feat(parsing.utils): support chat-specific hashtags by allowing '@'

Telegram recently added a feature called "chat-specific hashtags," formatting as `#hashtag@username`. However, '@' was escaped, resulting in these hashtags being broken. Properly supports such hashtags by allowing '@' in hashtags. Signed-off-by: Rongrong <[email protected]>
Rongronggg9 · Nov 6, 2024 · 37d8c96 · 37d8c96
1 parent 067606b
commit 37d8c96
Showing 1 changed file with 9 additions and 2 deletions.
diff --git a/src/parsing/utils.py b/src/parsing/utils.py
@@ -96,8 +96,15 @@
 )
 INVALID_CHARACTERS_IN_HASHTAG: Final[str] = ''.join(
     sorted(
-        # Known characters that break hashtags. Though '・' breaks hashtags, it is not the case of '·'.
-        set(chain(SPACES, INVALID_CHARACTERS, string.punctuation, string.whitespace, '・'))
+        # Known characters that break hashtags.
+        set(chain(
+            SPACES, INVALID_CHARACTERS, string.punctuation, string.whitespace,
+            '・',  # Though '・' breaks hashtags, it is not the case of '·'.
+        ))
+        # Characters included in `string.punctuation` but valid in hashtags.
+        - set(
+            '@'  # Used in "chat-specific hashtags".
+        )
     )
 )