Say in --help where the database is and what each report prints (closes #177)

The help of sfdupes and of scan names the database, its default path
and SFDUPES_DATABASE. The help of report and trees lists the columns,
the order of the rows and the four escapes. The help of info lists its
lines. The help of dwim says that it scans /, should run as root and
keeps the scan in the database.

The README's opening drops its sentence on copies deleted after the
scan, an edge case that its report and trees sections already cover.

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"
@@ -359,7 +359,7 @@ func TestRunScanInterrupted(t *testing.T) {
 	dir := buildSmokeTree(t)
 
 	err := runScan(t.Context(), []string{dir}, walkCancelWorkers, false,
-		false)
+		false, nil)
 	if err != nil {
 		t.Fatal(err)
 	}
@@ -383,7 +383,7 @@ func TestRunScanInterrupted(t *testing.T) {
 		defer close(done)
 
 		err = runScan(cancelledContext(t), []string{dir}, walkCancelWorkers,
-			false, false)
+			false, false, nil)
 	}()
 
 	awaitReturn(t, done, "runScan")
@@ -411,7 +411,7 @@ func TestRunScanInterrupted(t *testing.T) {
 	}
 
 	err = runScan(t.Context(), []string{dir}, walkCancelWorkers, false,
-		false)
+		false, nil)
 	if err != nil {
 		t.Fatal(err)
 	}
@@ -437,7 +437,7 @@ func TestRunScanInterruptedMidHash(t *testing.T) {
 	dir := buildWalkCancelTree(t)
 
 	err := runScan(newWalkClock(hashCancelAtDone), []string{dir},
-		walkCancelWorkers, false, false)
+		walkCancelWorkers, false, false, nil)
 	if !errors.Is(err, errInterrupted) {
 		t.Fatalf("runScan interrupted mid-hash = %v, want %v",
 			err, errInterrupted)

internal/sfdupes/cli.go

@@ -1,23 +1,6 @@
-// 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 --version
-//
-// See README.md for the complete specification.
-package main
+// Package sfdupes implements the sfdupes command and the database its
+// subcommands share.
+package sfdupes
 
 import (
 	"context"
@@ -27,6 +10,7 @@ import (
 	"os"
 	"runtime"
 	"runtime/debug"
+	"slices"
 
 	"github.com/spf13/cobra"
 )
@@ -45,6 +29,70 @@ const (
 	cmdReport = "report"
 	cmdTrees  = "trees"
 	cmdInfo   = "info"
+	cmdDwim   = "dwim"
+)
+
+// databaseHelp is the paragraph of the root and scan help that names
+// the database (README "Location").
+const databaseHelp = "scan and dwim store what they find in a database " +
+	"file. report, trees\nand info read it. The file is $" + databaseEnv +
+	" when that is set and\nnot empty, and otherwise " +
+	defaultDatabasePath + ", where creating it\nneeds root.\n"
+
+// escapesHelp is the paragraph of the report and trees help on how
+// paths are escaped (README "Report output format").
+const escapesHelp = `Four characters in a path are escaped, so each row stays one line:
+
+  \\  a backslash
+  \t  a tab
+  \n  a newline
+  \r  a carriage return
+`
+
+// reportHelp, treesHelp, infoHelp and dwimHelp follow the one-line
+// summary in the help of their subcommands.
+const (
+	reportHelp = `The report is tab-separated text on stdout: a header line, then one
+row per duplicate file. The columns are:
+
+  first   the path that sorts first, byte by byte, in its group of copies
+  dupe    another copy of that file
+  size    the file's size in bytes
+
+Rows are ordered by size, largest first, then by path.
+
+` + escapesHelp
+
+	treesHelp = `The report is tab-separated text on stdout: a header line, then one
+row per duplicate directory tree. The columns are:
+
+  first      the path that sorts first, byte by byte, in its group of copies
+  dupe       another copy of that tree
+  files      the number of regular files in one copy
+  size       their total size in bytes
+  disk_size  the bytes the dupe copy takes on disk
+
+Rows are ordered by size, largest first, then by path.
+
+` + escapesHelp
+
+	infoHelp = `The details go to stdout, one per line. Each line holds a name and its
+value, separated by a tab:
+
+  database                the path, and where it came from
+  database file size      in bytes, then rounded, as 2147483648 (2.0 GiB)
+  -wal file size          in bytes, then rounded; only if a -wal file exists
+  modified                when the database file last changed, in UTC
+  schema version          the version of the database's layout
+  records                 the number of records
+  size of recorded files  their total size, in bytes, then rounded
+`
+
+	dwimHelp = `dwim runs what "sfdupes scan /" runs, then what "sfdupes trees" runs.
+Run it as root, so that the scan can read every file. The scan is stored
+in the database, as scan stores it, so "sfdupes trees" prints the report
+again later.
+`
 )
 
 // errNoSubcommand is returned by the root command when it is invoked
@@ -56,6 +104,11 @@ var errNoSubcommand = errors.New("no subcommand")
 // below 1.
 var errWorkersBelowOne = errors.New("--workers must be at least 1")
 
+// errEmptyExcludeValue is the usage error for an empty scan --exclude
+// value, as from --exclude "$DIR" with DIR unset. Taken as a path, it
+// would name the working directory.
+var errEmptyExcludeValue = errors.New("--exclude must not be empty")
+
 // Version is the build version, injected at link time via -ldflags
 // (see the Makefile); empty when the linker set none, as for a binary
 // built by go install. buildVersion turns it into what --version prints.
@@ -84,20 +137,22 @@ 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
-// write their data to stdout.
+// runs before the process ends. The report, trees, info and dwim
+// 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.
@@ -201,38 +256,64 @@ 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.Long = root.Short + ".\n\n" + databaseHelp
+	reportCmd.Long = reportCmd.Short + ".\n\n" + reportHelp
+	treesCmd.Long = treesCmd.Short + ".\n\n" + treesHelp
+	infoCmd.Long = infoCmd.Short + ".\n\n" + infoHelp
+	dwimCmd.Long = dwimCmd.Short + ".\n\n" + dwimHelp
+
+	root.AddCommand(newScanCommand(), reportCmd, treesCmd, infoCmd, dwimCmd)
 
 	return root
 }
 
-// newScanCommand builds the scan subcommand, with its --workers, -x and
-// --no-default-excludes flags. Its help lists the default excludes of
-// the system it runs on, and the filesystem types it never records
-// anything on.
+// newScanCommand builds the scan subcommand, with its --workers, -x,
+// --no-default-excludes and --exclude flags. Its help names the
+// database, and lists the default excludes of the system it runs on and
+// the filesystem types it never records anything on.
 func newScanCommand() *cobra.Command {
 	var (
 		scanWorkers           int
 		scanOneFS             bool
 		scanNoDefaultExcludes bool
+		scanExclude           []string
 	)
 
 	short := "Walk trees and synchronize the scan database"
 
 	scanCmd := &cobra.Command{
-		Use:   cmdScan + " [--workers N] [-x] [--no-default-excludes] PATH...",
-		Short: short,
-		Long:  short + ".\n\n" + defaultExcludesHelp(runtime.GOOS),
-		Args:  cobra.MinimumNArgs(1),
+		Use: cmdScan + " [--workers N] [-x] [--no-default-excludes] " +
+			"[--exclude PATH]... PATH...",
+		// The Use line already names every flag, so cobra must not
+		// append its generic "[flags]" to it.
+		DisableFlagsInUseLine: true,
+		Short:                 short,
+		Long: short + ".\n\n" + databaseHelp + "\n" +
+			defaultExcludesHelp(runtime.GOOS),
+		Args: cobra.MinimumNArgs(1),
 		PreRunE: func(cmd *cobra.Command, _ []string) error {
-			return checkScanWorkers(cmd, scanWorkers)
+			err := checkScanWorkers(cmd, scanWorkers)
+			if err != nil {
+				return err
+			}
+
+			return rejectEmptyExcludeValue(cmd, scanExclude)
 		},
 		RunE: runE(func(ctx context.Context, args []string) error {
 			ctx, stop := interruptContext(ctx)
 			defer stop()
 
 			return runScan(ctx, args, scanWorkers, scanOneFS,
-				scanNoDefaultExcludes)
+				scanNoDefaultExcludes, scanExclude)
 		}),
 	}
 	scanCmd.Flags().IntVar(&scanWorkers, "workers", runtime.NumCPU(),
@@ -241,6 +322,10 @@ func newScanCommand() *cobra.Command {
 		"do not cross filesystem boundaries")
 	scanCmd.Flags().BoolVar(&scanNoDefaultExcludes, "no-default-excludes",
 		false, "enter the default excludes, the paths listed above")
+	// A string array, not a slice, so a comma in a path is not a
+	// separator.
+	scanCmd.Flags().StringArrayVar(&scanExclude, "exclude", nil,
+		"never enter or record `PATH` or anything below it; repeatable")
 
 	return scanCmd
 }
@@ -258,6 +343,18 @@ func checkScanWorkers(cmd *cobra.Command, workers int) error {
 	return fmt.Errorf("%w, got %d", errWorkersBelowOne, workers)
 }
 
+// rejectEmptyExcludeValue rejects an empty scan --exclude value. That
+// is a usage error reported in one line, as for --workers below 1.
+func rejectEmptyExcludeValue(cmd *cobra.Command, excludePaths []string) error {
+	if !slices.Contains(excludePaths, "") {
+		return nil
+	}
+
+	cmd.SilenceUsage = true
+
+	return errEmptyExcludeValue
+}
+
 // runE adapts a subcommand implementation, or the version print, to
 // cobra's RunE. Cobra prints the error and the command's usage text for
 // every error RunE returns, but a subcommand that ran and failed has no

internal/sfdupes/cli_test.go

@@ -1,4 +1,4 @@
-package main
+package sfdupes //nolint:testpackage // drives the unexported run
 
 import (
 	"bytes"
@@ -14,12 +14,17 @@ import (
 	"strconv"
 	"strings"
 	"testing"
+
+	"golang.org/x/sys/unix"
 )
 
 // usageMarker is the first line of cobra's usage text, which a usage
 // error prints and a runtime failure must not.
 const usageMarker = "Usage:"
 
+// helpFlag asks for the help text.
+const helpFlag = "--help"
+
 // TestMain stops the tests at once, saying why, when their temporary
 // directory is not on a persistent filesystem: scan records nothing
 // there (README "Rules for the walk"), so most scan tests would fail
@@ -180,9 +185,9 @@ func capture(t *testing.T, std **os.File) func() string {
 }
 
 // brokenDatabase writes a database that opens cleanly and passes the
-// schema-version check but has no files table, so the first query
-// fails with the database already open: a fatal error on a path that
-// owns an open database. It closes the database the way scan does.
+// schema-version check but has no tables, so the first query fails
+// with the database already open: a fatal error on a path that owns an
+// open database. It closes the database the way scan does.
 func brokenDatabase(t *testing.T) string {
 	t.Helper()
 
@@ -265,8 +270,9 @@ func TestRunFatalAfterOpenClosesDatabase(t *testing.T) {
 			assertFatalOutput(t, stderr.String(), stdout())
 
 			// Proof that the failure happened after the open: only a
-			// query against the opened database can report this.
-			if !strings.Contains(stderr.String(), "no such table: files") {
+			// query against the opened database can report this. Each
+			// subcommand's first query reads totals.
+			if !strings.Contains(stderr.String(), "no such table: totals") {
 				t.Errorf("stderr = %q, want the failure to come from a "+
 					"query on the open database", stderr.String())
 			}
@@ -393,7 +399,7 @@ 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
@@ -567,7 +573,8 @@ func TestRunNamesDefaultDatabase(t *testing.T) {
 	}{
 		cmdScan: {
 			run: func() error {
-				return runScan(t.Context(), []string{missing}, 1, false, false)
+				return runScan(t.Context(), []string{missing}, 1, false, false,
+					nil)
 			},
 			want: scanWant,
 		},
@@ -619,6 +626,7 @@ func TestRunUsageErrors(t *testing.T) {
 		"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"},
 	}
@@ -648,7 +656,7 @@ 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) {
@@ -686,9 +694,9 @@ func TestRunScanRejectsWorkersBelowOne(t *testing.T) {
 func TestRunHelp(t *testing.T) {
 	t.Parallel()
 
-	// README §Subcommands: help goes to stderr, exits 0, and leaves
-	// stdout empty.
-	cases := [][]string{{"--help"}, {"-h"}, {cmdScan, "--help"}}
+	// README §Settings: help goes to stderr, exits 0, and leaves stdout
+	// empty.
+	cases := [][]string{{helpFlag}, {"-h"}, {cmdScan, helpFlag}}
 
 	for _, args := range cases {
 		var stdout, stderr bytes.Buffer
@@ -708,13 +716,119 @@ func TestRunHelp(t *testing.T) {
 				args, got)
 		}
 	}
+
+	// The scan help lists --exclude with its argument.
+	var stdout, stderr bytes.Buffer
+
+	run([]string{cmdScan, "-h"}, &stdout, &stderr)
+
+	if !strings.Contains(stderr.String(), excludeFlag+" PATH") {
+		t.Errorf("scan -h stderr = %q, want %s PATH", stderr.String(),
+			excludeFlag)
+	}
+}
+
+func TestRunScanUsageLine(t *testing.T) {
+	t.Parallel()
+
+	// README §Subcommands shows this usage line for scan, and the help
+	// and the usage error both print it.
+	const want = "\n  sfdupes scan [--workers N] [-x] [--no-default-excludes] " +
+		"[--exclude PATH]... PATH...\n"
+
+	cases := map[string][]string{
+		"help":          {cmdScan, "-h"},
+		"missing paths": {cmdScan},
+	}
+
+	for name, args := range cases {
+		t.Run(name, func(t *testing.T) {
+			t.Parallel()
+
+			var stdout, stderr bytes.Buffer
+
+			run(args, &stdout, &stderr)
+
+			if !strings.Contains(stderr.String(), want) {
+				t.Errorf("run(%v) stderr = %q, want the usage line %q",
+					args, stderr.String(), want)
+			}
+		})
+	}
+}
+
+func TestRunHelpDescribesDatabaseAndOutput(t *testing.T) {
+	t.Parallel()
+
+	// README §Settings: the help names the database, and says what
+	// report, trees, info and dwim print.
+	database := []string{
+		"scan and dwim store", databaseEnv, defaultDatabasePath, "needs root",
+	}
+	escapes := []string{`\\`, `\t`, `\n`, `\r`}
+
+	// The subcommand whose help is printed; none for the root.
+	cases := []struct {
+		subcommand []string
+		want       []string
+	}{
+		{nil, database},
+		{[]string{cmdScan}, database},
+		{
+			[]string{cmdReport},
+			append([]string{
+				"tab-separated", "\n  first ", "\n  dupe ", "\n  size ",
+				"largest first",
+			}, escapes...),
+		},
+		{
+			[]string{cmdTrees},
+			append([]string{
+				"tab-separated", "\n  first ", "\n  dupe ", "\n  files ",
+				"\n  size ", "\n  disk_size ", "largest first",
+			}, escapes...),
+		},
+		{
+			[]string{cmdInfo},
+			[]string{
+				"\n  database ", "\n  database file size ",
+				"\n  -wal file size ", "\n  modified ",
+				"\n  schema version ", "\n  records ",
+				"\n  size of recorded files ",
+			},
+		},
+		{
+			[]string{cmdDwim},
+			[]string{
+				"sfdupes scan /", "as root", "sfdupes trees", "database",
+			},
+		},
+	}
+
+	for _, tc := range cases {
+		var stdout, stderr bytes.Buffer
+
+		args := slices.Concat(tc.subcommand, []string{helpFlag})
+
+		code := run(args, &stdout, &stderr)
+		if code != exitOK {
+			t.Fatalf("run(%v) = %d, want %d", args, code, exitOK)
+		}
+
+		for _, want := range tc.want {
+			if !strings.Contains(stderr.String(), want) {
+				t.Errorf("run(%v) help lacks %q:\n%s",
+					args, want, stderr.String())
+			}
+		}
+	}
 }
 
 func TestRunVersion(t *testing.T) {
 	t.Parallel()
 
-	// README §Subcommands: the version is one line on stdout, with
-	// nothing on stderr, and exits 0.
+	// README §Settings: the version is one line on stdout, with nothing
+	// on stderr, and exits 0.
 	info, _ := debug.ReadBuildInfo()
 
 	for _, arg := range []string{"--version", "-v"} {
@@ -773,8 +887,8 @@ func TestBuildVersion(t *testing.T) {
 func TestRunVersionWriteFailureIsFatal(t *testing.T) {
 	t.Parallel()
 
-	// README §Error handling: a stdout write failure exits 1, reported
-	// in one line on stderr.
+	// README §Error handling: a failed write to stdout is a fatal error,
+	// exit 1, reported on stderr starting with "sfdupes:".
 	var stderr bytes.Buffer
 
 	code := run([]string{"--version"}, failingWriter{}, &stderr)
@@ -796,7 +910,7 @@ 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)),
@@ -817,6 +931,23 @@ func scanFixture(t *testing.T) []string {
 	return dupes
 }
 
