2
|
1 |
/*
|
5506
|
2 |
* Copyright (c) 2003, 2006, Oracle and/or its affiliates. All rights reserved.
|
2
|
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
|
5506
|
7 |
* published by the Free Software Foundation. Oracle designates this
|
2
|
8 |
* particular file as subject to the "Classpath" exception as provided
|
5506
|
9 |
* by Oracle in the LICENSE file that accompanied this code.
|
2
|
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 |
*
|
5506
|
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.
|
2
|
24 |
*/
|
|
25 |
|
|
26 |
/*
|
|
27 |
*/
|
|
28 |
|
|
29 |
package sun.nio.cs.ext;
|
|
30 |
|
|
31 |
import java.nio.ByteBuffer;
|
|
32 |
import java.nio.CharBuffer;
|
|
33 |
import java.nio.charset.Charset;
|
|
34 |
import java.nio.charset.CharsetEncoder;
|
|
35 |
import java.nio.charset.CoderResult;
|
|
36 |
import sun.nio.cs.Surrogate;
|
|
37 |
|
|
38 |
|
|
39 |
public abstract class SimpleEUCEncoder
|
|
40 |
extends CharsetEncoder
|
|
41 |
{
|
|
42 |
|
|
43 |
protected short index1[];
|
|
44 |
protected String index2;
|
|
45 |
protected String index2a;
|
|
46 |
protected String index2b;
|
|
47 |
protected String index2c;
|
|
48 |
protected int mask1;
|
|
49 |
protected int mask2;
|
|
50 |
protected int shift;
|
|
51 |
|
|
52 |
private byte[] outputByte = new byte[4];
|
|
53 |
private final Surrogate.Parser sgp = new Surrogate.Parser();
|
|
54 |
|
|
55 |
protected SimpleEUCEncoder(Charset cs)
|
|
56 |
{
|
|
57 |
super(cs, 3.0f, 4.0f);
|
|
58 |
}
|
|
59 |
|
|
60 |
/**
|
|
61 |
* Returns true if the given character can be converted to the
|
|
62 |
* target character encoding.
|
|
63 |
*/
|
|
64 |
|
|
65 |
public boolean canEncode(char ch) {
|
|
66 |
int index;
|
|
67 |
String theChars;
|
|
68 |
|
|
69 |
index = index1[((ch & mask1) >> shift)] + (ch & mask2);
|
|
70 |
|
|
71 |
if (index < 7500)
|
|
72 |
theChars = index2;
|
|
73 |
else
|
|
74 |
if (index < 15000) {
|
|
75 |
index = index - 7500;
|
|
76 |
theChars = index2a;
|
|
77 |
}
|
|
78 |
else
|
|
79 |
if (index < 22500){
|
|
80 |
index = index - 15000;
|
|
81 |
theChars = index2b;
|
|
82 |
}
|
|
83 |
else {
|
|
84 |
index = index - 22500;
|
|
85 |
theChars = index2c;
|
|
86 |
}
|
|
87 |
|
|
88 |
if (theChars.charAt(2*index) != '\u0000' ||
|
|
89 |
theChars.charAt(2*index + 1) != '\u0000')
|
|
90 |
return (true);
|
|
91 |
|
|
92 |
// only return true if input char was unicode null - all others are
|
|
93 |
// undefined
|
|
94 |
return( ch == '\u0000');
|
|
95 |
|
|
96 |
}
|
|
97 |
private CoderResult encodeArrayLoop(CharBuffer src, ByteBuffer dst) {
|
|
98 |
char[] sa = src.array();
|
|
99 |
int sp = src.arrayOffset() + src.position();
|
|
100 |
int sl = src.arrayOffset() + src.limit();
|
|
