J. Duke | 319a3b9 | 2007-12-01 00:00:00 +0000 | [diff] [blame^] | 1 | /* |
| 2 | * Copyright 1997-2003 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 | package sun.io; |
| 26 | |
| 27 | import java.io.UnsupportedEncodingException; |
| 28 | import sun.nio.cs.ext.JISAutoDetect; |
| 29 | |
| 30 | public class ByteToCharJISAutoDetect extends ByteToCharConverter { |
| 31 | |
| 32 | private final static int EUCJP_MASK = 0x01; |
| 33 | private final static int SJIS2B_MASK = 0x02; |
| 34 | private final static int SJIS1B_MASK = 0x04; |
| 35 | private final static int EUCJP_KANA1_MASK = 0x08; |
| 36 | private final static int EUCJP_KANA2_MASK = 0x10; |
| 37 | private static byte[] maskTable1; |
| 38 | private static byte[] maskTable2; |
| 39 | |
| 40 | private final static int SS2 = 0x8e; |
| 41 | private final static int SS3 = 0x8f; |
| 42 | |
| 43 | private final static JISAutoDetect nioCoder = new JISAutoDetect(); |
| 44 | |
| 45 | // SJISName is set to either "SJIS" or "MS932" |
| 46 | private String SJISName; |
| 47 | private String EUCJPName; |
| 48 | |
| 49 | private String convName = null; |
| 50 | private ByteToCharConverter detectedConv = null; |
| 51 | private ByteToCharConverter defaultConv = null; |
| 52 | |
| 53 | public ByteToCharJISAutoDetect() { |
| 54 | super(); |
| 55 | SJISName = CharacterEncoding.getSJISName(); |
| 56 | EUCJPName = CharacterEncoding.getEUCJPName(); |
| 57 | defaultConv = new ByteToCharISO8859_1(); |
| 58 | defaultConv.subChars = subChars; |
| 59 | defaultConv.subMode = subMode; |
| 60 | maskTable1 = nioCoder.getByteMask1(); |
| 61 | maskTable2 = nioCoder.getByteMask2(); |
| 62 | } |
| 63 | |
| 64 | public int flush(char [] output, int outStart, int outEnd) |
| 65 | throws MalformedInputException, ConversionBufferFullException |
| 66 | { |
| 67 | badInputLength = 0; |
| 68 | if(detectedConv != null) |
| 69 | return detectedConv.flush(output, outStart, outEnd); |
| 70 | else |
| 71 | return defaultConv.flush(output, outStart, outEnd); |
| 72 | } |
| 73 | |
| 74 | |
| 75 | /** |
| 76 | * Character conversion |
| 77 | */ |
| 78 | public int convert(byte[] input, int inOff, int inEnd, |
| 79 | char[] output, int outOff, int outEnd) |
| 80 | throws UnknownCharacterException, MalformedInputException, |
| 81 | ConversionBufferFullException |
| 82 | { |
| 83 | int num = 0; |
| 84 | |
| 85 | charOff = outOff; |
| 86 | byteOff = inOff; |
| 87 | |
| 88 | try { |
| 89 | if (detectedConv == null) { |
| 90 | int euckana = 0; |
| 91 | int ss2count = 0; |
| 92 | int firstmask = 0; |
| 93 | int secondmask = 0; |
| 94 | int cnt; |
| 95 | boolean nonAsciiFound = false; |
| 96 | |
| 97 | for (cnt = inOff; cnt < inEnd; cnt++) { |
| 98 | firstmask = 0; |
| 99 | secondmask = 0; |
| 100 | int byte1 = input[cnt]&0xff; |
| 101 | int byte2; |
| 102 | |
| 103 | // TODO: should check valid escape sequences! |
| 104 | if (byte1 == 0x1b) { |
| 105 | convName = "ISO2022JP"; |
| 106 | break; |
| 107 | } |
| 108 | |
| 109 | // Try to convert all leading ASCII characters. |
| 110 | if ((nonAsciiFound == false) && (byte1 < 0x80)) { |
| 111 | if (charOff >= outEnd) |
| 112 | throw new ConversionBufferFullException(); |
| 113 | output[charOff++] = (char) byte1; |
| 114 | byteOff++; |
| 115 | num++; |
| 116 | continue; |
| 117 | } |
| 118 | |
| 119 | // We can no longer convert ASCII. |
| 120 | nonAsciiFound = true; |
| 121 | |
| 122 | firstmask = maskTable1[byte1]; |
| 123 | if (byte1 == SS2) |
| 124 | ss2count++; |
| 125 | |
| 126 | if (firstmask != 0) { |
| 127 | if (cnt+1 < inEnd) { |
| 128 | byte2 = input[++cnt] & 0xff; |
| 129 | secondmask = maskTable2[byte2]; |
