1 Commits
Author SHA1 Message Date
sneak d85eabd242 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 02:56:16 +00:00
9 changed files with 133 additions and 242 deletions
+7 -6
View File
@@ -349,11 +349,9 @@ the backup destination store. Blobs are NOT touched — deleting blobs
requires reading every remaining remote manifest (the destination store
may hold snapshots this host doesn't know about), which is what
`vaultik prune` does. On success the command prints the exact `vaultik
prune` invocation to run as a follow-up. An ID that names no snapshot in
the local index or on the destination store is an error; with
`--local-only`, the snapshot must be in the local index. Local row
cleanup (files, chunks, blobs the snapshot was the last referrer for)
runs automatically. If the destination store is unreachable, the local-DB
prune` invocation to run as a follow-up. Local row cleanup (files,
chunks, blobs the snapshot was the last referrer for) runs
automatically. If the destination store is unreachable, the local-DB
removal still completes and a warning is emitted; run `vaultik snapshot
remove <snapshot-id>` again once the store is reachable to remove the
snapshot's metadata from it (`vaultik prune` does not). To wipe everything
@@ -429,7 +427,10 @@ 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`).
+10 -9
View File
@@ -22,15 +22,16 @@ the tag exists and is exercised; what is left is merging `next` to
# Completed Steps
- 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
from the local database and from the destination store and exited 0,
under `--json`, `--dry-run` and `--local-only` too. An ID that names
no snapshot in the local index or on the destination store is now an
error; with `--local-only`, the snapshot must be in the local index.
The command now reports a removal from either side only when one
happened, and `remote_removed` is true only when metadata was deleted.
- 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.
- 2026-10-12: Bound the local index to the destination an `s3.*` config
names ([issue #298](https://git.eeqj.de/sneak/vaultik/issues/298)).
+1 -5
View File
@@ -255,12 +255,8 @@ manifest (the destination store may hold snapshots this host doesn't
know about), which is what 'vaultik prune' does. On success the command
prints the exact 'vaultik prune' invocation to run as a follow-up.
An ID that names no snapshot in the local index or on the destination
store is an error.
Use --local-only to skip the remote half (e.g. when you want to forget a
snapshot locally without touching the destination store); the snapshot
must then be in the local index.
snapshot locally without touching the destination store).
If the remote is unreachable, the local-database removal still completes
and a warning is emitted; run 'vaultik snapshot remove <snapshot-id>' again
+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},
-115
View File
@@ -3,21 +3,17 @@ package vaultik_test
import (
"bytes"
"context"
"database/sql"
"io"
"strings"
"sync"
"testing"
"time"
"github.com/klauspost/compress/zstd"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
"sneak.berlin/go/vaultik/internal/database"
"sneak.berlin/go/vaultik/internal/log"
"sneak.berlin/go/vaultik/internal/snapshot"
"sneak.berlin/go/vaultik/internal/storage"
"sneak.berlin/go/vaultik/internal/types"
"sneak.berlin/go/vaultik/internal/vaultik"
)
@@ -218,37 +214,6 @@ func addBlob(t *testing.T, store *testStorer, hash string) {
require.NoError(t, err)
}
// newLocalIndex returns an in-memory local index holding a completed
// snapshot row for each of ids.
