Stop restore --verify re-reporting files that failed to restore (closes #323)

With --skip-errors, a file that failed to restore was verified anyway,
failed again because it was never written, and was added to the same
failure list as the restore failure. restore --verify then listed it
twice and called every entry a checksum mismatch.

Verification now skips the files that failed to restore and keeps its
own failures in a separate list, so failed restores and failed
verifications are reported apart, each path once. The restore still
exits non-zero.

Model: opus-5-5

README.md

@@ -375,7 +375,9 @@ on the destination in one go, use `vaultik remote nuke --force`.
 * Optional path arguments to restore specific files/directories (default: all)
 * Preserves file permissions, timestamps, ownership (ownership requires root),
   symlinks, and empty directories
-* `--verify`: After restoring, verify every file's chunk hashes match
+* `--verify`: After restoring, verify every restored file's chunk hashes
+  match. A file skipped under `--skip-errors` is reported as failed to
+  restore and is not verified.
 
 **`prune`**: Tidy up everything that isn't needed. Runs three passes:
 (1) reconcile the local index against the destination store — any
@@ -433,10 +435,7 @@ object store. Credentials are read from `s3.access_key_id` and
 `s3.secret_access_key` in the config file.
 
 **Local filesystem** (`file:///path/to/backup`): Stores blobs and metadata on
-a local or mounted filesystem. Useful for testing or backing up to a NAS. The
-path must be absolute; a relative one is refused when the config loads.
-Percent-escapes in the path are decoded, so `my%20stick` and `my stick` name
-the same directory.
+a local or mounted filesystem. Useful for testing or backing up to a NAS.
 
 **Rclone** (`rclone://remote/path`): Uses rclone's 70+ supported cloud
 providers. Requires rclone to be configured separately (`rclone config`).

internal/blob/packer.go

@@ -245,17 +245,6 @@ func (p *Packer) Flush(ctx context.Context) error {
 	return nil
 }
 
-// DiscardCurrentBlob closes and removes the temp file of the blob being
-// packed, if any, and drops that blob. A caller that stops before Flush
-// must call it, or the temp file is left behind. Thread-safe.
-func (p *Packer) DiscardCurrentBlob() {
-	p.mu.Lock()
-	defer p.mu.Unlock()
-
-	p.cleanupTempFile()
-	p.currentBlob = nil
-}
-
 // FinalizeBlob finalizes the current blob being assembled.
 // This compresses the accumulated chunks, encrypts the result, and computes
 // the content-addressed hash. The finalized blob is either passed to the

internal/config/config.go

@@ -61,9 +61,6 @@ var (
 	errBadS3PartSize    = errors.New("s3.part_size must be between 5MiB and 5GiB")
 	errBadStorageScheme = errors.New(
 		"storage_url must start with s3://, file://, or rclone://")
-	errFileURLNotAbsolute = errors.New(
-		"a file:// storage_url needs an absolute path, " +
-			"as in file:///path/to/backup")
 	errStorageNotConfigured = errors.New(
 		"storage not configured; set storage_url or provide s3.endpoint + " +
 			"s3.bucket + credentials")
@@ -464,18 +461,11 @@ func (c *Config) validateStorage() error {
 
 // validateStorageURL validates URL-based storage configuration. File and
 // rclone URLs need no credentials; S3 URLs require the legacy s3.*
-// credential fields. A file URL must name an absolute path: a relative one
-// would resolve against the working directory, so the destination would
-// move with it.
+// credential fields.
 func (c *Config) validateStorageURL() error {
 	switch {
 	case strings.HasPrefix(c.StorageURL, "file://"):
-		// storage.ParseStorageURL applies the same rule, but config
-		// cannot import storage, which imports config.
-		if !strings.HasPrefix(c.StorageURL, "file:///") {
-			return errFileURLNotAbsolute
-		}
-
+		// File storage doesn't need S3 credentials
 		return nil
 	case strings.HasPrefix(c.StorageURL, "rclone://"):
 		// Rclone storage uses rclone's own config

