Author SHA1 Message Date
sneak 15ae8c03df Add tests for internal/storage URL parsing and the file backend (closes #66)
check / check (pull_request) Failing after 1s
internal/storage had no tests. This adds table-driven coverage for
ParseStorageURL (each scheme, query parameters, missing components, an
unknown scheme, and the fields that decide which backend is built) and a
backend-agnostic Storer conformance suite run against the file:// backend
over a temp directory: put, get, stat, list with prefix filtering,
overwrite, delete, delete-of-missing, and not-found on Get and Stat.

Tests only; no production code changed and no defect surfaced. New files
(url_parse_test.go, file_backend_test.go) avoid colliding with the
s3_test.go and file-backend work in flight on other branches. The
conformance helper takes a constructor, so s3:// and rclone:// can adopt
it once their harness is wired.

Model: opus-4-8
2026-09-21 19:10:31 +00:00
13 changed files with 413 additions and 548 deletions
+1 -21
View File
@@ -25,27 +25,6 @@ release" is exactly the contradiction
# Completed Steps
- 2026-09-21: Stopped `prune` from reporting a failed row count as 0
([issue #96](https://git.eeqj.de/sneak/vaultik/issues/96)). The seven
`getTableCount` reads in `PruneDatabase` discarded their error, so a
query that could not run became a plausible `0` and the before/after
delta computed from it looked like real work. Each read now logs at
warn on failure and renders as `unknown`, never `0`, so an empty table
is distinguishable from one that could not be queried. The counts have
no `--json` representation — under `--json` the summary is suppressed
entirely — so nothing there can show a false `0`.
- 2026-09-21: Stopped `--json` from silencing stderr diagnostics
([issue #112](https://git.eeqj.de/sneak/vaultik/issues/112)). `--json`
used to be folded into `Quiet`, which pinned the log level to `WARN`,
so `prune --json` gave a machine consumer no record of the local index
rows it deleted even under `--verbose`. `--json` now quiets only the
stdout UI (the JSON document must stay clean, per
[issue #108](https://git.eeqj.de/sneak/vaultik/issues/108)); the stderr
log level follows `--verbose`/`--debug` again. The coupling was
removed the same way for `snapshot verify`, `snapshot remove`, and
`remote info`, which carried it for the same outdated reason.
- 2026-09-21: Made the s3 storage backend report a missing object as
`storage.ErrNotFound`, like the `file` and `rclone` backends and as the
`Storer` interface documents. `S3Storer.Get` and `Stat` returned the raw
@@ -54,6 +33,7 @@ release" is exactly the contradiction
helper (reused by `HeadObject`) and a test that a missing key maps to
`ErrNotFound`
([issue #129](https://git.eeqj.de/sneak/vaultik/issues/129)).
- 2026-09-21: Fixed `verify --deep` reporting healthy snapshots as
corrupt. Its final blob-integrity check hashed the encrypted
downloaded bytes with a single SHA256 and compared that to the blob
+4 -11
View File
@@ -48,11 +48,6 @@ type AppOptions struct {
// silenced — per the documented convention that --quiet suppresses
// non-error output only. The startup banner is printed by Entry
// before cobra parses arguments, gated by the same arg-level check.
//
// --json quiets the UI here too, because stdout then carries a JSON
// document and human narration would corrupt it. Unlike Quiet it does
// not lower the stderr log level (issue #112), so --verbose/--debug
// still surface diagnostics alongside the document.
func setupGlobals(
lc fx.Lifecycle, g *globals.Globals, v *vaultik.Vaultik, opts log.Options,
) {
@@ -60,7 +55,7 @@ func setupGlobals(
OnStart: func(_ context.Context) error {
g.StartTime = time.Now().UTC()
if opts.Cron || opts.Quiet || opts.JSON {
if opts.Cron || opts.Quiet {
v.UI.SetQuiet(true)
}
@@ -207,10 +202,9 @@ func RunApp(ctx context.Context, app *fx.App) error {
// instance in a goroutine, report a failure prefixed with failMsg
// (suppressed while suppressErrors is true, e.g. under --json), then
// trigger shutdown. The operation is cancelled when the app stops.
