Print progress at once off a terminal, keep warnings out of redraws (closes #13)

When stderr is not a terminal, each phase prints its zero-state line
as it starts instead of after its first item. stderrIsTTY uses
term.IsTerminal from golang.org/x/term, now a direct dependency, so
/dev/null is no longer taken for a terminal.

A spinner keeps the library's background redraw, so its count and
elapsed time stay current while a phase waits for its next item. A
warning printed during a spinner phase goes through the bar
(progressbar.Bprintln), which prints it before its next redraw instead
of racing it. Bars with a total have no background redraw and still
print warnings directly.

Model: opus-5-5

.dockerignore

@@ -1,4 +1,9 @@
-.git
+# .git is sent without its config. Without a VERSION build argument the
+# stage that compiles runs `git describe --tags --always` on .git, which
+# does not need .git/config; that file can hold a credential, such as a
+# password in a remote URL or the token the CI checkout step stores there.
+.git/config
+
 .claude
 .DS_Store
 sfdupes

.gitea/workflows/check.yml

@@ -6,4 +6,6 @@ jobs:
         steps:
             # actions/checkout v4.2.2, 2026-02-22
             - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
+              with:
+                  fetch-depth: 0
             - run: script/cibuild

Dockerfile

@@ -108,7 +108,19 @@ ARG CHECK_EPOCH
 RUN echo "gate test, epoch ${CHECK_EPOCH}" && make test
 RUN echo "gate fmt-check, epoch ${CHECK_EPOCH}" && make fmt-check
 
-RUN make build
+# The version stamped into the binary: the VERSION build argument when
+# one is given, otherwise `git describe --tags --always` of the .git in
+# the build context (git is installed by script/bootstrap above). A
+# context that carries .git and still yields no version fails the build;
+# with neither, as from a source tarball, it is "dev".
+ARG VERSION
+RUN version="${VERSION:-$(git describe --tags --always || echo dev)}"; \
+    if [ -e .git ] && { [ -z "$version" ] || [ "$version" = dev ] || \
+        [ "$version" = unknown ]; }; then \
+        echo "no version could be derived although the build context carries .git" >&2; \
+        exit 1; \
+    fi; \
+    make build VERSION="$version"
 
 # Runtime stage
 # alpine:3.22, 2026-07-23

README.md

@@ -113,7 +113,8 @@ Goals, in order:
     `sfdupes`.
 -   Dependencies: standard library, `github.com/spf13/cobra` for the
     CLI, **one progress-bar library**
-    (`github.com/schollz/progressbar/v3`), and **one SQLite driver**
+    (`github.com/schollz/progressbar/v3`), `golang.org/x/term` to tell
+    whether stderr is a terminal, and **one SQLite driver**
     (`modernc.org/sqlite`, pure Go, so builds keep cgo disabled).
     `github.com/spf13/viper` is permitted if configuration-file support
     is ever needed, but is not currently used. No other third-party
@@ -152,16 +153,28 @@ 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.
--   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.
+-   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.
 -   Schema (`PRAGMA user_version` is the schema version, currently 1; a
     database with any other version is a fatal error):
 
@@ -428,6 +441,15 @@ first	dupe	size
 /srv/a/big.iso	/srv/c/big-copy2.iso	4294967296
 ```
 
+Paths are raw bytes and may hold any byte except NUL, so the path
+columns (`first` and `dupe`) are escaped to keep every row one line of
+tab-separated fields: a backslash is written as `\\`, a tab as `\t`, a
+newline as `\n`, and a carriage return as `\r`. Every other byte is
+written unchanged, including bytes that are not valid UTF-8. Undoing
+those four escapes gives back the stored path. Grouping and ordering
+use the stored path, not the escaped one. The warnings `scan` prints on
+stderr are escaped the same way, so each warning is one line.
+
 Summary to stderr: records read, number of duplicate groups, number of
 dupe files, and total reclaimable bytes (sum of `size` over all dupe
 rows) in human units.
@@ -499,6 +521,9 @@ first	dupe	files	size
 /srv/a/project	/srv/backup/project	3417	104857600
 ```
 
