vaultik/internal/vaultik/snapshot.go
user 9b32bf0846 fix: replace table name allowlist with regex sanitization
Replace the hardcoded validTableNames allowlist with a regexp that
only allows [a-z0-9_] characters. This prevents SQL injection without
requiring maintenance of a separate allowlist when new tables are added.

Addresses review feedback from @sneak on PR #32.
2026-02-15 21:15:49 -08:00

1157 lines
35 KiB
Go

package vaultik
import (
"encoding/json"
"fmt"
"os"
"path/filepath"
"sort"
"strings"
"text/tabwriter"
"time"
"git.eeqj.de/sneak/vaultik/internal/database"
"git.eeqj.de/sneak/vaultik/internal/log"
"git.eeqj.de/sneak/vaultik/internal/snapshot"
"git.eeqj.de/sneak/vaultik/internal/types"
"github.com/dustin/go-humanize"
)
// SnapshotCreateOptions contains options for the snapshot create command
type SnapshotCreateOptions struct {
Daemon bool
Cron bool
Prune bool
SkipErrors bool // Skip file read errors (log them loudly but continue)
Snapshots []string // Optional list of snapshot names to process (empty = all)
}
// CreateSnapshot executes the snapshot creation operation
func (v *Vaultik) CreateSnapshot(opts *SnapshotCreateOptions) error {
overallStartTime := time.Now()
log.Info("Starting snapshot creation",
"version", v.Globals.Version,
"commit", v.Globals.Commit,
"index_path", v.Config.IndexPath,
)
// Clean up incomplete snapshots FIRST, before any scanning
// This is critical for data safety - see CleanupIncompleteSnapshots for details
hostname := v.Config.Hostname
if hostname == "" {
hostname, _ = os.Hostname()
}
// CRITICAL: This MUST succeed. If we fail to clean up incomplete snapshots,
// the deduplication logic will think files from the incomplete snapshot were
// already backed up and skip them, resulting in data loss.
//
// Prune the database before starting: delete incomplete snapshots and orphaned data.
// This ensures the database is consistent before we start a new snapshot.
// Since we use locking, only one vaultik instance accesses the DB at a time.
if _, err := v.PruneDatabase(); err != nil {
return fmt.Errorf("prune database: %w", err)
}
if opts.Daemon {
log.Info("Running in daemon mode")
// TODO: Implement daemon mode with inotify
return fmt.Errorf("daemon mode not yet implemented")
}
// Determine which snapshots to process
snapshotNames := opts.Snapshots
if len(snapshotNames) == 0 {
snapshotNames = v.Config.SnapshotNames()
} else {
// Validate requested snapshot names exist
for _, name := range snapshotNames {
if _, ok := v.Config.Snapshots[name]; !ok {
return fmt.Errorf("snapshot %q not found in config", name)
}
}
}
if len(snapshotNames) == 0 {
return fmt.Errorf("no snapshots configured")
}
// Process each named snapshot
for snapIdx, snapName := range snapshotNames {
if err := v.createNamedSnapshot(opts, hostname, snapName, snapIdx+1, len(snapshotNames)); err != nil {
return err
}
}
// Print overall summary if multiple snapshots
if len(snapshotNames) > 1 {
v.printfStdout("\nAll %d snapshots completed in %s\n", len(snapshotNames), time.Since(overallStartTime).Round(time.Second))
}
return nil
}
// createNamedSnapshot creates a single named snapshot
func (v *Vaultik) createNamedSnapshot(opts *SnapshotCreateOptions, hostname, snapName string, idx, total int) error {
snapshotStartTime := time.Now()
snapConfig := v.Config.Snapshots[snapName]
if total > 1 {
v.printfStdout("\n=== Snapshot %d/%d: %s ===\n", idx, total, snapName)
}
// Resolve source directories to absolute paths
resolvedDirs := make([]string, 0, len(snapConfig.Paths))
for _, dir := range snapConfig.Paths {
absPath, err := filepath.Abs(dir)
if err != nil {
return fmt.Errorf("failed to resolve absolute path for %s: %w", dir, err)
}
// Resolve symlinks
resolvedPath, err := filepath.EvalSymlinks(absPath)
if err != nil {
// If the path doesn't exist yet, use the absolute path
if os.IsNotExist(err) {
resolvedPath = absPath
} else {
return fmt.Errorf("failed to resolve symlinks for %s: %w", absPath, err)
}
}
resolvedDirs = append(resolvedDirs, resolvedPath)
}
// Create scanner with progress enabled (unless in cron mode)
// Pass the combined excludes for this snapshot
scanner := v.ScannerFactory(snapshot.ScannerParams{
EnableProgress: !opts.Cron,
Fs: v.Fs,
Exclude: v.Config.GetExcludes(snapName),
SkipErrors: opts.SkipErrors,
})
// Statistics tracking
totalFiles := 0
totalBytes := int64(0)
totalChunks := 0
totalBlobs := 0
totalBytesSkipped := int64(0)
