Canonical findings: add artist image (guarded, schema-safe)

Findings now carry artist_thumb_url alongside album_thumb_url (same key the
track-repair findings use, so the findings UI already renders it).

Fetched via a guarded _lookup_artist_thumb() — checks the artists table has a
thumb_url column first and swallows any error — rather than adding ar.thumb_url
to the shared load_album_and_tracks SELECT. The shared-loader approach was
tried first and REVERTED: it crashed reorganize on schemas whose artists table
has no thumb_url column (caught by 40 orchestrator tests). The lookup only runs
for albums that actually resolve, so it adds no cost to the no-source-id
short-circuit majority.

Tests: orchestration test asserts artist_name + album_thumb_url + artist_thumb_url
flow through. 47 canonical + 104 canonical/reorganize regression tests pass.
This commit is contained in:
BoulderBadgeDad 2026-06-02 14:04:09 -07:00
parent ec8091caad
commit 03d099fb1d
2 changed files with 54 additions and 0 deletions

View file

@ -162,6 +162,28 @@ def default_fetch_tracklist(source: str, album_id: str) -> Optional[List[Dict[st
return out or None
def _lookup_artist_thumb(db, artist_id) -> Optional[str]:
"""Best-effort artist thumb URL by id. Returns None on missing column / any
error (the artists table doesn't have thumb_url in every schema)."""
if not artist_id:
return None
conn = None
try:
conn = db._get_connection()
cursor = conn.cursor()
cursor.execute("PRAGMA table_info(artists)")
if 'thumb_url' not in {r[1] for r in cursor.fetchall()}:
return None
cursor.execute("SELECT thumb_url FROM artists WHERE id = ?", (str(artist_id),))
row = cursor.fetchone()
return (row[0] or None) if row else None
except Exception:
return None
finally:
if conn:
conn.close()
def resolve_and_store_canonical_for_album(
db,
album_id,
@ -223,6 +245,12 @@ def resolve_and_store_canonical_for_album(
result['artist_name'] = album_data.get('artist_name') or ''
if album_data.get('thumb_url'):
result['album_thumb_url'] = album_data['thumb_url']
# Artist thumb via a guarded lookup (not the shared album loader — some
# schemas have no artists.thumb_url column). Only runs for resolved
# albums, so no cost on the no-source-id short-circuit majority.
artist_thumb = _lookup_artist_thumb(db, album_data.get('artist_id'))
if artist_thumb:
result['artist_thumb_url'] = artist_thumb
if store:
db.set_album_canonical(album_id, result['source'], result['album_id'], result['score'])
return result

View file

@ -70,6 +70,32 @@ def test_default_mode_prefers_active_source(tmp_path):
assert out["source"] == "spotify" # active source preferred
def test_result_includes_artist_and_album_context(tmp_path):
db = MusicDatabase(str(tmp_path / "m.db"))
conn = db._get_connection()
cur = conn.cursor()
cur.execute("INSERT INTO artists (id, name, thumb_url) VALUES ('art1', 'Imagine Dragons', 'http://artist.jpg')")
cur.execute(
"INSERT INTO albums (id, title, artist_id, thumb_url, spotify_album_id) "
"VALUES ('alb1', 'Evolve', 'art1', 'http://album.jpg', 'sp1')"
)
for i in range(11):
cur.execute(
"INSERT INTO tracks (id, album_id, artist_id, title, track_number, duration) "
"VALUES (?, 'alb1', 'art1', ?, ?, ?)",
(f"t{i}", f"Song {i+1}", i + 1, 180_000 + i * 10_000),
)
conn.commit()
conn.close()
out = resolve_and_store_canonical_for_album(
db, "alb1", fetch_tracklist=lambda s, a: STD, source_priority=["spotify"],
)
assert out["artist_name"] == "Imagine Dragons"
assert out["album_thumb_url"] == "http://album.jpg"
assert out["artist_thumb_url"] == "http://artist.jpg"
def test_resolve_returns_none_when_album_has_no_source_ids(tmp_path):
db = MusicDatabase(str(tmp_path / "m.db"))
album_id = _seed(db, spotify=None, deezer=None)