【发布时间】:2014-10-17 02:02:19
【问题描述】:
我一直在努力将这些类转换为 C#(DataInputStream 和 DataOutputStream),并且我已经完成了 DataOutputStream 类,现在问题都在输入流类。
注意:我没有在 C# 中使用 Encoding 类的原因是因为 Java 中的 DataInput/DataOutputStream 使用了自定义的 UTF-8 编码。
基本上,我有这个代码: (C#) 它使用 BinaryReader 类
public String ReadUTF()
{
int utflen = this.ReadUnsignedShort ();
byte[] bytearr = null;
char[] chararr = null;
if(bytearr.Length < utflen)
{
bytearr = new byte[utflen * 2];
chararr = new char[utflen * 2];
}
int c, char2, char3;
int count = 0;
int chararr_count=0;
this.ReadFully(bytearr, 0, utflen);
while (count < utflen) {
c = (int) bytearr[count] & 0xff;
if (c > 127) break;
count++;
chararr[chararr_count++]=(char)c;
}
while (count < utflen) {
c = (int) bytearr[count] & 0xff;
switch (c >> 4) {
case 0: case 1: case 2: case 3: case 4: case 5: case 6: case 7:
/* 0xxxxxxx*/
count++;
chararr[chararr_count++]=(char)c;
break;
case 12: case 13:
/* 110x xxxx 10xx xxxx*/
count += 2;
if (count > utflen)
throw new Exception(
"malformed input: partial character at end");
char2 = (int) bytearr[count-1];
if ((char2 & 0xC0) != 0x80)
throw new Exception(
"malformed input around byte " + count);
chararr[chararr_count++]=(char)(((c & 0x1F) << 6) |
(char2 & 0x3F));
break;
case 14:
/* 1110 xxxx 10xx xxxx 10xx xxxx */
count += 3;
if (count > utflen)
throw new Exception(
"malformed input: partial character at end");
char2 = (int) bytearr[count-2];
char3 = (int) bytearr[count-1];
if (((char2 & 0xC0) != 0x80) || ((char3 & 0xC0) != 0x80))
throw new Exception(
"malformed input around byte " + (count-1));
chararr[chararr_count++]=(char)(((c & 0x0F) << 12) |
((char2 & 0x3F) << 6) |
((char3 & 0x3F) << 0));
break;
default:
/* 10xx xxxx, 1111 xxxx */
throw new Exception(
"malformed input around byte " + count);
}
}
// The number of chars produced may be less than utflen
return new String(chararr, 0, chararr_count);
}
这是我的 ReadUnsignedShort 方法
public int ReadUnsignedShort()
{
int ch1 = BinaryReader.Read();
int ch2 = BinaryReader.Read();
if ((ch1 | ch2) < 0)
{
throw new EndOfStreamException(); // Temp- To be changed
}
return (ch1 << 8) + (ch2 << 0);
}
这也是使用的 Readfully 方法:
public void ReadFully(byte[] b, int off, int len)
{
if(len < 0)
{
throw new IndexOutOfRangeException();
}
int n = 0;
while(n < len)
{
int count = ClientInput.Read(b, off + n, len - n);
if(count < 0)
{
throw new EndOfStreamException(); // Temp - to be changed
}
n += count;
}
}
对于 OutputStream,问题在于我使用的是 Write(int) 而不是 Write(byte) 函数,但我认为这里不是这种情况,或者我一定是盲目的。
如果您对如何发送 UTF 字符串感兴趣,这里是它的 C# 转换:
public int WriteUTF(string str)
{
int strlen = str.Length;
int utflen = 0;
int c, count = 0;
for(int i = 0; i < strlen; i++)
{
c = str.ToCharArray()[i];
if((c >= 0x0001) && (c <= 0x007F))
{
utflen++;
}
else if(c > 0x07FF)
{
utflen += 3;
}
else
{
utflen += 2;
}
}
if(utflen > 65535)
{
throw new Exception("Encoded string is too long: " + utflen + " bytes");
}
byte[] bytearr = null;
bytearr = new byte[(utflen*2) + 2];
bytearr[count++] = (byte) (((uint)utflen >> 8) & 0xFF);
bytearr[count++] = (byte) (((uint)utflen >> 0) & 0xFF);
int x = 0;
for(x = 0; x < strlen; x++)
{
c = str.ToCharArray()[x];
if (!((c >= 0x0001) && (c <= 0x007F))) break;
bytearr[count++] = (byte)c;
}
for(;x < strlen; x++)
{
c = str.ToCharArray()[x];
if ((c >= 0x0001) && (c <= 0x007F))
{
bytearr[count++] = (byte)c;
}
else if (c > 0x07FF)
{
bytearr[count++] = (byte) (0xE0 | ((c >> 12) & 0x0F));
bytearr[count++] = (byte) (0x80 | ((c >> 6) & 0x3F));
bytearr[count++] = (byte) (0x80 | ((c >> 0) & 0x3F));
}
else
{
bytearr[count++] = (byte) (0xC0 | ((c >> 6) & 0x1F));
bytearr[count++] = (byte) (0x80 | ((c >> 0) & 0x3F));
}
}
ClientOutput.Write (bytearr, 0, utflen+2);
return utflen + 2;
}
希望我已经提供了足够的信息,以便在阅读 UTF 值方面获得一点帮助,这确实为我的项目进度设置了障碍。
【问题讨论】: