J. Duke | 319a3b9 | 2007-12-01 00:00:00 +0000 | [diff] [blame^] | 1 | /* |
| 2 | * Copyright 2001-2003 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 | /* |
| 27 | */ |
| 28 | |
| 29 | package sun.io; |
| 30 | |
| 31 | import sun.nio.cs.ext.GB18030; |
| 32 | |
| 33 | public class ByteToCharGB18030 extends ByteToCharGB18030DB { |
| 34 | |
| 35 | private static final int GB18030_SINGLE_BYTE = 1; |
| 36 | private static final int GB18030_DOUBLE_BYTE = 2; |
| 37 | private static final int GB18030_FOUR_BYTE = 3; |
| 38 | private static short[] decoderIndex1; |
| 39 | private static String[] decoderIndex2; |
| 40 | |
| 41 | private int currentState; |
| 42 | private int savedSize; |
| 43 | private byte[] savedBytes; |
| 44 | |
| 45 | public ByteToCharGB18030() { |
| 46 | super(); |
| 47 | GB18030 nioCoder = new GB18030(); |
| 48 | savedBytes = new byte[3]; |
| 49 | currentState = GB18030_DOUBLE_BYTE; |
| 50 | decoderIndex1 = nioCoder.getDecoderIndex1(); |
| 51 | decoderIndex2 = nioCoder.getDecoderIndex2(); |
| 52 | savedSize = 0; |
| 53 | } |
| 54 | |
| 55 | public short[] getOuter() { |
| 56 | return(index1); |
| 57 | } |
| 58 | |
| 59 | public String[] getInner() { |
| 60 | return(index2); |
| 61 | } |
| 62 | |
| 63 | public short[] getDBIndex1() { |
| 64 | return(super.index1); |
| 65 | } |
| 66 | |
| 67 | public String[] getDBIndex2() { |
| 68 | return(super.index2); |
| 69 | } |
| 70 | |
| 71 | public int flush(char [] output, int outStart, int outEnd) |
| 72 | throws MalformedInputException |
| 73 | { |
| 74 | if (savedSize != 0) { |
| 75 | savedSize = 0; |
| 76 | currentState = GB18030_DOUBLE_BYTE; |
| 77 | badInputLength = 0; |
| 78 | throw new MalformedInputException(); |
| 79 | } |
| 80 | byteOff = charOff = 0; |
| 81 | return 0; |
| 82 | } |
| 83 | |
| 84 | |
| 85 | /** |
| 86 | * Character conversion |
| 87 | */ |
| 88 | public int convert(byte[] input, int inOff, int inEnd, |
| 89 | char[] output, int outOff, int outEnd) |
| 90 | throws UnknownCharacterException, MalformedInputException, |
| 91 | ConversionBufferFullException |
| 92 | { |
| 93 | int inputSize = 0; |
| 94 | char outputChar = '\uFFFD'; |
| 95 | // readOff keeps the actual buffer's pointer. |
| 96 | // byteOff keeps original buffer's pointer. |
| 97 | int readOff = byteOff = inOff; |
| 98 | |
| 99 | if (savedSize != 0) { |
| 100 | // Filter illegal bytes when they are detected in saved |
| 101 | // partial input from a previous conversion attempt. |
| 102 | if (((savedBytes[0] & 0xFF) < 0x81 || savedBytes[0] > 0xFE) || |
| 103 | (savedSize > 1 && |
| 104 | (savedBytes[1] & 0xFF) < 0x30 ) || |
| 105 | (savedSize > 2 && |
| 106 | ((savedBytes[2] & 0xFF) < 0x81 || |
| 107 | (savedBytes[2] & 0xFF) > 0xFE ))) { |
| 108 | badInputLength = 0; |
| 109 | throw new MalformedInputException(); |
| 110 | } |
| 111 | |
| 112 | byte[] newBuf = new byte[inEnd - inOff + savedSize]; |
| 113 | for (int i = 0; i < savedSize; i++) { |
| 114 | newBuf[i] = savedBytes[i]; |
| 115 | } |
| 116 | System.arraycopy(input, inOff, newBuf, savedSize, inEnd - inOff); |
| 117 | byteOff -= savedSize; |
| 118 | input = newBuf; |
| 119 | inOff = 0; |
| 120 | inEnd = newBuf.length; |
| 121 | savedSize = 0; |
| 122 | } |
| 123 | |
| 124 | charOff = outOff; |
| 125 | readOff = inOff; |
| 126 | |
| 127 | while(readOff < inEnd) { |
| 128 | int byte1 = 0 , byte2 = 0, byte3 = 0, byte4 = 0; |
| 129 | |
| 130 | // Is there room in the output buffer for the result? |
| 131 | if (charOff >= outEnd) { |
| 132 | throw new ConversionBufferFullException(); |
| 133 | } |
| 134 | |
| 135 | // Get the input byte |
| 136 | byte1 = input[readOff++] & 0xFF; |
| 137 | inputSize = 1; |
| 138 | |
| 139 | if ((byte1 & (byte)0x80) == 0){ // US-ASCII range |
| 140 | outputChar = (char)byte1; |
| 141 | currentState = GB18030_SINGLE_BYTE; |
| 142 | } |
| 143 | |
| 144 | else if (byte1 < 0x81 || byte1 > 0xfe) { |
| 145 | if (subMode) |
| 146 | outputChar = subChars[0]; |
| 147 | else { |
| 148 | badInputLength = 1; |
| 149 | throw new UnknownCharacterException(); |
| 150 | } |
| 151 | } |
| 152 | else { |
| 153 | // Either 2 or 4 byte sequence follows |
| 154 | // If an underrun is detected save for later |
| 155 | // replay. |
| 156 | |
| 157 | if (readOff + inputSize > inEnd) { |
| 158 | savedBytes[0]=(byte)byte1; |
| 159 | savedSize = 1; |
| 160 | break; |
| 161 | } |
| 162 | |
| 163 | byte2 = input[readOff++] & 0xFF; |
| 164 | inputSize = 2; |
| 165 | |
| 166 | if (byte2 < 0x30) { |
| 167 | badInputLength = 1; |
| 168 | throw new MalformedInputException(); |
| 169 | } |
| 170 | else if (byte2 >= 0x30 && byte2 <= 0x39) { |
| 171 | currentState = GB18030_FOUR_BYTE; |
| 172 | inputSize = 4; |
| 173 | |
| 174 | if (readOff + 2 > inEnd) { |
| 175 | if (readOff + 1 > inEnd) { |
| 176 | savedBytes[0] = (byte)byte1; |
| 177 | savedBytes[1] = (byte)byte2; |
| 178 | savedSize = 2; |
| 179 | } |
| 180 | else { |
| 181 | savedBytes[0] = (byte)byte1; |
| 182 | savedBytes[1] = (byte)byte2; |
| 183 | savedBytes[2] = input[readOff++]; |
| 184 | savedSize = 3; |
| 185 | } |
| 186 | break; |
| 187 | } |
| 188 | byte3 = input[readOff++] & 0xFF; |
| 189 | if (byte3 < 0x81 || byte3 > 0xfe) { |
| 190 | badInputLength = 3; |
| 191 | throw new MalformedInputException(); |
| 192 | } |
| 193 | |
| 194 | byte4 = input[readOff++] & 0xFF; |
| 195 | |
| 196 | if (byte4 < 0x30 || byte4 > 0x39) { |
| 197 | badInputLength = 4; |
| 198 | throw new MalformedInputException(); |
| 199 | } |
| 200 | } |
| 201 | else if (byte2 == 0x7f || byte2 == 0xff || |
| 202 | (byte2 < 0x40 )) { |
| 203 | badInputLength = 2; |
| 204 | throw new MalformedInputException(); |
| 205 | } |
| 206 | else |
| 207 | currentState = GB18030_DOUBLE_BYTE; |
| 208 | } |
| 209 | |
| 210 | switch (currentState){ |
| 211 | case GB18030_SINGLE_BYTE: |
| 212 | output[charOff++] = (char)(byte1); |
| 213 | break; |
