List a file:// destination through a symlinked directory (closes #296)

List and ListStream walked the destination with afero.Walk, which uses
Lstat and so saw a symlinked metadata/ or blobs/ as one file, while Put,
Get and Stat follow the link. The store then listed as empty, and prune
dropped the local snapshot records and deleted every blob. The listings,
and DeletePartialUploads (used by remote nuke), now walk a view without
Lstat, so afero falls back to Stat and enters the link. A prefix lists
as empty only when truly missing; a missing symlink target on it or
above it, such as an unmounted volume, fails the listing.

Judgement call: a symlink loop is not detected; it is followed until the
system refuses the path, and the listing fails.

Model: opus-5-5

README.md

@@ -373,9 +373,7 @@ 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 restored file's chunk hashes

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/storage/file.go

@@ -120,9 +120,10 @@ func (f *FileStorer) Delete(_ context.Context, key string) error {
 	return nil
 }
 
-// List returns all keys with the given prefix. It fails when the
-// destination directory is missing; a missing prefix under it is an
-// empty listing.
+// List returns all keys with the given prefix, reading through symlinked
+// directories. It fails when the destination directory is missing, or
+// when the prefix or a directory above it is a symlink whose target is
+// missing; a prefix that is truly missing is an empty listing.
 func (f *FileStorer) List(ctx context.Context, prefix string) ([]string, error) {
 	var keys []string
 
@@ -133,8 +134,7 @@ func (f *FileStorer) List(ctx context.Context, prefix string) ([]string, error)
 
 	basePath := f.fullPath(prefix)
 
-	// Check if the prefix exists
-	exists, err := afero.Exists(f.fs, basePath)
+	exists, err := f.prefixExists(prefix)
 	if err != nil {
 		return nil, fmt.Errorf("checking path: %w", err)
 	}
@@ -143,7 +143,7 @@ func (f *FileStorer) List(ctx context.Context, prefix string) ([]string, error)
 		return keys, nil // Empty list for non-existent prefix
 	}
 
-	err = afero.Walk(f.fs, basePath, func(path string, info os.FileInfo, err error) error {
+	err = f.walk(basePath, func(path string, info os.FileInfo, err error) error {
 		if err != nil {
 			return err
 		}
@@ -176,7 +176,9 @@ func (f *FileStorer) List(ctx context.Context, prefix string) ([]string, error)
 }
 
 // ListStream returns a channel of ObjectInfo for large result sets. Like
-// List, it sends an error when the destination directory is missing.
+// List, it reads through symlinked directories and sends an error when
+// the destination directory is missing, or when the prefix or a directory
+// above it is a symlink whose target is missing.
 func (f *FileStorer) ListStream(ctx context.Context, prefix string) <-chan ObjectInfo {
 	ch := make(chan ObjectInfo)
 
@@ -192,8 +194,7 @@ func (f *FileStorer) ListStream(ctx context.Context, prefix string) <-chan Objec
 
 		basePath := f.fullPath(prefix)
 
-		// Check if the prefix exists
-		exists, err := afero.Exists(f.fs, basePath)
+		exists, err := f.prefixExists(prefix)
 		if err != nil {
 			ch <- ObjectInfo{Err: fmt.Errorf("checking path: %w", err)}
 
@@ -204,7 +205,7 @@ func (f *FileStorer) ListStream(ctx context.Context, prefix string) <-chan Objec
 			return // Empty channel for non-existent prefix
 		}
 
-		_ = afero.Walk(f.fs, basePath, func(path string, info os.FileInfo, err error) error {
+		_ = f.walk(basePath, func(path string, info os.FileInfo, err error) error {
 			// Check context cancellation
 			select {
 			case <-ctx.Done():
@@ -243,11 +244,12 @@ func (f *FileStorer) ListStream(ctx context.Context, prefix string) <-chan Objec
 }
 
 // DeletePartialUploads removes every file under prefix whose name ends in
-// tempSuffix. A missing prefix has none to remove.
+// tempSuffix. Like List, it reads through symlinked directories and fails
+// on one whose target is missing. A missing prefix has none to remove.
 func (f *FileStorer) DeletePartialUploads(ctx context.Context, prefix string) error {
 	basePath := f.fullPath(prefix)
 
