Fail restore for a requested path that matches nothing (closes #309)

snapshot restore said nothing about a requested path that matched no
entry in the snapshot (a typo, a relative path, or a path through a
configured snapshot path that is a symlink, whose entries are stored
under the resolved directory) and exited 0, also when nothing matched
at all. Each such path is now named in a warning, and restore returns
an error after restoring the paths that do match.

Making a path through a symlink match is not part of this change.
Judgement call: when files also fail to restore, that error is the one
returned; the unmatched paths are still named.

Model: opus-5-5

README.md

@@ -372,7 +372,9 @@ 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)
+* 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
 * Preserves file permissions, timestamps, ownership (ownership requires root),
   symlinks, and empty directories
 * `--verify`: After restoring, verify every file's chunk hashes match
@@ -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
+a local or mounted filesystem. Useful for testing or backing up to a NAS.
-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`).

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/cli/snapshot_restore.go

@@ -30,6 +30,8 @@ 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

@@ -61,9 +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
+// credential fields.
-// 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://"):
-		// storage.ParseStorageURL applies the same rule, but config
+		// File storage doesn't need S3 credentials
-		// 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

@@ -337,35 +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")
+	ErrEmptyStorageURL   = errors.New("storage URL is empty")
-	ErrEmptyFilePath    = errors.New("file URL path 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(
@@ -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 (
+	const bucket = "mybucket"
-		bucket     = "mybucket"
-		fileScheme = "file"
-	)
 
 	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"},
+			want: &storage.URL{Scheme: "file", 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",
@@ -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/restore.go

@@ -27,6 +27,7 @@ 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" +
@@ -149,7 +150,7 @@ func (v *Vaultik) Restore(opts *RestoreOptions) error {
 	repos := database.NewRepositories(tempDB)
 
 	// Step 2: Get list of files to restore
-	files, err := v.getFilesToRestore(v.ctx, repos, opts.Paths)
+	files, unmatched, err := v.getFilesToRestore(v.ctx, repos, opts.Paths)
 	if err != nil {
 		return fmt.Errorf("getting files to restore: %w", err)
 	}
@@ -158,7 +159,7 @@ func (v *Vaultik) Restore(opts *RestoreOptions) error {
 		log.Warn("No files found to restore")
 		v.UI.Warningf("No files found to restore.")
 
-		return nil
+		return v.reportUnmatchedPaths(unmatched)
 	}
 
 	log.Info("Found files to restore", "count", len(files))
@@ -198,14 +199,16 @@ func (v *Vaultik) Restore(opts *RestoreOptions) error {
 		v.UI.Duration(result.Duration),
 	)
 
-	return v.finishRestore(repos, files, opts, result)
+	return v.finishRestore(repos, files, unmatched, opts, result)
 }
 
 // finishRestore emits the post-restore warnings, runs optional
-// verification, and converts any failed-file count into an error.
+// verification, and converts any failed-file count or requested path
+// that matched nothing into an error.
 func (v *Vaultik) finishRestore(
 	repos *database.Repositories,
 	files []*database.File,
+	unmatched []string,
 	opts *RestoreOptions,
 	result *RestoreResult,
 ) error {
@@ -223,6 +226,8 @@ func (v *Vaultik) finishRestore(
 		}
 	}
 
+	unmatchedErr := v.reportUnmatchedPaths(unmatched)
+
 	// Run verification if requested
 	if opts.Verify {
 		err := v.handleRestoreVerification(repos, files, opts, result)
@@ -235,7 +240,23 @@ func (v *Vaultik) finishRestore(
 		return fmt.Errorf("%d %w", result.FilesFailed, errFilesFailedRestore)
 	}
 
-	return nil
+	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)
 }
 
 // restoreIdentities parses the configured age secret key once into every
@@ -812,27 +833,34 @@ func (v *Vaultik) materializeSnapshotDB(
 	return db, tempDir, nil
 }
 
-// getFilesToRestore returns the list of files to restore based on path filters
+// getFilesToRestore returns the list of files to restore based on path
+// filters, and the filters, as given, that matched no file.
 func (v *Vaultik) getFilesToRestore(
 	ctx context.Context, repos *database.Repositories, pathFilters []string,
-) ([]*database.File, error) {
+) ([]*database.File, []string, error) {
 	// If no filters, get all files
 	if len(pathFilters) == 0 {
-		return repos.Files.ListAll(ctx)
+		files, err := repos.Files.ListAll(ctx)
+
+		return files, nil, err
 	}
 
 	// Get files matching the path filters
-	var result []*database.File
+	var (
+		result    []*database.File
+		unmatched []string
+	)
 
 	seen := make(map[string]bool)
 
 	for _, filter := range pathFilters {
-		// Normalize the filter path
+		files, err := repos.Files.ListUnderPath(ctx, filepath.Clean(filter))
-		filter = filepath.Clean(filter)
-
-		files, err := repos.Files.ListUnderPath(ctx, filter)
 		if err != nil {
-			return nil, fmt.Errorf("listing files under %s: %w", filter, err)
+			return nil, nil, fmt.Errorf("listing files under %s: %w", filter, err)
+		}
+
+		if len(files) == 0 {
+			unmatched = append(unmatched, filter)
 		}
 
 		for _, file := range files {
@@ -843,7 +871,7 @@ func (v *Vaultik) getFilesToRestore(
 		}
 	}
 
-	return result, nil
+	return result, unmatched, nil
 }
 
 // buildChunkToBlobMap creates a mapping from chunk hash to blob information

internal/vaultik/restore_unmatched_path_test.go

@@ -0,0 +1,142 @@
+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")
+}