+// storedDiskSize returns the disk_size of the record for path in the
+// database at dbPath. A test of a trees run compares with this rather
+// than with a new lstat, which on ZFS can differ from the scan's (see
+// diskSizeOf).
+func storedDiskSize(t *testing.T, dbPath, path string) int64 {
+	t.Helper()
+
+	db, err := openReportDatabase(t.Context(), dbPath)
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	defer func() { _ = db.Close() }()
+
+	return recordByPath(t, dbRecords(t, db), path).diskSize
+}
+
 // scanOK runs scan over operands, fails the test unless it exits 0 with
 // nothing on stdout, and returns everything it printed to stderr.
 func scanOK(t *testing.T, operands ...string) string {
@@ -849,7 +980,7 @@ 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.
@@ -877,75 +1008,292 @@ func TestRunScanSucceedsDespiteWarnings(t *testing.T) {
 	assertNoSidecars(t, path)
 }
 
-func TestRunScanSkipsSymlinkOperand(t *testing.T) {
-	path := testDBPath(t)
-	t.Setenv(databaseEnv, path)
+// realTempDir returns a new temporary directory by its real path, so
+// tests hold where the temporary directory is reached through a
+// symlink.
+func realTempDir(t *testing.T) string {
+	t.Helper()
 
-	dir := t.TempDir()
-	writeFile(t, dir, "target/sub/f", pattern(1, 10))
-
-	link := filepath.Join(dir, "link")
-
-	err := os.Symlink(filepath.Join(dir, "target"), link)
+	dir, err := filepath.EvalSymlinks(t.TempDir())
 	if err != nil {
 		t.Fatal(err)
 	}
 
-	// Scanning a directory through the symlink stores a record beneath
-	// 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"))
+	return dir
 }
 
+// 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()
-	writeFile(t, dir, "target/sub/f", pattern(1, 10))
+	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)
 
-	err := os.Symlink(filepath.Join(dir, "target"), link)
-	if err != nil {
-		t.Fatal(err)
+	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)
 	}
 
-	// link is dropped as a symlink, but link/sub must still be scanned,
-	// not dropped as lying under link.
-	scanOK(t, link, filepath.Join(link, "sub"))
-
-	db, err := openDB(path, reportParams)
-	if err != nil {
-		t.Fatal(err)
+	if got := storedPaths(t, path); !slices.Equal(got, []string{f}) {
+		t.Errorf("records = %q, want %q", got, []string{f})
 	}
-
-	t.Cleanup(func() { _ = db.Close() })
-
-	recordByPath(t, dbRecords(t, db), filepath.Join(link, "sub", "f"))
 }
 
-func TestRunScanSkipsZFSOperand(t *testing.T) {
+// 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)
 
-	zfs := filepath.Join(t.TempDir(), ".zfs")
-	snapshot := filepath.Join(zfs, "snapshot", "hourly")
-	f := writeFile(t, snapshot, "f", pattern(1, 10))
+	dir := realTempDir(t)
+	a := writeFile(t, dir, "a", pattern(1, 10))
 
-	// An operand beneath a .zfs directory is walked, because it is not
-	// itself named .zfs.
-	scanOK(t, snapshot)
+	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)
+	}
+
+	symlink(t, filepath.Join(dir, "data", "proj"),
+		filepath.Join(dir, "home", "proj"))
+
+	// 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)
+	}
+
+	link := filepath.Join(dir, "link")
+	symlink(t, fifo, link)
+
+	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(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
+	// beneath the operand is written straight into the database.
+	path := seedDatabase(t, []scanRec{{size: 10, path: f}})
+	t.Setenv(databaseEnv, path)
 
 	assertOperandSkipped(t, path, zfs, ".zfs directory", f)
 }
 
 // assertOperandSkipped scans operand alone and checks that it is skipped
 // as kind: a warning naming it, one skip in the summary, exit 0, and the
-// record for kept, which an earlier scan stored beneath operand, still
-// in the database at dbPath.
+// record for kept, stored beneath operand before this scan, still in the
+// database at dbPath.
 func assertOperandSkipped(t *testing.T, dbPath, operand, kind,
 	kept string,
 ) {
@@ -974,6 +1322,107 @@ func assertOperandSkipped(t *testing.T, dbPath, operand, kind,
 	recordByPath(t, dbRecords(t, db), kept)
 }
 
+// TestRunScanSkipsOperandInsideZFS scans a directory inside a .zfs
+// directory, first alone and then under another operand. Each time it
+// is warned about and counted as skipped, and nothing in it is walked.
+// The other operand is scanned as usual.
+func TestRunScanSkipsOperandInsideZFS(t *testing.T) {
+	path := testDBPath(t)
+	t.Setenv(databaseEnv, path)
+
+	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))
+
+	warning := "walk " + hourly + ": skipping operand inside a .zfs directory\n"
+
+	for _, tc := range []struct {
+		operands []string
+		summary  string
+	}{
+		{
+			[]string{hourly},
+			"scan: 0 files seen (0 added, 0 updated, 0 removed, " +
+				"0 unchanged), 1 skipped\n",
+		},
+		{
+			[]string{dir, hourly},
+			"scan: 1 files seen (1 added, 0 updated, 0 removed, " +
+				"0 unchanged), 1 skipped\n",
+		},
+	} {
+		stderr := scanOK(t, tc.operands...)
+		if !strings.Contains(stderr, warning) ||
+			!strings.Contains(stderr, tc.summary) {
+			t.Errorf("scan %q: stderr = %q, want %q and %q", tc.operands,
+				stderr, warning, tc.summary)
+		}
+	}
+
+	db, err := openDB(path, reportParams)
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	t.Cleanup(func() { _ = db.Close() })
+
+	if got := recordPaths(dbRecords(t, db)); !slices.Equal(got, []string{f}) {
+		t.Errorf("records = %q, want %q", got, []string{f})
+	}
+}
+
+// TestRunScanSkipsOperandThroughSymlinkIntoZFS scans snaps/daily, where
+// snaps is a symlink to pool/.zfs/snapshot. The operand is warned about
+// by its real path, counted as skipped, and not walked.
+func TestRunScanSkipsOperandThroughSymlinkIntoZFS(t *testing.T) {
+	t.Setenv(databaseEnv, testDBPath(t))
+
+	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)
+
+	stderr := scanOK(t, filepath.Join(snaps, "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"
+
+	if !strings.Contains(stderr, warning) ||
+		!strings.Contains(stderr, summary) {
+		t.Errorf("stderr = %q, want %q and %q", stderr, warning, summary)
+	}
+}
+
+// TestRunScanWalksOperandThroughSymlink scans data/daily, where data is
+// a symlink to pool/data. The operand is scanned as usual, and its file
+// is recorded by its real path.
+func TestRunScanWalksOperandThroughSymlink(t *testing.T) {
+	path := testDBPath(t)
+	t.Setenv(databaseEnv, path)
+
+	dir := realTempDir(t)
+	f := writeFile(t, dir, "pool/data/daily/f", pattern(1, 10))
+
+	data := filepath.Join(dir, "data")
+	symlink(t, filepath.Join(dir, "pool", "data"), data)
+
+	stderr := scanOK(t, filepath.Join(data, "daily"))
+
+	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})
+	}
+}
+
 func TestRunReportSucceeds(t *testing.T) {
 	path := testDBPath(t)
 	t.Setenv(databaseEnv, path)
@@ -1028,8 +1477,9 @@ func TestRunTreesSucceeds(t *testing.T) {
 
 	// The two directories holding the duplicate pair are duplicate
 	// trees of each other.
-	want := "first\tdupe\tfiles\tsize\n" +
-		filepath.Dir(dupes[0]) + "\t" + filepath.Dir(dupes[1]) + "\t1\t300\n"
+	want := "first\tdupe\tfiles\tsize\tdisk_size\n" +
+		filepath.Dir(dupes[0]) + "\t" + filepath.Dir(dupes[1]) + "\t1\t300\t" +
+		strconv.FormatInt(storedDiskSize(t, path, dupes[1]), 10) + "\n"
 	if got := stdout.String(); got != want {
 		t.Errorf("stdout = %q, want %q", got, want)
 	}
@@ -1063,9 +1513,10 @@ func TestRunReportsNeedOnlyReadAccess(t *testing.T) {
 	cases := map[string]string{
 		cmdReport: "first\tdupe\tsize\n" +
 			dupes[0] + "\t" + dupes[1] + "\t300\n",
-		cmdTrees: "first\tdupe\tfiles\tsize\n" +
+		cmdTrees: "first\tdupe\tfiles\tsize\tdisk_size\n" +
 			filepath.Dir(dupes[0]) + "\t" + filepath.Dir(dupes[1]) +
-			"\t1\t300\n",
+			"\t1\t300\t" +
+			strconv.FormatInt(storedDiskSize(t, path, dupes[1]), 10) + "\n",
 	}
 
 	for name, want := range cases {
@@ -1100,8 +1551,11 @@ func assertRunsUseDatabase(t *testing.T, dir, name string) {
 		t.Errorf("report stdout = %q, want %q", got, want)
 	}
 
-	want = "first\tdupe\tfiles\tsize\n" +
-		filepath.Dir(dupes[0]) + "\t" + filepath.Dir(dupes[1]) + "\t1\t300\n"
+	diskSize := storedDiskSize(t, filepath.Join(dir, name), dupes[1])
+
+	want = "first\tdupe\tfiles\tsize\tdisk_size\n" +
+		filepath.Dir(dupes[0]) + "\t" + filepath.Dir(dupes[1]) + "\t1\t300\t" +
+		strconv.FormatInt(diskSize, 10) + "\n"
 	if got := runStdout(t, cmdTrees); got != want {
 		t.Errorf("trees stdout = %q, want %q", got, want)
 	}
@@ -1122,7 +1576,7 @@ 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
@@ -1167,9 +1621,8 @@ func holdScanLock(t *testing.T, path string) {
 }
 
 func TestRunSecondScanFails(t *testing.T) {
-	// README §Database: while one scan holds the lock, a second scan
-	// fails at once, naming the lock file, without opening the
-	// database.
+	// README §Database: a second scan that finds the lock held fails
+	// at once, naming the lock file, without opening the database.
 	path := testDBPath(t)
 	t.Setenv(databaseEnv, path)
 
@@ -1228,7 +1681,7 @@ 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.
@@ -1333,8 +1786,8 @@ func TestRunReportsDuringScan(t *testing.T) {
 }
 
 func TestRunStdoutClosedIsFatal(t *testing.T) {
-	// README §Error handling: a stdout write failure exits 1, reported
-	// in one line on stderr.
+	// README §Error handling: a failed write to stdout is a fatal error,
+	// 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))

internal/sfdupes/db.go

@@ -1,4 +1,4 @@
-package main
+package sfdupes
 
 import (
 	"context"
@@ -47,14 +47,15 @@ const dbFilePerm = 0o644
 const lockFilePerm = 0o600
 
 // createTableSQL is the schema applied to a fresh database. Paths are
-// BLOBs because Unix paths are raw bytes, not guaranteed UTF-8. mtime
-// holds whole Unix seconds and mtime_nsec the nanoseconds within that
-// second. head, tail and content each hold the raw 32 bytes of a
-// SHA-256.
+// BLOBs because Unix paths are raw bytes, not guaranteed UTF-8.
+// disk_size holds the bytes the file takes on disk. mtime holds whole
+// Unix seconds and mtime_nsec the nanoseconds within that second. head,
+// tail and content each hold the raw 32 bytes of a SHA-256.
 const createTableSQL = `
 CREATE TABLE files (
     path       BLOB PRIMARY KEY,
     size       INTEGER NOT NULL,
+    disk_size  INTEGER NOT NULL,
     mtime      INTEGER NOT NULL,
     mtime_nsec INTEGER NOT NULL,
     head       BLOB NOT NULL,
@@ -69,14 +70,59 @@ const createIndexSQL = `
 CREATE INDEX files_signature ON files (size, head, tail, content)
 `
 
+// createTotalsSQL creates the totals table, which holds one row: the
+// number of records and the sizes of all records added up. Counting
+// them over files would read every record. The three triggers below
+// keep the row current, in the transaction of each change to files.
+const createTotalsSQL = `
+CREATE TABLE totals (
+    records INTEGER NOT NULL,
+    size    INTEGER NOT NULL
+)
+`
+
+// insertTotalsSQL adds the one row of totals, for an empty files table.
+const insertTotalsSQL = `
+INSERT INTO totals (records, size) VALUES (0, 0)
+`
+
+// totalsAfterInsertSQL counts each inserted record into totals.
+const totalsAfterInsertSQL = `
+CREATE TRIGGER totals_after_insert AFTER INSERT ON files BEGIN
+    UPDATE totals SET records = records + 1, size = size + NEW.size;
+END
+`
+
+// totalsAfterDeleteSQL takes each deleted record out of totals.
+const totalsAfterDeleteSQL = `
+CREATE TRIGGER totals_after_delete AFTER DELETE ON files BEGIN
+    UPDATE totals SET records = records - 1, size = size - OLD.size;
+END
+`
+
+// totalsAfterUpdateSQL replaces a record's old size in totals with its
+// new one. scan's upsert of an existing record is such an update.
+const totalsAfterUpdateSQL = `
+CREATE TRIGGER totals_after_update AFTER UPDATE OF size ON files BEGIN
+    UPDATE totals SET size = size + NEW.size - OLD.size;
+END
+`
+
+// recordCountSQL reads the number of records from totals.
+const recordCountSQL = `
+SELECT records FROM totals
+`
+
 // upsertSQL inserts one file record, replacing any existing record for
 // the same path.
 const upsertSQL = `
-INSERT INTO files (path, size, mtime, mtime_nsec, head, tail, content)
-VALUES (?, ?, ?, ?, ?, ?, ?)
+INSERT INTO files (
+    path, size, disk_size, mtime, mtime_nsec, head, tail, content
+)
+VALUES (?, ?, ?, ?, ?, ?, ?, ?)
 ON CONFLICT (path) DO UPDATE SET
-    size = excluded.size, mtime = excluded.mtime,
-    mtime_nsec = excluded.mtime_nsec,
+    size = excluded.size, disk_size = excluded.disk_size,
+    mtime = excluded.mtime, mtime_nsec = excluded.mtime_nsec,
     head = excluded.head, tail = excluded.tail,
     content = excluded.content
 `
@@ -100,33 +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
-// of it when it is relative, and where the path came from, "default" or
-// "from SFDUPES_DATABASE", for the line each subcommand prints first on
-// stderr.
+// path, made absolute by absolutePath, and where the path came from,
+// "default" or "from SFDUPES_DATABASE", for the line each subcommand
+// prints first on 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) {
-		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()
+	abs, err := absolutePath(path)
 	if err != nil {
 		return "", "", fmt.Errorf("resolve database path %s: %w", path, err)
 	}
 
-	// Not filepath.Abs or filepath.Join: they clean the path, which
-	// drops each ".." together with the directory name before it. When
-	// that directory is a symlink, the cleaned path names another file.
+	return abs, source, nil
+}
+
+// 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
@@ -150,9 +207,14 @@ func createDatabaseDirectory(path string) error {
 // scanParams are the connection parameters for scan: read-write, with
 // WAL journaling and a busy timeout, so a report can run while a cron
 // scan is in progress. closeScanDatabase leaves WAL mode again.
+//
+// Each write to files fires a trigger, so SQLite keeps a statement
+// journal for it. temp_store(MEMORY) keeps that journal in memory,
+// which costs far less than a temporary file.
 const scanParams = "_pragma=busy_timeout(10000)" +
 	"&_pragma=journal_mode(WAL)" +
-	"&_pragma=synchronous(NORMAL)"
+	"&_pragma=synchronous(NORMAL)" +
+	"&_pragma=temp_store(MEMORY)"
 
 // reportParams are the connection parameters for report, trees and
 // info: read-only, with the same busy timeout. They set no journal
@@ -426,14 +488,14 @@ func createSchema(ctx context.Context, db *sql.DB) error {
 
 	defer func() { _ = tx.Rollback() }()
 
-	_, err = tx.ExecContext(ctx, createTableSQL)
-	if err != nil {
-		return fmt.Errorf("create schema: %w", err)
-	}
-
-	_, err = tx.ExecContext(ctx, createIndexSQL)
-	if err != nil {
-		return fmt.Errorf("create schema: %w", err)
+	for _, stmt := range []string{
+		createTableSQL, createIndexSQL, createTotalsSQL, insertTotalsSQL,
+		totalsAfterInsertSQL, totalsAfterDeleteSQL, totalsAfterUpdateSQL,
+	} {
+		_, err = tx.ExecContext(ctx, stmt)
+		if err != nil {
+			return fmt.Errorf("create schema: %w", err)
+		}
 	}
 
 	_, err = tx.ExecContext(ctx,
@@ -480,7 +542,7 @@ func loadFileRows(ctx context.Context, db *sql.DB, total func(n int64),
 
 	var n int64
 
-	err = tx.QueryRowContext(ctx, "SELECT COUNT(*) FROM files").Scan(&n)
+	err = tx.QueryRowContext(ctx, recordCountSQL).Scan(&n)
 	if err != nil {
 		return fmt.Errorf("count records: %w", err)
 	}
@@ -488,8 +550,8 @@ func loadFileRows(ctx context.Context, db *sql.DB, total func(n int64),
 	total(n)
 
 	rows, err := tx.QueryContext(ctx,
-		"SELECT path, size, mtime, mtime_nsec, head, tail, content "+
-			"FROM files ORDER BY path")
+		"SELECT path, size, disk_size, mtime, mtime_nsec, head, tail, "+
+			"content FROM files ORDER BY path")
 	if err != nil {
 		return fmt.Errorf("read records: %w", err)
 	}
@@ -503,7 +565,8 @@ func loadFileRows(ctx context.Context, db *sql.DB, total func(n int64),
 			r                         scanRec
 		)
 
