From f718e2b0db0fe3477212a8dd6c3ec067f4432862 Mon Sep 17 00:00:00 2001 From: Klaus Weidenbach Date: Sat, 18 Mar 2017 17:50:05 +0100 Subject: :arrow_up: Update HTML Purifier library. Updated HTML Purifier from 4.6.0 to 4.9.2 with better PHP7 compatibility. Used composer to manage this library. --- .../library/HTMLPurifier/EntityParser.php | 285 +++++++++++++++++++++ 1 file changed, 285 insertions(+) create mode 100644 vendor/ezyang/htmlpurifier/library/HTMLPurifier/EntityParser.php (limited to 'vendor/ezyang/htmlpurifier/library/HTMLPurifier/EntityParser.php') diff --git a/vendor/ezyang/htmlpurifier/library/HTMLPurifier/EntityParser.php b/vendor/ezyang/htmlpurifier/library/HTMLPurifier/EntityParser.php new file mode 100644 index 000000000..c372b5a6a --- /dev/null +++ b/vendor/ezyang/htmlpurifier/library/HTMLPurifier/EntityParser.php @@ -0,0 +1,285 @@ +_semiOptionalPrefixRegex = "/&()()()($semi_optional)/"; + + $this->_textEntitiesRegex = + '/&(?:'. + // hex + '[#]x([a-fA-F0-9]+);?|'. + // dec + '[#]0*(\d+);?|'. + // string (mandatory semicolon) + // NB: order matters: match semicolon preferentially + '([A-Za-z_:][A-Za-z0-9.\-_:]*);|'. + // string (optional semicolon) + "($semi_optional)". + ')/'; + + $this->_attrEntitiesRegex = + '/&(?:'. + // hex + '[#]x([a-fA-F0-9]+);?|'. + // dec + '[#]0*(\d+);?|'. + // string (mandatory semicolon) + // NB: order matters: match semicolon preferentially + '([A-Za-z_:][A-Za-z0-9.\-_:]*);|'. + // string (optional semicolon) + // don't match if trailing is equals or alphanumeric (URL + // like) + "($semi_optional)(?![=;A-Za-z0-9])". + ')/'; + + } + + /** + * Substitute entities with the parsed equivalents. Use this on + * textual data in an HTML document (as opposed to attributes.) + * + * @param string $string String to have entities parsed. + * @return string Parsed string. + */ + public function substituteTextEntities($string) + { + return preg_replace_callback( + $this->_textEntitiesRegex, + array($this, 'entityCallback'), + $string + ); + } + + /** + * Substitute entities with the parsed equivalents. Use this on + * attribute contents in documents. + * + * @param string $string String to have entities parsed. + * @return string Parsed string. + */ + public function substituteAttrEntities($string) + { + return preg_replace_callback( + $this->_attrEntitiesRegex, + array($this, 'entityCallback'), + $string + ); + } + + /** + * Callback function for substituteNonSpecialEntities() that does the work. + * + * @param array $matches PCRE matches array, with 0 the entire match, and + * either index 1, 2 or 3 set with a hex value, dec value, + * or string (respectively). + * @return string Replacement string. + */ + + protected function entityCallback($matches) + { + $entity = $matches[0]; + $hex_part = @$matches[1]; + $dec_part = @$matches[2]; + $named_part = empty($matches[3]) ? @$matches[4] : $matches[3]; + if ($hex_part !== NULL && $hex_part !== "") { + return HTMLPurifier_Encoder::unichr(hexdec($hex_part)); + } elseif ($dec_part !== NULL && $dec_part !== "") { + return HTMLPurifier_Encoder::unichr((int) $dec_part); + } else { + if (!$this->_entity_lookup) { + $this->_entity_lookup = HTMLPurifier_EntityLookup::instance(); + } + if (isset($this->_entity_lookup->table[$named_part])) { + return $this->_entity_lookup->table[$named_part]; + } else { + // exact match didn't match anything, so test if + // any of the semicolon optional match the prefix. + // Test that this is an EXACT match is important to + // prevent infinite loop + if (!empty($matches[3])) { + return preg_replace_callback( + $this->_semiOptionalPrefixRegex, + array($this, 'entityCallback'), + $entity + ); + } + return $entity; + } + } + } + + // LEGACY CODE BELOW + + /** + * Callback regex string for parsing entities. + * @type string + */ + protected $_substituteEntitiesRegex = + '/&(?:[#]x([a-fA-F0-9]+)|[#]0*(\d+)|([A-Za-z_:][A-Za-z0-9.\-_:]*));?/'; + // 1. hex 2. dec 3. string (XML style) + + /** + * Decimal to parsed string conversion table for special entities. + * @type array + */ + protected $_special_dec2str = + array( + 34 => '"', + 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]]) ? + $this->_special_dec2str[$this->_special_ent2dec[$matches[3]]] : + $entity; + } + } +} + +// vim: et sw=4 sts=4 -- cgit v1.2.3