vaultik/internal/vaultik/snapshot.go

package vaultik

import (
	"encoding/json"
	"errors"
	"fmt"
	"os"
	"path/filepath"
	"regexp"
	"sort"
	"strings"
	"time"

	"sneak.berlin/go/vaultik/internal/log"
	"sneak.berlin/go/vaultik/internal/snapshot"
)

// Sentinel errors for snapshot management.
var (
	errSnapshotNotInConfig  = errors.New("snapshot not found in config")
	errNoSnapshotsInConfig  = errors.New("no snapshots configured")
	errBlobsMissing         = errors.New("blobs are missing")
	errSnapshotVerifyFailed = errors.New("verification failed")
	errRemoveAllNeedsForce  = errors.New("--all requires --force")
	errInvalidTableName     = errors.New("invalid table name")
)

// listRecentLimit caps how many snapshot rows are fetched from the
// local index for listing and purge operations.
const listRecentLimit = 10000

// SnapshotCreateOptions contains options for the snapshot create command
type SnapshotCreateOptions struct {
	Cron  bool
	Prune bool
	// KeepNewerThan is used with --prune: keep snapshots newer than this
	// duration (e.g. "4w"); default: keep only latest.
	KeepNewerThan string
	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,
	)

	err := v.EnsureStorageBinding()
	if err != nil {
		return err
	}

	// 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.
	_, err = v.PruneDatabase()
	if err != nil {
		return fmt.Errorf("prune database: %w", err)
	}

	// 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("%w: %q", errSnapshotNotInConfig, name)
			}
		}
	}

	if len(snapshotNames) == 0 {
		return errNoSnapshotsInConfig
	}

	// Process each named snapshot
	for snapIdx, snapName := range snapshotNames {
		err = v.createNamedSnapshot(
			opts, hostname, snapName, snapIdx+1, len(snapshotNames))
		if err != nil {
			return err
		}
	}

	// Print overall summary if multiple snapshots
	if len(snapshotNames) > 1 {
		v.UI.Completef("All %d snapshots completed in %s.",
			len(snapshotNames), v.UI.Duration(time.Since(overallStartTime)))
	}

	if opts.Prune {
		err = v.runPostBackupPrune(snapshotNames, opts.KeepNewerThan)
		if err != nil {
			return fmt.Errorf("post-backup prune: %w", err)
		}
	}

	// Terminus must obey the --cron invariant: silent on total
	// success only. UI.Complete is dropped in cron/quiet mode (that's
	// the success path), but if any warnings fired during the run we
	// emit the summary via UI.Warning so cron actually delivers
	// something for the user to look at.
	if v.UI.WarningCount() > 0 {
		v.UI.Warningf("Finished with %d warning(s) — review the output above.",
			v.UI.WarningCount())
	} else {
		v.UI.Completef("Finished successfully.")
	}

	return nil
}

// runPostBackupPrune drops older snapshots of the given names and removes
// orphan blobs from remote storage. If keepNewerThan is set (e.g. "4w"),
// snapshots newer than that duration are kept. Otherwise only the latest
// snapshot of each name is kept.
func (v *Vaultik) runPostBackupPrune(
	snapshotNames []string, keepNewerThan string,
) error {
	log.Info("Running post-backup prune",
		"snapshots", snapshotNames, "keep_newer_than", keepNewerThan)
	v.UI.Beginf("Running post-backup prune.")

	purgeOpts := &SnapshotPurgeOptions{
		Force: true,
		Names: snapshotNames,
		Quiet: true,
	}

	if keepNewerThan != "" {
		purgeOpts.OlderThan = keepNewerThan
	} else {
		purgeOpts.KeepLatest = true
	}

	err := v.PurgeSnapshotsWithOptions(purgeOpts)
	if err != nil {
		return fmt.Errorf("purging old snapshots: %w", err)
	}

	err = v.PruneBlobs(&PruneOptions{Force: true})
	if err != nil {
		return fmt.Errorf("pruning orphaned blobs: %w", err)
	}

	return nil
}

// snapshotStats tracks aggregate statistics across directory scans
type snapshotStats struct {
	totalFiles         int
	totalBytes         int64
	totalChunks        int
	totalBlobs         int
	totalBytesSkipped  int64
	totalFilesSkipped  int
	totalFilesDeleted  int
	totalBytesDeleted  int64
	totalBytesUploaded int64
	totalBlobsUploaded int
	uploadDuration     time.Duration
}

// createNamedSnapshot creates a single named snapshot
func (v *Vaultik) createNamedSnapshot(
	opts *SnapshotCreateOptions, hostname, snapName string, idx, total int,
) error {
	snapshotStartTime := time.Now()

	if total > 1 {
		v.UI.Infof("Snapshot %d/%d: %s.", idx, total, snapName)
	}

	resolvedDirs, err := v.resolveSnapshotPaths(snapName)
	if err != nil {
		return err
	}

	scanner := v.ScannerFactory(snapshot.ScannerParams{
		EnableProgress: !opts.Cron,
		UI:             v.UI,
		Fs:             v.Fs,
		Exclude:        v.Config.GetExcludes(snapName),
		SkipErrors:     opts.SkipErrors,
	})

