1 /*
2 * Copyright (c) 2003, 2015, 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 java.lang;
27
28 /**
29 * The CharacterData00 class encapsulates the large tables once found in
30 * java.lang.Character
31 */
32
33 class CharacterData00 extends CharacterData {
34 /* The character properties are currently encoded into 32 bits in the following manner:
35 1 bit mirrored property
36 4 bits directionality property
37 9 bits signed offset used for converting case
38 1 bit if 1, adding the signed offset converts the character to lowercase
39 1 bit if 1, subtracting the signed offset converts the character to uppercase
40 1 bit if 1, this character has a titlecase equivalent (possibly itself)
41 3 bits 0 may not be part of an identifier
42 1 ignorable control; may continue a Unicode identifier or Java identifier
43 2 may continue a Java identifier but not a Unicode identifier (unused)
44 3 may continue a Unicode identifier or Java identifier
45 4 is a Java whitespace character
46 5 may start or continue a Java identifier;
47 may continue but not start a Unicode identifier (underscores)
48 6 may start or continue a Java identifier but not a Unicode identifier ($)
49 7 may start or continue a Unicode identifier or Java identifier
50 Thus:
51 5, 6, 7 may start a Java identifier
52 1, 2, 3, 5, 6, 7 may continue a Java identifier
53 7 may start a Unicode identifier
54 1, 3, 5, 7 may continue a Unicode identifier
55 1 is ignorable within an identifier
56 4 is Java whitespace
57 2 bits 0 this character has no numeric property
58 1 adding the digit offset to the character code and then
59 masking with 0x1F will produce the desired numeric value
60 2 this character has a "strange" numeric value
61 3 a Java supradecimal digit: adding the digit offset to the
62 character code, then masking with 0x1F, then adding 10
63 will produce the desired numeric value
64 5 bits digit offset
65 5 bits character type
66
67 The encoding of character properties is subject to change at any time.
68 */
69
70 int getProperties(int ch) {
71 char offset = (char)ch;
72 int props = $$Lookup(offset);
73 return props;
74 }
75
76 int getPropertiesEx(int ch) {
77 char offset = (char)ch;
78 int props = $$LookupEx(offset);
79 return props;
80 }
81
82 int getType(int ch) {
83 int props = getProperties(ch);
84 return (props & $$maskType);
85 }
86
87 boolean isOtherLowercase(int ch) {
88 int props = getPropertiesEx(ch);
89 return (props & $$maskOtherLowercase) != 0;
90 }
91
92 boolean isOtherUppercase(int ch) {
93 int props = getPropertiesEx(ch);
94 return (props & $$maskOtherUppercase) != 0;
95 }
96
97 boolean isOtherAlphabetic(int ch) {
98 int props = getPropertiesEx(ch);
99 return (props & $$maskOtherAlphabetic) != 0;
100 }
101
102 boolean isIdeographic(int ch) {
103 int props = getPropertiesEx(ch);
104 return (props & $$maskIdeographic) != 0;
105 }
106
107 boolean isJavaIdentifierStart(int ch) {
108 int props = getProperties(ch);
109 return ((props & $$maskIdentifierInfo) >= $$lowJavaStart);
110 }
111
112 boolean isJavaIdentifierPart(int ch) {
113 int props = getProperties(ch);
