Reducción Programáticos acento en JavaScript (también conocido como la normalización de texto o unaccenting)

Question

necesito para comparar 2 cadenas, como la igualdad como éstas:

== Lübeck Lübeck

En JavaScript.

¿Por qué? Bueno, tengo un campo auto-realización que va a un servicio de Java utilizando Lucene, donde los nombres de lugares se almacenan de forma natural (como Lübeck), sino también indexado como texto normalizado,

import sun.text.Normalizer; 
oDoc.setNameLC = Normalizer.normalize(oLocName, Normalizer.DECOMP, 0) 
    .toLowerCase().replaceAll("[^\\p{ASCII}]",""); 

De esta manera alguna, uno que no sabe escribir "Mèxico" puede escribir "mexico" y obtener una coincidencia que devuelve "Mèxico" (entre muchos otros posibles éxitos, como "Café Mèxico, Dubai, Emiratos Árabes Unidos").

Ahora la cosa es que no tengo la capacidad de cambiar el servicio para hacer cualquier resaltado en el lado del servidor, por lo tanto, me destaco en el cliente JavaScript lado con algo como:

return result.replace(input.replace(/[aeiou]/g,"."), "<b>$1</b>"); 

Es una un poco más elegante porque estoy escapando caracteres especiales de expresiones regulares en la entrada. Esto está bien para una sencilla palabra coincide en el comienzo de un éxito, pero en realidad se descompone si de repente desea apoyar varias palabras partidos como "café de Londres":

input = input.strip().toLowerCase(); //fyi prototype's strip is like trim 
re = new RegEx(input.replace(/[aeiou]/g,".").replace(/\s+/g,"|"),"gi"); 
return result.replace(re, "<b>$1</b>"); 

Esto no funciona para la opinión "london ca" (estaba escribiendo london cafe), porque marcaría "Jack London Cabin, Dawson City, Canada" como: "Ja<b>ck</b> <b>London</b> <b>ca</b>bin, Dawson <b>Ci</b>ty, <b>Ca<b/>nada" [tenga en cuenta "ck" y "Ci" en particular]

Por lo tanto, estoy un poco buscando algo que no es tan loco como:

input = input.strip().toLowerCase(); 
input = input.replace(/a/g,"[ÀàÁáÂâÃãÄäÅåÆæĀāĂ㥹]"); 
input = input.replace(/e/g,"[ÈèÉéÊêËëĒēĔĕĖėĘęĚě]"); 
// ditto for i, o, u, y, c, n, maybe also d, g, h, j, k, l, r, s, t, w, z 
re = new RegEx(input.replace(/\s+/g,"|"),"gi"); 
return result.replace(re, "<b>$1</b>"); 

¿Hay un compilado En la tabla me puedo referir a la asignación de un rango de caracteres que son versiones acentuadas de otro carácter a ese carácter, por lo que no me refiero al gráfico Unicode simple. Y si es así, ¿podría evitar el uso de declaraciones RegEx extrañas, posiblemente lentas?

Sobre la generosidad:
Antes de empezar una recompensa había dos respuestas, el que me apuntando a hacerlo en Ruby, y the one que MizzardX escribió que era un término de la forma básica que había puesto en mi pregunta. Ahora no me malinterpreten, realmente aprecio resolverlo tan completamente como él lo hizo, pero solo deseé que pudiera haber otra manera. Hasta ahora, parece que todos los que han pasado por aquí para ver la pregunta y la respuesta han decidido que MizzardX lo cubre muy bien, o que no tienen un enfoque diferente. Me interesaría un enfoque diferente, y si simplemente no está disponible antes de que se cierre la recompensa, MizzardX ganará la recompensa (aunque en un giro cruel, sus ediciones fueron una respuesta wiki de la comunidad, así que no estoy seguro si ¡obtendrá la recompensa!)

