search for standard sites
pub-search.waow.tech
search
zig
blog
atproto
feat: detect leaflet platform from content.$type for custom domains
Custom domain Leaflet sites (e.g., cailean.journal.ewancroft.uk) use
site.standard.document but have content.$type = "pub.leaflet.content".
- Add content_type field to ExtractedDocument
- Extract content.$type during document extraction
- Use as fallback in platform detection when basePath doesn't match
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
+29
-5
+7
backend/src/extractor.zig
+7
backend/src/extractor.zig
···
43
43
platform: Platform,
44
44
source_collection: []const u8,
45
45
path: ?[]const u8, // URL path from record (e.g., "/001" for zat.dev)
46
+
content_type: ?[]const u8, // content.$type (e.g., "pub.leaflet.content") for platform detection
46
47
47
48
pub fn deinit(self: *ExtractedDocument) void {
48
49
self.allocator.free(self.content);
···
103
104
// extract URL path (site.standard.document uses "path" field like "/001")
104
105
const path = zat.json.getString(record_val, "path");
105
106
107
+
// extract content.$type for platform detection (e.g., "pub.leaflet.content")
108
+
const content_type = zat.json.getString(record_val, "content.$type");
109
+
106
110
// extract tags - allocate owned slice
107
111
const tags = try extractTags(allocator, record_val);
108
112
errdefer allocator.free(tags);
···
120
124
.platform = platform,
121
125
.source_collection = collection,
122
126
.path = path,
127
+
.content_type = content_type,
123
128
};
124
129
}
125
130
···
291
296
292
297
try std.testing.expectEqualStrings("Test Post", doc.title);
293
298
try std.testing.expectEqualStrings("Hello world", doc.content);
299
+
// content_type should be extracted for platform detection (custom domain support)
300
+
try std.testing.expectEqualStrings("pub.leaflet.content", doc.content_type.?);
294
301
}
+7
backend/src/indexer.zig
+7
backend/src/indexer.zig
···
13
13
platform: []const u8,
14
14
source_collection: []const u8,
15
15
path: ?[]const u8,
16
+
content_type: ?[]const u8,
16
17
) !void {
17
18
const c = db.getClient() orelse return error.NotInitialized;
18
19
···
108
109
actual_platform = "offprint";
109
110
} else if (std.mem.indexOf(u8, base_path, "greengale.app") != null) {
110
111
actual_platform = "greengale";
112
+
} else if (content_type) |ct| {
113
+
// fallback: detect platform from content.$type for custom domains
114
+
// e.g., "pub.leaflet.content" indicates leaflet even with custom domain
115
+
if (std.mem.startsWith(u8, ct, "pub.leaflet.")) {
116
+
actual_platform = "leaflet";
117
+
}
111
118
}
112
119
}
113
120
+1
backend/src/tap.zig
+1
backend/src/tap.zig
+14
-5
docs/content-extraction.md
+14
-5
docs/content-extraction.md
···
67
67
68
68
## platform detection
69
69
70
-
collection name doesn't indicate platform for `site.standard.*` records. infer from publication `basePath`:
70
+
collection name doesn't indicate platform for `site.standard.*` records. detection order:
71
+
72
+
1. **basePath** - infer from publication basePath:
71
73
72
74
| basePath contains | platform |
73
75
|-------------------|----------|
···
75
77
| `pckt.blog` | pckt |
76
78
| `offprint.app` | offprint |
77
79
| `greengale.app` | greengale |
78
-
| (none) | other |
80
+
81
+
2. **content.$type** - fallback for custom domains (e.g., `cailean.journal.ewancroft.uk`):
82
+
83
+
| content.$type starts with | platform |
84
+
|---------------------------|----------|
85
+
| `pub.leaflet.` | leaflet |
86
+
87
+
3. if neither matches → `other`
79
88
80
89
## summary
81
90
82
91
- **pckt/offprint/greengale**: use `textContent` directly
83
92
- **leaflet**: extract from `content.pages[].blocks[].block.plaintext`
84
93
- **deduplication**: `ON CONFLICT` on `(did, rkey)` or `uri`
85
-
- **platform**: infer from publication basePath, not collection name
94
+
- **platform**: infer from basePath, fallback to content.$type for custom domains
86
95
87
96
## code references
88
97
89
-
- `backend/src/extractor.zig` - content extraction logic
90
-
- `backend/src/indexer.zig:99-112` - platform detection from basePath
98
+
- `backend/src/extractor.zig` - content extraction logic, content_type field
99
+
- `backend/src/indexer.zig:99-118` - platform detection from basePath + content_type