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

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

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

Model: opus-5-5

README.md

@@ -286,7 +286,9 @@ needed.
   remove orphaned blobs from remote storage. By default keeps only the latest
   snapshot per name; use `--keep-newer-than` for a rolling window.
 * `--keep-newer-than <duration>`: With `--prune`, keep snapshots newer than
-  this duration instead of only the latest (e.g. `4w`, `30d`, `6mo`, `1y`)
+  this duration instead of only the latest (e.g. `4w`, `30d`, `6mo`, `1y`).
+  Without `--prune`, or with a value that is not a valid duration, the
+  command fails before the backup starts.
 
 **`snapshot list`**: Show every snapshot known to this host — the union
 of the local index and the backup destination store — with timestamps
@@ -370,7 +372,9 @@ on the destination in one go, use `vaultik remote nuke --force`.
   store — its remote key (or an unambiguous leading part of it) as shown
   by `snapshot list`. See
   [restoring on another machine](#restoring-on-another-machine).
-* Optional path arguments to restore specific files/directories (default: all)
+* Optional path arguments to restore specific files/directories (default: all).
+  A path that matches nothing in the snapshot is named in a warning, and the
+  command exits non-zero after restoring the paths that match
 * Preserves file permissions, timestamps, ownership (ownership requires root),
   symlinks, and empty directories
 * `--verify`: After restoring, verify every file's chunk hashes match

internal/cli/entry_snapshot_create_prune_test.go

@@ -0,0 +1,108 @@
+package cli //nolint:testpackage // shares runEntry and the hermetic config helpers
+
+import (
+	"os"
+	"path/filepath"
+	"strings"
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+)
+
+// Flags of `snapshot create` used to build argument vectors below.
+const (
+	flagPrune         = "--prune"
+	flagKeepNewerThan = "--keep-newer-than"
+)
+
+// TestEntrySnapshotCreateRejectsKeepNewerThanBeforeBackup checks that a
+// --keep-newer-than the post-backup prune could not use stops `snapshot
+// create` before the backup: the command fails and the destination
+// store stays empty. It used to be read only by the prune, after the
+// snapshot was uploaded, and without --prune it was ignored.
+//
+//nolint:paralleltest // replaces os.Args, os.Stdout, os.Stderr and the xdg globals
+func TestEntrySnapshotCreateRejectsKeepNewerThanBeforeBackup(t *testing.T) {
+	for _, testCase := range []struct {
+		name string
+		args []string
+	}{
+		{
+			name: "decimal in a day count",
+			args: []string{flagPrune, flagKeepNewerThan, "1.5d"},
+		},
+		{
+			name: "unknown unit",
+			args: []string{flagPrune, flagKeepNewerThan, "4x"},
+		},
+		{
+			name: "without --prune",
+			args: []string{flagKeepNewerThan, "4w"},
+		},
+	} {
+		t.Run(testCase.name, func(t *testing.T) {
+			configPath, storeDir := writeBackupConfig(t)
+
+			code, _, _ := runEntry(t, append(
+				[]string{flagConfig, configPath, cmdSnapshot, cmdCreate},
+				testCase.args...)...)
+
+			assert.Equal(t, 1, code)
+
+			stored, err := os.ReadDir(storeDir)
+			require.NoError(t, err)
+			assert.Empty(t, stored, "nothing may be uploaded")
+		})
+	}
+}
+
+// TestEntrySnapshotCreateReportsPostBackupPruneFailure makes the
+// post-backup prune fail after a good backup, by planting a manifest
+// that cannot be decoded, and checks that the failure is reported as the
+// prune's and not as a failed snapshot creation.
+//
+//nolint:paralleltest // replaces os.Args, os.Stdout, os.Stderr and the xdg globals
+func TestEntrySnapshotCreateReportsPostBackupPruneFailure(t *testing.T) {
+	configPath, storeDir := writeBackupConfig(t)
+
+	// A remote key is 64 lowercase hex characters. The prune reads every
+	// manifest on the store and fails on one it cannot decode.
+	plantedDir := filepath.Join(storeDir, "metadata", strings.Repeat("a", 64))
+	require.NoError(t, os.MkdirAll(plantedDir, 0o750))
+	require.NoError(t, os.WriteFile(
+		filepath.Join(plantedDir, "manifest.json.zst"),
+		[]byte("not a valid manifest"), 0o600))
+
+	code, _, stderr := runEntry(t,
+		flagConfig, configPath, cmdSnapshot, cmdCreate, flagPrune)
+
+	assert.Equal(t, 1, code)
+	assert.Contains(t, stderr, "Backup completed, but post-backup prune failed")
+	assert.NotContains(t, stderr, "Snapshot creation failed")
+
+	snapshots, err := os.ReadDir(filepath.Join(storeDir, "metadata"))
+	require.NoError(t, err)
+	assert.Len(t, snapshots, 2,
+		"the new snapshot is on the store beside the planted one")
+}
+
+// writeBackupConfig builds a hermetic config with one small file in its
+// source directory and an empty destination store directory. Returns the
+// config path and the store directory.
+func writeBackupConfig(t *testing.T) (string, string) {
+	t.Helper()
+
+	configPath := writeHermeticPruneConfig(t, false)
+
+	// writeHermeticPruneConfig puts the source and store directories
+	// beside the config file.
+	dir := filepath.Dir(configPath)
+	sourceDir := filepath.Join(dir, "source")
+
+	require.NoError(t, os.Mkdir(sourceDir, 0o750))
+	require.NoError(t, os.WriteFile(
+		filepath.Join(sourceDir, "file.txt"), []byte("hello"), 0o600))
+
+	return configPath, filepath.Join(dir, "store")
+}

