novel-segment
Version:
Chinese word segmentation 簡繁中文分词模块 以網路小說為樣本
35 lines (34 loc) • 1.18 kB
TypeScript
/**
* 通配符识别模块
*
* @author 老雷<leizongmin@gmail.com>
*/
import { SubSModuleTokenizer, ISubTokenizerCreate } from '../mod';
import { Segment, IWord, IDICT, IDICT2 } from '../Segment';
import { IWordDebugInfo } from '../util/index';
export declare class WildcardTokenizer extends SubSModuleTokenizer {
name: string;
protected _TABLE: IDICT<IWord>;
protected _TABLE2: IDICT2<IWord>;
_cache(): void;
/**
* 对未识别的单词进行分词
*
* @param {array} words 单词数组
* @return {array}
*/
split(words: IWord[]): IWord[];
createWildcardToken(word: IWord, lasttype?: number, attr?: IWordDebugInfo): Segment.IWord;
splitWildcard(text: string, cur?: number): IWord[];
/**
* 匹配单词，返回相关信息
*
* @param {string} text 文本
* @param {int} cur 开始位置
* @return {array} 返回格式 {w: '单词', c: 开始位置}
*/
matchWord(text: string, cur?: number): Segment.IWord[];
}
export declare const init: ISubTokenizerCreate<WildcardTokenizer, SubSModuleTokenizer>;
export declare const type = "tokenizer";
export default WildcardTokenizer;