Stop restore --verify re-reporting files that failed to restore (closes #323)

With --skip-errors, a file that failed to restore was verified anyway,
failed again because it was never written, and was added to the same
failure list as the restore failure. restore --verify then listed it
twice and called every entry a checksum mismatch.

Verification now skips the files that failed to restore and keeps its
own failures in a separate list, so failed restores and failed
verifications are reported apart, each path once. The restore still
exits non-zero.

Model: opus-5-5

README.md

@@ -435,10 +435,7 @@ 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. The
-path must be absolute; a relative one is refused when the config loads.
-Percent-escapes in the path are decoded, so `my%20stick` and `my stick` name
-the same directory.
+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`).

internal/blob/packer.go

@@ -245,17 +245,6 @@ func (p *Packer) Flush(ctx context.Context) error {
 	return nil
 }
 
-// DiscardCurrentBlob closes and removes the temp file of the blob being
-// packed, if any, and drops that blob. A caller that stops before Flush
-// must call it, or the temp file is left behind. Thread-safe.
-func (p *Packer) DiscardCurrentBlob() {
-	p.mu.Lock()
-	defer p.mu.Unlock()
-
-	p.cleanupTempFile()
-	p.currentBlob = nil
-}
-
 // FinalizeBlob finalizes the current blob being assembled.
 // This compresses the accumulated chunks, encrypts the result, and computes
 // the content-addressed hash. The finalized blob is either passed to the

internal/cli/config.go

@@ -251,12 +251,6 @@ func NewConfigCommand() *cobra.Command {
 		Use:   "config",
 		Short: "Manage the configuration file",
 		Long:  "Commands for creating, editing, and querying the vaultik config file.",
-		// cobra checks Args only on a command that has a Run: without
-		// one, a mistyped subcommand printed help and exited 0.
-		Args: cobra.NoArgs,
-		Run: func(cmd *cobra.Command, _ []string) {
-			_ = cmd.Help()
-		},
 	}
 
 	cmd.AddCommand(newConfigInitCommand())

internal/cli/database.go

@@ -15,12 +15,6 @@ func NewDatabaseCommand() *cobra.Command {
 		Use:   "database",
 		Short: "Manage the local state database",
 		Long:  `Commands for managing the local SQLite state database.`,
-		// cobra checks Args only on a command that has a Run: without
-		// one, a mistyped subcommand printed help and exited 0.
-		Args: cobra.NoArgs,
-		Run: func(cmd *cobra.Command, _ []string) {
-			_ = cmd.Help()
-		},
 	}
 
 	cmd.AddCommand(

internal/cli/entry_unknown_subcommand_test.go

@@ -1,43 +0,0 @@
-package cli //nolint:testpackage // shares runEntry and the command-word constants
-
-import (
-	"testing"
-
-	"github.com/stretchr/testify/assert"
-)
-
-// TestEntryGroupRejectsUnknownSubcommand runs each group command with a
-// mistyped subcommand, as a crontab line might carry one. It must fail
-// with exit 1 and name the word, as `vaultik bogus` does at the top
-// level, instead of printing the group's help and exiting 0 having done
-// nothing. The group name alone still prints its help.
-//
-//nolint:paralleltest // replaces os.Args, os.Stdout and os.Stderr
-func TestEntryGroupRejectsUnknownSubcommand(t *testing.T) {
-	for _, testCase := range []struct {
-		group    string
-		mistyped string
-	}{
-		{group: cmdSnapshot, mistyped: "craete"},
-		{group: "config", mistyped: "inti"},
-		{group: cmdRemote, mistyped: "ifno"},
-		{group: "database", mistyped: "delte"},
-		{group: "completion", mistyped: "nosuchshell"},
-	} {
-		t.Run(testCase.group, func(t *testing.T) {
-			code, stdout, stderr := runEntry(t,
-				testCase.group, testCase.mistyped)
-
-			assert.Equal(t, 1, code)
-			assert.Empty(t, stdout)
-			assert.Contains(t, stderr,
-				`unknown command "`+testCase.mistyped+`"`)
-
-			code, stdout, _ = runEntry(t, testCase.group)
-
-			assert.Equal(t, 0, code)
-			assert.Contains(t, stdout,
-				programName+" "+testCase.group+" [command]")
-		})
-	}
-}

internal/cli/remote.go

@@ -18,12 +18,6 @@ func NewRemoteCommand() *cobra.Command {
 		Use:   "remote",
 		Short: "Remote storage management commands",
 		Long:  "Commands for inspecting and managing remote storage",
-		// cobra checks Args only on a command that has a Run: without
-		// one, a mistyped subcommand printed help and exited 0.
-		Args: cobra.NoArgs,
-		Run: func(cmd *cobra.Command, _ []string) {
-			_ = cmd.Help()
-		},
 	}
 
