1 /*

     2  * Copyright (c) 2003, Oracle and/or its affiliates. All rights reserved.

     3  * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.

     4  *

     5  * This code is free software; you can redistribute it and/or modify it

     6  * under the terms of the GNU General Public License version 2 only, as

     7  * published by the Free Software Foundation.  Oracle designates this

     8  * particular file as subject to the "Classpath" exception as provided

     9  * by Oracle in the LICENSE file that accompanied this code.

    10  *

    11  * This code is distributed in the hope that it will be useful, but WITHOUT

    12  * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or

    13  * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License

    14  * version 2 for more details (a copy is included in the LICENSE file that

    15  * accompanied this code).

    16  *

    17  * You should have received a copy of the GNU General Public License version

    18  * 2 along with this work; if not, write to the Free Software Foundation,

    19  * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.

    20  *

    21  * Please contact Oracle, 500 Oracle Parkway, Redwood Shores, CA 94065 USA

    22  * or visit www.oracle.com if you need additional information or have any

    23  * questions.

    24  */

    25 

    26 package sun.io;

    27 

    28 import sun.nio.cs.ext.JIS_X_0208_Solaris_Decoder;

    29 import sun.nio.cs.ext.JIS_X_0212_Solaris_Decoder;

    30 /**

    31  *

    32  * @author Limin Shi

    33  * @author Ian Little

    34  *

    35  * EUC_JP variant converter for Solaris with vendor defined chars

    36  * added (4765370)

    37  */

    38 

    39 

    40 public class ByteToCharEUC_JP_Solaris extends ByteToCharEUC_JP {

    41     private byte savedSecond = 0;

    42 

    43     ByteToCharJIS0201 bcJIS0201 = new ByteToCharJIS0201();

    44     ByteToCharJIS0212_Solaris bcJIS0212 = new ByteToCharJIS0212_Solaris();

    45 

    46     short[] j0208Index1 = JIS_X_0208_Solaris_Decoder.getIndex1();

    47     String[] j0208Index2 = JIS_X_0208_Solaris_Decoder.getIndex2();

    48     ByteToCharJIS0212_Solaris j0212Decoder = new ByteToCharJIS0212_Solaris();

    49 

    50     public ByteToCharEUC_JP_Solaris() {

    51         super();

    52         start = 0xA1;

    53         end = 0xFE;

    54         savedSecond = 0;

    55     }

    56 

    57     public int flush(char[] output, int outStart, int outEnd)

    58         throws MalformedInputException

    59     {

    60         if (savedSecond != 0) {

    61             reset();

    62             throw new MalformedInputException();

    63         }

    64         reset();

    65         return 0;

    66     }

    67 

    68     /**

    69      * Resets the converter.

    70      * Call this method to reset the converter to its initial state

    71      */

    72     public void reset() {

    73         super.reset();

    74         savedSecond = 0;

    75     }

    76 

    77     public String getCharacterEncoding() {

    78         return "eucJP-open";

    79     }

    80 

    81     protected char convSingleByte(int b) {

    82         if (b < 0 || b > 0x7F)

    83             return REPLACE_CHAR;

    84         return bcJIS0201.getUnicode(b);

    85     }

    86 

    87     protected char getUnicode(int byte1, int byte2) {

    88         if (byte1 == 0x8E) {

    89             return bcJIS0201.getUnicode(byte2 - 256);

    90         }

    91         // Fix for bug 4121358 - similar fix for bug 4117820 put

    92         // into ByteToCharDoubleByte.getUnicode()

    93         if (((byte1 < 0) || (byte1 > j0208Index1.length))

    94             || ((byte2 < start) || (byte2 > end)))

    95             return REPLACE_CHAR;

    96 

    97         char result = super.getUnicode(byte1, byte2);

    98         if (result != '\uFFFD') {

    99             return result;

   100         } else {

   101             int n = (j0208Index1[byte1 - 0x80] & 0xf) * (end - start + 1)

   102                 + (byte2 - start);

   103         return j0208Index2[j0208Index1[byte1 - 0x80] >> 4].charAt(n);

   104         }

   105     }

   106 

   107     protected char decode0212(int byte1, int byte2) {

   108         return j0212Decoder.getUnicode(byte1, byte2);

   109     }

   110 

   111     /**

   112      * Converts sequences of bytes to characters.

