Files
lodash/lodash.deburr/index.js
2016-08-12 13:45:38 -07:00

69 lines
2.6 KiB
JavaScript

/**
* lodash 3.0.2 (Custom Build) <https://lodash.com/>
* Build: `lodash modern modularize exports="npm" -o ./`
* Copyright 2012-2015 The Dojo Foundation <http://dojofoundation.org/>
* Based on Underscore.js 1.8.3 <http://underscorejs.org/LICENSE>
* Copyright 2009-2015 Jeremy Ashkenas, DocumentCloud and Investigative Reporters & Editors
* Available under MIT license <https://lodash.com/license>
*/
var baseToString = require('lodash._basetostring');
/** Used to match [combining diacritical marks](https://en.wikipedia.org/wiki/Combining_Diacritical_Marks). */
var reComboMark = /[\u0300-\u036f\ufe20-\ufe23]/g;
/** Used to match latin-1 supplementary letters (excluding mathematical operators). */
var reLatin1 = /[\xc0-\xd6\xd8-\xde\xdf-\xf6\xf8-\xff]/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];
}
/**
* 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 = baseToString(string);
return string && string.replace(reLatin1, deburrLetter).replace(reComboMark, '');
}
module.exports = deburr;