	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.UI.Beginf("Creating snapshot %s.", v.UI.Snapshot(snapshotID))

	stats, err := v.scanAllDirectories(scanner, resolvedDirs, snapshotID)
	if err != nil {
		return err
	}

	v.collectUploadStats(scanner, stats)

	err = v.finalizeSnapshotMetadata(snapshotID, stats)
	if err != nil {
		return err
	}

	log.Info("Snapshot complete",
		"snapshot_id", snapshotID,
		"name", snapName,
		"files", stats.totalFiles,
		"blobs_uploaded", stats.totalBlobsUploaded,
		"bytes_uploaded", stats.totalBytesUploaded,
		"duration", time.Since(snapshotStartTime))

	v.printSnapshotSummary(snapshotID, snapshotStartTime, stats)

	return nil
}

// resolveSnapshotPaths resolves source directories to absolute paths
// with symlink resolution.
func (v *Vaultik) resolveSnapshotPaths(snapName string) ([]string, error) {
	snapConfig := v.Config.Snapshots[snapName]
	resolvedDirs := make([]string, 0, len(snapConfig.Paths))

	for _, dir := range snapConfig.Paths {
		absPath, err := filepath.Abs(dir)
		if err != nil {
			return nil, fmt.Errorf("failed to resolve absolute path for %s: %w", dir, err)
		}

		resolvedPath, err := filepath.EvalSymlinks(absPath)
		if err != nil {
			if os.IsNotExist(err) {
				resolvedPath = absPath
			} else {
				return nil, fmt.Errorf(
					"failed to resolve symlinks for %s: %w", absPath, err)
			}
		}

		resolvedDirs = append(resolvedDirs, resolvedPath)
	}

	return resolvedDirs, nil
}

// scanAllDirectories runs the scanner on each resolved directory and
// accumulates stats.
func (v *Vaultik) scanAllDirectories(
	scanner *snapshot.Scanner, resolvedDirs []string, snapshotID string,
) (*snapshotStats, error) {
	stats := &snapshotStats{}

	for i, dir := range resolvedDirs {
		select {
		case <-v.ctx.Done():
			log.Info("Snapshot creation cancelled")

			return nil, v.ctx.Err()
		default:
		}

		log.Info("Scanning directory", "path", dir)
		v.UI.Beginf("Enumerating snapshot source files in %s (%d of %d).",
			v.UI.Path(dir), i+1, len(resolvedDirs))

		result, err := scanner.Scan(v.ctx, dir, snapshotID)
		if err != nil {
			return nil, fmt.Errorf("failed to scan %s: %w", dir, err)
		}

		stats.totalFiles += result.FilesScanned
		stats.totalBytes += result.BytesScanned
		stats.totalChunks += result.ChunksCreated
		stats.totalBlobs += result.BlobsCreated
		stats.totalFilesSkipped += result.FilesSkipped
		stats.totalBytesSkipped += result.BytesSkipped
		stats.totalFilesDeleted += result.FilesDeleted
		stats.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))
	}

	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, marks complete, and exports metadata
func (v *Vaultik) finalizeSnapshotMetadata(
	snapshotID string, stats *snapshotStats,
) error {
	extStats := snapshot.ExtendedBackupStats{
		BackupStats: snapshot.BackupStats{
			FilesScanned:  stats.totalFiles,
			BytesScanned:  stats.totalBytes,
			ChunksCreated: stats.totalChunks,
			BlobsCreated:  stats.totalBlobs,
			BytesUploaded: stats.totalBytesUploaded,
		},
		BlobUncompressedSize: 0,
		CompressionLevel:     v.Config.CompressionLevel,
		UploadDurationMs:     stats.uploadDuration.Milliseconds(),
	}

	err := v.SnapshotManager.UpdateSnapshotStatsExtended(v.ctx, snapshotID, extStats)
	if err != nil {
		return fmt.Errorf("updating snapshot stats: %w", err)
	}

	err = v.SnapshotManager.CompleteSnapshot(v.ctx, snapshotID)
	if err != nil {
		return fmt.Errorf("completing snapshot: %w", err)
	}

	err = v.SnapshotManager.ExportSnapshotMetadata(
		v.ctx, v.Config.IndexPath, snapshotID)
	if err != nil {
		return fmt.Errorf("exporting snapshot metadata: %w", err)
	}

	return nil
}

// uploadSpeed returns the average network upload rate as a colorized
// bits/sec string, or "N/A" when there's no usable data.
func (v *Vaultik) uploadSpeed(bytesUploaded int64, duration time.Duration) string {
	if bytesUploaded <= 0 || duration <= 0 {
		return v.UI.Speed(0)
	}

	return v.UI.Speed(float64(bytesUploaded) / duration.Seconds())
}

// printSnapshotSummary prints the comprehensive snapshot completion summary
func (v *Vaultik) printSnapshotSummary(
	snapshotID string, startTime time.Time, stats *snapshotStats,
) {
	snapshotDuration := time.Since(startTime)
	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)
	} else {
		compressionRatio = 1.0
	}

	v.UI.Completef("Created snapshot %s.", v.UI.Snapshot(snapshotID))

	filesMsg := fmt.Sprintf("Files: %s examined, %s backed up, %s unchanged",
		v.UI.Count(stats.totalFiles),
		v.UI.Count(totalFilesChanged),
		v.UI.Count(stats.totalFilesSkipped))
	if stats.totalFilesDeleted > 0 {
		filesMsg += fmt.Sprintf(", %s deleted", v.UI.Count(stats.totalFilesDeleted))
	}

	v.UI.Detailf("%s.", filesMsg)

	dataMsg := fmt.Sprintf("Data: %s total (%s backed up)",
		v.UI.Size(totalBytesAll),
		v.UI.Size(stats.totalBytes))
	if stats.totalBytesDeleted > 0 {
		dataMsg += fmt.Sprintf(", %s deleted", v.UI.Size(stats.totalBytesDeleted))
	}

	v.UI.Detailf("%s.", dataMsg)

	if stats.totalBlobsUploaded > 0 {
		v.UI.Detailf("Storage: %s compressed from %s (%.2fx ratio).",
			v.UI.Size(compressedSize),
			v.UI.Size(uncompressedSize),
			compressionRatio)
		v.UI.Detailf("Upload: %d blobs, %s in %s (%s).",
			stats.totalBlobsUploaded,
			v.UI.Size(stats.totalBytesUploaded),
			v.UI.Duration(stats.uploadDuration),
			v.uploadSpeed(stats.totalBytesUploaded, stats.uploadDuration))
	}

