vaultik/internal/vaultik/prune_metadata_dir_test.go

package vaultik_test

import (
	"bytes"
	"context"
	"encoding/json"
	"os"
	"path/filepath"
	"strings"
	"testing"
	"time"

	"github.com/stretchr/testify/assert"
	"github.com/stretchr/testify/require"
	"sneak.berlin/go/vaultik/internal/config"
	"sneak.berlin/go/vaultik/internal/log"
	"sneak.berlin/go/vaultik/internal/snapshot"
	"sneak.berlin/go/vaultik/internal/storage"
	"sneak.berlin/go/vaultik/internal/storage/faultstore"
	"sneak.berlin/go/vaultik/internal/ui"
	"sneak.berlin/go/vaultik/internal/vaultik"
)

// metadataObjectKey returns the key of the named file in the metadata
// directory of the snapshot with the given human ID.
func metadataObjectKey(snapshotID, name string) string {
	return "metadata/" + snapshot.RemoteSnapshotKey(snapshotID) + "/" + name
}

// TestPruneDeletesMetadataDirWithoutManifestOlderThanGracePeriod checks
// that prune deletes a directory under metadata/ holding only
// db.zst.age, as a backup leaves when its manifest upload fails, once it
// is older than the grace period, and keeps one newer than that. A
// directory with a manifest is never deleted, however old.
func TestPruneDeletesMetadataDirWithoutManifestOlderThanGracePeriod(
	t *testing.T,
) {
	log.Initialize(log.Config{})
	t.Parallel()

	ctx := context.Background()
	storeDir := t.TempDir()

	store, err := storage.NewFileStorer(storeDir)
	require.NoError(t, err)

	const (
		oldID      = "testhost_home_2026-01-01T00:00:00Z"
		newID      = "testhost_home_2026-01-02T00:00:00Z"
		completeID = "testhost_home_2026-01-03T00:00:00Z"
	)

	oldDB := metadataObjectKey(oldID, "db.zst.age")
	newDB := metadataObjectKey(newID, "db.zst.age")
	completeDB := metadataObjectKey(completeID, "db.zst.age")
	completeManifest := metadataObjectKey(completeID, "manifest.json.zst")

	manifest, err := snapshot.EncodeManifest(&snapshot.Manifest{
		SnapshotID: snapshot.RemoteSnapshotKey(completeID),
	}, 3)
	require.NoError(t, err)

	for _, key := range []string{oldDB, newDB, completeDB} {
		require.NoError(t, store.Put(ctx, key, strings.NewReader("db")))
	}

	require.NoError(t, store.Put(ctx, completeManifest,
		bytes.NewReader(manifest)))

	gracePeriod := time.Hour
	beforeGracePeriod := time.Now().Add(-gracePeriod - time.Minute)

	for _, key := range []string{oldDB, completeDB, completeManifest} {
		require.NoError(t, os.Chtimes(filepath.Join(storeDir, key),
			beforeGracePeriod, beforeGracePeriod))
	}

	stdout := &bytes.Buffer{}
	v := &vaultik.Vaultik{
		Config:  &config.Config{PruneGracePeriod: gracePeriod},
		Storage: store,
		Stdout:  stdout,
		UI:      ui.NewWithColor(stdout, false),
	}
	v.SetContext(ctx)

	require.NoError(t, v.PruneBlobs(&vaultik.PruneOptions{JSON: true}))

	_, err = store.Stat(ctx, oldDB)
	require.ErrorIs(t, err, storage.ErrNotFound,
		"a directory with no manifest older than the grace period "+
			"must be deleted")

	for _, key := range []string{newDB, completeDB, completeManifest} {
		_, err = store.Stat(ctx, key)
		require.NoError(t, err, "%s must be kept", key)
	}

	var result vaultik.PruneBlobsResult

	require.NoError(t, json.Unmarshal(stdout.Bytes(), &result))
	assert.Equal(t, 1, result.MetadataDirsDeleted)
}

