scan: skip OS default excludes, and record nothing on filesystems that are not persistent (closes #124)

scan never records or reads anything on a filesystem that is not
persistent (tmpfs, proc, sysfs and the like), however it reaches it; no
flag turns this off. It notes each such filesystem's device ID as it
starts: on Linux from /proc/self/mountinfo, on macOS by lstat of each
listed mount point. Below an operand the walk also skips the default
excludes, a path list per system (Linux, macOS, and Windows, not used
yet); --no-default-excludes turns off only those. A default exclude that
is itself an operand gets no skip line. The tests stop at once, saying
why, when TMPDIR is not on a persistent filesystem.

Judgement call: an unreadable mount list fails the scan, and no flag gets round it.
Judgement call: a file on such a filesystem below an operand gets the same line as a directory.
Judgement call: such an operand that another operand's walk also reaches is named twice.
Unverified: whether macOS's mount list gives the device lstat reports, so macOS keeps lstat, and a hidden mount there can still add another filesystem's device.
Unverified: the macOS code is never built or run here; bind mounts need root to test.

Model: opus-5-5

exclude_test.go

@@ -0,0 +1,583 @@
+package main
+
+import (
+	"bytes"
+	"errors"
+	"maps"
+	"os"
+	"path/filepath"
+	"runtime"
+	"slices"
+	"strings"
+	"testing"
+
+	"golang.org/x/sys/unix"
+)
+
+func TestDefaultExcludes(t *testing.T) {
+	t.Parallel()
+
+	// README "Rules for the walk": each system's list.
+	cases := map[string][]string{
+		goosLinux: {"/proc", "/sys", "/dev", "/run", "/tmp", "/var/tmp"},
+		goosDarwin: {
+			"/dev", "/private/tmp", "/private/var/tmp", "/private/var/vm",
+			"/System/Volumes/VM", "/System/Volumes/Data",
+		},
+		goosWindows: {
+			"pagefile.sys", "swapfile.sys", "hiberfil.sys",
+			"System Volume Information", "$Recycle.Bin", `Windows\Temp`,
+			`Users\*\AppData\Local\Temp`,
+		},
+		"freebsd": nil,
+	}
+
+	for goos, want := range cases {
+		if got := defaultExcludes(goos); !slices.Equal(got, want) {
+			t.Errorf("defaultExcludes(%q) = %q, want %q", goos, got, want)
+		}
+	}
+}
+
+func TestIsDefaultExclude(t *testing.T) {
+	t.Parallel()
+
+	// A * matches one path component, no more and no fewer.
+	excludes := []string{"/scratch", "/home/*/cache"}
+
+	cases := map[string]bool{
+		"/scratch":        true,
+		"/scratch/x":      false,
+		"/home/u/cache":   true,
+		"/home/u/v/cache": false,
+		"/home/cache":     false,
+	}
+
+	for path, want := range cases {
+		if got := isDefaultExclude(path, excludes); got != want {
+			t.Errorf("isDefaultExclude(%q) = %v, want %v", path, got, want)
+		}
+	}
+}
+
+func TestReadMountInfo(t *testing.T) {
+	t.Parallel()
+
+	// The second-to-last line has no optional fields. The tmpfs on
+	// /data/a/b is hidden by the root filesystem's /srv, mounted over
+	// /data/a after it: the tmpfs still gives its own device, and the
+	// root filesystem's device is not listed.
