feat(server/m7-scan-progress): wire stagePublisher into 4 scan stages

Each of the 4 stage workers (library walk, MBID backfill, cover
enrich, artist art enrich) gains a progressCb parameter that
receives a snapshot of the current running state per item processed.
The orchestrator stores the snapshot in a local var that the
publisher's marshal closure reads at flush time.

scanrun.go's 4 stage blocks are rewritten to construct one publisher
per stage, pass a Tick-firing closure to the worker as progressCb,
and call Flush() after the worker returns (routing any persist error
to captureErr — preserves today's diagnostic behavior).

The previous post-stage UpdateScanRun* calls are removed; the
publisher's Flush handles the final write. Cadence: every 500 items
OR every 1s, whichever fires first.

Outside-orchestrator callers (scanner_test.go, enricher_test.go)
pass nil for progressCb — no-op behavior preserved for tests that
don't need progress observability.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
2026-05-06 21:14:50 -04:00
parent 7b9ea131a2
commit 3e9e46f190
7 changed files with 141 additions and 45 deletions
+11 -1
View File
@@ -135,7 +135,8 @@ func (e *Enricher) recordArtistArt(ctx context.Context, artistID pgtype.UUID, th
// EnrichArtistBatch drains up to limit artists whose eligibility loop
// determines they need processing. Iterates serially. Returns
// per-batch tallies for the orchestrator's scan-run record.
func (e *Enricher) EnrichArtistBatch(ctx context.Context, limit int, dataDir string) (processed, succeeded, failed int, err error) {
func (e *Enricher) EnrichArtistBatch(ctx context.Context, limit int, dataDir string,
progressCb func(processed, succeeded, failed int)) (processed, succeeded, failed int, err error) {
if limit <= 0 {
return 0, 0, 0, nil
}
@@ -156,12 +157,18 @@ func (e *Enricher) EnrichArtistBatch(ctx context.Context, limit int, dataDir str
e.logger.Warn("coverart: artist batch entry failed",
"artist_id", uuidString(id), "err", eerr)
failed++
if progressCb != nil {
progressCb(processed, succeeded, failed)
}
continue
}
// Re-read to classify.
row, rerr := q.GetArtistByID(ctx, id)
if rerr != nil {
failed++
if progressCb != nil {
progressCb(processed, succeeded, failed)
}
continue
}
if row.ArtistArtSource != nil &&
@@ -171,6 +178,9 @@ func (e *Enricher) EnrichArtistBatch(ctx context.Context, limit int, dataDir str
} else {
failed++
}
if progressCb != nil {
progressCb(processed, succeeded, failed)
}
}
return processed, succeeded, failed, nil
}
+11 -1
View File
@@ -146,7 +146,8 @@ func (e *Enricher) recordAlbumCover(ctx context.Context, albumID pgtype.UUID, pa
// EnrichBatch drains up to limit albums whose eligibility loop
// determines they need processing. Iterates serially. Returns
// per-batch tallies for the orchestrator's scan-run record.
func (e *Enricher) EnrichBatch(ctx context.Context, limit int) (processed, succeeded, failed int, err error) {
func (e *Enricher) EnrichBatch(ctx context.Context, limit int,
progressCb func(processed, succeeded, failed int)) (processed, succeeded, failed int, err error) {
if limit <= 0 {
return 0, 0, 0, nil
}
@@ -167,12 +168,18 @@ func (e *Enricher) EnrichBatch(ctx context.Context, limit int) (processed, succe
e.logger.Warn("coverart: batch entry failed",
"album_id", uuidString(id), "err", eerr)
failed++
if progressCb != nil {
progressCb(processed, succeeded, failed)
}
continue
}
// Re-read to classify.
row, rerr := q.GetAlbumWithFirstTrackPath(ctx, id)
if rerr != nil {
failed++
if progressCb != nil {
progressCb(processed, succeeded, failed)
}
continue
}
if row.CoverArtSource != nil &&
@@ -184,6 +191,9 @@ func (e *Enricher) EnrichBatch(ctx context.Context, limit int) (processed, succe
} else {
failed++
}
if progressCb != nil {
progressCb(processed, succeeded, failed)
}
}
return processed, succeeded, failed, nil
}
+1 -1
View File
@@ -263,7 +263,7 @@ func TestEnrichBatch_DrainsNullSourceOnly(t *testing.T) {
}
e := newTestEnricher(t, pool)
processed, _, _, err := e.EnrichBatch(context.Background(), 100)
processed, _, _, err := e.EnrichBatch(context.Background(), 100, nil)
if err != nil {
t.Fatalf("batch: %v", err)
}
+14 -1
View File
@@ -46,7 +46,8 @@ type BackfillMBIDsResult struct {
// limit caps how many albums are processed in one call. Pass -1 for no
// cap. The caller normally batches (e.g. limit=500 per boot) to avoid
// stalling startup on huge libraries.