	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
	// OlderThan drops snapshots older than this duration (e.g. "30d",
	// "6m", "1y").
	OlderThan string
	Force     bool // Skip confirmation prompt
	// Names restricts the operation to snapshots with one of these
	// names when non-empty.
	Names []string
	Quiet bool // Suppress informational output (used by --prune flag)
}

// PurgeSnapshotsWithOptions removes old snapshots based on criteria.
// Retention is per-snapshot-name: KeepLatest keeps the latest of EACH configured
// snapshot name, not the latest globally. This prevents `home` and `system`
// snapshots from cannibalizing each other.
func (v *Vaultik) PurgeSnapshotsWithOptions(opts *SnapshotPurgeOptions) error {
	err := v.EnsureStorageBinding()
	if err != nil {
		return err
	}
	// Sync with remote first
	err = v.syncWithRemote()
	if err != nil {
		return fmt.Errorf("syncing with remote: %w", err)
	}

	// Get snapshots from local database
	dbSnapshots, err := v.Repositories.Snapshots.ListRecent(v.ctx, listRecentLimit)
	if err != nil {
		return fmt.Errorf("listing snapshots: %w", err)
	}

	// Build name filter set if --snapshot was specified.
	nameFilter := make(map[string]struct{}, len(opts.Names))
	for _, n := range opts.Names {
		nameFilter[n] = struct{}{}
	}

	// Collect completed snapshots, applying the name filter.
	snapshots := make([]SnapshotInfo, 0, len(dbSnapshots))
	for _, s := range dbSnapshots {
		if s.CompletedAt == nil {
			continue
		}

		if len(nameFilter) > 0 {
			if _, ok := nameFilter[parseSnapshotName(s.ID.String())]; !ok {
				continue
			}
		}

		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)
	})

	toDelete, err := selectSnapshotsToPurge(snapshots, opts)
	if err != nil {
		return err
	}

	if len(toDelete) == 0 {
		if !opts.Quiet {
			v.printlnStdout("No snapshots to delete")
		}

		return nil
	}

	return v.confirmAndExecutePurge(toDelete, opts.Force, opts.Quiet)
}

// selectSnapshotsToPurge applies the purge retention criteria to the
// newest-first sorted snapshot list and returns the deletion
// candidates.
func selectSnapshotsToPurge(
	snapshots []SnapshotInfo, opts *SnapshotPurgeOptions,
) ([]SnapshotInfo, error) {
	var toDelete []SnapshotInfo

	switch {
	case opts.KeepLatest:
		// Keep the latest snapshot per snapshot name. Snapshots are sorted
		// newest-first, so the first occurrence of each name is kept.
		seen := make(map[string]bool)

		for _, snap := range snapshots {
			name := parseSnapshotName(snap.ID.String())
			if seen[name] {
				toDelete = append(toDelete, snap)

				continue
			}

			seen[name] = true
		}
	case opts.OlderThan != "":
		duration, err := parseDuration(opts.OlderThan)
		if err != nil {
			return nil, 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)
			}
		}
	}

	return toDelete, nil
}

// confirmAndExecutePurge shows deletion candidates, confirms with the
// user, and deletes snapshots.
func (v *Vaultik) confirmAndExecutePurge(
	toDelete []SnapshotInfo, force, quiet bool,
) error {
	if !quiet {
		v.stdoutf("The following snapshots will be deleted:\n\n")

		for _, snap := range toDelete {
			v.stdoutf("  %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.stdoutf("\nDelete %d snapshot(s)? [y/N] ", len(toDelete))

		var confirm string

		_, err := v.scanStdin(&confirm)
		if err != nil {
			v.printlnStdout("Cancelled")

			return nil //nolint:nilerr // treat EOF or read error as "no"
		}

		if strings.ToLower(confirm) != "y" {
			v.printlnStdout("Cancelled")

			return nil
		}
	} else if !quiet {
		v.stdoutf("\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)

		err := v.deleteSnapshotFromLocalDB(snapshotID)
		if err != nil {
			log.Error("Failed to delete from local database",
				"snapshot_id", snapshotID, "error", err)
		}

		err = v.deleteRemoteSnapshotByKey(snapshot.RemoteSnapshotKey(snapshotID))
		if err != nil {
			return fmt.Errorf("deleting snapshot %s from remote: %w", snapshotID, err)
		}
	}

