1.1 --- a/emul/src/main/java/java/lang/Character.java Sun Sep 30 18:29:37 2012 -0700
1.2 +++ b/emul/src/main/java/java/lang/Character.java Sun Sep 30 18:40:47 2012 -0700
1.3 @@ -25,11 +25,6 @@
1.4
1.5 package java.lang;
1.6
1.7 -import java.util.Arrays;
1.8 -import java.util.Map;
1.9 -import java.util.HashMap;
1.10 -import java.util.Locale;
1.11 -
1.12 /**
1.13 * The {@code Character} class wraps a value of the primitive
1.14 * type {@code char} in an object. An object of type
1.15 @@ -171,7 +166,6 @@
1.16 *
1.17 * @since 1.1
1.18 */
1.19 - @SuppressWarnings("unchecked")
1.20 public static final Class<Character> TYPE = Class.getPrimitiveClass("char");
1.21
1.22 /*
1.23 @@ -636,3702 +630,6 @@
1.24 // See http://www.unicode.org/Public/UNIDATA/Blocks.txt
1.25 // for the latest specification of Unicode Blocks.
1.26
1.27 - /**
1.28 - * A family of character subsets representing the character blocks in the
1.29 - * Unicode specification. Character blocks generally define characters
1.30 - * used for a specific script or purpose. A character is contained by
1.31 - * at most one Unicode block.
1.32 - *
1.33 - * @since 1.2
1.34 - */
1.35 - public static final class UnicodeBlock extends Subset {
1.36 -
1.37 - private static Map<String, UnicodeBlock> map = new HashMap<>(256);
1.38 -
1.39 - /**
1.40 - * Creates a UnicodeBlock with the given identifier name.
1.41 - * This name must be the same as the block identifier.
1.42 - */
1.43 - private UnicodeBlock(String idName) {
1.44 - super(idName);
1.45 - map.put(idName, this);
1.46 - }
1.47 -
1.48 - /**
1.49 - * Creates a UnicodeBlock with the given identifier name and
1.50 - * alias name.
1.51 - */
1.52 - private UnicodeBlock(String idName, String alias) {
1.53 - this(idName);
1.54 - map.put(alias, this);
1.55 - }
1.56 -
1.57 - /**
1.58 - * Creates a UnicodeBlock with the given identifier name and
1.59 - * alias names.
1.60 - */
1.61 - private UnicodeBlock(String idName, String... aliases) {
1.62 - this(idName);
1.63 - for (String alias : aliases)
1.64 - map.put(alias, this);
1.65 - }
1.66 -
1.67 - /**
1.68 - * Constant for the "Basic Latin" Unicode character block.
1.69 - * @since 1.2
1.70 - */
1.71 - public static final UnicodeBlock BASIC_LATIN =
1.72 - new UnicodeBlock("BASIC_LATIN",
1.73 - "BASIC LATIN",
1.74 - "BASICLATIN");
1.75 -
1.76 - /**
1.77 - * Constant for the "Latin-1 Supplement" Unicode character block.
1.78 - * @since 1.2
1.79 - */
1.80 - public static final UnicodeBlock LATIN_1_SUPPLEMENT =
1.81 - new UnicodeBlock("LATIN_1_SUPPLEMENT",
1.82 - "LATIN-1 SUPPLEMENT",
1.83 - "LATIN-1SUPPLEMENT");
1.84 -
1.85 - /**
1.86 - * Constant for the "Latin Extended-A" Unicode character block.
1.87 - * @since 1.2
1.88 - */
1.89 - public static final UnicodeBlock LATIN_EXTENDED_A =
1.90 - new UnicodeBlock("LATIN_EXTENDED_A",
1.91 - "LATIN EXTENDED-A",
1.92 - "LATINEXTENDED-A");
1.93 -
1.94 - /**
1.95 - * Constant for the "Latin Extended-B" Unicode character block.
1.96 - * @since 1.2
1.97 - */
1.98 - public static final UnicodeBlock LATIN_EXTENDED_B =
1.99 - new UnicodeBlock("LATIN_EXTENDED_B",
1.100 - "LATIN EXTENDED-B",
1.101 - "LATINEXTENDED-B");
1.102 -
1.103 - /**
1.104 - * Constant for the "IPA Extensions" Unicode character block.
1.105 - * @since 1.2
1.106 - */
1.107 - public static final UnicodeBlock IPA_EXTENSIONS =
1.108 - new UnicodeBlock("IPA_EXTENSIONS",
1.109 - "IPA EXTENSIONS",
1.110 - "IPAEXTENSIONS");
1.111 -
1.112 - /**
1.113 - * Constant for the "Spacing Modifier Letters" Unicode character block.
1.114 - * @since 1.2
1.115 - */
1.116 - public static final UnicodeBlock SPACING_MODIFIER_LETTERS =
1.117 - new UnicodeBlock("SPACING_MODIFIER_LETTERS",
1.118 - "SPACING MODIFIER LETTERS",
1.119 - "SPACINGMODIFIERLETTERS");
1.120 -
1.121 - /**
1.122 - * Constant for the "Combining Diacritical Marks" Unicode character block.
1.123 - * @since 1.2
1.124 - */
1.125 - public static final UnicodeBlock COMBINING_DIACRITICAL_MARKS =
1.126 - new UnicodeBlock("COMBINING_DIACRITICAL_MARKS",
1.127 - "COMBINING DIACRITICAL MARKS",
1.128 - "COMBININGDIACRITICALMARKS");
1.129 -
1.130 - /**
1.131 - * Constant for the "Greek and Coptic" Unicode character block.
1.132 - * <p>
1.133 - * This block was previously known as the "Greek" block.
1.134 - *
1.135 - * @since 1.2
1.136 - */
1.137 - public static final UnicodeBlock GREEK =
1.138 - new UnicodeBlock("GREEK",
1.139 - "GREEK AND COPTIC",
1.140 - "GREEKANDCOPTIC");
1.141 -
1.142 - /**
1.143 - * Constant for the "Cyrillic" Unicode character block.
1.144 - * @since 1.2
1.145 - */
1.146 - public static final UnicodeBlock CYRILLIC =
1.147 - new UnicodeBlock("CYRILLIC");
1.148 -
1.149 - /**
1.150 - * Constant for the "Armenian" Unicode character block.
1.151 - * @since 1.2
1.152 - */
1.153 - public static final UnicodeBlock ARMENIAN =
1.154 - new UnicodeBlock("ARMENIAN");
1.155 -
1.156 - /**
1.157 - * Constant for the "Hebrew" Unicode character block.
1.158 - * @since 1.2
1.159 - */
1.160 - public static final UnicodeBlock HEBREW =
1.161 - new UnicodeBlock("HEBREW");
1.162 -
1.163 - /**
1.164 - * Constant for the "Arabic" Unicode character block.
1.165 - * @since 1.2
1.166 - */
1.167 - public static final UnicodeBlock ARABIC =
1.168 - new UnicodeBlock("ARABIC");
1.169 -
1.170 - /**
1.171 - * Constant for the "Devanagari" Unicode character block.
1.172 - * @since 1.2
1.173 - */
1.174 - public static final UnicodeBlock DEVANAGARI =
1.175 - new UnicodeBlock("DEVANAGARI");
1.176 -
1.177 - /**
1.178 - * Constant for the "Bengali" Unicode character block.
1.179 - * @since 1.2
1.180 - */
1.181 - public static final UnicodeBlock BENGALI =
1.182 - new UnicodeBlock("BENGALI");
1.183 -
1.184 - /**
1.185 - * Constant for the "Gurmukhi" Unicode character block.
1.186 - * @since 1.2
1.187 - */
1.188 - public static final UnicodeBlock GURMUKHI =
1.189 - new UnicodeBlock("GURMUKHI");
1.190 -
1.191 - /**
1.192 - * Constant for the "Gujarati" Unicode character block.
1.193 - * @since 1.2
1.194 - */
1.195 - public static final UnicodeBlock GUJARATI =
1.196 - new UnicodeBlock("GUJARATI");
1.197 -
1.198 - /**
1.199 - * Constant for the "Oriya" Unicode character block.
1.200 - * @since 1.2
1.201 - */
1.202 - public static final UnicodeBlock ORIYA =
1.203 - new UnicodeBlock("ORIYA");
1.204 -
1.205 - /**
1.206 - * Constant for the "Tamil" Unicode character block.
1.207 - * @since 1.2
1.208 - */
1.209 - public static final UnicodeBlock TAMIL =
1.210 - new UnicodeBlock("TAMIL");
1.211 -
1.212 - /**
1.213 - * Constant for the "Telugu" Unicode character block.
1.214 - * @since 1.2
1.215 - */
1.216 - public static final UnicodeBlock TELUGU =
1.217 - new UnicodeBlock("TELUGU");
1.218 -
1.219 - /**
1.220 - * Constant for the "Kannada" Unicode character block.
1.221 - * @since 1.2
1.222 - */
1.223 - public static final UnicodeBlock KANNADA =
1.224 - new UnicodeBlock("KANNADA");
1.225 -
1.226 - /**
1.227 - * Constant for the "Malayalam" Unicode character block.
1.228 - * @since 1.2
1.229 - */
1.230 - public static final UnicodeBlock MALAYALAM =
1.231 - new UnicodeBlock("MALAYALAM");
1.232 -
1.233 - /**
1.234 - * Constant for the "Thai" Unicode character block.
1.235 - * @since 1.2
1.236 - */
1.237 - public static final UnicodeBlock THAI =
1.238 - new UnicodeBlock("THAI");
1.239 -
1.240 - /**
1.241 - * Constant for the "Lao" Unicode character block.
1.242 - * @since 1.2
1.243 - */
1.244 - public static final UnicodeBlock LAO =
1.245 - new UnicodeBlock("LAO");
1.246 -
1.247 - /**
1.248 - * Constant for the "Tibetan" Unicode character block.
1.249 - * @since 1.2
1.250 - */
1.251 - public static final UnicodeBlock TIBETAN =
1.252 - new UnicodeBlock("TIBETAN");
1.253 -
1.254 - /**
1.255 - * Constant for the "Georgian" Unicode character block.
1.256 - * @since 1.2
1.257 - */
1.258 - public static final UnicodeBlock GEORGIAN =
1.259 - new UnicodeBlock("GEORGIAN");
1.260 -
1.261 - /**
1.262 - * Constant for the "Hangul Jamo" Unicode character block.
1.263 - * @since 1.2
1.264 - */
1.265 - public static final UnicodeBlock HANGUL_JAMO =
1.266 - new UnicodeBlock("HANGUL_JAMO",
1.267 - "HANGUL JAMO",
1.268 - "HANGULJAMO");
1.269 -
1.270 - /**
1.271 - * Constant for the "Latin Extended Additional" Unicode character block.
1.272 - * @since 1.2
1.273 - */
1.274 - public static final UnicodeBlock LATIN_EXTENDED_ADDITIONAL =
1.275 - new UnicodeBlock("LATIN_EXTENDED_ADDITIONAL",
1.276 - "LATIN EXTENDED ADDITIONAL",
1.277 - "LATINEXTENDEDADDITIONAL");
1.278 -
1.279 - /**
1.280 - * Constant for the "Greek Extended" Unicode character block.
1.281 - * @since 1.2
1.282 - */
1.283 - public static final UnicodeBlock GREEK_EXTENDED =
1.284 - new UnicodeBlock("GREEK_EXTENDED",
1.285 - "GREEK EXTENDED",
1.286 - "GREEKEXTENDED");
1.287 -
1.288 - /**
1.289 - * Constant for the "General Punctuation" Unicode character block.
1.290 - * @since 1.2
1.291 - */
1.292 - public static final UnicodeBlock GENERAL_PUNCTUATION =
1.293 - new UnicodeBlock("GENERAL_PUNCTUATION",
1.294 - "GENERAL PUNCTUATION",
1.295 - "GENERALPUNCTUATION");
1.296 -
1.297 - /**
1.298 - * Constant for the "Superscripts and Subscripts" Unicode character
1.299 - * block.
1.300 - * @since 1.2
1.301 - */
1.302 - public static final UnicodeBlock SUPERSCRIPTS_AND_SUBSCRIPTS =
1.303 - new UnicodeBlock("SUPERSCRIPTS_AND_SUBSCRIPTS",
1.304 - "SUPERSCRIPTS AND SUBSCRIPTS",
1.305 - "SUPERSCRIPTSANDSUBSCRIPTS");
1.306 -
1.307 - /**
1.308 - * Constant for the "Currency Symbols" Unicode character block.
1.309 - * @since 1.2
1.310 - */
1.311 - public static final UnicodeBlock CURRENCY_SYMBOLS =
1.312 - new UnicodeBlock("CURRENCY_SYMBOLS",
1.313 - "CURRENCY SYMBOLS",
1.314 - "CURRENCYSYMBOLS");
1.315 -
1.316 - /**
1.317 - * Constant for the "Combining Diacritical Marks for Symbols" Unicode
1.318 - * character block.
1.319 - * <p>
1.320 - * This block was previously known as "Combining Marks for Symbols".
1.321 - * @since 1.2
1.322 - */
1.323 - public static final UnicodeBlock COMBINING_MARKS_FOR_SYMBOLS =
1.324 - new UnicodeBlock("COMBINING_MARKS_FOR_SYMBOLS",
1.325 - "COMBINING DIACRITICAL MARKS FOR SYMBOLS",
1.326 - "COMBININGDIACRITICALMARKSFORSYMBOLS",
1.327 - "COMBINING MARKS FOR SYMBOLS",
1.328 - "COMBININGMARKSFORSYMBOLS");
1.329 -
1.330 - /**
1.331 - * Constant for the "Letterlike Symbols" Unicode character block.
1.332 - * @since 1.2
1.333 - */
1.334 - public static final UnicodeBlock LETTERLIKE_SYMBOLS =
1.335 - new UnicodeBlock("LETTERLIKE_SYMBOLS",
1.336 - "LETTERLIKE SYMBOLS",
1.337 - "LETTERLIKESYMBOLS");
1.338 -
1.339 - /**
1.340 - * Constant for the "Number Forms" Unicode character block.
1.341 - * @since 1.2
1.342 - */
1.343 - public static final UnicodeBlock NUMBER_FORMS =
1.344 - new UnicodeBlock("NUMBER_FORMS",
1.345 - "NUMBER FORMS",
1.346 - "NUMBERFORMS");
1.347 -
1.348 - /**
1.349 - * Constant for the "Arrows" Unicode character block.
1.350 - * @since 1.2
1.351 - */
1.352 - public static final UnicodeBlock ARROWS =
1.353 - new UnicodeBlock("ARROWS");
1.354 -
1.355 - /**
1.356 - * Constant for the "Mathematical Operators" Unicode character block.
1.357 - * @since 1.2
1.358 - */
1.359 - public static final UnicodeBlock MATHEMATICAL_OPERATORS =
1.360 - new UnicodeBlock("MATHEMATICAL_OPERATORS",
1.361 - "MATHEMATICAL OPERATORS",
1.362 - "MATHEMATICALOPERATORS");
1.363 -
1.364 - /**
1.365 - * Constant for the "Miscellaneous Technical" Unicode character block.
1.366 - * @since 1.2
1.367 - */
1.368 - public static final UnicodeBlock MISCELLANEOUS_TECHNICAL =
1.369 - new UnicodeBlock("MISCELLANEOUS_TECHNICAL",
1.370 - "MISCELLANEOUS TECHNICAL",
1.371 - "MISCELLANEOUSTECHNICAL");
1.372 -
1.373 - /**
1.374 - * Constant for the "Control Pictures" Unicode character block.
1.375 - * @since 1.2
1.376 - */
1.377 - public static final UnicodeBlock CONTROL_PICTURES =
1.378 - new UnicodeBlock("CONTROL_PICTURES",
1.379 - "CONTROL PICTURES",
1.380 - "CONTROLPICTURES");
1.381 -
1.382 - /**
1.383 - * Constant for the "Optical Character Recognition" Unicode character block.
1.384 - * @since 1.2
1.385 - */
1.386 - public static final UnicodeBlock OPTICAL_CHARACTER_RECOGNITION =
1.387 - new UnicodeBlock("OPTICAL_CHARACTER_RECOGNITION",
1.388 - "OPTICAL CHARACTER RECOGNITION",
1.389 - "OPTICALCHARACTERRECOGNITION");
1.390 -
1.391 - /**
1.392 - * Constant for the "Enclosed Alphanumerics" Unicode character block.
1.393 - * @since 1.2
1.394 - */
1.395 - public static final UnicodeBlock ENCLOSED_ALPHANUMERICS =
1.396 - new UnicodeBlock("ENCLOSED_ALPHANUMERICS",
1.397 - "ENCLOSED ALPHANUMERICS",
1.398 - "ENCLOSEDALPHANUMERICS");
1.399 -
1.400 - /**
1.401 - * Constant for the "Box Drawing" Unicode character block.
1.402 - * @since 1.2
1.403 - */
1.404 - public static final UnicodeBlock BOX_DRAWING =
1.405 - new UnicodeBlock("BOX_DRAWING",
1.406 - "BOX DRAWING",
1.407 - "BOXDRAWING");
1.408 -
1.409 - /**
1.410 - * Constant for the "Block Elements" Unicode character block.
1.411 - * @since 1.2
1.412 - */
1.413 - public static final UnicodeBlock BLOCK_ELEMENTS =
1.414 - new UnicodeBlock("BLOCK_ELEMENTS",
1.415 - "BLOCK ELEMENTS",
1.416 - "BLOCKELEMENTS");
1.417 -
1.418 - /**
1.419 - * Constant for the "Geometric Shapes" Unicode character block.
1.420 - * @since 1.2
1.421 - */
1.422 - public static final UnicodeBlock GEOMETRIC_SHAPES =
1.423 - new UnicodeBlock("GEOMETRIC_SHAPES",
1.424 - "GEOMETRIC SHAPES",
1.425 - "GEOMETRICSHAPES");
1.426 -
1.427 - /**
1.428 - * Constant for the "Miscellaneous Symbols" Unicode character block.
1.429 - * @since 1.2
1.430 - */
1.431 - public static final UnicodeBlock MISCELLANEOUS_SYMBOLS =
1.432 - new UnicodeBlock("MISCELLANEOUS_SYMBOLS",
1.433 - "MISCELLANEOUS SYMBOLS",
1.434 - "MISCELLANEOUSSYMBOLS");
1.435 -
1.436 - /**
1.437 - * Constant for the "Dingbats" Unicode character block.
1.438 - * @since 1.2
1.439 - */
1.440 - public static final UnicodeBlock DINGBATS =
1.441 - new UnicodeBlock("DINGBATS");
1.442 -
1.443 - /**
1.444 - * Constant for the "CJK Symbols and Punctuation" Unicode character block.
1.445 - * @since 1.2
1.446 - */
1.447 - public static final UnicodeBlock CJK_SYMBOLS_AND_PUNCTUATION =
1.448 - new UnicodeBlock("CJK_SYMBOLS_AND_PUNCTUATION",
1.449 - "CJK SYMBOLS AND PUNCTUATION",
1.450 - "CJKSYMBOLSANDPUNCTUATION");
1.451 -
1.452 - /**
1.453 - * Constant for the "Hiragana" Unicode character block.
1.454 - * @since 1.2
1.455 - */
1.456 - public static final UnicodeBlock HIRAGANA =
1.457 - new UnicodeBlock("HIRAGANA");
1.458 -
1.459 - /**
1.460 - * Constant for the "Katakana" Unicode character block.
1.461 - * @since 1.2
1.462 - */
1.463 - public static final UnicodeBlock KATAKANA =
1.464 - new UnicodeBlock("KATAKANA");
1.465 -
1.466 - /**
1.467 - * Constant for the "Bopomofo" Unicode character block.
1.468 - * @since 1.2
1.469 - */
1.470 - public static final UnicodeBlock BOPOMOFO =
1.471 - new UnicodeBlock("BOPOMOFO");
1.472 -
1.473 - /**
1.474 - * Constant for the "Hangul Compatibility Jamo" Unicode character block.
1.475 - * @since 1.2
1.476 - */
1.477 - public static final UnicodeBlock HANGUL_COMPATIBILITY_JAMO =
1.478 - new UnicodeBlock("HANGUL_COMPATIBILITY_JAMO",
1.479 - "HANGUL COMPATIBILITY JAMO",
1.480 - "HANGULCOMPATIBILITYJAMO");
1.481 -
1.482 - /**
1.483 - * Constant for the "Kanbun" Unicode character block.
1.484 - * @since 1.2
1.485 - */
1.486 - public static final UnicodeBlock KANBUN =
1.487 - new UnicodeBlock("KANBUN");
1.488 -
1.489 - /**
1.490 - * Constant for the "Enclosed CJK Letters and Months" Unicode character block.
1.491 - * @since 1.2
1.492 - */
1.493 - public static final UnicodeBlock ENCLOSED_CJK_LETTERS_AND_MONTHS =
1.494 - new UnicodeBlock("ENCLOSED_CJK_LETTERS_AND_MONTHS",
1.495 - "ENCLOSED CJK LETTERS AND MONTHS",
1.496 - "ENCLOSEDCJKLETTERSANDMONTHS");
1.497 -
1.498 - /**
1.499 - * Constant for the "CJK Compatibility" Unicode character block.
1.500 - * @since 1.2
1.501 - */
1.502 - public static final UnicodeBlock CJK_COMPATIBILITY =
1.503 - new UnicodeBlock("CJK_COMPATIBILITY",
1.504 - "CJK COMPATIBILITY",
1.505 - "CJKCOMPATIBILITY");
1.506 -
1.507 - /**
1.508 - * Constant for the "CJK Unified Ideographs" Unicode character block.
1.509 - * @since 1.2
1.510 - */
1.511 - public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS =
1.512 - new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS",
1.513 - "CJK UNIFIED IDEOGRAPHS",
1.514 - "CJKUNIFIEDIDEOGRAPHS");
1.515 -
1.516 - /**
1.517 - * Constant for the "Hangul Syllables" Unicode character block.
1.518 - * @since 1.2
1.519 - */
1.520 - public static final UnicodeBlock HANGUL_SYLLABLES =
1.521 - new UnicodeBlock("HANGUL_SYLLABLES",
1.522 - "HANGUL SYLLABLES",
1.523 - "HANGULSYLLABLES");
1.524 -
1.525 - /**
1.526 - * Constant for the "Private Use Area" Unicode character block.
1.527 - * @since 1.2
1.528 - */
1.529 - public static final UnicodeBlock PRIVATE_USE_AREA =
1.530 - new UnicodeBlock("PRIVATE_USE_AREA",
1.531 - "PRIVATE USE AREA",
1.532 - "PRIVATEUSEAREA");
1.533 -
1.534 - /**
1.535 - * Constant for the "CJK Compatibility Ideographs" Unicode character
1.536 - * block.
1.537 - * @since 1.2
1.538 - */
1.539 - public static final UnicodeBlock CJK_COMPATIBILITY_IDEOGRAPHS =
1.540 - new UnicodeBlock("CJK_COMPATIBILITY_IDEOGRAPHS",
1.541 - "CJK COMPATIBILITY IDEOGRAPHS",
1.542 - "CJKCOMPATIBILITYIDEOGRAPHS");
1.543 -
1.544 - /**
1.545 - * Constant for the "Alphabetic Presentation Forms" Unicode character block.
1.546 - * @since 1.2
1.547 - */
1.548 - public static final UnicodeBlock ALPHABETIC_PRESENTATION_FORMS =
1.549 - new UnicodeBlock("ALPHABETIC_PRESENTATION_FORMS",
1.550 - "ALPHABETIC PRESENTATION FORMS",
1.551 - "ALPHABETICPRESENTATIONFORMS");
1.552 -
1.553 - /**
1.554 - * Constant for the "Arabic Presentation Forms-A" Unicode character
1.555 - * block.
1.556 - * @since 1.2
1.557 - */
1.558 - public static final UnicodeBlock ARABIC_PRESENTATION_FORMS_A =
1.559 - new UnicodeBlock("ARABIC_PRESENTATION_FORMS_A",
1.560 - "ARABIC PRESENTATION FORMS-A",
1.561 - "ARABICPRESENTATIONFORMS-A");
1.562 -
1.563 - /**
1.564 - * Constant for the "Combining Half Marks" Unicode character block.
1.565 - * @since 1.2
1.566 - */
1.567 - public static final UnicodeBlock COMBINING_HALF_MARKS =
1.568 - new UnicodeBlock("COMBINING_HALF_MARKS",
1.569 - "COMBINING HALF MARKS",
1.570 - "COMBININGHALFMARKS");
1.571 -
1.572 - /**
1.573 - * Constant for the "CJK Compatibility Forms" Unicode character block.
1.574 - * @since 1.2
1.575 - */
1.576 - public static final UnicodeBlock CJK_COMPATIBILITY_FORMS =
1.577 - new UnicodeBlock("CJK_COMPATIBILITY_FORMS",
1.578 - "CJK COMPATIBILITY FORMS",
1.579 - "CJKCOMPATIBILITYFORMS");
1.580 -
1.581 - /**
1.582 - * Constant for the "Small Form Variants" Unicode character block.
1.583 - * @since 1.2
1.584 - */
1.585 - public static final UnicodeBlock SMALL_FORM_VARIANTS =
1.586 - new UnicodeBlock("SMALL_FORM_VARIANTS",
1.587 - "SMALL FORM VARIANTS",
1.588 - "SMALLFORMVARIANTS");
1.589 -
1.590 - /**
1.591 - * Constant for the "Arabic Presentation Forms-B" Unicode character block.
1.592 - * @since 1.2
1.593 - */
1.594 - public static final UnicodeBlock ARABIC_PRESENTATION_FORMS_B =
1.595 - new UnicodeBlock("ARABIC_PRESENTATION_FORMS_B",
1.596 - "ARABIC PRESENTATION FORMS-B",
1.597 - "ARABICPRESENTATIONFORMS-B");
1.598 -
1.599 - /**
1.600 - * Constant for the "Halfwidth and Fullwidth Forms" Unicode character
1.601 - * block.
1.602 - * @since 1.2
1.603 - */
1.604 - public static final UnicodeBlock HALFWIDTH_AND_FULLWIDTH_FORMS =
1.605 - new UnicodeBlock("HALFWIDTH_AND_FULLWIDTH_FORMS",
1.606 - "HALFWIDTH AND FULLWIDTH FORMS",
1.607 - "HALFWIDTHANDFULLWIDTHFORMS");
1.608 -
1.609 - /**
1.610 - * Constant for the "Specials" Unicode character block.
1.611 - * @since 1.2
1.612 - */
1.613 - public static final UnicodeBlock SPECIALS =
1.614 - new UnicodeBlock("SPECIALS");
1.615 -
1.616 - /**
1.617 - * @deprecated As of J2SE 5, use {@link #HIGH_SURROGATES},
1.618 - * {@link #HIGH_PRIVATE_USE_SURROGATES}, and
1.619 - * {@link #LOW_SURROGATES}. These new constants match
1.620 - * the block definitions of the Unicode Standard.
1.621 - * The {@link #of(char)} and {@link #of(int)} methods
1.622 - * return the new constants, not SURROGATES_AREA.
1.623 - */
1.624 - @Deprecated
1.625 - public static final UnicodeBlock SURROGATES_AREA =
1.626 - new UnicodeBlock("SURROGATES_AREA");
1.627 -
1.628 - /**
1.629 - * Constant for the "Syriac" Unicode character block.
1.630 - * @since 1.4
1.631 - */
1.632 - public static final UnicodeBlock SYRIAC =
1.633 - new UnicodeBlock("SYRIAC");
1.634 -
1.635 - /**
1.636 - * Constant for the "Thaana" Unicode character block.
1.637 - * @since 1.4
1.638 - */
1.639 - public static final UnicodeBlock THAANA =
1.640 - new UnicodeBlock("THAANA");
1.641 -
1.642 - /**
1.643 - * Constant for the "Sinhala" Unicode character block.
1.644 - * @since 1.4
1.645 - */
1.646 - public static final UnicodeBlock SINHALA =
1.647 - new UnicodeBlock("SINHALA");
1.648 -
1.649 - /**
1.650 - * Constant for the "Myanmar" Unicode character block.
1.651 - * @since 1.4
1.652 - */
1.653 - public static final UnicodeBlock MYANMAR =
1.654 - new UnicodeBlock("MYANMAR");
1.655 -
1.656 - /**
1.657 - * Constant for the "Ethiopic" Unicode character block.