-		err = rows.Scan(&path, &r.size, &sec, &nsec, &head, &tail, &content)
+		err = rows.Scan(&path, &r.size, &r.diskSize, &sec, &nsec,
+			&head, &tail, &content)
 		if err != nil {
 			return fmt.Errorf("read record: %w", err)
 		}
@@ -538,10 +601,11 @@ ORDER BY size DESC, head DESC, tail DESC, content DESC
 `
 
 // loadSignatureRows gives total the number of records, then streams
-// every record's signature and path to fn, without its mtime, in the
-// order of signatureRowsSQL. The count and the records are read in one
-// transaction, so they agree while a scan is committing. An error from
-// fn stops the reading and is returned as it is.
+// every record's signature and path to fn, without its mtime or its
+// disk_size, in the order of signatureRowsSQL. The count and the
+// records are read in one transaction, so they agree while a scan is
+// committing. An error from fn stops the reading and is returned as it
+// is.
 func loadSignatureRows(ctx context.Context, db *sql.DB,
 	total func(n int64), fn func(r scanRec) error,
 ) error {
@@ -556,7 +620,7 @@ func loadSignatureRows(ctx context.Context, db *sql.DB,
 
 	var n int64
 
-	err = tx.QueryRowContext(ctx, "SELECT COUNT(*) FROM files").Scan(&n)
+	err = tx.QueryRowContext(ctx, recordCountSQL).Scan(&n)
 	if err != nil {
 		return fmt.Errorf("count records: %w", err)
 	}
@@ -622,7 +686,7 @@ func (r *scanRec) setHashes(head, tail, content []byte) error {
 func countRecords(ctx context.Context, db *sql.DB) (int64, error) {
 	var n int64
 
-	err := db.QueryRowContext(ctx, "SELECT COUNT(*) FROM files").Scan(&n)
+	err := db.QueryRowContext(ctx, recordCountSQL).Scan(&n)
 	if err != nil {
 		return 0, fmt.Errorf("count records: %w", err)
 	}
@@ -630,12 +694,10 @@ func countRecords(ctx context.Context, db *sql.DB) (int64, error) {
 	return n, nil
 }
 
-// databaseCountsSQL counts the records and adds up their sizes, in one
-// pass over the table. A SUM over no rows is NULL, so on an empty table
-// the SUM falls back to 0.
+// databaseCountsSQL reads the number of records and the sizes of all
+// records added up from totals.
 const databaseCountsSQL = `
-SELECT COUNT(*), COALESCE(SUM(size), 0)
-FROM files
+SELECT records, size FROM totals
 `
 
 // databaseCounts is what info reads from the database: its schema
@@ -678,15 +740,15 @@ func readDatabaseCounts(ctx context.Context,
 	return c, nil
 }
 
-// loadFileMeta streams every record's path, size and mtime to fn. Scan
-// change detection needs no hash values, and skipping the hash columns
-// keeps the scan's in-memory index small on multi-million-file
-// databases.
+// loadFileMeta streams every record's path, size, disk_size and mtime
+// to fn. Scan change detection needs no hash values, and skipping the
+// hash columns keeps the scan's in-memory index small on
+// multi-million-file databases.
 func loadFileMeta(ctx context.Context, db *sql.DB,
-	fn func(path string, size int64, mtime time.Time),
+	fn func(path string, m fileMeta),
 ) error {
 	rows, err := db.QueryContext(ctx,
-		"SELECT path, size, mtime, mtime_nsec FROM files")
+		"SELECT path, size, disk_size, mtime, mtime_nsec FROM files")
 	if err != nil {
 		return fmt.Errorf("read records: %w", err)
 	}
@@ -695,16 +757,19 @@ func loadFileMeta(ctx context.Context, db *sql.DB,
 
 	for rows.Next() {
 		var (
-			path            []byte
-			size, sec, nsec int64
+			path      []byte
+			m         fileMeta
+			sec, nsec int64
 		)
 
-		err = rows.Scan(&path, &size, &sec, &nsec)
+		err = rows.Scan(&path, &m.size, &m.diskSize, &sec, &nsec)
 		if err != nil {
 			return fmt.Errorf("read record: %w", err)
 		}
 
-		fn(string(path), size, time.Unix(sec, nsec))
+		m.mtime = time.Unix(sec, nsec)
+
+		fn(string(path), m)
 	}
 
 	err = rows.Err()
@@ -722,21 +787,21 @@ func loadFileMeta(ctx context.Context, db *sql.DB,
 // WAL small and let concurrent reports observe progress.
 const updateBatchSize = 10000
 
-// applyChanges writes one scan's database changes — upserts for new and
-// changed files, deletes for vanished ones — in batched transactions.
-// Progress is rendered on prog (one increment per change).
+// applyChanges writes upserts for new and changed files and deletes for
+// vanished ones, in batched transactions. Progress is rendered on prog
+// (one increment per change).
 func applyChanges(ctx context.Context, db *sql.DB, upserts []scanRec,
 	deletes []string, prog *progress,
 ) error {
 	for batch := range slices.Chunk(upserts, updateBatchSize) {
-		err := applyBatch(ctx, db, batch, nil, prog)
+		err := applyBatch(ctx, db, batch, nil, nil, prog)
 		if err != nil {
 			return err
 		}
 	}
 
 	for batch := range slices.Chunk(deletes, updateBatchSize) {
-		err := applyBatch(ctx, db, nil, batch, prog)
+		err := applyBatch(ctx, db, nil, nil, batch, prog)
 		if err != nil {
 			return err
 		}
@@ -745,10 +810,26 @@ func applyChanges(ctx context.Context, db *sql.DB, upserts []scanRec,
 	return nil
 }
 
-// applyBatch commits one batch of upserts and deletes in a single
-// transaction.
+// applyDiskSizes writes the disk_size of each of recs into its record,
+// in batched transactions, and leaves the rest of the record alone.
+// Progress is rendered on prog (one increment per record).
+func applyDiskSizes(ctx context.Context, db *sql.DB, recs []fileRec,
+	prog *progress,
+) error {
+	for batch := range slices.Chunk(recs, updateBatchSize) {
+		err := applyBatch(ctx, db, nil, batch, nil, prog)
+		if err != nil {
+			return err
+		}
+	}
+
+	return nil
+}
+
+// applyBatch commits one batch of upserts, disk_size updates and
+// deletes in a single transaction.
 func applyBatch(ctx context.Context, db *sql.DB, upserts []scanRec,
-	deletes []string, prog *progress,
+	diskSizes []fileRec, deletes []string, prog *progress,
 ) error {
 	tx, err := db.BeginTx(ctx, nil)
 	if err != nil {
@@ -762,6 +843,11 @@ func applyBatch(ctx context.Context, db *sql.DB, upserts []scanRec,
 		return err
 	}
 
+	err = execDiskSizes(ctx, tx, diskSizes, prog)
+	if err != nil {
+		return err
+	}
+
 	err = execDeletes(ctx, tx, deletes, prog)
 	if err != nil {
 		return err
@@ -787,7 +873,7 @@ func execUpserts(ctx context.Context, tx *sql.Tx, upserts []scanRec,
 	defer func() { _ = st.Close() }()
 
 	for _, r := range upserts {
-		_, err = st.ExecContext(ctx, []byte(r.path), r.size,
+		_, err = st.ExecContext(ctx, []byte(r.path), r.size, r.diskSize,
 			r.mtime.Unix(), r.mtime.Nanosecond(),
 			r.head[:], r.tail[:], r.content[:])
 		if err != nil {
@@ -800,6 +886,31 @@ func execUpserts(ctx context.Context, tx *sql.Tx, upserts []scanRec,
 	return nil
 }
 
+// execDiskSizes sets the disk_size of the record of each of recs. It
+// does not touch size, so the totals triggers do not fire.
+func execDiskSizes(ctx context.Context, tx *sql.Tx, recs []fileRec,
+	prog *progress,
+) error {
+	st, err := tx.PrepareContext(ctx,
+		"UPDATE files SET disk_size = ? WHERE path = ?")
+	if err != nil {
+		return fmt.Errorf("prepare disk_size update: %w", err)
+	}
+
+	defer func() { _ = st.Close() }()
+
+	for _, r := range recs {
+		_, err = st.ExecContext(ctx, r.diskSize, []byte(r.path))
+		if err != nil {
+			return fmt.Errorf("update disk_size of %s: %w", r.path, err)
+		}
+
+		prog.increment()
+	}
+
+	return nil
+}
+
 // execDeletes removes the records for paths no longer present.
 func execDeletes(ctx context.Context, tx *sql.Tx, deletes []string,
 	prog *progress,

internal/sfdupes/db_test.go

@@ -1,4 +1,4 @@
-package main
+package sfdupes //nolint:testpackage // calls the unexported database openers
 
 import (
 	"context"
@@ -535,17 +535,12 @@ func TestLoadRowsRefuseWrongSizeHash(t *testing.T) {
 	}
 }
 
-// TestSignatureRowsNeedNoSort checks that SQLite reads signatureRowsSQL
-// from the files_signature index alone, with nothing to sort: the
-// first record comes at once, so report's read phase counts each
-// record as it comes rather than waiting on SQLite for all of them.
-func TestSignatureRowsNeedNoSort(t *testing.T) {
-	t.Parallel()
+// queryPlan returns the detail of each line of SQLite's EXPLAIN QUERY
+// PLAN for query.
+func queryPlan(t *testing.T, db *sql.DB, query string) []string {
+	t.Helper()
 
-	db := openTestDB(t)
-
-	rows, err := db.QueryContext(t.Context(),
-		"EXPLAIN QUERY PLAN "+signatureRowsSQL)
+	rows, err := db.QueryContext(t.Context(), "EXPLAIN QUERY PLAN "+query)
 	if err != nil {
 		t.Fatal(err)
 	}
@@ -573,12 +568,164 @@ func TestSignatureRowsNeedNoSort(t *testing.T) {
 		t.Fatal(err)
 	}
 
+	return plan
+}
+
+// TestSignatureRowsNeedNoSort checks that SQLite reads signatureRowsSQL
+// from the files_signature index alone, with nothing to sort: the
+// first record comes at once, so report's read phase counts each
+// record as it comes rather than waiting on SQLite for all of them.
+func TestSignatureRowsNeedNoSort(t *testing.T) {
+	t.Parallel()
+
+	db := openTestDB(t)
+
+	plan := queryPlan(t, db, signatureRowsSQL)
+
 	want := []string{"SCAN files USING COVERING INDEX files_signature"}
 	if !slices.Equal(plan, want) {
 		t.Errorf("query plan = %q, want %q", plan, want)
 	}
 }
 
+// TestCountsReadOnlyTotals checks that SQLite answers the queries for
+// the number of records and their total size from the one row of
+// totals. A plan that reads files or its index reads every record.
+func TestCountsReadOnlyTotals(t *testing.T) {
+	t.Parallel()
+
+	db := openTestDB(t)
+
+	for _, query := range []string{recordCountSQL, databaseCountsSQL} {
+		plan := queryPlan(t, db, query)
+
+		want := []string{"SCAN totals"}
+		if !slices.Equal(plan, want) {
+			t.Errorf("query plan of %q = %q, want %q", query, plan, want)
+		}
+	}
+}
+
+// TestCountsComeFromTotals sets the row of totals to numbers that files
+// does not hold, then checks that scan's load phase, the read phases of
+// trees and report, and info each report the numbers from totals.
+func TestCountsComeFromTotals(t *testing.T) {
+	t.Parallel()
+
+	// files is empty, so a count over files gives 0 records of 0 bytes.
+	const records, size = 7, 9000
+
+	db := openTestDB(t)
+
+	_, err := db.ExecContext(t.Context(),
+		"UPDATE totals SET records = ?, size = ?", records, size)
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	scanTotal, err := countRecords(t.Context(), db)
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	var treesTotal, reportTotal int64
+
+	err = loadFileRows(t.Context(), db,
+		func(n int64) { treesTotal = n }, func(scanRec) {})
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	err = loadSignatureRows(t.Context(), db,
+		func(n int64) { reportTotal = n },
+		func(scanRec) error { return nil })
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	info, err := readDatabaseCounts(t.Context(), db)
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	for name, got := range map[string]int64{
+		"scan's load":   scanTotal,
+		"trees' read":   treesTotal,
+		"report's read": reportTotal,
+		"info":          info.records,
+	} {
+		if got != records {
+			t.Errorf("%s: %d records, want %d from totals",
+				name, got, records)
+		}
+	}
+
+	if info.size != size {
+		t.Errorf("info: size %d, want %d from totals", info.size, size)
+	}
+}
+
+// assertTotalsMatchFiles fails unless the row of totals holds the
+// number of records and the sizes of all records added up, as counted
+// over files.
+func assertTotalsMatchFiles(t *testing.T, db *sql.DB) {
+	t.Helper()
+
+	got, err := readDatabaseCounts(t.Context(), db)
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	var records, size int64
+
+	err = db.QueryRowContext(t.Context(),
+		"SELECT COUNT(*), COALESCE(SUM(size), 0) FROM files").
+		Scan(&records, &size)
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	if got.records != records || got.size != size {
+		t.Errorf("totals = %d records of %d bytes, files holds %d of %d",
+			got.records, got.size, records, size)
+	}
+}
+
+// TestTotalsMatchFiles scans the smoke tree, rescans it after two files
+// change size, and rescans it after two files are removed. After each
+// scan the row of totals must agree with files.
+func TestTotalsMatchFiles(t *testing.T) {
+	t.Parallel()
+
+	dir := buildSmokeTree(t)
+	db := openTestDB(t)
+
+	syncTree(t, db, dir)
+	assertTotalsMatchFiles(t, db)
+
+	writeFile(t, dir, "a/one.bin", pattern(10, 2500))
+	writeFile(t, dir, "t1/f1", pattern(30, 1000))
+
+	if st := syncTree(t, db, dir); st.updated != 2 {
+		t.Fatalf("rescan stats = %+v, want 2 updated", st)
+	}
+
+	assertTotalsMatchFiles(t, db)
+
+	for _, name := range []string{"a/unique.bin", "t2/sub/f2"} {
+		err := os.Remove(filepath.Join(dir, name))
+		if err != nil {
+			t.Fatal(err)
+		}
+	}
+
+	if st := syncTree(t, db, dir); st.removed != 2 {
+		t.Fatalf("rescan stats = %+v, want 2 removed", st)
+	}
+
+	assertTotalsMatchFiles(t, db)
+}
+
 func TestApplyChangesRoundTrip(t *testing.T) {
 	t.Parallel()
 

internal/sfdupes/dwim.go

@@ -0,0 +1,38 @@
+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,
+		nil)
+
+	stop()
+
+	if err != nil {
+		return err
+	}
+
+	err = runTrees(ctx, 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

@@ -1,8 +1,9 @@
-package main
+package sfdupes
 
-// This file holds two rules for the walk (README "Rules for the walk"):
+// This file holds three rules for the walk (README "Rules for the
+// walk"): the paths given with --exclude, which the scan never enters;
 // the default excludes, the paths a scan's walk does not enter below an
-// operand unless scan is given --no-default-excludes, and the
+// operand unless scan is given --no-default-excludes; and the
 // filesystems that are not persistent, on which the scan never records
 // or reads anything.
 