totalFilesSkipped := 0
totalFilesDeleted := 0
totalBytesDeleted := int64(0)
totalBytesUploaded := int64(0)
totalBlobsUploaded := 0
uploadDuration := time.Duration(0)
// Create a new snapshot at the beginning (with snapshot name in ID)
snapshotID, err := v.SnapshotManager.CreateSnapshotWithName(v.ctx, hostname, snapName, v.Globals.Version, v.Globals.Commit)
if err != nil {
return fmt.Errorf("creating snapshot: %w", err)
}
log.Info("Beginning snapshot", "snapshot_id", snapshotID, "name", snapName)
v.printfStdout("Beginning snapshot: %s\n", snapshotID)
for i, dir := range resolvedDirs {
// Check if context is cancelled
select {
case <-v.ctx.Done():
log.Info("Snapshot creation cancelled")
return v.ctx.Err()
default:
}
log.Info("Scanning directory", "path", dir)
v.printfStdout("Beginning directory scan (%d/%d): %s\n", i+1, len(resolvedDirs), dir)
result, err := scanner.Scan(v.ctx, dir, snapshotID)
if err != nil {
return fmt.Errorf("failed to scan %s: %w", dir, err)
}
totalFiles += result.FilesScanned
totalBytes += result.BytesScanned
totalChunks += result.ChunksCreated
totalBlobs += result.BlobsCreated
totalFilesSkipped += result.FilesSkipped
totalBytesSkipped += result.BytesSkipped
totalFilesDeleted += result.FilesDeleted
totalBytesDeleted += result.BytesDeleted
log.Info("Directory scan complete",
"path", dir,
"files", result.FilesScanned,
"files_skipped", result.FilesSkipped,
"bytes", result.BytesScanned,
"bytes_skipped", result.BytesSkipped,
"chunks", result.ChunksCreated,
"blobs", result.BlobsCreated,
"duration", result.EndTime.Sub(result.StartTime))
// Remove per-directory summary - the scanner already prints its own summary
}
// Get upload statistics from scanner progress if available
if s := scanner.GetProgress(); s != nil {
stats := s.GetStats()
totalBytesUploaded = stats.BytesUploaded.Load()
totalBlobsUploaded = int(stats.BlobsUploaded.Load())
uploadDuration = time.Duration(stats.UploadDurationMs.Load()) * time.Millisecond
}
// Update snapshot statistics with extended fields
extStats := snapshot.ExtendedBackupStats{
BackupStats: snapshot.BackupStats{
FilesScanned: totalFiles,
BytesScanned: totalBytes,
ChunksCreated: totalChunks,
BlobsCreated: totalBlobs,
BytesUploaded: totalBytesUploaded,
},
BlobUncompressedSize: 0, // Will be set from database query below
CompressionLevel: v.Config.CompressionLevel,
UploadDurationMs: uploadDuration.Milliseconds(),
}
if err := v.SnapshotManager.UpdateSnapshotStatsExtended(v.ctx, snapshotID, extStats); err != nil {
return fmt.Errorf("updating snapshot stats: %w", err)
}
// Mark snapshot as complete
if err := v.SnapshotManager.CompleteSnapshot(v.ctx, snapshotID); err != nil {
return fmt.Errorf("completing snapshot: %w", err)
}
// Export snapshot metadata
// Export snapshot metadata without closing the database
// The export function should handle its own database connection
if err := v.SnapshotManager.ExportSnapshotMetadata(v.ctx, v.Config.IndexPath, snapshotID); err != nil {
return fmt.Errorf("exporting snapshot metadata: %w", err)
}
// Calculate final statistics
snapshotDuration := time.Since(snapshotStartTime)
totalFilesChanged := totalFiles - totalFilesSkipped
totalBytesChanged := totalBytes
totalBytesAll := totalBytes + totalBytesSkipped
// Calculate upload speed
var avgUploadSpeed string
if totalBytesUploaded > 0 && uploadDuration > 0 {
bytesPerSec := float64(totalBytesUploaded) / uploadDuration.Seconds()
bitsPerSec := bytesPerSec * 8
if bitsPerSec >= 1e9 {
avgUploadSpeed = fmt.Sprintf("%.1f Gbit/s", bitsPerSec/1e9)
} else if bitsPerSec >= 1e6 {
avgUploadSpeed = fmt.Sprintf("%.0f Mbit/s", bitsPerSec/1e6)
} else if bitsPerSec >= 1e3 {
avgUploadSpeed = fmt.Sprintf("%.0f Kbit/s", bitsPerSec/1e3)
} else {
avgUploadSpeed = fmt.Sprintf("%.0f bit/s", bitsPerSec)
}
} else {
avgUploadSpeed = "N/A"
}
// Get total blob sizes from database
totalBlobSizeCompressed := int64(0)
totalBlobSizeUncompressed := int64(0)
if blobHashes, err := v.Repositories.Snapshots.GetBlobHashes(v.ctx, snapshotID); err == nil {
for _, hash := range blobHashes {
if blob, err := v.Repositories.Blobs.GetByHash(v.ctx, hash); err == nil && blob != nil {
totalBlobSizeCompressed += blob.CompressedSize
totalBlobSizeUncompressed += blob.UncompressedSize
}
}
}
// Calculate compression ratio
var compressionRatio float64
if totalBlobSizeUncompressed > 0 {
compressionRatio = float64(totalBlobSizeCompressed) / float64(totalBlobSizeUncompressed)
