState() {
+ // Consume the next input character:
+ $this->char++;
+ $char = $this->character($this->char);
+
+ if($char === '"') {
+ /* U+0022 QUOTATION MARK (")
+ Switch to the before attribute name state. */
+ $this->state = 'beforeAttributeName';
+
+ } elseif($char === '&') {
+ /* U+0026 AMPERSAND (&)
+ Switch to the entity in attribute value state. */
+ $this->entityInAttributeValueState('double');
+
+ } elseif($this->char === $this->EOF) {
+ /* EOF
+ Parse error. Emit the current tag token. Reconsume the character
+ in the data state. */
+ $this->emitToken($this->token);
+
+ $this->char--;
+ $this->state = 'data';
+
+ } else {
+ /* Anything else
+ Append the current input character to the current attribute's value.
+ Stay in the attribute value (double-quoted) state. */
+ $last = count($this->token['attr']) - 1;
+ $this->token['attr'][$last]['value'] .= $char;
+
+ $this->state = 'attributeValueDoubleQuoted';
+ }
+ }
+
+ private function attributeValueSingleQuotedState() {
+ // Consume the next input character:
+ $this->char++;
+ $char = $this->character($this->char);
+
+ if($char === '\'') {
+ /* U+0022 QUOTATION MARK (')
+ Switch to the before attribute name state. */
+ $this->state = 'beforeAttributeName';
+
+ } elseif($char === '&') {
+ /* U+0026 AMPERSAND (&)
+ Switch to the entity in attribute value state. */
+ $this->entityInAttributeValueState('single');
+
+ } elseif($this->char === $this->EOF) {
+ /* EOF
+ Parse error. Emit the current tag token. Reconsume the character
+ in the data state. */
+ $this->emitToken($this->token);
+
+ $this->char--;
+ $this->state = 'data';
+
+ } else {
+ /* Anything else
+ Append the current input character to the current attribute's value.
+ Stay in the attribute value (single-quoted) state. */
+ $last = count($this->token['attr']) - 1;
+ $this->token['attr'][$last]['value'] .= $char;
+
+ $this->state = 'attributeValueSingleQuoted';
+ }
+ }
+
+ private function attributeValueUnquotedState() {
+ // Consume the next input character:
+ $this->char++;
+ $char = $this->character($this->char);
+
+ if(preg_match('/^[\t\n\x0b\x0c ]$/', $char)) {
+ /* U+0009 CHARACTER TABULATION
+ U+000A LINE FEED (LF)
+ U+000B LINE TABULATION
+ U+000C FORM FEED (FF)
+ U+0020 SPACE
+ Switch to the before attribute name state. */
+ $this->state = 'beforeAttributeName';
+
+ } elseif($char === '&') {
+ /* U+0026 AMPERSAND (&)
+ Switch to the entity in attribute value state. */
+ $this->entityInAttributeValueState();
+
+ } elseif($char === '>') {
+ /* U+003E GREATER-THAN SIGN (>)
+ Emit the current tag token. Switch to the data state. */
+ $this->emitToken($this->token);
+ $this->state = 'data';
+
+ } else {
+ /* Anything else
+ Append the current input character to the current attribute's value.
+ Stay in the attribute value (unquoted) state. */
+ $last = count($this->token['attr']) - 1;
+ $this->token['attr'][$last]['value'] .= $char;
+
+ $this->state = 'attributeValueUnquoted';
+ }
+ }
+
+ private function entityInAttributeValueState() {
+ // Attempt to consume an entity.
+ $entity = $this->entity();
+
+ // If nothing is returned, append a U+0026 AMPERSAND character to the
+ // current attribute's value. Otherwise, emit the character token that
+ // was returned.
+ $char = (!$entity)
+ ? '&'
+ : $entity;
+
+ $last = count($this->token['attr']) - 1;
+ $this->token['attr'][$last]['value'] .= $char;
+ }
+
+ private function bogusCommentState() {
+ /* Consume every character up to the first U+003E GREATER-THAN SIGN
+ character (>) or the end of the file (EOF), whichever comes first. Emit
+ a comment token whose data is the concatenation of all the characters
+ starting from and including the character that caused the state machine
+ to switch into the bogus comment state, up to and including the last
+ consumed character before the U+003E character, if any, or up to the
+ end of the file otherwise. (If the comment was started by the end of
+ the file (EOF), the token is empty.) */
+ $data = $this->characters('^>', $this->char);
+ $this->emitToken(array(
+ 'data' => $data,
+ 'type' => self::COMMENT
+ ));
+
+ $this->char += strlen($data);
+
+ /* Switch to the data state. */
+ $this->state = 'data';
+
+ /* If the end of the file was reached, reconsume the EOF character. */
+ if($this->char === $this->EOF) {
+ $this->char = $this->EOF - 1;
+ }
+ }
+
+ private function markupDeclarationOpenState() {
+ /* If the next two characters are both U+002D HYPHEN-MINUS (-)
+ characters, consume those two characters, create a comment token whose
+ data is the empty string, and switch to the comment state. */
+ if($this->character($this->char + 1, 2) === '--') {
+ $this->char += 2;
+ $this->state = 'comment';
+ $this->token = array(
+ 'data' => null,
+ 'type' => self::COMMENT
+ );
+
+ /* Otherwise if the next seven chacacters are a case-insensitive match
+ for the word "DOCTYPE", then consume those characters and switch to the
+ DOCTYPE state. */
+ } elseif(strtolower($this->character($this->char + 1, 7)) === 'doctype') {
+ $this->char += 7;
+ $this->state = 'doctype';
+
+ /* Otherwise, is is a parse error. Switch to the bogus comment state.
+ The next character that is consumed, if any, is the first character
+ that will be in the comment. */
+ } else {
+ $this->char++;
+ $this->state = 'bogusComment';
+ }
+ }
+
+ private function commentState() {
+ /* Consume the next input character: */
+ $this->char++;
+ $char = $this->char();
+
+ /* U+002D HYPHEN-MINUS (-) */
+ if($char === '-') {
+ /* Switch to the comment dash state */
+ $this->state = 'commentDash';
+
+ /* EOF */
+ } elseif($this->char === $this->EOF) {
+ /* Parse error. Emit the comment token. Reconsume the EOF character
+ in the data state. */
+ $this->emitToken($this->token);
+ $this->char--;
+ $this->state = 'data';
+
+ /* Anything else */
+ } else {
+ /* Append the input character to the comment token's data. Stay in
+ the comment state. */
+ $this->token['data'] .= $char;
+ }
+ }
+
+ private function commentDashState() {
+ /* Consume the next input character: */
+ $this->char++;
+ $char = $this->char();
+
+ /* U+002D HYPHEN-MINUS (-) */
+ if($char === '-') {
+ /* Switch to the comment end state */
+ $this->state = 'commentEnd';
+
+ /* EOF */
+ } elseif($this->char === $this->EOF) {
+ /* Parse error. Emit the comment token. Reconsume the EOF character
+ in the data state. */
+ $this->emitToken($this->token);
+ $this->char--;
+ $this->state = 'data';
+
+ /* Anything else */
+ } else {
+ /* Append a U+002D HYPHEN-MINUS (-) character and the input
+ character to the comment token's data. Switch to the comment state. */
+ $this->token['data'] .= '-'.$char;
+ $this->state = 'comment';
+ }
+ }
+
+ private function commentEndState() {
+ /* Consume the next input character: */
+ $this->char++;
+ $char = $this->char();
+
+ if($char === '>') {
+ $this->emitToken($this->token);
+ $this->state = 'data';
+
+ } elseif($char === '-') {
+ $this->token['data'] .= '-';
+
+ } elseif($this->char === $this->EOF) {
+ $this->emitToken($this->token);
+ $this->char--;
+ $this->state = 'data';
+
+ } else {
+ $this->token['data'] .= '--'.$char;
+ $this->state = 'comment';
+ }
+ }
+
+ private function doctypeState() {
+ /* Consume the next input character: */
+ $this->char++;
+ $char = $this->char();
+
+ if(preg_match('/^[\t\n\x0b\x0c ]$/', $char)) {
+ $this->state = 'beforeDoctypeName';
+
+ } else {
+ $this->char--;
+ $this->state = 'beforeDoctypeName';
+ }
+ }
+
+ private function beforeDoctypeNameState() {
+ /* Consume the next input character: */
+ $this->char++;
+ $char = $this->char();
+
+ if(preg_match('/^[\t\n\x0b\x0c ]$/', $char)) {
+ // Stay in the before DOCTYPE name state.
+
+ } elseif(preg_match('/^[a-z]$/', $char)) {
+ $this->token = array(
+ 'name' => strtoupper($char),
+ 'type' => self::DOCTYPE,
+ 'error' => true
+ );
+
+ $this->state = 'doctypeName';
+
+ } elseif($char === '>') {
+ $this->emitToken(array(
+ 'name' => null,
+ 'type' => self::DOCTYPE,
+ 'error' => true
+ ));
+
+ $this->state = 'data';
+
+ } elseif($this->char === $this->EOF) {
+ $this->emitToken(array(
+ 'name' => null,
+ 'type' => self::DOCTYPE,
+ 'error' => true
+ ));
+
+ $this->char--;
+ $this->state = 'data';
+
+ } else {
+ $this->token = array(
+ 'name' => $char,
+ 'type' => self::DOCTYPE,
+ 'error' => true
+ );
+
+ $this->state = 'doctypeName';
+ }
+ }
+
+ private function doctypeNameState() {
+ /* Consume the next input character: */
+ $this->char++;
+ $char = $this->char();
+
+ if(preg_match('/^[\t\n\x0b\x0c ]$/', $char)) {
+ $this->state = 'AfterDoctypeName';
+
+ } elseif($char === '>') {
+ $this->emitToken($this->token);
+ $this->state = 'data';
+
+ } elseif(preg_match('/^[a-z]$/', $char)) {
+ $this->token['name'] .= strtoupper($char);
+
+ } elseif($this->char === $this->EOF) {
+ $this->emitToken($this->token);
+ $this->char--;
+ $this->state = 'data';
+
+ } else {
+ $this->token['name'] .= $char;
+ }
+
+ $this->token['error'] = ($this->token['name'] === 'HTML')
+ ? false
+ : true;
+ }
+
+ private function afterDoctypeNameState() {
+ /* Consume the next input character: */
+ $this->char++;
+ $char = $this->char();
+
+ if(preg_match('/^[\t\n\x0b\x0c ]$/', $char)) {
+ // Stay in the DOCTYPE name state.
+
+ } elseif($char === '>') {
+ $this->emitToken($this->token);
+ $this->state = 'data';
+
+ } elseif($this->char === $this->EOF) {
+ $this->emitToken($this->token);
+ $this->char--;
+ $this->state = 'data';
+
+ } else {
+ $this->token['error'] = true;
+ $this->state = 'bogusDoctype';
+ }
+ }
+
+ private function bogusDoctypeState() {
+ /* Consume the next input character: */
+ $this->char++;
+ $char = $this->char();
+
+ if($char === '>') {
+ $this->emitToken($this->token);
+ $this->state = 'data';
+
+ } elseif($this->char === $this->EOF) {
+ $this->emitToken($this->token);
+ $this->char--;
+ $this->state = 'data';
+
+ } else {
+ // Stay in the bogus DOCTYPE state.
+ }
+ }
+
+ private function entity() {
+ $start = $this->char;
+
+ // This section defines how to consume an entity. This definition is
+ // used when parsing entities in text and in attributes.
+
+ // The behaviour depends on the identity of the next character (the
+ // one immediately after the U+0026 AMPERSAND character):
+
+ switch($this->character($this->char + 1)) {
+ // U+0023 NUMBER SIGN (#)
+ case '#':
+
+ // The behaviour further depends on the character after the
+ // U+0023 NUMBER SIGN:
+ switch($this->character($this->char + 1)) {
+ // U+0078 LATIN SMALL LETTER X
+ // U+0058 LATIN CAPITAL LETTER X
+ case 'x':
+ case 'X':
+ // Follow the steps below, but using the range of
+ // characters U+0030 DIGIT ZERO through to U+0039 DIGIT
+ // NINE, U+0061 LATIN SMALL LETTER A through to U+0066
+ // LATIN SMALL LETTER F, and U+0041 LATIN CAPITAL LETTER
+ // A, through to U+0046 LATIN CAPITAL LETTER F (in other
+ // words, 0-9, A-F, a-f).
+ $char = 1;
+ $char_class = '0-9A-Fa-f';
+ break;
+
+ // Anything else
+ default:
+ // Follow the steps below, but using the range of
+ // characters U+0030 DIGIT ZERO through to U+0039 DIGIT
+ // NINE (i.e. just 0-9).
+ $char = 0;
+ $char_class = '0-9';
+ break;
+ }
+
+ // Consume as many characters as match the range of characters
+ // given above.
+ $this->char++;
+ $e_name = $this->characters($char_class, $this->char + $char + 1);
+ $entity = $this->character($start, $this->char);
+ $cond = strlen($e_name) > 0;
+
+ // The rest of the parsing happens bellow.
+ break;
+
+ // Anything else
+ default:
+ // Consume the maximum number of characters possible, with the
+ // consumed characters case-sensitively matching one of the
+ // identifiers in the first column of the entities table.
+ $e_name = $this->characters('0-9A-Za-z;', $this->char + 1);
+ $len = strlen($e_name);
+
+ for($c = 1; $c <= $len; $c++) {
+ $id = substr($e_name, 0, $c);
+ $this->char++;
+
+ if(in_array($id, $this->entities)) {
+ if ($e_name[$c-1] !== ';') {
+ if ($c < $len && $e_name[$c] == ';') {
+ $this->char++; // consume extra semicolon
+ }
+ }
+ $entity = $id;
+ break;
+ }
+ }
+
+ $cond = isset($entity);
+ // The rest of the parsing happens bellow.
+ break;
+ }
+
+ if(!$cond) {
+ // If no match can be made, then this is a parse error. No
+ // characters are consumed, and nothing is returned.
+ $this->char = $start;
+ return false;
+ }
+
+ // Return a character token for the character corresponding to the
+ // entity name (as given by the second column of the entities table).
+ return html_entity_decode('&'.$entity.';', ENT_QUOTES, 'UTF-8');
+ }
+
+ private function emitToken($token) {
+ $emit = $this->tree->emitToken($token);
+
+ if(is_int($emit)) {
+ $this->content_model = $emit;
+
+ } elseif($token['type'] === self::ENDTAG) {
+ $this->content_model = self::PCDATA;
+ }
+ }
+
+ private function EOF() {
+ $this->state = null;
+ $this->tree->emitToken(array(
+ 'type' => self::EOF
+ ));
+ }
+}
+
+class HTML5TreeConstructer {
+ public $stack = array();
+
+ private $phase;
+ private $mode;
+ private $dom;
+ private $foster_parent = null;
+ private $a_formatting = array();
+
+ private $head_pointer = null;
+ private $form_pointer = null;
+
+ private $scoping = array('button','caption','html','marquee','object','table','td','th');
+ private $formatting = array('a','b','big','em','font','i','nobr','s','small','strike','strong','tt','u');
+ private $special = array('address','area','base','basefont','bgsound',
+ 'blockquote','body','br','center','col','colgroup','dd','dir','div','dl',
+ 'dt','embed','fieldset','form','frame','frameset','h1','h2','h3','h4','h5',
+ 'h6','head','hr','iframe','image','img','input','isindex','li','link',
+ 'listing','menu','meta','noembed','noframes','noscript','ol','optgroup',
+ 'option','p','param','plaintext','pre','script','select','spacer','style',
+ 'tbody','textarea','tfoot','thead','title','tr','ul','wbr');
+
+ // The different phases.
+ const INIT_PHASE = 0;
+ const ROOT_PHASE = 1;
+ const MAIN_PHASE = 2;
+ const END_PHASE = 3;
+
+ // The different insertion modes for the main phase.
+ const BEFOR_HEAD = 0;
+ const IN_HEAD = 1;
+ const AFTER_HEAD = 2;
+ const IN_BODY = 3;
+ const IN_TABLE = 4;
+ const IN_CAPTION = 5;
+ const IN_CGROUP = 6;
+ const IN_TBODY = 7;
+ const IN_ROW = 8;
+ const IN_CELL = 9;
+ const IN_SELECT = 10;
+ const AFTER_BODY = 11;
+ const IN_FRAME = 12;
+ const AFTR_FRAME = 13;
+
+ // The different types of elements.
