Add deterministic deduplication, rclone backend, and database purge command

- Implement deterministic blob hashing using double SHA256 of uncompressed
  plaintext data, enabling deduplication even after local DB is cleared
- Add Stat() check before blob upload to skip existing blobs in storage
- Add rclone storage backend for additional remote storage options
- Add 'vaultik database purge' command to erase local state DB
- Add 'vaultik remote check' command to verify remote connectivity
- Show configured snapshots in 'vaultik snapshot list' output
- Skip macOS resource fork files (._*) when listing remote snapshots
- Use multi-threaded zstd compression (CPUs - 2 threads)
- Add writer tests for double hashing behavior
This commit is contained in:
2026-01-28 15:50:17 -08:00
parent bdaaadf990
commit 470bf648c4
26 changed files with 2966 additions and 777 deletions

View File

@@ -5,6 +5,8 @@ import (
"context"
"database/sql"
"io"
"os"
"path/filepath"
"sync"
"testing"
"time"
@@ -15,6 +17,7 @@ import (
"git.eeqj.de/sneak/vaultik/internal/snapshot"
"git.eeqj.de/sneak/vaultik/internal/storage"
"git.eeqj.de/sneak/vaultik/internal/types"
"git.eeqj.de/sneak/vaultik/internal/vaultik"
"github.com/spf13/afero"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
@@ -403,3 +406,138 @@ func TestBackupAndVerify(t *testing.T) {
t.Logf("Backup and verify test completed successfully")
}
// TestBackupAndRestore tests the full backup and restore workflow
// This test verifies that the restore code correctly handles the binary SQLite
// database format that is exported by the snapshot manager.
func TestBackupAndRestore(t *testing.T) {
// Initialize logger
log.Initialize(log.Config{})
// Create real temp directory for the database (SQLite needs real filesystem)
realTempDir, err := os.MkdirTemp("", "vaultik-test-")
require.NoError(t, err)
defer func() { _ = os.RemoveAll(realTempDir) }()
// Use real OS filesystem for this test
fs := afero.NewOsFs()
// Create test directory structure and files
dataDir := filepath.Join(realTempDir, "data")
testFiles := map[string]string{
filepath.Join(dataDir, "file1.txt"): "This is file 1 content",
filepath.Join(dataDir, "file2.txt"): "This is file 2 content with more data",
filepath.Join(dataDir, "subdir", "file3.txt"): "This is file 3 in a subdirectory",
}
// Create directories and files
for path, content := range testFiles {
dir := filepath.Dir(path)
if err := fs.MkdirAll(dir, 0755); err != nil {
t.Fatalf("failed to create directory %s: %v", dir, err)
}
if err := afero.WriteFile(fs, path, []byte(content), 0644); err != nil {
t.Fatalf("failed to create test file %s: %v", path, err)
}
}
ctx := context.Background()
// Create mock storage
mockStorage := NewMockStorer()
// Test keypair
agePublicKey := "age1ezrjmfpwsc95svdg0y54mums3zevgzu0x0ecq2f7tp8a05gl0sjq9q9wjg"
ageSecretKey := "AGE-SECRET-KEY-19CR5YSFW59HM4TLD6GXVEDMZFTVVF7PPHKUT68TXSFPK7APHXA2QS2NJA5"
// Create database file
dbPath := filepath.Join(realTempDir, "test.db")
db, err := database.New(ctx, dbPath)
require.NoError(t, err)
defer func() { _ = db.Close() }()
repos := database.NewRepositories(db)
// Create config for snapshot manager
cfg := &config.Config{
AgeSecretKey: ageSecretKey,
AgeRecipients: []string{agePublicKey},
CompressionLevel: 3,
}
// Create snapshot manager
sm := snapshot.NewSnapshotManager(snapshot.SnapshotManagerParams{
Repos: repos,
Storage: mockStorage,
Config: cfg,
})
sm.SetFilesystem(fs)
// Create scanner
scanner := snapshot.NewScanner(snapshot.ScannerConfig{
FS: fs,
Storage: mockStorage,
ChunkSize: int64(16 * 1024),
MaxBlobSize: int64(100 * 1024),
CompressionLevel: 3,
AgeRecipients: []string{agePublicKey},
Repositories: repos,
})
// Create a snapshot
snapshotID, err := sm.CreateSnapshot(ctx, "test-host", "test-version", "test-git")
require.NoError(t, err)
t.Logf("Created snapshot: %s", snapshotID)
// Run the backup (scan)
result, err := scanner.Scan(ctx, dataDir, snapshotID)
require.NoError(t, err)
t.Logf("Scan complete: %d files, %d blobs", result.FilesScanned, result.BlobsCreated)
// Complete the snapshot
err = sm.CompleteSnapshot(ctx, snapshotID)
require.NoError(t, err)
// Export snapshot metadata (this uploads db.zst.age and manifest.json.zst)
err = sm.ExportSnapshotMetadata(ctx, dbPath, snapshotID)
require.NoError(t, err)
t.Logf("Exported snapshot metadata")
// Verify metadata was uploaded
keys, err := mockStorage.List(ctx, "metadata/")
require.NoError(t, err)
t.Logf("Metadata keys: %v", keys)
assert.GreaterOrEqual(t, len(keys), 2, "Should have at least db.zst.age and manifest.json.zst")
// Close the source database
err = db.Close()
require.NoError(t, err)
// Create Vaultik instance for restore
vaultikApp := &vaultik.Vaultik{
Config: cfg,
Storage: mockStorage,
Fs: fs,
Stdout: io.Discard,
Stderr: io.Discard,
}
vaultikApp.SetContext(ctx)
// Try to restore - this should work with binary SQLite format
restoreDir := filepath.Join(realTempDir, "restored")
err = vaultikApp.Restore(&vaultik.RestoreOptions{
SnapshotID: snapshotID,
TargetDir: restoreDir,
})
require.NoError(t, err, "Restore should succeed with binary SQLite database format")
// Verify restored files match originals
for origPath, expectedContent := range testFiles {
restoredPath := filepath.Join(restoreDir, origPath)
restoredContent, err := afero.ReadFile(fs, restoredPath)
require.NoError(t, err, "Should be able to read restored file: %s", restoredPath)
assert.Equal(t, expectedContent, string(restoredContent), "Restored content should match original for: %s", origPath)
}
t.Log("Backup and restore test completed successfully")
}