Refuse credentials in a storage URL's endpoint or rclone remote name (closes #322)

storage_url refused only the outer URL's userinfo and unknown query
parameters. Userinfo inside the s3 endpoint= value, and rclone's
remote,param=value parameters in the remote name, were accepted and
then printed by info, remote info and snapshot create. Both are now
refused without echoing the value: a host name never contains "@", and
an rclone remote name never contains a comma. An s3 query that cannot
be decoded (a ";" or a bad "%" escape) is refused too, because decoding
drops that part, endpoint included, before it can be checked. The comma
is checked before url.Parse, whose error for such a name prints part of
it. The rclone case has its own error pointing at rclone config.

Model: opus-5-5

ARCHITECTURE.md

@@ -279,8 +279,8 @@ Key methods:
 - `Scan(ctx, path, snapshotID)` → Main scan operation
 
 Scan phases:
-1. **Phase 1**: Walk directory, identify files needing processing
+1. **Phase 0**: Detect deleted files from previous snapshots
-2. **Phase 1b**: Count as deleted the files that the previous snapshot of the same name lists and the walk did not find; a file that is excluded, or inside an excluded directory, is not counted
+2. **Phase 1**: Walk directory, identify files needing processing
 3. **Phase 2**: Process files (chunk → pack → upload)
 
 #### SnapshotManager
@@ -320,13 +320,13 @@ CreateSnapshot(opts)
     │       │
     │       ├─► scanner.Scan(ctx, path, snapshotID)
     │       │       │
+    │       │       ├─► Phase 0: detectDeletedFiles()
+    │       │       │
     │       │       ├─► Phase 1: scanPhase()
     │       │       │       Walk directory
     │       │       │       Check file metadata changes
     │       │       │       Build list of files to process
     │       │       │
-    │       │       ├─► Phase 1b: detectDeletedFiles()
-    │       │       │
     │       │       └─► Phase 2: processPhase()
     │       │               For each file:
     │       │                   chunker.ChunkReaderStreaming()

internal/database/files.go

@@ -267,45 +267,6 @@ func (r *FileRepository) ListUnderPath(
 	return files, rows.Err()
 }
 
-// ListUnderPathInSnapshot returns the files that ListUnderPath returns
-// for path and that the snapshot lists, in no particular order.
-func (r *FileRepository) ListUnderPathInSnapshot(
-	ctx context.Context, path, snapshotID string,
-) ([]*File, error) {
-	path = strings.TrimRight(path, "/")
-	dirPrefix := path + "/"
-
-	query := `
-		SELECT f.id, f.path, f.source_path, f.mtime, f.mtime_nsec, f.size,
-			f.mode, f.uid, f.gid, f.link_target
-		FROM files f
-		JOIN snapshot_files sf ON sf.file_id = f.id
-		WHERE sf.snapshot_id = ?
-		  AND (f.path = ? OR substr(f.path, 1, length(?)) = ?)
-	`
-
-	rows, err := r.db.conn.QueryContext(ctx, query,
-		snapshotID, path, dirPrefix, dirPrefix)
-	if err != nil {
-		return nil, fmt.Errorf("querying files: %w", err)
-	}
-
-	defer func() { _ = rows.Close() }()
-
-	var files []*File
-
-	for rows.Next() {
-		file, err := r.scanFileRows(rows)
-		if err != nil {
-			return nil, fmt.Errorf("scanning file: %w", err)
-		}
-
-		files = append(files, file)
-	}
-
-	return files, rows.Err()
-}
-
 // ListIDsWithChunksNotInUploadedBlobs returns the IDs of the files whose
 // path starts with prefix and that list at least one chunk held by no
 // blob whose upload has completed (uploaded_ts set). A new snapshot

internal/database/files_test.go

@@ -212,65 +212,6 @@ func TestFileRepositoryListUnderPath(t *testing.T) {
 	}
 }
 
-// ListUnderPathInSnapshot leaves out files outside path and files the
-// snapshot does not list, though another snapshot lists them.
-func TestFileRepositoryListUnderPathInSnapshot(t *testing.T) {
-	t.Parallel()
-
-	db, cleanup := setupTestDB(t)
-	defer cleanup()
-
-	ctx := context.Background()
-	files := database.NewFileRepository(db)
-	snapshots := database.NewSnapshotRepository(db)
-
-	listed := map[string][]string{
-		"one": {"/src/a.txt", "/src2/c.txt"},
-		"two": {"/src/b.txt"},
-	}
-
-	for snapshotID, paths := range listed {
-		err := snapshots.Create(ctx, nil, &database.Snapshot{
-			ID:        types.SnapshotID(snapshotID),
-			Hostname:  "host",
-			StartedAt: time.Now(),
-		})
-		if err != nil {
-			t.Fatalf("failed to create snapshot %s: %v", snapshotID, err)
-		}
-
-		for _, path := range paths {
-			err := files.Create(ctx, nil, &database.File{
-				Path:  types.FilePath(path),
-				MTime: time.Now().Truncate(time.Second),
-				Mode:  0644,
-			})
-			if err != nil {
-				t.Fatalf("failed to create %s: %v", path, err)
-			}
-
-			err = snapshots.AddFile(ctx, nil, snapshotID, path)
-			if err != nil {
-				t.Fatalf("failed to add %s to %s: %v", path, snapshotID, err)
-			}
-		}
-	}
-
-	found, err := files.ListUnderPathInSnapshot(ctx, "/src", "one")
-	if err != nil {
-		t.Fatalf("failed to list files: %v", err)
-	}
-
-	got := make([]string, 0, len(found))
-	for _, f := range found {
-		got = append(got, f.Path.String())
-	}
-
-	if !slices.Equal(got, []string{"/src/a.txt"}) {
-		t.Errorf("got %q, want only /src/a.txt", got)
-	}
-}
-
 func TestFileRepositorySymlink(t *testing.T) {
 	t.Parallel()
 

internal/snapshot/module.go

@@ -16,9 +16,6 @@ type ScannerParams struct {
 	Fs             afero.Fs
 	Exclude        []string // Exclude patterns (combined global + snapshot-specific)
 	SkipErrors     bool     // Skip file read errors (log loudly but continue)
-	// PreviousSnapshotID is the most recent completed snapshot of the
-	// same name, "" for none.
-	PreviousSnapshotID string
 }
 