	// Tidy up local DB orphans now so users don't have to run a
	// separate command after a purge. Guarded against nil for tests
	// that don't wire up a SnapshotManager.
	if v.SnapshotManager != nil {
		err := v.SnapshotManager.CleanupOrphanedData(v.ctx)
		if err != nil {
			log.Warn("Failed to clean up orphaned local data after purge",
				"error", err)
		}
	}

	if !quiet {
		v.stdoutf("Deleted %d snapshot(s)\n", len(toDelete))
		v.printlnStdout(
			"\nNote: Run 'vaultik prune' to clean up unreferenced remote 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.
// Deep verification is delegated to RunDeepVerify so this function only
// implements the shallow (existence-only) path.
func (v *Vaultik) VerifySnapshotWithOptions(
	snapshotID string, opts *VerifyOptions,
) error {
	if opts.Deep {
		return v.RunDeepVerify(snapshotID, opts)
	}

	result := &VerifyResult{
		SnapshotID: snapshotID,
		Mode:       "shallow",
	}

	v.printVerifyHeader(snapshotID, opts)

	// Download and parse manifest. The caller supplies a human
	// snapshot ID; we hash it to address remote storage.
	manifest, err := v.downloadManifestByKey(snapshot.RemoteSnapshotKey(snapshotID))
	if err != nil {
		if opts.JSON {
			result.Status = verifyStatusFailed
			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.stdoutf("Snapshot information:\n")
		v.stdoutf("  Blob count:   %d\n", manifest.BlobCount)
		v.stdoutf("  Total size:   %s\n", ubytes(manifest.TotalCompressedSize))

		if manifest.Timestamp != "" {
			t, terr := time.Parse(time.RFC3339, manifest.Timestamp)
			if terr == nil {
				v.stdoutf("  Created:      %s\n",
					t.Format("2006-01-02 15:04:05 MST"))
			}
		}

		v.printlnStdout()

		// Check each blob exists
		v.stdoutf("Checking blob existence...\n")
	}

	result.Verified, result.Missing, result.MissingSize =
		v.verifyManifestBlobsExist(manifest, opts)

	return v.formatVerifyResult(result, manifest, opts)
}

// printVerifyHeader prints the snapshot ID and parsed timestamp for
// verification output. Snapshot ID format: hostname[_name]_<RFC3339>
func (v *Vaultik) printVerifyHeader(snapshotID string, opts *VerifyOptions) {
	var snapshotTime time.Time

	t, err := parseSnapshotTimestamp(snapshotID)
	if err == nil {
		snapshotTime = t
	}

	if !opts.JSON {
		v.stdoutf("Verifying snapshot %s\n", snapshotID)

		if !snapshotTime.IsZero() {
			v.stdoutf("Snapshot time: %s\n",
				snapshotTime.Format("2006-01-02 15:04:05 MST"))
		}

		v.printlnStdout()
	}
}

// verifyManifestBlobsExist checks that each blob in the manifest exists
// in storage, returning the verified count, missing count, and total
// missing bytes.
func (v *Vaultik) verifyManifestBlobsExist(
	manifest *snapshot.Manifest, opts *VerifyOptions,
) (int, int, int64) {
	var (
		verified, missing int
		missingSize       int64
	)

	for _, blob := range manifest.Blobs {
		blobPath := fmt.Sprintf("blobs/%s/%s/%s",
			blob.Hash[:2], blob.Hash[2:4], blob.Hash)

		// Shallow: check existence only (deep verification is handled
		// by RunDeepVerify).
		_, err := v.Storage.Stat(v.ctx, blobPath)
		if err != nil {
			if !opts.JSON {
				v.stdoutf("  Missing: %s (%s)\n",
					blob.Hash, ubytes(blob.CompressedSize))
			}

			missing++
			missingSize += blob.CompressedSize
		} else {
			verified++
		}
	}

	return verified, missing, missingSize
}

// formatVerifyResult outputs the final verification results as JSON or
// human-readable text.
func (v *Vaultik) formatVerifyResult(
	result *VerifyResult, manifest *snapshot.Manifest, opts *VerifyOptions,
) error {
	if opts.JSON {
		if result.Missing > 0 {
			result.Status = verifyStatusFailed
			result.ErrorMessage = fmt.Sprintf("%d blobs are missing", result.Missing)
		} else {
			result.Status = "ok"
		}

		return v.outputVerifyJSON(result)
	}

	v.stdoutf("\nVerification complete:\n")
	v.stdoutf("  Verified:     %d blobs (%s)\n", result.Verified,
		ubytes(manifest.TotalCompressedSize-result.MissingSize))

	if result.Missing > 0 {
		v.stdoutf("  Missing:      %d blobs (%s)\n",
			result.Missing, ubytes(result.MissingSize))
	} else {
		v.stdoutf("  Missing:      0 blobs\n")
	}

	v.stdoutf("  Status:       ")

	if result.Missing > 0 {
		v.stdoutf("FAILED - %d blobs are missing\n", result.Missing)

		return fmt.Errorf("%d %w", result.Missing, errBlobsMissing)
	}

	v.stdoutf("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("", "  ")

	err := encoder.Encode(result)
	if err != nil {
		return fmt.Errorf("encoding JSON: %w", err)
	}

	if result.Status == verifyStatusFailed {
		return fmt.Errorf("%w: %s", errSnapshotVerifyFailed, result.ErrorMessage)
	}

	return nil
}

// CleanupLocalSnapshots removes local snapshot records that have no
// corresponding metadata in remote storage. These are typically left
// behind by incomplete or interrupted backups. Each local snapshot's
// human ID is hashed via RemoteSnapshotKey and compared against the
// remote listing.
//
// It takes the whole *PruneOptions, symmetric with PruneBlobs, because
// it is the other half of one command: Prune runs this phase and then
// that one. Only JSON is read here. Under --json every write below is
// suppressed, because stdout carries the PruneBlobsResult document and
// nothing else — prose ahead of it is what made `vaultik prune --json |
// jq` fail (issue #108). The narration is duplicated as log records,
// which go to stderr and so cannot corrupt the document.
func (v *Vaultik) CleanupLocalSnapshots(opts *PruneOptions) error {
	err := v.EnsureStorageBinding()
	if err != nil {
		return err
	}

