Skip vaultik's own index and PID file in a backup (closes #421)

A backup of a directory that holds the local index stored a torn copy
of it, its -wal and -shm side files and vaultik.pid, all being written
while they were read. The scan now treats these files as excluded,
whatever the config says. Their paths come from index_path and the lock
directory, with symlinks in their directories resolved the way source
paths are. If index_path is itself a symlink, SQLite writes the file it
points to, so that file and its side files are skipped too. pidlock now
owns the lock directory and the PID file name, so the CLI and the
scanner use the same path.

Model: opus-5-5

internal/cli/app.go

@@ -7,11 +7,9 @@ import (
 	"context"
 	"errors"
 	"fmt"
-	"path/filepath"
 	"sync"
 	"time"
 
-	"github.com/adrg/xdg"
 	"github.com/spf13/cobra"
 	"go.uber.org/dig"
 	"go.uber.org/fx"
@@ -351,8 +349,7 @@ func runVaultikApp(
 // only one runs at a time; a read-only command runs without it and is not
 // blocked while a mutator holds the lock (opts.Mode).
 func RunWithApp(ctx context.Context, opts AppOptions) error {
-	release, err := acquireLockIfMutating(opts.Mode,
+	release, err := acquireLockIfMutating(opts.Mode, pidlock.Dir())
-		filepath.Join(xdg.DataHome, "vaultik"))
 	if err != nil {
 		return err
 	}

internal/cli/entry_snapshot_create_own_files_test.go

@@ -0,0 +1,69 @@
+package cli //nolint:testpackage // shares runEntry and the hermetic config helpers
+
+import (
+	"fmt"
+	"os"
+	"path/filepath"
+	"testing"
+
+	"github.com/adrg/xdg"
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+)
+
+// TestEntrySnapshotCreateSkipsOwnFiles backs up a directory that holds
+// vaultik's index and PID file beside one other file, with no exclude
+// pattern set. The summary counts only the other file. See
+// https://git.eeqj.de/sneak/vaultik/issues/421.
+//
+// Not parallel: it replaces os.Args, os.Stdout, os.Stderr and the xdg
+// globals.
+func TestEntrySnapshotCreateSkipsOwnFiles(t *testing.T) {
+	for _, testCase := range []struct {
+		name string
+		// linked sets index_path to a symlink outside the backed-up
+		// directory that points to the index inside it.
+		linked bool
+	}{
+		{name: "index in the backed-up directory"},
+		{name: "index_path links into the backed-up directory", linked: true},
+	} {
+		t.Run(testCase.name, func(t *testing.T) {
+			dir := t.TempDir()
+			configPath := filepath.Join(dir, "config.yml")
+			sourceDir := filepath.Join(dir, "source")
+			storeDir := filepath.Join(dir, "store")
+
+			indexPath := filepath.Join(sourceDir, "index.sqlite")
+
+			if testCase.linked {
+				link := filepath.Join(dir, "index.sqlite")
+				require.NoError(t, os.Symlink(indexPath, link))
+
+				indexPath = link
+			}
+
+			contents := fmt.Sprintf(hermeticConfig,
+				sourceDir, storeDir, indexPath)
+			require.NoError(t,
+				os.WriteFile(configPath, []byte(contents), configFileMode))
+			require.NoError(t, os.Mkdir(storeDir, 0o750))
+			require.NoError(t, os.Mkdir(sourceDir, 0o750))
+			require.NoError(t, os.WriteFile(
+				filepath.Join(sourceDir, "file.txt"), []byte("hello"), 0o600))
+
+			// The PID file goes in a directory under XDG_DATA_HOME, which
+			// xdg reads at package init.
+			t.Setenv("XDG_DATA_HOME", filepath.Join(sourceDir, "data"))
+			xdg.Reload()
+			t.Cleanup(xdg.Reload)
+
+			code, stdout, _ := runEntry(t,
+				flagConfig, configPath, cmdSnapshot, cmdCreate)
+
+			require.Equal(t, 0, code)
+			assert.Contains(t, stdout,
+				"Files: 1 examined, 1 backed up, 0 unchanged.")
+		})
+	}
+}

internal/database/module.go

@@ -20,6 +20,17 @@ const indexDirPerm = 0o700
 // backed-up path and chunk hash and must stay private.
 const indexFilePerm = 0o600
 