func newLocalIndex(t *testing.T, ids ...string) *database.Repositories {
t.Helper()
ctx := context.Background()
db, err := database.New(ctx, ":memory:")
require.NoError(t, err)
t.Cleanup(func() { _ = db.Close() })
repos := database.NewRepositories(db)
for _, id := range ids {
completedAt := time.Now().UTC()
snap := &database.Snapshot{
ID: types.SnapshotID(id),
Hostname: snapHostname,
StartedAt: completedAt,
CompletedAt: &completedAt,
}
err = repos.WithTx(ctx, func(ctx context.Context, tx *sql.Tx) error {
return repos.Snapshots.Create(ctx, tx, snap)
})
require.NoError(t, err)
}
return repos
}
// ============================================================================
// Unit Tests for RemoveSnapshot
// ============================================================================
@@ -268,7 +233,6 @@ func TestRemoveSnapshot_LocalOnly_PreservesRemote(t *testing.T) {
addBlob(t, store, blobA)
tv := vaultik.NewForTesting(store)
tv.Repositories = newLocalIndex(t, "snapshot-001")
opts := &vaultik.RemoveOptions{Force: true, LocalOnly: true}
result, err := tv.RemoveSnapshot("snapshot-001", opts)
@@ -304,7 +268,6 @@ func TestRemoveSnapshot_DefaultRemovesMetadataNotBlobs(t *testing.T) {
addBlob(t, store, blobShared)
tv := vaultik.NewForTesting(store)
tv.Repositories = newLocalIndex(t, "snapshot-001", "snapshot-002")
opts := &vaultik.RemoveOptions{Force: true}
result, err := tv.RemoveSnapshot("snapshot-001", opts)
@@ -353,84 +316,6 @@ func TestRemoveSnapshot_DryRun(t *testing.T) {
assert.Contains(t, tv.Stdout.String(), "[Dry run - no changes made]")
}
// TestRemoveSnapshot_UnknownIDIsError checks that an ID naming no
// snapshot in the local index or on the destination store is an error
// under every option, and that nothing is reported as removed.
func TestRemoveSnapshot_UnknownIDIsError(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
for name, opts := range map[string]vaultik.RemoveOptions{
"force": {Force: true},
"json": {JSON: true},
"dry-run": {Force: true, DryRun: true},
"local-only": {Force: true, LocalOnly: true},
} {
t.Run(name, func(t *testing.T) {
t.Parallel()
store := newTestStorer()
addManifest(t, store, "snapshot-001", nil)
tv := vaultik.NewForTesting(store)
tv.Repositories = newLocalIndex(t, "snapshot-001")
result, err := tv.RemoveSnapshot("snapshot-999", &opts)
require.ErrorContains(t, err, "snapshot not found")
assert.False(t, result.RemoteRemoved)
assert.Empty(t, tv.Stdout.String())
assert.True(t, store.hasKey(remoteKeyPath("snapshot-001")))
})
}
}
// TestRemoveSnapshot_NoMetadataOnDestination checks that removing a
// snapshot whose metadata is not on the destination store does not
// report metadata removed from it.
func TestRemoveSnapshot_NoMetadataOnDestination(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
tv := vaultik.NewForTesting(newTestStorer())
tv.Repositories = newLocalIndex(t, "snapshot-001")
result, err := tv.RemoveSnapshot("snapshot-001",
&vaultik.RemoveOptions{Force: true})
require.NoError(t, err)
assert.False(t, result.RemoteRemoved)
out := tv.Stdout.String()
assert.Contains(t, out, "Removed snapshot 'snapshot-001' from local database")
assert.NotContains(t, out, "Removed snapshot metadata from remote storage")
}
// TestRemoveSnapshot_NotInLocalIndex checks that removing a snapshot
// only the destination store holds removes its metadata there without
// reporting a removal from the local database.
