2
|
1 |
/*
|
5506
|
2 |
* Copyright (c) 2002, 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 |
|
|
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 |
/**
|
|
335 |
* This accessor is temporarily supplied while sun.io
|
|
336 |
* converters co-exist with the sun.nio.cs.{ext} charset coders
|
|
337 |
* These facilitate sharing of conversion tables between the
|
|
338 |
* two co-existing implementations. When sun.io converters
|
|
339 |
* are made extinct these will be unnecessary and should be removed
|
|
340 |
*/
|
|
341 |
|
|
342 |
public static char[] getDirectMapTable() {
|
|
343 |
return directMapTable;
|
|
344 |
}
|
|
345 |
|
|
346 |
private static final byte[] encoderMappingTable = {
|
|
347 |
NO_CHAR,NO_CHAR, //0900 <reserved>
|
|
348 |
(byte)161,NO_CHAR, //0901 -- DEVANAGARI SIGN CANDRABINDU = anunasika
|
|
349 |
(byte)162,NO_CHAR, //0902 -- DEVANAGARI SIGN ANUSVARA = bindu
|
|
350 |
(byte)163,NO_CHAR, //0903 -- DEVANAGARI SIGN VISARGA
|
|
351 |
NO_CHAR,NO_CHAR, //0904 <reserved>
|
|
352 |
(byte)164,NO_CHAR, //0905 -- DEVANAGARI LETTER A
|
|
353 |
(byte)165,NO_CHAR, //0906 -- DEVANAGARI LETTER AA
|
|
354 |
(byte)166,NO_CHAR, //0907 -- DEVANAGARI LETTER I
|
|
355 |
(byte)167,NO_CHAR, //0908 -- DEVANAGARI LETTER II
|
|
356 |
(byte)168,NO_CHAR, //0909 -- DEVANAGARI LETTER U
|
|
357 |
(byte)169,NO_CHAR, //090a -- DEVANAGARI LETTER UU
|
|
358 |
(byte)170,NO_CHAR, //090b -- DEVANAGARI LETTER VOCALIC R
|
|
359 |
(byte)166,(byte)233, //090c -- DEVANAGARI LETTER VOVALIC L
|
|
360 |
(byte)174,NO_CHAR, //090d -- DEVANAGARI LETTER CANDRA E
|
|
361 |
(byte)171,NO_CHAR, //090e -- DEVANAGARI LETTER SHORT E
|
|
362 |
(byte)172,NO_CHAR, //090f -- DEVANAGARI LETTER E
|
|
363 |
(byte)173,NO_CHAR, //0910 -- DEVANAGARI LETTER AI
|
|
364 |
(byte)178,NO_CHAR, //0911 -- DEVANAGARI LETTER CANDRA O
|
|
365 |
(byte)175,NO_CHAR, //0912 -- DEVANAGARI LETTER SHORT O
|
|
366 |
(byte)176,NO_CHAR, //0913 -- DEVANAGARI LETTER O
|
|
367 |
(byte)177,NO_CHAR, //0914 -- DEVANAGARI LETTER AU
|
|
368 |
(byte)179,NO_CHAR, //0915 -- DEVANAGARI LETTER KA
|
|
369 |
(byte)180,NO_CHAR, //0916 -- DEVANAGARI LETTER KHA
|
|
370 |
(byte)181,NO_CHAR, //0917 -- DEVANAGARI LETTER GA
|
|
371 |
(byte)182,NO_CHAR, //0918 -- DEVANAGARI LETTER GHA
|
|
372 |
(byte)183,NO_CHAR, //0919 -- DEVANAGARI LETTER NGA
|
|
373 |
(byte)184,NO_CHAR, //091a -- DEVANAGARI LETTER CA
|
|
374 |
(byte)185,NO_CHAR, //091b -- DEVANAGARI LETTER CHA
|
|
375 |
(byte)186,NO_CHAR, //091c -- DEVANAGARI LETTER JA
|
|
376 |
(byte)187,NO_CHAR, //091d -- DEVANAGARI LETTER JHA
|
|
377 |
(byte)188,NO_CHAR, //091e -- DEVANAGARI LETTER NYA
|
|
378 |
(byte)189,NO_CHAR, //091f -- DEVANAGARI LETTER TTA
|
|
379 |
(byte)190,NO_CHAR, //0920 -- DEVANAGARI LETTER TTHA
|
|
380 |
(byte)191,NO_CHAR, //0921 -- DEVANAGARI LETTER DDA
|
|
381 |
(byte)192,NO_CHAR, //0922 -- DEVANAGARI LETTER DDHA
|
|
382 |
(byte)193,NO_CHAR, //0923 -- DEVANAGARI LETTER NNA
|
|
383 |
(byte)194,NO_CHAR, //0924 -- DEVANAGARI LETTER TA
