counter 0.7.1

Simple package to count generic iterables
Documentation 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253

#[cfg(test)]
mod tests {
    use std::{any::Any, ops::Deref};

    use counter::Counter;
    use rand::Rng;
    use std::hash::{BuildHasher, Hasher, RandomState};

    #[test]
    fn test_composite_add_sub() {
        let mut counts = "able babble table babble rabble table able fable scrabble"
            .split_whitespace()
            .collect::<Counter<_>>();
        // add or subtract an iterable of the same type
        counts += "cain and abel fable table cable".split_whitespace();
        // or add or subtract from another Counter of the same type
        let other_counts = "scrabble cabbie fable babble"
            .split_whitespace()
            .collect::<Counter<_>>();
        let _diff = counts - other_counts;
    }

    #[test]
    fn test_most_common() {
        let counter = "abbccc".chars().collect::<Counter<_>>();
        let by_common = counter.most_common();
        let expected = vec![('c', 3), ('b', 2), ('a', 1)];
        assert!(by_common == expected);
    }

    #[test]
    fn test_most_common_tiebreaker() {
        let counter = "eaddbbccc".chars().collect::<Counter<_>>();
        let by_common = counter.most_common_tiebreaker(|&a, &b| a.cmp(&b));
        let expected = vec![('c', 3), ('b', 2), ('d', 2), ('a', 1), ('e', 1)];
        assert!(by_common == expected);
    }

    #[test]
    fn test_most_common_tiebreaker_reversed() {
        let counter = "eaddbbccc".chars().collect::<Counter<_>>();
        let by_common = counter.most_common_tiebreaker(|&a, &b| b.cmp(&a));
        let expected = vec![('c', 3), ('d', 2), ('b', 2), ('e', 1), ('a', 1)];
        assert!(by_common == expected);
    }

    // The main purpose of this test is to see that we can call `Counter::most_common_tiebreaker()`
    // with a closure that is `FnMut` but not `Fn`.
    #[test]
    fn test_most_common_tiebreaker_fn_mut() {
        let counter: Counter<_> = "abracadabra".chars().collect::<Counter<_>>();
        // Count how many times the tiebreaker closure is called.
        let mut num_ties = 0;
        let sorted = counter.most_common_tiebreaker(|a, b| {
            num_ties += 1;
            a.cmp(b)
        });
        let expected = vec![('a', 5), ('b', 2), ('r', 2), ('c', 1), ('d', 1)];
        assert_eq!(sorted, expected);
        // We should have called the tiebreaker twice: once to resolve the tie between `'b'` and
        // `'r'` and once to resolve the tie between `'c'` and `'d'`.
        assert_eq!(num_ties, 2);
    }

    #[test]
    fn test_most_common_ordered() {
        let counter = "eaddbbccc".chars().collect::<Counter<_>>();
        let by_common = counter.most_common_ordered();
        let expected = vec![('c', 3), ('b', 2), ('d', 2), ('a', 1), ('e', 1)];
        assert!(by_common == expected);
    }

    #[test]
    fn test_k_most_common_ordered() {
        let counter: Counter<_> = "abracadabra".chars().collect();
        let all = counter.most_common_ordered();
        for k in 0..=counter.len() {
            let topk = counter.k_most_common_ordered(k);
            assert_eq!(&topk, &all[..k]);
        }
    }

    /// This test is fundamentally the same as `test_k_most_common_ordered`, but it operates on
    /// a wider variety of data. In particular, it tests both longer, narrower, and wider
    /// distributions of data than the other test does.
    #[test]
    fn test_k_most_common_ordered_heavy() {
        let mut rng = rand::rng();

        for container_size in [5, 10, 25, 100, 256] {
            for max_value_factor in [0.25, 0.5, 1.0, 1.25, 2.0, 10.0, 100.0] {
                let max_value = ((container_size as f64) * max_value_factor) as u32;
                let mut values = vec![0; container_size];
                for value in values.iter_mut() {
                    *value = rng.random_range(0..=max_value);
                }

                let counter: Counter<_> = values.into_iter().collect();
                let all = counter.most_common_ordered();
                for k in 0..=counter.len() {
                    let topk = counter.k_most_common_ordered(k);
                    assert_eq!(&topk, &all[..k]);
                }
            }
        }
    }