 	// Add subcommands

internal/cli/root.go

@@ -74,21 +74,6 @@ on the source system.`,
 		NewDatabaseCommand(),
 	)
 
-	// cobra adds the completion command only when Execute runs, and with
-	// no Run, so it skipped its own cobra.NoArgs and a mistyped shell name
-	// printed help and exited 0. Adding it here lets it have a Run. Its
-	// scripts go to os.Stdout as it is now: a later SetOut does not
-	// redirect them.
-	cmd.InitDefaultCompletionCmd()
-
-	for _, sub := range cmd.Commands() {
-		if sub.Name() == "completion" {
-			sub.Run = func(completion *cobra.Command, _ []string) {
-				_ = completion.Help()
-			}
-		}
-	}
-
 	return cmd
 }
 

internal/cli/snapshot.go

@@ -41,12 +41,6 @@ func NewSnapshotCommand() *cobra.Command {
 		Use:   "snapshot",
 		Short: "Snapshot management commands",
 		Long:  "Commands for creating, listing, and managing snapshots",
-		// cobra checks Args only on a command that has a Run: without
-		// one, a mistyped subcommand printed help and exited 0.
-		Args: cobra.NoArgs,
-		Run: func(cmd *cobra.Command, _ []string) {
-			_ = cmd.Help()
-		},
 	}
 
 	// Add subcommands

internal/config/config.go

@@ -61,9 +61,6 @@ var (
 	errBadS3PartSize    = errors.New("s3.part_size must be between 5MiB and 5GiB")
 	errBadStorageScheme = errors.New(
 		"storage_url must start with s3://, file://, or rclone://")
-	errFileURLNotAbsolute = errors.New(
-		"a file:// storage_url needs an absolute path, " +
-			"as in file:///path/to/backup")
 	errStorageNotConfigured = errors.New(
 		"storage not configured; set storage_url or provide s3.endpoint + " +
 			"s3.bucket + credentials")
@@ -464,18 +461,11 @@ func (c *Config) validateStorage() error {
 
 // validateStorageURL validates URL-based storage configuration. File and
 // rclone URLs need no credentials; S3 URLs require the legacy s3.*
-// credential fields. A file URL must name an absolute path: a relative one
-// would resolve against the working directory, so the destination would
-// move with it.
+// credential fields.
 func (c *Config) validateStorageURL() error {
 	switch {
 	case strings.HasPrefix(c.StorageURL, "file://"):
-		// storage.ParseStorageURL applies the same rule, but config
-		// cannot import storage, which imports config.
-		if !strings.HasPrefix(c.StorageURL, "file:///") {
-			return errFileURLNotAbsolute
-		}
-
+		// File storage doesn't need S3 credentials
 		return nil
 	case strings.HasPrefix(c.StorageURL, "rclone://"):
 		// Rclone storage uses rclone's own config

internal/config/config_test.go

@@ -337,35 +337,6 @@ func TestLoadS3PartSize(t *testing.T) {
 	})
 }
 
-// TestLoadRejectsRelativeFileURL checks that a file:// storage_url with a
-// relative path fails at load. Accepted, it would resolve against the
-// working directory, so a backup run from another directory would write
-// to a different destination and still succeed.
-func TestLoadRejectsRelativeFileURL(t *testing.T) {
-	t.Parallel()
-
-	const relativeConfig = "snapshots:\n" +
-		"  test:\n" +
-		"    paths: [/tmp/vaultik-test-source]\n" +
-		"storage_url: file://dest\n"
-
-	path := filepath.Join(t.TempDir(), "config.yml")
-
-	err := os.WriteFile(path, []byte(relativeConfig), 0o600)
-	if err != nil {
-		t.Fatalf("write config: %v", err)
-	}
-
-	_, err = Load(path)
-	if !errors.Is(err, errFileURLNotAbsolute) {
-		t.Fatalf("Load() error = %v, want errFileURLNotAbsolute", err)
-	}
-
-	if !strings.Contains(err.Error(), "absolute path") {
-		t.Errorf("error %q does not say to use an absolute path", err.Error())
-	}
-}
-
 // TestValidateAgeRecipients checks that recipients are parsed at config load
 // (a bad entry fails immediately, not mid-backup) and that no invalid entry —
 // least of all a pasted secret key — is echoed in the error. An empty list

