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 as soon as the list
of files to restore is built, so the names show even when the restore
then stops on an error, 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 fail to restore or the restore stops on an
error, that error is the one returned.
The restore summary moved into finishRestore to keep Restore within
the function length limit.

Model: opus-5-5

README.md

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

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/storage/url.go

@@ -30,12 +30,6 @@ 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.
@@ -96,9 +90,8 @@ func parseFileURL(rawPath string) (*URL, error) {
 }
 
 // parseS3URL parses an s3://bucket/prefix URL. It rejects credentials in
-// the userinfo or in the endpoint parameter's userinfo, a query that
+// the userinfo and any query parameter other than endpoint, region and
-// cannot be decoded, and any query parameter other than endpoint, region
+// ssl, so a credential-bearing URL is never stored or echoed.
-// 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 {
@@ -114,26 +107,13 @@ func parseS3URL(rawURL string) (*URL, error) {
 		return nil, ErrMissingBucket
 	}
 
-	// u.Query() would silently drop a part it cannot decode, endpoint
+	query := u.Query()
-	// 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,
@@ -145,23 +125,9 @@ func parseS3URL(rawURL string) (*URL, error) {
 }
 
 // parseRcloneURL parses an rclone://remote/path URL. rclone:// takes no
-// query parameters, so credentials in the userinfo, parameters in the
+// query parameters, so credentials in the userinfo and any parameter at
-// remote name and any query parameter at all are rejected rather than
+// all are rejected rather than silently ignored.
-// 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)
@@ -171,7 +137,7 @@ 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

@@ -150,19 +150,6 @@ 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,
@@ -216,104 +203,6 @@ 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/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" +
@@ -150,16 +151,20 @@ 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)
 	}
 
+	// 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 nil
+		return unmatchedErr
 	}
 
 	log.Info("Found files to restore", "count", len(files))
@@ -185,6 +190,20 @@ 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),
@@ -199,17 +218,6 @@ func (v *Vaultik) Restore(opts *RestoreOptions) error {
 		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 " +
@@ -236,7 +244,23 @@ 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
@@ -840,27 +864,34 @@ func (v *Vaultik) materializeSnapshotDB(
 	return db, tempDir, nil
 }
 
-// getFilesToRestore returns the list of files to restore based on path filters
+// getFilesToRestore returns the list of files to restore based on path
+// filters, and the filters, as given, that matched no file.
 func (v *Vaultik) getFilesToRestore(
 	ctx context.Context, repos *database.Repositories, pathFilters []string,
-) ([]*database.File, error) {
+) ([]*database.File, []string, error) {
 	// If no filters, get all files
 	if len(pathFilters) == 0 {
-		return repos.Files.ListAll(ctx)
+		files, err := repos.Files.ListAll(ctx)
+
+		return files, nil, err
 	}
 
 	// Get files matching the path filters
-	var result []*database.File
+	var (
+		result    []*database.File
+		unmatched []string
+	)
 
 	seen := make(map[string]bool)
 
 	for _, filter := range pathFilters {
-		// Normalize the filter path
+		files, err := repos.Files.ListUnderPath(ctx, filepath.Clean(filter))
-		filter = filepath.Clean(filter)
-
-		files, err := repos.Files.ListUnderPath(ctx, filter)
 		if err != nil {
-			return nil, fmt.Errorf("listing files under %s: %w", filter, err)
+			return nil, nil, fmt.Errorf("listing files under %s: %w", filter, err)
+		}
+
+		if len(files) == 0 {
+			unmatched = append(unmatched, filter)
 		}
 
 		for _, file := range files {
@@ -871,7 +902,7 @@ 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 +1,202 @@
+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")
+}