feat(library): fingerprint every new or changed file — M400 #3905-#3907
test-go / test (push) Successful in 1m9s
test-go / integration (push) Successful in 3m28s
release / Build signed APK (releases and dev) (push) Successful in 4m38s
release / Build + push container image (push) Successful in 1m26s
release / Verify release artifacts (tag releases only) (push) Skipped
test-go / test (push) Successful in 1m9s
test-go / integration (push) Successful in 3m28s
release / Build signed APK (releases and dev) (push) Successful in 4m38s
release / Build + push container image (push) Successful in 1m26s
release / Verify release artifacts (tag releases only) (push) Skipped
Two identities per track, because they answer different questions: - audio_stream_sha256: SHA-256 of the ENCODED audio packets (ffmpeg -map 0:a -c:a copy -f hash). Equal means identical audio whatever the tags say. Measured against the #3885 pair: the two WWW files hash identically here and differently as whole files. Packets rather than decoded samples, so an ffmpeg upgrade cannot silently change every stored hash, and nothing is decoded. - chromaprint: fpcalc -raw -signed. The same recording at another bitrate or codec, for the acoustic tier. fpcalc ships in the image (libchromaprint-tools); shelled out because CGO_ENABLED=0 rules out bindings. Stored in a track_fingerprints table rather than on tracks: eight queries read tracks with SELECT *, including album pages, search and the Subsonic surface, and a ~4 KB array there would be de-TOASTed on every one of them. The scan fingerprints only bytes it has not seen (a new path, or mtime past the row's). A tag-repair pass leaves fingerprints alone, and unchanged files with no fingerprint are the backfill's job (#3908). Folding that into the skip check would re-decode the whole library on the first scan after upgrade and push a sync change per track. A failure that says nothing about the file (timeout, cancelled scan, tool not installed) is never stored, and on changed bytes it removes the old row. A tool that rejects the file stores NULL at the current version, so the backfill does not retry it every boot. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01SQ31KQpYbStyK5y58UmPLH
This commit is contained in:
@@ -0,0 +1,59 @@
|
||||
// Code generated by sqlc. DO NOT EDIT.
|
||||
// versions:
|
||||
// sqlc v1.31.1
|
||||
// source: fingerprints.sql
|
||||
|
||||
package dbq
|
||||
|
||||
import (
|
||||
"context"
|
||||
|
||||
"github.com/jackc/pgx/v5/pgtype"
|
||||
)
|
||||
|
||||
const deleteTrackFingerprint = `-- name: DeleteTrackFingerprint :exec
|
||||
DELETE FROM track_fingerprints WHERE track_id = $1
|
||||
`
|
||||
|
||||
// A file changed but could not be fingerprinted, for a reason unrelated to the
|
||||
// file. The stored row describes the OLD bytes, so it goes and the backfill
|
||||
// re-derives it — nothing may keep trusting a stale identity.
|
||||
func (q *Queries) DeleteTrackFingerprint(ctx context.Context, trackID pgtype.UUID) error {
|
||||
_, err := q.db.Exec(ctx, deleteTrackFingerprint, trackID)
|
||||
return err
|
||||
}
|
||||
|
||||
const upsertTrackFingerprint = `-- name: UpsertTrackFingerprint :exec
|
||||
INSERT INTO track_fingerprints (
|
||||
track_id, audio_stream_sha256, chromaprint, fingerprint_version
|
||||
) VALUES (
|
||||
$1, $2, $3,
|
||||
$4
|
||||
)
|
||||
ON CONFLICT (track_id) DO UPDATE SET
|
||||
audio_stream_sha256 = EXCLUDED.audio_stream_sha256,
|
||||
chromaprint = EXCLUDED.chromaprint,
|
||||
fingerprint_version = EXCLUDED.fingerprint_version,
|
||||
computed_at = now()
|
||||
`
|
||||
|
||||
type UpsertTrackFingerprintParams struct {
|
||||
TrackID pgtype.UUID
|
||||
AudioStreamSha256 []byte
|
||||
Chromaprint []int32
|
||||
FingerprintVersion int16
|
||||
}
|
||||
|
||||
// Written whenever a track's fingerprint is derived: by the scan when a file is
|
||||
// new or its bytes changed, and by the backfill (#3908) for rows derived by an
|
||||
// older method. Replaces the row wholesale — a fingerprint of the old bytes has
|
||||
// no standing once the file has changed.
|
||||
func (q *Queries) UpsertTrackFingerprint(ctx context.Context, arg UpsertTrackFingerprintParams) error {
|
||||
_, err := q.db.Exec(ctx, upsertTrackFingerprint,
|
||||
arg.TrackID,
|
||||
arg.AudioStreamSha256,
|
||||
arg.Chromaprint,
|
||||
arg.FingerprintVersion,
|
||||
)
|
||||
return err
|
||||
}
|
||||
Reference in New Issue
Block a user