String Normalization

Abstract

This page is NOT about UTF-8 string normalization but making a string more friendly for Natural Language Processing algorithms and specially deals with accentued characters and ligatures in Latin UTF-8 blocks.

Normalize php function

Description

This function "normalize" a string replacing accentued characters and ligatures according to the Normalizing Table. It replace all non alpha characters by space.

<?php
function normalize($str)
{
	/** Use a static to decode json array only once*/
	static $replace = true;
	if($replace === true)
	{
		/*We use a version of the conversion array with lower case result*/
		$replace = json_decode('{"\u1e00":"a","\u1e01":"a","\u1e9a":"a","\u1ea0":"a","\u1ea1":"a","\u1ea2":"a","\u1ea3":"a","\u1ea4":"a","\u1ea5":"a","\u1ea6":"a","\u1ea7":"a","\u1ea8":"a","\u1ea9":"a","\u1eaa":"a","\u1eab":"a","\u1eac":"a","\u1ead":"a","\u1eae":"a","\u1eaf":"a","\u1eb0":"a","\u1eb1":"a","\u1eb2":"a","\u1eb3":"a","\u1eb4":"a","\u1eb5":"a","\u1eb6":"a","\u1eb7":"a","\u00c0":"a","\u00c1":"a","\u00c2":"a","\u00c3":"a","\u00c4":"a","\u00c5":"a","\u00e0":"a","\u00e1":"a","\u00e2":"a","\u00e3":"a","\u00e4":"a","\u00e5":"a","\u0100":"a","\u0101":"a","\u0102":"a","\u0103":"a","\u0104":"a","\u0105":"a","\u01cd":"a","\u01ce":"a","\u01de":"a","\u01df":"a","\u01e0":"a","\u01e1":"a","\u01fa":"a","\u01fb":"a","\u0200":"a","\u0201":"a","\u0202":"a","\u0203":"a","\u0226":"a","\u0227":"a","\u023a":"a","\u2c65":"a","\u2c6f":"a","\u0250":"a","\u1e02":"b","\u1e03":"b","\u1e04":"b","\u1e05":"b","\u1e06":"b","\u1e07":"b","\u0180":"b","\u0181":"b","\u0182":"b","\u0183":"b","\u0243":"b","\u0253":"b","\u1e08":"c","\u1e09":"c","\u00c7":"c","\u00e7":"c","\u0106":"c","\u0107":"c","\u0108":"c","\u0109":"c","\u010a":"c","\u010b":"c","\u010c":"c","\u010d":"c","\u0187":"c","\u0188":"c","\u023b":"c","\u023c":"c","\ua73e":"c","\ua73f":"c","\u0255":"c","\u1e0a":"d","\u1e0b":"d","\u1e0c":"d","\u1e0d":"d","\u1e0e":"d","\u1e0f":"d","\u1e10":"d","\u1e11":"d","\u1e12":"d","\u1e13":"d","\u010e":"d","\u010f":"d","\u0110":"d","\u0111":"d","\u0189":"d","\u018a":"d","\u018b":"d","\u018c":"d","\u01c5":"d","\u01f2":"d","\u0221":"d","\ua779":"d","\ua77a":"d","\u0256":"d","\u0257":"d","\u1e14":"e","\u1e15":"e","\u1e16":"e","\u1e17":"e","\u1e18":"e","\u1e19":"e","\u1e1a":"e","\u1e1b":"e","\u1e1c":"e","\u1e1d":"e","\u1eb8":"e","\u1eb9":"e","\u1eba":"e","\u1ebb":"e","\u1ebc":"e","\u1ebd":"e","\u1ebe":"e","\u1ebf":"e","\u1ec0":"e","\u1ec1":"e","\u1ec2":"e","\u1ec3":"e","\u1ec4":"e","\u1ec5":"e","\u1ec6":"e","\u1ec7":"e","\u00c8":"e","\u00c9":"e","\u00ca":"e","\u00cb":"e","\u00e8":"e","\u00e9":"e","\u00ea":"e","\u00eb":"e","\u0112":"e","\u0113":"e","\u0114":"e","\u0115":"e","\u0116":"e","\u0117":"e","\u0118":"e","\u0119":"e","\u011a":"e","\u011b":"e","\u018e":"e