Add test suite covering parsing, grouping, digests, and scan passes

Covers splitNUL framing, parseScanStream (malformed records, tabs and
newlines in paths, unterminated trailing record), duplicate grouping
with ordering/tie-break/determinism, humanBytes units, Merkle digest
equality and name/content sensitivity, maximal-tree suppression
(including sibling and differing-parent cases), hashHeadTail edge
sizes and error paths, walkPass .zfs/symlink skipping, statPass
vanished files, and an end-to-end walk/stat/hash pipeline test of the
README smoke-test scenario. 64% statement coverage.
This commit is contained in:
2026-07-23 05:42:38 +07:00
parent 316ea9072d
commit 7a6adae0d2
3 changed files with 735 additions and 0 deletions

204
report_test.go Normal file
View File

@@ -0,0 +1,204 @@
package main
import (
"bufio"
"fmt"
"slices"
"strings"
"testing"
)
// mkRecord serializes one scan record in the on-the-wire format.
func mkRecord(size, mtime int64, head, tail, path string) string {
return fmt.Sprintf("%d\t%d\t%s\t%s\t%s\x00",
size, mtime, head, tail, path)
}
func TestSplitNULScanner(t *testing.T) {
t.Parallel()
sc := bufio.NewScanner(strings.NewReader("a\x00bb\x00\x00tail"))
sc.Split(splitNUL)
var got []string
for sc.Scan() {
got = append(got, sc.Text())
}
err := sc.Err()
if err != nil {
t.Fatalf("scanner error: %v", err)
}
want := []string{"a", "bb", "", "tail"}
if !slices.Equal(got, want) {
t.Fatalf("tokens = %q, want %q", got, want)
}
}
func TestParseScanStream(t *testing.T) {
t.Parallel()
stream := mkRecord(10, 1, "h1", "t1", "/a/x") +
"garbage-without-tabs\x00" +
"notanumber\t1\th\tt\t/a/bad\x00" +
mkRecord(20, 2, "h2", "t2", "/a/tab\tin\tname") +
"30\t3\th3\tt3\t/trailing/no-nul"
recs, malformed := parseScanStream(strings.NewReader(stream), "test")
if malformed != 2 {
t.Errorf("malformed = %d, want 2", malformed)
}
want := []scanRec{
{size: 10, head: "h1", tail: "t1", path: "/a/x"},
{size: 20, head: "h2", tail: "t2", path: "/a/tab\tin\tname"},
{size: 30, head: "h3", tail: "t3", path: "/trailing/no-nul"},
}
if !slices.Equal(recs, want) {
t.Fatalf("recs = %+v, want %+v", recs, want)
}
}
func TestParseScanStreamPathWithNewline(t *testing.T) {
t.Parallel()
in := strings.NewReader(mkRecord(5, 9, "h", "t", "/a/new\nline"))
recs, malformed := parseScanStream(in, "test")
if malformed != 0 || len(recs) != 1 {
t.Fatalf("got %d recs, %d malformed, want 1, 0",
len(recs), malformed)
}
if recs[0].path != "/a/new\nline" {
t.Fatalf("path = %q, want %q", recs[0].path, "/a/new\nline")
}
}
func TestParseScanStreamEmpty(t *testing.T) {
t.Parallel()
recs, malformed := parseScanStream(strings.NewReader(""), "test")
if len(recs) != 0 || malformed != 0 {
t.Fatalf("got %d recs, %d malformed, want 0, 0",
len(recs), malformed)
}
}
func TestCollectDupeGroups(t *testing.T) {
t.Parallel()
recs := []scanRec{
{size: 100, head: "h", tail: "t", path: "/z/b"},
{size: 100, head: "h", tail: "t", path: "/z/a"},
{size: 100, head: "h", tail: "t", path: "/z/c"},
{size: 4000, head: "H", tail: "T", path: "/big/2"},
{size: 4000, head: "H", tail: "T", path: "/big/1"},
// Same size as the /z group but a different head hash.
