sneak/vaultik
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Compare commits

base: sneak:main
Branches Tags
sneak:main sneak:feature/daemon-mode sneak:fix/ctime-scanner-population sneak:fix/sync-snapshot-cleanup sneak:feature/restore-progress-bar sneak:feature/implement-prune-flag-on-snapshot-create sneak:fix/restore-error-handling sneak:fix/issue-25 sneak:fix/sql-injection-whitelist sneak:fix/issue-29 sneak:add-compressstream-regression-test sneak:fix/issue-26 sneak:fix/issue-27 sneak:fix/issue-28 sneak:feature/pluggable-storage-backend
..
compare: sneak:a36b314c796cde1d27ae0dca148319571cb2e14d
Branches Tags
sneak:main sneak:feature/daemon-mode sneak:fix/ctime-scanner-population sneak:fix/sync-snapshot-cleanup sneak:feature/restore-progress-bar sneak:feature/implement-prune-flag-on-snapshot-create sneak:fix/restore-error-handling sneak:fix/issue-25 sneak:fix/sql-injection-whitelist sneak:fix/issue-29 sneak:add-compressstream-regression-test sneak:fix/issue-26 sneak:fix/issue-27 sneak:fix/issue-28 sneak:feature/pluggable-storage-backend

1 Commits
main ... a36b314c79

Author SHA1 Message Date
clawbot
a36b314c79 fix: remove destructive sync from ListSnapshots
All checks were successful
check / check (pull_request) Successful in 4m8s
Details 
ListSnapshots() silently deleted local snapshot records not found in
remote storage. A list/read operation should not have destructive side
effects.

Changes:
- Remove the inline deletion loop from ListSnapshots() that deleted
  local snapshots not present in remote storage
- Update syncWithRemote() to use deleteSnapshotFromLocalDB() for
  proper cascade cleanup (deleting snapshot_files, snapshot_blobs,
  and snapshot_uploads before the snapshot record itself)

The sync behavior remains available via syncWithRemote(), which is
called explicitly by PurgeSnapshots().

closes #15
 2026-03-18 16:28:34 -07:00
100 changed files with 2027 additions and 5081 deletions
Expand all files Collapse all files

2
.gitignore vendored
View File

@@ -1,5 +1,5 @@
# Binary
/vaultik
vaultik
# Test artifacts
*.out

56
.goreleaser.yaml
View File

@@ -1,56 +0,0 @@
version: 2
project_name: vaultik
before:
hooks:
- go mod tidy
builds:
- id: vaultik
main: ./cmd/vaultik
binary: vaultik
env:
- CGO_ENABLED=0
goos:
- linux
- darwin
goarch:
- amd64
- arm64
ldflags:
- -s -w
- -X 'sneak.berlin/go/vaultik/internal/globals.Version={{ .Version }}'
- -X 'sneak.berlin/go/vaultik/internal/globals.Commit={{ .Commit }}'
- -X 'sneak.berlin/go/vaultik/internal/globals.CommitDate={{ slice .CommitDate 0 10 }}'
archives:
- id: default
name_template: "{{ .ProjectName }}_{{ .Version }}_{{ .Os }}_{{ .Arch }}"
formats:
- tar.gz
files:
- LICENSE
- README.md
checksum:
name_template: "checksums.txt"
algorithm: sha256
snapshot:
version_template: "{{ incpatch .Version }}-next"
changelog:
sort: asc
use: git
filters:
exclude:
- "^docs:"
- "^test:"
- "^chore:"
- "Merge pull request"
- "Merge branch"
release:
draft: true
prerelease: auto

13
AGENTS.md
View File

@@ -38,9 +38,10 @@ Version: 2025-06-08
1. Before committing, tests must pass (`make test`), linting must pass
(`make lint`), and code must be formatted (`make fmt`). For go, those
makefile targets should use `go fmt` and `go test -v ./...` and
`golangci-lint run`. Each Makefile target does exactly one thing — to
run lint + fmt-check + test together (the standard pre-commit gate),
use `make check`.
`golangci-lint run`. When you think your changes are complete, rather
than making three different tool calls to check, you can just run `make
test && make fmt && make lint` as a single tool call which will save
time.
2. Always write a `Makefile` with the default target being `test`, and with
a `fmt` target that formats the code. The `test` target should run all
@@ -102,9 +103,3 @@ Version: 2025-06-08
build files are acceptable in the root, but source code and other files
should be organized in appropriate subdirectories.
13. Pre-1.0: NEVER write database migrations. There are no live databases
anywhere — every user's local index can be rebuilt from a fresh full
backup. When the schema changes, just change `schema.sql` (and any code
that touches the affected tables). The local index is disposable until
1.0 ships and is tagged.

23
ARCHITECTURE.md
View File

@@ -53,8 +53,8 @@ The database tracks five primary entities and their relationships:
### Entity Descriptions
#### File (`database.File`)
Represents a file, directory, or symlink in the backup system. Stores metadata needed for restoration:
- Path, source_path (for restore path stripping), mtime
Represents a file or directory in the backup system. Stores metadata needed for restoration:
- Path, timestamps (mtime, ctime)
- Size, mode, ownership (uid, gid)
- Symlink target (if applicable)
@@ -95,7 +95,7 @@ Maps chunks to their position within blobs:
#### Snapshot (`database.Snapshot`)
Represents a point-in-time backup:
- `ID`: Format is `{hostname}_{snapshot-name}_{RFC3339}` (e.g. `server1_home_2025-06-01T12:00:00Z`)
- `ID`: Format is `{hostname}-{YYYYMMDD}-{HHMMSS}Z`
- Tracks file count, chunk count, blob count, sizes, compression ratio
- `CompletedAt`: Null until snapshot finishes successfully
@@ -127,7 +127,7 @@ fx.New(
config.Module, // 5. Config
database.Module, // 6. Database + Repositories
log.Module, // 7. Logger initialization
storage.Module, // 8. Storage backend (S3/file/rclone)
s3.Module, // 8. S3 client
snapshot.Module, // 9. SnapshotManager + ScannerFactory
fx.Provide(vaultik.New), // 10. Vaultik orchestrator
)
@@ -161,7 +161,7 @@ type Vaultik struct {
Config *config.Config
DB *database.DB
Repositories *database.Repositories
Storage storage.Storer
S3Client *s3.Client
ScannerFactory snapshot.ScannerFactory
SnapshotManager *snapshot.SnapshotManager
Shutdowner fx.Shutdowner
@@ -341,11 +341,12 @@ CreateSnapshot(opts)
└─► SnapshotManager.ExportSnapshotMetadata()
│
├─► Copy database to temp file
├─► Clean to only current snapshot data (VACUUM)
├─► Compress binary SQLite with zstd
├─► Clean to only current snapshot data
├─► Dump to SQL
├─► Compress with zstd
├─► Encrypt with age
├─► Upload db.zst.age to storage
└─► Upload manifest.json.zst to storage
├─► Upload db.zst.age to S3
└─► Upload manifest.json.zst to S3
```
## Deduplication Strategy
@@ -367,8 +368,8 @@ bucket/
│
└── metadata/
└── {snapshot-id}/
├── db.zst.age # Encrypted binary SQLite database
└── manifest.json.zst # Blob list (for pruning/verification)
├── db.zst.age # Encrypted database dump
└── manifest.json.zst # Blob list (for verification)
```
## Thread Safety

4
Dockerfile
View File

@@ -41,8 +41,8 @@ COPY . .
# Run tests
RUN make test
# Build (pure Go, no CGO required since we use modernc.org/sqlite)
RUN CGO_ENABLED=0 go build -ldflags "-X 'sneak.berlin/go/vaultik/internal/globals.Version=${VERSION}' -X 'sneak.berlin/go/vaultik/internal/globals.Commit=$(git rev-parse HEAD 2>/dev/null || echo unknown)' -X 'sneak.berlin/go/vaultik/internal/globals.CommitDate=$(git show -s --format=%cs HEAD 2>/dev/null || echo unknown)'" -o /vaultik ./cmd/vaultik
# Build with CGO enabled (required for mattn/go-sqlite3)
RUN CGO_ENABLED=1 go build -ldflags "-X 'git.eeqj.de/sneak/vaultik/internal/globals.Version=${VERSION}' -X 'git.eeqj.de/sneak/vaultik/internal/globals.Commit=$(git rev-parse HEAD 2>/dev/null || echo unknown)'" -o /vaultik ./cmd/vaultik
# Runtime stage
# alpine:3.21, 2026-02-25

47
Makefile
View File

@@ -1,59 +1,49 @@
.PHONY: all check test lint fmt fmt-check build clean deps test-coverage test-integration local install release release-snapshot docker hooks
.PHONY: test fmt lint fmt-check check build clean all docker hooks
# Version number
VERSION := 1.0.0-rc.1
VERSION := 0.0.1
# Build variables
GIT_REVISION := $(shell git rev-parse HEAD 2>/dev/null || echo "unknown")
GIT_COMMIT_DATE := $(shell git show -s --format=%cs HEAD 2>/dev/null || echo "unknown")
# Linker flags
LDFLAGS := -X 'sneak.berlin/go/vaultik/internal/globals.Version=$(VERSION)' \
-X 'sneak.berlin/go/vaultik/internal/globals.Commit=$(GIT_REVISION)' \
-X 'sneak.berlin/go/vaultik/internal/globals.CommitDate=$(GIT_COMMIT_DATE)'
LDFLAGS := -X 'git.eeqj.de/sneak/vaultik/internal/globals.Version=$(VERSION)' \
-X 'git.eeqj.de/sneak/vaultik/internal/globals.Commit=$(GIT_REVISION)'
# Default target
all: vaultik
# Combined pre-commit/CI gate: lint, format check, then tests.
check: lint fmt-check test
# Run tests only.
# Run tests
test:
go test -race -timeout 30s ./...
# Check if code is formatted (read-only).
# Check if code is formatted (read-only)
fmt-check:
@test -z "$$(gofmt -l .)" || (echo "Files not formatted:" && gofmt -l . && exit 1)
# Format code.
# Format code
fmt:
go fmt ./...
# Run linter only.
# Run linter
lint:
golangci-lint run ./...
# Build binary.
# Build binary
vaultik: internal/*/*.go cmd/vaultik/*.go
go build -ldflags "$(LDFLAGS)" -o $@ ./cmd/vaultik
# Clean build artifacts.
# Clean build artifacts
clean:
rm -f vaultik
go clean
# Install dependencies.
deps:
go mod download
go install github.com/golangci/golangci-lint/cmd/golangci-lint@latest
# Run tests with coverage.
# Run tests with coverage
test-coverage:
go test -v -coverprofile=coverage.out ./...
go tool cover -html=coverage.out -o coverage.html
# Run integration tests.
# Run integration tests
test-integration:
go test -v -tags=integration ./...
@@ -64,19 +54,14 @@ local:
install: vaultik
cp ./vaultik $(HOME)/bin/
# Build and publish release artifacts (linux/darwin × amd64/arm64) via goreleaser.
release:
goreleaser release --clean
# Run all checks (formatting, linting, tests) without modifying files
check: fmt-check lint test
# Dry-run a release build without publishing or tagging.
release-snapshot:
goreleaser release --clean --snapshot
# Build Docker image.
# Build Docker image
docker:
docker build -t vaultik .
# Install pre-commit hook.
# Install pre-commit hook
hooks:
@printf '#!/bin/sh\nset -e\n' > .git/hooks/pre-commit
@printf 'go mod tidy\ngo fmt ./...\ngit diff --exit-code -- go.mod go.sum || { echo "go mod tidy changed files; please stage and retry"; exit 1; }\n' >> .git/hooks/pre-commit

556
PROCESS.md Normal file
View File

@@ -0,0 +1,556 @@
# Vaultik Snapshot Creation Process
This document describes the lifecycle of objects during snapshot creation, with a focus on database transactions and foreign key constraints.
## Database Schema Overview
### Tables and Foreign Key Dependencies
```
┌─────────────────────────────────────────────────────────────────────────┐
│ FOREIGN KEY GRAPH │
│ │
│ snapshots ◄────── snapshot_files ────────► files │
│ │ │ │
│ └───────── snapshot_blobs ────────► blobs │ │
│ │ │ │
│ │ ├──► file_chunks ◄── chunks│
│ │ │ ▲ │
│ │ └──► chunk_files ────┘ │
│ │ │
│ └──► blob_chunks ─────────────┘│
│ │
│ uploads ───────► blobs.blob_hash │
│ └──────────► snapshots.id │
└─────────────────────────────────────────────────────────────────────────┘
```
### Critical Constraint: `chunks` Must Exist First
These tables reference `chunks.chunk_hash` **without CASCADE**:
- `file_chunks.chunk_hash` → `chunks.chunk_hash`
- `chunk_files.chunk_hash` → `chunks.chunk_hash`
- `blob_chunks.chunk_hash` → `chunks.chunk_hash`
**Implication**: A chunk record MUST be committed to the database BEFORE any of these referencing records can be created.
### Order of Operations Required by Schema
```
1. snapshots (created first, before scan)
2. blobs (created when packer starts new blob)
3. chunks (created during file processing)
4. blob_chunks (created immediately after chunk added to packer)
5. files (created after file fully chunked)
6. file_chunks (created with file record)
7. chunk_files (created with file record)
8. snapshot_files (created with file record)
9. snapshot_blobs (created after blob uploaded)
10. uploads (created after blob uploaded)
```
---
## Snapshot Creation Phases
### Phase 0: Initialization
**Actions:**
1. Snapshot record created in database (Transaction T0)
2. Known files loaded into memory from `files` table
3. Known chunks loaded into memory from `chunks` table
**Transactions:**
```
T0: INSERT INTO snapshots (id, hostname, ...) VALUES (...)
COMMIT
```
---
### Phase 1: Scan Directory
**Actions:**
1. Walk filesystem directory tree
2. For each file, compare against in-memory `knownFiles` map
3. Classify files as: unchanged, new, or modified
4. Collect unchanged file IDs for later association
5. Collect new/modified files for processing
**Transactions:**
```
(None during scan - all in-memory)
```
---
### Phase 1b: Associate Unchanged Files
**Actions:**
1. For unchanged files, add entries to `snapshot_files` table
2. Done in batches of 1000
**Transactions:**
```
For each batch of 1000 file IDs:
T: BEGIN
INSERT INTO snapshot_files (snapshot_id, file_id) VALUES (?, ?)
... (up to 1000 inserts)
COMMIT
```
---
### Phase 2: Process Files
For each file that needs processing:
#### Step 2a: Open and Chunk File
**Location:** `processFileStreaming()`
For each chunk produced by content-defined chunking:
##### Step 2a-1: Check Chunk Existence
```go
chunkExists := s.chunkExists(chunk.Hash) // In-memory lookup
```
##### Step 2a-2: Create Chunk Record (if new)
```go
// TRANSACTION: Create chunk in database
err := s.repos.WithTx(ctx, func(txCtx context.Context, tx *sql.Tx) error {
dbChunk := &database.Chunk{ChunkHash: chunk.Hash, Size: chunk.Size}
return s.repos.Chunks.Create(txCtx, tx, dbChunk)
})
// COMMIT immediately after WithTx returns
// Update in-memory cache
s.addKnownChunk(chunk.Hash)
```
**Transaction:**
```
T_chunk: BEGIN
INSERT INTO chunks (chunk_hash, size) VALUES (?, ?)
COMMIT
```
##### Step 2a-3: Add Chunk to Packer
```go
s.packer.AddChunk(&blob.ChunkRef{Hash: chunk.Hash, Data: chunk.Data})
```
**Inside packer.AddChunk → addChunkToCurrentBlob():**
```go
// TRANSACTION: Create blob_chunks record IMMEDIATELY
if p.repos != nil {
blobChunk := &database.BlobChunk{
BlobID: p.currentBlob.id,
ChunkHash: chunk.Hash,
Offset: offset,
Length: chunkSize,
}
err := p.repos.WithTx(context.Background(), func(ctx context.Context, tx *sql.Tx) error {
return p.repos.BlobChunks.Create(ctx, tx, blobChunk)
})
// COMMIT immediately
}
```
**Transaction:**
```
T_blob_chunk: BEGIN
INSERT INTO blob_chunks (blob_id, chunk_hash, offset, length) VALUES (?, ?, ?, ?)
COMMIT
```
**⚠️ CRITICAL DEPENDENCY**: This transaction requires `chunks.chunk_hash` to exist (FK constraint).
The chunk MUST be committed in Step 2a-2 BEFORE this can succeed.
---
#### Step 2b: Blob Size Limit Handling
If adding a chunk would exceed blob size limit:
```go
if err == blob.ErrBlobSizeLimitExceeded {
if err := s.packer.FinalizeBlob(); err != nil { ... }
// Retry adding the chunk
if err := s.packer.AddChunk(...); err != nil { ... }
}
```
**FinalizeBlob() transactions:**
```
T_blob_finish: BEGIN
UPDATE blobs SET blob_hash=?, uncompressed_size=?, compressed_size=?, finished_ts=? WHERE id=?
COMMIT
```
Then blob handler is called (handleBlobReady):
```
(Upload to S3 - no transaction)
T_blob_uploaded: BEGIN
UPDATE blobs SET uploaded_ts=? WHERE id=?
INSERT INTO snapshot_blobs (snapshot_id, blob_id, blob_hash) VALUES (?, ?, ?)
INSERT INTO uploads (blob_hash, snapshot_id, uploaded_at, size, duration_ms) VALUES (?, ?, ?, ?, ?)
COMMIT
```
---
#### Step 2c: Queue File for Batch Insertion
After all chunks for a file are processed:
```go
// Build file data (in-memory, no DB)
fileChunks := make([]database.FileChunk, len(chunks))
chunkFiles := make([]database.ChunkFile, len(chunks))
// Queue for batch insertion
return s.addPendingFile(ctx, pendingFileData{
file: fileToProcess.File,
fileChunks: fileChunks,
chunkFiles: chunkFiles,
})
```
**No transaction yet** - just adds to `pendingFiles` slice.
If `len(pendingFiles) >= fileBatchSize (100)`, triggers `flushPendingFiles()`.
---
### Step 2d: Flush Pending Files
**Location:** `flushPendingFiles()` - called when batch is full or at end of processing
```go
return s.repos.WithTx(ctx, func(txCtx context.Context, tx *sql.Tx) error {
for _, data := range files {
// 1. Create file record
s.repos.Files.Create(txCtx, tx, data.file) // INSERT OR REPLACE
// 2. Delete old associations
s.repos.FileChunks.DeleteByFileID(txCtx, tx, data.file.ID)
s.repos.ChunkFiles.DeleteByFileID(txCtx, tx, data.file.ID)
// 3. Create file_chunks records
for _, fc := range data.fileChunks {
s.repos.FileChunks.Create(txCtx, tx, &fc) // FK: chunks.chunk_hash
}
// 4. Create chunk_files records
for _, cf := range data.chunkFiles {
s.repos.ChunkFiles.Create(txCtx, tx, &cf) // FK: chunks.chunk_hash
}
// 5. Add file to snapshot
s.repos.Snapshots.AddFileByID(txCtx, tx, s.snapshotID, data.file.ID)
}
return nil
})
// COMMIT (all or nothing for the batch)
```
**Transaction:**
```
T_files_batch: BEGIN
-- For each file in batch:
INSERT OR REPLACE INTO files (...) VALUES (...)
DELETE FROM file_chunks WHERE file_id = ?
DELETE FROM chunk_files WHERE file_id = ?
INSERT INTO file_chunks (file_id, idx, chunk_hash) VALUES (?, ?, ?) -- FK: chunks
INSERT INTO chunk_files (chunk_hash, file_id, ...) VALUES (?, ?, ...) -- FK: chunks
INSERT INTO snapshot_files (snapshot_id, file_id) VALUES (?, ?)
-- Repeat for each file
COMMIT
```
**⚠️ CRITICAL DEPENDENCY**: `file_chunks` and `chunk_files` require `chunks.chunk_hash` to exist.
---
### Phase 2 End: Final Flush
```go
// Flush any remaining pending files
if err := s.flushAllPending(ctx); err != nil { ... }
// Final packer flush
s.packer.Flush()
```
---
## The Current Bug
### Problem
The current code attempts to batch file insertions, but `file_chunks` and `chunk_files` have foreign keys to `chunks.chunk_hash`. The batched file flush tries to insert these records, but if the chunks haven't been committed yet, the FK constraint fails.
### Why It's Happening
Looking at the sequence:
1. Process file A, chunk X
2. Create chunk X in DB (Transaction commits)
3. Add chunk X to packer
4. Packer creates blob_chunks for chunk X (needs chunk X - OK, committed in step 2)
5. Queue file A with chunk references
6. Process file B, chunk Y
7. Create chunk Y in DB (Transaction commits)
8. ... etc ...
9. At end: flushPendingFiles()
10. Insert file_chunks for file A referencing chunk X (chunk X committed - should work)
The chunks ARE being created individually. But something is going wrong.
### Actual Issue
Wait - let me re-read the code. The issue is:
In `processFileStreaming`, when we queue file data:
```go
fileChunks[i] = database.FileChunk{
FileID: fileToProcess.File.ID,
Idx: ci.fileChunk.Idx,
ChunkHash: ci.fileChunk.ChunkHash,
}
```
The `FileID` is set, but `fileToProcess.File.ID` might be empty at this point because the file record hasn't been created yet!
Looking at `checkFileInMemory`:
```go
// For new files:
if !exists {
return file, true // file.ID is empty string!
}
// For existing files:
file.ID = existingFile.ID // Reuse existing ID
```
**For NEW files, `file.ID` is empty!**
Then in `flushPendingFiles`:
```go
s.repos.Files.Create(txCtx, tx, data.file) // This generates/uses the ID
```
But `data.fileChunks` was built with the EMPTY ID!
### The Real Problem
For new files:
1. `checkFileInMemory` creates file record with empty ID
2. `processFileStreaming` queues file_chunks with empty `FileID`
3. `flushPendingFiles` creates file (generates ID), but file_chunks still have empty `FileID`
Wait, but `Files.Create` should be INSERT OR REPLACE by path, and the file struct should get updated... Let me check.
Actually, looking more carefully at the code path - the file IS created first in the flush, but the `fileChunks` slice was already built with the old (possibly empty) ID. The ID isn't updated after the file is created.
Hmm, but looking at the current code:
```go
fileChunks[i] = database.FileChunk{
FileID: fileToProcess.File.ID, // This uses the ID from the File struct
```
And in `checkFileInMemory` for new files, we create a file struct but don't set the ID. However, looking at the database repository, `Files.Create` should be doing `INSERT OR REPLACE` and the ID should be pre-generated...
Let me check if IDs are being generated. Looking at the File struct usage, it seems like UUIDs should be generated somewhere...
Actually, looking at the test failures again:
```
creating file chunk: inserting file_chunk: constraint failed: FOREIGN KEY constraint failed (787)
```
Error 787 is SQLite's foreign key constraint error. The failing FK is on `file_chunks.chunk_hash → chunks.chunk_hash`.
So the chunks ARE NOT in the database when we try to insert file_chunks. Let me trace through more carefully...
---
## Transaction Timing Issue
The problem is transaction visibility in SQLite.
Each `WithTx` creates a new transaction that commits at the end. But with batched file insertion:
1. Chunk transactions commit one at a time
2. File batch transaction runs later
If chunks are being inserted but something goes wrong with transaction isolation, the file batch might not see them.
But actually SQLite in WAL mode should have SERIALIZABLE isolation by default, so committed transactions should be visible.
Let me check if the in-memory cache is masking a database problem...
Actually, wait. Let me re-check the current broken code more carefully. The issue might be simpler.
---
## Current Code Flow Analysis
Looking at `processFileStreaming` in the current broken state:
```go
// For each chunk:
if !chunkExists {
err := s.repos.WithTx(ctx, func(txCtx context.Context, tx *sql.Tx) error {
dbChunk := &database.Chunk{ChunkHash: chunk.Hash, Size: chunk.Size}
return s.repos.Chunks.Create(txCtx, tx, dbChunk)
})
// ... check error ...
s.addKnownChunk(chunk.Hash)
}
// ... add to packer (creates blob_chunks) ...
// Collect chunk info for file
chunks = append(chunks, chunkInfo{...})
```
Then at end of function:
```go
// Queue file for batch insertion
return s.addPendingFile(ctx, pendingFileData{
file: fileToProcess.File,
fileChunks: fileChunks,
chunkFiles: chunkFiles,
})
```
At end of `processPhase`:
```go
if err := s.flushAllPending(ctx); err != nil { ... }
```
The chunks are being created one-by-one with individual transactions. By the time `flushPendingFiles` runs, all chunk transactions should have committed.
Unless... there's a bug in how the chunks are being referenced. Let me check if the chunk_hash values are correct.
Or... maybe the test database is being recreated between operations somehow?
Actually, let me check the test setup. Maybe the issue is specific to the test environment.
---
## Summary of Object Lifecycle
| Object | When Created | Transaction | Dependencies |
|--------|--------------|-------------|--------------|
| snapshot | Before scan | Individual tx | None |
| blob | When packer needs new blob | Individual tx | None |
| chunk | During file chunking (each chunk) | Individual tx | None |
| blob_chunks | Immediately after adding chunk to packer | Individual tx | chunks, blobs |
| files | Batched at end of processing | Batch tx | None |
| file_chunks | With file (batched) | Batch tx | files, chunks |
| chunk_files | With file (batched) | Batch tx | files, chunks |
| snapshot_files | With file (batched) | Batch tx | snapshots, files |
| snapshot_blobs | After blob upload | Individual tx | snapshots, blobs |
| uploads | After blob upload | Same tx as snapshot_blobs | blobs, snapshots |
---
## Root Cause Analysis
After detailed analysis, I believe the issue is one of the following:
### Hypothesis 1: File ID Not Set
Looking at `checkFileInMemory()` for NEW files:
```go
if !exists {
return file, true // file.ID is empty string!
}
```
For new files, `file.ID` is empty. Then in `processFileStreaming`:
```go
fileChunks[i] = database.FileChunk{
FileID: fileToProcess.File.ID, // Empty for new files!
...
}
```
The `FileID` in the built `fileChunks` slice is empty.
Then in `flushPendingFiles`:
```go
s.repos.Files.Create(txCtx, tx, data.file) // This generates the ID
// But data.fileChunks still has empty FileID!
for i := range data.fileChunks {
s.repos.FileChunks.Create(...) // Uses empty FileID
}
```
**Solution**: Generate file IDs upfront in `checkFileInMemory()`:
```go
file := &database.File{
ID: uuid.New().String(), // Generate ID immediately
Path: path,
...
}
```
### Hypothesis 2: Transaction Isolation
SQLite with a single connection pool (`MaxOpenConns(1)`) should serialize all transactions. Committed data should be visible to subsequent transactions.
However, there might be a subtle issue with how `context.Background()` is used in the packer vs the scanner's context.
## Recommended Fix
**Step 1: Generate file IDs upfront**
In `checkFileInMemory()`, generate the UUID for new files immediately:
```go
file := &database.File{
ID: uuid.New().String(), // Always generate ID
Path: path,
...
}
```
This ensures `file.ID` is set when building `fileChunks` and `chunkFiles` slices.
**Step 2: Verify by reverting to per-file transactions**
If Step 1 doesn't fix it, revert to non-batched file insertion to isolate the issue:
```go
// Instead of queuing:
// return s.addPendingFile(ctx, pendingFileData{...})
// Do immediate insertion:
return s.repos.WithTx(ctx, func(txCtx context.Context, tx *sql.Tx) error {
// Create file
s.repos.Files.Create(txCtx, tx, fileToProcess.File)
// Delete old associations
s.repos.FileChunks.DeleteByFileID(...)
s.repos.ChunkFiles.DeleteByFileID(...)
// Create new associations
for _, fc := range fileChunks {
s.repos.FileChunks.Create(...)
}
for _, cf := range chunkFiles {
s.repos.ChunkFiles.Create(...)
}
// Add to snapshot
s.repos.Snapshots.AddFileByID(...)
return nil
})
```
**Step 3: If batching is still desired**
After confirming per-file transactions work, re-implement batching with the ID fix in place, and add debug logging to trace exactly which chunk_hash is failing and why.

671
README.md
View File

@@ -1,65 +1,43 @@
# vaultik (ваултик)
`vaultik` is an incremental backup tool written in Go. It encrypts data
WIP: pre-1.0, some functions may not be fully implemented yet
`vaultik` is an incremental backup daemon written in Go. It encrypts data
using an `age` public key and uploads each encrypted blob directly to a
remote S3-compatible object store. It requires no private keys, secrets, or
credentials (other than those required to PUT to encrypted object storage,
such as S3 API keys) stored on the backed-up system.
## quickstart
It includes table-stakes features such as:
```sh
# install
go install sneak.berlin/go/vaultik/cmd/vaultik@latest
# create a default config file (prints the path it wrote to)
vaultik config init
# generate an age keypair; keep the private key file somewhere safe and
# offline — you need it to restore, and the backed-up machine does not need it
age-keygen -o vaultik_backup_private_key.txt
grep 'public key' vaultik_backup_private_key.txt
# configure the encryption key and backup destination
vaultik config set age_recipients.0 age1YOUR_PUBLIC_KEY_HERE
vaultik config set storage_url "file:///Volumes/usbstick/mybackup"
# macOS only: grant your terminal app Full Disk Access first
# (System Settings → Privacy & Security → Full Disk Access), otherwise
# the backup will abort with a permission error on protected directories
# run your first backup (the default config backs up ~ and /Applications
# with sensible excludes)
vaultik snapshot create
# see what you have
vaultik snapshot list
```
Features:
* modern encryption ([age](https://age-encryption.org/), X25519 + XChaCha20-Poly1305)
* content-defined chunking with deduplication (FastCDC)
* incremental backups (only changed files are re-chunked)
* multithreaded zstd compression at configurable levels
* modern encryption (the excellent `age`)
* deduplication
* incremental backups
* modern multithreaded zstd compression with configurable levels
* content-addressed immutable storage
* local state tracking in SQLite (enables write-only incremental backups)
* local state tracking in standard SQLite database, enables write-only
incremental backups to destination
* no mutable remote metadata
* no plaintext file paths or metadata in remote storage
* packs small files into large blobs (keeps S3 operation counts down)
* backs up regular files, symlinks, empty directories, and file permissions
* pluggable storage backends: S3, local filesystem, rclone (70+ providers)
* pure Go (no CGO), cross-compiles to linux/darwin × amd64/arm64
* no plaintext file paths or metadata stored in remote
* does not create huge numbers of small files (to keep S3 operation counts
down) even if the source system has many small files
## why
Existing backup software fails under one or more of these conditions:
* Requires secrets (passwords, private keys) on the source system, which
compromises encrypted backups in the case of host system compromise
* Depends on symmetric encryption unsuitable for zero-trust environments
* Creates one-blob-per-file, which results in excessive S3 operation counts
* is slow
Other backup tools like `restic`, `borg`, and `duplicity` are designed for
environments where the source host can store secrets and has access to
decryption keys. `vaultik` is for environments where you don't want to
store backup decryption keys on your hosts — only public keys for
encryption.
decryption keys. I don't want to store backup decryption keys on my hosts,
only public keys for encryption.
Requirements that no existing tool meets:
My requirements are:
* open source
* no passphrases or private keys on the source host
@@ -68,21 +46,99 @@ Requirements that no existing tool meets:
* encrypted
* s3 compatible without an intermediate step or tool
## daily use
Surprisingly, no existing tool meets these requirements, so I wrote `vaultik`.
```sh
# verify a snapshot (shallow: checks all blobs exist)
vaultik snapshot verify <snapshot-id>
## design goals
# deep verify (downloads and cryptographically verifies every blob)
VAULTIK_AGE_SECRET_KEY='AGE-SECRET-KEY-...' vaultik snapshot verify --deep <snapshot-id>
1. Backups must require only a public key on the source host.
1. No secrets or private keys may exist on the source system.
1. Restore must be possible using **only** the backup bucket and a private key.
1. Prune must be possible (requires private key, done on different hosts).
1. All encryption uses [`age`](https://age-encryption.org/) (X25519, XChaCha20-Poly1305).
1. Compression uses `zstd` at a configurable level.
1. Files are chunked, and multiple chunks are packed into encrypted blobs
to reduce object count for filesystems with many small files.
1. All metadata (snapshots) is stored remotely as encrypted SQLite DBs.
# restore (requires the private key)
VAULTIK_AGE_SECRET_KEY='AGE-SECRET-KEY-...' vaultik snapshot restore <snapshot-id> /tmp/restored
## what
# daily cron job: back up, keep a 4-week rolling window of snapshots
# 0 3 * * * vaultik snapshot create --cron --prune --keep-newer-than 4w
```
`vaultik` walks a set of configured directories and builds a
content-addressable chunk map of changed files using deterministic chunking.
Each chunk is streamed into a blob packer. Blobs are compressed with `zstd`,
encrypted with `age`, and uploaded directly to remote storage under a
content-addressed S3 path. At the end, a pruned snapshot-specific sqlite
database of metadata is created, encrypted, and uploaded alongside the
blobs.
No plaintext file contents ever hit disk. No private key or secret
passphrase is needed or stored locally.
## how
1. **install**
```sh
go install git.eeqj.de/sneak/vaultik@latest
```
1. **generate keypair**
```sh
age-keygen -o agekey.txt
grep 'public key:' agekey.txt
```
1. **write config**
```yaml
# Named snapshots - each snapshot can contain multiple paths
snapshots:
system:
paths:
- /etc
- /var/lib
exclude:
- '*.cache' # Snapshot-specific exclusions
home:
paths:
- /home/user/documents
- /home/user/photos
# Global exclusions (apply to all snapshots)
exclude:
- '*.log'
- '*.tmp'
- '.git'
- 'node_modules'
age_recipients:
- age1278m9q7dp3chsh2dcy82qk27v047zywyvtxwnj4cvt0z65jw6a7q5dqhfj
s3:
endpoint: https://s3.example.com
bucket: vaultik-data
prefix: host1/
access_key_id: ...
secret_access_key: ...
region: us-east-1
backup_interval: 1h
full_scan_interval: 24h
min_time_between_run: 15m
chunk_size: 10MB
blob_size_limit: 1GB
```
1. **run**
```sh
# Create all configured snapshots
vaultik --config /etc/vaultik.yaml snapshot create
# Create specific snapshots by name
vaultik --config /etc/vaultik.yaml snapshot create home system
# Silent mode for cron
vaultik --config /etc/vaultik.yaml snapshot create --cron
```
---
@@ -91,396 +147,253 @@ VAULTIK_AGE_SECRET_KEY='AGE-SECRET-KEY-...' vaultik snapshot restore <snapshot-i
### commands
```sh
vaultik [--config <path>] config init
vaultik [--config <path>] config edit
vaultik [--config <path>] config get <key>
vaultik [--config <path>] config set <key> <value>
vaultik [--config <path>] snapshot create [snapshot-names...] [--cron] [--prune] [--keep-newer-than <duration>]
vaultik [--config <path>] snapshot create [snapshot-names...] [--cron] [--daemon] [--prune]
vaultik [--config <path>] snapshot list [--json]
vaultik [--config <path>] snapshot verify <snapshot-id> [--deep] [--json]
vaultik [--config <path>] snapshot purge [--keep-latest | --older-than <duration>] [--snapshot <name>...] [--force]
vaultik [--config <path>] snapshot remove <snapshot-id|--all> [--dry-run] [--force] [--remote] [--json]
vaultik [--config <path>] snapshot verify <snapshot-id> [--deep]
vaultik [--config <path>] snapshot purge [--keep-latest | --older-than <duration>] [--force]
vaultik [--config <path>] snapshot remove <snapshot-id> [--dry-run] [--force]
vaultik [--config <path>] snapshot prune
vaultik [--config <path>] snapshot cleanup
vaultik [--config <path>] restore <snapshot-id> <target-dir> [paths...] [--verify]
vaultik [--config <path>] prune [--force] [--json]
vaultik [--config <path>] restore <snapshot-id> <target-dir> [paths...]
vaultik [--config <path>] prune [--dry-run] [--force]
vaultik [--config <path>] info
vaultik [--config <path>] remote info [--json]
vaultik [--config <path>] remote nuke --force
vaultik [--config <path>] store info
vaultik [--config <path>] database purge [--force]
vaultik completion <bash|zsh|fish|powershell>
vaultik version
```
### global flags
### environment
* `--config <path>`: Path to config file (default: `$VAULTIK_CONFIG`, then platform config dir, then `/etc/vaultik/config.yml`)
* `--verbose`, `-v`: Enable verbose output
* `--debug`: Enable debug output
* `--quiet`, `-q`: Suppress non-error output (also suppresses startup banner)
* `--skip-errors`: Continue past per-file errors instead of aborting (applies to `snapshot create` and `restore`)
### environment variables
* `VAULTIK_AGE_SECRET_KEY`: Age private key for decryption (required for `restore` and `verify --deep`)
* `VAULTIK_CONFIG`: Path to config file (overridden by `--config`)
* `VAULTIK_INDEX_PATH`: Override local SQLite index path
### shell completion
```sh
# zsh: load for the current session
source <(vaultik completion zsh)
# zsh: install permanently
vaultik completion zsh > "${fpath[1]}/_vaultik"
# bash: load for the current session
source <(vaultik completion bash)
# bash: install permanently (Linux)
vaultik completion bash > /etc/bash_completion.d/vaultik
# fish
vaultik completion fish > ~/.config/fish/completions/vaultik.fish
```
* `VAULTIK_AGE_SECRET_KEY`: Required for `restore` and deep `verify`. Contains the age private key for decryption.
* `VAULTIK_CONFIG`: Optional path to config file.
### command details
**`config init`**: Write a default config file with commented explanations for
every setting. Writes to the path from `--config`, `$VAULTIK_CONFIG`, or the
platform config directory (`~/Library/Application Support/vaultik/` on macOS,
`~/.config/vaultik/` on Linux, `/etc/vaultik/` as root). Refuses to overwrite an
existing file. Created with mode `0600` since it will contain credentials.
**`config edit`**: Open the config file in `$EDITOR` (falls back to `vi`).
**`config get`**: Print a config value addressed by dotted YAML path
(e.g. `vaultik config get s3.bucket`). Non-scalar values print as YAML.
**`config set`**: Set a scalar config value by dotted YAML path
(e.g. `vaultik config set compression_level 9`). Comments and formatting
in the file are preserved; intermediate maps are created as needed.
**`snapshot create`**: Perform incremental backup of configured snapshots.
**snapshot create**: Perform incremental backup of configured snapshots
* Config is located at `/etc/vaultik/config.yml` by default
* Optional snapshot names argument to create specific snapshots (default: all)
* On macOS, the terminal application running vaultik needs Full Disk Access
(System Settings → Privacy & Security → Full Disk Access) to read
TCC-protected directories; without it the backup aborts with a permission
error that explains how to fix it
* `--cron`: Silent unless error (for crontab)
* `--prune`: After backup, drop older snapshots of each backed-up name and
remove orphaned blobs from remote storage. By default keeps only the latest
snapshot per name; use `--keep-newer-than` for a rolling window.
* `--keep-newer-than <duration>`: With `--prune`, keep snapshots newer than
this duration instead of only the latest (e.g. `4w`, `30d`, `6mo`, `1y`)
* `--daemon`: Run continuously with inotify monitoring and periodic scans
* `--prune`: Delete old snapshots and orphaned blobs after backup
**`snapshot list`**: List all snapshots with their timestamps and sizes.
**snapshot list**: List all snapshots with their timestamps and sizes
* `--json`: Output in JSON format
**`snapshot verify`**: Verify snapshot integrity.
* Default (shallow): checks that all blobs referenced in the manifest exist in storage
* `--deep`: Downloads and decrypts each blob, verifies chunk hashes against the
encrypted metadata database
* `--json`: Output results as JSON
**snapshot verify**: Verify snapshot integrity
* `--deep`: Download and verify blob contents (not just existence)
**`snapshot purge`**: Remove old snapshots based on criteria. Retention is
per-snapshot-name (`--keep-latest` keeps the latest of each name, not the
latest globally).
* `--keep-latest`: Keep only the most recent snapshot of each name
* `--older-than <duration>`: Remove snapshots older than duration (e.g. `30d`, `6m`, `1y`)
* `--snapshot <name>`: Restrict to specific snapshot names (repeat for multiple)
**snapshot purge**: Remove old snapshots based on criteria
* `--keep-latest`: Keep only the most recent snapshot
* `--older-than`: Remove snapshots older than duration (e.g., 30d, 6mo, 1y)
* `--force`: Skip confirmation prompt
**`snapshot remove`**: Remove a specific snapshot from the local database.
* `--remote`: Also remove snapshot metadata from remote storage
* `--all`: Remove all snapshots (requires `--force`)
**snapshot remove**: Remove a specific snapshot
* `--dry-run`: Show what would be deleted without deleting
* `--force`: Skip confirmation prompt
* `--json`: Output result as JSON
**`snapshot prune`**: Clean orphaned data from the local database (files,
chunks, blobs not referenced by any snapshot).
**snapshot prune**: Clean orphaned data from local database
**`snapshot cleanup`**: Remove stale local snapshot records that have no
corresponding metadata in remote storage. These are typically left behind
by incomplete or interrupted backups. Does not touch remote storage.
**`restore`**: Restore files from a backup snapshot.
* Requires `VAULTIK_AGE_SECRET_KEY` environment variable
**restore**: Restore snapshot to target directory
* Requires `VAULTIK_AGE_SECRET_KEY` environment variable with age private key
* Optional path arguments to restore specific files/directories (default: all)
* Preserves file permissions, timestamps, ownership (ownership requires root),
symlinks, and empty directories
* `--verify`: After restoring, verify every file's chunk hashes match
* Downloads and decrypts metadata, fetches required blobs, reconstructs files
* Preserves file permissions, timestamps, and ownership (ownership requires root)
* Handles symlinks and directories
**`prune`**: Remove unreferenced blobs from remote storage.
* Scans all snapshot manifests for referenced blobs, deletes any blob not referenced
* `--force`: Skip confirmation prompt
* `--json`: Output stats as JSON
**prune**: Remove unreferenced blobs from remote storage
* Scans all snapshots for referenced blobs
* Deletes orphaned blobs
**`info`**: Display system configuration, storage settings, encryption
recipients, and local database statistics.
**info**: Display system and configuration information
**`remote info`**: Show detailed remote storage information including per-snapshot
metadata sizes, blob counts, and orphaned blob detection.
* `--json`: Output as JSON
**`remote nuke`**: Delete every snapshot's metadata and every blob from the
backup destination store, leaving the bucket prefix empty. Destructive and
irreversible.
* `--force`: Required to confirm destruction.
**`store info`**: Display storage backend type and statistics.
**`database purge`**: Delete the local SQLite state database entirely. Remote
storage is unaffected; the next backup will do a full scan and re-deduplicate
against existing remote blobs.
* `--force`: Skip confirmation prompt
---
## storage backends
vaultik supports three storage backends, selected via the `storage_url` config field:
**S3** (`s3://bucket/prefix?endpoint=host&region=us-east-1`): Any S3-compatible
object store. Credentials are read from `s3.access_key_id` and
`s3.secret_access_key` in the config file.
**Local filesystem** (`file:///path/to/backup`): Stores blobs and metadata on
a local or mounted filesystem. Useful for testing or backing up to a NAS.
**Rclone** (`rclone://remote/path`): Uses rclone's 70+ supported cloud
providers. Requires rclone to be configured separately (`rclone config`).
Legacy S3 configuration via `s3.*` fields (endpoint, bucket, prefix, etc.) is
still supported for backward compatibility. `storage_url` takes precedence if
both are set.
**store info**: Display S3 bucket configuration and storage statistics
---
## architecture
### remote storage layout
### s3 bucket layout
```
<bucket>/<prefix>/
s3://<bucket>/<prefix>/
├── blobs/
│ └── <aa>/<bb>/<full_blob_hash>
└── metadata/
└── <snapshot_id>/
├── db.zst.age # Encrypted binary SQLite database
└── manifest.json.zst # Unencrypted blob list (for pruning)
├── <snapshot_id>/
│ ├── db.zst.age
│ └── manifest.json.zst
```
* Blobs are two-level directory sharded using the first 4 hex chars of the blob hash
* `db.zst.age` is a binary SQLite database (zstd compressed, age encrypted)
containing all file metadata, chunk mappings, and relationships for the snapshot
* `manifest.json.zst` is an unencrypted compressed JSON blob list, enabling
pruning without the private key
* `blobs/<aa>/<bb>/...`: Two-level directory sharding using first 4 hex chars of blob hash
* `metadata/<snapshot_id>/db.zst.age`: Encrypted, compressed SQLite database
* `metadata/<snapshot_id>/manifest.json.zst`: Unencrypted blob list for pruning
Snapshot IDs follow the format `<hostname>_<snapshot-name>_<RFC3339-timestamp>`
(e.g. `server1_home_2025-06-01T12:00:00Z`).
### blob manifest format
The `manifest.json.zst` file is unencrypted (compressed JSON) to enable pruning without decryption:
```json
{
"snapshot_id": "hostname_snapshotname_2025-01-01T12:00:00Z",
"blob_hashes": [
"aa1234567890abcdef...",
"bb2345678901bcdef0..."
]
}
```
Snapshot IDs follow the format `<hostname>_<snapshot-name>_<timestamp>` (e.g., `server1_home_2025-01-01T12:00:00Z`).
### local sqlite schema
```sql
CREATE TABLE files (
id TEXT PRIMARY KEY,
path TEXT NOT NULL UNIQUE,
mtime INTEGER NOT NULL,
size INTEGER NOT NULL,
mode INTEGER NOT NULL,
uid INTEGER NOT NULL,
gid INTEGER NOT NULL
);
CREATE TABLE file_chunks (
file_id TEXT NOT NULL,
idx INTEGER NOT NULL,
chunk_hash TEXT NOT NULL,
PRIMARY KEY (file_id, idx),
FOREIGN KEY (file_id) REFERENCES files(id) ON DELETE CASCADE
);
CREATE TABLE chunks (
chunk_hash TEXT PRIMARY KEY,
size INTEGER NOT NULL
);
CREATE TABLE blobs (
id TEXT PRIMARY KEY,
blob_hash TEXT NOT NULL UNIQUE,
uncompressed INTEGER NOT NULL,
compressed INTEGER NOT NULL,
uploaded_at INTEGER
);
CREATE TABLE blob_chunks (
blob_hash TEXT NOT NULL,
chunk_hash TEXT NOT NULL,
offset INTEGER NOT NULL,
length INTEGER NOT NULL,
PRIMARY KEY (blob_hash, chunk_hash)
);
CREATE TABLE chunk_files (
chunk_hash TEXT NOT NULL,
file_id TEXT NOT NULL,
file_offset INTEGER NOT NULL,
length INTEGER NOT NULL,
PRIMARY KEY (chunk_hash, file_id)
);
CREATE TABLE snapshots (
id TEXT PRIMARY KEY,
hostname TEXT NOT NULL,
vaultik_version TEXT NOT NULL,
started_at INTEGER NOT NULL,
completed_at INTEGER,
file_count INTEGER NOT NULL,
chunk_count INTEGER NOT NULL,
blob_count INTEGER NOT NULL,
total_size INTEGER NOT NULL,
blob_size INTEGER NOT NULL,
compression_ratio REAL NOT NULL
);
CREATE TABLE snapshot_files (
snapshot_id TEXT NOT NULL,
file_id TEXT NOT NULL,
PRIMARY KEY (snapshot_id, file_id)
);
CREATE TABLE snapshot_blobs (
snapshot_id TEXT NOT NULL,
blob_id TEXT NOT NULL,
blob_hash TEXT NOT NULL,
PRIMARY KEY (snapshot_id, blob_id)
);
```
### data flow
**backup:**
#### backup
1. Open local SQLite index, load known files and chunks into memory
2. Walk source directories, compare mtime/size/mode against index
3. For changed/new files: chunk using content-defined chunking (FastCDC)
4. For symlinks and directories: record metadata (no chunking)
5. For each chunk: hash, check dedup, add to blob packer
6. When blob reaches size threshold: compress (zstd), encrypt (age), upload
7. Build snapshot metadata database, compress, encrypt, upload
8. Create unencrypted blob manifest for pruning support
1. Load config, open local SQLite index
1. Walk source directories, check mtime/size against index
1. For changed/new files: chunk using content-defined chunking
1. For each chunk: hash, check if already uploaded, add to blob packer
1. When blob reaches threshold: compress, encrypt, upload to S3
1. Build snapshot metadata, compress, encrypt, upload
1. Create blob manifest (unencrypted) for pruning support
**restore:**
#### restore
1. Download and decrypt `metadata/<snapshot_id>/db.zst.age`
2. Open the binary SQLite database
3. Query files (optionally filtered by paths)
4. Download and decrypt required blobs
5. Extract chunks, reconstruct files
6. Restore permissions, timestamps, ownership, symlinks
1. Download `metadata/<snapshot_id>/db.zst.age`
1. Decrypt and decompress SQLite database
1. Query files table (optionally filtered by paths)
1. For each file, get ordered chunk list from file_chunks
1. Download required blobs, decrypt, decompress
1. Extract chunks and reconstruct files
1. Restore permissions, mtime, uid/gid
**prune:**
#### prune
1. List all snapshot manifests
2. Build set of all referenced blob hashes
3. List all blobs in storage
4. Delete any blob not in the referenced set
1. Build set of all referenced blob hashes
1. List all blobs in storage
1. Delete any blob not in referenced set
### chunking and deduplication
### chunking
* Content-defined chunking using the FastCDC algorithm
* Content-defined chunking using FastCDC algorithm
* Average chunk size: configurable (default 10MB)
* Deduplication at file level (unchanged files skipped) and chunk level
(identical chunks across files stored once)
* Multiple chunks packed into blobs to reduce object count
* Deduplication at chunk level
* Multiple chunks packed into blobs for efficiency
### encryption
* Asymmetric encryption using age (X25519 + XChaCha20-Poly1305)
* Only the public key is needed on the source host
* Each blob and each metadata database is encrypted independently
* Multiple recipients supported (encrypt to multiple keys)
* Only public key needed on source host
* Each blob encrypted independently
* Metadata databases also encrypted
### compression
* zstd compression at configurable level (1-19, default 3)
* Applied before encryption at the blob level
* zstd compression at configurable level
* Applied before encryption
* Blob-level compression for efficiency
---
## configuration reference
## does not
Run `vaultik config init` to generate a fully commented config file.
Key fields:
* Store any secrets on the backed-up machine
* Require mutable remote metadata
* Use tarballs, restic, rsync, or ssh
* Require a symmetric passphrase or password
* Trust the source system with anything
| Field | Default | Description |
|-------|---------|-------------|
| `age_recipients` | (required) | Age public keys for encryption |
| `snapshots` | (required) | Named snapshot definitions with paths and excludes |
| `storage_url` | | Storage backend URL (`s3://`, `file://`, `rclone://`) |
| `s3.*` | | Legacy S3 configuration (endpoint, bucket, credentials) |
| `exclude` | | Global exclude patterns (applied to all snapshots) |
| `chunk_size` | `10MB` | Average chunk size for content-defined chunking |
| `blob_size_limit` | `10GB` | Maximum blob size before splitting |
| `compression_level` | `3` | zstd compression level (1-19) |
| `hostname` | system hostname | Hostname used in snapshot IDs |
| `index_path` | platform data dir | Local SQLite index path |
## does
* Incremental deduplicated backup
* Blob-packed chunk encryption
* Content-addressed immutable blobs
* Public-key encryption only
* SQLite-based local and snapshot metadata
* Fully stream-processed storage
---
## limitations
* **No extended attributes (xattrs).** ACLs, macOS Finder metadata,
quarantine flags, SELinux labels, and other extended attributes are not
backed up or restored.
* **No hard link detection.** Two hard links to the same inode are backed
up as independent files. Content deduplication means the data is stored
once, but the hard link relationship is lost on restore.
* **No sparse file support.** Sparse files are fully materialized during
backup. A 100 GB sparse VM disk that is mostly zeros will consume the
full (compressed) size in storage.
* **No bandwidth limiting.** Uploads and downloads use whatever bandwidth
is available. There is no `--bwlimit` flag yet.
* **No parallel blob downloads during restore.** Blobs are fetched
sequentially. Restore speed is bound by single-stream throughput.
* **Device nodes, named pipes, and sockets are silently skipped.** Only
regular files, directories, and symlinks are backed up.
* **No database migrations.** If the local SQLite schema changes between
versions, delete the local database (`vaultik database purge`) and run
a full backup. Remote storage is unaffected.
* **Files that change during backup may be inconsistent.** There is no
filesystem snapshot or freeze. If a file is modified between the scan
and chunk phases, the backed-up copy may reflect a partial write.
* **Ownership restoration requires root.** File uid/gid are recorded
and restored, but `chown` requires elevated privileges. Without root,
files are restored with the current user's ownership.
---
## roadmap
Items for future releases:
* Error-condition tests (network failures, disk full, corrupted/missing blobs)
* Parallel blob downloads during restore
* Bandwidth limiting (`--bwlimit`)
* Security audit of encryption implementation
* Man pages and richer `--help` examples
---
## output style
All user-facing output goes through helpers in `internal/ui` and conforms
to a uniform style. Color is enabled when stdout is a TTY and the
`NO_COLOR` environment variable is unset (https://no-color.org/).
Message classes:
| Class | Marker | Alignment | Use for |
|-------|--------|-----------|---------|
| Banner | none | column 0 | The startup line printed once per invocation |
| Begin | `》` (white) | column 0 | An operation is about to start (present-continuous verb) |
| Complete | `》` (green) | column 0 | An operation just finished (past-tense verb) |
| Info | `》` (white) | column 0 | Neutral status update |
| Notice | `》` (cyan) | column 0 | Important note that is not a warning |
| Warning | `⚠️ Warning:` (orange/yellow) | column 0 | Recoverable problem |
| Error | `🛑 ERROR:` (red) | column 0 | Operation aborted |
| Progress | ` 》` (white) | column 2 | Heartbeat or per-item status during a long-running operation |
| Detail | ` 》` (white) | column 2 | Continuation/sub-line of a preceding Complete (visually identical to Progress) |
Conventions:
* Messages are complete English sentences ending with a period.
* Fully qualify terms — say "backup destination store" instead of
"storage", "snapshot source files enumeration" instead of "scan",
"local index database" instead of "database".
* Every operation that emits a Complete also emits a corresponding
Begin. Operations that print only a Begin (because completion is
obvious from a later Begin) should be rare and intentional.
* Use natural verb tense to signal state: "Uploading" for Begin,
"Uploaded" for Complete. Never write the words "begin" or "complete"
in the body — the marker color already conveys that.
* All elapsed and remaining-time fields are explicitly scoped to their
subject: write "blob upload elapsed: 30s, blob upload ETA: 03:15:00
(est remain 14s)", never just "elapsed 30s, ETA 14s".
* "ETA" means an absolute clock time (when the operation will finish),
not a remaining-duration. Use `ui.Time()` for the former and
`ui.Duration()` for the latter, and label both.
* `ui.Time` formats same-day times as `HH:MM:SS` and other-day times as
`YYYY-MM-DD HH:MM:SS`. No timezone — local time is implied.
Value colorizers in `internal/ui` colorize specific value types
consistently. Compose messages from these helpers rather than embedding
ANSI escapes inline:
| Helper | Color | Use for |
|--------|-------|---------|
| `Hex` | cyan | Blob hashes, chunk hashes (truncated to 12 chars + `...`) |
| `Snapshot` | bold cyan | Snapshot IDs (untruncated) |
| `Path` | blue | Filesystem paths |
| `Size` | magenta | Byte counts (human-readable) |
| `Speed` | magenta | Bytes-per-second rates |
| `Duration` | yellow | Elapsed or remaining time |
| `Time` | yellow | Absolute clock times |
| `Count` | magenta | Integer counts with thousands separators |
| `Percent` | magenta | Percentages |
When `NO_COLOR` is set or output is not a TTY, all helpers return plain
text and the marker prefixes (`》`, `Warning:`, `ERROR:`) emit without
ANSI escapes. The emoji prefixes on Warning and Error are always emitted
regardless of color setting (emoji are not color).
## requirements
* Go 1.26 or later
* S3-compatible object storage (or local filesystem, or rclone remote)
## development workflow
All changes follow this workflow. No exceptions.
1. Create a feature branch off `main`.
2. Write tests.
3. Write the implementation.
4. Fix implementation errors until it compiles and tests pass.
5. Fix linting errors (`make lint`).
6. Update documentation and README as required by the change.
7. Format code (`make fmt`).
8. Run `make check` (lint + fmt-check + test). Fix any issues. Repeat until clean.
9. Commit on the branch.
10. Merge to `main`.
11. Push.
Do not commit directly to `main`. Do not skip steps.
Repository policies for AI agents are in [`AGENTS.md`](AGENTS.md).
* Go 1.24 or later
* S3-compatible object storage
* Sufficient disk space for local index (typically <1GB)
## license