","\u0190":"e","\u01dd":"e","\u0204":"e","\u0205":"e","\u0206":"e","\u0207":"e","\u0228":"e","\u0229":"e","\u0246":"e","\u0247":"e","\u2c78":"e","\u0258":"e","\u025b":"e","\u025c":"e","\u025d":"e","\u025e":"e","\u029a":"e","\u1e1e":"f","\u1e1f":"f","\u0191":"f","\u0192":"f","\ua77b":"f","\ua77c":"f","\u1e20":"g","\u1e21":"g","\u011c":"g","\u011d":"g","\u011e":"g","\u011f":"g","\u0120":"g","\u0121":"g","\u0122":"g","\u0123":"g","\u0193":"g","\u01e4":"g","\u01e5":"g","\u01e6":"g","\u01e7":"g","\u01f4":"g","\u01f5":"g","\ua77d":"g","\ua77e":"g","\ua77f":"g","\ua7a0":"g","\ua7a1":"g","\u0260":"g","\u0261":"g","\u1e22":"h","\u1e23":"h","\u1e24":"h","\u1e25":"h","\u1e26":"h","\u1e27":"h","\u1e28":"h","\u1e29":"h","\u1e2a":"h","\u1e2b":"h","\u1e96":"h","\u0124":"h","\u0125":"h","\u0126":"h","\u0127":"h","\u021e":"h","\u021f":"h","\u2c67":"h","\u2c68":"h","\u2c75":"h","\u2c76":"h","\ua78d":"h","\u0265":"h","\u0266":"h","\u02ae":"h","\u02af":"h","\u1e2c":"i","\u1e2d":"i","\u1e2e":"i","\u1e2f":"i","\u1ec8":"i","\u1ec9":"i","\u1eca":"i","\u1ecb":"i","\u00cc":"i","\u00cd":"i","\u00ce":"i","\u00cf":"i","\u00ec":"i","\u00ed":"i","\u00ee":"i","\u00ef":"i","\u0128":"i","\u0129":"i","\u012a":"i","\u012b":"i","\u012c":"i","\u012d":"i","\u012e":"i","\u012f":"i","\u0130":"i","\u0131":"i","\u0197":"i","\u01cf":"i","\u01d0":"i","\u0208":"i","\u0209":"i","\u020a":"i","\u020b":"i","\u0268":"i","\u1e30":"k","\u1e31":"k","\u1e32":"k","\u1e33":"k","\u1e34":"k","\u1e35":"k","\u0136":"k","\u0137":"k","\u0198":"k","\u0199":"k","\u01e8":"k","\u01e9":"k","\u2c69":"k","\u2c6a":"k","\ua740":"k","\ua741":"k","\ua742":"k","\ua743":"k","\ua744":"k","\ua745":"k","\ua7a2":"k","\ua7a3":"k","\u029e":"k","\u1e36":"l","\u1e37":"l","\u1e38":"l","\u1e39":"l","\u1e3a":"l","\u1e3b":"l","\u1e3c":"l","\u1e3d":"l","\u0139":"l","\u013a":"l","\u013b":"l","\u013c":"l","\u013d":"l","\u013e":"l","\u013f":"l","\u0140":"l","\u0141":"l","\u0142":"l","\u019a":"l","\u01c8":"l","\u0234":"l","\u023d":"l","\u2c60":"l","\u2c61":"l","\u2c62":"l","\ua746":"l","\ua747":"l","\ua748":"l","\ua749":"l","\ua780":"l","\ua781":"l","\ua78e":"l","\u026b":"l","\u026c":"l","\u026d":"l","\u1e3e":"m","\u1e3f":"m","\u1e40":"m","\u1e41":"m","\u1e42":"m","\u1e43":"m","\u019c":"m","\u2c6e":"m","\u026f":"m","\u0270":"m","\u0271":"m","\u1e44":"n","\u1e45":"n","\u1e46":"n","\u1e47":"n","\u1e48":"n","\u1e49":"n","\u1e4a":"n","\u1e4b":"n","\u00d1":"n","\u00f1":"n","\u0143":"n","\u0144":"n","\u0145":"n","\u0146":"n","\u0147":"n","\u0148":"n","\u0149":"n","\u019d":"n","\u019e":"n","\u01cb":"n","\u01f8":"n","\u01f9":"n","\u0220":"n","\u0235":"n","\ua790":"n","\ua791":"n","\ua7a4":"n","\ua7a5":"n","\u0272":"n","\u0273":"n","\u1e4c":"o","\u1e4d":"o","\u1e4e":"o","\u1e4f":"o","\u1e50":"o","\u1e51":"o","\u1e52":"o","\u1e53":"o","\u1ecc":"o","\u1ecd":