@@ -12,6 +13,7 @@ import (
 	"fmt"
 	"io"
 	"io/fs"
+	"os"
 	"path/filepath"
 	"slices"
 	"strings"
@@ -43,17 +45,25 @@ const typesPerHelpLine = 6
 // readMountInfo reads.
 var errMountInfoLine = errors.New("unexpected line")
 
+// errExcludedOperand reports an operand at or below a path given with
+// --exclude.
+var errExcludedOperand = errors.New("operand excluded by --exclude")
+
 // walkRules holds the rules for the walk that a scan sets up as it
-// starts. excludes are the default excludes, or none with
-// --no-default-excludes. nonPersistent maps the device ID of every
-// mounted filesystem that is not persistent to its type; the scan
-// records and reads nothing on one of those, whatever the flags.
-// databaseFiles are the scan's own database files, which the walk
-// passes over (see databaseFiles in db.go).
+// starts. excludePaths are the paths given with --exclude, each with
+// the device ID and inode number of the file it names (see
+// excludePathInodes), which the walk neither enters nor records,
+// whatever path leads to them. defaultExcludes are the default
+// excludes, or none with --no-default-excludes. nonPersistent maps the
+// device ID of every mounted filesystem that is not persistent to its
+// type; the scan records and reads nothing on one of those, whatever
+// the flags. databaseFiles are the scan's own database files, which the
+// walk passes over (see databaseFiles in db.go).
 type walkRules struct {
-	excludes      []string
-	nonPersistent map[uint64]string
-	databaseFiles []fileRec
+	excludePaths    []fileRec
+	defaultExcludes []string
+	nonPersistent   map[uint64]string
+	databaseFiles   []fileRec
 }
 
 // defaultExcludes returns the default excludes of the system goos
@@ -97,6 +107,88 @@ func isDefaultExclude(path string, excludes []string) bool {
 	return false
 }
 
+// excludePathInodes returns each of paths, the --exclude values, as its
+// real path (see realPaths) with the device ID and inode number of the
+// file there. The walk compares what it reaches with those, as it does
+// with the database files, so it also leaves out an --exclude path
+// spelled another way, such as in another letter case on macOS.
+func excludePathInodes(paths []string) ([]fileRec, error) {
+	resolved, err := realPaths(paths)
+	if err != nil {
+		return nil, err
+	}
+
+	files := make([]fileRec, 0, len(resolved))
+
+	for _, path := range resolved {
+		fi, err := os.Lstat(path)
+		if err != nil {
+			return nil, err
+		}
+
+		dev, ino := inodeOfInfo(fi)
+		files = append(files, fileRec{path: path, dev: dev, ino: ino})
+	}
+
+	return files, nil
+}
+
+// matchingExcludePath returns the path of the one of excludePaths with
+// the device ID and inode number of fi, an lstat result, or "" when
+// there is none.
+func matchingExcludePath(fi fs.FileInfo, excludePaths []fileRec) string {
+	dev, ino := inodeOfInfo(fi)
+	f := fileRec{dev: dev, ino: ino}
+
+	for _, exclude := range excludePaths {
+		if sameInode(exclude, f) {
+			return exclude.path
+		}
+	}
+
+	return ""
+}
+
+// checkOperandsNotExcluded returns an error when one of roots, the
+// operands, or a directory above it is one of excludePaths, the
+// --exclude paths, by device ID and inode number. The error names the
+// operand and the --exclude path. The roots are absolute, so the
+// directories above each one end at /. A path here that lstat cannot
+// read is an error too.
+func checkOperandsNotExcluded(roots []string, excludePaths []fileRec) error {
+	for _, root := range roots {
+		for path := root; ; path = filepath.Dir(path) {
+			fi, err := os.Lstat(path)
+			if err != nil {
+				return fmt.Errorf("scan %s: %w", root, err)
+			}
+
+			exclude := matchingExcludePath(fi, excludePaths)
+			if exclude != "" {
+				return fmt.Errorf("scan %s: %w %s", root, errExcludedOperand,
+					exclude)
+			}
+
+			if path == "/" {
+				break
+			}
+		}
+	}
+
+	return nil
+}
+
+// excludePathLine returns the line the scan prints for path when fi,
+// its lstat, makes it one of rules.excludePaths, and "" when it does
+// not.
+func (rules walkRules) excludePathLine(path string, fi fs.FileInfo) string {
+	if matchingExcludePath(fi, rules.excludePaths) == "" {
+		return ""
+	}
+
+	return fmt.Sprintf("scan: skipped %s (--exclude)", path)
+}
+
 // nonPersistentFilesystemTypes returns the filesystem types that are
 // not persistent: filesystems that the kernel makes up or that are kept
 // in memory. devfs is the macOS filesystem of /dev; the others are

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"
@@ -14,10 +14,15 @@ import (
 	"golang.org/x/sys/unix"
 )
 
+// excludeFlag is the scan flag that names a path the walk never enters.
+const excludeFlag = "--exclude"
+
 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: {
@@ -186,7 +191,7 @@ func TestScanDoesNotEnterDefaultExclude(t *testing.T) {
 	unseen := writeFile(t, excluded, "new", pattern(2, 10))
 
 	st, err := syncScan(t.Context(), db, []string{dir}, 1, false,
-		walkRules{excludes: []string{excluded}})
+		walkRules{defaultExcludes: []string{excluded}})
 	if err != nil {
 		t.Fatal(err)
 	}
@@ -232,7 +237,7 @@ func TestScanWalksOperandInDefaultExclude(t *testing.T) {
 			db := openTestDB(t)
 
 			st, err := syncScan(t.Context(), db, roots, 1, false,
-				walkRules{excludes: []string{excluded}})
+				walkRules{defaultExcludes: []string{excluded}})
 			if err != nil {
 				t.Fatal(err)
 			}
@@ -260,7 +265,7 @@ func TestScanNamesNoDefaultExcludeThatIsAnOperand(t *testing.T) {
 	f := writeFile(t, excluded, "f", pattern(1, 10))
 
 	st, err := syncScan(t.Context(), db, []string{dir, excluded}, 1, false,
-		walkRules{excludes: []string{excluded}})
+		walkRules{defaultExcludes: []string{excluded}})
 	if err != nil {
 		t.Fatal(err)
 	}
@@ -284,7 +289,7 @@ 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")
 	}
@@ -354,6 +359,217 @@ func TestRunScanNoDefaultExcludes(t *testing.T) {
 	assertRecorded(t, path, f, true)
 }
 
+// TestRunScanExcludeNested scans a tree through the command with an
+// --exclude path two levels below the operand. The walk records nothing
+// at or below it and says so. The record an earlier scan left there is
+// kept although its file is gone.
+func TestRunScanExcludeNested(t *testing.T) {
+	path := testDBPath(t)
+	t.Setenv(databaseEnv, path)
+
+	dir := realTempDir(t)
+	excluded := filepath.Join(dir, "a", "b")
+	kept := writeFile(t, dir, "a/f", pattern(1, 10))
+	gone := writeFile(t, excluded, "gone", pattern(2, 10))
+
+	scanOK(t, dir)
+
+	err := os.Remove(gone)
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	unseen := writeFile(t, excluded, "c/new", pattern(3, 10))
+
+	stderr := scanOK(t, excludeFlag, excluded, dir)
+
+	line := "scan: skipped " + excluded + " (--exclude)\n"
+	if !strings.Contains(stderr, line) {
+		t.Errorf("stderr = %q, want %q", stderr, line)
+	}
+
+	assertRecorded(t, path, kept, true)
+	assertRecorded(t, path, gone, true)
+	assertRecorded(t, path, unseen, false)
+}
+
+// TestRunScanExcludeRepeated gives --exclude twice, once for a
+// directory and once for a file, the file through a symlink to it. The
+// walk records neither, and records the file beside them.
+func TestRunScanExcludeRepeated(t *testing.T) {
+	path := testDBPath(t)
+	t.Setenv(databaseEnv, path)
+
+	dir := realTempDir(t)
+	inDir := writeFile(t, dir, "skip/f", pattern(1, 10))
+	file := writeFile(t, dir, "skip-file", pattern(2, 10))
+	kept := writeFile(t, dir, "keep", pattern(3, 10))
+
+	link := filepath.Join(t.TempDir(), "link")
+	symlink(t, file, link)
+
+	scanOK(t, excludeFlag, filepath.Dir(inDir), excludeFlag, link, dir)
+
+	assertRecorded(t, path, inDir, false)
+	assertRecorded(t, path, file, false)
+	assertRecorded(t, path, kept, true)
+}
+
+// TestRunScanExcludeReachedByAnotherPath gives --exclude a directory
+// through a symlink and a file through "..", so the walk reaches
+// neither by the path given. The walk also reaches the file through a
+// hard link. It records none of these, prints a line naming each, and
+// records the file beside them.
+func TestRunScanExcludeReachedByAnotherPath(t *testing.T) {
+	path := testDBPath(t)
+	t.Setenv(databaseEnv, path)
+
+	dir := realTempDir(t)
+	inDir := writeFile(t, dir, "a/cache/f", pattern(1, 10))
+	file := writeFile(t, dir, "a/big", pattern(2, 10))
+	kept := writeFile(t, dir, "keep", pattern(3, 10))
+
+	hardLink := filepath.Join(dir, "big-link")
+
+	err := os.Link(file, hardLink)
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	link := filepath.Join(t.TempDir(), "link")
+	symlink(t, filepath.Join(dir, "a"), link)
+
+	// Joined as text, since filepath.Join would drop the "..".
+	dotDot := dir + "/a/cache/../big"
+
+	stderr := scanOK(t, excludeFlag, filepath.Join(link, "cache"),
+		excludeFlag, dotDot, dir)
+
+	for _, skipped := range []string{filepath.Dir(inDir), file, hardLink} {
+		line := "scan: skipped " + skipped + " (--exclude)\n"
+		if !strings.Contains(stderr, line) {
+			t.Errorf("stderr = %q, want %q", stderr, line)
+		}
+	}
+
+	assertRecorded(t, path, inDir, false)
+	assertRecorded(t, path, file, false)
+	assertRecorded(t, path, hardLink, false)
+	assertRecorded(t, path, kept, true)
+}
+
+// TestRunScanExcludedOperand checks that an operand at or below an
+// --exclude path is a fatal error that names both, and so is an
+// --exclude path that does not exist. An operand that is a hard link to
+// an --exclude file is at it. Neither scan writes a database.
+func TestRunScanExcludedOperand(t *testing.T) {
+	dir := realTempDir(t)
+	sub := filepath.Join(dir, "sub")
+	f := writeFile(t, sub, "f", pattern(1, 10))
+
+	hardLink := filepath.Join(dir, "f-link")
+
+	err := os.Link(f, hardLink)
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	cases := map[string]struct {
+		args []string
+		want string
+	}{
+		"at it": {
+			[]string{excludeFlag, sub, sub},
+			"scan " + sub + ": operand excluded by --exclude " + sub + "\n",
+		},
+		"below it": {
+			[]string{excludeFlag, dir, sub},
+			"scan " + sub + ": operand excluded by --exclude " + dir + "\n",
+		},
+		"after an operand it does not exclude": {
+			[]string{dir, excludeFlag, sub, sub},
+			"scan " + sub + ": operand excluded by --exclude " + sub + "\n",
+		},
+		"a hard link to it": {
+			[]string{excludeFlag, f, hardLink},
+			"scan " + hardLink + ": operand excluded by --exclude " + f + "\n",
+		},
+		"exclude missing": {
+			[]string{excludeFlag, filepath.Join(dir, "nope"), dir},
+			"--exclude: resolve " + filepath.Join(dir, "nope") + ": ",
+		},
+	}
+
+	for name, tc := range cases {
+		t.Run(name, func(t *testing.T) {
+			path := testDBPath(t)
+			t.Setenv(databaseEnv, path)
+
+			stdout := captureStdout(t)
+			stderr := captureStderr(t)
+
+			code := run(append([]string{cmdScan}, tc.args...), os.Stdout,
+				os.Stderr)
+			if code != exitFatal {
+				t.Errorf("run(scan %q) = %d, want %d", tc.args, code,
+					exitFatal)
+			}
+
+			assertFatalOutput(t, stderr(), stdout())
+
+			if !strings.Contains(stderr(), "sfdupes: "+tc.want) {
+				t.Errorf("stderr = %q, want %q", stderr(), tc.want)
+			}
+
+			_, err := os.Lstat(path)
+			if !errors.Is(err, os.ErrNotExist) {
+				t.Errorf("lstat %s: %v, want no database", path, err)
+			}
+		})
+	}
+}
+
+// TestRunScanRejectsEmptyExclude checks that an empty --exclude value,
+// given as its own argument, after "=" or after another --exclude, is
+// a usage error reported in one line before anything is scanned
+// (README "Settings").
+func TestRunScanRejectsEmptyExclude(t *testing.T) {
+	dir := t.TempDir()
+
+	cases := map[string][]string{
+		"separate":     {excludeFlag, "", dir},
+		"joined by =":  {excludeFlag + "=", dir},
+		"after a path": {excludeFlag, t.TempDir(), excludeFlag, "", dir},
+	}
+
+	for name, args := range cases {
+		t.Run(name, func(t *testing.T) {
+			path := testDBPath(t)
+			t.Setenv(databaseEnv, path)
+
+			var stdout, stderr bytes.Buffer
+
+			code := run(append([]string{cmdScan}, args...), &stdout,
+				&stderr)
+			if code != exitUsage {
+				t.Errorf("run(scan %q) = %d, want %d", args, code,
+					exitUsage)
+			}
+
+			want := "Error: --exclude must not be empty\n"
+			if stdout.String() != "" || stderr.String() != want {
+				t.Errorf("stdout, stderr = %q, %q, want \"\", %q",
+					stdout.String(), stderr.String(), want)
+			}
+
+			_, err := os.Lstat(path)
+			if !errors.Is(err, os.ErrNotExist) {
+				t.Errorf("lstat %s: %v, want no database", path, err)
+			}
+		})
+	}
+}
+
 // TestRunScanSkipsNonPersistentOperand scans, through the command, a
 // directory on a filesystem that is not persistent, with and without
 // --no-default-excludes: either way it is skipped, with a line saying

internal/sfdupes/info.go

@@ -1,4 +1,4 @@
-package main
+package sfdupes
 
 import (
 	"context"
@@ -26,11 +26,11 @@ func infoPhase(name string) string {
 // 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 count (count the records,
-// with one query). Each display ends before the next phase starts, and
-// before an error is returned to be printed. The details are written
-// once the last display has ended, so no display is drawn while they
-// are written.
+// own on stderr: open (open the database) and count (read the number of
+// records and their total size from the totals table). Each display
+// ends before the next phase starts, and before an error is returned
+// to be printed. The details are written once the last display has
+// ended, so no display is drawn while they are written.
 func runInfo(ctx context.Context, stdout io.Writer) error {
 	dbPath, source, err := databasePath()
 	if err != nil {
@@ -56,7 +56,7 @@ func runInfo(ctx context.Context, stdout io.Writer) error {
 
 	defer func() { _ = db.Close() }()
 
-	// One query counts everything, so the phase never has a total.
+	// One row holds both counts, so the phase never has a total.
 	prog = newProgress(progressParams{
 		label: infoPhase("count"), total: -1,
 		waitingFor: countingRecords,

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"
@@ -60,7 +60,7 @@ const fallbackWidth = 80
 const spinnerMargin = 5
 
 // countingRecords is what the display of a phase that reads the records
-// says while it counts them, before it has its total.
+// says until it has the number of records, its total.
 const countingRecords = "counting the records"
 
 // openPhase is the name of the phase in which report, trees and info

internal/sfdupes/progress_test.go

@@ -1,4 +1,4 @@
-package main
+package sfdupes //nolint:testpackage // drives the unexported startProgress
 
 import (
 	"fmt"
@@ -642,9 +642,9 @@ func TestTerminalStalledLines(t *testing.T) {
 		{label: scanPhase("hash"), stalledOn: hashStalledOn},
 		{label: scanPhase("update"), stalledOn: "db"},
 		{label: treesPhase("read"), stalledOn: "db"},
-		{label: treesPhase("group"), stalledOn: "cpu"},
+		{label: treesPhase("group"), stalledOn: "cpu/disk"},
 		{label: treesPhase("write"), stalledOn: "out"},
-		{label: reportPhase("read"), stalledOn: "db/out"},
+		{label: reportPhase("read"), stalledOn: "db/disk/out"},
 	}
 
 	for _, params := range phases {

internal/sfdupes/report.go

@@ -1,14 +1,17 @@
-package main
+package sfdupes
 
 import (
 	"context"
 	"crypto/sha256"
 	"database/sql"
+	"errors"
 	"fmt"
 	"io"
+	"io/fs"
 	"os"
 	"slices"
 	"strings"
+	"syscall"
 	"time"
 )
 
@@ -21,14 +24,16 @@ const minGroupSize = 2
 
 // scanRec is one file record from the database. The signature (size,
 // head, tail, content) is the duplicate key; mtime is informational
-// only and used by scan for change detection.
+// only and used by scan for change detection. diskSize is the bytes the
+// file takes on disk, which trees adds up.
 type scanRec struct {
-	size    int64
-	mtime   time.Time
-	head    [sha256.Size]byte
-	tail    [sha256.Size]byte
-	content [sha256.Size]byte
-	path    string
+	size     int64
+	diskSize int64
+	mtime    time.Time
+	head     [sha256.Size]byte
+	tail     [sha256.Size]byte
+	content  [sha256.Size]byte
+	path     string
 }
 
 // reportPhase names one phase of report with its place among all of
@@ -39,17 +44,17 @@ 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
-// 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.
+// duplicates report as TSV on stdout. Of the scanned filesystem it
+// only checks, with pathExists, that each path in a duplicate group is
+// still there. 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 (count the records,
-// then read them in signature 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.
+// own on stderr: open (open the database) and read (read the number of
+// records from the totals table, then read the records in signature
+// 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 {
 	dbPath, source, err := databasePath()
 	if err != nil {
@@ -75,13 +80,14 @@ func runReport(ctx context.Context, stdout io.Writer) error {
 
 	defer func() { _ = db.Close() }()
 
-	// The read phase writes the report to stdout while it reads the
-	// records, so it may wait on either.
+	// The read phase checks the paths of each duplicate group on disk
+	// and writes the report to stdout while it reads the records, so it
+	// may wait on any of the three.
 	prog = newProgress(progressParams{
 		label: reportPhase("read"), unit: "records", total: -1,
-		waitingFor: countingRecords, stalledOn: "db/out",
+		waitingFor: countingRecords, stalledOn: "db/disk/out",
 	})
-	report, err := readReport(ctx, db, dbPath, stdout, prog)
+	report, err := readReport(ctx, db, dbPath, stdout, pathExists, prog)
 
 	prog.finish()
 
@@ -102,14 +108,15 @@ 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
-// through prog's writer. It returns what it wrote, with the totals for
-// the summary line.
+// read. A path for which exists returns false is left out of its 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,
+	stdout io.Writer, exists func(path string) bool, prog *progress,
 ) (*reportWriter, error) {
 	out := prog.writer(stdout)
-	report := &reportWriter{out: out}
+	report := &reportWriter{out: out, exists: exists}
 
