Test report and trees stdout write failures (closes #30)

report and trees already checked every stdout write and the final
flush. run now takes the stdout it hands to them, so tests pass a
closed file or a failing writer instead of swapping os.Stdout: a
closed stdout exits 1 with a one-line diagnostic, and the writer's
error reaches the caller.

README "Error handling" now states the two cases that never reach
sfdupes as a failed write: a pipe reader that exits early ends the
process with SIGPIPE, as with cat; and stdout closed with >&- is
replaced by /dev/null by the Go runtime before main runs, so the run
succeeds.

Model: opus-5-5

README.md

@@ -152,28 +152,16 @@ All three subcommands operate on a single SQLite database file:
     use. `report` and `trees` require an existing database; a missing
     database file is a fatal error (exit 1) telling the user to run
     `scan` first.
--   While `scan` runs, the database is in WAL journal mode with a busy
-    timeout, so running a report while a cron `scan` is in progress is
-    safe. The filesystem is authoritative; the database is an
-    eventually-consistent reflection of it. Hashed records are
-    committed in batched transactions while the scan is still running
-    (keeping the WAL small and letting concurrent reports observe
-    progress), so a report may see a scan's changes partially applied,
-    and a scan that dies partway leaves a valid database holding
-    everything hashed so far; the next scan skips those records and
-    converges toward the filesystem.
--   `scan` switches the database back to rollback-journal mode when it
-    closes it, so between scans the database file alone holds the whole
-    database. Each switch needs the database to itself: a `scan` that
-    starts while a report is still reading waits for it up to the
-    10-second busy timeout, then fails; a `scan` that ends while a
-    report has the database open warns and leaves the database in WAL
-    mode until the next scan.
--   `report` and `trees` open the database read-only and need only read
-    access to the database file, and no write access to its directory.
-    While the database is in WAL mode they also read the `-wal` and
-    `-shm` files beside it, which SQLite creates with the database
-    file's permissions.
+-   The database uses WAL journal mode and a busy timeout, so running a
+    report while a cron `scan` is in progress is safe. The filesystem
+    is authoritative; the database is an eventually-consistent
+    reflection of it. Hashed records are committed in batched
+    transactions while the scan is still running (keeping the WAL
+    small and letting concurrent reports observe progress), so a
+    report may see a scan's changes partially applied, and a scan
+    that dies partway leaves a valid database holding everything
+    hashed so far; the next scan skips those records and converges
+    toward the filesystem.
 -   Schema (`PRAGMA user_version` is the schema version, currently 1; a
     database with any other version is a fatal error):
 
@@ -573,6 +561,18 @@ Additional requirements:
 -   `2`: usage error (including `scan` with no `PATH` operand and
     `report`/`trees` with any positional argument).
 
+A stdout write failure, such as a full disk, is reported in one line on
+stderr and exits 1. Two cases never reach sfdupes as a failed write:
+
+-   When the reader of a stdout pipe exits early, as in
+    `sfdupes report | head`, the next write ends sfdupes with `SIGPIPE`,
+    quietly and without a summary, the way `cat` or `sort` end. The
+    shell reports the signal (status 141 in most shells), not exit 1.
+-   When stdout is closed outright (`sfdupes report >&-`), the Go
+    runtime opens `/dev/null` in its place before sfdupes starts, so
+    the output is discarded and the run succeeds, as with
+    `> /dev/null`.
+
 ## Entrypoints
 
 This repository adheres to the

TODO.md

@@ -29,9 +29,9 @@
 
 # Completed Steps
 
-- `report` and `trees` open the database read-only, and `scan` leaves it
-  out of WAL mode, so reading needs only read access (2026-10-03, closes
-  https://git.eeqj.de/sneak/sfdupes/issues/8)
+- test stdout write failures in `report` and `trees`; README states that
+  `| head` ends sfdupes by `SIGPIPE` and `>&-` writes to `/dev/null`
+  (2026-10-03, https://git.eeqj.de/sneak/sfdupes/issues/30)
 