+The `first` and `dupe` paths are escaped as described under "Report
+output format". The root directory's path is `/`.
+
 Summary to stderr: records read, number of duplicate-tree groups,
 number of dupe trees, and total reclaimable bytes (sum of `size` over
 all dupe rows) in human units.
@@ -533,10 +558,16 @@ hash: [12345/98765] 12% |████      | 92 files/s elapsed 2:32 eta 17:54
 
 Additional requirements:
 
--   When stderr is not a TTY, do not emit ANSI redraws: print a plain
-    one-line progress update no more often than every 5 seconds instead.
+-   When stderr is not a terminal (a pipe, a file, `/dev/null`), do not
+    emit ANSI redraws: print a plain one-line progress update the moment
+    each phase starts, then no more often than every 5 seconds.
 -   Progress updates are driven from the main goroutine and must be
-    non-blocking with respect to the worker pool.
+    non-blocking with respect to the worker pool. On a terminal the
+    spinner-style displays also redraw on their own several times a
+    second, so their count and elapsed time stay current while a phase
+    waits for its next item.
+-   A warning printed during a phase always lands on a line of its own,
+    never inside the progress display.
 -   `report` and `trees` modes need no progress display, only their
     stderr summaries.
 

TODO.md

@@ -29,6 +29,29 @@
 
 # Completed Steps
 
+- progress prints at once on a non-terminal, uses a real terminal test,
+  and prints warnings through a spinner instead of racing its redraw
+  (2026-10-03, https://git.eeqj.de/sneak/sfdupes/issues/13)
+
+- `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)
+
+- escape tabs, newlines, carriage returns and backslashes in report,
+  trees and warning paths; the root directory's path is `/`
+  (2026-10-03, https://git.eeqj.de/sneak/sfdupes/issues/7)
+
+- stamp the git tag or short commit in a plain `docker build .`
+  instead of `dev` (2026-10-02, branch `next`, closes
+  https://git.eeqj.de/sneak/sfdupes/issues/67): `.dockerignore` now
+  sends `.git`, without `.git/config`, and the `Dockerfile` build
+  stage takes the `VERSION` build argument when one is given,
+  otherwise `git describe --tags --always` of that `.git`. The build
+  fails if the context carries `.git` and the version still comes out
+  empty, `dev` or `unknown`. The CI checkout step fetches the full
+  history (`fetch-depth: 0`) so CI sees the tag and stamps the same
+  value as `make build`.
+
 - replace the 1 KiB end-window sampling with the head/tail plus
   content-hash ladder (2026-09-22, branch `next`, closes
   https://git.eeqj.de/sneak/sfdupes/issues/61): a file under 10 MiB is

db.go

@@ -74,16 +74,24 @@ func databasePath() string {
 	return defaultDatabasePath
 }
 
-// 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)" +
+// 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)"
 
-	db, err := sql.Open("sqlite", dsn)
+// 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)
 	if err != nil {
 		return nil, fmt.Errorf("open database %s: %w", path, err)
 	}
@@ -104,7 +112,7 @@ func openScanDatabase(ctx context.Context, path string) (*sql.DB, error) {
 		return nil, fmt.Errorf("create database directory: %w", err)
 	}
 
-	db, err := openDB(path)
+	db, err := openDB(path, scanParams)
 	if err != nil {
 		return nil, err
 	}
@@ -119,6 +127,24 @@ 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.
@@ -134,7 +160,7 @@ func openReportDatabase(ctx context.Context,
 		return nil, fmt.Errorf("database: %w", err)
 	}
 
-	db, err := openDB(path)
+	db, err := openDB(path, reportParams)
 	if err != nil {
 		return nil, err
 	}

db_test.go

@@ -5,6 +5,7 @@ import (
 	"database/sql"
 	"errors"
 	"fmt"
+	"os"
 	"path/filepath"
 	"slices"
 	"strings"
@@ -130,6 +131,49 @@ 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()
 

go.mod

@@ -5,6 +5,7 @@ go 1.25.7
 require (
 	github.com/schollz/progressbar/v3 v3.19.1
 	github.com/spf13/cobra v1.10.2
+	golang.org/x/term v0.44.0
 	modernc.org/sqlite v1.54.0
 )
 