 	_, err := fmt.Fprintln(out, "first\tdupe\tsize")
 	if err != nil {
@@ -156,6 +163,10 @@ func readReport(ctx context.Context, db *sql.DB, dbPath string,
 type reportWriter struct {
 	out io.Writer
 
+	// exists reports whether a path is still on disk. A path that is
+	// gone is left out of its group.
+	exists func(path string) bool
+
 	sig    scanRec    // the signature being read; its path is not used
 	paths  []string   // the paths read so far with sig
 	groups [][]string // the duplicate groups of sig.size, each sorted
@@ -192,11 +203,20 @@ func (w *reportWriter) add(r scanRec) error {
 	return nil
 }
 
-// endGroup ends the paths read with w.sig: two or more are a duplicate
-// group, held with its paths sorted until writeGroups writes it.
+// endGroup ends the paths read with w.sig: two or more that are still
+// on disk are a duplicate group, held with its paths sorted until
+// writeGroups writes it. Empty files form no group, since removing one
+// frees nothing. Only the paths of a possible group are checked, never
+// a path with no duplicate or an empty file.
 func (w *reportWriter) endGroup() {
-	if len(w.paths) < minGroupSize {
-		// A path with no duplicate is dropped, and its slice reused.
+	if len(w.paths) >= minGroupSize && w.sig.size > 0 {
+		w.paths = slices.DeleteFunc(w.paths, func(p string) bool {
+			return !w.exists(p)
+		})
+	}
+
+	if len(w.paths) < minGroupSize || w.sig.size == 0 {
+		// The paths are dropped, and their slice reused.
 		w.paths = w.paths[:0]
 
 		return
@@ -243,6 +263,16 @@ func (w *reportWriter) finish() error {
 	return w.writeGroups()
 }
 
+// pathExists reports whether path is still on disk, for report and
+// trees. It is false only when lstat finds that the path, or a
+// directory above it, is gone. Any other error counts as present, so
+// a user who may not look inside a directory still sees its copies.
+func pathExists(path string) bool {
+	_, err := os.Lstat(path)
+
+	return !errors.Is(err, fs.ErrNotExist) && !errors.Is(err, syscall.ENOTDIR)
+}
+
 // 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"
@@ -38,8 +38,8 @@ func awkwardPairRecs() []scanRec {
 	h, tl, c := testHash("h"), testHash("t"), testHash("c")
 
 	return []scanRec{
-		{size: 5, head: h, tail: tl, content: c, path: "/d/A/f"},
-		{size: 5, head: h, tail: tl, content: c, path: awkwardDir + "/f"},
+		{size: 5, diskSize: 4096, head: h, tail: tl, content: c, path: "/d/A/f"},
+		{size: 5, diskSize: 4096, head: h, tail: tl, content: c, path: awkwardDir + "/f"},
 	}
 }
 
@@ -72,15 +72,37 @@ type dupeGroup struct {
 	paths []string
 }
 
+// everyPathExists stands in for pathExists where a test's records name
+// made-up paths that are not on disk.
+func everyPathExists(string) bool { return true }
+
+// recsOnDisk returns a new directory and recs with each path moved
+// under it, after creating an empty file at each moved path: report and
+// trees then find every path still on disk.
+func recsOnDisk(t *testing.T, recs []scanRec) (string, []scanRec) {
+	t.Helper()
+
+	dir := realTempDir(t)
+	moved := make([]scanRec, len(recs))
+
+	for i, r := range recs {
+		r.path = writeFile(t, dir, r.path, nil)
+		moved[i] = r
+	}
+
+	return dir, moved
+}
+
 // dupeGroups returns the duplicate groups report reads from db, in
 // report order, from the rows it writes: a group's rows come together,
-// each naming the group's first path.
+// each naming the group's first path. Every path counts as still on
+// disk.
 func dupeGroups(t *testing.T, db *sql.DB) []dupeGroup {
 	t.Helper()
 
 	var out bytes.Buffer
 
-	_, err := readReport(t.Context(), db, "", &out, nil)
+	_, err := readReport(t.Context(), db, "", &out, everyPathExists, nil)
 	if err != nil {
 		t.Fatal(err)
 	}
@@ -127,7 +149,8 @@ func dupeGroupsOf(t *testing.T, recs []scanRec) []dupeGroup {
 }
 
 func TestRunReportEscapesPaths(t *testing.T) {
-	t.Setenv(databaseEnv, seedDatabase(t, awkwardPairRecs()))
+	dir, recs := recsOnDisk(t, awkwardPairRecs())
+	t.Setenv(databaseEnv, seedDatabase(t, recs))
 
 	var stdout, stderr bytes.Buffer
 
@@ -138,7 +161,7 @@ func TestRunReportEscapesPaths(t *testing.T) {
 	}
 
 	want := "first\tdupe\tsize\n" +
-		`/d/\tone\ntwo\rthree\\four/f` + "\t/d/A/f\t5\n"
+		dir + `/d/\tone\ntwo\rthree\\four/f` + "\t" + dir + "/d/A/f\t5\n"
 	if got := stdout.String(); got != want {
 		t.Errorf("stdout = %q, want %q", got, want)
 	}
@@ -172,7 +195,8 @@ 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, "", failingWriter{},
+		everyPathExists, prog)
 	if !errors.Is(err, errWriteFailed) ||
 		!strings.HasPrefix(err.Error(), "write stdout: ") {
 		t.Errorf("error = %v, want write stdout: %v", err, errWriteFailed)
@@ -203,7 +227,8 @@ const smokeReport = "first\tdupe\tsize\n" +
 // it ends; read counts the 6 records before it reads them. The summary
 // comes last, and stdout holds the report alone.
 func TestRunReportProgressNamesEachPhase(t *testing.T) {
-	path := seedDatabase(t, smokeTreeRecs())
+	dir, recs := recsOnDisk(t, smokeTreeRecs())
+	path := seedDatabase(t, recs)
 	t.Setenv(databaseEnv, path)
 
 	stderr := captureStderr(t)
@@ -216,8 +241,9 @@ func TestRunReportProgressNamesEachPhase(t *testing.T) {
 			code, exitOK, stderr())
 	}
 
-	if got := stdout.String(); got != smokeReport {
-		t.Errorf("stdout = %q, want %q", got, smokeReport)
+	report := strings.ReplaceAll(smokeReport, "/d/", dir+"/d/")
+	if got := stdout.String(); got != report {
+		t.Errorf("stdout = %q, want %q", got, report)
 	}
 
 	// How each line starts; the rate at the end of a phase varies.
@@ -266,7 +292,7 @@ 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, "", os.Stderr, everyPathExists, p)
 
 	p.finish()
 
@@ -301,6 +327,8 @@ func TestRunReportsIgnoreInsertionOrder(t *testing.T) {
 		scanRec{size: 50, head: a, tail: a, content: a, path: "/x/1"},
 	)
 
+	_, recs = recsOnDisk(t, recs)
+
 	reversed := slices.Clone(recs)
 	slices.Reverse(reversed)
 
@@ -434,6 +462,140 @@ 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)
+	}
+}
+
+// TestReadReportChecksOnlyPossibleDuplicates checks that report asks
+// whether a path is on disk only when its signature has two or more
+// records, and never for an empty file.
+func TestReadReportChecksOnlyPossibleDuplicates(t *testing.T) {
+	t.Parallel()
+
+	a, u, e := testHash("a"), testHash("u"), sha256.Sum256(nil)
+	recs := []scanRec{
+		{size: 9, head: a, tail: a, content: a, path: "/copy/1"},
+		{size: 9, head: a, tail: a, content: a, path: "/copy/2"},
+		{size: 9, head: a, tail: a, content: a, path: "/copy/3"},
+		{size: 9, head: u, tail: u, content: u, path: "/lonely"},
+		{size: 0, head: e, tail: e, content: e, path: "/empty1"},
+		{size: 0, head: e, tail: e, content: e, path: "/empty2"},
+	}
+
+	db := openTestDB(t)
+
+	err := applyChanges(t.Context(), db, recs, nil, nil)
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	var checked []string
+
+	exists := func(path string) bool {
+		checked = append(checked, path)
+
+		return true
+	}
+
+	_, err = readReport(t.Context(), db, "", io.Discard, exists, nil)
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	slices.Sort(checked)
+
+	want := []string{"/copy/1", "/copy/2", "/copy/3"}
+	if !slices.Equal(checked, want) {
+		t.Errorf("paths checked on disk = %q, want %q", checked, want)
+	}
+}
+
+// TestReadReportDropsGroupLeftWithOnePath checks that a group of two
+// paths, one of them gone, is no duplicate group. If kept, it would
+// write no row, but the summary line would count it.
+func TestReadReportDropsGroupLeftWithOnePath(t *testing.T) {
+	t.Parallel()
+
+	a := testHash("a")
+	recs := []scanRec{
+		{size: 9, head: a, tail: a, content: a, path: "/a/kept"},
+		{size: 9, head: a, tail: a, content: a, path: "/a/gone"},
+	}
+
+	db := openTestDB(t)
+
+	err := applyChanges(t.Context(), db, recs, nil, nil)
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	exists := func(path string) bool { return path != "/a/gone" }
+
+	report, err := readReport(t.Context(), db, "", io.Discard, exists, nil)
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	if report.dupeGroups != 0 {
+		t.Errorf("duplicate groups = %d, want 0", report.dupeGroups)
+	}
+}
+
+// TestReadReportKeepsGroupLeftWithTwoPaths checks that a group of three
+// paths, one of them gone, is a duplicate group of the other two.
+func TestReadReportKeepsGroupLeftWithTwoPaths(t *testing.T) {
+	t.Parallel()
+
+	a := testHash("a")
+	recs := []scanRec{
+		{size: 9, head: a, tail: a, content: a, path: "/b/kept1"},
+		{size: 9, head: a, tail: a, content: a, path: "/b/gone"},
+		{size: 9, head: a, tail: a, content: a, path: "/b/kept2"},
+	}
+
+	db := openTestDB(t)
+
+	err := applyChanges(t.Context(), db, recs, nil, nil)
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	exists := func(path string) bool { return path != "/b/gone" }
+
+	var out bytes.Buffer
+
+	report, err := readReport(t.Context(), db, "", &out, exists, nil)
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	if report.dupeGroups != 1 {
+		t.Errorf("duplicate groups = %d, want 1", report.dupeGroups)
+	}
+
+	want := "first\tdupe\tsize\n/b/kept1\t/b/kept2\t9\n"
+	if got := out.String(); got != want {
+		t.Errorf("stdout = %q, want %q", got, want)
+	}
+}
+
 func TestDupeGroupsContentSeparates(t *testing.T) {
 	t.Parallel()
 

internal/sfdupes/scan.go

@@ -1,4 +1,4 @@
-package main
+package sfdupes
 
 import (
 	"cmp"
@@ -48,32 +48,30 @@ const sampleWindow = 1024 * 1024
 // and hash worker pools.
 const workQueueDepth = 1024
 
-// zfsDirName is the name of the directory in which ZFS shows a
-// filesystem's snapshots. The walk never enters one, since it would
-// list every file once per snapshot.
-const zfsDirName = ".zfs"
-
 // errInterrupted reports a scan stopped by SIGINT or SIGTERM. runScan
 // has already printed its line, so run prints nothing more.
 var errInterrupted = errors.New("scan interrupted")
 
-// fileRec carries one statted file between the scan phases. dev and
-// ino identify the underlying inode so hard-linked paths can share
-// one read; both are zero when the platform exposes no inode.
+// fileRec carries one statted file between the scan phases. diskSize is
+// the bytes the file takes on disk. dev and ino identify the underlying
+// inode so hard-linked paths can share one read; both are zero when the
+// platform exposes no inode.
 type fileRec struct {
-	path  string
-	size  int64
-	mtime time.Time
-	dev   uint64
-	ino   uint64
+	path     string
+	size     int64
+	diskSize int64
+	mtime    time.Time
+	dev      uint64
+	ino      uint64
 }
 
 // fileMeta is the in-memory index entry for one existing database
-// record: just enough for change detection. Hashes stay on disk; at
+// record: what the walk compares the file with. Hashes stay on disk; at
 // tens of millions of records they would dominate the scan's memory.
 type fileMeta struct {
-	size  int64
-	mtime time.Time
+	size     int64
+	diskSize int64
+	mtime    time.Time
 }
 
 // scanUnit is what every scan phase counts, as its progress display
@@ -104,40 +102,44 @@ func scanPhase(name string) string {
 // scan command rejects anything less. Before the lock is taken, the
 // scan lists the filesystems that are not persistent, on which the walk
 // records nothing; unless noDefaultExcludes is set, the walk does not
-// enter the default excludes either. Once the database is open, the
-// scan notes its files, which the walk passes over.
+// enter the default excludes either. The walk neither enters nor
+// records the paths in excludePaths, the --exclude values; an operand
+// at or below one is a fatal error. Once the database is open, the scan
+// notes its files, which the walk passes over.
 func runScan(ctx context.Context, roots []string, workers int,
-	oneFS, noDefaultExcludes bool,
+	oneFS, noDefaultExcludes bool, excludePaths []string,
 ) error {
 	dbPath, source, err := databasePath()
 	if err != nil {
 		return err
 	}
 
-	// A database file missing now is created by lockScanDatabase below.
-	what := "database"
+	printDatabasePath(dbPath, source)
 
-	_, err = os.Stat(dbPath)
-	if errors.Is(err, fs.ErrNotExist) {
-		what = "new database"
-	}
-
-	fmt.Fprintf(os.Stderr, "scan: %s %s (%s)\n", what, escapePath(dbPath),
-		source)
-
-	roots, err = resolveRoots(roots)
+	roots, err = realPaths(roots)
 	if err != nil {
 		return err
 	}
 
-	nonPersistent, err := nonPersistentFilesystems()
+	var rules walkRules
+
+	rules.excludePaths, err = excludePathInodes(excludePaths)
+	if err != nil {
+		return fmt.Errorf("--exclude: %w", err)
+	}
+
+	err = checkOperandsNotExcluded(roots, rules.excludePaths)
+	if err != nil {
+		return err
+	}
+
+	rules.nonPersistent, err = nonPersistentFilesystems()
 	if err != nil {
 		return fmt.Errorf("list the mounted filesystems: %w", err)
 	}
 
-	rules := walkRules{nonPersistent: nonPersistent}
 	if !noDefaultExcludes {
-		rules.excludes = defaultExcludes(runtime.GOOS)
+		rules.defaultExcludes = defaultExcludes(runtime.GOOS)
 	}
 
 	lock, err := lockScanDatabase(dbPath)
@@ -183,6 +185,21 @@ func runScan(ctx context.Context, roots []string, workers int,
 	return nil
 }
 
+// printDatabasePath prints on stderr the line that names the database
+// at dbPath, with source, saying whether it is new. A database file
+// missing now is new: lockScanDatabase creates it.
+func printDatabasePath(dbPath, source string) {
+	what := "database"
+
+	_, err := os.Stat(dbPath)
+	if errors.Is(err, fs.ErrNotExist) {
+		what = "new database"
+	}
+
+	fmt.Fprintf(os.Stderr, "scan: %s %s (%s)\n", what, escapePath(dbPath),
+		source)
+}
+
 // interruptContext returns a copy of ctx that the first SIGINT or
 // SIGTERM cancels; the scan command runs the scan under it. stop
 // releases the signals.
@@ -211,29 +228,31 @@ func interrupted(walked int) error {
 	return errInterrupted
 }
 
-// resolveRoots converts each PATH operand to an absolute, lexically
-// cleaned path (symlinks are not resolved) and verifies that it
-// exists. Database records are keyed by absolute path, so scan results
-// must not depend on the working directory.
-func resolveRoots(roots []string) ([]string, error) {
-	abs := make([]string, 0, len(roots))
+// realPaths returns the real path of each of paths, the PATH operands
+// or the --exclude values: absolute, with every symlink in it followed.
+// Database records are keyed by that path, so scan results depend
+// neither on the working directory nor on the symlinks an operand was
+// given through. A path 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 realPaths(paths []string) ([]string, error) {
+	resolved := make([]string, 0, len(paths))
 
-	for _, root := range roots {
-		a, err := filepath.Abs(root)
+	for _, path := range paths {
+		a, err := absolutePath(path)
 		if err != nil {
-			return nil, fmt.Errorf("resolve %s: %w", root, err)
+			return nil, fmt.Errorf("resolve %s: %w", path, err)
 		}
 
-		// A nonexistent operand is a fatal error before any scanning.
-		_, err = os.Lstat(a)
+		r, err := filepath.EvalSymlinks(a)
 		if err != nil {
-			return nil, err
+			return nil, fmt.Errorf("resolve %s: %w", path, err)
 		}
 
-		abs = append(abs, a)
+		resolved = append(resolved, r)
 	}
 
-	return abs, nil
+	return resolved, nil
 }
 
 // pruneRoots drops operands already covered by another operand:
@@ -277,10 +296,9 @@ func pruneRoots(roots []string, oneFS bool, rules walkRules,
 }
 