{size: 100, head: "other", tail: "t", path: "/z/d"},
// A singleton signature must not form a group.
{size: 7, head: "u", tail: "u", path: "/lonely"},
}
groups := collectDupeGroups(recs)
if len(groups) != 2 {
t.Fatalf("len(groups) = %d, want 2", len(groups))
}
if groups[0].size != 4000 ||
!slices.Equal(groups[0].paths, []string{"/big/1", "/big/2"}) {
t.Errorf("groups[0] = %+v, want size 4000, paths /big/1 /big/2",
groups[0])
}
if groups[1].size != 100 ||
!slices.Equal(groups[1].paths, []string{"/z/a", "/z/b", "/z/c"}) {
t.Errorf("groups[1] = %+v, want size 100, paths /z/a /z/b /z/c",
groups[1])
}
}
func TestCollectDupeGroupsTieBreak(t *testing.T) {
t.Parallel()
recs := []scanRec{
{size: 50, head: "b", tail: "b", path: "/beta/2"},
{size: 50, head: "b", tail: "b", path: "/beta/1"},
{size: 50, head: "a", tail: "a", path: "/alpha/2"},
{size: 50, head: "a", tail: "a", path: "/alpha/1"},
}
groups := collectDupeGroups(recs)
if len(groups) != 2 {
t.Fatalf("len(groups) = %d, want 2", len(groups))
}
// Equal sizes: ordered by first path ascending.
if groups[0].paths[0] != "/alpha/1" || groups[1].paths[0] != "/beta/1" {
t.Fatalf("tie-break order wrong: %q then %q",
groups[0].paths[0], groups[1].paths[0])
}
}
func TestCollectDupeGroupsDeterministic(t *testing.T) {
t.Parallel()
recs := []scanRec{
{size: 1, head: "a", tail: "a", path: "/p/1"},
{size: 1, head: "a", tail: "a", path: "/p/2"},
{size: 2, head: "b", tail: "b", path: "/q/1"},
{size: 2, head: "b", tail: "b", path: "/q/2"},
}
forward := collectDupeGroups(recs)
reversed := slices.Clone(recs)
slices.Reverse(reversed)
backward := collectDupeGroups(reversed)
if !slices.EqualFunc(forward, backward, func(a, b dupeGroup) bool {
return a.size == b.size && slices.Equal(a.paths, b.paths)
}) {
t.Fatalf("output depends on record order: %+v vs %+v",
forward, backward)
}
}
func TestHumanBytes(t *testing.T) {
t.Parallel()
cases := []struct {
n int64
want string
}{
{0, "0 B"},
{1, "1 B"},
{1023, "1023 B"},
{1024, "1.0 KiB"},
{1536, "1.5 KiB"},
{1 << 20, "1.0 MiB"},
{5 << 30, "5.0 GiB"},
{1 << 40, "1.0 TiB"},
{1 << 50, "1.0 PiB"},
{1 << 60, "1.0 EiB"},
}
for _, c := range cases {
if got := humanBytes(c.n); got != c.want {
t.Errorf("humanBytes(%d) = %q, want %q", c.n, got, c.want)
}
}
}
func TestMalformedNote(t *testing.T) {
t.Parallel()
if got := malformedNote(0); got != "" {
t.Errorf("malformedNote(0) = %q, want empty", got)
}
if got := malformedNote(3); got != " (3 malformed, skipped)" {
t.Errorf("malformedNote(3) = %q", got)
}
}

311
scan_test.go Normal file
View File

@@ -0,0 +1,311 @@
package main
import (
"bytes"
"crypto/sha256"
"encoding/hex"
"io"
"os"
"path/filepath"
"slices"
"strings"
"testing"
)
// writeFile creates a file with the given content and returns its path.