|
|
384 |
(byte)195,NO_CHAR, //0925 -- DEVANAGARI LETTER THA
|
|
385 |
(byte)196,NO_CHAR, //0926 -- DEVANAGARI LETTER DA
|
|
386 |
(byte)197,NO_CHAR, //0927 -- DEVANAGARI LETTER DHA
|
|
387 |
(byte)198,NO_CHAR, //0928 -- DEVANAGARI LETTER NA
|
|
388 |
(byte)199,NO_CHAR, //0929 -- DEVANAGARI LETTER NNNA <=> 0928 + 093C
|
|
389 |
(byte)200,NO_CHAR, //092a -- DEVANAGARI LETTER PA
|
|
390 |
(byte)201,NO_CHAR, //092b -- DEVANAGARI LETTER PHA
|
|
391 |
(byte)202,NO_CHAR, //092c -- DEVANAGARI LETTER BA
|
|
392 |
(byte)203,NO_CHAR, //092d -- DEVANAGARI LETTER BHA
|
|
393 |
(byte)204,NO_CHAR, //092e -- DEVANAGARI LETTER MA
|
|
394 |
(byte)205,NO_CHAR, //092f -- DEVANAGARI LETTER YA
|
|
395 |
(byte)207,NO_CHAR, //0930 -- DEVANAGARI LETTER RA
|
|
396 |
(byte)208,NO_CHAR, //0931 -- DEVANAGARI LETTER RRA <=> 0930 + 093C
|
|
397 |
(byte)209,NO_CHAR, //0932 -- DEVANAGARI LETTER LA
|
|
398 |
(byte)210,NO_CHAR, //0933 -- DEVANAGARI LETTER LLA
|
|
399 |
(byte)211,NO_CHAR, //0934 -- DEVANAGARI LETTER LLLA <=> 0933 + 093C
|
|
400 |
(byte)212,NO_CHAR, //0935 -- DEVANAGARI LETTER VA
|
|
401 |
(byte)213,NO_CHAR, //0936 -- DEVANAGARI LETTER SHA
|
|
402 |
(byte)214,NO_CHAR, //0937 -- DEVANAGARI LETTER SSA
|
|
403 |
(byte)215,NO_CHAR, //0938 -- DEVANAGARI LETTER SA
|
|
404 |
(byte)216,NO_CHAR, //0939 -- DEVANAGARI LETTER HA
|
|
405 |
NO_CHAR,NO_CHAR, //093a <reserved>
|
|
406 |
NO_CHAR,NO_CHAR, //093b <reserved>
|
|
407 |
(byte)233,NO_CHAR, //093c -- DEVANAGARI SIGN NUKTA
|
|
408 |
(byte)234,(byte)233, //093d -- DEVANAGARI SIGN AVAGRAHA
|
|
409 |
(byte)218,NO_CHAR, //093e -- DEVANAGARI VOWEL SIGN AA
|
|
410 |
(byte)219,NO_CHAR, //093f -- DEVANAGARI VOWEL SIGN I
|
|
411 |
(byte)220,NO_CHAR, //0940 -- DEVANAGARI VOWEL SIGN II
|
|
412 |
(byte)221,NO_CHAR, //0941 -- DEVANAGARI VOWEL SIGN U
|
|
413 |
(byte)222,NO_CHAR, //0942 -- DEVANAGARI VOWEL SIGN UU
|
|
414 |
(byte)223,NO_CHAR, //0943 -- DEVANAGARI VOWEL SIGN VOCALIC R
|
|
415 |
(byte)223,(byte)233, //0944 -- DEVANAGARI VOWEL SIGN VOCALIC RR
|
|
416 |
(byte)227,NO_CHAR, //0945 -- DEVANAGARI VOWEL SIGN CANDRA E
|
|
417 |
(byte)224,NO_CHAR, //0946 -- DEVANAGARI VOWEL SIGN SHORT E
|
|
418 |
(byte)225,NO_CHAR, //0947 -- DEVANAGARI VOWEL SIGN E
|
|
419 |
(byte)226,NO_CHAR, //0948 -- DEVANAGARI VOWEL SIGN AI
|
|
420 |
(byte)231,NO_CHAR, //0949 -- DEVANAGARI VOWEL SIGN CANDRA O
|
|
421 |
(byte)228,NO_CHAR, //094a -- DEVANAGARI VOWEL SIGN SHORT O
|
|
422 |
(byte)229,NO_CHAR, //094b -- DEVANAGARI VOWEL SIGN O
|
|
423 |
(byte)230,NO_CHAR, //094c -- DEVANAGARI VOWEL SIGN AU
|
|
424 |
(byte)232,NO_CHAR, //094d -- DEVANAGARI SIGN VIRAMA ( halant )
|
|
425 |
NO_CHAR,NO_CHAR, //094e <reserved>
|
|
426 |
NO_CHAR,NO_CHAR, //094f <reserved>
|
|
427 |
(byte)161,(byte)233, //0950 -- DEVANAGARI OM
|
|
428 |
(byte)240,(byte)181, //0951 -- DEVANAGARI STRESS SIGN UDATTA
|
|
429 |
(byte)240,(byte)184, //0952 -- DEVANAGARI STRESS SIGN ANUDATTA
|
|
430 |