114 return ((props & $$nonzeroJavaPart) != 0);
115 }
116
117 boolean isUnicodeIdentifierStart(int ch) {
118 int props = getProperties(ch);
119 return ((props & $$maskIdentifierInfo) == $$valueUnicodeStart);
120 }
121
122 boolean isUnicodeIdentifierPart(int ch) {
123 int props = getProperties(ch);
124 return ((props & $$maskUnicodePart) != 0);
125 }
126
127 boolean isIdentifierIgnorable(int ch) {
128 int props = getProperties(ch);
129 return ((props & $$maskIdentifierInfo) == $$valueIgnorable);
130 }
131
132 int toLowerCase(int ch) {
133 int mapChar = ch;
134 int val = getProperties(ch);
135
136 if ((val & $$maskLowerCase) != 0) {
137 if ((val & $$maskCaseOffset) == $$maskCaseOffset) {
138 switch(ch) {
139 // map the offset overflow chars
140 case 0x0130 : mapChar = 0x0069; break;
141 case 0x2126 : mapChar = 0x03C9; break;
142 case 0x212A : mapChar = 0x006B; break;
143 case 0x212B : mapChar = 0x00E5; break;
144 // map the titlecase chars with both a 1:M uppercase map
145 // and a lowercase map
146 case 0x1F88 : mapChar = 0x1F80; break;
147 case 0x1F89 : mapChar = 0x1F81; break;
148 case 0x1F8A : mapChar = 0x1F82; break;
149 case 0x1F8B : mapChar = 0x1F83; break;
150 case 0x1F8C : mapChar = 0x1F84; break;
151 case 0x1F8D : mapChar = 0x1F85; break;
152 case 0x1F8E : mapChar = 0x1F86; break;
153 case 0x1F8F : mapChar = 0x1F87; break;
154 case 0x1F98 : mapChar = 0x1F90; break;
155 case 0x1F99 : mapChar = 0x1F91; break;
156 case 0x1F9A : mapChar = 0x1F92; break;
157 case 0x1F9B : mapChar = 0x1F93; break;
158 case 0x1F9C : mapChar = 0x1F94; break;
159 case 0x1F9D : mapChar = 0x1F95; break;
160 case 0x1F9E : mapChar = 0x1F96; break;
161 case 0x1F9F : mapChar = 0x1F97; break;
162 case 0x1FA8 : mapChar = 0x1FA0; break;
163 case 0x1FA9 : mapChar = 0x1FA1; break;
164 case 0x1FAA : mapChar = 0x1FA2; break;
165 case 0x1FAB : mapChar = 0x1FA3; break;
166 case 0x1FAC : mapChar = 0x1FA4; break;
167 case 0x1FAD : mapChar = 0x1FA5; break;
168 case 0x1FAE : mapChar = 0x1FA6; break;
169 case 0x1FAF : mapChar = 0x1FA7; break;
170 case 0x1FBC : mapChar = 0x1FB3; break;
171 case 0x1FCC : mapChar = 0x1FC3; break;
172 case 0x1FFC : mapChar = 0x1FF3; break;
173
174 case 0x023A : mapChar = 0x2C65; break;
175 case 0x023E : mapChar = 0x2C66; break;
176 case 0x10A0 : mapChar = 0x2D00; break;
177 case 0x10A1 : mapChar = 0x2D01; break;
178 case 0x10A2 : mapChar = 0x2D02; break;
179 case 0x10A3 : mapChar = 0x2D03; break;
180 case 0x10A4 : mapChar = 0x2D04; break;
181 case 0x10A5 : mapChar = 0x2D05; break;
182 case 0x10A6 : mapChar = 0x2D06; break;
183 case 0x10A7 : mapChar = 0x2D07; break;
184 case 0x10A8 : mapChar = 0x2D08; break;
185 case 0x10A9 : mapChar = 0x2D09; break;
186 case 0x10AA : mapChar = 0x2D0A; break;
187 case 0x10AB : mapChar = 0x2D0B; break;
188 case 0x10AC : mapChar = 0x2D0C; break;
189 case 0x10AD : mapChar = 0x2D0D; break;
190 case 0x10AE : mapChar = 0x2D0E; break;
191 case 0x10AF : mapChar = 0x2D0F; break;
192 case 0x10B0 : mapChar = 0x2D10; break;
193 case 0x10B1 : mapChar = 0x2D11; break;
194 case 0x10B2 : mapChar = 0x2D12; break;