func writeFile(t *testing.T, dir, name string, data []byte) string {
t.Helper()
p := filepath.Join(dir, name)
err := os.MkdirAll(filepath.Dir(p), 0o750)
if err != nil {
t.Fatal(err)
}
err = os.WriteFile(p, data, 0o600)
if err != nil {
t.Fatal(err)
}
return p
}
// hexSum returns the lowercase-hex SHA-256 of data.
func hexSum(data []byte) string {
s := sha256.Sum256(data)
return hex.EncodeToString(s[:])
}
// pattern returns n bytes of deterministic content seeded by tag.
func pattern(tag byte, n int) []byte {
data := make([]byte, n)
for i := range data {
data[i] = tag ^ byte(i)
}
return data
}
func TestHashHeadTail(t *testing.T) {
t.Parallel()
dir := t.TempDir()
cases := []struct {
name string
data []byte
}{
{"empty", nil},
{"one-byte", []byte("x")},
{"under-one-chunk", pattern(1, chunk-1)},
{"exactly-one-chunk", pattern(2, chunk)},
{"overlapping-reads", pattern(3, chunk+chunk/2)},
{"exactly-two-chunks", pattern(4, 2*chunk)},
{"beyond-two-chunks", pattern(5, 3*chunk)},
}
for _, c := range cases {
t.Run(c.name, func(t *testing.T) {
t.Parallel()
p := writeFile(t, dir, c.name, c.data)
head, tail, err := hashHeadTail(p, int64(len(c.data)))
if err != nil {
t.Fatalf("hashHeadTail: %v", err)
}
n := min(chunk, len(c.data))
if want := hexSum(c.data[:n]); head != want {
t.Errorf("head = %s, want %s", head, want)
}
if want := hexSum(c.data[len(c.data)-n:]); tail != want {
t.Errorf("tail = %s, want %s", tail, want)
}
})
}
}
func TestHashHeadTailErrors(t *testing.T) {
t.Parallel()
dir := t.TempDir()
_, _, err := hashHeadTail(filepath.Join(dir, "missing"), 1)
if err == nil {
t.Error("no error for a missing file")
}
// A file that shrank between the stat and hash passes: reading at
// the stat-reported size must fail rather than emit wrong hashes.
p := writeFile(t, dir, "shrunk", []byte("tiny"))
_, _, err = hashHeadTail(p, int64(2*chunk))
if err == nil {
t.Error("no error when the stat size exceeds the file size")
}
}
func TestWalkPass(t *testing.T) {
t.Parallel()
dir := t.TempDir()
want := []string{
writeFile(t, dir, "a.txt", []byte("a")),
writeFile(t, dir, "sub/b.txt", []byte("b")),
writeFile(t, dir, "sub/deeper/c.txt", []byte("c")),
}
slices.Sort(want)
// Files under a .zfs directory must never be walked.
writeFile(t, dir, ".zfs/snapshot/hourly/a.txt", []byte("a"))
// Symlinks are skipped, not followed.
err := os.Symlink(want[0], filepath.Join(dir, "link"))
if err != nil {
t.Fatal(err)
}
paths, errs := walkPass(dir)
if errs != 0 {
t.Fatalf("errs = %d, want 0", errs)
}
slices.Sort(paths)
if !slices.Equal(paths, want) {
t.Fatalf("paths = %q, want %q", paths, want)
}
}
func TestStatPass(t *testing.T) {
t.Parallel()
dir := t.TempDir()
a := writeFile(t, dir, "a", pattern(1, 10))
b := writeFile(t, dir, "b", pattern(2, 20))
missing := filepath.Join(dir, "vanished")
recs, errs := statPass([]string{a, b, missing}, 2)
if errs != 1 {
t.Fatalf("errs = %d, want 1 for the vanished file", errs)
}
slices.SortFunc(recs, func(x, y fileRec) int {
return strings.Compare(x.path, y.path)
})
if len(recs) != 2 || recs[0].size != 10 || recs[1].size != 20 {
t.Fatalf("recs = %+v, want sizes 10 and 20", recs)
}
if recs[0].mtime <= 0 || recs[1].mtime <= 0 {
t.Fatalf("recs = %+v, want positive mtimes", recs)
}
}
// captureStdout runs fn with os.Stdout redirected to a temp file and
// returns everything fn wrote to it.
