Leave removed copies out of report and trees (closes #173) (#184)

internal/sfdupes/progress_test.go

@@ -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

@@ -4,11 +4,14 @@ import (
 	"context"
 	"crypto/sha256"
 	"database/sql"
+	"errors"
 	"fmt"
 	"io"
+	"io/fs"
 	"os"
 	"slices"
 	"strings"
+	"syscall"
 	"time"
 )
 
@@ -41,10 +44,10 @@ 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 (read the number of
@@ -77,13 +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()
 
@@ -104,14 +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 {
@@ -158,6 +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
@@ -194,10 +203,18 @@ 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. Empty
-// files form no group, since removing one frees nothing.
+// 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 && 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]
@@ -246,6 +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

@@ -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)
 
@@ -455,6 +483,119 @@ func TestDupeGroupsLeavesOutEmptyFiles(t *testing.T) {
 	}
 }
 
+// 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_test.go

@@ -1215,7 +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))
 	}
@@ -2307,23 +2307,86 @@ func TestPruneRoots(t *testing.T) {
 	}
 }
 
-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) {

internal/sfdupes/trees.go

@@ -38,10 +38,11 @@ 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 (read the number of
@@ -86,13 +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()
 
@@ -300,12 +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. 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.
+// 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 {
@@ -323,6 +326,16 @@ func collectTreeGroups(allDirs []*treeNode, super *treeNode,
 			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
+		}
+
 		slices.SortFunc(g, func(a, b *treeNode) int {
 			return strings.Compare(a.path, b.path)
 		})

internal/sfdupes/trees_test.go

@@ -6,6 +6,7 @@ import (
 	"database/sql"
 	"os"
 	"slices"
+	"strconv"
 	"strings"
 	"testing"
 	"time"
@@ -179,7 +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"}}
@@ -195,7 +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
 
@@ -206,7 +208,7 @@ func TestRunTreesEscapesPaths(t *testing.T) {
 	}
 
 	want := "first\tdupe\tfiles\tsize\tdisk_size\n" +
-		`/d/\tone\ntwo\rthree\\four` + "\t/d/A\t1\t5\t4096\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)
 	}
@@ -224,9 +226,11 @@ func TestRunTreesDiskSize(t *testing.T) {
 		{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/a\t/b\t2\t30\t1536\n"
+	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)
 	}
@@ -237,10 +241,11 @@ func TestRunTreesDiskSize(t *testing.T) {
 // 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)
@@ -254,11 +259,15 @@ func TestRunTreesProgressNamesEachPhase(t *testing.T) {
 	}
 
 	report := "first\tdupe\tfiles\tsize\tdisk_size\n" +
-		"/d/t1\t/d/t2\t2\t3100\t8192\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 + ")",
@@ -266,8 +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, ",
@@ -296,7 +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{
@@ -377,7 +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,
@@ -401,14 +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)
@@ -428,7 +440,7 @@ 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) {
@@ -457,7 +469,7 @@ func TestCollectTreeGroupsLeavesOutEmptyTrees(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) {
@@ -480,10 +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)
+	}
+}