 - escape tabs, newlines, carriage returns and backslashes in report,
   trees and warning paths; the root directory's path is `/`

db.go

@@ -74,24 +74,16 @@ func databasePath() string {
 	return defaultDatabasePath
 }
 
-// scanParams are the connection parameters for scan: read-write, with
-// WAL journaling and a busy timeout, so a report can run while a cron
-// scan is in progress. closeScanDatabase leaves WAL mode again.
-const scanParams = "_pragma=busy_timeout(10000)" +
-	"&_pragma=journal_mode(WAL)" +
-	"&_pragma=synchronous(NORMAL)"
+// openDB opens the SQLite database at path with WAL journaling and a
+// busy timeout, so a report can run while a cron scan is in progress.
+// It does not create or verify the schema.
+func openDB(path string) (*sql.DB, error) {
+	dsn := "file:" + path +
+		"?_pragma=busy_timeout(10000)" +
+		"&_pragma=journal_mode(WAL)" +
+		"&_pragma=synchronous(NORMAL)"
 
-// reportParams are the connection parameters for report and trees:
-// read-only, with the same busy timeout. They set no journal mode,
-// because setting one is a write.
-const reportParams = "mode=ro" +
-	"&_pragma=busy_timeout(10000)" +
-	"&_pragma=query_only(1)"
-
-// openDB opens the SQLite database at path with the connection
-// parameters params. It does not create or verify the schema.
-func openDB(path, params string) (*sql.DB, error) {
-	db, err := sql.Open("sqlite", "file:"+path+"?"+params)
+	db, err := sql.Open("sqlite", dsn)
 	if err != nil {
 		return nil, fmt.Errorf("open database %s: %w", path, err)
 	}
@@ -112,7 +104,7 @@ func openScanDatabase(ctx context.Context, path string) (*sql.DB, error) {
 		return nil, fmt.Errorf("create database directory: %w", err)
 	}
 
-	db, err := openDB(path, scanParams)
+	db, err := openDB(path)
 	if err != nil {
 		return nil, err
 	}
@@ -127,24 +119,6 @@ func openScanDatabase(ctx context.Context, path string) (*sql.DB, error) {
 	return db, nil
 }
 
-// closeScanDatabase switches the database at path from WAL back to
-// rollback-journal mode and closes it. Out of WAL mode the database
-// file alone holds the whole database, so a reader needs no -wal or
-// -shm file beside it, nor write access to create them. The switch
-// fails while a report has the database open; the database then stays
-// in WAL mode, still readable, until a later scan closes it.
-func closeScanDatabase(ctx context.Context, db *sql.DB, path string) {
-	// Runs on the way out of a cancelled scan too.
-	_, err := db.ExecContext(context.WithoutCancel(ctx),
-		"PRAGMA journal_mode = DELETE")
-	if err != nil {
-		fmt.Fprintf(os.Stderr, "scan: database %s left in WAL mode: %v\n",
-			path, err)
-	}
-
-	_ = db.Close()
-}
-
 // openReportDatabase opens an existing database for the report and
 // trees subcommands. A missing database file is an error directing the
 // user to run scan first; the schema version must match exactly.
@@ -160,7 +134,7 @@ func openReportDatabase(ctx context.Context,
 		return nil, fmt.Errorf("database: %w", err)
 	}
 
-	db, err := openDB(path, reportParams)
+	db, err := openDB(path)
 	if err != nil {
 		return nil, err
 	}

db_test.go

@@ -5,7 +5,6 @@ import (
 	"database/sql"
 	"errors"
 	"fmt"
-	"os"
 	"path/filepath"
 	"slices"
 	"strings"
@@ -131,49 +130,6 @@ func TestOpenReportDatabaseOK(t *testing.T) {
 	_ = db.Close()
 }
 