+ const SPECIAL = 0;
+ const SCOPING = 1;
+ const FORMATTING = 2;
+ const PHRASING = 3;
+
+ const MARKER = 0;
+
+ public function __construct() {
+ $this->phase = self::INIT_PHASE;
+ $this->mode = self::BEFOR_HEAD;
+ $this->dom = new DOMDocument;
+
+ $this->dom->encoding = 'UTF-8';
+ $this->dom->preserveWhiteSpace = true;
+ $this->dom->substituteEntities = true;
+ $this->dom->strictErrorChecking = false;
+ }
+
+ // Process tag tokens
+ public function emitToken($token) {
+ switch($this->phase) {
+ case self::INIT_PHASE: return $this->initPhase($token); break;
+ case self::ROOT_PHASE: return $this->rootElementPhase($token); break;
+ case self::MAIN_PHASE: return $this->mainPhase($token); break;
+ case self::END_PHASE : return $this->trailingEndPhase($token); break;
+ }
+ }
+
+ private function initPhase($token) {
+ /* Initially, the tree construction stage must handle each token
+ emitted from the tokenisation stage as follows: */
+
+ /* A DOCTYPE token that is marked as being in error
+ A comment token
+ A start tag token
+ An end tag token
+ A character token that is not one of one of U+0009 CHARACTER TABULATION,
+ U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF),
+ or U+0020 SPACE
+ An end-of-file token */
+ if((isset($token['error']) && $token['error']) ||
+ $token['type'] === HTML5::COMMENT ||
+ $token['type'] === HTML5::STARTTAG ||
+ $token['type'] === HTML5::ENDTAG ||
+ $token['type'] === HTML5::EOF ||
+ ($token['type'] === HTML5::CHARACTR && isset($token['data']) &&
+ !preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data']))) {
+ /* This specification does not define how to handle this case. In
+ particular, user agents may ignore the entirety of this specification
+ altogether for such documents, and instead invoke special parse modes
+ with a greater emphasis on backwards compatibility. */
+
+ $this->phase = self::ROOT_PHASE;
+ return $this->rootElementPhase($token);
+
+ /* A DOCTYPE token marked as being correct */
+ } elseif(isset($token['error']) && !$token['error']) {
+ /* Append a DocumentType node to the Document node, with the name
+ attribute set to the name given in the DOCTYPE token (which will be
+ "HTML"), and the other attributes specific to DocumentType objects
+ set to null, empty lists, or the empty string as appropriate. */
+ $doctype = new DOMDocumentType(null, null, 'HTML');
+
+ /* Then, switch to the root element phase of the tree construction
+ stage. */
+ $this->phase = self::ROOT_PHASE;
+
+ /* A character token that is one of one of U+0009 CHARACTER TABULATION,
+ U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF),
+ or U+0020 SPACE */
+ } elseif(isset($token['data']) && preg_match('/^[\t\n\x0b\x0c ]+$/',
+ $token['data'])) {
+ /* Append that character to the Document node. */
+ $text = $this->dom->createTextNode($token['data']);
+ $this->dom->appendChild($text);
+ }
+ }
+
+ private function rootElementPhase($token) {
+ /* After the initial phase, as each token is emitted from the tokenisation
+ stage, it must be processed as described in this section. */
+
+ /* A DOCTYPE token */
+ if($token['type'] === HTML5::DOCTYPE) {
+ // Parse error. Ignore the token.
+
+ /* A comment token */
+ } elseif($token['type'] === HTML5::COMMENT) {
+ /* Append a Comment node to the Document object with the data
+ attribute set to the data given in the comment token. */
+ $comment = $this->dom->createComment($token['data']);
+ $this->dom->appendChild($comment);
+
+ /* A character token that is one of one of U+0009 CHARACTER TABULATION,
+ U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF),
+ or U+0020 SPACE */
+ } elseif($token['type'] === HTML5::CHARACTR &&
+ preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) {
+ /* Append that character to the Document node. */
+ $text = $this->dom->createTextNode($token['data']);
+ $this->dom->appendChild($text);
+
+ /* A character token that is not one of U+0009 CHARACTER TABULATION,
+ U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED
+ (FF), or U+0020 SPACE
+ A start tag token
+ An end tag token
+ An end-of-file token */
+ } elseif(($token['type'] === HTML5::CHARACTR &&
+ !preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) ||
+ $token['type'] === HTML5::STARTTAG ||
+ $token['type'] === HTML5::ENDTAG ||
+ $token['type'] === HTML5::EOF) {
+ /* Create an HTMLElement node with the tag name html, in the HTML
+ namespace. Append it to the Document object. Switch to the main
+ phase and reprocess the current token. */
+ $html = $this->dom->createElement('html');
+ $this->dom->appendChild($html);
+ $this->stack[] = $html;
+
+ $this->phase = self::MAIN_PHASE;
+ return $this->mainPhase($token);
+ }
+ }
+
+ private function mainPhase($token) {
+ /* Tokens in the main phase must be handled as follows: */
+
+ /* A DOCTYPE token */
+ if($token['type'] === HTML5::DOCTYPE) {
+ // Parse error. Ignore the token.
+
+ /* A start tag token with the tag name "html" */
+ } elseif($token['type'] === HTML5::STARTTAG && $token['name'] === 'html') {
+ /* If this start tag token was not the first start tag token, then
+ it is a parse error. */
+
+ /* For each attribute on the token, check to see if the attribute
+ is already present on the top element of the stack of open elements.
+ If it is not, add the attribute and its corresponding value to that
+ element. */
+ foreach($token['attr'] as $attr) {
+ if(!$this->stack[0]->hasAttribute($attr['name'])) {
+ $this->stack[0]->setAttribute($attr['name'], $attr['value']);
+ }
+ }
+
+ /* An end-of-file token */
+ } elseif($token['type'] === HTML5::EOF) {
+ /* Generate implied end tags. */
+ $this->generateImpliedEndTags();
+
+ /* Anything else. */
+ } else {
+ /* Depends on the insertion mode: */
+ switch($this->mode) {
+ case self::BEFOR_HEAD: return $this->beforeHead($token); break;
+ case self::IN_HEAD: return $this->inHead($token); break;
+ case self::AFTER_HEAD: return $this->afterHead($token); break;
+ case self::IN_BODY: return $this->inBody($token); break;
+ case self::IN_TABLE: return $this->inTable($token); break;
+ case self::IN_CAPTION: return $this->inCaption($token); break;
+ case self::IN_CGROUP: return $this->inColumnGroup($token); break;
+ case self::IN_TBODY: return $this->inTableBody($token); break;
+ case self::IN_ROW: return $this->inRow($token); break;
+ case self::IN_CELL: return $this->inCell($token); break;
+ case self::IN_SELECT: return $this->inSelect($token); break;
+ case self::AFTER_BODY: return $this->afterBody($token); break;
+ case self::IN_FRAME: return $this->inFrameset($token); break;
+ case self::AFTR_FRAME: return $this->afterFrameset($token); break;
+ case self::END_PHASE: return $this->trailingEndPhase($token); break;
+ }
+ }
+ }
+
+ private function beforeHead($token) {
+ /* Handle the token as follows: */
+
+ /* A character token that is one of one of U+0009 CHARACTER TABULATION,
+ U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF),
+ or U+0020 SPACE */
+ if($token['type'] === HTML5::CHARACTR &&
+ preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) {
+ /* Append the character to the current node. */
+ $this->insertText($token['data']);
+
+ /* A comment token */
+ } elseif($token['type'] === HTML5::COMMENT) {
+ /* Append a Comment node to the current node with the data attribute
+ set to the data given in the comment token. */
+ $this->insertComment($token['data']);
+
+ /* A start tag token with the tag name "head" */
+ } elseif($token['type'] === HTML5::STARTTAG && $token['name'] === 'head') {
+ /* Create an element for the token, append the new element to the
+ current node and push it onto the stack of open elements. */
+ $element = $this->insertElement($token);
+
+ /* Set the head element pointer to this new element node. */
+ $this->head_pointer = $element;
+
+ /* Change the insertion mode to "in head". */
+ $this->mode = self::IN_HEAD;
+
+ /* A start tag token whose tag name is one of: "base", "link", "meta",
+ "script", "style", "title". Or an end tag with the tag name "html".
+ Or a character token that is not one of U+0009 CHARACTER TABULATION,
+ U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF),
+ or U+0020 SPACE. Or any other start tag token */
+ } elseif($token['type'] === HTML5::STARTTAG ||
+ ($token['type'] === HTML5::ENDTAG && $token['name'] === 'html') ||
+ ($token['type'] === HTML5::CHARACTR && !preg_match('/^[\t\n\x0b\x0c ]$/',
+ $token['data']))) {
+ /* Act as if a start tag token with the tag name "head" and no
+ attributes had been seen, then reprocess the current token. */
+ $this->beforeHead(array(
+ 'name' => 'head',
+ 'type' => HTML5::STARTTAG,
+ 'attr' => array()
+ ));
+
+ return $this->inHead($token);
+
+ /* Any other end tag */
+ } elseif($token['type'] === HTML5::ENDTAG) {
+ /* Parse error. Ignore the token. */
+ }
+ }
+
+ private function inHead($token) {
+ /* Handle the token as follows: */
+
+ /* A character token that is one of one of U+0009 CHARACTER TABULATION,
+ U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF),
+ or U+0020 SPACE.
+
+ THIS DIFFERS FROM THE SPEC: If the current node is either a title, style
+ or script element, append the character to the current node regardless
+ of its content. */
+ if(($token['type'] === HTML5::CHARACTR &&
+ preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) || (
+ $token['type'] === HTML5::CHARACTR && in_array(end($this->stack)->nodeName,
+ array('title', 'style', 'script')))) {
+ /* Append the character to the current node. */
+ $this->insertText($token['data']);
+
+ /* A comment token */
+ } elseif($token['type'] === HTML5::COMMENT) {
+ /* Append a Comment node to the current node with the data attribute
+ set to the data given in the comment token. */
+ $this->insertComment($token['data']);
+
+ } elseif($token['type'] === HTML5::ENDTAG &&
+ in_array($token['name'], array('title', 'style', 'script'))) {
+ array_pop($this->stack);
+ return HTML5::PCDATA;
+
+ /* A start tag with the tag name "title" */
+ } elseif($token['type'] === HTML5::STARTTAG && $token['name'] === 'title') {
+ /* Create an element for the token and append the new element to the
+ node pointed to by the head element pointer, or, if that is null
+ (innerHTML case), to the current node. */
+ if($this->head_pointer !== null) {
+ $element = $this->insertElement($token, false);
+ $this->head_pointer->appendChild($element);
+
+ } else {
+ $element = $this->insertElement($token);
+ }
+
+ /* Switch the tokeniser's content model flag to the RCDATA state. */
+ return HTML5::RCDATA;
+
+ /* A start tag with the tag name "style" */
+ } elseif($token['type'] === HTML5::STARTTAG && $token['name'] === 'style') {
+ /* Create an element for the token and append the new element to the
+ node pointed to by the head element pointer, or, if that is null
+ (innerHTML case), to the current node. */
+ if($this->head_pointer !== null) {
+ $element = $this->insertElement($token, false);
+ $this->head_pointer->appendChild($element);
+
+ } else {
+ $this->insertElement($token);
+ }
+
+ /* Switch the tokeniser's content model flag to the CDATA state. */
+ return HTML5::CDATA;
+
+ /* A start tag with the tag name "script" */
+ } elseif($token['type'] === HTML5::STARTTAG && $token['name'] === 'script') {
+ /* Create an element for the token. */
+ $element = $this->insertElement($token, false);
+ $this->head_pointer->appendChild($element);
+
+ /* Switch the tokeniser's content model flag to the CDATA state. */
+ return HTML5::CDATA;
+
+ /* A start tag with the tag name "base", "link", or "meta" */
+ } elseif($token['type'] === HTML5::STARTTAG && in_array($token['name'],
+ array('base', 'link', 'meta'))) {
+ /* Create an element for the token and append the new element to the
+ node pointed to by the head element pointer, or, if that is null
+ (innerHTML case), to the current node. */
+ if($this->head_pointer !== null) {
+ $element = $this->insertElement($token, false);
+ $this->head_pointer->appendChild($element);
+ array_pop($this->stack);
+
+ } else {
+ $this->insertElement($token);
+ }
+
+ /* An end tag with the tag name "head" */
+ } elseif($token['type'] === HTML5::ENDTAG && $token['name'] === 'head') {
+ /* If the current node is a head element, pop the current node off
+ the stack of open elements. */
+ if($this->head_pointer->isSameNode(end($this->stack))) {
+ array_pop($this->stack);
+
+ /* Otherwise, this is a parse error. */
+ } else {
+ // k
+ }
+
+ /* Change the insertion mode to "after head". */
+ $this->mode = self::AFTER_HEAD;
+
+ /* A start tag with the tag name "head" or an end tag except "html". */
+ } elseif(($token['type'] === HTML5::STARTTAG && $token['name'] === 'head') ||
+ ($token['type'] === HTML5::ENDTAG && $token['name'] !== 'html')) {
+ // Parse error. Ignore the token.
+
+ /* Anything else */
+ } else {
+ /* If the current node is a head element, act as if an end tag
+ token with the tag name "head" had been seen. */
+ if($this->head_pointer->isSameNode(end($this->stack))) {
+ $this->inHead(array(
+ 'name' => 'head',
+ 'type' => HTML5::ENDTAG
+ ));
+
+ /* Otherwise, change the insertion mode to "after head". */
+ } else {
+ $this->mode = self::AFTER_HEAD;
+ }
+
+ /* Then, reprocess the current token. */
+ return $this->afterHead($token);
+ }
+ }
+
+ private function afterHead($token) {
+ /* Handle the token as follows: */
+
+ /* A character token that is one of one of U+0009 CHARACTER TABULATION,
+ U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF),
+ or U+0020 SPACE */
+ if($token['type'] === HTML5::CHARACTR &&
+ preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) {
+ /* Append the character to the current node. */
+ $this->insertText($token['data']);
+
+ /* A comment token */
+ } elseif($token['type'] === HTML5::COMMENT) {
+ /* Append a Comment node to the current node with the data attribute
+ set to the data given in the comment token. */
+ $this->insertComment($token['data']);
+
+ /* A start tag token with the tag name "body" */
+ } elseif($token['type'] === HTML5::STARTTAG && $token['name'] === 'body') {
+ /* Insert a body element for the token. */
+ $this->insertElement($token);
+
+ /* Change the insertion mode to "in body". */
+ $this->mode = self::IN_BODY;
+
+ /* A start tag token with the tag name "frameset" */
+ } elseif($token['type'] === HTML5::STARTTAG && $token['name'] === 'frameset') {
+ /* Insert a frameset element for the token. */
+ $this->insertElement($token);
+
+ /* Change the insertion mode to "in frameset". */
+ $this->mode = self::IN_FRAME;
+
+ /* A start tag token whose tag name is one of: "base", "link", "meta",
+ "script", "style", "title" */
+ } elseif($token['type'] === HTML5::STARTTAG && in_array($token['name'],
+ array('base', 'link', 'meta', 'script', 'style', 'title'))) {
+ /* Parse error. Switch the insertion mode back to "in head" and
+ reprocess the token. */
+ $this->mode = self::IN_HEAD;
+ return $this->inHead($token);
+
+ /* Anything else */
+ } else {
+ /* Act as if a start tag token with the tag name "body" and no
+ attributes had been seen, and then reprocess the current token. */
+ $this->afterHead(array(
+ 'name' => 'body',
+ 'type' => HTML5::STARTTAG,
+ 'attr' => array()
+ ));
+
+ return $this->inBody($token);
+ }
+ }
+
+ private function inBody($token) {
+ /* Handle the token as follows: */
+
+ switch($token['type']) {
+ /* A character token */
+ case HTML5::CHARACTR:
+ /* Reconstruct the active formatting elements, if any. */
+ $this->reconstructActiveFormattingElements();
+
+ /* Append the token's character to the current node. */
+ $this->insertText($token['data']);
+ break;
+
+ /* A comment token */
+ case HTML5::COMMENT:
+ /* Append a Comment node to the current node with the data
+ attribute set to the data given in the comment token. */
+ $this->insertComment($token['data']);
+ break;
+
+ case HTML5::STARTTAG:
+ switch($token['name']) {
+ /* A start tag token whose tag name is one of: "script",
+ "style" */
+ case 'script': case 'style':
+ /* Process the token as if the insertion mode had been "in
+ head". */
+ return $this->inHead($token);
+ break;
+
+ /* A start tag token whose tag name is one of: "base", "link",
+ "meta", "title" */
+ case 'base': case 'link': case 'meta': case 'title':
+ /* Parse error. Process the token as if the insertion mode
+ had been "in head". */
+ return $this->inHead($token);
+ break;
+
+ /* A start tag token with the tag name "body" */
+ case 'body':
+ /* Parse error. If the second element on the stack of open
+ elements is not a body element, or, if the stack of open
+ elements has only one node on it, then ignore the token.
+ (innerHTML case) */
+ if(count($this->stack) === 1 || $this->stack[1]->nodeName !== 'body') {
+ // Ignore
+
+ /* Otherwise, for each attribute on the token, check to see
+ if the attribute is already present on the body element (the
+ second element) on the stack of open elements. If it is not,
+ add the attribute and its corresponding value to that
+ element. */
+ } else {
+ foreach($token['attr'] as $attr) {
+ if(!$this->stack[1]->hasAttribute($attr['name'])) {
+ $this->stack[1]->setAttribute($attr['name'], $attr['value']);
+ }
+ }
+ }
+ break;
+
+ /* A start tag whose tag name is one of: "address",
+ "blockquote", "center", "dir", "div", "dl", "fieldset",
+ "listing", "menu", "ol", "p", "ul" */
+ case 'address': case 'blockquote': case 'center': case 'dir':
+ case 'div': case 'dl': case 'fieldset': case 'listing':
+ case 'menu': case 'ol': case 'p': case 'ul':
+ /* If the stack of open elements has a p element in scope,
+ then act as if an end tag with the tag name p had been
+ seen. */
+ if($this->elementInScope('p')) {
+ $this->emitToken(array(
+ 'name' => 'p',
+ 'type' => HTML5::ENDTAG
+ ));
+ }
+
+ /* Insert an HTML element for the token. */
+ $this->insertElement($token);
+ break;
+
+ /* A start tag whose tag name is "form" */
+ case 'form':
+ /* If the form element pointer is not null, ignore the
+ token with a parse error. */
+ if($this->form_pointer !== null) {
+ // Ignore.
