在Javascript中将ASCII字符串转换为十六进制和base-64的转换非常简单。但是,处理二进制和UTF编码的字符串会引发误解。
Javascript的内置atob()和btoa()函数不适用于UTF编码的字符串,这是来自声明UTF-8字符集的HTML文档中的元素(例如输入)的字符串的主要问题。此外,似乎base-64只能使用已经是ASCII编码的十六进制的字符串直接编码,没有直接的方法将二进制字符串(ASCII或UTF-8编码)转换为base-64。 / p>
为了进一步加剧这个问题,似乎SO和其他地方发布的几乎所有问题都假设“二进制字符串”等同于以十六进制编码字符串表示的二进制数据,而不是由基数组成的字符串 - 2个数字。
鉴于UTF-8或ASCII编码的字符串由二进制,十六进制或base-64字符组成,您如何在三者之间进行转换?
答案 0 :(得分:0)
这是我到目前为止所提出的答案。我还没有考虑消除hex⇌base-64的中间步骤,所以这些函数涉及到二进制的转换。
// Binary → Hex
binToHex = (value) => {
let hexString = '';
for (let i=0; i < (value.length)/4; i++) {
let piece = value.substr(4*i, 4);
hexString += parseInt(piece, 2).toString(16);
}
return hexString;
}
// Binary → Base-64
binToB64 = (value) => {
let arrayBuffer = new ArrayBuffer(Math.ceil(value.length/8))
,decArray
,uint8DecArray
bitsToDecArray = (bits) => {
let decArray = [];
for (let i=0; i< Math.ceil(value.length/8); i++) {
let length = 8*i+8 > value.length ? value.length - 8*i : 8
,bin = value.substr(8*i, length)
decArray.push(parseInt(bin, 2).toString(10));
}
return decArray;
}
decArray = bitsToDecArray(value);
uint8DecArray = new Uint8Array(decArray);
// From http://stackoverflow.com/a/7372816/4111381
base64ArrayBuffer = (arrayBuffer) => {
let base64 = ''
,encodings = 'ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/'
,bytes = new Uint8Array(arrayBuffer)
,byteLength = bytes.byteLength
,byteRemainder = byteLength % 3
,mainLength = byteLength - byteRemainder
,a, b, c, d
,chunk
// Main loop deals with bytes in chunks of 3
for (var i = 0; i < mainLength; i = i + 3) {
// Combine the three bytes into a single integer
chunk = (bytes[i] << 16) | (bytes[i + 1] << 8) | bytes[i + 2]
// Use bitmasks to extract 6-bit segments from the triplet
a = (chunk & 16515072) >> 18 // 16515072 = (2^6 - 1) << 18
b = (chunk & 258048) >> 12 // 258048 = (2^6 - 1) << 12
c = (chunk & 4032) >> 6 // 4032 = (2^6 - 1) << 6
d = chunk & 63 // 63 = 2^6 - 1
// Convert the raw binary segments to the appropriate ASCII encoding
base64 += encodings[a] + encodings[b] + encodings[c] + encodings[d]
}
// Deal with the remaining bytes and padding
if (byteRemainder == 1) {
chunk = bytes[mainLength]
a = (chunk & 252) >> 2 // 252 = (2^6 - 1) << 2
// Set the 4 least significant bits to zero
b = (chunk & 3) << 4 // 3 = 2^2 - 1
base64 += encodings[a] + encodings[b] + '=='
} else if (byteRemainder == 2) {
chunk = (bytes[mainLength] << 8) | bytes[mainLength + 1]
a = (chunk & 64512) >> 10 // 64512 = (2^6 - 1) << 10
b = (chunk & 1008) >> 4 // 1008 = (2^6 - 1) << 4
// Set the 2 least significant bits to zero
c = (chunk & 15) << 2 // 15 = 2^4 - 1
base64 += encodings[a] + encodings[b] + encodings[c] + '='
}
return base64
}
return base64ArrayBuffer(uint8DecArray);
}
// Hex → Bin
hexToBin = (value) => {
let binString = '';
for (let i=0; i < value.length; i++) {
let bin = parseInt(value[i], 16).toString(2);
binString += ('0000' + bin).slice(-4);
}
return binString;
}
// Hex → Base-64
hexToB64 = (value) => {
return binToB64(hexToBin(value));
}
// Base-64 → Binary
b64ToBin = (value) => {
let bitString = ''
,base64chars = 'ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/'
for(let i = 0; i < value.length; i+=4) {
let segment = '';
for (let j = 0; j < 4; j++) {
console.log(i+j)
if (value[i+j] != '=') {
let bin = base64chars.indexOf(value[i+j]).toString(2)
segment += ('000000' + bin).slice(-6);
}
else segment += '000000';
}
bitString += segment;
}
// Strip ending null bytes
while (bitString.endsWith('00000000')) {
bitString = bitString.substr(0, bitString.length-8);
}
return bitString;
}
// Base-64 → Hex
b64ToHex = (value) => {
return binToHex(b64ToBin(value));
}