Author SHA1 Message Date
sneak 437ec591ad Refuse a relative file:// storage_url and decode its escapes (closes #299)
check / check (push) Waiting to run
The path after file:// was used as written. file://dest resolved
against the working directory, so a backup run from another directory
wrote elsewhere, exited 0 and left a snapshot that could not be
restored; my%20stick created a directory with that literal name.

Config load now refuses a file:// storage_url whose path is not
absolute. ParseStorageURL refuses it too and decodes percent-escapes;
a literal space still works. The rule is written in both packages
because config cannot import storage, which imports config.

A % not followed by two hex digits now fails when the storage is
opened, not at config load.

Model: opus-5-5
2026-10-13 04:02:59 +00:00
9 changed files with 114 additions and 207 deletions
+5 -4
View File
@@ -370,9 +370,7 @@ 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 file's chunk hashes match
@@ -431,7 +429,10 @@ object store. Credentials are read from `s3.access_key_id` and
`s3.secret_access_key` in the config file.
**Local filesystem** (`file:///path/to/backup`): Stores blobs and metadata on
a local or mounted filesystem. Useful for testing or backing up to a NAS.
a local or mounted filesystem. Useful for testing or backing up to a NAS. The
path must be absolute; a relative one is refused when the config loads.
Percent-escapes in the path are decoded, so `my%20stick` and `my stick` name
the same directory.
**Rclone** (`rclone://remote/path`): Uses rclone's 70+ supported cloud
providers. Requires rclone to be configured separately (`rclone config`).
+11
View File
@@ -22,6 +22,17 @@ the tag exists and is exercised; what is left is merging `next` to
# Completed Steps
- 2026-10-13: Refused a `file://` `storage_url` whose path is relative
([issue #299](https://git.eeqj.de/sneak/vaultik/issues/299)). The text
after `file://` was used as written, so `file://dest` resolved against
the working directory: a backup run from another directory wrote to a
different destination, still exited 0, and left a snapshot that could
not be restored. Such a URL now fails when the config loads, with an
error asking for an absolute path. Percent-escapes in the path are now
decoded, so `my%20stick` names the directory `my stick` instead of
creating one named `my%20stick`; a path written with a literal space
works as before.
- 2026-10-13: Made `snapshot remove` fail for a snapshot that does not
exist ([issue #293](https://git.eeqj.de/sneak/vaultik/issues/293)).
The command never checked the ID: it reported the snapshot removed
-2
View File
@@ -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
+12 -2
View File
@@ -61,6 +61,9 @@ var (
errBadS3PartSize = errors.New("s3.part_size must be between 5MiB and 5GiB")
errBadStorageScheme = errors.New(
"storage_url must start with s3://, file://, or rclone://")
errFileURLNotAbsolute = errors.New(
"a file:// storage_url needs an absolute path, " +
"as in file:///path/to/backup")
errStorageNotConfigured = errors.New(
"storage not configured; set storage_url or provide s3.endpoint + " +
"s3.bucket + credentials")
@@ -461,11 +464,18 @@ func (c *Config) validateStorage() error {
// validateStorageURL validates URL-based storage configuration. File and
// rclone URLs need no credentials; S3 URLs require the legacy s3.*
// credential fields.
// credential fields. A file URL must name an absolute path: a relative one
// would resolve against the working directory, so the destination would
// move with it.
func (c *Config) validateStorageURL() error {
switch {
case strings.HasPrefix(c.StorageURL, "file://"):
// File storage doesn't need S3 credentials
// storage.ParseStorageURL applies the same rule, but config
// cannot import storage, which imports config.
if !strings.HasPrefix(c.StorageURL, "file:///") {
return errFileURLNotAbsolute
}
return nil
case strings.HasPrefix(c.StorageURL, "rclone://"):
// Rclone storage uses rclone's own config
+29
View File
@@ -337,6 +337,35 @@ func TestLoadS3PartSize(t *testing.T) {
})
}
// TestLoadRejectsRelativeFileURL checks that a file:// storage_url with a
// relative path fails at load. Accepted, it would resolve against the
// working directory, so a backup run from another directory would write
// to a different destination and still succeed.
func TestLoadRejectsRelativeFileURL(t *testing.T) {
t.Parallel()
const relativeConfig = "snapshots:\n" +
" test:\n" +
" paths: [/tmp/vaultik-test-source]\n" +
"storage_url: file://dest\n"
path := filepath.Join(t.TempDir(), "config.yml")
err := os.WriteFile(path, []byte(relativeConfig), 0o600)
if err != nil {
t.Fatalf("write config: %v", err)
}
_, err = Load(path)
if !errors.Is(err, errFileURLNotAbsolute) {
t.Fatalf("Load() error = %v, want errFileURLNotAbsolute", err)
}
if !strings.Contains(err.Error(), "absolute path") {
t.Errorf("error %q does not say to use an absolute path", err.Error())
}
}
// TestValidateAgeRecipients checks that recipients are parsed at config load
