1 /* |
|
2 * Copyright (c) 2002, 2012, 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.nio.cs.ext; |
|
27 |
|
28 import java.nio.ByteBuffer; |
|
29 import java.nio.CharBuffer; |
|
30 import java.nio.charset.Charset; |
|
31 import java.nio.charset.CharsetDecoder; |
|
32 import java.nio.charset.CharsetEncoder; |
|
33 import java.nio.charset.CoderResult; |
|
34 import sun.nio.cs.HistoricallyNamedCharset; |
|
35 import sun.nio.cs.Surrogate; |
|
36 import sun.nio.cs.SingleByte; |
|
37 import static sun.nio.cs.CharsetMapping.*; |
|
38 |
|
39 public class EUC_JP |
|
40 extends Charset |
|
41 implements HistoricallyNamedCharset |
|
42 { |
|
43 public EUC_JP() { |
|
44 super("EUC-JP", ExtendedCharsets.aliasesFor("EUC-JP")); |
|
45 } |
|
46 |
|
47 public String historicalName() { |
|
48 return "EUC_JP"; |
|
49 } |
|
50 |
|
51 public boolean contains(Charset cs) { |
|
52 return ((cs.name().equals("US-ASCII")) |
|
53 || (cs instanceof JIS_X_0201) |
|
54 || (cs instanceof JIS_X_0208) |
|
55 || (cs instanceof JIS_X_0212) |
|
56 || (cs instanceof EUC_JP)); |
|
57 } |
|
58 |
|
59 public CharsetDecoder newDecoder() { |
|
60 return new Decoder(this); |
|
61 } |
|
62 |
|
63 public CharsetEncoder newEncoder() { |
|
64 return new Encoder(this); |
|
65 } |
|
66 |
|
67 static class Decoder extends CharsetDecoder |
|
68 implements DelegatableDecoder { |
|
69 |
|
70 final static SingleByte.Decoder DEC0201 = |
|
71 (SingleByte.Decoder)new JIS_X_0201().newDecoder(); |
|
72 |
|
73 final static DoubleByte.Decoder DEC0208 = |
|
74 (DoubleByte.Decoder)new JIS_X_0208().newDecoder(); |
|
75 |
|
76 final static DoubleByte.Decoder DEC0212 = |
|
77 (DoubleByte.Decoder)new JIS_X_0212().newDecoder(); |
|
78 |
|
79 private final SingleByte.Decoder dec0201; |
|
80 private final DoubleByte.Decoder dec0208; |
|
81 private final DoubleByte.Decoder dec0212; |
|
82 |
|
83 protected Decoder(Charset cs) { |
|
84 this(cs, 0.5f, 1.0f, DEC0201, DEC0208, DEC0212); |
|
85 } |
|
86 |
|
87 protected Decoder(Charset cs, float avgCpb, float maxCpb, |
|
88 SingleByte.Decoder dec0201, |
|
89 DoubleByte.Decoder dec0208, |
|
90 DoubleByte.Decoder dec0212) { |
|
91 super(cs, avgCpb, maxCpb); |
|
92 this.dec0201 = dec0201; |
|
93 this.dec0208 = dec0208; |
|
94 this.dec0212 = dec0212; |
|
95 } |
|
96 |
|
97 |
|
98 protected char decodeDouble(int byte1, int byte2) { |
|
99 if (byte1 == 0x8e) { |
|
100 if (byte2 < 0x80) |
|
101 return UNMAPPABLE_DECODING; |
|
102 return dec0201.decode((byte)byte2); |
|
103 } |
|
104 return dec0208.decodeDouble(byte1 - 0x80, byte2 - 0x80); |
|
105 } |
|
106 |
|
107 private CoderResult decodeArrayLoop(ByteBuffer src, |
|
108 CharBuffer dst) |
|
109 { |
|
110 byte[] sa = src.array(); |
|
111 int sp = src.arrayOffset() + src.position(); |
|
112 int sl = src.arrayOffset() + src.limit(); |
|
113 assert (sp <= sl); |
|
114 sp = (sp <= sl ? sp : sl); |
|
115 |
|
116 char[] da = dst.array(); |
|
117 int dp = dst.arrayOffset() + dst.position(); |
|
118 int dl = dst.arrayOffset() + dst.limit(); |
