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_Encoder;

    29 import sun.nio.cs.ext.JIS_X_0212_Solaris_Encoder;

    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 public class CharToByteEUC_JP_Solaris extends CharToByteEUC_JP {

    40     CharToByteJIS0201 cbJIS0201 = new CharToByteJIS0201();

    41     CharToByteJIS0212_Solaris cbJIS0212 = new CharToByteJIS0212_Solaris();

    42 

    43     short[] j0208Index1 = JIS_X_0208_Solaris_Encoder.getIndex1();

    44     String[] j0208Index2 = JIS_X_0208_Solaris_Encoder.getIndex2();

    45 

    46     public String getCharacterEncoding() {

    47         return "eucJP-open";

    48     }

    49 

    50     protected int convSingleByte(char inputChar, byte[] outputByte) {

    51         byte b;

    52 

    53         if (inputChar == 0) {

    54             outputByte[0] = (byte)0;

    55             return 1;

    56         }

    57 

    58         if ((b = cbJIS0201.getNative(inputChar)) == 0)

    59             return 0;

    60 

    61         if (b > 0 && b < 128) {

    62             outputByte[0] = b;

    63             return 1;

    64         }

    65         outputByte[0] = (byte)0x8E;

    66         outputByte[1] = b;

    67         return 2;

    68     }

    69 

    70     protected int getNative(char ch) {

    71         int r = super.getNative(ch);

    72         if (r != 0) {

    73             return r;

    74         } else {

    75             int offset = j0208Index1[((ch & 0xff00) >> 8 )] << 8;

    76             r = j0208Index2[offset >> 12].charAt((offset & 0xfff) + (ch & 0xff));

    77             if (r > 0x7500)

    78                 return 0x8f8080 + cbJIS0212.getNative(ch);

    79         }

    80         return (r == 0)? r : r + 0x8080;

    81     }

    82 

    83 

    84     /**

    85      * Converts characters to sequences of bytes.

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

    87      * convert again, with appropriately modified parameters.

    88      * @return the characters written to output.

    89      * @param input char array containing text in Unicode

    90      * @param inStart offset in input array

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

    92      * @param output byte array to receive conversion result

    93      * @param outStart starting offset

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

    95      * @throw UnsupportedCharacterException for any character

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

    97      */

    98     public int convert(char[] input, int inOff, int inEnd,

    99                        byte[] output, int outOff, int outEnd)

   100         throws MalformedInputException, UnknownCharacterException,

   101                ConversionBufferFullException

   102     {

   103         char    inputChar;                 // Input character to be converted

   104         byte[]  outputByte;                // Output byte written to output

   105         int     inputSize = 0;             // Size of input

   106         int     outputSize = 0;            // Size of output

   107         byte[]  tmpbuf = new byte[4];

   108 

   109         // Record beginning offsets

   110         charOff = inOff;

   111         byteOff = outOff;

   112 

   113         if (highHalfZoneCode != 0) {

   114             inputChar = highHalfZoneCode;

   115             highHalfZoneCode = 0;

   116             if (input[inOff] >= 0xdc00 && input[inOff] <= 0xdfff) {

   117                 // This is legal UTF16 sequence.

   118                 badInputLength = 1;

   119                 throw new UnknownCharacterException();

   120             } else {

   121                 // This is illegal UTF16 sequence.

   122                 badInputLength = 0;

   123                 throw new MalformedInputException();

   124             }

   125         }

   126 

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

   128         while(charOff < inEnd) {

   129             inputSize = 1;

   130             outputByte = tmpbuf;

   131             inputChar = input[charOff]; // Get the input character

   132 

   133             // Is this a high surrogate?

   134             if(inputChar >= '\uD800' && inputChar <= '\uDBFF') {

   135                 // Is this the last character of the input?

   136                 if (charOff + 1 >= inEnd) {

   137                     highHalfZoneCode = inputChar;

   138                     break;

   139                 }

   140 

   141                 // Is there a low surrogate following?

   142                 inputChar = input[charOff + 1];

   143                 if (inputChar >= '\uDC00' && inputChar <= '\uDFFF') {

   144                     // We have a valid surrogate pair.  Too bad we don't do

   145                     // surrogates.  Is substitution enabled?

   146                     if (subMode) {

   147                         outputByte = subBytes;

   148                         outputSize = subBytes.length;

   149                         inputSize = 2;

   150                     } else {

   151                         badInputLength = 2;

   152                         throw new UnknownCharacterException();

   153                     }

   154                 } else {

   155                     // We have a malformed surrogate pair

   156                     badInputLength = 1;

   157                     throw new MalformedInputException();

   158                 }

   159             }

   160             // Is this an unaccompanied low surrogate?

   161             else if (inputChar >= '\uDC00' && inputChar <= '\uDFFF') {

   162                 badInputLength = 1;

   163                 throw new MalformedInputException();

   164             } else {

   165                 outputSize = convSingleByte(inputChar, outputByte);

   166                 if (outputSize == 0) { // DoubleByte

   167                     int ncode = getNative(inputChar);

   168                     if (ncode != 0 ) {

   169                         if ((ncode & 0xFF0000) == 0) {

   170                             outputByte[0] = (byte) ((ncode & 0xff00) >> 8);

   171                             outputByte[1] = (byte) (ncode & 0xff);

   172                             outputSize = 2;

   173                         } else {

   174                             outputByte[0] = (byte) 0x8F;

   175                             outputByte[1] = (byte) ((ncode & 0xff00) >> 8);

   176                             outputByte[2] = (byte) (ncode & 0xff);

   177                             outputSize = 3;

   178                         }

   179                     } else {

   180                         if (subMode) {

   181                             outputByte = subBytes;

   182                             outputSize = subBytes.length;

   183                         } else {

   184                             badInputLength = 1;

   185                             throw new UnknownCharacterException();

   186                         }

   187                     }

   188                 }

   189             }

   190 

   191             // If we don't have room for the output, throw an exception

   192             if (byteOff + outputSize > outEnd)

   193                 throw new ConversionBufferFullException();

   194 

   195             // Put the byte in the output buffer

   196             for (int i = 0; i < outputSize; i++) {

   197                 output[byteOff++] = outputByte[i];

   198             }

   199             charOff += inputSize;

   200         }

   201         // Return the length written to the output buffer

   202         return byteOff - outOff;

   203     }

   204 

   205 

   206     /**

   207      * the maximum number of bytes needed to hold a converted char

   208      * @returns the maximum number of bytes needed for a converted char

   209      */

   210     public int getMaxBytesPerChar() {

   211         return 3;

   212     }

   213 }