Compare commits

..

10 Commits

Author SHA1 Message Date
clawbot
e8b4ef80ab fix: resolve rebase conflicts, fix errcheck issues, implement FetchAndDecryptBlob 2026-02-19 23:42:53 -08:00
0b0398b3e9 feat: implement --prune flag on snapshot create (closes #4)
The --prune flag on 'snapshot create' was accepted but silently did nothing
(TODO stub). This connects it to actually:

1. Purge old snapshots (keeping only the latest) via PurgeSnapshots
2. Remove unreferenced blobs from storage via PruneBlobs

The pruning runs after all snapshots complete successfully, not per-snapshot.
Both operations use --force mode (no interactive confirmation) since --prune
is an explicit opt-in flag.

Moved the prune logic from createNamedSnapshot (per-snapshot) to
CreateSnapshot (after all snapshots), which is the correct location.
2026-02-19 23:37:11 -08:00
user
09f23a7ef8 refactor: add helper wrappers for stdin/stdout/stderr IO
Address all four review concerns on PR #31:

1. Fix missed bare fmt.Println() in VerifySnapshotWithOptions (line 620)
2. Replace all direct fmt.Fprintf(v.Stdout,...) / fmt.Fprintln(v.Stdout,...) /
   fmt.Fscanln(v.Stdin,...) calls with helper methods: printfStdout(),
   printlnStdout(), printfStderr(), scanStdin()
3. Route progress bar and stderr output through v.Stderr instead of os.Stderr
   in restore.go (concern #4: v.Stderr now actually used)
4. Rename exported Outputf to unexported printfStdout (YAGNI: only helpers
   actually used are created)
2026-02-19 23:37:11 -08:00
clawbot
28614410a7 fix: use v.Stdout/v.Stdin instead of os.Stdout for all user-facing output
Multiple methods wrote directly to os.Stdout instead of using the injectable
v.Stdout writer, breaking the TestVaultik testing infrastructure and making
output impossible to capture or redirect.

Fixed in: ListSnapshots, PurgeSnapshots, VerifySnapshotWithOptions,
PruneBlobs, outputPruneBlobsJSON, outputRemoveJSON, ShowInfo, RemoteInfo.
2026-02-19 23:37:07 -08:00
b7c094c5e0 fix: replace in-memory blob cache with disk-based LRU cache (closes #29)
Blobs are typically hundreds of megabytes and should not be held in memory.
The new blobDiskCache writes cached blobs to a temp directory, tracks LRU
order in memory, and evicts least-recently-used files when total disk usage
exceeds a configurable limit (default 10 GiB).

Design:
- Blobs written to os.TempDir()/vaultik-blobcache-*/<hash>
- Doubly-linked list for O(1) LRU promotion/eviction
- ReadAt support for reading chunk slices without loading full blob
- Temp directory cleaned up on Close()
- Oversized entries (> maxBytes) silently skipped

Also adds blob_fetch_stub.go with stub implementations for
FetchAndDecryptBlob/FetchBlob to fix pre-existing compile errors.
2026-02-19 23:36:44 -08:00
825f25da58 Merge pull request 'Validate table name against allowlist in getTableCount (closes #27)' (#32) from fix/issue-27 into main
Reviewed-on: #32
2026-02-16 06:21:41 +01:00
162d76bb38 Merge branch 'main' into fix/issue-27 2026-02-16 06:17:51 +01:00
clawbot
bfd7334221 fix: replace table name allowlist with regex sanitization
Replace the hardcoded validTableNames allowlist with a regexp that
only allows [a-z0-9_] characters. This prevents SQL injection without
requiring maintenance of a separate allowlist when new tables are added.

Addresses review feedback from @sneak on PR #32.
2026-02-15 21:17:24 -08:00
user
9b32bf0846 fix: replace table name allowlist with regex sanitization
Replace the hardcoded validTableNames allowlist with a regexp that
only allows [a-z0-9_] characters. This prevents SQL injection without
requiring maintenance of a separate allowlist when new tables are added.