(byte)254,NO_CHAR, //0953 -- DEVANAGARI GRAVE ACCENT || MISSING
|
|
431 |
(byte)254,NO_CHAR, //0954 -- DEVANAGARI ACUTE ACCENT || MISSING
|
|
432 |
NO_CHAR,NO_CHAR, //0955 <reserved>
|
|
433 |
NO_CHAR,NO_CHAR, //0956 <reserved>
|
|
434 |
NO_CHAR,NO_CHAR, //0957 <reserved>
|
|
435 |
(byte)179,(byte)233, //0958 -- DEVANAGARI LETTER QA <=> 0915 + 093C
|
|
436 |
(byte)180,(byte)233, //0959 -- DEVANAGARI LETTER KHHA <=> 0916 + 093C
|
|
437 |
(byte)181,(byte)233, //095a -- DEVANAGARI LETTER GHHA <=> 0917 + 093C
|
|
438 |
(byte)186,(byte)233, //095b -- DEVANAGARI LETTER ZA <=> 091C + 093C
|
|
439 |
(byte)191,(byte)233, //095c -- DEVANAGARI LETTER DDDHA <=> 0921 + 093C
|
|
440 |
(byte)192,(byte)233, //095d -- DEVANAGARI LETTER RHA <=> 0922 + 093C
|
|
441 |
(byte)201,(byte)233, //095e -- DEVANAGARI LETTER FA <=> 092B + 093C
|
|
442 |
(byte)206,NO_CHAR, //095f -- DEVANAGARI LETTER YYA <=> 092F + 093C
|
|
443 |
(byte)170,(byte)233, //0960 -- DEVANAGARI LETTER VOCALIC RR
|
|
444 |
(byte)167,(byte)233, //0961 -- DEVANAGARI LETTER VOCALIC LL
|
|
445 |
(byte)219,(byte)233, //0962 -- DEVANAGARI VOWEL SIGN VOCALIC L
|
|
446 |
(byte)220,(byte)233, //0963 -- DEVANAGARI VOWEL SIGN VOCALIC LL
|
|
447 |
(byte)234,NO_CHAR, //0964 -- DEVANAGARI DANDA ( phrase separator )
|
|
448 |
(byte)234,(byte)234, //0965 -- DEVANAGARI DOUBLE DANDA
|
|
449 |
(byte)241,NO_CHAR, //0966 -- DEVANAGARI DIGIT ZERO
|
|
450 |
(byte)242,NO_CHAR, //0967 -- DEVANAGARI DIGIT ONE
|
|
451 |
(byte)243,NO_CHAR, //0968 -- DEVANAGARI DIGIT TWO
|
|
452 |
(byte)244,NO_CHAR, //0969 -- DEVANAGARI DIGIT THREE
|
|
453 |
(byte)245,NO_CHAR, //096a -- DEVANAGARI DIGIT FOUR
|
|
454 |
(byte)246,NO_CHAR, //096b -- DEVANAGARI DIGIT FIVE
|
|
455 |
(byte)247,NO_CHAR, //096c -- DEVANAGARI DIGIT SIX
|
|
456 |
(byte)248,NO_CHAR, //096d -- DEVANAGARI DIGIT SEVEN
|
|
457 |
(byte)249,NO_CHAR, //096e -- DEVANAGARI DIGIT EIGHT
|
|
458 |
(byte)250,NO_CHAR, //096f -- DEVANAGARI DIGIT NINE
|
|
459 |
(byte)240,(byte)191, //0970 -- DEVANAGARI ABBREVIATION SIGN
|
|
460 |
NO_CHAR,NO_CHAR, //0971 -- reserved
|
|
461 |
NO_CHAR,NO_CHAR, //0972 -- reserved
|
|
462 |
NO_CHAR,NO_CHAR, //0973 -- reserved
|
|
463 |
NO_CHAR,NO_CHAR, //0974 -- reserved
|
|
464 |
NO_CHAR,NO_CHAR, //0975 -- reserved
|
|
465 |
NO_CHAR,NO_CHAR, //0976 -- reserved
|
|
466 |
NO_CHAR,NO_CHAR, //0977 -- reserved
|
|
467 |
NO_CHAR,NO_CHAR, //0978 -- reserved
|
|
468 |
NO_CHAR,NO_CHAR, //0979 -- reserved
|
|
469 |
NO_CHAR,NO_CHAR, //097a -- reserved
|
|
470 |
NO_CHAR,NO_CHAR, //097b -- reserved
|
|
471 |
NO_CHAR,NO_CHAR, //097c -- reserved
|
|
472 |
NO_CHAR,NO_CHAR, //097d -- reserved
|
|
473 |
NO_CHAR,NO_CHAR, //097e -- reserved
|
|
474 |
NO_CHAR,NO_CHAR //097f -- reserved
|
|
475 |
}; //end of table definition
|
|
476 |
|
|
477 |
|
|
478 |
/**
|
|
479 |
* This accessor is temporarily supplied while sun.io
|
|
480 |
* converters co-exist with the sun.nio.cs.{ext} charset coders
|
|
481 |
* These facilitate sharing of conversion tables between the
|
|
