Limit report and trees to given paths (closes #174)

report and trees take optional PATH operands and use only the records
at or below them. Operands are made absolute and cleaned as text, never
looked up on the filesystem. With operands, trees reports only
directories at or below an operand: a directory above them holds
unused files, so its digest neither gets reported nor suppresses its
children's group. The summary still counts every record read.

Model: opus-5-5

Makefile

@@ -4,7 +4,7 @@ export CGO_ENABLED = 0
 
 BINARY := sfdupes
 VERSION := $(shell git describe --tags --always --dirty 2>/dev/null || echo dev)
-LDFLAGS := -X main.Version=$(VERSION)
+LDFLAGS := -X sneak.berlin/go/sfdupes/internal/sfdupes.Version=$(VERSION)
 
 .PHONY: sfdupes build bootstrap setup test lint fmt fmt-check check docker hooks clean
 
@@ -14,7 +14,7 @@ LDFLAGS := -X main.Version=$(VERSION)
 # Default target: build the binary. Phony so go build (which has its
 # own build cache) always decides what to recompile.
 sfdupes:
-	go build -ldflags "$(LDFLAGS)" -o $(BINARY)
+	go build -ldflags "$(LDFLAGS)" -o $(BINARY) ./cmd/sfdupes
 
 build: sfdupes
 

cmd/sfdupes/main.go

@@ -0,0 +1,29 @@
+// Command sfdupes quickly identifies candidate duplicate files across
+// very large filesystems without reading every byte of every file.
+// Files are considered duplicates when their sizes are equal and they
+// agree on three SHA-256 hashes: of the first 64 KiB, of the last 64
+// KiB, and of the content. The content hash covers the whole file under
+// 100 MiB, and 1 MiB at each gigabyte at 100 MiB or more, so a large
+// file is never read in full. scan maintains a persistent SQLite
+// database of file signatures (SFDUPES_DATABASE, default
+// /var/lib/sfdupes/db.sqlite) that the other subcommands read.
+//
+// Usage:
+//
+//	sfdupes scan [--workers N] [-x] [--no-default-excludes] PATH...
+//	sfdupes report > dupes.tsv
+//	sfdupes trees > dupetrees.tsv
+//	sfdupes info
+//	sfdupes dwim
+//	sfdupes --version
+//
+// See README.md for the complete specification.
+package main
+
+import (
+	"os"
+
+	"sneak.berlin/go/sfdupes/internal/sfdupes"
+)
+
+func main() { os.Exit(sfdupes.Main()) }

internal/sfdupes/cancel_test.go

@@ -1,4 +1,4 @@
-package main
+package sfdupes //nolint:testpackage // cancels the unexported runScan and hashWorker
 
 import (
 	"context"

internal/sfdupes/cli.go

@@ -1,23 +1,6 @@
-// Command sfdupes quickly identifies candidate duplicate files across
+// Package sfdupes implements the sfdupes command and the database its
-// very large filesystems without reading every byte of every file.
+// subcommands share.
-// Files are considered duplicates when their sizes are equal and they
+package sfdupes
-// agree on three SHA-256 hashes: of the first 64 KiB, of the last 64
-// KiB, and of the content. The content hash covers the whole file under
-// 100 MiB, and 1 MiB at each gigabyte at 100 MiB or more, so a large
-// file is never read in full. scan maintains a persistent SQLite
-// database of file signatures (SFDUPES_DATABASE, default
-// /var/lib/sfdupes/db.sqlite) that the other subcommands read.
-//
-// Usage:
-//
-//	sfdupes scan [--workers N] [-x] [--no-default-excludes] PATH...
-//	sfdupes report > dupes.tsv
-//	sfdupes trees > dupetrees.tsv
-//	sfdupes info
-//	sfdupes --version
-//
-// See README.md for the complete specification.
-package main
 
 import (
 	"context"
@@ -45,8 +28,16 @@ const (
 	cmdReport = "report"
 	cmdTrees  = "trees"
 	cmdInfo   = "info"
+	cmdDwim   = "dwim"
 )
 
+// reportPathsHelp explains the PATH operands of report and trees in
+// their help.
+const reportPathsHelp = "With PATH operands, only the records at or " +
+	"below them are used. A relative PATH is joined to the working " +
+	"directory. No PATH is looked up on the filesystem, so a symlink in " +
+	"one is not followed."
+
 // errNoSubcommand is returned by the root command when it is invoked
 // without a subcommand. That is a usage error, and the usage text
 // cobra prints for it is the whole message.
@@ -84,20 +75,22 @@ func buildVersion(linkerVersion string, info *debug.BuildInfo) string {
 	return info.Main.Version
 }
 
-func main() {
+// Main runs the command line in os.Args and returns the process exit
+// code.
+func Main() int {
 	// 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))
+	return 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. The report, trees and info subcommands
+// runs before the process ends. The report, trees, info and dwim
-// write their data to stdout.
+// 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.
@@ -175,20 +168,24 @@ func newRootCommand(stdout, stderr io.Writer) *cobra.Command {
 		"print the version to stdout")
 
 	reportCmd := &cobra.Command{
-		Use:   cmdReport,
+		Use:   cmdReport + " [PATH...]",
 		Short: "Read the scan database and print the file-level duplicates report",
-		Args:  cobra.NoArgs,
+		Long: "Read the scan database and print the file-level duplicates " +
-		RunE: runE(func(ctx context.Context, _ []string) error {
+			"report.\n\n" + reportPathsHelp,
-			return runReport(ctx, stdout)
+		Args: cobra.ArbitraryArgs,
+		RunE: runE(func(ctx context.Context, args []string) error {
+			return runReport(ctx, args, stdout)
 		}),
 	}
 
 	treesCmd := &cobra.Command{
-		Use:   cmdTrees,
+		Use:   cmdTrees + " [PATH...]",
 		Short: "Read the scan database and print the duplicate-tree report",
-		Args:  cobra.NoArgs,
+		Long: "Read the scan database and print the duplicate-tree " +
-		RunE: runE(func(ctx context.Context, _ []string) error {
+			"report.\n\n" + reportPathsHelp,
-			return runTrees(ctx, stdout)
+		Args: cobra.ArbitraryArgs,
+		RunE: runE(func(ctx context.Context, args []string) error {
+			return runTrees(ctx, args, stdout)
 		}),
 	}
 
@@ -201,7 +198,16 @@ func newRootCommand(stdout, stderr io.Writer) *cobra.Command {
 		}),
 	}
 
-	root.AddCommand(newScanCommand(), reportCmd, treesCmd, infoCmd)
+	dwimCmd := &cobra.Command{
+		Use:   cmdDwim,
+		Short: "Scan / with the default excludes, then print the duplicate-tree report",
+		Args:  cobra.NoArgs,
+		RunE: runE(func(ctx context.Context, _ []string) error {
+			return runDwim(ctx, "/", stdout)
+		}),
+	}
+
+	root.AddCommand(newScanCommand(), reportCmd, treesCmd, infoCmd, dwimCmd)
 
 	return root
 }

internal/sfdupes/cli_test.go

@@ -1,4 +1,4 @@
-package main
+package sfdupes //nolint:testpackage // drives the unexported run
 
 import (
 	"bytes"
@@ -14,6 +14,8 @@ import (
 	"strconv"
 	"strings"
 	"testing"
+
+	"golang.org/x/sys/unix"
 )
 
 // usageMarker is the first line of cobra's usage text, which a usage
@@ -394,7 +396,7 @@ func TestRunNamesRelativeDatabase(t *testing.T) {
 }
 
 func TestRunUsesDatabaseThroughSymlinkedDirectory(t *testing.T) {
-	// README §Database: the path names the file exactly. With link a
+	// README §Settings: the path names the file exactly. With link a
 	// symlink to the directory real/sub, link/../db.sqlite names
 	// real/db.sqlite, not db.sqlite beside link. Every subcommand must
 	// use that file, relative or absolute, and its first line must name
@@ -574,14 +576,14 @@ func TestRunNamesDefaultDatabase(t *testing.T) {
 		},
 		cmdReport: {
 			run: func() error {
-				return runReport(cancelledContext(t), io.Discard)
+				return runReport(cancelledContext(t), nil, io.Discard)
 			},
 			want: "report: database " + defaultDatabasePath + " (default)\n" +
 				reportOpenLine + "\n" + reportOpenLine + "\n",
 		},
 		cmdTrees: {
 			run: func() error {
-				return runTrees(cancelledContext(t), io.Discard)
+				return runTrees(cancelledContext(t), nil, io.Discard)
 			},
 			want: "trees: database " + defaultDatabasePath + " (default)\n" +
 				treesOpenLine + "\n" + treesOpenLine + "\n",
@@ -617,9 +619,8 @@ func TestRunUsageErrors(t *testing.T) {
 	}{
 		"no subcommand":      {[]string{}, usageMarker},
 		"scan without paths": {[]string{cmdScan}, usageMarker},
-		"report with args":   {[]string{cmdReport, "x"}, usageMarker},
-		"trees with args":    {[]string{cmdTrees, "x"}, usageMarker},
 		"info with args":     {[]string{cmdInfo, "x"}, usageMarker},
+		"dwim with args":     {[]string{cmdDwim, "x"}, usageMarker},
 		"unknown flag":       {[]string{cmdScan, "--nope", "/"}, usageMarker},
 		"unknown subcommand": {[]string{"nope"}, "unknown command"},
 	}
@@ -649,7 +650,7 @@ func TestRunUsageErrors(t *testing.T) {
 }
 
 func TestRunScanRejectsWorkersBelowOne(t *testing.T) {
-	// README §scan mode: --workers below 1 is a usage error reported in
+	// README §Settings: --workers below 1 is a usage error reported in
 	// one line on stderr, before the scan opens the database.
 	for _, workers := range []string{"0", "-1"} {
 		t.Run(workers, func(t *testing.T) {
@@ -687,8 +688,8 @@ func TestRunScanRejectsWorkersBelowOne(t *testing.T) {
 func TestRunHelp(t *testing.T) {
 	t.Parallel()
 
