From 8139ccffdb6450f4413eff4a9d880b6741c7dd01 Mon Sep 17 00:00:00 2001
From: Andrew Godwin
Date: Tue, 29 Nov 2022 09:44:22 -0700
Subject: Fix hashtag extraction

---
 activities/models/hashtag.py            | 2 +-
 tests/activities/models/test_hashtag.py | 4 +++-
 2 files changed, 4 insertions(+), 2 deletions(-)

diff --git a/activities/models/hashtag.py b/activities/models/hashtag.py
index 9cfb21d..b7f0832 100644
--- a/activities/models/hashtag.py
+++ b/activities/models/hashtag.py
@@ -176,7 +176,7 @@ class Hashtag(StatorModel):
         leading '#'.
         """
         hashtag_hits = cls.hashtag_regex.findall(strip_html(content))
-        hashtags = sorted({tag[1].lower() for tag in hashtag_hits})
+        hashtags = sorted({tag.lower() for tag in hashtag_hits})
         return list(hashtags)
 
     @classmethod
diff --git a/tests/activities/models/test_hashtag.py b/tests/activities/models/test_hashtag.py
index 32742d6..91af45c 100644
--- a/tests/activities/models/test_hashtag.py
+++ b/tests/activities/models/test_hashtag.py
@@ -9,11 +9,13 @@ def test_hashtag_from_content():
         "with",
     ]
     assert Hashtag.hashtags_from_content("#hashtag.") == ["hashtag"]
-    assert Hashtag.hashtags_from_content("More text\n#one # two ##three #hashtag;") == [
+    assert Hashtag.hashtags_from_content("More text\n#one # two ##three #hashtag!") == [
         "hashtag",
         "one",
         "three",
     ]
+    assert Hashtag.hashtags_from_content("my #html loves   entities") == ["html"]
+    assert Hashtag.hashtags_from_content("<span class='hash'>#</span>tag") == ["tag"]
 
 
 def test_linkify_hashtag():
-- 
cgit v1.2.3