482 |
* two co-existing implementations. When sun.io converters
|
|
483 |
* are made extinct these will be unnecessary and should be removed
|
|
484 |
*/
|
|
485 |
|
|
486 |
public static byte[] getEncoderMappingTable() {
|
|
487 |
return encoderMappingTable;
|
|
488 |
}
|
|
489 |
|
|
490 |
|
|
491 |
private static class Decoder extends CharsetDecoder {
|
|
492 |
|
|
493 |
private static final char ZWNJ_CHAR = '\u200c';
|
|
494 |
private static final char ZWJ_CHAR = '\u200d';
|
|
495 |
private static final char INVALID_CHAR = '\uffff';
|
|
496 |
|
|
497 |
private char contextChar = INVALID_CHAR;
|
|
498 |
private boolean needFlushing = false;
|
|
499 |
|
|
500 |
|
|
501 |
private Decoder(Charset cs) {
|
|
502 |
super(cs, 1.0f, 1.0f);
|
|
503 |
}
|
|
504 |
|
|
505 |
protected CoderResult implFlush(CharBuffer out) {
|
|
506 |
if(needFlushing) {
|
|
507 |
if (out.remaining() < 1) {
|
|
508 |
return CoderResult.OVERFLOW;
|
|
509 |
} else {
|
|
510 |
out.put(contextChar);
|
|
511 |
}
|
|
512 |
}
|
|
513 |
contextChar = INVALID_CHAR;
|
|
514 |
needFlushing = false;
|
|
515 |
return CoderResult.UNDERFLOW;
|
|
516 |
}
|
|
517 |
|
|
518 |
/*Rules:
|
|
519 |
* 1)ATR,EXT,following character to be replaced with '\ufffd'
|
|
520 |
* 2)Halant + Halant => '\u094d' (Virama) + '\u200c'(ZWNJ)
|
|
521 |
* 3)Halant + Nukta => '\u094d' (Virama) + '\u200d'(ZWJ)
|
|
522 |
*/
|
|
523 |
private CoderResult decodeArrayLoop(ByteBuffer src,
|
|
524 |
CharBuffer dst)
|
|
525 |
{
|
|
526 |
byte[] sa = src.array();
|
|
527 |
int sp = src.arrayOffset() + src.position();
|
|
528 |
int sl = src.arrayOffset() + src.limit();
|
|
529 |
assert (sp <= sl);
|
|
530 |
sp = (sp <= sl ? sp : sl);
|
|
531 |
|
|
532 |
char[] da = dst.array();
|
|
533 |
int dp = dst.arrayOffset() + dst.position();
|
|
534 |
int dl = dst.arrayOffset() + dst.limit();
|
|
535 |
assert (dp <= dl);
|
|
536 |
dp = (dp <= dl ? dp : dl);
|
|
537 |
|
|
538 |
try {
|
|
539 |
while (sp < sl) {
|
|
540 |
int index = sa[sp];
|
|
541 |
index = ( index < 0 )? ( index + 255 ):index;
|
|
542 |
char currentChar = directMapTable[index];
|
|
543 |
|
|
544 |
// if the contextChar is either ATR || EXT
|
|
545 |
// set the output to '\ufffd'
|
|
546 |
if(contextChar == '\ufffd') {
|
|
547 |
if (dl - dp < 1)
|
|
548 |
return CoderResult.OVERFLOW;
|
|
549 |
da[dp++] = '\ufffd';
|
|
550 |
contextChar = INVALID_CHAR;
|
|
551 |
needFlushing = false;
|
|
552 |
sp++;
|
|
553 |
continue;
|
|
554 |
}
|
|
555 |
|
|
556 |
switch(currentChar) {
|
|
557 |
case '\u0901':
|
|
558 |
case '\u0907':
|
|
559 |
case '\u0908':
|
|
560 |
case '\u090b':
|
|
561 |
case '\u093f':
|
|
562 |
case '\u0940':
|
|
563 |
case '\u0943':
|
|
564 |
case '\u0964':
|
|
565 |
if(needFlushing) {
|
|
566 |
if (dl - dp < 1)
|
|
567 |
return CoderResult.OVERFLOW;
|
|
568 |
da[dp++] = contextChar;
|
|
569 |
contextChar = currentChar;
|
|
570 |
sp++;
|
|
571 |
continue;
|
|
572 |
}
|
|
573 |
contextChar = currentChar;
|
|
574 |
