From: Mikael Nordfeldth Date: Thu, 28 Jan 2016 17:57:36 +0000 (+0100) Subject: Replace htmLawed with HTMLPurifier X-Git-Url: https://git.mxchange.org/?a=commitdiff_plain;h=7e6783bb8f5ed562c56af18aaa2e016ba95c81a7;p=quix0rs-gnu-social.git Replace htmLawed with HTMLPurifier --- diff --git a/actions/sitenoticeadminpanel.php b/actions/sitenoticeadminpanel.php index 145ae80d07..72c9f9a128 100644 --- a/actions/sitenoticeadminpanel.php +++ b/actions/sitenoticeadminpanel.php @@ -27,11 +27,7 @@ * @link http://status.net/ */ -if (!defined('STATUSNET')) { - exit(1); -} - -require_once INSTALLDIR.'/extlib/htmLawed/htmLawed.php'; +if (!defined('GNUSOCIAL')) { exit(1); } /** * Update the site-wide notice text @@ -114,13 +110,9 @@ class SitenoticeadminpanelAction extends AdminPanelAction } // scrub HTML input - - $config = array( - 'safe' => 1, - 'deny_attribute' => 'id,style,on*' - ); - - $siteNotice = htmLawed($siteNotice, $config); + require_once INSTALLDIR.'/extlib/HTMLPurifier/HTMLPurifier.auto.php'; + $purifier = new HTMLPurifier(); + $siteNotice = $purifier->purify($siteNotice); } } diff --git a/extlib/HTMLPurifier/CREDITS b/extlib/HTMLPurifier/CREDITS new file mode 100644 index 0000000000..7921b45af7 --- /dev/null +++ b/extlib/HTMLPurifier/CREDITS @@ -0,0 +1,9 @@ + +CREDITS + +Almost everything written by Edward Z. Yang (Ambush Commander). Lots of thanks +to the DevNetwork Community for their help (see docs/ref-devnetwork.html for +more details), Feyd especially (namely IPv6 and optimization). Thanks to RSnake +for letting me package his fantastic XSS cheatsheet for a smoketest. + + vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier.auto.php b/extlib/HTMLPurifier/HTMLPurifier.auto.php new file mode 100644 index 0000000000..1960c399f8 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier.auto.php @@ -0,0 +1,11 @@ +purify($html, $config); +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier.includes.php b/extlib/HTMLPurifier/HTMLPurifier.includes.php new file mode 100644 index 0000000000..fdb58c2d37 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier.includes.php @@ -0,0 +1,229 @@ + $attributes) { + $allowed_elements[$element] = true; + foreach ($attributes as $attribute => $x) { + $allowed_attributes["$element.$attribute"] = true; + } + } + $config->set('HTML.AllowedElements', $allowed_elements); + $config->set('HTML.AllowedAttributes', $allowed_attributes); + if ($allowed_protocols !== null) { + $config->set('URI.AllowedSchemes', $allowed_protocols); + } + $purifier = new HTMLPurifier($config); + return $purifier->purify($string); +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier.path.php b/extlib/HTMLPurifier/HTMLPurifier.path.php new file mode 100644 index 0000000000..39b1b65319 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier.path.php @@ -0,0 +1,11 @@ +config = HTMLPurifier_Config::create($config); + $this->strategy = new HTMLPurifier_Strategy_Core(); + } + + /** + * Adds a filter to process the output. First come first serve + * + * @param HTMLPurifier_Filter $filter HTMLPurifier_Filter object + */ + public function addFilter($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 string $html String of HTML to purify + * @param HTMLPurifier_Config $config Config object for this operation, + * if omitted, defaults to the config object specified during this + * object's construction. The parameter can also be any type + * that HTMLPurifier_Config::create() supports. + * + * @return string Purified HTML + */ + public function purify($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 string[] $array_of_html Array of html snippets + * @param HTMLPurifier_Config $config Optional config object for this operation. + * See HTMLPurifier::purify() for more details. + * + * @return string[] Array of purified HTML + */ + public function purifyArray($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 HTMLPurifier|HTMLPurifier_Config $prototype Optional prototype + * HTMLPurifier instance to overload singleton with, + * or HTMLPurifier_Config instance to configure the + * generated version with. + * + * @return HTMLPurifier + */ + public static function instance($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; + } + + /** + * Singleton for enforcing just one HTML Purifier in your system + * + * @param HTMLPurifier|HTMLPurifier_Config $prototype Optional prototype + * HTMLPurifier instance to overload singleton with, + * or HTMLPurifier_Config instance to configure the + * generated version with. + * + * @return HTMLPurifier + * @note Backwards compatibility, see instance() + */ + public static function getInstance($prototype = null) + { + return HTMLPurifier::instance($prototype); + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier.safe-includes.php b/extlib/HTMLPurifier/HTMLPurifier.safe-includes.php new file mode 100644 index 0000000000..9dea6d1ed5 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier.safe-includes.php @@ -0,0 +1,223 @@ +getHTMLDefinition(); + $parent = new HTMLPurifier_Token_Start($definition->info_parent); + $stack = array($parent->toNode()); + foreach ($tokens as $token) { + $token->skip = null; // [MUT] + $token->carryover = null; // [MUT] + if ($token instanceof HTMLPurifier_Token_End) { + $token->start = null; // [MUT] + $r = array_pop($stack); + assert($r->name === $token->name); + assert(empty($token->attr)); + $r->endCol = $token->col; + $r->endLine = $token->line; + $r->endArmor = $token->armor; + continue; + } + $node = $token->toNode(); + $stack[count($stack)-1]->children[] = $node; + if ($token instanceof HTMLPurifier_Token_Start) { + $stack[] = $node; + } + } + assert(count($stack) == 1); + return $stack[0]; + } + + public static function flatten($node, $config, $context) { + $level = 0; + $nodes = array($level => new HTMLPurifier_Queue(array($node))); + $closingTokens = array(); + $tokens = array(); + do { + while (!$nodes[$level]->isEmpty()) { + $node = $nodes[$level]->shift(); // FIFO + list($start, $end) = $node->toTokenPair(); + if ($level > 0) { + $tokens[] = $start; + } + if ($end !== NULL) { + $closingTokens[$level][] = $end; + } + if ($node instanceof HTMLPurifier_Node_Element) { + $level++; + $nodes[$level] = new HTMLPurifier_Queue(); + foreach ($node->children as $childNode) { + $nodes[$level]->push($childNode); + } + } + } + $level--; + if ($level && isset($closingTokens[$level])) { + while ($token = array_pop($closingTokens[$level])) { + $tokens[] = $token; + } + } + } while ($level > 0); + return $tokens; + } +} diff --git a/extlib/HTMLPurifier/HTMLPurifier/AttrCollections.php b/extlib/HTMLPurifier/HTMLPurifier/AttrCollections.php new file mode 100644 index 0000000000..4f6c2e39a2 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/AttrCollections.php @@ -0,0 +1,143 @@ +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], $attr_types); + } + } + + /** + * Takes a reference to an attribute associative array and performs + * all inclusions specified by the zero index. + * @param array &$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 array &$attr Reference to attribute array + * @param HTMLPurifier_AttrTypes $attr_types HTMLPurifier_AttrTypes instance + */ + public function expandIdentifiers(&$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[$def_i]); + } + } + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/AttrDef.php b/extlib/HTMLPurifier/HTMLPurifier/AttrDef.php new file mode 100644 index 0000000000..5ac06522b9 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/AttrDef.php @@ -0,0 +1,138 @@ + by removing + * leading and trailing whitespace, ignoring line feeds, and replacing + * carriage returns and tabs with spaces. While most useful for HTML + * attributes specified as CDATA, it can also be applied to most CSS + * values. + * + * @note This method is not entirely standards compliant, as trim() removes + * more types of whitespace than specified in the spec. In practice, + * this is rarely a problem, as those extra characters usually have + * already been removed by HTMLPurifier_Encoder. + * + * @warning This processing is inconsistent with XML's whitespace handling + * as specified by section 3.3.3 and referenced XHTML 1.0 section + * 4.7. However, note that we are NOT necessarily + * parsing XML, thus, this behavior may still be correct. We + * assume that newlines have been normalized. + */ + public function parseCDATA($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 String construction info + * @return HTMLPurifier_AttrDef 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! + * @param string $string a CSS colour definition + * @return string + */ + protected function mungeRgb($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 $ret; + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/AttrDef/CSS.php b/extlib/HTMLPurifier/HTMLPurifier/AttrDef/CSS.php new file mode 100644 index 0000000000..02c1641fb2 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/AttrDef/CSS.php @@ -0,0 +1,106 @@ +parseCDATA($css); + + $definition = $config->getCSSDefinition(); + + // we're going to break the spec and explode by semicolons. + // This is because semicolon rarely appears in escaped form + // Doing this is generally flaky but fast + // IT MIGHT APPEAR IN URIs, see HTMLPurifier_AttrDef_CSSURI + // for details + + $declarations = explode(';', $css); + $propvalues = array(); + + /** + * Name of the current CSS property being validated. + */ + $property = false; + $context->register('CurrentCSSProperty', $property); + + foreach ($declarations as $declaration) { + if (!$declaration) { + continue; + } + if (!strpos($declaration, ':')) { + continue; + } + list($property, $value) = explode(':', $declaration, 2); + $property = trim($property); + $value = trim($value); + $ok = false; + do { + if (isset($definition->info[$property])) { + $ok = true; + break; + } + if (ctype_lower($property)) { + break; + } + $property = strtolower($property); + if (isset($definition->info[$property])) { + $ok = true; + break; + } + } while (0); + if (!$ok) { + continue; + } + // inefficient call, since the validator will do this again + if (strtolower(trim($value)) !== 'inherit') { + // inherit works for everything (but only on the base property) + $result = $definition->info[$property]->validate( + $value, + $config, + $context + ); + } else { + $result = 'inherit'; + } + if ($result === false) { + continue; + } + $propvalues[$property] = $result; + } + + $context->destroy('CurrentCSSProperty'); + + // procedure does not write the new CSS simultaneously, so it's + // slightly inefficient, but it's the only way of getting rid of + // duplicates. Perhaps config to optimize it, but not now. + + $new_declarations = ''; + foreach ($propvalues as $prop => $value) { + $new_declarations .= "$prop:$value;"; + } + + return $new_declarations ? $new_declarations : false; + + } + +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/AttrDef/CSS/AlphaValue.php b/extlib/HTMLPurifier/HTMLPurifier/AttrDef/CSS/AlphaValue.php new file mode 100644 index 0000000000..af2b83dff8 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/AttrDef/CSS/AlphaValue.php @@ -0,0 +1,34 @@ + 1.0) { + $result = '1'; + } + return $result; + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/AttrDef/CSS/Background.php b/extlib/HTMLPurifier/HTMLPurifier/AttrDef/CSS/Background.php new file mode 100644 index 0000000000..7f1ea3b0f1 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/AttrDef/CSS/Background.php @@ -0,0 +1,111 @@ +getCSSDefinition(); + $this->info['background-color'] = $def->info['background-color']; + $this->info['background-image'] = $def->info['background-image']; + $this->info['background-repeat'] = $def->info['background-repeat']; + $this->info['background-attachment'] = $def->info['background-attachment']; + $this->info['background-position'] = $def->info['background-position']; + } + + /** + * @param string $string + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool|string + */ + public function validate($string, $config, $context) + { + // regular pre-processing + $string = $this->parseCDATA($string); + if ($string === '') { + return false; + } + + // munge rgb() decl if necessary + $string = $this->mungeRgb($string); + + // assumes URI doesn't have spaces in it + $bits = explode(' ', $string); // bits to process + + $caught = array(); + $caught['color'] = false; + $caught['image'] = false; + $caught['repeat'] = false; + $caught['attachment'] = false; + $caught['position'] = false; + + $i = 0; // number of catches + + foreach ($bits as $bit) { + if ($bit === '') { + continue; + } + foreach ($caught as $key => $status) { + if ($key != 'position') { + if ($status !== false) { + continue; + } + $r = $this->info['background-' . $key]->validate($bit, $config, $context); + } else { + $r = $bit; + } + if ($r === false) { + continue; + } + if ($key == 'position') { + if ($caught[$key] === false) { + $caught[$key] = ''; + } + $caught[$key] .= $r . ' '; + } else { + $caught[$key] = $r; + } + $i++; + break; + } + } + + if (!$i) { + return false; + } + if ($caught['position'] !== false) { + $caught['position'] = $this->info['background-position']-> + validate($caught['position'], $config, $context); + } + + $ret = array(); + foreach ($caught as $value) { + if ($value === false) { + continue; + } + $ret[] = $value; + } + + if (empty($ret)) { + return false; + } + return implode(' ', $ret); + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/AttrDef/CSS/BackgroundPosition.php b/extlib/HTMLPurifier/HTMLPurifier/AttrDef/CSS/BackgroundPosition.php new file mode 100644 index 0000000000..4580ef5a91 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/AttrDef/CSS/BackgroundPosition.php @@ -0,0 +1,157 @@ + | | left | center | right + ] + [ + | | top | center | bottom + ]? + ] | + [ // this signifies that the vertical and horizontal adjectives + // can be arbitrarily ordered, however, there can only be two, + // one of each, or none at all + [ + left | center | right + ] || + [ + top | center | bottom + ] + ] + top, left = 0% + center, (none) = 50% + bottom, right = 100% +*/ + +/* QuirksMode says: + keyword + length/percentage must be ordered correctly, as per W3C + + Internet Explorer and Opera, however, support arbitrary ordering. We + should fix it up. + + Minor issue though, not strictly necessary. +*/ + +// control freaks may appreciate the ability to convert these to +// percentages or something, but it's not necessary + +/** + * Validates the value of background-position. + */ +class HTMLPurifier_AttrDef_CSS_BackgroundPosition extends HTMLPurifier_AttrDef +{ + + /** + * @type HTMLPurifier_AttrDef_CSS_Length + */ + protected $length; + + /** + * @type HTMLPurifier_AttrDef_CSS_Percentage + */ + protected $percentage; + + public function __construct() + { + $this->length = new HTMLPurifier_AttrDef_CSS_Length(); + $this->percentage = new HTMLPurifier_AttrDef_CSS_Percentage(); + } + + /** + * @param string $string + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool|string + */ + public function validate($string, $config, $context) + { + $string = $this->parseCDATA($string); + $bits = explode(' ', $string); + + $keywords = array(); + $keywords['h'] = false; // left, right + $keywords['v'] = false; // top, bottom + $keywords['ch'] = false; // center (first word) + $keywords['cv'] = false; // center (second word) + $measures = array(); + + $i = 0; + + $lookup = array( + 'top' => 'v', + 'bottom' => 'v', + 'left' => 'h', + 'right' => 'h', + 'center' => 'c' + ); + + foreach ($bits as $bit) { + if ($bit === '') { + continue; + } + + // test for keyword + $lbit = ctype_lower($bit) ? $bit : strtolower($bit); + if (isset($lookup[$lbit])) { + $status = $lookup[$lbit]; + if ($status == 'c') { + if ($i == 0) { + $status = 'ch'; + } else { + $status = 'cv'; + } + } + $keywords[$status] = $lbit; + $i++; + } + + // test for length + $r = $this->length->validate($bit, $config, $context); + if ($r !== false) { + $measures[] = $r; + $i++; + } + + // test for percentage + $r = $this->percentage->validate($bit, $config, $context); + if ($r !== false) { + $measures[] = $r; + $i++; + } + } + + if (!$i) { + return false; + } // no valid values were caught + + $ret = array(); + + // first keyword + if ($keywords['h']) { + $ret[] = $keywords['h']; + } elseif ($keywords['ch']) { + $ret[] = $keywords['ch']; + $keywords['cv'] = false; // prevent re-use: center = center center + } elseif (count($measures)) { + $ret[] = array_shift($measures); + } + + if ($keywords['v']) { + $ret[] = $keywords['v']; + } elseif ($keywords['cv']) { + $ret[] = $keywords['cv']; + } elseif (count($measures)) { + $ret[] = array_shift($measures); + } + + if (empty($ret)) { + return false; + } + return implode(' ', $ret); + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/AttrDef/CSS/Border.php b/extlib/HTMLPurifier/HTMLPurifier/AttrDef/CSS/Border.php new file mode 100644 index 0000000000..16243ba1ed --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/AttrDef/CSS/Border.php @@ -0,0 +1,56 @@ +getCSSDefinition(); + $this->info['border-width'] = $def->info['border-width']; + $this->info['border-style'] = $def->info['border-style']; + $this->info['border-top-color'] = $def->info['border-top-color']; + } + + /** + * @param string $string + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool|string + */ + public function validate($string, $config, $context) + { + $string = $this->parseCDATA($string); + $string = $this->mungeRgb($string); + $bits = explode(' ', $string); + $done = array(); // segments we've finished + $ret = ''; // return value + foreach ($bits as $bit) { + foreach ($this->info as $propname => $validator) { + if (isset($done[$propname])) { + continue; + } + $r = $validator->validate($bit, $config, $context); + if ($r !== false) { + $ret .= $r . ' '; + $done[$propname] = true; + break; + } + } + } + return rtrim($ret); + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/AttrDef/CSS/Color.php b/extlib/HTMLPurifier/HTMLPurifier/AttrDef/CSS/Color.php new file mode 100644 index 0000000000..16d2a6b98c --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/AttrDef/CSS/Color.php @@ -0,0 +1,105 @@ +get('Core.ColorKeywords'); + } + + $color = trim($color); + if ($color === '') { + return false; + } + + $lower = strtolower($color); + if (isset($colors[$lower])) { + return $colors[$lower]; + } + + if (strpos($color, 'rgb(') !== false) { + // rgb literal handling + $length = strlen($color); + if (strpos($color, ')') !== $length - 1) { + return false; + } + $triad = substr($color, 4, $length - 4 - 1); + $parts = explode(',', $triad); + if (count($parts) !== 3) { + return false; + } + $type = false; // to ensure that they're all the same type + $new_parts = array(); + foreach ($parts as $part) { + $part = trim($part); + if ($part === '') { + return false; + } + $length = strlen($part); + if ($part[$length - 1] === '%') { + // handle percents + if (!$type) { + $type = 'percentage'; + } elseif ($type !== 'percentage') { + return false; + } + $num = (float)substr($part, 0, $length - 1); + if ($num < 0) { + $num = 0; + } + if ($num > 100) { + $num = 100; + } + $new_parts[] = "$num%"; + } else { + // handle integers + if (!$type) { + $type = 'integer'; + } elseif ($type !== 'integer') { + return false; + } + $num = (int)$part; + if ($num < 0) { + $num = 0; + } + if ($num > 255) { + $num = 255; + } + $new_parts[] = (string)$num; + } + } + $new_triad = implode(',', $new_parts); + $color = "rgb($new_triad)"; + } else { + // hexadecimal handling + if ($color[0] === '#') { + $hex = substr($color, 1); + } else { + $hex = $color; + $color = '#' . $color; + } + $length = strlen($hex); + if ($length !== 3 && $length !== 6) { + return false; + } + if (!ctype_xdigit($hex)) { + return false; + } + } + return $color; + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/AttrDef/CSS/Composite.php b/extlib/HTMLPurifier/HTMLPurifier/AttrDef/CSS/Composite.php new file mode 100644 index 0000000000..9c1750554f --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/AttrDef/CSS/Composite.php @@ -0,0 +1,48 @@ +defs = $defs; + } + + /** + * @param string $string + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool|string + */ + public function validate($string, $config, $context) + { + foreach ($this->defs as $i => $def) { + $result = $this->defs[$i]->validate($string, $config, $context); + if ($result !== false) { + return $result; + } + } + return false; + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/AttrDef/CSS/DenyElementDecorator.php b/extlib/HTMLPurifier/HTMLPurifier/AttrDef/CSS/DenyElementDecorator.php new file mode 100644 index 0000000000..9d77cc9aaf --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/AttrDef/CSS/DenyElementDecorator.php @@ -0,0 +1,44 @@ +def = $def; + $this->element = $element; + } + + /** + * Checks if CurrentToken is set and equal to $this->element + * @param string $string + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool|string + */ + public function validate($string, $config, $context) + { + $token = $context->get('CurrentToken', true); + if ($token && $token->name == $this->element) { + return false; + } + return $this->def->validate($string, $config, $context); + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/AttrDef/CSS/Filter.php b/extlib/HTMLPurifier/HTMLPurifier/AttrDef/CSS/Filter.php new file mode 100644 index 0000000000..bde4c3301f --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/AttrDef/CSS/Filter.php @@ -0,0 +1,77 @@ +intValidator = new HTMLPurifier_AttrDef_Integer(); + } + + /** + * @param string $value + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool|string + */ + public function validate($value, $config, $context) + { + $value = $this->parseCDATA($value); + if ($value === 'none') { + return $value; + } + // if we looped this we could support multiple filters + $function_length = strcspn($value, '('); + $function = trim(substr($value, 0, $function_length)); + if ($function !== 'alpha' && + $function !== 'Alpha' && + $function !== 'progid:DXImageTransform.Microsoft.Alpha' + ) { + return false; + } + $cursor = $function_length + 1; + $parameters_length = strcspn($value, ')', $cursor); + $parameters = substr($value, $cursor, $parameters_length); + $params = explode(',', $parameters); + $ret_params = array(); + $lookup = array(); + foreach ($params as $param) { + list($key, $value) = explode('=', $param); + $key = trim($key); + $value = trim($value); + if (isset($lookup[$key])) { + continue; + } + if ($key !== 'opacity') { + continue; + } + $value = $this->intValidator->validate($value, $config, $context); + if ($value === false) { + continue; + } + $int = (int)$value; + if ($int > 100) { + $value = '100'; + } + if ($int < 0) { + $value = '0'; + } + $ret_params[] = "$key=$value"; + $lookup[$key] = true; + } + $ret_parameters = implode(',', $ret_params); + $ret_function = "$function($ret_parameters)"; + return $ret_function; + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/AttrDef/CSS/Font.php b/extlib/HTMLPurifier/HTMLPurifier/AttrDef/CSS/Font.php new file mode 100644 index 0000000000..579b97ef1c --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/AttrDef/CSS/Font.php @@ -0,0 +1,176 @@ +getCSSDefinition(); + $this->info['font-style'] = $def->info['font-style']; + $this->info['font-variant'] = $def->info['font-variant']; + $this->info['font-weight'] = $def->info['font-weight']; + $this->info['font-size'] = $def->info['font-size']; + $this->info['line-height'] = $def->info['line-height']; + $this->info['font-family'] = $def->info['font-family']; + } + + /** + * @param string $string + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool|string + */ + public function validate($string, $config, $context) + { + static $system_fonts = array( + 'caption' => true, + 'icon' => true, + 'menu' => true, + 'message-box' => true, + 'small-caption' => true, + 'status-bar' => true + ); + + // regular pre-processing + $string = $this->parseCDATA($string); + if ($string === '') { + return false; + } + + // check if it's one of the keywords + $lowercase_string = strtolower($string); + if (isset($system_fonts[$lowercase_string])) { + return $lowercase_string; + } + + $bits = explode(' ', $string); // bits to process + $stage = 0; // this indicates what we're looking for + $caught = array(); // which stage 0 properties have we caught? + $stage_1 = array('font-style', 'font-variant', 'font-weight'); + $final = ''; // output + + for ($i = 0, $size = count($bits); $i < $size; $i++) { + if ($bits[$i] === '') { + continue; + } + switch ($stage) { + case 0: // attempting to catch font-style, font-variant or font-weight + foreach ($stage_1 as $validator_name) { + if (isset($caught[$validator_name])) { + continue; + } + $r = $this->info[$validator_name]->validate( + $bits[$i], + $config, + $context + ); + if ($r !== false) { + $final .= $r . ' '; + $caught[$validator_name] = true; + break; + } + } + // all three caught, continue on + if (count($caught) >= 3) { + $stage = 1; + } + if ($r !== false) { + break; + } + case 1: // attempting to catch font-size and perhaps line-height + $found_slash = false; + if (strpos($bits[$i], '/') !== false) { + list($font_size, $line_height) = + explode('/', $bits[$i]); + if ($line_height === '') { + // ooh, there's a space after the slash! + $line_height = false; + $found_slash = true; + } + } else { + $font_size = $bits[$i]; + $line_height = false; + } + $r = $this->info['font-size']->validate( + $font_size, + $config, + $context + ); + if ($r !== false) { + $final .= $r; + // attempt to catch line-height + if ($line_height === false) { + // we need to scroll forward + for ($j = $i + 1; $j < $size; $j++) { + if ($bits[$j] === '') { + continue; + } + if ($bits[$j] === '/') { + if ($found_slash) { + return false; + } else { + $found_slash = true; + continue; + } + } + $line_height = $bits[$j]; + break; + } + } else { + // slash already found + $found_slash = true; + $j = $i; + } + if ($found_slash) { + $i = $j; + $r = $this->info['line-height']->validate( + $line_height, + $config, + $context + ); + if ($r !== false) { + $final .= '/' . $r; + } + } + $final .= ' '; + $stage = 2; + break; + } + return false; + case 2: // attempting to catch font-family + $font_family = + implode(' ', array_slice($bits, $i, $size - $i)); + $r = $this->info['font-family']->validate( + $font_family, + $config, + $context + ); + if ($r !== false) { + $final .= $r . ' '; + // processing completed successfully + return rtrim($final); + } + return false; + } + } + return false; + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/AttrDef/CSS/FontFamily.php b/extlib/HTMLPurifier/HTMLPurifier/AttrDef/CSS/FontFamily.php new file mode 100644 index 0000000000..74e24c8816 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/AttrDef/CSS/FontFamily.php @@ -0,0 +1,219 @@ +mask = '_- '; + for ($c = 'a'; $c <= 'z'; $c++) { + $this->mask .= $c; + } + for ($c = 'A'; $c <= 'Z'; $c++) { + $this->mask .= $c; + } + for ($c = '0'; $c <= '9'; $c++) { + $this->mask .= $c; + } // cast-y, but should be fine + // special bytes used by UTF-8 + for ($i = 0x80; $i <= 0xFF; $i++) { + // We don't bother excluding invalid bytes in this range, + // because the our restriction of well-formed UTF-8 will + // prevent these from ever occurring. + $this->mask .= chr($i); + } + + /* + PHP's internal strcspn implementation is + O(length of string * length of mask), making it inefficient + for large masks. However, it's still faster than + preg_match 8) + for (p = s1;;) { + spanp = s2; + do { + if (*spanp == c || p == s1_end) { + return p - s1; + } + } while (spanp++ < (s2_end - 1)); + c = *++p; + } + */ + // possible optimization: invert the mask. + } + + /** + * @param string $string + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool|string + */ + public function validate($string, $config, $context) + { + static $generic_names = array( + 'serif' => true, + 'sans-serif' => true, + 'monospace' => true, + 'fantasy' => true, + 'cursive' => true + ); + $allowed_fonts = $config->get('CSS.AllowedFonts'); + + // assume that no font names contain commas in them + $fonts = explode(',', $string); + $final = ''; + foreach ($fonts as $font) { + $font = trim($font); + if ($font === '') { + continue; + } + // match a generic name + if (isset($generic_names[$font])) { + if ($allowed_fonts === null || isset($allowed_fonts[$font])) { + $final .= $font . ', '; + } + continue; + } + // match a quoted name + if ($font[0] === '"' || $font[0] === "'") { + $length = strlen($font); + if ($length <= 2) { + continue; + } + $quote = $font[0]; + if ($font[$length - 1] !== $quote) { + continue; + } + $font = substr($font, 1, $length - 2); + } + + $font = $this->expandCSSEscape($font); + + // $font is a pure representation of the font name + + if ($allowed_fonts !== null && !isset($allowed_fonts[$font])) { + continue; + } + + if (ctype_alnum($font) && $font !== '') { + // very simple font, allow it in unharmed + $final .= $font . ', '; + continue; + } + + // bugger out on whitespace. form feed (0C) really + // shouldn't show up regardless + $font = str_replace(array("\n", "\t", "\r", "\x0C"), ' ', $font); + + // Here, there are various classes of characters which need + // to be treated differently: + // - Alphanumeric characters are essentially safe. We + // handled these above. + // - Spaces require quoting, though most parsers will do + // the right thing if there aren't any characters that + // can be misinterpreted + // - Dashes rarely occur, but they fairly unproblematic + // for parsing/rendering purposes. + // The above characters cover the majority of Western font + // names. + // - Arbitrary Unicode characters not in ASCII. Because + // most parsers give little thought to Unicode, treatment + // of these codepoints is basically uniform, even for + // punctuation-like codepoints. These characters can + // show up in non-Western pages and are supported by most + // major browsers, for example: "ＭＳ 明朝" is a + // legitimate font-name + // . See + // the CSS3 spec for more examples: + // + // You can see live samples of these on the Internet: + // + // However, most of these fonts have ASCII equivalents: + // for example, 'MS Mincho', and it's considered + // professional to use ASCII font names instead of + // Unicode font names. Thanks Takeshi Terada for + // providing this information. + // The following characters, to my knowledge, have not been + // used to name font names. + // - Single quote. While theoretically you might find a + // font name that has a single quote in its name (serving + // as an apostrophe, e.g. Dave's Scribble), I haven't + // been able to find any actual examples of this. + // Internet Explorer's cssText translation (which I + // believe is invoked by innerHTML) normalizes any + // quoting to single quotes, and fails to escape single + // quotes. (Note that this is not IE's behavior for all + // CSS properties, just some sort of special casing for + // font-family). So a single quote *cannot* be used + // safely in the font-family context if there will be an + // innerHTML/cssText translation. Note that Firefox 3.x + // does this too. + // - Double quote. In IE, these get normalized to + // single-quotes, no matter what the encoding. (Fun + // fact, in IE8, the 'content' CSS property gained + // support, where they special cased to preserve encoded + // double quotes, but still translate unadorned double + // quotes into single quotes.) So, because their + // fixpoint behavior is identical to single quotes, they + // cannot be allowed either. Firefox 3.x displays + // single-quote style behavior. + // - Backslashes are reduced by one (so \\ -> \) every + // iteration, so they cannot be used safely. This shows + // up in IE7, IE8 and FF3 + // - Semicolons, commas and backticks are handled properly. + // - The rest of the ASCII punctuation is handled properly. + // We haven't checked what browsers do to unadorned + // versions, but this is not important as long as the + // browser doesn't /remove/ surrounding quotes (as IE does + // for HTML). + // + // With these results in hand, we conclude that there are + // various levels of safety: + // - Paranoid: alphanumeric, spaces and dashes(?) + // - International: Paranoid + non-ASCII Unicode + // - Edgy: Everything except quotes, backslashes + // - NoJS: Standards compliance, e.g. sod IE. Note that + // with some judicious character escaping (since certain + // types of escaping doesn't work) this is theoretically + // OK as long as innerHTML/cssText is not called. + // We believe that international is a reasonable default + // (that we will implement now), and once we do more + // extensive research, we may feel comfortable with dropping + // it down to edgy. + + // Edgy: alphanumeric, spaces, dashes, underscores and Unicode. Use of + // str(c)spn assumes that the string was already well formed + // Unicode (which of course it is). + if (strspn($font, $this->mask) !== strlen($font)) { + continue; + } + + // Historical: + // In the absence of innerHTML/cssText, these ugly + // transforms don't pose a security risk (as \\ and \" + // might--these escapes are not supported by most browsers). + // We could try to be clever and use single-quote wrapping + // when there is a double quote present, but I have choosen + // not to implement that. (NOTE: you can reduce the amount + // of escapes by one depending on what quoting style you use) + // $font = str_replace('\\', '\\5C ', $font); + // $font = str_replace('"', '\\22 ', $font); + // $font = str_replace("'", '\\27 ', $font); + + // font possibly with spaces, requires quoting + $final .= "'$font', "; + } + $final = rtrim($final, ', '); + if ($final === '') { + return false; + } + return $final; + } + +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/AttrDef/CSS/Ident.php b/extlib/HTMLPurifier/HTMLPurifier/AttrDef/CSS/Ident.php new file mode 100644 index 0000000000..973002c17f --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/AttrDef/CSS/Ident.php @@ -0,0 +1,32 @@ +def = $def; + $this->allow = $allow; + } + + /** + * Intercepts and removes !important if necessary + * @param string $string + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool|string + */ + public function validate($string, $config, $context) + { + // test for ! and important tokens + $string = trim($string); + $is_important = false; + // :TODO: optimization: test directly for !important and ! important + if (strlen($string) >= 9 && substr($string, -9) === 'important') { + $temp = rtrim(substr($string, 0, -9)); + // use a temp, because we might want to restore important + if (strlen($temp) >= 1 && substr($temp, -1) === '!') { + $string = rtrim(substr($temp, 0, -1)); + $is_important = true; + } + } + $string = $this->def->validate($string, $config, $context); + if ($this->allow && $is_important) { + $string .= ' !important'; + } + return $string; + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/AttrDef/CSS/Length.php b/extlib/HTMLPurifier/HTMLPurifier/AttrDef/CSS/Length.php new file mode 100644 index 0000000000..f12453a04a --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/AttrDef/CSS/Length.php @@ -0,0 +1,77 @@ +min = $min !== null ? HTMLPurifier_Length::make($min) : null; + $this->max = $max !== null ? HTMLPurifier_Length::make($max) : null; + } + + /** + * @param string $string + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool|string + */ + public function validate($string, $config, $context) + { + $string = $this->parseCDATA($string); + + // Optimizations + if ($string === '') { + return false; + } + if ($string === '0') { + return '0'; + } + if (strlen($string) === 1) { + return false; + } + + $length = HTMLPurifier_Length::make($string); + if (!$length->isValid()) { + return false; + } + + if ($this->min) { + $c = $length->compareTo($this->min); + if ($c === false) { + return false; + } + if ($c < 0) { + return false; + } + } + if ($this->max) { + $c = $length->compareTo($this->max); + if ($c === false) { + return false; + } + if ($c > 0) { + return false; + } + } + return $length->toString(); + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/AttrDef/CSS/ListStyle.php b/extlib/HTMLPurifier/HTMLPurifier/AttrDef/CSS/ListStyle.php new file mode 100644 index 0000000000..e74d42654e --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/AttrDef/CSS/ListStyle.php @@ -0,0 +1,112 @@ +getCSSDefinition(); + $this->info['list-style-type'] = $def->info['list-style-type']; + $this->info['list-style-position'] = $def->info['list-style-position']; + $this->info['list-style-image'] = $def->info['list-style-image']; + } + + /** + * @param string $string + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool|string + */ + public function validate($string, $config, $context) + { + // regular pre-processing + $string = $this->parseCDATA($string); + if ($string === '') { + return false; + } + + // assumes URI doesn't have spaces in it + $bits = explode(' ', strtolower($string)); // bits to process + + $caught = array(); + $caught['type'] = false; + $caught['position'] = false; + $caught['image'] = false; + + $i = 0; // number of catches + $none = false; + + foreach ($bits as $bit) { + if ($i >= 3) { + return; + } // optimization bit + if ($bit === '') { + continue; + } + foreach ($caught as $key => $status) { + if ($status !== false) { + continue; + } + $r = $this->info['list-style-' . $key]->validate($bit, $config, $context); + if ($r === false) { + continue; + } + if ($r === 'none') { + if ($none) { + continue; + } else { + $none = true; + } + if ($key == 'image') { + continue; + } + } + $caught[$key] = $r; + $i++; + break; + } + } + + if (!$i) { + return false; + } + + $ret = array(); + + // construct type + if ($caught['type']) { + $ret[] = $caught['type']; + } + + // construct image + if ($caught['image']) { + $ret[] = $caught['image']; + } + + // construct position + if ($caught['position']) { + $ret[] = $caught['position']; + } + + if (empty($ret)) { + return false; + } + return implode(' ', $ret); + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/AttrDef/CSS/Multiple.php b/extlib/HTMLPurifier/HTMLPurifier/AttrDef/CSS/Multiple.php new file mode 100644 index 0000000000..e707f871ca --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/AttrDef/CSS/Multiple.php @@ -0,0 +1,71 @@ +single = $single; + $this->max = $max; + } + + /** + * @param string $string + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool|string + */ + public function validate($string, $config, $context) + { + $string = $this->mungeRgb($this->parseCDATA($string)); + if ($string === '') { + return false; + } + $parts = explode(' ', $string); // parseCDATA replaced \r, \t and \n + $length = count($parts); + $final = ''; + for ($i = 0, $num = 0; $i < $length && $num < $this->max; $i++) { + if (ctype_space($parts[$i])) { + continue; + } + $result = $this->single->validate($parts[$i], $config, $context); + if ($result !== false) { + $final .= $result . ' '; + $num++; + } + } + if ($final === '') { + return false; + } + return rtrim($final); + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/AttrDef/CSS/Number.php b/extlib/HTMLPurifier/HTMLPurifier/AttrDef/CSS/Number.php new file mode 100644 index 0000000000..8edc159e72 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/AttrDef/CSS/Number.php @@ -0,0 +1,84 @@ +non_negative = $non_negative; + } + + /** + * @param string $number + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return string|bool + * @warning Some contexts do not pass $config, $context. These + * variables should not be used without checking HTMLPurifier_Length + */ + public function validate($number, $config, $context) + { + $number = $this->parseCDATA($number); + + if ($number === '') { + return false; + } + if ($number === '0') { + return '0'; + } + + $sign = ''; + switch ($number[0]) { + case '-': + if ($this->non_negative) { + return false; + } + $sign = '-'; + case '+': + $number = substr($number, 1); + } + + if (ctype_digit($number)) { + $number = ltrim($number, '0'); + return $number ? $sign . $number : '0'; + } + + // Period is the only non-numeric character allowed + if (strpos($number, '.') === false) { + return false; + } + + list($left, $right) = explode('.', $number, 2); + + if ($left === '' && $right === '') { + return false; + } + if ($left !== '' && !ctype_digit($left)) { + return false; + } + + $left = ltrim($left, '0'); + $right = rtrim($right, '0'); + + if ($right === '') { + return $left ? $sign . $left : '0'; + } elseif (!ctype_digit($right)) { + return false; + } + return $sign . $left . '.' . $right; + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/AttrDef/CSS/Percentage.php b/extlib/HTMLPurifier/HTMLPurifier/AttrDef/CSS/Percentage.php new file mode 100644 index 0000000000..f0f25c50a8 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/AttrDef/CSS/Percentage.php @@ -0,0 +1,54 @@ +number_def = new HTMLPurifier_AttrDef_CSS_Number($non_negative); + } + + /** + * @param string $string + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool|string + */ + public function validate($string, $config, $context) + { + $string = $this->parseCDATA($string); + + if ($string === '') { + return false; + } + $length = strlen($string); + if ($length === 1) { + return false; + } + if ($string[$length - 1] !== '%') { + return false; + } + + $number = substr($string, 0, $length - 1); + $number = $this->number_def->validate($number, $config, $context); + + if ($number === false) { + return false; + } + return "$number%"; + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/AttrDef/CSS/TextDecoration.php b/extlib/HTMLPurifier/HTMLPurifier/AttrDef/CSS/TextDecoration.php new file mode 100644 index 0000000000..5fd4b7f7b4 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/AttrDef/CSS/TextDecoration.php @@ -0,0 +1,46 @@ + true, + 'overline' => true, + 'underline' => true, + ); + + $string = strtolower($this->parseCDATA($string)); + + if ($string === 'none') { + return $string; + } + + $parts = explode(' ', $string); + $final = ''; + foreach ($parts as $part) { + if (isset($allowed_values[$part])) { + $final .= $part . ' '; + } + } + $final = rtrim($final); + if ($final === '') { + return false; + } + return $final; + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/AttrDef/CSS/URI.php b/extlib/HTMLPurifier/HTMLPurifier/AttrDef/CSS/URI.php new file mode 100644 index 0000000000..f9434230e2 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/AttrDef/CSS/URI.php @@ -0,0 +1,74 @@ +parseCDATA($uri_string); + if (strpos($uri_string, 'url(') !== 0) { + return false; + } + $uri_string = substr($uri_string, 4); + $new_length = strlen($uri_string) - 1; + if ($uri_string[$new_length] != ')') { + return false; + } + $uri = trim(substr($uri_string, 0, $new_length)); + + if (!empty($uri) && ($uri[0] == "'" || $uri[0] == '"')) { + $quote = $uri[0]; + $new_length = strlen($uri) - 1; + if ($uri[$new_length] !== $quote) { + return false; + } + $uri = substr($uri, 1, $new_length - 1); + } + + $uri = $this->expandCSSEscape($uri); + + $result = parent::validate($uri, $config, $context); + + if ($result === false) { + return false; + } + + // extra sanity check; should have been done by URI + $result = str_replace(array('"', "\\", "\n", "\x0c", "\r"), "", $result); + + // suspicious characters are ()'; we're going to percent encode + // them for safety. + $result = str_replace(array('(', ')', "'"), array('%28', '%29', '%27'), $result); + + // there's an extra bug where ampersands lose their escaping on + // an innerHTML cycle, so a very unlucky query parameter could + // then change the meaning of the URL. Unfortunately, there's + // not much we can do about that... + return "url(\"$result\")"; + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/AttrDef/Clone.php b/extlib/HTMLPurifier/HTMLPurifier/AttrDef/Clone.php new file mode 100644 index 0000000000..6698a00c01 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/AttrDef/Clone.php @@ -0,0 +1,44 @@ +clone = $clone; + } + + /** + * @param string $v + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool|string + */ + public function validate($v, $config, $context) + { + return $this->clone->validate($v, $config, $context); + } + + /** + * @param string $string + * @return HTMLPurifier_AttrDef + */ + public function make($string) + { + return clone $this->clone; + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/AttrDef/Enum.php b/extlib/HTMLPurifier/HTMLPurifier/AttrDef/Enum.php new file mode 100644 index 0000000000..8abda7f6e2 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/AttrDef/Enum.php @@ -0,0 +1,73 @@ +valid_values = array_flip($valid_values); + $this->case_sensitive = $case_sensitive; + } + + /** + * @param string $string + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool|string + */ + public function validate($string, $config, $context) + { + $string = trim($string); + if (!$this->case_sensitive) { + // we may want to do full case-insensitive libraries + $string = ctype_lower($string) ? $string : strtolower($string); + } + $result = isset($this->valid_values[$string]); + + return $result ? $string : false; + } + + /** + * @param string $string In form of comma-delimited list of case-insensitive + * valid values. Example: "foo,bar,baz". Prepend "s:" to make + * case sensitive + * @return HTMLPurifier_AttrDef_Enum + */ + public function make($string) + { + if (strlen($string) > 2 && $string[0] == 's' && $string[1] == ':') { + $string = substr($string, 2); + $sensitive = true; + } else { + $sensitive = false; + } + $values = explode(',', $string); + return new HTMLPurifier_AttrDef_Enum($values, $sensitive); + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/AttrDef/HTML/Bool.php b/extlib/HTMLPurifier/HTMLPurifier/AttrDef/HTML/Bool.php new file mode 100644 index 0000000000..dea15d2cd2 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/AttrDef/HTML/Bool.php @@ -0,0 +1,48 @@ +name = $name; + } + + /** + * @param string $string + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool|string + */ + public function validate($string, $config, $context) + { + return $this->name; + } + + /** + * @param string $string Name of attribute + * @return HTMLPurifier_AttrDef_HTML_Bool + */ + public function make($string) + { + return new HTMLPurifier_AttrDef_HTML_Bool($string); + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/AttrDef/HTML/Class.php b/extlib/HTMLPurifier/HTMLPurifier/AttrDef/HTML/Class.php new file mode 100644 index 0000000000..d5013488fc --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/AttrDef/HTML/Class.php @@ -0,0 +1,48 @@ +getDefinition('HTML')->doctype->name; + if ($name == "XHTML 1.1" || $name == "XHTML 2.0") { + return parent::split($string, $config, $context); + } else { + return preg_split('/\s+/', $string); + } + } + + /** + * @param array $tokens + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return array + */ + protected function filter($tokens, $config, $context) + { + $allowed = $config->get('Attr.AllowedClasses'); + $forbidden = $config->get('Attr.ForbiddenClasses'); + $ret = array(); + foreach ($tokens as $token) { + if (($allowed === null || isset($allowed[$token])) && + !isset($forbidden[$token]) && + // We need this O(n) check because of PHP's array + // implementation that casts -0 to 0. + !in_array($token, $ret, true) + ) { + $ret[] = $token; + } + } + return $ret; + } +} diff --git a/extlib/HTMLPurifier/HTMLPurifier/AttrDef/HTML/Color.php b/extlib/HTMLPurifier/HTMLPurifier/AttrDef/HTML/Color.php new file mode 100644 index 0000000000..946ebb7820 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/AttrDef/HTML/Color.php @@ -0,0 +1,51 @@ +get('Core.ColorKeywords'); + } + + $string = trim($string); + + if (empty($string)) { + return false; + } + $lower = strtolower($string); + if (isset($colors[$lower])) { + return $colors[$lower]; + } + if ($string[0] === '#') { + $hex = substr($string, 1); + } else { + $hex = $string; + } + + $length = strlen($hex); + if ($length !== 3 && $length !== 6) { + return false; + } + if (!ctype_xdigit($hex)) { + return false; + } + if ($length === 3) { + $hex = $hex[0] . $hex[0] . $hex[1] . $hex[1] . $hex[2] . $hex[2]; + } + return "#$hex"; + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/AttrDef/HTML/FrameTarget.php b/extlib/HTMLPurifier/HTMLPurifier/AttrDef/HTML/FrameTarget.php new file mode 100644 index 0000000000..d79ba12b3f --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/AttrDef/HTML/FrameTarget.php @@ -0,0 +1,38 @@ +valid_values === false) { + $this->valid_values = $config->get('Attr.AllowedFrameTargets'); + } + return parent::validate($string, $config, $context); + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/AttrDef/HTML/ID.php b/extlib/HTMLPurifier/HTMLPurifier/AttrDef/HTML/ID.php new file mode 100644 index 0000000000..3d86efb44c --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/AttrDef/HTML/ID.php @@ -0,0 +1,105 @@ +selector = $selector; + } + + /** + * @param string $id + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool|string + */ + public function validate($id, $config, $context) + { + if (!$this->selector && !$config->get('Attr.EnableID')) { + return false; + } + + $id = trim($id); // trim it first + + if ($id === '') { + return false; + } + + $prefix = $config->get('Attr.IDPrefix'); + if ($prefix !== '') { + $prefix .= $config->get('Attr.IDPrefixLocal'); + // prevent re-appending the prefix + if (strpos($id, $prefix) !== 0) { + $id = $prefix . $id; + } + } elseif ($config->get('Attr.IDPrefixLocal') !== '') { + trigger_error( + '%Attr.IDPrefixLocal cannot be used unless ' . + '%Attr.IDPrefix is set', + E_USER_WARNING + ); + } + + if (!$this->selector) { + $id_accumulator =& $context->get('IDAccumulator'); + if (isset($id_accumulator->ids[$id])) { + return false; + } + } + + // we purposely avoid using regex, hopefully this is faster + + if (ctype_alpha($id)) { + $result = true; + } else { + if (!ctype_alpha(@$id[0])) { + return false; + } + // primitive style of regexps, I suppose + $trim = trim( + $id, + 'A..Za..z0..9:-._' + ); + $result = ($trim === ''); + } + + $regexp = $config->get('Attr.IDBlacklistRegexp'); + if ($regexp && preg_match($regexp, $id)) { + return false; + } + + if (!$this->selector && $result) { + $id_accumulator->add($id); + } + + // if no change was made to the ID, return the result + // else, return the new id if stripping whitespace made it + // valid, or return false. + return $result ? $id : false; + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/AttrDef/HTML/Length.php b/extlib/HTMLPurifier/HTMLPurifier/AttrDef/HTML/Length.php new file mode 100644 index 0000000000..1c4006fbbd --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/AttrDef/HTML/Length.php @@ -0,0 +1,56 @@ + 100) { + return '100%'; + } + return ((string)$points) . '%'; + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/AttrDef/HTML/LinkTypes.php b/extlib/HTMLPurifier/HTMLPurifier/AttrDef/HTML/LinkTypes.php new file mode 100644 index 0000000000..63fa04c15c --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/AttrDef/HTML/LinkTypes.php @@ -0,0 +1,72 @@ + 'AllowedRel', + 'rev' => 'AllowedRev' + ); + if (!isset($configLookup[$name])) { + trigger_error( + 'Unrecognized attribute name for link ' . + 'relationship.', + E_USER_ERROR + ); + return; + } + $this->name = $configLookup[$name]; + } + + /** + * @param string $string + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool|string + */ + public function validate($string, $config, $context) + { + $allowed = $config->get('Attr.' . $this->name); + if (empty($allowed)) { + return false; + } + + $string = $this->parseCDATA($string); + $parts = explode(' ', $string); + + // lookup to prevent duplicates + $ret_lookup = array(); + foreach ($parts as $part) { + $part = strtolower(trim($part)); + if (!isset($allowed[$part])) { + continue; + } + $ret_lookup[$part] = true; + } + + if (empty($ret_lookup)) { + return false; + } + $string = implode(' ', array_keys($ret_lookup)); + return $string; + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/AttrDef/HTML/MultiLength.php b/extlib/HTMLPurifier/HTMLPurifier/AttrDef/HTML/MultiLength.php new file mode 100644 index 0000000000..bbb20f2f80 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/AttrDef/HTML/MultiLength.php @@ -0,0 +1,60 @@ +split($string, $config, $context); + $tokens = $this->filter($tokens, $config, $context); + if (empty($tokens)) { + return false; + } + return implode(' ', $tokens); + } + + /** + * Splits a space separated list of tokens into its constituent parts. + * @param string $string + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return array + */ + protected function split($string, $config, $context) + { + // OPTIMIZABLE! + // do the preg_match, capture all subpatterns for reformulation + + // we don't support U+00A1 and up codepoints or + // escaping because I don't know how to do that with regexps + // and plus it would complicate optimization efforts (you never + // see that anyway). + $pattern = '/(?:(?<=\s)|\A)' . // look behind for space or string start + '((?:--|-?[A-Za-z_])[A-Za-z_\-0-9]*)' . + '(?:(?=\s)|\z)/'; // look ahead for space or string end + preg_match_all($pattern, $string, $matches); + return $matches[1]; + } + + /** + * Template method for removing certain tokens based on arbitrary criteria. + * @note If we wanted to be really functional, we'd do an array_filter + * with a callback. But... we're not. + * @param array $tokens + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return array + */ + protected function filter($tokens, $config, $context) + { + return $tokens; + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/AttrDef/HTML/Pixels.php b/extlib/HTMLPurifier/HTMLPurifier/AttrDef/HTML/Pixels.php new file mode 100644 index 0000000000..a1d019e095 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/AttrDef/HTML/Pixels.php @@ -0,0 +1,76 @@ +max = $max; + } + + /** + * @param string $string + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool|string + */ + public function validate($string, $config, $context) + { + $string = trim($string); + if ($string === '0') { + return $string; + } + if ($string === '') { + return false; + } + $length = strlen($string); + if (substr($string, $length - 2) == 'px') { + $string = substr($string, 0, $length - 2); + } + if (!is_numeric($string)) { + return false; + } + $int = (int)$string; + + if ($int < 0) { + return '0'; + } + + // upper-bound value, extremely high values can + // crash operating systems, see + // WARNING, above link WILL crash you if you're using Windows + + if ($this->max !== null && $int > $this->max) { + return (string)$this->max; + } + return (string)$int; + } + + /** + * @param string $string + * @return HTMLPurifier_AttrDef + */ + public function make($string) + { + if ($string === '') { + $max = null; + } else { + $max = (int)$string; + } + $class = get_class($this); + return new $class($max); + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/AttrDef/Integer.php b/extlib/HTMLPurifier/HTMLPurifier/AttrDef/Integer.php new file mode 100644 index 0000000000..400e707d2f --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/AttrDef/Integer.php @@ -0,0 +1,91 @@ +negative = $negative; + $this->zero = $zero; + $this->positive = $positive; + } + + /** + * @param string $integer + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool|string + */ + public function validate($integer, $config, $context) + { + $integer = $this->parseCDATA($integer); + if ($integer === '') { + return false; + } + + // we could possibly simply typecast it to integer, but there are + // certain fringe cases that must not return an integer. + + // clip leading sign + if ($this->negative && $integer[0] === '-') { + $digits = substr($integer, 1); + if ($digits === '0') { + $integer = '0'; + } // rm minus sign for zero + } elseif ($this->positive && $integer[0] === '+') { + $digits = $integer = substr($integer, 1); // rm unnecessary plus + } else { + $digits = $integer; + } + + // test if it's numeric + if (!ctype_digit($digits)) { + return false; + } + + // perform scope tests + if (!$this->zero && $integer == 0) { + return false; + } + if (!$this->positive && $integer > 0) { + return false; + } + if (!$this->negative && $integer < 0) { + return false; + } + + return $integer; + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/AttrDef/Lang.php b/extlib/HTMLPurifier/HTMLPurifier/AttrDef/Lang.php new file mode 100644 index 0000000000..2a55cea642 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/AttrDef/Lang.php @@ -0,0 +1,86 @@ + 8 || !ctype_alnum($subtags[1])) { + return $new_string; + } + if (!ctype_lower($subtags[1])) { + $subtags[1] = strtolower($subtags[1]); + } + + $new_string .= '-' . $subtags[1]; + if ($num_subtags == 2) { + return $new_string; + } + + // process all other subtags, index 2 and up + for ($i = 2; $i < $num_subtags; $i++) { + $length = strlen($subtags[$i]); + if ($length == 0 || $length > 8 || !ctype_alnum($subtags[$i])) { + return $new_string; + } + if (!ctype_lower($subtags[$i])) { + $subtags[$i] = strtolower($subtags[$i]); + } + $new_string .= '-' . $subtags[$i]; + } + return $new_string; + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/AttrDef/Switch.php b/extlib/HTMLPurifier/HTMLPurifier/AttrDef/Switch.php new file mode 100644 index 0000000000..c7eb3199a4 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/AttrDef/Switch.php @@ -0,0 +1,53 @@ +tag = $tag; + $this->withTag = $with_tag; + $this->withoutTag = $without_tag; + } + + /** + * @param string $string + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool|string + */ + public function validate($string, $config, $context) + { + $token = $context->get('CurrentToken', true); + if (!$token || $token->name !== $this->tag) { + return $this->withoutTag->validate($string, $config, $context); + } else { + return $this->withTag->validate($string, $config, $context); + } + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/AttrDef/Text.php b/extlib/HTMLPurifier/HTMLPurifier/AttrDef/Text.php new file mode 100644 index 0000000000..4553a4ea9b --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/AttrDef/Text.php @@ -0,0 +1,21 @@ +parseCDATA($string); + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/AttrDef/URI.php b/extlib/HTMLPurifier/HTMLPurifier/AttrDef/URI.php new file mode 100644 index 0000000000..c1cd89772c --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/AttrDef/URI.php @@ -0,0 +1,111 @@ +parser = new HTMLPurifier_URIParser(); + $this->embedsResource = (bool)$embeds_resource; + } + + /** + * @param string $string + * @return HTMLPurifier_AttrDef_URI + */ + public function make($string) + { + $embeds = ($string === 'embedded'); + return new HTMLPurifier_AttrDef_URI($embeds); + } + + /** + * @param string $uri + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool|string + */ + public function validate($uri, $config, $context) + { + if ($config->get('URI.Disable')) { + return false; + } + + $uri = $this->parseCDATA($uri); + + // parse the URI + $uri = $this->parser->parse($uri); + if ($uri === false) { + return false; + } + + // add embedded flag to context for validators + $context->register('EmbeddedURI', $this->embedsResource); + + $ok = false; + do { + + // generic validation + $result = $uri->validate($config, $context); + if (!$result) { + break; + } + + // chained filtering + $uri_def = $config->getDefinition('URI'); + $result = $uri_def->filter($uri, $config, $context); + if (!$result) { + break; + } + + // scheme-specific validation + $scheme_obj = $uri->getSchemeObj($config, $context); + if (!$scheme_obj) { + break; + } + if ($this->embedsResource && !$scheme_obj->browsable) { + break; + } + $result = $scheme_obj->validate($uri, $config, $context); + if (!$result) { + break; + } + + // Post chained filtering + $result = $uri_def->postFilter($uri, $config, $context); + if (!$result) { + break; + } + + // survived gauntlet + $ok = true; + + } while (false); + + $context->destroy('EmbeddedURI'); + if (!$ok) { + return false; + } + // back to string + return $uri->toString(); + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/AttrDef/URI/Email.php b/extlib/HTMLPurifier/HTMLPurifier/AttrDef/URI/Email.php new file mode 100644 index 0000000000..daf32b7643 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/AttrDef/URI/Email.php @@ -0,0 +1,20 @@ +" + // that needs more percent encoding to be done + if ($string == '') { + return false; + } + $string = trim($string); + $result = preg_match('/^[A-Z0-9._%-]+@[A-Z0-9.-]+\.[A-Z]{2,4}$/i', $string); + return $result ? $string : false; + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/AttrDef/URI/Host.php b/extlib/HTMLPurifier/HTMLPurifier/AttrDef/URI/Host.php new file mode 100644 index 0000000000..e7df800b1e --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/AttrDef/URI/Host.php @@ -0,0 +1,128 @@ +ipv4 = new HTMLPurifier_AttrDef_URI_IPv4(); + $this->ipv6 = new HTMLPurifier_AttrDef_URI_IPv6(); + } + + /** + * @param string $string + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool|string + */ + public function validate($string, $config, $context) + { + $length = strlen($string); + // empty hostname is OK; it's usually semantically equivalent: + // the default host as defined by a URI scheme is used: + // + // If the URI scheme defines a default for host, then that + // default applies when the host subcomponent is undefined + // or when the registered name is empty (zero length). + if ($string === '') { + return ''; + } + if ($length > 1 && $string[0] === '[' && $string[$length - 1] === ']') { + //IPv6 + $ip = substr($string, 1, $length - 2); + $valid = $this->ipv6->validate($ip, $config, $context); + if ($valid === false) { + return false; + } + return '[' . $valid . ']'; + } + + // need to do checks on unusual encodings too + $ipv4 = $this->ipv4->validate($string, $config, $context); + if ($ipv4 !== false) { + return $ipv4; + } + + // A regular domain name. + + // This doesn't match I18N domain names, but we don't have proper IRI support, + // so force users to insert Punycode. + + // There is not a good sense in which underscores should be + // allowed, since it's technically not! (And if you go as + // far to allow everything as specified by the DNS spec... + // well, that's literally everything, modulo some space limits + // for the components and the overall name (which, by the way, + // we are NOT checking!). So we (arbitrarily) decide this: + // let's allow underscores wherever we would have allowed + // hyphens, if they are enabled. This is a pretty good match + // for browser behavior, for example, a large number of browsers + // cannot handle foo_.example.com, but foo_bar.example.com is + // fairly well supported. + $underscore = $config->get('Core.AllowHostnameUnderscore') ? '_' : ''; + + // The productions describing this are: + $a = '[a-z]'; // alpha + $an = '[a-z0-9]'; // alphanum + $and = "[a-z0-9-$underscore]"; // alphanum | "-" + // domainlabel = alphanum | alphanum *( alphanum | "-" ) alphanum + $domainlabel = "$an($and*$an)?"; + // toplabel = alpha | alpha *( alphanum | "-" ) alphanum + $toplabel = "$a($and*$an)?"; + // hostname = *( domainlabel "." ) toplabel [ "." ] + if (preg_match("/^($domainlabel\.)*$toplabel\.?$/i", $string)) { + return $string; + } + + // If we have Net_IDNA2 support, we can support IRIs by + // punycoding them. (This is the most portable thing to do, + // since otherwise we have to assume browsers support + + if ($config->get('Core.EnableIDNA')) { + $idna = new Net_IDNA2(array('encoding' => 'utf8', 'overlong' => false, 'strict' => true)); + // we need to encode each period separately + $parts = explode('.', $string); + try { + $new_parts = array(); + foreach ($parts as $part) { + $encodable = false; + for ($i = 0, $c = strlen($part); $i < $c; $i++) { + if (ord($part[$i]) > 0x7a) { + $encodable = true; + break; + } + } + if (!$encodable) { + $new_parts[] = $part; + } else { + $new_parts[] = $idna->encode($part); + } + } + $string = implode('.', $new_parts); + if (preg_match("/^($domainlabel\.)*$toplabel\.?$/i", $string)) { + return $string; + } + } catch (Exception $e) { + // XXX error reporting + } + } + return false; + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/AttrDef/URI/IPv4.php b/extlib/HTMLPurifier/HTMLPurifier/AttrDef/URI/IPv4.php new file mode 100644 index 0000000000..30ac16c9e7 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/AttrDef/URI/IPv4.php @@ -0,0 +1,45 @@ +ip4) { + $this->_loadRegex(); + } + + if (preg_match('#^' . $this->ip4 . '$#s', $aIP)) { + return $aIP; + } + return false; + } + + /** + * Lazy load function to prevent regex from being stuffed in + * cache. + */ + protected function _loadRegex() + { + $oct = '(?:25[0-5]|2[0-4][0-9]|1[0-9]{2}|[1-9][0-9]|[0-9])'; // 0-255 + $this->ip4 = "(?:{$oct}\\.{$oct}\\.{$oct}\\.{$oct})"; + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/AttrDef/URI/IPv6.php b/extlib/HTMLPurifier/HTMLPurifier/AttrDef/URI/IPv6.php new file mode 100644 index 0000000000..f243793eeb --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/AttrDef/URI/IPv6.php @@ -0,0 +1,89 @@ +ip4) { + $this->_loadRegex(); + } + + $original = $aIP; + + $hex = '[0-9a-fA-F]'; + $blk = '(?:' . $hex . '{1,4})'; + $pre = '(?:/(?:12[0-8]|1[0-1][0-9]|[1-9][0-9]|[0-9]))'; // /0 - /128 + + // prefix check + if (strpos($aIP, '/') !== false) { + if (preg_match('#' . $pre . '$#s', $aIP, $find)) { + $aIP = substr($aIP, 0, 0 - strlen($find[0])); + unset($find); + } else { + return false; + } + } + + // IPv4-compatiblity check + if (preg_match('#(?<=:' . ')' . $this->ip4 . '$#s', $aIP, $find)) { + $aIP = substr($aIP, 0, 0 - strlen($find[0])); + $ip = explode('.', $find[0]); + $ip = array_map('dechex', $ip); + $aIP .= $ip[0] . $ip[1] . ':' . $ip[2] . $ip[3]; + unset($find, $ip); + } + + // compression check + $aIP = explode('::', $aIP); + $c = count($aIP); + if ($c > 2) { + return false; + } elseif ($c == 2) { + list($first, $second) = $aIP; + $first = explode(':', $first); + $second = explode(':', $second); + + if (count($first) + count($second) > 8) { + return false; + } + + while (count($first) < 8) { + array_push($first, '0'); + } + + array_splice($first, 8 - count($second), 8, $second); + $aIP = $first; + unset($first, $second); + } else { + $aIP = explode(':', $aIP[0]); + } + $c = count($aIP); + + if ($c != 8) { + return false; + } + + // All the pieces should be 16-bit hex strings. Are they? + foreach ($aIP as $piece) { + if (!preg_match('#^[0-9a-fA-F]{4}$#s', sprintf('%04s', $piece))) { + return false; + } + } + return $original; + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/AttrTransform.php b/extlib/HTMLPurifier/HTMLPurifier/AttrTransform.php new file mode 100644 index 0000000000..b428331f15 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/AttrTransform.php @@ -0,0 +1,60 @@ +confiscateAttr($attr, 'background'); + // some validation should happen here + + $this->prependCSS($attr, "background-image:url($background);"); + return $attr; + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/AttrTransform/BdoDir.php b/extlib/HTMLPurifier/HTMLPurifier/AttrTransform/BdoDir.php new file mode 100644 index 0000000000..d66c04a5b8 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/AttrTransform/BdoDir.php @@ -0,0 +1,27 @@ +get('Attr.DefaultTextDir'); + return $attr; + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/AttrTransform/BgColor.php b/extlib/HTMLPurifier/HTMLPurifier/AttrTransform/BgColor.php new file mode 100644 index 0000000000..0f51fd2cec --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/AttrTransform/BgColor.php @@ -0,0 +1,28 @@ +confiscateAttr($attr, 'bgcolor'); + // some validation should happen here + + $this->prependCSS($attr, "background-color:$bgcolor;"); + return $attr; + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/AttrTransform/BoolToCSS.php b/extlib/HTMLPurifier/HTMLPurifier/AttrTransform/BoolToCSS.php new file mode 100644 index 0000000000..f25cd01955 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/AttrTransform/BoolToCSS.php @@ -0,0 +1,47 @@ +attr = $attr; + $this->css = $css; + } + + /** + * @param array $attr + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return array + */ + public function transform($attr, $config, $context) + { + if (!isset($attr[$this->attr])) { + return $attr; + } + unset($attr[$this->attr]); + $this->prependCSS($attr, $this->css); + return $attr; + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/AttrTransform/Border.php b/extlib/HTMLPurifier/HTMLPurifier/AttrTransform/Border.php new file mode 100644 index 0000000000..057dc017fa --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/AttrTransform/Border.php @@ -0,0 +1,26 @@ +confiscateAttr($attr, 'border'); + // some validation should happen here + $this->prependCSS($attr, "border:{$border_width}px solid;"); + return $attr; + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/AttrTransform/EnumToCSS.php b/extlib/HTMLPurifier/HTMLPurifier/AttrTransform/EnumToCSS.php new file mode 100644 index 0000000000..7ccd0e3fb7 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/AttrTransform/EnumToCSS.php @@ -0,0 +1,68 @@ +attr = $attr; + $this->enumToCSS = $enum_to_css; + $this->caseSensitive = (bool)$case_sensitive; + } + + /** + * @param array $attr + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return array + */ + public function transform($attr, $config, $context) + { + if (!isset($attr[$this->attr])) { + return $attr; + } + + $value = trim($attr[$this->attr]); + unset($attr[$this->attr]); + + if (!$this->caseSensitive) { + $value = strtolower($value); + } + + if (!isset($this->enumToCSS[$value])) { + return $attr; + } + $this->prependCSS($attr, $this->enumToCSS[$value]); + return $attr; + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/AttrTransform/ImgRequired.php b/extlib/HTMLPurifier/HTMLPurifier/AttrTransform/ImgRequired.php new file mode 100644 index 0000000000..7df6cb3e1b --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/AttrTransform/ImgRequired.php @@ -0,0 +1,48 @@ +get('Core.RemoveInvalidImg')) { + return $attr; + } + $attr['src'] = $config->get('Attr.DefaultInvalidImage'); + $src = false; + } + + if (!isset($attr['alt'])) { + if ($src) { + $alt = $config->get('Attr.DefaultImageAlt'); + if ($alt === null) { + // truncate if the alt is too long + $attr['alt'] = substr(basename($attr['src']), 0, 40); + } else { + $attr['alt'] = $alt; + } + } else { + $attr['alt'] = $config->get('Attr.DefaultInvalidImageAlt'); + } + } + return $attr; + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/AttrTransform/ImgSpace.php b/extlib/HTMLPurifier/HTMLPurifier/AttrTransform/ImgSpace.php new file mode 100644 index 0000000000..350b3358fc --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/AttrTransform/ImgSpace.php @@ -0,0 +1,61 @@ + array('left', 'right'), + 'vspace' => array('top', 'bottom') + ); + + /** + * @param string $attr + */ + public function __construct($attr) + { + $this->attr = $attr; + if (!isset($this->css[$attr])) { + trigger_error(htmlspecialchars($attr) . ' is not valid space attribute'); + } + } + + /** + * @param array $attr + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return array + */ + public function transform($attr, $config, $context) + { + if (!isset($attr[$this->attr])) { + return $attr; + } + + $width = $this->confiscateAttr($attr, $this->attr); + // some validation could happen here + + if (!isset($this->css[$this->attr])) { + return $attr; + } + + $style = ''; + foreach ($this->css[$this->attr] as $suffix) { + $property = "margin-$suffix"; + $style .= "$property:{$width}px;"; + } + $this->prependCSS($attr, $style); + return $attr; + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/AttrTransform/Input.php b/extlib/HTMLPurifier/HTMLPurifier/AttrTransform/Input.php new file mode 100644 index 0000000000..3ab47ed8c9 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/AttrTransform/Input.php @@ -0,0 +1,56 @@ +pixels = new HTMLPurifier_AttrDef_HTML_Pixels(); + } + + /** + * @param array $attr + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return array + */ + public function transform($attr, $config, $context) + { + if (!isset($attr['type'])) { + $t = 'text'; + } else { + $t = strtolower($attr['type']); + } + if (isset($attr['checked']) && $t !== 'radio' && $t !== 'checkbox') { + unset($attr['checked']); + } + if (isset($attr['maxlength']) && $t !== 'text' && $t !== 'password') { + unset($attr['maxlength']); + } + if (isset($attr['size']) && $t !== 'text' && $t !== 'password') { + $result = $this->pixels->validate($attr['size'], $config, $context); + if ($result === false) { + unset($attr['size']); + } else { + $attr['size'] = $result; + } + } + if (isset($attr['src']) && $t !== 'image') { + unset($attr['src']); + } + if (!isset($attr['value']) && ($t === 'radio' || $t === 'checkbox')) { + $attr['value'] = ''; + } + return $attr; + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/AttrTransform/Lang.php b/extlib/HTMLPurifier/HTMLPurifier/AttrTransform/Lang.php new file mode 100644 index 0000000000..5b0aff0e40 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/AttrTransform/Lang.php @@ -0,0 +1,31 @@ +name = $name; + $this->cssName = $css_name ? $css_name : $name; + } + + /** + * @param array $attr + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return array + */ + public function transform($attr, $config, $context) + { + if (!isset($attr[$this->name])) { + return $attr; + } + $length = $this->confiscateAttr($attr, $this->name); + if (ctype_digit($length)) { + $length .= 'px'; + } + $this->prependCSS($attr, $this->cssName . ":$length;"); + return $attr; + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/AttrTransform/Name.php b/extlib/HTMLPurifier/HTMLPurifier/AttrTransform/Name.php new file mode 100644 index 0000000000..63cce6837a --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/AttrTransform/Name.php @@ -0,0 +1,33 @@ +get('HTML.Attr.Name.UseCDATA')) { + return $attr; + } + if (!isset($attr['name'])) { + return $attr; + } + $id = $this->confiscateAttr($attr, 'name'); + if (isset($attr['id'])) { + return $attr; + } + $attr['id'] = $id; + return $attr; + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/AttrTransform/NameSync.php b/extlib/HTMLPurifier/HTMLPurifier/AttrTransform/NameSync.php new file mode 100644 index 0000000000..36079b786f --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/AttrTransform/NameSync.php @@ -0,0 +1,41 @@ +idDef = new HTMLPurifier_AttrDef_HTML_ID(); + } + + /** + * @param array $attr + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return array + */ + public function transform($attr, $config, $context) + { + if (!isset($attr['name'])) { + return $attr; + } + $name = $attr['name']; + if (isset($attr['id']) && $attr['id'] === $name) { + return $attr; + } + $result = $this->idDef->validate($name, $config, $context); + if ($result === false) { + unset($attr['name']); + } else { + $attr['name'] = $result; + } + return $attr; + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/AttrTransform/Nofollow.php b/extlib/HTMLPurifier/HTMLPurifier/AttrTransform/Nofollow.php new file mode 100644 index 0000000000..1057ebee1b --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/AttrTransform/Nofollow.php @@ -0,0 +1,52 @@ +parser = new HTMLPurifier_URIParser(); + } + + /** + * @param array $attr + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return array + */ + public function transform($attr, $config, $context) + { + if (!isset($attr['href'])) { + return $attr; + } + + // XXX Kind of inefficient + $url = $this->parser->parse($attr['href']); + $scheme = $url->getSchemeObj($config, $context); + + if ($scheme->browsable && !$url->isLocal($config, $context)) { + if (isset($attr['rel'])) { + $rels = explode(' ', $attr['rel']); + if (!in_array('nofollow', $rels)) { + $rels[] = 'nofollow'; + } + $attr['rel'] = implode(' ', $rels); + } else { + $attr['rel'] = 'nofollow'; + } + } + return $attr; + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/AttrTransform/SafeEmbed.php b/extlib/HTMLPurifier/HTMLPurifier/AttrTransform/SafeEmbed.php new file mode 100644 index 0000000000..231c81a3f0 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/AttrTransform/SafeEmbed.php @@ -0,0 +1,25 @@ +uri = new HTMLPurifier_AttrDef_URI(true); // embedded + $this->wmode = new HTMLPurifier_AttrDef_Enum(array('window', 'opaque', 'transparent')); + } + + /** + * @param array $attr + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return array + */ + public function transform($attr, $config, $context) + { + // If we add support for other objects, we'll need to alter the + // transforms. + switch ($attr['name']) { + // application/x-shockwave-flash + // Keep this synchronized with Injector/SafeObject.php + case 'allowScriptAccess': + $attr['value'] = 'never'; + break; + case 'allowNetworking': + $attr['value'] = 'internal'; + break; + case 'allowFullScreen': + if ($config->get('HTML.FlashAllowFullScreen')) { + $attr['value'] = ($attr['value'] == 'true') ? 'true' : 'false'; + } else { + $attr['value'] = 'false'; + } + break; + case 'wmode': + $attr['value'] = $this->wmode->validate($attr['value'], $config, $context); + break; + case 'movie': + case 'src': + $attr['name'] = "movie"; + $attr['value'] = $this->uri->validate($attr['value'], $config, $context); + break; + case 'flashvars': + // we're going to allow arbitrary inputs to the SWF, on + // the reasoning that it could only hack the SWF, not us. + break; + // add other cases to support other param name/value pairs + default: + $attr['name'] = $attr['value'] = null; + } + return $attr; + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/AttrTransform/ScriptRequired.php b/extlib/HTMLPurifier/HTMLPurifier/AttrTransform/ScriptRequired.php new file mode 100644 index 0000000000..b7057bbf8e --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/AttrTransform/ScriptRequired.php @@ -0,0 +1,23 @@ + + */ +class HTMLPurifier_AttrTransform_ScriptRequired extends HTMLPurifier_AttrTransform +{ + /** + * @param array $attr + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return array + */ + public function transform($attr, $config, $context) + { + if (!isset($attr['type'])) { + $attr['type'] = 'text/javascript'; + } + return $attr; + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/AttrTransform/TargetBlank.php b/extlib/HTMLPurifier/HTMLPurifier/AttrTransform/TargetBlank.php new file mode 100644 index 0000000000..dd63ea89cb --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/AttrTransform/TargetBlank.php @@ -0,0 +1,45 @@ +parser = new HTMLPurifier_URIParser(); + } + + /** + * @param array $attr + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return array + */ + public function transform($attr, $config, $context) + { + if (!isset($attr['href'])) { + return $attr; + } + + // XXX Kind of inefficient + $url = $this->parser->parse($attr['href']); + $scheme = $url->getSchemeObj($config, $context); + + if ($scheme->browsable && !$url->isBenign($config, $context)) { + $attr['target'] = '_blank'; + } + return $attr; + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/AttrTransform/Textarea.php b/extlib/HTMLPurifier/HTMLPurifier/AttrTransform/Textarea.php new file mode 100644 index 0000000000..6a9f33a0c8 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/AttrTransform/Textarea.php @@ -0,0 +1,27 @@ + + */ +class HTMLPurifier_AttrTransform_Textarea extends HTMLPurifier_AttrTransform +{ + /** + * @param array $attr + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return array + */ + public function transform($attr, $config, $context) + { + // Calculated from Firefox + if (!isset($attr['cols'])) { + $attr['cols'] = '22'; + } + if (!isset($attr['rows'])) { + $attr['rows'] = '3'; + } + return $attr; + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/AttrTypes.php b/extlib/HTMLPurifier/HTMLPurifier/AttrTypes.php new file mode 100644 index 0000000000..3b70520b6a --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/AttrTypes.php @@ -0,0 +1,96 @@ +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 string $type String type name + * @return HTMLPurifier_AttrDef Object AttrDef for type + */ + public function get($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 string $type String type name + * @param HTMLPurifier_AttrDef $impl Object AttrDef for type + */ + public function set($type, $impl) + { + $this->info[$type] = $impl; + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/AttrValidator.php b/extlib/HTMLPurifier/HTMLPurifier/AttrValidator.php new file mode 100644 index 0000000000..f97dc93edd --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/AttrValidator.php @@ -0,0 +1,178 @@ +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; + } + + // 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'); + } + + } + + +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/Bootstrap.php b/extlib/HTMLPurifier/HTMLPurifier/Bootstrap.php new file mode 100644 index 0000000000..707122bb29 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/Bootstrap.php @@ -0,0 +1,124 @@ + +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 string $class Class to load + * @return bool + */ + public static function autoload($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. + * @param string $class Class path to get + * @return string + */ + public static function getPath($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); + } + } + } + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/CSSDefinition.php b/extlib/HTMLPurifier/HTMLPurifier/CSSDefinition.php new file mode 100644 index 0000000000..07cc941758 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/CSSDefinition.php @@ -0,0 +1,474 @@ +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); + } + + /** + * @param HTMLPurifier_Config $config + */ + protected function doSetupProprietary($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(); + + // vendor specific prefixes of opacity + $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')); + + } + + /** + * @param HTMLPurifier_Config $config + */ + protected function doSetupTricky($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')); + $this->info['opacity'] = new HTMLPurifier_AttrDef_CSS_AlphaValue(); + } + + /** + * @param HTMLPurifier_Config $config + */ + protected function doSetupTrusted($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. + * @param HTMLPurifier_Config $config + * @todo Refactor duplicate elements into common class (probably using + * composition, not inheritance). + */ + protected function setupConfigStuff($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]); + } + } + } + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/ChildDef.php b/extlib/HTMLPurifier/HTMLPurifier/ChildDef.php new file mode 100644 index 0000000000..8eb17b82e1 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/ChildDef.php @@ -0,0 +1,52 @@ +elements; + } + + /** + * Validates nodes according to definition and returns modification. + * + * @param HTMLPurifier_Node[] $children Array of HTMLPurifier_Node + * @param HTMLPurifier_Config $config HTMLPurifier_Config object + * @param HTMLPurifier_Context $context HTMLPurifier_Context object + * @return bool|array true to leave nodes as is, false to remove parent node, array of replacement children + */ + abstract public function validateChildren($children, $config, $context); +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/ChildDef/Chameleon.php b/extlib/HTMLPurifier/HTMLPurifier/ChildDef/Chameleon.php new file mode 100644 index 0000000000..7439be26b6 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/ChildDef/Chameleon.php @@ -0,0 +1,67 @@ +inline = new HTMLPurifier_ChildDef_Optional($inline); + $this->block = new HTMLPurifier_ChildDef_Optional($block); + $this->elements = $this->block->elements; + } + + /** + * @param HTMLPurifier_Node[] $children + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool + */ + public function validateChildren($children, $config, $context) + { + if ($context->get('IsInline') === false) { + return $this->block->validateChildren( + $children, + $config, + $context + ); + } else { + return $this->inline->validateChildren( + $children, + $config, + $context + ); + } + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/ChildDef/Custom.php b/extlib/HTMLPurifier/HTMLPurifier/ChildDef/Custom.php new file mode 100644 index 0000000000..128132e96d --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/ChildDef/Custom.php @@ -0,0 +1,102 @@ +dtd_regex = $dtd_regex; + $this->_compileRegex(); + } + + /** + * Compiles the PCRE regex from a DTD regex ($dtd_regex to $_pcre_regex) + */ + protected function _compileRegex() + { + $raw = str_replace(' ', '', $this->dtd_regex); + if ($raw{0} != '(') { + $raw = "($raw)"; + } + $el = '[#a-zA-Z0-9_.-]+'; + $reg = $raw; + + // COMPLICATED! AND MIGHT BE BUGGY! I HAVE NO CLUE WHAT I'M + // DOING! Seriously: if there's problems, please report them. + + // collect all elements into the $elements array + preg_match_all("/$el/", $reg, $matches); + foreach ($matches[0] as $match) { + $this->elements[$match] = true; + } + + // setup all elements as parentheticals with leading commas + $reg = preg_replace("/$el/", '(,\\0)', $reg); + + // remove commas when they were not solicited + $reg = preg_replace("/([^,(|]\(+),/", '\\1', $reg); + + // remove all non-paranthetical commas: they are handled by first regex + $reg = preg_replace("/,\(/", '(', $reg); + + $this->_pcre_regex = $reg; + } + + /** + * @param HTMLPurifier_Node[] $children + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool + */ + public function validateChildren($children, $config, $context) + { + $list_of_children = ''; + $nesting = 0; // depth into the nest + foreach ($children as $node) { + if (!empty($node->is_whitespace)) { + continue; + } + $list_of_children .= $node->name . ','; + } + // add leading comma to deal with stray comma declarations + $list_of_children = ',' . rtrim($list_of_children, ','); + $okay = + preg_match( + '/^,?' . $this->_pcre_regex . '$/', + $list_of_children + ); + return (bool)$okay; + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/ChildDef/Empty.php b/extlib/HTMLPurifier/HTMLPurifier/ChildDef/Empty.php new file mode 100644 index 0000000000..a8a6cbdd2c --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/ChildDef/Empty.php @@ -0,0 +1,38 @@ + true, 'ul' => true, 'ol' => true); + + /** + * @param array $children + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return array + */ + public function validateChildren($children, $config, $context) + { + // Flag for subclasses + $this->whitespace = false; + + // if there are no tokens, delete parent node + if (empty($children)) { + return false; + } + + // the new set of children + $result = array(); + + // a little sanity check to make sure it's not ALL whitespace + $all_whitespace = true; + + $current_li = false; + + foreach ($children as $node) { + if (!empty($node->is_whitespace)) { + $result[] = $node; + continue; + } + $all_whitespace = false; // phew, we're not talking about whitespace + + if ($node->name === 'li') { + // good + $current_li = $node; + $result[] = $node; + } else { + // we want to tuck this into the previous li + // Invariant: we expect the node to be ol/ul + // ToDo: Make this more robust in the case of not ol/ul + // by distinguishing between existing li and li created + // to handle non-list elements; non-list elements should + // not be appended to an existing li; only li created + // for non-list. This distinction is not currently made. + if ($current_li === false) { + $current_li = new HTMLPurifier_Node_Element('li'); + $result[] = $current_li; + } + $current_li->children[] = $node; + $current_li->empty = false; // XXX fascinating! Check for this error elsewhere ToDo + } + } + if (empty($result)) { + return false; + } + if ($all_whitespace) { + return false; + } + return $result; + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/ChildDef/Optional.php b/extlib/HTMLPurifier/HTMLPurifier/ChildDef/Optional.php new file mode 100644 index 0000000000..b9468063b1 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/ChildDef/Optional.php @@ -0,0 +1,45 @@ +whitespace) { + return $children; + } else { + return array(); + } + } + return $result; + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/ChildDef/Required.php b/extlib/HTMLPurifier/HTMLPurifier/ChildDef/Required.php new file mode 100644 index 0000000000..0d1c8f5f39 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/ChildDef/Required.php @@ -0,0 +1,118 @@ + $x) { + $elements[$i] = true; + if (empty($i)) { + unset($elements[$i]); + } // remove blank + } + } + $this->elements = $elements; + } + + /** + * @type bool + */ + public $allow_empty = false; + + /** + * @type string + */ + public $type = 'required'; + + /** + * @param array $children + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return array + */ + public function validateChildren($children, $config, $context) + { + // Flag for subclasses + $this->whitespace = false; + + // if there are no tokens, delete parent node + if (empty($children)) { + return false; + } + + // the new set of children + $result = array(); + + // whether or not parsed character data is allowed + // this controls whether or not we silently drop a tag + // or generate escaped HTML from it + $pcdata_allowed = isset($this->elements['#PCDATA']); + + // a little sanity check to make sure it's not ALL whitespace + $all_whitespace = true; + + $stack = array_reverse($children); + while (!empty($stack)) { + $node = array_pop($stack); + if (!empty($node->is_whitespace)) { + $result[] = $node; + continue; + } + $all_whitespace = false; // phew, we're not talking about whitespace + + if (!isset($this->elements[$node->name])) { + // special case text + // XXX One of these ought to be redundant or something + if ($pcdata_allowed && $node instanceof HTMLPurifier_Node_Text) { + $result[] = $node; + continue; + } + // spill the child contents in + // ToDo: Make configurable + if ($node instanceof HTMLPurifier_Node_Element) { + for ($i = count($node->children) - 1; $i >= 0; $i--) { + $stack[] = $node->children[$i]; + } + continue; + } + continue; + } + $result[] = $node; + } + if (empty($result)) { + return false; + } + if ($all_whitespace) { + $this->whitespace = true; + return false; + } + return $result; + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/ChildDef/StrictBlockquote.php b/extlib/HTMLPurifier/HTMLPurifier/ChildDef/StrictBlockquote.php new file mode 100644 index 0000000000..3270a46e1b --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/ChildDef/StrictBlockquote.php @@ -0,0 +1,110 @@ +init($config); + return $this->fake_elements; + } + + /** + * @param array $children + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return array + */ + public function validateChildren($children, $config, $context) + { + $this->init($config); + + // trick the parent class into thinking it allows more + $this->elements = $this->fake_elements; + $result = parent::validateChildren($children, $config, $context); + $this->elements = $this->real_elements; + + if ($result === false) { + return array(); + } + if ($result === true) { + $result = $children; + } + + $def = $config->getHTMLDefinition(); + $block_wrap_name = $def->info_block_wrapper; + $block_wrap = false; + $ret = array(); + + foreach ($result as $node) { + if ($block_wrap === false) { + if (($node instanceof HTMLPurifier_Node_Text && !$node->is_whitespace) || + ($node instanceof HTMLPurifier_Node_Element && !isset($this->elements[$node->name]))) { + $block_wrap = new HTMLPurifier_Node_Element($def->info_block_wrapper); + $ret[] = $block_wrap; + } + } else { + if ($node instanceof HTMLPurifier_Node_Element && isset($this->elements[$node->name])) { + $block_wrap = false; + + } + } + if ($block_wrap) { + $block_wrap->children[] = $node; + } else { + $ret[] = $node; + } + } + return $ret; + } + + /** + * @param HTMLPurifier_Config $config + */ + private function init($config) + { + if (!$this->init) { + $def = $config->getHTMLDefinition(); + // allow all inline elements + $this->real_elements = $this->elements; + $this->fake_elements = $def->info_content_sets['Flow']; + $this->fake_elements['#PCDATA'] = true; + $this->init = true; + } + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/ChildDef/Table.php b/extlib/HTMLPurifier/HTMLPurifier/ChildDef/Table.php new file mode 100644 index 0000000000..3e4a0f2182 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/ChildDef/Table.php @@ -0,0 +1,224 @@ + true, + 'tbody' => true, + 'thead' => true, + 'tfoot' => true, + 'caption' => true, + 'colgroup' => true, + 'col' => true + ); + + public function __construct() + { + } + + /** + * @param array $children + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return array + */ + public function validateChildren($children, $config, $context) + { + if (empty($children)) { + return false; + } + + // only one of these elements is allowed in a table + $caption = false; + $thead = false; + $tfoot = false; + + // whitespace + $initial_ws = array(); + $after_caption_ws = array(); + $after_thead_ws = array(); + $after_tfoot_ws = array(); + + // as many of these as you want + $cols = array(); + $content = array(); + + $tbody_mode = false; // if true, then we need to wrap any stray + // s with a . + + $ws_accum =& $initial_ws; + + foreach ($children as $node) { + if ($node instanceof HTMLPurifier_Node_Comment) { + $ws_accum[] = $node; + continue; + } + switch ($node->name) { + case 'tbody': + $tbody_mode = true; + // fall through + case 'tr': + $content[] = $node; + $ws_accum =& $content; + break; + case 'caption': + // there can only be one caption! + if ($caption !== false) break; + $caption = $node; + $ws_accum =& $after_caption_ws; + break; + case 'thead': + $tbody_mode = true; + // XXX This breaks rendering properties with + // Firefox, which never floats a to + // the top. Ever. (Our scheme will float the + // first to the top.) So maybe + // s that are not first should be + // turned into ? Very tricky, indeed. + if ($thead === false) { + $thead = $node; + $ws_accum =& $after_thead_ws; + } else { + // Oops, there's a second one! What + // should we do? Current behavior is to + // transmutate the first and last entries into + // tbody tags, and then put into content. + // Maybe a better idea is to *attach + // it* to the existing thead or tfoot? + // We don't do this, because Firefox + // doesn't float an extra tfoot to the + // bottom like it does for the first one. + $node->name = 'tbody'; + $content[] = $node; + $ws_accum =& $content; + } + break; + case 'tfoot': + // see above for some aveats + $tbody_mode = true; + if ($tfoot === false) { + $tfoot = $node; + $ws_accum =& $after_tfoot_ws; + } else { + $node->name = 'tbody'; + $content[] = $node; + $ws_accum =& $content; + } + break; + case 'colgroup': + case 'col': + $cols[] = $node; + $ws_accum =& $cols; + break; + case '#PCDATA': + // How is whitespace handled? We treat is as sticky to + // the *end* of the previous element. So all of the + // nonsense we have worked on is to keep things + // together. + if (!empty($node->is_whitespace)) { + $ws_accum[] = $node; + } + break; + } + } + + if (empty($content)) { + return false; + } + + $ret = $initial_ws; + if ($caption !== false) { + $ret[] = $caption; + $ret = array_merge($ret, $after_caption_ws); + } + if ($cols !== false) { + $ret = array_merge($ret, $cols); + } + if ($thead !== false) { + $ret[] = $thead; + $ret = array_merge($ret, $after_thead_ws); + } + if ($tfoot !== false) { + $ret[] = $tfoot; + $ret = array_merge($ret, $after_tfoot_ws); + } + + if ($tbody_mode) { + // we have to shuffle tr into tbody + $current_tr_tbody = null; + + foreach($content as $node) { + switch ($node->name) { + case 'tbody': + $current_tr_tbody = null; + $ret[] = $node; + break; + case 'tr': + if ($current_tr_tbody === null) { + $current_tr_tbody = new HTMLPurifier_Node_Element('tbody'); + $ret[] = $current_tr_tbody; + } + $current_tr_tbody->children[] = $node; + break; + case '#PCDATA': + assert($node->is_whitespace); + if ($current_tr_tbody === null) { + $ret[] = $node; + } else { + $current_tr_tbody->children[] = $node; + } + break; + } + } + } else { + $ret = array_merge($ret, $content); + } + + return $ret; + + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/Config.php b/extlib/HTMLPurifier/HTMLPurifier/Config.php new file mode 100644 index 0000000000..2b2db0c264 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/Config.php @@ -0,0 +1,920 @@ +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 $schema Schema object + * @return HTMLPurifier_Config Configured object + */ + public static function create($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 HTMLPurifier_Config default object. + */ + public static function createDefault() + { + $definition = HTMLPurifier_ConfigSchema::instance(); + $config = new HTMLPurifier_Config($definition); + return $config; + } + + /** + * Retrieves a value from the configuration. + * + * @param string $key String key + * @param mixed $a + * + * @return mixed + */ + public function get($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); + } + + /** + * Retrieves an array of directives to values from a given namespace + * + * @param string $namespace String namespace + * + * @return array + */ + public function getBatch($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 + * + * @param string $namespace Namespace to get serial for + * + * @return string + * @note Revision is handled specially and is removed from the batch + * before processing! + */ + public function getBatchSerial($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 + * + * @return string + */ + 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 string $key key + * @param mixed $value value + * @param mixed $a + */ + public function set($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 + * + * @param array $lookup + * + * @return string + */ + private function _listify($lookup) + { + $list = array(); + foreach ($lookup as $name => $b) { + $list[] = $name; + } + return implode(', ', $list); + } + + /** + * Retrieves object reference to the HTML definition. + * + * @param bool $raw Return a copy that has not been setup yet. Must be + * called before it's been setup, otherwise won't work. + * @param bool $optimized If true, this method may return null, to + * indicate that a cached version of the modified + * definition object is available and no further edits + * are necessary. Consider using + * maybeGetRawHTMLDefinition, which is more explicitly + * named, instead. + * + * @return HTMLPurifier_HTMLDefinition + */ + public function getHTMLDefinition($raw = false, $optimized = false) + { + return $this->getDefinition('HTML', $raw, $optimized); + } + + /** + * Retrieves object reference to the CSS definition + * + * @param bool $raw Return a copy that has not been setup yet. Must be + * called before it's been setup, otherwise won't work. + * @param bool $optimized If true, this method may return null, to + * indicate that a cached version of the modified + * definition object is available and no further edits + * are necessary. Consider using + * maybeGetRawCSSDefinition, which is more explicitly + * named, instead. + * + * @return HTMLPurifier_CSSDefinition + */ + public function getCSSDefinition($raw = false, $optimized = false) + { + return $this->getDefinition('CSS', $raw, $optimized); + } + + /** + * Retrieves object reference to the URI definition + * + * @param bool $raw Return a copy that has not been setup yet. Must be + * called before it's been setup, otherwise won't work. + * @param bool $optimized If true, this method may return null, to + * indicate that a cached version of the modified + * definition object is available and no further edits + * are necessary. Consider using + * maybeGetRawURIDefinition, which is more explicitly + * named, instead. + * + * @return HTMLPurifier_URIDefinition + */ + public function getURIDefinition($raw = false, $optimized = false) + { + return $this->getDefinition('URI', $raw, $optimized); + } + + /** + * Retrieves a definition + * + * @param string $type Type of definition: HTML, CSS, etc + * @param bool $raw Whether or not definition should be returned raw + * @param bool $optimized Only has an effect when $raw is true. Whether + * or not to return null if the result is already present in + * the cache. This is off by default for backwards + * compatibility reasons, but you need to do things this + * way in order to ensure that caching is done properly. + * Check out enduser-customize.html for more details. + * We probably won't ever change this default, as much as the + * maybe semantics is the "right thing to do." + * + * @throws HTMLPurifier_Exception + * @return HTMLPurifier_Definition + */ + public function getDefinition($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!"); + } + + /** + * Initialise definition + * + * @param string $type What type of definition to create + * + * @return HTMLPurifier_CSSDefinition|HTMLPurifier_HTMLDefinition|HTMLPurifier_URIDefinition + * @throws HTMLPurifier_Exception + */ + private function initDefinition($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); + } + + /** + * @return HTMLPurifier_HTMLDefinition + */ + public function maybeGetRawHTMLDefinition() + { + return $this->getDefinition('HTML', true, true); + } + + /** + * @return HTMLPurifier_CSSDefinition + */ + public function maybeGetRawCSSDefinition() + { + return $this->getDefinition('CSS', true, true); + } + + /** + * @return HTMLPurifier_URIDefinition + */ + public function maybeGetRawURIDefinition() + { + return $this->getDefinition('URI', true, true); + } + + /** + * Loads configuration values from an array with the following structure: + * Namespace.Directive => Value + * + * @param array $config_array Configuration associative array + */ + public function loadArray($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 => $value2) { + $this->set($namespace .'.'. $directive, $value2); + } + } + } + } + + /** + * 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 array $allowed List of allowed namespaces/directives + * @param HTMLPurifier_ConfigSchema $schema Schema to use, if not global copy + * + * @return array + */ + public static function getAllowedDirectivesForForm($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 $array $_GET or $_POST array to import + * @param string|bool $index Index/name that the config variables are in + * @param array|bool $allowed List of allowed namespaces/directives + * @param bool $mq_fix Boolean whether or not to enable magic quotes fix + * @param HTMLPurifier_ConfigSchema $schema Schema to use, if not global copy + * + * @return mixed + */ + public static function loadArrayFromForm($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. + * + * @param array $array $_GET or $_POST array to import + * @param string|bool $index Index/name that the config variables are in + * @param array|bool $allowed List of allowed namespaces/directives + * @param bool $mq_fix Boolean whether or not to enable magic quotes fix + */ + public function mergeArrayFromForm($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 + * + * @param array $array $_GET or $_POST array to import + * @param string|bool $index Index/name that the config variables are in + * @param array|bool $allowed List of allowed namespaces/directives + * @param bool $mq_fix Boolean whether or not to enable magic quotes fix + * @param HTMLPurifier_ConfigSchema $schema Schema to use, if not global copy + * + * @return array + */ + public static function prepareArrayFromForm($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 string $filename Name of ini file + */ + public function loadIni($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 string|bool $error String error message, or false for no error + * + * @return bool + */ + public function isFinalized($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. + * + * @param string $msg An error message + * @param int $no An error number + */ + protected function triggerError($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. + * + * @return string + */ + public function serialize() + { + $this->getDefinition('HTML'); + $this->getDefinition('CSS'); + $this->getDefinition('URI'); + return serialize($this); + } + +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema.php b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema.php new file mode 100644 index 0000000000..bfbb0f92f5 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema.php @@ -0,0 +1,176 @@ + 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. + * @type array + */ + public $info = array(); + + /** + * Application-wide singleton + * @type HTMLPurifier_ConfigSchema + */ + protected static $singleton; + + public function __construct() + { + $this->defaultPlist = new HTMLPurifier_PropertyList(); + } + + /** + * Unserializes the default ConfigSchema. + * @return HTMLPurifier_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. + * @param HTMLPurifier_ConfigSchema $prototype + * @return HTMLPurifier_ConfigSchema + */ + public static function instance($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 string $key Name of directive + * @param mixed $default Default value of directive + * @param string $type Allowed type of the directive. See + * HTMLPurifier_DirectiveDef::$type for allowed values + * @param bool $allow_null Whether or not to allow null values + */ + public function add($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 string $key Name of Directive + * @param array $aliases Hash of aliased values to the real alias + */ + public function addValueAliases($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 string $key Name of directive + * @param array $allowed Lookup array of allowed values + */ + public function addAllowedValues($key, $allowed) + { + $this->info[$key]->allowed = $allowed; + } + + /** + * Defines a directive alias for backwards compatibility + * @param string $key Directive that will be aliased + * @param string $new_key Directive that the alias will be to + */ + public function addAlias($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; + } + } + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/Builder/ConfigSchema.php b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/Builder/ConfigSchema.php new file mode 100644 index 0000000000..d5906cd46d --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/Builder/ConfigSchema.php @@ -0,0 +1,48 @@ +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/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/Builder/Xml.php b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/Builder/Xml.php new file mode 100644 index 0000000000..5fa56f7ddb --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/Builder/Xml.php @@ -0,0 +1,144 @@ +startElement('div'); + + $purifier = HTMLPurifier::getInstance(); + $html = $purifier->purify($html); + $this->writeAttribute('xmlns', 'http://www.w3.org/1999/xhtml'); + $this->writeRaw($html); + + $this->endElement(); // div + } + + /** + * @param mixed $var + * @return string + */ + protected function export($var) + { + if ($var === array()) { + return 'array()'; + } + return var_export($var, true); + } + + /** + * @param HTMLPurifier_ConfigSchema_Interchange $interchange + */ + public function build($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(); + } + + /** + * @param HTMLPurifier_ConfigSchema_Interchange_Directive $directive + */ + public function buildDirective($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/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/Exception.php b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/Exception.php new file mode 100644 index 0000000000..2671516c58 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/Exception.php @@ -0,0 +1,11 @@ + array(directive info) + * @type HTMLPurifier_ConfigSchema_Interchange_Directive[] + */ + public $directives = array(); + + /** + * Adds a directive array to $directives + * @param HTMLPurifier_ConfigSchema_Interchange_Directive $directive + * @throws HTMLPurifier_ConfigSchema_Exception + */ + public function addDirective($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/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/Interchange/Directive.php b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/Interchange/Directive.php new file mode 100644 index 0000000000..127a39a673 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/Interchange/Directive.php @@ -0,0 +1,89 @@ + true). + * Null if all values are allowed. + * @type array + */ + public $allowed; + + /** + * List of aliases for the directive. + * e.g. array(new HTMLPurifier_ConfigSchema_Interchange_Id('Ns', 'Dir'))). + * @type HTMLPurifier_ConfigSchema_Interchange_Id[] + */ + public $aliases = array(); + + /** + * Hash of value aliases, e.g. array('alt' => 'real'). Null if value + * aliasing is disabled (necessary for non-scalar types). + * @type array + */ + public $valueAliases; + + /** + * Version of HTML Purifier the directive was introduced, e.g. '1.3.1'. + * Null if the directive has always existed. + * @type string + */ + public $version; + + /** + * ID of directive that supercedes this old directive. + * Null if not deprecated. + * @type HTMLPurifier_ConfigSchema_Interchange_Id + */ + public $deprecatedUse; + + /** + * Version of HTML Purifier this directive was deprecated. Null if not + * deprecated. + * @type string + */ + public $deprecatedVersion; + + /** + * List of external projects this directive depends on, e.g. array('CSSTidy'). + * @type array + */ + public $external = array(); +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/Interchange/Id.php b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/Interchange/Id.php new file mode 100644 index 0000000000..126f09d957 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/Interchange/Id.php @@ -0,0 +1,58 @@ +key = $key; + } + + /** + * @return string + * @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 $this->key; + } + + /** + * @return string + */ + public function getRootNamespace() + { + return substr($this->key, 0, strpos($this->key, ".")); + } + + /** + * @return string + */ + public function getDirective() + { + return substr($this->key, strpos($this->key, ".") + 1); + } + + /** + * @param string $id + * @return HTMLPurifier_ConfigSchema_Interchange_Id + */ + public static function make($id) + { + return new HTMLPurifier_ConfigSchema_Interchange_Id($id); + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/InterchangeBuilder.php b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/InterchangeBuilder.php new file mode 100644 index 0000000000..655e6dd1b9 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/InterchangeBuilder.php @@ -0,0 +1,226 @@ +varParser = $varParser ? $varParser : new HTMLPurifier_VarParser_Native(); + } + + /** + * @param string $dir + * @return HTMLPurifier_ConfigSchema_Interchange + */ + public static function buildFromDirectory($dir = null) + { + $builder = new HTMLPurifier_ConfigSchema_InterchangeBuilder(); + $interchange = new HTMLPurifier_ConfigSchema_Interchange(); + return $builder->buildDir($interchange, $dir); + } + + /** + * @param HTMLPurifier_ConfigSchema_Interchange $interchange + * @param string $dir + * @return HTMLPurifier_ConfigSchema_Interchange + */ + public function buildDir($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; + } + + /** + * @param HTMLPurifier_ConfigSchema_Interchange $interchange + * @param string $file + */ + public function buildFile($interchange, $file) + { + $parser = new HTMLPurifier_StringHashParser(); + $this->build( + $interchange, + new HTMLPurifier_StringHash($parser->parseFile($file)) + ); + } + + /** + * Builds an interchange object based on a hash. + * @param HTMLPurifier_ConfigSchema_Interchange $interchange HTMLPurifier_ConfigSchema_Interchange object to build + * @param HTMLPurifier_StringHash $hash source data + * @throws HTMLPurifier_ConfigSchema_Exception + */ + public function build($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); + } + + /** + * @param HTMLPurifier_ConfigSchema_Interchange $interchange + * @param HTMLPurifier_StringHash $hash + * @throws HTMLPurifier_ConfigSchema_Exception + */ + public function buildDirective($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 + * @param string $contents + */ + protected function evalArray($contents) + { + return eval('return array(' . $contents . ');'); + } + + /** + * Converts an array list into a lookup array. + * @param array $array + * @return array + */ + protected function lookup($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. + * @param string $id + * @return HTMLPurifier_ConfigSchema_Interchange_Id + */ + protected function id($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 HTMLPurifier_StringHash $hash Hash to check. + */ + protected function _findUnused($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/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/Validator.php b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/Validator.php new file mode 100644 index 0000000000..fb31277889 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/Validator.php @@ -0,0 +1,248 @@ +parser = new HTMLPurifier_VarParser(); + } + + /** + * Validates a fully-formed interchange object. + * @param HTMLPurifier_ConfigSchema_Interchange $interchange + * @return bool + */ + public function validate($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. + * @param HTMLPurifier_ConfigSchema_Interchange_Id $id + */ + public function validateId($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. + * @param HTMLPurifier_ConfigSchema_Interchange_Directive $d + */ + public function validateDirective($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. + * @param HTMLPurifier_ConfigSchema_Interchange_Directive $d + */ + public function validateDirectiveAllowed($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. + * @param HTMLPurifier_ConfigSchema_Interchange_Directive $d + */ + public function validateDirectiveValueAliases($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. + * @param HTMLPurifier_ConfigSchema_Interchange_Directive $d + */ + public function validateDirectiveAliases($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. + * @param $obj + * @param $member + * @return HTMLPurifier_ConfigSchema_ValidatorAtom + */ + protected function with($obj, $member) + { + return new HTMLPurifier_ConfigSchema_ValidatorAtom($this->getFormattedContext(), $obj, $member); + } + + /** + * Emits an error, providing helpful context. + * @throws HTMLPurifier_ConfigSchema_Exception + */ + protected function error($target, $msg) + { + if ($target !== false) { + $prefix = ucfirst($target) . ' in ' . $this->getFormattedContext(); + } else { + $prefix = ucfirst($this->getFormattedContext()); + } + throw new HTMLPurifier_ConfigSchema_Exception(trim($prefix . ' ' . $msg)); + } + + /** + * Returns a formatted context string. + * @return string + */ + protected function getFormattedContext() + { + return implode(' in ', array_reverse($this->context)); + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/ValidatorAtom.php b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/ValidatorAtom.php new file mode 100644 index 0000000000..c9aa3644af --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/ValidatorAtom.php @@ -0,0 +1,130 @@ +context = $context; + $this->obj = $obj; + $this->member = $member; + $this->contents =& $obj->$member; + } + + /** + * @return HTMLPurifier_ConfigSchema_ValidatorAtom + */ + public function assertIsString() + { + if (!is_string($this->contents)) { + $this->error('must be a string'); + } + return $this; + } + + /** + * @return HTMLPurifier_ConfigSchema_ValidatorAtom + */ + public function assertIsBool() + { + if (!is_bool($this->contents)) { + $this->error('must be a boolean'); + } + return $this; + } + + /** + * @return HTMLPurifier_ConfigSchema_ValidatorAtom + */ + public function assertIsArray() + { + if (!is_array($this->contents)) { + $this->error('must be an array'); + } + return $this; + } + + /** + * @return HTMLPurifier_ConfigSchema_ValidatorAtom + */ + public function assertNotNull() + { + if ($this->contents === null) { + $this->error('must not be null'); + } + return $this; + } + + /** + * @return HTMLPurifier_ConfigSchema_ValidatorAtom + */ + public function assertAlnum() + { + $this->assertIsString(); + if (!ctype_alnum($this->contents)) { + $this->error('must be alphanumeric'); + } + return $this; + } + + /** + * @return HTMLPurifier_ConfigSchema_ValidatorAtom + */ + public function assertNotEmpty() + { + if (empty($this->contents)) { + $this->error('must not be empty'); + } + return $this; + } + + /** + * @return HTMLPurifier_ConfigSchema_ValidatorAtom + */ + public function assertIsLookup() + { + $this->assertIsArray(); + foreach ($this->contents as $v) { + if ($v !== true) { + $this->error('must be a lookup array'); + } + } + return $this; + } + + /** + * @param string $msg + * @throws HTMLPurifier_ConfigSchema_Exception + */ + protected function error($msg) + { + throw new HTMLPurifier_ConfigSchema_Exception(ucfirst($this->member) . ' in ' . $this->context . ' ' . $msg); + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema.ser b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema.ser new file mode 100644 index 0000000000..1e6ccd2275 Binary files /dev/null and b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema.ser differ diff --git a/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Attr.AllowedClasses.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Attr.AllowedClasses.txt new file mode 100644 index 0000000000..0517fed0a1 --- /dev/null +++ b/extlib/HTMLPurifier/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/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Attr.AllowedFrameTargets.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Attr.AllowedFrameTargets.txt new file mode 100644 index 0000000000..249edd647b --- /dev/null +++ b/extlib/HTMLPurifier/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/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Attr.AllowedRel.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Attr.AllowedRel.txt new file mode 100644 index 0000000000..9a8fa6a2e2 --- /dev/null +++ b/extlib/HTMLPurifier/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/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Attr.AllowedRev.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Attr.AllowedRev.txt new file mode 100644 index 0000000000..b017883485 --- /dev/null +++ b/extlib/HTMLPurifier/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/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Attr.ClassUseCDATA.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Attr.ClassUseCDATA.txt new file mode 100644 index 0000000000..e774b823b1 --- /dev/null +++ b/extlib/HTMLPurifier/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/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Attr.DefaultImageAlt.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Attr.DefaultImageAlt.txt new file mode 100644 index 0000000000..533165e175 --- /dev/null +++ b/extlib/HTMLPurifier/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/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Attr.DefaultInvalidImage.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Attr.DefaultInvalidImage.txt new file mode 100644 index 0000000000..9eb7e38469 --- /dev/null +++ b/extlib/HTMLPurifier/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/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Attr.DefaultInvalidImageAlt.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Attr.DefaultInvalidImageAlt.txt new file mode 100644 index 0000000000..2f17bf477a --- /dev/null +++ b/extlib/HTMLPurifier/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/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Attr.DefaultTextDir.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Attr.DefaultTextDir.txt new file mode 100644 index 0000000000..52654b53ae --- /dev/null +++ b/extlib/HTMLPurifier/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/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Attr.EnableID.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Attr.EnableID.txt new file mode 100644 index 0000000000..6440d21032 --- /dev/null +++ b/extlib/HTMLPurifier/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/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Attr.ForbiddenClasses.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Attr.ForbiddenClasses.txt new file mode 100644 index 0000000000..f31d226f58 --- /dev/null +++ b/extlib/HTMLPurifier/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/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Attr.IDBlacklist.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Attr.IDBlacklist.txt new file mode 100644 index 0000000000..5f2b5e3d2c --- /dev/null +++ b/extlib/HTMLPurifier/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/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Attr.IDBlacklistRegexp.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Attr.IDBlacklistRegexp.txt new file mode 100644 index 0000000000..6f5824586e --- /dev/null +++ b/extlib/HTMLPurifier/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/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Attr.IDPrefix.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Attr.IDPrefix.txt new file mode 100644 index 0000000000..cc49d43fd0 --- /dev/null +++ b/extlib/HTMLPurifier/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/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Attr.IDPrefixLocal.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Attr.IDPrefixLocal.txt new file mode 100644 index 0000000000..2c5924a7ad --- /dev/null +++ b/extlib/HTMLPurifier/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/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/AutoFormat.AutoParagraph.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/AutoFormat.AutoParagraph.txt new file mode 100644 index 0000000000..d5caa1bb97 --- /dev/null +++ b/extlib/HTMLPurifier/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/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/AutoFormat.Custom.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/AutoFormat.Custom.txt new file mode 100644 index 0000000000..2a476481af --- /dev/null +++ b/extlib/HTMLPurifier/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. +

