=')) {
require_once 'HTMLPurifier/Lexer/DOMLex.php';
$lexer = new HTMLPurifier_Lexer_DOMLex();
} else {
require_once 'HTMLPurifier/Lexer/DirectLex.php';
$lexer = new HTMLPurifier_Lexer_DirectLex();
}
}
return $lexer;
}
/**
* Decimal to parsed string conversion table for special entities.
* @protected
*/
var $_special_dec2str =
array(
34 => '"',
38 => '&',
39 => "'",
60 => '<',
62 => '>'
);
/**
* Stripped entity names to decimal conversion table for special entities.
* @protected
*/
var $_special_ent2dec =
array(
'quot' => 34,
'amp' => 38,
'lt' => 60,
'gt' => 62
);
/**
* Most common entity to raw value conversion table for special entities.
* @protected
*/
var $_special_entity2str =
array(
'"' => '"',
'&' => '&',
'<' => '<',
'>' => '>',
''' => "'",
''' => "'",
''' => "'"
);
/**
* Callback regex string for parsing entities.
* @protected
*/
var $_substituteEntitiesRegex =
'/&(?:[#]x([a-fA-F0-9]+)|[#]0*(\d+)|([A-Za-z]+));?/';
// 1. hex 2. dec 3. string
/**
* 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.
*
* @protected
* @param $string String to have non-special entities parsed.
* @returns Parsed string.
*/
function substituteNonSpecialEntities($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.
*
* @warning Though this is public in order to let the callback happen,
* calling it directly is not recommended.
* @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.
* @param $matches PCRE matches array, with 0 the entire match, and
* either index 1, 2 or 3 set with a hex value, dec value,
* or string (respectively).
* @returns Replacement string.
* @todo Implement string translations
*/
// +----------+----------+----------+----------+
// | 33222222 | 22221111 | 111111 | |
// | 10987654 | 32109876 | 54321098 | 76543210 | bit
// +----------+----------+----------+----------+
// | | | | 0xxxxxxx | 1 byte 0x00000000..0x0000007F
// | | | 110yyyyy | 10xxxxxx | 2 byte 0x00000080..0x000007FF
// | | 1110zzzz | 10yyyyyy | 10xxxxxx | 3 byte 0x00000800..0x0000FFFF
// | 11110www | 10wwzzzz | 10yyyyyy | 10xxxxxx | 4 byte 0x00010000..0x0010FFFF
// +----------+----------+----------+----------+
// | 00000000 | 00011111 | 11111111 | 11111111 | Theoretical upper limit of legal scalars: 2097151 (0x001FFFFF)
// | 00000000 | 00010000 | 11111111 | 11111111 | Defined upper limit of legal scalar codes
// +----------+----------+----------+----------+
function nonSpecialEntityCallback($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 $entity;
if($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 $ret;
} else {
if (isset($this->_special_ent2dec[$matches[3]])) return $entity;
if (!$this->_entity_lookup) {
require_once 'HTMLPurifier/EntityLookup.php';
$this->_entity_lookup = HTMLPurifier_EntityLookup::instance();
}
if (isset($this->_entity_lookup->table[$matches[3]])) {
return $this->_entity_lookup->table[$matches[3]];
} else {
return $entity;
}
}
}
/**
* Contains a copy of the EntityLookup table.
* @protected
*/
var $_entity_lookup;
/**
* Translates CDATA sections into regular sections (through escaping).
*
* @protected
* @param $string HTML string to process.
* @returns HTML with CDATA sections escaped.
*/
function escapeCDATA($string) {
return preg_replace_callback(
'//',
array('HTMLPurifier_Lexer', 'CDATACallback'),
$string
);
}
/**
* Callback function for escapeCDATA() that does the work.
*
* @warning Though this is public in order to let the callback happen,
* calling it directly is not recommended.
* @params $matches PCRE matches array, with index 0 the entire match
* and 1 the inside of the CDATA section.
* @returns Escaped internals of the CDATA section.
*/
function CDATACallback($matches) {
// not exactly sure why the character set is needed, but whatever
return htmlspecialchars($matches[1], ENT_COMPAT, 'UTF-8');
}
/**
* Takes a string of HTML (fragment or document) and returns the content
*/
function extractBody($html) {
$matches = array();
$result = preg_match('!]*>(.+?)!is', $html, $matches);
if ($result) {
return $matches[1];
} else {
return $html;
}
}
/**
* 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.
*
* @warning This function can find a lot of use, so we may be moving
* it to a dedicated class.
*
* @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 The functionality provided by the original function could be
* implemented with iconv using 'UTF-8//IGNORE', mbstring, or
* even the PCRE modifier 'u', these do not allow us to strip
* control characters or disallowed code points, and the latter
* does not allow invalid UTF8 characters to be ignored.
*
* @note Decomposing the string into Unicode code points is necessary
* because SGML disallows the use of specific code points, not
* necessarily bytes. A naive implementation that simply strtr
* disallowed code points as bytes will break other Unicode
* characters in which using such bytes is valid.
*
* @note Code adapted from utf8ToUnicode by Henri Sivonen and
* hsivonen@iki.fi at