   113      * Conversions that result in Exceptions can be restarted by calling

   114      * convert again, with appropriately modified parameters.

   115      * @return the characters written to output.

   116      * @param input byte array containing text in Double/single Byte

   117      * @param inStart offset in input array

   118      * @param inEnd offset of last byte to be converted

   119      * @param output character array to receive conversion result

   120      * @param outStart starting offset

   121      * @param outEnd offset of last byte to be written to

   122      * @throw UnsupportedCharacterException for any bytes

   123      * that cannot be converted to the external character set.

   124      */

   125     public int convert(byte[] input, int inOff, int inEnd,

   126                        char[] output, int outOff, int outEnd)

   127         throws UnknownCharacterException,

   128                ConversionBufferFullException

   129     {

   130         char    outputChar = REPLACE_CHAR;

   131         int     inputSize = 0;          // Size of input

   132 

   133         // Record beginning offsets

   134         charOff = outOff;

   135         byteOff = inOff;

   136 

   137         // Loop until we hit the end of the input

   138         while (byteOff < inEnd) {

   139             int byte1, byte2;

   140 

   141             if (savedByte == 0) {

   142                 byte1 = input[byteOff];

   143                 inputSize = 1;

   144             } else {

   145                 byte1 = savedByte;

   146                 savedByte = 0;

   147                 inputSize = 0;

   148             }

   149 

   150             outputChar = convSingleByte(byte1);

   151 

   152             if (outputChar == REPLACE_CHAR) {   // Multibyte char

   153                 if ((byte1 & 0xff) == 0x8F) {   // JIS0212

   154                     if (byteOff + inputSize + 1 >= inEnd) {

   155                         // split in the middle of a character

   156                         // save the first 2 bytes for next time around

   157                         savedByte = (byte) byte1;

   158                         byteOff += inputSize;

   159                         if (byteOff < inEnd) {

   160                             savedSecond = input[byteOff];

   161                             byteOff++;

   162                         }

   163                         break;

   164                     }

   165                     if (savedSecond != 0) {

   166                         byte1 = savedSecond & 0xff;

   167                         savedSecond = 0;

   168                     } else {

   169                         byte1 = input[byteOff + inputSize] & 0xff;

   170                         inputSize++;

   171                     }

   172                     byte2 = input[byteOff + inputSize] & 0xff;

   173                     inputSize++;

   174                     outputChar = bcJIS0212.getUnicode(byte1-0x80, byte2-0x80);

   175                 } else { // JIS0208

   176                     if (byteOff + inputSize >= inEnd) {

   177                         // split in the middle of a character

   178                         // save the first byte for next time around

   179                         savedByte = (byte) byte1;

   180                         byteOff += inputSize;

   181                         break;

   182                     }

   183                     byte1 &= 0xff;

   184                     byte2 = input[byteOff + inputSize] & 0xff;

   185                     inputSize++;

   186                     outputChar = getUnicode(byte1, byte2);

   187                 }

   188             }

   189 

   190             if (outputChar == REPLACE_CHAR) {

   191                 if (subMode)

   192                     outputChar = subChars[0];

   193                 else {

   194                     badInputLength = inputSize;

   195                     throw new UnknownCharacterException();

   196                 }

   197             }

   198 

   199             if (charOff >= outEnd)

   200                 throw new ConversionBufferFullException();

   201 

   202             output[charOff++] = outputChar;

   203             byteOff += inputSize;

   204         }

   205 

   206         return charOff - outOff;

   207     }

   208 

   209 }