+--# vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/AutoFormat.DisplayLinkURI.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/AutoFormat.DisplayLinkURI.txt new file mode 100644 index 0000000000..663064a344 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/AutoFormat.DisplayLinkURI.txt @@ -0,0 +1,11 @@ +AutoFormat.DisplayLinkURI +TYPE: bool +VERSION: 3.2.0 +DEFAULT: false +--DESCRIPTION-- +

+ 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). +

+--# vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/AutoFormat.Linkify.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/AutoFormat.Linkify.txt new file mode 100644 index 0000000000..3a48ba960e --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/AutoFormat.Linkify.txt @@ -0,0 +1,12 @@ +AutoFormat.Linkify +TYPE: bool +VERSION: 2.0.1 +DEFAULT: false +--DESCRIPTION-- + +

+ This directive turns on linkification, auto-linking http, ftp and + https URLs. a tags with the href attribute + must be allowed. +

+--# vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/AutoFormat.PurifierLinkify.DocURL.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/AutoFormat.PurifierLinkify.DocURL.txt new file mode 100644 index 0000000000..db58b13464 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/AutoFormat.PurifierLinkify.DocURL.txt @@ -0,0 +1,12 @@ +AutoFormat.PurifierLinkify.DocURL +TYPE: string +VERSION: 2.0.1 +DEFAULT: '#%s' +ALIASES: AutoFormatParam.PurifierLinkifyDocURL +--DESCRIPTION-- +

+ Location of configuration documentation to link to, let %s substitute + into the configuration's namespace and directive names sans the percent + sign. +

+--# vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/AutoFormat.PurifierLinkify.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/AutoFormat.PurifierLinkify.txt new file mode 100644 index 0000000000..7996488be0 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/AutoFormat.PurifierLinkify.txt @@ -0,0 +1,12 @@ +AutoFormat.PurifierLinkify +TYPE: bool +VERSION: 2.0.1 +DEFAULT: false +--DESCRIPTION-- + +

+ Internal auto-formatter that converts configuration directives in + syntax %Namespace.Directive to links. a tags + with the href attribute must be allowed. +

+--# vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/AutoFormat.RemoveEmpty.Predicate.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/AutoFormat.RemoveEmpty.Predicate.txt new file mode 100644 index 0000000000..6367fe23c9 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/AutoFormat.RemoveEmpty.Predicate.txt @@ -0,0 +1,14 @@ +AutoFormat.RemoveEmpty.Predicate +TYPE: hash +VERSION: 4.7.0 +DEFAULT: array('colgroup' => array(), 'th' => array(), 'td' => array(), 'iframe' => array('src')) +--DESCRIPTION-- +

+ Given that an element has no contents, it will be removed by default, unless + this predicate dictates otherwise. The predicate can either be an associative + map from tag name to list of attributes that must be present for the element + to be considered preserved: thus, the default always preserves colgroup, + th and td, and also iframe if it + has a src. +

+--# vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/AutoFormat.RemoveEmpty.RemoveNbsp.Exceptions.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/AutoFormat.RemoveEmpty.RemoveNbsp.Exceptions.txt new file mode 100644 index 0000000000..35c393b4e6 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/AutoFormat.RemoveEmpty.RemoveNbsp.Exceptions.txt @@ -0,0 +1,11 @@ +AutoFormat.RemoveEmpty.RemoveNbsp.Exceptions +TYPE: lookup +VERSION: 4.0.0 +DEFAULT: array('td' => true, 'th' => true) +--DESCRIPTION-- +

+ 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. +

+--# vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/AutoFormat.RemoveEmpty.RemoveNbsp.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/AutoFormat.RemoveEmpty.RemoveNbsp.txt new file mode 100644 index 0000000000..ca17eb1dc4 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/AutoFormat.RemoveEmpty.RemoveNbsp.txt @@ -0,0 +1,15 @@ +AutoFormat.RemoveEmpty.RemoveNbsp +TYPE: bool +VERSION: 4.0.0 +DEFAULT: false +--DESCRIPTION-- +

+ 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. +

+--# vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/AutoFormat.RemoveEmpty.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/AutoFormat.RemoveEmpty.txt new file mode 100644 index 0000000000..34657ba47b --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/AutoFormat.RemoveEmpty.txt @@ -0,0 +1,46 @@ +AutoFormat.RemoveEmpty +TYPE: bool +VERSION: 3.2.0 +DEFAULT: false +--DESCRIPTION-- +

+ 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. +

+--# vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/AutoFormat.RemoveSpansWithoutAttributes.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/AutoFormat.RemoveSpansWithoutAttributes.txt new file mode 100644 index 0000000000..dde990ab26 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/AutoFormat.RemoveSpansWithoutAttributes.txt @@ -0,0 +1,11 @@ +AutoFormat.RemoveSpansWithoutAttributes +TYPE: bool +VERSION: 4.0.1 +DEFAULT: false +--DESCRIPTION-- +

+ 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/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/CSS.AllowImportant.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/CSS.AllowImportant.txt new file mode 100644 index 0000000000..b324608f76 --- /dev/null +++ b/extlib/HTMLPurifier/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/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/CSS.AllowTricky.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/CSS.AllowTricky.txt new file mode 100644 index 0000000000..748be0eec8 --- /dev/null +++ b/extlib/HTMLPurifier/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/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/CSS.AllowedFonts.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/CSS.AllowedFonts.txt new file mode 100644 index 0000000000..3fd4654065 --- /dev/null +++ b/extlib/HTMLPurifier/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. +

+--# vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/CSS.AllowedProperties.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/CSS.AllowedProperties.txt new file mode 100644 index 0000000000..460112ebe0 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/CSS.AllowedProperties.txt @@ -0,0 +1,18 @@ +CSS.AllowedProperties +TYPE: lookup/null +VERSION: 3.1.0 +DEFAULT: NULL +--DESCRIPTION-- + +

+ 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/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/CSS.DefinitionRev.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/CSS.DefinitionRev.txt new file mode 100644 index 0000000000..5cb7dda3ba --- /dev/null +++ b/extlib/HTMLPurifier/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. +

+--# vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/CSS.ForbiddenProperties.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/CSS.ForbiddenProperties.txt new file mode 100644 index 0000000000..f1f5c5f12b --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/CSS.ForbiddenProperties.txt @@ -0,0 +1,13 @@ +CSS.ForbiddenProperties +TYPE: lookup +VERSION: 4.2.0 +DEFAULT: array() +--DESCRIPTION-- +

+ 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. +

+--# vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/CSS.MaxImgLength.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/CSS.MaxImgLength.txt new file mode 100644 index 0000000000..7a3291470c --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/CSS.MaxImgLength.txt @@ -0,0 +1,16 @@ +CSS.MaxImgLength +TYPE: string/null +DEFAULT: '1200px' +VERSION: 3.1.1 +--DESCRIPTION-- +

+ 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). +

+--# vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/CSS.Proprietary.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/CSS.Proprietary.txt new file mode 100644 index 0000000000..148eedb8be --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/CSS.Proprietary.txt @@ -0,0 +1,10 @@ +CSS.Proprietary +TYPE: bool +VERSION: 3.0.0 +DEFAULT: false +--DESCRIPTION-- + +

+ Whether or not to allow safe, proprietary CSS values. +

+--# vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/CSS.Trusted.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/CSS.Trusted.txt new file mode 100644 index 0000000000..e733a61e8a --- /dev/null +++ b/extlib/HTMLPurifier/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/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Cache.DefinitionImpl.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Cache.DefinitionImpl.txt new file mode 100644 index 0000000000..c486724c88 --- /dev/null +++ b/extlib/HTMLPurifier/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/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Cache.SerializerPath.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Cache.SerializerPath.txt new file mode 100644 index 0000000000..54036507d6 --- /dev/null +++ b/extlib/HTMLPurifier/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/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Cache.SerializerPermissions.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Cache.SerializerPermissions.txt new file mode 100644 index 0000000000..b2b83d9ab6 --- /dev/null +++ b/extlib/HTMLPurifier/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. +

+--# vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Core.AggressivelyFixLt.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Core.AggressivelyFixLt.txt new file mode 100644 index 0000000000..568cbf3b32 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Core.AggressivelyFixLt.txt @@ -0,0 +1,18 @@ +Core.AggressivelyFixLt +TYPE: bool +VERSION: 2.1.0 +DEFAULT: true +--DESCRIPTION-- +

+ 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/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Core.AllowHostnameUnderscore.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Core.AllowHostnameUnderscore.txt new file mode 100644 index 0000000000..2c910cc7de --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Core.AllowHostnameUnderscore.txt @@ -0,0 +1,16 @@ +Core.AllowHostnameUnderscore +TYPE: bool +VERSION: 4.6.0 +DEFAULT: false +--DESCRIPTION-- +

+ By RFC 1123, underscores are not permitted in host names. + (This is in contrast to the specification for DNS, RFC + 2181, which allows underscores.) + However, most browsers do the right thing when faced with + an underscore in the host name, and so some poorly written + websites are written with the expectation this should work. + Setting this parameter to true relaxes our allowed character + check so that underscores are permitted. +

+--# vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Core.CollectErrors.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Core.CollectErrors.txt new file mode 100644 index 0000000000..d7317911fa --- /dev/null +++ b/extlib/HTMLPurifier/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/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Core.ColorKeywords.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Core.ColorKeywords.txt new file mode 100644 index 0000000000..c572c14ec1 --- /dev/null +++ b/extlib/HTMLPurifier/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/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Core.ConvertDocumentToFragment.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Core.ConvertDocumentToFragment.txt new file mode 100644 index 0000000000..64b114fce2 --- /dev/null +++ b/extlib/HTMLPurifier/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/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Core.DirectLexLineNumberSyncInterval.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Core.DirectLexLineNumberSyncInterval.txt new file mode 100644 index 0000000000..36f16e07ea --- /dev/null +++ b/extlib/HTMLPurifier/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. +

+--# vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Core.DisableExcludes.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Core.DisableExcludes.txt new file mode 100644 index 0000000000..1cd4c2c964 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Core.DisableExcludes.txt @@ -0,0 +1,14 @@ +Core.DisableExcludes +TYPE: bool +DEFAULT: false +VERSION: 4.5.0 +--DESCRIPTION-- +

+ 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/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Core.EnableIDNA.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Core.EnableIDNA.txt new file mode 100644 index 0000000000..ce243c35dc --- /dev/null +++ b/extlib/HTMLPurifier/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/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Core.Encoding.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Core.Encoding.txt new file mode 100644 index 0000000000..8bfb47c3ac --- /dev/null +++ b/extlib/HTMLPurifier/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/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Core.EscapeInvalidChildren.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Core.EscapeInvalidChildren.txt new file mode 100644 index 0000000000..a3881be75c --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Core.EscapeInvalidChildren.txt @@ -0,0 +1,12 @@ +Core.EscapeInvalidChildren +TYPE: bool +DEFAULT: false +--DESCRIPTION-- +

Warning: this configuration option is no longer does anything as of 4.6.0.

+ +

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/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Core.EscapeInvalidTags.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Core.EscapeInvalidTags.txt new file mode 100644 index 0000000000..a7a5b249bb --- /dev/null +++ b/extlib/HTMLPurifier/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/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Core.EscapeNonASCIICharacters.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Core.EscapeNonASCIICharacters.txt new file mode 100644 index 0000000000..abb499948a --- /dev/null +++ b/extlib/HTMLPurifier/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/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Core.HiddenElements.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Core.HiddenElements.txt new file mode 100644 index 0000000000..915391edb7 --- /dev/null +++ b/extlib/HTMLPurifier/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/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Core.Language.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Core.Language.txt new file mode 100644 index 0000000000..233fca14f8 --- /dev/null +++ b/extlib/HTMLPurifier/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/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Core.LexerImpl.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Core.LexerImpl.txt new file mode 100644 index 0000000000..8983e2cca9 --- /dev/null +++ b/extlib/HTMLPurifier/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. +
+
+--# vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Core.MaintainLineNumbers.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Core.MaintainLineNumbers.txt new file mode 100644 index 0000000000..eb841a7597 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Core.MaintainLineNumbers.txt @@ -0,0 +1,16 @@ +Core.MaintainLineNumbers +TYPE: bool/null +VERSION: 2.0.0 +DEFAULT: NULL +--DESCRIPTION-- + +

+ 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. +

+--# vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Core.NormalizeNewlines.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Core.NormalizeNewlines.txt new file mode 100644 index 0000000000..d77f5360d7 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Core.NormalizeNewlines.txt @@ -0,0 +1,11 @@ +Core.NormalizeNewlines +TYPE: bool +VERSION: 4.2.0 +DEFAULT: true +--DESCRIPTION-- +

+ Whether or not to normalize newlines to the operating + system default. When false, HTML Purifier + will attempt to preserve mixed newline files. +

+--# vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Core.RemoveInvalidImg.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Core.RemoveInvalidImg.txt new file mode 100644 index 0000000000..4070c2a0de --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Core.RemoveInvalidImg.txt @@ -0,0 +1,12 @@ +Core.RemoveInvalidImg +TYPE: bool +DEFAULT: true +VERSION: 1.3.0 +--DESCRIPTION-- + +

+ 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/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Core.RemoveProcessingInstructions.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Core.RemoveProcessingInstructions.txt new file mode 100644 index 0000000000..3397d9f71f --- /dev/null +++ b/extlib/HTMLPurifier/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/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Core.RemoveScriptContents.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Core.RemoveScriptContents.txt new file mode 100644 index 0000000000..a4cd966df8 --- /dev/null +++ b/extlib/HTMLPurifier/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/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Filter.Custom.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Filter.Custom.txt new file mode 100644 index 0000000000..3db50ef204 --- /dev/null +++ b/extlib/HTMLPurifier/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. +

+--# vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Filter.ExtractStyleBlocks.Escaping.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Filter.ExtractStyleBlocks.Escaping.txt new file mode 100644 index 0000000000..16829bcda0 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Filter.ExtractStyleBlocks.Escaping.txt @@ -0,0 +1,14 @@ +Filter.ExtractStyleBlocks.Escaping +TYPE: bool +VERSION: 3.0.0 +DEFAULT: true +ALIASES: Filter.ExtractStyleBlocksEscaping, FilterParam.ExtractStyleBlocksEscaping +--DESCRIPTION-- + +

+ 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. +

+--# vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Filter.ExtractStyleBlocks.Scope.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Filter.ExtractStyleBlocks.Scope.txt new file mode 100644 index 0000000000..7f95f54d12 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Filter.ExtractStyleBlocks.Scope.txt @@ -0,0 +1,29 @@ +Filter.ExtractStyleBlocks.Scope +TYPE: string/null +VERSION: 3.0.0 +DEFAULT: NULL +ALIASES: Filter.ExtractStyleBlocksScope, FilterParam.ExtractStyleBlocksScope +--DESCRIPTION-- + +

+ 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. +

+--# vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Filter.ExtractStyleBlocks.TidyImpl.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Filter.ExtractStyleBlocks.TidyImpl.txt new file mode 100644 index 0000000000..6c231b2d7f --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Filter.ExtractStyleBlocks.TidyImpl.txt @@ -0,0 +1,16 @@ +Filter.ExtractStyleBlocks.TidyImpl +TYPE: mixed/null +VERSION: 3.1.0 +DEFAULT: NULL +ALIASES: FilterParam.ExtractStyleBlocksTidyImpl +--DESCRIPTION-- +

+ 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. +

+--# vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Filter.ExtractStyleBlocks.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Filter.ExtractStyleBlocks.txt new file mode 100644 index 0000000000..078d087417 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Filter.ExtractStyleBlocks.txt @@ -0,0 +1,74 @@ +Filter.ExtractStyleBlocks +TYPE: bool +VERSION: 3.1.0 +DEFAULT: false +EXTERNAL: CSSTidy +--DESCRIPTION-- +

+ 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. +

+--# vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Filter.YouTube.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Filter.YouTube.txt new file mode 100644 index 0000000000..321eaa2d80 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Filter.YouTube.txt @@ -0,0 +1,16 @@ +Filter.YouTube +TYPE: bool +VERSION: 3.1.0 +DEFAULT: false +--DESCRIPTION-- +

+ 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. +

+--# vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.Allowed.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.Allowed.txt new file mode 100644 index 0000000000..0b2c106da5 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.Allowed.txt @@ -0,0 +1,25 @@ +HTML.Allowed +TYPE: itext/null +VERSION: 2.0.0 +DEFAULT: NULL +--DESCRIPTION-- + +

+ 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. +

+--# vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.AllowedAttributes.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.AllowedAttributes.txt new file mode 100644 index 0000000000..fcf093f17d --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.AllowedAttributes.txt @@ -0,0 +1,19 @@ +HTML.AllowedAttributes +TYPE: lookup/null +VERSION: 1.3.0 +DEFAULT: NULL +--DESCRIPTION-- + +

+ 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/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.AllowedComments.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.AllowedComments.txt new file mode 100644 index 0000000000..140e21423e --- /dev/null +++ b/extlib/HTMLPurifier/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/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.AllowedCommentsRegexp.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.AllowedCommentsRegexp.txt new file mode 100644 index 0000000000..f22e977d43 --- /dev/null +++ b/extlib/HTMLPurifier/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/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.AllowedElements.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.AllowedElements.txt new file mode 100644 index 0000000000..1d3fa7907d --- /dev/null +++ b/extlib/HTMLPurifier/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. +

+--# vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.AllowedModules.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.AllowedModules.txt new file mode 100644 index 0000000000..5a59a55c08 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.AllowedModules.txt @@ -0,0 +1,20 @@ +HTML.AllowedModules +TYPE: lookup/null +VERSION: 2.0.0 +DEFAULT: NULL +--DESCRIPTION-- + +

+ 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/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.Attr.Name.UseCDATA.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.Attr.Name.UseCDATA.txt new file mode 100644 index 0000000000..151fb7b826 --- /dev/null +++ b/extlib/HTMLPurifier/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/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.BlockWrapper.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.BlockWrapper.txt new file mode 100644 index 0000000000..45ae469ec9 --- /dev/null +++ b/extlib/HTMLPurifier/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. +

+--# vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.CoreModules.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.CoreModules.txt new file mode 100644 index 0000000000..5246188795 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.CoreModules.txt @@ -0,0 +1,23 @@ +HTML.CoreModules +TYPE: lookup +VERSION: 2.0.0 +--DEFAULT-- +array ( + 'Structure' => true, + 'Text' => true, + 'Hypertext' => true, + 'List' => true, + 'NonXMLCommonAttributes' => true, + 'XMLCommonAttributes' => true, + 'CommonAttributes' => true, +) +--DESCRIPTION-- + +

+ 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/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.CustomDoctype.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.CustomDoctype.txt new file mode 100644 index 0000000000..6ed70b599f --- /dev/null +++ b/extlib/HTMLPurifier/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 their own document +type. This directive only applies when %HTML.Doctype is blank. +--# vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.DefinitionID.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.DefinitionID.txt new file mode 100644 index 0000000000..103db754a2 --- /dev/null +++ b/extlib/HTMLPurifier/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: +

+
+$config = HTMLPurifier_Config::createDefault();
+$config->set('HTML', 'DefinitionID', '1');
+$def = $config->getHTMLDefinition();
+$def->addAttribute('a', 'tabindex', 'Number');
+
+

+ 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/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.DefinitionRev.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.DefinitionRev.txt new file mode 100644 index 0000000000..229ae0267a --- /dev/null +++ b/extlib/HTMLPurifier/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/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.Doctype.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.Doctype.txt new file mode 100644 index 0000000000..9dab497f2f --- /dev/null +++ b/extlib/HTMLPurifier/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/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.FlashAllowFullScreen.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.FlashAllowFullScreen.txt new file mode 100644 index 0000000000..7878dc0bf6 --- /dev/null +++ b/extlib/HTMLPurifier/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. +

+--# vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.ForbiddenAttributes.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.ForbiddenAttributes.txt new file mode 100644 index 0000000000..57358f9bad --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.ForbiddenAttributes.txt @@ -0,0 +1,21 @@ +HTML.ForbiddenAttributes +TYPE: lookup +VERSION: 3.1.0 +DEFAULT: array() +--DESCRIPTION-- +

+ 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. +

+--# vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.ForbiddenElements.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.ForbiddenElements.txt new file mode 100644 index 0000000000..93a53e14fb --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.ForbiddenElements.txt @@ -0,0 +1,20 @@ +HTML.ForbiddenElements +TYPE: lookup +VERSION: 3.1.0 +DEFAULT: array() +--DESCRIPTION-- +

+ 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. +

+--# vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.MaxImgLength.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.MaxImgLength.txt new file mode 100644 index 0000000000..e424c386ec --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.MaxImgLength.txt @@ -0,0 +1,14 @@ +HTML.MaxImgLength +TYPE: int/null +DEFAULT: 1200 +VERSION: 3.1.1 +--DESCRIPTION-- +

+ 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/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.Nofollow.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.Nofollow.txt new file mode 100644 index 0000000000..700b30924a --- /dev/null +++ b/extlib/HTMLPurifier/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/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.Parent.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.Parent.txt new file mode 100644 index 0000000000..62e8e160c7 --- /dev/null +++ b/extlib/HTMLPurifier/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. +

+--# vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.Proprietary.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.Proprietary.txt new file mode 100644 index 0000000000..dfb720496d --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.Proprietary.txt @@ -0,0 +1,12 @@ +HTML.Proprietary +TYPE: bool +VERSION: 3.1.0 +DEFAULT: false +--DESCRIPTION-- +

+ 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! +

+--# vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.SafeEmbed.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.SafeEmbed.txt new file mode 100644 index 0000000000..cdda09a4c5 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.SafeEmbed.txt @@ -0,0 +1,13 @@ +HTML.SafeEmbed +TYPE: bool +VERSION: 3.1.1 +DEFAULT: false +--DESCRIPTION-- +

+ 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.

+--# vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.SafeIframe.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.SafeIframe.txt new file mode 100644 index 0000000000..5eb6ec2b5a --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.SafeIframe.txt @@ -0,0 +1,13 @@ +HTML.SafeIframe +TYPE: bool +VERSION: 4.4.0 +DEFAULT: false +--DESCRIPTION-- +

+ 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. +

+--# vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.SafeObject.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.SafeObject.txt new file mode 100644 index 0000000000..ceb342e22b --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.SafeObject.txt @@ -0,0 +1,13 @@ +HTML.SafeObject +TYPE: bool +VERSION: 3.1.1 +DEFAULT: false +--DESCRIPTION-- +

+ 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. +

+--# vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.SafeScripting.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.SafeScripting.txt new file mode 100644 index 0000000000..5ebc7a19d5 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.SafeScripting.txt @@ -0,0 +1,10 @@ +HTML.SafeScripting +TYPE: lookup +VERSION: 4.5.0 +DEFAULT: array() +--DESCRIPTION-- +

+ 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/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.Strict.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.Strict.txt new file mode 100644 index 0000000000..a8b1de56be --- /dev/null +++ b/extlib/HTMLPurifier/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/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.TargetBlank.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.TargetBlank.txt new file mode 100644 index 0000000000..587a16778b --- /dev/null +++ b/extlib/HTMLPurifier/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/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.TidyAdd.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.TidyAdd.txt new file mode 100644 index 0000000000..b4c271b7fa --- /dev/null +++ b/extlib/HTMLPurifier/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/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.TidyLevel.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.TidyLevel.txt new file mode 100644 index 0000000000..4186ccd0d1 --- /dev/null +++ b/extlib/HTMLPurifier/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/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.TidyRemove.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.TidyRemove.txt new file mode 100644 index 0000000000..996762bd1d --- /dev/null +++ b/extlib/HTMLPurifier/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/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.Trusted.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.Trusted.txt new file mode 100644 index 0000000000..1db9237e9e --- /dev/null +++ b/extlib/HTMLPurifier/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/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.XHTML.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/HTML.XHTML.txt new file mode 100644 index 0000000000..2a47e384f4 --- /dev/null +++ b/extlib/HTMLPurifier/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/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Output.CommentScriptContents.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Output.CommentScriptContents.txt new file mode 100644 index 0000000000..08921fde70 --- /dev/null +++ b/extlib/HTMLPurifier/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/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Output.FixInnerHTML.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Output.FixInnerHTML.txt new file mode 100644 index 0000000000..d6f0d9f295 --- /dev/null +++ b/extlib/HTMLPurifier/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. +

+--# vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Output.FlashCompat.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Output.FlashCompat.txt new file mode 100644 index 0000000000..93398e8598 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Output.FlashCompat.txt @@ -0,0 +1,11 @@ +Output.FlashCompat +TYPE: bool +VERSION: 4.1.0 +DEFAULT: false +--DESCRIPTION-- +

+ If true, HTML Purifier will generate Internet Explorer compatibility + code for all object code. This is highly recommended if you enable + %HTML.SafeObject. +

+--# vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Output.Newline.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Output.Newline.txt new file mode 100644 index 0000000000..79f8ad82cf --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Output.Newline.txt @@ -0,0 +1,13 @@ +Output.Newline +TYPE: string/null +VERSION: 2.0.1 +DEFAULT: NULL +--DESCRIPTION-- + +

+ 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. +

+--# vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Output.SortAttr.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Output.SortAttr.txt new file mode 100644 index 0000000000..232b02362a --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Output.SortAttr.txt @@ -0,0 +1,14 @@ +Output.SortAttr +TYPE: bool +VERSION: 3.2.0 +DEFAULT: false +--DESCRIPTION-- +

+ 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. +

+--# vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Output.TidyFormat.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Output.TidyFormat.txt new file mode 100644 index 0000000000..06bab00a0a --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Output.TidyFormat.txt @@ -0,0 +1,25 @@ +Output.TidyFormat +TYPE: bool +VERSION: 1.1.1 +DEFAULT: false +--DESCRIPTION-- +

+ 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/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Test.ForceNoIconv.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/Test.ForceNoIconv.txt new file mode 100644 index 0000000000..071bc0295d --- /dev/null +++ b/extlib/HTMLPurifier/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/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/URI.AllowedSchemes.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/URI.AllowedSchemes.txt new file mode 100644 index 0000000000..666635a5ff --- /dev/null +++ b/extlib/HTMLPurifier/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/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/URI.Base.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/URI.Base.txt new file mode 100644 index 0000000000..876f0680cf --- /dev/null +++ b/extlib/HTMLPurifier/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. +

+--# vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/URI.DefaultScheme.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/URI.DefaultScheme.txt new file mode 100644 index 0000000000..728e378cbe --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/URI.DefaultScheme.txt @@ -0,0 +1,10 @@ +URI.DefaultScheme +TYPE: string +DEFAULT: 'http' +--DESCRIPTION-- + +

+ Defines through what scheme the output will be served, in order to + select the proper object validator when no scheme information is present. +

+--# vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/URI.DefinitionID.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/URI.DefinitionID.txt new file mode 100644 index 0000000000..f05312ba86 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/URI.DefinitionID.txt @@ -0,0 +1,11 @@ +URI.DefinitionID +TYPE: string/null +VERSION: 2.1.0 +DEFAULT: NULL +--DESCRIPTION-- + +

+ Unique identifier for a custom-built URI definition. If you want + to add custom URIFilters, you must specify this value. +

+--# vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/URI.DefinitionRev.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/URI.DefinitionRev.txt new file mode 100644 index 0000000000..80cfea93f7 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/URI.DefinitionRev.txt @@ -0,0 +1,11 @@ +URI.DefinitionRev +TYPE: int +VERSION: 2.1.0 +DEFAULT: 1 +--DESCRIPTION-- + +

+ Revision identifier for your custom definition. See + %HTML.DefinitionRev for details. +

+--# vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/URI.Disable.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/URI.Disable.txt new file mode 100644 index 0000000000..71ce025a2d --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/URI.Disable.txt @@ -0,0 +1,14 @@ +URI.Disable +TYPE: bool +VERSION: 1.3.0 +DEFAULT: false +--DESCRIPTION-- + +

+ 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/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/URI.DisableExternal.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/URI.DisableExternal.txt new file mode 100644 index 0000000000..13c122c8ce --- /dev/null +++ b/extlib/HTMLPurifier/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/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/URI.DisableExternalResources.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/URI.DisableExternalResources.txt new file mode 100644 index 0000000000..abcc1efd61 --- /dev/null +++ b/extlib/HTMLPurifier/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/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/URI.DisableResources.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/URI.DisableResources.txt new file mode 100644 index 0000000000..f891de4996 --- /dev/null +++ b/extlib/HTMLPurifier/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. +

+--# vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/URI.Host.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/URI.Host.txt new file mode 100644 index 0000000000..ee83b121de --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/URI.Host.txt @@ -0,0 +1,19 @@ +URI.Host +TYPE: string/null +VERSION: 1.2.0 +DEFAULT: NULL +--DESCRIPTION-- + +

+ 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/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/URI.HostBlacklist.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/URI.HostBlacklist.txt new file mode 100644 index 0000000000..0b6df7625d --- /dev/null +++ b/extlib/HTMLPurifier/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/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/URI.MakeAbsolute.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/URI.MakeAbsolute.txt new file mode 100644 index 0000000000..4214900a59 --- /dev/null +++ b/extlib/HTMLPurifier/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. +

+--# vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/URI.Munge.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/URI.Munge.txt new file mode 100644 index 0000000000..58c81dcc44 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/URI.Munge.txt @@ -0,0 +1,83 @@ +URI.Munge +TYPE: string/null +VERSION: 1.3.0 +DEFAULT: NULL +--DESCRIPTION-- + +

+ 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: +

+ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
KeyDescriptionExample <a href="">
%r1 - The URI embeds a resource
(blank) - The URI is merely a link
%nThe name of the tag this URI came froma
%mThe name of the attribute this URI came fromhref
%pThe 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. +

+--# vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/URI.MungeResources.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/URI.MungeResources.txt new file mode 100644 index 0000000000..6fce0fdc37 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/URI.MungeResources.txt @@ -0,0 +1,17 @@ +URI.MungeResources +TYPE: bool +VERSION: 3.1.1 +DEFAULT: false +--DESCRIPTION-- +

+ 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. +

+--# vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/URI.MungeSecretKey.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/URI.MungeSecretKey.txt new file mode 100644 index 0000000000..1e17c1d461 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/URI.MungeSecretKey.txt @@ -0,0 +1,30 @@ +URI.MungeSecretKey +TYPE: string/null +VERSION: 3.1.1 +DEFAULT: NULL +--DESCRIPTION-- +

+ 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 === hash_hmac("sha256", $url, $secret_key)
+ +

+ 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/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/URI.OverrideAllowedSchemes.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/URI.OverrideAllowedSchemes.txt new file mode 100644 index 0000000000..23331a4e79 --- /dev/null +++ b/extlib/HTMLPurifier/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/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/URI.SafeIframeRegexp.txt b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/URI.SafeIframeRegexp.txt new file mode 100644 index 0000000000..79084832be --- /dev/null +++ b/extlib/HTMLPurifier/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/% - Allow YouTube videos
    • +
  • %^http://player.vimeo.com/video/% - Allow Vimeo videos
    • +
  • %^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. +

+--# vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/info.ini b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/info.ini new file mode 100644 index 0000000000..5de4505e1b --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/ConfigSchema/schema/info.ini @@ -0,0 +1,3 @@ +name = "HTML Purifier" + +; vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/ContentSets.php b/extlib/HTMLPurifier/HTMLPurifier/ContentSets.php new file mode 100644 index 0000000000..543e3f8f11 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/ContentSets.php @@ -0,0 +1,170 @@ + true) indexed by name. + * @type array + * @note This is in HTMLPurifier_HTMLDefinition->info_content_sets + */ + public $lookup = array(); + + /** + * Synchronized list of defined content sets (keys of info). + * @type array + */ + protected $keys = array(); + /** + * Synchronized list of defined content values (values of info). + * @type array + */ + 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 HTMLPurifier_HTMLModule[] $modules List of HTMLPurifier_HTMLModule + */ + public function __construct($modules) + { + if (!is_array($modules)) { + $modules = array($modules); + } + // populate content_sets based on module hints + // sorry, no way of overloading + foreach ($modules as $module) { + foreach ($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 HTMLPurifier_ElementDef $def HTMLPurifier_ElementDef reference + * @param HTMLPurifier_HTMLModule $module Module that defined the ElementDef + */ + public function generateChildDef(&$def, $module) + { + if (!empty($def->child)) { // already done! + return; + } + $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 HTMLPurifier_ElementDef $def HTMLPurifier_ElementDef to have ChildDef extracted + * @param HTMLPurifier_HTMLModule $module Module that defined the ElementDef + * @return HTMLPurifier_ChildDef corresponding to ElementDef + */ + public function getChildDef($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 $string List of elements + * @return array Lookup array of elements + */ + protected function convertToLookup($string) + { + $array = explode('|', str_replace(' ', '', $string)); + $ret = array(); + foreach ($array as $k) { + $ret[$k] = true; + } + return $ret; + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/Context.php b/extlib/HTMLPurifier/HTMLPurifier/Context.php new file mode 100644 index 0000000000..00e509c85c --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/Context.php @@ -0,0 +1,95 @@ +_storage)) { + 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 string $name String name + * @param bool $ignore_error Boolean whether or not to ignore error + * @return mixed + */ + public function &get($name, $ignore_error = false) + { + if (!array_key_exists($name, $this->_storage)) { + if (!$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]; + } + + /** + * Destroys a variable in the context. + * @param string $name String name + */ + public function destroy($name) + { + if (!array_key_exists($name, $this->_storage)) { + 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 string $name String name + * @return bool + */ + public function exists($name) + { + return array_key_exists($name, $this->_storage); + } + + /** + * Loads a series of variables from an associative array + * @param array $context_array Assoc array of variables to load + */ + public function loadArray($context_array) + { + foreach ($context_array as $key => $discard) { + $this->register($key, $context_array[$key]); + } + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/Definition.php b/extlib/HTMLPurifier/HTMLPurifier/Definition.php new file mode 100644 index 0000000000..bc6d433647 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/Definition.php @@ -0,0 +1,55 @@ +setup) { + return; + } + $this->setup = true; + $this->doSetup($config); + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/DefinitionCache.php b/extlib/HTMLPurifier/HTMLPurifier/DefinitionCache.php new file mode 100644 index 0000000000..67bb5b1e69 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/DefinitionCache.php @@ -0,0 +1,129 @@ +type = $type; + } + + /** + * Generates a unique identifier for a particular configuration + * @param HTMLPurifier_Config $config Instance of HTMLPurifier_Config + * @return string + */ + public function generateKey($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 string $key Key to test + * @param HTMLPurifier_Config $config Instance of HTMLPurifier_Config to test against + * @return bool + */ + public function isOld($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 HTMLPurifier_Definition $def Definition object to check + * @return bool true if good, false if not + */ + public function checkDefType($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 + * @param HTMLPurifier_Definition $def + * @param HTMLPurifier_Config $config + */ + abstract public function add($def, $config); + + /** + * Unconditionally saves a definition object to the cache + * @param HTMLPurifier_Definition $def + * @param HTMLPurifier_Config $config + */ + abstract public function set($def, $config); + + /** + * Replace an object in the cache + * @param HTMLPurifier_Definition $def + * @param HTMLPurifier_Config $config + */ + abstract public function replace($def, $config); + + /** + * Retrieves a definition object from the cache + * @param HTMLPurifier_Config $config + */ + abstract public function get($config); + + /** + * Removes a definition object to the cache + * @param HTMLPurifier_Config $config + */ + abstract public function remove($config); + + /** + * Clears all objects from cache + * @param HTMLPurifier_Config $config + */ + abstract public function flush($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. + * @param HTMLPurifier_Config $config + */ + abstract public function cleanup($config); +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/DefinitionCache/Decorator.php b/extlib/HTMLPurifier/HTMLPurifier/DefinitionCache/Decorator.php new file mode 100644 index 0000000000..b57a51b6cb --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/DefinitionCache/Decorator.php @@ -0,0 +1,112 @@ +copy(); + // reference is necessary for mocks in PHP 4 + $decorator->cache =& $cache; + $decorator->type = $cache->type; + return $decorator; + } + + /** + * Cross-compatible clone substitute + * @return HTMLPurifier_DefinitionCache_Decorator + */ + public function copy() + { + return new HTMLPurifier_DefinitionCache_Decorator(); + } + + /** + * @param HTMLPurifier_Definition $def + * @param HTMLPurifier_Config $config + * @return mixed + */ + public function add($def, $config) + { + return $this->cache->add($def, $config); + } + + /** + * @param HTMLPurifier_Definition $def + * @param HTMLPurifier_Config $config + * @return mixed + */ + public function set($def, $config) + { + return $this->cache->set($def, $config); + } + + /** + * @param HTMLPurifier_Definition $def + * @param HTMLPurifier_Config $config + * @return mixed + */ + public function replace($def, $config) + { + return $this->cache->replace($def, $config); + } + + /** + * @param HTMLPurifier_Config $config + * @return mixed + */ + public function get($config) + { + return $this->cache->get($config); + } + + /** + * @param HTMLPurifier_Config $config + * @return mixed + */ + public function remove($config) + { + return $this->cache->remove($config); + } + + /** + * @param HTMLPurifier_Config $config + * @return mixed + */ + public function flush($config) + { + return $this->cache->flush($config); + } + + /** + * @param HTMLPurifier_Config $config + * @return mixed + */ + public function cleanup($config) + { + return $this->cache->cleanup($config); + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/DefinitionCache/Decorator/Cleanup.php b/extlib/HTMLPurifier/HTMLPurifier/DefinitionCache/Decorator/Cleanup.php new file mode 100644 index 0000000000..4991777ce1 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/DefinitionCache/Decorator/Cleanup.php @@ -0,0 +1,78 @@ +definitions[$this->generateKey($config)] = $def; + } + return $status; + } + + /** + * @param HTMLPurifier_Definition $def + * @param HTMLPurifier_Config $config + * @return mixed + */ + public function set($def, $config) + { + $status = parent::set($def, $config); + if ($status) { + $this->definitions[$this->generateKey($config)] = $def; + } + return $status; + } + + /** + * @param HTMLPurifier_Definition $def + * @param HTMLPurifier_Config $config + * @return mixed + */ + public function replace($def, $config) + { + $status = parent::replace($def, $config); + if ($status) { + $this->definitions[$this->generateKey($config)] = $def; + } + return $status; + } + + /** + * @param HTMLPurifier_Config $config + * @return mixed + */ + public function get($config) + { + $key = $this->generateKey($config); + if (isset($this->definitions[$key])) { + return $this->definitions[$key]; + } + $this->definitions[$key] = parent::get($config); + return $this->definitions[$key]; + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/DefinitionCache/Decorator/Template.php.in b/extlib/HTMLPurifier/HTMLPurifier/DefinitionCache/Decorator/Template.php.in new file mode 100644 index 0000000000..b1fec8d367 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/DefinitionCache/Decorator/Template.php.in @@ -0,0 +1,82 @@ +checkDefType($def)) { + return; + } + $file = $this->generateFilePath($config); + if (file_exists($file)) { + return false; + } + if (!$this->_prepareDir($config)) { + return false; + } + return $this->_write($file, serialize($def), $config); + } + + /** + * @param HTMLPurifier_Definition $def + * @param HTMLPurifier_Config $config + * @return int|bool + */ + public function set($def, $config) + { + if (!$this->checkDefType($def)) { + return; + } + $file = $this->generateFilePath($config); + if (!$this->_prepareDir($config)) { + return false; + } + return $this->_write($file, serialize($def), $config); + } + + /** + * @param HTMLPurifier_Definition $def + * @param HTMLPurifier_Config $config + * @return int|bool + */ + public function replace($def, $config) + { + if (!$this->checkDefType($def)) { + return; + } + $file = $this->generateFilePath($config); + if (!file_exists($file)) { + return false; + } + if (!$this->_prepareDir($config)) { + return false; + } + return $this->_write($file, serialize($def), $config); + } + + /** + * @param HTMLPurifier_Config $config + * @return bool|HTMLPurifier_Config + */ + public function get($config) + { + $file = $this->generateFilePath($config); + if (!file_exists($file)) { + return false; + } + return unserialize(file_get_contents($file)); + } + + /** + * @param HTMLPurifier_Config $config + * @return bool + */ + public function remove($config) + { + $file = $this->generateFilePath($config); + if (!file_exists($file)) { + return false; + } + return unlink($file); + } + + /** + * @param HTMLPurifier_Config $config + * @return bool + */ + public function flush($config) + { + if (!$this->_prepareDir($config)) { + return false; + } + $dir = $this->generateDirectoryPath($config); + $dh = opendir($dir); + while (false !== ($filename = readdir($dh))) { + if (empty($filename)) { + continue; + } + if ($filename[0] === '.') { + continue; + } + unlink($dir . '/' . $filename); + } + } + + /** + * @param HTMLPurifier_Config $config + * @return bool + */ + public function cleanup($config) + { + if (!$this->_prepareDir($config)) { + return false; + } + $dir = $this->generateDirectoryPath($config); + $dh = opendir($dir); + while (false !== ($filename = readdir($dh))) { + if (empty($filename)) { + continue; + } + if ($filename[0] === '.') { + continue; + } + $key = substr($filename, 0, strlen($filename) - 4); + if ($this->isOld($key, $config)) { + unlink($dir . '/' . $filename); + } + } + } + + /** + * Generates the file path to the serial file corresponding to + * the configuration and definition name + * @param HTMLPurifier_Config $config + * @return string + * @todo Make protected + */ + public function generateFilePath($config) + { + $key = $this->generateKey($config); + return $this->generateDirectoryPath($config) . '/' . $key . '.ser'; + } + + /** + * Generates the path to the directory contain this cache's serial files + * @param HTMLPurifier_Config $config + * @return string + * @note No trailing slash + * @todo Make protected + */ + public function generateDirectoryPath($config) + { + $base = $this->generateBaseDirectoryPath($config); + return $base . '/' . $this->type; + } + + /** + * Generates path to base directory that contains all definition type + * serials + * @param HTMLPurifier_Config $config + * @return mixed|string + * @todo Make protected + */ + public function generateBaseDirectoryPath($config) + { + $base = $config->get('Cache.SerializerPath'); + $base = is_null($base) ? HTMLPURIFIER_PREFIX . '/HTMLPurifier/DefinitionCache/Serializer' : $base; + return $base; + } + + /** + * Convenience wrapper function for file_put_contents + * @param string $file File name to write to + * @param string $data Data to write into file + * @param HTMLPurifier_Config $config + * @return int|bool Number of bytes written if success, or false if failure. + */ + private function _write($file, $data, $config) + { + $result = file_put_contents($file, $data); + if ($result !== false) { + // set permissions of the new file (no execute) + $chmod = $config->get('Cache.SerializerPermissions'); + if (!$chmod) { + $chmod = 0644; // invalid config or simpletest + } + $chmod = $chmod & 0666; + chmod($file, $chmod); + } + return $result; + } + + /** + * Prepares the directory that this type stores the serials in + * @param HTMLPurifier_Config $config + * @return bool True if successful + */ + private function _prepareDir($config) + { + $directory = $this->generateDirectoryPath($config); + $chmod = $config->get('Cache.SerializerPermissions'); + if (!$chmod) { + $chmod = 0755; // invalid config or simpletest + } + if (!is_dir($directory)) { + $base = $this->generateBaseDirectoryPath($config); + if (!is_dir($base)) { + trigger_error( + 'Base directory ' . $base . ' does not exist, + please create or change using %Cache.SerializerPath', + E_USER_WARNING + ); + return false; + } elseif (!$this->_testPermissions($base, $chmod)) { + return false; + } + mkdir($directory, $chmod); + if (!$this->_testPermissions($directory, $chmod)) { + trigger_error( + 'Base directory ' . $base . ' does not exist, + please create or change using %Cache.SerializerPath', + E_USER_WARNING + ); + return false; + } + } elseif (!$this->_testPermissions($directory, $chmod)) { + return false; + } + return true; + } + + /** + * Tests permissions on a directory and throws out friendly + * error messages and attempts to chmod it itself if possible + * @param string $dir Directory path + * @param int $chmod Permissions + * @return bool True if directory is writable + */ + private function _testPermissions($dir, $chmod) + { + // early abort, if it is writable, everything is hunky-dory + if (is_writable($dir)) { + return true; + } + if (!is_dir($dir)) { + // generally, you'll want to handle this beforehand + // so a more specific error message can be given + trigger_error( + 'Directory ' . $dir . ' does not exist', + E_USER_WARNING + ); + return false; + } + if (function_exists('posix_getuid')) { + // POSIX system, we can give more specific advice + if (fileowner($dir) === posix_getuid()) { + // we can chmod it ourselves + $chmod = $chmod | 0700; + if (chmod($dir, $chmod)) { + return true; + } + } elseif (filegroup($dir) === posix_getgid()) { + $chmod = $chmod | 0070; + } else { + // PHP's probably running as nobody, so we'll + // need to give global permissions + $chmod = $chmod | 0777; + } + trigger_error( + 'Directory ' . $dir . ' not writable, ' . + 'please chmod to ' . decoct($chmod), + E_USER_WARNING + ); + } else { + // generic error message + trigger_error( + 'Directory ' . $dir . ' not writable, ' . + 'please alter file permissions', + E_USER_WARNING + ); + } + return false; + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/DefinitionCache/Serializer/CSS/4.7.0,24166bfe16a0cc6bd18d813b83121ef2eaf16545,1.ser b/extlib/HTMLPurifier/HTMLPurifier/DefinitionCache/Serializer/CSS/4.7.0,24166bfe16a0cc6bd18d813b83121ef2eaf16545,1.ser new file mode 100644 index 0000000000..fe7977acba Binary files /dev/null and b/extlib/HTMLPurifier/HTMLPurifier/DefinitionCache/Serializer/CSS/4.7.0,24166bfe16a0cc6bd18d813b83121ef2eaf16545,1.ser differ diff --git a/extlib/HTMLPurifier/HTMLPurifier/DefinitionCache/Serializer/HTML/4.7.0,4063a3df859f6892bd455e3d5a04d1c3a0fc36bf,1.ser b/extlib/HTMLPurifier/HTMLPurifier/DefinitionCache/Serializer/HTML/4.7.0,4063a3df859f6892bd455e3d5a04d1c3a0fc36bf,1.ser new file mode 100644 index 0000000000..3af2636b39 Binary files /dev/null and b/extlib/HTMLPurifier/HTMLPurifier/DefinitionCache/Serializer/HTML/4.7.0,4063a3df859f6892bd455e3d5a04d1c3a0fc36bf,1.ser differ diff --git a/extlib/HTMLPurifier/HTMLPurifier/DefinitionCache/Serializer/HTML/4.7.0,449d41d06cbcda52d33f6829f087a787ec01cb84,1.ser b/extlib/HTMLPurifier/HTMLPurifier/DefinitionCache/Serializer/HTML/4.7.0,449d41d06cbcda52d33f6829f087a787ec01cb84,1.ser new file mode 100644 index 0000000000..c39f38446a Binary files /dev/null and b/extlib/HTMLPurifier/HTMLPurifier/DefinitionCache/Serializer/HTML/4.7.0,449d41d06cbcda52d33f6829f087a787ec01cb84,1.ser differ diff --git a/extlib/HTMLPurifier/HTMLPurifier/DefinitionCache/Serializer/HTML/4.7.0,5c4840e226ded29edc85d3405cfa3d941477052b,1.ser b/extlib/HTMLPurifier/HTMLPurifier/DefinitionCache/Serializer/HTML/4.7.0,5c4840e226ded29edc85d3405cfa3d941477052b,1.ser new file mode 100644 index 0000000000..3af2636b39 Binary files /dev/null and b/extlib/HTMLPurifier/HTMLPurifier/DefinitionCache/Serializer/HTML/4.7.0,5c4840e226ded29edc85d3405cfa3d941477052b,1.ser differ diff --git a/extlib/HTMLPurifier/HTMLPurifier/DefinitionCache/Serializer/HTML/4.7.0,bd08c5afbc77123dbd4e9e026a723c450e9f844b,1.ser b/extlib/HTMLPurifier/HTMLPurifier/DefinitionCache/Serializer/HTML/4.7.0,bd08c5afbc77123dbd4e9e026a723c450e9f844b,1.ser new file mode 100644 index 0000000000..2b741ba876 Binary files /dev/null and b/extlib/HTMLPurifier/HTMLPurifier/DefinitionCache/Serializer/HTML/4.7.0,bd08c5afbc77123dbd4e9e026a723c450e9f844b,1.ser differ diff --git a/extlib/HTMLPurifier/HTMLPurifier/DefinitionCache/Serializer/README b/extlib/HTMLPurifier/HTMLPurifier/DefinitionCache/Serializer/README new file mode 100755 index 0000000000..2e35c1c3d0 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/DefinitionCache/Serializer/README @@ -0,0 +1,3 @@ +This is a dummy file to prevent Git from ignoring this empty directory. + + vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/DefinitionCache/Serializer/URI/4.7.0,8d03c8ec0e84e7feb92afd4c0f1735841b5fdacf,1.ser b/extlib/HTMLPurifier/HTMLPurifier/DefinitionCache/Serializer/URI/4.7.0,8d03c8ec0e84e7feb92afd4c0f1735841b5fdacf,1.ser new file mode 100644 index 0000000000..f6d3e812b7 Binary files /dev/null and b/extlib/HTMLPurifier/HTMLPurifier/DefinitionCache/Serializer/URI/4.7.0,8d03c8ec0e84e7feb92afd4c0f1735841b5fdacf,1.ser differ diff --git a/extlib/HTMLPurifier/HTMLPurifier/DefinitionCacheFactory.php b/extlib/HTMLPurifier/HTMLPurifier/DefinitionCacheFactory.php new file mode 100644 index 0000000000..fd1cc9be46 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/DefinitionCacheFactory.php @@ -0,0 +1,106 @@ + array()); + + /** + * @type array + */ + protected $implementations = array(); + + /** + * @type HTMLPurifier_DefinitionCache_Decorator[] + */ + protected $decorators = array(); + + /** + * Initialize default decorators + */ + public function setup() + { + $this->addDecorator('Cleanup'); + } + + /** + * Retrieves an instance of global definition cache factory. + * @param HTMLPurifier_DefinitionCacheFactory $prototype + * @return HTMLPurifier_DefinitionCacheFactory + */ + public static function instance($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 string $short Short name of cache object, for reference + * @param string $long Full class name of cache object, for construction + */ + public function register($short, $long) + { + $this->implementations[$short] = $long; + } + + /** + * Factory method that creates a cache object based on configuration + * @param string $type Name of definitions handled by cache + * @param HTMLPurifier_Config $config Config instance + * @return mixed + */ + public function create($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 HTMLPurifier_DefinitionCache_Decorator|string $decorator An instance or the name of a decorator + */ + public function addDecorator($decorator) + { + if (is_string($decorator)) { + $class = "HTMLPurifier_DefinitionCache_Decorator_$decorator"; + $decorator = new $class; + } + $this->decorators[$decorator->name] = $decorator; + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/Doctype.php b/extlib/HTMLPurifier/HTMLPurifier/Doctype.php new file mode 100644 index 0000000000..4acd06e5bd --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/Doctype.php @@ -0,0 +1,73 @@ +renderDoctype. + * If structure changes, please update that function. + */ +class HTMLPurifier_Doctype +{ + /** + * Full name of doctype + * @type string + */ + public $name; + + /** + * List of standard modules (string identifiers or literal objects) + * that this doctype uses + * @type array + */ + public $modules = array(); + + /** + * List of modules to use for tidying up code + * @type array + */ + public $tidyModules = array(); + + /** + * Is the language derived from XML (i.e. XHTML)? + * @type bool + */ + public $xml = true; + + /** + * List of aliases for this doctype + * @type array + */ + public $aliases = array(); + + /** + * Public DTD identifier + * @type string + */ + public $dtdPublic; + + /** + * System DTD identifier + * @type string + */ + 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 = $dtd_system; + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/DoctypeRegistry.php b/extlib/HTMLPurifier/HTMLPurifier/DoctypeRegistry.php new file mode 100644 index 0000000000..acc1d64a62 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/DoctypeRegistry.php @@ -0,0 +1,142 @@ +doctypes[$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 string $doctype Name of doctype + * @return HTMLPurifier_Doctype Editable doctype object + */ + public function get($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). + * @param HTMLPurifier_Config $config + * @return HTMLPurifier_Doctype + */ + public function make($config) + { + return clone $this->get($this->getDoctypeFromConfig($config)); + } + + /** + * Retrieves the doctype from the configuration object + * @param HTMLPurifier_Config $config + * @return string + */ + public function getDoctypeFromConfig($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; + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/ElementDef.php b/extlib/HTMLPurifier/HTMLPurifier/ElementDef.php new file mode 100644 index 0000000000..d5311cedcf --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/ElementDef.php @@ -0,0 +1,216 @@ +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. + * @type array + */ + public $attr_transform_pre = array(); + + /** + * List of tags HTMLPurifier_AttrTransform to be done after validation. + * @type array + */ + public $attr_transform_post = array(); + + /** + * HTMLPurifier_ChildDef of this tag. + * @type HTMLPurifier_ChildDef + */ + 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 + * @type string + */ + 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 + * @type string + */ + 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. + * @type bool + */ + public $descendants_are_inline = false; + + /** + * List of the names of required attributes this element has. + * Dynamically populated by HTMLPurifier_HTMLDefinition::getElement() + * @type array + */ + public $required_attr = array(); + + /** + * Lookup table of tags excluded from all descendants of this tag. + * @type array + * @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. + * @type array + */ + 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. + * @type string + */ + public $wrap; + + /** + * Whether or not this is a formatting element affected by the + * "Active Formatting Elements" algorithm. + * @type bool + */ + 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. + * @param HTMLPurifier_ElementDef $def + */ + public function mergeIn($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; + } + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/Encoder.php b/extlib/HTMLPurifier/HTMLPurifier/Encoder.php new file mode 100644 index 0000000000..fef9b58906 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/Encoder.php @@ -0,0 +1,611 @@ += $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. + * + * @param string $str The string to clean + * @param bool $force_php + * @return string + * + * @note Just for reference, the non-SGML code points are 0 to 31 and + * 127 to 159, inclusive. However, we allow code points 9, 10 + * and 13, which are the tab, line feed and carriage return + * respectively. 128 and above the code points map to multibyte + * UTF-8 representations. + * + * @note Fallback code adapted from utf8ToUnicode by Henri Sivonen and + * hsivonen@iki.fi at under the + * LGPL license. Notes on what changed are inside, but in general, + * the original code transformed UTF-8 text into an array of integer + * Unicode codepoints. Understandably, transforming that back to + * a string would be somewhat expensive, so the function was modded to + * directly operate on the string. However, this discourages code + * reuse, and the logic enumerated here would be useful for any + * function that needs to be able to understand UTF-8 characters. + * As of right now, only smart lossless character encoding converters + * would need that, and I'm probably not going to implement them. + * Once again, PHP 6 should solve all our problems. + */ + public static function cleanUTF8($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; + } + + /** + * @return bool + */ + public static function iconvAvailable() + { + static $iconv = null; + if ($iconv === null) { + $iconv = function_exists('iconv') && self::testIconvTruncateBug() != self::ICONV_UNUSABLE; + } + return $iconv; + } + + /** + * Convert a string to UTF-8 based on configuration. + * @param string $str The string to convert + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return string + */ + public static function convertToUTF8($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. + * @param string $str The string to convert + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return string + * @note Currently, this is a lossy conversion, with unexpressable + * characters being omitted. + */ + public static function convertFromUTF8($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 string $str UTF-8 string to be converted to ASCII + * @return string 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. + * + * @return int 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 $ret; + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/EntityLookup.php b/extlib/HTMLPurifier/HTMLPurifier/EntityLookup.php new file mode 100644 index 0000000000..f12ff13a35 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/EntityLookup.php @@ -0,0 +1,48 @@ +table = unserialize(file_get_contents($file)); + } + + /** + * Retrieves sole instance of the object. + * @param bool|HTMLPurifier_EntityLookup $prototype Optional prototype of custom lookup table to overload with. + * @return HTMLPurifier_EntityLookup + */ + public static function instance($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; + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/EntityLookup/entities.ser b/extlib/HTMLPurifier/HTMLPurifier/EntityLookup/entities.ser new file mode 100644 index 0000000000..e8b08128be --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/EntityLookup/entities.ser @@ -0,0 +1 @@ +a:253:{s:4:"fnof";s:2:"ƒ";s:5:"Alpha";s:2:"Α";s:4:"Beta";s:2:"Β";s:5:"Gamma";s:2:"Γ";s:5:"Delta";s:2:"Δ";s:7:"Epsilon";s:2:"Ε";s:4:"Zeta";s:2:"Ζ";s:3:"Eta";s:2:"Η";s:5:"Theta";s:2:"Θ";s:4:"Iota";s:2:"Ι";s:5:"Kappa";s:2:"Κ";s:6:"Lambda";s:2:"Λ";s:2:"Mu";s:2:"Μ";s:2:"Nu";s:2:"Ν";s:2:"Xi";s:2:"Ξ";s:7:"Omicron";s:2:"Ο";s:2:"Pi";s:2:"Π";s:3:"Rho";s:2:"Ρ";s:5:"Sigma";s:2:"Σ";s:3:"Tau";s:2:"Τ";s:7:"Upsilon";s:2:"Υ";s:3:"Phi";s:2:"Φ";s:3:"Chi";s:2:"Χ";s:3:"Psi";s:2:"Ψ";s:5:"Omega";s:2:"Ω";s:5:"alpha";s:2:"α";s:4:"beta";s:2:"β";s:5:"gamma";s:2:"γ";s:5:"delta";s:2:"δ";s:7:"epsilon";s:2:"ε";s:4:"zeta";s:2:"ζ";s:3:"eta";s:2:"η";s:5:"theta";s:2:"θ";s:4:"iota";s:2:"ι";s:5:"kappa";s:2:"κ";s:6:"lambda";s:2:"λ";s:2:"mu";s:2:"μ";s:2:"nu";s:2:"ν";s:2:"xi";s:2:"ξ";s:7:"omicron";s:2:"ο";s:2:"pi";s:2:"π";s:3:"rho";s:2:"ρ";s:6:"sigmaf";s:2:"ς";s:5:"sigma";s:2:"σ";s:3:"tau";s:2:"τ";s:7:"upsilon";s:2:"υ";s:3:"phi";s:2:"φ";s:3:"chi";s:2:"χ";s:3:"psi";s:2:"ψ";s:5:"omega";s:2:"ω";s:8:"thetasym";s:2:"ϑ";s:5:"upsih";s:2:"ϒ";s:3:"piv";s:2:"ϖ";s:4:"bull";s:3:"•";s:6:"hellip";s:3:"…";s:5:"prime";s:3:"′";s:5:"Prime";s:3:"″";s:5:"oline";s:3:"‾";s:5:"frasl";s:3:"⁄";s:6:"weierp";s:3:"℘";s:5:"image";s:3:"ℑ";s:4:"real";s:3:"ℜ";s:5:"trade";s:3:"™";s:7:"alefsym";s:3:"ℵ";s:4:"larr";s:3:"←";s:4:"uarr";s:3:"↑";s:4:"rarr";s:3:"→";s:4:"darr";s:3:"↓";s:4:"harr";s:3:"↔";s:5:"crarr";s:3:"↵";s:4:"lArr";s:3:"⇐";s:4:"uArr";s:3:"⇑";s:4:"rArr";s:3:"⇒";s:4:"dArr";s:3:"⇓";s:4:"hArr";s:3:"⇔";s:6:"forall";s:3:"∀";s:4:"part";s:3:"∂";s:5:"exist";s:3:"∃";s:5:"empty";s:3:"∅";s:5:"nabla";s:3:"∇";s:4:"isin";s:3:"∈";s:5:"notin";s:3:"∉";s:2:"ni";s:3:"∋";s:4:"prod";s:3:"∏";s:3:"sum";s:3:"∑";s:5:"minus";s:3:"−";s:6:"lowast";s:3:"∗";s:5:"radic";s:3:"√";s:4:"prop";s:3:"∝";s:5:"infin";s:3:"∞";s:3:"ang";s:3:"∠";s:3:"and";s:3:"∧";s:2:"or";s:3:"∨";s:3:"cap";s:3:"∩";s:3:"cup";s:3:"∪";s:3:"int";s:3:"∫";s:6:"there4";s:3:"∴";s:3:"sim";s:3:"∼";s:4:"cong";s:3:"≅";s:5:"asymp";s:3:"≈";s:2:"ne";s:3:"≠";s:5:"equiv";s:3:"≡";s:2:"le";s:3:"≤";s:2:"ge";s:3:"≥";s:3:"sub";s:3:"⊂";s:3:"sup";s:3:"⊃";s:4:"nsub";s:3:"⊄";s:4:"sube";s:3:"⊆";s:4:"supe";s:3:"⊇";s:5:"oplus";s:3:"⊕";s:6:"otimes";s:3:"⊗";s:4:"perp";s:3:"⊥";s:4:"sdot";s:3:"⋅";s:5:"lceil";s:3:"⌈";s:5:"rceil";s:3:"⌉";s:6:"lfloor";s:3:"⌊";s:6:"rfloor";s:3:"⌋";s:4:"lang";s:3:"〈";s:4:"rang";s:3:"〉";s:3:"loz";s:3:"◊";s:6:"spades";s:3:"♠";s:5:"clubs";s:3:"♣";s:6:"hearts";s:3:"♥";s:5:"diams";s:3:"♦";s:4:"quot";s:1:""";s:3:"amp";s:1:"&";s:2:"lt";s:1:"<";s:2:"gt";s:1:">";s:4:"apos";s:1:"'";s:5:"OElig";s:2:"Œ";s:5:"oelig";s:2:"œ";s:6:"Scaron";s:2:"Š";s:6:"scaron";s:2:"š";s:4:"Yuml";s:2:"Ÿ";s:4:"circ";s:2:"ˆ";s:5:"tilde";s:2:"˜";s:4:"ensp";s:3:" ";s:4:"emsp";s:3:" ";s:6:"thinsp";s:3:" ";s:4:"zwnj";s:3:"‌";s:3:"zwj";s:3:"‍";s:3:"lrm";s:3:"‎";s:3:"rlm";s:3:"‏";s:5:"ndash";s:3:"–";s:5:"mdash";s:3:"—";s:5:"lsquo";s:3:"‘";s:5:"rsquo";s:3:"’";s:5:"sbquo";s:3:"‚";s:5:"ldquo";s:3:"“";s:5:"rdquo";s:3:"”";s:5:"bdquo";s:3:"„";s:6:"dagger";s:3:"†";s:6:"Dagger";s:3:"‡";s:6:"permil";s:3:"‰";s:6:"lsaquo";s:3:"‹";s:6:"rsaquo";s:3:"›";s:4:"euro";s:3:"€";s:4:"nbsp";s:2:" ";s:5:"iexcl";s:2:"¡";s:4:"cent";s:2:"¢";s:5:"pound";s:2:"£";s:6:"curren";s:2:"¤";s:3:"yen";s:2:"¥";s:6:"brvbar";s:2:"¦";s:4:"sect";s:2:"§";s:3:"uml";s:2:"¨";s:4:"copy";s:2:"©";s:4:"ordf";s:2:"ª";s:5:"laquo";s:2:"«";s:3:"not";s:2:"¬";s:3:"shy";s:2:"­";s:3:"reg";s:2:"®";s:4:"macr";s:2:"¯";s:3:"deg";s:2:"°";s:6:"plusmn";s:2:"±";s:4:"sup2";s:2:"²";s:4:"sup3";s:2:"³";s:5:"acute";s:2:"´";s:5:"micro";s:2:"µ";s:4:"para";s:2:"¶";s:6:"middot";s:2:"·";s:5:"cedil";s:2:"¸";s:4:"sup1";s:2:"¹";s:4:"ordm";s:2:"º";s:5:"raquo";s:2:"»";s:6:"frac14";s:2:"¼";s:6:"frac12";s:2:"½";s:6:"frac34";s:2:"¾";s:6:"iquest";s:2:"¿";s:6:"Agrave";s:2:"À";s:6:"Aacute";s:2:"Á";s:5:"Acirc";s:2:"Â";s:6:"Atilde";s:2:"Ã";s:4:"Auml";s:2:"Ä";s:5:"Aring";s:2:"Å";s:5:"AElig";s:2:"Æ";s:6:"Ccedil";s:2:"Ç";s:6:"Egrave";s:2:"È";s:6:"Eacute";s:2:"É";s:5:"Ecirc";s:2:"Ê";s:4:"Euml";s:2:"Ë";s:6:"Igrave";s:2:"Ì";s:6:"Iacute";s:2:"Í";s:5:"Icirc";s:2:"Î";s:4:"Iuml";s:2:"Ï";s:3:"ETH";s:2:"Ð";s:6:"Ntilde";s:2:"Ñ";s:6:"Ograve";s:2:"Ò";s:6:"Oacute";s:2:"Ó";s:5:"Ocirc";s:2:"Ô";s:6:"Otilde";s:2:"Õ";s:4:"Ouml";s:2:"Ö";s:5:"times";s:2:"×";s:6:"Oslash";s:2:"Ø";s:6:"Ugrave";s:2:"Ù";s:6:"Uacute";s:2:"Ú";s:5:"Ucirc";s:2:"Û";s:4:"Uuml";s:2:"Ü";s:6:"Yacute";s:2:"Ý";s:5:"THORN";s:2:"Þ";s:5:"szlig";s:2:"ß";s:6:"agrave";s:2:"à";s:6:"aacute";s:2:"á";s:5:"acirc";s:2:"â";s:6:"atilde";s:2:"ã";s:4:"auml";s:2:"ä";s:5:"aring";s:2:"å";s:5:"aelig";s:2:"æ";s:6:"ccedil";s:2:"ç";s:6:"egrave";s:2:"è";s:6:"eacute";s:2:"é";s:5:"ecirc";s:2:"ê";s:4:"euml";s:2:"ë";s:6:"igrave";s:2:"ì";s:6:"iacute";s:2:"í";s:5:"icirc";s:2:"î";s:4:"iuml";s:2:"ï";s:3:"eth";s:2:"ð";s:6:"ntilde";s:2:"ñ";s:6:"ograve";s:2:"ò";s:6:"oacute";s:2:"ó";s:5:"ocirc";s:2:"ô";s:6:"otilde";s:2:"õ";s:4:"ouml";s:2:"ö";s:6:"divide";s:2:"÷";s:6:"oslash";s:2:"ø";s:6:"ugrave";s:2:"ù";s:6:"uacute";s:2:"ú";s:5:"ucirc";s:2:"û";s:4:"uuml";s:2:"ü";s:6:"yacute";s:2:"ý";s:5:"thorn";s:2:"þ";s:4:"yuml";s:2:"ÿ";} \ No newline at end of file diff --git a/extlib/HTMLPurifier/HTMLPurifier/EntityParser.php b/extlib/HTMLPurifier/HTMLPurifier/EntityParser.php new file mode 100644 index 0000000000..61529dcd9d --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/EntityParser.php @@ -0,0 +1,153 @@ + '"', + 38 => '&', + 39 => "'", + 60 => '<', + 62 => '>' + ); + + /** + * Stripped entity names to decimal conversion table for special entities. + * @type array + */ + 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 $string String to have non-special entities parsed. + * @return string Parsed string. + */ + public function substituteNonSpecialEntities($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 array $matches PCRE matches array, with 0 the entire match, and + * either index 1, 2 or 3 set with a hex value, dec value, + * or string (respectively). + * @return string Replacement string. + */ + + protected function nonSpecialEntityCallback($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 $string String to have non-special entities parsed. + * @return string Parsed string. + */ + public function substituteSpecialEntities($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 array $matches PCRE-style matches array, with 0 the entire match, and + * either index 1, 2 or 3 set with a hex value, dec value, + * or string (respectively). + * @return string Replacement string. + */ + protected function specialEntityCallback($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; + } + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/ErrorCollector.php b/extlib/HTMLPurifier/HTMLPurifier/ErrorCollector.php new file mode 100644 index 0000000000..d47e3f2e24 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/ErrorCollector.php @@ -0,0 +1,244 @@ +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 int $severity Error severity, PHP error style (don't use E_USER_) + * @param string $msg Error message text + */ + public function send($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 ... + // 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 + */ + public function getRaw() + { + return $this->errors; + } + + /** + * Default HTML formatting implementation for error messages + * @param HTMLPurifier_Config $config Configuration, vital for HTML output nature + * @param array $errors Errors array to display; used for recursion. + * @return string + */ + public function getHTMLFormatted($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') . '