+	mountinfo := strings.Join([]string{
+		"22 1 8:1 / / rw,relatime shared:1 - ext4 /dev/sda1 rw",
+		"23 22 0:21 / /proc rw,nosuid shared:12 - proc none rw",
+		"24 22 0:22 / /sys rw,nosuid shared:7 - sysfs none rw",
+		"25 22 0:23 / /data/a/b rw shared:2 - tmpfs none rw",
+		"26 22 8:1 /srv /data/a rw - ext4 /dev/sda1 rw",
+		"27 22 0:25 / /srv/auto rw shared:4 - autofs systemd-1 rw",
+	}, "\n")
+
+	got, err := readMountInfo(strings.NewReader(mountinfo))
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	want := map[uint64]string{
+		unix.Mkdev(0, 21): "proc", unix.Mkdev(0, 22): "sysfs",
+		unix.Mkdev(0, 23): "tmpfs", unix.Mkdev(0, 25): "autofs",
+	}
+	if !maps.Equal(got, want) {
+		t.Errorf("readMountInfo = %v, want %v", got, want)
+	}
+
+	for _, line := range []string{
+		"22 1 8:1 / / rw,relatime\n",
+		"22 1 sda / / rw,relatime shared:1 - ext4 /dev/sda1 rw\n",
+	} {
+		_, err = readMountInfo(strings.NewReader(line))
+		if !errors.Is(err, errMountInfoLine) {
+			t.Errorf("readMountInfo(%q) = %v, want %v", line, err,
+				errMountInfoLine)
+		}
+	}
+}
+
+func TestNonPersistentFilesystems(t *testing.T) {
+	t.Parallel()
+
+	if runtime.GOOS != goosLinux {
+		t.Skip("the test knows a mount only on Linux: /proc")
+	}
+
+	nonPersistent, err := nonPersistentFilesystems()
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	dev, ok := deviceOfPath("/proc")
+	if !ok {
+		t.Fatal("no device for /proc")
+	}
+
+	if got := nonPersistent[dev]; got != "proc" {
+		t.Errorf("filesystem of /proc = %q, want %q", got, "proc")
+	}
+}
+
+func TestDefaultExcludesHelp(t *testing.T) {
+	t.Parallel()
+
+	for _, goos := range []string{goosLinux, goosDarwin, goosWindows} {
+		help := defaultExcludesHelp(goos)
+
+		for _, dir := range defaultExcludes(goos) {
+			if !strings.Contains(help, "\n  "+dir+"\n") {
+				t.Errorf("help for %s does not list %s:\n%s", goos, dir, help)
+			}
+		}
+
+		// Only Linux and macOS list their mounted filesystems.
+		for _, fsType := range nonPersistentFilesystemTypes() {
+			listed := strings.Contains(help, " "+fsType+",") ||
+				strings.Contains(help, " "+fsType+"\n")
+			if listed != (goos != goosWindows) {
+				t.Errorf("help for %s lists %s: %v", goos, fsType, listed)
+			}
+		}
+	}
+
+	want := "This system has no default excludes.\n"
+	if got := defaultExcludesHelp("freebsd"); got != want {
+		t.Errorf("help for freebsd = %q, want %q", got, want)
+	}
+
+	// scan's help shows those of the system it runs on.
+	var stdout, stderr bytes.Buffer
+
+	run([]string{cmdScan, "-h"}, &stdout, &stderr)
+
+	help := strings.TrimSpace(defaultExcludesHelp(runtime.GOOS))
+	if !strings.Contains(stderr.String(), help) {
+		t.Errorf("scan --help = %q, want it to hold %q", stderr.String(), help)
+	}
+}
+
+// TestScanDoesNotEnterDefaultExclude checks that the walk does not
+// enter a default exclude below an operand. It says so on a line of its
+// own and does not count it as skipped. The records below it count as
+// outside the operands: the record of a file gone from it is kept, and
+// its size joins the size census, while a file added to it is not
+// recorded.
+//
+//nolint:paralleltest // captureStderr replaces the process-wide os.Stderr
+func TestScanDoesNotEnterDefaultExclude(t *testing.T) {
+	stderr := captureStderr(t)
+	dir := t.TempDir()
+	db := openTestDB(t)
+	excluded := filepath.Join(dir, "tmp")
+
+	// A scan with no default excludes records the file in excluded.
+	gone := writeFile(t, excluded, "gone", pattern(1, 100))
+	syncTree(t, db, dir)
+
+	err := os.Remove(gone)
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	unseen := writeFile(t, excluded, "new", pattern(2, 10))
+
+	// The same size as gone, so it is hashed only if the census holds the
+	// size of gone's record.
+	added := writeFile(t, dir, "added", pattern(3, 100))
+
+	st, err := syncScan(t.Context(), db, []string{dir}, 1, false,
+		walkRules{excludes: []string{excluded}})
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	if st.skipped != 0 {
+		t.Errorf("skipped = %d, want 0", st.skipped)
+	}
+
+	recs := dbRecords(t, db)
+	recordByPath(t, recs, gone)
+
+	if recordByPath(t, recs, added).head == "" {
+		t.Errorf("%s not hashed: the census lacks the size of %s",
+			added, gone)
+	}
+
+	if slices.Contains(recordPaths(recs), unseen) {
+		t.Errorf("%s recorded: the walk entered %s", unseen, excluded)
+	}
+
+	line := "\nscan: skipped " + excluded + " (default exclude)\n"
+	if !strings.Contains(stderr(), line) {
+		t.Errorf("stderr = %q, want %q", stderr(), line)
+	}
+}
+
+// TestScanWalksOperandInDefaultExclude checks that an operand at or
+// inside a default exclude is walked, also when it lies under another
+// operand, whose walk does not enter the default exclude.