Answer 1

/** 
* Creates a RegExp that matches the words in the search string. 
* Case and accent insensitive. 
*/ 
function make_pattern(search_string) { 
    // escape meta characters 
    search_string = search_string.replace(/([|()[{.+*?^$\\])/g,"\\$1"); 

    // split into words 
    var words = search_string.split(/\s+/); 

    // sort by length 
    var length_comp = function (a,b) { 
     return b.length - a.length; 
    }; 
    words.sort(length_comp); 

    // replace characters by their compositors 
    var accent_replacer = function(chr) { 
     return accented[chr.toUpperCase()] || chr; 
    } 
    for (var i = 0; i < words.length; i++) { 
     words[i] = words[i].replace(/\S/g,accent_replacer); 
    } 

    // join as alternatives 
    var regexp = words.join("|"); 
    return new RegExp(regexp,'g'); 
} 

var accented = { 
    'A': '[Aa\xaa\xc0-\xc5\xe0-\xe5\u0100-\u0105\u01cd\u01ce\u0200-\u0203\u0226\u0227\u1d2c\u1d43\u1e00\u1e01\u1e9a\u1ea0-\u1ea3\u2090\u2100\u2101\u213b\u249c\u24b6\u24d0\u3371-\u3374\u3380-\u3384\u3388\u3389\u33a9-\u33af\u33c2\u33ca\u33df\u33ff\uff21\uff41]', 
    'B': '[Bb\u1d2e\u1d47\u1e02-\u1e07\u212c\u249d\u24b7\u24d1\u3374\u3385-\u3387\u33c3\u33c8\u33d4\u33dd\uff22\uff42]', 
    'C': '[Cc\xc7\xe7\u0106-\u010d\u1d9c\u2100\u2102\u2103\u2105\u2106\u212d\u216d\u217d\u249e\u24b8\u24d2\u3376\u3388\u3389\u339d\u33a0\u33a4\u33c4-\u33c7\uff23\uff43]', 
    'D': '[Dd\u010e\u010f\u01c4-\u01c6\u01f1-\u01f3\u1d30\u1d48\u1e0a-\u1e13\u2145\u2146\u216e\u217e\u249f\u24b9\u24d3\u32cf\u3372\u3377-\u3379\u3397\u33ad-\u33af\u33c5\u33c8\uff24\uff44]', 
    'E': '[Ee\xc8-\xcb\xe8-\xeb\u0112-\u011b\u0204-\u0207\u0228\u0229\u1d31\u1d49\u1e18-\u1e1b\u1eb8-\u1ebd\u2091\u2121\u212f\u2130\u2147\u24a0\u24ba\u24d4\u3250\u32cd\u32ce\uff25\uff45]', 
    'F': '[Ff\u1da0\u1e1e\u1e1f\u2109\u2131\u213b\u24a1\u24bb\u24d5\u338a-\u338c\u3399\ufb00-\ufb04\uff26\uff46]', 
    'G': '[Gg\u011c-\u0123\u01e6\u01e7\u01f4\u01f5\u1d33\u1d4d\u1e20\u1e21\u210a\u24a2\u24bc\u24d6\u32cc\u32cd\u3387\u338d-\u338f\u3393\u33ac\u33c6\u33c9\u33d2\u33ff\uff27\uff47]', 
    'H': '[Hh\u0124\u0125\u021e\u021f\u02b0\u1d34\u1e22-\u1e2b\u1e96\u210b-\u210e\u24a3\u24bd\u24d7\u32cc\u3371\u3390-\u3394\u33ca\u33cb\u33d7\uff28\uff48]', 
    'I': '[Ii\xcc-\xcf\xec-\xef\u0128-\u0130\u0132\u0133\u01cf\u01d0\u0208-\u020b\u1d35\u1d62\u1e2c\u1e2d\u1ec8-\u1ecb\u2071\u2110\u2111\u2139\u2148\u2160-\u2163\u2165-\u2168\u216a\u216b\u2170-\u2173\u2175-\u2178\u217a\u217b\u24a4\u24be\u24d8\u337a\u33cc\u33d5\ufb01\ufb03\uff29\uff49]', 
    'J': '[Jj\u0132-\u0135\u01c7-\u01cc\u01f0\u02b2\u1d36\u2149\u24a5\u24bf\u24d9\u2c7c\uff2a\uff4a]', 
