jakob/friendica
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

Add style and script tag escaping when parsing charset in Util\ParseUrl

Browse source 
- Address https://github.com/friendica/friendica/issues/9251#issuecomment-698086677
This commit is contained in:
Hypolite Petovan 2020-09-25 06:55:52 -04:00
parent 6d4454582d
commit f52d44554e
1 changed files with 7 additions and 3 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

10
src/Util/ParseUrl.php
View file

@ -212,9 +212,13 @@ class ParseUrl
// Expected forms:
// - <meta http-equiv="Content-Type" content="text/html; charset=utf-8">
// - <meta charset="utf-8">
if (preg_match('/charset=["\']?([^\'"]*?)[\'"]/', $body, $matches)) {
$charset = trim(trim(trim(array_pop($matches)), ';,'));
}
// We escape <style> and <script> tags since they can contain irrelevant charset information
// (see https://github.com/friendica/friendica/issues/9251#issuecomment-698636806)
Strings::performWithEscapedBlocks($body, '#<(?:style|script).*?</(?:style|script)>#ism', function ($body) use (&$charset) {
if (preg_match('/charset=["\']?([^\',"]*?)[\'"]/', $body, $matches)) {
$charset = trim(trim(trim(array_pop($matches)), ';,'));
}
});
if ($charset && strtoupper($charset) != 'UTF-8') {
// See https://github.com/friendica/friendica/issues/5470#issuecomment-418351211