Walk an operand nested on another filesystem with -x (closes #106)

With -x, an operand under another operand is kept when it is a
directory on a different filesystem than the deepest kept operand
above it, or a regular file in such a directory, because that
operand's walk then does not reach it; it is walked on its own. A
regular file is judged by its directory, since the walk checks
devices only on directories. Below a kept operand, the rule that keeps
the records under a directory -x did not enter applies only to
directories its own walk did not enter, so the records of files gone
from it are deleted.

The new tests stub the devices and share their scan steps with the
test for #99, whose comment no
longer claims it runs every phase. The startWalk comment is rewrapped.

Model: opus-5-5

README.md

@@ -398,7 +398,10 @@ results do not depend on the working directory. All operands belong to a single
 scan and are enumerated concurrently: every operand seeds the shared walk worker
 pool. Overlapping operands are harmless — an operand that duplicates another or
 lies under another is dropped before walking, so every file is reached exactly
-once and produces one database record.
+once and produces one database record. With `-x`, though, an operand under
+another one is kept and walked on its own when it is a directory on a different
+filesystem than the operand covering it, or a regular file in such a directory,
+because the walk of the covering operand does not reach it.
 
 An operand that is a symlink (never followed, not even as an operand), socket,
 FIFO, or device node, or a directory named `.zfs`, is not scanned. `scan` prints
@@ -451,7 +454,8 @@ operands:
   directory is on another filesystem than its operand counts as outside the
   scanned operands: it is not deleted, and its size joins the size census. A
   filesystem mounted under an operand can therefore be scanned on its own
-  schedule into the same database.
+  schedule into the same database. Records below an operand at or inside such a
+  directory are not kept this way, since that operand's own walk verifies them.
 
 `scan` runs **four sequential phases over the whole scan**. Parallelism lives
 inside each phase; batched database writes begin during the hash phase:

TODO.md

@@ -29,6 +29,12 @@
 
 # Completed Steps
 
+- with `-x`, an operand under another operand is walked on its own instead of
+  being dropped when it is a directory on a different filesystem than that
+  operand, or a regular file in such a directory, and the records of files gone
+  from below it are deleted (2026-10-14,
+  https://git.eeqj.de/sneak/sfdupes/issues/106)
+
 - with `-x`, `scan` keeps the records below a directory on another filesystem
   under its operand, and counts their sizes in the size census, instead of
   deleting them (2026-10-14, https://git.eeqj.de/sneak/sfdupes/issues/99)

scan.go

@@ -203,10 +203,16 @@ func resolveRoots(roots []string) ([]string, error) {
 }
 
 // pruneRoots drops operands already covered by another operand:
-// duplicates and any operand lying under another one. Every remaining
-// file is then reachable through exactly one root, so walked paths are
-// unique without keeping a scan-wide set of every path seen.
-func pruneRoots(roots []string) []string {
+// duplicates and any operand lying under another one. With -x, an
+// operand under another one is kept when device puts it, or for a
+// regular file its directory, on a different filesystem than the
+// deepest kept operand above it, because that operand's walk then does
+// not reach it. Every remaining file is then reachable through exactly
+// one root, so walked paths are unique without keeping a scan-wide set
+// of every path seen.
+func pruneRoots(roots []string, oneFS bool,
+	device func(path string) (uint64, bool),
+) []string {
 	// Shorter-first ordering guarantees an ancestor is kept before any
 	// operand under it is considered.
 	sorted := slices.Clone(roots)
@@ -221,7 +227,31 @@ func pruneRoots(roots []string) []string {
 	kept := make([]string, 0, len(sorted))
 
 	for _, r := range sorted {
-		if !underAnyRoot(r, kept) {
+		above := deepestRoot(r, kept)
+		if above == "" {
+			kept = append(kept, r)
+
+			continue
+		}
+
+		// Without -x, and always for a duplicate, r is dropped.
+		if !oneFS || above == r {
+			continue
+		}
+
+		// The walk of above enters a directory only when it is on
+		// above's filesystem, and then reaches every regular file in it
+		// whatever device the file reports, so for a regular-file
+		// operand its directory decides.
+		dir := r
+		if fi, err := os.Lstat(r); err == nil && fi.Mode().IsRegular() {
+			dir = filepath.Dir(r)
+		}
+
+		dev, ok := device(dir)
+		aboveDev, aboveOK := device(above)
+
+		if ok && aboveOK && dev != aboveDev {
 			kept = append(kept, r)
 		}
 	}
@@ -229,6 +259,17 @@ func pruneRoots(roots []string) []string {
 	return kept
 }
 
