lodash/lodash.words/index.js

/**
 * lodash (Custom Build) <https://lodash.com/>
 * Build: `lodash modularize exports="npm" -o ./`
 * Copyright jQuery Foundation and other contributors <https://jquery.org/>
 * Released under MIT license <https://lodash.com/license>
 * Based on Underscore.js 1.8.3 <http://underscorejs.org/LICENSE>
 * Copyright Jeremy Ashkenas, DocumentCloud and Investigative Reporters & Editors
 */

/** Used as references for various `Number` constants. */
var INFINITY = 1 / 0;

/** `Object#toString` result references. */
var symbolTag = '[object Symbol]';

/** Used to match words composed of alphanumeric characters. */
var reAsciiWord = /[^\x00-\x2f\x3a-\x40\x5b-\x60\x7b-\x7f]+/g;

/** Used to compose unicode character classes. */
var rsAstralRange = '\\ud800-\\udfff',
    rsComboMarksRange = '\\u0300-\\u036f\\ufe20-\\ufe23',
    rsComboSymbolsRange = '\\u20d0-\\u20f0',
    rsDingbatRange = '\\u2700-\\u27bf',
    rsLowerRange = 'a-z\\xdf-\\xf6\\xf8-\\xff',
    rsMathOpRange = '\\xac\\xb1\\xd7\\xf7',
    rsNonCharRange = '\\x00-\\x2f\\x3a-\\x40\\x5b-\\x60\\x7b-\\xbf',
    rsPunctuationRange = '\\u2000-\\u206f',
    rsSpaceRange = ' \\t\\x0b\\f\\xa0\\ufeff\\n\\r\\u2028\\u2029\\u1680\\u180e\\u2000\\u2001\\u2002\\u2003\\u2004\\u2005\\u2006\\u2007\\u2008\\u2009\\u200a\\u202f\\u205f\\u3000',
    rsUpperRange = 'A-Z\\xc0-\\xd6\\xd8-\\xde',
    rsVarRange = '\\ufe0e\\ufe0f',
    rsBreakRange = rsMathOpRange + rsNonCharRange + rsPunctuationRange + rsSpaceRange;

/** Used to compose unicode capture groups. */
var rsApos = "['\u2019]",
    rsBreak = '[' + rsBreakRange + ']',
    rsCombo = '[' + rsComboMarksRange + rsComboSymbolsRange + ']',
    rsDigits = '\\d+',
    rsDingbat = '[' + rsDingbatRange + ']',
    rsLower = '[' + rsLowerRange + ']',
    rsMisc = '[^' + rsAstralRange + rsBreakRange + rsDigits + rsDingbatRange + rsLowerRange + rsUpperRange + ']',
    rsFitz = '\\ud83c[\\udffb-\\udfff]',
    rsModifier = '(?:' + rsCombo + '|' + rsFitz + ')',
    rsNonAstral = '[^' + rsAstralRange + ']',
    rsRegional = '(?:\\ud83c[\\udde6-\\uddff]){2}',
    rsSurrPair = '[\\ud800-\\udbff][\\udc00-\\udfff]',
    rsUpper = '[' + rsUpperRange + ']',
    rsZWJ = '\\u200d';

/** Used to compose unicode regexes. */
var rsLowerMisc = '(?:' + rsLower + '|' + rsMisc + ')',
    rsUpperMisc = '(?:' + rsUpper + '|' + rsMisc + ')',
    rsOptLowerContr = '(?:' + rsApos + '(?:d|ll|m|re|s|t|ve))?',
    rsOptUpperContr = '(?:' + rsApos + '(?:D|LL|M|RE|S|T|VE))?',
    reOptMod = rsModifier + '?',
    rsOptVar = '[' + rsVarRange + ']?',
    rsOptJoin = '(?:' + rsZWJ + '(?:' + [rsNonAstral, rsRegional, rsSurrPair].join('|') + ')' + rsOptVar + reOptMod + ')*',
    rsSeq = rsOptVar + reOptMod + rsOptJoin,
    rsEmoji = '(?:' + [rsDingbat, rsRegional, rsSurrPair].join('|') + ')' + rsSeq;

/** Used to match complex or compound words. */
var reUnicodeWord = RegExp([
  rsUpper + '?' + rsLower + '+' + rsOptLowerContr + '(?=' + [rsBreak, rsUpper, '$'].join('|') + ')',
  rsUpperMisc + '+' + rsOptUpperContr + '(?=' + [rsBreak, rsUpper + rsLowerMisc, '$'].join('|') + ')',
  rsUpper + '?' + rsLowerMisc + '+' + rsOptLowerContr,
  rsUpper + '+' + rsOptUpperContr,
  rsDigits,
  rsEmoji
].join('|'), 'g');

/** Used to detect strings that need a more robust regexp to match words. */
var reHasUnicodeWord = /[a-z][A-Z]|[A-Z]{2,}[a-z]|[0-9][a-zA-Z]|[a-zA-Z][0-9]|[^a-zA-Z0-9 ]/;

