使用Javascript';s atob解码base64不';t正确解码utf-8字符串
我正在使用Javascript使用Javascript';s atob解码base64不';t正确解码utf-8字符串,javascript,encoding,utf-8,Javascript,Encoding,Utf 8,我正在使用Javascriptwindow.atob()函数来解码base64编码的字符串(特别是来自GitHub API的base64编码内容)。问题是我要取回ASCII编码字符(比如而不是™)。如何正确处理传入的base64编码流,以便将其解码为utf-8?Unicode问题 尽管JavaScript(ECMAScript)已经成熟,但Base64、ASCII和Unicode编码的脆弱性已经引起了很多人的头疼(大部分都在这个问题的历史中) 考虑以下示例: const ok = "a
window.atob()
函数来解码base64编码的字符串(特别是来自GitHub API的base64编码内容)。问题是我要取回ASCII编码字符(比如而不是™代码>)。如何正确处理传入的base64编码流,以便将其解码为utf-8?Unicode问题
尽管JavaScript(ECMAScript)已经成熟,但Base64、ASCII和Unicode编码的脆弱性已经引起了很多人的头疼(大部分都在这个问题的历史中)
考虑以下示例:
const ok = "a";
console.log(ok.codePointAt(0).toString(16)); // 61: occupies < 1 byte
const notOK = "✓"
console.log(notOK.codePointAt(0).toString(16)); // 2713: occupies > 1 byte
console.log(btoa(ok)); // YQ==
console.log(btoa(notOK)); // error
二进制解码⇢ UTF-8
解码base64⇢ UTF8
(为什么我们需要这样做?('00'+c.charCodeAt(0).toString(16)).slice(-2)
将一个0前置到单个字符串,例如当c==\n
时,c.charCodeAt(0).toString(16)
返回a
,强制a
表示为0a
)
类型脚本支持
这是一个相同的解决方案,具有一些额外的TypeScript兼容性(通过@MA Maddin):
第一个解决方案(已弃用)
这使用了escape
和unescape
(现在已被弃用,尽管这仍然适用于所有现代浏览器):
最后一件事:我第一次遇到这个问题是在调用GitHub API时。为了让它在(移动)Safari上正常工作,我实际上必须在解码base64源代码之前去掉所有空白。无论这在2021年是否仍然相关,我不知道:
function b64_to_utf8( str ) {
str = str.replace(/\s/g, '');
return decodeURIComponent(escape(window.atob( str )));
}
不推荐使用小修正、取消扫描和转义,因此:
function utf8_to_b64( str ) {
return window.btoa(decodeURIComponent(encodeURIComponent(str)));
}
function b64_to_utf8( str ) {
return decodeURIComponent(encodeURIComponent(window.atob(str)));
}
function b64_to_utf8( str ) {
str = str.replace(/\s/g, '');
return decodeURIComponent(encodeURIComponent(window.atob(str)));
}
事情变了。这些方法已被弃用
可以在对字符串进行Base64编码之前对其进行URI编码。请注意,这不会生成Base64编码的UTF8,而是生成Base64编码的URL编码数据。双方必须就相同的编码达成一致
请参见此处的工作示例:
对于OP的问题,第三方库(如)应该可以解决该问题。以下是一些针对可能缺少escape/unescape()
的浏览器的经得起未来考验的代码。请注意,IE 9和更早版本不支持atob/btoa()
,因此需要为它们使用自定义的base64函数
// Polyfill for escape/unescape
if( !window.unescape ){
window.unescape = function( s ){
return s.replace( /%([0-9A-F]{2})/g, function( m, p ) {
return String.fromCharCode( '0x' + p );
} );
};
}
if( !window.escape ){
window.escape = function( s ){
var chr, hex, i = 0, l = s.length, out = '';
for( ; i < l; i ++ ){
chr = s.charAt( i );
if( chr.search( /[A-Za-z0-9\@\*\_\+\-\.\/]/ ) > -1 ){
out += chr; continue; }
hex = s.charCodeAt( i ).toString( 16 );
out += '%' + ( hex.length % 2 != 0 ? '0' : '' ) + hex;
}
return out;
};
}
// Base64 encoding of UTF-8 strings
var utf8ToB64 = function( s ){
return btoa( unescape( encodeURIComponent( s ) ) );
};
var b64ToUtf8 = function( s ){
return decodeURIComponent( escape( atob( s ) ) );
};
//用于escape/unescape的Polyfill
如果(!window.unescape){
window.unescape=函数{
返回s.replace(/%([0-9A-F]{2})/g,函数(m,p){
返回字符串.fromCharCode('0x'+p);
} );
};
}
如果(!window.escape){
window.escape=函数{
变量chr,hex,i=0,l=s.length,out='';
对于(;i-1){
out+=chr;continue;}
十六进制=s.charCodeAt(i).toString(16);
out+='%'+(十六进制长度%2!=0?'0':'')+hex;
}
返回;
};
}
//UTF-8字符串的Base64编码
var utf8ToB64=函数{
返回btoa(unescape(一个或多个组件));
};
var b64ToUtf8=函数{
返回组件(转义(atob));
};
这里可以找到一个更全面的UTF-8编码和解码示例:如果您更喜欢将字符串视为字节,那么可以使用以下函数
function u_atob(ascii) {
return Uint8Array.from(atob(ascii), c => c.charCodeAt(0));
}
function u_btoa(buffer) {
var binary = [];
var bytes = new Uint8Array(buffer);
for (var i = 0, il = bytes.byteLength; i < il; i++) {
binary.push(String.fromCharCode(bytes[i]));
}
return btoa(binary.join(''));
}
// example, it works also with astral plane characters such as 'including above solution if still facing issue try as below, Considerign the case where escape is not supported for TS.