 // walkReaches reports whether the walk of operand above reaches r, an
-// operand under it. That walk never follows a symlink. It does not
-// enter a directory named .zfs, nor a default exclude in rules, nor a
-// directory that device puts on a filesystem in rules that is not
-// persistent, nor, with -x, one that device puts on a different
+// operand under it. That walk does not enter a default exclude in
+// rules, nor a directory that device puts on a filesystem in rules that
+// is not persistent, nor, with -x, one that device puts on a different
 // filesystem than above, when device knows above's. It reaches every
 // regular file in a directory it enters, so for a regular-file operand
 // the directories checked start at its directory; they end below above.
@@ -297,16 +315,7 @@ func walkReaches(above, r string, oneFS bool, rules walkRules,
 	}
 
 	for ; dir != above; dir = filepath.Dir(dir) {
-		if isDefaultExclude(dir, rules.excludes) {
-			return false
-		}
-
-		if filepath.Base(dir) == zfsDirName {
-			return false
-		}
-
-		fi, err = os.Lstat(dir)
-		if err == nil && fi.Mode()&fs.ModeSymlink != 0 {
+		if isDefaultExclude(dir, rules.defaultExcludes) {
 			return false
 		}
 
@@ -354,11 +363,12 @@ type scanStats struct {
 // whatever remains after the walk and hash phases is deleted by the
 // update phase.
 type scanState struct {
-	db       *sql.DB
-	existing map[string]fileMeta
-	toHash   []fileRec // new and changed files: must be read
-	batch    []scanRec
-	st       scanStats
+	db        *sql.DB
+	existing  map[string]fileMeta
+	toHash    []fileRec // new and changed files: must be read
+	diskSizes []fileRec // unchanged files whose disk_size changed
+	batch     []scanRec
+	st        scanStats
 }
 
 // syncScan synchronizes the database with the filesystem under roots;
@@ -398,7 +408,8 @@ func (s *scanState) runPhases(ctx context.Context, roots []string,
 ) error {
 	// Types and filesystems are checked before pruning so that an
 	// operand under a dropped one is still scanned, not dropped as lying
-	// under it.
+	// under it, and so that an operand inside a .zfs directory gets its
+	// warning even when it lies under another operand.
 	roots = pruneRoots(s.walkableRoots(roots, rules), oneFS, rules,
 		deviceOfPath)
 
@@ -426,15 +437,17 @@ 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. Every other operand is warned
-// about, counted as skipped, and dropped. A dropped operand is no
-// longer a root, so the records stored beneath it are treated as if it
-// had not been given: those under no other root count as outside the
-// roots and are not deleted as unverified. An operand on a filesystem
-// in rules that is not persistent is dropped 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.
+// files, and directories not named .zfs, none of them inside a
+// directory named .zfs. The operands are real paths from realPaths,
+// so these checks apply to what a symlink operand points at. Every
+// other operand is warned about, counted as skipped, and dropped. A
+// dropped operand is no longer a root, so the records stored beneath it
+// are treated as if it had not been given: those under no other root
+// count as outside the roots and are not deleted as unverified. An
+// operand on a filesystem in rules that is not persistent is dropped
+// 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))
 
@@ -469,8 +482,8 @@ func (s *scanState) walkableRoots(roots []string, rules walkRules) []string {
 // included, so its display counts against the number of records.
 func (s *scanState) loadIndex(ctx context.Context, roots []string) error {
 	// Indexing tens of millions of records takes real time; without a
-	// display the scan looks hung before the walk begins. Counting them
-	// first gives the display its total.
+	// display the scan looks hung before the walk begins. The number of
+	// records, read first, gives the display its total.
 	prog := newProgress(progressParams{
 		label: scanPhase("load"), unit: scanUnit, total: -1,
 		waitingFor: countingRecords, stalledOn: "db",
@@ -486,24 +499,25 @@ func (s *scanState) loadIndex(ctx context.Context, roots []string) error {
 
 	s.existing = make(map[string]fileMeta)
 
-	return loadFileMeta(ctx, s.db,
-		func(path string, size int64, mtime time.Time) {
-			prog.increment()
+	return loadFileMeta(ctx, s.db, func(path string, m fileMeta) {
+		prog.increment()
 
-			if underAnyRoot(path, roots) {
-				s.existing[path] = fileMeta{size: size, mtime: mtime}
-			}
-		})
+		if underAnyRoot(path, roots) {
+			s.existing[path] = m
+		}
+	})
 }
 
 // walkPhase drains the walk and queues every new or changed file for
-// the hash phase. An unchanged file needs nothing more, and its record
-// counts as verified. A record at or below a path the walk left out,
-// because -x stopped at it, it is a default exclude, or it is not on a
-// persistent filesystem, counts as outside the roots: it is not
-// deleted. That does not hold below a root at or inside that path,
-// since that root's own walk verifies the records below it; nor is a
-// line printed for such a root.
+// the hash phase. An unchanged file is not read, and its record counts
+// as verified. When its disk_size differs from the record's, it is
+// queued for the update phase, which writes the new disk_size. A record
+// at or below a path the walk left out, because -x stopped at it, it is
+// an --exclude path or a default exclude, or it is not on a persistent
+// filesystem, counts as outside the roots: it is not deleted. That does
+// not hold below a root at or inside that path, since that root's own
+// walk verifies the records below it; nor is a line printed for such a
+// root.
 func (s *scanState) walkPhase(events <-chan walkEvent, roots []string) {
 	// The records the last scan left under the roots estimate how many
 	// files the walk will find. A first scan has none, and no estimate.
@@ -552,7 +566,7 @@ func (s *scanState) walkPhase(events <-chan walkEvent, roots []string) {
 		prog.increment()
 
 		old, ok := s.existing[ev.rec.path]
-		if !ok || old.size != ev.rec.size || mtimeAfter(ev.rec.mtime, old.mtime) {
+		if !ok || old.size != ev.rec.size || !ev.rec.mtime.Equal(old.mtime) {
 			s.toHash = append(s.toHash, ev.rec)
 
 			continue
@@ -561,6 +575,13 @@ func (s *scanState) walkPhase(events <-chan walkEvent, roots []string) {
 		delete(s.existing, ev.rec.path)
 
 		s.st.unchanged++
+
+		// 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
+		// up to seconds after the write.
+		if old.diskSize != ev.rec.diskSize {
+			s.diskSizes = append(s.diskSizes, ev.rec)
+		}
 	}
 
 	prog.finish()
@@ -709,12 +730,13 @@ func (s *scanState) recordRun(ctx context.Context, r hashResult) error {
 		s.resolve(rec.path)
 
 		s.batch = append(s.batch, scanRec{
-			size:    rec.size,
-			mtime:   rec.mtime,
-			head:    r.head,
-			tail:    r.tail,
-			content: r.content,
-			path:    rec.path,
+			size:     rec.size,
+			diskSize: rec.diskSize,
+			mtime:    rec.mtime,
+			head:     r.head,
+			tail:     r.tail,
+			content:  r.content,
+			path:     rec.path,
 		})
 	}
 
@@ -730,7 +752,7 @@ func (s *scanState) commitFullBatch(ctx context.Context) error {
 		return nil
 	}
 
-	err := applyBatch(ctx, s.db, s.batch, nil, nil)
+	err := applyBatch(ctx, s.db, s.batch, nil, nil, nil)
 	if err != nil {
 		return err
 	}
@@ -741,9 +763,10 @@ func (s *scanState) commitFullBatch(ctx context.Context) error {
 }
 
 // updatePhase writes the scan's tail under one progress display: the
-// final partial batch of hashed records, and deletions for every record
-// the scan did not verify (vanished files, plus paths that failed to
-// stat or hash).
+// final partial batch of hashed records, the new disk_size of every
+// unchanged file whose disk_size changed, and deletions for every
+// record the scan did not verify (vanished files, plus paths that
+// failed to stat or hash).
 func (s *scanState) updatePhase(ctx context.Context) error {
 	deletes := make([]string, 0, len(s.existing))
 	for path := range s.existing {
@@ -755,7 +778,7 @@ func (s *scanState) updatePhase(ctx context.Context) error {
 
 	s.st.removed = len(deletes)
 
-	total := len(s.batch) + len(deletes)
+	total := len(s.batch) + len(s.diskSizes) + len(deletes)
 	prog := newProgress(progressParams{
 		label: scanPhase("update"), unit: scanUnit, total: int64(total),
 		stalledOn: "db",
@@ -770,17 +793,12 @@ func (s *scanState) updatePhase(ctx context.Context) error {
 
 	s.batch = nil
 
-	return applyChanges(ctx, s.db, nil, deletes, prog)
-}
-
-// mtimeAfter reports whether mtime a is later than mtime b.
-// Not a.After(b): time.Time wraps an mtime past year 292 billion; Unix() undoes it.
-func mtimeAfter(a, b time.Time) bool {
-	if a.Unix() != b.Unix() {
-		return a.Unix() > b.Unix()
+	err = applyDiskSizes(ctx, s.db, s.diskSizes, prog)
+	if err != nil {
+		return err
 	}
 
-	return a.Nanosecond() > b.Nanosecond()
+	return applyChanges(ctx, s.db, nil, deletes, prog)
 }
 
 // underAnyRoot reports whether path is any of the roots or lies under
@@ -837,9 +855,9 @@ type dirJob struct {
 // file's statted record, a warning when fail is set, or a path the walk
 // left out: when otherFSDir is set, a directory -x did not enter
 // because it is on another filesystem than its operand, and when
-// leftOut is set, a default exclude or a directory or file on a
-// filesystem that is not persistent, with warn holding the line that
-// says so.
+// leftOut is set, an --exclude path, a default exclude or a directory or
+// file on a filesystem that is not persistent, with warn holding the
+// line that says so.
 type walkEvent struct {
 	rec        fileRec
 	warn       string
@@ -889,16 +907,25 @@ 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. Symlinks are
-// never followed, including as operands.
+// does: a regular file, or a directory not named .zfs, that is not
+// inside a directory named .zfs. realPaths has already followed the
+// 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.
+	if slices.Contains(strings.Split(filepath.Dir(root), "/"), ".zfs") {
+		return fmt.Sprintf("walk %s: skipping operand inside a .zfs directory",
+			root)
+	}
+
 	var kind string
 
 	switch mode := fi.Mode(); {
 	case mode.IsRegular():
 		return ""
 	case mode.IsDir():
-		if filepath.Base(root) != zfsDirName {
+		if filepath.Base(root) != ".zfs" {
 			return ""
 		}
 
@@ -960,11 +987,12 @@ func seedRoot(ctx context.Context, root string, rules walkRules,
 
 	dev, ino := inodeOfInfo(fi)
 	rec := fileRec{
-		path:  root,
-		size:  fi.Size(),
-		mtime: fi.ModTime(),
-		dev:   dev,
-		ino:   ino,
+		path:     root,
+		size:     fi.Size(),
+		diskSize: diskSizeOfInfo(fi),
+		mtime:    fi.ModTime(),
+		dev:      dev,
+		ino:      ino,
 	}
 
 	if !isDatabaseFile(rec, rules) {
@@ -1111,8 +1139,9 @@ func walkOneDir(ctx context.Context, job dirJob, oneFS bool,
 // no longer exists, and one that has stopped being a regular file is
 // skipped. A file on a filesystem in rules that is not persistent, as
 // through a bind mount of one file, is not recorded: it gets an event
-// naming it instead. One of the scan's own database files in rules gets
-// no event at all.
+// naming it instead, and so does a file given with --exclude, reached
+// by any path, a hard link to it included. One of the scan's own
+// database files in rules gets no event at all.
 func emitFile(ctx context.Context, p string, e fs.DirEntry,
 	rules walkRules, events chan<- walkEvent,
 ) {
@@ -1136,6 +1165,10 @@ func emitFile(ctx context.Context, p string, e fs.DirEntry,
 	}
 
 	line := rules.nonPersistentLine(p, info)
+	if line == "" {
+		line = rules.excludePathLine(p, info)
+	}
+
 	if line != "" {
 		sendEvent(ctx, events, walkEvent{leftOut: p, warn: line})
 
@@ -1144,11 +1177,12 @@ func emitFile(ctx context.Context, p string, e fs.DirEntry,
 
 	dev, ino := inodeOfInfo(info)
 	rec := fileRec{
-		path:  p,
-		size:  info.Size(),
-		mtime: info.ModTime(),
-		dev:   dev,
-		ino:   ino,
+		path:     p,
+		size:     info.Size(),
+		diskSize: diskSizeOfInfo(info),
+		mtime:    info.ModTime(),
+		dev:      dev,
+		ino:      ino,
 	}
 
 	if !isDatabaseFile(rec, rules) {
@@ -1159,16 +1193,16 @@ func emitFile(ctx context.Context, p string, e fs.DirEntry,
 // subdirJob applies the descent rules to directory p: never enter
 // .zfs (ZFS snapshot pseudo-dirs would list every file once per
 // snapshot), never enter a directory on a filesystem in rules that is
-// not persistent, nor a default exclude in rules, and with -x never
-// enter a directory on a different filesystem than its operand. For the
-// last three it sends an event that names the directory, so the scan
-// keeps the records below it, except those below an operand at or
-// inside it.
+// not persistent, nor an --exclude path or a default exclude in rules,
+// and with -x never enter a directory on a different filesystem than
+// its operand. For all but .zfs it sends an event that names the
+// directory, so the scan keeps the records below it, except those below
+// an operand at or inside it.
 func subdirJob(ctx context.Context, p string, e fs.DirEntry,
 	parent dirJob, oneFS bool, rules walkRules,
 	events chan<- walkEvent,
 ) (dirJob, bool) {
-	if e.Name() == zfsDirName {
+	if e.Name() == ".zfs" {
 		return dirJob{}, false
 	}
 
@@ -1188,13 +1222,17 @@ func subdirJob(ctx context.Context, p string, e fs.DirEntry,
 	}
 
 	line := rules.nonPersistentLine(p, info)
+	if line == "" {
+		line = rules.excludePathLine(p, info)
+	}
+
 	if line != "" {
 		sendEvent(ctx, events, walkEvent{leftOut: p, warn: line})
 
 		return dirJob{}, false
 	}
 
-	if isDefaultExclude(p, rules.excludes) {
+	if isDefaultExclude(p, rules.defaultExcludes) {
 		sendEvent(ctx, events, walkEvent{
 			leftOut: p,
 			warn:    fmt.Sprintf("scan: skipped %s (default exclude)", p),
@@ -1240,6 +1278,23 @@ func inodeOfInfo(fi fs.FileInfo) (uint64, uint64) {
 	return statDev(st), st.Ino
 }
 
+// statBlockSize is the unit of st_blocks in an lstat result on Linux and
+// macOS, whatever the filesystem's own block size.
+const statBlockSize = 512
+
+// diskSizeOfInfo returns the bytes a file takes on disk: its allocated
+// blocks, st_blocks × 512. On a compressed or sparse file it is less
+// than the file's size. It is 0 when the platform exposes no block
+// count.
+func diskSizeOfInfo(fi fs.FileInfo) int64 {
+	st, ok := fi.Sys().(*syscall.Stat_t)
+	if !ok {
+		return 0
+	}
+
+	return st.Blocks * statBlockSize
+}
+
 // hashResult carries the hashes computed for one inode run (or the
 // error that prevented computing them) from the pool's workers to the
 // hash phase. Its run leaves out the paths found removed.

