source: trunk/openjdk/jdk/make/tools/GenerateCharacter/CharacterData00.java.template

Last change on this file was 278, checked in by dmik, 15 years ago

trunk: Merged in openjdk6 b22 from branches/vendor/oracle.
File size: 18.8 KB
Line 
1/*
2 * Copyright (c) 2003, 2006, 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
26package java.lang;
27
28/**
29 * The CharacterData00 class encapsulates the large tables once found in
30 * java.lang.Character
31*/
32
33class 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 = $$Lookup(offset);
73 return props;
74 }
75
76 int getType(int ch) {
77 int props = getProperties(ch);
78 return (props & $$maskType);
79 }
80
81 boolean isJavaIdentifierStart(int ch) {
82 int props = getProperties(ch);
83 return ((props & $$maskIdentifierInfo) >= $$lowJavaStart);
84 }
85
86 boolean isJavaIdentifierPart(int ch) {
87 int props = getProperties(ch);
88 return ((props & $$nonzeroJavaPart) != 0);
89 }
90
91 boolean isUnicodeIdentifierStart(int ch) {
92 int props = getProperties(ch);
93 return ((props & $$maskIdentifierInfo) == $$valueUnicodeStart);
94 }
95
96 boolean isUnicodeIdentifierPart(int ch) {
97 int props = getProperties(ch);
98 return ((props & $$maskUnicodePart) != 0);
99 }
100
101 boolean isIdentifierIgnorable(int ch) {
102 int props = getProperties(ch);
103 return ((props & $$maskIdentifierInfo) == $$valueIgnorable);
104 }
105
106 int toLowerCase(int ch) {
107 int mapChar = ch;
108 int val = getProperties(ch);
109
110 if ((val & $$maskLowerCase) != 0) {
111 if ((val & $$maskCaseOffset) == $$maskCaseOffset) {
112 switch(ch) {
113 // map the offset overflow chars
114 case 0x0130 : mapChar = 0x0069; break;
115 case 0x2126 : mapChar = 0x03C9; break;
116 case 0x212A : mapChar = 0x006B; break;
117 case 0x212B : mapChar = 0x00E5; break;
118 // map the titlecase chars with both a 1:M uppercase map
119 // and a lowercase map
120 case 0x1F88 : mapChar = 0x1F80; break;
121 case 0x1F89 : mapChar = 0x1F81; break;
122 case 0x1F8A : mapChar = 0x1F82; break;
123 case 0x1F8B : mapChar = 0x1F83; break;
124 case 0x1F8C : mapChar = 0x1F84; break;
125 case 0x1F8D : mapChar = 0x1F85; break;
126 case 0x1F8E : mapChar = 0x1F86; break;
127 case 0x1F8F : mapChar = 0x1F87; break;
128 case 0x1F98 : mapChar = 0x1F90; break;
129 case 0x1F99 : mapChar = 0x1F91; break;
130 case 0x1F9A : mapChar = 0x1F92; break;
131 case 0x1F9B : mapChar = 0x1F93; break;
132 case 0x1F9C : mapChar = 0x1F94; break;
133 case 0x1F9D : mapChar = 0x1F95; break;
134 case 0x1F9E : mapChar = 0x1F96; break;
135 case 0x1F9F : mapChar = 0x1F97; break;
136 case 0x1FA8 : mapChar = 0x1FA0; break;
137 case 0x1FA9 : mapChar = 0x1FA1; break;
138 case 0x1FAA : mapChar = 0x1FA2; break;
139 case 0x1FAB : mapChar = 0x1FA3; break;
140 case 0x1FAC : mapChar = 0x1FA4; break;
141 case 0x1FAD : mapChar = 0x1FA5; break;
142 case 0x1FAE : mapChar = 0x1FA6; break;
143 case 0x1FAF : mapChar = 0x1FA7; break;
144 case 0x1FBC : mapChar = 0x1FB3; break;
145 case 0x1FCC : mapChar = 0x1FC3; break;
146 case 0x1FFC : mapChar = 0x1FF3; break;
147 // default mapChar is already set, so no
148 // need to redo it here.
