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

Dockerfile

@@ -1,6 +1,6 @@
 # Lint stage — fast feedback on formatting and lint issues
-# golangci/golangci-lint:v2.12.2 (Debian-based), 2026-08-07
-FROM golangci/golangci-lint:v2.12.2@sha256:5cceeef04e53efe1470638d4b4b4f5ceefd574955ab3941b2d9a68a8c9ad5240 AS lint
+# golangci/golangci-lint:v2.12.2, 2026-08-07
+FROM golangci/golangci-lint@sha256:5cceeef04e53efe1470638d4b4b4f5ceefd574955ab3941b2d9a68a8c9ad5240 AS lint
 WORKDIR /src
 COPY go.mod go.sum ./
 RUN go mod download

Dockerfile.lint

@@ -9,8 +9,8 @@
 # stage of the main Dockerfile because script/lint must not depend on
 # the rest of that build; the two FROM lines are kept identical by
 # script/verify-lint-image-pin, run as a gate below.
-# golangci/golangci-lint:v2.12.2 (Debian-based), 2026-08-07
-FROM golangci/golangci-lint:v2.12.2@sha256:5cceeef04e53efe1470638d4b4b4f5ceefd574955ab3941b2d9a68a8c9ad5240
+# golangci/golangci-lint:v2.12.2, 2026-08-07
+FROM golangci/golangci-lint@sha256:5cceeef04e53efe1470638d4b4b4f5ceefd574955ab3941b2d9a68a8c9ad5240
 
 WORKDIR /src
 

Makefile

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

TODO.md

@@ -29,6 +29,26 @@
 
 # Completed Steps
 
+- 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
+  https://git.eeqj.de/sneak/sfdupes/issues/25): dropped the false
+  `(Debian-based)` parenthetical (v2.12.1 was Debian too) and the
+  redundant tag, so both pins are the policy `# image:vX.Y.Z,
+  YYYY-MM-DD` comment over a bare `FROM image@sha256:...`. Digest
+  unchanged. `script/verify-lint-image-pin` parses those `FROM` lines
+  and still matches the tagless form; its advice line lost the now
+  meaningless "tag and digest". With no tag in either reference, a
+  tag-only disagreement no longer exists — a one-sided tag is caught as
+  a plain mismatch.
+
 - run all linting in Docker via `Dockerfile.lint` and `script/lint`
   (2026-08-10, branch `next`, closes
   https://git.eeqj.de/sneak/sfdupes/issues/46): per the owner ruling, the

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()
 

script/verify-lint-image-pin

@@ -71,9 +71,9 @@ main() {
             "the two pins disagree:" >&2
         echo "verify-lint-image-pin:   $LINT_DOCKERFILE: $lint_ref" >&2
         echo "verify-lint-image-pin:   $MAIN_DOCKERFILE: $main_ref" >&2
-        echo "verify-lint-image-pin: bump both FROM lines together, tag and" \
-            "digest, so script/lint and the Dockerfile lint stage keep" \
-            "running the same linter" >&2
+        echo "verify-lint-image-pin: bump both FROM lines together so" \
+            "script/lint and the Dockerfile lint stage keep running the" \
+            "same linter" >&2
         exit 1
     fi