blob = new Blob(["\ufeff", csv_content]); // this will make symbols to appears in excel
函数u_atob(ascii){
返回Uint8Array.from(atob(ascii),c=>c.charCodeAt(0));
}
功能u_btoa(缓冲区){
var二进制=[];
var字节=新的Uint8Array(缓冲区);
for(var i=0,il=bytes.bytellength;i //例如,它也适用于星体平面字符,如“,包括上述解决方案,如果仍然面临问题,请尝试如下,考虑到TS不支持转义的情况
function b64DecodeUnicode(str: any) {
return decodeURIComponent(atob(str).split('').map((c: any) => {
return '%' + ('00' + c.charCodeAt(0).toString(16)).slice(-2);
}).join(''));
}
对于csv_内容,您可以像下面这样尝试
function b64EncodeUnicode(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);
}));
}
b64EncodeUnicode('✓ à la mode'); // "4pyTIMOgIGxhIG1vZGU="
b64EncodeUnicode('\n'); // "Cg=="
以下是2018年更新的解决方案,如
从UNICODE编码到B64
function b64DecodeUnicode(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(''));
}
b64DecodeUnicode('4pyTIMOgIGxhIG1vZGU='); // "✓ à la mode"
b64DecodeUnicode('Cg=='); // "\n"
从B64解码为UNICODE
!function(e){"use strict";function h(b){var a=b.charCodeAt(0);if(55296<=a&&56319>=a)if(b=b.charCodeAt(1),b===b&&56320<=b&&57343>=b){if(a=1024*(a-55296)+b-56320+65536,65535<a)return d(240|a>>>18,128|a>>>12&63,128|a>>>6&63,128|a&63)}else return d(239,191,189);return 127>=a?inputString:2047>=a?d(192|a>>>6,128|a&63):d(224|a>>>12,128|a>>>6&63,128|a&63)}function k(b){var a=b.charCodeAt(0)<<24,f=l(~a),c=0,e=b.length,g="";if(5>f&&e>=f){a=a<<f>>>24+f;for(c=1;c<f;++c)a=a<<6|b.charCodeAt(c)&63;65535>=a?g+=d(a):1114111>=a?(a-=65536,g+=d((a>>10)+55296,(a&1023)+56320)):c=0}for(;c<e;++c)g+="\ufffd";return g}var m=Math.log,n=Math.LN2,l=Math.clz32||function(b){return 31-m(b>>>0)/n|0},d=String.fromCharCode,p=atob,q=btoa;e.btoaUTF8=function(b,a){return q((a?"\u00ef\u00bb\u00bf":"")+b.replace(/[\x80-\uD7ff\uDC00-\uFFFF]|[\uD800-\uDBFF][\uDC00-\uDFFF]?/g,h))};e.atobUTF8=function(b,a){a||"\u00ef\u00bb\u00bf"!==b.substring(0,3)||(b=b.substring(3));return p(b).replace(/[\xc0-\xff][\x80-\xbf]*/g,k)}}(""+void 0==typeof global?""+void 0==typeof self?this:self:global)
我假设您可能需要一个能够产生广泛使用的base64 URI的解决方案。请访问数据:文本/纯文本;字符集=utf-8;base64,4pi44pi54pi64pi74pi84pi+4pi/
查看演示(复制数据uri,打开新选项卡,将数据uri粘贴到地址栏,然后按enter键进入页面)。尽管这个URI是base64编码的,浏览器仍然能够识别高代码点并正确解码。小型编码器+解码器为1058字节(+Gzip)→(589字节)
您好\u1234 W\186\0256ld!