"o","\u1ece":"o","\u1ecf":"o","\u1ed0":"o","\u1ed1":"o","\u1ed2":"o","\u1ed3":"o","\u1ed4":"o","\u1ed5":"o","\u1ed6":"o","\u1ed7":"o","\u1ed8":"o","\u1ed9":"o","\u1eda":"o","\u1edb":"o","\u1edc":"o","\u1edd":"o","\u1ede":"o","\u1edf":"o","\u1ee0":"o","\u1ee1":"o","\u1ee2":"o","\u1ee3":"o","\u00d2":"o","\u00d3":"o","\u00d4":"o","\u00d5":"o","\u00d6":"o","\u00d8":"o","\u00f2":"o","\u00f3":"o","\u00f4":"o","\u00f5":"o","\u00f6":"o","\u00f8":"o","\u014c":"o","\u014d":"o","\u014e":"o","\u014f":"o","\u0150":"o","\u0151":"o","\u0186":"o","\u019f":"o","\u01a0":"o","\u01a1":"o","\u01d1":"o","\u01d2":"o","\u01ea":"o","\u01eb":"o","\u01ec":"o","\u01ed":"o","\u01fe":"o","\u01ff":"o","\u020c":"o","\u020d":"o","\u020e":"o","\u020f":"o","\u022a":"o","\u022b":"o","\u022c":"o","\u022d":"o","\u022e":"o","\u022f":"o","\u0230":"o","\u0231":"o","\u2c7a":"o","\ua74a":"o","\ua74b":"o","\ua74c":"o","\ua74d":"o","\u0254":"o","\u0275":"o","\u1e54":"p","\u1e55":"p","\u1e56":"p","\u1e57":"p","\u01a4":"p","\u01a5":"p","\u2c63":"p","\ua750":"p","\ua751":"p","\ua752":"p","\ua753":"p","\ua754":"p","\ua755":"p","\u1e58":"r","\u1e59":"r","\u1e5a":"r","\u1e5b":"r","\u1e5c":"r","\u1e5d":"r","\u1e5e":"r","\u1e5f":"r","\u0154":"r","\u0155":"r","\u0156":"r","\u0157":"r","\u0158":"r","\u0159":"r","\u0210":"r","\u0211":"r","\u0212":"r","\u0213":"r","\u024c":"r","\u024d":"r","\u2c64":"r","\u2c79":"r","\ua75a":"r","\ua75b":"r","\ua782":"r","\ua783":"r","\ua7a6":"r","\ua7a7":"r","\u0279":"r","\u027a":"r","\u027b":"r","\u027c":"r","\u027d":"r","\u027e":"r","\u027f":"r","\u1e60":"s","\u1e61":"s","\u1e62":"s","\u1e63":"s","\u1e64":"s","\u1e65":"s","\u1e66":"s","\u1e67":"s","\u1e68":"s","\u1e69":"s","\u1e9b":"s","\u1e9c":"s","\u1e9d":"s","\u1e9e":"s","\u00df":"s","\u015a":"s","\u015b":"s","\u015c":"s","\u015d":"s","\u015e":"s","\u015f":"s","\u0160":"s","\u0161":"s","\u017f":"s","\u0218":"s","\u0219":"s","\u023f":"s","\u2c7e":"s","\ua784":"s","\ua785":"s","\ua7a8":"s","\ua7a9":"s","\u0282":"s","\u1e6a":"t","\u1e6b":"t","\u1e6c":"t","\u1e6d":"t","\u1e6e":"t","\u1e6f":"t","\u1e70":"t","\u1e71":"t","\u1e97":"t","\u0162":"t","\u0163":"t","\u0164":"t","\u0165":"t","\u0166":"t","\u0167":"t","\u01ab":"t","\u01ac":"t","\u01ad":"t","\u01ae":"t","\u021a":"t","\u021b":"t","\u0236":"t","\u023e":"t","\u2c66":"t","\ua786":"t","\ua787":"t","\u0287":"t","\u0288":"t","\u1e72":"u","\u1e73":"u","\u1e74":"u","\u1e75":"u","\u1e76":"u","\u1e77":"u","\u1e78":"u","\u1e79":"u","\u1e7a":"u","\u1e7b":"u","\u1ee4":"u","\u1ee5":"u","\u1ee6":"u","\u1ee7":"u","\u1ee8":"u","\u1ee9":"u","\u1eea":"u","\u1eeb":"u","\u1eec":"u","\u1eed":"u","\u1eee":"u","\u1eef":"u","\u1ef0":"u","\u1ef1":"u","\u00d9":"u","\u00da":"u","\u00db":"u","\u00dc":"u","\u00f9":"u","\u00fa":"u","\u00fb":"u","\u00fc":"u","\u0168":"u","\u0169":"u","\u016a":"u","\u016