Record the stored size of a blob a backup finds already stored (closes #300)

When a finished blob already existed at the destination, the upload was
skipped but the blob row, and so the manifest, kept the size of the
local copy. That copy can differ from the stored object when
compression_level or the recipients changed since it was written, and
then shallow and deep verify failed on a good snapshot. Marking a blob
uploaded now records the size of the object in storage: for an existing
blob, the size Stat reports.

Judgement call: the test adds a recipient rather than changing the
compression level, because an extra age recipient always makes the
local copy larger, while two zstd levels need not compress the test
data differently.

Model: opus-5-5

README.md

@@ -372,9 +372,7 @@ on the destination in one go, use `vaultik remote nuke --force`.
   store — its remote key (or an unambiguous leading part of it) as shown
   by `snapshot list`. See
   [restoring on another machine](#restoring-on-another-machine).
-* Optional path arguments to restore specific files/directories (default: all).
-  A path that matches nothing in the snapshot is named in a warning, and the
-  command exits non-zero after restoring the paths that match
+* 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
@@ -435,7 +433,10 @@ 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.
+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.
 
 **Rclone** (`rclone://remote/path`): Uses rclone's 70+ supported cloud
 providers. Requires rclone to be configured separately (`rclone config`).

docs/DATAMODEL.md

@@ -90,7 +90,7 @@ Stores information about packed, compressed, and encrypted blob files.
 - `created_ts` (INTEGER NOT NULL) - Creation timestamp
 - `finished_ts` (INTEGER) - Finalization timestamp (NULL if in progress)
 - `uncompressed_size` (INTEGER NOT NULL DEFAULT 0) - Total size of chunks before compression
-- `compressed_size` (INTEGER NOT NULL DEFAULT 0) - Size after compression and encryption
+- `compressed_size` (INTEGER NOT NULL DEFAULT 0) - Size after compression and encryption. Once uploaded, the size of the object in storage: when the blob was already stored, under another compression level or other recipients, this can differ from the size of the local copy
 - `uploaded_ts` (INTEGER) - Upload completion timestamp (NULL if not uploaded)
 
 **Purpose:** Tracks blob lifecycle from creation through upload. The UUID primary key allows immediate association of chunks with blobs.
@@ -183,7 +183,7 @@ Tracks blob upload metrics.
    - `UPDATE blobs SET blob_hash = ?, finished_ts = ?` - Finalize blob after packing
 
 4. **Upload**
-   - `UPDATE blobs SET uploaded_ts = ?` - Mark blob as uploaded
+   - `UPDATE blobs SET uploaded_ts = ?, compressed_size = ?` - Mark blob as uploaded, with the size of the object in storage (the upload is skipped when the blob is already stored)
    - `INSERT INTO uploads` - Record upload metrics with snapshot_id
    - `INSERT INTO snapshot_blobs` - Associate blob with snapshot
 

internal/blob/packer.go

@@ -245,6 +245,17 @@ 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/cli/config.go

@@ -251,6 +251,12 @@ func NewConfigCommand() *cobra.Command {
 		Use:   "config",
 		Short: "Manage the configuration file",
 		Long:  "Commands for creating, editing, and querying the vaultik config file.",
+		// cobra checks Args only on a command that has a Run: without
+		// one, a mistyped subcommand printed help and exited 0.
+		Args: cobra.NoArgs,
+		Run: func(cmd *cobra.Command, _ []string) {
+			_ = cmd.Help()
+		},
 	}
 
 	cmd.AddCommand(newConfigInitCommand())

internal/cli/database.go

@@ -15,6 +15,12 @@ func NewDatabaseCommand() *cobra.Command {
 		Use:   "database",
 		Short: "Manage the local state database",
 		Long:  `Commands for managing the local SQLite state database.`,
+		// cobra checks Args only on a command that has a Run: without
+		// one, a mistyped subcommand printed help and exited 0.
+		Args: cobra.NoArgs,
+		Run: func(cmd *cobra.Command, _ []string) {
+			_ = cmd.Help()
+		},
 	}
 