-	// README §Subcommands: help goes to stderr, exits 0, and leaves
+	// README §Settings: help goes to stderr, exits 0, and leaves stdout
-	// stdout empty.
+	// empty.
 	cases := [][]string{{"--help"}, {"-h"}, {cmdScan, "--help"}}
 
 	for _, args := range cases {
@@ -714,8 +715,8 @@ func TestRunHelp(t *testing.T) {
 func TestRunVersion(t *testing.T) {
 	t.Parallel()
 
-	// README §Subcommands: the version is one line on stdout, with
+	// README §Settings: the version is one line on stdout, with nothing
-	// nothing on stderr, and exits 0.
+	// on stderr, and exits 0.
 	info, _ := debug.ReadBuildInfo()
 
 	for _, arg := range []string{"--version", "-v"} {
@@ -774,8 +775,8 @@ func TestBuildVersion(t *testing.T) {
 func TestRunVersionWriteFailureIsFatal(t *testing.T) {
 	t.Parallel()
 
-	// README §Error handling: a stdout write failure exits 1, reported
+	// README §Error handling: a failed write to stdout is a fatal error,
-	// in one line on stderr.
+	// exit 1, reported on stderr starting with "sfdupes:".
 	var stderr bytes.Buffer
 
 	code := run([]string{"--version"}, failingWriter{}, &stderr)
@@ -797,7 +798,7 @@ func TestRunVersionWriteFailureIsFatal(t *testing.T) {
 func scanFixture(t *testing.T) []string {
 	t.Helper()
 
-	dir := t.TempDir()
+	dir := realTempDir(t)
 
 	dupes := []string{
 		writeFile(t, dir, "one/a.bin", pattern(1, 300)),
@@ -867,7 +868,7 @@ func TestRunScanSucceedsDespiteWarnings(t *testing.T) {
 	path := testDBPath(t)
 	t.Setenv(databaseEnv, path)
 
-	dir := t.TempDir()
+	dir := realTempDir(t)
 	writeFile(t, dir, "a.bin", pattern(1, 300))
 
 	// Same size as a.bin, so the scan reads it, and the read fails.
@@ -895,58 +896,278 @@ func TestRunScanSucceedsDespiteWarnings(t *testing.T) {
 	assertNoSidecars(t, path)
 }
 
-func TestRunScanSkipsSymlinkOperand(t *testing.T) {
+// realTempDir returns a new temporary directory by its real path, so
-	path := testDBPath(t)
+// tests hold where the temporary directory is reached through a
-	t.Setenv(databaseEnv, path)
+// symlink.
+func realTempDir(t *testing.T) string {
+	t.Helper()
 
-	dir := t.TempDir()
+	dir, err := filepath.EvalSymlinks(t.TempDir())
-	writeFile(t, dir, "target/sub/f", pattern(1, 10))
-
-	link := filepath.Join(dir, "link")
-
-	err := os.Symlink(filepath.Join(dir, "target"), link)
 	if err != nil {
 		t.Fatal(err)
 	}
 
-	// Scanning a directory through the symlink stores a record beneath
+	return dir
-	// the symlink's own path for a file beneath its target.
-	scanOK(t, filepath.Join(link, "sub"))
-
-	assertOperandSkipped(t, path, link, "symlink",
-		filepath.Join(link, "sub", "f"))
 }
 
+// symlink creates link pointing at target.
+func symlink(t *testing.T, target, link string) {
+	t.Helper()
+
+	err := os.Symlink(target, link)
+	if err != nil {
+		t.Fatal(err)
+	}
+}
+
+// TestRunScanFollowsSymlinkOperand scans link, a symlink to target.
+// The operand is scanned at its real path, and its file is recorded
+// there.
+func TestRunScanFollowsSymlinkOperand(t *testing.T) {
+	path := testDBPath(t)
+	t.Setenv(databaseEnv, path)
+
+	dir := realTempDir(t)
+	f := writeFile(t, dir, "target/sub/f", pattern(1, 10))
+
+	link := filepath.Join(dir, "link")
+	symlink(t, filepath.Join(dir, "target"), link)
+
+	stderr := scanOK(t, link)
+
+	summary := "scan: 1 files seen (1 added, 0 updated, 0 removed, " +
+		"0 unchanged), 0 skipped\n"
+	if !strings.Contains(stderr, summary) {
+		t.Errorf("stderr = %q, want %q", stderr, summary)
+	}
+
+	if got := storedPaths(t, path); !slices.Equal(got, []string{f}) {
+		t.Errorf("records = %q, want %q", got, []string{f})
+	}
+}
+
+// TestRunScanWalksOperandUnderSymlinkOperand scans link and link/sub,
+// with link a symlink to target. Both resolve under target, so
+// target/sub is walked once, as part of target.
 func TestRunScanWalksOperandUnderSymlinkOperand(t *testing.T) {
 	path := testDBPath(t)
 	t.Setenv(databaseEnv, path)
 
-	dir := t.TempDir()
+	dir := realTempDir(t)
-	writeFile(t, dir, "target/sub/f", pattern(1, 10))
+	f := writeFile(t, dir, "target/sub/f", pattern(1, 10))
 
 	link := filepath.Join(dir, "link")
+	symlink(t, filepath.Join(dir, "target"), link)
 
-	err := os.Symlink(filepath.Join(dir, "target"), link)
+	stderr := scanOK(t, link, filepath.Join(link, "sub"))
+
+	summary := "scan: 1 files seen (1 added, 0 updated, 0 removed, " +
+		"0 unchanged), 0 skipped\n"
+	if !strings.Contains(stderr, summary) {
+		t.Errorf("stderr = %q, want %q", stderr, summary)
+	}
+
+	if got := storedPaths(t, path); !slices.Equal(got, []string{f}) {
+		t.Errorf("records = %q, want %q", got, []string{f})
+	}
+}
+
+// TestRunScanWalksSymlinkedOperandBelowOperand is the case of
+// https://git.eeqj.de/sneak/sfdupes/issues/144: scan dir dir/link/sub,
+// with dir/link a symlink to a directory outside dir. The walk of dir
+// does not follow link, so dir/link/sub is walked on its own at its
+// real path, and the record an earlier scan stored there survives.
+func TestRunScanWalksSymlinkedOperandBelowOperand(t *testing.T) {
+	path := testDBPath(t)
+	t.Setenv(databaseEnv, path)
+
+	dir := realTempDir(t)
+	a := writeFile(t, dir, "a", pattern(1, 10))
+
+	outside := realTempDir(t)
+	f := writeFile(t, outside, "sub/f", pattern(2, 10))
+
+	symlink(t, outside, filepath.Join(dir, "link"))
+
+	scanOK(t, filepath.Join(outside, "sub"))
+
+	stderr := scanOK(t, dir, filepath.Join(dir, "link", "sub"))
+
+	summary := "scan: 2 files seen (1 added, 0 updated, 0 removed, " +
+		"1 unchanged), 0 skipped\n"
+	if !strings.Contains(stderr, summary) {
+		t.Errorf("stderr = %q, want %q", stderr, summary)
+	}
+
+	want := []string{a, f}
+	slices.Sort(want)
+
+	if got := storedPaths(t, path); !slices.Equal(got, want) {
+		t.Errorf("records = %q, want %q", got, want)
+	}
+}
+
+// TestRunScanDropsSymlinkOperandInsideOperand scans dir and link, with
+// link, outside dir, a symlink to dir/real. link resolves inside dir,
+// so it is dropped as covered by dir, and its file is recorded once.
+func TestRunScanDropsSymlinkOperandInsideOperand(t *testing.T) {
+	path := testDBPath(t)
+	t.Setenv(databaseEnv, path)
+
+	dir := realTempDir(t)
+	f := writeFile(t, dir, "real/f", pattern(1, 10))
+
+	link := filepath.Join(realTempDir(t), "link")
+	symlink(t, filepath.Join(dir, "real"), link)
+
+	stderr := scanOK(t, dir, link)
+
+	summary := "scan: 1 files seen (1 added, 0 updated, 0 removed, " +
+		"0 unchanged), 0 skipped\n"
+	if !strings.Contains(stderr, summary) {
+		t.Errorf("stderr = %q, want %q", stderr, summary)
+	}
+
+	if got := storedPaths(t, path); !slices.Equal(got, []string{f}) {
+		t.Errorf("records = %q, want %q", got, []string{f})
+	}
+}
+
+// TestRunScanDanglingSymlinkOperandIsFatal scans a valid directory and
+// a symlink whose target does not exist. The scan fails with exit 1 and
+// an error naming the symlink as given, before it walks anything, so no
+// database is created.
+func TestRunScanDanglingSymlinkOperandIsFatal(t *testing.T) {
+	path := testDBPath(t)
+	t.Setenv(databaseEnv, path)
+
+	dir := realTempDir(t)
+	writeFile(t, dir, "f", pattern(1, 10))
+
+	dangling := filepath.Join(realTempDir(t), "dangling")
+	symlink(t, filepath.Join(dir, "missing"), dangling)
+
+	stdout := captureStdout(t)
+
+	var stderr bytes.Buffer
+
+	code := run([]string{cmdScan, dir, dangling}, os.Stdout, &stderr)
+	if code != exitFatal {
+		t.Errorf("run(scan %s %s) = %d, want %d", dir, dangling, code,
+			exitFatal)
+	}
+
+	assertFatalOutput(t, stderr.String(), stdout())
+
+	want := "sfdupes: resolve " + dangling + ": "
+	if !strings.Contains(stderr.String(), want) {
+		t.Errorf("stderr = %q, want %q", stderr.String(), want)
+	}
+
+	_, err := os.Stat(path)
+	if !errors.Is(err, fs.ErrNotExist) {
+		t.Errorf("database: stat error %v, want it missing", err)
+	}
+}
+
+// TestRunScanFromSymlinkedWorkingDirectoryRecordsRealPath runs scan .
+// after a cd through home/proj, a symlink to data/proj. The file is
+// recorded under data/proj, its real path.
+func TestRunScanFromSymlinkedWorkingDirectoryRecordsRealPath(t *testing.T) {
+	path := testDBPath(t)
+	t.Setenv(databaseEnv, path)
+
+	dir := realTempDir(t)
+	f := writeFile(t, dir, "data/proj/f", pattern(1, 10))
+
+	err := os.Mkdir(filepath.Join(dir, "home"), 0o750)
 	if err != nil {
 		t.Fatal(err)
 	}
 