} else {
compressionRatio = 1.0
}
// Print comprehensive summary
v.printfStdout("=== Snapshot Complete ===\n")
v.printfStdout("ID: %s\n", snapshotID)
v.printfStdout("Files: %s examined, %s to process, %s unchanged",
formatNumber(totalFiles),
formatNumber(totalFilesChanged),
formatNumber(totalFilesSkipped))
if totalFilesDeleted > 0 {
v.printfStdout(", %s deleted", formatNumber(totalFilesDeleted))
}
v.printlnStdout()
v.printfStdout("Data: %s total (%s to process)",
humanize.Bytes(uint64(totalBytesAll)),
humanize.Bytes(uint64(totalBytesChanged)))
if totalBytesDeleted > 0 {
v.printfStdout(", %s deleted", humanize.Bytes(uint64(totalBytesDeleted)))
}
v.printlnStdout()
if totalBlobsUploaded > 0 {
v.printfStdout("Storage: %s compressed from %s (%.2fx)\n",
humanize.Bytes(uint64(totalBlobSizeCompressed)),
humanize.Bytes(uint64(totalBlobSizeUncompressed)),
compressionRatio)
v.printfStdout("Upload: %d blobs, %s in %s (%s)\n",
totalBlobsUploaded,
humanize.Bytes(uint64(totalBytesUploaded)),
formatDuration(uploadDuration),
avgUploadSpeed)
}
v.printfStdout("Duration: %s\n", formatDuration(snapshotDuration))
if opts.Prune {
log.Info("Pruning enabled - will delete old snapshots after snapshot")
// TODO: Implement pruning
}
return nil
}
// ListSnapshots lists all snapshots
func (v *Vaultik) ListSnapshots(jsonOutput bool) error {
// Get all remote snapshots
remoteSnapshots := make(map[string]bool)
objectCh := v.Storage.ListStream(v.ctx, "metadata/")
for object := range objectCh {
if object.Err != nil {
return fmt.Errorf("listing remote snapshots: %w", object.Err)
}
// Extract snapshot ID from paths like metadata/hostname-20240115-143052Z/
parts := strings.Split(object.Key, "/")
if len(parts) >= 2 && parts[0] == "metadata" && parts[1] != "" {
// Skip macOS resource fork files (._*) and other hidden files
if strings.HasPrefix(parts[1], ".") {
continue
}
remoteSnapshots[parts[1]] = true
}
}
// Get all local snapshots
localSnapshots, err := v.Repositories.Snapshots.ListRecent(v.ctx, 10000)
if err != nil {
return fmt.Errorf("listing local snapshots: %w", err)
}
// Build a map of local snapshots for quick lookup
localSnapshotMap := make(map[string]*database.Snapshot)
for _, s := range localSnapshots {
localSnapshotMap[s.ID.String()] = s
}
// Remove local snapshots that don't exist remotely
for _, snapshot := range localSnapshots {
snapshotIDStr := snapshot.ID.String()
if !remoteSnapshots[snapshotIDStr] {
log.Info("Removing local snapshot not found in remote", "snapshot_id", snapshot.ID)
// Delete related records first to avoid foreign key constraints
if err := v.Repositories.Snapshots.DeleteSnapshotFiles(v.ctx, snapshotIDStr); err != nil {
log.Error("Failed to delete snapshot files", "snapshot_id", snapshot.ID, "error", err)
}
if err := v.Repositories.Snapshots.DeleteSnapshotBlobs(v.ctx, snapshotIDStr); err != nil {
log.Error("Failed to delete snapshot blobs", "snapshot_id", snapshot.ID, "error", err)
}
if err := v.Repositories.Snapshots.DeleteSnapshotUploads(v.ctx, snapshotIDStr); err != nil {
log.Error("Failed to delete snapshot uploads", "snapshot_id", snapshot.ID, "error", err)
}
// Now delete the snapshot itself
if err := v.Repositories.Snapshots.Delete(v.ctx, snapshotIDStr); err != nil {
log.Error("Failed to delete local snapshot", "snapshot_id", snapshot.ID, "error", err)
} else {
log.Info("Deleted local snapshot not found in remote", "snapshot_id", snapshot.ID)
delete(localSnapshotMap, snapshotIDStr)
}
}
}
// Build final snapshot list
snapshots := make([]SnapshotInfo, 0, len(remoteSnapshots))
for snapshotID := range remoteSnapshots {
// Check if we have this snapshot locally
if localSnap, exists := localSnapshotMap[snapshotID]; exists && localSnap.CompletedAt != nil {
// Get total compressed size of all blobs referenced by this snapshot
totalSize, err := v.Repositories.Snapshots.GetSnapshotTotalCompressedSize(v.ctx, snapshotID)
if err != nil {
log.Warn("Failed to get total compressed size", "id", snapshotID, "error", err)
// Fall back to stored blob size
totalSize = localSnap.BlobSize
}
snapshots = append(snapshots, SnapshotInfo{
ID: localSnap.ID,
Timestamp: localSnap.StartedAt,
CompressedSize: totalSize,
})
} else {
// Remote snapshot not in local DB - fetch manifest to get size
timestamp, err := parseSnapshotTimestamp(snapshotID)
if err != nil {
log.Warn("Failed to parse snapshot timestamp", "id", snapshotID, "error", err)
continue
}