'; + } else { + return '
  • ' . implode('
  • ', $ret) . '
'; + } + + } + + private function _renderStruct(&$ret, $struct, $line = null, $col = null) + { + $stack = array($struct); + $context_stack = array(array()); + while ($current = array_pop($stack)) { + $context = array_pop($context_stack); + foreach ($current->errors as $error) { + list($severity, $msg) = $error; + $string = ''; + $string .= '
'; + // 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 $array) { + $context[] = $current; + $stack = array_merge($stack, array_reverse($array, true)); + for ($i = count($array); $i > 0; $i--) { + $context_stack[] = $context; + } + } + } + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/ErrorStruct.php b/extlib/HTMLPurifier/HTMLPurifier/ErrorStruct.php new file mode 100644 index 0000000000..cf869d3212 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/ErrorStruct.php @@ -0,0 +1,74 @@ +children[$type][$id])) { + $this->children[$type][$id] = new HTMLPurifier_ErrorStruct(); + $this->children[$type][$id]->type = $type; + } + return $this->children[$type][$id]; + } + + /** + * @param int $severity + * @param string $message + */ + public function addError($severity, $message) + { + $this->errors[] = array($severity, $message); + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/Exception.php b/extlib/HTMLPurifier/HTMLPurifier/Exception.php new file mode 100644 index 0000000000..be85b4c560 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/Exception.php @@ -0,0 +1,12 @@ +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. + * @type string + */ + public $name; + + /** + * Pre-processor function, handles HTML before HTML Purifier + * @param string $html + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return string + */ + public function preFilter($html, $config, $context) + { + return $html; + } + + /** + * Post-processor function, handles HTML after HTML Purifier + * @param string $html + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return string + */ + public function postFilter($html, $config, $context) + { + return $html; + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/Filter/ExtractStyleBlocks.php b/extlib/HTMLPurifier/HTMLPurifier/Filter/ExtractStyleBlocks.php new file mode 100644 index 0000000000..08e62c16bf --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/Filter/ExtractStyleBlocks.php @@ -0,0 +1,338 @@ + blocks from input HTML, cleans them up + * using CSSTidy, and then places them in $purifier->context->get('StyleBlocks') + * so they can be used elsewhere in the document. + * + * @note + * See tests/HTMLPurifier/Filter/ExtractStyleBlocksTest.php for + * sample usage. + * + * @note + * This filter can also be used on stylesheets not included in the + * document--something purists would probably prefer. Just directly + * call HTMLPurifier_Filter_ExtractStyleBlocks->cleanCSS() + */ +class HTMLPurifier_Filter_ExtractStyleBlocks extends HTMLPurifier_Filter +{ + /** + * @type string + */ + public $name = 'ExtractStyleBlocks'; + + /** + * @type array + */ + private $_styleMatches = array(); + + /** + * @type csstidy + */ + private $_tidy; + + /** + * @type HTMLPurifier_AttrDef_HTML_ID + */ + private $_id_attrdef; + + /** + * @type HTMLPurifier_AttrDef_CSS_Ident + */ + private $_class_attrdef; + + /** + * @type HTMLPurifier_AttrDef_Enum + */ + private $_enum_attrdef; + + public function __construct() + { + $this->_tidy = new csstidy(); + $this->_tidy->set_cfg('lowercase_s', false); + $this->_id_attrdef = new HTMLPurifier_AttrDef_HTML_ID(true); + $this->_class_attrdef = new HTMLPurifier_AttrDef_CSS_Ident(); + $this->_enum_attrdef = new HTMLPurifier_AttrDef_Enum( + array( + 'first-child', + 'link', + 'visited', + 'active', + 'hover', + 'focus' + ) + ); + } + + /** + * Save the contents of CSS blocks to style matches + * @param array $matches preg_replace style $matches array + */ + protected function styleCallback($matches) + { + $this->_styleMatches[] = $matches[1]; + } + + /** + * Removes inline #isU', array($this, 'styleCallback'), $html); + $style_blocks = $this->_styleMatches; + $this->_styleMatches = array(); // reset + $context->register('StyleBlocks', $style_blocks); // $context must not be reused + if ($this->_tidy) { + foreach ($style_blocks as &$style) { + $style = $this->cleanCSS($style, $config, $context); + } + } + return $html; + } + + /** + * Takes CSS (the stuff found in in a font-family prop). + if ($config->get('Filter.ExtractStyleBlocks.Escaping')) { + $css = str_replace( + array('<', '>', '&'), + array('\3C ', '\3E ', '\26 '), + $css + ); + } + return $css; + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/Filter/YouTube.php b/extlib/HTMLPurifier/HTMLPurifier/Filter/YouTube.php new file mode 100644 index 0000000000..276d8362fa --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/Filter/YouTube.php @@ -0,0 +1,65 @@ +]+>.+?' . + '(?:http:)?//www.youtube.com/((?:v|cp)/[A-Za-z0-9\-_=]+).+?#s'; + $pre_replace = '\1'; + return preg_replace($pre_regex, $pre_replace, $html); + } + + /** + * @param string $html + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return string + */ + public function postFilter($html, $config, $context) + { + $post_regex = '#((?:v|cp)/[A-Za-z0-9\-_=]+)#'; + return preg_replace_callback($post_regex, array($this, 'postFilterCallback'), $html); + } + + /** + * @param $url + * @return string + */ + protected function armorUrl($url) + { + return str_replace('--', '--', $url); + } + + /** + * @param array $matches + * @return string + */ + protected function postFilterCallback($matches) + { + $url = $this->armorUrl($matches[1]); + return '' . + '' . + '' . + ''; + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/Generator.php b/extlib/HTMLPurifier/HTMLPurifier/Generator.php new file mode 100644 index 0000000000..6fb5687146 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/Generator.php @@ -0,0 +1,286 @@ + tags. + * @type bool + */ + private $_scriptFix = false; + + /** + * Cache of HTMLDefinition during HTML output to determine whether or + * not attributes should be minimized. + * @type HTMLPurifier_HTMLDefinition + */ + private $_def; + + /** + * Cache of %Output.SortAttr. + * @type bool + */ + private $_sortAttr; + + /** + * Cache of %Output.FlashCompat. + * @type bool + */ + private $_flashCompat; + + /** + * Cache of %Output.FixInnerHTML. + * @type bool + */ + private $_innerHTMLFix; + + /** + * Stack for keeping track of object information when outputting IE + * compatibility code. + * @type array + */ + private $_flashStack = array(); + + /** + * Configuration for the generator + * @type HTMLPurifier_Config + */ + protected $config; + + /** + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + */ + public function __construct($config, $context) + { + $this->config = $config; + $this->_scriptFix = $config->get('Output.CommentScriptContents'); + $this->_innerHTMLFix = $config->get('Output.FixInnerHTML'); + $this->_sortAttr = $config->get('Output.SortAttr'); + $this->_flashCompat = $config->get('Output.FlashCompat'); + $this->_def = $config->getHTMLDefinition(); + $this->_xhtml = $this->_def->doctype->xml; + } + + /** + * Generates HTML from an array of tokens. + * @param HTMLPurifier_Token[] $tokens Array of HTMLPurifier_Token + * @return string Generated HTML + */ + public function generateFromTokens($tokens) + { + if (!$tokens) { + return ''; + } + + // Basic algorithm + $html = ''; + for ($i = 0, $size = count($tokens); $i < $size; $i++) { + if ($this->_scriptFix && $tokens[$i]->name === 'script' + && $i + 2 < $size && $tokens[$i+2] instanceof HTMLPurifier_Token_End) { + // script special case + // the contents of the script block must be ONE token + // for this to work. + $html .= $this->generateFromToken($tokens[$i++]); + $html .= $this->generateScriptFromToken($tokens[$i++]); + } + $html .= $this->generateFromToken($tokens[$i]); + } + + // Tidy cleanup + if (extension_loaded('tidy') && $this->config->get('Output.TidyFormat')) { + $tidy = new Tidy; + $tidy->parseString( + $html, + array( + 'indent'=> true, + 'output-xhtml' => $this->_xhtml, + 'show-body-only' => true, + 'indent-spaces' => 2, + 'wrap' => 68, + ), + 'utf8' + ); + $tidy->cleanRepair(); + $html = (string) $tidy; // explicit cast necessary + } + + // Normalize newlines to system defined value + if ($this->config->get('Core.NormalizeNewlines')) { + $nl = $this->config->get('Output.Newline'); + if ($nl === null) { + $nl = PHP_EOL; + } + if ($nl !== "\n") { + $html = str_replace("\n", $nl, $html); + } + } + return $html; + } + + /** + * Generates HTML from a single token. + * @param HTMLPurifier_Token $token HTMLPurifier_Token object. + * @return string Generated HTML + */ + public function generateFromToken($token) + { + if (!$token instanceof HTMLPurifier_Token) { + trigger_error('Cannot generate HTML from non-HTMLPurifier_Token object', E_USER_WARNING); + return ''; + + } elseif ($token instanceof HTMLPurifier_Token_Start) { + $attr = $this->generateAttributes($token->attr, $token->name); + if ($this->_flashCompat) { + if ($token->name == "object") { + $flash = new stdclass(); + $flash->attr = $token->attr; + $flash->param = array(); + $this->_flashStack[] = $flash; + } + } + return '<' . $token->name . ($attr ? ' ' : '') . $attr . '>'; + + } elseif ($token instanceof HTMLPurifier_Token_End) { + $_extra = ''; + if ($this->_flashCompat) { + if ($token->name == "object" && !empty($this->_flashStack)) { + // doesn't do anything for now + } + } + return $_extra . 'name . '>'; + + } elseif ($token instanceof HTMLPurifier_Token_Empty) { + if ($this->_flashCompat && $token->name == "param" && !empty($this->_flashStack)) { + $this->_flashStack[count($this->_flashStack)-1]->param[$token->attr['name']] = $token->attr['value']; + } + $attr = $this->generateAttributes($token->attr, $token->name); + return '<' . $token->name . ($attr ? ' ' : '') . $attr . + ( $this->_xhtml ? ' /': '' ) //
v.
+ . '>'; + + } elseif ($token instanceof HTMLPurifier_Token_Text) { + return $this->escape($token->data, ENT_NOQUOTES); + + } elseif ($token instanceof HTMLPurifier_Token_Comment) { + return ''; + } else { + return ''; + + } + } + + /** + * Special case processor for the contents of script tags + * @param HTMLPurifier_Token $token HTMLPurifier_Token object. + * @return string + * @warning This runs into problems if there's already a literal + * --> somewhere inside the script contents. + */ + public function generateScriptFromToken($token) + { + if (!$token instanceof HTMLPurifier_Token_Text) { + return $this->generateFromToken($token); + } + // Thanks + $data = preg_replace('#//\s*$#', '', $token->data); + return ''; + } + + /** + * Generates attribute declarations from attribute array. + * @note This does not include the leading or trailing space. + * @param array $assoc_array_of_attributes Attribute array + * @param string $element Name of element attributes are for, used to check + * attribute minimization. + * @return string Generated HTML fragment for insertion. + */ + public function generateAttributes($assoc_array_of_attributes, $element = '') + { + $html = ''; + if ($this->_sortAttr) { + ksort($assoc_array_of_attributes); + } + foreach ($assoc_array_of_attributes as $key => $value) { + if (!$this->_xhtml) { + // Remove namespaced attributes + if (strpos($key, ':') !== false) { + continue; + } + // Check if we should minimize the attribute: val="val" -> val + if ($element && !empty($this->_def->info[$element]->attr[$key]->minimized)) { + $html .= $key . ' '; + continue; + } + } + // Workaround for Internet Explorer innerHTML bug. + // Essentially, Internet Explorer, when calculating + // innerHTML, omits quotes if there are no instances of + // angled brackets, quotes or spaces. However, when parsing + // HTML (for example, when you assign to innerHTML), it + // treats backticks as quotes. Thus, + // `` + // becomes + // `` + // becomes + // + // Fortunately, all we need to do is trigger an appropriate + // quoting style, which we do by adding an extra space. + // This also is consistent with the W3C spec, which states + // that user agents may ignore leading or trailing + // whitespace (in fact, most don't, at least for attributes + // like alt, but an extra space at the end is barely + // noticeable). Still, we have a configuration knob for + // this, since this transformation is not necesary if you + // don't process user input with innerHTML or you don't plan + // on supporting Internet Explorer. + if ($this->_innerHTMLFix) { + if (strpos($value, '`') !== false) { + // check if correct quoting style would not already be + // triggered + if (strcspn($value, '"\' <>') === strlen($value)) { + // protect! + $value .= ' '; + } + } + } + $html .= $key.'="'.$this->escape($value).'" '; + } + return rtrim($html); + } + + /** + * Escapes raw text data. + * @todo This really ought to be protected, but until we have a facility + * for properly generating HTML here w/o using tokens, it stays + * public. + * @param string $string String data to escape for HTML. + * @param int $quote Quoting style, like htmlspecialchars. ENT_NOQUOTES is + * permissible for non-attribute output. + * @return string escaped data. + */ + public function escape($string, $quote = null) + { + // Workaround for APC bug on Mac Leopard reported by sidepodcast + // http://htmlpurifier.org/phorum/read.php?3,4823,4846 + if ($quote === null) { + $quote = ENT_COMPAT; + } + return htmlspecialchars($string, $quote, 'UTF-8'); + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/HTMLDefinition.php b/extlib/HTMLPurifier/HTMLPurifier/HTMLDefinition.php new file mode 100644 index 0000000000..9b7b334dd9 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/HTMLDefinition.php @@ -0,0 +1,493 @@ +getAnonymousModule(); + if (!isset($module->info[$element_name])) { + $element = $module->addBlankElement($element_name); + } else { + $element = $module->info[$element_name]; + } + $element->attr[$attr_name] = $def; + } + + /** + * Adds a custom element to your HTML definition + * @see HTMLPurifier_HTMLModule::addElement() for detailed + * parameter and return value descriptions. + */ + public function addElement($element_name, $type, $contents, $attr_collections, $attributes = array()) + { + $module = $this->getAnonymousModule(); + // assume that if the user is calling this, the element + // is safe. This may not be a good idea + $element = $module->addElement($element_name, $type, $contents, $attr_collections, $attributes); + return $element; + } + + /** + * Adds a blank element to your HTML definition, for overriding + * existing behavior + * @param string $element_name + * @return HTMLPurifier_ElementDef + * @see HTMLPurifier_HTMLModule::addBlankElement() for detailed + * parameter and return value descriptions. + */ + public function addBlankElement($element_name) + { + $module = $this->getAnonymousModule(); + $element = $module->addBlankElement($element_name); + return $element; + } + + /** + * Retrieves a reference to the anonymous module, so you can + * bust out advanced features without having to make your own + * module. + * @return HTMLPurifier_HTMLModule + */ + public function getAnonymousModule() + { + if (!$this->_anonModule) { + $this->_anonModule = new HTMLPurifier_HTMLModule(); + $this->_anonModule->name = 'Anonymous'; + } + return $this->_anonModule; + } + + private $_anonModule = null; + + // PUBLIC BUT INTERNAL VARIABLES -------------------------------------- + + /** + * @type string + */ + public $type = 'HTML'; + + /** + * @type HTMLPurifier_HTMLModuleManager + */ + public $manager; + + /** + * Performs low-cost, preliminary initialization. + */ + public function __construct() + { + $this->manager = new HTMLPurifier_HTMLModuleManager(); + } + + /** + * @param HTMLPurifier_Config $config + */ + protected function doSetup($config) + { + $this->processModules($config); + $this->setupConfigStuff($config); + unset($this->manager); + + // cleanup some of the element definitions + foreach ($this->info as $k => $v) { + unset($this->info[$k]->content_model); + unset($this->info[$k]->content_model_type); + } + } + + /** + * Extract out the information from the manager + * @param HTMLPurifier_Config $config + */ + protected function processModules($config) + { + if ($this->_anonModule) { + // for user specific changes + // this is late-loaded so we don't have to deal with PHP4 + // reference wonky-ness + $this->manager->addModule($this->_anonModule); + unset($this->_anonModule); + } + + $this->manager->setup($config); + $this->doctype = $this->manager->doctype; + + foreach ($this->manager->modules as $module) { + foreach ($module->info_tag_transform as $k => $v) { + if ($v === false) { + unset($this->info_tag_transform[$k]); + } else { + $this->info_tag_transform[$k] = $v; + } + } + foreach ($module->info_attr_transform_pre as $k => $v) { + if ($v === false) { + unset($this->info_attr_transform_pre[$k]); + } else { + $this->info_attr_transform_pre[$k] = $v; + } + } + foreach ($module->info_attr_transform_post as $k => $v) { + if ($v === false) { + unset($this->info_attr_transform_post[$k]); + } else { + $this->info_attr_transform_post[$k] = $v; + } + } + foreach ($module->info_injector as $k => $v) { + if ($v === false) { + unset($this->info_injector[$k]); + } else { + $this->info_injector[$k] = $v; + } + } + } + $this->info = $this->manager->getElements(); + $this->info_content_sets = $this->manager->contentSets->lookup; + } + + /** + * Sets up stuff based on config. We need a better way of doing this. + * @param HTMLPurifier_Config $config + */ + protected function setupConfigStuff($config) + { + $block_wrapper = $config->get('HTML.BlockWrapper'); + if (isset($this->info_content_sets['Block'][$block_wrapper])) { + $this->info_block_wrapper = $block_wrapper; + } else { + trigger_error( + 'Cannot use non-block element as block wrapper', + E_USER_ERROR + ); + } + + $parent = $config->get('HTML.Parent'); + $def = $this->manager->getElement($parent, true); + if ($def) { + $this->info_parent = $parent; + $this->info_parent_def = $def; + } else { + trigger_error( + 'Cannot use unrecognized element as parent', + E_USER_ERROR + ); + $this->info_parent_def = $this->manager->getElement($this->info_parent, true); + } + + // support template text + $support = "(for information on implementing this, see the support forums) "; + + // setup allowed elements ----------------------------------------- + + $allowed_elements = $config->get('HTML.AllowedElements'); + $allowed_attributes = $config->get('HTML.AllowedAttributes'); // retrieve early + + if (!is_array($allowed_elements) && !is_array($allowed_attributes)) { + $allowed = $config->get('HTML.Allowed'); + if (is_string($allowed)) { + list($allowed_elements, $allowed_attributes) = $this->parseTinyMCEAllowedList($allowed); + } + } + + if (is_array($allowed_elements)) { + foreach ($this->info as $name => $d) { + if (!isset($allowed_elements[$name])) { + unset($this->info[$name]); + } + unset($allowed_elements[$name]); + } + // emit errors + foreach ($allowed_elements as $element => $d) { + $element = htmlspecialchars($element); // PHP doesn't escape errors, be careful! + trigger_error("Element '$element' is not supported $support", E_USER_WARNING); + } + } + + // setup allowed attributes --------------------------------------- + + $allowed_attributes_mutable = $allowed_attributes; // by copy! + if (is_array($allowed_attributes)) { + // This actually doesn't do anything, since we went away from + // global attributes. It's possible that userland code uses + // it, but HTMLModuleManager doesn't! + foreach ($this->info_global_attr as $attr => $x) { + $keys = array($attr, "*@$attr", "*.$attr"); + $delete = true; + foreach ($keys as $key) { + if ($delete && isset($allowed_attributes[$key])) { + $delete = false; + } + if (isset($allowed_attributes_mutable[$key])) { + unset($allowed_attributes_mutable[$key]); + } + } + if ($delete) { + unset($this->info_global_attr[$attr]); + } + } + + foreach ($this->info as $tag => $info) { + foreach ($info->attr as $attr => $x) { + $keys = array("$tag@$attr", $attr, "*@$attr", "$tag.$attr", "*.$attr"); + $delete = true; + foreach ($keys as $key) { + if ($delete && isset($allowed_attributes[$key])) { + $delete = false; + } + if (isset($allowed_attributes_mutable[$key])) { + unset($allowed_attributes_mutable[$key]); + } + } + if ($delete) { + if ($this->info[$tag]->attr[$attr]->required) { + trigger_error( + "Required attribute '$attr' in element '$tag' " . + "was not allowed, which means '$tag' will not be allowed either", + E_USER_WARNING + ); + } + unset($this->info[$tag]->attr[$attr]); + } + } + } + // emit errors + foreach ($allowed_attributes_mutable as $elattr => $d) { + $bits = preg_split('/[.@]/', $elattr, 2); + $c = count($bits); + switch ($c) { + case 2: + if ($bits[0] !== '*') { + $element = htmlspecialchars($bits[0]); + $attribute = htmlspecialchars($bits[1]); + if (!isset($this->info[$element])) { + trigger_error( + "Cannot allow attribute '$attribute' if element " . + "'$element' is not allowed/supported $support" + ); + } else { + trigger_error( + "Attribute '$attribute' in element '$element' not supported $support", + E_USER_WARNING + ); + } + break; + } + // otherwise fall through + case 1: + $attribute = htmlspecialchars($bits[0]); + trigger_error( + "Global attribute '$attribute' is not ". + "supported in any elements $support", + E_USER_WARNING + ); + break; + } + } + } + + // setup forbidden elements --------------------------------------- + + $forbidden_elements = $config->get('HTML.ForbiddenElements'); + $forbidden_attributes = $config->get('HTML.ForbiddenAttributes'); + + foreach ($this->info as $tag => $info) { + if (isset($forbidden_elements[$tag])) { + unset($this->info[$tag]); + continue; + } + foreach ($info->attr as $attr => $x) { + if (isset($forbidden_attributes["$tag@$attr"]) || + isset($forbidden_attributes["*@$attr"]) || + isset($forbidden_attributes[$attr]) + ) { + unset($this->info[$tag]->attr[$attr]); + continue; + } elseif (isset($forbidden_attributes["$tag.$attr"])) { // this segment might get removed eventually + // $tag.$attr are not user supplied, so no worries! + trigger_error( + "Error with $tag.$attr: tag.attr syntax not supported for " . + "HTML.ForbiddenAttributes; use tag@attr instead", + E_USER_WARNING + ); + } + } + } + foreach ($forbidden_attributes as $key => $v) { + if (strlen($key) < 2) { + continue; + } + if ($key[0] != '*') { + continue; + } + if ($key[1] == '.') { + trigger_error( + "Error with $key: *.attr syntax not supported for HTML.ForbiddenAttributes; use attr instead", + E_USER_WARNING + ); + } + } + + // setup injectors ----------------------------------------------------- + foreach ($this->info_injector as $i => $injector) { + if ($injector->checkNeeded($config) !== false) { + // remove injector that does not have it's required + // elements/attributes present, and is thus not needed. + unset($this->info_injector[$i]); + } + } + } + + /** + * Parses a TinyMCE-flavored Allowed Elements and Attributes list into + * separate lists for processing. Format is element[attr1|attr2],element2... + * @warning Although it's largely drawn from TinyMCE's implementation, + * it is different, and you'll probably have to modify your lists + * @param array $list String list to parse + * @return array + * @todo Give this its own class, probably static interface + */ + public function parseTinyMCEAllowedList($list) + { + $list = str_replace(array(' ', "\t"), '', $list); + + $elements = array(); + $attributes = array(); + + $chunks = preg_split('/(,|[\n\r]+)/', $list); + foreach ($chunks as $chunk) { + if (empty($chunk)) { + continue; + } + // remove TinyMCE element control characters + if (!strpos($chunk, '[')) { + $element = $chunk; + $attr = false; + } else { + list($element, $attr) = explode('[', $chunk); + } + if ($element !== '*') { + $elements[$element] = true; + } + if (!$attr) { + continue; + } + $attr = substr($attr, 0, strlen($attr) - 1); // remove trailing ] + $attr = explode('|', $attr); + foreach ($attr as $key) { + $attributes["$element.$key"] = true; + } + } + return array($elements, $attributes); + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/HTMLModule.php b/extlib/HTMLPurifier/HTMLPurifier/HTMLModule.php new file mode 100644 index 0000000000..bb3a9230b1 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/HTMLModule.php @@ -0,0 +1,284 @@ +info, since the object's data is only info, + * with extra behavior associated with it. + * @type array + */ + public $attr_collections = array(); + + /** + * Associative array of deprecated tag name to HTMLPurifier_TagTransform. + * @type array + */ + public $info_tag_transform = array(); + + /** + * List of HTMLPurifier_AttrTransform to be performed before validation. + * @type array + */ + public $info_attr_transform_pre = array(); + + /** + * List of HTMLPurifier_AttrTransform to be performed after validation. + * @type array + */ + public $info_attr_transform_post = array(); + + /** + * List of HTMLPurifier_Injector to be performed during well-formedness fixing. + * An injector will only be invoked if all of it's pre-requisites are met; + * if an injector fails setup, there will be no error; it will simply be + * silently disabled. + * @type array + */ + public $info_injector = array(); + + /** + * Boolean flag that indicates whether or not getChildDef is implemented. + * For optimization reasons: may save a call to a function. Be sure + * to set it if you do implement getChildDef(), otherwise it will have + * no effect! + * @type bool + */ + public $defines_child_def = false; + + /** + * Boolean flag whether or not this module is safe. If it is not safe, all + * of its members are unsafe. Modules are safe by default (this might be + * slightly dangerous, but it doesn't make much sense to force HTML Purifier, + * which is based off of safe HTML, to explicitly say, "This is safe," even + * though there are modules which are "unsafe") + * + * @type bool + * @note Previously, safety could be applied at an element level granularity. + * We've removed this ability, so in order to add "unsafe" elements + * or attributes, a dedicated module with this property set to false + * must be used. + */ + public $safe = true; + + /** + * Retrieves a proper HTMLPurifier_ChildDef subclass based on + * content_model and content_model_type member variables of + * the HTMLPurifier_ElementDef class. There is a similar function + * in HTMLPurifier_HTMLDefinition. + * @param HTMLPurifier_ElementDef $def + * @return HTMLPurifier_ChildDef subclass + */ + public function getChildDef($def) + { + return false; + } + + // -- Convenience ----------------------------------------------------- + + /** + * Convenience function that sets up a new element + * @param string $element Name of element to add + * @param string|bool $type What content set should element be registered to? + * Set as false to skip this step. + * @param string $contents Allowed children in form of: + * "$content_model_type: $content_model" + * @param array $attr_includes What attribute collections to register to + * element? + * @param array $attr What unique attributes does the element define? + * @see HTMLPurifier_ElementDef:: for in-depth descriptions of these parameters. + * @return HTMLPurifier_ElementDef Created element definition object, so you + * can set advanced parameters + */ + public function addElement($element, $type, $contents, $attr_includes = array(), $attr = array()) + { + $this->elements[] = $element; + // parse content_model + list($content_model_type, $content_model) = $this->parseContents($contents); + // merge in attribute inclusions + $this->mergeInAttrIncludes($attr, $attr_includes); + // add element to content sets + if ($type) { + $this->addElementToContentSet($element, $type); + } + // create element + $this->info[$element] = HTMLPurifier_ElementDef::create( + $content_model, + $content_model_type, + $attr + ); + // literal object $contents means direct child manipulation + if (!is_string($contents)) { + $this->info[$element]->child = $contents; + } + return $this->info[$element]; + } + + /** + * Convenience function that creates a totally blank, non-standalone + * element. + * @param string $element Name of element to create + * @return HTMLPurifier_ElementDef Created element + */ + public function addBlankElement($element) + { + if (!isset($this->info[$element])) { + $this->elements[] = $element; + $this->info[$element] = new HTMLPurifier_ElementDef(); + $this->info[$element]->standalone = false; + } else { + trigger_error("Definition for $element already exists in module, cannot redefine"); + } + return $this->info[$element]; + } + + /** + * Convenience function that registers an element to a content set + * @param string $element Element to register + * @param string $type Name content set (warning: case sensitive, usually upper-case + * first letter) + */ + public function addElementToContentSet($element, $type) + { + if (!isset($this->content_sets[$type])) { + $this->content_sets[$type] = ''; + } else { + $this->content_sets[$type] .= ' | '; + } + $this->content_sets[$type] .= $element; + } + + /** + * Convenience function that transforms single-string contents + * into separate content model and content model type + * @param string $contents Allowed children in form of: + * "$content_model_type: $content_model" + * @return array + * @note If contents is an object, an array of two nulls will be + * returned, and the callee needs to take the original $contents + * and use it directly. + */ + public function parseContents($contents) + { + if (!is_string($contents)) { + return array(null, null); + } // defer + switch ($contents) { + // check for shorthand content model forms + case 'Empty': + return array('empty', ''); + case 'Inline': + return array('optional', 'Inline | #PCDATA'); + case 'Flow': + return array('optional', 'Flow | #PCDATA'); + } + list($content_model_type, $content_model) = explode(':', $contents); + $content_model_type = strtolower(trim($content_model_type)); + $content_model = trim($content_model); + return array($content_model_type, $content_model); + } + + /** + * Convenience function that merges a list of attribute includes into + * an attribute array. + * @param array $attr Reference to attr array to modify + * @param array $attr_includes Array of includes / string include to merge in + */ + public function mergeInAttrIncludes(&$attr, $attr_includes) + { + if (!is_array($attr_includes)) { + if (empty($attr_includes)) { + $attr_includes = array(); + } else { + $attr_includes = array($attr_includes); + } + } + $attr[0] = $attr_includes; + } + + /** + * Convenience function that generates a lookup table with boolean + * true as value. + * @param string $list List of values to turn into a lookup + * @note You can also pass an arbitrary number of arguments in + * place of the regular argument + * @return array array equivalent of list + */ + public function makeLookup($list) + { + if (is_string($list)) { + $list = func_get_args(); + } + $ret = array(); + foreach ($list as $value) { + if (is_null($value)) { + continue; + } + $ret[$value] = true; + } + return $ret; + } + + /** + * Lazy load construction of the module after determining whether + * or not it's needed, and also when a finalized configuration object + * is available. + * @param HTMLPurifier_Config $config + */ + public function setup($config) + { + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/HTMLModule/Bdo.php b/extlib/HTMLPurifier/HTMLPurifier/HTMLModule/Bdo.php new file mode 100644 index 0000000000..1e67c790d0 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/HTMLModule/Bdo.php @@ -0,0 +1,44 @@ + array('dir' => false) + ); + + /** + * @param HTMLPurifier_Config $config + */ + public function setup($config) + { + $bdo = $this->addElement( + 'bdo', + 'Inline', + 'Inline', + array('Core', 'Lang'), + array( + 'dir' => 'Enum#ltr,rtl', // required + // The Abstract Module specification has the attribute + // inclusions wrong for bdo: bdo allows Lang + ) + ); + $bdo->attr_transform_post[] = new HTMLPurifier_AttrTransform_BdoDir(); + + $this->attr_collections['I18N']['dir'] = 'Enum#ltr,rtl'; + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/HTMLModule/CommonAttributes.php b/extlib/HTMLPurifier/HTMLPurifier/HTMLModule/CommonAttributes.php new file mode 100644 index 0000000000..a96ab1bef1 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/HTMLModule/CommonAttributes.php @@ -0,0 +1,31 @@ + array( + 0 => array('Style'), + // 'xml:space' => false, + 'class' => 'Class', + 'id' => 'ID', + 'title' => 'CDATA', + ), + 'Lang' => array(), + 'I18N' => array( + 0 => array('Lang'), // proprietary, for xml:lang/lang + ), + 'Common' => array( + 0 => array('Core', 'I18N') + ) + ); +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/HTMLModule/Edit.php b/extlib/HTMLPurifier/HTMLPurifier/HTMLModule/Edit.php new file mode 100644 index 0000000000..a9042a3577 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/HTMLModule/Edit.php @@ -0,0 +1,55 @@ + 'URI', + // 'datetime' => 'Datetime', // not implemented + ); + $this->addElement('del', 'Inline', $contents, 'Common', $attr); + $this->addElement('ins', 'Inline', $contents, 'Common', $attr); + } + + // HTML 4.01 specifies that ins/del must not contain block + // elements when used in an inline context, chameleon is + // a complicated workaround to acheive this effect + + // Inline context ! Block context (exclamation mark is + // separator, see getChildDef for parsing) + + /** + * @type bool + */ + public $defines_child_def = true; + + /** + * @param HTMLPurifier_ElementDef $def + * @return HTMLPurifier_ChildDef_Chameleon + */ + public function getChildDef($def) + { + if ($def->content_model_type != 'chameleon') { + return false; + } + $value = explode('!', $def->content_model); + return new HTMLPurifier_ChildDef_Chameleon($value[0], $value[1]); + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/HTMLModule/Forms.php b/extlib/HTMLPurifier/HTMLPurifier/HTMLModule/Forms.php new file mode 100644 index 0000000000..6f7ddbc05b --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/HTMLModule/Forms.php @@ -0,0 +1,190 @@ + 'Form', + 'Inline' => 'Formctrl', + ); + + /** + * @param HTMLPurifier_Config $config + */ + public function setup($config) + { + $form = $this->addElement( + 'form', + 'Form', + 'Required: Heading | List | Block | fieldset', + 'Common', + array( + 'accept' => 'ContentTypes', + 'accept-charset' => 'Charsets', + 'action*' => 'URI', + 'method' => 'Enum#get,post', + // really ContentType, but these two are the only ones used today + 'enctype' => 'Enum#application/x-www-form-urlencoded,multipart/form-data', + ) + ); + $form->excludes = array('form' => true); + + $input = $this->addElement( + 'input', + 'Formctrl', + 'Empty', + 'Common', + array( + 'accept' => 'ContentTypes', + 'accesskey' => 'Character', + 'alt' => 'Text', + 'checked' => 'Bool#checked', + 'disabled' => 'Bool#disabled', + 'maxlength' => 'Number', + 'name' => 'CDATA', + 'readonly' => 'Bool#readonly', + 'size' => 'Number', + 'src' => 'URI#embedded', + 'tabindex' => 'Number', + 'type' => 'Enum#text,password,checkbox,button,radio,submit,reset,file,hidden,image', + 'value' => 'CDATA', + ) + ); + $input->attr_transform_post[] = new HTMLPurifier_AttrTransform_Input(); + + $this->addElement( + 'select', + 'Formctrl', + 'Required: optgroup | option', + 'Common', + array( + 'disabled' => 'Bool#disabled', + 'multiple' => 'Bool#multiple', + 'name' => 'CDATA', + 'size' => 'Number', + 'tabindex' => 'Number', + ) + ); + + $this->addElement( + 'option', + false, + 'Optional: #PCDATA', + 'Common', + array( + 'disabled' => 'Bool#disabled', + 'label' => 'Text', + 'selected' => 'Bool#selected', + 'value' => 'CDATA', + ) + ); + // It's illegal for there to be more than one selected, but not + // be multiple. Also, no selected means undefined behavior. This might + // be difficult to implement; perhaps an injector, or a context variable. + + $textarea = $this->addElement( + 'textarea', + 'Formctrl', + 'Optional: #PCDATA', + 'Common', + array( + 'accesskey' => 'Character', + 'cols*' => 'Number', + 'disabled' => 'Bool#disabled', + 'name' => 'CDATA', + 'readonly' => 'Bool#readonly', + 'rows*' => 'Number', + 'tabindex' => 'Number', + ) + ); + $textarea->attr_transform_pre[] = new HTMLPurifier_AttrTransform_Textarea(); + + $button = $this->addElement( + 'button', + 'Formctrl', + 'Optional: #PCDATA | Heading | List | Block | Inline', + 'Common', + array( + 'accesskey' => 'Character', + 'disabled' => 'Bool#disabled', + 'name' => 'CDATA', + 'tabindex' => 'Number', + 'type' => 'Enum#button,submit,reset', + 'value' => 'CDATA', + ) + ); + + // For exclusions, ideally we'd specify content sets, not literal elements + $button->excludes = $this->makeLookup( + 'form', + 'fieldset', // Form + 'input', + 'select', + 'textarea', + 'label', + 'button', // Formctrl + 'a', // as per HTML 4.01 spec, this is omitted by modularization + 'isindex', + 'iframe' // legacy items + ); + + // Extra exclusion: img usemap="" is not permitted within this element. + // We'll omit this for now, since we don't have any good way of + // indicating it yet. + + // This is HIGHLY user-unfriendly; we need a custom child-def for this + $this->addElement('fieldset', 'Form', 'Custom: (#WS?,legend,(Flow|#PCDATA)*)', 'Common'); + + $label = $this->addElement( + 'label', + 'Formctrl', + 'Optional: #PCDATA | Inline', + 'Common', + array( + 'accesskey' => 'Character', + // 'for' => 'IDREF', // IDREF not implemented, cannot allow + ) + ); + $label->excludes = array('label' => true); + + $this->addElement( + 'legend', + false, + 'Optional: #PCDATA | Inline', + 'Common', + array( + 'accesskey' => 'Character', + ) + ); + + $this->addElement( + 'optgroup', + false, + 'Required: option', + 'Common', + array( + 'disabled' => 'Bool#disabled', + 'label*' => 'Text', + ) + ); + // Don't forget an injector for . This one's a little complex + // because it maps to multiple elements. + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/HTMLModule/Hypertext.php b/extlib/HTMLPurifier/HTMLPurifier/HTMLModule/Hypertext.php new file mode 100644 index 0000000000..72d7a31e68 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/HTMLModule/Hypertext.php @@ -0,0 +1,40 @@ +addElement( + 'a', + 'Inline', + 'Inline', + 'Common', + array( + // 'accesskey' => 'Character', + // 'charset' => 'Charset', + 'href' => 'URI', + // 'hreflang' => 'LanguageCode', + 'rel' => new HTMLPurifier_AttrDef_HTML_LinkTypes('rel'), + 'rev' => new HTMLPurifier_AttrDef_HTML_LinkTypes('rev'), + // 'tabindex' => 'Number', + // 'type' => 'ContentType', + ) + ); + $a->formatting = true; + $a->excludes = array('a' => true); + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/HTMLModule/Iframe.php b/extlib/HTMLPurifier/HTMLPurifier/HTMLModule/Iframe.php new file mode 100644 index 0000000000..f7e7c91c02 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/HTMLModule/Iframe.php @@ -0,0 +1,51 @@ +get('HTML.SafeIframe')) { + $this->safe = true; + } + $this->addElement( + 'iframe', + 'Inline', + 'Flow', + 'Common', + array( + 'src' => 'URI#embedded', + 'width' => 'Length', + 'height' => 'Length', + 'name' => 'ID', + 'scrolling' => 'Enum#yes,no,auto', + 'frameborder' => 'Enum#0,1', + 'longdesc' => 'URI', + 'marginheight' => 'Pixels', + 'marginwidth' => 'Pixels', + ) + ); + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/HTMLModule/Image.php b/extlib/HTMLPurifier/HTMLPurifier/HTMLModule/Image.php new file mode 100644 index 0000000000..0f5fdb3baf --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/HTMLModule/Image.php @@ -0,0 +1,49 @@ +get('HTML.MaxImgLength'); + $img = $this->addElement( + 'img', + 'Inline', + 'Empty', + 'Common', + array( + 'alt*' => 'Text', + // According to the spec, it's Length, but percents can + // be abused, so we allow only Pixels. + 'height' => 'Pixels#' . $max, + 'width' => 'Pixels#' . $max, + 'longdesc' => 'URI', + 'src*' => new HTMLPurifier_AttrDef_URI(true), // embedded + ) + ); + if ($max === null || $config->get('HTML.Trusted')) { + $img->attr['height'] = + $img->attr['width'] = 'Length'; + } + + // kind of strange, but splitting things up would be inefficient + $img->attr_transform_pre[] = + $img->attr_transform_post[] = + new HTMLPurifier_AttrTransform_ImgRequired(); + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/HTMLModule/Legacy.php b/extlib/HTMLPurifier/HTMLPurifier/HTMLModule/Legacy.php new file mode 100644 index 0000000000..86b5299579 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/HTMLModule/Legacy.php @@ -0,0 +1,186 @@ +addElement( + 'basefont', + 'Inline', + 'Empty', + null, + array( + 'color' => 'Color', + 'face' => 'Text', // extremely broad, we should + 'size' => 'Text', // tighten it + 'id' => 'ID' + ) + ); + $this->addElement('center', 'Block', 'Flow', 'Common'); + $this->addElement( + 'dir', + 'Block', + 'Required: li', + 'Common', + array( + 'compact' => 'Bool#compact' + ) + ); + $this->addElement( + 'font', + 'Inline', + 'Inline', + array('Core', 'I18N'), + array( + 'color' => 'Color', + 'face' => 'Text', // extremely broad, we should + 'size' => 'Text', // tighten it + ) + ); + $this->addElement( + 'menu', + 'Block', + 'Required: li', + 'Common', + array( + 'compact' => 'Bool#compact' + ) + ); + + $s = $this->addElement('s', 'Inline', 'Inline', 'Common'); + $s->formatting = true; + + $strike = $this->addElement('strike', 'Inline', 'Inline', 'Common'); + $strike->formatting = true; + + $u = $this->addElement('u', 'Inline', 'Inline', 'Common'); + $u->formatting = true; + + // setup modifications to old elements + + $align = 'Enum#left,right,center,justify'; + + $address = $this->addBlankElement('address'); + $address->content_model = 'Inline | #PCDATA | p'; + $address->content_model_type = 'optional'; + $address->child = false; + + $blockquote = $this->addBlankElement('blockquote'); + $blockquote->content_model = 'Flow | #PCDATA'; + $blockquote->content_model_type = 'optional'; + $blockquote->child = false; + + $br = $this->addBlankElement('br'); + $br->attr['clear'] = 'Enum#left,all,right,none'; + + $caption = $this->addBlankElement('caption'); + $caption->attr['align'] = 'Enum#top,bottom,left,right'; + + $div = $this->addBlankElement('div'); + $div->attr['align'] = $align; + + $dl = $this->addBlankElement('dl'); + $dl->attr['compact'] = 'Bool#compact'; + + for ($i = 1; $i <= 6; $i++) { + $h = $this->addBlankElement("h$i"); + $h->attr['align'] = $align; + } + + $hr = $this->addBlankElement('hr'); + $hr->attr['align'] = $align; + $hr->attr['noshade'] = 'Bool#noshade'; + $hr->attr['size'] = 'Pixels'; + $hr->attr['width'] = 'Length'; + + $img = $this->addBlankElement('img'); + $img->attr['align'] = 'IAlign'; + $img->attr['border'] = 'Pixels'; + $img->attr['hspace'] = 'Pixels'; + $img->attr['vspace'] = 'Pixels'; + + // figure out this integer business + + $li = $this->addBlankElement('li'); + $li->attr['value'] = new HTMLPurifier_AttrDef_Integer(); + $li->attr['type'] = 'Enum#s:1,i,I,a,A,disc,square,circle'; + + $ol = $this->addBlankElement('ol'); + $ol->attr['compact'] = 'Bool#compact'; + $ol->attr['start'] = new HTMLPurifier_AttrDef_Integer(); + $ol->attr['type'] = 'Enum#s:1,i,I,a,A'; + + $p = $this->addBlankElement('p'); + $p->attr['align'] = $align; + + $pre = $this->addBlankElement('pre'); + $pre->attr['width'] = 'Number'; + + // script omitted + + $table = $this->addBlankElement('table'); + $table->attr['align'] = 'Enum#left,center,right'; + $table->attr['bgcolor'] = 'Color'; + + $tr = $this->addBlankElement('tr'); + $tr->attr['bgcolor'] = 'Color'; + + $th = $this->addBlankElement('th'); + $th->attr['bgcolor'] = 'Color'; + $th->attr['height'] = 'Length'; + $th->attr['nowrap'] = 'Bool#nowrap'; + $th->attr['width'] = 'Length'; + + $td = $this->addBlankElement('td'); + $td->attr['bgcolor'] = 'Color'; + $td->attr['height'] = 'Length'; + $td->attr['nowrap'] = 'Bool#nowrap'; + $td->attr['width'] = 'Length'; + + $ul = $this->addBlankElement('ul'); + $ul->attr['compact'] = 'Bool#compact'; + $ul->attr['type'] = 'Enum#square,disc,circle'; + + // "safe" modifications to "unsafe" elements + // WARNING: If you want to add support for an unsafe, legacy + // attribute, make a new TrustedLegacy module with the trusted + // bit set appropriately + + $form = $this->addBlankElement('form'); + $form->content_model = 'Flow | #PCDATA'; + $form->content_model_type = 'optional'; + $form->attr['target'] = 'FrameTarget'; + + $input = $this->addBlankElement('input'); + $input->attr['align'] = 'IAlign'; + + $legend = $this->addBlankElement('legend'); + $legend->attr['align'] = 'LAlign'; + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/HTMLModule/List.php b/extlib/HTMLPurifier/HTMLPurifier/HTMLModule/List.php new file mode 100644 index 0000000000..7a20ff701c --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/HTMLModule/List.php @@ -0,0 +1,51 @@ + 'List'); + + /** + * @param HTMLPurifier_Config $config + */ + public function setup($config) + { + $ol = $this->addElement('ol', 'List', new HTMLPurifier_ChildDef_List(), 'Common'); + $ul = $this->addElement('ul', 'List', new HTMLPurifier_ChildDef_List(), 'Common'); + // XXX The wrap attribute is handled by MakeWellFormed. This is all + // quite unsatisfactory, because we generated this + // *specifically* for lists, and now a big chunk of the handling + // is done properly by the List ChildDef. So actually, we just + // want enough information to make autoclosing work properly, + // and then hand off the tricky stuff to the ChildDef. + $ol->wrap = 'li'; + $ul->wrap = 'li'; + $this->addElement('dl', 'List', 'Required: dt | dd', 'Common'); + + $this->addElement('li', false, 'Flow', 'Common'); + + $this->addElement('dd', false, 'Flow', 'Common'); + $this->addElement('dt', false, 'Inline', 'Common'); + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/HTMLModule/Name.php b/extlib/HTMLPurifier/HTMLPurifier/HTMLModule/Name.php new file mode 100644 index 0000000000..60c0545154 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/HTMLModule/Name.php @@ -0,0 +1,26 @@ +addBlankElement($name); + $element->attr['name'] = 'CDATA'; + if (!$config->get('HTML.Attr.Name.UseCDATA')) { + $element->attr_transform_post[] = new HTMLPurifier_AttrTransform_NameSync(); + } + } + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/HTMLModule/Nofollow.php b/extlib/HTMLPurifier/HTMLPurifier/HTMLModule/Nofollow.php new file mode 100644 index 0000000000..dc9410a895 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/HTMLModule/Nofollow.php @@ -0,0 +1,25 @@ +addBlankElement('a'); + $a->attr_transform_post[] = new HTMLPurifier_AttrTransform_Nofollow(); + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/HTMLModule/NonXMLCommonAttributes.php b/extlib/HTMLPurifier/HTMLPurifier/HTMLModule/NonXMLCommonAttributes.php new file mode 100644 index 0000000000..da722253ac --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/HTMLModule/NonXMLCommonAttributes.php @@ -0,0 +1,20 @@ + array( + 'lang' => 'LanguageCode', + ) + ); +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/HTMLModule/Object.php b/extlib/HTMLPurifier/HTMLPurifier/HTMLModule/Object.php new file mode 100644 index 0000000000..2f9efc5c88 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/HTMLModule/Object.php @@ -0,0 +1,62 @@ + to cater to legacy browsers: this + * module does not allow this sort of behavior + */ +class HTMLPurifier_HTMLModule_Object extends HTMLPurifier_HTMLModule +{ + /** + * @type string + */ + public $name = 'Object'; + + /** + * @type bool + */ + public $safe = false; + + /** + * @param HTMLPurifier_Config $config + */ + public function setup($config) + { + $this->addElement( + 'object', + 'Inline', + 'Optional: #PCDATA | Flow | param', + 'Common', + array( + 'archive' => 'URI', + 'classid' => 'URI', + 'codebase' => 'URI', + 'codetype' => 'Text', + 'data' => 'URI', + 'declare' => 'Bool#declare', + 'height' => 'Length', + 'name' => 'CDATA', + 'standby' => 'Text', + 'tabindex' => 'Number', + 'type' => 'ContentType', + 'width' => 'Length' + ) + ); + + $this->addElement( + 'param', + false, + 'Empty', + null, + array( + 'id' => 'ID', + 'name*' => 'Text', + 'type' => 'Text', + 'value' => 'Text', + 'valuetype' => 'Enum#data,ref,object' + ) + ); + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/HTMLModule/Presentation.php b/extlib/HTMLPurifier/HTMLPurifier/HTMLModule/Presentation.php new file mode 100644 index 0000000000..6458ce9d88 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/HTMLModule/Presentation.php @@ -0,0 +1,42 @@ +addElement('hr', 'Block', 'Empty', 'Common'); + $this->addElement('sub', 'Inline', 'Inline', 'Common'); + $this->addElement('sup', 'Inline', 'Inline', 'Common'); + $b = $this->addElement('b', 'Inline', 'Inline', 'Common'); + $b->formatting = true; + $big = $this->addElement('big', 'Inline', 'Inline', 'Common'); + $big->formatting = true; + $i = $this->addElement('i', 'Inline', 'Inline', 'Common'); + $i->formatting = true; + $small = $this->addElement('small', 'Inline', 'Inline', 'Common'); + $small->formatting = true; + $tt = $this->addElement('tt', 'Inline', 'Inline', 'Common'); + $tt->formatting = true; + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/HTMLModule/Proprietary.php b/extlib/HTMLPurifier/HTMLPurifier/HTMLModule/Proprietary.php new file mode 100644 index 0000000000..5ee3c8e67f --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/HTMLModule/Proprietary.php @@ -0,0 +1,40 @@ +addElement( + 'marquee', + 'Inline', + 'Flow', + 'Common', + array( + 'direction' => 'Enum#left,right,up,down', + 'behavior' => 'Enum#alternate', + 'width' => 'Length', + 'height' => 'Length', + 'scrolldelay' => 'Number', + 'scrollamount' => 'Number', + 'loop' => 'Number', + 'bgcolor' => 'Color', + 'hspace' => 'Pixels', + 'vspace' => 'Pixels', + ) + ); + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/HTMLModule/Ruby.php b/extlib/HTMLPurifier/HTMLPurifier/HTMLModule/Ruby.php new file mode 100644 index 0000000000..a0d48924da --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/HTMLModule/Ruby.php @@ -0,0 +1,36 @@ +addElement( + 'ruby', + 'Inline', + 'Custom: ((rb, (rt | (rp, rt, rp))) | (rbc, rtc, rtc?))', + 'Common' + ); + $this->addElement('rbc', false, 'Required: rb', 'Common'); + $this->addElement('rtc', false, 'Required: rt', 'Common'); + $rb = $this->addElement('rb', false, 'Inline', 'Common'); + $rb->excludes = array('ruby' => true); + $rt = $this->addElement('rt', false, 'Inline', 'Common', array('rbspan' => 'Number')); + $rt->excludes = array('ruby' => true); + $this->addElement('rp', false, 'Optional: #PCDATA', 'Common'); + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/HTMLModule/SafeEmbed.php b/extlib/HTMLPurifier/HTMLPurifier/HTMLModule/SafeEmbed.php new file mode 100644 index 0000000000..04e6689ea6 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/HTMLModule/SafeEmbed.php @@ -0,0 +1,40 @@ +get('HTML.MaxImgLength'); + $embed = $this->addElement( + 'embed', + 'Inline', + 'Empty', + 'Common', + array( + 'src*' => 'URI#embedded', + 'type' => 'Enum#application/x-shockwave-flash', + 'width' => 'Pixels#' . $max, + 'height' => 'Pixels#' . $max, + 'allowscriptaccess' => 'Enum#never', + 'allownetworking' => 'Enum#internal', + 'flashvars' => 'Text', + 'wmode' => 'Enum#window,transparent,opaque', + 'name' => 'ID', + ) + ); + $embed->attr_transform_post[] = new HTMLPurifier_AttrTransform_SafeEmbed(); + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/HTMLModule/SafeObject.php b/extlib/HTMLPurifier/HTMLPurifier/HTMLModule/SafeObject.php new file mode 100644 index 0000000000..1297f80a39 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/HTMLModule/SafeObject.php @@ -0,0 +1,62 @@ +get('HTML.MaxImgLength'); + $object = $this->addElement( + 'object', + 'Inline', + 'Optional: param | Flow | #PCDATA', + 'Common', + array( + // While technically not required by the spec, we're forcing + // it to this value. + 'type' => 'Enum#application/x-shockwave-flash', + 'width' => 'Pixels#' . $max, + 'height' => 'Pixels#' . $max, + 'data' => 'URI#embedded', + 'codebase' => new HTMLPurifier_AttrDef_Enum( + array( + 'http://download.macromedia.com/pub/shockwave/cabs/flash/swflash.cab#version=6,0,40,0' + ) + ), + ) + ); + $object->attr_transform_post[] = new HTMLPurifier_AttrTransform_SafeObject(); + + $param = $this->addElement( + 'param', + false, + 'Empty', + false, + array( + 'id' => 'ID', + 'name*' => 'Text', + 'value' => 'Text' + ) + ); + $param->attr_transform_post[] = new HTMLPurifier_AttrTransform_SafeParam(); + $this->info_injector[] = 'SafeObject'; + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/HTMLModule/SafeScripting.php b/extlib/HTMLPurifier/HTMLPurifier/HTMLModule/SafeScripting.php new file mode 100644 index 0000000000..0330cd97f8 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/HTMLModule/SafeScripting.php @@ -0,0 +1,40 @@ +get('HTML.SafeScripting'); + $script = $this->addElement( + 'script', + 'Inline', + 'Empty', + null, + array( + // While technically not required by the spec, we're forcing + // it to this value. + 'type' => 'Enum#text/javascript', + 'src*' => new HTMLPurifier_AttrDef_Enum(array_keys($allowed)) + ) + ); + $script->attr_transform_pre[] = + $script->attr_transform_post[] = new HTMLPurifier_AttrTransform_ScriptRequired(); + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/HTMLModule/Scripting.php b/extlib/HTMLPurifier/HTMLPurifier/HTMLModule/Scripting.php new file mode 100644 index 0000000000..8b28a7b7ea --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/HTMLModule/Scripting.php @@ -0,0 +1,73 @@ + 'script | noscript', 'Inline' => 'script | noscript'); + + /** + * @type bool + */ + public $safe = false; + + /** + * @param HTMLPurifier_Config $config + */ + public function setup($config) + { + // TODO: create custom child-definition for noscript that + // auto-wraps stray #PCDATA in a similar manner to + // blockquote's custom definition (we would use it but + // blockquote's contents are optional while noscript's contents + // are required) + + // TODO: convert this to new syntax, main problem is getting + // both content sets working + + // In theory, this could be safe, but I don't see any reason to + // allow it. + $this->info['noscript'] = new HTMLPurifier_ElementDef(); + $this->info['noscript']->attr = array(0 => array('Common')); + $this->info['noscript']->content_model = 'Heading | List | Block'; + $this->info['noscript']->content_model_type = 'required'; + + $this->info['script'] = new HTMLPurifier_ElementDef(); + $this->info['script']->attr = array( + 'defer' => new HTMLPurifier_AttrDef_Enum(array('defer')), + 'src' => new HTMLPurifier_AttrDef_URI(true), + 'type' => new HTMLPurifier_AttrDef_Enum(array('text/javascript')) + ); + $this->info['script']->content_model = '#PCDATA'; + $this->info['script']->content_model_type = 'optional'; + $this->info['script']->attr_transform_pre[] = + $this->info['script']->attr_transform_post[] = + new HTMLPurifier_AttrTransform_ScriptRequired(); + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/HTMLModule/StyleAttribute.php b/extlib/HTMLPurifier/HTMLPurifier/HTMLModule/StyleAttribute.php new file mode 100644 index 0000000000..497b832ae2 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/HTMLModule/StyleAttribute.php @@ -0,0 +1,33 @@ + array('style' => false), // see constructor + 'Core' => array(0 => array('Style')) + ); + + /** + * @param HTMLPurifier_Config $config + */ + public function setup($config) + { + $this->attr_collections['Style']['style'] = new HTMLPurifier_AttrDef_CSS(); + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/HTMLModule/Tables.php b/extlib/HTMLPurifier/HTMLPurifier/HTMLModule/Tables.php new file mode 100644 index 0000000000..8a0b3b4616 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/HTMLModule/Tables.php @@ -0,0 +1,75 @@ +addElement('caption', false, 'Inline', 'Common'); + + $this->addElement( + 'table', + 'Block', + new HTMLPurifier_ChildDef_Table(), + 'Common', + array( + 'border' => 'Pixels', + 'cellpadding' => 'Length', + 'cellspacing' => 'Length', + 'frame' => 'Enum#void,above,below,hsides,lhs,rhs,vsides,box,border', + 'rules' => 'Enum#none,groups,rows,cols,all', + 'summary' => 'Text', + 'width' => 'Length' + ) + ); + + // common attributes + $cell_align = array( + 'align' => 'Enum#left,center,right,justify,char', + 'charoff' => 'Length', + 'valign' => 'Enum#top,middle,bottom,baseline', + ); + + $cell_t = array_merge( + array( + 'abbr' => 'Text', + 'colspan' => 'Number', + 'rowspan' => 'Number', + // Apparently, as of HTML5 this attribute only applies + // to 'th' elements. + 'scope' => 'Enum#row,col,rowgroup,colgroup', + ), + $cell_align + ); + $this->addElement('td', false, 'Flow', 'Common', $cell_t); + $this->addElement('th', false, 'Flow', 'Common', $cell_t); + + $this->addElement('tr', false, 'Required: td | th', 'Common', $cell_align); + + $cell_col = array_merge( + array( + 'span' => 'Number', + 'width' => 'MultiLength', + ), + $cell_align + ); + $this->addElement('col', false, 'Empty', 'Common', $cell_col); + $this->addElement('colgroup', false, 'Optional: col', 'Common', $cell_col); + + $this->addElement('tbody', false, 'Required: tr', 'Common', $cell_align); + $this->addElement('thead', false, 'Required: tr', 'Common', $cell_align); + $this->addElement('tfoot', false, 'Required: tr', 'Common', $cell_align); + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/HTMLModule/Target.php b/extlib/HTMLPurifier/HTMLPurifier/HTMLModule/Target.php new file mode 100644 index 0000000000..b188ac9369 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/HTMLModule/Target.php @@ -0,0 +1,28 @@ +addBlankElement($name); + $e->attr = array( + 'target' => new HTMLPurifier_AttrDef_HTML_FrameTarget() + ); + } + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/HTMLModule/TargetBlank.php b/extlib/HTMLPurifier/HTMLPurifier/HTMLModule/TargetBlank.php new file mode 100644 index 0000000000..58ccc68941 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/HTMLModule/TargetBlank.php @@ -0,0 +1,24 @@ +addBlankElement('a'); + $a->attr_transform_post[] = new HTMLPurifier_AttrTransform_TargetBlank(); + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/HTMLModule/Text.php b/extlib/HTMLPurifier/HTMLPurifier/HTMLModule/Text.php new file mode 100644 index 0000000000..7a65e0048f --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/HTMLModule/Text.php @@ -0,0 +1,87 @@ + 'Heading | Block | Inline' + ); + + /** + * @param HTMLPurifier_Config $config + */ + public function setup($config) + { + // Inline Phrasal ------------------------------------------------- + $this->addElement('abbr', 'Inline', 'Inline', 'Common'); + $this->addElement('acronym', 'Inline', 'Inline', 'Common'); + $this->addElement('cite', 'Inline', 'Inline', 'Common'); + $this->addElement('dfn', 'Inline', 'Inline', 'Common'); + $this->addElement('kbd', 'Inline', 'Inline', 'Common'); + $this->addElement('q', 'Inline', 'Inline', 'Common', array('cite' => 'URI')); + $this->addElement('samp', 'Inline', 'Inline', 'Common'); + $this->addElement('var', 'Inline', 'Inline', 'Common'); + + $em = $this->addElement('em', 'Inline', 'Inline', 'Common'); + $em->formatting = true; + + $strong = $this->addElement('strong', 'Inline', 'Inline', 'Common'); + $strong->formatting = true; + + $code = $this->addElement('code', 'Inline', 'Inline', 'Common'); + $code->formatting = true; + + // Inline Structural ---------------------------------------------- + $this->addElement('span', 'Inline', 'Inline', 'Common'); + $this->addElement('br', 'Inline', 'Empty', 'Core'); + + // Block Phrasal -------------------------------------------------- + $this->addElement('address', 'Block', 'Inline', 'Common'); + $this->addElement('blockquote', 'Block', 'Optional: Heading | Block | List', 'Common', array('cite' => 'URI')); + $pre = $this->addElement('pre', 'Block', 'Inline', 'Common'); + $pre->excludes = $this->makeLookup( + 'img', + 'big', + 'small', + 'object', + 'applet', + 'font', + 'basefont' + ); + $this->addElement('h1', 'Heading', 'Inline', 'Common'); + $this->addElement('h2', 'Heading', 'Inline', 'Common'); + $this->addElement('h3', 'Heading', 'Inline', 'Common'); + $this->addElement('h4', 'Heading', 'Inline', 'Common'); + $this->addElement('h5', 'Heading', 'Inline', 'Common'); + $this->addElement('h6', 'Heading', 'Inline', 'Common'); + + // Block Structural ----------------------------------------------- + $p = $this->addElement('p', 'Block', 'Inline', 'Common'); + $p->autoclose = array_flip( + array("address", "blockquote", "center", "dir", "div", "dl", "fieldset", "ol", "p", "ul") + ); + + $this->addElement('div', 'Block', 'Flow', 'Common'); + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/HTMLModule/Tidy.php b/extlib/HTMLPurifier/HTMLPurifier/HTMLModule/Tidy.php new file mode 100644 index 0000000000..08aa232470 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/HTMLModule/Tidy.php @@ -0,0 +1,230 @@ + 'none', 'light', 'medium', 'heavy'); + + /** + * Default level to place all fixes in. + * Disabled by default. + * @type string + */ + public $defaultLevel = null; + + /** + * Lists of fixes used by getFixesForLevel(). + * Format is: + * HTMLModule_Tidy->fixesForLevel[$level] = array('fix-1', 'fix-2'); + * @type array + */ + public $fixesForLevel = array( + 'light' => array(), + 'medium' => array(), + 'heavy' => array() + ); + + /** + * Lazy load constructs the module by determining the necessary + * fixes to create and then delegating to the populate() function. + * @param HTMLPurifier_Config $config + * @todo Wildcard matching and error reporting when an added or + * subtracted fix has no effect. + */ + public function setup($config) + { + // create fixes, initialize fixesForLevel + $fixes = $this->makeFixes(); + $this->makeFixesForLevel($fixes); + + // figure out which fixes to use + $level = $config->get('HTML.TidyLevel'); + $fixes_lookup = $this->getFixesForLevel($level); + + // get custom fix declarations: these need namespace processing + $add_fixes = $config->get('HTML.TidyAdd'); + $remove_fixes = $config->get('HTML.TidyRemove'); + + foreach ($fixes as $name => $fix) { + // needs to be refactored a little to implement globbing + if (isset($remove_fixes[$name]) || + (!isset($add_fixes[$name]) && !isset($fixes_lookup[$name]))) { + unset($fixes[$name]); + } + } + + // populate this module with necessary fixes + $this->populate($fixes); + } + + /** + * Retrieves all fixes per a level, returning fixes for that specific + * level as well as all levels below it. + * @param string $level level identifier, see $levels for valid values + * @return array Lookup up table of fixes + */ + public function getFixesForLevel($level) + { + if ($level == $this->levels[0]) { + return array(); + } + $activated_levels = array(); + for ($i = 1, $c = count($this->levels); $i < $c; $i++) { + $activated_levels[] = $this->levels[$i]; + if ($this->levels[$i] == $level) { + break; + } + } + if ($i == $c) { + trigger_error( + 'Tidy level ' . htmlspecialchars($level) . ' not recognized', + E_USER_WARNING + ); + return array(); + } + $ret = array(); + foreach ($activated_levels as $level) { + foreach ($this->fixesForLevel[$level] as $fix) { + $ret[$fix] = true; + } + } + return $ret; + } + + /** + * Dynamically populates the $fixesForLevel member variable using + * the fixes array. It may be custom overloaded, used in conjunction + * with $defaultLevel, or not used at all. + * @param array $fixes + */ + public function makeFixesForLevel($fixes) + { + if (!isset($this->defaultLevel)) { + return; + } + if (!isset($this->fixesForLevel[$this->defaultLevel])) { + trigger_error( + 'Default level ' . $this->defaultLevel . ' does not exist', + E_USER_ERROR + ); + return; + } + $this->fixesForLevel[$this->defaultLevel] = array_keys($fixes); + } + + /** + * Populates the module with transforms and other special-case code + * based on a list of fixes passed to it + * @param array $fixes Lookup table of fixes to activate + */ + public function populate($fixes) + { + foreach ($fixes as $name => $fix) { + // determine what the fix is for + list($type, $params) = $this->getFixType($name); + switch ($type) { + case 'attr_transform_pre': + case 'attr_transform_post': + $attr = $params['attr']; + if (isset($params['element'])) { + $element = $params['element']; + if (empty($this->info[$element])) { + $e = $this->addBlankElement($element); + } else { + $e = $this->info[$element]; + } + } else { + $type = "info_$type"; + $e = $this; + } + // PHP does some weird parsing when I do + // $e->$type[$attr], so I have to assign a ref. + $f =& $e->$type; + $f[$attr] = $fix; + break; + case 'tag_transform': + $this->info_tag_transform[$params['element']] = $fix; + break; + case 'child': + case 'content_model_type': + $element = $params['element']; + if (empty($this->info[$element])) { + $e = $this->addBlankElement($element); + } else { + $e = $this->info[$element]; + } + $e->$type = $fix; + break; + default: + trigger_error("Fix type $type not supported", E_USER_ERROR); + break; + } + } + } + + /** + * Parses a fix name and determines what kind of fix it is, as well + * as other information defined by the fix + * @param $name String name of fix + * @return array(string $fix_type, array $fix_parameters) + * @note $fix_parameters is type dependant, see populate() for usage + * of these parameters + */ + public function getFixType($name) + { + // parse it + $property = $attr = null; + if (strpos($name, '#') !== false) { + list($name, $property) = explode('#', $name); + } + if (strpos($name, '@') !== false) { + list($name, $attr) = explode('@', $name); + } + + // figure out the parameters + $params = array(); + if ($name !== '') { + $params['element'] = $name; + } + if (!is_null($attr)) { + $params['attr'] = $attr; + } + + // special case: attribute transform + if (!is_null($attr)) { + if (is_null($property)) { + $property = 'pre'; + } + $type = 'attr_transform_' . $property; + return array($type, $params); + } + + // special case: tag transform + if (is_null($property)) { + return array('tag_transform', $params); + } + + return array($property, $params); + + } + + /** + * Defines all fixes the module will perform in a compact + * associative array of fix name to fix implementation. + * @return array + */ + public function makeFixes() + { + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/HTMLModule/Tidy/Name.php b/extlib/HTMLPurifier/HTMLPurifier/HTMLModule/Tidy/Name.php new file mode 100644 index 0000000000..a995161b28 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/HTMLModule/Tidy/Name.php @@ -0,0 +1,33 @@ +content_model_type != 'strictblockquote') { + return parent::getChildDef($def); + } + return new HTMLPurifier_ChildDef_StrictBlockquote($def->content_model); + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/HTMLModule/Tidy/Transitional.php b/extlib/HTMLPurifier/HTMLPurifier/HTMLModule/Tidy/Transitional.php new file mode 100644 index 0000000000..c095ad9745 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/HTMLModule/Tidy/Transitional.php @@ -0,0 +1,16 @@ + 'text-align:left;', + 'right' => 'text-align:right;', + 'top' => 'caption-side:top;', + 'bottom' => 'caption-side:bottom;' // not supported by IE + ) + ); + + // @align for img ------------------------------------------------- + $r['img@align'] = + new HTMLPurifier_AttrTransform_EnumToCSS( + 'align', + array( + 'left' => 'float:left;', + 'right' => 'float:right;', + 'top' => 'vertical-align:top;', + 'middle' => 'vertical-align:middle;', + 'bottom' => 'vertical-align:baseline;', + ) + ); + + // @align for table ----------------------------------------------- + $r['table@align'] = + new HTMLPurifier_AttrTransform_EnumToCSS( + 'align', + array( + 'left' => 'float:left;', + 'center' => 'margin-left:auto;margin-right:auto;', + 'right' => 'float:right;' + ) + ); + + // @align for hr ----------------------------------------------- + $r['hr@align'] = + new HTMLPurifier_AttrTransform_EnumToCSS( + 'align', + array( + // we use both text-align and margin because these work + // for different browsers (IE and Firefox, respectively) + // and the melange makes for a pretty cross-compatible + // solution + 'left' => 'margin-left:0;margin-right:auto;text-align:left;', + 'center' => 'margin-left:auto;margin-right:auto;text-align:center;', + 'right' => 'margin-left:auto;margin-right:0;text-align:right;' + ) + ); + + // @align for h1, h2, h3, h4, h5, h6, p, div ---------------------- + // {{{ + $align_lookup = array(); + $align_values = array('left', 'right', 'center', 'justify'); + foreach ($align_values as $v) { + $align_lookup[$v] = "text-align:$v;"; + } + // }}} + $r['h1@align'] = + $r['h2@align'] = + $r['h3@align'] = + $r['h4@align'] = + $r['h5@align'] = + $r['h6@align'] = + $r['p@align'] = + $r['div@align'] = + new HTMLPurifier_AttrTransform_EnumToCSS('align', $align_lookup); + + // @bgcolor for table, tr, td, th --------------------------------- + $r['table@bgcolor'] = + $r['td@bgcolor'] = + $r['th@bgcolor'] = + new HTMLPurifier_AttrTransform_BgColor(); + + // @border for img ------------------------------------------------ + $r['img@border'] = new HTMLPurifier_AttrTransform_Border(); + + // @clear for br -------------------------------------------------- + $r['br@clear'] = + new HTMLPurifier_AttrTransform_EnumToCSS( + 'clear', + array( + 'left' => 'clear:left;', + 'right' => 'clear:right;', + 'all' => 'clear:both;', + 'none' => 'clear:none;', + ) + ); + + // @height for td, th --------------------------------------------- + $r['td@height'] = + $r['th@height'] = + new HTMLPurifier_AttrTransform_Length('height'); + + // @hspace for img ------------------------------------------------ + $r['img@hspace'] = new HTMLPurifier_AttrTransform_ImgSpace('hspace'); + + // @noshade for hr ------------------------------------------------ + // this transformation is not precise but often good enough. + // different browsers use different styles to designate noshade + $r['hr@noshade'] = + new HTMLPurifier_AttrTransform_BoolToCSS( + 'noshade', + 'color:#808080;background-color:#808080;border:0;' + ); + + // @nowrap for td, th --------------------------------------------- + $r['td@nowrap'] = + $r['th@nowrap'] = + new HTMLPurifier_AttrTransform_BoolToCSS( + 'nowrap', + 'white-space:nowrap;' + ); + + // @size for hr -------------------------------------------------- + $r['hr@size'] = new HTMLPurifier_AttrTransform_Length('size', 'height'); + + // @type for li, ol, ul ------------------------------------------- + // {{{ + $ul_types = array( + 'disc' => 'list-style-type:disc;', + 'square' => 'list-style-type:square;', + 'circle' => 'list-style-type:circle;' + ); + $ol_types = array( + '1' => 'list-style-type:decimal;', + 'i' => 'list-style-type:lower-roman;', + 'I' => 'list-style-type:upper-roman;', + 'a' => 'list-style-type:lower-alpha;', + 'A' => 'list-style-type:upper-alpha;' + ); + $li_types = $ul_types + $ol_types; + // }}} + + $r['ul@type'] = new HTMLPurifier_AttrTransform_EnumToCSS('type', $ul_types); + $r['ol@type'] = new HTMLPurifier_AttrTransform_EnumToCSS('type', $ol_types, true); + $r['li@type'] = new HTMLPurifier_AttrTransform_EnumToCSS('type', $li_types, true); + + // @vspace for img ------------------------------------------------ + $r['img@vspace'] = new HTMLPurifier_AttrTransform_ImgSpace('vspace'); + + // @width for hr, td, th ------------------------------------------ + $r['td@width'] = + $r['th@width'] = + $r['hr@width'] = new HTMLPurifier_AttrTransform_Length('width'); + + return $r; + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/HTMLModule/XMLCommonAttributes.php b/extlib/HTMLPurifier/HTMLPurifier/HTMLModule/XMLCommonAttributes.php new file mode 100644 index 0000000000..01dbe9deb6 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/HTMLModule/XMLCommonAttributes.php @@ -0,0 +1,20 @@ + array( + 'xml:lang' => 'LanguageCode', + ) + ); +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/HTMLModuleManager.php b/extlib/HTMLPurifier/HTMLPurifier/HTMLModuleManager.php new file mode 100644 index 0000000000..f3a17cb03b --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/HTMLModuleManager.php @@ -0,0 +1,459 @@ +attrTypes = new HTMLPurifier_AttrTypes(); + $this->doctypes = new HTMLPurifier_DoctypeRegistry(); + + // setup basic modules + $common = array( + 'CommonAttributes', 'Text', 'Hypertext', 'List', + 'Presentation', 'Edit', 'Bdo', 'Tables', 'Image', + 'StyleAttribute', + // Unsafe: + 'Scripting', 'Object', 'Forms', + // Sorta legacy, but present in strict: + 'Name', + ); + $transitional = array('Legacy', 'Target', 'Iframe'); + $xml = array('XMLCommonAttributes'); + $non_xml = array('NonXMLCommonAttributes'); + + // setup basic doctypes + $this->doctypes->register( + 'HTML 4.01 Transitional', + false, + array_merge($common, $transitional, $non_xml), + array('Tidy_Transitional', 'Tidy_Proprietary'), + array(), + '-//W3C//DTD HTML 4.01 Transitional//EN', + 'http://www.w3.org/TR/html4/loose.dtd' + ); + + $this->doctypes->register( + 'HTML 4.01 Strict', + false, + array_merge($common, $non_xml), + array('Tidy_Strict', 'Tidy_Proprietary', 'Tidy_Name'), + array(), + '-//W3C//DTD HTML 4.01//EN', + 'http://www.w3.org/TR/html4/strict.dtd' + ); + + $this->doctypes->register( + 'XHTML 1.0 Transitional', + true, + array_merge($common, $transitional, $xml, $non_xml), + array('Tidy_Transitional', 'Tidy_XHTML', 'Tidy_Proprietary', 'Tidy_Name'), + array(), + '-//W3C//DTD XHTML 1.0 Transitional//EN', + 'http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd' + ); + + $this->doctypes->register( + 'XHTML 1.0 Strict', + true, + array_merge($common, $xml, $non_xml), + array('Tidy_Strict', 'Tidy_XHTML', 'Tidy_Strict', 'Tidy_Proprietary', 'Tidy_Name'), + array(), + '-//W3C//DTD XHTML 1.0 Strict//EN', + 'http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd' + ); + + $this->doctypes->register( + 'XHTML 1.1', + true, + // Iframe is a real XHTML 1.1 module, despite being + // "transitional"! + array_merge($common, $xml, array('Ruby', 'Iframe')), + array('Tidy_Strict', 'Tidy_XHTML', 'Tidy_Proprietary', 'Tidy_Strict', 'Tidy_Name'), // Tidy_XHTML1_1 + array(), + '-//W3C//DTD XHTML 1.1//EN', + 'http://www.w3.org/TR/xhtml11/DTD/xhtml11.dtd' + ); + + } + + /** + * Registers a module to the recognized module list, useful for + * overloading pre-existing modules. + * @param $module Mixed: string module name, with or without + * HTMLPurifier_HTMLModule prefix, or instance of + * subclass of HTMLPurifier_HTMLModule. + * @param $overload Boolean whether or not to overload previous modules. + * If this is not set, and you do overload a module, + * HTML Purifier will complain with a warning. + * @note This function will not call autoload, you must instantiate + * (and thus invoke) autoload outside the method. + * @note If a string is passed as a module name, different variants + * will be tested in this order: + * - Check for HTMLPurifier_HTMLModule_$name + * - Check all prefixes with $name in order they were added + * - Check for literal object name + * - Throw fatal error + * If your object name collides with an internal class, specify + * your module manually. All modules must have been included + * externally: registerModule will not perform inclusions for you! + */ + public function registerModule($module, $overload = false) + { + if (is_string($module)) { + // attempt to load the module + $original_module = $module; + $ok = false; + foreach ($this->prefixes as $prefix) { + $module = $prefix . $original_module; + if (class_exists($module)) { + $ok = true; + break; + } + } + if (!$ok) { + $module = $original_module; + if (!class_exists($module)) { + trigger_error( + $original_module . ' module does not exist', + E_USER_ERROR + ); + return; + } + } + $module = new $module(); + } + if (empty($module->name)) { + trigger_error('Module instance of ' . get_class($module) . ' must have name'); + return; + } + if (!$overload && isset($this->registeredModules[$module->name])) { + trigger_error('Overloading ' . $module->name . ' without explicit overload parameter', E_USER_WARNING); + } + $this->registeredModules[$module->name] = $module; + } + + /** + * Adds a module to the current doctype by first registering it, + * and then tacking it on to the active doctype + */ + public function addModule($module) + { + $this->registerModule($module); + if (is_object($module)) { + $module = $module->name; + } + $this->userModules[] = $module; + } + + /** + * Adds a class prefix that registerModule() will use to resolve a + * string name to a concrete class + */ + public function addPrefix($prefix) + { + $this->prefixes[] = $prefix; + } + + /** + * Performs processing on modules, after being called you may + * use getElement() and getElements() + * @param HTMLPurifier_Config $config + */ + public function setup($config) + { + $this->trusted = $config->get('HTML.Trusted'); + + // generate + $this->doctype = $this->doctypes->make($config); + $modules = $this->doctype->modules; + + // take out the default modules that aren't allowed + $lookup = $config->get('HTML.AllowedModules'); + $special_cases = $config->get('HTML.CoreModules'); + + if (is_array($lookup)) { + foreach ($modules as $k => $m) { + if (isset($special_cases[$m])) { + continue; + } + if (!isset($lookup[$m])) { + unset($modules[$k]); + } + } + } + + // custom modules + if ($config->get('HTML.Proprietary')) { + $modules[] = 'Proprietary'; + } + if ($config->get('HTML.SafeObject')) { + $modules[] = 'SafeObject'; + } + if ($config->get('HTML.SafeEmbed')) { + $modules[] = 'SafeEmbed'; + } + if ($config->get('HTML.SafeScripting') !== array()) { + $modules[] = 'SafeScripting'; + } + if ($config->get('HTML.Nofollow')) { + $modules[] = 'Nofollow'; + } + if ($config->get('HTML.TargetBlank')) { + $modules[] = 'TargetBlank'; + } + + // merge in custom modules + $modules = array_merge($modules, $this->userModules); + + foreach ($modules as $module) { + $this->processModule($module); + $this->modules[$module]->setup($config); + } + + foreach ($this->doctype->tidyModules as $module) { + $this->processModule($module); + $this->modules[$module]->setup($config); + } + + // prepare any injectors + foreach ($this->modules as $module) { + $n = array(); + foreach ($module->info_injector as $injector) { + if (!is_object($injector)) { + $class = "HTMLPurifier_Injector_$injector"; + $injector = new $class; + } + $n[$injector->name] = $injector; + } + $module->info_injector = $n; + } + + // setup lookup table based on all valid modules + foreach ($this->modules as $module) { + foreach ($module->info as $name => $def) { + if (!isset($this->elementLookup[$name])) { + $this->elementLookup[$name] = array(); + } + $this->elementLookup[$name][] = $module->name; + } + } + + // note the different choice + $this->contentSets = new HTMLPurifier_ContentSets( + // content set assembly deals with all possible modules, + // not just ones deemed to be "safe" + $this->modules + ); + $this->attrCollections = new HTMLPurifier_AttrCollections( + $this->attrTypes, + // there is no way to directly disable a global attribute, + // but using AllowedAttributes or simply not including + // the module in your custom doctype should be sufficient + $this->modules + ); + } + + /** + * Takes a module and adds it to the active module collection, + * registering it if necessary. + */ + public function processModule($module) + { + if (!isset($this->registeredModules[$module]) || is_object($module)) { + $this->registerModule($module); + } + $this->modules[$module] = $this->registeredModules[$module]; + } + + /** + * Retrieves merged element definitions. + * @return Array of HTMLPurifier_ElementDef + */ + public function getElements() + { + $elements = array(); + foreach ($this->modules as $module) { + if (!$this->trusted && !$module->safe) { + continue; + } + foreach ($module->info as $name => $v) { + if (isset($elements[$name])) { + continue; + } + $elements[$name] = $this->getElement($name); + } + } + + // remove dud elements, this happens when an element that + // appeared to be safe actually wasn't + foreach ($elements as $n => $v) { + if ($v === false) { + unset($elements[$n]); + } + } + + return $elements; + + } + + /** + * Retrieves a single merged element definition + * @param string $name Name of element + * @param bool $trusted Boolean trusted overriding parameter: set to true + * if you want the full version of an element + * @return HTMLPurifier_ElementDef Merged HTMLPurifier_ElementDef + * @note You may notice that modules are getting iterated over twice (once + * in getElements() and once here). This + * is because + */ + public function getElement($name, $trusted = null) + { + if (!isset($this->elementLookup[$name])) { + return false; + } + + // setup global state variables + $def = false; + if ($trusted === null) { + $trusted = $this->trusted; + } + + // iterate through each module that has registered itself to this + // element + foreach ($this->elementLookup[$name] as $module_name) { + $module = $this->modules[$module_name]; + + // refuse to create/merge from a module that is deemed unsafe-- + // pretend the module doesn't exist--when trusted mode is not on. + if (!$trusted && !$module->safe) { + continue; + } + + // clone is used because, ideally speaking, the original + // definition should not be modified. Usually, this will + // make no difference, but for consistency's sake + $new_def = clone $module->info[$name]; + + if (!$def && $new_def->standalone) { + $def = $new_def; + } elseif ($def) { + // This will occur even if $new_def is standalone. In practice, + // this will usually result in a full replacement. + $def->mergeIn($new_def); + } else { + // :TODO: + // non-standalone definitions that don't have a standalone + // to merge into could be deferred to the end + // HOWEVER, it is perfectly valid for a non-standalone + // definition to lack a standalone definition, even + // after all processing: this allows us to safely + // specify extra attributes for elements that may not be + // enabled all in one place. In particular, this might + // be the case for trusted elements. WARNING: care must + // be taken that the /extra/ definitions are all safe. + continue; + } + + // attribute value expansions + $this->attrCollections->performInclusions($def->attr); + $this->attrCollections->expandIdentifiers($def->attr, $this->attrTypes); + + // descendants_are_inline, for ChildDef_Chameleon + if (is_string($def->content_model) && + strpos($def->content_model, 'Inline') !== false) { + if ($name != 'del' && $name != 'ins') { + // this is for you, ins/del + $def->descendants_are_inline = true; + } + } + + $this->contentSets->generateChildDef($def, $module); + } + + // This can occur if there is a blank definition, but no base to + // mix it in with + if (!$def) { + return false; + } + + // add information on required attributes + foreach ($def->attr as $attr_name => $attr_def) { + if ($attr_def->required) { + $def->required_attr[] = $attr_name; + } + } + return $def; + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/IDAccumulator.php b/extlib/HTMLPurifier/HTMLPurifier/IDAccumulator.php new file mode 100644 index 0000000000..65c902c076 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/IDAccumulator.php @@ -0,0 +1,57 @@ +load($config->get('Attr.IDBlacklist')); + return $id_accumulator; + } + + /** + * Add an ID to the lookup table. + * @param string $id ID to be added. + * @return bool status, true if success, false if there's a dupe + */ + public function add($id) + { + if (isset($this->ids[$id])) { + return false; + } + return $this->ids[$id] = true; + } + + /** + * Load a list of IDs into the lookup table + * @param $array_of_ids Array of IDs to load + * @note This function doesn't care about duplicates + */ + public function load($array_of_ids) + { + foreach ($array_of_ids as $id) { + $this->ids[$id] = true; + } + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/Injector.php b/extlib/HTMLPurifier/HTMLPurifier/Injector.php new file mode 100644 index 0000000000..5060eef9e2 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/Injector.php @@ -0,0 +1,281 @@ +processToken() + * documentation. + * + * @todo Allow injectors to request a re-run on their output. This + * would help if an operation is recursive. + */ +abstract class HTMLPurifier_Injector +{ + + /** + * Advisory name of injector, this is for friendly error messages. + * @type string + */ + public $name; + + /** + * @type HTMLPurifier_HTMLDefinition + */ + protected $htmlDefinition; + + /** + * Reference to CurrentNesting variable in Context. This is an array + * list of tokens that we are currently "inside" + * @type array + */ + protected $currentNesting; + + /** + * Reference to current token. + * @type HTMLPurifier_Token + */ + protected $currentToken; + + /** + * Reference to InputZipper variable in Context. + * @type HTMLPurifier_Zipper + */ + protected $inputZipper; + + /** + * Array of elements and attributes this injector creates and therefore + * need to be allowed by the definition. Takes form of + * array('element' => array('attr', 'attr2'), 'element2') + * @type array + */ + public $needed = array(); + + /** + * Number of elements to rewind backwards (relative). + * @type bool|int + */ + protected $rewindOffset = false; + + /** + * Rewind to a spot to re-perform processing. This is useful if you + * deleted a node, and now need to see if this change affected any + * earlier nodes. Rewinding does not affect other injectors, and can + * result in infinite loops if not used carefully. + * @param bool|int $offset + * @warning HTML Purifier will prevent you from fast-forwarding with this + * function. + */ + public function rewindOffset($offset) + { + $this->rewindOffset = $offset; + } + + /** + * Retrieves rewind offset, and then unsets it. + * @return bool|int + */ + public function getRewindOffset() + { + $r = $this->rewindOffset; + $this->rewindOffset = false; + return $r; + } + + /** + * Prepares the injector by giving it the config and context objects: + * this allows references to important variables to be made within + * the injector. This function also checks if the HTML environment + * will work with the Injector (see checkNeeded()). + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool|string Boolean false if success, string of missing needed element/attribute if failure + */ + public function prepare($config, $context) + { + $this->htmlDefinition = $config->getHTMLDefinition(); + // Even though this might fail, some unit tests ignore this and + // still test checkNeeded, so be careful. Maybe get rid of that + // dependency. + $result = $this->checkNeeded($config); + if ($result !== false) { + return $result; + } + $this->currentNesting =& $context->get('CurrentNesting'); + $this->currentToken =& $context->get('CurrentToken'); + $this->inputZipper =& $context->get('InputZipper'); + return false; + } + + /** + * This function checks if the HTML environment + * will work with the Injector: if p tags are not allowed, the + * Auto-Paragraphing injector should not be enabled. + * @param HTMLPurifier_Config $config + * @return bool|string Boolean false if success, string of missing needed element/attribute if failure + */ + public function checkNeeded($config) + { + $def = $config->getHTMLDefinition(); + foreach ($this->needed as $element => $attributes) { + if (is_int($element)) { + $element = $attributes; + } + if (!isset($def->info[$element])) { + return $element; + } + if (!is_array($attributes)) { + continue; + } + foreach ($attributes as $name) { + if (!isset($def->info[$element]->attr[$name])) { + return "$element.$name"; + } + } + } + return false; + } + + /** + * Tests if the context node allows a certain element + * @param string $name Name of element to test for + * @return bool True if element is allowed, false if it is not + */ + public function allowsElement($name) + { + if (!empty($this->currentNesting)) { + $parent_token = array_pop($this->currentNesting); + $this->currentNesting[] = $parent_token; + $parent = $this->htmlDefinition->info[$parent_token->name]; + } else { + $parent = $this->htmlDefinition->info_parent_def; + } + if (!isset($parent->child->elements[$name]) || isset($parent->excludes[$name])) { + return false; + } + // check for exclusion + for ($i = count($this->currentNesting) - 2; $i >= 0; $i--) { + $node = $this->currentNesting[$i]; + $def = $this->htmlDefinition->info[$node->name]; + if (isset($def->excludes[$name])) { + return false; + } + } + return true; + } + + /** + * Iterator function, which starts with the next token and continues until + * you reach the end of the input tokens. + * @warning Please prevent previous references from interfering with this + * functions by setting $i = null beforehand! + * @param int $i Current integer index variable for inputTokens + * @param HTMLPurifier_Token $current Current token variable. + * Do NOT use $token, as that variable is also a reference + * @return bool + */ + protected function forward(&$i, &$current) + { + if ($i === null) { + $i = count($this->inputZipper->back) - 1; + } else { + $i--; + } + if ($i < 0) { + return false; + } + $current = $this->inputZipper->back[$i]; + return true; + } + + /** + * Similar to _forward, but accepts a third parameter $nesting (which + * should be initialized at 0) and stops when we hit the end tag + * for the node $this->inputIndex starts in. + * @param int $i Current integer index variable for inputTokens + * @param HTMLPurifier_Token $current Current token variable. + * Do NOT use $token, as that variable is also a reference + * @param int $nesting + * @return bool + */ + protected function forwardUntilEndToken(&$i, &$current, &$nesting) + { + $result = $this->forward($i, $current); + if (!$result) { + return false; + } + if ($nesting === null) { + $nesting = 0; + } + if ($current instanceof HTMLPurifier_Token_Start) { + $nesting++; + } elseif ($current instanceof HTMLPurifier_Token_End) { + if ($nesting <= 0) { + return false; + } + $nesting--; + } + return true; + } + + /** + * Iterator function, starts with the previous token and continues until + * you reach the beginning of input tokens. + * @warning Please prevent previous references from interfering with this + * functions by setting $i = null beforehand! + * @param int $i Current integer index variable for inputTokens + * @param HTMLPurifier_Token $current Current token variable. + * Do NOT use $token, as that variable is also a reference + * @return bool + */ + protected function backward(&$i, &$current) + { + if ($i === null) { + $i = count($this->inputZipper->front) - 1; + } else { + $i--; + } + if ($i < 0) { + return false; + } + $current = $this->inputZipper->front[$i]; + return true; + } + + /** + * Handler that is called when a text token is processed + */ + public function handleText(&$token) + { + } + + /** + * Handler that is called when a start or empty token is processed + */ + public function handleElement(&$token) + { + } + + /** + * Handler that is called when an end token is processed + */ + public function handleEnd(&$token) + { + $this->notifyEnd($token); + } + + /** + * Notifier that is called when an end token is processed + * @param HTMLPurifier_Token $token Current token variable. + * @note This differs from handlers in that the token is read-only + * @deprecated + */ + public function notifyEnd($token) + { + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/Injector/AutoParagraph.php b/extlib/HTMLPurifier/HTMLPurifier/Injector/AutoParagraph.php new file mode 100644 index 0000000000..4afdd128d5 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/Injector/AutoParagraph.php @@ -0,0 +1,356 @@ +armor['MakeWellFormed_TagClosedError'] = true; + return $par; + } + + /** + * @param HTMLPurifier_Token_Text $token + */ + public function handleText(&$token) + { + $text = $token->data; + // Does the current parent allow

tags? + if ($this->allowsElement('p')) { + if (empty($this->currentNesting) || strpos($text, "\n\n") !== false) { + // Note that we have differing behavior when dealing with text + // in the anonymous root node, or a node inside the document. + // If the text as a double-newline, the treatment is the same; + // if it doesn't, see the next if-block if you're in the document. + + $i = $nesting = null; + if (!$this->forwardUntilEndToken($i, $current, $nesting) && $token->is_whitespace) { + // State 1.1: ... ^ (whitespace, then document end) + // ---- + // This is a degenerate case + } else { + if (!$token->is_whitespace || $this->_isInline($current)) { + // State 1.2: PAR1 + // ---- + + // State 1.3: PAR1\n\nPAR2 + // ------------ + + // State 1.4:

PAR1\n\nPAR2 (see State 2) + // ------------ + $token = array($this->_pStart()); + $this->_splitText($text, $token); + } else { + // State 1.5: \n
+ // -- + } + } + } else { + // State 2:
PAR1... (similar to 1.4) + // ---- + + // We're in an element that allows paragraph tags, but we're not + // sure if we're going to need them. + if ($this->_pLookAhead()) { + // State 2.1:
PAR1PAR1\n\nPAR2 + // ---- + // Note: This will always be the first child, since any + // previous inline element would have triggered this very + // same routine, and found the double newline. One possible + // exception would be a comment. + $token = array($this->_pStart(), $token); + } else { + // State 2.2.1:
PAR1
+ // ---- + + // State 2.2.2:
PAR1PAR1
+ // ---- + } + } + // Is the current parent a

tag? + } elseif (!empty($this->currentNesting) && + $this->currentNesting[count($this->currentNesting) - 1]->name == 'p') { + // State 3.1: ...