 	cmd.AddCommand(

internal/cli/entry_unknown_subcommand_test.go

@@ -0,0 +1,43 @@
+package cli //nolint:testpackage // shares runEntry and the command-word constants
+
+import (
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+)
+
+// TestEntryGroupRejectsUnknownSubcommand runs each group command with a
+// mistyped subcommand, as a crontab line might carry one. It must fail
+// with exit 1 and name the word, as `vaultik bogus` does at the top
+// level, instead of printing the group's help and exiting 0 having done
+// nothing. The group name alone still prints its help.
+//
+//nolint:paralleltest // replaces os.Args, os.Stdout and os.Stderr
+func TestEntryGroupRejectsUnknownSubcommand(t *testing.T) {
+	for _, testCase := range []struct {
+		group    string
+		mistyped string
+	}{
+		{group: cmdSnapshot, mistyped: "craete"},
+		{group: "config", mistyped: "inti"},
+		{group: cmdRemote, mistyped: "ifno"},
+		{group: "database", mistyped: "delte"},
+		{group: "completion", mistyped: "nosuchshell"},
+	} {
+		t.Run(testCase.group, func(t *testing.T) {
+			code, stdout, stderr := runEntry(t,
+				testCase.group, testCase.mistyped)
+
+			assert.Equal(t, 1, code)
+			assert.Empty(t, stdout)
+			assert.Contains(t, stderr,
+				`unknown command "`+testCase.mistyped+`"`)
+
+			code, stdout, _ = runEntry(t, testCase.group)
+
+			assert.Equal(t, 0, code)
+			assert.Contains(t, stdout,
+				programName+" "+testCase.group+" [command]")
+		})
+	}
+}

internal/cli/remote.go

@@ -18,6 +18,12 @@ func NewRemoteCommand() *cobra.Command {
 		Use:   "remote",
 		Short: "Remote storage management commands",
 		Long:  "Commands for inspecting and managing remote storage",
+		// cobra checks Args only on a command that has a Run: without
+		// one, a mistyped subcommand printed help and exited 0.
+		Args: cobra.NoArgs,
+		Run: func(cmd *cobra.Command, _ []string) {
+			_ = cmd.Help()
+		},
 	}
 
 	// Add subcommands

internal/cli/root.go

@@ -74,6 +74,21 @@ on the source system.`,
 		NewDatabaseCommand(),
 	)
 
+	// cobra adds the completion command only when Execute runs, and with
+	// no Run, so it skipped its own cobra.NoArgs and a mistyped shell name
+	// printed help and exited 0. Adding it here lets it have a Run. Its
+	// scripts go to os.Stdout as it is now: a later SetOut does not
+	// redirect them.
+	cmd.InitDefaultCompletionCmd()
+
+	for _, sub := range cmd.Commands() {
+		if sub.Name() == "completion" {
+			sub.Run = func(completion *cobra.Command, _ []string) {
+				_ = completion.Help()
+			}
+		}
+	}
+
 	return cmd
 }
 

internal/cli/snapshot.go

@@ -41,6 +41,12 @@ func NewSnapshotCommand() *cobra.Command {
 		Use:   "snapshot",
 		Short: "Snapshot management commands",
 		Long:  "Commands for creating, listing, and managing snapshots",
+		// cobra checks Args only on a command that has a Run: without
+		// one, a mistyped subcommand printed help and exited 0.
+		Args: cobra.NoArgs,
+		Run: func(cmd *cobra.Command, _ []string) {
+			_ = cmd.Help()
+		},
 	}
 
 	// Add subcommands

internal/cli/snapshot_restore.go

@@ -30,8 +30,6 @@ This command will restore files from the specified snapshot to the
 target directory.
 If no paths are specified, all files are restored.
 If paths are specified, only matching files/directories are restored.
-A path that matches nothing in the snapshot is named in a warning, and
-the command exits non-zero after restoring the paths that match.
 
 The snapshot may be named by its ID or, when restoring on a host with no
 local index, by the remote key that 'snapshot list' prints for a

internal/config/config.go

@@ -61,6 +61,9 @@ 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")
@@ -461,11 +464,18 @@ 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.
+// 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.
 func (c *Config) validateStorageURL() error {
 	switch {
 	case strings.HasPrefix(c.StorageURL, "file://"):
-		// File storage doesn't need S3 credentials
+		// storage.ParseStorageURL applies the same rule, but config
+		// cannot import storage, which imports config.
+		if !strings.HasPrefix(c.StorageURL, "file:///") {
+			return errFileURLNotAbsolute
+		}
+
 		return nil
 	case strings.HasPrefix(c.StorageURL, "rclone://"):
 		// Rclone storage uses rclone's own config

internal/config/config_test.go

@@ -337,6 +337,35 @@ 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/database/blobs.go