|
119 assert (dp <= dl); |
|
120 dp = (dp <= dl ? dp : dl); |
|
121 |
|
122 int b1 = 0, b2 = 0; |
|
123 int inputSize = 0; |
|
124 char outputChar = UNMAPPABLE_DECODING; |
|
125 try { |
|
126 while (sp < sl) { |
|
127 b1 = sa[sp] & 0xff; |
|
128 inputSize = 1; |
|
129 |
|
130 if ((b1 & 0x80) == 0) { |
|
131 outputChar = (char)b1; |
|
132 } else { // Multibyte char |
|
133 if (b1 == 0x8f) { // JIS0212 |
|
134 if (sp + 3 > sl) |
|
135 return CoderResult.UNDERFLOW; |
|
136 b1 = sa[sp + 1] & 0xff; |
|
137 b2 = sa[sp + 2] & 0xff; |
|
138 inputSize += 2; |
|
139 if (dec0212 == null) // JIS02012 not supported |
|
140 return CoderResult.unmappableForLength(inputSize); |
|
141 outputChar = dec0212.decodeDouble(b1-0x80, b2-0x80); |
|
142 } else { // JIS0201, JIS0208 |
|
143 if (sp + 2 > sl) |
|
144 return CoderResult.UNDERFLOW; |
|
145 b2 = sa[sp + 1] & 0xff; |
|
146 inputSize++; |
|
147 outputChar = decodeDouble(b1, b2); |
|
148 } |
|
149 } |
|
150 if (outputChar == UNMAPPABLE_DECODING) { // can't be decoded |
|
151 return CoderResult.unmappableForLength(inputSize); |
|
152 } |
|
153 if (dp + 1 > dl) |
|
154 return CoderResult.OVERFLOW; |
|
155 da[dp++] = outputChar; |
|
156 sp += inputSize; |
|
157 } |
|
158 return CoderResult.UNDERFLOW; |
|
159 } finally { |
|
160 src.position(sp - src.arrayOffset()); |
|
161 dst.position(dp - dst.arrayOffset()); |
|
162 } |
|
163 } |
|
164 |
|
165 private CoderResult decodeBufferLoop(ByteBuffer src, |
|
166 CharBuffer dst) |
|
167 { |
|
168 int mark = src.position(); |
|
169 int b1 = 0, b2 = 0; |
|
170 int inputSize = 0; |
|
171 char outputChar = UNMAPPABLE_DECODING; |
|
172 |
|
173 try { |
|
174 while (src.hasRemaining()) { |
|
175 b1 = src.get() & 0xff; |
|
176 inputSize = 1; |
|
177 if ((b1 & 0x80) == 0) { |
|
178 outputChar = (char)b1; |
|
179 } else { // Multibyte char |
|
180 if (b1 == 0x8f) { // JIS0212 |
|
181 if (src.remaining() < 2) |
|
182 return CoderResult.UNDERFLOW; |
|
183 b1 = src.get() & 0xff; |
|
184 b2 = src.get() & 0xff; |
|
185 inputSize += 2; |
|
186 if (dec0212 == null) // JIS02012 not supported |
|
187 return CoderResult.unmappableForLength(inputSize); |
|
188 outputChar = dec0212.decodeDouble(b1-0x80, b2-0x80); |
|
189 } else { // JIS0201 JIS0208 |
|
190 if (src.remaining() < 1) |
|
191 return CoderResult.UNDERFLOW; |
|
192 b2 = src.get() & 0xff; |
|
193 inputSize++; |
|
194 outputChar = decodeDouble(b1, b2); |
|
195 } |
|
196 } |
|
197 if (outputChar == UNMAPPABLE_DECODING) { |
|
198 return CoderResult.unmappableForLength(inputSize); |
|
199 } |
|
200 if (dst.remaining() < 1) |
|
201 return CoderResult.OVERFLOW; |
|
202 dst.put(outputChar); |
|
203 mark += inputSize; |
|
204 } |
|
205 return CoderResult.UNDERFLOW; |
|
206 } finally { |
|
207 src.position(mark); |
|
208 } |
|
209 } |
|
210 |
|
211 // Make some protected methods public for use by JISAutoDetect |
|
212 public CoderResult decodeLoop(ByteBuffer src, CharBuffer dst) { |
|
213 if (src.hasArray() && dst.hasArray()) |
|
