1 /*

     2  * Copyright (c) 1997, 2002, 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 /**

    29  * @author Limin Shi

    30  */

    31 

    32 public abstract class CharToByteDoubleByte extends CharToByteConverter {

    33 

    34     /*

    35      * 1st level index, provided by subclass

    36      */

    37     protected short index1[];

    38 

    39     /*

    40      * 2nd level index, provided by subclass

    41      */

    42     protected String  index2[];

    43 

    44     protected char highHalfZoneCode;

    45 

    46     public short[] getIndex1() {

    47         return index1;

    48     }

    49 

    50     public String[] getIndex2() {

    51         return index2;

    52     }

    53 

    54     public int flush(byte[] output, int outStart, int outEnd)

    55         throws MalformedInputException, ConversionBufferFullException

    56     {

    57         if (highHalfZoneCode != 0) {

    58             highHalfZoneCode = 0;

    59             badInputLength = 0;

    60             throw new MalformedInputException();

    61         }

    62         byteOff = charOff = 0;

    63         return 0;

    64     }

    65 

    66     /**

    67      * Converts characters to sequences of bytes.

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

    69      * convert again, with appropriately modified parameters.

    70      * @return the characters written to output.

    71      * @param input char array containing text in Unicode

    72      * @param inStart offset in input array

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

    74      * @param output byte array to receive conversion result

    75      * @param outStart starting offset

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

    77      * @throw UnsupportedCharacterException for any character

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

    79      */

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

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

    82         throws MalformedInputException, UnknownCharacterException,

    83                ConversionBufferFullException

    84     {

    85         char    inputChar;                 // Input character to be converted

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

    87         int     inputSize = 0;             // Size of input

    88         int     outputSize = 0;            // Size of output

    89         byte[]  tmpbuf = new byte[2];

    90 

    91         // Record beginning offsets

    92         charOff = inOff;

    93         byteOff = outOff;

    94 

    95         if (highHalfZoneCode != 0) {

    96             inputChar = highHalfZoneCode;

    97             highHalfZoneCode = 0;

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

    99                 // This is legal UTF16 sequence.

   100                 badInputLength = 1;

   101                 throw new UnknownCharacterException();

   102             } else {

   103                 // This is illegal UTF16 sequence.

   104                 badInputLength = 0;

   105                 throw new MalformedInputException();

   106             }

   107         }

   108 

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

   110         while(charOff < inEnd) {

   111             inputSize = 1;

   112             outputByte = tmpbuf;

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

   114 

   115             // Is this a high surrogate?

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

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

   118                 if (charOff + 1 >= inEnd) {

   119                     highHalfZoneCode = inputChar;

   120                     break;

   121                 }

   122 

   123                 // Is there a low surrogate following?

   124                 inputChar = input[charOff + 1];

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

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

   127                     // surrogates.  Is substitution enabled?

   128                     if (subMode) {

   129                         outputByte = subBytes;

   130                         outputSize = subBytes.length;

   131                         inputSize = 2;

   132                     } else {

   133                         badInputLength = 2;

   134                         throw new UnknownCharacterException();

   135                     }

   136                 } else {

   137                     // We have a malformed surrogate pair

   138                     badInputLength = 1;

   139                     throw new MalformedInputException();

   140                 }

   141             }

   142             // Is this an unaccompanied low surrogate?

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

   144                 badInputLength = 1;

   145                 throw new MalformedInputException();

   146             } else {

   147                 outputSize = convSingleByte(inputChar, outputByte);

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

   149                     int ncode = getNative(inputChar);

   150                     if (ncode != 0 ) {

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

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

   153                         outputSize = 2;

   154                     } else {

   155                         if (subMode) {

   156                             outputByte = subBytes;

   157                             outputSize = subBytes.length;

   158                         } else {

   159                             badInputLength = 1;

   160                             throw new UnknownCharacterException();

   161                         }

   162                     }

   163                 }

   164             }

   165 

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

   167             if (byteOff + outputSize > outEnd)

   168                 throw new ConversionBufferFullException();

   169 

   170             // Put the byte in the output buffer

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

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

   173             }

   174             charOff += inputSize;

   175         }

   176         // Return the length written to the output buffer

   177         return byteOff - outOff;

   178     }

   179 

   180 

   181     /**

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

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

   184      */

   185     public int getMaxBytesPerChar() {

   186         return 2;

   187     }

   188 

   189     /**

   190      *  Resets the converter.

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

   192      */

   193     public void reset() {

   194         byteOff = charOff = 0;

   195         highHalfZoneCode = 0;

   196     }

   197 

   198     /**

   199      * Return whether a character is mappable or not

   200      * @return true if a character is mappable

   201      */

   202     public boolean canConvert(char ch) {

   203         byte[] outByte = new byte[2];

   204 

   205         if ((ch == (char) 0) || (convSingleByte(ch, outByte) != 0))

   206             return true;

   207         if (this.getNative(ch) != 0)

   208             return true;

   209         return false;

   210     }

   211 

   212 

   213     /*

   214      * Can be changed by subclass

   215      */

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

   217         if (inputChar < 0x80) {

   218             outputByte[0] = (byte)(inputChar & 0x7f);

   219             return 1;

   220         }

   221         return 0;

   222     }

   223 

   224     /*

   225      * Can be changed by subclass

   226      */

   227     protected int getNative(char ch) {

   228         int offset = index1[((ch & 0xff00) >> 8 )] << 8;

   229         return index2[offset >> 12].charAt((offset & 0xfff) + (ch & 0xff));

   230     }

   231 

   232 }