J. Duke | 319a3b9 | 2007-12-01 00:00:00 +0000 | [diff] [blame^] | 1 | /* |
| 2 | * Copyright 1996-1999 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 | */ |
| 31 | |
| 32 | public class CharToByteEUC_JP extends CharToByteJIS0208 { |
| 33 | CharToByteJIS0201 cbJIS0201 = new CharToByteJIS0201(); |
| 34 | CharToByteJIS0212 cbJIS0212 = new CharToByteJIS0212(); |
| 35 | |
| 36 | public String getCharacterEncoding() { |
| 37 | return "EUC_JP"; |
| 38 | } |
| 39 | |
| 40 | protected int convSingleByte(char inputChar, byte[] outputByte) { |
| 41 | byte b; |
| 42 | |
| 43 | if (inputChar == 0) { |
| 44 | outputByte[0] = (byte)0; |
| 45 | return 1; |
| 46 | } |
| 47 | |
| 48 | if ((b = cbJIS0201.getNative(inputChar)) == 0) |
| 49 | return 0; |
| 50 | |
| 51 | if (b > 0 && b < 128) { |
| 52 | outputByte[0] = b; |
| 53 | return 1; |
| 54 | } |
| 55 | outputByte[0] = (byte)0x8E; |
| 56 | outputByte[1] = b; |
| 57 | return 2; |
| 58 | } |
| 59 | |
| 60 | protected int getNative(char ch) { |
| 61 | int offset = index1[((ch & 0xff00) >> 8 )] << 8; |
| 62 | int r = index2[offset >> 12].charAt((offset & 0xfff) + (ch & 0xff)); |
| 63 | if (r != 0) |
| 64 | return r + 0x8080; |
| 65 | r = cbJIS0212.getNative(ch); |
| 66 | if (r == 0) |
| 67 | return r; |
| 68 | return r + 0x8F8080; |
| 69 | } |
| 70 | |
| 71 | |
| 72 | /** |
| 73 | * Converts characters to sequences of bytes. |
| 74 | * Conversions that result in Exceptions can be restarted by calling |
| 75 | * convert again, with appropriately modified parameters. |
| 76 | * @return the characters written to output. |
| 77 | * @param input char array containing text in Unicode |
| 78 | * @param inStart offset in input array |
| 79 | * @param inEnd offset of last byte to be converted |
| 80 | * @param output byte array to receive conversion result |
| 81 | * @param outStart starting offset |
| 82 | * @param outEnd offset of last byte to be written to |
| 83 | * @throw UnsupportedCharacterException for any character |
| 84 | * that cannot be converted to the external character set. |
| 85 | */ |
| 86 | public int convert(char[] input, int inOff, int inEnd, |
| 87 | byte[] output, int outOff, int outEnd) |
| 88 | throws MalformedInputException, UnknownCharacterException, |
| 89 | ConversionBufferFullException |
| 90 | { |
| 91 | char inputChar; // Input character to be converted |
| 92 | byte[] outputByte; // Output byte written to output |
| 93 | int inputSize = 0; // Size of input |
| 94 | int outputSize = 0; // Size of output |
| 95 | byte[] tmpbuf = new byte[4]; |
| 96 | |
| 97 | // Record beginning offsets |
| 98 | charOff = inOff; |
| 99 | byteOff = outOff; |
| 100 | |
| 101 | if (highHalfZoneCode != 0) { |
| 102 | inputChar = highHalfZoneCode; |
| 103 | highHalfZoneCode = 0; |
| 104 | if (input[inOff] >= 0xdc00 && input[inOff] <= 0xdfff) { |
| 105 | // This is legal UTF16 sequence. |
| 106 | badInputLength = 1; |
| 107 | throw new UnknownCharacterException(); |
| 108 | } else { |
| 109 | // This is illegal UTF16 sequence. |
| 110 | badInputLength = 0; |
