|
1 /* |
|
2 * Copyright (c) 2002, 2011, 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 /* |
|
27 */ |
|
28 |
|
29 |
|
30 package sun.nio.cs.ext; |
|
31 |
|
32 import java.nio.charset.Charset; |
|
33 import java.nio.CharBuffer; |
|
34 import java.nio.ByteBuffer; |
|
35 import java.nio.charset.CharsetDecoder; |
|
36 import java.nio.charset.CharsetEncoder; |
|
37 import java.nio.charset.CoderResult; |
|
38 import sun.nio.cs.Surrogate; |
|
39 import sun.nio.cs.HistoricallyNamedCharset; |
|
40 |
|
41 public class ISCII91 extends Charset implements HistoricallyNamedCharset |
|
42 { |
|
43 private static final char NUKTA_CHAR = '\u093c'; |
|
44 private static final char HALANT_CHAR = '\u094d'; |
|
45 private static final byte NO_CHAR = (byte)255; |
|
46 |
|
47 public ISCII91() { |
|
48 super("x-ISCII91", ExtendedCharsets.aliasesFor("x-ISCII91")); |
|
49 } |
|
50 |
|
51 public String historicalName() { |
|
52 return "ISCII91"; |
|
53 } |
|
54 |
|
55 public boolean contains(Charset cs) { |
|
56 return ((cs.name().equals("US-ASCII")) |
|
57 || (cs instanceof ISCII91)); |
|
58 } |
|
59 |
|
60 public CharsetDecoder newDecoder() { |
|
61 return new Decoder(this); |
|
62 } |
|
63 |
|
64 public CharsetEncoder newEncoder() { |
|
65 return new Encoder(this); |
|
66 } |
|
67 |
|
68 private static final char[] directMapTable = { |
|
69 '\u0000', // ascii character |
|
70 '\u0001', // ascii character |
|
71 '\u0002', // ascii character |
|
72 '\u0003', // ascii character |
|
73 '\u0004', // ascii character |
|
74 '\u0005', // ascii character |
|
75 '\u0006', // ascii character |
|
76 '\u0007', // ascii character |
|
77 '\u0008', // ascii character |
|
78 '\u0009', // ascii character |
|
79 '\012', // ascii character |
|
80 '\u000b', // ascii character |
|
81 '\u000c', // ascii character |
|
82 '\015', // ascii character |
|
83 '\u000e', // ascii character |
|
84 '\u000f', // ascii character |
|
85 '\u0010', // ascii character |
|
86 '\u0011', // ascii character |
|
87 '\u0012', // ascii character |
|
88 '\u0013', // ascii character |
|
89 '\u0014', // ascii character |
|
90 '\u0015', // ascii character |
|
91 '\u0016', // ascii character |
|
92 '\u0017', // ascii character |
|
93 '\u0018', // ascii character |
|
94 '\u0019', // ascii character |
|
95 '\u001a', // ascii character |
|
96 '\u001b', // ascii character |
|
97 '\u001c', // ascii character |
|
98 '\u001d', // ascii character |
|
99 '\u001e', // ascii character |
|
100 '\u001f', // ascii character |
|
101 '\u0020', // ascii character |
|
102 '\u0021', // ascii character |
|
103 '\u0022', // ascii character |
|
104 '\u0023', // ascii character |
|
105 '\u0024', // ascii character |
|
106 '\u0025', // ascii character |
|
107 '\u0026', // ascii character |
|
108 (char)0x0027, // '\u0027' control -- ascii character |
|
109 '\u0028', // ascii character |
|
110 '\u0029', // ascii character |
|
111 '\u002a', // ascii character |
|
112 '\u002b', // ascii character |
|
113 '\u002c', // ascii character |
|
114 '\u002d', // ascii character |
|
115 '\u002e', // ascii character |
|
116 '\u002f', // ascii character |
|
117 '\u0030', // ascii character |
|
118 '\u0031', // ascii character |
|
119 '\u0032', // ascii character |
|
120 '\u0033', // ascii character |
|
121 '\u0034', // ascii character |
|
122 '\u0035', // ascii character |
|
123 '\u0036', // ascii character |
|
124 '\u0037', // ascii character |
|
125 '\u0038', // ascii character |
|
126 '\u0039', // ascii character |
|
127 '\u003a', // ascii character |
|
128 '\u003b', // ascii character |
|
129 '\u003c', // ascii character |
|
130 '\u003d', // ascii character |
|
131 '\u003e', // ascii character |
|
132 '\u003f', // ascii character |
|
133 '\u0040', // ascii character |
|
134 '\u0041', // ascii character |
|
135 '\u0042', // ascii character |
|
136 '\u0043', // ascii character |
|
137 '\u0044', // ascii character |
|
138 '\u0045', // ascii character |
|
139 '\u0046', // ascii character |
|
140 '\u0047', // ascii character |
|
141 '\u0048', // ascii character |
|
142 '\u0049', // ascii character |
|
143 '\u004a', // ascii character |
|