195 case 0x10B3 : mapChar = 0x2D13; break;
196 case 0x10B4 : mapChar = 0x2D14; break;
197 case 0x10B5 : mapChar = 0x2D15; break;
198 case 0x10B6 : mapChar = 0x2D16; break;
199 case 0x10B7 : mapChar = 0x2D17; break;
200 case 0x10B8 : mapChar = 0x2D18; break;
201 case 0x10B9 : mapChar = 0x2D19; break;
202 case 0x10BA : mapChar = 0x2D1A; break;
203 case 0x10BB : mapChar = 0x2D1B; break;
204 case 0x10BC : mapChar = 0x2D1C; break;
205 case 0x10BD : mapChar = 0x2D1D; break;
206 case 0x10BE : mapChar = 0x2D1E; break;
207 case 0x10BF : mapChar = 0x2D1F; break;
208 case 0x10C0 : mapChar = 0x2D20; break;
209 case 0x10C1 : mapChar = 0x2D21; break;
210 case 0x10C2 : mapChar = 0x2D22; break;
211 case 0x10C3 : mapChar = 0x2D23; break;
212 case 0x10C4 : mapChar = 0x2D24; break;
213 case 0x10C5 : mapChar = 0x2D25; break;
214 case 0x10C7 : mapChar = 0x2D27; break;
215 case 0x10CD : mapChar = 0x2D2D; break;
216 case 0x1E9E : mapChar = 0x00DF; break;
217 case 0x2C62 : mapChar = 0x026B; break;
218 case 0x2C63 : mapChar = 0x1D7D; break;
219 case 0x2C64 : mapChar = 0x027D; break;
220 case 0x2C6D : mapChar = 0x0251; break;
221 case 0x2C6E : mapChar = 0x0271; break;
222 case 0x2C6F : mapChar = 0x0250; break;
223 case 0x2C70 : mapChar = 0x0252; break;
224 case 0x2C7E : mapChar = 0x023F; break;
225 case 0x2C7F : mapChar = 0x0240; break;
226 case 0xA77D : mapChar = 0x1D79; break;
227 case 0xA78D : mapChar = 0x0265; break;
228 case 0xA7AA : mapChar = 0x0266; break;
229 case 0xA7AB : mapChar = 0x025C; break;
230 case 0xA7AC : mapChar = 0x0261; break;
231 case 0xA7AD : mapChar = 0x026C; break;
232 case 0xA7B0 : mapChar = 0x029E; break;
233 case 0xA7B1 : mapChar = 0x0287; break;
234 // default mapChar is already set, so no
235 // need to redo it here.
236 // default : mapChar = ch;
237 }
238 }
239 else {
240 int offset = val << $$shiftCaseOffsetSign >> ($$shiftCaseOffsetSign+$$shiftCaseOffset);
241 mapChar = ch + offset;
242 }
243 }
244 return mapChar;
245 }
246
247 int toUpperCase(int ch) {
248 int mapChar = ch;
249 int val = getProperties(ch);
250
251 if ((val & $$maskUpperCase) != 0) {
252 if ((val & $$maskCaseOffset) == $$maskCaseOffset) {
253 switch(ch) {
254 // map chars with overflow offsets
255 case 0x00B5 : mapChar = 0x039C; break;
256 case 0x017F : mapChar = 0x0053; break;
257 case 0x1FBE : mapChar = 0x0399; break;
258 // map char that have both a 1:1 and 1:M map
259 case 0x1F80 : mapChar = 0x1F88; break;
260 case 0x1F81 : mapChar = 0x1F89; break;
261 case 0x1F82 : mapChar = 0x1F8A; break;
262 case 0x1F83 : mapChar = 0x1F8B; break;
263 case 0x1F84 : mapChar = 0x1F8C; break;
264 case 0x1F85 : mapChar = 0x1F8D; break;
265 case 0x1F86 : mapChar = 0x1F8E; break;
266 case 0x1F87 : mapChar = 0x1F8F; break;
267 case 0x1F90 : mapChar = 0x1F98; break;
268 case 0x1F91 : mapChar = 0x1F99; break;
269 case 0x1F92 : mapChar = 0x1F9A; break;
270 case 0x1F93 : mapChar = 0x1F9B; break;
271 case 0x1F94 : mapChar = 0x1F9C; break;
272 case 0x1F95 : mapChar = 0x1F9D; break;
273 case 0x1F96 : mapChar = 0x1F9E; break;
274 case 0x1F97 : mapChar = 0x1F9F; break;
