libjava/gnu/java/nio/charset/UTF_16Decoder.java

   1 /* UTF_16Decoder.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., 59 Temple Place, Suite 330, Boston, MA
  19 02111-1307 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.CharBuffer;
  42 import java.nio.charset.Charset;
  43 import java.nio.charset.CharsetDecoder;
  44 import java.nio.charset.CoderResult;
  45
  46 /**
  47  * Decoder for UTF-16, UTF-15LE, and UTF-16BE.
  48  *
  49  * @author Jesse Rosenstock
  50  */
  51 final class UTF_16Decoder extends CharsetDecoder
  52 {
  53   // byte orders
  54   static final int BIG_ENDIAN = 0;
  55   static final int LITTLE_ENDIAN = 1;
  56   static final int UNKNOWN_ENDIAN = 2;
  57
  58   private static final char BYTE_ORDER_MARK = '\uFEFF';
  59   private static final char REVERSED_BYTE_ORDER_MARK = '\uFFFE';
  60
  61   private final int originalByteOrder;
  62   private int byteOrder;
  63
  64   UTF_16Decoder (Charset cs, int byteOrder)
  65   {
  66     super (cs, 0.5f, 1.0f);
  67     this.originalByteOrder = byteOrder;
  68     this.byteOrder = byteOrder;
  69   }
  70
  71   protected CoderResult decodeLoop (ByteBuffer in, CharBuffer out)
  72   {
  73     // TODO: Optimize this in the case in.hasArray() / out.hasArray()
  74
  75     int inPos = in.position ();
  76     try
  77       {
  78         while (in.remaining () >= 2)
  79           {
  80             byte b1 = in.get ();
  81             byte b2 = in.get ();
  82
  83             // handle byte order mark
  84             if (byteOrder == UNKNOWN_ENDIAN)
  85               {
  86                 char c = (char) ((b1 << 8) | b2);
  87                 if (c == BYTE_ORDER_MARK)
  88                   {
  89                     byteOrder = BIG_ENDIAN;
  90                     inPos += 2;
  91                     continue;
  92                   }
  93                 else if (c == REVERSED_BYTE_ORDER_MARK)
  94                   {
  95                     byteOrder = LITTLE_ENDIAN;
  96                     inPos += 2;
  97                     continue;
  98                   }
  99                 else
 100                   {
 101                     // assume big endian, do not consume bytes,
 102                     // continue with normal processing
 103                     byteOrder = BIG_ENDIAN;
 104                   }
 105               }
 106
 107             char c = byteOrder == BIG_ENDIAN ? (char) ((b1 << 8) | b2)
 108                                              : (char) ((b2 << 8) | b1);
 109
 110             if (0xD800 <= c && c <= 0xDFFF)
 111               {
 112                 // c is a surrogate
 113
 114                 // make sure c is a high surrogate
 115                 if (c > 0xDBFF)
 116                   return CoderResult.malformedForLength (2);
 117                 if (in.remaining () < 2)
 118                   return CoderResult.UNDERFLOW;
 119                 byte b3 = in.get ();
 120                 byte b4 = in.get ();
 121                 char d = byteOrder == BIG_ENDIAN ? (char) ((b3 << 8) | b4)
 122                                                  : (char) ((b4 << 8) | b3);
 123                 // make sure d is a low surrogate
 124                 if (d < 0xDC00 || d > 0xDFFF)
 125                   return CoderResult.malformedForLength (2);
 126                 out.put (c);
 127                 out.put (d);
 128                 inPos += 4;
 129               }
 130             else
 131               {
 132                 if (!out.hasRemaining ())
 133                   return CoderResult.UNDERFLOW;
 134                 out.put (c);
 135                 inPos += 2;
 136               }
 137           }
 138
 139         return CoderResult.UNDERFLOW;
 140       }
 141     finally
 142       {
 143         in.position (inPos);
 144       }
 145   }
 146
 147   /**
 148    * Writes <code>c</code> to <code>out</code> in the byte order
 149    * specified by <code>byteOrder</code>.
 150    **/
 151   private void put (ByteBuffer out, char c)
 152   {
 153     if (byteOrder == BIG_ENDIAN)
 154       {
 155         out.put ((byte) (c >> 8));
 156         out.put ((byte) (c & 0xFF));
 157       }
 158     else
 159       {
 160         out.put ((byte) (c & 0xFF));
 161         out.put ((byte) (c >> 8));
 162       }
 163   }
 164
 165   protected void implReset ()
 166   {
 167     byteOrder = originalByteOrder;
 168   }
 169 }