mirror of
https://github.com/gabehf/Koito.git
synced 2026-04-22 12:01:52 -07:00
8ce6ec494d
Adopts ListenBrainz-inspired patterns to speed up imports from ~24h to under 30 minutes for 49k scrobbles. Phase 1 - track_lookup cache table: - New migration (000006) adds persistent entity lookup cache - Maps normalized (artist, track, album) → (artist_id, album_id, track_id) - SubmitListen fast path: cache hit skips 18 DB queries → 2 queries - Cache populated after entity resolution, invalidated on merge/delete - Benefits both live scrobbles and imports Phase 2 - SaveListensBatch: - New batch listen insert using pgx CopyFrom → temp table → INSERT ON CONFLICT - Thousands of inserts per second vs one-at-a-time Phase 3 - BulkSubmitter: - Reusable import accelerator for all importers - Pre-deduplicates scrobbles by (artist, track, album) in memory - Worker pool (4 goroutines) for parallel entity creation on cache miss - Batch listen insertion via SaveListensBatch Phase 4 - Migrate importers: - Maloja, Spotify, LastFM, ListenBrainz importers use BulkSubmitter - Koito importer left as-is (already fast with pre-resolved IDs) Phase 5 - Skip image lookups during import: - GetArtistImage/GetAlbumImage calls fully skipped when SkipCacheImage=true - Background tasks (FetchMissingArtistImages/FetchMissingAlbumImages) backfill Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
76 lines
2 KiB
Go
76 lines
2 KiB
Go
package importer
|
|
|
|
import (
|
|
"context"
|
|
"encoding/json"
|
|
"fmt"
|
|
"os"
|
|
"path"
|
|
"time"
|
|
|
|
"github.com/gabehf/koito/internal/catalog"
|
|
"github.com/gabehf/koito/internal/cfg"
|
|
"github.com/gabehf/koito/internal/db"
|
|
"github.com/gabehf/koito/internal/logger"
|
|
"github.com/gabehf/koito/internal/mbz"
|
|
)
|
|
|
|
type SpotifyExportItem struct {
|
|
Timestamp time.Time `json:"ts"`
|
|
TrackName string `json:"master_metadata_track_name"`
|
|
ArtistName string `json:"master_metadata_album_artist_name"`
|
|
AlbumName string `json:"master_metadata_album_album_name"`
|
|
ReasonEnd string `json:"reason_end"`
|
|
MsPlayed int32 `json:"ms_played"`
|
|
}
|
|
|
|
func ImportSpotifyFile(ctx context.Context, store db.DB, mbzc mbz.MusicBrainzCaller, filename string) error {
|
|
l := logger.FromContext(ctx)
|
|
l.Info().Msgf("Beginning spotify import on file: %s", filename)
|
|
file, err := os.Open(path.Join(cfg.ConfigDir(), "import", filename))
|
|
if err != nil {
|
|
l.Err(err).Msgf("Failed to read import file: %s", filename)
|
|
return fmt.Errorf("ImportSpotifyFile: %w", err)
|
|
}
|
|
defer file.Close()
|
|
export := make([]SpotifyExportItem, 0)
|
|
err = json.NewDecoder(file).Decode(&export)
|
|
if err != nil {
|
|
return fmt.Errorf("ImportSpotifyFile: %w", err)
|
|
}
|
|
|
|
bs := NewBulkSubmitter(ctx, BulkSubmitterOpts{
|
|
Store: store,
|
|
Mbzc: mbzc,
|
|
})
|
|
|
|
for _, item := range export {
|
|
if item.ReasonEnd != "trackdone" {
|
|
continue
|
|
}
|
|
if !inImportTimeWindow(item.Timestamp) {
|
|
continue
|
|
}
|
|
if item.TrackName == "" || item.ArtistName == "" {
|
|
l.Debug().Msg("Skipping non-track item")
|
|
continue
|
|
}
|
|
bs.Accept(catalog.SubmitListenOpts{
|
|
MbzCaller: mbzc,
|
|
Artist: item.ArtistName,
|
|
TrackTitle: item.TrackName,
|
|
ReleaseTitle: item.AlbumName,
|
|
Duration: item.MsPlayed / 1000,
|
|
Time: item.Timestamp,
|
|
Client: "spotify",
|
|
UserID: 1,
|
|
SkipCacheImage: true,
|
|
})
|
|
}
|
|
|
|
count, err := bs.Flush()
|
|
if err != nil {
|
|
return fmt.Errorf("ImportSpotifyFile: %w", err)
|
|
}
|
|
return finishImport(ctx, filename, count)
|
|
}
|