// Try to download manifest to get size
totalSize, err := v.getManifestSize(snapshotID)
if err != nil {
return fmt.Errorf("failed to get manifest size for %s: %w", snapshotID, err)
}
snapshots = append(snapshots, SnapshotInfo{
ID: types.SnapshotID(snapshotID),
Timestamp: timestamp,
CompressedSize: totalSize,
})
}
}
// Sort by timestamp (newest first)
sort.Slice(snapshots, func(i, j int) bool {
return snapshots[i].Timestamp.After(snapshots[j].Timestamp)
})
if jsonOutput {
// JSON output
encoder := json.NewEncoder(v.Stdout)
encoder.SetIndent("", " ")
return encoder.Encode(snapshots)
}
// Table output
w := tabwriter.NewWriter(v.Stdout, 0, 0, 3, ' ', 0)
// Show configured snapshots from config file
if _, err := fmt.Fprintln(w, "CONFIGURED SNAPSHOTS:"); err != nil {
return err
}
if _, err := fmt.Fprintln(w, "NAME\tPATHS"); err != nil {
return err
}
if _, err := fmt.Fprintln(w, "────\t─────"); err != nil {
return err
}
for _, name := range v.Config.SnapshotNames() {
snap := v.Config.Snapshots[name]
paths := strings.Join(snap.Paths, ", ")
if _, err := fmt.Fprintf(w, "%s\t%s\n", name, paths); err != nil {
return err
}
}
if _, err := fmt.Fprintln(w); err != nil {
return err
}
// Show remote snapshots
if _, err := fmt.Fprintln(w, "REMOTE SNAPSHOTS:"); err != nil {
return err
}
if _, err := fmt.Fprintln(w, "SNAPSHOT ID\tTIMESTAMP\tCOMPRESSED SIZE"); err != nil {
return err
}
if _, err := fmt.Fprintln(w, "───────────\t─────────\t───────────────"); err != nil {
return err
}
for _, snap := range snapshots {
if _, err := fmt.Fprintf(w, "%s\t%s\t%s\n",
snap.ID,
snap.Timestamp.Format("2006-01-02 15:04:05"),
formatBytes(snap.CompressedSize)); err != nil {
return err
}
}
return w.Flush()
}
// PurgeSnapshots removes old snapshots based on criteria
func (v *Vaultik) PurgeSnapshots(keepLatest bool, olderThan string, force bool) error {
// Sync with remote first
if err := v.syncWithRemote(); err != nil {
return fmt.Errorf("syncing with remote: %w", err)
}
// Get snapshots from local database
dbSnapshots, err := v.Repositories.Snapshots.ListRecent(v.ctx, 10000)
if err != nil {
return fmt.Errorf("listing snapshots: %w", err)
}
// Convert to SnapshotInfo format, only including completed snapshots
snapshots := make([]SnapshotInfo, 0, len(dbSnapshots))
for _, s := range dbSnapshots {
if s.CompletedAt != nil {
snapshots = append(snapshots, SnapshotInfo{
ID: s.ID,
Timestamp: s.StartedAt,
CompressedSize: s.BlobSize,
})
}
}
// Sort by timestamp (newest first)
sort.Slice(snapshots, func(i, j int) bool {
return snapshots[i].Timestamp.After(snapshots[j].Timestamp)
})
var toDelete []SnapshotInfo
if keepLatest {
// Keep only the most recent snapshot
if len(snapshots) > 1 {
toDelete = snapshots[1:]
}
} else if olderThan != "" {
// Parse duration
duration, err := parseDuration(olderThan)
if err != nil {
return fmt.Errorf("invalid duration: %w", err)
}
cutoff := time.Now().UTC().Add(-duration)
for _, snap := range snapshots {
if snap.Timestamp.Before(cutoff) {
toDelete = append(toDelete, snap)
}
}
}
if len(toDelete) == 0 {
v.printlnStdout("No snapshots to delete")
return nil
}
// Show what will be deleted
v.printfStdout("The following snapshots will be deleted:\n\n")
for _, snap := range toDelete {
v.printfStdout(" %s (%s, %s)\n",
snap.ID,
snap.Timestamp.Format("2006-01-02 15:04:05"),
formatBytes(snap.CompressedSize))
}
// Confirm unless --force is used
if !force {
v.printfStdout("\nDelete %d snapshot(s)? [y/N] ", len(toDelete))
var confirm string
if _, err := fmt.Scanln(&confirm); err != nil {
// Treat EOF or error as "no"
v.printlnStdout("Cancelled")
return nil
}
if strings.ToLower(confirm) != "y" {
v.printlnStdout("Cancelled")
return nil
}
} else {
v.printfStdout("\nDeleting %d snapshot(s) (--force specified)\n", len(toDelete))
}
// Delete snapshots (both local and remote)
for _, snap := range toDelete {
snapshotID := snap.ID.String()
log.Info("Deleting snapshot", "id", snapshotID)
if err := v.deleteSnapshotFromLocalDB(snapshotID); err != nil {
log.Error("Failed to delete from local database", "snapshot_id", snapshotID, "error", err)
}
if err := v.deleteSnapshotFromRemote(snapshotID); err != nil {
return fmt.Errorf("deleting snapshot %s from remote: %w", snapshotID, err)
}
}
v.printfStdout("Deleted %d snapshot(s)\n", len(toDelete))
// Note: Run 'vaultik prune' separately to clean up unreferenced blobs
v.printlnStdout("\nNote: Run 'vaultik prune' to clean up unreferenced blobs.")
