如何从字符串中删除重音字符? 特别是在IE6中,我有这样的东西:

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;
};

但是IE6让我很烦,它好像不喜欢我的正则表达式。


当前回答

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'

其他回答


function removeAccents(strAccents){
    strAccents = strAccents.split('');
    strAccentsOut = new Array();
    strAccentsLen = strAccents.length;
    var accents = 'ÀÁÂÃÄÅàáâãäåÒÓÔÕÕÖØòóôõöøÈÉÊËèéêëðÇçÐÌÍÎÏìíîïÙÚÛÜùúûüÑñŠšŸÿýŽž';
    var accentsOut = ['A','A','A','A','A','A','a','a','a','a','a','a','O','O','O','O','O','O','O','o','o','o','o','o','o','E','E','E','E','e','e','e','e','e','C','c','D','I','I','I','I','i','i','i','i','U','U','U','U','u','u','u','u','N','n','S','s','Y','y','y','Z','z'];
    for (var y = 0; y < strAccentsLen; y++) {
        if (accents.indexOf(strAccents[y]) != -1) {
            strAccentsOut[y] = accentsOut[accents.indexOf(strAccents[y])];
        }
        else
            strAccentsOut[y] = strAccents[y];
    }
    strAccentsOut = strAccentsOut.join('');
    return strAccentsOut;
}

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。

我使用了string.js的latinise()方法,它可以让你这样做:

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

我发现所有这些都有点笨拙,而且我不太擅长正则表达式,所以这里有一个更简单的版本。将它翻译成你最喜欢的服务器端语言是很容易的,假设字符串已经在Unicode中:

// String containing replacement characters for stripping accents 
var stripstring = 
    'AAAAAAACEEEEIIII'+
    'DNOOOOO.OUUUUY..'+
    'aaaaaaaceeeeiiii'+
    'dnooooo.ouuuuy.y'+
    'AaAaAaCcCcCcCcDd'+
    'DdEeEeEeEeEeGgGg'+
    'GgGgHhHhIiIiIiIi'+
    'IiIiJjKkkLlLlLlL'+
    'lJlNnNnNnnNnOoOo'+
    'OoOoRrRrRrSsSsSs'+
    'SsTtTtTtUuUuUuUu'+
    'UuUuWwYyYZzZzZz.';

function stripaccents(str){
    var answer='';
    for(var i=0;i<str.length;i++){
        var ch=str[i];
        var chindex=ch.charCodeAt(0)-192;   // Index of character code in the strip string
        if(chindex>=0 && chindex<stripstring.length){
            // Character is within our table, so we can strip the accent...
            var outch=stripstring.charAt(chindex);
            // ...unless it was shown as a '.'
            if(outch!='.')ch=outch;
        }
        answer+=ch;
    }
    return answer;
}

您可以使用Lodash库中的_.deburr()方法。

它可以作为一个独立的NPM包lodash.deburr,也可以作为lodash包的一部分。

const myStringWithAccent = 'Mon café est plein de caféïne';
const myStringWithoutAccent = _.deburr( myStringWithAccent, );

结果就是:“我的咖啡里装满了咖啡因”