275 case 0x1FA0 : mapChar = 0x1FA8; break;
276 case 0x1FA1 : mapChar = 0x1FA9; break;
277 case 0x1FA2 : mapChar = 0x1FAA; break;
278 case 0x1FA3 : mapChar = 0x1FAB; break;
279 case 0x1FA4 : mapChar = 0x1FAC; break;
280 case 0x1FA5 : mapChar = 0x1FAD; break;
281 case 0x1FA6 : mapChar = 0x1FAE; break;
282 case 0x1FA7 : mapChar = 0x1FAF; break;
283 case 0x1FB3 : mapChar = 0x1FBC; break;
284 case 0x1FC3 : mapChar = 0x1FCC; break;
285 case 0x1FF3 : mapChar = 0x1FFC; break;
286
287 case 0x023F : mapChar = 0x2C7E; break;
288 case 0x0240 : mapChar = 0x2C7F; break;
289 case 0x0250 : mapChar = 0x2C6F; break;
290 case 0x0251 : mapChar = 0x2C6D; break;
291 case 0x0252 : mapChar = 0x2C70; break;
292 case 0x025C : mapChar = 0xA7AB; break;
293 case 0x0261 : mapChar = 0xA7AC; break;
294 case 0x0265 : mapChar = 0xA78D; break;
295 case 0x0266 : mapChar = 0xA7AA; break;
296 case 0x026B : mapChar = 0x2C62; break;
297 case 0x026C : mapChar = 0xA7AD; break;
298 case 0x0271 : mapChar = 0x2C6E; break;
299 case 0x0287 : mapChar = 0xA7B1; break;
300 case 0x029E : mapChar = 0xA7B0; break;
301 case 0x027D : mapChar = 0x2C64; break;
302 case 0x1D79 : mapChar = 0xA77D; break;
303 case 0x1D7D : mapChar = 0x2C63; break;
304 case 0x2C65 : mapChar = 0x023A; break;
305 case 0x2C66 : mapChar = 0x023E; break;
306 case 0x2D00 : mapChar = 0x10A0; break;
307 case 0x2D01 : mapChar = 0x10A1; break;
308 case 0x2D02 : mapChar = 0x10A2; break;
309 case 0x2D03 : mapChar = 0x10A3; break;
310 case 0x2D04 : mapChar = 0x10A4; break;
311 case 0x2D05 : mapChar = 0x10A5; break;
312 case 0x2D06 : mapChar = 0x10A6; break;
313 case 0x2D07 : mapChar = 0x10A7; break;
314 case 0x2D08 : mapChar = 0x10A8; break;
315 case 0x2D09 : mapChar = 0x10A9; break;
316 case 0x2D0A : mapChar = 0x10AA; break;
317 case 0x2D0B : mapChar = 0x10AB; break;
318 case 0x2D0C : mapChar = 0x10AC; break;
319 case 0x2D0D : mapChar = 0x10AD; break;
320 case 0x2D0E : mapChar = 0x10AE; break;
321 case 0x2D0F : mapChar = 0x10AF; break;
322 case 0x2D10 : mapChar = 0x10B0; break;
323 case 0x2D11 : mapChar = 0x10B1; break;
324 case 0x2D12 : mapChar = 0x10B2; break;
325 case 0x2D13 : mapChar = 0x10B3; break;
326 case 0x2D14 : mapChar = 0x10B4; break;
327 case 0x2D15 : mapChar = 0x10B5; break;
328 case 0x2D16 : mapChar = 0x10B6; break;
329 case 0x2D17 : mapChar = 0x10B7; break;
330 case 0x2D18 : mapChar = 0x10B8; break;
331 case 0x2D19 : mapChar = 0x10B9; break;
332 case 0x2D1A : mapChar = 0x10BA; break;
333 case 0x2D1B : mapChar = 0x10BB; break;
334 case 0x2D1C : mapChar = 0x10BC; break;
335 case 0x2D1D : mapChar = 0x10BD; break;
336 case 0x2D1E : mapChar = 0x10BE; break;
337 case 0x2D1F : mapChar = 0x10BF; break;
338 case 0x2D20 : mapChar = 0x10C0; break;
339 case 0x2D21 : mapChar = 0x10C1; break;
340 case 0x2D22 : mapChar = 0x10C2; break;
341 case 0x2D23 : mapChar = 0x10C3; break;
342 case 0x2D24 : mapChar = 0x10C4; break;
343 case 0x2D25 : mapChar = 0x10C5; break;
344 case 0x2D27 : mapChar = 0x10C7; break;
345 case 0x2D2D : mapChar = 0x10CD; break;
346 // ch must have a 1:M case mapping, but we
347 // can't handle it here. Return ch.