1.658 - * @since 1.4
1.659 - */
1.660 - public static final UnicodeBlock ETHIOPIC =
1.661 - new UnicodeBlock("ETHIOPIC");
1.662 -
1.663 - /**
1.664 - * Constant for the "Cherokee" Unicode character block.
1.665 - * @since 1.4
1.666 - */
1.667 - public static final UnicodeBlock CHEROKEE =
1.668 - new UnicodeBlock("CHEROKEE");
1.669 -
1.670 - /**
1.671 - * Constant for the "Unified Canadian Aboriginal Syllabics" Unicode character block.
1.672 - * @since 1.4
1.673 - */
1.674 - public static final UnicodeBlock UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS =
1.675 - new UnicodeBlock("UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS",
1.676 - "UNIFIED CANADIAN ABORIGINAL SYLLABICS",
1.677 - "UNIFIEDCANADIANABORIGINALSYLLABICS");
1.678 -
1.679 - /**
1.680 - * Constant for the "Ogham" Unicode character block.
1.681 - * @since 1.4
1.682 - */
1.683 - public static final UnicodeBlock OGHAM =
1.684 - new UnicodeBlock("OGHAM");
1.685 -
1.686 - /**
1.687 - * Constant for the "Runic" Unicode character block.
1.688 - * @since 1.4
1.689 - */
1.690 - public static final UnicodeBlock RUNIC =
1.691 - new UnicodeBlock("RUNIC");
1.692 -
1.693 - /**
1.694 - * Constant for the "Khmer" Unicode character block.
1.695 - * @since 1.4
1.696 - */
1.697 - public static final UnicodeBlock KHMER =
1.698 - new UnicodeBlock("KHMER");
1.699 -
1.700 - /**
1.701 - * Constant for the "Mongolian" Unicode character block.
1.702 - * @since 1.4
1.703 - */
1.704 - public static final UnicodeBlock MONGOLIAN =
1.705 - new UnicodeBlock("MONGOLIAN");
1.706 -
1.707 - /**
1.708 - * Constant for the "Braille Patterns" Unicode character block.
1.709 - * @since 1.4
1.710 - */
1.711 - public static final UnicodeBlock BRAILLE_PATTERNS =
1.712 - new UnicodeBlock("BRAILLE_PATTERNS",
1.713 - "BRAILLE PATTERNS",
1.714 - "BRAILLEPATTERNS");
1.715 -
1.716 - /**
1.717 - * Constant for the "CJK Radicals Supplement" Unicode character block.
1.718 - * @since 1.4
1.719 - */
1.720 - public static final UnicodeBlock CJK_RADICALS_SUPPLEMENT =
1.721 - new UnicodeBlock("CJK_RADICALS_SUPPLEMENT",
1.722 - "CJK RADICALS SUPPLEMENT",
1.723 - "CJKRADICALSSUPPLEMENT");
1.724 -
1.725 - /**
1.726 - * Constant for the "Kangxi Radicals" Unicode character block.
1.727 - * @since 1.4
1.728 - */
1.729 - public static final UnicodeBlock KANGXI_RADICALS =
1.730 - new UnicodeBlock("KANGXI_RADICALS",
1.731 - "KANGXI RADICALS",
1.732 - "KANGXIRADICALS");
1.733 -
1.734 - /**
1.735 - * Constant for the "Ideographic Description Characters" Unicode character block.
1.736 - * @since 1.4
1.737 - */
1.738 - public static final UnicodeBlock IDEOGRAPHIC_DESCRIPTION_CHARACTERS =
1.739 - new UnicodeBlock("IDEOGRAPHIC_DESCRIPTION_CHARACTERS",
1.740 - "IDEOGRAPHIC DESCRIPTION CHARACTERS",
1.741 - "IDEOGRAPHICDESCRIPTIONCHARACTERS");
1.742 -
1.743 - /**
1.744 - * Constant for the "Bopomofo Extended" Unicode character block.
1.745 - * @since 1.4
1.746 - */
1.747 - public static final UnicodeBlock BOPOMOFO_EXTENDED =
1.748 - new UnicodeBlock("BOPOMOFO_EXTENDED",
1.749 - "BOPOMOFO EXTENDED",
1.750 - "BOPOMOFOEXTENDED");
1.751 -
1.752 - /**
1.753 - * Constant for the "CJK Unified Ideographs Extension A" Unicode character block.
1.754 - * @since 1.4
1.755 - */
1.756 - public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A =
1.757 - new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A",
1.758 - "CJK UNIFIED IDEOGRAPHS EXTENSION A",
1.759 - "CJKUNIFIEDIDEOGRAPHSEXTENSIONA");
1.760 -
1.761 - /**
1.762 - * Constant for the "Yi Syllables" Unicode character block.
1.763 - * @since 1.4
1.764 - */
1.765 - public static final UnicodeBlock YI_SYLLABLES =
1.766 - new UnicodeBlock("YI_SYLLABLES",
1.767 - "YI SYLLABLES",
1.768 - "YISYLLABLES");
1.769 -
1.770 - /**
1.771 - * Constant for the "Yi Radicals" Unicode character block.
1.772 - * @since 1.4
1.773 - */
1.774 - public static final UnicodeBlock YI_RADICALS =
1.775 - new UnicodeBlock("YI_RADICALS",
1.776 - "YI RADICALS",
1.777 - "YIRADICALS");
1.778 -
1.779 - /**
1.780 - * Constant for the "Cyrillic Supplementary" Unicode character block.
1.781 - * @since 1.5
1.782 - */
1.783 - public static final UnicodeBlock CYRILLIC_SUPPLEMENTARY =
1.784 - new UnicodeBlock("CYRILLIC_SUPPLEMENTARY",
1.785 - "CYRILLIC SUPPLEMENTARY",
1.786 - "CYRILLICSUPPLEMENTARY",
1.787 - "CYRILLIC SUPPLEMENT",
1.788 - "CYRILLICSUPPLEMENT");
1.789 -
1.790 - /**
1.791 - * Constant for the "Tagalog" Unicode character block.
1.792 - * @since 1.5
1.793 - */
1.794 - public static final UnicodeBlock TAGALOG =
1.795 - new UnicodeBlock("TAGALOG");
1.796 -
1.797 - /**
1.798 - * Constant for the "Hanunoo" Unicode character block.
1.799 - * @since 1.5
1.800 - */
1.801 - public static final UnicodeBlock HANUNOO =
1.802 - new UnicodeBlock("HANUNOO");
1.803 -
1.804 - /**
1.805 - * Constant for the "Buhid" Unicode character block.
1.806 - * @since 1.5
1.807 - */
1.808 - public static final UnicodeBlock BUHID =
1.809 - new UnicodeBlock("BUHID");
1.810 -
1.811 - /**
1.812 - * Constant for the "Tagbanwa" Unicode character block.
1.813 - * @since 1.5
1.814 - */
1.815 - public static final UnicodeBlock TAGBANWA =
1.816 - new UnicodeBlock("TAGBANWA");
1.817 -
1.818 - /**
1.819 - * Constant for the "Limbu" Unicode character block.
1.820 - * @since 1.5
1.821 - */
1.822 - public static final UnicodeBlock LIMBU =
1.823 - new UnicodeBlock("LIMBU");
1.824 -
1.825 - /**
1.826 - * Constant for the "Tai Le" Unicode character block.
1.827 - * @since 1.5
1.828 - */
1.829 - public static final UnicodeBlock TAI_LE =
1.830 - new UnicodeBlock("TAI_LE",
1.831 - "TAI LE",
1.832 - "TAILE");
1.833 -
1.834 - /**
1.835 - * Constant for the "Khmer Symbols" Unicode character block.
1.836 - * @since 1.5
1.837 - */
1.838 - public static final UnicodeBlock KHMER_SYMBOLS =
1.839 - new UnicodeBlock("KHMER_SYMBOLS",
1.840 - "KHMER SYMBOLS",
1.841 - "KHMERSYMBOLS");
1.842 -
1.843 - /**
1.844 - * Constant for the "Phonetic Extensions" Unicode character block.
1.845 - * @since 1.5
1.846 - */
1.847 - public static final UnicodeBlock PHONETIC_EXTENSIONS =
1.848 - new UnicodeBlock("PHONETIC_EXTENSIONS",
1.849 - "PHONETIC EXTENSIONS",
1.850 - "PHONETICEXTENSIONS");
1.851 -
1.852 - /**
1.853 - * Constant for the "Miscellaneous Mathematical Symbols-A" Unicode character block.
1.854 - * @since 1.5
1.855 - */
1.856 - public static final UnicodeBlock MISCELLANEOUS_MATHEMATICAL_SYMBOLS_A =
1.857 - new UnicodeBlock("MISCELLANEOUS_MATHEMATICAL_SYMBOLS_A",
1.858 - "MISCELLANEOUS MATHEMATICAL SYMBOLS-A",
1.859 - "MISCELLANEOUSMATHEMATICALSYMBOLS-A");
1.860 -
1.861 - /**
1.862 - * Constant for the "Supplemental Arrows-A" Unicode character block.
1.863 - * @since 1.5
1.864 - */
1.865 - public static final UnicodeBlock SUPPLEMENTAL_ARROWS_A =
1.866 - new UnicodeBlock("SUPPLEMENTAL_ARROWS_A",
1.867 - "SUPPLEMENTAL ARROWS-A",
1.868 - "SUPPLEMENTALARROWS-A");
1.869 -
1.870 - /**
1.871 - * Constant for the "Supplemental Arrows-B" Unicode character block.
1.872 - * @since 1.5
1.873 - */
1.874 - public static final UnicodeBlock SUPPLEMENTAL_ARROWS_B =
1.875 - new UnicodeBlock("SUPPLEMENTAL_ARROWS_B",
1.876 - "SUPPLEMENTAL ARROWS-B",
1.877 - "SUPPLEMENTALARROWS-B");
1.878 -
1.879 - /**
1.880 - * Constant for the "Miscellaneous Mathematical Symbols-B" Unicode
1.881 - * character block.
1.882 - * @since 1.5
1.883 - */
1.884 - public static final UnicodeBlock MISCELLANEOUS_MATHEMATICAL_SYMBOLS_B =
1.885 - new UnicodeBlock("MISCELLANEOUS_MATHEMATICAL_SYMBOLS_B",
1.886 - "MISCELLANEOUS MATHEMATICAL SYMBOLS-B",
1.887 - "MISCELLANEOUSMATHEMATICALSYMBOLS-B");
1.888 -
1.889 - /**
1.890 - * Constant for the "Supplemental Mathematical Operators" Unicode
1.891 - * character block.
1.892 - * @since 1.5
1.893 - */
1.894 - public static final UnicodeBlock SUPPLEMENTAL_MATHEMATICAL_OPERATORS =
1.895 - new UnicodeBlock("SUPPLEMENTAL_MATHEMATICAL_OPERATORS",
1.896 - "SUPPLEMENTAL MATHEMATICAL OPERATORS",
1.897 - "SUPPLEMENTALMATHEMATICALOPERATORS");
1.898 -
1.899 - /**
1.900 - * Constant for the "Miscellaneous Symbols and Arrows" Unicode character
1.901 - * block.
1.902 - * @since 1.5
1.903 - */
1.904 - public static final UnicodeBlock MISCELLANEOUS_SYMBOLS_AND_ARROWS =
1.905 - new UnicodeBlock("MISCELLANEOUS_SYMBOLS_AND_ARROWS",
1.906 - "MISCELLANEOUS SYMBOLS AND ARROWS",
1.907 - "MISCELLANEOUSSYMBOLSANDARROWS");
1.908 -
1.909 - /**
1.910 - * Constant for the "Katakana Phonetic Extensions" Unicode character
1.911 - * block.
1.912 - * @since 1.5
1.913 - */
1.914 - public static final UnicodeBlock KATAKANA_PHONETIC_EXTENSIONS =
1.915 - new UnicodeBlock("KATAKANA_PHONETIC_EXTENSIONS",
1.916 - "KATAKANA PHONETIC EXTENSIONS",
1.917 - "KATAKANAPHONETICEXTENSIONS");
1.918 -
1.919 - /**
1.920 - * Constant for the "Yijing Hexagram Symbols" Unicode character block.
1.921 - * @since 1.5
1.922 - */
1.923 - public static final UnicodeBlock YIJING_HEXAGRAM_SYMBOLS =
1.924 - new UnicodeBlock("YIJING_HEXAGRAM_SYMBOLS",
1.925 - "YIJING HEXAGRAM SYMBOLS",
1.926 - "YIJINGHEXAGRAMSYMBOLS");
1.927 -
1.928 - /**
1.929 - * Constant for the "Variation Selectors" Unicode character block.
1.930 - * @since 1.5
1.931 - */
1.932 - public static final UnicodeBlock VARIATION_SELECTORS =
1.933 - new UnicodeBlock("VARIATION_SELECTORS",
1.934 - "VARIATION SELECTORS",
1.935 - "VARIATIONSELECTORS");
1.936 -
1.937 - /**
1.938 - * Constant for the "Linear B Syllabary" Unicode character block.
1.939 - * @since 1.5
1.940 - */
1.941 - public static final UnicodeBlock LINEAR_B_SYLLABARY =
1.942 - new UnicodeBlock("LINEAR_B_SYLLABARY",
1.943 - "LINEAR B SYLLABARY",
1.944 - "LINEARBSYLLABARY");
1.945 -
1.946 - /**
1.947 - * Constant for the "Linear B Ideograms" Unicode character block.
1.948 - * @since 1.5
1.949 - */
1.950 - public static final UnicodeBlock LINEAR_B_IDEOGRAMS =
1.951 - new UnicodeBlock("LINEAR_B_IDEOGRAMS",
1.952 - "LINEAR B IDEOGRAMS",
1.953 - "LINEARBIDEOGRAMS");
1.954 -
1.955 - /**
1.956 - * Constant for the "Aegean Numbers" Unicode character block.
1.957 - * @since 1.5
1.958 - */
1.959 - public static final UnicodeBlock AEGEAN_NUMBERS =
1.960 - new UnicodeBlock("AEGEAN_NUMBERS",
1.961 - "AEGEAN NUMBERS",
1.962 - "AEGEANNUMBERS");
1.963 -
1.964 - /**
1.965 - * Constant for the "Old Italic" Unicode character block.
1.966 - * @since 1.5
1.967 - */
1.968 - public static final UnicodeBlock OLD_ITALIC =
1.969 - new UnicodeBlock("OLD_ITALIC",
1.970 - "OLD ITALIC",
1.971 - "OLDITALIC");
1.972 -
1.973 - /**
1.974 - * Constant for the "Gothic" Unicode character block.
1.975 - * @since 1.5
1.976 - */
1.977 - public static final UnicodeBlock GOTHIC =
1.978 - new UnicodeBlock("GOTHIC");
1.979 -
1.980 - /**
1.981 - * Constant for the "Ugaritic" Unicode character block.
1.982 - * @since 1.5
1.983 - */
1.984 - public static final UnicodeBlock UGARITIC =
1.985 - new UnicodeBlock("UGARITIC");
1.986 -
1.987 - /**
1.988 - * Constant for the "Deseret" Unicode character block.
1.989 - * @since 1.5
1.990 - */
1.991 - public static final UnicodeBlock DESERET =
1.992 - new UnicodeBlock("DESERET");
1.993 -
1.994 - /**
1.995 - * Constant for the "Shavian" Unicode character block.
1.996 - * @since 1.5
1.997 - */
1.998 - public static final UnicodeBlock SHAVIAN =
1.999 - new UnicodeBlock("SHAVIAN");
1.1000 -
1.1001 - /**
1.1002 - * Constant for the "Osmanya" Unicode character block.
1.1003 - * @since 1.5
1.1004 - */
1.1005 - public static final UnicodeBlock OSMANYA =
1.1006 - new UnicodeBlock("OSMANYA");
1.1007 -
1.1008 - /**
1.1009 - * Constant for the "Cypriot Syllabary" Unicode character block.
1.1010 - * @since 1.5
1.1011 - */
1.1012 - public static final UnicodeBlock CYPRIOT_SYLLABARY =
1.1013 - new UnicodeBlock("CYPRIOT_SYLLABARY",
1.1014 - "CYPRIOT SYLLABARY",
1.1015 - "CYPRIOTSYLLABARY");
1.1016 -
1.1017 - /**
1.1018 - * Constant for the "Byzantine Musical Symbols" Unicode character block.
1.1019 - * @since 1.5
1.1020 - */
1.1021 - public static final UnicodeBlock BYZANTINE_MUSICAL_SYMBOLS =
1.1022 - new UnicodeBlock("BYZANTINE_MUSICAL_SYMBOLS",
1.1023 - "BYZANTINE MUSICAL SYMBOLS",
1.1024 - "BYZANTINEMUSICALSYMBOLS");
1.1025 -
1.1026 - /**
1.1027 - * Constant for the "Musical Symbols" Unicode character block.
1.1028 - * @since 1.5
1.1029 - */
1.1030 - public static final UnicodeBlock MUSICAL_SYMBOLS =
1.1031 - new UnicodeBlock("MUSICAL_SYMBOLS",
1.1032 - "MUSICAL SYMBOLS",
1.1033 - "MUSICALSYMBOLS");
1.1034 -
1.1035 - /**
1.1036 - * Constant for the "Tai Xuan Jing Symbols" Unicode character block.
1.1037 - * @since 1.5
1.1038 - */
1.1039 - public static final UnicodeBlock TAI_XUAN_JING_SYMBOLS =
1.1040 - new UnicodeBlock("TAI_XUAN_JING_SYMBOLS",
1.1041 - "TAI XUAN JING SYMBOLS",
1.1042 - "TAIXUANJINGSYMBOLS");
1.1043 -
1.1044 - /**
1.1045 - * Constant for the "Mathematical Alphanumeric Symbols" Unicode
1.1046 - * character block.
1.1047 - * @since 1.5
1.1048 - */
1.1049 - public static final UnicodeBlock MATHEMATICAL_ALPHANUMERIC_SYMBOLS =
1.1050 - new UnicodeBlock("MATHEMATICAL_ALPHANUMERIC_SYMBOLS",
1.1051 - "MATHEMATICAL ALPHANUMERIC SYMBOLS",
1.1052 - "MATHEMATICALALPHANUMERICSYMBOLS");
1.1053 -
1.1054 - /**
1.1055 - * Constant for the "CJK Unified Ideographs Extension B" Unicode
1.1056 - * character block.
1.1057 - * @since 1.5
1.1058 - */
1.1059 - public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_B =
1.1060 - new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_B",
1.1061 - "CJK UNIFIED IDEOGRAPHS EXTENSION B",
1.1062 - "CJKUNIFIEDIDEOGRAPHSEXTENSIONB");
1.1063 -
1.1064 - /**
1.1065 - * Constant for the "CJK Compatibility Ideographs Supplement" Unicode character block.
1.1066 - * @since 1.5
1.1067 - */
1.1068 - public static final UnicodeBlock CJK_COMPATIBILITY_IDEOGRAPHS_SUPPLEMENT =
1.1069 - new UnicodeBlock("CJK_COMPATIBILITY_IDEOGRAPHS_SUPPLEMENT",
1.1070 - "CJK COMPATIBILITY IDEOGRAPHS SUPPLEMENT",
1.1071 - "CJKCOMPATIBILITYIDEOGRAPHSSUPPLEMENT");
1.1072 -
1.1073 - /**
1.1074 - * Constant for the "Tags" Unicode character block.
1.1075 - * @since 1.5
1.1076 - */
1.1077 - public static final UnicodeBlock TAGS =
1.1078 - new UnicodeBlock("TAGS");
1.1079 -
1.1080 - /**
1.1081 - * Constant for the "Variation Selectors Supplement" Unicode character
1.1082 - * block.
1.1083 - * @since 1.5
1.1084 - */
1.1085 - public static final UnicodeBlock VARIATION_SELECTORS_SUPPLEMENT =
1.1086 - new UnicodeBlock("VARIATION_SELECTORS_SUPPLEMENT",
1.1087 - "VARIATION SELECTORS SUPPLEMENT",
1.1088 - "VARIATIONSELECTORSSUPPLEMENT");
1.1089 -
1.1090 - /**
1.1091 - * Constant for the "Supplementary Private Use Area-A" Unicode character
1.1092 - * block.
1.1093 - * @since 1.5
1.1094 - */
1.1095 - public static final UnicodeBlock SUPPLEMENTARY_PRIVATE_USE_AREA_A =
1.1096 - new UnicodeBlock("SUPPLEMENTARY_PRIVATE_USE_AREA_A",
1.1097 - "SUPPLEMENTARY PRIVATE USE AREA-A",
1.1098 - "SUPPLEMENTARYPRIVATEUSEAREA-A");
1.1099 -
1.1100 - /**
1.1101 - * Constant for the "Supplementary Private Use Area-B" Unicode character
1.1102 - * block.
1.1103 - * @since 1.5
1.1104 - */
1.1105 - public static final UnicodeBlock SUPPLEMENTARY_PRIVATE_USE_AREA_B =
1.1106 - new UnicodeBlock("SUPPLEMENTARY_PRIVATE_USE_AREA_B",
1.1107 - "SUPPLEMENTARY PRIVATE USE AREA-B",
1.1108 - "SUPPLEMENTARYPRIVATEUSEAREA-B");
1.1109 -
1.1110 - /**
1.1111 - * Constant for the "High Surrogates" Unicode character block.
1.1112 - * This block represents codepoint values in the high surrogate
1.1113 - * range: U+D800 through U+DB7F
1.1114 - *
1.1115 - * @since 1.5
1.1116 - */
1.1117 - public static final UnicodeBlock HIGH_SURROGATES =
1.1118 - new UnicodeBlock("HIGH_SURROGATES",
1.1119 - "HIGH SURROGATES",
1.1120 - "HIGHSURROGATES");
1.1121 -
1.1122 - /**
1.1123 - * Constant for the "High Private Use Surrogates" Unicode character
1.1124 - * block.
1.1125 - * This block represents codepoint values in the private use high
1.1126 - * surrogate range: U+DB80 through U+DBFF
1.1127 - *
1.1128 - * @since 1.5
1.1129 - */
1.1130 - public static final UnicodeBlock HIGH_PRIVATE_USE_SURROGATES =
1.1131 - new UnicodeBlock("HIGH_PRIVATE_USE_SURROGATES",
1.1132 - "HIGH PRIVATE USE SURROGATES",
1.1133 - "HIGHPRIVATEUSESURROGATES");
1.1134 -
1.1135 - /**
1.1136 - * Constant for the "Low Surrogates" Unicode character block.
1.1137 - * This block represents codepoint values in the low surrogate
1.1138 - * range: U+DC00 through U+DFFF
1.1139 - *
1.1140 - * @since 1.5
1.1141 - */
1.1142 - public static final UnicodeBlock LOW_SURROGATES =
1.1143 - new UnicodeBlock("LOW_SURROGATES",
1.1144 - "LOW SURROGATES",
1.1145 - "LOWSURROGATES");
1.1146 -
1.1147 - /**
1.1148 - * Constant for the "Arabic Supplement" Unicode character block.
1.1149 - * @since 1.7
1.1150 - */
1.1151 - public static final UnicodeBlock ARABIC_SUPPLEMENT =
1.1152 - new UnicodeBlock("ARABIC_SUPPLEMENT",
1.1153 - "ARABIC SUPPLEMENT",
1.1154 - "ARABICSUPPLEMENT");
1.1155 -
1.1156 - /**
1.1157 - * Constant for the "NKo" Unicode character block.
1.1158 - * @since 1.7
1.1159 - */
1.1160 - public static final UnicodeBlock NKO =
1.1161 - new UnicodeBlock("NKO");
1.1162 -
1.1163 - /**
1.1164 - * Constant for the "Samaritan" Unicode character block.
1.1165 - * @since 1.7
1.1166 - */
1.1167 - public static final UnicodeBlock SAMARITAN =
1.1168 - new UnicodeBlock("SAMARITAN");
1.1169 -
1.1170 - /**
1.1171 - * Constant for the "Mandaic" Unicode character block.
1.1172 - * @since 1.7
1.1173 - */
1.1174 - public static final UnicodeBlock MANDAIC =
1.1175 - new UnicodeBlock("MANDAIC");
1.1176 -
1.1177 - /**
1.1178 - * Constant for the "Ethiopic Supplement" Unicode character block.
1.1179 - * @since 1.7
1.1180 - */
1.1181 - public static final UnicodeBlock ETHIOPIC_SUPPLEMENT =
1.1182 - new UnicodeBlock("ETHIOPIC_SUPPLEMENT",
1.1183 - "ETHIOPIC SUPPLEMENT",
1.1184 - "ETHIOPICSUPPLEMENT");
1.1185 -
1.1186 - /**
1.1187 - * Constant for the "Unified Canadian Aboriginal Syllabics Extended"
1.1188 - * Unicode character block.
1.1189 - * @since 1.7
1.1190 - */
1.1191 - public static final UnicodeBlock UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED =
1.1192 - new UnicodeBlock("UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED",
1.1193 - "UNIFIED CANADIAN ABORIGINAL SYLLABICS EXTENDED",
1.1194 - "UNIFIEDCANADIANABORIGINALSYLLABICSEXTENDED");
1.1195 -
1.1196 - /**
1.1197 - * Constant for the "New Tai Lue" Unicode character block.
1.1198 - * @since 1.7
1.1199 - */
1.1200 - public static final UnicodeBlock NEW_TAI_LUE =
1.1201 - new UnicodeBlock("NEW_TAI_LUE",
1.1202 - "NEW TAI LUE",
1.1203 - "NEWTAILUE");
1.1204 -
1.1205 - /**
1.1206 - * Constant for the "Buginese" Unicode character block.
1.1207 - * @since 1.7
1.1208 - */
1.1209 - public static final UnicodeBlock BUGINESE =
1.1210 - new UnicodeBlock("BUGINESE");
1.1211 -
1.1212 - /**
1.1213 - * Constant for the "Tai Tham" Unicode character block.
1.1214 - * @since 1.7
1.1215 - */
1.1216 - public static final UnicodeBlock TAI_THAM =
1.1217 - new UnicodeBlock("TAI_THAM",
1.1218 - "TAI THAM",
1.1219 - "TAITHAM");
1.1220 -
1.1221 - /**
1.1222 - * Constant for the "Balinese" Unicode character block.
1.1223 - * @since 1.7
1.1224 - */
1.1225 - public static final UnicodeBlock BALINESE =
1.1226 - new UnicodeBlock("BALINESE");
1.1227 -
1.1228 - /**
1.1229 - * Constant for the "Sundanese" Unicode character block.
1.1230 - * @since 1.7
1.1231 - */
1.1232 - public static final UnicodeBlock SUNDANESE =
1.1233 - new UnicodeBlock("SUNDANESE");
1.1234 -
1.1235 - /**
1.1236 - * Constant for the "Batak" Unicode character block.
1.1237 - * @since 1.7
1.1238 - */
1.1239 - public static final UnicodeBlock BATAK =
1.1240 - new UnicodeBlock("BATAK");
1.1241 -
1.1242 - /**
1.1243 - * Constant for the "Lepcha" Unicode character block.
1.1244 - * @since 1.7
1.1245 - */
1.1246 - public static final UnicodeBlock LEPCHA =
1.1247 - new UnicodeBlock("LEPCHA");
1.1248 -
1.1249 - /**
1.1250 - * Constant for the "Ol Chiki" Unicode character block.
1.1251 - * @since 1.7
1.1252 - */
1.1253 - public static final UnicodeBlock OL_CHIKI =
1.1254 - new UnicodeBlock("OL_CHIKI",
1.1255 - "OL CHIKI",
1.1256 - "OLCHIKI");
1.1257 -
1.1258 - /**
1.1259 - * Constant for the "Vedic Extensions" Unicode character block.
1.1260 - * @since 1.7
1.1261 - */
1.1262 - public static final UnicodeBlock VEDIC_EXTENSIONS =
1.1263 - new UnicodeBlock("VEDIC_EXTENSIONS",
1.1264 - "VEDIC EXTENSIONS",
1.1265 - "VEDICEXTENSIONS");
1.1266 -
1.1267 - /**
1.1268 - * Constant for the "Phonetic Extensions Supplement" Unicode character
1.1269 - * block.
1.1270 - * @since 1.7
1.1271 - */
1.1272 - public static final UnicodeBlock PHONETIC_EXTENSIONS_SUPPLEMENT =
1.1273 - new UnicodeBlock("PHONETIC_EXTENSIONS_SUPPLEMENT",
1.1274 - "PHONETIC EXTENSIONS SUPPLEMENT",
1.1275 - "PHONETICEXTENSIONSSUPPLEMENT");
1.1276 -
1.1277 - /**
1.1278 - * Constant for the "Combining Diacritical Marks Supplement" Unicode
1.1279 - * character block.
