| 1 |
769 |
jeremybenn |
/* UTF_16Encoder.java --
|
| 2 |
|
|
Copyright (C) 2002 Free Software Foundation, Inc.
|
| 3 |
|
|
|
| 4 |
|
|
This file is part of GNU Classpath.
|
| 5 |
|
|
|
| 6 |
|
|
GNU Classpath is free software; you can redistribute it and/or modify
|
| 7 |
|
|
it under the terms of the GNU General Public License as published by
|
| 8 |
|
|
the Free Software Foundation; either version 2, or (at your option)
|
| 9 |
|
|
any later version.
|
| 10 |
|
|
|
| 11 |
|
|
GNU Classpath is distributed in the hope that it will be useful, but
|
| 12 |
|
|
WITHOUT ANY WARRANTY; without even the implied warranty of
|
| 13 |
|
|
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
|
| 14 |
|
|
General Public License for more details.
|
| 15 |
|
|
|
| 16 |
|
|
You should have received a copy of the GNU General Public License
|
| 17 |
|
|
along with GNU Classpath; see the file COPYING. If not, write to the
|
| 18 |
|
|
Free Software Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
|
| 19 |
|
|
02110-1301 USA.
|
| 20 |
|
|
|
| 21 |
|
|
Linking this library statically or dynamically with other modules is
|
| 22 |
|
|
making a combined work based on this library. Thus, the terms and
|
| 23 |
|
|
conditions of the GNU General Public License cover the whole
|
| 24 |
|
|
combination.
|
| 25 |
|
|
|
| 26 |
|
|
As a special exception, the copyright holders of this library give you
|
| 27 |
|
|
permission to link this library with independent modules to produce an
|
| 28 |
|
|
executable, regardless of the license terms of these independent
|
| 29 |
|
|
modules, and to copy and distribute the resulting executable under
|
| 30 |
|
|
terms of your choice, provided that you also meet, for each linked
|
| 31 |
|
|
independent module, the terms and conditions of the license of that
|
| 32 |
|
|
module. An independent module is a module which is not derived from
|
| 33 |
|
|
or based on this library. If you modify this library, you may extend
|
| 34 |
|
|
this exception to your version of the library, but you are not
|
| 35 |
|
|
obligated to do so. If you do not wish to do so, delete this
|
| 36 |
|
|
exception statement from your version. */
|
| 37 |
|
|
|
| 38 |
|
|
package gnu.java.nio.charset;
|
| 39 |
|
|
|
| 40 |
|
|
import java.nio.ByteBuffer;
|
| 41 |
|
|
import java.nio.ByteOrder;
|
| 42 |
|
|
import java.nio.CharBuffer;
|
| 43 |
|
|
import java.nio.charset.Charset;
|
| 44 |
|
|
import java.nio.charset.CharsetEncoder;
|
| 45 |
|
|
import java.nio.charset.CoderResult;
|
| 46 |
|
|
|
| 47 |
|
|
/**
|
| 48 |
|
|
* Encoder for UTF-16, UTF-15LE, and UTF-16BE.
|
| 49 |
|
|
*
|
| 50 |
|
|
* @author Jesse Rosenstock
|
| 51 |
|
|
*/
|
| 52 |
|
|
final class UTF_16Encoder extends CharsetEncoder
|
| 53 |
|
|
{
|
| 54 |
|
|
// byte orders
|
| 55 |
|
|
static final int BIG_ENDIAN = 0;
|
| 56 |
|
|
static final int LITTLE_ENDIAN = 1;
|
| 57 |
|
|
|
| 58 |
|
|
private static final char BYTE_ORDER_MARK = 0xFEFF;
|
| 59 |
|
|
|
| 60 |
|
|
private final ByteOrder byteOrder;
|
| 61 |
|
|
private final boolean useByteOrderMark;
|
| 62 |
|
|
private boolean needsByteOrderMark;
|
| 63 |
|
|
|
| 64 |
|
|
UTF_16Encoder (Charset cs, int byteOrder, boolean useByteOrderMark)
|
| 65 |
|
|
{
|
| 66 |
|
|
super (cs, 2.0f,
|
| 67 |
|
|
useByteOrderMark ? 4.0f : 2.0f,
|
| 68 |
|
|
byteOrder == BIG_ENDIAN
|
| 69 |
|
|
? new byte[] { (byte) 0xFF, (byte) 0xFD }
|
| 70 |
|
|
: new byte[] { (byte) 0xFD, (byte) 0xFF });
|
| 71 |
|
|
this.byteOrder = (byteOrder == BIG_ENDIAN) ?