101 |
assert (sp <= sl);
|
|
102 |
sp = (sp <= sl ? sp : sl);
|
|
103 |
byte[] da = dst.array();
|
|
104 |
int dp = dst.arrayOffset() + dst.position();
|
|
105 |
int dl = dst.arrayOffset() + dst.limit();
|
|
106 |
assert (dp <= dl);
|
|
107 |
dp = (dp <= dl ? dp : dl);
|
|
108 |
|
|
109 |
int index;
|
|
110 |
int spaceNeeded;
|
|
111 |
int i;
|
|
112 |
|
|
113 |
try {
|
|
114 |
while (sp < sl) {
|
|
115 |
boolean allZeroes = true;
|
|
116 |
char inputChar = sa[sp];
|
3714
|
117 |
if (Character.isSurrogate(inputChar)) {
|
2
|
118 |
if (sgp.parse(inputChar, sa, sp, sl) < 0)
|
|
119 |
return sgp.error();
|
|
120 |
return sgp.unmappableResult();
|
|
121 |
}
|
|
122 |
|
|
123 |
if (inputChar >= '\uFFFE')
|
|
124 |
return CoderResult.unmappableForLength(1);
|
|
125 |
|
|
126 |
String theChars;
|
|
127 |
char aChar;
|
|
128 |
|
|
129 |
// We have a valid character, get the bytes for it
|
|
130 |
index = index1[((inputChar & mask1) >> shift)] + (inputChar & mask2);
|
|
131 |
|
|
132 |
if (index < 7500)
|
|
133 |
theChars = index2;
|
|
134 |
else if (index < 15000) {
|
|
135 |
index = index - 7500;
|
|
136 |
theChars = index2a;
|
|
137 |
} else if (index < 22500){
|
|
138 |
index = index - 15000;
|
|
139 |
theChars = index2b;
|
|
140 |
}
|
|
141 |
else {
|
|
142 |
index = index - 22500;
|
|
143 |
theChars = index2c;
|
|
144 |
}
|
|
145 |
|
|
146 |
aChar = theChars.charAt(2*index);
|
|
147 |
outputByte[0] = (byte)((aChar & 0xff00)>>8);
|
|
148 |
outputByte[1] = (byte)(aChar & 0x00ff);
|
|
149 |
aChar = theChars.charAt(2*index + 1);
|
|
150 |
outputByte[2] = (byte)((aChar & 0xff00)>>8);
|
|
151 |
outputByte[3] = (byte)(aChar & 0x00ff);
|
|
152 |
|
|
153 |
for (i = 0; i < outputByte.length; i++) {
|
|
154 |
if (outputByte[i] != 0x00) {
|
|
155 |
allZeroes = false;
|
|
156 |
break;
|
|
157 |
}
|
|
158 |
}
|
|
159 |
|
|
160 |
if (allZeroes && inputChar != '\u0000') {
|
|
161 |
return CoderResult.unmappableForLength(1);
|
|
162 |
}
|
|
163 |
|
|
164 |
int oindex = 0;
|
|
165 |
|
|
166 |
for (spaceNeeded = outputByte.length;
|
|
167 |
spaceNeeded > 1; spaceNeeded--){
|
|
168 |
if (outputByte[oindex++] != 0x00 )
|
|
169 |
break;
|
|
170 |
}
|
|
171 |
|
|
172 |
if (dp + spaceNeeded > dl)
|
|
173 |
return CoderResult.OVERFLOW;
|
|
174 |
|
|
175 |
for (i = outputByte.length - spaceNeeded;
|
|
176 |
i < outputByte.length; i++) {
|
|
177 |
da[dp++] = outputByte[i];
|
|
178 |
}
|
|
179 |
sp++;
|
|
180 |
}
|
|
181 |
return CoderResult.UNDERFLOW;
|
|
182 |
} finally {
|
|
183 |
src.position(sp - src.arrayOffset());
|
|
184 |
dst.position(dp - dst.arrayOffset());
|
|
185 |
}
|
|
186 |
}
|
|
187 |
|
|
188 |
private CoderResult encodeBufferLoop(CharBuffer src, ByteBuffer dst) {
|
|
189 |
int index;