348 // since mapChar is already set, no need
349 // to redo it here.
350 //default : mapChar = ch;
351 }
352 }
353 else {
354 int offset = val << $$shiftCaseOffsetSign >> ($$shiftCaseOffsetSign+$$shiftCaseOffset);
355 mapChar = ch - offset;
356 }
357 }
358 return mapChar;
359 }
360
361 int toTitleCase(int ch) {
362 int mapChar = ch;
363 int val = getProperties(ch);
364
365 if ((val & $$maskTitleCase) != 0) {
366 // There is a titlecase equivalent. Perform further checks:
367 if ((val & $$maskUpperCase) == 0) {
368 // The character does not have an uppercase equivalent, so it must
369 // already be uppercase; so add 1 to get the titlecase form.
370 mapChar = ch + 1;
371 }
372 else if ((val & $$maskLowerCase) == 0) {
373 // The character does not have a lowercase equivalent, so it must
374 // already be lowercase; so subtract 1 to get the titlecase form.
375 mapChar = ch - 1;
376 }
377 // else {
378 // The character has both an uppercase equivalent and a lowercase
379 // equivalent, so it must itself be a titlecase form; return it.
380 // return ch;
381 //}
382 }
383 else if ((val & $$maskUpperCase) != 0) {
384 // This character has no titlecase equivalent but it does have an
385 // uppercase equivalent, so use that (subtract the signed case offset).
386 mapChar = toUpperCase(ch);
387 }
388 return mapChar;
389 }
390
391 int digit(int ch, int radix) {
392 int value = -1;
393 if (radix >= Character.MIN_RADIX && radix <= Character.MAX_RADIX) {
394 int val = getProperties(ch);
395 int kind = val & $$maskType;
396 if (kind == Character.DECIMAL_DIGIT_NUMBER) {
397 value = ch + ((val & $$maskDigitOffset) >> $$shiftDigitOffset) & $$maskDigit;
398 }
399 else if ((val & $$maskNumericType) == $$valueJavaSupradecimal) {
400 // Java supradecimal digit
401 value = (ch + ((val & $$maskDigitOffset) >> $$shiftDigitOffset) & $$maskDigit) + 10;
402 }
403 }
404 return (value < radix) ? value : -1;
405 }
406
407 int getNumericValue(int ch) {
408 int val = getProperties(ch);
409 int retval = -1;
410
411 switch (val & $$maskNumericType) {
412 default: // cannot occur
413 case ($$valueNotNumeric): // not numeric
414 retval = -1;
415 break;
416 case ($$valueDigit): // simple numeric
417 retval = ch + ((val & $$maskDigitOffset) >> $$shiftDigitOffset) & $$maskDigit;
418 break;
419 case ($$valueStrangeNumeric) : // "strange" numeric
420 switch (ch) {
421 case 0x0BF1: retval = 100; break; // TAMIL NUMBER ONE HUNDRED
422 case 0x0BF2: retval = 1000; break; // TAMIL NUMBER ONE THOUSAND
423 case 0x1375: retval = 40; break; // ETHIOPIC NUMBER FORTY
424 case 0x1376: retval = 50; break; // ETHIOPIC NUMBER FIFTY
425 case 0x1377: retval = 60; break; // ETHIOPIC NUMBER SIXTY
426 case 0x1378: retval = 70; break; // ETHIOPIC NUMBER SEVENTY
427 case 0x1379: retval = 80; break; // ETHIOPIC NUMBER EIGHTY
428 case 0x137A: retval = 90; break; // ETHIOPIC NUMBER NINETY
429 case 0x137B: retval = 100; break; // ETHIOPIC NUMBER HUNDRED
430 case 0x137C: retval = 10000; break; // ETHIOPIC NUMBER TEN THOUSAND
