J. Duke | 319a3b9 | 2007-12-01 00:00:00 +0000 | [diff] [blame^] | 1 | /* |
| 2 | * Copyright 1996-1997 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 | public class ByteToCharISO2022JP extends ByteToCharJIS0208 { |
| 29 | |
| 30 | private static final int ASCII = 0; // ESC ( B |
| 31 | private static final int JISX0201_1976 = 1; // ESC ( J |
| 32 | private static final int JISX0208_1978 = 2; // ESC $ @ |
| 33 | private static final int JISX0208_1983 = 3; // ESC $ B |
| 34 | private static final int JISX0201_1976_KANA = 4; // ESC ( I |
| 35 | private static final int SHIFTOUT = 5; // SO (0x0e) |
| 36 | |
| 37 | private int currentState; |
| 38 | private int savedSize; |
| 39 | private byte[] savedBytes; |
| 40 | |
| 41 | public ByteToCharISO2022JP() { |
| 42 | super(); |
| 43 | savedBytes = new byte[2]; |
| 44 | currentState = ASCII; |
| 45 | savedSize = 0; |
| 46 | } |
| 47 | |
| 48 | public int flush(char [] output, int outStart, int outEnd) |
| 49 | throws MalformedInputException |
| 50 | { |
| 51 | if (savedSize != 0) { |
| 52 | savedSize = 0; |
| 53 | currentState = ASCII; |
| 54 | badInputLength = 0; |
| 55 | throw new MalformedInputException(); |
| 56 | } |
| 57 | byteOff = charOff = 0; |
| 58 | return 0; |
| 59 | } |
| 60 | |
| 61 | |
| 62 | /** |
| 63 | * Character conversion |
| 64 | */ |
| 65 | public int convert(byte[] input, int inOff, int inEnd, |
| 66 | char[] output, int outOff, int outEnd) |
| 67 | throws UnknownCharacterException, MalformedInputException, |
| 68 | ConversionBufferFullException |
| 69 | { |
| 70 | int previousState = ASCII; |
| 71 | int inputSize = 0; |
| 72 | char outputChar = '\uFFFD'; |
| 73 | // readOff keeps the actual buffer's pointer. |
| 74 | // byteOff keeps original buffer's pointer. |
| 75 | int readOff = byteOff = inOff; |
| 76 | |
| 77 | if (savedSize != 0) { |
| 78 | if (savedBytes[0] == 0x1b) { // ESC |
| 79 | if ((savedSize == 2 && |
| 80 | (savedBytes[1] == 0x28 && |
| 81 | input[0] != 'B' && |
| 82 | input[0] != 'J' && |
| 83 | input[0] != 'I') && |
| 84 | (savedBytes[1] == 0x24 && |
| 85 | input[0] != '@' && |
| 86 | input[0] != 'B')) || |
| 87 | ((savedSize == 1) && |
| 88 | (input[0] != 0x28 && |
| 89 | input[0] != 0x24))) { |
| 90 | badInputLength = 0; |
| 91 | throw new MalformedInputException(); |
| 92 | } |
| 93 | if ((inEnd - inOff) == 1 && savedSize == 1 && |
| 94 | savedBytes[0] == 0x1b) { |
| 95 | savedSize = 2; |
| 96 | savedBytes[1] = input[0]; |
| 97 | byteOff++; |
| 98 | return 0; |
| 99 | } |
| 100 | } |
| 101 | byte[] newBuf = new byte[inEnd - inOff + savedSize]; |
| 102 | for (int i = 0; i < savedSize; i++) { |
| 103 | newBuf[i] = savedBytes[i]; |
| 104 | } |
| 105 | System.arraycopy(input, inOff, newBuf, savedSize, inEnd - inOff); |
| 106 | byteOff -= savedSize; |
| 107 | input = newBuf; |
| 108 | inOff = 0; |
| 109 | inEnd = newBuf.length; |
| 110 | savedSize = 0; |
| 111 | } |
| 112 | |
| 113 | charOff = outOff; |
| 114 | readOff = inOff; |
| 115 | |