func TestRemoveSnapshot_NotInLocalIndex(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
store := newTestStorer()
addManifest(t, store, "snapshot-001", nil)
tv := vaultik.NewForTesting(store)
tv.Repositories = newLocalIndex(t)
result, err := tv.RemoveSnapshot("snapshot-001",
&vaultik.RemoveOptions{Force: true})
require.NoError(t, err)
assert.True(t, result.RemoteRemoved)
assert.False(t, store.hasKey(remoteKeyPath("snapshot-001")))
out := tv.Stdout.String()
assert.NotContains(t, out, "from local database")
assert.Contains(t, out, "Removed snapshot metadata from remote storage")
}
func TestRemoveAllSnapshots_RequiresForce(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
+32 -91
View File
@@ -23,7 +23,6 @@ var (
errNoSnapshotsInConfig = errors.New("no snapshots configured")
errSnapshotVerifyFailed = errors.New("verification failed")
errRemoveAllNeedsForce = errors.New("--all requires --force")
errSnapshotNotFound = errors.New("snapshot not found")
errInvalidTableName = errors.New("invalid table name")
errNoAgeRecipients = errors.New(
"creating a snapshot needs at least one public key in " +
@@ -644,7 +643,7 @@ func (v *Vaultik) confirmAndExecutePurge(
"snapshot_id", snapshotID, "error", err)
}
_, err = v.deleteRemoteSnapshotByKey(snapshot.RemoteSnapshotKey(snapshotID))
err = v.deleteRemoteSnapshotByKey(snapshot.RemoteSnapshotKey(snapshotID))
if err != nil {
return fmt.Errorf("deleting snapshot %s from remote: %w", snapshotID, err)
}
@@ -1154,11 +1153,6 @@ func (v *Vaultik) RemoveSnapshot(
return result, err
}
inLocalIndex, err := v.findSnapshotToRemove(snapshotID, opts)
if err != nil {
return result, err
}
if opts.DryRun {
return v.removeSnapshotDryRun(result, snapshotID, opts)
}
@@ -1167,13 +1161,11 @@ func (v *Vaultik) RemoveSnapshot(
return result, nil
}
if inLocalIndex {
log.Info("Removing snapshot from local database", "snapshot_id", snapshotID)
log.Info("Removing snapshot from local database", "snapshot_id", snapshotID)
err = v.deleteSnapshotFromLocalDB(snapshotID)
if err != nil {
return result, fmt.Errorf("removing from local database: %w", err)
}
err = v.deleteSnapshotFromLocalDB(snapshotID)
if err != nil {
return result, fmt.Errorf("removing from local database: %w", err)
}
if !opts.LocalOnly {
@@ -1192,11 +1184,9 @@ func (v *Vaultik) RemoveSnapshot(
return result, v.outputRemoveJSON(result)
}
if inLocalIndex {
v.stdoutf("Removed snapshot '%s' from local database\n", snapshotID)
}
v.stdoutf("Removed snapshot '%s' from local database\n", snapshotID)
if result.RemoteRemoved {
if !opts.LocalOnly && result.RemoteRemoved {
v.printlnStdout("Removed snapshot metadata from remote storage")
v.stdoutf("\nNote: The removed snapshot's blobs remain on the remote. "+
"Run '%s' to delete any blobs no longer referenced by any "+
@@ -1206,45 +1196,6 @@ func (v *Vaultik) RemoveSnapshot(
return result, nil
}
// findSnapshotToRemove reports whether the local index has a row for
// snapshotID, and returns errSnapshotNotFound when there is nothing to
// remove: no row and, unless LocalOnly is set, no metadata on the
// destination store either. The destination store is consulted only
// when the local index has no row, so a snapshot in the local index can
// still be removed from it while the destination store is unreachable.
func (v *Vaultik) findSnapshotToRemove(
snapshotID string, opts *RemoveOptions,
) (bool, error) {
if v.Repositories != nil {
snap, err := v.Repositories.Snapshots.GetByID(v.ctx, snapshotID)
if err != nil {
return false, fmt.Errorf("looking up snapshot in local index: %w", err)
}
if snap != nil {
return true, nil
}
}
if opts.LocalOnly {
return false, fmt.Errorf("%w in the local index: %s",
errSnapshotNotFound, snapshotID)
}
objects, err := v.remoteSnapshotObjects(snapshot.RemoteSnapshotKey(snapshotID))
if err != nil {
return false, fmt.Errorf("looking up snapshot on destination store: %w", err)
}
if len(objects) == 0 {
return false, fmt.Errorf(
"%w in the local index or on the destination store: %s",
errSnapshotNotFound, snapshotID)
}
return false, nil
}
// removeSnapshotDryRun reports what RemoveSnapshot would do without
// making changes.
func (v *Vaultik) removeSnapshotDryRun(
@@ -1304,14 +1255,14 @@ func (v *Vaultik) confirmRemoveSnapshot(snapshotID string, opts *RemoveOptions)
// didn't finish and to run `vaultik snapshot remove` for the snapshot
// again once the destination store is reachable (`vaultik prune` never
// removes snapshot metadata). Returns true when the remote removal
// succeeded and deleted something.
