1 /* 2 * Copyright (c) 2002, 2018, Oracle and/or its affiliates. All rights reserved. 3 * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. 4 * 5 * This code is free software; you can redistribute it and/or modify it 6 * under the terms of the GNU General Public License version 2 only, as 7 * published by the Free Software Foundation. Oracle designates this 8 * particular file as subject to the "Classpath" exception as provided 9 * by Oracle in the LICENSE file that accompanied this code. 10 * 11 * This code is distributed in the hope that it will be useful, but WITHOUT 12 * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or 13 * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License 14 * version 2 for more details (a copy is included in the LICENSE file that 15 * accompanied this code). 16 * 17 * You should have received a copy of the GNU General Public License version 18 * 2 along with this work; if not, write to the Free Software Foundation, 19 * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA. 20 * 21 * Please contact Oracle, 500 Oracle Parkway, Redwood Shores, CA 94065 USA 22 * or visit www.oracle.com if you need additional information or have any 23 * questions. 24 */ 25 26 package java.lang; 27 28 import java.util.Arrays; 29 import java.util.Map; 30 import java.util.HashMap; 31 import java.util.Locale; 32 33 import jdk.internal.HotSpotIntrinsicCandidate; 34 import jdk.internal.misc.VM; 35 36 /** 37 * The {@code Character} class wraps a value of the primitive 38 * type {@code char} in an object. An object of type 39 * {@code Character} contains a single field whose type is 40 * {@code char}. 41 * <p> 42 * In addition, this class provides several methods for determining 43 * a character's category (lowercase letter, digit, etc.) and for converting 44 * characters from uppercase to lowercase and vice versa. 45 * <p> 46 * Character information is based on the Unicode Standard, version 11.0.0. 47 * <p> 48 * The methods and data of class {@code Character} are defined by 49 * the information in the <i>UnicodeData</i> file that is part of the 50 * Unicode Character Database maintained by the Unicode 51 * Consortium. This file specifies various properties including name 52 * and general category for every defined Unicode code point or 53 * character range. 54 * <p> 55 * The file and its description are available from the Unicode Consortium at: 56 * <ul> 57 * <li><a href="http://www.unicode.org">http://www.unicode.org</a> 58 * </ul> 59 * <p> 60 * The code point, U+32FF, is reserved by the Unicode Consortium 61 * to represent the Japanese square character for the new era that begins 62 * May 2019. Relevant methods in the Character class return the same 63 * properties as for the existing Japanese era characters (e.g., U+337E for 64 * "Meizi"). For the details of the code point, refer to 65 * <a href="http://blog.unicode.org/2018/09/new-japanese-era.html"> 66 * http://blog.unicode.org/2018/09/new-japanese-era.html</a>. 67 * 68 * <h3><a id="unicode">Unicode Character Representations</a></h3> 69 * 70 * <p>The {@code char} data type (and therefore the value that a 71 * {@code Character} object encapsulates) are based on the 72 * original Unicode specification, which defined characters as 73 * fixed-width 16-bit entities. The Unicode Standard has since been 74 * changed to allow for characters whose representation requires more 75 * than 16 bits. The range of legal <em>code point</em>s is now 76 * U+0000 to U+10FFFF, known as <em>Unicode scalar value</em>. 77 * (Refer to the <a 78 * href="http://www.unicode.org/reports/tr27/#notation"><i> 79 * definition</i></a> of the U+<i>n</i> notation in the Unicode 80 * Standard.) 81 * 82 * <p><a id="BMP">The set of characters from U+0000 to U+FFFF</a> is 83 * sometimes referred to as the <em>Basic Multilingual Plane (BMP)</em>. 84 * <a id="supplementary">Characters</a> whose code points are greater 85 * than U+FFFF are called <em>supplementary character</em>s. The Java 86 * platform uses the UTF-16 representation in {@code char} arrays and 87 * in the {@code String} and {@code StringBuffer} classes. In 88 * this representation, supplementary characters are represented as a pair 89 * of {@code char} values, the first from the <em>high-surrogates</em> 90 * range, (\uD800-\uDBFF), the second from the 91 * <em>low-surrogates</em> range (\uDC00-\uDFFF). 92 * 93 * <p>A {@code char} value, therefore, represents Basic 94 * Multilingual Plane (BMP) code points, including the surrogate 95 * code points, or code units of the UTF-16 encoding. An 96 * {@code int} value represents all Unicode code points, 97 * including supplementary code points. The lower (least significant) 98 * 21 bits of {@code int} are used to represent Unicode code 99 * points and the upper (most significant) 11 bits must be zero. 100 * Unless otherwise specified, the behavior with respect to 101 * supplementary characters and surrogate {@code char} values is 102 * as follows: 103 * 104 * <ul> 105 * <li>The methods that only accept a {@code char} value cannot support 106 * supplementary characters. They treat {@code char} values from the 107 * surrogate ranges as undefined characters. For example, 108 * {@code Character.isLetter('\u005CuD840')} returns {@code false}, even though 109 * this specific value if followed by any low-surrogate value in a string 110 * would represent a letter. 111 * 112 * <li>The methods that accept an {@code int} value support all 113 * Unicode characters, including supplementary characters. For 114 * example, {@code Character.isLetter(0x2F81A)} returns 115 * {@code true} because the code point value represents a letter 116 * (a CJK ideograph). 117 * </ul> 118 * 119 * <p>In the Java SE API documentation, <em>Unicode code point</em> is 120 * used for character values in the range between U+0000 and U+10FFFF, 121 * and <em>Unicode code unit</em> is used for 16-bit 122 * {@code char} values that are code units of the <em>UTF-16</em> 123 * encoding. For more information on Unicode terminology, refer to the 124 * <a href="http://www.unicode.org/glossary/">Unicode Glossary</a>. 125 * 126 * @author Lee Boynton 127 * @author Guy Steele 128 * @author Akira Tanaka 129 * @author Martin Buchholz 130 * @author Ulf Zibis 131 * @since 1.0 132 */ 133 public final 134 class Character implements java.io.Serializable, Comparable<Character> { 135 /** 136 * The minimum radix available for conversion to and from strings. 137 * The constant value of this field is the smallest value permitted 138 * for the radix argument in radix-conversion methods such as the 139 * {@code digit} method, the {@code forDigit} method, and the 140 * {@code toString} method of class {@code Integer}. 141 * 142 * @see Character#digit(char, int) 143 * @see Character#forDigit(int, int) 144 * @see Integer#toString(int, int) 145 * @see Integer#valueOf(String) 146 */ 147 public static final int MIN_RADIX = 2; 148 149 /** 150 * The maximum radix available for conversion to and from strings. 151 * The constant value of this field is the largest value permitted 152 * for the radix argument in radix-conversion methods such as the 153 * {@code digit} method, the {@code forDigit} method, and the 154 * {@code toString} method of class {@code Integer}. 155 * 156 * @see Character#digit(char, int) 157 * @see Character#forDigit(int, int) 158 * @see Integer#toString(int, int) 159 * @see Integer#valueOf(String) 160 */ 161 public static final int MAX_RADIX = 36; 162 163 /** 164 * The constant value of this field is the smallest value of type 165 * {@code char}, {@code '\u005Cu0000'}. 166 * 167 * @since 1.0.2 168 */ 169 public static final char MIN_VALUE = '\u0000'; 170 171 /** 172 * The constant value of this field is the largest value of type 173 * {@code char}, {@code '\u005CuFFFF'}. 174 * 175 * @since 1.0.2 176 */ 177 public static final char MAX_VALUE = '\uFFFF'; 178 179 /** 180 * The {@code Class} instance representing the primitive type 181 * {@code char}. 182 * 183 * @since 1.1 184 */ 185 @SuppressWarnings("unchecked") 186 public static final Class<Character> TYPE = (Class<Character>) Class.getPrimitiveClass("char"); 187 188 /* 189 * Normative general types 190 */ 191 192 /* 193 * General character types 194 */ 195 196 /** 197 * General category "Cn" in the Unicode specification. 198 * @since 1.1 199 */ 200 public static final byte UNASSIGNED = 0; 201 202 /** 203 * General category "Lu" in the Unicode specification. 204 * @since 1.1 205 */ 206 public static final byte UPPERCASE_LETTER = 1; 207 208 /** 209 * General category "Ll" in the Unicode specification. 210 * @since 1.1 211 */ 212 public static final byte LOWERCASE_LETTER = 2; 213 214 /** 215 * General category "Lt" in the Unicode specification. 216 * @since 1.1 217 */ 218 public static final byte TITLECASE_LETTER = 3; 219 220 /** 221 * General category "Lm" in the Unicode specification. 222 * @since 1.1 223 */ 224 public static final byte MODIFIER_LETTER = 4; 225 226 /** 227 * General category "Lo" in the Unicode specification. 228 * @since 1.1 229 */ 230 public static final byte OTHER_LETTER = 5; 231 232 /** 233 * General category "Mn" in the Unicode specification. 234 * @since 1.1 235 */ 236 public static final byte NON_SPACING_MARK = 6; 237 238 /** 239 * General category "Me" in the Unicode specification. 240 * @since 1.1 241 */ 242 public static final byte ENCLOSING_MARK = 7; 243 244 /** 245 * General category "Mc" in the Unicode specification. 246 * @since 1.1 247 */ 248 public static final byte COMBINING_SPACING_MARK = 8; 249 250 /** 251 * General category "Nd" in the Unicode specification. 252 * @since 1.1 253 */ 254 public static final byte DECIMAL_DIGIT_NUMBER = 9; 255 256 /** 257 * General category "Nl" in the Unicode specification. 