node-nlp/lib/nlp/tokenizers/chinese-tokenizer.js

Library for NLU (Natural Language Understanding) done in Node.js

/*
 * Copyright (c) AXA Shared Services Spain S.A.
 *
 * Permission is hereby granted, free of charge, to any person obtaining
 * a copy of this software and associated documentation files (the
 * "Software"), to deal in the Software without restriction, including
 * without limitation the rights to use, copy, modify, merge, publish,
 * distribute, sublicense, and/or sell copies of the Software, and to
 * permit persons to whom the Software is furnished to do so, subject to
 * the following conditions:
 *
 * The above copyright notice and this permission notice shall be
 * included in all copies or substantial portions of the Software.
 *
 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
 * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
 * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
 * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
 * LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
 * OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
 * WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
 */
/* eslint-disable */
// istanbul ignore else
if (typeof window === "undefined") {
  const name = "novel-segment";
  const Segment = require(name);
  class ChineseTokenizer {
    constructor(settings) {
      this.settings = settings || {};
    }

    tokenize(text) {
      return ChineseTokenizer.segment.doSegment(text);
    }
  }

  ChineseTokenizer.segment = new Segment();
  ChineseTokenizer.segment.useDefault();
  module.exports = ChineseTokenizer;
} else {
  // istanbul ignore next
  class ChineseTokenizer {
    constructor(settings) {
      this.settings = settings || {};
    }

    tokenize(text) {
      return this.trim(text.split(/\W+/));
    }
  }
  // istanbul ignore next
  module.exports = ChineseTokenizer;
}