Author SHA1 Message Date
sneak 3543f45ba8 Add storage tests for URL parsing and every in-process backend (closes #66)
check / check (pull_request) Failing after 1s
internal/storage had no tests. This adds table-driven ParseStorageURL
coverage and a shared Storer conformance suite, defined once in
conformance_test.go and run against every backend that can run
in-process: file:// over a temp dir and s3:// over the same in-memory
S3 harness (gofakes3 + s3mem) that internal/s3 and the not-found test
use, so a new backend inherits the contract by passing its constructor.
The rclone backend gets construction and argument-shaping tests via
rclone's in-process ":local" backend, plus the missing-remote error
path; a comment records that its data-plane operations need a configured
remote and so cannot run in a unit test.

Tests only; no production code changed and no defect surfaced.

Model: opus-4-8
2026-09-21 19:55:20 +00:00
clawbot c355ef4d25 Report a prune count that could not be read as unknown, not 0 (closes #96)
check / check (pull_request) Failing after 1s
check / check (push) Successful in 2m46s
Prune read table row counts before and after to report how many orphaned files, chunks and blobs it removed, and discarded the error from every read. A failed query therefore reported as a count of 0, and the summary showed plausible wrong numbers.

A count that cannot be read is now logged as a warning (on stderr, also under --json) and shown as "unknown"; a difference computed from an unknown count is itself unknown. 0 still means the table was empty. No --json document carries these counts, so none can show a false 0.

model: claude-opus-4-8 (implementation, review); claude-fable-5-1 (merge)
2026-09-21 21:41:57 +02:00
5 changed files with 429 additions and 14 deletions
+198
View File
@@ -0,0 +1,198 @@
package storage_test
import (
"bytes"
"context"
"errors"
"io"
"reflect"
"sort"
"testing"
"sneak.berlin/go/vaultik/internal/storage"
)
// runStorerConformance is the shared Storer contract. Every backend that
// can run in-process is expected to pass it: TestFileStorer runs it against
// file://, TestS3Storer against s3://. A new backend inherits this coverage
// by passing its own constructor, so the contract is defined once.
//
// It exercises the public Storer interface: round-trip, stat, list with
// prefix filtering, overwrite, delete, delete-of-missing, and not-found on
// Get and Stat. Each section takes its own fresh backend instance, so the
// order of sections never matters and no section sees another's objects.
func runStorerConformance(t *testing.T, newStorer func(*testing.T) storage.Storer) {
t.Helper()
conformanceRoundTrip(t, newStorer(t))
conformanceOverwrite(t, newStorer(t))
conformanceList(t, newStorer(t))
conformanceDelete(t, newStorer(t))
conformanceNotFound(t, newStorer(t))
}
// conformanceRoundTrip stores a nested key, then reads it back and stats it.
func conformanceRoundTrip(t *testing.T, s storage.Storer) {
t.Helper()
ctx := context.Background()
key := "blobs/aa/bb/object.bin"
want := []byte("round-trip payload")
err := s.Put(ctx, key, bytes.NewReader(want))
if err != nil {
t.Fatalf("Put: %v", err)
}
got := getBytes(t, s, key)
if !bytes.Equal(got, want) {
t.Errorf("Get returned %q, want %q", got, want)
}
info, err := s.Stat(ctx, key)
if err != nil {
t.Fatalf("Stat: %v", err)
}
if info.Key != key {
t.Errorf("Stat key = %q, want %q", info.Key, key)
}
if info.Size != int64(len(want)) {
t.Errorf("Stat size = %d, want %d", info.Size, len(want))
}
}
// conformanceOverwrite checks that a second Put replaces the first.
func conformanceOverwrite(t *testing.T, s storage.Storer) {
t.Helper()
ctx := context.Background()
key := "meta/snapshot.json"
err := s.Put(ctx, key, bytes.NewReader([]byte("first")))
if err != nil {
t.Fatalf("first Put: %v", err)
}
want := []byte("second and longer payload")
err = s.Put(ctx, key, bytes.NewReader(want))
if err != nil {
t.Fatalf("second Put: %v", err)
}
got := getBytes(t, s, key)
if !bytes.Equal(got, want) {
t.Errorf("after overwrite Get returned %q, want %q", got, want)
}
}
// conformanceList checks prefix filtering and the empty result for a
// prefix that matches nothing.