-	// link is dropped as a symlink, but link/sub must still be scanned,
+	symlink(t, filepath.Join(dir, "data", "proj"),
-	// not dropped as lying under link.
+		filepath.Join(dir, "home", "proj"))
-	scanOK(t, link, filepath.Join(link, "sub"))
 
-	db, err := openDB(path, reportParams)
+	// t.Chdir also sets PWD to the path through the symlink, as a
+	// shell does after cd.
+	t.Chdir(filepath.Join(dir, "home", "proj"))
+
+	scanOK(t, ".")
+
+	if got := storedPaths(t, path); !slices.Equal(got, []string{f}) {
+		t.Errorf("records = %q, want %q", got, []string{f})
+	}
+}
+
+// TestRunScanFollowsSymlinkBeforeDotDot scans a path with a ".." after
+// home/proj, a symlink to data/proj: home/proj/.. from dir, and .. after
+// a cd through home/proj. As with realpath, the ".." counts from
+// data/proj, so data is scanned and home is not.
+func TestRunScanFollowsSymlinkBeforeDotDot(t *testing.T) {
+	for _, tc := range []struct{ wd, operand string }{
+		{"", "home/proj/.."},
+		{"home/proj", ".."},
+	} {
+		t.Run(tc.operand, func(t *testing.T) {
+			path := testDBPath(t)
+			t.Setenv(databaseEnv, path)
+
+			dir := realTempDir(t)
+			f := writeFile(t, dir, "data/proj/f", pattern(1, 10))
+			g := writeFile(t, dir, "data/g", pattern(2, 10))
+			writeFile(t, dir, "home/h", pattern(3, 10))
+			symlink(t, filepath.Join(dir, "data", "proj"),
+				filepath.Join(dir, "home", "proj"))
+
+			// t.Chdir also sets PWD to the path given, as a shell does
+			// after cd.
+			t.Chdir(filepath.Join(dir, tc.wd))
+
+			scanOK(t, tc.operand)
+
+			want := []string{f, g}
+			slices.Sort(want)
+
+			if got := storedPaths(t, path); !slices.Equal(got, want) {
+				t.Errorf("records = %q, want %q", got, want)
+			}
+		})
+	}
+}
+
+// TestRunScanSkipsSymlinkToFIFOOperand scans link, a symlink to a FIFO.
+// The scan warns about the FIFO by its real path, counts it as skipped,
+// and exits 0.
+func TestRunScanSkipsSymlinkToFIFOOperand(t *testing.T) {
+	t.Setenv(databaseEnv, testDBPath(t))
+
+	dir := realTempDir(t)
+	fifo := filepath.Join(dir, "fifo")
+
+	err := unix.Mkfifo(fifo, 0o600)
 	if err != nil {
 		t.Fatal(err)
 	}
 
-	t.Cleanup(func() { _ = db.Close() })
+	link := filepath.Join(dir, "link")
+	symlink(t, fifo, link)
 
-	recordByPath(t, dbRecords(t, db), filepath.Join(link, "sub", "f"))
+	stderr := scanOK(t, link)
+
+	warning := "walk " + fifo + ": skipping FIFO operand\n"
+	if !strings.Contains(stderr, warning) {
+		t.Errorf("stderr = %q, want %q", stderr, warning)
+	}
+
+	summary := "scan: 0 files seen (0 added, 0 updated, 0 removed, " +
+		"0 unchanged), 1 skipped\n"
+	if !strings.Contains(stderr, summary) {
+		t.Errorf("stderr = %q, want %q", stderr, summary)
+	}
 }
 
 func TestRunScanSkipsZFSOperand(t *testing.T) {
-	zfs := filepath.Join(t.TempDir(), ".zfs")
+	zfs := filepath.Join(realTempDir(t), ".zfs")
 	f := writeFile(t, zfs, "snapshot/hourly/f", pattern(1, 10))
 
 	// No scan records a file inside a .zfs directory, so the record
@@ -997,7 +1218,7 @@ func TestRunScanSkipsOperandInsideZFS(t *testing.T) {
 	path := testDBPath(t)
 	t.Setenv(databaseEnv, path)
 
-	dir := t.TempDir()
+	dir := realTempDir(t)
 	hourly := filepath.Join(dir, ".zfs", "snapshot", "hourly")
 	writeFile(t, hourly, "f", pattern(1, 10))
 	f := writeFile(t, dir, "f", pattern(2, 10))
@@ -1041,23 +1262,19 @@ func TestRunScanSkipsOperandInsideZFS(t *testing.T) {
 
 // TestRunScanSkipsOperandThroughSymlinkIntoZFS scans snaps/daily, where
 // snaps is a symlink to pool/.zfs/snapshot. The operand is warned about
-// by the path given, counted as skipped, and not walked.
+// by its real path, counted as skipped, and not walked.
 func TestRunScanSkipsOperandThroughSymlinkIntoZFS(t *testing.T) {
 	t.Setenv(databaseEnv, testDBPath(t))
 
-	dir := t.TempDir()
+	dir := realTempDir(t)
 	writeFile(t, dir, "pool/.zfs/snapshot/daily/f", pattern(1, 10))
 
 	snaps := filepath.Join(dir, "snaps")
+	symlink(t, filepath.Join(dir, "pool", ".zfs", "snapshot"), snaps)
 
-	err := os.Symlink(filepath.Join(dir, "pool", ".zfs", "snapshot"), snaps)
+	stderr := scanOK(t, filepath.Join(snaps, "daily"))
-	if err != nil {
-		t.Fatal(err)
-	}
-
-	daily := filepath.Join(snaps, "daily")
-	stderr := scanOK(t, daily)
 
+	daily := filepath.Join(dir, "pool", ".zfs", "snapshot", "daily")
 	warning := "walk " + daily + ": skipping operand inside a .zfs directory\n"
 	summary := "scan: 0 files seen (0 added, 0 updated, 0 removed, " +
 		"0 unchanged), 1 skipped\n"
@@ -1069,24 +1286,19 @@ func TestRunScanSkipsOperandThroughSymlinkIntoZFS(t *testing.T) {
 }
 
 // TestRunScanWalksOperandThroughSymlink scans data/daily, where data is
-// a symlink to a directory outside any .zfs directory. The operand is
+// a symlink to pool/data. The operand is scanned as usual, and its file
-// scanned as usual, and its file is recorded by the path given.
+// is recorded by its real path.
 func TestRunScanWalksOperandThroughSymlink(t *testing.T) {
 	path := testDBPath(t)
 	t.Setenv(databaseEnv, path)
 
-	dir := t.TempDir()
+	dir := realTempDir(t)
-	writeFile(t, dir, "pool/data/daily/f", pattern(1, 10))
+	f := writeFile(t, dir, "pool/data/daily/f", pattern(1, 10))
 
 	data := filepath.Join(dir, "data")
+	symlink(t, filepath.Join(dir, "pool", "data"), data)
 
-	err := os.Symlink(filepath.Join(dir, "pool", "data"), data)
+	stderr := scanOK(t, filepath.Join(data, "daily"))
-	if err != nil {
-		t.Fatal(err)
-	}
-
-	daily := filepath.Join(data, "daily")
-	stderr := scanOK(t, daily)
 
 	summary := "scan: 1 files seen (1 added, 0 updated, 0 removed, " +
 		"0 unchanged), 0 skipped\n"
@@ -1094,14 +1306,9 @@ func TestRunScanWalksOperandThroughSymlink(t *testing.T) {
 		t.Errorf("stderr = %q, want %q", stderr, summary)
 	}
 
-	db, err := openDB(path, reportParams)
+	if got := storedPaths(t, path); !slices.Equal(got, []string{f}) {
-	if err != nil {
+		t.Errorf("records = %q, want %q", got, []string{f})
-		t.Fatal(err)
 	}
-
-	t.Cleanup(func() { _ = db.Close() })
-
-	recordByPath(t, dbRecords(t, db), filepath.Join(daily, "f"))
 }
 
 func TestRunReportSucceeds(t *testing.T) {
@@ -1257,7 +1464,7 @@ func assertRunsUseDatabase(t *testing.T, dir, name string) {
 }
 
 func TestRunDatabasePathUsedAsGiven(t *testing.T) {
-	// README §Database: the path names the database file exactly. In
+	// README §Settings: the path names the database file exactly. In
 	// SQLite's connection string an unescaped ? or # would end the file
 	// name and % would start an escape, and a path starting with //
 	// could be read as a host name. %25 is a valid escape, so unescaped
@@ -1302,9 +1509,8 @@ func holdScanLock(t *testing.T, path string) {
 }
 
 func TestRunSecondScanFails(t *testing.T) {
-	// README §Database: while one scan holds the lock, a second scan
+	// README §Database: a second scan that finds the lock held fails
-	// fails at once, naming the lock file, without opening the
+	// at once, naming the lock file, without opening the database.
-	// database.
 	path := testDBPath(t)
 	t.Setenv(databaseEnv, path)
 
