1 /* |
|
2 * Copyright (c) 1996, 2004, 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 import sun.nio.cs.ext.EUC_TW; |
|
29 |
|
30 /* |
|
31 * @author Limin Shi |
|
32 */ |
|
33 public class ByteToCharEUC_TW extends ByteToCharConverter |
|
34 { |
|
35 private final byte G0 = 0; |
|
36 private final byte G1 = 1; |
|
37 private final byte G2 = 2; |
|
38 private final byte G3 = 3; |
|
39 private final byte G4 = 4; |
|
40 private final byte MSB = (byte) 0x80; |
|
41 private final byte SS2 = (byte) 0x8E; |
|
42 |
|
43 private byte firstByte = 0, state = G0; |
|
44 private int cnsPlane = 0; |
|
45 |
|
46 private EUC_TW.Decoder dec = (EUC_TW.Decoder)(new EUC_TW().newDecoder()); |
|
47 |
|
48 public ByteToCharEUC_TW() { |
|
49 } |
|
50 |
|
51 public int flush(char[] output, int outStart, int outEnd) |
|
52 throws MalformedInputException |
|
53 { |
|
54 if (state != G0) { |
|
55 state = G0; |
|
56 firstByte = 0; |
|
57 badInputLength = 0; |
|
58 throw new MalformedInputException(); |
|
59 } |
|
60 reset(); |
|
61 return 0; |
|
62 } |
|
63 |
|
64 public void reset() { |
|
65 dec.reset(); |
|
66 state = G0; |
|
67 firstByte = 0; |
|
68 byteOff = charOff = 0; |
|
69 } |
|
70 |
|
71 /** |
|
72 * Character conversion |
|
73 */ |
|
74 public int convert(byte[] input, int inOff, int inEnd, |
|
75 char[] output, int outOff, int outEnd) |
|
76 throws UnknownCharacterException, MalformedInputException, |
|
77 ConversionBufferFullException |
|
78 { |
|
79 int inputSize = 0; |
|
80 char[] c1 = new char[1]; |
|
81 |
|
82 byteOff = inOff; |
|
83 charOff = outOff; |
|
84 |
|
85 cnsPlane = 3; |
|
86 while (byteOff < inEnd) { |
|
87 if (charOff >= outEnd) |
|
88 throw new ConversionBufferFullException(); |
|
89 char[] outputChar = null; |
|
90 switch (state) { |
|
91 case G0: |
|
92 if ( (input[byteOff] & MSB) == 0) { // ASCII |
|
93 outputChar = c1; |
|
94 outputChar[0] = (char) input[byteOff]; |
|
95 } else if (input[byteOff] == SS2) { // Codeset 2 |
|
96 state = G2; |
|
97 } else { // Codeset 1 |
|
98 firstByte = input[byteOff]; |
|
99 state = G1; |
|
100 } |
|
101 break; |
|
102 case G1: |
|
103 inputSize = 2; |
|
104 if ( (input[byteOff] & MSB) != 0) { // 2nd byte |
|
105 cnsPlane = 0; |
|
106 outputChar = dec.toUnicode(firstByte & 0xff, |
|
107 input[byteOff] & 0xff, |
|
108 cnsPlane); |
|
109 } else { // Error |
|
110 badInputLength = 1; |
|
111 throw new MalformedInputException(); |
|
112 } |
|
113 firstByte = 0; |
|
114 state = G0; |
|
115 break; |
|
116 case G2: |
|
117 cnsPlane = (input[byteOff] & (byte)0x0f); |
|
118 // Adjust String array index for plan 15 |
|
119 cnsPlane = (cnsPlane == 15)? 8 : cnsPlane; |
|
120 |
|
121 if (cnsPlane < 15) { |
|
122 state = G3; |
|
123 } else { |
|
124 badInputLength = 2; |
|
125 throw new MalformedInputException(); |
|
126 } |
|
127 |
|
128 break; |
|
129 case G3: |
|
130 if ( (input[byteOff] & MSB) != 0) { // 1st byte |
|
131 firstByte = input[byteOff]; |
|
132 state = G4; |
|
133 } else { // Error |
|
134 state = G0; |
|
135 badInputLength = 2; |
|
136 throw new MalformedInputException(); |
|
137 } |
|
138 break; |
|
139 case G4: |
|
140 if ( (input[byteOff] & MSB) != 0) { // 2nd byte |
|
141 outputChar = dec.toUnicode(firstByte & 0xff, |
|
142 input[byteOff] & 0xff, |
|
143 cnsPlane - 1); |
|
144 } else { // Error |
|
145 badInputLength = 3; |
|
146 throw new MalformedInputException(); |
|
147 } |
|
148 firstByte = 0; |
|
149 state = G0; |
|
150 break; |
|
151 } |
|
152 byteOff++; |
|
153 if (state == G0) { |
|
154 if (outputChar == null) { |
|
155 if (subMode) { // substitution enabled |
|
156 outputChar = c1; |
|
157 outputChar[0] = subChars[0]; |
|
158 } else { |
|
159 badInputLength = inputSize; |
|
160 throw new UnknownCharacterException(); |
|
161 } |
|
162 } |
|
163 output[charOff++] = outputChar[0]; |
|
164 } |
|
165 } |
|
166 return charOff - outOff; |
|
167 } |
|
168 |
|
169 |
|
170 /** |
|
171 * Return the character set ID |
|
172 */ |
|
173 public String getCharacterEncoding() { |
|
174 return "EUC_TW"; |
|
175 } |
|
176 } |
|