258 * @since 1.1 259 */ 260 public static final byte LETTER_NUMBER = 10; 261 262 /** 263 * General category "No" in the Unicode specification. 264 * @since 1.1 265 */ 266 public static final byte OTHER_NUMBER = 11; 267 268 /** 269 * General category "Zs" in the Unicode specification. 270 * @since 1.1 271 */ 272 public static final byte SPACE_SEPARATOR = 12; 273 274 /** 275 * General category "Zl" in the Unicode specification. 276 * @since 1.1 277 */ 278 public static final byte LINE_SEPARATOR = 13; 279 280 /** 281 * General category "Zp" in the Unicode specification. 282 * @since 1.1 283 */ 284 public static final byte PARAGRAPH_SEPARATOR = 14; 285 286 /** 287 * General category "Cc" in the Unicode specification. 288 * @since 1.1 289 */ 290 public static final byte CONTROL = 15; 291 292 /** 293 * General category "Cf" in the Unicode specification. 294 * @since 1.1 295 */ 296 public static final byte FORMAT = 16; 297 298 /** 299 * General category "Co" in the Unicode specification. 300 * @since 1.1 301 */ 302 public static final byte PRIVATE_USE = 18; 303 304 /** 305 * General category "Cs" in the Unicode specification. 306 * @since 1.1 307 */ 308 public static final byte SURROGATE = 19; 309 310 /** 311 * General category "Pd" in the Unicode specification. 312 * @since 1.1 313 */ 314 public static final byte DASH_PUNCTUATION = 20; 315 316 /** 317 * General category "Ps" in the Unicode specification. 318 * @since 1.1 319 */ 320 public static final byte START_PUNCTUATION = 21; 321 322 /** 323 * General category "Pe" in the Unicode specification. 324 * @since 1.1 325 */ 326 public static final byte END_PUNCTUATION = 22; 327 328 /** 329 * General category "Pc" in the Unicode specification. 330 * @since 1.1 331 */ 332 public static final byte CONNECTOR_PUNCTUATION = 23; 333 334 /** 335 * General category "Po" in the Unicode specification. 336 * @since 1.1 337 */ 338 public static final byte OTHER_PUNCTUATION = 24; 339 340 /** 341 * General category "Sm" in the Unicode specification. 342 * @since 1.1 343 */ 344 public static final byte MATH_SYMBOL = 25; 345 346 /** 347 * General category "Sc" in the Unicode specification. 348 * @since 1.1 349 */ 350 public static final byte CURRENCY_SYMBOL = 26; 351 352 /** 353 * General category "Sk" in the Unicode specification. 354 * @since 1.1 355 */ 356 public static final byte MODIFIER_SYMBOL = 27; 357 358 /** 359 * General category "So" in the Unicode specification. 360 * @since 1.1 361 */ 362 public static final byte OTHER_SYMBOL = 28; 363 364 /** 365 * General category "Pi" in the Unicode specification. 366 * @since 1.4 367 */ 368 public static final byte INITIAL_QUOTE_PUNCTUATION = 29; 369 370 /** 371 * General category "Pf" in the Unicode specification. 372 * @since 1.4 373 */ 374 public static final byte FINAL_QUOTE_PUNCTUATION = 30; 375 376 /** 377 * Error flag. Use int (code point) to avoid confusion with U+FFFF. 378 */ 379 static final int ERROR = 0xFFFFFFFF; 380 381 382 /** 383 * Undefined bidirectional character type. Undefined {@code char} 384 * values have undefined directionality in the Unicode specification. 385 * @since 1.4 386 */ 387 public static final byte DIRECTIONALITY_UNDEFINED = -1; 388 389 /** 390 * Strong bidirectional character type "L" in the Unicode specification. 391 * @since 1.4 392 */ 393 public static final byte DIRECTIONALITY_LEFT_TO_RIGHT = 0; 394 395 /** 396 * Strong bidirectional character type "R" in the Unicode specification. 397 * @since 1.4 398 */ 399 public static final byte DIRECTIONALITY_RIGHT_TO_LEFT = 1; 400 401 /** 402 * Strong bidirectional character type "AL" in the Unicode specification. 403 * @since 1.4 404 */ 405 public static final byte DIRECTIONALITY_RIGHT_TO_LEFT_ARABIC = 2; 406 407 /** 408 * Weak bidirectional character type "EN" in the Unicode specification. 409 * @since 1.4 410 */ 411 public static final byte DIRECTIONALITY_EUROPEAN_NUMBER = 3; 412 413 /** 414 * Weak bidirectional character type "ES" in the Unicode specification. 415 * @since 1.4 416 */ 417 public static final byte DIRECTIONALITY_EUROPEAN_NUMBER_SEPARATOR = 4; 418 419 /** 420 * Weak bidirectional character type "ET" in the Unicode specification. 421 * @since 1.4 422 */ 423 public static final byte DIRECTIONALITY_EUROPEAN_NUMBER_TERMINATOR = 5; 424 425 /** 426 * Weak bidirectional character type "AN" in the Unicode specification. 427 * @since 1.4 428 */ 429 public static final byte DIRECTIONALITY_ARABIC_NUMBER = 6; 430 431 /** 432 * Weak bidirectional character type "CS" in the Unicode specification. 433 * @since 1.4 434 */ 435 public static final byte DIRECTIONALITY_COMMON_NUMBER_SEPARATOR = 7; 436 437 /** 438 * Weak bidirectional character type "NSM" in the Unicode specification. 439 * @since 1.4 440 */ 441 public static final byte DIRECTIONALITY_NONSPACING_MARK = 8; 442 443 /** 444 * Weak bidirectional character type "BN" in the Unicode specification. 445 * @since 1.4 446 */ 447 public static final byte DIRECTIONALITY_BOUNDARY_NEUTRAL = 9; 448 449 /** 450 * Neutral bidirectional character type "B" in the Unicode specification. 451 * @since 1.4 452 */ 453 public static final byte DIRECTIONALITY_PARAGRAPH_SEPARATOR = 10; 454 455 /** 456 * Neutral bidirectional character type "S" in the Unicode specification. 457 * @since 1.4 458 */ 459 public static final byte DIRECTIONALITY_SEGMENT_SEPARATOR = 11; 460 461 /** 462 * Neutral bidirectional character type "WS" in the Unicode specification. 463 * @since 1.4 464 */ 465 public static final byte DIRECTIONALITY_WHITESPACE = 12; 466 467 /** 468 * Neutral bidirectional character type "ON" in the Unicode specification. 469 * @since 1.4 470 */ 471 public static final byte DIRECTIONALITY_OTHER_NEUTRALS = 13; 472 473 /** 474 * Strong bidirectional character type "LRE" in the Unicode specification. 475 * @since 1.4 476 */ 477 public static final byte DIRECTIONALITY_LEFT_TO_RIGHT_EMBEDDING = 14; 478 479 /** 480 * Strong bidirectional character type "LRO" in the Unicode specification. 481 * @since 1.4 482 */ 483 public static final byte DIRECTIONALITY_LEFT_TO_RIGHT_OVERRIDE = 15; 484 485 /** 486 * Strong bidirectional character type "RLE" in the Unicode specification. 487 * @since 1.4 488 */ 489 public static final byte DIRECTIONALITY_RIGHT_TO_LEFT_EMBEDDING = 16; 490 491 /** 492 * Strong bidirectional character type "RLO" in the Unicode specification. 493 * @since 1.4 494 */ 495 public static final byte DIRECTIONALITY_RIGHT_TO_LEFT_OVERRIDE = 17; 496 497 /** 498 * Weak bidirectional character type "PDF" in the Unicode specification. 499 * @since 1.4 500 */ 501 public static final byte DIRECTIONALITY_POP_DIRECTIONAL_FORMAT = 18; 502 503 /** 504 * Weak bidirectional character type "LRI" in the Unicode specification. 505 * @since 9 506 */ 507 public static final byte DIRECTIONALITY_LEFT_TO_RIGHT_ISOLATE = 19; 508 509 /** 510 * Weak bidirectional character type "RLI" in the Unicode specification. 511 * @since 9 512 */ 513 public static final byte DIRECTIONALITY_RIGHT_TO_LEFT_ISOLATE = 20; 514 515 /** 516 * Weak bidirectional character type "FSI" in the Unicode specification. 517 * @since 9 518 */ 519 public static final byte DIRECTIONALITY_FIRST_STRONG_ISOLATE = 21; 520 521 /** 522 * Weak bidirectional character type "PDI" in the Unicode specification. 523 * @since 9 524 */ 525 public static final byte DIRECTIONALITY_POP_DIRECTIONAL_ISOLATE = 22; 526 527 /** 528 * The minimum value of a 529 * <a href="http://www.unicode.org/glossary/#high_surrogate_code_unit"> 530 * Unicode high-surrogate code unit</a> 531 * in the UTF-16 encoding, constant {@code '\u005CuD800'}. 532 * A high-surrogate is also known as a <i>leading-surrogate</i>. 533 * 534 * @since 1.5 535 */ 536 public static final char MIN_HIGH_SURROGATE = '\uD800'; 537 538 /** 539 * The maximum value of a 540 * <a href="http://www.unicode.org/glossary/#high_surrogate_code_unit"> 541 * Unicode high-surrogate code unit</a> 542 * in the UTF-16 encoding, constant {@code '\u005CuDBFF'}. 543 * A high-surrogate is also known as a <i>leading-surrogate</i>. 544 * 545 * @since 1.5 546 */ 547 public static final char MAX_HIGH_SURROGATE = '\uDBFF'; 548 549 /** 550 * The minimum value of a 551 * <a href="http://www.unicode.org/glossary/#low_surrogate_code_unit"> 552 * Unicode low-surrogate code unit</a> 553 * in the UTF-16 encoding, constant {@code '\u005CuDC00'}. 554 * A low-surrogate is also known as a <i>trailing-surrogate</i>. 555 * 556 * @since 1.5 557 */ 558 public static final char MIN_LOW_SURROGATE = '\uDC00'; 559 560 /** 561 * The maximum value of a 562 * <a href="http://www.unicode.org/glossary/#low_surrogate_code_unit"> 563 * Unicode low-surrogate code unit</a> 564 * in the UTF-16 encoding, constant {@code '\u005CuDFFF'}. 565 * A low-surrogate is also known as a <i>trailing-surrogate</i>. 566 * 567 * @since 1.5 568 */ 569 public static final char MAX_LOW_SURROGATE = '\uDFFF'; 570 571 /** 572 * The minimum value of a Unicode surrogate code unit in the 573 * UTF-16 encoding, constant {@code '\u005CuD800'}. 574 * 575 * @since 1.5 576 */ 577 public static final char MIN_SURROGATE = MIN_HIGH_SURROGATE; 578 579 /** 580 * The maximum value of a Unicode surrogate code unit in the 581 * UTF-16 encoding, constant {@code '\u005CuDFFF'}. 582 * 583 * @since 1.5 584 */ 585 public static final char MAX_SURROGATE = MAX_LOW_SURROGATE; 586 587 /** 588 * The minimum value of a 589 * <a href="http://www.unicode.org/glossary/#supplementary_code_point"> 590 * Unicode supplementary code point</a>, constant {@code U+10000}. 591 * 592 * @since 1.5 593 */ 594 public static final int MIN_SUPPLEMENTARY_CODE_POINT = 0x010000; 595 596 /** 597 * The minimum value of a 598 * <a href="http://www.unicode.org/glossary/#code_point"> 599 * Unicode code point</a>, constant {@code U+0000}. 600 * 601 * @since 1.5 602 */ 603 public static final int MIN_CODE_POINT = 0x000000; 604 605 /** 606 * The maximum value of a 607 * <a href="http://www.unicode.org/glossary/#code_point"> 608 * Unicode code point</a>, constant {@code U+10FFFF}. 609 * 610 * @since 1.5 611 */ 612 public static final int MAX_CODE_POINT = 0X10FFFF; 613 614 615 /** 616 * Instances of this class represent particular subsets of the Unicode 617 * character set. The only family of subsets defined in the 618 * {@code Character} class is {@link Character.UnicodeBlock}. 619 * Other portions of the Java API may define other subsets for their 620 * own purposes. 621 * 622 * @since 1.2 623 */ 624 public static class Subset { 625 626 private String name; 627 628 /** 629 * Constructs a new {@code Subset} instance. 630 * 631 * @param name The name of this subset 632 * @throws NullPointerException if name is {@code null} 633 */ 634 protected Subset(String name) { 635 if (name == null) { 636 throw new NullPointerException("name"); 637 } 638 this.name = name; 639 } 640 641 /** 642 * Compares two {@code Subset} objects for equality. 643 * This method returns {@code true} if and only if 644 * {@code this} and the argument refer to the same 645 * object; since this method is {@code final}, this 646 * guarantee holds for all subclasses. 647 */ 648 public final boolean equals(Object obj) { 649 return (this == obj); 650 } 651 652 /** 653 * Returns the standard hash code as defined by the 654 * {@link Object#hashCode} method. This method 655 * is {@code final} in order to ensure that the 656 * {@code equals} and {@code hashCode} methods will 657 * be consistent in all subclasses. 658 */ 659 public final int hashCode() { 660 return super.hashCode(); 661 } 662 663 /** 664 * Returns the name of this subset. 665 */ 666 public final String toString() { 667 return name; 668 } 669 } 670 671 // See http://www.unicode.org/Public/UNIDATA/Blocks.txt 672 // for the latest specification of Unicode Blocks. 673 674 /** 675 * A family of character subsets representing the character blocks in the 676 * Unicode specification. Character blocks generally define characters 677 * used for a specific script or purpose. A character is contained by 678 * at most one Unicode block. 679 * 680 * @since 1.2 681 */ 682 public static final class UnicodeBlock extends Subset { 683 /** 684 * 649 - the expected number of entities 685 * 0.75 - the default load factor of HashMap 686 */ 687 private static Map<String, UnicodeBlock> map = 688 new HashMap<>((int)(649 / 0.75f + 1.0f)); 689 690 /** 691 * Creates a UnicodeBlock with the given identifier name. 692 * This name must be the same as the block identifier. 693 */ 694 private UnicodeBlock(String idName) { 695 super(idName); 696 map.put(idName, this); 697 } 698 699 /** 700 * Creates a UnicodeBlock with the given identifier name and 701 * alias name. 702 */ 703 private UnicodeBlock(String idName, String alias) { 704 this(idName); 705 map.put(alias, this); 706 } 707 708 /** 709 * Creates a UnicodeBlock with the given identifier name and 710 * alias names. 711 */ 712 private UnicodeBlock(String idName, String... aliases) { 713 this(idName); 714 for (String alias : aliases) 715 map.put(alias, this); 716 } 717 718 /** 719 * Constant for the "Basic Latin" Unicode character block. 720 * @since 1.2 721 */ 722 public static final UnicodeBlock BASIC_LATIN = 723 new UnicodeBlock("BASIC_LATIN", 724 "BASIC LATIN", 725 "BASICLATIN"); 726 727 /** 728 * Constant for the "Latin-1 Supplement" Unicode character block. 729 * @since 1.2 730 */ 731 public static final UnicodeBlock LATIN_1_SUPPLEMENT = 732 new UnicodeBlock("LATIN_1_SUPPLEMENT", 733 "LATIN-1 SUPPLEMENT", 734 "LATIN-1SUPPLEMENT"); 735 736 /** 737 * Constant for the "Latin Extended-A" Unicode character block. 738 * @since 1.2 739 */ 740 public static final UnicodeBlock LATIN_EXTENDED_A = 741 new UnicodeBlock("LATIN_EXTENDED_A", 742 "LATIN EXTENDED-A", 743 "LATINEXTENDED-A"); 744 745 /** 746 * Constant for the "Latin Extended-B" Unicode character block. 747 * @since 1.2 748 */ 749 public static final UnicodeBlock LATIN_EXTENDED_B = 750 new UnicodeBlock("LATIN_EXTENDED_B", 751 "LATIN EXTENDED-B", 752 "LATINEXTENDED-B"); 753 754 /** 755 * Constant for the "IPA Extensions" Unicode character block. 756 * @since 1.2 757 */ 758 public static final UnicodeBlock IPA_EXTENSIONS = 759 new UnicodeBlock("IPA_EXTENSIONS", 760 "IPA EXTENSIONS", 761 "IPAEXTENSIONS"); 762 763 /** 764 * Constant for the "Spacing Modifier Letters" Unicode character block. 765 * @since 1.2 766 */ 767 public static final UnicodeBlock SPACING_MODIFIER_LETTERS = 768 new UnicodeBlock("SPACING_MODIFIER_LETTERS", 769 "SPACING MODIFIER LETTERS", 770 "SPACINGMODIFIERLETTERS"); 771 772 /** 773 * Constant for the "Combining Diacritical Marks" Unicode character block. 774 * @since 1.2 775 */ 776 public static final UnicodeBlock COMBINING_DIACRITICAL_MARKS = 777 new UnicodeBlock("COMBINING_DIACRITICAL_MARKS", 778 "COMBINING DIACRITICAL MARKS", 779 "COMBININGDIACRITICALMARKS"); 780 781 /** 782 * Constant for the "Greek and Coptic" Unicode character block. 783 * <p> 784 * This block was previously known as the "Greek" block. 785 * 786 * @since 1.2 787 */ 788 public static final UnicodeBlock GREEK = 789 new UnicodeBlock("GREEK", 790 "GREEK AND COPTIC", 791 "GREEKANDCOPTIC"); 792 793 /** 794 * Constant for the "Cyrillic" Unicode character block. 795 * @since 1.2 796 */ 797 public static final UnicodeBlock CYRILLIC = 798 new UnicodeBlock("CYRILLIC"); 799 800 /** 801 * Constant for the "Armenian" Unicode character block. 802 * @since 1.2 803 */ 804 public static final UnicodeBlock ARMENIAN = 805 new UnicodeBlock("ARMENIAN"); 806 807 /** 808 * Constant for the "Hebrew" Unicode character block. 809 * @since 1.2 810 */ 811 public static final UnicodeBlock HEBREW = 812 new UnicodeBlock("HEBREW"); 813 814 /** 815 * Constant for the "Arabic" Unicode character block. 816 * @since 1.2 817 */ 818 public static final UnicodeBlock ARABIC = 819 new UnicodeBlock("ARABIC"); 820 821 /** 822 * Constant for the "Devanagari" Unicode character block. 823 * @since 1.2 824 */ 825 public static final UnicodeBlock DEVANAGARI = 826 new UnicodeBlock("DEVANAGARI"); 827 828 /** 829 * Constant for the "Bengali" Unicode character block. 830 * @since 1.2 831 */ 832 public static final UnicodeBlock BENGALI = 833 new UnicodeBlock("BENGALI"); 834 835 /** 836 * Constant for the "Gurmukhi" Unicode character block. 837 * @since 1.2 838 */ 839 public static final UnicodeBlock GURMUKHI = 840 new UnicodeBlock("GURMUKHI"); 841 842 /** 843 * Constant for the "Gujarati" Unicode character block. 844 * @since 1.2 845 */ 846 public static final UnicodeBlock GUJARATI = 847 new UnicodeBlock("GUJARATI"); 848 849 /** 850 * Constant for the "Oriya" Unicode character block. 851 * @since 1.2 852 */ 853 public static final UnicodeBlock ORIYA = 854 new UnicodeBlock("ORIYA"); 855 856 /** 857 * Constant for the "Tamil" Unicode character block. 858 * @since 1.2 859 */ 860 public static final UnicodeBlock TAMIL = 861 new UnicodeBlock("TAMIL"); 862 863 /** 864 * Constant for the "Telugu" Unicode character block. 865 * @since 1.2 866 */ 867 public static final UnicodeBlock TELUGU = 868 new UnicodeBlock("TELUGU"); 869 870 /** 871 * Constant for the "Kannada" Unicode character block. 872 * @since 1.2 873 */ 874 public static final UnicodeBlock KANNADA = 875 new UnicodeBlock("KANNADA"); 876 877 /** 878 * Constant for the "Malayalam" Unicode character block. 879 * @since 1.2 880 */ 881 public static final UnicodeBlock MALAYALAM = 882 new UnicodeBlock("MALAYALAM"); 883 884 /** 885 * Constant for the "Thai" Unicode character block. 886 * @since 1.2 887 */ 888 public static final UnicodeBlock THAI = 889 new UnicodeBlock("THAI"); 890 891 /** 892 * Constant for the "Lao" Unicode character block. 893 * @since 1.2 894 */ 895 public static final UnicodeBlock LAO = 896 new UnicodeBlock("LAO"); 897 898 /** 899 * Constant for the "Tibetan" Unicode character block. 900 * @since 1.2 901 */ 902 public static final UnicodeBlock TIBETAN = 903 new UnicodeBlock("TIBETAN"); 904 905 /** 906 * Constant for the "Georgian" Unicode character block. 907 * @since 1.2 908 */ 909 public static final UnicodeBlock GEORGIAN = 910 new UnicodeBlock("GEORGIAN"); 911 912 /** 913 * Constant for the "Hangul Jamo" Unicode character block. 914 * @since 1.2 915 */ 916 public static final UnicodeBlock HANGUL_JAMO = 917 new UnicodeBlock("HANGUL_JAMO", 918 "HANGUL JAMO", 919 "HANGULJAMO"); 920 921 /** 922 * Constant for the "Latin Extended Additional" Unicode character block. 923 * @since 1.2 924 */ 925 public static final UnicodeBlock LATIN_EXTENDED_ADDITIONAL = 926 new UnicodeBlock("LATIN_EXTENDED_ADDITIONAL", 927 "LATIN EXTENDED ADDITIONAL", 928 "LATINEXTENDEDADDITIONAL"); 929 930 /** 931 * Constant for the "Greek Extended" Unicode character block. 932 * @since 1.2 933 */ 934 public static final UnicodeBlock GREEK_EXTENDED = 935 new UnicodeBlock("GREEK_EXTENDED", 936 "GREEK EXTENDED", 937 "GREEKEXTENDED"); 938 939 /** 940 * Constant for the "General Punctuation" Unicode character block. 941 * @since 1.2 942 */ 943 public static final UnicodeBlock GENERAL_PUNCTUATION = 944 new UnicodeBlock("GENERAL_PUNCTUATION", 945 "GENERAL PUNCTUATION", 946 "GENERALPUNCTUATION"); 947 948 /** 949 * Constant for the "Superscripts and Subscripts" Unicode character 950 * block. 951 * @since 1.2 952 */ 953 public static final UnicodeBlock SUPERSCRIPTS_AND_SUBSCRIPTS = 954 new UnicodeBlock("SUPERSCRIPTS_AND_SUBSCRIPTS", 955 "SUPERSCRIPTS AND SUBSCRIPTS", 956 "SUPERSCRIPTSANDSUBSCRIPTS"); 957 958 /** 959 * Constant for the "Currency Symbols" Unicode character block. 