mirrors/htmlpurifier
0
0
Fork 0
mirror of https://github.com/ezyang/htmlpurifier.git synced 2025-03-15 10:57:05 +00:00
Code Releases Activity

Hacky full docuement parse thingy removed from DOMLex, fixes barfing on full HTML documents.

Browse Source 
git-svn-id: http://htmlpurifier.org/svnroot/htmlpurifier/trunk@328 48356398-32a2-884e-a903-53898d9a118a
This commit is contained in:
Edward Z. Yang 2006-08-27 22:06:58 +00:00
parent 24cde9c891
commit 7588068b7b
2 changed files with 3 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
library/HTMLPurifier/Lexer.php
View File

@ -295,10 +295,9 @@ class HTMLPurifier_Lexer
/**
* Takes a string of HTML (fragment or document) and returns the content
*/
function extractBody($html, $return_bool = false) {
function extractBody($html) {
$matches = array();
$result = preg_match('!<body[^>]*>(.+?)</body>!is', $html, $matches);
if ($return_bool) return $result;
if ($result) {
return $matches[1];
} else {

6
library/HTMLPurifier/Lexer/DOMLex.php
View File

@ -37,7 +37,7 @@ class HTMLPurifier_Lexer_DOMLex extends HTMLPurifier_Lexer
if (!$config) $config = HTMLPurifier_Config::createDefault();
if ($config->get('Core', 'AcceptFullDocuments')) {
$is_full = $this->extractBody($string, true);
$string = $this->extractBody($string);
}
$doc = new DOMDocument();
@ -55,9 +55,8 @@ class HTMLPurifier_Lexer_DOMLex extends HTMLPurifier_Lexer
// clean it into well-formed UTF-8 string
$string = $this->cleanUTF8($string);
if (!$is_full) {
// preprocess string, essential for UTF-8
$string =
$string =
'<!DOCTYPE html '.
'PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"'.
'"http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">'.
@ -65,7 +64,6 @@ class HTMLPurifier_Lexer_DOMLex extends HTMLPurifier_Lexer
'<meta http-equiv="Content-Type" content="text/html;'.
' charset=utf-8" />'.
'</head><body><div>'.$string.'</div></body></html>';
}
@$doc->loadHTML($string); // mute all errors, handle it transparently