 // Module exports backup functionality as an fx module.
@@ -47,18 +44,17 @@ func provideScannerFactory(
 		}
 
 		return NewScanner(ScannerConfig{
-			FS:                 params.Fs,
+			FS:               params.Fs,
-			ChunkSize:          cfg.ChunkSize.Int64(),
+			ChunkSize:        cfg.ChunkSize.Int64(),
-			Repositories:       repos,
+			Repositories:     repos,
-			Storage:            storer,
+			Storage:          storer,
-			MaxBlobSize:        cfg.BlobSizeLimit.Int64(),
+			MaxBlobSize:      cfg.BlobSizeLimit.Int64(),
-			CompressionLevel:   cfg.CompressionLevel,
+			CompressionLevel: cfg.CompressionLevel,
-			AgeRecipients:      cfg.AgeRecipients,
+			AgeRecipients:    cfg.AgeRecipients,
-			EnableProgress:     params.EnableProgress,
+			EnableProgress:   params.EnableProgress,
-			UI:                 params.UI,
+			UI:               params.UI,
-			Exclude:            excludes,
+			Exclude:          excludes,
-			SkipErrors:         params.SkipErrors,
+			SkipErrors:       params.SkipErrors,
-			PreviousSnapshotID: params.PreviousSnapshotID,
 		})
 	}
 }

internal/snapshot/scanner.go

@@ -58,10 +58,6 @@ type Scanner struct {
 	compressionLevel int
 	ageRecipient     string
 	snapshotID       string // Current snapshot being processed
-	// previousSnapshotID is the most recent completed snapshot of the
-	// same name, "" for none. Only a file it lists can be counted as
-	// deleted.
-	previousSnapshotID string
 	// currentSourcePath is the source directory being scanned, stored with
 	// each file record.
 	currentSourcePath string
@@ -133,9 +129,6 @@ type ScannerConfig struct {
 	// SkipErrors skips files that cannot be opened or read (log loudly but
 	// continue); packer, database, encryption, and upload errors still abort.
 	SkipErrors bool
-	// PreviousSnapshotID is the most recent completed snapshot of the
-	// same name, "" for none.
-	PreviousSnapshotID string
 }
 
 // ScanResult contains the results of a scan operation. Files and bytes
@@ -214,7 +207,6 @@ func NewScanner(cfg ScannerConfig) *Scanner {
 		compiledExclude:    compiledExclude,
 		progress:           progress,
 		skipErrors:         cfg.SkipErrors,
-		previousSnapshotID: cfg.PreviousSnapshotID,
 		ui:                 uiw,
 		pendingChunkHashes: make(map[string]struct{}),
 	}
@@ -266,9 +258,8 @@ func (s *Scanner) Scan(
 
 	filesToProcess := scanResult.FilesToProcess
 
-	// Phase 1b: Detect deleted files by comparing the previous snapshot
+	// Phase 1b: Detect deleted files by comparing DB against scanned files
-	// of this name against scanned files
+	err = s.detectDeletedFilesFromMap(ctx, knownFiles, existingFiles, result)
-	err = s.detectDeletedFiles(ctx, path, existingFiles, result)
 	if err != nil {
 		return nil, fmt.Errorf("detecting deleted files: %w", err)
 	}
@@ -448,8 +439,9 @@ func (s *Scanner) summarizeScanPhase(
 }
 
 // loadKnownFiles loads the known files at and beneath path from the
-// database into a map for fast lookup. This avoids per-file database
+// database into a map for fast lookup. Every loaded file the scan does
-// queries during the scan phase.
+// not find is counted as deleted. This avoids per-file database queries
+// during the scan phase.
 func (s *Scanner) loadKnownFiles(
 	ctx context.Context, path string,
 ) (map[string]*database.File, error) {
@@ -1962,28 +1954,21 @@ func (s *Scanner) queueFileForBatchInsert(
 	})
 }
 
-// detectDeletedFiles counts as deleted each file at or beneath path that
+// detectDeletedFilesFromMap finds files that existed in previous snapshots
-// the previous snapshot of this name lists and the walk did not find.
+// but no longer exist. Uses pre-loaded maps to avoid any filesystem or
-// A file that is excluded, or inside an excluded directory, is not
+// database access.
-// counted: the walk skips it whether or not it is still on disk.
+func (s *Scanner) detectDeletedFilesFromMap(
-func (s *Scanner) detectDeletedFiles(
 	ctx context.Context,
-	path string,
+	knownFiles map[string]*database.File,
 	existingFiles map[string]struct{},
 	result *ScanResult,
 ) error {
-	if s.previousSnapshotID == "" {
+	if len(knownFiles) == 0 {
 		return nil
 	}
 
-	previousFiles, err := s.repos.Files.ListUnderPathInSnapshot(
+	// Check each known file against the enumerated set (no filesystem access needed)
-		ctx, path, s.previousSnapshotID)
+	for path, file := range knownFiles {
-	if err != nil {
-		return fmt.Errorf("listing files of snapshot %s: %w",
-			s.previousSnapshotID, err)
-	}
-
-	for _, file := range previousFiles {
 		// Check context cancellation periodically
 		select {
 		case <-ctx.Done():
@@ -1991,16 +1976,13 @@ func (s *Scanner) detectDeletedFiles(
 		default:
 		}
 