-func TestCloseScanDatabaseWhileReportOpen(t *testing.T) {
-	t.Parallel()
-
-	// A report holding the database open stops scan from taking it out
-	// of WAL mode. The -wal and -shm files must then stay beside it, so
-	// that a later report still needs only read access.
-	path := testDBPath(t)
-
-	scanDB, err := openScanDatabase(t.Context(), path)
-	if err != nil {
-		t.Fatal(err)
-	}
-
-	reportDB, err := openReportDatabase(t.Context(), path)
-	if err != nil {
-		t.Fatal(err)
-	}
-
-	closeScanDatabase(t.Context(), scanDB, path)
-
-	_ = reportDB.Close()
-
-	_, err = os.Stat(path + "-wal")
-	if err != nil {
-		t.Fatalf("no -wal left: the switch out of WAL mode was not "+
-			"stopped: %v", err)
-	}
-
-	makeReadOnly(t, path)
-
-	reportDB, err = openReportDatabase(t.Context(), path)
-	if err != nil {
-		t.Fatalf("openReportDatabase: %v", err)
-	}
-
-	defer func() { _ = reportDB.Close() }()
-
-	_, err = loadFileRows(t.Context(), reportDB)
-	if err != nil {
-		t.Fatalf("loadFileRows: %v", err)
-	}
-}
-
 func TestApplyChangesRoundTrip(t *testing.T) {
 	t.Parallel()
 

main.go

@@ -57,22 +57,27 @@ var errNoSubcommand = errors.New("no subcommand")
 var Version = "dev"
 
 func main() {
-	os.Exit(run(os.Args[1:], os.Stderr))
+	// Once the reader of a stdout pipe has gone, as in "sfdupes report |
+	// head", the Go runtime ends the process with SIGPIPE on the next
+	// write instead of returning an error (README "Error handling").
+	// Registering for SIGPIPE with os/signal would change that.
+	os.Exit(run(os.Args[1:], os.Stdout, os.Stderr))
 }
 
 // run executes args against the command tree and returns the process
 // exit code. It is the program's single exit point: the subcommands
 // return their errors instead of exiting, so every deferred cleanup —
 // above all closing the database, which checkpoints the SQLite WAL —
-// runs before the process ends.
-func run(args []string, stderr io.Writer) int {
+// runs before the process ends. The report and trees subcommands write
+// their data to stdout.
+func run(args []string, stdout, stderr io.Writer) int {
 	// A nil slice makes cobra fall back to os.Args, which would let a
 	// test binary's own flags reach the command tree.
 	if args == nil {
 		args = []string{}
 	}
 
-	root := newRootCommand(stderr)
+	root := newRootCommand(stdout, stderr)
 	root.SetArgs(args)
 
 	err := root.Execute()
@@ -98,7 +103,7 @@ func run(args []string, stderr io.Writer) int {
 // newRootCommand builds the command tree. Everything on stdout is
 // machine-readable data; all human-facing output (help, usage, errors)
 // goes to stderr.
-func newRootCommand(stderr io.Writer) *cobra.Command {
+func newRootCommand(stdout, stderr io.Writer) *cobra.Command {
 	root := &cobra.Command{
 		Use:     "sfdupes",
 		Short:   "Find candidate duplicate files by size and head/tail/content SHA-256",
@@ -140,7 +145,7 @@ func newRootCommand(stderr io.Writer) *cobra.Command {
 		Short: "Read the scan database and print the file-level duplicates report",
 		Args:  cobra.NoArgs,
 		RunE: runE(func(ctx context.Context, _ []string) error {
-			return runReport(ctx)
+			return runReport(ctx, stdout)
 		}),
 	}
 
@@ -149,7 +154,7 @@ func newRootCommand(stderr io.Writer) *cobra.Command {
 		Short: "Read the scan database and print the duplicate-tree report",
 		Args:  cobra.NoArgs,
 		RunE: runE(func(ctx context.Context, _ []string) error {
-			return runTrees(ctx)
+			return runTrees(ctx, stdout)
 		}),
 	}
 