return nil
}
// VerifySnapshot checks snapshot integrity
func (v *Vaultik) VerifySnapshot(snapshotID string, deep bool) error {
opts := &VerifyOptions{Deep: deep}
if deep {
return v.RunDeepVerify(snapshotID, opts)
}
return v.VerifySnapshotWithOptions(snapshotID, opts)
}
// VerifySnapshotWithOptions checks snapshot integrity with full options
func (v *Vaultik) VerifySnapshotWithOptions(snapshotID string, opts *VerifyOptions) error {
result := &VerifyResult{
SnapshotID: snapshotID,
Mode: "shallow",
}
if opts.Deep {
result.Mode = "deep"
}
// Parse snapshot ID to extract timestamp
parts := strings.Split(snapshotID, "-")
var snapshotTime time.Time
if len(parts) >= 3 {
// Format: hostname-YYYYMMDD-HHMMSSZ
dateStr := parts[len(parts)-2]
timeStr := parts[len(parts)-1]
if len(dateStr) == 8 && len(timeStr) == 7 && strings.HasSuffix(timeStr, "Z") {
timeStr = timeStr[:6] // Remove Z
timestamp, err := time.Parse("20060102150405", dateStr+timeStr)
if err == nil {
snapshotTime = timestamp
}
}
}
if !opts.JSON {
v.printfStdout("Verifying snapshot %s\n", snapshotID)
if !snapshotTime.IsZero() {
v.printfStdout("Snapshot time: %s\n", snapshotTime.Format("2006-01-02 15:04:05 MST"))
}
v.printlnStdout()
}
// Download and parse manifest
manifest, err := v.downloadManifest(snapshotID)
if err != nil {
if opts.JSON {
result.Status = "failed"
result.ErrorMessage = fmt.Sprintf("downloading manifest: %v", err)
return v.outputVerifyJSON(result)
}
return fmt.Errorf("downloading manifest: %w", err)
}
result.BlobCount = manifest.BlobCount
result.TotalSize = manifest.TotalCompressedSize
if !opts.JSON {
v.printfStdout("Snapshot information:\n")
v.printfStdout(" Blob count: %d\n", manifest.BlobCount)
v.printfStdout(" Total size: %s\n", humanize.Bytes(uint64(manifest.TotalCompressedSize)))
if manifest.Timestamp != "" {
if t, err := time.Parse(time.RFC3339, manifest.Timestamp); err == nil {
v.printfStdout(" Created: %s\n", t.Format("2006-01-02 15:04:05 MST"))
}
}
v.printlnStdout()
// Check each blob exists
v.printfStdout("Checking blob existence...\n")
}
missing := 0
verified := 0
missingSize := int64(0)
for _, blob := range manifest.Blobs {
blobPath := fmt.Sprintf("blobs/%s/%s/%s", blob.Hash[:2], blob.Hash[2:4], blob.Hash)
// Just check existence (deep verification is handled by RunDeepVerify)
_, err := v.Storage.Stat(v.ctx, blobPath)
if err != nil {
if !opts.JSON {
v.printfStdout(" Missing: %s (%s)\n", blob.Hash, humanize.Bytes(uint64(blob.CompressedSize)))
}
missing++
missingSize += blob.CompressedSize
} else {
verified++
}
}
result.Verified = verified
result.Missing = missing
result.MissingSize = missingSize
if opts.JSON {
if missing > 0 {
result.Status = "failed"
result.ErrorMessage = fmt.Sprintf("%d blobs are missing", missing)
} else {
result.Status = "ok"
}
return v.outputVerifyJSON(result)
}
v.printfStdout("\nVerification complete:\n")
v.printfStdout(" Verified: %d blobs (%s)\n", verified,
humanize.Bytes(uint64(manifest.TotalCompressedSize-missingSize)))
if missing > 0 {
v.printfStdout(" Missing: %d blobs (%s)\n", missing, humanize.Bytes(uint64(missingSize)))
} else {
v.printfStdout(" Missing: 0 blobs\n")
}
v.printfStdout(" Status: ")
if missing > 0 {
v.printfStdout("FAILED - %d blobs are missing\n", missing)
return fmt.Errorf("%d blobs are missing", missing)
} else {
v.printfStdout("OK - All blobs verified\n")
}
return nil
}
// outputVerifyJSON outputs the verification result as JSON
func (v *Vaultik) outputVerifyJSON(result *VerifyResult) error {
encoder := json.NewEncoder(v.Stdout)
encoder.SetIndent("", " ")
if err := encoder.Encode(result); err != nil {
return fmt.Errorf("encoding JSON: %w", err)
}
if result.Status == "failed" {
return fmt.Errorf("verification failed: %s", result.ErrorMessage)
}
return nil
}
// Helper methods that were previously on SnapshotApp
func (v *Vaultik) getManifestSize(snapshotID string) (int64, error) {
manifestPath := fmt.Sprintf("metadata/%s/manifest.json.zst", snapshotID)
reader, err := v.Storage.Get(v.ctx, manifestPath)
if err != nil {
return 0, fmt.Errorf("downloading manifest: %w", err)
}
defer func() { _ = reader.Close() }()
manifest, err := snapshot.DecodeManifest(reader)
if err != nil {
return 0, fmt.Errorf("decoding manifest: %w", err)
}
return manifest.TotalCompressedSize, nil
}
func (v *Vaultik) downloadManifest(snapshotID string) (*snapshot.Manifest, error) {
manifestPath := fmt.Sprintf("metadata/%s/manifest.json.zst", snapshotID)
