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

.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

@@ -428,6 +428,15 @@ 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 +508,9 @@ 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.
@@ -549,6 +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

@@ -29,6 +29,25 @@
 
 # Completed Steps
 
+- 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 `/`
+  (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

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

@@ -44,50 +44,6 @@ func assertNoSidecars(t *testing.T, path string) {
 	}
 }
 
-// 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
@@ -160,17 +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.
@@ -188,18 +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
@@ -243,11 +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)
 			}
@@ -256,7 +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)
 			}
 		})
@@ -265,9 +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")
 }
@@ -278,11 +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)
 	}
@@ -291,7 +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)
 	}
 }
@@ -320,17 +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)
 	}
 
@@ -351,18 +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)
 	}
 
@@ -375,11 +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())
@@ -389,9 +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 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))
+
+			scanFixture(t)
+
+			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, fn := range cases {
+		err := fn(t.Context(), failingWriter{})
+		if !errors.Is(err, errWriteFailed) {
+			t.Errorf("%s: error = %v, want %v", name, err, errWriteFailed)
+		}
+	}
+}

progress.go

@@ -106,6 +106,8 @@ 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
@@ -115,7 +117,7 @@ func (p *progress) warnf(format string, args ...any) {
 		_ = p.bar.Clear()
 	}
 
-	fmt.Fprintf(os.Stderr, format+"\n", args...)
+	fmt.Fprintln(os.Stderr, escapePath(fmt.Sprintf(format, args...)))
 }
 
 // finish terminates the pass's display.

report.go

@@ -4,6 +4,7 @@ import (
 	"bufio"
 	"context"
 	"fmt"
+	"io"
 	"os"
 	"slices"
 	"strings"
@@ -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 {
@@ -87,7 +88,7 @@ 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 +157,21 @@ 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 +1,126 @@
 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 stdout, stderr bytes.Buffer
+
+	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" +
+		`/d/\tone\ntwo\rthree\\four/f` + "\t/d/A/f\t5\n"
+	if got := stdout.String(); 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_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())

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

@@ -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 {
@@ -62,7 +63,8 @@ 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 +89,8 @@ 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 +104,17 @@ 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 +85,44 @@ 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 stdout, stderr bytes.Buffer
+
+	code := run([]string{cmdTrees}, &stdout, &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.String(); got != want {
+		t.Errorf("stdout = %q, want %q", got, want)
+	}
+}
+
 func TestTreeDigests(t *testing.T) {
 	t.Parallel()