@@ -1363,7 +1569,7 @@ func assertSecondScanFails(t *testing.T, path string) {
 }
 
 func TestRunSecondScanThroughSymlinkFails(t *testing.T) {
-	// README §Database: every path to one database names the same lock
+	// README §Database: a path through a symlink names the same lock
 	// file, so while a scan holds it through one path, a scan through
 	// another fails, naming the lock file beside the database's real
 	// path.
@@ -1468,8 +1674,8 @@ func TestRunReportsDuringScan(t *testing.T) {
 }
 
 func TestRunStdoutClosedIsFatal(t *testing.T) {
-	// README §Error handling: a stdout write failure exits 1, reported
+	// README §Error handling: a failed write to stdout is a fatal error,
-	// in one line on stderr.
+	// exit 1, reported on stderr starting with "sfdupes:".
 	for _, name := range []string{cmdReport, cmdTrees, cmdInfo} {
 		t.Run(name, func(t *testing.T) {
 			t.Setenv(databaseEnv, testDBPath(t))
@@ -1518,9 +1724,13 @@ func TestStdoutWriteErrorPropagates(t *testing.T) {
 	scanFixture(t)
 
 	cases := map[string]func(context.Context, io.Writer) error{
-		cmdReport: runReport,
+		cmdReport: func(ctx context.Context, w io.Writer) error {
-		cmdTrees:  runTrees,
+			return runReport(ctx, nil, w)
-		cmdInfo:   runInfo,
+		},
+		cmdTrees: func(ctx context.Context, w io.Writer) error {
+			return runTrees(ctx, nil, w)
+		},
+		cmdInfo: runInfo,
 	}
 
 	for name, fn := range cases {

internal/sfdupes/db.go

@@ -1,4 +1,4 @@
-package main
+package sfdupes
 
 import (
 	"context"
@@ -146,33 +146,44 @@ var errHashSize = errors.New("hash is not 32 bytes")
 
 // databasePath resolves the database location: SFDUPES_DATABASE when
 // set and non-empty, the compiled-in default otherwise. It returns the
-// path, with the working directory, its symlinks resolved, put in front
+// path, made absolute by absolutePath, and where the path came from,
-// of it when it is relative, and where the path came from, "default" or
+// "default" or "from SFDUPES_DATABASE", for the line each subcommand
-// "from SFDUPES_DATABASE", for the line each subcommand prints first on
+// prints first on stderr.
-// stderr.
 func databasePath() (string, string, error) {
 	path, source := defaultDatabasePath, "default"
 	if p := os.Getenv(databaseEnv); p != "" {
 		path, source = p, "from "+databaseEnv
 	}
 
-	if filepath.IsAbs(path) {
+	abs, err := absolutePath(path)
-		return path, source, nil
-	}
-
-	// The working directory as the kernel reports it, with no symlink
-	// in it, as README "Database" says. os.Getwd may return PWD
-	// instead, which can name it through a symlink.
-	wd, err := unix.Getwd()
 	if err != nil {
 		return "", "", fmt.Errorf("resolve database path %s: %w", path, err)
 	}
 
-	// Not filepath.Abs or filepath.Join: they clean the path, which
+	return abs, source, nil
-	// drops each ".." together with the directory name before it. When
+}
-	// that directory is a symlink, the cleaned path names another file.
+
+// absolutePath returns path unchanged when it is absolute, and
+// otherwise the working directory, a "/" and path. The working
+// directory is the one the kernel reports, with no symlink in it;
+// os.Getwd may return PWD instead, which can name it through a symlink.
+// The result is not cleaned, as filepath.Abs and filepath.Join would
+// clean it. Cleaning drops each ".." together with the directory name
+// before it. When that name is a symlink, the cleaned path names
+// another file than the one the system reaches by following the symlink
+// first.
+func absolutePath(path string) (string, error) {
+	if filepath.IsAbs(path) {
+		return path, nil
+	}
+
+	wd, err := unix.Getwd()
+	if err != nil {
+		return "", err
+	}
+
 	// The working directory ends in "/" only when it is the root.
-	return strings.TrimSuffix(wd, "/") + "/" + path, source, nil
+	return strings.TrimSuffix(wd, "/") + "/" + path, nil
 }
 
 // createDatabaseDirectory creates the directory the database at path

internal/sfdupes/db_test.go

@@ -1,4 +1,4 @@
-package main
+package sfdupes //nolint:testpackage // calls the unexported database openers
 
 import (
 	"context"

internal/sfdupes/dwim.go

@@ -0,0 +1,37 @@
+package sfdupes
+
+import (
+	"context"
+	"fmt"
+	"io"
+	"os"
+	"runtime"
+)
+
+// runDwim implements the dwim subcommand: it runs what "sfdupes scan
+// root" runs with no flags, then what "sfdupes trees" runs, and ends
+// with a line on stderr saying how to print the report again. The dwim
+// command passes "/" as root. It catches SIGINT and SIGTERM as scan
+// does, but only during the scan. An error from the scan, an interrupt
+// included, ends it before the report. During the report, a signal
+// ends it at once, as it ends trees.
+func runDwim(ctx context.Context, root string, stdout io.Writer) error {
+	scanCtx, stop := interruptContext(ctx)
+	err := runScan(scanCtx, []string{root}, runtime.NumCPU(), false, false)
+
+	stop()
+
+	if err != nil {
+		return err
+	}
+
+	err = runTrees(ctx, nil, stdout)
+	if err != nil {
+		return err
+	}
+
+	fmt.Fprintln(os.Stderr,
+		`dwim: run "sfdupes trees" to print this report again`)
+
+	return nil
+}

internal/sfdupes/dwim_test.go

@@ -0,0 +1,83 @@
+package sfdupes //nolint:testpackage // calls the unexported runDwim
+
+import (
+	"bytes"
+	"path/filepath"
+	"strings"
+	"testing"
+)
+
+func TestRunDwimPrintsLargestTreesFirst(t *testing.T) {
+	// dwim scans its root, then prints the trees report, the larger of
+	// two duplicate-tree pairs first, and ends by saying how to print
+	// the report again.
+	t.Setenv(databaseEnv, testDBPath(t))
+
+	root := realTempDir(t)
+
+	small := []string{
+		filepath.Dir(writeFile(t, root, "a1/f.bin", pattern(1, 300))),
+		filepath.Dir(writeFile(t, root, "a2/f.bin", pattern(1, 300))),
+	}
+	large := []string{
+		filepath.Dir(writeFile(t, root, "b1/f.bin", pattern(2, 5000))),
+		filepath.Dir(writeFile(t, root, "b2/f.bin", pattern(2, 5000))),
+	}
+
+	var stdout bytes.Buffer
+
+	stderr := captureStderr(t)
+
+	err := runDwim(t.Context(), root, &stdout)
+	if err != nil {
+		t.Fatalf("runDwim: %v; stderr: %s", err, stderr())
+	}
+
+	lines := strings.Split(strings.TrimSuffix(stdout.String(), "\n"), "\n")
+	if len(lines) != 3 {
+		t.Fatalf("stdout = %q, want a header and two groups",
+			stdout.String())
+	}
+
+	wantFirst := large[0] + "\t" + large[1] + "\t1\t5000\t"
+	if !strings.HasPrefix(lines[1], wantFirst) {
+		t.Errorf("first group = %q, want it to start %q", lines[1], wantFirst)
+	}
+
+	wantSecond := small[0] + "\t" + small[1] + "\t1\t300\t"
+	if !strings.HasPrefix(lines[2], wantSecond) {
+		t.Errorf("second group = %q, want it to start %q",
+			lines[2], wantSecond)
+	}
+
+	last := "\ndwim: run \"sfdupes trees\" to print this report again\n"
+	if got := stderr(); !strings.HasSuffix(got, last) {
+		t.Errorf("stderr = %q, want it to end %q", got, last)
+	}
+}
+
+func TestRunDwimScanErrorPrintsNoReport(t *testing.T) {
+	// A fatal scan error ends dwim before the report: a root that does
+	// not exist fails the scan as it fails scan itself.
+	t.Setenv(databaseEnv, testDBPath(t))
+
+	missing := filepath.Join(realTempDir(t), "missing")
+
+	var stdout bytes.Buffer
+
+	stderr := captureStderr(t)
+
+	err := runDwim(t.Context(), missing, &stdout)
+	if err == nil {
+		t.Fatal("runDwim on a missing root: error = nil, want it fatal")
+	}
+
+	if got := stdout.String(); got != "" {
+		t.Errorf("stdout = %q, want no report", got)
+	}
+
+	if got := stderr(); strings.Contains(got, "trees:") ||
+		strings.Contains(got, "dwim:") {
+		t.Errorf("stderr = %q, want nothing from trees or dwim", got)
+	}
+}

internal/sfdupes/exclude.go

@@ -1,4 +1,4 @@
-package main
+package sfdupes
 
 // This file holds two rules for the walk (README "Rules for the walk"):
 // the default excludes, the paths a scan's walk does not enter below an

internal/sfdupes/exclude_darwin.go

@@ -1,6 +1,6 @@
 //go:build darwin
 
-package main
+package sfdupes
 
 import (
 	"slices"

internal/sfdupes/exclude_other.go

@@ -1,6 +1,6 @@
 //go:build !darwin
 
-package main
+package sfdupes
 
 import (
 	"fmt"

internal/sfdupes/exclude_test.go

@@ -1,4 +1,4 @@
-package main
+package sfdupes //nolint:testpackage // checks the unexported defaultExcludes
 
 import (
 	"bytes"
@@ -17,7 +17,9 @@ import (
 func TestDefaultExcludes(t *testing.T) {
 	t.Parallel()
 
-	// README "Rules for the walk": each system's list.
+	// README "Rules for the walk": the Linux and macOS lists, and none
+	// on any other system. The Windows list exists in the code only: the
+	// binary does not build for Windows, so the README leaves it out.
 	cases := map[string][]string{
 		goosLinux: {"/proc", "/sys", "/dev", "/run", "/tmp", "/var/tmp"},
 		goosDarwin: {
@@ -284,7 +286,7 @@ func TestRunScanTempDirOperand(t *testing.T) {
 	path := testDBPath(t)
 	t.Setenv(databaseEnv, path)
 