960 * @since 1.2 961 */ 962 public static final UnicodeBlock CURRENCY_SYMBOLS = 963 new UnicodeBlock("CURRENCY_SYMBOLS", 964 "CURRENCY SYMBOLS", 965 "CURRENCYSYMBOLS"); 966 967 /** 968 * Constant for the "Combining Diacritical Marks for Symbols" Unicode 969 * character block. 970 * <p> 971 * This block was previously known as "Combining Marks for Symbols". 972 * @since 1.2 973 */ 974 public static final UnicodeBlock COMBINING_MARKS_FOR_SYMBOLS = 975 new UnicodeBlock("COMBINING_MARKS_FOR_SYMBOLS", 976 "COMBINING DIACRITICAL MARKS FOR SYMBOLS", 977 "COMBININGDIACRITICALMARKSFORSYMBOLS", 978 "COMBINING MARKS FOR SYMBOLS", 979 "COMBININGMARKSFORSYMBOLS"); 980 981 /** 982 * Constant for the "Letterlike Symbols" Unicode character block. 983 * @since 1.2 984 */ 985 public static final UnicodeBlock LETTERLIKE_SYMBOLS = 986 new UnicodeBlock("LETTERLIKE_SYMBOLS", 987 "LETTERLIKE SYMBOLS", 988 "LETTERLIKESYMBOLS"); 989 990 /** 991 * Constant for the "Number Forms" Unicode character block. 992 * @since 1.2 993 */ 994 public static final UnicodeBlock NUMBER_FORMS = 995 new UnicodeBlock("NUMBER_FORMS", 996 "NUMBER FORMS", 997 "NUMBERFORMS"); 998 999 /** 1000 * Constant for the "Arrows" Unicode character block. 1001 * @since 1.2 1002 */ 1003 public static final UnicodeBlock ARROWS = 1004 new UnicodeBlock("ARROWS"); 1005 1006 /** 1007 * Constant for the "Mathematical Operators" Unicode character block. 1008 * @since 1.2 1009 */ 1010 public static final UnicodeBlock MATHEMATICAL_OPERATORS = 1011 new UnicodeBlock("MATHEMATICAL_OPERATORS", 1012 "MATHEMATICAL OPERATORS", 1013 "MATHEMATICALOPERATORS"); 1014 1015 /** 1016 * Constant for the "Miscellaneous Technical" Unicode character block. 1017 * @since 1.2 1018 */ 1019 public static final UnicodeBlock MISCELLANEOUS_TECHNICAL = 1020 new UnicodeBlock("MISCELLANEOUS_TECHNICAL", 1021 "MISCELLANEOUS TECHNICAL", 1022 "MISCELLANEOUSTECHNICAL"); 1023 1024 /** 1025 * Constant for the "Control Pictures" Unicode character block. 1026 * @since 1.2 1027 */ 1028 public static final UnicodeBlock CONTROL_PICTURES = 1029 new UnicodeBlock("CONTROL_PICTURES", 1030 "CONTROL PICTURES", 1031 "CONTROLPICTURES"); 1032 1033 /** 1034 * Constant for the "Optical Character Recognition" Unicode character block. 1035 * @since 1.2 1036 */ 1037 public static final UnicodeBlock OPTICAL_CHARACTER_RECOGNITION = 1038 new UnicodeBlock("OPTICAL_CHARACTER_RECOGNITION", 1039 "OPTICAL CHARACTER RECOGNITION", 1040 "OPTICALCHARACTERRECOGNITION"); 1041 1042 /** 1043 * Constant for the "Enclosed Alphanumerics" Unicode character block. 1044 * @since 1.2 1045 */ 1046 public static final UnicodeBlock ENCLOSED_ALPHANUMERICS = 1047 new UnicodeBlock("ENCLOSED_ALPHANUMERICS", 1048 "ENCLOSED ALPHANUMERICS", 1049 "ENCLOSEDALPHANUMERICS"); 1050 1051 /** 1052 * Constant for the "Box Drawing" Unicode character block. 1053 * @since 1.2 1054 */ 1055 public static final UnicodeBlock BOX_DRAWING = 1056 new UnicodeBlock("BOX_DRAWING", 1057 "BOX DRAWING", 1058 "BOXDRAWING"); 1059 1060 /** 1061 * Constant for the "Block Elements" Unicode character block. 1062 * @since 1.2 1063 */ 1064 public static final UnicodeBlock BLOCK_ELEMENTS = 1065 new UnicodeBlock("BLOCK_ELEMENTS", 1066 "BLOCK ELEMENTS", 1067 "BLOCKELEMENTS"); 1068 1069 /** 1070 * Constant for the "Geometric Shapes" Unicode character block. 1071 * @since 1.2 1072 */ 1073 public static final UnicodeBlock GEOMETRIC_SHAPES = 1074 new UnicodeBlock("GEOMETRIC_SHAPES", 1075 "GEOMETRIC SHAPES", 1076 "GEOMETRICSHAPES"); 1077 1078 /** 1079 * Constant for the "Miscellaneous Symbols" Unicode character block. 1080 * @since 1.2 1081 */ 1082 public static final UnicodeBlock MISCELLANEOUS_SYMBOLS = 1083 new UnicodeBlock("MISCELLANEOUS_SYMBOLS", 1084 "MISCELLANEOUS SYMBOLS", 1085 "MISCELLANEOUSSYMBOLS"); 1086 1087 /** 1088 * Constant for the "Dingbats" Unicode character block. 1089 * @since 1.2 1090 */ 1091 public static final UnicodeBlock DINGBATS = 1092 new UnicodeBlock("DINGBATS"); 1093 1094 /** 1095 * Constant for the "CJK Symbols and Punctuation" Unicode character block. 1096 * @since 1.2 1097 */ 1098 public static final UnicodeBlock CJK_SYMBOLS_AND_PUNCTUATION = 1099 new UnicodeBlock("CJK_SYMBOLS_AND_PUNCTUATION", 1100 "CJK SYMBOLS AND PUNCTUATION", 1101 "CJKSYMBOLSANDPUNCTUATION"); 1102 1103 /** 1104 * Constant for the "Hiragana" Unicode character block. 1105 * @since 1.2 1106 */ 1107 public static final UnicodeBlock HIRAGANA = 1108 new UnicodeBlock("HIRAGANA"); 1109 1110 /** 1111 * Constant for the "Katakana" Unicode character block. 1112 * @since 1.2 1113 */ 1114 public static final UnicodeBlock KATAKANA = 1115 new UnicodeBlock("KATAKANA"); 1116 1117 /** 1118 * Constant for the "Bopomofo" Unicode character block. 1119 * @since 1.2 1120 */ 1121 public static final UnicodeBlock BOPOMOFO = 1122 new UnicodeBlock("BOPOMOFO"); 1123 1124 /** 1125 * Constant for the "Hangul Compatibility Jamo" Unicode character block. 1126 * @since 1.2 1127 */ 1128 public static final UnicodeBlock HANGUL_COMPATIBILITY_JAMO = 1129 new UnicodeBlock("HANGUL_COMPATIBILITY_JAMO", 1130 "HANGUL COMPATIBILITY JAMO", 1131 "HANGULCOMPATIBILITYJAMO"); 1132 1133 /** 1134 * Constant for the "Kanbun" Unicode character block. 1135 * @since 1.2 1136 */ 1137 public static final UnicodeBlock KANBUN = 1138 new UnicodeBlock("KANBUN"); 1139 1140 /** 1141 * Constant for the "Enclosed CJK Letters and Months" Unicode character block. 1142 * @since 1.2 1143 */ 1144 public static final UnicodeBlock ENCLOSED_CJK_LETTERS_AND_MONTHS = 1145 new UnicodeBlock("ENCLOSED_CJK_LETTERS_AND_MONTHS", 1146 "ENCLOSED CJK LETTERS AND MONTHS", 1147 "ENCLOSEDCJKLETTERSANDMONTHS"); 1148 1149 /** 1150 * Constant for the "CJK Compatibility" Unicode character block. 1151 * @since 1.2 1152 */ 1153 public static final UnicodeBlock CJK_COMPATIBILITY = 1154 new UnicodeBlock("CJK_COMPATIBILITY", 1155 "CJK COMPATIBILITY", 1156 "CJKCOMPATIBILITY"); 1157 1158 /** 1159 * Constant for the "CJK Unified Ideographs" Unicode character block. 1160 * @since 1.2 1161 */ 1162 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS = 1163 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS", 1164 "CJK UNIFIED IDEOGRAPHS", 1165 "CJKUNIFIEDIDEOGRAPHS"); 1166 1167 /** 1168 * Constant for the "Hangul Syllables" Unicode character block. 1169 * @since 1.2 1170 */ 1171 public static final UnicodeBlock HANGUL_SYLLABLES = 1172 new UnicodeBlock("HANGUL_SYLLABLES", 1173 "HANGUL SYLLABLES", 1174 "HANGULSYLLABLES"); 1175 1176 /** 1177 * Constant for the "Private Use Area" Unicode character block. 1178 * @since 1.2 1179 */ 1180 public static final UnicodeBlock PRIVATE_USE_AREA = 1181 new UnicodeBlock("PRIVATE_USE_AREA", 1182 "PRIVATE USE AREA", 1183 "PRIVATEUSEAREA"); 1184 1185 /** 1186 * Constant for the "CJK Compatibility Ideographs" Unicode character 1187 * block. 1188 * @since 1.2 1189 */ 1190 public static final UnicodeBlock CJK_COMPATIBILITY_IDEOGRAPHS = 1191 new UnicodeBlock("CJK_COMPATIBILITY_IDEOGRAPHS", 1192 "CJK COMPATIBILITY IDEOGRAPHS", 1193 "CJKCOMPATIBILITYIDEOGRAPHS"); 1194 1195 /** 1196 * Constant for the "Alphabetic Presentation Forms" Unicode character block. 1197 * @since 1.2 1198 */ 1199 public static final UnicodeBlock ALPHABETIC_PRESENTATION_FORMS = 1200 new UnicodeBlock("ALPHABETIC_PRESENTATION_FORMS", 1201 "ALPHABETIC PRESENTATION FORMS", 1202 "ALPHABETICPRESENTATIONFORMS"); 1203 1204 /** 1205 * Constant for the "Arabic Presentation Forms-A" Unicode character 1206 * block. 1207 * @since 1.2 1208 */ 1209 public static final UnicodeBlock ARABIC_PRESENTATION_FORMS_A = 1210 new UnicodeBlock("ARABIC_PRESENTATION_FORMS_A", 1211 "ARABIC PRESENTATION FORMS-A", 1212 "ARABICPRESENTATIONFORMS-A"); 1213 1214 /** 1215 * Constant for the "Combining Half Marks" Unicode character block. 1216 * @since 1.2 1217 */ 1218 public static final UnicodeBlock COMBINING_HALF_MARKS = 1219 new UnicodeBlock("COMBINING_HALF_MARKS", 1220 "COMBINING HALF MARKS", 1221 "COMBININGHALFMARKS"); 1222 1223 /** 1224 * Constant for the "CJK Compatibility Forms" Unicode character block. 1225 * @since 1.2 1226 */ 1227 public static final UnicodeBlock CJK_COMPATIBILITY_FORMS = 1228 new UnicodeBlock("CJK_COMPATIBILITY_FORMS", 1229 "CJK COMPATIBILITY FORMS", 1230 "CJKCOMPATIBILITYFORMS"); 1231 1232 /** 1233 * Constant for the "Small Form Variants" Unicode character block. 1234 * @since 1.2 1235 */ 1236 public static final UnicodeBlock SMALL_FORM_VARIANTS = 1237 new UnicodeBlock("SMALL_FORM_VARIANTS", 1238 "SMALL FORM VARIANTS", 1239 "SMALLFORMVARIANTS"); 1240 1241 /** 1242 * Constant for the "Arabic Presentation Forms-B" Unicode character block. 1243 * @since 1.2 1244 */ 1245 public static final UnicodeBlock ARABIC_PRESENTATION_FORMS_B = 1246 new UnicodeBlock("ARABIC_PRESENTATION_FORMS_B", 1247 "ARABIC PRESENTATION FORMS-B", 1248 "ARABICPRESENTATIONFORMS-B"); 1249 1250 /** 1251 * Constant for the "Halfwidth and Fullwidth Forms" Unicode character 1252 * block. 1253 * @since 1.2 1254 */ 1255 public static final UnicodeBlock HALFWIDTH_AND_FULLWIDTH_FORMS = 1256 new UnicodeBlock("HALFWIDTH_AND_FULLWIDTH_FORMS", 1257 "HALFWIDTH AND FULLWIDTH FORMS", 1258 "HALFWIDTHANDFULLWIDTHFORMS"); 1259 1260 /** 1261 * Constant for the "Specials" Unicode character block. 1262 * @since 1.2 1263 */ 1264 public static final UnicodeBlock SPECIALS = 1265 new UnicodeBlock("SPECIALS"); 1266 1267 /** 1268 * @deprecated 1269 * Instead of {@code SURROGATES_AREA}, use {@link #HIGH_SURROGATES}, 1270 * {@link #HIGH_PRIVATE_USE_SURROGATES}, and {@link #LOW_SURROGATES}. 1271 * These constants match the block definitions of the Unicode Standard. 1272 * The {@link #of(char)} and {@link #of(int)} methods return the 1273 * standard constants. 