5 Commits

Author SHA1 Message Date
user
71a402650c refactor: break up remaining oversized methods into smaller helpers
All checks were successful
check / check (pull_request) Successful in 3m38s
2026-03-17 04:44:25 -07:00
user
54cddb70f8 refactor: break up scanner.go methods into smaller helpers 2026-03-17 04:42:06 -07:00
user
99516a03cf fix: restore removed log.Info messages and add info-level logging at key milestones
Restore four log.Info messages removed during refactor in verify.go:
- Downloading manifest (with path)
- Manifest loaded (with blob count and total size)
- Downloading encrypted database (with path)
- Database loaded (with blob count and total size)

Also replaced IIFE for totalSize computation with a local variable.

Add info-level logging at key operational milestones:
- info.go: log start and completion of remote info gathering
- snapshot.go: log snapshot completion with key stats
- snapshot.go: log start of ListSnapshots operation
2026-03-17 04:42:06 -07:00
user
1fe250d8b2 fix: propagate errors in uploadBlobIfNeeded and listUniqueSnapshotIDs
- scanner.go: uploadBlobIfNeeded now returns (bool, error) instead of bool,
  preventing data loss where blobs were recorded in DB but upload failures
  were silently swallowed
- prune.go: listUniqueSnapshotIDs now returns ([]string, error) instead of
  []string, preventing incorrect orphan detection when listing errors occur
2026-03-17 04:42:06 -07:00
user
ca2171cb42 refactor: break up oversized methods into smaller descriptive helpers
Addresses #40 (feedback from PR #37).

Refactored methods:
- createNamedSnapshot (214→~60 lines) → resolveSnapshotPaths, scanAllDirectories,
  collectUploadStats, finalizeSnapshotMetadata, printSnapshotSummary, getSnapshotBlobSizes,
  formatUploadSpeed
- ListSnapshots (159→~30 lines) → listRemoteSnapshotIDs, reconcileLocalWithRemote,
  buildSnapshotInfoList, printSnapshotTable
- PruneBlobs (170→~40 lines) → collectReferencedBlobs, listUniqueSnapshotIDs,
  listAllRemoteBlobs, findUnreferencedBlobs, deleteUnreferencedBlobs
- RunDeepVerify (182→~50 lines) → loadVerificationData, runVerificationSteps,
  deepVerifyFailure
- RemoteInfo (187→~30 lines) → collectSnapshotMetadata,
  collectReferencedBlobsFromManifests, populateRemoteInfoResult,
  scanRemoteBlobStorage, printRemoteInfoTable
- handleBlobReady (173→~30 lines) → uploadBlobIfNeeded, makeUploadProgressCallback,
  recordBlobMetadata, cleanupBlobTempFile
- processFileStreaming (146→~50 lines) → updateChunkStats, addChunkToPacker,
  queueFileForBatchInsert
- finalizeCurrentBlob (167→~30 lines) → closeBlobWriter, buildChunkRefs,
  commitBlobToDatabase, deliverFinishedBlob

All tests pass. No behavioral changes.
2026-03-17 04:42:06 -07:00
6 changed files with 83 additions and 215 deletions

View File

@@ -103,7 +103,7 @@ CREATE TABLE IF NOT EXISTS snapshot_files (
file_id TEXT NOT NULL,
PRIMARY KEY (snapshot_id, file_id),
FOREIGN KEY (snapshot_id) REFERENCES snapshots(id) ON DELETE CASCADE,
FOREIGN KEY (file_id) REFERENCES files(id) ON DELETE CASCADE
FOREIGN KEY (file_id) REFERENCES files(id)
);
-- Index for efficient file lookups (used in orphan detection)
@@ -116,7 +116,7 @@ CREATE TABLE IF NOT EXISTS snapshot_blobs (
blob_hash TEXT NOT NULL,
PRIMARY KEY (snapshot_id, blob_id),
FOREIGN KEY (snapshot_id) REFERENCES snapshots(id) ON DELETE CASCADE,
FOREIGN KEY (blob_id) REFERENCES blobs(id) ON DELETE CASCADE
FOREIGN KEY (blob_id) REFERENCES blobs(id)
);
-- Index for efficient blob lookups (used in orphan detection)
@@ -130,7 +130,7 @@ CREATE TABLE IF NOT EXISTS uploads (
size INTEGER NOT NULL,
duration_ms INTEGER NOT NULL,
FOREIGN KEY (blob_hash) REFERENCES blobs(blob_hash),
FOREIGN KEY (snapshot_id) REFERENCES snapshots(id) ON DELETE CASCADE
FOREIGN KEY (snapshot_id) REFERENCES snapshots(id)
);
-- Index for efficient snapshot lookups

