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
|
/*
* Copyright 1997 Sun Microsystems, Inc. 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. Sun designates this
* particular file as subject to the "Classpath" exception as provided
* by Sun in the LICENSE file that accompanied this code.
*
* 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 Sun Microsystems, Inc., 4150 Network Circle, Santa Clara,
* CA 95054 USA or visit www.sun.com if you need additional information or
* have any questions.
*/
package sun.io;
public abstract class CharToByteDBCS_ASCII extends CharToByteConverter
{
private char highHalfZoneCode;
private byte[] outputByte = new byte[2];
protected short index1[];
protected String index2;
protected String index2a;
protected int mask1;
protected int mask2;
protected int shift;
/**
* flush out any residual data and reset the buffer state
*/
public int flush(byte [] output, int outStart, int outEnd)
throws MalformedInputException, ConversionBufferFullException
{
if (highHalfZoneCode != 0) {
reset();
badInputLength = 0;
throw new MalformedInputException();
}
reset();
return 0;
}
/**
* Character conversion
*/
public int convert(char[] input, int inOff, int inEnd,
byte[] output, int outOff, int outEnd)
throws UnknownCharacterException, MalformedInputException,
ConversionBufferFullException
{
char inputChar;
int inputSize;
byteOff = outOff;
charOff = inOff;
while(charOff < inEnd) {
int index;
int theBytes;
int spaceNeeded;
if (highHalfZoneCode == 0) {
inputChar = input[charOff];
inputSize = 1;
} else {
inputChar = highHalfZoneCode;
inputSize = 0;
highHalfZoneCode = 0;
}
// Is this a high surrogate?
if(inputChar >= '\ud800' && inputChar <= '\udbff') {
// Is this the last character of the input?
if (charOff + inputSize >= inEnd) {
highHalfZoneCode = inputChar;
charOff += inputSize;
break;
}
// Is there a low surrogate following?
inputChar = input[charOff + inputSize];
if (inputChar >= '\udc00' && inputChar <= '\udfff') {
// We have a valid surrogate pair. Too bad we don't do
// surrogates. Is substitution enabled?
if (subMode) {
if (subBytes.length == 1) {
outputByte[0] = 0x00;
outputByte[1] = subBytes[0];
}
else {
outputByte[0] = subBytes[0];
outputByte[1] = subBytes[1];
}
inputSize++;
} else {
badInputLength = 2;
throw new UnknownCharacterException();
}
} else {
// We have a malformed surrogate pair
badInputLength = 1;
throw new MalformedInputException();
}
}
// Is this an unaccompanied low surrogate?
else
if (inputChar >= '\uDC00' && inputChar <= '\uDFFF') {
badInputLength = 1;
throw new MalformedInputException();
} else {
// We have a valid character, get the bytes for it
index = index1[((inputChar & mask1) >> shift)] + (inputChar & mask2);
if (index < 15000)
theBytes = (int)(index2.charAt(index));
else
theBytes = (int)(index2a.charAt(index-15000));
outputByte[0] = (byte)((theBytes & 0x0000ff00)>>8);
outputByte[1] = (byte)(theBytes & 0x000000ff);
}
// if there was no mapping - look for substitution characters
if (outputByte[0] == 0x00 && outputByte[1] == 0x00
&& inputChar != '\u0000')
{
if (subMode) {
if (subBytes.length == 1) {
outputByte[0] = 0x00;
outputByte[1] = subBytes[0];
} else {
outputByte[0] = subBytes[0];
outputByte[1] = subBytes[1];
}
} else {
badInputLength = 1;
throw new UnknownCharacterException();
}
}
if (outputByte[0] == 0x00)
spaceNeeded = 1;
else
spaceNeeded = 2;
if (byteOff + spaceNeeded > outEnd)
throw new ConversionBufferFullException();
if (spaceNeeded == 1)
output[byteOff++] = outputByte[1];
else {
output[byteOff++] = outputByte[0];
output[byteOff++] = outputByte[1];
}
charOff += inputSize;
}
return byteOff - outOff;
}
/**
* Resets converter to its initial state.
*/
public void reset() {
charOff = byteOff = 0;
highHalfZoneCode = 0;
}
/**
* Returns the maximum number of bytes needed to convert a char.
*/
public int getMaxBytesPerChar() {
return 2;
}
/**
* Returns true if the given character can be converted to the
* target character encoding.
*/
public boolean canConvert(char ch) {
int index;
int theBytes;
index = index1[((ch & mask1) >> shift)] + (ch & mask2);
if (index < 15000)
theBytes = (int)(index2.charAt(index));
else
theBytes = (int)(index2a.charAt(index-15000));
if (theBytes != 0)
return (true);
// only return true if input char was unicode null - all others are
// undefined
return( ch == '\u0000');
}
}
|