main_test.go

@@ -44,98 +44,16 @@ func assertNoSidecars(t *testing.T, path string) {
 	}
 }
 
-// makeReadOnly takes write permission away from the database at path,
-// from any WAL sidecar beside it, and from their directory, as for a
-// user reading a database that a root cron scan keeps. Root ignores
-// file permissions, so it skips the test when run as root.
-func makeReadOnly(t *testing.T, path string) {
-	t.Helper()
-
-	if os.Geteuid() == 0 {
-		t.Skip("root ignores file permissions")
-	}
-
-	err := os.Chmod(path, 0o400)
-	if err != nil {
-		t.Fatal(err)
-	}
-
-	for _, suffix := range walSuffixes {
-		err = os.Chmod(path+suffix, 0o400)
-		if err != nil && !errors.Is(err, fs.ErrNotExist) {
-			t.Fatal(err)
-		}
-	}
-
-	dir := filepath.Dir(path)
-
-	//nolint:gosec // reaching the database needs the search bit
-	err = os.Chmod(dir, 0o500)
-	if err != nil {
-		t.Fatal(err)
-	}
-
-	// Runs before t.TempDir's own cleanup, which must delete the files.
-	t.Cleanup(func() {
-		//nolint:gosec // removing the directory needs its search bit back
-		_ = os.Chmod(dir, 0o700)
-	})
-}
-
-// captureStdout redirects os.Stdout to a file for the rest of the test
-// and returns a function reading back everything written to it. Only
-// machine-readable data belongs on stdout (README design goal 4), so
-// the tests assert on it directly.
-func captureStdout(t *testing.T) func() string {
-	t.Helper()
-
-	f, err := os.Create(filepath.Join(t.TempDir(), "stdout"))
-	if err != nil {
-		t.Fatal(err)
-	}
-
-	saved := os.Stdout
-	os.Stdout = f
-
-	t.Cleanup(func() {
-		os.Stdout = saved
-
-		_ = f.Close()
-	})
-
-	return func() string {
-		// Read what has been written without disturbing the write
-		// offset, so the capture can be inspected more than once.
-		size, err := f.Seek(0, io.SeekCurrent)
-		if err != nil {
-			t.Fatal(err)
-		}
-
-		if size == 0 {
-			return ""
-		}
-
-		b := make([]byte, size)
-
-		_, err = f.ReadAt(b, 0)
-		if err != nil {
-			t.Fatal(err)
-		}
-
-		return string(b)
-	}
-}
-
 // brokenDatabase writes a database that opens cleanly and passes the
 // schema-version check but has no files table, so the first query
 // fails with the database already open: a fatal error on a path that
-// owns an open database. It closes the database the way scan does.
+// owns an open database.
 func brokenDatabase(t *testing.T) string {
 	t.Helper()
 
 	path := testDBPath(t)
 
-	db, err := openDB(path, scanParams)
+	db, err := openDB(path)
 	if err != nil {
 		t.Fatal(err)
 	}
@@ -146,7 +64,10 @@ func brokenDatabase(t *testing.T) string {
 		t.Fatal(err)
 	}
 
-	closeScanDatabase(t.Context(), db, path)
+	err = db.Close()
+	if err != nil {
+		t.Fatal(err)
+	}
 
 	return path
 }
@@ -179,10 +100,7 @@ func TestOpenDatabaseKeepsWALWhileOpen(t *testing.T) {
 
 func TestRunFatalAfterOpenClosesDatabase(t *testing.T) {
 	// Every subcommand that owns an open database must close it when
-	// it fails: no os.Exit between the open and the return. The
-	// sidecar check is evidence of the close only for scan: report and
-	// trees only read a database that is out of WAL mode, which leaves
-	// nothing on disk whether they close it or not.
+	// it fails: no os.Exit between the open and the return.
 	cases := map[string][]string{
 		cmdScan:   {cmdScan},
 		cmdReport: {cmdReport},
@@ -198,17 +116,15 @@ func TestRunFatalAfterOpenClosesDatabase(t *testing.T) {
 				args = append(args, t.TempDir())
 			}
 