149 // default : mapChar = ch;
150 }
151 }
152 else {
153 int offset = val << $$shiftCaseOffsetSign >> ($$shiftCaseOffsetSign+$$shiftCaseOffset);
154 mapChar = ch + offset;
155 }
156 }
157 return mapChar;
158 }
159
160 int toUpperCase(int ch) {
161 int mapChar = ch;
162 int val = getProperties(ch);
163
164 if ((val & $$maskUpperCase) != 0) {
165 if ((val & $$maskCaseOffset) == $$maskCaseOffset) {
166 switch(ch) {
167 // map chars with overflow offsets
168 case 0x00B5 : mapChar = 0x039C; break;
169 case 0x017F : mapChar = 0x0053; break;
170 case 0x1FBE : mapChar = 0x0399; break;
171 // map char that have both a 1:1 and 1:M map
172 case 0x1F80 : mapChar = 0x1F88; break;
173 case 0x1F81 : mapChar = 0x1F89; break;
174 case 0x1F82 : mapChar = 0x1F8A; break;
175 case 0x1F83 : mapChar = 0x1F8B; break;
176 case 0x1F84 : mapChar = 0x1F8C; break;
177 case 0x1F85 : mapChar = 0x1F8D; break;
178 case 0x1F86 : mapChar = 0x1F8E; break;
179 case 0x1F87 : mapChar = 0x1F8F; break;
180 case 0x1F90 : mapChar = 0x1F98; break;
181 case 0x1F91 : mapChar = 0x1F99; break;
182 case 0x1F92 : mapChar = 0x1F9A; break;
183 case 0x1F93 : mapChar = 0x1F9B; break;
184 case 0x1F94 : mapChar = 0x1F9C; break;
185 case 0x1F95 : mapChar = 0x1F9D; break;
186 case 0x1F96 : mapChar = 0x1F9E; break;
187 case 0x1F97 : mapChar = 0x1F9F; break;
188 case 0x1FA0 : mapChar = 0x1FA8; break;
189 case 0x1FA1 : mapChar = 0x1FA9; break;
190 case 0x1FA2 : mapChar = 0x1FAA; break;
191 case 0x1FA3 : mapChar = 0x1FAB; break;
192 case 0x1FA4 : mapChar = 0x1FAC; break;
193 case 0x1FA5 : mapChar = 0x1FAD; break;
194 case 0x1FA6 : mapChar = 0x1FAE; break;
195 case 0x1FA7 : mapChar = 0x1FAF; break;
196 case 0x1FB3 : mapChar = 0x1FBC; break;
197 case 0x1FC3 : mapChar = 0x1FCC; break;
198 case 0x1FF3 : mapChar = 0x1FFC; break;
199 // ch must have a 1:M case mapping, but we
200 // can't handle it here. Return ch.
201 // since mapChar is already set, no need
202 // to redo it here.
203 //default : mapChar = ch;
204 }
205 }
206 else {
207 int offset = val << $$shiftCaseOffsetSign >> ($$shiftCaseOffsetSign+$$shiftCaseOffset);
208 mapChar = ch - offset;
209 }
210 }
211 return mapChar;
212 }
213
214 int toTitleCase(int ch) {
215 int mapChar = ch;
216 int val = getProperties(ch);
217
218 if ((val & $$maskTitleCase) != 0) {
219 // There is a titlecase equivalent. Perform further checks:
220 if ((val & $$maskUpperCase) == 0) {
221 // The character does not have an uppercase equivalent, so it must
222 // already be uppercase; so add 1 to get the titlecase form.
223 mapChar = ch + 1;
224 }
225 else if ((val & $$maskLowerCase) == 0) {
226 // The character does not have a lowercase equivalent, so it must
227 // already be lowercase; so subtract 1 to get the titlecase form.
228 mapChar = ch - 1;
229 }
230 // else {
231 // The character has both an uppercase equivalent and a lowercase
232 // equivalent, so it must itself be a titlecase form; return it.
233 // return ch;
234 //}
235 }
236 else if ((val & $$maskUpperCase) != 0) {
237 // This character has no titlecase equivalent but it does have an
238 // uppercase equivalent, so use that (subtract the signed case offset).
