Refuse an unversioned database that already has a files table (closes #11)

An unversioned database (user_version 0) that already contains a files
table was not created by this build; it is a foreign or partially
initialized file. Adopting it silently could corrupt unrelated data, so
createSchema now checks for a files table first and, when one exists,
returns the schema-version error telling the operator to remove the file
and rescan. A genuinely empty database is still created and stamped as
before.

Model: opus-4-8

.dockerignore

@@ -2,7 +2,6 @@
 .claude
 .DS_Store
 sfdupes
-files.dat
 *.log
 *.out
 *.test

.gitignore

@@ -27,7 +27,6 @@ node_modules/
 *.log
 
 # Local scan data
-files.dat
 *.sqlite
 *.sqlite-shm
 *.sqlite-wal

Makefile

@@ -46,4 +46,4 @@ hooks:
 	@script/install-precommit
 
 clean:
-	rm -f $(BINARY) files.dat
+	rm -f $(BINARY)

TODO.md

@@ -29,11 +29,13 @@
 
 # Completed Steps
 
-- test the `-x` filesystem-boundary rejection branch by calling
-  `subdirJob` directly: reject across a boundary, bypass when the root
-  device is unknown, stat-error warning, and default crossing
-  (2026-09-21, branch `next`, closes
-  https://git.eeqj.de/sneak/sfdupes/issues/17)
+- refuse an unversioned database that already has a `files` table with
+  a clear schema-version error (2026-09-21, closes
+  https://git.eeqj.de/sneak/sfdupes/issues/11)
+
+- remove the dead `files.dat` references from `Makefile`, `.gitignore`
+  and `.dockerignore` (2026-09-21, branch `next`, closes
+  https://git.eeqj.de/sneak/sfdupes/issues/22)
 
 - fix the lint-image pin comments and `FROM` form in `Dockerfile` and
   `Dockerfile.lint` (2026-08-10, branch `next`, closes

db.go

@@ -174,9 +174,30 @@ func initSchema(ctx context.Context, db *sql.DB) error {
 }
 
 // createSchema applies the schema to a fresh database and stamps the
-// schema version.
+// schema version. A database with user_version 0 that already has a
+// files table was not created by this build — a foreign or partially
+// initialized file. Adopting it silently could corrupt unrelated data,
+// so that is a fatal schema-version error telling the operator to
+// remove the file and rescan.
 func createSchema(ctx context.Context, db *sql.DB) error {
-	_, err := db.ExecContext(ctx, createTableSQL)
+	var name string
+
+	err := db.QueryRowContext(ctx,
+		"SELECT name FROM sqlite_master "+
+			"WHERE type = 'table' AND name = 'files'").Scan(&name)
+
+	switch {
+	case err == nil:
+		return fmt.Errorf(
+			"has a files table but no schema version; "+
+				"remove the file and rescan: %w", errSchemaVersion)
+	case errors.Is(err, sql.ErrNoRows):
+		// Genuinely empty: create the schema below.
+	default:
+		return fmt.Errorf("check for files table: %w", err)
+	}
+
+	_, err = db.ExecContext(ctx, createTableSQL)
 	if err != nil {
 		return fmt.Errorf("create schema: %w", err)
 	}

db_test.go

@@ -78,6 +78,38 @@ func TestOpenScanDatabaseCreates(t *testing.T) {
 	}
 }
 
+func TestOpenScanDatabaseUnversionedForeign(t *testing.T) {
+	t.Parallel()
+
+	path := testDBPath(t)
+
+	// A database that has a files table but user_version 0 — a foreign
+	// or partially initialized file. scan must refuse it with a clear
+	// schema-version error, not adopt it and not emit a raw SQLite
+	// "table files already exists".
+	db, err := openDB(path)
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	_, err = db.ExecContext(t.Context(), "CREATE TABLE files (x INTEGER)")
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	_ = db.Close()
+
+	_, err = openScanDatabase(t.Context(), path)
+	if !errors.Is(err, errSchemaVersion) {
+		t.Fatalf("err = %v, want errSchemaVersion", err)
+	}
+
+	if !strings.Contains(err.Error(), "remove the file and rescan") {
+		t.Fatalf("err = %v, want it to tell the operator to remove and rescan",
+			err)
+	}
+}
+
 func TestOpenReportDatabaseMissing(t *testing.T) {
 	t.Parallel()
 

scan_test.go

@@ -6,9 +6,7 @@ import (
 	"crypto/sha256"
 	"database/sql"
 	"encoding/hex"
-	"errors"
 	"fmt"
-	"io/fs"
 	"os"
 	"path/filepath"
 	"runtime"
@@ -326,152 +324,6 @@ func TestDeviceOfInfo(t *testing.T) {
 	}
 }
 