internal/config/config_test.go

@@ -337,35 +337,6 @@ func TestLoadS3PartSize(t *testing.T) {
 	})
 }
 
-// TestLoadRejectsRelativeFileURL checks that a file:// storage_url with a
-// relative path fails at load. Accepted, it would resolve against the
-// working directory, so a backup run from another directory would write
-// to a different destination and still succeed.
-func TestLoadRejectsRelativeFileURL(t *testing.T) {
-	t.Parallel()
-
-	const relativeConfig = "snapshots:\n" +
-		"  test:\n" +
-		"    paths: [/tmp/vaultik-test-source]\n" +
-		"storage_url: file://dest\n"
-
-	path := filepath.Join(t.TempDir(), "config.yml")
-
-	err := os.WriteFile(path, []byte(relativeConfig), 0o600)
-	if err != nil {
-		t.Fatalf("write config: %v", err)
-	}
-
-	_, err = Load(path)
-	if !errors.Is(err, errFileURLNotAbsolute) {
-		t.Fatalf("Load() error = %v, want errFileURLNotAbsolute", err)
-	}
-
-	if !strings.Contains(err.Error(), "absolute path") {
-		t.Errorf("error %q does not say to use an absolute path", err.Error())
-	}
-}
-
 // TestValidateAgeRecipients checks that recipients are parsed at config load
 // (a bad entry fails immediately, not mid-backup) and that no invalid entry —
 // least of all a pasted secret key — is echoed in the error. An empty list

internal/snapshot/scanner.go

@@ -1295,11 +1295,6 @@ func (s *Scanner) batchAddFilesToSnapshot(
 func (s *Scanner) processPhase(
 	ctx context.Context, filesToProcess []*FileToProcess, result *ScanResult,
 ) error {
-	// On an error or cancellation the blob being packed is never
-	// finalized, so its temp file must be removed here. After a
-	// successful flush there is no such blob and this does nothing.
-	defer s.packer.DiscardCurrentBlob()
-
 	// Calculate total bytes to process
 	var totalBytes int64
 	for _, f := range filesToProcess {

internal/snapshot/skip_errors_test.go

@@ -381,60 +381,3 @@ func TestScannerCancelStopsSkipErrorsRun(t *testing.T) {
 		})
 	}
 }
-
-// TestScannerRemovesBlobTempFileWhenRunStops checks that a run stopped
-// part-way, by a file it cannot read or by a cancellation, removes the
-// temp file of the blob it was packing.
-func TestScannerRemovesBlobTempFileWhenRunStops(t *testing.T) {
-	t.Parallel()
-
-	// a.txt is backed up first and starts a blob; the run stops at b.txt.
-	const target = "/source/b.txt"
-
-	tests := []struct {
-		name  string
-		newFs func(cancel context.CancelFunc) afero.Fs
-	}{
-		{
-			name: "file cannot be read",
-			newFs: func(context.CancelFunc) afero.Fs {
-				return &readFailFs{Fs: afero.NewMemMapFs(), target: target}
-			},
-		},
-		{
-			name: "cancelled",
-			newFs: func(cancel context.CancelFunc) afero.Fs {
-				return &cancelOnOpenFs{
-					Fs: afero.NewMemMapFs(), target: target, cancel: cancel,
-				}
-			},
-		},
-	}
-
-	for _, tt := range tests {
-		t.Run(tt.name, func(t *testing.T) {
-			t.Parallel()
-
-			ctx, cancel := context.WithCancel(context.Background())
-			defer cancel()
-
-			fs := tt.newFs(cancel)
-			writeSkipErrorTestFile(t, fs, "/source/a.txt", "first file content")
-			writeSkipErrorTestFile(t, fs, target, "second file content")
-
-			_, err := runSkipErrorScan(ctx, t, fs, "/source", false, nil)
-			if err == nil {
-				t.Fatal("expected the scan to stop with an error, got nil")
-			}
-
-			left, err := afero.Glob(fs, filepath.Join(os.TempDir(), "vaultik-blob-*"))
-			if err != nil {
-				t.Fatalf("listing blob temp files: %v", err)
-			}
-
-			if len(left) != 0 {
-				t.Fatalf("expected no blob temp file left, got %v", left)
-			}
-		})
-	}
-}

