javascript - 将其他语言的数字更改为英文数字的正则表达式

Question

我想检查一个数字是否是阿拉伯数字，并将其所有数字替换为英文，以便我可以对其进行计算。我正在尝试这个 Function ，但我不知道什么正则表达式适合它:

function enNumber(num)
{
for (var i=0;i<10;i++)
num=num.replace(*[regular expression]*,i);
return num;}

Answer 1

所提出问题的最低解决方案

这应该可以解决您的要求:

function fromArabicToASCII(arabic) {
  return arabic.replace(
    /[\u0660-\u0669\u06F0-\u06F9]/g,
    function(a) {
      return String.fromCharCode((a.charCodeAt(0)&15)+48);
    }
  );
};

Unicode 类 Nd(数字、十进制数字)中所有已知数字的通用函数

下面的函数支持 Unicode 类 Nd(数字、十进制数字): Adlam、Ahom、阿拉伯印度语、巴厘岛语、孟加拉语、Bhaiksuki、婆罗米语、Chakma、Cham、梵文、扩展阿拉伯语-印度语、全 Angular 、古吉拉特语、古尔木希语、 java 语、卡纳达语、克耶里语、高棉语、Khudawadi、老挝语、雷普查语, 林布语, 马拉雅拉姆语, 数学粗体, 数学双线, 数学等宽字体, 数学无衬线粗体, 数学无衬线, Meetei Mayek, Modi, 蒙古语, Mro, Myanmar Shan, Myanmar Tai Laing, Myanmar, New Tai Lue, Newa 、Nko、Ol Chiki、Oriya、Osmanya、Pahawh Hmong、Saurashtra、Sharada、Sinhala Lith、Sora Sompeng、Sundanese、Tai Tham Hora、Tai Tham Tham、Takri、泰米尔语、泰卢固语、泰语、藏语、Tirhuta、Vai、Warang Citi。

不支持罗马数字和其他非十进制数字，因为它们不是十进制。

// This function takes an UTF16 encoded string as input,
// and returns with all suported digits from Unicode
// class 'Nd' (Number, Decimal Digit) replaced with their
// equivalent ASCII digit.
// Source : http://stackoverflow.com/a/12171250/36866
// License: MIT
// Author : <a href="https://stackoverflow.com/cdn-cgi/l/email-protection" class="__cf_email__" data-cfemail="ea9985878faa8e85878b8384c4848b878f" rel="noreferrer noopener nofollow">[email protected]</a>
// Note   : If you are going to use this code I would appreciate to
//          get an email to <a href="https://stackoverflow.com/cdn-cgi/l/email-protection" class="__cf_email__" data-cfemail="94e7fbf9f1d4f0fbf9f5fdfabafaf5f9f1" rel="noreferrer noopener nofollow">[email protected]</a>. You don't have to but
//          it would make me happier!
var digitsToASCII=
  (function () {
    // Regexp that matches all supported digits.
    // Most Unicode digit classes have the zero digit at a codepoint
    // where the four least significant bits are ether zero or six.
    // The notable exception is the Math-class where several classes
    // have sequential codepoints. The information about the offset
    // is needed when decoding, and by using groups in the RexExp
    // no lookup is needed.
    var reDigit = new RegExp(
      '('+ // Offset 0
        '['+
          '\u0030-\u0039\u0660-\u0669\u06F0-\u06F9\u07C0-\u07C9'+
          '\u0E50-\u0E59\u0ED0-\u0ED9\u0F20-\u0F29\u1040-\u1049'+
          '\u1090-\u1099\u17E0-\u17E9\u1810-\u1819\u19D0-\u19D9'+
          '\u1A80-\u1A89\u1A90-\u1A99\u1B50-\u1B59\u1BB0-\u1BB9'+
          '\u1C40-\u1C49\u1C50-\u1C59\uA620-\uA629\uA8D0-\uA8D9'+
          '\uA900-\uA909\uA9D0-\uA9D9\uA9F0-\uA9F9\uAA50-\uAA59'+
          '\uABF0-\uABF9\uFF10-\uFF19'+
        ']'+
        '|\uD801[\uDCA0-\uDCA9]'+
        '|\uD804[\uDCF0-\uDCF9\uDDD0-\uDDD9\uDEF0-\uDEF9]'+
        '|\uD805['+
          '\uDC50-\uDC59\uDCD0-\uDCD9\uDE50-\uDE59'+
          '\uDEC0-\uDEC9\uDF30-\uDF39'+
        ']'+
        '|\uD806[\uDCE0-\uDCE9]|\uD807[\uDC50-\uDC59]'+
        '|\uD81A[\uDE60-\uDE69]|\uD81A[\uDF50-\uDF59]'+
        '|\uD83A[\uDD50-\uDD59]'+
      ')|('+ // Offset 6
        '['+
          '\u0966-\u096F\u09E6-\u09EF\u0A66-\u0A6F\u0AE6-\u0AEF'+
          '\u0B66-\u0B6F\u0BE6-\u0BEF\u0C66-\u0C6F\u0CE6-\u0CEF'+
          '\u0D66-\u0D6F\u0DE6-\u0DEF\u1946-\u194F'+
        ']'+
        '|\uD804[\uDC66-\uDC6F\uDD36-\uDD3F]'+
      ')|('+ // Math
        '\uD835[\uDFCE-\uDFFF]'+
      ')',
      'g'
    );

    function replace(match, offset0, offset6, offsetMath) {
      // 'match' contains the whole match and can therefore have
      // a length longer than one character if surrogate pairs is used.
      // By getting the last character from 'match' the operation is simplified.
      var raw = match.charCodeAt( match.length - 1);
      var digit =
        offset0 ? raw & 0xF : // use 4 bits
        offset6 ? (raw -6) & 0xF : // subtract 6, use 4 bits
        offsetMath ? ((raw - 0xCE) & 0x3F) % 10 : // subtract CE, use 6 bits
        null;

      return String.fromCharCode(48 + digit); // Digit to ASCII
    }

    return function replaceDigits(input) {
      return input.replace(reDigit, replace);
    }
  })();

用法:

myAsciiVariable = digitsToASCII( myForeignVariable );

node.js 模块

现在，名为 unicodedigits 的 Node.js 模块中提供了与此类似的功能。该函数可以将任何支持的数字转换为 ASCII 或任何支持的范围。

您可以使用npm install unicodedigits --save来安装它，或者在 github.com/somec/unicodedigits 上找到它