+// IndexFiles returns the path of the index at indexPath and the paths of
+// the side files SQLite keeps beside it while it writes.
+func IndexFiles(indexPath string) []string {
+	return []string{
+		indexPath,
+		indexPath + "-wal",
+		indexPath + "-shm",
+		indexPath + "-journal",
+	}
+}
+
 // ensureIndexFileMode makes the index file owner-only before the SQLite
 // driver opens it: it creates the file 0600 if absent, or chmods an existing
 // one to 0600. Doing this first matters because SQLite creates its -wal and

internal/pidlock/pidlock.go

@@ -11,6 +11,7 @@ import (
 	"strconv"
 	"strings"
 
+	"github.com/adrg/xdg"
 	"golang.org/x/sys/unix"
 )
 
@@ -29,8 +30,20 @@ const (
 	lockDirPerm = 0o700
 	// pidFilePerm is the mode for the PID file (owner-only).
 	pidFilePerm = 0o600
+	// pidFileName is the name of the PID file in the lock directory.
+	pidFileName = "vaultik.pid"
 )
 
+// Dir returns the directory that holds vaultik's PID file.
+func Dir() string {
+	return filepath.Join(xdg.DataHome, "vaultik")
+}
+
+// Path returns the path of the PID file that Acquire uses in lockDir.
+func Path(lockDir string) string {
+	return filepath.Join(lockDir, pidFileName)
+}
+
 // Acquire attempts to acquire a PID lock in the specified directory.
 // If another process holds the lock, it returns ErrAlreadyRunning with
 // that process's PID. On success, it writes the current PID to the lock
@@ -42,7 +55,7 @@ func Acquire(lockDir string) (*Lock, error) {
 		return nil, fmt.Errorf("creating lock directory: %w", err)
 	}
 
-	lockPath := filepath.Join(lockDir, "vaultik.pid")
+	lockPath := Path(lockDir)
 
 	// No O_TRUNC: the file may hold the PID of the process that has the
 	// lock, which the error below reports.

internal/snapshot/module.go

@@ -2,11 +2,13 @@ package snapshot
 
 import (
 	"os"
+	"path/filepath"
 
 	"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/pidlock"
 	"sneak.berlin/go/vaultik/internal/storage"
 	"sneak.berlin/go/vaultik/internal/ui"
 )
@@ -62,9 +64,51 @@ func provideScannerFactory(
 			EnableProgress:     params.EnableProgress,
 			UI:                 params.UI,
 			Exclude:            excludes,
+			OwnFiles:           ownFiles(cfg.IndexPath, pidlock.Dir()),
 			SkipErrors:         params.SkipErrors,
 			PreviousSnapshotID: params.PreviousSnapshotID,
 			DeviceNumber:       params.DeviceNumber,
 		})
 	}
 }
+
+// ownFiles returns the paths of the index at indexPath, its side files
+// and the PID file in lockDir. Symlinks in their directories are resolved,
+// as they are in the snapshot's source paths, so the scan finds them under
+// the same names. If indexPath is a symlink, the file it points to and
+// that file's side files are returned too.
+func ownFiles(indexPath, lockDir string) []string {
+	paths := append(database.IndexFiles(indexPath), pidlock.Path(lockDir))
+	for i, p := range paths {
+		paths[i] = resolveDir(p)
+	}
+
+	// SQLite writes the file a symlinked index points to and keeps the
+	// side files beside that file. The database package creates the index
+	// before the scanner is built, so the link resolves.
+	index := resolveDir(indexPath)
+
+	target, err := filepath.EvalSymlinks(index)
+	if err == nil && target != index {
+		paths = append(paths, database.IndexFiles(target)...)
+	}
+
+	return paths
+}
+
+// resolveDir returns the absolute form of path with the symlinks in its
+// directory resolved. If the directory cannot be resolved, it returns the
+// absolute form unresolved. If path has no absolute form, it returns path.
+func resolveDir(path string) string {
+	abs, err := filepath.Abs(path)
+	if err != nil {
+		return path
+	}
+
+	dir, err := filepath.EvalSymlinks(filepath.Dir(abs))
+	if err != nil {
+		return abs
+	}
+
+	return filepath.Join(dir, filepath.Base(abs))
+}

