fix unicode hashtag

little_boxes/content_helper.py

@@ -1,10 +1,11 @@
-import re
 from typing import Dict
 from typing import List
 from typing import Tuple
 
 from markdown import markdown
 
+import regex as re
+
 from .activitypub import get_backend
 from .webfinger import get_actor_url
 
@@ -24,7 +25,10 @@ MENTION_REGEX = re.compile(r"@[\d\w_.+-]+@[\d\w-]+\.[\d\w\-.]+")
 def hashtagify(content: str) -> Tuple[str, List[Dict[str, str]]]:
     base_url = get_backend().base_url()
     tags = []
-    for hashtag in re.findall(HASHTAG_REGEX, content):
+    hashtags = re.findall(HASHTAG_REGEX, content)
+    hashtags.sort()
+    hashtags.reverse()  # replace longest tags first
+    for hashtag in hashtags:
         tag = hashtag[1:]
         link = f'<a href="{base_url}/tags/{tag}" class="mention hashtag" rel="tag">#<span>{tag}</span></a>'
         tags.append(dict(href=f"{base_url}/tags/{tag}", name=hashtag, type="Hashtag"))

requirements.txt

@@ -5,3 +5,4 @@ markdown
 pyld
 pycryptodome
 html2text
+regex

setup.py

@@ -1,11 +1,12 @@
 #!/usr/bin/env python
 
+from distutils.core import setup
 import io
 import os
-from distutils.core import setup
 
 from setuptools import find_packages
 
+
 here = os.path.abspath(os.path.dirname(__file__))
 
 
@@ -29,6 +30,7 @@ REQUIRED = [
     "pycryptodome",
     "html2text",
     "mdx_linkify",
+    "regex",
 ]
 
 DEPENDENCY_LINKS = []