-		filePath := file.Path.String()
+		// Check if the file exists in our enumerated set
-
+		if _, exists := existingFiles[path]; !exists {
-		_, exists := existingFiles[filePath]
+			// File has been deleted
-		if exists || s.excludedOrInExcludedDir(filePath, path) {
+			result.FilesDeleted++
-			continue
+			result.BytesDeleted += file.Size
+			log.Debug("Detected deleted file", "path", path, "size", file.Size)
 		}
-
-		result.FilesDeleted++
-		result.BytesDeleted += file.Size
-		log.Debug("Detected deleted file", "path", filePath, "size", file.Size)
 	}
 
 	if result.FilesDeleted > 0 {
@@ -2011,20 +1993,6 @@ func (s *Scanner) detectDeletedFiles(
 	return nil
 }
 
-// excludedOrInExcludedDir reports whether filePath, which is at or
-// beneath rootPath, or any directory between rootPath and it, matches an
-// exclude pattern. A pattern such as */.local/share/Trash matches the
-// directory but not the files inside it, which the walk skips too.
-func (s *Scanner) excludedOrInExcludedDir(filePath, rootPath string) bool {
-	for p := filePath; len(p) > len(rootPath); p = filepath.Dir(p) {
-		if s.shouldExclude(p, rootPath) {
-			return true
-		}
-	}
-
-	return false
-}
-
 // wrapPermissionError augments permission errors with platform-specific
 // remediation instructions. On macOS, TCC-protected directories (Calendars,
 // Reminders, Photos, etc.) return EPERM unless the running application has

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
+// List returns all keys with the given prefix, reading through symlinked
-// destination directory is missing; a missing prefix under it is an
+// directories. It fails when the destination directory is missing, or
-// empty listing.
+// 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 := f.prefixExists(prefix)
-	exists, err := afero.Exists(f.fs, basePath)
 	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 := f.prefixExists(prefix)
-		exists, err := afero.Exists(f.fs, basePath)
 		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/storage/url.go

@@ -30,6 +30,12 @@ var (
 		"storage URL must not carry credentials; " +
 			"set s3.access_key_id and s3.secret_access_key in the config instead")
 	ErrURLUnknownParam = errors.New("unknown query parameter in storage URL")
+	ErrURLBadQuery     = errors.New(
+		"storage URL query cannot be decoded; " +
+			"check it for a ; or a % not followed by two hex digits")
+	ErrRcloneRemoteParams = errors.New(
+		"rclone URL must not carry parameters in the remote name; " +
+			"set them on the remote with rclone config instead")
 )
 
 // URL represents a parsed storage URL.
@@ -90,8 +96,9 @@ func parseFileURL(rawPath string) (*URL, error) {
 }
 
 // parseS3URL parses an s3://bucket/prefix URL. It rejects credentials in
-// the userinfo and any query parameter other than endpoint, region and
+// the userinfo or in the endpoint parameter's userinfo, a query that
-// ssl, so a credential-bearing URL is never stored or echoed.
+// cannot be decoded, and any query parameter other than endpoint, region
+// and ssl, so a credential-bearing URL is never stored or echoed.
 func parseS3URL(rawURL string) (*URL, error) {
 	u, err := url.Parse(rawURL)
 	if err != nil {
@@ -107,13 +114,26 @@ func parseS3URL(rawURL string) (*URL, error) {
 		return nil, ErrMissingBucket
 	}
 
-	query := u.Query()
+	// u.Query() would silently drop a part it cannot decode, endpoint
+	// included. The decode error is not wrapped: it can quote the value.
+	query, err := url.ParseQuery(u.RawQuery)
+	if err != nil {
+		return nil, ErrURLBadQuery
+	}
 
 	err = rejectUnknownParams(query, "endpoint", "region", "ssl")
 	if err != nil {
 		return nil, err
 	}
 
+	// A host name never contains "@", so one in an endpoint, with or
+	// without a scheme, can only introduce userinfo.
+	for _, endpoint := range query["endpoint"] {
+		if strings.Contains(endpoint, "@") {
+			return nil, ErrURLCredentials
+		}
+	}
+
 	return &URL{
 		Scheme:   schemeS3,
 		Bucket:   bucket,
@@ -125,9 +145,23 @@ func parseS3URL(rawURL string) (*URL, error) {
 }
 
 // parseRcloneURL parses an rclone://remote/path URL. rclone:// takes no
-// query parameters, so credentials in the userinfo and any parameter at
+// query parameters, so credentials in the userinfo, parameters in the
-// all are rejected rather than silently ignored.
+// remote name and any query parameter at all are rejected rather than
+// silently ignored.
 func parseRcloneURL(rawURL string) (*URL, error) {
+	// The remote name runs up to the first "/", "?" or "#". It never
+	// contains a comma; one starts rclone's remote,param=value form,
+	// whose values can be credentials. This is checked before url.Parse,
+	// whose error for such a name can print part of it.
+	remote := strings.TrimPrefix(rawURL, "rclone://")
+	if end := strings.IndexAny(remote, "/?#"); end >= 0 {
+		remote = remote[:end]
+	}
+
+	if strings.Contains(remote, ",") {
+		return nil, ErrRcloneRemoteParams
+	}
+
 	u, err := url.Parse(rawURL)
 	if err != nil {
 		return nil, wrapParseError(err)
@@ -137,7 +171,7 @@ func parseRcloneURL(rawURL string) (*URL, error) {
 		return nil, ErrURLCredentials
 	}
 