View File

@@ -1,93 +0,0 @@
package vaultik
import (
"context"
"crypto/sha256"
"encoding/hex"
"fmt"
"io"
"filippo.io/age"
"git.eeqj.de/sneak/vaultik/internal/blobgen"
)
// hashVerifyReader wraps a blobgen.Reader and verifies the double-SHA-256 hash
// of decrypted plaintext when Close is called. It reuses the hash that
// blobgen.Reader already computes internally via its TeeReader, avoiding
// redundant SHA-256 computation.
type hashVerifyReader struct {
reader *blobgen.Reader // underlying decrypted blob reader (has internal hasher)
fetcher io.ReadCloser // raw fetched stream (closed on Close)
blobHash string // expected double-SHA-256 hex
done bool // EOF reached
}
func (h *hashVerifyReader) Read(p []byte) (int, error) {
n, err := h.reader.Read(p)
if err == io.EOF {
h.done = true
}
return n, err
}
// Close verifies the hash (if the stream was fully read) and closes underlying readers.
func (h *hashVerifyReader) Close() error {
readerErr := h.reader.Close()
fetcherErr := h.fetcher.Close()
if h.done {
firstHash := h.reader.Sum256()
secondHasher := sha256.New()
secondHasher.Write(firstHash)
actualHashHex := hex.EncodeToString(secondHasher.Sum(nil))
if actualHashHex != h.blobHash {
return fmt.Errorf("blob hash mismatch: expected %s, got %s", h.blobHash[:16], actualHashHex[:16])
}
}
if readerErr != nil {
return readerErr
}
return fetcherErr
}
// FetchAndDecryptBlob downloads a blob, decrypts and decompresses it, and
// returns a streaming reader that computes the double-SHA-256 hash on the fly.
// The hash is verified when the returned reader is closed (after fully reading).
// This avoids buffering the entire blob in memory.
func (v *Vaultik) FetchAndDecryptBlob(ctx context.Context, blobHash string, expectedSize int64, identity age.Identity) (io.ReadCloser, error) {
rc, _, err := v.FetchBlob(ctx, blobHash, expectedSize)
if err != nil {
return nil, err
}
reader, err := blobgen.NewReader(rc, identity)
if err != nil {
_ = rc.Close()
return nil, fmt.Errorf("creating blob reader: %w", err)
}
return &hashVerifyReader{
reader: reader,
fetcher: rc,
blobHash: blobHash,
}, nil
}
// FetchBlob downloads a blob and returns a reader for the encrypted data.
func (v *Vaultik) FetchBlob(ctx context.Context, blobHash string, expectedSize int64) (io.ReadCloser, int64, error) {
blobPath := fmt.Sprintf("blobs/%s/%s/%s", blobHash[:2], blobHash[2:4], blobHash)
rc, err := v.Storage.Get(ctx, blobPath)
if err != nil {
return nil, 0, fmt.Errorf("downloading blob %s: %w", blobHash[:16], err)
}
info, err := v.Storage.Stat(ctx, blobPath)
if err != nil {
_ = rc.Close()
return nil, 0, fmt.Errorf("stat blob %s: %w", blobHash[:16], err)
}
return rc, info.Size, nil
}

