From 0783bf43aa54978faaff5128f3b1d0307a3ee8eb Mon Sep 17 00:00:00 2001
From: Alain St-Denis <alain@zenfolie.org>
Date: Sat, 15 Jul 2023 09:54:41 -0400
Subject: [PATCH] Remove unreachable code. Improve (I hope) the mention regex
 for raw text.

---
 federation/entities/activitypub/models.py | 10 +---------
 federation/utils/text.py                  |  4 ++--
 2 files changed, 3 insertions(+), 11 deletions(-)

diff --git a/federation/entities/activitypub/models.py b/federation/entities/activitypub/models.py
index f9df860..e7afbbe 100644
--- a/federation/entities/activitypub/models.py
+++ b/federation/entities/activitypub/models.py
@@ -874,21 +874,13 @@ class Note(Object, RawContentMixin):
 
     def extract_mentions(self):
         """
-        Extract mentions from the inbound Mention objects.
-
-        Also attempt to extract from raw_content if available
+        Attempt to extract mentions from raw_content if available
         """
 
         if self.raw_content:
             super().extract_mentions()
         return
 
-        for mention in self.tag_objects:
-            if isinstance(mention, Mention):
-                profile = get_profile_or_entity(fid=mention.href)
-                handle = getattr(profile, 'finger', None)
-                if handle: self._mentions.add(handle)
-
     @property
     def rendered_content(self):
         if self._soup: return str(self._soup)
diff --git a/federation/utils/text.py b/federation/utils/text.py
index e2cd78c..cbe6086 100644
--- a/federation/utils/text.py
+++ b/federation/utils/text.py
@@ -10,8 +10,8 @@ from commonmark import commonmark
 
 ILLEGAL_TAG_CHARS = "!#$%^&*+.,@£/()=?`'\\{[]}~;:\"’”—\xa0"
 TAG_PATTERN = re.compile(r'(#[\w]+)', re.UNICODE)
-MENTION_PATTERN = re.compile(r'(@{?[\S ]?[^{}@]+[@;]?\s*[\w\-./@]+[\w/]+}?)', re.UNICODE)
-
+# This will match non matching braces. I don't think it's an issue.
+MENTION_PATTERN = re.compile(r'(@\{?(?:[\w\-. \u263a-\U0001f645]*; *)?[\w]+@[\w\-.]+\.[\w]+}?)', re.UNICODE)
 
 def decode_if_bytes(text):
     try: