From d4da4dcc321ca65fb2cd19877f395cc5f75933ab Mon Sep 17 00:00:00 2001
From: Chih-Hsuan Yen <645432-yan12125@users.noreply.gitlab.com>
Date: Sun, 26 Nov 2023 20:53:05 +0800
Subject: Fix sanitizer with libxml2 >= 2.12.0
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Somehow with newer libxml2, `<?xml encoding="UTF-8">` no longer enforces
UTF-8. Instead, non-ASCII contents are treated as ISO-8859-1 and get
broken.

For example, `<p>中文</p>` becomes
`<p>&auml;&cedil;&shy;&aelig;&#150;&#135;</p>` (should be
`<p>&#20013;&#25991;</p>`).

Switching to another trick mentioned on [1] fixes the issue, and the
new trick still works with older libxml2 (tested 2.11.5).

As a side note, DOMDocument::loadHTML uses HTMLParser in libxml2 [2][3].

[1] https://stackoverflow.com/questions/8218230/php-domdocument-loadhtml-not-encoding-utf-8-correctly
[2] https://github.com/php/php-src/blob/php-8.1.26/ext/dom/document.c#L1855
[3] https://gnome.pages.gitlab.gnome.org/libxml2/devhelp/libxml2-HTMLparser.html
---
 classes/Sanitizer.php | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/classes/Sanitizer.php b/classes/Sanitizer.php
index a7bea9e5f..7af92f249 100644
--- a/classes/Sanitizer.php
+++ b/classes/Sanitizer.php
@@ -72,7 +72,7 @@ class Sanitizer {
 		$res = trim($str); if (!$res) return '';
 
 		$doc = new DOMDocument();
-		$doc->loadHTML('<?xml encoding="UTF-8">' . $res);
+		$doc->loadHTML('<meta charset="UTF-8">' . $res);
 		$xpath = new DOMXPath($doc);
 
 		// is it a good idea to possibly rewrite urls to our own prefix?
-- 
cgit v1.2.3