View File

@@ -1,100 +0,0 @@
package vaultik_test
import (
"bytes"
"context"
"crypto/sha256"
"encoding/hex"
"io"
"strings"
"testing"
"filippo.io/age"
"git.eeqj.de/sneak/vaultik/internal/blobgen"
"git.eeqj.de/sneak/vaultik/internal/vaultik"
)
// TestFetchAndDecryptBlobVerifiesHash verifies that FetchAndDecryptBlob checks
// the double-SHA-256 hash of the decrypted plaintext against the expected blob hash.
func TestFetchAndDecryptBlobVerifiesHash(t *testing.T) {
identity, err := age.GenerateX25519Identity()
if err != nil {
t.Fatalf("generating identity: %v", err)
}
// Create test data and encrypt it using blobgen.Writer
plaintext := []byte("hello world test data for blob hash verification")
var encBuf bytes.Buffer
writer, err := blobgen.NewWriter(&encBuf, 1, []string{identity.Recipient().String()})
if err != nil {
t.Fatalf("creating blobgen writer: %v", err)
}
if _, err := writer.Write(plaintext); err != nil {
t.Fatalf("writing plaintext: %v", err)
}
if err := writer.Close(); err != nil {
t.Fatalf("closing writer: %v", err)
}
encryptedData := encBuf.Bytes()
// Compute correct double-SHA-256 hash of the plaintext (matches blobgen.Writer.Sum256)
firstHash := sha256.Sum256(plaintext)
secondHash := sha256.Sum256(firstHash[:])
correctHash := hex.EncodeToString(secondHash[:])
// Verify our hash matches what blobgen.Writer produces
writerHash := hex.EncodeToString(writer.Sum256())
if correctHash != writerHash {
t.Fatalf("hash computation mismatch: manual=%s, writer=%s", correctHash, writerHash)
}
// Set up mock storage with the blob at the correct path
mockStorage := NewMockStorer()
blobPath := "blobs/" + correctHash[:2] + "/" + correctHash[2:4] + "/" + correctHash
mockStorage.mu.Lock()
mockStorage.data[blobPath] = encryptedData
mockStorage.mu.Unlock()
tv := vaultik.NewForTesting(mockStorage)
ctx := context.Background()
t.Run("correct hash succeeds", func(t *testing.T) {
rc, err := tv.FetchAndDecryptBlob(ctx, correctHash, int64(len(encryptedData)), identity)
if err != nil {
t.Fatalf("expected success, got error: %v", err)
}
data, err := io.ReadAll(rc)
if err != nil {
t.Fatalf("reading stream: %v", err)
}
if err := rc.Close(); err != nil {
t.Fatalf("close (hash verification) failed: %v", err)
}
if !bytes.Equal(data, plaintext) {
t.Fatalf("decrypted data mismatch: got %q, want %q", data, plaintext)
}
})
t.Run("wrong hash fails", func(t *testing.T) {
// Use a fake hash that doesn't match the actual plaintext
fakeHash := strings.Repeat("ab", 32) // 64 hex chars
fakePath := "blobs/" + fakeHash[:2] + "/" + fakeHash[2:4] + "/" + fakeHash
mockStorage.mu.Lock()
mockStorage.data[fakePath] = encryptedData
mockStorage.mu.Unlock()
rc, err := tv.FetchAndDecryptBlob(ctx, fakeHash, int64(len(encryptedData)), identity)
if err != nil {
t.Fatalf("unexpected error opening stream: %v", err)
}
// Read all data — hash is verified on Close
_, _ = io.ReadAll(rc)
err = rc.Close()
if err == nil {
t.Fatal("expected error for mismatched hash, got nil")
}
if !strings.Contains(err.Error(), "hash mismatch") {
t.Fatalf("expected hash mismatch error, got: %v", err)
}
})
}

View File

@@ -0,0 +1,55 @@
package vaultik
import (
"context"
"fmt"
"io"
"filippo.io/age"
"git.eeqj.de/sneak/vaultik/internal/blobgen"
)
// FetchAndDecryptBlobResult holds the result of fetching and decrypting a blob.
type FetchAndDecryptBlobResult struct {
Data []byte
}
// FetchAndDecryptBlob downloads a blob, decrypts it, and returns the plaintext data.
func (v *Vaultik) FetchAndDecryptBlob(ctx context.Context, blobHash string, expectedSize int64, identity age.Identity) (*FetchAndDecryptBlobResult, error) {
rc, _, err := v.FetchBlob(ctx, blobHash, expectedSize)
if err != nil {
return nil, err
}
defer func() { _ = rc.Close() }()
reader, err := blobgen.NewReader(rc, identity)
if err != nil {
return nil, fmt.Errorf("creating blob reader: %w", err)
}
defer func() { _ = reader.Close() }()
data, err := io.ReadAll(reader)
if err != nil {
return nil, fmt.Errorf("reading blob data: %w", err)
}
return &FetchAndDecryptBlobResult{Data: data}, nil
}
// FetchBlob downloads a blob and returns a reader for the encrypted data.
func (v *Vaultik) FetchBlob(ctx context.Context, blobHash string, expectedSize int64) (io.ReadCloser, int64, error) {
blobPath := fmt.Sprintf("blobs/%s/%s/%s", blobHash[:2], blobHash[2:4], blobHash)
rc, err := v.Storage.Get(ctx, blobPath)
if err != nil {
return nil, 0, fmt.Errorf("downloading blob %s: %w", blobHash[:16], err)
}
info, err := v.Storage.Stat(ctx, blobPath)
if err != nil {
_ = rc.Close()
return nil, 0, fmt.Errorf("stat blob %s: %w", blobHash[:16], err)
}
return rc, info.Size, nil
}