-	exists, err := afero.Exists(f.fs, basePath)
+	exists, err := f.prefixExists(prefix)
 	if err != nil {
 		return fmt.Errorf("checking path: %w", err)
 	}
@@ -256,7 +258,7 @@ func (f *FileStorer) DeletePartialUploads(ctx context.Context, prefix string) er
 		return nil
 	}
 
-	err = afero.Walk(f.fs, basePath, func(path string, info os.FileInfo, err error) error {
+	err = f.walk(basePath, func(path string, info os.FileInfo, err error) error {
 		if err != nil {
 			return err
 		}
@@ -352,6 +354,54 @@ func (f *FileStorer) writeAtomic(
 	return nil
 }
 
+// walk is afero.Walk, except that it reads through a symlinked directory
+// the way Get and Stat do, where afero.Walk reports the link as one file.
+// afero.Walk uses Lstat, which does not follow a link, whenever the
+// filesystem has one; the struct below carries only the afero.Fs methods,
+// so the walk uses Stat instead. A link back up the tree is followed until
+// the operating system refuses the path for too many levels of links, and
+// the walk then fails.
+func (f *FileStorer) walk(root string, fn filepath.WalkFunc) error {
+	return afero.Walk(struct{ afero.Fs }{f.fs}, root, fn)
+}
+
+// prefixExists reports whether prefix exists under the destination
+// directory. It checks each directory on the way down to prefix in turn,
+// and the first one Stat cannot find decides: if it is not there at all,
+// prefix is missing; if it is a symlink whose target is missing, such as
+// a link to a volume that is not mounted, prefixExists fails, since
+// listing it as empty would let prune delete every blob.
+func (f *FileStorer) prefixExists(prefix string) (bool, error) {
+	lstater, canLstat := f.fs.(afero.Lstater)
+	path := f.basePath
+
+	for name := range strings.SplitSeq(prefix, "/") {
+		path = filepath.Join(path, name)
+
+		_, err := f.fs.Stat(path)
+		if err == nil {
+			continue
+		}
+
+		if !os.IsNotExist(err) {
+			return false, err
+		}
+
+		// Lstat does not follow a symlink at path, so it finds the link
+		// that Stat could not follow.
+		if canLstat {
+			_, _, lstatErr := lstater.LstatIfPossible(path)
+			if lstatErr == nil {
+				return false, err
+			}
+		}
+
+		return false, nil
+	}
+
+	return true, nil
+}
+
 // fullPath returns the full filesystem path for a key.
 func (f *FileStorer) fullPath(key string) string {
 	return filepath.Join(f.basePath, key)

internal/storage/file_backend_test.go

@@ -4,7 +4,10 @@ import (
 	"context"
 	"errors"
 	"io/fs"
+	"os"
 	"path/filepath"
+	"reflect"
+	"strings"
 	"testing"
 