214 return decodeArrayLoop(src, dst); |
|
215 else |
|
216 return decodeBufferLoop(src, dst); |
|
217 } |
|
218 public void implReset() { |
|
219 super.implReset(); |
|
220 } |
|
221 public CoderResult implFlush(CharBuffer out) { |
|
222 return super.implFlush(out); |
|
223 } |
|
224 } |
|
225 |
|
226 |
|
227 static class Encoder extends CharsetEncoder { |
|
228 |
|
229 final static SingleByte.Encoder ENC0201 = |
|
230 (SingleByte.Encoder)new JIS_X_0201().newEncoder(); |
|
231 |
|
232 final static DoubleByte.Encoder ENC0208 = |
|
233 (DoubleByte.Encoder)new JIS_X_0208().newEncoder(); |
|
234 |
|
235 final static DoubleByte.Encoder ENC0212 = |
|
236 (DoubleByte.Encoder)new JIS_X_0212().newEncoder(); |
|
237 |
|
238 private final Surrogate.Parser sgp = new Surrogate.Parser(); |
|
239 |
|
240 |
|
241 private final SingleByte.Encoder enc0201; |
|
242 private final DoubleByte.Encoder enc0208; |
|
243 private final DoubleByte.Encoder enc0212; |
|
244 |
|
245 protected Encoder(Charset cs) { |
|
246 this(cs, 3.0f, 3.0f, ENC0201, ENC0208, ENC0212); |
|
247 } |
|
248 |
|
249 protected Encoder(Charset cs, float avgBpc, float maxBpc, |
|
250 SingleByte.Encoder enc0201, |
|
251 DoubleByte.Encoder enc0208, |
|
252 DoubleByte.Encoder enc0212) { |
|
253 super(cs, avgBpc, maxBpc); |
|
254 this.enc0201 = enc0201; |
|
255 this.enc0208 = enc0208; |
|
256 this.enc0212 = enc0212; |
|
257 } |
|
258 |
|
259 public boolean canEncode(char c) { |
|
260 byte[] encodedBytes = new byte[3]; |
|
261 return encodeSingle(c, encodedBytes) != 0 || |
|
262 encodeDouble(c) != UNMAPPABLE_ENCODING; |
|
263 } |
|
264 |
|
265 protected int encodeSingle(char inputChar, byte[] outputByte) { |
|
266 int b = enc0201.encode(inputChar); |
|
267 if (b == UNMAPPABLE_ENCODING) |
|
268 return 0; |
|
269 if (b >= 0 && b < 128) { |
|
270 outputByte[0] = (byte)b; |
|
271 return 1; |
|
272 } |
|
273 outputByte[0] = (byte)0x8e; |
|
274 outputByte[1] = (byte)b; |
|
275 return 2; |
|
276 } |
|
277 |
|
278 protected int encodeDouble(char ch) { |
|
279 int b = enc0208.encodeChar(ch); |
|
280 if (b != UNMAPPABLE_ENCODING) |
|
281 return b + 0x8080; |
|
282 if (enc0212 != null) { |
|
283 b = enc0212.encodeChar(ch); |
|
284 if (b != UNMAPPABLE_ENCODING) |
|
285 b += 0x8F8080; |
|
286 } |
|
287 return b; |
|
288 } |
|
289 |
|
290 private CoderResult encodeArrayLoop(CharBuffer src, |
|
291 ByteBuffer dst) |
|
292 { |
|
293 char[] sa = src.array(); |
|
294 int sp = src.arrayOffset() + src.position(); |
|
295 int sl = src.arrayOffset() + src.limit(); |
|
296 assert (sp <= sl); |
|
297 sp = (sp <= sl ? sp : sl); |
|
298 byte[] da = dst.array(); |
|
299 int dp = dst.arrayOffset() + dst.position(); |
|
300 int dl = dst.arrayOffset() + dst.limit(); |
|
301 assert (dp <= dl); |
|
302 dp = (dp <= dl ? dp : dl); |
|
303 |
|
304 int outputSize = 0; |
|
305 byte[] outputByte; |
|
306 int inputSize = 0; // Size of input |
|
307 byte[] tmpBuf = new byte[3]; |
|
308 |
|
309 try { |
|
310 while (sp < sl) { |
|
311 outputByte = tmpBuf; |