1274 */ 1275 @Deprecated(since="1.5") 1276 public static final UnicodeBlock SURROGATES_AREA = 1277 new UnicodeBlock("SURROGATES_AREA"); 1278 1279 /** 1280 * Constant for the "Syriac" Unicode character block. 1281 * @since 1.4 1282 */ 1283 public static final UnicodeBlock SYRIAC = 1284 new UnicodeBlock("SYRIAC"); 1285 1286 /** 1287 * Constant for the "Thaana" Unicode character block. 1288 * @since 1.4 1289 */ 1290 public static final UnicodeBlock THAANA = 1291 new UnicodeBlock("THAANA"); 1292 1293 /** 1294 * Constant for the "Sinhala" Unicode character block. 1295 * @since 1.4 1296 */ 1297 public static final UnicodeBlock SINHALA = 1298 new UnicodeBlock("SINHALA"); 1299 1300 /** 1301 * Constant for the "Myanmar" Unicode character block. 1302 * @since 1.4 1303 */ 1304 public static final UnicodeBlock MYANMAR = 1305 new UnicodeBlock("MYANMAR"); 1306 1307 /** 1308 * Constant for the "Ethiopic" Unicode character block. 1309 * @since 1.4 1310 */ 1311 public static final UnicodeBlock ETHIOPIC = 1312 new UnicodeBlock("ETHIOPIC"); 1313 1314 /** 1315 * Constant for the "Cherokee" Unicode character block. 1316 * @since 1.4 1317 */ 1318 public static final UnicodeBlock CHEROKEE = 1319 new UnicodeBlock("CHEROKEE"); 1320 1321 /** 1322 * Constant for the "Unified Canadian Aboriginal Syllabics" Unicode character block. 1323 * @since 1.4 1324 */ 1325 public static final UnicodeBlock UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS = 1326 new UnicodeBlock("UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS", 1327 "UNIFIED CANADIAN ABORIGINAL SYLLABICS", 1328 "UNIFIEDCANADIANABORIGINALSYLLABICS"); 1329 1330 /** 1331 * Constant for the "Ogham" Unicode character block. 1332 * @since 1.4 1333 */ 1334 public static final UnicodeBlock OGHAM = 1335 new UnicodeBlock("OGHAM"); 1336 1337 /** 1338 * Constant for the "Runic" Unicode character block. 1339 * @since 1.4 1340 */ 1341 public static final UnicodeBlock RUNIC = 1342 new UnicodeBlock("RUNIC"); 1343 1344 /** 1345 * Constant for the "Khmer" Unicode character block. 1346 * @since 1.4 1347 */ 1348 public static final UnicodeBlock KHMER = 1349 new UnicodeBlock("KHMER"); 1350 1351 /** 1352 * Constant for the "Mongolian" Unicode character block. 1353 * @since 1.4 1354 */ 1355 public static final UnicodeBlock MONGOLIAN = 1356 new UnicodeBlock("MONGOLIAN"); 1357 1358 /** 1359 * Constant for the "Braille Patterns" Unicode character block. 1360 * @since 1.4 1361 */ 1362 public static final UnicodeBlock BRAILLE_PATTERNS = 1363 new UnicodeBlock("BRAILLE_PATTERNS", 1364 "BRAILLE PATTERNS", 1365 "BRAILLEPATTERNS"); 1366 1367 /** 1368 * Constant for the "CJK Radicals Supplement" Unicode character block. 1369 * @since 1.4 1370 */ 1371 public static final UnicodeBlock CJK_RADICALS_SUPPLEMENT = 1372 new UnicodeBlock("CJK_RADICALS_SUPPLEMENT", 1373 "CJK RADICALS SUPPLEMENT", 1374 "CJKRADICALSSUPPLEMENT"); 1375 1376 /** 1377 * Constant for the "Kangxi Radicals" Unicode character block. 1378 * @since 1.4 1379 */ 1380 public static final UnicodeBlock KANGXI_RADICALS = 1381 new UnicodeBlock("KANGXI_RADICALS", 1382 "KANGXI RADICALS", 1383 "KANGXIRADICALS"); 1384 1385 /** 1386 * Constant for the "Ideographic Description Characters" Unicode character block. 1387 * @since 1.4 1388 */ 1389 public static final UnicodeBlock IDEOGRAPHIC_DESCRIPTION_CHARACTERS = 1390 new UnicodeBlock("IDEOGRAPHIC_DESCRIPTION_CHARACTERS", 1391 "IDEOGRAPHIC DESCRIPTION CHARACTERS", 1392 "IDEOGRAPHICDESCRIPTIONCHARACTERS"); 1393 1394 /** 1395 * Constant for the "Bopomofo Extended" Unicode character block. 1396 * @since 1.4 1397 */ 1398 public static final UnicodeBlock BOPOMOFO_EXTENDED = 1399 new UnicodeBlock("BOPOMOFO_EXTENDED", 1400 "BOPOMOFO EXTENDED", 1401 "BOPOMOFOEXTENDED"); 1402 1403 /** 1404 * Constant for the "CJK Unified Ideographs Extension A" Unicode character block. 1405 * @since 1.4 1406 */ 1407 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A = 1408 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A", 1409 "CJK UNIFIED IDEOGRAPHS EXTENSION A", 1410 "CJKUNIFIEDIDEOGRAPHSEXTENSIONA"); 1411 1412 /** 1413 * Constant for the "Yi Syllables" Unicode character block. 1414 * @since 1.4 1415 */ 1416 public static final UnicodeBlock YI_SYLLABLES = 1417 new UnicodeBlock("YI_SYLLABLES", 1418 "YI SYLLABLES", 1419 "YISYLLABLES"); 1420 1421 /** 1422 * Constant for the "Yi Radicals" Unicode character block. 1423 * @since 1.4 1424 */ 1425 public static final UnicodeBlock YI_RADICALS = 1426 new UnicodeBlock("YI_RADICALS", 1427 "YI RADICALS", 1428 "YIRADICALS"); 1429 1430 /** 1431 * Constant for the "Cyrillic Supplement" Unicode character block. 1432 * This block was previously known as the "Cyrillic Supplementary" block. 1433 * @since 1.5 1434 */ 1435 public static final UnicodeBlock CYRILLIC_SUPPLEMENTARY = 1436 new UnicodeBlock("CYRILLIC_SUPPLEMENTARY", 1437 "CYRILLIC SUPPLEMENTARY", 1438 "CYRILLICSUPPLEMENTARY", 1439 "CYRILLIC SUPPLEMENT", 1440 "CYRILLICSUPPLEMENT"); 1441 1442 /** 1443 * Constant for the "Tagalog" Unicode character block. 1444 * @since 1.5 1445 */ 1446 public static final UnicodeBlock TAGALOG = 1447 new UnicodeBlock("TAGALOG"); 1448 1449 /** 1450 * Constant for the "Hanunoo" Unicode character block. 1451 * @since 1.5 1452 */ 1453 public static final UnicodeBlock HANUNOO = 1454 new UnicodeBlock("HANUNOO"); 1455 1456 /** 1457 * Constant for the "Buhid" Unicode character block. 1458 * @since 1.5 1459 */ 1460 public static final UnicodeBlock BUHID = 1461 new UnicodeBlock("BUHID"); 1462 1463 /** 1464 * Constant for the "Tagbanwa" Unicode character block. 1465 * @since 1.5 1466 */ 1467 public static final UnicodeBlock TAGBANWA = 1468 new UnicodeBlock("TAGBANWA"); 1469 1470 /** 1471 * Constant for the "Limbu" Unicode character block. 1472 * @since 1.5 1473 */ 1474 public static final UnicodeBlock LIMBU = 1475 new UnicodeBlock("LIMBU"); 1476 1477 /** 1478 * Constant for the "Tai Le" Unicode character block. 1479 * @since 1.5 1480 */ 1481 public static final UnicodeBlock TAI_LE = 1482 new UnicodeBlock("TAI_LE", 1483 "TAI LE", 1484 "TAILE"); 1485 1486 /** 1487 * Constant for the "Khmer Symbols" Unicode character block. 1488 * @since 1.5 1489 */ 1490 public static final UnicodeBlock KHMER_SYMBOLS = 1491 new UnicodeBlock("KHMER_SYMBOLS", 1492 "KHMER SYMBOLS", 1493 "KHMERSYMBOLS"); 1494 1495 /** 1496 * Constant for the "Phonetic Extensions" Unicode character block. 1497 * @since 1.5 1498 */ 1499 public static final UnicodeBlock PHONETIC_EXTENSIONS = 1500 new UnicodeBlock("PHONETIC_EXTENSIONS", 1501 "PHONETIC EXTENSIONS", 1502 "PHONETICEXTENSIONS"); 1503 1504 /** 1505 * Constant for the "Miscellaneous Mathematical Symbols-A" Unicode character block. 1506 * @since 1.5 1507 */ 1508 public static final UnicodeBlock MISCELLANEOUS_MATHEMATICAL_SYMBOLS_A = 1509 new UnicodeBlock("MISCELLANEOUS_MATHEMATICAL_SYMBOLS_A", 1510 "MISCELLANEOUS MATHEMATICAL SYMBOLS-A", 1511 "MISCELLANEOUSMATHEMATICALSYMBOLS-A"); 1512 1513 /** 1514 * Constant for the "Supplemental Arrows-A" Unicode character block. 1515 * @since 1.5 1516 */ 1517 public static final UnicodeBlock SUPPLEMENTAL_ARROWS_A = 1518 new UnicodeBlock("SUPPLEMENTAL_ARROWS_A", 1519 "SUPPLEMENTAL ARROWS-A", 1520 "SUPPLEMENTALARROWS-A"); 1521 1522 /** 1523 * Constant for the "Supplemental Arrows-B" Unicode character block. 1524 * @since 1.5 1525 */ 1526 public static final UnicodeBlock SUPPLEMENTAL_ARROWS_B = 1527 new UnicodeBlock("SUPPLEMENTAL_ARROWS_B", 1528 "SUPPLEMENTAL ARROWS-B", 1529 "SUPPLEMENTALARROWS-B"); 1530 1531 /** 1532 * Constant for the "Miscellaneous Mathematical Symbols-B" Unicode 1533 * character block. 1534 * @since 1.5 1535 */ 1536 public static final UnicodeBlock MISCELLANEOUS_MATHEMATICAL_SYMBOLS_B = 1537 new UnicodeBlock("MISCELLANEOUS_MATHEMATICAL_SYMBOLS_B", 1538 "MISCELLANEOUS MATHEMATICAL SYMBOLS-B", 1539 "MISCELLANEOUSMATHEMATICALSYMBOLS-B"); 1540 1541 /** 1542 * Constant for the "Supplemental Mathematical Operators" Unicode 1543 * character block. 1544 * @since 1.5 1545 */ 1546 public static final UnicodeBlock SUPPLEMENTAL_MATHEMATICAL_OPERATORS = 1547 new UnicodeBlock("SUPPLEMENTAL_MATHEMATICAL_OPERATORS", 1548 "SUPPLEMENTAL MATHEMATICAL OPERATORS", 1549 "SUPPLEMENTALMATHEMATICALOPERATORS"); 1550 1551 /** 1552 * Constant for the "Miscellaneous Symbols and Arrows" Unicode character 1553 * block. 1554 * @since 1.5 1555 */ 1556 public static final UnicodeBlock MISCELLANEOUS_SYMBOLS_AND_ARROWS = 1557 new UnicodeBlock("MISCELLANEOUS_SYMBOLS_AND_ARROWS", 1558 "MISCELLANEOUS SYMBOLS AND ARROWS", 1559 "MISCELLANEOUSSYMBOLSANDARROWS"); 1560 1561 /** 1562 * Constant for the "Katakana Phonetic Extensions" Unicode character 1563 * block. 1564 * @since 1.5 1565 */ 1566 public static final UnicodeBlock KATAKANA_PHONETIC_EXTENSIONS = 1567 new UnicodeBlock("KATAKANA_PHONETIC_EXTENSIONS", 1568 "KATAKANA PHONETIC EXTENSIONS", 1569 "KATAKANAPHONETICEXTENSIONS"); 1570 1571 /** 1572 * Constant for the "Yijing Hexagram Symbols" Unicode character block. 1573 * @since 1.5 1574 */ 1575 public static final UnicodeBlock YIJING_HEXAGRAM_SYMBOLS = 1576 new UnicodeBlock("YIJING_HEXAGRAM_SYMBOLS", 1577 "YIJING HEXAGRAM SYMBOLS", 1578 "YIJINGHEXAGRAMSYMBOLS"); 1579 1580 /** 1581 * Constant for the "Variation Selectors" Unicode character block. 1582 * @since 1.5 1583 */ 1584 public static final UnicodeBlock VARIATION_SELECTORS = 1585 new UnicodeBlock("VARIATION_SELECTORS", 1586 "VARIATION SELECTORS", 1587 "VARIATIONSELECTORS"); 1588 1589 /** 1590 * Constant for the "Linear B Syllabary" Unicode character block. 1591 * @since 1.5 1592 */ 1593 public static final UnicodeBlock LINEAR_B_SYLLABARY = 1594 new UnicodeBlock("LINEAR_B_SYLLABARY", 1595 "LINEAR B SYLLABARY", 1596 "LINEARBSYLLABARY"); 1597 1598 /** 1599 * Constant for the "Linear B Ideograms" Unicode character block. 