func captureStdout(t *testing.T, fn func()) []byte {
t.Helper()
f, err := os.CreateTemp(t.TempDir(), "stdout")
if err != nil {
t.Fatal(err)
}
orig := os.Stdout
os.Stdout = f
defer func() { os.Stdout = orig }()
fn()
_, err = f.Seek(0, io.SeekStart)
if err != nil {
t.Fatal(err)
}
data, err := io.ReadAll(f)
if err != nil {
t.Fatal(err)
}
_ = f.Close()
return data
}
// buildSmokeTree recreates the README smoke-test filesystem layout
// with deterministic content and returns the tree root.
func buildSmokeTree(t *testing.T) string {
t.Helper()
dir := t.TempDir()
one := pattern(10, 2000)
f1 := pattern(30, 3000)
f2 := pattern(40, 100)
writeFile(t, dir, "a/one.bin", one)
writeFile(t, dir, "b/copy.bin", one)
writeFile(t, dir, "b/copy2.bin", one)
// Same size as one.bin, different content.
writeFile(t, dir, "a/unique.bin", pattern(20, 2000))
writeFile(t, dir, "tiny1", []byte("x"))
writeFile(t, dir, "tiny2", []byte("x"))
writeFile(t, dir, "tiny3", []byte("y"))
writeFile(t, dir, "empty1", nil)
writeFile(t, dir, "empty2", nil)
writeFile(t, dir, "t1/f1", f1)
writeFile(t, dir, "t1/sub/f2", f2)
writeFile(t, dir, "t2/f1", f1)
writeFile(t, dir, "t2/sub/f2", f2)
writeFile(t, dir, "t3/f1", f1)
writeFile(t, dir, "t3/sub/f2renamed", f2)
return dir
}
// scanToRecords runs the walk, stat, and hash passes over dir and
// parses the emitted stream back into records.
func scanToRecords(t *testing.T, dir string) []scanRec {
t.Helper()
paths, walkErrs := walkPass(dir)
if walkErrs != 0 {
t.Fatalf("walk errors: %d", walkErrs)
}
recs, statErrs := statPass(paths, 4)
if statErrs != 0 {
t.Fatalf("stat errors: %d", statErrs)
}
var emitted, hashErrs int
out := captureStdout(t, func() {
emitted, hashErrs = hashPass(recs, 4)
})
if emitted != len(paths) || hashErrs != 0 {
t.Fatalf("emitted %d of %d, %d hash errors",
emitted, len(paths), hashErrs)
}
parsed, malformed := parseScanStream(bytes.NewReader(out), "pipe")
if malformed != 0 || len(parsed) != len(paths) {
t.Fatalf("parsed %d records, %d malformed, want %d, 0",
len(parsed), malformed, len(paths))
}
return parsed
}
//nolint:paralleltest // redirects the process-wide os.Stdout
func TestScanPipeline(t *testing.T) {
dir := buildSmokeTree(t)
parsed := scanToRecords(t, dir)
groups := collectDupeGroups(parsed)
if len(groups) != 5 {
t.Fatalf("len(groups) = %d, want 5", len(groups))
}
wantSizes := []int64{3000, 2000, 100, 1, 0}
for i, g := range groups {
if g.size != wantSizes[i] {
t.Errorf("groups[%d].size = %d, want %d",
i, g.size, wantSizes[i])
}
}
wantF1 := []string{
filepath.Join(dir, "t1/f1"),
filepath.Join(dir, "t2/f1"),
filepath.Join(dir, "t3/f1"),
}
if !slices.Equal(groups[0].paths, wantF1) {
t.Errorf("groups[0].paths = %q, want %q", groups[0].paths, wantF1)
}
super, dirs := buildHierarchy(parsed)
super.compute()
tg := collectTreeGroups(dirs, super)
if len(tg) != 1 {
t.Fatalf("len(tree groups) = %d, want 1", len(tg))
}
wantTrees := []string{filepath.Join(dir, "t1"), filepath.Join(dir, "t2")}
if got := groupPaths(tg)[0]; !slices.Equal(got, wantTrees) {
t.Fatalf("tree group = %q, want %q", got, wantTrees)
}
if tg[0][0].fileCount != 2 || tg[0][0].totalSize != 3100 {
t.Fatalf("tree totals: %d files %d bytes, want 2 3100",
tg[0][0].fileCount, tg[0][0].totalSize)
}
}

220
trees_test.go Normal file
View File

@@ -0,0 +1,220 @@
package main
import (
"slices"
"testing"
)
// Signature hashes shared by the smoke-test records.
