yoastseo/build/languageProcessing/helpers/word/matchWordInSentence.js

Yoast client-side content analysis

"use strict";

Object.defineProperty(exports, "__esModule", {
  value: true
});
exports.isWordInSentence = exports.default = exports.characterInBoundary = void 0;
var _wordBoundaries = _interopRequireDefault(require("../../../config/wordBoundaries.js"));
var _lodash = require("lodash");
var _addWordboundary = _interopRequireDefault(require("./addWordboundary.js"));
function _interopRequireDefault(e) { return e && e.__esModule ? e : { default: e }; }
const WORD_BOUNDARIES = new Set((0, _wordBoundaries.default)());

/**
 * Checks whether a character is present in the list of word boundaries.
 *
 * @param {string} character The character to look for.
 * @returns {boolean} Whether or not the character is present in the list of word boundaries.
 */
const characterInBoundary = function (character) {
  return WORD_BOUNDARIES.has(character);
};

/**
 * Checks whether a word is present in a sentence.
 *
 * @param {string} word The word to search for in the sentence.
 * @param {string} sentence The sentence to look through.
 * @returns {boolean} Whether or not the word is present in the sentence.
 */
exports.characterInBoundary = characterInBoundary;
const isWordInSentence = function (word, sentence) {
  // To ensure proper matching, make everything lowercase.
  word = word.toLocaleLowerCase();
  sentence = sentence.toLocaleLowerCase();

  // Escape regex in word, since we use regex characters like in abbreviations ("e.g.").
  const wordWithBoundaries = (0, _addWordboundary.default)((0, _lodash.escapeRegExp)(word));
  let occurrenceStart = sentence.search(new RegExp(wordWithBoundaries, "ig"));
  // Return false if no match has been found.
  if (occurrenceStart === -1) {
    return false;
  }
  /*
  If there is a word boundary before the matched word, the regex includes this word boundary in the match.
  This means that occurrenceStart is the index of the word boundary before the match. Therefore 1 has to
  be added to occurrenceStart, except when there is no word boundary before the match (i.e. at the start
  of a sentence).
   */
  if (occurrenceStart > 0) {
    occurrenceStart += 1;
  }
  const occurrenceEnd = occurrenceStart + word.length;

  // Check if the previous and next character are word boundaries to determine if a complete word was detected
  const previousCharacter = characterInBoundary(sentence[occurrenceStart - 1]) || occurrenceStart === 0;
  const nextCharacter = characterInBoundary(sentence[occurrenceEnd]) || occurrenceEnd === sentence.length;
  return previousCharacter && nextCharacter;
};
exports.isWordInSentence = isWordInSentence;
var _default = exports.default = {
  characterInBoundary,
  isWordInSentence
};
//# sourceMappingURL=matchWordInSentence.js.map