Provide a high level wrapper for kuromoji.js.
- Promise based API
- Cache Layer
- Fetch the dictionary at once
- Return same tokens for same text
npm install kuromojin
📝 Require DecompressionStream supported browser
Export two API.
getTokenizer()returnPromisethat is resolved with kuromoji.js'stokenizerinstance.tokenize()returnPromisethat is resolved with analyzed tokens.
import {tokenize, getTokenizer} from "kuromojin";
getTokenizer().then(tokenizer => {
// kuromoji.js's `tokenizer` instance
});
tokenize(text).then(tokens => {
console.log(tokens)
/*
[ {
word_id: 509800, // 辞書内での単語ID
word_type: 'KNOWN', // 単語タイプ(辞書に登録されている単語ならKNOWN, 未知語ならUNKNOWN)
word_position: 1, // 単語の開始位置
surface_form: '黒文字', // 表層形
pos: '名詞', // 品詞
pos_detail_1: '一般', // 品詞細分類1
pos_detail_2: '*', // 品詞細分類2
pos_detail_3: '*', // 品詞細分類3
conjugated_type: '*', // 活用型
conjugated_form: '*', // 活用形
basic_form: '黒文字', // 基本形
reading: 'クロモジ', // 読み
pronunciation: 'クロモジ' // 発音
} ]
*/
});If window.kuromojin.dicPath is defined, kuromojin use it as default dict path.
import {getTokenizer} from "kuromojin";
// Affect all module that are used kuromojin.
window.kuromojin = {
dicPath: "https://cdn.jsdelivr.net/npm/kuromoji@0.1.2/dict"
};
// this `getTokenizer` function use "https://kuromojin.netlify.com/dict"
getTokenizer();
// ===
getTokenizer({dicPath: "https://cdn.jsdelivr.net/npm/kuromoji@0.1.2/dict"})📝 Test dictionary URL
- "https://cdn.jsdelivr.net/npm/kuromoji@0.1.2/dict"
- cdn dict for kuromoji.js
- https://kuromojin.netlify.com/dict/*.dat.gz
kuromojin v1.1.0 export tokenize as default function.
kuromojin v2.0.0 remove the default function.
import kuromojin from "kuromojin";
// kuromojin === tokenizeRecommended: use import {tokenize} from "kuromojin" instead of it
import {tokenize} from "kuromojin";kuromojin pin kuromoji's version.
It aim to dedupe kuromoji's dictionary. The dictionary is large and avoid to duplicated dictionary.
npm test
- Fork it!
- Create your feature branch:
git checkout -b my-new-feature - Commit your changes:
git commit -am 'Add some feature' - Push to the branch:
git push origin my-new-feature - Submit a pull request :D
MIT