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:
@@ -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,
|
||||
|
||||
@@ -0,0 +1,6 @@
|
||||
-- Reverts to the unique partial index. This FAILS if any recording
|
||||
-- MBID is shared across releases in the library (the exact case 0029
|
||||
-- exists to allow) — dedupe tracks.mbid before rolling back.
|
||||
|
||||
DROP INDEX IF EXISTS tracks_mbid_idx;
|
||||
CREATE UNIQUE INDEX tracks_mbid_unique ON tracks (mbid) WHERE mbid IS NOT NULL;
|
||||
@@ -0,0 +1,15 @@
|
||||
-- tracks.mbid holds the MusicBrainz *recording* MBID — the id the
|
||||
-- ListenBrainz similarity pipeline (ListPlayedTracksNeedingSimilarity,
|
||||
-- GetTracksByMBIDs) matches on. A single recording legitimately appears
|
||||
-- on multiple releases (album + compilation + single), so multiple
|
||||
-- tracks rows share one recording MBID.
|
||||
--
|
||||
-- tracks_mbid_unique (added in 0002, when this column was always NULL
|
||||
-- and never populated) wrongly assumes one MBID == one track. Now that
|
||||
-- the scanner extracts the recording MBID, that uniqueness throws
|
||||
-- 23505 for any recording present on >1 release. Replace it with a
|
||||
-- non-unique partial index serving the same lookups. Zero-risk: the
|
||||
-- column is 100% NULL at migration time.
|
||||
|
||||
DROP INDEX IF EXISTS tracks_mbid_unique;
|
||||
CREATE INDEX IF NOT EXISTS tracks_mbid_idx ON tracks (mbid) WHERE mbid IS NOT NULL;
|
||||
@@ -19,6 +19,22 @@ ON CONFLICT (file_path) DO UPDATE SET
|
||||
updated_at = now()
|
||||
RETURNING *;
|
||||
|
||||
-- name: ListTracksMissingMbidWithPath :many
|
||||
-- Track recording-MBID backfill: tracks with NULL mbid that still have
|
||||
-- a file to re-read. $1 caps the batch (mirrors the album backfill).
|
||||
SELECT id, file_path
|
||||
FROM tracks
|
||||
WHERE mbid IS NULL
|
||||
ORDER BY id
|
||||
LIMIT $1;
|
||||
|
||||
-- name: SetTrackMbidIfNull :exec
|
||||
-- Heal a track's recording MBID only while still NULL — idempotent, so
|
||||
-- re-running the backfill is a no-op for already-healed rows.
|
||||
UPDATE tracks
|
||||
SET mbid = $2, updated_at = now()
|
||||
WHERE id = $1 AND mbid IS NULL;
|
||||
|
||||
-- name: GetTrackByID :one
|
||||
SELECT * FROM tracks WHERE id = $1;
|
||||
|
||||
|
||||
@@ -167,3 +167,96 @@ func readMBIDsForFile(path string, logger *slog.Logger) (albumMBID, artistMBID s
|
||||
}
|
||||
return extractMBIDs(meta)
|
||||
}
|
||||
|
||||
// BackfillTrackMBIDsResult tallies the track recording-MBID backfill.
|
||||
type BackfillTrackMBIDsResult struct {
|
||||
Processed int // Tracks considered (mbid IS NULL).
|
||||
Healed int // Tracks whose recording MBID we set.
|
||||
Skipped int // Tracks whose file was missing / untagged / write failed.
|
||||
}
|
||||
|
||||
// BackfillTrackMBIDs walks tracks with NULL mbid, re-reads each file's
|
||||
// tags, and persists the MusicBrainz recording MBID. This is the
|
||||
// counterpart to BackfillMBIDs (which heals album/artist MBIDs); it
|
||||
// unblocks the ListenBrainz similarity pipeline, which is gated on
|
||||
// tracks.mbid IS NOT NULL.
|
||||
//
|
||||
// Idempotent via SetTrackMbidIfNull: re-running costs the same N file
|
||||
// reads but is a no-op for already-healed rows. limit caps one call;
|
||||
// pass -1 for unbounded (caller normally batches per scan).
