JavaScript byte数组 转 字符串 中文乱码怎么解决

Question

问题描述

通过websocket接收到一个byte数组转会字符串的时候 中文是乱码的

问题出现的环境背景及自己尝试过哪些方法

websocket编码是UTF-8的， vue框架

相关代码

// 请把代码文本粘贴到下方（请勿用图片代替代码）

只是我字符串转byte的代码 然后构造ArrayBuffer数组 发给websocket没问题

function stringToByte(str) {
    var bytes = new Array();
    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;

}

然后转字符串 中文就乱码了

function byteToString(arr) {
    if (typeof arr === 'string') {
        return arr;
    }
    var str = '', _arr = 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);
            }
            str += String.fromCharCode(parseInt(store, 2));
            i += bytesLength - 1;
        } else {
            str += String.fromCharCode(_arr[i]);
        }
    }
    return str;
}

你期待的结果是什么？实际看到的错误信息又是什么？

有什么解决的方法吗?

Answer 1

解决了 编码的问题

function utf8ByteToUnicodeStr(utf8Bytes){
    var unicodeStr ="";
    for (var pos = 0; pos < utf8Bytes.length;){
        var flag= utf8Bytes[pos];
        var unicode = 0 ;
        if ((flag >>>7) === 0 ) {
            unicodeStr+= String.fromCharCode(utf8Bytes[pos]);
            pos += 1;

        } else if ((flag &0xFC) === 0xFC ){
            unicode = (utf8Bytes[pos] & 0x3) << 30;
            unicode |= (utf8Bytes[pos+1] & 0x3F) << 24;
            unicode |= (utf8Bytes[pos+2] & 0x3F) << 18;
            unicode |= (utf8Bytes[pos+3] & 0x3F) << 12;
            unicode |= (utf8Bytes[pos+4] & 0x3F) << 6;
            unicode |= (utf8Bytes[pos+5] & 0x3F);
            unicodeStr+= String.fromCharCode(unicode) ;
            pos += 6;

        }else if ((flag &0xF8) === 0xF8 ){
            unicode = (utf8Bytes[pos] & 0x7) << 24;
            unicode |= (utf8Bytes[pos+1] & 0x3F) << 18;
            unicode |= (utf8Bytes[pos+2] & 0x3F) << 12;
            unicode |= (utf8Bytes[pos+3] & 0x3F) << 6;
            unicode |= (utf8Bytes[pos+4] & 0x3F);
            unicodeStr+= String.fromCharCode(unicode) ;
            pos += 5;

        } else if ((flag &0xF0) === 0xF0 ){
            unicode = (utf8Bytes[pos] & 0xF) << 18;
            unicode |= (utf8Bytes[pos+1] & 0x3F) << 12;
            unicode |= (utf8Bytes[pos+2] & 0x3F) << 6;
            unicode |= (utf8Bytes[pos+3] & 0x3F);
            unicodeStr+= String.fromCharCode(unicode) ;
            pos += 4;

        } else if ((flag &0xE0) === 0xE0 ){
            unicode = (utf8Bytes[pos] & 0x1F) << 12;;
            unicode |= (utf8Bytes[pos+1] & 0x3F) << 6;
            unicode |= (utf8Bytes[pos+2] & 0x3F);
            unicodeStr+= String.fromCharCode(unicode) ;
            pos += 3;

        } else if ((flag &0xC0) === 0xC0 ){ //110
            unicode = (utf8Bytes[pos] & 0x3F) << 6;
            unicode |= (utf8Bytes[pos+1] & 0x3F);
            unicodeStr+= String.fromCharCode(unicode) ;
            pos += 2;

        } else{
            unicodeStr+= String.fromCharCode(utf8Bytes[pos]);
            pos += 1;
        }
    }
    return unicodeStr;
}

Answer 2

你这个转换byte数组是必须的吗？如果不是必须的，为什么要加？