1 /*

     2  * Copyright (c) 1996, 2008, 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 static sun.nio.cs.CharsetMapping.*;

    29 

    30 /**

    31 * A table driven conversion from char to byte for single byte

    32 * character sets.  Tables will reside in the class CharToByteYYYYY,

    33 * where YYYYY is a unique character set identifier

    34 

    35     < TBD: Tables are of the form... >

    36 

    37 *

    38 * @author Lloyd Honomichl

    39 * @author Asmus Freytag

    40 * @version 8/28/96

    41 */

    42 

    43 public abstract class CharToByteSingleByte extends CharToByteConverter {

    44 

    45     /*

    46      * 1st level index, provided by subclass

    47      */

    48     protected char[] index1;

    49 

    50     /*

    51      * 2nd level index, provided by subclass

    52      */

    53     protected char[] index2;

    54 

    55     /*

    56      * Mask to isolate bits for 1st level index, from subclass

    57      */

    58     protected int   mask1;

    59 

    60     /*

    61      * Mask to isolate bits for 2nd level index, from subclass

    62      */

    63     protected int   mask2;

    64 

    65     /*

    66      * Shift to isolate bits for 1st level index, from subclass

    67      */

    68     protected int   shift;

    69 

    70     private char highHalfZoneCode;

    71 

    72     public char[] getIndex1() {

    73         return index1;

    74     }

    75 

    76     public char[] getIndex2() {

    77         return index2;

    78     }

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

    80         throws MalformedInputException

    81     {

    82         if (highHalfZoneCode != 0) {

    83             highHalfZoneCode = 0;

    84             badInputLength = 0;

    85             throw new MalformedInputException();

    86         }

    87         byteOff = charOff = 0;

    88         return 0;

    89     }

    90 

    91     /**

    92      * Converts characters to sequences of bytes.

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

    94      * convert again, with appropriately modified parameters.

    95      * @return the characters written to output.

    96      * @param input char array containing text in Unicode

    97      * @param inStart offset in input array

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

    99      * @param output byte array to receive conversion result

   100      * @param outStart starting offset

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

   102      * @throw MalformedInputException for any sequence of chars that is

   103      * illegal in Unicode (principally unpaired surrogates

   104      * and \uFFFF or \uFFFE), including any partial surrogate pair

   105      * which occurs at the end of an input buffer.

   106      * @throw UnsupportedCharacterException for any character that

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

   108      */

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

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

   111         throws MalformedInputException,

   112                UnknownCharacterException,

   113                ConversionBufferFullException

   114     {

   115         char    inputChar;          // Input character to be converted

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

   117         int     inputSize;          // Size of input

   118         int     outputSize;         // Size of output

   119 

   120         byte[]  tmpArray = new byte[1];

   121 

   122         // Record beginning offsets

   123         charOff = inOff;

   124         byteOff = outOff;

   125 

   126         if (highHalfZoneCode != 0) {

   127             inputChar = highHalfZoneCode;

   128             highHalfZoneCode = 0;

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

   130                 // This is legal UTF16 sequence.

   131                 badInputLength = 1;

   132                 throw new UnknownCharacterException();

   133             } else {

   134                 // This is illegal UTF16 sequence.

   135                 badInputLength = 0;

   136                 throw new MalformedInputException();

   137             }

   138         }

   139 

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

   141         while(charOff < inEnd) {

   142 

   143             outputByte = tmpArray;

   144 

   145             // Get the input character

   146             inputChar = input[charOff];

   147 

   148             // Default output size

   149             outputSize = 1;

   150 

   151             // Assume this is a simple character

   152             inputSize = 1;

   153 

   154             // Is this a high surrogate?

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

   156                 // Is this the last character in the input?

   157                 if (charOff + 1 >= inEnd) {

   158                     highHalfZoneCode = inputChar;

   159                     break;

   160                 }

   161 

   162                 // Is there a low surrogate following?

   163                 inputChar = input[charOff + 1];

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

   165                     // We have a valid surrogate pair.  Too bad we don't map

   166                     //  surrogates.  Is substitution enabled?

   167                     if (subMode) {

   168                         outputByte = subBytes;

   169                         outputSize = subBytes.length;

   170                         inputSize = 2;

   171                     } else {

   172                         badInputLength = 2;

   173                         throw new UnknownCharacterException();

   174                     }

   175                 } else {

   176                     // We have a malformed surrogate pair

   177                     badInputLength = 1;

   178                     throw new MalformedInputException();

   179                 }

   180             }

   181 

   182             // Is this an unaccompanied low surrogate?

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

   184                 badInputLength = 1;

   185                 throw new MalformedInputException();

   186             }

   187 

   188             // Not part of a surrogate, so look it up

   189             else {

   190                 // Get output using two level lookup

   191                 outputByte[0] = getNative(inputChar);

   192 

   193                 // Might this character be unmappable?

   194                 if (outputByte[0] == 0) {

   195                     // If outputByte is zero because the input was zero

   196                     //  then this character is actually mappable

   197                     if (input[charOff] != '\u0000') {

   198                         // We have an unmappable character

   199                         // Is substitution enabled?

   200                         if (subMode) {

   201                             outputByte = subBytes;

   202                             outputSize = subBytes.length;

   203                         } else {

   204                             badInputLength = 1;

   205                             throw new UnknownCharacterException();

   206                         }

   207                     }

   208                 }

   209             }

   210 

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

   212             if (byteOff + outputSize > outEnd)

   213                 throw new ConversionBufferFullException();

   214 

   215             // Put the byte in the output buffer

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

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

   218             }

   219             charOff += inputSize;

   220 

   221         }

   222 

   223         // Return the length written to the output buffer

   224         return byteOff - outOff;

   225     }

   226 

   227     /**

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

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

   230      */

   231     public int getMaxBytesPerChar() {

   232         return 1;

   233     }

   234 

   235     int encodeChar(char ch) {

   236         char index = index1[ch >> 8];

   237         if (index == UNMAPPABLE_ENCODING)

   238             return UNMAPPABLE_ENCODING;

   239         return index2[index + (ch & 0xff)];

   240     }

   241 

   242     public byte getNative(char inputChar) {

   243         int b = encodeChar(inputChar);

   244         if (b == UNMAPPABLE_ENCODING)

   245             return 0;

   246         return (byte)b;

   247     }

   248 

   249     /**

   250      *  Resets the converter.

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

   252      */

   253     public void reset() {

   254         byteOff = charOff = 0;

   255         highHalfZoneCode = 0;

   256     }

   257 

   258     /**

   259      * Return whether a character is mappable or not

   260      * @return true if a character is mappable

   261      */

   262     public boolean canConvert(char ch) {

   263         return encodeChar(ch) != UNMAPPABLE_ENCODING;

   264     }

   265 }