internal/storage/url.go

@@ -17,10 +17,8 @@ const (
 
 // Sentinel errors for storage URL parsing.
 var (
-	ErrEmptyStorageURL  = errors.New("storage URL is empty")
-	ErrEmptyFilePath    = errors.New("file URL path is empty")
-	ErrRelativeFilePath = errors.New(
-		"file URL needs an absolute path, as in file:///path/to/backup")
+	ErrEmptyStorageURL   = errors.New("storage URL is empty")
+	ErrEmptyFilePath     = errors.New("file URL path is empty")
 	ErrMissingBucket     = errors.New("s3 URL missing bucket name")
 	ErrMissingRemote     = errors.New("rclone URL missing remote name")
 	ErrUnsupportedScheme = errors.New(
@@ -53,8 +51,17 @@ func ParseStorageURL(rawURL string) (*URL, error) {
 		return nil, ErrEmptyStorageURL
 	}
 
+	// Handle file:// URLs
 	if after, ok := strings.CutPrefix(rawURL, "file://"); ok {
-		return parseFileURL(after)
+		path := after
+		if path == "" {
+			return nil, ErrEmptyFilePath
+		}
+
+		return &URL{
+			Scheme: schemeFile,
+			Prefix: path,
+		}, nil
 	}
 
 	if strings.HasPrefix(rawURL, "s3://") {
@@ -68,27 +75,6 @@ func ParseStorageURL(rawURL string) (*URL, error) {
 	return nil, ErrUnsupportedScheme
 }
 
-// parseFileURL parses the path that follows file://. The path must be
-// absolute: a relative one would resolve against the working directory,
-// so the destination would move with it. Percent-escapes are decoded, so
-// my%20stick names the directory "my stick"; a literal space is kept.
-func parseFileURL(rawPath string) (*URL, error) {
-	if rawPath == "" {
-		return nil, ErrEmptyFilePath
-	}
-
-	if !strings.HasPrefix(rawPath, "/") {
-		return nil, ErrRelativeFilePath
-	}
-
-	path, err := url.PathUnescape(rawPath)
-	if err != nil {
-		return nil, fmt.Errorf("invalid file URL path: %w", err)
-	}
-
-	return &URL{Scheme: schemeFile, Prefix: path}, nil
-}
-
 // parseS3URL parses an s3://bucket/prefix URL. It rejects credentials in
 // the userinfo and any query parameter other than endpoint, region and
 // ssl, so a credential-bearing URL is never stored or echoed.

internal/storage/url_parse_test.go

@@ -14,10 +14,7 @@ import (
 func TestParseStorageURLValid(t *testing.T) {
 	t.Parallel()
 
-	const (
-		bucket     = "mybucket"
-		fileScheme = "file"
-	)
+	const bucket = "mybucket"
 
 	cases := []struct {
 		name string
@@ -27,17 +24,7 @@ func TestParseStorageURLValid(t *testing.T) {
 		{
 			name: "file absolute path",
 			raw:  "file:///var/backups/vaultik",
-			want: &storage.URL{Scheme: fileScheme, Prefix: "/var/backups/vaultik"},
-		},
-		{
-			name: "file percent-escaped path is decoded",
-			raw:  "file:///Volumes/my%20stick/backup",
-			want: &storage.URL{Scheme: fileScheme, Prefix: "/Volumes/my stick/backup"},
-		},
-		{
-			name: "file path with a literal space",
-			raw:  "file:///Volumes/my stick/backup",
-			want: &storage.URL{Scheme: fileScheme, Prefix: "/Volumes/my stick/backup"},
+			want: &storage.URL{Scheme: "file", Prefix: "/var/backups/vaultik"},
 		},
 		{
 			name: "s3 bucket and prefix, ssl defaults on",
@@ -103,7 +90,6 @@ func TestParseStorageURLErrors(t *testing.T) {
 	}{
 		{"empty url", "", storage.ErrEmptyStorageURL},
 		{"file empty path", "file://", storage.ErrEmptyFilePath},
-		{"file relative path", "file://dest", storage.ErrRelativeFilePath},
 		{"s3 missing bucket", "s3://", storage.ErrMissingBucket},
 		{"s3 missing bucket with path", "s3:///justprefix", storage.ErrMissingBucket},
 		{"rclone missing remote", "rclone://", storage.ErrMissingRemote},