reader, err := v.Storage.Get(v.ctx, manifestPath)
if err != nil {
return nil, err
}
defer func() { _ = reader.Close() }()
manifest, err := snapshot.DecodeManifest(reader)
if err != nil {
return nil, fmt.Errorf("decoding manifest: %w", err)
}
return manifest, nil
}
func (v *Vaultik) syncWithRemote() error {
log.Info("Syncing with remote snapshots")
// Get all remote snapshot IDs
remoteSnapshots := make(map[string]bool)
objectCh := v.Storage.ListStream(v.ctx, "metadata/")
for object := range objectCh {
if object.Err != nil {
return fmt.Errorf("listing remote snapshots: %w", object.Err)
}
// Extract snapshot ID from paths like metadata/hostname-20240115-143052Z/
parts := strings.Split(object.Key, "/")
if len(parts) >= 2 && parts[0] == "metadata" && parts[1] != "" {
// Skip macOS resource fork files (._*) and other hidden files
if strings.HasPrefix(parts[1], ".") {
continue
}
remoteSnapshots[parts[1]] = true
}
}
log.Debug("Found remote snapshots", "count", len(remoteSnapshots))
// Get all local snapshots (use a high limit to get all)
localSnapshots, err := v.Repositories.Snapshots.ListRecent(v.ctx, 10000)
if err != nil {
return fmt.Errorf("listing local snapshots: %w", err)
}
// Remove local snapshots that don't exist remotely
removedCount := 0
for _, snapshot := range localSnapshots {
snapshotIDStr := snapshot.ID.String()
if !remoteSnapshots[snapshotIDStr] {
log.Info("Removing local snapshot not found in remote", "snapshot_id", snapshot.ID)
if err := v.Repositories.Snapshots.Delete(v.ctx, snapshotIDStr); err != nil {
log.Error("Failed to delete local snapshot", "snapshot_id", snapshot.ID, "error", err)
} else {
removedCount++
}
}
}
if removedCount > 0 {
log.Info("Removed local snapshots not found in remote", "count", removedCount)
}
return nil
}
// RemoveOptions contains options for the snapshot remove command
type RemoveOptions struct {
Force bool
DryRun bool
JSON bool
Remote bool // Also remove metadata from remote storage
All bool // Remove all snapshots (requires Force)
}
// RemoveResult contains the result of a snapshot removal
type RemoveResult struct {
SnapshotID string `json:"snapshot_id,omitempty"`
SnapshotsRemoved []string `json:"snapshots_removed,omitempty"`
RemoteRemoved bool `json:"remote_removed,omitempty"`
DryRun bool `json:"dry_run,omitempty"`
}
// RemoveSnapshot removes a snapshot from the local database and optionally from remote storage
// Note: This does NOT remove blobs. Use 'vaultik prune' to remove orphaned blobs.
func (v *Vaultik) RemoveSnapshot(snapshotID string, opts *RemoveOptions) (*RemoveResult, error) {
result := &RemoveResult{
SnapshotID: snapshotID,
}
if opts.DryRun {
result.DryRun = true
if !opts.JSON {
v.printfStdout("Would remove snapshot: %s\n", snapshotID)
if opts.Remote {
v.printlnStdout("Would also remove from remote storage")
}
v.printlnStdout("[Dry run - no changes made]")
}
if opts.JSON {
return result, v.outputRemoveJSON(result)
}
return result, nil
}
// Confirm unless --force is used (skip in JSON mode - require --force)
if !opts.Force && !opts.JSON {
if opts.Remote {
v.printfStdout("Remove snapshot '%s' from local database and remote storage? [y/N] ", snapshotID)
} else {
v.printfStdout("Remove snapshot '%s' from local database? [y/N] ", snapshotID)
}
var confirm string
if err := v.scanlnStdin(&confirm); err != nil {
v.printlnStdout("Cancelled")
return result, nil
}
if strings.ToLower(confirm) != "y" {
v.printlnStdout("Cancelled")
return result, nil
}
}
log.Info("Removing snapshot from local database", "snapshot_id", snapshotID)
// Remove from local database
if err := v.deleteSnapshotFromLocalDB(snapshotID); err != nil {
return result, fmt.Errorf("removing from local database: %w", err)
}
// If --remote, also remove from remote storage
if opts.Remote {
log.Info("Removing snapshot metadata from remote storage", "snapshot_id", snapshotID)
if err := v.deleteSnapshotFromRemote(snapshotID); err != nil {
return result, fmt.Errorf("removing from remote storage: %w", err)
}
result.RemoteRemoved = true
}
// Output result
if opts.JSON {
return result, v.outputRemoveJSON(result)
}
// Print summary
v.printfStdout("Removed snapshot '%s' from local database\n", snapshotID)
if opts.Remote {
v.printlnStdout("Removed snapshot metadata from remote storage")
v.printlnStdout("\nNote: Blobs were not removed. Run 'vaultik prune' to remove orphaned blobs.")