func BackfillMBIDs(ctx context.Context, pool *pgxpool.Pool, logger *slog.Logger, limit int) (BackfillMBIDsResult, error) {
func BackfillMBIDs(ctx context.Context, pool *pgxpool.Pool, logger *slog.Logger,
limit int, progressCb func(BackfillMBIDsResult)) (BackfillMBIDsResult, error) {
q := dbq.New(pool)
queryLimit := int32(limit)
if limit < 0 {
@@ -68,6 +69,9 @@ func BackfillMBIDs(ctx context.Context, pool *pgxpool.Pool, logger *slog.Logger,
albumMBID, artistMBID := readMBIDsForFile(r.TrackFilePath, logger)
if albumMBID == "" {
res.Skipped++
if progressCb != nil {
progressCb(res)
}
continue
}
@@ -85,11 +89,17 @@ func BackfillMBIDs(ctx context.Context, pool *pgxpool.Pool, logger *slog.Logger,
logger.Info("mbid backfill: duplicate album mbid (canonical row already owns it)",
"album_id", r.AlbumID, "mbid", albumMBID)
res.Duplicates++
if progressCb != nil {
progressCb(res)
}
continue
}
logger.Warn("mbid backfill: set album mbid failed",
"album_id", r.AlbumID, "err", err)
res.Skipped++
if progressCb != nil {
progressCb(res)
}
continue
}
@@ -124,6 +134,9 @@ func BackfillMBIDs(ctx context.Context, pool *pgxpool.Pool, logger *slog.Logger,
"processed", res.Processed, "healed", res.Healed,
"skipped", res.Skipped, "duplicates", res.Duplicates)
}
if progressCb != nil {
progressCb(res)
}
}
logger.Info("mbid backfill complete",
+10 -1
View File
@@ -52,7 +52,10 @@ func New(pool *pgxpool.Pool, logger *slog.Logger, paths []string) *Scanner {
// Scan walks every configured root and upserts any audio file whose mtime is
// newer than the existing row's updated_at. Walk errors and per-file errors
// are logged + counted; the scan keeps going.
func (s *Scanner) Scan(ctx context.Context) (Stats, error) {
//
// progressCb (may be nil) receives the current Stats snapshot after each
// processed file. Used by the orchestrator to drive partial-tally writes.
func (s *Scanner) Scan(ctx context.Context, progressCb func(Stats)) (Stats, error) {
var stats Stats
q := dbq.New(s.pool)
start := time.Now()
@@ -65,6 +68,9 @@ func (s *Scanner) Scan(ctx context.Context) (Stats, error) {
if err != nil {
s.logger.Warn("library scan walk error", "path", path, "err", err)
stats.Errored++
if progressCb != nil {
progressCb(stats)
}
return nil
}
if d.IsDir() {
@@ -77,6 +83,9 @@ func (s *Scanner) Scan(ctx context.Context) (Stats, error) {
s.logger.Warn("library scan file error", "path", path, "err", err)
stats.Errored++
}
if progressCb != nil {
progressCb(stats)
}
return nil
}); err != nil {
return stats, fmt.Errorf("library: walk %q: %w", root, err)
+2 -2
View File
@@ -82,7 +82,7 @@ func TestScanner_Integration(t *testing.T) {
})
scanner := New(pool, logger, []string{root})
stats, err := scanner.Scan(ctx)
stats, err := scanner.Scan(ctx, nil)
if err != nil {
t.Fatalf("first scan: %v", err)
}
@@ -103,7 +103,7 @@ func TestScanner_Integration(t *testing.T) {
t.Errorf("artist sort = [%q, %q], want [Artist X, Artist Y]", artists[0].SortName, artists[1].SortName)
}
stats2, err := scanner.Scan(ctx)
stats2, err := scanner.Scan(ctx, nil)
if err != nil {
t.Fatalf("second scan: %v", err)
}
+92 -38
View File
@@ -5,6 +5,7 @@ import (
"encoding/json"
"fmt"
"log/slog"
"time"
"github.com/jackc/pgx/v5/pgtype"
"github.com/jackc/pgx/v5/pgxpool"
@@ -93,68 +94,121 @@ func RunScan(
// Stage 1: library file-walk scan.
if scanner != nil {
stats, serr := scanner.Scan(ctx)
var lastStats Stats
libPub := newStagePublisher(ctx, 500, time.Second,
func() []byte {
blob, _ := json.Marshal(LibraryStageTallies{
Scanned: lastStats.Scanned, Added: lastStats.Added,
Updated: lastStats.Updated, Skipped: lastStats.Skipped,
Errored: lastStats.Errored,
})
return blob
},
func(blob []byte) error {
return q.UpdateScanRunLibrary(ctx, dbq.UpdateScanRunLibraryParams{
ID: row.ID, Library: blob,
})
},
)
stats, serr := scanner.Scan(ctx, func(s Stats) {
lastStats = s
libPub.Tick()
})
lastStats = stats // ensure final flush sees post-loop value
if err := libPub.Flush(); err != nil {
captureErr("library_persist", err)
}
if serr != nil {
captureErr("library", serr)
}
blob, _ := json.Marshal(LibraryStageTallies{
Scanned: stats.Scanned, Added: stats.Added, Updated: stats.Updated,
Skipped: stats.Skipped, Errored: stats.Errored,
})
if uerr := q.UpdateScanRunLibrary(ctx, dbq.UpdateScanRunLibraryParams{
ID: row.ID, Library: blob,
}); uerr != nil {
captureErr("library_persist", uerr)
}
}
// Stage 2: MBID backfill.
