Showing the changes to java/pkg/sun/io/CharToByteISO2022JP.java (1 of 18352 files). Show all
Unified · Split
| @@ -0,0 +1,319 @@ | ||
| 1 | +/* | |
| 2 | + * Copyright (c) 1996, 1999, Oracle and/or its affiliates. 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. Oracle designates this | |
| 8 | + * particular file as subject to the "Classpath" exception as provided | |
| 9 | + * by Oracle 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 Oracle, 500 Oracle Parkway, Redwood Shores, CA 94065 USA | |
| 22 | + * or visit www.oracle.com if you need additional information or have any | |
| 23 | + * questions. | |
| 24 | + */ | |
| 25 | + | |
| 26 | +package sun.io; | |
| 27 | +import java.io.*; | |
| 28 | + | |
| 29 | +public class CharToByteISO2022JP extends CharToByteJIS0208 { | |
| 30 | + | |
| 31 | + private static final int ASCII = 0; // ESC ( B | |
| 32 | + private static final int JISX0201_1976 = 1; // ESC ( J | |
| 33 | + private static final int JISX0208_1978 = 2; // ESC $ @ | |
| 34 | + private static final int JISX0208_1983 = 3; // ESC $ B | |
| 35 | + private static final int JISX0201_1976_KANA = 4; // ESC ( I | |
| 36 | + | |
| 37 | + private char highHalfZoneCode; | |
| 38 | + private boolean flushed = true; | |
| 39 | + | |
| 40 | + // JIS is state full encoding, so currentMode keep the | |
| 41 | + // current codeset | |
| 42 | + private int currentMode = ASCII; | |
| 43 | + | |
| 44 | + /** | |
| 45 | + * Bytes for substitute for unmappable input. | |
| 46 | + */ | |
| 47 | + // XXX: Assumes subBytes are ASCII string. Need to change Escape sequence | |
| 48 | + // for other character sets. | |
| 49 | + protected byte[] subBytesEscape = { (byte)0x1b, (byte)0x28, (byte)0x42 }; // ESC ( B | |
| 50 | + protected int subBytesMode = ASCII; | |
| 51 | + | |
| 52 | + public int flush(byte[] output, int outStart, int outEnd) | |
| 53 | + throws MalformedInputException, ConversionBufferFullException | |
| 54 | + { | |
| 55 | + if (highHalfZoneCode != 0) { | |
| 56 | + highHalfZoneCode = 0; | |
| 57 | + badInputLength = 0; | |
| 58 | + throw new MalformedInputException(); | |
| 59 | + } | |
| 60 | + | |
| 61 | + if (!flushed && (currentMode != ASCII)) { | |
| 62 | + if (outEnd - outStart < 3) { | |
| 63 | + throw new ConversionBufferFullException(); | |
| 64 | + } | |
| 65 | + output[outStart] = (byte)0x1b; | |
| 66 | + output[outStart + 1] = (byte)0x28; | |
| 67 | + output[outStart + 2] = (byte)0x42; | |
| 68 | + byteOff += 3; | |
| 69 | + byteOff = charOff = 0; | |
| 70 | + flushed = true; | |
| 71 | + currentMode = ASCII; | |
| 72 | + return 3; | |
| 73 | + } | |
| 74 | + return 0; | |
| 75 | + } | |
| 76 | + | |
| 77 | + public int convert(char[] input, int inOff, int inEnd, | |
| 78 | + byte[] output, int outOff, int outEnd) | |
| 79 | + throws MalformedInputException, UnknownCharacterException, | |
| 80 | + ConversionBufferFullException | |
| 81 | + | |
| 82 | + { | |
| 83 | + char inputChar; // Input character to be converted | |
| 84 | + int inputSize; // Size of the input | |
| 85 | + int outputSize; // Size of the output | |
| 86 | + | |
| 87 | + // Buffer for output bytes | |
| 88 | + byte[] tmpArray = new byte[6]; | |
| 89 | + byte[] outputByte; | |
| 90 | + | |
| 91 | + flushed = false; | |
| 92 | + | |
| 93 | + // Make copies of input and output indexes | |
| 94 | + charOff = inOff; | |
| 95 | + byteOff = outOff; | |
| 96 | + | |
| 97 | + if (highHalfZoneCode != 0) { | |
| 98 | + inputChar = highHalfZoneCode; | |
| 99 | + highHalfZoneCode = 0; | |
| 100 | + if (input[inOff] >= 0xdc00 && input[inOff] <= 0xdfff) { | |
| 101 | + // This is legal UTF16 sequence. | |
| 102 | + badInputLength = 1; | |
| 103 | + throw new UnknownCharacterException(); | |