128
TODO.md Normal file
View File

@@ -0,0 +1,128 @@
# Vaultik 1.0 TODO
Linear list of tasks to complete before 1.0 release.
## Rclone Storage Backend (Complete)
Add rclone as a storage backend via Go library import, allowing vaultik to use any of rclone's 70+ supported cloud storage providers.
**Configuration:**
```yaml
storage_url: "rclone://myremote/path/to/backups"
```
User must have rclone configured separately (via `rclone config`).
**Implementation Steps:**
1. [x] Add rclone dependency to go.mod
2. [x] Create `internal/storage/rclone.go` implementing `Storer` interface
- `NewRcloneStorer(remote, path)` - init with `configfile.Install()` and `fs.NewFs()`
- `Put` / `PutWithProgress` - use `operations.Rcat()`
- `Get` - use `fs.NewObject()` then `obj.Open()`
- `Stat` - use `fs.NewObject()` for size/metadata
- `Delete` - use `obj.Remove()`
- `List` / `ListStream` - use `operations.ListFn()`
- `Info` - return remote name
3. [x] Update `internal/storage/url.go` - parse `rclone://remote/path` URLs
4. [x] Update `internal/storage/module.go` - add rclone case to `storerFromURL()`
5. [x] Test with real rclone remote
**Error Mapping:**
- `fs.ErrorObjectNotFound` → `ErrNotFound`
- `fs.ErrorDirNotFound` → `ErrNotFound`
- `fs.ErrorNotFoundInConfigFile` → `ErrRemoteNotFound` (new)
---
## CLI Polish (Priority)
1. Improve error messages throughout
- Ensure all errors include actionable context
- Add suggestions for common issues (e.g., "did you set VAULTIK_AGE_SECRET_KEY?")
## Security (Priority)
1. Audit encryption implementation
- Verify age encryption is used correctly
- Ensure no plaintext leaks in logs or errors
- Verify blob hashes are computed correctly
1. Secure memory handling for secrets
- Clear S3 credentials from memory after client init
- Document that age_secret_key is env-var only (already implemented)
## Testing
1. Write integration tests for restore command
1. Write end-to-end integration test
- Create backup
- Verify backup
- Restore backup
- Compare restored files to originals
1. Add tests for edge cases
- Empty directories
- Symlinks
- Special characters in filenames
- Very large files (multi-GB)
- Many small files (100k+)
1. Add tests for error conditions
- Network failures during upload
- Disk full during restore
- Corrupted blobs
- Missing blobs
## Performance
1. Profile and optimize restore performance
- Parallel blob downloads
- Streaming decompression/decryption
- Efficient chunk reassembly
1. Add bandwidth limiting option
- `--bwlimit` flag for upload/download speed limiting
## Documentation
1. Add man page or --help improvements
- Detailed help for each command
- Examples in help output
## Final Polish
1. Ensure version is set correctly in releases
1. Create release process
- Binary releases for supported platforms
- Checksums for binaries
- Release notes template
1. Final code review
- Remove debug statements
- Ensure consistent code style
1. Tag and release v1.0.0
---
## Post-1.0 (Daemon Mode)
1. Implement inotify file watcher for Linux
- Watch source directories for changes
- Track dirty paths in memory
1. Implement FSEvents watcher for macOS
- Watch source directories for changes
- Track dirty paths in memory
1. Implement backup scheduler in daemon mode
- Respect backup_interval config
- Trigger backup when dirty paths exist and interval elapsed
- Implement full_scan_interval for periodic full scans
1. Add proper signal handling for daemon
- Graceful shutdown on SIGTERM/SIGINT
- Complete in-progress backup before exit
1. Write tests for daemon mode

2
cmd/vaultik/main.go
View File

@@ -5,7 +5,7 @@ import (
"runtime"
"runtime/pprof"
"sneak.berlin/go/vaultik/internal/cli"
"git.eeqj.de/sneak/vaultik/internal/cli"
)
func main() {

15
config.example.yml
View File

@@ -291,6 +291,21 @@ storage_url: "rclone://las1stor1//srv/pool.2024.04/backups/heraklion"
# # Default: 5MB
# #part_size: 5MB
# How often to run backups in daemon mode
# Format: 1h, 30m, 24h, etc
# Default: 1h
#backup_interval: 1h
# How often to do a full filesystem scan in daemon mode
# Between full scans, inotify is used to detect changes
# Default: 24h
#full_scan_interval: 24h
# Minimum time between backup runs in daemon mode
# Prevents backups from running too frequently
# Default: 15m
#min_time_between_run: 15m
# Path to local SQLite index database
# This database tracks file state for incremental backups
# Default: /var/lib/vaultik/index.sqlite

11
docs/DATAMODEL.md
View File

@@ -5,14 +5,8 @@
Vaultik uses a local SQLite database to track file metadata, chunk mappings, and blob associations during the backup process. This database serves as an index for incremental backups and enables efficient deduplication.
**Important Notes:**
- **No Migration Support (pre-1.0)**: Vaultik does not support database schema
migrations. The local index is treated as disposable — if the schema changes,
delete the local SQLite database (`vaultik database purge`) and run a full
backup. The remote storage is unaffected; the new index will re-deduplicate
against existing remote blobs.
- **Version Compatibility**: In rare cases, you may need to use the same version
of Vaultik to restore a backup as was used to create it. This ensures
compatibility with the metadata format stored in S3.
- **No Migration Support**: Vaultik does not support database schema migrations. If the schema changes, the local database must be deleted and recreated by performing a full backup.
- **Version Compatibility**: In rare cases, you may need to use the same version of Vaultik to restore a backup as was used to create it. This ensures compatibility with the metadata format stored in S3.
## Database Tables
@@ -23,6 +17,7 @@ Stores metadata about files in the filesystem being backed up.
- `id` (TEXT PRIMARY KEY) - UUID for the file record
- `path` (TEXT NOT NULL UNIQUE) - Absolute file path
- `mtime` (INTEGER NOT NULL) - Modification time as Unix timestamp
- `ctime` (INTEGER NOT NULL) - Change time as Unix timestamp
- `size` (INTEGER NOT NULL) - File size in bytes
- `mode` (INTEGER NOT NULL) - Unix file permissions and type
- `uid` (INTEGER NOT NULL) - User ID of file owner

