J. Duke | 319a3b9 | 2007-12-01 00:00:00 +0000 | [diff] [blame^] | 1 | /* |
| 2 | * Copyright 2003-2005 Sun Microsystems, Inc. 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. Sun designates this |
| 8 | * particular file as subject to the "Classpath" exception as provided |
| 9 | * by Sun 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 Sun Microsystems, Inc., 4150 Network Circle, Santa Clara, |
| 22 | * CA 95054 USA or visit www.sun.com if you need additional information or |
| 23 | * have any questions. |
| 24 | */ |
| 25 | |
| 26 | package java.lang; |
| 27 | |
| 28 | import java.text.BreakIterator; |
| 29 | import java.util.HashSet; |
| 30 | import java.util.Hashtable; |
| 31 | import java.util.Iterator; |
| 32 | import java.util.Locale; |
| 33 | import sun.text.Normalizer; |
| 34 | |
| 35 | |
| 36 | /** |
| 37 | * This is a utility class for <code>String.toLowerCase()</code> and |
| 38 | * <code>String.toUpperCase()</code>, that handles special casing with |
| 39 | * conditions. In other words, it handles the mappings with conditions |
| 40 | * that are defined in |
| 41 | * <a href="http://www.unicode.org/Public/UNIDATA/SpecialCasing.txt">Special |
| 42 | * Casing Properties</a> file. |
| 43 | * <p> |
| 44 | * Note that the unconditional case mappings (including 1:M mappings) |
| 45 | * are handled in <code>Character.toLower/UpperCase()</code>. |
| 46 | */ |
| 47 | final class ConditionalSpecialCasing { |
| 48 | |
| 49 | // context conditions. |
| 50 | final static int FINAL_CASED = 1; |
| 51 | final static int AFTER_SOFT_DOTTED = 2; |
| 52 | final static int MORE_ABOVE = 3; |
| 53 | final static int AFTER_I = 4; |
| 54 | final static int NOT_BEFORE_DOT = 5; |
| 55 | |
| 56 | // combining class definitions |
| 57 | final static int COMBINING_CLASS_ABOVE = 230; |
| 58 | |
| 59 | // Special case mapping entries |
| 60 | static Entry[] entry = { |
| 61 | //# ================================================================================ |
| 62 | //# Conditional mappings |
| 63 | //# ================================================================================ |
| 64 | new Entry(0x03A3, new char[]{0x03C2}, new char[]{0x03A3}, null, FINAL_CASED), // # GREEK CAPITAL LETTER SIGMA |
| 65 | |
| 66 | //# ================================================================================ |
| 67 | //# Locale-sensitive mappings |
| 68 | //# ================================================================================ |
| 69 | //# Lithuanian |
| 70 | new Entry(0x0307, new char[]{0x0307}, new char[]{}, "lt", AFTER_SOFT_DOTTED), // # COMBINING DOT ABOVE |
| 71 | new Entry(0x0049, new char[]{0x0069, 0x0307}, new char[]{0x0049}, "lt", MORE_ABOVE), // # LATIN CAPITAL LETTER I |
| 72 | new Entry(0x004A, new char[]{0x006A, 0x0307}, new char[]{0x004A}, "lt", MORE_ABOVE), // # LATIN CAPITAL LETTER J |
| 73 | new Entry(0x012E, new char[]{0x012F, 0x0307}, new char[]{0x012E}, "lt", MORE_ABOVE), // # LATIN CAPITAL LETTER I WITH OGONEK |
| 74 | new Entry(0x00CC, new char[]{0x0069, 0x0307, 0x0300}, new char[]{0x00CC}, "lt", 0), // # LATIN CAPITAL LETTER I WITH GRAVE |
| 75 | new Entry(0x00CD, new char[]{0x0069, 0x0307, 0x0301}, new char[]{0x00CD}, "lt", 0), // # LATIN CAPITAL LETTER I WITH ACUTE |
| 76 | new Entry(0x0128, new char[]{0x0069, 0x0307, 0x0303}, new char[]{0x0128}, "lt", 0), // # LATIN CAPITAL LETTER I WITH TILDE |
| 77 | |
| 78 | //# ================================================================================ |