+// deviceOfPath returns the filesystem device ID of the file at path,
+// when lstat succeeds and the platform exposes one.
+func deviceOfPath(path string) (uint64, bool) {
+	fi, err := os.Lstat(path)
+	if err != nil {
+		return 0, false
+	}
+
+	return deviceOfInfo(fi)
+}
+
 // scanStats summarizes one scan's database synchronization for the
 // final stderr summary, or for the line an interrupted scan prints.
 type scanStats struct {
@@ -295,14 +336,15 @@ func (s *scanState) runPhases(ctx context.Context, roots []string,
 ) error {
 	// Types are checked before pruning so that an operand under a
 	// dropped one is still scanned, not dropped as lying under it.
-	roots = pruneRoots(s.walkableRoots(roots))
+	roots = pruneRoots(s.walkableRoots(roots), oneFS, deviceOfPath)
 
 	err := s.loadIndex(ctx, roots)
 	if err != nil {
 		return err
 	}
 
-	changed, unhashed := s.walkPhase(startWalk(ctx, roots, oneFS, workers))
+	changed, unhashed := s.walkPhase(
+		startWalk(ctx, roots, oneFS, workers), roots)
 
 	// A cancelled walk stops early, so its size census covers only part
 	// of the roots, and every file it never reached would look vanished
@@ -393,9 +435,10 @@ func (s *scanState) loadIndex(ctx context.Context, roots []string) error {
 // hashes; both remain candidates until the census decides whether
 // their sizes are shared. A record below a directory -x did not enter
 // counts as outside the roots: it is not deleted, and its size joins
-// the census.
+// the census. That does not hold below a root at or inside that
+// directory, since that root's own walk verifies the records below it.
 func (s *scanState) walkPhase(
-	events <-chan walkEvent,
+	events <-chan walkEvent, roots []string,
 ) ([]fileRec, []fileRec) {
 	prog := newProgress("walk", -1)
 
@@ -441,7 +484,12 @@ func (s *scanState) walkPhase(
 	prog.finish()
 
 	for path, old := range s.existing {
-		if underAnyRoot(path, otherFSDirs) {
+		// Kept only when a directory -x did not enter lies below the
+		// deepest root above the record. A root at or below that
+		// directory was walked on its own and did not find the file.
+		// Both contain the record, so the longer path is the deeper.
+		otherFSDir := deepestRoot(path, otherFSDirs)
+		if len(otherFSDir) > len(deepestRoot(path, roots)) {
 			delete(s.existing, path)
 
 			s.sizes = append(s.sizes, old.size)
@@ -875,6 +923,20 @@ func underRoot(path, root string) bool {
 	return strings.HasPrefix(path, prefix)
 }
 
+// deepestRoot returns the longest of the roots that path is or lies
+// under, or "" when it lies under none.
+func deepestRoot(path string, roots []string) string {
+	deepest := ""
+
+	for _, root := range roots {
+		if underRoot(path, root) && len(root) > len(deepest) {
+			deepest = root
+		}
+	}
+
+	return deepest
+}
+
 // dirJob is one directory awaiting traversal by the walk workers. It
 // carries its operand's filesystem device so -x can stop at
 // filesystem boundaries.
@@ -898,10 +960,10 @@ type walkEvent struct {
 // startWalk seeds every root into the shared walk worker pool and
 // returns the event stream: one record per regular file, one warning
 // event per per-path error, and one event per directory -x did not
-// enter. The channel is closed when the walk
-// completes, and also when ctx is cancelled — every goroutine in the
-// pool abandons its blocking send in that case, so the consumer sees a
-// truncated but properly terminated stream instead of a stalled one.
+// enter. The channel is closed when the walk completes, and also when
+// ctx is cancelled — every goroutine in the pool abandons its blocking
+// send in that case, so the consumer sees a truncated but properly
+// terminated stream instead of a stalled one.
 func startWalk(ctx context.Context, roots []string, oneFS bool,
 	workers int,
 ) <-chan walkEvent {