19
docs/REPOSTRUCTURE.md
View File

@@ -43,19 +43,18 @@ Blobs contain the actual file data from backups and must be encrypted for securi
Each snapshot has its own subdirectory named with the snapshot ID.
### Snapshot ID Format
- **Format**: `<hostname>_<snapshot-name>_<RFC3339>` (or `<hostname>_<RFC3339>` if no
name was specified)
- **Example**: `laptop_home_2024-01-15T14:30:52Z`
- **Format**: `<hostname>-<YYYYMMDD>-<HHMMSSZ>`
- **Example**: `laptop-20240115-143052Z`
- **Components**:
- Short hostname (everything before the first dot is stripped from the FQDN)
- Snapshot name from the configured `snapshots:` map (optional)
- RFC3339 UTC timestamp
- Hostname (may contain hyphens)
- Date in YYYYMMDD format
- Time in HHMMSSZ format (Z indicates UTC)
### Files in Each Snapshot Directory
#### `db.zst.age` - Encrypted Database
- **What it contains**: Pruned binary SQLite database for this snapshot
- **Format**: Binary SQLite → Zstandard compressed → Age encrypted
#### `db.zst.age` - Encrypted Database Dump
- **What it contains**: Complete SQLite database dump for this snapshot
- **Format**: SQL dump → Zstandard compressed → Age encrypted
- **Encryption**: Encrypted with Age
- **Purpose**: Contains full file metadata, chunk mappings, and all relationships
- **Why encrypted**: Contains sensitive metadata like file paths, permissions, and ownership
@@ -68,7 +67,7 @@ Each snapshot has its own subdirectory named with the snapshot ID.
- **Structure**:
```json
{
"snapshot_id": "laptop_home_2024-01-15T14:30:52Z",
"snapshot_id": "laptop-20240115-143052Z",
"timestamp": "2024-01-15T14:30:52Z",
"blob_count": 42,
"blobs": [

8
go.mod
View File

@@ -1,4 +1,4 @@
module sneak.berlin/go/vaultik
module git.eeqj.de/sneak/vaultik
go 1.26.1
@@ -17,12 +17,13 @@ require (
github.com/google/uuid v1.6.0
github.com/johannesboyne/gofakes3 v0.0.0-20250603205740-ed9094be7668
github.com/klauspost/compress v1.18.1
github.com/mattn/go-sqlite3 v1.14.29
github.com/rclone/rclone v1.72.1
github.com/schollz/progressbar/v3 v3.19.0
github.com/spf13/afero v1.15.0
github.com/spf13/cobra v1.10.1
github.com/stretchr/testify v1.11.1
go.uber.org/fx v1.24.0
golang.org/x/sync v0.18.0
golang.org/x/term v0.37.0
gopkg.in/yaml.v3 v3.0.1
modernc.org/sqlite v1.38.0
@@ -185,6 +186,7 @@ require (
github.com/mattn/go-colorable v0.1.14 // indirect
github.com/mattn/go-isatty v0.0.20 // indirect
github.com/mattn/go-runewidth v0.0.19 // indirect
github.com/mitchellh/colorstring v0.0.0-20190213212951-d06e56a500db // indirect
github.com/mitchellh/go-homedir v1.1.0 // indirect
github.com/mitchellh/mapstructure v1.5.0 // indirect
github.com/modern-go/concurrent v0.0.0-20180306012644-bacd9c7ef1dd // indirect
@@ -215,6 +217,7 @@ require (
github.com/relvacode/iso8601 v1.7.0 // indirect
github.com/remyoudompheng/bigfft v0.0.0-20230129092748-24d4a6f8daec // indirect
github.com/rfjakob/eme v1.1.2 // indirect
github.com/rivo/uniseg v0.4.7 // indirect
github.com/ryanuber/go-glob v1.0.0 // indirect
github.com/ryszard/goskiplist v0.0.0-20150312221310-2dfbae5fcf46 // indirect
github.com/sabhiram/go-gitignore v0.0.0-20210923224102-525f6e181f06 // indirect
@@ -263,6 +266,7 @@ require (
golang.org/x/exp v0.0.0-20251023183803-a4bb9ffd2546 // indirect
golang.org/x/net v0.47.0 // indirect
golang.org/x/oauth2 v0.33.0 // indirect
golang.org/x/sync v0.18.0 // indirect
golang.org/x/sys v0.38.0 // indirect
golang.org/x/text v0.31.0 // indirect
golang.org/x/time v0.14.0 // indirect

10
go.sum
View File

@@ -202,6 +202,8 @@ github.com/cespare/xxhash/v2 v2.3.0 h1:UL815xU9SqsFlibzuggzjXhog7bL6oX9BbNZnL2UF
github.com/cespare/xxhash/v2 v2.3.0/go.mod h1:VGX0DQ3Q6kWi7AoAeZDth3/j3BFtOZR5XLFGgcrjCOs=
github.com/cevatbarisyilmaz/ara v0.0.4 h1:SGH10hXpBJhhTlObuZzTuFn1rrdmjQImITXnZVPSodc=
github.com/cevatbarisyilmaz/ara v0.0.4/go.mod h1:BfFOxnUd6Mj6xmcvRxHN3Sr21Z1T3U2MYkYOmoQe4Ts=
github.com/chengxilo/virtualterm v1.0.4 h1:Z6IpERbRVlfB8WkOmtbHiDbBANU7cimRIof7mk9/PwM=
github.com/chengxilo/virtualterm v1.0.4/go.mod h1:DyxxBZz/x1iqJjFxTFcr6/x+jSpqN0iwWCOK1q10rlY=
github.com/chilts/sid v0.0.0-20190607042430-660e94789ec9 h1:z0uK8UQqjMVYzvk4tiiu3obv2B44+XBsvgEJREQfnO8=
github.com/chilts/sid v0.0.0-20190607042430-660e94789ec9/go.mod h1:Jl2neWsQaDanWORdqZ4emBl50J4/aRBBS4FyyG9/PFo=
github.com/chzyer/logex v1.1.10/go.mod h1:+Ywpsq7O8HXn0nuIou7OrIPyXbp3wmkHB+jjWRnGsAI=
@@ -591,12 +593,16 @@ github.com/mattn/go-isatty v0.0.20/go.mod h1:W+V8PltTTMOvKvAeJH7IuucS94S2C6jfK/D
github.com/mattn/go-runewidth v0.0.3/go.mod h1:LwmH8dsx7+W8Uxz3IHJYH5QSwggIsqBzpuz5H//U1FU=
github.com/mattn/go-runewidth v0.0.19 h1:v++JhqYnZuu5jSKrk9RbgF5v4CGUjqRfBm05byFGLdw=
github.com/mattn/go-runewidth v0.0.19/go.mod h1:XBkDxAl56ILZc9knddidhrOlY5R/pDhgLpndooCuJAs=
github.com/mattn/go-sqlite3 v1.14.29 h1:1O6nRLJKvsi1H2Sj0Hzdfojwt8GiGKm+LOfLaBFaouQ=
github.com/mattn/go-sqlite3 v1.14.29/go.mod h1:Uh1q+B4BYcTPb+yiD3kU8Ct7aC0hY9fxUwlHK0RXw+Y=
github.com/matttproud/golang_protobuf_extensions v1.0.1/go.mod h1:D8He9yQNgCq6Z5Ld7szi9bcBfOoFv/3dc6xSMkL2PC0=
github.com/miekg/dns v1.1.26/go.mod h1:bPDLeHnStXmXAq1m/Ch/hvfNHr14JKNPMBo3VZKjuso=
github.com/miekg/dns v1.1.41 h1:WMszZWJG0XmzbK9FEmzH2TVcqYzFesusSIB41b8KHxY=
github.com/miekg/dns v1.1.41/go.mod h1:p6aan82bvRIyn+zDIv9xYNUpwa73JcSh9BKwknJysuI=
github.com/mitchellh/cli v1.0.0/go.mod h1:hNIlj7HEI86fIcpObd7a0FcrxTWetlwJDGcceTlRvqc=
github.com/mitchellh/cli v1.1.0/go.mod h1:xcISNoH86gajksDmfB23e/pu+B+GeFRMYmoHXxx3xhI=
github.com/mitchellh/colorstring v0.0.0-20190213212951-d06e56a500db h1:62I3jR2EmQ4l5rM/4FEfDWcRD+abF5XlKShorW5LRoQ=
github.com/mitchellh/colorstring v0.0.0-20190213212951-d06e56a500db/go.mod h1:l0dey0ia/Uv7NcFFVbCLtqEBQbrT4OCwCSKTEv6enCw=
github.com/mitchellh/go-homedir v1.1.0 h1:lukF9ziXFxDFPkA1vsr5zpc1XuPDn/wFntq5mG+4E0Y=
github.com/mitchellh/go-homedir v1.1.0/go.mod h1:SfyaCUpYCn1Vlf4IUYiD9fPX4A5wJrkLzIz1N1q0pr0=
github.com/mitchellh/go-wordwrap v1.0.0/go.mod h1:ZXFpozHsX6DPmq2I0TCekCxypsnAUbP2oI0UX1GXzOo=
@@ -701,6 +707,8 @@ github.com/remyoudompheng/bigfft v0.0.0-20230129092748-24d4a6f8daec h1:W09IVJc94
github.com/remyoudompheng/bigfft v0.0.0-20230129092748-24d4a6f8daec/go.mod h1:qqbHyh8v60DhA7CoWK5oRCqLrMHRGoxYCSS9EjAz6Eo=
github.com/rfjakob/eme v1.1.2 h1:SxziR8msSOElPayZNFfQw4Tjx/Sbaeeh3eRvrHVMUs4=
github.com/rfjakob/eme v1.1.2/go.mod h1:cVvpasglm/G3ngEfcfT/Wt0GwhkuO32pf/poW6Nyk1k=
github.com/rivo/uniseg v0.4.7 h1:WUdvkW8uEhrYfLC4ZzdpI2ztxP1I582+49Oc5Mq64VQ=
github.com/rivo/uniseg v0.4.7/go.mod h1:FN3SvrM+Zdj16jyLfmOkMNblXMcoc8DfTHruCPUcx88=
github.com/rogpeppe/go-internal v1.3.0/go.mod h1:M8bDsm7K2OlrFYOpmOWEs/qY81heoFRclV5y23lUDJ4=
github.com/rogpeppe/go-internal v1.14.1 h1:UQB4HGPB6osV0SQTLymcB4TgvyWu6ZyliaW0tI/otEQ=
github.com/rogpeppe/go-internal v1.14.1/go.mod h1:MaRKkUm5W0goXpeCfT7UZI6fk/L7L7so1lCWt35ZSgc=
@@ -715,6 +723,8 @@ github.com/sabhiram/go-gitignore v0.0.0-20210923224102-525f6e181f06 h1:OkMGxebDj
github.com/sabhiram/go-gitignore v0.0.0-20210923224102-525f6e181f06/go.mod h1:+ePHsJ1keEjQtpvf9HHw0f4ZeJ0TLRsxhunSI2hYJSs=
github.com/samber/lo v1.52.0 h1:Rvi+3BFHES3A8meP33VPAxiBZX/Aws5RxrschYGjomw=
github.com/samber/lo v1.52.0/go.mod h1:4+MXEGsJzbKGaUEQFKBq2xtfuznW9oz/WrgyzMzRoM0=
github.com/schollz/progressbar/v3 v3.19.0 h1:Ea18xuIRQXLAUidVDox3AbwfUhD0/1IvohyTutOIFoc=
github.com/schollz/progressbar/v3 v3.19.0/go.mod h1:IsO3lpbaGuzh8zIMzgY3+J8l4C8GjO0Y9S69eFvNsec=
github.com/sean-/seed v0.0.0-20170313163322-e2103e2c3529 h1:nn5Wsu0esKSJiIVhscUtVbo7ada43DJhG55ua/hjS5I=
github.com/sean-/seed v0.0.0-20170313163322-e2103e2c3529/go.mod h1:DxrIzT+xaE7yg65j358z/aeFdxmN0P9QXhEzd20vsDc=
github.com/sergi/go-diff v1.0.0/go.mod h1:0CfEIISq7TuYL3j771MWULgwwjU+GofnZX9QAmXWZgo=

8
internal/blob/packer.go
View File

@@ -23,12 +23,12 @@ import (
"sync"
"time"
"git.eeqj.de/sneak/vaultik/internal/blobgen"
"git.eeqj.de/sneak/vaultik/internal/database"
"git.eeqj.de/sneak/vaultik/internal/log"
"git.eeqj.de/sneak/vaultik/internal/types"
"github.com/google/uuid"
"github.com/spf13/afero"
"sneak.berlin/go/vaultik/internal/blobgen"
"sneak.berlin/go/vaultik/internal/database"
"sneak.berlin/go/vaultik/internal/log"
"sneak.berlin/go/vaultik/internal/types"
)
// BlobHandler is a callback function invoked when a blob is finalized and ready for upload.

6
internal/blob/packer_test.go
View File

@@ -10,11 +10,11 @@ import (
"testing"
"filippo.io/age"
"git.eeqj.de/sneak/vaultik/internal/database"
"git.eeqj.de/sneak/vaultik/internal/log"
"git.eeqj.de/sneak/vaultik/internal/types"
"github.com/klauspost/compress/zstd"
"github.com/spf13/afero"
"sneak.berlin/go/vaultik/internal/database"
"sneak.berlin/go/vaultik/internal/log"
"sneak.berlin/go/vaultik/internal/types"
)
const (

64
internal/cli/app.go
View File

@@ -7,21 +7,19 @@ import (
"os"
"os/signal"
"path/filepath"
"strings"
"syscall"
"time"
"git.eeqj.de/sneak/vaultik/internal/config"
"git.eeqj.de/sneak/vaultik/internal/database"
"git.eeqj.de/sneak/vaultik/internal/globals"
"git.eeqj.de/sneak/vaultik/internal/log"
"git.eeqj.de/sneak/vaultik/internal/pidlock"
"git.eeqj.de/sneak/vaultik/internal/snapshot"
"git.eeqj.de/sneak/vaultik/internal/storage"
"git.eeqj.de/sneak/vaultik/internal/vaultik"
"github.com/adrg/xdg"
"go.uber.org/fx"
"sneak.berlin/go/vaultik/internal/config"
"sneak.berlin/go/vaultik/internal/database"
"sneak.berlin/go/vaultik/internal/globals"
"sneak.berlin/go/vaultik/internal/log"
"sneak.berlin/go/vaultik/internal/pidlock"
"sneak.berlin/go/vaultik/internal/snapshot"
"sneak.berlin/go/vaultik/internal/storage"
"sneak.berlin/go/vaultik/internal/ui"
"sneak.berlin/go/vaultik/internal/vaultik"
)
// AppOptions contains common options for creating the fx application.
@@ -34,36 +32,16 @@ type AppOptions struct {
Invokes []fx.Option
}
// setupGlobals records the startup time and, when an output-suppression
// flag is active, marks the UI writer quiet so that Begin/Complete/
// Info/Notice/Detail/Progress are silenced. Warning and Error are NOT
// silenced — per the documented convention that --quiet suppresses
// non-error output only. The startup banner is printed by CLIEntry
// before cobra parses arguments, gated by the same arg-level check.
func setupGlobals(lc fx.Lifecycle, g *globals.Globals, v *vaultik.Vaultik, opts log.LogOptions) {
// setupGlobals sets up the globals with application startup time
func setupGlobals(lc fx.Lifecycle, g *globals.Globals) {
lc.Append(fx.Hook{
OnStart: func(ctx context.Context) error {
g.StartTime = time.Now().UTC()
if opts.Cron || opts.Quiet {
v.UI.SetQuiet(true)
}
return nil
},
})
}
// writeStartupBanner prints the two-line application banner followed by a
// blank line. Used both from the fx hook (for subcommand invocations) and
// from the root cobra Run handler (for `vaultik` with no subcommand).
func writeStartupBanner(w *ui.Writer, startTime time.Time, shortCommit string) {
w.Banner("%s %s by %s (commit %s, built on %s) starting up at %s.",
globals.Appname, globals.Version, globals.Author,
shortCommit, globals.CommitDate,
startTime.Format(time.RFC3339))
w.Banner("%s", globals.Homepage)
w.Banner("")
}
// NewApp creates a new fx application with common modules.
// It sets up the base modules (config, database, logging, globals) and
// combines them with any additional modules specified in the options.
@@ -90,24 +68,6 @@ func NewApp(opts AppOptions) *fx.App {
return fx.New(allOptions...)
}
// cleanStartupError strips fx's dependency-injection call-chain noise from
// startup errors. fx wraps the underlying error with messages like
//
// could not build arguments for function "X" (file:line): failed to build T:
// could not build arguments for function "Y" (file:line): failed to build U:
// received non-nil error from function "Z" (file:line): <real error>
//
// Users care about the real error, not the DI plumbing. We strip everything
// up through the last "): " (which is always the close-paren of an fx
// function-location annotation followed by the wrapped error).
func cleanStartupError(err error) error {
msg := err.Error()
if idx := strings.LastIndex(msg, "): "); idx >= 0 {
msg = msg[idx+3:]
}
return errors.New(msg)
}
// RunApp starts and stops the fx application within the given context.
// It handles graceful shutdown on interrupt signals (SIGINT, SIGTERM) and
// ensures the application stops cleanly. The function blocks until the
@@ -123,7 +83,7 @@ func RunApp(ctx context.Context, app *fx.App) error {
// Start the app
if err := app.Start(ctx); err != nil {
return cleanStartupError(err)
return fmt.Errorf("failed to start app: %w", err)
}
// Handle shutdown
@@ -165,7 +125,7 @@ func RunApp(ctx context.Context, app *fx.App) error {
// It acquires a PID lock before starting to prevent concurrent instances.
func RunWithApp(ctx context.Context, opts AppOptions) error {
// Acquire PID lock to prevent concurrent instances
lockDir := filepath.Join(xdg.DataHome, "vaultik")
lockDir := filepath.Join(xdg.DataHome, "berlin.sneak.app.vaultik")
lock, err := pidlock.Acquire(lockDir)
if err != nil {
if errors.Is(err, pidlock.ErrAlreadyRunning) {

39
internal/cli/app_test.go
View File

@@ -1,39 +0,0 @@
package cli
import (
"errors"
"testing"
)
func TestCleanStartupError(t *testing.T) {
tests := []struct {
name string
in string
want string
}{
{
name: "real fx error chain",
in: `could not build arguments for function "sneak.berlin/go/vaultik/internal/cli".newSnapshotCreateCommand.func1.1 (/Users/user/dev/vaultik/internal/cli/snapshot.go:71): failed to build *vaultik.Vaultik: could not build arguments for function "sneak.berlin/go/vaultik/internal/vaultik".New (/Users/user/dev/vaultik/internal/vaultik/vaultik.go:59): failed to build storage.Storer: received non-nil error from function "sneak.berlin/go/vaultik/internal/storage".NewStorer (/Users/user/dev/vaultik/internal/storage/module.go:23): creating base path: mkdir /Volumes/BACKUPS: permission denied`,
want: `creating base path: mkdir /Volumes/BACKUPS: permission denied`,
},
{
name: "no fx wrapping",
in: "plain error",
want: "plain error",
},
{
name: "single fx wrapping",
in: `received non-nil error from function "foo" (file.go:1): underlying problem`,
want: "underlying problem",
},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
got := cleanStartupError(errors.New(tt.in)).Error()
if got != tt.want {
t.Errorf("got %q, want %q", got, tt.want)
}
})
}
}

522
internal/cli/config.go
View File

@@ -1,522 +0,0 @@
package cli
import (
"fmt"
"os"
"os/exec"
"path/filepath"
"strconv"
"strings"
"github.com/spf13/cobra"
"gopkg.in/yaml.v3"
)
const defaultConfigTemplate = `# vaultik configuration
# Documentation: https://sneak.berlin/go/vaultik
# ─── REQUIRED ────────────────────────────────────────────────────────────────
# Age recipient public keys for encryption.
# Backups are encrypted to ALL listed recipients. Any one of the corresponding
# private keys can decrypt. Generate a keypair with:
# age-keygen -o vaultik_backup_private_key.txt
# grep 'public key' vaultik_backup_private_key.txt
age_recipients:
- age1REPLACE_WITH_YOUR_PUBLIC_KEY
# Named snapshots. Each snapshot backs up one or more paths and can have its
# own exclude patterns in addition to the global excludes below.
#
# Exclude pattern semantics:
# - Patterns starting with / are anchored to the snapshot path root
# (e.g. "/Library/Caches" matches only ~/Library/Caches in a ~ snapshot)
# - Patterns without a leading / match anywhere in the tree
# (e.g. ".cache" matches any directory named .cache at any depth)
# - Globs are supported: *, **, ?
snapshots:
home:
paths:
- "~"
exclude:
# Trash, temp, and filesystem metadata
- "/.Trash"
- "/.Trashes"
- "/.fseventsd"
- "/.Spotlight-V100"
- "/.TemporaryItems"
- "/tmp"
- "/.rnd"
- ".DS_Store"
# Caches and package manager state (rebuildable)
- ".cache"
- ".bundle"
- "/.cpan/build"
- "/.cpan/sources"
- "/.gradle/caches"
- "/.dropbox"
- "/.minikube/cache"
- "/.local/share/containers/podman/machine"
- "/.persepolis"
- "/Library/Caches"
- "/Library/Logs"
- "/Library/Cookies"
- "/Library/Metadata"
- "/Library/Suggestions"
- "/Library/PubSub"
- "/Library/Homebrew"
- "/Library/Developer"
- "/Library/Google/GoogleSoftwareUpdate"
- "/Library/Preferences/Macromedia/Flash Player"
- "/Library/Preferences/SDMHelpData"
- "/Library/VoiceTrigger/SAT"
# Language/toolchain package caches (rebuildable from registries)
- "/.npm"
- "/.cargo/registry"
- "/.cargo/git"
- "/.rustup/toolchains"
- "/go/pkg/mod"
- "/.m2/repository"
- "/.vagrant.d/boxes"
- "node_modules"
- "__pycache__"
- ".venv"
# Virtual machine disk images (huge; remove these lines to back them up)
- "/Parallels"
- "/Virtual Machines.localized"
- "/VirtualBox VMs"
- "/.orbstack"
- "/Library/Containers/com.utmapp.UTM"
# Downloaded LLM models (huge, re-downloadable)
- "/.ollama/models"
- "/.lmstudio/models"
# Cloud-synced storage. These are synced to a provider already, and on
# modern macOS may contain dataless placeholder files that the backup
# would force-download in full.
- "/Library/CloudStorage"
- "/Library/Mobile Documents"
# Android SDK and emulator images (re-downloadable)
- "/Library/Android/sdk"
- "/.android/avd"
# Cloud-synced or restorable-from-server data
- "/Library/Mail"
- "/Library/Mail Downloads"
- "/Library/Safari"
- "/Library/Application Support/Evernote"
- "/Library/Application Support/MobileSync"
- "/Library/Application Support/SyncServices"
- "/Library/Application Support/protonmail/bridge/cache"
- "/Library/Application Support/Syncthing/index-*"
- "/Library/Syncthing/folders"
- "/Documents/Dropbox/.dropbox.cache"
# Large rebuildable app data (games, media caches, device backups)
- "/Applications/Fortnite"
- "/Documents/Steam Content"
- "/Library/Application Support/Ableton"
- "/Library/Application Support/CrossOver Games"
- "/Library/Application Support/SecondLife/cache"
- "/Library/Application Support/Steam/SteamApps"
- "/Library/Containers/com.docker.docker"
- "/Library/Group Containers/group.com.apple.secure-control-center-preferences"
- "/Library/iTunes/iPad Software Updates"
- "/Library/iTunes/iPhone Software Updates"
- "/Movies/CacheClip"
- "/Movies/ProxyMedia"
- "/Music/iTunes/Album Artwork"
- "/Pictures/iPod Photo Cache"
# Third-party applications. OS-provided apps live in /System/Applications
# on modern macOS and are never in /Applications, but Apple-installed
# App Store apps (Safari, GarageBand, iWork, iMovie) are excluded since
# they are re-downloadable.
apps:
paths:
- /Applications
exclude:
- ".DS_Store"
- "/Safari.app"
- "/GarageBand.app"
- "/iMovie.app"
- "/Keynote.app"
- "/Numbers.app"
- "/Pages.app"
- "/Xcode.app"
- "/Spotify.app"
- "/Steam.app"
- "/VirtualBox.app"
- "/Utilities/Adobe Installers"
# Storage backend (pick ONE of the three forms below).
#
# S3-compatible:
# storage_url: "s3://mybucket/backups?endpoint=s3.example.com&region=us-east-1"
# (also set s3.access_key_id and s3.secret_access_key below)
#
# Local filesystem:
# storage_url: "file:///mnt/backups/vaultik"
#
# Rclone (requires rclone configured separately):
# storage_url: "rclone://myremote/path/to/backups"
storage_url: ""
# ─── S3 CREDENTIALS (required for s3:// storage_url) ────────────────────────
# s3:
# access_key_id: YOUR_ACCESS_KEY
# secret_access_key: YOUR_SECRET_KEY
# # region: us-east-1 # Default: us-east-1
# # use_ssl: true # Default: true
# # part_size: 5MB # Multipart upload part size. Default: 5MB
# ─── OPTIONAL ────────────────────────────────────────────────────────────────
# Global exclude patterns applied to ALL snapshots.
# Snapshot-specific excludes are additive.
# exclude:
# - "*.log"
# - "*.tmp"
# - ".git"
# - "node_modules"
# Average chunk size for content-defined chunking (FastCDC).
# Smaller = better deduplication but more metadata overhead.
# Accepts: 1MB, 10M, 64KB, etc.
# Default: 10MB
# chunk_size: 10MB
# Maximum blob size before splitting into a new blob.
# Accepts: 1GB, 10G, 500MB, etc.
# Default: 10GB
# blob_size_limit: 10GB
# Zstd compression level (1-19). Higher = better ratio but slower.
# Default: 3
# compression_level: 3
# Hostname used in snapshot IDs. Default: system hostname.
# hostname: myserver
# Path to the local SQLite index database.
# Default: the platform data directory, e.g.
# macOS: ~/Library/Application Support/vaultik/index.sqlite
# Linux: ~/.local/share/vaultik/index.sqlite
# index_path: /path/to/index.sqlite
`
// NewConfigCommand creates the config command group.
func NewConfigCommand() *cobra.Command {
cmd := &cobra.Command{
Use: "config",
Short: "Manage the configuration file",
Long: "Commands for creating, editing, and querying the vaultik config file.",
}
cmd.AddCommand(newConfigInitCommand())
cmd.AddCommand(newConfigEditCommand())
cmd.AddCommand(newConfigGetCommand())
cmd.AddCommand(newConfigSetCommand())
return cmd
}
// newConfigInitCommand creates the 'config init' subcommand.
func newConfigInitCommand() *cobra.Command {
return &cobra.Command{
Use: "init",
Short: "Write a default config file",
Long: `Creates a default configuration file with commented explanations
for every setting. If a config file already exists at the target path,
the command refuses to overwrite it.
The config is written to the path from --config, $VAULTIK_CONFIG, or
the platform default config directory (e.g. ~/Library/Application Support/
on macOS, ~/.config/ on Linux, /etc/vaultik/ as root).`,
Args: cobra.NoArgs,
RunE: func(cmd *cobra.Command, args []string) error {
path := configPathForInit()
if _, err := os.Stat(path); err == nil {
return fmt.Errorf("config file already exists: %s", path)
}
dir := filepath.Dir(path)
if err := os.MkdirAll(dir, 0o755); err != nil {
return fmt.Errorf("creating config directory %s: %w", dir, err)
}
if err := os.WriteFile(path, []byte(defaultConfigTemplate), 0o600); err != nil {
return fmt.Errorf("writing config file: %w", err)
}
fmt.Printf("Config written to %s\n", path)
fmt.Println("Edit it to set your age_recipients, snapshots, and storage_url.")
return nil
},
}
}
// newConfigEditCommand creates the 'config edit' subcommand.
func newConfigEditCommand() *cobra.Command {
return &cobra.Command{
Use: "edit",
Short: "Open the config file in $EDITOR",
Args: cobra.NoArgs,
RunE: func(cmd *cobra.Command, args []string) error {
path, err := ResolveConfigPath()
if err != nil {
return err
}
editor := os.Getenv("EDITOR")
if editor == "" {
editor = "vi"
}
ed := exec.Command(editor, path)
ed.Stdin = os.Stdin
ed.Stdout = os.Stdout
ed.Stderr = os.Stderr
return ed.Run()
},
}
}
// newConfigGetCommand creates the 'config get' subcommand.
func newConfigGetCommand() *cobra.Command {
return &cobra.Command{
Use: "get <key>",
Short: "Print a config value by dotted path (e.g. s3.bucket)",
Args: cobra.ExactArgs(1),
RunE: func(cmd *cobra.Command, args []string) error {
path, err := ResolveConfigPath()
if err != nil {
return err
}
root, err := loadYAMLFile(path)
if err != nil {
return err
}
node, err := yamlPathGet(root, strings.Split(args[0], "."))
if err != nil {
return err
}
if node.Kind == yaml.ScalarNode {
fmt.Println(node.Value)
return nil
}
out, err := yaml.Marshal(node)
if err != nil {
return fmt.Errorf("marshaling value: %w", err)
}
fmt.Print(string(out))
return nil
},
}
}
// newConfigSetCommand creates the 'config set' subcommand.
func newConfigSetCommand() *cobra.Command {
return &cobra.Command{
Use: "set <key> <value>",
Short: "Set a config value by dotted path (e.g. compression_level 5)",
Long: `Sets a scalar config value addressed by dotted YAML path and writes
the file back, preserving comments and formatting. Intermediate maps
are created as needed.
Examples:
vaultik config set compression_level 9
vaultik config set s3.bucket mybucket
vaultik config set storage_url "file:///mnt/backups"`,
Args: cobra.ExactArgs(2),
RunE: func(cmd *cobra.Command, args []string) error {
path, err := ResolveConfigPath()
if err != nil {
return err
}
root, err := loadYAMLFile(path)
if err != nil {
return err
}
if err := yamlPathSet(root, strings.Split(args[0], "."), args[1]); err != nil {
return err
}
out, err := yaml.Marshal(root)
if err != nil {
return fmt.Errorf("marshaling config: %w", err)
}
mode := os.FileMode(0o600)
if info, err := os.Stat(path); err == nil {
mode = info.Mode().Perm()
}
if err := os.WriteFile(path, out, mode); err != nil {
return fmt.Errorf("writing config file: %w", err)
}
fmt.Printf("%s = %s\n", args[0], args[1])
return nil
},
}
}
// loadYAMLFile parses a YAML file into a yaml.Node document tree,
// which preserves comments and ordering for round-tripping.
func loadYAMLFile(path string) (*yaml.Node, error) {
data, err := os.ReadFile(path)
if err != nil {
return nil, fmt.Errorf("reading config file: %w", err)
}
var root yaml.Node
if err := yaml.Unmarshal(data, &root); err != nil {
return nil, fmt.Errorf("parsing config file: %w", err)
}
// An empty file yields a zero node; normalize to an empty mapping document.
if root.Kind == 0 {
root = yaml.Node{
Kind: yaml.DocumentNode,
Content: []*yaml.Node{{Kind: yaml.MappingNode}},
}
}
return &root, nil
}
// yamlPathGet navigates a dotted key path through mapping and sequence
// nodes and returns the value node. Numeric path components index into
// sequences (e.g. "age_recipients.0").
func yamlPathGet(root *yaml.Node, keys []string) (*yaml.Node, error) {
node := root
if node.Kind == yaml.DocumentNode {
if len(node.Content) == 0 {
return nil, fmt.Errorf("empty config file")
}
node = node.Content[0]
}
for i, key := range keys {
switch node.Kind {
case yaml.MappingNode:
found := false
for j := 0; j+1 < len(node.Content); j += 2 {
if node.Content[j].Value == key {
node = node.Content[j+1]
found = true
break
}
}
if !found {
return nil, fmt.Errorf("key not found: %s", strings.Join(keys[:i+1], "."))
}
case yaml.SequenceNode:
idx, err := strconv.Atoi(key)
if err != nil {
return nil, fmt.Errorf("key %q is a list; use a numeric index", strings.Join(keys[:i], "."))
}
if idx < 0 || idx >= len(node.Content) {
return nil, fmt.Errorf("index %d out of range for %s (len %d)", idx, strings.Join(keys[:i], "."), len(node.Content))
}
node = node.Content[idx]
default:
return nil, fmt.Errorf("key %q is not a map or list", strings.Join(keys[:i], "."))
}
}
return node, nil
}
// yamlPathSet navigates a dotted key path, creating intermediate maps as
// needed, and sets the final key to the given scalar value. Numeric path
// components index into sequences; an index equal to the sequence length
// appends a new element (e.g. "age_recipients.1" on a 1-element list).
func yamlPathSet(root *yaml.Node, keys []string, value string) error {
node := root
if node.Kind == yaml.DocumentNode {
if len(node.Content) == 0 {
node.Content = []*yaml.Node{{Kind: yaml.MappingNode}}
}
node = node.Content[0]
}
for i, key := range keys {
last := i == len(keys)-1
switch node.Kind {
case yaml.MappingNode:
var valueNode *yaml.Node
for j := 0; j+1 < len(node.Content); j += 2 {
if node.Content[j].Value == key {
valueNode = node.Content[j+1]
break
}
}
if valueNode == nil {
keyNode := &yaml.Node{Kind: yaml.ScalarNode, Value: key}
valueNode = &yaml.Node{Kind: yaml.MappingNode}
if last {
valueNode = &yaml.Node{Kind: yaml.ScalarNode, Value: value}
}
node.Content = append(node.Content, keyNode, valueNode)
} else if last {
setScalar(valueNode, value)
}
node = valueNode
case yaml.SequenceNode:
idx, err := strconv.Atoi(key)
if err != nil {
return fmt.Errorf("key %q is a list; use a numeric index", strings.Join(keys[:i], "."))
}
if idx < 0 || idx > len(node.Content) {
return fmt.Errorf("index %d out of range for %s (len %d)", idx, strings.Join(keys[:i], "."), len(node.Content))
}
if idx == len(node.Content) {
newNode := &yaml.Node{Kind: yaml.MappingNode}
if last {
newNode = &yaml.Node{Kind: yaml.ScalarNode, Value: value}
}
node.Content = append(node.Content, newNode)
} else if last {
setScalar(node.Content[idx], value)
}
node = node.Content[idx]
default:
return fmt.Errorf("key %q is not a map or list", strings.Join(keys[:i], "."))
}
}
return nil
}
// setScalar overwrites a node in place with a plain scalar value.
func setScalar(n *yaml.Node, value string) {
n.Kind = yaml.ScalarNode
n.Tag = ""
n.Value = value
n.Content = nil
n.Style = 0
}
// configPathForInit returns the config path to write, checking --config flag,
// VAULTIK_CONFIG env, and the platform default.
func configPathForInit() string {
if rootFlags.ConfigPath != "" {
return rootFlags.ConfigPath
}
if envPath := os.Getenv("VAULTIK_CONFIG"); envPath != "" {
return envPath
}
return DefaultConfigPath()
}

161
internal/cli/config_test.go
View File

@@ -1,161 +0,0 @@
package cli
import (
"strings"
"testing"
"gopkg.in/yaml.v3"
"sneak.berlin/go/vaultik/internal/config"
)
// TestDefaultConfigTemplateParses ensures the init template is valid YAML
// that unmarshals into the Config struct with the expected snapshots.
func TestDefaultConfigTemplateParses(t *testing.T) {
var cfg config.Config
if err := yaml.Unmarshal([]byte(defaultConfigTemplate), &cfg); err != nil {
t.Fatalf("default config template is not valid YAML: %v", err)
}
if len(cfg.AgeRecipients) != 1 {
t.Errorf("expected 1 placeholder age recipient, got %d", len(cfg.AgeRecipients))
}
home, ok := cfg.Snapshots["home"]
if !ok {
t.Fatal("expected 'home' snapshot in default config")
}
if len(home.Paths) == 0 {
t.Error("home snapshot should have at least one path")
}
if len(home.Exclude) == 0 {
t.Error("home snapshot should have exclude patterns")
}
apps, ok := cfg.Snapshots["apps"]
if !ok {
t.Fatal("expected 'apps' snapshot in default config")
}
if len(apps.Paths) != 1 || apps.Paths[0] != "/Applications" {
t.Errorf("apps snapshot should back up /Applications, got %v", apps.Paths)
}
if len(apps.Exclude) == 0 {
t.Error("apps snapshot should have exclude patterns")
}
}
const testYAML = `# top comment
compression_level: 3
age_recipients:
- age1aaa
s3:
bucket: oldbucket # inline comment
region: us-east-1
snapshots:
home:
paths:
- "~"
`
func parseTestYAML(t *testing.T) *yaml.Node {
t.Helper()
var root yaml.Node
if err := yaml.Unmarshal([]byte(testYAML), &root); err != nil {
t.Fatalf("parsing test yaml: %v", err)
}
return &root
}
func TestYAMLPathGet(t *testing.T) {
root := parseTestYAML(t)
tests := []struct {
path string
want string
err bool
}{
{"compression_level", "3", false},
{"s3.bucket", "oldbucket", false},
{"s3.region", "us-east-1", false},
{"age_recipients.0", "age1aaa", false},
{"age_recipients.5", "", true},
{"age_recipients.notanumber", "", true},
{"s3.nonexistent", "", true},
{"nonexistent", "", true},
{"compression_level.sub", "", true},
}
for _, tt := range tests {
t.Run(tt.path, func(t *testing.T) {
node, err := yamlPathGet(root, splitPath(tt.path))
if tt.err {
if err == nil {
t.Fatalf("expected error for %q", tt.path)
}
return
}
if err != nil {
t.Fatalf("unexpected error: %v", err)
}
if node.Value != tt.want {
t.Errorf("get %q = %q, want %q", tt.path, node.Value, tt.want)
}
})
}
}
func TestYAMLPathSet(t *testing.T) {
root := parseTestYAML(t)
// Overwrite existing nested value
if err := yamlPathSet(root, splitPath("s3.bucket"), "newbucket"); err != nil {
t.Fatalf("set s3.bucket: %v", err)
}
// Create new nested key with intermediate map
if err := yamlPathSet(root, splitPath("s3.endpoint"), "s3.example.com"); err != nil {
t.Fatalf("set s3.endpoint: %v", err)
}
if err := yamlPathSet(root, splitPath("newmap.newkey"), "val"); err != nil {
t.Fatalf("set newmap.newkey: %v", err)
}
// Overwrite a sequence element and append a new one
if err := yamlPathSet(root, splitPath("age_recipients.0"), "age1bbb"); err != nil {
t.Fatalf("set age_recipients.0: %v", err)
}
if err := yamlPathSet(root, splitPath("age_recipients.1"), "age1ccc"); err != nil {
t.Fatalf("append age_recipients.1: %v", err)
}
if err := yamlPathSet(root, splitPath("age_recipients.5"), "age1ddd"); err == nil {
t.Error("expected out-of-range append to fail")
}
// Round-trip and verify values + comment preservation
out, err := yaml.Marshal(root)
if err != nil {
t.Fatalf("marshal: %v", err)
}
text := string(out)
for _, want := range []string{"newbucket", "s3.example.com", "newkey: val", "# top comment", "# inline comment", "age1bbb", "age1ccc"} {
if !contains(text, want) {
t.Errorf("round-tripped YAML missing %q:\n%s", want, text)
}
}
got, err := yamlPathGet(root, splitPath("s3.bucket"))
if err != nil {
t.Fatalf("get after set: %v", err)
}
if got.Value != "newbucket" {
t.Errorf("s3.bucket = %q after set, want newbucket", got.Value)
}
}
func splitPath(s string) []string {
return strings.Split(s, ".")
}
func contains(haystack, needle string) bool {
return strings.Contains(haystack, needle)
}

4
internal/cli/database.go
View File

@@ -4,9 +4,9 @@ import (
"fmt"
"os"
"git.eeqj.de/sneak/vaultik/internal/config"
"git.eeqj.de/sneak/vaultik/internal/log"
"github.com/spf13/cobra"
"sneak.berlin/go/vaultik/internal/config"
"sneak.berlin/go/vaultik/internal/log"
)
// NewDatabaseCommand creates the database command group

57
internal/cli/entry.go
View File

@@ -2,67 +2,14 @@ package cli
import (
"os"
"strings"
"time"
"sneak.berlin/go/vaultik/internal/globals"
"sneak.berlin/go/vaultik/internal/ui"
)
// CLIEntry is the main entry point for the CLI application.
// It prints the startup banner (unless a quiet flag is present in os.Args),
// executes the root cobra command, and routes any returned error through
// the ui.Writer so the user sees a properly formatted "🛑 ERROR:" line.
// It creates the root command, executes it, and exits with status 1
// if an error occurs. This function should be called from main().
func CLIEntry() {
if !bannerSuppressedInArgs(os.Args[1:]) {
short := globals.Commit
if len(short) > 12 {
short = short[:12]
}
writeStartupBanner(ui.New(os.Stdout), time.Now().UTC(), short)
}
rootCmd := NewRootCommand()
rootCmd.SilenceErrors = true
if err := rootCmd.Execute(); err != nil {
ReportError("%s", err.Error())
os.Exit(1)
}
}
// ReportError emits a user-facing error to stderr in the standard
// 🛑 ERROR: format. Use it from goroutine error paths (where returning
// an error to cobra isn't an option) and anywhere else a CLI command
// must surface a failure outside the normal RunE return path.
func ReportError(format string, args ...any) {
ui.New(os.Stderr).Error(format, args...)
}
// bannerSuppressedInArgs reports whether any of args is a flag that
// should suppress the startup banner (--quiet/-q/--cron). Stops at the
// "--" argument terminator. Recognizes both long forms and short -q,
// including combined short flags like "-qv".
func bannerSuppressedInArgs(args []string) bool {
for _, a := range args {
if a == "--" {
return false
}
switch a {
case "--quiet", "-q", "--cron":
return true
}
if strings.HasPrefix(a, "--quiet=") || strings.HasPrefix(a, "--cron=") {
return true
}
// Combined short flags like -qv or -vq.
if len(a) > 1 && a[0] == '-' && a[1] != '-' {
for _, c := range a[1:] {
if c == 'q' {
return true
}
}
}
}
return false
}

4
internal/cli/entry_test.go
View File

@@ -18,7 +18,7 @@ func TestCLIEntry(t *testing.T) {
}
// Verify all subcommands are registered
expectedCommands := []string{"config", "snapshot", "store", "prune", "info", "version", "remote", "database"}
expectedCommands := []string{"snapshot", "store", "restore", "prune", "verify", "info", "version"}
for _, expected := range expectedCommands {
found := false
for _, cmd := range cmd.Commands() {
@@ -38,7 +38,7 @@ func TestCLIEntry(t *testing.T) {
t.Errorf("Failed to find snapshot command: %v", err)
} else {
// Check snapshot subcommands
expectedSubCommands := []string{"create", "list", "purge", "verify", "cleanup", "restore"}
expectedSubCommands := []string{"create", "list", "purge", "verify"}
for _, expected := range expectedSubCommands {
found := false
for _, subcmd := range snapshotCmd.Commands() {

5
internal/cli/info.go
View File

@@ -4,10 +4,10 @@ import (
"context"
"os"
"git.eeqj.de/sneak/vaultik/internal/log"
"git.eeqj.de/sneak/vaultik/internal/vaultik"
"github.com/spf13/cobra"
"go.uber.org/fx"
"sneak.berlin/go/vaultik/internal/log"
"sneak.berlin/go/vaultik/internal/vaultik"
)
// NewInfoCommand creates the info command
@@ -47,7 +47,6 @@ func NewInfoCommand() *cobra.Command {
if err := v.ShowInfo(); err != nil {
if err != context.Canceled {
log.Error("Failed to show info", "error", err)
ReportError("Failed to show info: %v", err)
os.Exit(1)
}
}

5
internal/cli/prune.go
View File

@@ -4,10 +4,10 @@ import (
"context"
"os"
"git.eeqj.de/sneak/vaultik/internal/log"
"git.eeqj.de/sneak/vaultik/internal/vaultik"
"github.com/spf13/cobra"
"go.uber.org/fx"
"sneak.berlin/go/vaultik/internal/log"
"sneak.berlin/go/vaultik/internal/vaultik"
)
// NewPruneCommand creates the prune command
@@ -53,7 +53,6 @@ storage space.`,
if err != context.Canceled {
if !opts.JSON {
log.Error("Prune operation failed", "error", err)
ReportError("Prune failed: %v", err)
}
os.Exit(1)
}

100
internal/cli/purge.go Normal file
View File

@@ -0,0 +1,100 @@
package cli
import (
"context"
"fmt"
"os"
"git.eeqj.de/sneak/vaultik/internal/log"
"git.eeqj.de/sneak/vaultik/internal/vaultik"
"github.com/spf13/cobra"
"go.uber.org/fx"
)
// PurgeOptions contains options for the purge command
type PurgeOptions struct {
KeepLatest bool
OlderThan string
Force bool
}
// NewPurgeCommand creates the purge command
func NewPurgeCommand() *cobra.Command {
opts := &PurgeOptions{}
cmd := &cobra.Command{
Use: "purge",
Short: "Purge old snapshots",
Long: `Removes snapshots based on age or count criteria.
This command allows you to:
- Keep only the latest snapshot (--keep-latest)
- Remove snapshots older than a specific duration (--older-than)
Config is located at /etc/vaultik/config.yml by default, but can be overridden by
specifying a path using --config or by setting VAULTIK_CONFIG to a path.`,
Args: cobra.NoArgs,
RunE: func(cmd *cobra.Command, args []string) error {
// Validate flags
if !opts.KeepLatest && opts.OlderThan == "" {
return fmt.Errorf("must specify either --keep-latest or --older-than")
}
if opts.KeepLatest && opts.OlderThan != "" {
return fmt.Errorf("cannot specify both --keep-latest and --older-than")
}
// Use unified config resolution
configPath, err := ResolveConfigPath()
if err != nil {
return err
}
// Use the app framework like other commands
rootFlags := GetRootFlags()
return RunWithApp(cmd.Context(), AppOptions{
ConfigPath: configPath,
LogOptions: log.LogOptions{
Verbose: rootFlags.Verbose,
Debug: rootFlags.Debug,
Quiet: rootFlags.Quiet,
},
Modules: []fx.Option{},
Invokes: []fx.Option{
fx.Invoke(func(v *vaultik.Vaultik, lc fx.Lifecycle) {
lc.Append(fx.Hook{
OnStart: func(ctx context.Context) error {
// Start the purge operation in a goroutine
go func() {
// Run the purge operation
if err := v.PurgeSnapshots(opts.KeepLatest, opts.OlderThan, opts.Force); err != nil {
if err != context.Canceled {
log.Error("Purge operation failed", "error", err)
os.Exit(1)
}
}
// Shutdown the app when purge completes
if err := v.Shutdowner.Shutdown(); err != nil {
log.Error("Failed to shutdown", "error", err)
}
}()
return nil
},
OnStop: func(ctx context.Context) error {
log.Debug("Stopping purge operation")
v.Cancel()
return nil
},
})
}),
},
})
},
}
cmd.Flags().BoolVar(&opts.KeepLatest, "keep-latest", false, "Keep only the latest snapshot")
cmd.Flags().StringVar(&opts.OlderThan, "older-than", "", "Remove snapshots older than duration (e.g. 30d, 6m, 1y)")
cmd.Flags().BoolVar(&opts.Force, "force", false, "Skip confirmation prompts")
return cmd
}

73
internal/cli/remote.go
View File

@@ -2,13 +2,12 @@ package cli
import (
"context"
"fmt"
"os"
"git.eeqj.de/sneak/vaultik/internal/log"
"git.eeqj.de/sneak/vaultik/internal/vaultik"
"github.com/spf13/cobra"
"go.uber.org/fx"
"sneak.berlin/go/vaultik/internal/log"
"sneak.berlin/go/vaultik/internal/vaultik"
)
// NewRemoteCommand creates the remote command and subcommands
@@ -21,73 +20,6 @@ func NewRemoteCommand() *cobra.Command {
// Add subcommands
cmd.AddCommand(newRemoteInfoCommand())
cmd.AddCommand(newRemoteNukeCommand())
return cmd
}
// newRemoteNukeCommand creates the 'remote nuke' subcommand.
func newRemoteNukeCommand() *cobra.Command {
var force bool
cmd := &cobra.Command{
Use: "nuke",
Short: "Delete ALL snapshot metadata and blobs from the backup destination store",
Long: `Removes every snapshot's metadata and every blob from remote
storage. After this command completes successfully the bucket prefix is
empty and the next backup starts from scratch.
This is destructive and irreversible. Requires --force.`,
Args: cobra.NoArgs,
RunE: func(cmd *cobra.Command, args []string) error {
if !force {
return fmt.Errorf("remote nuke requires --force (this deletes ALL remote snapshots and blobs)")
}
configPath, err := ResolveConfigPath()
if err != nil {
return err
}
rootFlags := GetRootFlags()
return RunWithApp(cmd.Context(), AppOptions{
ConfigPath: configPath,
LogOptions: log.LogOptions{
Verbose: rootFlags.Verbose,
Debug: rootFlags.Debug,
Quiet: rootFlags.Quiet,
},
Modules: []fx.Option{},
Invokes: []fx.Option{
fx.Invoke(func(v *vaultik.Vaultik, lc fx.Lifecycle) {
lc.Append(fx.Hook{
OnStart: func(ctx context.Context) error {
go func() {
if err := v.NukeRemote(true); err != nil {
if err != context.Canceled {
log.Error("Remote nuke failed", "error", err)
ReportError("Remote nuke failed: %v", err)
os.Exit(1)
}
}
if err := v.Shutdowner.Shutdown(); err != nil {
log.Error("Failed to shutdown", "error", err)
}
}()
return nil
},
OnStop: func(ctx context.Context) error {
v.Cancel()
return nil
},
})
}),
},
})
},
}
cmd.Flags().BoolVar(&force, "force", false, "Required: confirm destruction of ALL remote data")
return cmd