    'K': '[Kk\u0136\u0137\u01e8\u01e9\u1d37\u1d4f\u1e30-\u1e35\u212a\u24a6\u24c0\u24da\u3384\u3385\u3389\u338f\u3391\u3398\u339e\u33a2\u33a6\u33aa\u33b8\u33be\u33c0\u33c6\u33cd-\u33cf\uff2b\uff4b]', 
    'L': '[Ll\u0139-\u0140\u01c7-\u01c9\u02e1\u1d38\u1e36\u1e37\u1e3a-\u1e3d\u2112\u2113\u2121\u216c\u217c\u24a7\u24c1\u24db\u32cf\u3388\u3389\u33d0-\u33d3\u33d5\u33d6\u33ff\ufb02\ufb04\uff2c\uff4c]', 
    'M': '[Mm\u1d39\u1d50\u1e3e-\u1e43\u2120\u2122\u2133\u216f\u217f\u24a8\u24c2\u24dc\u3377-\u3379\u3383\u3386\u338e\u3392\u3396\u3399-\u33a8\u33ab\u33b3\u33b7\u33b9\u33bd\u33bf\u33c1\u33c2\u33ce\u33d0\u33d4-\u33d6\u33d8\u33d9\u33de\u33df\uff2d\uff4d]', 
    'N': '[Nn\xd1\xf1\u0143-\u0149\u01ca-\u01cc\u01f8\u01f9\u1d3a\u1e44-\u1e4b\u207f\u2115\u2116\u24a9\u24c3\u24dd\u3381\u338b\u339a\u33b1\u33b5\u33bb\u33cc\u33d1\uff2e\uff4e]', 
    'O': '[Oo\xba\xd2-\xd6\xf2-\xf6\u014c-\u0151\u01a0\u01a1\u01d1\u01d2\u01ea\u01eb\u020c-\u020f\u022e\u022f\u1d3c\u1d52\u1ecc-\u1ecf\u2092\u2105\u2116\u2134\u24aa\u24c4\u24de\u3375\u33c7\u33d2\u33d6\uff2f\uff4f]', 
    'P': '[Pp\u1d3e\u1d56\u1e54-\u1e57\u2119\u24ab\u24c5\u24df\u3250\u3371\u3376\u3380\u338a\u33a9-\u33ac\u33b0\u33b4\u33ba\u33cb\u33d7-\u33da\uff30\uff50]', 
    'Q': '[Qq\u211a\u24ac\u24c6\u24e0\u33c3\uff31\uff51]', 
    'R': '[Rr\u0154-\u0159\u0210-\u0213\u02b3\u1d3f\u1d63\u1e58-\u1e5b\u1e5e\u1e5f\u20a8\u211b-\u211d\u24ad\u24c7\u24e1\u32cd\u3374\u33ad-\u33af\u33da\u33db\uff32\uff52]', 
    'S': '[Ss\u015a-\u0161\u017f\u0218\u0219\u02e2\u1e60-\u1e63\u20a8\u2101\u2120\u24ae\u24c8\u24e2\u33a7\u33a8\u33ae-\u33b3\u33db\u33dc\ufb06\uff33\uff53]', 
    'T': '[Tt\u0162-\u0165\u021a\u021b\u1d40\u1d57\u1e6a-\u1e71\u1e97\u2121\u2122\u24af\u24c9\u24e3\u3250\u32cf\u3394\u33cf\ufb05\ufb06\uff34\uff54]', 
    'U': '[Uu\xd9-\xdc\xf9-\xfc\u0168-\u0173\u01af\u01b0\u01d3\u01d4\u0214-\u0217\u1d41\u1d58\u1d64\u1e72-\u1e77\u1ee4-\u1ee7\u2106\u24b0\u24ca\u24e4\u3373\u337a\uff35\uff55]', 
    'V': '[Vv\u1d5b\u1d65\u1e7c-\u1e7f\u2163-\u2167\u2173-\u2177\u24b1\u24cb\u24e5\u2c7d\u32ce\u3375\u33b4-\u33b9\u33dc\u33de\uff36\uff56]', 
    'W': '[Ww\u0174\u0175\u02b7\u1d42\u1e80-\u1e89\u1e98\u24b2\u24cc\u24e6\u33ba-\u33bf\u33dd\uff37\uff57]', 
    'X': '[Xx\u02e3\u1e8a-\u1e8d\u2093\u213b\u2168-\u216b\u2178-\u217b\u24b3\u24cd\u24e7\u33d3\uff38\uff58]', 
    'Y': '[Yy\xdd\xfd\xff\u0176-\u0178\u0232\u0233\u02b8\u1e8e\u1e8f\u1e99\u1ef2-\u1ef9\u24b4\u24ce\u24e8\u33c9\uff39\uff59]', 
    'Z': '[Zz\u0179-\u017e\u01f1-\u01f3\u1dbb\u1e90-\u1e95\u2124\u2128\u24b5\u24cf\u24e9\u3390-\u3394\uff3a\uff5a]' 
}; 

