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

这对我很有用。JavaScript,谷歌应用程序脚本,GAS

function normalizetext(text) {
  var weird = 'öüóőúéáàűíÖÜÓŐÚÉÁÀŰÍçÇ!@£$%^&*()_+?/*."';
var normalized = 'ouooueaauiOUOOUEAAUIcC                 ';
var idoff = -1,new_text = '';
var lentext = text.toString().length -1

for (i = 0; i <= lentext; i++) {
idoff = weird.search(text.charAt(i));
if (idoff == -1) {
new_text = new_text + text.charAt(i);
} else {
new_text = new_text + normalized.charAt(idoff);
}

}
return new_text;

}

其他回答

有很多这样的方法,但我认为这个方法简单且足够好:

 function remove_accents(strAccents) {
    var strAccents = strAccents.split('');
    var strAccentsOut = new Array();
    var strAccentsLen = strAccents.length;
    var accents =    "ÀÁÂÃÄÅàáâãäåÒÓÔÕÕÖØòóôõöøÈÉÊËèéêëÇçðÐÌÍÎÏìíîïÙÚÛÜùúûüÑñŠšŸÿýŽž";
    var accentsOut = "AAAAAAaaaaaaOOOOOOOooooooEEEEeeeeCcdDIIIIiiiiUUUUuuuuNnSsYyyZz";
    for (var y = 0; y < strAccentsLen; y++) {
        if (accents.indexOf(strAccents[y]) != -1) {
            strAccentsOut[y] = accentsOut.substr(accents.indexOf(strAccents[y]), 1);
        } else
            strAccentsOut[y] = strAccents[y];
    }
    strAccentsOut = strAccentsOut.join('');

    return strAccentsOut;
}

如果你还想删除特殊字符,并转换下划线中的空格和连字符,请执行以下操作:

string = remove_accents(string);
string = string.replace(/[^a-z0-9\s]/gi, '').replace(/[-\s]/g, '_');

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).

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;
                };

替换变音符的一种更简单的方法。

function replaceDiacritics(str){

  var diacritics = [
    {char: 'A', base: /[\300-\306]/g},
    {char: 'a', base: /[\340-\346]/g},
    {char: 'E', base: /[\310-\313]/g},
    {char: 'e', base: /[\350-\353]/g},
    {char: 'I', base: /[\314-\317]/g},
    {char: 'i', base: /[\354-\357]/g},
    {char: 'O', base: /[\322-\330]/g},
    {char: 'o', base: /[\362-\370]/g},
    {char: 'U', base: /[\331-\334]/g},
    {char: 'u', base: /[\371-\374]/g},
    {char: 'N', base: /[\321]/g},
    {char: 'n', base: /[\361]/g},
    {char: 'C', base: /[\307]/g},
    {char: 'c', base: /[\347]/g}
  ]

  diacritics.forEach(function(letter){
    str = str.replace(letter.base, letter.char);
  });

  return str;
};
$scope.legal_name = $sanitize($scope.legal_name);
    console.log("Name before function...",$scope.legal_name);

    var str = "";
    for(var i=0; i < $scope.legal_name.length; i++) {
        var charName = $scope.legal_name.charAt(i);
        if((charName == '&') && ($scope.legal_name.charAt(i + 1) == '#')){
            var count = 0;
            var subString = "";
            while(true) {
                if(($scope.legal_name.charCodeAt(i + 2 + count) > 47) && ($scope.legal_name.charCodeAt(i + 1 + count) < 58 )) {
                    subString = subString + $scope.legal_name.charAt(i + 2 + count);
                    count++;
                } else {
                    if(subString.length > 0) {
                        var value = parseInt(subString);
                        str = str + String.fromCharCode(value);
                        i = i + 1 + count; 
                        break;
                    }
                }
            }               
        } else {
            str = str + charName;
        }
    }
    $scope.legal_name = str;
    console.log("Name After function...",str);