|
|
190 |
int spaceNeeded;
|
|
191 |
int i;
|
|
192 |
int mark = src.position();
|
|
193 |
try {
|
|
194 |
while (src.hasRemaining()) {
|
|
195 |
char inputChar = src.get();
|
|
196 |
boolean allZeroes = true;
|
3714
|
197 |
if (Character.isSurrogate(inputChar)) {
|
2
|
198 |
if (sgp.parse(inputChar, src) < 0)
|
|
199 |
return sgp.error();
|
|
200 |
return sgp.unmappableResult();
|
|
201 |
}
|
|
202 |
|
|
203 |
if (inputChar >= '\uFFFE')
|
|
204 |
return CoderResult.unmappableForLength(1);
|
|
205 |
|
|
206 |
String theChars;
|
|
207 |
char aChar;
|
|
208 |
|
|
209 |
// We have a valid character, get the bytes for it
|
|
210 |
index = index1[((inputChar & mask1) >> shift)] + (inputChar & mask2);
|
|
211 |
|
|
212 |
if (index < 7500)
|
|
213 |
theChars = index2;
|
|
214 |
else if (index < 15000) {
|
|
215 |
index = index - 7500;
|
|
216 |
theChars = index2a;
|
|
217 |
} else if (index < 22500){
|
|
218 |
index = index - 15000;
|
|
219 |
theChars = index2b;
|
|
220 |
}
|
|
221 |
else {
|
|
222 |
index = index - 22500;
|
|
223 |
theChars = index2c;
|
|
224 |
}
|
|
225 |
|
|
226 |
aChar = theChars.charAt(2*index);
|
|
227 |
outputByte[0] = (byte)((aChar & 0xff00)>>8);
|
|
228 |
outputByte[1] = (byte)(aChar & 0x00ff);
|
|
229 |
aChar = theChars.charAt(2*index + 1);
|
|
230 |
outputByte[2] = (byte)((aChar & 0xff00)>>8);
|
|
231 |
outputByte[3] = (byte)(aChar & 0x00ff);
|
|
232 |
|
|
233 |
for (i = 0; i < outputByte.length; i++) {
|
|
234 |
if (outputByte[i] != 0x00) {
|
|
235 |
allZeroes = false;
|
|
236 |
break;
|
|
237 |
}
|
|
238 |
}
|
|
239 |
if (allZeroes && inputChar != '\u0000') {
|
|
240 |
return CoderResult.unmappableForLength(1);
|
|
241 |
}
|
|
242 |
|
|
243 |
int oindex = 0;
|
|
244 |
|
|
245 |
for (spaceNeeded = outputByte.length;
|
|
246 |
spaceNeeded > 1; spaceNeeded--){
|
|
247 |
if (outputByte[oindex++] != 0x00 )
|
|
248 |
break;
|
|
249 |
}
|
|
250 |
if (dst.remaining() < spaceNeeded)
|
|
251 |
return CoderResult.OVERFLOW;
|
|
252 |
|
|
253 |
for (i = outputByte.length - spaceNeeded;
|
|
254 |
i < outputByte.length; i++) {
|
|
255 |
dst.put(outputByte[i]);
|
|
256 |
}
|
|
257 |
mark++;
|
|
258 |
}
|
|
259 |
return CoderResult.UNDERFLOW;
|
|
260 |
} finally {
|
|
261 |
src.position(mark);
|
|
262 |
}
|
|
263 |
}
|
|
264 |
|
|
265 |
protected CoderResult encodeLoop(CharBuffer src, ByteBuffer dst) {
|
|
266 |
if (true && src.hasArray() && dst.hasArray())
|
|
267 |
return encodeArrayLoop(src, dst);
|
|
268 |
else
|
|
269 |
return encodeBufferLoop(src, dst);
|
|
270 |
}
|
|
271 |
|
|
272 |
public byte encode(char inputChar) {
|
|
273 |
return (byte)index2.charAt(index1[(inputChar & mask1) >> shift] +
|
|
274 |
(inputChar & mask2));
|
|
275 |
}
|
|
276 |
}
|