1600 * @since 1.5 1601 */ 1602 public static final UnicodeBlock LINEAR_B_IDEOGRAMS = 1603 new UnicodeBlock("LINEAR_B_IDEOGRAMS", 1604 "LINEAR B IDEOGRAMS", 1605 "LINEARBIDEOGRAMS"); 1606 1607 /** 1608 * Constant for the "Aegean Numbers" Unicode character block. 1609 * @since 1.5 1610 */ 1611 public static final UnicodeBlock AEGEAN_NUMBERS = 1612 new UnicodeBlock("AEGEAN_NUMBERS", 1613 "AEGEAN NUMBERS", 1614 "AEGEANNUMBERS"); 1615 1616 /** 1617 * Constant for the "Old Italic" Unicode character block. 1618 * @since 1.5 1619 */ 1620 public static final UnicodeBlock OLD_ITALIC = 1621 new UnicodeBlock("OLD_ITALIC", 1622 "OLD ITALIC", 1623 "OLDITALIC"); 1624 1625 /** 1626 * Constant for the "Gothic" Unicode character block. 1627 * @since 1.5 1628 */ 1629 public static final UnicodeBlock GOTHIC = 1630 new UnicodeBlock("GOTHIC"); 1631 1632 /** 1633 * Constant for the "Ugaritic" Unicode character block. 1634 * @since 1.5 1635 */ 1636 public static final UnicodeBlock UGARITIC = 1637 new UnicodeBlock("UGARITIC"); 1638 1639 /** 1640 * Constant for the "Deseret" Unicode character block. 1641 * @since 1.5 1642 */ 1643 public static final UnicodeBlock DESERET = 1644 new UnicodeBlock("DESERET"); 1645 1646 /** 1647 * Constant for the "Shavian" Unicode character block. 1648 * @since 1.5 1649 */ 1650 public static final UnicodeBlock SHAVIAN = 1651 new UnicodeBlock("SHAVIAN"); 1652 1653 /** 1654 * Constant for the "Osmanya" Unicode character block. 1655 * @since 1.5 1656 */ 1657 public static final UnicodeBlock OSMANYA = 1658 new UnicodeBlock("OSMANYA"); 1659 1660 /** 1661 * Constant for the "Cypriot Syllabary" Unicode character block. 1662 * @since 1.5 1663 */ 1664 public static final UnicodeBlock CYPRIOT_SYLLABARY = 1665 new UnicodeBlock("CYPRIOT_SYLLABARY", 1666 "CYPRIOT SYLLABARY", 1667 "CYPRIOTSYLLABARY"); 1668 1669 /** 1670 * Constant for the "Byzantine Musical Symbols" Unicode character block. 1671 * @since 1.5 1672 */ 1673 public static final UnicodeBlock BYZANTINE_MUSICAL_SYMBOLS = 1674 new UnicodeBlock("BYZANTINE_MUSICAL_SYMBOLS", 1675 "BYZANTINE MUSICAL SYMBOLS", 1676 "BYZANTINEMUSICALSYMBOLS"); 1677 1678 /** 1679 * Constant for the "Musical Symbols" Unicode character block. 1680 * @since 1.5 1681 */ 1682 public static final UnicodeBlock MUSICAL_SYMBOLS = 1683 new UnicodeBlock("MUSICAL_SYMBOLS", 1684 "MUSICAL SYMBOLS", 1685 "MUSICALSYMBOLS"); 1686 1687 /** 1688 * Constant for the "Tai Xuan Jing Symbols" Unicode character block. 1689 * @since 1.5 1690 */ 1691 public static final UnicodeBlock TAI_XUAN_JING_SYMBOLS = 1692 new UnicodeBlock("TAI_XUAN_JING_SYMBOLS", 1693 "TAI XUAN JING SYMBOLS", 1694 "TAIXUANJINGSYMBOLS"); 1695 1696 /** 1697 * Constant for the "Mathematical Alphanumeric Symbols" Unicode 1698 * character block. 1699 * @since 1.5 1700 */ 1701 public static final UnicodeBlock MATHEMATICAL_ALPHANUMERIC_SYMBOLS = 1702 new UnicodeBlock("MATHEMATICAL_ALPHANUMERIC_SYMBOLS", 1703 "MATHEMATICAL ALPHANUMERIC SYMBOLS", 1704 "MATHEMATICALALPHANUMERICSYMBOLS"); 1705 1706 /** 1707 * Constant for the "CJK Unified Ideographs Extension B" Unicode 1708 * character block. 1709 * @since 1.5 1710 */ 1711 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_B = 1712 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_B", 1713 "CJK UNIFIED IDEOGRAPHS EXTENSION B", 1714 "CJKUNIFIEDIDEOGRAPHSEXTENSIONB"); 1715 1716 /** 1717 * Constant for the "CJK Compatibility Ideographs Supplement" Unicode character block. 1718 * @since 1.5 1719 */ 1720 public static final UnicodeBlock CJK_COMPATIBILITY_IDEOGRAPHS_SUPPLEMENT = 1721 new UnicodeBlock("CJK_COMPATIBILITY_IDEOGRAPHS_SUPPLEMENT", 1722 "CJK COMPATIBILITY IDEOGRAPHS SUPPLEMENT", 1723 "CJKCOMPATIBILITYIDEOGRAPHSSUPPLEMENT"); 1724 1725 /** 1726 * Constant for the "Tags" Unicode character block. 1727 * @since 1.5 1728 */ 1729 public static final UnicodeBlock TAGS = 1730 new UnicodeBlock("TAGS"); 1731 1732 /** 1733 * Constant for the "Variation Selectors Supplement" Unicode character 1734 * block. 1735 * @since 1.5 1736 */ 1737 public static final UnicodeBlock VARIATION_SELECTORS_SUPPLEMENT = 1738 new UnicodeBlock("VARIATION_SELECTORS_SUPPLEMENT", 1739 "VARIATION SELECTORS SUPPLEMENT", 1740 "VARIATIONSELECTORSSUPPLEMENT"); 1741 1742 /** 1743 * Constant for the "Supplementary Private Use Area-A" Unicode character 1744 * block. 1745 * @since 1.5 1746 */ 1747 public static final UnicodeBlock SUPPLEMENTARY_PRIVATE_USE_AREA_A = 1748 new UnicodeBlock("SUPPLEMENTARY_PRIVATE_USE_AREA_A", 1749 "SUPPLEMENTARY PRIVATE USE AREA-A", 1750 "SUPPLEMENTARYPRIVATEUSEAREA-A"); 1751 1752 /** 1753 * Constant for the "Supplementary Private Use Area-B" Unicode character 1754 * block. 1755 * @since 1.5 1756 */ 1757 public static final UnicodeBlock SUPPLEMENTARY_PRIVATE_USE_AREA_B = 1758 new UnicodeBlock("SUPPLEMENTARY_PRIVATE_USE_AREA_B", 1759 "SUPPLEMENTARY PRIVATE USE AREA-B", 1760 "SUPPLEMENTARYPRIVATEUSEAREA-B"); 1761 1762 /** 1763 * Constant for the "High Surrogates" Unicode character block. 1764 * This block represents codepoint values in the high surrogate 1765 * range: U+D800 through U+DB7F 1766 * 1767 * @since 1.5 1768 */ 1769 public static final UnicodeBlock HIGH_SURROGATES = 1770 new UnicodeBlock("HIGH_SURROGATES", 1771 "HIGH SURROGATES", 1772 "HIGHSURROGATES"); 1773 1774 /** 1775 * Constant for the "High Private Use Surrogates" Unicode character 1776 * block. 1777 * This block represents codepoint values in the private use high 1778 * surrogate range: U+DB80 through U+DBFF 1779 * 1780 * @since 1.5 1781 */ 1782 public static final UnicodeBlock HIGH_PRIVATE_USE_SURROGATES = 1783 new UnicodeBlock("HIGH_PRIVATE_USE_SURROGATES", 1784 "HIGH PRIVATE USE SURROGATES", 1785 "HIGHPRIVATEUSESURROGATES"); 1786 1787 /** 1788 * Constant for the "Low Surrogates" Unicode character block. 1789 * This block represents codepoint values in the low surrogate 1790 * range: U+DC00 through U+DFFF 1791 * 1792 * @since 1.5 1793 */ 1794 public static final UnicodeBlock LOW_SURROGATES = 1795 new UnicodeBlock("LOW_SURROGATES", 1796 "LOW SURROGATES", 1797 "LOWSURROGATES"); 1798 1799 /** 1800 * Constant for the "Arabic Supplement" Unicode character block. 1801 * @since 1.7 1802 */ 1803 public static final UnicodeBlock ARABIC_SUPPLEMENT = 1804 new UnicodeBlock("ARABIC_SUPPLEMENT", 1805 "ARABIC SUPPLEMENT", 1806 "ARABICSUPPLEMENT"); 1807 1808 /** 1809 * Constant for the "NKo" Unicode character block. 1810 * @since 1.7 1811 */ 1812 public static final UnicodeBlock NKO = 1813 new UnicodeBlock("NKO"); 1814 1815 /** 1816 * Constant for the "Samaritan" Unicode character block. 1817 * @since 1.7 1818 */ 1819 public static final UnicodeBlock SAMARITAN = 1820 new UnicodeBlock("SAMARITAN"); 1821 1822 /** 1823 * Constant for the "Mandaic" Unicode character block. 1824 * @since 1.7 1825 */ 1826 public static final UnicodeBlock MANDAIC = 1827 new UnicodeBlock("MANDAIC"); 1828 1829 /** 1830 * Constant for the "Ethiopic Supplement" Unicode character block. 1831 * @since 1.7 1832 */ 1833 public static final UnicodeBlock ETHIOPIC_SUPPLEMENT = 1834 new UnicodeBlock("ETHIOPIC_SUPPLEMENT", 1835 "ETHIOPIC SUPPLEMENT", 1836 "ETHIOPICSUPPLEMENT"); 1837 1838 /** 1839 * Constant for the "Unified Canadian Aboriginal Syllabics Extended" 1840 * Unicode character block. 1841 * @since 1.7 1842 */ 1843 public static final UnicodeBlock UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED = 1844 new UnicodeBlock("UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED", 1845 "UNIFIED CANADIAN ABORIGINAL SYLLABICS EXTENDED", 1846 "UNIFIEDCANADIANABORIGINALSYLLABICSEXTENDED"); 1847 1848 /** 1849 * Constant for the "New Tai Lue" Unicode character block. 1850 * @since 1.7 1851 */ 1852 public static final UnicodeBlock NEW_TAI_LUE = 1853 new UnicodeBlock("NEW_TAI_LUE", 1854 "NEW TAI LUE", 1855 "NEWTAILUE"); 1856 1857 /** 1858 * Constant for the "Buginese" Unicode character block. 1859 * @since 1.7 1860 */ 1861 public static final UnicodeBlock BUGINESE = 1862 new UnicodeBlock("BUGINESE"); 1863 1864 /** 1865 * Constant for the "Tai Tham" Unicode character block. 1866 * @since 1.7 1867 */ 1868 public static final UnicodeBlock TAI_THAM = 1869 new UnicodeBlock("TAI_THAM", 1870 "TAI THAM", 1871 "TAITHAM"); 1872 1873 /** 1874 * Constant for the "Balinese" Unicode character block. 1875 * @since 1.7 1876 */ 1877 public static final UnicodeBlock BALINESE = 1878 new UnicodeBlock("BALINESE"); 1879 1880 /** 1881 * Constant for the "Sundanese" Unicode character block. 1882 * @since 1.7 1883 */ 1884 public static final UnicodeBlock SUNDANESE = 1885 new UnicodeBlock("SUNDANESE"); 1886 1887 /** 1888 * Constant for the "Batak" Unicode character block. 1889 * @since 1.7 1890 */ 1891 public static final UnicodeBlock BATAK = 1892 new UnicodeBlock("BATAK"); 1893 1894 /** 1895 * Constant for the "Lepcha" Unicode character block. 1896 * @since 1.7 1897 */ 1898 public static final UnicodeBlock LEPCHA = 1899 new UnicodeBlock("LEPCHA"); 1900 1901 /** 1902 * Constant for the "Ol Chiki" Unicode character block. 1903 * @since 1.7 1904 */ 1905 public static final UnicodeBlock OL_CHIKI = 1906 new UnicodeBlock("OL_CHIKI", 1907 "OL CHIKI", 1908 "OLCHIKI"); 1909 1910 /** 1911 * Constant for the "Vedic Extensions" Unicode character block. 1912 * @since 1.7 1913 */ 1914 public static final UnicodeBlock VEDIC_EXTENSIONS = 1915 new UnicodeBlock("VEDIC_EXTENSIONS", 1916 "VEDIC EXTENSIONS", 1917 "VEDICEXTENSIONS"); 1918 1919 /** 1920 * Constant for the "Phonetic Extensions Supplement" Unicode character 1921 * block. 1922 * @since 1.7 1923 */ 1924 public static final UnicodeBlock PHONETIC_EXTENSIONS_SUPPLEMENT = 1925 new UnicodeBlock("PHONETIC_EXTENSIONS_SUPPLEMENT", 1926 "PHONETIC EXTENSIONS SUPPLEMENT", 1927 "PHONETICEXTENSIONSSUPPLEMENT"); 1928 1929 /** 1930 * Constant for the "Combining Diacritical Marks Supplement" Unicode 1931 * character block. 