1.1280 - * @since 1.7
1.1281 - */
1.1282 - public static final UnicodeBlock COMBINING_DIACRITICAL_MARKS_SUPPLEMENT =
1.1283 - new UnicodeBlock("COMBINING_DIACRITICAL_MARKS_SUPPLEMENT",
1.1284 - "COMBINING DIACRITICAL MARKS SUPPLEMENT",
1.1285 - "COMBININGDIACRITICALMARKSSUPPLEMENT");
1.1286 -
1.1287 - /**
1.1288 - * Constant for the "Glagolitic" Unicode character block.
1.1289 - * @since 1.7
1.1290 - */
1.1291 - public static final UnicodeBlock GLAGOLITIC =
1.1292 - new UnicodeBlock("GLAGOLITIC");
1.1293 -
1.1294 - /**
1.1295 - * Constant for the "Latin Extended-C" Unicode character block.
1.1296 - * @since 1.7
1.1297 - */
1.1298 - public static final UnicodeBlock LATIN_EXTENDED_C =
1.1299 - new UnicodeBlock("LATIN_EXTENDED_C",
1.1300 - "LATIN EXTENDED-C",
1.1301 - "LATINEXTENDED-C");
1.1302 -
1.1303 - /**
1.1304 - * Constant for the "Coptic" Unicode character block.
1.1305 - * @since 1.7
1.1306 - */
1.1307 - public static final UnicodeBlock COPTIC =
1.1308 - new UnicodeBlock("COPTIC");
1.1309 -
1.1310 - /**
1.1311 - * Constant for the "Georgian Supplement" Unicode character block.
1.1312 - * @since 1.7
1.1313 - */
1.1314 - public static final UnicodeBlock GEORGIAN_SUPPLEMENT =
1.1315 - new UnicodeBlock("GEORGIAN_SUPPLEMENT",
1.1316 - "GEORGIAN SUPPLEMENT",
1.1317 - "GEORGIANSUPPLEMENT");
1.1318 -
1.1319 - /**
1.1320 - * Constant for the "Tifinagh" Unicode character block.
1.1321 - * @since 1.7
1.1322 - */
1.1323 - public static final UnicodeBlock TIFINAGH =
1.1324 - new UnicodeBlock("TIFINAGH");
1.1325 -
1.1326 - /**
1.1327 - * Constant for the "Ethiopic Extended" Unicode character block.
1.1328 - * @since 1.7
1.1329 - */
1.1330 - public static final UnicodeBlock ETHIOPIC_EXTENDED =
1.1331 - new UnicodeBlock("ETHIOPIC_EXTENDED",
1.1332 - "ETHIOPIC EXTENDED",
1.1333 - "ETHIOPICEXTENDED");
1.1334 -
1.1335 - /**
1.1336 - * Constant for the "Cyrillic Extended-A" Unicode character block.
1.1337 - * @since 1.7
1.1338 - */
1.1339 - public static final UnicodeBlock CYRILLIC_EXTENDED_A =
1.1340 - new UnicodeBlock("CYRILLIC_EXTENDED_A",
1.1341 - "CYRILLIC EXTENDED-A",
1.1342 - "CYRILLICEXTENDED-A");
1.1343 -
1.1344 - /**
1.1345 - * Constant for the "Supplemental Punctuation" Unicode character block.
1.1346 - * @since 1.7
1.1347 - */
1.1348 - public static final UnicodeBlock SUPPLEMENTAL_PUNCTUATION =
1.1349 - new UnicodeBlock("SUPPLEMENTAL_PUNCTUATION",
1.1350 - "SUPPLEMENTAL PUNCTUATION",
1.1351 - "SUPPLEMENTALPUNCTUATION");
1.1352 -
1.1353 - /**
1.1354 - * Constant for the "CJK Strokes" Unicode character block.
1.1355 - * @since 1.7
1.1356 - */
1.1357 - public static final UnicodeBlock CJK_STROKES =
1.1358 - new UnicodeBlock("CJK_STROKES",
1.1359 - "CJK STROKES",
1.1360 - "CJKSTROKES");
1.1361 -
1.1362 - /**
1.1363 - * Constant for the "Lisu" Unicode character block.
1.1364 - * @since 1.7
1.1365 - */
1.1366 - public static final UnicodeBlock LISU =
1.1367 - new UnicodeBlock("LISU");
1.1368 -
1.1369 - /**
1.1370 - * Constant for the "Vai" Unicode character block.
1.1371 - * @since 1.7
1.1372 - */
1.1373 - public static final UnicodeBlock VAI =
1.1374 - new UnicodeBlock("VAI");
1.1375 -
1.1376 - /**
1.1377 - * Constant for the "Cyrillic Extended-B" Unicode character block.
1.1378 - * @since 1.7
1.1379 - */
1.1380 - public static final UnicodeBlock CYRILLIC_EXTENDED_B =
1.1381 - new UnicodeBlock("CYRILLIC_EXTENDED_B",
1.1382 - "CYRILLIC EXTENDED-B",
1.1383 - "CYRILLICEXTENDED-B");
1.1384 -
1.1385 - /**
1.1386 - * Constant for the "Bamum" Unicode character block.
1.1387 - * @since 1.7
1.1388 - */
1.1389 - public static final UnicodeBlock BAMUM =
1.1390 - new UnicodeBlock("BAMUM");
1.1391 -
1.1392 - /**
1.1393 - * Constant for the "Modifier Tone Letters" Unicode character block.
1.1394 - * @since 1.7
1.1395 - */
1.1396 - public static final UnicodeBlock MODIFIER_TONE_LETTERS =
1.1397 - new UnicodeBlock("MODIFIER_TONE_LETTERS",
1.1398 - "MODIFIER TONE LETTERS",
1.1399 - "MODIFIERTONELETTERS");
1.1400 -
1.1401 - /**
1.1402 - * Constant for the "Latin Extended-D" Unicode character block.
1.1403 - * @since 1.7
1.1404 - */
1.1405 - public static final UnicodeBlock LATIN_EXTENDED_D =
1.1406 - new UnicodeBlock("LATIN_EXTENDED_D",
1.1407 - "LATIN EXTENDED-D",
1.1408 - "LATINEXTENDED-D");
1.1409 -
1.1410 - /**
1.1411 - * Constant for the "Syloti Nagri" Unicode character block.
1.1412 - * @since 1.7
1.1413 - */
1.1414 - public static final UnicodeBlock SYLOTI_NAGRI =
1.1415 - new UnicodeBlock("SYLOTI_NAGRI",
1.1416 - "SYLOTI NAGRI",
1.1417 - "SYLOTINAGRI");
1.1418 -
1.1419 - /**
1.1420 - * Constant for the "Common Indic Number Forms" Unicode character block.
1.1421 - * @since 1.7
1.1422 - */
1.1423 - public static final UnicodeBlock COMMON_INDIC_NUMBER_FORMS =
1.1424 - new UnicodeBlock("COMMON_INDIC_NUMBER_FORMS",
1.1425 - "COMMON INDIC NUMBER FORMS",
1.1426 - "COMMONINDICNUMBERFORMS");
1.1427 -
1.1428 - /**
1.1429 - * Constant for the "Phags-pa" Unicode character block.
1.1430 - * @since 1.7
1.1431 - */
1.1432 - public static final UnicodeBlock PHAGS_PA =
1.1433 - new UnicodeBlock("PHAGS_PA",
1.1434 - "PHAGS-PA");
1.1435 -
1.1436 - /**
1.1437 - * Constant for the "Saurashtra" Unicode character block.
1.1438 - * @since 1.7
1.1439 - */
1.1440 - public static final UnicodeBlock SAURASHTRA =
1.1441 - new UnicodeBlock("SAURASHTRA");
1.1442 -
1.1443 - /**
1.1444 - * Constant for the "Devanagari Extended" Unicode character block.
1.1445 - * @since 1.7
1.1446 - */
1.1447 - public static final UnicodeBlock DEVANAGARI_EXTENDED =
1.1448 - new UnicodeBlock("DEVANAGARI_EXTENDED",
1.1449 - "DEVANAGARI EXTENDED",
1.1450 - "DEVANAGARIEXTENDED");
1.1451 -
1.1452 - /**
1.1453 - * Constant for the "Kayah Li" Unicode character block.
1.1454 - * @since 1.7
1.1455 - */
1.1456 - public static final UnicodeBlock KAYAH_LI =
1.1457 - new UnicodeBlock("KAYAH_LI",
1.1458 - "KAYAH LI",
1.1459 - "KAYAHLI");
1.1460 -
1.1461 - /**
1.1462 - * Constant for the "Rejang" Unicode character block.
1.1463 - * @since 1.7
1.1464 - */
1.1465 - public static final UnicodeBlock REJANG =
1.1466 - new UnicodeBlock("REJANG");
1.1467 -
1.1468 - /**
1.1469 - * Constant for the "Hangul Jamo Extended-A" Unicode character block.
1.1470 - * @since 1.7
1.1471 - */
1.1472 - public static final UnicodeBlock HANGUL_JAMO_EXTENDED_A =
1.1473 - new UnicodeBlock("HANGUL_JAMO_EXTENDED_A",
1.1474 - "HANGUL JAMO EXTENDED-A",
1.1475 - "HANGULJAMOEXTENDED-A");
1.1476 -
1.1477 - /**
1.1478 - * Constant for the "Javanese" Unicode character block.
1.1479 - * @since 1.7
1.1480 - */
1.1481 - public static final UnicodeBlock JAVANESE =
1.1482 - new UnicodeBlock("JAVANESE");
1.1483 -
1.1484 - /**
1.1485 - * Constant for the "Cham" Unicode character block.
1.1486 - * @since 1.7
1.1487 - */
1.1488 - public static final UnicodeBlock CHAM =
1.1489 - new UnicodeBlock("CHAM");
1.1490 -
1.1491 - /**
1.1492 - * Constant for the "Myanmar Extended-A" Unicode character block.
1.1493 - * @since 1.7
1.1494 - */
1.1495 - public static final UnicodeBlock MYANMAR_EXTENDED_A =
1.1496 - new UnicodeBlock("MYANMAR_EXTENDED_A",
1.1497 - "MYANMAR EXTENDED-A",
1.1498 - "MYANMAREXTENDED-A");
1.1499 -
1.1500 - /**
1.1501 - * Constant for the "Tai Viet" Unicode character block.
1.1502 - * @since 1.7
1.1503 - */
1.1504 - public static final UnicodeBlock TAI_VIET =
1.1505 - new UnicodeBlock("TAI_VIET",
1.1506 - "TAI VIET",
1.1507 - "TAIVIET");
1.1508 -
1.1509 - /**
1.1510 - * Constant for the "Ethiopic Extended-A" Unicode character block.
1.1511 - * @since 1.7
1.1512 - */
1.1513 - public static final UnicodeBlock ETHIOPIC_EXTENDED_A =
1.1514 - new UnicodeBlock("ETHIOPIC_EXTENDED_A",
1.1515 - "ETHIOPIC EXTENDED-A",
1.1516 - "ETHIOPICEXTENDED-A");
1.1517 -
1.1518 - /**
1.1519 - * Constant for the "Meetei Mayek" Unicode character block.
1.1520 - * @since 1.7
1.1521 - */
1.1522 - public static final UnicodeBlock MEETEI_MAYEK =
1.1523 - new UnicodeBlock("MEETEI_MAYEK",
1.1524 - "MEETEI MAYEK",
1.1525 - "MEETEIMAYEK");
1.1526 -
1.1527 - /**
1.1528 - * Constant for the "Hangul Jamo Extended-B" Unicode character block.
1.1529 - * @since 1.7
1.1530 - */
1.1531 - public static final UnicodeBlock HANGUL_JAMO_EXTENDED_B =
1.1532 - new UnicodeBlock("HANGUL_JAMO_EXTENDED_B",
1.1533 - "HANGUL JAMO EXTENDED-B",
1.1534 - "HANGULJAMOEXTENDED-B");
1.1535 -
1.1536 - /**
1.1537 - * Constant for the "Vertical Forms" Unicode character block.
1.1538 - * @since 1.7
1.1539 - */
1.1540 - public static final UnicodeBlock VERTICAL_FORMS =
1.1541 - new UnicodeBlock("VERTICAL_FORMS",
1.1542 - "VERTICAL FORMS",
1.1543 - "VERTICALFORMS");
1.1544 -
1.1545 - /**
1.1546 - * Constant for the "Ancient Greek Numbers" Unicode character block.
1.1547 - * @since 1.7
1.1548 - */
1.1549 - public static final UnicodeBlock ANCIENT_GREEK_NUMBERS =
1.1550 - new UnicodeBlock("ANCIENT_GREEK_NUMBERS",
1.1551 - "ANCIENT GREEK NUMBERS",
1.1552 - "ANCIENTGREEKNUMBERS");
1.1553 -
1.1554 - /**
1.1555 - * Constant for the "Ancient Symbols" Unicode character block.
1.1556 - * @since 1.7
1.1557 - */
1.1558 - public static final UnicodeBlock ANCIENT_SYMBOLS =
1.1559 - new UnicodeBlock("ANCIENT_SYMBOLS",
1.1560 - "ANCIENT SYMBOLS",
1.1561 - "ANCIENTSYMBOLS");
1.1562 -
1.1563 - /**
1.1564 - * Constant for the "Phaistos Disc" Unicode character block.
1.1565 - * @since 1.7
1.1566 - */
1.1567 - public static final UnicodeBlock PHAISTOS_DISC =
1.1568 - new UnicodeBlock("PHAISTOS_DISC",
1.1569 - "PHAISTOS DISC",
1.1570 - "PHAISTOSDISC");
1.1571 -
1.1572 - /**
1.1573 - * Constant for the "Lycian" Unicode character block.
1.1574 - * @since 1.7
1.1575 - */
1.1576 - public static final UnicodeBlock LYCIAN =
1.1577 - new UnicodeBlock("LYCIAN");
1.1578 -
1.1579 - /**
1.1580 - * Constant for the "Carian" Unicode character block.
1.1581 - * @since 1.7
1.1582 - */
1.1583 - public static final UnicodeBlock CARIAN =
1.1584 - new UnicodeBlock("CARIAN");
1.1585 -
1.1586 - /**
1.1587 - * Constant for the "Old Persian" Unicode character block.
1.1588 - * @since 1.7
1.1589 - */
1.1590 - public static final UnicodeBlock OLD_PERSIAN =
1.1591 - new UnicodeBlock("OLD_PERSIAN",
1.1592 - "OLD PERSIAN",
1.1593 - "OLDPERSIAN");
1.1594 -
1.1595 - /**
1.1596 - * Constant for the "Imperial Aramaic" Unicode character block.
1.1597 - * @since 1.7
1.1598 - */
1.1599 - public static final UnicodeBlock IMPERIAL_ARAMAIC =
1.1600 - new UnicodeBlock("IMPERIAL_ARAMAIC",
1.1601 - "IMPERIAL ARAMAIC",
1.1602 - "IMPERIALARAMAIC");
1.1603 -
1.1604 - /**
1.1605 - * Constant for the "Phoenician" Unicode character block.
1.1606 - * @since 1.7
1.1607 - */
1.1608 - public static final UnicodeBlock PHOENICIAN =
1.1609 - new UnicodeBlock("PHOENICIAN");
1.1610 -
1.1611 - /**
1.1612 - * Constant for the "Lydian" Unicode character block.
1.1613 - * @since 1.7
1.1614 - */
1.1615 - public static final UnicodeBlock LYDIAN =
1.1616 - new UnicodeBlock("LYDIAN");
1.1617 -
1.1618 - /**
1.1619 - * Constant for the "Kharoshthi" Unicode character block.
1.1620 - * @since 1.7
1.1621 - */
1.1622 - public static final UnicodeBlock KHAROSHTHI =
1.1623 - new UnicodeBlock("KHAROSHTHI");
1.1624 -
1.1625 - /**
1.1626 - * Constant for the "Old South Arabian" Unicode character block.
1.1627 - * @since 1.7
1.1628 - */
1.1629 - public static final UnicodeBlock OLD_SOUTH_ARABIAN =
1.1630 - new UnicodeBlock("OLD_SOUTH_ARABIAN",
1.1631 - "OLD SOUTH ARABIAN",
1.1632 - "OLDSOUTHARABIAN");
1.1633 -
1.1634 - /**
1.1635 - * Constant for the "Avestan" Unicode character block.
1.1636 - * @since 1.7
1.1637 - */
1.1638 - public static final UnicodeBlock AVESTAN =
1.1639 - new UnicodeBlock("AVESTAN");
1.1640 -
1.1641 - /**
1.1642 - * Constant for the "Inscriptional Parthian" Unicode character block.
1.1643 - * @since 1.7
1.1644 - */
1.1645 - public static final UnicodeBlock INSCRIPTIONAL_PARTHIAN =
1.1646 - new UnicodeBlock("INSCRIPTIONAL_PARTHIAN",
1.1647 - "INSCRIPTIONAL PARTHIAN",
1.1648 - "INSCRIPTIONALPARTHIAN");
1.1649 -
1.1650 - /**
1.1651 - * Constant for the "Inscriptional Pahlavi" Unicode character block.
1.1652 - * @since 1.7
1.1653 - */
1.1654 - public static final UnicodeBlock INSCRIPTIONAL_PAHLAVI =
1.1655 - new UnicodeBlock("INSCRIPTIONAL_PAHLAVI",
1.1656 - "INSCRIPTIONAL PAHLAVI",
1.1657 - "INSCRIPTIONALPAHLAVI");
1.1658 -
1.1659 - /**
1.1660 - * Constant for the "Old Turkic" Unicode character block.
1.1661 - * @since 1.7
1.1662 - */
1.1663 - public static final UnicodeBlock OLD_TURKIC =
1.1664 - new UnicodeBlock("OLD_TURKIC",
1.1665 - "OLD TURKIC",
1.1666 - "OLDTURKIC");
1.1667 -
1.1668 - /**
1.1669 - * Constant for the "Rumi Numeral Symbols" Unicode character block.
1.1670 - * @since 1.7
1.1671 - */
1.1672 - public static final UnicodeBlock RUMI_NUMERAL_SYMBOLS =
1.1673 - new UnicodeBlock("RUMI_NUMERAL_SYMBOLS",
1.1674 - "RUMI NUMERAL SYMBOLS",
1.1675 - "RUMINUMERALSYMBOLS");
1.1676 -
1.1677 - /**
1.1678 - * Constant for the "Brahmi" Unicode character block.
1.1679 - * @since 1.7
1.1680 - */
1.1681 - public static final UnicodeBlock BRAHMI =
1.1682 - new UnicodeBlock("BRAHMI");
1.1683 -
1.1684 - /**
1.1685 - * Constant for the "Kaithi" Unicode character block.
1.1686 - * @since 1.7
1.1687 - */
1.1688 - public static final UnicodeBlock KAITHI =
1.1689 - new UnicodeBlock("KAITHI");
1.1690 -
1.1691 - /**
1.1692 - * Constant for the "Cuneiform" Unicode character block.
1.1693 - * @since 1.7
1.1694 - */
1.1695 - public static final UnicodeBlock CUNEIFORM =
1.1696 - new UnicodeBlock("CUNEIFORM");
1.1697 -
1.1698 - /**
1.1699 - * Constant for the "Cuneiform Numbers and Punctuation" Unicode
1.1700 - * character block.
1.1701 - * @since 1.7
1.1702 - */
1.1703 - public static final UnicodeBlock CUNEIFORM_NUMBERS_AND_PUNCTUATION =
1.1704 - new UnicodeBlock("CUNEIFORM_NUMBERS_AND_PUNCTUATION",
1.1705 - "CUNEIFORM NUMBERS AND PUNCTUATION",
1.1706 - "CUNEIFORMNUMBERSANDPUNCTUATION");
1.1707 -
1.1708 - /**
1.1709 - * Constant for the "Egyptian Hieroglyphs" Unicode character block.
1.1710 - * @since 1.7
1.1711 - */
1.1712 - public static final UnicodeBlock EGYPTIAN_HIEROGLYPHS =
1.1713 - new UnicodeBlock("EGYPTIAN_HIEROGLYPHS",
1.1714 - "EGYPTIAN HIEROGLYPHS",
1.1715 - "EGYPTIANHIEROGLYPHS");
1.1716 -
1.1717 - /**
1.1718 - * Constant for the "Bamum Supplement" Unicode character block.
1.1719 - * @since 1.7
1.1720 - */
1.1721 - public static final UnicodeBlock BAMUM_SUPPLEMENT =
1.1722 - new UnicodeBlock("BAMUM_SUPPLEMENT",
1.1723 - "BAMUM SUPPLEMENT",
1.1724 - "BAMUMSUPPLEMENT");
1.1725 -
1.1726 - /**
1.1727 - * Constant for the "Kana Supplement" Unicode character block.
1.1728 - * @since 1.7
1.1729 - */
1.1730 - public static final UnicodeBlock KANA_SUPPLEMENT =
1.1731 - new UnicodeBlock("KANA_SUPPLEMENT",
1.1732 - "KANA SUPPLEMENT",
1.1733 - "KANASUPPLEMENT");
1.1734 -
1.1735 - /**
1.1736 - * Constant for the "Ancient Greek Musical Notation" Unicode character
1.1737 - * block.
1.1738 - * @since 1.7
1.1739 - */
1.1740 - public static final UnicodeBlock ANCIENT_GREEK_MUSICAL_NOTATION =
1.1741 - new UnicodeBlock("ANCIENT_GREEK_MUSICAL_NOTATION",
1.1742 - "ANCIENT GREEK MUSICAL NOTATION",
1.1743 - "ANCIENTGREEKMUSICALNOTATION");
1.1744 -
1.1745 - /**
1.1746 - * Constant for the "Counting Rod Numerals" Unicode character block.
1.1747 - * @since 1.7
1.1748 - */
1.1749 - public static final UnicodeBlock COUNTING_ROD_NUMERALS =
1.1750 - new UnicodeBlock("COUNTING_ROD_NUMERALS",
1.1751 - "COUNTING ROD NUMERALS",
1.1752 - "COUNTINGRODNUMERALS");
1.1753 -
1.1754 - /**
1.1755 - * Constant for the "Mahjong Tiles" Unicode character block.
1.1756 - * @since 1.7
1.1757 - */
1.1758 - public static final UnicodeBlock MAHJONG_TILES =
1.1759 - new UnicodeBlock("MAHJONG_TILES",
1.1760 - "MAHJONG TILES",
1.1761 - "MAHJONGTILES");
1.1762 -
1.1763 - /**
1.1764 - * Constant for the "Domino Tiles" Unicode character block.
1.1765 - * @since 1.7
1.1766 - */
1.1767 - public static final UnicodeBlock DOMINO_TILES =
1.1768 - new UnicodeBlock("DOMINO_TILES",
1.1769 - "DOMINO TILES",
1.1770 - "DOMINOTILES");
1.1771 -
1.1772 - /**
1.1773 - * Constant for the "Playing Cards" Unicode character block.
1.1774 - * @since 1.7
1.1775 - */
1.1776 - public static final UnicodeBlock PLAYING_CARDS =
1.1777 - new UnicodeBlock("PLAYING_CARDS",
1.1778 - "PLAYING CARDS",
1.1779 - "PLAYINGCARDS");
1.1780 -
1.1781 - /**
1.1782 - * Constant for the "Enclosed Alphanumeric Supplement" Unicode character
1.1783 - * block.
1.1784 - * @since 1.7
1.1785 - */
1.1786 - public static final UnicodeBlock ENCLOSED_ALPHANUMERIC_SUPPLEMENT =
1.1787 - new UnicodeBlock("ENCLOSED_ALPHANUMERIC_SUPPLEMENT",
1.1788 - "ENCLOSED ALPHANUMERIC SUPPLEMENT",
1.1789 - "ENCLOSEDALPHANUMERICSUPPLEMENT");
1.1790 -
1.1791 - /**
1.1792 - * Constant for the "Enclosed Ideographic Supplement" Unicode character
1.1793 - * block.
1.1794 - * @since 1.7
1.1795 - */
1.1796 - public static final UnicodeBlock ENCLOSED_IDEOGRAPHIC_SUPPLEMENT =
1.1797 - new UnicodeBlock("ENCLOSED_IDEOGRAPHIC_SUPPLEMENT",
1.1798 - "ENCLOSED IDEOGRAPHIC SUPPLEMENT",
1.1799 - "ENCLOSEDIDEOGRAPHICSUPPLEMENT");
1.1800 -
1.1801 - /**
1.1802 - * Constant for the "Miscellaneous Symbols And Pictographs" Unicode
1.1803 - * character block.
1.1804 - * @since 1.7
1.1805 - */
1.1806 - public static final UnicodeBlock MISCELLANEOUS_SYMBOLS_AND_PICTOGRAPHS =
1.1807 - new UnicodeBlock("MISCELLANEOUS_SYMBOLS_AND_PICTOGRAPHS",
1.1808 - "MISCELLANEOUS SYMBOLS AND PICTOGRAPHS",
1.1809 - "MISCELLANEOUSSYMBOLSANDPICTOGRAPHS");
1.1810 -
1.1811 - /**
1.1812 - * Constant for the "Emoticons" Unicode character block.
1.1813 - * @since 1.7
1.1814 - */
1.1815 - public static final UnicodeBlock EMOTICONS =
1.1816 - new UnicodeBlock("EMOTICONS");
1.1817 -
1.1818 - /**
1.1819 - * Constant for the "Transport And Map Symbols" Unicode character block.
1.1820 - * @since 1.7
1.1821 - */
1.1822 - public static final UnicodeBlock TRANSPORT_AND_MAP_SYMBOLS =
1.1823 - new UnicodeBlock("TRANSPORT_AND_MAP_SYMBOLS",
1.1824 - "TRANSPORT AND MAP SYMBOLS",
1.1825 - "TRANSPORTANDMAPSYMBOLS");
1.1826 -
1.1827 - /**
1.1828 - * Constant for the "Alchemical Symbols" Unicode character block.
1.1829 - * @since 1.7
1.1830 - */
1.1831 - public static final UnicodeBlock ALCHEMICAL_SYMBOLS =
1.1832 - new UnicodeBlock("ALCHEMICAL_SYMBOLS",
1.1833 - "ALCHEMICAL SYMBOLS",
1.1834 - "ALCHEMICALSYMBOLS");
1.1835 -
1.1836 - /**
1.1837 - * Constant for the "CJK Unified Ideographs Extension C" Unicode
1.1838 - * character block.
1.1839 - * @since 1.7
1.1840 - */
1.1841 - public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_C =
1.1842 - new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_C",
1.1843 - "CJK UNIFIED IDEOGRAPHS EXTENSION C",
1.1844 - "CJKUNIFIEDIDEOGRAPHSEXTENSIONC");
1.1845 -
1.1846 - /**
1.1847 - * Constant for the "CJK Unified Ideographs Extension D" Unicode
1.1848 - * character block.