    #[test]
    fn test_total() {
        let counter = "".chars().collect::<Counter<_>>();
        let total: usize = counter.total();
        assert_eq!(total, 0);

        let counter = "eaddbbccc".chars().collect::<Counter<_>>();
        let total: usize = counter.total();
        assert_eq!(total, 9);
    }

    #[test]
    fn test_add() {
        let d = "abbccc".chars().collect::<Counter<_>>();
        let e = "bccddd".chars().collect::<Counter<_>>();

        let out = d + e;
        let expected = "abbbcccccddd".chars().collect::<Counter<_>>();
        assert!(out == expected);
    }

    #[test]
    fn test_sub() {
        let d = "abbccc".chars().collect::<Counter<_>>();
        let e = "bccddd".chars().collect::<Counter<_>>();

        let out = d - e;
        let expected = "abc".chars().collect::<Counter<_>>();
        assert!(out == expected);
    }

    #[test]
    fn test_intersection() {
        let d = "abbccc".chars().collect::<Counter<_>>();
        let e = "bccddd".chars().collect::<Counter<_>>();

        let out = d & e;
        let expected = "bcc".chars().collect::<Counter<_>>();
        assert!(out == expected);
    }

    #[test]
    fn test_union() {
        let d = "abbccc".chars().collect::<Counter<_>>();
        let e = "bccddd".chars().collect::<Counter<_>>();

        let out = d | e;
        let expected = "abbcccddd".chars().collect::<Counter<_>>();
        assert!(out == expected);
    }

    #[test]
    fn test_delete_key_from_backing_map() {
        let mut counter = "aa-bb-cc".chars().collect::<Counter<_>>();
        counter.remove(&'-');
        assert!(counter == "aabbcc".chars().collect::<Counter<_>>());
    }

    #[test]
    fn test_superset_non_usize_count() {
        let mut a: Counter<_, i8> = "abbcccc".chars().collect();
        let mut b: Counter<_, i8> = "abb".chars().collect();
        assert!(a.is_superset(&b));
        // Negative values are possible, a is no longer a superset
        a[&'e'] = -1;
        assert!(!a.is_superset(&b));
        // Adjust b to make a a superset again
        b[&'e'] = -2;
        assert!(a.is_superset(&b));
    }

    #[test]
    fn test_subset_non_usize_count() {
        let mut a: Counter<_, i8> = "abb".chars().collect();
        let mut b: Counter<_, i8> = "abbcccc".chars().collect();
        assert!(a.is_subset(&b));
        // Negative values are possible; a is no longer a subset
        b[&'e'] = -1;
        assert!(!a.is_subset(&b));
        // Adjust a to make it a subset again
        a[&'e'] = -2;
        assert!(a.is_subset(&b));
    }

    #[test]
    fn test_custom_hasher() {
        let custom_hashed_counter: Counter<_, usize, _> =
            "abbccc".chars().collect::<Counter<_, _, TestBuildHasher>>();
        let default_counter: Counter<_> = "abbccc".chars().collect();

        // Check that the hashers for the underlying maps have the correct type id.
        assert_eq!(
            custom_hashed_counter.deref().hasher().type_id(),
            TestBuildHasher.type_id()
        );
        assert_eq!(
            default_counter.deref().hasher().type_id(),
            RandomState::default().type_id()
        );

        // Negative check - Ensure not just getting false positives
        assert_ne!(
            custom_hashed_counter.deref().hasher().type_id(),
            RandomState::default().type_id()
        );
        assert_ne!(
            default_counter.deref().hasher().type_id(),
            TestBuildHasher.type_id()
        );
    }

    #[cfg(feature = "serde")]
    #[test]
    fn test_serialize_deserialize() {
        let a = "abbccc".chars().collect::<Counter<_>>();
        let serialized = serde_json::to_string(&a).unwrap();
        let b: Counter<char> = serde_json::from_str(&serialized).unwrap();
        assert!(a == b)
    }

    #[derive(Default)]
    struct TestHasher {
        hash: u64,
    }

    impl Hasher for TestHasher {
        fn write(&mut self, bytes: &[u8]) {
            self.hash = bytes.len() as u64;
        }

        fn finish(&self) -> u64 {
            self.hash
        }
    }

    #[derive(Default, Clone)]
    struct TestBuildHasher;

    impl BuildHasher for TestBuildHasher {
        type Hasher = TestHasher;

        fn build_hasher(&self) -> Self::Hasher {
            TestHasher::default()
        }
    }
}