| 111 | throw new MalformedInputException(); |
| 112 | } |
| 113 | } |
| 114 | |
| 115 | // Loop until we hit the end of the input |
| 116 | while(charOff < inEnd) { |
| 117 | inputSize = 1; |
| 118 | outputByte = tmpbuf; |
| 119 | inputChar = input[charOff]; // Get the input character |
| 120 | |
| 121 | // Is this a high surrogate? |
| 122 | if(inputChar >= '\uD800' && inputChar <= '\uDBFF') { |
| 123 | // Is this the last character of the input? |
| 124 | if (charOff + 1 >= inEnd) { |
| 125 | highHalfZoneCode = inputChar; |
| 126 | break; |
| 127 | } |
| 128 | |
| 129 | // Is there a low surrogate following? |
| 130 | inputChar = input[charOff + 1]; |
| 131 | if (inputChar >= '\uDC00' && inputChar <= '\uDFFF') { |
| 132 | // We have a valid surrogate pair. Too bad we don't do |
| 133 | // surrogates. Is substitution enabled? |
| 134 | if (subMode) { |
| 135 | outputByte = subBytes; |
| 136 | outputSize = subBytes.length; |
| 137 | inputSize = 2; |
| 138 | } else { |
| 139 | badInputLength = 2; |
| 140 | throw new UnknownCharacterException(); |
| 141 | } |
| 142 | } else { |
| 143 | // We have a malformed surrogate pair |
| 144 | badInputLength = 1; |
| 145 | throw new MalformedInputException(); |
| 146 | } |
| 147 | } |
| 148 | // Is this an unaccompanied low surrogate? |
| 149 | else if (inputChar >= '\uDC00' && inputChar <= '\uDFFF') { |
| 150 | badInputLength = 1; |
| 151 | throw new MalformedInputException(); |
| 152 | } else { |
| 153 | outputSize = convSingleByte(inputChar, outputByte); |
| 154 | if (outputSize == 0) { // DoubleByte |
| 155 | int ncode = getNative(inputChar); |
| 156 | if (ncode != 0 ) { |
| 157 | if ((ncode & 0xFF0000) == 0) { |
| 158 | outputByte[0] = (byte) ((ncode & 0xff00) >> 8); |
| 159 | outputByte[1] = (byte) (ncode & 0xff); |
| 160 | outputSize = 2; |
| 161 | } else { |
| 162 | outputByte[0] = (byte) 0x8F; |
| 163 | outputByte[1] = (byte) ((ncode & 0xff00) >> 8); |
| 164 | outputByte[2] = (byte) (ncode & 0xff); |
| 165 | outputSize = 3; |
| 166 | } |
| 167 | } else { |
| 168 | if (subMode) { |
| 169 | outputByte = subBytes; |
| 170 | outputSize = subBytes.length; |
| 171 | } else { |
| 172 | badInputLength = 1; |
| 173 | throw new UnknownCharacterException(); |
| 174 | } |
| 175 | } |
| 176 | } |
| 177 | } |
| 178 | |
| 179 | // If we don't have room for the output, throw an exception |
| 180 | if (byteOff + outputSize > outEnd) |
| 181 | throw new ConversionBufferFullException(); |
| 182 | |
| 183 | // Put the byte in the output buffer |
| 184 | for (int i = 0; i < outputSize; i++) { |
| 185 | output[byteOff++] = outputByte[i]; |
| 186 | } |
| 187 | charOff += inputSize; |
| 188 | } |
| 189 | // Return the length written to the output buffer |
| 190 | return byteOff - outOff; |
| 191 | } |
| 192 | |
| 193 | |
| 194 | /** |
| 195 | * the maximum number of bytes needed to hold a converted char |
| 196 | * @returns the maximum number of bytes needed for a converted char |
| 197 | */ |
| 198 | public int getMaxBytesPerChar() { |
| 199 | return 3; |
| 200 | } |
| 201 | } |