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
//! 集合工具:分组、去重、分块、查找
use std::collections::HashMap;
use std::hash::Hash;
/// 集合扩展工具
pub struct CollectionExt;
impl CollectionExt {
/// 按指定键分组(类似 SQL GROUP BY)
///
/// # 示例
///
/// ```
/// use wordval_utils::collection::CollectionExt;
///
/// let items = vec![
/// ("apple", 1),
/// ("banana", 2),
/// ("apple", 3),
/// ];
/// let grouped = CollectionExt::group_by(&items, |item| item.0);
/// assert_eq!(grouped.get("apple").unwrap().len(), 2);
/// ```
pub fn group_by<T, K, F>(items: &[T], key_fn: F) -> HashMap<K, Vec<&T>>
where
K: Eq + Hash,
F: Fn(&T) -> K,
{
let mut map: HashMap<K, Vec<&T>> = HashMap::new();
for item in items {
let key = key_fn(item);
map.entry(key).or_default().push(item);
}
map
}
/// 去重并保持原始顺序
///
/// # 示例
///
/// ```
/// use wordval_utils::collection::CollectionExt;
///
/// let v = vec![3, 1, 2, 1, 3, 4];
/// assert_eq!(CollectionExt::dedup(v), vec![3, 1, 2, 4]);
/// ```
pub fn dedup<T>(items: Vec<T>) -> Vec<T>
where
T: Eq + Hash + Clone,
{
let mut seen = std::collections::HashSet::with_capacity(items.len());
let mut result = Vec::with_capacity(items.len());
for item in items {
if seen.insert(item.clone()) {
result.push(item);
}
}
result
}
/// 将大列表切成固定大小的块
///
/// # 示例
///
/// ```
/// use wordval_utils::collection::CollectionExt;
///
/// let v = vec![1, 2, 3, 4, 5];
/// let chunks = CollectionExt::chunks(v, 2);
/// assert_eq!(chunks, vec![vec![1, 2], vec![3, 4], vec![5]]);
/// ```
pub fn chunks<T>(items: Vec<T>, size: usize) -> Vec<Vec<T>> {
assert!(size > 0, "chunk size must be greater than 0");
// 消费型切分:直接移动元素,无需 Clone
let n = items.len().div_ceil(size);
let mut out = Vec::with_capacity(n);
let mut iter = items.into_iter();
for _ in 0..n {
out.push(iter.by_ref().take(size).collect());
}
out
}
/// 查找第一个满足条件的元素
///
/// # 示例
///
/// ```
/// use wordval_utils::collection::CollectionExt;
///
/// let items = vec![1, 2, 3, 4, 5];
/// assert_eq!(CollectionExt::find_first(&items, |x| *x > 3), Some(&4));
/// ```
pub fn find_first<T, F>(items: &[T], predicate: F) -> Option<&T>
where
F: Fn(&T) -> bool,
{
items.iter().find(|item| predicate(item))
}
/// 查找最后一个满足条件的元素
///
/// # 示例
///
/// ```
/// use wordval_utils::collection::CollectionExt;
///
/// let items = vec![1, 2, 3, 4, 5];
/// assert_eq!(CollectionExt::find_last(&items, |x| *x < 4), Some(&3));
/// ```
pub fn find_last<T, F>(items: &[T], predicate: F) -> Option<&T>
where
F: Fn(&T) -> bool,
{
items.iter().rev().find(|item| predicate(item))
}
/// 查找所有满足条件的元素
///
/// # 示例
///
/// ```
/// use wordval_utils::collection::CollectionExt;
///
/// let items = vec![1, 2, 3, 4, 5];
/// assert_eq!(CollectionExt::find_all(&items, |x| *x % 2 == 0), vec![&2, &4]);
/// ```
pub fn find_all<T, F>(items: &[T], predicate: F) -> Vec<&T>
where
F: Fn(&T) -> bool,
{
items.iter().filter(|item| predicate(item)).collect()
}
}
#[cfg(test)]
mod tests {
use super::*;
#[test]
fn test_group_by() {
let items = vec![
("apple", 1),
("banana", 2),
("apple", 3),
("cherry", 4),
("banana", 5),
];
let grouped = CollectionExt::group_by(&items, |item| item.0);
assert_eq!(grouped.get("apple").unwrap().len(), 2);
assert_eq!(grouped.get("banana").unwrap().len(), 2);
assert_eq!(grouped.get("cherry").unwrap().len(), 1);
}
#[test]
fn test_group_by_empty() {
let items: Vec<(&str, i32)> = vec![];
let grouped = CollectionExt::group_by(&items, |item| item.0);
assert!(grouped.is_empty());
}
#[test]
fn test_dedup() {
let v = vec![3, 1, 2, 1, 3, 4, 2, 5];
assert_eq!(CollectionExt::dedup(v), vec![3, 1, 2, 4, 5]);
}
#[test]
fn test_dedup_empty() {
let v: Vec<i32> = vec![];
assert_eq!(CollectionExt::dedup(v), Vec::<i32>::new());
}
#[test]
fn test_dedup_no_duplicates() {
let v = vec![1, 2, 3, 4, 5];
assert_eq!(CollectionExt::dedup(v), vec![1, 2, 3, 4, 5]);
}
#[test]
fn test_chunks() {
let v = vec![1, 2, 3, 4, 5, 6, 7];
assert_eq!(
CollectionExt::chunks(v, 3),
vec![vec![1, 2, 3], vec![4, 5, 6], vec![7]]
);
}
#[test]
fn test_chunks_exact() {
let v = vec![1, 2, 3, 4, 5, 6];
assert_eq!(
CollectionExt::chunks(v, 2),
vec![vec![1, 2], vec![3, 4], vec![5, 6]]
);
}
#[test]
fn test_chunks_empty() {
let v: Vec<i32> = vec![];
let result: Vec<Vec<i32>> = CollectionExt::chunks(v, 3);
assert!(result.is_empty());
}
#[test]
#[should_panic(expected = "chunk size must be greater than 0")]
fn test_chunks_zero_size() {
let v = vec![1, 2, 3];
CollectionExt::chunks(v, 0);
}
#[test]
fn test_find_first() {
let items = vec![1, 2, 3, 4, 5];
assert_eq!(CollectionExt::find_first(&items, |x| *x > 3), Some(&4));
assert_eq!(CollectionExt::find_first(&items, |x| *x > 10), None);
}
#[test]
fn test_find_last() {
let items = vec![1, 2, 3, 4, 5];
assert_eq!(CollectionExt::find_last(&items, |x| *x < 4), Some(&3));
assert_eq!(CollectionExt::find_last(&items, |x| *x > 10), None);
}
#[test]
fn test_find_all() {
let items = vec![1, 2, 3, 4, 5, 6];
let evens = CollectionExt::find_all(&items, |x| *x % 2 == 0);
assert_eq!(evens, vec![&2, &4, &6]);
}
#[test]
fn test_find_all_none() {
let items = vec![1, 3, 5, 7];
let evens = CollectionExt::find_all(&items, |x| *x % 2 == 0);
assert!(evens.is_empty());
}
}