项目中遇到一个问题,在JS中将byte数组转化为String的时候,有中文的情况下会出现乱码问题:
function decodeToString(payload) {
return String.fromCharCode.apply(String, payload);
}
上面这个方法,在没有中文的情况下是没有问题的,如果有中文则会出现乱码。
更换方法:
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;
}