云梦泽
云梦泽
1月前 · 9 人阅读

MDN中给出了base64编码函数btoa和解码函数atob.

let encoded = btoa('yo'); // "eW8="
let decoded = atob(encoded); // 'yo'

Unicode问题解法

有个小坑是它只支持ASCII. 如果你调用btoa("中文")会报错:

Uncaught DOMException: Failed to execute 'btoa' on 'Window': The string to be encoded contains characters outside of the Latin1 range.

浏览器中DOMString是UTF-16编码. 如果输入字符串中包含超过8位(0x00~0xFF)的字符, 就会报这个错误.

思路一

对整个字符串进行转义(如使用encodeURIComponent 进行UTF-8转义)然后再btoa编码.

let Base64 = {
    encode(str) {
        // first we use encodeURIComponent to get percent-encoded UTF-8,
        // then we convert the percent encodings into raw bytes which
        // can be fed into btoa.
        return btoa(encodeURIComponent(str).replace(/%([0-9A-F]{2})/g,
            function toSolidBytes(match, p1) {
                return String.fromCharCode('0x' + p1);
            }));
    },
    decode(str) {
        // Going backwards: from bytestream, to percent-encoding, to original string.
        return decodeURIComponent(atob(str).split('').map(function (c) {
            return '%' + ('00' + c.charCodeAt(0).toString(16)).slice(-2);
        }).join(''));
    }
};

let encoded = Base64.encode("哈ha"); // "5ZOIaGE="
let decoded = Base64.decode(encoded); // "哈ha"

思路二

将UTF-16的DOMString转化成UTF-8的字节数组然后编码.

MDN上此思路的解法用了很多库, 就不推荐了.

网上找到了下面这段代码, 思路是一样的, 但是是直接裸写的转换代码.

/**
*
*  Base64 encode / decode
*  http://www.webtoolkit.info
*
**/
var Base64 = {

    // private property
    _keyStr: "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/="

    // public method for encoding
    , encode: function (input)
    {
        var output = "";
        var chr1, chr2, chr3, enc1, enc2, enc3, enc4;
        var i = 0;

        input = Base64._utf8_encode(input);

        while (i < input.length)
        {
            chr1 = input.charCodeAt(i++);
            chr2 = input.charCodeAt(i++);
            chr3 = input.charCodeAt(i++);

            enc1 = chr1 >> 2;
            enc2 = ((chr1 & 3) << 4) | (chr2 >> 4);
            enc3 = ((chr2 & 15) << 2) | (chr3 >> 6);
            enc4 = chr3 & 63;

            if (isNaN(chr2))
            {
                enc3 = enc4 = 64;
            }
            else if (isNaN(chr3))
            {
                enc4 = 64;
            }

            output = output +
                this._keyStr.charAt(enc1) + this._keyStr.charAt(enc2) +
                this._keyStr.charAt(enc3) + this._keyStr.charAt(enc4);
        } // Whend 

        return output;
    } // End Function encode 


    // public method for decoding
    ,decode: function (input)
    {
        var output = "";
        var chr1, chr2, chr3;
        var enc1, enc2, enc3, enc4;
        var i = 0;

        input = input.replace(/[^A-Za-z0-9+/=]/g, "");
        while (i < input.length)
        {
            enc1 = this._keyStr.indexOf(input.charAt(i++));
            enc2 = this._keyStr.indexOf(input.charAt(i++));
            enc3 = this._keyStr.indexOf(input.charAt(i++));
            enc4 = this._keyStr.indexOf(input.charAt(i++));

            chr1 = (enc1 << 2) | (enc2 >> 4);
            chr2 = ((enc2 & 15) << 4) | (enc3 >> 2);
            chr3 = ((enc3 & 3) << 6) | enc4;

            output = output + String.fromCharCode(chr1);

            if (enc3 != 64)
            {
                output = output + String.fromCharCode(chr2);
            }

            if (enc4 != 64)
            {
                output = output + String.fromCharCode(chr3);
            }

