private static string DecodeUTF(int utfSize, IDataInput @in)
{
byte[] buf = new byte[utfSize];
char[] @out = new char[utfSize];
@in.ReadFully(buf, 0, utfSize);
return(ConvertUTF8WithBuf(buf, @out, 0, utfSize));
}
public static string ReadUTF(IDataInput @in)
{
int utflen = @in.ReadUnsignedShort();
byte[] bytearr = null;
char[] chararr = null;
if (@in is DataInputStream)
{
DataInputStream dis = (DataInputStream)@in;
if (dis.bytearr.Length < utflen)
{
dis.bytearr = new byte[utflen * 2];
dis.chararr = new char[utflen * 2];
}
chararr = dis.chararr;
bytearr = dis.bytearr;
}
else
{
bytearr = new byte[utflen];
chararr = new char[utflen];
}
int c, char2, char3;
int count = 0;
int chararr_count = 0;
@in.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 FormatException(
"malformed input: partial character at end");
}
char2 = (int)bytearr[count - 1];
if ((char2 & 0xC0) != 0x80)
{
throw new FormatException(
"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 FormatException(
"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 FormatException(
"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 FormatException(
"malformed input around byte " + count);
}
}
// The number of chars produced may be less than utflen
return(new string(chararr, 0, chararr_count));
}
public static string ReadUTF(IDataInput @in)
{
int utflen = @in.ReadUnsignedShort();
byte[] bytearr = null;
char[] chararr = null;
if (@in is DataInputStream)
{
DataInputStream dis = (DataInputStream)@in;
if (dis.bytearr.Length < utflen)
{
dis.bytearr = new byte[utflen * 2];
dis.chararr = new char[utflen * 2];
}
chararr = dis.chararr;
bytearr = dis.bytearr;
}
else
{
bytearr = new byte[utflen];
chararr = new char[utflen];
}
int c, char2, char3;
int count = 0;
int chararr_count = 0;
@in.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 FormatException(
"malformed input: partial character at end");
char2 = (int)bytearr[count - 1];
if ((char2 & 0xC0) != 0x80)
throw new FormatException(
"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 FormatException(
"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 FormatException(
"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 FormatException(
"malformed input around byte " + count);
}
}
// The number of chars produced may be less than utflen
return new string(chararr, 0, chararr_count);
}
