Make **/ in an exclude pattern match zero directories (closes #338)

The glob library needs a slash on both sides of **, so the anchored
pattern /**/x missed an x directly under the snapshot path, and
a/**/*.log missed a/x.log. As in gitignore, a leading **/ now makes any
pattern, anchored or not, match at every depth, and a pattern holding
/**/ is also compiled with each /**/ made a single slash. The library's
{a,b} alternatives cannot express this: with ** inside them in
mid-pattern they miss paths they should match.

Judgement call: the test for a/**/b uses a/**/*.log, because with a
plain name after the ** the glob library already matched a/b.

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/snapshot/exclude_test.go

@@ -578,3 +578,54 @@ func TestExcludePatterns_DoubleStarFileAtEveryDepth(t *testing.T) {
 	require.Equal(t, 1, result.FilesScanned,
 		"**/ file pattern should match at the top level and nested")
 }
+
+func TestExcludePatterns_AnchoredDoubleStarAtEveryDepth(t *testing.T) {
+	t.Parallel()
+
+	// As in gitignore, /**/ also matches directly under the source dir
+	fs := setupAnchoredTestFS(t)
+
+	scanner, repos, cleanup := createTestScanner(t, fs, []string{"/**/projectname"})
+	defer cleanup()
+
+	ctx := context.Background()
+	createSnapshotRecord(ctx, t, repos, "test-snapshot")
+
+	result, err := scanner.Scan(ctx, "/backup", "test-snapshot")
+	require.NoError(t, err)
+
+	// /**/projectname should exclude BOTH:
+	// - /backup/projectname/file.txt
+	// - /backup/otherproject/projectname/file.txt
+	// Total files: 4, excluded: 2
+	require.Equal(t, 2, result.FilesScanned,
+		"/**/ pattern should match at the top level and nested")
+}
+
+func TestExcludePatterns_DoubleStarInMiddleMatchesZeroDirectories(t *testing.T) {
+	t.Parallel()
+
+	// As in gitignore, a/**/b matches a/b as well as a/c/b. The last part
+	// is a glob: with a plain name the glob library already matched a/b.
+	fs := &afero.MemMapFs{}
+	files := []string{"/backup/a/x.log", "/backup/a/c/y.log", "/backup/a/c/kept.txt"}
+
+	for _, path := range files {
+		require.NoError(t, fs.MkdirAll(filepath.Dir(path), 0755))
+		require.NoError(t, afero.WriteFile(fs, path, []byte(path), 0644))
+	}
+
+	scanner, repos, cleanup := createTestScanner(t, fs, []string{"a/**/*.log"})
+	defer cleanup()
+
+	ctx := context.Background()
+	createSnapshotRecord(ctx, t, repos, "test-snapshot")
+
+	result, err := scanner.Scan(ctx, "/backup", "test-snapshot")
+	require.NoError(t, err)
+
+	// a/**/*.log should exclude /backup/a/x.log and /backup/a/c/y.log
+	// Total files: 3, excluded: 2
+	require.Equal(t, 1, result.FilesScanned,
+		"a/**/*.log should match a/x.log as well as a/c/y.log")
+}

internal/snapshot/scanner.go

@@ -2035,33 +2035,60 @@ func compileExcludePatterns(patterns []string) []compiledPattern {
 		pattern = strings.TrimSuffix(pattern, "/")
 
 		// A leading "**/" demands a "/" before the name and so misses an
-		// entry directly under the source path. An unanchored pattern
-		// already matches at every depth, so drop the prefix: as in
-		// gitignore, "**/x" then also matches a top-level "x".
-		if !anchored {
-			pattern = strings.TrimPrefix(pattern, "**/")
+		// entry directly under the source path. It means "at every depth",
+		// which is what an unanchored pattern already does, so drop the
+		// prefix and match unanchored: as in gitignore, "**/x" and
+		// "/**/x" then also match a top-level "x".
+		if rest, found := strings.CutPrefix(pattern, "**/"); found {
+			pattern = rest
+			anchored = false
 		}
 
-		// Compile the glob pattern
-		// For patterns without path separators, we need to match them as components
-		// e.g., ".git" should match ".git" anywhere in the path
-		g, err := glob.Compile(pattern, '/')
-		if err != nil {
-			log.Warn("Invalid exclude pattern, skipping", "pattern", p, "error", err)
+		// Likewise "/**/" inside a pattern demands two slashes, so
+		// "a/**/*.log" misses "a/x.log". As in gitignore it stands for
+		// zero or more directories, so also compile the pattern with it
+		// made a single "/". The glob library's {a,b} is no help: with a
+		// "**" inside it in mid-pattern, it misses paths it should match.
+		for _, variant := range doubleStarVariants(pattern) {
+			// For patterns without path separators, we need to match them as components
+			// e.g., ".git" should match ".git" anywhere in the path
+			g, err := glob.Compile(variant, '/')
+			if err != nil {
+				log.Warn("Invalid exclude pattern, skipping", "pattern", p, "error", err)
 
-			continue
+				break
+			}
+
+			compiled = append(compiled, compiledPattern{
+				pattern:  g,
+				anchored: anchored,
+				original: p,
+			})
 		}
-
-		compiled = append(compiled, compiledPattern{
-			pattern:  g,
-			anchored: anchored,
-			original: p,
-		})
 	}
 
 	return compiled
 }
 
+// doubleStarVariants returns pattern once for every way of keeping each
+// "/**/" in it or making it a single "/".
+func doubleStarVariants(pattern string) []string {
+	const doubleStar = "/**/"
+
+	before, after, found := strings.Cut(pattern, doubleStar)
+	if !found {
+		return []string{pattern}
+	}
+
+	var variants []string
+
+	for _, rest := range doubleStarVariants(after) {
+		variants = append(variants, before+doubleStar+rest, before+"/"+rest)
+	}
+
+	return variants
+}
+
 // shouldExclude checks if a path should be excluded based on exclude patterns
 // filePath is the full path to the file
 // rootPath is the root of the backup source directory

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")
-}