        } // Whend 

        output = Base64._utf8_decode(output);

        return output;
    } // End Function decode 


    // private method for UTF-8 encoding
    ,_utf8_encode: function (string)
    {
        var utftext = "";
        string = string.replace(/
/g, "
");

        for (var n = 0; n < string.length; n++)
        {
            var c = string.charCodeAt(n);

            if (c < 128)
            {
                utftext += String.fromCharCode(c);
            }
            else if ((c > 127) && (c < 2048))
            {
                utftext += String.fromCharCode((c >> 6) | 192);
                utftext += String.fromCharCode((c & 63) | 128);
            }
            else
            {
                utftext += String.fromCharCode((c >> 12) | 224);
                utftext += String.fromCharCode(((c >> 6) & 63) | 128);
                utftext += String.fromCharCode((c & 63) | 128);
            }

        } // Next n 

        return utftext;
    } // End Function _utf8_encode 

    // private method for UTF-8 decoding
    ,_utf8_decode: function (utftext)
    {
        var string = "";
        var i = 0;
        var c, c1, c2, c3;
        c = c1 = c2 = 0;

        while (i < utftext.length)
        {
            c = utftext.charCodeAt(i);

            if (c < 128)
            {
                string += String.fromCharCode(c);
                i++;
            }
            else if ((c > 191) && (c < 224))
            {
                c2 = utftext.charCodeAt(i + 1);
                string += String.fromCharCode(((c & 31) << 6) | (c2 & 63));
                i += 2;
            }
            else
            {
                c2 = utftext.charCodeAt(i + 1);
                c3 = utftext.charCodeAt(i + 2);
                string += String.fromCharCode(((c & 15) << 12) | ((c2 & 63) << 6) | (c3 & 63));
                i += 3;
            }

        } // Whend 

        return string;
    } // End Function _utf8_decode 

}

压缩版本

var Base64={_keyStr:"ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/=",encode:function(e){var t="";var n,r,i,s,o,u,a;var f=0;e=Base64._utf8_encode(e);while(f<e.length){n=e.charCodeAt(f++);r=e.charCodeAt(f++);i=e.charCodeAt(f++);s=n>>2;o=(n&3)<<4|r>>4;u=(r&15)<<2|i>>6;a=i&63;if(isNaN(r)){u=a=64}else if(isNaN(i)){a=64}t=t+this._keyStr.charAt(s)+this._keyStr.charAt(o)+this._keyStr.charAt(u)+this._keyStr.charAt(a)}return t},decode:function(e){var t="";var n,r,i;var s,o,u,a;var f=0;e=e.replace(/[^A-Za-z0-9+/=]/g,"");while(f<e.length){s=this._keyStr.indexOf(e.charAt(f++));o=this._keyStr.indexOf(e.charAt(f++));u=this._keyStr.indexOf(e.charAt(f++));a=this._keyStr.indexOf(e.charAt(f++));n=s<<2|o>>4;r=(o&15)<<4|u>>2;i=(u&3)<<6|a;t=t+String.fromCharCode(n);if(u!=64){t=t+String.fromCharCode(r)}if(a!=64){t=t+String.fromCharCode(i)}}t=Base64._utf8_decode(t);return t},_utf8_encode:function(e){e=e.replace(/rn/g,"n");var t="";for(var n=0;n<e.length;n++){var r=e.charCodeAt(n);if(r<128){t+=String.fromCharCode(r)}else if(r>127&&r<2048){t+=String.fromCharCode(r>>6|192);t+=String.fromCharCode(r&63|128)}else{t+=String.fromCharCode(r>>12|224);t+=String.fromCharCode(r>>6&63|128);t+=String.fromCharCode(r&63|128)}}return t},_utf8_decode:function(e){var t="";var n=0;var r=c1=c2=0;while(n<e.length){r=e.charCodeAt(n);if(r<128){t+=String.fromCharCode(r);n++}else if(r>191&&r<224){c2=e.charCodeAt(n+1);t+=String.fromCharCode((r&31)<<6|c2&63);n+=2}else{c2=e.charCodeAt(n+1);c3=e.charCodeAt(n+2);t+=String.fromCharCode((r&15)<<12|(c2&63)<<6|c3&63);n+=3}}return t}}

参考

  1. Base64 encoding and decoding
  2. Failed to execute 'btoa' on 'Window': The string to be encoded contains characters outside of the Latin1 range.
  3. How to Encode and Decode Strings with Base64 in JavaScript
收藏 0
关键词: var string fromcharcode ._ key
评论