Available on crate feature
tokenize
only.Expand description
Tokenizes the text. Splits input into array of strings separated by opinionated
TokenType
.
Example
use wana_kana::tokenize::*;
let empty: Vec<String> = vec![];
assert_eq!(tokenize(""), empty);
assert_eq!(tokenize("ふふフフ"), vec!["ふふ", "フフ"]);
assert_eq!(tokenize("感じ"), vec!["感", "じ"]);
assert_eq!(tokenize("私は悲しい"), vec!["私", "は", "悲", "しい"] );