mirror/php-htmlpurifier
1
0
Fork 0
mirror of https://github.com/ezyang/htmlpurifier.git synced 2025-08-08 23:26:39 +02:00
Code Issues Releases Wiki Activity

Remove a huge swath of duplicated function calls by factoring them into a normalize() function. Also made DirectLex's variable names consistent with the rest of the classes.

Browse Source 
git-svn-id: http://htmlpurifier.org/svnroot/htmlpurifier/trunk@340 48356398-32a2-884e-a903-53898d9a118a
This commit is contained in:
Edward Z. Yang
2006-08-29 20:05:26 +00:00
parent 1de3088276
commit 89376a11e3
4 changed files with 46 additions and 51 deletions
Download Patch File Download Diff File Expand all files Collapse all files

21
library/HTMLPurifier/Lexer/DOMLex.php
View File

@@ -37,24 +37,7 @@ class HTMLPurifier_Lexer_DOMLex extends HTMLPurifier_Lexer
public function tokenizeHTML($string, $config = null) {
if (!$config) $config = HTMLPurifier_Config::createDefault();
if ($config->get('Core', 'AcceptFullDocuments')) {
$string = $this->extractBody($string);
}
$doc = new DOMDocument();
$doc->encoding = 'UTF-8'; // technically does nothing, but whatever
// replace and escape the CDATA sections, since parsing under HTML
// mode won't get 'em.
$string = $this->escapeCDATA($string);
// substitute non-special entities. While DOM is perfectly capable
// of doing this, we need to get at the UTF-8 characters in
// cleanUTF8
$string = $this->_encoder->substituteNonSpecialEntities($string);
// clean it into well-formed UTF-8 string
$string = $this->_encoder->cleanUTF8($string);
$string = $this->normalize($string, $config);
// preprocess string, essential for UTF-8
$string =
@@ -66,6 +49,8 @@ class HTMLPurifier_Lexer_DOMLex extends HTMLPurifier_Lexer
' charset=utf-8" />'.
'</head><body><div>'.$string.'</div></body></html>';
$doc = new DOMDocument();
$doc->encoding = 'UTF-8'; // technically does nothing, but whatever
@$doc->loadHTML($string); // mute all errors, handle it transparently
$tokens = array();