/** Detect free variable `global` from Node.js. */
var freeGlobal = typeof global == 'object' && global && global.Object === Object && global;

/** Detect free variable `self`. */
var freeSelf = typeof self == 'object' && self && self.Object === Object && self;

/** Used as a reference to the global object. */
var root = freeGlobal || freeSelf || Function('return this')();

/**
 * Splits an ASCII `string` into an array of its words.
 *
 * @private
 * @param {string} The string to inspect.
 * @returns {Array} Returns the words of `string`.
 */
function asciiWords(string) {
  return string.match(reAsciiWord) || [];
}

/**
 * Checks if `string` contains a word composed of Unicode symbols.
 *
 * @private
 * @param {string} string The string to inspect.
 * @returns {boolean} Returns `true` if a word is found, else `false`.
 */
function hasUnicodeWord(string) {
  return reHasUnicodeWord.test(string);
}

/**
 * Splits a Unicode `string` into an array of its words.
 *
 * @private
 * @param {string} The string to inspect.
 * @returns {Array} Returns the words of `string`.
 */
function unicodeWords(string) {
  return string.match(reUnicodeWord) || [];
}

/** Used for built-in method references. */
var objectProto = Object.prototype;

/**
 * Used to resolve the
 * [`toStringTag`](http://ecma-international.org/ecma-262/7.0/#sec-object.prototype.tostring)
 * of values.
 */
var objectToString = objectProto.toString;

/** Built-in value references. */
var Symbol = root.Symbol;

/** Used to convert symbols to primitives and strings. */
var symbolProto = Symbol ? Symbol.prototype : undefined,
    symbolToString = symbolProto ? symbolProto.toString : undefined;

/**
 * The base implementation of `_.toString` which doesn't convert nullish
 * values to empty strings.
 *
 * @private
 * @param {*} value The value to process.
 * @returns {string} Returns the string.
 */
function baseToString(value) {
  // Exit early for strings to avoid a performance hit in some environments.
  if (typeof value == 'string') {
    return value;
  }
  if (isSymbol(value)) {
    return symbolToString ? symbolToString.call(value) : '';
  }
  var result = (value + '');
  return (result == '0' && (1 / value) == -INFINITY) ? '-0' : result;
}

/**
 * Checks if `value` is object-like. A value is object-like if it's not `null`
 * and has a `typeof` result of "object".
 *
 * @static
 * @memberOf _
 * @since 4.0.0
 * @category Lang
 * @param {*} value The value to check.
 * @returns {boolean} Returns `true` if `value` is object-like, else `false`.
 * @example
 *
 * _.isObjectLike({});
 * // => true
 *
 * _.isObjectLike([1, 2, 3]);
 * // => true
 *
 * _.isObjectLike(_.noop);
 * // => false
 *
 * _.isObjectLike(null);
 * // => false
 */
function isObjectLike(value) {
  return !!value && typeof value == 'object';
}

/**
 * Checks if `value` is classified as a `Symbol` primitive or object.
 *
 * @static
 * @memberOf _
 * @since 4.0.0
 * @category Lang
 * @param {*} value The value to check.
 * @returns {boolean} Returns `true` if `value` is a symbol, else `false`.
 * @example
 *
 * _.isSymbol(Symbol.iterator);
 * // => true
 *
 * _.isSymbol('abc');
 * // => false
 */
function isSymbol(value) {
  return typeof value == 'symbol' ||
    (isObjectLike(value) && objectToString.call(value) == symbolTag);
}

/**
 * Converts `value` to a string. An empty string is returned for `null`
 * and `undefined` values. The sign of `-0` is preserved.
 *
 * @static
 * @memberOf _
 * @since 4.0.0
 * @category Lang
 * @param {*} value The value to process.
 * @returns {string} Returns the string.
 * @example
 *
 * _.toString(null);
 * // => ''
 *
 * _.toString(-0);
 * // => '-0'
 *
 * _.toString([1, 2, 3]);
 * // => '1,2,3'
 */
function toString(value) {
  return value == null ? '' : baseToString(value);
}

/**
 * Splits `string` into an array of its words.
 *
 * @static
 * @memberOf _
 * @since 3.0.0
 * @category String
 * @param {string} [string=''] The string to inspect.
 * @param {RegExp|string} [pattern] The pattern to match words.
 * @param- {Object} [guard] Enables use as an iteratee for methods like `_.map`.
 * @returns {Array} Returns the words of `string`.
 * @example
 *
 * _.words('fred, barney, & pebbles');
 * // => ['fred', 'barney', 'pebbles']
 *
 * _.words('fred, barney, & pebbles', /[^, ]+/g);
 * // => ['fred', 'barney', '&', 'pebbles']
 */
function words(string, pattern, guard) {
  string = toString(string);
  pattern = guard ? undefined : pattern;

  if (pattern === undefined) {
    return hasUnicodeWord(string) ? unicodeWords(string) : asciiWords(string);
  }
  return string.match(pattern) || [];
}

module.exports = words;