PAR1 + // ---- + + // State 3.2: ...

PAR1\n\nPAR2 + // ------------ + $token = array(); + $this->_splitText($text, $token); + // Abort! + } else { + // State 4.1: ...PAR1 + // ---- + + // State 4.2: ...PAR1\n\nPAR2 + // ------------ + } + } + + /** + * @param HTMLPurifier_Token $token + */ + public function handleElement(&$token) + { + // We don't have to check if we're already in a

tag for block + // tokens, because the tag would have been autoclosed by MakeWellFormed. + if ($this->allowsElement('p')) { + if (!empty($this->currentNesting)) { + if ($this->_isInline($token)) { + // State 1:

... + // --- + // Check if this token is adjacent to the parent token + // (seek backwards until token isn't whitespace) + $i = null; + $this->backward($i, $prev); + + if (!$prev instanceof HTMLPurifier_Token_Start) { + // Token wasn't adjacent + if ($prev instanceof HTMLPurifier_Token_Text && + substr($prev->data, -2) === "\n\n" + ) { + // State 1.1.4:

PAR1

\n\n + // --- + // Quite frankly, this should be handled by splitText + $token = array($this->_pStart(), $token); + } else { + // State 1.1.1:

PAR1

+ // --- + // State 1.1.2:

+ // --- + // State 1.1.3:
PAR + // --- + } + } else { + // State 1.2.1:
+ // --- + // Lookahead to see if

is needed. + if ($this->_pLookAhead()) { + // State 1.3.1:

PAR1\n\nPAR2 + // --- + $token = array($this->_pStart(), $token); + } else { + // State 1.3.2:
PAR1
+ // --- + + // State 1.3.3:
PAR1
\n\n
+ // --- + } + } + } else { + // State 2.3: ...
+ // ----- + } + } else { + if ($this->_isInline($token)) { + // State 3.1: + // --- + // This is where the {p} tag is inserted, not reflected in + // inputTokens yet, however. + $token = array($this->_pStart(), $token); + } else { + // State 3.2:
+ // ----- + } + + $i = null; + if ($this->backward($i, $prev)) { + if (!$prev instanceof HTMLPurifier_Token_Text) { + // State 3.1.1: ...

{p} + // --- + // State 3.2.1: ...

+ // ----- + if (!is_array($token)) { + $token = array($token); + } + array_unshift($token, new HTMLPurifier_Token_Text("\n\n")); + } else { + // State 3.1.2: ...

\n\n{p} + // --- + // State 3.2.2: ...

\n\n
+ // ----- + // Note: PAR cannot occur because PAR would have been + // wrapped in

tags. + } + } + } + } else { + // State 2.2:

  • + // ---- + // State 2.4:

    + // --- + } + } + + /** + * Splits up a text in paragraph tokens and appends them + * to the result stream that will replace the original + * @param string $data String text data that will be processed + * into paragraphs + * @param HTMLPurifier_Token[] $result Reference to array of tokens that the + * tags will be appended onto + */ + private function _splitText($data, &$result) + { + $raw_paragraphs = explode("\n\n", $data); + $paragraphs = array(); // without empty paragraphs + $needs_start = false; + $needs_end = false; + + $c = count($raw_paragraphs); + if ($c == 1) { + // There were no double-newlines, abort quickly. In theory this + // should never happen. + $result[] = new HTMLPurifier_Token_Text($data); + return; + } + for ($i = 0; $i < $c; $i++) { + $par = $raw_paragraphs[$i]; + if (trim($par) !== '') { + $paragraphs[] = $par; + } else { + if ($i == 0) { + // Double newline at the front + if (empty($result)) { + // The empty result indicates that the AutoParagraph + // injector did not add any start paragraph tokens. + // This means that we have been in a paragraph for + // a while, and the newline means we should start a new one. + $result[] = new HTMLPurifier_Token_End('p'); + $result[] = new HTMLPurifier_Token_Text("\n\n"); + // However, the start token should only be added if + // there is more processing to be done (i.e. there are + // real paragraphs in here). If there are none, the + // next start paragraph tag will be handled by the + // next call to the injector + $needs_start = true; + } else { + // We just started a new paragraph! + // Reinstate a double-newline for presentation's sake, since + // it was in the source code. + array_unshift($result, new HTMLPurifier_Token_Text("\n\n")); + } + } elseif ($i + 1 == $c) { + // Double newline at the end + // There should be a trailing

    when we're finally done. + $needs_end = true; + } + } + } + + // Check if this was just a giant blob of whitespace. Move this earlier, + // perhaps? + if (empty($paragraphs)) { + return; + } + + // Add the start tag indicated by \n\n at the beginning of $data + if ($needs_start) { + $result[] = $this->_pStart(); + } + + // Append the paragraphs onto the result + foreach ($paragraphs as $par) { + $result[] = new HTMLPurifier_Token_Text($par); + $result[] = new HTMLPurifier_Token_End('p'); + $result[] = new HTMLPurifier_Token_Text("\n\n"); + $result[] = $this->_pStart(); + } + + // Remove trailing start token; Injector will handle this later if + // it was indeed needed. This prevents from needing to do a lookahead, + // at the cost of a lookbehind later. + array_pop($result); + + // If there is no need for an end tag, remove all of it and let + // MakeWellFormed close it later. + if (!$needs_end) { + array_pop($result); // removes \n\n + array_pop($result); // removes

    + } + } + + /** + * Returns true if passed token is inline (and, ergo, allowed in + * paragraph tags) + * @param HTMLPurifier_Token $token + * @return bool + */ + private function _isInline($token) + { + return isset($this->htmlDefinition->info['p']->child->elements[$token->name]); + } + + /** + * Looks ahead in the token list and determines whether or not we need + * to insert a

    tag. + * @return bool + */ + private function _pLookAhead() + { + if ($this->currentToken instanceof HTMLPurifier_Token_Start) { + $nesting = 1; + } else { + $nesting = 0; + } + $ok = false; + $i = null; + while ($this->forwardUntilEndToken($i, $current, $nesting)) { + $result = $this->_checkNeedsP($current); + if ($result !== null) { + $ok = $result; + break; + } + } + return $ok; + } + + /** + * Determines if a particular token requires an earlier inline token + * to get a paragraph. This should be used with _forwardUntilEndToken + * @param HTMLPurifier_Token $current + * @return bool + */ + private function _checkNeedsP($current) + { + if ($current instanceof HTMLPurifier_Token_Start) { + if (!$this->_isInline($current)) { + //