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"
@@ -42,6 +42,30 @@ func writeFile(t *testing.T, dir, name string, data []byte) string {
 	return p
 }
 
+// diskSizeOf returns the bytes the file at path takes on disk, from its
+// own lstat: st_blocks counts 512-byte units. ZFS counts a write's
+// blocks only when it commits the write, up to seconds later, and one
+// commit can take the file through several growing sizes. So this value
+// 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()
+
+	var st syscall.Stat_t
+
+	err := syscall.Lstat(path, &st)
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	return st.Blocks * 512
+}
+
 // pattern returns n bytes of deterministic content seeded by tag.
 func pattern(tag byte, n int) []byte {
 	data := make([]byte, n)
@@ -1064,12 +1088,13 @@ func TestScanOneFilesystemWalksNestedFileOperand(t *testing.T) {
 	}
 }
 
-// buildSmokeTree recreates the README smoke-test filesystem layout
-// with deterministic content and returns the tree root.
+// buildSmokeTree recreates the tree of the test under README
+// "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)
@@ -1160,11 +1185,12 @@ func assertSmokeDupeGroups(t *testing.T, dir string, db *sql.DB) {
 	t.Helper()
 
 	groups := dupeGroups(t, db)
-	if len(groups) != 5 {
-		t.Fatalf("len(groups) = %d, want 5", len(groups))
+	if len(groups) != 4 {
+		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",
@@ -1189,7 +1215,7 @@ func assertSmokeTreeGroups(t *testing.T, dir string, db *sql.DB) {
 
 	super, dirs := dbTree(t, db)
 
-	tg := collectTreeGroups(dirs, super, nil)
+	tg := collectTreeGroups(dirs, super, everyPathExists, nil)
 	if len(tg) != 1 {
 		t.Fatalf("len(tree groups) = %d, want 1", len(tg))
 	}
@@ -1228,9 +1254,9 @@ func TestScanPipeline(t *testing.T) {
 // TestScanProgressNamesEachPhase checks the plain progress lines of a
 // first scan, and of a rescan of one operand holding two of the
 // database's records. Each phase's first line names it with its place
-// among the four: load counts the records before reading them, and the
-// walk estimates its total from the records under its operand, or says
-// its time remaining is unknown when there are none.
+// among the four: load gets the number of records before reading them,
+// and the walk estimates its total from the records under its operand,
+// or says its time remaining is unknown when there are none.
 //
 //nolint:paralleltest // captureStderr replaces the process-wide os.Stderr
 func TestScanProgressNamesEachPhase(t *testing.T) {
@@ -1358,6 +1384,47 @@ func TestSyncScanMtimeBump(t *testing.T) {
 	}
 }
 
+// TestSyncScanMtimeMovedBack replaces a file with other content of the
+// same size and an older mtime, as cp -p or a restore from backup does.
+// The next scan must hash the file again.
+func TestSyncScanMtimeMovedBack(t *testing.T) {
+	t.Parallel()
+
+	dir := t.TempDir()
+	db := openTestDB(t)
+	a := writeFile(t, dir, "a.bin", pattern(1, 500))
+
+	recorded := time.Date(2026, 1, 2, 3, 4, 5, 0, time.UTC)
+
+	err := os.Chtimes(a, recorded, recorded)
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	syncTree(t, db, dir)
+
+	replaced := pattern(3, 500)
+	writeFile(t, dir, "a.bin", replaced)
+
+	older := recorded.Add(-time.Hour)
+
+	err = os.Chtimes(a, older, older)
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	st := syncTree(t, db, dir)
+	if st != (scanStats{walked: 1, updated: 1}) {
+		t.Fatalf("rescan stats = %+v, want 1 updated", st)
+	}
+
+	assertWholeFileHashed(t, db, a, replaced)
+
+	if r := recordByPath(t, dbRecords(t, db), a); !r.mtime.Equal(older) {
+		t.Fatalf("mtime = %v, want %v", r.mtime, older)
+	}
+}
+
 // assertWholeFileHashed fails unless the record for path holds the
 // whole-file hash of data as its head, tail, and content.
 func assertWholeFileHashed(t *testing.T, db *sql.DB, path string,
@@ -1416,6 +1483,159 @@ func TestScanStoresRawHashes(t *testing.T) {
 	}
 }
 
+// TestScanStoresDiskSize scans a sparse file, which takes less space on
+// disk than its length, once through its directory and once as the
+// operand itself. Each scan stores the disk_size of the file's lstat.
+func TestScanStoresDiskSize(t *testing.T) {
+	t.Parallel()
+
+	const length = 1024 * 1024
+
+	p := sparseFile(t, t.TempDir(), "sparse", length)
+	pokeAt(t, p, 0, []byte("x"))
+
+	unix.Sync() // see diskSizeOf
+
+	size := diskSizeOf(t, p)
+	if size == 0 || size >= length {
+		t.Fatalf("the file takes %d bytes on disk, want more than none "+
+			"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 < before || got > after {
+			t.Errorf("scan of %s: disk_size = %d, want %d to %d",
+				operand, got, before, after)
+		}
+	}
+}
+
+// TestSyncScanRewriteUpdatesDiskSize writes into the hole of a scanned
+// sparse file and moves its mtime on. The rescan hashes the file again
+// and rewrites its record with the new disk_size.
+func TestSyncScanRewriteUpdatesDiskSize(t *testing.T) {
+	t.Parallel()
+
+	dir := t.TempDir()
+	db := openTestDB(t)
+	p := sparseFile(t, dir, "sparse", 1024*1024)
+	pokeAt(t, p, 0, []byte("x"))
+
+	syncTree(t, db, dir)
+
+	recorded := recordByPath(t, dbRecords(t, db), p).diskSize
+
+	pokeAt(t, p, 512*1024, pattern(7, 64*1024))
+
+	// The write may leave the mtime the scan recorded; a later one makes
+	// the rescan read the file again.
+	later := time.Now().Add(time.Hour)
+
+	err := os.Chtimes(p, later, later)
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	// 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)
+		}
+
+		unix.Sync()
+	}
+
+	// ZFS may still be counting, so the size may change during a rescan.
+	// Only a rescan with the same size on both sides of it can be compared
+	// exactly. A rescan that keeps the old size still fails, because the
+	// wait made before differ from it.
+	for {
+		before := diskSizeOf(t, p)
+
+		st := syncTree(t, db, dir)
+
+		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)
+		}
+	}
+}
+
+// TestSyncScanUnchangedUpdatesDiskSize gives a file's record a
+// disk_size the file does not have, as when ZFS had not yet counted the
+// file's blocks at the last scan. The rescan writes the file's own
+// disk_size into the record without reading the file again.
+func TestSyncScanUnchangedUpdatesDiskSize(t *testing.T) {
+	t.Parallel()
+
+	dir := t.TempDir()
+	db := openTestDB(t)
+	p := writeFile(t, dir, "a.bin", pattern(1, 500))
+
+	syncTree(t, db, dir)
+
+	// lstat counts 512-byte units, so no file takes 1 byte on disk.
+	_, err := db.ExecContext(t.Context(),
+		"UPDATE files SET disk_size = 1 WHERE path = ?", []byte(p))
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	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 got < before || got > after {
+		t.Errorf("disk_size = %d, want %d to %d", got, before, after)
+	}
+}
+
 // TestSyncScanSameSecondRewrite rewrites a file in place at the same
 // size with an mtime later in the same second as the recorded one: the
 // next scan must notice the change and re-hash the file. The operand is
@@ -1672,81 +1892,6 @@ func TestSyncScanOverlappingRoots(t *testing.T) {
 	}
 }
 
-// TestScanWalksOperandInZFSDirectory checks that an operand inside a
-// directory named .zfs below another operand is walked on its own,
-// since the walk of the other operand does not enter .zfs. The file
-// under it is recorded, and a second scan keeps the record.
-func TestScanWalksOperandInZFSDirectory(t *testing.T) {
-	t.Parallel()
-
-	dir := t.TempDir()
-	db := openTestDB(t)
-	f := writeFile(t, dir, "pool/.zfs/snapshot/daily/f", pattern(1, 10))
-	daily := filepath.Dir(f)
-
-	syncTree(t, db, dir, daily)
-	recordByPath(t, dbRecords(t, db), f)
-
-	syncTree(t, db, dir, daily)
-	recordByPath(t, dbRecords(t, db), f)
-}
-
-// TestScanWalksOperandBehindSymlink checks that an operand reached
-// through a symlinked directory below another operand is walked on its
-// own, since the walk of the other operand does not follow the symlink.
-// The file under it is recorded, and a second scan keeps the record.
-func TestScanWalksOperandBehindSymlink(t *testing.T) {
-	t.Parallel()
-
-	dir := t.TempDir()
-	target := t.TempDir()
-	db := openTestDB(t)
-	writeFile(t, target, "sub/f", pattern(1, 10))
-
-	link := filepath.Join(dir, "link")
-
-	err := os.Symlink(target, link)
-	if err != nil {
-		t.Fatal(err)
-	}
-
-	sub := filepath.Join(link, "sub")
-	f := filepath.Join(sub, "f")
-
-	syncTree(t, db, dir, sub)
-	recordByPath(t, dbRecords(t, db), f)
-
-	syncTree(t, db, dir, sub)
-	recordByPath(t, dbRecords(t, db), f)
-}
-
-// TestScanDropsOperandReachedBehindSymlink checks that an operand under
-// another one is still dropped when both lie behind the same symlinked
-// directory: the walk of the other operand starts past the symlink and
-// reaches it, so the file under it is walked once.
-func TestScanDropsOperandReachedBehindSymlink(t *testing.T) {
-	t.Parallel()
-
-	dir := t.TempDir()
-	target := t.TempDir()
-	db := openTestDB(t)
-	writeFile(t, target, "sub/deeper/f", pattern(1, 10))
-
-	link := filepath.Join(dir, "link")
-
-	err := os.Symlink(target, link)
-	if err != nil {
-		t.Fatal(err)
-	}
-
-	sub := filepath.Join(link, "sub")
-
-	st := syncTree(t, db, sub, filepath.Join(sub, "deeper"))
-	if st != (scanStats{walked: 1, added: 1}) {
-		t.Fatalf("stats = %+v, want 1 walked and added", st)
-	}
-}
-
 // TestScanHashesUniqueSize checks that a file whose size no other file
 // shares is hashed like every other file.
 func TestScanHashesUniqueSize(t *testing.T) {
@@ -2144,7 +2289,7 @@ func TestPruneRoots(t *testing.T) {
 
 	// The walk of /p does not enter /p/q when it is a default exclude, so
 	// /p/q is kept, without -x too; /p/q/r lies under it and is dropped.
-	got = pruneRoots(nested, false, walkRules{excludes: []string{pqRoot}},
+	got = pruneRoots(nested, false, walkRules{defaultExcludes: []string{pqRoot}},
 		device)
 	if !slices.Equal(got, want) {
 		t.Fatalf("pruneRoots excluding %s = %q, want %q", pqRoot, got, want)
@@ -2160,35 +2305,88 @@ func TestPruneRoots(t *testing.T) {
 		t.Fatalf("pruneRoots with %s not persistent = %q, want %q",
 			pqRoot, got, want)
 	}
-
-	// Nor does it enter a directory named .zfs, so /p/.zfs/s is kept. The
-	// walk of /p/.zfs/s reaches /p/.zfs/s/t, which is dropped.
-	got = pruneRoots([]string{"/p", "/p/.zfs/s", "/p/.zfs/s/t"}, false,
-		walkRules{}, device)
-
-	want = []string{"/p", "/p/.zfs/s"}
-	if !slices.Equal(got, want) {
-		t.Fatalf("pruneRoots with .zfs = %q, want %q", got, want)
-	}
 }
 
-func TestReportsNeverTouchFilesystem(t *testing.T) {
-	t.Parallel()
+// TestRunReportsLeaveOutRemovedCopies scans the smoke tree, then
+// removes copies the reports name. report leaves out each removed file,
+// and a group left with one path. trees checks only the root of each
+// duplicate tree: with a file under t2 removed it still names t2, and
+// with t2 removed it names nothing.
+func TestRunReportsLeaveOutRemovedCopies(t *testing.T) {
+	t.Setenv(databaseEnv, testDBPath(t))
 
 	dir := buildSmokeTree(t)
-	db := openTestDB(t)
+	p := func(name string) string { return filepath.Join(dir, name) }
 
-	syncTree(t, db, dir)
+	scanOK(t, dir)
 
-	// Remove the scanned tree entirely; the analysis must be
-	// unaffected because it reads the database alone.
-	err := os.RemoveAll(dir)
+	for _, name := range []string{"b/copy2.bin", "tiny2", "t2/sub/f2"} {
+		err := os.Remove(p(name))
+		if err != nil {
+			t.Fatal(err)
+		}
+	}
+
+	want := "first\tdupe\tsize\n" +
+		p("t1/f1") + "\t" + p("t2/f1") + "\t3000\n" +
+		p("t1/f1") + "\t" + p("t3/f1") + "\t3000\n" +
+		p("a/one.bin") + "\t" + p("b/copy.bin") + "\t2000\n" +
+		p("t1/sub/f2") + "\t" + p("t3/sub/f2renamed") + "\t100\n"
+	if got := runStdout(t, cmdReport); got != want {
+		t.Errorf("report stdout = %q, want %q", got, want)
+	}
+
+	// disk_size, the last column, depends on the filesystem.
+	header := "first\tdupe\tfiles\tsize\tdisk_size\n"
+
+	want = header + p("t1") + "\t" + p("t2") + "\t2\t3100\t"
+	if got := runStdout(t, cmdTrees); !strings.HasPrefix(got, want) ||
+		strings.Count(got, "\n") != 2 {
+		t.Errorf("trees stdout = %q, want one row starting %q", got, want)
+	}
+
+	err := os.RemoveAll(p("t2"))
 	if err != nil {
 		t.Fatal(err)
 	}
 
-	assertSmokeDupeGroups(t, dir, db)
-	assertSmokeTreeGroups(t, dir, db)
+	if got := runStdout(t, cmdTrees); got != header {
+		t.Errorf("trees stdout after removing t2 = %q, want %q", got, header)
+	}
+}
+
+func TestPathExists(t *testing.T) {
+	t.Parallel()
+
+	dir := t.TempDir()
+	file := writeFile(t, dir, "file", nil)
+	locked := writeFile(t, dir, "locked/file", nil)
+
+	// Without search permission on its directory, a file cannot be
+	// looked at by anyone but root.
+	err := os.Chmod(filepath.Dir(locked), 0)
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	// Runs before t.TempDir's own cleanup, which must delete the files.
+	t.Cleanup(func() {
+		//nolint:gosec // removing the directory needs its search bit back
+		_ = os.Chmod(filepath.Dir(locked), 0o700)
+	})
+
+	cases := map[string]bool{
+		dir:                                 true,
+		file:                                true,
+		locked:                              true,
+		filepath.Join(dir, "gone"):          false,
+		filepath.Join(file, "under-a-file"): false,
+	}
+	for path, want := range cases {
+		if got := pathExists(path); got != want {
+			t.Errorf("pathExists(%q) = %v, want %v", path, got, want)
+		}
+	}
 }
 
 func TestUnderRoot(t *testing.T) {
@@ -2217,33 +2415,24 @@ func TestUnderRoot(t *testing.T) {
 }
 
 // TestRunScanPassesOverDatabase scans a tree that holds the scan's own
-// database, reached directly and through a symlinked directory. The
-// walk passes over the database file, its -wal and -shm files and its
-// .lock file with no line and no count, and the record an 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.
+// database, and in one case also a hard link to the database file. The
+// walk knows the database's files by device ID and inode number, so it
+// passes over the database file, its -wal and -shm files, its .lock
+// file and the hard link with no line and no count. The record an
+// 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} {
-		t.Run(fmt.Sprintf("via symlink %v", viaSymlink), func(t *testing.T) {
-			base := t.TempDir()
-			tree := filepath.Join(base, "real", "tree")
-			operand := tree
+	for _, viaHardLink := range []bool{false, true} {
+		t.Run(fmt.Sprintf("via hard link %v", viaHardLink), func(t *testing.T) {
+			tree := realTempDir(t)
+			hardLink := filepath.Join(tree, "hardlink")
 
 			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)
 
@@ -2253,7 +2442,7 @@ 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)
@@ -2261,17 +2450,30 @@ 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)
-			assertScanSummary(t,
+				tree)
+			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")) {
-				t.Errorf("report = %q, want the empty files and none of "+
+				strings.Contains(report, hardLink) ||
+				!strings.Contains(report, filepath.Join(tree, "b")) {
+				t.Errorf("report = %q, want a and b and none of "+
 					"the database's files", report)
 			}
 		})
@@ -2295,8 +2497,9 @@ 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.
-func assertScanSummary(t *testing.T, counts string, operands ...string) {
+// the database is the only one that names one of its files. It returns
+// everything the scan printed to stderr.
+func assertScanSummary(t *testing.T, counts string, operands ...string) string {
 	t.Helper()
 
 	stderr := scanOK(t, operands...)
@@ -2310,4 +2513,6 @@ 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"
@@ -22,6 +22,10 @@ type treeNode struct {
 	digest    [sha256.Size]byte
 	fileCount int64
 	totalSize int64
+	// diskSize is the bytes the directory's files take on disk. Two
+	// copies of one tree have the same totalSize, but their diskSize
+	// can differ.
+	diskSize int64
 }
 
 // treesPhase names one phase of trees with its place among all of them,
@@ -34,17 +38,18 @@ 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
-// 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.
+// prints maximal duplicate-tree groups as TSV on stdout. Of the scanned
+// filesystem it only checks, with pathExists, that the root of each
+// duplicate tree is still there, never the files below it. It names the
+// database on stderr before it opens it. Any database problem,
+// including a missing database, is fatal.
 //
 // The work runs in four phases, each under a progress display of its
-// own on stderr: open (open the database), read (count the records,
-// then read them into the 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.
+// own on stderr: open (open the database), read (read the number of
+// records from the totals table, then read the records into the
+// 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 {
 	dbPath, source, err := databasePath()
 	if err != nil {
@@ -82,13 +87,13 @@ func runTrees(ctx context.Context, stdout io.Writer) error {
 		return fmt.Errorf("database %s: %w", dbPath, err)
 	}
 
-	// Grouping works in memory, so it waits on nothing but the
-	// processor.
+	// Grouping works in memory, then checks the root of each duplicate
+	// tree on disk, so it waits on the processor or the disk.
 	prog = newProgress(progressParams{
 		label: treesPhase("group"), unit: "directories",
-		total: int64(len(allDirs)), stalledOn: "cpu",
+		total: int64(len(allDirs)), stalledOn: "cpu/disk",
 	})
-	dupes := collectTreeGroups(allDirs, super, prog)
+	dupes := collectTreeGroups(allDirs, super, pathExists, prog)
 
 	prog.finish()
 
@@ -139,15 +144,16 @@ func readTree(ctx context.Context, db *sql.DB,
 
 // writeTreeGroups writes dupes to stdout as TSV, a header line and then
 // a row for every member of each group but its first, counting each
-// group on prog once its rows are written. stdout may be the terminal
-// prog is drawn on, so the lines go through prog's writer. It returns
-// the number of rows (dupe trees) and the bytes they could reclaim.
+// group on prog once its rows are written. The disk_size column is the
+// dupe's own. stdout may be the terminal prog is drawn on, so the lines
+// go through prog's writer. It returns the number of rows (dupe trees)
+// and the bytes they could reclaim.
 func writeTreeGroups(stdout io.Writer, dupes [][]*treeNode,
 	prog *progress,
 ) (int, int64, error) {
 	out := prog.writer(stdout)
 