| 104 | + } else { | |
| 105 | + // This is illegal UTF16 sequence. | |
| 106 | + badInputLength = 0; | |
| 107 | + throw new MalformedInputException(); | |
| 108 | + } | |
| 109 | + } | |
| 110 | + | |
| 111 | + // Loop until we run out of input | |
| 112 | + while(charOff < inEnd) { | |
| 113 | + outputByte = tmpArray; | |
| 114 | + int newMode = currentMode; // Trace character mode changing | |
| 115 | + | |
| 116 | + // Get the input character | |
| 117 | + inputChar = input[charOff]; | |
| 118 | + inputSize = 1; | |
| 119 | + outputSize = 1; | |
| 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 | + if (currentMode != subBytesMode) { | |
| 136 | + System.arraycopy(subBytesEscape, 0, outputByte, 0, | |
| 137 | + subBytesEscape.length); | |
| 138 | + outputSize = subBytesEscape.length; | |
| 139 | + System.arraycopy(subBytes, 0, outputByte, | |
| 140 | + outputSize, subBytes.length); | |
| 141 | + outputSize += subBytes.length; | |
| 142 | + newMode = subBytesMode; | |
| 143 | + } else { | |
| 144 | + outputByte = subBytes; | |
| 145 | + outputSize = subBytes.length; | |
| 146 | + } | |
| 147 | + inputSize = 2; | |
| 148 | + } else { | |
| 149 | + badInputLength = 2; | |
| 150 | + throw new UnknownCharacterException(); | |
| 151 | + } | |
| 152 | + } else { | |
| 153 | + // We have a malformed surrogate pair | |
| 154 | + badInputLength = 1; | |
| 155 | + throw new MalformedInputException(); | |
| 156 | + } | |
| 157 | + } | |
| 158 | + | |
| 159 | + // Is this an unaccompanied low surrogate? | |
| 160 | + else if (inputChar >= '\uDC00' && inputChar <= '\uDFFF') { | |
| 161 | + badInputLength = 1; | |
| 162 | + throw new MalformedInputException(); | |
| 163 | + } else { | |
| 164 | + // Not part of a surrogate | |
| 165 | + | |
| 166 | + // Does this map to the Roman range? | |
| 167 | + if (inputChar <= '\u007F') { | |
| 168 | + if (currentMode != ASCII) { | |
| 169 | + outputByte[0] = (byte)0x1b; | |
| 170 | + outputByte[1] = (byte)0x28; | |
| 171 | + outputByte[2] = (byte)0x42; | |
| 172 | + outputByte[3] = (byte)inputChar; | |
| 173 | + outputSize = 4; | |
| 174 | + newMode = ASCII; | |
| 175 | + } else { | |
| 176 | + outputByte[0] = (byte)inputChar; | |
| 177 | + outputSize = 1; | |
| 178 | + } | |
| 179 | + } | |
| 180 | + // Is it a single byte kana? | |
| 181 | + else if (inputChar >= 0xFF61 && inputChar <= 0xFF9F) { | |
| 182 | + if (currentMode != JISX0201_1976_KANA) { | |
| 183 | + outputByte[0] = (byte)0x1b; | |
| 184 | + outputByte[1] = (byte)0x28; | |
| 185 | + outputByte[2] = (byte)0x49; | |
| 186 | + outputByte[3] = (byte)(inputChar - 0xff40); | |
| 187 | + outputSize = 4; | |
| 188 | + newMode = JISX0201_1976_KANA; | |
| 189 | + } else { | |
| 190 | + outputByte[0] = (byte)(inputChar - 0xff40); | |
| 191 | + outputSize = 1; | |
| 192 | + } | |
| 193 | + } | |
| 194 | + // Is it a yen sign? | |
| 195 | + else if (inputChar == '\u00A5') { | |
| 196 | + if (currentMode != JISX0201_1976) { | |
| 197 | + outputByte[0] = (byte)0x1b; | |
| 198 | + outputByte[1] = (byte)0x28; | |
| 199 | + outputByte[2] = (byte)0x4a; | |
| 200 | + outputByte[3] = (byte)0x5c; | |
| 201 | + outputSize = 4; | |
| 202 | + newMode = JISX0201_1976; | |
| 203 | + } else { | |
| 204 | + outputByte[0] = (byte)0x5C; | |
| 205 | + outputSize = 1; | |
| 206 | + } | |
| 207 | + } | |
| 208 | + // Is it a tilde? | |
| 209 | + else if (inputChar == '\u203E') | |
| 210 | + { | |
| 211 | + if (currentMode != JISX0201_1976) { | |
| 212 | + outputByte[0] = (byte)0x1b; | |
| 213 | + outputByte[1] = (byte)0x28; | |
| 214 | + outputByte[2] = (byte)0x4a; | |
| 215 | + outputByte[3] = (byte)0x7e; | |
| 216 | + outputSize = 4; | |