// jsonOutput marks a command whose stdout is a JSON document: it quiets
// the UI but, unlike Quiet, leaves the stderr log level alone.
// extraQuiet is OR-ed into LogOptions.Quiet (e.g. --json output modes).
func runVaultikApp(
cmd *cobra.Command, jsonOutput, suppressErrors bool,
cmd *cobra.Command, extraQuiet, suppressErrors bool,
failMsg string, op func(v *vaultik.Vaultik) error,
) error {
configPath, err := ResolveConfigPath()
@@ -225,8 +219,7 @@ func runVaultikApp(
LogOptions: log.Options{
Verbose: rootFlags.Verbose,
Debug: rootFlags.Debug,
Quiet: rootFlags.Quiet,
JSON: jsonOutput,
Quiet: rootFlags.Quiet || extraQuiet,
},
Modules: []fx.Option{},
Invokes: []fx.Option{
@@ -1,139 +0,0 @@
package cli //nolint:testpackage // shares the prune fixtures and capture helpers
import (
"bytes"
"io"
"os"
"testing"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
)
// staleRecordLogMessage is the local-cleanup audit line CleanupLocalSnapshots
// logs for each stale record. It is exactly the signal issue #112 says a
// machine consumer lost under --json: gated off stdout, and pinned below
// the log level on stderr because --json used to force Quiet.
const staleRecordLogMessage = "Removing stale local snapshot record"
// TestEntryPruneJSONStderrHonoursVerbosity is the end-to-end regression
// guard for issue #112. Under --json the log level must still follow
// --verbose/--debug rather than being pinned to WARN, so the
// local-cleanup records reach stderr under --verbose while stdout stays
// exactly one JSON document; without --verbose they stay below the
// level, as they do without --json.
//
// Both halves are asserted together on the same run, because the fix has
// to keep the document clean (issue #108) while freeing stderr.
//
// Not parallel: it replaces os.Args, os.Stdout, os.Stderr and the xdg
// globals.
//
//nolint:paralleltest // replaces os.Args, os.Stdout, os.Stderr and the xdg globals
func TestEntryPruneJSONStderrHonoursVerbosity(t *testing.T) {
for _, testCase := range []struct {
name string
verbose bool
wantOnStderr bool
}{
{
name: "verbose json surfaces the cleanup record on stderr",
verbose: true,
wantOnStderr: true,
},
{
name: "json alone keeps the cleanup record below the level",
verbose: false,
wantOnStderr: false,
},
} {
t.Run(testCase.name, func(t *testing.T) {
configPath := writeHermeticPruneConfig(t, true)
previousArgs := os.Args
t.Cleanup(func() {
os.Args = previousArgs
rootFlags = RootFlags{}
})
args := []string{
programName, flagConfig, configPath, cmdPrune, flagJSON,
}
if testCase.verbose {
args = append(args, "--verbose")
}
os.Args = args
stdout, stderr := captureProcessStdoutAndStderr(t, Entry)
// The document stays clean in both cases: freeing stderr must
// not regress issue #108.
requireExactlyOneJSONDocument(t, stdout)
if testCase.wantOnStderr {
assert.Contains(t, stderr, staleRecordLogMessage,
"--verbose --json must emit the cleanup record on stderr")
assert.Contains(t, stderr, stalePruneSnapshotID,
"the record must name the snapshot it removed")
} else {
assert.NotContains(t, stderr, staleRecordLogMessage,
"without --verbose the record stays below the log level")
}
})
}
}
// captureProcessStdoutAndStderr redirects both of the process's own
// standard streams to pipes for the duration of fn and returns what was
// written to each. The redirection is at the file-descriptor level
// because the logger binds os.Stderr when it initializes inside fn, and
// the JSON document reaches os.Stdout independently; the point is to see
// where each actually lands.