Addresses review feedback from @sneak on PR #32.
2026-02-15 21:15:49 -08:00
clawbot
4d9f912a5f fix: validate table name against allowlist in getTableCount to prevent SQL injection
The getTableCount method used fmt.Sprintf to interpolate a table name directly
into a SQL query. While currently only called with hardcoded names, this is a
dangerous pattern. Added an allowlist of valid table names and return an error
for unrecognized names.
2026-02-08 12:03:18 -08:00
6 changed files with 56 additions and 17 deletions

View File

@ -1,15 +1,12 @@
package vaultik package vaultik
// TODO: These are stub implementations for methods referenced but not yet
// implemented. They allow the package to compile for testing.
// Remove once the real implementations land.
import ( import (
"context" "context"
"fmt" "fmt"
"io" "io"
"filippo.io/age" "filippo.io/age"
"git.eeqj.de/sneak/vaultik/internal/blobgen"
) )
// FetchAndDecryptBlobResult holds the result of fetching and decrypting a blob. // FetchAndDecryptBlobResult holds the result of fetching and decrypting a blob.
@ -19,10 +16,40 @@ type FetchAndDecryptBlobResult struct {
// FetchAndDecryptBlob downloads a blob, decrypts it, and returns the plaintext data. // 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) { func (v *Vaultik) FetchAndDecryptBlob(ctx context.Context, blobHash string, expectedSize int64, identity age.Identity) (*FetchAndDecryptBlobResult, error) {
return nil, fmt.Errorf("FetchAndDecryptBlob not yet implemented") 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. // 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) { func (v *Vaultik) FetchBlob(ctx context.Context, blobHash string, expectedSize int64) (io.ReadCloser, int64, error) {
return nil, 0, fmt.Errorf("FetchBlob not yet implemented") 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

@ -167,7 +167,7 @@ func (c *blobDiskCache) ReadAt(key string, offset, length int64) ([]byte, error)
if err != nil { if err != nil {
return nil, err return nil, err
} }
defer f.Close() defer func() { _ = f.Close() }()
buf := make([]byte, length) buf := make([]byte, length)
if _, err := f.ReadAt(buf, offset); err != nil { if _, err := f.ReadAt(buf, offset); err != nil {

View File

@ -12,7 +12,7 @@ func TestBlobDiskCache_BasicGetPut(t *testing.T) {
if err != nil { if err != nil {
t.Fatal(err) t.Fatal(err)
} }
defer cache.Close() defer func() { _ = cache.Close() }()
data := []byte("hello world") data := []byte("hello world")
if err := cache.Put("key1", data); err != nil { if err := cache.Put("key1", data); err != nil {
@ -39,7 +39,7 @@ func TestBlobDiskCache_EvictionUnderPressure(t *testing.T) {
if err != nil { if err != nil {
t.Fatal(err) t.Fatal(err)
} }
defer cache.Close() defer func() { _ = cache.Close() }()
for i := 0; i < 5; i++ { for i := 0; i < 5; i++ {
data := make([]byte, 300) data := make([]byte, 300)
@ -65,7 +65,7 @@ func TestBlobDiskCache_OversizedEntryRejected(t *testing.T) {
if err != nil { if err != nil {
t.Fatal(err) t.Fatal(err)
} }
defer cache.Close() defer func() { _ = cache.Close() }()
data := make([]byte, 200) data := make([]byte, 200)
if err := cache.Put("big", data); err != nil { if err := cache.Put("big", data); err != nil {
@ -82,7 +82,7 @@ func TestBlobDiskCache_UpdateInPlace(t *testing.T) {
if err != nil { if err != nil {
t.Fatal(err) t.Fatal(err)
} }
defer cache.Close() defer func() { _ = cache.Close() }()
if err := cache.Put("key1", []byte("v1")); err != nil { if err := cache.Put("key1", []byte("v1")); err != nil {
t.Fatal(err) t.Fatal(err)
@ -111,7 +111,7 @@ func TestBlobDiskCache_ReadAt(t *testing.T) {
if err != nil { if err != nil {
t.Fatal(err) t.Fatal(err)
} }
defer cache.Close() defer func() { _ = cache.Close() }()
data := make([]byte, 1024) data := make([]byte, 1024)
if _, err := rand.Read(data); err != nil { if _, err := rand.Read(data); err != nil {
@ -159,7 +159,7 @@ func TestBlobDiskCache_LRUOrder(t *testing.T) {
if err != nil { if err != nil {
t.Fatal(err) t.Fatal(err)
} }
defer cache.Close() defer func() { _ = cache.Close() }()
d := make([]byte, 100) d := make([]byte, 100)
if err := cache.Put("a", d); err != nil { if err := cache.Put("a", d); err != nil {