431 case 0x215F: retval = 1; break; // FRACTION NUMERATOR ONE
432 case 0x216C: retval = 50; break; // ROMAN NUMERAL FIFTY
433 case 0x216D: retval = 100; break; // ROMAN NUMERAL ONE HUNDRED
434 case 0x216E: retval = 500; break; // ROMAN NUMERAL FIVE HUNDRED
435 case 0x216F: retval = 1000; break; // ROMAN NUMERAL ONE THOUSAND
436 case 0x217C: retval = 50; break; // SMALL ROMAN NUMERAL FIFTY
437 case 0x217D: retval = 100; break; // SMALL ROMAN NUMERAL ONE HUNDRED
438 case 0x217E: retval = 500; break; // SMALL ROMAN NUMERAL FIVE HUNDRED
439 case 0x217F: retval = 1000; break; // SMALL ROMAN NUMERAL ONE THOUSAND
440 case 0x2180: retval = 1000; break; // ROMAN NUMERAL ONE THOUSAND C D
441 case 0x2181: retval = 5000; break; // ROMAN NUMERAL FIVE THOUSAND
442 case 0x2182: retval = 10000; break; // ROMAN NUMERAL TEN THOUSAND
443
444 case 0x324B: retval = 40; break;
445 case 0x324C: retval = 50; break;
446 case 0x324D: retval = 60; break;
447 case 0x324E: retval = 70; break;
448 case 0x324F: retval = 80; break;
449 case 0x325C: retval = 32; break;
450
451 case 0x325D: retval = 33; break; // CIRCLED NUMBER THIRTY THREE
452 case 0x325E: retval = 34; break; // CIRCLED NUMBER THIRTY FOUR
453 case 0x325F: retval = 35; break; // CIRCLED NUMBER THIRTY FIVE
454 case 0x32B1: retval = 36; break; // CIRCLED NUMBER THIRTY SIX
455 case 0x32B2: retval = 37; break; // CIRCLED NUMBER THIRTY SEVEN
456 case 0x32B3: retval = 38; break; // CIRCLED NUMBER THIRTY EIGHT
457 case 0x32B4: retval = 39; break; // CIRCLED NUMBER THIRTY NINE
458 case 0x32B5: retval = 40; break; // CIRCLED NUMBER FORTY
459 case 0x32B6: retval = 41; break; // CIRCLED NUMBER FORTY ONE
460 case 0x32B7: retval = 42; break; // CIRCLED NUMBER FORTY TWO
461 case 0x32B8: retval = 43; break; // CIRCLED NUMBER FORTY THREE
462 case 0x32B9: retval = 44; break; // CIRCLED NUMBER FORTY FOUR
463 case 0x32BA: retval = 45; break; // CIRCLED NUMBER FORTY FIVE
464 case 0x32BB: retval = 46; break; // CIRCLED NUMBER FORTY SIX
465 case 0x32BC: retval = 47; break; // CIRCLED NUMBER FORTY SEVEN
466 case 0x32BD: retval = 48; break; // CIRCLED NUMBER FORTY EIGHT
467 case 0x32BE: retval = 49; break; // CIRCLED NUMBER FORTY NINE
468 case 0x32BF: retval = 50; break; // CIRCLED NUMBER FIFTY
469
470 case 0x0D71: retval = 100; break; // MALAYALAM NUMBER ONE HUNDRED
471 case 0x0D72: retval = 1000; break; // MALAYALAM NUMBER ONE THOUSAND
472 case 0x2186: retval = 50; break; // ROMAN NUMERAL FIFTY EARLY FORM
473 case 0x2187: retval = 50000; break; // ROMAN NUMERAL FIFTY THOUSAND
474 case 0x2188: retval = 100000; break; // ROMAN NUMERAL ONE HUNDRED THOUSAND
475
476 default: retval = -2; break;
477 }
478 break;
479 case ($$valueJavaSupradecimal): // Java supradecimal
480 retval = (ch + ((val & $$maskDigitOffset) >> $$shiftDigitOffset) & $$maskDigit) + 10;
481 break;
482 }
483 return retval;
484 }
485
486 boolean isWhitespace(int ch) {
487 int props = getProperties(ch);
488 return ((props & $$maskIdentifierInfo) == $$valueJavaWhitespace);