}
@@ -130,7 +62,6 @@ func newRemoteInfoCommand() *cobra.Command {
if err != context.Canceled {
if !jsonOutput {
log.Error("Failed to get remote info", "error", err)
ReportError("Failed to get remote info: %v", err)
}
os.Exit(1)
}

28
internal/cli/snapshot_restore.go → internal/cli/restore.go
View File

@@ -2,15 +2,14 @@ package cli
import (
"context"
"os"
"git.eeqj.de/sneak/vaultik/internal/config"
"git.eeqj.de/sneak/vaultik/internal/globals"
"git.eeqj.de/sneak/vaultik/internal/log"
"git.eeqj.de/sneak/vaultik/internal/storage"
"git.eeqj.de/sneak/vaultik/internal/vaultik"
"github.com/spf13/cobra"
"go.uber.org/fx"
"sneak.berlin/go/vaultik/internal/config"
"sneak.berlin/go/vaultik/internal/globals"
"sneak.berlin/go/vaultik/internal/log"
"sneak.berlin/go/vaultik/internal/storage"
"sneak.berlin/go/vaultik/internal/vaultik"
)
// RestoreOptions contains options for the restore command
@@ -29,13 +28,13 @@ type RestoreApp struct {
Shutdowner fx.Shutdowner
}
// newSnapshotRestoreCommand creates the 'snapshot restore' subcommand
func newSnapshotRestoreCommand() *cobra.Command {
// NewRestoreCommand creates the restore command
func NewRestoreCommand() *cobra.Command {
opts := &RestoreOptions{}
cmd := &cobra.Command{
Use: "restore <snapshot-id> <target-dir> [paths...]",
Short: "Restore files from a snapshot",
Short: "Restore files from backup",
Long: `Download and decrypt files from a backup snapshot.
This command will restore files from the specified snapshot to the target directory.
@@ -46,16 +45,16 @@ Requires the VAULTIK_AGE_SECRET_KEY environment variable to be set with the age
Examples:
# Restore entire snapshot
vaultik snapshot restore myhost_docs_2025-01-01T12:00:00Z /restore
vaultik restore myhost_docs_2025-01-01T12:00:00Z /restore
# Restore specific file
vaultik snapshot restore myhost_docs_2025-01-01T12:00:00Z /restore /home/user/important.txt
vaultik restore myhost_docs_2025-01-01T12:00:00Z /restore /home/user/important.txt
# Restore specific directory
vaultik snapshot restore myhost_docs_2025-01-01T12:00:00Z /restore /home/user/documents/
vaultik restore myhost_docs_2025-01-01T12:00:00Z /restore /home/user/documents/
# Restore and verify all files
vaultik snapshot restore --verify myhost_docs_2025-01-01T12:00:00Z /restore`,
vaultik restore --verify myhost_docs_2025-01-01T12:00:00Z /restore`,
Args: cobra.MinimumNArgs(2),
RunE: func(cmd *cobra.Command, args []string) error {
return runRestore(cmd, args, opts)
@@ -127,13 +126,10 @@ func buildRestoreInvokes(snapshotID string, opts *RestoreOptions) []fx.Option {
TargetDir: opts.TargetDir,
Paths: opts.Paths,
Verify: opts.Verify,
SkipErrors: GetRootFlags().SkipErrors,
}
if err := app.Vaultik.Restore(restoreOpts); err != nil {
if err != context.Canceled {
log.Error("Restore operation failed", "error", err)
ReportError("Restore failed: %v", err)
os.Exit(1)
}
}

71
internal/cli/root.go
View File

@@ -3,10 +3,7 @@ package cli
import (
"fmt"
"os"
"path/filepath"
"strings"
"github.com/adrg/xdg"
"github.com/spf13/cobra"
)
@@ -17,7 +14,6 @@ type RootFlags struct {
Verbose bool
Debug bool
Quiet bool
SkipErrors bool
}
var rootFlags RootFlags
@@ -29,30 +25,23 @@ func NewRootCommand() *cobra.Command {
cmd := &cobra.Command{
Use: "vaultik",
Short: "Secure incremental backup tool with asymmetric encryption",
Long: `vaultik is a secure incremental backup tool that encrypts data using age
Long: `vaultik is a secure incremental backup daemon that encrypts data using age
public keys and uploads to S3-compatible storage. No private keys are needed
on the source system.`,
SilenceUsage: true,
// Bare 'vaultik' (no subcommand): print help. The banner is
// printed once at process startup by CLIEntry, before cobra
// parses arguments, so it appears even when cobra rejects
// args (e.g. "requires at least 2 arg(s)") and on --help.
Run: func(cmd *cobra.Command, args []string) {
_ = cmd.Help()
},
}
// Add global flags
cmd.PersistentFlags().StringVar(&rootFlags.ConfigPath, "config", "", "Path to config file (default: $VAULTIK_CONFIG or platform config dir)")
cmd.PersistentFlags().StringVar(&rootFlags.ConfigPath, "config", "", "Path to config file (default: $VAULTIK_CONFIG or /etc/vaultik/config.yml)")
cmd.PersistentFlags().BoolVarP(&rootFlags.Verbose, "verbose", "v", false, "Enable verbose output")
cmd.PersistentFlags().BoolVar(&rootFlags.Debug, "debug", false, "Enable debug output")
cmd.PersistentFlags().BoolVarP(&rootFlags.Quiet, "quiet", "q", false, "Suppress non-error output")
cmd.PersistentFlags().BoolVar(&rootFlags.SkipErrors, "skip-errors", false, "Continue past per-file errors instead of aborting (applies to snapshot create and restore)")
// Add subcommands
cmd.AddCommand(
NewConfigCommand(),
NewRestoreCommand(),
NewPruneCommand(),
NewVerifyCommand(),
NewStoreCommand(),
NewSnapshotCommand(),
NewInfoCommand(),
@@ -71,49 +60,25 @@ func GetRootFlags() RootFlags {
}
// ResolveConfigPath resolves the config file path from flags, environment, or default.
// Search order: --config flag, VAULTIK_CONFIG env, XDG config dir, /etc/vaultik/config.yml.
// Explicit paths from --config and $VAULTIK_CONFIG are checked for existence
// so the user gets a clear error instead of a downstream YAML parser failure.
// It checks in order: 1) --config flag, 2) VAULTIK_CONFIG environment variable,
// 3) default location /etc/vaultik/config.yml. Returns an error if no valid
// config file can be found through any of these methods.
func ResolveConfigPath() (string, error) {
if path := rootFlags.ConfigPath; path != "" {
if _, err := os.Stat(path); err != nil {
return "", fmt.Errorf("config file from --config not found: %s (run 'vaultik config init --config %s' to create it)", path, path)
}
return path, nil
// First check global flag
if rootFlags.ConfigPath != "" {
return rootFlags.ConfigPath, nil
}
if path := os.Getenv("VAULTIK_CONFIG"); path != "" {
if _, err := os.Stat(path); err != nil {
return "", fmt.Errorf("config file from $VAULTIK_CONFIG not found: %s (unset VAULTIK_CONFIG, point it at an existing file, or run 'vaultik config init')", path)
}
return path, nil
// Then check environment variable
if envPath := os.Getenv("VAULTIK_CONFIG"); envPath != "" {
return envPath, nil
}
for _, path := range defaultConfigPaths() {
if _, err := os.Stat(path); err == nil {
return path, nil
}
// Finally check default location
defaultPath := "/etc/vaultik/config.yml"
if _, err := os.Stat(defaultPath); err == nil {
return defaultPath, nil
}
return "", fmt.Errorf("no config file found at %s (run 'vaultik config init' to create the default config, or pass --config <path>)", strings.Join(defaultConfigPaths(), " or "))
}
// defaultConfigPaths returns the ordered list of config paths to search.
// On macOS: ~/Library/Application Support/vaultik/config.yml
// On Linux: ~/.config/vaultik/config.yml
// Fallback: /etc/vaultik/config.yml
func defaultConfigPaths() []string {
return []string{
filepath.Join(xdg.ConfigHome, "vaultik", "config.yml"),
"/etc/vaultik/config.yml",
}
}
// DefaultConfigPath returns the platform-appropriate default config path.
// Used by the init command and in help text.
func DefaultConfigPath() string {
if os.Getuid() == 0 {
return "/etc/vaultik/config.yml"
}
return filepath.Join(xdg.ConfigHome, "vaultik", "config.yml")
return "", fmt.Errorf("no config file specified, VAULTIK_CONFIG not set, and %s not found", defaultPath)
}

113
internal/cli/snapshot.go
View File

@@ -5,10 +5,10 @@ import (
"fmt"
"os"
"git.eeqj.de/sneak/vaultik/internal/log"
"git.eeqj.de/sneak/vaultik/internal/vaultik"
"github.com/spf13/cobra"
"go.uber.org/fx"
"sneak.berlin/go/vaultik/internal/log"
"sneak.berlin/go/vaultik/internal/vaultik"
)
// NewSnapshotCommand creates the snapshot command and subcommands
@@ -26,8 +26,6 @@ func NewSnapshotCommand() *cobra.Command {
cmd.AddCommand(newSnapshotVerifyCommand())
cmd.AddCommand(newSnapshotRemoveCommand())
cmd.AddCommand(newSnapshotPruneCommand())
cmd.AddCommand(newSnapshotCleanupCommand())
cmd.AddCommand(newSnapshotRestoreCommand())
return cmd
}
@@ -50,8 +48,6 @@ specifying a path using --config or by setting VAULTIK_CONFIG to a path.`,
RunE: func(cmd *cobra.Command, args []string) error {
// Pass snapshot names from args
opts.Snapshots = args
// --skip-errors is a global flag on the root command.
opts.SkipErrors = rootFlags.SkipErrors
// Use unified config resolution
configPath, err := ResolveConfigPath()
if err != nil {
@@ -75,12 +71,10 @@ specifying a path using --config or by setting VAULTIK_CONFIG to a path.`,
OnStart: func(ctx context.Context) error {
// Start the snapshot creation in a goroutine
go func() {
// --cron suppression is wired through v.UI by setupGlobals.
// Run the snapshot creation
if err := v.CreateSnapshot(opts); err != nil {
if err != context.Canceled {
log.Error("Snapshot creation failed", "error", err)
ReportError("Snapshot creation failed: %v", err)
os.Exit(1)
}
}
@@ -104,9 +98,10 @@ specifying a path using --config or by setting VAULTIK_CONFIG to a path.`,
},
}
cmd.Flags().BoolVar(&opts.Daemon, "daemon", false, "Run in daemon mode with inotify monitoring")
cmd.Flags().BoolVar(&opts.Cron, "cron", false, "Run in cron mode (silent unless error)")
cmd.Flags().BoolVar(&opts.Prune, "prune", false, "After backup, drop older snapshots of the same name and remove orphaned blobs")
cmd.Flags().StringVar(&opts.KeepNewerThan, "keep-newer-than", "", "With --prune: keep snapshots newer than this duration (e.g. 4w, 30d, 6mo) instead of only the latest")
cmd.Flags().BoolVar(&opts.Prune, "prune", false, "Delete all previous snapshots and unreferenced blobs after backup")
cmd.Flags().BoolVar(&opts.SkipErrors, "skip-errors", false, "Skip file read errors (log them loudly but continue)")
return cmd
}
@@ -145,7 +140,6 @@ func newSnapshotListCommand() *cobra.Command {
if err := v.ListSnapshots(jsonOutput); err != nil {
if err != context.Canceled {
log.Error("Failed to list snapshots", "error", err)
ReportError("Failed to list snapshots: %v", err)
os.Exit(1)
}
}
@@ -173,23 +167,21 @@ func newSnapshotListCommand() *cobra.Command {
// newSnapshotPurgeCommand creates the 'snapshot purge' subcommand
func newSnapshotPurgeCommand() *cobra.Command {
opts := &vaultik.SnapshotPurgeOptions{}
var keepLatest bool
var olderThan string
var force bool
cmd := &cobra.Command{
Use: "purge",
Short: "Purge old snapshots",
Long: `Removes snapshots based on age or count criteria.
Retention is per-snapshot-name: --keep-latest keeps the latest of each
configured snapshot name, not the latest globally. Use --snapshot to
restrict the operation to specific snapshot names.`,
Args: cobra.NoArgs,
Long: "Removes snapshots based on age or count criteria",
Args: cobra.NoArgs,
RunE: func(cmd *cobra.Command, args []string) error {
// Validate flags
if !opts.KeepLatest && opts.OlderThan == "" {
if !keepLatest && olderThan == "" {
return fmt.Errorf("must specify either --keep-latest or --older-than")
}
if opts.KeepLatest && opts.OlderThan != "" {
if keepLatest && olderThan != "" {
return fmt.Errorf("cannot specify both --keep-latest and --older-than")
}
@@ -213,10 +205,9 @@ restrict the operation to specific snapshot names.`,
lc.Append(fx.Hook{
OnStart: func(ctx context.Context) error {
go func() {
if err := v.PurgeSnapshotsWithOptions(opts); err != nil {
if err := v.PurgeSnapshots(keepLatest, olderThan, force); err != nil {
if err != context.Canceled {
log.Error("Failed to purge snapshots", "error", err)
ReportError("Failed to purge snapshots: %v", err)
os.Exit(1)
}
}
@@ -237,10 +228,9 @@ restrict the operation to specific snapshot names.`,
},
}
cmd.Flags().BoolVar(&opts.KeepLatest, "keep-latest", false, "Keep only the latest snapshot of each name")
cmd.Flags().StringVar(&opts.OlderThan, "older-than", "", "Remove snapshots older than duration (e.g., 30d, 6m, 1y)")
cmd.Flags().BoolVar(&opts.Force, "force", false, "Skip confirmation prompt")
cmd.Flags().StringArrayVar(&opts.Names, "snapshot", nil, "Restrict to snapshots with these names (repeat for multiple)")
cmd.Flags().BoolVar(&keepLatest, "keep-latest", false, "Keep only the latest snapshot")
cmd.Flags().StringVar(&olderThan, "older-than", "", "Remove snapshots older than duration (e.g., 30d, 6m, 1y)")
cmd.Flags().BoolVar(&force, "force", false, "Skip confirmation prompt")
return cmd
}
@@ -286,11 +276,16 @@ func newSnapshotVerifyCommand() *cobra.Command {
lc.Append(fx.Hook{
OnStart: func(ctx context.Context) error {
go func() {
if err := v.VerifySnapshotWithOptions(snapshotID, opts); err != nil {
var err error
if opts.Deep {
err = v.RunDeepVerify(snapshotID, opts)
} else {
err = v.VerifySnapshotWithOptions(snapshotID, opts)
}
if err != nil {
if err != context.Canceled {
if !opts.JSON {
log.Error("Verification failed", "error", err)
ReportError("Verification failed: %v", err)
}
os.Exit(1)
}
@@ -384,7 +379,6 @@ Use --all --force to remove all snapshots.`,
if err != context.Canceled {
if !opts.JSON {
log.Error("Failed to remove snapshot", "error", err)
ReportError("Failed to remove snapshot: %v", err)
}
os.Exit(1)
}
@@ -449,65 +443,6 @@ accumulate from incomplete backups or deleted snapshots.`,
if _, err := v.PruneDatabase(); err != nil {
if err != context.Canceled {
log.Error("Failed to prune database", "error", err)
ReportError("Failed to prune database: %v", err)
os.Exit(1)
}
}
if err := v.Shutdowner.Shutdown(); err != nil {
log.Error("Failed to shutdown", "error", err)
}
}()
return nil
},
OnStop: func(ctx context.Context) error {
v.Cancel()
return nil
},
})
}),
},
})
},
}
return cmd
}
// newSnapshotCleanupCommand creates the 'snapshot cleanup' subcommand
func newSnapshotCleanupCommand() *cobra.Command {
cmd := &cobra.Command{
Use: "cleanup",
Short: "Remove stale local snapshot records not found in remote storage",
Long: `Removes local database records for snapshots whose metadata no longer
exists in remote storage. These are typically left behind by incomplete
or interrupted backups.
This command does not delete anything from remote storage.`,
Args: cobra.NoArgs,
RunE: func(cmd *cobra.Command, args []string) error {
configPath, err := ResolveConfigPath()
if err != nil {
return err
}
rootFlags := GetRootFlags()
return RunWithApp(cmd.Context(), AppOptions{
ConfigPath: configPath,
LogOptions: log.LogOptions{
Verbose: rootFlags.Verbose,
Debug: rootFlags.Debug,
Quiet: rootFlags.Quiet,
},
Modules: []fx.Option{},
Invokes: []fx.Option{
fx.Invoke(func(v *vaultik.Vaultik, lc fx.Lifecycle) {
lc.Append(fx.Hook{
OnStart: func(ctx context.Context) error {
go func() {
if err := v.CleanupLocalSnapshots(); err != nil {
if err != context.Canceled {
log.Error("Cleanup failed", "error", err)
ReportError("Cleanup failed: %v", err)
os.Exit(1)
}
}

4
internal/cli/store.go
View File

@@ -6,10 +6,10 @@ import (
"strings"
"time"
"git.eeqj.de/sneak/vaultik/internal/log"
"git.eeqj.de/sneak/vaultik/internal/storage"
"github.com/spf13/cobra"
"go.uber.org/fx"
"sneak.berlin/go/vaultik/internal/log"
"sneak.berlin/go/vaultik/internal/storage"
)
// StoreApp contains dependencies for store commands

98
internal/cli/verify.go Normal file
View File

@@ -0,0 +1,98 @@
package cli
import (
"context"
"os"
"git.eeqj.de/sneak/vaultik/internal/log"
"git.eeqj.de/sneak/vaultik/internal/vaultik"
"github.com/spf13/cobra"
"go.uber.org/fx"
)
// NewVerifyCommand creates the verify command
func NewVerifyCommand() *cobra.Command {
opts := &vaultik.VerifyOptions{}
cmd := &cobra.Command{
Use: "verify <snapshot-id>",
Short: "Verify snapshot integrity",
Long: `Verifies that all blobs referenced in a snapshot exist and optionally verifies their contents.
Shallow verification (default):
- Downloads and decompresses manifest
- Checks existence of all blobs in S3
- Reports missing blobs
Deep verification (--deep):
- Downloads and decrypts database
- Verifies blob lists match between manifest and database
- Downloads, decrypts, and decompresses each blob
- Verifies SHA256 hash of each chunk matches database
- Ensures chunks are ordered correctly
The command will fail immediately on any verification error and exit with non-zero status.`,
Args: cobra.ExactArgs(1),
RunE: func(cmd *cobra.Command, args []string) error {
snapshotID := args[0]
// Use unified config resolution
configPath, err := ResolveConfigPath()
if err != nil {
return err
}
// Use the app framework for all verification
rootFlags := GetRootFlags()
return RunWithApp(cmd.Context(), AppOptions{
ConfigPath: configPath,
LogOptions: log.LogOptions{
Verbose: rootFlags.Verbose,
Debug: rootFlags.Debug,
Quiet: rootFlags.Quiet || opts.JSON, // Suppress log output in JSON mode
},
Modules: []fx.Option{},
Invokes: []fx.Option{
fx.Invoke(func(v *vaultik.Vaultik, lc fx.Lifecycle) {
lc.Append(fx.Hook{
OnStart: func(ctx context.Context) error {
// Run the verify operation directly
go func() {
var err error
if opts.Deep {
err = v.RunDeepVerify(snapshotID, opts)
} else {
err = v.VerifySnapshotWithOptions(snapshotID, opts)
}
if err != nil {
if err != context.Canceled {
if !opts.JSON {
log.Error("Verification failed", "error", err)
}
os.Exit(1)
}
}
if err := v.Shutdowner.Shutdown(); err != nil {
log.Error("Failed to shutdown", "error", err)
}
}()
return nil
},
OnStop: func(ctx context.Context) error {
log.Debug("Stopping verify operation")
v.Cancel()
return nil
},
})
}),
},
})
},
}
cmd.Flags().BoolVar(&opts.Deep, "deep", false, "Perform deep verification by downloading and verifying all blob contents")
cmd.Flags().BoolVar(&opts.JSON, "json", false, "Output verification results as JSON")
return cmd
}

18
internal/cli/version.go
View File

@@ -4,8 +4,8 @@ import (
"fmt"
"runtime"
"git.eeqj.de/sneak/vaultik/internal/globals"
"github.com/spf13/cobra"
"sneak.berlin/go/vaultik/internal/globals"
)
// NewVersionCommand creates the version command
@@ -17,19 +17,9 @@ func NewVersionCommand() *cobra.Command {
Args: cobra.NoArgs,
Run: func(cmd *cobra.Command, args []string) {
fmt.Printf("vaultik %s\n", globals.Version)
fmt.Printf(" commit: %s\n", globals.Commit)
fmt.Printf(" build date: %s\n", globals.CommitDate)
fmt.Printf(" go: %s\n", runtime.Version())
fmt.Printf(" os/arch: %s/%s\n", runtime.GOOS, runtime.GOARCH)
fmt.Printf(" author: %s\n", globals.Author)
fmt.Printf(" homepage: %s\n", globals.Homepage)
fmt.Printf(" license: %s\n", globals.License)
if globals.Version == "dev" {
fmt.Println()
fmt.Println("This is a development build (no version information embedded).")
fmt.Println("Build a release binary with 'make vaultik' or download from")
fmt.Println("https://sneak.berlin/go/vaultik for embedded version metadata.")
}
fmt.Printf(" commit: %s\n", globals.Commit)
fmt.Printf(" go: %s\n", runtime.Version())
fmt.Printf(" os/arch: %s/%s\n", runtime.GOOS, runtime.GOARCH)
},
}

45
internal/config/config.go
View File

@@ -6,16 +6,17 @@ import (
"path/filepath"
"sort"
"strings"
"time"
"filippo.io/age"
"git.eeqj.de/sneak/smartconfig"
"git.eeqj.de/sneak/vaultik/internal/log"
"github.com/adrg/xdg"
"go.uber.org/fx"
"gopkg.in/yaml.v3"
"sneak.berlin/go/vaultik/internal/log"
)
const appName = "vaultik"
const appName = "berlin.sneak.app.vaultik"
// expandTilde expands ~ at the start of a path to the user's home directory.
func expandTilde(path string) string {
@@ -82,16 +83,19 @@ func (c *Config) SnapshotNames() []string {
// encryption recipients, storage configuration, and performance tuning parameters.
// Configuration is typically loaded from a YAML file.
type Config struct {
AgeRecipients []string `yaml:"age_recipients"`
AgeSecretKey string `yaml:"age_secret_key"`
BlobSizeLimit Size `yaml:"blob_size_limit"`
ChunkSize Size `yaml:"chunk_size"`
Exclude []string `yaml:"exclude"` // Global excludes applied to all snapshots
Hostname string `yaml:"hostname"`
IndexPath string `yaml:"index_path"`
S3 S3Config `yaml:"s3"`
Snapshots map[string]SnapshotConfig `yaml:"snapshots"`
CompressionLevel int `yaml:"compression_level"`
AgeRecipients []string `yaml:"age_recipients"`
AgeSecretKey string `yaml:"age_secret_key"`
BackupInterval time.Duration `yaml:"backup_interval"`
BlobSizeLimit Size `yaml:"blob_size_limit"`
ChunkSize Size `yaml:"chunk_size"`
Exclude []string `yaml:"exclude"` // Global excludes applied to all snapshots
FullScanInterval time.Duration `yaml:"full_scan_interval"`
Hostname string `yaml:"hostname"`
IndexPath string `yaml:"index_path"`
MinTimeBetweenRun time.Duration `yaml:"min_time_between_run"`
S3 S3Config `yaml:"s3"`
Snapshots map[string]SnapshotConfig `yaml:"snapshots"`
CompressionLevel int `yaml:"compression_level"`
// StorageURL specifies the storage backend using a URL format.
// Takes precedence over S3Config if set.
@@ -151,10 +155,13 @@ func Load(path string) (*Config, error) {
cfg := &Config{
// Set defaults
BlobSizeLimit: Size(10 * 1024 * 1024 * 1024), // 10GB
ChunkSize: Size(10 * 1024 * 1024), // 10MB
IndexPath: filepath.Join(xdg.DataHome, appName, "index.sqlite"),
CompressionLevel: 3,
BlobSizeLimit: Size(10 * 1024 * 1024 * 1024), // 10GB
ChunkSize: Size(10 * 1024 * 1024), // 10MB
BackupInterval: 1 * time.Hour,
FullScanInterval: 24 * time.Hour,
MinTimeBetweenRun: 15 * time.Minute,
IndexPath: filepath.Join(xdg.DataHome, appName, "index.sqlite"),
CompressionLevel: 3,
}
// Convert smartconfig data to YAML then unmarshal
@@ -236,11 +243,11 @@ func Load(path string) (*Config, error) {
// Returns an error describing the first validation failure encountered.
func (c *Config) Validate() error {
if len(c.AgeRecipients) == 0 {
return fmt.Errorf("at least one age_recipient is required (generate with: age-keygen)")
return fmt.Errorf("at least one age_recipient is required")
}
if len(c.Snapshots) == 0 {
return fmt.Errorf("at least one snapshot must be configured (see config.example.yml)")
return fmt.Errorf("at least one snapshot must be configured")
}
for name, snap := range c.Snapshots {
@@ -299,7 +306,7 @@ func (c *Config) validateStorage() error {
// Legacy S3 configuration
if c.S3.Endpoint == "" {
return fmt.Errorf("storage not configured; set storage_url or provide s3.endpoint + s3.bucket + credentials")
return fmt.Errorf("s3.endpoint is required (or set storage_url)")
}
if c.S3.Bucket == "" {

2
internal/database/blob_chunks_test.go
View File

@@ -6,7 +6,7 @@ import (
"testing"
"time"
"sneak.berlin/go/vaultik/internal/types"
"git.eeqj.de/sneak/vaultik/internal/types"
)
func TestBlobChunkRepository(t *testing.T) {

2
internal/database/blobs.go
View File

@@ -6,7 +6,7 @@ import (
"fmt"
"time"
"sneak.berlin/go/vaultik/internal/log"
"git.eeqj.de/sneak/vaultik/internal/log"
)
type BlobRepository struct {

2
internal/database/blobs_test.go
View File

@@ -5,7 +5,7 @@ import (
"testing"
"time"
"sneak.berlin/go/vaultik/internal/types"
"git.eeqj.de/sneak/vaultik/internal/types"
)
func TestBlobRepository(t *testing.T) {

3
internal/database/cascade_debug_test.go
View File

@@ -6,7 +6,7 @@ import (
"testing"
"time"
"sneak.berlin/go/vaultik/internal/types"
"git.eeqj.de/sneak/vaultik/internal/types"
)
// TestCascadeDeleteDebug tests cascade delete with debug output
@@ -29,6 +29,7 @@ func TestCascadeDeleteDebug(t *testing.T) {
file := &File{
Path: "/cascade-test.txt",
MTime: time.Now().Truncate(time.Second),
CTime: time.Now().Truncate(time.Second),
Size: 1024,
Mode: 0644,
UID: 1000,

2
internal/database/chunk_files.go
View File

@@ -5,7 +5,7 @@ import (
"database/sql"
"fmt"
"sneak.berlin/go/vaultik/internal/types"
"git.eeqj.de/sneak/vaultik/internal/types"
)
type ChunkFileRepository struct {

10
internal/database/chunk_files_test.go
View File

@@ -5,7 +5,7 @@ import (
"testing"
"time"
"sneak.berlin/go/vaultik/internal/types"
"git.eeqj.de/sneak/vaultik/internal/types"
)
func TestChunkFileRepository(t *testing.T) {
@@ -22,6 +22,7 @@ func TestChunkFileRepository(t *testing.T) {
file1 := &File{
Path: "/file1.txt",
MTime: testTime,
CTime: testTime,
Size: 1024,
Mode: 0644,
UID: 1000,
@@ -36,6 +37,7 @@ func TestChunkFileRepository(t *testing.T) {
file2 := &File{
Path: "/file2.txt",
MTime: testTime,
CTime: testTime,
Size: 1024,
Mode: 0644,
UID: 1000,
@@ -136,9 +138,9 @@ func TestChunkFileRepositoryComplexDeduplication(t *testing.T) {
// Create test files
testTime := time.Now().Truncate(time.Second)
file1 := &File{Path: "/file1.txt", MTime: testTime, Size: 3072, Mode: 0644, UID: 1000, GID: 1000}
file2 := &File{Path: "/file2.txt", MTime: testTime, Size: 3072, Mode: 0644, UID: 1000, GID: 1000}
file3 := &File{Path: "/file3.txt", MTime: testTime, Size: 2048, Mode: 0644, UID: 1000, GID: 1000}
file1 := &File{Path: "/file1.txt", MTime: testTime, CTime: testTime, Size: 3072, Mode: 0644, UID: 1000, GID: 1000}
file2 := &File{Path: "/file2.txt", MTime: testTime, CTime: testTime, Size: 3072, Mode: 0644, UID: 1000, GID: 1000}
file3 := &File{Path: "/file3.txt", MTime: testTime, CTime: testTime, Size: 2048, Mode: 0644, UID: 1000, GID: 1000}
if err := fileRepo.Create(ctx, nil, file1); err != nil {
t.Fatalf("failed to create file1: %v", err)

2
internal/database/chunks.go
View File

@@ -5,7 +5,7 @@ import (
"database/sql"
"fmt"
"sneak.berlin/go/vaultik/internal/log"
"git.eeqj.de/sneak/vaultik/internal/log"
)
type ChunkRepository struct {

2
internal/database/chunks_test.go
View File

@@ -4,7 +4,7 @@ import (
"context"
"testing"
"sneak.berlin/go/vaultik/internal/types"
"git.eeqj.de/sneak/vaultik/internal/types"
)
func TestChunkRepository(t *testing.T) {

185
internal/database/database.go
View File

@@ -6,32 +6,24 @@
// multiple source files. Blobs are content-addressed, meaning their filename
// is derived from their SHA256 hash after compression and encryption.
//
// Schema is managed via numbered SQL migrations embedded in the schema/
// directory. Migration 000.sql bootstraps the schema_migrations tracking
// table; subsequent migrations (001, 002, …) are applied in order.
// The database does not support migrations. If the schema changes, delete
// the local database and perform a full backup to recreate it.
package database
import (
"context"
"database/sql"
"embed"
_ "embed"
"fmt"
"os"
"path/filepath"
"sort"
"strconv"
"strings"
"git.eeqj.de/sneak/vaultik/internal/log"
_ "modernc.org/sqlite"
"sneak.berlin/go/vaultik/internal/log"
)
//go:embed schema/*.sql
var schemaFS embed.FS
// bootstrapVersion is the migration that creates the schema_migrations
// table itself. It is applied before the normal migration loop.
const bootstrapVersion = 0
//go:embed schema.sql
var schemaSQL string
// DB represents the Vaultik local index database connection.
// It uses SQLite to track file metadata, content-defined chunks, and blob associations.
@@ -43,46 +35,6 @@ type DB struct {
path string
}
// ParseMigrationVersion extracts the numeric version prefix from a migration
// filename. Filenames must follow the pattern "<version>.sql" or
// "<version>_<description>.sql", where version is a zero-padded numeric
// string (e.g. "001", "002"). Returns the version as an integer and an
// error if the filename does not match the expected pattern.
func ParseMigrationVersion(filename string) (int, error) {
name := strings.TrimSuffix(filename, filepath.Ext(filename))
if name == "" {
return 0, fmt.Errorf("invalid migration filename %q: empty name", filename)
}
// Split on underscore to separate version from description.
// If there's no underscore, the entire stem is the version.
versionStr := name
if idx := strings.IndexByte(name, '_'); idx >= 0 {
versionStr = name[:idx]
}
if versionStr == "" {
return 0, fmt.Errorf("invalid migration filename %q: empty version prefix", filename)
}
// Validate the version is purely numeric.
for _, ch := range versionStr {
if ch < '0' || ch > '9' {
return 0, fmt.Errorf(
"invalid migration filename %q: version %q contains non-numeric character %q",
filename, versionStr, string(ch),
)
}
}
version, err := strconv.Atoi(versionStr)
if err != nil {
return 0, fmt.Errorf("invalid migration filename %q: %w", filename, err)
}
return version, nil
}
// New creates a new database connection at the specified path.
// It creates the schema if needed and configures SQLite with WAL mode for
// better concurrency. SQLite handles crash recovery automatically when
@@ -120,9 +72,9 @@ func New(ctx context.Context, path string) (*DB, error) {
}
db := &DB{conn: conn, path: path}
if err := applyMigrations(ctx, conn); err != nil {
if err := db.createSchema(ctx); err != nil {
_ = conn.Close()
return nil, fmt.Errorf("applying migrations: %w", err)
return nil, fmt.Errorf("creating schema: %w", err)
}
return db, nil
}
@@ -173,9 +125,9 @@ func New(ctx context.Context, path string) (*DB, error) {
}
db := &DB{conn: conn, path: path}
if err := applyMigrations(ctx, conn); err != nil {
if err := db.createSchema(ctx); err != nil {
_ = conn.Close()
return nil, fmt.Errorf("applying migrations: %w", err)
return nil, fmt.Errorf("creating schema: %w", err)
}
log.Debug("Database connection established successfully", "path", path)
@@ -246,120 +198,9 @@ func (db *DB) QueryRowWithLog(
return db.conn.QueryRowContext(ctx, query, args...)
}
// collectMigrations reads the embedded schema directory and returns
// migration filenames sorted lexicographically.
func collectMigrations() ([]string, error) {
entries, err := schemaFS.ReadDir("schema")
if err != nil {
return nil, fmt.Errorf("failed to read schema directory: %w", err)
}
var migrations []string
for _, entry := range entries {
if !entry.IsDir() && strings.HasSuffix(entry.Name(), ".sql") {
migrations = append(migrations, entry.Name())
}
}
sort.Strings(migrations)
return migrations, nil
}
// bootstrapMigrationsTable ensures the schema_migrations table exists
// by applying 000.sql if the table is missing.
func bootstrapMigrationsTable(ctx context.Context, db *sql.DB) error {
var tableExists int
err := db.QueryRowContext(ctx,
"SELECT COUNT(*) FROM sqlite_master WHERE type='table' AND name='schema_migrations'",
).Scan(&tableExists)
if err != nil {
return fmt.Errorf("failed to check for migrations table: %w", err)
}
if tableExists > 0 {
return nil
}
content, err := schemaFS.ReadFile("schema/000.sql")
if err != nil {
return fmt.Errorf("failed to read bootstrap migration 000.sql: %w", err)
}
log.Info("applying bootstrap migration", "version", bootstrapVersion)
_, err = db.ExecContext(ctx, string(content))
if err != nil {
return fmt.Errorf("failed to apply bootstrap migration: %w", err)
}
return nil
}
// applyMigrations applies all pending migrations to db. It first bootstraps
// the schema_migrations table via 000.sql, then iterates through remaining
// migration files in order.
func applyMigrations(ctx context.Context, db *sql.DB) error {
if err := bootstrapMigrationsTable(ctx, db); err != nil {
return err
}
migrations, err := collectMigrations()
if err != nil {
return err
}
for _, migration := range migrations {
version, parseErr := ParseMigrationVersion(migration)
if parseErr != nil {
return parseErr
}
// Check if already applied.
var count int
err := db.QueryRowContext(ctx,
"SELECT COUNT(*) FROM schema_migrations WHERE version = ?",
version,
).Scan(&count)
if err != nil {
return fmt.Errorf("failed to check migration status: %w", err)
}
if count > 0 {
log.Debug("migration already applied", "version", version)
continue
}
// Read and apply migration.
content, readErr := schemaFS.ReadFile(filepath.Join("schema", migration))
if readErr != nil {
return fmt.Errorf("failed to read migration %s: %w", migration, readErr)
}
log.Info("applying migration", "version", version)
_, execErr := db.ExecContext(ctx, string(content))
if execErr != nil {
return fmt.Errorf("failed to apply migration %s: %w", migration, execErr)
}
// Record migration as applied.
_, recErr := db.ExecContext(ctx,
"INSERT INTO schema_migrations (version) VALUES (?)",
version,
)
if recErr != nil {
return fmt.Errorf("failed to record migration %s: %w", migration, recErr)
}
log.Info("migration applied successfully", "version", version)
}
return nil
func (db *DB) createSchema(ctx context.Context) error {
_, err := db.conn.ExecContext(ctx, schemaSQL)
return err
}
// NewTestDB creates an in-memory SQLite database for testing purposes.

140
internal/database/database_test.go
View File

@@ -2,7 +2,6 @@ package database
import (
"context"
"database/sql"
"fmt"
"path/filepath"
"testing"
@@ -27,10 +26,9 @@ func TestDatabase(t *testing.T) {
t.Fatal("database connection is nil")
}
// Test schema creation (already done in New via migrations)
// Test schema creation (already done in New)
// Verify tables exist
tables := []string{
"schema_migrations",
"files", "file_chunks", "chunks", "blobs",
"blob_chunks", "chunk_files", "snapshots",
}
@@ -101,139 +99,3 @@ func TestDatabaseConcurrentAccess(t *testing.T) {
t.Errorf("expected 10 chunks, got %d", count)
}
}
func TestParseMigrationVersion(t *testing.T) {
tests := []struct {
name string
filename string
wantVer int
wantError bool
}{
{name: "valid 000.sql", filename: "000.sql", wantVer: 0, wantError: false},
{name: "valid 001.sql", filename: "001.sql", wantVer: 1, wantError: false},
{name: "valid 099.sql", filename: "099.sql", wantVer: 99, wantError: false},
{name: "valid with description", filename: "001_initial_schema.sql", wantVer: 1, wantError: false},
{name: "valid large version", filename: "123_big_migration.sql", wantVer: 123, wantError: false},
{name: "invalid alpha version", filename: "abc.sql", wantVer: 0, wantError: true},
{name: "invalid mixed chars", filename: "12a.sql", wantVer: 0, wantError: true},
{name: "invalid no extension", filename: "schema.sql", wantVer: 0, wantError: true},
{name: "empty string", filename: "", wantVer: 0, wantError: true},
}
for _, tc := range tests {
t.Run(tc.name, func(t *testing.T) {
got, err := ParseMigrationVersion(tc.filename)
if tc.wantError {
if err == nil {
t.Errorf("ParseMigrationVersion(%q) = %d, nil; want error", tc.filename, got)
}
return
}
if err != nil {
t.Errorf("ParseMigrationVersion(%q) unexpected error: %v", tc.filename, err)
return
}
if got != tc.wantVer {
t.Errorf("ParseMigrationVersion(%q) = %d; want %d", tc.filename, got, tc.wantVer)
}
})
}
}
func TestApplyMigrations_Idempotent(t *testing.T) {
ctx := context.Background()
conn, err := sql.Open("sqlite", ":memory:?_foreign_keys=ON")
if err != nil {
t.Fatalf("failed to open database: %v", err)
}
defer func() {
if err := conn.Close(); err != nil {
t.Errorf("failed to close database: %v", err)
}
}()
conn.SetMaxOpenConns(1)
conn.SetMaxIdleConns(1)
// First run: apply all migrations.
if err := applyMigrations(ctx, conn); err != nil {
t.Fatalf("first applyMigrations failed: %v", err)
}
// Count rows in schema_migrations after first run.
var countBefore int
if err := conn.QueryRowContext(ctx, "SELECT COUNT(*) FROM schema_migrations").Scan(&countBefore); err != nil {
t.Fatalf("failed to count schema_migrations after first run: %v", err)
}
// Second run: must be a no-op.
if err := applyMigrations(ctx, conn); err != nil {
t.Fatalf("second applyMigrations failed: %v", err)
}
// Count rows in schema_migrations after second run — must be unchanged.
var countAfter int
if err := conn.QueryRowContext(ctx, "SELECT COUNT(*) FROM schema_migrations").Scan(&countAfter); err != nil {
t.Fatalf("failed to count schema_migrations after second run: %v", err)
}
if countBefore != countAfter {
t.Errorf("schema_migrations row count changed: before=%d, after=%d", countBefore, countAfter)
}
}
func TestBootstrapMigrationsTable_FreshDatabase(t *testing.T) {
ctx := context.Background()
conn, err := sql.Open("sqlite", ":memory:?_foreign_keys=ON")
if err != nil {
t.Fatalf("failed to open database: %v", err)
}
defer func() {
if err := conn.Close(); err != nil {
t.Errorf("failed to close database: %v", err)
}
}()
conn.SetMaxOpenConns(1)
conn.SetMaxIdleConns(1)
// Verify schema_migrations does NOT exist yet.
var tableBefore int
if err := conn.QueryRowContext(ctx,
"SELECT COUNT(*) FROM sqlite_master WHERE type='table' AND name='schema_migrations'",
).Scan(&tableBefore); err != nil {
t.Fatalf("failed to check for table before bootstrap: %v", err)
}
if tableBefore != 0 {
t.Fatal("schema_migrations table should not exist before bootstrap")
}
// Run bootstrap.
if err := bootstrapMigrationsTable(ctx, conn); err != nil {
t.Fatalf("bootstrapMigrationsTable failed: %v", err)
}
// Verify schema_migrations now exists.
var tableAfter int
if err := conn.QueryRowContext(ctx,
"SELECT COUNT(*) FROM sqlite_master WHERE type='table' AND name='schema_migrations'",
).Scan(&tableAfter); err != nil {
t.Fatalf("failed to check for table after bootstrap: %v", err)
}
if tableAfter != 1 {
t.Fatalf("schema_migrations table should exist after bootstrap, got count=%d", tableAfter)
}
// Verify version 0 row exists.
var version int
if err := conn.QueryRowContext(ctx,
"SELECT version FROM schema_migrations WHERE version = 0",
).Scan(&version); err != nil {
t.Fatalf("version 0 row not found in schema_migrations: %v", err)
}
if version != 0 {
t.Errorf("expected version 0, got %d", version)
}
}

2
internal/database/file_chunks.go
View File

@@ -5,7 +5,7 @@ import (
"database/sql"
"fmt"
"sneak.berlin/go/vaultik/internal/types"
"git.eeqj.de/sneak/vaultik/internal/types"
)
type FileChunkRepository struct {

4
internal/database/file_chunks_test.go
View File

@@ -6,7 +6,7 @@ import (
"testing"
"time"
"sneak.berlin/go/vaultik/internal/types"
"git.eeqj.de/sneak/vaultik/internal/types"
)
func TestFileChunkRepository(t *testing.T) {
@@ -22,6 +22,7 @@ func TestFileChunkRepository(t *testing.T) {
file := &File{
Path: "/test/file.txt",
MTime: testTime,
CTime: testTime,
Size: 3072,
Mode: 0644,
UID: 1000,
@@ -134,6 +135,7 @@ func TestFileChunkRepositoryMultipleFiles(t *testing.T) {
file := &File{
Path: types.FilePath(path),
MTime: testTime,
CTime: testTime,
Size: 2048,
Mode: 0644,
UID: 1000,

46
internal/database/files.go
View File

@@ -6,8 +6,8 @@ import (
"fmt"
"time"
"sneak.berlin/go/vaultik/internal/log"
"sneak.berlin/go/vaultik/internal/types"
"git.eeqj.de/sneak/vaultik/internal/log"
"git.eeqj.de/sneak/vaultik/internal/types"
)
type FileRepository struct {
@@ -25,11 +25,12 @@ func (r *FileRepository) Create(ctx context.Context, tx *sql.Tx, file *File) err
}
query := `
INSERT INTO files (id, path, source_path, mtime, size, mode, uid, gid, link_target)
VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?)
INSERT INTO files (id, path, source_path, mtime, ctime, size, mode, uid, gid, link_target)
VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?)
ON CONFLICT(path) DO UPDATE SET
source_path = excluded.source_path,
mtime = excluded.mtime,
ctime = excluded.ctime,
size = excluded.size,
mode = excluded.mode,
uid = excluded.uid,
@@ -41,10 +42,10 @@ func (r *FileRepository) Create(ctx context.Context, tx *sql.Tx, file *File) err
var idStr string
var err error
if tx != nil {
LogSQL("Execute", query, file.ID.String(), file.Path.String(), file.SourcePath.String(), file.MTime.Unix(), file.Size, file.Mode, file.UID, file.GID, file.LinkTarget.String())
err = tx.QueryRowContext(ctx, query, file.ID.String(), file.Path.String(), file.SourcePath.String(), file.MTime.Unix(), file.Size, file.Mode, file.UID, file.GID, file.LinkTarget.String()).Scan(&idStr)
LogSQL("Execute", query, file.ID.String(), file.Path.String(), file.SourcePath.String(), file.MTime.Unix(), file.CTime.Unix(), file.Size, file.Mode, file.UID, file.GID, file.LinkTarget.String())
err = tx.QueryRowContext(ctx, query, file.ID.String(), file.Path.String(), file.SourcePath.String(), file.MTime.Unix(), file.CTime.Unix(), file.Size, file.Mode, file.UID, file.GID, file.LinkTarget.String()).Scan(&idStr)
} else {
err = r.db.QueryRowWithLog(ctx, query, file.ID.String(), file.Path.String(), file.SourcePath.String(), file.MTime.Unix(), file.Size, file.Mode, file.UID, file.GID, file.LinkTarget.String()).Scan(&idStr)
err = r.db.QueryRowWithLog(ctx, query, file.ID.String(), file.Path.String(), file.SourcePath.String(), file.MTime.Unix(), file.CTime.Unix(), file.Size, file.Mode, file.UID, file.GID, file.LinkTarget.String()).Scan(&idStr)
}
if err != nil {
@@ -62,7 +63,7 @@ func (r *FileRepository) Create(ctx context.Context, tx *sql.Tx, file *File) err
func (r *FileRepository) GetByPath(ctx context.Context, path string) (*File, error) {
query := `
SELECT id, path, source_path, mtime, size, mode, uid, gid, link_target
SELECT id, path, source_path, mtime, ctime, size, mode, uid, gid, link_target
FROM files
WHERE path = ?
`
@@ -81,7 +82,7 @@ func (r *FileRepository) GetByPath(ctx context.Context, path string) (*File, err
// GetByID retrieves a file by its UUID
func (r *FileRepository) GetByID(ctx context.Context, id types.FileID) (*File, error) {
query := `
SELECT id, path, source_path, mtime, size, mode, uid, gid, link_target
SELECT id, path, source_path, mtime, ctime, size, mode, uid, gid, link_target
FROM files
WHERE id = ?
`
@@ -99,7 +100,7 @@ func (r *FileRepository) GetByID(ctx context.Context, id types.FileID) (*File, e
func (r *FileRepository) GetByPathTx(ctx context.Context, tx *sql.Tx, path string) (*File, error) {
query := `
SELECT id, path, source_path, mtime, size, mode, uid, gid, link_target
SELECT id, path, source_path, mtime, ctime, size, mode, uid, gid, link_target
FROM files
WHERE path = ?
`
@@ -122,7 +123,7 @@ func (r *FileRepository) GetByPathTx(ctx context.Context, tx *sql.Tx, path strin
func (r *FileRepository) scanFile(row *sql.Row) (*File, error) {
var file File
var idStr, pathStr, sourcePathStr string
var mtimeUnix int64
var mtimeUnix, ctimeUnix int64
var linkTarget sql.NullString
err := row.Scan(
@@ -130,6 +131,7 @@ func (r *FileRepository) scanFile(row *sql.Row) (*File, error) {