-	remote := u.Host
+	remote = u.Host
 	if remote == "" {
 		return nil, ErrMissingRemote
 	}

internal/storage/url_parse_test.go

@@ -150,6 +150,19 @@ func TestParseStorageURLRejectsCredentials(t *testing.T) {
 			wantErr: storage.ErrURLCredentials,
 			secrets: []string{key, secret, "mybucket"},
 		},
+		{
+			name: "s3 userinfo in endpoint",
+			raw: "s3://mybucket?endpoint=https://" +
+				key + ":" + secret + "@minio.example.com",
+			wantErr: storage.ErrURLCredentials,
+			secrets: []string{key, secret},
+		},
+		{
+			name:    "s3 userinfo in endpoint without scheme",
+			raw:     "s3://mybucket?endpoint=" + key + ":" + secret + "@minio.example.com",
+			wantErr: storage.ErrURLCredentials,
+			secrets: []string{key, secret},
+		},
 		{
 			name:    "s3 unknown query param",
 			raw:     "s3://mybucket?access_key=" + key + "&secret=" + secret,
@@ -203,6 +216,104 @@ func TestParseStorageURLRejectsCredentials(t *testing.T) {
 	}
 }
 
+// TestParseStorageURLRejectsRcloneRemoteParams checks that an rclone
+// remote name carrying parameters (rclone's "remote,param=value" form,
+// which can hold a credential) is rejected without echoing the value,
+// including the URLs that url.Parse itself refuses.
+func TestParseStorageURLRejectsRcloneRemoteParams(t *testing.T) {
+	t.Parallel()
+
+	cases := []struct {
+		name    string
+		raw     string
+		secrets []string // must not appear in the error message
+	}{
+		{
+			name:    "configured remote",
+			raw:     "rclone://gdrive,client_secret=topsecret/backups",
+			secrets: []string{"topsecret"},
+		},
+		{
+			name:    "remote defined inline",
+			raw:     "rclone://:s3,access_key_id=KEY,secret_access_key=SECRET/bucket",
+			secrets: []string{"KEY", "SECRET"},
+		},
+		{
+			name:    "colon in a parameter value",
+			raw:     "rclone://gdrive,client_secret=ab:cd/backups",
+			secrets: []string{"cd"},
+		},
+	}
+
+	for _, tc := range cases {
+		t.Run(tc.name, func(t *testing.T) {
+			t.Parallel()
+
+			_, err := storage.ParseStorageURL(tc.raw)
+			if !errors.Is(err, storage.ErrRcloneRemoteParams) {
+				t.Fatalf("ParseStorageURL(%q) error = %v, want %v",
+					tc.raw, err, storage.ErrRcloneRemoteParams)
+			}
+
+			for _, secret := range tc.secrets {
+				if strings.Contains(err.Error(), secret) {
+					t.Errorf("error message leaked %q: %v", secret, err.Error())
+				}
+			}
+		})
+	}
+}
+
+// TestParseStorageURLRejectsUndecodableQuery checks that an s3 URL whose
+// query cannot be decoded is rejected, not read with that part of the
+// query left out, and that the error does not echo it.
+func TestParseStorageURLRejectsUndecodableQuery(t *testing.T) {
+	t.Parallel()
+
+	const (
+		key    = "AKIAKEY"
+		secret = "topsecret"
+	)
+
+	cases := []struct {
+		name string
+		raw  string
+	}{
+		{
+			name: "semicolon",
+			raw: "s3://mybucket/prefix?endpoint=https://" + key + ":" + secret +
+				"@minio.example.com:9000;region=us-east-1",
+		},
+		{
+			name: "bad percent escape",
+			raw: "s3://mybucket/prefix?endpoint=https://" + key + ":" + secret +
+				"%zz@minio.example.com:9000",
+		},
+	}
+
+	for _, tc := range cases {
+		t.Run(tc.name, func(t *testing.T) {
+			t.Parallel()
+
+			_, err := storage.ParseStorageURL(tc.raw)
+			if err == nil {
+				t.Fatalf("ParseStorageURL(%q) returned no error", tc.raw)
+			}
+
+			if !errors.Is(err, storage.ErrURLBadQuery) {
+				t.Errorf("ParseStorageURL(%q) error = %v, want %v",
+					tc.raw, err, storage.ErrURLBadQuery)
+			}
+
+			for _, s := range []string{key, secret, "minio.example.com"} {
+				if strings.Contains(err.Error(), s) {
+					t.Errorf("error message leaked %q: %v", s, err.Error())
+				}
+			}
+		})
+	}
+}
+
 // TestParseStorageURLParseFailureHidesURL checks that when url.Parse
 // itself fails, the wrapped error carries only the inner cause, not the
 // *url.Error whose text embeds the raw (possibly credential-bearing) URL.

internal/vaultik/deep_verify_test.go

@@ -1,7 +1,9 @@
 package vaultik_test
 
 import (
+	"bytes"
 	"context"
+	"crypto/rand"
 	"io"
 	"os"
 	"path/filepath"
@@ -9,7 +11,9 @@ import (
 
 	"github.com/spf13/afero"
 	"github.com/stretchr/testify/require"
+	"sneak.berlin/go/vaultik/internal/config"
 	"sneak.berlin/go/vaultik/internal/log"
+	"sneak.berlin/go/vaultik/internal/storage"
 	"sneak.berlin/go/vaultik/internal/ui"
 	"sneak.berlin/go/vaultik/internal/vaultik"
 )
@@ -77,6 +81,174 @@ func TestDeepVerifyAcceptsHealthyAndRejectsCorruptBlob(t *testing.T) {
 		"deep verify should fail on a corrupted blob")
 }
 