	remoteKeys, err := v.listAllRemoteSnapshotKeys()
	if err != nil {
		return err
	}

	remoteSet := make(map[string]bool, len(remoteKeys))
	for _, k := range remoteKeys {
		remoteSet[k] = true
	}

	localSnapshots, err := v.Repositories.Snapshots.ListRecent(v.ctx, listRecentLimit)
	if err != nil {
		return fmt.Errorf("listing local snapshots: %w", err)
	}

	var removed int

	for _, snap := range localSnapshots {
		id := snap.ID.String()
		if !remoteSet[snapshot.RemoteSnapshotKey(id)] {
			log.Info("Removing stale local snapshot record", "snapshot_id", id)

			if !opts.JSON {
				v.stdoutf("Removing stale local record: %s\n", id)
			}

			err = v.deleteSnapshotFromLocalDB(id)
			if err != nil {
				log.Error("Failed to delete local snapshot",
					"snapshot_id", id, "error", err)

				continue
			}

			removed++
		}
	}

	log.Info("Reconciled local snapshot records against remote metadata",
		"removed", removed, "examined", len(localSnapshots))

	if opts.JSON {
		return nil
	}

	if removed == 0 {
		v.printlnStdout("No stale local snapshots found.")
	} else {
		v.stdoutf("Removed %d stale local snapshot record(s).\n", removed)
	}

	return nil
}

// Helper methods that were previously on SnapshotApp

// downloadManifestByKey fetches the manifest at
// metadata/<remoteKey>/manifest.json.zst. The remoteKey is the double-
// SHA256 derivation produced by snapshot.RemoteSnapshotKey, not the
// human snapshot ID. Callers that have a human ID must hash first.
//
// This is the only place vaultik reads a manifest off the destination
// store, deliberately: the manifest is currently stored compressed but
// unencrypted, which is what lets `snapshot list` enumerate the
// destination on a host holding no private key. Whether to encrypt it
// is open (issue #81), and routing every read through here means that
// decision has exactly one call site to change. Keep it that way — do
// not open metadata/<key>/manifest.json.zst directly elsewhere.
func (v *Vaultik) downloadManifestByKey(remoteKey string) (*snapshot.Manifest, error) {
	manifestPath := fmt.Sprintf("metadata/%s/manifest.json.zst", remoteKey)

	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) >= minSnapshotIDParts &&
			parts[0] == metadataDirName && 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, listRecentLimit)
	if err != nil {
		return fmt.Errorf("listing local snapshots: %w", err)
	}

	// Remove local snapshots that don't exist remotely
	removedCount := 0

	for _, snap := range localSnapshots {
		snapshotIDStr := snap.ID.String()
		if !remoteSnapshots[snapshotIDStr] {
			log.Info("Removing local snapshot not found in remote",
				"snapshot_id", snap.ID)

			err = v.deleteSnapshotFromLocalDB(snapshotIDStr)
			if err != nil {
				log.Error("Failed to delete local snapshot",
					"snapshot_id", snap.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
	LocalOnly bool // Skip remote cleanup; only touch the local index
}

// RemoveResult contains the result of a snapshot removal
//
//nolint:tagliatelle // snake_case is the established JSON output format
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"`
}

// pruneCommandHint is the exact command suggested after a remove
// completes so the user knows how to clean up the blobs that the
// just-removed snapshot left behind on the destination store.
const pruneCommandHint = "vaultik prune"

// RemoveSnapshot removes a snapshot from the local index database and,
// unless LocalOnly is set, also strips the snapshot's metadata from the
// destination store. Blobs are NOT touched: removing a snapshot's
// blobs requires reading every remaining remote manifest (the remote
// may hold snapshots this host doesn't know about), which is what
// `vaultik prune` is for — the command prints the prune invocation to
// run as a follow-up. When the remote is unreachable the command still
// completes the local-DB removal and warns.
func (v *Vaultik) RemoveSnapshot(
	snapshotID string, opts *RemoveOptions,
) (*RemoveResult, error) {
	result := &RemoveResult{
		SnapshotID: snapshotID,
	}

	err := v.EnsureStorageBinding()
	if err != nil {
		return result, err
	}

	if opts.DryRun {
		return v.removeSnapshotDryRun(result, snapshotID, opts)
	}

	if !opts.Force && !opts.JSON && !v.confirmRemoveSnapshot(snapshotID, opts) {
		return result, nil
	}

	log.Info("Removing snapshot from local database", "snapshot_id", snapshotID)

	err = v.deleteSnapshotFromLocalDB(snapshotID)
	if err != nil {
		return result, fmt.Errorf("removing from local database: %w", err)
	}

	if !opts.LocalOnly {
		result.RemoteRemoved = v.removeSnapshotRemote(snapshotID)
	}

	if v.SnapshotManager != nil {
		err = v.SnapshotManager.CleanupOrphanedData(v.ctx)
		if err != nil {
			log.Warn("Failed to clean up orphaned local data after removal",
				"error", err)
		}
	}

	if opts.JSON {
		return result, v.outputRemoveJSON(result)
	}

	v.stdoutf("Removed snapshot '%s' from local database\n", snapshotID)