489 }
490
491 byte getDirectionality(int ch) {
492 int val = getProperties(ch);
493 byte directionality = (byte)((val & $$maskBidi) >> $$shiftBidi);
494 if (directionality == 0xF ) {
495 switch(ch) {
496 case 0x202A :
497 // This is the only char with LRE
498 directionality = Character.DIRECTIONALITY_LEFT_TO_RIGHT_EMBEDDING;
499 break;
500 case 0x202B :
501 // This is the only char with RLE
502 directionality = Character.DIRECTIONALITY_RIGHT_TO_LEFT_EMBEDDING;
503 break;
504 case 0x202C :
505 // This is the only char with PDF
506 directionality = Character.DIRECTIONALITY_POP_DIRECTIONAL_FORMAT;
507 break;
508 case 0x202D :
509 // This is the only char with LRO
510 directionality = Character.DIRECTIONALITY_LEFT_TO_RIGHT_OVERRIDE;
511 break;
512 case 0x202E :
513 // This is the only char with RLO
514 directionality = Character.DIRECTIONALITY_RIGHT_TO_LEFT_OVERRIDE;
515 break;
516 case 0x2066 :
517 // This is the only char with LRI
518 directionality = Character.DIRECTIONALITY_LEFT_TO_RIGHT_ISOLATE;
519 break;
520 case 0x2067 :
521 // This is the only char with RLI
522 directionality = Character.DIRECTIONALITY_RIGHT_TO_LEFT_ISOLATE;
523 break;
524 case 0x2068 :
525 // This is the only char with FSI
526 directionality = Character.DIRECTIONALITY_FIRST_STRONG_ISOLATE;
527 break;
528 case 0x2069 :
529 // This is the only char with PDI
530 directionality = Character.DIRECTIONALITY_POP_DIRECTIONAL_ISOLATE;
531 break;
532 default :
533 directionality = Character.DIRECTIONALITY_UNDEFINED;
534 break;
535 }
536 }
537 return directionality;
538 }
539
540 boolean isMirrored(int ch) {
541 int props = getProperties(ch);
542 return ((props & $$maskMirrored) != 0);
543 }
544
545 int toUpperCaseEx(int ch) {
546 int mapChar = ch;
547 int val = getProperties(ch);
548
549 if ((val & $$maskUpperCase) != 0) {
550 if ((val & $$maskCaseOffset) != $$maskCaseOffset) {
551 int offset = val << $$shiftCaseOffsetSign >> ($$shiftCaseOffsetSign+$$shiftCaseOffset);
552 mapChar = ch - offset;
553 }
554 else {
555 switch(ch) {
556 // map overflow characters
557 case 0x00B5 : mapChar = 0x039C; break;
558 case 0x017F : mapChar = 0x0053; break;
559 case 0x1FBE : mapChar = 0x0399; break;
560
561 case 0x023F : mapChar = 0x2C7E; break;
562 case 0x0240 : mapChar = 0x2C7F; break;
563 case 0x0250 : mapChar = 0x2C6F; break;
564 case 0x0251 : mapChar = 0x2C6D; break;
565 case 0x0252 : mapChar = 0x2C70; break;
566 case 0x025C : mapChar = 0xA7AB; break;
567 case 0x0261 : mapChar = 0xA7AC; break;
568 case 0x0265 : mapChar = 0xA78D; break;
569 case 0x0266 : mapChar = 0xA7AA; break;
570 case 0x026B : mapChar = 0x2C62; break;
571 case 0x026C : mapChar = 0xA7AD; break;
572 case 0x0271 : mapChar = 0x2C6E; break;
573 case 0x027D : mapChar = 0x2C64; break;
574 case 0x0287 : mapChar = 0xA7B1; break;
575 case 0x029E : mapChar = 0xA7B0; break;
576 case 0x1D79 : mapChar = 0xA77D; break;
577 case 0x1D7D : mapChar = 0x2C63; break;
578 case 0x2C65 : mapChar = 0x023A; break;