 	"sneak.berlin/go/vaultik/internal/storage"
@@ -60,3 +63,232 @@ func TestFileStorerListMissingDestination(t *testing.T) {
 		t.Errorf("ListStream error = %v, want a not-exist error", streamErr)
 	}
 }
+
+// The two directories at the top of a destination, either of which the
+// tests below replace with a symlink.
+const (
+	metadataDir = "metadata"
+	blobsDir    = "blobs"
+)
+
+// moveBehindSymlink moves base/dir to a directory elsewhere and puts a
+// symlink to it in its place.
+func moveBehindSymlink(t *testing.T, base, dir string) {
+	t.Helper()
+
+	linkPath := filepath.Join(base, dir)
+	movedPath := filepath.Join(t.TempDir(), dir)
+
+	err := os.Rename(linkPath, movedPath)
+	if err != nil {
+		t.Fatalf("moving %s away: %v", dir, err)
+	}
+
+	err = os.Symlink(movedPath, linkPath)
+	if err != nil {
+		t.Fatalf("linking %s: %v", dir, err)
+	}
+}
+
+// TestFileStorerListsThroughSymlinkedDirectory checks that List and
+// ListStream read through a symlinked metadata/ or blobs/ directory, as Get
+// and Stat do, instead of listing the link as one key. Listing the whole
+// destination meets the link part-way through the walk; listing its prefix
+// starts the walk at the link. A prefix missing behind the link lists as
+// empty.
+func TestFileStorerListsThroughSymlinkedDirectory(t *testing.T) {
+	t.Parallel()
+
+	for _, dir := range []string{metadataDir, blobsDir} {
+		t.Run(dir, func(t *testing.T) {
+			t.Parallel()
+
+			base := t.TempDir()
+			key := dir + "/aa/bb/object"
+
+			s, err := storage.NewFileStorer(base)
+			if err != nil {
+				t.Fatalf("NewFileStorer: %v", err)
+			}
+
+			err = s.Put(context.Background(), key, strings.NewReader("data"))
+			if err != nil {
+				t.Fatalf("Put: %v", err)
+			}
+
+			moveBehindSymlink(t, base, dir)
+
+			want := []string{key}
+
+			for _, prefix := range []string{"", dir + "/"} {
+				got := listSorted(t, s, prefix)
+				if !reflect.DeepEqual(got, want) {
+					t.Errorf("List(%q) = %v, want %v", prefix, got, want)
+				}
+
+				got = listStreamKeys(t, s, prefix)
+				if !reflect.DeepEqual(got, want) {
+					t.Errorf("ListStream(%q) = %v, want %v", prefix, got, want)
+				}
+			}
+
+			absent := dir + "/absent/"
+
+			if got := listSorted(t, s, absent); len(got) != 0 {
+				t.Errorf("List(%q) = %v, want empty", absent, got)
+			}
+
+			if got := listStreamKeys(t, s, absent); len(got) != 0 {
+				t.Errorf("ListStream(%q) = %v, want empty", absent, got)
+			}
+		})
+	}
+}
+
+// TestFileStorerListFailsOnSymlinkWithMissingTarget checks that List and
+// ListStream fail on a symlinked metadata/ or blobs/ directory whose target
+// is missing, such as a link to a volume that is not mounted, as they do on
+// a missing destination directory, instead of listing it as empty. That
+// holds for a prefix below the link too.
+func TestFileStorerListFailsOnSymlinkWithMissingTarget(t *testing.T) {
+	t.Parallel()
+
+	ctx := context.Background()
+
+	for _, dir := range []string{metadataDir, blobsDir} {
+		t.Run(dir, func(t *testing.T) {
+			t.Parallel()
+
+			base := t.TempDir()
+
+			s, err := storage.NewFileStorer(base)
+			if err != nil {
+				t.Fatalf("NewFileStorer: %v", err)
+			}
+
+			unmounted := filepath.Join(t.TempDir(), "unmounted")
+
+			err = os.Symlink(unmounted, filepath.Join(base, dir))
+			if err != nil {
+				t.Fatalf("Symlink: %v", err)
+			}
+
+			for _, prefix := range []string{"", dir + "/", dir + "/aa/"} {
+				keys, err := s.List(ctx, prefix)
+				if !errors.Is(err, fs.ErrNotExist) {
+					t.Errorf("List(%q) = %v, %v; want a not-exist error",
+						prefix, keys, err)
+				}
+
+				var streamErr error
+
+				for object := range s.ListStream(ctx, prefix) {
+					if object.Err != nil {
+						streamErr = object.Err
+					}
+				}
+
+				if !errors.Is(streamErr, fs.ErrNotExist) {
+					t.Errorf("ListStream(%q) error = %v, want a not-exist error",
+						prefix, streamErr)
+				}
+			}
+		})
+	}
+}
+
+// TestFileStorerListFailsOnSymlinkLoop checks that a symlink pointing back
+// at the destination makes List and ListStream fail instead of walking it
+// forever.
+func TestFileStorerListFailsOnSymlinkLoop(t *testing.T) {
+	t.Parallel()
+
+	ctx := context.Background()
+	base := t.TempDir()
+
+	s, err := storage.NewFileStorer(base)
+	if err != nil {
+		t.Fatalf("NewFileStorer: %v", err)
+	}
+
+	err = s.Put(ctx, testBlobKey, strings.NewReader("data"))
+	if err != nil {
+		t.Fatalf("Put: %v", err)
+	}
+
+	err = os.Symlink(base, filepath.Join(base, "blobs", "loop"))
+	if err != nil {
+		t.Fatalf("Symlink: %v", err)
+	}
+
+	keys, err := s.List(ctx, "blobs/")
+	if err == nil {
+		t.Errorf("List = %d keys and no error, want an error", len(keys))
+	}
+
+	var streamErr error
+
+	for object := range s.ListStream(ctx, "blobs/") {
+		if object.Err != nil {
+			streamErr = object.Err
+		}
+	}
+
+	if streamErr == nil {
+		t.Error("ListStream sent no error, want one")
+	}
+}
+
+// TestFileStorerDeletePartialUploadsThroughSymlinkedDirectory checks that
+// DeletePartialUploads, which remote nuke uses, removes a leftover temp
+// file behind a symlinked metadata/ or blobs/ directory and keeps the
+// object at the real key.
+func TestFileStorerDeletePartialUploadsThroughSymlinkedDirectory(t *testing.T) {
+	t.Parallel()
+
+	ctx := context.Background()
+
+	for _, dir := range []string{metadataDir, blobsDir} {
+		t.Run(dir, func(t *testing.T) {
+			t.Parallel()
+
+			base := t.TempDir()
+			key := dir + "/aa/bb/object"
+
+			s, err := storage.NewFileStorer(base)
+			if err != nil {
+				t.Fatalf("NewFileStorer: %v", err)
+			}
+
+			err = s.Put(ctx, key, strings.NewReader("data"))
+			if err != nil {
+				t.Fatalf("Put: %v", err)
+			}
+
+			leftover := filepath.Join(base, key+"-123456.partial")
+
+			err = os.WriteFile(leftover, []byte("half"), 0o600)
+			if err != nil {
+				t.Fatalf("writing leftover temp file: %v", err)
+			}
+
+			moveBehindSymlink(t, base, dir)
+
+			err = s.DeletePartialUploads(ctx, dir+"/")
+			if err != nil {
+				t.Fatalf("DeletePartialUploads: %v", err)
+			}
+
+			// leftover runs through the link.
+			_, err = os.Stat(leftover)
+			if !os.IsNotExist(err) {
+				t.Errorf("leftover temp file was not removed: %v", err)
+			}
+
+			_, err = s.Stat(ctx, key)
+			if err != nil {
+				t.Errorf("Stat of the real key: %v", err)
+			}
+		})
+	}
+}