	if !opts.LocalOnly && result.RemoteRemoved {
		v.printlnStdout("Removed snapshot metadata from remote storage")
		v.stdoutf("\nNote: The removed snapshot's blobs remain on the remote. "+
			"Run '%s' to delete any blobs no longer referenced by any "+
			"remaining remote snapshot.\n", pruneCommandHint)
	}

	return result, nil
}

// removeSnapshotDryRun reports what RemoveSnapshot would do without
// making changes.
func (v *Vaultik) removeSnapshotDryRun(
	result *RemoveResult, snapshotID string, opts *RemoveOptions,
) (*RemoveResult, error) {
	result.DryRun = true

	if opts.JSON {
		return result, v.outputRemoveJSON(result)
	}

	v.stdoutf("Would remove snapshot: %s\n", snapshotID)

	if !opts.LocalOnly {
		v.printlnStdout("Would also remove snapshot metadata from " +
			"remote storage (blobs untouched)")
	}

	v.printlnStdout("[Dry run - no changes made]")

	return result, nil
}

// confirmRemoveSnapshot prompts for confirmation before removing a
// snapshot. Returns false (treating EOF/read errors as "no") unless the
// user answers "y".
func (v *Vaultik) confirmRemoveSnapshot(snapshotID string, opts *RemoveOptions) bool {
	if opts.LocalOnly {
		v.stdoutf("Remove snapshot '%s' from local database "+
			"(remote untouched)? [y/N] ", snapshotID)
	} else {
		v.stdoutf("Remove snapshot '%s' from local database AND its metadata "+
			"from remote storage? [y/N] ", snapshotID)
	}

	var confirm string

	_, err := v.scanStdin(&confirm)
	if err != nil {
		v.printlnStdout("Cancelled")

		return false
	}

	if strings.ToLower(confirm) != "y" {
		v.printlnStdout("Cancelled")

		return false
	}

	return true
}

// removeSnapshotRemote strips the snapshot's metadata from the
// destination store, warning and proceeding on failure: the local-DB
// removal has already happened, so the user is told the remote half
// didn't finish and can retry with `vaultik prune` once the destination
// store is reachable. Returns true when the remote removal succeeded.
func (v *Vaultik) removeSnapshotRemote(snapshotID string) bool {
	log.Info("Removing snapshot metadata from remote storage",
		"snapshot_id", snapshotID)

	remoteKey := snapshot.RemoteSnapshotKey(snapshotID)

	err := v.deleteRemoteSnapshotByKey(remoteKey)
	if err != nil {
		log.Warn("Could not remove snapshot metadata from remote storage",
			"error", err)

		if v.UI != nil {
			v.UI.Warningf("Could not remove snapshot metadata from remote: "+
				"%v. Run '%s' once the remote is reachable to finish cleanup.",
				err, pruneCommandHint)
		}

		return false
	}

	return true
}

// RemoveAllSnapshots removes every snapshot known to the local
// database from the local index, and (with --remote) every snapshot
// metadata directory in remote storage. Both sides are processed so a
// "remove --all" leaves nothing behind, even when the local DB and
// remote storage have diverged.
func (v *Vaultik) RemoveAllSnapshots(opts *RemoveOptions) (*RemoveResult, error) {
	err := v.EnsureStorageBinding()
	if err != nil {
		return nil, err
	}

	localSnaps, err := v.localSnapshotIDs()
	if err != nil {
		return nil, fmt.Errorf("listing local snapshots: %w", err)
	}

	// remoteKeys is the set of metadata/<key>/ subdirectories on the
	// destination store; failures are downgraded to a warning so a
	// permission-denied or unreachable remote can't block a local-only
	// remove.
	remoteKeys, remoteErr := v.listAllRemoteSnapshotKeys()
	if remoteErr != nil {
		log.Warn("Could not list remote snapshots", "error", remoteErr)
		v.UI.Warningf("Could not list remote snapshots: %v.", remoteErr)
	}

	// Anything visible on the remote that doesn't correspond to a
	// known local human ID is treated as an orphan key — handled only
	// when --remote is in effect.
	knownLocalKeys := make(map[string]string, len(localSnaps))
	for _, id := range localSnaps {
		knownLocalKeys[snapshot.RemoteSnapshotKey(id)] = id
	}

	var orphanRemoteKeys []string

	for _, key := range remoteKeys {
		if _, known := knownLocalKeys[key]; !known {
			orphanRemoteKeys = append(orphanRemoteKeys, key)
		}
	}

	if len(localSnaps) == 0 && len(orphanRemoteKeys) == 0 {
		if !opts.JSON {
			v.printlnStdout("No snapshots found")
		}

		return &RemoveResult{}, nil
	}

	if opts.DryRun {
		return v.handleRemoveAllDryRun(localSnaps, orphanRemoteKeys, opts)
	}

	return v.executeRemoveAll(localSnaps, orphanRemoteKeys, opts)
}

// localSnapshotIDs returns every snapshot ID present in the local
// index database, sorted for deterministic iteration. Empty slice if
// the database has no Repositories (e.g. tests).
func (v *Vaultik) localSnapshotIDs() ([]string, error) {
	if v.Repositories == nil {
		return nil, nil
	}

	snaps, err := v.Repositories.Snapshots.ListRecent(v.ctx, listRecentLimit)
	if err != nil {
		return nil, err
	}

	ids := make([]string, 0, len(snaps))
	for _, s := range snaps {
		ids = append(ids, s.ID.String())
	}