+func TestScanWalksOperandInDefaultExclude(t *testing.T) {
+	t.Parallel()
+
+	dir := t.TempDir()
+	excluded := filepath.Join(dir, "tmp")
+	f := writeFile(t, excluded, "sub/f", pattern(1, 10))
+	sub := filepath.Dir(f)
+
+	cases := map[string][]string{
+		"at it":                      {excluded},
+		"inside it":                  {sub},
+		"inside it under an operand": {dir, sub},
+	}
+
+	for name, roots := range cases {
+		t.Run(name, func(t *testing.T) {
+			t.Parallel()
+
+			db := openTestDB(t)
+
+			st, err := syncScan(t.Context(), db, roots, 1, false,
+				walkRules{excludes: []string{excluded}})
+			if err != nil {
+				t.Fatal(err)
+			}
+
+			if st.added != 1 {
+				t.Errorf("added = %d, want %s recorded once", st.added, f)
+			}
+
+			recordByPath(t, dbRecords(t, db), f)
+		})
+	}
+}
+
+// TestScanNamesNoDefaultExcludeThatIsAnOperand checks that a default
+// exclude given as an operand under another operand, which the walk of
+// that other operand does not enter, gets no line saying it was
+// skipped: it is walked as an operand of its own.
+//
+//nolint:paralleltest // captureStderr replaces the process-wide os.Stderr
+func TestScanNamesNoDefaultExcludeThatIsAnOperand(t *testing.T) {
+	stderr := captureStderr(t)
+	dir := t.TempDir()
+	db := openTestDB(t)
+	excluded := filepath.Join(dir, "tmp")
+	f := writeFile(t, excluded, "f", pattern(1, 10))
+
+	st, err := syncScan(t.Context(), db, []string{dir, excluded}, 1, false,
+		walkRules{excludes: []string{excluded}})
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	if st.added != 1 {
+		t.Errorf("added = %d, want %s recorded once", st.added, f)
+	}
+
+	recordByPath(t, dbRecords(t, db), f)
+
+	if strings.Contains(stderr(), "scan: skipped") {
+		t.Errorf("stderr = %q, want no line for %s", stderr(), excluded)
+	}
+}
+
+// TestRunScanTempDirOperand scans a tree in the tests' temporary
+// directory, which on Linux lies inside the default exclude /tmp unless
+// TMPDIR names another place, with the system's own default excludes:
+// the scan walks the whole tree and reports no default exclude.
+func TestRunScanTempDirOperand(t *testing.T) {
+	path := testDBPath(t)
+	t.Setenv(databaseEnv, path)
+
+	dir := t.TempDir()
+	if !underAnyRoot(dir, defaultExcludes(runtime.GOOS)) {
+		t.Skip(dir + " is not inside a default exclude")
+	}
+
+	f := writeFile(t, dir, "sub/f", pattern(1, 10))
+
+	stderr := scanOK(t, dir)
+	if strings.Contains(stderr, "scan: skipped") {
+		t.Errorf("stderr = %q, want no line saying a path was skipped",
+			stderr)
+	}
+
+	assertRecorded(t, path, f, true)
+}
+
+// TestRunScanNoDefaultExcludes scans /var through the command. Its
+// /var/tmp, on a persistent filesystem, is a default exclude on Linux:
+// without --no-default-excludes the walk does not enter it and says so,
+// and with that flag the walk records a file the test puts there.