internal/vaultik/blob_fetch.go

@@ -103,8 +103,6 @@ func (v *Vaultik) FetchAndDecryptBlob(
 }
 
 // FetchBlob downloads a blob and returns a reader for the encrypted data.
-// The reader is closed as soon as ctx is cancelled, which ends a read
-// blocked inside it.
 func (v *Vaultik) FetchBlob(
 	ctx context.Context, blobHash string,
 ) (io.ReadCloser, error) {
@@ -122,47 +120,5 @@ func (v *Vaultik) FetchBlob(
 		return nil, fmt.Errorf("downloading blob %s: %w", shortHash(blobHash), err)
 	}
 
-	return newCloseOnCancelReader(ctx, rc), nil
-}
-
-// closeOnCancelReader closes the reader it wraps when ctx is cancelled.
-// Not every backend's reader stops on cancel by itself (the file
-// backend's does not), and a read stalled on a slow or hung source would
-// otherwise outlast the shutdown timeout, so the process would exit
-// before restore or deep verify removed its decrypted temporary files.
-type closeOnCancelReader struct {
-	io.ReadCloser
-
-	ctx  context.Context //nolint:containedctx // Read reports its error
-	stop func() bool
-}
-
-func newCloseOnCancelReader(
-	ctx context.Context, rc io.ReadCloser,
-) *closeOnCancelReader {
-	return &closeOnCancelReader{
-		ReadCloser: rc,
-		ctx:        ctx,
-		stop:       context.AfterFunc(ctx, func() { _ = rc.Close() }),
-	}
-}
-
-// Read returns the context's error, not the closed reader's, once ctx
-// has been cancelled.
-func (r *closeOnCancelReader) Read(p []byte) (int, error) {
-	n, err := r.ReadCloser.Read(p)
-	if err != nil && r.ctx.Err() != nil {
-		return n, r.ctx.Err()
-	}
-
-	return n, err
-}
-
-// Close closes the wrapped reader, unless the cancel already closed it.
-func (r *closeOnCancelReader) Close() error {
-	if !r.stop() {
-		return nil
-	}
-
-	return r.ReadCloser.Close()
+	return rc, nil
 }

internal/vaultik/restore.go

@@ -103,11 +103,12 @@ type RestoreResult struct {
 	BlobsDownloaded int
 	BytesDownloaded int64
 	Duration        time.Duration
+	FilesFailed     int
+	FailedFiles     []string // Paths of files that failed to restore
 	// Verification results (only populated if Verify option is set)
-	FilesVerified int
-	BytesVerified int64
-	FilesFailed   int
-	FailedFiles   []string // Paths of files that failed verification
+	FilesVerified     int
+	BytesVerified     int64
+	VerifyFailedFiles []string // Paths of restored files that failed verification
 }
 
 // Restore restores files from a snapshot to the target directory
@@ -647,20 +648,34 @@ func (v *Vaultik) handleRestoreVerification(
 	opts *RestoreOptions,
 	result *RestoreResult,
 ) error {
-	err := v.verifyRestoredFiles(v.ctx, repos, files, opts.TargetDir, result)
+	// A file that failed to restore was not written and is already
+	// reported as such, so it is not verified.
+	failedToRestore := make(map[string]bool, len(result.FailedFiles))
+	for _, path := range result.FailedFiles {
+		failedToRestore[path] = true
+	}
+
+	restored := make([]*database.File, 0, len(files))
+	for _, file := range files {
+		if !failedToRestore[file.Path.String()] {
+			restored = append(restored, file)
+		}
+	}
+
+	err := v.verifyRestoredFiles(v.ctx, repos, restored, opts.TargetDir, result)
 	if err != nil {
 		return fmt.Errorf("verification failed: %w", err)
 	}
 
-	if result.FilesFailed > 0 {
+	if len(result.VerifyFailedFiles) > 0 {
 		v.UI.Errorf("Verification failed: %s files did not match expected checksums.",
-			v.UI.Count(result.FilesFailed))
+			v.UI.Count(len(result.VerifyFailedFiles)))
 
-		for _, path := range result.FailedFiles {
+		for _, path := range result.VerifyFailedFiles {
 			v.UI.Detailf("%s", v.UI.Path(path))
 		}
 
