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
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
|
/*
* Copyright (c) 2002, 2012, 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.CharsetEncoder;
import java.nio.charset.CoderResult;
import sun.nio.cs.Surrogate;
public abstract class DoubleByteEncoder
extends CharsetEncoder
{
private short index1[];
private String index2[];
private final Surrogate.Parser sgp = new Surrogate.Parser();
protected DoubleByteEncoder(Charset cs,
short[] index1, String[] index2)
{
super(cs, 2.0f, 2.0f);
this.index1 = index1;
this.index2 = index2;
}
protected DoubleByteEncoder(Charset cs,
short[] index1, String[] index2,
float avg, float max)
{
super(cs, avg, max);
this.index1 = index1;
this.index2 = index2;
}
protected DoubleByteEncoder(Charset cs,
short[] index1, String[] index2, byte[] repl)
{
super(cs, 2.0f, 2.0f, repl);
this.index1 = index1;
this.index2 = index2;
}
protected DoubleByteEncoder(Charset cs,
short[] index1, String[] index2,
byte[] repl, float avg, float max)
{
super(cs, avg, max,repl);
this.index1 = index1;
this.index2 = index2;
}
public boolean canEncode(char c) {
return (encodeSingle(c) != -1 ||
encodeDouble(c) != 0);
}
private CoderResult encodeArrayLoop(CharBuffer src, ByteBuffer dst) {
char[] sa = src.array();
int sp = src.arrayOffset() + src.position();
int sl = src.arrayOffset() + src.limit();
byte[] da = dst.array();
int dp = dst.arrayOffset() + dst.position();
int dl = dst.arrayOffset() + dst.limit();
try {
while (sp < sl) {
char c = sa[sp];
if (Character.isSurrogate(c)) {
if (sgp.parse(c, sa, sp, sl) < 0)
return sgp.error();
if (sl - sp < 2)
return CoderResult.UNDERFLOW;
char c2 = sa[sp + 1];
byte[] outputBytes = new byte[2];
outputBytes = encodeSurrogate(c, c2);
if (outputBytes == null) {
return sgp.unmappableResult();
}
else {
if (dl - dp < 2)
return CoderResult.OVERFLOW;
da[dp++] = outputBytes[0];
da[dp++] = outputBytes[1];
sp += 2;
continue;
}
}
if (c >= '\uFFFE')
return CoderResult.unmappableForLength(1);
int b = encodeSingle(c);
if (b != -1) { // Single Byte
if (dl - dp < 1)
return CoderResult.OVERFLOW;
da[dp++] = (byte)b;
sp++;
continue;
}
int ncode = encodeDouble(c);
if (ncode != 0 && c != '\u0000' ) {
if (dl - dp < 2)
return CoderResult.OVERFLOW;
da[dp++] = (byte) ((ncode & 0xff00) >> 8);
da[dp++] = (byte) (ncode & 0xff);
sp++;
continue;
}
return CoderResult.unmappableForLength(1);
}
return CoderResult.UNDERFLOW;
} finally {
src.position(sp - src.arrayOffset());
dst.position(dp - dst.arrayOffset());
}
}
private CoderResult encodeBufferLoop(CharBuffer src, ByteBuffer dst) {
int mark = src.position();
try {
while (src.hasRemaining()) {
char c = src.get();
if (Character.isSurrogate(c)) {
int surr;
if ((surr = sgp.parse(c, src)) < 0)
return sgp.error();
char c2 = Surrogate.low(surr);
byte[] outputBytes = new byte[2];
outputBytes = encodeSurrogate(c, c2);
if (outputBytes == null) {
return sgp.unmappableResult();
} else {
if (dst.remaining() < 2)
return CoderResult.OVERFLOW;
mark += 2;
dst.put(outputBytes[0]);
dst.put(outputBytes[1]);
continue;
}
}
if (c >= '\uFFFE')
return CoderResult.unmappableForLength(1);
int b = encodeSingle(c);
if (b != -1) { // Single-byte character
if (dst.remaining() < 1)
return CoderResult.OVERFLOW;
mark++;
dst.put((byte)b);
continue;
}
// Double Byte character
int ncode = encodeDouble(c);
if (ncode != 0 && c != '\u0000') {
if (dst.remaining() < 2)
return CoderResult.OVERFLOW;
mark++;
dst.put((byte) ((ncode & 0xff00) >> 8));
dst.put((byte) ncode);
continue;
}
return CoderResult.unmappableForLength(1);
}
return CoderResult.UNDERFLOW;
} finally {
src.position(mark);
}
}
protected CoderResult encodeLoop(CharBuffer src, ByteBuffer dst) {
if (true && src.hasArray() && dst.hasArray())
return encodeArrayLoop(src, dst);
else
return encodeBufferLoop(src, dst);
}
/*
* Can be changed by subclass
*/
protected int encodeDouble(char ch) {
int offset = index1[((ch & 0xff00) >> 8 )] << 8;
return index2[offset >> 12].charAt((offset & 0xfff) + (ch & 0xff));
}
/*
* Can be changed by subclass
*/
protected int encodeSingle(char inputChar) {
if (inputChar < 0x80)
return (byte)inputChar;
else
return -1;
}
/**
* Protected method which should be overridden by concrete DBCS
* CharsetEncoder classes which included supplementary characters
* within their mapping coverage.
* null return value indicates surrogate values could not be
* handled or encoded.
*/
protected byte[] encodeSurrogate(char highSurrogate, char lowSurrogate) {
return null;
}
}
|