@@ -19,7 +20,6 @@ require (
 	github.com/rivo/uniseg v0.4.7 // indirect
 	github.com/spf13/pflag v1.0.9 // indirect
 	golang.org/x/sys v0.46.0 // indirect
-	golang.org/x/term v0.44.0 // indirect
 	modernc.org/libc v1.74.1 // indirect
 	modernc.org/mathutil v1.7.1 // indirect
 	modernc.org/memory v1.11.0 // indirect

main_test.go

@@ -44,6 +44,44 @@ 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
@@ -91,13 +129,13 @@ func captureStdout(t *testing.T) func() string {
 // 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.
+// owns an open database. It closes the database the way scan does.
 func brokenDatabase(t *testing.T) string {
 	t.Helper()
 
 	path := testDBPath(t)
 
-	db, err := openDB(path)
+	db, err := openDB(path, scanParams)
 	if err != nil {
 		t.Fatal(err)
 	}
@@ -108,10 +146,7 @@ func brokenDatabase(t *testing.T) string {
 		t.Fatal(err)
 	}
 
-	err = db.Close()
-	if err != nil {
-		t.Fatal(err)
-	}
+	closeScanDatabase(t.Context(), db, path)
 
 	return path
 }
@@ -144,7 +179,10 @@ 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.
+	// 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.
 	cases := map[string][]string{
 		cmdScan:   {cmdScan},
 		cmdReport: {cmdReport},
@@ -395,3 +433,41 @@ func TestRunTreesSucceeds(t *testing.T) {
 
 	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)
+
+	dupes := scanFixture(t)
+	assertNoSidecars(t, path)
+	makeReadOnly(t, path)
+
+	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",
+	}
+
+	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)
+		}
+	}
+}

progress.go

@@ -6,6 +6,7 @@ import (
 	"time"
 
 	"github.com/schollz/progressbar/v3"
+	"golang.org/x/term"
 )
 
 // plainInterval is the minimum time between progress lines when stderr
@@ -24,24 +25,23 @@ const percentScale = 100
 
 // stderrIsTTY reports whether stderr is attached to a terminal.
 func stderrIsTTY() bool {
-	fi, err := os.Stderr.Stat()
-	if err != nil {
-		return false
-	}
-
-	return fi.Mode()&os.ModeCharDevice != 0
+	return term.IsTerminal(int(os.Stderr.Fd()))
 }
 
 // progress renders one scan pass's progress on stderr. On a TTY it
 // delegates to the progressbar library (spinner style when the total is
 // unknown, full bar with count/percent/rate/elapsed/ETA otherwise). When
 // stderr is not a TTY it emits no ANSI redraws: it prints a plain
-// one-line update no more often than every plainInterval.
+// one-line update as the pass starts, then no more often than every
+// plainInterval.
 //
-// All methods must be called from the main goroutine only. A nil
-// *progress is a valid no-display receiver: every method is a no-op,
-// so batched database flushes during the streaming pass can reuse the
-// update-pass helpers without rendering anything.
+// All methods must be called from the main goroutine only. On a TTY
+// the library also redraws a spinner from its own goroutine, several
+// times a second, so its count and elapsed time stay current while a
+// pass waits for its next item. A nil *progress is a valid
+// no-display receiver: every method is a no-op, so batched database
+// flushes during the streaming pass can reuse the update-pass helpers
+// without rendering anything.
 type progress struct {
 	label string
 	total int64 // -1 when unknown (walk pass)
@@ -53,10 +53,22 @@ type progress struct {
 
 func newProgress(label string, total int64) *progress {
 	p := &progress{label: label, total: total, start: time.Now()}
-	if !stderrIsTTY() {
+	if stderrIsTTY() {
+		p.bar = newBar(label, total)
+
 		return p
 	}
 
+	// Print the zero state at once: the first item may take minutes,
+	// and a pass must never look hung.
+	p.last = p.start
+	fmt.Fprintln(os.Stderr, p.plainLine())
+
+	return p
+}
+
+// newBar builds the TTY display for newProgress.
+func newBar(label string, total int64) *progressbar.ProgressBar {
 	opts := []progressbar.Option{
 		progressbar.OptionSetWriter(os.Stderr),
 		progressbar.OptionSetDescription(label),
@@ -81,9 +93,7 @@ func newProgress(label string, total int64) *progress {
 		)
 	}
 