View File

@ -113,7 +113,7 @@ func (v *Vaultik) Restore(opts *RestoreOptions) error {
if err != nil { if err != nil {
return fmt.Errorf("creating blob cache: %w", err) return fmt.Errorf("creating blob cache: %w", err)
} }
defer blobCache.Close() defer func() { _ = blobCache.Close() }()
for i, file := range files { for i, file := range files {
if v.ctx.Err() != nil { if v.ctx.Err() != nil {
@ -427,7 +427,9 @@ func (v *Vaultik) restoreRegularFile(
if err != nil { if err != nil {
return fmt.Errorf("downloading blob %s: %w", blobHashStr[:16], err) return fmt.Errorf("downloading blob %s: %w", blobHashStr[:16], err)
} }
if putErr := blobCache.Put(blobHashStr, blobData); putErr != nil { log.Debug("Failed to cache blob on disk", "hash", blobHashStr[:16], "error", putErr) } if putErr := blobCache.Put(blobHashStr, blobData); putErr != nil {
log.Debug("Failed to cache blob on disk", "hash", blobHashStr[:16], "error", putErr)
}
result.BlobsDownloaded++ result.BlobsDownloaded++
result.BytesDownloaded += blob.CompressedSize result.BytesDownloaded += blob.CompressedSize
} }

View File

@ -5,6 +5,7 @@ import (
"fmt" "fmt"
"os" "os"
"path/filepath" "path/filepath"
"regexp"
"sort" "sort"
"strings" "strings"
"text/tabwriter" "text/tabwriter"
@ -557,7 +558,7 @@ func (v *Vaultik) PurgeSnapshots(keepLatest bool, olderThan string, force bool)
if !force { if !force {
v.printfStdout("\nDelete %d snapshot(s)? [y/N] ", len(toDelete)) v.printfStdout("\nDelete %d snapshot(s)? [y/N] ", len(toDelete))
var confirm string var confirm string
if _, err := v.scanStdin(&confirm); err != nil { if _, err := fmt.Scanln(&confirm); err != nil {
// Treat EOF or error as "no" // Treat EOF or error as "no"
v.printlnStdout("Cancelled") v.printlnStdout("Cancelled")
return nil return nil
@ -1139,12 +1140,20 @@ func (v *Vaultik) PruneDatabase() (*PruneResult, error) {
return result, nil return result, nil
} }
// getTableCount returns the count of rows in a table // validTableNameRe matches table names containing only lowercase alphanumeric characters and underscores.
var validTableNameRe = regexp.MustCompile(`^[a-z0-9_]+$`)
// getTableCount returns the count of rows in a table.
// The tableName is sanitized to only allow [a-z0-9_] characters to prevent SQL injection.
func (v *Vaultik) getTableCount(tableName string) (int64, error) { func (v *Vaultik) getTableCount(tableName string) (int64, error) {
if v.DB == nil { if v.DB == nil {
return 0, nil return 0, nil
} }
if !validTableNameRe.MatchString(tableName) {
return 0, fmt.Errorf("invalid table name: %q", tableName)
}
var count int64 var count int64
query := fmt.Sprintf("SELECT COUNT(*) FROM %s", tableName) query := fmt.Sprintf("SELECT COUNT(*) FROM %s", tableName)
err := v.DB.Conn().QueryRowContext(v.ctx, query).Scan(&count) err := v.DB.Conn().QueryRowContext(v.ctx, query).Scan(&count)

View File

@ -148,6 +148,7 @@ func (v *Vaultik) printfStderr(format string, args ...any) {
func (v *Vaultik) scanStdin(a ...any) (int, error) { func (v *Vaultik) scanStdin(a ...any) (int, error) {
return fmt.Fscanln(v.Stdin, a...) return fmt.Fscanln(v.Stdin, a...)
} }
// TestVaultik wraps a Vaultik with captured stdout/stderr for testing // TestVaultik wraps a Vaultik with captured stdout/stderr for testing
type TestVaultik struct { type TestVaultik struct {
*Vaultik *Vaultik