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

100% Statements 5/5
66.67% Branches 2/3
100% Functions 2/2
100% Lines 5/5

Press n or j to go to the next uncovered block, b, p or k for the previous block.

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                                              55x       2x             2x         2x       55x  
/*
 * Copyright (c) AXA Group Operations 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 AggressiveTokenizerPl extends AggressiveTokenizer {
  clearText(text) {
    return text
      .replace(/[^a-zążśźęćńół0-9]/gi, ' ')
      .replace(/[\s\n]+/g, ' ')
      .trim();
  }
 
  tokenize(text, normalize = true) {
    const normalized = normalize
      ? this.clearText(text)
          .normalize('NFD')
          .replace(/[\u0300-\u036f]/g, '')
      : this.clearText(text);
    return this.clearEmptyString(normalized.split(' '));
  }
}
 
module.exports = AggressiveTokenizerPl;