internal/cli/snapshot.go

@@ -71,6 +71,11 @@ otherwise from the platform config directory (~/.config/vaultik/config.yml
 on Linux), then /etc/vaultik/config.yml.`,
 		Args: cobra.ArbitraryArgs,
 		RunE: func(cmd *cobra.Command, args []string) error {
+			err := opts.Validate()
+			if err != nil {
+				return err
+			}
+
 			// Pass snapshot names from args
 			opts.Snapshots = args
 			// --skip-errors is a global flag on the root command.
@@ -97,6 +102,13 @@ on Linux), then /etc/vaultik/config.yml.`,
 			}, func(v *vaultik.Vaultik) error {
 				return v.CreateSnapshot(opts)
 			}, func(err error) {
+				if errors.Is(err, vaultik.ErrPostBackupPruneFailed) {
+					log.Error("Post-backup prune failed", "error", err)
+					ReportErrorf("Backup completed, but %v", err)
+
+					return
+				}
+
 				log.Error("Snapshot creation failed", "error", err)
 				ReportErrorf("Snapshot creation failed: %v", err)
 			})

internal/cli/snapshot_restore.go

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

internal/vaultik/restore.go

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

internal/vaultik/restore_unmatched_path_test.go

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

internal/vaultik/snapshot.go

@@ -28,8 +28,14 @@ var (
 	errNoAgeRecipients      = errors.New(
 		"creating a snapshot needs at least one public key in " +
 			"age_recipients (generate a keypair with: age-keygen)")
+	errKeepNewerThanNeedsPrune = errors.New("--keep-newer-than requires --prune")
 )
 
+// ErrPostBackupPruneFailed wraps a failure of the post-backup prune,
+// which runs only after every snapshot was created and uploaded, so the
+// caller can report it apart from a failed backup.
+var ErrPostBackupPruneFailed = errors.New("post-backup prune failed")
+
 // listRecentLimit caps how many snapshot rows are fetched from the
 // local index for listing and purge operations.
 const listRecentLimit = 10000
@@ -45,6 +51,26 @@ type SnapshotCreateOptions struct {
 	Snapshots     []string // Optional list of snapshot names to process (empty = all)
 }
 
+// Validate fails when KeepNewerThan is set without Prune or is not a
+// valid duration. Only the post-backup prune reads KeepNewerThan, after
+// the backup, so the caller checks it before starting one.
+func (opts *SnapshotCreateOptions) Validate() error {
+	if opts.KeepNewerThan == "" {
+		return nil
+	}
+
+	if !opts.Prune {
+		return errKeepNewerThanNeedsPrune
+	}
+
+	_, err := parseDuration(opts.KeepNewerThan)
+	if err != nil {
+		return fmt.Errorf("--keep-newer-than: %w", err)
+	}
+
+	return nil
+}
+
 // CreateSnapshot executes the snapshot creation operation
 func (v *Vaultik) CreateSnapshot(opts *SnapshotCreateOptions) error {
 	// config.Load accepts an empty list, since listing, verifying and
@@ -123,7 +149,7 @@ func (v *Vaultik) CreateSnapshot(opts *SnapshotCreateOptions) error {
 	if opts.Prune {
 		err = v.runPostBackupPrune(snapshotNames, opts.KeepNewerThan)
 		if err != nil {
-			return fmt.Errorf("post-backup prune: %w", err)
+			return fmt.Errorf("%w: %w", ErrPostBackupPruneFailed, err)
 		}
 	}