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" +
@@ -151,20 +150,16 @@ 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)
 	}
 
-	// Named before anything is restored, so the names are shown even
-	// when the restore stops on an error.
-	unmatchedErr := v.reportUnmatchedPaths(unmatched)
-
 	if len(files) == 0 {
 		log.Warn("No files found to restore")
 		v.UI.Warningf("No files found to restore.")
 
-		return unmatchedErr
+		return nil
 	}
 
 	log.Info("Found files to restore", "count", len(files))
@@ -190,20 +185,6 @@ func (v *Vaultik) Restore(opts *RestoreOptions) error {
 
 	result.Duration = time.Since(startTime)
 
-	return v.finishRestore(repos, files, unmatchedErr, opts, result)
-}
-
-// finishRestore prints the restore summary and the post-restore
-// warnings, runs optional verification, and converts any failed-file
-// count into an error. Otherwise it returns unmatchedErr, the error for
-// the requested paths that matched nothing (nil when there are none).
-func (v *Vaultik) finishRestore(
-	repos *database.Repositories,
-	files []*database.File,
-	unmatchedErr error,
-	opts *RestoreOptions,
-	result *RestoreResult,
-) error {
 	log.Info("Restore complete",
 		"files_restored", result.FilesRestored,
 		"bytes_restored", ubytes(result.BytesRestored),
@@ -218,6 +199,17 @@ func (v *Vaultik) finishRestore(
 		v.UI.Duration(result.Duration),
 	)
 