1.1849 - * @since 1.7
1.1850 - */
1.1851 - public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_D =
1.1852 - new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_D",
1.1853 - "CJK UNIFIED IDEOGRAPHS EXTENSION D",
1.1854 - "CJKUNIFIEDIDEOGRAPHSEXTENSIOND");
1.1855 -
1.1856 - private static final int blockStarts[] = {
1.1857 - 0x0000, // 0000..007F; Basic Latin
1.1858 - 0x0080, // 0080..00FF; Latin-1 Supplement
1.1859 - 0x0100, // 0100..017F; Latin Extended-A
1.1860 - 0x0180, // 0180..024F; Latin Extended-B
1.1861 - 0x0250, // 0250..02AF; IPA Extensions
1.1862 - 0x02B0, // 02B0..02FF; Spacing Modifier Letters
1.1863 - 0x0300, // 0300..036F; Combining Diacritical Marks
1.1864 - 0x0370, // 0370..03FF; Greek and Coptic
1.1865 - 0x0400, // 0400..04FF; Cyrillic
1.1866 - 0x0500, // 0500..052F; Cyrillic Supplement
1.1867 - 0x0530, // 0530..058F; Armenian
1.1868 - 0x0590, // 0590..05FF; Hebrew
1.1869 - 0x0600, // 0600..06FF; Arabic
1.1870 - 0x0700, // 0700..074F; Syriac
1.1871 - 0x0750, // 0750..077F; Arabic Supplement
1.1872 - 0x0780, // 0780..07BF; Thaana
1.1873 - 0x07C0, // 07C0..07FF; NKo
1.1874 - 0x0800, // 0800..083F; Samaritan
1.1875 - 0x0840, // 0840..085F; Mandaic
1.1876 - 0x0860, // unassigned
1.1877 - 0x0900, // 0900..097F; Devanagari
1.1878 - 0x0980, // 0980..09FF; Bengali
1.1879 - 0x0A00, // 0A00..0A7F; Gurmukhi
1.1880 - 0x0A80, // 0A80..0AFF; Gujarati
1.1881 - 0x0B00, // 0B00..0B7F; Oriya
1.1882 - 0x0B80, // 0B80..0BFF; Tamil
1.1883 - 0x0C00, // 0C00..0C7F; Telugu
1.1884 - 0x0C80, // 0C80..0CFF; Kannada
1.1885 - 0x0D00, // 0D00..0D7F; Malayalam
1.1886 - 0x0D80, // 0D80..0DFF; Sinhala
1.1887 - 0x0E00, // 0E00..0E7F; Thai
1.1888 - 0x0E80, // 0E80..0EFF; Lao
1.1889 - 0x0F00, // 0F00..0FFF; Tibetan
1.1890 - 0x1000, // 1000..109F; Myanmar
1.1891 - 0x10A0, // 10A0..10FF; Georgian
1.1892 - 0x1100, // 1100..11FF; Hangul Jamo
1.1893 - 0x1200, // 1200..137F; Ethiopic
1.1894 - 0x1380, // 1380..139F; Ethiopic Supplement
1.1895 - 0x13A0, // 13A0..13FF; Cherokee
1.1896 - 0x1400, // 1400..167F; Unified Canadian Aboriginal Syllabics
1.1897 - 0x1680, // 1680..169F; Ogham
1.1898 - 0x16A0, // 16A0..16FF; Runic
1.1899 - 0x1700, // 1700..171F; Tagalog
1.1900 - 0x1720, // 1720..173F; Hanunoo
1.1901 - 0x1740, // 1740..175F; Buhid
1.1902 - 0x1760, // 1760..177F; Tagbanwa
1.1903 - 0x1780, // 1780..17FF; Khmer
1.1904 - 0x1800, // 1800..18AF; Mongolian
1.1905 - 0x18B0, // 18B0..18FF; Unified Canadian Aboriginal Syllabics Extended
1.1906 - 0x1900, // 1900..194F; Limbu
1.1907 - 0x1950, // 1950..197F; Tai Le
1.1908 - 0x1980, // 1980..19DF; New Tai Lue
1.1909 - 0x19E0, // 19E0..19FF; Khmer Symbols
1.1910 - 0x1A00, // 1A00..1A1F; Buginese
1.1911 - 0x1A20, // 1A20..1AAF; Tai Tham
1.1912 - 0x1AB0, // unassigned
1.1913 - 0x1B00, // 1B00..1B7F; Balinese
1.1914 - 0x1B80, // 1B80..1BBF; Sundanese
1.1915 - 0x1BC0, // 1BC0..1BFF; Batak
1.1916 - 0x1C00, // 1C00..1C4F; Lepcha
1.1917 - 0x1C50, // 1C50..1C7F; Ol Chiki
1.1918 - 0x1C80, // unassigned
1.1919 - 0x1CD0, // 1CD0..1CFF; Vedic Extensions
1.1920 - 0x1D00, // 1D00..1D7F; Phonetic Extensions
1.1921 - 0x1D80, // 1D80..1DBF; Phonetic Extensions Supplement
1.1922 - 0x1DC0, // 1DC0..1DFF; Combining Diacritical Marks Supplement
1.1923 - 0x1E00, // 1E00..1EFF; Latin Extended Additional
1.1924 - 0x1F00, // 1F00..1FFF; Greek Extended
1.1925 - 0x2000, // 2000..206F; General Punctuation
1.1926 - 0x2070, // 2070..209F; Superscripts and Subscripts
1.1927 - 0x20A0, // 20A0..20CF; Currency Symbols
1.1928 - 0x20D0, // 20D0..20FF; Combining Diacritical Marks for Symbols
1.1929 - 0x2100, // 2100..214F; Letterlike Symbols
1.1930 - 0x2150, // 2150..218F; Number Forms
1.1931 - 0x2190, // 2190..21FF; Arrows
1.1932 - 0x2200, // 2200..22FF; Mathematical Operators
1.1933 - 0x2300, // 2300..23FF; Miscellaneous Technical
1.1934 - 0x2400, // 2400..243F; Control Pictures
1.1935 - 0x2440, // 2440..245F; Optical Character Recognition
1.1936 - 0x2460, // 2460..24FF; Enclosed Alphanumerics
1.1937 - 0x2500, // 2500..257F; Box Drawing
1.1938 - 0x2580, // 2580..259F; Block Elements
1.1939 - 0x25A0, // 25A0..25FF; Geometric Shapes
1.1940 - 0x2600, // 2600..26FF; Miscellaneous Symbols
1.1941 - 0x2700, // 2700..27BF; Dingbats
1.1942 - 0x27C0, // 27C0..27EF; Miscellaneous Mathematical Symbols-A
1.1943 - 0x27F0, // 27F0..27FF; Supplemental Arrows-A
1.1944 - 0x2800, // 2800..28FF; Braille Patterns
1.1945 - 0x2900, // 2900..297F; Supplemental Arrows-B
1.1946 - 0x2980, // 2980..29FF; Miscellaneous Mathematical Symbols-B
1.1947 - 0x2A00, // 2A00..2AFF; Supplemental Mathematical Operators
1.1948 - 0x2B00, // 2B00..2BFF; Miscellaneous Symbols and Arrows
1.1949 - 0x2C00, // 2C00..2C5F; Glagolitic
1.1950 - 0x2C60, // 2C60..2C7F; Latin Extended-C
1.1951 - 0x2C80, // 2C80..2CFF; Coptic
1.1952 - 0x2D00, // 2D00..2D2F; Georgian Supplement
1.1953 - 0x2D30, // 2D30..2D7F; Tifinagh
1.1954 - 0x2D80, // 2D80..2DDF; Ethiopic Extended
1.1955 - 0x2DE0, // 2DE0..2DFF; Cyrillic Extended-A
1.1956 - 0x2E00, // 2E00..2E7F; Supplemental Punctuation
1.1957 - 0x2E80, // 2E80..2EFF; CJK Radicals Supplement
1.1958 - 0x2F00, // 2F00..2FDF; Kangxi Radicals
1.1959 - 0x2FE0, // unassigned
1.1960 - 0x2FF0, // 2FF0..2FFF; Ideographic Description Characters
1.1961 - 0x3000, // 3000..303F; CJK Symbols and Punctuation
1.1962 - 0x3040, // 3040..309F; Hiragana
1.1963 - 0x30A0, // 30A0..30FF; Katakana
1.1964 - 0x3100, // 3100..312F; Bopomofo
1.1965 - 0x3130, // 3130..318F; Hangul Compatibility Jamo
1.1966 - 0x3190, // 3190..319F; Kanbun
1.1967 - 0x31A0, // 31A0..31BF; Bopomofo Extended
1.1968 - 0x31C0, // 31C0..31EF; CJK Strokes
1.1969 - 0x31F0, // 31F0..31FF; Katakana Phonetic Extensions
1.1970 - 0x3200, // 3200..32FF; Enclosed CJK Letters and Months
1.1971 - 0x3300, // 3300..33FF; CJK Compatibility
1.1972 - 0x3400, // 3400..4DBF; CJK Unified Ideographs Extension A
1.1973 - 0x4DC0, // 4DC0..4DFF; Yijing Hexagram Symbols
1.1974 - 0x4E00, // 4E00..9FFF; CJK Unified Ideographs
1.1975 - 0xA000, // A000..A48F; Yi Syllables
1.1976 - 0xA490, // A490..A4CF; Yi Radicals
1.1977 - 0xA4D0, // A4D0..A4FF; Lisu
1.1978 - 0xA500, // A500..A63F; Vai
1.1979 - 0xA640, // A640..A69F; Cyrillic Extended-B
1.1980 - 0xA6A0, // A6A0..A6FF; Bamum
1.1981 - 0xA700, // A700..A71F; Modifier Tone Letters
1.1982 - 0xA720, // A720..A7FF; Latin Extended-D
1.1983 - 0xA800, // A800..A82F; Syloti Nagri
1.1984 - 0xA830, // A830..A83F; Common Indic Number Forms
1.1985 - 0xA840, // A840..A87F; Phags-pa
1.1986 - 0xA880, // A880..A8DF; Saurashtra
1.1987 - 0xA8E0, // A8E0..A8FF; Devanagari Extended
1.1988 - 0xA900, // A900..A92F; Kayah Li
1.1989 - 0xA930, // A930..A95F; Rejang
1.1990 - 0xA960, // A960..A97F; Hangul Jamo Extended-A
1.1991 - 0xA980, // A980..A9DF; Javanese
1.1992 - 0xA9E0, // unassigned
1.1993 - 0xAA00, // AA00..AA5F; Cham
1.1994 - 0xAA60, // AA60..AA7F; Myanmar Extended-A
1.1995 - 0xAA80, // AA80..AADF; Tai Viet
1.1996 - 0xAAE0, // unassigned
1.1997 - 0xAB00, // AB00..AB2F; Ethiopic Extended-A
1.1998 - 0xAB30, // unassigned
1.1999 - 0xABC0, // ABC0..ABFF; Meetei Mayek
1.2000 - 0xAC00, // AC00..D7AF; Hangul Syllables
1.2001 - 0xD7B0, // D7B0..D7FF; Hangul Jamo Extended-B
1.2002 - 0xD800, // D800..DB7F; High Surrogates
1.2003 - 0xDB80, // DB80..DBFF; High Private Use Surrogates
1.2004 - 0xDC00, // DC00..DFFF; Low Surrogates
1.2005 - 0xE000, // E000..F8FF; Private Use Area
1.2006 - 0xF900, // F900..FAFF; CJK Compatibility Ideographs
1.2007 - 0xFB00, // FB00..FB4F; Alphabetic Presentation Forms
1.2008 - 0xFB50, // FB50..FDFF; Arabic Presentation Forms-A
1.2009 - 0xFE00, // FE00..FE0F; Variation Selectors
1.2010 - 0xFE10, // FE10..FE1F; Vertical Forms
1.2011 - 0xFE20, // FE20..FE2F; Combining Half Marks
1.2012 - 0xFE30, // FE30..FE4F; CJK Compatibility Forms
1.2013 - 0xFE50, // FE50..FE6F; Small Form Variants
1.2014 - 0xFE70, // FE70..FEFF; Arabic Presentation Forms-B
1.2015 - 0xFF00, // FF00..FFEF; Halfwidth and Fullwidth Forms
1.2016 - 0xFFF0, // FFF0..FFFF; Specials
1.2017 - 0x10000, // 10000..1007F; Linear B Syllabary
1.2018 - 0x10080, // 10080..100FF; Linear B Ideograms
1.2019 - 0x10100, // 10100..1013F; Aegean Numbers
1.2020 - 0x10140, // 10140..1018F; Ancient Greek Numbers
1.2021 - 0x10190, // 10190..101CF; Ancient Symbols
1.2022 - 0x101D0, // 101D0..101FF; Phaistos Disc
1.2023 - 0x10200, // unassigned
1.2024 - 0x10280, // 10280..1029F; Lycian
1.2025 - 0x102A0, // 102A0..102DF; Carian
1.2026 - 0x102E0, // unassigned
1.2027 - 0x10300, // 10300..1032F; Old Italic
1.2028 - 0x10330, // 10330..1034F; Gothic
1.2029 - 0x10350, // unassigned
1.2030 - 0x10380, // 10380..1039F; Ugaritic
1.2031 - 0x103A0, // 103A0..103DF; Old Persian
1.2032 - 0x103E0, // unassigned
1.2033 - 0x10400, // 10400..1044F; Deseret
1.2034 - 0x10450, // 10450..1047F; Shavian
1.2035 - 0x10480, // 10480..104AF; Osmanya
1.2036 - 0x104B0, // unassigned
1.2037 - 0x10800, // 10800..1083F; Cypriot Syllabary
1.2038 - 0x10840, // 10840..1085F; Imperial Aramaic
1.2039 - 0x10860, // unassigned
1.2040 - 0x10900, // 10900..1091F; Phoenician
1.2041 - 0x10920, // 10920..1093F; Lydian
1.2042 - 0x10940, // unassigned
1.2043 - 0x10A00, // 10A00..10A5F; Kharoshthi
1.2044 - 0x10A60, // 10A60..10A7F; Old South Arabian
1.2045 - 0x10A80, // unassigned
1.2046 - 0x10B00, // 10B00..10B3F; Avestan
1.2047 - 0x10B40, // 10B40..10B5F; Inscriptional Parthian
1.2048 - 0x10B60, // 10B60..10B7F; Inscriptional Pahlavi
1.2049 - 0x10B80, // unassigned
1.2050 - 0x10C00, // 10C00..10C4F; Old Turkic
1.2051 - 0x10C50, // unassigned
1.2052 - 0x10E60, // 10E60..10E7F; Rumi Numeral Symbols
1.2053 - 0x10E80, // unassigned
1.2054 - 0x11000, // 11000..1107F; Brahmi
1.2055 - 0x11080, // 11080..110CF; Kaithi
1.2056 - 0x110D0, // unassigned
1.2057 - 0x12000, // 12000..123FF; Cuneiform
1.2058 - 0x12400, // 12400..1247F; Cuneiform Numbers and Punctuation
1.2059 - 0x12480, // unassigned
1.2060 - 0x13000, // 13000..1342F; Egyptian Hieroglyphs
1.2061 - 0x13430, // unassigned
1.2062 - 0x16800, // 16800..16A3F; Bamum Supplement
1.2063 - 0x16A40, // unassigned
1.2064 - 0x1B000, // 1B000..1B0FF; Kana Supplement
1.2065 - 0x1B100, // unassigned
1.2066 - 0x1D000, // 1D000..1D0FF; Byzantine Musical Symbols
1.2067 - 0x1D100, // 1D100..1D1FF; Musical Symbols
1.2068 - 0x1D200, // 1D200..1D24F; Ancient Greek Musical Notation
1.2069 - 0x1D250, // unassigned
1.2070 - 0x1D300, // 1D300..1D35F; Tai Xuan Jing Symbols
1.2071 - 0x1D360, // 1D360..1D37F; Counting Rod Numerals
1.2072 - 0x1D380, // unassigned
1.2073 - 0x1D400, // 1D400..1D7FF; Mathematical Alphanumeric Symbols
1.2074 - 0x1D800, // unassigned
1.2075 - 0x1F000, // 1F000..1F02F; Mahjong Tiles
1.2076 - 0x1F030, // 1F030..1F09F; Domino Tiles
1.2077 - 0x1F0A0, // 1F0A0..1F0FF; Playing Cards
1.2078 - 0x1F100, // 1F100..1F1FF; Enclosed Alphanumeric Supplement
1.2079 - 0x1F200, // 1F200..1F2FF; Enclosed Ideographic Supplement
1.2080 - 0x1F300, // 1F300..1F5FF; Miscellaneous Symbols And Pictographs
1.2081 - 0x1F600, // 1F600..1F64F; Emoticons
1.2082 - 0x1F650, // unassigned
1.2083 - 0x1F680, // 1F680..1F6FF; Transport And Map Symbols
1.2084 - 0x1F700, // 1F700..1F77F; Alchemical Symbols
1.2085 - 0x1F780, // unassigned
1.2086 - 0x20000, // 20000..2A6DF; CJK Unified Ideographs Extension B
1.2087 - 0x2A6E0, // unassigned
1.2088 - 0x2A700, // 2A700..2B73F; CJK Unified Ideographs Extension C
1.2089 - 0x2B740, // 2B740..2B81F; CJK Unified Ideographs Extension D
1.2090 - 0x2B820, // unassigned
1.2091 - 0x2F800, // 2F800..2FA1F; CJK Compatibility Ideographs Supplement
1.2092 - 0x2FA20, // unassigned
1.2093 - 0xE0000, // E0000..E007F; Tags
1.2094 - 0xE0080, // unassigned
1.2095 - 0xE0100, // E0100..E01EF; Variation Selectors Supplement
1.2096 - 0xE01F0, // unassigned
1.2097 - 0xF0000, // F0000..FFFFF; Supplementary Private Use Area-A
1.2098 - 0x100000 // 100000..10FFFF; Supplementary Private Use Area-B
1.2099 - };
1.2100 -
1.2101 - private static final UnicodeBlock[] blocks = {
1.2102 - BASIC_LATIN,
1.2103 - LATIN_1_SUPPLEMENT,
1.2104 - LATIN_EXTENDED_A,
1.2105 - LATIN_EXTENDED_B,
1.2106 - IPA_EXTENSIONS,
1.2107 - SPACING_MODIFIER_LETTERS,
1.2108 - COMBINING_DIACRITICAL_MARKS,
1.2109 - GREEK,
1.2110 - CYRILLIC,
1.2111 - CYRILLIC_SUPPLEMENTARY,
1.2112 - ARMENIAN,
1.2113 - HEBREW,
1.2114 - ARABIC,
1.2115 - SYRIAC,
1.2116 - ARABIC_SUPPLEMENT,
1.2117 - THAANA,
1.2118 - NKO,
1.2119 - SAMARITAN,
1.2120 - MANDAIC,
1.2121 - null,
1.2122 - DEVANAGARI,
1.2123 - BENGALI,
1.2124 - GURMUKHI,
1.2125 - GUJARATI,
1.2126 - ORIYA,
1.2127 - TAMIL,
1.2128 - TELUGU,
1.2129 - KANNADA,
1.2130 - MALAYALAM,
1.2131 - SINHALA,
1.2132 - THAI,
1.2133 - LAO,
1.2134 - TIBETAN,
1.2135 - MYANMAR,
1.2136 - GEORGIAN,
1.2137 - HANGUL_JAMO,
1.2138 - ETHIOPIC,
1.2139 - ETHIOPIC_SUPPLEMENT,
1.2140 - CHEROKEE,
1.2141 - UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS,
1.2142 - OGHAM,
1.2143 - RUNIC,
1.2144 - TAGALOG,
1.2145 - HANUNOO,
1.2146 - BUHID,
1.2147 - TAGBANWA,
1.2148 - KHMER,
1.2149 - MONGOLIAN,
1.2150 - UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED,
1.2151 - LIMBU,
1.2152 - TAI_LE,
1.2153 - NEW_TAI_LUE,
1.2154 - KHMER_SYMBOLS,
1.2155 - BUGINESE,
1.2156 - TAI_THAM,
1.2157 - null,
1.2158 - BALINESE,
1.2159 - SUNDANESE,
1.2160 - BATAK,
1.2161 - LEPCHA,
1.2162 - OL_CHIKI,
1.2163 - null,
1.2164 - VEDIC_EXTENSIONS,
1.2165 - PHONETIC_EXTENSIONS,
1.2166 - PHONETIC_EXTENSIONS_SUPPLEMENT,
1.2167 - COMBINING_DIACRITICAL_MARKS_SUPPLEMENT,
1.2168 - LATIN_EXTENDED_ADDITIONAL,
1.2169 - GREEK_EXTENDED,
1.2170 - GENERAL_PUNCTUATION,
1.2171 - SUPERSCRIPTS_AND_SUBSCRIPTS,
1.2172 - CURRENCY_SYMBOLS,
1.2173 - COMBINING_MARKS_FOR_SYMBOLS,
1.2174 - LETTERLIKE_SYMBOLS,
1.2175 - NUMBER_FORMS,
1.2176 - ARROWS,
1.2177 - MATHEMATICAL_OPERATORS,
1.2178 - MISCELLANEOUS_TECHNICAL,
1.2179 - CONTROL_PICTURES,
1.2180 - OPTICAL_CHARACTER_RECOGNITION,
1.2181 - ENCLOSED_ALPHANUMERICS,
1.2182 - BOX_DRAWING,
1.2183 - BLOCK_ELEMENTS,
1.2184 - GEOMETRIC_SHAPES,
1.2185 - MISCELLANEOUS_SYMBOLS,
1.2186 - DINGBATS,
1.2187 - MISCELLANEOUS_MATHEMATICAL_SYMBOLS_A,
1.2188 - SUPPLEMENTAL_ARROWS_A,
1.2189 - BRAILLE_PATTERNS,
1.2190 - SUPPLEMENTAL_ARROWS_B,
1.2191 - MISCELLANEOUS_MATHEMATICAL_SYMBOLS_B,
1.2192 - SUPPLEMENTAL_MATHEMATICAL_OPERATORS,
1.2193 - MISCELLANEOUS_SYMBOLS_AND_ARROWS,
1.2194 - GLAGOLITIC,
1.2195 - LATIN_EXTENDED_C,
1.2196 - COPTIC,
1.2197 - GEORGIAN_SUPPLEMENT,
1.2198 - TIFINAGH,
1.2199 - ETHIOPIC_EXTENDED,
1.2200 - CYRILLIC_EXTENDED_A,
1.2201 - SUPPLEMENTAL_PUNCTUATION,
1.2202 - CJK_RADICALS_SUPPLEMENT,
1.2203 - KANGXI_RADICALS,
1.2204 - null,
1.2205 - IDEOGRAPHIC_DESCRIPTION_CHARACTERS,
1.2206 - CJK_SYMBOLS_AND_PUNCTUATION,
1.2207 - HIRAGANA,
1.2208 - KATAKANA,
1.2209 - BOPOMOFO,
1.2210 - HANGUL_COMPATIBILITY_JAMO,
1.2211 - KANBUN,
1.2212 - BOPOMOFO_EXTENDED,
1.2213 - CJK_STROKES,
1.2214 - KATAKANA_PHONETIC_EXTENSIONS,
1.2215 - ENCLOSED_CJK_LETTERS_AND_MONTHS,
1.2216 - CJK_COMPATIBILITY,
1.2217 - CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A,
1.2218 - YIJING_HEXAGRAM_SYMBOLS,
1.2219 - CJK_UNIFIED_IDEOGRAPHS,
1.2220 - YI_SYLLABLES,
1.2221 - YI_RADICALS,
1.2222 - LISU,
1.2223 - VAI,
1.2224 - CYRILLIC_EXTENDED_B,
1.2225 - BAMUM,
1.2226 - MODIFIER_TONE_LETTERS,
1.2227 - LATIN_EXTENDED_D,
1.2228 - SYLOTI_NAGRI,
1.2229 - COMMON_INDIC_NUMBER_FORMS,
1.2230 - PHAGS_PA,
1.2231 - SAURASHTRA,
1.2232 - DEVANAGARI_EXTENDED,
1.2233 - KAYAH_LI,
1.2234 - REJANG,
1.2235 - HANGUL_JAMO_EXTENDED_A,
1.2236 - JAVANESE,
1.2237 - null,
1.2238 - CHAM,
1.2239 - MYANMAR_EXTENDED_A,
1.2240 - TAI_VIET,
1.2241 - null,
1.2242 - ETHIOPIC_EXTENDED_A,
1.2243 - null,
1.2244 - MEETEI_MAYEK,
1.2245 - HANGUL_SYLLABLES,
1.2246 - HANGUL_JAMO_EXTENDED_B,
1.2247 - HIGH_SURROGATES,
1.2248 - HIGH_PRIVATE_USE_SURROGATES,
1.2249 - LOW_SURROGATES,
1.2250 - PRIVATE_USE_AREA,
1.2251 - CJK_COMPATIBILITY_IDEOGRAPHS,
1.2252 - ALPHABETIC_PRESENTATION_FORMS,
1.2253 - ARABIC_PRESENTATION_FORMS_A,
1.2254 - VARIATION_SELECTORS,
1.2255 - VERTICAL_FORMS,
1.2256 - COMBINING_HALF_MARKS,
1.2257 - CJK_COMPATIBILITY_FORMS,
1.2258 - SMALL_FORM_VARIANTS,
1.2259 - ARABIC_PRESENTATION_FORMS_B,
1.2260 - HALFWIDTH_AND_FULLWIDTH_FORMS,
1.2261 - SPECIALS,
1.2262 - LINEAR_B_SYLLABARY,
1.2263 - LINEAR_B_IDEOGRAMS,
1.2264 - AEGEAN_NUMBERS,
1.2265 - ANCIENT_GREEK_NUMBERS,
1.2266 - ANCIENT_SYMBOLS,
1.2267 - PHAISTOS_DISC,
1.2268 - null,
1.2269 - LYCIAN,
1.2270 - CARIAN,
1.2271 - null,
1.2272 - OLD_ITALIC,
1.2273 - GOTHIC,
1.2274 - null,
1.2275 - UGARITIC,
1.2276 - OLD_PERSIAN,
1.2277 - null,
1.2278 - DESERET,
1.2279 - SHAVIAN,
1.2280 - OSMANYA,
1.2281 - null,
1.2282 - CYPRIOT_SYLLABARY,
1.2283 - IMPERIAL_ARAMAIC,
1.2284 - null,
1.2285 - PHOENICIAN,
1.2286 - LYDIAN,
1.2287 - null,
1.2288 - KHAROSHTHI,
1.2289 - OLD_SOUTH_ARABIAN,
1.2290 - null,
1.2291 - AVESTAN,
1.2292 - INSCRIPTIONAL_PARTHIAN,
1.2293 - INSCRIPTIONAL_PAHLAVI,
1.2294 - null,
1.2295 - OLD_TURKIC,
1.2296 - null,
1.2297 - RUMI_NUMERAL_SYMBOLS,
1.2298 - null,
1.2299 - BRAHMI,
1.2300 - KAITHI,
1.2301 - null,
1.2302 - CUNEIFORM,
1.2303 - CUNEIFORM_NUMBERS_AND_PUNCTUATION,
1.2304 - null,
1.2305 - EGYPTIAN_HIEROGLYPHS,
1.2306 - null,
1.2307 - BAMUM_SUPPLEMENT,
1.2308 - null,
1.2309 - KANA_SUPPLEMENT,
1.2310 - null,
1.2311 - BYZANTINE_MUSICAL_SYMBOLS,
1.2312 - MUSICAL_SYMBOLS,
1.2313 - ANCIENT_GREEK_MUSICAL_NOTATION,
1.2314 - null,
1.2315 - TAI_XUAN_JING_SYMBOLS,
1.2316 - COUNTING_ROD_NUMERALS,
1.2317 - null,
1.2318 - MATHEMATICAL_ALPHANUMERIC_SYMBOLS,
1.2319 - null,
1.2320 - MAHJONG_TILES,
1.2321 - DOMINO_TILES,
1.2322 - PLAYING_CARDS,
1.2323 - ENCLOSED_ALPHANUMERIC_SUPPLEMENT,
1.2324 - ENCLOSED_IDEOGRAPHIC_SUPPLEMENT,
1.2325 - MISCELLANEOUS_SYMBOLS_AND_PICTOGRAPHS,
1.2326 - EMOTICONS,
1.2327 - null,
1.2328 - TRANSPORT_AND_MAP_SYMBOLS,
1.2329 - ALCHEMICAL_SYMBOLS,
1.2330 - null,
1.2331 - CJK_UNIFIED_IDEOGRAPHS_EXTENSION_B,
1.2332 - null,
1.2333 - CJK_UNIFIED_IDEOGRAPHS_EXTENSION_C,
1.2334 - CJK_UNIFIED_IDEOGRAPHS_EXTENSION_D,
1.2335 - null,
1.2336 - CJK_COMPATIBILITY_IDEOGRAPHS_SUPPLEMENT,
1.2337 - null,
1.2338 - TAGS,
1.2339 - null,
1.2340 - VARIATION_SELECTORS_SUPPLEMENT,
1.2341 - null,
1.2342 - SUPPLEMENTARY_PRIVATE_USE_AREA_A,
1.2343 - SUPPLEMENTARY_PRIVATE_USE_AREA_B
1.2344 - };
1.2345 -
1.2346 -
1.2347 - /**
1.2348 - * Returns the object representing the Unicode block containing the
1.2349 - * given character, or {@code null} if the character is not a
1.2350 - * member of a defined block.
1.2351 - *
1.2352 - * <p><b>Note:</b> This method cannot handle
1.2353 - * <a href="Character.html#supplementary"> supplementary
1.2354 - * characters</a>. To support all Unicode characters, including
1.2355 - * supplementary characters, use the {@link #of(int)} method.