| 79 | //# Turkish and Azeri |
| 80 | // new Entry(0x0130, new char[]{0x0069}, new char[]{0x0130}, "tr", 0), // # LATIN CAPITAL LETTER I WITH DOT ABOVE |
| 81 | // new Entry(0x0130, new char[]{0x0069}, new char[]{0x0130}, "az", 0), // # LATIN CAPITAL LETTER I WITH DOT ABOVE |
| 82 | new Entry(0x0307, new char[]{}, new char[]{0x0307}, "tr", AFTER_I), // # COMBINING DOT ABOVE |
| 83 | new Entry(0x0307, new char[]{}, new char[]{0x0307}, "az", AFTER_I), // # COMBINING DOT ABOVE |
| 84 | new Entry(0x0049, new char[]{0x0131}, new char[]{0x0049}, "tr", NOT_BEFORE_DOT), // # LATIN CAPITAL LETTER I |
| 85 | new Entry(0x0049, new char[]{0x0131}, new char[]{0x0049}, "az", NOT_BEFORE_DOT), // # LATIN CAPITAL LETTER I |
| 86 | new Entry(0x0069, new char[]{0x0069}, new char[]{0x0130}, "tr", 0), // # LATIN SMALL LETTER I |
| 87 | new Entry(0x0069, new char[]{0x0069}, new char[]{0x0130}, "az", 0) // # LATIN SMALL LETTER I |
| 88 | }; |
| 89 | |
| 90 | // A hash table that contains the above entries |
| 91 | static Hashtable entryTable = new Hashtable(); |
| 92 | static { |
| 93 | // create hashtable from the entry |
| 94 | for (int i = 0; i < entry.length; i ++) { |
| 95 | Entry cur = entry[i]; |
| 96 | Integer cp = new Integer(cur.getCodePoint()); |
| 97 | HashSet set = (HashSet)entryTable.get(cp); |
| 98 | if (set == null) { |
| 99 | set = new HashSet(); |
| 100 | } |
| 101 | set.add(cur); |
| 102 | entryTable.put(cp, set); |
| 103 | } |
| 104 | } |
| 105 | |
| 106 | static int toLowerCaseEx(String src, int index, Locale locale) { |
| 107 | char[] result = lookUpTable(src, index, locale, true); |
| 108 | |
| 109 | if (result != null) { |
| 110 | if (result.length == 1) { |
| 111 | return result[0]; |
| 112 | } else { |
| 113 | return Character.ERROR; |
| 114 | } |
| 115 | } else { |
| 116 | // default to Character class' one |
| 117 | return Character.toLowerCase(src.codePointAt(index)); |
| 118 | } |
| 119 | } |
| 120 | |
| 121 | static int toUpperCaseEx(String src, int index, Locale locale) { |
| 122 | char[] result = lookUpTable(src, index, locale, false); |
| 123 | |
| 124 | if (result != null) { |
| 125 | if (result.length == 1) { |
| 126 | return result[0]; |
| 127 | } else { |
| 128 | return Character.ERROR; |
| 129 | } |
| 130 | } else { |
| 131 | // default to Character class' one |
| 132 | return Character.toUpperCaseEx(src.codePointAt(index)); |
| 133 | } |
| 134 | } |
| 135 | |
| 136 | static char[] toLowerCaseCharArray(String src, int index, Locale locale) { |
| 137 | return lookUpTable(src, index, locale, true); |
| 138 | } |
| 139 | |
| 140 | static char[] toUpperCaseCharArray(String src, int index, Locale locale) { |
| 141 | char[] result = lookUpTable(src, index, locale, false); |
| 142 | if (result != null) { |
| 143 | return result; |
| 144 | } else { |
| 145 | return Character.toUpperCaseCharArray(src.codePointAt(index)); |
| 146 | } |
| 147 | } |
| 148 | |
| 149 | private static char[] lookUpTable(String src, int index, Locale locale, boolean bLowerCasing) { |
| 150 | HashSet set = (HashSet)entryTable.get(new Integer(src.codePointAt(index))); |
| 151 | |
| 152 | if (set != null) { |
| 153 | Iterator iter = set.iterator(); |
| 154 | String currentLang = locale.getLanguage(); |
| 155 | while (iter.hasNext()) { |
| 156 | Entry entry = (Entry)iter.next(); |
| 157 | String conditionLang= entry.getLanguage(); |
| 158 | if (((conditionLang == null) || (conditionLang.equals(currentLang))) && |
