feat: MusicBrainz-aware intake and completeness check against canonical track count

worker/tests/test_intake.py

@@ -0,0 +1,78 @@
+from lyra_worker.adapters.youtube import YouTubeAdapter
+from lyra_worker.claim import claim_next
+from lyra_worker.pipeline import run_pipeline
+from lyra_worker.types import MBTarget
+from tests.conftest import insert_request
+from tests.test_youtube_adapter import FakeYtClient
+
+
+class FakeResolver:
+    def __init__(self, target):
+        self._target = target
+
+    def resolve(self, artist, album):
+        return self._target
+
+
+def _job_state(conn, job_id):
+    with conn.cursor() as cur:
+        cur.execute('SELECT state FROM "Job" WHERE id = %s', (job_id,))
+        return cur.fetchone()[0]
+
+
+def test_single_track_download_rejected_against_musicbrainz_count(conn):
+    # MusicBrainz says Continuum has 12 tracks; a 1-track YouTube "full album" video must be rejected.
+    resolver = FakeResolver(MBTarget(artist="John Mayer", album="Continuum", track_count=12))
+    yt = [{"source_ref": "yt1", "title": "Continuum", "artist": "John Mayer", "track_count": 1}]
+    # FakeYtClient.download reports the same 1-track count for the single-video candidate:
+    client = FakeYtClient(results=yt)
+    client.download = lambda source_ref, dest, on_progress: (on_progress(1.0), {"track_count": 1, "path": dest})[1]
+
+    job_id = insert_request(conn, artist="john mayer", album="continuum")
+    claim_next(conn)
+    run_pipeline(conn, job_id, [YouTubeAdapter(client)], resolver=resolver, dest_root="/tmp/lib")
+
+    assert _job_state(conn, job_id) == "needs_attention"
+
+
+def test_complete_download_imports_with_musicbrainz_count(conn):
+    resolver = FakeResolver(MBTarget(artist="John Mayer", album="Continuum", track_count=12))
+    yt = [{"source_ref": "yt1", "title": "Continuum", "artist": "John Mayer", "track_count": 12}]
+    client = FakeYtClient(results=yt)
+    client.download = lambda source_ref, dest, on_progress: (on_progress(1.0), {"track_count": 12, "path": dest})[1]
+
+    job_id = insert_request(conn, artist="john mayer", album="continuum")
+    claim_next(conn)
+    run_pipeline(conn, job_id, [YouTubeAdapter(client)], resolver=resolver, dest_root="/tmp/lib")
+
+    assert _job_state(conn, job_id) == "imported"
+    with conn.cursor() as cur:
+        # canonical artist/album from MusicBrainz are what get stored
+        cur.execute('SELECT artist, album FROM "LibraryItem"')
+        assert cur.fetchone() == ("John Mayer", "Continuum")
+
+
+def test_no_resolver_preserves_legacy_behavior(conn):
+    # Without a resolver, target.track_count stays None and the candidate's own count is used.
+    yt = [{"source_ref": "yt1", "title": "Continuum", "artist": "John Mayer", "track_count": 1}]
+    client = FakeYtClient(results=yt)
+    client.download = lambda source_ref, dest, on_progress: (on_progress(1.0), {"track_count": 1, "path": dest})[1]
+
+    job_id = insert_request(conn, artist="John Mayer", album="Continuum")
+    claim_next(conn)
+    run_pipeline(conn, job_id, [YouTubeAdapter(client)], dest_root="/tmp/lib")  # no resolver
+
+    assert _job_state(conn, job_id) == "imported"  # 1 == 1, passes as before
+
+
+def test_resolver_returning_none_falls_back_to_request(conn):
+    resolver = FakeResolver(None)
+    yt = [{"source_ref": "yt1", "title": "Continuum", "artist": "John Mayer", "track_count": 1}]
+    client = FakeYtClient(results=yt)
+    client.download = lambda source_ref, dest, on_progress: (on_progress(1.0), {"track_count": 1, "path": dest})[1]
+
+    job_id = insert_request(conn, artist="John Mayer", album="Continuum")
+    claim_next(conn)
+    run_pipeline(conn, job_id, [YouTubeAdapter(client)], resolver=resolver, dest_root="/tmp/lib")
+
+    assert _job_state(conn, job_id) == "imported"  # falls back to raw target, 1==1