search for standard sites
pub-search.waow.tech
search
zig
blog
atproto
fix: detect platform from basePath, not lexicon
standard.site is a LEXICON, not a platform. platforms like pckt, leaflet,
and offprint use the standard.site lexicon.
- backend: migration detects pckt/leaflet from publication basePath
- frontend: shows 'standard.site' when platform unknown (not raw name)
- backfill-pds: also detects platform from basePath post-insert
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
+42
-5
+15
-1
backend/src/db/schema.zig
+15
-1
backend/src/db/schema.zig
···
143
143
// backfill platform from source_collection for records indexed before platform detection fix
144
144
client.exec("UPDATE documents SET platform = 'leaflet' WHERE platform = 'unknown' AND source_collection LIKE 'pub.leaflet.%'", &.{}) catch {};
145
145
client.exec("UPDATE documents SET platform = 'pckt' WHERE platform = 'unknown' AND source_collection LIKE 'blog.pckt.%'", &.{}) catch {};
146
-
client.exec("UPDATE documents SET platform = 'standardsite' WHERE platform = 'unknown' AND source_collection LIKE 'site.standard.%'", &.{}) catch {};
146
+
147
+
// detect platform from publication basePath (site.standard.* is a lexicon, not a platform)
148
+
// pckt uses site.standard.* lexicon but basePath contains pckt.blog
149
+
client.exec(
150
+
\\UPDATE documents SET platform = 'pckt'
151
+
\\WHERE platform IN ('standardsite', 'unknown')
152
+
\\AND publication_uri IN (SELECT uri FROM publications WHERE base_path LIKE '%pckt.blog%')
153
+
, &.{}) catch {};
154
+
155
+
// leaflet also uses site.standard.* lexicon, detect by basePath
156
+
client.exec(
157
+
\\UPDATE documents SET platform = 'leaflet'
158
+
\\WHERE platform IN ('standardsite', 'unknown')
159
+
\\AND publication_uri IN (SELECT uri FROM publications WHERE base_path LIKE '%leaflet.pub%')
160
+
, &.{}) catch {};
147
161
}
+25
-3
scripts/backfill-pds
+25
-3
scripts/backfill-pds
···
133
133
if not isinstance(tags, list):
134
134
tags = []
135
135
136
-
# Determine platform from collection
136
+
# Determine platform from collection (site.standard is a lexicon, not a platform)
137
137
if collection.startswith("pub.leaflet"):
138
138
platform = "leaflet"
139
-
elif collection.startswith("site.standard"):
140
-
platform = "standardsite"
139
+
elif collection.startswith("blog.pckt"):
140
+
platform = "pckt"
141
141
else:
142
+
# site.standard.* and others - platform will be detected from publication basePath
142
143
platform = "unknown"
143
144
144
145
return {
···
278
279
)
279
280
print(f" indexed pub: {name}")
280
281
total_pubs += 1
282
+
283
+
# post-process: detect platform from publication basePath
284
+
if not args.dry_run and (total_docs > 0 or total_pubs > 0):
285
+
print("detecting platforms from publication basePath...")
286
+
turso_exec(
287
+
settings,
288
+
"""
289
+
UPDATE documents SET platform = 'pckt'
290
+
WHERE platform IN ('standardsite', 'unknown')
291
+
AND publication_uri IN (SELECT uri FROM publications WHERE base_path LIKE '%pckt.blog%')
292
+
""",
293
+
)
294
+
turso_exec(
295
+
settings,
296
+
"""
297
+
UPDATE documents SET platform = 'leaflet'
298
+
WHERE platform IN ('standardsite', 'unknown')
299
+
AND publication_uri IN (SELECT uri FROM publications WHERE base_path LIKE '%leaflet.pub%')
300
+
""",
301
+
)
302
+
print(" done")
281
303
282
304
print(f"\ndone! {total_docs} documents, {total_pubs} publications")
283
305
+2
-1
site/index.html
+2
-1
site/index.html
···
535
535
if (config) {
536
536
return { url: config.home, label: config.label };
537
537
}
538
-
return { url: null, label: platform }; // just show platform name, no link
538
+
// unknown platform using standard.site lexicon - link to standard.site
539
+
return { url: 'https://standard.site', label: 'standard.site' };
539
540
}
540
541
541
542
function highlightTerms(text, query) {