Compare commits

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
8 changed files with 102 additions and 123 deletions
+4 -1
View File
@@ -429,7 +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`).
+10 -8
View File
@@ -22,14 +22,16 @@ the tag exists and is exercised; what is left is merging `next` to
# Completed Steps
- 2026-10-13: Made an S3 listing that the server cuts short an error
([issue #297](https://git.eeqj.de/sneak/vaultik/issues/297)). A page
marked truncated with no continuation token, as a server answering V2
listings V1-style sends, ended the listing without an error, so
`prune` saw only the snapshots on the first page and could delete
blobs the rest still use. Such a page is now a listing error, and
`prune`, `snapshot list` and `remote nuke` handle it as a destination
that cannot be listed.
- 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)).
+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
+2 -29
View File
@@ -18,13 +18,6 @@ import (
"github.com/aws/smithy-go/logging"
)
// ErrNoContinuationToken is returned by ListObjects and ListObjectsStream
// when the server marks a page of a listing truncated but sends no
// continuation token to fetch the rest with, as a server answering V2
// listings V1-style does.
var ErrNoContinuationToken = errors.New(
"server marked the listing truncated but sent no continuation token")
// Client wraps the AWS S3 client for vaultik operations.
// It provides a simplified interface for S3 operations with automatic
// prefix handling and connection management. All operations are performed
@@ -221,7 +214,7 @@ func (c *Client) ListObjects(ctx context.Context, prefix string) ([]string, erro
})
for paginator.HasMorePages() {
page, err := nextListPage(ctx, paginator)
page, err := paginator.NextPage(ctx)
if err != nil {
return nil, err
}
@@ -242,26 +235,6 @@ func (c *Client) ListObjects(ctx context.Context, prefix string) ([]string, erro
return keys, nil
}
// nextListPage fetches the next page of a listing. The SDK paginator takes
// a page marked truncated without a continuation token for the last page
// and stops without an error, so such a page is ErrNoContinuationToken
// here instead.
func nextListPage(
ctx context.Context, paginator *s3.ListObjectsV2Paginator,
) (*s3.ListObjectsV2Output, error) {
page, err := paginator.NextPage(ctx)
if err != nil {
return nil, err
}
truncated := aws.ToBool(page.IsTruncated)
if truncated && aws.ToString(page.NextContinuationToken) == "" {
return nil, ErrNoContinuationToken
}
return page, nil
}
// HeadObject checks if an object exists in S3.
// Returns true if the object exists, false otherwise.
// The key is automatically prefixed with the configured prefix.
@@ -327,7 +300,7 @@ func (c *Client) ListObjectsStream(
})
for paginator.HasMorePages() {
page, err := nextListPage(ctx, paginator)
page, err := paginator.NextPage(ctx)
if err != nil {
ch <- ObjectInfo{Err: err}
+3 -69
View File
@@ -4,7 +4,6 @@ import (
"bytes"
"context"
"errors"
"io"
"net/http"
"net/http/httptest"
"slices"
@@ -23,16 +22,13 @@ import (
// s3TestBucket is the bucket created for each in-process S3 server.
const s3TestBucket = "test-bucket"
// Credentials for the tests' S3 clients. The test servers accept any.
// Credentials for the tests that build a storer from a config.Config. The
// in-process S3 server accepts any.
const (
s3TestAccessKeyID = "key"
s3TestSecretAccessKey = "secret"
)
// s3TestRegion is the region of the S3 clients built here with
// s3.NewClient. The test servers ignore it.
const s3TestRegion = "us-east-1"
// newS3Storer builds an s3:// backend backed by a fresh in-process
// S3 server. It reuses the same in-memory S3 harness (gofakes3 + s3mem
// over httptest) that internal/s3 and the not-found regression test use,
@@ -59,7 +55,7 @@ func newS3Storer(t *testing.T) storage.Storer {
Bucket: s3TestBucket,
AccessKeyID: "test",
SecretAccessKey: "test",
Region: s3TestRegion,
Region: "us-east-1",
})
if err != nil {
t.Fatalf("new client: %v", err)
@@ -97,68 +93,6 @@ func TestS3StorerMissingKeyMapsToErrNotFound(t *testing.T) {
}
}
// TestS3ListingCutShortIsAnError checks that List and ListStream fail on a
// listing page marked truncated that carries no continuation token, as a
// server answering V2 listings V1-style sends it. Taken as the last page,
// it would hide every later key, and prune would treat the blobs of the
// snapshots listed there as unreferenced.
func TestS3ListingCutShortIsAnError(t *testing.T) {
t.Parallel()
const (
prefix = "metadata/"
truncatedPage = `<?xml version="1.0" encoding="UTF-8"?>
<ListBucketResult xmlns="http://s3.amazonaws.com/doc/2006-03-01/">
<Name>test-bucket</Name>
<Prefix>metadata/</Prefix>
<KeyCount>1</KeyCount>
<MaxKeys>1</MaxKeys>
<IsTruncated>true</IsTruncated>
<Contents>
<Key>metadata/snap/manifest.json.zst</Key>
<Size>8</Size>
</Contents>
</ListBucketResult>`
)
srv := httptest.NewServer(http.HandlerFunc(
func(w http.ResponseWriter, _ *http.Request) {
_, _ = io.WriteString(w, truncatedPage)
}))
t.Cleanup(srv.Close)
client, err := s3.NewClient(context.Background(), s3.Config{
Endpoint: srv.URL,
Bucket: s3TestBucket,
AccessKeyID: s3TestAccessKeyID,
SecretAccessKey: s3TestSecretAccessKey,
Region: s3TestRegion,
})
if err != nil {
t.Fatalf("new client: %v", err)
}
storer := storage.NewS3Storer(client)
ctx := context.Background()
keys, err := storer.List(ctx, prefix)
if !errors.Is(err, s3.ErrNoContinuationToken) {
t.Errorf("List = %q, %v; want ErrNoContinuationToken", keys, err)
}
var streamErr error
for obj := range storer.ListStream(ctx, prefix) {
if obj.Err != nil {
streamErr = obj.Err
}
}
if !errors.Is(streamErr, s3.ErrNoContinuationToken) {
t.Errorf("ListStream error = %v, want ErrNoContinuationToken", streamErr)
}
}
// TestS3URLPrefixKeyLayout pins the bucket keys an s3:// URL reads and
// writes: the README's remote storage layout, with the prefix joined to
// each key by one "/". s3://b/p and s3://b/p/ must be the same
+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},