@@ -159,13 +159,16 @@ func (r *BlobRepository) UpdateFinished(
 	return nil
 }
 
-// UpdateUploaded marks a blob as uploaded
+// UpdateUploaded marks a blob as uploaded and records the size of the
+// stored object as its compressed size. That size can differ from the
+// local copy's when an identical blob was already stored with another
+// compression level or other recipients.
 func (r *BlobRepository) UpdateUploaded(
-	ctx context.Context, tx *sql.Tx, id string,
+	ctx context.Context, tx *sql.Tx, id string, storedSize int64,
 ) error {
 	query := `
-		UPDATE blobs 
-		SET uploaded_ts = ?
+		UPDATE blobs
+		SET uploaded_ts = ?, compressed_size = ?
 		WHERE id = ?
 	`
 
@@ -173,9 +176,9 @@ func (r *BlobRepository) UpdateUploaded(
 
 	var err error
 	if tx != nil {
-		_, err = tx.ExecContext(ctx, query, now, id)
+		_, err = tx.ExecContext(ctx, query, now, storedSize, id)
 	} else {
-		_, err = r.db.ExecWithLog(ctx, query, now, id)
+		_, err = r.db.ExecWithLog(ctx, query, now, storedSize, id)
 	}
 
 	if err != nil {

internal/database/blobs_test.go

@@ -122,8 +122,8 @@ func TestBlobRepositoryUpdates(t *testing.T) {
 		t.Errorf("expected compressed size 500, got %d", updated.CompressedSize)
 	}
 
-	// Test UpdateUploaded
-	err = repo.UpdateUploaded(ctx, nil, blob.ID.String())
+	// Test UpdateUploaded, with a stored object larger than the local copy
+	err = repo.UpdateUploaded(ctx, nil, blob.ID.String(), 600)
 	if err != nil {
 		t.Fatalf("failed to update blob as uploaded: %v", err)
 	}
@@ -141,6 +141,10 @@ func TestBlobRepositoryUpdates(t *testing.T) {
 	if uploaded.UploadedTS.Before(now.Add(-1 * time.Second)) {
 		t.Error("uploaded timestamp should be around test time")
 	}
+
+	if uploaded.CompressedSize != 600 {
+		t.Errorf("expected the stored size 600, got %d", uploaded.CompressedSize)
+	}
 }
 
 func TestBlobRepositoryDuplicate(t *testing.T) {

internal/snapshot/exclude_test.go

@@ -531,3 +531,50 @@ func TestExcludePatterns_UnanchoredPatternFile(t *testing.T) {
 	require.Equal(t, 1, result.FilesScanned,
 		"Unanchored pattern for file should match anywhere")
 }
+
+func TestExcludePatterns_DoubleStarDirectoryAtEveryDepth(t *testing.T) {
+	t.Parallel()
+
+	// As in gitignore, a leading **/ also matches directly under the source dir
+	fs := setupAnchoredTestFS(t)
+
+	scanner, repos, cleanup := createTestScanner(t, fs, []string{"**/projectname"})
+	defer cleanup()
+
+	ctx := context.Background()
+	createSnapshotRecord(ctx, t, repos, "test-snapshot")
+
+	result, err := scanner.Scan(ctx, "/backup", "test-snapshot")
+	require.NoError(t, err)
+
+	// **/projectname should exclude BOTH:
+	// - /backup/projectname/file.txt
+	// - /backup/otherproject/projectname/file.txt
+	// Total files: 4, excluded: 2
+	require.Equal(t, 2, result.FilesScanned,
+		"**/ directory pattern should match at the top level and nested")
+}
+
+func TestExcludePatterns_DoubleStarFileAtEveryDepth(t *testing.T) {
+	t.Parallel()
+
+	// As in gitignore, a leading **/ also matches directly under the source dir
+	fs := setupAnchoredTestFS(t)
+
+	scanner, repos, cleanup := createTestScanner(t, fs, []string{"**/*.txt"})
+	defer cleanup()
+
+	ctx := context.Background()
+	createSnapshotRecord(ctx, t, repos, "test-snapshot")
+
+	result, err := scanner.Scan(ctx, "/backup", "test-snapshot")
+	require.NoError(t, err)
+
+	// **/*.txt should exclude ALL .txt files:
+	// - /backup/file.txt
+	// - /backup/projectname/file.txt
+	// - /backup/otherproject/projectname/file.txt
+	// Total files: 4, excluded: 3
+	require.Equal(t, 1, result.FilesScanned,
+		"**/ file pattern should match at the top level and nested")
+}

