1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
|
/*
* Copyright (c) 2003, 2006, Oracle and/or its affiliates. All rights reserved.
* DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
*
* This code is free software; you can redistribute it and/or modify it
* under the terms of the GNU General Public License version 2 only, as
* published by the Free Software Foundation.
*
* This code is distributed in the hope that it will be useful, but WITHOUT
* ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
* FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
* version 2 for more details (a copy is included in the LICENSE file that
* accompanied this code).
*
* You should have received a copy of the GNU General Public License version
* 2 along with this work; if not, write to the Free Software Foundation,
* Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
*
* Please contact Oracle, 500 Oracle Parkway, Redwood Shores, CA 94065 USA
* or visit www.oracle.com if you need additional information or have any
* questions.
*/
/*
*/
import java.nio.ByteBuffer;
import java.nio.CharBuffer;
import java.nio.charset.Charset;
import java.nio.charset.CharsetDecoder;
import java.nio.charset.CoderResult;
/**
* An abstract base class for subclasses which decode
* IBM double byte ebcdic host encodings such as ibm code
* pages 933, 935, 937,... etc
*
*/
public abstract class DBCS_IBM_EBCDIC_Decoder extends CharsetDecoder
{
private DBCSDecoderMapping decoderMapping;
protected static final char REPLACE_CHAR='\uFFFD';
protected String singleByteToChar;
protected short index1[];
protected String index2;
protected int mask1;
protected int mask2;
protected int shift;
private static final int SBCS = 0;
private static final int DBCS = 1;
private static final int SO = 0x0e;
private static final int SI = 0x0f;
private int currentState;
protected DBCS_IBM_EBCDIC_Decoder(Charset cs) {
super(cs, 0.5f, 1.0f);
}
protected void implReset() {
currentState = SBCS;
}
private CoderResult decodeArrayLoop(ByteBuffer src, CharBuffer dst) {
byte[] sa = src.array();
int sp = src.arrayOffset() + src.position();
int sl = src.arrayOffset() + src.limit();
assert (sp <= sl);
sp = (sp <= sl ? sp : sl);
char[] da = dst.array();
int dp = dst.arrayOffset() + dst.position();
int dl = dst.arrayOffset() + dst.limit();
assert (dp <= dl);
dp = (dp <= dl ? dp : dl);
try {
while (sp < sl) {
int b1, b2;
b1 = sa[sp];
int inputSize = 1;
int v = 0;
char outputChar = REPLACE_CHAR;
if (b1 < 0)
b1 += 256;
if (b1 == SO) { // Shift out
// For SO characters - simply validate the state and if OK
// update the state and go to the next byte
if (currentState != SBCS)
return CoderResult.malformedForLength(1);
else
currentState = DBCS;
} else if (b1 == SI) {
// For SI characters - simply validate the state and if OK
// update the state and go to the next byte
if (currentState != DBCS) {
return CoderResult.malformedForLength(1);
} else {
currentState = SBCS;
}
} else {
if (currentState == SBCS) {
outputChar = singleByteToChar.charAt(b1);
} else {
if (sl - sp < 2)
return CoderResult.UNDERFLOW;
b2 = sa[sp + 1];
if (b2 < 0)
b2 += 256;
inputSize++;
// Check validity of dbcs ebcdic byte pair values
if ((b1 != 0x40 || b2 != 0x40) &&
(b2 < 0x41 || b2 > 0xfe)) {
return CoderResult.malformedForLength(2);
}
// Lookup in the two level index
v = b1 * 256 + b2;
outputChar = index2.charAt(index1[((v & mask1) >> shift)]
+ (v & mask2));
}
if (outputChar == '\uFFFD')
return CoderResult.unmappableForLength(inputSize);
if (dl - dp < 1)
return CoderResult.OVERFLOW;
da[dp++] = outputChar;
}
sp += inputSize;
}
return CoderResult.UNDERFLOW;
} finally {
src.position(sp - src.arrayOffset());
dst.position(dp - dst.arrayOffset());
}
}
private CoderResult decodeBufferLoop(ByteBuffer src, CharBuffer dst) {
int mark = src.position();
try {
while (src.hasRemaining()) {
int b1, b2;
int v = 0;
b1 = src.get();
int inputSize = 1;
char outputChar = REPLACE_CHAR;
if (b1 < 0)
b1 += 256;
if (b1 == SO) { // Shift out
// For SO characters - simply validate the state and if OK
// update the state and go to the next byte
if (currentState != SBCS)
return CoderResult.malformedForLength(1);
else
currentState = DBCS;
} else if (b1 == SI) {
// For SI characters - simply validate the state and if OK
// update the state and go to the next byte
if (currentState != DBCS) {
return CoderResult.malformedForLength(1);
} else {
currentState = SBCS;
}
} else {
if (currentState == SBCS) {
outputChar = singleByteToChar.charAt(b1);
} else {
if (src.remaining() < 1)
return CoderResult.UNDERFLOW;
b2 = src.get();
if (b2 < 0)
b2 += 256;
inputSize++;
// Check validity of dbcs ebcdic byte pair values
if ((b1 != 0x40 || b2 != 0x40) &&
(b2 < 0x41 || b2 > 0xfe)) {
return CoderResult.malformedForLength(2);
}
// Lookup in the two level index
v = b1 * 256 + b2;
outputChar = index2.charAt(index1[((v & mask1) >> shift)]
+ (v & mask2));
}
if (outputChar == REPLACE_CHAR)
return CoderResult.unmappableForLength(inputSize);
if (!dst.hasRemaining())
return CoderResult.OVERFLOW;
dst.put(outputChar);
}
mark += inputSize;
}
return CoderResult.UNDERFLOW;
} finally {
src.position(mark);
}
}
protected CoderResult decodeLoop(ByteBuffer src, CharBuffer dst) {
if (src.hasArray() && dst.hasArray())
return decodeArrayLoop(src, dst);
else
return decodeBufferLoop(src, dst);
}
}
|
