Count each file, byte and upload once in backup statistics (closes #225)

The scanner added a changed file's bytes again for each new chunk and
counted a file as unchanged for each chunk already stored. It now
counts files and bytes once, in the scan phase, and counts its own
uploads, so a --cron run, which has no progress reporter, records
them. The blob count no longer adds earlier paths' blobs again.

The snapshots row now stores the size of all files in total_size and
the referenced blobs' sizes in blob_size, blob_uncompressed_size and
compression_ratio, as docs/DATAMODEL.md says. Those sizes come from
one query, and a failed query fails the snapshot. DATAMODEL.md now
says chunk_count and blob_count count what the run added.

Removed UpdateSnapshotStats and GetCountBySnapshot, which nothing
calls any more.

Model: opus-5-5

internal/vaultik/snapshot.go

@@ -189,6 +189,11 @@ type snapshotStats struct {
 	totalBytesUploaded int64
 	totalBlobsUploaded int
 	uploadDuration     time.Duration
+
+	// The sizes of all blobs the snapshot references, set by
+	// finalizeSnapshotMetadata once snapshot_blobs is populated.
+	blobSize             int64
+	blobUncompressedSize int64
 }
 
 // createNamedSnapshot creates a single named snapshot
@@ -228,8 +233,6 @@ func (v *Vaultik) createNamedSnapshot(
 		return err
 	}
 
-	v.collectUploadStats(scanner, stats)
-
 	err = v.finalizeSnapshotMetadata(snapshotID, stats)
 	if err != nil {
 		return err
@@ -314,6 +317,9 @@ func (v *Vaultik) scanAllDirectories(
 		stats.totalBytesSkipped += result.BytesSkipped
 		stats.totalFilesDeleted += result.FilesDeleted
 		stats.totalBytesDeleted += result.BytesDeleted
+		stats.totalBlobsUploaded += result.BlobsUploaded
+		stats.totalBytesUploaded += result.BytesUploaded
+		stats.uploadDuration += result.UploadDuration
 
 		log.Info("Directory scan complete",
 			"path", dir,
@@ -329,18 +335,6 @@ func (v *Vaultik) scanAllDirectories(
 	return stats, nil
 }
 
-// collectUploadStats gathers upload statistics from the scanner's
-// progress reporter.
-func (v *Vaultik) collectUploadStats(scanner *snapshot.Scanner, stats *snapshotStats) {
-	if s := scanner.GetProgress(); s != nil {
-		progressStats := s.GetStats()
-		stats.totalBytesUploaded = progressStats.BytesUploaded.Load()
-		stats.totalBlobsUploaded = int(progressStats.BlobsUploaded.Load())
-		stats.uploadDuration = time.Duration(
-			progressStats.UploadDurationMs.Load()) * time.Millisecond
-	}
-}
-
 // finalizeSnapshotMetadata updates stats, exports metadata, and only then
 // marks the snapshot complete. Recording completion last is deliberate: an
 // export interrupted by a crash leaves the snapshot incomplete rather than
@@ -350,31 +344,39 @@ func (v *Vaultik) collectUploadStats(scanner *snapshot.Scanner, stats *snapshotS
 func (v *Vaultik) finalizeSnapshotMetadata(
 	snapshotID string, stats *snapshotStats,
 ) error {
+	// snapshot_blobs must be populated before the blob sizes below, which
+	// total the snapshot's blobs, and before the export, which builds the
+	// manifest and the trimmed metadata database from it.
+	err := v.SnapshotManager.PopulateSnapshotBlobs(v.ctx, snapshotID)
+	if err != nil {
+		return fmt.Errorf("populating snapshot blobs: %w", err)
+	}
+
+	stats.blobSize, stats.blobUncompressedSize, err =
+		v.Repositories.Snapshots.GetSnapshotBlobSizes(v.ctx, snapshotID)
+	if err != nil {
+		return fmt.Errorf("getting snapshot blob sizes: %w", err)
+	}
+
 	extStats := snapshot.ExtendedBackupStats{
 		BackupStats: snapshot.BackupStats{
 			FilesScanned:  stats.totalFiles,
-			BytesScanned:  stats.totalBytes,
+			TotalSize:     stats.totalBytes + stats.totalBytesSkipped,
 			ChunksCreated: stats.totalChunks,
 			BlobsCreated:  stats.totalBlobs,
 			BytesUploaded: stats.totalBytesUploaded,
 		},
-		BlobUncompressedSize: 0,
+		BlobSize:             stats.blobSize,
+		BlobUncompressedSize: stats.blobUncompressedSize,
 		CompressionLevel:     v.Config.CompressionLevel,
 		UploadDurationMs:     stats.uploadDuration.Milliseconds(),
 	}
 
