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
|
use criterion::{black_box, criterion_group, criterion_main, Criterion};
use unicode_segmentation;
use std::fs;
use unicode_segmentation::UnicodeSegmentation;
fn graphemes(c: &mut Criterion, lang: &str, path: &str) {
let text = fs::read_to_string(path).unwrap();
c.bench_function(&format!("graphemes_{}", lang), |bench| {
bench.iter(|| {
for g in UnicodeSegmentation::graphemes(black_box(&*text), true) {
black_box(g);
}
})
});
}
fn graphemes_arabic(c: &mut Criterion) {
graphemes(c, "arabic", "benches/texts/arabic.txt");
}
fn graphemes_english(c: &mut Criterion) {
graphemes(c, "english", "benches/texts/english.txt");
}
fn graphemes_hindi(c: &mut Criterion) {
graphemes(c, "hindi", "benches/texts/hindi.txt");
}
fn graphemes_japanese(c: &mut Criterion) {
graphemes(c, "japanese", "benches/texts/japanese.txt");
}
fn graphemes_korean(c: &mut Criterion) {
graphemes(c, "korean", "benches/texts/korean.txt");
}
fn graphemes_mandarin(c: &mut Criterion) {
graphemes(c, "mandarin", "benches/texts/mandarin.txt");
}
fn graphemes_russian(c: &mut Criterion) {
graphemes(c, "russian", "benches/texts/russian.txt");
}
fn graphemes_source_code(c: &mut Criterion) {
graphemes(c, "source_code", "benches/texts/source_code.txt");
}
criterion_group!(
benches,
graphemes_arabic,
graphemes_english,
graphemes_hindi,
graphemes_japanese,
graphemes_korean,
graphemes_mandarin,
graphemes_russian,
graphemes_source_code,
);
criterion_main!(benches);
|