if cfg.BackfillCap != 0 {
bfRes, bferr := BackfillMBIDs(ctx, pool, logger, cfg.BackfillCap)
var lastRes BackfillMBIDsResult
bfPub := newStagePublisher(ctx, 500, time.Second,
func() []byte {
blob, _ := json.Marshal(MBIDBackfillStageTallies{
Processed: lastRes.Processed, Healed: lastRes.Healed,
Skipped: lastRes.Skipped, Duplicates: lastRes.Duplicates,
})
return blob
},
func(blob []byte) error {
return q.UpdateScanRunMbidBackfill(ctx, dbq.UpdateScanRunMbidBackfillParams{
ID: row.ID, MbidBackfill: blob,
})
},
)
bfRes, bferr := BackfillMBIDs(ctx, pool, logger, cfg.BackfillCap, func(r BackfillMBIDsResult) {
lastRes = r
bfPub.Tick()
})
lastRes = bfRes
if err := bfPub.Flush(); err != nil {
captureErr("mbid_backfill_persist", err)
}
if bferr != nil {
captureErr("mbid_backfill", bferr)
}
blob, _ := json.Marshal(MBIDBackfillStageTallies{
Processed: bfRes.Processed, Healed: bfRes.Healed,
Skipped: bfRes.Skipped, Duplicates: bfRes.Duplicates,
})
if uerr := q.UpdateScanRunMbidBackfill(ctx, dbq.UpdateScanRunMbidBackfillParams{
ID: row.ID, MbidBackfill: blob,
}); uerr != nil {
captureErr("mbid_backfill_persist", uerr)
}
}
// Stage 3: cover enrichment.
if enricher != nil && cfg.EnrichCap != 0 {
processed, succeeded, failed, ceerr := enricher.EnrichBatch(ctx, cfg.EnrichCap)
var lastP, lastS, lastF int
coverPub := newStagePublisher(ctx, 500, time.Second,
func() []byte {
blob, _ := json.Marshal(CoverEnrichStageTallies{
Processed: lastP, Succeeded: lastS, Failed: lastF,
})
return blob
},
func(blob []byte) error {
return q.UpdateScanRunCoverEnrich(ctx, dbq.UpdateScanRunCoverEnrichParams{
ID: row.ID, CoverEnrich: blob,
})
},
)
processed, succeeded, failed, ceerr := enricher.EnrichBatch(ctx, cfg.EnrichCap, func(p, s, f int) {
lastP, lastS, lastF = p, s, f
coverPub.Tick()
})
lastP, lastS, lastF = processed, succeeded, failed
if err := coverPub.Flush(); err != nil {
captureErr("cover_enrich_persist", err)
}
if ceerr != nil {
captureErr("cover_enrich", ceerr)
}
blob, _ := json.Marshal(CoverEnrichStageTallies{
Processed: processed, Succeeded: succeeded, Failed: failed,
})
if uerr := q.UpdateScanRunCoverEnrich(ctx, dbq.UpdateScanRunCoverEnrichParams{
ID: row.ID, CoverEnrich: blob,
}); uerr != nil {
captureErr("cover_enrich_persist", uerr)
}
}
// Stage 4: artist art enrichment.
if enricher != nil && cfg.ArtistEnrichCap != 0 && cfg.DataDir != "" {
processed, succeeded, failed, ceerr := enricher.EnrichArtistBatch(ctx, cfg.ArtistEnrichCap, cfg.DataDir)
var lastP, lastS, lastF int
aaPub := newStagePublisher(ctx, 500, time.Second,
func() []byte {
blob, _ := json.Marshal(ArtistArtEnrichStageTallies{
Processed: lastP, Succeeded: lastS, Failed: lastF,
})
return blob
},
func(blob []byte) error {
return q.UpdateScanRunArtistArtEnrich(ctx, dbq.UpdateScanRunArtistArtEnrichParams{
ID: row.ID, ArtistArtEnrich: blob,
})
},
)
processed, succeeded, failed, ceerr := enricher.EnrichArtistBatch(ctx, cfg.ArtistEnrichCap, cfg.DataDir, func(p, s, f int) {
lastP, lastS, lastF = p, s, f
aaPub.Tick()
})
lastP, lastS, lastF = processed, succeeded, failed
if err := aaPub.Flush(); err != nil {
captureErr("artist_art_enrich_persist", err)
}
if ceerr != nil {
captureErr("artist_art_enrich", ceerr)
}
blob, _ := json.Marshal(ArtistArtEnrichStageTallies{
Processed: processed, Succeeded: succeeded, Failed: failed,
})
if uerr := q.UpdateScanRunArtistArtEnrich(ctx, dbq.UpdateScanRunArtistArtEnrichParams{
ID: row.ID, ArtistArtEnrich: blob,
}); uerr != nil {
captureErr("artist_art_enrich_persist", uerr)
}
}
// Finalize: set finished_at + error message (or empty string if all stages succeeded).