-	p.bar = progressbar.NewOptions64(total, opts...)
-
-	return p
+	return progressbar.NewOptions64(total, opts...)
 }
 
 // increment records one completed item and refreshes the display.
@@ -106,16 +116,29 @@ func (p *progress) increment() {
 }
 
 // warnf prints a one-line warning to stderr without corrupting the bar.
+// The whole message is escaped like a report's path columns, so a path
+// holding a newline cannot split the warning.
 func (p *progress) warnf(format string, args ...any) {
 	if p == nil {
 		return
 	}
 
+	msg := escapePath(fmt.Sprintf(format, args...))
+
+	if p.bar != nil && p.total < 0 {
+		// The library also redraws a spinner from its own goroutine, so
+		// a direct write could land inside a redraw. The bar prints the
+		// warning itself, just before its next redraw.
+		_, _ = progressbar.Bprintln(p.bar, msg)
+
+		return
+	}
+
 	if p.bar != nil {
 		_ = p.bar.Clear()
 	}
 
-	fmt.Fprintf(os.Stderr, format+"\n", args...)
+	fmt.Fprintln(os.Stderr, msg)
 }
 
 // finish terminates the pass's display.

progress_test.go

@@ -0,0 +1,186 @@
+package main
+
+import (
+	"os"
+	"path/filepath"
+	"slices"
+	"strings"
+	"testing"
+	"time"
+)
+
+// spinnerIdle comfortably outlasts the 100ms interval at which the
+// progressbar library redraws a spinner from its own goroutine.
+const spinnerIdle = 500 * time.Millisecond
+
+// captureStderr points os.Stderr at a file for the rest of the test and
+// returns a function reading back everything written to it.
+func captureStderr(t *testing.T) func() string {
+	t.Helper()
+
+	path := filepath.Join(t.TempDir(), "stderr")
+
+	f, err := os.Create(path) //nolint:gosec // test-controlled path
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	saved := os.Stderr
+	os.Stderr = f
+
+	t.Cleanup(func() {
+		os.Stderr = saved
+
+		_ = f.Close()
+	})
+
+	return func() string {
+		b, err := os.ReadFile(path) //nolint:gosec // test-controlled path
+		if err != nil {
+			t.Fatal(err)
+		}
+
+		return string(b)
+	}
+}
+
+//nolint:paralleltest // replaces the process-wide os.Stderr
+func TestStderrIsTTYFalseForNonTerminals(t *testing.T) {
+	r, pipe, err := os.Pipe()
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	regular, err := os.Create(filepath.Join(t.TempDir(), "stderr"))
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	devNull, err := os.OpenFile(os.DevNull, os.O_WRONLY, 0)
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	saved := os.Stderr
+
+	t.Cleanup(func() {
+		os.Stderr = saved
+
+		for _, f := range []*os.File{r, pipe, regular, devNull} {
+			_ = f.Close()
+		}
+	})
+
+	cases := map[string]*os.File{
+		"a pipe":         pipe,
+		"a regular file": regular,
+		os.DevNull:       devNull,
+	}
+
+	for name, f := range cases {
+		os.Stderr = f
+
+		if stderrIsTTY() {
+			t.Errorf("stderrIsTTY() = true with stderr on %s", name)
+		}
+	}
+}
+
+// TestNewProgressPrintsBeforeFirstItem checks that each pass shows its
+// zero state the moment it starts when stderr is not a terminal, and
+// that the next line still waits for plainInterval.
+//
+//nolint:paralleltest // captureStderr replaces the process-wide os.Stderr
+func TestNewProgressPrintsBeforeFirstItem(t *testing.T) {
+	stderr := captureStderr(t)
+
+	newProgress("walk", -1).increment()
+	newProgress("hash", 10).increment()
+
+	want := "walk: 0 files, elapsed 0s\n" +
+		"hash: [0/10] 0% 0 files/s elapsed 0s eta ?\n"
+	if got := stderr(); got != want {
+		t.Errorf("stderr = %q, want %q", got, want)
+	}
+}
+
+// newWalkSpinner returns the walk pass's terminal display, writing to
+// os.Stderr whether or not it is a terminal, and stops the library's
+// redraws when the test ends.
+func newWalkSpinner(t *testing.T) *progress {
+	t.Helper()
+
+	p := &progress{
+		label: "walk", total: -1, start: time.Now(),
+		bar: newBar("walk", -1),
+	}
+	t.Cleanup(p.finish)
+
+	return p
+}
+
+// TestProgressWarningsOnOwnLines drives the terminal display of the walk
+// pass: every warning must land on a line of its own, never inside a
+// redraw of the spinner.
+//
+//nolint:paralleltest // captureStderr replaces the process-wide os.Stderr
+func TestProgressWarningsOnOwnLines(t *testing.T) {
+	stderr := captureStderr(t)
+	p := newWalkSpinner(t)
+
+	for _, w := range []string{"first", "second", "third"} {
+		p.increment()
+		p.warnf("warning %s", w)
+	}
+
+	p.increment()
+
+	// The spinner prints the warnings at its next redraw.
+	time.Sleep(spinnerIdle)
+
+	// A terminal shows each line as the text after its last carriage
+	// return.
+	var warnings []string
+
+	for line := range strings.SplitSeq(stderr(), "\n") {
+		if strings.Contains(line, "warning") {
+			warnings = append(warnings, line[strings.LastIndex(line, "\r")+1:])
+		}
+	}
+
+	want := []string{"warning first", "warning second", "warning third"}
+	if !slices.Equal(warnings, want) {
+		t.Errorf("warning lines = %q, want %q", warnings, want)
+	}
+}
+
+// TestSpinnerShowsCountAfterBurst checks that once a burst of items
+// faster than the redraw limit is over, the walk display shows every
+// item completed while it waits for the next one.
+//
+//nolint:paralleltest // captureStderr replaces the process-wide os.Stderr
+func TestSpinnerShowsCountAfterBurst(t *testing.T) {
+	stderr := captureStderr(t)
+	p := newWalkSpinner(t)
+
+	for range 50 {
+		p.increment()
+	}
+
+	time.Sleep(spinnerIdle)
+
+	// A terminal shows the last frame drawn. The library starts each
+	// frame with a carriage return and erases the previous one with
+	// spaces first.
+	var shown string
+
+	for frame := range strings.SplitSeq(stderr(), "\r") {
+		if strings.TrimSpace(frame) != "" {
+			shown = frame
+		}
+	}
+
+	if !strings.Contains(shown, "(50/-,") {
+		t.Errorf("terminal shows %q, want a count of 50", shown)
+	}
+}

