unicode_reader

文档

包装字节读取器并提供以 Unicode 代码点或字符群形式输出的适配器。

与其它以字符串为工作对象的 Unicode 解析器（例如，unicode_segmentation，此项目基于此构建）不同，这个crate在流上工作，不需要将整个数据读入内存。相反，它在读取的同时输出字符或代码点。

extern crate unicode_reader;
use unicode_reader::Graphemes;

use std::io::Cursor;

fn main() {
    let input = Cursor::new("He\u{302}\u{320}llo");
    let mut graphemes = Graphemes::from(input);
    assert_eq!("H",                 graphemes.next().unwrap().unwrap());
    assert_eq!("e\u{302}\u{320}",   graphemes.next().unwrap().unwrap()); // note 3 characters
    assert_eq!("l",                 graphemes.next().unwrap().unwrap());
    assert_eq!("l",                 graphemes.next().unwrap().unwrap());
    assert_eq!("o",                 graphemes.next().unwrap().unwrap());
    assert!(graphemes.next().is_none());

    let greek_bytes = vec![0xCE, 0xA7, 0xCE, 0xB1, 0xCE, 0xAF, 0xCF, 0x81, 0xCE, 0xB5,
                           0xCF, 0x84, 0xCE, 0xB5];
    let mut codepoints = CodePoints::from(Cursor::new(greek_bytes));
    assert_eq!(vec!['Χ', 'α', 'ί', 'ρ', 'ε', 'τ', 'ε'],
                codepoints.map(|r| r.unwrap())
                          .collect::<Vec<char>>());
}