1.2356 - *
1.2357 - * @param c The character in question
1.2358 - * @return The {@code UnicodeBlock} instance representing the
1.2359 - * Unicode block of which this character is a member, or
1.2360 - * {@code null} if the character is not a member of any
1.2361 - * Unicode block
1.2362 - */
1.2363 - public static UnicodeBlock of(char c) {
1.2364 - return of((int)c);
1.2365 - }
1.2366 -
1.2367 - /**
1.2368 - * Returns the object representing the Unicode block
1.2369 - * containing the given character (Unicode code point), or
1.2370 - * {@code null} if the character is not a member of a
1.2371 - * defined block.
1.2372 - *
1.2373 - * @param codePoint the character (Unicode code point) in question.
1.2374 - * @return The {@code UnicodeBlock} instance representing the
1.2375 - * Unicode block of which this character is a member, or
1.2376 - * {@code null} if the character is not a member of any
1.2377 - * Unicode block
1.2378 - * @exception IllegalArgumentException if the specified
1.2379 - * {@code codePoint} is an invalid Unicode code point.
1.2380 - * @see Character#isValidCodePoint(int)
1.2381 - * @since 1.5
1.2382 - */
1.2383 - public static UnicodeBlock of(int codePoint) {
1.2384 - if (!isValidCodePoint(codePoint)) {
1.2385 - throw new IllegalArgumentException();
1.2386 - }
1.2387 -
1.2388 - int top, bottom, current;
1.2389 - bottom = 0;
1.2390 - top = blockStarts.length;
1.2391 - current = top/2;
1.2392 -
1.2393 - // invariant: top > current >= bottom && codePoint >= unicodeBlockStarts[bottom]
1.2394 - while (top - bottom > 1) {
1.2395 - if (codePoint >= blockStarts[current]) {
1.2396 - bottom = current;
1.2397 - } else {
1.2398 - top = current;
1.2399 - }
1.2400 - current = (top + bottom) / 2;
1.2401 - }
1.2402 - return blocks[current];
1.2403 - }
1.2404 -
1.2405 - /**
1.2406 - * Returns the UnicodeBlock with the given name. Block
1.2407 - * names are determined by The Unicode Standard. The file
1.2408 - * Blocks-<version>.txt defines blocks for a particular
1.2409 - * version of the standard. The {@link Character} class specifies
1.2410 - * the version of the standard that it supports.
1.2411 - * <p>
1.2412 - * This method accepts block names in the following forms:
1.2413 - * <ol>
1.2414 - * <li> Canonical block names as defined by the Unicode Standard.
1.2415 - * For example, the standard defines a "Basic Latin" block. Therefore, this
1.2416 - * method accepts "Basic Latin" as a valid block name. The documentation of
1.2417 - * each UnicodeBlock provides the canonical name.
1.2418 - * <li>Canonical block names with all spaces removed. For example, "BasicLatin"
1.2419 - * is a valid block name for the "Basic Latin" block.
1.2420 - * <li>The text representation of each constant UnicodeBlock identifier.
1.2421 - * For example, this method will return the {@link #BASIC_LATIN} block if
1.2422 - * provided with the "BASIC_LATIN" name. This form replaces all spaces and
1.2423 - * hyphens in the canonical name with underscores.
1.2424 - * </ol>
1.2425 - * Finally, character case is ignored for all of the valid block name forms.
1.2426 - * For example, "BASIC_LATIN" and "basic_latin" are both valid block names.
1.2427 - * The en_US locale's case mapping rules are used to provide case-insensitive
1.2428 - * string comparisons for block name validation.
1.2429 - * <p>
1.2430 - * If the Unicode Standard changes block names, both the previous and
1.2431 - * current names will be accepted.
1.2432 - *
1.2433 - * @param blockName A {@code UnicodeBlock} name.
1.2434 - * @return The {@code UnicodeBlock} instance identified
1.2435 - * by {@code blockName}
1.2436 - * @throws IllegalArgumentException if {@code blockName} is an
1.2437 - * invalid name
1.2438 - * @throws NullPointerException if {@code blockName} is null
1.2439 - * @since 1.5
1.2440 - */
1.2441 - public static final UnicodeBlock forName(String blockName) {
1.2442 - UnicodeBlock block = map.get(blockName.toUpperCase(Locale.US));
1.2443 - if (block == null) {
1.2444 - throw new IllegalArgumentException();
1.2445 - }
1.2446 - return block;
1.2447 - }
1.2448 - }
1.2449 -
1.2450 -
1.2451 - /**
1.2452 - * A family of character subsets representing the character scripts
1.2453 - * defined in the <a href="http://www.unicode.org/reports/tr24/">
1.2454 - * <i>Unicode Standard Annex #24: Script Names</i></a>. Every Unicode
1.2455 - * character is assigned to a single Unicode script, either a specific
1.2456 - * script, such as {@link Character.UnicodeScript#LATIN Latin}, or
1.2457 - * one of the following three special values,
1.2458 - * {@link Character.UnicodeScript#INHERITED Inherited},
1.2459 - * {@link Character.UnicodeScript#COMMON Common} or
1.2460 - * {@link Character.UnicodeScript#UNKNOWN Unknown}.
1.2461 - *
1.2462 - * @since 1.7
1.2463 - */
1.2464 - public static enum UnicodeScript {
1.2465 - /**
1.2466 - * Unicode script "Common".
1.2467 - */
1.2468 - COMMON,
1.2469 -
1.2470 - /**
1.2471 - * Unicode script "Latin".
1.2472 - */
1.2473 - LATIN,
1.2474 -
1.2475 - /**
1.2476 - * Unicode script "Greek".
1.2477 - */
1.2478 - GREEK,
1.2479 -
1.2480 - /**
1.2481 - * Unicode script "Cyrillic".
1.2482 - */
1.2483 - CYRILLIC,
1.2484 -
1.2485 - /**
1.2486 - * Unicode script "Armenian".
1.2487 - */
1.2488 - ARMENIAN,
1.2489 -
1.2490 - /**
1.2491 - * Unicode script "Hebrew".
1.2492 - */
1.2493 - HEBREW,
1.2494 -
1.2495 - /**
1.2496 - * Unicode script "Arabic".
1.2497 - */
1.2498 - ARABIC,
1.2499 -
1.2500 - /**
1.2501 - * Unicode script "Syriac".
1.2502 - */
1.2503 - SYRIAC,
1.2504 -
1.2505 - /**
1.2506 - * Unicode script "Thaana".
1.2507 - */
1.2508 - THAANA,
1.2509 -
1.2510 - /**
1.2511 - * Unicode script "Devanagari".
1.2512 - */
1.2513 - DEVANAGARI,
1.2514 -
1.2515 - /**
1.2516 - * Unicode script "Bengali".
1.2517 - */
1.2518 - BENGALI,
1.2519 -
1.2520 - /**
1.2521 - * Unicode script "Gurmukhi".
1.2522 - */
1.2523 - GURMUKHI,
1.2524 -
1.2525 - /**
1.2526 - * Unicode script "Gujarati".
1.2527 - */
1.2528 - GUJARATI,
1.2529 -
1.2530 - /**
1.2531 - * Unicode script "Oriya".
1.2532 - */
1.2533 - ORIYA,
1.2534 -
1.2535 - /**
1.2536 - * Unicode script "Tamil".
1.2537 - */
1.2538 - TAMIL,
1.2539 -
1.2540 - /**
1.2541 - * Unicode script "Telugu".
1.2542 - */
1.2543 - TELUGU,
1.2544 -
1.2545 - /**
1.2546 - * Unicode script "Kannada".
1.2547 - */
1.2548 - KANNADA,
1.2549 -
1.2550 - /**
1.2551 - * Unicode script "Malayalam".
1.2552 - */
1.2553 - MALAYALAM,
1.2554 -
1.2555 - /**
1.2556 - * Unicode script "Sinhala".
1.2557 - */
1.2558 - SINHALA,
1.2559 -
1.2560 - /**
1.2561 - * Unicode script "Thai".
1.2562 - */
1.2563 - THAI,
1.2564 -
1.2565 - /**
1.2566 - * Unicode script "Lao".
1.2567 - */
1.2568 - LAO,
1.2569 -
1.2570 - /**
1.2571 - * Unicode script "Tibetan".
1.2572 - */
1.2573 - TIBETAN,
1.2574 -
1.2575 - /**
1.2576 - * Unicode script "Myanmar".
1.2577 - */
1.2578 - MYANMAR,
1.2579 -
1.2580 - /**
1.2581 - * Unicode script "Georgian".
1.2582 - */
1.2583 - GEORGIAN,
1.2584 -
1.2585 - /**
1.2586 - * Unicode script "Hangul".
1.2587 - */
1.2588 - HANGUL,
1.2589 -
1.2590 - /**
1.2591 - * Unicode script "Ethiopic".
1.2592 - */
1.2593 - ETHIOPIC,
1.2594 -
1.2595 - /**
1.2596 - * Unicode script "Cherokee".
1.2597 - */
1.2598 - CHEROKEE,
1.2599 -
1.2600 - /**
1.2601 - * Unicode script "Canadian_Aboriginal".
1.2602 - */
1.2603 - CANADIAN_ABORIGINAL,
1.2604 -
1.2605 - /**
1.2606 - * Unicode script "Ogham".
1.2607 - */
1.2608 - OGHAM,
1.2609 -
1.2610 - /**
1.2611 - * Unicode script "Runic".
1.2612 - */
1.2613 - RUNIC,
1.2614 -
1.2615 - /**
1.2616 - * Unicode script "Khmer".
1.2617 - */
1.2618 - KHMER,
1.2619 -
1.2620 - /**
1.2621 - * Unicode script "Mongolian".
1.2622 - */
1.2623 - MONGOLIAN,
1.2624 -
1.2625 - /**
1.2626 - * Unicode script "Hiragana".
1.2627 - */
1.2628 - HIRAGANA,
1.2629 -
1.2630 - /**
1.2631 - * Unicode script "Katakana".
1.2632 - */
1.2633 - KATAKANA,
1.2634 -
1.2635 - /**
1.2636 - * Unicode script "Bopomofo".
1.2637 - */
1.2638 - BOPOMOFO,
1.2639 -
1.2640 - /**
1.2641 - * Unicode script "Han".
1.2642 - */
1.2643 - HAN,
1.2644 -
1.2645 - /**
1.2646 - * Unicode script "Yi".
1.2647 - */
1.2648 - YI,
1.2649 -
1.2650 - /**
1.2651 - * Unicode script "Old_Italic".
1.2652 - */
1.2653 - OLD_ITALIC,
1.2654 -
1.2655 - /**
1.2656 - * Unicode script "Gothic".
1.2657 - */
1.2658 - GOTHIC,
1.2659 -
1.2660 - /**
1.2661 - * Unicode script "Deseret".
1.2662 - */
1.2663 - DESERET,
1.2664 -
1.2665 - /**
1.2666 - * Unicode script "Inherited".
1.2667 - */
1.2668 - INHERITED,
1.2669 -
1.2670 - /**
1.2671 - * Unicode script "Tagalog".
1.2672 - */
1.2673 - TAGALOG,
1.2674 -
1.2675 - /**
1.2676 - * Unicode script "Hanunoo".
1.2677 - */
1.2678 - HANUNOO,
1.2679 -
1.2680 - /**
1.2681 - * Unicode script "Buhid".
1.2682 - */
1.2683 - BUHID,
1.2684 -
1.2685 - /**
1.2686 - * Unicode script "Tagbanwa".
1.2687 - */
1.2688 - TAGBANWA,
1.2689 -
1.2690 - /**
1.2691 - * Unicode script "Limbu".
1.2692 - */
1.2693 - LIMBU,
1.2694 -
1.2695 - /**
1.2696 - * Unicode script "Tai_Le".
1.2697 - */
1.2698 - TAI_LE,
1.2699 -
1.2700 - /**
1.2701 - * Unicode script "Linear_B".
1.2702 - */
1.2703 - LINEAR_B,
1.2704 -
1.2705 - /**
1.2706 - * Unicode script "Ugaritic".
1.2707 - */
1.2708 - UGARITIC,
1.2709 -
1.2710 - /**
1.2711 - * Unicode script "Shavian".
1.2712 - */
1.2713 - SHAVIAN,
1.2714 -
1.2715 - /**
1.2716 - * Unicode script "Osmanya".
1.2717 - */
1.2718 - OSMANYA,
1.2719 -
1.2720 - /**
1.2721 - * Unicode script "Cypriot".
1.2722 - */
1.2723 - CYPRIOT,
1.2724 -
1.2725 - /**
1.2726 - * Unicode script "Braille".
1.2727 - */
1.2728 - BRAILLE,
1.2729 -
1.2730 - /**
1.2731 - * Unicode script "Buginese".
1.2732 - */
1.2733 - BUGINESE,
1.2734 -
1.2735 - /**
1.2736 - * Unicode script "Coptic".
1.2737 - */
1.2738 - COPTIC,
1.2739 -
1.2740 - /**
1.2741 - * Unicode script "New_Tai_Lue".
1.2742 - */
1.2743 - NEW_TAI_LUE,
1.2744 -
1.2745 - /**
1.2746 - * Unicode script "Glagolitic".
1.2747 - */
1.2748 - GLAGOLITIC,
1.2749 -
1.2750 - /**
1.2751 - * Unicode script "Tifinagh".
1.2752 - */
1.2753 - TIFINAGH,
1.2754 -
1.2755 - /**
1.2756 - * Unicode script "Syloti_Nagri".
1.2757 - */
1.2758 - SYLOTI_NAGRI,
1.2759 -
1.2760 - /**
1.2761 - * Unicode script "Old_Persian".
1.2762 - */
1.2763 - OLD_PERSIAN,
1.2764 -
1.2765 - /**
1.2766 - * Unicode script "Kharoshthi".
1.2767 - */
1.2768 - KHAROSHTHI,
1.2769 -
1.2770 - /**
1.2771 - * Unicode script "Balinese".
1.2772 - */
1.2773 - BALINESE,
1.2774 -
1.2775 - /**
1.2776 - * Unicode script "Cuneiform".
1.2777 - */
1.2778 - CUNEIFORM,
1.2779 -
1.2780 - /**
1.2781 - * Unicode script "Phoenician".
1.2782 - */
1.2783 - PHOENICIAN,
1.2784 -
1.2785 - /**
1.2786 - * Unicode script "Phags_Pa".
1.2787 - */
1.2788 - PHAGS_PA,
1.2789 -
1.2790 - /**
1.2791 - * Unicode script "Nko".
1.2792 - */
1.2793 - NKO,
1.2794 -
1.2795 - /**
1.2796 - * Unicode script "Sundanese".
1.2797 - */
1.2798 - SUNDANESE,
1.2799 -
1.2800 - /**
1.2801 - * Unicode script "Batak".
1.2802 - */
1.2803 - BATAK,
1.2804 -
1.2805 - /**
1.2806 - * Unicode script "Lepcha".
1.2807 - */
1.2808 - LEPCHA,
1.2809 -
1.2810 - /**
1.2811 - * Unicode script "Ol_Chiki".
1.2812 - */
1.2813 - OL_CHIKI,
1.2814 -
1.2815 - /**
1.2816 - * Unicode script "Vai".
1.2817 - */
1.2818 - VAI,
1.2819 -
1.2820 - /**
1.2821 - * Unicode script "Saurashtra".
1.2822 - */
1.2823 - SAURASHTRA,
1.2824 -
1.2825 - /**
1.2826 - * Unicode script "Kayah_Li".
1.2827 - */
1.2828 - KAYAH_LI,
1.2829 -
1.2830 - /**
1.2831 - * Unicode script "Rejang".
1.2832 - */
1.2833 - REJANG,
1.2834 -
1.2835 - /**
1.2836 - * Unicode script "Lycian".
1.2837 - */
1.2838 - LYCIAN,
1.2839 -
1.2840 - /**
1.2841 - * Unicode script "Carian".
1.2842 - */
1.2843 - CARIAN,
1.2844 -
1.2845 - /**
1.2846 - * Unicode script "Lydian".
1.2847 - */
1.2848 - LYDIAN,
1.2849 -
1.2850 - /**
1.2851 - * Unicode script "Cham".
1.2852 - */
1.2853 - CHAM,
1.2854 -
1.2855 - /**
1.2856 - * Unicode script "Tai_Tham".
1.2857 - */
1.2858 - TAI_THAM,
1.2859 -
1.2860 - /**
1.2861 - * Unicode script "Tai_Viet".
1.2862 - */
1.2863 - TAI_VIET,
1.2864 -
1.2865 - /**
1.2866 - * Unicode script "Avestan".
1.2867 - */
1.2868 - AVESTAN,
1.2869 -
1.2870 - /**
1.2871 - * Unicode script "Egyptian_Hieroglyphs".
1.2872 - */
1.2873 - EGYPTIAN_HIEROGLYPHS,
1.2874 -
1.2875 - /**
1.2876 - * Unicode script "Samaritan".
1.2877 - */
1.2878 - SAMARITAN,
1.2879 -
1.2880 - /**
1.2881 - * Unicode script "Mandaic".
1.2882 - */
1.2883 - MANDAIC,
1.2884 -
1.2885 - /**
1.2886 - * Unicode script "Lisu".
1.2887 - */
1.2888 - LISU,
1.2889 -
1.2890 - /**
1.2891 - * Unicode script "Bamum".
1.2892 - */
1.2893 - BAMUM,
1.2894 -
1.2895 - /**
1.2896 - * Unicode script "Javanese".
1.2897 - */
1.2898 - JAVANESE,
1.2899 -
1.2900 - /**
1.2901 - * Unicode script "Meetei_Mayek".
1.2902 - */
1.2903 - MEETEI_MAYEK,
1.2904 -
1.2905 - /**
1.2906 - * Unicode script "Imperial_Aramaic".
1.2907 - */
1.2908 - IMPERIAL_ARAMAIC,
1.2909 -
1.2910 - /**
1.2911 - * Unicode script "Old_South_Arabian".
1.2912 - */
1.2913 - OLD_SOUTH_ARABIAN,
1.2914 -
1.2915 - /**
1.2916 - * Unicode script "Inscriptional_Parthian".
1.2917 - */
1.2918 - INSCRIPTIONAL_PARTHIAN,
1.2919 -
1.2920 - /**
1.2921 - * Unicode script "Inscriptional_Pahlavi".
1.2922 - */
1.2923 - INSCRIPTIONAL_PAHLAVI,
1.2924 -
1.2925 - /**
1.2926 - * Unicode script "Old_Turkic".
1.2927 - */
1.2928 - OLD_TURKIC,
1.2929 -
1.2930 - /**
1.2931 - * Unicode script "Brahmi".
1.2932 - */
1.2933 - BRAHMI,
1.2934 -
1.2935 - /**
1.2936 - * Unicode script "Kaithi".
1.2937 - */
1.2938 - KAITHI,
1.2939 -
1.2940 - /**
1.2941 - * Unicode script "Unknown".
1.2942 - */
1.2943 - UNKNOWN;
1.2944 -
1.2945 - private static final int[] scriptStarts = {
1.2946 - 0x0000, // 0000..0040; COMMON
1.2947 - 0x0041, // 0041..005A; LATIN
1.2948 - 0x005B, // 005B..0060; COMMON
1.2949 - 0x0061, // 0061..007A; LATIN
1.2950 - 0x007B, // 007B..00A9; COMMON
1.2951 - 0x00AA, // 00AA..00AA; LATIN
1.2952 - 0x00AB, // 00AB..00B9; COMMON
1.2953 - 0x00BA, // 00BA..00BA; LATIN
1.2954 - 0x00BB, // 00BB..00BF; COMMON
1.2955 - 0x00C0, // 00C0..00D6; LATIN
1.2956 - 0x00D7, // 00D7..00D7; COMMON
1.2957 - 0x00D8, // 00D8..00F6; LATIN
1.2958 - 0x00F7, // 00F7..00F7; COMMON
1.2959 - 0x00F8, // 00F8..02B8; LATIN
1.2960 - 0x02B9, // 02B9..02DF; COMMON
1.2961 - 0x02E0, // 02E0..02E4; LATIN
1.2962 - 0x02E5, // 02E5..02E9; COMMON
1.2963 - 0x02EA, // 02EA..02EB; BOPOMOFO
1.2964 - 0x02EC, // 02EC..02FF; COMMON
1.2965 - 0x0300, // 0300..036F; INHERITED
1.2966 - 0x0370, // 0370..0373; GREEK
1.2967 - 0x0374, // 0374..0374; COMMON
1.2968 - 0x0375, // 0375..037D; GREEK
1.2969 - 0x037E, // 037E..0383; COMMON
1.2970 - 0x0384, // 0384..0384; GREEK
1.2971 - 0x0385, // 0385..0385; COMMON
1.2972 - 0x0386, // 0386..0386; GREEK
1.2973 - 0x0387, // 0387..0387; COMMON
1.2974 - 0x0388, // 0388..03E1; GREEK
1.2975 - 0x03E2, // 03E2..03EF; COPTIC
1.2976 - 0x03F0, // 03F0..03FF; GREEK
1.2977 - 0x0400, // 0400..0484; CYRILLIC
1.2978 - 0x0485, // 0485..0486; INHERITED
1.2979 - 0x0487, // 0487..0530; CYRILLIC
1.2980 - 0x0531, // 0531..0588; ARMENIAN
1.2981 - 0x0589, // 0589..0589; COMMON
1.2982 - 0x058A, // 058A..0590; ARMENIAN
1.2983 - 0x0591, // 0591..05FF; HEBREW
1.2984 - 0x0600, // 0600..060B; ARABIC
1.2985 - 0x060C, // 060C..060C; COMMON
1.2986 - 0x060D, // 060D..061A; ARABIC
1.2987 - 0x061B, // 061B..061D; COMMON
1.2988 - 0x061E, // 061E..061E; ARABIC
1.2989 - 0x061F, // 061F..061F; COMMON
1.2990 - 0x0620, // 0620..063F; ARABIC
1.2991 - 0x0640, // 0640..0640; COMMON
1.2992 - 0x0641, // 0641..064A; ARABIC
1.2993 - 0x064B, // 064B..0655; INHERITED
1.2994 - 0x0656, // 0656..065E; ARABIC
1.2995 - 0x065F, // 065F..065F; INHERITED
1.2996 - 0x0660, // 0660..0669; COMMON
1.2997 - 0x066A, // 066A..066F; ARABIC
1.2998 - 0x0670, // 0670..0670; INHERITED
1.2999 - 0x0671, // 0671..06DC; ARABIC
1.3000 - 0x06DD, // 06DD..06DD; COMMON
1.3001 - 0x06DE, // 06DE..06FF; ARABIC
1.3002 - 0x0700, // 0700..074F; SYRIAC
1.3003 - 0x0750, // 0750..077F; ARABIC
1.3004 - 0x0780, // 0780..07BF; THAANA
1.3005 - 0x07C0, // 07C0..07FF; NKO
1.3006 - 0x0800, // 0800..083F; SAMARITAN
1.3007 - 0x0840, // 0840..08FF; MANDAIC
1.3008 - 0x0900, // 0900..0950; DEVANAGARI
1.3009 - 0x0951, // 0951..0952; INHERITED
1.3010 - 0x0953, // 0953..0963; DEVANAGARI
1.3011 - 0x0964, // 0964..0965; COMMON
1.3012 - 0x0966, // 0966..096F; DEVANAGARI
1.3013 - 0x0970, // 0970..0970; COMMON
1.3014 - 0x0971, // 0971..0980; DEVANAGARI
1.3015 - 0x0981, // 0981..0A00; BENGALI
1.3016 - 0x0A01, // 0A01..0A80; GURMUKHI
1.3017 - 0x0A81, // 0A81..0B00; GUJARATI
1.3018 - 0x0B01, // 0B01..0B81; ORIYA
1.3019 - 0x0B82, // 0B82..0C00; TAMIL
1.3020 - 0x0C01, // 0C01..0C81; TELUGU
1.3021 - 0x0C82, // 0C82..0CF0; KANNADA
1.3022 - 0x0D02, // 0D02..0D81; MALAYALAM
1.3023 - 0x0D82, // 0D82..0E00; SINHALA
1.3024 - 0x0E01, // 0E01..0E3E; THAI
1.3025 - 0x0E3F, // 0E3F..0E3F; COMMON
1.3026 - 0x0E40, // 0E40..0E80; THAI
1.3027 - 0x0E81, // 0E81..0EFF; LAO
1.3028 - 0x0F00, // 0F00..0FD4; TIBETAN
1.3029 - 0x0FD5, // 0FD5..0FD8; COMMON
1.3030 - 0x0FD9, // 0FD9..0FFF; TIBETAN
1.3031 - 0x1000, // 1000..109F; MYANMAR
1.3032 - 0x10A0, // 10A0..10FA; GEORGIAN
1.3033 - 0x10FB, // 10FB..10FB; COMMON
1.3034 - 0x10FC, // 10FC..10FF; GEORGIAN
1.3035 - 0x1100, // 1100..11FF; HANGUL
1.3036 - 0x1200, // 1200..139F; ETHIOPIC
1.3037 - 0x13A0, // 13A0..13FF; CHEROKEE
1.3038 - 0x1400, // 1400..167F; CANADIAN_ABORIGINAL
1.3039 - 0x1680, // 1680..169F; OGHAM
1.3040 - 0x16A0, // 16A0..16EA; RUNIC
1.3041 - 0x16EB, // 16EB..16ED; COMMON
1.3042 - 0x16EE, // 16EE..16FF; RUNIC
1.3043 - 0x1700, // 1700..171F; TAGALOG
1.3044 - 0x1720, // 1720..1734; HANUNOO
1.3045 - 0x1735, // 1735..173F; COMMON
1.3046 - 0x1740, // 1740..175F; BUHID
1.3047 - 0x1760, // 1760..177F; TAGBANWA
1.3048 - 0x1780, // 1780..17FF; KHMER
1.3049 - 0x1800, // 1800..1801; MONGOLIAN
1.3050 - 0x1802, // 1802..1803; COMMON
1.3051 - 0x1804, // 1804..1804; MONGOLIAN
1.3052 - 0x1805, // 1805..1805; COMMON
1.3053 - 0x1806, // 1806..18AF; MONGOLIAN
1.3054 - 0x18B0, // 18B0..18FF; CANADIAN_ABORIGINAL
1.3055 - 0x1900, // 1900..194F; LIMBU
1.3056 - 0x1950, // 1950..197F; TAI_LE
1.3057 - 0x1980, // 1980..19DF; NEW_TAI_LUE