&pathStr,
&sourcePathStr,
&mtimeUnix,
&ctimeUnix,
&file.Size,
&file.Mode,
&file.UID,
@@ -147,6 +149,7 @@ func (r *FileRepository) scanFile(row *sql.Row) (*File, error) {
file.Path = types.FilePath(pathStr)
file.SourcePath = types.SourcePath(sourcePathStr)
file.MTime = time.Unix(mtimeUnix, 0).UTC()
file.CTime = time.Unix(ctimeUnix, 0).UTC()
if linkTarget.Valid {
file.LinkTarget = types.FilePath(linkTarget.String)
}
@@ -158,7 +161,7 @@ func (r *FileRepository) scanFile(row *sql.Row) (*File, error) {
func (r *FileRepository) scanFileRows(rows *sql.Rows) (*File, error) {
var file File
var idStr, pathStr, sourcePathStr string
var mtimeUnix int64
var mtimeUnix, ctimeUnix int64
var linkTarget sql.NullString
err := rows.Scan(
@@ -166,6 +169,7 @@ func (r *FileRepository) scanFileRows(rows *sql.Rows) (*File, error) {
&pathStr,
&sourcePathStr,
&mtimeUnix,
&ctimeUnix,
&file.Size,
&file.Mode,
&file.UID,
@@ -183,6 +187,7 @@ func (r *FileRepository) scanFileRows(rows *sql.Rows) (*File, error) {
file.Path = types.FilePath(pathStr)
file.SourcePath = types.SourcePath(sourcePathStr)
file.MTime = time.Unix(mtimeUnix, 0).UTC()
file.CTime = time.Unix(ctimeUnix, 0).UTC()
if linkTarget.Valid {
file.LinkTarget = types.FilePath(linkTarget.String)
}
@@ -192,7 +197,7 @@ func (r *FileRepository) scanFileRows(rows *sql.Rows) (*File, error) {
func (r *FileRepository) ListModifiedSince(ctx context.Context, since time.Time) ([]*File, error) {
query := `
SELECT id, path, source_path, mtime, size, mode, uid, gid, link_target
SELECT id, path, source_path, mtime, ctime, size, mode, uid, gid, link_target
FROM files
WHERE mtime >= ?
ORDER BY path
@@ -253,7 +258,7 @@ func (r *FileRepository) DeleteByID(ctx context.Context, tx *sql.Tx, id types.Fi
func (r *FileRepository) ListByPrefix(ctx context.Context, prefix string) ([]*File, error) {
query := `
SELECT id, path, source_path, mtime, size, mode, uid, gid, link_target
SELECT id, path, source_path, mtime, ctime, size, mode, uid, gid, link_target
FROM files
WHERE path LIKE ? || '%'
ORDER BY path
@@ -280,7 +285,7 @@ func (r *FileRepository) ListByPrefix(ctx context.Context, prefix string) ([]*Fi
// ListAll returns all files in the database
func (r *FileRepository) ListAll(ctx context.Context) ([]*File, error) {
query := `
SELECT id, path, source_path, mtime, size, mode, uid, gid, link_target
SELECT id, path, source_path, mtime, ctime, size, mode, uid, gid, link_target
FROM files
ORDER BY path
`
@@ -310,7 +315,7 @@ func (r *FileRepository) CreateBatch(ctx context.Context, tx *sql.Tx, files []*F
return nil
}
// Each File has 9 values, so batch at 100 to be safe with SQLite's variable limit
// Each File has 10 values, so batch at 100 to be safe with SQLite's variable limit
const batchSize = 100
for i := 0; i < len(files); i += batchSize {
@@ -320,18 +325,19 @@ func (r *FileRepository) CreateBatch(ctx context.Context, tx *sql.Tx, files []*F
}
batch := files[i:end]
query := `INSERT INTO files (id, path, source_path, mtime, size, mode, uid, gid, link_target) VALUES `
args := make([]interface{}, 0, len(batch)*9)
query := `INSERT INTO files (id, path, source_path, mtime, ctime, size, mode, uid, gid, link_target) VALUES `
args := make([]interface{}, 0, len(batch)*10)
for j, f := range batch {
if j > 0 {
query += ", "
}
query += "(?, ?, ?, ?, ?, ?, ?, ?, ?)"
args = append(args, f.ID.String(), f.Path.String(), f.SourcePath.String(), f.MTime.Unix(), f.Size, f.Mode, f.UID, f.GID, f.LinkTarget.String())
query += "(?, ?, ?, ?, ?, ?, ?, ?, ?, ?)"
args = append(args, f.ID.String(), f.Path.String(), f.SourcePath.String(), f.MTime.Unix(), f.CTime.Unix(), f.Size, f.Mode, f.UID, f.GID, f.LinkTarget.String())
}
query += ` ON CONFLICT(path) DO UPDATE SET
source_path = excluded.source_path,
mtime = excluded.mtime,
ctime = excluded.ctime,
size = excluded.size,
mode = excluded.mode,
uid = excluded.uid,

3
internal/database/files_test.go
View File

@@ -39,6 +39,7 @@ func TestFileRepository(t *testing.T) {
file := &File{
Path: "/test/file.txt",
MTime: time.Now().Truncate(time.Second),
CTime: time.Now().Truncate(time.Second),
Size: 1024,
Mode: 0644,
UID: 1000,
@@ -123,6 +124,7 @@ func TestFileRepositorySymlink(t *testing.T) {
symlink := &File{
Path: "/test/link",
MTime: time.Now().Truncate(time.Second),
CTime: time.Now().Truncate(time.Second),
Size: 0,
Mode: uint32(0777 | os.ModeSymlink),
UID: 1000,
@@ -159,6 +161,7 @@ func TestFileRepositoryTransaction(t *testing.T) {
file := &File{
Path: "/test/tx_file.txt",
MTime: time.Now().Truncate(time.Second),
CTime: time.Now().Truncate(time.Second),
Size: 1024,
Mode: 0644,
UID: 1000,

3
internal/database/models.go
View File

@@ -5,7 +5,7 @@ package database
import (
"time"
"sneak.berlin/go/vaultik/internal/types"
"git.eeqj.de/sneak/vaultik/internal/types"
)
// File represents a file or directory in the backup system.
@@ -17,6 +17,7 @@ type File struct {
Path types.FilePath // Absolute path of the file
SourcePath types.SourcePath // The source directory this file came from (for restore path stripping)
MTime time.Time
CTime time.Time
Size int64
Mode uint32
UID uint32

4
internal/database/module.go
View File

@@ -6,9 +6,9 @@ import (
"os"
"path/filepath"
"git.eeqj.de/sneak/vaultik/internal/config"
"git.eeqj.de/sneak/vaultik/internal/log"
"go.uber.org/fx"
"sneak.berlin/go/vaultik/internal/config"
"sneak.berlin/go/vaultik/internal/log"
)
// Module provides database dependencies

6
internal/database/repositories_test.go
View File

@@ -7,7 +7,7 @@ import (
"testing"
"time"
"sneak.berlin/go/vaultik/internal/types"
"git.eeqj.de/sneak/vaultik/internal/types"
)
func TestRepositoriesTransaction(t *testing.T) {
@@ -23,6 +23,7 @@ func TestRepositoriesTransaction(t *testing.T) {
file := &File{
Path: "/test/tx_file.txt",
MTime: time.Now().Truncate(time.Second),
CTime: time.Now().Truncate(time.Second),
Size: 1024,
Mode: 0644,
UID: 1000,
@@ -145,6 +146,7 @@ func TestRepositoriesTransactionRollback(t *testing.T) {
file := &File{
Path: "/test/rollback_file.txt",
MTime: time.Now().Truncate(time.Second),
CTime: time.Now().Truncate(time.Second),
Size: 1024,
Mode: 0644,
UID: 1000,
@@ -200,6 +202,7 @@ func TestRepositoriesReadTransaction(t *testing.T) {
file := &File{
Path: "/test/read_file.txt",
MTime: time.Now().Truncate(time.Second),
CTime: time.Now().Truncate(time.Second),
Size: 1024,
Mode: 0644,
UID: 1000,
@@ -223,6 +226,7 @@ func TestRepositoriesReadTransaction(t *testing.T) {
_ = repos.Files.Create(ctx, tx, &File{
Path: "/test/should_fail.txt",
MTime: time.Now(),
CTime: time.Now(),
Size: 0,
Mode: 0644,
UID: 1000,

15
internal/database/repository_comprehensive_test.go
View File

@@ -7,7 +7,7 @@ import (
"testing"
"time"
"sneak.berlin/go/vaultik/internal/types"
"git.eeqj.de/sneak/vaultik/internal/types"
)
// TestFileRepositoryUUIDGeneration tests that files get unique UUIDs
@@ -23,6 +23,7 @@ func TestFileRepositoryUUIDGeneration(t *testing.T) {
{
Path: "/file1.txt",
MTime: time.Now().Truncate(time.Second),
CTime: time.Now().Truncate(time.Second),
Size: 1024,
Mode: 0644,
UID: 1000,
@@ -31,6 +32,7 @@ func TestFileRepositoryUUIDGeneration(t *testing.T) {
{
Path: "/file2.txt",
MTime: time.Now().Truncate(time.Second),
CTime: time.Now().Truncate(time.Second),
Size: 2048,
Mode: 0644,
UID: 1000,
@@ -70,6 +72,7 @@ func TestFileRepositoryGetByID(t *testing.T) {
file := &File{
Path: "/test.txt",
MTime: time.Now().Truncate(time.Second),
CTime: time.Now().Truncate(time.Second),
Size: 1024,
Mode: 0644,
UID: 1000,
@@ -117,6 +120,7 @@ func TestOrphanedFileCleanup(t *testing.T) {
file1 := &File{
Path: "/orphaned.txt",
MTime: time.Now().Truncate(time.Second),
CTime: time.Now().Truncate(time.Second),
Size: 1024,
Mode: 0644,
UID: 1000,
@@ -125,6 +129,7 @@ func TestOrphanedFileCleanup(t *testing.T) {
file2 := &File{
Path: "/referenced.txt",
MTime: time.Now().Truncate(time.Second),
CTime: time.Now().Truncate(time.Second),
Size: 2048,
Mode: 0644,
UID: 1000,
@@ -213,6 +218,7 @@ func TestOrphanedChunkCleanup(t *testing.T) {
file := &File{
Path: "/test.txt",
MTime: time.Now().Truncate(time.Second),
CTime: time.Now().Truncate(time.Second),
Size: 1024,
Mode: 0644,
UID: 1000,
@@ -342,6 +348,7 @@ func TestFileChunkRepositoryWithUUIDs(t *testing.T) {
file := &File{
Path: "/test.txt",
MTime: time.Now().Truncate(time.Second),
CTime: time.Now().Truncate(time.Second),
Size: 3072,
Mode: 0644,
UID: 1000,
@@ -412,6 +419,7 @@ func TestChunkFileRepositoryWithUUIDs(t *testing.T) {
file1 := &File{
Path: "/file1.txt",
MTime: time.Now().Truncate(time.Second),
CTime: time.Now().Truncate(time.Second),
Size: 1024,
Mode: 0644,
UID: 1000,
@@ -420,6 +428,7 @@ func TestChunkFileRepositoryWithUUIDs(t *testing.T) {
file2 := &File{
Path: "/file2.txt",
MTime: time.Now().Truncate(time.Second),
CTime: time.Now().Truncate(time.Second),
Size: 1024,
Mode: 0644,
UID: 1000,
@@ -577,6 +586,7 @@ func TestComplexOrphanedDataScenario(t *testing.T) {
files[i] = &File{
Path: types.FilePath(fmt.Sprintf("/file%d.txt", i)),
MTime: time.Now().Truncate(time.Second),
CTime: time.Now().Truncate(time.Second),
Size: 1024,
Mode: 0644,
UID: 1000,
@@ -668,6 +678,7 @@ func TestCascadeDelete(t *testing.T) {
file := &File{
Path: "/cascade-test.txt",
MTime: time.Now().Truncate(time.Second),
CTime: time.Now().Truncate(time.Second),
Size: 1024,
Mode: 0644,
UID: 1000,
@@ -739,6 +750,7 @@ func TestTransactionIsolation(t *testing.T) {
file := &File{
Path: "/tx-test.txt",
MTime: time.Now().Truncate(time.Second),
CTime: time.Now().Truncate(time.Second),
Size: 1024,
Mode: 0644,
UID: 1000,
@@ -800,6 +812,7 @@ func TestConcurrentOrphanedCleanup(t *testing.T) {
file := &File{
Path: types.FilePath(fmt.Sprintf("/concurrent-%d.txt", i)),
MTime: time.Now().Truncate(time.Second),
CTime: time.Now().Truncate(time.Second),
Size: 1024,
Mode: 0644,
UID: 1000,

2
internal/database/repository_debug_test.go
View File

@@ -18,6 +18,7 @@ func TestOrphanedFileCleanupDebug(t *testing.T) {
file1 := &File{
Path: "/orphaned.txt",
MTime: time.Now().Truncate(time.Second),
CTime: time.Now().Truncate(time.Second),
Size: 1024,
Mode: 0644,
UID: 1000,
@@ -26,6 +27,7 @@ func TestOrphanedFileCleanupDebug(t *testing.T) {
file2 := &File{
Path: "/referenced.txt",
MTime: time.Now().Truncate(time.Second),
CTime: time.Now().Truncate(time.Second),
Size: 2048,
Mode: 0644,
UID: 1000,

14
internal/database/repository_edge_cases_test.go
View File

@@ -7,7 +7,7 @@ import (
"testing"
"time"
"sneak.berlin/go/vaultik/internal/types"
"git.eeqj.de/sneak/vaultik/internal/types"
)
// TestFileRepositoryEdgeCases tests edge cases for file repository
@@ -29,6 +29,7 @@ func TestFileRepositoryEdgeCases(t *testing.T) {
file: &File{
Path: "",
MTime: time.Now(),
CTime: time.Now(),
Size: 1024,
Mode: 0644,
UID: 1000,
@@ -41,6 +42,7 @@ func TestFileRepositoryEdgeCases(t *testing.T) {
file: &File{
Path: types.FilePath("/" + strings.Repeat("a", 4096)),
MTime: time.Now(),
CTime: time.Now(),
Size: 1024,
Mode: 0644,
UID: 1000,
@@ -53,6 +55,7 @@ func TestFileRepositoryEdgeCases(t *testing.T) {
file: &File{
Path: "/test/file with spaces and 特殊文字.txt",
MTime: time.Now(),
CTime: time.Now(),
Size: 1024,
Mode: 0644,
UID: 1000,
@@ -65,6 +68,7 @@ func TestFileRepositoryEdgeCases(t *testing.T) {
file: &File{
Path: "/empty.txt",
MTime: time.Now(),
CTime: time.Now(),
Size: 0,
Mode: 0644,
UID: 1000,
@@ -77,6 +81,7 @@ func TestFileRepositoryEdgeCases(t *testing.T) {
file: &File{
Path: "/link",
MTime: time.Now(),
CTime: time.Now(),
Size: 0,
Mode: 0777 | 0120000, // symlink mode
UID: 1000,
@@ -118,6 +123,7 @@ func TestDuplicateHandling(t *testing.T) {
file1 := &File{
Path: "/duplicate.txt",
MTime: time.Now(),
CTime: time.Now(),
Size: 1024,
Mode: 0644,
UID: 1000,
@@ -126,6 +132,7 @@ func TestDuplicateHandling(t *testing.T) {
file2 := &File{
Path: "/duplicate.txt", // Same path
MTime: time.Now().Add(time.Hour),
CTime: time.Now().Add(time.Hour),
Size: 2048,
Mode: 0644,
UID: 1000,
@@ -185,6 +192,7 @@ func TestDuplicateHandling(t *testing.T) {
file := &File{
Path: "/test-dup-fc.txt",
MTime: time.Now(),
CTime: time.Now(),
Size: 1024,
Mode: 0644,
UID: 1000,
@@ -236,6 +244,7 @@ func TestNullHandling(t *testing.T) {
file := &File{
Path: "/regular.txt",
MTime: time.Now(),
CTime: time.Now(),
Size: 1024,
Mode: 0644,
UID: 1000,
@@ -340,6 +349,7 @@ func TestLargeDatasets(t *testing.T) {
file := &File{
Path: types.FilePath(fmt.Sprintf("/large/file%05d.txt", i)),
MTime: time.Now(),
CTime: time.Now(),
Size: int64(i * 1024),
Mode: 0644,
UID: uint32(1000 + (i % 10)),
@@ -464,6 +474,7 @@ func TestQueryInjection(t *testing.T) {
file := &File{
Path: types.FilePath(injection),
MTime: time.Now(),
CTime: time.Now(),
Size: 1024,
Mode: 0644,
UID: 1000,
@@ -502,6 +513,7 @@ func TestTimezoneHandling(t *testing.T) {
file := &File{
Path: "/timezone-test.txt",
MTime: nyTime,
CTime: nyTime,
Size: 1024,
Mode: 0644,
UID: 1000,

14
internal/database/schema/001.sql → internal/database/schema.sql
View File

@@ -1,5 +1,6 @@
-- Migration 001: Initial Vaultik schema
-- All core tables for tracking files, chunks, blobs, snapshots, and uploads.
-- Vaultik Database Schema
-- Note: This database does not support migrations. If the schema changes,
-- delete the local database and perform a full backup to recreate it.
-- Files table: stores metadata about files in the filesystem
CREATE TABLE IF NOT EXISTS files (
@@ -7,6 +8,7 @@ CREATE TABLE IF NOT EXISTS files (
path TEXT NOT NULL UNIQUE,
source_path TEXT NOT NULL DEFAULT '', -- The source directory this file came from (for restore path stripping)
mtime INTEGER NOT NULL,
ctime INTEGER NOT NULL,
size INTEGER NOT NULL,
mode INTEGER NOT NULL,
uid INTEGER NOT NULL,
@@ -101,7 +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)
@@ -114,7 +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)
@@ -128,8 +130,8 @@ 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
CREATE INDEX IF NOT EXISTS idx_uploads_snapshot_id ON uploads(snapshot_id);
CREATE INDEX IF NOT EXISTS idx_uploads_snapshot_id ON uploads(snapshot_id);

9
internal/database/schema/000.sql
View File

@@ -1,9 +0,0 @@
-- Migration 000: Schema migrations tracking table
-- Applied as a bootstrap step before the normal migration loop.
CREATE TABLE IF NOT EXISTS schema_migrations (
version INTEGER PRIMARY KEY,
applied_at DATETIME DEFAULT CURRENT_TIMESTAMP
);
INSERT OR IGNORE INTO schema_migrations (version) VALUES (0);

11
internal/database/schema/008_uploads.sql Normal file
View File

@@ -0,0 +1,11 @@
-- Track blob upload metrics
CREATE TABLE IF NOT EXISTS uploads (
blob_hash TEXT PRIMARY KEY,
uploaded_at TIMESTAMP NOT NULL,
size INTEGER NOT NULL,
duration_ms INTEGER NOT NULL,
FOREIGN KEY (blob_hash) REFERENCES blobs(blob_hash)
);
CREATE INDEX idx_uploads_uploaded_at ON uploads(uploaded_at);
CREATE INDEX idx_uploads_duration ON uploads(duration_ms);

98
internal/database/snapshots.go
View File

@@ -6,7 +6,7 @@ import (
"fmt"
"time"
"sneak.berlin/go/vaultik/internal/types"
"git.eeqj.de/sneak/vaultik/internal/types"
)
type SnapshotRepository struct {
@@ -331,43 +331,6 @@ func (r *SnapshotRepository) AddFilesByIDBatch(ctx context.Context, tx *sql.Tx,
return nil
}
// PopulateReferencedBlobs ensures snapshot_blobs contains an entry for
// every blob that holds a chunk referenced by any file in the snapshot.
// This is necessary because the AddBlob hook only runs when a blob is
// newly uploaded during a snapshot — fully-deduplicated snapshots (where
// every chunk already exists in storage from a prior run) would otherwise
// have an empty snapshot_blobs set and be impossible to restore.
//
// Returns the number of rows inserted (i.e. blobs that were previously
// referenced indirectly via file_chunks but not yet recorded in
// snapshot_blobs for this snapshot).
func (r *SnapshotRepository) PopulateReferencedBlobs(ctx context.Context, tx *sql.Tx, snapshotID string) (int64, error) {
query := `
INSERT OR IGNORE INTO snapshot_blobs (snapshot_id, blob_id, blob_hash)
SELECT DISTINCT ?, blobs.id, blobs.blob_hash
FROM blobs
JOIN blob_chunks ON blob_chunks.blob_id = blobs.id
JOIN file_chunks ON file_chunks.chunk_hash = blob_chunks.chunk_hash
JOIN snapshot_files ON snapshot_files.file_id = file_chunks.file_id
WHERE snapshot_files.snapshot_id = ?
AND blobs.blob_hash IS NOT NULL
`
var result sql.Result
var err error
if tx != nil {
result, err = tx.ExecContext(ctx, query, snapshotID, snapshotID)
} else {
result, err = r.db.ExecWithLog(ctx, query, snapshotID, snapshotID)
}
if err != nil {
return 0, fmt.Errorf("populating referenced blobs: %w", err)
}
n, _ := result.RowsAffected()
return n, nil
}
// AddBlob adds a blob to a snapshot
func (r *SnapshotRepository) AddBlob(ctx context.Context, tx *sql.Tx, snapshotID string, blobID types.BlobID, blobHash types.BlobHash) error {
query := `
@@ -434,65 +397,6 @@ func (r *SnapshotRepository) GetSnapshotTotalCompressedSize(ctx context.Context,
return totalSize, nil
}
// GetSnapshotUncompressedChunkSize returns the sum of plaintext sizes of all unique
// chunks referenced by a snapshot (via snapshot_files → file_chunks → chunks).
func (r *SnapshotRepository) GetSnapshotUncompressedChunkSize(ctx context.Context, snapshotID string) (int64, error) {
query := `
SELECT COALESCE(SUM(c.size), 0)
FROM (
SELECT DISTINCT fc.chunk_hash
FROM snapshot_files sf
JOIN file_chunks fc ON sf.file_id = fc.file_id
WHERE sf.snapshot_id = ?
) sc
JOIN chunks c ON sc.chunk_hash = c.chunk_hash
`
var totalSize int64
err := r.db.conn.QueryRowContext(ctx, query, snapshotID).Scan(&totalSize)
if err != nil {
return 0, fmt.Errorf("querying uncompressed chunk size: %w", err)
}
return totalSize, nil
}
// GetSnapshotNewChunkSize returns the sum of plaintext sizes of chunks that are
// referenced by this snapshot but not by any earlier completed snapshot known to
// the local database. The result is the marginal uncompressed data this snapshot
// added to the dedup pool — i.e., the delta from prior snapshots.
func (r *SnapshotRepository) GetSnapshotNewChunkSize(ctx context.Context, snapshotID string) (int64, error) {
query := `
WITH this_snap_chunks AS (
SELECT DISTINCT fc.chunk_hash
FROM snapshot_files sf
JOIN file_chunks fc ON sf.file_id = fc.file_id
WHERE sf.snapshot_id = ?
),
prior_chunks AS (
SELECT DISTINCT fc.chunk_hash
FROM snapshots s
JOIN snapshot_files sf ON sf.snapshot_id = s.id
JOIN file_chunks fc ON fc.file_id = sf.file_id
WHERE s.completed_at IS NOT NULL
AND s.id != ?
AND s.started_at < (SELECT started_at FROM snapshots WHERE id = ?)
)
SELECT COALESCE(SUM(c.size), 0)
FROM chunks c
JOIN this_snap_chunks t ON c.chunk_hash = t.chunk_hash
WHERE c.chunk_hash NOT IN (SELECT chunk_hash FROM prior_chunks)
`
var totalSize int64
err := r.db.conn.QueryRowContext(ctx, query, snapshotID, snapshotID, snapshotID).Scan(&totalSize)
if err != nil {
return 0, fmt.Errorf("querying new chunk size: %w", err)
}
return totalSize, nil
}
// GetIncompleteSnapshots returns all snapshots that haven't been completed
func (r *SnapshotRepository) GetIncompleteSnapshots(ctx context.Context) ([]*Snapshot, error) {
query := `

2
internal/database/snapshots_test.go
View File

@@ -7,7 +7,7 @@ import (
"testing"
"time"
"sneak.berlin/go/vaultik/internal/types"
"git.eeqj.de/sneak/vaultik/internal/types"
)
const (

2
internal/database/uploads.go
View File

@@ -5,7 +5,7 @@ import (
"database/sql"
"time"
"sneak.berlin/go/vaultik/internal/log"
"git.eeqj.de/sneak/vaultik/internal/log"
)
// Upload represents a blob upload record

37
internal/globals/globals.go
View File

@@ -13,42 +13,19 @@ var Version string = "dev"
// Commit is the git commit hash, populated from main().
var Commit string = "unknown"
// CommitDate is the ISO-8601 date of the commit, populated from main().
var CommitDate string = "unknown"
// Author identifies the upstream author of vaultik.
const Author = "Jeffrey Paul <sneak@sneak.berlin>"
// Homepage is the canonical URL for vaultik.
const Homepage = "https://sneak.berlin/go/vaultik"
// License is the SPDX identifier for the project license.
const License = "MIT"
// Globals contains application-wide configuration and metadata.
type Globals struct {
Appname string
Version string
Commit string
CommitDate string
StartTime time.Time
Appname string
Version string
Commit string
StartTime time.Time
}
// New creates and returns a new Globals instance initialized with the package-level variables.
func New() (*Globals, error) {
return &Globals{
Appname: Appname,
Version: Version,
Commit: Commit,
CommitDate: CommitDate,
Appname: Appname,
Version: Version,
Commit: Commit,
}, nil
}
// ShortCommit returns the first 12 chars of the commit hash, or the
// whole string if it's shorter (e.g. "unknown").
func (g *Globals) ShortCommit() string {
if len(g.Commit) > 12 {
return g.Commit[:12]
}
return g.Commit
}

7
internal/models/models.go
View File

@@ -63,3 +63,10 @@ type Chunk struct {
Offset int64
Length int64
}
// DirtyPath represents a path marked for backup by inotify
type DirtyPath struct {
Path string
MarkedAt time.Time
EventType string // "create", "modify", "delete"
}

11
internal/s3/client.go
View File

@@ -2,7 +2,6 @@ package s3
import (
"context"
"errors"
"io"
"sync/atomic"
@@ -11,7 +10,6 @@ import (
"github.com/aws/aws-sdk-go-v2/credentials"
"github.com/aws/aws-sdk-go-v2/feature/s3/manager"
"github.com/aws/aws-sdk-go-v2/service/s3"
s3types "github.com/aws/aws-sdk-go-v2/service/s3/types"
"github.com/aws/smithy-go/logging"
)
@@ -205,12 +203,9 @@ func (c *Client) HeadObject(ctx context.Context, key string) (bool, error) {
Key: aws.String(fullKey),
})
if err != nil {
var notFound *s3types.NotFound
var noSuchKey *s3types.NoSuchKey
if errors.As(err, &notFound) || errors.As(err, &noSuchKey) {
return false, nil
}
return false, err
// Check if it's a not found error
// TODO: Add proper error type checking
return false, nil
}
return true, nil
}

2
internal/s3/client_test.go
View File

@@ -6,7 +6,7 @@ import (
"io"
"testing"
"sneak.berlin/go/vaultik/internal/s3"
"git.eeqj.de/sneak/vaultik/internal/s3"
)
func TestClient(t *testing.T) {

2
internal/s3/module.go
View File

@@ -3,8 +3,8 @@ package s3
import (
"context"
"git.eeqj.de/sneak/vaultik/internal/config"
"go.uber.org/fx"
"sneak.berlin/go/vaultik/internal/config"
)
// Module exports S3 functionality as an fx module.

9
internal/snapshot/backup_test.go
View File

@@ -13,8 +13,8 @@ import (
"testing/fstest"
"time"
"sneak.berlin/go/vaultik/internal/database"
"sneak.berlin/go/vaultik/internal/types"
"git.eeqj.de/sneak/vaultik/internal/database"
"git.eeqj.de/sneak/vaultik/internal/types"
)
// MockS3Client is a mock implementation of S3 operations for testing
@@ -345,8 +345,9 @@ func (b *BackupEngine) Backup(ctx context.Context, fsys fs.FS, root string) (str
Size: info.Size(),
Mode: uint32(info.Mode()),
MTime: info.ModTime(),
UID: 1000, // Default UID for test
GID: 1000, // Default GID for test
CTime: info.ModTime(), // Use mtime as ctime for test
UID: 1000, // Default UID for test
GID: 1000, // Default GID for test
}
err = b.repos.WithTx(ctx, func(ctx context.Context, tx *sql.Tx) error {
return b.repos.Files.Create(ctx, tx, file)

8
internal/snapshot/exclude_test.go
View File

@@ -7,12 +7,12 @@ import (
"testing"
"time"
"git.eeqj.de/sneak/vaultik/internal/database"
"git.eeqj.de/sneak/vaultik/internal/log"
"git.eeqj.de/sneak/vaultik/internal/snapshot"
"git.eeqj.de/sneak/vaultik/internal/types"
"github.com/spf13/afero"
"github.com/stretchr/testify/require"
"sneak.berlin/go/vaultik/internal/database"
"sneak.berlin/go/vaultik/internal/log"
"sneak.berlin/go/vaultik/internal/snapshot"
"sneak.berlin/go/vaultik/internal/types"
)
func setupExcludeTestFS(t *testing.T) afero.Fs {

8
internal/snapshot/file_change_test.go
View File

@@ -6,13 +6,13 @@ import (
"testing"
"time"
"git.eeqj.de/sneak/vaultik/internal/database"
"git.eeqj.de/sneak/vaultik/internal/log"
"git.eeqj.de/sneak/vaultik/internal/snapshot"
"git.eeqj.de/sneak/vaultik/internal/types"
"github.com/spf13/afero"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
"sneak.berlin/go/vaultik/internal/database"
"sneak.berlin/go/vaultik/internal/log"
"sneak.berlin/go/vaultik/internal/snapshot"
"sneak.berlin/go/vaultik/internal/types"
)
// TestFileContentChange verifies that when a file's content changes,

9
internal/snapshot/module.go
View File

@@ -1,18 +1,16 @@
package snapshot
import (
"git.eeqj.de/sneak/vaultik/internal/config"
"git.eeqj.de/sneak/vaultik/internal/database"
"git.eeqj.de/sneak/vaultik/internal/storage"
"github.com/spf13/afero"
"go.uber.org/fx"
"sneak.berlin/go/vaultik/internal/config"
"sneak.berlin/go/vaultik/internal/database"
"sneak.berlin/go/vaultik/internal/storage"
"sneak.berlin/go/vaultik/internal/ui"
)
// ScannerParams holds parameters for scanner creation
type ScannerParams struct {
EnableProgress bool
UI *ui.Writer // Where user-facing scanner messages go; nil = discard
Fs afero.Fs
Exclude []string // Exclude patterns (combined global + snapshot-specific)
SkipErrors bool // Skip file read errors (log loudly but continue)
@@ -48,7 +46,6 @@ func provideScannerFactory(cfg *config.Config, repos *database.Repositories, sto
CompressionLevel: cfg.CompressionLevel,
AgeRecipients: cfg.AgeRecipients,
EnableProgress: params.EnableProgress,
UI: params.UI,
Exclude: excludes,
SkipErrors: params.SkipErrors,
})

42
internal/snapshot/permission_error_test.go
View File

@@ -1,42 +0,0 @@
package snapshot
import (
"errors"
"fmt"
"os"
"runtime"
"strings"
"testing"
)
func TestWrapPermissionError(t *testing.T) {
// Non-permission errors pass through unchanged.
plain := errors.New("disk on fire")
if got := wrapPermissionError("/some/path", plain); got != plain {
t.Errorf("non-permission error should pass through, got %v", got)
}
// Permission errors get remediation instructions.
permErr := fmt.Errorf("open /x: %w", os.ErrPermission)
wrapped := wrapPermissionError("/Users/u/Library/Calendars", permErr)
if !errors.Is(wrapped, os.ErrPermission) {
t.Error("wrapped error should still match os.ErrPermission")
}
if !strings.Contains(wrapped.Error(), "/Users/u/Library/Calendars") {
t.Error("wrapped error should name the offending path")
}
if runtime.GOOS == "darwin" {
if !strings.Contains(wrapped.Error(), "Full Disk Access") {
t.Errorf("macOS permission error should mention Full Disk Access:\n%s", wrapped.Error())
}
if !strings.Contains(wrapped.Error(), "System Settings") {
t.Errorf("macOS permission error should point at System Settings:\n%s", wrapped.Error())
}
} else {
if !strings.Contains(wrapped.Error(), "--skip-errors") {
t.Errorf("non-macOS permission error should mention --skip-errors:\n%s", wrapped.Error())
}
}
}

2
internal/snapshot/progress.go
View File

@@ -10,8 +10,8 @@ import (
"syscall"
"time"
"git.eeqj.de/sneak/vaultik/internal/log"
"github.com/dustin/go-humanize"
"sneak.berlin/go/vaultik/internal/log"
)
const (

362
internal/snapshot/scanner.go
View File

@@ -5,24 +5,21 @@ import (
"database/sql"
"errors"
"fmt"
"io"
"os"
"path/filepath"
"runtime"
"strings"
"sync"
"time"
"git.eeqj.de/sneak/vaultik/internal/blob"
"git.eeqj.de/sneak/vaultik/internal/chunker"
"git.eeqj.de/sneak/vaultik/internal/database"
"git.eeqj.de/sneak/vaultik/internal/log"
"git.eeqj.de/sneak/vaultik/internal/storage"
"git.eeqj.de/sneak/vaultik/internal/types"
"github.com/dustin/go-humanize"
"github.com/gobwas/glob"
"github.com/spf13/afero"
"sneak.berlin/go/vaultik/internal/blob"
"sneak.berlin/go/vaultik/internal/chunker"
"sneak.berlin/go/vaultik/internal/database"
"sneak.berlin/go/vaultik/internal/log"
"sneak.berlin/go/vaultik/internal/storage"
"sneak.berlin/go/vaultik/internal/types"
"sneak.berlin/go/vaultik/internal/ui"
)
// FileToProcess holds information about a file that needs processing
@@ -61,8 +58,7 @@ type Scanner struct {
exclude []string // Glob patterns for files/directories to exclude
compiledExclude []compiledPattern // Compiled glob patterns
progress *ProgressReporter
skipErrors bool // Skip file read errors (log loudly but continue)
ui *ui.Writer // User-facing output; never nil (defaults to a discarding writer)
skipErrors bool // Skip file read errors (log loudly but continue)
// In-memory cache of known chunk hashes for fast existence checks
knownChunks map[string]struct{}
@@ -93,11 +89,10 @@ type ScannerConfig struct {
Storage storage.Storer
MaxBlobSize int64
CompressionLevel int
AgeRecipients []string // Optional, empty means no encryption
EnableProgress bool // Enable the live progress reporter (ETAs, throughput)
UI *ui.Writer // Where user-facing scanner messages go; nil = discard
Exclude []string // Glob patterns for files/directories to exclude
SkipErrors bool // Skip file read errors (log loudly but continue)
AgeRecipients []string // Optional, empty means no encryption
EnableProgress bool // Enable progress reporting
Exclude []string // Glob patterns for files/directories to exclude
SkipErrors bool // Skip file read errors (log loudly but continue)
}
// ScanResult contains the results of a scan operation
@@ -144,11 +139,6 @@ func NewScanner(cfg ScannerConfig) *Scanner {
// Compile exclude patterns
compiledExclude := compileExcludePatterns(cfg.Exclude)
uiw := cfg.UI
if uiw == nil {
uiw = ui.NewWithColor(io.Discard, false)
}
return &Scanner{
fs: cfg.FS,
chunker: chunker.NewChunker(cfg.ChunkSize),
@@ -162,7 +152,6 @@ func NewScanner(cfg ScannerConfig) *Scanner {
compiledExclude: compiledExclude,
progress: progress,
skipErrors: cfg.SkipErrors,
ui: uiw,
pendingChunkHashes: make(map[string]struct{}),
}
}
@@ -213,7 +202,7 @@ func (s *Scanner) Scan(ctx context.Context, path string, snapshotID string) (*Sc
// Phase 1c: Associate unchanged files with this snapshot (no new records needed)
if len(scanResult.UnchangedFileIDs) > 0 {
s.ui.Begin("Associating %s unchanged files with the snapshot.", s.ui.Count(len(scanResult.UnchangedFileIDs)))
fmt.Printf("Associating %s unchanged files with snapshot...\n", formatNumber(len(scanResult.UnchangedFileIDs)))
if err := s.batchAddFilesToSnapshot(ctx, scanResult.UnchangedFileIDs); err != nil {
return nil, fmt.Errorf("associating unchanged files: %w", err)
}
@@ -224,13 +213,13 @@ func (s *Scanner) Scan(ctx context.Context, path string, snapshotID string) (*Sc
// Phase 2: Process files and create chunks
if len(filesToProcess) > 0 {
s.ui.Begin("Backing up %s snapshot source files (chunking, compressing, encrypting, uploading).", s.ui.Count(len(filesToProcess)))
fmt.Printf("Processing %s files...\n", formatNumber(len(filesToProcess)))
log.Info("Phase 2/3: Creating snapshot (chunking, compressing, encrypting, and uploading blobs)")
if err := s.processPhase(ctx, filesToProcess, result); err != nil {
return nil, fmt.Errorf("process phase failed: %w", err)
}
} else {
s.ui.Info("Snapshot file backup skipped: no changed files (creating metadata-only snapshot).")
fmt.Printf("No files need processing. Creating metadata-only snapshot.\n")
log.Info("Phase 2/3: Skipping (no files need processing, metadata-only snapshot)")
}
@@ -243,18 +232,18 @@ func (s *Scanner) Scan(ctx context.Context, path string, snapshotID string) (*Sc
// loadDatabaseState loads known files and chunks from the database into memory for fast lookup
// This avoids per-file and per-chunk database queries during the scan and process phases
func (s *Scanner) loadDatabaseState(ctx context.Context, path string) (map[string]*database.File, error) {
s.ui.Begin("Loading known files from local index database.")
fmt.Println("Loading known files from database...")
knownFiles, err := s.loadKnownFiles(ctx, path)
if err != nil {
return nil, fmt.Errorf("loading known files: %w", err)
}
s.ui.Complete("Loaded %s known files from local index database.", s.ui.Count(len(knownFiles)))
fmt.Printf("Loaded %s known files from database\n", formatNumber(len(knownFiles)))
s.ui.Begin("Loading known chunks from local index database.")
fmt.Println("Loading known chunks from database...")
if err := s.loadKnownChunks(ctx); err != nil {
return nil, fmt.Errorf("loading known chunks: %w", err)
}
s.ui.Complete("Loaded %s known chunks from local index database.", s.ui.Count(len(s.knownChunks)))
fmt.Printf("Loaded %s known chunks from database\n", formatNumber(len(s.knownChunks)))
return knownFiles, nil
}
@@ -278,17 +267,17 @@ func (s *Scanner) summarizeScanPhase(result *ScanResult, filesToProcess []*FileT
"files_skipped", result.FilesSkipped,
"bytes_skipped", humanize.Bytes(uint64(result.BytesSkipped)))
msg := fmt.Sprintf("Enumerated %s snapshot source files (%s total), %s to back up (%s)",
s.ui.Count(result.FilesScanned),
s.ui.Size(totalSizeToProcess+result.BytesSkipped),
s.ui.Count(len(filesToProcess)),
s.ui.Size(totalSizeToProcess))
fmt.Printf("Scan complete: %s examined (%s), %s to process (%s)",
formatNumber(result.FilesScanned),
humanize.Bytes(uint64(totalSizeToProcess+result.BytesSkipped)),
formatNumber(len(filesToProcess)),
humanize.Bytes(uint64(totalSizeToProcess)))
if result.FilesDeleted > 0 {
msg += fmt.Sprintf(", %s deleted (%s)",
s.ui.Count(result.FilesDeleted),
s.ui.Size(result.BytesDeleted))
fmt.Printf(", %s deleted (%s)",
formatNumber(result.FilesDeleted),
humanize.Bytes(uint64(result.BytesDeleted)))
}
s.ui.Complete("%s.", msg)
fmt.Println()
}
// finalizeScanResult populates final blob statistics in the scan result
@@ -629,12 +618,12 @@ func (s *Scanner) scanPhase(ctx context.Context, path string, result *ScanResult
err := afero.Walk(s.fs, path, func(filePath string, info os.FileInfo, err error) error {
if err != nil {
if s.skipErrors {
log.Error("Failed to access file (skipping due to --skip-errors)", "path", filePath, "error", err)
s.ui.Error("Failed to access %s: %v. Skipping (--skip-errors).", s.ui.Path(filePath), err)
log.Error("ERROR: Failed to access file (skipping due to --skip-errors)", "path", filePath, "error", err)
fmt.Printf("ERROR: Failed to access %s: %v (skipping)\n", filePath, err)
return nil // Continue scanning
}
log.Debug("Error accessing filesystem entry", "path", filePath, "error", err)
return wrapPermissionError(filePath, err)
return err
}
// Check context cancellation
@@ -652,40 +641,7 @@ func (s *Scanner) scanPhase(ctx context.Context, path string, result *ScanResult
return nil
}
// Handle symlinks
if info.Mode()&os.ModeSymlink != 0 {
file := s.buildSymlinkEntry(filePath, info)
if file != nil {
existingFiles[filePath] = struct{}{}
mu.Lock()
filesToProcess = append(filesToProcess, &FileToProcess{
Path: filePath,
FileInfo: info,
File: file,
})
filesScanned++
mu.Unlock()
s.updateScanEntryStats(result, true, info)
}
return nil
}
// Handle directories (record for permission/ownership preservation and empty-dir support)
if info.IsDir() {
file := s.buildDirectoryEntry(filePath, info)
existingFiles[filePath] = struct{}{}
mu.Lock()
filesToProcess = append(filesToProcess, &FileToProcess{
Path: filePath,
FileInfo: info,
File: file,
})
filesScanned++
mu.Unlock()
return nil
}
// Skip other non-regular files (devices, sockets, etc.)
// Skip non-regular files for processing (but still count them)
if !info.Mode().IsRegular() {
return nil
}
@@ -717,7 +673,7 @@ func (s *Scanner) scanPhase(ctx context.Context, path string, result *ScanResult
// Output periodic status
if time.Since(lastStatusTime) >= statusInterval {
s.printScanProgressLine(filesScanned, changedCount, estimatedTotal, startTime)
printScanProgressLine(filesScanned, changedCount, estimatedTotal, startTime)
lastStatusTime = time.Now()
}
@@ -758,7 +714,7 @@ func (s *Scanner) updateScanEntryStats(result *ScanResult, needsProcessing bool,
// printScanProgressLine prints a periodic progress line during the scan phase,
// showing files scanned, percentage complete (if estimate available), and ETA
func (s *Scanner) printScanProgressLine(filesScanned int64, changedCount int, estimatedTotal int64, startTime time.Time) {
func printScanProgressLine(filesScanned int64, changedCount int, estimatedTotal int64, startTime time.Time) {
elapsed := time.Since(startTime)
rate := float64(filesScanned) / elapsed.Seconds()
@@ -776,95 +732,24 @@ func (s *Scanner) printScanProgressLine(filesScanned int64, changedCount int, es
if rate > 0 && remaining > 0 {
eta = time.Duration(float64(remaining)/rate) * time.Second
}
if eta > 0 {
s.ui.Progress("Snapshot source files enumeration: %s files (~%s), %s changed or new, %.0f files/sec, enumeration elapsed: %s, enumeration ETA: %s (est remain %s).",
s.ui.Count(int(filesScanned)),
s.ui.Percent(pct),
s.ui.Count(changedCount),
rate,
s.ui.Duration(elapsed),
s.ui.Time(time.Now().Add(eta)),
s.ui.Duration(eta))
} else {
s.ui.Progress("Snapshot source files enumeration: %s files (~%s), %s changed or new, %.0f files/sec, enumeration elapsed: %s.",
s.ui.Count(int(filesScanned)),
s.ui.Percent(pct),
s.ui.Count(changedCount),
rate,
s.ui.Duration(elapsed))
}
} else {
s.ui.Progress("Snapshot source files enumeration: %s files seen, %s changed or new, %.0f files/sec, enumeration elapsed: %s.",
s.ui.Count(int(filesScanned)),
s.ui.Count(changedCount),
fmt.Printf("Scan: %s files (~%.0f%%), %s changed/new, %.0f files/sec, %s elapsed",
formatNumber(int(filesScanned)),
pct,
formatNumber(changedCount),
rate,
s.ui.Duration(elapsed))
}
}
// buildSymlinkEntry creates a File record for a symlink.
// Returns nil if the link target cannot be read.
func (s *Scanner) buildSymlinkEntry(path string, info os.FileInfo) *database.File {
target, err := os.Readlink(path)
if err != nil {
log.Debug("Cannot read symlink target", "path", path, "error", err)
return nil
}
var uid, gid uint32
if stat, ok := info.Sys().(interface {
Uid() uint32
Gid() uint32
}); ok {
uid = stat.Uid()
gid = stat.Gid()
}
return &database.File{
ID: types.NewFileID(),
Path: types.FilePath(path),
SourcePath: types.SourcePath(s.currentSourcePath),
MTime: info.ModTime(),
Size: 0,
Mode: uint32(info.Mode()),
UID: uid,
GID: gid,
LinkTarget: types.FilePath(target),
}
}
// buildDirectoryEntry creates a File record for a directory.
func (s *Scanner) buildDirectoryEntry(path string, info os.FileInfo) *database.File {
var uid, gid uint32
if stat, ok := info.Sys().(interface {
Uid() uint32
Gid() uint32
}); ok {
uid = stat.Uid()
gid = stat.Gid()
}
return &database.File{
ID: types.NewFileID(),
Path: types.FilePath(path),
SourcePath: types.SourcePath(s.currentSourcePath),
MTime: info.ModTime(),
Size: 0,
Mode: uint32(info.Mode()),
UID: uid,
GID: gid,
}
}
// recordNonRegularFile writes a symlink or directory entry to the database
// and associates it with the current snapshot. No chunking is performed.
func (s *Scanner) recordNonRegularFile(ctx context.Context, ftp *FileToProcess) error {
return s.repos.WithTx(ctx, func(txCtx context.Context, tx *sql.Tx) error {
if err := s.repos.Files.Create(txCtx, tx, ftp.File); err != nil {
return fmt.Errorf("creating non-regular file record: %w", err)
elapsed.Round(time.Second))
if eta > 0 {
fmt.Printf(", ETA %s", eta.Round(time.Second))
}
return s.repos.Snapshots.AddFileByID(txCtx, tx, s.snapshotID, ftp.File.ID)
})
fmt.Println()
} else {
// First backup - no estimate available
fmt.Printf("Scan: %s files, %s changed/new, %.0f files/sec, %s elapsed\n",
formatNumber(int(filesScanned)),
formatNumber(changedCount),
rate,
elapsed.Round(time.Second))
}
}
// checkFileInMemory checks if a file needs processing using the in-memory map
@@ -900,6 +785,7 @@ func (s *Scanner) checkFileInMemory(path string, info os.FileInfo, knownFiles ma
Path: types.FilePath(path),
SourcePath: types.SourcePath(s.currentSourcePath), // Store source directory for restore path stripping
MTime: info.ModTime(),
CTime: info.ModTime(), // afero doesn't provide ctime
Size: info.Size(),
Mode: uint32(info.Mode()),
UID: uid,
@@ -964,16 +850,16 @@ func (s *Scanner) batchAddFilesToSnapshot(ctx context.Context, fileIDs []types.F
elapsed := time.Since(startTime)
rate := float64(end) / elapsed.Seconds()
pct := float64(end) / float64(len(fileIDs)) * 100
s.ui.Progress("Snapshot unchanged-file association: %s/%s (%s), %.0f files/sec.",
s.ui.Count(end), s.ui.Count(len(fileIDs)), s.ui.Percent(pct), rate)
fmt.Printf("Associating files: %s/%s (%.1f%%), %.0f files/sec\n",
formatNumber(end), formatNumber(len(fileIDs)), pct, rate)
lastStatusTime = time.Now()
}
}
elapsed := time.Since(startTime)
rate := float64(len(fileIDs)) / elapsed.Seconds()
s.ui.Complete("Associated %s unchanged files with the snapshot in %s (%.0f files/sec).",
s.ui.Count(len(fileIDs)), s.ui.Duration(elapsed), rate)
fmt.Printf("Associated %s unchanged files in %s (%.0f files/sec)\n",
formatNumber(len(fileIDs)), elapsed.Round(time.Second), rate)
return nil
}
@@ -1020,7 +906,7 @@ func (s *Scanner) processPhase(ctx context.Context, filesToProcess []*FileToProc
// Output periodic status
if time.Since(lastStatusTime) >= statusInterval {
s.printProcessingProgress(filesProcessed, totalFiles, bytesProcessed, totalBytes, startTime)
printProcessingProgress(filesProcessed, totalFiles, bytesProcessed, totalBytes, startTime)
lastStatusTime = time.Now()
}
}
@@ -1041,8 +927,8 @@ func (s *Scanner) processFileWithErrorHandling(ctx context.Context, fileToProces
}
// Skip file read errors if --skip-errors is enabled
if s.skipErrors {
log.Error("Failed to process file (skipping due to --skip-errors)", "path", fileToProcess.Path, "error", err)
s.ui.Error("Failed to process %s: %v. Skipping (--skip-errors).", s.ui.Path(fileToProcess.Path), err)
log.Error("ERROR: Failed to process file (skipping due to --skip-errors)", "path", fileToProcess.Path, "error", err)
fmt.Printf("ERROR: Failed to process %s: %v (skipping)\n", fileToProcess.Path, err)
result.FilesSkipped++
return true, nil
}