| 159 | isConditionMet(src, index, locale, entry.getCondition())) { |
| 160 | return (bLowerCasing ? entry.getLowerCase() : entry.getUpperCase()); |
| 161 | } |
| 162 | } |
| 163 | } |
| 164 | |
| 165 | return null; |
| 166 | } |
| 167 | |
| 168 | private static boolean isConditionMet(String src, int index, Locale locale, int condition) { |
| 169 | switch (condition) { |
| 170 | case FINAL_CASED: |
| 171 | return isFinalCased(src, index, locale); |
| 172 | |
| 173 | case AFTER_SOFT_DOTTED: |
| 174 | return isAfterSoftDotted(src, index); |
| 175 | |
| 176 | case MORE_ABOVE: |
| 177 | return isMoreAbove(src, index); |
| 178 | |
| 179 | case AFTER_I: |
| 180 | return isAfterI(src, index); |
| 181 | |
| 182 | case NOT_BEFORE_DOT: |
| 183 | return !isBeforeDot(src, index); |
| 184 | |
| 185 | default: |
| 186 | return true; |
| 187 | } |
| 188 | } |
| 189 | |
| 190 | /** |
| 191 | * Implements the "Final_Cased" condition |
| 192 | * |
| 193 | * Specification: Within the closest word boundaries containing C, there is a cased |
| 194 | * letter before C, and there is no cased letter after C. |
| 195 | * |
| 196 | * Regular Expression: |
| 197 | * Before C: [{cased==true}][{wordBoundary!=true}]* |
| 198 | * After C: !([{wordBoundary!=true}]*[{cased}]) |
| 199 | */ |
| 200 | private static boolean isFinalCased(String src, int index, Locale locale) { |
| 201 | BreakIterator wordBoundary = BreakIterator.getWordInstance(locale); |
| 202 | wordBoundary.setText(src); |
| 203 | int ch; |
| 204 | |
| 205 | // Look for a preceding 'cased' letter |
| 206 | for (int i = index; (i >= 0) && !wordBoundary.isBoundary(i); |
| 207 | i -= Character.charCount(ch)) { |
| 208 | |
| 209 | ch = src.codePointBefore(i); |
| 210 | if (isCased(ch)) { |
| 211 | |
| 212 | int len = src.length(); |
| 213 | // Check that there is no 'cased' letter after the index |
| 214 | for (i = index + Character.charCount(src.codePointAt(index)); |
| 215 | (i < len) && !wordBoundary.isBoundary(i); |
| 216 | i += Character.charCount(ch)) { |
| 217 | |
| 218 | ch = src.codePointAt(i); |
| 219 | if (isCased(ch)) { |
| 220 | return false; |
| 221 | } |
| 222 | } |
| 223 | |
| 224 | return true; |
| 225 | } |
| 226 | } |
| 227 | |
| 228 | return false; |
| 229 | } |
| 230 | |
| 231 | /** |
| 232 | * Implements the "After_I" condition |
| 233 | * |
| 234 | * Specification: The last preceding base character was an uppercase I, |
| 235 | * and there is no intervening combining character class 230 (ABOVE). |
| 236 | * |
| 237 | * Regular Expression: |
| 238 | * Before C: [I]([{cc!=230}&{cc!=0}])* |
| 239 | */ |
| 240 | private static boolean isAfterI(String src, int index) { |
| 241 | int ch; |
| 242 | int cc; |
| 243 | |
| 244 | // Look for the last preceding base character |
| 245 | for (int i = index; i > 0; i -= Character.charCount(ch)) { |
| 246 | |
| 247 | ch = src.codePointBefore(i); |
| 248 | |
| 249 | if (ch == 'I') { |
| 250 | return true; |
| 251 | } else { |
| 252 | cc = Normalizer.getCombiningClass(ch); |
| 253 | if ((cc == 0) || (cc == COMBINING_CLASS_ABOVE)) { |
| 254 | return false; |
| 255 | } |
| 256 | } |
| 257 | } |
| 258 | |
| 259 | return false; |
| 260 | } |
| 261 | |
| 262 | /** |
| 263 | * Implements the "After_Soft_Dotted" condition |
| 264 | * |
| 265 | * Specification: The last preceding character with combining class |
| 266 | * of zero before C was Soft_Dotted, and there is no intervening |
