vaultik/internal/vaultik/restore_another_machine_test.go

package vaultik_test

import (
	"bytes"
	"context"
	"io"
	"path/filepath"
	"testing"

	"github.com/spf13/afero"
	"github.com/stretchr/testify/assert"
	"github.com/stretchr/testify/require"
	"sneak.berlin/go/vaultik/internal/config"
	"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/ui"
	"sneak.berlin/go/vaultik/internal/vaultik"
)

// TestRestoreOnAnotherMachine proves the disaster-recovery path: a host
// that has only the vaultik binary, the age secret key, and the storage
// credentials — no local index, a different hostname, and no
// age_recipients configured — can list, restore, and verify a snapshot
// straight from the destination store.
//
// The backup half writes a snapshot with one index and hostname. The
// restore half throws that index away entirely: a fresh, empty index and
// a config that shares nothing with the original but the storage location
// and the secret key. If restore or verify needed the original local
// index — or the human snapshot ID that only that index holds — this test
// could not run, because the recovery host can know neither.
func TestRestoreOnAnotherMachine(t *testing.T) {
	log.Initialize(log.Config{})
	t.Parallel()

	fs := afero.NewOsFs()
	tempDir := t.TempDir()

	dataDir := filepath.Join(tempDir, "source")
	storeDir := filepath.Join(tempDir, "remote")
	restoreDir := filepath.Join(tempDir, "restored")
	dbPath := filepath.Join(tempDir, "index.sqlite")

	chunkSize := int64(64 * 1024)
	maxBlobSize := int64(512 * 1024)

	sourceFiles := writeRecoverySourceTree(t, fs, dataDir, chunkSize)

	ctx := context.Background()

	// Backup host: one index, hostname test-host, age_recipients set.
	// runFileStorageBackup closes the index before returning, so nothing
	// below can lean on it.
	_, storer, originalID := runFileStorageBackup(
		ctx, t, fs, dataDir, storeDir, dbPath, chunkSize, maxBlobSize)

	// Recovery host: a fresh empty index, a different hostname, and no
	// age_recipients — only the secret key and the same storage location.
	recovery, stdout := newRecoveryHost(ctx, t, fs, storer)

	// The recovery index really is empty. This is the assertion that makes
	// the test a guard against restore quietly depending on the original
	// index: if it did, an empty index would make restore fail.
	localSnaps, err := recovery.Repositories.Snapshots.ListRecent(ctx, 100)
	require.NoError(t, err)
	require.Empty(t, localSnaps, "recovery host must start with no local index")

	// List: the snapshot shows up as remote-only, identified by its remote
	// key, with no recoverable human ID.
	require.NoError(t, recovery.ListSnapshots(true))

	rows := decodeListJSON(t, stdout.String())
	require.Len(t, rows, 1)

	remote := rows[0]
	assert.False(t, remote.LocallyTracked, "snapshot must be remote-only here")
	assert.Empty(t, remote.ID, "the human ID is unknown to the recovery host")
	require.Len(t, remote.RemoteKey, 64)
	assert.Equal(t, snapshot.RemoteSnapshotKey(originalID), remote.RemoteKey,
		"the listed key is the hashed snapshot ID")

	// Restore driven by the abbreviated identifier the table prints (the
	// first 12 hex of the remote key), then deep-verify from the store
	// keyed by the full remote key. Both are what a recovery host can know.
	require.NoError(t, recovery.Restore(&vaultik.RestoreOptions{
		SnapshotID: remote.RemoteKey[:12],
		TargetDir:  restoreDir,
		Verify:     true,
	}))
	require.NoError(t, recovery.RunDeepVerify(
		remote.RemoteKey, &vaultik.VerifyOptions{Deep: true}))

	assertRestoredTreeMatches(t, fs, restoreDir, sourceFiles)
}

// writeRecoverySourceTree writes a small source tree spanning several
// chunks (so restore reassembles real multi-chunk files) and returns the
// content keyed by absolute path.
func writeRecoverySourceTree(
	t *testing.T, fs afero.Fs, dataDir string, chunkSize int64,
) map[string][]byte {
	t.Helper()

	sourceFiles := map[string][]byte{
		filepath.Join(dataDir, "notes.txt"):        []byte("recover me"),
		filepath.Join(dataDir, "sub", "big.bin"):   bytesPattern("big-", int(chunkSize*3)),
		filepath.Join(dataDir, "sub", "small.bin"): bytesPattern("small-", 128),
	}

	for path, content := range sourceFiles {
		require.NoError(t, fs.MkdirAll(filepath.Dir(path), 0o755))
		require.NoError(t, afero.WriteFile(fs, path, content, 0o644))
	}

	return sourceFiles
}

// newRecoveryHost builds the Vaultik a replacement machine would run: an
// empty in-memory index, a hostname different from the backup host, no
// age_recipients, and only the secret key plus the shared storer. It
// returns the instance and the buffer its stdout is wired to.
func newRecoveryHost(
	ctx context.Context, t *testing.T, fs afero.Fs, storer storage.Storer,
) (*vaultik.Vaultik, *bytes.Buffer) {
	t.Helper()

	recoveryDB, err := database.New(ctx, ":memory:")
	require.NoError(t, err)
	t.Cleanup(func() { _ = recoveryDB.Close() })

	stdout := &bytes.Buffer{}

	recovery := &vaultik.Vaultik{
		Config: &config.Config{
			AgeSecretKey: testAgeSecretKey,
			Hostname:     "recovery-host",
		},
		Storage:      storer,
		Fs:           fs,
		Repositories: database.NewRepositories(recoveryDB),
		DB:           recoveryDB,
		Stdout:       stdout,
		Stderr:       io.Discard,
		UI:           ui.NewWithColor(io.Discard, false),
	}
	recovery.SetContext(ctx)

	return recovery, stdout
}

// assertRestoredTreeMatches byte-compares every restored file against its
// source content.
func assertRestoredTreeMatches(
	t *testing.T, fs afero.Fs, restoreDir string, sourceFiles map[string][]byte,
) {
	t.Helper()

	for origPath, expected := range sourceFiles {
		restored := filepath.Join(restoreDir, origPath)
		got, err := afero.ReadFile(fs, restored)
		require.NoErrorf(t, err, "restored file missing: %s", restored)
		require.Truef(t, bytes.Equal(got, expected),
			"byte mismatch for %s", origPath)
	}
}