Showing the changes to java/pkg/sun/nio/cs/UnicodeDecoder.java (1 of 18352 files). Show all
Unified · Split
| @@ -0,0 +1,135 @@ | ||
| 1 | +/* | |
| 2 | + * Copyright (c) 2000, 2006, 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.nio.cs; | |
| 27 | + | |
| 28 | +import java.nio.ByteBuffer; | |
| 29 | +import java.nio.CharBuffer; | |
| 30 | +import java.nio.charset.Charset; | |
| 31 | +import java.nio.charset.CharsetDecoder; | |
| 32 | +import java.nio.charset.CoderResult; | |
| 33 | +import java.nio.charset.CharacterCodingException; | |
| 34 | +import java.nio.charset.MalformedInputException; | |
| 35 | + | |
| 36 | + | |
| 37 | +abstract class UnicodeDecoder extends CharsetDecoder { | |
| 38 | + | |
| 39 | + protected static final char BYTE_ORDER_MARK = (char) 0xfeff; | |
| 40 | + protected static final char REVERSED_MARK = (char) 0xfffe; | |
| 41 | + | |
| 42 | + protected static final int NONE = 0; | |
| 43 | + protected static final int BIG = 1; | |
| 44 | + protected static final int LITTLE = 2; | |
| 45 | + | |
| 46 | + private final int expectedByteOrder; | |
| 47 | + private int currentByteOrder; | |
| 48 | + private int defaultByteOrder = BIG; | |
| 49 | + | |
| 50 | + public UnicodeDecoder(Charset cs, int bo) { | |
| 51 | + super(cs, 0.5f, 1.0f); | |
| 52 | + expectedByteOrder = currentByteOrder = bo; | |
| 53 | + } | |
| 54 | + | |
| 55 | + public UnicodeDecoder(Charset cs, int bo, int defaultBO) { | |
| 56 | + this(cs, bo); | |
| 57 | + defaultByteOrder = defaultBO; | |
| 58 | + } | |
| 59 | + | |
| 60 | + private char decode(int b1, int b2) { | |
| 61 | + if (currentByteOrder == BIG) | |
| 62 | + return (char)((b1 << 8) | b2); | |
| 63 | + else | |
| 64 | + return (char)((b2 << 8) | b1); | |
| 65 | + } | |
| 66 | + | |
| 67 | + protected CoderResult decodeLoop(ByteBuffer src, CharBuffer dst) { | |
| 68 | + int mark = src.position(); | |
| 69 | + | |
| 70 | + try { | |
| 71 | + while (src.remaining() > 1) { | |
| 72 | + int b1 = src.get() & 0xff; | |
| 73 | + int b2 = src.get() & 0xff; | |
| 74 | + | |
| 75 | + // Byte Order Mark interpretation | |
| 76 | + if (currentByteOrder == NONE) { | |
| 77 | + char c = (char)((b1 << 8) | b2); | |
| 78 | + if (c == BYTE_ORDER_MARK) { | |
| 79 | + currentByteOrder = BIG; | |
| 80 | + mark += 2; | |
| 81 | + continue; | |
| 82 | + } else if (c == REVERSED_MARK) { | |
| 83 | + currentByteOrder = LITTLE; | |
| 84 | + mark += 2; | |
| 85 | + continue; | |
| 86 | + } else { | |
| 87 | + currentByteOrder = defaultByteOrder; | |
| 88 | + // FALL THROUGH to process b1, b2 normally | |
| 89 | + } | |
| 90 | + } | |
| 91 | + | |
| 92 | + char c = decode(b1, b2); | |
| 93 | + | |
| 94 | + if (c == REVERSED_MARK) { | |
| 95 | + // A reversed BOM cannot occur within middle of stream | |
| 96 | + return CoderResult.malformedForLength(2); | |
| 97 | + } | |
| 98 | + | |
| 99 | + // Surrogates | |
| 100 | + if (Character.isSurrogate(c)) { | |
| 101 | + if (Character.isHighSurrogate(c)) { | |
| 102 | + if (src.remaining() < 2) | |
| 103 | + return CoderResult.UNDERFLOW; | |
| 104 | + char c2 = decode(src.get() & 0xff, src.get() & 0xff); | |
| 105 | + if (!Character.isLowSurrogate(c2)) | |
| 106 | + return CoderResult.malformedForLength(4); | |
| 107 | + if (dst.remaining() < 2) | |
| 108 | + return CoderResult.OVERFLOW; | |
| 109 | + mark += 4; | |
| 110 | + dst.put(c); | |
| 111 | + dst.put(c2); | |
| 112 | + continue; | |
| 113 | + } | |
| 114 | + // Unpaired low surrogate | |
| 115 | + return CoderResult.malformedForLength(2); | |
| 116 | + } | |
| 117 | + | |
| 118 | + if (!dst.hasRemaining()) | |
| 119 | + return CoderResult.OVERFLOW; | |
| 120 | + mark += 2; | |
| 121 | + dst.put(c); | |
| 122 | + | |
| 123 | + } | |
| 124 | + return CoderResult.UNDERFLOW; | |
| 125 | + | |
| 126 | + } finally { | |
| 127 | + src.position(mark); | |
| 128 | + } | |
| 129 | + } | |
| 130 | + | |
| 131 | + protected void implReset() { | |
| 132 | + currentByteOrder = expectedByteOrder; | |
| 133 | + } | |
| 134 | + | |
| 135 | +} | |