All files / lib/nlp/tokenizers aggressive-tokenizer-en.js

77.27% Statements 17/22
60% Branches 6/10
100% Functions 3/3
77.27% Lines 17/22
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76                                              42x       89x           89x               89x 89x 420x 420x     420x 420x 5x               5x 5x     415x       89x       89x 89x       42x  
/*
 * 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.
 */
 
const AggressiveTokenizer = require('./aggressive-tokenizer');
 
class AggressiveTokenizerEn extends AggressiveTokenizer {
  replaceContractions(arr) {
    const contractionsBase = {
      cannot: ['can', 'not'],
      gonna: ['going', 'to'],
      wanna: ['want', 'to'],
    };
 
    const contractions = {
      s: 'is',
      re: 'are',
      m: 'am',
      ve: 'have',
      d: 'had',
      t: 'not',
    };
    const result = [];
    arr.forEach(item => {
      const lowitem = item.toLowerCase();
      Iif (contractionsBase[lowitem]) {
        result.push(...contractionsBase[lowitem]);
      } else {
        const tokens = lowitem.split(/[^a-zA-Zá-úÁ-ÚñÑüÜ]+/);
        if (tokens.length === 2) {
          Iif (tokens[1] === 't') {
            if (tokens[0][tokens[0].length - 1] === 'n') {
              result.push(tokens[0].substring(0, tokens[0].length - 1));
              result.push('not');
            } else {
              result.push(item);
            }
          } else {
            result.push(tokens[0]);
            result.push(contractions[tokens[1]] || tokens[1]);
          }
        } else {
          result.push(item);
        }
      }
    });
    return result;
  }
 
  tokenize(text) {
    const arr = this.trim(text.split(/[^a-zA-Zá-úÁ-ÚñÑüÜ']+/));
    return this.replaceContractions(arr);
  }
}
 
module.exports = AggressiveTokenizerEn;