//
// Not parallel-safe: os.Stdout and os.Stderr are process-global.
func captureProcessStdoutAndStderr(t *testing.T, fn func()) (string, string) {
t.Helper()
outReader, outWriter, err := os.Pipe()
require.NoError(t, err)
errReader, errWriter, err := os.Pipe()
require.NoError(t, err)
previousOut, previousErr := os.Stdout, os.Stderr
os.Stdout, os.Stderr = outWriter, errWriter
capturedOut := drain(outReader)
capturedErr := drain(errReader)
fn()
os.Stdout, os.Stderr = previousOut, previousErr
require.NoError(t, outWriter.Close())
require.NoError(t, errWriter.Close())
out, errOut := <-capturedOut, <-capturedErr
require.NoError(t, outReader.Close())
require.NoError(t, errReader.Close())
return out, errOut
}
// drain copies a reader to a string on a goroutine and delivers the
// result once the writer end is closed.
func drain(reader io.Reader) <-chan string {
captured := make(chan string, 1)
go func() {
var buf bytes.Buffer
_, _ = io.Copy(&buf, reader)
captured <- buf.String()
}()
return captured
}
+1 -2
View File
@@ -46,8 +46,7 @@ work (e.g. after a crashed backup or to reclaim storage).`,
LogOptions: log.Options{
Verbose: rootFlags.Verbose,
Debug: rootFlags.Debug,
Quiet: rootFlags.Quiet,
JSON: opts.JSON,
Quiet: rootFlags.Quiet || opts.JSON,
},
Modules: []fx.Option{},
Invokes: []fx.Option{
+1 -2
View File
@@ -88,8 +88,7 @@ func newRemoteInfoCommand() *cobra.Command {
LogOptions: log.Options{
Verbose: rootFlags.Verbose,
Debug: rootFlags.Debug,
Quiet: rootFlags.Quiet,
JSON: jsonOutput,
Quiet: rootFlags.Quiet || jsonOutput,
},
Modules: []fx.Option{},
Invokes: []fx.Option{
+1 -2
View File
@@ -239,8 +239,7 @@ func newSnapshotVerifyCommand() *cobra.Command {
LogOptions: log.Options{
Verbose: rootFlags.Verbose,
Debug: rootFlags.Debug,
Quiet: rootFlags.Quiet,
JSON: opts.JSON,
Quiet: rootFlags.Quiet || opts.JSON,
},
Modules: []fx.Option{},
Invokes: []fx.Option{
+1 -15
View File
@@ -14,18 +14,8 @@ var Module = fx.Module("log",
)
// New creates a new logger configuration from provided options.
//
// JSON is intentionally not carried into Config: a command emitting a
// JSON document on stdout must keep its stderr log level under
// --verbose/--debug, so --json must not lower it (issue #112). JSON
// silences the stdout UI in setupGlobals instead.
func New(opts Options) Config {
return Config{
Verbose: opts.Verbose,
Debug: opts.Debug,
Cron: opts.Cron,
Quiet: opts.Quiet,
}
return Config(opts)
}
// Options are provided by the CLI.
@@ -34,8 +24,4 @@ type Options struct {
Debug bool
Cron bool
Quiet bool
// JSON marks a command whose stdout carries a machine-readable
// document. It silences the human UI on stdout (see setupGlobals),
// but unlike Quiet it leaves the stderr log level alone.
JSON bool
}
+54 -79
View File
@@ -46,18 +46,31 @@ func (f *FileStorer) SetFilesystem(fs afero.Fs) {
// storage base path.
const storageDirPerm = 0o755
// tempSuffix marks a partially written object. writeAtomic streams into a
// temp file carrying this suffix and only renames it onto the real key once
// the whole object is on disk, so an interrupted write can never leave a
// truncated object at the key a later run would Stat and trust as a complete
// blob. List and ListStream skip these files, so a leftover from an
// interrupted write is never listed or trusted as a blob; it is otherwise
// harmless and is overwritten when the same key is written again.
const tempSuffix = ".partial"
// Put stores data at the specified key.
func (f *FileStorer) Put(_ context.Context, key string, data io.Reader) error {
return f.writeAtomic(key, data, nil)
path := f.fullPath(key)
// Create parent directories
dir := filepath.Dir(path)
err := f.fs.MkdirAll(dir, storageDirPerm)
if err != nil {
return fmt.Errorf("creating directories: %w", err)
}
file, err := f.fs.Create(path)
if err != nil {
return fmt.Errorf("creating file: %w", err)
}
defer func() { _ = file.Close() }()
_, err = io.Copy(file, data)
if err != nil {
return fmt.Errorf("writing file: %w", err)
}
return nil
}
// PutWithProgress stores data with progress reporting.