1932 * @since 1.7 1933 */ 1934 public static final UnicodeBlock COMBINING_DIACRITICAL_MARKS_SUPPLEMENT = 1935 new UnicodeBlock("COMBINING_DIACRITICAL_MARKS_SUPPLEMENT", 1936 "COMBINING DIACRITICAL MARKS SUPPLEMENT", 1937 "COMBININGDIACRITICALMARKSSUPPLEMENT"); 1938 1939 /** 1940 * Constant for the "Glagolitic" Unicode character block. 1941 * @since 1.7 1942 */ 1943 public static final UnicodeBlock GLAGOLITIC = 1944 new UnicodeBlock("GLAGOLITIC"); 1945 1946 /** 1947 * Constant for the "Latin Extended-C" Unicode character block. 1948 * @since 1.7 1949 */ 1950 public static final UnicodeBlock LATIN_EXTENDED_C = 1951 new UnicodeBlock("LATIN_EXTENDED_C", 1952 "LATIN EXTENDED-C", 1953 "LATINEXTENDED-C"); 1954 1955 /** 1956 * Constant for the "Coptic" Unicode character block. 1957 * @since 1.7 1958 */ 1959 public static final UnicodeBlock COPTIC = 1960 new UnicodeBlock("COPTIC"); 1961 1962 /** 1963 * Constant for the "Georgian Supplement" Unicode character block. 1964 * @since 1.7 1965 */ 1966 public static final UnicodeBlock GEORGIAN_SUPPLEMENT = 1967 new UnicodeBlock("GEORGIAN_SUPPLEMENT", 1968 "GEORGIAN SUPPLEMENT", 1969 "GEORGIANSUPPLEMENT"); 1970 1971 /** 1972 * Constant for the "Tifinagh" Unicode character block. 1973 * @since 1.7 1974 */ 1975 public static final UnicodeBlock TIFINAGH = 1976 new UnicodeBlock("TIFINAGH"); 1977 1978 /** 1979 * Constant for the "Ethiopic Extended" Unicode character block. 1980 * @since 1.7 1981 */ 1982 public static final UnicodeBlock ETHIOPIC_EXTENDED = 1983 new UnicodeBlock("ETHIOPIC_EXTENDED", 1984 "ETHIOPIC EXTENDED", 1985 "ETHIOPICEXTENDED"); 1986 1987 /** 1988 * Constant for the "Cyrillic Extended-A" Unicode character block. 1989 * @since 1.7 1990 */ 1991 public static final UnicodeBlock CYRILLIC_EXTENDED_A = 1992 new UnicodeBlock("CYRILLIC_EXTENDED_A", 1993 "CYRILLIC EXTENDED-A", 1994 "CYRILLICEXTENDED-A"); 1995 1996 /** 1997 * Constant for the "Supplemental Punctuation" Unicode character block. 1998 * @since 1.7 1999 */ 2000 public static final UnicodeBlock SUPPLEMENTAL_PUNCTUATION = 2001 new UnicodeBlock("SUPPLEMENTAL_PUNCTUATION", 2002 "SUPPLEMENTAL PUNCTUATION", 2003 "SUPPLEMENTALPUNCTUATION"); 2004 2005 /** 2006 * Constant for the "CJK Strokes" Unicode character block. 2007 * @since 1.7 2008 */ 2009 public static final UnicodeBlock CJK_STROKES = 2010 new UnicodeBlock("CJK_STROKES", 2011 "CJK STROKES", 2012 "CJKSTROKES"); 2013 2014 /** 2015 * Constant for the "Lisu" Unicode character block. 2016 * @since 1.7 2017 */ 2018 public static final UnicodeBlock LISU = 2019 new UnicodeBlock("LISU"); 2020 2021 /** 2022 * Constant for the "Vai" Unicode character block. 2023 * @since 1.7 2024 */ 2025 public static final UnicodeBlock VAI = 2026 new UnicodeBlock("VAI"); 2027 2028 /** 2029 * Constant for the "Cyrillic Extended-B" Unicode character block. 2030 * @since 1.7 2031 */ 2032 public static final UnicodeBlock CYRILLIC_EXTENDED_B = 2033 new UnicodeBlock("CYRILLIC_EXTENDED_B", 2034 "CYRILLIC EXTENDED-B", 2035 "CYRILLICEXTENDED-B"); 2036 2037 /** 2038 * Constant for the "Bamum" Unicode character block. 2039 * @since 1.7 2040 */ 2041 public static final UnicodeBlock BAMUM = 2042 new UnicodeBlock("BAMUM"); 2043 2044 /** 2045 * Constant for the "Modifier Tone Letters" Unicode character block. 2046 * @since 1.7 2047 */ 2048 public static final UnicodeBlock MODIFIER_TONE_LETTERS = 2049 new UnicodeBlock("MODIFIER_TONE_LETTERS", 2050 "MODIFIER TONE LETTERS", 2051 "MODIFIERTONELETTERS"); 2052 2053 /** 2054 * Constant for the "Latin Extended-D" Unicode character block. 2055 * @since 1.7 2056 */ 2057 public static final UnicodeBlock LATIN_EXTENDED_D = 2058 new UnicodeBlock("LATIN_EXTENDED_D", 2059 "LATIN EXTENDED-D", 2060 "LATINEXTENDED-D"); 2061 2062 /** 2063 * Constant for the "Syloti Nagri" Unicode character block. 2064 * @since 1.7 2065 */ 2066 public static final UnicodeBlock SYLOTI_NAGRI = 2067 new UnicodeBlock("SYLOTI_NAGRI", 2068 "SYLOTI NAGRI", 2069 "SYLOTINAGRI"); 2070 2071 /** 2072 * Constant for the "Common Indic Number Forms" Unicode character block. 2073 * @since 1.7 2074 */ 2075 public static final UnicodeBlock COMMON_INDIC_NUMBER_FORMS = 2076 new UnicodeBlock("COMMON_INDIC_NUMBER_FORMS", 2077 "COMMON INDIC NUMBER FORMS", 2078 "COMMONINDICNUMBERFORMS"); 2079 2080 /** 2081 * Constant for the "Phags-pa" Unicode character block. 2082 * @since 1.7 2083 */ 2084 public static final UnicodeBlock PHAGS_PA = 2085 new UnicodeBlock("PHAGS_PA", 2086 "PHAGS-PA"); 2087 2088 /** 2089 * Constant for the "Saurashtra" Unicode character block. 2090 * @since 1.7 2091 */ 2092 public static final UnicodeBlock SAURASHTRA = 2093 new UnicodeBlock("SAURASHTRA"); 2094 2095 /** 2096 * Constant for the "Devanagari Extended" Unicode character block. 2097 * @since 1.7 2098 */ 2099 public static final UnicodeBlock DEVANAGARI_EXTENDED = 2100 new UnicodeBlock("DEVANAGARI_EXTENDED", 2101 "DEVANAGARI EXTENDED", 2102 "DEVANAGARIEXTENDED"); 2103 2104 /** 2105 * Constant for the "Kayah Li" Unicode character block. 2106 * @since 1.7 2107 */ 2108 public static final UnicodeBlock KAYAH_LI = 2109 new UnicodeBlock("KAYAH_LI", 2110 "KAYAH LI", 2111 "KAYAHLI"); 2112 2113 /** 2114 * Constant for the "Rejang" Unicode character block. 2115 * @since 1.7 2116 */ 2117 public static final UnicodeBlock REJANG = 2118 new UnicodeBlock("REJANG"); 2119 2120 /** 2121 * Constant for the "Hangul Jamo Extended-A" Unicode character block. 2122 * @since 1.7 2123 */ 2124 public static final UnicodeBlock HANGUL_JAMO_EXTENDED_A = 2125 new UnicodeBlock("HANGUL_JAMO_EXTENDED_A", 2126 "HANGUL JAMO EXTENDED-A", 2127 "HANGULJAMOEXTENDED-A"); 2128 2129 /** 2130 * Constant for the "Javanese" Unicode character block. 2131 * @since 1.7 2132 */ 2133 public static final UnicodeBlock JAVANESE = 2134 new UnicodeBlock("JAVANESE"); 2135 2136 /** 2137 * Constant for the "Cham" Unicode character block. 2138 * @since 1.7 2139 */ 2140 public static final UnicodeBlock CHAM = 2141 new UnicodeBlock("CHAM"); 2142 2143 /** 2144 * Constant for the "Myanmar Extended-A" Unicode character block. 2145 * @since 1.7 2146 */ 2147 public static final UnicodeBlock MYANMAR_EXTENDED_A = 2148 new UnicodeBlock("MYANMAR_EXTENDED_A", 2149 "MYANMAR EXTENDED-A", 2150 "MYANMAREXTENDED-A"); 2151 2152 /** 2153 * Constant for the "Tai Viet" Unicode character block. 2154 * @since 1.7 2155 */ 2156 public static final UnicodeBlock TAI_VIET = 2157 new UnicodeBlock("TAI_VIET", 2158 "TAI VIET", 2159 "TAIVIET"); 2160 2161 /** 2162 * Constant for the "Ethiopic Extended-A" Unicode character block. 2163 * @since 1.7 2164 */ 2165 public static final UnicodeBlock ETHIOPIC_EXTENDED_A = 2166 new UnicodeBlock("ETHIOPIC_EXTENDED_A", 2167 "ETHIOPIC EXTENDED-A", 2168 "ETHIOPICEXTENDED-A"); 2169 2170 /** 2171 * Constant for the "Meetei Mayek" Unicode character block. 2172 * @since 1.7 2173 */ 2174 public static final UnicodeBlock MEETEI_MAYEK = 2175 new UnicodeBlock("MEETEI_MAYEK", 2176 "MEETEI MAYEK", 2177 "MEETEIMAYEK"); 2178 2179 /** 2180 * Constant for the "Hangul Jamo Extended-B" Unicode character block. 2181 * @since 1.7 2182 */ 2183 public static final UnicodeBlock HANGUL_JAMO_EXTENDED_B = 2184 new UnicodeBlock("HANGUL_JAMO_EXTENDED_B", 2185 "HANGUL JAMO EXTENDED-B", 2186 "HANGULJAMOEXTENDED-B"); 2187 2188 /** 2189 * Constant for the "Vertical Forms" Unicode character block. 2190 * @since 1.7 2191 */ 2192 public static final UnicodeBlock VERTICAL_FORMS = 2193 new UnicodeBlock("VERTICAL_FORMS", 2194 "VERTICAL FORMS", 2195 "VERTICALFORMS"); 2196 2197 /** 2198 * Constant for the "Ancient Greek Numbers" Unicode character block. 2199 * @since 1.7 2200 */ 2201 public static final UnicodeBlock ANCIENT_GREEK_NUMBERS = 2202 new UnicodeBlock("ANCIENT_GREEK_NUMBERS", 2203 "ANCIENT GREEK NUMBERS", 2204 "ANCIENTGREEKNUMBERS"); 2205 2206 /** 2207 * Constant for the "Ancient Symbols" Unicode character block. 2208 * @since 1.7 2209 */ 2210 public static final UnicodeBlock ANCIENT_SYMBOLS = 2211 new UnicodeBlock("ANCIENT_SYMBOLS", 2212 "ANCIENT SYMBOLS", 2213 "ANCIENTSYMBOLS"); 2214 2215 /** 2216 * Constant for the "Phaistos Disc" Unicode character block. 2217 * @since 1.7 2218 */ 2219 public static final UnicodeBlock PHAISTOS_DISC = 2220 new UnicodeBlock("PHAISTOS_DISC", 2221 "PHAISTOS DISC", 2222 "PHAISTOSDISC"); 2223 2224 /** 2225 * Constant for the "Lycian" Unicode character block. 2226 * @since 1.7 2227 */ 2228 public static final UnicodeBlock LYCIAN = 2229 new UnicodeBlock("LYCIAN"); 2230 2231 /** 2232 * Constant for the "Carian" Unicode character block. 2233 * @since 1.7 2234 */ 2235 public static final UnicodeBlock CARIAN = 2236 new UnicodeBlock("CARIAN"); 2237 2238 /** 2239 * Constant for the "Old Persian" Unicode character block. 2240 * @since 1.7 2241 */ 2242 public static final UnicodeBlock OLD_PERSIAN = 2243 new UnicodeBlock("OLD_PERSIAN", 2244 "OLD PERSIAN", 2245 "OLDPERSIAN"); 2246 2247 /** 2248 * Constant for the "Imperial Aramaic" Unicode character block. 2249 * @since 1.7 2250 */ 2251 public static final UnicodeBlock IMPERIAL_ARAMAIC = 2252 new UnicodeBlock("IMPERIAL_ARAMAIC", 2253 "IMPERIAL ARAMAIC", 2254 "IMPERIALARAMAIC"); 2255 2256 /** 2257 * Constant for the "Phoenician" Unicode character block. 2258 * @since 1.7 2259 */ 2260 public static final UnicodeBlock PHOENICIAN = 2261 new UnicodeBlock("PHOENICIAN"); 2262 2263 /** 2264 * Constant for the "Lydian" Unicode character block. 2265 * @since 1.7 2266 */ 2267 public static final UnicodeBlock LYDIAN = 2268 new UnicodeBlock("LYDIAN"); 2269 2270 /** 2271 * Constant for the "Kharoshthi" Unicode character block. 