minstrel/internal/library/moved.go

package library

import (
	"context"

	"github.com/jackc/pgx/v5/pgtype"

	"git.fabledsword.com/bvandeusen/minstrel/internal/db/dbq"
	syncpkg "git.fabledsword.com/bvandeusen/minstrel/internal/sync"
)

// Move detection (#2528).
//
// Track identity is file_path: UpsertTrack conflicts on it, and the reconcile
// pass in reconcile.go clears a missing mark when the walk sees that same path
// again. So a file that comes back exactly where it was restores cleanly, but a
// file that comes back RENAMED or in a different directory looked, to the
// scanner, like a deletion plus an unrelated new track:
//
//   - the old row stayed marked missing, holding the like and every play_event
//   - a fresh row appeared with no history
//   - nothing connected them
//
// A liked song read as unliked after a retag, its play count reset to zero, and
// Rediscover could offer it as a discovery. All silently. Renumbering an album
// was enough to do it — which is exactly what happened on the operator's copy of
// Minutes to Midnight.
//
// The fix adopts the existing row rather than inserting: re-point its file_path
// at the new location and clear the mark. The caller's normal UpsertTrack then
// conflicts on file_path and updates THAT row, so the track id survives and
// likes, plays and playlist memberships travel with it. Clients see an update
// rather than a delete-and-create, so no cache churn either.
//
// Only rows already marked missing are eligible. A row whose file is present
// elsewhere is a duplicate, not a move, and re-pointing it would corrupt the
// copy that still exists. That constraint is what makes this safe, and the
// marking added in #2523 is what makes it expressible.

// trackAdopter is the slice of dbq.Queries move detection needs, narrowed so the
// match/ambiguity logic can be tested against a fake.
type trackAdopter interface {
	FindMissingTrackByMbid(ctx context.Context, mbid string) ([]dbq.FindMissingTrackByMbidRow, error)
	FindMissingTrackByAudioHash(ctx context.Context, audioStreamSha256 []byte) ([]dbq.FindMissingTrackByAudioHashRow, error)
	AdoptTrackPath(ctx context.Context, arg dbq.AdoptTrackPathParams) (int64, error)
}

// adoptMovedTrack looks for a missing row that is the same recording as the file
// at newPath and re-points it there. Reports whether a row was adopted.
//
// Never returns an error: failing to detect a move is a missed optimisation, not
// a broken scan. The caller carries on and inserts a fresh row, which is the
// pre-#2528 behaviour.
func (s *Scanner) adoptMovedTrack(
	ctx context.Context, q trackAdopter, newPath string,
	audioHash []byte, recordingMBID string,
) bool {
	// MBID first. It identifies the recording rather than the bytes, so it
	// survives a re-encode that the audio hash cannot.
	if recordingMBID != "" {
		rows, err := q.FindMissingTrackByMbid(ctx, recordingMBID)
		if err != nil {
			s.logger.Warn("library scan: move lookup by mbid failed",
				"path", newPath, "err", err)
		} else if c, ok := s.uniqueMatch(rowsFromMbid(rows), newPath, "mbid"); ok {
			return s.adopt(ctx, q, c, newPath, "mbid")
		}
	}

	// Audio-hash fallback for untagged files (#3914): the encoded audio itself,
	// which a rename, a move or a retag leaves unchanged. Absent when the hash
	// could not be taken, and then nothing is matched — an empty hash must never
	// be looked up, or every unhashable file would pair with every other.
	if len(audioHash) > 0 {
		rows, err := q.FindMissingTrackByAudioHash(ctx, audioHash)
		if err != nil {
			s.logger.Warn("library scan: move lookup by audio hash failed",
				"path", newPath, "err", err)
		} else if c, ok := s.uniqueMatch(rowsFromAudioHash(rows), newPath, "audio_hash"); ok {
			return s.adopt(ctx, q, c, newPath, "audio_hash")
		}
	}

	return false
}

// candidate is the shared shape of both lookups, so uniqueMatch is written once.
type candidate struct {
	id       pgtype.UUID
	filePath string
}

func rowsFromMbid(rows []dbq.FindMissingTrackByMbidRow) []candidate {
	out := make([]candidate, 0, len(rows))
	for _, r := range rows {
		out = append(out, candidate{id: r.ID, filePath: r.FilePath})
	}
	return out
}

func rowsFromAudioHash(rows []dbq.FindMissingTrackByAudioHashRow) []candidate {
	out := make([]candidate, 0, len(rows))
	for _, r := range rows {
		out = append(out, candidate{id: r.ID, filePath: r.FilePath})
	}
	return out
}

// uniqueMatch requires exactly one candidate. Adopting an arbitrary row out of
// several would attach this file's future history to a coin flip, which is worse
// than starting a fresh row — a fork is recoverable later, a wrong merge isn't.
// Libraries with genuine duplicates hit this, so it's logged rather than silent.
func (s *Scanner) uniqueMatch(
	cands []candidate, newPath, via string,
) (candidate, bool) {
	switch len(cands) {
	case 0:
		return candidate{}, false
	case 1:
		return cands[0], true
	default:
		s.logger.Info("library scan: ambiguous move match, inserting a new track instead",
			"path", newPath, "via", via, "candidates", len(cands))
		return candidate{}, false
	}
}

func (s *Scanner) adopt(
	ctx context.Context, q trackAdopter, c candidate, newPath, via string,
) bool {
	n, err := q.AdoptTrackPath(ctx, dbq.AdoptTrackPathParams{ID: c.id, FilePath: newPath})
	if err != nil {
		// A unique violation on file_path means something else claimed this path
		// first. Fall through to a normal insert rather than failing the file.
		s.logger.Warn("library scan: adopting moved track failed",
			"path", newPath, "via", via, "err", err)
		return false
	}
	if n == 0 {
		// Lost the race: another file adopted this row between lookup and
		// update, so its mark was already cleared.
		return false
	}
	// Logged with both paths: this is the operator's only window onto a
	// reorganisation being understood as a move rather than a new track.
	s.logger.Info("library scan: track moved, history preserved",
		"from", c.filePath, "to", newPath, "via", via, "track_id", syncpkg.FormatUUID(c.id))
	return true
}