internal/snapshot/module_test.go

@@ -0,0 +1,32 @@
+//nolint:testpackage // exercises the unexported ownFiles helper
+package snapshot
+
+import (
+	"os"
+	"path/filepath"
+	"testing"
+
+	"github.com/stretchr/testify/require"
+)
+
+// The scan walks source paths with symlinks resolved, so vaultik's own
+// files are named the same way, or a symlinked home would back them up.
+func TestOwnFilesResolvesSymlinkedDirectory(t *testing.T) {
+	t.Parallel()
+
+	realDir, err := filepath.EvalSymlinks(t.TempDir())
+	require.NoError(t, err)
+
+	link := filepath.Join(t.TempDir(), "link")
+	require.NoError(t, os.Symlink(realDir, link))
+
+	paths := ownFiles(filepath.Join(link, "index.sqlite"), link)
+
+	require.Equal(t, []string{
+		filepath.Join(realDir, "index.sqlite"),
+		filepath.Join(realDir, "index.sqlite-wal"),
+		filepath.Join(realDir, "index.sqlite-shm"),
+		filepath.Join(realDir, "index.sqlite-journal"),
+		filepath.Join(realDir, "vaultik.pid"),
+	}, paths)
+}

internal/snapshot/own_files_test.go

@@ -0,0 +1,65 @@
+package snapshot_test
+
+import (
+	"context"
+	"testing"
+
+	"github.com/spf13/afero"
+	"github.com/stretchr/testify/require"
+	"sneak.berlin/go/vaultik/internal/database"
+	"sneak.berlin/go/vaultik/internal/snapshot"
+)
+
+// A backup of the directory that holds vaultik's index and PID file
+// stores neither, with no exclude pattern set, and still stores the
+// files beside them. See https://git.eeqj.de/sneak/vaultik/issues/421.
+func TestScanSkipsOwnFiles(t *testing.T) {
+	t.Parallel()
+
+	const dataDir = "/home/user/.local/share/vaultik"
+
+	ownFiles := append(database.IndexFiles(dataDir+"/index.sqlite"),
+		dataDir+"/vaultik.pid")
+
+	fs := afero.NewMemMapFs()
+	for _, p := range append(ownFiles, dataDir+"/notes.txt") {
+		require.NoError(t, afero.WriteFile(fs, p, []byte("data"), 0o600))
+	}
+
+	db, err := database.NewTestDB()
+	require.NoError(t, err)
+
+	defer func() { _ = db.Close() }()
+
+	repos := database.NewRepositories(db)
+
+	scanner := snapshot.NewScanner(snapshot.ScannerConfig{
+		FS:               fs,
+		ChunkSize:        64 * 1024,
+		Repositories:     repos,
+		MaxBlobSize:      1024 * 1024,
+		CompressionLevel: 3,
+		AgeRecipients: []string{
+			"age1ql3z7hjy54pw3hyww5ayyfg7zqgvc7w3j2elw8zmrj2kg5sfn9aqmcac8p"},
+		OwnFiles: ownFiles,
+	})
+	require.NotNil(t, scanner)
+
+	ctx := context.Background()
+	createSnapshotRecord(ctx, t, repos, "test-snapshot")
+
+	result, err := scanner.Scan(ctx, "/home/user", "test-snapshot")
+	require.NoError(t, err)
+
+	require.Equal(t, 1, result.FilesScanned)
+
+	stored, err := repos.Files.GetByPath(ctx, dataDir+"/notes.txt")
+	require.NoError(t, err)
+	require.NotNil(t, stored, "a file beside the index is stored")
+
+	for _, p := range ownFiles {
+		f, err := repos.Files.GetByPath(ctx, p)
+		require.NoError(t, err)
+		require.Nil(t, f, "%s is not stored", p)
+	}
+}

