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 | package sun.io; |
| 26 | |
| 27 | |
| 28 | /** |
| 29 | * UCS Transformation Format 8 (UTF-8) -> UCS2 (UTF16) converter |
| 30 | * |
| 31 | * see CharToByteUTF8.java about UTF-8 format |
| 32 | */ |
| 33 | |
| 34 | public class ByteToCharUTF8 extends ByteToCharConverter { |
| 35 | |
| 36 | private int savedSize; |
| 37 | private byte[] savedBytes; |
| 38 | |
| 39 | public ByteToCharUTF8() { |
| 40 | super(); |
| 41 | savedSize = 0; |
| 42 | savedBytes = new byte[5]; |
| 43 | } |
| 44 | |
| 45 | public int flush(char[] output, int outStart, int outEnd) |
| 46 | throws MalformedInputException |
| 47 | { |
| 48 | if (savedSize != 0) { |
| 49 | savedSize = 0; |
| 50 | badInputLength = 0; |
| 51 | throw new MalformedInputException(); |
| 52 | } |
| 53 | byteOff = charOff = 0; |
| 54 | return 0; |
| 55 | } |
| 56 | |
| 57 | /** |
| 58 | * Character converson |
| 59 | */ |
| 60 | public int convert(byte[] input, int inOff, int inEnd, |
| 61 | char[] output, int outOff, int outEnd) |
| 62 | throws MalformedInputException, ConversionBufferFullException |
| 63 | { |
| 64 | int byte1, byte2, byte3, byte4; |
| 65 | char[] outputChar = new char[2]; |
| 66 | int outputSize; |
| 67 | int byteOffAdjustment = 0; |
| 68 | |
| 69 | if (savedSize != 0) { |
| 70 | byte[] newBuf; |
| 71 | newBuf = new byte[inEnd - inOff + savedSize]; |
| 72 | for (int i = 0; i < savedSize; i++) { |
| 73 | newBuf[i] = savedBytes[i]; |
| 74 | } |
| 75 | System.arraycopy(input, inOff, newBuf, savedSize, inEnd - inOff); |
| 76 | input = newBuf; |
| 77 | inOff = 0; |
| 78 | inEnd = newBuf.length; |
| 79 | byteOffAdjustment = -savedSize; |
| 80 | savedSize = 0; |
| 81 | } |
| 82 | |
| 83 | charOff = outOff; |
| 84 | byteOff = inOff; |
| 85 | int startByteOff; |
| 86 | |
| 87 | while(byteOff < inEnd) { |
| 88 | |
| 89 | startByteOff = byteOff; |
| 90 | byte1 = input[byteOff++] & 0xff; |
| 91 | |
| 92 | if ((byte1 & 0x80) == 0){ |
| 93 | outputChar[0] = (char)byte1; |
| 94 | outputSize = 1; |
| 95 | } else if ((byte1 & 0xe0) == 0xc0) { |
| 96 | if (byteOff >= inEnd) { |
| 97 | savedSize = 1; |
| 98 | savedBytes[0] = (byte)byte1; |
| 99 | break; |
| 100 | } |
| 101 | byte2 = input[byteOff++] & 0xff; |
| 102 | if ((byte2 & 0xc0) != 0x80) { |
| 103 | badInputLength = 2; |
| 104 | byteOff += byteOffAdjustment; |
| 105 | throw new MalformedInputException(); |
| 106 | } |
| 107 | outputChar[0] = (char)(((byte1 & 0x1f) << 6) | (byte2 & 0x3f)); |
| 108 | outputSize = 1; |
| 109 | } else if ((byte1 & 0xf0) == 0xe0){ |
| 110 | if (byteOff + 1 >= inEnd) { |
| 111 | savedBytes[0] = (byte)byte1; |
| 112 | if (byteOff >= inEnd) { |
| 113 | savedSize = 1; |
| 114 | } else { |
| 115 | savedSize = 2; |
| 116 | savedBytes[1] = (byte)input[byteOff++]; |
| 117 | } |
| 118 | break; |
| 119 | } |
| 120 | byte2 = input[byteOff++] & 0xff; |
| 121 | byte3 = input[byteOff++] & 0xff; |
| 122 | if ((byte2 & 0xc0) != 0x80 || (byte3 & 0xc0) != 0x80) { |
| 123 | badInputLength = 3; |
| 124 | byteOff += byteOffAdjustment; |
| 125 | throw new MalformedInputException(); |
| 126 | } |
| 127 | outputChar[0] = (char)(((byte1 & 0x0f) << 12) |
| 128 | | ((byte2 & 0x3f) << 6) |
| 129 | | (byte3 & 0x3f)); |
| 130 | outputSize = 1; |
| 131 | } else if ((byte1 & 0xf8) == 0xf0) { |
| 132 | if (byteOff + 2 >= inEnd) { |
| 133 | savedBytes[0] = (byte)byte1; |
| 134 | if (byteOff >= inEnd) { |
| 135 | savedSize = 1; |
| 136 | } else if (byteOff + 1 >= inEnd) { |
| 137 | savedSize = 2; |
| 138 | savedBytes[1] = (byte)input[byteOff++]; |
| 139 | } else { |
| 140 | savedSize = 3; |
| 141 | savedBytes[1] = (byte)input[byteOff++]; |
| 142 | savedBytes[2] = (byte)input[byteOff++]; |
| 143 | } |
| 144 | break; |
| 145 | } |
| 146 | byte2 = input[byteOff++] & 0xff; |
| 147 | byte3 = input[byteOff++] & 0xff; |
| 148 | byte4 = input[byteOff++] & 0xff; |
| 149 | if ((byte2 & 0xc0) != 0x80 || |
| 150 | (byte3 & 0xc0) != 0x80 || |
| 151 | (byte4 & 0xc0) != 0x80) { |
| 152 | badInputLength = 4; |
| 153 | byteOff += byteOffAdjustment; |
| 154 | throw new MalformedInputException(); |
| 155 | } |
| 156 | // this byte sequence is UTF16 character |
| 157 | int ucs4 = (int)(0x07 & byte1) << 18 | |
| 158 | (int)(0x3f & byte2) << 12 | |
| 159 | (int)(0x3f & byte3) << 6 | |
| 160 | (int)(0x3f & byte4); |
| 161 | outputChar[0] = (char)((ucs4 - 0x10000) / 0x400 + 0xd800); |
| 162 | outputChar[1] = (char)((ucs4 - 0x10000) % 0x400 + 0xdc00); |
| 163 | outputSize = 2; |
| 164 | } else { |
| 165 | badInputLength = 1; |
| 166 | byteOff += byteOffAdjustment; |
| 167 | throw new MalformedInputException(); |
| 168 | } |
| 169 | |
| 170 | if (charOff + outputSize > outEnd) { |
| 171 | byteOff = startByteOff; |
| 172 | byteOff += byteOffAdjustment; |
| 173 | throw new ConversionBufferFullException(); |
| 174 | } |
| 175 | |
| 176 | for (int i = 0; i < outputSize; i++) { |
| 177 | output[charOff + i] = outputChar[i]; |
| 178 | } |
| 179 | charOff += outputSize; |
| 180 | } |
| 181 | |
| 182 | byteOff += byteOffAdjustment; |
| 183 | return charOff - outOff; |
| 184 | } |
| 185 | |
| 186 | /* |
| 187 | * Return the character set id |
| 188 | */ |
| 189 | public String getCharacterEncoding() { |
| 190 | return "UTF8"; |
| 191 | } |
| 192 | |
| 193 | /* |
| 194 | * Reset after finding bad input |
| 195 | */ |
| 196 | public void reset() { |
| 197 | byteOff = charOff = 0; |
| 198 | savedSize = 0; |
| 199 | } |
| 200 | } |