sfdupes/report_test.go

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)
	}
}