-			var stderr bytes.Buffer
+			var stdout, stderr bytes.Buffer
 
-			stdout := captureStdout(t)
-
-			code := run(args, &stderr)
+			code := run(args, &stdout, &stderr)
 			if code != exitFatal {
 				t.Errorf("run(%v) = %d, want %d", args, code, exitFatal)
 			}
 
 			assertNoSidecars(t, path)
-			assertFatalOutput(t, stderr.String(), stdout())
+			assertFatalOutput(t, stderr.String(), stdout.String())
 
 			// Proof that the failure happened after the open: only a
 			// query against the opened database can report this.
@@ -226,18 +142,16 @@ func TestRunMissingOperandIsFatalNotUsage(t *testing.T) {
 	// must not dump the usage text.
 	t.Setenv(databaseEnv, testDBPath(t))
 
-	var stderr bytes.Buffer
-
-	stdout := captureStdout(t)
+	var stdout, stderr bytes.Buffer
 
 	missing := filepath.Join(t.TempDir(), "nope")
 
-	code := run([]string{cmdScan, missing}, &stderr)
+	code := run([]string{cmdScan, missing}, &stdout, &stderr)
 	if code != exitFatal {
 		t.Errorf("run(scan %s) = %d, want %d", missing, code, exitFatal)
 	}
 
-	assertFatalOutput(t, stderr.String(), stdout())
+	assertFatalOutput(t, stderr.String(), stdout.String())
 }
 
 // assertFatalOutput checks that a fatal error was reported the way
@@ -281,11 +195,9 @@ func TestRunUsageErrors(t *testing.T) {
 			// path that does not exist.
 			t.Setenv(databaseEnv, testDBPath(t))
 
-			var stderr bytes.Buffer
+			var stdout, stderr bytes.Buffer
 
-			stdout := captureStdout(t)
-
-			code := run(tc.args, &stderr)
+			code := run(tc.args, &stdout, &stderr)
 			if code != exitUsage {
 				t.Errorf("run(%v) = %d, want %d", tc.args, code, exitUsage)
 			}
@@ -294,7 +206,7 @@ func TestRunUsageErrors(t *testing.T) {
 				t.Errorf("stderr = %q, want %q", stderr.String(), tc.want)
 			}
 
-			if got := stdout(); got != "" {
+			if got := stdout.String(); got != "" {
 				t.Errorf("stdout = %q, want nothing (data only)", got)
 			}
 		})
@@ -303,9 +215,9 @@ func TestRunUsageErrors(t *testing.T) {
 
 // TestRunHelpAndVersionSucceed checks that the two informational flags
 // exit 0 and keep their human-facing output on stderr.
-//
-//nolint:paralleltest // captureStdout replaces the process-wide os.Stdout
 func TestRunHelpAndVersionSucceed(t *testing.T) {
+	t.Parallel()
+
 	assertHumanOutput(t, "--help")
 	assertHumanOutput(t, "--version")
 }
@@ -316,11 +228,9 @@ func TestRunHelpAndVersionSucceed(t *testing.T) {
 func assertHumanOutput(t *testing.T, arg string) {
 	t.Helper()
 
-	var stderr bytes.Buffer
+	var stdout, stderr bytes.Buffer
 
-	stdout := captureStdout(t)
-
-	code := run([]string{arg}, &stderr)
+	code := run([]string{arg}, &stdout, &stderr)
 	if code != exitOK {
 		t.Errorf("run(%s) = %d, want %d", arg, code, exitOK)
 	}
@@ -329,7 +239,7 @@ func assertHumanOutput(t *testing.T, arg string) {
 		t.Errorf("run(%s) wrote nothing to stderr", arg)
 	}
 
-	if got := stdout(); got != "" {
+	if got := stdout.String(); got != "" {
 		t.Errorf("stdout = %q, want nothing (data only)", got)
 	}
 }
@@ -358,17 +268,15 @@ func scanFixture(t *testing.T) []string {
 		t.Fatal(err)
 	}
 
-	var stderr bytes.Buffer
+	var stdout, stderr bytes.Buffer
 
-	stdout := captureStdout(t)
-
-	code := run([]string{cmdScan, dir}, &stderr)
+	code := run([]string{cmdScan, dir}, &stdout, &stderr)
 	if code != exitOK {
 		t.Fatalf("run(scan) = %d, want %d; stderr: %s",
 			code, exitOK, stderr.String())
 	}
 