|
||||
func BackfillTrackMBIDs(ctx context.Context, pool *pgxpool.Pool, logger *slog.Logger,
|
||||
limit int, progressCb func(BackfillTrackMBIDsResult)) (BackfillTrackMBIDsResult, error) {
|
||||
q := dbq.New(pool)
|
||||
queryLimit := int32(limit)
|
||||
if limit < 0 {
|
||||
queryLimit = 1<<31 - 1 // effectively unbounded
|
||||
}
|
||||
|
||||
rows, err := q.ListTracksMissingMbidWithPath(ctx, queryLimit)
|
||||
if err != nil {
|
||||
return BackfillTrackMBIDsResult{}, fmt.Errorf("list tracks missing mbid: %w", err)
|
||||
}
|
||||
|
||||
var res BackfillTrackMBIDsResult
|
||||
for i, r := range rows {
|
||||
if ctx.Err() != nil {
|
||||
return res, ctx.Err()
|
||||
}
|
||||
res.Processed++
|
||||
|
||||
rec := readRecordingMBIDForFile(r.FilePath, logger)
|
||||
if rec == "" {
|
||||
res.Skipped++
|
||||
if progressCb != nil {
|
||||
progressCb(res)
|
||||
}
|
||||
continue
|
||||
}
|
||||
|
||||
m := rec
|
||||
if uerr := q.SetTrackMbidIfNull(ctx, dbq.SetTrackMbidIfNullParams{
|
||||
ID: r.ID, Mbid: &m,
|
||||
}); uerr != nil {
|
||||
logger.Warn("track mbid backfill: set failed",
|
||||
"track_id", r.ID, "err", uerr)
|
||||
res.Skipped++
|
||||
if progressCb != nil {
|
||||
progressCb(res)
|
||||
}
|
||||
continue
|
||||
}
|
||||
|
||||
res.Healed++
|
||||
if (i+1)%500 == 0 {
|
||||
logger.Info("track mbid backfill progress",
|
||||
"processed", res.Processed, "healed", res.Healed, "skipped", res.Skipped)
|
||||
}
|
||||
if progressCb != nil {
|
||||
progressCb(res)
|
||||
}
|
||||
}
|
||||
|
||||
logger.Info("track mbid backfill complete",
|
||||
"processed", res.Processed, "healed", res.Healed, "skipped", res.Skipped)
|
||||
return res, nil
|
||||
}
|
||||
|
||||
// readRecordingMBIDForFile opens one audio file and returns its
|
||||
// MusicBrainz recording MBID, or "" when the file can't be opened, the
|
||||
// tag read fails, or the tag is absent. Errors are logged at Warn, not
|
||||
// propagated — one broken file must not halt the backfill.
|
||||
func readRecordingMBIDForFile(path string, logger *slog.Logger) string {
|
||||
f, err := os.Open(path)
|
||||
if err != nil {
|
||||
logger.Warn("track mbid backfill: open failed", "path", path, "err", err)
|
||||
return ""
|
||||
}
|
||||
defer func() { _ = f.Close() }()
|
||||
|
||||
meta, err := tag.ReadFrom(f)
|
||||
if err != nil {
|
||||
logger.Warn("track mbid backfill: tag read failed", "path", path, "err", err)
|
||||
return ""
|
||||
}
|
||||
return extractRecordingMBID(meta)
|
||||
}
|
||||
|
||||
@@ -27,6 +27,19 @@ func extractMBIDs(m tag.Metadata) (albumMBID, artistMBID string) {
|
||||
return cleanMBID(info.Get(mbz.Album)), cleanMBID(info.Get(mbz.Artist))
|
||||
}
|
||||
|
||||
// extractRecordingMBID reads the MusicBrainz *recording* ID — Picard's
|
||||
// musicbrainz_recordingid, surfaced by dhowden/tag as mbz.Recording
|
||||
// (tag display name "MusicBrainz Track Id"). This is the id ListenBrainz
|
||||
// /explore/similar-recordings keys on and what tracks.mbid stores.
|
||||
//
|
||||
// Deliberately NOT mbz.Track ("MusicBrainz Release Track Id"): that is
|
||||
// per-release-track, whereas similarity is per-recording. Kept separate
|
||||
// from extractMBIDs so its existing (album, artist) signature and unit
|
||||
// tests stay untouched.
|
||||
func extractRecordingMBID(m tag.Metadata) string {
|
||||
return cleanMBID(mbz.Extract(m).Get(mbz.Recording))
|
||||
}
|
||||
|
||||
func cleanMBID(s string) string {
|
||||
if s == "" {
|
||||
return ""
|
||||
|
||||
@@ -142,6 +142,7 @@ func (s *Scanner) scanFile(ctx context.Context, q *dbq.Queries, path string, sta
|
||||
return fmt.Errorf("tag read: %w", err)
|
||||
}
|
||||
albumMBID, artistMBID := extractMBIDs(meta)
|
||||
recordingMBID := extractRecordingMBID(meta)
|
||||
|
||||
artistName := meta.Artist()
|
||||
if artistName == "" {
|
||||
@@ -195,6 +196,13 @@ func (s *Scanner) scanFile(ctx context.Context, q *dbq.Queries, path string, sta
|
||||
if g := meta.Genre(); g != "" {
|
||||
params.Genre = &g
|
||||
}
|
||||
// Recording MBID feeds the ListenBrainz similarity pipeline.
|
||||
// UpsertTrack heals mbid on the file_path conflict, so a re-scan
|
||||
// of a previously-untagged-into-DB track backfills it for free.
|
||||
if recordingMBID != "" {
|
||||
m := recordingMBID
|
||||
params.Mbid = &m
|
||||
}
|
||||
|
||||
track, err := q.UpsertTrack(ctx, params)
|
||||
if err != nil {
|
||||
|
||||
@@ -154,6 +154,16 @@ func RunScan(
|
||||
}
|
||||
}
|
||||
|
||||
// Stage 2b: track recording-MBID backfill. Unblocks the ListenBrainz
|
||||
// similarity pipeline (gated on tracks.mbid IS NOT NULL). Log-only
|
||||
// progress — no scan_runs jsonb column to avoid a schema addition;
|
||||
// it's idempotent and reruns each scan until every file is healed.
|
||||
if cfg.BackfillCap != 0 {
|
||||
if _, tberr := BackfillTrackMBIDs(ctx, pool, logger, cfg.BackfillCap, nil); tberr != nil {
|
||||
captureErr("track_mbid_backfill", tberr)
|
||||
}
|
||||
}
|
||||
|
||||
// Stage 3: cover enrichment.
|
||||
if enricher != nil && cfg.EnrichCap != 0 {
|
||||
var lastP, lastS, lastF int
|
||||
|
||||
Reference in New Issue
Block a user