@@ -65,7 +78,35 @@ func (f *FileStorer) PutWithProgress(
_ context.Context, key string, data io.Reader,
_ int64, progress ProgressCallback,
) error {
return f.writeAtomic(key, data, progress)
path := f.fullPath(key)
// Create parent directories
dir := filepath.Dir(path)
err := f.fs.MkdirAll(dir, storageDirPerm)
if err != nil {
return fmt.Errorf("creating directories: %w", err)
}
file, err := f.fs.Create(path)
if err != nil {
return fmt.Errorf("creating file: %w", err)
}
defer func() { _ = file.Close() }()
// Wrap with progress tracking
pw := &progressWriter{
writer: file,
callback: progress,
}
_, err = io.Copy(pw, data)
if err != nil {
return fmt.Errorf("writing file: %w", err)
}
return nil
}
// Get retrieves data from the specified key.
@@ -147,7 +188,7 @@ func (f *FileStorer) List(ctx context.Context, prefix string) ([]string, error)
default:
}
if !info.IsDir() && !strings.HasSuffix(info.Name(), tempSuffix) {
if !info.IsDir() {
// Convert back to key (relative path from basePath)
relPath, err := filepath.Rel(f.basePath, path)
if err != nil {
@@ -204,7 +245,7 @@ func (f *FileStorer) ListStream(ctx context.Context, prefix string) <-chan Objec
return nil //nolint:nilerr // continue walking despite errors
}
if !info.IsDir() && !strings.HasSuffix(info.Name(), tempSuffix) {
if !info.IsDir() {
relPath, err := filepath.Rel(f.basePath, path)
if err != nil {
ch <- ObjectInfo{Err: fmt.Errorf("computing relative path: %w", err)}
@@ -234,72 +275,6 @@ func (f *FileStorer) Info() Info {
}
}
// writeAtomic streams data into a temp file in the destination directory,
// fsyncs it, and renames it onto the final key. The key therefore appears
// only once the whole object has been durably written; a failure part-way
// leaves a temp file (removed here on the failing path) rather than a
// truncated object at the key.
func (f *FileStorer) writeAtomic(
key string, data io.Reader, progress ProgressCallback,
) error {
path := f.fullPath(key)
dir := filepath.Dir(path)
err := f.fs.MkdirAll(dir, storageDirPerm)
if err != nil {
return fmt.Errorf("creating directories: %w", err)
}
tmp, err := afero.TempFile(f.fs, dir, filepath.Base(path)+"-*"+tempSuffix)
if err != nil {
return fmt.Errorf("creating temp file: %w", err)
}
tmpPath := tmp.Name()
// Remove the temp file unless the rename below claims it. On the success
// path renamed is true, so the deferred Close and Remove are harmless
// no-ops on a name that no longer exists.
renamed := false
defer func() {
_ = tmp.Close()
if !renamed {
_ = f.fs.Remove(tmpPath)
}
}()
var w io.Writer = tmp
if progress != nil {
w = &progressWriter{writer: tmp, callback: progress}
}
_, err = io.Copy(w, data)
if err != nil {
return fmt.Errorf("writing file: %w", err)
}
err = tmp.Sync()
if err != nil {
return fmt.Errorf("syncing temp file: %w", err)
}
err = tmp.Close()
if err != nil {
return fmt.Errorf("closing temp file: %w", err)
}
err = f.fs.Rename(tmpPath, path)
if err != nil {
return fmt.Errorf("renaming temp file: %w", err)
}
renamed = true
return nil
}
// fullPath returns the full filesystem path for a key.
func (f *FileStorer) fullPath(key string) string {
return filepath.Join(f.basePath, key)
-119
View File
@@ -1,119 +0,0 @@
package storage_test
import (
"context"
"errors"
"os"
"path/filepath"
"strings"
"testing"
"sneak.berlin/go/vaultik/internal/storage"
)
// errStreamInterrupted stands in for an upload cut off mid-stream.
var errStreamInterrupted = errors.New("connection reset mid-upload")
// failingReader yields its data once, then fails.
