From 8137c6b4b1bbb6fee639a979150fc14a190c8f9d Mon Sep 17 00:00:00 2001
From: freamon <f78673709@gmail.com>
Date: Mon, 17 Jun 2024 16:54:27 +0100
Subject: [PATCH] Simplify regex for raw URLs in text

---
 app/utils.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/app/utils.py b/app/utils.py
index 3376e228..da5c24a8 100644
--- a/app/utils.py
+++ b/app/utils.py
@@ -188,7 +188,7 @@ def allowlist_html(html: str) -> str:
     soup = BeautifulSoup(html, 'html.parser')
 
     # Find all plain text links, convert to <a> tags
-    re_url = re.compile(r'(http[s]?://(?:[a-zA-Z]|[0-9]|[$-_@.&+]|[!*\(\),]|(?:%[0-9a-fA-F][0-9a-fA-F]))+)')
+    re_url = re.compile(r'(http[s]?://[!-~]+)')   # http(s):// followed by chars in ASCII range 33 to 126
     for tag in soup.find_all(text=True):
         tags = []
         url = False