144 '\u004b', // ascii character |
|
145 '\u004c', // ascii character |
|
146 '\u004d', // ascii character |
|
147 '\u004e', // ascii character |
|
148 '\u004f', // ascii character |
|
149 '\u0050', // ascii character |
|
150 '\u0051', // ascii character |
|
151 '\u0052', // ascii character |
|
152 '\u0053', // ascii character |
|
153 '\u0054', // ascii character |
|
154 '\u0055', // ascii character |
|
155 '\u0056', // ascii character |
|
156 '\u0057', // ascii character |
|
157 '\u0058', // ascii character |
|
158 '\u0059', // ascii character |
|
159 '\u005a', // ascii character |
|
160 '\u005b', // ascii character |
|
161 '\\',// '\u005c' -- ascii character |
|
162 '\u005d', // ascii character |
|
163 '\u005e', // ascii character |
|
164 '\u005f', // ascii character |
|
165 '\u0060', // ascii character |
|
166 '\u0061', // ascii character |
|
167 '\u0062', // ascii character |
|
168 '\u0063', // ascii character |
|
169 '\u0064', // ascii character |
|
170 '\u0065', // ascii character |
|
171 '\u0066', // ascii character |
|
172 '\u0067', // ascii character |
|
173 '\u0068', // ascii character |
|
174 '\u0069', // ascii character |
|
175 '\u006a', // ascii character |
|
176 '\u006b', // ascii character |
|
177 '\u006c', // ascii character |
|
178 '\u006d', // ascii character |
|
179 '\u006e', // ascii character |
|
180 '\u006f', // ascii character |
|
181 '\u0070', // ascii character |
|
182 '\u0071', // ascii character |
|
183 '\u0072', // ascii character |
|
184 '\u0073', // ascii character |
|
185 '\u0074', // ascii character |
|
186 '\u0075', // ascii character |
|
187 '\u0076', // ascii character |
|
188 '\u0077', // ascii character |
|
189 '\u0078', // ascii character |
|
190 '\u0079', // ascii character |
|
191 '\u007a', // ascii character |
|
192 '\u007b', // ascii character |
|
193 '\u007c', // ascii character |
|
194 '\u007d', // ascii character |
|
195 '\u007e', // ascii character |
|
196 '\u007f', // ascii character |
|
197 '\uffff', // unknown character |
|
198 '\uffff', // unknown character |
|
199 '\uffff', // unknown character |
|
200 '\uffff', // unknown character |
|
201 '\uffff', // unknown character |
|
202 '\uffff', // unknown character |
|
203 '\uffff', // unknown character |
|
204 '\uffff', // unknown character |
|
205 '\uffff', // unknown character |
|
206 '\uffff', // unknown character |
|
207 '\uffff', // unknown character |
|
208 '\uffff', // unknown character |
|
209 '\uffff', // unknown character |
|
210 '\uffff', // unknown character |
|
211 '\uffff', // unknown character |
|
212 '\uffff', // unknown character |
|
213 '\uffff', // unknown character |
|
214 '\uffff', // unknown character |
|
215 '\uffff', // unknown character |
|
216 '\uffff', // unknown character |
|
217 '\uffff', // unknown character |
|
218 '\uffff', // unknown character |
|
219 '\uffff', // unknown character |
|
220 '\uffff', // unknown character |
|
221 '\uffff', // unknown character |
|
222 '\uffff', // unknown character |
|
223 '\uffff', // unknown character |
|
224 '\uffff', // unknown character |
|
225 '\uffff', // unknown character |
|
226 '\uffff', // unknown character |
|
227 '\uffff', // unknown character |
|
228 '\uffff', // unknown character |
|
229 '\u0901', // a1 -- Vowel-modifier CHANDRABINDU |
|
230 '\u0902', // a2 -- Vowel-modifier ANUSWAR |
|
231 '\u0903', // a3 -- Vowel-modifier VISARG |
|
232 |
|
233 '\u0905', // a4 -- Vowel A |
|
234 '\u0906', // a5 -- Vowel AA |
|
235 '\u0907', // a6 -- Vowel I |
|
236 '\u0908', // a7 -- Vowel II |
|
237 '\u0909', // a8 -- Vowel U |
|
238 '\u090a', // a9 -- Vowel UU |
|
239 '\u090b', // aa -- Vowel RI |
|
240 '\u090e', // ab -- Vowel E ( Southern Scripts ) |
|
241 '\u090f', // ac -- Vowel EY |
|
242 '\u0910', // ad -- Vowel AI |
|
243 '\u090d', // ae -- Vowel AYE ( Devanagari Script ) |
|
244 '\u0912', // af -- Vowel O ( Southern Scripts ) |
|
245 '\u0913', // b0 -- Vowel OW |
|
246 '\u0914', // b1 -- Vowel AU |
|
247 '\u0911', // b2 -- Vowel AWE ( Devanagari Script ) |
|
248 '\u0915', // b3 -- Consonant KA |
|
249 '\u0916', // b4 -- Consonant KHA |
|
250 '\u0917', // b5 -- Consonant GA |
|