needFlushing = true;
|
|
575 |
sp++;
|
|
576 |
continue;
|
|
577 |
case NUKTA_CHAR:
|
|
578 |
if (dl - dp < 1)
|
|
579 |
return CoderResult.OVERFLOW;
|
|
580 |
switch(contextChar) {
|
|
581 |
case '\u0901':
|
|
582 |
da[dp++] = '\u0950';
|
|
583 |
break;
|
|
584 |
case '\u0907':
|
|
585 |
da[dp++] = '\u090c';
|
|
586 |
break;
|
|
587 |
case '\u0908':
|
|
588 |
da[dp++] = '\u0961';
|
|
589 |
break;
|
|
590 |
case '\u090b':
|
|
591 |
da[dp++] = '\u0960';
|
|
592 |
break;
|
|
593 |
case '\u093f':
|
|
594 |
da[dp++] = '\u0962';
|
|
595 |
break;
|
|
596 |
case '\u0940':
|
|
597 |
da[dp++] = '\u0963';
|
|
598 |
break;
|
|
599 |
case '\u0943':
|
|
600 |
da[dp++] = '\u0944';
|
|
601 |
break;
|
|
602 |
case '\u0964':
|
|
603 |
da[dp++] = '\u093d';
|
|
604 |
break;
|
|
605 |
case HALANT_CHAR:
|
|
606 |
if(needFlushing) {
|
|
607 |
da[dp++] = contextChar;
|
|
608 |
contextChar = currentChar;
|
|
609 |
sp++;
|
|
610 |
continue;
|
|
611 |
}
|
|
612 |
da[dp++] = ZWJ_CHAR;
|
|
613 |
break;
|
|
614 |
default:
|
|
615 |
if(needFlushing) {
|
|
616 |
da[dp++] = contextChar;
|
|
617 |
contextChar = currentChar;
|
|
618 |
sp++;
|
|
619 |
continue;
|
|
620 |
}
|
|
621 |
da[dp++] = NUKTA_CHAR;
|
|
622 |
}
|
|
623 |
break;
|
|
624 |
case HALANT_CHAR:
|
|
625 |
if (dl - dp < 1)
|
|
626 |
return CoderResult.OVERFLOW;
|
|
627 |
if(needFlushing) {
|
|
628 |
da[dp++] = contextChar;
|
|
629 |
contextChar = currentChar;
|
|
630 |
sp++;
|
|
631 |
continue;
|
|
632 |
}
|
|
633 |
if(contextChar == HALANT_CHAR) {
|
|
634 |
da[dp++] = ZWNJ_CHAR;
|
|
635 |
break;
|
|
636 |
}
|
|
637 |
da[dp++] = HALANT_CHAR;
|
|
638 |
break;
|
|
639 |
case INVALID_CHAR:
|
|
640 |
if(needFlushing) {
|
|
641 |
if (dl - dp < 1)
|
|
642 |
return CoderResult.OVERFLOW;
|
|
643 |
da[dp++] = contextChar;
|
|
644 |
contextChar = currentChar;
|
|
645 |
sp++;
|
|
646 |
continue;
|
|
647 |
}
|
|
648 |
return CoderResult.unmappableForLength(1);
|
|
649 |
default:
|
|
650 |
if (dl - dp < 1)
|
|
651 |
return CoderResult.OVERFLOW;
|
|
652 |
if(needFlushing) {
|
|
653 |
da[dp++] = contextChar;
|
|
654 |
contextChar = currentChar;
|
|
655 |
sp++;
|
|
656 |
continue;
|
|
657 |
}
|
|
658 |
da[dp++] = currentChar;
|
|
659 |
break;
|
|
660 |
}//end switch
|
|
661 |
|
|
662 |
contextChar = currentChar;
|
|
663 |
needFlushing = false;
|
|
664 |
sp++;
|
|
665 |
}
|
|
666 |
return CoderResult.UNDERFLOW;
|
|
667 |
} finally {
|
|
668 |
src.position(sp - src.arrayOffset());
|
|
669 |
dst.position(dp - dst.arrayOffset());
|
|
670 |
}
|
|
671 |
}
|
|
672 |
|
|
673 |
private CoderResult decodeBufferLoop(ByteBuffer src,
|
|
674 |
CharBuffer dst)
|
|
675 |
{
|
|
676 |
int mark = src.position();
|
|
677 |
|
|
678 |
try {
|
|
679 |
while (src.hasRemaining()) {
|
|
680 |
int index = src.get();
|
|
681 |
index = ( index < 0 )? ( index + 255 ):index;
|
|
682 |
char currentChar = directMapTable[index];
|
|
683 |
|
|
684 |
// if the contextChar is either ATR || EXT
|
|
685 |
// set the output to '\ufffd'