+
+ /* Otherwise: */
+ } else {
+ /* If the stack of open elements has a p element in
+ scope, then act as if an end tag with the tag name p
+ had been seen. */
+ if($this->elementInScope('p')) {
+ $this->emitToken(array(
+ 'name' => 'p',
+ 'type' => HTML5::ENDTAG
+ ));
+ }
+
+ /* Insert an HTML element for the token, and set the
+ form element pointer to point to the element created. */
+ $element = $this->insertElement($token);
+ $this->form_pointer = $element;
+ }
+ break;
+
+ /* A start tag whose tag name is "li", "dd" or "dt" */
+ case 'li': case 'dd': case 'dt':
+ /* If the stack of open elements has a p element in scope,
+ then act as if an end tag with the tag name p had been
+ seen. */
+ if($this->elementInScope('p')) {
+ $this->emitToken(array(
+ 'name' => 'p',
+ 'type' => HTML5::ENDTAG
+ ));
+ }
+
+ $stack_length = count($this->stack) - 1;
+
+ for($n = $stack_length; 0 <= $n; $n--) {
+ /* 1. Initialise node to be the current node (the
+ bottommost node of the stack). */
+ $stop = false;
+ $node = $this->stack[$n];
+ $cat = $this->getElementCategory($node->tagName);
+
+ /* 2. If node is an li, dd or dt element, then pop all
+ the nodes from the current node up to node, including
+ node, then stop this algorithm. */
+ if($token['name'] === $node->tagName || ($token['name'] !== 'li'
+ && ($node->tagName === 'dd' || $node->tagName === 'dt'))) {
+ for($x = $stack_length; $x >= $n ; $x--) {
+ array_pop($this->stack);
+ }
+
+ break;
+ }
+
+ /* 3. If node is not in the formatting category, and is
+ not in the phrasing category, and is not an address or
+ div element, then stop this algorithm. */
+ if($cat !== self::FORMATTING && $cat !== self::PHRASING &&
+ $node->tagName !== 'address' && $node->tagName !== 'div') {
+ break;
+ }
+ }
+
+ /* Finally, insert an HTML element with the same tag
+ name as the token's. */
+ $this->insertElement($token);
+ break;
+
+ /* A start tag token whose tag name is "plaintext" */
+ case 'plaintext':
+ /* If the stack of open elements has a p element in scope,
+ then act as if an end tag with the tag name p had been
+ seen. */
+ if($this->elementInScope('p')) {
+ $this->emitToken(array(
+ 'name' => 'p',
+ 'type' => HTML5::ENDTAG
+ ));
+ }
+
+ /* Insert an HTML element for the token. */
+ $this->insertElement($token);
+
+ return HTML5::PLAINTEXT;
+ break;
+
+ /* A start tag whose tag name is one of: "h1", "h2", "h3", "h4",
+ "h5", "h6" */
+ case 'h1': case 'h2': case 'h3': case 'h4': case 'h5': case 'h6':
+ /* If the stack of open elements has a p element in scope,
+ then act as if an end tag with the tag name p had been seen. */
+ if($this->elementInScope('p')) {
+ $this->emitToken(array(
+ 'name' => 'p',
+ 'type' => HTML5::ENDTAG
+ ));
+ }
+
+ /* If the stack of open elements has in scope an element whose
+ tag name is one of "h1", "h2", "h3", "h4", "h5", or "h6", then
+ this is a parse error; pop elements from the stack until an
+ element with one of those tag names has been popped from the
+ stack. */
+ while($this->elementInScope(array('h1', 'h2', 'h3', 'h4', 'h5', 'h6'))) {
+ array_pop($this->stack);
+ }
+
+ /* Insert an HTML element for the token. */
+ $this->insertElement($token);
+ break;
+
+ /* A start tag whose tag name is "a" */
+ case 'a':
+ /* If the list of active formatting elements contains
+ an element whose tag name is "a" between the end of the
+ list and the last marker on the list (or the start of
+ the list if there is no marker on the list), then this
+ is a parse error; act as if an end tag with the tag name
+ "a" had been seen, then remove that element from the list
+ of active formatting elements and the stack of open
+ elements if the end tag didn't already remove it (it
+ might not have if the element is not in table scope). */
+ $leng = count($this->a_formatting);
+
+ for($n = $leng - 1; $n >= 0; $n--) {
+ if($this->a_formatting[$n] === self::MARKER) {
+ break;
+
+ } elseif($this->a_formatting[$n]->nodeName === 'a') {
+ $this->emitToken(array(
+ 'name' => 'a',
+ 'type' => HTML5::ENDTAG
+ ));
+ break;
+ }
+ }
+
+ /* Reconstruct the active formatting elements, if any. */
+ $this->reconstructActiveFormattingElements();
+
+ /* Insert an HTML element for the token. */
+ $el = $this->insertElement($token);
+
+ /* Add that element to the list of active formatting
+ elements. */
+ $this->a_formatting[] = $el;
+ break;
+
+ /* A start tag whose tag name is one of: "b", "big", "em", "font",
+ "i", "nobr", "s", "small", "strike", "strong", "tt", "u" */
+ case 'b': case 'big': case 'em': case 'font': case 'i':
+ case 'nobr': case 's': case 'small': case 'strike':
+ case 'strong': case 'tt': case 'u':
+ /* Reconstruct the active formatting elements, if any. */
+ $this->reconstructActiveFormattingElements();
+
+ /* Insert an HTML element for the token. */
+ $el = $this->insertElement($token);
+
+ /* Add that element to the list of active formatting
+ elements. */
+ $this->a_formatting[] = $el;
+ break;
+
+ /* A start tag token whose tag name is "button" */
+ case 'button':
+ /* If the stack of open elements has a button element in scope,
+ then this is a parse error; act as if an end tag with the tag
+ name "button" had been seen, then reprocess the token. (We don't
+ do that. Unnecessary.) */
+ if($this->elementInScope('button')) {
+ $this->inBody(array(
+ 'name' => 'button',
+ 'type' => HTML5::ENDTAG
+ ));
+ }
+
+ /* Reconstruct the active formatting elements, if any. */
+ $this->reconstructActiveFormattingElements();
+
+ /* Insert an HTML element for the token. */
+ $this->insertElement($token);
+
+ /* Insert a marker at the end of the list of active
+ formatting elements. */
+ $this->a_formatting[] = self::MARKER;
+ break;
+
+ /* A start tag token whose tag name is one of: "marquee", "object" */
+ case 'marquee': case 'object':
+ /* Reconstruct the active formatting elements, if any. */
+ $this->reconstructActiveFormattingElements();
+
+ /* Insert an HTML element for the token. */
+ $this->insertElement($token);
+
+ /* Insert a marker at the end of the list of active
+ formatting elements. */
+ $this->a_formatting[] = self::MARKER;
+ break;
+
+ /* A start tag token whose tag name is "xmp" */
+ case 'xmp':
+ /* Reconstruct the active formatting elements, if any. */
+ $this->reconstructActiveFormattingElements();
+
+ /* Insert an HTML element for the token. */
+ $this->insertElement($token);
+
+ /* Switch the content model flag to the CDATA state. */
+ return HTML5::CDATA;
+ break;
+
+ /* A start tag whose tag name is "table" */
+ case 'table':
+ /* If the stack of open elements has a p element in scope,
+ then act as if an end tag with the tag name p had been seen. */
+ if($this->elementInScope('p')) {
+ $this->emitToken(array(
+ 'name' => 'p',
+ 'type' => HTML5::ENDTAG
+ ));
+ }
+
+ /* Insert an HTML element for the token. */
+ $this->insertElement($token);
+
+ /* Change the insertion mode to "in table". */
+ $this->mode = self::IN_TABLE;
+ break;
+
+ /* A start tag whose tag name is one of: "area", "basefont",
+ "bgsound", "br", "embed", "img", "param", "spacer", "wbr" */
+ case 'area': case 'basefont': case 'bgsound': case 'br':
+ case 'embed': case 'img': case 'param': case 'spacer':
+ case 'wbr':
+ /* Reconstruct the active formatting elements, if any. */
+ $this->reconstructActiveFormattingElements();
+
+ /* Insert an HTML element for the token. */
+ $this->insertElement($token);
+
+ /* Immediately pop the current node off the stack of open elements. */
+ array_pop($this->stack);
+ break;
+
+ /* A start tag whose tag name is "hr" */
+ case 'hr':
+ /* If the stack of open elements has a p element in scope,
+ then act as if an end tag with the tag name p had been seen. */
+ if($this->elementInScope('p')) {
+ $this->emitToken(array(
+ 'name' => 'p',
+ 'type' => HTML5::ENDTAG
+ ));
+ }
+
+ /* Insert an HTML element for the token. */
+ $this->insertElement($token);
+
+ /* Immediately pop the current node off the stack of open elements. */
+ array_pop($this->stack);
+ break;
+
+ /* A start tag whose tag name is "image" */
+ case 'image':
+ /* Parse error. Change the token's tag name to "img" and
+ reprocess it. (Don't ask.) */
+ $token['name'] = 'img';
+ return $this->inBody($token);
+ break;
+
+ /* A start tag whose tag name is "input" */
+ case 'input':
+ /* Reconstruct the active formatting elements, if any. */
+ $this->reconstructActiveFormattingElements();
+
+ /* Insert an input element for the token. */
+ $element = $this->insertElement($token, false);
+
+ /* If the form element pointer is not null, then associate the
+ input element with the form element pointed to by the form
+ element pointer. */
+ $this->form_pointer !== null
+ ? $this->form_pointer->appendChild($element)
+ : end($this->stack)->appendChild($element);
+
+ /* Pop that input element off the stack of open elements. */
+ array_pop($this->stack);
+ break;
+
+ /* A start tag whose tag name is "isindex" */
+ case 'isindex':
+ /* Parse error. */
+ // w/e
+
+ /* If the form element pointer is not null,
+ then ignore the token. */
+ if($this->form_pointer === null) {
+ /* Act as if a start tag token with the tag name "form" had
+ been seen. */
+ $this->inBody(array(
+ 'name' => 'body',
+ 'type' => HTML5::STARTTAG,
+ 'attr' => array()
+ ));
+
+ /* Act as if a start tag token with the tag name "hr" had
+ been seen. */
+ $this->inBody(array(
+ 'name' => 'hr',
+ 'type' => HTML5::STARTTAG,
+ 'attr' => array()
+ ));
+
+ /* Act as if a start tag token with the tag name "p" had
+ been seen. */
+ $this->inBody(array(
+ 'name' => 'p',
+ 'type' => HTML5::STARTTAG,
+ 'attr' => array()
+ ));
+
+ /* Act as if a start tag token with the tag name "label"
+ had been seen. */
+ $this->inBody(array(
+ 'name' => 'label',
+ 'type' => HTML5::STARTTAG,
+ 'attr' => array()
+ ));
+
+ /* Act as if a stream of character tokens had been seen. */
+ $this->insertText('This is a searchable index. '.
+ 'Insert your search keywords here: ');
+
+ /* Act as if a start tag token with the tag name "input"
+ had been seen, with all the attributes from the "isindex"
+ token, except with the "name" attribute set to the value
+ "isindex" (ignoring any explicit "name" attribute). */
+ $attr = $token['attr'];
+ $attr[] = array('name' => 'name', 'value' => 'isindex');
+
+ $this->inBody(array(
+ 'name' => 'input',
+ 'type' => HTML5::STARTTAG,
+ 'attr' => $attr
+ ));
+
+ /* Act as if a stream of character tokens had been seen
+ (see below for what they should say). */
+ $this->insertText('This is a searchable index. '.
+ 'Insert your search keywords here: ');
+
+ /* Act as if an end tag token with the tag name "label"
+ had been seen. */
+ $this->inBody(array(
+ 'name' => 'label',
+ 'type' => HTML5::ENDTAG
+ ));
+
+ /* Act as if an end tag token with the tag name "p" had
+ been seen. */
+ $this->inBody(array(
+ 'name' => 'p',
+ 'type' => HTML5::ENDTAG
+ ));
+
+ /* Act as if a start tag token with the tag name "hr" had
+ been seen. */
+ $this->inBody(array(
+ 'name' => 'hr',
+ 'type' => HTML5::ENDTAG
+ ));
+
+ /* Act as if an end tag token with the tag name "form" had
+ been seen. */
+ $this->inBody(array(
+ 'name' => 'form',
+ 'type' => HTML5::ENDTAG
+ ));
+ }
+ break;
+
+ /* A start tag whose tag name is "textarea" */
+ case 'textarea':
+ $this->insertElement($token);
+
+ /* Switch the tokeniser's content model flag to the
+ RCDATA state. */
+ return HTML5::RCDATA;
+ break;
+
+ /* A start tag whose tag name is one of: "iframe", "noembed",
+ "noframes" */
+ case 'iframe': case 'noembed': case 'noframes':
+ $this->insertElement($token);
+
+ /* Switch the tokeniser's content model flag to the CDATA state. */
+ return HTML5::CDATA;
+ break;
+
+ /* A start tag whose tag name is "select" */
+ case 'select':
+ /* Reconstruct the active formatting elements, if any. */
+ $this->reconstructActiveFormattingElements();
+
+ /* Insert an HTML element for the token. */
+ $this->insertElement($token);
+
+ /* Change the insertion mode to "in select". */
+ $this->mode = self::IN_SELECT;
+ break;
+
+ /* A start or end tag whose tag name is one of: "caption", "col",
+ "colgroup", "frame", "frameset", "head", "option", "optgroup",
+ "tbody", "td", "tfoot", "th", "thead", "tr". */
+ case 'caption': case 'col': case 'colgroup': case 'frame':
+ case 'frameset': case 'head': case 'option': case 'optgroup':
+ case 'tbody': case 'td': case 'tfoot': case 'th': case 'thead':
+ case 'tr':
+ // Parse error. Ignore the token.
+ break;
+
+ /* A start or end tag whose tag name is one of: "event-source",
+ "section", "nav", "article", "aside", "header", "footer",
+ "datagrid", "command" */
+ case 'event-source': case 'section': case 'nav': case 'article':
+ case 'aside': case 'header': case 'footer': case 'datagrid':
+ case 'command':
+ // Work in progress!
+ break;
+
+ /* A start tag token not covered by the previous entries */
+ default:
+ /* Reconstruct the active formatting elements, if any. */
+ $this->reconstructActiveFormattingElements();
+
+ $this->insertElement($token, true, true);
+ break;
+ }
+ break;
+
+ case HTML5::ENDTAG:
+ switch($token['name']) {
+ /* An end tag with the tag name "body" */
+ case 'body':
+ /* If the second element in the stack of open elements is
+ not a body element, this is a parse error. Ignore the token.
+ (innerHTML case) */
+ if(count($this->stack) < 2 || $this->stack[1]->nodeName !== 'body') {
+ // Ignore.
+
+ /* If the current node is not the body element, then this
+ is a parse error. */
+ } elseif(end($this->stack)->nodeName !== 'body') {
+ // Parse error.
+ }
+
+ /* Change the insertion mode to "after body". */
+ $this->mode = self::AFTER_BODY;
+ break;
+
+ /* An end tag with the tag name "html" */
+ case 'html':
+ /* Act as if an end tag with tag name "body" had been seen,
+ then, if that token wasn't ignored, reprocess the current
+ token. */
+ $this->inBody(array(
+ 'name' => 'body',
+ 'type' => HTML5::ENDTAG
+ ));
+
+ return $this->afterBody($token);
+ break;
+
+ /* An end tag whose tag name is one of: "address", "blockquote",
+ "center", "dir", "div", "dl", "fieldset", "listing", "menu",
+ "ol", "pre", "ul" */
+ case 'address': case 'blockquote': case 'center': case 'dir':
+ case 'div': case 'dl': case 'fieldset': case 'listing':
+ case 'menu': case 'ol': case 'pre': case 'ul':
+ /* If the stack of open elements has an element in scope
+ with the same tag name as that of the token, then generate
+ implied end tags. */
+ if($this->elementInScope($token['name'])) {
+ $this->generateImpliedEndTags();
+
+ /* Now, if the current node is not an element with
+ the same tag name as that of the token, then this
+ is a parse error. */
+ // w/e
+
+ /* If the stack of open elements has an element in
+ scope with the same tag name as that of the token,
+ then pop elements from this stack until an element
+ with that tag name has been popped from the stack. */
+ for($n = count($this->stack) - 1; $n >= 0; $n--) {
+ if($this->stack[$n]->nodeName === $token['name']) {
+ $n = -1;
+ }
+
+ array_pop($this->stack);
+ }
+ }
+ break;
+
+ /* An end tag whose tag name is "form" */
+ case 'form':
+ /* If the stack of open elements has an element in scope
+ with the same tag name as that of the token, then generate
+ implied end tags. */
+ if($this->elementInScope($token['name'])) {
+ $this->generateImpliedEndTags();
+
+ }
+
+ if(end($this->stack)->nodeName !== $token['name']) {
+ /* Now, if the current node is not an element with the
+ same tag name as that of the token, then this is a parse
+ error. */
+ // w/e
+
+ } else {
+ /* Otherwise, if the current node is an element with
+ the same tag name as that of the token pop that element
+ from the stack. */
+ array_pop($this->stack);
+ }
+
+ /* In any case, set the form element pointer to null. */
+ $this->form_pointer = null;
+ break;
+
+ /* An end tag whose tag name is "p" */
+ case 'p':
+ /* If the stack of open elements has a p element in scope,
+ then generate implied end tags, except for p elements. */
+ if($this->elementInScope('p')) {
+ $this->generateImpliedEndTags(array('p'));
+
+ /* If the current node is not a p element, then this is
+ a parse error. */
+ // k
+
+ /* If the stack of open elements has a p element in
+ scope, then pop elements from this stack until the stack
+ no longer has a p element in scope. */
+ for($n = count($this->stack) - 1; $n >= 0; $n--) {
+ if($this->elementInScope('p')) {
+ array_pop($this->stack);
+
+ } else {
+ break;
+ }
+ }
+ }
+ break;
+
+ /* An end tag whose tag name is "dd", "dt", or "li" */
+ case 'dd': case 'dt': case 'li':
+ /* If the stack of open elements has an element in scope
+ whose tag name matches the tag name of the token, then
+ generate implied end tags, except for elements with the
+ same tag name as the token. */
+ if($this->elementInScope($token['name'])) {
+ $this->generateImpliedEndTags(array($token['name']));
+
+ /* If the current node is not an element with the same
+ tag name as the token, then this is a parse error. */
+ // w/e
+
+ /* If the stack of open elements has an element in scope
+ whose tag name matches the tag name of the token, then
+ pop elements from this stack until an element with that
+ tag name has been popped from the stack. */
+ for($n = count($this->stack) - 1; $n >= 0; $n--) {
+ if($this->stack[$n]->nodeName === $token['name']) {
+ $n = -1;
+ }
+
+ array_pop($this->stack);
+ }
+ }
+ break;
+
+ /* An end tag whose tag name is one of: "h1", "h2", "h3", "h4",
+ "h5", "h6" */
+ case 'h1': case 'h2': case 'h3': case 'h4': case 'h5': case 'h6':
+ $elements = array('h1', 'h2', 'h3', 'h4', 'h5', 'h6');
+
+ /* If the stack of open elements has in scope an element whose
+ tag name is one of "h1", "h2", "h3", "h4", "h5", or "h6", then
+ generate implied end tags. */
+ if($this->elementInScope($elements)) {
+ $this->generateImpliedEndTags();
+
+ /* Now, if the current node is not an element with the same
+ tag name as that of the token, then this is a parse error. */
+ // w/e
+
+ /* If the stack of open elements has in scope an element
+ whose tag name is one of "h1", "h2", "h3", "h4", "h5", or
+ "h6", then pop elements from the stack until an element
+ with one of those tag names has been popped from the stack. */
+ while($this->elementInScope($elements)) {
+ array_pop($this->stack);
+ }
+ }
+ break;
+
+ /* An end tag whose tag name is one of: "a", "b", "big", "em",
+ "font", "i", "nobr", "s", "small", "strike", "strong", "tt", "u" */
+ case 'a': case 'b': case 'big': case 'em': case 'font':
+ case 'i': case 'nobr': case 's': case 'small': case 'strike':
+ case 'strong': case 'tt': case 'u':
+ /* 1. Let the formatting element be the last element in
+ the list of active formatting elements that:
+ * is between the end of the list and the last scope
+ marker in the list, if any, or the start of the list
+ otherwise, and
+ * has the same tag name as the token.