scan_test.go

@@ -1135,14 +1135,71 @@ func TestSubdirJobStatError(t *testing.T) {
 	}
 }
 
+// syncOneFilesystem scans roots into db with -x and returns the scan
+// stats, taking the device of each operand, and of a regular-file
+// operand's directory, from devices instead of from lstat, so a test
+// can put an operand on a filesystem that no directory here is on. It
+// runs the steps of runPhases except the content phase.
+func syncOneFilesystem(t *testing.T, db *sql.DB, roots []string,
+	devices map[string]uint64,
+) scanStats {
+	t.Helper()
+
+	device := func(path string) (uint64, bool) {
+		dev, ok := devices[path]
+
+		return dev, ok
+	}
+
+	roots = pruneRoots(roots, true, device)
+
+	ctx := t.Context()
+	s := &scanState{db: db}
+
+	err := s.loadIndex(ctx, roots)
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	jobs, subdirs, events := startWalkWorkers(ctx, 2, true)
+
+	// seedRoot emits a regular-file operand itself and returns a job
+	// only for a directory operand.
+	var initial []dirJob
+
+	for _, root := range roots {
+		for _, job := range seedRoot(ctx, root, events) {
+			job.rootDev = devices[root]
+			initial = append(initial, job)
+		}
+	}
+
+	dispatchDirs(ctx, initial, jobs, subdirs)
+
+	changed, unhashed := s.walkPhase(events, roots)
+	s.partition(changed, unhashed)
+
+	err = s.hashPhase(ctx, 2)
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	err = s.updatePhase(ctx)
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	return s.st
+}
+
 // TestScanOneFilesystemKeepsOtherFilesystemRecords checks that with -x a
 // record below a directory the walk does not enter, because it is on
 // another filesystem than its operand, counts as outside the operands:
 // it is not deleted, and its size joins the size census. The record of
 // a gone file that is not below that directory is still deleted, even
-// when its path begins with the directory's name. The walk starts from
-// an operand device that no directory here is on, so no second real
-// filesystem is needed; the phases after it run as runPhases runs them.
+// when its path begins with the directory's name. The operand is given
+// a device that no directory here is on, so no second real filesystem
+// is needed.
 func TestScanOneFilesystemKeepsOtherFilesystemRecords(t *testing.T) {
 	t.Parallel()
 
@@ -1174,30 +1231,7 @@ func TestScanOneFilesystemKeepsOtherFilesystemRecords(t *testing.T) {
 		t.Skip("platform exposes no device id")
 	}
 
-	ctx := t.Context()
-	s := &scanState{db: db}
-
-	err = s.loadIndex(ctx, []string{dir})
-	if err != nil {
-		t.Fatal(err)
-	}
-
-	jobs, subdirs, events := startWalkWorkers(ctx, 2, true)
-	root := dirJob{path: dir, rootDev: dev + 1, rootDevOK: true}
-	dispatchDirs(ctx, []dirJob{root}, jobs, subdirs)
-
-	changed, unhashed := s.walkPhase(events)
-	s.partition(changed, unhashed)
-
-	err = s.hashPhase(ctx, 2)
-	if err != nil {
-		t.Fatal(err)
-	}
-
-	err = s.updatePhase(ctx)
-	if err != nil {
-		t.Fatal(err)
-	}
+	syncOneFilesystem(t, db, []string{dir}, map[string]uint64{dir: dev + 1})
 
 	recs := dbRecords(t, db)
 	recordByPath(t, recs, mounted)
@@ -1213,6 +1247,93 @@ func TestScanOneFilesystemKeepsOtherFilesystemRecords(t *testing.T) {
 	}
 }
 