-	if got := stdout(); got != "" {
+	if got := stdout.String(); got != "" {
 		t.Errorf("scan stdout = %q, want nothing (data only)", got)
 	}
 
@@ -389,18 +297,16 @@ func TestRunReportSucceeds(t *testing.T) {
 
 	dupes := scanFixture(t)
 
-	var stderr bytes.Buffer
+	var stdout, stderr bytes.Buffer
 
-	stdout := captureStdout(t)
-
-	code := run([]string{cmdReport}, &stderr)
+	code := run([]string{cmdReport}, &stdout, &stderr)
 	if code != exitOK {
 		t.Fatalf("run(report) = %d, want %d; stderr: %s",
 			code, exitOK, stderr.String())
 	}
 
 	want := "first\tdupe\tsize\n" + dupes[0] + "\t" + dupes[1] + "\t300\n"
-	if got := stdout(); got != want {
+	if got := stdout.String(); got != want {
 		t.Errorf("stdout = %q, want %q", got, want)
 	}
 
@@ -413,11 +319,9 @@ func TestRunTreesSucceeds(t *testing.T) {
 
 	dupes := scanFixture(t)
 
-	var stderr bytes.Buffer
+	var stdout, stderr bytes.Buffer
 
-	stdout := captureStdout(t)
-
-	code := run([]string{cmdTrees}, &stderr)
+	code := run([]string{cmdTrees}, &stdout, &stderr)
 	if code != exitOK {
 		t.Fatalf("run(trees) = %d, want %d; stderr: %s",
 			code, exitOK, stderr.String())
@@ -427,47 +331,72 @@ func TestRunTreesSucceeds(t *testing.T) {
 	// trees of each other.
 	want := "first\tdupe\tfiles\tsize\n" +
 		filepath.Dir(dupes[0]) + "\t" + filepath.Dir(dupes[1]) + "\t1\t300\n"
-	if got := stdout(); got != want {
+	if got := stdout.String(); got != want {
 		t.Errorf("stdout = %q, want %q", got, want)
 	}
 
 	assertNoSidecars(t, path)
 }
 
-func TestRunReportsNeedOnlyReadAccess(t *testing.T) {
-	// README §Database: report and trees need only read access to the
-	// database file. With its directory read-only as well, SQLite
-	// cannot create any file beside it.
-	path := testDBPath(t)
-	t.Setenv(databaseEnv, path)
+func TestRunStdoutClosedIsFatal(t *testing.T) {
+	// README §Error handling: a stdout write failure exits 1, reported
+	// in one line on stderr.
+	for _, name := range []string{cmdReport, cmdTrees} {
+		t.Run(name, func(t *testing.T) {
+			t.Setenv(databaseEnv, testDBPath(t))
 
-	dupes := scanFixture(t)
-	assertNoSidecars(t, path)
-	makeReadOnly(t, path)
+			scanFixture(t)
 
-	cases := map[string]string{
-		cmdReport: "first\tdupe\tsize\n" +
-			dupes[0] + "\t" + dupes[1] + "\t300\n",
-		cmdTrees: "first\tdupe\tfiles\tsize\n" +
-			filepath.Dir(dupes[0]) + "\t" + filepath.Dir(dupes[1]) +
-			"\t1\t300\n",
+			stdout, err := os.Create(filepath.Join(t.TempDir(), "stdout"))
+			if err != nil {
+				t.Fatal(err)
+			}
+
+			err = stdout.Close()
+			if err != nil {
+				t.Fatal(err)
+			}
+
+			var stderr bytes.Buffer
+
+			code := run([]string{name}, stdout, &stderr)
+			if code != exitFatal {
+				t.Errorf("run(%s) = %d, want %d", name, code, exitFatal)
+			}
+
+			got := stderr.String()
+			if !strings.HasPrefix(got, "sfdupes: write stdout: ") ||
+				!strings.Contains(got, os.ErrClosed.Error()) ||
+				strings.Count(got, "\n") != 1 {
+				t.Errorf("stderr = %q, want one line reporting the "+
+					"failed stdout write", got)
+			}
+		})
+	}
+}
+
+// errWriteFailed is the error failingWriter returns.
+var errWriteFailed = errors.New("write failed")
+
+// failingWriter is a stdout that fails every write.
+type failingWriter struct{}
+
+func (failingWriter) Write([]byte) (int, error) { return 0, errWriteFailed }
+
+func TestStdoutWriteErrorPropagates(t *testing.T) {
+	t.Setenv(databaseEnv, testDBPath(t))
+
+	scanFixture(t)
+
+	cases := map[string]func(context.Context, io.Writer) error{
+		cmdReport: runReport,
+		cmdTrees:  runTrees,
 	}
 
