J. Duke | 319a3b9 | 2007-12-01 00:00:00 +0000 | [diff] [blame^] | 1 | /* |
| 2 | * Copyright 1997-2001 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 | * An algorithmic conversion from ISO 2022 to Unicode |
| 30 | * |
| 31 | * @author Tom Zhou |
| 32 | */ |
| 33 | public abstract class ByteToCharISO2022 extends ByteToCharConverter |
| 34 | { |
| 35 | // Value to be filled by subclass |
| 36 | protected String SODesignator[]; |
| 37 | protected String SS2Designator[] = null; |
| 38 | protected String SS3Designator[] = null; |
| 39 | |
| 40 | protected ByteToCharConverter SOConverter[]; |
| 41 | protected ByteToCharConverter SS2Converter[] = null; |
| 42 | protected ByteToCharConverter SS3Converter[] = null; |
| 43 | |
| 44 | private static final byte ISO_ESC = 0x1b; |
| 45 | private static final byte ISO_SI = 0x0f; |
| 46 | private static final byte ISO_SO = 0x0e; |
| 47 | private static final byte ISO_SS2_7 = 0x4e; |
| 48 | private static final byte ISO_SS3_7 = 0x4f; |
| 49 | private static final byte MSB = (byte)0x80; |
| 50 | private static final char REPLACE_CHAR = '\uFFFD'; |
| 51 | private static final byte maximumDesignatorLength = 3; |
| 52 | |
| 53 | private static final byte SOFlag = 0; |
| 54 | private static final byte SS2Flag = 1; |
| 55 | private static final byte SS3Flag = 2; |
| 56 | private static final byte G0 = 0; |
| 57 | private static final byte G1 = 1; |
| 58 | |
| 59 | private ByteToCharConverter tmpConverter[]; |
| 60 | |
| 61 | private int curSODes, curSS2Des, curSS3Des; |
| 62 | private boolean shiftout; |
| 63 | |
| 64 | private byte remainByte[] = new byte[10]; |
| 65 | private int remainIndex = -1; |
| 66 | private byte state, firstByte; |
| 67 | |
| 68 | public void reset() |
| 69 | { |
| 70 | int i = 0; |
| 71 | |
| 72 | shiftout = false; |
| 73 | state = G0; |
| 74 | firstByte = 0; |
| 75 | |
| 76 | curSODes = 0; |
| 77 | curSS2Des = 0; |
| 78 | curSS3Des = 0; |
| 79 | |
| 80 | charOff = byteOff = 0; |
| 81 | remainIndex = -1; |
| 82 | |
| 83 | for(i = 0; i < remainByte.length; i++) |
| 84 | remainByte[i] = 0; |
| 85 | } |
| 86 | |
| 87 | public int flush(char[] output, int outStart, int outEnd) |
| 88 | throws MalformedInputException |
| 89 | { |
| 90 | int i; |
| 91 | if (state != G0) { |
| 92 | badInputLength = 0; |
| 93 | throw new MalformedInputException(); |
| 94 | } |
| 95 | reset(); |
| 96 | return 0; |
| 97 | } |
| 98 | |
| 99 | private byte[] savetyGetSrc(byte[] input, int inOff, int inEnd, int nbytes) |
| 100 | { |
| 101 | int i; |
| 102 | byte tmp[]; |
| 103 | |
| 104 | if(inOff <= (inEnd-nbytes+1)) |
| 105 | tmp = new byte[nbytes]; |
| 106 | else |
| 107 | tmp = new byte[inEnd-inOff]; |
| 108 | |
| 109 | for(i = 0; i < tmp.length; i++) |
| 110 | tmp[i] = input[inOff+i]; |
| 111 | return tmp; |
| 112 | } |
| 113 | |
| 114 | private char getUnicode(byte byte1, byte byte2, byte shiftFlag) |
| 115 | { |
| 116 | byte1 |= MSB; |
| 117 | byte2 |= MSB; |
| 118 | |
| 119 | byte[] tmpByte = {byte1,byte2}; |
| 120 | char[] tmpChar = new char[1]; |
| 121 | int i = 0, |
| 122 | tmpIndex = 0; |
| 123 | |
| 124 | switch(shiftFlag) { |
| 125 | case SOFlag: |
| 126 | tmpIndex = curSODes; |
| 127 | tmpConverter = (ByteToCharConverter [])SOConverter; |
| 128 | break; |
| 129 | case SS2Flag: |
| 130 | tmpIndex = curSS2Des; |
| 131 | tmpConverter = (ByteToCharConverter [])SS2Converter; |
| 132 | break; |
| 133 | case SS3Flag: |
| 134 | tmpIndex = curSS3Des; |
| 135 | tmpConverter = (ByteToCharConverter [])SS3Converter; |
| 136 | break; |
| 137 | } |
| 138 | |
| 139 | for(i = 0; i < tmpConverter.length; i++) { |
| 140 | if(tmpIndex == i) { |
| 141 | try { |
| 142 | tmpConverter[i].convert(tmpByte, 0, 2, tmpChar, 0, 1); |
| 143 | } catch (Exception e) {} |
| 144 | return tmpChar[0]; |
| 145 | } |
| 146 | } |
| 147 | return REPLACE_CHAR; |
| 148 | } |
| 149 | |
| 150 | public final int convert(byte[] input, int inOff, int inEnd, |
| 151 | char[] output, int outOff, int outEnd) |
| 152 | throws ConversionBufferFullException, |
| 153 | MalformedInputException |
| 154 | { |
| 155 | int i; |
| 156 | int DesignatorLength = 0; |
| 157 | charOff = outOff; |
| 158 | byteOff = inOff; |
| 159 | |
| 160 | // Loop until we hit the end of the input |
| 161 | while (byteOff < inEnd) { |
| 162 | // If we don't have room for the output, throw an exception |
| 163 | if (charOff >= outEnd) |
| 164 | throw new ConversionBufferFullException(); |
| 165 | if(remainIndex < 0) { |
| 166 | remainByte[0] = input[byteOff]; |
| 167 | remainIndex = 0; |
| 168 | byteOff++; |
| 169 | } |
| 170 | switch (remainByte[0]) { |
| 171 | case ISO_SO: |
| 172 | shiftout = true; |
| 173 | if(remainIndex > 0) |
| 174 | System.arraycopy(remainByte, 1, remainByte, 0, remainIndex); |
| 175 | remainIndex--; |
| 176 | break; |
| 177 | case ISO_SI: |
| 178 | shiftout = false; |
| 179 | if(remainIndex > 0) |
| 180 | System.arraycopy(remainByte, 1, remainByte, 0, remainIndex); |
| 181 | remainIndex--; |
| 182 | break; |
| 183 | case ISO_ESC: |
| 184 | byte tmp[] = savetyGetSrc(input, byteOff, inEnd, |
| 185 | (maximumDesignatorLength-remainIndex)); |
| 186 | System.arraycopy(tmp, 0, remainByte, remainIndex+1, tmp.length); |
| 187 | remainIndex += tmp.length; |
| 188 | byteOff += tmp.length; |
| 189 | if(tmp.length<(maximumDesignatorLength-remainIndex)) |
| 190 | break; |
| 191 | String tmpString = new String(remainByte, 1, remainIndex); |
| 192 | for (i = 0; i < SODesignator.length; i++) { |
| 193 | if(tmpString.indexOf(SODesignator[i]) == 0) { |
| 194 | curSODes = i; |
| 195 | DesignatorLength = SODesignator[i].length(); |
| 196 | break; |
| 197 | } |
| 198 | } |
| 199 | |
| 200 | if (DesignatorLength == 0 ) { // Designator not recognized |
| 201 | badInputLength = tmp.length; |
| 202 | throw new MalformedInputException(); |
| 203 | } |
| 204 | |
| 205 | if (i == SODesignator.length) { |
| 206 | for (i = 0; i < SS2Designator.length; i++) { |
| 207 | if(tmpString.indexOf(SS2Designator[i]) == 0) { |
| 208 | curSS2Des = i; |
| 209 | DesignatorLength = SS2Designator[i].length(); |
| 210 | break; |
| 211 | } |
| 212 | } |
| 213 | if(i == SS2Designator.length) { |
| 214 | for(i = 0; i < SS3Designator.length; i++) { |
| 215 | if (tmpString.indexOf(SS3Designator[i]) == 0) { |
| 216 | curSS3Des = i; |
| 217 | DesignatorLength = SS3Designator[i].length(); |
| 218 | break; |
| 219 | } |
| 220 | } |
| 221 | if (i == SS3Designator.length) { |
| 222 | switch(remainByte[1]) { |
| 223 | case ISO_SS2_7: |
| 224 | output[charOff] = getUnicode(remainByte[2], |
| 225 | remainByte[3], |
| 226 | SS2Flag); |
| 227 | charOff++; |
| 228 | DesignatorLength = 3; |
| 229 | break; |
| 230 | case ISO_SS3_7: |
| 231 | output[charOff] = getUnicode(remainByte[2], |
| 232 | remainByte[3], |
| 233 | SS3Flag); |
| 234 | charOff++; |
| 235 | DesignatorLength = 3; |
| 236 | break; |
| 237 | default: |
| 238 | DesignatorLength = 0; |
| 239 | } |
| 240 | } |
| 241 | } |
| 242 | } |
| 243 | if (remainIndex > DesignatorLength) { |
| 244 | for(i = 0; i < remainIndex-DesignatorLength; i++) |
| 245 | remainByte[i] = remainByte[DesignatorLength+1+i]; |
| 246 | remainIndex = i-1; |
| 247 | } else { |
| 248 | remainIndex = -1; |
| 249 | } |
| 250 | break; |
| 251 | default: |
| 252 | if (!shiftout) { |
| 253 | output[charOff] = (char)remainByte[0]; |
| 254 | charOff++; |
| 255 | } else { |
| 256 | switch (state) { |
| 257 | case G0: |
| 258 | firstByte = remainByte[0]; |
| 259 | state = G1; |
| 260 | break; |
| 261 | case G1: |
| 262 | output[charOff] = getUnicode(firstByte, remainByte[0], |
| 263 | SOFlag); |
| 264 | charOff++; |
| 265 | state = G0; |
| 266 | break; |
| 267 | } |
| 268 | } |
| 269 | if (remainIndex > 0) |
| 270 | System.arraycopy(remainByte, 1, remainByte, 0, remainIndex); |
| 271 | remainIndex--; |
| 272 | } |
| 273 | } |
| 274 | return charOff - outOff; |
| 275 | } |
| 276 | } |