-		return fmt.Errorf("%d %w", result.FilesFailed, errFilesFailedVerify)
+		return fmt.Errorf("%d %w", len(result.VerifyFailedFiles), errFilesFailedVerify)
 	}
 
 	v.UI.Completef("Verified %s files (%s).",
@@ -1420,8 +1435,8 @@ func (v *Vaultik) verifyRestoredFiles(
 		if err != nil {
 			log.Error("File verification failed", "path", file.Path, "error", err)
 
-			result.FilesFailed++
-			result.FailedFiles = append(result.FailedFiles, file.Path.String())
+			result.VerifyFailedFiles = append(
+				result.VerifyFailedFiles, file.Path.String())
 		}
 
 		bytesProcessed += file.Size
@@ -1437,7 +1452,7 @@ func (v *Vaultik) verifyRestoredFiles(
 	log.Info("Verification complete",
 		"files_verified", result.FilesVerified,
 		"bytes_verified", ubytes(result.BytesVerified),
-		"files_failed", result.FilesFailed,
+		"files_failed", len(result.VerifyFailedFiles),
 	)
 
 	return nil

internal/vaultik/restore_interrupt_test.go

@@ -142,14 +142,14 @@ func TestRestoreCleansTempDirOnInterrupt(t *testing.T) {
 }
 
 // scratchEntries returns the vaultik blob-cache and snapshot-database
-// scratch entries (restore's and deep verify's) currently present in dir.
+// scratch entries currently present in dir.
 func scratchEntries(t *testing.T, dir string) []string {
 	t.Helper()
 
 	var matches []string
 
 	for _, pattern := range []string{
-		"vaultik-blobcache-*", "vaultik-restore-*", "vaultik-verify-*",
+		"vaultik-blobcache-*", "vaultik-restore-*",
 	} {
 		found, err := filepath.Glob(filepath.Join(dir, pattern))
 		require.NoError(t, err)
@@ -206,119 +206,3 @@ func TestRestoreSkipErrorsCancelDuringBlobDownload(t *testing.T) {
 	assert.NotContains(t, out.String(), srcPath,
 		"the cancel was reported as a failed file")
 }
-
-// stallingBlobStorer wraps a Storer so that every blob download hands
-// over the first half of the blob and then stalls, ignoring the context,
-// as a file:// blob on a hung USB stick or network share does. Only
-// closing the returned reader ends the stall.
-type stallingBlobStorer struct {
-	storage.Storer
-
-	once    sync.Once
-	stalled chan struct{}
-}
-
-func newStallingBlobStorer(inner storage.Storer) *stallingBlobStorer {
-	return &stallingBlobStorer{Storer: inner, stalled: make(chan struct{})}
-}
-
-func (s *stallingBlobStorer) Get(
-	ctx context.Context, key string,
-) (io.ReadCloser, error) {
-	rc, err := s.Storer.Get(ctx, key)
-	if err != nil || !strings.HasPrefix(key, "blobs/") {
-		return rc, err
-	}
-
-	blob, err := io.ReadAll(rc)
-	_ = rc.Close()
-
-	if err != nil {
-		return nil, err
-	}
-
-	// The writer is never closed, so once the first half has been read
-	// the next Read blocks until the reader is closed.
-	pr, pw := io.Pipe()
-
-	go func() {
-		_, _ = pw.Write(blob[:len(blob)/2])
-
-		s.once.Do(func() { close(s.stalled) })
-	}()
-
-	return pr, nil
-}
-
-// TestInterruptDuringStalledBlobReadCleansTempDir stops a restore and a
-// deep verify while a blob read is stalled on a source that ignores the
-// context. Stopping must end that read, so the operation unwinds and
-// removes its decrypted scratch files well within the shutdown timeout
-// (issue #325).
-//
-// Not parallel: it points TMPDIR at a private directory (via t.Setenv)
-// so it can assert on exactly the scratch files the operation created.
-func TestInterruptDuringStalledBlobReadCleansTempDir(t *testing.T) {
-	log.Initialize(log.Config{})
-
-	operations := map[string]func(v *Vaultik, snapshotID, targetDir string) error{
-		"restore": func(v *Vaultik, snapshotID, targetDir string) error {
-			return v.Restore(&RestoreOptions{
-				SnapshotID: snapshotID,
-				TargetDir:  targetDir,
-			})
-		},
-		"deep verify": func(v *Vaultik, snapshotID, _ string) error {
-			return v.RunDeepVerify(snapshotID, &VerifyOptions{Deep: true})
-		},
-	}
-
-	for name, op := range operations {
-		t.Run(name, func(t *testing.T) {
-			fs := afero.NewOsFs()
-			root := t.TempDir()
-
-			// Random content, so the blob stays large enough to stall
-			// part-way through its compressed, encrypted body.
-			cfg, storer, snapshotID, _ := backupOneFile(context.Background(),
-				t, fs, root, "a.bin", randomBytes(t, 256*1024), 0o644)
-
-			scratch := filepath.Join(root, "scratch")
-			require.NoError(t, fs.MkdirAll(scratch, 0o755))
-			t.Setenv("TMPDIR", scratch)
-
-			stalling := newStallingBlobStorer(storer)
-
-			ctx, cancel := context.WithCancel(context.Background())
-			defer cancel()
-
-			v := newRestoreVaultik(ctx, cfg, stalling, fs)
-			v.cancel = cancel
-
-			var opErr error
-
-			stop := v.StartOperation(func() {
-				opErr = op(v, snapshotID, filepath.Join(root, "restored"))
-			})
-
-			select {
-			case <-stalling.stalled:
-			case <-time.After(30 * time.Second):
-				t.Fatal("the operation never reached a blob read")
-			}
-
-			require.NotEmpty(t, scratchEntries(t, scratch),
-				"expected decrypted scratch files to exist mid-read")
-
-			stopCtx, stopCancel := context.WithTimeout(
-				context.Background(), 10*time.Second)
-			defer stopCancel()
-
-			require.True(t, stop(stopCtx),
-				"stop timed out; the stalled blob read was not interrupted")
-			require.ErrorIs(t, opErr, context.Canceled)
-			require.Empty(t, scratchEntries(t, scratch),
-				"decrypted scratch files remained after the interrupt")
-		})
-	}
-}