b":"u","\u016c":"u","\u016d":"u","\u016e":"u","\u016f":"u","\u0170":"u","\u0171":"u","\u0172":"u","\u0173":"u","\u01af":"u","\u01b0":"u","\u01d3":"u","\u01d4":"u","\u01d5":"u","\u01d6":"u","\u01d7":"u","\u01d8":"u","\u01d9":"u","\u01da":"u","\u01db":"u","\u01dc":"u","\u0214":"u","\u0215":"u","\u0216":"u","\u0217":"u","\u0244":"u","\u0289":"u","\u1e7c":"v","\u1e7d":"v","\u1e7e":"v","\u1e7f":"v","\u1efc":"v","\u1efd":"v","\u01b2":"v","\u0245":"v","\u2c71":"v","\u2c74":"v","\ua75e":"v","\ua75f":"v","\u028b":"v","\u028c":"v","\u1e80":"w","\u1e81":"w","\u1e82":"w","\u1e83":"w","\u1e84":"w","\u1e85":"w","\u1e86":"w","\u1e87":"w","\u1e88":"w","\u1e89":"w","\u1e98":"w","\u0174":"w","\u0175":"w","\u2c72":"w","\u2c73":"w","\u028d":"w","\u1e8a":"x","\u1e8b":"x","\u1e8c":"x","\u1e8d":"x","\u1e8e":"y","\u1e8f":"y","\u1e99":"y","\u1ef2":"y","\u1ef3":"y","\u1ef4":"y","\u1ef5":"y","\u1ef6":"y","\u1ef7":"y","\u1ef8":"y","\u1ef9":"y","\u1efe":"y","\u1eff":"y","\u00dd":"y","\u00fd":"y","\u00ff":"y","\u0176":"y","\u0177":"y","\u0178":"y","\u01b3":"y","\u01b4":"y","\u0232":"y","\u0233":"y","\u024e":"y","\u024f":"y","\u028e":"y","\u1e90":"z","\u1e91":"z","\u1e92":"z","\u1e93":"z","\u1e94":"z","\u1e95":"z","\u0179":"z","\u017a":"z","\u017b":"z","\u017c":"z","\u017d":"z","\u017e":"z","\u01b5":"z","\u01b6":"z","\u0224":"z","\u0225":"z","\u0240":"z","\u2c6b":"z","\u2c6c":"z","\u2c7f":"z","\ua762":"z","\ua763":"z","\u0290":"z","\u0291":"z","\u00c6":"ae","\u00e6":"ae","\u01e2":"ae","\u01e3":"ae","\u01fc":"ae","\u01fd":"ae","\u0132":"ij","\u0133":"ij","\u0134":"j","\u0135":"j","\u01f0":"j","\u0237":"j","\u0248":"j","\u0249":"j","\u025f":"j","\u0284":"j","\u029d":"j","\u0152":"oe","\u0153":"oe","\u0195":"hv","\u01a2":"oi","\u01a3":"oi","\u01c4":"dz","\u01c6":"dz","\u01f1":"dz","\u01f3":"dz","\u02a3":"dz","\u02a5":"dz","\u01c7":"lj","\u01c9":"lj","\u01ca":"nj","\u01cc":"nj","\u0238":"db","\u0239":"qp","\u024a":"q","\u024b":"q","\ua756":"q","\ua757":"q","\ua758":"q","\ua759":"q","\u02a0":"q","\ua728":"tz","\ua729":"tz","\ua732":"aa","\ua733":"aa","\ua734":"ao","\ua735":"ao","\ua736":"au","\ua737":"au","\ua738":"av","\ua739":"av","\ua73a":"av","\ua73b":"av","\ua73c":"ay","\ua73d":"ay","\ua74e":"oo","\ua74f":"oo","\ua760":"vy","\ua761":"vy","\ufb00":"ff","\ufb01":"fi","\ufb02":"fl","\ufb03":"ffi","\ufb04":"ffl","\ufb05":"st","\ufb06":"st"}',true);
	}
	/** Convert all characters with accents and ligatures é,ae,ij ...*/
	$str = strtr($str, $replace);
	/** Transform string to lower case*/
	$str = mb_strtolower($str, 'UTF-8');
	/** Set internal encoding to UTF-8*/
	mb_regex_encoding('UTF-8');
	/** Replace all non alpha with space */
	$str = mb_ereg_replace('[^0-9\p{L}]+', ' ', $str);
	/** We remove all the extra spaces*/
	$str = trim(preg_replace('~ {2,}+~', ' ',$str));
	return $str;
}
?>