251 '\u0918', // b6 -- Consonant GHA |
|
252 '\u0919', // b7 -- Consonant NGA |
|
253 '\u091a', // b8 -- Consonant CHA |
|
254 '\u091b', // b9 -- Consonant CHHA |
|
255 '\u091c', // ba -- Consonant JA |
|
256 '\u091d', // bb -- Consonant JHA |
|
257 '\u091e', // bc -- Consonant JNA |
|
258 '\u091f', // bd -- Consonant Hard TA |
|
259 '\u0920', // be -- Consonant Hard THA |
|
260 '\u0921', // bf -- Consonant Hard DA |
|
261 '\u0922', // c0 -- Consonant Hard DHA |
|
262 '\u0923', // c1 -- Consonant Hard NA |
|
263 '\u0924', // c2 -- Consonant Soft TA |
|
264 '\u0925', // c3 -- Consonant Soft THA |
|
265 '\u0926', // c4 -- Consonant Soft DA |
|
266 '\u0927', // c5 -- Consonant Soft DHA |
|
267 '\u0928', // c6 -- Consonant Soft NA |
|
268 '\u0929', // c7 -- Consonant NA ( Tamil ) |
|
269 '\u092a', // c8 -- Consonant PA |
|
270 '\u092b', // c9 -- Consonant PHA |
|
271 '\u092c', // ca -- Consonant BA |
|
272 '\u092d', // cb -- Consonant BHA |
|
273 '\u092e', // cc -- Consonant MA |
|
274 '\u092f', // cd -- Consonant YA |
|
275 '\u095f', // ce -- Consonant JYA ( Bengali, Assamese & Oriya ) |
|
276 '\u0930', // cf -- Consonant RA |
|
277 '\u0931', // d0 -- Consonant Hard RA ( Southern Scripts ) |
|
278 '\u0932', // d1 -- Consonant LA |
|
279 '\u0933', // d2 -- Consonant Hard LA |
|
280 '\u0934', // d3 -- Consonant ZHA ( Tamil & Malayalam ) |
|
281 '\u0935', // d4 -- Consonant VA |
|
282 '\u0936', // d5 -- Consonant SHA |
|
283 '\u0937', // d6 -- Consonant Hard SHA |
|
284 '\u0938', // d7 -- Consonant SA |
|
285 '\u0939', // d8 -- Consonant HA |
|
286 |
|
287 '\u200d', // d9 -- Consonant INVISIBLE |
|
288 '\u093e', // da -- Vowel Sign AA |
|
289 |
|
290 '\u093f', // db -- Vowel Sign I |
|
291 '\u0940', // dc -- Vowel Sign II |
|
292 '\u0941', // dd -- Vowel Sign U |
|
293 '\u0942', // de -- Vowel Sign UU |
|
294 '\u0943', // df -- Vowel Sign RI |
|
295 '\u0946', // e0 -- Vowel Sign E ( Southern Scripts ) |
|
296 '\u0947', // e1 -- Vowel Sign EY |
|
297 '\u0948', // e2 -- Vowel Sign AI |
|
298 '\u0945', // e3 -- Vowel Sign AYE ( Devanagari Script ) |
|
299 '\u094a', // e4 -- Vowel Sign O ( Southern Scripts ) |
|
300 '\u094b', // e5 -- Vowel Sign OW |
|
301 '\u094c', // e6 -- Vowel Sign AU |
|
302 '\u0949', // e7 -- Vowel Sign AWE ( Devanagari Script ) |
|
303 |
|
304 '\u094d', // e8 -- Vowel Omission Sign ( Halant ) |
|
305 '\u093c', // e9 -- Diacritic Sign ( Nukta ) |
|
306 '\u0964', // ea -- Full Stop ( Viram, Northern Scripts ) |
|
307 |
|
308 '\uffff', // eb -- This position shall not be used |
|
309 '\uffff', // ec -- This position shall not be used |
|
310 '\uffff', // ed -- This position shall not be used |
|
311 '\uffff', // ee -- This position shall not be used |
|
312 |
|
313 '\ufffd', // ef -- Attribute Code ( ATR ) |
|
314 '\ufffd', // f0 -- Extension Code ( EXT ) |
|
315 |
|
316 '\u0966', // f1 -- Digit 0 |
|
317 '\u0967', // f2 -- Digit 1 |
|
318 '\u0968', // f3 -- Digit 2 |
|
319 '\u0969', // f4 -- Digit 3 |
|
320 '\u096a', // f5 -- Digit 4 |
|
321 '\u096b', // f6 -- Digit 5 |
|
322 '\u096c', // f7 -- Digit 6 |
|
323 '\u096d', // f8 -- Digit 7 |
|
324 '\u096e', // f9 -- Digit 8 |
|
325 '\u096f', // fa -- Digit 9 |
|
326 |
|
327 '\uffff', // fb -- This position shall not be used |
|
328 '\uffff', // fc -- This position shall not be used |
|
329 '\uffff', // fd -- This position shall not be used |
|
330 '\uffff', // fe -- This position shall not be used |
|
331 '\uffff' // ff -- This position shall not be used |
|
332 }; //end of table definition |
|
333 |
|
334 private static final byte[] encoderMappingTable = { |
|
335 NO_CHAR,NO_CHAR, //0900 <reserved> |
|
336 (byte)161,NO_CHAR, //0901 -- DEVANAGARI SIGN CANDRABINDU = anunasika |
|
337 (byte)162,NO_CHAR, //0902 -- DEVANAGARI SIGN ANUSVARA = bindu |
|
338 (byte)163,NO_CHAR, //0903 -- DEVANAGARI SIGN VISARGA |
|
339 NO_CHAR,NO_CHAR, //0904 <reserved> |
|
340 (byte)164,NO_CHAR, //0905 -- DEVANAGARI LETTER A |
|
341 (byte)165,NO_CHAR, //0906 -- DEVANAGARI LETTER AA |
|
342 (byte)166,NO_CHAR, //0907 -- DEVANAGARI LETTER I |
|
343 (byte)167,NO_CHAR, //0908 -- DEVANAGARI LETTER II |
|
