fix(library): extract recording MBID → tracks.mbid; unblock LB similarity

tracks.mbid was 100% NULL: the scanner only extracted album + artist
MBIDs, never the recording MBID. The ListenBrainz similarity worker is
gated on tracks.mbid IS NOT NULL, so track_similarity could never
populate — starving For-You/radio's strongest candidate source
(lb_similar) on every library.

- mbids.go: add extractRecordingMBID (mbz.Recording / Picard
  musicbrainz_recordingid). Separate fn so extractMBIDs' signature +
  unit tests stay untouched.
- scanner.go: persist recording MBID via UpsertTrack (heals on the
  file_path conflict, so re-scans backfill for free).
- BackfillTrackMBIDs: one-shot pass mirroring BackfillMBIDs, wired as
  scan Stage 2b (idempotent via SetTrackMbidIfNull, gated by
  BackfillCap, log-only progress).
- migration 0029: tracks_mbid_unique (0002, written when the column
  was always NULL) wrongly assumes one MBID == one track. A recording
  appears on multiple releases, so rows legitimately share a recording
  MBID. Replace with a non-unique partial index. Zero-risk: column is
  100% NULL at migration time.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
2026-05-16 13:49:38 -04:00
parent 2e7b81fdfe
commit e2432caa65
8 changed files with 214 additions and 0 deletions
+53
View File
@@ -376,6 +376,41 @@ func (q *Queries) ListTracksByAlbum(ctx context.Context, arg ListTracksByAlbumPa
return items, nil
}
const listTracksMissingMbidWithPath = `-- name: ListTracksMissingMbidWithPath :many
SELECT id, file_path
FROM tracks
WHERE mbid IS NULL
ORDER BY id
LIMIT $1
`
type ListTracksMissingMbidWithPathRow struct {
ID pgtype.UUID
FilePath string
}
// Track recording-MBID backfill: tracks with NULL mbid that still have
// a file to re-read. $1 caps the batch (mirrors the album backfill).
func (q *Queries) ListTracksMissingMbidWithPath(ctx context.Context, limit int32) ([]ListTracksMissingMbidWithPathRow, error) {
rows, err := q.db.Query(ctx, listTracksMissingMbidWithPath, limit)
if err != nil {
return nil, err
}
defer rows.Close()
var items []ListTracksMissingMbidWithPathRow
for rows.Next() {
var i ListTracksMissingMbidWithPathRow
if err := rows.Scan(&i.ID, &i.FilePath); err != nil {
return nil, err
}
items = append(items, i)
}
if err := rows.Err(); err != nil {
return nil, err
}
return items, nil
}
const searchTracks = `-- name: SearchTracks :many
SELECT id, title, album_id, artist_id, track_number, disc_number, duration_ms, file_path, file_size, file_format, bitrate, mbid, genre, added_at, updated_at FROM tracks
WHERE title ILIKE '%' || $1::text || '%'
@@ -437,6 +472,24 @@ func (q *Queries) SearchTracks(ctx context.Context, arg SearchTracksParams) ([]T
return items, nil
}
const setTrackMbidIfNull = `-- name: SetTrackMbidIfNull :exec
UPDATE tracks
SET mbid = $2, updated_at = now()
WHERE id = $1 AND mbid IS NULL
`
type SetTrackMbidIfNullParams struct {
ID pgtype.UUID
Mbid *string
}
// Heal a track's recording MBID only while still NULL — idempotent, so
// re-running the backfill is a no-op for already-healed rows.
func (q *Queries) SetTrackMbidIfNull(ctx context.Context, arg SetTrackMbidIfNullParams) error {
_, err := q.db.Exec(ctx, setTrackMbidIfNull, arg.ID, arg.Mbid)
return err
}
const upsertTrack = `-- name: UpsertTrack :one
INSERT INTO tracks (
title, album_id, artist_id, track_number, disc_number,