🩹 Improve comment removal in Document class by using a non-greedy regex match.

dustingrofthenumber · dustingrofthenumber · commit e33858d1fdbe · 2025-12-09T11:41:18.000-08:00
diff --git a/src/Document.php b/src/Document.php
@@ -74,7 +74,8 @@ public function html(): string
         // Remove XML declaration/comment that libxml2 may add
         // Handles both <?xml encoding="UTF-8"> and any comments libxml2 adds
         $html = preg_replace('/^<\?xml[^>]*>\s*/i', '', $html);
-        $html = preg_replace('/^<!--[^>]*-->\s*/', '', $html);
+        // Use non-greedy match to handle comments containing > characters
+        $html = preg_replace('/^<!--.*?-->\s*/s', '', $html);
 
         return trim($html);
     }

Original file line number	Diff line number	Diff line change
`@@ -74,7 +74,8 @@ public function html(): string`
`74`	`74`	`// Remove XML declaration/comment that libxml2 may add`
`75`	`75`	`// Handles both <?xml encoding="UTF-8"> and any comments libxml2 adds`
`76`	`76`	`$html = preg_replace('/^<\?xml[^>]>\s/i', '', $html);`
`77`		`- $html = preg_replace('/^<!--[^>]-->\s/', '', $html);`
	`77`	`+ // Use non-greedy match to handle comments containing > characters`
	`78`	`+ $html = preg_replace('/^<!--.?-->\s/s', '', $html);`
`78`	`79`
`79`	`80`	`return trim($html);`
`80`	`81`	`}`