func conformanceList(t *testing.T, s storage.Storer) {
t.Helper()
ctx := context.Background()
keys := []string{"blobs/aa/one", "blobs/bb/two", "meta/three"}
for _, k := range keys {
err := s.Put(ctx, k, bytes.NewReader([]byte("data")))
if err != nil {
t.Fatalf("Put %q: %v", k, err)
}
}
if got := listSorted(t, s, ""); !reflect.DeepEqual(got, keys) {
t.Errorf("List(\"\") = %v, want %v", got, keys)
}
wantBlobs := []string{"blobs/aa/one", "blobs/bb/two"}
if got := listSorted(t, s, "blobs/"); !reflect.DeepEqual(got, wantBlobs) {
t.Errorf("List(\"blobs/\") = %v, want %v", got, wantBlobs)
}
if got := listSorted(t, s, "absent/"); len(got) != 0 {
t.Errorf("List(\"absent/\") = %v, want empty", got)
}
}
// conformanceDelete checks that Delete removes an object and that deleting
// a missing key is not an error.
func conformanceDelete(t *testing.T, s storage.Storer) {
t.Helper()
ctx := context.Background()
key := "blobs/cc/gone.bin"
err := s.Put(ctx, key, bytes.NewReader([]byte("temporary")))
if err != nil {
t.Fatalf("Put: %v", err)
}
err = s.Delete(ctx, key)
if err != nil {
t.Fatalf("Delete: %v", err)
}
_, err = s.Get(ctx, key)
if !errors.Is(err, storage.ErrNotFound) {
t.Errorf("Get after Delete error = %v, want ErrNotFound", err)
}
err = s.Delete(ctx, key)
if err != nil {
t.Errorf("Delete of missing key = %v, want nil", err)
}
}
// conformanceNotFound checks Get and Stat on an absent key.
func conformanceNotFound(t *testing.T, s storage.Storer) {
t.Helper()
ctx := context.Background()
key := "never/written"
_, err := s.Get(ctx, key)
if !errors.Is(err, storage.ErrNotFound) {
t.Errorf("Get error = %v, want ErrNotFound", err)
}
_, err = s.Stat(ctx, key)
if !errors.Is(err, storage.ErrNotFound) {
t.Errorf("Stat error = %v, want ErrNotFound", err)
}
}
// getBytes reads a key fully and closes the reader.
func getBytes(t *testing.T, s storage.Storer, key string) []byte {
t.Helper()
rc, err := s.Get(context.Background(), key)
if err != nil {
t.Fatalf("Get %q: %v", key, err)
}
defer func() { _ = rc.Close() }()
data, err := io.ReadAll(rc)
if err != nil {
t.Fatalf("read %q: %v", key, err)
}
return data
}
// listSorted returns the keys under a prefix in a stable order.
func listSorted(t *testing.T, s storage.Storer, prefix string) []string {
t.Helper()
keys, err := s.List(context.Background(), prefix)
if err != nil {
t.Fatalf("List %q: %v", prefix, err)
}
sort.Strings(keys)
return keys
}
+27
View File
@@ -0,0 +1,27 @@
package storage_test
import (
"testing"
"sneak.berlin/go/vaultik/internal/storage"
)
// newFileStorer builds a file:// backend rooted at a fresh temp directory.
//
//nolint:ireturn // conformance runs against the Storer interface by design
func newFileStorer(t *testing.T) storage.Storer {
t.Helper()
s, err := storage.NewFileStorer(t.TempDir())
if err != nil {
t.Fatalf("NewFileStorer: %v", err)
}
return s
}
// TestFileStorer runs the shared Storer contract against the file:// backend.
func TestFileStorer(t *testing.T) {
t.Parallel()
runStorerConformance(t, newFileStorer)
}
+58
View File
@@ -0,0 +1,58 @@
package storage_test
import (
"context"
"errors"
"testing"
"sneak.berlin/go/vaultik/internal/storage"
)
// The rclone backend is a thin adapter over the rclone library: it turns a
// (remote, path) pair into rclone's "remote:path" string, hands it to
// rclone, and maps rclone's own results back to the Storer interface. What
// can be tested in-process, without a configured remote or network, is that
// adapter layer — how the arguments are shaped and how construction errors
// are reported. The data-plane operations (Put/Get/List/Delete) are rclone's
// own, exercised against a real provider (drive, s3-via-rclone, ...), which
// needs a configured remote with credentials and network access and so is
// out of reach of a unit test. The shared Storer conformance suite therefore
// runs against the in-process file and s3 backends; the rclone backend
// inherits that contract once a remote is configured.