@@ -1053,7 +939,7 @@ func (s *Scanner) processFileWithErrorHandling(ctx context.Context, fileToProces
// printProcessingProgress prints a periodic progress line during the process phase,
// showing files processed, bytes transferred, throughput, and ETA
func (s *Scanner) printProcessingProgress(filesProcessed, totalFiles int, bytesProcessed, totalBytes int64, startTime time.Time) {
func printProcessingProgress(filesProcessed, totalFiles int, bytesProcessed, totalBytes int64, startTime time.Time) {
elapsed := time.Since(startTime)
pct := float64(bytesProcessed) / float64(totalBytes) * 100
byteRate := float64(bytesProcessed) / elapsed.Seconds()
@@ -1066,29 +952,20 @@ func (s *Scanner) printProcessingProgress(filesProcessed, totalFiles int, bytesP
eta = time.Duration(float64(remainingBytes)/byteRate) * time.Second
}
// Format: Progress [5.7k/610k] 6.7 GB/44 GB (15.4%), 106MB/sec, 500 files/sec, running for 1m30s, ETA: 5m49s
fmt.Printf("Progress [%s/%s] %s/%s (%.1f%%), %s/sec, %.0f files/sec, running for %s",
formatCompact(filesProcessed),
formatCompact(totalFiles),
humanize.Bytes(uint64(bytesProcessed)),
humanize.Bytes(uint64(totalBytes)),
pct,
humanize.Bytes(uint64(byteRate)),
fileRate,
elapsed.Round(time.Second))
if eta > 0 {
s.ui.Progress("Snapshot backup: %s/%s files (%s), %s/%s, %s, %.0f files/sec, backup elapsed: %s, backup ETA: %s (est remain %s).",
s.ui.Count(filesProcessed),
s.ui.Count(totalFiles),
s.ui.Percent(pct),
s.ui.Size(bytesProcessed),
s.ui.Size(totalBytes),
s.ui.Speed(byteRate),
fileRate,
s.ui.Duration(elapsed),
s.ui.Time(time.Now().Add(eta)),
s.ui.Duration(eta))
} else {
s.ui.Progress("Snapshot backup: %s/%s files (%s), %s/%s, %s, %.0f files/sec, backup elapsed: %s.",
s.ui.Count(filesProcessed),
s.ui.Count(totalFiles),
s.ui.Percent(pct),
s.ui.Size(bytesProcessed),
s.ui.Size(totalBytes),
s.ui.Speed(byteRate),
fileRate,
s.ui.Duration(elapsed))
fmt.Printf(", ETA: %s", eta.Round(time.Second))
}
fmt.Println()
}
// finalizeProcessPhase flushes the packer, writes remaining pending files to the database,
@@ -1180,15 +1057,12 @@ func (s *Scanner) uploadBlobIfNeeded(ctx context.Context, blobPath string, blobW
if _, err := s.storage.Stat(ctx, blobPath); err == nil {
log.Info("Blob already exists in storage, skipping upload",
"hash", finishedBlob.Hash, "size", humanize.Bytes(uint64(finishedBlob.Compressed)))
s.ui.Info("Blob %s (%s) already exists in backup destination store. Skipping upload.",
s.ui.Hex(finishedBlob.Hash), s.ui.Size(finishedBlob.Compressed))
fmt.Printf("Blob exists: %s (%s, skipped upload)\n",
finishedBlob.Hash[:12]+"...", humanize.Bytes(uint64(finishedBlob.Compressed)))
return true, nil
}
s.ui.Begin("Uploading blob %s (%s) to backup destination store.",
s.ui.Hex(finishedBlob.Hash), s.ui.Size(finishedBlob.Compressed))
progressCallback := s.makeUploadProgressCallback(ctx, finishedBlob, startTime)
progressCallback := s.makeUploadProgressCallback(ctx, finishedBlob)
if err := s.storage.PutWithProgress(ctx, blobPath, blobWithReader.Reader, finishedBlob.Compressed, progressCallback); err != nil {
log.Error("Failed to upload blob", "hash", finishedBlob.Hash, "error", err)
@@ -1198,11 +1072,11 @@ func (s *Scanner) uploadBlobIfNeeded(ctx context.Context, blobPath string, blobW
uploadDuration := time.Since(startTime)
uploadSpeedBps := float64(finishedBlob.Compressed) / uploadDuration.Seconds()
s.ui.Complete("Uploaded blob %s (%s) in %s at %s.",
s.ui.Hex(finishedBlob.Hash),
s.ui.Size(finishedBlob.Compressed),
s.ui.Duration(uploadDuration),
s.ui.Speed(uploadSpeedBps))
fmt.Printf("Blob stored: %s (%s, %s/sec, %s)\n",
finishedBlob.Hash[:12]+"...",
humanize.Bytes(uint64(finishedBlob.Compressed)),
humanize.Bytes(uint64(uploadSpeedBps)),
uploadDuration.Round(time.Millisecond))
log.Info("Successfully uploaded blob to storage",
"path", blobPath,
@@ -1220,14 +1094,10 @@ func (s *Scanner) uploadBlobIfNeeded(ctx context.Context, blobPath string, blobW
return false, nil
}
// makeUploadProgressCallback creates a progress callback for blob uploads.
// It updates the live progress reporter ~twice/sec for ETAs and prints a
// human-readable status line to s.output at most every 15 seconds.
func (s *Scanner) makeUploadProgressCallback(ctx context.Context, finishedBlob *blob.FinishedBlob, uploadStart time.Time) func(int64) error {
// makeUploadProgressCallback creates a progress callback for blob uploads
func (s *Scanner) makeUploadProgressCallback(ctx context.Context, finishedBlob *blob.FinishedBlob) func(int64) error {
lastProgressTime := time.Now()
lastProgressBytes := int64(0)
lastStdoutTime := time.Now()
const stdoutInterval = 15 * time.Second
return func(uploaded int64) error {
now := time.Now()
@@ -1241,28 +1111,6 @@ func (s *Scanner) makeUploadProgressCallback(ctx context.Context, finishedBlob *
lastProgressTime = now
lastProgressBytes = uploaded
}
// Periodic stdout status line so the user knows the upload is alive.
if now.Sub(lastStdoutTime) >= stdoutInterval {
totalElapsed := now.Sub(uploadStart)
pct := float64(uploaded) / float64(finishedBlob.Compressed) * 100
avgSpeed := float64(uploaded) / totalElapsed.Seconds()
var eta time.Duration
if avgSpeed > 0 {
eta = time.Duration(float64(finishedBlob.Compressed-uploaded)/avgSpeed) * time.Second
}
s.ui.Progress("Blob upload %s: %s / %s (%s) at %s, blob upload elapsed: %s, blob upload ETA: %s (est remain %s).",
s.ui.Hex(finishedBlob.Hash),
s.ui.Size(uploaded),
s.ui.Size(finishedBlob.Compressed),
s.ui.Percent(pct),
s.ui.Speed(avgSpeed),
s.ui.Duration(totalElapsed),
s.ui.Time(now.Add(eta)),
s.ui.Duration(eta))
lastStdoutTime = now
}
select {
case <-ctx.Done():
return ctx.Err()
@@ -1329,15 +1177,9 @@ type streamingChunkInfo struct {
// processFileStreaming processes a file by streaming chunks directly to the packer
func (s *Scanner) processFileStreaming(ctx context.Context, fileToProcess *FileToProcess, result *ScanResult) error {
// Symlinks and directories have no data to chunk — just record them in the DB.
mode := os.FileMode(fileToProcess.File.Mode)
if mode&os.ModeSymlink != 0 || mode.IsDir() {
return s.recordNonRegularFile(ctx, fileToProcess)
}
file, err := s.fs.Open(fileToProcess.Path)
if err != nil {
return fmt.Errorf("opening file: %w", wrapPermissionError(fileToProcess.Path, err))
return fmt.Errorf("opening file: %w", err)
}
defer func() { _ = file.Close() }()
@@ -1488,30 +1330,12 @@ func (s *Scanner) detectDeletedFilesFromMap(ctx context.Context, knownFiles map[
}
if result.FilesDeleted > 0 {
s.ui.Info("Snapshot source files enumeration detected %s deleted files.", s.ui.Count(result.FilesDeleted))
fmt.Printf("Found %s deleted files\n", formatNumber(result.FilesDeleted))
}
return nil
}
// wrapPermissionError augments permission errors with platform-specific
// remediation instructions. On macOS, TCC-protected directories (Calendars,
// Reminders, Photos, etc.) return EPERM unless the running application has
// been granted Full Disk Access.
func wrapPermissionError(path string, err error) error {
if !errors.Is(err, os.ErrPermission) {
return err
}
if runtime.GOOS == "darwin" {
return fmt.Errorf("cannot read %s: %w\n\n"+
"macOS is blocking access to this path. Grant Full Disk Access to your\n"+
"terminal application (or the app running vaultik):\n\n"+
" System Settings → Privacy & Security → Full Disk Access\n\n"+
"then quit and reopen the terminal and re-run the backup", path, err)
}
return fmt.Errorf("cannot read %s: %w (check file permissions, or run with --skip-errors to continue past unreadable files)", path, err)
}
// compileExcludePatterns compiles the exclude patterns into glob matchers
func compileExcludePatterns(patterns []string) []compiledPattern {
var compiled []compiledPattern
@@ -1610,3 +1434,25 @@ func (s *Scanner) shouldExclude(filePath, rootPath string) bool {
return false
}
// formatNumber formats a number with comma separators
func formatNumber(n int) string {
if n < 1000 {
return fmt.Sprintf("%d", n)
}
return humanize.Comma(int64(n))
}
// formatCompact formats a number compactly with k/M suffixes (e.g., 5.7k, 1.2M)
func formatCompact(n int) string {
if n < 1000 {
return fmt.Sprintf("%d", n)
}
if n < 10000 {
return fmt.Sprintf("%.1fk", float64(n)/1000)
}
if n < 1000000 {
return fmt.Sprintf("%.0fk", float64(n)/1000)
}
return fmt.Sprintf("%.1fM", float64(n)/1000000)
}

16
internal/snapshot/scanner_test.go
View File

@@ -7,11 +7,11 @@ import (
"testing"
"time"
"git.eeqj.de/sneak/vaultik/internal/database"
"git.eeqj.de/sneak/vaultik/internal/log"
"git.eeqj.de/sneak/vaultik/internal/snapshot"
"git.eeqj.de/sneak/vaultik/internal/types"
"github.com/spf13/afero"
"sneak.berlin/go/vaultik/internal/database"
"sneak.berlin/go/vaultik/internal/log"
"sneak.berlin/go/vaultik/internal/snapshot"
"sneak.berlin/go/vaultik/internal/types"
)
func TestScannerSimpleDirectory(t *testing.T) {
@@ -110,15 +110,15 @@ func TestScannerSimpleDirectory(t *testing.T) {
t.Errorf("expected at least 97 bytes scanned, got %d", result.BytesScanned)
}
// Verify files in database - includes regular files and directories
// Verify files in database - only regular files are stored
files, err := repos.Files.ListByPrefix(ctx, "/source")
if err != nil {
t.Fatalf("failed to list files: %v", err)
}
// 6 regular files + 3 directories (/source, /source/subdir, /source/subdir2)
if len(files) != 9 {
t.Errorf("expected 9 entries in database (6 files + 3 dirs), got %d", len(files))
// We should have 6 files (directories are not stored)
if len(files) != 6 {
t.Errorf("expected 6 files in database, got %d", len(files))
}
// Verify specific file

26
internal/snapshot/snapshot.go
View File

@@ -44,15 +44,15 @@ import (
"strings"
"time"
"git.eeqj.de/sneak/vaultik/internal/blobgen"
"git.eeqj.de/sneak/vaultik/internal/config"
"git.eeqj.de/sneak/vaultik/internal/database"
"git.eeqj.de/sneak/vaultik/internal/log"
"git.eeqj.de/sneak/vaultik/internal/storage"
"git.eeqj.de/sneak/vaultik/internal/types"
"github.com/dustin/go-humanize"
"github.com/spf13/afero"
"go.uber.org/fx"
"sneak.berlin/go/vaultik/internal/blobgen"
"sneak.berlin/go/vaultik/internal/config"
"sneak.berlin/go/vaultik/internal/database"
"sneak.berlin/go/vaultik/internal/log"
"sneak.berlin/go/vaultik/internal/storage"
"sneak.berlin/go/vaultik/internal/types"
)
// SnapshotManager handles snapshot creation and metadata export
@@ -180,20 +180,10 @@ func (sm *SnapshotManager) UpdateSnapshotStatsExtended(ctx context.Context, snap
})
}
// CompleteSnapshot marks a snapshot as completed and ensures snapshot_blobs
// is populated with every blob holding any chunk referenced by the
// snapshot's files (including deduplicated blobs uploaded by prior
// snapshots). Without this, fully-deduplicated snapshots are unrestorable.
// CompleteSnapshot marks a snapshot as completed and exports its metadata
func (sm *SnapshotManager) CompleteSnapshot(ctx context.Context, snapshotID string) error {
// Mark the snapshot as completed
err := sm.repos.WithTx(ctx, func(ctx context.Context, tx *sql.Tx) error {
added, err := sm.repos.Snapshots.PopulateReferencedBlobs(ctx, tx, snapshotID)
if err != nil {
return err
}
if added > 0 {
log.Info("Populated snapshot_blobs with dedup-referenced blobs",
"snapshot_id", snapshotID, "added", added)
}
return sm.repos.Snapshots.MarkComplete(ctx, tx, snapshotID)
})

6
internal/snapshot/snapshot_test.go
View File

@@ -7,10 +7,10 @@ import (
"path/filepath"
"testing"
"git.eeqj.de/sneak/vaultik/internal/config"
"git.eeqj.de/sneak/vaultik/internal/database"
"git.eeqj.de/sneak/vaultik/internal/log"
"github.com/spf13/afero"
"sneak.berlin/go/vaultik/internal/config"
"sneak.berlin/go/vaultik/internal/database"
"sneak.berlin/go/vaultik/internal/log"
)
const (

3
internal/storage/file.go
View File

@@ -23,8 +23,9 @@ type FileStorer struct {
// Uses the real OS filesystem by default; call SetFilesystem to override for testing.
func NewFileStorer(basePath string) (*FileStorer, error) {
fs := afero.NewOsFs()
// Ensure base path exists
if err := fs.MkdirAll(basePath, 0755); err != nil {
return nil, fmt.Errorf("file:// storage: cannot create or access %s: %w (check that the volume is mounted and writable)", basePath, err)
return nil, fmt.Errorf("creating base path: %w", err)
}
return &FileStorer{
fs: fs,

4
internal/storage/module.go
View File

@@ -5,9 +5,9 @@ import (
"fmt"
"strings"
"git.eeqj.de/sneak/vaultik/internal/config"
"git.eeqj.de/sneak/vaultik/internal/s3"
"go.uber.org/fx"
"sneak.berlin/go/vaultik/internal/config"
"sneak.berlin/go/vaultik/internal/s3"
)
// Module exports storage functionality as an fx module.

2
internal/storage/s3.go
View File

@@ -5,7 +5,7 @@ import (
"fmt"
"io"
"sneak.berlin/go/vaultik/internal/s3"
"git.eeqj.de/sneak/vaultik/internal/s3"
)
// S3Storer wraps the existing s3.Client to implement Storer.

288
internal/ui/ui.go
View File

@@ -1,288 +0,0 @@
// Package ui provides consistent user-facing output formatting for vaultik.
// All status updates, banners, errors, and warnings printed to the user
// should go through a *Writer from this package.
//
// Message classes (see Writer methods):
//
// - Begin — operation start, left-aligned, marker "》" (white)
// - Complete— operation completion, left-aligned, marker "》" (green)
// - Info — left-aligned neutral status, marker "》" (white)
// - Notice — left-aligned important note, marker "》" (cyan)
// - Warning — left-aligned warning, full word "Warning: " (orange/yellow)
// - Error — left-aligned error, full word "ERROR: " (red)
// - Progress— indented heartbeat / per-item update, marker " 》" (white)
// - Banner — application banner line, left-aligned, no marker
//
// Value formatters (Hex, Size, Duration, Time, Path, Snapshot, Speed,
// Count, Percent) return ANSI-colored strings the caller composes into
// the message body. When color is disabled (non-TTY output or NO_COLOR
// set) all formatters return plain text.
package ui
import (
"fmt"
"io"
"os"
"time"
"github.com/dustin/go-humanize"
"golang.org/x/term"
)
// ANSI SGR escape sequences.
const (
ansiReset = "\033[0m"
ansiBold = "\033[1m"
ansiRed = "\033[31m"
ansiGreen = "\033[32m"
ansiYellow = "\033[33m" // used for orange "Warning:" and for durations
ansiBlue = "\033[34m"
ansiMagenta = "\033[35m"
ansiCyan = "\033[36m"
ansiWhite = "\033[37m"
)
// Marker is the chevron prefix used for all non-error/warning lines.
const Marker = "》"
// Writer formats and emits user-facing messages with optional ANSI color.
// It also counts warnings and errors emitted so the caller can summarize at
// the end of an operation ("Finished successfully." vs "Finished with
// warnings.").
//
// When Quiet is set, Begin/Complete/Info/Notice/Detail/Progress/Banner
// are silently dropped, but Warning and Error always emit. This honors
// the convention that --quiet "Suppresses non-error output" — warnings
// and errors are by definition not suppressible.
type Writer struct {
out io.Writer
color bool
quiet bool
warnings int
errors int
}
// New returns a Writer that emits to out. Color is enabled when out is a
// TTY and the NO_COLOR environment variable is unset.
// https://no-color.org/
func New(out io.Writer) *Writer {
return &Writer{out: out, color: shouldColor(out)}
}
// NewWithColor returns a Writer with an explicit color setting, ignoring
// TTY detection. Useful for tests and for piped output that the caller
// wants to colorize anyway.
func NewWithColor(out io.Writer, color bool) *Writer {
return &Writer{out: out, color: color}
}
// SetQuiet toggles the writer's quiet mode. In quiet mode all message
// classes are silenced except Warning and Error.
func (w *Writer) SetQuiet(quiet bool) { w.quiet = quiet }
// Quiet reports whether the writer is in quiet mode.
func (w *Writer) Quiet() bool { return w.quiet }
// Out returns the underlying writer.
func (w *Writer) Out() io.Writer { return w.out }
// Color reports whether color is enabled on this writer.
func (w *Writer) Color() bool { return w.color }
// shouldColor returns true when w is a real TTY and NO_COLOR is unset.
func shouldColor(w io.Writer) bool {
if os.Getenv("NO_COLOR") != "" {
return false
}
f, ok := w.(*os.File)
if !ok {
return false
}
return term.IsTerminal(int(f.Fd()))
}
// paint wraps s in the given ANSI color when color is enabled.
func (w *Writer) paint(color, s string) string {
if !w.color {
return s
}
return color + s + ansiReset
}
// ───────────────────────── message methods ─────────────────────────
// Begin prints an operation-start line, left-aligned with a white marker.
func (w *Writer) Begin(format string, args ...any) {
if w.quiet {
return
}
w.emit(ansiWhite, Marker, "", format, args)
}
// Complete prints an operation-completion line in green, left-aligned.
func (w *Writer) Complete(format string, args ...any) {
if w.quiet {
return
}
w.emit(ansiGreen, Marker, ansiGreen, format, args)
}
// Info prints a neutral status line, left-aligned with a white marker.
func (w *Writer) Info(format string, args ...any) {
if w.quiet {
return
}
w.emit(ansiWhite, Marker, "", format, args)
}
// Notice prints an attention-worthy informational line, marker in cyan.
func (w *Writer) Notice(format string, args ...any) {
if w.quiet {
return
}
w.emit(ansiCyan, Marker, "", format, args)
}
// Warning prints "⚠️ Warning: " in orange/yellow followed by the message.
func (w *Writer) Warning(format string, args ...any) {
w.warnings++
prefix := "⚠️ " + w.paint(ansiYellow+ansiBold, "Warning: ")
_, _ = fmt.Fprintln(w.out, prefix+fmt.Sprintf(format, args...))
}
// Error prints "🛑 ERROR: " in red followed by the message. Goes to the
// same writer as everything else; callers that want stderr should
// construct a separate Writer for it.
func (w *Writer) Error(format string, args ...any) {
w.errors++
prefix := "🛑 " + w.paint(ansiRed+ansiBold, "ERROR: ")
_, _ = fmt.Fprintln(w.out, prefix+fmt.Sprintf(format, args...))
}
// Detail prints an indented continuation line under a preceding Complete
// (or other top-level message). Marker " 》" (white) at column 2.
// Distinct from Progress (semantically a "heartbeat") in usage but
// visually identical.
func (w *Writer) Detail(format string, args ...any) {
if w.quiet {
return
}
w.emit(ansiWhite, " "+Marker, "", format, args)
}
// WarningCount returns the number of Warning() calls this writer has emitted.
func (w *Writer) WarningCount() int { return w.warnings }
// ErrorCount returns the number of Error() calls this writer has emitted.
func (w *Writer) ErrorCount() int { return w.errors }
// Progress prints an indented heartbeat / per-item update, marker in white.
func (w *Writer) Progress(format string, args ...any) {
if w.quiet {
return
}
w.emit(ansiWhite, " "+Marker, "", format, args)
}
// Banner prints a line with no marker, left-aligned. Bold when color
// is enabled. Used for the application startup banner only.
func (w *Writer) Banner(format string, args ...any) {
if w.quiet {
return
}
body := fmt.Sprintf(format, args...)
if w.color {
body = ansiBold + body + ansiReset
}
_, _ = fmt.Fprintln(w.out, body)
}
// emit writes "<prefix> <body>\n" with the prefix painted in prefixColor
// and the body optionally painted in bodyColor (empty = no body color).
func (w *Writer) emit(prefixColor, prefix, bodyColor, format string, args []any) {
body := fmt.Sprintf(format, args...)
if bodyColor != "" {
body = w.paint(bodyColor, body)
}
_, _ = fmt.Fprintln(w.out, w.paint(prefixColor, prefix)+" "+body)
}
// ───────────────────────── value formatters ─────────────────────────
//
// These return ANSI-colored strings the caller composes into a message
// body. When color is disabled they return plain text.
// Hex colorizes a hex identifier (blob hash, chunk hash, snapshot id).
// Long hashes are abbreviated to first 12 chars with "...".
func (w *Writer) Hex(s string) string {
short := s
if len(s) > 12 {
short = s[:12] + "..."
}
return w.paint(ansiCyan, short)
}
// Snapshot colorizes a snapshot ID (full, no abbreviation).
func (w *Writer) Snapshot(id string) string {
return w.paint(ansiCyan+ansiBold, id)
}
// Path colorizes a filesystem path.
func (w *Writer) Path(p string) string {
return w.paint(ansiBlue, p)
}
// Size colorizes a byte count using humanize.Bytes.
func (w *Writer) Size(bytes int64) string {
return w.paint(ansiMagenta, humanize.Bytes(uint64(bytes)))
}
// Speed colorizes a network transfer rate. Input is bytes/sec; output is
// bits/sec with an appropriate SI unit (bit/s, Kbit/s, Mbit/s, Gbit/s) —
// network transfer rates are conventionally expressed in bits.
func (w *Writer) Speed(bytesPerSec float64) string {
if bytesPerSec <= 0 {
return w.paint(ansiMagenta, "N/A")
}
bitsPerSec := bytesPerSec * 8
var s string
switch {
case bitsPerSec >= 1e9:
s = fmt.Sprintf("%.1f Gbit/sec", bitsPerSec/1e9)
case bitsPerSec >= 1e6:
s = fmt.Sprintf("%.0f Mbit/sec", bitsPerSec/1e6)
case bitsPerSec >= 1e3:
s = fmt.Sprintf("%.0f Kbit/sec", bitsPerSec/1e3)
default:
s = fmt.Sprintf("%.0f bit/sec", bitsPerSec)
}
return w.paint(ansiMagenta, s)
}
// Duration colorizes a time.Duration rounded to the nearest second.
func (w *Writer) Duration(d time.Duration) string {
return w.paint(ansiYellow, d.Round(time.Second).String())
}
// Time colorizes an absolute clock time. If t falls on today's local
// calendar date the output is "HH:MM:SS"; otherwise it is
// "YYYY-MM-DD HH:MM:SS". No timezone is included — values are
// displayed in the process's local zone.
func (w *Writer) Time(t time.Time) string {
t = t.Local()
now := time.Now()
if t.Year() == now.Year() && t.YearDay() == now.YearDay() {
return w.paint(ansiYellow, t.Format("15:04:05"))
}
return w.paint(ansiYellow, t.Format("2006-01-02 15:04:05"))
}
// Count colorizes an integer count with thousands separators.
func (w *Writer) Count(n int) string {
return w.paint(ansiMagenta, humanize.Comma(int64(n)))
}
// Percent colorizes a 0..100 percentage.
func (w *Writer) Percent(p float64) string {
return w.paint(ansiMagenta, fmt.Sprintf("%.1f%%", p))
}

134
internal/ui/ui_test.go
View File

@@ -1,134 +0,0 @@
package ui
import (
"bytes"
"strings"
"testing"
"time"
)
func newTestWriter(color bool) (*Writer, *bytes.Buffer) {
buf := &bytes.Buffer{}
return NewWithColor(buf, color), buf
}
func TestMessageMethodsPlain(t *testing.T) {
tests := []struct {
method string
fn func(*Writer)
want string
}{
{"Begin", func(w *Writer) { w.Begin("starting %s", "thing") }, "》 starting thing\n"},
{"Complete", func(w *Writer) { w.Complete("done %s", "thing") }, "》 done thing\n"},
{"Info", func(w *Writer) { w.Info("status") }, "》 status\n"},
{"Notice", func(w *Writer) { w.Notice("note") }, "》 note\n"},
{"Warning", func(w *Writer) { w.Warning("oops") }, "⚠️ Warning: oops\n"},
{"Error", func(w *Writer) { w.Error("boom") }, "🛑 ERROR: boom\n"},
{"Progress", func(w *Writer) { w.Progress("p") }, " 》 p\n"},
{"Detail", func(w *Writer) { w.Detail("d") }, " 》 d\n"},
{"Banner", func(w *Writer) { w.Banner("hello") }, "hello\n"}, // plain mode, no bold
}
for _, tt := range tests {
t.Run(tt.method, func(t *testing.T) {
w, buf := newTestWriter(false)
tt.fn(w)
if got := buf.String(); got != tt.want {
t.Errorf("got %q, want %q", got, tt.want)
}
})
}
}
func TestWarningErrorCounters(t *testing.T) {
w, _ := newTestWriter(false)
if w.WarningCount() != 0 || w.ErrorCount() != 0 {
t.Fatalf("expected fresh writer to have zero counts")
}
w.Info("normal")
w.Warning("first warn")
w.Warning("second warn")
w.Error("only error")
if got, want := w.WarningCount(), 2; got != want {
t.Errorf("WarningCount: got %d, want %d", got, want)
}
if got, want := w.ErrorCount(), 1; got != want {
t.Errorf("ErrorCount: got %d, want %d", got, want)
}
}
func TestColorOutputContainsANSI(t *testing.T) {
w, buf := newTestWriter(true)
w.Error("boom")
out := buf.String()
if !strings.Contains(out, "\033[") {
t.Errorf("expected ANSI escapes in color output, got %q", out)
}
if !strings.Contains(out, "ERROR: ") {
t.Errorf("expected 'ERROR: ' text in output, got %q", out)
}
}
func TestBannerBoldWhenColor(t *testing.T) {
w, buf := newTestWriter(true)
w.Banner("hello")
out := buf.String()
if !strings.Contains(out, "\033[1m") {
t.Errorf("expected bold ANSI escape in colored Banner output, got %q", out)
}
}
func TestValueFormattersPlain(t *testing.T) {
w, _ := newTestWriter(false)
if got := w.Hex("0123456789abcdef0123"); got != "0123456789ab..." {
t.Errorf("Hex long: got %q", got)
}
if got := w.Hex("short"); got != "short" {
t.Errorf("Hex short: got %q", got)
}
if got := w.Size(1024); got != "1.0 kB" {
t.Errorf("Size: got %q", got)
}
if got := w.Duration(90 * time.Second); got != "1m30s" {
t.Errorf("Duration: got %q", got)
}
if got := w.Count(12345); got != "12,345" {
t.Errorf("Count: got %q", got)
}
if got := w.Percent(12.34); got != "12.3%" {
t.Errorf("Percent: got %q", got)
}
// Speed: input is bytes/sec, output is bits/sec.
if got := w.Speed(0); got != "N/A" {
t.Errorf("Speed(0): got %q, want N/A", got)
}
if got := w.Speed(125_000_000); got != "1.0 Gbit/sec" { // 1 Gbit/s = 125 MB/s
t.Errorf("Speed(125e6): got %q", got)
}
if got := w.Speed(125_000); got != "1 Mbit/sec" {
t.Errorf("Speed(125e3): got %q", got)
}
// Time format: today → HH:MM:SS, other day → YYYY-MM-DD HH:MM:SS.
today := time.Date(time.Now().Year(), time.Now().Month(), time.Now().Day(), 14, 30, 45, 0, time.Local)
if got := w.Time(today); got != "14:30:45" {
t.Errorf("Time today: got %q, want 14:30:45", got)
}
other := time.Date(2030, 1, 2, 3, 4, 5, 0, time.Local)
if got := w.Time(other); got != "2030-01-02 03:04:05" {
t.Errorf("Time other day: got %q", got)
}
}
func TestValueFormattersColored(t *testing.T) {
w, _ := newTestWriter(true)
hex := w.Hex("0123456789abcdef0123")
if !strings.Contains(hex, "\033[") {
t.Errorf("expected ANSI in colored Hex output, got %q", hex)
}
if !strings.Contains(hex, "0123456789ab") {
t.Errorf("expected hex content in output, got %q", hex)
}
}

4
internal/vaultik/blob_fetch_hash_test.go
View File

@@ -10,8 +10,8 @@ import (
"testing"
"filippo.io/age"
"sneak.berlin/go/vaultik/internal/blobgen"
"sneak.berlin/go/vaultik/internal/vaultik"
"git.eeqj.de/sneak/vaultik/internal/blobgen"
"git.eeqj.de/sneak/vaultik/internal/vaultik"
)
// TestFetchAndDecryptBlobVerifiesHash verifies that FetchAndDecryptBlob checks

19
internal/vaultik/blob_fetch.go → internal/vaultik/blob_fetch_stub.go
View File

@@ -6,11 +6,9 @@ import (
"encoding/hex"
"fmt"
"io"
"time"
"filippo.io/age"
"sneak.berlin/go/vaultik/internal/blobgen"
"sneak.berlin/go/vaultik/internal/log"
"git.eeqj.de/sneak/vaultik/internal/blobgen"
)
// hashVerifyReader wraps a blobgen.Reader and verifies the double-SHA-256 hash
@@ -77,34 +75,19 @@ func (v *Vaultik) FetchAndDecryptBlob(ctx context.Context, blobHash string, expe
}
// FetchBlob downloads a blob and returns a reader for the encrypted data.
// Times the Storage.Get and Storage.Stat round-trips separately at
// debug level so we can see whether the size-only Stat (which is an
// extra request on every fetch) is hurting throughput.
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)
t0 := time.Now()
rc, err := v.Storage.Get(ctx, blobPath)
getDur := time.Since(t0)
if err != nil {
return nil, 0, fmt.Errorf("downloading blob %s: %w", blobHash[:16], err)
}
t0 = time.Now()
info, err := v.Storage.Stat(ctx, blobPath)
statDur := time.Since(t0)
if err != nil {
_ = rc.Close()
return nil, 0, fmt.Errorf("stat blob %s: %w", blobHash[:16], err)
}
log.Debug("FetchBlob round-trips",
"hash", blobHash[:16],
"ms_storage_get", getDur.Milliseconds(),
"ms_storage_stat", statDur.Milliseconds(),
"expected_size", expectedSize,
"stat_size", info.Size,
)
return rc, info.Size, nil
}

28
internal/vaultik/blobcache.go
View File

@@ -181,34 +181,6 @@ func (c *blobDiskCache) Has(key string) bool {
return ok
}
// Delete removes a blob from the cache and its disk file. No-op if absent.
// Used by restore's sweep logic to free blobs whose chunks have all been
// restored (so they will never be needed again during this restore).
func (c *blobDiskCache) Delete(key string) {
c.mu.Lock()
defer c.mu.Unlock()
e, ok := c.items[key]
if !ok {
return
}
c.unlink(e)
delete(c.items, key)
c.curBytes -= e.size
_ = os.Remove(c.path(key))
}
// Keys returns a snapshot of all cached keys. Safe for iteration without
// holding the cache lock; the cache may change concurrently.
func (c *blobDiskCache) Keys() []string {
c.mu.Lock()
defer c.mu.Unlock()
keys := make([]string, 0, len(c.items))
for k := range c.items {
keys = append(keys, k)
}
return keys
}
// Size returns current total cached bytes.
func (c *blobDiskCache) Size() int64 {
c.mu.Lock()

105
internal/vaultik/helpers.go
View File

@@ -2,25 +2,49 @@ package vaultik
import (
"fmt"
"regexp"
"strconv"
"strings"
"time"
"sneak.berlin/go/vaultik/internal/types"
"git.eeqj.de/sneak/vaultik/internal/types"
)
// SnapshotInfo contains information about a snapshot.
// UncompressedSize and NewChunkSize are populated only when the snapshot
// is present in the local database; LocallyTracked indicates whether
// those values are meaningful.
// SnapshotInfo contains information about a snapshot
type SnapshotInfo struct {
ID types.SnapshotID `json:"id"`
Timestamp time.Time `json:"timestamp"`
CompressedSize int64 `json:"compressed_size"`
UncompressedSize int64 `json:"uncompressed_size,omitempty"`
NewChunkSize int64 `json:"new_chunk_size,omitempty"`
LocallyTracked bool `json:"locally_tracked"`
ID types.SnapshotID `json:"id"`
Timestamp time.Time `json:"timestamp"`
CompressedSize int64 `json:"compressed_size"`
}
// formatNumber formats a number with commas
func formatNumber(n int) string {
str := fmt.Sprintf("%d", n)
var result []string
for i, digit := range str {
if i > 0 && (len(str)-i)%3 == 0 {
result = append(result, ",")
}
result = append(result, string(digit))
}
return strings.Join(result, "")
}
// formatDuration formats a duration in a human-readable way
func formatDuration(d time.Duration) string {
if d < time.Second {
return fmt.Sprintf("%dms", d.Milliseconds())
}
if d < time.Minute {
return fmt.Sprintf("%.1fs", d.Seconds())
}
if d < time.Hour {
mins := int(d.Minutes())
secs := int(d.Seconds()) % 60
return fmt.Sprintf("%dm %ds", mins, secs)
}
hours := int(d.Hours())
mins := int(d.Minutes()) % 60
return fmt.Sprintf("%dh %dm", hours, mins)
}
// formatBytes formats bytes in a human-readable format
@@ -55,55 +79,18 @@ func parseSnapshotTimestamp(snapshotID string) (time.Time, error) {
return timestamp.UTC(), nil
}
// parseSnapshotName extracts the snapshot name from a snapshot ID.
// Format: hostname_snapshotname_timestamp — the middle part(s) between hostname
// and the RFC3339 timestamp are the snapshot name (may contain underscores).
// Returns the snapshot name, or empty string if the ID is malformed.
func parseSnapshotName(snapshotID string) string {
parts := strings.Split(snapshotID, "_")
if len(parts) < 3 {
// Format: hostname_timestamp — no snapshot name
return ""
}
// Format: hostname_name_timestamp — middle parts are the name.
// The last part is the RFC3339 timestamp, the first part is the hostname,
// everything in between is the snapshot name (which may itself contain underscores).
return strings.Join(parts[1:len(parts)-1], "_")
}
// parseDuration parses a duration string with support for human-friendly units:
// d/day/days, w/week/weeks, mo/month/months, y/year/years, plus standard Go
// duration units (h, m, s).
// parseDuration parses a duration string with support for days
func parseDuration(s string) (time.Duration, error) {
if d, err := time.ParseDuration(s); err == nil {
return d, nil
}
re := regexp.MustCompile(`(\d+)\s*([a-zA-Z]+)`)
matches := re.FindAllStringSubmatch(s, -1)
if len(matches) == 0 {
return 0, fmt.Errorf("invalid duration: %q", s)
}
var total time.Duration
for _, match := range matches {
n, err := strconv.Atoi(match[1])
// Check for days suffix
if strings.HasSuffix(s, "d") {
daysStr := strings.TrimSuffix(s, "d")
days, err := strconv.Atoi(daysStr)
if err != nil {
return 0, fmt.Errorf("invalid number %q: %w", match[1], err)
}
unit := strings.ToLower(match[2])
switch unit {
case "d", "day", "days":
total += time.Duration(n) * 24 * time.Hour
case "w", "week", "weeks":
total += time.Duration(n) * 7 * 24 * time.Hour
case "mo", "month", "months":
total += time.Duration(n) * 30 * 24 * time.Hour
case "y", "year", "years":
total += time.Duration(n) * 365 * 24 * time.Hour
default:
return 0, fmt.Errorf("unknown time unit %q", unit)
return 0, fmt.Errorf("invalid days value: %w", err)
}
return time.Duration(days) * 24 * time.Hour, nil
}
return total, nil
// Otherwise use standard Go duration parsing
return time.ParseDuration(s)
}

112
internal/vaultik/helpers_test.go
View File

@@ -1,112 +0,0 @@
package vaultik
import (
"testing"
"time"
)
func TestParseSnapshotName(t *testing.T) {
tests := []struct {
name string
snapshotID string
want string
}{
{
name: "standard format with name",
snapshotID: "myhost_home_2026-01-12T14:41:15Z",
want: "home",
},
{
name: "standard format with different name",
snapshotID: "server1_system_2026-02-15T09:30:00Z",
want: "system",
},
{
name: "name with underscores",
snapshotID: "myhost_my_special_backup_2026-03-01T00:00:00Z",
want: "my_special_backup",
},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
got := parseSnapshotName(tt.snapshotID)
if got != tt.want {
t.Errorf("parseSnapshotName(%q) = %q, want %q", tt.snapshotID, got, tt.want)
}
})
}
}
func TestParseDuration(t *testing.T) {
tests := []struct {
input string
want time.Duration
err bool
}{
{"30d", 30 * 24 * time.Hour, false},
{"4w", 4 * 7 * 24 * time.Hour, false},
{"6mo", 6 * 30 * 24 * time.Hour, false},
{"1y", 365 * 24 * time.Hour, false},
{"2w3d", 2*7*24*time.Hour + 3*24*time.Hour, false},
{"1h", time.Hour, false},
{"30s", 30 * time.Second, false},
{"garbage", 0, true},
}
for _, tt := range tests {
t.Run(tt.input, func(t *testing.T) {
got, err := parseDuration(tt.input)
if tt.err {
if err == nil {
t.Fatalf("expected error for %q, got %v", tt.input, got)
}
return
}
if err != nil {
t.Fatalf("unexpected error for %q: %v", tt.input, err)
}
if got != tt.want {
t.Errorf("parseDuration(%q) = %v, want %v", tt.input, got, tt.want)
}
})
}
}
func TestParseSnapshotTimestamp(t *testing.T) {
tests := []struct {
name string
snapshotID string
wantErr bool
}{
{
name: "valid with name",
snapshotID: "myhost_home_2026-01-12T14:41:15Z",
wantErr: false,
},
{
name: "valid without name",
snapshotID: "myhost_2026-01-12T14:41:15Z",
wantErr: false,
},
{
name: "invalid - single part",
snapshotID: "nounderscore",
wantErr: true,
},
{
name: "invalid - bad timestamp",
snapshotID: "myhost_home_notadate",
wantErr: true,
},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
_, err := parseSnapshotTimestamp(tt.snapshotID)
if (err != nil) != tt.wantErr {
t.Errorf("parseSnapshotTimestamp(%q) error = %v, wantErr %v", tt.snapshotID, err, tt.wantErr)
}
})
}
}

16
internal/vaultik/info.go
View File

@@ -7,9 +7,9 @@ import (
"sort"
"strings"
"git.eeqj.de/sneak/vaultik/internal/log"
"git.eeqj.de/sneak/vaultik/internal/snapshot"
"github.com/dustin/go-humanize"
"sneak.berlin/go/vaultik/internal/log"
"sneak.berlin/go/vaultik/internal/snapshot"
)
// ShowInfo displays system and configuration information
@@ -66,6 +66,18 @@ func (v *Vaultik) ShowInfo() error {
}
v.printlnStdout()
// Daemon Settings (if applicable)
if v.Config.BackupInterval > 0 || v.Config.MinTimeBetweenRun > 0 {
v.printfStdout("=== Daemon Settings ===\n")
if v.Config.BackupInterval > 0 {
v.printfStdout("Backup Interval: %s\n", v.Config.BackupInterval)
}
if v.Config.MinTimeBetweenRun > 0 {
v.printfStdout("Minimum Time: %s\n", v.Config.MinTimeBetweenRun)
}
v.printlnStdout()
}
// Local Database
v.printfStdout("=== Local Database ===\n")
v.printfStdout("Index Path: %s\n", v.Config.IndexPath)

306
internal/vaultik/integration_test.go
View File

@@ -11,17 +11,16 @@ import (
"testing"
"time"
"git.eeqj.de/sneak/vaultik/internal/config"
"git.eeqj.de/sneak/vaultik/internal/database"
"git.eeqj.de/sneak/vaultik/internal/log"
"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"
"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/types"
"sneak.berlin/go/vaultik/internal/ui"
"sneak.berlin/go/vaultik/internal/vaultik"
)
// MockStorer implements storage.Storer for testing
@@ -521,7 +520,6 @@ func TestBackupAndRestore(t *testing.T) {
Fs: fs,
Stdout: io.Discard,
Stderr: io.Discard,
UI: ui.NewWithColor(io.Discard, false),
}
vaultikApp.SetContext(ctx)
@@ -543,293 +541,3 @@ func TestBackupAndRestore(t *testing.T) {
t.Log("Backup and restore test completed successfully")
}
// TestEndToEndFileStorage exercises the full backup → restore loop against the
// real `file://` storage backend (FileStorer) on a real OS filesystem. This is
// the closest local approximation of a production backup: encrypted blobs get
// written to disk, the metadata SQLite database is exported through the same
// blobgen pipeline as a real backup, and restoration reads them back through
// the public Vaultik.Restore entrypoint. It is the canonical end-to-end smoke
// test for 1.0.
func TestEndToEndFileStorage(t *testing.T) {
log.Initialize(log.Config{})
// Real OS filesystem (SQLite + FileStorer both need it).
fs := afero.NewOsFs()
tempDir, err := os.MkdirTemp("", "vaultik-e2e-")
require.NoError(t, err)
defer func() { _ = os.RemoveAll(tempDir) }()
dataDir := filepath.Join(tempDir, "source")
storeDir := filepath.Join(tempDir, "remote")
restoreDir := filepath.Join(tempDir, "restored")
dbPath := filepath.Join(tempDir, "index.sqlite")
// Write a representative mix of file sizes:
// - empty file
// - tiny text file
// - file just under chunk boundary
// - file forcing multiple chunks
// - nested subdirectories
chunkSize := int64(64 * 1024)
maxBlobSize := int64(512 * 1024)
testFiles := map[string][]byte{
filepath.Join(dataDir, "empty.txt"): {},
filepath.Join(dataDir, "small.txt"): []byte("hello vaultik"),
filepath.Join(dataDir, "subdir", "medium.bin"): bytesPattern("medium-", int(chunkSize/2)),
filepath.Join(dataDir, "subdir", "large.bin"): bytesPattern("large-", int(chunkSize*4)),
filepath.Join(dataDir, "deep", "nest", "leaf.txt"): []byte("leaf"),
}
for path, content := range testFiles {
require.NoError(t, fs.MkdirAll(filepath.Dir(path), 0o755))
require.NoError(t, afero.WriteFile(fs, path, content, 0o644))
}
// Create a file with non-default permissions.
restrictedPath := filepath.Join(dataDir, "restricted.txt")
require.NoError(t, afero.WriteFile(fs, restrictedPath, []byte("secret"), 0o600))
testFiles[restrictedPath] = []byte("secret")
// Create an empty directory (should survive round-trip).
emptyDir := filepath.Join(dataDir, "emptydir")
require.NoError(t, fs.MkdirAll(emptyDir, 0o755))
// Create a symlink.
symlinkPath := filepath.Join(dataDir, "link-to-small")
require.NoError(t, os.Symlink("small.txt", symlinkPath))
// FileStorer is the real-world local-disk backend.
storer, err := storage.NewFileStorer(storeDir)
require.NoError(t, err)
agePublicKey := "age1ezrjmfpwsc95svdg0y54mums3zevgzu0x0ecq2f7tp8a05gl0sjq9q9wjg"
ageSecretKey := "AGE-SECRET-KEY-19CR5YSFW59HM4TLD6GXVEDMZFTVVF7PPHKUT68TXSFPK7APHXA2QS2NJA5"
cfg := &config.Config{
AgeRecipients: []string{agePublicKey},
AgeSecretKey: ageSecretKey,
CompressionLevel: 3,
Hostname: "test-host",
}
ctx := context.Background()
db, err := database.New(ctx, dbPath)
require.NoError(t, err)
defer func() { _ = db.Close() }()
repos := database.NewRepositories(db)
sm := snapshot.NewSnapshotManager(snapshot.SnapshotManagerParams{
Repos: repos,
Storage: storer,
Config: cfg,
})
sm.SetFilesystem(fs)
scanner := snapshot.NewScanner(snapshot.ScannerConfig{
FS: fs,
Storage: storer,
ChunkSize: chunkSize,
MaxBlobSize: maxBlobSize,
CompressionLevel: cfg.CompressionLevel,
AgeRecipients: cfg.AgeRecipients,
Repositories: repos,
})
snapshotID, err := sm.CreateSnapshotWithName(ctx, cfg.Hostname, "e2e", "test-version", "test-git")
require.NoError(t, err)
scanResult, err := scanner.Scan(ctx, dataDir, snapshotID)
require.NoError(t, err)
require.Greater(t, scanResult.FilesScanned, 0)
require.Greater(t, scanResult.BlobsCreated, 0)
require.NoError(t, sm.CompleteSnapshot(ctx, snapshotID))
require.NoError(t, sm.ExportSnapshotMetadata(ctx, dbPath, snapshotID))
// Verify the backup actually landed on disk under blobs/ and metadata/.
blobInfo, err := os.Stat(filepath.Join(storeDir, "blobs"))
require.NoError(t, err)
require.True(t, blobInfo.IsDir())
metaInfo, err := os.Stat(filepath.Join(storeDir, "metadata", snapshotID))
require.NoError(t, err)
require.True(t, metaInfo.IsDir())
// Tear down the source DB before restore — restore must work using only
// the remote bytes plus the secret key, with no help from the local index.
require.NoError(t, db.Close())
restoreVaultik := &vaultik.Vaultik{
Config: cfg,
Storage: storer,
Fs: fs,
Stdout: io.Discard,
Stderr: io.Discard,
UI: ui.NewWithColor(io.Discard, false),
}
restoreVaultik.SetContext(ctx)
require.NoError(t, restoreVaultik.Restore(&vaultik.RestoreOptions{
SnapshotID: snapshotID,
TargetDir: restoreDir,
Verify: true,
}))
// Byte-equality compare every original against its restored copy.
for origPath, expected := range testFiles {
restoredPath := filepath.Join(restoreDir, origPath)
got, err := afero.ReadFile(fs, restoredPath)
require.NoError(t, err, "restored file missing: %s", restoredPath)
require.Equalf(t, expected, got, "byte-equality failed for %s", origPath)
}
// Verify the restricted file kept its permissions.
restoredRestricted := filepath.Join(restoreDir, restrictedPath)
rInfo, err := os.Stat(restoredRestricted)
