Movatterモバイル変換

[0]ホーム
URL:

Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly

 Sign up
Appearance settings

Add ascii fast path for unicode_word_indices and unicode_words#147

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to ourterms of service andprivacy statement. We’ll occasionally send you account related emails.

Already on GitHub?Sign in to your account

Merged
Manishearth merged 13 commits intounicode-rs:masterfromPSeitz:master
Jul 28, 2025
Merged
Show file tree
Hide file tree
Changes fromall commits
Commits
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 6 additions & 0 deletionsCargo.toml
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -24,6 +24,7 @@ no_std = [] # This is a no-op, preserved for backward compatibility only.
[dev-dependencies]
quickcheck = "0.7"
criterion = "0.5"
proptest = "1.7.0"

[[bench]]
name = "chars"
Expand All@@ -36,3 +37,8 @@ harness = false
[[bench]]
name = "word_bounds"
harness = false

[[bench]]
name = "unicode_word_indices"
harness = false

4 changes: 2 additions & 2 deletionsbenches/chars.rs
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -41,15 +41,15 @@ fn bench_all(c: &mut Criterion) {
for file in FILES {
group.bench_with_input(
BenchmarkId::new("grapheme", file),
&fs::read_to_string(format!("benches/texts/{}.txt", file)).unwrap(),
&fs::read_to_string(format!("benches/texts/{file}.txt")).unwrap(),
|b, content| b.iter(|| grapheme(content)),
);
}

for file in FILES {
group.bench_with_input(
BenchmarkId::new("scalar", file),
&fs::read_to_string(format!("benches/texts/{}.txt", file)).unwrap(),
&fs::read_to_string(format!("benches/texts/{file}.txt")).unwrap(),
|b, content| b.iter(|| scalar(content)),
);
}
Expand Down
1 change: 1 addition & 0 deletionsbenches/texts/log.txt
View file
Open in desktop
Original file line numberDiff line numberDiff line change
@@ -0,0 +1 @@
2018-07-12 13:59:01 UTC | ERROR | (worker.go:131 in process) | Too many errors for endpoint 'dummy/api/v1/check_run?api_key=*************************00000': retrying later
37 changes: 37 additions & 0 deletionsbenches/unicode_word_indices.rs
View file
Open in desktop
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,37 @@
use criterion::{black_box, criterion_group, criterion_main, BenchmarkId, Criterion};

use std::fs;
use unicode_segmentation::UnicodeSegmentation;

const FILES: &[&str] = &[
"log", //"arabic",
"english",
//"hindi",
"japanese",
//"korean",
//"mandarin",
//"russian",
//"source_code",
];

#[inline(always)]
fn grapheme(text: &str) {
for w in text.unicode_word_indices() {
black_box(w);
}
}

fn bench_all(c: &mut Criterion) {
let mut group = c.benchmark_group("unicode_word_indices");

for file in FILES {
let input = fs::read_to_string(format!("benches/texts/{file}.txt")).unwrap();
group.throughput(criterion::Throughput::Bytes(input.len() as u64));
group.bench_with_input(BenchmarkId::from_parameter(file), &input, |b, content| {
b.iter(|| grapheme(content))
});
}
}

criterion_group!(benches, bench_all);
criterion_main!(benches);
2 changes: 1 addition & 1 deletionbenches/word_bounds.rs
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -27,7 +27,7 @@ fn bench_all(c: &mut Criterion) {
for file in FILES {
group.bench_with_input(
BenchmarkId::new("grapheme", file),
&fs::read_to_string(format!("benches/texts/{}.txt", file)).unwrap(),
&fs::read_to_string(format!("benches/texts/{file}.txt",)).unwrap(),
|b, content| b.iter(|| grapheme(content)),
);
}
Expand Down
4 changes: 2 additions & 2 deletionsbenches/words.rs
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -41,15 +41,15 @@ fn bench_all(c: &mut Criterion) {
for file in FILES {
group.bench_with_input(
BenchmarkId::new("grapheme", file),
&fs::read_to_string(format!("benches/texts/{}.txt", file)).unwrap(),
&fs::read_to_string(format!("benches/texts/{file}.txt")).unwrap(),
|b, content| b.iter(|| grapheme(content)),
);
}

for file in FILES {
group.bench_with_input(
BenchmarkId::new("scalar", file),
&fs::read_to_string(format!("benches/texts/{}.txt", file)).unwrap(),
&fs::read_to_string(format!("benches/texts/{file}.txt")).unwrap(),
|b, content| b.iter(|| scalar(content)),
);
}
Expand Down
21 changes: 13 additions & 8 deletionssrc/lib.rs
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -56,11 +56,16 @@
)]
#![no_std]

#[cfg(test)]
extern crate std;

pub use grapheme::{GraphemeCursor, GraphemeIncomplete};
pub use grapheme::{GraphemeIndices, Graphemes};
pub use sentence::{USentenceBoundIndices, USentenceBounds, UnicodeSentences};
pub use tables::UNICODE_VERSION;
pub use word::{UWordBoundIndices, UWordBounds, UnicodeWordIndices, UnicodeWords};
pub use word::{UWordBoundIndices, UWordBounds};

use crate::word::{UnicodeWordIndices, UnicodeWords};

mod grapheme;
mod sentence;
Expand DownExpand Up@@ -248,7 +253,7 @@ pub trait UnicodeSegmentation {

impl UnicodeSegmentation for str {
#[inline]
fn graphemes(&self, is_extended: bool) -> Graphemes {
fn graphemes(&self, is_extended: bool) -> Graphemes<'_> {
grapheme::new_graphemes(self, is_extended)
}

Expand All@@ -258,32 +263,32 @@ impl UnicodeSegmentation for str {
}

#[inline]
fn unicode_words(&self) -> UnicodeWords {
fn unicode_words(&self) -> UnicodeWords<'_> {
word::new_unicode_words(self)
}

#[inline]
fn unicode_word_indices(&self) -> UnicodeWordIndices {
fn unicode_word_indices(&self) -> UnicodeWordIndices<'_> {
word::new_unicode_word_indices(self)
}

#[inline]
fn split_word_bounds(&self) -> UWordBounds {
fn split_word_bounds(&self) -> UWordBounds<'_> {
word::new_word_bounds(self)
}

#[inline]
fn split_word_bound_indices(&self) -> UWordBoundIndices {
fn split_word_bound_indices(&self) -> UWordBoundIndices<'_> {
word::new_word_bound_indices(self)
}

#[inline]
fn unicode_sentences(&self) -> UnicodeSentences {
fn unicode_sentences(&self) -> UnicodeSentences<'_> {
sentence::new_unicode_sentences(self)
}

#[inline]
fn split_sentence_bounds(&self) -> USentenceBounds {
fn split_sentence_bounds(&self) -> USentenceBounds<'_> {
sentence::new_sentence_bounds(self)
}

Expand Down
Loading
[8]ページ先頭
©2009-2025 Movatter.jp