1.3058 - 0x19E0, // 19E0..19FF; KHMER
1.3059 - 0x1A00, // 1A00..1A1F; BUGINESE
1.3060 - 0x1A20, // 1A20..1AFF; TAI_THAM
1.3061 - 0x1B00, // 1B00..1B7F; BALINESE
1.3062 - 0x1B80, // 1B80..1BBF; SUNDANESE
1.3063 - 0x1BC0, // 1BC0..1BFF; BATAK
1.3064 - 0x1C00, // 1C00..1C4F; LEPCHA
1.3065 - 0x1C50, // 1C50..1CCF; OL_CHIKI
1.3066 - 0x1CD0, // 1CD0..1CD2; INHERITED
1.3067 - 0x1CD3, // 1CD3..1CD3; COMMON
1.3068 - 0x1CD4, // 1CD4..1CE0; INHERITED
1.3069 - 0x1CE1, // 1CE1..1CE1; COMMON
1.3070 - 0x1CE2, // 1CE2..1CE8; INHERITED
1.3071 - 0x1CE9, // 1CE9..1CEC; COMMON
1.3072 - 0x1CED, // 1CED..1CED; INHERITED
1.3073 - 0x1CEE, // 1CEE..1CFF; COMMON
1.3074 - 0x1D00, // 1D00..1D25; LATIN
1.3075 - 0x1D26, // 1D26..1D2A; GREEK
1.3076 - 0x1D2B, // 1D2B..1D2B; CYRILLIC
1.3077 - 0x1D2C, // 1D2C..1D5C; LATIN
1.3078 - 0x1D5D, // 1D5D..1D61; GREEK
1.3079 - 0x1D62, // 1D62..1D65; LATIN
1.3080 - 0x1D66, // 1D66..1D6A; GREEK
1.3081 - 0x1D6B, // 1D6B..1D77; LATIN
1.3082 - 0x1D78, // 1D78..1D78; CYRILLIC
1.3083 - 0x1D79, // 1D79..1DBE; LATIN
1.3084 - 0x1DBF, // 1DBF..1DBF; GREEK
1.3085 - 0x1DC0, // 1DC0..1DFF; INHERITED
1.3086 - 0x1E00, // 1E00..1EFF; LATIN
1.3087 - 0x1F00, // 1F00..1FFF; GREEK
1.3088 - 0x2000, // 2000..200B; COMMON
1.3089 - 0x200C, // 200C..200D; INHERITED
1.3090 - 0x200E, // 200E..2070; COMMON
1.3091 - 0x2071, // 2071..2073; LATIN
1.3092 - 0x2074, // 2074..207E; COMMON
1.3093 - 0x207F, // 207F..207F; LATIN
1.3094 - 0x2080, // 2080..208F; COMMON
1.3095 - 0x2090, // 2090..209F; LATIN
1.3096 - 0x20A0, // 20A0..20CF; COMMON
1.3097 - 0x20D0, // 20D0..20FF; INHERITED
1.3098 - 0x2100, // 2100..2125; COMMON
1.3099 - 0x2126, // 2126..2126; GREEK
1.3100 - 0x2127, // 2127..2129; COMMON
1.3101 - 0x212A, // 212A..212B; LATIN
1.3102 - 0x212C, // 212C..2131; COMMON
1.3103 - 0x2132, // 2132..2132; LATIN
1.3104 - 0x2133, // 2133..214D; COMMON
1.3105 - 0x214E, // 214E..214E; LATIN
1.3106 - 0x214F, // 214F..215F; COMMON
1.3107 - 0x2160, // 2160..2188; LATIN
1.3108 - 0x2189, // 2189..27FF; COMMON
1.3109 - 0x2800, // 2800..28FF; BRAILLE
1.3110 - 0x2900, // 2900..2BFF; COMMON
1.3111 - 0x2C00, // 2C00..2C5F; GLAGOLITIC
1.3112 - 0x2C60, // 2C60..2C7F; LATIN
1.3113 - 0x2C80, // 2C80..2CFF; COPTIC
1.3114 - 0x2D00, // 2D00..2D2F; GEORGIAN
1.3115 - 0x2D30, // 2D30..2D7F; TIFINAGH
1.3116 - 0x2D80, // 2D80..2DDF; ETHIOPIC
1.3117 - 0x2DE0, // 2DE0..2DFF; CYRILLIC
1.3118 - 0x2E00, // 2E00..2E7F; COMMON
1.3119 - 0x2E80, // 2E80..2FEF; HAN
1.3120 - 0x2FF0, // 2FF0..3004; COMMON
1.3121 - 0x3005, // 3005..3005; HAN
1.3122 - 0x3006, // 3006..3006; COMMON
1.3123 - 0x3007, // 3007..3007; HAN
1.3124 - 0x3008, // 3008..3020; COMMON
1.3125 - 0x3021, // 3021..3029; HAN
1.3126 - 0x302A, // 302A..302D; INHERITED
1.3127 - 0x302E, // 302E..302F; HANGUL
1.3128 - 0x3030, // 3030..3037; COMMON
1.3129 - 0x3038, // 3038..303B; HAN
1.3130 - 0x303C, // 303C..3040; COMMON
1.3131 - 0x3041, // 3041..3098; HIRAGANA
1.3132 - 0x3099, // 3099..309A; INHERITED
1.3133 - 0x309B, // 309B..309C; COMMON
1.3134 - 0x309D, // 309D..309F; HIRAGANA
1.3135 - 0x30A0, // 30A0..30A0; COMMON
1.3136 - 0x30A1, // 30A1..30FA; KATAKANA
1.3137 - 0x30FB, // 30FB..30FC; COMMON
1.3138 - 0x30FD, // 30FD..3104; KATAKANA
1.3139 - 0x3105, // 3105..3130; BOPOMOFO
1.3140 - 0x3131, // 3131..318F; HANGUL
1.3141 - 0x3190, // 3190..319F; COMMON
1.3142 - 0x31A0, // 31A0..31BF; BOPOMOFO
1.3143 - 0x31C0, // 31C0..31EF; COMMON
1.3144 - 0x31F0, // 31F0..31FF; KATAKANA
1.3145 - 0x3200, // 3200..321F; HANGUL
1.3146 - 0x3220, // 3220..325F; COMMON
1.3147 - 0x3260, // 3260..327E; HANGUL
1.3148 - 0x327F, // 327F..32CF; COMMON
1.3149 - 0x32D0, // 32D0..3357; KATAKANA
1.3150 - 0x3358, // 3358..33FF; COMMON
1.3151 - 0x3400, // 3400..4DBF; HAN
1.3152 - 0x4DC0, // 4DC0..4DFF; COMMON
1.3153 - 0x4E00, // 4E00..9FFF; HAN
1.3154 - 0xA000, // A000..A4CF; YI
1.3155 - 0xA4D0, // A4D0..A4FF; LISU
1.3156 - 0xA500, // A500..A63F; VAI
1.3157 - 0xA640, // A640..A69F; CYRILLIC
1.3158 - 0xA6A0, // A6A0..A6FF; BAMUM
1.3159 - 0xA700, // A700..A721; COMMON
1.3160 - 0xA722, // A722..A787; LATIN
1.3161 - 0xA788, // A788..A78A; COMMON
1.3162 - 0xA78B, // A78B..A7FF; LATIN
1.3163 - 0xA800, // A800..A82F; SYLOTI_NAGRI
1.3164 - 0xA830, // A830..A83F; COMMON
1.3165 - 0xA840, // A840..A87F; PHAGS_PA
1.3166 - 0xA880, // A880..A8DF; SAURASHTRA
1.3167 - 0xA8E0, // A8E0..A8FF; DEVANAGARI
1.3168 - 0xA900, // A900..A92F; KAYAH_LI
1.3169 - 0xA930, // A930..A95F; REJANG
1.3170 - 0xA960, // A960..A97F; HANGUL
1.3171 - 0xA980, // A980..A9FF; JAVANESE
1.3172 - 0xAA00, // AA00..AA5F; CHAM
1.3173 - 0xAA60, // AA60..AA7F; MYANMAR
1.3174 - 0xAA80, // AA80..AB00; TAI_VIET
1.3175 - 0xAB01, // AB01..ABBF; ETHIOPIC
1.3176 - 0xABC0, // ABC0..ABFF; MEETEI_MAYEK
1.3177 - 0xAC00, // AC00..D7FB; HANGUL
1.3178 - 0xD7FC, // D7FC..F8FF; UNKNOWN
1.3179 - 0xF900, // F900..FAFF; HAN
1.3180 - 0xFB00, // FB00..FB12; LATIN
1.3181 - 0xFB13, // FB13..FB1C; ARMENIAN
1.3182 - 0xFB1D, // FB1D..FB4F; HEBREW
1.3183 - 0xFB50, // FB50..FD3D; ARABIC
1.3184 - 0xFD3E, // FD3E..FD4F; COMMON
1.3185 - 0xFD50, // FD50..FDFC; ARABIC
1.3186 - 0xFDFD, // FDFD..FDFF; COMMON
1.3187 - 0xFE00, // FE00..FE0F; INHERITED
1.3188 - 0xFE10, // FE10..FE1F; COMMON
1.3189 - 0xFE20, // FE20..FE2F; INHERITED
1.3190 - 0xFE30, // FE30..FE6F; COMMON
1.3191 - 0xFE70, // FE70..FEFE; ARABIC
1.3192 - 0xFEFF, // FEFF..FF20; COMMON
1.3193 - 0xFF21, // FF21..FF3A; LATIN
1.3194 - 0xFF3B, // FF3B..FF40; COMMON
1.3195 - 0xFF41, // FF41..FF5A; LATIN
1.3196 - 0xFF5B, // FF5B..FF65; COMMON
1.3197 - 0xFF66, // FF66..FF6F; KATAKANA
1.3198 - 0xFF70, // FF70..FF70; COMMON
1.3199 - 0xFF71, // FF71..FF9D; KATAKANA
1.3200 - 0xFF9E, // FF9E..FF9F; COMMON
1.3201 - 0xFFA0, // FFA0..FFDF; HANGUL
1.3202 - 0xFFE0, // FFE0..FFFF; COMMON
1.3203 - 0x10000, // 10000..100FF; LINEAR_B
1.3204 - 0x10100, // 10100..1013F; COMMON
1.3205 - 0x10140, // 10140..1018F; GREEK
1.3206 - 0x10190, // 10190..101FC; COMMON
1.3207 - 0x101FD, // 101FD..1027F; INHERITED
1.3208 - 0x10280, // 10280..1029F; LYCIAN
1.3209 - 0x102A0, // 102A0..102FF; CARIAN
1.3210 - 0x10300, // 10300..1032F; OLD_ITALIC
1.3211 - 0x10330, // 10330..1037F; GOTHIC
1.3212 - 0x10380, // 10380..1039F; UGARITIC
1.3213 - 0x103A0, // 103A0..103FF; OLD_PERSIAN
1.3214 - 0x10400, // 10400..1044F; DESERET
1.3215 - 0x10450, // 10450..1047F; SHAVIAN
1.3216 - 0x10480, // 10480..107FF; OSMANYA
1.3217 - 0x10800, // 10800..1083F; CYPRIOT
1.3218 - 0x10840, // 10840..108FF; IMPERIAL_ARAMAIC
1.3219 - 0x10900, // 10900..1091F; PHOENICIAN
1.3220 - 0x10920, // 10920..109FF; LYDIAN
1.3221 - 0x10A00, // 10A00..10A5F; KHAROSHTHI
1.3222 - 0x10A60, // 10A60..10AFF; OLD_SOUTH_ARABIAN
1.3223 - 0x10B00, // 10B00..10B3F; AVESTAN
1.3224 - 0x10B40, // 10B40..10B5F; INSCRIPTIONAL_PARTHIAN
1.3225 - 0x10B60, // 10B60..10BFF; INSCRIPTIONAL_PAHLAVI
1.3226 - 0x10C00, // 10C00..10E5F; OLD_TURKIC
1.3227 - 0x10E60, // 10E60..10FFF; ARABIC
1.3228 - 0x11000, // 11000..1107F; BRAHMI
1.3229 - 0x11080, // 11080..11FFF; KAITHI
1.3230 - 0x12000, // 12000..12FFF; CUNEIFORM
1.3231 - 0x13000, // 13000..167FF; EGYPTIAN_HIEROGLYPHS
1.3232 - 0x16800, // 16800..16A38; BAMUM
1.3233 - 0x1B000, // 1B000..1B000; KATAKANA
1.3234 - 0x1B001, // 1B001..1CFFF; HIRAGANA
1.3235 - 0x1D000, // 1D000..1D166; COMMON
1.3236 - 0x1D167, // 1D167..1D169; INHERITED
1.3237 - 0x1D16A, // 1D16A..1D17A; COMMON
1.3238 - 0x1D17B, // 1D17B..1D182; INHERITED
1.3239 - 0x1D183, // 1D183..1D184; COMMON
1.3240 - 0x1D185, // 1D185..1D18B; INHERITED
1.3241 - 0x1D18C, // 1D18C..1D1A9; COMMON
1.3242 - 0x1D1AA, // 1D1AA..1D1AD; INHERITED
1.3243 - 0x1D1AE, // 1D1AE..1D1FF; COMMON
1.3244 - 0x1D200, // 1D200..1D2FF; GREEK
1.3245 - 0x1D300, // 1D300..1F1FF; COMMON
1.3246 - 0x1F200, // 1F200..1F200; HIRAGANA
1.3247 - 0x1F201, // 1F210..1FFFF; COMMON
1.3248 - 0x20000, // 20000..E0000; HAN
1.3249 - 0xE0001, // E0001..E00FF; COMMON
1.3250 - 0xE0100, // E0100..E01EF; INHERITED
1.3251 - 0xE01F0 // E01F0..10FFFF; UNKNOWN
1.3252 -
1.3253 - };
1.3254 -
1.3255 - private static final UnicodeScript[] scripts = {
1.3256 - COMMON,
1.3257 - LATIN,
1.3258 - COMMON,
1.3259 - LATIN,
1.3260 - COMMON,
1.3261 - LATIN,
1.3262 - COMMON,
1.3263 - LATIN,
1.3264 - COMMON,
1.3265 - LATIN,
1.3266 - COMMON,
1.3267 - LATIN,
1.3268 - COMMON,
1.3269 - LATIN,
1.3270 - COMMON,
1.3271 - LATIN,
1.3272 - COMMON,
1.3273 - BOPOMOFO,
1.3274 - COMMON,
1.3275 - INHERITED,
1.3276 - GREEK,
1.3277 - COMMON,
1.3278 - GREEK,
1.3279 - COMMON,
1.3280 - GREEK,
1.3281 - COMMON,
1.3282 - GREEK,
1.3283 - COMMON,
1.3284 - GREEK,
1.3285 - COPTIC,
1.3286 - GREEK,
1.3287 - CYRILLIC,
1.3288 - INHERITED,
1.3289 - CYRILLIC,
1.3290 - ARMENIAN,
1.3291 - COMMON,
1.3292 - ARMENIAN,
1.3293 - HEBREW,
1.3294 - ARABIC,
1.3295 - COMMON,
1.3296 - ARABIC,
1.3297 - COMMON,
1.3298 - ARABIC,
1.3299 - COMMON,
1.3300 - ARABIC,
1.3301 - COMMON,
1.3302 - ARABIC,
1.3303 - INHERITED,
1.3304 - ARABIC,
1.3305 - INHERITED,
1.3306 - COMMON,
1.3307 - ARABIC,
1.3308 - INHERITED,
1.3309 - ARABIC,
1.3310 - COMMON,
1.3311 - ARABIC,
1.3312 - SYRIAC,
1.3313 - ARABIC,
1.3314 - THAANA,
1.3315 - NKO,
1.3316 - SAMARITAN,
1.3317 - MANDAIC,
1.3318 - DEVANAGARI,
1.3319 - INHERITED,
1.3320 - DEVANAGARI,
1.3321 - COMMON,
1.3322 - DEVANAGARI,
1.3323 - COMMON,
1.3324 - DEVANAGARI,
1.3325 - BENGALI,
1.3326 - GURMUKHI,
1.3327 - GUJARATI,
1.3328 - ORIYA,
1.3329 - TAMIL,
1.3330 - TELUGU,
1.3331 - KANNADA,
1.3332 - MALAYALAM,
1.3333 - SINHALA,
1.3334 - THAI,
1.3335 - COMMON,
1.3336 - THAI,
1.3337 - LAO,
1.3338 - TIBETAN,
1.3339 - COMMON,
1.3340 - TIBETAN,
1.3341 - MYANMAR,
1.3342 - GEORGIAN,
1.3343 - COMMON,
1.3344 - GEORGIAN,
1.3345 - HANGUL,
1.3346 - ETHIOPIC,
1.3347 - CHEROKEE,
1.3348 - CANADIAN_ABORIGINAL,
1.3349 - OGHAM,
1.3350 - RUNIC,
1.3351 - COMMON,
1.3352 - RUNIC,
1.3353 - TAGALOG,
1.3354 - HANUNOO,
1.3355 - COMMON,
1.3356 - BUHID,
1.3357 - TAGBANWA,
1.3358 - KHMER,
1.3359 - MONGOLIAN,
1.3360 - COMMON,
1.3361 - MONGOLIAN,
1.3362 - COMMON,
1.3363 - MONGOLIAN,
1.3364 - CANADIAN_ABORIGINAL,
1.3365 - LIMBU,
1.3366 - TAI_LE,
1.3367 - NEW_TAI_LUE,
1.3368 - KHMER,
1.3369 - BUGINESE,
1.3370 - TAI_THAM,
1.3371 - BALINESE,
1.3372 - SUNDANESE,
1.3373 - BATAK,
1.3374 - LEPCHA,
1.3375 - OL_CHIKI,
1.3376 - INHERITED,
1.3377 - COMMON,
1.3378 - INHERITED,
1.3379 - COMMON,
1.3380 - INHERITED,
1.3381 - COMMON,
1.3382 - INHERITED,
1.3383 - COMMON,
1.3384 - LATIN,
1.3385 - GREEK,
1.3386 - CYRILLIC,
1.3387 - LATIN,
1.3388 - GREEK,
1.3389 - LATIN,
1.3390 - GREEK,
1.3391 - LATIN,
1.3392 - CYRILLIC,
1.3393 - LATIN,
1.3394 - GREEK,
1.3395 - INHERITED,
1.3396 - LATIN,
1.3397 - GREEK,
1.3398 - COMMON,
1.3399 - INHERITED,
1.3400 - COMMON,
1.3401 - LATIN,
1.3402 - COMMON,
1.3403 - LATIN,
1.3404 - COMMON,
1.3405 - LATIN,
1.3406 - COMMON,
1.3407 - INHERITED,
1.3408 - COMMON,
1.3409 - GREEK,
1.3410 - COMMON,
1.3411 - LATIN,
1.3412 - COMMON,
1.3413 - LATIN,
1.3414 - COMMON,
1.3415 - LATIN,
1.3416 - COMMON,
1.3417 - LATIN,
1.3418 - COMMON,
1.3419 - BRAILLE,
1.3420 - COMMON,
1.3421 - GLAGOLITIC,
1.3422 - LATIN,
1.3423 - COPTIC,
1.3424 - GEORGIAN,
1.3425 - TIFINAGH,
1.3426 - ETHIOPIC,
1.3427 - CYRILLIC,
1.3428 - COMMON,
1.3429 - HAN,
1.3430 - COMMON,
1.3431 - HAN,
1.3432 - COMMON,
1.3433 - HAN,
1.3434 - COMMON,
1.3435 - HAN,
1.3436 - INHERITED,
1.3437 - HANGUL,
1.3438 - COMMON,
1.3439 - HAN,
1.3440 - COMMON,
1.3441 - HIRAGANA,
1.3442 - INHERITED,
1.3443 - COMMON,
1.3444 - HIRAGANA,
1.3445 - COMMON,
1.3446 - KATAKANA,
1.3447 - COMMON,
1.3448 - KATAKANA,
1.3449 - BOPOMOFO,
1.3450 - HANGUL,
1.3451 - COMMON,
1.3452 - BOPOMOFO,
1.3453 - COMMON,
1.3454 - KATAKANA,
1.3455 - HANGUL,
1.3456 - COMMON,
1.3457 - HANGUL,
1.3458 - COMMON,
1.3459 - KATAKANA,
1.3460 - COMMON,
1.3461 - HAN,
1.3462 - COMMON,
1.3463 - HAN,
1.3464 - YI,
1.3465 - LISU,
1.3466 - VAI,
1.3467 - CYRILLIC,
1.3468 - BAMUM,
1.3469 - COMMON,
1.3470 - LATIN,
1.3471 - COMMON,
1.3472 - LATIN,
1.3473 - SYLOTI_NAGRI,
1.3474 - COMMON,
1.3475 - PHAGS_PA,
1.3476 - SAURASHTRA,
1.3477 - DEVANAGARI,
1.3478 - KAYAH_LI,
1.3479 - REJANG,
1.3480 - HANGUL,
1.3481 - JAVANESE,
1.3482 - CHAM,
1.3483 - MYANMAR,
1.3484 - TAI_VIET,
1.3485 - ETHIOPIC,
1.3486 - MEETEI_MAYEK,
1.3487 - HANGUL,
1.3488 - UNKNOWN,
1.3489 - HAN,
1.3490 - LATIN,
1.3491 - ARMENIAN,
1.3492 - HEBREW,
1.3493 - ARABIC,
1.3494 - COMMON,
1.3495 - ARABIC,
1.3496 - COMMON,
1.3497 - INHERITED,
1.3498 - COMMON,
1.3499 - INHERITED,
1.3500 - COMMON,
1.3501 - ARABIC,
1.3502 - COMMON,
1.3503 - LATIN,
1.3504 - COMMON,
1.3505 - LATIN,
1.3506 - COMMON,
1.3507 - KATAKANA,
1.3508 - COMMON,
1.3509 - KATAKANA,
1.3510 - COMMON,
1.3511 - HANGUL,
1.3512 - COMMON,
1.3513 - LINEAR_B,
1.3514 - COMMON,
1.3515 - GREEK,
1.3516 - COMMON,
1.3517 - INHERITED,
1.3518 - LYCIAN,
1.3519 - CARIAN,
1.3520 - OLD_ITALIC,
1.3521 - GOTHIC,
1.3522 - UGARITIC,
1.3523 - OLD_PERSIAN,
1.3524 - DESERET,
1.3525 - SHAVIAN,
1.3526 - OSMANYA,
1.3527 - CYPRIOT,
1.3528 - IMPERIAL_ARAMAIC,
1.3529 - PHOENICIAN,
1.3530 - LYDIAN,
1.3531 - KHAROSHTHI,
1.3532 - OLD_SOUTH_ARABIAN,
1.3533 - AVESTAN,
1.3534 - INSCRIPTIONAL_PARTHIAN,
1.3535 - INSCRIPTIONAL_PAHLAVI,
1.3536 - OLD_TURKIC,
1.3537 - ARABIC,
1.3538 - BRAHMI,
1.3539 - KAITHI,
1.3540 - CUNEIFORM,
1.3541 - EGYPTIAN_HIEROGLYPHS,
1.3542 - BAMUM,
1.3543 - KATAKANA,
1.3544 - HIRAGANA,
1.3545 - COMMON,
1.3546 - INHERITED,
1.3547 - COMMON,
1.3548 - INHERITED,
1.3549 - COMMON,
1.3550 - INHERITED,
1.3551 - COMMON,
1.3552 - INHERITED,
1.3553 - COMMON,
1.3554 - GREEK,
1.3555 - COMMON,
1.3556 - HIRAGANA,
1.3557 - COMMON,
1.3558 - HAN,
1.3559 - COMMON,
1.3560 - INHERITED,
1.3561 - UNKNOWN
1.3562 - };
1.3563 -
1.3564 - private static HashMap<String, Character.UnicodeScript> aliases;
1.3565 - static {
1.3566 - aliases = new HashMap<>(128);
1.3567 - aliases.put("ARAB", ARABIC);
1.3568 - aliases.put("ARMI", IMPERIAL_ARAMAIC);
1.3569 - aliases.put("ARMN", ARMENIAN);
1.3570 - aliases.put("AVST", AVESTAN);
1.3571 - aliases.put("BALI", BALINESE);
1.3572 - aliases.put("BAMU", BAMUM);
1.3573 - aliases.put("BATK", BATAK);
1.3574 - aliases.put("BENG", BENGALI);
1.3575 - aliases.put("BOPO", BOPOMOFO);
1.3576 - aliases.put("BRAI", BRAILLE);
1.3577 - aliases.put("BRAH", BRAHMI);
1.3578 - aliases.put("BUGI", BUGINESE);
1.3579 - aliases.put("BUHD", BUHID);
1.3580 - aliases.put("CANS", CANADIAN_ABORIGINAL);
1.3581 - aliases.put("CARI", CARIAN);
1.3582 - aliases.put("CHAM", CHAM);
1.3583 - aliases.put("CHER", CHEROKEE);
1.3584 - aliases.put("COPT", COPTIC);
1.3585 - aliases.put("CPRT", CYPRIOT);
1.3586 - aliases.put("CYRL", CYRILLIC);
1.3587 - aliases.put("DEVA", DEVANAGARI);
1.3588 - aliases.put("DSRT", DESERET);
1.3589 - aliases.put("EGYP", EGYPTIAN_HIEROGLYPHS);
1.3590 - aliases.put("ETHI", ETHIOPIC);
1.3591 - aliases.put("GEOR", GEORGIAN);
1.3592 - aliases.put("GLAG", GLAGOLITIC);
1.3593 - aliases.put("GOTH", GOTHIC);
1.3594 - aliases.put("GREK", GREEK);
1.3595 - aliases.put("GUJR", GUJARATI);
1.3596 - aliases.put("GURU", GURMUKHI);
1.3597 - aliases.put("HANG", HANGUL);
1.3598 - aliases.put("HANI", HAN);
1.3599 - aliases.put("HANO", HANUNOO);
1.3600 - aliases.put("HEBR", HEBREW);
1.3601 - aliases.put("HIRA", HIRAGANA);
1.3602 - // it appears we don't have the KATAKANA_OR_HIRAGANA
1.3603 - //aliases.put("HRKT", KATAKANA_OR_HIRAGANA);
1.3604 - aliases.put("ITAL", OLD_ITALIC);
1.3605 - aliases.put("JAVA", JAVANESE);
1.3606 - aliases.put("KALI", KAYAH_LI);
1.3607 - aliases.put("KANA", KATAKANA);
1.3608 - aliases.put("KHAR", KHAROSHTHI);
1.3609 - aliases.put("KHMR", KHMER);
1.3610 - aliases.put("KNDA", KANNADA);
1.3611 - aliases.put("KTHI", KAITHI);
1.3612 - aliases.put("LANA", TAI_THAM);
1.3613 - aliases.put("LAOO", LAO);
1.3614 - aliases.put("LATN", LATIN);
1.3615 - aliases.put("LEPC", LEPCHA);
1.3616 - aliases.put("LIMB", LIMBU);
1.3617 - aliases.put("LINB", LINEAR_B);
1.3618 - aliases.put("LISU", LISU);
1.3619 - aliases.put("LYCI", LYCIAN);
1.3620 - aliases.put("LYDI", LYDIAN);
1.3621 - aliases.put("MAND", MANDAIC);
1.3622 - aliases.put("MLYM", MALAYALAM);
1.3623 - aliases.put("MONG", MONGOLIAN);
1.3624 - aliases.put("MTEI", MEETEI_MAYEK);
1.3625 - aliases.put("MYMR", MYANMAR);
1.3626 - aliases.put("NKOO", NKO);
1.3627 - aliases.put("OGAM", OGHAM);
1.3628 - aliases.put("OLCK", OL_CHIKI);
1.3629 - aliases.put("ORKH", OLD_TURKIC);
1.3630 - aliases.put("ORYA", ORIYA);
1.3631 - aliases.put("OSMA", OSMANYA);
1.3632 - aliases.put("PHAG", PHAGS_PA);
1.3633 - aliases.put("PHLI", INSCRIPTIONAL_PAHLAVI);
1.3634 - aliases.put("PHNX", PHOENICIAN);
1.3635 - aliases.put("PRTI", INSCRIPTIONAL_PARTHIAN);
1.3636 - aliases.put("RJNG", REJANG);
1.3637 - aliases.put("RUNR", RUNIC);
1.3638 - aliases.put("SAMR", SAMARITAN);
1.3639 - aliases.put("SARB", OLD_SOUTH_ARABIAN);
1.3640 - aliases.put("SAUR", SAURASHTRA);
1.3641 - aliases.put("SHAW", SHAVIAN);
1.3642 - aliases.put("SINH", SINHALA);
1.3643 - aliases.put("SUND", SUNDANESE);
1.3644 - aliases.put("SYLO", SYLOTI_NAGRI);
1.3645 - aliases.put("SYRC", SYRIAC);
1.3646 - aliases.put("TAGB", TAGBANWA);
1.3647 - aliases.put("TALE", TAI_LE);
1.3648 - aliases.put("TALU", NEW_TAI_LUE);
1.3649 - aliases.put("TAML", TAMIL);
1.3650 - aliases.put("TAVT", TAI_VIET);
1.3651 - aliases.put("TELU", TELUGU);
1.3652 - aliases.put("TFNG", TIFINAGH);
1.3653 - aliases.put("TGLG", TAGALOG);
1.3654 - aliases.put("THAA", THAANA);
1.3655 - aliases.put("THAI", THAI);
1.3656 - aliases.put("TIBT", TIBETAN);
1.3657 - aliases.put("UGAR", UGARITIC);
1.3658 - aliases.put("VAII", VAI);
1.3659 - aliases.put("XPEO", OLD_PERSIAN);
1.3660 - aliases.put("XSUX", CUNEIFORM);
1.3661 - aliases.put("YIII", YI);
1.3662 - aliases.put("ZINH", INHERITED);
1.3663 - aliases.put("ZYYY", COMMON);
1.3664 - aliases.put("ZZZZ", UNKNOWN);
1.3665 - }
1.3666 -
1.3667 - /**
1.3668 - * Returns the enum constant representing the Unicode script of which
1.3669 - * the given character (Unicode code point) is assigned to.
1.3670 - *
1.3671 - * @param codePoint the character (Unicode code point) in question.
1.3672 - * @return The {@code UnicodeScript} constant representing the
1.3673 - * Unicode script of which this character is assigned to.
1.3674 - *
1.3675 - * @exception IllegalArgumentException if the specified
1.3676 - * {@code codePoint} is an invalid Unicode code point.