| 116 | while(readOff < inEnd) { |
| 117 | int byte1, byte2, byte3; |
| 118 | boolean noOutput = false; |
| 119 | |
| 120 | // Is there room in the output buffer for the result? |
| 121 | if (charOff >= outEnd) { |
| 122 | throw new ConversionBufferFullException(); |
| 123 | } |
| 124 | |
| 125 | // Get the input byte |
| 126 | byte1 = input[readOff] & 0xFF; |
| 127 | inputSize = 1; |
| 128 | |
| 129 | if ((byte1 & (byte)0x80) != 0){ |
| 130 | badInputLength = 1; |
| 131 | throw new MalformedInputException(); |
| 132 | } |
| 133 | |
| 134 | // Is this a escape sequence? |
| 135 | while (byte1 == 0x1b || byte1 == 0x0e || byte1 == 0x0f) { |
| 136 | if (byte1 == 0x1b){ // ESC |
| 137 | if (readOff + inputSize + 1 >= inEnd) { |
| 138 | if (readOff + inputSize >= inEnd) { |
| 139 | savedSize = 1; |
| 140 | savedBytes[0] = (byte)byte1; |
| 141 | } else { |
| 142 | savedSize = 2; |
| 143 | savedBytes[0] = (byte)byte1; |
| 144 | savedBytes[1] = (byte)input[readOff + inputSize]; |
| 145 | inputSize++; |
| 146 | } |
| 147 | break; |
| 148 | } |
| 149 | byte2 = input[readOff + inputSize] & 0xFF; |
| 150 | inputSize++; |
| 151 | if ((byte2 & (byte)0x80) != 0){ |
| 152 | badInputLength = 2; |
| 153 | throw new MalformedInputException(); |
| 154 | } |
| 155 | if (byte2 == 0x28){ |
| 156 | byte3 = input[readOff + inputSize] & 0xFF; |
| 157 | inputSize++; |
| 158 | if (byte3 == 'B'){ |
| 159 | currentState = ASCII; |
| 160 | } else if (byte3 == 'J'){ |
| 161 | currentState = JISX0201_1976; |
| 162 | } else if (byte3 == 'I'){ |
| 163 | currentState = JISX0201_1976_KANA; |
| 164 | } else { |
| 165 | // illegal ESC sequence |
| 166 | badInputLength = 3; |
| 167 | throw new MalformedInputException(); |
| 168 | } |
| 169 | } else if (byte2 == '$'){ |
| 170 | byte3 = input[readOff + inputSize] & 0xFF; |
| 171 | inputSize++; |
| 172 | if ((byte3 & (byte)0x80) != 0){ |
| 173 | badInputLength = 3; |
| 174 | throw new MalformedInputException(); |
| 175 | } |
| 176 | if (byte3 == '@'){ |
| 177 | currentState = JISX0208_1978; |
| 178 | } else if (byte3 == 'B'){ |
| 179 | currentState = JISX0208_1983; |
| 180 | } else { |
| 181 | // illegal ESC sequence |
| 182 | badInputLength = 3; |
| 183 | throw new MalformedInputException(); |
| 184 | } |
| 185 | } else { |
| 186 | // illegal ESC sequence |
| 187 | badInputLength = 2; |
| 188 | throw new MalformedInputException(); |
| 189 | } |
| 190 | if (readOff + inputSize >= inEnd) { |
| 191 | noOutput = true; |
| 192 | break; |
| 193 | } else { |
| 194 | byte1 = input[readOff + inputSize]; |
| 195 | inputSize++; |
| 196 | } |
| 197 | } else if (byte1 == 0x0e){ // shift out for one byte kana |
| 198 | previousState = currentState; |
| 199 | currentState = SHIFTOUT; |
| 200 | if (readOff + inputSize >= inEnd) { |
| 201 | noOutput = true; |
| 202 | break; |
| 203 | } |
| 204 | byte1 = input[readOff + inputSize]; |
| 205 | inputSize++; |
| 206 | if ((byte1 & (byte)0x80) != 0){ |
| 207 | badInputLength = 1; |