    PAR1
    + // ---- + // Terminate early, since we hit a block element + return false; + } + } elseif ($current instanceof HTMLPurifier_Token_Text) { + if (strpos($current->data, "\n\n") !== false) { + //
    PAR1PAR1\n\nPAR2 + // ---- + return true; + } else { + //
    PAR1PAR1... + // ---- + } + } + return null; + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/Injector/DisplayLinkURI.php b/extlib/HTMLPurifier/HTMLPurifier/Injector/DisplayLinkURI.php new file mode 100644 index 0000000000..c19b1bc271 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/Injector/DisplayLinkURI.php @@ -0,0 +1,40 @@ +start->attr['href'])) { + $url = $token->start->attr['href']; + unset($token->start->attr['href']); + $token = array($token, new HTMLPurifier_Token_Text(" ($url)")); + } else { + // nothing to display + } + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/Injector/Linkify.php b/extlib/HTMLPurifier/HTMLPurifier/Injector/Linkify.php new file mode 100644 index 0000000000..069708c250 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/Injector/Linkify.php @@ -0,0 +1,59 @@ + array('href')); + + /** + * @param HTMLPurifier_Token $token + */ + public function handleText(&$token) + { + if (!$this->allowsElement('a')) { + return; + } + + if (strpos($token->data, '://') === false) { + // our really quick heuristic failed, abort + // this may not work so well if we want to match things like + // "google.com", but then again, most people don't + return; + } + + // there is/are URL(s). Let's split the string: + // Note: this regex is extremely permissive + $bits = preg_split('#((?:https?|ftp)://[^\s\'",<>()]+)#Su', $token->data, -1, PREG_SPLIT_DELIM_CAPTURE); + + + $token = array(); + + // $i = index + // $c = count + // $l = is link + for ($i = 0, $c = count($bits), $l = false; $i < $c; $i++, $l = !$l) { + if (!$l) { + if ($bits[$i] === '') { + continue; + } + $token[] = new HTMLPurifier_Token_Text($bits[$i]); + } else { + $token[] = new HTMLPurifier_Token_Start('a', array('href' => $bits[$i])); + $token[] = new HTMLPurifier_Token_Text($bits[$i]); + $token[] = new HTMLPurifier_Token_End('a'); + } + } + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/Injector/PurifierLinkify.php b/extlib/HTMLPurifier/HTMLPurifier/Injector/PurifierLinkify.php new file mode 100644 index 0000000000..cb9046f334 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/Injector/PurifierLinkify.php @@ -0,0 +1,71 @@ + array('href')); + + /** + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return string + */ + public function prepare($config, $context) + { + $this->docURL = $config->get('AutoFormat.PurifierLinkify.DocURL'); + return parent::prepare($config, $context); + } + + /** + * @param HTMLPurifier_Token $token + */ + public function handleText(&$token) + { + if (!$this->allowsElement('a')) { + return; + } + if (strpos($token->data, '%') === false) { + return; + } + + $bits = preg_split('#%([a-z0-9]+\.[a-z0-9]+)#Si', $token->data, -1, PREG_SPLIT_DELIM_CAPTURE); + $token = array(); + + // $i = index + // $c = count + // $l = is link + for ($i = 0, $c = count($bits), $l = false; $i < $c; $i++, $l = !$l) { + if (!$l) { + if ($bits[$i] === '') { + continue; + } + $token[] = new HTMLPurifier_Token_Text($bits[$i]); + } else { + $token[] = new HTMLPurifier_Token_Start( + 'a', + array('href' => str_replace('%s', $bits[$i], $this->docURL)) + ); + $token[] = new HTMLPurifier_Token_Text('%' . $bits[$i]); + $token[] = new HTMLPurifier_Token_End('a'); + } + } + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/Injector/RemoveEmpty.php b/extlib/HTMLPurifier/HTMLPurifier/Injector/RemoveEmpty.php new file mode 100644 index 0000000000..01353ff1d5 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/Injector/RemoveEmpty.php @@ -0,0 +1,106 @@ +config = $config; + $this->context = $context; + $this->removeNbsp = $config->get('AutoFormat.RemoveEmpty.RemoveNbsp'); + $this->removeNbspExceptions = $config->get('AutoFormat.RemoveEmpty.RemoveNbsp.Exceptions'); + $this->exclude = $config->get('AutoFormat.RemoveEmpty.Predicate'); + $this->attrValidator = new HTMLPurifier_AttrValidator(); + } + + /** + * @param HTMLPurifier_Token $token + */ + public function handleElement(&$token) + { + if (!$token instanceof HTMLPurifier_Token_Start) { + return; + } + $next = false; + $deleted = 1; // the current tag + for ($i = count($this->inputZipper->back) - 1; $i >= 0; $i--, $deleted++) { + $next = $this->inputZipper->back[$i]; + if ($next instanceof HTMLPurifier_Token_Text) { + if ($next->is_whitespace) { + continue; + } + if ($this->removeNbsp && !isset($this->removeNbspExceptions[$token->name])) { + $plain = str_replace("\xC2\xA0", "", $next->data); + $isWsOrNbsp = $plain === '' || ctype_space($plain); + if ($isWsOrNbsp) { + continue; + } + } + } + break; + } + if (!$next || ($next instanceof HTMLPurifier_Token_End && $next->name == $token->name)) { + $this->attrValidator->validateToken($token, $this->config, $this->context); + $token->armor['ValidateAttributes'] = true; + if (isset($this->exclude[$token->name])) { + $r = true; + foreach ($this->exclude[$token->name] as $elem) { + if (!isset($token->attr[$elem])) $r = false; + } + if ($r) return; + } + if (isset($token->attr['id']) || isset($token->attr['name'])) { + return; + } + $token = $deleted + 1; + for ($b = 0, $c = count($this->inputZipper->front); $b < $c; $b++) { + $prev = $this->inputZipper->front[$b]; + if ($prev instanceof HTMLPurifier_Token_Text && $prev->is_whitespace) { + continue; + } + break; + } + // This is safe because we removed the token that triggered this. + $this->rewindOffset($b+$deleted); + return; + } + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/Injector/RemoveSpansWithoutAttributes.php b/extlib/HTMLPurifier/HTMLPurifier/Injector/RemoveSpansWithoutAttributes.php new file mode 100644 index 0000000000..9ee7aa84d7 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/Injector/RemoveSpansWithoutAttributes.php @@ -0,0 +1,84 @@ +attrValidator = new HTMLPurifier_AttrValidator(); + $this->config = $config; + $this->context = $context; + return parent::prepare($config, $context); + } + + /** + * @param HTMLPurifier_Token $token + */ + public function handleElement(&$token) + { + if ($token->name !== 'span' || !$token instanceof HTMLPurifier_Token_Start) { + return; + } + + // We need to validate the attributes now since this doesn't normally + // happen until after MakeWellFormed. If all the attributes are removed + // the span needs to be removed too. + $this->attrValidator->validateToken($token, $this->config, $this->context); + $token->armor['ValidateAttributes'] = true; + + if (!empty($token->attr)) { + return; + } + + $nesting = 0; + while ($this->forwardUntilEndToken($i, $current, $nesting)) { + } + + if ($current instanceof HTMLPurifier_Token_End && $current->name === 'span') { + // Mark closing span tag for deletion + $current->markForDeletion = true; + // Delete open span tag + $token = false; + } + } + + /** + * @param HTMLPurifier_Token $token + */ + public function handleEnd(&$token) + { + if ($token->markForDeletion) { + $token = false; + } + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/Injector/SafeObject.php b/extlib/HTMLPurifier/HTMLPurifier/Injector/SafeObject.php new file mode 100644 index 0000000000..3d17e07af2 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/Injector/SafeObject.php @@ -0,0 +1,121 @@ + 'never', + 'allowNetworking' => 'internal', + ); + + /** + * @type array + */ + protected $allowedParam = array( + 'wmode' => true, + 'movie' => true, + 'flashvars' => true, + 'src' => true, + 'allowFullScreen' => true, // if omitted, assume to be 'false' + ); + + /** + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return void + */ + public function prepare($config, $context) + { + parent::prepare($config, $context); + } + + /** + * @param HTMLPurifier_Token $token + */ + public function handleElement(&$token) + { + if ($token->name == 'object') { + $this->objectStack[] = $token; + $this->paramStack[] = array(); + $new = array($token); + foreach ($this->addParam as $name => $value) { + $new[] = new HTMLPurifier_Token_Empty('param', array('name' => $name, 'value' => $value)); + } + $token = $new; + } elseif ($token->name == 'param') { + $nest = count($this->currentNesting) - 1; + if ($nest >= 0 && $this->currentNesting[$nest]->name === 'object') { + $i = count($this->objectStack) - 1; + if (!isset($token->attr['name'])) { + $token = false; + return; + } + $n = $token->attr['name']; + // We need this fix because YouTube doesn't supply a data + // attribute, which we need if a type is specified. This is + // *very* Flash specific. + if (!isset($this->objectStack[$i]->attr['data']) && + ($token->attr['name'] == 'movie' || $token->attr['name'] == 'src') + ) { + $this->objectStack[$i]->attr['data'] = $token->attr['value']; + } + // Check if the parameter is the correct value but has not + // already been added + if (!isset($this->paramStack[$i][$n]) && + isset($this->addParam[$n]) && + $token->attr['name'] === $this->addParam[$n]) { + // keep token, and add to param stack + $this->paramStack[$i][$n] = true; + } elseif (isset($this->allowedParam[$n])) { + // keep token, don't do anything to it + // (could possibly check for duplicates here) + } else { + $token = false; + } + } else { + // not directly inside an object, DENY! + $token = false; + } + } + } + + public function handleEnd(&$token) + { + // This is the WRONG way of handling the object and param stacks; + // we should be inserting them directly on the relevant object tokens + // so that the global stack handling handles it. + if ($token->name == 'object') { + array_pop($this->objectStack); + array_pop($this->paramStack); + } + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/Language.php b/extlib/HTMLPurifier/HTMLPurifier/Language.php new file mode 100644 index 0000000000..65277dd43c --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/Language.php @@ -0,0 +1,204 @@ +config = $config; + $this->context = $context; + } + + /** + * Loads language object with necessary info from factory cache + * @note This is a lazy loader + */ + public function load() + { + if ($this->_loaded) { + return; + } + $factory = HTMLPurifier_LanguageFactory::instance(); + $factory->loadLanguage($this->code); + foreach ($factory->keys as $key) { + $this->$key = $factory->cache[$this->code][$key]; + } + $this->_loaded = true; + } + + /** + * Retrieves a localised message. + * @param string $key string identifier of message + * @return string localised message + */ + public function getMessage($key) + { + if (!$this->_loaded) { + $this->load(); + } + if (!isset($this->messages[$key])) { + return "[$key]"; + } + return $this->messages[$key]; + } + + /** + * Retrieves a localised error name. + * @param int $int error number, corresponding to PHP's error reporting + * @return string localised message + */ + public function getErrorName($int) + { + if (!$this->_loaded) { + $this->load(); + } + if (!isset($this->errorNames[$int])) { + return "[Error: $int]"; + } + return $this->errorNames[$int]; + } + + /** + * Converts an array list into a string readable representation + * @param array $array + * @return string + */ + public function listify($array) + { + $sep = $this->getMessage('Item separator'); + $sep_last = $this->getMessage('Item separator last'); + $ret = ''; + for ($i = 0, $c = count($array); $i < $c; $i++) { + if ($i == 0) { + } elseif ($i + 1 < $c) { + $ret .= $sep; + } else { + $ret .= $sep_last; + } + $ret .= $array[$i]; + } + return $ret; + } + + /** + * Formats a localised message with passed parameters + * @param string $key string identifier of message + * @param array $args Parameters to substitute in + * @return string localised message + * @todo Implement conditionals? Right now, some messages make + * reference to line numbers, but those aren't always available + */ + public function formatMessage($key, $args = array()) + { + if (!$this->_loaded) { + $this->load(); + } + if (!isset($this->messages[$key])) { + return "[$key]"; + } + $raw = $this->messages[$key]; + $subst = array(); + $generator = false; + foreach ($args as $i => $value) { + if (is_object($value)) { + if ($value instanceof HTMLPurifier_Token) { + // factor this out some time + if (!$generator) { + $generator = $this->context->get('Generator'); + } + if (isset($value->name)) { + $subst['$'.$i.'.Name'] = $value->name; + } + if (isset($value->data)) { + $subst['$'.$i.'.Data'] = $value->data; + } + $subst['$'.$i.'.Compact'] = + $subst['$'.$i.'.Serialized'] = $generator->generateFromToken($value); + // a more complex algorithm for compact representation + // could be introduced for all types of tokens. This + // may need to be factored out into a dedicated class + if (!empty($value->attr)) { + $stripped_token = clone $value; + $stripped_token->attr = array(); + $subst['$'.$i.'.Compact'] = $generator->generateFromToken($stripped_token); + } + $subst['$'.$i.'.Line'] = $value->line ? $value->line : 'unknown'; + } + continue; + } elseif (is_array($value)) { + $keys = array_keys($value); + if (array_keys($keys) === $keys) { + // list + $subst['$'.$i] = $this->listify($value); + } else { + // associative array + // no $i implementation yet, sorry + $subst['$'.$i.'.Keys'] = $this->listify($keys); + $subst['$'.$i.'.Values'] = $this->listify(array_values($value)); + } + continue; + } + $subst['$' . $i] = $value; + } + return strtr($raw, $subst); + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/Language/classes/en-x-test.php b/extlib/HTMLPurifier/HTMLPurifier/Language/classes/en-x-test.php new file mode 100644 index 0000000000..8828f5cded --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/Language/classes/en-x-test.php @@ -0,0 +1,9 @@ + 'HTML Purifier X' +); + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/Language/messages/en-x-testmini.php b/extlib/HTMLPurifier/HTMLPurifier/Language/messages/en-x-testmini.php new file mode 100644 index 0000000000..806c83fbf7 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/Language/messages/en-x-testmini.php @@ -0,0 +1,12 @@ + 'HTML Purifier XNone' +); + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/Language/messages/en.php b/extlib/HTMLPurifier/HTMLPurifier/Language/messages/en.php new file mode 100644 index 0000000000..c7f197e1e1 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/Language/messages/en.php @@ -0,0 +1,55 @@ + 'HTML Purifier', +// for unit testing purposes + 'LanguageFactoryTest: Pizza' => 'Pizza', + 'LanguageTest: List' => '$1', + 'LanguageTest: Hash' => '$1.Keys; $1.Values', + 'Item separator' => ', ', + 'Item separator last' => ' and ', // non-Harvard style + + 'ErrorCollector: No errors' => 'No errors detected. However, because error reporting is still incomplete, there may have been errors that the error collector was not notified of; please inspect the output HTML carefully.', + 'ErrorCollector: At line' => ' at line $line', + 'ErrorCollector: Incidental errors' => 'Incidental errors', + 'Lexer: Unclosed comment' => 'Unclosed comment', + 'Lexer: Unescaped lt' => 'Unescaped less-than sign (<) should be <', + 'Lexer: Missing gt' => 'Missing greater-than sign (>), previous less-than sign (<) should be escaped', + 'Lexer: Missing attribute key' => 'Attribute declaration has no key', + 'Lexer: Missing end quote' => 'Attribute declaration has no end quote', + 'Lexer: Extracted body' => 'Removed document metadata tags', + 'Strategy_RemoveForeignElements: Tag transform' => '<$1> element transformed into $CurrentToken.Serialized', + 'Strategy_RemoveForeignElements: Missing required attribute' => '$CurrentToken.Compact element missing required attribute $1', + 'Strategy_RemoveForeignElements: Foreign element to text' => 'Unrecognized $CurrentToken.Serialized tag converted to text', + 'Strategy_RemoveForeignElements: Foreign element removed' => 'Unrecognized $CurrentToken.Serialized tag removed', + 'Strategy_RemoveForeignElements: Comment removed' => 'Comment containing "$CurrentToken.Data" removed', + 'Strategy_RemoveForeignElements: Foreign meta element removed' => 'Unrecognized $CurrentToken.Serialized meta tag and all descendants removed', + 'Strategy_RemoveForeignElements: Token removed to end' => 'Tags and text starting from $1 element where removed to end', + 'Strategy_RemoveForeignElements: Trailing hyphen in comment removed' => 'Trailing hyphen(s) in comment removed', + 'Strategy_RemoveForeignElements: Hyphens in comment collapsed' => 'Double hyphens in comments are not allowed, and were collapsed into single hyphens', + 'Strategy_MakeWellFormed: Unnecessary end tag removed' => 'Unnecessary $CurrentToken.Serialized tag removed', + 'Strategy_MakeWellFormed: Unnecessary end tag to text' => 'Unnecessary $CurrentToken.Serialized tag converted to text', + 'Strategy_MakeWellFormed: Tag auto closed' => '$1.Compact started on line $1.Line auto-closed by $CurrentToken.Compact', + 'Strategy_MakeWellFormed: Tag carryover' => '$1.Compact started on line $1.Line auto-continued into $CurrentToken.Compact', + 'Strategy_MakeWellFormed: Stray end tag removed' => 'Stray $CurrentToken.Serialized tag removed', + 'Strategy_MakeWellFormed: Stray end tag to text' => 'Stray $CurrentToken.Serialized tag converted to text', + 'Strategy_MakeWellFormed: Tag closed by element end' => '$1.Compact tag started on line $1.Line closed by end of $CurrentToken.Serialized', + 'Strategy_MakeWellFormed: Tag closed by document end' => '$1.Compact tag started on line $1.Line closed by end of document', + 'Strategy_FixNesting: Node removed' => '$CurrentToken.Compact node removed', + 'Strategy_FixNesting: Node excluded' => '$CurrentToken.Compact node removed due to descendant exclusion by ancestor element', + 'Strategy_FixNesting: Node reorganized' => 'Contents of $CurrentToken.Compact node reorganized to enforce its content model', + 'Strategy_FixNesting: Node contents removed' => 'Contents of $CurrentToken.Compact node removed', + 'AttrValidator: Attributes transformed' => 'Attributes on $CurrentToken.Compact transformed from $1.Keys to $2.Keys', + 'AttrValidator: Attribute removed' => '$CurrentAttr.Name attribute on $CurrentToken.Compact removed', +); + +$errorNames = array( + E_ERROR => 'Error', + E_WARNING => 'Warning', + E_NOTICE => 'Notice' +); + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/LanguageFactory.php b/extlib/HTMLPurifier/HTMLPurifier/LanguageFactory.php new file mode 100644 index 0000000000..4e35272d87 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/LanguageFactory.php @@ -0,0 +1,209 @@ +cache[$language_code][$key] = $value + * @type array + */ + public $cache; + + /** + * Valid keys in the HTMLPurifier_Language object. Designates which + * variables to slurp out of a message file. + * @type array + */ + public $keys = array('fallback', 'messages', 'errorNames'); + + /** + * Instance to validate language codes. + * @type HTMLPurifier_AttrDef_Lang + * + */ + protected $validator; + + /** + * Cached copy of dirname(__FILE__), directory of current file without + * trailing slash. + * @type string + */ + protected $dir; + + /** + * Keys whose contents are a hash map and can be merged. + * @type array + */ + protected $mergeable_keys_map = array('messages' => true, 'errorNames' => true); + + /** + * Keys whose contents are a list and can be merged. + * @value array lookup + */ + protected $mergeable_keys_list = array(); + + /** + * Retrieve sole instance of the factory. + * @param HTMLPurifier_LanguageFactory $prototype Optional prototype to overload sole instance with, + * or bool true to reset to default factory. + * @return HTMLPurifier_LanguageFactory + */ + public static function instance($prototype = null) + { + static $instance = null; + if ($prototype !== null) { + $instance = $prototype; + } elseif ($instance === null || $prototype == true) { + $instance = new HTMLPurifier_LanguageFactory(); + $instance->setup(); + } + return $instance; + } + + /** + * Sets up the singleton, much like a constructor + * @note Prevents people from getting this outside of the singleton + */ + public function setup() + { + $this->validator = new HTMLPurifier_AttrDef_Lang(); + $this->dir = HTMLPURIFIER_PREFIX . '/HTMLPurifier'; + } + + /** + * Creates a language object, handles class fallbacks + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @param bool|string $code Code to override configuration with. Private parameter. + * @return HTMLPurifier_Language + */ + public function create($config, $context, $code = false) + { + // validate language code + if ($code === false) { + $code = $this->validator->validate( + $config->get('Core.Language'), + $config, + $context + ); + } else { + $code = $this->validator->validate($code, $config, $context); + } + if ($code === false) { + $code = 'en'; // malformed code becomes English + } + + $pcode = str_replace('-', '_', $code); // make valid PHP classname + static $depth = 0; // recursion protection + + if ($code == 'en') { + $lang = new HTMLPurifier_Language($config, $context); + } else { + $class = 'HTMLPurifier_Language_' . $pcode; + $file = $this->dir . '/Language/classes/' . $code . '.php'; + if (file_exists($file) || class_exists($class, false)) { + $lang = new $class($config, $context); + } else { + // Go fallback + $raw_fallback = $this->getFallbackFor($code); + $fallback = $raw_fallback ? $raw_fallback : 'en'; + $depth++; + $lang = $this->create($config, $context, $fallback); + if (!$raw_fallback) { + $lang->error = true; + } + $depth--; + } + } + $lang->code = $code; + return $lang; + } + + /** + * Returns the fallback language for language + * @note Loads the original language into cache + * @param string $code language code + * @return string|bool + */ + public function getFallbackFor($code) + { + $this->loadLanguage($code); + return $this->cache[$code]['fallback']; + } + + /** + * Loads language into the cache, handles message file and fallbacks + * @param string $code language code + */ + public function loadLanguage($code) + { + static $languages_seen = array(); // recursion guard + + // abort if we've already loaded it + if (isset($this->cache[$code])) { + return; + } + + // generate filename + $filename = $this->dir . '/Language/messages/' . $code . '.php'; + + // default fallback : may be overwritten by the ensuing include + $fallback = ($code != 'en') ? 'en' : false; + + // load primary localisation + if (!file_exists($filename)) { + // skip the include: will rely solely on fallback + $filename = $this->dir . '/Language/messages/en.php'; + $cache = array(); + } else { + include $filename; + $cache = compact($this->keys); + } + + // load fallback localisation + if (!empty($fallback)) { + + // infinite recursion guard + if (isset($languages_seen[$code])) { + trigger_error( + 'Circular fallback reference in language ' . + $code, + E_USER_ERROR + ); + $fallback = 'en'; + } + $language_seen[$code] = true; + + // load the fallback recursively + $this->loadLanguage($fallback); + $fallback_cache = $this->cache[$fallback]; + + // merge fallback with current language + foreach ($this->keys as $key) { + if (isset($cache[$key]) && isset($fallback_cache[$key])) { + if (isset($this->mergeable_keys_map[$key])) { + $cache[$key] = $cache[$key] + $fallback_cache[$key]; + } elseif (isset($this->mergeable_keys_list[$key])) { + $cache[$key] = array_merge($fallback_cache[$key], $cache[$key]); + } + } else { + $cache[$key] = $fallback_cache[$key]; + } + } + } + + // save to cache for later retrieval + $this->cache[$code] = $cache; + return; + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/Length.php b/extlib/HTMLPurifier/HTMLPurifier/Length.php new file mode 100644 index 0000000000..bbfbe6624d --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/Length.php @@ -0,0 +1,160 @@ + true, 'ex' => true, 'px' => true, 'in' => true, + 'cm' => true, 'mm' => true, 'pt' => true, 'pc' => true + ); + + /** + * @param string $n Magnitude + * @param bool|string $u Unit + */ + public function __construct($n = '0', $u = false) + { + $this->n = (string) $n; + $this->unit = $u !== false ? (string) $u : false; + } + + /** + * @param string $s Unit string, like '2em' or '3.4in' + * @return HTMLPurifier_Length + * @warning Does not perform validation. + */ + public static function make($s) + { + if ($s instanceof HTMLPurifier_Length) { + return $s; + } + $n_length = strspn($s, '1234567890.+-'); + $n = substr($s, 0, $n_length); + $unit = substr($s, $n_length); + if ($unit === '') { + $unit = false; + } + return new HTMLPurifier_Length($n, $unit); + } + + /** + * Validates the number and unit. + * @return bool + */ + protected function validate() + { + // Special case: + if ($this->n === '+0' || $this->n === '-0') { + $this->n = '0'; + } + if ($this->n === '0' && $this->unit === false) { + return true; + } + if (!ctype_lower($this->unit)) { + $this->unit = strtolower($this->unit); + } + if (!isset(HTMLPurifier_Length::$allowedUnits[$this->unit])) { + return false; + } + // Hack: + $def = new HTMLPurifier_AttrDef_CSS_Number(); + $result = $def->validate($this->n, false, false); + if ($result === false) { + return false; + } + $this->n = $result; + return true; + } + + /** + * Returns string representation of number. + * @return string + */ + public function toString() + { + if (!$this->isValid()) { + return false; + } + return $this->n . $this->unit; + } + + /** + * Retrieves string numeric magnitude. + * @return string + */ + public function getN() + { + return $this->n; + } + + /** + * Retrieves string unit. + * @return string + */ + public function getUnit() + { + return $this->unit; + } + + /** + * Returns true if this length unit is valid. + * @return bool + */ + public function isValid() + { + if ($this->isValid === null) { + $this->isValid = $this->validate(); + } + return $this->isValid; + } + + /** + * Compares two lengths, and returns 1 if greater, -1 if less and 0 if equal. + * @param HTMLPurifier_Length $l + * @return int + * @warning If both values are too large or small, this calculation will + * not work properly + */ + public function compareTo($l) + { + if ($l === false) { + return false; + } + if ($l->unit !== $this->unit) { + $converter = new HTMLPurifier_UnitConverter(); + $l = $converter->convert($l, $this->unit); + if ($l === false) { + return false; + } + } + return $this->n - $l->n; + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/Lexer.php b/extlib/HTMLPurifier/HTMLPurifier/Lexer.php new file mode 100644 index 0000000000..43732621dc --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/Lexer.php @@ -0,0 +1,357 @@ +get('Core.LexerImpl'); + } + + $needs_tracking = + $config->get('Core.MaintainLineNumbers') || + $config->get('Core.CollectErrors'); + + $inst = null; + if (is_object($lexer)) { + $inst = $lexer; + } else { + if (is_null($lexer)) { + do { + // auto-detection algorithm + if ($needs_tracking) { + $lexer = 'DirectLex'; + break; + } + + if (class_exists('DOMDocument') && + method_exists('DOMDocument', 'loadHTML') && + !extension_loaded('domxml') + ) { + // check for DOM support, because while it's part of the + // core, it can be disabled compile time. Also, the PECL + // domxml extension overrides the default DOM, and is evil + // and nasty and we shan't bother to support it + $lexer = 'DOMLex'; + } else { + $lexer = 'DirectLex'; + } + } while (0); + } // do..while so we can break + + // instantiate recognized string names + switch ($lexer) { + case 'DOMLex': + $inst = new HTMLPurifier_Lexer_DOMLex(); + break; + case 'DirectLex': + $inst = new HTMLPurifier_Lexer_DirectLex(); + break; + case 'PH5P': + $inst = new HTMLPurifier_Lexer_PH5P(); + break; + default: + throw new HTMLPurifier_Exception( + "Cannot instantiate unrecognized Lexer type " . + htmlspecialchars($lexer) + ); + } + } + + if (!$inst) { + throw new HTMLPurifier_Exception('No lexer was instantiated'); + } + + // once PHP DOM implements native line numbers, or we + // hack out something using XSLT, remove this stipulation + if ($needs_tracking && !$inst->tracksLineNumbers) { + throw new HTMLPurifier_Exception( + 'Cannot use lexer that does not support line numbers with ' . + 'Core.MaintainLineNumbers or Core.CollectErrors (use DirectLex instead)' + ); + } + + return $inst; + + } + + // -- CONVENIENCE MEMBERS --------------------------------------------- + + public function __construct() + { + $this->_entity_parser = new HTMLPurifier_EntityParser(); + } + + /** + * Most common entity to raw value conversion table for special entities. + * @type array + */ + protected $_special_entity2str = + array( + '"' => '"', + '&' => '&', + '<' => '<', + '>' => '>', + ''' => "'", + ''' => "'", + ''' => "'" + ); + + /** + * Parses special entities into the proper characters. + * + * This string will translate escaped versions of the special characters + * into the correct ones. + * + * @warning + * You should be able to treat the output of this function as + * completely parsed, but that's only because all other entities should + * have been handled previously in substituteNonSpecialEntities() + * + * @param string $string String character data to be parsed. + * @return string Parsed character data. + */ + public function parseData($string) + { + // following functions require at least one character + if ($string === '') { + return ''; + } + + // subtracts amps that cannot possibly be escaped + $num_amp = substr_count($string, '&') - substr_count($string, '& ') - + ($string[strlen($string) - 1] === '&' ? 1 : 0); + + if (!$num_amp) { + return $string; + } // abort if no entities + $num_esc_amp = substr_count($string, '&'); + $string = strtr($string, $this->_special_entity2str); + + // code duplication for sake of optimization, see above + $num_amp_2 = substr_count($string, '&') - substr_count($string, '& ') - + ($string[strlen($string) - 1] === '&' ? 1 : 0); + + if ($num_amp_2 <= $num_esc_amp) { + return $string; + } + + // hmm... now we have some uncommon entities. Use the callback. + $string = $this->_entity_parser->substituteSpecialEntities($string); + return $string; + } + + /** + * Lexes an HTML string into tokens. + * @param $string String HTML. + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return HTMLPurifier_Token[] array representation of HTML. + */ + public function tokenizeHTML($string, $config, $context) + { + trigger_error('Call to abstract class', E_USER_ERROR); + } + + /** + * Translates CDATA sections into regular sections (through escaping). + * @param string $string HTML string to process. + * @return string HTML with CDATA sections escaped. + */ + protected static function escapeCDATA($string) + { + return preg_replace_callback( + '//s', + array('HTMLPurifier_Lexer', 'CDATACallback'), + $string + ); + } + + /** + * Special CDATA case that is especially convoluted for )#si', + array($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 + * @param string $haystack + * @param string $needle + * @param int $offset + * @param int $length + * @return int + */ + protected function substrCount($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 $string Inside of tag excluding name. + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return array Assoc array of attributes. + */ + public function parseAttributeString($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 .= ' '; + + $old_cursor = -1; + while ($cursor < $size) { + if ($old_cursor >= $cursor) { + throw new Exception("Infinite loop detected"); + } + $old_cursor = $cursor; + + $cursor += ($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'); + } + $cursor += 1 + strcspn($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 $array; + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/Lexer/PH5P.php b/extlib/HTMLPurifier/HTMLPurifier/Lexer/PH5P.php new file mode 100644 index 0000000000..ff4fa218fb --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/Lexer/PH5P.php @@ -0,0 +1,4787 @@ +normalize($html, $config, $context); + $new_html = $this->wrapHTML($new_html, $config, $context); + try { + $parser = new HTML5($new_html); + $doc = $parser->save(); + } catch (DOMException $e) { + // Uh oh, it failed. Punt to DirectLex. + $lexer = new HTMLPurifier_Lexer_DirectLex(); + $context->register('PH5PError', $e); // save the error, so we can detect it + return $lexer->tokenizeHTML($html, $config, $context); // use original HTML + } + $tokens = array(); + $this->tokenizeDOM( + $doc->getElementsByTagName('html')->item(0)-> // + getElementsByTagName('body')->item(0) // + , + $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' => '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' => '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/extlib/HTMLPurifier/HTMLPurifier/Node.php b/extlib/HTMLPurifier/HTMLPurifier/Node.php new file mode 100644 index 0000000000..3995fec9fe --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/Node.php @@ -0,0 +1,49 @@ +data = $data; + $this->line = $line; + $this->col = $col; + } + + public function toTokenPair() { + return array(new HTMLPurifier_Token_Comment($this->data, $this->line, $this->col), null); + } +} diff --git a/extlib/HTMLPurifier/HTMLPurifier/Node/Element.php b/extlib/HTMLPurifier/HTMLPurifier/Node/Element.php new file mode 100644 index 0000000000..6cbf56dada --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/Node/Element.php @@ -0,0 +1,59 @@ + form or the form, i.e. + * is it a pair of start/end tokens or an empty token. + * @bool + */ + public $empty = false; + + public $endCol = null, $endLine = null, $endArmor = array(); + + public function __construct($name, $attr = array(), $line = null, $col = null, $armor = array()) { + $this->name = $name; + $this->attr = $attr; + $this->line = $line; + $this->col = $col; + $this->armor = $armor; + } + + public function toTokenPair() { + // XXX inefficiency here, normalization is not necessary + if ($this->empty) { + return array(new HTMLPurifier_Token_Empty($this->name, $this->attr, $this->line, $this->col, $this->armor), null); + } else { + $start = new HTMLPurifier_Token_Start($this->name, $this->attr, $this->line, $this->col, $this->armor); + $end = new HTMLPurifier_Token_End($this->name, array(), $this->endLine, $this->endCol, $this->endArmor); + //$end->start = $start; + return array($start, $end); + } + } +} + diff --git a/extlib/HTMLPurifier/HTMLPurifier/Node/Text.php b/extlib/HTMLPurifier/HTMLPurifier/Node/Text.php new file mode 100644 index 0000000000..aec9166473 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/Node/Text.php @@ -0,0 +1,54 @@ +data = $data; + $this->is_whitespace = $is_whitespace; + $this->line = $line; + $this->col = $col; + } + + public function toTokenPair() { + return array(new HTMLPurifier_Token_Text($this->data, $this->line, $this->col), null); + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/PercentEncoder.php b/extlib/HTMLPurifier/HTMLPurifier/PercentEncoder.php new file mode 100644 index 0000000000..18c8bbb00a --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/PercentEncoder.php @@ -0,0 +1,111 @@ +preserve[$i] = true; + } + for ($i = 65; $i <= 90; $i++) { // upper-case + $this->preserve[$i] = true; + } + for ($i = 97; $i <= 122; $i++) { // lower-case + $this->preserve[$i] = true; + } + $this->preserve[45] = true; // Dash - + $this->preserve[46] = true; // Period . + $this->preserve[95] = true; // Underscore _ + $this->preserve[126]= true; // Tilde ~ + + // extra letters not to escape + if ($preserve !== false) { + for ($i = 0, $c = strlen($preserve); $i < $c; $i++) { + $this->preserve[ord($preserve[$i])] = true; + } + } + } + + /** + * Our replacement for urlencode, it encodes all non-reserved characters, + * as well as any extra characters that were instructed to be preserved. + * @note + * Assumes that the string has already been normalized, making any + * and all percent escape sequences valid. Percents will not be + * re-escaped, regardless of their status in $preserve + * @param string $string String to be encoded + * @return string Encoded string. + */ + public function encode($string) + { + $ret = ''; + for ($i = 0, $c = strlen($string); $i < $c; $i++) { + if ($string[$i] !== '%' && !isset($this->preserve[$int = ord($string[$i])])) { + $ret .= '%' . sprintf('%02X', $int); + } else { + $ret .= $string[$i]; + } + } + return $ret; + } + + /** + * Fix up percent-encoding by decoding unreserved characters and normalizing. + * @warning This function is affected by $preserve, even though the + * usual desired behavior is for this not to preserve those + * characters. Be careful when reusing instances of PercentEncoder! + * @param string $string String to normalize + * @return string + */ + public function normalize($string) + { + if ($string == '') { + return ''; + } + $parts = explode('%', $string); + $ret = array_shift($parts); + foreach ($parts as $part) { + $length = strlen($part); + if ($length < 2) { + $ret .= '%25' . $part; + continue; + } + $encoding = substr($part, 0, 2); + $text = substr($part, 2); + if (!ctype_xdigit($encoding)) { + $ret .= '%25' . $part; + continue; + } + $int = hexdec($encoding); + if (isset($this->preserve[$int])) { + $ret .= chr($int) . $text; + continue; + } + $encoding = strtoupper($encoding); + $ret .= '%' . $encoding . $text; + } + return $ret; + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/Printer.php b/extlib/HTMLPurifier/HTMLPurifier/Printer.php new file mode 100644 index 0000000000..549e4cea1e --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/Printer.php @@ -0,0 +1,218 @@ +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 string $tag Tag name + * @param array $attr Attribute array + * @return string + */ + protected function start($tag, $attr = array()) + { + return $this->generator->generateFromToken( + new HTMLPurifier_Token_Start($tag, $attr ? $attr : array()) + ); + } + + /** + * Returns an end tag + * @param string $tag Tag name + * @return string + */ + protected function end($tag) + { + return $this->generator->generateFromToken( + new HTMLPurifier_Token_End($tag) + ); + } + + /** + * Prints a complete element with content inside + * @param string $tag Tag name + * @param string $contents Element contents + * @param array $attr Tag attributes + * @param bool $escape whether or not to escape contents + * @return string + */ + protected function element($tag, $contents, $attr = array(), $escape = true) + { + return $this->start($tag, $attr) . + ($escape ? $this->escape($contents) : $contents) . + $this->end($tag); + } + + /** + * @param string $tag + * @param array $attr + * @return string + */ + protected function elementEmpty($tag, $attr = array()) + { + return $this->generator->generateFromToken( + new HTMLPurifier_Token_Empty($tag, $attr) + ); + } + + /** + * @param string $text + * @return string + */ + protected function text($text) + { + return $this->generator->generateFromToken( + new HTMLPurifier_Token_Text($text) + ); + } + + /** + * Prints a simple key/value row in a table. + * @param string $name Key + * @param mixed $value Value + * @return string + */ + protected function row($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 $string String to escape + * @return string + */ + protected function escape($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 string[] $array List of strings + * @param bool $polite Bool whether or not to add an end before the last + * @return string + */ + protected function listify($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 object $obj Object to determine class of + * @param string $sec_prefix Further prefix to remove + * @return string + */ + protected function getClass($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/extlib/HTMLPurifier/HTMLPurifier/Printer/CSSDefinition.php b/extlib/HTMLPurifier/HTMLPurifier/Printer/CSSDefinition.php new file mode 100644 index 0000000000..29505fe12d --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/Printer/CSSDefinition.php @@ -0,0 +1,44 @@ +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/extlib/HTMLPurifier/HTMLPurifier/Printer/ConfigForm.css b/extlib/HTMLPurifier/HTMLPurifier/Printer/ConfigForm.css new file mode 100644 index 0000000000..3ff1a88aa4 --- /dev/null +++ b/extlib/HTMLPurifier/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/extlib/HTMLPurifier/HTMLPurifier/Printer/ConfigForm.js b/extlib/HTMLPurifier/HTMLPurifier/Printer/ConfigForm.js new file mode 100644 index 0000000000..cba00c9b80 --- /dev/null +++ b/extlib/HTMLPurifier/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/extlib/HTMLPurifier/HTMLPurifier/Printer/ConfigForm.php b/extlib/HTMLPurifier/HTMLPurifier/Printer/ConfigForm.php new file mode 100644 index 0000000000..36100ce738 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/Printer/ConfigForm.php @@ -0,0 +1,447 @@ +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 HTMLPurifier_Config|array $config Configuration object of current form state, or an array + * where [0] has an HTML namespace and [1] is being rendered. + * @param array|bool $allowed Optional namespace(s) and directives to restrict form to. + * @param bool $render_controls + * @return string + */ + public function render($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 array $directives array of directives to values + * @return string + */ + protected function renderNamespace($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 + * @type HTMLPurifier_Printer + */ + protected $obj; + + /** + * @param HTMLPurifier_Printer $obj Printer to decorate + */ + public function __construct($obj) + { + parent::__construct(); + $this->obj = $obj; + } + + /** + * @param string $ns + * @param string $directive + * @param string $value + * @param string $name + * @param HTMLPurifier_Config|array $config + * @return string + */ + public function render($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 +{ + /** + * @type int + */ + public $cols = 18; + + /** + * @type int + */ + public $rows = 5; + + /** + * @param string $ns + * @param string $directive + * @param string $value + * @param string $name + * @param HTMLPurifier_Config|array $config + * @return string + */ + public function render($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; + } + //TODO does this need a break? + 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 +{ + /** + * @param string $ns + * @param string $directive + * @param string $value + * @param string $name + * @param HTMLPurifier_Config|array $config + * @return string + */ + public function render($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/extlib/HTMLPurifier/HTMLPurifier/Printer/HTMLDefinition.php b/extlib/HTMLPurifier/HTMLPurifier/Printer/HTMLDefinition.php new file mode 100644 index 0000000000..5f2f2f8a7c --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/Printer/HTMLDefinition.php @@ -0,0 +1,324 @@ +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 + * @return string + */ + 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 + * @return string + */ + 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), null, 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 + * @return string + */ + 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 + * @return string + */ + 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 HTMLPurifier_ChildDef $def HTMLPurifier_ChildDef of pertinent element + * @return string + */ + protected function renderChildren($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)), + null, + 0 + ); + $ret .= $this->end('tr'); + $ret .= $this->start('tr'); + $ret .= $this->element( + 'td', + 'Inline: ' . + $this->escape($this->listifyTagLookup($def->inline->elements)), + null, + 0 + ); + + } elseif ($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)), + null, + 0 + ); + } + $ret .= $this->end('tr'); + return $ret; + } + + /** + * Listifies a tag lookup table. + * @param array $array Tag lookup array in form of array('tagname' => true) + * @return string + */ + protected function listifyTagLookup($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 $array List of objects + * @return string + * @todo Also add information about internal state + */ + protected function listifyObjectList($array) + { + ksort($array); + $list = array(); + foreach ($array as $obj) { + $list[] = $this->getClass($obj, 'AttrTransform_'); + } + return $this->listify($list); + } + + /** + * Listifies a hash of attributes to AttrDef classes + * @param array $array Array hash in form of array('attrname' => HTMLPurifier_AttrDef) + * @return string + */ + protected function listifyAttr($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 + * @param string $text + * @param int $num + * @return string + */ + protected function heavyHeader($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 diff --git a/extlib/HTMLPurifier/HTMLPurifier/PropertyList.php b/extlib/HTMLPurifier/HTMLPurifier/PropertyList.php new file mode 100644 index 0000000000..189348fd9e --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/PropertyList.php @@ -0,0 +1,122 @@ +parent = $parent; + } + + /** + * Recursively retrieves the value for a key + * @param string $name + * @throws HTMLPurifier_Exception + */ + public function get($name) + { + if ($this->has($name)) { + return $this->data[$name]; + } + // possible performance bottleneck, convert to iterative if necessary + if ($this->parent) { + return $this->parent->get($name); + } + throw new HTMLPurifier_Exception("Key '$name' not found"); + } + + /** + * Sets the value of a key, for this plist + * @param string $name + * @param mixed $value + */ + public function set($name, $value) + { + $this->data[$name] = $value; + } + + /** + * Returns true if a given key exists + * @param string $name + * @return bool + */ + public function has($name) + { + return array_key_exists($name, $this->data); + } + + /** + * Resets a value to the value of it's parent, usually the default. If + * no value is specified, the entire plist is reset. + * @param string $name + */ + public function reset($name = null) + { + if ($name == null) { + $this->data = array(); + } else { + unset($this->data[$name]); + } + } + + /** + * Squashes this property list and all of its property lists into a single + * array, and returns the array. This value is cached by default. + * @param bool $force If true, ignores the cache and regenerates the array. + * @return array + */ + public function squash($force = false) + { + if ($this->cache !== null && !$force) { + return $this->cache; + } + if ($this->parent) { + return $this->cache = array_merge($this->parent->squash($force), $this->data); + } else { + return $this->cache = $this->data; + } + } + + /** + * Returns the parent plist. + * @return HTMLPurifier_PropertyList + */ + public function getParent() + { + return $this->parent; + } + + /** + * Sets the parent plist. + * @param HTMLPurifier_PropertyList $plist Parent plist + */ + public function setParent($plist) + { + $this->parent = $plist; + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/PropertyListIterator.php b/extlib/HTMLPurifier/HTMLPurifier/PropertyListIterator.php new file mode 100644 index 0000000000..15b330ea30 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/PropertyListIterator.php @@ -0,0 +1,42 @@ +l = strlen($filter); + $this->filter = $filter; + } + + /** + * @return bool + */ + public function accept() + { + $key = $this->getInnerIterator()->key(); + if (strncmp($key, $this->filter, $this->l) !== 0) { + return false; + } + return true; + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/Queue.php b/extlib/HTMLPurifier/HTMLPurifier/Queue.php new file mode 100644 index 0000000000..f58db9042a --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/Queue.php @@ -0,0 +1,56 @@ +input = $input; + $this->output = array(); + } + + /** + * Shifts an element off the front of the queue. + */ + public function shift() { + if (empty($this->output)) { + $this->output = array_reverse($this->input); + $this->input = array(); + } + if (empty($this->output)) { + return NULL; + } + return array_pop($this->output); + } + + /** + * Pushes an element onto the front of the queue. + */ + public function push($x) { + array_push($this->input, $x); + } + + /** + * Checks if it's empty. + */ + public function isEmpty() { + return empty($this->input) && empty($this->output); + } +} diff --git a/extlib/HTMLPurifier/HTMLPurifier/Strategy.php b/extlib/HTMLPurifier/HTMLPurifier/Strategy.php new file mode 100644 index 0000000000..e1ff3b72df --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/Strategy.php @@ -0,0 +1,26 @@ +strategies as $strategy) { + $tokens = $strategy->execute($tokens, $config, $context); + } + return $tokens; + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/Strategy/Core.php b/extlib/HTMLPurifier/HTMLPurifier/Strategy/Core.php new file mode 100644 index 0000000000..4414c17d6e --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/Strategy/Core.php @@ -0,0 +1,17 @@ +strategies[] = new HTMLPurifier_Strategy_RemoveForeignElements(); + $this->strategies[] = new HTMLPurifier_Strategy_MakeWellFormed(); + $this->strategies[] = new HTMLPurifier_Strategy_FixNesting(); + $this->strategies[] = new HTMLPurifier_Strategy_ValidateAttributes(); + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/Strategy/FixNesting.php b/extlib/HTMLPurifier/HTMLPurifier/Strategy/FixNesting.php new file mode 100644 index 0000000000..6fa673db9a --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/Strategy/FixNesting.php @@ -0,0 +1,181 @@ +getHTMLDefinition(); + + $excludes_enabled = !$config->get('Core.DisableExcludes'); + + // 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 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. + $exclude_stack = array($definition->info_parent_def->excludes); + + // variable that contains the start token while we are processing + // nodes. This enables error reporting to do its job + $node = $top_node; + // dummy token + list($token, $d) = $node->toTokenPair(); + $context->register('CurrentNode', $node); + $context->register('CurrentToken', $token); + + //####################################################################// + // Loop + + // We need to implement a post-order traversal iteratively, to + // avoid running into stack space limits. This is pretty tricky + // to reason about, so we just manually stack-ify the recursive + // variant: + // + // function f($node) { + // foreach ($node->children as $child) { + // f($child); + // } + // validate($node); + // } + // + // Thus, we will represent a stack frame as array($node, + // $is_inline, stack of children) + // e.g. array_reverse($node->children) - already processed + // children. + + $parent_def = $definition->info_parent_def; + $stack = array( + array($top_node, + $parent_def->descendants_are_inline, + $parent_def->excludes, // exclusions + 0) + ); + + while (!empty($stack)) { + list($node, $is_inline, $excludes, $ix) = array_pop($stack); + // recursive call + $go = false; + $def = empty($stack) ? $definition->info_parent_def : $definition->info[$node->name]; + while (isset($node->children[$ix])) { + $child = $node->children[$ix++]; + if ($child instanceof HTMLPurifier_Node_Element) { + $go = true; + $stack[] = array($node, $is_inline, $excludes, $ix); + $stack[] = array($child, + // ToDo: I don't think it matters if it's def or + // child_def, but double check this... + $is_inline || $def->descendants_are_inline, + empty($def->excludes) ? $excludes + : array_merge($excludes, $def->excludes), + 0); + break; + } + }; + if ($go) continue; + list($token, $d) = $node->toTokenPair(); + // base case + if ($excludes_enabled && isset($excludes[$node->name])) { + $node->dead = true; + if ($e) $e->send(E_ERROR, 'Strategy_FixNesting: Node excluded'); + } else { + // XXX I suppose it would be slightly more efficient to + // avoid the allocation here and have children + // strategies handle it + $children = array(); + foreach ($node->children as $child) { + if (!$child->dead) $children[] = $child; + } + $result = $def->child->validateChildren($children, $config, $context); + if ($result === true) { + // nop + $node->children = $children; + } elseif ($result === false) { + $node->dead = true; + if ($e) $e->send(E_ERROR, 'Strategy_FixNesting: Node removed'); + } else { + $node->children = $result; + if ($e) { + // XXX This will miss mutations of internal nodes. Perhaps defer to the child validators + if (empty($result) && !empty($children)) { + $e->send(E_ERROR, 'Strategy_FixNesting: Node contents removed'); + } else if ($result != $children) { + $e->send(E_WARNING, 'Strategy_FixNesting: Node reorganized'); + } + } + } + } + } + + //####################################################################// + // Post-processing + + // remove context variables + $context->destroy('IsInline'); + $context->destroy('CurrentNode'); + $context->destroy('CurrentToken'); + + //####################################################################// + // Return + + return HTMLPurifier_Arborize::flatten($node, $config, $context); + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/Strategy/MakeWellFormed.php b/extlib/HTMLPurifier/HTMLPurifier/Strategy/MakeWellFormed.php new file mode 100644 index 0000000000..e389e00116 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/Strategy/MakeWellFormed.php @@ -0,0 +1,600 @@ +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 = $definition->info_parent_def->child->getAllowedElements($config); + $e = $context->get('ErrorCollector', true); + $i = false; // injector index + list($zipper, $token) = HTMLPurifier_Zipper::fromArray($tokens); + if ($token === NULL) { + return array(); + } + $reprocess = false; // whether or not to reprocess the same token + $stack = array(); + + // member variables + $this->stack =& $stack; + $this->tokens =& $tokens; + $this->token =& $token; + $this->zipper =& $zipper; + $this->config = $config; + $this->context = $context; + + // context variables + $context->register('CurrentNesting', $stack); + $context->register('InputZipper', $zipper); + $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 (;; + // only increment if we don't need to reprocess + $reprocess ? $reprocess = false : $token = $zipper->next($token)) { + + // check for a rewind + if (is_int($i)) { + // 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_offset = $this->injectors[$i]->getRewindOffset(); + if (is_int($rewind_offset)) { + for ($j = 0; $j < $rewind_offset; $j++) { + if (empty($zipper->front)) break; + $token = $zipper->prev($token); + // indicate that other injectors should not process this token, + // but we need to reprocess it + unset($token->skip[$i]); + $token->rewind = $i; + if ($token instanceof HTMLPurifier_Token_Start) { + array_pop($this->stack); + } elseif ($token instanceof HTMLPurifier_Token_End) { + $this->stack[] = $token->start; + } + } + } + $i = false; + } + + // handle case of document end + if ($token === NULL) { + // 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 + $token = new HTMLPurifier_Token_End($top_nesting->name); + + // punt! + $reprocess = true; + continue; + } + + //echo '
    '; printZipper($zipper, $token);//printTokens($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; + } + // XXX fuckup + $r = $token; + $injector->handleText($r); + $token = $this->processToken($r, $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 + // NB: this assignment is required + $old_token = $token; + $token = new HTMLPurifier_Token_End($token->name); + $token = $this->insertBefore( + new HTMLPurifier_Token_Start($old_token->name, $old_token->attr, $old_token->line, $old_token->col, $old_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; + + $parent_def = null; + $parent_elements = null; + $autoclose = false; + if (isset($definition->info[$parent->name])) { + $parent_def = $definition->info[$parent->name]; + $parent_elements = $parent_def->child->getAllowedElements($config); + $autoclose = !isset($parent_elements[$token->name]); + } + + if ($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); + if (isset($elements[$token->name]) && isset($parent_elements[$wrapname])) { + $newtoken = new HTMLPurifier_Token_Start($wrapname); + $token = $this->insertBefore($newtoken); + $reprocess = true; + continue; + } + } + + $carryover = false; + if ($autoclose && $parent_def->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 = $parent; + // [TagClosedSuppress] + if ($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', $parent); + } + } + if ($carryover) { + $element = clone $parent; + // [TagClosedAuto] + $element->armor['MakeWellFormed_TagClosedError'] = true; + $element->carryover = true; + $token = $this->processToken(array($new_token, $token, $element)); + } else { + $token = $this->insertBefore($new_token); + } + } else { + $token = $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; + } + $r = $token; + $injector->handleElement($r); + $token = $this->processToken($r, $i); + $reprocess = true; + break; + } + if (!$reprocess) { + // ah, nothing interesting happened; do normal processing + 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'); + } + $token = new HTMLPurifier_Token_Text($generator->generateFromToken($token)); + } else { + if ($e) { + $e->send(E_WARNING, 'Strategy_MakeWellFormed: Unnecessary end tag removed'); + } + $token = $this->remove(); + } + $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; + } + $r = $token; + $injector->handleEnd($r); + $token = $this->processToken($r, $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 ($escape_invalid_tags) { + if ($e) { + $e->send(E_WARNING, 'Strategy_MakeWellFormed: Stray end tag to text'); + } + $token = new HTMLPurifier_Token_Text($generator->generateFromToken($token)); + } else { + if ($e) { + $e->send(E_WARNING, 'Strategy_MakeWellFormed: Stray end tag removed'); + } + $token = $this->remove(); + } + $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; + } + } + $token = $this->processToken($replace); + $reprocess = true; + continue; + } + + $context->destroy('CurrentToken'); + $context->destroy('CurrentNesting'); + $context->destroy('InputZipper'); + + unset($this->injectors, $this->stack, $this->tokens); + return $zipper->toArray($token); + } + + /** + * 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 HTMLPurifier_Token|array|int|bool $token Token substitution value + * @param HTMLPurifier_Injector|int $injector Injector that performed the substitution; default is if + * this is not an injector related operation. + * @throws HTMLPurifier_Exception + */ + protected function processToken($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); + list($old, $r) = $this->zipper->splice($this->token, $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; + } + } + + return $r; + + } + + /** + * Inserts a token before the current token. Cursor now points to + * this token. You must reprocess after this. + * @param HTMLPurifier_Token $token + */ + private function insertBefore($token) + { + // NB not $this->zipper->insertBefore(), due to positioning + // differences + $splice = $this->zipper->splice($this->token, 0, array($token)); + + return $splice[1]; + } + + /** + * Removes current token. Cursor now points to new token occupying previously + * occupied space. You must reprocess after this. + */ + private function remove() + { + return $this->zipper->delete(); + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/Strategy/RemoveForeignElements.php b/extlib/HTMLPurifier/HTMLPurifier/Strategy/RemoveForeignElements.php new file mode 100644 index 0000000000..1a8149eccb --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/Strategy/RemoveForeignElements.php @@ -0,0 +1,207 @@ +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; + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/Strategy/ValidateAttributes.php b/extlib/HTMLPurifier/HTMLPurifier/Strategy/ValidateAttributes.php new file mode 100644 index 0000000000..fbb3d27c81 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/Strategy/ValidateAttributes.php @@ -0,0 +1,45 @@ +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); + } + $context->destroy('CurrentToken'); + return $tokens; + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/StringHash.php b/extlib/HTMLPurifier/HTMLPurifier/StringHash.php new file mode 100644 index 0000000000..c07370197a --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/StringHash.php @@ -0,0 +1,47 @@ +accessed[$index] = true; + return parent::offsetGet($index); + } + + /** + * Returns a lookup array of all array indexes that have been accessed. + * @return array in form array($index => true). + */ + public function getAccessed() + { + return $this->accessed; + } + + /** + * Resets the access array. + */ + public function resetAccessed() + { + $this->accessed = array(); + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/StringHashParser.php b/extlib/HTMLPurifier/HTMLPurifier/StringHashParser.php new file mode 100644 index 0000000000..7c73f80835 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/StringHashParser.php @@ -0,0 +1,136 @@ + 'DefaultKeyValue', + * 'KEY' => 'Value', + * 'KEY2' => 'Value2', + * 'MULTILINE-KEY' => "Multiline\nvalue.\n", + * ) + * + * We use this as an easy to use file-format for configuration schema + * files, but the class itself is usage agnostic. + * + * You can use ---- to forcibly terminate parsing of a single string-hash; + * this marker is used in multi string-hashes to delimit boundaries. + */ +class HTMLPurifier_StringHashParser +{ + + /** + * @type string + */ + public $default = 'ID'; + + /** + * Parses a file that contains a single string-hash. + * @param string $file + * @return array + */ + public function parseFile($file) + { + if (!file_exists($file)) { + return false; + } + $fh = fopen($file, 'r'); + if (!$fh) { + return false; + } + $ret = $this->parseHandle($fh); + fclose($fh); + return $ret; + } + + /** + * Parses a file that contains multiple string-hashes delimited by '----' + * @param string $file + * @return array + */ + public function parseMultiFile($file) + { + if (!file_exists($file)) { + return false; + } + $ret = array(); + $fh = fopen($file, 'r'); + if (!$fh) { + return false; + } + while (!feof($fh)) { + $ret[] = $this->parseHandle($fh); + } + fclose($fh); + return $ret; + } + + /** + * Internal parser that acepts a file handle. + * @note While it's possible to simulate in-memory parsing by using + * custom stream wrappers, if such a use-case arises we should + * factor out the file handle into its own class. + * @param resource $fh File handle with pointer at start of valid string-hash + * block. + * @return array + */ + protected function parseHandle($fh) + { + $state = false; + $single = false; + $ret = array(); + do { + $line = fgets($fh); + if ($line === false) { + break; + } + $line = rtrim($line, "\n\r"); + if (!$state && $line === '') { + continue; + } + if ($line === '----') { + break; + } + if (strncmp('--#', $line, 3) === 0) { + // Comment + continue; + } elseif (strncmp('--', $line, 2) === 0) { + // Multiline declaration + $state = trim($line, '- '); + if (!isset($ret[$state])) { + $ret[$state] = ''; + } + continue; + } elseif (!$state) { + $single = true; + if (strpos($line, ':') !== false) { + // Single-line declaration + list($state, $line) = explode(':', $line, 2); + $line = trim($line); + } else { + // Use default declaration + $state = $this->default; + } + } + if ($single) { + $ret[$state] = $line; + $single = false; + $state = false; + } else { + $ret[$state] .= "$line\n"; + } + } while (!feof($fh)); + return $ret; + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/TagTransform.php b/extlib/HTMLPurifier/HTMLPurifier/TagTransform.php new file mode 100644 index 0000000000..7b8d833433 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/TagTransform.php @@ -0,0 +1,37 @@ + '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%' + ); + + /** + * @param HTMLPurifier_Token_Tag $tag + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return HTMLPurifier_Token_End|string + */ + public function transform($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; + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/TagTransform/Simple.php b/extlib/HTMLPurifier/HTMLPurifier/TagTransform/Simple.php new file mode 100644 index 0000000000..71bf10b91f --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/TagTransform/Simple.php @@ -0,0 +1,44 @@ +transform_to = $transform_to; + $this->style = $style; + } + + /** + * @param HTMLPurifier_Token_Tag $tag + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return string + */ + public function transform($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; + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/Token.php b/extlib/HTMLPurifier/HTMLPurifier/Token.php new file mode 100644 index 0000000000..85b85e072d --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/Token.php @@ -0,0 +1,100 @@ +line = $l; + $this->col = $c; + } + + /** + * Convenience function for DirectLex settings line/col position. + * @param int $l + * @param int $c + */ + public function rawPosition($l, $c) + { + if ($c === -1) { + $l++; + } + $this->line = $l; + $this->col = $c; + } + + /** + * Converts a token into its corresponding node. + */ + abstract public function toNode(); +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/Token/Comment.php b/extlib/HTMLPurifier/HTMLPurifier/Token/Comment.php new file mode 100644 index 0000000000..23453c7052 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/Token/Comment.php @@ -0,0 +1,38 @@ +data = $data; + $this->line = $line; + $this->col = $col; + } + + public function toNode() { + return new HTMLPurifier_Node_Comment($this->data, $this->line, $this->col); + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/Token/Empty.php b/extlib/HTMLPurifier/HTMLPurifier/Token/Empty.php new file mode 100644 index 0000000000..78a95f5555 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/Token/Empty.php @@ -0,0 +1,15 @@ +empty = true; + return $n; + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/Token/End.php b/extlib/HTMLPurifier/HTMLPurifier/Token/End.php new file mode 100644 index 0000000000..59b38fdc57 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/Token/End.php @@ -0,0 +1,24 @@ +toNode not supported!"); + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/Token/Start.php b/extlib/HTMLPurifier/HTMLPurifier/Token/Start.php new file mode 100644 index 0000000000..019f317ada --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/Token/Start.php @@ -0,0 +1,10 @@ +!empty($obj->is_tag) + * without having to use a function call is_a(). + * @type bool + */ + 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. + * @type string + */ + public $name; + + /** + * Associative array of the tag's attributes. + * @type array + */ + public $attr = array(); + + /** + * Non-overloaded constructor, which lower-cases passed tag name. + * + * @param string $name String name. + * @param array $attr Associative array of attributes. + * @param int $line + * @param int $col + * @param array $armor + */ + public function __construct($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 = $armor; + } + + public function toNode() { + return new HTMLPurifier_Node_Element($this->name, $this->attr, $this->line, $this->col, $this->armor); + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/Token/Text.php b/extlib/HTMLPurifier/HTMLPurifier/Token/Text.php new file mode 100644 index 0000000000..f26a1c211b --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/Token/Text.php @@ -0,0 +1,53 @@ +data = $data; + $this->is_whitespace = ctype_space($data); + $this->line = $line; + $this->col = $col; + } + + public function toNode() { + return new HTMLPurifier_Node_Text($this->data, $this->is_whitespace, $this->line, $this->col); + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/TokenFactory.php b/extlib/HTMLPurifier/HTMLPurifier/TokenFactory.php new file mode 100644 index 0000000000..dea2446b93 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/TokenFactory.php @@ -0,0 +1,118 @@ +p_start = new HTMLPurifier_Token_Start('', array()); + $this->p_end = new HTMLPurifier_Token_End(''); + $this->p_empty = new HTMLPurifier_Token_Empty('', array()); + $this->p_text = new HTMLPurifier_Token_Text(''); + $this->p_comment = new HTMLPurifier_Token_Comment(''); + } + + /** + * Creates a HTMLPurifier_Token_Start. + * @param string $name Tag name + * @param array $attr Associative array of attributes + * @return HTMLPurifier_Token_Start Generated HTMLPurifier_Token_Start + */ + public function createStart($name, $attr = array()) + { + $p = clone $this->p_start; + $p->__construct($name, $attr); + return $p; + } + + /** + * Creates a HTMLPurifier_Token_End. + * @param string $name Tag name + * @return HTMLPurifier_Token_End Generated HTMLPurifier_Token_End + */ + public function createEnd($name) + { + $p = clone $this->p_end; + $p->__construct($name); + return $p; + } + + /** + * Creates a HTMLPurifier_Token_Empty. + * @param string $name Tag name + * @param array $attr Associative array of attributes + * @return HTMLPurifier_Token_Empty Generated HTMLPurifier_Token_Empty + */ + public function createEmpty($name, $attr = array()) + { + $p = clone $this->p_empty; + $p->__construct($name, $attr); + return $p; + } + + /** + * Creates a HTMLPurifier_Token_Text. + * @param string $data Data of text token + * @return HTMLPurifier_Token_Text Generated HTMLPurifier_Token_Text + */ + public function createText($data) + { + $p = clone $this->p_text; + $p->__construct($data); + return $p; + } + + /** + * Creates a HTMLPurifier_Token_Comment. + * @param string $data Data of comment token + * @return HTMLPurifier_Token_Comment Generated HTMLPurifier_Token_Comment + */ + public function createComment($data) + { + $p = clone $this->p_comment; + $p->__construct($data); + return $p; + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/URI.php b/extlib/HTMLPurifier/HTMLPurifier/URI.php new file mode 100644 index 0000000000..a5e7ae2984 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/URI.php @@ -0,0 +1,314 @@ +scheme = is_null($scheme) || ctype_lower($scheme) ? $scheme : strtolower($scheme); + $this->userinfo = $userinfo; + $this->host = $host; + $this->port = is_null($port) ? $port : (int)$port; + $this->path = $path; + $this->query = $query; + $this->fragment = $fragment; + } + + /** + * Retrieves a scheme object corresponding to the URI's scheme/default + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return HTMLPurifier_URIScheme Scheme object appropriate for validating this URI + */ + public function getSchemeObj($config, $context) + { + $registry = HTMLPurifier_URISchemeRegistry::instance(); + if ($this->scheme !== null) { + $scheme_obj = $registry->getScheme($this->scheme, $config, $context); + if (!$scheme_obj) { + return false; + } // invalid scheme, clean it out + } else { + // no scheme: retrieve the default one + $def = $config->getDefinition('URI'); + $scheme_obj = $def->getDefaultScheme($config, $context); + if (!$scheme_obj) { + // something funky happened to the default scheme object + trigger_error( + 'Default scheme object "' . $def->defaultScheme . '" was not readable', + E_USER_WARNING + ); + return false; + } + } + return $scheme_obj; + } + + /** + * Generic validation method applicable for all schemes. May modify + * this URI in order to get it into a compliant form. + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool True if validation/filtering succeeds, false if failure + */ + public function validate($config, $context) + { + // ABNF definitions from RFC 3986 + $chars_sub_delims = '!$&\'()*+,;='; + $chars_gen_delims = ':/?#[]@'; + $chars_pchar = $chars_sub_delims . ':@'; + + // validate host + if (!is_null($this->host)) { + $host_def = new HTMLPurifier_AttrDef_URI_Host(); + $this->host = $host_def->validate($this->host, $config, $context); + if ($this->host === false) { + $this->host = null; + } + } + + // validate scheme + // NOTE: It's not appropriate to check whether or not this + // scheme is in our registry, since a URIFilter may convert a + // URI that we don't allow into one we do. So instead, we just + // check if the scheme can be dropped because there is no host + // and it is our default scheme. + if (!is_null($this->scheme) && is_null($this->host) || $this->host === '') { + // support for relative paths is pretty abysmal when the + // scheme is present, so axe it when possible + $def = $config->getDefinition('URI'); + if ($def->defaultScheme === $this->scheme) { + $this->scheme = null; + } + } + + // validate username + if (!is_null($this->userinfo)) { + $encoder = new HTMLPurifier_PercentEncoder($chars_sub_delims . ':'); + $this->userinfo = $encoder->encode($this->userinfo); + } + + // validate port + if (!is_null($this->port)) { + if ($this->port < 1 || $this->port > 65535) { + $this->port = null; + } + } + + // validate path + $segments_encoder = new HTMLPurifier_PercentEncoder($chars_pchar . '/'); + if (!is_null($this->host)) { // this catches $this->host === '' + // path-abempty (hier and relative) + // http://www.example.com/my/path + // //www.example.com/my/path (looks odd, but works, and + // recognized by most browsers) + // (this set is valid or invalid on a scheme by scheme + // basis, so we'll deal with it later) + // file:///my/path + // ///my/path + $this->path = $segments_encoder->encode($this->path); + } elseif ($this->path !== '') { + if ($this->path[0] === '/') { + // path-absolute (hier and relative) + // http:/my/path + // /my/path + if (strlen($this->path) >= 2 && $this->path[1] === '/') { + // This could happen if both the host gets stripped + // out + // http://my/path + // //my/path + $this->path = ''; + } else { + $this->path = $segments_encoder->encode($this->path); + } + } elseif (!is_null($this->scheme)) { + // path-rootless (hier) + // http:my/path + // Short circuit evaluation means we don't need to check nz + $this->path = $segments_encoder->encode($this->path); + } else { + // path-noscheme (relative) + // my/path + // (once again, not checking nz) + $segment_nc_encoder = new HTMLPurifier_PercentEncoder($chars_sub_delims . '@'); + $c = strpos($this->path, '/'); + if ($c !== false) { + $this->path = + $segment_nc_encoder->encode(substr($this->path, 0, $c)) . + $segments_encoder->encode(substr($this->path, $c)); + } else { + $this->path = $segment_nc_encoder->encode($this->path); + } + } + } else { + // path-empty (hier and relative) + $this->path = ''; // just to be safe + } + + // qf = query and fragment + $qf_encoder = new HTMLPurifier_PercentEncoder($chars_pchar . '/?'); + + if (!is_null($this->query)) { + $this->query = $qf_encoder->encode($this->query); + } + + if (!is_null($this->fragment)) { + $this->fragment = $qf_encoder->encode($this->fragment); + } + return true; + } + + /** + * Convert URI back to string + * @return string URI appropriate for output + */ + public function toString() + { + // reconstruct authority + $authority = null; + // there is a rendering difference between a null authority + // (http:foo-bar) and an empty string authority + // (http:///foo-bar). + if (!is_null($this->host)) { + $authority = ''; + if (!is_null($this->userinfo)) { + $authority .= $this->userinfo . '@'; + } + $authority .= $this->host; + if (!is_null($this->port)) { + $authority .= ':' . $this->port; + } + } + + // Reconstruct the result + // One might wonder about parsing quirks from browsers after + // this reconstruction. Unfortunately, parsing behavior depends + // on what *scheme* was employed (file:///foo is handled *very* + // differently than http:///foo), so unfortunately we have to + // defer to the schemes to do the right thing. + $result = ''; + if (!is_null($this->scheme)) { + $result .= $this->scheme . ':'; + } + if (!is_null($authority)) { + $result .= '//' . $authority; + } + $result .= $this->path; + if (!is_null($this->query)) { + $result .= '?' . $this->query; + } + if (!is_null($this->fragment)) { + $result .= '#' . $this->fragment; + } + + return $result; + } + + /** + * Returns true if this URL might be considered a 'local' URL given + * the current context. This is true when the host is null, or + * when it matches the host supplied to the configuration. + * + * Note that this does not do any scheme checking, so it is mostly + * only appropriate for metadata that doesn't care about protocol + * security. isBenign is probably what you actually want. + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool + */ + public function isLocal($config, $context) + { + if ($this->host === null) { + return true; + } + $uri_def = $config->getDefinition('URI'); + if ($uri_def->host === $this->host) { + return true; + } + return false; + } + + /** + * Returns true if this URL should be considered a 'benign' URL, + * that is: + * + * - It is a local URL (isLocal), and + * - It has a equal or better level of security + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool + */ + public function isBenign($config, $context) + { + if (!$this->isLocal($config, $context)) { + return false; + } + + $scheme_obj = $this->getSchemeObj($config, $context); + if (!$scheme_obj) { + return false; + } // conservative approach + + $current_scheme_obj = $config->getDefinition('URI')->getDefaultScheme($config, $context); + if ($current_scheme_obj->secure) { + if (!$scheme_obj->secure) { + return false; + } + } + return true; + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/URIDefinition.php b/extlib/HTMLPurifier/HTMLPurifier/URIDefinition.php new file mode 100644 index 0000000000..e0bd8bcca8 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/URIDefinition.php @@ -0,0 +1,112 @@ +registerFilter(new HTMLPurifier_URIFilter_DisableExternal()); + $this->registerFilter(new HTMLPurifier_URIFilter_DisableExternalResources()); + $this->registerFilter(new HTMLPurifier_URIFilter_DisableResources()); + $this->registerFilter(new HTMLPurifier_URIFilter_HostBlacklist()); + $this->registerFilter(new HTMLPurifier_URIFilter_SafeIframe()); + $this->registerFilter(new HTMLPurifier_URIFilter_MakeAbsolute()); + $this->registerFilter(new HTMLPurifier_URIFilter_Munge()); + } + + public function registerFilter($filter) + { + $this->registeredFilters[$filter->name] = $filter; + } + + public function addFilter($filter, $config) + { + $r = $filter->prepare($config); + if ($r === false) return; // null is ok, for backwards compat + if ($filter->post) { + $this->postFilters[$filter->name] = $filter; + } else { + $this->filters[$filter->name] = $filter; + } + } + + protected function doSetup($config) + { + $this->setupMemberVariables($config); + $this->setupFilters($config); + } + + protected function setupFilters($config) + { + foreach ($this->registeredFilters as $name => $filter) { + if ($filter->always_load) { + $this->addFilter($filter, $config); + } else { + $conf = $config->get('URI.' . $name); + if ($conf !== false && $conf !== null) { + $this->addFilter($filter, $config); + } + } + } + unset($this->registeredFilters); + } + + protected function setupMemberVariables($config) + { + $this->host = $config->get('URI.Host'); + $base_uri = $config->get('URI.Base'); + if (!is_null($base_uri)) { + $parser = new HTMLPurifier_URIParser(); + $this->base = $parser->parse($base_uri); + $this->defaultScheme = $this->base->scheme; + if (is_null($this->host)) $this->host = $this->base->host; + } + if (is_null($this->defaultScheme)) $this->defaultScheme = $config->get('URI.DefaultScheme'); + } + + public function getDefaultScheme($config, $context) + { + return HTMLPurifier_URISchemeRegistry::instance()->getScheme($this->defaultScheme, $config, $context); + } + + public function filter(&$uri, $config, $context) + { + foreach ($this->filters as $name => $f) { + $result = $f->filter($uri, $config, $context); + if (!$result) return false; + } + return true; + } + + public function postFilter(&$uri, $config, $context) + { + foreach ($this->postFilters as $name => $f) { + $result = $f->filter($uri, $config, $context); + if (!$result) return false; + } + return true; + } + +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/URIFilter.php b/extlib/HTMLPurifier/HTMLPurifier/URIFilter.php new file mode 100644 index 0000000000..09724e9f41 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/URIFilter.php @@ -0,0 +1,74 @@ +getDefinition('URI')->host; + if ($our_host !== null) { + $this->ourHostParts = array_reverse(explode('.', $our_host)); + } + } + + /** + * @param HTMLPurifier_URI $uri Reference + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool + */ + public function filter(&$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; + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/URIFilter/DisableExternalResources.php b/extlib/HTMLPurifier/HTMLPurifier/URIFilter/DisableExternalResources.php new file mode 100644 index 0000000000..c6562169e0 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/URIFilter/DisableExternalResources.php @@ -0,0 +1,25 @@ +get('EmbeddedURI', true)) { + return true; + } + return parent::filter($uri, $config, $context); + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/URIFilter/DisableResources.php b/extlib/HTMLPurifier/HTMLPurifier/URIFilter/DisableResources.php new file mode 100644 index 0000000000..d5c412c444 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/URIFilter/DisableResources.php @@ -0,0 +1,22 @@ +get('EmbeddedURI', true); + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/URIFilter/HostBlacklist.php b/extlib/HTMLPurifier/HTMLPurifier/URIFilter/HostBlacklist.php new file mode 100644 index 0000000000..a6645c17ee --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/URIFilter/HostBlacklist.php @@ -0,0 +1,46 @@ +blacklist = $config->get('URI.HostBlacklist'); + return true; + } + + /** + * @param HTMLPurifier_URI $uri + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool + */ + public function filter(&$uri, $config, $context) + { + foreach ($this->blacklist as $blacklisted_host_fragment) { + if (strpos($uri->host, $blacklisted_host_fragment) !== false) { + return false; + } + } + return true; + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/URIFilter/MakeAbsolute.php b/extlib/HTMLPurifier/HTMLPurifier/URIFilter/MakeAbsolute.php new file mode 100644 index 0000000000..c507bbff8e --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/URIFilter/MakeAbsolute.php @@ -0,0 +1,158 @@ +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; + } + + /** + * @param HTMLPurifier_URI $uri + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool + */ + public function filter(&$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 + * @param array $stack + * @return array + */ + private function _collapseStack($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; + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/URIFilter/Munge.php b/extlib/HTMLPurifier/HTMLPurifier/URIFilter/Munge.php new file mode 100644 index 0000000000..6e03315a17 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/URIFilter/Munge.php @@ -0,0 +1,115 @@ +target = $config->get('URI.' . $this->name); + $this->parser = new HTMLPurifier_URIParser(); + $this->doEmbed = $config->get('URI.MungeResources'); + $this->secretKey = $config->get('URI.MungeSecretKey'); + if ($this->secretKey && !function_exists('hash_hmac')) { + throw new Exception("Cannot use %URI.MungeSecretKey without hash_hmac support."); + } + return true; + } + + /** + * @param HTMLPurifier_URI $uri + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool + */ + public function filter(&$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; + } + + /** + * @param HTMLPurifier_URI $uri + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + */ + protected function makeReplace($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'] = hash_hmac("sha256", $string, $this->secretKey); + } + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/URIFilter/SafeIframe.php b/extlib/HTMLPurifier/HTMLPurifier/URIFilter/SafeIframe.php new file mode 100644 index 0000000000..f609c47a34 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/URIFilter/SafeIframe.php @@ -0,0 +1,68 @@ +regexp = $config->get('URI.SafeIframeRegexp'); + return true; + } + + /** + * @param HTMLPurifier_URI $uri + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool + */ + public function filter(&$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()); + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/URIParser.php b/extlib/HTMLPurifier/HTMLPurifier/URIParser.php new file mode 100644 index 0000000000..0e7381a07b --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/URIParser.php @@ -0,0 +1,71 @@ +percentEncoder = new HTMLPurifier_PercentEncoder(); + } + + /** + * Parses a URI. + * @param $uri string URI to parse + * @return HTMLPurifier_URI representation of URI. This representation has + * not been validated yet and may not conform to RFC. + */ + public function parse($uri) + { + $uri = $this->percentEncoder->normalize($uri); + + // Regexp is as per Appendix B. + // Note that ["<>] are an addition to the RFC's recommended + // characters, because they represent external delimeters. + $r_URI = '!'. + '(([a-zA-Z0-9\.\+\-]+):)?'. // 2. Scheme + '(//([^/?#"<>]*))?'. // 4. Authority + '([^?#"<>]*)'. // 5. Path + '(\?([^#"<>]*))?'. // 7. Query + '(#([^"<>]*))?'. // 8. Fragment + '!'; + + $matches = array(); + $result = preg_match($r_URI, $uri, $matches); + + if (!$result) return false; // *really* invalid URI + + // seperate out parts + $scheme = !empty($matches[1]) ? $matches[2] : null; + $authority = !empty($matches[3]) ? $matches[4] : null; + $path = $matches[5]; // always present, can be empty + $query = !empty($matches[6]) ? $matches[7] : null; + $fragment = !empty($matches[8]) ? $matches[9] : null; + + // further parse authority + if ($authority !== null) { + $r_authority = "/^((.+?)@)?(\[[^\]]+\]|[^:]*)(:(\d*))?/"; + $matches = array(); + preg_match($r_authority, $authority, $matches); + $userinfo = !empty($matches[1]) ? $matches[2] : null; + $host = !empty($matches[3]) ? $matches[3] : ''; + $port = !empty($matches[4]) ? (int) $matches[5] : null; + } else { + $port = $host = $userinfo = null; + } + + return new HTMLPurifier_URI( + $scheme, $userinfo, $host, $port, $path, $query, $fragment); + } + +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/URIScheme.php b/extlib/HTMLPurifier/HTMLPurifier/URIScheme.php new file mode 100644 index 0000000000..fe9e82cf26 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/URIScheme.php @@ -0,0 +1,102 @@ +, resolves edge cases + * with making relative URIs absolute + * @type bool + */ + public $hierarchical = false; + + /** + * Whether or not the URI may omit a hostname when the scheme is + * explicitly specified, ala file:///path/to/file. As of writing, + * 'file' is the only scheme that browsers support his properly. + * @type bool + */ + public $may_omit_host = false; + + /** + * Validates the components of a URI for a specific scheme. + * @param HTMLPurifier_URI $uri Reference to a HTMLPurifier_URI object + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool success or failure + */ + abstract public function doValidate(&$uri, $config, $context); + + /** + * Public interface for validating components of a URI. Performs a + * bunch of default actions. Don't overload this method. + * @param HTMLPurifier_URI $uri Reference to a HTMLPurifier_URI object + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool success or failure + */ + public function validate(&$uri, $config, $context) + { + if ($this->default_port == $uri->port) { + $uri->port = null; + } + // kludge: browsers do funny things when the scheme but not the + // authority is set + if (!$this->may_omit_host && + // if the scheme is present, a missing host is always in error + (!is_null($uri->scheme) && ($uri->host === '' || is_null($uri->host))) || + // if the scheme is not present, a *blank* host is in error, + // since this translates into '///path' which most browsers + // interpret as being 'http://path'. + (is_null($uri->scheme) && $uri->host === '') + ) { + do { + if (is_null($uri->scheme)) { + if (substr($uri->path, 0, 2) != '//') { + $uri->host = null; + break; + } + // URI is '////path', so we cannot nullify the + // host to preserve semantics. Try expanding the + // hostname instead (fall through) + } + // first see if we can manually insert a hostname + $host = $config->get('URI.Host'); + if (!is_null($host)) { + $uri->host = $host; + } else { + // we can't do anything sensible, reject the URL. + return false; + } + } while (false); + } + return $this->doValidate($uri, $config, $context); + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/URIScheme/data.php b/extlib/HTMLPurifier/HTMLPurifier/URIScheme/data.php new file mode 100644 index 0000000000..6ebca49848 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/URIScheme/data.php @@ -0,0 +1,127 @@ + true, + 'image/gif' => true, + 'image/png' => true, + ); + // this is actually irrelevant since we only write out the path + // component + /** + * @type bool + */ + public $may_omit_host = true; + + /** + * @param HTMLPurifier_URI $uri + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool + */ + public function doValidate(&$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; + } + + /** + * @param int $errno + * @param string $errstr + */ + public function muteErrorHandler($errno, $errstr) + { + } +} diff --git a/extlib/HTMLPurifier/HTMLPurifier/URIScheme/file.php b/extlib/HTMLPurifier/HTMLPurifier/URIScheme/file.php new file mode 100644 index 0000000000..215be4ba80 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/URIScheme/file.php @@ -0,0 +1,44 @@ +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; + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/URIScheme/ftp.php b/extlib/HTMLPurifier/HTMLPurifier/URIScheme/ftp.php new file mode 100644 index 0000000000..1eb43ee5c4 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/URIScheme/ftp.php @@ -0,0 +1,58 @@ +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; + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/URIScheme/http.php b/extlib/HTMLPurifier/HTMLPurifier/URIScheme/http.php new file mode 100644 index 0000000000..ce69ec438a --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/URIScheme/http.php @@ -0,0 +1,36 @@ +userinfo = null; + return true; + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/URIScheme/https.php b/extlib/HTMLPurifier/HTMLPurifier/URIScheme/https.php new file mode 100644 index 0000000000..0e96882db9 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/URIScheme/https.php @@ -0,0 +1,18 @@ +userinfo = null; + $uri->host = null; + $uri->port = null; + // we need to validate path against RFC 2368's addr-spec + return true; + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/URIScheme/news.php b/extlib/HTMLPurifier/HTMLPurifier/URIScheme/news.php new file mode 100644 index 0000000000..7490927d63 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/URIScheme/news.php @@ -0,0 +1,35 @@ +userinfo = null; + $uri->host = null; + $uri->port = null; + $uri->query = null; + // typecode check needed on path + return true; + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/URIScheme/nntp.php b/extlib/HTMLPurifier/HTMLPurifier/URIScheme/nntp.php new file mode 100644 index 0000000000..f211d715e9 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/URIScheme/nntp.php @@ -0,0 +1,32 @@ +userinfo = null; + $uri->query = null; + return true; + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/URISchemeRegistry.php b/extlib/HTMLPurifier/HTMLPurifier/URISchemeRegistry.php new file mode 100644 index 0000000000..4ac8a0b76e --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/URISchemeRegistry.php @@ -0,0 +1,81 @@ +get('URI.AllowedSchemes'); + if (!$config->get('URI.OverrideAllowedSchemes') && + !isset($allowed_schemes[$scheme]) + ) { + return; + } + + if (isset($this->schemes[$scheme])) { + return $this->schemes[$scheme]; + } + if (!isset($allowed_schemes[$scheme])) { + return; + } + + $class = 'HTMLPurifier_URIScheme_' . $scheme; + if (!class_exists($class)) { + return; + } + $this->schemes[$scheme] = new $class(); + return $this->schemes[$scheme]; + } + + /** + * Registers a custom scheme to the cache, bypassing reflection. + * @param string $scheme Scheme name + * @param HTMLPurifier_URIScheme $scheme_obj + */ + public function register($scheme, $scheme_obj) + { + $this->schemes[$scheme] = $scheme_obj; + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/UnitConverter.php b/extlib/HTMLPurifier/HTMLPurifier/UnitConverter.php new file mode 100644 index 0000000000..166f3bf306 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/UnitConverter.php @@ -0,0 +1,307 @@ + array( + 'px' => 3, // This is as per CSS 2.1 and Firefox. Your mileage may vary + 'pt' => 4, + 'pc' => 48, + 'in' => 288, + self::METRIC => array('pt', '0.352777778', 'mm'), + ), + self::METRIC => array( + 'mm' => 1, + 'cm' => 10, + self::ENGLISH => array('mm', '2.83464567', 'pt'), + ), + ); + + /** + * Minimum bcmath precision for output. + * @type int + */ + protected $outputPrecision; + + /** + * Bcmath precision for internal calculations. + * @type int + */ + protected $internalPrecision; + + /** + * Whether or not BCMath is available. + * @type bool + */ + private $bcmath; + + public function __construct($output_precision = 4, $internal_precision = 10, $force_no_bcmath = false) + { + $this->outputPrecision = $output_precision; + $this->internalPrecision = $internal_precision; + $this->bcmath = !$force_no_bcmath && function_exists('bcmul'); + } + + /** + * Converts a length object of one unit into another unit. + * @param HTMLPurifier_Length $length + * Instance of HTMLPurifier_Length to convert. You must validate() + * it before passing it here! + * @param string $to_unit + * Unit to convert to. + * @return HTMLPurifier_Length|bool + * @note + * About precision: This conversion function pays very special + * attention to the incoming precision of values and attempts + * to maintain a number of significant figure. Results are + * fairly accurate up to nine digits. Some caveats: + * - If a number is zero-padded as a result of this significant + * figure tracking, the zeroes will be eliminated. + * - If a number contains less than four sigfigs ($outputPrecision) + * and this causes some decimals to be excluded, those + * decimals will be added on. + */ + public function convert($length, $to_unit) + { + if (!$length->isValid()) { + return false; + } + + $n = $length->getN(); + $unit = $length->getUnit(); + + if ($n === '0' || $unit === false) { + return new HTMLPurifier_Length('0', false); + } + + $state = $dest_state = false; + foreach (self::$units as $k => $x) { + if (isset($x[$unit])) { + $state = $k; + } + if (isset($x[$to_unit])) { + $dest_state = $k; + } + } + if (!$state || !$dest_state) { + return false; + } + + // Some calculations about the initial precision of the number; + // this will be useful when we need to do final rounding. + $sigfigs = $this->getSigFigs($n); + if ($sigfigs < $this->outputPrecision) { + $sigfigs = $this->outputPrecision; + } + + // BCMath's internal precision deals only with decimals. Use + // our default if the initial number has no decimals, or increase + // it by how ever many decimals, thus, the number of guard digits + // will always be greater than or equal to internalPrecision. + $log = (int)floor(log(abs($n), 10)); + $cp = ($log < 0) ? $this->internalPrecision - $log : $this->internalPrecision; // internal precision + + for ($i = 0; $i < 2; $i++) { + + // Determine what unit IN THIS SYSTEM we need to convert to + if ($dest_state === $state) { + // Simple conversion + $dest_unit = $to_unit; + } else { + // Convert to the smallest unit, pending a system shift + $dest_unit = self::$units[$state][$dest_state][0]; + } + + // Do the conversion if necessary + if ($dest_unit !== $unit) { + $factor = $this->div(self::$units[$state][$unit], self::$units[$state][$dest_unit], $cp); + $n = $this->mul($n, $factor, $cp); + $unit = $dest_unit; + } + + // Output was zero, so bail out early. Shouldn't ever happen. + if ($n === '') { + $n = '0'; + $unit = $to_unit; + break; + } + + // It was a simple conversion, so bail out + if ($dest_state === $state) { + break; + } + + if ($i !== 0) { + // Conversion failed! Apparently, the system we forwarded + // to didn't have this unit. This should never happen! + return false; + } + + // Pre-condition: $i == 0 + + // Perform conversion to next system of units + $n = $this->mul($n, self::$units[$state][$dest_state][1], $cp); + $unit = self::$units[$state][$dest_state][2]; + $state = $dest_state; + + // One more loop around to convert the unit in the new system. + + } + + // Post-condition: $unit == $to_unit + if ($unit !== $to_unit) { + return false; + } + + // Useful for debugging: + //echo "
        n";
+        //echo "$n\nsigfigs = $sigfigs\nnew_log = $new_log\nlog = $log\nrp = $rp\n
        \n"; + + $n = $this->round($n, $sigfigs); + if (strpos($n, '.') !== false) { + $n = rtrim($n, '0'); + } + $n = rtrim($n, '.'); + + return new HTMLPurifier_Length($n, $unit); + } + + /** + * Returns the number of significant figures in a string number. + * @param string $n Decimal number + * @return int number of sigfigs + */ + public function getSigFigs($n) + { + $n = ltrim($n, '0+-'); + $dp = strpos($n, '.'); // decimal position + if ($dp === false) { + $sigfigs = strlen(rtrim($n, '0')); + } else { + $sigfigs = strlen(ltrim($n, '0.')); // eliminate extra decimal character + if ($dp !== 0) { + $sigfigs--; + } + } + return $sigfigs; + } + + /** + * Adds two numbers, using arbitrary precision when available. + * @param string $s1 + * @param string $s2 + * @param int $scale + * @return string + */ + private function add($s1, $s2, $scale) + { + if ($this->bcmath) { + return bcadd($s1, $s2, $scale); + } else { + return $this->scale((float)$s1 + (float)$s2, $scale); + } + } + + /** + * Multiples two numbers, using arbitrary precision when available. + * @param string $s1 + * @param string $s2 + * @param int $scale + * @return string + */ + private function mul($s1, $s2, $scale) + { + if ($this->bcmath) { + return bcmul($s1, $s2, $scale); + } else { + return $this->scale((float)$s1 * (float)$s2, $scale); + } + } + + /** + * Divides two numbers, using arbitrary precision when available. + * @param string $s1 + * @param string $s2 + * @param int $scale + * @return string + */ + private function div($s1, $s2, $scale) + { + if ($this->bcmath) { + return bcdiv($s1, $s2, $scale); + } else { + return $this->scale((float)$s1 / (float)$s2, $scale); + } + } + + /** + * Rounds a number according to the number of sigfigs it should have, + * using arbitrary precision when available. + * @param float $n + * @param int $sigfigs + * @return string + */ + private function round($n, $sigfigs) + { + $new_log = (int)floor(log(abs($n), 10)); // Number of digits left of decimal - 1 + $rp = $sigfigs - $new_log - 1; // Number of decimal places needed + $neg = $n < 0 ? '-' : ''; // Negative sign + if ($this->bcmath) { + if ($rp >= 0) { + $n = bcadd($n, $neg . '0.' . str_repeat('0', $rp) . '5', $rp + 1); + $n = bcdiv($n, '1', $rp); + } else { + // This algorithm partially depends on the standardized + // form of numbers that comes out of bcmath. + $n = bcadd($n, $neg . '5' . str_repeat('0', $new_log - $sigfigs), 0); + $n = substr($n, 0, $sigfigs + strlen($neg)) . str_repeat('0', $new_log - $sigfigs + 1); + } + return $n; + } else { + return $this->scale(round($n, $sigfigs - $new_log - 1), $rp + 1); + } + } + + /** + * Scales a float to $scale digits right of decimal point, like BCMath. + * @param float $r + * @param int $scale + * @return string + */ + private function scale($r, $scale) + { + if ($scale < 0) { + // The f sprintf type doesn't support negative numbers, so we + // need to cludge things manually. First get the string. + $r = sprintf('%.0f', (float)$r); + // Due to floating point precision loss, $r will more than likely + // look something like 4652999999999.9234. We grab one more digit + // than we need to precise from $r and then use that to round + // appropriately. + $precise = (string)round(substr($r, 0, strlen($r) + $scale), -1); + // Now we return it, truncating the zero that was rounded off. + return substr($precise, 0, -1) . str_repeat('0', -$scale + 1); + } + return sprintf('%.' . $scale . 'f', (float)$r); + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/VarParser.php b/extlib/HTMLPurifier/HTMLPurifier/VarParser.php new file mode 100644 index 0000000000..50cba6910d --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/VarParser.php @@ -0,0 +1,198 @@ + self::STRING, + 'istring' => self::ISTRING, + 'text' => self::TEXT, + 'itext' => self::ITEXT, + 'int' => self::INT, + 'float' => self::FLOAT, + 'bool' => self::BOOL, + 'lookup' => self::LOOKUP, + 'list' => self::ALIST, + 'hash' => self::HASH, + 'mixed' => self::MIXED + ); + + /** + * Lookup table of types that are string, and can have aliases or + * allowed value lists. + */ + public static $stringTypes = array( + self::STRING => true, + self::ISTRING => true, + self::TEXT => true, + self::ITEXT => true, + ); + + /** + * Validate a variable according to type. + * It may return NULL as a valid type if $allow_null is true. + * + * @param mixed $var Variable to validate + * @param int $type Type of variable, see HTMLPurifier_VarParser->types + * @param bool $allow_null Whether or not to permit null as a value + * @return string Validated and type-coerced variable + * @throws HTMLPurifier_VarParserException + */ + final public function parse($var, $type, $allow_null = false) + { + if (is_string($type)) { + if (!isset(HTMLPurifier_VarParser::$types[$type])) { + throw new HTMLPurifier_VarParserException("Invalid type '$type'"); + } else { + $type = HTMLPurifier_VarParser::$types[$type]; + } + } + $var = $this->parseImplementation($var, $type, $allow_null); + if ($allow_null && $var === null) { + return null; + } + // These are basic checks, to make sure nothing horribly wrong + // happened in our implementations. + switch ($type) { + case (self::STRING): + case (self::ISTRING): + case (self::TEXT): + case (self::ITEXT): + if (!is_string($var)) { + break; + } + if ($type == self::ISTRING || $type == self::ITEXT) { + $var = strtolower($var); + } + return $var; + case (self::INT): + if (!is_int($var)) { + break; + } + return $var; + case (self::FLOAT): + if (!is_float($var)) { + break; + } + return $var; + case (self::BOOL): + if (!is_bool($var)) { + break; + } + return $var; + case (self::LOOKUP): + case (self::ALIST): + case (self::HASH): + if (!is_array($var)) { + break; + } + if ($type === self::LOOKUP) { + foreach ($var as $k) { + if ($k !== true) { + $this->error('Lookup table contains value other than true'); + } + } + } elseif ($type === self::ALIST) { + $keys = array_keys($var); + if (array_keys($keys) !== $keys) { + $this->error('Indices for list are not uniform'); + } + } + return $var; + case (self::MIXED): + return $var; + default: + $this->errorInconsistent(get_class($this), $type); + } + $this->errorGeneric($var, $type); + } + + /** + * Actually implements the parsing. Base implementation does not + * do anything to $var. Subclasses should overload this! + * @param mixed $var + * @param int $type + * @param bool $allow_null + * @return string + */ + protected function parseImplementation($var, $type, $allow_null) + { + return $var; + } + + /** + * Throws an exception. + * @throws HTMLPurifier_VarParserException + */ + protected function error($msg) + { + throw new HTMLPurifier_VarParserException($msg); + } + + /** + * Throws an inconsistency exception. + * @note This should not ever be called. It would be called if we + * extend the allowed values of HTMLPurifier_VarParser without + * updating subclasses. + * @param string $class + * @param int $type + * @throws HTMLPurifier_Exception + */ + protected function errorInconsistent($class, $type) + { + throw new HTMLPurifier_Exception( + "Inconsistency in $class: " . HTMLPurifier_VarParser::getTypeName($type) . + " not implemented" + ); + } + + /** + * Generic error for if a type didn't work. + * @param mixed $var + * @param int $type + */ + protected function errorGeneric($var, $type) + { + $vtype = gettype($var); + $this->error("Expected type " . HTMLPurifier_VarParser::getTypeName($type) . ", got $vtype"); + } + + /** + * @param int $type + * @return string + */ + public static function getTypeName($type) + { + static $lookup; + if (!$lookup) { + // Lazy load the alternative lookup table + $lookup = array_flip(HTMLPurifier_VarParser::$types); + } + if (!isset($lookup[$type])) { + return 'unknown'; + } + return $lookup[$type]; + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/VarParser/Flexible.php b/extlib/HTMLPurifier/HTMLPurifier/VarParser/Flexible.php new file mode 100644 index 0000000000..b15016c5b2 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/VarParser/Flexible.php @@ -0,0 +1,130 @@ + $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, $type); + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/VarParser/Native.php b/extlib/HTMLPurifier/HTMLPurifier/VarParser/Native.php new file mode 100644 index 0000000000..f11c318efb --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/VarParser/Native.php @@ -0,0 +1,38 @@ +evalExpression($var); + } + + /** + * @param string $expr + * @return mixed + * @throws HTMLPurifier_VarParserException + */ + protected function evalExpression($expr) + { + $var = null; + $result = eval("\$var = $expr;"); + if ($result === false) { + throw new HTMLPurifier_VarParserException("Fatal error in evaluated code"); + } + return $var; + } +} + +// vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/HTMLPurifier/VarParserException.php b/extlib/HTMLPurifier/HTMLPurifier/VarParserException.php new file mode 100644 index 0000000000..5df3414959 --- /dev/null +++ b/extlib/HTMLPurifier/HTMLPurifier/VarParserException.php @@ -0,0 +1,11 @@ +front = $front; + $this->back = $back; + } + + /** + * Creates a zipper from an array, with a hole in the + * 0-index position. + * @param Array to zipper-ify. + * @return Tuple of zipper and element of first position. + */ + static public function fromArray($array) { + $z = new self(array(), array_reverse($array)); + $t = $z->delete(); // delete the "dummy hole" + return array($z, $t); + } + + /** + * Convert zipper back into a normal array, optionally filling in + * the hole with a value. (Usually you should supply a $t, unless you + * are at the end of the array.) + */ + public function toArray($t = NULL) { + $a = $this->front; + if ($t !== NULL) $a[] = $t; + for ($i = count($this->back)-1; $i >= 0; $i--) { + $a[] = $this->back[$i]; + } + return $a; + } + + /** + * Move hole to the next element. + * @param $t Element to fill hole with + * @return Original contents of new hole. + */ + public function next($t) { + if ($t !== NULL) array_push($this->front, $t); + return empty($this->back) ? NULL : array_pop($this->back); + } + + /** + * Iterated hole advancement. + * @param $t Element to fill hole with + * @param $i How many forward to advance hole + * @return Original contents of new hole, i away + */ + public function advance($t, $n) { + for ($i = 0; $i < $n; $i++) { + $t = $this->next($t); + } + return $t; + } + + /** + * Move hole to the previous element + * @param $t Element to fill hole with + * @return Original contents of new hole. + */ + public function prev($t) { + if ($t !== NULL) array_push($this->back, $t); + return empty($this->front) ? NULL : array_pop($this->front); + } + + /** + * Delete contents of current hole, shifting hole to + * next element. + * @return Original contents of new hole. + */ + public function delete() { + return empty($this->back) ? NULL : array_pop($this->back); + } + + /** + * Returns true if we are at the end of the list. + * @return bool + */ + public function done() { + return empty($this->back); + } + + /** + * Insert element before hole. + * @param Element to insert + */ + public function insertBefore($t) { + if ($t !== NULL) array_push($this->front, $t); + } + + /** + * Insert element after hole. + * @param Element to insert + */ + public function insertAfter($t) { + if ($t !== NULL) array_push($this->back, $t); + } + + /** + * Splice in multiple elements at hole. Functional specification + * in terms of array_splice: + * + * $arr1 = $arr; + * $old1 = array_splice($arr1, $i, $delete, $replacement); + * + * list($z, $t) = HTMLPurifier_Zipper::fromArray($arr); + * $t = $z->advance($t, $i); + * list($old2, $t) = $z->splice($t, $delete, $replacement); + * $arr2 = $z->toArray($t); + * + * assert($old1 === $old2); + * assert($arr1 === $arr2); + * + * NB: the absolute index location after this operation is + * *unchanged!* + * + * @param Current contents of hole. + */ + public function splice($t, $delete, $replacement) { + // delete + $old = array(); + $r = $t; + for ($i = $delete; $i > 0; $i--) { + $old[] = $r; + $r = $this->delete(); + } + // insert + for ($i = count($replacement)-1; $i >= 0; $i--) { + $this->insertAfter($r); + $r = $replacement[$i]; + } + return array($old, $r); + } +} diff --git a/extlib/HTMLPurifier/LICENSE b/extlib/HTMLPurifier/LICENSE new file mode 100644 index 0000000000..8c88a20d45 --- /dev/null +++ b/extlib/HTMLPurifier/LICENSE @@ -0,0 +1,504 @@ + GNU LESSER GENERAL PUBLIC LICENSE + Version 2.1, February 1999 + + Copyright (C) 1991, 1999 Free Software Foundation, Inc. + 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA + Everyone is permitted to copy and distribute verbatim copies + of this license document, but changing it is not allowed. + +[This is the first released version of the Lesser GPL. It also counts + as the successor of the GNU Library Public License, version 2, hence + the version number 2.1.] + + Preamble + + The licenses for most software are designed to take away your +freedom to share and change it. By contrast, the GNU General Public +Licenses are intended to guarantee your freedom to share and change +free software--to make sure the software is free for all its users. + + This license, the Lesser General Public License, applies to some +specially designated software packages--typically libraries--of the +Free Software Foundation and other authors who decide to use it. You +can use it too, but we suggest you first think carefully about whether +this license or the ordinary General Public License is the better +strategy to use in any particular case, based on the explanations below. + + When we speak of free software, we are referring to freedom of use, +not price. Our General Public Licenses are designed to make sure that +you have the freedom to distribute copies of free software (and charge +for this service if you wish); that you receive source code or can get +it if you want it; that you can change the software and use pieces of +it in new free programs; and that you are informed that you can do +these things. + + To protect your rights, we need to make restrictions that forbid +distributors to deny you these rights or to ask you to surrender these +rights. These restrictions translate to certain responsibilities for +you if you distribute copies of the library or if you modify it. + + For example, if you distribute copies of the library, whether gratis +or for a fee, you must give the recipients all the rights that we gave +you. You must make sure that they, too, receive or can get the source +code. If you link other code with the library, you must provide +complete object files to the recipients, so that they can relink them +with the library after making changes to the library and recompiling +it. And you must show them these terms so they know their rights. + + We protect your rights with a two-step method: (1) we copyright the +library, and (2) we offer you this license, which gives you legal +permission to copy, distribute and/or modify the library. + + To protect each distributor, we want to make it very clear that +there is no warranty for the free library. Also, if the library is +modified by someone else and passed on, the recipients should know +that what they have is not the original version, so that the original +author's reputation will not be affected by problems that might be +introduced by others. + + Finally, software patents pose a constant threat to the existence of +any free program. We wish to make sure that a company cannot +effectively restrict the users of a free program by obtaining a +restrictive license from a patent holder. Therefore, we insist that +any patent license obtained for a version of the library must be +consistent with the full freedom of use specified in this license. + + Most GNU software, including some libraries, is covered by the +ordinary GNU General Public License. This license, the GNU Lesser +General Public License, applies to certain designated libraries, and +is quite different from the ordinary General Public License. We use +this license for certain libraries in order to permit linking those +libraries into non-free programs. + + When a program is linked with a library, whether statically or using +a shared library, the combination of the two is legally speaking a +combined work, a derivative of the original library. The ordinary +General Public License therefore permits such linking only if the +entire combination fits its criteria of freedom. The Lesser General +Public License permits more lax criteria for linking other code with +the library. + + We call this license the "Lesser" General Public License because it +does Less to protect the user's freedom than the ordinary General +Public License. It also provides other free software developers Less +of an advantage over competing non-free programs. These disadvantages +are the reason we use the ordinary General Public License for many +libraries. However, the Lesser license provides advantages in certain +special circumstances. + + For example, on rare occasions, there may be a special need to +encourage the widest possible use of a certain library, so that it becomes +a de-facto standard. To achieve this, non-free programs must be +allowed to use the library. A more frequent case is that a free +library does the same job as widely used non-free libraries. In this +case, there is little to gain by limiting the free library to free +software only, so we use the Lesser General Public License. + + In other cases, permission to use a particular library in non-free +programs enables a greater number of people to use a large body of +free software. For example, permission to use the GNU C Library in +non-free programs enables many more people to use the whole GNU +operating system, as well as its variant, the GNU/Linux operating +system. + + Although the Lesser General Public License is Less protective of the +users' freedom, it does ensure that the user of a program that is +linked with the Library has the freedom and the wherewithal to run +that program using a modified version of the Library. + + The precise terms and conditions for copying, distribution and +modification follow. Pay close attention to the difference between a +"work based on the library" and a "work that uses the library". The +former contains code derived from the library, whereas the latter must +be combined with the library in order to run. + + GNU LESSER GENERAL PUBLIC LICENSE + TERMS AND CONDITIONS FOR COPYING, DISTRIBUTION AND MODIFICATION + + 0. This License Agreement applies to any software library or other +program which contains a notice placed by the copyright holder or +other authorized party saying it may be distributed under the terms of +this Lesser General Public License (also called "this License"). +Each licensee is addressed as "you". + + A "library" means a collection of software functions and/or data +prepared so as to be conveniently linked with application programs +(which use some of those functions and data) to form executables. + + The "Library", below, refers to any such software library or work +which has been distributed under these terms. A "work based on the +Library" means either the Library or any derivative work under +copyright law: that is to say, a work containing the Library or a +portion of it, either verbatim or with modifications and/or translated +straightforwardly into another language. (Hereinafter, translation is +included without limitation in the term "modification".) + + "Source code" for a work means the preferred form of the work for +making modifications to it. For a library, complete source code means +all the source code for all modules it contains, plus any associated +interface definition files, plus the scripts used to control compilation +and installation of the library. + + Activities other than copying, distribution and modification are not +covered by this License; they are outside its scope. The act of +running a program using the Library is not restricted, and output from +such a program is covered only if its contents constitute a work based +on the Library (independent of the use of the Library in a tool for +writing it). Whether that is true depends on what the Library does +and what the program that uses the Library does. + + 1. You may copy and distribute verbatim copies of the Library's +complete source code as you receive it, in any medium, provided that +you conspicuously and appropriately publish on each copy an +appropriate copyright notice and disclaimer of warranty; keep intact +all the notices that refer to this License and to the absence of any +warranty; and distribute a copy of this License along with the +Library. + + You may charge a fee for the physical act of transferring a copy, +and you may at your option offer warranty protection in exchange for a +fee. + + 2. You may modify your copy or copies of the Library or any portion +of it, thus forming a work based on the Library, and copy and +distribute such modifications or work under the terms of Section 1 +above, provided that you also meet all of these conditions: + + a) The modified work must itself be a software library. + + b) You must cause the files modified to carry prominent notices + stating that you changed the files and the date of any change. + + c) You must cause the whole of the work to be licensed at no + charge to all third parties under the terms of this License. + + d) If a facility in the modified Library refers to a function or a + table of data to be supplied by an application program that uses + the facility, other than as an argument passed when the facility + is invoked, then you must make a good faith effort to ensure that, + in the event an application does not supply such function or + table, the facility still operates, and performs whatever part of + its purpose remains meaningful. + + (For example, a function in a library to compute square roots has + a purpose that is entirely well-defined independent of the + application. Therefore, Subsection 2d requires that any + application-supplied function or table used by this function must + be optional: if the application does not supply it, the square + root function must still compute square roots.) + +These requirements apply to the modified work as a whole. If +identifiable sections of that work are not derived from the Library, +and can be reasonably considered independent and separate works in +themselves, then this License, and its terms, do not apply to those +sections when you distribute them as separate works. But when you +distribute the same sections as part of a whole which is a work based +on the Library, the distribution of the whole must be on the terms of +this License, whose permissions for other licensees extend to the +entire whole, and thus to each and every part regardless of who wrote +it. + +Thus, it is not the intent of this section to claim rights or contest +your rights to work written entirely by you; rather, the intent is to +exercise the right to control the distribution of derivative or +collective works based on the Library. + +In addition, mere aggregation of another work not based on the Library +with the Library (or with a work based on the Library) on a volume of +a storage or distribution medium does not bring the other work under +the scope of this License. + + 3. You may opt to apply the terms of the ordinary GNU General Public +License instead of this License to a given copy of the Library. To do +this, you must alter all the notices that refer to this License, so +that they refer to the ordinary GNU General Public License, version 2, +instead of to this License. (If a newer version than version 2 of the +ordinary GNU General Public License has appeared, then you can specify +that version instead if you wish.) Do not make any other change in +these notices. + + Once this change is made in a given copy, it is irreversible for +that copy, so the ordinary GNU General Public License applies to all +subsequent copies and derivative works made from that copy. + + This option is useful when you wish to copy part of the code of +the Library into a program that is not a library. + + 4. You may copy and distribute the Library (or a portion or +derivative of it, under Section 2) in object code or executable form +under the terms of Sections 1 and 2 above provided that you accompany +it with the complete corresponding machine-readable source code, which +must be distributed under the terms of Sections 1 and 2 above on a +medium customarily used for software interchange. + + If distribution of object code is made by offering access to copy +from a designated place, then offering equivalent access to copy the +source code from the same place satisfies the requirement to +distribute the source code, even though third parties are not +compelled to copy the source along with the object code. + + 5. A program that contains no derivative of any portion of the +Library, but is designed to work with the Library by being compiled or +linked with it, is called a "work that uses the Library". Such a +work, in isolation, is not a derivative work of the Library, and +therefore falls outside the scope of this License. + + However, linking a "work that uses the Library" with the Library +creates an executable that is a derivative of the Library (because it +contains portions of the Library), rather than a "work that uses the +library". The executable is therefore covered by this License. +Section 6 states terms for distribution of such executables. + + When a "work that uses the Library" uses material from a header file +that is part of the Library, the object code for the work may be a +derivative work of the Library even though the source code is not. +Whether this is true is especially significant if the work can be +linked without the Library, or if the work is itself a library. The +threshold for this to be true is not precisely defined by law. + + If such an object file uses only numerical parameters, data +structure layouts and accessors, and small macros and small inline +functions (ten lines or less in length), then the use of the object +file is unrestricted, regardless of whether it is legally a derivative +work. (Executables containing this object code plus portions of the +Library will still fall under Section 6.) + + Otherwise, if the work is a derivative of the Library, you may +distribute the object code for the work under the terms of Section 6. +Any executables containing that work also fall under Section 6, +whether or not they are linked directly with the Library itself. + + 6. As an exception to the Sections above, you may also combine or +link a "work that uses the Library" with the Library to produce a +work containing portions of the Library, and distribute that work +under terms of your choice, provided that the terms permit +modification of the work for the customer's own use and reverse +engineering for debugging such modifications. + + You must give prominent notice with each copy of the work that the +Library is used in it and that the Library and its use are covered by +this License. You must supply a copy of this License. If the work +during execution displays copyright notices, you must include the +copyright notice for the Library among them, as well as a reference +directing the user to the copy of this License. Also, you must do one +of these things: + + a) Accompany the work with the complete corresponding + machine-readable source code for the Library including whatever + changes were used in the work (which must be distributed under + Sections 1 and 2 above); and, if the work is an executable linked + with the Library, with the complete machine-readable "work that + uses the Library", as object code and/or source code, so that the + user can modify the Library and then relink to produce a modified + executable containing the modified Library. (It is understood + that the user who changes the contents of definitions files in the + Library will not necessarily be able to recompile the application + to use the modified definitions.) + + b) Use a suitable shared library mechanism for linking with the + Library. A suitable mechanism is one that (1) uses at run time a + copy of the library already present on the user's computer system, + rather than copying library functions into the executable, and (2) + will operate properly with a modified version of the library, if + the user installs one, as long as the modified version is + interface-compatible with the version that the work was made with. + + c) Accompany the work with a written offer, valid for at + least three years, to give the same user the materials + specified in Subsection 6a, above, for a charge no more + than the cost of performing this distribution. + + d) If distribution of the work is made by offering access to copy + from a designated place, offer equivalent access to copy the above + specified materials from the same place. + + e) Verify that the user has already received a copy of these + materials or that you have already sent this user a copy. + + For an executable, the required form of the "work that uses the +Library" must include any data and utility programs needed for +reproducing the executable from it. However, as a special exception, +the materials to be distributed need not include anything that is +normally distributed (in either source or binary form) with the major +components (compiler, kernel, and so on) of the operating system on +which the executable runs, unless that component itself accompanies +the executable. + + It may happen that this requirement contradicts the license +restrictions of other proprietary libraries that do not normally +accompany the operating system. Such a contradiction means you cannot +use both them and the Library together in an executable that you +distribute. + + 7. You may place library facilities that are a work based on the +Library side-by-side in a single library together with other library +facilities not covered by this License, and distribute such a combined +library, provided that the separate distribution of the work based on +the Library and of the other library facilities is otherwise +permitted, and provided that you do these two things: + + a) Accompany the combined library with a copy of the same work + based on the Library, uncombined with any other library + facilities. This must be distributed under the terms of the + Sections above. + + b) Give prominent notice with the combined library of the fact + that part of it is a work based on the Library, and explaining + where to find the accompanying uncombined form of the same work. + + 8. You may not copy, modify, sublicense, link with, or distribute +the Library except as expressly provided under this License. Any +attempt otherwise to copy, modify, sublicense, link with, or +distribute the Library is void, and will automatically terminate your +rights under this License. However, parties who have received copies, +or rights, from you under this License will not have their licenses +terminated so long as such parties remain in full compliance. + + 9. You are not required to accept this License, since you have not +signed it. However, nothing else grants you permission to modify or +distribute the Library or its derivative works. These actions are +prohibited by law if you do not accept this License. Therefore, by +modifying or distributing the Library (or any work based on the +Library), you indicate your acceptance of this License to do so, and +all its terms and conditions for copying, distributing or modifying +the Library or works based on it. + + 10. Each time you redistribute the Library (or any work based on the +Library), the recipient automatically receives a license from the +original licensor to copy, distribute, link with or modify the Library +subject to these terms and conditions. You may not impose any further +restrictions on the recipients' exercise of the rights granted herein. +You are not responsible for enforcing compliance by third parties with +this License. + + 11. If, as a consequence of a court judgment or allegation of patent +infringement or for any other reason (not limited to patent issues), +conditions are imposed on you (whether by court order, agreement or +otherwise) that contradict the conditions of this License, they do not +excuse you from the conditions of this License. If you cannot +distribute so as to satisfy simultaneously your obligations under this +License and any other pertinent obligations, then as a consequence you +may not distribute the Library at all. For example, if a patent +license would not permit royalty-free redistribution of the Library by +all those who receive copies directly or indirectly through you, then +the only way you could satisfy both it and this License would be to +refrain entirely from distribution of the Library. + +If any portion of this section is held invalid or unenforceable under any +particular circumstance, the balance of the section is intended to apply, +and the section as a whole is intended to apply in other circumstances. + +It is not the purpose of this section to induce you to infringe any +patents or other property right claims or to contest validity of any +such claims; this section has the sole purpose of protecting the +integrity of the free software distribution system which is +implemented by public license practices. Many people have made +generous contributions to the wide range of software distributed +through that system in reliance on consistent application of that +system; it is up to the author/donor to decide if he or she is willing +to distribute software through any other system and a licensee cannot +impose that choice. + +This section is intended to make thoroughly clear what is believed to +be a consequence of the rest of this License. + + 12. If the distribution and/or use of the Library is restricted in +certain countries either by patents or by copyrighted interfaces, the +original copyright holder who places the Library under this License may add +an explicit geographical distribution limitation excluding those countries, +so that distribution is permitted only in or among countries not thus +excluded. In such case, this License incorporates the limitation as if +written in the body of this License. + + 13. The Free Software Foundation may publish revised and/or new +versions of the Lesser General Public License from time to time. +Such new versions will be similar in spirit to the present version, +but may differ in detail to address new problems or concerns. + +Each version is given a distinguishing version number. If the Library +specifies a version number of this License which applies to it and +"any later version", you have the option of following the terms and +conditions either of that version or of any later version published by +the Free Software Foundation. If the Library does not specify a +license version number, you may choose any version ever published by +the Free Software Foundation. + + 14. If you wish to incorporate parts of the Library into other free +programs whose distribution conditions are incompatible with these, +write to the author to ask for permission. For software which is +copyrighted by the Free Software Foundation, write to the Free +Software Foundation; we sometimes make exceptions for this. Our +decision will be guided by the two goals of preserving the free status +of all derivatives of our free software and of promoting the sharing +and reuse of software generally. + + NO WARRANTY + + 15. BECAUSE THE LIBRARY IS LICENSED FREE OF CHARGE, THERE IS NO +WARRANTY FOR THE LIBRARY, TO THE EXTENT PERMITTED BY APPLICABLE LAW. +EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT HOLDERS AND/OR +OTHER PARTIES PROVIDE THE LIBRARY "AS IS" WITHOUT WARRANTY OF ANY +KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, THE +IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR +PURPOSE. THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE +LIBRARY IS WITH YOU. SHOULD THE LIBRARY PROVE DEFECTIVE, YOU ASSUME +THE COST OF ALL NECESSARY SERVICING, REPAIR OR CORRECTION. + + 16. IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN +WRITING WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MAY MODIFY +AND/OR REDISTRIBUTE THE LIBRARY AS PERMITTED ABOVE, BE LIABLE TO YOU +FOR DAMAGES, INCLUDING ANY GENERAL, SPECIAL, INCIDENTAL OR +CONSEQUENTIAL DAMAGES ARISING OUT OF THE USE OR INABILITY TO USE THE +LIBRARY (INCLUDING BUT NOT LIMITED TO LOSS OF DATA OR DATA BEING +RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD PARTIES OR A +FAILURE OF THE LIBRARY TO OPERATE WITH ANY OTHER SOFTWARE), EVEN IF +SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF SUCH +DAMAGES. + + END OF TERMS AND CONDITIONS + + How to Apply These Terms to Your New Libraries + + If you develop a new library, and you want it to be of the greatest +possible use to the public, we recommend making it free software that +everyone can redistribute and change. You can do so by permitting +redistribution under these terms (or, alternatively, under the terms of the +ordinary General Public License). + + To apply these terms, attach the following notices to the library. It is +safest to attach them to the start of each source file to most effectively +convey the exclusion of warranty; and each file should have at least the +"copyright" line and a pointer to where the full notice is found. + + + Copyright (C) + + This library is free software; you can redistribute it and/or + modify it under the terms of the GNU Lesser General Public + License as published by the Free Software Foundation; either + version 2.1 of the License, or (at your option) any later version. + + This library is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + Lesser General Public License for more details. + + You should have received a copy of the GNU Lesser General Public + License along with this library; if not, write to the Free Software + Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA + +Also add information on how to contact you by electronic and paper mail. + +You should also get your employer (if you work as a programmer) or your +school, if any, to sign a "copyright disclaimer" for the library, if +necessary. Here is a sample; alter the names: + + Yoyodyne, Inc., hereby disclaims all copyright interest in the + library `Frob' (a library for tweaking knobs) written by James Random Hacker. + + , 1 April 1990 + Ty Coon, President of Vice + +That's all there is to it! + + vim: et sw=4 sts=4 diff --git a/extlib/HTMLPurifier/VERSION b/extlib/HTMLPurifier/VERSION new file mode 100644 index 0000000000..1163055e28 --- /dev/null +++ b/extlib/HTMLPurifier/VERSION @@ -0,0 +1 @@ +4.7.0 \ No newline at end of file diff --git a/extlib/htmLawed/htmLawed.php b/extlib/htmLawed/htmLawed.php deleted file mode 100755 index b10b8f257e..0000000000 --- a/extlib/htmLawed/htmLawed.php +++ /dev/null @@ -1,723 +0,0 @@ -1, 'abbr'=>1, 'acronym'=>1, 'address'=>1, 'applet'=>1, 'area'=>1, 'b'=>1, 'bdo'=>1, 'big'=>1, 'blockquote'=>1, 'br'=>1, 'button'=>1, 'caption'=>1, 'center'=>1, 'cite'=>1, 'code'=>1, 'col'=>1, 'colgroup'=>1, 'dd'=>1, 'del'=>1, 'dfn'=>1, 'dir'=>1, 'div'=>1, 'dl'=>1, 'dt'=>1, 'em'=>1, 'embed'=>1, 'fieldset'=>1, 'font'=>1, 'form'=>1, 'h1'=>1, 'h2'=>1, 'h3'=>1, 'h4'=>1, 'h5'=>1, 'h6'=>1, 'hr'=>1, 'i'=>1, 'iframe'=>1, 'img'=>1, 'input'=>1, 'ins'=>1, 'isindex'=>1, 'kbd'=>1, 'label'=>1, 'legend'=>1, 'li'=>1, 'map'=>1, 'menu'=>1, 'noscript'=>1, 'object'=>1, 'ol'=>1, 'optgroup'=>1, 'option'=>1, 'p'=>1, 'param'=>1, 'pre'=>1, 'q'=>1, 'rb'=>1, 'rbc'=>1, 'rp'=>1, 'rt'=>1, 'rtc'=>1, 'ruby'=>1, 's'=>1, 'samp'=>1, 'script'=>1, 'select'=>1, 'small'=>1, 'span'=>1, 'strike'=>1, 'strong'=>1, 'sub'=>1, 'sup'=>1, 'table'=>1, 'tbody'=>1, 'td'=>1, 'textarea'=>1, 'tfoot'=>1, 'th'=>1, 'thead'=>1, 'tr'=>1, 'tt'=>1, 'u'=>1, 'ul'=>1, 'var'=>1); // 86/deprecated+embed+ruby -if(!empty($C['safe'])){ - unset($e['applet'], $e['embed'], $e['iframe'], $e['object'], $e['script']); -} -$x = !empty($C['elements']) ? str_replace(array("\n", "\r", "\t", ' '), '', $C['elements']) : '*'; -if($x == '-*'){$e = array();} -elseif(strpos($x, '*') === false){$e = array_flip(explode(',', $x));} -else{ - if(isset($x[1])){ - preg_match_all('`(?:^|-|\+)[^\-+]+?(?=-|\+|$)`', $x, $m, PREG_SET_ORDER); - for($i=count($m); --$i>=0;){$m[$i] = $m[$i][0];} - foreach($m as $v){ - if($v[0] == '+'){$e[substr($v, 1)] = 1;} - if($v[0] == '-' && isset($e[($v = substr($v, 1))]) && !in_array('+'. $v, $m)){unset($e[$v]);} - } - } -} -$C['elements'] =& $e; -// config attrs -$x = !empty($C['deny_attribute']) ? str_replace(array("\n", "\r", "\t", ' '), '', $C['deny_attribute']) : ''; -$x = array_flip((isset($x[0]) && $x[0] == '*') ? explode('-', $x) : explode(',', $x. (!empty($C['safe']) ? ',on*' : ''))); -if(isset($x['on*'])){ - unset($x['on*']); - $x += array('onblur'=>1, 'onchange'=>1, 'onclick'=>1, 'ondblclick'=>1, 'onfocus'=>1, 'onkeydown'=>1, 'onkeypress'=>1, 'onkeyup'=>1, 'onmousedown'=>1, 'onmousemove'=>1, 'onmouseout'=>1, 'onmouseover'=>1, 'onmouseup'=>1, 'onreset'=>1, 'onselect'=>1, 'onsubmit'=>1); -} -$C['deny_attribute'] = $x; -// config URL -$x = (isset($C['schemes'][2]) && strpos($C['schemes'], ':')) ? strtolower($C['schemes']) : 'href: aim, feed, file, ftp, gopher, http, https, irc, mailto, news, nntp, sftp, ssh, telnet; *:file, http, https'; -$C['schemes'] = array(); -foreach(explode(';', str_replace(array(' ', "\t", "\r", "\n"), '', $x)) as $v){ - $x = $x2 = null; list($x, $x2) = explode(':', $v, 2); - if($x2){$C['schemes'][$x] = array_flip(explode(',', $x2));} -} -if(!isset($C['schemes']['*'])){$C['schemes']['*'] = array('file'=>1, 'http'=>1, 'https'=>1,);} -if(!empty($C['safe']) && empty($C['schemes']['style'])){$C['schemes']['style'] = array('!'=>1);} -$C['abs_url'] = isset($C['abs_url']) ? $C['abs_url'] : 0; -if(!isset($C['base_url']) or !preg_match('`^[a-zA-Z\d.+\-]+://[^/]+/(.+?/)?$`', $C['base_url'])){ - $C['base_url'] = $C['abs_url'] = 0; -} -// config rest -$C['and_mark'] = empty($C['and_mark']) ? 0 : 1; -$C['anti_link_spam'] = (isset($C['anti_link_spam']) && is_array($C['anti_link_spam']) && count($C['anti_link_spam']) == 2 && (empty($C['anti_link_spam'][0]) or hl_regex($C['anti_link_spam'][0])) && (empty($C['anti_link_spam'][1]) or hl_regex($C['anti_link_spam'][1]))) ? $C['anti_link_spam'] : 0; -$C['anti_mail_spam'] = isset($C['anti_mail_spam']) ? $C['anti_mail_spam'] : 0; -$C['balance'] = isset($C['balance']) ? (bool)$C['balance'] : 1; -$C['cdata'] = isset($C['cdata']) ? $C['cdata'] : (empty($C['safe']) ? 3 : 0); -$C['clean_ms_char'] = empty($C['clean_ms_char']) ? 0 : $C['clean_ms_char']; -$C['comment'] = isset($C['comment']) ? $C['comment'] : (empty($C['safe']) ? 3 : 0); -$C['css_expression'] = empty($C['css_expression']) ? 0 : 1; -$C['direct_list_nest'] = empty($C['direct_list_nest']) ? 0 : 1; -$C['hexdec_entity'] = isset($C['hexdec_entity']) ? $C['hexdec_entity'] : 1; -$C['hook'] = (!empty($C['hook']) && function_exists($C['hook'])) ? $C['hook'] : 0; -$C['hook_tag'] = (!empty($C['hook_tag']) && function_exists($C['hook_tag'])) ? $C['hook_tag'] : 0; -$C['keep_bad'] = isset($C['keep_bad']) ? $C['keep_bad'] : 6; -$C['lc_std_val'] = isset($C['lc_std_val']) ? (bool)$C['lc_std_val'] : 1; -$C['make_tag_strict'] = isset($C['make_tag_strict']) ? $C['make_tag_strict'] : 1; -$C['named_entity'] = isset($C['named_entity']) ? (bool)$C['named_entity'] : 1; -$C['no_deprecated_attr'] = isset($C['no_deprecated_attr']) ? $C['no_deprecated_attr'] : 1; -$C['parent'] = isset($C['parent'][0]) ? strtolower($C['parent']) : 'body'; -$C['show_setting'] = !empty($C['show_setting']) ? $C['show_setting'] : 0; -$C['style_pass'] = empty($C['style_pass']) ? 0 : 1; -$C['tidy'] = empty($C['tidy']) ? 0 : $C['tidy']; -$C['unique_ids'] = isset($C['unique_ids']) ? $C['unique_ids'] : 1; -$C['xml:lang'] = isset($C['xml:lang']) ? $C['xml:lang'] : 0; - -if(isset($GLOBALS['C'])){$reC = $GLOBALS['C'];} -$GLOBALS['C'] = $C; -$S = is_array($S) ? $S : hl_spec($S); -if(isset($GLOBALS['S'])){$reS = $GLOBALS['S'];} -$GLOBALS['S'] = $S; - -$t = preg_replace('`[\x00-\x08\x0b-\x0c\x0e-\x1f]`', '', $t); -if($C['clean_ms_char']){ - $x = array("\x7f"=>'', "\x80"=>'€', "\x81"=>'', "\x83"=>'ƒ', "\x85"=>'…', "\x86"=>'†', "\x87"=>'‡', "\x88"=>'ˆ', "\x89"=>'‰', "\x8a"=>'Š', "\x8b"=>'‹', "\x8c"=>'Œ', "\x8d"=>'', "\x8e"=>'Ž', "\x8f"=>'', "\x90"=>'', "\x95"=>'•', "\x96"=>'–', "\x97"=>'—', "\x98"=>'˜', "\x99"=>'™', "\x9a"=>'š', "\x9b"=>'›', "\x9c"=>'œ', "\x9d"=>'', "\x9e"=>'ž', "\x9f"=>'Ÿ'); - $x = $x + ($C['clean_ms_char'] == 1 ? array("\x82"=>'‚', "\x84"=>'„', "\x91"=>'‘', "\x92"=>'’', "\x93"=>'“', "\x94"=>'”') : array("\x82"=>'\'', "\x84"=>'"', "\x91"=>'\'', "\x92"=>'\'', "\x93"=>'"', "\x94"=>'"')); - $t = strtr($t, $x); -} -if($C['cdata'] or $C['comment']){$t = preg_replace_callback('``sm', 'hl_cmtcd', $t);} -$t = preg_replace_callback('`&([A-Za-z][A-Za-z0-9]{1,30}|#(?:[0-9]{1,8}|[Xx][0-9A-Fa-f]{1,7}));`', 'hl_ent', str_replace('&', '&', $t)); -if($C['unique_ids'] && !isset($GLOBALS['hl_Ids'])){$GLOBALS['hl_Ids'] = array();} -if($C['hook']){$t = $C['hook']($t, $C, $S);} -if($C['show_setting'] && preg_match('`^[a-z][a-z0-9_]*$`i', $C['show_setting'])){ - $GLOBALS[$C['show_setting']] = array('config'=>$C, 'spec'=>$S, 'time'=>microtime()); -} -// main -$t = preg_replace_callback('`<(?:(?:\s|$)|(?:[^>]*(?:>|$)))|>`m', 'hl_tag', $t); -$t = $C['balance'] ? hl_bal($t, $C['keep_bad'], $C['parent']) : $t; -$t = (($C['cdata'] or $C['comment']) && strpos($t, "\x01") !== false) ? str_replace(array("\x01", "\x02", "\x03", "\x04", "\x05"), array('', '', '&', '<', '>'), $t) : $t; -$t = $C['tidy'] ? hl_tidy($t, $C['tidy'], $C['parent']) : $t; -unset($C, $e); -if(isset($reC)){$GLOBALS['C'] = $reC;} -if(isset($reS)){$GLOBALS['S'] = $reS;} -return $t; -// eof -} - -function hl_attrval($t, $p){ -// check attr val against $S -$o = 1; $l = strlen($t); -foreach($p as $k=>$v){ - switch($k){ - case 'maxlen':if($l > $v){$o = 0;} - break; case 'minlen': if($l < $v){$o = 0;} - break; case 'maxval': if((float)($t) > $v){$o = 0;} - break; case 'minval': if((float)($t) < $v){$o = 0;} - break; case 'match': if(!preg_match($v, $t)){$o = 0;} - break; case 'nomatch': if(preg_match($v, $t)){$o = 0;} - break; case 'oneof': - $m = 0; - foreach(explode('|', $v) as $n){if($t == $n){$m = 1; break;}} - $o = $m; - break; case 'noneof': - $m = 1; - foreach(explode('|', $v) as $n){if($t == $n){$m = 0; break;}} - $o = $m; - break; default: - break; - } - if(!$o){break;} -} -return ($o ? $t : (isset($p['default']) ? $p['default'] : 0)); -// eof -} - -function hl_bal($t, $do=1, $in='div'){ -// balance tags -// by content -$cB = array('blockquote'=>1, 'form'=>1, 'map'=>1, 'noscript'=>1); // Block -$cE = array('area'=>1, 'br'=>1, 'col'=>1, 'embed'=>1, 'hr'=>1, 'img'=>1, 'input'=>1, 'isindex'=>1, 'param'=>1); // Empty -$cF = array('button'=>1, 'del'=>1, 'div'=>1, 'dd'=>1, 'fieldset'=>1, 'iframe'=>1, 'ins'=>1, 'li'=>1, 'noscript'=>1, 'object'=>1, 'td'=>1, 'th'=>1); // Flow; later context-wise dynamic move of ins & del to $cI -$cI = array('a'=>1, 'abbr'=>1, 'acronym'=>1, 'address'=>1, 'b'=>1, 'bdo'=>1, 'big'=>1, 'caption'=>1, 'cite'=>1, 'code'=>1, 'dfn'=>1, 'dt'=>1, 'em'=>1, 'font'=>1, 'h1'=>1, 'h2'=>1, 'h3'=>1, 'h4'=>1, 'h5'=>1, 'h6'=>1, 'i'=>1, 'kbd'=>1, 'label'=>1, 'legend'=>1, 'p'=>1, 'pre'=>1, 'q'=>1, 'rb'=>1, 'rt'=>1, 's'=>1, 'samp'=>1, 'small'=>1, 'span'=>1, 'strike'=>1, 'strong'=>1, 'sub'=>1, 'sup'=>1, 'tt'=>1, 'u'=>1, 'var'=>1); // Inline -$cN = array('a'=>array('a'=>1), 'button'=>array('a'=>1, 'button'=>1, 'fieldset'=>1, 'form'=>1, 'iframe'=>1, 'input'=>1, 'label'=>1, 'select'=>1, 'textarea'=>1), 'fieldset'=>array('fieldset'=>1), 'form'=>array('form'=>1), 'label'=>array('label'=>1), 'noscript'=>array('script'=>1), 'pre'=>array('big'=>1, 'font'=>1, 'img'=>1, 'object'=>1, 'script'=>1, 'small'=>1, 'sub'=>1, 'sup'=>1), 'rb'=>array('ruby'=>1), 'rt'=>array('ruby'=>1)); // Illegal -$cN2 = array_keys($cN); -$cR = array('blockquote'=>1, 'dir'=>1, 'dl'=>1, 'form'=>1, 'map'=>1, 'menu'=>1, 'noscript'=>1, 'ol'=>1, 'optgroup'=>1, 'rbc'=>1, 'rtc'=>1, 'ruby'=>1, 'select'=>1, 'table'=>1, 'tbody'=>1, 'tfoot'=>1, 'thead'=>1, 'tr'=>1, 'ul'=>1); -$cS = array('colgroup'=>array('col'=>1), 'dir'=>array('li'=>1), 'dl'=>array('dd'=>1, 'dt'=>1), 'menu'=>array('li'=>1), 'ol'=>array('li'=>1), 'optgroup'=>array('option'=>1), 'option'=>array('#pcdata'=>1), 'rbc'=>array('rb'=>1), 'rp'=>array('#pcdata'=>1), 'rtc'=>array('rt'=>1), 'ruby'=>array('rb'=>1, 'rbc'=>1, 'rp'=>1, 'rt'=>1, 'rtc'=>1), 'select'=>array('optgroup'=>1, 'option'=>1), 'script'=>array('#pcdata'=>1), 'table'=>array('caption'=>1, 'col'=>1, 'colgroup'=>1, 'tfoot'=>1, 'tbody'=>1, 'tr'=>1, 'thead'=>1), 'tbody'=>array('tr'=>1), 'tfoot'=>array('tr'=>1), 'textarea'=>array('#pcdata'=>1), 'thead'=>array('tr'=>1), 'tr'=>array('td'=>1, 'th'=>1), 'ul'=>array('li'=>1)); // Specific - immediate parent-child -if($GLOBALS['C']['direct_list_nest']){$cS['ol'] = $cS['ul'] += array('ol'=>1, 'ul'=>1);} -$cO = array('address'=>array('p'=>1), 'applet'=>array('param'=>1), 'blockquote'=>array('script'=>1), 'fieldset'=>array('legend'=>1, '#pcdata'=>1), 'form'=>array('script'=>1), 'map'=>array('area'=>1), 'object'=>array('param'=>1, 'embed'=>1)); // Other -$cT = array('colgroup'=>1, 'dd'=>1, 'dt'=>1, 'li'=>1, 'option'=>1, 'p'=>1, 'td'=>1, 'tfoot'=>1, 'th'=>1, 'thead'=>1, 'tr'=>1); // Omitable closing -// block/inline type; ins & del both type; #pcdata: text -$eB = array('address'=>1, 'blockquote'=>1, 'center'=>1, 'del'=>1, 'dir'=>1, 'dl'=>1, 'div'=>1, 'fieldset'=>1, 'form'=>1, 'ins'=>1, 'h1'=>1, 'h2'=>1, 'h3'=>1, 'h4'=>1, 'h5'=>1, 'h6'=>1, 'hr'=>1, 'isindex'=>1, 'menu'=>1, 'noscript'=>1, 'ol'=>1, 'p'=>1, 'pre'=>1, 'table'=>1, 'ul'=>1); -$eI = array('#pcdata'=>1, 'a'=>1, 'abbr'=>1, 'acronym'=>1, 'applet'=>1, 'b'=>1, 'bdo'=>1, 'big'=>1, 'br'=>1, 'button'=>1, 'cite'=>1, 'code'=>1, 'del'=>1, 'dfn'=>1, 'em'=>1, 'embed'=>1, 'font'=>1, 'i'=>1, 'iframe'=>1, 'img'=>1, 'input'=>1, 'ins'=>1, 'kbd'=>1, 'label'=>1, 'map'=>1, 'object'=>1, 'q'=>1, 'ruby'=>1, 's'=>1, 'samp'=>1, 'select'=>1, 'script'=>1, 'small'=>1, 'span'=>1, 'strike'=>1, 'strong'=>1, 'sub'=>1, 'sup'=>1, 'textarea'=>1, 'tt'=>1, 'u'=>1, 'var'=>1); -$eN = array('a'=>1, 'big'=>1, 'button'=>1, 'fieldset'=>1, 'font'=>1, 'form'=>1, 'iframe'=>1, 'img'=>1, 'input'=>1, 'label'=>1, 'object'=>1, 'ruby'=>1, 'script'=>1, 'select'=>1, 'small'=>1, 'sub'=>1, 'sup'=>1, 'textarea'=>1); // Exclude from specific ele; $cN values -$eO = array('area'=>1, 'caption'=>1, 'col'=>1, 'colgroup'=>1, 'dd'=>1, 'dt'=>1, 'legend'=>1, 'li'=>1, 'optgroup'=>1, 'option'=>1, 'param'=>1, 'rb'=>1, 'rbc'=>1, 'rp'=>1, 'rt'=>1, 'rtc'=>1, 'script'=>1, 'tbody'=>1, 'td'=>1, 'tfoot'=>1, 'thead'=>1, 'th'=>1, 'tr'=>1); // Missing in $eB & $eI -$eF = $eB + $eI; - -// $in sets allowed child -$in = ((isset($eF[$in]) && $in != '#pcdata') or isset($eO[$in])) ? $in : 'div'; -if(isset($cE[$in])){ - return (!$do ? '' : str_replace(array('<', '>'), array('<', '>'), $t)); -} -if(isset($cS[$in])){$inOk = $cS[$in];} -elseif(isset($cI[$in])){$inOk = $eI; $cI['del'] = 1; $cI['ins'] = 1;} -elseif(isset($cF[$in])){$inOk = $eF; unset($cI['del'], $cI['ins']);} -elseif(isset($cB[$in])){$inOk = $eB; unset($cI['del'], $cI['ins']);} -if(isset($cO[$in])){$inOk = $inOk + $cO[$in];} -if(isset($cN[$in])){$inOk = array_diff_assoc($inOk, $cN[$in]);} - -$t = explode('<', $t); -$ok = $q = array(); // $q seq list of open non-empty ele -ob_start(); - -for($i=-1, $ci=count($t); ++$i<$ci;){ - // allowed $ok in parent $p - if($ql = count($q)){ - $p = array_pop($q); - $q[] = $p; - if(isset($cS[$p])){$ok = $cS[$p];} - elseif(isset($cI[$p])){$ok = $eI; $cI['del'] = 1; $cI['ins'] = 1;} - elseif(isset($cF[$p])){$ok = $eF; unset($cI['del'], $cI['ins']);} - elseif(isset($cB[$p])){$ok = $eB; unset($cI['del'], $cI['ins']);} - if(isset($cO[$p])){$ok = $ok + $cO[$p];} - if(isset($cN[$p])){$ok = array_diff_assoc($ok, $cN[$p]);} - }else{$ok = $inOk; unset($cI['del'], $cI['ins']);} - // bad tags, & ele content - if(isset($e) && ($do == 1 or (isset($ok['#pcdata']) && ($do == 3 or $do == 5)))){ - echo '<', $s, $e, $a, '>'; - } - if(isset($x[0])){ - if(strlen(trim($x)) && (($ql && isset($cB[$p])) or (isset($cB[$in]) && !$ql))){ - echo '
        ', $x, '
        '; - } - elseif($do < 3 or isset($ok['#pcdata'])){echo $x;} - elseif(strpos($x, "\x02\x04")){ - foreach(preg_split('`(\x01\x02[^\x01\x02]+\x02\x01)`', $x, -1, PREG_SPLIT_DELIM_CAPTURE | PREG_SPLIT_NO_EMPTY) as $v){ - echo (substr($v, 0, 2) == "\x01\x02" ? $v : ($do > 4 ? preg_replace('`\S`', '', $v) : '')); - } - }elseif($do > 4){echo preg_replace('`\S`', '', $x);} - } - // get markup - if(!preg_match('`^(/?)([a-z1-6]+)([^>]*)>(.*)`sm', $t[$i], $r)){$x = $t[$i]; continue;} - $s = null; $e = null; $a = null; $x = null; list($all, $s, $e, $a, $x) = $r; - // close tag - if($s){ - if(isset($cE[$e]) or !in_array($e, $q)){continue;} // Empty/unopen - if($p == $e){array_pop($q); echo ''; unset($e); continue;} // Last open - $add = ''; // Nesting - close open tags that need to be - for($j=-1, $cj=count($q); ++$j<$cj;){ - if(($d = array_pop($q)) == $e){break;} - else{$add .= "";} - } - echo $add, ''; unset($e); continue; - } - // open tag - // $cB ele needs $eB ele as child - if(isset($cB[$e]) && strlen(trim($x))){ - $t[$i] = "{$e}{$a}>"; - array_splice($t, $i+1, 0, 'div>'. $x); unset($e, $x); ++$ci; --$i; continue; - } - if((($ql && isset($cB[$p])) or (isset($cB[$in]) && !$ql)) && !isset($eB[$e]) && !isset($ok[$e])){ - array_splice($t, $i, 0, 'div>'); unset($e, $x); ++$ci; --$i; continue; - } - // if no open ele, $in = parent; mostly immediate parent-child relation should hold - if(!$ql or !isset($eN[$e]) or !array_intersect($q, $cN2)){ - if(!isset($ok[$e])){ - if($ql && isset($cT[$p])){echo ''; unset($e, $x); --$i;} - continue; - } - if(!isset($cE[$e])){$q[] = $e;} - echo '<', $e, $a, '>'; unset($e); continue; - } - // specific parent-child - if(isset($cS[$p][$e])){ - if(!isset($cE[$e])){$q[] = $e;} - echo '<', $e, $a, '>'; unset($e); continue; - } - // nesting - $add = ''; - $q2 = array(); - for($k=-1, $kc=count($q); ++$k<$kc;){ - $d = $q[$k]; - $ok2 = array(); - if(isset($cS[$d])){$q2[] = $d; continue;} - $ok2 = isset($cI[$d]) ? $eI : $eF; - if(isset($cO[$d])){$ok2 = $ok2 + $cO[$d];} - if(isset($cN[$d])){$ok2 = array_diff_assoc($ok2, $cN[$d]);} - if(!isset($ok2[$e])){ - if(!$k && !isset($inOk[$e])){continue 2;} - $add = ""; - for(;++$k<$kc;){$add = "{$add}";} - break; - } - else{$q2[] = $d;} - } - $q = $q2; - if(!isset($cE[$e])){$q[] = $e;} - echo $add, '<', $e, $a, '>'; unset($e); continue; -} - -// end -if($ql = count($q)){ - $p = array_pop($q); - $q[] = $p; - if(isset($cS[$p])){$ok = $cS[$p];} - elseif(isset($cI[$p])){$ok = $eI; $cI['del'] = 1; $cI['ins'] = 1;} - elseif(isset($cF[$p])){$ok = $eF; unset($cI['del'], $cI['ins']);} - elseif(isset($cB[$p])){$ok = $eB; unset($cI['del'], $cI['ins']);} - if(isset($cO[$p])){$ok = $ok + $cO[$p];} - if(isset($cN[$p])){$ok = array_diff_assoc($ok, $cN[$p]);} -}else{$ok = $inOk; unset($cI['del'], $cI['ins']);} -if(isset($e) && ($do == 1 or (isset($ok['#pcdata']) && ($do == 3 or $do == 5)))){ - echo '<', $s, $e, $a, '>'; -} -if(isset($x[0])){ - if(strlen(trim($x)) && (($ql && isset($cB[$p])) or (isset($cB[$in]) && !$ql))){ - echo '
        ', $x, '
        '; - } - elseif($do < 3 or isset($ok['#pcdata'])){echo $x;} - elseif(strpos($x, "\x02\x04")){ - foreach(preg_split('`(\x01\x02[^\x01\x02]+\x02\x01)`', $x, -1, PREG_SPLIT_DELIM_CAPTURE | PREG_SPLIT_NO_EMPTY) as $v){ - echo (substr($v, 0, 2) == "\x01\x02" ? $v : ($do > 4 ? preg_replace('`\S`', '', $v) : '')); - } - }elseif($do > 4){echo preg_replace('`\S`', '', $x);} -} -while(!empty($q) && ($e = array_pop($q))){echo '';} -$o = ob_get_contents(); -ob_end_clean(); -return $o; -// eof -} - -function hl_cmtcd($t){ -// comment/CDATA sec handler -$t = $t[0]; -global $C; -if(!($v = $C[$n = $t[3] == '-' ? 'comment' : 'cdata'])){return $t;} -if($v == 1){return '';} -if($n == 'comment'){ - if(substr(($t = preg_replace('`--+`', '-', substr($t, 4, -3))), -1) != ' '){$t .= ' ';} -} -else{$t = substr($t, 1, -1);} -$t = $v == 2 ? str_replace(array('&', '<', '>'), array('&', '<', '>'), $t) : $t; -return str_replace(array('&', '<', '>'), array("\x03", "\x04", "\x05"), ($n == 'comment' ? "\x01\x02\x04!--$t--\x05\x02\x01" : "\x01\x01\x04$t\x05\x01\x01")); -// eof -} - -function hl_ent($t){ -// entitity handler -global $C; -$t = $t[1]; -static $U = array('quot'=>1,'amp'=>1,'lt'=>1,'gt'=>1); -static $N = array('fnof'=>'402', 'Alpha'=>'913', 'Beta'=>'914', 'Gamma'=>'915', 'Delta'=>'916', 'Epsilon'=>'917', 'Zeta'=>'918', 'Eta'=>'919', 'Theta'=>'920', 'Iota'=>'921', 'Kappa'=>'922', 'Lambda'=>'923', 'Mu'=>'924', 'Nu'=>'925', 'Xi'=>'926', 'Omicron'=>'927', 'Pi'=>'928', 'Rho'=>'929', 'Sigma'=>'931', 'Tau'=>'932', 'Upsilon'=>'933', 'Phi'=>'934', 'Chi'=>'935', 'Psi'=>'936', 'Omega'=>'937', 'alpha'=>'945', 'beta'=>'946', 'gamma'=>'947', 'delta'=>'948', 'epsilon'=>'949', 'zeta'=>'950', 'eta'=>'951', 'theta'=>'952', 'iota'=>'953', 'kappa'=>'954', 'lambda'=>'955', 'mu'=>'956', 'nu'=>'957', 'xi'=>'958', 'omicron'=>'959', 'pi'=>'960', 'rho'=>'961', 'sigmaf'=>'962', 'sigma'=>'963', 'tau'=>'964', 'upsilon'=>'965', 'phi'=>'966', 'chi'=>'967', 'psi'=>'968', 'omega'=>'969', 'thetasym'=>'977', 'upsih'=>'978', 'piv'=>'982', 'bull'=>'8226', 'hellip'=>'8230', 'prime'=>'8242', 'Prime'=>'8243', 'oline'=>'8254', 'frasl'=>'8260', 'weierp'=>'8472', 'image'=>'8465', 'real'=>'8476', 'trade'=>'8482', 'alefsym'=>'8501', 'larr'=>'8592', 'uarr'=>'8593', 'rarr'=>'8594', 'darr'=>'8595', 'harr'=>'8596', 'crarr'=>'8629', 'lArr'=>'8656', 'uArr'=>'8657', 'rArr'=>'8658', 'dArr'=>'8659', 'hArr'=>'8660', 'forall'=>'8704', 'part'=>'8706', 'exist'=>'8707', 'empty'=>'8709', 'nabla'=>'8711', 'isin'=>'8712', 'notin'=>'8713', 'ni'=>'8715', 'prod'=>'8719', 'sum'=>'8721', 'minus'=>'8722', 'lowast'=>'8727', 'radic'=>'8730', 'prop'=>'8733', 'infin'=>'8734', 'ang'=>'8736', 'and'=>'8743', 'or'=>'8744', 'cap'=>'8745', 'cup'=>'8746', 'int'=>'8747', 'there4'=>'8756', 'sim'=>'8764', 'cong'=>'8773', 'asymp'=>'8776', 'ne'=>'8800', 'equiv'=>'8801', 'le'=>'8804', 'ge'=>'8805', 'sub'=>'8834', 'sup'=>'8835', 'nsub'=>'8836', 'sube'=>'8838', 'supe'=>'8839', 'oplus'=>'8853', 'otimes'=>'8855', 'perp'=>'8869', 'sdot'=>'8901', 'lceil'=>'8968', 'rceil'=>'8969', 'lfloor'=>'8970', 'rfloor'=>'8971', 'lang'=>'9001', 'rang'=>'9002', 'loz'=>'9674', 'spades'=>'9824', 'clubs'=>'9827', 'hearts'=>'9829', 'diams'=>'9830', 'apos'=>'39', 'OElig'=>'338', 'oelig'=>'339', 'Scaron'=>'352', 'scaron'=>'353', 'Yuml'=>'376', 'circ'=>'710', 'tilde'=>'732', 'ensp'=>'8194', 'emsp'=>'8195', 'thinsp'=>'8201', 'zwnj'=>'8204', 'zwj'=>'8205', 'lrm'=>'8206', 'rlm'=>'8207', 'ndash'=>'8211', 'mdash'=>'8212', 'lsquo'=>'8216', 'rsquo'=>'8217', 'sbquo'=>'8218', 'ldquo'=>'8220', 'rdquo'=>'8221', 'bdquo'=>'8222', 'dagger'=>'8224', 'Dagger'=>'8225', 'permil'=>'8240', 'lsaquo'=>'8249', 'rsaquo'=>'8250', 'euro'=>'8364', 'nbsp'=>'160', 'iexcl'=>'161', 'cent'=>'162', 'pound'=>'163', 'curren'=>'164', 'yen'=>'165', 'brvbar'=>'166', 'sect'=>'167', 'uml'=>'168', 'copy'=>'169', 'ordf'=>'170', 'laquo'=>'171', 'not'=>'172', 'shy'=>'173', 'reg'=>'174', 'macr'=>'175', 'deg'=>'176', 'plusmn'=>'177', 'sup2'=>'178', 'sup3'=>'179', 'acute'=>'180', 'micro'=>'181', 'para'=>'182', 'middot'=>'183', 'cedil'=>'184', 'sup1'=>'185', 'ordm'=>'186', 'raquo'=>'187', 'frac14'=>'188', 'frac12'=>'189', 'frac34'=>'190', 'iquest'=>'191', 'Agrave'=>'192', 'Aacute'=>'193', 'Acirc'=>'194', 'Atilde'=>'195', 'Auml'=>'196', 'Aring'=>'197', 'AElig'=>'198', 'Ccedil'=>'199', 'Egrave'=>'200', 'Eacute'=>'201', 'Ecirc'=>'202', 'Euml'=>'203', 'Igrave'=>'204', 'Iacute'=>'205', 'Icirc'=>'206', 'Iuml'=>'207', 'ETH'=>'208', 'Ntilde'=>'209', 'Ograve'=>'210', 'Oacute'=>'211', 'Ocirc'=>'212', 'Otilde'=>'213', 'Ouml'=>'214', 'times'=>'215', 'Oslash'=>'216', 'Ugrave'=>'217', 'Uacute'=>'218', 'Ucirc'=>'219', 'Uuml'=>'220', 'Yacute'=>'221', 'THORN'=>'222', 'szlig'=>'223', 'agrave'=>'224', 'aacute'=>'225', 'acirc'=>'226', 'atilde'=>'227', 'auml'=>'228', 'aring'=>'229', 'aelig'=>'230', 'ccedil'=>'231', 'egrave'=>'232', 'eacute'=>'233', 'ecirc'=>'234', 'euml'=>'235', 'igrave'=>'236', 'iacute'=>'237', 'icirc'=>'238', 'iuml'=>'239', 'eth'=>'240', 'ntilde'=>'241', 'ograve'=>'242', 'oacute'=>'243', 'ocirc'=>'244', 'otilde'=>'245', 'ouml'=>'246', 'divide'=>'247', 'oslash'=>'248', 'ugrave'=>'249', 'uacute'=>'250', 'ucirc'=>'251', 'uuml'=>'252', 'yacute'=>'253', 'thorn'=>'254', 'yuml'=>'255'); -if($t[0] != '#'){ - return ($C['and_mark'] ? "\x06" : '&'). (isset($U[$t]) ? $t : (isset($N[$t]) ? (!$C['named_entity'] ? '#'. ($C['hexdec_entity'] > 1 ? 'x'. dechex($N[$t]) : $N[$t]) : $t) : 'amp;'. $t)). ';'; -} -if(($n = ctype_digit($t = substr($t, 1)) ? intval($t) : hexdec(substr($t, 1))) < 9 or ($n > 13 && $n < 32) or $n == 11 or $n == 12 or ($n > 126 && $n < 160 && $n != 133) or ($n > 55295 && ($n < 57344 or ($n > 64975 && $n < 64992) or $n == 65534 or $n == 65535 or $n > 1114111))){ - return ($C['and_mark'] ? "\x06" : '&'). "amp;#{$t};"; -} -return ($C['and_mark'] ? "\x06" : '&'). '#'. (((ctype_digit($t) && $C['hexdec_entity'] < 2) or !$C['hexdec_entity']) ? $n : 'x'. dechex($n)). ';'; -// eof -} - -function hl_prot($p, $c=null){ -// check URL scheme -global $C; -$b = $a = ''; -if($c == null){$c = 'style'; $b = $p[1]; $a = $p[3]; $p = trim($p[2]);} -$c = isset($C['schemes'][$c]) ? $C['schemes'][$c] : $C['schemes']['*']; -static $d = 'denied:'; -if(isset($c['!']) && substr($p, 0, 7) != $d){$p = "$d$p";} -if(isset($c['*']) or !strcspn($p, '#?;') or (substr($p, 0, 7) == $d)){return "{$b}{$p}{$a}";} // All ok, frag, query, param -if(preg_match('`^([^:?[@!$()*,=/\'\]]+?)(:|&#(58|x3a);|%3a|\\\\0{0,4}3a).`i', $p, $m) && !isset($c[strtolower($m[1])])){ // Denied prot - return "{$b}{$d}{$p}{$a}"; -} -if($C['abs_url']){ - if($C['abs_url'] == -1 && strpos($p, $C['base_url']) === 0){ // Make url rel - $p = substr($p, strlen($C['base_url'])); - }elseif(empty($m[1])){ // Make URL abs - if(substr($p, 0, 2) == '//'){$p = substr($C['base_url'], 0, strpos($C['base_url'], ':')+1). $p;} - elseif($p[0] == '/'){$p = preg_replace('`(^.+?://[^/]+)(.*)`', '$1', $C['base_url']). $p;} - elseif(strcspn($p, './')){$p = $C['base_url']. $p;} - else{ - preg_match('`^([a-zA-Z\d\-+.]+://[^/]+)(.*)`', $C['base_url'], $m); - $p = preg_replace('`(?<=/)\./`', '', $m[2]. $p); - while(preg_match('`(?<=/)([^/]{3,}|[^/.]+?|\.[^/.]|[^/.]\.)/\.\./`', $p)){ - $p = preg_replace('`(?<=/)([^/]{3,}|[^/.]+?|\.[^/.]|[^/.]\.)/\.\./`', '', $p); - } - $p = $m[1]. $p; - } - } -} -return "{$b}{$p}{$a}"; -// eof -} - -function hl_regex($p){ -// ?regex -if(empty($p)){return 0;} -if($t = ini_get('track_errors')){$o = isset($php_errormsg) ? $php_errormsg : null;} -else{ini_set('track_errors', 1);} -unset($php_errormsg); -if(($d = ini_get('display_errors'))){ini_set('display_errors', 0);} -preg_match($p, ''); -if($d){ini_set('display_errors', 1);} -$r = isset($php_errormsg) ? 0 : 1; -if($t){$php_errormsg = isset($o) ? $o : null;} -else{ini_set('track_errors', 0);} -return $r; -// eof -} - -function hl_spec($t){ -// final $spec -$s = array(); -$t = str_replace(array("\t", "\r", "\n", ' '), '', preg_replace_callback('/"(?>(`.|[^"])*)"/sm', create_function('$m', 'return substr(str_replace(array(";", "|", "~", " ", ",", "/", "(", ")", \'`"\'), array("\x01", "\x02", "\x03", "\x04", "\x05", "\x06", "\x07", "\x08", "\""), $m[0]), 1, -1);'), trim($t))); -for($i = count(($t = explode(';', $t))); --$i>=0;){ - $w = $t[$i]; - if(empty($w) or ($e = strpos($w, '=')) === false or !strlen(($a = substr($w, $e+1)))){continue;} - $y = $n = array(); - foreach(explode(',', $a) as $v){ - if(!preg_match('`^([a-z:\-\*]+)(?:\((.*?)\))?`i', $v, $m)){continue;} - if(($x = strtolower($m[1])) == '-*'){$n['*'] = 1; continue;} - if($x[0] == '-'){$n[substr($x, 1)] = 1; continue;} - if(!isset($m[2])){$y[$x] = 1; continue;} - foreach(explode('/', $m[2]) as $m){ - if(empty($m) or ($p = strpos($m, '=')) == 0 or $p < 5){$y[$x] = 1; continue;} - $y[$x][strtolower(substr($m, 0, $p))] = str_replace(array("\x01", "\x02", "\x03", "\x04", "\x05", "\x06", "\x07", "\x08"), array(";", "|", "~", " ", ",", "/", "(", ")"), substr($m, $p+1)); - } - if(isset($y[$x]['match']) && !hl_regex($y[$x]['match'])){unset($y[$x]['match']);} - if(isset($y[$x]['nomatch']) && !hl_regex($y[$x]['nomatch'])){unset($y[$x]['nomatch']);} - } - if(!count($y) && !count($n)){continue;} - foreach(explode(',', substr($w, 0, $e)) as $v){ - if(!strlen(($v = strtolower($v)))){continue;} - if(count($y)){$s[$v] = $y;} - if(count($n)){$s[$v]['n'] = $n;} - } -} -return $s; -// eof -} - -function hl_tag($t){ -// tag/attribute handler -global $C; -$t = $t[0]; -// invalid < > -if($t == '< '){return '< ';} -if($t == '>'){return '>';} -if(!preg_match('`^<(/?)([a-zA-Z][a-zA-Z1-6]*)([^>]*?)\s?>$`m', $t, $m)){ - return str_replace(array('<', '>'), array('<', '>'), $t); -}elseif(!isset($C['elements'][($e = strtolower($m[2]))])){ - return (($C['keep_bad']%2) ? str_replace(array('<', '>'), array('<', '>'), $t) : ''); -} -// attr string -$a = str_replace(array("\n", "\r", "\t"), ' ', trim($m[3])); -// tag transform -static $eD = array('applet'=>1, 'center'=>1, 'dir'=>1, 'embed'=>1, 'font'=>1, 'isindex'=>1, 'menu'=>1, 's'=>1, 'strike'=>1, 'u'=>1); // Deprecated -if($C['make_tag_strict'] && isset($eD[$e])){ - $trt = hl_tag2($e, $a, $C['make_tag_strict']); - if(!$e){return (($C['keep_bad']%2) ? str_replace(array('<', '>'), array('<', '>'), $t) : '');} -} -// close tag -static $eE = array('area'=>1, 'br'=>1, 'col'=>1, 'embed'=>1, 'hr'=>1, 'img'=>1, 'input'=>1, 'isindex'=>1, 'param'=>1); // Empty ele -if(!empty($m[1])){ - return (!isset($eE[$e]) ? (empty($C['hook_tag']) ? "" : $C['hook_tag']($e)) : (($C['keep_bad'])%2 ? str_replace(array('<', '>'), array('<', '>'), $t) : '')); -} - -// open tag & attr -static $aN = array('abbr'=>array('td'=>1, 'th'=>1), 'accept-charset'=>array('form'=>1), 'accept'=>array('form'=>1, 'input'=>1), 'accesskey'=>array('a'=>1, 'area'=>1, 'button'=>1, 'input'=>1, 'label'=>1, 'legend'=>1, 'textarea'=>1), 'action'=>array('form'=>1), 'align'=>array('caption'=>1, 'embed'=>1, 'applet'=>1, 'iframe'=>1, 'img'=>1, 'input'=>1, 'object'=>1, 'legend'=>1, 'table'=>1, 'hr'=>1, 'div'=>1, 'h1'=>1, 'h2'=>1, 'h3'=>1, 'h4'=>1, 'h5'=>1, 'h6'=>1, 'p'=>1, 'col'=>1, 'colgroup'=>1, 'tbody'=>1, 'td'=>1, 'tfoot'=>1, 'th'=>1, 'thead'=>1, 'tr'=>1), 'allowfullscreen'=>array('iframe'=>1), 'alt'=>array('applet'=>1, 'area'=>1, 'img'=>1, 'input'=>1), 'archive'=>array('applet'=>1, 'object'=>1), 'axis'=>array('td'=>1, 'th'=>1), 'bgcolor'=>array('embed'=>1, 'table'=>1, 'tr'=>1, 'td'=>1, 'th'=>1), 'border'=>array('table'=>1, 'img'=>1, 'object'=>1), 'bordercolor'=>array('table'=>1, 'td'=>1, 'tr'=>1), 'cellpadding'=>array('table'=>1), 'cellspacing'=>array('table'=>1), 'char'=>array('col'=>1, 'colgroup'=>1, 'tbody'=>1, 'td'=>1, 'tfoot'=>1, 'th'=>1, 'thead'=>1, 'tr'=>1), 'charoff'=>array('col'=>1, 'colgroup'=>1, 'tbody'=>1, 'td'=>1, 'tfoot'=>1, 'th'=>1, 'thead'=>1, 'tr'=>1), 'charset'=>array('a'=>1, 'script'=>1), 'checked'=>array('input'=>1), 'cite'=>array('blockquote'=>1, 'q'=>1, 'del'=>1, 'ins'=>1), 'classid'=>array('object'=>1), 'clear'=>array('br'=>1), 'code'=>array('applet'=>1), 'codebase'=>array('object'=>1, 'applet'=>1), 'codetype'=>array('object'=>1), 'color'=>array('font'=>1), 'cols'=>array('textarea'=>1), 'colspan'=>array('td'=>1, 'th'=>1), 'compact'=>array('dir'=>1, 'dl'=>1, 'menu'=>1, 'ol'=>1, 'ul'=>1), 'coords'=>array('area'=>1, 'a'=>1), 'data'=>array('object'=>1), 'datetime'=>array('del'=>1, 'ins'=>1), 'declare'=>array('object'=>1), 'defer'=>array('script'=>1), 'dir'=>array('bdo'=>1), 'disabled'=>array('button'=>1, 'input'=>1, 'optgroup'=>1, 'option'=>1, 'select'=>1, 'textarea'=>1), 'enctype'=>array('form'=>1), 'face'=>array('font'=>1), 'flashvars'=>array('embed'=>1), 'for'=>array('label'=>1), 'frame'=>array('table'=>1), 'frameborder'=>array('iframe'=>1), 'headers'=>array('td'=>1, 'th'=>1), 'height'=>array('embed'=>1, 'iframe'=>1, 'td'=>1, 'th'=>1, 'img'=>1, 'object'=>1, 'applet'=>1), 'href'=>array('a'=>1, 'area'=>1), 'hreflang'=>array('a'=>1), 'hspace'=>array('applet'=>1, 'img'=>1, 'object'=>1), 'ismap'=>array('img'=>1, 'input'=>1), 'label'=>array('option'=>1, 'optgroup'=>1), 'language'=>array('script'=>1), 'longdesc'=>array('img'=>1, 'iframe'=>1), 'marginheight'=>array('iframe'=>1), 'marginwidth'=>array('iframe'=>1), 'maxlength'=>array('input'=>1), 'method'=>array('form'=>1), 'model'=>array('embed'=>1), 'multiple'=>array('select'=>1), 'name'=>array('button'=>1, 'embed'=>1, 'textarea'=>1, 'applet'=>1, 'select'=>1, 'form'=>1, 'iframe'=>1, 'img'=>1, 'a'=>1, 'input'=>1, 'object'=>1, 'map'=>1, 'param'=>1), 'nohref'=>array('area'=>1), 'noshade'=>array('hr'=>1), 'nowrap'=>array('td'=>1, 'th'=>1), 'object'=>array('applet'=>1), 'onblur'=>array('a'=>1, 'area'=>1, 'button'=>1, 'input'=>1, 'label'=>1, 'select'=>1, 'textarea'=>1), 'onchange'=>array('input'=>1, 'select'=>1, 'textarea'=>1), 'onfocus'=>array('a'=>1, 'area'=>1, 'button'=>1, 'input'=>1, 'label'=>1, 'select'=>1, 'textarea'=>1), 'onreset'=>array('form'=>1), 'onselect'=>array('input'=>1, 'textarea'=>1), 'onsubmit'=>array('form'=>1), 'pluginspage'=>array('embed'=>1), 'pluginurl'=>array('embed'=>1), 'prompt'=>array('isindex'=>1), 'readonly'=>array('textarea'=>1, 'input'=>1), 'rel'=>array('a'=>1), 'rev'=>array('a'=>1), 'rows'=>array('textarea'=>1), 'rowspan'=>array('td'=>1, 'th'=>1), 'rules'=>array('table'=>1), 'scope'=>array('td'=>1, 'th'=>1), 'scrolling'=>array('iframe'=>1), 'selected'=>array('option'=>1), 'shape'=>array('area'=>1, 'a'=>1), 'size'=>array('hr'=>1, 'font'=>1, 'input'=>1, 'select'=>1), 'span'=>array('col'=>1, 'colgroup'=>1), 'src'=>array('embed'=>1, 'script'=>1, 'input'=>1, 'iframe'=>1, 'img'=>1), 'standby'=>array('object'=>1), 'start'=>array('ol'=>1), 'summary'=>array('table'=>1), 'tabindex'=>array('a'=>1, 'area'=>1, 'button'=>1, 'input'=>1, 'object'=>1, 'select'=>1, 'textarea'=>1), 'target'=>array('a'=>1, 'area'=>1, 'form'=>1), 'type'=>array('a'=>1, 'embed'=>1, 'object'=>1, 'param'=>1, 'script'=>1, 'input'=>1, 'li'=>1, 'ol'=>1, 'ul'=>1, 'button'=>1), 'usemap'=>array('img'=>1, 'input'=>1, 'object'=>1), 'valign'=>array('col'=>1, 'colgroup'=>1, 'tbody'=>1, 'td'=>1, 'tfoot'=>1, 'th'=>1, 'thead'=>1, 'tr'=>1), 'value'=>array('input'=>1, 'option'=>1, 'param'=>1, 'button'=>1, 'li'=>1), 'valuetype'=>array('param'=>1), 'vspace'=>array('applet'=>1, 'img'=>1, 'object'=>1), 'width'=>array('embed'=>1, 'hr'=>1, 'iframe'=>1, 'img'=>1, 'object'=>1, 'table'=>1, 'td'=>1, 'th'=>1, 'applet'=>1, 'col'=>1, 'colgroup'=>1, 'pre'=>1), 'wmode'=>array('embed'=>1), 'xml:space'=>array('pre'=>1, 'script'=>1, 'style'=>1)); // Ele-specific -static $aNE = array('allowfullscreen'=>1, 'checked'=>1, 'compact'=>1, 'declare'=>1, 'defer'=>1, 'disabled'=>1, 'ismap'=>1, 'multiple'=>1, 'nohref'=>1, 'noresize'=>1, 'noshade'=>1, 'nowrap'=>1, 'readonly'=>1, 'selected'=>1); // Empty -static $aNP = array('action'=>1, 'cite'=>1, 'classid'=>1, 'codebase'=>1, 'data'=>1, 'href'=>1, 'longdesc'=>1, 'model'=>1, 'pluginspage'=>1, 'pluginurl'=>1, 'usemap'=>1); // Need scheme check; excludes style, on* & src -static $aNU = array('class'=>array('param'=>1, 'script'=>1), 'dir'=>array('applet'=>1, 'bdo'=>1, 'br'=>1, 'iframe'=>1, 'param'=>1, 'script'=>1), 'id'=>array('script'=>1), 'lang'=>array('applet'=>1, 'br'=>1, 'iframe'=>1, 'param'=>1, 'script'=>1), 'xml:lang'=>array('applet'=>1, 'br'=>1, 'iframe'=>1, 'param'=>1, 'script'=>1), 'onclick'=>array('applet'=>1, 'bdo'=>1, 'br'=>1, 'font'=>1, 'iframe'=>1, 'isindex'=>1, 'param'=>1, 'script'=>1), 'ondblclick'=>array('applet'=>1, 'bdo'=>1, 'br'=>1, 'font'=>1, 'iframe'=>1, 'isindex'=>1, 'param'=>1, 'script'=>1), 'onkeydown'=>array('applet'=>1, 'bdo'=>1, 'br'=>1, 'font'=>1, 'iframe'=>1, 'isindex'=>1, 'param'=>1, 'script'=>1), 'onkeypress'=>array('applet'=>1, 'bdo'=>1, 'br'=>1, 'font'=>1, 'iframe'=>1, 'isindex'=>1, 'param'=>1, 'script'=>1), 'onkeyup'=>array('applet'=>1, 'bdo'=>1, 'br'=>1, 'font'=>1, 'iframe'=>1, 'isindex'=>1, 'param'=>1, 'script'=>1), 'onmousedown'=>array('applet'=>1, 'bdo'=>1, 'br'=>1, 'font'=>1, 'iframe'=>1, 'isindex'=>1, 'param'=>1, 'script'=>1), 'onmousemove'=>array('applet'=>1, 'bdo'=>1, 'br'=>1, 'font'=>1, 'iframe'=>1, 'isindex'=>1, 'param'=>1, 'script'=>1), 'onmouseout'=>array('applet'=>1, 'bdo'=>1, 'br'=>1, 'font'=>1, 'iframe'=>1, 'isindex'=>1, 'param'=>1, 'script'=>1), 'onmouseover'=>array('applet'=>1, 'bdo'=>1, 'br'=>1, 'font'=>1, 'iframe'=>1, 'isindex'=>1, 'param'=>1, 'script'=>1), 'onmouseup'=>array('applet'=>1, 'bdo'=>1, 'br'=>1, 'font'=>1, 'iframe'=>1, 'isindex'=>1, 'param'=>1, 'script'=>1), 'style'=>array('param'=>1, 'script'=>1), 'title'=>array('param'=>1, 'script'=>1)); // Univ & exceptions - -if($C['lc_std_val']){ - // predef attr vals for $eAL & $aNE ele - static $aNL = array('all'=>1, 'baseline'=>1, 'bottom'=>1, 'button'=>1, 'center'=>1, 'char'=>1, 'checkbox'=>1, 'circle'=>1, 'col'=>1, 'colgroup'=>1, 'cols'=>1, 'data'=>1, 'default'=>1, 'file'=>1, 'get'=>1, 'groups'=>1, 'hidden'=>1, 'image'=>1, 'justify'=>1, 'left'=>1, 'ltr'=>1, 'middle'=>1, 'none'=>1, 'object'=>1, 'password'=>1, 'poly'=>1, 'post'=>1, 'preserve'=>1, 'radio'=>1, 'rect'=>1, 'ref'=>1, 'reset'=>1, 'right'=>1, 'row'=>1, 'rowgroup'=>1, 'rows'=>1, 'rtl'=>1, 'submit'=>1, 'text'=>1, 'top'=>1); - static $eAL = array('a'=>1, 'area'=>1, 'bdo'=>1, 'button'=>1, 'col'=>1, 'form'=>1, 'img'=>1, 'input'=>1, 'object'=>1, 'optgroup'=>1, 'option'=>1, 'param'=>1, 'script'=>1, 'select'=>1, 'table'=>1, 'td'=>1, 'tfoot'=>1, 'th'=>1, 'thead'=>1, 'tr'=>1, 'xml:space'=>1); - $lcase = isset($eAL[$e]) ? 1 : 0; -} - -$depTr = 0; -if($C['no_deprecated_attr']){ - // dep attr:applicable ele - static $aND = array('align'=>array('caption'=>1, 'div'=>1, 'h1'=>1, 'h2'=>1, 'h3'=>1, 'h4'=>1, 'h5'=>1, 'h6'=>1, 'hr'=>1, 'img'=>1, 'input'=>1, 'legend'=>1, 'object'=>1, 'p'=>1, 'table'=>1), 'bgcolor'=>array('table'=>1, 'td'=>1, 'th'=>1, 'tr'=>1), 'border'=>array('img'=>1, 'object'=>1), 'bordercolor'=>array('table'=>1, 'td'=>1, 'tr'=>1), 'clear'=>array('br'=>1), 'compact'=>array('dl'=>1, 'ol'=>1, 'ul'=>1), 'height'=>array('td'=>1, 'th'=>1), 'hspace'=>array('img'=>1, 'object'=>1), 'language'=>array('script'=>1), 'name'=>array('a'=>1, 'form'=>1, 'iframe'=>1, 'img'=>1, 'map'=>1), 'noshade'=>array('hr'=>1), 'nowrap'=>array('td'=>1, 'th'=>1), 'size'=>array('hr'=>1), 'start'=>array('ol'=>1), 'type'=>array('li'=>1, 'ol'=>1, 'ul'=>1), 'value'=>array('li'=>1), 'vspace'=>array('img'=>1, 'object'=>1), 'width'=>array('hr'=>1, 'pre'=>1, 'td'=>1, 'th'=>1)); - static $eAD = array('a'=>1, 'br'=>1, 'caption'=>1, 'div'=>1, 'dl'=>1, 'form'=>1, 'h1'=>1, 'h2'=>1, 'h3'=>1, 'h4'=>1, 'h5'=>1, 'h6'=>1, 'hr'=>1, 'iframe'=>1, 'img'=>1, 'input'=>1, 'legend'=>1, 'li'=>1, 'map'=>1, 'object'=>1, 'ol'=>1, 'p'=>1, 'pre'=>1, 'script'=>1, 'table'=>1, 'td'=>1, 'th'=>1, 'tr'=>1, 'ul'=>1); - $depTr = isset($eAD[$e]) ? 1 : 0; -} - -// attr name-vals -if(strpos($a, "\x01") !== false){$a = preg_replace('`\x01[^\x01]*\x01`', '', $a);} // No comment/CDATA sec -$mode = 0; $a = trim($a, ' /'); $aA = array(); -while(strlen($a)){ - $w = 0; - switch($mode){ - case 0: // Name - if(preg_match('`^[a-zA-Z][\-a-zA-Z:]+`', $a, $m)){ - $nm = strtolower($m[0]); - $w = $mode = 1; $a = ltrim(substr_replace($a, '', 0, strlen($m[0]))); - } - break; case 1: - if($a[0] == '='){ // = - $w = 1; $mode = 2; $a = ltrim($a, '= '); - }else{ // No val - $w = 1; $mode = 0; $a = ltrim($a); - $aA[$nm] = ''; - } - break; case 2: // Val - if(preg_match('`^((?:"[^"]*")|(?:\'[^\']*\')|(?:\s*[^\s"\']+))(.*)`', $a, $m)){ - $a = ltrim($m[2]); $m = $m[1]; $w = 1; $mode = 0; - $aA[$nm] = trim(str_replace('<', '<', ($m[0] == '"' or $m[0] == '\'') ? substr($m, 1, -1) : $m)); - } - break; - } - if($w == 0){ // Parse errs, deal with space, " & ' - $a = preg_replace('`^(?:"[^"]*("|$)|\'[^\']*(\'|$)|\S)*\s*`', '', $a); - $mode = 0; - } -} -if($mode == 1){$aA[$nm] = '';} - -// clean attrs -global $S; -$rl = isset($S[$e]) ? $S[$e] : array(); -$a = array(); $nfr = 0; -foreach($aA as $k=>$v){ - if(((isset($C['deny_attribute']['*']) ? isset($C['deny_attribute'][$k]) : !isset($C['deny_attribute'][$k])) && (isset($aN[$k][$e]) or (isset($aNU[$k]) && !isset($aNU[$k][$e]))) && !isset($rl['n'][$k]) && !isset($rl['n']['*'])) or isset($rl[$k])){ - if(isset($aNE[$k])){$v = $k;} - elseif(!empty($lcase) && (($e != 'button' or $e != 'input') or $k == 'type')){ // Rather loose but ?not cause issues - $v = (isset($aNL[($v2 = strtolower($v))])) ? $v2 : $v; - } - if($k == 'style' && !$C['style_pass']){ - if(false !== strpos($v, '&#')){ - static $sC = array(' '=>' ', ' '=>' ', 'E'=>'e', 'E'=>'e', 'e'=>'e', 'e'=>'e', 'X'=>'x', 'X'=>'x', 'x'=>'x', 'x'=>'x', 'P'=>'p', 'P'=>'p', 'p'=>'p', 'p'=>'p', 'S'=>'s', 'S'=>'s', 's'=>'s', 's'=>'s', 'I'=>'i', 'I'=>'i', 'i'=>'i', 'i'=>'i', 'O'=>'o', 'O'=>'o', 'o'=>'o', 'o'=>'o', 'N'=>'n', 'N'=>'n', 'n'=>'n', 'n'=>'n', 'U'=>'u', 'U'=>'u', 'u'=>'u', 'u'=>'u', 'R'=>'r', 'R'=>'r', 'r'=>'r', 'r'=>'r', 'L'=>'l', 'L'=>'l', 'l'=>'l', 'l'=>'l', '('=>'(', '('=>'(', ')'=>')', ')'=>')', ' '=>':', ' '=>':', '"'=>'"', '"'=>'"', '''=>"'", '''=>"'", '/'=>'/', '/'=>'/', '*'=>'*', '*'=>'*', '\'=>'\\', '\'=>'\\'); - $v = strtr($v, $sC); - } - $v = preg_replace_callback('`(url(?:\()(?: )*(?:\'|"|&(?:quot|apos);)?)(.+?)((?:\'|"|&(?:quot|apos);)?(?: )*(?:\)))`iS', 'hl_prot', $v); - $v = !$C['css_expression'] ? preg_replace('`expression`i', ' ', preg_replace('`\\\\\S|(/|(%2f))(\*|(%2a))`i', ' ', $v)) : $v; - }elseif(isset($aNP[$k]) or strpos($k, 'src') !== false or $k[0] == 'o'){ - $v = str_replace("­", ' ', (strpos($v, '&') !== false ? str_replace(array('­', '­', '­'), ' ', $v) : $v)); # double-quoted char is soft-hyphen; appears here as "­" or hyphen or something else depending on viewing software - $v = hl_prot($v, $k); - if($k == 'href'){ // X-spam - if($C['anti_mail_spam'] && strpos($v, 'mailto:') === 0){ - $v = str_replace('@', htmlspecialchars($C['anti_mail_spam']), $v); - }elseif($C['anti_link_spam']){ - $r1 = $C['anti_link_spam'][1]; - if(!empty($r1) && preg_match($r1, $v)){continue;} - $r0 = $C['anti_link_spam'][0]; - if(!empty($r0) && preg_match($r0, $v)){ - if(isset($a['rel'])){ - if(!preg_match('`\bnofollow\b`i', $a['rel'])){$a['rel'] .= ' nofollow';} - }elseif(isset($aA['rel'])){ - if(!preg_match('`\bnofollow\b`i', $aA['rel'])){$nfr = 1;} - }else{$a['rel'] = 'nofollow';} - } - } - } - } - if(isset($rl[$k]) && is_array($rl[$k]) && ($v = hl_attrval($v, $rl[$k])) === 0){continue;} - $a[$k] = str_replace('"', '"', $v); - } -} -if($nfr){$a['rel'] = isset($a['rel']) ? $a['rel']. ' nofollow' : 'nofollow';} - -// rqd attr -static $eAR = array('area'=>array('alt'=>'area'), 'bdo'=>array('dir'=>'ltr'), 'form'=>array('action'=>''), 'img'=>array('src'=>'', 'alt'=>'image'), 'map'=>array('name'=>''), 'optgroup'=>array('label'=>''), 'param'=>array('name'=>''), 'script'=>array('type'=>'text/javascript'), 'textarea'=>array('rows'=>'10', 'cols'=>'50')); -if(isset($eAR[$e])){ - foreach($eAR[$e] as $k=>$v){ - if(!isset($a[$k])){$a[$k] = isset($v[0]) ? $v : $k;} - } -} - -// depr attrs -if($depTr){ - $c = array(); - foreach($a as $k=>$v){ - if($k == 'style' or !isset($aND[$k][$e])){continue;} - if($k == 'align'){ - unset($a['align']); - if($e == 'img' && ($v == 'left' or $v == 'right')){$c[] = 'float: '. $v;} - elseif(($e == 'div' or $e == 'table') && $v == 'center'){$c[] = 'margin: auto';} - else{$c[] = 'text-align: '. $v;} - }elseif($k == 'bgcolor'){ - unset($a['bgcolor']); - $c[] = 'background-color: '. $v; - }elseif($k == 'border'){ - unset($a['border']); $c[] = "border: {$v}px"; - }elseif($k == 'bordercolor'){ - unset($a['bordercolor']); $c[] = 'border-color: '. $v; - }elseif($k == 'clear'){ - unset($a['clear']); $c[] = 'clear: '. ($v != 'all' ? $v : 'both'); - }elseif($k == 'compact'){ - unset($a['compact']); $c[] = 'font-size: 85%'; - }elseif($k == 'height' or $k == 'width'){ - unset($a[$k]); $c[] = $k. ': '. ($v[0] != '*' ? $v. (ctype_digit($v) ? 'px' : '') : 'auto'); - }elseif($k == 'hspace'){ - unset($a['hspace']); $c[] = "margin-left: {$v}px; margin-right: {$v}px"; - }elseif($k == 'language' && !isset($a['type'])){ - unset($a['language']); - $a['type'] = 'text/'. strtolower($v); - }elseif($k == 'name'){ - if($C['no_deprecated_attr'] == 2 or ($e != 'a' && $e != 'map')){unset($a['name']);} - if(!isset($a['id']) && preg_match('`[a-zA-Z][a-zA-Z\d.:_\-]*`', $v)){$a['id'] = $v;} - }elseif($k == 'noshade'){ - unset($a['noshade']); $c[] = 'border-style: none; border: 0; background-color: gray; color: gray'; - }elseif($k == 'nowrap'){ - unset($a['nowrap']); $c[] = 'white-space: nowrap'; - }elseif($k == 'size'){ - unset($a['size']); $c[] = 'size: '. $v. 'px'; - }elseif($k == 'start' or $k == 'value'){ - unset($a[$k]); - }elseif($k == 'type'){ - unset($a['type']); - static $ol_type = array('i'=>'lower-roman', 'I'=>'upper-roman', 'a'=>'lower-latin', 'A'=>'upper-latin', '1'=>'decimal'); - $c[] = 'list-style-type: '. (isset($ol_type[$v]) ? $ol_type[$v] : 'decimal'); - }elseif($k == 'vspace'){ - unset($a['vspace']); $c[] = "margin-top: {$v}px; margin-bottom: {$v}px"; - } - } - if(count($c)){ - $c = implode('; ', $c); - $a['style'] = isset($a['style']) ? rtrim($a['style'], ' ;'). '; '. $c. ';': $c. ';'; - } -} -// unique ID -if($C['unique_ids'] && isset($a['id'])){ - if(!preg_match('`^[A-Za-z][A-Za-z0-9_\-.:]*$`', ($id = $a['id'])) or (isset($GLOBALS['hl_Ids'][$id]) && $C['unique_ids'] == 1)){unset($a['id']); - }else{ - while(isset($GLOBALS['hl_Ids'][$id])){$id = $C['unique_ids']. $id;} - $GLOBALS['hl_Ids'][($a['id'] = $id)] = 1; - } -} -// xml:lang -if($C['xml:lang'] && isset($a['lang'])){ - $a['xml:lang'] = isset($a['xml:lang']) ? $a['xml:lang'] : $a['lang']; - if($C['xml:lang'] == 2){unset($a['lang']);} -} -// for transformed tag -if(!empty($trt)){ - $a['style'] = isset($a['style']) ? rtrim($a['style'], ' ;'). '; '. $trt : $trt; -} -// return with empty ele / -if(empty($C['hook_tag'])){ - $aA = ''; - foreach($a as $k=>$v){$aA .= " {$k}=\"{$v}\"";} - return "<{$e}{$aA}". (isset($eE[$e]) ? ' /' : ''). '>'; -} -else{return $C['hook_tag']($e, $a);} -// eof -} - -function hl_tag2(&$e, &$a, $t=1){ -// transform tag -if($e == 'center'){$e = 'div'; return 'text-align: center;';} -if($e == 'dir' or $e == 'menu'){$e = 'ul'; return '';} -if($e == 's' or $e == 'strike'){$e = 'span'; return 'text-decoration: line-through;';} -if($e == 'u'){$e = 'span'; return 'text-decoration: underline;';} -static $fs = array('0'=>'xx-small', '1'=>'xx-small', '2'=>'small', '3'=>'medium', '4'=>'large', '5'=>'x-large', '6'=>'xx-large', '7'=>'300%', '-1'=>'smaller', '-2'=>'60%', '+1'=>'larger', '+2'=>'150%', '+3'=>'200%', '+4'=>'300%'); -if($e == 'font'){ - $a2 = ''; - if(preg_match('`face\s*=\s*(\'|")([^=]+?)\\1`i', $a, $m) or preg_match('`face\s*=(\s*)(\S+)`i', $a, $m)){ - $a2 .= ' font-family: '. str_replace('"', '\'', trim($m[2])). ';'; - } - if(preg_match('`color\s*=\s*(\'|")?(.+?)(\\1|\s|$)`i', $a, $m)){ - $a2 .= ' color: '. str_replace('"', '\'', trim($m[2])). ';'; - } - if(preg_match('`size\s*=\s*(\'|")?(.+?)(\\1|\s|$)`i', $a, $m) && isset($fs[($m = trim($m[2]))])){ - $a2 .= ' font-size: '. str_replace('"', '\'', $fs[$m]). ';'; - } - $e = 'span'; return ltrim($a2); -} -if($t == 2){$e = 0; return 0;} -return ''; -// eof -} - -function hl_tidy($t, $w, $p){ -// Tidy/compact HTM -if(strpos(' pre,script,textarea', "$p,")){return $t;} -$t = preg_replace('`\s+`', ' ', preg_replace_callback(array('`(<(!\[CDATA\[))(.+?)(\]\]>)`sm', '`(<(!--))(.+?)(-->)`sm', '`(<(pre|script|textarea)[^>]*?>)(.+?)()`sm'), create_function('$m', 'return $m[1]. str_replace(array("<", ">", "\n", "\r", "\t", " "), array("\x01", "\x02", "\x03", "\x04", "\x05", "\x07"), $m[3]). $m[4];'), $t)); -if(($w = strtolower($w)) == -1){ - return str_replace(array("\x01", "\x02", "\x03", "\x04", "\x05", "\x07"), array('<', '>', "\n", "\r", "\t", ' '), $t); -} -$s = strpos(" $w", 't') ? "\t" : ' '; -$s = preg_match('`\d`', $w, $m) ? str_repeat($s, $m[0]) : str_repeat($s, ($s == "\t" ? 1 : 2)); -$N = preg_match('`[ts]([1-9])`', $w, $m) ? $m[1] : 0; -$a = array('br'=>1); -$b = array('button'=>1, 'input'=>1, 'option'=>1, 'param'=>1); -$c = array('caption'=>1, 'dd'=>1, 'dt'=>1, 'h1'=>1, 'h2'=>1, 'h3'=>1, 'h4'=>1, 'h5'=>1, 'h6'=>1, 'isindex'=>1, 'label'=>1, 'legend'=>1, 'li'=>1, 'object'=>1, 'p'=>1, 'pre'=>1, 'td'=>1, 'textarea'=>1, 'th'=>1); -$d = array('address'=>1, 'blockquote'=>1, 'center'=>1, 'colgroup'=>1, 'dir'=>1, 'div'=>1, 'dl'=>1, 'fieldset'=>1, 'form'=>1, 'hr'=>1, 'iframe'=>1, 'map'=>1, 'menu'=>1, 'noscript'=>1, 'ol'=>1, 'optgroup'=>1, 'rbc'=>1, 'rtc'=>1, 'ruby'=>1, 'script'=>1, 'select'=>1, 'table'=>1, 'tbody'=>1, 'tfoot'=>1, 'thead'=>1, 'tr'=>1, 'ul'=>1); -$T = explode('<', $t); -$X = 1; -while($X){ - $n = $N; - $t = $T; - ob_start(); - if(isset($d[$p])){echo str_repeat($s, ++$n);} - echo ltrim(array_shift($t)); - for($i=-1, $j=count($t); ++$i<$j;){ - $r = ''; list($e, $r) = explode('>', $t[$i]); - $x = $e[0] == '/' ? 0 : (substr($e, -1) == '/' ? 1 : ($e[0] != '!' ? 2 : -1)); - $y = !$x ? ltrim($e, '/') : ($x > 0 ? substr($e, 0, strcspn($e, ' ')) : 0); - $e = "<$e>"; - if(isset($d[$y])){ - if(!$x){ - if($n){echo "\n", str_repeat($s, --$n), "$e\n", str_repeat($s, $n);} - else{++$N; ob_end_clean(); continue 2;} - } - else{echo "\n", str_repeat($s, $n), "$e\n", str_repeat($s, ($x != 1 ? ++$n : $n));} - echo $r; continue; - } - $f = "\n". str_repeat($s, $n); - if(isset($c[$y])){ - if(!$x){echo $e, $f, $r;} - else{echo $f, $e, $r;} - }elseif(isset($b[$y])){echo $f, $e, $r; - }elseif(isset($a[$y])){echo $e, $f, $r; - }elseif(!$y){echo $f, $e, $f, $r; - }else{echo $e, $r;} - } - $X = 0; -} -$t = str_replace(array("\n ", " \n"), "\n", preg_replace('`[\n]\s*?[\n]+`', "\n", ob_get_contents())); -ob_end_clean(); -if(($l = strpos(" $w", 'r') ? (strpos(" $w", 'n') ? "\r\n" : "\r") : 0)){ - $t = str_replace("\n", $l, $t); -} -return str_replace(array("\x01", "\x02", "\x03", "\x04", "\x05", "\x07"), array('<', '>', "\n", "\r", "\t", ' '), $t); -// eof -} - -function hl_version(){ -// rel -return '1.1.20'; -// eof -} - -function kses($t, $h, $p=array('http', 'https', 'ftp', 'news', 'nntp', 'telnet', 'gopher', 'mailto')){ -// kses compat -foreach($h as $k=>$v){ - $h[$k]['n']['*'] = 1; -} -$C['cdata'] = $C['comment'] = $C['make_tag_strict'] = $C['no_deprecated_attr'] = $C['unique_ids'] = 0; -$C['keep_bad'] = 1; -$C['elements'] = count($h) ? strtolower(implode(',', array_keys($h))) : '-*'; -$C['hook'] = 'kses_hook'; -$C['schemes'] = '*:'. implode(',', $p); -return htmLawed($t, $C, $h); -// eof -} - -function kses_hook($t, &$C, &$S){ -// kses compat -return $t; -// eof -} diff --git a/extlib/htmLawed/htmLawedTest.php b/extlib/htmLawed/htmLawedTest.php deleted file mode 100755 index 8604b69de0..0000000000 --- a/extlib/htmLawed/htmLawedTest.php +++ /dev/null @@ -1,650 +0,0 @@ - $v){ - $_POST[$k] = stripslashes($v); - } - ini_set('magic_quotes_gpc', 0); -} -if(get_magic_quotes_runtime()){ - set_magic_quotes_runtime(0); -} - -$_POST['enc'] = (isset($_POST['enc']) and preg_match('`^[-\w]+$`', $_POST['enc'])) ? $_POST['enc'] : 'utf-8'; - -// token for anti-CSRF -if(count($_POST)){ - if((empty($_GET['pre']) and ((!empty($_POST['token']) and !empty($_SESSION['token']) and $_POST['token'] != $_SESSION['token']) or empty($_POST[$_sid]) or $_POST[$_sid] != session_id() or empty($_COOKIE[$_sid]) or $_COOKIE[$_sid] != session_id())) or ($_POST[$_sid] != session_id())){ - $_POST = array('enc'=>'utf-8'); - } -} -if(empty($_GET['pre'])){ - $_SESSION['token'] = md5(uniqid(rand(), 1)); - $token = $_SESSION['token']; - session_regenerate_id(1); -} - -// compress -if(function_exists('gzencode') && isset($_SERVER['HTTP_ACCEPT_ENCODING']) && preg_match('`gzip|deflate`i', $_SERVER['HTTP_ACCEPT_ENCODING']) && !ini_get('zlib.output_compression')){ - ob_start('ob_gzhandler'); -} - -// HTM for unprocessed -if(isset($_POST['inputH'])){ - echo 'htmLawed test: HTML view of unprocessed input