344 (byte)168,NO_CHAR, //0909 -- DEVANAGARI LETTER U |
|
345 (byte)169,NO_CHAR, //090a -- DEVANAGARI LETTER UU |
|
346 (byte)170,NO_CHAR, //090b -- DEVANAGARI LETTER VOCALIC R |
|
347 (byte)166,(byte)233, //090c -- DEVANAGARI LETTER VOVALIC L |
|
348 (byte)174,NO_CHAR, //090d -- DEVANAGARI LETTER CANDRA E |
|
349 (byte)171,NO_CHAR, //090e -- DEVANAGARI LETTER SHORT E |
|
350 (byte)172,NO_CHAR, //090f -- DEVANAGARI LETTER E |
|
351 (byte)173,NO_CHAR, //0910 -- DEVANAGARI LETTER AI |
|
352 (byte)178,NO_CHAR, //0911 -- DEVANAGARI LETTER CANDRA O |
|
353 (byte)175,NO_CHAR, //0912 -- DEVANAGARI LETTER SHORT O |
|
354 (byte)176,NO_CHAR, //0913 -- DEVANAGARI LETTER O |
|
355 (byte)177,NO_CHAR, //0914 -- DEVANAGARI LETTER AU |
|
356 (byte)179,NO_CHAR, //0915 -- DEVANAGARI LETTER KA |
|
357 (byte)180,NO_CHAR, //0916 -- DEVANAGARI LETTER KHA |
|
358 (byte)181,NO_CHAR, //0917 -- DEVANAGARI LETTER GA |
|
359 (byte)182,NO_CHAR, //0918 -- DEVANAGARI LETTER GHA |
|
360 (byte)183,NO_CHAR, //0919 -- DEVANAGARI LETTER NGA |
|
361 (byte)184,NO_CHAR, //091a -- DEVANAGARI LETTER CA |
|
362 (byte)185,NO_CHAR, //091b -- DEVANAGARI LETTER CHA |
|
363 (byte)186,NO_CHAR, //091c -- DEVANAGARI LETTER JA |
|
364 (byte)187,NO_CHAR, //091d -- DEVANAGARI LETTER JHA |
|
365 (byte)188,NO_CHAR, //091e -- DEVANAGARI LETTER NYA |
|
366 (byte)189,NO_CHAR, //091f -- DEVANAGARI LETTER TTA |
|
367 (byte)190,NO_CHAR, //0920 -- DEVANAGARI LETTER TTHA |
|
368 (byte)191,NO_CHAR, //0921 -- DEVANAGARI LETTER DDA |
|
369 (byte)192,NO_CHAR, //0922 -- DEVANAGARI LETTER DDHA |
|
370 (byte)193,NO_CHAR, //0923 -- DEVANAGARI LETTER NNA |
|
371 (byte)194,NO_CHAR, //0924 -- DEVANAGARI LETTER TA |
|
372 (byte)195,NO_CHAR, //0925 -- DEVANAGARI LETTER THA |
|
373 (byte)196,NO_CHAR, //0926 -- DEVANAGARI LETTER DA |
|
374 (byte)197,NO_CHAR, //0927 -- DEVANAGARI LETTER DHA |
|
375 (byte)198,NO_CHAR, //0928 -- DEVANAGARI LETTER NA |
|
376 (byte)199,NO_CHAR, //0929 -- DEVANAGARI LETTER NNNA <=> 0928 + 093C |
|
377 (byte)200,NO_CHAR, //092a -- DEVANAGARI LETTER PA |
|
378 (byte)201,NO_CHAR, //092b -- DEVANAGARI LETTER PHA |
|
379 (byte)202,NO_CHAR, //092c -- DEVANAGARI LETTER BA |
|
380 (byte)203,NO_CHAR, //092d -- DEVANAGARI LETTER BHA |
|
381 (byte)204,NO_CHAR, //092e -- DEVANAGARI LETTER MA |
|
382 (byte)205,NO_CHAR, //092f -- DEVANAGARI LETTER YA |
|
383 (byte)207,NO_CHAR, //0930 -- DEVANAGARI LETTER RA |
|
384 (byte)208,NO_CHAR, //0931 -- DEVANAGARI LETTER RRA <=> 0930 + 093C |
|
385 (byte)209,NO_CHAR, //0932 -- DEVANAGARI LETTER LA |
|
386 (byte)210,NO_CHAR, //0933 -- DEVANAGARI LETTER LLA |
|
387 (byte)211,NO_CHAR, //0934 -- DEVANAGARI LETTER LLLA <=> 0933 + 093C |
|
388 (byte)212,NO_CHAR, //0935 -- DEVANAGARI LETTER VA |
|
389 (byte)213,NO_CHAR, //0936 -- DEVANAGARI LETTER SHA |
|
390 (byte)214,NO_CHAR, //0937 -- DEVANAGARI LETTER SSA |
|
391 (byte)215,NO_CHAR, //0938 -- DEVANAGARI LETTER SA |
|
392 (byte)216,NO_CHAR, //0939 -- DEVANAGARI LETTER HA |
|
393 NO_CHAR,NO_CHAR, //093a <reserved> |
|
394 NO_CHAR,NO_CHAR, //093b <reserved> |
|
395 (byte)233,NO_CHAR, //093c -- DEVANAGARI SIGN NUKTA |
|
396 (byte)234,(byte)233, //093d -- DEVANAGARI SIGN AVAGRAHA |
|
397 (byte)218,NO_CHAR, //093e -- DEVANAGARI VOWEL SIGN AA |
|
398 (byte)219,NO_CHAR, //093f -- DEVANAGARI VOWEL SIGN I |
|
399 (byte)220,NO_CHAR, //0940 -- DEVANAGARI VOWEL SIGN II |
|
400 (byte)221,NO_CHAR, //0941 -- DEVANAGARI VOWEL SIGN U |
|
401 (byte)222,NO_CHAR, //0942 -- DEVANAGARI VOWEL SIGN UU |
|
402 (byte)223,NO_CHAR, //0943 -- DEVANAGARI VOWEL SIGN VOCALIC R |
|
403 (byte)223,(byte)233, //0944 -- DEVANAGARI VOWEL SIGN VOCALIC RR |
|
404 (byte)227,NO_CHAR, //0945 -- DEVANAGARI VOWEL SIGN CANDRA E |
|
405 (byte)224,NO_CHAR, //0946 -- DEVANAGARI VOWEL SIGN SHORT E |
|
406 (byte)225,NO_CHAR, //0947 -- DEVANAGARI VOWEL SIGN E |
|
407 (byte)226,NO_CHAR, //0948 -- DEVANAGARI VOWEL SIGN AI |
|
408 (byte)231,NO_CHAR, //0949 -- DEVANAGARI VOWEL SIGN CANDRA O |
|
409 (byte)228,NO_CHAR, //094a -- DEVANAGARI VOWEL SIGN SHORT O |
|
410 (byte)229,NO_CHAR, //094b -- DEVANAGARI VOWEL SIGN O |
|
411 (byte)230,NO_CHAR, //094c -- DEVANAGARI VOWEL SIGN AU |
|