const (
f1Head = "f1h"
f1Tail = "f1t"
f2Head = "f2h"
f2Tail = "f2t"
)
// smokeTreeRecs mirrors the README smoke-test tree layout: /d/t1 and
// /d/t2 are identical, /d/t3 differs from them only by one filename.
func smokeTreeRecs() []scanRec {
return []scanRec{
{size: 3000, head: f1Head, tail: f1Tail, path: "/d/t1/f1"},
{size: 100, head: f2Head, tail: f2Tail, path: "/d/t1/sub/f2"},
{size: 3000, head: f1Head, tail: f1Tail, path: "/d/t2/f1"},
{size: 100, head: f2Head, tail: f2Tail, path: "/d/t2/sub/f2"},
{size: 3000, head: f1Head, tail: f1Tail, path: "/d/t3/f1"},
{size: 100, head: f2Head, tail: f2Tail, path: "/d/t3/sub/f2renamed"},
}
}
// nodeByPath finds the directory node with the given path.
func nodeByPath(t *testing.T, dirs []*treeNode, path string) *treeNode {
t.Helper()
for _, d := range dirs {
if d.path == path {
return d
}
}
t.Fatalf("no directory node with path %q", path)
return nil
}
// groupPaths flattens tree groups into their member path lists.
func groupPaths(groups [][]*treeNode) [][]string {
out := make([][]string, 0, len(groups))
for _, g := range groups {
paths := make([]string, 0, len(g))
for _, n := range g {
paths = append(paths, n.path)
}
out = append(out, paths)
}
return out
}
func TestBuildHierarchyCounts(t *testing.T) {
t.Parallel()
super, dirs := buildHierarchy(smokeTreeRecs())
super.compute()
d := nodeByPath(t, dirs, "/d")
if d.fileCount != 6 || d.totalSize != 9300 {
t.Errorf("/d: fileCount %d size %d, want 6 9300",
d.fileCount, d.totalSize)
}
t1 := nodeByPath(t, dirs, "/d/t1")
if t1.fileCount != 2 || t1.totalSize != 3100 {
t.Errorf("/d/t1: fileCount %d size %d, want 2 3100",
t1.fileCount, t1.totalSize)
}
sub := nodeByPath(t, dirs, "/d/t1/sub")
if sub.fileCount != 1 || sub.totalSize != 100 {
t.Errorf("/d/t1/sub: fileCount %d size %d, want 1 100",
sub.fileCount, sub.totalSize)
}
}
func TestTreeDigests(t *testing.T) {
t.Parallel()
super, dirs := buildHierarchy(smokeTreeRecs())
super.compute()
t1 := nodeByPath(t, dirs, "/d/t1")
t2 := nodeByPath(t, dirs, "/d/t2")
t3 := nodeByPath(t, dirs, "/d/t3")
if t1.digest != t2.digest {
t.Error("identical trees /d/t1 and /d/t2 have different digests")
}
// t3 differs only in a filename; names are part of the digest.