          Rendering of unprocessed input without an HTML doctype or charset declaration     close window | htmLawed test page

        ', $_POST['inputH'], '
        '; - exit; -} - -// main -$_POST['text'] = isset($_POST['text']) ? $_POST['text'] : 'text to process; < '. $_limit. ' characters'. ($_hlimit ? ' (for binary hexdump view, < '. $_hlimit. ')' : ''); -$do = (!empty($_POST[$_sid]) && isset($_POST['text'][0]) && !isset($_POST['text'][$_limit])) ? 1 : 0; -$limit_exceeded = isset($_POST['text'][$_limit]) ? 1 : 0; -$pre_mem = memory_get_usage(); -$validation = (!empty($_POST[$_sid]) and isset($_POST['w3c_validate'][0])) ? 1 : 0; -include './htmLawed.php'; - -function format($t){ - $t = "\n". str_replace(array("\t", "\r\n", "\r", '&', '<', '>', "\n"), array(' ', "\n", "\n", '&', '<', '>', "¬
        \n"), $t); - return str_replace(array('
        ', "\n ", ' '), array("\n
        \n", "\n ", '  '), $t); -} - -function hexdump($d){ -// Mainly by Aidan Lister , Peter Waller - $hexi = ''; - $ascii = ''; - ob_start(); - echo '
        ';
- $offset = 0;
- $len = strlen($d);
- for($i=$j=0; $i<$len; $i++)
- {
-  // Convert to hexidecimal
-  $hexi .= sprintf("%02X ", ord($d[$i]));
-  // Replace non-viewable bytes with '.'
-  if(ord($d[$i]) >= 32){
-   $ascii .= htmlspecialchars($d[$i]);
-  }else{
-   $ascii .= '.';
-  } 
-  // Add extra column spacing
-  if($j == 7){
-   $hexi .= ' ';
-   $ascii .= '  ';
-  }
-  // Add row
-  if(++$j == 16 || $i == $len-1){
-   // Join the hexi / ascii output
-   echo sprintf("%04X   %-49s   %s", $offset, $hexi, $ascii);   
-   // Reset vars
-   $hexi = $ascii = '';
-   $offset += 16;
-   $j = 0;  
-   // Add newline   
-   if ($i !== $len-1){
-    echo "\n";
-   }
-  }
- }
- echo '
        '; - $o = ob_get_contents(); - ob_end_clean(); - return $o; -} -?> - - - - - - - - -htmLawed (<?php echo hl_version();?>) test - - -
        - -
        HTMLAWED TEST
        -htm / txt documentation
        - -Input » (max. chars) - -
        - -
        - - -
        - - -'; - } -?> - - - - - - - - - - Validator tools: '; - } -} -?> - -Encoding: - -
        -
        - -Input text is too long!
        '; -} -?> - -
        - -Settings » - - -
        - -$v){ - if($k[0] == 'h' && $v != 'nil'){ - $cfg[substr($k, 1)] = $v; - } - } - - if(isset($cfg['anti_link_spam']) && $cfg['anti_link_spam'] && (!empty($cfg['anti_link_spam11']) or !empty($cfg['anti_link_spam12']))){ - $cfg['anti_link_spam'] = array($cfg['anti_link_spam11'], $cfg['anti_link_spam12']); - } - unset($cfg['anti_link_spam11'], $cfg['anti_link_spam12']); - if(isset($cfg['anti_mail_spam']) && $cfg['anti_mail_spam'] == 1){ - $cfg['anti_mail_spam'] = isset($cfg['anti_mail_spam1'][0]) ? $cfg['anti_mail_spam1'] : 0; - } - unset($cfg['anti_mail_spam11']); - if(isset($cfg['deny_attribute']) && $cfg['deny_attribute'] == 1){ - $cfg['deny_attribute'] = isset($cfg['deny_attribute1'][0]) ? $cfg['deny_attribute1'] : 0; - } - unset($cfg['deny_attribute1']); - if(isset($cfg['tidy']) && $cfg['tidy'] == 2){ - $cfg['tidy'] = isset($cfg['tidy2'][0]) ? $cfg['tidy2'] : 0; - } - unset($cfg['tidy2']); - if(isset($cfg['unique_ids']) && $cfg['unique_ids'] == 2){ - $cfg['unique_ids'] = isset($cfg['unique_ids2'][0]) ? $cfg['unique_ids2'] : 1; - } - unset($cfg['unique_ids2']); - unset($cfg['and_mark']); // disabling and_mark - - $cfg['show_setting'] = 'hlcfg'; - $st = microtime(); - $out = htmLawed($_POST['text'], $cfg, $_POST['spec']); - $et = microtime(); - echo '
        Input code » ', strlen($_POST['text']), ' chars, ~', ($tag = round((substr_count($_POST['text'], '>') + substr_count($_POST['text'], '<'))/2)), ' tag', ($tag > 1 ? 's' : ''), ' ', (!isset($_POST['text'][$_hlimit]) ? ' Input binary » ' : ''), ' Finalized internal settings »  ', '
        Output » htmLawed processing time ', number_format(((substr($et,0,9)) + (substr($et,-10)) - (substr($st,0,9)) - (substr($st,-10))),4), ' s', (($mem = memory_get_peak_usage()) !== false ? ', peak memory usage '. round(($mem-$pre_mem)/1048576, 2). ' MB' : ''), '
        '; - if($_w3c_validate && $validation) - { -?> - - - - -
        Output code »
        ', format($out), '
        ', (!isset($_POST['text'][$_hlimit]) ? ' Output binary »' : ''), ' Diff »
        Output rendered »
        ', $out, '
        '; -} -else{ -?> - -
        - -
        Use with a Javascript- and cookie-enabled, relatively new version of a common browser. Submitted input will also be HTML-rendered (XHTML 1) after htmLawed-filtering. - -
        You can use text from this collection of test-cases in the input. Set the character encoding of the browser to Unicode/utf-8 before copying.' : ''); ?> - -

        For anti-XSS tests, try the special test-page or see these results. - -

        Change Encoding to reflect the character encoding of the input text. Even then, it may not work or some characters may not display properly because of variable browser support and because of the form interface. Developers can write some PHP code to capture the filtered input to a file if this is important. -

        Refer to the htmLawed documentation (htm/txt) for details about Settings, and htmLawed's behavior and limitations. For Settings, incorrectly-specified values like regular expressions are silently ignored. One or more settings form-fields may have been disabled. Some characters are not allowed in the Spec field. - - -

        Hovering the mouse over some of the text can provide additional information in some browsers.         - - - -

        Because of character-encoding issues, the W3C validator (anyway not perfect) may reject validation requests or invalidate otherwise-valid code, esp. if text was copy-pasted in the input box. Local applications like the HTML Validator Firefox browser add-on may be useful in such cases.         - - - -
        - - - -
        - - diff --git a/extlib/htmLawed/htmLawed_README.htm b/extlib/htmLawed/htmLawed_README.htm deleted file mode 100644 index 3c643b7fc1..0000000000 --- a/extlib/htmLawed/htmLawed_README.htm +++ /dev/null @@ -1,2188 +0,0 @@ - - - - - - - - -htmLawed documentation | htmLawed PHP software is a free, open-source, customizable HTML input purifier and filter - - -
        -

        htmLawed documentation

        - -
        1  About htmLawed
        -  1.1  Example uses
        -  1.2  Features
        -  1.3  History
        -  1.4  License & copyright
        -  1.5  Terms used here
        -2  Usage
        -  2.1  Simple
        -  2.2  Configuring htmLawed using the $config parameter
        -  2.3  Extra HTML specifications using the $spec parameter
        -  2.4  Performance time & memory usage
        -  2.5  Some security risks to keep in mind
        -  2.6  Use without modifying old kses() code
        -  2.7  Tolerance for ill-written HTML
        -  2.8  Limitations & work-arounds
        -  2.9  Examples of usage
        -3  Details
        -  3.1  Invalid/dangerous characters
        -  3.2  Character references/entities
        -  3.3  HTML elements
        -    3.3.1  HTML comments and CDATA sections
        -    3.3.2  Tag-transformation for better XHTML-Strict
        -    3.3.3  Tag balancing and proper nesting
        -    3.3.4  Elements requiring child elements
        -    3.3.5  Beautify or compact HTML
        -  3.4  Attributes
        -    3.4.1  Auto-addition of XHTML-required attributes
        -    3.4.2  Duplicate/invalid id values
        -    3.4.3  URL schemes (protocols) and scripts in attribute values
        -    3.4.4  Absolute & relative URLs
        -    3.4.5  Lower-cased, standard attribute values
        -    3.4.6  Transformation of deprecated attributes
        -    3.4.7  Anti-spam & href
        -    3.4.8  Inline style properties
        -    3.4.9  Hook function for tag content
        -  3.5  Simple configuration directive for most valid XHTML
        -  3.6  Simple configuration directive for most safe HTML
        -  3.7  Using a hook function
        -  3.8  Obtaining finalized parameter values
        -  3.9  Retaining non-HTML tags in input with mixed markup
        -4  Other
        -  4.1  Support
        -  4.2  Known issues
        -  4.3  Change-log
        -  4.4  Testing
        -  4.5  Upgrade, & old versions
        -  4.6  Comparison with HTMLPurifier
        -  4.7  Use through application plug-ins/modules
        -  4.8  Use in non-PHP applications
        -  4.9  Donate
        -  4.10  Acknowledgements
        -5  Appendices
        -  5.1  Characters discouraged in HTML
        -  5.2  Valid attribute-element combinations
        -  5.3  CSS 2.1 properties accepting URLs
        -  5.4  Microsoft Windows 1252 character replacements
        -  5.5  URL format
        -  5.6  Brief on htmLawed code
        - -
        -
        -
        htmLawed_README.txt, 9 June 2015
        -htmLawed 1.1.20, 9 June 2015
        -Copyright Santosh Patnaik
        -Dual licensed with LGPL 3 and GPL 2+
        -A PHP Labware internal utility - http://www.bioinformatics.org/phplabware/internal_utilities/htmLawed 
        -
        - -

        -1  About htmLawed -

        (to top)
        -
        -  htmLawed is a PHP script to process text with HTML markup to make it more compliant with HTML standards and administrative policies. It works by making HTML well-formed with balanced and properly nested tags, neutralizing code that may be used for cross-site scripting (XSS) attacks, allowing only specified HTML tags and attributes, and so on. Such lawing in of HTML in text used in (X)HTML or XML documents ensures that it is in accordance with the aesthetics, safety and usability requirements set by administrators.
        -
        -  htmLawed is highly customizable, and fast with low memory usage. Its free and open-source code is in one small file, does not require extensions or libraries, and works in older versions of PHP as well. It is a good alternative to the HTML Tidy application.
        - -

        -1.1  Example uses -

        (to top)
        -
        -  *  Filtering of text submitted as comments on blogs to allow only certain HTML elements
        -
        -  *  Making RSS/Atom newsfeed item-content standard-compliant: often one uses an excerpt from an HTML document for the content, and with unbalanced tags, non-numerical entities, etc., such excerpts may not be XML-compliant
        -
        -  *  Text processing for stricter XML standard-compliance: e.g., to have lowercased x in hexadecimal numeric entities becomes necessary if an XHTML document with MathML content needs to be served as application/xml
        -
        -  *  Scraping text or data from web-pages
        -
        -  *  Pretty-printing HTML code
        - -
        -

        -1.2  Features -

        (to top)
        -
        -  Key: * security feature, ^ standard compliance, ~ requires setting right options, ` different from Kses
        -
        -  *  make input more secure and standard-compliant
        -  *  use for HTML 4, XHTML 1.0 or 1.1, or even generic XML documents  ^~`
        -
        -  *  beautify or compact HTML  ^~`
        -
        -  *  can restrict elements  ^~`
        -  *  ensures proper closure of empty elements like img  ^`
        -  *  transform deprecated elements like u  ^~`
        -  *  HTML comments and CDATA sections can be permitted  ^~`
        -  *  elements like script, object and form can be permitted  ~
        -
        -  *  restrict attributes, including element-specifically  ^~`
        -  *  remove invalid attributes  ^`
        -  *  element and attribute names are lower-cased  ^
        -  *  provide required attributes, like alt for image  ^`
        -  *  transforms deprecated attributes  ^~`
        -  *  attributes declared only once  ^`
        -
        -  *  restrict attribute values, including element-specifically  ^~`
        -  *  a value is declared for empty (minimized) attributes like checked  ^
        -  *  check for potentially dangerous attribute values  *~
        -  *  ensure unique id attribute values  ^~`
        -  *  double-quote attribute values  ^
        -  *  lower-case standard attribute values like password  ^`
        -  *  permit custom, non-standard attributes as well as custom rules for standard attributes  ~`
        -
        -  *  attribute-specific URL protocol/scheme restriction  *~`
        -  *  disable dynamic expressions in style values  *~`
        -
        -  *  neutralize invalid named character entities  ^`
        -  *  convert hexadecimal numeric entities to decimal ones, or vice versa  ^~`
        -  *  convert named entities to numeric ones for generic XML use  ^~`
        -
        -  *  remove null characters  *
        -  *  neutralize potentially dangerous proprietary Netscape Javascript entities  *
        -  *  replace potentially dangerous soft-hyphen character in URL-accepting attribute values with spaces  *
        -
        -  *  remove common invalid characters not allowed in HTML or XML  ^`
        -  *  replace characters from Microsoft applications like Word that are discouraged in HTML or XML  ^~`
        -  *  neutralize entities for characters invalid or discouraged in HTML or XML  ^`
        -  *  appropriately neutralize <, &, ", and > characters  ^*`
        -
        -  *  understands improperly spaced tag content (like, spread over more than a line) and properly spaces them  `
        -  *  attempts to balance tags for well-formedness  ^~`
        -  *  understands when omitable closing tags like </p> (allowed in HTML 4, transitional, e.g.) are missing  ^~`
        -  *  attempts to permit only validly nested tags  ^~`
        -  *  option to remove or neutralize bad content ^~`
        -  *  attempts to rectify common errors of plain-text misplacement (e.g., directly inside blockquote) ^~`
        -
        -  *  fast, non-OOP code of ~45 kb incurring peak basal memory usage of ~0.5 MB
        -  *  compatible with pre-existing code using Kses (the filter used by WordPress)
        -
        -  *  optional anti-spam measures such as addition of rel="nofollow" and link-disabling  ~`
        -  *  optionally makes relative URLs absolute, and vice versa  ~`
        -
        -  *  optionally mark & to identify the entities for &, < and > introduced by htmLawed  ~`
        -
        -  *  allows deployment of powerful hook functions to inject HTML, consolidate style attributes to class, finely check attribute values, etc.  ~`
        -
        -  *  independent of character encoding of input and does not affect it
        -
        -  *  tolerance for ill-written HTML to a certain degree
        - -
        -

        -1.3  History -

        (to top)
        -
        -  htmLawed was created in 2007 for use with LabWiki, a wiki software developed at PHP Labware, as a suitable software could not be found. Existing PHP software like Kses and HTMLPurifier were deemed inadequate, slow, resource-intensive, or dependent on an extension or external application like HTML Tidy. The core logic of htmLawed, that of identifying HTML elements and attributes, was based on the Kses (version 0.2.2) HTML filter software of Ulf Harnhammar (it can still be used with code that uses Kses; see section 2.6.).
        -
        -  See section 4.3 for a detailed log of changes in htmLawed over the years, and section 4.10 for acknowledgements.
        - -
        -

        -1.4  License & copyright -

        (to top)
        -
        -  htmLawed is free and open-source software dual copyrighted by Santosh Patnaik, MD, PhD, and licensed under LGPL license version 3, and GPL license version 2 (or later).
        - -
        -

        -1.5  Terms used here -

        (to top)
        -
        -  In this document, only HTML body-level elements are considered. htmLawed does not have support for head-level elements, body, and the frame-level elements, frameset, frame and noframes, and these elements are ignored here.
        -
        -  *  administrator - or admin; person setting up the code that utilizes htmLawed; also, user
        -  *  attributes - name-value pairs like href="http://x.com" in opening tags
        -  *  author - see writer
        -  *  character - atomic unit of text; internally represented by a numeric code-point as specified by the encoding or charset in use
        -  *  entity - markup like &gt; and &#160; used to refer to a character
        -  *  element - HTML element like a and img
        -  *  element content -  content between the opening and closing tags of an element, like click of the <a href="x">click</a> element
        -  *  HTML - implies XHTML unless specified otherwise
        -  *  HTML body - Complete HTML documents typically have a head and a body container. Information in head specifies title of the document, etc., whereas that in the body informs what is to be displayed on a web-page; it is only the elements for body, except frames, frameset and noframes that htmLawed is concerned with
        -  *  input - text given to htmLawed to process
        -  *  processing - involves filtering, correction, etc., of input
        -  *  safe - absence or reduction of certain characters and HTML elements and attributes in HTML of text that can otherwise potentially, and circumstantially, expose text readers to security vulnerabilities like cross-site scripting attacks (XSS)
        -  *  scheme - a URL protocol like http and ftp
        -  *  specifications - standard specifications, for HTML4, HTML5, Ruby, etc.
        -  *  style property - terms like border and height for which declarations are made in values for the style attribute of elements
        -  *  tag - markers like <a href="x"> and </a> delineating element content; the opening tag can contain attributes
        -  *  tag content - consists of tag markers < and >, element names like div, and possibly attributes
        -  *  user - administrator
        -  *  writer - end-user like a blog commenter providing the input that is to be processed; also, author
        - -
        -

        -1.6  Availability -

        (to top)
        -
        -  htmLawed can be downloaded for free at its website. Besides the htmLawed.php file, the download has the htmLawed documentation (this document) in plain text and HTML formats, a script for testing, and a text file for test-cases. htmLawed is also available as a PHP class (OOP code) on its website.
        - -
        -
        -

        -2  Usage -

        (to top)
        -
        -  htmLawed works in PHP version 4.4 or higher. Either include() the htmLawed.php file, or copy-paste the entire code. To use with PHP 4.3, have the following code included:
        -
        - -    if(!function_exists('ctype_digit')){ -
        - -     function ctype_digit($var){ -
        - -      return ((int) $var == $var); -
        - -     } -
        - -    } -
        - -

        -2.1  Simple -

        (to top)
        -
        -  The input text to be processed, $text, is passed as an argument of type string; htmLawed() returns the processed string:
        -
        - -    $processed = htmLawed($text); -
        -
        -  With the htmLawed class (section 1.6), usage is:
        -
        - -    $processed = htmLawed::hl($text); -
        -
        -  Notes: (1) If input is from a $_GET or $_POST value, and magic quotes are enabled on the PHP setup, run stripslashes() on the input before passing to htmLawed. (2) htmLawed does not have support for head-level elements, body, and the frame-level elements, frameset, frame and noframes.
        -
        -  By default, htmLawed will process the text allowing all valid HTML elements/tags, secure URL scheme/CSS style properties, etc. It will allow CDATA sections and HTML comments, balance tags, and ensure proper nesting of elements. Such actions can be configured using two other optional arguments -- $config and $spec:
        -
        - -    $processed = htmLawed($text, $config, $spec); -
        -
        -  The $config and $spec arguments are detailed below. Some examples are shown in section 2.9. For maximum protection against XSS and other scripting attacks (e.g., by disallowing Javascript code), consider using the safe parameter; see section 3.6.
        - -
        -

        -2.2  Configuring htmLawed using the $config parameter -

        (to top)
        -
        -  $config instructs htmLawed on how to tackle certain tasks. When $config is not specified, or not set as an array (e.g., $config = 1), htmLawed will take default actions. One or many of the task-action or value-specification pairs can be specified in $config as array key-value pairs. If a parameter is not specified, htmLawed will use the default value/action indicated further below.
        -
        - -    $config = array('comment'=>0, 'cdata'=>1); -
        - -    $processed = htmLawed($text, $config); -
        -
        -  Or,
        -
        - -    $processed = htmLawed($text, array('comment'=>0, 'cdata'=>1)); -
        -
        -  Below are the possible value-specification combinations. In PHP code, values that are integers should not be quoted and should be used as numeric types (unless meant as string/text).
        -
        -  Key: * default, ^ different default when htmLawed is used in the Kses-compatible mode (see section 2.6), ~ different default when valid_xhtml is set to 1 (see section 3.5), " different default when safe is set to 1 (see section 3.6)
        -
        -  abs_url
        -  Make URLs absolute or relative; $config["base_url"] needs to be set; see section 3.4.4
        -
        -  -1 - make relative
        -  0 - no action  *
        -  1 - make absolute
        -
        -  and_mark
        -  Mark & characters in the original input; see section 3.2
        -
        -  anti_link_spam
        -  Anti-link-spam measure; see section 3.4.7
        -
        -  0 - no measure taken  *
        -  array("regex1", "regex2") - will ensure a rel attribute with nofollow in its value in case the href attribute value matches the regular expression pattern regex1, and/or will remove href if its value matches the regular expression pattern regex2. E.g., array("/./", "/://\W*(?!(abc\.com|xyz\.org))/"); see section 3.4.7 for more.
        -
        -  anti_mail_spam
        -  Anti-mail-spam measure; see section 3.4.7
        -
        -  0 - no measure taken  *
        -  word - @ in mail address in href attribute value is replaced with specified word
        -
        -  balance
        -  Balance tags for well-formedness and proper nesting; see section 3.3.3
        -
        -  0 - no
        -  1 - yes  *
        -
        -  base_url
        -  Base URL value that needs to be set if $config["abs_url"] is not 0; see section 3.4.4
        -
        -  cdata
        -  Handling of CDATA sections; see section 3.3.1
        -
        -  0 - don't consider CDATA sections as markup and proceed as if plain text  ^"
        -  1 - remove
        -  2 - allow, but neutralize any <, >, and & inside by converting them to named entities
        -  3 - allow  *
        -
        -  clean_ms_char
        -  Replace discouraged characters introduced by Microsoft Word, etc.; see section 3.1
        -
        -  0 - no  *
        -  1 - yes
        -  2 - yes, but replace special single & double quotes with ordinary ones
        -
        -  comment
        -  Handling of HTML comments; see section 3.3.1
        -
        -  0 - don't consider comments as markup and proceed as if plain text  ^"
        -  1 - remove
        -  2 - allow, but neutralize any <, >, and & inside by converting to named entities
        -  3 - allow  *
        -
        -  css_expression
        -  Allow dynamic CSS expression by not removing the expression from CSS property values in style attributes; see section 3.4.8
        -
        -  0 - remove  *
        -  1 - allow
        -
        -  deny_attribute
        -  Denied HTML attributes; see section 3.4
        -
        -  0 - none  *
        -  string - dictated by values in string
        -  on* (like onfocus) attributes not allowed - "
        -
        -  direct_nest_list
        -  Allow direct nesting of a list within another without requiring it to be a list item; see section 3.3.4
        -
        -  0 - no  *
        -  1 - yes
        -
        -  elements
        -  Allowed HTML elements; see section 3.3
        -
        -  * -center -dir -font -isindex -menu -s -strike -u -  ~
        -  applet, embed, iframe, object, script not allowed - "
        -
        -  hexdec_entity
        -  Allow hexadecimal numeric entities and do not convert to the more widely accepted decimal ones, or convert decimal to hexadecimal ones; see section 3.2
        -
        -  0 - no
        -  1 - yes  *
        -  2 - convert decimal to hexadecimal ones
        -
        -  hook
        -  Name of an optional hook function to alter the input string, $config or $spec before htmLawed starts its main work; see section 3.7
        -
        -  0 - no hook function  *
        -  name - name is name of the hook function (kses_hook  ^)
        -
        -  hook_tag
        -  Name of an optional hook function to alter tag content finalized by htmLawed; see section 3.4.9
        -
        -  0 - no hook function  *
        -  name - name is name of the hook function
        -
        -  keep_bad
        -  Neutralize bad tags by converting < and > to entities, or remove them; see section 3.3.3
        -
        -  0 - remove  ^
        -  1 - neutralize both tags and element content
        -  2 - remove tags but neutralize element content
        -  3 and 4 - like 1 and 2 but remove if text (pcdata) is invalid in parent element
        -  5 and 6 * -  like 3 and 4 but line-breaks, tabs and spaces are left
        -
        -  lc_std_val
        -  For XHTML compliance, predefined, standard attribute values, like get for the method attribute of form, must be lowercased; see section 3.4.5
        -
        -  0 - no
        -  1 - yes  *
        -
        -  make_tag_strict
        -  Transform/remove these non-strict XHTML elements, even if they are allowed by the admin: applet center dir embed font isindex menu s strike u; see section 3.3.2
        -
        -  0 - no  ^
        -  1 - yes, but leave applet, embed and isindex elements that currently can't be transformed  *
        -  2 - yes, removing applet, embed and isindex elements and their contents (nested elements remain)  ~
        -
        -  named_entity
        -  Allow non-universal named HTML entities, or convert to numeric ones; see section 3.2
        -
        -  0 - convert
        -  1 - allow  *
        -
        -  no_deprecated_attr
        -  Allow deprecated attributes or transform them; see section 3.4.6
        -
        -  0 - allow  ^
        -  1 - transform, but name attributes for a and map are retained  *
        -  2 - transform
        -
        -  parent
        -  Name of the parent element, possibly imagined, that will hold the input; see section 3.3
        -
        -  safe
        -  Magic parameter to make input the most secure against XSS without needing to specify other relevant $config parameters; see section 3.6
        -
        -  0 - no  *
        -  1 - will auto-adjust other relevant $config parameters (indicated by " in this list)
        -
        -  schemes
        -  Array of attribute-specific, comma-separated, lower-cased list of schemes (protocols) allowed in attributes accepting URLs (or ! to deny any URL); * covers all unspecified attributes; see section 3.4.3
        -
        -  href: aim, feed, file, ftp, gopher, http, https, irc, mailto, news, nntp, sftp, ssh, telnet; *:file, http, https  *
        -  *: ftp, gopher, http, https, mailto, news, nntp, telnet  ^
        -  href: aim, feed, file, ftp, gopher, http, https, irc, mailto, news, nntp, sftp, ssh, telnet; style: !; *:file, http, https  "
        -
        -  show_setting
        -  Name of a PHP variable to assign the finalized $config and $spec values; see section 3.8
        -
        -  style_pass
        -  Do not look at style attribute values, letting them through without any alteration
        -
        -  0 - no *
        -  1 - htmLawed will let through any style value; see section 3.4.8
        -
        -  tidy
        -  Beautify or compact HTML code; see section 3.3.5
        -
        -  -1 - compact
        -  0 - no  *
        -  1 or string - beautify (custom format specified by string)
        -
        -  unique_ids
        -  id attribute value checks; see section 3.4.2
        -
        -  0 - no  ^
        -  1 - remove duplicate and/or invalid ones  *
        -  word - remove invalid ones and replace duplicate ones with new and unique ones based on the word; the admin-specified word, like my_, should begin with a letter (a-z) and can contain letters, digits, ., _, -, and :.
        -
        -  valid_xhtml
        -  Magic parameter to make input the most valid XHTML without needing to specify other relevant $config parameters; see section 3.5
        -
        -  0 - no  *
        -  1 - will auto-adjust other relevant $config parameters (indicated by ~ in this list)
        -
        -  xml:lang
        -  Auto-adding xml:lang attribute; see section 3.4.1
        -
        -  0 - no  *
        -  1 - add if lang attribute is present
        -  2 - add if lang attribute is present, and remove lang  ~
        - -
        -

        -2.3  Extra HTML specifications using the $spec parameter -

        (to top)
        -
        -  The $spec argument of htmLawed can be used to disallow an otherwise legal attribute for an element, or to restrict the attribute's values. This can also be helpful as a security measure (e.g., in certain versions of browsers, certain values can cause buffer overflows and denial of service attacks), or in enforcing admin policies. $spec is specified as a string of text containing one or more rules, with multiple rules separated from each other by a semi-colon (;). E.g.,
        -
        - -    $spec = 'i=-*; td, tr=style, id, -*; a=id(match="/[a-z][a-z\d.:\-`"]*/i"/minval=2), href(maxlen=100/minlen=34); img=-width,-alt'; -
        - -    $processed = htmLawed($text, $config, $spec); -
        -
        -  Or,
        -
        - -    $processed = htmLawed($text, $config, 'i=-*; td, tr=style, id, -*; a=id(match="/[a-z][a-z\d.:\-`"]*/i"/minval=2), href(maxlen=100/minlen=34); img=-width,-alt'); -
        -
        -  A rule begins with an HTML element name(s) (rule-element), for which the rule applies, followed by an equal (=) sign. A rule-element may represent multiple elements if comma (,)-separated element names are used. E.g., th,td,tr=.
        -
        -  Rest of the rule consists of comma-separated HTML attribute names. A minus (-) character before an attribute means that the attribute is not permitted inside the rule-element. E.g., -width. To deny all attributes, -* can be used.
        -
        -  Following shows examples of rule excerpts with rule-element a and the attributes that are being permitted:
        -
        -  *  a= - all
        -  *  a=id - all
        -  *  a=href, title, -id, -onclick - all except id and onclick
        -  *  a=*, id, -id - all except id
        -  *  a=-* - none
        -  *  a=-*, href, title - none except href and title
        -  *  a=-*, -id, href, title - none except href and title
        -
        -  Rules regarding attribute values are optionally specified inside round brackets after attribute names in slash ('/')-separated parameter = value pairs. E.g., title(maxlen=30/minlen=5). None or one or more of the following parameters may be specified:
        -
        -  *  oneof - one or more choices separated by | that the value should match; if only one choice is provided, then the value must match that choice
        -
        -  *  noneof - one or more choices separated by | that the value should not match
        -
        -  *  maxlen and minlen - upper and lower limits for the number of characters in the attribute value; specified in numbers
        -
        -  *  maxval and minval - upper and lower limits for the numerical value specified in the attribute value; specified in numbers
        -
        -  *  match and nomatch - pattern that the attribute value should or should not match; specified as PHP/PCRE-compatible regular expressions with delimiters and possibly modifiers
        -
        -  *  default - a value to force on the attribute if the value provided by the writer does not fit any of the specified parameters
        -
        -  If default is not set and the attribute value does not satisfy any of the specified parameters, then the attribute is removed. The default value can also be used to force all attribute declarations to take the same value (by getting the values declared illegal by setting, e.g., maxlen to -1).
        -
        -  Examples with input <input title="WIDTH" value="10em" /><input title="length" value="5" /> are shown below.
        -
        -  Rule: input=title(maxlen=60/minlen=6), value
        -  Output: <input value="10em" /><input title="length" value="5" />
        -
        -  Rule: input=title(), value(maxval=8/default=6)
        -  Output: <input title="WIDTH" value="6" /><input title="length" value="5" />
        -
        -  Rule: input=title(nomatch=%w.d%i), value(match=%em%/default=6em)
        -  Output: <input value="10em" /><input title="length" value="6em" />
        -
        -  Rule: input=title(oneof=height|depth/default=depth), value(noneof=5|6)
        -  Output: <input title="depth" value="10em" /><input title="depth" />
        -
        -  Special characters: The characters ;, ,, /, (, ), |, ~ and space have special meanings in the rules. Words in the rules that use such characters, or the characters themselves, should be escaped by enclosing in pairs of double-quotes ("). A back-tick (`) can be used to escape a literal ". An example rule illustrating this is input=value(maxlen=30/match="/^\w/"/default="your `"ID`"").
        -
        -  Note: To deny an attribute for all elements for which it is legal, $config["deny_attribute"] (see section 3.4) can be used instead of $spec. Also, attributes can be allowed element-specifically through $spec while being denied globally through $config["deny_attribute"]. The hook_tag parameter (section 3.4.9) can also be possibly used to implement a functionality like that achieved using $spec functionality.
        -
        -  $spec can also be used to permit custom, non-standard attributes as well as custom rules for standard attributes. Thus, the following value of $spec will permit the custom uses of the standard rel attribute in input (not permitted as per standards) and of a non-standard attribute, vFlag, in img.
        -
        - -    $spec = 'img=vFlag; input=rel' -
        -
        -  The attribute names can contain alphabets, colons (:) and hyphens (-), but they must start with an alphabet.
        - -
        -

        -2.4  Performance time & memory usage -

        (to top)
        -
        -  The time and memory consumed during text processing by htmLawed depends on its configuration, the size of the input, and the amount, nestedness and well-formedness of the HTML markup within the input. In particular, tag balancing and beautification each can increase the processing time by about a quarter.
        -
        -  The htmLawed demo can be used to evaluate the performance and effects of different types of input and $config.
        - -
        -

        -2.5  Some security risks to keep in mind -

        (to top)
        -
        -  When setting the parameters/arguments (like those to allow certain HTML elements) for use with htmLawed, one should bear in mind that the setting may let through potentially dangerous HTML code which is meant to steal user-data, deface a website, render a page non-functional, etc. Unless end-users, either people or software, supplying the content are completely trusted, security issues arising from the degree of HTML usage permitted through htmLawed's setting should be considered. For example, following increase security risks:
        -
        -  *  Allowing script, applet, embed, iframe or object elements, or certain of their attributes like allowscriptaccess
        -
        -  *  Allowing HTML comments (some Internet Explorer versions are vulnerable with, e.g., <!--[if gte IE 4]><script>alert("xss");</script><![endif]-->
        -
        -  *  Allowing dynamic CSS expressions (some Internet Explorer versions are vulnerable)
        -
        -  *  Allowing the style attribute
        -
        -  To remove unsecure HTML, code-developers using htmLawed must set $config appropriately. E.g., $config["elements"] = "* -script" to deny the script element (section 3.3), $config["safe"] = 1 to auto-configure ceratin htmLawed parameters for maximizing security (section 3.6), etc.
        -
        -  Permitting the *style* attribute brings in risks of click-jacking, phishing, web-page overlays, etc., even when the safe parameter is enabled (see section 3.6). Except for URLs and a few other things like CSS dynamic expressions, htmLawed currently does not check every CSS style property. It does provide ways for the code-developer implementing htmLawed to do such checks through htmLawed's $spec argument, and through the hook_tag parameter (see section 3.4.8 for more). Disallowing style completely and relying on CSS classes and stylesheet files is recommended.
        -
        -  htmLawed does not check or correct the character encoding of the input it receives. In conjunction with permissive circumstances, such as when the character encoding is left undefined through HTTP headers or HTML meta tags, this can allow for an exploit (like Google's UTF-7/XSS vulnerability of the past).
        - -
        -

        -2.6  Use without modifying old kses() code -

        (to top)
        -
        -  The Kses PHP script is used by many applications (like WordPress). It is possible to have such applications use htmLawed instead, since it is compatible with code that calls the kses() function declared in the Kses file (usually named kses.php). E.g., application code like this will continue to work after replacing Kses with htmLawed:
        -
        - -    $comment_filtered = kses($comment_input, array('a'=>array(), 'b'=>array(), 'i'=>array())); -
        -
        -  For some of the $config parameters, htmLawed will use values other than the default ones. These are indicated by ^ in section 2.2. To force htmLawed to use other values, function kses() in the htmLawed code should be edited -- a few configurable parameters/variables need to be changed.
        -
        -  If the application uses a Kses file that has the kses() function declared, then, to have the application use htmLawed instead of Kses, simply rename htmLawed.php (to kses.php, e.g.) and replace the Kses file (or just replace the code in the Kses file with the htmLawed code). If the kses() function in the Kses file had been renamed by the application developer (e.g., in WordPress, it is named wp_kses()), then appropriately rename the kses() function in the htmLawed code.
        -
        -  If the Kses file used by the application has been highly altered by the application developers, then one may need a different approach. E.g., with WordPress, it is best to copy the htmLawed code to wp_includes/kses.php, rename the newly added function kses() to wp_kses(), and delete the code for the original wp_kses() function.
        -
        -  If the Kses code has a non-empty hook function (e.g., wp_kses_hook() in case of WordPress), then the code for htmLawed's kses_hook() function should be appropriately edited. However, the requirement of the hook function should be re-evaluated considering that htmLawed has extra capabilities. With WordPress, the hook function is an essential one. The following code is suggested for the htmLawed kses_hook() in case of WordPress:
        -
        - -    function kses_hook($string, &$cf, &$spec){ -
        - -    // kses compatibility -
        - -    $allowed_html = $spec; -
        - -    $allowed_protocols = array(); -
        - -    foreach($cf['schemes'] as $v){ -
        - -     foreach($v as $k2=>$v2){ -
        - -      if(!in_array($k2, $allowed_protocols)){ -
        - -       $allowed_protocols[] = $k2; -
        - -      } -
        - -     } -
        - -    } -
        - -    return wp_kses_hook($string, $allowed_html, $allowed_protocols); -
        - -    // eof -
        - -    } -
        - -
        -

        -2.7  Tolerance for ill-written HTML -

        (to top)
        -
        -  htmLawed can work with ill-written HTML code in the input. However, HTML that is too ill-written may not be read as HTML, and may therefore get identified as mere plain text. Following statements indicate the degree of looseness that htmLawed can work with, and can be provided in instructions to writers:
        -
        -  *  Tags must be flanked by < and > with no > inside -- any needed > should be put in as &gt;. It is possible for tag content (element name and attributes) to be spread over many lines instead of being on one. A space may be present between the tag content and >, like <div > and <img / >, but not after the <.
        -
        -  *  Element and attribute names need not be lower-cased.
        -
        -  *  Attribute string of elements may be liberally spaced with tabs, line-breaks, etc.
        -
        -  *  Attribute values may be single- and not double-quoted.
        -
        -  *  Left-padding of numeric entities (like, &#0160;, &x07ff;) with 0 is okay as long as the number of characters between between the & and the ; does not exceed 8. All entities must end with ; though.
        -
        -  *  Named character entities must be properly cased. Thus, &Lt; or &TILDE; will not be recognized as entities and will be neutralized.
        -
        -  *  HTML comments should not be inside element tags (they can be between tags), and should begin with <!-- and end with -->. Characters like <, >, and & may be allowed inside depending on $config, but any --> inside should be put in as --&gt;. Any -- inside will be automatically converted to -, and a space will be added before the comment delimiter -->.
        -
        -  *  CDATA sections should not be inside element tags, and can be in element content only if plain text is allowed for that element. They should begin with <[CDATA[ and end with ]]>. Characters like <, >, and & may be allowed inside depending on $config, but any ]]> inside should be put in as ]]&gt;.
        -
        -  *  For attribute values, character entities &lt;, &gt; and &amp; should be used instead of characters < and >, and & (when & is not part of a character entity). This applies even for Javascript code in values of attributes like onclick.
        -
        -  *  Characters <, >, & and " that are part of actual Javascript, etc., code in script elements should be used as such and not be put in as entities like &gt;. Otherwise, though the HTML will be valid, the code may fail to work. Further, if such characters have to be used, then they should be put inside CDATA sections.
        -
        -  *  Simple instructions like "an opening tag cannot be present between two closing tags" and "nested elements should be closed in the reverse order of how they were opened" can help authors write balanced HTML. If tags are imbalanced, htmLawed will try to balance them, but in the process, depending on $config["keep_bad"], some code/text may be lost.
        -
        -  *  Input authors should be notified of admin-specified allowed elements, attributes, configuration values (like conversion of named entities to numeric ones), etc.
        -
        -  *  With $config["unique_ids"] not 0 and the id attribute being permitted, writers should carefully avoid using duplicate or invalid id values as even though htmLawed will correct/remove the values, the final output may not be the one desired. E.g., when <a id="home"></a><input id="home" /><label for="home"></label> is processed into
        -<a id="home"></a><input id="prefix_home" /><label for="home"></label>.
        -
        -  *  Even if intended HTML is lost from an ill-written input, the processed output will be more secure and standard-compliant.
        -
        -  *  For URLs, unless $config["scheme"] is appropriately set, writers should avoid using escape characters or entities in schemes. E.g., htt&#112; (which many browsers will read as the harmless http) may be considered bad by htmLawed.
        -
        -  *  htmLawed will attempt to put plain text present directly inside blockquote, form, map and noscript elements (illegal as per the specifications) inside auto-generated div elements.
        - -
        -

        -2.8  Limitations & work-arounds -

        (to top)
        -
        -  htmLawed's main objective is to make the input text more standard-compliant, secure for readers, and free of HTML elements and attributes considered undesirable by the administrator. Some of its current limitations, regardless of this objective, are noted below along with work-arounds.
        -
        -  It should be borne in mind that no browser application is 100% standard-compliant, and that some of the standard specifications (like asking for normalization of white-spacing within textarea elements) are clearly wrong. Regarding security, note that unsafe HTML code is not legally invalid per se.
        -
        -  *  htmLawed is meant for input that goes into the body of HTML documents. HTML's head-level elements are not supported, nor are the frameset elements frameset, frame and noframes. Content of the latter elements can, however, be individually filtered through htmLawed.
        -
        -  *  It cannot transform the non-standard embed elements to the standard-compliant object elements. Yet, it can allow embed elements if permitted (embed is widely used and supported). Admins can certainly use the hook_tag parameter (section 3.4.9) to deploy a custom embed-to-object converter function.
        -
        -  *  The only non-standard element that may be permitted is embed; others like noembed and nobr cannot be permitted without modifying the htmLawed code.
        -
        -  *  It cannot handle input that has non-HTML code like SVG and MathML. One way around is to break the input into pieces and passing only those without non-HTML code to htmLawed. Another is described in section 3.9. A third way may be to some how take advantage of the $config["and_mark"] parameter (see section 3.2).
        -
        -  *  By default, htmLawed won't check many attribute values for standard compliance. E.g., width="20m" with the dimension in non-standard m is let through. Implementing universal and strict attribute value checks can make htmLawed slow and resource-intensive. Admins should look at the hook_tag parameter (section 3.4.9) or $spec to enforce finer checks.
        -
        -  *  The attributes, deprecated (which can be transformed too) or not, that it supports are largely those that are in the specifications. Only a few of the proprietary attributes are supported.
        -
        -  *  Except for contained URLs and dynamic expressions (also optional), htmLawed does not check CSS style property values. Admins should look at using the hook_tag parameter (section 3.4.9) or $spec for finer checks. Perhaps the best option is to disallow style but allow class attributes with the right oneof or match values for class, and have the various class style properties in .css CSS stylesheet files.
        -
        -  *  htmLawed does not parse emoticons, decode BBcode, or wikify, auto-converting text to proper HTML. Similarly, it won't convert line-breaks to br elements. Such functions are beyond its purview. Admins should use other code to pre- or post-process the input for such purposes.
        -
        -  *  htmLawed cannot be used to have links force-opened in new windows (by auto-adding appropriate target and onclick attributes to a). Admins should look at Javascript-based DOM-modifying solutions for this. Admins may also be able to use a custom hook function to enforce such checks (hook_tag parameter; see section 3.4.9).
        -
        -  *  Nesting-based checks are not possible. E.g., one cannot disallow p elements specifically inside td while permitting it elsewhere. Admins may be able to use a custom hook function to enforce such checks (hook_tag parameter; see section 3.4.9).
        -
        -  *  Except for optionally converting absolute or relative URLs to the other type, htmLawed will not alter URLs (e.g., to change the value of query strings or to convert http to https. Having absolute URLs may be a standard-requirement, e.g., when HTML is embedded in email messages, whereas altering URLs for other purposes is beyond htmLawed's goals. Admins may be able to use a custom hook function to enforce such checks (hook_tag parameter; see section 3.4.9).
        -
        -  *  Pairs of opening and closing tags that do not enclose any content (like <em></em>) are not removed. This may be against the standard specifications for certain elements (e.g., table). However, presence of such standard-incompliant code will not break the display or layout of content. Admins can also use simple regex-based code to filter out such code.
        -
        -  *  htmLawed does not check for certain element orderings described in the standard specifications (e.g., in a table, tbody is allowed before tfoot). Admins may be able to use a custom hook function to enforce such checks (hook_tag parameter; see section 3.4.9).
        -
        -  *  htmLawed does not check the number of nested elements. E.g., it will allow two caption elements in a table element, illegal as per the specifications. Admins may be able to use a custom hook function to enforce such checks (hook_tag parameter; see section 3.4.9).
        -
        -  *  htmLawed might convert certain entities to actual characters and remove backslashes and CSS comment-markers (/*) in style attribute values in order to detect malicious HTML like crafted IE-specific dynamic expressions like &#101;xpression.... If this is too harsh, admins can allow CSS expressions through htmLawed core but then use a custom function through the hook_tag parameter (section 3.4.9) to more specifically identify CSS expressions in the style attribute values. Also, using $config["style_pass"], it is possible to have htmLawed pass style attribute values without even looking at them (section 3.4.8).
        -
        -  *  htmLawed does not correct certain possible attribute-based security vulnerabilities (e.g., <a href="http://x%22+style=%22background-image:xss">x</a>). These arise when browsers mis-identify markup in escaped text, defeating the very purpose of escaping text (a bad browser will read the given example as <a href="http://x" style="background-image:xss">x</a>).
        -
        -  *  Because of poor Unicode support in PHP, htmLawed does not remove the high value HTML-invalid characters with multi-byte code-points. Such characters however are extremely unlikely to be in the input. (see section 3.1).
        -
        -  *  htmLawed does not check or correct the character encoding of the input it receives. In conjunction with permitting circumstances such as when the character encoding is left undefined through HTTP headers or HTML meta tags, this can permit an exploit (like Google's UTF-7/XSS vulnerability of the past). Also, htmLawed can mangle input text if it is not well-formed in terms of character encoding. Administrators can consider using code available elsewhere to check well-formedness of input text characters to correct any defect.
        -
        -  *  htmLawed is expected to work with input texts in ASCII-compatible single byte encodings such as national variants of ASCII (like ISO-646-DE/German of the ISO 646 standard), extended ASCII variants (like ISO 8859-10/Turkish of the ISO 8859/ISO Latin standard), ISO 8859-based Windows variants (like Windows 1252), EBCDIC, Shift JIS (Japanese), GB-Roman (Chinese), and KS-Roman (Korean). It should also properly handle texts with variable byte encodings like UTF-7 (Unicode) and UTF-8 (Unicode). However, htmLawed may mangle input texts with double byte encodings like UTF-16 (Unicode), JIS X 0208:1997 (Japanese) and K SX 1001:1992 (Korean), or the UTF-32 (Unicode) quadruple byte encoding. If an input text has such an encoding, administrators can use PHP's iconv functions, or some other mean, to convert text to UTF-8 before passing it to htmLawed.
        -
        -  *  Like any script using PHP's PCRE regex functions, PHP setup-specific low PCRE limit values can cause htmLawed to at least partially fail with very long input texts.
        - -
        -

        -2.9  Examples of usage -

        (to top)
        -
        -  Safest, allowing only safe HTML markup --
        -
        - -    $config = array('safe'=>1); -
        - -    $out = htmLawed($in); -
        -
        -  Simplest, allowing all valid HTML markup except javascript: --
        -
        - -    $out = htmLawed($in); -
        -
        -  Allowing all valid HTML markup including javascript: --
        -
        - -    $config = array('schemes'=>'*:*'); -
        - -    $out = htmLawed($in, $config); -
        -
        -  Allowing only safe HTML and the elements a, em, and strong --
        -
        - -    $config = array('safe'=>1, 'elements'=>'a, em, strong'); -
        - -    $out = htmLawed($in, $config); -
        -
        -  Not allowing elements script and object --
        -
        - -    $config = array('elements'=>'* -script -object'); -
        - -    $out = htmLawed($in, $config); -
        -
        -  Not allowing attributes id and style --
        -
        - -    $config = array('deny_attribute'=>'id, style'); -
        - -    $out = htmLawed($in, $config); -
        -
        -  Permitting only attributes title and href --
        -
        - -    $config = array('deny_attribute'=>'* -title -href'); -
        - -    $out = htmLawed($in, $config); -
        -
        -  Remove bad/disallowed tags altogether instead of converting them to entities --
        -
        - -    $config = array('keep_bad'=>0); -
        - -    $out = htmLawed($in, $config); -
        -
        -  Allowing attribute title only in a and not allowing attributes id, style, or scriptable on* attributes like onclick --
        -
        - -    $config = array('deny_attribute'=>'title, id, style, on*'); -
        - -    $spec = 'a=title'; -
        - -    $out = htmLawed($in, $config, $spec); -
        -
        -  Allowing a custom attribute, vFlag, in img and permitting custom use of the standard attribute, rel, in input --
        -
        - -    $spec = 'img=vFlag; input=rel'; -
        - -    $out = htmLawed($in, $config, $spec); -
        -
        -  Some case-studies are presented below.
        -
        -  1. A blog administrator wants to allow only a, em, strike, strong and u in comments, but needs strike and u transformed to span for better XHTML 1-strict compliance, and, he wants the a links to point only to http or https resources:
        -
        - -    $processed = htmLawed($in, array('elements'=>'a, em, strike, strong, u', 'make_tag_strict'=>1, 'safe'=>1, 'schemes'=>'*:http, https'), 'a=href'); -
        -
        -  2. An author uses a custom-made web application to load content on his web-site. He is the only one using that application and the content he generates has all types of HTML, including scripts. The web application uses htmLawed primarily as a tool to correct errors that creep in while writing HTML and to take care of the occasional bad characters in copy-paste text introduced by Microsoft Office. The web application provides a preview before submitted input is added to the content. For the previewing process, htmLawed is set up as follows:
        -
        - -    $processed = htmLawed($in, array('css_expression'=>1, 'keep_bad'=>1, 'make_tag_strict'=>1, 'schemes'=>'*:*', 'valid_xhtml'=>1)); -
        -
        -  For the final submission process, keep_bad is set to 6. A value of 1 for the preview process allows the author to note and correct any HTML mistake without losing any of the typed text.
        -
        -  3. A data-miner is scraping information in a specific table of similar web-pages and is collating the data rows, and uses htmLawed to reduce unnecessary markup and white-spaces:
        -
        - -    $processed = htmLawed($in, array('elements'=>'tr, td', 'tidy'=>-1), 'tr, td ='); -
        - -
        -
        -

        -3  Details -

        (to top)
        -

        -3.1  Invalid/dangerous characters -

        (to top)
        -
        -  Valid characters (more correctly, their code-points) in HTML or XML are, hexadecimally, 9, a, d, 20 to d7ff, and e000 to 10ffff, except fffe and ffff (decimally, 9, 10, 13, 32 to 55295, and 57344 to 1114111, except 65534 and 65535). htmLawed removes the invalid characters 0 to 8, b, c, and e to 1f.
        -
        -  Because of PHP's poor native support for multi-byte characters, htmLawed cannot check for the remaining invalid code-points. However, for various reasons, it is very unlikely for any of those characters to be in the input.
        -
        -  Characters that are discouraged (see section 5.1) but not invalid are not removed by htmLawed.
        -
        -  It (function hl_tag()) also replaces the potentially dangerous (in some Mozilla [Firefox] and Opera browsers) soft-hyphen character (code-point, hexadecimally, ad, or decimally, 173) in attribute values with spaces. Where required, the characters <, >, &, and " are converted to entities.
        -
        -  With $config["clean_ms_char"] set as 1 or 2, many of the discouraged characters (decimal code-points 127 to 159 except 133) that many Microsoft applications incorrectly use (as per the Windows 1252 [Cp-1252] or a similar encoding system), and the character for decimal code-point 133, are converted to appropriate decimal numerical entities (or removed for a few cases)-- see appendix in section 5.4. This can help avoid some display issues arising from copying-pasting of content.
        -
        -  With $config["clean_ms_char"] set as 2, characters for the hexadecimal code-points 82, 91, and 92 (for special single-quotes), and 84, 93, and 94 (for special double-quotes) are converted to ordinary single and double quotes respectively and not to entities.
        -
        -  The character values are replaced with entities/characters and not character values referred to by the entities/characters to keep this task independent of the character-encoding of input text.
        -
        -  The $config["clean_ms_char"] parameter should not be used if authors do not copy-paste Microsoft-created text, or if the input text is not believed to use the Windows 1252 (Cp-1252) or a similar encoding like Cp-1251 (otherwise, for example when UTF-8 encoding is in use, Japanese or Korean characters can get mangled). Further, the input form and the web-pages displaying it or its content should have the character encoding appropriately marked-up.
        - -
        -

        -3.2  Character references/entities -

        (to top)
        -
        -  Valid character entities take the form &*; where * is #x followed by a hexadecimal number (hexadecimal numeric entity; like &#xA0; for non-breaking space), or alphanumeric like gt (external or named entity; like &nbsp; for non-breaking space), or # followed by a number (decimal numeric entity; like &#160; for non-breaking space). Character entities referring to the soft-hyphen character (the &shy; or \xad character; hexadecimal code-point ad [decimal 173]) in URL-accepting attribute values are always replaced with spaces; soft-hyphens in attribute values introduce vulnerabilities in some older versions of the Opera and Mozilla [Firefox] browsers.
        -
        -  htmLawed (function hl_ent()):
        -
        -  *  Neutralizes entities with multiple leading zeroes or missing semi-colons (potentially dangerous)
        -
        -  *  Lowercases the X (for XML-compliance) and A-F of hexadecimal numeric entities
        -
        -  *  Neutralizes entities referring to characters that are HTML-invalid (see section 3.1)
        -
        -  *  Neutralizes entities referring to characters that are HTML-discouraged (code-points, hexadecimally, 7f to 84, 86 to 9f, and fdd0 to fddf, or decimally, 127 to 132, 134 to 159, and 64991 to 64976). Entities referring to the remaining discouraged characters (see section 5.1 for a full list) are let through.
        -
        -  *  Neutralizes named entities that are not in the specs.
        -
        -  *  Optionally converts valid HTML-specific named entities except &gt;, &lt;, &quot;, and &amp; to decimal numeric ones (hexadecimal if $config["hexdec_entity"] is 2) for generic XML-compliance. For this, $config["named_entity"] should be 1.
        -
        -  *  Optionally converts hexadecimal numeric entities to the more widely supported decimal ones. For this, $config["hexdec_entity"] should be 0.
        -
        -  *  Optionally converts decimal numeric entities to the hexadecimal ones. For this, $config["hexdec_entity"] should be 2.
        -
        -  Neutralization refers to the entitification of & to &amp;.
        -
        -  Note: htmLawed does not convert entities to the actual characters represented by them; one can pass the htmLawed output through PHP's html_entity_decode function for that.
        -
        -  Note: If $config["and_mark"] is set, and set to a value other than 0, then the & characters in the original input are replaced with the control character for the hexadecimal code-point 6 (\x06; & characters introduced by htmLawed, e.g., after converting < to &lt;, are not affected). This allows one to distinguish, say, an &gt; introduced by htmLawed and an &gt; put in by the input writer, and can be helpful in further processing of the htmLawed-processed text (e.g., to identify the character sequence o(><)o to generate an emoticon image). When this feature is active, admins should ensure that the htmLawed output is not directly used in web pages or XML documents as the presence of the \x06 can break documents. Before use in such documents, and preferably before any storage, any remaining \x06 should be changed back to &, e.g., with:
        -
        - -    $final = str_replace("\x06", '&', $prelim); -
        -
        -  Also, see section 3.9.
        - -
        -

        -3.3  HTML elements -

        (to top)
        -
        -  htmLawed can be configured to allow only certain HTML elements (tags) in the input. Disallowed elements (just tag-content, and not element-content), based on $config["keep_bad"], are either neutralized (converted to plain text by entitification of < and >) or removed.
        -
        -  E.g., with only em permitted:
        -
        -  Input:
        -
        - -      <em>My</em> website is <a href="http://a.com>a.com</a>. -
        -
        -  Output, with $config["keep_bad"] = 0:
        -
        - -      <em>My</em> website is a.com. -
        -
        -  Output, with $config["keep_bad"] not 0:
        -
        - -      <em>My</em> website is &lt;a href=""&gt;a.com&lt;/a&gt;. -
        -
        -  See section 3.3.3 for differences between the various non-zero $config["keep_bad"] values.
        -
        -  htmLawed by default permits these 86 elements:
        -
        - -    a, abbr, acronym, address, applet, area, b, bdo, big, blockquote, br, button, caption, center, cite, code, col, colgroup, dd, del, dfn, dir, div, dl, dt, em, embed, fieldset, font, form, h1, h2, h3, h4, h5, h6, hr, i, iframe, img, input, ins, isindex, kbd, label, legend, li, map, menu, noscript, object, ol, optgroup, option, p, param, pre, q, rb, rbc, rp, rt, rtc, ruby, s, samp, script, select, small, span, strike, strong, sub, sup, table, tbody, td, textarea, tfoot, th, thead, tr, tt, u, ul, var -
        -
        -  Except for embed (included because of its wide-spread use) and the Ruby elements (rb, rbc, rp, rt, rtc, ruby; part of XHTML 1.1), these are all the elements in the HTML 4/XHTML 1 specs. Strict-specific specs. exclude center, dir, font, isindex, menu, s, strike, and u.
        -
        -  With $config["safe"] = 1, the default set will exclude applet, embed, iframe, object and script; see section 3.6.
        -
        -  When $config["elements"], which specifies allowed elements, is properly defined, and neither empty nor set to 0 or *, the default set is not used. To have elements added to or removed from the default set, a +/- notation is used. E.g., *-script-object implies that only script and object are disallowed, whereas *+embed means that noembed is also allowed. Elements can also be specified as comma separated names. E.g., a, b, i means only a, b and i are permitted. In this notation, *, + and - have no significance and can actually cause a mis-reading.
        -
        -  Some more examples of $config["elements"] values indicating permitted elements (note that empty spaces are liberally allowed for clarity):
        -
        -  *  a, blockquote, code, em, strong -- only a, blockquote, code, em, and strong
        -  *  *-script -- all excluding script
        -  *  * -center -dir -font -isindex -menu -s -strike -u -- only XHTML-Strict elements
        -  *  *+noembed-script -- all including noembed excluding script
        -
        -  Some mis-usages (and the resulting permitted elements) that can be avoided:
        -
        -  *  -* -- none; instead of htmLawed, one might just use, e.g., the htmlspecialchars() PHP function
        -  *  *, -script -- all except script; admin probably meant *-script
        -  *  -*, a, em, strong -- all; admin probably meant a, em, strong
        -  *  * -- all; admin need not have set elements
        -  *  *-form+form -- all; a + will always over-ride any -
        -  *  *, noembed -- only noembed; admin probably meant *+noembed
        -  *  a, +b, i -- only a and i; admin probably meant a, b, i
        -
        -  Basically, when using the +/- notation, commas (,) should not be used, and vice versa, and * should be used with the former but not the latter.
        -
        -  Note: Even if an element that is not in the default set is allowed through $config["elements"], like noembed in the last example, it will eventually be removed during tag balancing unless such balancing is turned off ($config["balance"] set to 0). Currently, the only way around this, which actually is simple, is to edit the various arrays in the function hl_bal() to accommodate the element and its nesting properties.
        -
        -  A possibly second way to specify allowed elements is to set $config["parent"] to an element name that supposedly will hold the input, and to set $config["balance"] to 1. During tag balancing (see section 3.3.3), all elements that cannot legally nest inside the parent element will be removed. The parent element is auto-reset to div if $config["parent"] is empty, body, or an element not in htmLawed's default set of 86 elements.
        -
        -  Tag transformation is possible for improving XHTML-Strict compliance -- most of the deprecated elements are removed or converted to valid XHTML-Strict ones; see section 3.3.2.
        - -

