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

A database at user_version 0 that already has a files table was not
created by sfdupes: a foreign or partially initialized file. scan used
to run its CREATE TABLE on it and fail with a raw SQLite error, and
report and trees gave only a bare version mismatch. All three now
check for a files table at version 0 and refuse such a database with
the schema-version error telling the operator to remove the file and
rescan. A genuinely empty database is unchanged: scan creates the
schema, report and trees refuse it as before.

Model: opus-4-8 (implementation); opus-5-5 (rebase)

README.md

@@ -209,7 +209,10 @@ All three subcommands operate on a single SQLite database file:
     `-shm` files beside it, which SQLite creates with the database
     file's permissions.
 -   Schema (`PRAGMA user_version` is the schema version, currently 1; a
-    database with any other version is a fatal error):
+    database with any other version is a fatal error. A database at
+    version 0 that already has a `files` table was not made by sfdupes;
+    every subcommand refuses it with an error telling the user to remove
+    the file and rescan):
 
     ```sql
     CREATE TABLE files (

TODO.md

@@ -29,6 +29,10 @@
 
 # Completed Steps
 
+- refuse an unversioned database that already has a `files` table with
+  a clear schema-version error (2026-10-04,
+  https://git.eeqj.de/sneak/sfdupes/issues/11)
+
 - the `Dockerfile` build stage keeps the Go module cache out of `builder`'s
   home and copies the sources with `--chown`, so no `chown -R` walks them
   (2026-10-04, https://git.eeqj.de/sneak/sfdupes/issues/43)

db.go

@@ -219,6 +219,12 @@ func openReportDatabase(ctx context.Context,
 	}
 
 	v, err := userVersion(ctx, db)
+	if err == nil && v == 0 {
+		// An empty database passes this check and fails the version
+		// check below.
+		err = checkUnversioned(ctx, db)
+	}
+
 	if err != nil {
 		_ = db.Close()
 
@@ -245,6 +251,11 @@ func initSchema(ctx context.Context, db *sql.DB) error {
 
 	switch v {
 	case 0:
+		err = checkUnversioned(ctx, db)
+		if err != nil {
+			return err
+		}
+
 		return createSchema(ctx, db)
 	case schemaVersion:
 		return nil
@@ -254,6 +265,31 @@ func initSchema(ctx context.Context, db *sql.DB) error {
 	}
 }
 
+// checkUnversioned checks a database at user_version 0 before it is
+// taken for an empty one. A database that already has a files table
+// was not created by this build: a foreign or partially initialized
+// file. Adopting it could corrupt unrelated data, so that is a
+// schema-version error telling the operator to remove the file and
+// rescan.
+func checkUnversioned(ctx context.Context, db *sql.DB) error {
+	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):
+		return nil
+	default:
+		return fmt.Errorf("check for files table: %w", err)
+	}
+}
+
 // createSchema applies the schema to a fresh database and stamps the
 // schema version.
 func createSchema(ctx context.Context, db *sql.DB) error {

db_test.go

@@ -8,6 +8,7 @@ import (
 	"os"
 	"path/filepath"
 	"slices"
+	"strings"
 	"testing"
 )
 
@@ -77,6 +78,42 @@ func TestOpenScanDatabaseCreates(t *testing.T) {
 	}
 }
 
+func TestOpenDatabaseUnversionedForeign(t *testing.T) {
+	t.Parallel()
+
+	// A database that has a files table but user_version 0, written by
+	// some other tool. report, trees and scan must refuse it with the
+	// schema-version error, not adopt it and not emit a raw SQLite
+	// "table files already exists".
+	path := testDBPath(t)
+
+	db, err := sql.Open("sqlite", 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 = openReportDatabase(t.Context(), path)
+	if !errors.Is(err, errSchemaVersion) ||
+		!strings.Contains(err.Error(), "remove the file and rescan") {
+		t.Fatalf("report: err = %v, want errSchemaVersion telling the "+
+			"operator to remove the file and rescan", err)
+	}
+
+	_, err = openScanDatabase(t.Context(), path)
+	if !errors.Is(err, errSchemaVersion) ||
+		!strings.Contains(err.Error(), "remove the file and rescan") {
+		t.Fatalf("scan: err = %v, want errSchemaVersion telling the "+
+			"operator to remove the file and rescan", err)
+	}
+}
+
 func TestOpenReportDatabaseMissing(t *testing.T) {
 	t.Parallel()