internal/snapshot/scanner.go

@@ -1295,6 +1295,11 @@ 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 {
@@ -1509,7 +1514,8 @@ func (s *Scanner) finalizeProcessPhase(ctx context.Context, result *ScanResult)
 			// snapshot references has uploaded_ts set, so deduplication and
 			// interrupted-run repair treat these blobs as trustworthy.
 			err = s.repos.WithTx(ctx, func(ctx context.Context, tx *sql.Tx) error {
-				err := s.repos.Blobs.UpdateUploaded(ctx, tx, b.ID)
+				err := s.repos.Blobs.UpdateUploaded(
+					ctx, tx, b.ID, b.Compressed)
 				if err != nil {
 					return fmt.Errorf("marking blob uploaded: %w", err)
 				}
@@ -1545,7 +1551,7 @@ func (s *Scanner) handleBlobReady(
 	blobPath := fmt.Sprintf("blobs/%s/%s/%s",
 		finishedBlob.Hash[:2], finishedBlob.Hash[2:4], finishedBlob.Hash)
 
-	blobExists, err := s.uploadBlobIfNeeded(
+	storedSize, blobExists, err := s.uploadBlobIfNeeded(
 		ctx, blobPath, blobWithReader, startTime, result)
 	if err != nil {
 		s.cleanupBlobTempFile(blobWithReader)
@@ -1553,7 +1559,8 @@ func (s *Scanner) handleBlobReady(
 		return fmt.Errorf("uploading blob %s: %w", finishedBlob.Hash, err)
 	}
 
-	err = s.recordBlobMetadata(ctx, finishedBlob, blobExists, startTime)
+	err = s.recordBlobMetadata(
+		ctx, finishedBlob, storedSize, blobExists, startTime)
 	if err != nil {
 		s.cleanupBlobTempFile(blobWithReader)
 
@@ -1575,20 +1582,22 @@ func (s *Scanner) handleBlobReady(
 }
 
 // uploadBlobIfNeeded uploads the blob to storage if it doesn't already
-// exist, returns whether it existed
+// exist. It returns the size of the object in storage, which for an
+// existing object can differ from the local copy's, and whether it
+// already existed.
 func (s *Scanner) uploadBlobIfNeeded(
 	ctx context.Context,
 	blobPath string,
 	blobWithReader *blob.WithReader,
 	startTime time.Time,
 	result *ScanResult,
-) (bool, error) {
+) (int64, bool, error) {
 	finishedBlob := blobWithReader.FinishedBlob
 
 	// Check if blob already exists (deduplication after restart)
 	destination := s.storage.Info().Location
 
-	_, err := s.storage.Stat(ctx, blobPath)
+	stored, err := s.storage.Stat(ctx, blobPath)
 	if err == nil {
 		log.Info("Blob already exists in storage, skipping upload",
 			"hash", finishedBlob.Hash,
@@ -1597,7 +1606,7 @@ func (s *Scanner) uploadBlobIfNeeded(
 			s.ui.Hex(finishedBlob.Hash), s.ui.Size(finishedBlob.Compressed),
 			s.ui.Path(destination))
 
-		return true, nil
+		return stored.Size, true, nil
 	}
 
 	s.ui.Beginf("Uploading blob %s (%s) to %s.",
@@ -1611,7 +1620,7 @@ func (s *Scanner) uploadBlobIfNeeded(
 	if err != nil {
 		log.Error("Failed to upload blob", "hash", finishedBlob.Hash, "error", err)
 
-		return false, fmt.Errorf("uploading blob to storage: %w", err)
+		return 0, false, fmt.Errorf("uploading blob to storage: %w", err)
 	}
 
 	uploadDuration := time.Since(startTime)
@@ -1642,7 +1651,7 @@ func (s *Scanner) uploadBlobIfNeeded(
 		stats.BytesUploaded.Add(finishedBlob.Compressed)
 	}
 
