zzstoatzz.io / leaflet-search
search for standard sites pub-search.waow.tech
search zig blog atproto
fork atom

fix: purge dead offprint links and filter .test domains

- delete 31 stale docs from turso (16 dead offprint links, 18 .test domains, 3 overlap)
- add .test domain filter in tap.zig (processPublication) and indexer.zig (insertDocument)
- revert offprint URL slug construction — old docs purged, only /a/ format remains

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

zzstoatzz.io 4458c628 f2c6d293

+12 -6
unified split
+3
backend/src/ingest/indexer.zig
··· 125 125 } 126 126 } 127 127 128 + // skip .test domains (dev/staging data) 129 + if (std.mem.endsWith(u8, base_path, ".test")) return; 130 + 128 131 // detect platform from basePath if platform is unknown/other 129 132 // this handles site.standard.* documents where collection doesn't indicate platform 130 133 var actual_platform = platform;
+8
backend/src/ingest/tap.zig
··· 496 496 const base_path = zat.json.getString(record_val, "base_path") orelse 497 497 stripUrlScheme(zat.json.getString(record_val, "url")); 498 498 499 + // skip .test domains (dev/staging data) 500 + if (base_path) |bp| { 501 + if (mem.endsWith(u8, bp, ".test")) { 502 + logfire.span("tap.dropped", .{ .reason = "test_domain", .uri = uri }).end(); 503 + return; 504 + } 505 + } 506 + 499 507 try indexer.insertPublication(uri, did, rkey, name, description, base_path); 500 508 logfire.counter("tap.publications_indexed", 1); 501 509 }
+1 -6
site/index.html
··· 1104 1104 return `https://${doc.basePath}${separator}${doc.path}`; 1105 1105 } 1106 1106 1107 - // 4. Platform-specific fallback URL (e.g., leaflet.pub/p/did/rkey) 1107 + // 5. Platform-specific fallback URL (e.g., leaflet.pub/p/did/rkey) 1108 1108 const config = PLATFORM_CONFIG[platform]; 1109 1109 if (config?.docUrl && doc.did && doc.rkey) { 1110 1110 return config.docUrl(doc.did, doc.rkey); 1111 - } 1112 - 1113 - // 5. Fallback: pdsls.dev universal viewer (always works for any AT Protocol record) 1114 - if (doc.uri) { 1115 - return `https://pdsls.dev/${doc.uri}`; 1116 1111 } 1117 1112 1118 1113 return null;