1.3677 - * @see Character#isValidCodePoint(int)
1.3678 - *
1.3679 - */
1.3680 - public static UnicodeScript of(int codePoint) {
1.3681 - if (!isValidCodePoint(codePoint))
1.3682 - throw new IllegalArgumentException();
1.3683 - int type = getType(codePoint);
1.3684 - // leave SURROGATE and PRIVATE_USE for table lookup
1.3685 - if (type == UNASSIGNED)
1.3686 - return UNKNOWN;
1.3687 - int index = Arrays.binarySearch(scriptStarts, codePoint);
1.3688 - if (index < 0)
1.3689 - index = -index - 2;
1.3690 - return scripts[index];
1.3691 - }
1.3692 -
1.3693 - /**
1.3694 - * Returns the UnicodeScript constant with the given Unicode script
1.3695 - * name or the script name alias. Script names and their aliases are
1.3696 - * determined by The Unicode Standard. The files Scripts<version>.txt
1.3697 - * and PropertyValueAliases<version>.txt define script names
1.3698 - * and the script name aliases for a particular version of the
1.3699 - * standard. The {@link Character} class specifies the version of
1.3700 - * the standard that it supports.
1.3701 - * <p>
1.3702 - * Character case is ignored for all of the valid script names.
1.3703 - * The en_US locale's case mapping rules are used to provide
1.3704 - * case-insensitive string comparisons for script name validation.
1.3705 - * <p>
1.3706 - *
1.3707 - * @param scriptName A {@code UnicodeScript} name.
1.3708 - * @return The {@code UnicodeScript} constant identified
1.3709 - * by {@code scriptName}
1.3710 - * @throws IllegalArgumentException if {@code scriptName} is an
1.3711 - * invalid name
1.3712 - * @throws NullPointerException if {@code scriptName} is null
1.3713 - */
1.3714 - public static final UnicodeScript forName(String scriptName) {
1.3715 - scriptName = scriptName.toUpperCase(Locale.ENGLISH);
1.3716 - //.replace(' ', '_'));
1.3717 - UnicodeScript sc = aliases.get(scriptName);
1.3718 - if (sc != null)
1.3719 - return sc;
1.3720 - return valueOf(scriptName);
1.3721 - }
1.3722 - }
1.3723
1.3724 /**
1.3725 * The value of the {@code Character}.
1.3726 @@ -5227,40 +1525,7 @@
1.3727 * @see Character#getType(char)
1.3728 */
1.3729 public static boolean isLowerCase(char ch) {
1.3730 - return isLowerCase((int)ch);
1.3731 - }
1.3732 -
1.3733 - /**
1.3734 - * Determines if the specified character (Unicode code point) is a
1.3735 - * lowercase character.
1.3736 - * <p>
1.3737 - * A character is lowercase if its general category type, provided
1.3738 - * by {@link Character#getType getType(codePoint)}, is
1.3739 - * {@code LOWERCASE_LETTER}, or it has contributory property
1.3740 - * Other_Lowercase as defined by the Unicode Standard.
1.3741 - * <p>
1.3742 - * The following are examples of lowercase characters:
1.3743 - * <p><blockquote><pre>
1.3744 - * a b c d e f g h i j k l m n o p q r s t u v w x y z
1.3745 - * '\u00DF' '\u00E0' '\u00E1' '\u00E2' '\u00E3' '\u00E4' '\u00E5' '\u00E6'
1.3746 - * '\u00E7' '\u00E8' '\u00E9' '\u00EA' '\u00EB' '\u00EC' '\u00ED' '\u00EE'
1.3747 - * '\u00EF' '\u00F0' '\u00F1' '\u00F2' '\u00F3' '\u00F4' '\u00F5' '\u00F6'
1.3748 - * '\u00F8' '\u00F9' '\u00FA' '\u00FB' '\u00FC' '\u00FD' '\u00FE' '\u00FF'
1.3749 - * </pre></blockquote>
1.3750 - * <p> Many other Unicode characters are lowercase too.
1.3751 - *
1.3752 - * @param codePoint the character (Unicode code point) to be tested.
1.3753 - * @return {@code true} if the character is lowercase;
1.3754 - * {@code false} otherwise.
1.3755 - * @see Character#isLowerCase(int)
1.3756 - * @see Character#isTitleCase(int)
1.3757 - * @see Character#toLowerCase(int)
1.3758 - * @see Character#getType(int)
1.3759 - * @since 1.5
1.3760 - */
1.3761 - public static boolean isLowerCase(int codePoint) {
1.3762 - return getType(codePoint) == Character.LOWERCASE_LETTER ||
1.3763 - CharacterData.of(codePoint).isOtherLowercase(codePoint);
1.3764 + throw new UnsupportedOperationException();
1.3765 }
1.3766
1.3767 /**
1.3768 @@ -5295,38 +1560,7 @@
1.3769 * @since 1.0
1.3770 */
1.3771 public static boolean isUpperCase(char ch) {
1.3772 - return isUpperCase((int)ch);
1.3773 - }
1.3774 -
1.3775 - /**
1.3776 - * Determines if the specified character (Unicode code point) is an uppercase character.
1.3777 - * <p>
1.3778 - * A character is uppercase if its general category type, provided by
1.3779 - * {@link Character#getType(int) getType(codePoint)}, is {@code UPPERCASE_LETTER},
1.3780 - * or it has contributory property Other_Uppercase as defined by the Unicode Standard.
1.3781 - * <p>
1.3782 - * The following are examples of uppercase characters:
1.3783 - * <p><blockquote><pre>
1.3784 - * A B C D E F G H I J K L M N O P Q R S T U V W X Y Z
1.3785 - * '\u00C0' '\u00C1' '\u00C2' '\u00C3' '\u00C4' '\u00C5' '\u00C6' '\u00C7'
1.3786 - * '\u00C8' '\u00C9' '\u00CA' '\u00CB' '\u00CC' '\u00CD' '\u00CE' '\u00CF'
1.3787 - * '\u00D0' '\u00D1' '\u00D2' '\u00D3' '\u00D4' '\u00D5' '\u00D6' '\u00D8'
1.3788 - * '\u00D9' '\u00DA' '\u00DB' '\u00DC' '\u00DD' '\u00DE'
1.3789 - * </pre></blockquote>
1.3790 - * <p> Many other Unicode characters are uppercase too.<p>
1.3791 - *
1.3792 - * @param codePoint the character (Unicode code point) to be tested.
1.3793 - * @return {@code true} if the character is uppercase;
1.3794 - * {@code false} otherwise.
1.3795 - * @see Character#isLowerCase(int)
1.3796 - * @see Character#isTitleCase(int)
1.3797 - * @see Character#toUpperCase(int)
1.3798 - * @see Character#getType(int)
1.3799 - * @since 1.5
1.3800 - */
1.3801 - public static boolean isUpperCase(int codePoint) {
1.3802 - return getType(codePoint) == Character.UPPERCASE_LETTER ||
1.3803 - CharacterData.of(codePoint).isOtherUppercase(codePoint);
1.3804 + throw new UnsupportedOperationException();
1.3805 }
1.3806
1.3807 /**
1.3808 @@ -5663,431 +1897,11 @@
1.3809 (1 << Character.DECIMAL_DIGIT_NUMBER)) >> getType(codePoint)) & 1)
1.3810 != 0;
1.3811 }
1.3812 -
1.3813 - /**
1.3814 - * Determines if the specified character is permissible as the first
1.3815 - * character in a Java identifier.
1.3816 - * <p>
1.3817 - * A character may start a Java identifier if and only if
1.3818 - * one of the following is true:
1.3819 - * <ul>
1.3820 - * <li> {@link #isLetter(char) isLetter(ch)} returns {@code true}
1.3821 - * <li> {@link #getType(char) getType(ch)} returns {@code LETTER_NUMBER}
1.3822 - * <li> {@code ch} is a currency symbol (such as {@code '$'})
1.3823 - * <li> {@code ch} is a connecting punctuation character (such as {@code '_'}).
1.3824 - * </ul>
1.3825 - *
1.3826 - * @param ch the character to be tested.
1.3827 - * @return {@code true} if the character may start a Java
1.3828 - * identifier; {@code false} otherwise.
1.3829 - * @see Character#isJavaLetterOrDigit(char)
1.3830 - * @see Character#isJavaIdentifierStart(char)
1.3831 - * @see Character#isJavaIdentifierPart(char)
1.3832 - * @see Character#isLetter(char)
1.3833 - * @see Character#isLetterOrDigit(char)
1.3834 - * @see Character#isUnicodeIdentifierStart(char)
1.3835 - * @since 1.02
1.3836 - * @deprecated Replaced by isJavaIdentifierStart(char).
1.3837 - */
1.3838 - @Deprecated
1.3839 - public static boolean isJavaLetter(char ch) {
1.3840 - return isJavaIdentifierStart(ch);
1.3841 +
1.3842 + static int getType(int x) {
1.3843 + throw new UnsupportedOperationException();
1.3844 }
1.3845 -
1.3846 - /**
1.3847 - * Determines if the specified character may be part of a Java
1.3848 - * identifier as other than the first character.
1.3849 - * <p>
1.3850 - * A character may be part of a Java identifier if and only if any
1.3851 - * of the following are true:
1.3852 - * <ul>
1.3853 - * <li> it is a letter
1.3854 - * <li> it is a currency symbol (such as {@code '$'})
1.3855 - * <li> it is a connecting punctuation character (such as {@code '_'})
1.3856 - * <li> it is a digit
1.3857 - * <li> it is a numeric letter (such as a Roman numeral character)
1.3858 - * <li> it is a combining mark
1.3859 - * <li> it is a non-spacing mark
1.3860 - * <li> {@code isIdentifierIgnorable} returns
1.3861 - * {@code true} for the character.
1.3862 - * </ul>
1.3863 - *
1.3864 - * @param ch the character to be tested.
1.3865 - * @return {@code true} if the character may be part of a
1.3866 - * Java identifier; {@code false} otherwise.
1.3867 - * @see Character#isJavaLetter(char)
1.3868 - * @see Character#isJavaIdentifierStart(char)
1.3869 - * @see Character#isJavaIdentifierPart(char)
1.3870 - * @see Character#isLetter(char)
1.3871 - * @see Character#isLetterOrDigit(char)
1.3872 - * @see Character#isUnicodeIdentifierPart(char)
1.3873 - * @see Character#isIdentifierIgnorable(char)
1.3874 - * @since 1.02
1.3875 - * @deprecated Replaced by isJavaIdentifierPart(char).
1.3876 - */
1.3877 - @Deprecated
1.3878 - public static boolean isJavaLetterOrDigit(char ch) {
1.3879 - return isJavaIdentifierPart(ch);
1.3880 - }
1.3881 -
1.3882 - /**
1.3883 - * Determines if the specified character (Unicode code point) is an alphabet.
1.3884 - * <p>
1.3885 - * A character is considered to be alphabetic if its general category type,
1.3886 - * provided by {@link Character#getType(int) getType(codePoint)}, is any of
1.3887 - * the following:
1.3888 - * <ul>
1.3889 - * <li> <code>UPPERCASE_LETTER</code>
1.3890 - * <li> <code>LOWERCASE_LETTER</code>
1.3891 - * <li> <code>TITLECASE_LETTER</code>
1.3892 - * <li> <code>MODIFIER_LETTER</code>
1.3893 - * <li> <code>OTHER_LETTER</code>
1.3894 - * <li> <code>LETTER_NUMBER</code>
1.3895 - * </ul>
1.3896 - * or it has contributory property Other_Alphabetic as defined by the
1.3897 - * Unicode Standard.
1.3898 - *
1.3899 - * @param codePoint the character (Unicode code point) to be tested.
1.3900 - * @return <code>true</code> if the character is a Unicode alphabet
1.3901 - * character, <code>false</code> otherwise.
1.3902 - * @since 1.7
1.3903 - */
1.3904 - public static boolean isAlphabetic(int codePoint) {
1.3905 - return (((((1 << Character.UPPERCASE_LETTER) |
1.3906 - (1 << Character.LOWERCASE_LETTER) |
1.3907 - (1 << Character.TITLECASE_LETTER) |
1.3908 - (1 << Character.MODIFIER_LETTER) |
1.3909 - (1 << Character.OTHER_LETTER) |
1.3910 - (1 << Character.LETTER_NUMBER)) >> getType(codePoint)) & 1) != 0) ||
1.3911 - CharacterData.of(codePoint).isOtherAlphabetic(codePoint);
1.3912 - }
1.3913 -
1.3914 - /**
1.3915 - * Determines if the specified character (Unicode code point) is a CJKV
1.3916 - * (Chinese, Japanese, Korean and Vietnamese) ideograph, as defined by
1.3917 - * the Unicode Standard.
1.3918 - *
1.3919 - * @param codePoint the character (Unicode code point) to be tested.
1.3920 - * @return <code>true</code> if the character is a Unicode ideograph
1.3921 - * character, <code>false</code> otherwise.
1.3922 - * @since 1.7
1.3923 - */
1.3924 - public static boolean isIdeographic(int codePoint) {
1.3925 - return CharacterData.of(codePoint).isIdeographic(codePoint);
1.3926 - }
1.3927 -
1.3928 - /**
1.3929 - * Determines if the specified character is
1.3930 - * permissible as the first character in a Java identifier.
1.3931 - * <p>
1.3932 - * A character may start a Java identifier if and only if
1.3933 - * one of the following conditions is true:
1.3934 - * <ul>
1.3935 - * <li> {@link #isLetter(char) isLetter(ch)} returns {@code true}
1.3936 - * <li> {@link #getType(char) getType(ch)} returns {@code LETTER_NUMBER}
1.3937 - * <li> {@code ch} is a currency symbol (such as {@code '$'})
1.3938 - * <li> {@code ch} is a connecting punctuation character (such as {@code '_'}).
1.3939 - * </ul>
1.3940 - *
1.3941 - * <p><b>Note:</b> This method cannot handle <a
1.3942 - * href="#supplementary"> supplementary characters</a>. To support
1.3943 - * all Unicode characters, including supplementary characters, use
1.3944 - * the {@link #isJavaIdentifierStart(int)} method.
1.3945 - *
1.3946 - * @param ch the character to be tested.
1.3947 - * @return {@code true} if the character may start a Java identifier;
1.3948 - * {@code false} otherwise.
1.3949 - * @see Character#isJavaIdentifierPart(char)
1.3950 - * @see Character#isLetter(char)
1.3951 - * @see Character#isUnicodeIdentifierStart(char)
1.3952 - * @see javax.lang.model.SourceVersion#isIdentifier(CharSequence)
1.3953 - * @since 1.1
1.3954 - */
1.3955 - public static boolean isJavaIdentifierStart(char ch) {
1.3956 - return isJavaIdentifierStart((int)ch);
1.3957 - }
1.3958 -
1.3959 - /**
1.3960 - * Determines if the character (Unicode code point) is
1.3961 - * permissible as the first character in a Java identifier.
1.3962 - * <p>
1.3963 - * A character may start a Java identifier if and only if
1.3964 - * one of the following conditions is true:
1.3965 - * <ul>
1.3966 - * <li> {@link #isLetter(int) isLetter(codePoint)}
1.3967 - * returns {@code true}
1.3968 - * <li> {@link #getType(int) getType(codePoint)}
1.3969 - * returns {@code LETTER_NUMBER}
1.3970 - * <li> the referenced character is a currency symbol (such as {@code '$'})
1.3971 - * <li> the referenced character is a connecting punctuation character
1.3972 - * (such as {@code '_'}).
1.3973 - * </ul>
1.3974 - *
1.3975 - * @param codePoint the character (Unicode code point) to be tested.
1.3976 - * @return {@code true} if the character may start a Java identifier;
1.3977 - * {@code false} otherwise.
1.3978 - * @see Character#isJavaIdentifierPart(int)
1.3979 - * @see Character#isLetter(int)
1.3980 - * @see Character#isUnicodeIdentifierStart(int)
1.3981 - * @see javax.lang.model.SourceVersion#isIdentifier(CharSequence)
1.3982 - * @since 1.5
1.3983 - */
1.3984 - public static boolean isJavaIdentifierStart(int codePoint) {
1.3985 - return CharacterData.of(codePoint).isJavaIdentifierStart(codePoint);
1.3986 - }
1.3987 -
1.3988 - /**
1.3989 - * Determines if the specified character may be part of a Java
1.3990 - * identifier as other than the first character.
1.3991 - * <p>
1.3992 - * A character may be part of a Java identifier if any of the following
1.3993 - * are true:
1.3994 - * <ul>
1.3995 - * <li> it is a letter
1.3996 - * <li> it is a currency symbol (such as {@code '$'})
1.3997 - * <li> it is a connecting punctuation character (such as {@code '_'})
1.3998 - * <li> it is a digit
1.3999 - * <li> it is a numeric letter (such as a Roman numeral character)
1.4000 - * <li> it is a combining mark
1.4001 - * <li> it is a non-spacing mark
1.4002 - * <li> {@code isIdentifierIgnorable} returns
1.4003 - * {@code true} for the character
1.4004 - * </ul>
1.4005 - *
1.4006 - * <p><b>Note:</b> This method cannot handle <a
1.4007 - * href="#supplementary"> supplementary characters</a>. To support
1.4008 - * all Unicode characters, including supplementary characters, use
1.4009 - * the {@link #isJavaIdentifierPart(int)} method.
1.4010 - *
1.4011 - * @param ch the character to be tested.
1.4012 - * @return {@code true} if the character may be part of a
1.4013 - * Java identifier; {@code false} otherwise.
1.4014 - * @see Character#isIdentifierIgnorable(char)
1.4015 - * @see Character#isJavaIdentifierStart(char)
1.4016 - * @see Character#isLetterOrDigit(char)
1.4017 - * @see Character#isUnicodeIdentifierPart(char)
1.4018 - * @see javax.lang.model.SourceVersion#isIdentifier(CharSequence)
1.4019 - * @since 1.1
1.4020 - */
1.4021 - public static boolean isJavaIdentifierPart(char ch) {
1.4022 - return isJavaIdentifierPart((int)ch);
1.4023 - }
1.4024 -
1.4025 - /**
1.4026 - * Determines if the character (Unicode code point) may be part of a Java
1.4027 - * identifier as other than the first character.
1.4028 - * <p>
1.4029 - * A character may be part of a Java identifier if any of the following
1.4030 - * are true:
1.4031 - * <ul>
1.4032 - * <li> it is a letter
1.4033 - * <li> it is a currency symbol (such as {@code '$'})
1.4034 - * <li> it is a connecting punctuation character (such as {@code '_'})
1.4035 - * <li> it is a digit
1.4036 - * <li> it is a numeric letter (such as a Roman numeral character)
1.4037 - * <li> it is a combining mark
1.4038 - * <li> it is a non-spacing mark
1.4039 - * <li> {@link #isIdentifierIgnorable(int)
1.4040 - * isIdentifierIgnorable(codePoint)} returns {@code true} for
1.4041 - * the character
1.4042 - * </ul>
1.4043 - *
1.4044 - * @param codePoint the character (Unicode code point) to be tested.
1.4045 - * @return {@code true} if the character may be part of a
1.4046 - * Java identifier; {@code false} otherwise.
1.4047 - * @see Character#isIdentifierIgnorable(int)
1.4048 - * @see Character#isJavaIdentifierStart(int)
1.4049 - * @see Character#isLetterOrDigit(int)
1.4050 - * @see Character#isUnicodeIdentifierPart(int)
1.4051 - * @see javax.lang.model.SourceVersion#isIdentifier(CharSequence)
1.4052 - * @since 1.5
1.4053 - */
1.4054 - public static boolean isJavaIdentifierPart(int codePoint) {
1.4055 - return CharacterData.of(codePoint).isJavaIdentifierPart(codePoint);
1.4056 - }
1.4057 -
1.4058 - /**
1.4059 - * Determines if the specified character is permissible as the
1.4060 - * first character in a Unicode identifier.
1.4061 - * <p>
1.4062 - * A character may start a Unicode identifier if and only if
1.4063 - * one of the following conditions is true:
1.4064 - * <ul>
1.4065 - * <li> {@link #isLetter(char) isLetter(ch)} returns {@code true}
1.4066 - * <li> {@link #getType(char) getType(ch)} returns
1.4067 - * {@code LETTER_NUMBER}.
1.4068 - * </ul>
1.4069 - *
1.4070 - * <p><b>Note:</b> This method cannot handle <a
1.4071 - * href="#supplementary"> supplementary characters</a>. To support
1.4072 - * all Unicode characters, including supplementary characters, use
1.4073 - * the {@link #isUnicodeIdentifierStart(int)} method.
1.4074 - *
1.4075 - * @param ch the character to be tested.
1.4076 - * @return {@code true} if the character may start a Unicode
1.4077 - * identifier; {@code false} otherwise.
1.4078 - * @see Character#isJavaIdentifierStart(char)
1.4079 - * @see Character#isLetter(char)
1.4080 - * @see Character#isUnicodeIdentifierPart(char)
1.4081 - * @since 1.1
1.4082 - */
1.4083 - public static boolean isUnicodeIdentifierStart(char ch) {
1.4084 - return isUnicodeIdentifierStart((int)ch);
1.4085 - }
1.4086 -
1.4087 - /**
1.4088 - * Determines if the specified character (Unicode code point) is permissible as the
1.4089 - * first character in a Unicode identifier.
1.4090 - * <p>
1.4091 - * A character may start a Unicode identifier if and only if
1.4092 - * one of the following conditions is true:
1.4093 - * <ul>
1.4094 - * <li> {@link #isLetter(int) isLetter(codePoint)}
1.4095 - * returns {@code true}
1.4096 - * <li> {@link #getType(int) getType(codePoint)}
1.4097 - * returns {@code LETTER_NUMBER}.
1.4098 - * </ul>
1.4099 - * @param codePoint the character (Unicode code point) to be tested.
1.4100 - * @return {@code true} if the character may start a Unicode
1.4101 - * identifier; {@code false} otherwise.
1.4102 - * @see Character#isJavaIdentifierStart(int)
1.4103 - * @see Character#isLetter(int)
1.4104 - * @see Character#isUnicodeIdentifierPart(int)
1.4105 - * @since 1.5
1.4106 - */
1.4107 - public static boolean isUnicodeIdentifierStart(int codePoint) {
1.4108 - return CharacterData.of(codePoint).isUnicodeIdentifierStart(codePoint);
1.4109 - }
1.4110 -
1.4111 - /**
1.4112 - * Determines if the specified character may be part of a Unicode
1.4113 - * identifier as other than the first character.
1.4114 - * <p>
1.4115 - * A character may be part of a Unicode identifier if and only if
1.4116 - * one of the following statements is true:
1.4117 - * <ul>
1.4118 - * <li> it is a letter
1.4119 - * <li> it is a connecting punctuation character (such as {@code '_'})
1.4120 - * <li> it is a digit
1.4121 - * <li> it is a numeric letter (such as a Roman numeral character)
1.4122 - * <li> it is a combining mark
1.4123 - * <li> it is a non-spacing mark
1.4124 - * <li> {@code isIdentifierIgnorable} returns
1.4125 - * {@code true} for this character.
1.4126 - * </ul>
1.4127 - *
1.4128 - * <p><b>Note:</b> This method cannot handle <a
1.4129 - * href="#supplementary"> supplementary characters</a>. To support
1.4130 - * all Unicode characters, including supplementary characters, use
1.4131 - * the {@link #isUnicodeIdentifierPart(int)} method.
1.4132 - *
1.4133 - * @param ch the character to be tested.
1.4134 - * @return {@code true} if the character may be part of a
1.4135 - * Unicode identifier; {@code false} otherwise.
1.4136 - * @see Character#isIdentifierIgnorable(char)
1.4137 - * @see Character#isJavaIdentifierPart(char)
1.4138 - * @see Character#isLetterOrDigit(char)
1.4139 - * @see Character#isUnicodeIdentifierStart(char)
1.4140 - * @since 1.1
1.4141 - */
1.4142 - public static boolean isUnicodeIdentifierPart(char ch) {
1.4143 - return isUnicodeIdentifierPart((int)ch);
1.4144 - }
1.4145 -
1.4146 - /**
1.4147 - * Determines if the specified character (Unicode code point) may be part of a Unicode
1.4148 - * identifier as other than the first character.
1.4149 - * <p>
1.4150 - * A character may be part of a Unicode identifier if and only if
1.4151 - * one of the following statements is true:
1.4152 - * <ul>
1.4153 - * <li> it is a letter
1.4154 - * <li> it is a connecting punctuation character (such as {@code '_'})
1.4155 - * <li> it is a digit
1.4156 - * <li> it is a numeric letter (such as a Roman numeral character)
1.4157 - * <li> it is a combining mark
1.4158 - * <li> it is a non-spacing mark
1.4159 - * <li> {@code isIdentifierIgnorable} returns
1.4160 - * {@code true} for this character.
1.4161 - * </ul>
1.4162 - * @param codePoint the character (Unicode code point) to be tested.
1.4163 - * @return {@code true} if the character may be part of a
1.4164 - * Unicode identifier; {@code false} otherwise.
1.4165 - * @see Character#isIdentifierIgnorable(int)
1.4166 - * @see Character#isJavaIdentifierPart(int)
1.4167 - * @see Character#isLetterOrDigit(int)
1.4168 - * @see Character#isUnicodeIdentifierStart(int)
1.4169 - * @since 1.5
1.4170 - */
1.4171 - public static boolean isUnicodeIdentifierPart(int codePoint) {
1.4172 - return CharacterData.of(codePoint).isUnicodeIdentifierPart(codePoint);
1.4173 - }
1.4174 -
1.4175 - /**
1.4176 - * Determines if the specified character should be regarded as
1.4177 - * an ignorable character in a Java identifier or a Unicode identifier.
1.4178 - * <p>
1.4179 - * The following Unicode characters are ignorable in a Java identifier
1.4180 - * or a Unicode identifier:
1.4181 - * <ul>
1.4182 - * <li>ISO control characters that are not whitespace
1.4183 - * <ul>
1.4184 - * <li>{@code '\u005Cu0000'} through {@code '\u005Cu0008'}
1.4185 - * <li>{@code '\u005Cu000E'} through {@code '\u005Cu001B'}
1.4186 - * <li>{@code '\u005Cu007F'} through {@code '\u005Cu009F'}
1.4187 - * </ul>
1.4188 - *
1.4189 - * <li>all characters that have the {@code FORMAT} general
1.4190 - * category value
1.4191 - * </ul>
1.4192 - *
1.4193 - * <p><b>Note:</b> This method cannot handle <a
1.4194 - * href="#supplementary"> supplementary characters</a>. To support
1.4195 - * all Unicode characters, including supplementary characters, use
1.4196 - * the {@link #isIdentifierIgnorable(int)} method.
1.4197 - *
1.4198 - * @param ch the character to be tested.
1.4199 - * @return {@code true} if the character is an ignorable control
1.4200 - * character that may be part of a Java or Unicode identifier;
1.4201 - * {@code false} otherwise.
1.4202 - * @see Character#isJavaIdentifierPart(char)
1.4203 - * @see Character#isUnicodeIdentifierPart(char)
1.4204 - * @since 1.1
1.4205 - */
1.4206 - public static boolean isIdentifierIgnorable(char ch) {
1.4207 - return isIdentifierIgnorable((int)ch);
1.4208 - }
1.4209 -
1.4210 - /**
1.4211 - * Determines if the specified character (Unicode code point) should be regarded as
1.4212 - * an ignorable character in a Java identifier or a Unicode identifier.
1.4213 - * <p>
1.4214 - * The following Unicode characters are ignorable in a Java identifier
1.4215 - * or a Unicode identifier:
1.4216 - * <ul>
1.4217 - * <li>ISO control characters that are not whitespace
1.4218 - * <ul>
1.4219 - * <li>{@code '\u005Cu0000'} through {@code '\u005Cu0008'}
1.4220 - * <li>{@code '\u005Cu000E'} through {@code '\u005Cu001B'}
1.4221 - * <li>{@code '\u005Cu007F'} through {@code '\u005Cu009F'}
1.4222 - * </ul>
1.4223 - *
1.4224 - * <li>all characters that have the {@code FORMAT} general
1.4225 - * category value
1.4226 - * </ul>
1.4227 - *
1.4228 - * @param codePoint the character (Unicode code point) to be tested.
1.4229 - * @return {@code true} if the character is an ignorable control
1.4230 - * character that may be part of a Java or Unicode identifier;
1.4231 - * {@code false} otherwise.
1.4232 - * @see Character#isJavaIdentifierPart(int)
1.4233 - * @see Character#isUnicodeIdentifierPart(int)
1.4234 - * @since 1.5
1.4235 - */
1.4236 - public static boolean isIdentifierIgnorable(int codePoint) {
1.4237 - return CharacterData.of(codePoint).isIdentifierIgnorable(codePoint);
1.4238 - }
1.4239 -
1.4240 +
1.4241 /**
1.4242 * Converts the character argument to lowercase using case
1.4243 * mapping information from the UnicodeData file.