| 208 | throw new MalformedInputException(); |
| 209 | } |
| 210 | } else if (byte1 == 0x0f){ // shift in for previous mode |
| 211 | currentState = previousState; |
| 212 | if (readOff + inputSize >= inEnd) { |
| 213 | noOutput = true; |
| 214 | break; |
| 215 | } |
| 216 | byte1 = input[readOff + inputSize]; |
| 217 | inputSize++; |
| 218 | if ((byte1 & (byte)0x80) != 0){ |
| 219 | badInputLength = 1; |
| 220 | throw new MalformedInputException(); |
| 221 | } |
| 222 | } |
| 223 | } |
| 224 | if (noOutput || savedSize != 0) { |
| 225 | byteOff += inputSize; |
| 226 | break; |
| 227 | } |
| 228 | noOutput = false; |
| 229 | switch (currentState){ |
| 230 | case ASCII: |
| 231 | outputChar = (char)(byte1 & 0xff); |
| 232 | break; |
| 233 | case JISX0201_1976: |
| 234 | switch (byte1) { |
| 235 | case 0x5c: |
| 236 | outputChar = '\u00a5'; |
| 237 | break; |
| 238 | case 0x7e: |
| 239 | outputChar = '\u203e'; |
| 240 | break; |
| 241 | default: |
| 242 | outputChar = (char)byte1; |
| 243 | break; |
| 244 | } |
| 245 | break; |
| 246 | case JISX0208_1978: |
| 247 | case JISX0208_1983: |
| 248 | if (readOff + inputSize >= inEnd) { |
| 249 | savedSize = 1; |
| 250 | savedBytes[0] = (byte)byte1; |
| 251 | break; |
| 252 | } |
| 253 | byte2 = input[readOff + inputSize] & 0xff; |
| 254 | inputSize++; |
| 255 | if ((byte2 & (byte)0x80) != 0){ |
| 256 | badInputLength = 1; |
| 257 | throw new MalformedInputException(); |
| 258 | } |
| 259 | // jisx0208Chars table convert FULLWIDTH_REVERSE_SOLIDUS |
| 260 | // 0x2140 to REVERSE_SOLIDUS (BACKSLASH) 0x5c. |
| 261 | // This behavior causes problem because |
| 262 | // 0x5c is special escape character for java. |
| 263 | if (byte1 == 0x21 && byte2 == 0x40) { |
| 264 | outputChar = '\uFF3C'; |
| 265 | } else { |
| 266 | try { |
| 267 | outputChar = getUnicode(byte1, byte2); |
| 268 | } catch (ArrayIndexOutOfBoundsException e) { |
| 269 | outputChar = '\uFFFD'; |
| 270 | } |
| 271 | } |
| 272 | break; |
| 273 | case JISX0201_1976_KANA: |
| 274 | case SHIFTOUT: |
| 275 | if (byte1 > 0x60) { |
| 276 | badInputLength = 1; |
| 277 | throw new MalformedInputException(); |
| 278 | } |
| 279 | outputChar = (char)(byte1 + 0xff40); |
| 280 | break; |
| 281 | } |
| 282 | |
| 283 | if (savedSize != 0) { |
| 284 | byteOff += inputSize; |
| 285 | break; |
| 286 | } |
| 287 | |
| 288 | if (outputChar == '\uFFFD') { |
| 289 | if (subMode) |
| 290 | outputChar = subChars[0]; |
| 291 | else { |
| 292 | badInputLength = inputSize; |
| 293 | throw new UnknownCharacterException(); |
| 294 | } |
| 295 | } |
| 296 | readOff += inputSize; |
| 297 | byteOff += inputSize; |
| 298 | output[charOff++] = outputChar; |
| 299 | } |
| 300 | |
| 301 | return charOff - outOff; |
| 302 | } |
| 303 | |
| 304 | public void reset() { |
| 305 | byteOff = charOff = 0; |
| 306 | currentState = ASCII; |
| 307 | savedSize = 0; |
| 308 | } |
| 309 | |
| 310 | public String getCharacterEncoding() { |
| 311 | return "ISO2022JP"; |
| 312 | } |
| 313 | } |