|
| 72 |
|
|
ByteOrder.BIG_ENDIAN : ByteOrder.LITTLE_ENDIAN;
|
| 73 |
|
|
this.useByteOrderMark = useByteOrderMark;
|
| 74 |
|
|
this.needsByteOrderMark = useByteOrderMark;
|
| 75 |
|
|
}
|
| 76 |
|
|
|
| 77 |
|
|
protected CoderResult encodeLoop (CharBuffer in, ByteBuffer out)
|
| 78 |
|
|
{
|
| 79 |
|
|
// TODO: Optimize this in the case in.hasArray() / out.hasArray()
|
| 80 |
|
|
|
| 81 |
|
|
ByteOrder originalBO = out.order();
|
| 82 |
|
|
out.order(byteOrder);
|
| 83 |
|
|
|
| 84 |
|
|
if (needsByteOrderMark)
|
| 85 |
|
|
{
|
| 86 |
|
|
if (out.remaining () < 2)
|
| 87 |
|
|
{
|
| 88 |
|
|
out.order(originalBO);
|
| 89 |
|
|
return CoderResult.OVERFLOW;
|
| 90 |
|
|
}
|
| 91 |
|
|
out.putChar (BYTE_ORDER_MARK);
|
| 92 |
|
|
needsByteOrderMark = false;
|
| 93 |
|
|
}
|
| 94 |
|
|
|
| 95 |
|
|
int inPos = in.position ();
|
| 96 |
|
|
try
|
| 97 |
|
|
{
|
| 98 |
|
|
while (in.hasRemaining ())
|
| 99 |
|
|
{
|
| 100 |
|
|
char c = in.get ();
|
| 101 |
|
|
if (0xD800 <= c && c <= 0xDFFF)
|
| 102 |
|
|
{
|
| 103 |
|
|
// c is a surrogate
|
| 104 |
|
|
|
| 105 |
|
|
// make sure c is a high surrogate
|
| 106 |
|
|
if (c > 0xDBFF)
|
| 107 |
|
|
return CoderResult.malformedForLength (1);
|
| 108 |
|
|
if (in.remaining () < 1)
|
| 109 |
|
|
return CoderResult.UNDERFLOW;
|
| 110 |
|
|
char d = in.get ();
|
| 111 |
|
|
// make sure d is a low surrogate
|
| 112 |
|
|
if (d < 0xDC00 || d > 0xDFFF)
|
| 113 |
|
|
return CoderResult.malformedForLength (1);
|
| 114 |
|
|
out.putChar (c);
|
| 115 |
|
|
out.putChar (d);
|
| 116 |
|
|
inPos += 2;
|
| 117 |
|
|
}
|
| 118 |
|
|
else
|
| 119 |
|
|
{
|
| 120 |
|
|
if (out.remaining () < 2)
|
| 121 |
|
|
{
|
| 122 |
|
|
out.order(originalBO);
|
| 123 |
|
|
return CoderResult.OVERFLOW;
|
| 124 |
|
|
}
|
| 125 |
|
|
out.putChar (c);
|
| 126 |
|
|
inPos++;
|
| 127 |
|
|
}
|
| 128 |
|
|
}
|
| 129 |
|
|
out.order(originalBO);
|
| 130 |
|
|
return CoderResult.UNDERFLOW;
|
| 131 |
|
|
}
|
| 132 |
|
|
finally
|
| 133 |
|
|
{
|
| 134 |
|
|
in.position (inPos);
|
| 135 |
|
|
}
|
| 136 |
|
|
}
|
| 137 |
|
|
|
| 138 |
|
|
protected void implReset ()
|
| 139 |
|
|
{
|
| 140 |
|
|
needsByteOrderMark = useByteOrderMark;
|
| 141 |
|
|
}
|
| 142 |
|
|
|
| 143 |
|
|
// TODO: override canEncode(char) and canEncode(CharSequence)
|
| 144 |
|
|
// for performance
|
| 145 |
|
|
}
|