+// TestDeepVerifyJSONCountsBlobs checks the verified and missing counts
+// that deep verify reports under --json: on a healthy snapshot, with a
+// damaged blob, and with missing blobs. Deep verify stops at the first
+// damaged blob, so the blobs read before it are the ones verified; when
+// blobs are missing it reads no blob contents, but counts every missing
+// blob.
+func TestDeepVerifyJSONCountsBlobs(t *testing.T) {
+	log.Initialize(log.Config{})
+	t.Parallel()
+
+	fs := afero.NewOsFs()
+	ctx := context.Background()
+	storeDir := filepath.Join(t.TempDir(), "remote")
+
+	cfg, storer, snapshotID, keys := backUpSeveralBlobs(ctx, t, storeDir)
+
+	healthy, err := deepVerifyJSON(ctx, t, cfg, storer, snapshotID)
+	require.NoError(t, err)
+	require.Equal(t, "ok", healthy.Status)
+	require.Len(t, keys, healthy.BlobCount)
+	require.Equal(t, healthy.BlobCount, healthy.Verified)
+	require.Zero(t, healthy.Missing)
+
+	// Damage the last blob read, keeping its length, so every blob before
+	// it is read and passes first.
+	lastPath := filepath.Join(storeDir, keys[len(keys)-1])
+	blob, err := afero.ReadFile(fs, lastPath)
+	require.NoError(t, err)
+
+	blob[len(blob)/2] ^= 0xff
+	require.NoError(t, afero.WriteFile(fs, lastPath, blob, 0o600))
+
+	got, err := deepVerifyJSON(ctx, t, cfg, storer, snapshotID)
+	require.Error(t, err)
+	require.Equal(t, "failed", got.Status)
+	require.Equal(t, healthy.BlobCount-1, got.Verified)
+	require.Zero(t, got.Missing)
+
+	// Delete the first blob and the damaged last one: both must be
+	// counted as missing, not only the first one found.
+	var deletedSize int64
+
+	for _, key := range []string{keys[0], keys[len(keys)-1]} {
+		info, statErr := storer.Stat(ctx, key)
+		require.NoError(t, statErr)
+
+		deletedSize += info.Size
+
+		require.NoError(t, storer.Delete(ctx, key))
+	}
+
+	got, err = deepVerifyJSON(ctx, t, cfg, storer, snapshotID)
+	require.Error(t, err)
+	require.Equal(t, "failed", got.Status)
+	require.Equal(t, 2, got.Missing)
+	require.Equal(t, deletedSize, got.MissingSize)
+	require.Zero(t, got.Verified)
+}
+
+// TestDeepVerifyJSONCountsWrongSizeBlob checks that under --deep --json a
+// blob of the wrong size is counted in mismatched and fails the run, and
+// that the check goes on past it to count a missing blob after it.
+func TestDeepVerifyJSONCountsWrongSizeBlob(t *testing.T) {
+	log.Initialize(log.Config{})
+	t.Parallel()
+
+	fs := afero.NewOsFs()
+	ctx := context.Background()
+	storeDir := filepath.Join(t.TempDir(), "remote")
+
+	cfg, storer, snapshotID, keys := backUpSeveralBlobs(ctx, t, storeDir)
+
+	// Make the first blob checked longer, and delete the last one.
+	firstPath := filepath.Join(storeDir, keys[0])
+	blob, err := afero.ReadFile(fs, firstPath)
+	require.NoError(t, err)
+
+	blob = append(blob, []byte("extra")...)
+	require.NoError(t, afero.WriteFile(fs, firstPath, blob, 0o600))
+	require.NoError(t, storer.Delete(ctx, keys[len(keys)-1]))
+
+	got, err := deepVerifyJSON(ctx, t, cfg, storer, snapshotID)
+	require.Error(t, err)
+	require.Equal(t, "failed", got.Status)
+	require.Equal(t, 1, got.Mismatched)
+	require.Equal(t, 1, got.Missing)
+	require.Zero(t, got.Verified)
+}
+
+// TestDeepVerifyStopsOnBlobThatCannotBeChecked checks that a blob that is
+// present in storage but cannot be checked is not counted as missing:
+// deep verify stops and fails with the storage error.
+func TestDeepVerifyStopsOnBlobThatCannotBeChecked(t *testing.T) {
+	log.Initialize(log.Config{})
+	t.Parallel()
+
+	ctx := context.Background()
+	storeDir := filepath.Join(t.TempDir(), "remote")
+
+	cfg, storer, snapshotID, keys := backUpSeveralBlobs(ctx, t, storeDir)
+	failing := statFailingStorer{Storer: storer, failKeys: []string{keys[0]}}
+
+	got, err := deepVerifyJSON(ctx, t, cfg, failing, snapshotID)
+	require.Error(t, err)
+	require.Equal(t, "failed", got.Status)
+	require.Zero(t, got.Missing)
+	require.Contains(t, got.ErrorMessage, errStatDenied.Error())
+}
+
+// backUpSeveralBlobs backs up random data, which does not compress or
+// deduplicate, so it fills at least three blobs in a store on disk at
+// storeDir. It returns the blobs' storage keys sorted, which is hash
+// order, the order deep verify reads them in.
+func backUpSeveralBlobs(
+	ctx context.Context, t *testing.T, storeDir string,
+) (*config.Config, *storage.FileStorer, string, []string) {
+	t.Helper()
+
+	fs := afero.NewOsFs()
+	tempDir := t.TempDir()
+	dataDir := filepath.Join(tempDir, "source")
+	dbPath := filepath.Join(tempDir, "index.sqlite")
+
+	chunkSize := int64(32 * 1024)
+	maxBlobSize := int64(128 * 1024)
+
+	data := make([]byte, maxBlobSize*4)
+	_, err := rand.Read(data)
+	require.NoError(t, err)
+	require.NoError(t, fs.MkdirAll(dataDir, 0o755))
+	require.NoError(t, afero.WriteFile(fs,
+		filepath.Join(dataDir, "data.bin"), data, 0o644))
+
+	cfg, storer, snapshotID := runFileStorageBackup(
+		ctx, t, fs, dataDir, storeDir, dbPath, chunkSize, maxBlobSize)
+
+	keys := storedBlobKeys(t, storeDir)
+	require.GreaterOrEqual(t, len(keys), 3)
+
+	return cfg, storer, snapshotID, keys
+}
+
+// deepVerifyJSON runs deep verify with --json on snapshotID and returns
+// the decoded result and the error RunDeepVerify returned.
+func deepVerifyJSON(
+	ctx context.Context, t *testing.T,
+	cfg *config.Config, storer storage.Storer, snapshotID string,
+) (vaultik.VerifyResult, error) {
+	t.Helper()
+
+	var out bytes.Buffer
+
+	v := &vaultik.Vaultik{
+		Config:  cfg,
+		Storage: storer,
+		Fs:      afero.NewOsFs(),
+		Stdout:  &out,
+		Stderr:  io.Discard,
+		UI:      ui.NewWithColor(io.Discard, false),
+	}
+	v.SetContext(ctx)
+
+	err := v.RunDeepVerify(snapshotID,
+		&vaultik.VerifyOptions{Deep: true, JSON: true})
+
+	return decodeVerifyResult(t, out.Bytes()), err
+}
+
 // corruptOneBlob flips a middle byte of the first blob file found under
 // blobsDir, leaving the file length unchanged.
 func corruptOneBlob(t *testing.T, fs afero.Fs, blobsDir string) {