+ */
+ while(true) {
+ for($a = count($this->a_formatting) - 1; $a >= 0; $a--) {
+ if($this->a_formatting[$a] === self::MARKER) {
+ break;
+
+ } elseif($this->a_formatting[$a]->tagName === $token['name']) {
+ $formatting_element = $this->a_formatting[$a];
+ $in_stack = in_array($formatting_element, $this->stack, true);
+ $fe_af_pos = $a;
+ break;
+ }
+ }
+
+ /* If there is no such node, or, if that node is
+ also in the stack of open elements but the element
+ is not in scope, then this is a parse error. Abort
+ these steps. The token is ignored. */
+ if(!isset($formatting_element) || ($in_stack &&
+ !$this->elementInScope($token['name']))) {
+ break;
+
+ /* Otherwise, if there is such a node, but that node
+ is not in the stack of open elements, then this is a
+ parse error; remove the element from the list, and
+ abort these steps. */
+ } elseif(isset($formatting_element) && !$in_stack) {
+ unset($this->a_formatting[$fe_af_pos]);
+ $this->a_formatting = array_merge($this->a_formatting);
+ break;
+ }
+
+ /* 2. Let the furthest block be the topmost node in the
+ stack of open elements that is lower in the stack
+ than the formatting element, and is not an element in
+ the phrasing or formatting categories. There might
+ not be one. */
+ $fe_s_pos = array_search($formatting_element, $this->stack, true);
+ $length = count($this->stack);
+
+ for($s = $fe_s_pos + 1; $s < $length; $s++) {
+ $category = $this->getElementCategory($this->stack[$s]->nodeName);
+
+ if($category !== self::PHRASING && $category !== self::FORMATTING) {
+ $furthest_block = $this->stack[$s];
+ }
+ }
+
+ /* 3. If there is no furthest block, then the UA must
+ skip the subsequent steps and instead just pop all
+ the nodes from the bottom of the stack of open
+ elements, from the current node up to the formatting
+ element, and remove the formatting element from the
+ list of active formatting elements. */
+ if(!isset($furthest_block)) {
+ for($n = $length - 1; $n >= $fe_s_pos; $n--) {
+ array_pop($this->stack);
+ }
+
+ unset($this->a_formatting[$fe_af_pos]);
+ $this->a_formatting = array_merge($this->a_formatting);
+ break;
+ }
+
+ /* 4. Let the common ancestor be the element
+ immediately above the formatting element in the stack
+ of open elements. */
+ $common_ancestor = $this->stack[$fe_s_pos - 1];
+
+ /* 5. If the furthest block has a parent node, then
+ remove the furthest block from its parent node. */
+ if($furthest_block->parentNode !== null) {
+ $furthest_block->parentNode->removeChild($furthest_block);
+ }
+
+ /* 6. Let a bookmark note the position of the
+ formatting element in the list of active formatting
+ elements relative to the elements on either side
+ of it in the list. */
+ $bookmark = $fe_af_pos;
+
+ /* 7. Let node and last node be the furthest block.
+ Follow these steps: */
+ $node = $furthest_block;
+ $last_node = $furthest_block;
+
+ while(true) {
+ for($n = array_search($node, $this->stack, true) - 1; $n >= 0; $n--) {
+ /* 7.1 Let node be the element immediately
+ prior to node in the stack of open elements. */
+ $node = $this->stack[$n];
+
+ /* 7.2 If node is not in the list of active
+ formatting elements, then remove node from
+ the stack of open elements and then go back
+ to step 1. */
+ if(!in_array($node, $this->a_formatting, true)) {
+ unset($this->stack[$n]);
+ $this->stack = array_merge($this->stack);
+
+ } else {
+ break;
+ }
+ }
+
+ /* 7.3 Otherwise, if node is the formatting
+ element, then go to the next step in the overall
+ algorithm. */
+ if($node === $formatting_element) {
+ break;
+
+ /* 7.4 Otherwise, if last node is the furthest
+ block, then move the aforementioned bookmark to
+ be immediately after the node in the list of
+ active formatting elements. */
+ } elseif($last_node === $furthest_block) {
+ $bookmark = array_search($node, $this->a_formatting, true) + 1;
+ }
+
+ /* 7.5 If node has any children, perform a
+ shallow clone of node, replace the entry for
+ node in the list of active formatting elements
+ with an entry for the clone, replace the entry
+ for node in the stack of open elements with an
+ entry for the clone, and let node be the clone. */
+ if($node->hasChildNodes()) {
+ $clone = $node->cloneNode();
+ $s_pos = array_search($node, $this->stack, true);
+ $a_pos = array_search($node, $this->a_formatting, true);
+
+ $this->stack[$s_pos] = $clone;
+ $this->a_formatting[$a_pos] = $clone;
+ $node = $clone;
+ }
+
+ /* 7.6 Insert last node into node, first removing
+ it from its previous parent node if any. */
+ if($last_node->parentNode !== null) {
+ $last_node->parentNode->removeChild($last_node);
+ }
+
+ $node->appendChild($last_node);
+
+ /* 7.7 Let last node be node. */
+ $last_node = $node;
+ }
+
+ /* 8. Insert whatever last node ended up being in
+ the previous step into the common ancestor node,
+ first removing it from its previous parent node if
+ any. */
+ if($last_node->parentNode !== null) {
+ $last_node->parentNode->removeChild($last_node);
+ }
+
+ $common_ancestor->appendChild($last_node);
+
+ /* 9. Perform a shallow clone of the formatting
+ element. */
+ $clone = $formatting_element->cloneNode();
+
+ /* 10. Take all of the child nodes of the furthest
+ block and append them to the clone created in the
+ last step. */
+ while($furthest_block->hasChildNodes()) {
+ $child = $furthest_block->firstChild;
+ $furthest_block->removeChild($child);
+ $clone->appendChild($child);
+ }
+
+ /* 11. Append that clone to the furthest block. */
+ $furthest_block->appendChild($clone);
+
+ /* 12. Remove the formatting element from the list
+ of active formatting elements, and insert the clone
+ into the list of active formatting elements at the
+ position of the aforementioned bookmark. */
+ $fe_af_pos = array_search($formatting_element, $this->a_formatting, true);
+ unset($this->a_formatting[$fe_af_pos]);
+ $this->a_formatting = array_merge($this->a_formatting);
+
+ $af_part1 = array_slice($this->a_formatting, 0, $bookmark - 1);
+ $af_part2 = array_slice($this->a_formatting, $bookmark, count($this->a_formatting));
+ $this->a_formatting = array_merge($af_part1, array($clone), $af_part2);
+
+ /* 13. Remove the formatting element from the stack
+ of open elements, and insert the clone into the stack
+ of open elements immediately after (i.e. in a more
+ deeply nested position than) the position of the
+ furthest block in that stack. */
+ $fe_s_pos = array_search($formatting_element, $this->stack, true);
+ $fb_s_pos = array_search($furthest_block, $this->stack, true);
+ unset($this->stack[$fe_s_pos]);
+
+ $s_part1 = array_slice($this->stack, 0, $fb_s_pos);
+ $s_part2 = array_slice($this->stack, $fb_s_pos + 1, count($this->stack));
+ $this->stack = array_merge($s_part1, array($clone), $s_part2);
+
+ /* 14. Jump back to step 1 in this series of steps. */
+ unset($formatting_element, $fe_af_pos, $fe_s_pos, $furthest_block);
+ }
+ break;
+
+ /* An end tag token whose tag name is one of: "button",
+ "marquee", "object" */
+ case 'button': case 'marquee': case 'object':
+ /* If the stack of open elements has an element in scope whose
+ tag name matches the tag name of the token, then generate implied
+ tags. */
+ if($this->elementInScope($token['name'])) {
+ $this->generateImpliedEndTags();
+
+ /* Now, if the current node is not an element with the same
+ tag name as the token, then this is a parse error. */
+ // k
+
+ /* Now, if the stack of open elements has an element in scope
+ whose tag name matches the tag name of the token, then pop
+ elements from the stack until that element has been popped from
+ the stack, and clear the list of active formatting elements up
+ to the last marker. */
+ for($n = count($this->stack) - 1; $n >= 0; $n--) {
+ if($this->stack[$n]->nodeName === $token['name']) {
+ $n = -1;
+ }
+
+ array_pop($this->stack);
+ }
+
+ $marker = end(array_keys($this->a_formatting, self::MARKER, true));
+
+ for($n = count($this->a_formatting) - 1; $n > $marker; $n--) {
+ array_pop($this->a_formatting);
+ }
+ }
+ break;
+
+ /* Or an end tag whose tag name is one of: "area", "basefont",
+ "bgsound", "br", "embed", "hr", "iframe", "image", "img",
+ "input", "isindex", "noembed", "noframes", "param", "select",
+ "spacer", "table", "textarea", "wbr" */
+ case 'area': case 'basefont': case 'bgsound': case 'br':
+ case 'embed': case 'hr': case 'iframe': case 'image':
+ case 'img': case 'input': case 'isindex': case 'noembed':
+ case 'noframes': case 'param': case 'select': case 'spacer':
+ case 'table': case 'textarea': case 'wbr':
+ // Parse error. Ignore the token.
+ break;
+
+ /* An end tag token not covered by the previous entries */
+ default:
+ for($n = count($this->stack) - 1; $n >= 0; $n--) {
+ /* Initialise node to be the current node (the bottommost
+ node of the stack). */
+ $node = end($this->stack);
+
+ /* If node has the same tag name as the end tag token,
+ then: */
+ if($token['name'] === $node->nodeName) {
+ /* Generate implied end tags. */
+ $this->generateImpliedEndTags();
+
+ /* If the tag name of the end tag token does not
+ match the tag name of the current node, this is a
+ parse error. */
+ // k
+
+ /* Pop all the nodes from the current node up to
+ node, including node, then stop this algorithm. */
+ for($x = count($this->stack) - $n; $x >= $n; $x--) {
+ array_pop($this->stack);
+ }
+
+ } else {
+ $category = $this->getElementCategory($node);
+
+ if($category !== self::SPECIAL && $category !== self::SCOPING) {
+ /* Otherwise, if node is in neither the formatting
+ category nor the phrasing category, then this is a
+ parse error. Stop this algorithm. The end tag token
+ is ignored. */
+ return false;
+ }
+ }
+ }
+ break;
+ }
+ break;
+ }
+ }
+
+ private function inTable($token) {
+ $clear = array('html', 'table');
+
+ /* A character token that is one of one of U+0009 CHARACTER TABULATION,
+ U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF),
+ or U+0020 SPACE */
+ if($token['type'] === HTML5::CHARACTR &&
+ preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) {
+ /* Append the character to the current node. */
+ $text = $this->dom->createTextNode($token['data']);
+ end($this->stack)->appendChild($text);
+
+ /* A comment token */
+ } elseif($token['type'] === HTML5::COMMENT) {
+ /* Append a Comment node to the current node with the data
+ attribute set to the data given in the comment token. */
+ $comment = $this->dom->createComment($token['data']);
+ end($this->stack)->appendChild($comment);
+
+ /* A start tag whose tag name is "caption" */
+ } elseif($token['type'] === HTML5::STARTTAG &&
+ $token['name'] === 'caption') {
+ /* Clear the stack back to a table context. */
+ $this->clearStackToTableContext($clear);
+
+ /* Insert a marker at the end of the list of active
+ formatting elements. */
+ $this->a_formatting[] = self::MARKER;
+
+ /* Insert an HTML element for the token, then switch the
+ insertion mode to "in caption". */
+ $this->insertElement($token);
+ $this->mode = self::IN_CAPTION;
+
+ /* A start tag whose tag name is "colgroup" */
+ } elseif($token['type'] === HTML5::STARTTAG &&
+ $token['name'] === 'colgroup') {
+ /* Clear the stack back to a table context. */
+ $this->clearStackToTableContext($clear);
+
+ /* Insert an HTML element for the token, then switch the
+ insertion mode to "in column group". */
+ $this->insertElement($token);
+ $this->mode = self::IN_CGROUP;
+
+ /* A start tag whose tag name is "col" */
+ } elseif($token['type'] === HTML5::STARTTAG &&
+ $token['name'] === 'col') {
+ $this->inTable(array(
+ 'name' => 'colgroup',
+ 'type' => HTML5::STARTTAG,
+ 'attr' => array()
+ ));
+
+ $this->inColumnGroup($token);
+
+ /* A start tag whose tag name is one of: "tbody", "tfoot", "thead" */
+ } elseif($token['type'] === HTML5::STARTTAG && in_array($token['name'],
+ array('tbody', 'tfoot', 'thead'))) {
+ /* Clear the stack back to a table context. */
+ $this->clearStackToTableContext($clear);
+
+ /* Insert an HTML element for the token, then switch the insertion
+ mode to "in table body". */
+ $this->insertElement($token);
+ $this->mode = self::IN_TBODY;
+
+ /* A start tag whose tag name is one of: "td", "th", "tr" */
+ } elseif($token['type'] === HTML5::STARTTAG &&
+ in_array($token['name'], array('td', 'th', 'tr'))) {
+ /* Act as if a start tag token with the tag name "tbody" had been
+ seen, then reprocess the current token. */
+ $this->inTable(array(
+ 'name' => 'tbody',
+ 'type' => HTML5::STARTTAG,
+ 'attr' => array()
+ ));
+
+ return $this->inTableBody($token);
+
+ /* A start tag whose tag name is "table" */
+ } elseif($token['type'] === HTML5::STARTTAG &&
+ $token['name'] === 'table') {
+ /* Parse error. Act as if an end tag token with the tag name "table"
+ had been seen, then, if that token wasn't ignored, reprocess the
+ current token. */
+ $this->inTable(array(
+ 'name' => 'table',
+ 'type' => HTML5::ENDTAG
+ ));
+
+ return $this->mainPhase($token);
+
+ /* An end tag whose tag name is "table" */
+ } elseif($token['type'] === HTML5::ENDTAG &&
+ $token['name'] === 'table') {
+ /* If the stack of open elements does not have an element in table
+ scope with the same tag name as the token, this is a parse error.
+ Ignore the token. (innerHTML case) */
+ if(!$this->elementInScope($token['name'], true)) {
+ return false;
+
+ /* Otherwise: */
+ } else {
+ /* Generate implied end tags. */
+ $this->generateImpliedEndTags();
+
+ /* Now, if the current node is not a table element, then this
+ is a parse error. */
+ // w/e
+
+ /* Pop elements from this stack until a table element has been
+ popped from the stack. */
+ while(true) {
+ $current = end($this->stack)->nodeName;
+ array_pop($this->stack);
+
+ if($current === 'table') {
+ break;
+ }
+ }
+
+ /* Reset the insertion mode appropriately. */
+ $this->resetInsertionMode();
+ }
+
+ /* An end tag whose tag name is one of: "body", "caption", "col",
+ "colgroup", "html", "tbody", "td", "tfoot", "th", "thead", "tr" */
+ } elseif($token['type'] === HTML5::ENDTAG && in_array($token['name'],
+ array('body', 'caption', 'col', 'colgroup', 'html', 'tbody', 'td',
+ 'tfoot', 'th', 'thead', 'tr'))) {
+ // Parse error. Ignore the token.
