From bd8b96c1f5b586dd1469f92426e25e7524ccaf46 Mon Sep 17 00:00:00 2001
From: official-techsupport
 <98240022+official-techsupport@users.noreply.github.com>
Date: Sun, 25 Sep 2022 01:06:53 +0300
Subject: [PATCH] fix the TLD matching to exclude numbers (#371)

---
 files/helpers/sanitize.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/files/helpers/sanitize.py b/files/helpers/sanitize.py
index 41d217c10..7052c53bf 100644
--- a/files/helpers/sanitize.py
+++ b/files/helpers/sanitize.py
@@ -95,7 +95,7 @@ def build_url_re(protocols):
 	return re.compile(
 		r"""\(*# Match any opening parentheses.
 		\b(?<![@.])(?:(?:{0}):/{{0,3}}(?:(?:\w+:)?\w+@)?)?# http://
-		([\w-]+\.)+(?:\w{{2,20}})(?:\:[0-9]+)?(?!\.\w)\b# xx.yy.tld(:##)?
+		([\w-]+\.)+(?:[A-Za-z]{{2,20}})(?:\:[0-9]+)?(?!\.\w)\b# xx.yy.tld(:##)?
 		(?:[/?][^#\s\{{\}}\|\\\^\[\]`<>"]*)?
 			# /path/zz (excluding "unsafe" chars from RFC 1738,
 			# except for ~, which happens in practice)