-	dir := t.TempDir()
+	dir := realTempDir(t)
 	if !underAnyRoot(dir, defaultExcludes(runtime.GOOS)) {
 		t.Skip(dir + " is not inside a default exclude")
 	}

internal/sfdupes/info.go

@@ -1,4 +1,4 @@
-package main
+package sfdupes
 
 import (
 	"context"

internal/sfdupes/info_test.go

@@ -1,4 +1,4 @@
-package main
+package sfdupes //nolint:testpackage // seeds the database with unexported scanRec
 
 import (
 	"fmt"

internal/sfdupes/progress.go

@@ -1,4 +1,4 @@
-package main
+package sfdupes
 
 import (
 	"fmt"

internal/sfdupes/progress_test.go

@@ -1,4 +1,4 @@
-package main
+package sfdupes //nolint:testpackage // drives the unexported startProgress
 
 import (
 	"fmt"

internal/sfdupes/report.go

@@ -1,4 +1,4 @@
-package main
+package sfdupes
 
 import (
 	"context"
@@ -7,6 +7,7 @@ import (
 	"fmt"
 	"io"
 	"os"
+	"path/filepath"
 	"slices"
 	"strings"
 	"time"
@@ -41,10 +42,11 @@ func reportPhase(name string) string {
 }
 
 // runReport implements the report subcommand: it prints the file-level
-// duplicates report as TSV on stdout. It never touches the scanned
+// duplicates report as TSV on stdout, from the records at or below the
-// filesystem; its only I/O is the database, stdout, and stderr. It
+// given paths, or from every record when none is given. It never
-// names the database on stderr before it opens it. Any database
+// touches the scanned filesystem; its only I/O is the database,
-// problem, including a missing database, is fatal.
+// stdout, and stderr. It names the database on stderr before it opens
+// it. Any database problem, including a missing database, is fatal.
 //
 // The work runs in two phases, each under a progress display of its
 // own on stderr: open (open the database) and read (read the number of
@@ -52,7 +54,12 @@ func reportPhase(name string) string {
 // order, writing each size's duplicate groups to stdout once that size
 // is read; see readReport). Each display ends before the next phase
 // starts, and before an error is returned to be printed.
-func runReport(ctx context.Context, stdout io.Writer) error {
+func runReport(ctx context.Context, args []string, stdout io.Writer) error {
+	paths, err := reportPaths(args)
+	if err != nil {
+		return err
+	}
+
 	dbPath, source, err := databasePath()
 	if err != nil {
 		return err
@@ -83,7 +90,7 @@ func runReport(ctx context.Context, stdout io.Writer) error {
 		label: reportPhase("read"), unit: "records", total: -1,
 		waitingFor: countingRecords, stalledOn: "db/out",
 	})
-	report, err := readReport(ctx, db, dbPath, stdout, prog)
+	report, err := readReport(ctx, db, dbPath, paths, stdout, prog)
 
 	prog.finish()
 
@@ -104,11 +111,12 @@ func runReport(ctx context.Context, stdout io.Writer) error {
 // dbPath, as its total, then reads every record in signature order,
 // counting each on prog, and writes the report to stdout: the header
 // line, then the rows of each size's duplicate groups once that size is
-// read. stdout may be the terminal prog is drawn on, so the lines go
+// read. Only the records that inReportPaths selects from paths join a
+// group. stdout may be the terminal prog is drawn on, so the lines go
 // through prog's writer. It returns what it wrote, with the totals for
 // the summary line.
 func readReport(ctx context.Context, db *sql.DB, dbPath string,
-	stdout io.Writer, prog *progress,
+	paths []string, stdout io.Writer, prog *progress,
 ) (*reportWriter, error) {
 	out := prog.writer(stdout)
 	report := &reportWriter{out: out}
@@ -123,6 +131,12 @@ func readReport(ctx context.Context, db *sql.DB, dbPath string,
 	err = loadSignatureRows(ctx, db, prog.setTotal, func(r scanRec) error {
 		prog.increment()
 
+		report.records++
+
+		if !inReportPaths(r.path, paths) {
+			return nil
+		}
+
 		writeErr = report.add(r)
 
 		return writeErr
@@ -154,7 +168,7 @@ func readReport(ctx context.Context, db *sql.DB, dbPath string,
 // records of one size, so it holds only the duplicate groups of the
 // size being read, and writes them, ordered by first path, once a
 // record of a smaller size comes. It counts what the summary line
-// reports.
+// reports; readReport counts the records read.
 type reportWriter struct {
 	out io.Writer
 
@@ -170,8 +184,6 @@ type reportWriter struct {
 // its paths; any other ends them, and one of a smaller size first
 // writes the groups of the size before.
 func (w *reportWriter) add(r scanRec) error {
-	w.records++
-
 	if r.size == w.sig.size && r.head == w.sig.head &&
 		r.tail == w.sig.tail && r.content == w.sig.content {
 		w.paths = append(w.paths, r.path)
@@ -195,10 +207,11 @@ func (w *reportWriter) add(r scanRec) error {
 }
 
 // endGroup ends the paths read with w.sig: two or more are a duplicate
-// group, held with its paths sorted until writeGroups writes it.
+// group, held with its paths sorted until writeGroups writes it. Empty
+// files form no group, since removing one frees nothing.
 func (w *reportWriter) endGroup() {
-	if len(w.paths) < minGroupSize {
+	if len(w.paths) < minGroupSize || w.sig.size == 0 {
-		// A path with no duplicate is dropped, and its slice reused.
+		// The paths are dropped, and their slice reused.
 		w.paths = w.paths[:0]
 
 		return
@@ -245,6 +258,46 @@ func (w *reportWriter) finish() error {
 	return w.writeGroups()
 }
 
+// reportPaths returns the paths given to report or trees, each made
+// absolute by absolutePath and then cleaned. The records hold real
+// paths, with no "." or ".." element and no repeated or trailing
+// slash, so a given path is cleaned to match them. No path is looked up
+// on the filesystem.
+func reportPaths(args []string) ([]string, error) {
+	paths := make([]string, 0, len(args))
+
+	for _, a := range args {
+		abs, err := absolutePath(a)
+		if err != nil {
+			return nil, fmt.Errorf("resolve path %s: %w", escapePath(a), err)
+		}
+
+		paths = append(paths, filepath.Clean(abs))
+	}
+
+	return paths, nil
+}
+
+// inReportPaths reports whether path is one of paths or lies below one
+// of them. Each of paths is clean and absolute, as reportPaths returns
+// it. With no paths, a report covers the whole database, so every path
+// is in it.
+func inReportPaths(path string, paths []string) bool {
+	if len(paths) == 0 {
+		return true
+	}
+
+	for _, p := range paths {
+		// Only the root directory's clean path ends in "/".
+		dir := strings.TrimSuffix(p, "/") + "/"
+		if path == p || strings.HasPrefix(path, dir) {
+			return true
+		}
+	}
+
+	return false
+}
+
 // 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.

internal/sfdupes/report_test.go

@@ -1,4 +1,4 @@
-package main
+package sfdupes //nolint:testpackage // checks the unexported dupeGroup results
 
 import (
 	"bytes"
@@ -80,7 +80,7 @@ func dupeGroups(t *testing.T, db *sql.DB) []dupeGroup {
 
 	var out bytes.Buffer
 
-	_, err := readReport(t.Context(), db, "", &out, nil)
+	_, err := readReport(t.Context(), db, "", nil, &out, nil)
 	if err != nil {
 		t.Fatal(err)
 	}
@@ -126,6 +126,98 @@ func dupeGroupsOf(t *testing.T, recs []scanRec) []dupeGroup {
 	return dupeGroups(t, db)
 }
 
+// TestRunReportPaths runs report with paths on three copies of one
+// file, two of them under /srv/photos, and a fourth copy in
+// /srv/photos2. Only the records at or below the given paths form the
+// groups and the totals, however each path is written.
+//
+//nolint:paralleltest // captureStderr replaces the process-wide os.Stderr
+func TestRunReportPaths(t *testing.T) {
+	h := testHash("h")
+	a, x, y, z := "/a/copy", "/srv/photos/x", "/srv/photos/y", "/srv/photos2/z"
+
+	recs := make([]scanRec, 0, 4)
+	for _, p := range []string{a, x, y, z} {
+		recs = append(recs,
+			scanRec{size: 7, head: h, tail: h, content: h, path: p})
+	}
+
+	t.Setenv(databaseEnv, seedDatabase(t, recs))
+
+	header := "first\tdupe\tsize\n"
+	row := func(first, dupe string) string {
+		return first + "\t" + dupe + "\t7\n"
+	}
+	photos := header + row(x, y)
+
+	cases := map[string]struct {
+		paths   []string
+		want    string
+		summary string
+	}{
+		"directory": {[]string{"/srv/photos"}, photos,
+			"1 duplicate groups, 1 dupe files, 7 B reclaimable"},
+		"trailing slash":  {[]string{"/srv/photos/"}, photos, ""},
+		"dot and dot-dot": {[]string{"/srv/./a/../photos"}, photos, ""},
+		"files":           {[]string{a, z}, header + row(a, z), ""},
+		"overlapping": {[]string{"/srv", "/srv/photos"},
+			header + row(x, y) + row(x, z), ""},
+		"root": {[]string{"/"},
+			header + row(a, x) + row(a, y) + row(a, z), ""},
+		"no record": {[]string{"/srv/photo"}, header,
+			"0 duplicate groups, 0 dupe files, 0 B reclaimable"},
+	}
+
+	for name, tc := range cases {
+		t.Run(name, func(t *testing.T) {
+			var stdout bytes.Buffer
+
+			stderr := captureStderr(t)
+
+			code := run(append([]string{cmdReport}, tc.paths...),
+				&stdout, os.Stderr)
+			if code != exitOK {
+				t.Fatalf("run(report %q) = %d, want %d; stderr: %s",
+					tc.paths, code, exitOK, stderr())
+			}
+
+			if got := stdout.String(); got != tc.want {
+				t.Errorf("stdout = %q, want %q", got, tc.want)
+			}
+
+			// The records read are all four, whatever the paths.
+			summary := "report: 4 records read, " + tc.summary + "\n"
+			if got := stderr(); tc.summary != "" &&
+				!strings.HasSuffix(got, summary) {
+				t.Errorf("stderr = %q, want it to end %q", got, summary)
+			}
+		})
+	}
+}
+
+//nolint:paralleltest // t.Chdir changes the process-wide working directory
+func TestReportPathsMakesRelativePathsAbsolute(t *testing.T) {
+	dir := t.TempDir()
+	t.Chdir(dir)
+
+	wd, err := absolutePath(".")
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	got, err := reportPaths([]string{"photos/", "a/../b", "/c//d"})
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	want := []string{
+		filepath.Join(wd, "photos"), filepath.Join(wd, "b"), "/c/d",
+	}
+	if !slices.Equal(got, want) {
+		t.Errorf("reportPaths = %q, want %q", got, want)
+	}
+}
+
 func TestRunReportEscapesPaths(t *testing.T) {
 	t.Setenv(databaseEnv, seedDatabase(t, awkwardPairRecs()))
 