+
+ /* Anything else */
+ } else {
+ /* Parse error. Process the token as if the insertion mode was "in
+ body", with the following exception: */
+
+ /* If the current node is a table, tbody, tfoot, thead, or tr
+ element, then, whenever a node would be inserted into the current
+ node, it must instead be inserted into the foster parent element. */
+ if(in_array(end($this->stack)->nodeName,
+ array('table', 'tbody', 'tfoot', 'thead', 'tr'))) {
+ /* The foster parent element is the parent element of the last
+ table element in the stack of open elements, if there is a
+ table element and it has such a parent element. If there is no
+ table element in the stack of open elements (innerHTML case),
+ then the foster parent element is the first element in the
+ stack of open elements (the html element). Otherwise, if there
+ is a table element in the stack of open elements, but the last
+ table element in the stack of open elements has no parent, or
+ its parent node is not an element, then the foster parent
+ element is the element before the last table element in the
+ stack of open elements. */
+ for($n = count($this->stack) - 1; $n >= 0; $n--) {
+ if($this->stack[$n]->nodeName === 'table') {
+ $table = $this->stack[$n];
+ break;
+ }
+ }
+
+ if(isset($table) && $table->parentNode !== null) {
+ $this->foster_parent = $table->parentNode;
+
+ } elseif(!isset($table)) {
+ $this->foster_parent = $this->stack[0];
+
+ } elseif(isset($table) && ($table->parentNode === null ||
+ $table->parentNode->nodeType !== XML_ELEMENT_NODE)) {
+ $this->foster_parent = $this->stack[$n - 1];
+ }
+ }
+
+ $this->inBody($token);
+ }
+ }
+
+ private function inCaption($token) {
+ /* An end tag whose tag name is "caption" */
+ if($token['type'] === HTML5::ENDTAG && $token['name'] === 'caption') {
+ /* If the stack of open elements does not have an element in table
+ scope with the same tag name as the token, this is a parse error.
+ Ignore the token. (innerHTML case) */
+ if(!$this->elementInScope($token['name'], true)) {
+ // Ignore
+
+ /* Otherwise: */
+ } else {
+ /* Generate implied end tags. */
+ $this->generateImpliedEndTags();
+
+ /* Now, if the current node is not a caption element, then this
+ is a parse error. */
+ // w/e
+
+ /* Pop elements from this stack until a caption element has
+ been popped from the stack. */
+ while(true) {
+ $node = end($this->stack)->nodeName;
+ array_pop($this->stack);
+
+ if($node === 'caption') {
+ break;
+ }
+ }
+
+ /* Clear the list of active formatting elements up to the last
+ marker. */
+ $this->clearTheActiveFormattingElementsUpToTheLastMarker();
+
+ /* Switch the insertion mode to "in table". */
+ $this->mode = self::IN_TABLE;
+ }
+
+ /* A start tag whose tag name is one of: "caption", "col", "colgroup",
+ "tbody", "td", "tfoot", "th", "thead", "tr", or an end tag whose tag
+ name is "table" */
+ } elseif(($token['type'] === HTML5::STARTTAG && in_array($token['name'],
+ array('caption', 'col', 'colgroup', 'tbody', 'td', 'tfoot', 'th',
+ 'thead', 'tr'))) || ($token['type'] === HTML5::ENDTAG &&
+ $token['name'] === 'table')) {
+ /* Parse error. Act as if an end tag with the tag name "caption"
+ had been seen, then, if that token wasn't ignored, reprocess the
+ current token. */
+ $this->inCaption(array(
+ 'name' => 'caption',
+ 'type' => HTML5::ENDTAG
+ ));
+
+ return $this->inTable($token);
+
+ /* An end tag whose tag name is one of: "body", "col", "colgroup",
+ "html", "tbody", "td", "tfoot", "th", "thead", "tr" */
+ } elseif($token['type'] === HTML5::ENDTAG && in_array($token['name'],
+ array('body', 'col', 'colgroup', 'html', 'tbody', 'tfoot', 'th',
+ 'thead', 'tr'))) {
+ // Parse error. Ignore the token.
+
+ /* Anything else */
+ } else {
+ /* Process the token as if the insertion mode was "in body". */
+ $this->inBody($token);
+ }
+ }
+
+ private function inColumnGroup($token) {
+ /* A character token that is one of one of U+0009 CHARACTER TABULATION,
+ U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF),
+ or U+0020 SPACE */
+ if($token['type'] === HTML5::CHARACTR &&
+ preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) {
+ /* Append the character to the current node. */
+ $text = $this->dom->createTextNode($token['data']);
+ end($this->stack)->appendChild($text);
+
+ /* A comment token */
+ } elseif($token['type'] === HTML5::COMMENT) {
+ /* Append a Comment node to the current node with the data
+ attribute set to the data given in the comment token. */
+ $comment = $this->dom->createComment($token['data']);
+ end($this->stack)->appendChild($comment);
+
+ /* A start tag whose tag name is "col" */
+ } elseif($token['type'] === HTML5::STARTTAG && $token['name'] === 'col') {
+ /* Insert a col element for the token. Immediately pop the current
+ node off the stack of open elements. */
+ $this->insertElement($token);
+ array_pop($this->stack);
+
+ /* An end tag whose tag name is "colgroup" */
+ } elseif($token['type'] === HTML5::ENDTAG &&
+ $token['name'] === 'colgroup') {
+ /* If the current node is the root html element, then this is a
+ parse error, ignore the token. (innerHTML case) */
+ if(end($this->stack)->nodeName === 'html') {
+ // Ignore
+
+ /* Otherwise, pop the current node (which will be a colgroup
+ element) from the stack of open elements. Switch the insertion
+ mode to "in table". */
+ } else {
+ array_pop($this->stack);
+ $this->mode = self::IN_TABLE;
+ }
+
+ /* An end tag whose tag name is "col" */
+ } elseif($token['type'] === HTML5::ENDTAG && $token['name'] === 'col') {
+ /* Parse error. Ignore the token. */
+
+ /* Anything else */
+ } else {
+ /* Act as if an end tag with the tag name "colgroup" had been seen,
+ and then, if that token wasn't ignored, reprocess the current token. */
+ $this->inColumnGroup(array(
+ 'name' => 'colgroup',
+ 'type' => HTML5::ENDTAG
+ ));
+
+ return $this->inTable($token);
+ }
+ }
+
+ private function inTableBody($token) {
+ $clear = array('tbody', 'tfoot', 'thead', 'html');
+
+ /* A start tag whose tag name is "tr" */
+ if($token['type'] === HTML5::STARTTAG && $token['name'] === 'tr') {
+ /* Clear the stack back to a table body context. */
+ $this->clearStackToTableContext($clear);
+
+ /* Insert a tr element for the token, then switch the insertion
+ mode to "in row". */
+ $this->insertElement($token);
+ $this->mode = self::IN_ROW;
+
+ /* A start tag whose tag name is one of: "th", "td" */
+ } elseif($token['type'] === HTML5::STARTTAG &&
+ ($token['name'] === 'th' || $token['name'] === 'td')) {
+ /* Parse error. Act as if a start tag with the tag name "tr" had
+ been seen, then reprocess the current token. */
+ $this->inTableBody(array(
+ 'name' => 'tr',
+ 'type' => HTML5::STARTTAG,
+ 'attr' => array()
+ ));
+
+ return $this->inRow($token);
+
+ /* An end tag whose tag name is one of: "tbody", "tfoot", "thead" */
+ } elseif($token['type'] === HTML5::ENDTAG &&
+ in_array($token['name'], array('tbody', 'tfoot', 'thead'))) {
+ /* If the stack of open elements does not have an element in table
+ scope with the same tag name as the token, this is a parse error.
+ Ignore the token. */
+ if(!$this->elementInScope($token['name'], true)) {
+ // Ignore
+
+ /* Otherwise: */
+ } else {
+ /* Clear the stack back to a table body context. */
+ $this->clearStackToTableContext($clear);
+
+ /* Pop the current node from the stack of open elements. Switch
+ the insertion mode to "in table". */
+ array_pop($this->stack);
+ $this->mode = self::IN_TABLE;
+ }
+
+ /* A start tag whose tag name is one of: "caption", "col", "colgroup",
+ "tbody", "tfoot", "thead", or an end tag whose tag name is "table" */
+ } elseif(($token['type'] === HTML5::STARTTAG && in_array($token['name'],
+ array('caption', 'col', 'colgroup', 'tbody', 'tfoor', 'thead'))) ||
+ ($token['type'] === HTML5::STARTTAG && $token['name'] === 'table')) {
+ /* If the stack of open elements does not have a tbody, thead, or
+ tfoot element in table scope, this is a parse error. Ignore the
+ token. (innerHTML case) */
+ if(!$this->elementInScope(array('tbody', 'thead', 'tfoot'), true)) {
+ // Ignore.
+
+ /* Otherwise: */
+ } else {
+ /* Clear the stack back to a table body context. */
+ $this->clearStackToTableContext($clear);
+
+ /* Act as if an end tag with the same tag name as the current
+ node ("tbody", "tfoot", or "thead") had been seen, then
+ reprocess the current token. */
+ $this->inTableBody(array(
+ 'name' => end($this->stack)->nodeName,
+ 'type' => HTML5::ENDTAG
+ ));
+
+ return $this->mainPhase($token);
+ }
+
+ /* An end tag whose tag name is one of: "body", "caption", "col",
+ "colgroup", "html", "td", "th", "tr" */
+ } elseif($token['type'] === HTML5::ENDTAG && in_array($token['name'],
+ array('body', 'caption', 'col', 'colgroup', 'html', 'td', 'th', 'tr'))) {
+ /* Parse error. Ignore the token. */
+
+ /* Anything else */
+ } else {
+ /* Process the token as if the insertion mode was "in table". */
+ $this->inTable($token);
+ }
+ }
+
+ private function inRow($token) {
+ $clear = array('tr', 'html');
+
+ /* A start tag whose tag name is one of: "th", "td" */
+ if($token['type'] === HTML5::STARTTAG &&
+ ($token['name'] === 'th' || $token['name'] === 'td')) {
+ /* Clear the stack back to a table row context. */
+ $this->clearStackToTableContext($clear);
+
+ /* Insert an HTML element for the token, then switch the insertion
+ mode to "in cell". */
+ $this->insertElement($token);
+ $this->mode = self::IN_CELL;
+
+ /* Insert a marker at the end of the list of active formatting
+ elements. */
+ $this->a_formatting[] = self::MARKER;
+
+ /* An end tag whose tag name is "tr" */
+ } elseif($token['type'] === HTML5::ENDTAG && $token['name'] === 'tr') {
+ /* If the stack of open elements does not have an element in table
+ scope with the same tag name as the token, this is a parse error.
+ Ignore the token. (innerHTML case) */
+ if(!$this->elementInScope($token['name'], true)) {
+ // Ignore.
+
+ /* Otherwise: */
+ } else {
+ /* Clear the stack back to a table row context. */
+ $this->clearStackToTableContext($clear);
+
+ /* Pop the current node (which will be a tr element) from the
+ stack of open elements. Switch the insertion mode to "in table
+ body". */
+ array_pop($this->stack);
+ $this->mode = self::IN_TBODY;
+ }
+
+ /* A start tag whose tag name is one of: "caption", "col", "colgroup",
+ "tbody", "tfoot", "thead", "tr" or an end tag whose tag name is "table" */
+ } elseif($token['type'] === HTML5::STARTTAG && in_array($token['name'],
+ array('caption', 'col', 'colgroup', 'tbody', 'tfoot', 'thead', 'tr'))) {
+ /* Act as if an end tag with the tag name "tr" had been seen, then,
+ if that token wasn't ignored, reprocess the current token. */
+ $this->inRow(array(
+ 'name' => 'tr',
+ 'type' => HTML5::ENDTAG
+ ));
+
+ return $this->inCell($token);
+
+ /* An end tag whose tag name is one of: "tbody", "tfoot", "thead" */
+ } elseif($token['type'] === HTML5::ENDTAG &&
+ in_array($token['name'], array('tbody', 'tfoot', 'thead'))) {
+ /* If the stack of open elements does not have an element in table
+ scope with the same tag name as the token, this is a parse error.
+ Ignore the token. */
+ if(!$this->elementInScope($token['name'], true)) {
+ // Ignore.
+
+ /* Otherwise: */
+ } else {
+ /* Otherwise, act as if an end tag with the tag name "tr" had
+ been seen, then reprocess the current token. */
+ $this->inRow(array(
+ 'name' => 'tr',
+ 'type' => HTML5::ENDTAG
+ ));
+
+ return $this->inCell($token);
+ }
+
+ /* An end tag whose tag name is one of: "body", "caption", "col",
+ "colgroup", "html", "td", "th" */
+ } elseif($token['type'] === HTML5::ENDTAG && in_array($token['name'],
+ array('body', 'caption', 'col', 'colgroup', 'html', 'td', 'th', 'tr'))) {
+ /* Parse error. Ignore the token. */
+
+ /* Anything else */
+ } else {
+ /* Process the token as if the insertion mode was "in table". */
+ $this->inTable($token);
+ }
+ }
+
+ private function inCell($token) {
+ /* An end tag whose tag name is one of: "td", "th" */
+ if($token['type'] === HTML5::ENDTAG &&
+ ($token['name'] === 'td' || $token['name'] === 'th')) {
+ /* If the stack of open elements does not have an element in table
+ scope with the same tag name as that of the token, then this is a
+ parse error and the token must be ignored. */
+ if(!$this->elementInScope($token['name'], true)) {
+ // Ignore.
+
+ /* Otherwise: */
+ } else {
+ /* Generate implied end tags, except for elements with the same
+ tag name as the token. */
+ $this->generateImpliedEndTags(array($token['name']));
+
+ /* Now, if the current node is not an element with the same tag
+ name as the token, then this is a parse error. */
+ // k
+
+ /* Pop elements from this stack until an element with the same
+ tag name as the token has been popped from the stack. */
+ while(true) {
+ $node = end($this->stack)->nodeName;
+ array_pop($this->stack);
+
+ if($node === $token['name']) {
+ break;
+ }
+ }
+
+ /* Clear the list of active formatting elements up to the last
+ marker. */
+ $this->clearTheActiveFormattingElementsUpToTheLastMarker();
+
+ /* Switch the insertion mode to "in row". (The current node
+ will be a tr element at this point.) */
+ $this->mode = self::IN_ROW;
+ }
+
+ /* A start tag whose tag name is one of: "caption", "col", "colgroup",
+ "tbody", "td", "tfoot", "th", "thead", "tr" */
+ } elseif($token['type'] === HTML5::STARTTAG && in_array($token['name'],
+ array('caption', 'col', 'colgroup', 'tbody', 'td', 'tfoot', 'th',
+ 'thead', 'tr'))) {
+ /* If the stack of open elements does not have a td or th element
+ in table scope, then this is a parse error; ignore the token.
+ (innerHTML case) */
+ if(!$this->elementInScope(array('td', 'th'), true)) {
+ // Ignore.
+
+ /* Otherwise, close the cell (see below) and reprocess the current
+ token. */
+ } else {
+ $this->closeCell();
+ return $this->inRow($token);
+ }
+
+ /* A start tag whose tag name is one of: "caption", "col", "colgroup",
+ "tbody", "td", "tfoot", "th", "thead", "tr" */
+ } elseif($token['type'] === HTML5::STARTTAG && in_array($token['name'],
+ array('caption', 'col', 'colgroup', 'tbody', 'td', 'tfoot', 'th',
+ 'thead', 'tr'))) {
+ /* If the stack of open elements does not have a td or th element
+ in table scope, then this is a parse error; ignore the token.
+ (innerHTML case) */
+ if(!$this->elementInScope(array('td', 'th'), true)) {
+ // Ignore.
+
+ /* Otherwise, close the cell (see below) and reprocess the current
+ token. */
+ } else {
+ $this->closeCell();
+ return $this->inRow($token);
+ }
+
+ /* An end tag whose tag name is one of: "body", "caption", "col",
+ "colgroup", "html" */
+ } elseif($token['type'] === HTML5::ENDTAG && in_array($token['name'],
+ array('body', 'caption', 'col', 'colgroup', 'html'))) {
+ /* Parse error. Ignore the token. */
+
+ /* An end tag whose tag name is one of: "table", "tbody", "tfoot",
+ "thead", "tr" */
+ } elseif($token['type'] === HTML5::ENDTAG && in_array($token['name'],
+ array('table', 'tbody', 'tfoot', 'thead', 'tr'))) {
+ /* If the stack of open elements does not have an element in table
+ scope with the same tag name as that of the token (which can only
+ happen for "tbody", "tfoot" and "thead", or, in the innerHTML case),
+ then this is a parse error and the token must be ignored. */
+ if(!$this->elementInScope($token['name'], true)) {
+ // Ignore.
