1
0
mirror of https://github.com/ezyang/htmlpurifier.git synced 2025-08-06 14:16:32 +02:00

Malformed UTF-8 and non-SGML character detection and cleaning implemented

git-svn-id: http://htmlpurifier.org/svnroot/htmlpurifier/trunk@303 48356398-32a2-884e-a903-53898d9a118a
This commit is contained in:
Edward Z. Yang
2006-08-19 17:53:59 +00:00
parent 53808ee34a
commit 973cc43b64
11 changed files with 131 additions and 58 deletions

View File

@@ -29,20 +29,21 @@ class HTMLPurifier_Lexer_PEARSax3 extends HTMLPurifier_Lexer
*/
var $tokens = array();
function tokenizeHTML($html, $config = null) {
function tokenizeHTML($string, $config = null) {
if (!$config) $config = HTMLPurifier_Config::createDefault();
$html = $this->escapeCDATA($html);
$string = $this->escapeCDATA($string);
if ($config->get('Core', 'AcceptFullDocuments')) {
$html = $this->extractBody($html);
$string = $this->extractBody($string);
}
$html = $this->substituteNonSpecialEntities($html);
$string = $this->substituteNonSpecialEntities($string);
$string = $this->cleanUTF8($string);
$parser=& new XML_HTMLSax3();
$parser->set_object($this);
$parser->set_element_handler('openHandler','closeHandler');
$parser->set_data_handler('dataHandler');
$parser->set_escape_handler('escapeHandler');
$parser->set_option('XML_OPTION_ENTITIES_PARSED', 1);
$parser->parse($html);
$parser->parse($string);
$tokens = $this->tokens;
$this->tokens = array();
return $tokens;