| 267 | * combining character class 230 (ABOVE). |
| 268 | * |
| 269 | * Regular Expression: |
| 270 | * Before C: [{Soft_Dotted==true}]([{cc!=230}&{cc!=0}])* |
| 271 | */ |
| 272 | private static boolean isAfterSoftDotted(String src, int index) { |
| 273 | int ch; |
| 274 | int cc; |
| 275 | |
| 276 | // Look for the last preceding character |
| 277 | for (int i = index; i > 0; i -= Character.charCount(ch)) { |
| 278 | |
| 279 | ch = src.codePointBefore(i); |
| 280 | |
| 281 | if (isSoftDotted(ch)) { |
| 282 | return true; |
| 283 | } else { |
| 284 | cc = Normalizer.getCombiningClass(ch); |
| 285 | if ((cc == 0) || (cc == COMBINING_CLASS_ABOVE)) { |
| 286 | return false; |
| 287 | } |
| 288 | } |
| 289 | } |
| 290 | |
| 291 | return false; |
| 292 | } |
| 293 | |
| 294 | /** |
| 295 | * Implements the "More_Above" condition |
| 296 | * |
| 297 | * Specification: C is followed by one or more characters of combining |
| 298 | * class 230 (ABOVE) in the combining character sequence. |
| 299 | * |
| 300 | * Regular Expression: |
| 301 | * After C: [{cc!=0}]*[{cc==230}] |
| 302 | */ |
| 303 | private static boolean isMoreAbove(String src, int index) { |
| 304 | int ch; |
| 305 | int cc; |
| 306 | int len = src.length(); |
| 307 | |
| 308 | // Look for a following ABOVE combining class character |
| 309 | for (int i = index + Character.charCount(src.codePointAt(index)); |
| 310 | i < len; i += Character.charCount(ch)) { |
| 311 | |
| 312 | ch = src.codePointAt(i); |
| 313 | cc = Normalizer.getCombiningClass(ch); |
| 314 | |
| 315 | if (cc == COMBINING_CLASS_ABOVE) { |
| 316 | return true; |
| 317 | } else if (cc == 0) { |
| 318 | return false; |
| 319 | } |
| 320 | } |
| 321 | |
| 322 | return false; |
| 323 | } |
| 324 | |
| 325 | /** |
| 326 | * Implements the "Before_Dot" condition |
| 327 | * |
| 328 | * Specification: C is followed by <code>U+0307 COMBINING DOT ABOVE</code>. |
| 329 | * Any sequence of characters with a combining class that is |
| 330 | * neither 0 nor 230 may intervene between the current character |
| 331 | * and the combining dot above. |
| 332 | * |
| 333 | * Regular Expression: |
| 334 | * After C: ([{cc!=230}&{cc!=0}])*[\u0307] |
| 335 | */ |
| 336 | private static boolean isBeforeDot(String src, int index) { |
| 337 | int ch; |
| 338 | int cc; |
| 339 | int len = src.length(); |
| 340 | |
| 341 | // Look for a following COMBINING DOT ABOVE |
| 342 | for (int i = index + Character.charCount(src.codePointAt(index)); |
| 343 | i < len; i += Character.charCount(ch)) { |
| 344 | |
| 345 | ch = src.codePointAt(i); |
| 346 | |
| 347 | if (ch == '\u0307') { |
| 348 | return true; |
| 349 | } else { |
| 350 | cc = Normalizer.getCombiningClass(ch); |
| 351 | if ((cc == 0) || (cc == COMBINING_CLASS_ABOVE)) { |
| 352 | return false; |
| 353 | } |
| 354 | } |
| 355 | } |
| 356 | |
| 357 | return false; |
| 358 | } |
| 359 | |
| 360 | /** |
| 361 | * Examines whether a character is 'cased'. |
| 362 | * |
| 363 | * A character C is defined to be 'cased' if and only if at least one of |
| 364 | * following are true for C: uppercase==true, or lowercase==true, or |
| 365 | * general_category==titlecase_letter. |
| 366 | * |
| 367 | * The uppercase and lowercase property values are specified in the data |
| 368 | * file DerivedCoreProperties.txt in the Unicode Character Database. |
| 369 | */ |
| 370 | private static boolean isCased(int ch) { |
| 371 | int type = Character.getType(ch); |
