search for standard sites
pub-search.waow.tech
search
zig
blog
atproto
fix: extract base_path from site.standard publication url field
+19
-4
+19
-4
backend/src/tap.zig
+19
-4
backend/src/tap.zig
···
268
268
std.debug.print("indexed document: {s} [{s}] ({} chars, {} tags)\n", .{ uri, doc.platformName(), doc.content.len, doc.tags.len });
269
269
}
270
270
271
-
fn processPublication(allocator: Allocator, uri: []const u8, did: []const u8, rkey: []const u8, record: json.ObjectMap) !void {
271
+
fn processPublication(_: Allocator, uri: []const u8, did: []const u8, rkey: []const u8, record: json.ObjectMap) !void {
272
272
const record_val: json.Value = .{ .object = record };
273
-
const pub_data = zat.json.extractAt(LeafletPublication, allocator, record_val, .{}) catch return;
273
+
274
+
// extract required field
275
+
const name = zat.json.getString(record_val, "name") orelse return;
276
+
const description = zat.json.getString(record_val, "description");
277
+
278
+
// base_path: try leaflet's "base_path", then site.standard's "url"
279
+
// url is full URL like "https://devlog.pckt.blog", we need just the host
280
+
const base_path = zat.json.getString(record_val, "base_path") orelse
281
+
stripUrlScheme(zat.json.getString(record_val, "url"));
282
+
283
+
try indexer.insertPublication(uri, did, rkey, name, description, base_path);
284
+
std.debug.print("indexed publication: {s} (base_path: {s})\n", .{ uri, base_path orelse "none" });
285
+
}
274
286
275
-
try indexer.insertPublication(uri, did, rkey, pub_data.name, pub_data.description, pub_data.base_path);
276
-
std.debug.print("indexed publication: {s} (base_path: {s})\n", .{ uri, pub_data.base_path orelse "none" });
287
+
fn stripUrlScheme(url: ?[]const u8) ?[]const u8 {
288
+
const u = url orelse return null;
289
+
if (mem.startsWith(u8, u, "https://")) return u["https://".len..];
290
+
if (mem.startsWith(u8, u, "http://")) return u["http://".len..];
291
+
return u;
277
292
}