-	return false, nil
+	return finishedBlob.Compressed, false, nil
 }
 
 // makeUploadProgressCallback creates a progress callback for blob uploads.
@@ -1712,6 +1721,7 @@ func (s *Scanner) makeUploadProgressCallback(
 func (s *Scanner) recordBlobMetadata(
 	ctx context.Context,
 	finishedBlob *blob.FinishedBlob,
+	storedSize int64,
 	blobExists bool,
 	startTime time.Time,
 ) error {
@@ -1723,7 +1733,8 @@ func (s *Scanner) recordBlobMetadata(
 	uploadDuration := time.Since(startTime)
 
 	return s.repos.WithTx(ctx, func(txCtx context.Context, tx *sql.Tx) error {
-		err := s.repos.Blobs.UpdateUploaded(txCtx, tx, finishedBlob.ID)
+		err := s.repos.Blobs.UpdateUploaded(
+			txCtx, tx, finishedBlob.ID, storedSize)
 		if err != nil {
 			return fmt.Errorf("updating blob upload timestamp: %w", err)
 		}
@@ -2013,6 +2024,14 @@ func compileExcludePatterns(patterns []string) []compiledPattern {
 		// Remove trailing slash if present (directory indicator)
 		pattern = strings.TrimSuffix(pattern, "/")
 
+		// A leading "**/" demands a "/" before the name and so misses an
+		// entry directly under the source path. An unanchored pattern
+		// already matches at every depth, so drop the prefix: as in
+		// gitignore, "**/x" then also matches a top-level "x".
+		if !anchored {
+			pattern = strings.TrimPrefix(pattern, "**/")
+		}
+
 		// Compile the glob pattern
 		// For patterns without path separators, we need to match them as components
 		// e.g., ".git" should match ".git" anywhere in the path

internal/snapshot/skip_errors_test.go

@@ -381,3 +381,60 @@ 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

@@ -17,8 +17,10 @@ const (
 
 // Sentinel errors for storage URL parsing.
 var (
-	ErrEmptyStorageURL   = errors.New("storage URL is empty")
-	ErrEmptyFilePath     = errors.New("file URL path is empty")
+	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")
 	ErrMissingBucket     = errors.New("s3 URL missing bucket name")
 	ErrMissingRemote     = errors.New("rclone URL missing remote name")
 	ErrUnsupportedScheme = errors.New(
@@ -51,17 +53,8 @@ func ParseStorageURL(rawURL string) (*URL, error) {
 		return nil, ErrEmptyStorageURL
 	}
 
-	// Handle file:// URLs
 	if after, ok := strings.CutPrefix(rawURL, "file://"); ok {
-		path := after
-		if path == "" {
-			return nil, ErrEmptyFilePath
-		}
-
-		return &URL{
-			Scheme: schemeFile,
-			Prefix: path,
-		}, nil
+		return parseFileURL(after)
 	}
 
 	if strings.HasPrefix(rawURL, "s3://") {
@@ -75,6 +68,27 @@ 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

@@ -14,7 +14,10 @@ import (
 func TestParseStorageURLValid(t *testing.T) {
 	t.Parallel()
 
-	const bucket = "mybucket"
+	const (
+		bucket     = "mybucket"
+		fileScheme = "file"
+	)
 
 	cases := []struct {
 		name string
@@ -24,7 +27,17 @@ func TestParseStorageURLValid(t *testing.T) {
 		{
 			name: "file absolute path",
 			raw:  "file:///var/backups/vaultik",
-			want: &storage.URL{Scheme: "file", Prefix: "/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"},
 		},
 		{
 			name: "s3 bucket and prefix, ssl defaults on",
@@ -90,6 +103,7 @@ 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

@@ -103,6 +103,8 @@ 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) {
@@ -120,5 +122,47 @@ func (v *Vaultik) FetchBlob(
 		return nil, fmt.Errorf("downloading blob %s: %w", shortHash(blobHash), err)
 	}
 
-	return rc, nil
+	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()
 }

internal/vaultik/restore.go

@@ -27,7 +27,6 @@ import (
 // Sentinel errors for restore failures.
 var (
 	errFilesFailedRestore    = errors.New("file(s) failed to restore")
-	errPathsNotInSnapshot    = errors.New("requested path(s) not in the snapshot")
 	errFilesFailedVerify     = errors.New("files failed verification")
 	errDecryptionKeyRequired = errors.New(
 		"decryption key required for restore\n\n" +
@@ -150,7 +149,7 @@ func (v *Vaultik) Restore(opts *RestoreOptions) error {
 	repos := database.NewRepositories(tempDB)
 
 	// Step 2: Get list of files to restore
-	files, unmatched, err := v.getFilesToRestore(v.ctx, repos, opts.Paths)
+	files, err := v.getFilesToRestore(v.ctx, repos, opts.Paths)
 	if err != nil {
 		return fmt.Errorf("getting files to restore: %w", err)
 	}
@@ -159,7 +158,7 @@ func (v *Vaultik) Restore(opts *RestoreOptions) error {
 		log.Warn("No files found to restore")
 		v.UI.Warningf("No files found to restore.")
 