-	for name, want := range cases {
-		var stderr bytes.Buffer
-
-		stdout := captureStdout(t)
-
-		code := run([]string{name}, &stderr)
-		if code != exitOK {
-			t.Errorf("run(%s) = %d, want %d; stderr: %s",
-				name, code, exitOK, stderr.String())
-
-			continue
-		}
-
-		if got := stdout(); got != want {
-			t.Errorf("%s stdout = %q, want %q", name, got, want)
+	for name, fn := range cases {
+		err := fn(t.Context(), failingWriter{})
+		if !errors.Is(err, errWriteFailed) {
+			t.Errorf("%s: error = %v, want %v", name, err, errWriteFailed)
 		}
 	}
 }

report.go

@@ -4,6 +4,7 @@ import (
 	"bufio"
 	"context"
 	"fmt"
+	"io"
 	"os"
 	"slices"
 	"strings"
@@ -31,9 +32,9 @@ type scanRec struct {
 // loadRecords opens the database and reads every file record for the
 // report and trees subcommands. Any database problem — including a
 // missing database — is fatal. The error is returned rather than
-// exiting, so that the deferred close always runs; the database is
-// closed before the caller formats its output, so it stays closed even
-// if that output fails.
+// exiting, so that the deferred close — which checkpoints the SQLite
+// WAL — always runs; the database is closed before the caller formats
+// its output, so it stays closed even if that output fails.
 func loadRecords(ctx context.Context) ([]scanRec, error) {
 	dbPath := databasePath()
 
@@ -65,7 +66,7 @@ type dupeGroup struct {
 // from the database and prints the file-level duplicates report as TSV
 // on stdout. It never touches the scanned filesystem; its only I/O is
 // the database, stdout, and stderr.
-func runReport(ctx context.Context) error {
+func runReport(ctx context.Context, stdout io.Writer) error {
 	recs, err := loadRecords(ctx)
 	if err != nil {
 		return err
@@ -73,7 +74,7 @@ func runReport(ctx context.Context) error {
 
 	dupes := collectDupeGroups(recs)
 
-	out := bufio.NewWriterSize(os.Stdout, ioBufSize)
+	out := bufio.NewWriterSize(stdout, ioBufSize)
 
 	_, err = fmt.Fprintln(out, "first\tdupe\tsize")
 	if err != nil {

report_test.go

@@ -50,11 +50,9 @@ func seedDatabase(t *testing.T, recs []scanRec) string {
 func TestRunReportEscapesPaths(t *testing.T) {
 	t.Setenv(databaseEnv, seedDatabase(t, awkwardPairRecs()))
 
