Files
Lyra/worker/tests/test_scan_trigger.py
Jonathan 6f325d30b9 fix(worker): evict removed-seed contributions + clear scan worklist on abandon
Two row-leak bugs found in whole-branch review:

- discovery.run_discovery now prunes DiscoverySeedContribution rows whose
  seedMbid is no longer a WatchedArtist (unfollow/removal has no FK cascade)
  and recomputes the touched candidates' scores this sweep, instead of
  letting a dead seed's contribution inflate the aggregate forever.

- maybe_run_scan's exception handler around scan_chunk now calls
  clear_worklist and clears scan.id, matching the drain path. Previously
  an exception mid-chunk left the already-done rows plus the remaining
  worklist for that scan_id orphaned forever, since the next scan mints a
  fresh uuid. Also clear scan.id in the build_worklist failure handler for
  consistency.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-07-13 15:39:38 +02:00

106 lines
4.0 KiB
Python

from lyra_worker.adapters.fakes import FakeMbBrowser
from lyra_worker.main import maybe_run_scan
from lyra_worker.types import MBTarget
class FakeProbe:
def probe(self, path):
from lyra_worker.probe import ProbeResult
return ProbeResult(artist="", album="", fmt="FLAC", quality_class=3)
class FakeResolver:
def resolve(self, artist, album):
return MBTarget(artist=artist, album=album, rg_mbid=f"rg-{album}", artist_mbid="a1")
class RaisingProbe:
def probe(self, path):
raise RuntimeError("probe boom")
def _set(conn, key, value):
with conn.cursor() as cur:
cur.execute(
'INSERT INTO "Config"(key, value, secret, "updatedAt") VALUES (%s, %s, false, now()) '
'ON CONFLICT (key) DO UPDATE SET value = EXCLUDED.value, "updatedAt" = now()',
(key, value),
)
conn.commit()
def _get(conn, key):
with conn.cursor() as cur:
cur.execute('SELECT value FROM "Config" WHERE key = %s', (key,))
row = cur.fetchone()
return row[0] if row else None
def _album(tmp_path, artist, folder):
d = tmp_path / artist / folder
d.mkdir(parents=True)
(d / "01.flac").write_bytes(b"")
def _cfg(conn):
from lyra_worker.config import get_config
return get_config(conn)
def test_scan_completes_in_one_chunk_writes_result_and_clears_flag(conn, tmp_path):
_album(tmp_path, "John Mayer", "Continuum (2006)")
_set(conn, "scan.requested", "true")
# one album, default chunk size 25 -> starts + finishes in a single call
maybe_run_scan(conn, FakeResolver(), FakeProbe(), FakeMbBrowser(), _cfg(conn), dest_root=str(tmp_path))
assert _get(conn, "scan.requested") == "false" # flag cleared
assert _get(conn, "scan.inProgress") == "false" # scan finished
assert "imported" in (_get(conn, "scan.result") or "") # summary written
with conn.cursor() as cur:
cur.execute('SELECT count(*) FROM "LibraryItem"')
assert cur.fetchone()[0] == 1
def test_scan_chunks_across_iterations_and_totals_correctly(conn, tmp_path):
for i in range(3):
_album(tmp_path, "Artist", f"Album {i}")
_set(conn, "scan.requested", "true")
_set(conn, "scan.chunkSize", "2")
# first call starts the scan and processes chunk 1 (2 albums), leaving it in progress
maybe_run_scan(conn, FakeResolver(), FakeProbe(), FakeMbBrowser(), _cfg(conn), dest_root=str(tmp_path))
assert _get(conn, "scan.inProgress") == "true"
assert _get(conn, "scan.requested") == "false"
assert _get(conn, "scan.progress") == "2/0"
# second call resumes from the cursor, finishes the last album
maybe_run_scan(conn, FakeResolver(), FakeProbe(), FakeMbBrowser(), _cfg(conn), dest_root=str(tmp_path))
assert _get(conn, "scan.inProgress") == "false"
assert _get(conn, "scan.result") == "imported 3, skipped 0"
with conn.cursor() as cur:
cur.execute('SELECT count(*) FROM "LibraryItem"')
assert cur.fetchone()[0] == 3
def test_scan_chunk_exception_clears_worklist_not_just_flags(conn, tmp_path):
# scan_chunk commits per item, so if it throws mid-chunk the except block must
# still clear the worklist — otherwise the done + not-yet-processed ScanWorkItem
# rows for this scan_id are orphaned forever (the next scan mints a fresh uuid).
_album(tmp_path, "Artist", "Album")
_set(conn, "scan.requested", "true")
maybe_run_scan(conn, FakeResolver(), RaisingProbe(), FakeMbBrowser(), _cfg(conn), dest_root=str(tmp_path))
assert _get(conn, "scan.inProgress") == "false"
with conn.cursor() as cur:
cur.execute('SELECT count(*) FROM "ScanWorkItem"')
assert cur.fetchone()[0] == 0
def test_maybe_run_scan_idle_when_not_requested_or_in_progress(conn, tmp_path):
# no flags set -> no-op, no result written
maybe_run_scan(conn, FakeResolver(), FakeProbe(), FakeMbBrowser(), _cfg(conn), dest_root=str(tmp_path))
assert _get(conn, "scan.result") is None
assert _get(conn, "scan.inProgress") is None