-		return v.reportUnmatchedPaths(unmatched)
+		return nil
 	}
 
 	log.Info("Found files to restore", "count", len(files))
@@ -199,16 +198,14 @@ func (v *Vaultik) Restore(opts *RestoreOptions) error {
 		v.UI.Duration(result.Duration),
 	)
 
-	return v.finishRestore(repos, files, unmatched, opts, result)
+	return v.finishRestore(repos, files, opts, result)
 }
 
 // finishRestore emits the post-restore warnings, runs optional
-// verification, and converts any failed-file count or requested path
-// that matched nothing into an error.
+// verification, and converts any failed-file count into an error.
 func (v *Vaultik) finishRestore(
 	repos *database.Repositories,
 	files []*database.File,
-	unmatched []string,
 	opts *RestoreOptions,
 	result *RestoreResult,
 ) error {
@@ -226,8 +223,6 @@ func (v *Vaultik) finishRestore(
 		}
 	}
 
-	unmatchedErr := v.reportUnmatchedPaths(unmatched)
-
 	// Run verification if requested
 	if opts.Verify {
 		err := v.handleRestoreVerification(repos, files, opts, result)
@@ -240,23 +235,7 @@ func (v *Vaultik) finishRestore(
 		return fmt.Errorf("%d %w", result.FilesFailed, errFilesFailedRestore)
 	}
 
-	return unmatchedErr
-}
-
-// reportUnmatchedPaths warns, by name, about each requested path that
-// matched nothing in the snapshot, and returns an error counting them,
-// or nil when there are none.
-func (v *Vaultik) reportUnmatchedPaths(unmatched []string) error {
-	if len(unmatched) == 0 {
-		return nil
-	}
-
-	for _, path := range unmatched {
-		log.Warn("Requested path matches nothing in the snapshot", "path", path)
-		v.UI.Warningf("%s matches nothing in the snapshot.", v.UI.Path(path))
-	}
-
-	return fmt.Errorf("%d %w", len(unmatched), errPathsNotInSnapshot)
+	return nil
 }
 
 // restoreIdentities parses the configured age secret key once into every
@@ -833,34 +812,27 @@ func (v *Vaultik) materializeSnapshotDB(
 	return db, tempDir, nil
 }
 
-// getFilesToRestore returns the list of files to restore based on path
-// filters, and the filters, as given, that matched no file.
+// getFilesToRestore returns the list of files to restore based on path filters
 func (v *Vaultik) getFilesToRestore(
 	ctx context.Context, repos *database.Repositories, pathFilters []string,
-) ([]*database.File, []string, error) {
+) ([]*database.File, error) {
 	// If no filters, get all files
 	if len(pathFilters) == 0 {
-		files, err := repos.Files.ListAll(ctx)
-
-		return files, nil, err
+		return repos.Files.ListAll(ctx)
 	}
 
 	// Get files matching the path filters
-	var (
-		result    []*database.File
-		unmatched []string
-	)
+	var result []*database.File
 
 	seen := make(map[string]bool)
 
 	for _, filter := range pathFilters {
-		files, err := repos.Files.ListUnderPath(ctx, filepath.Clean(filter))
-		if err != nil {
-			return nil, nil, fmt.Errorf("listing files under %s: %w", filter, err)
-		}
+		// Normalize the filter path
+		filter = filepath.Clean(filter)
 
-		if len(files) == 0 {
-			unmatched = append(unmatched, filter)
+		files, err := repos.Files.ListUnderPath(ctx, filter)
+		if err != nil {
+			return nil, fmt.Errorf("listing files under %s: %w", filter, err)
 		}
 
 		for _, file := range files {
@@ -871,7 +843,7 @@ func (v *Vaultik) getFilesToRestore(
 		}
 	}
 
-	return result, unmatched, nil
+	return result, nil
 }
 
 // buildChunkToBlobMap creates a mapping from chunk hash to blob information

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 currently present in dir.
+// scratch entries (restore's and deep verify's) 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-blobcache-*", "vaultik-restore-*", "vaultik-verify-*",
 	} {
 		found, err := filepath.Glob(filepath.Join(dir, pattern))
 		require.NoError(t, err)
@@ -206,3 +206,119 @@ 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_unmatched_path_test.go

