sfdupes/report_test.go

package main

import (
	"slices"
	"testing"
)

func TestCollectDupeGroups(t *testing.T) {
	t.Parallel()

	recs := []scanRec{
		{size: 100, head: "h", tail: "t", content: "c", path: "/z/b"},
		{size: 100, head: "h", tail: "t", content: "c", path: "/z/a"},
		{size: 100, head: "h", tail: "t", content: "c", path: "/z/c"},
		{size: 4000, head: "H", tail: "T", content: "C", path: "/big/2"},
		{size: 4000, head: "H", tail: "T", content: "C", path: "/big/1"},
		// Same size as the /z group but a different head hash.
		{size: 100, head: "other", tail: "t", content: "c", path: "/z/d"},
		// A singleton signature must not form a group.
		{size: 7, head: "u", tail: "u", content: "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 TestCollectDupeGroupsContentSeparates(t *testing.T) {
	t.Parallel()

	// Same size, head, and tail, but different content hashes: the final
	// rung keeps them apart, so no group forms. Matching content groups.
	// Records without a content hash never group, not even with each
	// other.
	recs := []scanRec{
		{size: 100, head: "h", tail: "t", content: "c1", path: "/a"},
		{size: 100, head: "h", tail: "t", content: "c2", path: "/b"},
		{size: 100, head: "h", tail: "t", content: "c1", path: "/c"},
		{size: 100, head: "h", tail: "t", path: "/d"},
		{size: 100, head: "h", tail: "t", path: "/e"},
	}

	groups := collectDupeGroups(recs)
	if len(groups) != 1 {
		t.Fatalf("len(groups) = %d, want 1 (only the matching content)",
			len(groups))
	}

	if !slices.Equal(groups[0].paths, []string{"/a", "/c"}) {
		t.Errorf("group paths = %q, want /a /c", groups[0].paths)
	}
}

func TestCollectDupeGroupsMtimeExcluded(t *testing.T) {
	t.Parallel()

	// mtime is informational only; records differing only in mtime
	// still group together.
	recs := []scanRec{
		{size: 9, mtime: 100, head: "h", tail: "t", content: "c", path: "/m/1"},
		{size: 9, mtime: 200, head: "h", tail: "t", content: "c", path: "/m/2"},
	}

	groups := collectDupeGroups(recs)
	if len(groups) != 1 {
		t.Fatalf("len(groups) = %d, want 1", len(groups))
	}
}

func TestCollectDupeGroupsTieBreak(t *testing.T) {
	t.Parallel()

	recs := []scanRec{
		{size: 50, head: "b", tail: "b", content: "b", path: "/beta/2"},
		{size: 50, head: "b", tail: "b", content: "b", path: "/beta/1"},
		{size: 50, head: "a", tail: "a", content: "a", path: "/alpha/2"},
		{size: 50, head: "a", tail: "a", content: "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", content: "a", path: "/p/1"},
		{size: 1, head: "a", tail: "a", content: "a", path: "/p/2"},
		{size: 2, head: "b", tail: "b", content: "b", path: "/q/1"},
		{size: 2, head: "b", tail: "b", content: "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)
		}
	}
}