phpjs/functions/strings/str_word_count.js

php.js offers community built php functions in javascript

function str_word_count(str, format, charlist) {
  // From: http://phpjs.org/functions
  // +   original by: Ole Vrijenhoek
  // +   bugfixed by: Kevin van Zonneveld (http://kevin.vanzonneveld.net)
  // +   bugfixed by: Brett Zamir (http://brett-zamir.me)
  // +   input by: Bug?
  // +   bugfixed by: Brett Zamir (http://brett-zamir.me)
  // +   improved by: Brett Zamir (http://brett-zamir.me)
  // -   depends on: ctype_alpha
  // *     example 1: str_word_count("Hello fri3nd, you're\r\n       looking          good today!", 1);
  // *     returns 1: ['Hello', 'fri', 'nd', "you're", 'looking', 'good', 'today']
  // *     example 2: str_word_count("Hello fri3nd, you're\r\n       looking          good today!", 2);
  // *     returns 2: {0: 'Hello', 6: 'fri', 10: 'nd', 14: "you're", 29: 'looking', 46: 'good', 51: 'today'}
  // *     example 3: str_word_count("Hello fri3nd, you're\r\n       looking          good today!", 1, '\u00e0\u00e1\u00e3\u00e73');
  // *     returns 3: ['Hello', 'fri3nd', "you're", 'looking', 'good', 'today']

  var len = str.length,
      cl = charlist && charlist.length,
      chr = '',
      tmpStr = '',
      i = 0,
      c = '',
      wArr = [],
      wC = 0,
      assoc = {},
      aC = 0,
      reg = '',
      match = false;

  // BEGIN STATIC
  var _preg_quote = function(str) {
    return (str + '').replace(/([\\\.\+\*\?\[\^\]\$\(\)\{\}\=\!<>\|\:])/g, '\\$1');
  };
  _getWholeChar = function(str, i) { // Use for rare cases of non-BMP characters
    var code = str.charCodeAt(i);
    if (code < 0xD800 || code > 0xDFFF) {
      return str.charAt(i);
    }
    if (0xD800 <= code && code <= 0xDBFF) { // High surrogate (could change last hex to 0xDB7F to treat high private surrogates as single characters)
      if (str.length <= (i + 1)) {
        throw 'High surrogate without following low surrogate';
      }
      var next = str.charCodeAt(i + 1);
      if (0xDC00 > next || next > 0xDFFF) {
        throw 'High surrogate without following low surrogate';
      }
      return str.charAt(i) + str.charAt(i + 1);
    }
    // Low surrogate (0xDC00 <= code && code <= 0xDFFF)
    if (i === 0) {
      throw 'Low surrogate without preceding high surrogate';
    }
    var prev = str.charCodeAt(i - 1);
    if (0xD800 > prev || prev > 0xDBFF) { // (could change last hex to 0xDB7F to treat high private surrogates as single characters)
      throw 'Low surrogate without preceding high surrogate';
    }
    return false; // We can pass over low surrogates now as the second component in a pair which we have already processed
  };
  // END STATIC
  if (cl) {
    reg = '^(' + _preg_quote(_getWholeChar(charlist, 0));
    for (i = 1; i < cl; i++) {
      if ((chr = _getWholeChar(charlist, i)) === false) {
        continue;
      }
      reg += '|' + _preg_quote(chr);
    }
    reg += ')$';
    reg = new RegExp(reg);
  }

  for (i = 0; i < len; i++) {
    if ((c = _getWholeChar(str, i)) === false) {
      continue;
    }
    match = this.ctype_alpha(c) || (reg && c.search(reg) !== -1) || ((i !== 0 && i !== len - 1) && c === '-') || // No hyphen at beginning or end unless allowed in charlist (or locale)
        (i !== 0 && c === "'"); // No apostrophe at beginning unless allowed in charlist (or locale)
    if (match) {
      if (tmpStr === '' && format === 2) {
        aC = i;
      }
      tmpStr = tmpStr + c;
    }
    if (i === len - 1 || !match && tmpStr !== '') {
      if (format !== 2) {
        wArr[wArr.length] = tmpStr;
      } else {
        assoc[aC] = tmpStr;
      }
      tmpStr = '';
      wC++;
    }
  }

  if (!format) {
    return wC;
  } else if (format === 1) {
    return wArr;
  } else if (format === 2) {
    return assoc;
  }

  throw 'You have supplied an incorrect format';
}