Author SHA1 Message Date
sneak 42a3c738fa Make **/ in an exclude pattern match zero directories (closes #338)
check / check (push) Waiting to run
The glob library needs a slash on both sides of **, so the anchored
pattern /**/x missed an x directly under the snapshot path, and
a/**/*.log missed a/x.log. As in gitignore, a leading **/ now makes any
pattern, anchored or not, match at every depth, and a pattern holding
/**/ is also compiled with each /**/ made a single slash. The library's
{a,b} alternatives cannot express this: with ** inside them in
mid-pattern they miss paths they should match.

Judgement call: the test for a/**/b uses a/**/*.log, because with a
plain name after the ** the glob library already matched a/b.

Model: opus-5-5
2026-10-13 19:21:54 +00:00
7 changed files with 117 additions and 327 deletions
+1 -3
View File
@@ -339,9 +339,7 @@ local index alone, and still exits zero.
**`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). If a snapshot cannot be removed from the local index, the
command stops there, leaves that snapshot's metadata on the destination store
and exits non-zero; `snapshot create --prune` fails the same way.
latest globally).
* `--keep-latest`: Keep only the most recent snapshot of each name
* `--older-than <duration>`: Remove snapshots older than duration (e.g. `30d`,
`4w`, `6mo`, `1y`; `m` is minutes, `mo` is months)
-90
View File
@@ -1,90 +0,0 @@
package cli //nolint:testpackage // shares runEntry and the hermetic config helpers
import (
"context"
"database/sql"
"os"
"path/filepath"
"testing"
"time"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
"sneak.berlin/go/vaultik/internal/database"
"sneak.berlin/go/vaultik/internal/snapshot"
"sneak.berlin/go/vaultik/internal/types"
)
// The `snapshot purge` command word and flags used below.
const (
cmdPurge = "purge"
flagKeepLatest = "--keep-latest"
flagForce = "--force"
)
// TestEntrySnapshotPurgeKeepsMetadataWhenLocalIndexDeleteFails makes
// removing a snapshot from the local index fail and checks that
// `snapshot purge` exits non-zero and leaves that snapshot's metadata on
// the destination store. It used to log the error, delete the metadata
// anyway and exit 0.
//
//nolint:paralleltest // replaces os.Args, os.Stdout, os.Stderr and the xdg globals
func TestEntrySnapshotPurgeKeepsMetadataWhenLocalIndexDeleteFails(t *testing.T) {
ctx := context.Background()
configPath := writeHermeticPruneConfig(t, false)
// writeHermeticPruneConfig puts the index and the store directory
// beside the config file.
dir := filepath.Dir(configPath)
// Two snapshots of the same name: --keep-latest purges the older.
olderStart := time.Date(2026, 5, 1, 9, 0, 0, 0, time.UTC)
newerStart := olderStart.Add(time.Hour)
olderID := "test-host_test_" + olderStart.Format(time.RFC3339)
newerID := "test-host_test_" + newerStart.Format(time.RFC3339)
db, err := database.New(ctx, filepath.Join(dir, "index.sqlite"))
require.NoError(t, err)
repos := database.NewRepositories(db)
manifestPaths := make(map[string]string)
for id, startedAt := range map[string]time.Time{
olderID: olderStart,
newerID: newerStart,
} {
completedAt := startedAt.Add(time.Minute)
snap := &database.Snapshot{
ID: types.SnapshotID(id),
Hostname: "test-host",
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)
manifestPaths[id] = filepath.Join(dir, "store", "metadata",
snapshot.RemoteSnapshotKey(id), "manifest.json.zst")
require.NoError(t, os.MkdirAll(filepath.Dir(manifestPaths[id]), 0o750))
require.NoError(t, os.WriteFile(manifestPaths[id], []byte("stub"), 0o600))
}
_, err = db.Conn().ExecContext(ctx, `
CREATE TRIGGER refuse_snapshot_delete BEFORE DELETE ON snapshots
BEGIN SELECT RAISE(ABORT, 'simulated index error'); END`)
require.NoError(t, err)
require.NoError(t, db.Close())
code, _, stderr := runEntry(t,
flagConfig, configPath, cmdSnapshot, cmdPurge, flagKeepLatest, flagForce)
assert.Equal(t, 1, code)
assert.Contains(t, stderr, "simulated index error")
assert.FileExists(t, manifestPaths[olderID],
"a snapshot still in the local index keeps its metadata")
}
+51
View File
@@ -578,3 +578,54 @@ func TestExcludePatterns_DoubleStarFileAtEveryDepth(t *testing.T) {
require.Equal(t, 1, result.FilesScanned,
"**/ file pattern should match at the top level and nested")
}
func TestExcludePatterns_AnchoredDoubleStarAtEveryDepth(t *testing.T) {
t.Parallel()
// As in gitignore, /**/ also matches directly under the source dir
fs := setupAnchoredTestFS(t)
scanner, repos, cleanup := createTestScanner(t, fs, []string{"/**/projectname"})
defer cleanup()
ctx := context.Background()
createSnapshotRecord(ctx, t, repos, "test-snapshot")
result, err := scanner.Scan(ctx, "/backup", "test-snapshot")
require.NoError(t, err)
// /**/projectname should exclude BOTH:
// - /backup/projectname/file.txt
// - /backup/otherproject/projectname/file.txt
// Total files: 4, excluded: 2
require.Equal(t, 2, result.FilesScanned,
"/**/ pattern should match at the top level and nested")
}
func TestExcludePatterns_DoubleStarInMiddleMatchesZeroDirectories(t *testing.T) {
t.Parallel()
// As in gitignore, a/**/b matches a/b as well as a/c/b. The last part
// is a glob: with a plain name the glob library already matched a/b.