Example

This example demonstrates the french developper nightmare when comparing string for NLP:

<?php
normalize('Qui vole un œuf vole un bœuf et tant va la cruche à l\'eau qu\'à la fin elle se brise')
?>

Output :

string 'qui vole un oeuf vole un boeuf et tant va la cruche a l eau qu a la fin elle se brise' (length=85)
?>
		

Normalizing Table

The following normalizing table is issued from the Latin unicode blocks :

• Latin-1 Supplement
• Latin Extended-A
• Latin Extended-B
• Latin Extended-C
• Latin Extended-D
• Latin Extended Additional
• IPA Extensions
• Alphabetic Presentation Forms

JSON Array

Here is the nornalizing table as an associative array (JSON format). Keys are characters to normalize and values are resulting characters.
{"\u1e00":"A","\u1e01":"a","\u1e9a":"a","\u1ea0":"A","\u1ea1":"a","\u1ea2":"A","\u1ea3":"a","\u1ea4":"A","\u1ea5":"a","\u1ea6":"A","\u1ea7":"a","\u1ea8":"A","\u1ea9":"a","\u1eaa":"A","\u1eab":"a","\u1eac":"A","\u1ead":"a","\u1eae":"A","\u1eaf":"a","\u1eb0":"A","\u1eb1":"a","\u1eb2":"A","\u1eb3":"a","\u1eb4":"A","\u1eb5":"a","\u1eb6":"A","\u1eb7":"a","\u00c0":"A","\u00c1":"A","\u00c2":"A","\u00c3":"A","\u00c4":"A","\u00c5":"A","\u00e0":"a","\u00e1":"a","\u00e2":"a","\u00e3":"a","\u00e4":"a","\u00e5":"a","\u0100":"A","\u0101":"a","\u0102":"A","\u0103":"a","\u0104":"A","\u0105":"a","\u01cd":"A","\u01ce":"a","\u01de":"A","\u01df":"a","\u01e0":"A","\u01e1":"a","\u01fa":"A","\u01fb":"a","\u0200":"A","\u0201":"a","\u0202":"A","\u0203":"a","\u0226":"A","\u0227":"a","\u023a":"A","\u2c65":"a","\u2c6f":"A","\u0250":"a","\ua732":"AA","\ua733":"aa","\u00c6":"AE","\u00e6":"ae","\u01e2":"AE","\u01e3":"ae","\u01fc":"AE","\u01fd":"ae","\ua734":"AO","\ua735":"ao","\ua736":"AU","\ua737":"au","\ua738":"AV","\ua739":"av","\ua73a":"AV","\ua73b":"av","\ua73c":"AY","\ua73d":"ay","\u1e02":"B","\u1e03":"b","\u1e04":"B","\u1e05":"b","\u1e06":"B","\u1e07":"b","\u0180":"b","\u0181":"B","\u0182":"B","\u0183":"b","\u0243":"B","\u0253":"b","\u1e08":"C","\u1e09":"c","\u00c7":"C","\u00e7":"c","\u0106":"C","\u0107":"c","\u0108":"C","\u0109":"c","\u010a":"C","\u010b":"c","\u010c":"C","\u010d":"c","\u0187":"C","\u0188":"c","\u023b":"C","\u023c":"c","\ua73e":"C","\ua73f":"c","\u0255":"c","\u1e0a":"D","\u1e0b":"d","\u1e0c":"D","\u1e0d":"d","\u1e0e":"D","\u1e0f":"d","\u1e10":"D","\u1e11":"d","\u1e12":"D","\u1e13":"d","\u010e":"D","\u010f":"d","\u0110":"D","\u0111":"d","\u0189":"D","\u018a":"D","\u018b":"D","\u018c":"d","\u01c5":"D","\u01f2":"D","\u0221":"d","\ua779":"D","\ua77a":"d","\u0256":"d","\u0257":"d","\u0238":"db","\u01c4":"DZ","\u01c6":"dz","\u01f1":"DZ","\u01f3":"dz","\u02a3":"dz","\u02a5":"dz","\u1e14":"E","\u1e15":"e","\u1e16":"E","\u1e17":"e","\u1e18":"E","\u1e19":"e","\u1e1a":"E","\u1e1b":"e","\u1e1c":"E","\u1e1d":"e","\u1eb8":"E","\u1eb9":"e","\u1eba":"E","\u1ebb":"e","\u1ebc":"E","\u1ebd":"e","\u1ebe":"E","\u1ebf":"e","\u1ec0":"E","\u1ec1":"e","\u1ec2":"E","\u1ec3":"e","\u1ec4":"E","\u1ec5":"e","\u1ec6":"E","\u1ec7":"e","\u00c8":"E","\u00c9":"E","\u00ca":"E","\u00cb":"E","\u00e8":"e","\u00e9":"e","\u00ea":"e","\u00eb":"e","\u0112":"E","\u0113":"e","\u0114":"E","\u0115":"e","\u0116":"E","\u0117":"e","\u0118":"E","\u0119":"e","\u011a":"E","\u011b":"e","\u018e":"E","\u0190":"E","\u01dd":"e","\u0204":"E","\u0205":"e","\u0206":"E","\u0207":"e","\u0228":"E","\u0229":"e","\u0246":"E","\u0247":"e","\u2c78":"e","\u0258":"e","\u025b":"e","\u025c":"e","\u025d":"e","\u025e":"e","\u029a":"e","\u1e1e":"F","\u1e1f":"f","\u0191":"F","\u0192":"f","\ua77b":"F","\ua77c":"f","\ufb00":"ff","\ufb03":"ffi","\ufb04":"ffl","\ufb01":"fi","\ufb02":"fl","\u1e20":