| 217 | + newMode = JISX0201_1976; | |
| 218 | + } else { | |
| 219 | + outputByte[0] = (byte)0x7e; | |
| 220 | + outputSize = 1; | |
| 221 | + } | |
| 222 | + } | |
| 223 | + // Is it a JIS-X-0208 character? | |
| 224 | + else { | |
| 225 | + int index = getNative(inputChar); | |
| 226 | + if (index != 0) { | |
| 227 | + if (currentMode != JISX0208_1983) { | |
| 228 | + outputByte[0] = (byte)0x1b; | |
| 229 | + outputByte[1] = (byte)0x24; | |
| 230 | + outputByte[2] = (byte)0x42; | |
| 231 | + outputByte[3] = (byte)(index >> 8); | |
| 232 | + outputByte[4] = (byte)(index & 0xff); | |
| 233 | + outputSize = 5; | |
| 234 | + newMode = JISX0208_1983; | |
| 235 | + } else { | |
| 236 | + outputByte[0] = (byte)(index >> 8); | |
| 237 | + outputByte[1] = (byte)(index & 0xff); | |
| 238 | + outputSize = 2; | |
| 239 | + } | |
| 240 | + } | |
| 241 | + // It doesn't map to JIS-0208! | |
| 242 | + else { | |
| 243 | + if (subMode) { | |
| 244 | + if (currentMode != subBytesMode) { | |
| 245 | + System.arraycopy(subBytesEscape, 0, outputByte, 0, | |
| 246 | + subBytesEscape.length); | |
| 247 | + outputSize = subBytesEscape.length; | |
| 248 | + System.arraycopy(subBytes, 0, outputByte, | |
| 249 | + outputSize, subBytes.length); | |
| 250 | + outputSize += subBytes.length; | |
| 251 | + newMode = subBytesMode; | |
| 252 | + } else { | |
| 253 | + outputByte = subBytes; | |
| 254 | + outputSize = subBytes.length; | |
| 255 | + } | |
| 256 | + } else { | |
| 257 | + badInputLength = 1; | |
| 258 | + throw new UnknownCharacterException(); | |
| 259 | + } | |
| 260 | + } | |
| 261 | + } | |
| 262 | + } | |
| 263 | + | |
| 264 | + // Is there room in the output buffer? | |
| 265 | + // XXX: The code assumes output buffer can hold at least 5 bytes, | |
| 266 | + // in this coverter case. However, there is no way for apps to | |
| 267 | + // see how many bytes will be necessary for next call. | |
| 268 | + // getMaxBytesPerChar() should be overriden in every subclass of | |
| 269 | + // CharToByteConverter and reflect real value (5 for this). | |
| 270 | + if (byteOff + outputSize > outEnd) | |
| 271 | + throw new ConversionBufferFullException(); | |
| 272 | + | |
| 273 | + // Put the output into the buffer | |
| 274 | + for ( int i = 0 ; i < outputSize ; i++ ) | |
| 275 | + output[byteOff++] = outputByte[i]; | |
| 276 | + | |
| 277 | + // Advance the input pointer | |
| 278 | + charOff += inputSize; | |
| 279 | + | |
| 280 | + // We can successfuly output the characters, changes | |
| 281 | + // current mode. Fix for 4251646. | |
| 282 | + currentMode = newMode; | |
| 283 | + } | |
| 284 | + | |
| 285 | + // return mode ASCII at the end | |
| 286 | + if (currentMode != ASCII){ | |
| 287 | + if (byteOff + 3 > outEnd) | |
| 288 | + throw new ConversionBufferFullException(); | |
| 289 | + | |
| 290 | + output[byteOff++] = 0x1b; | |
| 291 | + output[byteOff++] = 0x28; | |
| 292 | + output[byteOff++] = 0x42; | |
| 293 | + currentMode = ASCII; | |
| 294 | + } | |
| 295 | + | |
| 296 | + // Return the length written to the output buffer | |
| 297 | + return byteOff-outOff; | |
| 298 | + } | |
| 299 | + | |
| 300 | + // Reset | |
| 301 | + public void reset() { | |
| 302 | + highHalfZoneCode = 0; | |
| 303 | + byteOff = charOff = 0; | |
| 304 | + currentMode = ASCII; | |
| 305 | + } | |
| 306 | + | |
| 307 | + /** | |
| 308 | + * returns the maximum number of bytes needed to convert a char | |
| 309 | + */ | |
| 310 | + public int getMaxBytesPerChar() { | |
| 311 | + return 8; | |
| 312 | + } | |
| 313 | + | |
| 314 | + // Return the character set ID | |
| 315 | + public String getCharacterEncoding() { | |
| 316 | + return "ISO2022JP"; | |
| 317 | + } | |
| 318 | + | |
| 319 | +} | |