我有一个PHP脚本,可以将PNG图像编码为Base64字符串。

我想用JavaScript做同样的事情。我知道如何打开文件,但我不知道如何进行编码。我不习惯使用二进制数据。


当前回答

当我使用

btoa("☸☹☺☻☼☾☿"))

我得到:

InvalidCharacterError:要编码的字符串包含Latin1范围之外的字符。

我发现文档,Unicode字符串,提供了一个解决方案如下。

function toBinary(string) { const codeUnits = new Uint16Array(string.length); for (let i = 0; i < codeUnits.length; i++) { codeUnits[i] = string.charCodeAt(i); } return String.fromCharCode(...new Uint8Array(codeUnits.buffer)); } function fromBinary(binary) { const bytes = new Uint8Array(binary.length); for (let i = 0; i < bytes.length; i++) { bytes[i] = binary.charCodeAt(i); } return String.fromCharCode(...new Uint16Array(bytes.buffer)); } const myString = "☸☹☺☻☼☾☿" // console.log(btoa(myString)) // Error InvalidCharacterError: The string to be encoded contains characters outside of the Latin1 range. const converted = toBinary(myString) const encoded = btoa(converted) console.log(encoded) const decoded = atob(encoded) const original = fromBinary(decoded) console.log(original);

其他回答

对于更新的浏览器编码Uint8Array到字符串,并解码字符串到Uint8Array。

const base64 = {
    decode: s => Uint8Array.from(atob(s), c => c.charCodeAt(0)),
    encode: b => btoa(String.fromCharCode(...new Uint8Array(b)))
};

对于Node.js,你可以使用以下代码将string、Buffer或Uint8Array编码为string,并从string、Buffer或Uint8Array解码为Buffer。

const base64 = {
    decode: s => Buffer.from(s, 'base64'),
    encode: b => Buffer.from(b).toString('base64')
};

从这里开始:

/**
*
*  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);
        }
        return output;
    },

    // 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);
            }
        }

        output = Base64._utf8_decode(output);

        return output;
    },

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

        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);
            }
        }
        return utftext;
    },

    // private method for UTF-8 decoding
    _utf8_decode : function (utftext) {
        var string = "";
        var i = 0;
        var 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;
            }
        }
        return string;
    }
}

此外,搜索“JavaScript base64 encoding”会出现许多其他选项,上面是第一个。

我需要一个UTF-8字符串编码为Base64为我的一个项目。这里的大多数答案似乎在转换为UTF-8时不能正确处理UTF-16代理对,因此,为了完成,我将发布我的解决方案:

function strToUTF8Base64(str) {

    function decodeSurrogatePair(hi, lo) {
        var resultChar = 0x010000;
        resultChar += lo - 0xDC00;
        resultChar += (hi - 0xD800) << 10;
        return resultChar;
    }

    var bytes = [0, 0, 0];
    var byteIndex = 0;
    var result = [];

    function output(s) {
        result.push(s);
    }

    function emitBase64() {

        var digits =
                'ABCDEFGHIJKLMNOPQRSTUVWXYZ' +
                'abcdefghijklmnopqrstuvwxyz' +
                '0123456789+/';

        function toDigit(value) {
            return digits[value];
        }

        // --Byte 0--    --Byte 1--    --Byte 2--
        // 1111  1122    2222  3333    3344  4444

        var d1 = toDigit(bytes[0] >> 2);
        var d2 = toDigit(
            ((bytes[0] & 0x03) << 4) |
            (bytes[1] >> 4));
        var d3 = toDigit(
            ((bytes[1] & 0x0F) << 2) |
            (bytes[2] >> 6));
        var d4 = toDigit(
            bytes[2] & 0x3F);

        if (byteIndex === 1) {
            output(d1 + d2 + '==');
        }
        else if (byteIndex === 2) {
            output(d1 + d2 + d3 + '=');
        }
        else {
            output(d1 + d2 + d3 + d4);
        }
    }

    function emit(chr) {
        bytes[byteIndex++] = chr;
        if (byteIndex == 3) {
            emitBase64();
            bytes[0] = 0;
            bytes[1] = 0;
            bytes[2] = 0;
            byteIndex = 0;
        }
    }

    function emitLast() {
        if (byteIndex > 0) {
            emitBase64();
        }
    }

    // Converts the string to UTF8:

    var i, chr;
    var hi, lo;
    for (i = 0; i < str.length; i++) {
        chr = str.charCodeAt(i);

        // Test and decode surrogate pairs in the string
        if (chr >= 0xD800 && chr <= 0xDBFF) {
            hi = chr;
            lo = str.charCodeAt(i + 1);
            if (lo >= 0xDC00 && lo <= 0xDFFF) {
                chr = decodeSurrogatePair(hi, lo);
                i++;
            }
        }

        // Encode the character as UTF-8.
        if (chr < 0x80) {
            emit(chr);
        }
        else if (chr < 0x0800) {
            emit((chr >> 6) | 0xC0);
            emit(((chr >> 0) & 0x3F) | 0x80);
        }
        else if (chr < 0x10000) {
            emit((chr >> 12) | 0xE0);
            emit(((chr >>  6) & 0x3F) | 0x80);
            emit(((chr >>  0) & 0x3F) | 0x80);
        }
        else if (chr < 0x110000) {
            emit((chr >> 18) | 0xF0);
            emit(((chr >> 12) & 0x3F) | 0x80);
            emit(((chr >>  6) & 0x3F) | 0x80);
            emit(((chr >>  0) & 0x3F) | 0x80);
        }
    }

    emitLast();

    return result.join('');
}

注意,代码没有经过彻底的测试。我测试了一些输入,包括strToUTF8Base64('衠衢蠩蠨'),并将其与在线编码工具(https://www.base64encode.org/)的输出进行了比较。

如果你使用Node.js,你可以这样做:

let a = Buffer.from('JavaScript').toString('base64');
console.log(a);

let b = Buffer.from(a, 'base64').toString();
console.log(b);

对于我的项目,我仍然需要支持IE7和工作大输入编码。

根据Joe Dyndale提出的代码和Marius在评论中提出的建议,可以通过使用数组而不是字符串构造结果来提高IE7的性能。

下面是encode的例子:

var encode = function (input) {
    var output = [], chr1, chr2, chr3, enc1, enc2, enc3, enc4, i = 0;

    input = _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.push(_keyStr.charAt(enc1));
        output.push(_keyStr.charAt(enc2));
        output.push(_keyStr.charAt(enc3));
        output.push(_keyStr.charAt(enc4));

    }

    return output.join("");
};