fs := &afero.MemMapFs{}
files := []string{"/backup/a/x.log", "/backup/a/c/y.log", "/backup/a/c/kept.txt"}
for _, path := range files {
require.NoError(t, fs.MkdirAll(filepath.Dir(path), 0755))
require.NoError(t, afero.WriteFile(fs, path, []byte(path), 0644))
}
scanner, repos, cleanup := createTestScanner(t, fs, []string{"a/**/*.log"})
defer cleanup()
ctx := context.Background()
createSnapshotRecord(ctx, t, repos, "test-snapshot")
result, err := scanner.Scan(ctx, "/backup", "test-snapshot")
require.NoError(t, err)
// a/**/*.log should exclude /backup/a/x.log and /backup/a/c/y.log
// Total files: 3, excluded: 2
require.Equal(t, 1, result.FilesScanned,
"a/**/*.log should match a/x.log as well as a/c/y.log")
}
+45 -18
View File
@@ -2035,33 +2035,60 @@ func compileExcludePatterns(patterns []string) []compiledPattern {
pattern = strings.TrimSuffix(pattern, "/")
// A leading "**/" demands a "/" before the name and so misses an
// entry directly under the source path. An unanchored pattern
// already matches at every depth, so drop the prefix: as in
// gitignore, "**/x" then also matches a top-level "x".
if !anchored {
pattern = strings.TrimPrefix(pattern, "**/")
// entry directly under the source path. It means "at every depth",
// which is what an unanchored pattern already does, so drop the
// prefix and match unanchored: as in gitignore, "**/x" and
// "/**/x" then also match a top-level "x".
if rest, found := strings.CutPrefix(pattern, "**/"); found {
pattern = rest
anchored = false
}
// Compile the glob pattern
// For patterns without path separators, we need to match them as components
// e.g., ".git" should match ".git" anywhere in the path
g, err := glob.Compile(pattern, '/')
if err != nil {
log.Warn("Invalid exclude pattern, skipping", "pattern", p, "error", err)
// Likewise "/**/" inside a pattern demands two slashes, so
// "a/**/*.log" misses "a/x.log". As in gitignore it stands for
// zero or more directories, so also compile the pattern with it
// made a single "/". The glob library's {a,b} is no help: with a
// "**" inside it in mid-pattern, it misses paths it should match.
for _, variant := range doubleStarVariants(pattern) {
// For patterns without path separators, we need to match them as components
// e.g., ".git" should match ".git" anywhere in the path
g, err := glob.Compile(variant, '/')
if err != nil {
log.Warn("Invalid exclude pattern, skipping", "pattern", p, "error", err)
continue
break
}
compiled = append(compiled, compiledPattern{
pattern: g,
anchored: anchored,
original: p,
})
}
compiled = append(compiled, compiledPattern{
pattern: g,
anchored: anchored,
original: p,
})
}
return compiled
}
// doubleStarVariants returns pattern once for every way of keeping each
// "/**/" in it or making it a single "/".