|
312 char c = sa[sp]; |
|
313 if (Character.isSurrogate(c)) { |
|
314 if (sgp.parse(c, sa, sp, sl) < 0) |
|
315 return sgp.error(); |
|
316 return sgp.unmappableResult(); |
|
317 } |
|
318 outputSize = encodeSingle(c, outputByte); |
|
319 if (outputSize == 0) { // DoubleByte |
|
320 int ncode = encodeDouble(c); |
|
321 if (ncode != UNMAPPABLE_ENCODING) { |
|
322 if ((ncode & 0xFF0000) == 0) { |
|
323 outputByte[0] = (byte) ((ncode & 0xff00) >> 8); |
|
324 outputByte[1] = (byte) (ncode & 0xff); |
|
325 outputSize = 2; |
|
326 } else { |
|
327 outputByte[0] = (byte) 0x8f; |
|
328 outputByte[1] = (byte) ((ncode & 0xff00) >> 8); |
|
329 outputByte[2] = (byte) (ncode & 0xff); |
|
330 outputSize = 3; |
|
331 } |
|
332 } else { |
|
333 return CoderResult.unmappableForLength(1); |
|
334 } |
|
335 } |
|
336 if (dl - dp < outputSize) |
|
337 return CoderResult.OVERFLOW; |
|
338 // Put the byte in the output buffer |
|
339 for (int i = 0; i < outputSize; i++) { |
|
340 da[dp++] = outputByte[i]; |
|
341 } |
|
342 sp++; |
|
343 } |
|
344 return CoderResult.UNDERFLOW; |
|
345 } finally { |
|
346 src.position(sp - src.arrayOffset()); |
|
347 dst.position(dp - dst.arrayOffset()); |
|
348 } |
|
349 } |
|
350 |
|
351 private CoderResult encodeBufferLoop(CharBuffer src, |
|
352 ByteBuffer dst) |
|
353 { |
|
354 int outputSize = 0; |
|
355 byte[] outputByte; |
|
356 int inputSize = 0; // Size of input |
|
357 byte[] tmpBuf = new byte[3]; |
|
358 |
|
359 int mark = src.position(); |
|
360 |
|
361 try { |
|
362 while (src.hasRemaining()) { |
|
363 outputByte = tmpBuf; |
|
364 char c = src.get(); |
|
365 if (Character.isSurrogate(c)) { |
|
366 if (sgp.parse(c, src) < 0) |
|
367 return sgp.error(); |
|
368 return sgp.unmappableResult(); |
|
369 } |
|
370 outputSize = encodeSingle(c, outputByte); |
|
371 if (outputSize == 0) { // DoubleByte |
|
372 int ncode = encodeDouble(c); |
|
373 if (ncode != UNMAPPABLE_ENCODING) { |
|
374 if ((ncode & 0xFF0000) == 0) { |
|
375 outputByte[0] = (byte) ((ncode & 0xff00) >> 8); |
|
376 outputByte[1] = (byte) (ncode & 0xff); |
|
377 outputSize = 2; |
|
378 } else { |
|
379 outputByte[0] = (byte) 0x8f; |
|
380 outputByte[1] = (byte) ((ncode & 0xff00) >> 8); |
|
381 outputByte[2] = (byte) (ncode & 0xff); |
|
382 outputSize = 3; |
|
383 } |
|
384 } else { |
|
385 return CoderResult.unmappableForLength(1); |
|
386 } |
|
387 } |
|
388 if (dst.remaining() < outputSize) |
|
389 return CoderResult.OVERFLOW; |
|
390 // Put the byte in the output buffer |
|
391 for (int i = 0; i < outputSize; i++) { |
|
392 dst.put(outputByte[i]); |
|
393 } |
|
394 mark++; |
|
395 } |
|
396 return CoderResult.UNDERFLOW; |
|
397 } finally { |
|
398 src.position(mark); |
|
399 } |
|
400 } |
|
401 |
|
402 protected CoderResult encodeLoop(CharBuffer src, |
|
403 ByteBuffer dst) |
|
404 { |
|
405 if (src.hasArray() && dst.hasArray()) |
|
406 return encodeArrayLoop(src, dst); |
|
407 else |
|
408 return encodeBufferLoop(src, dst); |
|
409 } |
|
410 } |
|
411 } |
|