+// TestScanOneFilesystemWalksNestedOperand checks that with -x an
+// operand under another one, on a different filesystem than it, is
+// walked on its own: a file added below it is recorded, and the record
+// of a file gone from below it is deleted. A record below a directory
+// that its own walk does not enter is still kept. Each operand is given
+// a device that no directory here is on, so neither walk enters a
+// subdirectory.
+func TestScanOneFilesystemWalksNestedOperand(t *testing.T) {
+	t.Parallel()
+
+	dir := t.TempDir()
+	db := openTestDB(t)
+
+	// A scan without -x records both files below mnt.
+	gone := writeFile(t, dir, "mnt/gone", pattern(1, 10))
+	kept := writeFile(t, dir, "mnt/sub/kept", pattern(2, 20))
+	syncTree(t, db, dir)
+
+	err := os.Remove(gone)
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	added := writeFile(t, dir, "mnt/added", pattern(3, 30))
+
+	info, err := os.Lstat(dir)
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	dev, ok := deviceOfInfo(info)
+	if !ok {
+		t.Skip("platform exposes no device id")
+	}
+
+	mnt := filepath.Join(dir, "mnt")
+	syncOneFilesystem(t, db, []string{dir, mnt},
+		map[string]uint64{dir: dev + 1, mnt: dev + 2})
+
+	paths := recordPaths(dbRecords(t, db))
+
+	if !slices.Contains(paths, added) {
+		t.Errorf("no record for %s: the walk did not reach %s", added, mnt)
+	}
+
+	if slices.Contains(paths, gone) {
+		t.Errorf("record for %s kept: the file is gone", gone)
+	}
+
+	if !slices.Contains(paths, kept) {
+		t.Errorf("record for %s deleted: the walk of %s did not enter %s",
+			kept, mnt, filepath.Dir(kept))
+	}
+}
+
+// TestScanOneFilesystemRecordsNestedFileOnce checks that with -x a
+// regular-file operand under another operand is dropped when the file
+// reports a different device than that operand but its directory does
+// not, as a file bind-mounted into the tree does: the walk of the other
+// operand enters the directory and reaches the file, so the file is
+// recorded once.
+func TestScanOneFilesystemRecordsNestedFileOnce(t *testing.T) {
+	t.Parallel()
+
+	dir := t.TempDir()
+	db := openTestDB(t)
+	file := writeFile(t, dir, "sub/f", pattern(1, 10))
+
+	info, err := os.Lstat(dir)
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	dev, ok := deviceOfInfo(info)
+	if !ok {
+		t.Skip("platform exposes no device id")
+	}
+
+	st := syncOneFilesystem(t, db, []string{dir, file}, map[string]uint64{
+		dir: dev, filepath.Dir(file): dev, file: dev + 1,
+	})
+
+	if st.added != 1 {
+		t.Errorf("%s recorded %d times, want once", file, st.added)
+	}
+}
+
 // buildSmokeTree recreates the README smoke-test filesystem layout
 // with deterministic content and returns the tree root.
 func buildSmokeTree(t *testing.T) string {
@@ -2123,14 +2244,43 @@ func TestHashRuns(t *testing.T) {
 func TestPruneRoots(t *testing.T) {
 	t.Parallel()
 
+	const pqRoot = "/p/q"
+
+	// /p/q is on another filesystem than /p; /p/q/r is on the same one as
+	// /p/q, /p/s as /p, and /p/t has no known device.
+	devices := map[string]uint64{"/p": 1, pqRoot: 2, "/p/q/r": 2, "/p/s": 1}
+	device := func(path string) (uint64, bool) {
+		dev, ok := devices[path]
+
+		return dev, ok
+	}
+
 	// Duplicates and operands under other operands are dropped; /cc is
 	// not under /c (sibling with a shared prefix).
-	got := pruneRoots([]string{"/a/b", "/a", "/c", "/a", "/a/b/c", "/cc"})
+	got := pruneRoots([]string{"/a/b", "/a", "/c", "/a", "/a/b/c", "/cc"},
+		false, device)
 
 	want := []string{"/a", "/c", "/cc"}
 	if !slices.Equal(got, want) {
 		t.Fatalf("pruneRoots = %q, want %q", got, want)
 	}
+
+	nested := []string{"/p/q/r", pqRoot, "/p", "/p", "/p/s", "/p/t"}
+
+	got = pruneRoots(nested, false, device)
+
+	want = []string{"/p"}
+	if !slices.Equal(got, want) {
+		t.Fatalf("pruneRoots without -x = %q, want %q", got, want)
+	}
+
+	// With -x, /p/q, on another filesystem than /p, is kept as well.
+	got = pruneRoots(nested, true, device)
+
+	want = []string{"/p", pqRoot}
+	if !slices.Equal(got, want) {
+		t.Fatalf("pruneRoots with -x = %q, want %q", got, want)
+	}
 }
 
 func TestReportsNeverTouchFilesystem(t *testing.T) {