if t1.digest == t3.digest {
t.Error("/d/t3 digest equals /d/t1 despite a renamed file")
}
sub1 := nodeByPath(t, dirs, "/d/t1/sub")
sub3 := nodeByPath(t, dirs, "/d/t3/sub")
if sub1.digest == sub3.digest {
t.Error("subdirs with differently-named files share a digest")
}
}
func TestTreeDigestContentSensitivity(t *testing.T) {
t.Parallel()
const sharedTail = "same"
recs := []scanRec{
{size: 10, head: sharedTail, tail: sharedTail, path: "/r/a/f"},
{size: 10, head: "DIFF", tail: sharedTail, path: "/r/b/f"},
}
super, dirs := buildHierarchy(recs)
super.compute()
a := nodeByPath(t, dirs, "/r/a")
b := nodeByPath(t, dirs, "/r/b")
if a.digest == b.digest {
t.Error("trees with different file content share a digest")
}
}
func TestCollectTreeGroupsMaximal(t *testing.T) {
t.Parallel()
super, dirs := buildHierarchy(smokeTreeRecs())
super.compute()
groups := collectTreeGroups(dirs, super)
want := [][]string{{"/d/t1", "/d/t2"}}
if got := groupPaths(groups); !slices.EqualFunc(got, want,
slices.Equal) {
t.Fatalf("groups = %v, want %v", got, want)
}
// The /d/t1/sub vs /d/t2/sub group must be suppressed as implied
// by its parents' group; the winning group reports one copy's
// recursive totals.
if groups[0][0].fileCount != 2 || groups[0][0].totalSize != 3100 {
t.Errorf("group totals: %d files %d bytes, want 2 3100",
groups[0][0].fileCount, groups[0][0].totalSize)
}
}
func TestCollectTreeGroupsDeterministic(t *testing.T) {
t.Parallel()
recs := smokeTreeRecs()
super, dirs := buildHierarchy(recs)
super.compute()
forward := groupPaths(collectTreeGroups(dirs, super))
reversed := slices.Clone(recs)
slices.Reverse(reversed)
superR, dirsR := buildHierarchy(reversed)
superR.compute()
backward := groupPaths(collectTreeGroups(dirsR, superR))
if !slices.EqualFunc(forward, backward, slices.Equal) {
t.Fatalf("output depends on record order: %v vs %v",
forward, backward)
}
}
func TestCollectTreeGroupsSiblings(t *testing.T) {
t.Parallel()
// Identical sibling dirs share a parent, so their group cannot be
// implied by a parent group and must be reported.
recs := []scanRec{
{size: 10, head: "h", tail: "t", path: "/p/x1/f"},
{size: 10, head: "h", tail: "t", path: "/p/x2/f"},
}
super, dirs := buildHierarchy(recs)
super.compute()
got := groupPaths(collectTreeGroups(dirs, super))
want := [][]string{{"/p/x1", "/p/x2"}}
if !slices.EqualFunc(got, want, slices.Equal) {
t.Fatalf("groups = %v, want %v", got, want)
}
}
func TestCollectTreeGroupsDifferingParents(t *testing.T) {
t.Parallel()
// /p/a and /q/b contain identical x subtrees, but /p/a has an
// extra file, so the parents' digests differ and the x group must
// be reported.
recs := []scanRec{
{size: 10, head: "h", tail: "t", path: "/p/a/x/f"},
{size: 99, head: "e", tail: "e", path: "/p/a/extra"},
{size: 10, head: "h", tail: "t", path: "/q/b/x/f"},
}
super, dirs := buildHierarchy(recs)
super.compute()
got := groupPaths(collectTreeGroups(dirs, super))
want := [][]string{{"/p/a/x", "/q/b/x"}}
if !slices.EqualFunc(got, want, slices.Equal) {
t.Fatalf("groups = %v, want %v", got, want)
}
}