func doubleStarVariants(pattern string) []string {
const doubleStar = "/**/"
before, after, found := strings.Cut(pattern, doubleStar)
if !found {
return []string{pattern}
}
var variants []string
for _, rest := range doubleStarVariants(after) {
variants = append(variants, before+doubleStar+rest, before+"/"+rest)
}
return variants
}
// shouldExclude checks if a path should be excluded based on exclude patterns
// filePath is the full path to the file
// rootPath is the root of the backup source directory
-172
View File
@@ -1,9 +1,7 @@
package vaultik_test
import (
"bytes"
"context"
"crypto/rand"
"io"
"os"
"path/filepath"
@@ -11,9 +9,7 @@ import (
"github.com/spf13/afero"
"github.com/stretchr/testify/require"
"sneak.berlin/go/vaultik/internal/config"
"sneak.berlin/go/vaultik/internal/log"
"sneak.berlin/go/vaultik/internal/storage"
"sneak.berlin/go/vaultik/internal/ui"
"sneak.berlin/go/vaultik/internal/vaultik"
)
@@ -81,174 +77,6 @@ func TestDeepVerifyAcceptsHealthyAndRejectsCorruptBlob(t *testing.T) {
"deep verify should fail on a corrupted blob")
}
// TestDeepVerifyJSONCountsBlobs checks the verified and missing counts
// that deep verify reports under --json: on a healthy snapshot, with a
// damaged blob, and with missing blobs. Deep verify stops at the first
// damaged blob, so the blobs read before it are the ones verified; when
// blobs are missing it reads no blob contents, but counts every missing
// blob.
func TestDeepVerifyJSONCountsBlobs(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
fs := afero.NewOsFs()
ctx := context.Background()
storeDir := filepath.Join(t.TempDir(), "remote")
cfg, storer, snapshotID, keys := backUpSeveralBlobs(ctx, t, storeDir)
healthy, err := deepVerifyJSON(ctx, t, cfg, storer, snapshotID)
require.NoError(t, err)
require.Equal(t, "ok", healthy.Status)
require.Len(t, keys, healthy.BlobCount)
require.Equal(t, healthy.BlobCount, healthy.Verified)
require.Zero(t, healthy.Missing)
// Damage the last blob read, keeping its length, so every blob before
// it is read and passes first.
lastPath := filepath.Join(storeDir, keys[len(keys)-1])
blob, err := afero.ReadFile(fs, lastPath)
require.NoError(t, err)
blob[len(blob)/2] ^= 0xff
require.NoError(t, afero.WriteFile(fs, lastPath, blob, 0o600))
got, err := deepVerifyJSON(ctx, t, cfg, storer, snapshotID)
require.Error(t, err)
require.Equal(t, "failed", got.Status)
require.Equal(t, healthy.BlobCount-1, got.Verified)
require.Zero(t, got.Missing)
// Delete the first blob and the damaged last one: both must be
// counted as missing, not only the first one found.
var deletedSize int64
for _, key := range []string{keys[0], keys[len(keys)-1]} {
info, statErr := storer.Stat(ctx, key)
require.NoError(t, statErr)
deletedSize += info.Size
require.NoError(t, storer.Delete(ctx, key))
}
got, err = deepVerifyJSON(ctx, t, cfg, storer, snapshotID)
require.Error(t, err)
require.Equal(t, "failed", got.Status)
require.Equal(t, 2, got.Missing)
require.Equal(t, deletedSize, got.MissingSize)
require.Zero(t, got.Verified)
}
// TestDeepVerifyJSONCountsWrongSizeBlob checks that under --deep --json a
// blob of the wrong size is counted in mismatched and fails the run, and
// that the check goes on past it to count a missing blob after it.
func TestDeepVerifyJSONCountsWrongSizeBlob(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
fs := afero.NewOsFs()
ctx := context.Background()
storeDir := filepath.Join(t.TempDir(), "remote")
cfg, storer, snapshotID, keys := backUpSeveralBlobs(ctx, t, storeDir)
// Make the first blob checked longer, and delete the last one.
firstPath := filepath.Join(storeDir, keys[0])
blob, err := afero.ReadFile(fs, firstPath)
require.NoError(t, err)
blob = append(blob, []byte("extra")...)
require.NoError(t, afero.WriteFile(fs, firstPath, blob, 0o600))
require.NoError(t, storer.Delete(ctx, keys[len(keys)-1]))
got, err := deepVerifyJSON(ctx, t, cfg, storer, snapshotID)
require.Error(t, err)
require.Equal(t, "failed", got.Status)
require.Equal(t, 1, got.Mismatched)
require.Equal(t, 1, got.Missing)
require.Zero(t, got.Verified)
}
// TestDeepVerifyStopsOnBlobThatCannotBeChecked checks that a blob that is
// present in storage but cannot be checked is not counted as missing:
// deep verify stops and fails with the storage error.