internal/snapshot/exclude_test.go

@@ -531,50 +531,3 @@ func TestExcludePatterns_UnanchoredPatternFile(t *testing.T) {
 	require.Equal(t, 1, result.FilesScanned,
 		"Unanchored pattern for file should match anywhere")
 }
-
-func TestExcludePatterns_DoubleStarDirectoryAtEveryDepth(t *testing.T) {
-	t.Parallel()
-
-	// As in gitignore, a leading **/ 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,
-		"**/ directory pattern should match at the top level and nested")
-}
-
-func TestExcludePatterns_DoubleStarFileAtEveryDepth(t *testing.T) {
-	t.Parallel()
-
-	// As in gitignore, a leading **/ also matches directly under the source dir
-	fs := setupAnchoredTestFS(t)
-
-	scanner, repos, cleanup := createTestScanner(t, fs, []string{"**/*.txt"})
-	defer cleanup()
-
-	ctx := context.Background()
-	createSnapshotRecord(ctx, t, repos, "test-snapshot")
-
-	result, err := scanner.Scan(ctx, "/backup", "test-snapshot")
-	require.NoError(t, err)
-
-	// **/*.txt should exclude ALL .txt files:
-	// - /backup/file.txt
-	// - /backup/projectname/file.txt
-	// - /backup/otherproject/projectname/file.txt
-	// Total files: 4, excluded: 3
-	require.Equal(t, 1, result.FilesScanned,
-		"**/ file pattern should match at the top level and nested")
-}

internal/snapshot/scanner.go

@@ -1295,11 +1295,6 @@ func (s *Scanner) batchAddFilesToSnapshot(
 func (s *Scanner) processPhase(
 	ctx context.Context, filesToProcess []*FileToProcess, result *ScanResult,
 ) error {
-	// On an error or cancellation the blob being packed is never
-	// finalized, so its temp file must be removed here. After a
-	// successful flush there is no such blob and this does nothing.
-	defer s.packer.DiscardCurrentBlob()
-
 	// Calculate total bytes to process
 	var totalBytes int64
 	for _, f := range filesToProcess {
@@ -2018,14 +2013,6 @@ func compileExcludePatterns(patterns []string) []compiledPattern {
 		// Remove trailing slash if present (directory indicator)
 		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, "**/")
-		}
-
 		// 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

internal/snapshot/skip_errors_test.go

@@ -381,60 +381,3 @@ func TestScannerCancelStopsSkipErrorsRun(t *testing.T) {
 		})
 	}
 }
-
-// TestScannerRemovesBlobTempFileWhenRunStops checks that a run stopped
-// part-way, by a file it cannot read or by a cancellation, removes the
-// temp file of the blob it was packing.
-func TestScannerRemovesBlobTempFileWhenRunStops(t *testing.T) {
-	t.Parallel()
-
-	// a.txt is backed up first and starts a blob; the run stops at b.txt.
-	const target = "/source/b.txt"
-
-	tests := []struct {
-		name  string
-		newFs func(cancel context.CancelFunc) afero.Fs
-	}{
-		{
-			name: "file cannot be read",
-			newFs: func(context.CancelFunc) afero.Fs {
-				return &readFailFs{Fs: afero.NewMemMapFs(), target: target}
-			},
-		},
-		{
-			name: "cancelled",
-			newFs: func(cancel context.CancelFunc) afero.Fs {
-				return &cancelOnOpenFs{
-					Fs: afero.NewMemMapFs(), target: target, cancel: cancel,
-				}
-			},
-		},
-	}
-
-	for _, tt := range tests {
-		t.Run(tt.name, func(t *testing.T) {
-			t.Parallel()
-
-			ctx, cancel := context.WithCancel(context.Background())
-			defer cancel()
-
-			fs := tt.newFs(cancel)
-			writeSkipErrorTestFile(t, fs, "/source/a.txt", "first file content")
-			writeSkipErrorTestFile(t, fs, target, "second file content")
-
-			_, err := runSkipErrorScan(ctx, t, fs, "/source", false, nil)
-			if err == nil {
-				t.Fatal("expected the scan to stop with an error, got nil")
-			}
-
-			left, err := afero.Glob(fs, filepath.Join(os.TempDir(), "vaultik-blob-*"))
-			if err != nil {
-				t.Fatalf("listing blob temp files: %v", err)
-			}
-
-			if len(left) != 0 {
-				t.Fatalf("expected no blob temp file left, got %v", left)
-			}
-		})
-	}
-}