internal/snapshot/scanner.go

@@ -67,7 +67,10 @@ type Scanner struct {
 	currentSourcePath string
 	exclude           []string          // Glob patterns for files/directories to exclude
 	compiledExclude   []compiledPattern // Compiled glob patterns
-	progress          *ProgressReporter
+	// ownFiles holds the paths of vaultik's own working files, which the
+	// scan treats as excluded (ScannerConfig.OwnFiles).
+	ownFiles map[string]struct{}
+	progress *ProgressReporter
 	// skipErrors skips files that cannot be opened or read (logged loudly);
 	// packer, database, encryption, and upload errors still abort the run.
 	skipErrors bool
@@ -133,6 +136,11 @@ type ScannerConfig struct {
 	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
+	// OwnFiles are the absolute paths of vaultik's own working files: the
+	// index, its side files and the PID file. The scan treats them as
+	// excluded, whatever Exclude says, since a copy taken while they are
+	// being written is torn.
+	OwnFiles []string
 	// SkipErrors skips files that cannot be opened or read (log loudly but
 	// continue); packer, database, encryption, and upload errors still abort.
 	SkipErrors bool
@@ -226,6 +234,11 @@ func NewScanner(cfg ScannerConfig) *Scanner {
 		deviceNumber = deviceNumberFromStat
 	}
 
+	ownFiles := make(map[string]struct{}, len(cfg.OwnFiles))
+	for _, p := range cfg.OwnFiles {
+		ownFiles[filepath.Clean(p)] = struct{}{}
+	}
+
 	return &Scanner{
 		fs:                 cfg.FS,
 		chunker:            chunker.NewChunker(cfg.ChunkSize),
@@ -237,6 +250,7 @@ func NewScanner(cfg ScannerConfig) *Scanner {
 		ageRecipient:       strings.Join(cfg.AgeRecipients, ","),
 		exclude:            cfg.Exclude,
 		compiledExclude:    compiledExclude,
+		ownFiles:           ownFiles,
 		progress:           progress,
 		skipErrors:         cfg.SkipErrors,
 		previousSnapshotID: cfg.PreviousSnapshotID,
@@ -2248,8 +2262,9 @@ func (s *Scanner) detectDeletedFiles(
 
 // excludedOrInExcludedDir reports whether filePath, which is at or
 // beneath rootPath, or any directory between rootPath and it, matches an
-// exclude pattern. A pattern such as */.local/share/Trash matches the
+// exclude pattern or is one of vaultik's own files. A pattern such as
-// directory but not the files inside it, which the walk skips too.
+// */.local/share/Trash matches the directory but not the files inside it,
+// which the walk skips too.
 func (s *Scanner) excludedOrInExcludedDir(filePath, rootPath string) bool {
 	for p := filePath; len(p) > len(rootPath); p = filepath.Dir(p) {
 		if s.shouldExclude(p, rootPath) {
@@ -2373,9 +2388,14 @@ func doubleStarVariants(pattern string) []string {
 }
 
 // shouldExclude checks if a path should be excluded based on exclude patterns
+// or because it is one of vaultik's own working files.
 // filePath is the full path to the file
 // rootPath is the root of the backup source directory
 func (s *Scanner) shouldExclude(filePath, rootPath string) bool {
+	if _, own := s.ownFiles[filePath]; own {
+		return true
+	}
+
 	if len(s.compiledExclude) == 0 {
 		return false
 	}