|
|
686 |
if(contextChar == '\ufffd') {
|
|
687 |
if (dst.remaining() < 1)
|
|
688 |
return CoderResult.OVERFLOW;
|
|
689 |
dst.put('\ufffd');
|
|
690 |
contextChar = INVALID_CHAR;
|
|
691 |
needFlushing = false;
|
|
692 |
mark++;
|
|
693 |
continue;
|
|
694 |
}
|
|
695 |
|
|
696 |
switch(currentChar) {
|
|
697 |
case '\u0901':
|
|
698 |
case '\u0907':
|
|
699 |
case '\u0908':
|
|
700 |
case '\u090b':
|
|
701 |
case '\u093f':
|
|
702 |
case '\u0940':
|
|
703 |
case '\u0943':
|
|
704 |
case '\u0964':
|
|
705 |
if(needFlushing) {
|
|
706 |
if (dst.remaining() < 1)
|
|
707 |
return CoderResult.OVERFLOW;
|
|
708 |
dst.put(contextChar);
|
|
709 |
contextChar = currentChar;
|
|
710 |
mark++;
|
|
711 |
continue;
|
|
712 |
}
|
|
713 |
contextChar = currentChar;
|
|
714 |
needFlushing = true;
|
|
715 |
mark++;
|
|
716 |
continue;
|
|
717 |
case NUKTA_CHAR:
|
|
718 |
if (dst.remaining() < 1)
|
|
719 |
return CoderResult.OVERFLOW;
|
|
720 |
switch(contextChar) {
|
|
721 |
case '\u0901':
|
|
722 |
dst.put('\u0950');
|
|
723 |
break;
|
|
724 |
case '\u0907':
|
|
725 |
dst.put('\u090c');
|
|
726 |
break;
|
|
727 |
case '\u0908':
|
|
728 |
dst.put('\u0961');
|
|
729 |
break;
|
|
730 |
case '\u090b':
|
|
731 |
dst.put('\u0960');
|
|
732 |
break;
|
|
733 |
case '\u093f':
|
|
734 |
dst.put('\u0962');
|
|
735 |
break;
|
|
736 |
case '\u0940':
|
|
737 |
dst.put('\u0963');
|
|
738 |
break;
|
|
739 |
case '\u0943':
|
|
740 |
dst.put('\u0944');
|
|
741 |
break;
|
|
742 |
case '\u0964':
|
|
743 |
dst.put('\u093d');
|
|
744 |
break;
|
|
745 |
case HALANT_CHAR:
|
|
746 |
if(needFlushing) {
|
|
747 |
dst.put(contextChar);
|
|
748 |
contextChar = currentChar;
|
|
749 |
mark++;
|
|
750 |
continue;
|
|
751 |
}
|
|
752 |
dst.put(ZWJ_CHAR);
|
|
753 |
break;
|
|
754 |
default:
|
|
755 |
if(needFlushing) {
|
|
756 |
dst.put(contextChar);
|
|
757 |
contextChar = currentChar;
|
|
758 |
mark++;
|
|
759 |
continue;
|
|
760 |
}
|
|
761 |
dst.put(NUKTA_CHAR);
|
|
762 |
}
|
|
763 |
break;
|
|
764 |
case HALANT_CHAR:
|
|
765 |
if (dst.remaining() < 1)
|
|
766 |
return CoderResult.OVERFLOW;
|
|
767 |
if(needFlushing) {
|
|
768 |
dst.put(contextChar);
|
|
769 |
contextChar = currentChar;
|
|
770 |
mark++;
|
|
771 |
continue;
|
|
772 |
}
|
|
773 |
if(contextChar == HALANT_CHAR) {
|
|
774 |
dst.put(ZWNJ_CHAR);
|
|
775 |
break;
|
|
776 |
}
|
|
777 |
dst.put(HALANT_CHAR);
|
|
778 |
break;
|
|
779 |
case INVALID_CHAR:
|
|
780 |
if(needFlushing) {
|
|
781 |
if (dst.remaining() < 1)
|
|
782 |
return CoderResult.OVERFLOW;
|
|
783 |
dst.put(contextChar);
|
|
784 |
contextChar = currentChar;
|
|
785 |
mark++;
|
|
786 |
continue;
|
|
787 |
}
|
|
788 |
return CoderResult.unmappableForLength(1);
|
|
789 |
default:
|
|
790 |
if (dst.remaining() < 1)
|
|
791 |
return CoderResult.OVERFLOW;
|
|
792 |
if(needFlushing) {
|
|
793 |
dst.put(contextChar);
|
|
794 |
contextChar = currentChar;
|
|
795 |
mark++;
|
|
796 |
continue;
|
|
797 |
}
|
|
798 |
dst.put(currentChar);
