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

Replace HTML regular expression by HTML::extractCharset in ParseUrl::getSiteInfo

Browse source 
- Address https://github.com/friendica/friendica/issues/12488#issuecomment-1374537440
This commit is contained in:
Hypolite Petovan 2023-01-10 01:08:34 -05:00
parent 5e2b655b43
commit 3fcafd1d50
1 changed files with 11 additions and 19 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

30
src/Util/ParseUrl.php
View file

@ -24,6 +24,8 @@ namespace Friendica\Util;
use DOMDocument; use DOMDocument;
use DOMXPath; use DOMXPath;
use Friendica\Content\OEmbed; use Friendica\Content\OEmbed;
use Friendica\Content\Text\HTML;
use Friendica\Protocol\HTTP\MediaType;
use Friendica\Core\Hook; use Friendica\Core\Hook;
use Friendica\Core\Logger; use Friendica\Core\Logger;
use Friendica\Database\Database; use Friendica\Database\Database;
@ -283,25 +285,13 @@ class ParseUrl
} }
$charset = ''; $charset = '';
// Look for a charset, first in headers try {
// Expected form: Content-Type: text/html; charset=ISO-8859-4 // Look for a charset, first in headers
if (preg_match('/charset=([a-z0-9-_.\/]+)/i', $curlResult->getContentType(), $matches)) { $mediaType = MediaType::fromContentType($curlResult->getContentType());
$charset = trim(trim(trim(array_pop($matches)), ';,')); if (isset($mediaType->parameters['charset'])) {
} else { $charset = $mediaType->parameters['charset'];
// Then in body that gets precedence }
// Expected forms: } catch(\InvalidArgumentException $e) {}
// - <meta http-equiv="Content-Type" content="text/html; charset=utf-8">
// - <meta charset="utf-8">
// - <meta charset=utf-8>
// - <meta charSet="utf-8">
// We escape <style> and <script> tags since they can contain irrelevant charset information
// (see https://github.com/friendica/friendica/issues/9251#issuecomment-698636806)
Strings::performWithEscapedBlocks($body, '#<(?:style|script).*?</(?:style|script)>#ism', function ($body) use (&$charset) {
if (preg_match('/charset=["\']?([a-z0-9-_.\/]+)/i', $body, $matches)) {
$charset = trim(trim(trim(array_pop($matches)), ';,'));
}
});
}
$siteinfo['charset'] = $charset; $siteinfo['charset'] = $charset;
@ -322,6 +312,8 @@ class ParseUrl
$doc = new DOMDocument(); $doc = new DOMDocument();
@$doc->loadHTML($body); @$doc->loadHTML($body);
$siteinfo['charset'] = HTML::extractCharset($doc) ?? $siteinfo['charset'];
XML::deleteNode($doc, 'style'); XML::deleteNode($doc, 'style');
XML::deleteNode($doc, 'option'); XML::deleteNode($doc, 'option');
XML::deleteNode($doc, 'h1'); XML::deleteNode($doc, 'h1');