        -3.3.1  Handling of comments and CDATA sections -

        (to top)
        -
        -  CDATA sections have the format <![CDATA[...anything but not "]]>"...]]>, and HTML comments, <!--...anything but not "-->"... -->. Neither HTML comments nor CDATA sections can reside inside tags. HTML comments can exist anywhere else, but CDATA sections can exist only where plain text is allowed (e.g., immediately inside td element content but not immediately inside tr element content).
        -
        -  htmLawed (function hl_cmtcd()) handles HTML comments or CDATA sections depending on the values of $config["comment"] or $config["cdata"]. If 0, such markup is not looked for and the text is processed like plain text. If 1, it is removed completely. If 2, it is preserved but any <, > and & inside are changed to entities. If 3, they are left as such.
        -
        -  Note that for the last two cases, HTML comments and CDATA sections will always be removed from tag content (function hl_tag()).
        -
        -  Examples:
        -
        -  Input:
        - -    <!-- home link --><a href="home.htm"><![CDATA[x=&y]]>Home</a> -
        -  Output ($config["comment"] = 0, $config["cdata"] = 2):
        - -    &lt;-- home link --&gt;<a href="home.htm"><![CDATA[x=&amp;y]]>Home</a> -
        -  Output ($config["comment"] = 1, $config["cdata"] = 2):
        - -    <a href="home.htm"><![CDATA[x=&amp;y]]>Home</a> -
        -  Output ($config["comment"] = 2, $config["cdata"] = 2):
        - -    <!-- home link --><a href="home.htm"><![CDATA[x=&amp;y]]>Home</a> -
        -  Output ($config["comment"] = 2, $config["cdata"] = 1):
        - -    <!-- home link --><a href="home.htm">Home</a> -
        -  Output ($config["comment"] = 3, $config["cdata"] = 3):
        - -    <!-- home link --><a href="home.htm"><![CDATA[x=&y]]>Home</a> -
        -
        -  For standard-compliance, comments are given the form <!--comment -->, and any -- in the content is made -.
        -
        -  When $config["safe"] = 1, CDATA sections and comments are considered plain text unless $config["comment"] or $config["cdata"] is explicitly specified; see section 3.6.
        - -
        -

        -3.3.2  Tag-transformation for better XHTML-Strict -

        (to top)
        -
        -  If $config["make_tag_strict"] is set and not 0, following non-XHTML-Strict elements (and attributes), even if admin-permitted, are mutated as indicated (element content remains intact; function hl_tag2()):
        -
        -  *  applet - (based on $config["make_tag_strict"], unchanged (1) or removed (2))
        -  *  center - div style="text-align: center;"
        -  *  dir - ul
        -  *  embed - (based on $config["make_tag_strict"], unchanged (1) or removed (2))
        -  *  font (face, size, color) -    span style="font-family: ; font-size: ; color: ;" (size transformation reference)
        -  *  isindex - (based on $config["make_tag_strict"], unchanged (1) or removed (2))
        -  *  menu - ul
        -  *  s - span style="text-decoration: line-through;"
        -  *  strike - span style="text-decoration: line-through;"
        -  *  u - span style="text-decoration: underline;"
        -
        -  For an element with a pre-existing style attribute value, the extra style properties are appended.
        -
        -  Example input:
        -
        - -    <center> -
        - -     The PHP <s>software</s> script used for this <strike>web-page</strike> web-page is <font style="font-weight: bold " face=arial size='+3' color   =  "red  ">htmLawedTest.php</font>, from <u style= 'color:green'>PHP Labware</u>. -
        - -    </center> -
        -
        -  The output:
        -
        - -    <div style="text-align: center;"> -
        - -     The PHP <span style="text-decoration: line-through;">software</span> script used for this <span style="text-decoration: line-through;">web-page</span> web-page is <span style="font-weight: bold; font-family: arial; color: red; font-size: 200%;">htmLawedTest.php</span>, from <span style="color:green; text-decoration: underline;">PHP Labware</span>. -
        - -    </div> -
        - -
        -

        -3.3.3  Tag balancing and proper nesting -

        (to top)
        -
        -  If $config["balance"] is set to 1, htmLawed (function hl_bal()) checks and corrects the input to have properly balanced tags and legal element content (i.e., any element nesting should be valid, and plain text may be present only in the content of elements that allow them).
        -
        -  Depending on the value of $config["keep_bad"] (see section 2.2 and section 3.3), illegal content may be removed or neutralized to plain text by converting < and > to entities:
        -
        -  0 - remove; this option is available only to maintain Kses-compatibility and should not be used otherwise (see section 2.6)
        -  1 - neutralize tags and keep element content
        -  2 - remove tags but keep element content
        -  3 and 4 - like 1 and 2, but keep element content only if text (pcdata) is valid in parent element as per specs
        -  5 and 6 -  like 3 and 4, but line-breaks, tabs and spaces are left
        -
        -  Example input (disallowing the p element):
        -
        - -    <*> Pseudo-tags <*> -
        - -    <xml>Non-HTML tag xml</xml> -
        - -    <p> -
        - -    Disallowed tag p -
        - -    </p> -
        - -    <ul>Bad<li>OK</li></ul> -
        -
        -  The output with $config["keep_bad"] = 1:
        -
        - -    &lt;*&gt; Pseudo-tags &lt;*&gt; -
        - -    &lt;xml&gt;Non-HTML tag xml&lt;/xml&gt; -
        - -    &lt;p&gt; -
        - -    Disallowed tag p -
        - -    &lt;/p&gt; -
        - -    <ul>Bad<li>OK</li></ul> -
        -
        -  The output with $config["keep_bad"] = 3:
        -
        - -    &lt;*&gt; Pseudo-tags &lt;*&gt; -
        - -    &lt;xml&gt;Non-HTML tag xml&lt;/xml&gt; -
        - -    &lt;p&gt; -
        - -    Disallowed tag p -
        - -    &lt;/p&gt; -
        - -    <ul><li>OK</li></ul> -
        -
        -  The output with $config["keep_bad"] = 6:
        -
        - -    &lt;*&gt; Pseudo-tags &lt;*&gt; -
        - -    Non-HTML tag xml -
        -
        - -    Disallowed tag p -
        -
        - -    <ul><li>OK</li></ul> -
        -
        -  An option like 1 is useful, e.g., when a writer previews his submission, whereas one like 3 is useful before content is finalized and made available to all.
        -
        -  Note: In the example above, unlike <*>, <xml> gets considered as a tag (even though there is no HTML element named xml). Thus, the keep_bad parameter's value affects <xml> but not <*>. In general, text matching the regular expression pattern <(/?)([a-zA-Z][a-zA-Z1-6]*)([^>]*?)\s?> is considered a tag (phrase enclosed by the angled brackets < and >, and starting [with an optional slash preceding] with an alphanumeric word that starts with an alphabet...), and is subjected to the keep_bad value.
        -
        -  Nesting/content rules for each of the 86 elements in htmLawed's default set (see section 3.3) are defined in function hl_bal(). This means that if a non-standard element besides embed is being permitted through $config["elements"], the element's tag content will end up getting removed if $config["balance"] is set to 1.
        -
        -  Plain text and/or certain elements nested inside blockquote, form, map and noscript need to be in block-level elements. This point is often missed during manual writing of HTML code. htmLawed attempts to address this during balancing. E.g., if the parent container is set as form, the input B:<input type="text" value="b" />C:<input type="text" value="c" /> is converted to <div>B:<input type="text" value="b" />C:<input type="text" value="c" /></div>.
        - -
        -

        -3.3.4  Elements requiring child elements -

        (to top)
        -
        -  As per specs, the following elements require legal child elements nested inside them:
        -
        - -    blockquote, dir, dl, form, map, menu, noscript, ol, optgroup, rbc, rtc, ruby, select, table, tbody, tfoot, thead, tr, ul -
        -
        -  In some cases, the specs stipulate the number and/or the ordering of the child elements. A table can have 0 or 1 caption, tbody, tfoot, and thead, but they must be in this order: caption, thead, tfoot, tbody.
        -
        -  htmLawed currently does not check for conformance to these rules. Note that any non-compliance in this regard will not introduce security vulnerabilities, crash browser applications, or affect the rendering of web-pages.
        -
        -  With $config["direct_list_nest"] set to 1, htmLawed will allow direct nesting of an ol or ul list within another ol or ul without requiring the child list to be within an li of the parent list. While this is not standard-compliant, directly nested lists are rendered properly by almost all browsers. The parameter $config["direct_list_nest"] has no effect if tag-balancing (section 3.3.3) is turned off.
        - -
        -

        -3.3.5  Beautify or compact HTML -

        (to top)
        -
        -  By default, htmLawed will neither beautify HTML code by formatting it with indentations, etc., nor will it make it compact by removing un-needed white-space.(It does always properly white-space tag content.)
        -
        -  As per the HTML standards, spaces, tabs and line-breaks in web-pages (except those inside pre elements) are all considered equivalent, and referred to as white-spaces. Browser applications are supposed to consider contiguous white-spaces as just a single space, and to disregard white-spaces trailing opening tags or preceding closing tags. This white-space normalization allows the use of text/code beautifully formatted with indentations and line-spacings for readability. Such pretty HTML can, however, increase the size of web-pages, or make the extraction or scraping of plain text cumbersome.
        -
        -  With the $config parameter tidy, htmLawed can be used to beautify or compact the input text. Input with just plain text and no HTML markup is also subject to this. Besides pre, the script and textarea elements, CDATA sections, and HTML comments are not subjected to the tidying process.
        -
        -  To compact, use $config["tidy"] = -1; single instances or runs of white-spaces are replaced with a single space, and white-spaces trailing and leading open and closing tags, respectively, are removed.
        -
        -  To beautify, $config["tidy"] is set as 1, or for customized tidying, as a string like 2s2n. The s or t character specifies the use of spaces or tabs for indentation. The first and third characters, any of the digits 0-9, specify the number of spaces or tabs per indentation, and any parental lead spacing (extra indenting of the whole block of input text). The r and n characters are used to specify line-break characters: n for \n (Unix/Mac OS X line-breaks), rn or nr for \r\n (Windows/DOS line-breaks), or r for \r.
        -
        -  The $config["tidy"] value of 1 is equivalent to 2s0n. Other $config["tidy"] values are read loosely: a value of 4 is equivalent to 4s0n; t2, to 1t2n; s, to 2s0n; 2TR, to 2t0r; T1, to 1t1n; nr3, to 3s0nr, and so on. Except in the indentations and line-spacings, runs of white-spaces are replaced with a single space during beautification.
        -
        -  Input formatting using $config["tidy"] is not recommended when input text has mixed markup (like HTML + PHP).
        - -
        -
        -

        -3.4  Attributes -

        (to top)
        -
        -  htmLawed will only permit attributes described in the HTML specs (including deprecated ones). It also permits some attributes for use with the embed element (the non-standard embed element is supported in htmLawed because of its widespread use), and the allowfullscreen (in iframe, because of its widespread use), bordercolor (in table, td and tr, because of its widespread use), and xml:space (valid only in XHTML 1.1) attributes. A list of such 112 attributes and the elements they are allowed in is in section 5.2. Using the $spec argument, htmLawed can be forced to permit custom, non-standard attributes as well as custom rules for standard attributes (section 2.3).
        -
        -  When $config["deny_attribute"] is not set, or set to 0, or empty (""), all the 111 attributes are permitted. Otherwise, $config["deny_attribute"] can be set as a list of comma-separated names of the denied attributes. on* can be used to refer to the group of potentially dangerous, script-accepting attributes: onblur, onchange, onclick, ondblclick, onfocus, onkeydown, onkeypress, onkeyup, onmousedown, onmousemove, onmouseout, onmouseover, onmouseup, onreset, onselect and onsubmit.
        -
        -  Note that attributes specified in $config["deny_attribute"] are denied globally, for all elements. To deny attributes for only specific elements, $spec (see section 2.3) can be used. $spec can also be used to element-specifically permit an attribute otherwise denied through $config["deny_attribute"].
        -
        -  With $config["safe"] = 1 (section 3.6), the on* attributes are automatically disallowed.
        -
        -  Note: To deny all but a few attributes globally, a simpler way to specify $config["deny_attribute"] would be to use the notation * -attribute1 -attribute2 .... Thus, a value of * -title -href implies that except href and title (where allowed as per standards) all other attributes are to be removed. With this notation, the value for the parameter safe (section 3.6) will have no effect on deny_attribute.
        -
        -  htmLawed (function hl_tag()) also:
        -
        -  *  Lower-cases attribute names
        -  *  Removes duplicate attributes (last one stays)
        -  *  Gives attributes the form name="value" and single-spaces them, removing unnecessary white-spacing
        -  *  Provides required attributes (see section 3.4.1)
        -  *  Double-quotes values and escapes any " inside them
        -  *  Replaces the possibly dangerous soft-hyphen characters (hexadecimal code-point ad) in the values with spaces
        -  *  Allows custom function to additionally filter/modify attribute values (see section 3.4.9)
        - -

        -3.4.1  Auto-addition of XHTML-required attributes -

        (to top)
        -
        -  If indicated attributes for the following elements are found missing, htmLawed (function hl_tag()) will add them (with values same as attribute names unless indicated otherwise below):
        -
        -  *  area - alt (area)
        -  *  area, img - src, alt (image)
        -  *  bdo - dir (ltr)
        -  *  form - action
        -  *  map - name
        -  *  optgroup - label
        -  *  param - name
        -  *  script - type (text/javascript)
        -  *  textarea - rows (10), cols (50)
        -
        -  Additionally, with $config["xml:lang"] set to 1 or 2, if the lang but not the xml:lang attribute is declared, then the latter is added too, with a value copied from that of lang. This is for better standard-compliance. With $config["xml:lang"] set to 2, the lang attribute is removed (XHTML 1.1 specs).
        -
        -  Note that the name attribute for map, invalid in XHTML 1.1, is also transformed if required -- see section 3.4.6.
        - -
        -

        -3.4.2  Duplicate/invalid id values -

        (to top)
        -
        -  If $config["unique_ids"] is 1, htmLawed (function hl_tag()) removes id attributes with values that are not XHTML-compliant (must begin with a letter and can contain letters, digits, :, ., - and _) or duplicate. If $config["unique_ids"] is a word, any duplicate but otherwise valid value will be appropriately prefixed with the word to ensure its uniqueness. The word should begin with a letter and should contain only letters, numbers, :, ., _ and -.
        -
        -  Even if multiple inputs need to be filtered (through multiple calls to htmLawed), htmLawed ensures uniqueness of id values as it uses a global variable ($GLOBALS["hl_Ids"] array). Further, an admin can restrict the use of certain id values by presetting this variable before htmLawed is called into use. E.g.:
        -
        - -    $GLOBALS['hl_Ids'] = array('top'=>1, 'bottom'=>1, 'myform'=>1); // id values not allowed in input -
        - -    $processed = htmLawed($text); // filter input -
        - -
        -

        -3.4.3  URL schemes (protocols) and scripts in attribute values -

        (to top)
        -
        -  htmLawed edits attributes that take URLs as values if they are found to contain un-permitted schemes. E.g., if the afp scheme is not permitted, then <a href="afp://domain.org"> becomes <a href="denied:afp://domain.org">, and if Javascript is not permitted <a onclick="javascript:xss();"> becomes <a onclick="denied:javascript:xss();">.
        -
        -  By default htmLawed permits these schemes in URLs for the href attribute:
        -
        - -    aim, feed, file, ftp, gopher, http, https, irc, mailto, news, nntp, sftp, ssh, telnet -
        -
        -  Also, only file, http and https are permitted in attributes whose names start with o (like onmouseover), and in these attributes that accept URLs:
        -
        - -    action, cite, classid, codebase, data, href, longdesc, model, pluginspage, pluginurl, src, style, usemap -
        -
        -  These default sets are used when $config["schemes"] is not set (see section 2.2). To over-ride the defaults, $config["schemes"] is defined as a string of semi-colon-separated sub-strings of type attribute: comma-separated schemes. E.g., href: mailto, http, https; onclick: javascript; src: http, https. For unspecified attributes, file, http and https are permitted. This can be changed by passing schemes for * in $config["schemes"]. E.g., href: mailto, http, https; *: https, https.
        -
        -  * can be put in the list of schemes to permit all protocols. E.g., style: *; img: http, https results in protocols not being checked in style attribute values. However, in such cases, any relative-to-absolute URL conversion, or vice versa, (section 3.4.4) is not done.
        -
        -  Thus, to allow Javascript, one can set $config["schemes"] as href: mailto, http, https; *: http, https, javascript, or href: mailto, http, https, javascript; *: http, https, javascript, or *: *, and so on.
        -
        -  As a side-note, one may find style: * useful as URLs in style attributes can be specified in a variety of ways, and the patterns that htmLawed uses to identify URLs may mistakenly identify non-URL text.
        -
        -  ! can be put in the list of schemes to disallow all protocols as well as local URLs. Thus, with href: http, style: !, '<a href="http://cnn.com" style="background-image: url('local.jpg');">CNN</a>' will become '<a href="http://cnn.com" style="background-image: url('denied:local.jpg');">CNN</a>'.
        -
        -  Note: If URL-accepting attributes other than those listed above are being allowed, then the scheme will not be checked unless the attribute name contains the string src (e.g., dynsrc) or starts with o (e.g., onbeforecopy).
        -
        -  With $config["safe"] = 1, all URLs are disallowed in the style attribute values.
        - -
        -

        -3.4.4  Absolute & relative URLs in attribute values -

        (to top)
        -
        -  htmLawed can make absolute URLs in attributes like href relative ($config["abs_url"] is -1), and vice versa ($config["abs_url"] is 1). URLs in scripts are not considered for this, and so are URLs like #section_6 (fragment), ?name=Tim#show (starting with query string), and ;var=1?name=Tim#show (starting with parameters). Further, this requires that $config["base_url"] be set properly, with the :// and a trailing slash (/), with no query string, etc. E.g., file:///D:/page/, https://abc.com/x/y/, or http://localhost/demo/ are okay, but file:///D:/page/?help=1, abc.com/x/y/ and http://localhost/demo/index.htm are not.
        -
        -  For making absolute URLs relative, only those URLs that have the $config["base_url"] string at the beginning are converted. E.g., with $config["base_url"] = "https://abc.com/x/y/", https://abc.com/x/y/a.gif and https://abc.com/x/y/z/b.gif become a.gif and z/b.gif respectively, while https://abc.com/x/c.gif is not changed.
        -
        -  When making relative URLs absolute, only values for scheme, network location (host-name) and path values in the base URL are inherited. See section 5.5 for more about the URL specification as per RFC 1808.
        - -
        -

        -3.4.5  Lower-cased, standard attribute values -

        (to top)
        -
        -  Optionally, for standard-compliance, htmLawed (function hl_tag()) lower-cases standard attribute values to give, e.g., input type="password" instead of input type="Password", if $config["lc_std_val"] is 1. Attribute values matching those listed below for any of the elements (plus those for the type attribute of button or input) are lower-cased:
        -
        - -    all, baseline, bottom, button, center, char, checkbox, circle, col, colgroup, cols, data, default, file, get, groups, hidden, image, justify, left, ltr, middle, none, object, password, poly, post, preserve, radio, rect, ref, reset, right, row, rowgroup, rows, rtl, submit, text, top -
        -
        - -    a, area, bdo, button, col, form, img, input, object, option, optgroup, param, script, select, table, td, tfoot, th, thead, tr, xml:space -
        -
        -  The following empty (minimized) attributes are always assigned lower-cased values (same as the names):
        -
        - -    checked, compact, declare, defer, disabled, ismap, multiple, nohref, noresize, noshade, nowrap, readonly, selected -
        - -
        -

        -3.4.6  Transformation of deprecated attributes -

        (to top)
        -
        -  If $config["no_deprecated_attr"] is 0, then deprecated attributes (see appendix in section 5.2) are removed and, in most cases, their values are transformed to CSS style properties and added to the style attributes (function hl_tag()). Except for bordercolor for table, tr and td, the scores of proprietary attributes that were never part of any cross-browser standard are not supported.
        -
        -  Note: The attribute target for a is allowed even though it is not in XHTML 1.0 specs. This is because of the attribute's wide-spread use and browser-support, and because the attribute is valid in XHTML 1.1 onwards.
        -
        -  *  align - for img with value of left or right, becomes, e.g., float: left; for div and table with value center, becomes margin: auto; all others become, e.g., text-align: right
        -
        -  *  bgcolor - E.g., bgcolor="#ffffff" becomes background-color: #ffffff
        -  *  border - E.g., height= "10" becomes height: 10px
        -  *  bordercolor - E.g., bordercolor=#999999 becomes border-color: #999999;
        -  *  compact - font-size: 85%
        -  *  clear - E.g., 'clear="all" becomes clear: both
        -
        -  *  height - E.g., height= "10" becomes height: 10px and height="*" becomes height: auto
        -
        -  *  hspace - E.g., hspace="10" becomes margin-left: 10px; margin-right: 10px
        -  *  language - language="VBScript" becomes type="text/vbscript"
        -  *  name - E.g., name="xx" becomes id="xx"
        -  *  noshade - border-style: none; border: 0; background-color: gray; color: gray
        -  *  nowrap - white-space: nowrap
        -  *  size - E.g., size="10" becomes height: 10px
        -  *  start - removed
        -  *  type - E.g., type="i" becomes list-style-type: lower-roman
        -  *  value - removed
        -  *  vspace - E.g., vspace="10" becomes margin-top: 10px; margin-bottom: 10px
        -  *  width - like height
        -
        -  Example input:
        -
        - -    <img src="j.gif" alt="image" name="dad's" /><img src="k.gif" alt="image" id="dad_off" name="dad" /> -
        - -    <br clear="left" /> -
        - -    <hr noshade size="1" /> -
        - -    <img name="img" src="i.gif" align="left" alt="image" hspace="10" vspace="10" width="10em" height="20" border="1" style="padding:5px;" /> -
        - -    <table width="50em" align="center" bgcolor="red"> -
        - -     <tr> -
        - -      <td width="20%"> -
        - -       <div align="center"> -
        - -        <h3 align="right">Section</h3> -
        - -        <p align="right">Para</p> -
        - -        <ol type="a" start="e"><li value="x">First item</li></ol> -
        - -       </div> -
        - -      </td> -
        - -      <td width="*"> -
        - -       <ol type="1"><li>First item</li></ol> -
        - -      </td> -
        - -     </tr> -
        - -    </table> -
        - -    <br clear="all" /> -
        -
        -  And the output with $config["no_deprecated_attr"] = 1:
        -
        - -    <img src="j.gif" alt="image" /><img src="k.gif" alt="image" id="dad_off" /> -
        - -    <br style="clear: left;" /> -
        - -    <hr style="border-style: none; border: 0; background-color: gray; color: gray; size: 1px;" /> -
        - -    <img src="i.gif" alt="image" width="10em" height="20" style="padding:5px; float: left; margin-left: 10px; margin-right: 10px; margin-top: 10px; margin-bottom: 10px; border: 1px;" id="img" /> -
        - -    <table width="50em" style="margin: auto; background-color: red;"> -
        - -     <tr> -
        - -      <td style="width: 20%;"> -
        - -       <div style="margin: auto;"> -
        - -        <h3 style="text-align: right;">Section</h3> -
        - -        <p style="text-align: right;">Para</p> -
        - -        <ol style="list-style-type: lower-latin;"><li>First item</li></ol> -
        - -       </div> -
        - -      </td> -
        - -      <td style="width: auto;"> -
        - -       <ol style="list-style-type: decimal;"><li>First item</li></ol> -
        - -      </td> -
        - -     </tr> -
        - -    </table> -
        - -    <br style="clear: both;" /> -
        -
        -  For lang, deprecated in XHTML 1.1, transformation is taken care of through $config["xml:lang"]; see section 3.4.1.
        -
        -  The attribute name is deprecated in form, iframe, and img, and is replaced with id if an id attribute doesn't exist and if the name value is appropriate for id. For such replacements for a and map, for which the name attribute is deprecated in XHTML 1.1, $config["no_deprecated_attr"] should be set to 2 (when set to 1, for these two elements, the name attribute is retained).
        - -
        -

        -3.4.7  Anti-spam & href -

        (to top)
        -
        -  htmLawed (function hl_tag()) can check the href attribute values (link addresses) as an anti-spam (email or link spam) measure.
        -
        -  If $config["anti_mail_spam"] is not 0, the @ of email addresses in href values like mailto:a@b.com is replaced with text specified by $config["anti_mail_spam"]. The text should be of a form that makes it clear to others that the address needs to be edited before a mail is sent; e.g., <remove_this_antispam>@ (makes the example address a<remove_this_antispam>@b.com).
        -
        -  For regular links, one can choose to have a rel attribute with nofollow in its value (which tells some search engines to not follow a link). This can discourage link spammers. Additionally, or as an alternative, one can choose to empty the href value altogether (disable the link).
        -
        -  For use of these options, $config["anti_link_spam"] should be set as an array with values regex1 and regex2, both or one of which can be empty (like array("", "regex2")) to indicate that that option is not to be used. Otherwise, regex1 or regex2 should be PHP- and PCRE-compatible regular expression patterns: href values will be matched against them and those matching the pattern will accordingly be treated.
        -
        -  Note that the regular expressions should have delimiters, and be well-formed and preferably fast. Absolute efficiency/accuracy is often not needed.
        -
        -  An example, to have a rel attribute with nofollow for all links, and to disable links that do not point to domains abc.com and xyz.org:
        -
        - -    $config["anti_link_spam"] = array('`.`', '`://\W*(?!(abc\.com|xyz\.org))`'); -
        - -
        -

        -3.4.8  Inline style properties -

        (to top)
        -
        -  htmLawed can check URL schemes and dynamic expressions (to guard against Javascript, etc., script-based insecurities) in inline CSS style property values in the style attributes. (CSS properties like background-image that accept URLs in their values are noted in section 5.3.) Dynamic CSS expressions that allow scripting in the IE browser, and can be a vulnerability, can be removed from property values by setting $config["css_expression"] to 1 (default setting). Note that when $config["css_expression"] is set to 1, htmLawed will remove /* from the style values.
        -
        -  Note: Because of the various ways of representing characters in attribute values (URL-escapement, entitification, etc.), htmLawed might alter the values of the style attribute values, and may even falsely identify dynamic CSS expressions and URL schemes in them. If this is an important issue, checking of URLs and dynamic expressions can be turned off ($config["schemes"] = "...style:*...", see section 3.4.3, and $config["css_expression"] = 0). Alternately, admins can use their own custom function for finer handling of style values through the hook_tag parameter (see section 3.4.9).
        -
        -  It is also possible to have htmLawed let through any style value by setting $config["style_pass"] to 1.
        -
        -  As such, it is better to set up a CSS file with class declarations, disallow the style attribute, set a $spec rule (see section 2.3) for class for the oneof or match parameter, and ask writers to make use of the class attribute.
        - -
        -

        -3.4.9  Hook function for tag content -

        (to top)
        -
        -  It is possible to utilize a custom hook function to alter the tag content htmLawed has finalized (i.e., after it has checked/corrected for required attributes, transformed attributes, lower-cased attribute names, etc.).
        -
        -  When $config parameter hook_tag is set to the name of a function, htmLawed (function hl_tag()) will pass on the element name, and, in the case of an opening tag, the finalized attribute name-value pairs as array elements to the function. The function, after completing a task such as filtering or tag transformation, will typically return an empty string, the full opening tag string like <element_name attribute_1_name="attribute_1_value"...> (for empty elements like img and input, the element-closing slash / should also be included), etc.
        -
        -  Any hook_tag function, since htmLawed version 1.1.11, also receives names of elements in closing tags, such as a in the closing </a> tag of the element <a href="http://cnn.com">CNN</a>. Unlike for opening tags, no other value (i.e., the attribute name-value array) is passed to the function since a closing tag contains only element names. Typically, the function will return an empty string or a full closing tag (like </a>).
        -
        -  This is a powerful functionality that can be exploited for various objectives: consolidate-and-convert inline style attributes to class, convert embed elements to object, permit only one caption element in a table element, disallow embedding of certain types of media, inject HTML, use CSSTidy to sanitize style attribute values, etc.
        -
        -  As an example, the custom hook code below can be used to force a series of specifically ordered id attributes on all elements, and a specific param element inside all object elements:
        -
        - -    function my_tag_function($element, $attribute_array=0){ -
        -
        - -      // If second argument is not received, it means a closing tag is being handled -
        - -      if(is_numeric($attribute_array)){ -
        - -        return "</$element>"; -
        - -      } -
        -
        - -      static $id = 0; -
        - -      // Remove any duplicate element -
        - -      if($element == 'param' && isset($attribute_array['allowscriptaccess'])){ -
        - -        return ''; -
        - -      } -
        -
        - -      $new_element = ''; -
        -
        - -      // Force a serialized ID number -
        - -      $attribute_array['id'] = 'my_'. $id; -
        - -      ++$id; -
        -
        - -      // Inject param for allowscriptaccess -
        - -      if($element == 'object'){ -
        - -        $new_element = '<param id='my_'. $id; allowscriptaccess="never" />'; -
        - -        ++$id; -
        - -      } -
        -
        - -      $string = ''; -
        - -      foreach($attribute_array as $k=>$v){ -
        - -        $string .= " {$k}=\"{$v}\""; -
        - -      } -
        -
        - -      static $empty_elements = array('area'=>1, 'br'=>1, 'col'=>1, 'embed'=>1, 'hr'=>1, 'img'=>1, 'input'=>1, 'isindex'=>1, 'param'=>1); -
        -
        - -      return "<{$element}{$string}". (isset($in_array($element, $empty_elements) ? ' /' : ''). '>'. $new_element; -
        - -    } -
        -
        -  The hook_tag parameter is different from the hook parameter (section 3.7).
        -
        -  Snippets of hook function code developed by others may be available on the htmLawed website.
        - -
        -
        -

        -3.5  Simple configuration directive for most valid XHTML -

        (to top)
        -
        -  If $config["valid_xhtml"] is set to 1, some relevant $config parameters (indicated by ~ in section 2.2) are auto-adjusted. This allows one to pass the $config argument with a simpler value. If a value for a parameter auto-set through valid_xhtml is still manually provided, then that value will over-ride the auto-set value.
        - -
        -

        -3.6  Simple configuration directive for most safe HTML -

        (to top)
        -
        -  Safe HTML refers to HTML that is restricted to reduce the vulnerability for scripting attacks (such as XSS) based on HTML code which otherwise may still be legal and compliant with the HTML standard specs. When elements such as script and object, and attributes such as onmouseover and style are allowed in the input text, an input writer can introduce malevolent HTML code. Note that what is considered safe depends on the nature of the web application and the trust-level accorded to its users.
        -
        -  htmLawed allows an admin to use $config["safe"] to auto-adjust multiple $config parameters (such as elements which declares the allowed element-set), which otherwise would have to be manually set. The relevant parameters are indicated by " in section 2.2). Thus, one can pass the $config argument with a simpler value.
        -
        -  With the value of 1, htmLawed considers CDATA sections and HTML comments as plain text, and prohibits the applet, embed, iframe, object and script elements, and the on* attributes like onclick. ( There are $config parameters like css_expression that are not affected by the value set for safe but whose default values still contribute towards a more safe output.) Further, URLs with schemes (see section 3.4.3) are neutralized so that, e.g., style="moz-binding:url(http://danger)" becomes style="moz-binding:url(denied:http://danger)".
        -
        -  Admins, however, may still want to completely deny the style attribute, e.g., with code like
        -
        - -    $processed = htmLawed($text, array('safe'=>1, 'deny_attribute'=>'style')); -
        -
        -  Permitting the style attribute brings in risks of click-jacking, etc. CSS property values can render a page non-functional or be used to deface it. Except for URLs, dynamic expressions, and some other things, htmLawed does not completely check style values. It does provide ways for the code-developer implementing htmLawed to do such checks through the $spec argument, and through the hook_tag parameter (see section 3.4.8 for more). Disallowing style completely and relying on CSS classes and stylesheet files is recommended.
        -
        -  If a value for a parameter auto-set through safe is still manually provided, then that value can over-ride the auto-set value. E.g., with $config["safe"] = 1 and $config["elements"] = "*+script", script, but not applet, is allowed.
        -
        -  A page illustrating the efficacy of htmLawed's anti-XSS abilities with safe set to 1 against XSS vectors listed by RSnake may be available here.
        - -
        -

        -3.7  Using a hook function -

        (to top)
        -
        -  If $config["hook"] is not set to 0, then htmLawed will allow preliminarily processed input to be altered by a hook function named by $config["hook"] before starting the main work (but after handling of characters, entities, HTML comments and CDATA sections -- see code for function htmLawed()).
        -
        -  The hook function also allows one to alter the finalized values of $config and $spec.
        -
        -  Note that the hook parameter is different from the hook_tag parameter (section 3.4.9).
        -
        -  Snippets of hook function code developed by others may be available on the htmLawed website.
        - -
        -

        -3.8  Obtaining finalized parameter values -

        (to top)
        -
        -  htmLawed can assign the finalized $config and $spec values to a variable named by $config["show_setting"]. The variable, made global by htmLawed, is set as an array with three keys: config, with the $config value, spec, with the $spec value, and time, with a value that is the Unix time (the output of PHP's microtime() function) when the value was assigned. Admins should use a PHP-compliant variable name (e.g., one that does not begin with a numerical digit) that does not conflict with variable names in their non-htmLawed code.
        -
        -  The values, which are also post-hook function (if any), can be used to auto-generate information (on, e.g., the elements that are permitted) for input writers.
        - -
        -

        -3.9  Retaining non-HTML tags in input with mixed markup -

        (to top)
        -
        -  htmLawed does not remove certain characters that, though invalid, are nevertheless discouraged in HTML documents as per the specifications (see section 5.1). This can be utilized to deal with input that contains mixed markup. Input that may have HTML markup as well as some other markup that is based on the <, > and & characters is considered to have mixed markup. The non-HTML markup can be rather proprietary (like markup for emoticons/smileys), or standard (like MathML or SVG). Or it can be programming code meant for execution/evaluation (such as embedded PHP code).
        -
        -  To deal with such mixed markup, the input text can be pre-processed to hide the non-HTML markup by specifically replacing the <, > and & characters with some of the HTML-discouraged characters (see section 3.1.2). Post-htmLawed processing, the replacements are reverted.
        -
        -  An example (mixed HTML and PHP code in input text):
        -
        - -    $text = preg_replace('`<\?php(.+?)\?>`sm', "\x83?php\\1?\x84", $text); -
        - -    $processed = htmLawed($text); -
        - -    $processed = preg_replace('`\x83\?php(.+?)\?\x84`sm', '<?php$1?>', $processed); -
        -
        -  This code will not work if $config["clean_ms_char"] is set to 1 (section 3.1), in which case one should instead deploy a hook function (section 3.7). (htmLawed internally uses certain control characters, code-points 1 to 7, and use of these characters as markers in the logic of hook functions may cause issues.)
        -
        -  Admins may also be able to use $config["and_mark"] to deal with such mixed markup; see section 3.2.
        - -
        -
        -

        -4  Other -

        (to top)
        -

        -4.1  Support -

        (to top)
        -
        -  A careful reading of this documentation may provide an answer.
        -
        -  Software updates and forum-based community-support may be found at http://www.bioinformatics.org/phplabware/internal_utilities/htmLawed. For general PHP issues (not htmLawed-specific), support may be found through internet searches and at http://php.net.
        - -
        -

        -4.2  Known issues -

        (to top)
        -
        -  See section 2.8.
        - -
        -

        -4.3  Change-log -

        (to top)
        -
        -  (The release date for the downloadable package of files containing documentation, demo script, test-cases, etc., besides the htmLawed.php file, may be updated without a change-log entry if the secondary files, but not htmLawed per se, are revised.)
        -
        -  Version number - Release date. Notes
        -
        -
        -  1.1.20 - 9 June 2015. Fix for a potential security vulnerability arising from unescaped double-quote character in single-quoted attribute value of some deprecated elements when tag transformation is enabled; recognition for non-(HTML4) standard allowfullscreen attribute of iframe.
        -
        -  1.1.19 - 19 January 2015. Fix for a bug in cleaning of soft-hyphens in URL values, etc.
        -
        -  1.1.18 - 2 August 2014. Fix for a potential security vulnerability arising from specially encoded text with serial opening tags
        -
        -  1.1.17 - 11 March 2014. Removed use of PHP function preg_replace with e modifier for compatibility with PHP 5.5
        -
        -  1.1.16 - 29 August 2013. Fix for a potential security vulnerability arising from specially encoded space characters in URL schemes/protocols
        -
        -  1.1.15 - 11 August 2013. Improved tidying/prettifying functionality
        -
        -  1.1.14 - 8 August 2012. Fix for possible segmental loss of incremental indentation during tidying when balance is disabled; fix for non-effectuation under some circumstances of a corrective behavior to preserve plain text within elements like blockquote.
        -
        -  1.1.13 - 22 July 2012. Added feature allowing use of custom, non-standard attributes or custom rules for standard attributes
        -
        -  1.1.12 - 5 July 2012. Fix for a bug in identifying an unquoted value of the face attribute
        -
        -  1.1.11 - 5 June 2012. Fix for possible problem with handling of multi-byte characters in attribute values in an mbstring.func_overload environment. $config["hook_tag"], if specified, now receives names of elements in closing tags.
        -
        -  1.1.10 - 22 October 2011. Fix for a bug in the tidy functionality that caused the entire input to be replaced with a single space; new parameter, $config["direct_list_nest"] to allow direct descendence of a list in a list. (5 April 2012. Dual licensing from LGPLv3 to LGPLv3 and GPLv2+.)
        -
        -  1.1.9.5 - 6 July 2011. Minor correction of a rule for nesting of li within dir
        -
        -  1.1.9.4 - 3 July 2010. Parameter schemes now accepts ! so any URL, even a local one, can be denied. An issue in which a second URL value in style properties was not checked was fixed.
        -
        -  1.1.9.3 - 17 May 2010. Checks for correct nesting of param
        -
        -  1.1.9.2 - 26 April 2010. Minor fix regarding rendering of denied URL schemes
        -
        -  1.1.9.1 - 26 February 2010. htmLawed now uses the LGPL version 3 license; support for flashvars attribute for embed
        -
        -  1.1.9 - 22 December 2009. Soft-hyphens are now removed only from URL-accepting attribute values
        -
        -  1.1.8.1 - 16 July 2009. Minor code-change to fix a PHP error notice
        -
        -  1.1.8 - 23 April 2009. Parameter deny_attribute now accepts the wild-card *, making it simpler to specify its value when all but a few attributes are being denied; fixed a bug in interpreting $spec
        -
        -  1.1.7 - 11-12 March 2009. Attributes globally denied through deny_attribute can be allowed element-specifically through $spec; $config["style_pass"] allowing letting through any style value introduced; altered logic to catch certain types of dynamic crafted CSS expressions
        -
        -  1.1.3-6 - 28-31 January - 4 February 2009. Altered logic to catch certain types of dynamic crafted CSS expressions
        -
        -  1.1.2 - 22 January 2009. Fixed bug in parsing of font attributes during tag transformation
        -
        -  1.1.1 - 27 September 2008. Better nesting correction when omitable closing tags are absent
        -
        -  1.1 - 29 June 2008. $config["hook_tag"] and $config["tidy"] introduced for custom tag/attribute check/modification/injection and output compaction/beautification; fixed a regex-in-$spec parsing bug
        -
        -  1.0.9 - 11 June 2008. Fix for a bug in checks for invalid HTML code-point entities
        -
        -  1.0.8 - 15 May 2008. Permit bordercolor attribute for table, td and tr
        -
        -  1.0.7 - 1 May 2008. Support for wmode attribute for embed; $config["show_setting"] introduced; improved $config["elements"] evaluation
        -
        -  1.0.6 - 20 April 2008. $config["and_mark"] introduced
        -
        -  1.0.5 - 12 March 2008. style URL schemes essentially disallowed when $config safe is on; improved regex for CSS expression search
        -
        -  1.0.4 - 10 March 2008. Improved corrections for blockquote, form, map and noscript
        -
        -  1.0.3 - 3 March 2008. Character entities for soft-hyphens are now replaced with spaces (instead of being removed); fix for a bug allowing td directly inside table; $config["safe"] introduced
        -
        -  1.0.2 - 13 February 2008. Improved implementation of $config["keep_bad"]
        -
        -  1.0.1 - 7 November 2007. Improved regex for identifying URLs, protocols and dynamic expressions (hl_tag() and hl_prot()); no error display with hl_regex()
        -
        -  1.0 - 2 November 2007. First release
        - -
        -

        -4.4  Testing -

        (to top)
        -
        -  To test htmLawed using a form interface, a demo web-page is provided with the htmLawed distribution (htmLawed.php and htmLawedTest.php should be in the same directory on the web-server). A file with test-cases is also provided.
        - -
        -

        -4.5  Upgrade, & old versions -

        (to top)
        -
        -  Upgrading is as simple as replacing the previous version of htmLawed.php (assuming it was not modified for customized features). As htmLawed output is almost always used in static documents, upgrading should not affect old, finalized content.
        -
        -  Important  The following upgrades may affect the functionality of a specific htmLawed installation:
        -
        -  (1) From version 1.1-1.1.10 to 1.1.11 (or later), if a hook_tag function is in use: In version 1.1.11, elements in closing tags (and not just the opening tags) are also passed to the function. There are no attribute names/values to pass, so a hook_tag function receives only the element name. The hook_tag function therefore may have to be edited. See section 3.4.9.
        -
        -  Old versions of htmLawed may be available online. E.g., for version 1.0, check http://www.bioinformatics.org/phplabware/downloads/htmLawed1.zip, for 1.1.1, htmLawed111.zip, and for 1.1.10, htmLawed1110.zip.
        - -
        -

        -4.6  Comparison with HTMLPurifier -

        (to top)
        -
        -  The HTMLPurifier PHP library by Edward Yang is a very good HTML filtering script that uses object oriented PHP code. Compared to htmLawed, it (as of year 2010):
        -
        -  *  does not support PHP versions older than 5.0 (HTMLPurifier dropped PHP 4 support after version 2)
        -
        -  *  is 15-20 times bigger (scores of files totalling more than 750 kb)
        -
        -  *  consumes 10-15 times more RAM memory (just including the HTMLPurifier files without calling the filter requires a few MBs of memory)
        -
        -  *  is expectedly slower
        -
        -  *  does not allow admins to fully allow all valid HTML (because of incomplete HTML support, it always considers elements like script illegal)
        -
        -  *  lacks many of the extra features of htmLawed (like entity conversions and code compaction/beautification)
        -
        -  *  has poor documentation
        -
        -  However, HTMLPurifier has finer checks for character encodings and attribute values, and can log warnings and errors. Visit the HTMLPurifier website for updated information.
        - -
        -

        -4.7  Use through application plug-ins/modules -

        (to top)
        -
        -  Plug-ins/modules to implement htmLawed in applications such as Drupal and DokuWiki may have been developed. Please check the application websites and the forum on the htmLawed site.
        - -
        -

        -4.8  Use in non-PHP applications -

        (to top)
        -
        -  Non-PHP applications written in Python, Ruby, etc., may be able to use htmLawed through system calls to the PHP engine. Such code may have been documented on the internet. Also check the forum on the htmLawed site.
        - -
        -

        -4.9  Donate -

        (to top)
        -
        -  A donation in any currency and amount to appreciate or support this software can be sent by PayPal to this email address: drpatnaik at yahoo dot com.
        - -
        -

        -4.10  Acknowledgements -

        (to top)
        -
        -  Nicholas Alipaz, Bryan Blakey, Pádraic Brady, Dac Chartrand, Ulf Harnhammer, Gareth Heyes, Hakre, Klaus Leithoff, Lukasz Pilorz, Shelley Powers, Psych0tr1a, Lincoln Russell, Tomas Sykorka, Harro Verton, Edward Yang, and many anonymous users.
        -
        -  Thank you!
        - -
        -
        -

        -5  Appendices -

        (to top)
        -

        -5.1  Characters discouraged in XHTML -

        (to top)
        -
        -  Characters represented by the following hexadecimal code-points are not invalid, even though some validators may issue messages stating otherwise.
        -
        -  7f to 84, 86 to 9f, fdd0 to fddf, 1fffe, 1ffff, 2fffe, 2ffff, 3fffe, 3ffff, 4fffe, 4ffff, 5fffe, 5ffff, 6fffe, 6ffff, 7fffe, 7ffff, 8fffe, 8ffff, 9fffe, 9ffff, afffe, affff, bfffe, bffff, cfffe, cffff, dfffe, dffff, efffe, effff, ffffe, fffff, 10fffe and 10ffff
        - -
        -

        -5.2  Valid attribute-element combinations -

        (to top)
        -
        -  Valid attribute-element combinations as per W3C specs.
        -
        -  *  includes deprecated attributes (marked ^), attributes for the non-standard embed element (marked *), and the non-standard allowfullscreen and bordercolor (marked ~)
        -  *  only non-frameset, HTML body elements
        -  *  name for a and map, and lang are invalid in XHTML 1.1
        -  *  target is valid for a in XHTML 1.1 and higher
        -  *  xml:space is only for XHTML 1.1
        -
        -  abbr - td, th
        -  accept - form, input
        -  accept-charset - form
        -  accesskey - a, area, button, input, label, legend, textarea
        -  action - form
        -  align - caption^, embed, applet, iframe, img^, input^, object^, legend^, table^, hr^, div^, h1^, h2^, h3^, h4^, h5^, h6^, p^, col, colgroup, tbody, td, tfoot, th, thead, tr
        -  allowfullscreen - iframe~
        -  alt - applet, area, img, input
        -  archive - applet, object
        -  axis - td, th
        -  bgcolor - embed, table^, tr^, td^, th^
        -  border - table, img^, object^
        -  bordercolor~ - table, td, tr
        -  cellpadding - table
        -  cellspacing - table
        -  char - col, colgroup, tbody, td, tfoot, th, thead, tr
        -  charoff - col, colgroup, tbody, td, tfoot, th, thead, tr
        -  charset - a, script
        -  checked - input
        -  cite - blockquote, q, del, ins
        -  classid - object
        -  clear - br^
        -  code - applet
        -  codebase - object, applet
        -  codetype - object
        -  color - font
        -  cols - textarea
        -  colspan - td, th
        -  compact - dir, dl^, menu, ol^, ul^
        -  coords - area, a
        -  data - object
        -  datetime - del, ins
        -  declare - object
        -  defer - script
        -  dir - bdo
        -  disabled - button, input, optgroup, option, select, textarea
        -  enctype - form
        -  face - font
        -  flashvars* - embed
        -  for - label
        -  frame - table
        -  frameborder - iframe
        -  headers - td, th
        -  height - embed, iframe, td^, th^, img, object, applet
        -  href - a, area
        -  hreflang - a
        -  hspace - applet, img^, object^
        -  ismap - img, input
        -  label - option, optgroup
        -  language - script^
        -  longdesc - img, iframe
        -  marginheight - iframe
        -  marginwidth - iframe
        -  maxlength - input
        -  method - form
        -  model* - embed
        -  multiple - select
        -  name - button, embed, textarea, applet^, select, form^, iframe^, img^, a^, input, object, map^, param
        -  nohref - area
        -  noshade - hr^
        -  nowrap - td^, th^
        -  object - applet
        -  onblur - a, area, button, input, label, select, textarea
        -  onchange - input, select, textarea
        -  onfocus - a, area, button, input, label, select, textarea
        -  onreset - form
        -  onselect - input, textarea
        -  onsubmit - form
        -  pluginspage* - embed
        -  pluginurl* - embed
        -  prompt - isindex
        -  readonly - textarea, input
        -  rel - a
        -  rev - a
        -  rows - textarea
        -  rowspan - td, th
        -  rules - table
        -  scope - td, th
        -  scrolling - iframe
        -  selected - option
        -  shape - area, a
        -  size - hr^, font, input, select
        -  span - col, colgroup
        -  src - embed, script, input, iframe, img
        -  standby - object
        -  start - ol^
        -  summary - table
        -  tabindex - a, area, button, input, object, select, textarea
        -  target - a^, area, form
        -  type - a, embed, object, param, script, input, li^, ol^, ul^, button
        -  usemap - img, input, object
        -  valign - col, colgroup, tbody, td, tfoot, th, thead, tr
        -  value - input, option, param, button, li^
        -  valuetype - param
        -  vspace - applet, img^, object^
        -  width - embed, hr^, iframe, img, object, table, td^, th^, applet, col, colgroup, pre^
        -  wmode - embed
        -  xml:space - pre, script, style
        -
        -  These are allowed in all but the shown elements:
        -
        -  class - param, script
        -  dir - applet, bdo, br, iframe, param, script
        -  id - script
        -  lang - applet, br, iframe, param, script
        -  onclick - applet, bdo, br, font, iframe, isindex, param, script
        -  ondblclick - applet, bdo, br, font, iframe, isindex, param, script
        -  onkeydown - applet, bdo, br, font, iframe, isindex, param, script
        -  onkeypress - applet, bdo, br, font, iframe, isindex, param, script
        -  onkeyup - applet, bdo, br, font, iframe, isindex, param, script
        -  onmousedown - applet, bdo, br, font, iframe, isindex, param, script
        -  onmousemove - applet, bdo, br, font, iframe, isindex, param, script
        -  onmouseout - applet, bdo, br, font, iframe, isindex, param, script
        -  onmouseover - applet, bdo, br, font, iframe, isindex, param, script
        -  onmouseup - applet, bdo, br, font, iframe, isindex, param, script
        -  style - param, script
        -  title - param, script
        -  xml:lang - applet, br, iframe, param, script
        - -
        -

        -5.3  CSS 2.1 properties accepting URLs -

        (to top)
        -
        -  background
        -  background-image
        -  content
        -  cue-after
        -  cue-before
        -  cursor
        -  list-style
        -  list-style-image
        -  play-during
        - -
        -

        -5.4  Microsoft Windows 1252 character replacements -

        (to top)
        -
        -  Key: d double, l left, q quote, r right, s. single
        -
        -  Code-point (decimal) - hexadecimal value - replacement entity - represented character
        -
        -  127 - 7f - (removed) - (not used)
        -  128 - 80 - &#8364; - euro
        -  129 - 81 - (removed) - (not used)
        -  130 - 82 - &#8218; - baseline s. q
        -  131 - 83 - &#402; - florin
        -  132 - 84 - &#8222; - baseline d q
        -  133 - 85 - &#8230; - ellipsis
        -  134 - 86 - &#8224; - dagger
        -  135 - 87 - &#8225; - d dagger
        -  136 - 88 - &#710; - circumflex accent
        -  137 - 89 - &#8240; - permile
        -  138 - 8a - &#352; - S Hacek
        -  139 - 8b - &#8249; - l s. guillemet
        -  140 - 8c - &#338; - OE ligature
        -  141 - 8d - (removed) - (not used)
        -  142 - 8e - &#381; - Z dieresis
        -  143 - 8f - (removed) - (not used)
        -  144 - 90 - (removed) - (not used)
        -  145 - 91 - &#8216; - l s. q
        -  146 - 92 - &#8217; - r s. q
        -  147 - 93 - &#8220; - l d q
        -  148 - 94 - &#8221; - r d q
        -  149 - 95 - &#8226; - bullet
        -  150 - 96 - &#8211; - en dash
        -  151 - 97 - &#8212; - em dash
        -  152 - 98 - &#732; - tilde accent
        -  153 - 99 - &#8482; - trademark
        -  154 - 9a - &#353; - s Hacek
        -  155 - 9b - &#8250; - r s. guillemet
        -  156 - 9c - &#339; - oe ligature
        -  157 - 9d - (removed) - (not used)
        -  158 - 9e - &#382; - z dieresis
        -  159 - 9f - &#376; - Y dieresis
        - -
        -

        -5.5  URL format -

        (to top)
        -
        -  An absolute URL has a protocol or scheme, a network location or hostname, and, optional path, parameters, query and fragment segments. Thus, an absolute URL has this generic structure:
        -
        - -    (scheme) : (//network location) /(path) ;(parameters) ?(query) #(fragment) -
        -
        -  The schemes can only contain letters, digits, +, . and -. Hostname is the portion after the // and up to the first / (if any; else, up to the end) when : is followed by a // (e.g., abc.com in ftp://abc.com/def); otherwise, it consists of everything after the : (e.g., def@abc.com in mailto:def@abc.com').
        -
        -  Relative URLs do not have explicit schemes and network locations; such values are inherited from a base URL.
        - -
        -

        -5.6  Brief on htmLawed code -

        (to top)
        -
        -  Much of the code's logic and reasoning can be understood from the documentation above.
        -
        -  The output of htmLawed is a text string containing the processed input. There is no custom error tracking.
        -
        -  Function arguments for htmLawed are:
        -
        -  *  $in - first argument; a text string; the input text to be processed. Any extraneous slashes added by PHP when magic quotes are enabled should be removed beforehand using PHP's stripslashes() function.
        -
        -  *  $config - second argument; an associative array; optional; named $C within htmLawed code. The array has keys with names like balance and keep_bad, and the values, which can be boolean, string, or array, depending on the key, are read to accordingly set the configurable parameters (indicated by the keys). All configurable parameters receive some default value if the value to be used is not specified by the user through $config. Finalized $config is thus a filtered and possibly larger array.
        -
        -  *  $spec - third argument; a text string; optional. The string has rules, written in an htmLawed-designated format, specifying element-specific attribute and attribute value restrictions. Function hl_spec() is used to convert the string to an associative-array, named $S within htmLawed code, for internal use. Finalized $spec is thus an array.
        -
        -  Finalized $config and $spec are made global variables while htmLawed is at work. Values of any pre-existing global variables with same names are noted, and their values are restored after htmLawed finishes processing the input (to capture the finalized values, the show_settings parameter of $config should be used). Depending on $config, another global variable hl_Ids, to track id attribute values for uniqueness, may be set. Unlike the other two variables, this one is not reset (or unset) post-processing.
        -
        -  Except for the main function htmLawed() and the functions kses() and kses_hook(), htmLawed's functions are name-spaced using the hl_ prefix. The functions and their roles are:
        -
        -  *  hl_attrval - checking attribute values against $spec
        -  *  hl_bal - tag balancing
        -  *  hl_cmtcd - handling CDATA sections and HTML comments
        -  *  hl_ent - entity handling
        -  *  hl_prot - checking a URL scheme/protocol
        -  *  hl_regex - checking syntax of a regular expression
        -  *  hl_spec - converting user-supplied $spec value to one used by htmLawed internally
        -  *  hl_tag - handling tags
        -  *  hl_tag2 - transforming tags
        -  *  hl_tidy - compact/beautify HTML
        -  *  hl_version - reporting htmLawed version
        -  *  htmLawed - main function
        -  *  kses - main function of kses
        -  *  kses_hook - hook function of kses
        -
        -  The last two are for compatibility with pre-existing code using the kses script. htmLawed's kses() basically passes on the filtering task to htmLawed() function after deciphering $config and $spec from the argument values supplied to it. kses_hook() is an empty function and is meant for being filled with custom code if the kses script users were using one.
        -
        -  htmLawed() finalizes $spec (with the help of hl_spec()) and $config, and globalizes them. Finalization of $config involves setting default values if an inappropriate or invalid one is supplied. This includes calling hl_regex() to check well-formedness of regular expression patterns if such expressions are user-supplied through $config. htmLawed() then removes invalid characters like nulls and x01 and appropriately handles entities using hl_ent(). HTML comments and CDATA sections are identified and treated as per $config with the help of hl_cmtcd(). When retained, the < and > characters identifying them, and the <, > and & characters inside them, are replaced with control characters (code-points 1 to 5) till any tag balancing is completed.
        -
        -  After this initial processing htmLawed() identifies tags using regex and processes them with the help of hl_tag() --  a large function that analyzes tag content, filtering it as per HTML standards, $config and $spec. Among other things, hl_tag() transforms deprecated elements using hl_tag2(), removes attributes from closing tags, checks attribute values as per $spec rules using hl_attrval(), and checks URL protocols using hl_prot(). htmLawed() performs tag balancing and nesting checks with a call to hl_bal(), and optionally compacts/beautifies the output with proper white-spacing with a call to hl_tidy(). The latter temporarily replaces white-space, and <, > and & characters inside pre, script and textarea elements, and HTML comments and CDATA sections with control characters (code-points 1 to 5, and 7).
        -
        -  htmLawed permits the use of custom code or hook functions at two stages. The first, called inside htmLawed(), allows the input text as well as the finalized $config and $spec values to be altered right after the initial processing (see section 3.7). The second is called by hl_tag() once the tag content is finalized (see section 3.4.9).
        -
        -  The functionality of htmLawed is dictated by the external HTML standard. It is thus coded for a clear-cut objective with not much concern for tweakability. The code is only minimally annotated with comments -- it is not meant to instruct; PHP developers familiar with the HTML specifications will see the logic, and others can always refer to the htmLawed documentation. The compact structuring of the statements is meant to aid a quick grasp of the logic. -
        -
        -
        -


        HTM version of htmLawed_README.txt generated on 10 Jun, 2015 using rTxt2htm from PHP Labware -
        -
        - - \ No newline at end of file diff --git a/extlib/htmLawed/htmLawed_README.txt b/extlib/htmLawed/htmLawed_README.txt deleted file mode 100755 index 091e5ef70f..0000000000 --- a/extlib/htmLawed/htmLawed_README.txt +++ /dev/null @@ -1,1744 +0,0 @@ -/* -htmLawed_README.txt, 9 June 2015 -htmLawed 1.1.20, 9 June 2015 -Copyright Santosh Patnaik -Dual licensed with LGPL 3 and GPL 2+ -A PHP Labware internal utility - http://www.bioinformatics.org/phplabware/internal_utilities/htmLawed -*/ - - -== Content ========================================================== - - -1 About htmLawed - 1.1 Example uses - 1.2 Features - 1.3 History - 1.4 License & copyright - 1.5 Terms used here -2 Usage - 2.1 Simple - 2.2 Configuring htmLawed using the '$config' parameter - 2.3 Extra HTML specifications using the '$spec' parameter - 2.4 Performance time & memory usage - 2.5 Some security risks to keep in mind - 2.6 Use without modifying old 'kses()' code - 2.7 Tolerance for ill-written HTML - 2.8 Limitations & work-arounds - 2.9 Examples of usage -3 Details - 3.1 Invalid/dangerous characters - 3.2 Character references/entities - 3.3 HTML elements - 3.3.1 HTML comments and 'CDATA' sections - 3.3.2 Tag-transformation for better XHTML-Strict - 3.3.3 Tag balancing and proper nesting - 3.3.4 Elements requiring child elements - 3.3.5 Beautify or compact HTML - 3.4 Attributes - 3.4.1 Auto-addition of XHTML-required attributes - 3.4.2 Duplicate/invalid 'id' values - 3.4.3 URL schemes (protocols) and scripts in attribute values - 3.4.4 Absolute & relative URLs - 3.4.5 Lower-cased, standard attribute values - 3.4.6 Transformation of deprecated attributes - 3.4.7 Anti-spam & 'href' - 3.4.8 Inline style properties - 3.4.9 Hook function for tag content - 3.5 Simple configuration directive for most valid XHTML - 3.6 Simple configuration directive for most `safe` HTML - 3.7 Using a hook function - 3.8 Obtaining `finalized` parameter values - 3.9 Retaining non-HTML tags in input with mixed markup -4 Other - 4.1 Support - 4.2 Known issues - 4.3 Change-log - 4.4 Testing - 4.5 Upgrade, & old versions - 4.6 Comparison with 'HTMLPurifier' - 4.7 Use through application plug-ins/modules - 4.8 Use in non-PHP applications - 4.9 Donate - 4.10 Acknowledgements -5 Appendices - 5.1 Characters discouraged in HTML - 5.2 Valid attribute-element combinations - 5.3 CSS 2.1 properties accepting URLs - 5.4 Microsoft Windows 1252 character replacements - 5.5 URL format - 5.6 Brief on htmLawed code - - -== 1 About htmLawed ================================================ - - - htmLawed is a PHP script to process text with HTML markup to make it more compliant with HTML standards and administrative policies. It works by making HTML well-formed with balanced and properly nested tags, neutralizing code that may be used for cross-site scripting (XSS) attacks, allowing only specified HTML tags and attributes, and so on. Such `lawing in` of HTML in text used in (X)HTML or XML documents ensures that it is in accordance with the aesthetics, safety and usability requirements set by administrators. - - htmLawed is highly customizable, and fast with low memory usage. Its free and open-source code is in one small file, does not require extensions or libraries, and works in older versions of PHP as well. It is a good alternative to the HTML Tidy:- http://tidy.sourceforge.net application. - - --- 1.1 Example uses ------------------------------------------------ - - - * Filtering of text submitted as comments on blogs to allow only certain HTML elements - - * Making RSS/Atom newsfeed item-content standard-compliant: often one uses an excerpt from an HTML document for the content, and with unbalanced tags, non-numerical entities, etc., such excerpts may not be XML-compliant - - * Text processing for stricter XML standard-compliance: e.g., to have lowercased 'x' in hexadecimal numeric entities becomes necessary if an XHTML document with MathML content needs to be served as 'application/xml' - - * Scraping text or data from web-pages - - * Pretty-printing HTML code - - --- 1.2 Features ---------------------------------------------------o - - - Key: '*' security feature, '^' standard compliance, '~' requires setting right options, '`' different from 'Kses' - - * make input more *secure* and *standard-compliant* - * use for HTML 4, XHTML 1.0 or 1.1, or even generic *XML* documents ^~` - - * *beautify* or *compact* HTML ^~` - - * can *restrict elements* ^~` - * ensures proper closure of empty elements like 'img' ^` - * *transform deprecated elements* like 'u' ^~` - * HTML *comments* and 'CDATA' sections can be permitted ^~` - * elements like 'script', 'object' and 'form' can be permitted ~ - - * *restrict attributes*, including *element-specifically* ^~` - * remove *invalid attributes* ^` - * element and attribute names are *lower-cased* ^ - * provide *required attributes*, like 'alt' for 'image' ^` - * *transforms deprecated attributes* ^~` - * attributes *declared only once* ^` - - * *restrict attribute values*, including *element-specifically* ^~` - * a value is declared for `empty` (`minimized`) attributes like 'checked' ^ - * check for potentially dangerous attribute values *~ - * ensure *unique* 'id' attribute values ^~` - * *double-quote* attribute values ^ - * lower-case *standard attribute values* like 'password' ^` - * permit custom, non-standard attributes as well as custom rules for standard attributes ~` - - * *attribute-specific URL protocol/scheme restriction* *~` - * disable *dynamic expressions* in 'style' values *~` - - * neutralize invalid named character entities ^` - * *convert* hexadecimal numeric entities to decimal ones, or vice versa ^~` - * convert named entities to numeric ones for generic XML use ^~` - - * remove *null* characters * - * neutralize potentially dangerous proprietary Netscape *Javascript entities* * - * replace potentially dangerous *soft-hyphen* character in URL-accepting attribute values with spaces * - - * remove common *invalid characters* not allowed in HTML or XML ^` - * replace *characters from Microsoft applications* like 'Word' that are discouraged in HTML or XML ^~` - * neutralize entities for characters invalid or discouraged in HTML or XML ^` - * appropriately neutralize '<', '&', '"', and '>' characters ^*` - - * understands improperly spaced tag content (like, spread over more than a line) and properly spaces them ` - * attempts to *balance tags* for well-formedness ^~` - * understands when *omitable closing tags* like '

        ' (allowed in HTML 4, transitional, e.g.) are missing ^~` - * attempts to permit only *validly nested tags* ^~` - * option to *remove or neutralize bad content* ^~` - * attempts to *rectify common errors of plain-text misplacement* (e.g., directly inside 'blockquote') ^~` - - * fast, *non-OOP* code of ~45 kb incurring peak basal memory usage of ~0.5 MB - * *compatible* with pre-existing code using 'Kses' (the filter used by 'WordPress') - - * optional *anti-spam* measures such as addition of 'rel="nofollow"' and link-disabling ~` - * optionally makes *relative URLs absolute*, and vice versa ~` - - * optionally mark '&' to identify the entities for '&', '<' and '>' introduced by htmLawed ~` - - * allows deployment of powerful *hook functions* to *inject* HTML, *consolidate* 'style' attributes to 'class', finely check attribute values, etc. ~` - - * *independent of character encoding* of input and does not affect it - - * *tolerance for ill-written HTML* to a certain degree - - --- 1.3 History ----------------------------------------------------o - - - htmLawed was created in 2007 for use with 'LabWiki', a wiki software developed at PHP Labware, as a suitable software could not be found. Existing PHP software like 'Kses' and 'HTMLPurifier' were deemed inadequate, slow, resource-intensive, or dependent on an extension or external application like 'HTML Tidy'. The core logic of htmLawed, that of identifying HTML elements and attributes, was based on the 'Kses' (version 0.2.2) HTML filter software of Ulf Harnhammar (it can still be used with code that uses 'Kses'; see section:- #2.6.). - - See section:- #4.3 for a detailed log of changes in htmLawed over the years, and section:- #4.10 for acknowledgements. - - --- 1.4 License & copyright ----------------------------------------o - - - htmLawed is free and open-source software dual copyrighted by Santosh Patnaik, MD, PhD, and licensed under LGPL license version 3:- http://www.gnu.org/licenses/lgpl-3.0.txt, and GPL license version 2:- http://www.gnu.org/licenses/gpl-2.0.txt (or later). - - --- 1.5 Terms used here --------------------------------------------o - - - In this document, only HTML body-level elements are considered. htmLawed does not have support for head-level elements, 'body', and the frame-level elements, 'frameset', 'frame' and 'noframes', and these elements are ignored here. - - * `administrator` - or admin; person setting up the code that utilizes htmLawed; also, `user` - * `attributes` - name-value pairs like 'href="http://x.com"' in opening tags - * `author` - see `writer` - * `character` - atomic unit of text; internally represented by a numeric `code-point` as specified by the `encoding` or `charset` in use - * `entity` - markup like '>' and ' ' used to refer to a character - * `element` - HTML element like 'a' and 'img' - * `element content` - content between the opening and closing tags of an element, like 'click' of the 'click' element - * `HTML` - implies XHTML unless specified otherwise - * `HTML body` - Complete HTML documents typically have a `head` and a `body` container. Information in `head` specifies title of the document, etc., whereas that in the body informs what is to be displayed on a web-page; it is only the elements for `body`, except 'frames', 'frameset' and 'noframes' that htmLawed is concerned with - * `input` - text given to htmLawed to process - * `processing` - involves filtering, correction, etc., of input - * `safe` - absence or reduction of certain characters and HTML elements and attributes in HTML of text that can otherwise potentially, and circumstantially, expose text readers to security vulnerabilities like cross-site scripting attacks (XSS) - * `scheme` - a URL protocol like 'http' and 'ftp' - * `specifications` - standard specifications, for HTML4, HTML5, Ruby, etc. - * `style property` - terms like 'border' and 'height' for which declarations are made in values for the 'style' attribute of elements - * `tag` - markers like '' and '' delineating element content; the opening tag can contain attributes - * `tag content` - consists of tag markers '<' and '>', element names like 'div', and possibly attributes - * `user` - administrator - * `writer` - end-user like a blog commenter providing the input that is to be processed; also, `author` - - --- 1.6 Availability ------------------------------------------------o - - - htmLawed can be downloaded for free at its website:- http://www.bioinformatics.org/phplabware/internal_utilities/htmLawed. Besides the 'htmLawed.php' file, the download has the htmLawed documentation (this document) in plain text:- htmLawed_README.txt and HTML:- htmLawed_README.htm formats, a script for testing:- htmLawedTest.php, and a text file for test-cases:- htmLawed_TESTCASE.txt. htmLawed is also available as a PHP class (OOP code) on its website. - - -== 2 Usage ========================================================oo - - - htmLawed works in PHP version 4.4 or higher. Either 'include()' the 'htmLawed.php' file, or copy-paste the entire code. To use with PHP 4.3, have the following code included: - - if(!function_exists('ctype_digit')){ - function ctype_digit($var){ - return ((int) $var == $var); - } - } - - --- 2.1 Simple ------------------------------------------------------ - - - The input text to be processed, '$text', is passed as an argument of type string; 'htmLawed()' returns the processed string: - - $processed = htmLawed($text); - - With the 'htmLawed class' (section:- #1.6), usage is: - - $processed = htmLawed::hl($text); - - *Notes*: (1) If input is from a '$_GET' or '$_POST' value, and 'magic quotes' are enabled on the PHP setup, run 'stripslashes()' on the input before passing to htmLawed. (2) htmLawed does not have support for head-level elements, 'body', and the frame-level elements, 'frameset', 'frame' and 'noframes'. - - By default, htmLawed will process the text allowing all valid HTML elements/tags, secure URL scheme/CSS style properties, etc. It will allow 'CDATA' sections and HTML comments, balance tags, and ensure proper nesting of elements. Such actions can be configured using two other optional arguments -- '$config' and '$spec': - - $processed = htmLawed($text, $config, $spec); - - The '$config' and '$spec' arguments are detailed below. Some examples are shown in section:- #2.9. For maximum protection against 'XSS' and other scripting attacks (e.g., by disallowing Javascript code), consider using the 'safe' parameter; see section:- #3.6. - - --- 2.2 Configuring htmLawed using the '$config' parameter ---------o - - - '$config' instructs htmLawed on how to tackle certain tasks. When '$config' is not specified, or not set as an array (e.g., '$config = 1'), htmLawed will take default actions. One or many of the task-action or value-specification pairs can be specified in '$config' as array key-value pairs. If a parameter is not specified, htmLawed will use the default value/action indicated further below. - - $config = array('comment'=>0, 'cdata'=>1); - $processed = htmLawed($text, $config); - - Or, - - $processed = htmLawed($text, array('comment'=>0, 'cdata'=>1)); - - Below are the possible value-specification combinations. In PHP code, values that are integers should not be quoted and should be used as numeric types (unless meant as string/text). - - Key: '*' default, '^' different default when htmLawed is used in the Kses-compatible mode (see section:- #2.6), '~' different default when 'valid_xhtml' is set to '1' (see section:- #3.5), '"' different default when 'safe' is set to '1' (see section:- #3.6) - - *abs_url* - Make URLs absolute or relative; '$config["base_url"]' needs to be set; see section:- #3.4.4 - - '-1' - make relative - '0' - no action * - '1' - make absolute - - *and_mark* - Mark '&' characters in the original input; see section:- #3.2 - - *anti_link_spam* - Anti-link-spam measure; see section:- #3.4.7 - - '0' - no measure taken * - `array("regex1", "regex2")` - will ensure a 'rel' attribute with 'nofollow' in its value in case the 'href' attribute value matches the regular expression pattern 'regex1', and/or will remove 'href' if its value matches the regular expression pattern 'regex2'. E.g., 'array("/./", "/://\W*(?!(abc\.com|xyz\.org))/")'; see section:- #3.4.7 for more. - - *anti_mail_spam* - Anti-mail-spam measure; see section:- #3.4.7 - - '0' - no measure taken * - `word` - '@' in mail address in 'href' attribute value is replaced with specified `word` - - *balance* - Balance tags for well-formedness and proper nesting; see section:- #3.3.3 - - '0' - no - '1' - yes * - - *base_url* - Base URL value that needs to be set if '$config["abs_url"]' is not '0'; see section:- #3.4.4 - - *cdata* - Handling of 'CDATA' sections; see section:- #3.3.1 - - '0' - don't consider 'CDATA' sections as markup and proceed as if plain text ^" - '1' - remove - '2' - allow, but neutralize any '<', '>', and '&' inside by converting them to named entities - '3' - allow * - - *clean_ms_char* - Replace discouraged characters introduced by Microsoft Word, etc.; see section:- #3.1 - - '0' - no * - '1' - yes - '2' - yes, but replace special single & double quotes with ordinary ones - - *comment* - Handling of HTML comments; see section:- #3.3.1 - - '0' - don't consider comments as markup and proceed as if plain text ^" - '1' - remove - '2' - allow, but neutralize any '<', '>', and '&' inside by converting to named entities - '3' - allow * - - *css_expression* - Allow dynamic CSS expression by not removing the expression from CSS property values in 'style' attributes; see section:- #3.4.8 - - '0' - remove * - '1' - allow - - *deny_attribute* - Denied HTML attributes; see section:- #3.4 - - '0' - none * - `string` - dictated by values in `string` - 'on*' (like 'onfocus') attributes not allowed - " - - *direct_nest_list* - Allow direct nesting of a list within another without requiring it to be a list item; see section:- #3.3.4 - - '0' - no * - '1' - yes - - *elements* - Allowed HTML elements; see section:- #3.3 - - '* -center -dir -font -isindex -menu -s -strike -u' - ~ - 'applet, embed, iframe, object, script' not allowed - " - - *hexdec_entity* - Allow hexadecimal numeric entities and do not convert to the more widely accepted decimal ones, or convert decimal to hexadecimal ones; see section:- #3.2 - - '0' - no - '1' - yes * - '2' - convert decimal to hexadecimal ones - - *hook* - Name of an optional hook function to alter the input string, '$config' or '$spec' before htmLawed starts its main work; see section:- #3.7 - - '0' - no hook function * - `name` - `name` is name of the hook function ('kses_hook' ^) - - *hook_tag* - Name of an optional hook function to alter tag content finalized by htmLawed; see section:- #3.4.9 - - '0' - no hook function * - `name` - `name` is name of the hook function - - *keep_bad* - Neutralize bad tags by converting '<' and '>' to entities, or remove them; see section:- #3.3.3 - - '0' - remove ^ - '1' - neutralize both tags and element content - '2' - remove tags but neutralize element content - '3' and '4' - like '1' and '2' but remove if text ('pcdata') is invalid in parent element - '5' and '6' * - like '3' and '4' but line-breaks, tabs and spaces are left - - *lc_std_val* - For XHTML compliance, predefined, standard attribute values, like 'get' for the 'method' attribute of 'form', must be lowercased; see section:- #3.4.5 - - '0' - no - '1' - yes * - - *make_tag_strict* - Transform/remove these non-strict XHTML elements, even if they are allowed by the admin: 'applet' 'center' 'dir' 'embed' 'font' 'isindex' 'menu' 's' 'strike' 'u'; see section:- #3.3.2 - - '0' - no ^ - '1' - yes, but leave 'applet', 'embed' and 'isindex' elements that currently can't be transformed * - '2' - yes, removing 'applet', 'embed' and 'isindex' elements and their contents (nested elements remain) ~ - - *named_entity* - Allow non-universal named HTML entities, or convert to numeric ones; see section:- #3.2 - - '0' - convert - '1' - allow * - - *no_deprecated_attr* - Allow deprecated attributes or transform them; see section:- #3.4.6 - - '0' - allow ^ - '1' - transform, but 'name' attributes for 'a' and 'map' are retained * - '2' - transform - - *parent* - Name of the parent element, possibly imagined, that will hold the input; see section:- #3.3 - - *safe* - Magic parameter to make input the most secure against XSS without needing to specify other relevant '$config' parameters; see section:- #3.6 - - '0' - no * - '1' - will auto-adjust other relevant '$config' parameters (indicated by '"' in this list) - - *schemes* - Array of attribute-specific, comma-separated, lower-cased list of schemes (protocols) allowed in attributes accepting URLs (or '!' to `deny` any URL); '*' covers all unspecified attributes; see section:- #3.4.3 - - 'href: aim, feed, file, ftp, gopher, http, https, irc, mailto, news, nntp, sftp, ssh, telnet; *:file, http, https' * - '*: ftp, gopher, http, https, mailto, news, nntp, telnet' ^ - 'href: aim, feed, file, ftp, gopher, http, https, irc, mailto, news, nntp, sftp, ssh, telnet; style: !; *:file, http, https' " - - *show_setting* - Name of a PHP variable to assign the `finalized` '$config' and '$spec' values; see section:- #3.8 - - *style_pass* - Do not look at 'style' attribute values, letting them through without any alteration - - '0' - no * - '1' - htmLawed will let through any 'style' value; see section:- #3.4.8 - - *tidy* - Beautify or compact HTML code; see section:- #3.3.5 - - '-1' - compact - '0' - no * - '1' or 'string' - beautify (custom format specified by 'string') - - *unique_ids* - 'id' attribute value checks; see section:- #3.4.2 - - '0' - no ^ - '1' - remove duplicate and/or invalid ones * - `word` - remove invalid ones and replace duplicate ones with new and unique ones based on the `word`; the admin-specified `word`, like 'my_', should begin with a letter (a-z) and can contain letters, digits, '.', '_', '-', and ':'. - - *valid_xhtml* - Magic parameter to make input the most valid XHTML without needing to specify other relevant '$config' parameters; see section:- #3.5 - - '0' - no * - '1' - will auto-adjust other relevant '$config' parameters (indicated by '~' in this list) - - *xml:lang* - Auto-adding 'xml:lang' attribute; see section:- #3.4.1 - - '0' - no * - '1' - add if 'lang' attribute is present - '2' - add if 'lang' attribute is present, and remove 'lang' ~ - - --- 2.3 Extra HTML specifications using the $spec parameter --------o - - - The '$spec' argument of htmLawed can be used to disallow an otherwise legal attribute for an element, or to restrict the attribute's values. This can also be helpful as a security measure (e.g., in certain versions of browsers, certain values can cause buffer overflows and denial of service attacks), or in enforcing admin policies. '$spec' is specified as a string of text containing one or more `rules`, with multiple rules separated from each other by a semi-colon (';'). E.g., - - $spec = 'i=-*; td, tr=style, id, -*; a=id(match="/[a-z][a-z\d.:\-`"]*/i"/minval=2), href(maxlen=100/minlen=34); img=-width,-alt'; - $processed = htmLawed($text, $config, $spec); - - Or, - - $processed = htmLawed($text, $config, 'i=-*; td, tr=style, id, -*; a=id(match="/[a-z][a-z\d.:\-`"]*/i"/minval=2), href(maxlen=100/minlen=34); img=-width,-alt'); - - A rule begins with an HTML *element* name(s) (`rule-element`), for which the rule applies, followed by an equal ('=') sign. A rule-element may represent multiple elements if comma (,)-separated element names are used. E.g., 'th,td,tr='. - - Rest of the rule consists of comma-separated HTML *attribute names*. A minus ('-') character before an attribute means that the attribute is not permitted inside the rule-element. E.g., '-width'. To deny all attributes, '-*' can be used. - - Following shows examples of rule excerpts with rule-element 'a' and the attributes that are being permitted: - - * 'a=' - all - * 'a=id' - all - * 'a=href, title, -id, -onclick' - all except 'id' and 'onclick' - * 'a=*, id, -id' - all except 'id' - * 'a=-*' - none - * 'a=-*, href, title' - none except 'href' and 'title' - * 'a=-*, -id, href, title' - none except 'href' and 'title' - - Rules regarding *attribute values* are optionally specified inside round brackets after attribute names in slash ('/')-separated `parameter = value` pairs. E.g., 'title(maxlen=30/minlen=5)'. None or one or more of the following parameters may be specified: - - * 'oneof' - one or more choices separated by '|' that the value should match; if only one choice is provided, then the value must match that choice - - * 'noneof' - one or more choices separated by '|' that the value should not match - - * 'maxlen' and 'minlen' - upper and lower limits for the number of characters in the attribute value; specified in numbers - - * 'maxval' and 'minval' - upper and lower limits for the numerical value specified in the attribute value; specified in numbers - - * 'match' and 'nomatch' - pattern that the attribute value should or should not match; specified as PHP/PCRE-compatible regular expressions with delimiters and possibly modifiers - - * 'default' - a value to force on the attribute if the value provided by the writer does not fit any of the specified parameters - - If 'default' is not set and the attribute value does not satisfy any of the specified parameters, then the attribute is removed. The 'default' value can also be used to force all attribute declarations to take the same value (by getting the values declared illegal by setting, e.g., 'maxlen' to '-1'). - - Examples with `input` '' are shown below. - - `Rule`: 'input=title(maxlen=60/minlen=6), value' - `Output`: '' - - `Rule`: 'input=title(), value(maxval=8/default=6)' - `Output`: '' - - `Rule`: 'input=title(nomatch=%w.d%i), value(match=%em%/default=6em)' - `Output`: '' - - `Rule`: 'input=title(oneof=height|depth/default=depth), value(noneof=5|6)' - `Output`: '' - - *Special characters*: The characters ';', ',', '/', '(', ')', '|', '~' and space have special meanings in the rules. Words in the rules that use such characters, or the characters themselves, should be `escaped` by enclosing in pairs of double-quotes ('"'). A back-tick ('`') can be used to escape a literal '"'. An example rule illustrating this is 'input=value(maxlen=30/match="/^\w/"/default="your `"ID`"")'. - - *Note*: To deny an attribute for all elements for which it is legal, '$config["deny_attribute"]' (see section:- #3.4) can be used instead of '$spec'. Also, attributes can be allowed element-specifically through '$spec' while being denied globally through '$config["deny_attribute"]'. The 'hook_tag' parameter (section:- #3.4.9) can also be possibly used to implement a functionality like that achieved using '$spec' functionality. - - '$spec' can also be used to permit custom, non-standard attributes as well as custom rules for standard attributes. Thus, the following value of '$spec' will permit the custom uses of the standard 'rel' attribute in 'input' (not permitted as per standards) and of a non-standard attribute, 'vFlag', in 'img'. - - $spec = 'img=vFlag; input=rel' - - The attribute names can contain alphabets, colons (:) and hyphens (-), but they must start with an alphabet. - - --- 2.4 Performance time & memory usage ----------------------------o - - - The time and memory consumed during text processing by htmLawed depends on its configuration, the size of the input, and the amount, nestedness and well-formedness of the HTML markup within the input. In particular, tag balancing and beautification each can increase the processing time by about a quarter. - - The htmLawed demo:- htmLawedTest.php can be used to evaluate the performance and effects of different types of input and '$config'. - - --- 2.5 Some security risks to keep in mind ------------------------o - - - When setting the parameters/arguments (like those to allow certain HTML elements) for use with htmLawed, one should bear in mind that the setting may let through potentially `dangerous` HTML code which is meant to steal user-data, deface a website, render a page non-functional, etc. Unless end-users, either people or software, supplying the content are completely trusted, security issues arising from the degree of HTML usage permitted through htmLawed's setting should be considered. For example, following increase security risks: - - * Allowing 'script', 'applet', 'embed', 'iframe' or 'object' elements, or certain of their attributes like 'allowscriptaccess' - - * Allowing HTML comments (some Internet Explorer versions are vulnerable with, e.g., '' - - * Allowing dynamic CSS expressions (some Internet Explorer versions are vulnerable) - - * Allowing the 'style' attribute - - To remove `unsecure` HTML, code-developers using htmLawed must set '$config' appropriately. E.g., '$config["elements"] = "* -script"' to deny the 'script' element (section:- #3.3), '$config["safe"] = 1' to auto-configure ceratin htmLawed parameters for maximizing security (section:- #3.6), etc. - - Permitting the '*style*' attribute brings in risks of `click-jacking`, `phishing`, web-page overlays, etc., `even` when the 'safe' parameter is enabled (see section:- #3.6). Except for URLs and a few other things like CSS dynamic expressions, htmLawed currently does not check every CSS style property. It does provide ways for the code-developer implementing htmLawed to do such checks through htmLawed's '$spec' argument, and through the 'hook_tag' parameter (see section:- #3.4.8 for more). Disallowing 'style' completely and relying on CSS classes and stylesheet files is recommended. - - htmLawed does not check or correct the character *encoding* of the input it receives. In conjunction with permissive circumstances, such as when the character encoding is left undefined through HTTP headers or HTML 'meta' tags, this can allow for an exploit (like Google's `UTF-7/XSS` vulnerability of the past). - - --- 2.6 Use without modifying old 'kses()' code --------------------o - - - The 'Kses' PHP script is used by many applications (like 'WordPress'). It is possible to have such applications use htmLawed instead, since it is compatible with code that calls the 'kses()' function declared in the 'Kses' file (usually named 'kses.php'). E.g., application code like this will continue to work after replacing 'Kses' with htmLawed: - - $comment_filtered = kses($comment_input, array('a'=>array(), 'b'=>array(), 'i'=>array())); - - For some of the '$config' parameters, htmLawed will use values other than the default ones. These are indicated by '^' in section:- #2.2. To force htmLawed to use other values, function 'kses()' in the htmLawed code should be edited -- a few configurable parameters/variables need to be changed. - - If the application uses a 'Kses' file that has the 'kses()' function declared, then, to have the application use htmLawed instead of 'Kses', simply rename 'htmLawed.php' (to 'kses.php', e.g.) and replace the 'Kses' file (or just replace the code in the 'Kses' file with the htmLawed code). If the 'kses()' function in the 'Kses' file had been renamed by the application developer (e.g., in 'WordPress', it is named 'wp_kses()'), then appropriately rename the 'kses()' function in the htmLawed code. - - If the 'Kses' file used by the application has been highly altered by the application developers, then one may need a different approach. E.g., with 'WordPress', it is best to copy the htmLawed code to 'wp_includes/kses.php', rename the newly added function 'kses()' to 'wp_kses()', and delete the code for the original 'wp_kses()' function. - - If the 'Kses' code has a non-empty hook function (e.g., 'wp_kses_hook()' in case of 'WordPress'), then the code for htmLawed's 'kses_hook()' function should be appropriately edited. However, the requirement of the hook function should be re-evaluated considering that htmLawed has extra capabilities. With 'WordPress', the hook function is an essential one. The following code is suggested for the htmLawed 'kses_hook()' in case of 'WordPress': - - function kses_hook($string, &$cf, &$spec){ - // kses compatibility - $allowed_html = $spec; - $allowed_protocols = array(); - foreach($cf['schemes'] as $v){ - foreach($v as $k2=>$v2){ - if(!in_array($k2, $allowed_protocols)){ - $allowed_protocols[] = $k2; - } - } - } - return wp_kses_hook($string, $allowed_html, $allowed_protocols); - // eof - } - - --- 2.7 Tolerance for ill-written HTML -----------------------------o - - - htmLawed can work with ill-written HTML code in the input. However, HTML that is too ill-written may not be `read` as HTML, and may therefore get identified as mere plain text. Following statements indicate the degree of `looseness` that htmLawed can work with, and can be provided in instructions to writers: - - * Tags must be flanked by '<' and '>' with no '>' inside -- any needed '>' should be put in as '>'. It is possible for tag content (element name and attributes) to be spread over many lines instead of being on one. A space may be present between the tag content and '>', like '
        ' and '', but not after the '<'. - - * Element and attribute names need not be lower-cased. - - * Attribute string of elements may be liberally spaced with tabs, line-breaks, etc. - - * Attribute values may be single- and not double-quoted. - - * Left-padding of numeric entities (like, ' ', '&x07ff;') with '0' is okay as long as the number of characters between between the '&' and the ';' does not exceed 8. All entities must end with ';' though. - - * Named character entities must be properly cased. Thus, '≪' or '&TILDE;' will not be recognized as entities and will be `neutralized`. - - * HTML comments should not be inside element tags (they can be between tags), and should begin with ''. Characters like '<', '>', and '&' may be allowed inside depending on '$config', but any '-->' inside should be put in as '-->'. Any '--' inside will be automatically converted to '-', and a space will be added before the comment delimiter '-->'. - - * 'CDATA' sections should not be inside element tags, and can be in element content only if plain text is allowed for that element. They should begin with '<[CDATA[' and end with ']]>'. Characters like '<', '>', and '&' may be allowed inside depending on '$config', but any ']]>' inside should be put in as ']]>'. - - * For attribute values, character entities '<', '>' and '&' should be used instead of characters '<' and '>', and '&' (when '&' is not part of a character entity). This applies even for Javascript code in values of attributes like 'onclick'. - - * Characters '<', '>', '&' and '"' that are part of actual Javascript, etc., code in 'script' elements should be used as such and not be put in as entities like '>'. Otherwise, though the HTML will be valid, the code may fail to work. Further, if such characters have to be used, then they should be put inside 'CDATA' sections. - - * Simple instructions like "an opening tag cannot be present between two closing tags" and "nested elements should be closed in the reverse order of how they were opened" can help authors write balanced HTML. If tags are imbalanced, htmLawed will try to balance them, but in the process, depending on '$config["keep_bad"]', some code/text may be lost. - - * Input authors should be notified of admin-specified allowed elements, attributes, configuration values (like conversion of named entities to numeric ones), etc. - - * With '$config["unique_ids"]' not '0' and the 'id' attribute being permitted, writers should carefully avoid using duplicate or invalid 'id' values as even though htmLawed will correct/remove the values, the final output may not be the one desired. E.g., when '' is processed into -''. - - * Even if intended HTML is lost from an ill-written input, the processed output will be more secure and standard-compliant. - - * For URLs, unless '$config["scheme"]' is appropriately set, writers should avoid using escape characters or entities in schemes. E.g., 'http' (which many browsers will read as the harmless 'http') may be considered bad by htmLawed. - - * htmLawed will attempt to put plain text present directly inside 'blockquote', 'form', 'map' and 'noscript' elements (illegal as per the specifications) inside auto-generated 'div' elements. - - --- 2.8 Limitations & work-arounds ---------------------------------o - - - htmLawed's main objective is to make the input text `more` standard-compliant, secure for readers, and free of HTML elements and attributes considered undesirable by the administrator. Some of its current limitations, regardless of this objective, are noted below along with work-arounds. - - It should be borne in mind that no browser application is 100% standard-compliant, and that some of the standard specifications (like asking for normalization of white-spacing within 'textarea' elements) are clearly wrong. Regarding security, note that `unsafe` HTML code is not legally invalid per se. - - * htmLawed is meant for input that goes into the 'body' of HTML documents. HTML's head-level elements are not supported, nor are the frameset elements 'frameset', 'frame' and 'noframes'. Content of the latter elements can, however, be individually filtered through htmLawed. - - * It cannot transform the non-standard 'embed' elements to the standard-compliant 'object' elements. Yet, it can allow 'embed' elements if permitted ('embed' is widely used and supported). Admins can certainly use the 'hook_tag' parameter (section:- #3.4.9) to deploy a custom embed-to-object converter function. - - * The only non-standard element that may be permitted is 'embed'; others like 'noembed' and 'nobr' cannot be permitted without modifying the htmLawed code. - - * It cannot handle input that has non-HTML code like 'SVG' and 'MathML'. One way around is to break the input into pieces and passing only those without non-HTML code to htmLawed. Another is described in section:- #3.9. A third way may be to some how take advantage of the '$config["and_mark"]' parameter (see section:- #3.2). - - * By default, htmLawed won't check many attribute values for standard compliance. E.g., 'width="20m"' with the dimension in non-standard 'm' is let through. Implementing universal and strict attribute value checks can make htmLawed slow and resource-intensive. Admins should look at the 'hook_tag' parameter (section:- #3.4.9) or '$spec' to enforce finer checks. - - * The attributes, deprecated (which can be transformed too) or not, that it supports are largely those that are in the specifications. Only a few of the proprietary attributes are supported. - - * Except for contained URLs and dynamic expressions (also optional), htmLawed does not check CSS style property values. Admins should look at using the 'hook_tag' parameter (section:- #3.4.9) or '$spec' for finer checks. Perhaps the best option is to disallow 'style' but allow 'class' attributes with the right 'oneof' or 'match' values for 'class', and have the various class style properties in '.css' CSS stylesheet files. - - * htmLawed does not parse emoticons, decode `BBcode`, or `wikify`, auto-converting text to proper HTML. Similarly, it won't convert line-breaks to 'br' elements. Such functions are beyond its purview. Admins should use other code to pre- or post-process the input for such purposes. - - * htmLawed cannot be used to have links force-opened in new windows (by auto-adding appropriate 'target' and 'onclick' attributes to 'a'). Admins should look at Javascript-based DOM-modifying solutions for this. Admins may also be able to use a custom hook function to enforce such checks ('hook_tag' parameter; see section:- #3.4.9). - - * Nesting-based checks are not possible. E.g., one cannot disallow 'p' elements specifically inside 'td' while permitting it elsewhere. Admins may be able to use a custom hook function to enforce such checks ('hook_tag' parameter; see section:- #3.4.9). - - * Except for optionally converting absolute or relative URLs to the other type, htmLawed will not alter URLs (e.g., to change the value of query strings or to convert 'http' to 'https'. Having absolute URLs may be a standard-requirement, e.g., when HTML is embedded in email messages, whereas altering URLs for other purposes is beyond htmLawed's goals. Admins may be able to use a custom hook function to enforce such checks ('hook_tag' parameter; see section:- #3.4.9). - - * Pairs of opening and closing tags that do not enclose any content (like '') are not removed. This may be against the standard specifications for certain elements (e.g., 'table'). However, presence of such standard-incompliant code will not break the display or layout of content. Admins can also use simple regex-based code to filter out such code. - - * htmLawed does not check for certain element orderings described in the standard specifications (e.g., in a 'table', 'tbody' is allowed before 'tfoot'). Admins may be able to use a custom hook function to enforce such checks ('hook_tag' parameter; see section:- #3.4.9). - - * htmLawed does not check the number of nested elements. E.g., it will allow two 'caption' elements in a 'table' element, illegal as per the specifications. Admins may be able to use a custom hook function to enforce such checks ('hook_tag' parameter; see section:- #3.4.9). - - * htmLawed might convert certain entities to actual characters and remove backslashes and CSS comment-markers ('/*') in 'style' attribute values in order to detect malicious HTML like crafted IE-specific dynamic expressions like 'expression...'. If this is too harsh, admins can allow CSS expressions through htmLawed core but then use a custom function through the 'hook_tag' parameter (section:- #3.4.9) to more specifically identify CSS expressions in the 'style' attribute values. Also, using '$config["style_pass"]', it is possible to have htmLawed pass 'style' attribute values without even looking at them (section:- #3.4.8). - - * htmLawed does not correct certain possible attribute-based security vulnerabilities (e.g., 'x'). These arise when browsers mis-identify markup in `escaped` text, defeating the very purpose of escaping text (a bad browser will read the given example as 'x'). - - * Because of poor Unicode support in PHP, htmLawed does not remove the `high value` HTML-invalid characters with multi-byte code-points. Such characters however are extremely unlikely to be in the input. (see section:- #3.1). - - * htmLawed does not check or correct the character encoding of the input it receives. In conjunction with permitting circumstances such as when the character encoding is left undefined through HTTP headers or HTML 'meta' tags, this can permit an exploit (like Google's `UTF-7/XSS` vulnerability of the past). Also, htmLawed can mangle input text if it is not well-formed in terms of character encoding. Administrators can consider using code available elsewhere to check well-formedness of input text characters to correct any defect. - - * htmLawed is expected to work with input texts in ASCII-compatible single byte encodings such as national variants of ASCII (like ISO-646-DE/German of the ISO 646 standard), extended ASCII variants (like ISO 8859-10/Turkish of the ISO 8859/ISO Latin standard), ISO 8859-based Windows variants (like Windows 1252), EBCDIC, Shift JIS (Japanese), GB-Roman (Chinese), and KS-Roman (Korean). It should also properly handle texts with variable byte encodings like UTF-7 (Unicode) and UTF-8 (Unicode). However, htmLawed may mangle input texts with double byte encodings like UTF-16 (Unicode), JIS X 0208:1997 (Japanese) and K SX 1001:1992 (Korean), or the UTF-32 (Unicode) quadruple byte encoding. If an input text has such an encoding, administrators can use PHP's iconv:- http://php.net/manual/en/book.iconv.php functions, or some other mean, to convert text to UTF-8 before passing it to htmLawed. - - * Like any script using PHP's PCRE regex functions, PHP setup-specific low PCRE limit values can cause htmLawed to at least partially fail with very long input texts. - - --- 2.9 Examples of usage -------------------------------------------o - - - Safest, allowing only `safe` HTML markup -- - - $config = array('safe'=>1); - $out = htmLawed($in); - - Simplest, allowing all valid HTML markup except 'javascript:' -- - - $out = htmLawed($in); - - Allowing all valid HTML markup including 'javascript:' -- - - $config = array('schemes'=>'*:*'); - $out = htmLawed($in, $config); - - Allowing only 'safe' HTML and the elements 'a', 'em', and 'strong' -- - - $config = array('safe'=>1, 'elements'=>'a, em, strong'); - $out = htmLawed($in, $config); - - Not allowing elements 'script' and 'object' -- - - $config = array('elements'=>'* -script -object'); - $out = htmLawed($in, $config); - - Not allowing attributes 'id' and 'style' -- - - $config = array('deny_attribute'=>'id, style'); - $out = htmLawed($in, $config); - - Permitting only attributes 'title' and 'href' -- - - $config = array('deny_attribute'=>'* -title -href'); - $out = htmLawed($in, $config); - - Remove bad/disallowed tags altogether instead of converting them to entities -- - - $config = array('keep_bad'=>0); - $out = htmLawed($in, $config); - - Allowing attribute 'title' only in 'a' and not allowing attributes 'id', 'style', or scriptable `on*` attributes like 'onclick' -- - - $config = array('deny_attribute'=>'title, id, style, on*'); - $spec = 'a=title'; - $out = htmLawed($in, $config, $spec); - - Allowing a custom attribute, 'vFlag', in 'img' and permitting custom use of the standard attribute, 'rel', in 'input' -- - - $spec = 'img=vFlag; input=rel'; - $out = htmLawed($in, $config, $spec); - - Some case-studies are presented below. - - *1.* A blog administrator wants to allow only 'a', 'em', 'strike', 'strong' and 'u' in comments, but needs 'strike' and 'u' transformed to 'span' for better XHTML 1-strict compliance, and, he wants the 'a' links to point only to 'http' or 'https' resources: - - $processed = htmLawed($in, array('elements'=>'a, em, strike, strong, u', 'make_tag_strict'=>1, 'safe'=>1, 'schemes'=>'*:http, https'), 'a=href'); - - *2.* An author uses a custom-made web application to load content on his web-site. He is the only one using that application and the content he generates has all types of HTML, including scripts. The web application uses htmLawed primarily as a tool to correct errors that creep in while writing HTML and to take care of the occasional `bad` characters in copy-paste text introduced by Microsoft Office. The web application provides a preview before submitted input is added to the content. For the previewing process, htmLawed is set up as follows: - - $processed = htmLawed($in, array('css_expression'=>1, 'keep_bad'=>1, 'make_tag_strict'=>1, 'schemes'=>'*:*', 'valid_xhtml'=>1)); - - For the final submission process, 'keep_bad' is set to '6'. A value of '1' for the preview process allows the author to note and correct any HTML mistake without losing any of the typed text. - - *3.* A data-miner is scraping information in a specific table of similar web-pages and is collating the data rows, and uses htmLawed to reduce unnecessary markup and white-spaces: - - $processed = htmLawed($in, array('elements'=>'tr, td', 'tidy'=>-1), 'tr, td ='); - - -== 3 Details =====================================================oo - - --- 3.1 Invalid/dangerous characters -------------------------------- - - - Valid characters (more correctly, their code-points) in HTML or XML are, hexadecimally, '9', 'a', 'd', '20' to 'd7ff', and 'e000' to '10ffff', except 'fffe' and 'ffff' (decimally, '9', '10', '13', '32' to '55295', and '57344' to '1114111', except '65534' and '65535'). htmLawed removes the invalid characters '0' to '8', 'b', 'c', and 'e' to '1f'. - - Because of PHP's poor native support for multi-byte characters, htmLawed cannot check for the remaining invalid code-points. However, for various reasons, it is very unlikely for any of those characters to be in the input. - - Characters that are discouraged (see section:- #5.1) but not invalid are not removed by htmLawed. - - It (function 'hl_tag()') also replaces the potentially dangerous (in some Mozilla [Firefox] and Opera browsers) soft-hyphen character (code-point, hexadecimally, 'ad', or decimally, '173') in attribute values with spaces. Where required, the characters '<', '>', '&', and '"' are converted to entities. - - With '$config["clean_ms_char"]' set as '1' or '2', many of the discouraged characters (decimal code-points '127' to '159' except '133') that many Microsoft applications incorrectly use (as per the 'Windows 1252' ['Cp-1252'] or a similar encoding system), and the character for decimal code-point '133', are converted to appropriate decimal numerical entities (or removed for a few cases)-- see appendix in section:- #5.4. This can help avoid some display issues arising from copying-pasting of content. - - With '$config["clean_ms_char"]' set as '2', characters for the hexadecimal code-points '82', '91', and '92' (for special single-quotes), and '84', '93', and '94' (for special double-quotes) are converted to ordinary single and double quotes respectively and not to entities. - - The character values are replaced with entities/characters and not character values referred to by the entities/characters to keep this task independent of the character-encoding of input text. - - The '$config["clean_ms_char"]' parameter should not be used if authors do not copy-paste Microsoft-created text, or if the input text is not believed to use the 'Windows 1252' ('Cp-1252') or a similar encoding like 'Cp-1251' (otherwise, for example when UTF-8 encoding is in use, Japanese or Korean characters can get mangled). Further, the input form and the web-pages displaying it or its content should have the character encoding appropriately marked-up. - - --- 3.2 Character references/entities ------------------------------o - - - Valid character entities take the form '&*;' where '*' is '#x' followed by a hexadecimal number (hexadecimal numeric entity; like ' ' for non-breaking space), or alphanumeric like 'gt' (external or named entity; like ' ' for non-breaking space), or '#' followed by a number (decimal numeric entity; like ' ' for non-breaking space). Character entities referring to the soft-hyphen character (the '­' or '\xad' character; hexadecimal code-point 'ad' [decimal '173']) in URL-accepting attribute values are always replaced with spaces; soft-hyphens in attribute values introduce vulnerabilities in some older versions of the Opera and Mozilla [Firefox] browsers. - - htmLawed (function 'hl_ent()'): - - * Neutralizes entities with multiple leading zeroes or missing semi-colons (potentially dangerous) - - * Lowercases the 'X' (for XML-compliance) and 'A-F' of hexadecimal numeric entities - - * Neutralizes entities referring to characters that are HTML-invalid (see section:- #3.1) - - * Neutralizes entities referring to characters that are HTML-discouraged (code-points, hexadecimally, '7f' to '84', '86' to '9f', and 'fdd0' to 'fddf', or decimally, '127' to '132', '134' to '159', and '64991' to '64976'). Entities referring to the remaining discouraged characters (see section:- #5.1 for a full list) are let through. - - * Neutralizes named entities that are not in the specs. - - * Optionally converts valid HTML-specific named entities except '>', '<', '"', and '&' to decimal numeric ones (hexadecimal if $config["hexdec_entity"] is '2') for generic XML-compliance. For this, '$config["named_entity"]' should be '1'. - - * Optionally converts hexadecimal numeric entities to the more widely supported decimal ones. For this, '$config["hexdec_entity"]' should be '0'. - - * Optionally converts decimal numeric entities to the hexadecimal ones. For this, '$config["hexdec_entity"]' should be '2'. - - `Neutralization` refers to the `entitification` of '&' to '&'. - - *Note*: htmLawed does not convert entities to the actual characters represented by them; one can pass the htmLawed output through PHP's 'html_entity_decode' function:- http://www.php.net/html_entity_decode for that. - - *Note*: If '$config["and_mark"]' is set, and set to a value other than '0', then the '&' characters in the original input are replaced with the control character for the hexadecimal code-point '6' ('\x06'; '&' characters introduced by htmLawed, e.g., after converting '<' to '<', are not affected). This allows one to distinguish, say, an '>' introduced by htmLawed and an '>' put in by the input writer, and can be helpful in further processing of the htmLawed-processed text (e.g., to identify the character sequence 'o(><)o' to generate an emoticon image). When this feature is active, admins should ensure that the htmLawed output is not directly used in web pages or XML documents as the presence of the '\x06' can break documents. Before use in such documents, and preferably before any storage, any remaining '\x06' should be changed back to '&', e.g., with: - - $final = str_replace("\x06", '&', $prelim); - - Also, see section:- #3.9. - - --- 3.3 HTML elements ----------------------------------------------o - - - htmLawed can be configured to allow only certain HTML elements (tags) in the input. Disallowed elements (just tag-content, and not element-content), based on '$config["keep_bad"]', are either `neutralized` (converted to plain text by entitification of '<' and '>') or removed. - - E.g., with only 'em' permitted: - - Input: - - My website is My website is a.com. - - Output, with '$config["keep_bad"]' not '0': - - My website is <a href="">a.com</a>. - - See section:- #3.3.3 for differences between the various non-zero '$config["keep_bad"]' values. - - htmLawed by default permits these 86 elements: - - a, abbr, acronym, address, applet, area, b, bdo, big, blockquote, br, button, caption, center, cite, code, col, colgroup, dd, del, dfn, dir, div, dl, dt, em, embed, fieldset, font, form, h1, h2, h3, h4, h5, h6, hr, i, iframe, img, input, ins, isindex, kbd, label, legend, li, map, menu, noscript, object, ol, optgroup, option, p, param, pre, q, rb, rbc, rp, rt, rtc, ruby, s, samp, script, select, small, span, strike, strong, sub, sup, table, tbody, td, textarea, tfoot, th, thead, tr, tt, u, ul, var - - Except for 'embed' (included because of its wide-spread use) and the Ruby elements ('rb', 'rbc', 'rp', 'rt', 'rtc', 'ruby'; part of XHTML 1.1), these are all the elements in the HTML 4/XHTML 1 specs. Strict-specific specs. exclude 'center', 'dir', 'font', 'isindex', 'menu', 's', 'strike', and 'u'. - - With '$config["safe"] = 1', the default set will exclude 'applet', 'embed', 'iframe', 'object' and 'script'; see section:- #3.6. - - When '$config["elements"]', which specifies allowed elements, is `properly` defined, and neither empty nor set to '0' or '*', the default set is not used. To have elements added to or removed from the default set, a '+/-' notation is used. E.g., '*-script-object' implies that only 'script' and 'object' are disallowed, whereas '*+embed' means that 'noembed' is also allowed. Elements can also be specified as comma separated names. E.g., 'a, b, i' means only 'a', 'b' and 'i' are permitted. In this notation, '*', '+' and '-' have no significance and can actually cause a mis-reading. - - Some more examples of '$config["elements"]' values indicating permitted elements (note that empty spaces are liberally allowed for clarity): - - * 'a, blockquote, code, em, strong' -- only 'a', 'blockquote', 'code', 'em', and 'strong' - * '*-script' -- all excluding 'script' - * '* -center -dir -font -isindex -menu -s -strike -u' -- only XHTML-Strict elements - * '*+noembed-script' -- all including 'noembed' excluding 'script' - - Some mis-usages (and the resulting permitted elements) that can be avoided: - - * '-*' -- none; instead of htmLawed, one might just use, e.g., the 'htmlspecialchars()' PHP function - * '*, -script' -- all except 'script'; admin probably meant '*-script' - * '-*, a, em, strong' -- all; admin probably meant 'a, em, strong' - * '*' -- all; admin need not have set 'elements' - * '*-form+form' -- all; a '+' will always over-ride any '-' - * '*, noembed' -- only 'noembed'; admin probably meant '*+noembed' - * 'a, +b, i' -- only 'a' and 'i'; admin probably meant 'a, b, i' - - Basically, when using the '+/-' notation, commas (',') should not be used, and vice versa, and '*' should be used with the former but not the latter. - - *Note*: Even if an element that is not in the default set is allowed through '$config["elements"]', like 'noembed' in the last example, it will eventually be removed during tag balancing unless such balancing is turned off ('$config["balance"]' set to '0'). Currently, the only way around this, which actually is simple, is to edit the various arrays in the function 'hl_bal()' to accommodate the element and its nesting properties. - - *A possibly second way to specify allowed elements* is to set '$config["parent"]' to an element name that supposedly will hold the input, and to set '$config["balance"]' to '1'. During tag balancing (see section:- #3.3.3), all elements that cannot legally nest inside the parent element will be removed. The parent element is auto-reset to 'div' if '$config["parent"]' is empty, 'body', or an element not in htmLawed's default set of 86 elements. - - `Tag transformation` is possible for improving XHTML-Strict compliance -- most of the deprecated elements are removed or converted to valid XHTML-Strict ones; see section:- #3.3.2. - - -.. 3.3.1 Handling of comments and CDATA sections ................... - - - 'CDATA' sections have the format '"...]]>', and HTML comments, '"... -->'. Neither HTML comments nor 'CDATA' sections can reside inside tags. HTML comments can exist anywhere else, but 'CDATA' sections can exist only where plain text is allowed (e.g., immediately inside 'td' element content but not immediately inside 'tr' element content). - - htmLawed (function 'hl_cmtcd()') handles HTML comments or 'CDATA' sections depending on the values of '$config["comment"]' or '$config["cdata"]'. If '0', such markup is not looked for and the text is processed like plain text. If '1', it is removed completely. If '2', it is preserved but any '<', '>' and '&' inside are changed to entities. If '3', they are left as such. - - Note that for the last two cases, HTML comments and 'CDATA' sections will always be removed from tag content (function 'hl_tag()'). - - Examples: - - Input: - Home - Output ('$config["comment"] = 0, $config["cdata"] = 2'): - <-- home link -->Home - Output ('$config["comment"] = 1, $config["cdata"] = 2'): - Home - Output ('$config["comment"] = 2, $config["cdata"] = 2'): - Home - Output ('$config["comment"] = 2, $config["cdata"] = 1'): - Home - Output ('$config["comment"] = 3, $config["cdata"] = 3'): - Home - - For standard-compliance, comments are given the form '', and any '--' in the content is made '-'. - - When '$config["safe"] = 1', CDATA sections and comments are considered plain text unless '$config["comment"]' or '$config["cdata"]' is explicitly specified; see section:- #3.6. - - -.. 3.3.2 Tag-transformation for better XHTML-Strict ................o - - - If '$config["make_tag_strict"]' is set and not '0', following non-XHTML-Strict elements (and attributes), even if admin-permitted, are mutated as indicated (element content remains intact; function 'hl_tag2()'): - - * applet - (based on '$config["make_tag_strict"]', unchanged ('1') or removed ('2')) - * center - 'div style="text-align: center;"' - * dir - 'ul' - * embed - (based on '$config["make_tag_strict"]', unchanged ('1') or removed ('2')) - * font (face, size, color) - 'span style="font-family: ; font-size: ; color: ;"' (size transformation reference:- http://style.cleverchimp.com/font_size_intervals/altintervals.html) - * isindex - (based on '$config["make_tag_strict"]', unchanged ('1') or removed ('2')) - * menu - 'ul' - * s - 'span style="text-decoration: line-through;"' - * strike - 'span style="text-decoration: line-through;"' - * u - 'span style="text-decoration: underline;"' - - For an element with a pre-existing 'style' attribute value, the extra style properties are appended. - - Example input: - -
        - The PHP software script used for this web-page web-page is htmLawedTest.php, from PHP Labware. -
        - - The output: - -
        - The PHP software script used for this web-page web-page is htmLawedTest.php, from PHP Labware. -
        - - --- 3.3.3 Tag balancing and proper nesting -------------------------o - - - If '$config["balance"]' is set to '1', htmLawed (function 'hl_bal()') checks and corrects the input to have properly balanced tags and legal element content (i.e., any element nesting should be valid, and plain text may be present only in the content of elements that allow them). - - Depending on the value of '$config["keep_bad"]' (see section:- #2.2 and section:- #3.3), illegal content may be removed or neutralized to plain text by converting < and > to entities: - - '0' - remove; this option is available only to maintain Kses-compatibility and should not be used otherwise (see section:- #2.6) - '1' - neutralize tags and keep element content - '2' - remove tags but keep element content - '3' and '4' - like '1' and '2', but keep element content only if text ('pcdata') is valid in parent element as per specs - '5' and '6' - like '3' and '4', but line-breaks, tabs and spaces are left - - Example input (disallowing the 'p' element): - - <*> Pseudo-tags <*> - Non-HTML tag xml -