internal/vaultik/fault_injection_test.go

@@ -661,18 +661,17 @@ func faultScannerFactory(
 ) snapshot.ScannerFactory {
 	return func(params snapshot.ScannerParams) *snapshot.Scanner {
 		return snapshot.NewScanner(snapshot.ScannerConfig{
-			FS:                 params.Fs,
+			FS:               params.Fs,
-			Storage:            storer,
+			Storage:          storer,
-			ChunkSize:          faultChunkSize,
+			ChunkSize:        faultChunkSize,
-			MaxBlobSize:        faultMaxBlobSize,
+			MaxBlobSize:      faultMaxBlobSize,
-			CompressionLevel:   cfg.CompressionLevel,
+			CompressionLevel: cfg.CompressionLevel,
-			AgeRecipients:      cfg.AgeRecipients,
+			AgeRecipients:    cfg.AgeRecipients,
-			Repositories:       repos,
+			Repositories:     repos,
-			EnableProgress:     params.EnableProgress,
+			EnableProgress:   params.EnableProgress,
-			UI:                 params.UI,
+			UI:               params.UI,
-			Exclude:            params.Exclude,
+			Exclude:          params.Exclude,
-			SkipErrors:         params.SkipErrors,
+			SkipErrors:       params.SkipErrors,
-			PreviousSnapshotID: params.PreviousSnapshotID,
 		})
 	}
 }

internal/vaultik/snapshot.go

@@ -243,18 +243,12 @@ func (v *Vaultik) createNamedSnapshot(
 		return err
 	}
 
-	previousSnapshotID, err := v.previousSnapshotID(snapName)
-	if err != nil {
-		return err
-	}
-
 	scanner := v.ScannerFactory(snapshot.ScannerParams{
-		EnableProgress:     !opts.Cron,
+		EnableProgress: !opts.Cron,
-		UI:                 v.UI,
+		UI:             v.UI,
-		Fs:                 v.Fs,
+		Fs:             v.Fs,
-		Exclude:            v.Config.GetExcludes(snapName),
+		Exclude:        v.Config.GetExcludes(snapName),
-		SkipErrors:         opts.SkipErrors,
+		SkipErrors:     opts.SkipErrors,
-		PreviousSnapshotID: previousSnapshotID,
 	})
 
 	snapshotID, err := v.SnapshotManager.CreateSnapshotWithName(
@@ -289,24 +283,6 @@ func (v *Vaultik) createNamedSnapshot(
 	return nil
 }
 
-// previousSnapshotID returns the ID of the most recent completed snapshot
-// named snapName in the local index, or "" when there is none.
-func (v *Vaultik) previousSnapshotID(snapName string) (string, error) {
-	snapshots, err := v.Repositories.Snapshots.ListRecent(v.ctx, listRecentLimit)
-	if err != nil {
-		return "", fmt.Errorf("listing snapshots: %w", err)
-	}
-
-	for _, s := range snapshots {
-		if s.CompletedAt != nil &&
-			parseSnapshotName(s.ID.String(), s.Hostname.String()) == snapName {
-			return s.ID.String(), nil
-		}
-	}
-
-	return "", nil
-}
-
 // resolveSnapshotPaths resolves source directories to absolute paths
 // with symlink resolution.
 func (v *Vaultik) resolveSnapshotPaths(snapName string) ([]string, error) {