@@ -1,142 +0,0 @@
-package vaultik_test
-
-import (
-	"bytes"
-	"context"
-	"os"
-	"path/filepath"
-	"strings"
-	"testing"
-
-	"github.com/spf13/afero"
-	"github.com/stretchr/testify/assert"
-	"github.com/stretchr/testify/require"
-	"sneak.berlin/go/vaultik/internal/config"
-	"sneak.berlin/go/vaultik/internal/database"
-	"sneak.berlin/go/vaultik/internal/log"
-	"sneak.berlin/go/vaultik/internal/storage"
-	"sneak.berlin/go/vaultik/internal/ui"
-	"sneak.berlin/go/vaultik/internal/vaultik"
-)
-
-// These tests cover https://git.eeqj.de/sneak/vaultik/issues/309: a path
-// given to restore that matches nothing in the snapshot is named in a
-// warning and makes the restore fail, after the paths that do match are
-// restored.
-
-func TestRestoreNamesUnmatchedPathAndRestoresTheMatchingOne(t *testing.T) {
-	log.Initialize(log.Config{})
-	t.Parallel()
-
-	fs := afero.NewOsFs()
-	tempDir := t.TempDir()
-	dataDir := filepath.Join(tempDir, "src")
-	storeDir := filepath.Join(tempDir, "remote")
-	restoreDir := filepath.Join(tempDir, "restored")
-	dbPath := filepath.Join(tempDir, "index.sqlite")
-
-	ctx := context.Background()
-	cfg := faultTestConfig()
-	files := writeFaultSourceTree(t, fs, dataDir)
-
-	store, err := storage.NewFileStorer(storeDir)
-	require.NoError(t, err)
-
-	db, err := database.New(ctx, dbPath)
-	require.NoError(t, err)
-
-	id := fullFaultBackup(ctx, t, fs, store, cfg,
-		database.NewRepositories(db), dataDir, dbPath, "unmatched")
-	require.NoError(t, db.Close())
-
-	matched := filepath.Join(dataDir, "small.txt")
-	unmatched := filepath.Join(dataDir, "typo.txt")
-
-	var out bytes.Buffer
-
-	v := newReaderVaultik(ctx, cfg, store, nil, fs)
-	v.UI = ui.NewWithColor(&out, false)
-
-	err = v.Restore(&vaultik.RestoreOptions{
-		SnapshotID: id,
-		TargetDir:  restoreDir,
-		Paths:      []string{matched, unmatched},
-	})
-
-	require.Error(t, err, "a path that matches nothing must fail the restore")
-	assert.Contains(t, out.String(), unmatched,
-		"the path that matches nothing must be named")
-	assert.NotContains(t, out.String(), matched,
-		"the path that matches must not be reported")
-
-	got, err := afero.ReadFile(fs, filepath.Join(restoreDir, matched))
-	require.NoError(t, err, "the path that matches must still be restored")
-	assert.Equal(t, files[matched], got)
-}
-
-// When no requested path matches, nothing is restored and each path is
-// named. One path is relative. The other goes through the symlink that
-// is the snapshot's configured path, while the entries are stored under
-// the directory the symlink points to.
-func TestRestoreNamesEveryPathWhenNothingMatches(t *testing.T) {
-	log.Initialize(log.Config{})
-	t.Parallel()
-
-	const snapshotName = "linked"
-
-	fs := afero.NewOsFs()
-	tempDir := t.TempDir()
-	dataDir := filepath.Join(tempDir, "src")
-	linkDir := filepath.Join(tempDir, "srclink")
-	storeDir := filepath.Join(tempDir, "remote")
-	restoreDir := filepath.Join(tempDir, "restored")
-	dbPath := filepath.Join(tempDir, "index.sqlite")
-
-	ctx := context.Background()
-	writeFaultSourceTree(t, fs, dataDir)
-	require.NoError(t, os.Symlink(dataDir, linkDir))
-
-	cfg := faultTestConfig()
-	cfg.IndexPath = dbPath
-	cfg.ChunkSize = config.Size(faultChunkSize)
-	cfg.Snapshots = map[string]config.SnapshotConfig{
-		snapshotName: {Paths: []string{linkDir}},
-	}
-
-	store, err := storage.NewFileStorer(storeDir)
-	require.NoError(t, err)
-
-	db, err := database.New(ctx, dbPath)
-	require.NoError(t, err)
-
-	repos := database.NewRepositories(db)
-	v := newBackupVaultik(ctx, cfg, store, repos, db, fs)
-
-	require.NoError(t, backUp(v, snapshotName))
-
-	id := localSnapshotID(ctx, t, repos, snapshotName)
-	require.NoError(t, db.Close())
-
-	throughLink := filepath.Join(linkDir, "sub")
-	relative := strings.TrimPrefix(filepath.Join(dataDir, "small.txt"), "/")
-
-	var out bytes.Buffer
-
-	reader := newReaderVaultik(ctx, cfg, store, nil, fs)
-	reader.UI = ui.NewWithColor(&out, false)
-
-	err = reader.Restore(&vaultik.RestoreOptions{
-		SnapshotID: id,
-		TargetDir:  restoreDir,
-		Paths:      []string{throughLink, relative},
-	})
-
-	require.Error(t, err, "a restore that matches nothing must fail")
-	assert.Contains(t, out.String(), throughLink,
-		"the path through the symlink must be named")
-	assert.Contains(t, out.String(), relative,
-		"the relative path must be named")
-
-	_, err = fs.Stat(restoreDir)
-	assert.True(t, os.IsNotExist(err), "nothing must be restored")
-}

