fix: Support URL extraction from markdown link syntax

Fixes #55849

Update URL_REGEX to match URLs embedded in markdown link syntax [label](url).
Previously, the regex required whitespace before/after URLs, which didn't
match markdown links where URLs are preceded by ]( and followed by ).

Also support square brackets in URL query parameters (e.g., ?foo[bar]=baz).

Changes:
- Add \]\( as valid URL prefix (markdown link start)
- Add \) as valid URL suffix (markdown link end)
- Add support for [ ] characters in URL paths
- Update both backend (IURLGenerator.php) and frontend (comments.js) regex
- Fix ReferenceManager to extract clean URLs using capture groups
- Maintain backward compatibility with plain URL extraction

Signed-off-by: Alexander Askin <[email protected]>

Author: LexioJ

core/src/OCP/comments.js

@@ -16,7 +16,7 @@ import $ from 'jquery'
  *
  * This is a copy of the backend regex in IURLGenerator, make sure to adjust both when changing
  */
-const urlRegex = /(\s|^)(https?:\/\/)([-A-Z0-9+_.]+(?::[0-9]+)?(?:\/[-A-Z0-9+&@#%?=~_|!:,.;()]*)*)(\s|$)/ig
+const urlRegex = /(\s|^|\]\()(https?:\/\/)([-A-Z0-9+_.]+(?::[0-9]+)?(?:\/[-A-Z0-9+&@#%?=~_|!:,.;\[\()]*)*)(\s|$|\))/ig
 
 /**
  * @param {any} content -

lib/private/Collaboration/Reference/ReferenceManager.php

@@ -51,10 +51,20 @@ public function __construct(
 	 */
 	public function extractReferences(string $text): array {
 		preg_match_all(IURLGenerator::URL_REGEX, $text, $matches);
-		$references = $matches[0] ?? [];
-		return array_map(function ($reference) {
-			return trim($reference);
-		}, $references);
+		// Use capture groups 2 (protocol) and 3 (domain/path) to extract clean URLs
+		// This excludes the prefix group 1 (\s|\n|^|\]\() and suffix group 4 (\s|\n|$|\))
+		$references = [];
+		if (!empty($matches[1]) && !empty($matches[2]) && !empty($matches[3])) {
+			for ($i = 0; $i < count($matches[2]); $i++) {
+				$url = $matches[2][$i] . $matches[3][$i];
+				// If the URL was in markdown syntax [](url), remove the trailing )
+				if ($matches[1][$i] === '](') {
+					$url = rtrim($url, ')');
+				}
+				$references[] = $url;
+			}
+		}
+		return $references;
 	}
 
 	/**

lib/public/IURLGenerator.php

@@ -30,8 +30,9 @@ interface IURLGenerator {
 	 *
 	 * @since 25.0.0
 	 * @since 29.0.0 changed to match localhost and hostnames with ports
+	 * @since 33.0.0 changed to match URLs in markdown link syntax and square brackets in query parameters
 	 */
-	public const URL_REGEX_NO_MODIFIERS = '(\s|\n|^)(https?:\/\/)([-A-Z0-9+_.]+(?::[0-9]+)?(?:\/[-A-Z0-9+&@#%?=~_|!:,.;()]*)*)(\s|\n|$)';
+	public const URL_REGEX_NO_MODIFIERS = '(\s|\n|^|\]\()(https?:\/\/)([-A-Z0-9+_.]+(?::[0-9]+)?(?:\/[-A-Z0-9+&@#%?=~_|!:,.;\[\()]*)*)(\s|\n|$|\))';
 
 	/**
 	 * Returns the URL for a route