@@ -172,7 +264,7 @@ func TestReportStdoutFailsWhileReading(t *testing.T) {
 	// Counts the records read, and draws nothing.
 	prog := &progress{now: time.Now}
 
-	_, err = readReport(t.Context(), db, "", failingWriter{}, prog)
+	_, err = readReport(t.Context(), db, "", nil, failingWriter{}, prog)
 	if !errors.Is(err, errWriteFailed) ||
 		!strings.HasPrefix(err.Error(), "write stdout: ") {
 		t.Errorf("error = %v, want write stdout: %v", err, errWriteFailed)
@@ -266,7 +358,7 @@ func TestReadReportOnTerminal(t *testing.T) {
 		waitingFor: countingRecords,
 	}, terminalWidth, time.Hour, time.Now)
 
-	_, err = readReport(t.Context(), db, "", os.Stderr, p)
+	_, err = readReport(t.Context(), db, "", nil, os.Stderr, p)
 
 	p.finish()
 
@@ -434,6 +526,27 @@ func TestDupeGroups(t *testing.T) {
 	}
 }
 
+// TestDupeGroupsLeavesOutEmptyFiles checks that empty files form no
+// duplicate group, while 1-byte files still do.
+func TestDupeGroupsLeavesOutEmptyFiles(t *testing.T) {
+	t.Parallel()
+
+	e, x := sha256.Sum256(nil), testHash("x")
+	recs := []scanRec{
+		{size: 0, head: e, tail: e, content: e, path: "/a/.gitkeep"},
+		{size: 0, head: e, tail: e, content: e, path: "/b/.gitkeep"},
+		{size: 0, head: e, tail: e, content: e, path: "/c/__init__.py"},
+		{size: 1, head: x, tail: x, content: x, path: "/tiny1"},
+		{size: 1, head: x, tail: x, content: x, path: "/tiny2"},
+	}
+
+	groups := dupeGroupsOf(t, recs)
+	if len(groups) != 1 || groups[0].size != 1 ||
+		!slices.Equal(groups[0].paths, []string{"/tiny1", "/tiny2"}) {
+		t.Fatalf("groups = %+v, want only /tiny1 /tiny2 of size 1", groups)
+	}
+}
+
 func TestDupeGroupsContentSeparates(t *testing.T) {
 	t.Parallel()
 

internal/sfdupes/scan.go

@@ -1,4 +1,4 @@
-package main
+package sfdupes
 
 import (
 	"cmp"
@@ -209,29 +209,30 @@ func interrupted(walked int) error {
 	return errInterrupted
 }
 
-// resolveRoots converts each PATH operand to an absolute, lexically
+// resolveRoots converts each PATH operand to its real path: absolute,
-// cleaned path (symlinks are not resolved) and verifies that it
+// with every symlink in it followed. Database records are keyed by
-// exists. Database records are keyed by absolute path, so scan results
+// that path, so scan results depend neither on the working directory
-// must not depend on the working directory.
+// nor on the symlinks an operand was given through. An operand that
+// cannot be resolved, because it or a symlink's target does not exist
+// or cannot be read, is a fatal error before any scanning.
 func resolveRoots(roots []string) ([]string, error) {
-	abs := make([]string, 0, len(roots))
+	resolved := make([]string, 0, len(roots))
 
 	for _, root := range roots {
-		a, err := filepath.Abs(root)
+		a, err := absolutePath(root)
 		if err != nil {
 			return nil, fmt.Errorf("resolve %s: %w", root, err)
 		}
 
-		// A nonexistent operand is a fatal error before any scanning.
+		r, err := filepath.EvalSymlinks(a)
-		_, err = os.Lstat(a)
 		if err != nil {
-			return nil, err
+			return nil, fmt.Errorf("resolve %s: %w", root, err)
 		}
 
-		abs = append(abs, a)
+		resolved = append(resolved, r)
 	}
 
-	return abs, nil
+	return resolved, nil
 }
 
 // pruneRoots drops operands already covered by another operand:
@@ -417,14 +418,16 @@ func (s *scanState) runPhases(ctx context.Context, roots []string,
 
 // walkableRoots returns the operands the walk can start from: regular
 // files, and directories not named .zfs, none of them inside a
-// directory named .zfs. Every other operand is warned about, counted as
+// directory named .zfs. The operands are real paths from resolveRoots,
-// skipped, and dropped. A dropped operand is no longer a root, so the
+// so these checks apply to what a symlink operand points at. Every
-// records stored beneath it are treated as if it had not been given:
+// other operand is warned about, counted as skipped, and dropped. A
-// those under no other root count as outside the roots and are not
+// dropped operand is no longer a root, so the records stored beneath it
-// deleted as unverified. An operand on a filesystem in rules that is not
+// are treated as if it had not been given: those under no other root
-// persistent is dropped the same way, with a line saying so that is not
+// count as outside the roots and are not deleted as unverified. An
-// a warning, and is not counted as skipped. An operand that fails lstat
+// operand on a filesystem in rules that is not persistent is dropped
-// here is kept, and the walk warns about it unless it no longer exists.
+// the same way, with a line saying so that is not a warning, and is not
+// counted as skipped. An operand that fails lstat here is kept, and the
+// walk warns about it unless it no longer exists.
 func (s *scanState) walkableRoots(roots []string, rules walkRules) []string {
 	kept := make([]string, 0, len(roots))
 
@@ -554,7 +557,7 @@ func (s *scanState) walkPhase(events <-chan walkEvent, roots []string) {
 
 		// The space a file takes on disk can change while its size and
 		// mtime stay the same. ZFS, for one, counts a new file's blocks
-		// only seconds after the write.
+		// up to seconds after the write.
 		if old.diskSize != ev.rec.diskSize {
 			s.diskSizes = append(s.diskSizes, ev.rec)
 		}
@@ -894,19 +897,13 @@ func sendEvent(ctx context.Context, events chan<- walkEvent,
 // operandWarning returns the one-line warning for an operand the walk
 // does not start from, naming the path and what it is, or "" for one it
 // does: a regular file, or a directory not named .zfs, that is not
-// inside a directory named .zfs, neither as given nor with its symlinks
+// inside a directory named .zfs. resolveRoots has already followed the
-// resolved. Symlinks are never followed, including as operands.
+// operand's symlinks, so a symlink here is an operand replaced by one
+// after it was resolved, and is not followed.
 func operandWarning(root string, fi fs.FileInfo) string {
 	// The walk never enters a .zfs directory, so it starts from nothing
-	// inside one either, not even through a symlink. An operand whose
+	// inside one either.
-	// symlinks cannot be resolved is checked as given.
+	if slices.Contains(strings.Split(filepath.Dir(root), "/"), ".zfs") {
-	resolved, err := filepath.EvalSymlinks(root)
-	if err != nil {
-		resolved = root
-	}
-
-	if slices.Contains(strings.Split(filepath.Dir(root), "/"), ".zfs") ||
-		slices.Contains(strings.Split(filepath.Dir(resolved), "/"), ".zfs") {
 		return fmt.Sprintf("walk %s: skipping operand inside a .zfs directory",
 			root)
 	}

internal/sfdupes/scan_dev_darwin.go

@@ -1,6 +1,6 @@
 //go:build darwin
 
-package main
+package sfdupes
 
 import "syscall"
 

internal/sfdupes/scan_dev_other.go

@@ -1,6 +1,6 @@
 //go:build !darwin
 
-package main
+package sfdupes
 
 import "syscall"
 

internal/sfdupes/scan_test.go

@@ -1,4 +1,4 @@
-package main
+package sfdupes //nolint:testpackage // drives the unexported syncTree
 
 import (
 	"bytes"
@@ -43,10 +43,16 @@ func writeFile(t *testing.T, dir, name string, data []byte) string {
 }
 
 // diskSizeOf returns the bytes the file at path takes on disk, from its
-// own lstat: st_blocks counts 512-byte units. ZFS counts a new file's
+// own lstat: st_blocks counts 512-byte units. ZFS counts a write's
-// blocks only seconds after the write, and fsync does not hasten that.
+// blocks only when it commits the write, up to seconds later, and one
-// A test therefore calls unix.Sync, which waits for it, before the scan
+// commit can take the file through several growing sizes. So this value
-// whose disk_size it compares with this.
+// can change at any moment. Neither fsync nor unix.Sync hastens that,
+// but a unix.Sync call often takes long enough that the blocks are
+// counted when it returns. A test that needs the value to change waits
+// for the change. A test that compares it with a scan's disk_size reads
+// it before and after the scan. The rewrite test rescans until the two
+// reads match, then compares exactly. The other two tests fail only on
+// a disk_size outside the two reads.
 func diskSizeOf(t *testing.T, path string) int64 {
 	t.Helper()
 
@@ -1082,12 +1088,13 @@ func TestScanOneFilesystemWalksNestedFileOperand(t *testing.T) {
 	}
 }
 
-// buildSmokeTree recreates the README smoke-test filesystem layout
+// buildSmokeTree recreates the tree of the test under README
-// with deterministic content and returns the tree root.
+// "Definition of done" with deterministic content and returns the tree
+// root.
 func buildSmokeTree(t *testing.T) string {
 	t.Helper()
 