"G","\u1e21":"g","\u011c":"G","\u011d":"g","\u011e":"G","\u011f":"g","\u0120":"G","\u0121":"g","\u0122":"G","\u0123":"g","\u0193":"G","\u01e4":"G","\u01e5":"g","\u01e6":"G","\u01e7":"g","\u01f4":"G","\u01f5":"g","\ua77d":"G","\ua77e":"G","\ua77f":"g","\ua7a0":"G","\ua7a1":"g","\u0260":"g","\u0261":"g","\u1e22":"H","\u1e23":"h","\u1e24":"H","\u1e25":"h","\u1e26":"H","\u1e27":"h","\u1e28":"H","\u1e29":"h","\u1e2a":"H","\u1e2b":"h","\u1e96":"h","\u0124":"H","\u0125":"h","\u0126":"H","\u0127":"h","\u021e":"H","\u021f":"h","\u2c67":"H","\u2c68":"h","\u2c75":"H","\u2c76":"h","\ua78d":"H","\u0265":"h","\u0266":"h","\u02ae":"h","\u02af":"h","\u0195":"hv","\u1e2c":"I","\u1e2d":"i","\u1e2e":"I","\u1e2f":"i","\u1ec8":"I","\u1ec9":"i","\u1eca":"I","\u1ecb":"i","\u00cc":"I","\u00cd":"I","\u00ce":"I","\u00cf":"I","\u00ec":"i","\u00ed":"i","\u00ee":"i","\u00ef":"i","\u0128":"I","\u0129":"i","\u012a":"I","\u012b":"i","\u012c":"I","\u012d":"i","\u012e":"I","\u012f":"i","\u0130":"I","\u0131":"i","\u0197":"I","\u01cf":"I","\u01d0":"i","\u0208":"I","\u0209":"i","\u020a":"I","\u020b":"i","\u0268":"i","\u0132":"IJ","\u0133":"ij","\u0134":"J","\u0135":"j","\u01f0":"j","\u0237":"j","\u0248":"J","\u0249":"j","\u025f":"j","\u0284":"j","\u029d":"j","\u1e30":"K","\u1e31":"k","\u1e32":"K","\u1e33":"k","\u1e34":"K","\u1e35":"k","\u0136":"K","\u0137":"k","\u0198":"K","\u0199":"k","\u01e8":"K","\u01e9":"k","\u2c69":"K","\u2c6a":"k","\ua740":"K","\ua741":"k","\ua742":"K","\ua743":"k","\ua744":"K","\ua745":"k","\ua7a2":"K","\ua7a3":"k","\u029e":"k","\u1e36":"L","\u1e37":"l","\u1e38":"L","\u1e39":"l","\u1e3a":"L","\u1e3b":"l","\u1e3c":"L","\u1e3d":"l","\u0139":"L","\u013a":"l","\u013b":"L","\u013c":"l","\u013d":"L","\u013e":"l","\u013f":"L","\u0140":"l","\u0141":"L","\u0142":"l","\u019a":"l","\u01c8":"L","\u0234":"l","\u023d":"L","\u2c60":"L","\u2c61":"l","\u2c62":"L","\ua746":"L","\ua747":"l","\ua748":"L","\ua749":"l","\ua780":"L","\ua781":"l","\ua78e":"l","\u026b":"l","\u026c":"l","\u026d":"l","\u01c7":"LJ","\u01c9":"lj","\u1e3e":"M","\u1e3f":"m","\u1e40":"M","\u1e41":"m","\u1e42":"M","\u1e43":"m","\u019c":"M","\u2c6e":"M","\u026f":"m","\u0270":"m","\u0271":"m","\u1e44":"N","\u1e45":"n","\u1e46":"N","\u1e47":"n","\u1e48":"N","\u1e49":"n","\u1e4a":"N","\u1e4b":"n","\u00d1":"N","\u00f1":"n","\u0143":"N","\u0144":"n","\u0145":"N","\u0146":"n","\u0147":"N","\u0148":"n","\u0149":"n","\u019d":"N","\u019e":"n","\u01cb":"N","\u01f8":"N","\u01f9":"n","\u0220":"N","\u0235":"n","\ua790":"N","\ua791":"n","\ua7a4":"N","\ua7a5":"n","\u0272":"n","\u0273":"n","\u01ca":"NJ","\u01cc":"nj","\u1e4c":"O","\u1e4d":"o","\u1e4e":"O","\u1e4f":"o","\u1e50":"O","\u1e51":"o","\u1e52":"O","\u1e53":"o","\u1ecc":"O","\u1ecd":"o","\u1ece":"O","\u1ecf":"o","\u1ed0":"O","\u1ed1":"o","\u1ed2":"O","\u1ed3":"o","\u1ed4":"O","\u1ed5":"o","\u1ed6":"O","\u1ed7":"o","\u1ed8":"O","\u1ed9":"o","\u1eda":"O","\u1edb":"o","\u1edc":"O","\u1edd":"o","\u1ede":"O","\u1edf":"o","\u1ee0":"O","\u1ee1":"o","\u1ee2":"O","\u1ee3":"o","\u00d2":"O","\u00d3":"O","\u00d4":"O","\u00d5":"O","\u00d6":"O","\u00d8":"O","\u00f2":"o","\u00f3":"o","\u00f4":"o","\u00f5":"o","\u00f6":"o","\u00f8":"o","\u014c":"O","\u014d":"o","\u014e":"O","\u014f":"o","\u0150":"O","\u0151":"o","\u0186":"O","\u019f":"O","\u01a0":"O","\u01a1":"o","\u01d1":"O","\u01d2":"o","\u01ea":"O","\u01eb":"o","\u01ec":"O","\u01ed":"o","\u01fe":"O","\u01ff":"o","\u020c":"O","\u020d":"o","\u020e":"O","\u020f":"o","\u022a":"O","\u022b":"o","\u022c":"O","\u022d":"o","\u022e":"O","\u022f":"o","\u0230":"O","\u0231":"o","\u2c7a":"o","\ua74a":"O","\ua74b":"o","\ua74c":"O","\ua74d":"o","\