239 mapChar = toUpperCase(ch);
240 }
241 return mapChar;
242 }
243
244 int digit(int ch, int radix) {
245 int value = -1;
246 if (radix >= Character.MIN_RADIX && radix <= Character.MAX_RADIX) {
247 int val = getProperties(ch);
248 int kind = val & $$maskType;
249 if (kind == Character.DECIMAL_DIGIT_NUMBER) {
250 value = ch + ((val & $$maskDigitOffset) >> $$shiftDigitOffset) & $$maskDigit;
251 }
252 else if ((val & $$maskNumericType) == $$valueJavaSupradecimal) {
253 // Java supradecimal digit
254 value = (ch + ((val & $$maskDigitOffset) >> $$shiftDigitOffset) & $$maskDigit) + 10;
255 }
256 }
257 return (value < radix) ? value : -1;
258 }
259
260 int getNumericValue(int ch) {
261 int val = getProperties(ch);
262 int retval = -1;
263
264 switch (val & $$maskNumericType) {
265 default: // cannot occur
266 case ($$valueNotNumeric): // not numeric
267 retval = -1;
268 break;
269 case ($$valueDigit): // simple numeric
270 retval = ch + ((val & $$maskDigitOffset) >> $$shiftDigitOffset) & $$maskDigit;
271 break;
272 case ($$valueStrangeNumeric) : // "strange" numeric
273 switch (ch) {
274 case 0x0BF1: retval = 100; break; // TAMIL NUMBER ONE HUNDRED
275 case 0x0BF2: retval = 1000; break; // TAMIL NUMBER ONE THOUSAND
276 case 0x1375: retval = 40; break; // ETHIOPIC NUMBER FORTY
277 case 0x1376: retval = 50; break; // ETHIOPIC NUMBER FIFTY
278 case 0x1377: retval = 60; break; // ETHIOPIC NUMBER SIXTY
279 case 0x1378: retval = 70; break; // ETHIOPIC NUMBER SEVENTY
280 case 0x1379: retval = 80; break; // ETHIOPIC NUMBER EIGHTY
281 case 0x137A: retval = 90; break; // ETHIOPIC NUMBER NINETY
282 case 0x137B: retval = 100; break; // ETHIOPIC NUMBER HUNDRED
283 case 0x137C: retval = 10000; break; // ETHIOPIC NUMBER TEN THOUSAND
284 case 0x215F: retval = 1; break; // FRACTION NUMERATOR ONE
285 case 0x216C: retval = 50; break; // ROMAN NUMERAL FIFTY
286 case 0x216D: retval = 100; break; // ROMAN NUMERAL ONE HUNDRED
287 case 0x216E: retval = 500; break; // ROMAN NUMERAL FIVE HUNDRED
288 case 0x216F: retval = 1000; break; // ROMAN NUMERAL ONE THOUSAND
289 case 0x217C: retval = 50; break; // SMALL ROMAN NUMERAL FIFTY
290 case 0x217D: retval = 100; break; // SMALL ROMAN NUMERAL ONE HUNDRED
291 case 0x217E: retval = 500; break; // SMALL ROMAN NUMERAL FIVE HUNDRED
292 case 0x217F: retval = 1000; break; // SMALL ROMAN NUMERAL ONE THOUSAND
293 case 0x2180: retval = 1000; break; // ROMAN NUMERAL ONE THOUSAND C D
294 case 0x2181: retval = 5000; break; // ROMAN NUMERAL FIVE THOUSAND
295 case 0x2182: retval = 10000; break; // ROMAN NUMERAL TEN THOUSAND
296
297 case 0x325C: retval = 32; break;
298
299 case 0x325D: retval = 33; break; // CIRCLED NUMBER THIRTY THREE
300 case 0x325E: retval = 34; break; // CIRCLED NUMBER THIRTY FOUR
301 case 0x325F: retval = 35; break; // CIRCLED NUMBER THIRTY FIVE
302 case 0x32B1: retval = 36; break; // CIRCLED NUMBER THIRTY SIX
303 case 0x32B2: retval = 37; break; // CIRCLED NUMBER THIRTY SEVEN
304 case 0x32B3: retval = 38; break; // CIRCLED NUMBER THIRTY EIGHT
305 case 0x32B4: retval = 39; break; // CIRCLED NUMBER THIRTY NINE
306 case 0x32B5: retval = 40; break; // CIRCLED NUMBER FORTY
307 case 0x32B6: retval = 41; break; // CIRCLED NUMBER FORTY ONE
308 case 0x32B7: retval = 42; break; // CIRCLED NUMBER FORTY TWO
309 case 0x32B8: retval = 43; break; // CIRCLED NUMBER FORTY THREE
310 case 0x32B9: retval = 44; break; // CIRCLED NUMBER FORTY FOUR
311 case 0x32BA: retval = 45; break; // CIRCLED NUMBER FORTY FIVE
312 case 0x32BB: retval = 46; break; // CIRCLED NUMBER FORTY SIX