+func TestRunScanNoDefaultExcludes(t *testing.T) {
+	if runtime.GOOS != goosLinux {
+		t.Skip("only Linux has /var/tmp among its default excludes")
+	}
+
+	nonPersistent, err := nonPersistentFilesystems()
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	rules := walkRules{nonPersistent: nonPersistent}
+
+	for _, dir := range []string{"/var", "/var/tmp"} {
+		fi, lstatErr := os.Lstat(dir)
+		if lstatErr != nil || !fi.IsDir() ||
+			rules.nonPersistentLine(dir, fi) != "" {
+			t.Skip(dir + " is not a directory on a persistent filesystem here")
+		}
+	}
+
+	//nolint:usetesting // the directory must be inside /var/tmp
+	tmp, err := os.MkdirTemp("/var/tmp", "sfdupes-test-")
+	if err != nil {
+		t.Skip("cannot write to /var/tmp here: " + err.Error())
+	}
+
+	t.Cleanup(func() { _ = os.RemoveAll(tmp) })
+
+	f := writeFile(t, tmp, "f", pattern(1, 10))
+
+	path := testDBPath(t)
+	t.Setenv(databaseEnv, path)
+
+	line := "scan: skipped /var/tmp (default exclude)\n"
+
+	if stderr := scanOK(t, "/var"); !strings.Contains(stderr, line) {
+		t.Errorf("scan /var: stderr = %q, want %q", stderr, line)
+	}
+
+	assertRecorded(t, path, f, false)
+
+	stderr := scanOK(t, "--no-default-excludes", "/var")
+	if strings.Contains(stderr, line) {
+		t.Errorf("scan --no-default-excludes /var: stderr = %q, want no %q",
+			stderr, line)
+	}
+
+	assertRecorded(t, path, f, true)
+}
+
+// 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
+// so, and nothing in it is recorded.
+func TestRunScanSkipsNonPersistentOperand(t *testing.T) {
+	shm, fsType, _ := shmTempDir(t)
+	writeFile(t, shm, "f", pattern(1, 10))
+
+	t.Setenv(databaseEnv, testDBPath(t))
+
+	line := "scan: skipped " + shm + " (" + fsType +
+		", not a persistent filesystem)\n"
+	summary := "scan: 0 files seen"
+
+	for _, flags := range [][]string{nil, {"--no-default-excludes"}} {
+		stderr := scanOK(t, append(flags, shm)...)
+		if !strings.Contains(stderr, line) ||
+			!strings.Contains(stderr, summary) {
+			t.Errorf("scan %q: stderr = %q, want %q and %q", flags, stderr,
+				line, summary)
+		}
+	}
+}
+
+// TestScanKeepsRecordsOnNonPersistent scans a directory on a filesystem
+// that is not persistent beside one on the tests' temporary directory.
+// The records an earlier scan left in it count as outside the operands:
+// the record of a file gone from it is kept, and its size joins the size
+// census, while a file added to it is not recorded, and its size does
+// not join the census.
+//
+//nolint:paralleltest // captureStderr replaces the process-wide os.Stderr
+func TestScanKeepsRecordsOnNonPersistent(t *testing.T) {
+	shm, fsType, rules := shmTempDir(t)
+	stderr := captureStderr(t)
+	dir := t.TempDir()
+	db := openTestDB(t)
+
+	// A scan that, without the list of filesystems, records gone.
+	gone := writeFile(t, shm, "gone", pattern(1, 100))
+	syncTree(t, db, shm)
+
+	err := os.Remove(gone)
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	unseen := writeFile(t, shm, "new", pattern(2, 10))
+
+	// added has the size of gone, and lonely that of unseen: each is
+	// hashed only if the census holds that size.
+	added := writeFile(t, dir, "added", pattern(3, 100))
+	lonely := writeFile(t, dir, "lonely", pattern(4, 10))
+
+	st, err := syncScan(t.Context(), db, []string{shm, dir}, 1, false, rules)
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	if st.skipped != 0 {
+		t.Errorf("skipped = %d, want 0", st.skipped)
+	}
+
+	recs := dbRecords(t, db)
+	recordByPath(t, recs, gone)
+
+	if recordByPath(t, recs, added).head == "" {
+		t.Errorf("%s not hashed: the census lacks the size of %s",
+			added, gone)
+	}
+
+	if recordByPath(t, recs, lonely).head != "" {
+		t.Errorf("%s hashed: the census holds the size of %s", lonely, unseen)
+	}
+
+	if slices.Contains(recordPaths(recs), unseen) {
+		t.Errorf("%s recorded", unseen)
+	}
+
+	line := "scan: skipped " + shm + " (" + fsType +
+		", not a persistent filesystem)\n"
+	if !strings.Contains(stderr(), line) {
+		t.Errorf("stderr = %q, want %q", stderr(), line)
+	}
+}
+
+// TestScanContentSkipsNonPersistent checks that the content phase does
+// not read a file on a filesystem that is not persistent, though an
+// earlier scan left a record for it: it is treated as a changed file,
+// so its record is left as it is and its identical copy in another
+// tree, having no other match, is not read either.
