8000 add benchmark · unicode-rs/unicode-segmentation@592d99d · GitHub
[go: up one dir, main page]
Skip to content

Commit 592d99d

Browse files
PSeitz-ddPSeitz-dd
committed
add benchmark
1 parent 9e3f88c commit 592d99d

File tree

5 files changed

+48
-5
lines changed

5 files changed

+48
-5
lines changed

‎Cargo.toml

Lines changed: 6 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -24,6 +24,7 @@ no_std = [] # This is a no-op, preserved for backward compatibility only.
2424
[dev-dependencies]
2525
quickcheck = "0.7"
2626
criterion = "0.5"
27+
proptest = "1.7.0"
2728

2829
[[bench]]
2930
name = "chars"
@@ -36,3 +37,8 @@ harness = false
3637
[[bench]]
3738
name = "word_bounds"
3839
harness = false
40+
41+
[[bench]]
42+
name = "unicode_word_indices"
43+
harness = false
44+

‎benches/chars.rs

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -41,15 +41,15 @@ fn bench_all(c: &mut Criterion) {
4141
for file in FILES {
4242
group.bench_with_input(
4343
BenchmarkId::new("grapheme", file),
44-
&fs::read_to_string(format!("benches/texts/{}.txt", file)).unwrap(),
44+
&fs::read_to_string(format!("benches/texts/{file}.txt")).unwrap(),
4545
|b, content| b.iter(|| grapheme(content)),
4646
);
4747
}
4848

4949
for file in FILES {
5050
group.bench_with_input(
5151
BenchmarkId::new("scalar", file),
52-
&fs::read_to_string(format!("benches/texts/{}.txt", file)).unwrap(),
52+
&fs::read_to_string(format!("benches/texts/{file}.txt")).unwrap(),
5353
|b, content| b.iter(|| scalar(content)),
5454
);
5555
}

‎benches/unicode_word_indices.rs

Lines changed: 37 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,37 @@
1+
use criterion::{black_box, criterion_group, criterion_main, BenchmarkId, Criterion};
2+
3+
use std::fs;
4+
use unicode_segmentation::UnicodeSegmentation;
5+
6+
const FILES: &[&str] = &[
7+
"log", //"arabic",
8+
"english",
9+
//"hindi",
10+
"japanese",
11+
//"korean",
12+
//"mandarin",
13+
//"russian",
14+
//"source_code",
15+
];
16+
17+
#[inline(always)]
18+
fn grapheme(text: &str) {
19+
for w in text.unicode_word_indices() {
20+
black_box(w);
21+
}
22+
}
23+
24+
fn bench_all(c: &mut Criterion) {
25+
let mut group = c.benchmark_group("unicode_word_indices");
26+
27+
for file in FILES {
28+
let input = fs::read_to_string(format!("benches/texts/{file}.txt")).unwrap();
29+
group.throughput(criterion::Throughput::Bytes(input.len() as u64));
30+
group.bench_with_input(BenchmarkId::from_parameter(file), &input, |b, content| {
31+
b.iter(|| grapheme(content))
32+
});
33+
}
34+
}
35+
36+
criterion_group!(benches, bench_all);
37+
criterion_main!(benches);

‎benches/word_bounds.rs

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -27,7 +27,7 @@ fn bench_all(c: &mut Criterion) {
2727
for file in FILES {
2828
group.bench_with_input(
2929
BenchmarkId::new("grapheme", file),
30-
&fs::read_to_string(format!("benches/texts/{}.txt", file)).unwrap(),
30+
&fs::read_to_string(format!("benches/texts/{file}.txt",)).unwrap(),
3131
|b, content| b.iter(|| grapheme(content)),
3232
);
3333
}

‎benches/words.rs

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -41,15 +41,15 @@ fn bench_all(c: &mut Criterion) {
4141
for file in FILES {
4242
group.bench_with_input(
4343
BenchmarkId::new("grapheme", file),
44-
&fs::read_to_string(format!("benches/texts/{}.txt", file)).unwrap(),
44+
&fs::read_to_string(format!("benches/texts/{file}.txt")).unwrap(),
4545
|b, content| b.iter(|| grapheme(content)),
4646
);
4747
}
4848

4949
for file in FILES {
5050
group.bench_with_input(
5151
BenchmarkId::new("scalar", file),
52-
&fs::read_to_string(format!("benches/texts/{}.txt", file)).unwrap(),
52+
&fs::read_to_string(format!("benches/texts/{file}.txt")).unwrap(),
5353
|b, content| b.iter(|| scalar(content)),
5454
);
5555
}

0 commit comments

Comments
 (0)
0