-	dir := t.TempDir()
+	dir := realTempDir(t)
 	one := pattern(10, 2000)
 	f1 := pattern(30, 3000)
 	f2 := pattern(40, 100)
@@ -1178,11 +1185,12 @@ func assertSmokeDupeGroups(t *testing.T, dir string, db *sql.DB) {
 	t.Helper()
 
 	groups := dupeGroups(t, db)
-	if len(groups) != 5 {
+	if len(groups) != 4 {
-		t.Fatalf("len(groups) = %d, want 5", len(groups))
+		t.Fatalf("len(groups) = %d, want 4", len(groups))
 	}
 
-	wantSizes := []int64{3000, 2000, 100, 1, 0}
+	// The empty files empty1 and empty2 form no group.
+	wantSizes := []int64{3000, 2000, 100, 1}
 	for i, g := range groups {
 		if g.size != wantSizes[i] {
 			t.Errorf("groups[%d].size = %d, want %d",
@@ -1447,20 +1455,26 @@ func TestScanStoresDiskSize(t *testing.T) {
 
 	unix.Sync() // see diskSizeOf
 
-	want := diskSizeOf(t, p)
+	size := diskSizeOf(t, p)
-	if want == 0 || want >= length {
+	if size == 0 || size >= length {
 		t.Fatalf("the file takes %d bytes on disk, want more than none "+
-			"and fewer than its length %d", want, length)
+			"and fewer than its length %d", size, length)
 	}
 
 	for _, operand := range []string{filepath.Dir(p), p} {
 		db := openTestDB(t)
+
+		// ZFS may count the blocks during the scan; see diskSizeOf.
+		before := diskSizeOf(t, p)
+
 		syncTree(t, db, operand)
 
+		after := diskSizeOf(t, p)
+
 		got := recordByPath(t, dbRecords(t, db), p).diskSize
-		if got != want {
+		if got < before || got > after {
-			t.Errorf("scan of %s: disk_size = %d, want %d",
+			t.Errorf("scan of %s: disk_size = %d, want %d to %d",
-				operand, got, want)
+				operand, got, before, after)
 		}
 	}
 }
@@ -1478,7 +1492,7 @@ func TestSyncScanRewriteUpdatesDiskSize(t *testing.T) {
 
 	syncTree(t, db, dir)
 
-	before := recordByPath(t, dbRecords(t, db), p).diskSize
+	recorded := recordByPath(t, dbRecords(t, db), p).diskSize
 
 	pokeAt(t, p, 512*1024, pattern(7, 64*1024))
 
@@ -1491,22 +1505,53 @@ func TestSyncScanRewriteUpdatesDiskSize(t *testing.T) {
 		t.Fatal(err)
 	}
 
-	unix.Sync() // see diskSizeOf
+	// Wait for ZFS to count the write; see diskSizeOf.
+	deadline := time.Now().Add(30 * time.Second)
+	for diskSizeOf(t, p) == recorded {
+		if time.Now().After(deadline) {
+			t.Fatalf("the file still takes %d bytes on disk 30 seconds "+
+				"after the write into its hole", recorded)
+		}
 
-	want := diskSizeOf(t, p)
+		unix.Sync()
-	if want == before {
-		t.Fatalf("the file still takes %d bytes on disk after the write "+
-			"into its hole", want)
 	}
 
-	st := syncTree(t, db, dir)
+	// ZFS may still be counting, so the size may change during a rescan.
-	if st != (scanStats{walked: 1, updated: 1}) {
+	// Only a rescan with the same size on both sides of it can be compared
-		t.Fatalf("rescan stats = %+v, want 1 updated", st)
+	// exactly. A rescan that keeps the old size still fails, because the
-	}
+	// wait made before differ from it.
+	for {
+		before := diskSizeOf(t, p)
 
-	got := recordByPath(t, dbRecords(t, db), p).diskSize
+		st := syncTree(t, db, dir)
-	if got != want {
+
-		t.Errorf("disk_size = %d, want %d", got, want)
+		after := diskSizeOf(t, p)
+
+		if st != (scanStats{walked: 1, updated: 1}) {
+			t.Fatalf("rescan stats = %+v, want 1 updated", st)
+		}
+
+		if before == after {
+			got := recordByPath(t, dbRecords(t, db), p).diskSize
+			if got != after {
+				t.Errorf("disk_size = %d, want %d", got, after)
+			}
+
+			return
+		}
+
+		if time.Now().After(deadline) {
+			t.Fatalf("the size on disk was still changing 30 seconds after "+
+				"the write into its hole: %d, then %d", before, after)
+		}
+
+		// A later mtime makes the next rescan read the file again.
+		later = later.Add(time.Second)
+
+		err = os.Chtimes(p, later, later)
+		if err != nil {
+			t.Fatal(err)
+		}
 	}
 }
 
@@ -1532,15 +1577,21 @@ func TestSyncScanUnchangedUpdatesDiskSize(t *testing.T) {
 
 	unix.Sync() // see diskSizeOf
 
+	// ZFS may count the blocks during the rescan; see diskSizeOf.
+	before := diskSizeOf(t, p)
+
 	// A file read again would count as updated.
 	st := syncTree(t, db, dir)
+
+	after := diskSizeOf(t, p)
+
 	if st != (scanStats{walked: 1, unchanged: 1}) {
 		t.Fatalf("rescan stats = %+v, want 1 unchanged", st)
 	}
 
 	got := recordByPath(t, dbRecords(t, db), p).diskSize
-	if want := diskSizeOf(t, p); got != want {
+	if got < before || got > after {
-		t.Errorf("disk_size = %d, want %d", got, want)
+		t.Errorf("disk_size = %d, want %d to %d", got, before, after)
 	}
 }
 
@@ -2260,33 +2311,24 @@ func TestUnderRoot(t *testing.T) {
 }
 
 // TestRunScanPassesOverDatabase scans a tree that holds the scan's own
-// database, reached directly and through a symlinked directory. The
+// database, and in one case also a hard link to the database file. The
-// walk passes over the database file, its -wal and -shm files and its
+// walk knows the database's files by device ID and inode number, so it
-// .lock file with no line and no count, and the record an earlier scan
+// passes over the database file, its -wal and -shm files, its .lock
-// left for the .lock file is deleted. A rescan of the unchanged tree
+// file and the hard link with no line and no count. The record an
-// updates nothing, and report lists none of the database's files.
+// earlier scan left for the .lock file is deleted. A rescan of the
+// unchanged tree updates nothing, and report lists none of the
+// database's files.
 func TestRunScanPassesOverDatabase(t *testing.T) {
-	for _, viaSymlink := range []bool{false, true} {
+	for _, viaHardLink := range []bool{false, true} {
-		t.Run(fmt.Sprintf("via symlink %v", viaSymlink), func(t *testing.T) {
+		t.Run(fmt.Sprintf("via hard link %v", viaHardLink), func(t *testing.T) {
-			base := t.TempDir()
+			tree := realTempDir(t)
-			tree := filepath.Join(base, "real", "tree")
+			hardLink := filepath.Join(tree, "hardlink")
-			operand := tree
 
 			writeFile(t, tree, "a", pattern(1, 100))
 			writeFile(t, tree, "b", pattern(1, 100))
 			writeFile(t, tree, "empty1", nil)
 			writeFile(t, tree, "empty2", nil)
 
-			if viaSymlink {
-				err := os.Symlink(filepath.Join(base, "real"),
-					filepath.Join(base, "link"))
-				if err != nil {
-					t.Fatal(err)
-				}
-
-				operand = filepath.Join(base, "link", "tree")
-			}
-
 			dbPath := filepath.Join(tree, "db.sqlite")
 			t.Setenv(databaseEnv, dbPath)
 
@@ -2296,7 +2338,7 @@ func TestRunScanPassesOverDatabase(t *testing.T) {
 			}
 
 			err = applyChanges(t.Context(), db, []scanRec{
-				{path: filepath.Join(operand, "db.sqlite.lock")},
+				{path: filepath.Join(tree, "db.sqlite.lock")},
 			}, nil, nil)
 			if err != nil {
 				t.Fatal(err)
@@ -2304,17 +2346,30 @@ func TestRunScanPassesOverDatabase(t *testing.T) {
 
 			closeScanDatabase(t.Context(), db, dbPath)
 
-			assertScanSummary(t,
+			if viaHardLink {
+				err = os.Link(dbPath, hardLink)
+				if err != nil {
+					t.Fatal(err)
+				}
+			}
+
+			stderr := assertScanSummary(t,
 				"4 files seen (4 added, 0 updated, 1 removed, 0 unchanged)",
-				operand)
+				tree)
-			assertScanSummary(t,
+			stderr += assertScanSummary(t,
 				"4 files seen (0 added, 0 updated, 0 removed, 4 unchanged)",
-				operand)
+				tree)
+
+			if strings.Contains(stderr, hardLink) {
+				t.Errorf("scan stderr = %q, want no line naming %s",
+					stderr, hardLink)
+			}
 
 			report := runStdout(t, cmdReport)
 			if strings.Contains(report, "db.sqlite") ||
-				!strings.Contains(report, filepath.Join(operand, "empty2")) {
+				strings.Contains(report, hardLink) ||
-				t.Errorf("report = %q, want the empty files and none of "+
+				!strings.Contains(report, filepath.Join(tree, "b")) {
+				t.Errorf("report = %q, want a and b and none of "+
 					"the database's files", report)
 			}
 		})
@@ -2338,8 +2393,9 @@ func TestRunScanPassesOverDatabaseOperands(t *testing.T) {
 