require.NoError(t, err)
assert.Equal(t, os.FileMode(0o600), rInfo.Mode().Perm(),
"restricted file should preserve 0600 permissions")
// Verify the empty directory was restored.
restoredEmptyDir := filepath.Join(restoreDir, emptyDir)
dInfo, err := os.Stat(restoredEmptyDir)
require.NoError(t, err, "empty directory should be restored")
assert.True(t, dInfo.IsDir(), "emptydir should be a directory")
// Verify the symlink was restored with the correct target.
restoredSymlink := filepath.Join(restoreDir, symlinkPath)
target, err := os.Readlink(restoredSymlink)
require.NoError(t, err, "symlink should be restored")
assert.Equal(t, "small.txt", target, "symlink target should be preserved")
}
// TestDedupOnlySnapshotRestores backs up the same directory twice without
// touching it between runs, then restores the SECOND (fully-deduplicated)
// snapshot. The second snapshot uploads no new blobs — every chunk is
// already in storage from the first run. This test guards against the
// regression where snapshot_blobs was populated only for blobs uploaded
// during the snapshot, leaving fully-deduplicated snapshots unrestorable
// with "chunk X not found in any blob" errors.
func TestDedupOnlySnapshotRestores(t *testing.T) {
log.Initialize(log.Config{})
fs := afero.NewOsFs()
tempDir, err := os.MkdirTemp("", "vaultik-dedup-")
require.NoError(t, err)
defer func() { _ = os.RemoveAll(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)
testFiles := map[string][]byte{
filepath.Join(dataDir, "a.bin"): bytesPattern("a-", int(chunkSize*3)),
filepath.Join(dataDir, "b.bin"): bytesPattern("b-", int(chunkSize*2)),
}
for path, content := range testFiles {
require.NoError(t, fs.MkdirAll(filepath.Dir(path), 0o755))
require.NoError(t, afero.WriteFile(fs, path, content, 0o644))
}
storer, err := storage.NewFileStorer(storeDir)
require.NoError(t, err)
agePublicKey := "age1ezrjmfpwsc95svdg0y54mums3zevgzu0x0ecq2f7tp8a05gl0sjq9q9wjg"
ageSecretKey := "AGE-SECRET-KEY-19CR5YSFW59HM4TLD6GXVEDMZFTVVF7PPHKUT68TXSFPK7APHXA2QS2NJA5"
cfg := &config.Config{
AgeRecipients: []string{agePublicKey},
AgeSecretKey: ageSecretKey,
CompressionLevel: 3,
Hostname: "test-host",
}
ctx := context.Background()
db, err := database.New(ctx, dbPath)
require.NoError(t, err)
defer func() { _ = db.Close() }()
repos := database.NewRepositories(db)
makeScanner := func() *snapshot.Scanner {
return snapshot.NewScanner(snapshot.ScannerConfig{
FS: fs,
Storage: storer,
ChunkSize: chunkSize,
MaxBlobSize: maxBlobSize,
CompressionLevel: cfg.CompressionLevel,
AgeRecipients: cfg.AgeRecipients,
Repositories: repos,
})
}
sm := snapshot.NewSnapshotManager(snapshot.SnapshotManagerParams{
Repos: repos, Storage: storer, Config: cfg,
})
sm.SetFilesystem(fs)
// First snapshot — uploads all blobs.
id1, err := sm.CreateSnapshotWithName(ctx, cfg.Hostname, "dedup", "v", "g")
require.NoError(t, err)
r1, err := makeScanner().Scan(ctx, dataDir, id1)
require.NoError(t, err)
require.Greater(t, r1.BlobsCreated, 0, "first snapshot should upload at least one blob")
require.NoError(t, sm.CompleteSnapshot(ctx, id1))
require.NoError(t, sm.ExportSnapshotMetadata(ctx, dbPath, id1))
// Second snapshot — same data, every chunk dedups. Sleep past the
// second-precision timestamp so the snapshot IDs differ.
time.Sleep(1100 * time.Millisecond)
id2, err := sm.CreateSnapshotWithName(ctx, cfg.Hostname, "dedup", "v", "g")
require.NoError(t, err)
r2, err := makeScanner().Scan(ctx, dataDir, id2)
require.NoError(t, err)
require.Equal(t, 0, r2.BlobsCreated, "second snapshot should upload zero new blobs (fully dedup'd)")
require.NoError(t, sm.CompleteSnapshot(ctx, id2))
require.NoError(t, sm.ExportSnapshotMetadata(ctx, dbPath, id2))
// snapshot_blobs for id2 must be populated despite no uploads.
blobHashes, err := repos.Snapshots.GetBlobHashes(ctx, id2)
require.NoError(t, err)
require.NotEmpty(t, blobHashes, "snapshot_blobs for fully-dedup'd snapshot must reference blobs uploaded by prior snapshot")
require.NoError(t, db.Close())
restoreVaultik := &vaultik.Vaultik{
Config: cfg,
Storage: storer,
Fs: fs,
Stdout: io.Discard,
Stderr: io.Discard,
UI: ui.NewWithColor(io.Discard, false),
}
restoreVaultik.SetContext(ctx)
require.NoError(t, restoreVaultik.Restore(&vaultik.RestoreOptions{
SnapshotID: id2,
TargetDir: restoreDir,
Verify: true,
}))
for origPath, expected := range testFiles {
restoredPath := filepath.Join(restoreDir, origPath)
got, err := afero.ReadFile(fs, restoredPath)
require.NoError(t, err, "restored file missing: %s", restoredPath)
require.Equalf(t, expected, got, "byte-equality failed for %s", origPath)
}
}
// bytesPattern returns a deterministic byte slice of length n with a tag prefix,
// useful for forcing chunker behavior with reproducible content.
func bytesPattern(tag string, n int) []byte {
out := make([]byte, n)
for i := range out {
out[i] = byte(tag[i%len(tag)] ^ byte(i&0xff))
}
return out
}

27
internal/vaultik/prune.go
View File

@@ -5,8 +5,8 @@ import (
"fmt"
"strings"
"git.eeqj.de/sneak/vaultik/internal/log"
"github.com/dustin/go-humanize"
"sneak.berlin/go/vaultik/internal/log"
)
// PruneOptions contains options for the prune command
@@ -15,31 +15,6 @@ type PruneOptions struct {
JSON bool
}
// NukeRemote deletes every snapshot's metadata and every blob from remote
// storage. After this returns successfully the bucket prefix is empty and
// the next backup starts from scratch.
//
// Refuses to run unless force is true. The caller is responsible for
// confirming with the user.
func (v *Vaultik) NukeRemote(force bool) error {
if !force {
return fmt.Errorf("nuke requires --force (this deletes ALL remote snapshots and blobs)")
}
v.UI.Begin("Removing all snapshot metadata from backup destination store.")
if _, err := v.RemoveAllSnapshots(&RemoveOptions{Force: true, Remote: true}); err != nil {
return fmt.Errorf("removing all snapshots: %w", err)
}
v.UI.Begin("Removing all blobs from backup destination store.")
if err := v.PruneBlobs(&PruneOptions{Force: true}); err != nil {
return fmt.Errorf("pruning blobs: %w", err)
}
v.UI.Complete("Backup destination store is now empty.")
return nil
}
// PruneBlobsResult contains the result of a blob prune operation
type PruneBlobsResult struct {
BlobsFound int `json:"blobs_found"`

256
internal/vaultik/purge_per_name_test.go
View File

@@ -1,256 +0,0 @@
package vaultik_test
import (
"bytes"
"context"
"database/sql"
"strings"
"testing"
"time"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
"sneak.berlin/go/vaultik/internal/database"
"sneak.berlin/go/vaultik/internal/log"
"sneak.berlin/go/vaultik/internal/types"
"sneak.berlin/go/vaultik/internal/vaultik"
)
// setupPurgeTest creates a Vaultik instance with an in-memory database and mock
// storage pre-populated with the given snapshot IDs. Each snapshot is marked as
// completed. Remote metadata stubs are created so syncWithRemote keeps them.
func setupPurgeTest(t *testing.T, snapshotIDs []string) *vaultik.Vaultik {
t.Helper()
log.Initialize(log.Config{})
ctx := context.Background()
db, err := database.New(ctx, ":memory:")
require.NoError(t, err)
t.Cleanup(func() { _ = db.Close() })
repos := database.NewRepositories(db)
mockStorage := NewMockStorer()
// Insert each snapshot into the DB and create remote metadata stubs.
// Use timestamps parsed from snapshot IDs for realistic ordering.
for _, id := range snapshotIDs {
// Parse timestamp from the snapshot ID
parts := strings.Split(id, "_")
timestampStr := parts[len(parts)-1]
startedAt, err := time.Parse(time.RFC3339, timestampStr)
require.NoError(t, err, "parsing timestamp from snapshot ID %q", id)
completedAt := startedAt.Add(5 * time.Minute)
snap := &database.Snapshot{
ID: types.SnapshotID(id),
Hostname: "testhost",
VaultikVersion: "test",
StartedAt: startedAt,
CompletedAt: &completedAt,
}
err = repos.WithTx(ctx, func(ctx context.Context, tx *sql.Tx) error {
return repos.Snapshots.Create(ctx, tx, snap)
})
require.NoError(t, err, "creating snapshot %s", id)
// Create remote metadata stub so syncWithRemote keeps it
metadataKey := "metadata/" + id + "/manifest.json.zst"
err = mockStorage.Put(ctx, metadataKey, strings.NewReader("stub"))
require.NoError(t, err)
}
stdout := &bytes.Buffer{}
stderr := &bytes.Buffer{}
stdin := &bytes.Buffer{}
v := &vaultik.Vaultik{
Storage: mockStorage,
Repositories: repos,
DB: db,
Stdout: stdout,
Stderr: stderr,
Stdin: stdin,
}
v.SetContext(ctx)
return v
}
// listRemainingSnapshots returns IDs of all completed snapshots in the database.
func listRemainingSnapshots(t *testing.T, v *vaultik.Vaultik) []string {
t.Helper()
ctx := context.Background()
dbSnaps, err := v.Repositories.Snapshots.ListRecent(ctx, 10000)
require.NoError(t, err)
var ids []string
for _, s := range dbSnaps {
if s.CompletedAt != nil {
ids = append(ids, s.ID.String())
}
}
return ids
}
func TestPurgeKeepLatest_PerName(t *testing.T) {
// Create snapshots for two different names: "home" and "system".
// With per-name --keep-latest, the latest of each should be kept.
snapshotIDs := []string{
"testhost_system_2026-01-01T00:00:00Z",
"testhost_home_2026-01-01T01:00:00Z",
"testhost_system_2026-01-01T02:00:00Z",
"testhost_home_2026-01-01T03:00:00Z",
"testhost_system_2026-01-01T04:00:00Z",
}
v := setupPurgeTest(t, snapshotIDs)
err := v.PurgeSnapshotsWithOptions(&vaultik.SnapshotPurgeOptions{
KeepLatest: true,
Force: true,
})
require.NoError(t, err)
remaining := listRemainingSnapshots(t, v)
// Should keep the latest of each name
assert.Len(t, remaining, 2, "should keep exactly 2 snapshots (one per name)")
assert.Contains(t, remaining, "testhost_system_2026-01-01T04:00:00Z", "should keep latest system")
assert.Contains(t, remaining, "testhost_home_2026-01-01T03:00:00Z", "should keep latest home")
}
func TestPurgeKeepLatest_SingleName(t *testing.T) {
// All snapshots have the same name — keep-latest should keep exactly one.
snapshotIDs := []string{
"testhost_home_2026-01-01T00:00:00Z",
"testhost_home_2026-01-01T01:00:00Z",
"testhost_home_2026-01-01T02:00:00Z",
}
v := setupPurgeTest(t, snapshotIDs)
err := v.PurgeSnapshotsWithOptions(&vaultik.SnapshotPurgeOptions{
KeepLatest: true,
Force: true,
})
require.NoError(t, err)
remaining := listRemainingSnapshots(t, v)
assert.Len(t, remaining, 1)
assert.Contains(t, remaining, "testhost_home_2026-01-01T02:00:00Z", "should keep the newest")
}
func TestPurgeKeepLatest_WithNameFilter(t *testing.T) {
// Use --name to filter purge to only "home" snapshots.
// "system" snapshots should be untouched.
snapshotIDs := []string{
"testhost_system_2026-01-01T00:00:00Z",
"testhost_home_2026-01-01T01:00:00Z",
"testhost_system_2026-01-01T02:00:00Z",
"testhost_home_2026-01-01T03:00:00Z",
"testhost_home_2026-01-01T04:00:00Z",
}
v := setupPurgeTest(t, snapshotIDs)
err := v.PurgeSnapshotsWithOptions(&vaultik.SnapshotPurgeOptions{
KeepLatest: true,
Force: true,
Names: []string{"home"},
})
require.NoError(t, err)
remaining := listRemainingSnapshots(t, v)
// 2 system snapshots untouched + 1 latest home = 3
assert.Len(t, remaining, 3)
assert.Contains(t, remaining, "testhost_system_2026-01-01T00:00:00Z")
assert.Contains(t, remaining, "testhost_system_2026-01-01T02:00:00Z")
assert.Contains(t, remaining, "testhost_home_2026-01-01T04:00:00Z")
}
func TestPurgeKeepLatest_NoSnapshots(t *testing.T) {
v := setupPurgeTest(t, nil)
err := v.PurgeSnapshotsWithOptions(&vaultik.SnapshotPurgeOptions{
KeepLatest: true,
Force: true,
})
require.NoError(t, err)
}
func TestPurgeKeepLatest_NameFilterNoMatch(t *testing.T) {
snapshotIDs := []string{
"testhost_system_2026-01-01T00:00:00Z",
"testhost_system_2026-01-01T01:00:00Z",
}
v := setupPurgeTest(t, snapshotIDs)
err := v.PurgeSnapshotsWithOptions(&vaultik.SnapshotPurgeOptions{
KeepLatest: true,
Force: true,
Names: []string{"nonexistent"},
})
require.NoError(t, err)
// All snapshots should remain — the name filter matched nothing
remaining := listRemainingSnapshots(t, v)
assert.Len(t, remaining, 2)
}
func TestPurgeOlderThan_WithNameFilter(t *testing.T) {
// Snapshots with different names and timestamps.
// --older-than should apply only to the named subset when --name is used.
snapshotIDs := []string{
"testhost_system_2020-01-01T00:00:00Z",
"testhost_home_2020-01-01T00:00:00Z",
"testhost_system_2026-01-01T00:00:00Z",
"testhost_home_2026-01-01T00:00:00Z",
}
v := setupPurgeTest(t, snapshotIDs)
// Purge only "home" snapshots older than 365 days
err := v.PurgeSnapshotsWithOptions(&vaultik.SnapshotPurgeOptions{
OlderThan: "365d",
Force: true,
Names: []string{"home"},
})
require.NoError(t, err)
remaining := listRemainingSnapshots(t, v)
// Old system stays (not filtered by name), old home deleted, recent ones stay
assert.Len(t, remaining, 3)
assert.Contains(t, remaining, "testhost_system_2020-01-01T00:00:00Z")
assert.Contains(t, remaining, "testhost_system_2026-01-01T00:00:00Z")
assert.Contains(t, remaining, "testhost_home_2026-01-01T00:00:00Z")
}
func TestPurgeKeepLatest_ThreeNames(t *testing.T) {
// Three different snapshot names with multiple snapshots each.
snapshotIDs := []string{
"testhost_home_2026-01-01T00:00:00Z",
"testhost_system_2026-01-01T01:00:00Z",
"testhost_media_2026-01-01T02:00:00Z",
"testhost_home_2026-01-01T03:00:00Z",
"testhost_system_2026-01-01T04:00:00Z",
"testhost_media_2026-01-01T05:00:00Z",
"testhost_home_2026-01-01T06:00:00Z",
}
v := setupPurgeTest(t, snapshotIDs)
err := v.PurgeSnapshotsWithOptions(&vaultik.SnapshotPurgeOptions{
KeepLatest: true,
Force: true,
})
require.NoError(t, err)
remaining := listRemainingSnapshots(t, v)
assert.Len(t, remaining, 3, "should keep one per name")
assert.Contains(t, remaining, "testhost_home_2026-01-01T06:00:00Z")
assert.Contains(t, remaining, "testhost_system_2026-01-01T04:00:00Z")
assert.Contains(t, remaining, "testhost_media_2026-01-01T05:00:00Z")
}

351
internal/vaultik/remove_snapshot_test.go
View File

@@ -1,351 +0,0 @@
package vaultik_test
import (
"bytes"
"context"
"io"
"strings"
"sync"
"testing"
"github.com/klauspost/compress/zstd"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
"sneak.berlin/go/vaultik/internal/log"
"sneak.berlin/go/vaultik/internal/snapshot"
"sneak.berlin/go/vaultik/internal/storage"
"sneak.berlin/go/vaultik/internal/vaultik"
)
// testStorer implements storage.Storer for testing
type testStorer struct {
mu sync.Mutex
data map[string][]byte
}
func newTestStorer() *testStorer {
return &testStorer{
data: make(map[string][]byte),
}
}
func (s *testStorer) Put(ctx context.Context, key string, reader io.Reader) error {
s.mu.Lock()
defer s.mu.Unlock()
data, err := io.ReadAll(reader)
if err != nil {
return err
}
s.data[key] = data
return nil
}
func (s *testStorer) PutWithProgress(ctx context.Context, key string, reader io.Reader, size int64, progress storage.ProgressCallback) error {
return s.Put(ctx, key, reader)
}
func (s *testStorer) Get(ctx context.Context, key string) (io.ReadCloser, error) {
s.mu.Lock()
defer s.mu.Unlock()
data, exists := s.data[key]
if !exists {
return nil, storage.ErrNotFound
}
return io.NopCloser(bytes.NewReader(data)), nil
}
func (s *testStorer) Stat(ctx context.Context, key string) (*storage.ObjectInfo, error) {
s.mu.Lock()
defer s.mu.Unlock()
data, exists := s.data[key]
if !exists {
return nil, storage.ErrNotFound
}
return &storage.ObjectInfo{
Key: key,
Size: int64(len(data)),
}, nil
}
func (s *testStorer) Delete(ctx context.Context, key string) error {
s.mu.Lock()
defer s.mu.Unlock()
delete(s.data, key)
return nil
}
func (s *testStorer) List(ctx context.Context, prefix string) ([]string, error) {
s.mu.Lock()
defer s.mu.Unlock()
var keys []string
for key := range s.data {
if prefix == "" || strings.HasPrefix(key, prefix) {
keys = append(keys, key)
}
}
return keys, nil
}
func (s *testStorer) ListStream(ctx context.Context, prefix string) <-chan storage.ObjectInfo {
ch := make(chan storage.ObjectInfo)
go func() {
defer close(ch)
s.mu.Lock()
defer s.mu.Unlock()
for key, data := range s.data {
if prefix == "" || strings.HasPrefix(key, prefix) {
ch <- storage.ObjectInfo{
Key: key,
Size: int64(len(data)),
}
}
}
}()
return ch
}
func (s *testStorer) hasKey(key string) bool {
s.mu.Lock()
defer s.mu.Unlock()
_, exists := s.data[key]
return exists
}
func (s *testStorer) keyCount() int {
s.mu.Lock()
defer s.mu.Unlock()
return len(s.data)
}
func (s *testStorer) Info() storage.StorageInfo {
return storage.StorageInfo{
Type: "test",
Location: "memory",
}
}
// addManifest creates a compressed manifest in storage
func addManifest(t *testing.T, store *testStorer, snapshotID string, blobHashes []string) {
t.Helper()
blobs := make([]snapshot.BlobInfo, len(blobHashes))
for i, hash := range blobHashes {
blobs[i] = snapshot.BlobInfo{
Hash: hash,
CompressedSize: 1000,
}
}
manifest := &snapshot.Manifest{
SnapshotID: snapshotID,
BlobCount: len(blobs),
Blobs: blobs,
}
data, err := snapshot.EncodeManifest(manifest, 3)
require.NoError(t, err)
key := "metadata/" + snapshotID + "/manifest.json.zst"
err = store.Put(context.Background(), key, bytes.NewReader(data))
require.NoError(t, err)
}
// addBlob adds a fake blob to storage
func addBlob(t *testing.T, store *testStorer, hash string) {
t.Helper()
// Create zstd compressed data
var buf bytes.Buffer
writer, _ := zstd.NewWriter(&buf)
_, _ = writer.Write([]byte("blob data"))
_ = writer.Close()
key := "blobs/" + hash[:2] + "/" + hash[2:4] + "/" + hash
err := store.Put(context.Background(), key, bytes.NewReader(buf.Bytes()))
require.NoError(t, err)
}
// ============================================================================
// Unit Tests for RemoveSnapshot
// ============================================================================
func TestRemoveSnapshot_LocalOnly(t *testing.T) {
log.Initialize(log.Config{})
store := newTestStorer()
blobA := "aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa"
addManifest(t, store, "snapshot-001", []string{blobA})
addBlob(t, store, blobA)
tv := vaultik.NewForTesting(store)
opts := &vaultik.RemoveOptions{Force: true}
result, err := tv.RemoveSnapshot("snapshot-001", opts)
require.NoError(t, err)
assert.Equal(t, "snapshot-001", result.SnapshotID)
assert.False(t, result.RemoteRemoved)
// Blobs should NOT be deleted (that's what prune is for)
assert.True(t, store.hasKey("blobs/aa/aa/"+blobA))
// Remote metadata should NOT be deleted (no --remote flag)
assert.True(t, store.hasKey("metadata/snapshot-001/manifest.json.zst"))
// Verify output
assert.Contains(t, tv.Stdout.String(), "Removed snapshot 'snapshot-001' from local database")
}
func TestRemoveSnapshot_WithRemote(t *testing.T) {
log.Initialize(log.Config{})
store := newTestStorer()
blobA := "aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa"
addManifest(t, store, "snapshot-001", []string{blobA})
addBlob(t, store, blobA)
tv := vaultik.NewForTesting(store)
opts := &vaultik.RemoveOptions{Force: true, Remote: true}
result, err := tv.RemoveSnapshot("snapshot-001", opts)
require.NoError(t, err)
assert.Equal(t, "snapshot-001", result.SnapshotID)
assert.True(t, result.RemoteRemoved)
// Blobs should NOT be deleted
assert.True(t, store.hasKey("blobs/aa/aa/"+blobA))
// Remote metadata SHOULD be deleted
assert.False(t, store.hasKey("metadata/snapshot-001/manifest.json.zst"))
// Verify output mentions prune
assert.Contains(t, tv.Stdout.String(), "Removed snapshot 'snapshot-001' from local database")
assert.Contains(t, tv.Stdout.String(), "Removed snapshot metadata from remote storage")
assert.Contains(t, tv.Stdout.String(), "Run 'vaultik prune' to remove orphaned blobs")
}
func TestRemoveSnapshot_DryRun(t *testing.T) {
log.Initialize(log.Config{})
store := newTestStorer()
blobA := "aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa"
addManifest(t, store, "snapshot-001", []string{blobA})
addBlob(t, store, blobA)
initialCount := store.keyCount()
tv := vaultik.NewForTesting(store)
opts := &vaultik.RemoveOptions{Force: true, DryRun: true, Remote: true}
result, err := tv.RemoveSnapshot("snapshot-001", opts)
require.NoError(t, err)
assert.True(t, result.DryRun)
// Nothing should be deleted
assert.Equal(t, initialCount, store.keyCount())
assert.True(t, store.hasKey("blobs/aa/aa/"+blobA))
assert.True(t, store.hasKey("metadata/snapshot-001/manifest.json.zst"))
// Verify dry run message
assert.Contains(t, tv.Stdout.String(), "[Dry run - no changes made]")
}
func TestRemoveAllSnapshots_RequiresForce(t *testing.T) {
log.Initialize(log.Config{})
store := newTestStorer()
addManifest(t, store, "snapshot-001", []string{})
addManifest(t, store, "snapshot-002", []string{})
tv := vaultik.NewForTesting(store)
opts := &vaultik.RemoveOptions{All: true} // No Force
_, err := tv.RemoveAllSnapshots(opts)
assert.Error(t, err)
assert.Contains(t, err.Error(), "--all requires --force")
}
func TestRemoveAllSnapshots_WithForce(t *testing.T) {
log.Initialize(log.Config{})
store := newTestStorer()
blobA := "aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa"
addManifest(t, store, "snapshot-001", []string{blobA})
addManifest(t, store, "snapshot-002", []string{blobA})
addBlob(t, store, blobA)
tv := vaultik.NewForTesting(store)
opts := &vaultik.RemoveOptions{All: true, Force: true, Remote: true}
result, err := tv.RemoveAllSnapshots(opts)
require.NoError(t, err)
assert.Len(t, result.SnapshotsRemoved, 2)
assert.True(t, result.RemoteRemoved)
// Blobs should NOT be deleted
assert.True(t, store.hasKey("blobs/aa/aa/"+blobA))
// Remote metadata SHOULD be deleted
assert.False(t, store.hasKey("metadata/snapshot-001/manifest.json.zst"))
assert.False(t, store.hasKey("metadata/snapshot-002/manifest.json.zst"))
// Verify output
assert.Contains(t, tv.Stdout.String(), "Removed 2 snapshot(s)")
assert.Contains(t, tv.Stdout.String(), "Run 'vaultik prune' to remove orphaned blobs")
}
func TestRemoveAllSnapshots_DryRun(t *testing.T) {
log.Initialize(log.Config{})
store := newTestStorer()
addManifest(t, store, "snapshot-001", []string{})
addManifest(t, store, "snapshot-002", []string{})
initialCount := store.keyCount()
tv := vaultik.NewForTesting(store)
opts := &vaultik.RemoveOptions{All: true, Force: true, DryRun: true}
result, err := tv.RemoveAllSnapshots(opts)
require.NoError(t, err)
assert.True(t, result.DryRun)
assert.Len(t, result.SnapshotsRemoved, 2)
// Nothing should be deleted
assert.Equal(t, initialCount, store.keyCount())
// Verify dry run message
assert.Contains(t, tv.Stdout.String(), "[Dry run - no changes made]")
}
func TestRemoveAllSnapshots_NoSnapshots(t *testing.T) {
log.Initialize(log.Config{})
store := newTestStorer()
// No snapshots added
tv := vaultik.NewForTesting(store)
opts := &vaultik.RemoveOptions{All: true, Force: true}
result, err := tv.RemoveAllSnapshots(opts)
require.NoError(t, err)
assert.Len(t, result.SnapshotsRemoved, 0)
// Verify output
assert.Contains(t, tv.Stdout.String(), "No snapshots found")
}

325
internal/vaultik/restore.go
View File

@@ -7,18 +7,26 @@ import (
"encoding/hex"
"fmt"
"io"
"math"
"os"
"path/filepath"
"time"
"filippo.io/age"
"git.eeqj.de/sneak/vaultik/internal/blobgen"
"git.eeqj.de/sneak/vaultik/internal/database"
"git.eeqj.de/sneak/vaultik/internal/log"
"git.eeqj.de/sneak/vaultik/internal/types"
"github.com/dustin/go-humanize"
"github.com/schollz/progressbar/v3"
"github.com/spf13/afero"
"sneak.berlin/go/vaultik/internal/blobgen"
"sneak.berlin/go/vaultik/internal/database"
"sneak.berlin/go/vaultik/internal/log"
"sneak.berlin/go/vaultik/internal/types"
"golang.org/x/term"
)
const (
// progressBarWidth is the character width of the progress bar display.
progressBarWidth = 40
// progressBarThrottle is the minimum interval between progress bar redraws.
progressBarThrottle = 100 * time.Millisecond
)
// RestoreOptions contains options for the restore operation
@@ -27,7 +35,6 @@ type RestoreOptions struct {
TargetDir string
Paths []string // Optional paths to restore (empty = all)
Verify bool // Verify restored files by checking chunk hashes
SkipErrors bool // Continue past file-restore errors instead of aborting
}
// RestoreResult contains statistics from a restore operation
@@ -85,12 +92,10 @@ func (v *Vaultik) Restore(opts *RestoreOptions) error {
if len(files) == 0 {
log.Warn("No files found to restore")
v.UI.Warning("No files found to restore.")
return nil
}
log.Info("Found files to restore", "count", len(files))
v.UI.Info("Found %s files to restore.", v.UI.Count(len(files)))
// Step 3: Create target directory
if err := v.Fs.MkdirAll(opts.TargetDir, 0755); err != nil {
@@ -119,16 +124,16 @@ func (v *Vaultik) Restore(opts *RestoreOptions) error {
"duration", result.Duration,
)
v.UI.Complete("Restored %s files (%s) in %s.",
v.UI.Count(result.FilesRestored),
v.UI.Size(result.BytesRestored),
v.UI.Duration(result.Duration),
v.printfStdout("Restored %d files (%s) in %s\n",
result.FilesRestored,
humanize.Bytes(uint64(result.BytesRestored)),
result.Duration.Round(time.Second),
)
if result.FilesFailed > 0 {
v.UI.Warning("%d file(s) failed to restore:", result.FilesFailed)
_, _ = fmt.Fprintf(v.Stdout, "\nWARNING: %d file(s) failed to restore:\n", result.FilesFailed)
for _, path := range result.FailedFiles {
v.UI.Detail("%s", v.UI.Path(path))
_, _ = fmt.Fprintf(v.Stdout, " - %s\n", path)
}
}
@@ -168,64 +173,43 @@ func (v *Vaultik) restoreAllFiles(
chunkToBlobMap map[string]*database.BlobChunk,
) (*RestoreResult, error) {
result := &RestoreResult{}
// The restore-side blob cache is unbounded — restores may read any
// blob many times across deduplicated files and we want to avoid
// re-downloading until we can prove a blob is no longer needed.
// Cleanup is driven by the sweeper below, not by LRU.
blobCache, err := newBlobDiskCache(math.MaxInt64)
blobCache, err := newBlobDiskCache(4 * v.Config.BlobSizeLimit.Int64())
if err != nil {
return nil, fmt.Errorf("creating blob cache: %w", err)
}
defer func() { _ = blobCache.Close() }()
// Per-restore sweep state: every blob_size_limit/100 bytes written,
// scan the cache and delete any blob whose remaining file references
// are all already restored.
sweeper := newRestoreSweeper(v.ctx, repos, blobCache, v.Config.BlobSizeLimit.Int64()/100)
// Calculate total bytes expected for percentage / ETA arithmetic.
// Calculate total bytes for progress bar
var totalBytesExpected int64
for _, file := range files {
totalBytesExpected += file.Size
}
v.UI.Begin("Restoring %s files (%s) to %s.",
v.UI.Count(len(files)),
v.UI.Size(totalBytesExpected),
v.UI.Path(opts.TargetDir))
// Periodic progress output, matching the snapshot create cadence.
startTime := time.Now()
lastStatusTime := startTime
const statusInterval = 15 * time.Second
// Create progress bar if output is a terminal
bar := v.newProgressBar("Restoring", totalBytesExpected)
for i, file := range files {
if v.ctx.Err() != nil {
return nil, v.ctx.Err()
}
if err := v.restoreFile(v.ctx, repos, file, opts.TargetDir, identity, chunkToBlobMap, blobCache, sweeper, result); err != nil {
if err := v.restoreFile(v.ctx, repos, file, opts.TargetDir, identity, chunkToBlobMap, blobCache, result); err != nil {
log.Error("Failed to restore file", "path", file.Path, "error", err)
if !opts.SkipErrors {
return nil, fmt.Errorf("restoring %s: %w (pass --skip-errors to continue past restore failures)", file.Path, err)
}
v.UI.Error("Failed to restore %s: %v. Skipping (--skip-errors).", v.UI.Path(file.Path.String()), err)
result.FilesFailed++
result.FailedFiles = append(result.FailedFiles, file.Path.String())
// Update progress bar even on failure
if bar != nil {
_ = bar.Add64(file.Size)
}
continue
}
// Record the file as restored so the sweeper can free blobs once
// all referencing files are done.
sweeper.fileRestored(file.ID.String())
if time.Since(lastStatusTime) >= statusInterval {
v.printRestoreProgress(i+1, len(files), result.BytesRestored, totalBytesExpected, startTime)
lastStatusTime = time.Now()
// Update progress bar
if bar != nil {
_ = bar.Add64(file.Size)
}
// Structured progress log for --verbose / JSON consumers.
// Progress logging (for non-terminal or structured logs)
if (i+1)%100 == 0 || i+1 == len(files) {
log.Info("Restore progress",
"files", fmt.Sprintf("%d/%d", i+1, len(files)),
@@ -234,49 +218,13 @@ func (v *Vaultik) restoreAllFiles(
}
}
if bar != nil {
_ = bar.Finish()
}
return result, nil
}
// printRestoreProgress emits a periodic restore-phase status line via
// the UI writer, mirroring scanner.printProcessingProgress so the two
// long-running commands have the same on-screen rhythm.
func (v *Vaultik) printRestoreProgress(filesDone, totalFiles int, bytesDone, totalBytes int64, startTime time.Time) {
elapsed := time.Since(startTime)
pct := float64(bytesDone) / float64(totalBytes) * 100
byteRate := float64(bytesDone) / elapsed.Seconds()
fileRate := float64(filesDone) / elapsed.Seconds()
remainingBytes := totalBytes - bytesDone
var eta time.Duration
if byteRate > 0 && remainingBytes > 0 {
eta = time.Duration(float64(remainingBytes)/byteRate) * time.Second
}
if eta > 0 {
v.UI.Progress("Restore: %s/%s files (%s), %s/%s, %s, %.0f files/sec, restore elapsed: %s, restore ETA: %s (est remain %s).",
v.UI.Count(filesDone),
v.UI.Count(totalFiles),
v.UI.Percent(pct),
v.UI.Size(bytesDone),
v.UI.Size(totalBytes),
v.UI.Speed(byteRate),
fileRate,
v.UI.Duration(elapsed),
v.UI.Time(time.Now().Add(eta)),
v.UI.Duration(eta))
return
}
v.UI.Progress("Restore: %s/%s files (%s), %s/%s, %s, %.0f files/sec, restore elapsed: %s.",
v.UI.Count(filesDone),
v.UI.Count(totalFiles),
v.UI.Percent(pct),
v.UI.Size(bytesDone),
v.UI.Size(totalBytes),
v.UI.Speed(byteRate),
fileRate,
v.UI.Duration(elapsed))
}
// handleRestoreVerification runs post-restore verification if requested
func (v *Vaultik) handleRestoreVerification(
repos *database.Repositories,
@@ -289,17 +237,17 @@ func (v *Vaultik) handleRestoreVerification(
}
if result.FilesFailed > 0 {
v.UI.Error("Verification failed: %s files did not match expected checksums.",
v.UI.Count(result.FilesFailed))
v.printfStdout("\nVerification FAILED: %d files did not match expected checksums\n", result.FilesFailed)
for _, path := range result.FailedFiles {
v.UI.Detail("%s", v.UI.Path(path))
v.printfStdout(" - %s\n", path)
}
return fmt.Errorf("%d files failed verification", result.FilesFailed)
}
v.UI.Complete("Verified %s files (%s).",
v.UI.Count(result.FilesVerified),
v.UI.Size(result.BytesVerified))
v.printfStdout("Verified %d files (%s)\n",
result.FilesVerified,
humanize.Bytes(uint64(result.BytesVerified)),
)
return nil
}
@@ -433,7 +381,6 @@ func (v *Vaultik) restoreFile(
identity age.Identity,
chunkToBlobMap map[string]*database.BlobChunk,
blobCache *blobDiskCache,
sweeper *restoreSweeper,
result *RestoreResult,
) error {
// Calculate target path - use full original path under target directory
@@ -456,7 +403,7 @@ func (v *Vaultik) restoreFile(
}
// Handle regular files
return v.restoreRegularFile(ctx, repos, file, targetPath, identity, chunkToBlobMap, blobCache, sweeper, result)
return v.restoreRegularFile(ctx, repos, file, targetPath, identity, chunkToBlobMap, blobCache, result)
}
// restoreSymlink restores a symbolic link
@@ -518,41 +465,23 @@ func (v *Vaultik) restoreRegularFile(
identity age.Identity,
chunkToBlobMap map[string]*database.BlobChunk,
blobCache *blobDiskCache,
sweeper *restoreSweeper,
result *RestoreResult,
) error {
fileStart := time.Now()
// Get file chunks in order
t0 := time.Now()
fileChunks, err := repos.FileChunks.GetByFileID(ctx, file.ID)
fileChunksQueryDur := time.Since(t0)
if err != nil {
return fmt.Errorf("getting file chunks: %w", err)
}
// Create output file
t0 = time.Now()
outFile, err := v.Fs.Create(targetPath)
createDur := time.Since(t0)
if err != nil {
return fmt.Errorf("creating output file: %w", err)
}
defer func() { _ = outFile.Close() }()
// Per-file timing buckets so --debug shows exactly where seconds go.
var (
blobDBLookupDur time.Duration
cacheGetDur time.Duration
downloadDur time.Duration
cachePutDur time.Duration
writeDur time.Duration
sweeperDur time.Duration
downloadCount int
cacheHitCount int
bytesWritten int64
)
// Write chunks in order
var bytesWritten int64
for _, fc := range fileChunks {
// Find which blob contains this chunk
chunkHashStr := fc.ChunkHash.String()
@@ -561,36 +490,25 @@ func (v *Vaultik) restoreRegularFile(
return fmt.Errorf("chunk %s not found in any blob", chunkHashStr[:16])
}
// Get the blob's hash from the database (runs per chunk).
t0 = time.Now()
// Get the blob's hash from the database
blob, err := repos.Blobs.GetByID(ctx, blobChunk.BlobID.String())
blobDBLookupDur += time.Since(t0)
if err != nil {
return fmt.Errorf("getting blob %s: %w", blobChunk.BlobID, err)
}
// Download and decrypt blob if not cached
blobHashStr := blob.Hash.String()
t0 = time.Now()
blobData, ok := blobCache.Get(blobHashStr)
cacheGetDur += time.Since(t0)
if !ok {
t0 = time.Now()
blobData, err = v.downloadBlob(ctx, blobHashStr, blob.CompressedSize, identity)
downloadDur += time.Since(t0)
if err != nil {
return fmt.Errorf("downloading blob %s: %w", blobHashStr[:16], err)
}
t0 = time.Now()
if putErr := blobCache.Put(blobHashStr, blobData); putErr != nil {
log.Debug("Failed to cache blob on disk", "hash", blobHashStr[:16], "error", putErr)
}
cachePutDur += time.Since(t0)
downloadCount++
result.BlobsDownloaded++
result.BytesDownloaded += blob.CompressedSize
} else {
cacheHitCount++
}
// Extract chunk from blob
@@ -601,39 +519,13 @@ func (v *Vaultik) restoreRegularFile(
chunkData := blobData[blobChunk.Offset : blobChunk.Offset+blobChunk.Length]
// Write chunk to output file
t0 = time.Now()
n, err := outFile.Write(chunkData)
writeDur += time.Since(t0)
if err != nil {
return fmt.Errorf("writing chunk: %w", err)
}
bytesWritten += int64(n)
// Tell the sweeper about the bytes we just restored so it can
// run an eviction sweep once the accumulated total crosses its
// threshold (config.BlobSizeLimit/100).
t0 = time.Now()
sweeper.chunkRestored(int64(n))
sweeperDur += time.Since(t0)
}
log.Debug("Restored regular file (timings)",
"path", file.Path,
"chunks", len(fileChunks),
"bytes_written", bytesWritten,
"downloads", downloadCount,
"cache_hits", cacheHitCount,
"ms_total", time.Since(fileStart).Milliseconds(),
"ms_file_chunks_query", fileChunksQueryDur.Milliseconds(),
"ms_create", createDur.Milliseconds(),
"ms_blob_db_lookups", blobDBLookupDur.Milliseconds(),
"ms_cache_gets", cacheGetDur.Milliseconds(),
"ms_cache_puts", cachePutDur.Milliseconds(),
"ms_downloads", downloadDur.Milliseconds(),
"ms_writes", writeDur.Milliseconds(),
"ms_sweeper", sweeperDur.Milliseconds(),
)
// Close file before setting metadata
if err := outFile.Close(); err != nil {
return fmt.Errorf("closing output file: %w", err)
@@ -664,44 +556,23 @@ func (v *Vaultik) restoreRegularFile(
return nil
}
// downloadBlob downloads and decrypts a blob, returning the plaintext.
// Emits a debug log line splitting time spent in the network fetch (Get
// + Stat round-trips) from the streaming decrypt/decompress/read phase
// so --debug shows which side of the wire is the bottleneck.
// downloadBlob downloads and decrypts a blob
func (v *Vaultik) downloadBlob(ctx context.Context, blobHash string, expectedSize int64, identity age.Identity) ([]byte, error) {
start := time.Now()
t0 := time.Now()
rc, err := v.FetchAndDecryptBlob(ctx, blobHash, expectedSize, identity)
fetchSetupDur := time.Since(t0)
if err != nil {
return nil, err
}
t0 = time.Now()
data, err := io.ReadAll(rc)
readAllDur := time.Since(t0)
if err != nil {
_ = rc.Close()
return nil, fmt.Errorf("reading blob data: %w", err)
}
// Close triggers hash verification
t0 = time.Now()
if err := rc.Close(); err != nil {
return nil, err
}
closeDur := time.Since(t0)
log.Debug("Downloaded and decrypted blob (timings)",
"hash", blobHash[:16],
"compressed_bytes", expectedSize,
"plaintext_bytes", len(data),
"ms_total", time.Since(start).Milliseconds(),
"ms_fetch_setup", fetchSetupDur.Milliseconds(),
"ms_read_decrypt_decompress", readAllDur.Milliseconds(),
"ms_close_verify", closeDur.Milliseconds(),
)
return data, nil
}
@@ -735,16 +606,16 @@ func (v *Vaultik) verifyRestoredFiles(
"files", len(regularFiles),
"bytes", humanize.Bytes(uint64(totalBytes)),
)
v.UI.Begin("Verifying %s files (%s).",
v.UI.Count(len(regularFiles)),
v.UI.Size(totalBytes))
v.printfStdout("\nVerifying %d files (%s)...\n",
len(regularFiles),
humanize.Bytes(uint64(totalBytes)),
)
startTime := time.Now()
lastStatusTime := startTime
const statusInterval = 15 * time.Second
// Create progress bar if output is a terminal
bar := v.newProgressBar("Verifying", totalBytes)
var bytesProcessed int64
for i, file := range regularFiles {
// Verify each file
for _, file := range regularFiles {
if ctx.Err() != nil {
return ctx.Err()
}
@@ -759,14 +630,17 @@ func (v *Vaultik) verifyRestoredFiles(
result.FilesVerified++
result.BytesVerified += bytesVerified
}
bytesProcessed += file.Size
if time.Since(lastStatusTime) >= statusInterval {
v.printVerifyProgress(i+1, len(regularFiles), bytesProcessed, totalBytes, startTime)
lastStatusTime = time.Now()
// Update progress bar
if bar != nil {
_ = bar.Add64(file.Size)
}
}
if bar != nil {
_ = bar.Finish()
}
log.Info("Verification complete",
"files_verified", result.FilesVerified,
"bytes_verified", humanize.Bytes(uint64(result.BytesVerified)),
@@ -776,46 +650,6 @@ func (v *Vaultik) verifyRestoredFiles(
return nil
}
// printVerifyProgress emits a periodic verify-phase status line. Same
// shape as the restore progress line so user-facing pacing is uniform
// across the two phases.
func (v *Vaultik) printVerifyProgress(filesDone, totalFiles int, bytesDone, totalBytes int64, startTime time.Time) {
elapsed := time.Since(startTime)
pct := float64(bytesDone) / float64(totalBytes) * 100
byteRate := float64(bytesDone) / elapsed.Seconds()
fileRate := float64(filesDone) / elapsed.Seconds()
remainingBytes := totalBytes - bytesDone
var eta time.Duration
if byteRate > 0 && remainingBytes > 0 {
eta = time.Duration(float64(remainingBytes)/byteRate) * time.Second
}
if eta > 0 {
v.UI.Progress("Verify: %s/%s files (%s), %s/%s, %s, %.0f files/sec, verify elapsed: %s, verify ETA: %s (est remain %s).",
v.UI.Count(filesDone),
v.UI.Count(totalFiles),
v.UI.Percent(pct),
v.UI.Size(bytesDone),
v.UI.Size(totalBytes),
v.UI.Speed(byteRate),
fileRate,
v.UI.Duration(elapsed),
v.UI.Time(time.Now().Add(eta)),
v.UI.Duration(eta))
return
}
v.UI.Progress("Verify: %s/%s files (%s), %s/%s, %s, %.0f files/sec, verify elapsed: %s.",
v.UI.Count(filesDone),
v.UI.Count(totalFiles),
v.UI.Percent(pct),
v.UI.Size(bytesDone),
v.UI.Size(totalBytes),
v.UI.Speed(byteRate),
fileRate,
v.UI.Duration(elapsed))
}
// verifyFile verifies a single restored file by checking its chunk hashes
func (v *Vaultik) verifyFile(
ctx context.Context,
@@ -871,3 +705,38 @@ func (v *Vaultik) verifyFile(
log.Debug("File verified", "path", file.Path, "bytes", bytesVerified, "chunks", len(fileChunks))
return bytesVerified, nil
}
// newProgressBar creates a terminal-aware progress bar with standard options.
// It returns nil if stdout is not a terminal.
func (v *Vaultik) newProgressBar(description string, total int64) *progressbar.ProgressBar {
if !v.isTerminal() {
return nil
}
return progressbar.NewOptions64(
total,
progressbar.OptionSetDescription(description),
progressbar.OptionSetWriter(v.Stderr),
progressbar.OptionShowBytes(true),
progressbar.OptionShowCount(),
progressbar.OptionSetWidth(progressBarWidth),
progressbar.OptionThrottle(progressBarThrottle),
progressbar.OptionOnCompletion(func() {
v.printfStderr("\n")
}),
progressbar.OptionSetRenderBlankState(true),
)
}
// isTerminal returns true if stdout is a terminal.
// It checks whether v.Stdout implements Fd() (i.e. is an *os.File),
// and falls back to false for non-file writers (e.g. in tests).
func (v *Vaultik) isTerminal() bool {
type fder interface {
Fd() uintptr
}
f, ok := v.Stdout.(fder)
if !ok {
return false
}
return term.IsTerminal(int(f.Fd()))
}

118
internal/vaultik/restore_sweeper.go
View File

@@ -1,118 +0,0 @@
package vaultik
import (
"context"
"fmt"
"sneak.berlin/go/vaultik/internal/database"
"sneak.berlin/go/vaultik/internal/log"
)
// restoreSweeper frees cached blobs once all files that reference any of
// their chunks have been restored. It works as follows:
//
// 1. Callers add a file's ID to an in-memory restored set via
// fileRestored once the file is fully written to disk.
// 2. After each chunk is restored, chunkRestored accumulates a running
// byte count.
// 3. When the accumulator crosses a threshold (one hundredth of the
// configured blob size — so a sweep runs about a hundred times per
// blob's worth of restored bytes), the sweeper iterates every key in
// the cache. For each cached blob it asks the DB which files
// reference any chunk in that blob, then compares that list against
// the in-memory restored set. If any referencing file is missing
// from the set the blob is kept; otherwise the cache entry is
// deleted.
//
// All DB reads happen against the snapshot's temporary metadata DB,
// which is local, indexed, and not under contention — the queries are
// cheap and run at most once per blob per sweep interval.
type restoreSweeper struct {
ctx context.Context
repos *database.Repositories
cache *blobDiskCache
threshold int64
bytesAccum int64
restored map[string]struct{}
}
// newRestoreSweeper returns a sweeper that triggers eviction every
// `threshold` bytes restored. Callers should pass blob_size_limit/100.
func newRestoreSweeper(ctx context.Context, repos *database.Repositories, cache *blobDiskCache, threshold int64) *restoreSweeper {