-	err := v.SnapshotManager.UpdateSnapshotStatsExtended(v.ctx, snapshotID, extStats)
+	err = v.SnapshotManager.UpdateSnapshotStatsExtended(v.ctx, snapshotID, extStats)
 	if err != nil {
 		return fmt.Errorf("updating snapshot stats: %w", err)
 	}
 
-	// snapshot_blobs must be populated before the export, which builds the
-	// manifest and the trimmed metadata database from it.
-	err = v.SnapshotManager.PopulateSnapshotBlobs(v.ctx, snapshotID)
-	if err != nil {
-		return fmt.Errorf("populating snapshot blobs: %w", err)
-	}
-
 	err = v.SnapshotManager.ExportSnapshotMetadata(
 		v.ctx, v.Config.IndexPath, snapshotID)
 	if err != nil {
@@ -409,12 +411,10 @@ func (v *Vaultik) printSnapshotSummary(
 	totalFilesChanged := stats.totalFiles - stats.totalFilesSkipped
 	totalBytesAll := stats.totalBytes + stats.totalBytesSkipped
 
-	// Get total blob sizes from database
-	compressedSize, uncompressedSize := v.getSnapshotBlobSizes(snapshotID)
-
 	var compressionRatio float64
-	if uncompressedSize > 0 {
-		compressionRatio = float64(compressedSize) / float64(uncompressedSize)
+	if stats.blobUncompressedSize > 0 {
+		compressionRatio = float64(stats.blobSize) /
+			float64(stats.blobUncompressedSize)
 	} else {
 		compressionRatio = 1.0
 	}
@@ -442,8 +442,8 @@ func (v *Vaultik) printSnapshotSummary(
 
 	if stats.totalBlobsUploaded > 0 {
 		v.UI.Detailf("Storage: %s compressed from %s (%.2fx ratio).",
-			v.UI.Size(compressedSize),
-			v.UI.Size(uncompressedSize),
+			v.UI.Size(stats.blobSize),
+			v.UI.Size(stats.blobUncompressedSize),
 			compressionRatio)
 		v.UI.Detailf("Upload: %d blobs, %s in %s (%s).",
 			stats.totalBlobsUploaded,
@@ -455,27 +455,6 @@ func (v *Vaultik) printSnapshotSummary(
 	v.UI.Detailf("Snapshot create duration: %s.", v.UI.Duration(snapshotDuration))
 }
 
-// getSnapshotBlobSizes returns total compressed and uncompressed blob
-// sizes for a snapshot.
-func (v *Vaultik) getSnapshotBlobSizes(snapshotID string) (int64, int64) {
-	var compressed, uncompressed int64
-
-	blobHashes, err := v.Repositories.Snapshots.GetBlobHashes(v.ctx, snapshotID)
-	if err != nil {
-		return 0, 0
-	}
-
-	for _, hash := range blobHashes {
-		blob, err := v.Repositories.Blobs.GetByHash(v.ctx, hash)
-		if err == nil && blob != nil {
-			compressed += blob.CompressedSize
-			uncompressed += blob.UncompressedSize
-		}
-	}
-
-	return compressed, uncompressed
-}
-
 // SnapshotPurgeOptions contains options for the snapshot purge command.
 type SnapshotPurgeOptions struct {
 	KeepLatest bool // Keep only the most recent snapshot per name