|
|
799 |
break;
|
|
800 |
}//end switch
|
|
801 |
contextChar = currentChar;
|
|
802 |
needFlushing = false;
|
|
803 |
mark++;
|
|
804 |
}
|
|
805 |
return CoderResult.UNDERFLOW;
|
|
806 |
} finally {
|
|
807 |
src.position(mark);
|
|
808 |
}
|
|
809 |
}
|
|
810 |
|
|
811 |
protected CoderResult decodeLoop(ByteBuffer src,
|
|
812 |
CharBuffer dst)
|
|
813 |
{
|
|
814 |
if (src.hasArray() && dst.hasArray())
|
|
815 |
return decodeArrayLoop(src, dst);
|
|
816 |
else
|
|
817 |
return decodeBufferLoop(src, dst);
|
|
818 |
}
|
|
819 |
}
|
|
820 |
|
|
821 |
private static class Encoder extends CharsetEncoder {
|
|
822 |
|
|
823 |
private static final byte NO_CHAR = (byte)255;
|
|
824 |
|
|
825 |
//private static CharToByteISCII91 c2b = new CharToByteISCII91();
|
|
826 |
//private static final byte[] directMapTable = c2b.getISCIIEncoderMap();
|
|
827 |
|
|
828 |
private final Surrogate.Parser sgp = new Surrogate.Parser();
|
|
829 |
|
|
830 |
private Encoder(Charset cs) {
|
|
831 |
super(cs, 2.0f, 2.0f);
|
|
832 |
}
|
|
833 |
|
|
834 |
public boolean canEncode(char ch) {
|
|
835 |
//check for Devanagari range,ZWJ,ZWNJ and ASCII range.
|
|
836 |
return ((ch >= '\u0900' && ch <= '\u097f' &&
|
|
837 |
encoderMappingTable[2*(ch-'\u0900')] != NO_CHAR) ||
|
|
838 |
(ch == '\u200d') ||
|
|
839 |
(ch == '\u200c') ||
|
|
840 |
(ch <= '\u007f'));
|
|
841 |
}
|
|
842 |
|
|
843 |
|
|
844 |
private CoderResult encodeArrayLoop(CharBuffer src,
|
|
845 |
ByteBuffer dst)
|
|
846 |
{
|
|
847 |
char[] sa = src.array();
|
|
848 |
int sp = src.arrayOffset() + src.position();
|
|
849 |
int sl = src.arrayOffset() + src.limit();
|
|
850 |
assert (sp <= sl);
|
|
851 |
sp = (sp <= sl ? sp : sl);
|
|
852 |
byte[] da = dst.array();
|
|
853 |
int dp = dst.arrayOffset() + dst.position();
|
|
854 |
int dl = dst.arrayOffset() + dst.limit();
|
|
855 |
assert (dp <= dl);
|
|
856 |
dp = (dp <= dl ? dp : dl);
|
|
857 |
|
|
858 |
int outputSize = 0;
|
|
859 |
|
|
860 |
try {
|
|
861 |
char inputChar;
|
|
862 |
while (sp < sl) {
|
|
863 |
int index = Integer.MIN_VALUE;
|
|
864 |
inputChar = sa[sp];
|
|
865 |
|
|
866 |
if (inputChar >= 0x0000 && inputChar <= 0x007f) {
|
|
867 |
if (dl - dp < 1)
|
|
868 |
return CoderResult.OVERFLOW;
|
|
869 |
da[dp++] = (byte) inputChar;
|
|
870 |
sp++;
|
|
871 |
continue;
|
|
872 |
}
|
|
873 |
|
|
874 |
// if inputChar == ZWJ replace it with halant
|
|
875 |
// if inputChar == ZWNJ replace it with Nukta
|
|
876 |
|
|
877 |
if (inputChar == 0x200c) {
|
|
878 |
inputChar = HALANT_CHAR;
|
|
879 |
}
|
|
880 |
else if (inputChar == 0x200d) {
|
|
881 |
inputChar = NUKTA_CHAR;
|
|
882 |
}
|
|
883 |
|
|
884 |
if (inputChar >= 0x0900 && inputChar <= 0x097f) {
|
|
885 |
index = ((int)(inputChar) - 0x0900)*2;
|
|
886 |
}
|
|
887 |
|
3714
|
888 |
if (Character.isSurrogate(inputChar)) {
|
2
|
889 |
if (sgp.parse(inputChar, sa, sp, sl) < 0)
|
|
890 |
return sgp.error();
|
|
891 |
return sgp.unmappableResult();
|
|
892 |
