J. Duke | 319a3b9 | 2007-12-01 00:00:00 +0000 | [diff] [blame^] | 1 | /* |
| 2 | * Copyright 1997-2002 Sun Microsystems, Inc. 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. Sun designates this |
| 8 | * particular file as subject to the "Classpath" exception as provided |
| 9 | * by Sun 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 Sun Microsystems, Inc., 4150 Network Circle, Santa Clara, |
| 22 | * CA 95054 USA or visit www.sun.com if you need additional information or |
| 23 | * have any questions. |
| 24 | */ |
| 25 | |
| 26 | package sun.io; |
| 27 | |
| 28 | /** |
| 29 | * @author Limin Shi |
| 30 | * Sean Jiang |
| 31 | */ |
| 32 | |
| 33 | public abstract class ByteToCharDoubleByte extends ByteToCharConverter { |
| 34 | protected byte savedByte; |
| 35 | |
| 36 | /* |
| 37 | * 1st level index, provided by subclass |
| 38 | */ |
| 39 | protected short index1[]; |
| 40 | |
| 41 | /* |
| 42 | * 2nd level index, provided by subclass |
| 43 | * every string has 0x10*(end-start+1) characters. |
| 44 | */ |
| 45 | protected String index2[]; |
| 46 | |
| 47 | protected int start; |
| 48 | protected int end; |
| 49 | |
| 50 | /* |
| 51 | * Size of bad input that caused conversion to stop |
| 52 | */ |
| 53 | protected int badInputLength; |
| 54 | |
| 55 | public ByteToCharDoubleByte() { |
| 56 | super(); |
| 57 | savedByte = 0; |
| 58 | } |
| 59 | |
| 60 | |
| 61 | public short[] getIndex1() { |
| 62 | return(index1); |
| 63 | } |
| 64 | |
| 65 | public String[] getIndex2() { |
| 66 | return(index2); |
| 67 | } |
| 68 | |
| 69 | public int flush(char[] output, int outStart, int outEnd) |
| 70 | throws MalformedInputException |
| 71 | { |
| 72 | if (savedByte != 0) { |
| 73 | reset(); |
| 74 | badInputLength = 0; |
| 75 | throw new MalformedInputException(); |
| 76 | } |
| 77 | reset(); |
| 78 | return 0; |
| 79 | } |
| 80 | |
| 81 | /** |
| 82 | * Converts sequences of bytes to characters. |
| 83 | * Conversions that result in Exceptions can be restarted by calling |
| 84 | * convert again, with appropriately modified parameters. |
| 85 | * @return the characters written to output. |
| 86 | * @param input byte array containing text in Double/single Byte |
| 87 | * @param inStart offset in input array |
| 88 | * @param inEnd offset of last byte to be converted |
| 89 | * @param output character array to receive conversion result |
| 90 | * @param outStart starting offset |
| 91 | * @param outEnd offset of last byte to be written to |
| 92 | * @throw UnsupportedCharacterException for any bytes |
| 93 | * that cannot be converted to the external character set. |
| 94 | */ |
| 95 | public int convert(byte[] input, int inOff, int inEnd, |
| 96 | char[] output, int outOff, int outEnd) |
| 97 | throws UnknownCharacterException, MalformedInputException, |
| 98 | ConversionBufferFullException |
| 99 | { |
| 100 | char outputChar = REPLACE_CHAR; |
| 101 | int inputSize = 0; // Size of input |
| 102 | |
| 103 | // Record beginning offsets |
| 104 | charOff = outOff; |
| 105 | byteOff = inOff; |
| 106 | |
| 107 | // Loop until we hit the end of the input |
| 108 | while (byteOff < inEnd) { |
| 109 | int byte1, byte2; |
| 110 | |
| 111 | if (savedByte == 0) { |
| 112 | byte1 = input[byteOff]; |
| 113 | inputSize = 1; |
| 114 | } else { |
| 115 | byte1 = savedByte; |
| 116 | savedByte = 0; |
| 117 | inputSize = 0; |
| 118 | } |
| 119 | |
| 120 | outputChar = convSingleByte(byte1); |
| 121 | |
| 122 | if (outputChar == REPLACE_CHAR) { // DoubleByte char |
| 123 | if (byteOff + inputSize >= inEnd) { |
| 124 | // split in the middle of a character |
| 125 | // save the first byte for next time around |
| 126 | savedByte = (byte) byte1; |
| 127 | byteOff += inputSize; |
| 128 | break; |
| 129 | } |
| 130 | |
| 131 | byte1 &= 0xff; |
| 132 | byte2 = input[byteOff + inputSize] & 0xff; |
| 133 | |
| 134 | inputSize++; |
| 135 | outputChar = getUnicode(byte1, byte2); |
| 136 | } |
| 137 | |
| 138 | if (outputChar == REPLACE_CHAR) { |
| 139 | if (subMode) |
| 140 | outputChar = subChars[0]; |
| 141 | else { |
| 142 | badInputLength = inputSize; |
| 143 | throw new UnknownCharacterException(); |
| 144 | } |
| 145 | } |
| 146 | |
| 147 | if (charOff >= outEnd) |
| 148 | throw new ConversionBufferFullException(); |
| 149 | |
| 150 | output[charOff++] = outputChar; |
| 151 | byteOff += inputSize; |
| 152 | } |
| 153 | |
| 154 | return charOff - outOff; |
| 155 | } |
| 156 | |
| 157 | /** |
| 158 | * Resets the converter. |
| 159 | * Call this method to reset the converter to its initial state |
| 160 | */ |
| 161 | public void reset() { |
| 162 | byteOff = charOff = 0; |
| 163 | savedByte = 0; |
| 164 | } |
| 165 | |
| 166 | |
| 167 | /* |
| 168 | * Can be changed by subclass |
| 169 | */ |
| 170 | protected char convSingleByte(int b) { |
| 171 | if (b >= 0) |
| 172 | return (char) b; |
| 173 | return REPLACE_CHAR; |
| 174 | } |
| 175 | |
| 176 | /* |
| 177 | * Can be changed by subclass |
| 178 | */ |
| 179 | protected char getUnicode(int byte1, int byte2) { |
| 180 | // Fix for bug 4117820 - similar fix for bug 4121358 put |
| 181 | // into ByteToCharEUC_JP.getUnicode() |
| 182 | if (((byte1 < 0) || (byte1 > index1.length)) |
| 183 | || ((byte2 < start) || (byte2 > end))) |
| 184 | return REPLACE_CHAR; |
| 185 | |
| 186 | int n = (index1[byte1] & 0xf) * (end - start + 1) + (byte2 - start); |
| 187 | return index2[index1[byte1] >> 4].charAt(n); |
| 188 | } |
| 189 | |
| 190 | protected final static char REPLACE_CHAR = '\uFFFD'; |
| 191 | } |