//
// These tests use rclone's ":local:" on-the-fly backend, which addresses the
// local filesystem directly without any configured remote, so construction
// runs entirely in-process.
// TestNewRcloneStorerConstruction checks that a valid remote constructs a
// backend and that Info() reports the shaped "remote:path" location.
//
//nolint:paralleltest // NewRcloneStorer installs the process-global rclone config
func TestNewRcloneStorerConstruction(t *testing.T) {
dir := t.TempDir()
s, err := storage.NewRcloneStorer(context.Background(), ":local", dir)
if err != nil {
t.Fatalf("NewRcloneStorer: %v", err)
}
// Info().Location is the "remote:path" string the adapter builds from
// its two arguments, so asserting it confirms the argument shaping.
want := ":local:" + dir
if got := s.Info().Location; got != want {
t.Errorf("Info().Location = %q, want %q", got, want)
}
}
// TestNewRcloneStorerUnknownRemote checks that a remote that is not in the
// rclone config fails construction with the ErrRemoteNotFound sentinel,
// rather than silently returning a backend pointed nowhere.
//
//nolint:paralleltest // NewRcloneStorer installs the process-global rclone config
func TestNewRcloneStorerUnknownRemote(t *testing.T) {
_, err := storage.NewRcloneStorer(
context.Background(), "vaultik-no-such-remote", "path")
if !errors.Is(err, storage.ErrRemoteNotFound) {
t.Errorf("NewRcloneStorer error = %v, want ErrRemoteNotFound", err)
}
}
+36 -14
View File
@@ -13,18 +13,23 @@ import (
"sneak.berlin/go/vaultik/internal/storage"
)
// TestS3StorerMissingKeyMapsToErrNotFound verifies that the s3 backend reports
// a missing object as storage.ErrNotFound, matching the file and rclone
// backends and the Storer contract. Without the mapping, Get and Stat leak the
// raw SDK error and errors.Is(err, storage.ErrNotFound) is false.
// s3TestBucket is the bucket created for each in-process S3 server.
const s3TestBucket = "test-bucket"
// 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,
// so no new mock or dependency is introduced. Each call gets its own
// server, bucket, and client, so the conformance suite's per-section
// instances stay isolated.
//
//nolint:paralleltest // shares an in-process S3 server via t.Cleanup
func TestS3StorerMissingKeyMapsToErrNotFound(t *testing.T) {
const bucket = "test-bucket"
//nolint:ireturn // conformance runs against the Storer interface by design
func newS3Storer(t *testing.T) storage.Storer {
t.Helper()
backend := s3mem.New()
err := backend.CreateBucket(bucket)
err := backend.CreateBucket(s3TestBucket)
if err != nil {
t.Fatalf("create bucket: %v", err)
}
@@ -32,11 +37,9 @@ func TestS3StorerMissingKeyMapsToErrNotFound(t *testing.T) {
srv := httptest.NewServer(gofakes3.New(backend).Server())
t.Cleanup(srv.Close)
ctx := context.Background()
client, err := s3.NewClient(ctx, s3.Config{
client, err := s3.NewClient(context.Background(), s3.Config{
Endpoint: srv.URL,
Bucket: bucket,
Bucket: s3TestBucket,
AccessKeyID: "test",
SecretAccessKey: "test",
Region: "us-east-1",
@@ -45,9 +48,28 @@ func TestS3StorerMissingKeyMapsToErrNotFound(t *testing.T) {
t.Fatalf("new client: %v", err)
}
storer := storage.NewS3Storer(client)
return storage.NewS3Storer(client)
}
_, err = storer.Get(ctx, "does-not-exist")
// TestS3Storer runs the shared Storer contract against the s3:// backend,
// so it is held to the same round-trip, list, delete, and not-found
// behaviour as the file:// backend.