 // assertScanSummary scans operands and fails the test unless the
 // summary line gives counts with nothing skipped, and the line naming
-// the database is the only one that names one of its files.
+// the database is the only one that names one of its files. It returns
-func assertScanSummary(t *testing.T, counts string, operands ...string) {
+// everything the scan printed to stderr.
+func assertScanSummary(t *testing.T, counts string, operands ...string) string {
 	t.Helper()
 
 	stderr := scanOK(t, operands...)
@@ -2353,4 +2409,6 @@ func assertScanSummary(t *testing.T, counts string, operands ...string) {
 		t.Errorf("scan %q: stderr = %q, want only the line naming the "+
 			"database to name one of its files", operands, stderr)
 	}
+
+	return stderr
 }

internal/sfdupes/trees.go

@@ -1,4 +1,4 @@
-package main
+package sfdupes
 
 import (
 	"context"
@@ -37,8 +37,9 @@ func treesPhase(name string) string {
 
 // runTrees implements the trees subcommand: it reads every record from
 // the database in path order, reconstructs the directory hierarchy from
-// the record paths, computes a Merkle-style digest per directory, and
+// the paths of the records at or below the given paths (of every record
-// prints maximal duplicate-tree groups as TSV on stdout. It never
+// when none is given), computes a Merkle-style digest per directory,
+// and prints maximal duplicate-tree groups as TSV on stdout. It never
 // touches the scanned filesystem; its only I/O is the database, stdout,
 // and stderr. It names the database on stderr before it opens it. Any
 // database problem, including a missing database, is fatal.
@@ -49,7 +50,12 @@ func treesPhase(name string) string {
 // hierarchy), group (group the directories by digest) and write (write
 // the groups to stdout). Each display ends before the next phase
 // starts, and before an error is returned to be printed.
-func runTrees(ctx context.Context, stdout io.Writer) error {
+func runTrees(ctx context.Context, args []string, stdout io.Writer) error {
+	paths, err := reportPaths(args)
+	if err != nil {
+		return err
+	}
+
 	dbPath, source, err := databasePath()
 	if err != nil {
 		return err
@@ -78,7 +84,7 @@ func runTrees(ctx context.Context, stdout io.Writer) error {
 		label: treesPhase("read"), unit: "records", total: -1,
 		waitingFor: countingRecords, stalledOn: "db",
 	})
-	records, super, allDirs, err := readTree(ctx, db, prog)
+	records, super, allDirs, err := readTree(ctx, db, paths, prog)
 
 	prog.finish()
 
@@ -117,10 +123,17 @@ func runTrees(ctx context.Context, stdout io.Writer) error {
 }
 
 // readTree gives prog the number of records in db as its total, then
-// reads every record in path order into the directory hierarchy,
+// reads every record in path order, counting each on prog. It adds the
-// counting each on prog. It returns the number of records read, the
+// records that inReportPaths selects from paths to the directory
-// super-root and every directory.
+// hierarchy. It returns the number of records read, the super-root and
-func readTree(ctx context.Context, db *sql.DB,
+// every directory at or below one of paths.
+//
+// A directory above every one of paths holds only the selected records
+// under it, so its digest does not describe it. It is left out of the
+// directories returned. A directory whose parent is left out gets the
+// super-root as its parent, so suppressed never judges its group by
+// that parent's digest.
+func readTree(ctx context.Context, db *sql.DB, paths []string,
 	prog *progress,
 ) (int, *treeNode, []*treeNode, error) {
 	records := 0
@@ -130,7 +143,10 @@ func readTree(ctx context.Context, db *sql.DB,
 		records++
 
 		prog.increment()
-		tree.add(r)
+
+		if inReportPaths(r.path, paths) {
+			tree.add(r)
+		}
 	})
 	if err != nil {
 		return 0, nil, nil, err
@@ -138,7 +154,21 @@ func readTree(ctx context.Context, db *sql.DB,
 
 	super, allDirs := tree.finish()
 
-	return records, super, allDirs, nil
+	dirs := allDirs[:0]
+
+	for _, d := range allDirs {
+		if !inReportPaths(d.path, paths) {
+			continue
+		}
+
+		if !inReportPaths(d.parent.path, paths) {
+			d.parent = super
+		}
+
+		dirs = append(dirs, d)
+	}
+
+	return records, super, dirs, nil
 }
 
 // writeTreeGroups writes dupes to stdout as TSV, a header line and then
@@ -301,7 +331,9 @@ func fileEntry(name string, r scanRec) string {
 // collectTreeGroups groups directories by digest, counting each one on
 // prog as it is grouped, and returns every maximal group with two or
 // more members, each group's members sorted by path, groups ordered by
-// tree size descending then by first path ascending.
+// tree size descending then by first path ascending. A group whose
+// trees hold 0 bytes is left out, since removing one frees nothing. The
+// groups it implies hold 0 bytes too, so leaving it out hides nothing.
 func collectTreeGroups(allDirs []*treeNode, super *treeNode,
 	prog *progress,
 ) [][]*treeNode {
@@ -315,7 +347,9 @@ func collectTreeGroups(allDirs []*treeNode, super *treeNode,
 	var dupes [][]*treeNode
 
 	for _, g := range groups {
-		if len(g) < minGroupSize || suppressed(g, super) {
+		// The members share a digest, so they share a total size.
+		if len(g) < minGroupSize || g[0].totalSize == 0 ||
+			suppressed(g, super) {
 			continue
 		}
 

internal/sfdupes/trees_test.go

@@ -1,7 +1,8 @@
-package main
+package sfdupes //nolint:testpackage // checks the unexported treeNode results
 
 import (
 	"bytes"
+	"crypto/sha256"
 	"database/sql"
 	"os"
 	"slices"
@@ -15,9 +16,9 @@ import (
 const treesOpenLine = "[1/4] open: opening the database, elapsed 0s, " +
 	"remain unknown"
 
-// smokeTreeRecs mirrors the README smoke-test tree layout: /d/t1 and
+// smokeTreeRecs mirrors the tree of the test under README "Definition
-// /d/t2 are identical, /d/t3 differs from them only by one filename.
+// of done": /d/t1 and /d/t2 are identical, /d/t3 differs from them only
-// Each file takes one 4 KiB block on disk.
+// by one filename. Each file takes one 4 KiB block on disk.
 func smokeTreeRecs() []scanRec {
 	f1Head, f1Tail, f1Content := testHash("f1h"), testHash("f1t"), testHash("f1c")
 	f2Head, f2Tail, f2Content := testHash("f2h"), testHash("f2t"), testHash("f2c")
@@ -211,6 +212,55 @@ func TestRunTreesEscapesPaths(t *testing.T) {
 	}
 }
 
+// TestRunTreesPaths runs trees with paths. /x/a and /y/a are copies,
+// and so are /y/a and /srv/b. /x and /y also hold files that differ.
+// Given /x/a and /y/a, trees reads /x and /y as holding one copy each
+// of a, yet neither is reported: only the directories at or below a
+// given path are.
+func TestRunTreesPaths(t *testing.T) {
+	f, g, k := testHash("f"), testHash("g"), testHash("k")
+	recs := []scanRec{
+		{size: 10, head: f, tail: f, content: f, path: "/srv/b/f"},
+		{size: 10, head: f, tail: f, content: f, path: "/x/a/f"},
+		{size: 20, head: g, tail: g, content: g, path: "/x/g"},
+		{size: 10, head: f, tail: f, content: f, path: "/y/a/f"},
+		{size: 30, head: k, tail: k, content: k, path: "/y/k"},
+	}
+
+	header := "first\tdupe\tfiles\tsize\tdisk_size\n"
+
+	cases := map[string]struct {
+		paths []string
+		want  string
+	}{
+		"none": {nil, header + "/srv/b\t/x/a\t1\t10\t0\n" +
+			"/srv/b\t/y/a\t1\t10\t0\n"},
+		"two copies": {[]string{"/x/a", "/y/a"},
+			header + "/x/a\t/y/a\t1\t10\t0\n"},
+		"parents":  {[]string{"/x", "/y"}, header + "/x/a\t/y/a\t1\t10\t0\n"},
+		"one copy": {[]string{"/srv/b"}, header},
+	}
+
+	for name, tc := range cases {
+		t.Run(name, func(t *testing.T) {
+			t.Setenv(databaseEnv, seedDatabase(t, recs))
+
+			var stdout, stderr bytes.Buffer
+
+			code := run(append([]string{cmdTrees}, tc.paths...),
+				&stdout, &stderr)
+			if code != exitOK {
+				t.Fatalf("run(trees %q) = %d, want %d; stderr: %s",
+					tc.paths, code, exitOK, stderr.String())
+			}
+
+			if got := stdout.String(); got != tc.want {
+				t.Errorf("stdout = %q, want %q", got, tc.want)
+			}
+		})
+	}
+}
+
 // TestRunTreesDiskSize runs trees on two copies of a tree whose files
 // take different space on disk. The row's disk_size is the sum over the
 // dupe copy's files, those in its subdirectory included.
@@ -435,6 +485,35 @@ func TestCollectTreeGroupsSiblings(t *testing.T) {
 	}
 }
 
+// TestCollectTreeGroupsLeavesOutEmptyTrees checks that directories
+// holding only empty files form no group, and that an empty file still
+// counts toward the digest of a tree that holds other files.
+func TestCollectTreeGroupsLeavesOutEmptyTrees(t *testing.T) {
+	t.Parallel()
+
+	h, tl, c, e := testHash("h"), testHash("t"), testHash("c"),
+		sha256.Sum256(nil)
+	recs := []scanRec{
+		{size: 0, head: e, tail: e, content: e, path: "/e/a/.gitkeep"},
+		{size: 0, head: e, tail: e, content: e, path: "/e/b/.gitkeep"},
+		{size: 10, head: h, tail: tl, content: c, path: "/p/x1/f"},
+		{size: 0, head: e, tail: e, content: e, path: "/p/x1/.gitkeep"},
+		{size: 10, head: h, tail: tl, content: c, path: "/p/x2/f"},
+		{size: 0, head: e, tail: e, content: e, path: "/p/x2/.gitkeep"},
+		// Without the empty file, /p/x3 is no copy of /p/x1.
+		{size: 10, head: h, tail: tl, content: c, path: "/p/x3/f"},
+	}
+
+	super, dirs := treeOf(t, recs)
+
+	got := groupPaths(collectTreeGroups(dirs, super, nil))
+
+	want := [][]string{{"/p/x1", "/p/x2"}}
+	if !slices.EqualFunc(got, want, slices.Equal) {
+		t.Fatalf("groups = %v, want %v", got, want)
+	}
+}
+
 func TestCollectTreeGroupsDifferingParents(t *testing.T) {
 	t.Parallel()