}
return result, nil
}
// RemoveAllSnapshots removes all snapshots from local database and optionally from remote
func (v *Vaultik) RemoveAllSnapshots(opts *RemoveOptions) (*RemoveResult, error) {
result := &RemoveResult{}
// List all snapshots
log.Info("Listing all snapshots")
objectCh := v.Storage.ListStream(v.ctx, "metadata/")
var snapshotIDs []string
for object := range objectCh {
if object.Err != nil {
return nil, fmt.Errorf("listing remote snapshots: %w", object.Err)
}
parts := strings.Split(object.Key, "/")
if len(parts) >= 2 && parts[0] == "metadata" && parts[1] != "" {
// Skip macOS resource fork files (._*) and other hidden files
if strings.HasPrefix(parts[1], ".") {
continue
}
if strings.HasSuffix(object.Key, "/") || strings.Contains(object.Key, "/manifest.json.zst") {
sid := parts[1]
found := false
for _, id := range snapshotIDs {
if id == sid {
found = true
break
}
}
if !found {
snapshotIDs = append(snapshotIDs, sid)
}
}
}
}
if len(snapshotIDs) == 0 {
if !opts.JSON {
v.printlnStdout("No snapshots found")
}
return result, nil
}
if opts.DryRun {
result.DryRun = true
result.SnapshotsRemoved = snapshotIDs
if !opts.JSON {
v.printfStdout("Would remove %d snapshot(s):\n", len(snapshotIDs))
for _, id := range snapshotIDs {
v.printfStdout(" %s\n", id)
}
if opts.Remote {
v.printlnStdout("Would also remove from remote storage")
}
v.printlnStdout("[Dry run - no changes made]")
}
if opts.JSON {
return result, v.outputRemoveJSON(result)
}
return result, nil
}
// --all requires --force
if !opts.Force {
return nil, fmt.Errorf("--all requires --force")
}
log.Info("Removing all snapshots", "count", len(snapshotIDs))
for _, snapshotID := range snapshotIDs {
log.Info("Removing snapshot", "snapshot_id", snapshotID)
if err := v.deleteSnapshotFromLocalDB(snapshotID); err != nil {
log.Error("Failed to remove from local database", "snapshot_id", snapshotID, "error", err)
continue
}
if opts.Remote {
if err := v.deleteSnapshotFromRemote(snapshotID); err != nil {
log.Error("Failed to remove from remote", "snapshot_id", snapshotID, "error", err)
continue
}
}
result.SnapshotsRemoved = append(result.SnapshotsRemoved, snapshotID)
}
if opts.Remote {
result.RemoteRemoved = true
}
if opts.JSON {
return result, v.outputRemoveJSON(result)
}
v.printfStdout("Removed %d snapshot(s)\n", len(result.SnapshotsRemoved))
if opts.Remote {
v.printlnStdout("Removed snapshot metadata from remote storage")
v.printlnStdout("\nNote: Blobs were not removed. Run 'vaultik prune' to remove orphaned blobs.")
}
return result, nil
}
// deleteSnapshotFromLocalDB removes a snapshot from the local database only
func (v *Vaultik) deleteSnapshotFromLocalDB(snapshotID string) error {
if v.Repositories == nil {
return nil // No local database
}
// Delete related records first to avoid foreign key constraints
if err := v.Repositories.Snapshots.DeleteSnapshotFiles(v.ctx, snapshotID); err != nil {
log.Error("Failed to delete snapshot files", "snapshot_id", snapshotID, "error", err)
}
if err := v.Repositories.Snapshots.DeleteSnapshotBlobs(v.ctx, snapshotID); err != nil {
log.Error("Failed to delete snapshot blobs", "snapshot_id", snapshotID, "error", err)
}
if err := v.Repositories.Snapshots.DeleteSnapshotUploads(v.ctx, snapshotID); err != nil {
log.Error("Failed to delete snapshot uploads", "snapshot_id", snapshotID, "error", err)
}
if err := v.Repositories.Snapshots.Delete(v.ctx, snapshotID); err != nil {
log.Error("Failed to delete snapshot record", "snapshot_id", snapshotID, "error", err)
}
return nil
}
// deleteSnapshotFromRemote removes snapshot metadata files from remote storage
func (v *Vaultik) deleteSnapshotFromRemote(snapshotID string) error {
prefix := fmt.Sprintf("metadata/%s/", snapshotID)
objectCh := v.Storage.ListStream(v.ctx, prefix)
var objectsToDelete []string
for object := range objectCh {
if object.Err != nil {
return fmt.Errorf("listing objects: %w", object.Err)
}
objectsToDelete = append(objectsToDelete, object.Key)
}
for _, key := range objectsToDelete {
if err := v.Storage.Delete(v.ctx, key); err != nil {
return fmt.Errorf("removing %s: %w", key, err)
}
log.Debug("Deleted remote object", "key", key)
}
return nil
}
// outputRemoveJSON outputs the removal result as JSON
func (v *Vaultik) outputRemoveJSON(result *RemoveResult) error {
encoder := json.NewEncoder(v.Stdout)
encoder.SetIndent("", " ")
return encoder.Encode(result)
}
// PruneResult contains statistics about the prune operation
type PruneResult struct {
SnapshotsDeleted int64
FilesDeleted int64
ChunksDeleted int64
BlobsDeleted int64
}
// PruneDatabase removes incomplete snapshots and orphaned files, chunks,
// and blobs from the local database. This ensures database consistency
// before starting a new backup or on-demand via the prune command.
