JS字符串与字节转换

一、字符串转byte数组

 function stringToByte(str) {
        var bytes = new Array(10000);
        var len, c;
        len = str.length;
        for(var i = 0; i < len; i++) {
            c = str.charCodeAt(i);
            if(c >= 0x010000 && c <= 0x10FFFF) {
                bytes.push(((c >> 18) & 0x07) | 0xF0);
                bytes.push(((c >> 12) & 0x3F) | 0x80);
                bytes.push(((c >> 6) & 0x3F) | 0x80);
                bytes.push((c & 0x3F) | 0x80);
            } else if(c >= 0x000800 && c <= 0x00FFFF) {
                bytes.push(((c >> 12) & 0x0F) | 0xE0);
                bytes.push(((c >> 6) & 0x3F) | 0x80);
                bytes.push((c & 0x3F) | 0x80);
            } else if(c >= 0x000080 && c <= 0x0007FF) {
                bytes.push(((c >> 6) & 0x1F) | 0xC0);
                bytes.push((c & 0x3F) | 0x80);
            } else {
                bytes.push(c & 0xFF);
            }
        }
        return bytes;
       

function stringToBytes(str) {
    str = unescape(encodeURIComponent(str))
    for (var bytes = [], i = 0; i < str.length; i++)
        bytes.push(str.charCodeAt(i) & 0xFF);
    return bytes;
	}

//byte转字符串
function bytesToString(bytes) {
		for (var str = [], i = 0; i < bytes.length; i++)
			str.push(String.fromCharCode(bytes[i]));
		return str.join("");
	}

二、读取UTF8编码的字节，并专为Unicode的字符串

function readUTF(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
}

三、将字符串格式化为UTF8编码的字节

function writeUTF(str, isGetBytes=true) {
      var back = [];
      var byteSize = 0;
      for (var i = 0; i < str.length; i++) {
          var code = str.codePointAt(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)))
          }else if((0x10000 <= code && code <= 0x10ffff)){
          	byteSize+=4;
            back.push((240 |(7 & (code>>18))));
            back.push((128 |(63 & (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);
        }
}

四、参考

1、CryptoJS 官方地址：https://github.com/sytelus/CryptoJS