412 (byte)232,NO_CHAR, //094d -- DEVANAGARI SIGN VIRAMA ( halant ) |
|
413 NO_CHAR,NO_CHAR, //094e <reserved> |
|
414 NO_CHAR,NO_CHAR, //094f <reserved> |
|
415 (byte)161,(byte)233, //0950 -- DEVANAGARI OM |
|
416 (byte)240,(byte)181, //0951 -- DEVANAGARI STRESS SIGN UDATTA |
|
417 (byte)240,(byte)184, //0952 -- DEVANAGARI STRESS SIGN ANUDATTA |
|
418 (byte)254,NO_CHAR, //0953 -- DEVANAGARI GRAVE ACCENT || MISSING |
|
419 (byte)254,NO_CHAR, //0954 -- DEVANAGARI ACUTE ACCENT || MISSING |
|
420 NO_CHAR,NO_CHAR, //0955 <reserved> |
|
421 NO_CHAR,NO_CHAR, //0956 <reserved> |
|
422 NO_CHAR,NO_CHAR, //0957 <reserved> |
|
423 (byte)179,(byte)233, //0958 -- DEVANAGARI LETTER QA <=> 0915 + 093C |
|
424 (byte)180,(byte)233, //0959 -- DEVANAGARI LETTER KHHA <=> 0916 + 093C |
|
425 (byte)181,(byte)233, //095a -- DEVANAGARI LETTER GHHA <=> 0917 + 093C |
|
426 (byte)186,(byte)233, //095b -- DEVANAGARI LETTER ZA <=> 091C + 093C |
|
427 (byte)191,(byte)233, //095c -- DEVANAGARI LETTER DDDHA <=> 0921 + 093C |
|
428 (byte)192,(byte)233, //095d -- DEVANAGARI LETTER RHA <=> 0922 + 093C |
|
429 (byte)201,(byte)233, //095e -- DEVANAGARI LETTER FA <=> 092B + 093C |
|
430 (byte)206,NO_CHAR, //095f -- DEVANAGARI LETTER YYA <=> 092F + 093C |
|
431 (byte)170,(byte)233, //0960 -- DEVANAGARI LETTER VOCALIC RR |
|
432 (byte)167,(byte)233, //0961 -- DEVANAGARI LETTER VOCALIC LL |
|
433 (byte)219,(byte)233, //0962 -- DEVANAGARI VOWEL SIGN VOCALIC L |
|
434 (byte)220,(byte)233, //0963 -- DEVANAGARI VOWEL SIGN VOCALIC LL |
|
435 (byte)234,NO_CHAR, //0964 -- DEVANAGARI DANDA ( phrase separator ) |
|
436 (byte)234,(byte)234, //0965 -- DEVANAGARI DOUBLE DANDA |
|
437 (byte)241,NO_CHAR, //0966 -- DEVANAGARI DIGIT ZERO |
|
438 (byte)242,NO_CHAR, //0967 -- DEVANAGARI DIGIT ONE |
|
439 (byte)243,NO_CHAR, //0968 -- DEVANAGARI DIGIT TWO |
|
440 (byte)244,NO_CHAR, //0969 -- DEVANAGARI DIGIT THREE |
|
441 (byte)245,NO_CHAR, //096a -- DEVANAGARI DIGIT FOUR |
|
442 (byte)246,NO_CHAR, //096b -- DEVANAGARI DIGIT FIVE |
|
443 (byte)247,NO_CHAR, //096c -- DEVANAGARI DIGIT SIX |
|
444 (byte)248,NO_CHAR, //096d -- DEVANAGARI DIGIT SEVEN |
|
445 (byte)249,NO_CHAR, //096e -- DEVANAGARI DIGIT EIGHT |
|
446 (byte)250,NO_CHAR, //096f -- DEVANAGARI DIGIT NINE |
|
447 (byte)240,(byte)191, //0970 -- DEVANAGARI ABBREVIATION SIGN |
|
448 NO_CHAR,NO_CHAR, //0971 -- reserved |
|
449 NO_CHAR,NO_CHAR, //0972 -- reserved |
|
450 NO_CHAR,NO_CHAR, //0973 -- reserved |
|
451 NO_CHAR,NO_CHAR, //0974 -- reserved |
|
452 NO_CHAR,NO_CHAR, //0975 -- reserved |
|
453 NO_CHAR,NO_CHAR, //0976 -- reserved |
|
454 NO_CHAR,NO_CHAR, //0977 -- reserved |
|
455 NO_CHAR,NO_CHAR, //0978 -- reserved |
|
456 NO_CHAR,NO_CHAR, //0979 -- reserved |
|
457 NO_CHAR,NO_CHAR, //097a -- reserved |
|
458 NO_CHAR,NO_CHAR, //097b -- reserved |
|
459 NO_CHAR,NO_CHAR, //097c -- reserved |
|
460 NO_CHAR,NO_CHAR, //097d -- reserved |
|
461 NO_CHAR,NO_CHAR, //097e -- reserved |
|
462 NO_CHAR,NO_CHAR //097f -- reserved |
|
463 }; //end of table definition |
|
464 |
|
465 private static class Decoder extends CharsetDecoder { |
|
466 |
|
467 private static final char ZWNJ_CHAR = '\u200c'; |
|
468 private static final char ZWJ_CHAR = '\u200d'; |
|
469 private static final char INVALID_CHAR = '\uffff'; |
|
470 |
|
471 private char contextChar = INVALID_CHAR; |
|
472 private boolean needFlushing = false; |
|
473 |
|
474 |
|
475 private Decoder(Charset cs) { |
|
476 super(cs, 1.0f, 1.0f); |
|
477 } |
|
478 |
|
479 protected CoderResult implFlush(CharBuffer out) { |
|
480 if(needFlushing) { |
|
481 if (out.remaining() < 1) { |
|
482 return CoderResult.OVERFLOW; |
|
483 } else { |
|
484 out.put(contextChar); |
|
485 } |
|
486 } |
|
487 contextChar = INVALID_CHAR; |
|
488 needFlushing = false; |
|
489 return CoderResult.UNDERFLOW; |
|
490 } |
|
491 |
|
492 /*Rules: |
|
493 * 1)ATR,EXT,following character to be replaced with '\ufffd' |
|
494 * 2)Halant + Halant => '\u094d' (Virama) + '\u200c'(ZWNJ) |
|
495 * 3)Halant + Nukta => '\u094d' (Virama) + '\u200d'(ZWJ) |
|
496 */ |
|
497 private CoderResult decodeArrayLoop(ByteBuffer src, |
|
498 CharBuffer dst) |
|
499 { |
|