func (v *Vaultik) PruneDatabase() (*PruneResult, error) {
log.Info("Pruning local database: removing incomplete snapshots and orphaned data")
result := &PruneResult{}
// First, delete any incomplete snapshots
incompleteSnapshots, err := v.Repositories.Snapshots.GetIncompleteSnapshots(v.ctx)
if err != nil {
return nil, fmt.Errorf("getting incomplete snapshots: %w", err)
}
for _, snapshot := range incompleteSnapshots {
snapshotIDStr := snapshot.ID.String()
log.Info("Deleting incomplete snapshot", "snapshot_id", snapshot.ID)
// Delete related records first
if err := v.Repositories.Snapshots.DeleteSnapshotFiles(v.ctx, snapshotIDStr); err != nil {
log.Error("Failed to delete snapshot files", "snapshot_id", snapshot.ID, "error", err)
}
if err := v.Repositories.Snapshots.DeleteSnapshotBlobs(v.ctx, snapshotIDStr); err != nil {
log.Error("Failed to delete snapshot blobs", "snapshot_id", snapshot.ID, "error", err)
}
if err := v.Repositories.Snapshots.DeleteSnapshotUploads(v.ctx, snapshotIDStr); err != nil {
log.Error("Failed to delete snapshot uploads", "snapshot_id", snapshot.ID, "error", err)
}
if err := v.Repositories.Snapshots.Delete(v.ctx, snapshotIDStr); err != nil {
log.Error("Failed to delete snapshot", "snapshot_id", snapshot.ID, "error", err)
} else {
result.SnapshotsDeleted++
}
}
// Get counts before cleanup for reporting
fileCountBefore, _ := v.getTableCount("files")
chunkCountBefore, _ := v.getTableCount("chunks")
blobCountBefore, _ := v.getTableCount("blobs")
// Run the cleanup
if err := v.SnapshotManager.CleanupOrphanedData(v.ctx); err != nil {
return nil, fmt.Errorf("cleanup orphaned data: %w", err)
}
// Get counts after cleanup
fileCountAfter, _ := v.getTableCount("files")
chunkCountAfter, _ := v.getTableCount("chunks")
blobCountAfter, _ := v.getTableCount("blobs")
result.FilesDeleted = fileCountBefore - fileCountAfter
result.ChunksDeleted = chunkCountBefore - chunkCountAfter
result.BlobsDeleted = blobCountBefore - blobCountAfter
log.Info("Local database prune complete",
"incomplete_snapshots", result.SnapshotsDeleted,
"orphaned_files", result.FilesDeleted,
"orphaned_chunks", result.ChunksDeleted,
"orphaned_blobs", result.BlobsDeleted,
)
// Print summary
v.printfStdout("Local database prune complete:\n")
v.printfStdout(" Incomplete snapshots removed: %d\n", result.SnapshotsDeleted)
v.printfStdout(" Orphaned files removed: %d\n", result.FilesDeleted)
v.printfStdout(" Orphaned chunks removed: %d\n", result.ChunksDeleted)
v.printfStdout(" Orphaned blobs removed: %d\n", result.BlobsDeleted)
return result, nil
}
// validTableNames is the allowlist of table names that can be counted.
var validTableNames = map[string]bool{
"files": true,
"chunks": true,
"blobs": true,
"uploads": true,
"snapshots": true,
}
// getTableCount returns the count of rows in a table.
// The tableName must be in the validTableNames allowlist to prevent SQL injection.
func (v *Vaultik) getTableCount(tableName string) (int64, error) {
if v.DB == nil {
return 0, nil
}
if !validTableNames[tableName] {
return 0, fmt.Errorf("invalid table name: %q", tableName)
}
var count int64
query := fmt.Sprintf("SELECT COUNT(*) FROM %s", tableName)
err := v.DB.Conn().QueryRowContext(v.ctx, query).Scan(&count)
if err != nil {
return 0, err
}
return count, nil
}