// succeeded.
func (v *Vaultik) removeSnapshotRemote(snapshotID string, opts *RemoveOptions) bool {
log.Info("Removing snapshot metadata from remote storage",
"snapshot_id", snapshotID)
remoteKey := snapshot.RemoteSnapshotKey(snapshotID)
deleted, err := v.deleteRemoteSnapshotByKey(remoteKey)
err := v.deleteRemoteSnapshotByKey(remoteKey)
if err != nil {
log.Warn("Could not remove snapshot metadata from remote storage; "+
"run '"+snapshotRemoveCommandHint+"' with the snapshot's ID "+
@@ -1329,7 +1280,7 @@ func (v *Vaultik) removeSnapshotRemote(snapshotID string, opts *RemoveOptions) b
return false
}
return deleted > 0
return true
}
// RemoveAllSnapshots removes every snapshot known to the local
@@ -1621,7 +1572,7 @@ func (v *Vaultik) removeAllLocalSnapshots(
}
if !opts.LocalOnly {
_, err = v.deleteRemoteSnapshotByKey(
err = v.deleteRemoteSnapshotByKey(
snapshot.RemoteSnapshotKey(snapshotID))
if err != nil {
log.Warn("Failed to remove snapshot metadata from remote",
@@ -1647,7 +1598,7 @@ func (v *Vaultik) removeAllOrphanRemotes(
for _, key := range orphanRemoteKeys {
log.Info("Removing orphan remote snapshot", "remote_key", key)
_, err := v.deleteRemoteSnapshotByKey(key)
err := v.deleteRemoteSnapshotByKey(key)
if err != nil {
log.Warn("Failed to remove orphan from remote",
"remote_key", key, "error", err)
@@ -1694,44 +1645,34 @@ func (v *Vaultik) deleteSnapshotFromLocalDB(snapshotID string) error {
}
// deleteRemoteSnapshotByKey removes everything under
// metadata/<remoteKey>/ on the destination store and returns how many
// objects it deleted. The argument is a remote key (double-SHA256
// derivation), not a human snapshot ID; callers that have a human ID
// must hash via snapshot.RemoteSnapshotKey first.
func (v *Vaultik) deleteRemoteSnapshotByKey(remoteKey string) (int, error) {
objectsToDelete, err := v.remoteSnapshotObjects(remoteKey)
if err != nil {
return 0, err
// metadata/<remoteKey>/ on the destination store. The argument is a
// remote key (double-SHA256 derivation), not a human snapshot ID;
// callers that have a human ID must hash via snapshot.RemoteSnapshotKey
// first.
func (v *Vaultik) deleteRemoteSnapshotByKey(remoteKey string) error {
prefix := fmt.Sprintf("metadata/%s/", remoteKey)
objectCh := v.Storage.ListStream(v.ctx, prefix)
var objectsToDelete []string
for object := range objectCh {
if object.Err != nil {
return fmt.Errorf("listing objects: %w", object.Err)
}
objectsToDelete = append(objectsToDelete, object.Key)
}
for i, key := range objectsToDelete {
err = v.Storage.Delete(v.ctx, key)
for _, key := range objectsToDelete {
err := v.Storage.Delete(v.ctx, key)
if err != nil {
return i, fmt.Errorf("removing %s: %w", key, err)
return fmt.Errorf("removing %s: %w", key, err)
}
log.Debug("Deleted remote object", "key", key)
}
return len(objectsToDelete), nil
}
// remoteSnapshotObjects lists the keys of every object under
// metadata/<remoteKey>/ on the destination store.
func (v *Vaultik) remoteSnapshotObjects(remoteKey string) ([]string, error) {
prefix := fmt.Sprintf("metadata/%s/", remoteKey)
var keys []string
for object := range v.Storage.ListStream(v.ctx, prefix) {
if object.Err != nil {
return nil, fmt.Errorf("listing objects: %w", object.Err)
}
keys = append(keys, object.Key)
}
return keys, nil
return nil
}
// outputRemoveJSON outputs the removal result as JSON