| 214 | case GB18030_DOUBLE_BYTE: |
| 215 | output[charOff++] = super.getUnicode(byte1, byte2); |
| 216 | break; |
| 217 | case GB18030_FOUR_BYTE: |
| 218 | int offset = (((byte1 - 0x81) * 10 + |
| 219 | (byte2 - 0x30)) * 126 + |
| 220 | byte3 - 0x81) * 10 + byte4 - 0x30; |
| 221 | int hiByte = (offset >>8) & 0xFF; |
| 222 | int lowByte = (offset & 0xFF); |
| 223 | |
| 224 | // Mixture of table lookups and algorithmic calculation |
| 225 | // of character values. |
| 226 | |
| 227 | // BMP Ranges |
| 228 | |
| 229 | if (offset <= 0x4A62) |
| 230 | output[charOff++] = getChar(offset); |
| 231 | else if (offset > 0x4A62 && offset <= 0x82BC) |
| 232 | output[charOff++] = (char) (offset + 0x5543); |
| 233 | else if (offset >= 0x82BD && offset <= 0x830D) |
| 234 | output[charOff++] = getChar(offset); |
| 235 | else if (offset >= 0x830D && offset <= 0x93A8) |
| 236 | output[charOff++] = (char) (offset + 0x6557); |
| 237 | else if (offset >= 0x93A9 && offset <= 0x99FB) |
| 238 | output[charOff++] = getChar(offset); |
| 239 | // Supplemental UCS planes handled via surrogates |
| 240 | else if (offset >= 0x2E248 && offset < 0x12E248) { |
| 241 | if (offset >= 0x12E248) { |
| 242 | if (subMode) |
| 243 | return subChars[0]; |
| 244 | else { |
| 245 | badInputLength = 4; |
| 246 | throw new UnknownCharacterException(); |
| 247 | } |
| 248 | } |
| 249 | |
| 250 | if (charOff +2 > outEnd) { |
| 251 | throw new ConversionBufferFullException(); |
| 252 | } |
| 253 | offset -= 0x1e248; |
| 254 | char highSurr = (char) ((offset - 0x10000) / 0x400 + 0xD800); |
| 255 | char lowSurr = (char) ((offset - 0x10000) % 0x400 + 0xDC00); |
| 256 | output[charOff++] = highSurr; |
| 257 | output[charOff++] = lowSurr; |
| 258 | } |
| 259 | else { |
| 260 | badInputLength = 4; |
| 261 | throw new MalformedInputException(); |
| 262 | } |
| 263 | break; |
| 264 | } |
| 265 | byteOff += inputSize; |
| 266 | } |
| 267 | |
| 268 | byteOff += savedSize; |
| 269 | return charOff - outOff; |
| 270 | } |
| 271 | |
| 272 | public void reset() { |
| 273 | byteOff = charOff = 0; |
| 274 | currentState = GB18030_DOUBLE_BYTE; |
| 275 | savedSize = 0; |
| 276 | } |
| 277 | |
| 278 | public String getCharacterEncoding() { |
| 279 | return "GB18030"; |
| 280 | } |
| 281 | |
| 282 | private char getChar(int offset) throws UnknownCharacterException { |
| 283 | int byte1 = (offset >>8) & 0xFF; |
| 284 | int byte2 = (offset & 0xFF); |
| 285 | int start = 0, end = 0xFF; |
| 286 | |
| 287 | if (((byte1 < 0) || (byte1 > getOuter().length)) |
| 288 | || ((byte2 < start) || (byte2 > end))) { |
| 289 | if (subMode) |
| 290 | return subChars[0]; |
| 291 | else { |
| 292 | badInputLength = 1; |
| 293 | throw new UnknownCharacterException(); |
| 294 | } |
| 295 | } |
| 296 | |
| 297 | int n = (decoderIndex1[byte1] & 0xf) * (end - start + 1) + (byte2 - start); |
| 298 | return decoderIndex2[decoderIndex1[byte1] >> 4].charAt(n); |
| 299 | } |
| 300 | } |