| 130 | int mask = firstmask & secondmask; |
| 131 | if (mask == EUCJP_MASK) { |
| 132 | convName = EUCJPName; |
| 133 | break; |
| 134 | } |
| 135 | if ((mask == SJIS2B_MASK) || (mask == SJIS1B_MASK) |
| 136 | || (nioCoder.canBeSJIS1B(firstmask) && secondmask == 0)) { |
| 137 | convName = SJISName; |
| 138 | break; |
| 139 | } |
| 140 | |
| 141 | // If the first byte is a SS3 and the third byte |
| 142 | // is not an EUC byte, it should be SJIS. |
| 143 | // Otherwise, we can't determine it yet, but it's |
| 144 | // very likely SJIS. So we don't take the EUCJP CS3 |
| 145 | // character boundary. If we tried both |
| 146 | // possibilities here, it might be able to be |
| 147 | // determined correctly. |
| 148 | if ((byte1 == SS3) && nioCoder.canBeEUCJP(secondmask)) { |
| 149 | if (cnt+1 < inEnd) { |
| 150 | int nextbyte = input[cnt+1] & 0xff; |
| 151 | if (! nioCoder.canBeEUCJP(maskTable2[nextbyte])) |
| 152 | convName = SJISName; |
| 153 | } else |
| 154 | convName = SJISName; |
| 155 | } |
| 156 | if (nioCoder.canBeEUCKana(firstmask, secondmask)) |
| 157 | euckana++; |
| 158 | } else { |
| 159 | if ((firstmask & SJIS1B_MASK) != 0) { |
| 160 | convName = SJISName; |
| 161 | break; |
| 162 | } |
| 163 | } |
| 164 | } |
| 165 | } |
| 166 | |
| 167 | if (nonAsciiFound && (convName == null)) { |
| 168 | if ((euckana > 1) || (ss2count > 1)) |
| 169 | convName = EUCJPName; |
| 170 | else |
| 171 | convName = SJISName; |
| 172 | } |
| 173 | |
| 174 | if (convName != null) { |
| 175 | try { |
| 176 | detectedConv = ByteToCharConverter.getConverter(convName); |
| 177 | detectedConv.subChars = subChars; |
| 178 | detectedConv.subMode = subMode; |
| 179 | } catch (UnsupportedEncodingException e){ |
| 180 | detectedConv = null; |
| 181 | convName = null; |
| 182 | } |
| 183 | } |
| 184 | } |
| 185 | } catch (ConversionBufferFullException bufferFullException) { |
| 186 | throw bufferFullException; |
| 187 | } catch (Exception e) { |
| 188 | // If we fail to detect the converter needed for any reason, |
| 189 | // use the default converter. |
| 190 | detectedConv = defaultConv; |
| 191 | } |
| 192 | |
| 193 | // If we've converted all ASCII characters, then return. |
| 194 | if (byteOff == inEnd) { |
| 195 | return num; |
| 196 | } |
| 197 | |
| 198 | if(detectedConv != null) { |
| 199 | try { |
| 200 | num += detectedConv.convert(input, inOff + num, inEnd, |
| 201 | output, outOff + num, outEnd); |
| 202 | } finally { |
| 203 | charOff = detectedConv.nextCharIndex(); |
| 204 | byteOff = detectedConv.nextByteIndex(); |
| 205 | badInputLength = detectedConv.badInputLength; |
| 206 | } |
| 207 | } else { |
| 208 | try { |
| 209 | num += defaultConv.convert(input, inOff + num, inEnd, |
| 210 | output, outOff + num, outEnd); |
| 211 | } finally { |
| 212 | charOff = defaultConv.nextCharIndex(); |
| 213 | byteOff = defaultConv.nextByteIndex(); |
| 214 | badInputLength = defaultConv.badInputLength; |
| 215 | } |
| 216 | } |
| 217 | return num; |
| 218 | } |
| 219 | |
| 220 | public void reset() { |
| 221 | if(detectedConv != null) { |
| 222 | detectedConv.reset(); |
| 223 | detectedConv = null; |
| 224 | convName = null; |
| 225 | } else |
| 226 | defaultConv.reset(); |
| 227 | charOff = byteOff = 0; |
| 228 | } |
| 229 | |
| 230 | public String getCharacterEncoding() { |
| 231 | return "JISAutoDetect"; |
| 232 | } |
| 233 | |
| 234 | public String toString() { |
| 235 | String s = getCharacterEncoding(); |
| 236 | if (detectedConv != null) { |
| 237 | s += "[" + detectedConv.getCharacterEncoding() + "]"; |
| 238 | } else { |
| 239 | s += "[unknown]"; |
| 240 | } |
| 241 | return s; |
| 242 | } |
| 243 | } |