-	var stderr bytes.Buffer
+	var stdout, stderr bytes.Buffer
 
-	stdout := captureStdout(t)
-
-	code := run([]string{cmdReport}, &stderr)
+	code := run([]string{cmdReport}, &stdout, &stderr)
 	if code != exitOK {
 		t.Fatalf("run(report) = %d, want %d; stderr: %s",
 			code, exitOK, stderr.String())
@@ -62,7 +60,7 @@ func TestRunReportEscapesPaths(t *testing.T) {
 
 	want := "first\tdupe\tsize\n" +
 		`/d/\tone\ntwo\rthree\\four/f` + "\t/d/A/f\t5\n"
-	if got := stdout(); got != want {
+	if got := stdout.String(); got != want {
 		t.Errorf("stdout = %q, want %q", got, want)
 	}
 }

scan.go

@@ -87,9 +87,8 @@ type fileMeta struct {
 // hash only when its size, head, and tail match another file's. Flag
 // parsing and the at-least-one-operand check are done by cobra. Errors
 // are returned rather than exiting, so that the deferred close — which
-// takes the database out of WAL mode — always runs. Cancelling ctx
-// unwinds the worker pools and aborts the scan with the context's
-// error.
+// checkpoints the SQLite WAL — always runs. Cancelling ctx unwinds the
+// worker pools and aborts the scan with the context's error.
 func runScan(ctx context.Context, roots []string, workers int,
 	oneFS bool,
 ) error {
@@ -109,7 +108,7 @@ func runScan(ctx context.Context, roots []string, workers int,
 		return err
 	}
 
-	defer closeScanDatabase(ctx, db, dbPath)
+	defer func() { _ = db.Close() }()
 
 	st, err := syncScan(ctx, db, roots, workers, oneFS)
 	if err != nil {

scan_test.go

@@ -7,6 +7,7 @@ import (
 	"database/sql"
 	"encoding/hex"
 	"fmt"
+	"io"
 	"os"
 	"path/filepath"
 	"runtime"
@@ -1548,7 +1549,7 @@ func TestScanHashWriteFailureUnwindsPool(t *testing.T) {
 
 	code := run([]string{
 		cmdScan, "--workers", strconv.Itoa(hashLeakWorkers), dir,
-	}, &stderr)
+	}, io.Discard, &stderr)
 	if code != exitFatal {
 		t.Fatalf("run(scan) = %d, want %d; stderr: %s",
 			code, exitFatal, stderr.String())

trees.go

@@ -5,6 +5,7 @@ import (
 	"context"
 	"crypto/sha256"
 	"fmt"
+	"io"
 	"os"
 	"slices"
 	"strconv"
@@ -36,7 +37,7 @@ type treeNode struct {
 // maximal duplicate-tree groups as TSV on stdout. It never touches the
 // scanned filesystem; its only I/O is the database, stdout, and
 // stderr.
-func runTrees(ctx context.Context) error {
+func runTrees(ctx context.Context, stdout io.Writer) error {
 	recs, err := loadRecords(ctx)
 	if err != nil {
 		return err
@@ -47,7 +48,7 @@ func runTrees(ctx context.Context) error {
 
 	dupes := collectTreeGroups(allDirs, super)
 
-	out := bufio.NewWriterSize(os.Stdout, ioBufSize)
+	out := bufio.NewWriterSize(stdout, ioBufSize)
 
 	_, err = fmt.Fprintln(out, "first\tdupe\tfiles\tsize")
 	if err != nil {

trees_test.go

@@ -108,11 +108,9 @@ func TestBuildHierarchyRootPath(t *testing.T) {
 func TestRunTreesEscapesPaths(t *testing.T) {
 	t.Setenv(databaseEnv, seedDatabase(t, awkwardPairRecs()))
 
-	var stderr bytes.Buffer
+	var stdout, stderr bytes.Buffer
 
-	stdout := captureStdout(t)
-
-	code := run([]string{cmdTrees}, &stderr)
+	code := run([]string{cmdTrees}, &stdout, &stderr)
 	if code != exitOK {
 		t.Fatalf("run(trees) = %d, want %d; stderr: %s",
 			code, exitOK, stderr.String())
@@ -120,7 +118,7 @@ func TestRunTreesEscapesPaths(t *testing.T) {
 
 	want := "first\tdupe\tfiles\tsize\n" +
 		`/d/\tone\ntwo\rthree\\four` + "\t/d/A\t1\t5\n"
-	if got := stdout(); got != want {
+	if got := stdout.String(); got != want {
 		t.Errorf("stdout = %q, want %q", got, want)
 	}
 }