+
+ /* Otherwise, close the cell (see below) and reprocess the current
+ token. */
+ } else {
+ $this->closeCell();
+ return $this->inRow($token);
+ }
+
+ /* Anything else */
+ } else {
+ /* Process the token as if the insertion mode was "in body". */
+ $this->inBody($token);
+ }
+ }
+
+ private function inSelect($token) {
+ /* Handle the token as follows: */
+
+ /* A character token */
+ if($token['type'] === HTML5::CHARACTR) {
+ /* Append the token's character to the current node. */
+ $this->insertText($token['data']);
+
+ /* A comment token */
+ } elseif($token['type'] === HTML5::COMMENT) {
+ /* Append a Comment node to the current node with the data
+ attribute set to the data given in the comment token. */
+ $this->insertComment($token['data']);
+
+ /* A start tag token whose tag name is "option" */
+ } elseif($token['type'] === HTML5::STARTTAG &&
+ $token['name'] === 'option') {
+ /* If the current node is an option element, act as if an end tag
+ with the tag name "option" had been seen. */
+ if(end($this->stack)->nodeName === 'option') {
+ $this->inSelect(array(
+ 'name' => 'option',
+ 'type' => HTML5::ENDTAG
+ ));
+ }
+
+ /* Insert an HTML element for the token. */
+ $this->insertElement($token);
+
+ /* A start tag token whose tag name is "optgroup" */
+ } elseif($token['type'] === HTML5::STARTTAG &&
+ $token['name'] === 'optgroup') {
+ /* If the current node is an option element, act as if an end tag
+ with the tag name "option" had been seen. */
+ if(end($this->stack)->nodeName === 'option') {
+ $this->inSelect(array(
+ 'name' => 'option',
+ 'type' => HTML5::ENDTAG
+ ));
+ }
+
+ /* If the current node is an optgroup element, act as if an end tag
+ with the tag name "optgroup" had been seen. */
+ if(end($this->stack)->nodeName === 'optgroup') {
+ $this->inSelect(array(
+ 'name' => 'optgroup',
+ 'type' => HTML5::ENDTAG
+ ));
+ }
+
+ /* Insert an HTML element for the token. */
+ $this->insertElement($token);
+
+ /* An end tag token whose tag name is "optgroup" */
+ } elseif($token['type'] === HTML5::ENDTAG &&
+ $token['name'] === 'optgroup') {
+ /* First, if the current node is an option element, and the node
+ immediately before it in the stack of open elements is an optgroup
+ element, then act as if an end tag with the tag name "option" had
+ been seen. */
+ $elements_in_stack = count($this->stack);
+
+ if($this->stack[$elements_in_stack - 1]->nodeName === 'option' &&
+ $this->stack[$elements_in_stack - 2]->nodeName === 'optgroup') {
+ $this->inSelect(array(
+ 'name' => 'option',
+ 'type' => HTML5::ENDTAG
+ ));
+ }
+
+ /* If the current node is an optgroup element, then pop that node
+ from the stack of open elements. Otherwise, this is a parse error,
+ ignore the token. */
+ if($this->stack[$elements_in_stack - 1] === 'optgroup') {
+ array_pop($this->stack);
+ }
+
+ /* An end tag token whose tag name is "option" */
+ } elseif($token['type'] === HTML5::ENDTAG &&
+ $token['name'] === 'option') {
+ /* If the current node is an option element, then pop that node
+ from the stack of open elements. Otherwise, this is a parse error,
+ ignore the token. */
+ if(end($this->stack)->nodeName === 'option') {
+ array_pop($this->stack);
+ }
+
+ /* An end tag whose tag name is "select" */
+ } elseif($token['type'] === HTML5::ENDTAG &&
+ $token['name'] === 'select') {
+ /* If the stack of open elements does not have an element in table
+ scope with the same tag name as the token, this is a parse error.
+ Ignore the token. (innerHTML case) */
+ if(!$this->elementInScope($token['name'], true)) {
+ // w/e
+
+ /* Otherwise: */
+ } else {
+ /* Pop elements from the stack of open elements until a select
+ element has been popped from the stack. */
+ while(true) {
+ $current = end($this->stack)->nodeName;
+ array_pop($this->stack);
+
+ if($current === 'select') {
+ break;
+ }
+ }
+
+ /* Reset the insertion mode appropriately. */
+ $this->resetInsertionMode();
+ }
+
+ /* A start tag whose tag name is "select" */
+ } elseif($token['name'] === 'select' &&
+ $token['type'] === HTML5::STARTTAG) {
+ /* Parse error. Act as if the token had been an end tag with the
+ tag name "select" instead. */
+ $this->inSelect(array(
+ 'name' => 'select',
+ 'type' => HTML5::ENDTAG
+ ));
+
+ /* An end tag whose tag name is one of: "caption", "table", "tbody",
+ "tfoot", "thead", "tr", "td", "th" */
+ } elseif(in_array($token['name'], array('caption', 'table', 'tbody',
+ 'tfoot', 'thead', 'tr', 'td', 'th')) && $token['type'] === HTML5::ENDTAG) {
+ /* Parse error. */
+ // w/e
+
+ /* If the stack of open elements has an element in table scope with
+ the same tag name as that of the token, then act as if an end tag
+ with the tag name "select" had been seen, and reprocess the token.
+ Otherwise, ignore the token. */
+ if($this->elementInScope($token['name'], true)) {
+ $this->inSelect(array(
+ 'name' => 'select',
+ 'type' => HTML5::ENDTAG
+ ));
+
+ $this->mainPhase($token);
+ }
+
+ /* Anything else */
+ } else {
+ /* Parse error. Ignore the token. */
+ }
+ }
+
+ private function afterBody($token) {
+ /* Handle the token as follows: */
+
+ /* A character token that is one of one of U+0009 CHARACTER TABULATION,
+ U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF),
+ or U+0020 SPACE */
+ if($token['type'] === HTML5::CHARACTR &&
+ preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) {
+ /* Process the token as it would be processed if the insertion mode
+ was "in body". */
+ $this->inBody($token);
+
+ /* A comment token */
+ } elseif($token['type'] === HTML5::COMMENT) {
+ /* Append a Comment node to the first element in the stack of open
+ elements (the html element), with the data attribute set to the
+ data given in the comment token. */
+ $comment = $this->dom->createComment($token['data']);
+ $this->stack[0]->appendChild($comment);
+
+ /* An end tag with the tag name "html" */
+ } elseif($token['type'] === HTML5::ENDTAG && $token['name'] === 'html') {
+ /* If the parser was originally created in order to handle the
+ setting of an element's innerHTML attribute, this is a parse error;
+ ignore the token. (The element will be an html element in this
+ case.) (innerHTML case) */
+
+ /* Otherwise, switch to the trailing end phase. */
+ $this->phase = self::END_PHASE;
+
+ /* Anything else */
+ } else {
+ /* Parse error. Set the insertion mode to "in body" and reprocess
+ the token. */
+ $this->mode = self::IN_BODY;
+ return $this->inBody($token);
+ }
+ }
+
+ private function inFrameset($token) {
+ /* Handle the token as follows: */
+
+ /* A character token that is one of one of U+0009 CHARACTER TABULATION,
+ U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF),
+ U+000D CARRIAGE RETURN (CR), or U+0020 SPACE */
+ if($token['type'] === HTML5::CHARACTR &&
+ preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) {
+ /* Append the character to the current node. */
+ $this->insertText($token['data']);
+
+ /* A comment token */
+ } elseif($token['type'] === HTML5::COMMENT) {
+ /* Append a Comment node to the current node with the data
+ attribute set to the data given in the comment token. */
+ $this->insertComment($token['data']);
+
+ /* A start tag with the tag name "frameset" */
+ } elseif($token['name'] === 'frameset' &&
+ $token['type'] === HTML5::STARTTAG) {
+ $this->insertElement($token);
+
+ /* An end tag with the tag name "frameset" */
+ } elseif($token['name'] === 'frameset' &&
+ $token['type'] === HTML5::ENDTAG) {
+ /* If the current node is the root html element, then this is a
+ parse error; ignore the token. (innerHTML case) */
+ if(end($this->stack)->nodeName === 'html') {
+ // Ignore
+
+ } else {
+ /* Otherwise, pop the current node from the stack of open
+ elements. */
+ array_pop($this->stack);
+
+ /* If the parser was not originally created in order to handle
+ the setting of an element's innerHTML attribute (innerHTML case),
+ and the current node is no longer a frameset element, then change
+ the insertion mode to "after frameset". */
+ $this->mode = self::AFTR_FRAME;
+ }
+
+ /* A start tag with the tag name "frame" */
+ } elseif($token['name'] === 'frame' &&
+ $token['type'] === HTML5::STARTTAG) {
+ /* Insert an HTML element for the token. */
+ $this->insertElement($token);
+
+ /* Immediately pop the current node off the stack of open elements. */
+ array_pop($this->stack);
+
+ /* A start tag with the tag name "noframes" */
+ } elseif($token['name'] === 'noframes' &&
+ $token['type'] === HTML5::STARTTAG) {
+ /* Process the token as if the insertion mode had been "in body". */
+ $this->inBody($token);
+
+ /* Anything else */
+ } else {
+ /* Parse error. Ignore the token. */
+ }
+ }
+
+ private function afterFrameset($token) {
+ /* Handle the token as follows: */
+
+ /* A character token that is one of one of U+0009 CHARACTER TABULATION,
+ U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF),
+ U+000D CARRIAGE RETURN (CR), or U+0020 SPACE */
+ if($token['type'] === HTML5::CHARACTR &&
+ preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) {
+ /* Append the character to the current node. */
+ $this->insertText($token['data']);
+
+ /* A comment token */
+ } elseif($token['type'] === HTML5::COMMENT) {
+ /* Append a Comment node to the current node with the data
+ attribute set to the data given in the comment token. */
+ $this->insertComment($token['data']);
+
+ /* An end tag with the tag name "html" */
+ } elseif($token['name'] === 'html' &&
+ $token['type'] === HTML5::ENDTAG) {
+ /* Switch to the trailing end phase. */
+ $this->phase = self::END_PHASE;
+
+ /* A start tag with the tag name "noframes" */
+ } elseif($token['name'] === 'noframes' &&
+ $token['type'] === HTML5::STARTTAG) {
+ /* Process the token as if the insertion mode had been "in body". */
+ $this->inBody($token);
+
+ /* Anything else */
+ } else {
+ /* Parse error. Ignore the token. */
+ }
+ }
+
+ private function trailingEndPhase($token) {
+ /* After the main phase, as each token is emitted from the tokenisation
+ stage, it must be processed as described in this section. */
+
+ /* A DOCTYPE token */
+ if($token['type'] === HTML5::DOCTYPE) {
+ // Parse error. Ignore the token.
+
+ /* A comment token */
+ } elseif($token['type'] === HTML5::COMMENT) {
+ /* Append a Comment node to the Document object with the data
+ attribute set to the data given in the comment token. */
+ $comment = $this->dom->createComment($token['data']);
+ $this->dom->appendChild($comment);
+
+ /* A character token that is one of one of U+0009 CHARACTER TABULATION,
+ U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF),
+ or U+0020 SPACE */
+ } elseif($token['type'] === HTML5::CHARACTR &&
+ preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) {
+ /* Process the token as it would be processed in the main phase. */
+ $this->mainPhase($token);
+
+ /* A character token that is not one of U+0009 CHARACTER TABULATION,
+ U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF),
+ or U+0020 SPACE. Or a start tag token. Or an end tag token. */
+ } elseif(($token['type'] === HTML5::CHARACTR &&
+ preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) ||
+ $token['type'] === HTML5::STARTTAG || $token['type'] === HTML5::ENDTAG) {
+ /* Parse error. Switch back to the main phase and reprocess the
+ token. */
+ $this->phase = self::MAIN_PHASE;
+ return $this->mainPhase($token);
+
+ /* An end-of-file token */
+ } elseif($token['type'] === HTML5::EOF) {
+ /* OMG DONE!! */
+ }
+ }
+
+ private function insertElement($token, $append = true, $check = false) {
+ // Proprietary workaround for libxml2's limitations with tag names
+ if ($check) {
+ // Slightly modified HTML5 tag-name modification,
+ // removing anything that's not an ASCII letter, digit, or hyphen
+ $token['name'] = preg_replace('/[^a-z0-9-]/i', '', $token['name']);
+ // Remove leading hyphens and numbers
+ $token['name'] = ltrim($token['name'], '-0..9');
+ // In theory, this should ever be needed, but just in case
+ if ($token['name'] === '') $token['name'] = 'span'; // arbitrary generic choice
+ }
+
+ $el = $this->dom->createElement($token['name']);
+
+ foreach($token['attr'] as $attr) {
+ if(!$el->hasAttribute($attr['name'])) {
+ $el->setAttribute($attr['name'], $attr['value']);
+ }
+ }
+
+ $this->appendToRealParent($el);
+ $this->stack[] = $el;
+
+ return $el;
+ }
+
+ private function insertText($data) {
+ $text = $this->dom->createTextNode($data);
+ $this->appendToRealParent($text);
+ }
+
+ private function insertComment($data) {
+ $comment = $this->dom->createComment($data);
+ $this->appendToRealParent($comment);
+ }
+
+ private function appendToRealParent($node) {
+ if($this->foster_parent === null) {
+ end($this->stack)->appendChild($node);
+
+ } elseif($this->foster_parent !== null) {
+ /* If the foster parent element is the parent element of the
+ last table element in the stack of open elements, then the new
+ node must be inserted immediately before the last table element
+ in the stack of open elements in the foster parent element;
+ otherwise, the new node must be appended to the foster parent
+ element. */
+ for($n = count($this->stack) - 1; $n >= 0; $n--) {
+ if($this->stack[$n]->nodeName === 'table' &&
+ $this->stack[$n]->parentNode !== null) {
+ $table = $this->stack[$n];
+ break;
+ }
+ }
+
+ if(isset($table) && $this->foster_parent->isSameNode($table->parentNode))
+ $this->foster_parent->insertBefore($node, $table);
+ else
+ $this->foster_parent->appendChild($node);
+
+ $this->foster_parent = null;
+ }
+ }
+
+ private function elementInScope($el, $table = false) {
+ if(is_array($el)) {
+ foreach($el as $element) {
+ if($this->elementInScope($element, $table)) {
+ return true;
+ }
+ }
+
+ return false;
+ }
+
+ $leng = count($this->stack);
+
+ for($n = 0; $n < $leng; $n++) {
+ /* 1. Initialise node to be the current node (the bottommost node of
+ the stack). */
+ $node = $this->stack[$leng - 1 - $n];
+
+ if($node->tagName === $el) {
+ /* 2. If node is the target node, terminate in a match state. */
+ return true;
+
+ } elseif($node->tagName === 'table') {
+ /* 3. Otherwise, if node is a table element, terminate in a failure
+ state. */
+ return false;
+
+ } elseif($table === true && in_array($node->tagName, array('caption', 'td',
+ 'th', 'button', 'marquee', 'object'))) {
+ /* 4. Otherwise, if the algorithm is the "has an element in scope"
+ variant (rather than the "has an element in table scope" variant),
+ and node is one of the following, terminate in a failure state. */
+ return false;
+
+ } elseif($node === $node->ownerDocument->documentElement) {
+ /* 5. Otherwise, if node is an html element (root element), terminate
+ in a failure state. (This can only happen if the node is the topmost
+ node of the stack of open elements, and prevents the next step from
+ being invoked if there are no more elements in the stack.) */
+ return false;
+ }
+
+ /* Otherwise, set node to the previous entry in the stack of open
+ elements and return to step 2. (This will never fail, since the loop
+ will always terminate in the previous step if the top of the stack
+ is reached.) */
+ }
+ }
+
+ private function reconstructActiveFormattingElements() {
+ /* 1. If there are no entries in the list of active formatting elements,
+ then there is nothing to reconstruct; stop this algorithm. */
+ $formatting_elements = count($this->a_formatting);
+
+ if($formatting_elements === 0) {
+ return false;
+ }
+
+ /* 3. Let entry be the last (most recently added) element in the list
+ of active formatting elements. */
+ $entry = end($this->a_formatting);
+
+ /* 2. If the last (most recently added) entry in the list of active
+ formatting elements is a marker, or if it is an element that is in the
+ stack of open elements, then there is nothing to reconstruct; stop this
+ algorithm. */
+ if($entry === self::MARKER || in_array($entry, $this->stack, true)) {
+ return false;
+ }
+
+ for($a = $formatting_elements - 1; $a >= 0; true) {
+ /* 4. If there are no entries before entry in the list of active
+ formatting elements, then jump to step 8. */
+ if($a === 0) {
+ $step_seven = false;
+ break;
+ }
+
+ /* 5. Let entry be the entry one earlier than entry in the list of
+ active formatting elements. */
+ $a--;
+ $entry = $this->a_formatting[$a];
+
+ /* 6. If entry is neither a marker nor an element that is also in
+ thetack of open elements, go to step 4. */
+ if($entry === self::MARKER || in_array($entry, $this->stack, true)) {
+ break;
+ }
+ }
+
+ while(true) {
+ /* 7. Let entry be the element one later than entry in the list of
+ active formatting elements. */
+ if(isset($step_seven) && $step_seven === true) {
+ $a++;
+ $entry = $this->a_formatting[$a];
+ }
+
+ /* 8. Perform a shallow clone of the element entry to obtain clone. */
+ $clone = $entry->cloneNode();
+
+ /* 9. Append clone to the current node and push it onto the stack
+ of open elements so that it is the new current node. */
+ end($this->stack)->appendChild($clone);
+ $this->stack[] = $clone;
+
+ /* 10. Replace the entry for entry in the list with an entry for
+ clone. */
+ $this->a_formatting[$a] = $clone;
+
+ /* 11. If the entry for clone in the list of active formatting
+ elements is not the last entry in the list, return to step 7. */
+ if(end($this->a_formatting) !== $clone) {
+ $step_seven = true;
+ } else {
+ break;
+ }
+ }
+ }
+
+ private function clearTheActiveFormattingElementsUpToTheLastMarker() {
+ /* When the steps below require the UA to clear the list of active
+ formatting elements up to the last marker, the UA must perform the
+ following steps: */
+
+ while(true) {
+ /* 1. Let entry be the last (most recently added) entry in the list
+ of active formatting elements. */
+ $entry = end($this->a_formatting);
+
+ /* 2. Remove entry from the list of active formatting elements. */
+ array_pop($this->a_formatting);
+
+ /* 3. If entry was a marker, then stop the algorithm at this point.