}
|
|
893 |
|
|
894 |
if (index == Integer.MIN_VALUE ||
|
|
895 |
encoderMappingTable[index] == NO_CHAR) {
|
|
896 |
return CoderResult.unmappableForLength(1);
|
|
897 |
} else {
|
|
898 |
if(encoderMappingTable[index + 1] == NO_CHAR) {
|
|
899 |
if(dl - dp < 1)
|
|
900 |
return CoderResult.OVERFLOW;
|
|
901 |
da[dp++] = encoderMappingTable[index];
|
|
902 |
} else {
|
|
903 |
if(dl - dp < 2)
|
|
904 |
return CoderResult.OVERFLOW;
|
|
905 |
da[dp++] = encoderMappingTable[index];
|
|
906 |
da[dp++] = encoderMappingTable[index + 1];
|
|
907 |
}
|
|
908 |
sp++;
|
|
909 |
}
|
|
910 |
}
|
|
911 |
return CoderResult.UNDERFLOW;
|
|
912 |
} finally {
|
|
913 |
src.position(sp - src.arrayOffset());
|
|
914 |
dst.position(dp - dst.arrayOffset());
|
|
915 |
}
|
|
916 |
}
|
|
917 |
|
|
918 |
private CoderResult encodeBufferLoop(CharBuffer src,
|
|
919 |
ByteBuffer dst)
|
|
920 |
{
|
|
921 |
int mark = src.position();
|
|
922 |
|
|
923 |
try {
|
|
924 |
char inputChar;
|
|
925 |
while (src.hasRemaining()) {
|
|
926 |
int index = Integer.MIN_VALUE;
|
|
927 |
inputChar = src.get();
|
|
928 |
|
|
929 |
if (inputChar >= 0x0000 && inputChar <= 0x007f) {
|
|
930 |
if (dst.remaining() < 1)
|
|
931 |
return CoderResult.OVERFLOW;
|
|
932 |
dst.put((byte) inputChar);
|
|
933 |
mark++;
|
|
934 |
continue;
|
|
935 |
}
|
|
936 |
|
|
937 |
// if inputChar == ZWJ replace it with halant
|
|
938 |
// if inputChar == ZWNJ replace it with Nukta
|
|
939 |
|
|
940 |
if (inputChar == 0x200c) {
|
|
941 |
inputChar = HALANT_CHAR;
|
|
942 |
}
|
|
943 |
else if (inputChar == 0x200d) {
|
|
944 |
inputChar = NUKTA_CHAR;
|
|
945 |
}
|
|
946 |
|
|
947 |
if (inputChar >= 0x0900 && inputChar <= 0x097f) {
|
|
948 |
index = ((int)(inputChar) - 0x0900)*2;
|
|
949 |
}
|
|
950 |
|
3714
|
951 |
if (Character.isSurrogate(inputChar)) {
|
2
|
952 |
if (sgp.parse(inputChar, src) < 0)
|
|
953 |
return sgp.error();
|
|
954 |
return sgp.unmappableResult();
|
|
955 |
}
|
|
956 |
|
|
957 |
if (index == Integer.MIN_VALUE ||
|
|
958 |
encoderMappingTable[index] == NO_CHAR) {
|
|
959 |
return CoderResult.unmappableForLength(1);
|
|
960 |
} else {
|
|
961 |
if(encoderMappingTable[index + 1] == NO_CHAR) {
|
|
962 |
if(dst.remaining() < 1)
|
|
963 |
return CoderResult.OVERFLOW;
|
|
964 |
dst.put(encoderMappingTable[index]);
|
|
965 |
} else {
|
|
966 |
if(dst.remaining() < 2)
|
|
967 |
return CoderResult.OVERFLOW;
|
|
968 |
dst.put(encoderMappingTable[index]);
|
|
969 |
dst.put(encoderMappingTable[index + 1]);
|
|
970 |
}
|
|
971 |
}
|
|
972 |
mark++;
|
|
973 |
}
|
|
974 |
return CoderResult.UNDERFLOW;
|
|
975 |
} finally {
|
|
976 |
src.position(mark);
|
|
977 |
}
|
|
978 |
}
|
|
979 |
|
|
980 |
protected CoderResult encodeLoop(CharBuffer src,
|
|
981 |
ByteBuffer dst)
|
|
982 |
{
|
|
983 |
if (src.hasArray() && dst.hasArray())
|
|
984 |
return encodeArrayLoop(src, dst);
|
|
985 |
else
|
|
986 |
return encodeBufferLoop(src, dst);
|
|
987 |
}
|
|
988 |
}
|
|
989 |
}
|