Iterators which split strings on Grapheme Cluster or Word boundaries, according to the Unicode Standard Annex #29 rules.
use unicode_segmentation::UnicodeSegmentation;
fn main() {
let s = "a̐éö̲\r\n";
let g = UnicodeSegmentation::graphemes(s, true).collect::<Vec<&str>>();
let b: &[_] = &["a̐", "é", "ö̲", "\r\n"];
assert_eq!(g, b);
let s = "The quick (\"brown\") fox can't jump 32.3 feet, right?";
let w = s.unicode_words().collect::<Vec<&str>>();
let b: &[_] = &["The", "quick", "brown", "fox", "can't", "jump", "32.3", "feet", "right"];
assert_eq!(w, b);
let s = "The quick (\"brown\") fox";
let w = s.split_word_bounds().collect::<Vec<&str>>();
let b: &[_] = &["The", " ", "quick", " ", "(", "\"", "brown", "\"", ")", " ", " ", "fox"];
assert_eq!(w, b);
}unicode-segmentation does not depend on libstd, so it can be used in crates
with the #![no_std] attribute.
You can use this package in your project by adding the following
to your Cargo.toml:
[dependencies]
unicode-segmentation = "1.3.0"- New
GraphemeCursorAPI allows random access and bidirectional iteration. - Fixed incorrect splitting of certain emoji modifier sequences.
- Add
as_strmethods to the iterator types.
- Code cleanup and additional tests.
- Fix a bug affecting some grapheme clusters containing Prepend characters.
- Upgrade to Unicode 9.0.0.