所以结果你只想在 node.js 中使用原始字节,有一个模块可以做到。如果你是一个真正的巫师,你可以让这些东西单独使用 javascript 字符串,但它更难,效率也低得多。
var b = new Buffer(1);
b[0] = 213;
console.log(b.toString()); //�
var b = new Buffer(3);
b[0] = 0xE2;
b[1] = 0x98;
b[2] = 0x85;
console.log(b.toString()); //★
print chr(213) # prints � on the console
因此,这会打印一个原始字节 ( 0xD5
),它以 UTF-8(很可能)解释,这不是有效的 UTF-8 字节序列,因此显示为替换字符 (�)。
UTF-8 的解释与此处无关,您很可能只需要原始字节。
要在 javascript 中创建原始字节,您可以使用UInt8Array
.
var a = new Uint8Array(1);
a[0] = 213;
您可以选择将原始字节解释为 utf-8:
console.log( utf8decode(a)); // "�"
//Not recommended for production use ;D
//Doesn't handle > BMP to keep the answer shorter
function utf8decode(uint8array) {
var codePoints = [],
i = 0,
byte, codePoint, len = uint8array.length;
for (i = 0; i < len; ++i) {
byte = uint8array[i];
if ((byte & 0xF8) === 0xF0 && len > i + 3) {
codePoint = ((byte & 0x7) << 18) | ((uint8array[++i] & 0x3F) << 12) | ((uint8array[++i] & 0x3F) << 6) | (uint8array[++i] & 0x3F);
if (!(0xFFFF < codePoint && codePoint <= 0x10FFFF)) {
codePoints.push(0xFFFD, 0xFFFD, 0xFFFD, 0xFFFD);
} else {
codePoints.push(codePoint);
}
} else if ((byte & 0xF0) === 0xE0 && len > i + 2) {
codePoint = ((byte & 0xF) << 12) | ((uint8array[++i] & 0x3F) << 6) | (uint8array[++i] & 0x3F);
if (!(0x7FF < codePoint && codePoint <= 0xFFFF)) {
codePoints.push(0xFFFD, 0xFFFD, 0xFFFD);
} else {
codePoints.push(codePoint);
}
} else if ((byte & 0xE0) === 0xC0 && len > i + 1) {
codePoint = ((byte & 0x1F) << 6) | ((uint8array[++i] & 0x3F));
if (!(0x7F < codePoint && codePoint <= 0x7FF)) {
codePoints.push(0xFFFD, 0xFFFD);
} else {
codePoints.push(codePoint);
}
} else if ((byte & 0x80) === 0x00) {
codePoints.push(byte & 0x7F);
} else {
codePoints.push(0xFFFD);
}
}
return String.fromCharCode.apply(String, codePoints);
}
您最有可能尝试做的事情与尝试将字节解释为 utf8 无关。
另一个例子:
//UTF-8 For the black star U+2605 ★:
var a = new Uint8Array(3);
a[0] = 0xE2;
a[1] = 0x98;
a[2] = 0x85;
utf8decode(a) === String.fromCharCode(0x2605) //True
utf8decode(a) // ★
在 python 2.7 (Ubuntu) 中:
print chr(0xE2) + chr(0x98) + chr(0x85)
#prints ★