Merge pull request 'feat(library): extract track duration via ffprobe' (#13) from dev into main

internal/library/scanner.go

@@ -6,8 +6,11 @@ import (
 	"fmt"
 	"io/fs"
 	"log/slog"
+	"math"
 	"os"
+	"os/exec"
 	"path/filepath"
+	"strconv"
 	"strings"
 	"time"
 
@@ -108,7 +111,12 @@ func (s *Scanner) scanFile(ctx context.Context, q *dbq.Queries, path string, sta
 	if err != nil && !errors.Is(err, pgx.ErrNoRows) {
 		return fmt.Errorf("lookup: %w", err)
 	}
-	if knownTrack && !existing.UpdatedAt.Time.Before(mtime) {
+	// Incremental skip: only when the file hasn't changed AND we already have
+	// a real duration. The second clause lets older scans that recorded
+	// duration_ms=0 (before ffprobe was wired) get backfilled without forcing
+	// the operator to wipe the library. Once duration is set, subsequent
+	// scans short-circuit as before.
+	if knownTrack && !existing.UpdatedAt.Time.Before(mtime) && existing.DurationMs > 0 {
 		stats.Skipped++
 		return nil
 	}
@@ -148,11 +156,19 @@ func (s *Scanner) scanFile(ctx context.Context, q *dbq.Queries, path string, sta
 
 	trackNum, _ := meta.Track()
 	discNum, _ := meta.Disc()
+	durationMs, err := probeDurationMs(ctx, path)
+	if err != nil {
+		// Missing duration is degraded UX (clients can't scrub) but not a
+		// blocker for ingestion. Record the file with 0ms; the next scan
+		// will retry via the backfill clause in the skip check above.
+		s.logger.Warn("library scan: ffprobe failed", "path", path, "err", err)
+		durationMs = 0
+	}
 	params := dbq.UpsertTrackParams{
 		Title:      trackTitle,
 		AlbumID:    album.ID,
 		ArtistID:   artist.ID,
-		DurationMs: 0,
+		DurationMs: durationMs,
 		FilePath:   path,
 		FileSize:   info.Size(),
 		FileFormat: strings.TrimPrefix(strings.ToLower(filepath.Ext(path)), "."),
@@ -243,3 +259,39 @@ func sortKey(s string) string {
 	}
 	return s
 }
+
+// probeTimeout bounds how long ffprobe is allowed to inspect a single file.
+// 10s is generous for local mp3/flac — hits are usually <100ms — but caps
+// blast radius if a pathological file or a slow network mount stalls a scan.
+const probeTimeout = 10 * time.Second
+
+// probeDurationMs shells out to ffprobe to extract a track's duration. We
+// rely on ffmpeg being in the image (see Dockerfile). The CLI is slow per
+// call (fork+exec) but scans are batch-mode; this is simpler than pulling
+// a Go-side decoder library and handles every format ffmpeg does.
+func probeDurationMs(ctx context.Context, path string) (int32, error) {
+	probeCtx, cancel := context.WithTimeout(ctx, probeTimeout)
+	defer cancel()
+	cmd := exec.CommandContext(probeCtx, "ffprobe",
+		"-v", "error",
+		"-show_entries", "format=duration",
+		"-of", "default=noprint_wrappers=1:nokey=1",
+		path,
+	)
+	out, err := cmd.Output()
+	if err != nil {
+		return 0, fmt.Errorf("ffprobe: %w", err)
+	}
+	seconds, err := strconv.ParseFloat(strings.TrimSpace(string(out)), 64)
+	if err != nil {
+		return 0, fmt.Errorf("parse ffprobe output %q: %w", out, err)
+	}
+	if seconds <= 0 || math.IsNaN(seconds) || math.IsInf(seconds, 0) {
+		return 0, fmt.Errorf("invalid duration: %v", seconds)
+	}
+	ms := seconds * 1000
+	if ms > math.MaxInt32 {
+		ms = math.MaxInt32
+	}
+	return int32(ms), nil
+}