type failingReader struct {
data []byte
done bool
}
func (r *failingReader) Read(p []byte) (int, error) {
if r.done {
return 0, errStreamInterrupted
}
n := copy(p, r.data)
r.done = true
return n, nil
}
// TestFileStorer_InterruptedWriteLeavesNoTrustedObject checks that a write
// cut off mid-stream leaves nothing at the destination key, so a later run
// cannot Stat a truncated object and trust it as a complete blob.
func TestFileStorer_InterruptedWriteLeavesNoTrustedObject(t *testing.T) {
t.Parallel()
f, err := storage.NewFileStorer(t.TempDir())
if err != nil {
t.Fatalf("NewFileStorer: %v", err)
}
ctx := context.Background()
key := "blobs/aa/bb/aabbccddeeff"
err = f.PutWithProgress(ctx, key, &failingReader{data: []byte("partial")}, 4096, nil)
if err == nil {
t.Fatal("expected the interrupted write to fail, got nil")
}
_, err = f.Stat(ctx, key)
if !errors.Is(err, storage.ErrNotFound) {
t.Fatalf("expected key absent after interrupted write, got Stat err %v", err)
}
keys, err := f.List(ctx, "blobs/")
if err != nil {
t.Fatalf("List: %v", err)
}
if len(keys) != 0 {
t.Fatalf("expected no keys listed after interrupted write, got %v", keys)
}
}
// TestFileStorer_ListSkipsPartialFiles checks that a leftover temp file (the
// storage layer names them with a ".partial" suffix) is never surfaced as a
// key by List or ListStream.
func TestFileStorer_ListSkipsPartialFiles(t *testing.T) {
t.Parallel()
base := t.TempDir()
f, err := storage.NewFileStorer(base)
if err != nil {
t.Fatalf("NewFileStorer: %v", err)
}
ctx := context.Background()
realKey := "blobs/aa/bb/aabbccddeeff"
err = f.Put(ctx, realKey, strings.NewReader("blob-bytes"))
if err != nil {
t.Fatalf("Put: %v", err)
}
// A stray temp file, as an interrupted write would leave behind.
leftover := filepath.Join(base, "blobs/aa/bb/aabbccddeeff-123456.partial")
err = os.WriteFile(leftover, []byte("half"), 0o600)
if err != nil {
t.Fatalf("writing leftover temp file: %v", err)
}
keys, err := f.List(ctx, "blobs/")
if err != nil {
t.Fatalf("List: %v", err)
}
if len(keys) != 1 || keys[0] != realKey {
t.Fatalf("List should return only the real key, got %v", keys)
}
var streamed []string
for obj := range f.ListStream(ctx, "blobs/") {
if obj.Err != nil {
t.Fatalf("ListStream: %v", obj.Err)
}
streamed = append(streamed, obj.Key)
}
if len(streamed) != 1 || streamed[0] != realKey {
t.Fatalf("ListStream should return only the real key, got %v", streamed)
}
}
+214
View File
@@ -0,0 +1,214 @@
package storage_test
import (
"bytes"
"context"
"errors"
"io"
"reflect"
"sort"
"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 Storer contract against the file:// backend.
// The conformance helper is backend-agnostic, so a new backend inherits
// this coverage by passing its own constructor.
func TestFileStorer(t *testing.T) {
t.Parallel()
runStorerConformance(t, newFileStorer)
}
// runStorerConformance exercises the public Storer contract: round-trip,
// stat, list, overwrite, delete, and not-found behaviour. Each section
// uses its own backend instance so ordering never matters.
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
}
+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)
}
})
}
}
-79
View File
@@ -1,79 +0,0 @@
package vaultik //nolint:testpackage // exercises unexported count helpers
import (
"context"
"testing"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
"sneak.berlin/go/vaultik/internal/database"
"sneak.berlin/go/vaultik/internal/log"
)
// TestTableCountForReportSurfacesReadFailure is the regression guard for
// the discarded-error bug: getTableCount for a table its query cannot
// resolve must not silently become 0. A count that could not be read is
// reported as unknown, which a reader can tell apart from an empty table.