313 case 0x32BC: retval = 47; break; // CIRCLED NUMBER FORTY SEVEN
314 case 0x32BD: retval = 48; break; // CIRCLED NUMBER FORTY EIGHT
315 case 0x32BE: retval = 49; break; // CIRCLED NUMBER FORTY NINE
316 case 0x32BF: retval = 50; break; // CIRCLED NUMBER FIFTY
317
318 default: retval = -2; break;
319 }
320 break;
321 case ($$valueJavaSupradecimal): // Java supradecimal
322 retval = (ch + ((val & $$maskDigitOffset) >> $$shiftDigitOffset) & $$maskDigit) + 10;
323 break;
324 }
325 return retval;
326 }
327
328 boolean isWhitespace(int ch) {
329 int props = getProperties(ch);
330 return ((props & $$maskIdentifierInfo) == $$valueJavaWhitespace);
331 }
332
333 byte getDirectionality(int ch) {
334 int val = getProperties(ch);
335 byte directionality = (byte)((val & $$maskBidi) >> $$shiftBidi);
336 if (directionality == 0xF ) {
337 switch(ch) {
338 case 0x202A :
339 // This is the only char with LRE
340 directionality = Character.DIRECTIONALITY_LEFT_TO_RIGHT_EMBEDDING;
341 break;
342 case 0x202B :
343 // This is the only char with RLE
344 directionality = Character.DIRECTIONALITY_RIGHT_TO_LEFT_EMBEDDING;
345 break;
346 case 0x202C :
347 // This is the only char with PDF
348 directionality = Character.DIRECTIONALITY_POP_DIRECTIONAL_FORMAT;
349 break;
350 case 0x202D :
351 // This is the only char with LRO
352 directionality = Character.DIRECTIONALITY_LEFT_TO_RIGHT_OVERRIDE;
353 break;
354 case 0x202E :
355 // This is the only char with RLO
356 directionality = Character.DIRECTIONALITY_RIGHT_TO_LEFT_OVERRIDE;
357 break;
358 default :
359 directionality = Character.DIRECTIONALITY_UNDEFINED;
360 break;
361 }
362 }
363 return directionality;
364 }
365
366 boolean isMirrored(int ch) {
367 int props = getProperties(ch);
368 return ((props & $$maskMirrored) != 0);
369 }
370
371 int toUpperCaseEx(int ch) {
372 int mapChar = ch;
373 int val = getProperties(ch);
374
375 if ((val & $$maskUpperCase) != 0) {
376 if ((val & $$maskCaseOffset) != $$maskCaseOffset) {
377 int offset = val << $$shiftCaseOffsetSign >> ($$shiftCaseOffsetSign+$$shiftCaseOffset);
378 mapChar = ch - offset;
379 }
380 else {
381 switch(ch) {
382 // map overflow characters
383 case 0x00B5 : mapChar = 0x039C; break;
384 case 0x017F : mapChar = 0x0053; break;
385 case 0x1FBE : mapChar = 0x0399; break;
386 default : mapChar = Character.ERROR; break;
387 }
388 }
389 }
390 return mapChar;
391 }
392
393 char[] toUpperCaseCharArray(int ch) {
394 char[] upperMap = {(char)ch};
395 int location = findInCharMap(ch);
396 if (location != -1) {
397 upperMap = charMap[location][1];
398 }
399 return upperMap;
400 }
401
402
403 /**
404 * Finds the character in the uppercase mapping table.
405 *
406 * @param ch the <code>char</code> to search
407 * @return the index location ch in the table or -1 if not found
408 * @since 1.4
409 */
410 int findInCharMap(int ch) {
411 if (charMap == null || charMap.length == 0) {
412 return -1;
413 }
414 int top, bottom, current;
415 bottom = 0;
416 top = charMap.length;
417 current = top/2;
418 // invariant: top > current >= bottom && ch >= CharacterData.charMap[bottom][0]
419 while (top - bottom > 1) {
420 if (ch >= charMap[current][0][0]) {
421 bottom = current;
422 } else {
423 top = current;
424 }
425 current = (top + bottom) / 2;
426 }
427 if (ch == charMap[current][0][0]) return current;
428 else return -1;
429 }
430
431 static final CharacterData00 instance = new CharacterData00();
432 private CharacterData00() {};
433
434 $$Tables
435
436 static {
437 $$Initializers
438 }
439}
Note: See TracBrowser for help on using the repository browser.