+	return v.finishRestore(repos, files, opts, result)
+}
+
+// finishRestore emits the post-restore warnings, runs optional
+// verification, and converts any failed-file count into an error.
+func (v *Vaultik) finishRestore(
+	repos *database.Repositories,
+	files []*database.File,
+	opts *RestoreOptions,
+	result *RestoreResult,
+) error {
 	if os.Geteuid() != 0 {
 		v.UI.Warningf("Restore did not preserve file ownership: chown(2) " +
 			"requires root. Re-run as root (e.g. with sudo) if you need " +
@@ -244,23 +236,7 @@ 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
@@ -864,34 +840,27 @@ 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 {
@@ -902,7 +871,7 @@ func (v *Vaultik) getFilesToRestore(
 		}
 	}
 
-	return result, unmatched, nil
+	return result, nil
 }
 
 // buildChunkToBlobMap creates a mapping from chunk hash to blob information

internal/vaultik/restore_unmatched_path_test.go

@@ -1,202 +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/storage/faultstore"
-	"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")
-}
-
-// Without --skip-errors a damaged blob stops the restore part way. The
-// path that matches nothing must still be named.
-func TestRestoreNamesUnmatchedPathWhenADamagedBlobStopsIt(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()
-
-	writeFaultSourceTree(t, fs, dataDir)
-
-	inner, err := storage.NewFileStorer(storeDir)
-	require.NoError(t, err)
-
-	db, err := database.New(ctx, dbPath)
-	require.NoError(t, err)
-
-	id := fullFaultBackup(ctx, t, fs, inner, cfg,
-		database.NewRepositories(db), dataDir, dbPath, "damaged")
-	require.NoError(t, db.Close())
-
-	damaged := faultstore.New(inner)
-	damaged.OnGet = func(key string) faultstore.GetFault {
-		if strings.HasPrefix(key, "blobs/") {
-			return faultstore.GetCorrupt
-		}
-
-		return faultstore.GetNormal
-	}
-
-	matched := filepath.Join(dataDir, "small.txt")
-	unmatched := filepath.Join(dataDir, "typo.txt")
-
-	var out bytes.Buffer
-
-	v := newReaderVaultik(ctx, cfg, damaged, 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 damaged blob must stop the restore")
-	assert.Contains(t, err.Error(), "blob",
-		"the restore must stop on the damaged blob")
-	assert.Contains(t, out.String(), unmatched,
-		"the path that matches nothing must be named")
-}