internal/storage/url.go

@@ -17,10 +17,8 @@ const (
 
 // Sentinel errors for storage URL parsing.
 var (
-	ErrEmptyStorageURL  = errors.New("storage URL is empty")
-	ErrEmptyFilePath    = errors.New("file URL path is empty")
-	ErrRelativeFilePath = errors.New(
-		"file URL needs an absolute path, as in file:///path/to/backup")
+	ErrEmptyStorageURL   = errors.New("storage URL is empty")
+	ErrEmptyFilePath     = errors.New("file URL path is empty")
 	ErrMissingBucket     = errors.New("s3 URL missing bucket name")
 	ErrMissingRemote     = errors.New("rclone URL missing remote name")
 	ErrUnsupportedScheme = errors.New(
@@ -53,8 +51,17 @@ func ParseStorageURL(rawURL string) (*URL, error) {
 		return nil, ErrEmptyStorageURL
 	}
 
+	// Handle file:// URLs
 	if after, ok := strings.CutPrefix(rawURL, "file://"); ok {
-		return parseFileURL(after)
+		path := after
+		if path == "" {
+			return nil, ErrEmptyFilePath
+		}
+
+		return &URL{
+			Scheme: schemeFile,
+			Prefix: path,
+		}, nil
 	}
 
 	if strings.HasPrefix(rawURL, "s3://") {
@@ -68,27 +75,6 @@ func ParseStorageURL(rawURL string) (*URL, error) {
 	return nil, ErrUnsupportedScheme
 }
 
-// parseFileURL parses the path that follows file://. The path must be
-// absolute: a relative one would resolve against the working directory,
-// so the destination would move with it. Percent-escapes are decoded, so
-// my%20stick names the directory "my stick"; a literal space is kept.
-func parseFileURL(rawPath string) (*URL, error) {
-	if rawPath == "" {
-		return nil, ErrEmptyFilePath
-	}
-
-	if !strings.HasPrefix(rawPath, "/") {
-		return nil, ErrRelativeFilePath
-	}
-
-	path, err := url.PathUnescape(rawPath)
-	if err != nil {
-		return nil, fmt.Errorf("invalid file URL path: %w", err)
-	}
-
-	return &URL{Scheme: schemeFile, Prefix: path}, nil
-}
-
 // parseS3URL parses an s3://bucket/prefix URL. It rejects credentials in
 // the userinfo and any query parameter other than endpoint, region and
 // ssl, so a credential-bearing URL is never stored or echoed.

internal/storage/url_parse_test.go

@@ -14,10 +14,7 @@ import (
 func TestParseStorageURLValid(t *testing.T) {
 	t.Parallel()
 
-	const (
-		bucket     = "mybucket"
-		fileScheme = "file"
-	)
+	const bucket = "mybucket"
 
 	cases := []struct {
 		name string
@@ -27,17 +24,7 @@ func TestParseStorageURLValid(t *testing.T) {
 		{
 			name: "file absolute path",
 			raw:  "file:///var/backups/vaultik",
-			want: &storage.URL{Scheme: fileScheme, Prefix: "/var/backups/vaultik"},
-		},
-		{
-			name: "file percent-escaped path is decoded",
-			raw:  "file:///Volumes/my%20stick/backup",
-			want: &storage.URL{Scheme: fileScheme, Prefix: "/Volumes/my stick/backup"},
-		},
-		{
-			name: "file path with a literal space",
-			raw:  "file:///Volumes/my stick/backup",
-			want: &storage.URL{Scheme: fileScheme, Prefix: "/Volumes/my stick/backup"},
+			want: &storage.URL{Scheme: "file", Prefix: "/var/backups/vaultik"},
 		},
 		{
 			name: "s3 bucket and prefix, ssl defaults on",
@@ -103,7 +90,6 @@ func TestParseStorageURLErrors(t *testing.T) {
 	}{
 		{"empty url", "", storage.ErrEmptyStorageURL},
 		{"file empty path", "file://", storage.ErrEmptyFilePath},
-		{"file relative path", "file://dest", storage.ErrRelativeFilePath},
 		{"s3 missing bucket", "s3://", storage.ErrMissingBucket},
 		{"s3 missing bucket with path", "s3:///justprefix", storage.ErrMissingBucket},
 		{"rclone missing remote", "rclone://", storage.ErrMissingRemote},

