tinysegmenter 0.1.1

Compact Japanese tokenizer
Documentation
1
2
3
4
5
6
7
8
9
10
11
12
13
14
extern crate tinysegmenter;

#[test]
fn tokenize() {
  assert_eq!(
    tinysegmenter::tokenize("私の名前は中野です"),
    ["", "", "名前", "", "中野", "です"]);

  assert_eq!(
    tinysegmenter::tokenize("TinySegmenterは25kBで書かれています。"),
    ["TinySegmenter", "", "2", "5", "kB", "", "書か", "", "", "", "ます", ""]);

  assert_eq!(tinysegmenter::tokenize(""), [] as [&str; 0]);
}