579 case 0x2C66 : mapChar = 0x023E; break;
580 case 0x2D00 : mapChar = 0x10A0; break;
581 case 0x2D01 : mapChar = 0x10A1; break;
582 case 0x2D02 : mapChar = 0x10A2; break;
583 case 0x2D03 : mapChar = 0x10A3; break;
584 case 0x2D04 : mapChar = 0x10A4; break;
585 case 0x2D05 : mapChar = 0x10A5; break;
586 case 0x2D06 : mapChar = 0x10A6; break;
587 case 0x2D07 : mapChar = 0x10A7; break;
588 case 0x2D08 : mapChar = 0x10A8; break;
589 case 0x2D09 : mapChar = 0x10A9; break;
590 case 0x2D0A : mapChar = 0x10AA; break;
591 case 0x2D0B : mapChar = 0x10AB; break;
592 case 0x2D0C : mapChar = 0x10AC; break;
593 case 0x2D0D : mapChar = 0x10AD; break;
594 case 0x2D0E : mapChar = 0x10AE; break;
595 case 0x2D0F : mapChar = 0x10AF; break;
596 case 0x2D10 : mapChar = 0x10B0; break;
597 case 0x2D11 : mapChar = 0x10B1; break;
598 case 0x2D12 : mapChar = 0x10B2; break;
599 case 0x2D13 : mapChar = 0x10B3; break;
600 case 0x2D14 : mapChar = 0x10B4; break;
601 case 0x2D15 : mapChar = 0x10B5; break;
602 case 0x2D16 : mapChar = 0x10B6; break;
603 case 0x2D17 : mapChar = 0x10B7; break;
604 case 0x2D18 : mapChar = 0x10B8; break;
605 case 0x2D19 : mapChar = 0x10B9; break;
606 case 0x2D1A : mapChar = 0x10BA; break;
607 case 0x2D1B : mapChar = 0x10BB; break;
608 case 0x2D1C : mapChar = 0x10BC; break;
609 case 0x2D1D : mapChar = 0x10BD; break;
610 case 0x2D1E : mapChar = 0x10BE; break;
611 case 0x2D1F : mapChar = 0x10BF; break;
612 case 0x2D20 : mapChar = 0x10C0; break;
613 case 0x2D21 : mapChar = 0x10C1; break;
614 case 0x2D22 : mapChar = 0x10C2; break;
615 case 0x2D23 : mapChar = 0x10C3; break;
616 case 0x2D24 : mapChar = 0x10C4; break;
617 case 0x2D25 : mapChar = 0x10C5; break;
618 case 0x2D27 : mapChar = 0x10C7; break;
619 case 0x2D2D : mapChar = 0x10CD; break;
620 default : mapChar = Character.ERROR; break;
621 }
622 }
623 }
624 return mapChar;
625 }
626
627 char[] toUpperCaseCharArray(int ch) {
628 char[] upperMap = {(char)ch};
629 int location = findInCharMap(ch);
630 if (location != -1) {
631 upperMap = charMap[location][1];
632 }
633 return upperMap;
634 }
635
636
637 /**
638 * Finds the character in the uppercase mapping table.
639 *
640 * @param ch the <code>char</code> to search
641 * @return the index location ch in the table or -1 if not found
642 * @since 1.4
643 */
644 int findInCharMap(int ch) {
645 if (charMap == null || charMap.length == 0) {
646 return -1;
647 }
648 int top, bottom, current;
649 bottom = 0;
650 top = charMap.length;
651 current = top/2;
652 // invariant: top > current >= bottom && ch >= CharacterData.charMap[bottom][0]
653 while (top - bottom > 1) {
654 if (ch >= charMap[current][0][0]) {
655 bottom = current;
656 } else {
657 top = current;
658 }
659 current = (top + bottom) / 2;
660 }
661 if (ch == charMap[current][0][0]) return current;
662 else return -1;
663 }
664
665 static final CharacterData00 instance = new CharacterData00();
666 private CharacterData00() {};
667
668 $$Tables
669
670 static {
671 $$Initializers
672 }
673 }