internal/vaultik/restore_skip_errors_test.go

@@ -4,9 +4,7 @@ import (
 	"bytes"
 	"context"
 	"fmt"
-	"os"
 	"path/filepath"
-	"strings"
 	"testing"
 
 	"github.com/spf13/afero"
@@ -121,95 +119,6 @@ func TestRestoreSkipErrorsVerifyChecksOnlyRestoredFiles(t *testing.T) {
 	assert.NotContains(t, out.String(), "Verification failed")
 }
 
-// TestRestoreSkipErrorsVerifyReportsFailuresApart restores with
-// SkipErrors and Verify after one blob of a two-blob snapshot was
-// deleted, while one file that does restore is written one byte too long.
-// The restore warning must list only the files of the deleted blob, the
-// verification summary only the long file, each path once, and Restore
-// must return an error.
-func TestRestoreSkipErrorsVerifyReportsFailuresApart(t *testing.T) {
-	log.Initialize(log.Config{})
-	t.Parallel()
-
-	ctx := context.Background()
-	backup := backupThenDeleteOneBlob(ctx, t)
-
-	var long string
-
-	for path := range backup.files {
-		if !backup.lost[path] {
-			long = path
-
-			break
-		}
-	}
-
-	var out bytes.Buffer
-
-	fs := trailingByteFs{Fs: backup.fs, suffix: long}
-	v := newReaderVaultik(ctx, backup.cfg, backup.storer, nil, fs)
-	v.UI = ui.NewWithColor(&out, false)
-
-	err := v.Restore(&vaultik.RestoreOptions{
-		SnapshotID: backup.snapshotID,
-		TargetDir:  backup.restoreDir,
-		Verify:     true,
-		SkipErrors: true,
-	})
-	require.Error(t, err, "restore must fail when files failed")
-
-	_, afterWarning, found := strings.Cut(out.String(),
-		fmt.Sprintf("%d file(s) failed to restore:", len(backup.lost)))
-	require.Truef(t, found, "no restore warning in:\n%s", out.String())
-
-	warning, summary, found := strings.Cut(afterWarning,
-		"Verification failed: 1 files did not match")
-	require.Truef(t, found, "no verification summary in:\n%s", out.String())
-
-	for path := range backup.lost {
-		assert.Equalf(t, 1, strings.Count(warning, path),
-			"%s must be listed once as failed to restore", path)
-		assert.NotContainsf(t, summary, path,
-			"%s was not restored and must not fail verification", path)
-	}
-
-	assert.NotContainsf(t, warning, long,
-		"%s was restored and must not be listed as failed to restore", long)
-	assert.Equalf(t, 1, strings.Count(summary, long),
-		"%s must be listed once as failing verification", long)
-}
-
-// trailingByteFs appends one byte, on close, to the file it opens whose
-// path ends in suffix, so that file is restored one byte too long and
-// fails verification.
-type trailingByteFs struct {
-	afero.Fs
-
-	suffix string
-}
-
-//nolint:ireturn // afero.Fs.OpenFile is defined to return the interface
-func (fs trailingByteFs) OpenFile(
-	name string, flag int, perm os.FileMode,
-) (afero.File, error) {
-	f, err := fs.Fs.OpenFile(name, flag, perm)
-	if err != nil || !strings.HasSuffix(name, fs.suffix) {
-		return f, err
-	}
-
-	return trailingByteFile{File: f}, nil
-}
-
-type trailingByteFile struct {
-	afero.File
-}
-
-func (f trailingByteFile) Close() error {
-	_, _ = f.File.Write([]byte{'x'})
-
-	return f.File.Close()
-}
-
 // TestRestoreMissingBlobAbortsWithoutSkipErrors checks that a deleted blob
 // still ends the restore with an error when SkipErrors is not set.
 func TestRestoreMissingBlobAbortsWithoutSkipErrors(t *testing.T) {