500 byte[] sa = src.array(); |
|
501 int sp = src.arrayOffset() + src.position(); |
|
502 int sl = src.arrayOffset() + src.limit(); |
|
503 assert (sp <= sl); |
|
504 sp = (sp <= sl ? sp : sl); |
|
505 |
|
506 char[] da = dst.array(); |
|
507 int dp = dst.arrayOffset() + dst.position(); |
|
508 int dl = dst.arrayOffset() + dst.limit(); |
|
509 assert (dp <= dl); |
|
510 dp = (dp <= dl ? dp : dl); |
|
511 |
|
512 try { |
|
513 while (sp < sl) { |
|
514 int index = sa[sp]; |
|
515 index = ( index < 0 )? ( index + 255 ):index; |
|
516 char currentChar = directMapTable[index]; |
|
517 |
|
518 // if the contextChar is either ATR || EXT |
|
519 // set the output to '\ufffd' |
|
520 if(contextChar == '\ufffd') { |
|
521 if (dl - dp < 1) |
|
522 return CoderResult.OVERFLOW; |
|
523 da[dp++] = '\ufffd'; |
|
524 contextChar = INVALID_CHAR; |
|
525 needFlushing = false; |
|
526 sp++; |
|
527 continue; |
|
528 } |
|
529 |
|
530 switch(currentChar) { |
|
531 case '\u0901': |
|
532 case '\u0907': |
|
533 case '\u0908': |
|
534 case '\u090b': |
|
535 case '\u093f': |
|
536 case '\u0940': |
|
537 case '\u0943': |
|
538 case '\u0964': |
|
539 if(needFlushing) { |
|
540 if (dl - dp < 1) |
|
541 return CoderResult.OVERFLOW; |
|
542 da[dp++] = contextChar; |
|
543 contextChar = currentChar; |
|
544 sp++; |
|
545 continue; |
|
546 } |
|
547 contextChar = currentChar; |
|
548 needFlushing = true; |
|
549 sp++; |
|
550 continue; |
|
551 case NUKTA_CHAR: |
|
552 if (dl - dp < 1) |
|
553 return CoderResult.OVERFLOW; |
|
554 switch(contextChar) { |
|
555 case '\u0901': |
|
556 da[dp++] = '\u0950'; |
|
557 break; |
|
558 case '\u0907': |
|
559 da[dp++] = '\u090c'; |
|
560 break; |
|
561 case '\u0908': |
|
562 da[dp++] = '\u0961'; |
|
563 break; |
|
564 case '\u090b': |
|
565 da[dp++] = '\u0960'; |
|
566 break; |
|
567 case '\u093f': |
|
568 da[dp++] = '\u0962'; |
|
569 break; |
|
570 case '\u0940': |
|
571 da[dp++] = '\u0963'; |
|
572 break; |
|
573 case '\u0943': |
|
574 da[dp++] = '\u0944'; |
|
575 break; |
|
576 case '\u0964': |
|
577 da[dp++] = '\u093d'; |
|
578 break; |
|
579 case HALANT_CHAR: |
|
580 if(needFlushing) { |
|
581 da[dp++] = contextChar; |
|
582 contextChar = currentChar; |
|
583 sp++; |
|
584 continue; |
|
585 } |
|
586 da[dp++] = ZWJ_CHAR; |
|
587 break; |
|
588 default: |
|
589 if(needFlushing) { |
|
590 da[dp++] = contextChar; |
|
591 contextChar = currentChar; |
|
592 sp++; |
|
593 continue; |
|
594 } |
|
595 da[dp++] = NUKTA_CHAR; |
|
596 } |
|
597 break; |
|
598 case HALANT_CHAR: |
|
599 if (dl - dp < 1) |
|
600 return CoderResult.OVERFLOW; |
|
601 if(needFlushing) { |
|
602 da[dp++] = contextChar; |
|
603 contextChar = currentChar; |
|
604 sp++; |
|
605 continue; |
|
606 } |
|
607 if(contextChar == HALANT_CHAR) { |
|
608 da[dp++] = ZWNJ_CHAR; |
|
609 break; |
|
610 } |
|
611 da[dp++] = HALANT_CHAR; |
|
612 break; |
|
613 case INVALID_CHAR: |
|
614 if(needFlushing) { |
|
615 if (dl - dp < 1) |
|
616 return CoderResult.OVERFLOW; |
|
617 da[dp++] = contextChar; |
|
618 contextChar = currentChar; |
|
619 sp++; |
|
620 continue; |
|
621 } |
|
622 return CoderResult.unmappableForLength(1); |
|
623 default: |
|
624 if (dl - dp < 1) |
|
625 return CoderResult.OVERFLOW; |
|
626 if(needFlushing) { |
|
627 da[dp++] = contextChar; |
|
628 contextChar = currentChar; |
|
629 sp++; |
|
630 continue; |
|
631 } |
|
632 da[dp++] = currentChar; |
|
633 break; |
|
634 }//end switch |
|
635 |
|
636 contextChar = currentChar; |
|
637 needFlushing = false; |
|
638 sp++; |
|
639 } |
|
640 return CoderResult.UNDERFLOW; |
|
641 } finally { |
|
642 src.position(sp - src.arrayOffset()); |
|
643 dst.position(dp - dst.arrayOffset()); |
|
644 } |
|
645 } |
|
646 |
|
647 private CoderResult decodeBufferLoop(ByteBuffer src, |
|
648 CharBuffer dst) |
|
649 { |
|
650 int mark = src.position(); |
|
651 |
|
652 try { |
|
653 while (src.hasRemaining()) { |
|
654 int index = src.get(); |
|
655 index = ( index < 0 )? ( index + 255 ):index; |
|
656 char currentChar = directMapTable[index]; |
|
657 |
|
658 // if the contextChar is either ATR || EXT |
|
659 // set the output to '\ufffd' |
|