Answer 2

Una versión más completa con soporte sensible a mayúsculas, ligaduras y otras cosas. Fuente original en: http://lehelk.com/2011/05/06/script-to-remove-diacritics/

var defaultDiacriticsRemovalMap = [ 
    {'base':'A', 'letters':/[\u0041\u24B6\uFF21\u00C0\u00C1\u00C2\u1EA6\u1EA4\u1EAA\u1EA8\u00C3\u0100\u0102\u1EB0\u1EAE\u1EB4\u1EB2\u0226\u01E0\u00C4\u01DE\u1EA2\u00C5\u01FA\u01CD\u0200\u0202\u1EA0\u1EAC\u1EB6\u1E00\u0104\u023A\u2C6F]/g}, 
    {'base':'AA','letters':/[\uA732]/g}, 
    {'base':'AE','letters':/[\u00C6\u01FC\u01E2]/g}, 
    {'base':'AO','letters':/[\uA734]/g}, 
    {'base':'AU','letters':/[\uA736]/g}, 
    {'base':'AV','letters':/[\uA738\uA73A]/g}, 
    {'base':'AY','letters':/[\uA73C]/g}, 
    {'base':'B', 'letters':/[\u0042\u24B7\uFF22\u1E02\u1E04\u1E06\u0243\u0182\u0181]/g}, 
    {'base':'C', 'letters':/[\u0043\u24B8\uFF23\u0106\u0108\u010A\u010C\u00C7\u1E08\u0187\u023B\uA73E]/g}, 
    {'base':'D', 'letters':/[\u0044\u24B9\uFF24\u1E0A\u010E\u1E0C\u1E10\u1E12\u1E0E\u0110\u018B\u018A\u0189\uA779]/g}, 
    {'base':'DZ','letters':/[\u01F1\u01C4]/g}, 
    {'base':'Dz','letters':/[\u01F2\u01C5]/g}, 
    {'base':'E', 'letters':/[\u0045\u24BA\uFF25\u00C8\u00C9\u00CA\u1EC0\u1EBE\u1EC4\u1EC2\u1EBC\u0112\u1E14\u1E16\u0114\u0116\u00CB\u1EBA\u011A\u0204\u0206\u1EB8\u1EC6\u0228\u1E1C\u0118\u1E18\u1E1A\u0190\u018E]/g}, 
    {'base':'F', 'letters':/[\u0046\u24BB\uFF26\u1E1E\u0191\uA77B]/g}, 
    {'base':'G', 'letters':/[\u0047\u24BC\uFF27\u01F4\u011C\u1E20\u011E\u0120\u01E6\u0122\u01E4\u0193\uA7A0\uA77D\uA77E]/g}, 
    {'base':'H', 'letters':/[\u0048\u24BD\uFF28\u0124\u1E22\u1E26\u021E\u1E24\u1E28\u1E2A\u0126\u2C67\u2C75\uA78D]/g}, 
    {'base':'I', 'letters':/[\u0049\u24BE\uFF29\u00CC\u00CD\u00CE\u0128\u012A\u012C\u0130\u00CF\u1E2E\u1EC8\u01CF\u0208\u020A\u1ECA\u012E\u1E2C\u0197]/g}, 
    {'base':'J', 'letters':/[\u004A\u24BF\uFF2A\u0134\u0248]/g}, 
    {'base':'K', 'letters':/[\u004B\u24C0\uFF2B\u1E30\u01E8\u1E32\u0136\u1E34\u0198\u2C69\uA740\uA742\uA744\uA7A2]/g}, 
    {'base':'L', 'letters':/[\u004C\u24C1\uFF2C\u013F\u0139\u013D\u1E36\u1E38\u013B\u1E3C\u1E3A\u0141\u023D\u2C62\u2C60\uA748\uA746\uA780]/g}, 