func TestS3Storer(t *testing.T) {
t.Parallel()
runStorerConformance(t, newS3Storer)
}
// TestS3StorerMissingKeyMapsToErrNotFound pins the specific contract that a
// missing object surfaces as storage.ErrNotFound rather than the raw AWS SDK
// error. Without the mapping, errors.Is(err, storage.ErrNotFound) is false on
// s3 and callers would branch differently per backend.
func TestS3StorerMissingKeyMapsToErrNotFound(t *testing.T) {
t.Parallel()
storer := newS3Storer(t)
ctx := context.Background()
_, err := storer.Get(ctx, "does-not-exist")
if !errors.Is(err, storage.ErrNotFound) {
t.Errorf("Get on missing key: got %v, want ErrNotFound", err)
}
+110
View File
@@ -0,0 +1,110 @@
package storage_test
import (
"errors"
"reflect"
"testing"
"sneak.berlin/go/vaultik/internal/storage"
)
// TestParseStorageURLValid checks that each supported scheme parses into
// the expected fields, since those fields decide which backend is built.
func TestParseStorageURLValid(t *testing.T) {
t.Parallel()
const bucket = "mybucket"
cases := []struct {
name string
raw string
want *storage.URL
}{
{
name: "file absolute path",
raw: "file:///var/backups/vaultik",
want: &storage.URL{Scheme: "file", Prefix: "/var/backups/vaultik"},
},
{
name: "s3 bucket and prefix, ssl defaults on",
raw: "s3://mybucket/backups/host",
want: &storage.URL{
Scheme: "s3", Bucket: bucket,
Prefix: "backups/host", UseSSL: true,
},
},
{
name: "s3 bucket only",
raw: "s3://mybucket",
want: &storage.URL{Scheme: "s3", Bucket: bucket, UseSSL: true},
},
{
name: "s3 with endpoint, region, ssl off",
raw: "s3://mybucket?endpoint=minio.example.com&region=us-west-2&ssl=false",
want: &storage.URL{
Scheme: "s3", Bucket: bucket,
Endpoint: "minio.example.com", Region: "us-west-2", UseSSL: false,
},
},
{
name: "rclone remote and path",
raw: "rclone://gdrive/backups/host",
want: &storage.URL{
Scheme: "rclone", RcloneRemote: "gdrive", Prefix: "backups/host",
},
},
{
name: "rclone remote only",
raw: "rclone://gdrive",
want: &storage.URL{Scheme: "rclone", RcloneRemote: "gdrive"},
},
}
for _, tc := range cases {
t.Run(tc.name, func(t *testing.T) {
t.Parallel()
got, err := storage.ParseStorageURL(tc.raw)
if err != nil {
t.Fatalf("ParseStorageURL(%q) returned error: %v", tc.raw, err)
}
if !reflect.DeepEqual(got, tc.want) {
t.Errorf("ParseStorageURL(%q) = %+v, want %+v", tc.raw, got, tc.want)
}
})
}
}
// TestParseStorageURLErrors checks that empty, missing, and unknown-scheme
// inputs fail with the documented sentinel errors instead of parsing to a
// wrong destination.
func TestParseStorageURLErrors(t *testing.T) {
t.Parallel()
cases := []struct {
name string
raw string
wantErr error
}{
{"empty url", "", storage.ErrEmptyStorageURL},
{"file empty path", "file://", storage.ErrEmptyFilePath},
{"s3 missing bucket", "s3://", storage.ErrMissingBucket},
{"s3 missing bucket with path", "s3:///justprefix", storage.ErrMissingBucket},
{"rclone missing remote", "rclone://", storage.ErrMissingRemote},
{"unknown scheme", "gs://bucket/x", storage.ErrUnsupportedScheme},
{"no scheme", "/local/path", storage.ErrUnsupportedScheme},
}
for _, tc := range cases {
t.Run(tc.name, func(t *testing.T) {
t.Parallel()
_, err := storage.ParseStorageURL(tc.raw)
if !errors.Is(err, tc.wantErr) {
t.Errorf("ParseStorageURL(%q) error = %v, want %v",
tc.raw, err, tc.wantErr)
}
})
}
}