Add 64 KiB head/tail and content-hash duplicate ladder (closes #61) (#62)

report_test.go

@@ -38,6 +38,28 @@ func TestCollectDupeGroups(t *testing.T) {
 	}
 }
 
+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.
+	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"},
+	}
+
+	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()