lodash/lodash.deburr/index.js

/**
 * lodash 3.2.0 (Custom Build) <https://lodash.com/>
 * Build: `lodash modularize exports="npm" -o ./`
 * Copyright 2012-2016 The Dojo Foundation <http://dojofoundation.org/>
 * Based on Underscore.js 1.8.3 <http://underscorejs.org/LICENSE>
 * Copyright 2009-2016 Jeremy Ashkenas, DocumentCloud and Investigative Reporters & Editors
 * Available under MIT license <https://lodash.com/license>
 */
var root = require('lodash._root');

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

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

/** Used to match latin-1 supplementary letters (excluding mathematical operators). */
var reLatin1 = /[\xc0-\xd6\xd8-\xde\xdf-\xf6\xf8-\xff]/g;

/** Used to compose unicode character classes. */
var rsComboMarksRange = '\\u0300-\\u036f\\ufe20-\\ufe23',
    rsComboSymbolsRange = '\\u20d0-\\u20f0';

/** Used to compose unicode capture groups. */
var rsCombo = '[' + rsComboMarksRange + rsComboSymbolsRange + ']';

/**
 * Used to match [combining diacritical marks](https://en.wikipedia.org/wiki/Combining_Diacritical_Marks) and
 * [combining diacritical marks for symbols](https://en.wikipedia.org/wiki/Combining_Diacritical_Marks_for_Symbols).
 */
var reComboMark = RegExp(rsCombo, 'g');

/** Used to map latin-1 supplementary letters to basic latin letters. */
var deburredLetters = {
  '\xc0': 'A',  '\xc1': 'A', '\xc2': 'A', '\xc3': 'A', '\xc4': 'A', '\xc5': 'A',
  '\xe0': 'a',  '\xe1': 'a', '\xe2': 'a', '\xe3': 'a', '\xe4': 'a', '\xe5': 'a',
  '\xc7': 'C',  '\xe7': 'c',
  '\xd0': 'D',  '\xf0': 'd',
  '\xc8': 'E',  '\xc9': 'E', '\xca': 'E', '\xcb': 'E',
  '\xe8': 'e',  '\xe9': 'e', '\xea': 'e', '\xeb': 'e',
  '\xcC': 'I',  '\xcd': 'I', '\xce': 'I', '\xcf': 'I',
  '\xeC': 'i',  '\xed': 'i', '\xee': 'i', '\xef': 'i',
  '\xd1': 'N',  '\xf1': 'n',
  '\xd2': 'O',  '\xd3': 'O', '\xd4': 'O', '\xd5': 'O', '\xd6': 'O', '\xd8': 'O',
  '\xf2': 'o',  '\xf3': 'o', '\xf4': 'o', '\xf5': 'o', '\xf6': 'o', '\xf8': 'o',
  '\xd9': 'U',  '\xda': 'U', '\xdb': 'U', '\xdc': 'U',
  '\xf9': 'u',  '\xfa': 'u', '\xfb': 'u', '\xfc': 'u',
  '\xdd': 'Y',  '\xfd': 'y', '\xff': 'y',
  '\xc6': 'Ae', '\xe6': 'ae',
  '\xde': 'Th', '\xfe': 'th',
  '\xdf': 'ss'
};

/**
 * Used by `_.deburr` to convert latin-1 supplementary letters to basic latin letters.
 *
 * @private
 * @param {string} letter The matched letter to deburr.
 * @returns {string} Returns the deburred letter.
 */
function deburrLetter(letter) {
  return deburredLetters[letter];
}

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

/**
 * Used to resolve the [`toStringTag`](http://ecma-international.org/ecma-262/6.0/#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 = Symbol ? symbolProto.toString : undefined;

/**
 * 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 _
 * @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 _
 * @category Lang
 * @param {*} value The value to check.
 * @returns {boolean} Returns `true` if `value` is correctly classified, 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 if it's not one. An empty string is returned
 * for `null` and `undefined` values. The sign of `-0` is preserved.
 *
 * @static
 * @memberOf _
 * @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) {
  // Exit early for strings to avoid a performance hit in some environments.
  if (typeof value == 'string') {
    return value;
  }
  if (value == null) {
    return '';
  }
  if (isSymbol(value)) {
    return Symbol ? symbolToString.call(value) : '';
  }
  var result = (value + '');
  return (result == '0' && (1 / value) == -INFINITY) ? '-0' : result;
}

/**
 * Deburrs `string` by converting [latin-1 supplementary letters](https://en.wikipedia.org/wiki/Latin-1_Supplement_(Unicode_block)#Character_table)
 * to basic latin letters and removing [combining diacritical marks](https://en.wikipedia.org/wiki/Combining_Diacritical_Marks).
 *
 * @static
 * @memberOf _
 * @category String
 * @param {string} [string=''] The string to deburr.
 * @returns {string} Returns the deburred string.
 * @example
 *
 * _.deburr('déjà vu');
 * // => 'deja vu'
 */
function deburr(string) {
  string = toString(string);
  return string && string.replace(reLatin1, deburrLetter).replace(reComboMark, '');
}

module.exports = deburr;