u0254":"o","\u0275":"o","\u0152":"OE","\u0153":"oe","\u01a2":"OI","\u01a3":"oi","\ua74e":"OO","\ua74f":"oo","\u1e54":"P","\u1e55":"p","\u1e56":"P","\u1e57":"p","\u01a4":"P","\u01a5":"p","\u2c63":"P","\ua750":"P","\ua751":"p","\ua752":"P","\ua753":"p","\ua754":"P","\ua755":"p","\u024a":"Q","\u024b":"q","\ua756":"Q","\ua757":"q","\ua758":"Q","\ua759":"q","\u02a0":"q","\u0239":"qp","\u1e58":"R","\u1e59":"r","\u1e5a":"R","\u1e5b":"r","\u1e5c":"R","\u1e5d":"r","\u1e5e":"R","\u1e5f":"r","\u0154":"R","\u0155":"r","\u0156":"R","\u0157":"r","\u0158":"R","\u0159":"r","\u0210":"R","\u0211":"r","\u0212":"R","\u0213":"r","\u024c":"R","\u024d":"r","\u2c64":"R","\u2c79":"r","\ua75a":"R","\ua75b":"r","\ua782":"R","\ua783":"r","\ua7a6":"R","\ua7a7":"r","\u0279":"r","\u027a":"r","\u027b":"r","\u027c":"r","\u027d":"r","\u027e":"r","\u027f":"r","\u1e60":"S","\u1e61":"s","\u1e62":"S","\u1e63":"s","\u1e64":"S","\u1e65":"s","\u1e66":"S","\u1e67":"s","\u1e68":"S","\u1e69":"s","\u1e9b":"s","\u1e9c":"s","\u1e9d":"s","\u1e9e":"S","\u00df":"s","\u015a":"S","\u015b":"s","\u015c":"S","\u015d":"s","\u015e":"S","\u015f":"s","\u0160":"S","\u0161":"s","\u017f":"s","\u0218":"S","\u0219":"s","\u023f":"s","\u2c7e":"S","\ua784":"S","\ua785":"s","\ua7a8":"S","\ua7a9":"s","\u0282":"s","\ufb05":"st","\ufb06":"st","\u1e6a":"T","\u1e6b":"t","\u1e6c":"T","\u1e6d":"t","\u1e6e":"T","\u1e6f":"t","\u1e70":"T","\u1e71":"t","\u1e97":"t","\u0162":"T","\u0163":"t","\u0164":"T","\u0165":"t","\u0166":"T","\u0167":"t","\u01ab":"t","\u01ac":"T","\u01ad":"t","\u01ae":"T","\u021a":"T","\u021b":"t","\u0236":"t","\u023e":"T","\u2c66":"t","\ua786":"T","\ua787":"t","\u0287":"t","\u0288":"t","\ua728":"TZ","\ua729":"tz","\u1e72":"U","\u1e73":"u","\u1e74":"U","\u1e75":"u","\u1e76":"U","\u1e77":"u","\u1e78":"U","\u1e79":"u","\u1e7a":"U","\u1e7b":"u","\u1ee4":"U","\u1ee5":"u","\u1ee6":"U","\u1ee7":"u","\u1ee8":"U","\u1ee9":"u","\u1eea":"U","\u1eeb":"u","\u1eec":"U","\u1eed":"u","\u1eee":"U","\u1eef":"u","\u1ef0":"U","\u1ef1":"u","\u00d9":"U","\u00da":"U","\u00db":"U","\u00dc":"U","\u00f9":"u","\u00fa":"u","\u00fb":"u","\u00fc":"u","\u0168":"U","\u0169":"u","\u016a":"U","\u016b":"u","\u016c":"U","\u016d":"u","\u016e":"U","\u016f":"u","\u0170":"U","\u0171":"u","\u0172":"U","\u0173":"u","\u01af":"U","\u01b0":"u","\u01d3":"U","\u01d4":"u","\u01d5":"U","\u01d6":"u","\u01d7":"U","\u01d8":"u","\u01d9":"U","\u01da":"u","\u01db":"U","\u01dc":"u","\u0214":"U","\u0215":"u","\u0216":"U","\u0217":"u","\u0244":"U","\u0289":"u","\u1e7c":"V","\u1e7d":"v","\u1e7e":"V","\u1e7f":"v","\u1efc":"V","\u1efd":"v","\u01b2":"V","\u0245":"V","\u2c71":"v","\u2c74":"v","\ua75e":"V","\ua75f":"v","\u028b":"v","\u028c":"v","\ua760":"VY","\ua761":"vy","\u1e80":"W","\u1e81":"w","\u1e82":"W","\u1e83":"w","\u1e84":"W","\u1e85":"w","\u1e86":"W","\u1e87":"w","\u1e88":"W","\u1e89":"w","\u1e98":"w","\u0174":"W","\u0175":"w","\u2c72":"W","\u2c73":"w","\u028d":"w","\u1e8a":"X","\u1e8b":"x","\u1e8c":"X","\u1e8d":"x","\u1e8e":"Y","\u1e8f":"y","\u1e99":"y","\u1ef2":"Y","\u1ef3":"y","\u1ef4":"Y","\u1ef5":"y","\u1ef6":"Y","\u1ef7":"y","\u1ef8":"Y","\u1ef9":"y","\u1efe":"Y","\u1eff":"y","\u00dd":"Y","\u00fd":"y","\u00ff":"y","\u0176":"Y","\u0177":"y","\u0178":"Y","\u01b3":"Y","\u01b4":"y","\u0232":"Y","\u0233":"y","\u024e":"Y","\u024f":"y","\u028e":"y","\u1e90":"Z","\u1e91":"z","\u1e92":"Z","\u1e93":"z","\u1e94":"Z","\u1e95":"z","\u0179":"Z","\u017a":"z","\u017b":"Z","\u017c":"z","\u017d":"Z","\u017e":"z","\u01b5":"Z","\u01b6":"z","\u0224":"Z","\u0225":"z","\u0240":"z","\u2c6b":"Z","\u2c6c":"z","\u2c7f":"Z","\ua762":"Z","\ua763":"z","\u0290":"z","\u0291":"z"}