//
//nolint:paralleltest // installs the global logger via log.Initialize
func TestTableCountForReportSurfacesReadFailure(t *testing.T) {
log.Initialize(log.Config{})
ctx := context.Background()
db, err := database.New(ctx, ":memory:")
require.NoError(t, err)
t.Cleanup(func() { _ = db.Close() })
v := &Vaultik{DB: db}
v.SetContext(ctx)
// A table present in the schema reads as a real count.
blobs := v.tableCountForReport("blobs")
require.NotNil(t, blobs, "an existing table must read as a real count")
assert.Equal(t, int64(0), *blobs)
// A syntactically valid name the sanitizer accepts but whose table
// the query cannot resolve is the exact shape #96 describes: a
// would-be loud failure that used to be discarded into a 0.
_, err = v.getTableCount("snapshots_missing")
require.Error(t, err, "a query against a nonexistent table must fail")
missing := v.tableCountForReport("snapshots_missing")
assert.Nil(t, missing, "a failed read is unknown, not a count")
// The rendered count for a failed read must say unknown, never 0.
assert.Equal(t, countUnknown, countText(missing))
assert.NotEqual(t, "0", countText(missing))
}
// TestCountTextDistinguishesEmptyFromUnknown pins the distinction the
// output has to preserve: 0 means the table was empty, "unknown" means
// the count could not be read.
func TestCountTextDistinguishesEmptyFromUnknown(t *testing.T) {
t.Parallel()
zero := int64(0)
seven := int64(7)
assert.Equal(t, "0", countText(&zero))
assert.Equal(t, "7", countText(&seven))
assert.Equal(t, countUnknown, countText(nil))
}
// TestCountDiffUnknownWhenEitherSideUnknown checks that a delta computed
// from an unreadable count is itself unknown rather than a plausible
// number.
func TestCountDiffUnknownWhenEitherSideUnknown(t *testing.T) {
t.Parallel()
before := int64(10)
after := int64(3)
require.NotNil(t, countDiff(&before, &after))
assert.Equal(t, int64(7), *countDiff(&before, &after))
assert.Nil(t, countDiff(nil, &after), "unknown before yields unknown delta")
assert.Nil(t, countDiff(&before, nil), "unknown after yields unknown delta")
assert.Nil(t, countDiff(nil, nil))
}
+26 -79
View File
@@ -8,7 +8,6 @@ import (
"path/filepath"
"regexp"
"sort"
"strconv"
"strings"
"time"
@@ -1541,17 +1540,12 @@ func (v *Vaultik) outputRemoveJSON(result *RemoveResult) error {
return encoder.Encode(result)
}
// PruneResult contains statistics about the prune operation.
// SnapshotsDeleted counts snapshots actually deleted. FilesDeleted,
// ChunksDeleted, and BlobsDeleted are derived from before/after row
// counts of the local index; each is nil when a count could not be read,
// so an unreadable count is reported as unknown rather than silently
// as 0.
// PruneResult contains statistics about the prune operation
type PruneResult struct {
SnapshotsDeleted int64
FilesDeleted *int64
ChunksDeleted *int64
BlobsDeleted *int64
FilesDeleted int64
ChunksDeleted int64
BlobsDeleted int64
}
// PruneDatabase removes incomplete snapshots and orphaned files, chunks,
@@ -1566,7 +1560,7 @@ func (v *Vaultik) PruneDatabase() (*PruneResult, error) {
result := &PruneResult{}
// Snapshot counts before deletion of incompletes.
