Jonathan
62b60e3dae
scan_chunk resolves album folders whose (artist, album) sorts after a cursor, up to a limit, returning (new_cursor, imported, skipped, done). scan_library becomes the unbounded case (limit=None), so its behavior and tests are unchanged. Idempotent: all writes are ON CONFLICT, so an overlapping/repeated cursor is safe. Enables chunked scanning in the loop. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
82 lines
3.9 KiB
Python
82 lines
3.9 KiB
Python
from lyra_worker.adapters.fakes import FakeMbBrowser
|
|
from lyra_worker.browser import ReleaseGroupInfo
|
|
from lyra_worker.scan import scan_chunk
|
|
from lyra_worker.types import MBTarget
|
|
from tests.test_scan import FakeProbe, FakeResolver, _album, _counts
|
|
|
|
|
|
def _tree(tmp_path):
|
|
"""Three albums across two artists, in nested-sorted order:
|
|
Artist A/Alpha, Artist A/Beta, Artist B/Gamma."""
|
|
_album(tmp_path, "Artist A", "Alpha (2001)")
|
|
_album(tmp_path, "Artist A", "Beta (2002)")
|
|
_album(tmp_path, "Artist B", "Gamma (2003)")
|
|
resolver = FakeResolver({
|
|
("Artist A", "Alpha"): MBTarget(artist="Artist A", album="Alpha", year=2001, rg_mbid="rg-a1", artist_mbid="ma"),
|
|
("Artist A", "Beta"): MBTarget(artist="Artist A", album="Beta", year=2002, rg_mbid="rg-a2", artist_mbid="ma"),
|
|
("Artist B", "Gamma"): MBTarget(artist="Artist B", album="Gamma", year=2003, rg_mbid="rg-b1", artist_mbid="mb"),
|
|
})
|
|
browser = FakeMbBrowser(releases={
|
|
"ma": [ReleaseGroupInfo("rg-a1", "Alpha", "Album", (), "2001"),
|
|
ReleaseGroupInfo("rg-a2", "Beta", "Album", (), "2002")],
|
|
"mb": [ReleaseGroupInfo("rg-b1", "Gamma", "Album", (), "2003")],
|
|
})
|
|
return resolver, browser
|
|
|
|
|
|
def test_scan_chunk_respects_limit_and_returns_cursor(conn, tmp_path):
|
|
resolver, browser = _tree(tmp_path)
|
|
cursor, imported, skipped, done = scan_chunk(
|
|
conn, resolver, FakeProbe(quality_class=2), browser, str(tmp_path), cursor="", limit=2)
|
|
assert (imported, skipped, done) == (2, 0, False) # processed 2 of 3, more remain
|
|
assert cursor == "Artist A/Beta (2002)" # last processed key
|
|
with conn.cursor() as cur:
|
|
cur.execute('SELECT count(*) FROM "LibraryItem"')
|
|
assert cur.fetchone()[0] == 2
|
|
|
|
|
|
def test_scan_chunk_resumes_from_cursor(conn, tmp_path):
|
|
resolver, browser = _tree(tmp_path)
|
|
cursor, imported, skipped, done = scan_chunk(
|
|
conn, resolver, FakeProbe(quality_class=2), browser, str(tmp_path),
|
|
cursor="Artist A/Beta (2002)", limit=25)
|
|
assert (imported, skipped, done) == (1, 0, True) # only Gamma remains
|
|
assert cursor == "Artist B/Gamma (2003)"
|
|
with conn.cursor() as cur:
|
|
cur.execute('SELECT album FROM "LibraryItem"')
|
|
assert cur.fetchall() == [("Gamma",)] # only Gamma imported
|
|
|
|
|
|
def test_scan_chunk_cursor_past_end_is_noop(conn, tmp_path):
|
|
resolver, browser = _tree(tmp_path)
|
|
cursor, imported, skipped, done = scan_chunk(
|
|
conn, resolver, FakeProbe(), browser, str(tmp_path), cursor="zzzz/zzzz", limit=10)
|
|
assert (imported, skipped, done) == (0, 0, True)
|
|
assert cursor == "zzzz/zzzz" # unchanged
|
|
assert _counts(conn)["LibraryItem"] == 0
|
|
|
|
|
|
def test_scan_chunk_splits_artist_across_chunks_idempotently(conn, tmp_path):
|
|
# limit=1 forces Artist A's two albums into separate chunks, re-browsing its
|
|
# discography — which must stay idempotent (ON CONFLICT) and total the same as one scan.
|
|
resolver, browser = _tree(tmp_path)
|
|
cursor, done, total_i, total_s, guard = "", False, 0, 0, 0
|
|
while not done and guard < 10:
|
|
cursor, i, s, done = scan_chunk(
|
|
conn, resolver, FakeProbe(quality_class=2), browser, str(tmp_path), cursor=cursor, limit=1)
|
|
total_i += i
|
|
total_s += s
|
|
guard += 1
|
|
assert (total_i, total_s) == (3, 0)
|
|
assert guard == 3 # three albums, one per chunk, then done
|
|
assert _counts(conn) == {"LibraryItem": 3, "MonitoredRelease": 3, "WatchedArtist": 2}
|
|
|
|
|
|
def test_scan_chunk_unbounded_matches_full_walk(conn, tmp_path):
|
|
resolver, browser = _tree(tmp_path)
|
|
cursor, imported, skipped, done = scan_chunk(
|
|
conn, resolver, FakeProbe(quality_class=2), browser, str(tmp_path), cursor="", limit=None)
|
|
assert (imported, skipped, done) == (3, 0, True)
|
|
assert cursor == "Artist B/Gamma (2003)"
|
|
assert _counts(conn) == {"LibraryItem": 3, "MonitoredRelease": 3, "WatchedArtist": 2}
|