report.go

@@ -31,9 +31,9 @@ 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 — 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.
+// 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.
 func loadRecords(ctx context.Context) ([]scanRec, error) {
 	dbPath := databasePath()
 
@@ -87,7 +87,7 @@ func runReport(ctx context.Context) error {
 	for _, g := range dupes {
 		for _, p := range g.paths[1:] {
 			_, err = fmt.Fprintf(out, "%s\t%s\t%d\n",
-				g.paths[0], p, g.size)
+				escapePath(g.paths[0]), escapePath(p), g.size)
 			if err != nil {
 				return fmt.Errorf("write stdout: %w", err)
 			}
@@ -156,6 +156,21 @@ func collectDupeGroups(recs []scanRec) []dupeGroup {
 	return dupes
 }
 
+// escapePath returns a path as it is written in a report column (README
+// "Report output format"): a backslash, tab, newline or carriage return
+// becomes \\, \t, \n or \r, and every other byte is kept as it is.
+// Grouping and sorting use the raw path, never this form.
+func escapePath(p string) string {
+	// Most paths need no escaping; skip building a replacer for them.
+	if !strings.ContainsAny(p, "\\\t\n\r") {
+		return p
+	}
+
+	return strings.NewReplacer(
+		`\`, `\\`, "\t", `\t`, "\n", `\n`, "\r", `\r`,
+	).Replace(p)
+}
+
 // humanBytes formats a byte count in human units (binary prefixes).
 func humanBytes(n int64) string {
 	const unit = 1024

report_test.go

@@ -1,10 +1,128 @@
 package main
 
 import (
+	"bytes"
+	"io"
+	"os"
+	"path/filepath"
 	"slices"
 	"testing"
 )
 
