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
+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).