snapshotCountBefore := v.tableCountForReport("snapshots")
snapshotCountBefore, _ := v.getTableCount("snapshots")
// First, delete any incomplete snapshots
incompleteSnapshots, err := v.Repositories.Snapshots.GetIncompleteSnapshots(v.ctx)
@@ -1581,9 +1575,9 @@ func (v *Vaultik) PruneDatabase() (*PruneResult, error) {
}
// Get counts before cleanup for reporting
fileCountBefore := v.tableCountForReport("files")
chunkCountBefore := v.tableCountForReport("chunks")
blobCountBefore := v.tableCountForReport("blobs")
fileCountBefore, _ := v.getTableCount("files")
chunkCountBefore, _ := v.getTableCount("chunks")
blobCountBefore, _ := v.getTableCount("blobs")
// Run the cleanup
err = v.SnapshotManager.CleanupOrphanedData(v.ctx)
@@ -1592,83 +1586,36 @@ func (v *Vaultik) PruneDatabase() (*PruneResult, error) {
}
// Get counts after cleanup
fileCountAfter := v.tableCountForReport("files")
chunkCountAfter := v.tableCountForReport("chunks")
blobCountAfter := v.tableCountForReport("blobs")
fileCountAfter, _ := v.getTableCount("files")
chunkCountAfter, _ := v.getTableCount("chunks")
blobCountAfter, _ := v.getTableCount("blobs")
result.FilesDeleted = countDiff(fileCountBefore, fileCountAfter)
result.ChunksDeleted = countDiff(chunkCountBefore, chunkCountAfter)
result.BlobsDeleted = countDiff(blobCountBefore, blobCountAfter)
result.FilesDeleted = fileCountBefore - fileCountAfter
result.ChunksDeleted = chunkCountBefore - chunkCountAfter
result.BlobsDeleted = blobCountBefore - blobCountAfter
log.Info("Local database prune complete",
"incomplete_snapshots", result.SnapshotsDeleted,
"orphaned_files", countText(result.FilesDeleted),
"orphaned_chunks", countText(result.ChunksDeleted),
"orphaned_blobs", countText(result.BlobsDeleted),
"orphaned_files", result.FilesDeleted,
"orphaned_chunks", result.ChunksDeleted,
"orphaned_blobs", result.BlobsDeleted,
)
// Snapshots remaining after removing the incomplete ones; unknown if
// the pre-prune snapshot count could not be read.
snapshotsRemain := countDiff(snapshotCountBefore, &result.SnapshotsDeleted)
snapshotCountAfter := snapshotCountBefore - result.SnapshotsDeleted
v.UI.Completef("Pruned local index database.")
v.UI.Detailf("Incomplete snapshots: %s removed (%s remain).",
countText(&result.SnapshotsDeleted), countText(snapshotsRemain))
v.UI.Detailf("Orphaned files: %s removed (%s remain).",
countText(result.FilesDeleted), countText(fileCountAfter))
v.UI.Detailf("Orphaned chunks: %s removed (%s remain).",
countText(result.ChunksDeleted), countText(chunkCountAfter))
v.UI.Detailf("Orphaned blobs: %s removed (%s remain).",
countText(result.BlobsDeleted), countText(blobCountAfter))
v.UI.Detailf("Incomplete snapshots: %d removed (%d remain).",
result.SnapshotsDeleted, snapshotCountAfter)
v.UI.Detailf("Orphaned files: %d removed (%d remain).",
result.FilesDeleted, fileCountAfter)
v.UI.Detailf("Orphaned chunks: %d removed (%d remain).",
result.ChunksDeleted, chunkCountAfter)
v.UI.Detailf("Orphaned blobs: %d removed (%d remain).",
result.BlobsDeleted, blobCountAfter)
return result, nil
}
// countUnknown is what a count reads as when its query could not be run,
// distinct from "0", which means the table really was empty.
const countUnknown = "unknown"
// tableCountForReport returns the row count of a table for the prune
// summary, or nil if the count could not be read. A read failure is
// logged at warn — visible even under --json, which routes warnings to
// stderr — and then rendered as unknown rather than silently becoming 0,
// so a broken query is a visible failure instead of a plausible wrong
// number.
func (v *Vaultik) tableCountForReport(tableName string) *int64 {
count, err := v.getTableCount(tableName)
if err != nil {
log.Warn("could not read table row count for prune summary",
"table", tableName, "error", err)
return nil
}
return &count
}
// countDiff returns before-after, or nil if either count is unknown so
// that an unreadable count does not collapse into a plausible delta.
func countDiff(before, after *int64) *int64 {
if before == nil || after == nil {
return nil
}
diff := *before - *after
return &diff
}
// countText renders a count that may be unknown: nil (the read failed)
// becomes "unknown", never "0", so a reader can tell an empty table from
// one that could not be queried.
func countText(count *int64) string {
if count == nil {
return countUnknown
}
return strconv.FormatInt(*count, 10)
}
// validTableNameRe matches table names containing only lowercase
// alphanumeric characters and underscores.
var validTableNameRe = regexp.MustCompile(`^[a-z0-9_]+$`)