+ The list has been cleared up to the last marker. */
+ if($entry === self::MARKER) {
+ break;
+ }
+ }
+ }
+
+ private function generateImpliedEndTags($exclude = array()) {
+ /* When the steps below require the UA to generate implied end tags,
+ then, if the current node is a dd element, a dt element, an li element,
+ a p element, a td element, a th element, or a tr element, the UA must
+ act as if an end tag with the respective tag name had been seen and
+ then generate implied end tags again. */
+ $node = end($this->stack);
+ $elements = array_diff(array('dd', 'dt', 'li', 'p', 'td', 'th', 'tr'), $exclude);
+
+ while(in_array(end($this->stack)->nodeName, $elements)) {
+ array_pop($this->stack);
+ }
+ }
+
+ private function getElementCategory($node) {
+ $name = $node->tagName;
+ if(in_array($name, $this->special))
+ return self::SPECIAL;
+
+ elseif(in_array($name, $this->scoping))
+ return self::SCOPING;
+
+ elseif(in_array($name, $this->formatting))
+ return self::FORMATTING;
+
+ else
+ return self::PHRASING;
+ }
+
+ private function clearStackToTableContext($elements) {
+ /* When the steps above require the UA to clear the stack back to a
+ table context, it means that the UA must, while the current node is not
+ a table element or an html element, pop elements from the stack of open
+ elements. If this causes any elements to be popped from the stack, then
+ this is a parse error. */
+ while(true) {
+ $node = end($this->stack)->nodeName;
+
+ if(in_array($node, $elements)) {
+ break;
+ } else {
+ array_pop($this->stack);
+ }
+ }
+ }
+
+ private function resetInsertionMode() {
+ /* 1. Let last be false. */
+ $last = false;
+ $leng = count($this->stack);
+
+ for($n = $leng - 1; $n >= 0; $n--) {
+ /* 2. Let node be the last node in the stack of open elements. */
+ $node = $this->stack[$n];
+
+ /* 3. If node is the first node in the stack of open elements, then
+ set last to true. If the element whose innerHTML attribute is being
+ set is neither a td element nor a th element, then set node to the
+ element whose innerHTML attribute is being set. (innerHTML case) */
+ if($this->stack[0]->isSameNode($node)) {
+ $last = true;
+ }
+
+ /* 4. If node is a select element, then switch the insertion mode to
+ "in select" and abort these steps. (innerHTML case) */
+ if($node->nodeName === 'select') {
+ $this->mode = self::IN_SELECT;
+ break;
+
+ /* 5. If node is a td or th element, then switch the insertion mode
+ to "in cell" and abort these steps. */
+ } elseif($node->nodeName === 'td' || $node->nodeName === 'th') {
+ $this->mode = self::IN_CELL;
+ break;
+
+ /* 6. If node is a tr element, then switch the insertion mode to
+ "in row" and abort these steps. */
+ } elseif($node->nodeName === 'tr') {
+ $this->mode = self::IN_ROW;
+ break;
+
+ /* 7. If node is a tbody, thead, or tfoot element, then switch the
+ insertion mode to "in table body" and abort these steps. */
+ } elseif(in_array($node->nodeName, array('tbody', 'thead', 'tfoot'))) {
+ $this->mode = self::IN_TBODY;
+ break;
+
+ /* 8. If node is a caption element, then switch the insertion mode
+ to "in caption" and abort these steps. */
+ } elseif($node->nodeName === 'caption') {
+ $this->mode = self::IN_CAPTION;
+ break;
+
+ /* 9. If node is a colgroup element, then switch the insertion mode
+ to "in column group" and abort these steps. (innerHTML case) */
+ } elseif($node->nodeName === 'colgroup') {
+ $this->mode = self::IN_CGROUP;
+ break;
+
+ /* 10. If node is a table element, then switch the insertion mode
+ to "in table" and abort these steps. */
+ } elseif($node->nodeName === 'table') {
+ $this->mode = self::IN_TABLE;
+ break;
+
+ /* 11. If node is a head element, then switch the insertion mode
+ to "in body" ("in body"! not "in head"!) and abort these steps.
+ (innerHTML case) */
+ } elseif($node->nodeName === 'head') {
+ $this->mode = self::IN_BODY;
+ break;
+
+ /* 12. If node is a body element, then switch the insertion mode to
+ "in body" and abort these steps. */
+ } elseif($node->nodeName === 'body') {
+ $this->mode = self::IN_BODY;
+ break;
+
+ /* 13. If node is a frameset element, then switch the insertion
+ mode to "in frameset" and abort these steps. (innerHTML case) */
+ } elseif($node->nodeName === 'frameset') {
+ $this->mode = self::IN_FRAME;
+ break;
+
+ /* 14. If node is an html element, then: if the head element
+ pointer is null, switch the insertion mode to "before head",
+ otherwise, switch the insertion mode to "after head". In either
+ case, abort these steps. (innerHTML case) */
+ } elseif($node->nodeName === 'html') {
+ $this->mode = ($this->head_pointer === null)
+ ? self::BEFOR_HEAD
+ : self::AFTER_HEAD;
+
+ break;
+
+ /* 15. If last is true, then set the insertion mode to "in body"
+ and abort these steps. (innerHTML case) */
+ } elseif($last) {
+ $this->mode = self::IN_BODY;
+ break;
+ }
+ }
+ }
+
+ private function closeCell() {
+ /* If the stack of open elements has a td or th element in table scope,
+ then act as if an end tag token with that tag name had been seen. */
+ foreach(array('td', 'th') as $cell) {
+ if($this->elementInScope($cell, true)) {
+ $this->inCell(array(
+ 'name' => $cell,
+ 'type' => HTML5::ENDTAG
+ ));
+
+ break;
+ }
+ }
+ }
+
+ public function save() {
+ return $this->dom;
+ }
+}
+?>
diff --git a/plugin/htmlpurifier/standalone/HTMLPurifier/Printer.php b/plugin/htmlpurifier/standalone/HTMLPurifier/Printer.php
new file mode 100644
index 000000000..e7eb82e83
--- /dev/null
+++ b/plugin/htmlpurifier/standalone/HTMLPurifier/Printer.php
@@ -0,0 +1,176 @@
+getAll();
+ $context = new HTMLPurifier_Context();
+ $this->generator = new HTMLPurifier_Generator($config, $context);
+ }
+
+ /**
+ * Main function that renders object or aspect of that object
+ * @note Parameters vary depending on printer
+ */
+ // function render() {}
+
+ /**
+ * Returns a start tag
+ * @param $tag Tag name
+ * @param $attr Attribute array
+ */
+ protected function start($tag, $attr = array()) {
+ return $this->generator->generateFromToken(
+ new HTMLPurifier_Token_Start($tag, $attr ? $attr : array())
+ );
+ }
+
+ /**
+ * Returns an end teg
+ * @param $tag Tag name
+ */
+ protected function end($tag) {
+ return $this->generator->generateFromToken(
+ new HTMLPurifier_Token_End($tag)
+ );
+ }
+
+ /**
+ * Prints a complete element with content inside
+ * @param $tag Tag name
+ * @param $contents Element contents
+ * @param $attr Tag attributes
+ * @param $escape Bool whether or not to escape contents
+ */
+ protected function element($tag, $contents, $attr = array(), $escape = true) {
+ return $this->start($tag, $attr) .
+ ($escape ? $this->escape($contents) : $contents) .
+ $this->end($tag);
+ }
+
+ protected function elementEmpty($tag, $attr = array()) {
+ return $this->generator->generateFromToken(
+ new HTMLPurifier_Token_Empty($tag, $attr)
+ );
+ }
+
+ protected function text($text) {
+ return $this->generator->generateFromToken(
+ new HTMLPurifier_Token_Text($text)
+ );
+ }
+
+ /**
+ * Prints a simple key/value row in a table.
+ * @param $name Key
+ * @param $value Value
+ */
+ protected function row($name, $value) {
+ if (is_bool($value)) $value = $value ? 'On' : 'Off';
+ return
+ $this->start('tr') . "\n" .
+ $this->element('th', $name) . "\n" .
+ $this->element('td', $value) . "\n" .
+ $this->end('tr')
+ ;
+ }
+
+ /**
+ * Escapes a string for HTML output.
+ * @param $string String to escape
+ */
+ protected function escape($string) {
+ $string = HTMLPurifier_Encoder::cleanUTF8($string);
+ $string = htmlspecialchars($string, ENT_COMPAT, 'UTF-8');
+ return $string;
+ }
+
+ /**
+ * Takes a list of strings and turns them into a single list
+ * @param $array List of strings
+ * @param $polite Bool whether or not to add an end before the last
+ */
+ protected function listify($array, $polite = false) {
+ if (empty($array)) return 'None';
+ $ret = '';
+ $i = count($array);
+ foreach ($array as $value) {
+ $i--;
+ $ret .= $value;
+ if ($i > 0 && !($polite && $i == 1)) $ret .= ', ';
+ if ($polite && $i == 1) $ret .= 'and ';
+ }
+ return $ret;
+ }
+
+ /**
+ * Retrieves the class of an object without prefixes, as well as metadata
+ * @param $obj Object to determine class of
+ * @param $prefix Further prefix to remove
+ */
+ protected function getClass($obj, $sec_prefix = '') {
+ static $five = null;
+ if ($five === null) $five = version_compare(PHP_VERSION, '5', '>=');
+ $prefix = 'HTMLPurifier_' . $sec_prefix;
+ if (!$five) $prefix = strtolower($prefix);
+ $class = str_replace($prefix, '', get_class($obj));
+ $lclass = strtolower($class);
+ $class .= '(';
+ switch ($lclass) {
+ case 'enum':
+ $values = array();
+ foreach ($obj->valid_values as $value => $bool) {
+ $values[] = $value;
+ }
+ $class .= implode(', ', $values);
+ break;
+ case 'css_composite':
+ $values = array();
+ foreach ($obj->defs as $def) {
+ $values[] = $this->getClass($def, $sec_prefix);
+ }
+ $class .= implode(', ', $values);
+ break;
+ case 'css_multiple':
+ $class .= $this->getClass($obj->single, $sec_prefix) . ', ';
+ $class .= $obj->max;
+ break;
+ case 'css_denyelementdecorator':
+ $class .= $this->getClass($obj->def, $sec_prefix) . ', ';
+ $class .= $obj->element;
+ break;
+ case 'css_importantdecorator':
+ $class .= $this->getClass($obj->def, $sec_prefix);
+ if ($obj->allow) $class .= ', !important';
+ break;
+ }
+ $class .= ')';
+ return $class;
+ }
+
+}
+
+// vim: et sw=4 sts=4
diff --git a/plugin/htmlpurifier/standalone/HTMLPurifier/Printer/CSSDefinition.php b/plugin/htmlpurifier/standalone/HTMLPurifier/Printer/CSSDefinition.php
new file mode 100644
index 000000000..81f986590
--- /dev/null
+++ b/plugin/htmlpurifier/standalone/HTMLPurifier/Printer/CSSDefinition.php
@@ -0,0 +1,38 @@
+def = $config->getCSSDefinition();
+ $ret = '';
+
+ $ret .= $this->start('div', array('class' => 'HTMLPurifier_Printer'));
+ $ret .= $this->start('table');
+
+ $ret .= $this->element('caption', 'Properties ($info)');
+
+ $ret .= $this->start('thead');
+ $ret .= $this->start('tr');
+ $ret .= $this->element('th', 'Property', array('class' => 'heavy'));
+ $ret .= $this->element('th', 'Definition', array('class' => 'heavy', 'style' => 'width:auto;'));
+ $ret .= $this->end('tr');
+ $ret .= $this->end('thead');
+
+ ksort($this->def->info);
+ foreach ($this->def->info as $property => $obj) {
+ $name = $this->getClass($obj, 'AttrDef_');
+ $ret .= $this->row($property, $name);
+ }
+
+ $ret .= $this->end('table');
+ $ret .= $this->end('div');
+
+ return $ret;
+ }
+
+}
+
+// vim: et sw=4 sts=4
diff --git a/plugin/htmlpurifier/standalone/HTMLPurifier/Printer/ConfigForm.css b/plugin/htmlpurifier/standalone/HTMLPurifier/Printer/ConfigForm.css
new file mode 100644
index 000000000..3ff1a88aa
--- /dev/null
+++ b/plugin/htmlpurifier/standalone/HTMLPurifier/Printer/ConfigForm.css
@@ -0,0 +1,10 @@
+
+.hp-config {}
+
+.hp-config tbody th {text-align:right; padding-right:0.5em;}
+.hp-config thead, .hp-config .namespace {background:#3C578C; color:#FFF;}
+.hp-config .namespace th {text-align:center;}
+.hp-config .verbose {display:none;}
+.hp-config .controls {text-align:center;}
+
+/* vim: et sw=4 sts=4 */
diff --git a/plugin/htmlpurifier/standalone/HTMLPurifier/Printer/ConfigForm.js b/plugin/htmlpurifier/standalone/HTMLPurifier/Printer/ConfigForm.js
new file mode 100644
index 000000000..cba00c9b8
--- /dev/null
+++ b/plugin/htmlpurifier/standalone/HTMLPurifier/Printer/ConfigForm.js
@@ -0,0 +1,5 @@
+function toggleWriteability(id_of_patient, checked) {
+ document.getElementById(id_of_patient).disabled = checked;
+}
+
+// vim: et sw=4 sts=4
diff --git a/plugin/htmlpurifier/standalone/HTMLPurifier/Printer/ConfigForm.php b/plugin/htmlpurifier/standalone/HTMLPurifier/Printer/ConfigForm.php
new file mode 100644
index 000000000..02aa65689
--- /dev/null
+++ b/plugin/htmlpurifier/standalone/HTMLPurifier/Printer/ConfigForm.php
@@ -0,0 +1,368 @@
+docURL = $doc_url;
+ $this->name = $name;
+ $this->compress = $compress;
+ // initialize sub-printers
+ $this->fields[0] = new HTMLPurifier_Printer_ConfigForm_default();
+ $this->fields[HTMLPurifier_VarParser::BOOL] = new HTMLPurifier_Printer_ConfigForm_bool();
+ }
+
+ /**
+ * Sets default column and row size for textareas in sub-printers
+ * @param $cols Integer columns of textarea, null to use default
+ * @param $rows Integer rows of textarea, null to use default
+ */
+ public function setTextareaDimensions($cols = null, $rows = null) {
+ if ($cols) $this->fields['default']->cols = $cols;
+ if ($rows) $this->fields['default']->rows = $rows;
+ }
+
+ /**
+ * Retrieves styling, in case it is not accessible by webserver
+ */
+ public static function getCSS() {
+ return file_get_contents(HTMLPURIFIER_PREFIX . '/HTMLPurifier/Printer/ConfigForm.css');
+ }
+
+ /**
+ * Retrieves JavaScript, in case it is not accessible by webserver
+ */
+ public static function getJavaScript() {
+ return file_get_contents(HTMLPURIFIER_PREFIX . '/HTMLPurifier/Printer/ConfigForm.js');
+ }
+
+ /**
+ * Returns HTML output for a configuration form
+ * @param $config Configuration object of current form state, or an array
+ * where [0] has an HTML namespace and [1] is being rendered.
+ * @param $allowed Optional namespace(s) and directives to restrict form to.
+ */
+ public function render($config, $allowed = true, $render_controls = true) {
+ if (is_array($config) && isset($config[0])) {
+ $gen_config = $config[0];
+ $config = $config[1];
+ } else {
+ $gen_config = $config;
+ }
+
+ $this->config = $config;
+ $this->genConfig = $gen_config;
+ $this->prepareGenerator($gen_config);
+
+ $allowed = HTMLPurifier_Config::getAllowedDirectivesForForm($allowed, $config->def);
+ $all = array();
+ foreach ($allowed as $key) {
+ list($ns, $directive) = $key;
+ $all[$ns][$directive] = $config->get($ns .'.'. $directive);
+ }
+
+ $ret = '';
+ $ret .= $this->start('table', array('class' => 'hp-config'));
+ $ret .= $this->start('thead');
+ $ret .= $this->start('tr');
+ $ret .= $this->element('th', 'Directive', array('class' => 'hp-directive'));
+ $ret .= $this->element('th', 'Value', array('class' => 'hp-value'));
+ $ret .= $this->end('tr');
+ $ret .= $this->end('thead');
+ foreach ($all as $ns => $directives) {
+ $ret .= $this->renderNamespace($ns, $directives);
+ }
+ if ($render_controls) {
+ $ret .= $this->start('tbody');
+ $ret .= $this->start('tr');
+ $ret .= $this->start('td', array('colspan' => 2, 'class' => 'controls'));
+ $ret .= $this->elementEmpty('input', array('type' => 'submit', 'value' => 'Submit'));
+ $ret .= '[Reset]';
+ $ret .= $this->end('td');
+ $ret .= $this->end('tr');
+ $ret .= $this->end('tbody');
+ }
+ $ret .= $this->end('table');
+ return $ret;
+ }
+
+ /**
+ * Renders a single namespace
+ * @param $ns String namespace name
+ * @param $directive Associative array of directives to values
+ */
+ protected function renderNamespace($ns, $directives) {
+ $ret = '';
+ $ret .= $this->start('tbody', array('class' => 'namespace'));
+ $ret .= $this->start('tr');
+ $ret .= $this->element('th', $ns, array('colspan' => 2));
+ $ret .= $this->end('tr');
+ $ret .= $this->end('tbody');
+ $ret .= $this->start('tbody');
+ foreach ($directives as $directive => $value) {
+ $ret .= $this->start('tr');
+ $ret .= $this->start('th');
+ if ($this->docURL) {
+ $url = str_replace('%s', urlencode("$ns.$directive"), $this->docURL);
+ $ret .= $this->start('a', array('href' => $url));
+ }
+ $attr = array('for' => "{$this->name}:$ns.$directive");
+
+ // crop directive name if it's too long
+ if (!$this->compress || (strlen($directive) < $this->compress)) {
+ $directive_disp = $directive;
+ } else {
+ $directive_disp = substr($directive, 0, $this->compress - 2) . '...';
+ $attr['title'] = $directive;
+ }
+
+ $ret .= $this->element(
+ 'label',
+ $directive_disp,
+ // component printers must create an element with this id
+ $attr
+ );
+ if ($this->docURL) $ret .= $this->end('a');
+ $ret .= $this->end('th');
+
+ $ret .= $this->start('td');
+ $def = $this->config->def->info["$ns.$directive"];
+ if (is_int($def)) {
+ $allow_null = $def < 0;
+ $type = abs($def);
+ } else {
+ $type = $def->type;
+ $allow_null = isset($def->allow_null);
+ }
+ if (!isset($this->fields[$type])) $type = 0; // default
+ $type_obj = $this->fields[$type];
+ if ($allow_null) {
+ $type_obj = new HTMLPurifier_Printer_ConfigForm_NullDecorator($type_obj);
+ }
+ $ret .= $type_obj->render($ns, $directive, $value, $this->name, array($this->genConfig, $this->config));
+ $ret .= $this->end('td');
+ $ret .= $this->end('tr');
+ }
+ $ret .= $this->end('tbody');
+ return $ret;
+ }
+
+}
+
+/**
+ * Printer decorator for directives that accept null
+ */
+class HTMLPurifier_Printer_ConfigForm_NullDecorator extends HTMLPurifier_Printer {
+ /**
+ * Printer being decorated
+ */
+ protected $obj;
+ /**
+ * @param $obj Printer to decorate
+ */
+ public function __construct($obj) {
+ parent::__construct();
+ $this->obj = $obj;
+ }
+ public function render($ns, $directive, $value, $name, $config) {
+ if (is_array($config) && isset($config[0])) {
+ $gen_config = $config[0];
+ $config = $config[1];
+ } else {
+ $gen_config = $config;
+ }
+ $this->prepareGenerator($gen_config);
+
+ $ret = '';
+ $ret .= $this->start('label', array('for' => "$name:Null_$ns.$directive"));
+ $ret .= $this->element('span', "$ns.$directive:", array('class' => 'verbose'));
+ $ret .= $this->text(' Null/Disabled');
+ $ret .= $this->end('label');
+ $attr = array(
+ 'type' => 'checkbox',
+ 'value' => '1',
+ 'class' => 'null-toggle',
+ 'name' => "$name"."[Null_$ns.$directive]",
+ 'id' => "$name:Null_$ns.$directive",
+ 'onclick' => "toggleWriteability('$name:$ns.$directive',checked)" // INLINE JAVASCRIPT!!!!