在顶部框中输入文本。然后URL将自动更新。
适合我的完整文章:
我们从Unicode/UTF-8编码的部分是
function b64DecodeUnicode(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(''));
}
这是当今最常用的方法之一。将base64解码为UTF8字符串
以下是@brandonscript最新投票结果
function decodeBase64(base64) {
const text = atob(base64);
const length = text.length;
const bytes = new Uint8Array(length);
for (let i = 0; i < length; i++) {
bytes[i] = text.charCodeAt(i);
}
const decoder = new TextDecoder(); // default is utf-8
return decoder.decode(bytes);
}
上面的代码可以工作,但速度非常慢。如果您的输入是非常大的base64字符串,例如,对于base64 html文档为30000个字符。这将需要大量的计算
这是我的答案,使用内置的文本解码器,对于大输入,比上面的代码快近10倍
函数decodeBase64(base64){
常量文本=atob(base64);
常量长度=text.length;
常量字节=新的Uint8Array(长度);
for(设i=0;i
您链接的MDN页面有一个以短语“用于Unicode或UTF-8字符串”开头的段落。您在节点上吗?有比atob
更好的解决方案,看起来doc链接甚至与现在不同,建议使用正则表达式解决方案来管理它。这不起作用,因为encodeURIComponent
与decodeuricomonen相反
function u_atob(ascii) {
return Uint8Array.from(atob(ascii), c => c.charCodeAt(0));
}
function u_btoa(buffer) {
var binary = [];
var bytes = new Uint8Array(buffer);
for (var i = 0, il = bytes.byteLength; i < il; i++) {
binary.push(String.fromCharCode(bytes[i]));
}
return btoa(binary.join(''));
}
// example, it works also with astral plane characters such as 'including above solution if still facing issue try as below, Considerign the case where escape is not supported for TS.
blob = new Blob(["\ufeff", csv_content]); // this will make symbols to appears in excel
function b64DecodeUnicode(str: any) {
return decodeURIComponent(atob(str).split('').map((c: any) => {
return '%' + ('00' + c.charCodeAt(0).toString(16)).slice(-2);
}).join(''));
}
function b64EncodeUnicode(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);
}));
}
b64EncodeUnicode('✓ à la mode'); // "4pyTIMOgIGxhIG1vZGU="
b64EncodeUnicode('\n'); // "Cg=="
function b64DecodeUnicode(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(''));
}
b64DecodeUnicode('4pyTIMOgIGxhIG1vZGU='); // "✓ à la mode"
b64DecodeUnicode('Cg=='); // "\n"
!function(e){"use strict";function h(b){var a=b.charCodeAt(0);if(55296<=a&&56319>=a)if(b=b.charCodeAt(1),b===b&&56320<=b&&57343>=b){if(a=1024*(a-55296)+b-56320+65536,65535<a)return d(240|a>>>18,128|a>>>12&63,128|a>>>6&63,128|a&63)}else return d(239,191,189);return 127>=a?inputString:2047>=a?d(192|a>>>6,128|a&63):d(224|a>>>12,128|a>>>6&63,128|a&63)}function k(b){var a=b.charCodeAt(0)<<24,f=l(~a),c=0,e=b.length,g="";if(5>f&&e>=f){a=a<<f>>>24+f;for(c=1;c<f;++c)a=a<<6|b.charCodeAt(c)&63;65535>=a?g+=d(a):1114111>=a?(a-=65536,g+=d((a>>10)+55296,(a&1023)+56320)):c=0}for(;c<e;++c)g+="\ufffd";return g}var m=Math.log,n=Math.LN2,l=Math.clz32||function(b){return 31-m(b>>>0)/n|0},d=String.fromCharCode,p=atob,q=btoa;e.btoaUTF8=function(b,a){return q((a?"\u00ef\u00bb\u00bf":"")+b.replace(/[\x80-\uD7ff\uDC00-\uFFFF]|[\uD800-\uDBFF][\uDC00-\uDFFF]?/g,h))};e.atobUTF8=function(b,a){a||"\u00ef\u00bb\u00bf"!==b.substring(0,3)||(b=b.substring(3));return p(b).replace(/[\xc0-\xff][\x80-\xbf]*/g,k)}}(""+void 0==typeof global?""+void 0==typeof self?this:self:global)
var fromCharCode = String.fromCharCode;
var btoaUTF8 = (function(btoa, replacer){"use strict";
return function(inputString, BOMit){
return btoa((BOMit ? "\xEF\xBB\xBF" : "") + inputString.replace(
/[\x80-\uD7ff\uDC00-\uFFFF]|[\uD800-\uDBFF][\uDC00-\uDFFF]?/g, replacer
));
}
})(btoa, function(nonAsciiChars){"use strict";
