zzstoatzz.io
search for standard sites
pub-search.waow.tech
search
zig
blog
atproto
feat: add whitewind support to backfill-pds script + fix dep URLs
- backfill-pds now handles com.whtwnd.blog.entry collection
- extracts markdown content from whitewind's content field
- sets platform to "whitewind", skips visibility:"author" entries
- prefers publishedAt over createdAt for date extraction
- update tangled.sh URLs to tangled.org in build.zig.zon
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
+2
-2
backend/build.zig.zon
+2
-2
backend/build.zig.zon
···
13
13
.hash = "zql-0.0.1-alpha-xNRI4IRNAABUb9gLat5FWUaZDD5HvxAxet_-elgR_A_y",
14
14
},
15
15
.zat = .{
16
-
.url = "https://tangled.sh/zat.dev/zat/archive/main",
16
+
.url = "https://tangled.org/zat.dev/zat/archive/main",
17
17
.hash = "zat-0.1.0-5PuC7s8BAwDFmyYbkyZ8w4azed6eR_cqmHbh8f00NBSB",
18
18
},
19
19
.zqlite = .{
···
21
21
.hash = "zqlite-0.0.1-RWLaYz6bmAAT7E_jxopXf-j5Ea8VQldnxsd6TU8sa0Bb",
22
22
},
23
23
.logfire = .{
24
-
.url = "https://tangled.sh/zzstoatzz.io/logfire-zig/archive/main",
24
+
.url = "https://tangled.org/zzstoatzz.io/logfire-zig/archive/main",
25
25
.hash = "logfire_zig-0.1.0-x2yDLgdwAADOXAZLNQJ8FUH5v1vfFwe5CApJtQ7c_pZd",
26
26
},
27
27
},
+22
-12
scripts/backfill-pds
+22
-12
scripts/backfill-pds
···
161
161
if not title:
162
162
return None
163
163
164
-
# Get content - try textContent (site.standard), then leaflet blocks
164
+
# Skip author-only whitewind entries
165
+
if collection == "com.whtwnd.blog.entry":
166
+
if value.get("visibility") == "author":
167
+
return None
168
+
169
+
# Get content - try textContent (site.standard), then content as string
170
+
# (whitewind stores markdown), then leaflet blocks
165
171
content = value.get("textContent") or ""
166
172
if not content:
167
-
# Try leaflet-style pages/blocks at top level (pub.leaflet.document)
168
-
pages = value.get("pages", [])
169
-
if pages:
170
-
content = extract_leaflet_blocks(pages)
171
-
if not content:
172
-
# Try content.pages (site.standard.document with pub.leaflet.content)
173
173
content_obj = value.get("content")
174
-
if isinstance(content_obj, dict):
174
+
if isinstance(content_obj, str):
175
+
content = content_obj
176
+
elif isinstance(content_obj, dict):
175
177
pages = content_obj.get("pages", [])
176
178
if pages:
177
179
content = extract_leaflet_blocks(pages)
180
+
if not content:
181
+
# Try leaflet-style pages/blocks at top level (pub.leaflet.document)
182
+
pages = value.get("pages", [])
183
+
if pages:
184
+
content = extract_leaflet_blocks(pages)
178
185
179
-
# Get created_at
180
-
created_at = value.get("createdAt", "")
186
+
# Get created_at (prefer publishedAt for leaflet/standard, createdAt for whitewind)
187
+
created_at = value.get("publishedAt") or value.get("createdAt", "")
181
188
182
189
# Get publication reference - try "publication" (leaflet) then "site" (site.standard)
183
190
publication = value.get("publication") or value.get("site")
···
196
203
if not isinstance(tags, list):
197
204
tags = []
198
205
199
-
# Determine platform from collection (site.standard is a lexicon, not a platform)
206
+
# Determine platform from collection
200
207
if collection.startswith("pub.leaflet"):
201
208
platform = "leaflet"
202
209
elif collection.startswith("blog.pckt"):
203
210
platform = "pckt"
211
+
elif collection.startswith("com.whtwnd"):
212
+
platform = "whitewind"
204
213
else:
205
214
# site.standard.* and others - platform will be detected from publication basePath
206
215
platform = "unknown"
···
250
259
"pub.leaflet.publication",
251
260
"site.standard.document",
252
261
"site.standard.publication",
262
+
"com.whtwnd.blog.entry",
253
263
]
254
264
255
265
total_docs = 0
···
277
287
parts = uri.split("/")
278
288
rkey = parts[-1]
279
289
280
-
if collection.endswith(".document"):
290
+
if collection.endswith(".document") or collection == "com.whtwnd.blog.entry":
281
291
doc = extract_document(record, collection)
282
292
if not doc:
283
293
print(f" skip {uri} (no title)")