Latin letter "A" normalized

Latin letter "AA" normalized

Latin letter "AE" normalized

Latin letter "AO" normalized

Latin letter "AU" normalized

Latin letter "AV" normalized

Latin letter "AY" normalized

Latin letter "B" normalized

Latin letter "C" normalized

Latin letter "D" normalized

Latin letter "DB" normalized

Latin letter "DZ" normalized

Latin letter "E" normalized

Latin letter "F" normalized

Latin letter "FF" normalized

Latin letter "FFI" normalized

Latin letter "FFL" normalized

Latin letter "FI" normalized

Latin letter "FL" normalized

Latin letter "G" normalized

Latin letter "H" normalized

Latin letter "HV" normalized

Latin letter "I" normalized

Latin letter "IJ" normalized

Latin letter "J" normalized

Latin letter "K" normalized

Latin letter "L" normalized

Latin letter "LJ" normalized

Latin letter "M" normalized

Latin letter "N" normalized

Latin letter "NJ" normalized

Latin letter "O" normalized

Latin letter "OE" normalized

Latin letter "OI" normalized

Latin letter "OO" normalized

Latin letter "P" normalized

Latin letter "Q" normalized

Latin letter "QP" normalized

Latin letter "R" normalized

Latin letter "S" normalized

Latin letter "S T" normalized

Latin letter "ST" normalized

Latin letter "T" normalized

Latin letter "TZ" normalized

Latin letter "U" normalized

Latin letter "V" normalized

Latin letter "VY" normalized

Latin letter "W" normalized

Latin letter "X" normalized

Latin letter "Y" normalized

Latin letter "Z" normalized