func TestDeepVerifyStopsOnBlobThatCannotBeChecked(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
ctx := context.Background()
storeDir := filepath.Join(t.TempDir(), "remote")
cfg, storer, snapshotID, keys := backUpSeveralBlobs(ctx, t, storeDir)
failing := statFailingStorer{Storer: storer, failKeys: []string{keys[0]}}
got, err := deepVerifyJSON(ctx, t, cfg, failing, snapshotID)
require.Error(t, err)
require.Equal(t, "failed", got.Status)
require.Zero(t, got.Missing)
require.Contains(t, got.ErrorMessage, errStatDenied.Error())
}
// backUpSeveralBlobs backs up random data, which does not compress or
// deduplicate, so it fills at least three blobs in a store on disk at
// storeDir. It returns the blobs' storage keys sorted, which is hash
// order, the order deep verify reads them in.
func backUpSeveralBlobs(
ctx context.Context, t *testing.T, storeDir string,
) (*config.Config, *storage.FileStorer, string, []string) {
t.Helper()
fs := afero.NewOsFs()
tempDir := t.TempDir()
dataDir := filepath.Join(tempDir, "source")
dbPath := filepath.Join(tempDir, "index.sqlite")
chunkSize := int64(32 * 1024)
maxBlobSize := int64(128 * 1024)
data := make([]byte, maxBlobSize*4)
_, err := rand.Read(data)
require.NoError(t, err)
require.NoError(t, fs.MkdirAll(dataDir, 0o755))
require.NoError(t, afero.WriteFile(fs,
filepath.Join(dataDir, "data.bin"), data, 0o644))
cfg, storer, snapshotID := runFileStorageBackup(
ctx, t, fs, dataDir, storeDir, dbPath, chunkSize, maxBlobSize)
keys := storedBlobKeys(t, storeDir)
require.GreaterOrEqual(t, len(keys), 3)
return cfg, storer, snapshotID, keys
}
// deepVerifyJSON runs deep verify with --json on snapshotID and returns
// the decoded result and the error RunDeepVerify returned.
func deepVerifyJSON(
ctx context.Context, t *testing.T,
cfg *config.Config, storer storage.Storer, snapshotID string,
) (vaultik.VerifyResult, error) {
t.Helper()
var out bytes.Buffer
v := &vaultik.Vaultik{
Config: cfg,
Storage: storer,
Fs: afero.NewOsFs(),
Stdout: &out,
Stderr: io.Discard,
UI: ui.NewWithColor(io.Discard, false),
}
v.SetContext(ctx)
err := v.RunDeepVerify(snapshotID,
&vaultik.VerifyOptions{Deep: true, JSON: true})
return decodeVerifyResult(t, out.Bytes()), err
}
// corruptOneBlob flips a middle byte of the first blob file found under
// blobsDir, leaving the file length unchanged.
func corruptOneBlob(t *testing.T, fs afero.Fs, blobsDir string) {
+3 -5
View File
@@ -627,8 +627,7 @@ func selectSnapshotsToPurge(
}
// confirmAndExecutePurge shows deletion candidates, confirms with the
// user, and deletes snapshots. It stops with an error at the first
// snapshot it cannot delete.
// user, and deletes snapshots.
func (v *Vaultik) confirmAndExecutePurge(
toDelete []SnapshotInfo, force, quiet bool,
) error {
@@ -670,11 +669,10 @@ func (v *Vaultik) confirmAndExecutePurge(
snapshotID := snap.ID.String()
log.Info("Deleting snapshot", "id", snapshotID)
// Stop before the remote delete: a snapshot still in the local
// index must keep its metadata on the destination store.
err := v.deleteSnapshotFromLocalDB(snapshotID)
if err != nil {
return fmt.Errorf("deleting snapshot %s from local index: %w", snapshotID, err)
log.Error("Failed to delete from local database",
"snapshot_id", snapshotID, "error", err)
}
_, err = v.deleteRemoteSnapshotByKey(snapshot.RemoteSnapshotKey(snapshotID))
+17 -39
View File
@@ -17,7 +17,6 @@ import (
"sneak.berlin/go/vaultik/internal/database"
"sneak.berlin/go/vaultik/internal/log"
"sneak.berlin/go/vaultik/internal/snapshot"
"sneak.berlin/go/vaultik/internal/storage"
)
// Sentinel errors for snapshot verification failures.
@@ -33,9 +32,7 @@ var (
errManifestExtraBlob = errors.New("manifest contains blob not in database")
errManifestMissingBlob = errors.New(
"manifest omits blob present in database")
errBlobSizeMismatch = errors.New("blob size mismatch")
errBlobsNotInStorage = errors.New(
"blobs missing from storage or stored with the wrong size")
errBlobSizeMismatch = errors.New("blob size mismatch")
)
// verifyStatusFailed is the JSON status value for a failed verification.
