this repo has no description
Add hashtag support to Bluesky post facets
Added hashtag parsing to both reply_to_post() in bsky_utils.py and
create_new_bluesky_post() in tools/post.py. Hashtags are now properly
parsed and converted to app.bsky.richtext.facet#tag facets with correct
byte positions.
- Parse hashtags using regex pattern that matches #word patterns
- Create facets with proper byte slice positioning
- Include hashtag tracking in debug logging
- Tested regex with various hashtag patterns
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
+48
-3
+27
-1
bsky_utils.py
+27
-1
bsky_utils.py
···
364
364
365
365
# Parse URLs - fixed to handle URLs at start of text
366
366
url_regex = rb"(?:^|[$|\W])(https?:\/\/(www\.)?[-a-zA-Z0-9@:%._\+~#=]{1,256}\.[a-zA-Z0-9()]{1,6}\b([-a-zA-Z0-9()@:%_\+.~#?&//=]*[-a-zA-Z0-9@%_\+~#//=])?)"
367
-
367
+
368
368
for m in re.finditer(url_regex, text_bytes):
369
369
url = m.group(1).decode("UTF-8")
370
370
urls_found.append(url)
···
381
381
)
382
382
)
383
383
logger.debug(f"[{correlation_id}] Found URL: {url}")
384
+
385
+
# Parse hashtags
386
+
hashtag_regex = rb"(?:^|[$|\s])#([a-zA-Z0-9_]+)"
387
+
hashtags_found = []
388
+
389
+
for m in re.finditer(hashtag_regex, text_bytes):
390
+
tag = m.group(1).decode("UTF-8") # Get tag without # prefix
391
+
hashtags_found.append(tag)
392
+
# Get byte positions for the entire hashtag including #
393
+
tag_start = m.start(0)
394
+
# Adjust start if there's a space/prefix
395
+
if text_bytes[tag_start:tag_start+1] in (b' ', b'$'):
396
+
tag_start += 1
397
+
tag_end = m.end(0)
398
+
facets.append(
399
+
models.AppBskyRichtextFacet.Main(
400
+
index=models.AppBskyRichtextFacet.ByteSlice(
401
+
byteStart=tag_start,
402
+
byteEnd=tag_end
403
+
),
404
+
features=[models.AppBskyRichtextFacet.Tag(tag=tag)]
405
+
)
406
+
)
407
+
logger.debug(f"[{correlation_id}] Found hashtag: #{tag}")
384
408
385
409
logger.debug(f"[{correlation_id}] Facet parsing complete", extra={
386
410
'correlation_id': correlation_id,
···
388
412
'mentions': mentions_found,
389
413
'urls_count': len(urls_found),
390
414
'urls': urls_found,
415
+
'hashtags_count': len(hashtags_found),
416
+
'hashtags': hashtags_found,
391
417
'total_facets': len(facets)
392
418
})
393
419
+21
-2
tools/post.py
+21
-2
tools/post.py
···
134
134
135
135
# Parse URLs - fixed to handle URLs at start of text
136
136
url_regex = rb"(?:^|[$|\W])(https?:\/\/(www\.)?[-a-zA-Z0-9@:%._\+~#=]{1,256}\.[a-zA-Z0-9()]{1,6}\b([-a-zA-Z0-9()@:%_\+.~#?&//=]*[-a-zA-Z0-9@%_\+~#//=])?)"
137
-
137
+
138
138
for m in re.finditer(url_regex, text_bytes):
139
139
url = m.group(1).decode("UTF-8")
140
140
# Adjust byte positions to account for the optional prefix
···
147
147
},
148
148
"features": [{"$type": "app.bsky.richtext.facet#link", "uri": url}],
149
149
})
150
-
150
+
151
+
# Parse hashtags
152
+
hashtag_regex = rb"(?:^|[$|\s])#([a-zA-Z0-9_]+)"
153
+
154
+
for m in re.finditer(hashtag_regex, text_bytes):
155
+
tag = m.group(1).decode("UTF-8") # Get tag without # prefix
156
+
# Get byte positions for the entire hashtag including #
157
+
tag_start = m.start(0)
158
+
# Adjust start if there's a space/prefix
159
+
if text_bytes[tag_start:tag_start+1] in (b' ', b'$'):
160
+
tag_start += 1
161
+
tag_end = m.end(0)
162
+
facets.append({
163
+
"index": {
164
+
"byteStart": tag_start,
165
+
"byteEnd": tag_end,
166
+
},
167
+
"features": [{"$type": "app.bsky.richtext.facet#tag", "tag": tag}],
168
+
})
169
+
151
170
if facets:
152
171
post_record["facets"] = facets
153
172