	sort.Strings(ids)

	return ids, nil
}

// listAllRemoteSnapshotKeys collects the hashed remote keys
// (subdirectories under metadata/) currently present in the
// destination store. Returns (nil, err) when the store cannot be
// listed; callers must treat that as "no remote info available," not
// fatal.
func (v *Vaultik) listAllRemoteSnapshotKeys() ([]string, error) {
	log.Info("Listing all remote snapshots")

	objectCh := v.Storage.ListStream(v.ctx, "metadata/")

	seen := make(map[string]bool)

	var keys []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) >= minSnapshotIDParts &&
			parts[0] == metadataDirName && 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") {
				key := parts[1]
				if !seen[key] {
					seen[key] = true
					keys = append(keys, key)
				}
			}
		}
	}

	return keys, nil
}

// handleRemoveAllDryRun handles the dry-run mode for removing all snapshots
func (v *Vaultik) handleRemoveAllDryRun(
	localSnaps, orphanRemoteKeys []string, opts *RemoveOptions,
) (*RemoveResult, error) {
	result := &RemoveResult{DryRun: true}

	result.SnapshotsRemoved = append(result.SnapshotsRemoved, localSnaps...)
	if !opts.LocalOnly {
		result.SnapshotsRemoved = append(
			result.SnapshotsRemoved, orphanRemoteKeys...)
	}

	if !opts.JSON {
		v.stdoutf("Would remove %d local snapshot(s):\n", len(localSnaps))

		for _, id := range localSnaps {
			v.stdoutf("  %s\n", id)
		}

		if !opts.LocalOnly {
			if len(orphanRemoteKeys) > 0 {
				v.stdoutf("Would also remove %d orphan remote snapshot key(s):\n",
					len(orphanRemoteKeys))

				for _, key := range orphanRemoteKeys {
					v.stdoutf("  %s\n", key)
				}
			} else {
				v.printlnStdout("Would also remove snapshot metadata from " +
					"remote storage (blobs untouched)")
			}
		}

		v.printlnStdout("[Dry run - no changes made]")
	}

	if opts.JSON {
		return result, v.outputRemoveJSON(result)
	}

	return result, nil
}

// executeRemoveAll deletes every local snapshot and, unless LocalOnly
// is set, every corresponding remote metadata directory plus any
// orphan remote keys. Blobs are not touched; the printed prune-command
// hint is the next step.
func (v *Vaultik) executeRemoveAll(
	localSnaps, orphanRemoteKeys []string, opts *RemoveOptions,
) (*RemoveResult, error) {
	if !opts.Force {
		return nil, errRemoveAllNeedsForce
	}

	log.Info("Removing all snapshots",
		"local_count", len(localSnaps),
		"orphan_remote_count", len(orphanRemoteKeys))

	result := &RemoveResult{}

	remoteErrors := v.removeAllLocalSnapshots(localSnaps, opts, result)

	if !opts.LocalOnly {
		remoteErrors += v.removeAllOrphanRemotes(orphanRemoteKeys, result)

		if remoteErrors == 0 {
			result.RemoteRemoved = true
		} else if v.UI != nil {
			v.UI.Warningf("Some remote metadata deletions failed. Run '%s' "+
				"once the remote is healthy to clean up unreferenced blobs.",
				pruneCommandHint)
		}
	}

	if v.SnapshotManager != nil {
		err := v.SnapshotManager.CleanupOrphanedData(v.ctx)
		if err != nil {
			log.Warn("Failed to clean up orphaned local data after bulk removal", "error", err)
		}
	}

	if opts.JSON {
		return result, v.outputRemoveJSON(result)
	}

	v.stdoutf("Removed %d snapshot(s)\n", len(result.SnapshotsRemoved))

	if !opts.LocalOnly && result.RemoteRemoved {
		v.printlnStdout("Removed snapshot metadata from remote storage")
		v.stdoutf("\nNote: Removed snapshots' blobs remain on the remote. "+
			"Run '%s' to delete any blobs no longer referenced by any "+
			"remaining remote snapshot.\n", pruneCommandHint)
	}

	return result, nil
}

// deleteIncompleteSnapshot deletes one incomplete snapshot and its
// association rows, reporting whether the snapshot row itself was
// deleted.
func (v *Vaultik) deleteIncompleteSnapshot(snapshotIDStr string, id any) bool {
	log.Info("Deleting incomplete snapshot", "snapshot_id", id)

	// Delete related records first
	err := v.Repositories.Snapshots.DeleteSnapshotFiles(v.ctx, snapshotIDStr)
	if err != nil {
		log.Error("Failed to delete snapshot files",
			"snapshot_id", id, "error", err)
	}

	err = v.Repositories.Snapshots.DeleteSnapshotBlobs(v.ctx, snapshotIDStr)
	if err != nil {
		log.Error("Failed to delete snapshot blobs",
			"snapshot_id", id, "error", err)
	}

	err = v.Repositories.Snapshots.DeleteSnapshotUploads(v.ctx, snapshotIDStr)
	if err != nil {
		log.Error("Failed to delete snapshot uploads",
			"snapshot_id", id, "error", err)
	}

	err = v.Repositories.Snapshots.Delete(v.ctx, snapshotIDStr)
	if err != nil {
		log.Error("Failed to delete snapshot",
			"snapshot_id", id, "error", err)