660 if(contextChar == '\ufffd') { |
|
661 if (dst.remaining() < 1) |
|
662 return CoderResult.OVERFLOW; |
|
663 dst.put('\ufffd'); |
|
664 contextChar = INVALID_CHAR; |
|
665 needFlushing = false; |
|
666 mark++; |
|
667 continue; |
|
668 } |
|
669 |
|
670 switch(currentChar) { |
|
671 case '\u0901': |
|
672 case '\u0907': |
|
673 case '\u0908': |
|
674 case '\u090b': |
|
675 case '\u093f': |
|
676 case '\u0940': |
|
677 case '\u0943': |
|
678 case '\u0964': |
|
679 if(needFlushing) { |
|
680 if (dst.remaining() < 1) |
|
681 return CoderResult.OVERFLOW; |
|
682 dst.put(contextChar); |
|
683 contextChar = currentChar; |
|
684 mark++; |
|
685 continue; |
|
686 } |
|
687 contextChar = currentChar; |
|
688 needFlushing = true; |
|
689 mark++; |
|
690 continue; |
|
691 case NUKTA_CHAR: |
|
692 if (dst.remaining() < 1) |
|
693 return CoderResult.OVERFLOW; |
|
694 switch(contextChar) { |
|
695 case '\u0901': |
|
696 dst.put('\u0950'); |
|
697 break; |
|
698 case '\u0907': |
|
699 dst.put('\u090c'); |
|
700 break; |
|
701 case '\u0908': |
|
702 dst.put('\u0961'); |
|
703 break; |
|
704 case '\u090b': |
|
705 dst.put('\u0960'); |
|
706 break; |
|
707 case '\u093f': |
|
708 dst.put('\u0962'); |
|
709 break; |
|
710 case '\u0940': |
|
711 dst.put('\u0963'); |
|
712 break; |
|
713 case '\u0943': |
|
714 dst.put('\u0944'); |
|
715 break; |
|
716 case '\u0964': |
|
717 dst.put('\u093d'); |
|
718 break; |
|
719 case HALANT_CHAR: |
|
720 if(needFlushing) { |
|
721 dst.put(contextChar); |
|
722 contextChar = currentChar; |
|
723 mark++; |
|
724 continue; |
|
725 } |
|
726 dst.put(ZWJ_CHAR); |
|
727 break; |
|
728 default: |
|
729 if(needFlushing) { |
|
730 dst.put(contextChar); |
|
731 contextChar = currentChar; |
|
732 mark++; |
|
733 continue; |
|
734 } |
|
735 dst.put(NUKTA_CHAR); |
|
736 } |
|
737 break; |
|
738 case HALANT_CHAR: |
|
739 if (dst.remaining() < 1) |
|
740 return CoderResult.OVERFLOW; |
|
741 if(needFlushing) { |
|
742 dst.put(contextChar); |
|
743 contextChar = currentChar; |
|
744 mark++; |
|
745 continue; |
|
746 } |
|
747 if(contextChar == HALANT_CHAR) { |
|
748 dst.put(ZWNJ_CHAR); |
|
749 break; |
|
750 } |
|
751 dst.put(HALANT_CHAR); |
|
752 break; |
|
753 case INVALID_CHAR: |
|
754 if(needFlushing) { |
|
755 if (dst.remaining() < 1) |
|
756 return CoderResult.OVERFLOW; |
|
757 dst.put(contextChar); |
|
758 contextChar = currentChar; |
|
759 mark++; |
|
760 continue; |
|
761 } |
|
762 return CoderResult.unmappableForLength(1); |
|
763 default: |
|
764 if (dst.remaining() < 1) |
|
765 return CoderResult.OVERFLOW; |
|
766 if(needFlushing) { |
|
767 dst.put(contextChar); |
|
768 contextChar = currentChar; |
|
769 mark++; |
|
770 continue; |
|
771 } |
|
772 dst.put(currentChar); |
|
773 break; |
|
774 }//end switch |
|
775 contextChar = currentChar; |
|
776 needFlushing = false; |
|
777 mark++; |
|
778 } |
|
779 return CoderResult.UNDERFLOW; |
|
780 } finally { |
|
781 src.position(mark); |
|
782 } |
|
783 } |
|
784 |
|
785 protected CoderResult decodeLoop(ByteBuffer src, |
|
786 CharBuffer dst) |
|
787 { |
|
788 if (src.hasArray() && dst.hasArray()) |
|
789 return decodeArrayLoop(src, dst); |
|
790 else |
|
791 return decodeBufferLoop(src, dst); |
|
792 } |
|
793 } |
|
794 |
|
795 private static class Encoder extends CharsetEncoder { |
|
796 |
|
797 private static final byte NO_CHAR = (byte)255; |
|
798 |
|
799 //private static CharToByteISCII91 c2b = new CharToByteISCII91(); |
|
800 //private static final byte[] directMapTable = c2b.getISCIIEncoderMap(); |
|
801 |
|
802 private final Surrogate.Parser sgp = new Surrogate.Parser(); |
|
803 |
|
804 private Encoder(Charset cs) { |
|
805 super(cs, 2.0f, 2.0f); |
|
806 } |
|
807 |
|
808 public boolean canEncode(char ch) { |
|
809 //check for Devanagari range,ZWJ,ZWNJ and ASCII range. |
|
810 return ((ch >= '\u0900' && ch <= '\u097f' && |
|
811 encoderMappingTable[2*(ch-'\u0900')] != NO_CHAR) || |
|
812 (ch == '\u200d') || |
|
813 (ch == '\u200c') || |
|
814 (ch <= '\u007f')); |
|
815 } |
|
816 |
|
817 |
|
818 private CoderResult encodeArrayLoop(CharBuffer src, |
|
819 ByteBuffer dst) |
|
820 { |
