Showing the changes to java/pkg/sun/io/CharToByteEUC_JP_LINUX.java (1 of 18352 files). Show all
Unified · Split
| @@ -0,0 +1,193 @@ | ||
| 1 | +/* | |
| 2 | + * Copyright (c) 2000, 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 | + | |
| 28 | +/** | |
| 29 | + * Class for converting characters to bytes for the EUC-JP encoding in | |
| 30 | + * linux. This converter supports the JIS0201 and the JIS0208 encoding and | |
| 31 | + * omits support for the JIS212 encoding. | |
| 32 | + * | |
| 33 | + * @author Naveen Sanjeeva | |
| 34 | + */ | |
| 35 | + | |
| 36 | +public class CharToByteEUC_JP_LINUX extends CharToByteJIS0208 { | |
| 37 | + CharToByteJIS0201 cbJIS0201 = new CharToByteJIS0201(); | |
| 38 | + | |
| 39 | + public String getCharacterEncoding() { | |
| 40 | + return "EUC_JP_LINUX"; | |
| 41 | + } | |
| 42 | + | |
| 43 | + protected int convSingleByte(char inputChar, byte[] outputByte) { | |
| 44 | + byte b; | |
| 45 | + | |
| 46 | + if (inputChar == 0) { | |
| 47 | + outputByte[0] = (byte)0; | |
| 48 | + return 1; | |
| 49 | + } | |
| 50 | + | |
| 51 | + if ((b = cbJIS0201.getNative(inputChar)) == 0) | |
| 52 | + return 0; | |
| 53 | + | |
| 54 | + if (b > 0 && b < 128) { | |
| 55 | + outputByte[0] = b; | |
| 56 | + return 1; | |
| 57 | + } | |
| 58 | + outputByte[0] = (byte)0x8E; | |
| 59 | + outputByte[1] = b; | |
| 60 | + return 2; | |
| 61 | + } | |
| 62 | + | |
| 63 | + protected int getNative(char ch) { | |
| 64 | + int offset = index1[((ch & 0xff00) >> 8 )] << 8; | |
| 65 | + int r = index2[offset >> 12].charAt((offset & 0xfff) + (ch & 0xff)); | |
| 66 | + if (r != 0) | |
| 67 | + return r + 0x8080; | |
| 68 | + return r; | |
| 69 | + } | |
| 70 | + | |
| 71 | + /** | |
| 72 | + * Converts characters to sequences of bytes. | |
| 73 | + * Conversions that result in Exceptions can be restarted by calling | |
| 74 | + * convert again, with appropriately modified parameters. | |
| 75 | + * @return the characters written to output. | |
| 76 | + * @param input char array containing text in Unicode | |
| 77 | + * @param inStart offset in input array | |
| 78 | + * @param inEnd offset of last byte to be converted | |
| 79 | + * @param output byte array to receive conversion result | |
| 80 | + * @param outStart starting offset | |
| 81 | + * @param outEnd offset of last byte to be written to | |
| 82 | + * @throw UnsupportedCharacterException for any character | |
| 83 | + * that cannot be converted to the external character set. | |
| 84 | + */ | |
| 85 | + public int convert(char[] input, int inOff, int inEnd, | |
| 86 | + byte[] output, int outOff, int outEnd) | |
| 87 | + throws MalformedInputException, UnknownCharacterException, | |
| 88 | + ConversionBufferFullException | |
| 89 | + { | |
| 90 | + char inputChar; // Input character to be converted | |
| 91 | + byte[] outputByte; // Output byte written to output | |
| 92 | + int inputSize = 0; // Size of input | |
| 93 | + int outputSize = 0; // Size of output | |
| 94 | + byte[] tmpbuf = new byte[4]; | |
| 95 | + | |
| 96 | + // Record beginning offsets | |
| 97 | + charOff = inOff; | |
| 98 | + byteOff = outOff; | |
| 99 | + | |
| 100 | + if (highHalfZoneCode != 0) { | |
| 101 | + inputChar = highHalfZoneCode; | |
| 102 | + highHalfZoneCode = 0; | |
| 103 | + if (input[inOff] >= 0xdc00 && input[inOff] <= 0xdfff) { | |
| 104 | + // This is legal UTF16 sequence. | |