		return false
	}

	return true
}

// removeAllLocalSnapshots removes each known local snapshot (and, unless
// --local-only, its remote metadata), returning the number of remote
// deletion failures.
func (v *Vaultik) removeAllLocalSnapshots(
	localSnaps []string, opts *RemoveOptions, result *RemoveResult,
) int {
	remoteErrors := 0

	for _, snapshotID := range localSnaps {
		log.Info("Removing snapshot", "snapshot_id", snapshotID)

		err := v.deleteSnapshotFromLocalDB(snapshotID)
		if err != nil {
			log.Error("Failed to remove from local database",
				"snapshot_id", snapshotID, "error", err)

			continue
		}

		if !opts.LocalOnly {
			err = v.deleteRemoteSnapshotByKey(
				snapshot.RemoteSnapshotKey(snapshotID))
			if err != nil {
				log.Warn("Failed to remove snapshot metadata from remote",
					"snapshot_id", snapshotID, "error", err)

				remoteErrors++
			}
		}

		result.SnapshotsRemoved = append(result.SnapshotsRemoved, snapshotID)
	}

	return remoteErrors
}

// removeAllOrphanRemotes deletes remote snapshot metadata that has no
// local counterpart, returning the number of deletion failures.
func (v *Vaultik) removeAllOrphanRemotes(
	orphanRemoteKeys []string, result *RemoveResult,
) int {
	remoteErrors := 0

	for _, key := range orphanRemoteKeys {
		log.Info("Removing orphan remote snapshot", "remote_key", key)

		err := v.deleteRemoteSnapshotByKey(key)
		if err != nil {
			log.Warn("Failed to remove orphan from remote",
				"remote_key", key, "error", err)

			remoteErrors++

			continue
		}

		result.SnapshotsRemoved = append(result.SnapshotsRemoved, key)
	}

	return remoteErrors
}

// 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
	err := v.Repositories.Snapshots.DeleteSnapshotFiles(v.ctx, snapshotID)
	if err != nil {
		return fmt.Errorf("deleting snapshot files for %s: %w", snapshotID, err)
	}

	err = v.Repositories.Snapshots.DeleteSnapshotBlobs(v.ctx, snapshotID)
	if err != nil {
		return fmt.Errorf("deleting snapshot blobs for %s: %w", snapshotID, err)
	}

	err = v.Repositories.Snapshots.DeleteSnapshotUploads(v.ctx, snapshotID)
	if err != nil {
		return fmt.Errorf("deleting snapshot uploads for %s: %w", snapshotID, err)
	}

	err = v.Repositories.Snapshots.Delete(v.ctx, snapshotID)
	if err != nil {
		return fmt.Errorf("deleting snapshot record %s: %w", snapshotID, err)
	}

	return nil
}

// deleteRemoteSnapshotByKey removes everything under
// metadata/<remoteKey>/ on the destination store. The argument is a
// remote key (double-SHA256 derivation), not a human snapshot ID;
// callers that have a human ID must hash via snapshot.RemoteSnapshotKey
// first.
func (v *Vaultik) deleteRemoteSnapshotByKey(remoteKey string) error {
	prefix := fmt.Sprintf("metadata/%s/", remoteKey)
	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 {
		err := v.Storage.Delete(v.ctx, key)
		if 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")
	v.UI.Beginf("Pruning local index database " +
		"(removing incomplete snapshots and orphaned data).")

	result := &PruneResult{}

	// Snapshot counts before deletion of incompletes.
	snapshotCountBefore, _ := v.getTableCount("snapshots")

	// 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 _, snap := range incompleteSnapshots {
		if v.deleteIncompleteSnapshot(snap.ID.String(), snap.ID) {
			result.SnapshotsDeleted++
		}
	}

	// Get counts before cleanup for reporting
	fileCountBefore, _ := v.getTableCount("files")
	chunkCountBefore, _ := v.getTableCount("chunks")
	blobCountBefore, _ := v.getTableCount("blobs")

	// Run the cleanup
	err = v.SnapshotManager.CleanupOrphanedData(v.ctx)
	if 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,
	)

	snapshotCountAfter := snapshotCountBefore - result.SnapshotsDeleted

	v.UI.Completef("Pruned local index database.")
	v.UI.Detailf("Incomplete snapshots: %d removed (%d remain).",
		result.SnapshotsDeleted, snapshotCountAfter)
	v.UI.Detailf("Orphaned files: %d removed (%d remain).",
		result.FilesDeleted, fileCountAfter)
	v.UI.Detailf("Orphaned chunks: %d removed (%d remain).",
		result.ChunksDeleted, chunkCountAfter)
	v.UI.Detailf("Orphaned blobs: %d removed (%d remain).",
		result.BlobsDeleted, blobCountAfter)

	return result, nil
}

// validTableNameRe matches table names containing only lowercase
// alphanumeric characters and underscores.
var validTableNameRe = regexp.MustCompile(`^[a-z0-9_]+$`)

// getTableCount returns the count of rows in a table. The tableName is
// sanitized to only allow [a-z0-9_] characters to prevent SQL
// injection.
func (v *Vaultik) getTableCount(tableName string) (int64, error) {
	if v.DB == nil {
		return 0, nil
	}

	if !validTableNameRe.MatchString(tableName) {
		return 0, fmt.Errorf("%w: %q", errInvalidTableName, tableName)
	}

	var count int64

	query := "SELECT COUNT(*) FROM " + tableName

	err := v.DB.Conn().QueryRowContext(v.ctx, query).Scan(&count)
	if err != nil {
		return 0, err
	}

	return count, nil
}