一,测试Demo
namespace 不同编码下的中英文字符大小
{
class Program
{
static void Main(string[] args)
{
ShowCode();
}
private static void ShowCode() {
string[] strArray = { "b","abc","乙","甲乙丙丁"};
byte[] buffer;
string mode, back;
foreach (string str in strArray)
{
for (int i=0; i<=2; i++)
{
if (i==0) //ASCII编码
{
buffer = Encoding.ASCII.GetBytes(str);
back = Encoding.ASCII.GetString(buffer, 0, buffer.Length);
mode = "ASCII";
}
else if(i==1) //UTF8编码
{
buffer = Encoding.UTF8.GetBytes(str);
back = Encoding.UTF8.GetString(buffer, 0, buffer.Length);
mode = "UTF8";
}
else //Unicode编码
{
buffer = Encoding.Unicode.GetBytes(str);
back = Encoding.Unicode.GetString(buffer, 0, buffer.Length);
mode = "Unicode";
}
Console.WriteLine("编码方式:{0} ;字符串:{1} ;长度:{2}", mode, str, buffer.Length);
Console.WriteLine("编码后的字节数组:");
for (int j = 0; j <=buffer.Length-1; j++)
{
Console.WriteLine(" "+buffer[j]+" ");
}
Console.WriteLine("\n编码后字符为:{0} \n",back);
}
Console.WriteLine("----------------------------------------------------------");
}
}
}
}
二,结果如下
b只有在Unicode下面编码为2字节,读到的byte[1]被编码为了0;ASCII码和UTF-8编码相同。
Unicode编码每个字节后面都补了个0;
对于中文:
ASCII码编码后连外星人都读不出来了;
UTF8编码出了3个字节;
Unicode出来了两个字节;