+ );
+ if ($this->obj instanceof HTMLPurifier_Printer_ConfigForm_bool) {
+ // modify inline javascript slightly
+ $attr['onclick'] = "toggleWriteability('$name:Yes_$ns.$directive',checked);toggleWriteability('$name:No_$ns.$directive',checked)";
+ }
+ if ($value === null) $attr['checked'] = 'checked';
+ $ret .= $this->elementEmpty('input', $attr);
+ $ret .= $this->text(' or ');
+ $ret .= $this->elementEmpty('br');
+ $ret .= $this->obj->render($ns, $directive, $value, $name, array($gen_config, $config));
+ return $ret;
+ }
+}
+
+/**
+ * Swiss-army knife configuration form field printer
+ */
+class HTMLPurifier_Printer_ConfigForm_default extends HTMLPurifier_Printer {
+ public $cols = 18;
+ public $rows = 5;
+ public function render($ns, $directive, $value, $name, $config) {
+ if (is_array($config) && isset($config[0])) {
+ $gen_config = $config[0];
+ $config = $config[1];
+ } else {
+ $gen_config = $config;
+ }
+ $this->prepareGenerator($gen_config);
+ // this should probably be split up a little
+ $ret = '';
+ $def = $config->def->info["$ns.$directive"];
+ if (is_int($def)) {
+ $type = abs($def);
+ } else {
+ $type = $def->type;
+ }
+ if (is_array($value)) {
+ switch ($type) {
+ case HTMLPurifier_VarParser::LOOKUP:
+ $array = $value;
+ $value = array();
+ foreach ($array as $val => $b) {
+ $value[] = $val;
+ }
+ case HTMLPurifier_VarParser::ALIST:
+ $value = implode(PHP_EOL, $value);
+ break;
+ case HTMLPurifier_VarParser::HASH:
+ $nvalue = '';
+ foreach ($value as $i => $v) {
+ $nvalue .= "$i:$v" . PHP_EOL;
+ }
+ $value = $nvalue;
+ break;
+ default:
+ $value = '';
+ }
+ }
+ if ($type === HTMLPurifier_VarParser::MIXED) {
+ return 'Not supported';
+ $value = serialize($value);
+ }
+ $attr = array(
+ 'name' => "$name"."[$ns.$directive]",
+ 'id' => "$name:$ns.$directive"
+ );
+ if ($value === null) $attr['disabled'] = 'disabled';
+ if (isset($def->allowed)) {
+ $ret .= $this->start('select', $attr);
+ foreach ($def->allowed as $val => $b) {
+ $attr = array();
+ if ($value == $val) $attr['selected'] = 'selected';
+ $ret .= $this->element('option', $val, $attr);
+ }
+ $ret .= $this->end('select');
+ } elseif (
+ $type === HTMLPurifier_VarParser::TEXT ||
+ $type === HTMLPurifier_VarParser::ITEXT ||
+ $type === HTMLPurifier_VarParser::ALIST ||
+ $type === HTMLPurifier_VarParser::HASH ||
+ $type === HTMLPurifier_VarParser::LOOKUP
+ ) {
+ $attr['cols'] = $this->cols;
+ $attr['rows'] = $this->rows;
+ $ret .= $this->start('textarea', $attr);
+ $ret .= $this->text($value);
+ $ret .= $this->end('textarea');
+ } else {
+ $attr['value'] = $value;
+ $attr['type'] = 'text';
+ $ret .= $this->elementEmpty('input', $attr);
+ }
+ return $ret;
+ }
+}
+
+/**
+ * Bool form field printer
+ */
+class HTMLPurifier_Printer_ConfigForm_bool extends HTMLPurifier_Printer {
+ public function render($ns, $directive, $value, $name, $config) {
+ if (is_array($config) && isset($config[0])) {
+ $gen_config = $config[0];
+ $config = $config[1];
+ } else {
+ $gen_config = $config;
+ }
+ $this->prepareGenerator($gen_config);
+ $ret = '';
+ $ret .= $this->start('div', array('id' => "$name:$ns.$directive"));
+
+ $ret .= $this->start('label', array('for' => "$name:Yes_$ns.$directive"));
+ $ret .= $this->element('span', "$ns.$directive:", array('class' => 'verbose'));
+ $ret .= $this->text(' Yes');
+ $ret .= $this->end('label');
+
+ $attr = array(
+ 'type' => 'radio',
+ 'name' => "$name"."[$ns.$directive]",
+ 'id' => "$name:Yes_$ns.$directive",
+ 'value' => '1'
+ );
+ if ($value === true) $attr['checked'] = 'checked';
+ if ($value === null) $attr['disabled'] = 'disabled';
+ $ret .= $this->elementEmpty('input', $attr);
+
+ $ret .= $this->start('label', array('for' => "$name:No_$ns.$directive"));
+ $ret .= $this->element('span', "$ns.$directive:", array('class' => 'verbose'));
+ $ret .= $this->text(' No');
+ $ret .= $this->end('label');
+
+ $attr = array(
+ 'type' => 'radio',
+ 'name' => "$name"."[$ns.$directive]",
+ 'id' => "$name:No_$ns.$directive",
+ 'value' => '0'
+ );
+ if ($value === false) $attr['checked'] = 'checked';
+ if ($value === null) $attr['disabled'] = 'disabled';
+ $ret .= $this->elementEmpty('input', $attr);
+
+ $ret .= $this->end('div');
+
+ return $ret;
+ }
+}
+
+// vim: et sw=4 sts=4
diff --git a/plugin/htmlpurifier/standalone/HTMLPurifier/Printer/HTMLDefinition.php b/plugin/htmlpurifier/standalone/HTMLPurifier/Printer/HTMLDefinition.php
new file mode 100644
index 000000000..8a8f126b8
--- /dev/null
+++ b/plugin/htmlpurifier/standalone/HTMLPurifier/Printer/HTMLDefinition.php
@@ -0,0 +1,272 @@
+config =& $config;
+
+ $this->def = $config->getHTMLDefinition();
+
+ $ret .= $this->start('div', array('class' => 'HTMLPurifier_Printer'));
+
+ $ret .= $this->renderDoctype();
+ $ret .= $this->renderEnvironment();
+ $ret .= $this->renderContentSets();
+ $ret .= $this->renderInfo();
+
+ $ret .= $this->end('div');
+
+ return $ret;
+ }
+
+ /**
+ * Renders the Doctype table
+ */
+ protected function renderDoctype() {
+ $doctype = $this->def->doctype;
+ $ret = '';
+ $ret .= $this->start('table');
+ $ret .= $this->element('caption', 'Doctype');
+ $ret .= $this->row('Name', $doctype->name);
+ $ret .= $this->row('XML', $doctype->xml ? 'Yes' : 'No');
+ $ret .= $this->row('Default Modules', implode($doctype->modules, ', '));
+ $ret .= $this->row('Default Tidy Modules', implode($doctype->tidyModules, ', '));
+ $ret .= $this->end('table');
+ return $ret;
+ }
+
+
+ /**
+ * Renders environment table, which is miscellaneous info
+ */
+ protected function renderEnvironment() {
+ $def = $this->def;
+
+ $ret = '';
+
+ $ret .= $this->start('table');
+ $ret .= $this->element('caption', 'Environment');
+
+ $ret .= $this->row('Parent of fragment', $def->info_parent);
+ $ret .= $this->renderChildren($def->info_parent_def->child);
+ $ret .= $this->row('Block wrap name', $def->info_block_wrapper);
+
+ $ret .= $this->start('tr');
+ $ret .= $this->element('th', 'Global attributes');
+ $ret .= $this->element('td', $this->listifyAttr($def->info_global_attr),0,0);
+ $ret .= $this->end('tr');
+
+ $ret .= $this->start('tr');
+ $ret .= $this->element('th', 'Tag transforms');
+ $list = array();
+ foreach ($def->info_tag_transform as $old => $new) {
+ $new = $this->getClass($new, 'TagTransform_');
+ $list[] = "<$old> with $new";
+ }
+ $ret .= $this->element('td', $this->listify($list));
+ $ret .= $this->end('tr');
+
+ $ret .= $this->start('tr');
+ $ret .= $this->element('th', 'Pre-AttrTransform');
+ $ret .= $this->element('td', $this->listifyObjectList($def->info_attr_transform_pre));
+ $ret .= $this->end('tr');
+
+ $ret .= $this->start('tr');
+ $ret .= $this->element('th', 'Post-AttrTransform');
+ $ret .= $this->element('td', $this->listifyObjectList($def->info_attr_transform_post));
+ $ret .= $this->end('tr');
+
+ $ret .= $this->end('table');
+ return $ret;
+ }
+
+ /**
+ * Renders the Content Sets table
+ */
+ protected function renderContentSets() {
+ $ret = '';
+ $ret .= $this->start('table');
+ $ret .= $this->element('caption', 'Content Sets');
+ foreach ($this->def->info_content_sets as $name => $lookup) {
+ $ret .= $this->heavyHeader($name);
+ $ret .= $this->start('tr');
+ $ret .= $this->element('td', $this->listifyTagLookup($lookup));
+ $ret .= $this->end('tr');
+ }
+ $ret .= $this->end('table');
+ return $ret;
+ }
+
+ /**
+ * Renders the Elements ($info) table
+ */
+ protected function renderInfo() {
+ $ret = '';
+ $ret .= $this->start('table');
+ $ret .= $this->element('caption', 'Elements ($info)');
+ ksort($this->def->info);
+ $ret .= $this->heavyHeader('Allowed tags', 2);
+ $ret .= $this->start('tr');
+ $ret .= $this->element('td', $this->listifyTagLookup($this->def->info), array('colspan' => 2));
+ $ret .= $this->end('tr');
+ foreach ($this->def->info as $name => $def) {
+ $ret .= $this->start('tr');
+ $ret .= $this->element('th', "<$name>", array('class'=>'heavy', 'colspan' => 2));
+ $ret .= $this->end('tr');
+ $ret .= $this->start('tr');
+ $ret .= $this->element('th', 'Inline content');
+ $ret .= $this->element('td', $def->descendants_are_inline ? 'Yes' : 'No');
+ $ret .= $this->end('tr');
+ if (!empty($def->excludes)) {
+ $ret .= $this->start('tr');
+ $ret .= $this->element('th', 'Excludes');
+ $ret .= $this->element('td', $this->listifyTagLookup($def->excludes));
+ $ret .= $this->end('tr');
+ }
+ if (!empty($def->attr_transform_pre)) {
+ $ret .= $this->start('tr');
+ $ret .= $this->element('th', 'Pre-AttrTransform');
+ $ret .= $this->element('td', $this->listifyObjectList($def->attr_transform_pre));
+ $ret .= $this->end('tr');
+ }
+ if (!empty($def->attr_transform_post)) {
+ $ret .= $this->start('tr');
+ $ret .= $this->element('th', 'Post-AttrTransform');
+ $ret .= $this->element('td', $this->listifyObjectList($def->attr_transform_post));
+ $ret .= $this->end('tr');
+ }
+ if (!empty($def->auto_close)) {
+ $ret .= $this->start('tr');
+ $ret .= $this->element('th', 'Auto closed by');
+ $ret .= $this->element('td', $this->listifyTagLookup($def->auto_close));
+ $ret .= $this->end('tr');
+ }
+ $ret .= $this->start('tr');
+ $ret .= $this->element('th', 'Allowed attributes');
+ $ret .= $this->element('td',$this->listifyAttr($def->attr), array(), 0);
+ $ret .= $this->end('tr');
+
+ if (!empty($def->required_attr)) {
+ $ret .= $this->row('Required attributes', $this->listify($def->required_attr));
+ }
+
+ $ret .= $this->renderChildren($def->child);
+ }
+ $ret .= $this->end('table');
+ return $ret;
+ }
+
+ /**
+ * Renders a row describing the allowed children of an element
+ * @param $def HTMLPurifier_ChildDef of pertinent element
+ */
+ protected function renderChildren($def) {
+ $context = new HTMLPurifier_Context();
+ $ret = '';
+ $ret .= $this->start('tr');
+ $elements = array();
+ $attr = array();
+ if (isset($def->elements)) {
+ if ($def->type == 'strictblockquote') {
+ $def->validateChildren(array(), $this->config, $context);
+ }
+ $elements = $def->elements;
+ }
+ if ($def->type == 'chameleon') {
+ $attr['rowspan'] = 2;
+ } elseif ($def->type == 'empty') {
+ $elements = array();
+ } elseif ($def->type == 'table') {
+ $elements = array_flip(array('col', 'caption', 'colgroup', 'thead',
+ 'tfoot', 'tbody', 'tr'));
+ }
+ $ret .= $this->element('th', 'Allowed children', $attr);
+
+ if ($def->type == 'chameleon') {
+
+ $ret .= $this->element('td',
+ 'Block: ' .
+ $this->escape($this->listifyTagLookup($def->block->elements)),0,0);
+ $ret .= $this->end('tr');
+ $ret .= $this->start('tr');
+ $ret .= $this->element('td',
+ 'Inline: ' .
+ $this->escape($this->listifyTagLookup($def->inline->elements)),0,0);
+
+ } elseif ($def->type == 'custom') {
+
+ $ret .= $this->element('td', ''.ucfirst($def->type).': ' .
+ $def->dtd_regex);
+
+ } else {
+ $ret .= $this->element('td',
+ ''.ucfirst($def->type).': ' .
+ $this->escape($this->listifyTagLookup($elements)),0,0);
+ }
+ $ret .= $this->end('tr');
+ return $ret;
+ }
+
+ /**
+ * Listifies a tag lookup table.
+ * @param $array Tag lookup array in form of array('tagname' => true)
+ */
+ protected function listifyTagLookup($array) {
+ ksort($array);
+ $list = array();
+ foreach ($array as $name => $discard) {
+ if ($name !== '#PCDATA' && !isset($this->def->info[$name])) continue;
+ $list[] = $name;
+ }
+ return $this->listify($list);
+ }
+
+ /**
+ * Listifies a list of objects by retrieving class names and internal state
+ * @param $array List of objects
+ * @todo Also add information about internal state
+ */
+ protected function listifyObjectList($array) {
+ ksort($array);
+ $list = array();
+ foreach ($array as $discard => $obj) {
+ $list[] = $this->getClass($obj, 'AttrTransform_');
+ }
+ return $this->listify($list);
+ }
+
+ /**
+ * Listifies a hash of attributes to AttrDef classes
+ * @param $array Array hash in form of array('attrname' => HTMLPurifier_AttrDef)
+ */
+ protected function listifyAttr($array) {
+ ksort($array);
+ $list = array();
+ foreach ($array as $name => $obj) {
+ if ($obj === false) continue;
+ $list[] = "$name = " . $this->getClass($obj, 'AttrDef_') . '';
+ }
+ return $this->listify($list);
+ }
+
+ /**
+ * Creates a heavy header row
+ */
+ protected function heavyHeader($text, $num = 1) {
+ $ret = '';
+ $ret .= $this->start('tr');
+ $ret .= $this->element('th', $text, array('colspan' => $num, 'class' => 'heavy'));
+ $ret .= $this->end('tr');
+ return $ret;
+ }
+
+}
+
+// vim: et sw=4 sts=4