internal/vaultik/symlinked_destination_test.go

@@ -0,0 +1,147 @@
+package vaultik_test
+
+import (
+	"context"
+	"io/fs"
+	"os"
+	"path/filepath"
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+	"sneak.berlin/go/vaultik/internal/log"
+	"sneak.berlin/go/vaultik/internal/vaultik"
+)
+
+// TestPruneDeletesNothingThroughSymlinkedDirectory checks that prune keeps
+// every blob and the local snapshot record when the metadata/ or blobs/
+// directory of a file:// destination is a symlink to a directory elsewhere
+// (https://git.eeqj.de/sneak/vaultik/issues/296). A backup writes through
+// such a link, so prune has to list through it too.
+func TestPruneDeletesNothingThroughSymlinkedDirectory(t *testing.T) {
+	log.Initialize(log.Config{})
+	t.Parallel()
+
+	for _, dir := range []string{"metadata", "blobs"} {
+		t.Run(dir, func(t *testing.T) {
+			t.Parallel()
+
+			ctx := context.Background()
+			storeDir := filepath.Join(t.TempDir(), "store")
+			v, repos, _ := backUpToFileDestination(ctx, t, storeDir)
+			blobFiles := blobFilesIn(t, storeDir)
+			moveBehindSymlink(t, storeDir, dir)
+
+			require.NoError(t, v.Prune(&vaultik.PruneOptions{Force: true}))
+
+			// When blobs/ is the link, these paths run through it.
+			for _, blobFile := range blobFiles {
+				assert.FileExists(t, blobFile, "prune must delete no blob")
+			}
+
+			snapshots, err := repos.Snapshots.ListRecent(ctx, listRecentTestLimit)
+			require.NoError(t, err)
+			assert.Len(t, snapshots, 1, "prune must delete no local snapshot record")
+		})
+	}
+}
+
+// TestPruneFailsOnSymlinkedDirectoryWithMissingTarget checks that prune
+// fails, deleting no blob and keeping the local snapshot record, when the
+// metadata/ or blobs/ directory of a file:// destination is a symlink
+// whose target is missing, as a link to a volume that is not mounted is.
+func TestPruneFailsOnSymlinkedDirectoryWithMissingTarget(t *testing.T) {
+	log.Initialize(log.Config{})
+	t.Parallel()
+
+	for _, dir := range []string{"metadata", "blobs"} {
+		t.Run(dir, func(t *testing.T) {
+			t.Parallel()
+
+			ctx := context.Background()
+			storeDir := filepath.Join(t.TempDir(), "store")
+			v, repos, _ := backUpToFileDestination(ctx, t, storeDir)
+			blobFiles := blobFilesIn(t, storeDir)
+			targetPath := moveBehindSymlink(t, storeDir, dir)
+
+			// Unmount the volume the link points to, and mount it again
+			// once prune has run.
+			unmountedPath := targetPath + "-unmounted"
+			require.NoError(t, os.Rename(targetPath, unmountedPath))
+
+			err := v.Prune(&vaultik.PruneOptions{Force: true})
+			require.ErrorIs(t, err, fs.ErrNotExist)
+
+			require.NoError(t, os.Rename(unmountedPath, targetPath))
+
+			// When blobs/ is the link, these paths run through it.
+			for _, blobFile := range blobFiles {
+				assert.FileExists(t, blobFile, "prune must delete no blob")
+			}
+
+			snapshots, err := repos.Snapshots.ListRecent(ctx, listRecentTestLimit)
+			require.NoError(t, err)
+			assert.Len(t, snapshots, 1, "prune must delete no local snapshot record")
+		})
+	}
+}
+
+// TestRemoveSnapshotWarnsOnSymlinkedMetadataWithMissingTarget checks that
+// snapshot remove warns that the metadata could not be removed from the
+// destination when metadata/ is a symlink whose target is missing, as it
+// does when the destination directory is missing, instead of finding no
+// metadata to remove.
+func TestRemoveSnapshotWarnsOnSymlinkedMetadataWithMissingTarget(t *testing.T) {
+	log.Initialize(log.Config{})
+	t.Parallel()
+
+	ctx := context.Background()
+	storeDir := filepath.Join(t.TempDir(), "store")
+	v, repos, out := backUpToFileDestination(ctx, t, storeDir)
+	targetPath := moveBehindSymlink(t, storeDir, "metadata")
+	require.NoError(t, os.Rename(targetPath, targetPath+"-unmounted"))
+
+	result, err := v.RemoveSnapshot(localSnapshotID(ctx, t, repos, "first"),
+		&vaultik.RemoveOptions{Force: true})
+	require.NoError(t, err)
+
+	assert.False(t, result.RemoteRemoved)
+	assert.Contains(t, out.String(),
+		"Could not remove snapshot metadata from remote")
+	assert.NotContains(t, out.String(),
+		"Removed snapshot metadata from remote storage")
+}
+
+// blobFilesIn returns the paths of the blob files under storeDir/blobs, and
+// fails the test when there are none.
+func blobFilesIn(t *testing.T, storeDir string) []string {
+	t.Helper()
+
+	var blobFiles []string
+
+	err := filepath.WalkDir(filepath.Join(storeDir, "blobs"),
+		func(path string, entry fs.DirEntry, err error) error {
+			if err == nil && !entry.IsDir() {
+				blobFiles = append(blobFiles, path)
+			}
+
+			return err
+		})
+	require.NoError(t, err)
+	require.NotEmpty(t, blobFiles)
+
+	return blobFiles
+}
+
+// moveBehindSymlink moves storeDir/dir to a directory elsewhere, puts a
+// symlink to it in its place, and returns where it went.
+func moveBehindSymlink(t *testing.T, storeDir, dir string) string {
+	t.Helper()
+
+	linkPath := filepath.Join(storeDir, dir)
+	targetPath := filepath.Join(t.TempDir(), dir)
+	require.NoError(t, os.Rename(linkPath, targetPath))
+	require.NoError(t, os.Symlink(targetPath, linkPath))
+
+	return targetPath
+}