+func TestScanContentSkipsNonPersistent(t *testing.T) {
+	t.Parallel()
+
+	shm, _, rules := shmTempDir(t)
+	db := openTestDB(t)
+
+	// A scan that, without the list of filesystems, records a with a
+	// head and tail but no content hash.
+	a := sparseFileWithoutMatch(t, shm, "a", headTailMin)
+
+	syncTree(t, db, shm)
+
+	before := recordByPath(t, dbRecords(t, db), a)
+	if before.head == "" || before.content != "" {
+		t.Fatalf("after scanning %s: %+v, want head and tail only", shm, before)
+	}
+
+	b := sparseFile(t, t.TempDir(), "b", headTailMin)
+
+	st, err := syncScan(t.Context(), db, []string{filepath.Dir(b)}, 1, false,
+		rules)
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	if st.skipped != 0 {
+		t.Errorf("skipped = %d, want 0", st.skipped)
+	}
+
+	recs := dbRecords(t, db)
+	if r := recordByPath(t, recs, a); r != before {
+		t.Errorf("record = %+v, want it left as %+v", r, before)
+	}
+
+	if r := recordByPath(t, recs, b); r.content != "" {
+		t.Errorf("%s: content = %q, want none: its only match is on %s",
+			b, r.content, shm)
+	}
+}
+
+// TestWalkLeavesOutNonPersistent starts the walk itself in a directory
+// on a filesystem that is not persistent, which a scan never does: it
+// drops such an operand first. Below a directory on a persistent
+// filesystem, one on another takes a mount, which a test cannot make.
+// The walk enters no directory and records no file there, and names
+// each.
+func TestWalkLeavesOutNonPersistent(t *testing.T) {
+	t.Parallel()
+
+	shm, fsType, rules := shmTempDir(t)
+	f := writeFile(t, shm, "f", pattern(1, 10))
+	sub := filepath.Dir(writeFile(t, shm, "sub/g", pattern(1, 10)))
+
+	var leftOut []string
+
+	for ev := range startWalk(t.Context(), []string{shm}, false, rules, 1) {
+		if ev.rec.path != "" {
+			t.Errorf("walk recorded %s", ev.rec.path)
+		}
+
+		if ev.leftOut == "" {
+			continue
+		}
+
+		leftOut = append(leftOut, ev.leftOut)
+
+		want := "scan: skipped " + ev.leftOut + " (" + fsType +
+			", not a persistent filesystem)"
+		if ev.warn != want {
+			t.Errorf("line = %q, want %q", ev.warn, want)
+		}
+	}
+
+	slices.Sort(leftOut)
+
+	if want := []string{f, sub}; !slices.Equal(leftOut, want) {
+		t.Errorf("walk left out %q, want %q", leftOut, want)
+	}
+}
+
+// shmTempDir returns a new directory in /dev/shm, removed when the test
+// ends, the type of its filesystem, and the rules holding the real
+// filesystems that are not persistent. It skips the test where /dev/shm
+// is on a persistent filesystem, or cannot be written to.
+func shmTempDir(t *testing.T) (string, string, walkRules) {
+	t.Helper()
+
+	nonPersistent, err := nonPersistentFilesystems()
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	dev, ok := deviceOfPath("/dev/shm")
+
+	fsType, found := nonPersistent[dev]
+	if !ok || !found {
+		t.Skip("/dev/shm is not a memory-backed filesystem here")
+	}
+
+	//nolint:usetesting // the directory must be inside /dev/shm
+	dir, err := os.MkdirTemp("/dev/shm", "sfdupes-test-")
+	if err != nil {
+		t.Skip("cannot write to /dev/shm here: " + err.Error())
+	}
+
+	t.Cleanup(func() { _ = os.RemoveAll(dir) })
+
+	return dir, fsType, walkRules{nonPersistent: nonPersistent}
+}
+
+// assertRecorded checks that the database at dbPath holds a record for
+// path when want is set, and none when it is not.
+func assertRecorded(t *testing.T, dbPath, path string, want bool) {
+	t.Helper()
+
+	db, err := openDB(dbPath, reportParams)
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	defer func() { _ = db.Close() }()
+
+	if got := slices.Contains(recordPaths(dbRecords(t, db)), path); got != want {
+		t.Errorf("%s recorded: %v, want %v", path, got, want)
+	}
+}