    {'base':'LJ','letters':/[\u01C7]/g}, 
    {'base':'Lj','letters':/[\u01C8]/g}, 
    {'base':'M', 'letters':/[\u004D\u24C2\uFF2D\u1E3E\u1E40\u1E42\u2C6E\u019C]/g}, 
    {'base':'N', 'letters':/[\u004E\u24C3\uFF2E\u01F8\u0143\u00D1\u1E44\u0147\u1E46\u0145\u1E4A\u1E48\u0220\u019D\uA790\uA7A4]/g}, 
    {'base':'NJ','letters':/[\u01CA]/g}, 
    {'base':'Nj','letters':/[\u01CB]/g}, 
    {'base':'O', 'letters':/[\u004F\u24C4\uFF2F\u00D2\u00D3\u00D4\u1ED2\u1ED0\u1ED6\u1ED4\u00D5\u1E4C\u022C\u1E4E\u014C\u1E50\u1E52\u014E\u022E\u0230\u00D6\u022A\u1ECE\u0150\u01D1\u020C\u020E\u01A0\u1EDC\u1EDA\u1EE0\u1EDE\u1EE2\u1ECC\u1ED8\u01EA\u01EC\u00D8\u01FE\u0186\u019F\uA74A\uA74C]/g}, 
    {'base':'OI','letters':/[\u01A2]/g}, 
    {'base':'OO','letters':/[\uA74E]/g}, 
    {'base':'OU','letters':/[\u0222]/g}, 
    {'base':'P', 'letters':/[\u0050\u24C5\uFF30\u1E54\u1E56\u01A4\u2C63\uA750\uA752\uA754]/g}, 
    {'base':'Q', 'letters':/[\u0051\u24C6\uFF31\uA756\uA758\u024A]/g}, 
    {'base':'R', 'letters':/[\u0052\u24C7\uFF32\u0154\u1E58\u0158\u0210\u0212\u1E5A\u1E5C\u0156\u1E5E\u024C\u2C64\uA75A\uA7A6\uA782]/g}, 
    {'base':'S', 'letters':/[\u0053\u24C8\uFF33\u1E9E\u015A\u1E64\u015C\u1E60\u0160\u1E66\u1E62\u1E68\u0218\u015E\u2C7E\uA7A8\uA784]/g}, 
    {'base':'T', 'letters':/[\u0054\u24C9\uFF34\u1E6A\u0164\u1E6C\u021A\u0162\u1E70\u1E6E\u0166\u01AC\u01AE\u023E\uA786]/g}, 
    {'base':'TZ','letters':/[\uA728]/g}, 
    {'base':'U', 'letters':/[\u0055\u24CA\uFF35\u00D9\u00DA\u00DB\u0168\u1E78\u016A\u1E7A\u016C\u00DC\u01DB\u01D7\u01D5\u01D9\u1EE6\u016E\u0170\u01D3\u0214\u0216\u01AF\u1EEA\u1EE8\u1EEE\u1EEC\u1EF0\u1EE4\u1E72\u0172\u1E76\u1E74\u0244]/g}, 
    {'base':'V', 'letters':/[\u0056\u24CB\uFF36\u1E7C\u1E7E\u01B2\uA75E\u0245]/g}, 
    {'base':'VY','letters':/[\uA760]/g}, 
    {'base':'W', 'letters':/[\u0057\u24CC\uFF37\u1E80\u1E82\u0174\u1E86\u1E84\u1E88\u2C72]/g}, 
    {'base':'X', 'letters':/[\u0058\u24CD\uFF38\u1E8A\u1E8C]/g}, 
    {'base':'Y', 'letters':/[\u0059\u24CE\uFF39\u1EF2\u00DD\u0176\u1EF8\u0232\u1E8E\u0178\u1EF6\u1EF4\u01B3\u024E\u1EFE]/g}, 
    {'base':'Z', 'letters':/[\u005A\u24CF\uFF3A\u0179\u1E90\u017B\u017D\u1E92\u1E94\u01B5\u0224\u2C7F\u2C6B\uA762]/g}, 