| 372 | if (type == Character.LOWERCASE_LETTER || |
| 373 | type == Character.UPPERCASE_LETTER || |
| 374 | type == Character.TITLECASE_LETTER) { |
| 375 | return true; |
| 376 | } else { |
| 377 | // Check for Other_Lowercase and Other_Uppercase |
| 378 | // |
| 379 | if ((ch >= 0x02B0) && (ch <= 0x02B8)) { |
| 380 | // MODIFIER LETTER SMALL H..MODIFIER LETTER SMALL Y |
| 381 | return true; |
| 382 | } else if ((ch >= 0x02C0) && (ch <= 0x02C1)) { |
| 383 | // MODIFIER LETTER GLOTTAL STOP..MODIFIER LETTER REVERSED GLOTTAL STOP |
| 384 | return true; |
| 385 | } else if ((ch >= 0x02E0) && (ch <= 0x02E4)) { |
| 386 | // MODIFIER LETTER SMALL GAMMA..MODIFIER LETTER SMALL REVERSED GLOTTAL STOP |
| 387 | return true; |
| 388 | } else if (ch == 0x0345) { |
| 389 | // COMBINING GREEK YPOGEGRAMMENI |
| 390 | return true; |
| 391 | } else if (ch == 0x037A) { |
| 392 | // GREEK YPOGEGRAMMENI |
| 393 | return true; |
| 394 | } else if ((ch >= 0x1D2C) && (ch <= 0x1D61)) { |
| 395 | // MODIFIER LETTER CAPITAL A..MODIFIER LETTER SMALL CHI |
| 396 | return true; |
| 397 | } else if ((ch >= 0x2160) && (ch <= 0x217F)) { |
| 398 | // ROMAN NUMERAL ONE..ROMAN NUMERAL ONE THOUSAND |
| 399 | // SMALL ROMAN NUMERAL ONE..SMALL ROMAN NUMERAL ONE THOUSAND |
| 400 | return true; |
| 401 | } else if ((ch >= 0x24B6) && (ch <= 0x24E9)) { |
| 402 | // CIRCLED LATIN CAPITAL LETTER A..CIRCLED LATIN CAPITAL LETTER Z |
| 403 | // CIRCLED LATIN SMALL LETTER A..CIRCLED LATIN SMALL LETTER Z |
| 404 | return true; |
| 405 | } else { |
| 406 | return false; |
| 407 | } |
| 408 | } |
| 409 | } |
| 410 | |
| 411 | private static boolean isSoftDotted(int ch) { |
| 412 | switch (ch) { |
| 413 | case 0x0069: // Soft_Dotted # L& LATIN SMALL LETTER I |
| 414 | case 0x006A: // Soft_Dotted # L& LATIN SMALL LETTER J |
| 415 | case 0x012F: // Soft_Dotted # L& LATIN SMALL LETTER I WITH OGONEK |
| 416 | case 0x0268: // Soft_Dotted # L& LATIN SMALL LETTER I WITH STROKE |
| 417 | case 0x0456: // Soft_Dotted # L& CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I |
| 418 | case 0x0458: // Soft_Dotted # L& CYRILLIC SMALL LETTER JE |
| 419 | case 0x1D62: // Soft_Dotted # L& LATIN SUBSCRIPT SMALL LETTER I |
| 420 | case 0x1E2D: // Soft_Dotted # L& LATIN SMALL LETTER I WITH TILDE BELOW |
| 421 | case 0x1ECB: // Soft_Dotted # L& LATIN SMALL LETTER I WITH DOT BELOW |
| 422 | case 0x2071: // Soft_Dotted # L& SUPERSCRIPT LATIN SMALL LETTER I |
| 423 | return true; |
| 424 | default: |
| 425 | return false; |
| 426 | } |
| 427 | } |
| 428 | |
| 429 | /** |
| 430 | * An internal class that represents an entry in the Special Casing Properties. |
| 431 | */ |
| 432 | static class Entry { |
| 433 | int ch; |
| 434 | char [] lower; |
| 435 | char [] upper; |
| 436 | String lang; |
| 437 | int condition; |
| 438 | |
| 439 | Entry(int ch, char[] lower, char[] upper, String lang, int condition) { |
| 440 | this.ch = ch; |
| 441 | this.lower = lower; |
| 442 | this.upper = upper; |
| 443 | this.lang = lang; |
| 444 | this.condition = condition; |
| 445 | } |
| 446 | |
| 447 | int getCodePoint() { |
| 448 | return ch; |
| 449 | } |
| 450 | |
| 451 | char[] getLowerCase() { |
| 452 | return lower; |
| 453 | } |
| 454 | |
| 455 | char[] getUpperCase() { |
| 456 | return upper; |
| 457 | } |
| 458 | |
| 459 | String getLanguage() { |
| 460 | return lang; |
| 461 | } |
| 462 | |
| 463 | int getCondition() { |
| 464 | return condition; |
| 465 | } |
| 466 | } |
| 467 | } |