+// awkwardDir is a directory name holding every byte the reports escape.
+const awkwardDir = "/d/\tone\ntwo\rthree\\four"
+
+// awkwardPairRecs is a duplicate pair in sibling directories /d/A and
+// awkwardDir. A raw tab sorts before "A" but its escaped form `\t`
+// sorts after it, so awkwardDir coming first shows that sorting uses
+// the raw path.
+func awkwardPairRecs() []scanRec {
+	return []scanRec{
+		{size: 5, head: "h", tail: "t", content: "c", path: "/d/A/f"},
+		{size: 5, head: "h", tail: "t", content: "c", path: awkwardDir + "/f"},
+	}
+}
+
+// seedDatabase writes recs into a fresh database and returns its path.
+func seedDatabase(t *testing.T, recs []scanRec) string {
+	t.Helper()
+
+	path := testDBPath(t)
+
+	db, err := openScanDatabase(t.Context(), path)
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	err = applyChanges(t.Context(), db, recs, nil, nil)
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	err = db.Close()
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	return path
+}
+
+func TestRunReportEscapesPaths(t *testing.T) {
+	t.Setenv(databaseEnv, seedDatabase(t, awkwardPairRecs()))
+
+	var stderr bytes.Buffer
+
+	stdout := captureStdout(t)
+
+	code := run([]string{cmdReport}, &stderr)
+	if code != exitOK {
+		t.Fatalf("run(report) = %d, want %d; stderr: %s",
+			code, exitOK, stderr.String())
+	}
+
+	want := "first\tdupe\tsize\n" +
+		`/d/\tone\ntwo\rthree\\four/f` + "\t/d/A/f\t5\n"
+	if got := stdout(); got != want {
+		t.Errorf("stdout = %q, want %q", got, want)
+	}
+}
+
+func TestEscapePath(t *testing.T) {
+	t.Parallel()
+
+	cases := map[string]string{
+		"/srv/plain":    "/srv/plain",
+		"/a\tb":         `/a\tb`,
+		"/a\nb":         `/a\nb`,
+		"/a\rb":         `/a\rb`,
+		`/a\b`:          `/a\\b`,
+		`/a\tb`:         `/a\\tb`,
+		"/not-utf8\xff": "/not-utf8\xff",
+	}
+	for in, want := range cases {
+		if got := escapePath(in); got != want {
+			t.Errorf("escapePath(%q) = %q, want %q", in, got, want)
+		}
+	}
+}
+
+// TestWarnfEscapes checks that a warning naming a path that holds a
+// newline is still one line.
+//
+//nolint:paralleltest // replaces the process-wide os.Stderr
+func TestWarnfEscapes(t *testing.T) {
+	f, err := os.Create(filepath.Join(t.TempDir(), "stderr"))
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	saved := os.Stderr
+	os.Stderr = f
+
+	t.Cleanup(func() {
+		os.Stderr = saved
+
+		_ = f.Close()
+	})
+
+	(&progress{}).warnf("stat %s: %s", "/d/a\nb", "gone")
+
+	_, err = f.Seek(0, io.SeekStart)
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	got, err := io.ReadAll(f)
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	want := `stat /d/a\nb: gone` + "\n"
+	if string(got) != want {
+		t.Errorf("warning = %q, want %q", got, want)
+	}
+}
+
 func TestCollectDupeGroups(t *testing.T) {
 	t.Parallel()
 

scan.go

@@ -87,8 +87,9 @@ 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
-// checkpoints the SQLite WAL — always runs. Cancelling ctx unwinds the
-// worker pools and aborts the scan with the context's error.
+// takes the database out of WAL mode — 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 {
@@ -108,7 +109,7 @@ func runScan(ctx context.Context, roots []string, workers int,
 		return err
 	}
 