-	_, err := fmt.Fprintln(out, "first\tdupe\tfiles\tsize")
+	_, err := fmt.Fprintln(out, "first\tdupe\tfiles\tsize\tdisk_size")
 	if err != nil {
 		return 0, 0, fmt.Errorf("write stdout: %w", err)
 	}
@@ -159,9 +165,9 @@ func writeTreeGroups(stdout io.Writer, dupes [][]*treeNode,
 	for _, g := range dupes {
 		first := g[0]
 		for _, n := range g[1:] {
-			_, err = fmt.Fprintf(out, "%s\t%s\t%d\t%d\n",
+			_, err = fmt.Fprintf(out, "%s\t%s\t%d\t%d\t%d\n",
 				escapePath(first.path), escapePath(n.path),
-				first.fileCount, first.totalSize)
+				first.fileCount, first.totalSize, n.diskSize)
 			if err != nil {
 				return 0, 0, fmt.Errorf("write stdout: %w", err)
 			}
@@ -232,6 +238,7 @@ func (b *treeBuilder) add(r scanRec) {
 	dir.entries = append(dir.entries, fileEntry(name, r))
 	dir.fileCount++
 	dir.totalSize += r.size
+	dir.diskSize += r.diskSize
 }
 
 // openDir starts the directory called name inside the innermost open
@@ -270,6 +277,7 @@ func (b *treeBuilder) closeTo(n int) {
 			"d\x00"+name+"\x00"+string(dir.digest[:]))
 		dir.parent.fileCount += dir.fileCount
 		dir.parent.totalSize += dir.totalSize
+		dir.parent.diskSize += dir.diskSize
 		b.dirs = append(b.dirs, dir)
 	}
 }
@@ -293,10 +301,14 @@ 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.
+// more members for which exists returns true, each group's members
+// sorted by path, groups ordered by 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. exists is called only on the members
+// of maximal groups.
 func collectTreeGroups(allDirs []*treeNode, super *treeNode,
-	prog *progress,
+	exists func(path string) bool, prog *progress,
 ) [][]*treeNode {
 	groups := make(map[[sha256.Size]byte][]*treeNode)
 	for _, d := range allDirs {
@@ -308,7 +320,19 @@ 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
+		}
+
+		// A member that is gone leaves the group. A suppressed group is
+		// still implied: its members still on disk have parents still
+		// on disk, and those parents' group is checked the same way.
+		g = slices.DeleteFunc(g, func(n *treeNode) bool {
+			return !exists(n.path)
+		})
+		if len(g) < minGroupSize {
 			continue
 		}
 

internal/sfdupes/trees_test.go

@@ -1,10 +1,12 @@
-package main
+package sfdupes //nolint:testpackage // checks the unexported treeNode results
 
 import (
 	"bytes"
+	"crypto/sha256"
 	"database/sql"
 	"os"
 	"slices"
+	"strconv"
 	"strings"
 	"testing"
 	"time"
@@ -15,20 +17,26 @@ import (
 const treesOpenLine = "[1/4] open: opening the database, elapsed 0s, " +
 	"remain unknown"
 
-// smokeTreeRecs mirrors the README smoke-test tree layout: /d/t1 and
-// /d/t2 are identical, /d/t3 differs from them only by one filename.
+// smokeTreeRecs mirrors the tree of the test under README "Definition
+// of done": /d/t1 and /d/t2 are identical, /d/t3 differs from them only
+// 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")
 
 	return []scanRec{
-		{size: 3000, head: f1Head, tail: f1Tail, content: f1Content, path: "/d/t1/f1"},
-		{size: 100, head: f2Head, tail: f2Tail, content: f2Content, path: "/d/t1/sub/f2"},
-		{size: 3000, head: f1Head, tail: f1Tail, content: f1Content, path: "/d/t2/f1"},
-		{size: 100, head: f2Head, tail: f2Tail, content: f2Content, path: "/d/t2/sub/f2"},
-		{size: 3000, head: f1Head, tail: f1Tail, content: f1Content, path: "/d/t3/f1"},
-		{size: 100, head: f2Head, tail: f2Tail, content: f2Content,
-			path: "/d/t3/sub/f2renamed"},
+		{size: 3000, diskSize: 4096, head: f1Head, tail: f1Tail,
+			content: f1Content, path: "/d/t1/f1"},
+		{size: 100, diskSize: 4096, head: f2Head, tail: f2Tail,
+			content: f2Content, path: "/d/t1/sub/f2"},
+		{size: 3000, diskSize: 4096, head: f1Head, tail: f1Tail,
+			content: f1Content, path: "/d/t2/f1"},
+		{size: 100, diskSize: 4096, head: f2Head, tail: f2Tail,
+			content: f2Content, path: "/d/t2/sub/f2"},
+		{size: 3000, diskSize: 4096, head: f1Head, tail: f1Tail,
+			content: f1Content, path: "/d/t3/f1"},
+		{size: 100, diskSize: 4096, head: f2Head, tail: f2Tail,
+			content: f2Content, path: "/d/t3/sub/f2renamed"},
 	}
 }
 
@@ -172,7 +180,7 @@ func TestTreeNamesSortingBeforeSlash(t *testing.T) {
 		t.Fatalf("directory paths = %q, want %q", got, want)
 	}
 
-	groups := collectTreeGroups(dirs, super, nil)
+	groups := collectTreeGroups(dirs, super, everyPathExists, nil)
 
 	gotGroups := groupPaths(groups)
 	wantGroups := [][]string{{"/a", "/c"}}
@@ -188,7 +196,8 @@ func TestTreeNamesSortingBeforeSlash(t *testing.T) {
 }
 
 func TestRunTreesEscapesPaths(t *testing.T) {
-	t.Setenv(databaseEnv, seedDatabase(t, awkwardPairRecs()))
+	dir, recs := recsOnDisk(t, awkwardPairRecs())
+	t.Setenv(databaseEnv, seedDatabase(t, recs))
 
 	var stdout, stderr bytes.Buffer
 
@@ -198,22 +207,45 @@ func TestRunTreesEscapesPaths(t *testing.T) {
 			code, exitOK, stderr.String())
 	}
 
-	want := "first\tdupe\tfiles\tsize\n" +
-		`/d/\tone\ntwo\rthree\\four` + "\t/d/A\t1\t5\n"
+	want := "first\tdupe\tfiles\tsize\tdisk_size\n" +
+		dir + `/d/\tone\ntwo\rthree\\four` + "\t" + dir + "/d/A\t1\t5\t4096\n"
 	if got := stdout.String(); got != want {
 		t.Errorf("stdout = %q, want %q", got, 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.
+func TestRunTreesDiskSize(t *testing.T) {
+	f, g := testHash("f"), testHash("g")
+	recs := []scanRec{
+		{size: 10, diskSize: 4096, head: f, tail: f, content: f, path: "/a/f"},
+		{size: 20, diskSize: 4096, head: g, tail: g, content: g, path: "/a/sub/g"},
+		{size: 10, diskSize: 512, head: f, tail: f, content: f, path: "/b/f"},
+		{size: 20, diskSize: 1024, head: g, tail: g, content: g, path: "/b/sub/g"},
+	}
+
+	dir, recs := recsOnDisk(t, recs)
+	t.Setenv(databaseEnv, seedDatabase(t, recs))
+
+	want := "first\tdupe\tfiles\tsize\tdisk_size\n" +
+		dir + "/a\t" + dir + "/b\t2\t30\t1536\n"
+	if got := runStdout(t, cmdTrees); got != want {
+		t.Errorf("stdout = %q, want %q", got, want)
+	}
+}
+
 // TestRunTreesProgressNamesEachPhase runs trees on the smoke-test
 // records with stderr not a terminal, and checks every line it prints
 // there. After the line naming the database, each phase prints a line
 // naming it with its place among the four as it starts and another as
 // it ends. read counts the 6 records before it reads them, group counts
-// the 8 directories, and write the 1 group. The summary comes last, and
+// the directories, and write the 1 group. The summary comes last, and
 // stdout holds the report alone.
 func TestRunTreesProgressNamesEachPhase(t *testing.T) {
-	path := seedDatabase(t, smokeTreeRecs())
+	dir, recs := recsOnDisk(t, smokeTreeRecs())
+	path := seedDatabase(t, recs)
 	t.Setenv(databaseEnv, path)
 
 	stderr := captureStderr(t)
@@ -226,11 +258,16 @@ func TestRunTreesProgressNamesEachPhase(t *testing.T) {
 			code, exitOK, stderr())
 	}
 
-	report := "first\tdupe\tfiles\tsize\n/d/t1\t/d/t2\t2\t3100\n"
+	report := "first\tdupe\tfiles\tsize\tdisk_size\n" +
+		dir + "/d/t1\t" + dir + "/d/t2\t2\t3100\t8192\n"
 	if got := stdout.String(); got != report {
 		t.Errorf("stdout = %q, want %q", got, report)
 	}
 
+	// The smoke-test records name 8 directories, / included. Moved under
+	// dir, they name one more for each slash in dir.
+	dirs := strconv.Itoa(8 + strings.Count(dir, "/"))
+
 	// How each line starts; the rate at the end of a phase varies.
 	want := []string{
 		"trees: database " + path + " (from " + databaseEnv + ")",
@@ -238,8 +275,9 @@ func TestRunTreesProgressNamesEachPhase(t *testing.T) {
 		treesOpenLine,
 		"[2/4] read: counting the records, elapsed 0s, remain unknown",
 		"[2/4] read: [6/6] 100%, ",
-		"[3/4] group: [0/8] 0%, 0 directories/s, elapsed 0s, remain unknown",
-		"[3/4] group: [8/8] 100%, ",
+		"[3/4] group: [0/" + dirs + "] 0%, 0 directories/s, elapsed 0s, " +
+			"remain unknown",
+		"[3/4] group: [" + dirs + "/" + dirs + "] 100%, ",
 		"[4/4] write: [0/1] 0%, 0 groups/s, elapsed 0s, remain unknown",
 		"[4/4] write: [1/1] 100%, ",
 		"trees: 6 records read, 1 duplicate tree groups, 1 dupe trees, ",
@@ -268,7 +306,7 @@ func TestRunTreesProgressNamesEachPhase(t *testing.T) {
 func TestWriteTreeGroupsOnTerminal(t *testing.T) {
 	stderr := captureStderr(t)
 	super, dirs := treeOf(t, smokeTreeRecs())
-	dupes := collectTreeGroups(dirs, super, nil)
+	dupes := collectTreeGroups(dirs, super, everyPathExists, nil)
 
 	// No timed draws: the display is drawn as it starts and as it ends.
 	p := startProgress(progressParams{
@@ -291,7 +329,9 @@ func TestWriteTreeGroupsOnTerminal(t *testing.T) {
 		shown = append(shown, line[strings.LastIndex(line, "\r")+1:])
 	}
 
-	want := []string{"first\tdupe\tfiles\tsize", "/d/t1\t/d/t2\t2\t3100"}
+	want := []string{
+		"first\tdupe\tfiles\tsize\tdisk_size", "/d/t1\t/d/t2\t2\t3100\t8192",
+	}
 	if len(shown) < len(want) || !slices.Equal(shown[:len(want)], want) {
 		t.Errorf("terminal shows lines %q, want %q first", shown, want)
 	}
@@ -347,7 +387,7 @@ func TestCollectTreeGroupsMaximal(t *testing.T) {
 
 	super, dirs := treeOf(t, smokeTreeRecs())
 
-	groups := collectTreeGroups(dirs, super, nil)
+	groups := collectTreeGroups(dirs, super, everyPathExists, nil)
 
 	want := [][]string{{"/d/t1", "/d/t2"}}
 	if got := groupPaths(groups); !slices.EqualFunc(got, want,
@@ -371,14 +411,16 @@ func TestCollectTreeGroupsDeterministic(t *testing.T) {
 
 	super, dirs := treeOf(t, recs)
 
-	forward := groupPaths(collectTreeGroups(dirs, super, nil))
+	forward := groupPaths(collectTreeGroups(dirs, super, everyPathExists,
+		nil))
 
 	reversed := slices.Clone(recs)
 	slices.Reverse(reversed)
 
 	superR, dirsR := treeOf(t, reversed)
 
-	backward := groupPaths(collectTreeGroups(dirsR, superR, nil))
+	backward := groupPaths(collectTreeGroups(dirsR, superR, everyPathExists,
+		nil))
 	if !slices.EqualFunc(forward, backward, slices.Equal) {
 		t.Fatalf("output depends on record order: %v vs %v",
 			forward, backward)
@@ -398,7 +440,36 @@ func TestCollectTreeGroupsSiblings(t *testing.T) {
 
 	super, dirs := treeOf(t, recs)
 
-	got := groupPaths(collectTreeGroups(dirs, super, nil))
+	got := groupPaths(collectTreeGroups(dirs, super, everyPathExists, nil))
+
+	want := [][]string{{"/p/x1", "/p/x2"}}
+	if !slices.EqualFunc(got, want, slices.Equal) {
+		t.Fatalf("groups = %v, want %v", got, want)
+	}
+}
+
+// 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, everyPathExists, nil))
 
 	want := [][]string{{"/p/x1", "/p/x2"}}
 	if !slices.EqualFunc(got, want, slices.Equal) {
@@ -421,10 +492,98 @@ func TestCollectTreeGroupsDifferingParents(t *testing.T) {
 
 	super, dirs := treeOf(t, recs)
 
-	got := groupPaths(collectTreeGroups(dirs, super, nil))
+	got := groupPaths(collectTreeGroups(dirs, super, everyPathExists, nil))
 
 	want := [][]string{{"/p/a/x", "/q/b/x"}}
 	if !slices.EqualFunc(got, want, slices.Equal) {
 		t.Fatalf("groups = %v, want %v", got, want)
 	}
 }
+
+// TestCollectTreeGroupsChecksOnlyReportedCopies checks that trees asks
+// whether a directory is on disk only for the members of the groups it
+// returns. It never asks about /a/proj/sub, which lies inside a copy
+// and whose group the group of /a/proj implies.
+func TestCollectTreeGroupsChecksOnlyReportedCopies(t *testing.T) {
+	t.Parallel()
+
+	f, g, u := testHash("f"), testHash("g"), testHash("u")
+	recs := []scanRec{
+		{size: 10, head: f, tail: f, content: f, path: "/a/proj/f"},
+		{size: 20, head: g, tail: g, content: g, path: "/a/proj/sub/g"},
+		{size: 10, head: f, tail: f, content: f, path: "/b/proj/f"},
+		{size: 20, head: g, tail: g, content: g, path: "/b/proj/sub/g"},
+		// /a lacks this file, so /a and /b are no copies of each other.
+		{size: 30, head: u, tail: u, content: u, path: "/b/lonely"},
+	}
+
+	super, dirs := treeOf(t, recs)
+
+	var checked []string
+
+	exists := func(path string) bool {
+		checked = append(checked, path)
+
+		return true
+	}
+
+	got := groupPaths(collectTreeGroups(dirs, super, exists, nil))
+
+	want := [][]string{{"/a/proj", "/b/proj"}}
+	if !slices.EqualFunc(got, want, slices.Equal) {
+		t.Fatalf("groups = %v, want %v", got, want)
+	}
+
+	slices.Sort(checked)
+
+	if !slices.Equal(checked, want[0]) {
+		t.Errorf("directories checked on disk = %q, want %q",
+			checked, want[0])
+	}
+}
+
+// TestCollectTreeGroupsDropsGroupLeftWithOneCopy checks that a group of
+// two copies, one of them gone, is not returned. If kept, it would
+// write no row, but the summary line would count it.
+func TestCollectTreeGroupsDropsGroupLeftWithOneCopy(t *testing.T) {
+	t.Parallel()
+
+	f := testHash("f")
+	recs := []scanRec{
+		{size: 10, head: f, tail: f, content: f, path: "/c/kept/f"},
+		{size: 10, head: f, tail: f, content: f, path: "/c/gone/f"},
+	}
+
+	super, dirs := treeOf(t, recs)
+
+	exists := func(path string) bool { return path != "/c/gone" }
+
+	got := groupPaths(collectTreeGroups(dirs, super, exists, nil))
+	if len(got) != 0 {
+		t.Errorf("groups = %v, want none", got)
+	}
+}
+
+// TestCollectTreeGroupsKeepsGroupLeftWithTwoCopies checks that a group
+// of three copies, one of them gone, is returned with the other two.
+func TestCollectTreeGroupsKeepsGroupLeftWithTwoCopies(t *testing.T) {
+	t.Parallel()
+
+	f := testHash("f")
+	recs := []scanRec{
+		{size: 10, head: f, tail: f, content: f, path: "/d/kept1/f"},
+		{size: 10, head: f, tail: f, content: f, path: "/d/gone/f"},
+		{size: 10, head: f, tail: f, content: f, path: "/d/kept2/f"},
+	}
+
+	super, dirs := treeOf(t, recs)
+
+	exists := func(path string) bool { return path != "/d/gone" }
+
+	got := groupPaths(collectTreeGroups(dirs, super, exists, nil))
+
+	want := [][]string{{"/d/kept1", "/d/kept2"}}
+	if !slices.EqualFunc(got, want, slices.Equal) {
+		t.Errorf("groups = %v, want %v", got, want)
+	}
+}