mirror of
https://github.com/ezyang/htmlpurifier.git
synced 2024-11-08 14:58:42 +00:00
b93892a3b6
git-svn-id: http://htmlpurifier.org/svnroot/htmlpurifier/trunk@436 48356398-32a2-884e-a903-53898d9a118a
179 lines
6.5 KiB
PHP
179 lines
6.5 KiB
PHP
<?php
|
|
|
|
require_once 'HTMLPurifier/EntityLookup.php';
|
|
require_once 'HTMLPurifier/Encoder.php';
|
|
|
|
/**
|
|
* Handles referencing and derefencing character entities
|
|
*/
|
|
class HTMLPurifier_EntityParser
|
|
{
|
|
|
|
/**
|
|
* Reference to entity lookup table.
|
|
* @protected
|
|
*/
|
|
var $_entity_lookup;
|
|
|
|
/**
|
|
* 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
|
|
|
|
|
|
/**
|
|
* 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
|
|
);
|
|
|
|
/**
|
|
* 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
|
|
* <http://forums.devnetwork.net/viewtopic.php?p=191404#191404>,
|
|
* 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 function is heavily intimate with the inner workings of
|
|
* UTF-8 and would also be well suited in the Encoder class (or at
|
|
* least deferring some processing to it). This is also very
|
|
* similar to the unichr function in
|
|
* maintenance/generate-entity-file.php (although this is superior,
|
|
* due to its sanity checks).
|
|
* @param $matches PCRE matches array, with 0 the entire match, and
|
|
* either index 1, 2 or 3 set with a hex value, dec value,
|
|
* or string (respectively).
|
|
* @returns Replacement string.
|
|
*/
|
|
|
|
// +----------+----------+----------+----------+
|
|
// | 33222222 | 22221111 | 111111 | |
|
|
// | 10987654 | 32109876 | 54321098 | 76543210 | bit
|
|
// +----------+----------+----------+----------+
|
|
// | | | | 0xxxxxxx | 1 byte 0x00000000..0x0000007F
|
|
// | | | 110yyyyy | 10xxxxxx | 2 byte 0x00000080..0x000007FF
|
|
// | | 1110zzzz | 10yyyyyy | 10xxxxxx | 3 byte 0x00000800..0x0000FFFF
|
|
// | 11110www | 10wwzzzz | 10yyyyyy | 10xxxxxx | 4 byte 0x00010000..0x0010FFFF
|
|
// +----------+----------+----------+----------+
|
|
// | 00000000 | 00011111 | 11111111 | 11111111 | Theoretical upper limit of legal scalars: 2097151 (0x001FFFFF)
|
|
// | 00000000 | 00010000 | 11111111 | 11111111 | Defined upper limit of legal scalar codes
|
|
// +----------+----------+----------+----------+
|
|
|
|
function nonSpecialEntityCallback($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 $entity;
|
|
|
|
return HTMLPurifier_Encoder::unichr($code);
|
|
} 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;
|
|
}
|
|
}
|
|
}
|
|
|
|
/**
|
|
* 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).
|
|
*
|
|
* @protected
|
|
* @param $string String to have non-special entities parsed.
|
|
* @returns Parsed string.
|
|
*/
|
|
function substituteSpecialEntities($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().
|
|
*
|
|
* @warning Though this is public in order to let the callback happen,
|
|
* calling it directly is not recommended.
|
|
* @param $matches PCRE-style matches array, with 0 the entire match, and
|
|
* either index 1, 2 or 3 set with a hex value, dec value,
|
|
* or string (respectively).
|
|
* @returns Replacement string.
|
|
*/
|
|
function specialEntityCallback($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;
|
|
}
|
|
}
|
|
|
|
}
|
|
|
|
?>
|