J. Duke | 319a3b9 | 2007-12-01 00:00:00 +0000 | [diff] [blame^] | 1 | /* |
| 2 | * Copyright 2003-2006 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 | /* |
| 27 | */ |
| 28 | |
| 29 | /** |
| 30 | * Simple EUC-like decoder used by IBM01383 and IBM970 |
| 31 | * supports G1 - no support for G2 or G3 |
| 32 | */ |
| 33 | |
| 34 | package sun.nio.cs.ext; |
| 35 | |
| 36 | import java.nio.ByteBuffer; |
| 37 | import java.nio.CharBuffer; |
| 38 | import java.nio.charset.Charset; |
| 39 | import java.nio.charset.CharsetDecoder; |
| 40 | import java.nio.charset.CoderResult; |
| 41 | |
| 42 | abstract class SimpleEUCDecoder |
| 43 | extends CharsetDecoder |
| 44 | { |
| 45 | private final int SS2 = 0x8E; |
| 46 | private final int SS3 = 0x8F; |
| 47 | |
| 48 | protected static String mappingTableG1; |
| 49 | protected static String byteToCharTable; |
| 50 | |
| 51 | protected SimpleEUCDecoder(Charset cs) { |
| 52 | super(cs, 0.5f, 1.0f); |
| 53 | } |
| 54 | |
| 55 | private CoderResult decodeArrayLoop(ByteBuffer src, CharBuffer dst) { |
| 56 | byte[] sa = src.array(); |
| 57 | int sp = src.arrayOffset() + src.position(); |
| 58 | int sl = src.arrayOffset() + src.limit(); |
| 59 | assert (sp <= sl); |
| 60 | sp = (sp <= sl ? sp : sl); |
| 61 | char[] da = dst.array(); |
| 62 | int dp = dst.arrayOffset() + dst.position(); |
| 63 | int dl = dst.arrayOffset() + dst.limit(); |
| 64 | assert (dp <= dl); |
| 65 | dp = (dp <= dl ? dp : dl); |
| 66 | |
| 67 | try { |
| 68 | while (sp < sl) { |
| 69 | int byte1, byte2; |
| 70 | int inputSize = 1; |
| 71 | char outputChar = '\uFFFD'; |
| 72 | |
| 73 | byte1 = sa[sp] & 0xff; |
| 74 | |
| 75 | if ( byte1 <= 0x9f ) { // < 0x9f has its own table (G0) |
| 76 | if (byte1 == SS2 || byte1 == SS3 ) { |
| 77 | // No support provided for G2/G3 at this time. |
| 78 | return CoderResult.malformedForLength(1); |
| 79 | } |
| 80 | outputChar = byteToCharTable.charAt(byte1); |
| 81 | } else if (byte1 < 0xa1 || byte1 > 0xfe) { // invalid range? |
| 82 | return CoderResult.malformedForLength(1); |
| 83 | } else { // (G1) |
| 84 | if (sl - sp < 2) { |
| 85 | return CoderResult.UNDERFLOW; |
| 86 | } |
| 87 | byte2 = sa[sp + 1] & 0xff; |
| 88 | inputSize++; |
| 89 | if ( byte2 < 0xa1 || byte2 > 0xfe) { |
| 90 | return CoderResult.malformedForLength(2); |
| 91 | } |
| 92 | outputChar = mappingTableG1.charAt(((byte1 - 0xa1) * 94) + byte2 - 0xa1); |
| 93 | } |
| 94 | if (outputChar == '\uFFFD') { |
| 95 | return CoderResult.unmappableForLength(inputSize); |
| 96 | } |
| 97 | if (dl - dp < 1) |
| 98 | return CoderResult.OVERFLOW; |
| 99 | da[dp++] = outputChar; |
| 100 | sp += inputSize; |
| 101 | } |
| 102 | return CoderResult.UNDERFLOW; |
| 103 | } finally { |
| 104 | src.position(sp - src.arrayOffset()); |
| 105 | dst.position(dp - dst.arrayOffset()); |
| 106 | } |
| 107 | } |
| 108 | |
| 109 | private CoderResult decodeBufferLoop(ByteBuffer src, CharBuffer dst) { |
| 110 | int mark = src.position(); |
| 111 | |
| 112 | try { |
| 113 | while (src.hasRemaining()) { |
| 114 | char outputChar = '\uFFFD'; |
| 115 | int inputSize = 1; |
| 116 | int byte1, byte2; |
| 117 | |
| 118 | byte1 = src.get() & 0xff; |
| 119 | if ( byte1 <= 0x9f ) { |
| 120 | if (byte1 == SS2 || byte1 == SS3 ) { |
| 121 | return CoderResult.malformedForLength(1); |
| 122 | } |
| 123 | outputChar = byteToCharTable.charAt(byte1); |
| 124 | } else if (byte1 < 0xa1 || byte1 > 0xfe) { |
| 125 | return CoderResult.malformedForLength(1); |
| 126 | } else { |
| 127 | if (!src.hasRemaining()) { |
| 128 | return CoderResult.UNDERFLOW; |
| 129 | } |
| 130 | byte2 = src.get() & 0xff; |
| 131 | inputSize++; |
| 132 | if ( byte2 < 0xa1 || byte2 > 0xfe) { |
| 133 | return CoderResult.malformedForLength(2); |
| 134 | } |
| 135 | outputChar = mappingTableG1.charAt(((byte1 - 0xa1) * 94) + byte2 - 0xa1); |
| 136 | } |
| 137 | if (outputChar == '\uFFFD') { |
| 138 | return CoderResult.unmappableForLength(inputSize); |
| 139 | } |
| 140 | if (!dst.hasRemaining()) |
| 141 | return CoderResult.OVERFLOW; |
| 142 | dst.put(outputChar); |
| 143 | mark += inputSize; |
| 144 | } |
| 145 | return CoderResult.UNDERFLOW; |
| 146 | } finally { |
| 147 | src.position(mark); |
| 148 | } |
| 149 | } |
| 150 | |
| 151 | protected CoderResult decodeLoop(ByteBuffer src, CharBuffer dst) { |
| 152 | if (src.hasArray() && dst.hasArray()) |
| 153 | return decodeArrayLoop(src, dst); |
| 154 | else |
| 155 | return decodeBufferLoop(src, dst); |
| 156 | } |
| 157 | } |