    {'base':'a', 'letters':/[\u0061\u24D0\uFF41\u1E9A\u00E0\u00E1\u00E2\u1EA7\u1EA5\u1EAB\u1EA9\u00E3\u0101\u0103\u1EB1\u1EAF\u1EB5\u1EB3\u0227\u01E1\u00E4\u01DF\u1EA3\u00E5\u01FB\u01CE\u0201\u0203\u1EA1\u1EAD\u1EB7\u1E01\u0105\u2C65\u0250]/g}, 
    {'base':'aa','letters':/[\uA733]/g}, 
    {'base':'ae','letters':/[\u00E6\u01FD\u01E3]/g}, 
    {'base':'ao','letters':/[\uA735]/g}, 
    {'base':'au','letters':/[\uA737]/g}, 
    {'base':'av','letters':/[\uA739\uA73B]/g}, 
    {'base':'ay','letters':/[\uA73D]/g}, 
    {'base':'b', 'letters':/[\u0062\u24D1\uFF42\u1E03\u1E05\u1E07\u0180\u0183\u0253]/g}, 
    {'base':'c', 'letters':/[\u0063\u24D2\uFF43\u0107\u0109\u010B\u010D\u00E7\u1E09\u0188\u023C\uA73F\u2184]/g}, 
    {'base':'d', 'letters':/[\u0064\u24D3\uFF44\u1E0B\u010F\u1E0D\u1E11\u1E13\u1E0F\u0111\u018C\u0256\u0257\uA77A]/g}, 
    {'base':'dz','letters':/[\u01F3\u01C6]/g}, 
    {'base':'e', 'letters':/[\u0065\u24D4\uFF45\u00E8\u00E9\u00EA\u1EC1\u1EBF\u1EC5\u1EC3\u1EBD\u0113\u1E15\u1E17\u0115\u0117\u00EB\u1EBB\u011B\u0205\u0207\u1EB9\u1EC7\u0229\u1E1D\u0119\u1E19\u1E1B\u0247\u025B\u01DD]/g}, 
    {'base':'f', 'letters':/[\u0066\u24D5\uFF46\u1E1F\u0192\uA77C]/g}, 
    {'base':'g', 'letters':/[\u0067\u24D6\uFF47\u01F5\u011D\u1E21\u011F\u0121\u01E7\u0123\u01E5\u0260\uA7A1\u1D79\uA77F]/g}, 
    {'base':'h', 'letters':/[\u0068\u24D7\uFF48\u0125\u1E23\u1E27\u021F\u1E25\u1E29\u1E2B\u1E96\u0127\u2C68\u2C76\u0265]/g}, 
    {'base':'hv','letters':/[\u0195]/g}, 
    {'base':'i', 'letters':/[\u0069\u24D8\uFF49\u00EC\u00ED\u00EE\u0129\u012B\u012D\u00EF\u1E2F\u1EC9\u01D0\u0209\u020B\u1ECB\u012F\u1E2D\u0268\u0131]/g}, 
    {'base':'j', 'letters':/[\u006A\u24D9\uFF4A\u0135\u01F0\u0249]/g}, 
    {'base':'k', 'letters':/[\u006B\u24DA\uFF4B\u1E31\u01E9\u1E33\u0137\u1E35\u0199\u2C6A\uA741\uA743\uA745\uA7A3]/g}, 
    {'base':'l', 'letters':/[\u006C\u24DB\uFF4C\u0140\u013A\u013E\u1E37\u1E39\u013C\u1E3D\u1E3B\u017F\u0142\u019A\u026B\u2C61\uA749\uA781\uA747]/g}, 
    {'base':'lj','letters':/[\u01C9]/g}, 
    {'base':'m', 'letters':/[\u006D\u24DC\uFF4D\u1E3F\u1E41\u1E43\u0271\u026F]/g}, 
    {'base':'n', 'letters':/[\u006E\u24DD\uFF4E\u01F9\u0144\u00F1\u1E45\u0148\u1E47\u0146\u1E4B\u1E49\u019E\u0272\u0149\uA791\uA7A5]/g}, 
