mirrors/htmlpurifier
0
0
Fork 0
mirror of https://github.com/ezyang/htmlpurifier.git synced 2024-11-09 23:28:42 +00:00
Code Releases Activity

Fix DOM bug where default encoding for HTML docs is not UTF-8.

Browse Source 
git-svn-id: http://htmlpurifier.org/svnroot/htmlpurifier/trunk@252 48356398-32a2-884e-a903-53898d9a118a
This commit is contained in:
Edward Z. Yang 2006-08-14 13:27:18 +00:00
parent ebf0da9b78
commit 299236f695
3 changed files with 45 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
library/HTMLPurifier/Lexer/DOMLex.php
View File

@ -27,18 +27,23 @@ class HTMLPurifier_Lexer_DOMLex extends HTMLPurifier_Lexer
public function tokenizeHTML($string) { public function tokenizeHTML($string) {
$doc = new DOMDocument(); $doc = new DOMDocument();
$doc->encoding = 'UTF-8'; // technically does nothing, but comprehensive
// preprocess string
$string = '<html><body><div>'.$string.'</div></body></html>';
// replace and escape the CDATA sections, since parsing under HTML // replace and escape the CDATA sections, since parsing under HTML
// mode won't get 'em. // mode won't get 'em.
$string = $this->escapeCDATA($string); $string = $this->escapeCDATA($string);
// preprocess string, essential for UTF-8
$string =
'<html><head>'.
'<meta http-equiv="Content-Type" content="text/html;'.
' charset=utf-8" />'.
'</head><body><div>'.$string.'</div></body></html>';
@$doc->loadHTML($string); // mute all errors, handle it transparently @$doc->loadHTML($string); // mute all errors, handle it transparently
return $this->tokenizeDOM( return $this->tokenizeDOM(
$doc->childNodes->item(1)-> // html $doc->childNodes->item(1)-> // html
childNodes->item(0)-> // body childNodes->item(1)-> // body
childNodes->item(0) // div childNodes->item(0) // div
); );
} }

31
smoketests/utf8.php Normal file
View File

@ -0,0 +1,31 @@
<!DOCTYPE html
PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"
"http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
<html>
<head>
<title>HTMLPurifier UTF-8 Smoketest</title>
<meta http-equiv="Content-Type" content="text/html; charset=UTF-8" />
</head>
<body>
<h1>HTMLPurifier UTF-8 Smoketest</h1>
<?php
set_include_path('../library' . PATH_SEPARATOR . get_include_path());
require_once 'HTMLPurifier.php';
$purifier = new HTMLPurifier();
$string = '
<ul>
<li><b>Chinese</b> - 太極拳</li>
<li><b>Russian</b> - ЊЎЖ</li>
<li><b>Arabic</b> - لمنس</li>
</ul>
';
?>
<h2>Raw</h2>
<?php echo $string; ?>
<h2>Purified</h2>
<?php echo $purifier->purify($string); ?>
</body>
</html>

5
tests/HTMLPurifier/LexerTest.php
View File

@ -216,6 +216,11 @@ class HTMLPurifier_LexerTest extends UnitTestCase
); );
$sax_expect[16] = false; // PEARSax doesn't support it! $sax_expect[16] = false; // PEARSax doesn't support it!
// test that UTF-8 is preserved
$char_hearts = $this->_entity_lookup->table['hearts'];
$input[17] = $char_hearts;
$expect[17] = array( new HTMLPurifier_Token_Text($char_hearts) );
foreach($input as $i => $discard) { foreach($input as $i => $discard) {
$result = $this->DirectLex->tokenizeHTML($input[$i]); $result = $this->DirectLex->tokenizeHTML($input[$i]);
$this->assertEqual($expect[$i], $result, 'DirectLexTest '.$i.': %s'); $this->assertEqual($expect[$i], $result, 'DirectLexTest '.$i.': %s');