@@ -152,6 +149,7 @@ func (v *Vaultik) RunDeepVerify(snapshotID string, opts *VerifyOptions) error {
}
result.Status = "ok"
result.Verified = len(dbBlobs)
if opts.JSON {
return v.outputVerifyJSON(result)
@@ -308,7 +306,7 @@ func (v *Vaultik) runVerificationSteps(
v.stdoutf("Checking blob existence in remote storage...\n")
}
err = v.verifyBlobExistenceFromDB(dbBlobs, result)
err = v.verifyBlobExistenceFromDB(dbBlobs)
if err != nil {
return v.deepVerifyFailure(result, opts, err.Error(), err)
}
@@ -319,8 +317,7 @@ func (v *Vaultik) runVerificationSteps(
len(dbBlobs), ubytes(totalSize))
}
err = v.performDeepVerificationFromDB(
dbBlobs, tdb.db.Conn(), opts, result, identities)
err = v.performDeepVerificationFromDB(dbBlobs, tdb.db.Conn(), opts, identities)
if err != nil {
return v.deepVerifyFailure(result, opts, err.Error(), err)
}
@@ -672,14 +669,8 @@ func (v *Vaultik) verifyManifestAgainstDatabase(
return nil
}
// verifyBlobExistenceFromDB checks that every blob from the database is
// in storage with the size the database records. It checks them all,
// counting the missing and wrong-size blobs in result, and fails if it
// found any. Any storage error other than not found stops the check and
// fails with that error.
func (v *Vaultik) verifyBlobExistenceFromDB(
blobs []snapshot.BlobInfo, result *VerifyResult,
) error {
// verifyBlobExistenceFromDB checks that all blobs from database exist in S3
func (v *Vaultik) verifyBlobExistenceFromDB(blobs []snapshot.BlobInfo) error {
log.Info("Verifying blob existence in S3", "blob_count", len(blobs))
for i, blob := range blobs {
@@ -692,23 +683,17 @@ func (v *Vaultik) verifyBlobExistenceFromDB(
// Construct blob path
blobPath := fmt.Sprintf("blobs/%s/%s/%s", blob.Hash[:2], blob.Hash[2:4], blob.Hash)
// Check blob exists
stat, err := v.Storage.Stat(v.ctx, blobPath)
switch {
case errors.Is(err, storage.ErrNotFound):
log.Warn("Blob missing from storage", "hash", blob.Hash)
if err != nil {
return fmt.Errorf("blob %s missing from storage: %w", blob.Hash, err)
}
result.Missing++
result.MissingSize += blob.CompressedSize
case err != nil:
return fmt.Errorf("checking blob %s in storage: %w",
blob.Hash, err)
case stat.Size != blob.CompressedSize:
log.Warn("Blob has the wrong size in storage",
"hash", blob.Hash,
"storage_size", stat.Size,
"database_size", blob.CompressedSize)
result.Mismatched++
// Verify size matches
if stat.Size != blob.CompressedSize {
return fmt.Errorf(
"%w: blob %s: S3 has %d bytes, database has %d bytes",
errBlobSizeMismatch, blob.Hash, stat.Size, blob.CompressedSize)
}
// Progress update every 100 blobs
@@ -722,22 +707,16 @@ func (v *Vaultik) verifyBlobExistenceFromDB(
}
}
if result.Missing > 0 || result.Mismatched > 0 {
return fmt.Errorf("%w: %d missing, %d with the wrong size",
errBlobsNotInStorage, result.Missing, result.Mismatched)
}
log.Info("✓ All blobs exist in storage")
return nil
}
// performDeepVerificationFromDB downloads and verifies the content of
// each blob using the database as source, stopping at the first blob that
// fails. Each blob that passes is counted in result.Verified.
// each blob using the database as source.
func (v *Vaultik) performDeepVerificationFromDB(
blobs []snapshot.BlobInfo, db *sql.DB, opts *VerifyOptions,
result *VerifyResult, identities []age.Identity,
identities []age.Identity,
) error {
// Calculate total bytes for ETA
var totalBytesExpected int64
@@ -760,7 +739,6 @@ func (v *Vaultik) performDeepVerificationFromDB(
return fmt.Errorf("blob %s verification failed: %w", blobInfo.Hash, err)
}
result.Verified++
bytesProcessed += blobInfo.CompressedSize
elapsed := time.Since(startTime)
remaining := len(blobs) - (i + 1)