From 41dfe74e303fdd7bb245ba46d4e82215418427df Mon Sep 17 00:00:00 2001
From: Thomas Hohn <tho@gyldendal.dk>
Date: Wed, 31 Jan 2024 13:17:07 +0100
Subject: [PATCH] [BUGFIX] Handle if some tags are upper-case and
 strict-comparison

The method getTagContent in class HtmlContentExtractor should also for
work for tags that are not lower case.

Resolves: #3940
---
 Classes/HtmlContentExtractor.php | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/Classes/HtmlContentExtractor.php b/Classes/HtmlContentExtractor.php
index 6460bc48ac..49e3e6daee 100644
--- a/Classes/HtmlContentExtractor.php
+++ b/Classes/HtmlContentExtractor.php
@@ -224,7 +224,8 @@ public function getTagContent(): array
         foreach ($matches[1] as $key => $tag) {
             // We don't want to index links auto-generated by the url filter.
             $pattern = '@(?:http://|https://|ftp://|mailto:|smb://|afp://|file://|gopher://|news://|ssl://|sslv2://|sslv3://|tls://|tcp://|udp://|www\.)[a-zA-Z0-9]+@';
-            if ($tag != 'a' || !preg_match($pattern, $matches[2][$key])) {
+            $tag = strtolower((string)$tag);
+            if ($tag !== 'a' || !preg_match($pattern, $matches[2][$key])) {
                 $fieldName = $this->tagToFieldMapping[$tag];
                 $hasContentForFieldName = empty($result[$fieldName]);
                 $separator = ($hasContentForFieldName) ? '' : ' ';