internal/vaultik/restore_skip_errors_test.go

@@ -84,6 +84,41 @@ func TestRestoreSkipErrorsSkipsFilesOfMissingBlob(t *testing.T) {
 	}
 }
 
+// TestRestoreSkipErrorsVerifyChecksOnlyRestoredFiles restores with
+// SkipErrors and Verify after one blob of a two-blob snapshot was
+// deleted. Verification must check only the files that were written, so
+// a file of the deleted blob is reported as failed to restore and not
+// also as failing verification, and Restore must still return an error.
+func TestRestoreSkipErrorsVerifyChecksOnlyRestoredFiles(t *testing.T) {
+	log.Initialize(log.Config{})
+	t.Parallel()
+
+	ctx := context.Background()
+	backup := backupThenDeleteOneBlob(ctx, t)
+
+	var out bytes.Buffer
+
+	v := newReaderVaultik(ctx, backup.cfg, backup.storer, nil, backup.fs)
+	v.UI = ui.NewWithColor(&out, false)
+
+	err := v.Restore(&vaultik.RestoreOptions{
+		SnapshotID: backup.snapshotID,
+		TargetDir:  backup.restoreDir,
+		Verify:     true,
+		SkipErrors: true,
+	})
+
+	require.Error(t, err, "restore must fail when files were skipped")
+	assert.Contains(t, err.Error(),
+		fmt.Sprintf("%d file(s) failed to restore", len(backup.lost)))
+
+	written := len(backup.files) - len(backup.lost)
+
+	assert.Contains(t, out.String(), fmt.Sprintf("Verifying %d files", written))
+	assert.Contains(t, out.String(), fmt.Sprintf("Verified %d files", written))
+	assert.NotContains(t, out.String(), "Verification failed")
+}
+
 // TestRestoreMissingBlobAbortsWithoutSkipErrors checks that a deleted blob
 // still ends the restore with an error when SkipErrors is not set.
 func TestRestoreMissingBlobAbortsWithoutSkipErrors(t *testing.T) {