this repo has no description
Fix links.json to support multiple source articles per URL and resolve url_mapping.json empty file issue
- Changed links.json structure to map URLs to lists of atom IDs instead of single IDs
- Added proper deduplication to avoid storing duplicate entry IDs for same URL
- Fixed url_mapping.json by converting HttpUrl objects to strings for proper comparison
- Added debug output to show registered URLs count for troubleshooting
- Updated filtering logic to handle new list-based link structure
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
+17
-11
+17
-11
src/thicket/cli/commands/links_cmd.py
+17
-11
src/thicket/cli/commands/links_cmd.py
···
214
214
# Process all entries
215
215
all_links = []
216
216
link_categories = {"internal": [], "user": [], "unknown": []}
217
-
link_dict = {} # Dictionary with link URL as key, maps to atom ID
217
+
link_dict = {} # Dictionary with link URL as key, maps to list of atom IDs
218
218
reverse_dict = {} # Dictionary with atom ID as key, maps to list of URLs
219
219
220
220
with Progress(
···
265
265
266
266
category, target_username = categorizer.categorize_url(link_data.url, username)
267
267
268
-
# Add to link dictionary (URL as key, maps to atom ID only)
268
+
# Add to link dictionary (URL as key, maps to list of atom IDs)
269
269
if link_data.url not in link_dict:
270
-
link_dict[link_data.url] = link_data.entry_id
270
+
link_dict[link_data.url] = []
271
+
if link_data.entry_id not in link_dict[link_data.url]:
272
+
link_dict[link_data.url].append(link_data.entry_id)
271
273
272
274
# Also add to reverse mapping (atom ID -> list of URLs)
273
275
if link_data.entry_id not in reverse_dict:
274
276
reverse_dict[link_data.entry_id] = []
275
-
reverse_dict[link_data.entry_id].append(link_data.url)
277
+
if link_data.url not in reverse_dict[link_data.entry_id]:
278
+
reverse_dict[link_data.entry_id].append(link_data.url)
276
279
277
280
# Add category info to link data for categories tracking
278
281
link_info = link_data.to_dict()
···
313
316
for entry in entries:
314
317
# Try to match entry URLs with extracted links
315
318
if hasattr(entry, 'link') and entry.link:
316
-
registered_urls.add(entry.link)
319
+
registered_urls.add(str(entry.link))
317
320
318
321
# Also check entry alternate links if they exist
319
322
if hasattr(entry, 'links') and entry.links:
320
323
for link in entry.links:
321
324
if hasattr(link, 'href') and link.href:
322
-
registered_urls.add(link.href)
325
+
registered_urls.add(str(link.href))
323
326
324
327
# Create filtered version for URL mapping (only links to registered posts)
325
328
filtered_link_dict = {}
326
329
filtered_reverse_dict = {}
327
330
328
-
for url, entry_id in link_dict.items():
331
+
for url, entry_ids in link_dict.items():
329
332
if url in registered_urls:
330
-
filtered_link_dict[url] = entry_id
333
+
filtered_link_dict[url] = entry_ids
331
334
332
335
# Also update reverse mapping
333
-
if entry_id not in filtered_reverse_dict:
334
-
filtered_reverse_dict[entry_id] = []
335
-
filtered_reverse_dict[entry_id].append(url)
336
+
for entry_id in entry_ids:
337
+
if entry_id not in filtered_reverse_dict:
338
+
filtered_reverse_dict[entry_id] = []
339
+
if url not in filtered_reverse_dict[entry_id]:
340
+
filtered_reverse_dict[entry_id].append(url)
336
341
337
342
# Use all links for main output, not filtered ones
338
343
output_data = link_dict
339
344
340
345
if verbose:
346
+
console.print(f"Found {len(registered_urls)} registered post URLs")
341
347
console.print(f"Found {len(link_dict)} total links, {len(filtered_link_dict)} links to registered posts")
342
348
343
349
# Save links data (URL -> atom ID mapping, all links)