// TestPruneKeepsMetadataDirClaimedUnknownAgeOrNotRemoteKey checks that
// prune --force keeps a directory under metadata/ with no manifest when a
// local snapshot record claims it, when the listing gives no time for an
// object in it, or when its name is not a remote key. A fourth such
// directory is named, deleted and reported, although there are no
// unreferenced blobs to delete.
func TestPruneKeepsMetadataDirClaimedUnknownAgeOrNotRemoteKey(t *testing.T) {
	log.Initialize(log.Config{})
	t.Parallel()

	ctx := context.Background()
	env := newListEnv(t)

	const (
		claimedID = "testhost_home_2026-01-01T00:00:00Z"
		leftID    = "testhost_home_2026-01-03T00:00:00Z"
	)

	env.addLocal(t, claimedID, time.Now().Add(-time.Hour))

	claimedDB := metadataObjectKey(claimedID, "db.zst.age")
	unknownAgeDB := metadataObjectKey("testhost_home_2026-01-02T00:00:00Z",
		"db.zst.age")
	leftDB := metadataObjectKey(leftID, "db.zst.age")
	notRemoteKeyDB := "metadata/not-a-remote-key/db.zst.age"

	for _, key := range []string{claimedDB, leftDB, notRemoteKeyDB} {
		require.NoError(t, env.store.Put(ctx, key, strings.NewReader("db")))
	}

	// Written into the mock store's map directly rather than through
	// Put, so its listing gives no time.
	env.store.data[unknownAgeDB] = []byte("db")

	require.NoError(t, env.v.PruneBlobs(&vaultik.PruneOptions{Force: true}))

	assert.True(t, env.store.hasKey(claimedDB),
		"a directory a local snapshot record claims must be kept")
	assert.True(t, env.store.hasKey(unknownAgeDB),
		"a directory holding an object of unknown age must be kept")
	assert.True(t, env.store.hasKey(notRemoteKeyDB),
		"a directory whose name is not a remote key must be kept")
	assert.False(t, env.store.hasKey(leftDB),
		"a directory with no manifest, unclaimed and old, must be deleted")

	output := env.stdout.String()

	assert.Contains(t, output, "Found 1 metadata director(ies) left by "+
		"backups that stopped before their manifest:")
	assert.Contains(t, output,
		"metadata/"+snapshot.RemoteSnapshotKey(leftID)+"/")
	assert.NotContains(t, output, "not-a-remote-key")
	assert.Contains(t, output,
		"Deleted 1 metadata director(ies) with no manifest.")
	assert.NotContains(t, output, "No unreferenced blobs to remove.")
}

// TestPruneDeclinedKeepsMetadataDirWithoutManifest checks that the prompt
// names a directory under metadata/ with no manifest that prune is about
// to delete, and that answering no keeps it.
func TestPruneDeclinedKeepsMetadataDirWithoutManifest(t *testing.T) {
	log.Initialize(log.Config{})
	t.Parallel()

	env := newListEnv(t)

	const leftID = "testhost_home_2026-01-01T00:00:00Z"

	leftDB := metadataObjectKey(leftID, "db.zst.age")
	require.NoError(t, env.store.Put(context.Background(), leftDB,
		strings.NewReader("db")))

	env.v.Stdin = strings.NewReader("n\n")

	require.NoError(t, env.v.PruneBlobs(&vaultik.PruneOptions{}))

	assert.True(t, env.store.hasKey(leftDB),
		"a declined prune must keep the directory")

	output := env.stdout.String()

	assert.Contains(t, output,
		"  metadata/"+snapshot.RemoteSnapshotKey(leftID)+"/\n")
	assert.Contains(t, output, "Delete 1 metadata director(ies)? [y/N] ")
	assert.Contains(t, output, "Cancelled")
	assert.NotContains(t, output, "Deleted")
}

// TestPruneFailedMetadataDirDeleteReturnsError checks that prune --json
// counts a directory under metadata/ with no manifest that it cannot
// delete, and then returns an error, so the command exits non-zero.
func TestPruneFailedMetadataDirDeleteReturnsError(t *testing.T) {
	log.Initialize(log.Config{})
	t.Parallel()

	env := newListEnv(t)

	leftDB := metadataObjectKey("testhost_home_2026-01-01T00:00:00Z",
		"db.zst.age")
	require.NoError(t, env.store.Put(context.Background(), leftDB,
		strings.NewReader("db")))

	store := faultstore.New(env.store)
	store.OnDelete = func(key string) bool {
		return strings.HasPrefix(key, "metadata/")
	}
	env.v.Storage = store

	err := env.v.PruneBlobs(&vaultik.PruneOptions{JSON: true})

	require.ErrorContains(t, err,
		"1 metadata director(ies) with no manifest could not be deleted")
	assert.True(t, env.store.hasKey(leftDB))

	var result vaultik.PruneBlobsResult

	require.NoError(t, json.Unmarshal(env.stdout.Bytes(), &result),
		"stdout must hold the JSON document, got:\n%s", env.stdout.String())
	assert.Equal(t, 1, result.MetadataDirsFailed)
	assert.Equal(t, 0, result.MetadataDirsDeleted)
}