// make the UTF string into a binary UTF-8 encoded string
var point = nonAsciiChars.charCodeAt(0);
if (point >= 0xD800 && point <= 0xDBFF) {
var nextcode = nonAsciiChars.charCodeAt(1);
if (nextcode !== nextcode) // NaN because string is 1 code point long
return fromCharCode(0xef/*11101111*/, 0xbf/*10111111*/, 0xbd/*10111101*/);
// https://mathiasbynens.be/notes/javascript-encoding#surrogate-formulae
if (nextcode >= 0xDC00 && nextcode <= 0xDFFF) {
point = (point - 0xD800) * 0x400 + nextcode - 0xDC00 + 0x10000;
if (point > 0xffff)
return fromCharCode(
(0x1e/*0b11110*/<<3) | (point>>>18),
(0x2/*0b10*/<<6) | ((point>>>12)&0x3f/*0b00111111*/),
(0x2/*0b10*/<<6) | ((point>>>6)&0x3f/*0b00111111*/),
(0x2/*0b10*/<<6) | (point&0x3f/*0b00111111*/)
);
} else return fromCharCode(0xef, 0xbf, 0xbd);
}
if (point <= 0x007f) return nonAsciiChars;
else if (point <= 0x07ff) {
return fromCharCode((0x6<<5)|(point>>>6), (0x2<<6)|(point&0x3f));
} else return fromCharCode(
(0xe/*0b1110*/<<4) | (point>>>12),
(0x2/*0b10*/<<6) | ((point>>>6)&0x3f/*0b00111111*/),
(0x2/*0b10*/<<6) | (point&0x3f/*0b00111111*/)
);
});
var clz32 = Math.clz32 || (function(log, LN2){"use strict";
return function(x) {return 31 - log(x >>> 0) / LN2 | 0};
})(Math.log, Math.LN2);
var fromCharCode = String.fromCharCode;
var atobUTF8 = (function(atob, replacer){"use strict";
return function(inputString, keepBOM){
inputString = atob(inputString);
if (!keepBOM && inputString.substring(0,3) === "\xEF\xBB\xBF")
inputString = inputString.substring(3); // eradicate UTF-8 BOM
// 0xc0 => 0b11000000; 0xff => 0b11111111; 0xc0-0xff => 0b11xxxxxx
// 0x80 => 0b10000000; 0xbf => 0b10111111; 0x80-0xbf => 0b10xxxxxx
return inputString.replace(/[\xc0-\xff][\x80-\xbf]*/g, replacer);
}
})(atob, function(encoded){"use strict";
var codePoint = encoded.charCodeAt(0) << 24;
var leadingOnes = clz32(~codePoint);
var endPos = 0, stringLen = encoded.length;
var result = "";
if (leadingOnes < 5 && stringLen >= leadingOnes) {
codePoint = (codePoint<<leadingOnes)>>>(24+leadingOnes);
for (endPos = 1; endPos < leadingOnes; ++endPos)
codePoint = (codePoint<<6) | (encoded.charCodeAt(endPos)&0x3f/*0b00111111*/);
if (codePoint <= 0xFFFF) { // BMP code point
result += fromCharCode(codePoint);
} else if (codePoint <= 0x10FFFF) {
// https://mathiasbynens.be/notes/javascript-encoding#surrogate-formulae
codePoint -= 0x10000;
result += fromCharCode(
(codePoint >> 10) + 0xD800, // highSurrogate
(codePoint & 0x3ff) + 0xDC00 // lowSurrogate
);
} else endPos = 0; // to fill it in with INVALIDs
}
for (; endPos < stringLen; ++endPos) result += "\ufffd"; // replacement character
return result;
});
function utf8_to_b64( str ) {
return window.btoa(unescape(encodeURIComponent( str )));
}
function b64_to_utf8( str ) {
return decodeURIComponent(escape(window.atob( str )));
}
// Usage:
utf8_to_b64('✓ à la mode'); // "4pyTIMOgIGxhIG1vZGU="
b64_to_utf8('4pyTIMOgIGxhIG1vZGU='); // "✓ à la mode"
function b64DecodeUnicode(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(''));
}
function decodeBase64(base64) {
const text = atob(base64);
const length = text.length;
const bytes = new Uint8Array(length);
for (let i = 0; i < length; i++) {
bytes[i] = text.charCodeAt(i);
}
const decoder = new TextDecoder(); // default is utf-8
return decoder.decode(bytes);
}