search for standard sites
pub-search.waow.tech
search
zig
blog
atproto
feat: add site.standard.* support for indexing
- Add `standardsite` platform enum with displayName() returning "standard.site"
- Add site.standard.document and site.standard.publication to TAP_COLLECTION_FILTERS
- Extractor already handles textContent field used by site.standard
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
+24
-2
+23
-1
backend/src/extractor.zig
+23
-1
backend/src/extractor.zig
···
4
4
const Allocator = mem.Allocator;
5
5
const zat = @import("zat");
6
6
7
-
/// Detected platform from content.$type
7
+
/// Detected platform from collection name
8
8
pub const Platform = enum {
9
9
leaflet,
10
10
pckt,
11
11
offprint,
12
+
standardsite,
12
13
unknown,
13
14
14
15
pub fn fromCollection(collection: []const u8) Platform {
15
16
if (mem.startsWith(u8, collection, "pub.leaflet.")) return .leaflet;
16
17
if (mem.startsWith(u8, collection, "blog.pckt.")) return .pckt;
17
18
if (mem.startsWith(u8, collection, "app.offprint.")) return .offprint;
19
+
if (mem.startsWith(u8, collection, "site.standard.")) return .standardsite;
18
20
return .unknown;
19
21
}
20
22
23
+
/// Internal name (for DB storage)
21
24
pub fn name(self: Platform) []const u8 {
22
25
return @tagName(self);
26
+
}
27
+
28
+
/// Display name (for UI)
29
+
pub fn displayName(self: Platform) []const u8 {
30
+
return switch (self) {
31
+
.standardsite => "standard.site",
32
+
else => @tagName(self),
33
+
};
23
34
}
24
35
};
25
36
···
230
241
try std.testing.expectEqual(Platform.offprint, Platform.fromCollection("app.offprint.document"));
231
242
}
232
243
244
+
test "Platform.fromCollection: standardsite" {
245
+
try std.testing.expectEqual(Platform.standardsite, Platform.fromCollection("site.standard.document"));
246
+
try std.testing.expectEqual(Platform.standardsite, Platform.fromCollection("site.standard.publication"));
247
+
}
248
+
233
249
test "Platform.fromCollection: unknown" {
234
250
try std.testing.expectEqual(Platform.unknown, Platform.fromCollection("something.else"));
235
251
try std.testing.expectEqual(Platform.unknown, Platform.fromCollection(""));
···
239
255
try std.testing.expectEqualStrings("leaflet", Platform.leaflet.name());
240
256
try std.testing.expectEqualStrings("pckt", Platform.pckt.name());
241
257
try std.testing.expectEqualStrings("offprint", Platform.offprint.name());
258
+
try std.testing.expectEqualStrings("standardsite", Platform.standardsite.name());
242
259
try std.testing.expectEqualStrings("unknown", Platform.unknown.name());
243
260
}
261
+
262
+
test "Platform.displayName" {
263
+
try std.testing.expectEqualStrings("leaflet", Platform.leaflet.displayName());
264
+
try std.testing.expectEqualStrings("standard.site", Platform.standardsite.displayName());
265
+
}
+1
-1
tap/fly.toml
+1
-1
tap/fly.toml
···
9
9
TAP_BIND = ':2480'
10
10
TAP_RELAY_URL = 'https://relay1.us-east.bsky.network'
11
11
TAP_SIGNAL_COLLECTION = 'pub.leaflet.document'
12
-
TAP_COLLECTION_FILTERS = 'pub.leaflet.document,pub.leaflet.publication'
12
+
TAP_COLLECTION_FILTERS = 'pub.leaflet.document,pub.leaflet.publication,site.standard.document,site.standard.publication'
13
13
TAP_LOG_LEVEL = 'info'
14
14
TAP_RESYNC_PARALLELISM = '2'
15
15
TAP_IDENT_CACHE_SIZE = '10000'