        - Disallowed tag p -

        -
          Bad
        • OK
        - - The output with '$config["keep_bad"] = 1': - - <*> Pseudo-tags <*> - <xml>Non-HTML tag xml</xml> - <p> - Disallowed tag p - </p> -
          Bad
        • OK
        - - The output with '$config["keep_bad"] = 3': - - <*> Pseudo-tags <*> - <xml>Non-HTML tag xml</xml> - <p> - Disallowed tag p - </p> -
        • OK
        - - The output with '$config["keep_bad"] = 6': - - <*> Pseudo-tags <*> - Non-HTML tag xml - - Disallowed tag p - -
        • OK
        - - An option like '1' is useful, e.g., when a writer previews his submission, whereas one like '3' is useful before content is finalized and made available to all. - - *Note:* In the example above, unlike '<*>', '' gets considered as a tag (even though there is no HTML element named 'xml'). Thus, the 'keep_bad' parameter's value affects '' but not '<*>'. In general, text matching the regular expression pattern '<(/?)([a-zA-Z][a-zA-Z1-6]*)([^>]*?)\s?>' is considered a tag (phrase enclosed by the angled brackets '<' and '>', and starting [with an optional slash preceding] with an alphanumeric word that starts with an alphabet...), and is subjected to the 'keep_bad' value. - - Nesting/content rules for each of the 86 elements in htmLawed's default set (see section:- #3.3) are defined in function 'hl_bal()'. This means that if a non-standard element besides 'embed' is being permitted through '$config["elements"]', the element's tag content will end up getting removed if '$config["balance"]' is set to '1'. - - Plain text and/or certain elements nested inside 'blockquote', 'form', 'map' and 'noscript' need to be in block-level elements. This point is often missed during manual writing of HTML code. htmLawed attempts to address this during balancing. E.g., if the parent container is set as 'form', the input 'B:C:' is converted to '
        B:C:
        '. - - --- 3.3.4 Elements requiring child elements ------------------------o - - - As per specs, the following elements require legal child elements nested inside them: - - blockquote, dir, dl, form, map, menu, noscript, ol, optgroup, rbc, rtc, ruby, select, table, tbody, tfoot, thead, tr, ul - - In some cases, the specs stipulate the number and/or the ordering of the child elements. A 'table' can have 0 or 1 'caption', 'tbody', 'tfoot', and 'thead', but they must be in this order: 'caption', 'thead', 'tfoot', 'tbody'. - - htmLawed currently does not check for conformance to these rules. Note that any non-compliance in this regard will not introduce security vulnerabilities, crash browser applications, or affect the rendering of web-pages. - - With '$config["direct_list_nest"]' set to '1', htmLawed will allow direct nesting of an 'ol' or 'ul' list within another 'ol' or 'ul' without requiring the child list to be within an 'li' of the parent list. While this is not standard-compliant, directly nested lists are rendered properly by almost all browsers. The parameter '$config["direct_list_nest"]' has no effect if tag-balancing (section:- #3.3.3) is turned off. - - --- 3.3.5 Beautify or compact HTML ---------------------------------o - - - By default, htmLawed will neither `beautify` HTML code by formatting it with indentations, etc., nor will it make it compact by removing un-needed white-space.(It does always properly white-space tag content.) - - As per the HTML standards, spaces, tabs and line-breaks in web-pages (except those inside 'pre' elements) are all considered equivalent, and referred to as `white-spaces`. Browser applications are supposed to consider contiguous white-spaces as just a single space, and to disregard white-spaces trailing opening tags or preceding closing tags. This white-space `normalization` allows the use of text/code beautifully formatted with indentations and line-spacings for readability. Such `pretty` HTML can, however, increase the size of web-pages, or make the extraction or scraping of plain text cumbersome. - - With the '$config' parameter 'tidy', htmLawed can be used to beautify or compact the input text. Input with just plain text and no HTML markup is also subject to this. Besides 'pre', the 'script' and 'textarea' elements, CDATA sections, and HTML comments are not subjected to the tidying process. - - To `compact`, use '$config["tidy"] = -1'; single instances or runs of white-spaces are replaced with a single space, and white-spaces trailing and leading open and closing tags, respectively, are removed. - - To `beautify`, '$config["tidy"]' is set as '1', or for customized tidying, as a string like '2s2n'. The 's' or 't' character specifies the use of spaces or tabs for indentation. The first and third characters, any of the digits 0-9, specify the number of spaces or tabs per indentation, and any parental lead spacing (extra indenting of the whole block of input text). The 'r' and 'n' characters are used to specify line-break characters: 'n' for '\n' (Unix/Mac OS X line-breaks), 'rn' or 'nr' for '\r\n' (Windows/DOS line-breaks), or 'r' for '\r'. - - The '$config["tidy"]' value of '1' is equivalent to '2s0n'. Other '$config["tidy"]' values are read loosely: a value of '4' is equivalent to '4s0n'; 't2', to '1t2n'; 's', to '2s0n'; '2TR', to '2t0r'; 'T1', to '1t1n'; 'nr3', to '3s0nr', and so on. Except in the indentations and line-spacings, runs of white-spaces are replaced with a single space during beautification. - - Input formatting using '$config["tidy"]' is not recommended when input text has mixed markup (like HTML + PHP). - - --- 3.4 Attributes ------------------------------------------------oo - - - htmLawed will only permit attributes described in the HTML specs (including deprecated ones). It also permits some attributes for use with the 'embed' element (the non-standard 'embed' element is supported in htmLawed because of its widespread use), and the 'allowfullscreen' (in 'iframe', because of its widespread use), 'bordercolor' (in 'table', 'td' and 'tr', because of its widespread use), and 'xml:space' (valid only in XHTML 1.1) attributes. A list of such 112 attributes and the elements they are allowed in is in section:- #5.2. Using the '$spec' argument, htmLawed can be forced to permit custom, non-standard attributes as well as custom rules for standard attributes (section:- #2.3). - - When '$config["deny_attribute"]' is not set, or set to '0', or empty ('""'), all the 111 attributes are permitted. Otherwise, '$config["deny_attribute"]' can be set as a list of comma-separated names of the denied attributes. 'on*' can be used to refer to the group of potentially dangerous, script-accepting attributes: 'onblur', 'onchange', 'onclick', 'ondblclick', 'onfocus', 'onkeydown', 'onkeypress', 'onkeyup', 'onmousedown', 'onmousemove', 'onmouseout', 'onmouseover', 'onmouseup', 'onreset', 'onselect' and 'onsubmit'. - - Note that attributes specified in '$config["deny_attribute"]' are denied globally, for all elements. To deny attributes for only specific elements, '$spec' (see section:- #2.3) can be used. '$spec' can also be used to element-specifically permit an attribute otherwise denied through '$config["deny_attribute"]'. - - With '$config["safe"] = 1' (section:- #3.6), the 'on*' attributes are automatically disallowed. - - *Note*: To deny all but a few attributes globally, a simpler way to specify '$config["deny_attribute"]' would be to use the notation '* -attribute1 -attribute2 ...'. Thus, a value of '* -title -href' implies that except 'href' and 'title' (where allowed as per standards) all other attributes are to be removed. With this notation, the value for the parameter 'safe' (section:- #3.6) will have no effect on 'deny_attribute'. - - htmLawed (function 'hl_tag()') also: - - * Lower-cases attribute names - * Removes duplicate attributes (last one stays) - * Gives attributes the form 'name="value"' and single-spaces them, removing unnecessary white-spacing - * Provides `required` attributes (see section:- #3.4.1) - * Double-quotes values and escapes any '"' inside them - * Replaces the possibly dangerous soft-hyphen characters (hexadecimal code-point 'ad') in the values with spaces - * Allows custom function to additionally filter/modify attribute values (see section:- #3.4.9) - - -.. 3.4.1 Auto-addition of XHTML-required attributes ................ - - - If indicated attributes for the following elements are found missing, htmLawed (function 'hl_tag()') will add them (with values same as attribute names unless indicated otherwise below): - - * area - alt ('area') - * area, img - src, alt ('image') - * bdo - dir ('ltr') - * form - action - * map - name - * optgroup - label - * param - name - * script - type ('text/javascript') - * textarea - rows ('10'), cols ('50') - - Additionally, with '$config["xml:lang"]' set to '1' or '2', if the 'lang' but not the 'xml:lang' attribute is declared, then the latter is added too, with a value copied from that of 'lang'. This is for better standard-compliance. With '$config["xml:lang"]' set to '2', the 'lang' attribute is removed (XHTML 1.1 specs). - - Note that the 'name' attribute for 'map', invalid in XHTML 1.1, is also transformed if required -- see section:- #3.4.6. - - -.. 3.4.2 Duplicate/invalid 'id' values ............................o - - - If '$config["unique_ids"]' is '1', htmLawed (function 'hl_tag()') removes 'id' attributes with values that are not XHTML-compliant (must begin with a letter and can contain letters, digits, ':', '.', '-' and '_') or duplicate. If '$config["unique_ids"]' is a word, any duplicate but otherwise valid value will be appropriately prefixed with the word to ensure its uniqueness. The word should begin with a letter and should contain only letters, numbers, ':', '.', '_' and '-'. - - Even if multiple inputs need to be filtered (through multiple calls to htmLawed), htmLawed ensures uniqueness of 'id' values as it uses a global variable ('$GLOBALS["hl_Ids"]' array). Further, an admin can restrict the use of certain 'id' values by presetting this variable before htmLawed is called into use. E.g.: - - $GLOBALS['hl_Ids'] = array('top'=>1, 'bottom'=>1, 'myform'=>1); // id values not allowed in input - $processed = htmLawed($text); // filter input - - -.. 3.4.3 URL schemes (protocols) and scripts in attribute values ............o - - - htmLawed edits attributes that take URLs as values if they are found to contain un-permitted schemes. E.g., if the 'afp' scheme is not permitted, then '' becomes '', and if Javascript is not permitted '' becomes ''. - - By default htmLawed permits these schemes in URLs for the 'href' attribute: - - aim, feed, file, ftp, gopher, http, https, irc, mailto, news, nntp, sftp, ssh, telnet - - Also, only 'file', 'http' and 'https' are permitted in attributes whose names start with 'o' (like 'onmouseover'), and in these attributes that accept URLs: - - action, cite, classid, codebase, data, href, longdesc, model, pluginspage, pluginurl, src, style, usemap - - These default sets are used when '$config["schemes"]' is not set (see section:- #2.2). To over-ride the defaults, '$config["schemes"]' is defined as a string of semi-colon-separated sub-strings of type 'attribute: comma-separated schemes'. E.g., 'href: mailto, http, https; onclick: javascript; src: http, https'. For unspecified attributes, 'file', 'http' and 'https' are permitted. This can be changed by passing schemes for '*' in '$config["schemes"]'. E.g., 'href: mailto, http, https; *: https, https'. - - '*' can be put in the list of schemes to permit all protocols. E.g., 'style: *; img: http, https' results in protocols not being checked in 'style' attribute values. However, in such cases, any relative-to-absolute URL conversion, or vice versa, (section:- #3.4.4) is not done. - - Thus, `to allow Javascript`, one can set '$config["schemes"]' as 'href: mailto, http, https; *: http, https, javascript', or 'href: mailto, http, https, javascript; *: http, https, javascript', or '*: *', and so on. - - As a side-note, one may find 'style: *' useful as URLs in 'style' attributes can be specified in a variety of ways, and the patterns that htmLawed uses to identify URLs may mistakenly identify non-URL text. - - '!' can be put in the list of schemes to disallow all protocols as well as `local` URLs. Thus, with 'href: http, style: !', 'CNN' will become 'CNN'. - - *Note*: If URL-accepting attributes other than those listed above are being allowed, then the scheme will not be checked unless the attribute name contains the string 'src' (e.g., 'dynsrc') or starts with 'o' (e.g., 'onbeforecopy'). - - With '$config["safe"] = 1', all URLs are disallowed in the 'style' attribute values. - - -.. 3.4.4 Absolute & relative URLs in attribute values .............o - - - htmLawed can make absolute URLs in attributes like 'href' relative ('$config["abs_url"]' is '-1'), and vice versa ('$config["abs_url"]' is '1'). URLs in scripts are not considered for this, and so are URLs like '#section_6' (fragment), '?name=Tim#show' (starting with query string), and ';var=1?name=Tim#show' (starting with parameters). Further, this requires that '$config["base_url"]' be set properly, with the '://' and a trailing slash ('/'), with no query string, etc. E.g., 'file:///D:/page/', 'https://abc.com/x/y/', or 'http://localhost/demo/' are okay, but 'file:///D:/page/?help=1', 'abc.com/x/y/' and 'http://localhost/demo/index.htm' are not. - - For making absolute URLs relative, only those URLs that have the '$config["base_url"]' string at the beginning are converted. E.g., with '$config["base_url"] = "https://abc.com/x/y/"', 'https://abc.com/x/y/a.gif' and 'https://abc.com/x/y/z/b.gif' become 'a.gif' and 'z/b.gif' respectively, while 'https://abc.com/x/c.gif' is not changed. - - When making relative URLs absolute, only values for scheme, network location (host-name) and path values in the base URL are inherited. See section:- #5.5 for more about the URL specification as per RFC 1808:- http://www.ietf.org/rfc/rfc1808.txt. - - -.. 3.4.5 Lower-cased, standard attribute values ....................o - - - Optionally, for standard-compliance, htmLawed (function 'hl_tag()') lower-cases standard attribute values to give, e.g., 'input type="password"' instead of 'input type="Password"', if '$config["lc_std_val"]' is '1'. Attribute values matching those listed below for any of the elements (plus those for the 'type' attribute of 'button' or 'input') are lower-cased: - - all, baseline, bottom, button, center, char, checkbox, circle, col, colgroup, cols, data, default, file, get, groups, hidden, image, justify, left, ltr, middle, none, object, password, poly, post, preserve, radio, rect, ref, reset, right, row, rowgroup, rows, rtl, submit, text, top - - a, area, bdo, button, col, form, img, input, object, option, optgroup, param, script, select, table, td, tfoot, th, thead, tr, xml:space - - The following `empty` (`minimized`) attributes are always assigned lower-cased values (same as the names): - - checked, compact, declare, defer, disabled, ismap, multiple, nohref, noresize, noshade, nowrap, readonly, selected - - -.. 3.4.6 Transformation of deprecated attributes ..................o - - - If '$config["no_deprecated_attr"]' is '0', then deprecated attributes (see appendix in section:- #5.2) are removed and, in most cases, their values are transformed to CSS style properties and added to the 'style' attributes (function 'hl_tag()'). Except for 'bordercolor' for 'table', 'tr' and 'td', the scores of proprietary attributes that were never part of any cross-browser standard are not supported. - - *Note*: The attribute 'target' for 'a' is allowed even though it is not in XHTML 1.0 specs. This is because of the attribute's wide-spread use and browser-support, and because the attribute is valid in XHTML 1.1 onwards. - - * align - for 'img' with value of 'left' or 'right', becomes, e.g., 'float: left'; for 'div' and 'table' with value 'center', becomes 'margin: auto'; all others become, e.g., 'text-align: right' - - * bgcolor - E.g., 'bgcolor="#ffffff"' becomes 'background-color: #ffffff' - * border - E.g., 'height= "10"' becomes 'height: 10px' - * bordercolor - E.g., 'bordercolor=#999999' becomes 'border-color: #999999;' - * compact - 'font-size: 85%' - * clear - E.g., 'clear="all" becomes 'clear: both' - - * height - E.g., 'height= "10"' becomes 'height: 10px' and 'height="*"' becomes 'height: auto' - - * hspace - E.g., 'hspace="10"' becomes 'margin-left: 10px; margin-right: 10px' - * language - 'language="VBScript"' becomes 'type="text/vbscript"' - * name - E.g., 'name="xx"' becomes 'id="xx"' - * noshade - 'border-style: none; border: 0; background-color: gray; color: gray' - * nowrap - 'white-space: nowrap' - * size - E.g., 'size="10"' becomes 'height: 10px' - * start - removed - * type - E.g., 'type="i"' becomes 'list-style-type: lower-roman' - * value - removed - * vspace - E.g., 'vspace="10"' becomes 'margin-top: 10px; margin-bottom: 10px' - * width - like 'height' - - Example input: - - imageimage -
        -
        - image - - - - - -
        -
        -

        Section

        -

        Para

        -
        1. First item
        -
        -         		-
        1. First item
        -
        -
        - - And the output with '$config["no_deprecated_attr"] = 1': - - imageimage -
        -
        - image - - - - - -
        -
        -

        Section

        -

        Para

        -
        1. First item
        -
        -         		-
        1. First item
        -
        -
        - - For 'lang', deprecated in XHTML 1.1, transformation is taken care of through '$config["xml:lang"]'; see section:- #3.4.1. - - The attribute 'name' is deprecated in 'form', 'iframe', and 'img', and is replaced with 'id' if an 'id' attribute doesn't exist and if the 'name' value is appropriate for 'id'. For such replacements for 'a' and 'map', for which the 'name' attribute is deprecated in XHTML 1.1, '$config["no_deprecated_attr"]' should be set to '2' (when set to '1', for these two elements, the 'name' attribute is retained). - - --- 3.4.7 Anti-spam & 'href' ---------------------------------------o - - - htmLawed (function 'hl_tag()') can check the 'href' attribute values (link addresses) as an anti-spam (email or link spam) measure. - - If '$config["anti_mail_spam"]' is not '0', the '@' of email addresses in 'href' values like 'mailto:a@b.com' is replaced with text specified by '$config["anti_mail_spam"]'. The text should be of a form that makes it clear to others that the address needs to be edited before a mail is sent; e.g., '@' (makes the example address 'a@b.com'). - - For regular links, one can choose to have a 'rel' attribute with 'nofollow' in its value (which tells some search engines to not follow a link). This can discourage link spammers. Additionally, or as an alternative, one can choose to empty the 'href' value altogether (disable the link). - - For use of these options, '$config["anti_link_spam"]' should be set as an array with values 'regex1' and 'regex2', both or one of which can be empty (like 'array("", "regex2")') to indicate that that option is not to be used. Otherwise, 'regex1' or 'regex2' should be PHP- and PCRE-compatible regular expression patterns: 'href' values will be matched against them and those matching the pattern will accordingly be treated. - - Note that the regular expressions should have `delimiters`, and be well-formed and preferably fast. Absolute efficiency/accuracy is often not needed. - - An example, to have a 'rel' attribute with 'nofollow' for all links, and to disable links that do not point to domains 'abc.com' and 'xyz.org': - - $config["anti_link_spam"] = array('`.`', '`://\W*(?!(abc\.com|xyz\.org))`'); - - --- 3.4.8 Inline style properties ----------------------------------o - - - htmLawed can check URL schemes and dynamic expressions (to guard against Javascript, etc., script-based insecurities) in inline CSS style property values in the 'style' attributes. (CSS properties like 'background-image' that accept URLs in their values are noted in section:- #5.3.) Dynamic CSS expressions that allow scripting in the IE browser, and can be a vulnerability, can be removed from property values by setting '$config["css_expression"]' to '1' (default setting). Note that when '$config["css_expression"]' is set to '1', htmLawed will remove '/*' from the 'style' values. - - *Note*: Because of the various ways of representing characters in attribute values (URL-escapement, entitification, etc.), htmLawed might alter the values of the 'style' attribute values, and may even falsely identify dynamic CSS expressions and URL schemes in them. If this is an important issue, checking of URLs and dynamic expressions can be turned off ('$config["schemes"] = "...style:*..."', see section:- #3.4.3, and '$config["css_expression"] = 0'). Alternately, admins can use their own custom function for finer handling of 'style' values through the 'hook_tag' parameter (see section:- #3.4.9). - - It is also possible to have htmLawed let through any 'style' value by setting '$config["style_pass"]' to '1'. - - As such, it is better to set up a CSS file with class declarations, disallow the 'style' attribute, set a '$spec' rule (see section:- #2.3) for 'class' for the 'oneof' or 'match' parameter, and ask writers to make use of the 'class' attribute. - - --- 3.4.9 Hook function for tag content ----------------------------o - - - It is possible to utilize a custom hook function to alter the tag content htmLawed has finalized (i.e., after it has checked/corrected for required attributes, transformed attributes, lower-cased attribute names, etc.). - - When '$config' parameter 'hook_tag' is set to the name of a function, htmLawed (function 'hl_tag()') will pass on the element name, and, in the case of an opening tag, the `finalized` attribute name-value pairs as array elements to the function. The function, after completing a task such as filtering or tag transformation, will typically return an empty string, the full opening tag string like '' (for empty elements like 'img' and 'input', the element-closing slash '/' should also be included), etc. - - Any 'hook_tag' function, since htmLawed version 1.1.11, also receives names of elements in closing tags, such as 'a' in the closing '' tag of the element 'CNN'. Unlike for opening tags, no other value (i.e., the attribute name-value array) is passed to the function since a closing tag contains only element names. Typically, the function will return an empty string or a full closing tag (like ''). - - This is a *powerful functionality* that can be exploited for various objectives: consolidate-and-convert inline 'style' attributes to 'class', convert 'embed' elements to 'object', permit only one 'caption' element in a 'table' element, disallow embedding of certain types of media, *inject HTML*, use CSSTidy:- http://csstidy.sourceforge.net to sanitize 'style' attribute values, etc. - - As an example, the custom hook code below can be used to force a series of specifically ordered 'id' attributes on all elements, and a specific 'param' element inside all 'object' elements: - - function my_tag_function($element, $attribute_array=0){ - - // If second argument is not received, it means a closing tag is being handled - if(is_numeric($attribute_array)){ - return ""; - } - - static $id = 0; - // Remove any duplicate element - if($element == 'param' && isset($attribute_array['allowscriptaccess'])){ - return ''; - } - - $new_element = ''; - - // Force a serialized ID number - $attribute_array['id'] = 'my_'. $id; - ++$id; - - // Inject param for allowscriptaccess - if($element == 'object'){ - $new_element = ''; - ++$id; - } - - $string = ''; - foreach($attribute_array as $k=>$v){ - $string .= " {$k}=\"{$v}\""; - } - - static $empty_elements = array('area'=>1, 'br'=>1, 'col'=>1, 'embed'=>1, 'hr'=>1, 'img'=>1, 'input'=>1, 'isindex'=>1, 'param'=>1); - - return "<{$element}{$string}". (isset($in_array($element, $empty_elements) ? ' /' : ''). '>'. $new_element; - } - - The 'hook_tag' parameter is different from the 'hook' parameter (section:- #3.7). - - Snippets of hook function code developed by others may be available on the htmLawed:- http://www.bioinformatics.org/phplabware/internal_utilities/htmLawed website. - - --- 3.5 Simple configuration directive for most valid XHTML -------oo - - - If '$config["valid_xhtml"]' is set to '1', some relevant '$config' parameters (indicated by '~' in section:- #2.2) are auto-adjusted. This allows one to pass the '$config' argument with a simpler value. If a value for a parameter auto-set through 'valid_xhtml' is still manually provided, then that value will over-ride the auto-set value. - - --- 3.6 Simple configuration directive for most `safe` HTML --------o - - - `Safe` HTML refers to HTML that is restricted to reduce the vulnerability for scripting attacks (such as XSS) based on HTML code which otherwise may still be legal and compliant with the HTML standard specs. When elements such as 'script' and 'object', and attributes such as 'onmouseover' and 'style' are allowed in the input text, an input writer can introduce malevolent HTML code. Note that what is considered 'safe' depends on the nature of the web application and the trust-level accorded to its users. - - htmLawed allows an admin to use '$config["safe"]' to auto-adjust multiple '$config' parameters (such as 'elements' which declares the allowed element-set), which otherwise would have to be manually set. The relevant parameters are indicated by '"' in section:- #2.2). Thus, one can pass the '$config' argument with a simpler value. - - With the value of '1', htmLawed considers 'CDATA' sections and HTML comments as plain text, and prohibits the 'applet', 'embed', 'iframe', 'object' and 'script' elements, and the 'on*' attributes like 'onclick'. ( There are '$config' parameters like 'css_expression' that are not affected by the value set for 'safe' but whose default values still contribute towards a more `safe` output.) Further, URLs with schemes (see section:- #3.4.3) are neutralized so that, e.g., 'style="moz-binding:url(http://danger)"' becomes 'style="moz-binding:url(denied:http://danger)"'. - - Admins, however, may still want to completely deny the 'style' attribute, e.g., with code like - - $processed = htmLawed($text, array('safe'=>1, 'deny_attribute'=>'style')); - - Permitting the 'style' attribute brings in risks of `click-jacking`, etc. CSS property values can render a page non-functional or be used to deface it. Except for URLs, dynamic expressions, and some other things, htmLawed does not completely check 'style' values. It does provide ways for the code-developer implementing htmLawed to do such checks through the '$spec' argument, and through the 'hook_tag' parameter (see section:- #3.4.8 for more). Disallowing style completely and relying on CSS classes and stylesheet files is recommended. - - If a value for a parameter auto-set through 'safe' is still manually provided, then that value can over-ride the auto-set value. E.g., with '$config["safe"] = 1' and '$config["elements"] = "*+script"', 'script', but not 'applet', is allowed. - - A page illustrating the efficacy of htmLawed's anti-XSS abilities with 'safe' set to '1' against XSS vectors listed by RSnake:- http://ha.ckers.org/xss.html may be available here:- http://www.bioinformatics.org/phplabware/internal_utilities/htmLawed/rsnake/RSnakeXSSTest.htm. - - --- 3.7 Using a hook function --------------------------------------o - - - If '$config["hook"]' is not set to '0', then htmLawed will allow preliminarily processed input to be altered by a hook function named by '$config["hook"]' before starting the main work (but after handling of characters, entities, HTML comments and 'CDATA' sections -- see code for function 'htmLawed()'). - - The hook function also allows one to alter the `finalized` values of '$config' and '$spec'. - - Note that the 'hook' parameter is different from the 'hook_tag' parameter (section:- #3.4.9). - - Snippets of hook function code developed by others may be available on the htmLawed:- http://www.bioinformatics.org/phplabware/internal_utilities/htmLawed website. - - --- 3.8 Obtaining `finalized` parameter values ---------------------o - - - htmLawed can assign the `finalized` '$config' and '$spec' values to a variable named by '$config["show_setting"]'. The variable, made global by htmLawed, is set as an array with three keys: 'config', with the '$config' value, 'spec', with the '$spec' value, and 'time', with a value that is the Unix time (the output of PHP's 'microtime()' function) when the value was assigned. Admins should use a PHP-compliant variable name (e.g., one that does not begin with a numerical digit) that does not conflict with variable names in their non-htmLawed code. - - The values, which are also post-hook function (if any), can be used to auto-generate information (on, e.g., the elements that are permitted) for input writers. - - --- 3.9 Retaining non-HTML tags in input with mixed markup ---------o - - - htmLawed does not remove certain characters that, though invalid, are nevertheless `discouraged` in HTML documents as per the specifications (see section:- #5.1). This can be utilized to deal with input that contains mixed markup. Input that may have HTML markup as well as some other markup that is based on the '<', '>' and '&' characters is considered to have mixed markup. The non-HTML markup can be rather proprietary (like markup for emoticons/smileys), or standard (like MathML or SVG). Or it can be programming code meant for execution/evaluation (such as embedded PHP code). - - To deal with such mixed markup, the input text can be pre-processed to hide the non-HTML markup by specifically replacing the '<', '>' and '&' characters with some of the HTML-discouraged characters (see section:- #3.1.2). Post-htmLawed processing, the replacements are reverted. - - An example (mixed HTML and PHP code in input text): - - $text = preg_replace('`<\?php(.+?)\?>`sm', "\x83?php\\1?\x84", $text); - $processed = htmLawed($text); - $processed = preg_replace('`\x83\?php(.+?)\?\x84`sm', '', $processed); - - This code will not work if '$config["clean_ms_char"]' is set to '1' (section:- #3.1), in which case one should instead deploy a hook function (section:- #3.7). (htmLawed internally uses certain control characters, code-points '1' to '7', and use of these characters as markers in the logic of hook functions may cause issues.) - - Admins may also be able to use '$config["and_mark"]' to deal with such mixed markup; see section:- #3.2. - - -== 4 Other =======================================================oo - - --- 4.1 Support ----------------------------------------------------- - - - A careful reading of this documentation may provide an answer. - - Software updates and forum-based community-support may be found at http://www.bioinformatics.org/phplabware/internal_utilities/htmLawed. For general PHP issues (not htmLawed-specific), support may be found through internet searches and at http://php.net. - - --- 4.2 Known issues -----------------------------------------------o - - - See section:- #2.8. - - --- 4.3 Change-log -------------------------------------------------o - - - (The release date for the downloadable package of files containing documentation, demo script, test-cases, etc., besides the 'htmLawed.php' file, may be updated without a change-log entry if the secondary files, but not htmLawed per se, are revised.) - - `Version number - Release date. Notes` - - - 1.1.20 - 9 June 2015. Fix for a potential security vulnerability arising from unescaped double-quote character in single-quoted attribute value of some deprecated elements when tag transformation is enabled; recognition for non-(HTML4) standard 'allowfullscreen' attribute of 'iframe.' - - 1.1.19 - 19 January 2015. Fix for a bug in cleaning of soft-hyphens in URL values, etc. - - 1.1.18 - 2 August 2014. Fix for a potential security vulnerability arising from specially encoded text with serial opening tags - - 1.1.17 - 11 March 2014. Removed use of PHP function preg_replace with 'e' modifier for compatibility with PHP 5.5 - - 1.1.16 - 29 August 2013. Fix for a potential security vulnerability arising from specially encoded space characters in URL schemes/protocols - - 1.1.15 - 11 August 2013. Improved tidying/prettifying functionality - - 1.1.14 - 8 August 2012. Fix for possible segmental loss of incremental indentation during 'tidying' when 'balance' is disabled; fix for non-effectuation under some circumstances of a corrective behavior to preserve plain text within elements like 'blockquote'. - - 1.1.13 - 22 July 2012. Added feature allowing use of custom, non-standard attributes or custom rules for standard attributes - - 1.1.12 - 5 July 2012. Fix for a bug in identifying an unquoted value of the 'face' attribute - - 1.1.11 - 5 June 2012. Fix for possible problem with handling of multi-byte characters in attribute values in an mbstring.func_overload environment. '$config["hook_tag"]', if specified, now receives names of elements in closing tags. - - 1.1.10 - 22 October 2011. Fix for a bug in the 'tidy' functionality that caused the entire input to be replaced with a single space; new parameter, '$config["direct_list_nest"]' to allow direct descendence of a list in a list. (5 April 2012. Dual licensing from LGPLv3 to LGPLv3 and GPLv2+.) - - 1.1.9.5 - 6 July 2011. Minor correction of a rule for nesting of 'li' within 'dir' - - 1.1.9.4 - 3 July 2010. Parameter 'schemes' now accepts '!' so any URL, even a local one, can be `denied`. An issue in which a second URL value in 'style' properties was not checked was fixed. - - 1.1.9.3 - 17 May 2010. Checks for correct nesting of 'param' - - 1.1.9.2 - 26 April 2010. Minor fix regarding rendering of denied URL schemes - - 1.1.9.1 - 26 February 2010. htmLawed now uses the LGPL version 3 license; support for 'flashvars' attribute for 'embed' - - 1.1.9 - 22 December 2009. Soft-hyphens are now removed only from URL-accepting attribute values - - 1.1.8.1 - 16 July 2009. Minor code-change to fix a PHP error notice - - 1.1.8 - 23 April 2009. Parameter 'deny_attribute' now accepts the wild-card '*', making it simpler to specify its value when all but a few attributes are being denied; fixed a bug in interpreting '$spec' - - 1.1.7 - 11-12 March 2009. Attributes globally denied through 'deny_attribute' can be allowed element-specifically through '$spec'; '$config["style_pass"]' allowing letting through any 'style' value introduced; altered logic to catch certain types of dynamic crafted CSS expressions - - 1.1.3-6 - 28-31 January - 4 February 2009. Altered logic to catch certain types of dynamic crafted CSS expressions - - 1.1.2 - 22 January 2009. Fixed bug in parsing of 'font' attributes during tag transformation - - 1.1.1 - 27 September 2008. Better nesting correction when omitable closing tags are absent - - 1.1 - 29 June 2008. '$config["hook_tag"]' and '$config["tidy"]' introduced for custom tag/attribute check/modification/injection and output compaction/beautification; fixed a regex-in-$spec parsing bug - - 1.0.9 - 11 June 2008. Fix for a bug in checks for invalid HTML code-point entities - - 1.0.8 - 15 May 2008. Permit 'bordercolor' attribute for 'table', 'td' and 'tr' - - 1.0.7 - 1 May 2008. Support for 'wmode' attribute for 'embed'; '$config["show_setting"]' introduced; improved '$config["elements"]' evaluation - - 1.0.6 - 20 April 2008. '$config["and_mark"]' introduced - - 1.0.5 - 12 March 2008. 'style' URL schemes essentially disallowed when $config 'safe' is on; improved regex for CSS expression search - - 1.0.4 - 10 March 2008. Improved corrections for 'blockquote', 'form', 'map' and 'noscript' - - 1.0.3 - 3 March 2008. Character entities for soft-hyphens are now replaced with spaces (instead of being removed); fix for a bug allowing 'td' directly inside 'table'; '$config["safe"]' introduced - - 1.0.2 - 13 February 2008. Improved implementation of '$config["keep_bad"]' - - 1.0.1 - 7 November 2007. Improved regex for identifying URLs, protocols and dynamic expressions ('hl_tag()' and 'hl_prot()'); no error display with 'hl_regex()' - - 1.0 - 2 November 2007. First release - - --- 4.4 Testing ----------------------------------------------------o - - - To test htmLawed using a form interface, a demo:- htmLawedTest.php web-page is provided with the htmLawed distribution ('htmLawed.php' and 'htmLawedTest.php' should be in the same directory on the web-server). A file with test-cases:- htmLawed_TESTCASE.txt is also provided. - - --- 4.5 Upgrade, & old versions ------------------------------------o - - - Upgrading is as simple as replacing the previous version of 'htmLawed.php' (assuming it was not modified for customized features). As htmLawed output is almost always used in static documents, upgrading should not affect old, finalized content. - - *Important* The following upgrades may affect the functionality of a specific htmLawed installation: - - (1) From version 1.1-1.1.10 to 1.1.11 (or later), if a 'hook_tag' function is in use: In version 1.1.11, elements in closing tags (and not just the opening tags) are also passed to the function. There are no attribute names/values to pass, so a 'hook_tag' function receives only the element name. The 'hook_tag' function therefore may have to be edited. See section:- #3.4.9. - - Old versions of htmLawed may be available online. E.g., for version 1.0, check http://www.bioinformatics.org/phplabware/downloads/htmLawed1.zip, for 1.1.1, htmLawed111.zip, and for 1.1.10, htmLawed1110.zip. - - --- 4.6 Comparison with 'HTMLPurifier' -----------------------------o - - - The HTMLPurifier PHP library by Edward Yang is a very good HTML filtering script that uses object oriented PHP code. Compared to htmLawed, it (as of year 2010): - - * does not support PHP versions older than 5.0 (HTMLPurifier dropped PHP 4 support after version 2) - - * is 15-20 times bigger (scores of files totalling more than 750 kb) - - * consumes 10-15 times more RAM memory (just including the HTMLPurifier files without calling the filter requires a few MBs of memory) - - * is expectedly slower - - * does not allow admins to fully allow all valid HTML (because of incomplete HTML support, it always considers elements like 'script' illegal) - - * lacks many of the extra features of htmLawed (like entity conversions and code compaction/beautification) - - * has poor documentation - - However, HTMLPurifier has finer checks for character encodings and attribute values, and can log warnings and errors. Visit the HTMLPurifier website:- http://htmlpurifier.org for updated information. - - --- 4.7 Use through application plug-ins/modules -------------------o - - - Plug-ins/modules to implement htmLawed in applications such as Drupal and DokuWiki may have been developed. Please check the application websites and the forum on the htmLawed site:- http://www.bioinformatics.org/phplabware/internal_utilities/htmLawed. - - --- 4.8 Use in non-PHP applications --------------------------------o - - - Non-PHP applications written in Python, Ruby, etc., may be able to use htmLawed through system calls to the PHP engine. Such code may have been documented on the internet. Also check the forum on the htmLawed site:- http://www.bioinformatics.org/phplabware/internal_utilities/htmLawed. - - --- 4.9 Donate -----------------------------------------------------o - - - A donation in any currency and amount to appreciate or support this software can be sent by PayPal:- http://paypal.com to this email address: drpatnaik at yahoo dot com. - - --- 4.10 Acknowledgements ------------------------------------------o - - - Nicholas Alipaz, Bryan Blakey, Pádraic Brady, Dac Chartrand, Ulf Harnhammer, Gareth Heyes, Hakre, Klaus Leithoff, Lukasz Pilorz, Shelley Powers, Psych0tr1a, Lincoln Russell, Tomas Sykorka, Harro Verton, Edward Yang, and many anonymous users. - - Thank you! - - -== 5 Appendices ==================================================oo - - --- 5.1 Characters discouraged in XHTML ----------------------------- - - - Characters represented by the following hexadecimal code-points are `not` invalid, even though some validators may issue messages stating otherwise. - - '7f' to '84', '86' to '9f', 'fdd0' to 'fddf', '1fffe', '1ffff', '2fffe', '2ffff', '3fffe', '3ffff', '4fffe', '4ffff', '5fffe', '5ffff', '6fffe', '6ffff', '7fffe', '7ffff', '8fffe', '8ffff', '9fffe', '9ffff', 'afffe', 'affff', 'bfffe', 'bffff', 'cfffe', 'cffff', 'dfffe', 'dffff', 'efffe', 'effff', 'ffffe', 'fffff', '10fffe' and '10ffff' - - --- 5.2 Valid attribute-element combinations -----------------------o - - - Valid attribute-element combinations as per W3C:- http://www.w3c.org specs. - - * includes deprecated attributes (marked '^'), attributes for the non-standard 'embed' element (marked '*'), and the non-standard 'allowfullscreen' and 'bordercolor' (marked '~') - * only non-frameset, HTML body elements - * 'name' for 'a' and 'map', and 'lang' are invalid in XHTML 1.1 - * 'target' is valid for 'a' in XHTML 1.1 and higher - * 'xml:space' is only for XHTML 1.1 - - abbr - td, th - accept - form, input - accept-charset - form - accesskey - a, area, button, input, label, legend, textarea - action - form - align - caption^, embed, applet, iframe, img^, input^, object^, legend^, table^, hr^, div^, h1^, h2^, h3^, h4^, h5^, h6^, p^, col, colgroup, tbody, td, tfoot, th, thead, tr - allowfullscreen - iframe~ - alt - applet, area, img, input - archive - applet, object - axis - td, th - bgcolor - embed, table^, tr^, td^, th^ - border - table, img^, object^ - bordercolor~ - table, td, tr - cellpadding - table - cellspacing - table - char - col, colgroup, tbody, td, tfoot, th, thead, tr - charoff - col, colgroup, tbody, td, tfoot, th, thead, tr - charset - a, script - checked - input - cite - blockquote, q, del, ins - classid - object - clear - br^ - code - applet - codebase - object, applet - codetype - object - color - font - cols - textarea - colspan - td, th - compact - dir, dl^, menu, ol^, ul^ - coords - area, a - data - object - datetime - del, ins - declare - object - defer - script - dir - bdo - disabled - button, input, optgroup, option, select, textarea - enctype - form - face - font - flashvars* - embed - for - label - frame - table - frameborder - iframe - headers - td, th - height - embed, iframe, td^, th^, img, object, applet - href - a, area - hreflang - a - hspace - applet, img^, object^ - ismap - img, input - label - option, optgroup - language - script^ - longdesc - img, iframe - marginheight - iframe - marginwidth - iframe - maxlength - input - method - form - model* - embed - multiple - select - name - button, embed, textarea, applet^, select, form^, iframe^, img^, a^, input, object, map^, param - nohref - area - noshade - hr^ - nowrap - td^, th^ - object - applet - onblur - a, area, button, input, label, select, textarea - onchange - input, select, textarea - onfocus - a, area, button, input, label, select, textarea - onreset - form - onselect - input, textarea - onsubmit - form - pluginspage* - embed - pluginurl* - embed - prompt - isindex - readonly - textarea, input - rel - a - rev - a - rows - textarea - rowspan - td, th - rules - table - scope - td, th - scrolling - iframe - selected - option - shape - area, a - size - hr^, font, input, select - span - col, colgroup - src - embed, script, input, iframe, img - standby - object - start - ol^ - summary - table - tabindex - a, area, button, input, object, select, textarea - target - a^, area, form - type - a, embed, object, param, script, input, li^, ol^, ul^, button - usemap - img, input, object - valign - col, colgroup, tbody, td, tfoot, th, thead, tr - value - input, option, param, button, li^ - valuetype - param - vspace - applet, img^, object^ - width - embed, hr^, iframe, img, object, table, td^, th^, applet, col, colgroup, pre^ - wmode - embed - xml:space - pre, script, style - - These are allowed in all but the shown elements: - - class - param, script - dir - applet, bdo, br, iframe, param, script - id - script - lang - applet, br, iframe, param, script - onclick - applet, bdo, br, font, iframe, isindex, param, script - ondblclick - applet, bdo, br, font, iframe, isindex, param, script - onkeydown - applet, bdo, br, font, iframe, isindex, param, script - onkeypress - applet, bdo, br, font, iframe, isindex, param, script - onkeyup - applet, bdo, br, font, iframe, isindex, param, script - onmousedown - applet, bdo, br, font, iframe, isindex, param, script - onmousemove - applet, bdo, br, font, iframe, isindex, param, script - onmouseout - applet, bdo, br, font, iframe, isindex, param, script - onmouseover - applet, bdo, br, font, iframe, isindex, param, script - onmouseup - applet, bdo, br, font, iframe, isindex, param, script - style - param, script - title - param, script - xml:lang - applet, br, iframe, param, script - - --- 5.3 CSS 2.1 properties accepting URLs ------------------------o - - - background - background-image - content - cue-after - cue-before - cursor - list-style - list-style-image - play-during - - --- 5.4 Microsoft Windows 1252 character replacements --------------o - - - Key: 'd' double, 'l' left, 'q' quote, 'r' right, 's.' single - - Code-point (decimal) - hexadecimal value - replacement entity - represented character - - 127 - 7f - (removed) - (not used) - 128 - 80 - € - euro - 129 - 81 - (removed) - (not used) - 130 - 82 - ‚ - baseline s. q - 131 - 83 - ƒ - florin - 132 - 84 - „ - baseline d q - 133 - 85 - … - ellipsis - 134 - 86 - † - dagger - 135 - 87 - ‡ - d dagger - 136 - 88 - ˆ - circumflex accent - 137 - 89 - ‰ - permile - 138 - 8a - Š - S Hacek - 139 - 8b - ‹ - l s. guillemet - 140 - 8c - Œ - OE ligature - 141 - 8d - (removed) - (not used) - 142 - 8e - Ž - Z dieresis - 143 - 8f - (removed) - (not used) - 144 - 90 - (removed) - (not used) - 145 - 91 - ‘ - l s. q - 146 - 92 - ’ - r s. q - 147 - 93 - “ - l d q - 148 - 94 - ” - r d q - 149 - 95 - • - bullet - 150 - 96 - – - en dash - 151 - 97 - — - em dash - 152 - 98 - ˜ - tilde accent - 153 - 99 - ™ - trademark - 154 - 9a - š - s Hacek - 155 - 9b - › - r s. guillemet - 156 - 9c - œ - oe ligature - 157 - 9d - (removed) - (not used) - 158 - 9e - ž - z dieresis - 159 - 9f - Ÿ - Y dieresis - - --- 5.5 URL format -------------------------------------------------o - - - An `absolute` URL has a 'protocol' or 'scheme', a 'network location' or 'hostname', and, optional 'path', 'parameters', 'query' and 'fragment' segments. Thus, an absolute URL has this generic structure: - - (scheme) : (//network location) /(path) ;(parameters) ?(query) #(fragment) - - The schemes can only contain letters, digits, '+', '.' and '-'. Hostname is the portion after the '//' and up to the first '/' (if any; else, up to the end) when ':' is followed by a '//' (e.g., 'abc.com' in 'ftp://abc.com/def'); otherwise, it consists of everything after the ':' (e.g., 'def@abc.com' in mailto:def@abc.com'). - - `Relative` URLs do not have explicit schemes and network locations; such values are inherited from a `base` URL. - - --- 5.6 Brief on htmLawed code -------------------------------------o - - - Much of the code's logic and reasoning can be understood from the documentation above. - - The *output* of htmLawed is a text string containing the processed input. There is no custom error tracking. - - *Function arguments* for htmLawed are: - - * '$in' - first argument; a text string; the *input text* to be processed. Any extraneous slashes added by PHP when `magic quotes` are enabled should be removed beforehand using PHP's 'stripslashes()' function. - - * '$config' - second argument; an associative array; optional; named '$C' within htmLawed code. The array has keys with names like 'balance' and 'keep_bad', and the values, which can be boolean, string, or array, depending on the key, are read to accordingly set the *configurable parameters* (indicated by the keys). All configurable parameters receive some default value if the value to be used is not specified by the user through '$config'. `Finalized` '$config' is thus a filtered and possibly larger array. - - * '$spec' - third argument; a text string; optional. The string has rules, written in an htmLawed-designated format, *specifying* element-specific attribute and attribute value restrictions. Function 'hl_spec()' is used to convert the string to an associative-array, named '$S' within htmLawed code, for internal use. `Finalized` '$spec' is thus an array. - - `Finalized` '$config' and '$spec' are made *global variables* while htmLawed is at work. Values of any pre-existing global variables with same names are noted, and their values are restored after htmLawed finishes processing the input (to capture the `finalized` values, the 'show_settings' parameter of '$config' should be used). Depending on '$config', another global variable 'hl_Ids', to track 'id' attribute values for uniqueness, may be set. Unlike the other two variables, this one is not reset (or unset) post-processing. - - Except for the main function 'htmLawed()' and the functions 'kses()' and 'kses_hook()', htmLawed's functions are *name-spaced* using the 'hl_' prefix. The *functions* and their roles are: - - * 'hl_attrval' - checking attribute values against $spec - * 'hl_bal' - tag balancing - * 'hl_cmtcd' - handling CDATA sections and HTML comments - * 'hl_ent' - entity handling - * 'hl_prot' - checking a URL scheme/protocol - * 'hl_regex' - checking syntax of a regular expression - * 'hl_spec' - converting user-supplied $spec value to one used by htmLawed internally - * 'hl_tag' - handling tags - * 'hl_tag2' - transforming tags - * 'hl_tidy' - compact/beautify HTML - * 'hl_version' - reporting htmLawed version - * 'htmLawed' - main function - * 'kses' - main function of 'kses' - * 'kses_hook' - hook function of 'kses' - - The last two are for compatibility with pre-existing code using the 'kses' script. htmLawed's 'kses()' basically passes on the filtering task to 'htmLawed()' function after deciphering '$config' and '$spec' from the argument values supplied to it. 'kses_hook()' is an empty function and is meant for being filled with custom code if the 'kses' script users were using one. - - 'htmLawed()' finalizes '$spec' (with the help of 'hl_spec()') and '$config', and globalizes them. Finalization of '$config' involves setting default values if an inappropriate or invalid one is supplied. This includes calling 'hl_regex()' to check well-formedness of regular expression patterns if such expressions are user-supplied through '$config'. 'htmLawed()' then removes invalid characters like nulls and 'x01' and appropriately handles entities using 'hl_ent()'. HTML comments and CDATA sections are identified and treated as per '$config' with the help of 'hl_cmtcd()'. When retained, the '<' and '>' characters identifying them, and the '<', '>' and '&' characters inside them, are replaced with control characters (code-points '1' to '5') till any tag balancing is completed. - - After this `initial processing` 'htmLawed()' identifies tags using regex and processes them with the help of 'hl_tag()' -- a large function that analyzes tag content, filtering it as per HTML standards, '$config' and '$spec'. Among other things, 'hl_tag()' transforms deprecated elements using 'hl_tag2()', removes attributes from closing tags, checks attribute values as per '$spec' rules using 'hl_attrval()', and checks URL protocols using 'hl_prot()'. 'htmLawed()' performs tag balancing and nesting checks with a call to 'hl_bal()', and optionally compacts/beautifies the output with proper white-spacing with a call to 'hl_tidy()'. The latter temporarily replaces white-space, and '<', '>' and '&' characters inside 'pre', 'script' and 'textarea' elements, and HTML comments and CDATA sections with control characters (code-points '1' to '5', and '7'). - - htmLawed permits the use of custom code or *hook functions* at two stages. The first, called inside 'htmLawed()', allows the input text as well as the finalized '$config' and '$spec' values to be altered right after the initial processing (see section:- #3.7). The second is called by 'hl_tag()' once the tag content is finalized (see section:- #3.4.9). - - The functionality of htmLawed is dictated by the external HTML standard. It is thus coded for a clear-cut objective with not much concern for tweakability. The code is only minimally annotated with comments -- it is not meant to instruct; PHP developers familiar with the HTML specifications will see the logic, and others can always refer to the htmLawed documentation. The compact structuring of the statements is meant to aid a quick grasp of the logic. - -___________________________________________________________________oo - - -@@description: htmLawed PHP software is a free, open-source, customizable HTML input purifier and filter -@@encoding: utf-8 -@@keywords: htmLawed, HTM, HTML, HTML Tidy, converter, filter, formatter, purifier, sanitizer, XSS, input, PHP, software, code, script, security, cross-site scripting, hack, sanitize, remove, standards, tags, attributes, elements -@@language: en -@@title: htmLawed documentation diff --git a/extlib/htmLawed/htmLawed_TESTCASE.txt b/extlib/htmLawed/htmLawed_TESTCASE.txt deleted file mode 100755 index fc4251873a..0000000000 --- a/extlib/htmLawed/htmLawed_TESTCASE.txt +++ /dev/null @@ -1,453 +0,0 @@ -/* -htmLawed_TESTCASE.txt, 9 June 2015 -htmLawed 1.1.20, 9 June 2015 -Copyright Santosh Patnaik -Dual licensed with LGPL 3 and GPL 2+ -A PHP Labware internal utility - http://www.bioinformatics.org/phplabware/internal_utilities/htmLawed -*/ - -This file has UTF-8-encoded text with both correct and incorrect/malformed HTML/XHTML code snippets to test htmLawed (test cases/samples). The entire text may also be used as a unit. - -************************************************ -when viewing this file in a web browser, set the -character encoding to Unicode/UTF-8 -************************************************ - ---------------------- start -------------------- - -Try different $config and $spec values. Some text even when filtered in will not be displayed in a rendered web-page
        - -
        Attributes
        - -Xml:lang:, ,
        -Standard, predefined value, or empty attribute: , ,
        -Required: , image
        -Quote & space variation: a, a, a
        -Invalid: a
        -Duplicated: a
        -Deprecated: a,

        -Casing:
        -Custom: image
        -Data-*: a
        -Admin-restricted?: - -
        Attribute values
        - -Duplicate ID value:, ,
        -(try 'my_' for prefix)
        -Double-quotes in value:, ,
        -(try filter for CSS expression)
        -CSS expression:

        -Other: ,
        -(try 'maxlen', 'maxval', etc., for 'input' in '$spec') - -
        Blockquotes
        - -
        abc

        -
        abc
        def

        -
        abc
        def

        -
        abc
        def
        ghi

        -abc
        def
        ghi
        -
        QQQ
        x

        -
        x
        QQQ

        -
        x
        QQQ
        x

        -
        x
        QQQ

        x


        -
        -(try with blockquote parent) - -
        CDATA sections
        - -Special characters inside: ]]>, 3.5, & 4 > 4 ]]>
        -Normal: , CDATA follows:
        -Malformed: , < ![CDATA check ]]>, , < ![CDATA check ] ]>
        -Invalid: >CDATA in tag content,
        text not allowed
        - -
        Complex-1: deprecated elements
        - -
        -The PHP software script used for this web-page webpage is htmLawedTest.php, from PHP Labware. -
        - -
        Complex-2: deprecated attributes
        - -aa -
        -
        -image - - - - - -
        -
        -

        Section

        -

        Para

        -
        1. First item
        -
        -         		-
        1. First item
        -
        -
        - -
        Complex-3: embed, object, area
        - -
        - -
        - - -

        navigate the site: 1 | 3 | 4

        - -         - -value - - - - - - - - -
        Complex-4: nested and other tables
        - -
        Cell
        Cell
        Cell
        Cell Cell Cell
        Cell
        Cell Cell Cell

        -PCDATA wrong: Well
        Hello

        -Missing tr:
        Well

        - -
        Complex-5: pseudo, disallowed or non-HTML tags
        - -(Try different 'keep_bad' values) -<*> Pseudotags <*> -Non-HTML tag xml -

        -Disallowed tag p -

        -
          Bad
        • OK
        - -
        Elements
        - -Unbalanced: check
        -Non-XHTML:

        -Malformed: < a href="">, , , , < /a>, < a href="">, a, a,
        -Invalid: a
        -Empty: a, a, atext
        -Content invalid: 12
        -Content invalid?:

        (try setting 'form' as parent)
        -Casing:
        -Check for tidy:
    hi
    - -
    Entities
    - -Special: & 3 < 2 & 5>4 and j >i >a & ia
    -Padding: B B f f  
    -Malformed: & #x27;, &x27;, ' &TILDE;, &tilde
    -Invalid: , �, , �, ￿, &bad;
    -Discouraged characters: , „, ﷠, 􏿾
    -Context: '>', <?
    -Casing: ', ', &TILDE;, ˜ -
    -(also check named-to-numeric and hexdec-to-decimal, and vice versa, conversions) - -
    Format
    - -Valid but ill-formatted: text -text - text text
    p r e
    - text text
    -text none text -text none t e x t -     text none t e x t - -text none t e x t - -
    - 
    p r e
    - 
    -				pre
-
    -
    -
    Cell
    Cell
    Cell
    CellCellCell
    Cell
    CellCellCell
    -(try to compact or beautify) - -
    Forms
    - -(note nesting of 'form', missing required attributes, etc.)
    -
    - -
    pl
    - h - -

    -


    -
    B:C:

    -(try each of these lines separately)
    -
    what
    -what -(try with container as div and as form)
    -c a b - -
    HTML comments (also CDATA)
    - -Script inside:
    -Special characters inside: , , , c
    -Normal: , , comment:,
    text not allowed

    -Malformed: , < ![CDATA check ]]>, < ![CDATA check ] ]>
    -Invalid:     >comment in tag content, - -
    HTML5
    - -figure and figcaption:
    picture
    Caption for the awesome picture
    -article:

    A

    B

    C

    E

    F

    G

    -meter:

    Heat 150.

    -datalist: - -
    Ins-Del
    - -(depending on context, these elements can be of either block or inline type)
    -

    block


    -

    d


    -

    d

    d

    d
     - -
    Lists
    - -Invalid character data:
    • (item
      • )

    -Definition list:
    a
    bad
    first one
    b
    second

    -Definition list, close-tags omitted:
    a
    bad
    first one
    b
    second

    -Definition lists, nested:
    -
    T1
    -
    D1
    -
    T2
    -
    D2
    t1
    d1
    t2
    d2
    -
    T3
    -
    D3
    -
    T4
    -
    D4
    t1
    d1
    -

    -Definition lists, nested, close-tags omitted:
    -
    T1 -
    D1
    -
    T2
    -
    D2
    t1
    d1
    t2
    d2
    -
    T3 -
    D3 -
    T4 -
    D4
    t1
    d1
    -

    -Nested:
      -
    • l1
      • -
    • l2
      1. lo1
      2. lo2
      • -
    • l3
      • -
    • l4
      1. lo3
      2. lo4
        1. lo5
      • -

    -Nested, directly:
      -
    • l1
      • -
        l2
      -
    • l3
      • -

    -Nested, close-tags omitted:
      -
    • l1
      • -
    • l2
      1. lo1
      2. lo2
      -
    • l3 -
    • l4
      1. lo3
      2. lo4
        1. lo5
      -

    -Complex: -
    1. -
      -
    -Menu:
  • - -
    • -     - -
    Microdata
    - -
    -I am X but people call me Y. -Find me at -
    - -
    Microsoft Word
    - -Proprietary tag:

     


    -XML declaration:
    -XML-invalid character code-point (may not replicate):

    “Where is he?” asked both Mary – the one so lovely – and Jane.

    - -
    Nesting
    - -Block or inline a:

    text

    hi

    - -
    Non-English text-1
    - -Inscrieţi-vă acum la a Zecea Conferinţă Internaţională
    -გთხოვთ ახლავე გაიაროთ რეგისტრაცია
    -večjezično računalništvo
    -อ.อ่าง
    -Зарегистрируйтесь сейчас -на Десятую Международную Конференцию по
    -(this file should have utf-8 encoding; some characters may not be displayed because of missing fonts, etc.) - -
    Non-English text-2: entities
    - -用统一码
    -გთხოვთ
    -Inscreva-se agora para a Décima Conferência Internacional Sobre O Unicode, realizada entre os dias 10 e 12 de março de 1997 em Mainz -na Alemanha. - -
    Ruby
    - -(need compatible browser)
    - - - 斎 - 藤 - 信 - 男 - - - さい - とう - のぶ - お - - - W3C Associate Chairman - -
    - - WWW - (World Wide Web) -
    - - A - (aaa) - - - -
    Tables
    - -Omitted closing tags: -- - -
    h1c1h1c2 -
    r1c1r1c2 -
    r2c1r2c2 -

    -Nested, omitted closing tags: -- - -
    h1c1h1c2 -
    r1c1r1c2 -- - -
    h1c1h1c2 -
    r1c1r1c2 -
    r2c1r2c2 -
    -
    r2c1r2c2 -

    - -
    Tag transformation
    -Font element intended as 'inline' element:

    hi


    -Font element intended as 'block' element:
    hi

    -Font element intended as 'block' element:
    hi
    QQQ

    - -
    Tidy
    -White-space handling: abc def ghi abc def ghi - -
    URLs
    - -Relative and absolute: , , , , , ,
    -(try base URL value of 'http://a.com/b/')
    -CSS URLs:
    ,
    ,
    ,
    ,

    -Double URLs: b
    -Anti-spam: (try regex for 'http://a.com', etc.) , , , , , , ,
    -Soft-hyphen: ídis­c - -
    XSS
    - -<img onmouseover=confirm(1)// -'';!--"=&{()}
    -
    -
    -
    -
    -test -

    -

    -

    -
    -
    -

    -test
    -Bad IE7: x
    -Opera: link -Bad IE7: xxx
    -Bad IE7: xxx
    -Bad IE7: xxx
    -Bad IE7: xxx
    -Bad IE7: xxx
    -Bad IE7: xxx
    -Bad IE7: xxx
    -Bad IE7: xxx
    -Bad IE7: xxx
    -Bad IE7: xxx
    -Bad IE7: xxx
    -Bad IE7: xxx
    -Bad IE7: xxx
    -Bad IE7: x
    -Bad IE7: x
    -Bad IE7: x
    -Bad IE7: x
    -Bad IE7: exp/*x
    -Bad IE7: hi
    -Bad IE7: hi
    -Bad IE7: test
    -Bad IE7: hi
    -Bad IE7: hi
    - -
    Other
    - -3 < 4
    -3 > 4
    - > 3
    -<._.> hi!
    -<<< ALERT >>>
    - some stuff
    -
    -
    -
    -if(13age){say 'teen'}
    -age >51 and a smoking history of >51 pack-years was
    -age > 51 and a smoking history of >51 pack-years was
    -age <51 and a smoking history of <51 pack-years was
    -age < 51 and a smoking history of < 51 pack-years was
    -age >51 and a smoking history of >51 pack-years
    -age > 51 and a smoking history of >51 pack-years
    -age <51 and a smoking history of <51 pack-years
    -age < 51 and a smoking history of < 51 pack-years
    diff --git a/lib/attachmentlistitem.php b/lib/attachmentlistitem.php index 28ce9900b8..291cf685d1 100644 --- a/lib/attachmentlistitem.php +++ b/lib/attachmentlistitem.php @@ -234,13 +234,9 @@ class AttachmentListItem extends Widget $body = preg_replace('/^.*]*>/is', '', $body); $body = preg_replace('/<\/body[^>]*>.*$/is', '', $body); - require_once INSTALLDIR.'/extlib/htmLawed/htmLawed.php'; - $config = array('safe' => 1, - 'deny_attribute' => 'id,style,on*', - 'comment' => 1); // remove comments - $scrubbed = htmLawed($body, $config); - - return $scrubbed; + require_once INSTALLDIR.'/extlib/HTMLPurifier/HTMLPurifier.auto.php'; + $purifier = new HTMLPurifier(); + return $purifier->purify($body); } /** diff --git a/lib/default.php b/lib/default.php index 8d8ef11788..466bd26fff 100644 --- a/lib/default.php +++ b/lib/default.php @@ -277,7 +277,7 @@ $default = array('handle' => false, // whether to handle sessions ourselves 'debug' => false, // debugging output for sessions 'gc_limit' => 1000), // max sessions to expire at a time - 'htmlfilter' => array( // purify HTML through htmLawed + 'htmlfilter' => array( // purify HTML through HTMLPurifier 'img' => true, 'video' => true, 'audio' => true, diff --git a/lib/framework.php b/lib/framework.php index f8c877954f..732fecd30d 100644 --- a/lib/framework.php +++ b/lib/framework.php @@ -138,15 +138,15 @@ spl_autoload_register('GNUsocial_class_autoload'); * and is available here: http://www.php-fig.org/psr/psr-0/ */ spl_autoload_register(function($class){ - $class_path = preg_replace('{\\\\|_(?!.*\\\\)}', DIRECTORY_SEPARATOR, ltrim($class, '\\')).'.php'; - $file = INSTALLDIR.'/extlib/'.$class_path; + $class_base = preg_replace('{\\\\|_(?!.*\\\\)}', DIRECTORY_SEPARATOR, ltrim($class, '\\')); + $file = INSTALLDIR."/extlib/{$class_base}.php"; if (file_exists($file)) { require_once $file; return; } # Try if the system has this external library - $file = '/usr/share/php/'.$class_path; + $file = "/usr/share/php/{$class_base}.php"; if (file_exists($file)) { require_once $file; return; diff --git a/lib/util.php b/lib/util.php index 3a909d3592..4dd86fa370 100644 --- a/lib/util.php +++ b/lib/util.php @@ -577,24 +577,25 @@ function common_canonical_email($email) function common_purify($html) { - require_once INSTALLDIR.'/extlib/htmLawed/htmLawed.php'; + require_once INSTALLDIR.'/extlib/HTMLPurifier/HTMLPurifier.auto.php'; - $config = array('safe' => 1, // means that elements=* means elements=*-applet-embed-iframe-object-script or so - 'elements' => '*', - 'deny_attribute' => 'id,style,on*', - 'cdata' => 1); + $cfg = HTMLPurifier_Config::createDefault(); + $cfg->set('HTML.ForbiddenAttributes', array('style')); // id, on* etc. are already filtered by default - // Remove more elements than what the 'safe' filter gives (elements must be '*' before this) - // http://www.bioinformatics.org/phplabware/internal_utilities/htmLawed/htmLawed_README.htm#s3.6 + // Remove more elements than what the default filter removes, default in GNU social are remotely + // linked resources such as img, video, audio + $forbiddenElements = array(); foreach (common_config('htmlfilter') as $tag=>$filter) { if ($filter === true) { - $config['elements'] .= "-{$tag}"; + $forbiddenElements[] = $tag; } } + $cfg->set('HTML.ForbiddenElements', $forbiddenElements); $html = common_remove_unicode_formatting($html); - $purified = htmLawed($html, $config); + $purifier = new HTMLPurifier($cfg); + $purified = $purifier->purify($html); Event::handle('EndCommonPurify', array(&$purified, $html)); return $purified; diff --git a/plugins/Oembed/OembedPlugin.php b/plugins/Oembed/OembedPlugin.php index d17a1e68c3..361e4b54b8 100644 --- a/plugins/Oembed/OembedPlugin.php +++ b/plugins/Oembed/OembedPlugin.php @@ -233,16 +233,14 @@ class OembedPlugin extends Plugin // the 'photo' type is shown through ordinary means, using StartShowAttachmentRepresentation! switch ($oembed->type) { - case 'rich': case 'video': case 'link': if (!empty($oembed->html) && (GNUsocial::isAjax() || common_config('attachments', 'show_html'))) { - require_once INSTALLDIR.'/extlib/htmLawed/htmLawed.php'; - $config = array( - 'safe'=>1, - 'elements'=>'*+object+embed'); - $out->raw(htmLawed($oembed->html,$config)); + require_once INSTALLDIR.'/extlib/HTMLPurifier/HTMLPurifier.auto.php'; + $purifier = new HTMLPurifier(); + // FIXME: do we allow and here? we did that when we used htmLawed, but I'm not sure anymore... + $out->raw($purifier->purify($oembed->html)); } return false; break; diff --git a/plugins/Oembed/lib/oembedhelper.php b/plugins/Oembed/lib/oembedhelper.php index cb1c56e755..f76ea0a3c3 100644 --- a/plugins/Oembed/lib/oembedhelper.php +++ b/plugins/Oembed/lib/oembedhelper.php @@ -252,4 +252,4 @@ class oEmbedHelper_DiscoveryException extends oEmbedHelper_Exception { return parent::__construct('No oEmbed discovery data.', 0, $previous); } -} \ No newline at end of file +}