标准化变音符是非常有用的

    const { normalize } = require('normalize-diacritics');
     
    /** Assuming top-level await is enabled... */
    await normalize('söme stüff with áccènts'); // 'some stuff with accents'

新RegExp的格式为

RegExp(something, 'modifiers');

所以你会想

accentsTidy = function(s){
                        var r=s.toLowerCase();
                        r = r.replace(new RegExp("\\s", 'g'),"");
                        r = r.replace(new RegExp("[àáâãäå]", 'g'),"a");
                        r = r.replace(new RegExp("æ", 'g'),"ae");
                        r = r.replace(new RegExp("ç", 'g'),"c");
                        r = r.replace(new RegExp("[èéêë]", 'g'),"e");
                        r = r.replace(new RegExp("[ìíîï]", 'g'),"i");
                        r = r.replace(new RegExp("ñ", 'g'),"n");                            
                        r = r.replace(new RegExp("[òóôõö]", 'g'),"o");
                        r = r.replace(new RegExp("œ", 'g'),"oe");
                        r = r.replace(new RegExp("[ùúûü]", 'g'),"u");
                        r = r.replace(new RegExp("[ýÿ]", 'g'),"y");
                        r = r.replace(new RegExp("\\W", 'g'),"");
                        return r;
                };

在NPM中有一个包:latinize

这是解决这个问题的一个很好的方案。

我使用了string.js的latinise()方法，它可以让你这样做:

var output = S(input).latinise().toString();

你可以用多种方式创建正则表达式。使用新的regexp -构造函数:

var re = new RegExp("[a-z]", "ig") //(string pattern, string modifiers)

或者使用正则表达式文字表示法:

var re = /[a-z]/ig; // /pattern/modifiers

你把两者混在一起了。

谢谢大家 我使用这个版本并说明原因(因为我在开始时错过了这些解释，所以我试图帮助下一个读者，如果他和我一样无聊…)

备注:我想要一个高效的解决方案，所以:

只有一次regexp编译(如果需要) 每个字符串只扫描一个字符串 查找已翻译字符的有效方法 等等……

我的版本是: (里面没有新的技术技巧，只有一些精选的+解释)

makeSortString = (function() {
    var translate_re = /[¹²³áàâãäåaaaÀÁÂÃÄÅAAAÆccç©CCÇÐÐèéê?ëeeeeeÈÊË?EEEEE€gGiìíîïìiiiÌÍÎÏ?ÌIIIlLnnñNNÑòóôõöoooøÒÓÔÕÖOOOØŒr®Ršs?ߊS?ùúûüuuuuÙÚÛÜUUUUýÿÝŸžzzŽZZ]/g;
    var translate = {
"¹":"1","²":"2","³":"3","á":"a","à":"a","â":"a","ã":"a","ä":"a","å":"a","a":"a","a":"a","a":"a","À":"a","Á":"a","Â":"a","Ã":"a","Ä":"a","Å":"a","A":"a","A":"a",
"A":"a","Æ":"a","c":"c","c":"c","ç":"c","©":"c","C":"c","C":"c","Ç":"c","Ð":"d","Ð":"d","è":"e","é":"e","ê":"e","?":"e","ë":"e","e":"e","e":"e","e":"e","e":"e",
"e":"e","È":"e","Ê":"e","Ë":"e","?":"e","E":"e","E":"e","E":"e","E":"e","E":"e","€":"e","g":"g","G":"g","i":"i","ì":"i","í":"i","î":"i","ï":"i","ì":"i","i":"i",
"i":"i","i":"i","Ì":"i","Í":"i","Î":"i","Ï":"i","?":"i","Ì":"i","I":"i","I":"i","I":"i","l":"l","L":"l","n":"n","n":"n","ñ":"n","N":"n","N":"n","Ñ":"n","ò":"o",
"ó":"o","ô":"o","õ":"o","ö":"o","o":"o","o":"o","o":"o","ø":"o","Ò":"o","Ó":"o","Ô":"o","Õ":"o","Ö":"o","O":"o","O":"o","O":"o","Ø":"o","Œ":"o","r":"r","®":"r",
"R":"r","š":"s","s":"s","?":"s","ß":"s","Š":"s","S":"s","?":"s","ù":"u","ú":"u","û":"u","ü":"u","u":"u","u":"u","u":"u","u":"u","Ù":"u","Ú":"u","Û":"u","Ü":"u",
"U":"u","U":"u","U":"u","U":"u","ý":"y","ÿ":"y","Ý":"y","Ÿ":"y","ž":"z","z":"z","z":"z","Ž":"z","Z":"z","Z":"z"
    };
    return function(s) {
        return(s.replace(translate_re, function(match){return translate[match];}) );
    }
})();

我是这样用的:

var without_accents = makeSortString("wïthêüÄTrèsBïgüeAk100t");
// I let you guess the result,
// no I was kidding you : I give you the result : witheuatresbigueak100t

评论:

Tthe instruction inside it is done once (after, makeSortString != undefined) function(){...} is stored once in makeSortString, so the "big" translate_re and translate objects are stored once When you call makeSortString('something') it call directly the inside function which calls only s.replace(...) : it is efficient s.replace uses regexp (the special syntax of var translate_re= .... is in fact equivalent to var translate_re = new RegExp("[¹....Z]","g"); but the compilation of the regexp is done once for all, and the scan of the s String is done one for a call of the function (not for every character as it would be in a loop) For each character found s.replace calls function(match) where parameter match contains the character found, and it call the corresponding translated character (translate[match]) Translate[match] is probably efficient too as the javascript translate object is probably implemented by javascript with a hashtab or something equivalent and allow the program to find the translated character almost directly and not for instance through a loop on a array of all characters to find the right one (which would be awfully unefficient).