1.4244 @@ -6116,36 +1930,7 @@
1.4245 * @see String#toLowerCase()
1.4246 */
1.4247 public static char toLowerCase(char ch) {
1.4248 - return (char)toLowerCase((int)ch);
1.4249 - }
1.4250 -
1.4251 - /**
1.4252 - * Converts the character (Unicode code point) argument to
1.4253 - * lowercase using case mapping information from the UnicodeData
1.4254 - * file.
1.4255 - *
1.4256 - * <p> Note that
1.4257 - * {@code Character.isLowerCase(Character.toLowerCase(codePoint))}
1.4258 - * does not always return {@code true} for some ranges of
1.4259 - * characters, particularly those that are symbols or ideographs.
1.4260 - *
1.4261 - * <p>In general, {@link String#toLowerCase()} should be used to map
1.4262 - * characters to lowercase. {@code String} case mapping methods
1.4263 - * have several benefits over {@code Character} case mapping methods.
1.4264 - * {@code String} case mapping methods can perform locale-sensitive
1.4265 - * mappings, context-sensitive mappings, and 1:M character mappings, whereas
1.4266 - * the {@code Character} case mapping methods cannot.
1.4267 - *
1.4268 - * @param codePoint the character (Unicode code point) to be converted.
1.4269 - * @return the lowercase equivalent of the character (Unicode code
1.4270 - * point), if any; otherwise, the character itself.
1.4271 - * @see Character#isLowerCase(int)
1.4272 - * @see String#toLowerCase()
1.4273 - *
1.4274 - * @since 1.5
1.4275 - */
1.4276 - public static int toLowerCase(int codePoint) {
1.4277 - return CharacterData.of(codePoint).toLowerCase(codePoint);
1.4278 + throw new UnsupportedOperationException();
1.4279 }
1.4280
1.4281 /**
1.4282 @@ -6176,95 +1961,7 @@
1.4283 * @see String#toUpperCase()
1.4284 */
1.4285 public static char toUpperCase(char ch) {
1.4286 - return (char)toUpperCase((int)ch);
1.4287 - }
1.4288 -
1.4289 - /**
1.4290 - * Converts the character (Unicode code point) argument to
1.4291 - * uppercase using case mapping information from the UnicodeData
1.4292 - * file.
1.4293 - *
1.4294 - * <p>Note that
1.4295 - * {@code Character.isUpperCase(Character.toUpperCase(codePoint))}
1.4296 - * does not always return {@code true} for some ranges of
1.4297 - * characters, particularly those that are symbols or ideographs.
1.4298 - *
1.4299 - * <p>In general, {@link String#toUpperCase()} should be used to map
1.4300 - * characters to uppercase. {@code String} case mapping methods
1.4301 - * have several benefits over {@code Character} case mapping methods.
1.4302 - * {@code String} case mapping methods can perform locale-sensitive
1.4303 - * mappings, context-sensitive mappings, and 1:M character mappings, whereas
1.4304 - * the {@code Character} case mapping methods cannot.
1.4305 - *
1.4306 - * @param codePoint the character (Unicode code point) to be converted.
1.4307 - * @return the uppercase equivalent of the character, if any;
1.4308 - * otherwise, the character itself.
1.4309 - * @see Character#isUpperCase(int)
1.4310 - * @see String#toUpperCase()
1.4311 - *
1.4312 - * @since 1.5
1.4313 - */
1.4314 - public static int toUpperCase(int codePoint) {
1.4315 - return CharacterData.of(codePoint).toUpperCase(codePoint);
1.4316 - }
1.4317 -
1.4318 - /**
1.4319 - * Converts the character argument to titlecase using case mapping
1.4320 - * information from the UnicodeData file. If a character has no
1.4321 - * explicit titlecase mapping and is not itself a titlecase char
1.4322 - * according to UnicodeData, then the uppercase mapping is
1.4323 - * returned as an equivalent titlecase mapping. If the
1.4324 - * {@code char} argument is already a titlecase
1.4325 - * {@code char}, the same {@code char} value will be
1.4326 - * returned.
1.4327 - * <p>
1.4328 - * Note that
1.4329 - * {@code Character.isTitleCase(Character.toTitleCase(ch))}
1.4330 - * does not always return {@code true} for some ranges of
1.4331 - * characters.
1.4332 - *
1.4333 - * <p><b>Note:</b> This method cannot handle <a
1.4334 - * href="#supplementary"> supplementary characters</a>. To support
1.4335 - * all Unicode characters, including supplementary characters, use
1.4336 - * the {@link #toTitleCase(int)} method.
1.4337 - *
1.4338 - * @param ch the character to be converted.
1.4339 - * @return the titlecase equivalent of the character, if any;
1.4340 - * otherwise, the character itself.
1.4341 - * @see Character#isTitleCase(char)
1.4342 - * @see Character#toLowerCase(char)
1.4343 - * @see Character#toUpperCase(char)
1.4344 - * @since 1.0.2
1.4345 - */
1.4346 - public static char toTitleCase(char ch) {
1.4347 - return (char)toTitleCase((int)ch);
1.4348 - }
1.4349 -
1.4350 - /**
1.4351 - * Converts the character (Unicode code point) argument to titlecase using case mapping
1.4352 - * information from the UnicodeData file. If a character has no
1.4353 - * explicit titlecase mapping and is not itself a titlecase char
1.4354 - * according to UnicodeData, then the uppercase mapping is
1.4355 - * returned as an equivalent titlecase mapping. If the
1.4356 - * character argument is already a titlecase
1.4357 - * character, the same character value will be
1.4358 - * returned.
1.4359 - *
1.4360 - * <p>Note that
1.4361 - * {@code Character.isTitleCase(Character.toTitleCase(codePoint))}
1.4362 - * does not always return {@code true} for some ranges of
1.4363 - * characters.
1.4364 - *
1.4365 - * @param codePoint the character (Unicode code point) to be converted.
1.4366 - * @return the titlecase equivalent of the character, if any;
1.4367 - * otherwise, the character itself.
1.4368 - * @see Character#isTitleCase(int)
1.4369 - * @see Character#toLowerCase(int)
1.4370 - * @see Character#toUpperCase(int)
1.4371 - * @since 1.5
1.4372 - */
1.4373 - public static int toTitleCase(int codePoint) {
1.4374 - return CharacterData.of(codePoint).toTitleCase(codePoint);
1.4375 + throw new UnsupportedOperationException();
1.4376 }
1.4377
1.4378 /**
1.4379 @@ -6370,7 +2067,7 @@
1.4380 * @since 1.5
1.4381 */
1.4382 public static int digit(int codePoint, int radix) {
1.4383 - return CharacterData.of(codePoint).digit(codePoint, radix);
1.4384 + throw new UnsupportedOperationException();
1.4385 }
1.4386
1.4387 /**
1.4388 @@ -6441,7 +2138,7 @@
1.4389 * @since 1.5
1.4390 */
1.4391 public static int getNumericValue(int codePoint) {
1.4392 - return CharacterData.of(codePoint).getNumericValue(codePoint);
1.4393 + throw new UnsupportedOperationException();
1.4394 }
1.4395
1.4396 /**
1.4397 @@ -6479,58 +2176,6 @@
1.4398 }
1.4399
1.4400
1.4401 - /**
1.4402 - * Determines if the specified character is a Unicode space character.
1.4403 - * A character is considered to be a space character if and only if
1.4404 - * it is specified to be a space character by the Unicode Standard. This
1.4405 - * method returns true if the character's general category type is any of
1.4406 - * the following:
1.4407 - * <ul>
1.4408 - * <li> {@code SPACE_SEPARATOR}
1.4409 - * <li> {@code LINE_SEPARATOR}
1.4410 - * <li> {@code PARAGRAPH_SEPARATOR}
1.4411 - * </ul>
1.4412 - *
1.4413 - * <p><b>Note:</b> This method cannot handle <a
1.4414 - * href="#supplementary"> supplementary characters</a>. To support
1.4415 - * all Unicode characters, including supplementary characters, use
1.4416 - * the {@link #isSpaceChar(int)} method.
1.4417 - *
1.4418 - * @param ch the character to be tested.
1.4419 - * @return {@code true} if the character is a space character;
1.4420 - * {@code false} otherwise.
1.4421 - * @see Character#isWhitespace(char)
1.4422 - * @since 1.1
1.4423 - */
1.4424 - public static boolean isSpaceChar(char ch) {
1.4425 - return isSpaceChar((int)ch);
1.4426 - }
1.4427 -
1.4428 - /**
1.4429 - * Determines if the specified character (Unicode code point) is a
1.4430 - * Unicode space character. A character is considered to be a
1.4431 - * space character if and only if it is specified to be a space
1.4432 - * character by the Unicode Standard. This method returns true if
1.4433 - * the character's general category type is any of the following:
1.4434 - *
1.4435 - * <ul>
1.4436 - * <li> {@link #SPACE_SEPARATOR}
1.4437 - * <li> {@link #LINE_SEPARATOR}
1.4438 - * <li> {@link #PARAGRAPH_SEPARATOR}
1.4439 - * </ul>
1.4440 - *
1.4441 - * @param codePoint the character (Unicode code point) to be tested.
1.4442 - * @return {@code true} if the character is a space character;
1.4443 - * {@code false} otherwise.
1.4444 - * @see Character#isWhitespace(int)
1.4445 - * @since 1.5
1.4446 - */
1.4447 - public static boolean isSpaceChar(int codePoint) {
1.4448 - return ((((1 << Character.SPACE_SEPARATOR) |
1.4449 - (1 << Character.LINE_SEPARATOR) |
1.4450 - (1 << Character.PARAGRAPH_SEPARATOR)) >> getType(codePoint)) & 1)
1.4451 - != 0;
1.4452 - }
1.4453
1.4454 /**
1.4455 * Determines if the specified character is white space according to Java.
1.4456 @@ -6596,7 +2241,7 @@
1.4457 * @since 1.5
1.4458 */
1.4459 public static boolean isWhitespace(int codePoint) {
1.4460 - return CharacterData.of(codePoint).isWhitespace(codePoint);
1.4461 + throw new UnsupportedOperationException();
1.4462 }
1.4463
1.4464 /**
1.4465 @@ -6646,95 +2291,6 @@
1.4466 }
1.4467
1.4468 /**
1.4469 - * Returns a value indicating a character's general category.
1.4470 - *
1.4471 - * <p><b>Note:</b> This method cannot handle <a
1.4472 - * href="#supplementary"> supplementary characters</a>. To support
1.4473 - * all Unicode characters, including supplementary characters, use
1.4474 - * the {@link #getType(int)} method.
1.4475 - *
1.4476 - * @param ch the character to be tested.
1.4477 - * @return a value of type {@code int} representing the
1.4478 - * character's general category.
1.4479 - * @see Character#COMBINING_SPACING_MARK
1.4480 - * @see Character#CONNECTOR_PUNCTUATION
1.4481 - * @see Character#CONTROL
1.4482 - * @see Character#CURRENCY_SYMBOL
1.4483 - * @see Character#DASH_PUNCTUATION
1.4484 - * @see Character#DECIMAL_DIGIT_NUMBER
1.4485 - * @see Character#ENCLOSING_MARK
1.4486 - * @see Character#END_PUNCTUATION
1.4487 - * @see Character#FINAL_QUOTE_PUNCTUATION
1.4488 - * @see Character#FORMAT
1.4489 - * @see Character#INITIAL_QUOTE_PUNCTUATION
1.4490 - * @see Character#LETTER_NUMBER
1.4491 - * @see Character#LINE_SEPARATOR
1.4492 - * @see Character#LOWERCASE_LETTER
1.4493 - * @see Character#MATH_SYMBOL
1.4494 - * @see Character#MODIFIER_LETTER
1.4495 - * @see Character#MODIFIER_SYMBOL
1.4496 - * @see Character#NON_SPACING_MARK
1.4497 - * @see Character#OTHER_LETTER
1.4498 - * @see Character#OTHER_NUMBER
1.4499 - * @see Character#OTHER_PUNCTUATION
1.4500 - * @see Character#OTHER_SYMBOL
1.4501 - * @see Character#PARAGRAPH_SEPARATOR
1.4502 - * @see Character#PRIVATE_USE
1.4503 - * @see Character#SPACE_SEPARATOR
1.4504 - * @see Character#START_PUNCTUATION
1.4505 - * @see Character#SURROGATE
1.4506 - * @see Character#TITLECASE_LETTER
1.4507 - * @see Character#UNASSIGNED
1.4508 - * @see Character#UPPERCASE_LETTER
1.4509 - * @since 1.1
1.4510 - */
1.4511 - public static int getType(char ch) {
1.4512 - return getType((int)ch);
1.4513 - }
1.4514 -
1.4515 - /**
1.4516 - * Returns a value indicating a character's general category.
1.4517 - *
1.4518 - * @param codePoint the character (Unicode code point) to be tested.
1.4519 - * @return a value of type {@code int} representing the
1.4520 - * character's general category.
1.4521 - * @see Character#COMBINING_SPACING_MARK COMBINING_SPACING_MARK
1.4522 - * @see Character#CONNECTOR_PUNCTUATION CONNECTOR_PUNCTUATION
1.4523 - * @see Character#CONTROL CONTROL
1.4524 - * @see Character#CURRENCY_SYMBOL CURRENCY_SYMBOL
1.4525 - * @see Character#DASH_PUNCTUATION DASH_PUNCTUATION
1.4526 - * @see Character#DECIMAL_DIGIT_NUMBER DECIMAL_DIGIT_NUMBER
1.4527 - * @see Character#ENCLOSING_MARK ENCLOSING_MARK
1.4528 - * @see Character#END_PUNCTUATION END_PUNCTUATION
1.4529 - * @see Character#FINAL_QUOTE_PUNCTUATION FINAL_QUOTE_PUNCTUATION
1.4530 - * @see Character#FORMAT FORMAT
1.4531 - * @see Character#INITIAL_QUOTE_PUNCTUATION INITIAL_QUOTE_PUNCTUATION
1.4532 - * @see Character#LETTER_NUMBER LETTER_NUMBER
1.4533 - * @see Character#LINE_SEPARATOR LINE_SEPARATOR
1.4534 - * @see Character#LOWERCASE_LETTER LOWERCASE_LETTER
1.4535 - * @see Character#MATH_SYMBOL MATH_SYMBOL
1.4536 - * @see Character#MODIFIER_LETTER MODIFIER_LETTER
1.4537 - * @see Character#MODIFIER_SYMBOL MODIFIER_SYMBOL
1.4538 - * @see Character#NON_SPACING_MARK NON_SPACING_MARK
1.4539 - * @see Character#OTHER_LETTER OTHER_LETTER
1.4540 - * @see Character#OTHER_NUMBER OTHER_NUMBER
1.4541 - * @see Character#OTHER_PUNCTUATION OTHER_PUNCTUATION
1.4542 - * @see Character#OTHER_SYMBOL OTHER_SYMBOL
1.4543 - * @see Character#PARAGRAPH_SEPARATOR PARAGRAPH_SEPARATOR
1.4544 - * @see Character#PRIVATE_USE PRIVATE_USE
1.4545 - * @see Character#SPACE_SEPARATOR SPACE_SEPARATOR
1.4546 - * @see Character#START_PUNCTUATION START_PUNCTUATION
1.4547 - * @see Character#SURROGATE SURROGATE
1.4548 - * @see Character#TITLECASE_LETTER TITLECASE_LETTER
1.4549 - * @see Character#UNASSIGNED UNASSIGNED
1.4550 - * @see Character#UPPERCASE_LETTER UPPERCASE_LETTER
1.4551 - * @since 1.5
1.4552 - */
1.4553 - public static int getType(int codePoint) {
1.4554 - return CharacterData.of(codePoint).getType(codePoint);
1.4555 - }
1.4556 -
1.4557 - /**
1.4558 * Determines the character representation for a specific digit in
1.4559 * the specified radix. If the value of {@code radix} is not a
1.4560 * valid radix, or the value of {@code digit} is not a valid
1.4561 @@ -6772,126 +2328,6 @@
1.4562 }
1.4563
1.4564 /**
1.4565 - * Returns the Unicode directionality property for the given
1.4566 - * character. Character directionality is used to calculate the
1.4567 - * visual ordering of text. The directionality value of undefined
1.4568 - * {@code char} values is {@code DIRECTIONALITY_UNDEFINED}.
1.4569 - *
1.4570 - * <p><b>Note:</b> This method cannot handle <a
1.4571 - * href="#supplementary"> supplementary characters</a>. To support
1.4572 - * all Unicode characters, including supplementary characters, use
1.4573 - * the {@link #getDirectionality(int)} method.
1.4574 - *
1.4575 - * @param ch {@code char} for which the directionality property
1.4576 - * is requested.
1.4577 - * @return the directionality property of the {@code char} value.
1.4578 - *
1.4579 - * @see Character#DIRECTIONALITY_UNDEFINED
1.4580 - * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT
1.4581 - * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT
1.4582 - * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_ARABIC
1.4583 - * @see Character#DIRECTIONALITY_EUROPEAN_NUMBER
1.4584 - * @see Character#DIRECTIONALITY_EUROPEAN_NUMBER_SEPARATOR
1.4585 - * @see Character#DIRECTIONALITY_EUROPEAN_NUMBER_TERMINATOR
1.4586 - * @see Character#DIRECTIONALITY_ARABIC_NUMBER
1.4587 - * @see Character#DIRECTIONALITY_COMMON_NUMBER_SEPARATOR
1.4588 - * @see Character#DIRECTIONALITY_NONSPACING_MARK
1.4589 - * @see Character#DIRECTIONALITY_BOUNDARY_NEUTRAL
1.4590 - * @see Character#DIRECTIONALITY_PARAGRAPH_SEPARATOR
1.4591 - * @see Character#DIRECTIONALITY_SEGMENT_SEPARATOR
1.4592 - * @see Character#DIRECTIONALITY_WHITESPACE
1.4593 - * @see Character#DIRECTIONALITY_OTHER_NEUTRALS
1.4594 - * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT_EMBEDDING
1.4595 - * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT_OVERRIDE
1.4596 - * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_EMBEDDING
1.4597 - * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_OVERRIDE
1.4598 - * @see Character#DIRECTIONALITY_POP_DIRECTIONAL_FORMAT
1.4599 - * @since 1.4
1.4600 - */
1.4601 - public static byte getDirectionality(char ch) {
1.4602 - return getDirectionality((int)ch);
1.4603 - }
1.4604 -
1.4605 - /**
1.4606 - * Returns the Unicode directionality property for the given
1.4607 - * character (Unicode code point). Character directionality is
1.4608 - * used to calculate the visual ordering of text. The
1.4609 - * directionality value of undefined character is {@link
1.4610 - * #DIRECTIONALITY_UNDEFINED}.
1.4611 - *
1.4612 - * @param codePoint the character (Unicode code point) for which
1.4613 - * the directionality property is requested.
1.4614 - * @return the directionality property of the character.
1.4615 - *
1.4616 - * @see Character#DIRECTIONALITY_UNDEFINED DIRECTIONALITY_UNDEFINED
1.4617 - * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT DIRECTIONALITY_LEFT_TO_RIGHT
1.4618 - * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT DIRECTIONALITY_RIGHT_TO_LEFT
1.4619 - * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_ARABIC DIRECTIONALITY_RIGHT_TO_LEFT_ARABIC
1.4620 - * @see Character#DIRECTIONALITY_EUROPEAN_NUMBER DIRECTIONALITY_EUROPEAN_NUMBER
1.4621 - * @see Character#DIRECTIONALITY_EUROPEAN_NUMBER_SEPARATOR DIRECTIONALITY_EUROPEAN_NUMBER_SEPARATOR
1.4622 - * @see Character#DIRECTIONALITY_EUROPEAN_NUMBER_TERMINATOR DIRECTIONALITY_EUROPEAN_NUMBER_TERMINATOR
1.4623 - * @see Character#DIRECTIONALITY_ARABIC_NUMBER DIRECTIONALITY_ARABIC_NUMBER
1.4624 - * @see Character#DIRECTIONALITY_COMMON_NUMBER_SEPARATOR DIRECTIONALITY_COMMON_NUMBER_SEPARATOR
1.4625 - * @see Character#DIRECTIONALITY_NONSPACING_MARK DIRECTIONALITY_NONSPACING_MARK
1.4626 - * @see Character#DIRECTIONALITY_BOUNDARY_NEUTRAL DIRECTIONALITY_BOUNDARY_NEUTRAL
1.4627 - * @see Character#DIRECTIONALITY_PARAGRAPH_SEPARATOR DIRECTIONALITY_PARAGRAPH_SEPARATOR
1.4628 - * @see Character#DIRECTIONALITY_SEGMENT_SEPARATOR DIRECTIONALITY_SEGMENT_SEPARATOR
1.4629 - * @see Character#DIRECTIONALITY_WHITESPACE DIRECTIONALITY_WHITESPACE
1.4630 - * @see Character#DIRECTIONALITY_OTHER_NEUTRALS DIRECTIONALITY_OTHER_NEUTRALS
1.4631 - * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT_EMBEDDING DIRECTIONALITY_LEFT_TO_RIGHT_EMBEDDING
1.4632 - * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT_OVERRIDE DIRECTIONALITY_LEFT_TO_RIGHT_OVERRIDE
1.4633 - * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_EMBEDDING DIRECTIONALITY_RIGHT_TO_LEFT_EMBEDDING
1.4634 - * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_OVERRIDE DIRECTIONALITY_RIGHT_TO_LEFT_OVERRIDE
1.4635 - * @see Character#DIRECTIONALITY_POP_DIRECTIONAL_FORMAT DIRECTIONALITY_POP_DIRECTIONAL_FORMAT
1.4636 - * @since 1.5
1.4637 - */
1.4638 - public static byte getDirectionality(int codePoint) {
1.4639 - return CharacterData.of(codePoint).getDirectionality(codePoint);
1.4640 - }
1.4641 -
1.4642 - /**
1.4643 - * Determines whether the character is mirrored according to the
1.4644 - * Unicode specification. Mirrored characters should have their
1.4645 - * glyphs horizontally mirrored when displayed in text that is
1.4646 - * right-to-left. For example, {@code '\u005Cu0028'} LEFT
1.4647 - * PARENTHESIS is semantically defined to be an <i>opening
1.4648 - * parenthesis</i>. This will appear as a "(" in text that is
1.4649 - * left-to-right but as a ")" in text that is right-to-left.
1.4650 - *
1.4651 - * <p><b>Note:</b> This method cannot handle <a
1.4652 - * href="#supplementary"> supplementary characters</a>. To support
1.4653 - * all Unicode characters, including supplementary characters, use
1.4654 - * the {@link #isMirrored(int)} method.
1.4655 - *
1.4656 - * @param ch {@code char} for which the mirrored property is requested
1.4657 - * @return {@code true} if the char is mirrored, {@code false}
1.4658 - * if the {@code char} is not mirrored or is not defined.
1.4659 - * @since 1.4
1.4660 - */
1.4661 - public static boolean isMirrored(char ch) {
1.4662 - return isMirrored((int)ch);
1.4663 - }
1.4664 -
1.4665 - /**
1.4666 - * Determines whether the specified character (Unicode code point)
1.4667 - * is mirrored according to the Unicode specification. Mirrored
1.4668 - * characters should have their glyphs horizontally mirrored when
1.4669 - * displayed in text that is right-to-left. For example,
1.4670 - * {@code '\u005Cu0028'} LEFT PARENTHESIS is semantically
1.4671 - * defined to be an <i>opening parenthesis</i>. This will appear
1.4672 - * as a "(" in text that is left-to-right but as a ")" in text
1.4673 - * that is right-to-left.
1.4674 - *
1.4675 - * @param codePoint the character (Unicode code point) to be tested.
1.4676 - * @return {@code true} if the character is mirrored, {@code false}
1.4677 - * if the character is not mirrored or is not defined.
1.4678 - * @since 1.5
1.4679 - */
1.4680 - public static boolean isMirrored(int codePoint) {
1.4681 - return CharacterData.of(codePoint).isMirrored(codePoint);
1.4682 - }
1.4683 -
1.4684 - /**
1.4685 * Compares two {@code Character} objects numerically.
1.4686 *
1.4687 * @param anotherCharacter the {@code Character} to be compared.
1.4688 @@ -6928,42 +2364,6 @@
1.4689 return x - y;
1.4690 }
1.4691
1.4692 - /**
1.4693 - * Converts the character (Unicode code point) argument to uppercase using
1.4694 - * information from the UnicodeData file.
1.4695 - * <p>
1.4696 - *
1.4697 - * @param codePoint the character (Unicode code point) to be converted.
1.4698 - * @return either the uppercase equivalent of the character, if
1.4699 - * any, or an error flag ({@code Character.ERROR})
1.4700 - * that indicates that a 1:M {@code char} mapping exists.
1.4701 - * @see Character#isLowerCase(char)
1.4702 - * @see Character#isUpperCase(char)
1.4703 - * @see Character#toLowerCase(char)
1.4704 - * @see Character#toTitleCase(char)
1.4705 - * @since 1.4
1.4706 - */
1.4707 - static int toUpperCaseEx(int codePoint) {
1.4708 - assert isValidCodePoint(codePoint);
1.4709 - return CharacterData.of(codePoint).toUpperCaseEx(codePoint);
1.4710 - }
1.4711 -
1.4712 - /**
1.4713 - * Converts the character (Unicode code point) argument to uppercase using case
1.4714 - * mapping information from the SpecialCasing file in the Unicode
1.4715 - * specification. If a character has no explicit uppercase
1.4716 - * mapping, then the {@code char} itself is returned in the
1.4717 - * {@code char[]}.
1.4718 - *
1.4719 - * @param codePoint the character (Unicode code point) to be converted.
1.4720 - * @return a {@code char[]} with the uppercased character.
1.4721 - * @since 1.4
1.4722 - */
1.4723 - static char[] toUpperCaseCharArray(int codePoint) {
1.4724 - // As of Unicode 6.0, 1:M uppercasings only happen in the BMP.
1.4725 - assert isBmpCodePoint(codePoint);
1.4726 - return CharacterData.of(codePoint).toUpperCaseCharArray(codePoint);
1.4727 - }
1.4728
1.4729 /**
1.4730 * The number of bits used to represent a <tt>char</tt> value in unsigned
1.4731 @@ -6985,48 +2385,4 @@
1.4732 return (char) (((ch & 0xFF00) >> 8) | (ch << 8));
1.4733 }
1.4734
1.4735 - /**
1.4736 - * Returns the Unicode name of the specified character
1.4737 - * {@code codePoint}, or null if the code point is
1.4738 - * {@link #UNASSIGNED unassigned}.
1.4739 - * <p>
1.4740 - * Note: if the specified character is not assigned a name by
1.4741 - * the <i>UnicodeData</i> file (part of the Unicode Character
1.4742 - * Database maintained by the Unicode Consortium), the returned
1.4743 - * name is the same as the result of expression.
1.4744 - *
1.4745 - * <blockquote>{@code
1.4746 - * Character.UnicodeBlock.of(codePoint).toString().replace('_', ' ')
1.4747 - * + " "
1.4748 - * + Integer.toHexString(codePoint).toUpperCase(Locale.ENGLISH);
1.4749 - *
1.4750 - * }</blockquote>
1.4751 - *
1.4752 - * @param codePoint the character (Unicode code point)
1.4753 - *
1.4754 - * @return the Unicode name of the specified character, or null if
1.4755 - * the code point is unassigned.
1.4756 - *
1.4757 - * @exception IllegalArgumentException if the specified
1.4758 - * {@code codePoint} is not a valid Unicode
1.4759 - * code point.
1.4760 - *
1.4761 - * @since 1.7
1.4762 - */
1.4763 - public static String getName(int codePoint) {
1.4764 - if (!isValidCodePoint(codePoint)) {
1.4765 - throw new IllegalArgumentException();
1.4766 - }
1.4767 - String name = CharacterName.get(codePoint);
1.4768 - if (name != null)
1.4769 - return name;
1.4770 - if (getType(codePoint) == UNASSIGNED)
1.4771 - return null;
1.4772 - UnicodeBlock block = UnicodeBlock.of(codePoint);
1.4773 - if (block != null)
1.4774 - return block.toString().replace('_', ' ') + " "
1.4775 - + Integer.toHexString(codePoint).toUpperCase(Locale.ENGLISH);
1.4776 - // should never come here
1.4777 - return Integer.toHexString(codePoint).toUpperCase(Locale.ENGLISH);
1.4778 - }
1.4779 }