-	defer func() { _ = db.Close() }()
+	defer closeScanDatabase(ctx, db, dbPath)
 
 	st, err := syncScan(ctx, db, roots, workers, oneFS)
 	if err != nil {

script/cibuild

@@ -16,10 +16,10 @@
 # implies the repo is green.
 #
 # That implication holds only because of CHECK_EPOCH. A COPY layer is
-# invalidated by changed content, and a merge commit's tree is
-# byte-identical to the branch head it merges, so without a fresh value
-# here Docker serves the gate layers from cache and the build reports a
-# green it never earned. Passing the current epoch invalidates the gate
+# invalidated only by changed content, and a rebuild of an unchanged
+# checkout sends the same content, so without a fresh value here Docker
+# serves the gate layers from cache and the build reports a green it
+# never earned. Passing the current epoch invalidates the gate
 # layers on every run while leaving the pinned base images and
 # go mod download cached; see the Dockerfile for the placement.
 set -eu

trees.go

@@ -62,7 +62,8 @@ func runTrees(ctx context.Context) error {
 		first := g[0]
 		for _, n := range g[1:] {
 			_, err = fmt.Fprintf(out, "%s\t%s\t%d\t%d\n",
-				first.path, n.path, first.fileCount, first.totalSize)
+				escapePath(first.path), escapePath(n.path),
+				first.fileCount, first.totalSize)
 			if err != nil {
 				return fmt.Errorf("write stdout: %w", err)
 			}
@@ -87,8 +88,8 @@ func runTrees(ctx context.Context) error {
 
 // buildHierarchy reconstructs the directory hierarchy from the record
 // paths under a synthetic super-root. Paths are split on "/"; for
-// absolute paths the first component is empty, which simply becomes a
-// top-level node representing "/". It returns the super-root and every
+// absolute paths the first component is empty, which becomes the
+// top-level node with path "/". It returns the super-root and every
 // directory node created.
 func buildHierarchy(recs []scanRec) (*treeNode, []*treeNode) {
 	super := &treeNode{}
@@ -102,9 +103,17 @@ func buildHierarchy(recs []scanRec) (*treeNode, []*treeNode) {
 		for _, c := range comps[:len(comps)-1] {
 			child := node.dirs[c]
 			if child == nil {
-				childPath := c
-				if node != super {
-					childPath = node.path + "/" + c
+				childPath := node.path + "/" + c
+
+				// The root directory's path is "/", not empty, and its
+				// children's paths start with one slash, not two.
+				switch {
+				case node == super && c == "":
+					childPath = "/"
+				case node == super:
+					childPath = c
+				case node.path == "/":
+					childPath = "/" + c
 				}
 
 				child = &treeNode{path: childPath, parent: node}

trees_test.go

@@ -1,6 +1,7 @@
 package main
 
 import (
+	"bytes"
 	"slices"
 	"testing"
 )
@@ -84,6 +85,46 @@ func TestBuildHierarchyCounts(t *testing.T) {
 	}
 }
 
+func TestBuildHierarchyRootPath(t *testing.T) {
+	t.Parallel()
+
+	// The root directory's path is "/", never empty, and its
+	// children's paths start with a single slash.
+	_, dirs := buildHierarchy([]scanRec{{path: "/f"}, {path: "/srv/g"}})
+
+	got := make([]string, 0, len(dirs))
+	for _, d := range dirs {
+		got = append(got, d.path)
+	}
+
+	slices.Sort(got)
+
+	want := []string{"/", "/srv"}
+	if !slices.Equal(got, want) {
+		t.Fatalf("directory paths = %q, want %q", got, want)
+	}
+}
+
+func TestRunTreesEscapesPaths(t *testing.T) {
+	t.Setenv(databaseEnv, seedDatabase(t, awkwardPairRecs()))
+
+	var stderr bytes.Buffer
+
+	stdout := captureStdout(t)
+
+	code := run([]string{cmdTrees}, &stderr)
+	if code != exitOK {
+		t.Fatalf("run(trees) = %d, want %d; stderr: %s",
+			code, exitOK, stderr.String())
+	}
+
+	want := "first\tdupe\tfiles\tsize\n" +
+		`/d/\tone\ntwo\rthree\\four` + "\t/d/A\t1\t5\n"
+	if got := stdout(); got != want {
+		t.Errorf("stdout = %q, want %q", got, want)
+	}
+}
+
 func TestTreeDigests(t *testing.T) {
 	t.Parallel()