internal/vaultik/reused_blob_verify_test.go

@@ -0,0 +1,83 @@
+package vaultik_test
+
+import (
+	"context"
+	"io"
+	"path/filepath"
+	"testing"
+
+	"filippo.io/age"
+	"github.com/spf13/afero"
+	"github.com/stretchr/testify/require"
+	"sneak.berlin/go/vaultik/internal/log"
+	"sneak.berlin/go/vaultik/internal/ui"
+	"sneak.berlin/go/vaultik/internal/vaultik"
+)
+
+// TestVerifyPassesWhenBackupReusesStoredBlob backs up a file, then backs it
+// up again from an empty local index, as after `database delete`, with an
+// extra age recipient. The second backup builds the same blob, finds it
+// already stored and skips the upload, but its own copy is larger, because
+// age writes a header entry for each recipient. The second snapshot must
+// record the size of the stored object, so shallow and deep verify pass.
+func TestVerifyPassesWhenBackupReusesStoredBlob(t *testing.T) {
+	log.Initialize(log.Config{})
+	t.Parallel()
+
+	fs := afero.NewOsFs()
+	tempDir := t.TempDir()
+
+	dataDir := filepath.Join(tempDir, "source")
+	storeDir := filepath.Join(tempDir, "remote")
+	secondDBPath := filepath.Join(tempDir, "second.sqlite")
+
+	chunkSize := int64(64 * 1024)
+	maxBlobSize := int64(512 * 1024)
+
+	require.NoError(t, fs.MkdirAll(dataDir, 0o755))
+	require.NoError(t, afero.WriteFile(fs,
+		filepath.Join(dataDir, "data.bin"),
+		bytesPattern("reuse-", int(chunkSize*3)), 0o644))
+
+	ctx := context.Background()
+
+	runFileStorageBackup(ctx, t, fs, dataDir, storeDir,
+		filepath.Join(tempDir, "first.sqlite"), chunkSize, maxBlobSize)
+
+	env := setupDedupBackupEnv(
+		ctx, t, fs, storeDir, secondDBPath, chunkSize, maxBlobSize)
+
+	defer func() { _ = env.db.Close() }()
+
+	extra, err := age.GenerateX25519Identity()
+	require.NoError(t, err)
+
+	env.cfg.AgeRecipients = append(env.cfg.AgeRecipients,
+		extra.Recipient().String())
+
+	snapshotID, result := runDedupSnapshot(ctx, t, env.sm, env.makeScanner(),
+		env.cfg.Hostname, "second", dataDir, secondDBPath)
+	require.Positive(t, result.BlobsCreated)
+	require.Zero(t, result.BlobsUploaded,
+		"the second backup should find every blob already stored")
+
+	require.NoError(t, env.db.Close())
+
+	verifier := &vaultik.Vaultik{
+		Config:  env.cfg,
+		Storage: env.storer,
+		Fs:      fs,
+		Stdout:  io.Discard,
+		Stderr:  io.Discard,
+		UI:      ui.NewWithColor(io.Discard, false),
+	}
+	verifier.SetContext(ctx)
+
+	require.NoError(t,
+		verifier.VerifySnapshotWithOptions(snapshotID, &vaultik.VerifyOptions{}),
+		"shallow verify should pass")
+	require.NoError(t,
+		verifier.VerifySnapshotWithOptions(snapshotID,
+			&vaultik.VerifyOptions{Deep: true}),
+		"deep verify should pass")
+}