    {'base':'nj','letters':/[\u01CC]/g}, 
    {'base':'o', 'letters':/[\u006F\u24DE\uFF4F\u00F2\u00F3\u00F4\u1ED3\u1ED1\u1ED7\u1ED5\u00F5\u1E4D\u022D\u1E4F\u014D\u1E51\u1E53\u014F\u022F\u0231\u00F6\u022B\u1ECF\u0151\u01D2\u020D\u020F\u01A1\u1EDD\u1EDB\u1EE1\u1EDF\u1EE3\u1ECD\u1ED9\u01EB\u01ED\u00F8\u01FF\u0254\uA74B\uA74D\u0275]/g}, 
    {'base':'oi','letters':/[\u01A3]/g}, 
    {'base':'ou','letters':/[\u0223]/g}, 
    {'base':'oo','letters':/[\uA74F]/g}, 
    {'base':'p','letters':/[\u0070\u24DF\uFF50\u1E55\u1E57\u01A5\u1D7D\uA751\uA753\uA755]/g}, 
    {'base':'q','letters':/[\u0071\u24E0\uFF51\u024B\uA757\uA759]/g}, 
    {'base':'r','letters':/[\u0072\u24E1\uFF52\u0155\u1E59\u0159\u0211\u0213\u1E5B\u1E5D\u0157\u1E5F\u024D\u027D\uA75B\uA7A7\uA783]/g}, 
    {'base':'s','letters':/[\u0073\u24E2\uFF53\u00DF\u015B\u1E65\u015D\u1E61\u0161\u1E67\u1E63\u1E69\u0219\u015F\u023F\uA7A9\uA785\u1E9B]/g}, 
    {'base':'t','letters':/[\u0074\u24E3\uFF54\u1E6B\u1E97\u0165\u1E6D\u021B\u0163\u1E71\u1E6F\u0167\u01AD\u0288\u2C66\uA787]/g}, 
    {'base':'tz','letters':/[\uA729]/g}, 
    {'base':'u','letters':/[\u0075\u24E4\uFF55\u00F9\u00FA\u00FB\u0169\u1E79\u016B\u1E7B\u016D\u00FC\u01DC\u01D8\u01D6\u01DA\u1EE7\u016F\u0171\u01D4\u0215\u0217\u01B0\u1EEB\u1EE9\u1EEF\u1EED\u1EF1\u1EE5\u1E73\u0173\u1E77\u1E75\u0289]/g}, 
    {'base':'v','letters':/[\u0076\u24E5\uFF56\u1E7D\u1E7F\u028B\uA75F\u028C]/g}, 
    {'base':'vy','letters':/[\uA761]/g}, 
    {'base':'w','letters':/[\u0077\u24E6\uFF57\u1E81\u1E83\u0175\u1E87\u1E85\u1E98\u1E89\u2C73]/g}, 
    {'base':'x','letters':/[\u0078\u24E7\uFF58\u1E8B\u1E8D]/g}, 
    {'base':'y','letters':/[\u0079\u24E8\uFF59\u1EF3\u00FD\u0177\u1EF9\u0233\u1E8F\u00FF\u1EF7\u1E99\u1EF5\u01B4\u024F\u1EFF]/g}, 
    {'base':'z','letters':/[\u007A\u24E9\uFF5A\u017A\u1E91\u017C\u017E\u1E93\u1E95\u01B6\u0225\u0240\u2C6C\uA763]/g} 
]; 
var changes; 
function removeDiacritics (str) { 
    if(!changes) { 
     changes = defaultDiacriticsRemovalMap; 
    } 
    for(var i=0; i<changes.length; i++) { 
     str = str.replace(changes[i].letters, changes[i].base); 
    } 
    return str; 
}