internal/vaultik/snapshot_deleted_count_test.go

@@ -1,196 +0,0 @@
-package vaultik_test
-
-import (
-	"bytes"
-	"context"
-	"fmt"
-	"os"
-	"path/filepath"
-	"testing"
-	"time"
-
-	"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/304: a
-// backup counts a file as deleted only when the previous snapshot of
-// the same name had it and it is gone, and never counts an excluded
-// file.
-
-// deletedCountEnv is a backup setup over the source directory src whose
-// user-facing output is kept in out. Each test configures its snapshots
-// with setSnapshot.
-type deletedCountEnv struct {
-	v   *vaultik.Vaultik
-	out *bytes.Buffer
-	src string
-}
-
-// newDeletedCountEnv writes files, keyed by path relative to src.
-func newDeletedCountEnv(t *testing.T, files map[string][]byte) *deletedCountEnv {
-	t.Helper()
-
-	ctx := context.Background()
-	fs := afero.NewOsFs()
-	tempDir := t.TempDir()
-	srcDir := filepath.Join(tempDir, "src")
-
-	for rel, content := range files {
-		path := filepath.Join(srcDir, rel)
-		require.NoError(t, fs.MkdirAll(filepath.Dir(path), 0o755))
-		require.NoError(t, afero.WriteFile(fs, path, content, 0o644))
-	}
-
-	cfg := faultTestConfig()
-	cfg.IndexPath = filepath.Join(tempDir, "index.sqlite")
-	cfg.Snapshots = map[string]config.SnapshotConfig{}
-
-	store, err := storage.NewFileStorer(filepath.Join(tempDir, "remote"))
-	require.NoError(t, err)
-
-	db, err := database.New(ctx, cfg.IndexPath)
-	require.NoError(t, err)
-	t.Cleanup(func() { _ = db.Close() })
-
-	repos := database.NewRepositories(db)
-	out := &bytes.Buffer{}
-	v := newBackupVaultik(ctx, cfg, store, repos, db, fs)
-	v.UI = ui.NewWithColor(out, false)
-
-	return &deletedCountEnv{v: v, out: out, src: srcDir}
-}
-
-// setSnapshot configures the snapshot name to back up the path rel
-// beneath src, with the given excludes.
-func (e *deletedCountEnv) setSnapshot(name, rel string, exclude ...string) {
-	e.v.Config.Snapshots[name] = config.SnapshotConfig{
-		Paths:   []string{filepath.Join(e.src, rel)},
-		Exclude: exclude,
-	}
-}
-
-// backUp runs a backup of the named snapshot and returns its output.
-func (e *deletedCountEnv) backUp(t *testing.T, name string) string {
-	t.Helper()
-
-	e.out.Reset()
-	require.NoError(t, e.v.CreateSnapshot(&vaultik.SnapshotCreateOptions{
-		Snapshots: []string{name},
-	}))
-
-	return e.out.String()
-}
-
-// A file this snapshot excludes is not counted as deleted: neither one
-// that another snapshot backs up, nor one that the previous snapshot of
-// this name had before the exclude was added.
-func TestBackupDoesNotCountExcludedFileAsDeleted(t *testing.T) {
-	log.Initialize(log.Config{})
-	t.Parallel()
-
-	env := newDeletedCountEnv(t, map[string][]byte{
-		"top.txt":       []byte("top"),
-		"cache/tmp.bin": []byte("cache"),
-		"photos/a.jpg":  []byte("photo a"),
-		"photos/b.jpg":  []byte("photo b"),
-		"photos/c.jpg":  []byte("photo c"),
-	})
-	env.setSnapshot("photos", "photos")
-	env.setSnapshot("home", "", "/photos")
-
-	env.backUp(t, "photos")
-	assert.Contains(t, env.backUp(t, "home"), filesLine(2, 2, 0))
-
-	env.setSnapshot("home", "", "/photos", "/cache")
-	assert.Contains(t, env.backUp(t, "home"), filesLine(1, 0, 1))
-}
-
-// A file inside a directory that an exclude added after a backup
-// matches is not counted as deleted, though the pattern matches only the
-// directory.
-func TestBackupDoesNotCountFileInExcludedDirectoryAsDeleted(t *testing.T) {
-	log.Initialize(log.Config{})
-	t.Parallel()
-
-	env := newDeletedCountEnv(t, map[string][]byte{
-		"top.txt":                         []byte("top"),
-		"user/.local/share/Trash/old.txt": []byte("old"),
-	})
-	env.setSnapshot("home", "")
-
-	assert.Contains(t, env.backUp(t, "home"), filesLine(2, 2, 0))
-
-	env.setSnapshot("home", "", "*/.local/share/Trash")
-	assert.Contains(t, env.backUp(t, "home"), filesLine(1, 0, 1))
-}
-
-// A backup counts only files that the previous snapshot of its own name
-// had, not one that a later snapshot of another name over the same path
-// had and that is since removed.
-func TestBackupIgnoresSnapshotOfAnotherName(t *testing.T) {
-	log.Initialize(log.Config{})
-	t.Parallel()
-
-	env := newDeletedCountEnv(t, map[string][]byte{
-		"kept.txt": []byte("kept"),
-	})
-	env.setSnapshot("home", "")
-	env.setSnapshot("other", "")
-
-	env.backUp(t, "home")
-
-	// Snapshot start times are kept in whole seconds: wait so that other's
-	// snapshot is strictly the most recent.
-	time.Sleep(time.Second)
-
-	extra := filepath.Join(env.src, "extra.txt")
-	require.NoError(t, os.WriteFile(extra, []byte("extra"), 0o600))
-	env.backUp(t, "other")
-	require.NoError(t, os.Remove(extra))
-
-	assert.Contains(t, env.backUp(t, "home"), filesLine(1, 0, 1))
-}
-
-// A file removed from disk is counted as deleted by the next backup of
-// the snapshot that had it, and not by any later backup of that
-// snapshot, nor by the first backup of another name over the same path.
-func TestBackupCountsDeletedFileOnce(t *testing.T) {
-	log.Initialize(log.Config{})
-	t.Parallel()
-
-	aContent := bytes.Repeat([]byte("a"), 1000)
-	bContent := bytes.Repeat([]byte("b"), 2000)
-	keptContent := bytes.Repeat([]byte("k"), 500)
-
-	env := newDeletedCountEnv(t, map[string][]byte{
-		"a.txt":    aContent,
-		"b.txt":    bContent,
-		"kept.txt": keptContent,
-	})
-	env.setSnapshot("home", "")
-	env.setSnapshot("other", "")
-
-	assert.Contains(t, env.backUp(t, "home"), filesLine(3, 3, 0))
-
-	require.NoError(t, os.Remove(filepath.Join(env.src, "a.txt")))
-	require.NoError(t, os.Remove(filepath.Join(env.src, "b.txt")))
-
-	summary := env.backUp(t, "home")
-	assert.Contains(t, summary,
-		"Files: 1 examined, 0 backed up, 1 unchanged, 2 deleted.")
-	assert.Contains(t, summary,
-		fmt.Sprintf("Data: %s total (%s backed up), %s deleted.",
-			env.v.UI.Size(int64(len(keptContent))), env.v.UI.Size(0),
-			env.v.UI.Size(int64(len(aContent)+len(bContent)))))
-
-	assert.Contains(t, env.backUp(t, "home"), filesLine(1, 0, 1))
-	assert.Contains(t, env.backUp(t, "other"), filesLine(1, 0, 1))
-}