// (a bad entry fails immediately, not mid-backup) and that no invalid entry —
// least of all a pasted secret key — is echoed in the error. An empty list
+26 -12
View File
@@ -17,8 +17,10 @@ const (
// Sentinel errors for storage URL parsing.
var (
ErrEmptyStorageURL = errors.New("storage URL is empty")
ErrEmptyFilePath = errors.New("file URL path is empty")
ErrEmptyStorageURL = errors.New("storage URL is empty")
ErrEmptyFilePath = errors.New("file URL path is empty")
ErrRelativeFilePath = errors.New(
"file URL needs an absolute path, as in file:///path/to/backup")
ErrMissingBucket = errors.New("s3 URL missing bucket name")
ErrMissingRemote = errors.New("rclone URL missing remote name")
ErrUnsupportedScheme = errors.New(
@@ -51,17 +53,8 @@ func ParseStorageURL(rawURL string) (*URL, error) {
return nil, ErrEmptyStorageURL
}
// Handle file:// URLs
if after, ok := strings.CutPrefix(rawURL, "file://"); ok {
path := after
if path == "" {
return nil, ErrEmptyFilePath
}
return &URL{
Scheme: schemeFile,
Prefix: path,
}, nil
return parseFileURL(after)
}
if strings.HasPrefix(rawURL, "s3://") {
@@ -75,6 +68,27 @@ func ParseStorageURL(rawURL string) (*URL, error) {
return nil, ErrUnsupportedScheme
}
// parseFileURL parses the path that follows file://. The path must be
// absolute: a relative one would resolve against the working directory,
// so the destination would move with it. Percent-escapes are decoded, so
// my%20stick names the directory "my stick"; a literal space is kept.
func parseFileURL(rawPath string) (*URL, error) {
if rawPath == "" {
return nil, ErrEmptyFilePath
}
if !strings.HasPrefix(rawPath, "/") {
return nil, ErrRelativeFilePath
}
path, err := url.PathUnescape(rawPath)
if err != nil {
return nil, fmt.Errorf("invalid file URL path: %w", err)
}
return &URL{Scheme: schemeFile, Prefix: path}, nil
}
// parseS3URL parses an s3://bucket/prefix URL. It rejects credentials in
// the userinfo and any query parameter other than endpoint, region and
// ssl, so a credential-bearing URL is never stored or echoed.
+16 -2
View File
@@ -14,7 +14,10 @@ import (
func TestParseStorageURLValid(t *testing.T) {
t.Parallel()
const bucket = "mybucket"
const (
bucket = "mybucket"
fileScheme = "file"
)
cases := []struct {
name string
@@ -24,7 +27,17 @@ func TestParseStorageURLValid(t *testing.T) {
{
name: "file absolute path",
raw: "file:///var/backups/vaultik",
want: &storage.URL{Scheme: "file", Prefix: "/var/backups/vaultik"},
want: &storage.URL{Scheme: fileScheme, Prefix: "/var/backups/vaultik"},
},
{
name: "file percent-escaped path is decoded",
raw: "file:///Volumes/my%20stick/backup",
want: &storage.URL{Scheme: fileScheme, Prefix: "/Volumes/my stick/backup"},
},
{
name: "file path with a literal space",
raw: "file:///Volumes/my stick/backup",
want: &storage.URL{Scheme: fileScheme, Prefix: "/Volumes/my stick/backup"},
},
{
name: "s3 bucket and prefix, ssl defaults on",
@@ -90,6 +103,7 @@ func TestParseStorageURLErrors(t *testing.T) {
}{
{"empty url", "", storage.ErrEmptyStorageURL},
{"file empty path", "file://", storage.ErrEmptyFilePath},
{"file relative path", "file://dest", storage.ErrRelativeFilePath},
{"s3 missing bucket", "s3://", storage.ErrMissingBucket},
{"s3 missing bucket with path", "s3:///justprefix", storage.ErrMissingBucket},
{"rclone missing remote", "rclone://", storage.ErrMissingRemote},
+15 -43
View File
@@ -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" +
@@ -150,7 +149,7 @@ 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)
}
@@ -159,7 +158,7 @@ func (v *Vaultik) Restore(opts *RestoreOptions) error {
log.Warn("No files found to restore")
v.UI.Warningf("No files found to restore.")
return v.reportUnmatchedPaths(unmatched)
return nil
}
log.Info("Found files to restore", "count", len(files))
@@ -199,16 +198,14 @@ func (v *Vaultik) Restore(opts *RestoreOptions) error {
v.UI.Duration(result.Duration),
)
return v.finishRestore(repos, files, unmatched, opts, result)
return v.finishRestore(repos, files, opts, result)
}
// finishRestore emits the post-restore warnings, runs optional
// verification, and converts any failed-file count or requested path
// that matched nothing into an error.
// verification, and converts any failed-file count into an error.
func (v *Vaultik) finishRestore(
repos *database.Repositories,
files []*database.File,
unmatched []string,
opts *RestoreOptions,
result *RestoreResult,
) error {
@@ -226,8 +223,6 @@ func (v *Vaultik) finishRestore(
}
}
unmatchedErr := v.reportUnmatchedPaths(unmatched)
// Run verification if requested
if opts.Verify {
err := v.handleRestoreVerification(repos, files, opts, result)
@@ -240,23 +235,7 @@ 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
@@ -833,34 +812,27 @@ 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 {
@@ -871,7 +843,7 @@ func (v *Vaultik) getFilesToRestore(
}
}
return result, unmatched, nil
return result, nil
}
// buildChunkToBlobMap creates a mapping from chunk hash to blob information
@@ -1,142 +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/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")
}