mirror/FreshRSS
0
0
Fork 0
mirror of https://github.com/FreshRSS/FreshRSS.git synced 2025-12-23 21:47:44 -05:00
Code Issues Packages Projects Releases Wiki Activity

Fix saveHTML() scrambling encoding in newer libxml2 (#8296)

Browse Source 
fix https://github.com/FreshRSS/FreshRSS/pull/8279#issuecomment-3620674818
This commit is contained in:
Alexandre Alapetite
2025-12-08 23:18:33 +01:00
committed by GitHub
parent fd9e2843f1
commit ec26638124
1 changed files with 15 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

18
app/Utils/httpUtil.php
View File

@@ -203,8 +203,8 @@ final class FreshRSS_http_Util {
}
}
if ($httpCharsetNormalized === 'UTF-8') {
// Save encoding information as XML declaration
return '<' . '?xml version="1.0" encoding="' . $httpCharsetNormalized . '" ?' . ">\n" . $html;
// Save encoding information as Unicode BOM
return "\xEF\xBB\xBF" . $html;
}
// Give up
return $html;
@@ -241,7 +241,19 @@ final class FreshRSS_http_Util {
$doc->documentElement->insertBefore($base, $doc->documentElement->firstChild);
}
}
return $doc->saveHTML() ?: $html;
// Save the start of HTML because libxml2 saveHTML() risks scrambling it
$htmlPos = stripos($html, '<html');
$htmlStart = $htmlPos === false || $htmlPos > 512 ? '' : substr($html, 0, $htmlPos);
$html = $doc->saveHTML() ?: $html;
if ($htmlStart !== '' && !str_starts_with($html, $htmlStart)) {
// libxml2 saveHTML() risks removing Unicode BOM and XML declaration,
// which affects future detection of charset encoding, so manually restore it
$htmlPos = stripos($html, '<html');
$html = $htmlPos === false || $htmlPos > 512 ? $html : $htmlStart . substr($html, $htmlPos);
}
return $html;
}
/**