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
+}

internal/vaultik/verify.go

@@ -17,6 +17,7 @@ import (
 	"sneak.berlin/go/vaultik/internal/database"
 	"sneak.berlin/go/vaultik/internal/log"
 	"sneak.berlin/go/vaultik/internal/snapshot"
+	"sneak.berlin/go/vaultik/internal/storage"
 )
 
 // Sentinel errors for snapshot verification failures.
@@ -32,7 +33,9 @@ var (
 	errManifestExtraBlob   = errors.New("manifest contains blob not in database")
 	errManifestMissingBlob = errors.New(
 		"manifest omits blob present in database")
-	errBlobSizeMismatch = errors.New("blob size mismatch")
+	errBlobSizeMismatch  = errors.New("blob size mismatch")
+	errBlobsNotInStorage = errors.New(
+		"blobs missing from storage or stored with the wrong size")
 )
 
 // verifyStatusFailed is the JSON status value for a failed verification.
@@ -149,7 +152,6 @@ func (v *Vaultik) RunDeepVerify(snapshotID string, opts *VerifyOptions) error {
 	}
 
 	result.Status = "ok"
-	result.Verified = len(dbBlobs)
 
 	if opts.JSON {
 		return v.outputVerifyJSON(result)
@@ -306,7 +308,7 @@ func (v *Vaultik) runVerificationSteps(
 		v.stdoutf("Checking blob existence in remote storage...\n")
 	}
 
-	err = v.verifyBlobExistenceFromDB(dbBlobs)
+	err = v.verifyBlobExistenceFromDB(dbBlobs, result)
 	if err != nil {
 		return v.deepVerifyFailure(result, opts, err.Error(), err)
 	}
@@ -317,7 +319,8 @@ func (v *Vaultik) runVerificationSteps(
 			len(dbBlobs), ubytes(totalSize))
 	}
 
-	err = v.performDeepVerificationFromDB(dbBlobs, tdb.db.Conn(), opts, identities)
+	err = v.performDeepVerificationFromDB(
+		dbBlobs, tdb.db.Conn(), opts, result, identities)
 	if err != nil {
 		return v.deepVerifyFailure(result, opts, err.Error(), err)
 	}
@@ -669,8 +672,14 @@ func (v *Vaultik) verifyManifestAgainstDatabase(
 	return nil
 }
 
-// verifyBlobExistenceFromDB checks that all blobs from database exist in S3
+// verifyBlobExistenceFromDB checks that every blob from the database is
-func (v *Vaultik) verifyBlobExistenceFromDB(blobs []snapshot.BlobInfo) error {
+// in storage with the size the database records. It checks them all,
+// counting the missing and wrong-size blobs in result, and fails if it
+// found any. Any storage error other than not found stops the check and
+// fails with that error.
+func (v *Vaultik) verifyBlobExistenceFromDB(
+	blobs []snapshot.BlobInfo, result *VerifyResult,
+) error {
 	log.Info("Verifying blob existence in S3", "blob_count", len(blobs))
 
 	for i, blob := range blobs {
@@ -683,17 +692,23 @@ func (v *Vaultik) verifyBlobExistenceFromDB(blobs []snapshot.BlobInfo) error {
 		// Construct blob path
 		blobPath := fmt.Sprintf("blobs/%s/%s/%s", blob.Hash[:2], blob.Hash[2:4], blob.Hash)
 
-		// Check blob exists
 		stat, err := v.Storage.Stat(v.ctx, blobPath)
-		if err != nil {
+		switch {
-			return fmt.Errorf("blob %s missing from storage: %w", blob.Hash, err)
+		case errors.Is(err, storage.ErrNotFound):
-		}
+			log.Warn("Blob missing from storage", "hash", blob.Hash)
 
-		// Verify size matches
+			result.Missing++
-		if stat.Size != blob.CompressedSize {
+			result.MissingSize += blob.CompressedSize
-			return fmt.Errorf(
+		case err != nil:
-				"%w: blob %s: S3 has %d bytes, database has %d bytes",
+			return fmt.Errorf("checking blob %s in storage: %w",
-				errBlobSizeMismatch, blob.Hash, stat.Size, blob.CompressedSize)
+				blob.Hash, err)
+		case stat.Size != blob.CompressedSize:
+			log.Warn("Blob has the wrong size in storage",
+				"hash", blob.Hash,
+				"storage_size", stat.Size,
+				"database_size", blob.CompressedSize)
+
+			result.Mismatched++
 		}
 
 		// Progress update every 100 blobs
@@ -707,16 +722,22 @@ func (v *Vaultik) verifyBlobExistenceFromDB(blobs []snapshot.BlobInfo) error {
 		}
 	}
 
+	if result.Missing > 0 || result.Mismatched > 0 {
+		return fmt.Errorf("%w: %d missing, %d with the wrong size",
+			errBlobsNotInStorage, result.Missing, result.Mismatched)
+	}
+
 	log.Info("✓ All blobs exist in storage")
 
 	return nil
 }
 
 // performDeepVerificationFromDB downloads and verifies the content of
-// each blob using the database as source.
+// each blob using the database as source, stopping at the first blob that
+// fails. Each blob that passes is counted in result.Verified.
 func (v *Vaultik) performDeepVerificationFromDB(
 	blobs []snapshot.BlobInfo, db *sql.DB, opts *VerifyOptions,
-	identities []age.Identity,
+	result *VerifyResult, identities []age.Identity,
 ) error {
 	// Calculate total bytes for ETA
 	var totalBytesExpected int64
@@ -739,6 +760,7 @@ func (v *Vaultik) performDeepVerificationFromDB(
 			return fmt.Errorf("blob %s verification failed: %w", blobInfo.Hash, err)
 		}
 
+		result.Verified++
 		bytesProcessed += blobInfo.CompressedSize
 		elapsed := time.Since(startTime)
 		remaining := len(blobs) - (i + 1)