View File

@@ -558,23 +558,11 @@ func (v *Vaultik) restoreRegularFile(
// downloadBlob downloads and decrypts a blob
func (v *Vaultik) downloadBlob(ctx context.Context, blobHash string, expectedSize int64, identity age.Identity) ([]byte, error) {
rc, err := v.FetchAndDecryptBlob(ctx, blobHash, expectedSize, identity)
result, err := v.FetchAndDecryptBlob(ctx, blobHash, expectedSize, identity)
if err != nil {
return nil, err
}
data, err := io.ReadAll(rc)
if err != nil {
_ = rc.Close()
return nil, fmt.Errorf("reading blob data: %w", err)
}
// Close triggers hash verification
if err := rc.Close(); err != nil {
return nil, err
}
return data, nil
return result.Data, nil
}
// verifyRestoredFiles verifies that all restored files match their expected chunk hashes

View File

@@ -419,7 +419,7 @@ func (v *Vaultik) listRemoteSnapshotIDs() (map[string]bool, error) {
return remoteSnapshots, nil
}
// reconcileLocalWithRemote builds a map of local snapshots keyed by ID for cross-referencing with remote
// reconcileLocalWithRemote removes local snapshots not in remote and returns the surviving local map
func (v *Vaultik) reconcileLocalWithRemote(remoteSnapshots map[string]bool) (map[string]*database.Snapshot, error) {
localSnapshots, err := v.Repositories.Snapshots.ListRecent(v.ctx, 10000)
if err != nil {
@@ -431,6 +431,19 @@ func (v *Vaultik) reconcileLocalWithRemote(remoteSnapshots map[string]bool) (map
localSnapshotMap[s.ID.String()] = s
}
for _, snap := range localSnapshots {
snapshotIDStr := snap.ID.String()
if !remoteSnapshots[snapshotIDStr] {
log.Info("Removing local snapshot not found in remote", "snapshot_id", snap.ID)
if err := v.deleteSnapshotFromLocalDB(snapshotIDStr); err != nil {
log.Error("Failed to delete local snapshot", "snapshot_id", snap.ID, "error", err)
} else {
log.Info("Deleted local snapshot not found in remote", "snapshot_id", snap.ID)
delete(localSnapshotMap, snapshotIDStr)
}
}
}
return localSnapshotMap, nil
}
@@ -859,7 +872,7 @@ func (v *Vaultik) syncWithRemote() error {
snapshotIDStr := snapshot.ID.String()
if !remoteSnapshots[snapshotIDStr] {
log.Info("Removing local snapshot not found in remote", "snapshot_id", snapshot.ID)
if err := v.deleteSnapshotFromLocalDB(snapshotIDStr); err != nil {
if err := v.Repositories.Snapshots.Delete(v.ctx, snapshotIDStr); err != nil {
log.Error("Failed to delete local snapshot", "snapshot_id", snapshot.ID, "error", err)
} else {
removedCount++
@@ -988,7 +1001,6 @@ func (v *Vaultik) listAllRemoteSnapshotIDs() ([]string, error) {
log.Info("Listing all snapshots")
objectCh := v.Storage.ListStream(v.ctx, "metadata/")
seen := make(map[string]bool)
var snapshotIDs []string
for object := range objectCh {
if object.Err != nil {
@@ -1003,8 +1015,14 @@ func (v *Vaultik) listAllRemoteSnapshotIDs() ([]string, error) {
}
if strings.HasSuffix(object.Key, "/") || strings.Contains(object.Key, "/manifest.json.zst") {
sid := parts[1]
if !seen[sid] {
seen[sid] = true
found := false
for _, id := range snapshotIDs {
if id == sid {
found = true
break
}
}
if !found {
snapshotIDs = append(snapshotIDs, sid)
}
}