| 105 | + badInputLength = 1; | |
| 106 | + throw new UnknownCharacterException(); | |
| 107 | + } else { | |
| 108 | + // This is illegal UTF16 sequence. | |
| 109 | + badInputLength = 0; | |
| 110 | + throw new MalformedInputException(); | |
| 111 | + } | |
| 112 | + } | |
| 113 | + | |
| 114 | + // Loop until we hit the end of the input | |
| 115 | + while(charOff < inEnd) { | |
| 116 | + inputSize = 1; | |
| 117 | + outputByte = tmpbuf; | |
| 118 | + inputChar = input[charOff]; // Get the input character | |
| 119 | + | |
| 120 | + // Is this a high surrogate? | |
| 121 | + if(inputChar >= '\uD800' && inputChar <= '\uDBFF') { | |
| 122 | + // Is this the last character of the input? | |
| 123 | + if (charOff + 1 >= inEnd) { | |
| 124 | + highHalfZoneCode = inputChar; | |
| 125 | + break; | |
| 126 | + } | |
| 127 | + | |
| 128 | + // Is there a low surrogate following? | |
| 129 | + inputChar = input[charOff + 1]; | |
| 130 | + if (inputChar >= '\uDC00' && inputChar <= '\uDFFF') { | |
| 131 | + // We have a valid surrogate pair. Too bad we don't do | |
| 132 | + // surrogates. Is substitution enabled? | |
| 133 | + if (subMode) { | |
| 134 | + outputByte = subBytes; | |
| 135 | + outputSize = subBytes.length; | |
| 136 | + inputSize = 2; | |
| 137 | + } else { | |
| 138 | + badInputLength = 2; | |
| 139 | + throw new UnknownCharacterException(); | |
| 140 | + } | |
| 141 | + } else { | |
| 142 | + // We have a malformed surrogate pair | |
| 143 | + badInputLength = 1; | |
| 144 | + throw new MalformedInputException(); | |
| 145 | + } | |
| 146 | + } | |
| 147 | + // Is this an unaccompanied low surrogate? | |
| 148 | + else if (inputChar >= '\uDC00' && inputChar <= '\uDFFF') { | |
| 149 | + badInputLength = 1; | |
| 150 | + throw new MalformedInputException(); | |
| 151 | + } else { | |
| 152 | + outputSize = convSingleByte(inputChar, outputByte); | |
| 153 | + if (outputSize == 0) { // DoubleByte | |
| 154 | + int ncode = getNative(inputChar); | |
| 155 | + if (ncode != 0 && ((ncode & 0xFF0000) == 0)) { | |
| 156 | + outputByte[0] = (byte) ((ncode & 0xff00) >> 8); | |
| 157 | + outputByte[1] = (byte) (ncode & 0xff); | |
| 158 | + outputSize = 2; | |
| 159 | + } else { | |
| 160 | + if (subMode) { | |
| 161 | + outputByte = subBytes; | |
| 162 | + outputSize = subBytes.length; | |
| 163 | + } else { | |
| 164 | + badInputLength = 1; | |
| 165 | + throw new UnknownCharacterException(); | |
| 166 | + } | |
| 167 | + } | |
| 168 | + } | |
| 169 | + } | |
| 170 | + | |
| 171 | + // If we don't have room for the output, throw an exception | |
| 172 | + if (byteOff + outputSize > outEnd) | |
| 173 | + throw new ConversionBufferFullException(); | |
| 174 | + | |
| 175 | + // Put the byte in the output buffer | |
| 176 | + for (int i = 0; i < outputSize; i++) { | |
| 177 | + output[byteOff++] = outputByte[i]; | |
| 178 | + } | |
| 179 | + charOff += inputSize; | |
| 180 | + } | |
| 181 | + // Return the length written to the output buffer | |
| 182 | + return byteOff - outOff; | |
| 183 | + } | |
| 184 | + | |
| 185 | + | |
| 186 | + /** | |
| 187 | + * the maximum number of bytes needed to hold a converted char | |
| 188 | + * @returns the maximum number of bytes needed for a converted char | |
| 189 | + */ | |
| 190 | + public int getMaxBytesPerChar() { | |
| 191 | + return 2; | |
| 192 | + } | |
| 193 | +} | |