通过JS将一串字符串进行UTF-8编码

通过JS将一串字符串进行UTF-8编码

// 将字符串格式化为UTF8编码的字节
var writeUTF = function (str, isGetBytes) {
var back = [];
var byteSize = 0;
for (var i = 0; i < str.length; i++) {
var code = str.charCodeAt(i);
if (0x00 <= code && code <= 0x7f) {
byteSize += 1;
back.push(code);
} else if (0x80 <= code && code <= 0x7ff) {
byteSize += 2;
back.push((192 | (31 & (code >> 6))));
back.push((128 | (63 & code)))
} else if ((0x800 <= code && code <= 0xd7ff)
|| (0xe000 <= code && code <= 0xffff)) {
byteSize += 3;
back.push((224 | (15 & (code >> 12))));
back.push((128 | (63 & (code >> 6))));
back.push((128 | (63 & code)))
}
}
for (i = 0; i < back.length; i++) {
back[i] &= 0xff;
}
if (isGetBytes) {
return back
}
if (byteSize <= 0xff) {
return [0, byteSize].concat(back);
} else {
return [byteSize >> 8, byteSize & 0xff].concat(back);
}
}

writeUTF(‘中’); // => [0, 3, 228, 184, 173]
// 前两位表示后面utf8字节的长度。因为长度为3，所以前两个字节为0，3
// 内容为228, 184, 173转成16进制就是0xE4 0xB8 0xAD

// 读取UTF8编码的字节，并专为Unicode的字符串
var readUTF = function (arr) {
if (typeof arr === ‘string’) {
return arr;
}
var UTF = ‘’, _arr = this.init(arr);
for (var i = 0; i < _arr.length; i++) {
var one = _arr[i].toString(2),
v = one.match(/^1+?(?=0)/);
if (v && one.length == 8) {
var bytesLength = v[0].length;
var store = _arr[i].toString(2).slice(7 - bytesLength);
for (var st = 1; st < bytesLength; st++) {
store += _arr[st + i].toString(2).slice(2)
}
UTF += String.fromCharCode(parseInt(store, 2));
i += bytesLength - 1
} else {
UTF += String.fromCharCode(_arr[i])
}
}
return UTF
}

readUTF([0, 3, 228, 184, 173]); => ‘中’