if threshold <= 0 {
threshold = 1
}
return &restoreSweeper{
ctx: ctx,
repos: repos,
cache: cache,
threshold: threshold,
restored: make(map[string]struct{}),
}
}
// fileRestored records a file as fully restored. After this call, any
// blob whose only remaining references come from files in the restored
// set may be evicted on the next sweep.
func (s *restoreSweeper) fileRestored(fileID string) {
s.restored[fileID] = struct{}{}
}
// chunkRestored accounts n bytes against the sweep threshold and runs a
// sweep if the threshold has been crossed since the last sweep.
func (s *restoreSweeper) chunkRestored(n int64) {
s.bytesAccum += n
if s.bytesAccum < s.threshold {
return
}
s.bytesAccum = 0
s.sweep()
}
// sweep deletes any cached blob whose chunks are no longer referenced
// by an unrestored file. Per-blob DB failures are logged and the blob
// is kept — we'd rather hold a blob longer than risk a re-download.
func (s *restoreSweeper) sweep() {
for _, blobHash := range s.cache.Keys() {
needed, err := s.blobStillNeeded(blobHash)
if err != nil {
log.Debug("sweeper referencing-files query failed", "blob_hash", blobHash[:16], "error", err)
continue
}
if !needed {
s.cache.Delete(blobHash)
}
}
}
// blobStillNeeded returns true if any file that references a chunk in
// this blob has not yet been restored. On any error the function
// returns true — keeping the blob is always the safe answer because we
// can't prove we're done with it.
func (s *restoreSweeper) blobStillNeeded(blobHash string) (bool, error) {
rows, err := s.repos.DB().Conn().QueryContext(s.ctx, `
SELECT DISTINCT fc.file_id
FROM file_chunks fc
JOIN blob_chunks bc ON bc.chunk_hash = fc.chunk_hash
JOIN blobs b ON b.id = bc.blob_id
WHERE b.blob_hash = ?
`, blobHash)
if err != nil {
return true, fmt.Errorf("querying referencing files: %w", err)
}
defer func() { _ = rows.Close() }()
for rows.Next() {
var fileID string
if err := rows.Scan(&fileID); err != nil {
return true, fmt.Errorf("scanning file_id: %w", err)
}
if _, ok := s.restored[fileID]; !ok {
return true, nil
}
}
if err := rows.Err(); err != nil {
return true, err
}
return false, nil
}

248
internal/vaultik/restore_sweeper_integration_test.go
View File

@@ -1,248 +0,0 @@
package vaultik_test
import (
"context"
"fmt"
"io"
"math/rand"
"os"
"path/filepath"
"strings"
"sync"
"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"
)
// TestRestoreSweeperEvictsBlobs exercises the reference-counted blob
// disk cache eviction during restore.
//
// The scenario: 30 unique 1 MB random files plus 10 duplicates of those
// (40 files total, 30 MB of unique content) get backed up with a 10 MB
// blob_size_limit. After backup the snapshot's encrypted blobs are
// restored through Vaultik.Restore, and per-key Get counts on the
// storage layer are recorded. Each blob in the snapshot MUST be
// downloaded exactly once — re-downloads would mean the sweeper either
// evicted a blob that was still needed (LRU regression) or that the
// cache held nothing at all (broken cache).
//
// The duplicates ensure deduplicated files share blobs with their
// originals; the sweeper must keep each blob alive until BOTH the
// original AND every duplicate referencing its chunks have been
// restored.
func TestRestoreSweeperEvictsBlobs(t *testing.T) {
log.Initialize(log.Config{})
fs := afero.NewOsFs()
tempDir, err := os.MkdirTemp("", "vaultik-sweeper-")
require.NoError(t, err)
defer func() { _ = os.RemoveAll(tempDir) }()
dataDir := filepath.Join(tempDir, "source")
storeDir := filepath.Join(tempDir, "remote")
restoreDir := filepath.Join(tempDir, "restored")
dbPath := filepath.Join(tempDir, "index.sqlite")
require.NoError(t, fs.MkdirAll(dataDir, 0o755))
// Generate 30 unique 1 MB random files. The PRNG seed is fixed so
// failures are reproducible; the entropy is what matters here — the
// FastCDC chunker needs realistic-looking data to pick chunk
// boundaries naturally.
const (
uniqueFiles = 30
duplicateFiles = 10
fileSize = 1 * 1024 * 1024
)
rng := rand.New(rand.NewSource(42))
type sourceFile struct {
path string
data []byte
}
uniques := make([]sourceFile, 0, uniqueFiles)
expected := make(map[string][]byte, uniqueFiles+duplicateFiles)
for i := 0; i < uniqueFiles; i++ {
data := make([]byte, fileSize)
_, err := rng.Read(data)
require.NoError(t, err)
path := filepath.Join(dataDir, fmt.Sprintf("unique-%02d.bin", i))
require.NoError(t, afero.WriteFile(fs, path, data, 0o644))
uniques = append(uniques, sourceFile{path: path, data: data})
expected[path] = data
}
// Pick 10 of the originals and copy each to a fresh path so the
// chunker dedups them against the originals' blobs.
for i, idx := range rng.Perm(uniqueFiles)[:duplicateFiles] {
src := uniques[idx]
dstPath := filepath.Join(dataDir, fmt.Sprintf("dup-%02d.bin", i))
require.NoError(t, afero.WriteFile(fs, dstPath, src.data, 0o644))
expected[dstPath] = src.data
}
chunkSize := int64(64 * 1024)
maxBlobSize := int64(10 * 1024 * 1024)
storer, err := storage.NewFileStorer(storeDir)
require.NoError(t, err)
agePublicKey := "age1ezrjmfpwsc95svdg0y54mums3zevgzu0x0ecq2f7tp8a05gl0sjq9q9wjg"
ageSecretKey := "AGE-SECRET-KEY-19CR5YSFW59HM4TLD6GXVEDMZFTVVF7PPHKUT68TXSFPK7APHXA2QS2NJA5"
cfg := &config.Config{
AgeRecipients: []string{agePublicKey},
AgeSecretKey: ageSecretKey,
CompressionLevel: 3,
Hostname: "test-host",
BlobSizeLimit: config.Size(maxBlobSize),
}
ctx := context.Background()
db, err := database.New(ctx, dbPath)
require.NoError(t, err)
defer func() { _ = db.Close() }()
repos := database.NewRepositories(db)
sm := snapshot.NewSnapshotManager(snapshot.SnapshotManagerParams{
Repos: repos,
Storage: storer,
Config: cfg,
})
sm.SetFilesystem(fs)
scanner := snapshot.NewScanner(snapshot.ScannerConfig{
FS: fs,
Storage: storer,
ChunkSize: chunkSize,
MaxBlobSize: maxBlobSize,
CompressionLevel: cfg.CompressionLevel,
AgeRecipients: cfg.AgeRecipients,
Repositories: repos,
})
snapshotID, err := sm.CreateSnapshotWithName(ctx, cfg.Hostname, "sweeper", "test-version", "test-git")
require.NoError(t, err)
scanResult, err := scanner.Scan(ctx, dataDir, snapshotID)
require.NoError(t, err)
require.Equal(t, uniqueFiles+duplicateFiles, scanResult.FilesScanned)
require.Greater(t, scanResult.BlobsCreated, 1, "30 MB of unique data at 10 MB blob size should yield multiple blobs")
require.NoError(t, sm.CompleteSnapshot(ctx, snapshotID))
require.NoError(t, sm.ExportSnapshotMetadata(ctx, dbPath, snapshotID))
// Count blobs actually present on disk; this is the ground-truth
// figure each blob's GET count must equal exactly once.
blobCount := countBlobsOnDisk(t, storeDir)
require.Greater(t, blobCount, 1, "expected more than one blob")
t.Logf("backup produced %d blobs from %d files (%d unique + %d duplicates)",
blobCount, uniqueFiles+duplicateFiles, uniqueFiles, duplicateFiles)
// Force restore to operate without the source-side index, exactly
// as a real restore on a fresh machine would.
require.NoError(t, db.Close())
counter := newCountingStorer(storer)
restoreVaultik := &vaultik.Vaultik{
Config: cfg,
Storage: counter,
Fs: fs,
Stdout: io.Discard,
Stderr: io.Discard,
UI: ui.NewWithColor(io.Discard, false),
}
restoreVaultik.SetContext(ctx)
require.NoError(t, restoreVaultik.Restore(&vaultik.RestoreOptions{
SnapshotID: snapshotID,
TargetDir: restoreDir,
}))
// Verify every restored file byte-matches its source.
for origPath, want := range expected {
restoredPath := filepath.Join(restoreDir, origPath)
got, err := afero.ReadFile(fs, restoredPath)
require.NoErrorf(t, err, "restored file missing: %s", restoredPath)
require.Equalf(t, want, got, "byte mismatch for %s", origPath)
}
// Each blob must have been downloaded exactly once. >1 means the
// sweeper evicted a still-needed blob; 0 means the cache silently
// stopped being consulted.
blobDownloads := 0
for key, count := range counter.snapshot() {
if !strings.HasPrefix(key, "blobs/") {
continue
}
assert.Equalf(t, 1, count,
"blob %s should have been downloaded exactly once during restore, got %d", key, count)
blobDownloads++
}
assert.Equal(t, blobCount, blobDownloads,
"every blob on disk should have been fetched exactly once during restore")
t.Logf("restore downloaded %d blobs, each exactly once", blobDownloads)
}
// countingStorer wraps a Storer and records the number of Get calls per
// key. Used to verify that the restore-side blob cache + sweeper avoid
// re-downloading blobs that are evicted while still needed.
type countingStorer struct {
storage.Storer
mu sync.Mutex
counts map[string]int
}
func newCountingStorer(inner storage.Storer) *countingStorer {
return &countingStorer{Storer: inner, counts: make(map[string]int)}
}
func (c *countingStorer) Get(ctx context.Context, key string) (io.ReadCloser, error) {
c.mu.Lock()
c.counts[key]++
c.mu.Unlock()
return c.Storer.Get(ctx, key)
}
func (c *countingStorer) snapshot() map[string]int {
c.mu.Lock()
defer c.mu.Unlock()
out := make(map[string]int, len(c.counts))
for k, v := range c.counts {
out[k] = v
}
return out
}
// countBlobsOnDisk walks the blobs/ tree of a FileStorer-backed store
// and returns the total number of blob files. Used to ground-truth the
// expected number of restore-time downloads.
func countBlobsOnDisk(t *testing.T, storeDir string) int {
t.Helper()
count := 0
root := filepath.Join(storeDir, "blobs")
err := filepath.Walk(root, func(_ string, info os.FileInfo, err error) error {
if err != nil {
return err
}
if !info.IsDir() {
count++
}
return nil
})
require.NoError(t, err)
return count
}

504
internal/vaultik/snapshot.go
View File

@@ -8,25 +8,23 @@ import (
"regexp"
"sort"
"strings"
"sync"
"text/tabwriter"
"time"
"git.eeqj.de/sneak/vaultik/internal/database"
"git.eeqj.de/sneak/vaultik/internal/log"
"git.eeqj.de/sneak/vaultik/internal/snapshot"
"git.eeqj.de/sneak/vaultik/internal/types"
"github.com/dustin/go-humanize"
"golang.org/x/sync/errgroup"
"sneak.berlin/go/vaultik/internal/database"
"sneak.berlin/go/vaultik/internal/log"
"sneak.berlin/go/vaultik/internal/snapshot"
"sneak.berlin/go/vaultik/internal/types"
)
// SnapshotCreateOptions contains options for the snapshot create command
type SnapshotCreateOptions struct {
Cron bool
Prune bool
KeepNewerThan string // With --prune: keep snapshots newer than this duration (e.g. "4w"); default: keep only latest
SkipErrors bool // Skip file read errors (log them loudly but continue)
Snapshots []string // Optional list of snapshot names to process (empty = all)
Daemon bool
Cron bool
Prune bool
SkipErrors bool // Skip file read errors (log them loudly but continue)
Snapshots []string // Optional list of snapshot names to process (empty = all)
}
// CreateSnapshot executes the snapshot creation operation
@@ -57,6 +55,12 @@ func (v *Vaultik) CreateSnapshot(opts *SnapshotCreateOptions) error {
return fmt.Errorf("prune database: %w", err)
}
if opts.Daemon {
log.Info("Running in daemon mode")
// TODO: Implement daemon mode with inotify
return fmt.Errorf("daemon mode not yet implemented")
}
// Determine which snapshots to process
snapshotNames := opts.Snapshots
if len(snapshotNames) == 0 {
@@ -83,50 +87,25 @@ func (v *Vaultik) CreateSnapshot(opts *SnapshotCreateOptions) error {
// Print overall summary if multiple snapshots
if len(snapshotNames) > 1 {
v.UI.Complete("All %d snapshots completed in %s.", len(snapshotNames), v.UI.Duration(time.Since(overallStartTime)))
v.printfStdout("\nAll %d snapshots completed in %s\n", len(snapshotNames), time.Since(overallStartTime).Round(time.Second))
}
// Prune old snapshots and unreferenced blobs if --prune was specified
if opts.Prune {
if err := v.runPostBackupPrune(snapshotNames, opts.KeepNewerThan); err != nil {
return fmt.Errorf("post-backup prune: %w", err)
log.Info("Pruning enabled - deleting old snapshots and unreferenced blobs")
v.printlnStdout("\nPruning old snapshots (keeping latest)...")
if err := v.PurgeSnapshots(true, "", true); err != nil {
return fmt.Errorf("prune: purging old snapshots: %w", err)
}
}
if v.UI.WarningCount() > 0 {
v.UI.Complete("Finished (with %d warnings).", v.UI.WarningCount())
} else {
v.UI.Complete("Finished successfully.")
}
v.printlnStdout("Pruning unreferenced blobs...")
return nil
}
if err := v.PruneBlobs(&PruneOptions{Force: true}); err != nil {
return fmt.Errorf("prune: removing unreferenced blobs: %w", err)
}
// runPostBackupPrune drops older snapshots of the given names and removes
// orphan blobs from remote storage. If keepNewerThan is set (e.g. "4w"),
// snapshots newer than that duration are kept. Otherwise only the latest
// snapshot of each name is kept.
func (v *Vaultik) runPostBackupPrune(snapshotNames []string, keepNewerThan string) error {
log.Info("Running post-backup prune", "snapshots", snapshotNames, "keep_newer_than", keepNewerThan)
v.UI.Begin("Running post-backup prune.")
purgeOpts := &SnapshotPurgeOptions{
Force: true,
Names: snapshotNames,
Quiet: true,
}
if keepNewerThan != "" {
purgeOpts.OlderThan = keepNewerThan
} else {
purgeOpts.KeepLatest = true
}
if err := v.PurgeSnapshotsWithOptions(purgeOpts); err != nil {
return fmt.Errorf("purging old snapshots: %w", err)
}
if err := v.PruneBlobs(&PruneOptions{Force: true}); err != nil {
return fmt.Errorf("pruning orphaned blobs: %w", err)
log.Info("Pruning complete")
}
return nil
@@ -152,7 +131,7 @@ func (v *Vaultik) createNamedSnapshot(opts *SnapshotCreateOptions, hostname, sna
snapshotStartTime := time.Now()
if total > 1 {
v.UI.Info("Snapshot %d/%d: %s.", idx, total, snapName)
v.printfStdout("\n=== Snapshot %d/%d: %s ===\n", idx, total, snapName)
}
resolvedDirs, err := v.resolveSnapshotPaths(snapName)
@@ -162,7 +141,6 @@ func (v *Vaultik) createNamedSnapshot(opts *SnapshotCreateOptions, hostname, sna
scanner := v.ScannerFactory(snapshot.ScannerParams{
EnableProgress: !opts.Cron,
UI: v.UI,
Fs: v.Fs,
Exclude: v.Config.GetExcludes(snapName),
SkipErrors: opts.SkipErrors,
@@ -173,7 +151,7 @@ func (v *Vaultik) createNamedSnapshot(opts *SnapshotCreateOptions, hostname, sna
return fmt.Errorf("creating snapshot: %w", err)
}
log.Info("Beginning snapshot", "snapshot_id", snapshotID, "name", snapName)
v.UI.Begin("Creating snapshot %s.", v.UI.Snapshot(snapshotID))
v.printfStdout("Beginning snapshot: %s\n", snapshotID)
stats, err := v.scanAllDirectories(scanner, resolvedDirs, snapshotID)
if err != nil {
@@ -237,7 +215,7 @@ func (v *Vaultik) scanAllDirectories(scanner *snapshot.Scanner, resolvedDirs []s
}
log.Info("Scanning directory", "path", dir)
v.UI.Begin("Enumerating snapshot source files in %s (%d of %d).", v.UI.Path(dir), i+1, len(resolvedDirs))
v.printfStdout("Beginning directory scan (%d/%d): %s\n", i+1, len(resolvedDirs), dir)
result, err := scanner.Scan(v.ctx, dir, snapshotID)
if err != nil {
return nil, fmt.Errorf("failed to scan %s: %w", dir, err)
@@ -306,13 +284,23 @@ func (v *Vaultik) finalizeSnapshotMetadata(snapshotID string, stats *snapshotSta
return nil
}
// uploadSpeed returns the average network upload rate as a colorized
// bits/sec string, or "N/A" when there's no usable data.
func (v *Vaultik) uploadSpeed(bytesUploaded int64, duration time.Duration) string {
// formatUploadSpeed formats bytes uploaded and duration into a human-readable speed string
func formatUploadSpeed(bytesUploaded int64, duration time.Duration) string {
if bytesUploaded <= 0 || duration <= 0 {
return v.UI.Speed(0)
return "N/A"
}
bytesPerSec := float64(bytesUploaded) / duration.Seconds()
bitsPerSec := bytesPerSec * 8
switch {
case bitsPerSec >= 1e9:
return fmt.Sprintf("%.1f Gbit/s", bitsPerSec/1e9)
case bitsPerSec >= 1e6:
return fmt.Sprintf("%.0f Mbit/s", bitsPerSec/1e6)
case bitsPerSec >= 1e3:
return fmt.Sprintf("%.0f Kbit/s", bitsPerSec/1e3)
default:
return fmt.Sprintf("%.0f bit/s", bitsPerSec)
}
return v.UI.Speed(float64(bytesUploaded) / duration.Seconds())
}
// printSnapshotSummary prints the comprehensive snapshot completion summary
@@ -331,36 +319,35 @@ func (v *Vaultik) printSnapshotSummary(snapshotID string, startTime time.Time, s
compressionRatio = 1.0
}
v.UI.Complete("Created snapshot %s.", v.UI.Snapshot(snapshotID))
filesMsg := fmt.Sprintf("Files: %s examined, %s backed up, %s unchanged",
v.UI.Count(stats.totalFiles),
v.UI.Count(totalFilesChanged),
v.UI.Count(stats.totalFilesSkipped))
v.printfStdout("=== Snapshot Complete ===\n")
v.printfStdout("ID: %s\n", snapshotID)
v.printfStdout("Files: %s examined, %s to process, %s unchanged",
formatNumber(stats.totalFiles),
formatNumber(totalFilesChanged),
formatNumber(stats.totalFilesSkipped))
if stats.totalFilesDeleted > 0 {
filesMsg += fmt.Sprintf(", %s deleted", v.UI.Count(stats.totalFilesDeleted))
v.printfStdout(", %s deleted", formatNumber(stats.totalFilesDeleted))
}
v.UI.Detail("%s.", filesMsg)
dataMsg := fmt.Sprintf("Data: %s total (%s backed up)",
v.UI.Size(totalBytesAll),
v.UI.Size(stats.totalBytes))
v.printlnStdout()
v.printfStdout("Data: %s total (%s to process)",
humanize.Bytes(uint64(totalBytesAll)),
humanize.Bytes(uint64(stats.totalBytes)))
if stats.totalBytesDeleted > 0 {
dataMsg += fmt.Sprintf(", %s deleted", v.UI.Size(stats.totalBytesDeleted))
v.printfStdout(", %s deleted", humanize.Bytes(uint64(stats.totalBytesDeleted)))
}
v.UI.Detail("%s.", dataMsg)
v.printlnStdout()
if stats.totalBlobsUploaded > 0 {
v.UI.Detail("Storage: %s compressed from %s (%.2fx ratio).",
v.UI.Size(totalBlobSizeCompressed),
v.UI.Size(totalBlobSizeUncompressed),
v.printfStdout("Storage: %s compressed from %s (%.2fx)\n",
humanize.Bytes(uint64(totalBlobSizeCompressed)),
humanize.Bytes(uint64(totalBlobSizeUncompressed)),
compressionRatio)
v.UI.Detail("Upload: %d blobs, %s in %s (%s).",
v.printfStdout("Upload: %d blobs, %s in %s (%s)\n",
stats.totalBlobsUploaded,
v.UI.Size(stats.totalBytesUploaded),
v.UI.Duration(stats.uploadDuration),
v.uploadSpeed(stats.totalBytesUploaded, stats.uploadDuration))
humanize.Bytes(uint64(stats.totalBytesUploaded)),
formatDuration(stats.uploadDuration),
formatUploadSpeed(stats.totalBytesUploaded, stats.uploadDuration))
}
v.UI.Detail("Snapshot create duration: %s.", v.UI.Duration(snapshotDuration))
v.printfStdout("Duration: %s\n", formatDuration(snapshotDuration))
}
// getSnapshotBlobSizes returns total compressed and uncompressed blob sizes for a snapshot
@@ -407,26 +394,7 @@ func (v *Vaultik) ListSnapshots(jsonOutput bool) error {
return encoder.Encode(snapshots)
}
if err := v.printSnapshotTable(snapshots); err != nil {
return err
}
// Warn about local snapshots that don't exist in remote storage.
var stale []string
for id := range localSnapshotMap {
if !remoteSnapshots[id] {
stale = append(stale, id)
}
}
if len(stale) > 0 {
v.UI.Warning("%d local snapshot record(s) not found in backup destination store:", len(stale))
for _, id := range stale {
v.UI.Info("%s", v.UI.Snapshot(id))
}
v.UI.Info("Run 'vaultik snapshot cleanup' to remove stale local records.")
}
return nil
return v.printSnapshotTable(snapshots)
}
// listRemoteSnapshotIDs returns a set of snapshot IDs found in remote storage
@@ -470,9 +438,6 @@ func (v *Vaultik) reconcileLocalWithRemote(remoteSnapshots map[string]bool) (map
func (v *Vaultik) buildSnapshotInfoList(remoteSnapshots map[string]bool, localSnapshotMap map[string]*database.Snapshot) ([]SnapshotInfo, error) {
snapshots := make([]SnapshotInfo, 0, len(remoteSnapshots))
// remoteOnly collects snapshot IDs that need a manifest download.
var remoteOnly []string
for snapshotID := range remoteSnapshots {
if localSnap, exists := localSnapshotMap[snapshotID]; exists && localSnap.CompletedAt != nil {
totalSize, err := v.Repositories.Snapshots.GetSnapshotTotalCompressedSize(v.ctx, snapshotID)
@@ -481,23 +446,10 @@ func (v *Vaultik) buildSnapshotInfoList(remoteSnapshots map[string]bool, localSn
totalSize = localSnap.BlobSize
}
uncompressedSize, err := v.Repositories.Snapshots.GetSnapshotUncompressedChunkSize(v.ctx, snapshotID)
if err != nil {
log.Warn("Failed to get uncompressed chunk size", "id", snapshotID, "error", err)
}
newChunkSize, err := v.Repositories.Snapshots.GetSnapshotNewChunkSize(v.ctx, snapshotID)
if err != nil {
log.Warn("Failed to get new chunk size", "id", snapshotID, "error", err)
}
snapshots = append(snapshots, SnapshotInfo{
ID: localSnap.ID,
Timestamp: localSnap.StartedAt,
CompressedSize: totalSize,
UncompressedSize: uncompressedSize,
NewChunkSize: newChunkSize,
LocallyTracked: true,
ID: localSnap.ID,
Timestamp: localSnap.StartedAt,
CompressedSize: totalSize,
})
} else {
timestamp, err := parseSnapshotTimestamp(snapshotID)
@@ -506,74 +458,16 @@ func (v *Vaultik) buildSnapshotInfoList(remoteSnapshots map[string]bool, localSn
continue
}
// Pre-add with zero size; will be filled by concurrent downloads.
totalSize, err := v.getManifestSize(snapshotID)
if err != nil {
return nil, fmt.Errorf("failed to get manifest size for %s: %w", snapshotID, err)
}
snapshots = append(snapshots, SnapshotInfo{
ID: types.SnapshotID(snapshotID),
Timestamp: timestamp,
CompressedSize: 0,
LocallyTracked: false,
CompressedSize: totalSize,
})
remoteOnly = append(remoteOnly, snapshotID)
}
}
// Download manifests concurrently for remote-only snapshots.
if len(remoteOnly) > 0 {
// maxConcurrentManifestDownloads bounds parallel manifest fetches to
// avoid overwhelming the S3 endpoint while still being much faster
// than serial downloads.
const maxConcurrentManifestDownloads = 10
type manifestResult struct {
snapshotID string
size int64
}
var (
mu sync.Mutex
results []manifestResult
)
g, gctx := errgroup.WithContext(v.ctx)
g.SetLimit(maxConcurrentManifestDownloads)
for _, sid := range remoteOnly {
g.Go(func() error {
manifestPath := fmt.Sprintf("metadata/%s/manifest.json.zst", sid)
reader, err := v.Storage.Get(gctx, manifestPath)
if err != nil {
return fmt.Errorf("downloading manifest for %s: %w", sid, err)
}
defer func() { _ = reader.Close() }()
manifest, err := snapshot.DecodeManifest(reader)
if err != nil {
return fmt.Errorf("decoding manifest for %s: %w", sid, err)
}
mu.Lock()
results = append(results, manifestResult{
snapshotID: sid,
size: manifest.TotalCompressedSize,
})
mu.Unlock()
return nil
})
}
if err := g.Wait(); err != nil {
return nil, fmt.Errorf("fetching manifest sizes: %w", err)
}
// Build a lookup from results and patch the pre-added entries.
sizeMap := make(map[string]int64, len(results))
for _, r := range results {
sizeMap[r.snapshotID] = r.size
}
for i := range snapshots {
if sz, ok := sizeMap[string(snapshots[i].ID)]; ok {
snapshots[i].CompressedSize = sz
}
}
}
@@ -607,27 +501,18 @@ func (v *Vaultik) printSnapshotTable(snapshots []SnapshotInfo) error {
if _, err := fmt.Fprintln(w, "REMOTE SNAPSHOTS:"); err != nil {
return err
}
if _, err := fmt.Fprintln(w, "SNAPSHOT ID\tTIMESTAMP\tCOMPRESSED SIZE\tUNCOMPRESSED SIZE\tNEW CHUNK SIZE"); err != nil {
if _, err := fmt.Fprintln(w, "SNAPSHOT ID\tTIMESTAMP\tCOMPRESSED SIZE"); err != nil {
return err
}
if _, err := fmt.Fprintln(w, "───────────\t─────────\t───────────────\t─────────────────\t──────────────"); err != nil {
if _, err := fmt.Fprintln(w, "───────────\t─────────\t───────────────"); err != nil {
return err
}
const remoteOnlyCell = "<remote only>"
for _, snap := range snapshots {
uncompressed := remoteOnlyCell
newChunks := remoteOnlyCell
if snap.LocallyTracked {
uncompressed = formatBytes(snap.UncompressedSize)
newChunks = formatBytes(snap.NewChunkSize)
}
if _, err := fmt.Fprintf(w, "%s\t%s\t%s\t%s\t%s\n",
if _, err := fmt.Fprintf(w, "%s\t%s\t%s\n",
snap.ID,
snap.Timestamp.Format("2006-01-02 15:04:05"),
formatBytes(snap.CompressedSize),
uncompressed,
newChunks); err != nil {
formatBytes(snap.CompressedSize)); err != nil {
return err
}
}
@@ -635,20 +520,8 @@ func (v *Vaultik) printSnapshotTable(snapshots []SnapshotInfo) error {
return w.Flush()
}
// SnapshotPurgeOptions contains options for the snapshot purge command.
type SnapshotPurgeOptions struct {
KeepLatest bool // Keep only the most recent snapshot per name
OlderThan string // Drop snapshots older than this duration (e.g. "30d", "6m", "1y")
Force bool // Skip confirmation prompt
Names []string // If non-empty, only operate on snapshots with one of these names
Quiet bool // Suppress informational output (used by --prune flag)
}
// PurgeSnapshotsWithOptions removes old snapshots based on criteria.
// Retention is per-snapshot-name: KeepLatest keeps the latest of EACH configured
// snapshot name, not the latest globally. This prevents `home` and `system`
// snapshots from cannibalizing each other.
func (v *Vaultik) PurgeSnapshotsWithOptions(opts *SnapshotPurgeOptions) error {
// PurgeSnapshots removes old snapshots based on criteria
func (v *Vaultik) PurgeSnapshots(keepLatest bool, olderThan string, force bool) error {
// Sync with remote first
if err := v.syncWithRemote(); err != nil {
return fmt.Errorf("syncing with remote: %w", err)
@@ -660,28 +533,16 @@ func (v *Vaultik) PurgeSnapshotsWithOptions(opts *SnapshotPurgeOptions) error {
return fmt.Errorf("listing snapshots: %w", err)
}
// Build name filter set if --snapshot was specified.
nameFilter := make(map[string]struct{}, len(opts.Names))
for _, n := range opts.Names {
nameFilter[n] = struct{}{}
}
// Collect completed snapshots, applying the name filter.
// Convert to SnapshotInfo format, only including completed snapshots
snapshots := make([]SnapshotInfo, 0, len(dbSnapshots))
for _, s := range dbSnapshots {
if s.CompletedAt == nil {
continue
if s.CompletedAt != nil {
snapshots = append(snapshots, SnapshotInfo{
ID: s.ID,
Timestamp: s.StartedAt,
CompressedSize: s.BlobSize,
})
}
if len(nameFilter) > 0 {
if _, ok := nameFilter[parseSnapshotName(s.ID.String())]; !ok {
continue
}
}
snapshots = append(snapshots, SnapshotInfo{
ID: s.ID,
Timestamp: s.StartedAt,
CompressedSize: s.BlobSize,
})
}
// Sort by timestamp (newest first)
@@ -689,54 +550,58 @@ func (v *Vaultik) PurgeSnapshotsWithOptions(opts *SnapshotPurgeOptions) error {
return snapshots[i].Timestamp.After(snapshots[j].Timestamp)
})
var toDelete []SnapshotInfo
toDelete, err := v.collectSnapshotsToPurge(snapshots, keepLatest, olderThan)
if err != nil {
return err
}
if opts.KeepLatest {
// Keep the latest snapshot per snapshot name. Snapshots are sorted
// newest-first, so the first occurrence of each name is kept.
seen := make(map[string]bool)
for _, snap := range snapshots {
name := parseSnapshotName(snap.ID.String())
if seen[name] {
toDelete = append(toDelete, snap)
continue
}
seen[name] = true
if len(toDelete) == 0 {
v.printlnStdout("No snapshots to delete")
return nil
}
return v.confirmAndExecutePurge(toDelete, force)
}
// collectSnapshotsToPurge determines which snapshots to delete based on retention criteria
func (v *Vaultik) collectSnapshotsToPurge(snapshots []SnapshotInfo, keepLatest bool, olderThan string) ([]SnapshotInfo, error) {
if keepLatest {
// Keep only the most recent snapshot
if len(snapshots) > 1 {
return snapshots[1:], nil
}
} else if opts.OlderThan != "" {
duration, err := parseDuration(opts.OlderThan)
return nil, nil
}
if olderThan != "" {
// Parse duration
duration, err := parseDuration(olderThan)
if err != nil {
return fmt.Errorf("invalid duration: %w", err)
return nil, fmt.Errorf("invalid duration: %w", err)
}
cutoff := time.Now().UTC().Add(-duration)
var toDelete []SnapshotInfo
for _, snap := range snapshots {
if snap.Timestamp.Before(cutoff) {
toDelete = append(toDelete, snap)
}
}
return toDelete, nil
}
if len(toDelete) == 0 {
if !opts.Quiet {
v.printlnStdout("No snapshots to delete")
}
return nil
}
return v.confirmAndExecutePurge(toDelete, opts.Force, opts.Quiet)
return nil, nil
}
// confirmAndExecutePurge shows deletion candidates, confirms with user, and deletes snapshots
func (v *Vaultik) confirmAndExecutePurge(toDelete []SnapshotInfo, force, quiet bool) error {
if !quiet {
v.printfStdout("The following snapshots will be deleted:\n\n")
for _, snap := range toDelete {
v.printfStdout(" %s (%s, %s)\n",
snap.ID,
snap.Timestamp.Format("2006-01-02 15:04:05"),
formatBytes(snap.CompressedSize))
}
func (v *Vaultik) confirmAndExecutePurge(toDelete []SnapshotInfo, force bool) error {
// Show what will be deleted
v.printfStdout("The following snapshots will be deleted:\n\n")
for _, snap := range toDelete {
v.printfStdout(" %s (%s, %s)\n",
snap.ID,
snap.Timestamp.Format("2006-01-02 15:04:05"),
formatBytes(snap.CompressedSize))
}
// Confirm unless --force is used
@@ -752,7 +617,7 @@ func (v *Vaultik) confirmAndExecutePurge(toDelete []SnapshotInfo, force, quiet b
v.printlnStdout("Cancelled")
return nil
}
} else if !quiet {
} else {
v.printfStdout("\nDeleting %d snapshot(s) (--force specified)\n", len(toDelete))
}
@@ -768,10 +633,10 @@ func (v *Vaultik) confirmAndExecutePurge(toDelete []SnapshotInfo, force, quiet b
}
}
if !quiet {
v.printfStdout("Deleted %d snapshot(s)\n", len(toDelete))
v.printlnStdout("\nNote: Run 'vaultik prune' to clean up unreferenced blobs.")
}
v.printfStdout("Deleted %d snapshot(s)\n", len(toDelete))
// Note: Run 'vaultik prune' separately to clean up unreferenced blobs
v.printlnStdout("\nNote: Run 'vaultik prune' to clean up unreferenced blobs.")
return nil
}
@@ -785,17 +650,15 @@ func (v *Vaultik) VerifySnapshot(snapshotID string, deep bool) error {
return v.VerifySnapshotWithOptions(snapshotID, opts)
}
// VerifySnapshotWithOptions checks snapshot integrity with full options.
// Deep verification is delegated to RunDeepVerify so this function only
// implements the shallow (existence-only) path.
// VerifySnapshotWithOptions checks snapshot integrity with full options
func (v *Vaultik) VerifySnapshotWithOptions(snapshotID string, opts *VerifyOptions) error {
if opts.Deep {
return v.RunDeepVerify(snapshotID, opts)
}
result := &VerifyResult{
SnapshotID: snapshotID,
Mode: "shallow",
}
if opts.Deep {
result.Mode = "deep"
}
v.printVerifyHeader(snapshotID, opts)
@@ -833,12 +696,22 @@ func (v *Vaultik) VerifySnapshotWithOptions(snapshotID string, opts *VerifyOptio
return v.formatVerifyResult(result, manifest, opts)
}
// printVerifyHeader prints the snapshot ID and parsed timestamp for verification output.
// Snapshot ID format: hostname[_name]_<RFC3339>
// printVerifyHeader prints the snapshot ID and parsed timestamp for verification output
func (v *Vaultik) printVerifyHeader(snapshotID string, opts *VerifyOptions) {
// Parse snapshot ID to extract timestamp
parts := strings.Split(snapshotID, "-")
var snapshotTime time.Time
if t, err := parseSnapshotTimestamp(snapshotID); err == nil {
snapshotTime = t
if len(parts) >= 3 {
// Format: hostname-YYYYMMDD-HHMMSSZ
dateStr := parts[len(parts)-2]
timeStr := parts[len(parts)-1]
if len(dateStr) == 8 && len(timeStr) == 7 && strings.HasSuffix(timeStr, "Z") {
timeStr = timeStr[:6] // Remove Z
timestamp, err := time.Parse("20060102150405", dateStr+timeStr)
if err == nil {
snapshotTime = timestamp
}
}
}
if !opts.JSON {
@@ -855,7 +728,7 @@ func (v *Vaultik) verifyManifestBlobsExist(manifest *snapshot.Manifest, opts *Ve
for _, blob := range manifest.Blobs {
blobPath := fmt.Sprintf("blobs/%s/%s/%s", blob.Hash[:2], blob.Hash[2:4], blob.Hash)
// Shallow: just check existence (deep verification is handled by RunDeepVerify)
// Just check existence (deep verification is handled by RunDeepVerify)
_, err := v.Storage.Stat(v.ctx, blobPath)
if err != nil {
if !opts.JSON {
@@ -913,43 +786,25 @@ func (v *Vaultik) outputVerifyJSON(result *VerifyResult) error {
return nil
}
// CleanupLocalSnapshots removes local snapshot records that have no
// corresponding metadata in remote storage. These are typically left
// behind by incomplete or interrupted backups.
func (v *Vaultik) CleanupLocalSnapshots() error {
remoteSnapshots, err := v.listRemoteSnapshotIDs()
if err != nil {
return err
}
localSnapshots, err := v.Repositories.Snapshots.ListRecent(v.ctx, 10000)
if err != nil {
return fmt.Errorf("listing local snapshots: %w", err)
}
var removed int
for _, snap := range localSnapshots {
id := snap.ID.String()
if !remoteSnapshots[id] {
v.printfStdout("Removing stale local record: %s\n", id)
if err := v.deleteSnapshotFromLocalDB(id); err != nil {
log.Error("Failed to delete local snapshot", "snapshot_id", id, "error", err)
continue
}
removed++
}
}
if removed == 0 {
v.printlnStdout("No stale local snapshots found.")
} else {
v.printfStdout("Removed %d stale local snapshot record(s).\n", removed)
}
return nil
}
// Helper methods that were previously on SnapshotApp
func (v *Vaultik) getManifestSize(snapshotID string) (int64, error) {
manifestPath := fmt.Sprintf("metadata/%s/manifest.json.zst", snapshotID)
reader, err := v.Storage.Get(v.ctx, manifestPath)
if err != nil {
return 0, fmt.Errorf("downloading manifest: %w", err)
}
defer func() { _ = reader.Close() }()
manifest, err := snapshot.DecodeManifest(reader)
if err != nil {
return 0, fmt.Errorf("decoding manifest: %w", err)
}
return manifest.TotalCompressedSize, nil
}
func (v *Vaultik) downloadManifest(snapshotID string) (*snapshot.Manifest, error) {
manifestPath := fmt.Sprintf("metadata/%s/manifest.json.zst", snapshotID)
@@ -1133,7 +988,6 @@ 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 {
@@ -1148,8 +1002,14 @@ 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)
}
}
@@ -1292,13 +1152,9 @@ type PruneResult struct {
// before starting a new backup or on-demand via the prune command.
func (v *Vaultik) PruneDatabase() (*PruneResult, error) {
log.Info("Pruning local database: removing incomplete snapshots and orphaned data")
v.UI.Begin("Pruning local index database (removing incomplete snapshots and orphaned data).")
result := &PruneResult{}
// Snapshot counts before deletion of incompletes.
snapshotCountBefore, _ := v.getTableCount("snapshots")
// First, delete any incomplete snapshots
incompleteSnapshots, err := v.Repositories.Snapshots.GetIncompleteSnapshots(v.ctx)
if err != nil {
@@ -1351,12 +1207,12 @@ func (v *Vaultik) PruneDatabase() (*PruneResult, error) {
"orphaned_blobs", result.BlobsDeleted,
)
snapshotCountAfter := snapshotCountBefore - result.SnapshotsDeleted
v.UI.Complete("Pruned local index database.")
v.UI.Detail("Incomplete snapshots: %d removed (%d remain).", result.SnapshotsDeleted, snapshotCountAfter)
v.UI.Detail("Orphaned files: %d removed (%d remain).", result.FilesDeleted, fileCountAfter)
v.UI.Detail("Orphaned chunks: %d removed (%d remain).", result.ChunksDeleted, chunkCountAfter)
v.UI.Detail("Orphaned blobs: %d removed (%d remain).", result.BlobsDeleted, blobCountAfter)
// Print summary
v.printfStdout("Local database prune complete:\n")
v.printfStdout(" Incomplete snapshots removed: %d\n", result.SnapshotsDeleted)
v.printfStdout(" Orphaned files removed: %d\n", result.FilesDeleted)
v.printfStdout(" Orphaned chunks removed: %d\n", result.ChunksDeleted)
v.printfStdout(" Orphaned blobs removed: %d\n", result.BlobsDeleted)
return result, nil
}

25
internal/vaultik/vaultik.go
View File

@@ -7,15 +7,14 @@ import (
"io"
"os"
"git.eeqj.de/sneak/vaultik/internal/config"
"git.eeqj.de/sneak/vaultik/internal/crypto"
"git.eeqj.de/sneak/vaultik/internal/database"
"git.eeqj.de/sneak/vaultik/internal/globals"
"git.eeqj.de/sneak/vaultik/internal/snapshot"
"git.eeqj.de/sneak/vaultik/internal/storage"
"github.com/spf13/afero"
"go.uber.org/fx"
"sneak.berlin/go/vaultik/internal/config"
"sneak.berlin/go/vaultik/internal/crypto"
"sneak.berlin/go/vaultik/internal/database"
"sneak.berlin/go/vaultik/internal/globals"
"sneak.berlin/go/vaultik/internal/snapshot"
"sneak.berlin/go/vaultik/internal/storage"
"sneak.berlin/go/vaultik/internal/ui"
)
// Vaultik contains all dependencies needed for vaultik operations
@@ -38,12 +37,6 @@ type Vaultik struct {
Stdout io.Writer
Stderr io.Writer
Stdin io.Reader
// UI is the writer for user-facing status, progress, warnings, errors.
// See package internal/ui for formatting conventions. Defaults to a
// writer wrapping Stdout; the cli layer replaces it with a discarding
// writer in --cron mode.
UI *ui.Writer
}
// VaultikParams contains all parameters for New that can be provided by fx
@@ -90,7 +83,6 @@ func New(params VaultikParams) *Vaultik {
Stdout: os.Stdout,
Stderr: os.Stderr,
Stdin: os.Stdin,
UI: ui.New(os.Stdout),
}
}
@@ -147,6 +139,11 @@ func (v *Vaultik) printlnStdout(args ...any) {
_, _ = fmt.Fprintln(v.Stdout, args...)
}
// printfStderr writes formatted output to stderr.
func (v *Vaultik) printfStderr(format string, args ...any) {
_, _ = fmt.Fprintf(v.Stderr, format, args...)
}
// scanStdin reads a line of input from stdin.
func (v *Vaultik) scanStdin(a ...any) (int, error) {
return fmt.Fscanln(v.Stdin, a...)

13
internal/vaultik/verify.go
View File

@@ -10,11 +10,11 @@ import (
"os"
"time"
"git.eeqj.de/sneak/vaultik/internal/log"
"git.eeqj.de/sneak/vaultik/internal/snapshot"
"github.com/dustin/go-humanize"
"github.com/klauspost/compress/zstd"
_ "modernc.org/sqlite"
"sneak.berlin/go/vaultik/internal/log"
"sneak.berlin/go/vaultik/internal/snapshot"
_ "github.com/mattn/go-sqlite3"
)
// VerifyOptions contains options for the verify command
@@ -57,8 +57,9 @@ func (v *Vaultik) RunDeepVerify(snapshotID string, opts *VerifyOptions) error {
}
if !v.CanDecrypt() {
msg := "VAULTIK_AGE_SECRET_KEY not set; required for deep verification"
return v.deepVerifyFailure(result, opts, msg, fmt.Errorf("%s", msg))
return v.deepVerifyFailure(result, opts,
"VAULTIK_AGE_SECRET_KEY environment variable not set - required for deep verification",
fmt.Errorf("VAULTIK_AGE_SECRET_KEY environment variable not set - required for deep verification"))
}
log.Info("Starting snapshot verification", "snapshot_id", snapshotID, "mode", "deep")
@@ -257,7 +258,7 @@ func (v *Vaultik) decryptAndLoadDatabase(reader io.ReadCloser, secretKey string)
log.Info("Database decompressed", "size", humanize.Bytes(uint64(written)))
// Open the database
db, err := sql.Open("sqlite", tempPath)
db, err := sql.Open("sqlite3", tempPath)
if err != nil {
_ = os.Remove(tempPath)
return nil, fmt.Errorf("failed to open database: %w", err)

92
internal/vaultik/verify_test.go
View File

@@ -1,92 +0,0 @@
package vaultik_test
import (
"bytes"
"crypto/rand"
"crypto/sha256"
"encoding/hex"
"io"
"testing"
"github.com/klauspost/compress/zstd"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
"sneak.berlin/go/vaultik/internal/crypto"
)
// TestTeeReaderWithDecryption tests that TeeReader correctly hashes all encrypted
// bytes when streaming through age decryption and zstd decompression.
// This validates the verification path: hash encrypted blob -> decrypt -> decompress.
func TestTeeReaderWithDecryption(t *testing.T) {
// Test data - use random data that doesn't compress well (5MB)
testData := make([]byte, 5*1024*1024)
_, err := rand.Read(testData)
require.NoError(t, err)
// Compress the data
var compressedBuf bytes.Buffer
compressor, err := zstd.NewWriter(&compressedBuf, zstd.WithEncoderLevel(zstd.SpeedDefault))
require.NoError(t, err)
_, err = compressor.Write(testData)
require.NoError(t, err)
err = compressor.Close()
require.NoError(t, err)
// Encrypt the compressed data
testRecipient := "age1cplgrwj77ta54dnmydvvmzn64ltk83ankxl5sww04mrtmu62kv3s89gmvv"
testSecretKey := "AGE-SECRET-KEY-1C77PYNTHXSHNNC6EYR2W52UWYXACXA5JT00J9CCW9986M3XY87PSGP89AQ"
encryptor, err := crypto.NewEncryptor([]string{testRecipient})
require.NoError(t, err)
var encryptedBuf bytes.Buffer
err = encryptor.EncryptStream(&encryptedBuf, bytes.NewReader(compressedBuf.Bytes()))
require.NoError(t, err)
encryptedData := encryptedBuf.Bytes()
// Calculate the expected hash of the encrypted data directly
expectedHash := sha256.Sum256(encryptedData)
expectedHashStr := hex.EncodeToString(expectedHash[:])
t.Logf("Encrypted data size: %d bytes", len(encryptedData))
t.Logf("Expected hash: %s", expectedHashStr)
// Now simulate what verifyBlob does: use TeeReader to hash while decrypting
decryptor, err := crypto.NewDecryptor(testSecretKey)
require.NoError(t, err)
// Create hasher and tee reader
hasher := sha256.New()
reader := bytes.NewReader(encryptedData)
teeReader := io.TeeReader(reader, hasher)
// Decrypt through the tee reader
decryptedReader, err := decryptor.DecryptStream(teeReader)
require.NoError(t, err)
// Decompress
decompressor, err := zstd.NewReader(decryptedReader)
require.NoError(t, err)
defer decompressor.Close()
// Read all decompressed data (simulating chunk verification)
decompressedData, err := io.ReadAll(decompressor)
require.NoError(t, err)
// Verify we got the original data back
assert.Equal(t, testData, decompressedData, "Decompressed data should match original")
// Drain remaining decompressed data (should be 0)
remaining, err := io.Copy(io.Discard, decompressor)
require.NoError(t, err)
assert.Equal(t, int64(0), remaining, "No remaining decompressed data")
// Calculate hash from tee reader
calculatedHashStr := hex.EncodeToString(hasher.Sum(nil))
t.Logf("Calculated hash (before drain): %s", calculatedHashStr)
// Verify the hash matches the direct hash of encrypted data
assert.Equal(t, expectedHashStr, calculatedHashStr,
"Hash calculated via TeeReader should match direct hash of encrypted data")
}

3
test/config.yaml
View File

@@ -20,6 +20,9 @@ s3:
region: us-east-1
use_ssl: true
part_size: 5242880 # 5MB
backup_interval: 1h
full_scan_interval: 24h
min_time_between_run: 15m
index_path: /tmp/vaultik-test.sqlite
chunk_size: 10MB
blob_size_limit: 10GB

3
test/integration-config.yml
View File

@@ -17,6 +17,9 @@ s3:
region: us-east-1
use_ssl: false
part_size: 5242880 # 5MB
backup_interval: 1h
full_scan_interval: 24h
min_time_between_run: 15m
index_path: /tmp/vaultik-integration-test.sqlite
chunk_size: 10MB
blob_size_limit: 10GB