-// dirEntryFor returns the fs.DirEntry for name within dir, obtained via
-// the same os.ReadDir the walk uses, so it carries a real Info().
-func dirEntryFor(t *testing.T, dir, name string) fs.DirEntry {
-	t.Helper()
-
-	entries, err := os.ReadDir(dir)
-	if err != nil {
-		t.Fatal(err)
-	}
-
-	for _, e := range entries {
-		if e.Name() == name {
-			return e
-		}
-	}
-
-	t.Fatalf("entry %q not found in %q", name, dir)
-
-	return nil
-}
-
-// callSubdirJob runs subdirJob against e under parent, collecting any
-// warning events it emits (subdirJob emits at most one).
-func callSubdirJob(t *testing.T, p string, e fs.DirEntry,
-	parent dirJob, oneFS bool,
-) (dirJob, bool, []walkEvent) {
-	t.Helper()
-
-	events := make(chan walkEvent, 1)
-	job, ok := subdirJob(t.Context(), p, e, parent, oneFS, events)
-	close(events)
-
-	var evs []walkEvent
-	for ev := range events {
-		evs = append(evs, ev)
-	}
-
-	return job, ok, evs
-}
-
-// TestSubdirJobOneFilesystem exercises the -x boundary check in
-// subdirJob directly, so no second real filesystem is needed. The
-// subdirectory's real device is compared against a fabricated operand
-// device.
-func TestSubdirJobOneFilesystem(t *testing.T) {
-	t.Parallel()
-
-	dir := t.TempDir()
-
-	sub := filepath.Join(dir, "sub")
-
-	err := os.Mkdir(sub, 0o750)
-	if err != nil {
-		t.Fatal(err)
-	}
-
-	info, err := os.Lstat(sub)
-	if err != nil {
-		t.Fatal(err)
-	}
-
-	dev, ok := deviceOfInfo(info)
-	if !ok {
-		t.Skip("platform exposes no device id")
-	}
-
-	// A device the subdirectory is not on, standing in for an operand
-	// rooted on a different filesystem.
-	otherDev := dev + 1
-	e := dirEntryFor(t, dir, "sub")
-
-	cases := []struct {
-		name   string
-		oneFS  bool
-		parent dirJob
-		wantOK bool
-	}{
-		// -x on, subdirectory on a different device than its operand:
-		// descent is refused.
-		{"reject across boundary", true,
-			dirJob{rootDev: otherDev, rootDevOK: true}, false},
-		// -x on but the operand's own device is unknown: the boundary
-		// check is bypassed and descent proceeds.
-		{"bypass when root device unknown", true,
-			dirJob{rootDev: otherDev, rootDevOK: false}, true},
-		// Default (no -x): boundaries are crossed even onto a different
-		// device.
-		{"cross by default", false,
-			dirJob{rootDev: otherDev, rootDevOK: true}, true},
-	}
-
-	for _, tc := range cases {
-		t.Run(tc.name, func(t *testing.T) {
-			t.Parallel()
-
-			job, ok, evs := callSubdirJob(t, sub, e, tc.parent, tc.oneFS)
-			if ok != tc.wantOK {
-				t.Fatalf("accepted = %v, want %v", ok, tc.wantOK)
-			}
-
-			if len(evs) != 0 {
-				t.Fatalf("unexpected events: %+v", evs)
-			}
-
-			if ok && job.path != sub {
-				t.Fatalf("job.path = %q, want %q", job.path, sub)
-			}
-		})
-	}
-}
-
-// errInfoUnavailable is returned by errDirEntry.Info().
-var errInfoUnavailable = errors.New("info unavailable")
-
-// errDirEntry is a directory entry whose Info() always fails, driving
-// subdirJob's stat-error branch deterministically.
-type errDirEntry struct{ name string }
-
-func (e errDirEntry) Name() string { return e.name }
-func (errDirEntry) IsDir() bool    { return true }
-func (errDirEntry) Type() fs.FileMode {
-	return fs.ModeDir
-}
-
-func (errDirEntry) Info() (fs.FileInfo, error) {
-	return nil, errInfoUnavailable
-}
-
-// TestSubdirJobStatError asserts that when a subdirectory's Info()
-// fails under -x, subdirJob warns and refuses descent.
-func TestSubdirJobStatError(t *testing.T) {
-	t.Parallel()
-
-	p := "/does/not/matter/sub"
-
-	_, ok, evs := callSubdirJob(t, p, errDirEntry{name: "sub"},
-		dirJob{rootDev: 1, rootDevOK: true}, true)
-	if ok {
-		t.Fatal("descent accepted after stat error, want refused")
-	}
-
-	if len(evs) != 1 || !evs[0].fail || !strings.Contains(evs[0].warn, p) {
-		t.Fatalf("want one warning naming the path, got %+v", evs)
-	}
-}
-
 // buildSmokeTree recreates the README smoke-test filesystem layout
 // with deterministic content and returns the tree root.
 func buildSmokeTree(t *testing.T) string {