|
821 char[] sa = src.array(); |
|
822 int sp = src.arrayOffset() + src.position(); |
|
823 int sl = src.arrayOffset() + src.limit(); |
|
824 assert (sp <= sl); |
|
825 sp = (sp <= sl ? sp : sl); |
|
826 byte[] da = dst.array(); |
|
827 int dp = dst.arrayOffset() + dst.position(); |
|
828 int dl = dst.arrayOffset() + dst.limit(); |
|
829 assert (dp <= dl); |
|
830 dp = (dp <= dl ? dp : dl); |
|
831 |
|
832 int outputSize = 0; |
|
833 |
|
834 try { |
|
835 char inputChar; |
|
836 while (sp < sl) { |
|
837 int index = Integer.MIN_VALUE; |
|
838 inputChar = sa[sp]; |
|
839 |
|
840 if (inputChar >= 0x0000 && inputChar <= 0x007f) { |
|
841 if (dl - dp < 1) |
|
842 return CoderResult.OVERFLOW; |
|
843 da[dp++] = (byte) inputChar; |
|
844 sp++; |
|
845 continue; |
|
846 } |
|
847 |
|
848 // if inputChar == ZWJ replace it with halant |
|
849 // if inputChar == ZWNJ replace it with Nukta |
|
850 |
|
851 if (inputChar == 0x200c) { |
|
852 inputChar = HALANT_CHAR; |
|
853 } |
|
854 else if (inputChar == 0x200d) { |
|
855 inputChar = NUKTA_CHAR; |
|
856 } |
|
857 |
|
858 if (inputChar >= 0x0900 && inputChar <= 0x097f) { |
|
859 index = ((int)(inputChar) - 0x0900)*2; |
|
860 } |
|
861 |
|
862 if (Character.isSurrogate(inputChar)) { |
|
863 if (sgp.parse(inputChar, sa, sp, sl) < 0) |
|
864 return sgp.error(); |
|
865 return sgp.unmappableResult(); |
|
866 } |
|
867 |
|
868 if (index == Integer.MIN_VALUE || |
|
869 encoderMappingTable[index] == NO_CHAR) { |
|
870 return CoderResult.unmappableForLength(1); |
|
871 } else { |
|
872 if(encoderMappingTable[index + 1] == NO_CHAR) { |
|
873 if(dl - dp < 1) |
|
874 return CoderResult.OVERFLOW; |
|
875 da[dp++] = encoderMappingTable[index]; |
|
876 } else { |
|
877 if(dl - dp < 2) |
|
878 return CoderResult.OVERFLOW; |
|
879 da[dp++] = encoderMappingTable[index]; |
|
880 da[dp++] = encoderMappingTable[index + 1]; |
|
881 } |
|
882 sp++; |
|
883 } |
|
884 } |
|
885 return CoderResult.UNDERFLOW; |
|
886 } finally { |
|
887 src.position(sp - src.arrayOffset()); |
|
888 dst.position(dp - dst.arrayOffset()); |
|
889 } |
|
890 } |
|
891 |
|
892 private CoderResult encodeBufferLoop(CharBuffer src, |
|
893 ByteBuffer dst) |
|
894 { |
|
895 int mark = src.position(); |
|
896 |
|
897 try { |
|
898 char inputChar; |
|
899 while (src.hasRemaining()) { |
|
900 int index = Integer.MIN_VALUE; |
|
901 inputChar = src.get(); |
|
902 |
|
903 if (inputChar >= 0x0000 && inputChar <= 0x007f) { |
|
904 if (dst.remaining() < 1) |
|
905 return CoderResult.OVERFLOW; |
|
906 dst.put((byte) inputChar); |
|
907 mark++; |
|
908 continue; |
|
909 } |
|
910 |
|
911 // if inputChar == ZWJ replace it with halant |
|
912 // if inputChar == ZWNJ replace it with Nukta |
|
913 |
|
914 if (inputChar == 0x200c) { |
|
915 inputChar = HALANT_CHAR; |
|
916 } |
|
917 else if (inputChar == 0x200d) { |
|
918 inputChar = NUKTA_CHAR; |
|
919 } |
|
920 |
|
921 if (inputChar >= 0x0900 && inputChar <= 0x097f) { |
|
922 index = ((int)(inputChar) - 0x0900)*2; |
|
923 } |
|
924 |
|
925 if (Character.isSurrogate(inputChar)) { |
|
926 if (sgp.parse(inputChar, src) < 0) |
|
927 return sgp.error(); |
|
928 return sgp.unmappableResult(); |
|
929 } |
|
930 |
|
931 if (index == Integer.MIN_VALUE || |
|
932 encoderMappingTable[index] == NO_CHAR) { |
|
933 return CoderResult.unmappableForLength(1); |
|
934 } else { |
|
935 if(encoderMappingTable[index + 1] == NO_CHAR) { |
|
936 if(dst.remaining() < 1) |
|
937 return CoderResult.OVERFLOW; |
|
938 dst.put(encoderMappingTable[index]); |
|
939 } else { |
|
940 if(dst.remaining() < 2) |
|
941 return CoderResult.OVERFLOW; |
|
942 dst.put(encoderMappingTable[index]); |
|
943 dst.put(encoderMappingTable[index + 1]); |
|
944 } |
|
945 } |
|
946 mark++; |
|
947 } |
|
948 return CoderResult.UNDERFLOW; |
|
949 } finally { |
|
950 src.position(mark); |
|
951 } |
|
952 } |
|
953 |
|
954 protected CoderResult encodeLoop(CharBuffer src, |
|
955 ByteBuffer dst) |
|
956 { |
|
957 if (src.hasArray() && dst.hasArray()) |
|
958 return encodeArrayLoop(src, dst); |
|
959 else |
|
960 return encodeBufferLoop(src, dst); |
|
961 } |
|
962 } |
|
963 } |