2272 * @since 1.7 2273 */ 2274 public static final UnicodeBlock KHAROSHTHI = 2275 new UnicodeBlock("KHAROSHTHI"); 2276 2277 /** 2278 * Constant for the "Old South Arabian" Unicode character block. 2279 * @since 1.7 2280 */ 2281 public static final UnicodeBlock OLD_SOUTH_ARABIAN = 2282 new UnicodeBlock("OLD_SOUTH_ARABIAN", 2283 "OLD SOUTH ARABIAN", 2284 "OLDSOUTHARABIAN"); 2285 2286 /** 2287 * Constant for the "Avestan" Unicode character block. 2288 * @since 1.7 2289 */ 2290 public static final UnicodeBlock AVESTAN = 2291 new UnicodeBlock("AVESTAN"); 2292 2293 /** 2294 * Constant for the "Inscriptional Parthian" Unicode character block. 2295 * @since 1.7 2296 */ 2297 public static final UnicodeBlock INSCRIPTIONAL_PARTHIAN = 2298 new UnicodeBlock("INSCRIPTIONAL_PARTHIAN", 2299 "INSCRIPTIONAL PARTHIAN", 2300 "INSCRIPTIONALPARTHIAN"); 2301 2302 /** 2303 * Constant for the "Inscriptional Pahlavi" Unicode character block. 2304 * @since 1.7 2305 */ 2306 public static final UnicodeBlock INSCRIPTIONAL_PAHLAVI = 2307 new UnicodeBlock("INSCRIPTIONAL_PAHLAVI", 2308 "INSCRIPTIONAL PAHLAVI", 2309 "INSCRIPTIONALPAHLAVI"); 2310 2311 /** 2312 * Constant for the "Old Turkic" Unicode character block. 2313 * @since 1.7 2314 */ 2315 public static final UnicodeBlock OLD_TURKIC = 2316 new UnicodeBlock("OLD_TURKIC", 2317 "OLD TURKIC", 2318 "OLDTURKIC"); 2319 2320 /** 2321 * Constant for the "Rumi Numeral Symbols" Unicode character block. 2322 * @since 1.7 2323 */ 2324 public static final UnicodeBlock RUMI_NUMERAL_SYMBOLS = 2325 new UnicodeBlock("RUMI_NUMERAL_SYMBOLS", 2326 "RUMI NUMERAL SYMBOLS", 2327 "RUMINUMERALSYMBOLS"); 2328 2329 /** 2330 * Constant for the "Brahmi" Unicode character block. 2331 * @since 1.7 2332 */ 2333 public static final UnicodeBlock BRAHMI = 2334 new UnicodeBlock("BRAHMI"); 2335 2336 /** 2337 * Constant for the "Kaithi" Unicode character block. 2338 * @since 1.7 2339 */ 2340 public static final UnicodeBlock KAITHI = 2341 new UnicodeBlock("KAITHI"); 2342 2343 /** 2344 * Constant for the "Cuneiform" Unicode character block. 2345 * @since 1.7 2346 */ 2347 public static final UnicodeBlock CUNEIFORM = 2348 new UnicodeBlock("CUNEIFORM"); 2349 2350 /** 2351 * Constant for the "Cuneiform Numbers and Punctuation" Unicode 2352 * character block. 2353 * @since 1.7 2354 */ 2355 public static final UnicodeBlock CUNEIFORM_NUMBERS_AND_PUNCTUATION = 2356 new UnicodeBlock("CUNEIFORM_NUMBERS_AND_PUNCTUATION", 2357 "CUNEIFORM NUMBERS AND PUNCTUATION", 2358 "CUNEIFORMNUMBERSANDPUNCTUATION"); 2359 2360 /** 2361 * Constant for the "Egyptian Hieroglyphs" Unicode character block. 2362 * @since 1.7 2363 */ 2364 public static final UnicodeBlock EGYPTIAN_HIEROGLYPHS = 2365 new UnicodeBlock("EGYPTIAN_HIEROGLYPHS", 2366 "EGYPTIAN HIEROGLYPHS", 2367 "EGYPTIANHIEROGLYPHS"); 2368 2369 /** 2370 * Constant for the "Bamum Supplement" Unicode character block. 2371 * @since 1.7 2372 */ 2373 public static final UnicodeBlock BAMUM_SUPPLEMENT = 2374 new UnicodeBlock("BAMUM_SUPPLEMENT", 2375 "BAMUM SUPPLEMENT", 2376 "BAMUMSUPPLEMENT"); 2377 2378 /** 2379 * Constant for the "Kana Supplement" Unicode character block. 2380 * @since 1.7 2381 */ 2382 public static final UnicodeBlock KANA_SUPPLEMENT = 2383 new UnicodeBlock("KANA_SUPPLEMENT", 2384 "KANA SUPPLEMENT", 2385 "KANASUPPLEMENT"); 2386 2387 /** 2388 * Constant for the "Ancient Greek Musical Notation" Unicode character 2389 * block. 2390 * @since 1.7 2391 */ 2392 public static final UnicodeBlock ANCIENT_GREEK_MUSICAL_NOTATION = 2393 new UnicodeBlock("ANCIENT_GREEK_MUSICAL_NOTATION", 2394 "ANCIENT GREEK MUSICAL NOTATION", 2395 "ANCIENTGREEKMUSICALNOTATION"); 2396 2397 /** 2398 * Constant for the "Counting Rod Numerals" Unicode character block. 2399 * @since 1.7 2400 */ 2401 public static final UnicodeBlock COUNTING_ROD_NUMERALS = 2402 new UnicodeBlock("COUNTING_ROD_NUMERALS", 2403 "COUNTING ROD NUMERALS", 2404 "COUNTINGRODNUMERALS"); 2405 2406 /** 2407 * Constant for the "Mahjong Tiles" Unicode character block. 2408 * @since 1.7 2409 */ 2410 public static final UnicodeBlock MAHJONG_TILES = 2411 new UnicodeBlock("MAHJONG_TILES", 2412 "MAHJONG TILES", 2413 "MAHJONGTILES"); 2414 2415 /** 2416 * Constant for the "Domino Tiles" Unicode character block. 2417 * @since 1.7 2418 */ 2419 public static final UnicodeBlock DOMINO_TILES = 2420 new UnicodeBlock("DOMINO_TILES", 2421 "DOMINO TILES", 2422 "DOMINOTILES"); 2423 2424 /** 2425 * Constant for the "Playing Cards" Unicode character block. 2426 * @since 1.7 2427 */ 2428 public static final UnicodeBlock PLAYING_CARDS = 2429 new UnicodeBlock("PLAYING_CARDS", 2430 "PLAYING CARDS", 2431 "PLAYINGCARDS"); 2432 2433 /** 2434 * Constant for the "Enclosed Alphanumeric Supplement" Unicode character 2435 * block. 2436 * @since 1.7 2437 */ 2438 public static final UnicodeBlock ENCLOSED_ALPHANUMERIC_SUPPLEMENT = 2439 new UnicodeBlock("ENCLOSED_ALPHANUMERIC_SUPPLEMENT", 2440 "ENCLOSED ALPHANUMERIC SUPPLEMENT", 2441 "ENCLOSEDALPHANUMERICSUPPLEMENT"); 2442 2443 /** 2444 * Constant for the "Enclosed Ideographic Supplement" Unicode character 2445 * block. 2446 * @since 1.7 2447 */ 2448 public static final UnicodeBlock ENCLOSED_IDEOGRAPHIC_SUPPLEMENT = 2449 new UnicodeBlock("ENCLOSED_IDEOGRAPHIC_SUPPLEMENT", 2450 "ENCLOSED IDEOGRAPHIC SUPPLEMENT", 2451 "ENCLOSEDIDEOGRAPHICSUPPLEMENT"); 2452 2453 /** 2454 * Constant for the "Miscellaneous Symbols And Pictographs" Unicode 2455 * character block. 2456 * @since 1.7 2457 */ 2458 public static final UnicodeBlock MISCELLANEOUS_SYMBOLS_AND_PICTOGRAPHS = 2459 new UnicodeBlock("MISCELLANEOUS_SYMBOLS_AND_PICTOGRAPHS", 2460 "MISCELLANEOUS SYMBOLS AND PICTOGRAPHS", 2461 "MISCELLANEOUSSYMBOLSANDPICTOGRAPHS"); 2462 2463 /** 2464 * Constant for the "Emoticons" Unicode character block. 2465 * @since 1.7 2466 */ 2467 public static final UnicodeBlock EMOTICONS = 2468 new UnicodeBlock("EMOTICONS"); 2469 2470 /** 2471 * Constant for the "Transport And Map Symbols" Unicode character block. 2472 * @since 1.7 2473 */ 2474 public static final UnicodeBlock TRANSPORT_AND_MAP_SYMBOLS = 2475 new UnicodeBlock("TRANSPORT_AND_MAP_SYMBOLS", 2476 "TRANSPORT AND MAP SYMBOLS", 2477 "TRANSPORTANDMAPSYMBOLS"); 2478 2479 /** 2480 * Constant for the "Alchemical Symbols" Unicode character block. 2481 * @since 1.7 2482 */ 2483 public static final UnicodeBlock ALCHEMICAL_SYMBOLS = 2484 new UnicodeBlock("ALCHEMICAL_SYMBOLS", 2485 "ALCHEMICAL SYMBOLS", 2486 "ALCHEMICALSYMBOLS"); 2487 2488 /** 2489 * Constant for the "CJK Unified Ideographs Extension C" Unicode 2490 * character block. 2491 * @since 1.7 2492 */ 2493 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_C = 2494 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_C", 2495 "CJK UNIFIED IDEOGRAPHS EXTENSION C", 2496 "CJKUNIFIEDIDEOGRAPHSEXTENSIONC"); 2497 2498 /** 2499 * Constant for the "CJK Unified Ideographs Extension D" Unicode 2500 * character block. 2501 * @since 1.7 2502 */ 2503 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_D = 2504 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_D", 2505 "CJK UNIFIED IDEOGRAPHS EXTENSION D", 2506 "CJKUNIFIEDIDEOGRAPHSEXTENSIOND"); 2507 2508 /** 2509 * Constant for the "Arabic Extended-A" Unicode character block. 2510 * @since 1.8 2511 */ 2512 public static final UnicodeBlock ARABIC_EXTENDED_A = 2513 new UnicodeBlock("ARABIC_EXTENDED_A", 2514 "ARABIC EXTENDED-A", 2515 "ARABICEXTENDED-A"); 2516 2517 /** 2518 * Constant for the "Sundanese Supplement" Unicode character block. 2519 * @since 1.8 2520 */ 2521 public static final UnicodeBlock SUNDANESE_SUPPLEMENT = 2522 new UnicodeBlock("SUNDANESE_SUPPLEMENT", 2523 "SUNDANESE SUPPLEMENT", 2524 "SUNDANESESUPPLEMENT"); 2525 2526 /** 2527 * Constant for the "Meetei Mayek Extensions" Unicode character block. 2528 * @since 1.8 2529 */ 2530 public static final UnicodeBlock MEETEI_MAYEK_EXTENSIONS = 2531 new UnicodeBlock("MEETEI_MAYEK_EXTENSIONS", 2532 "MEETEI MAYEK EXTENSIONS", 2533 "MEETEIMAYEKEXTENSIONS"); 2534 2535 /** 2536 * Constant for the "Meroitic Hieroglyphs" Unicode character block. 2537 * @since 1.8 2538 */ 2539 public static final UnicodeBlock MEROITIC_HIEROGLYPHS = 2540 new UnicodeBlock("MEROITIC_HIEROGLYPHS", 2541 "MEROITIC HIEROGLYPHS", 2542 "MEROITICHIEROGLYPHS"); 2543 2544 /** 2545 * Constant for the "Meroitic Cursive" Unicode character block. 2546 * @since 1.8 2547 */ 2548 public static final UnicodeBlock MEROITIC_CURSIVE = 2549 new UnicodeBlock("MEROITIC_CURSIVE", 2550 "MEROITIC CURSIVE", 2551 "MEROITICCURSIVE"); 2552 2553 /** 2554 * Constant for the "Sora Sompeng" Unicode character block. 2555 * @since 1.8 2556 */ 2557 public static final UnicodeBlock SORA_SOMPENG = 2558 new UnicodeBlock("SORA_SOMPENG", 2559 "SORA SOMPENG", 2560 "SORASOMPENG"); 2561 2562 /** 2563 * Constant for the "Chakma" Unicode character block. 2564 * @since 1.8 2565 */ 2566 public static final UnicodeBlock CHAKMA = 2567 new UnicodeBlock("CHAKMA"); 2568 2569 /** 2570 * Constant for the "Sharada" Unicode character block. 2571 * @since 1.8 2572 */ 2573 public static final UnicodeBlock SHARADA = 2574 new UnicodeBlock("SHARADA"); 2575 2576 /** 2577 * Constant for the "Takri" Unicode character block. 2578 * @since 1.8 2579 */ 2580 public static final UnicodeBlock TAKRI = 2581 new UnicodeBlock("TAKRI"); 2582 2583 /** 2584 * Constant for the "Miao" Unicode character block. 2585 * @since 1.8 2586 */ 2587 public static final UnicodeBlock MIAO = 2588 new UnicodeBlock("MIAO"); 2589 2590 /** 2591 * Constant for the "Arabic Mathematical Alphabetic Symbols" Unicode 2592 * character block. 2593 * @since 1.8 2594 */ 2595 public static final UnicodeBlock ARABIC_MATHEMATICAL_ALPHABETIC_SYMBOLS = 2596 new UnicodeBlock("ARABIC_MATHEMATICAL_ALPHABETIC_SYMBOLS", 2597 "ARABIC MATHEMATICAL ALPHABETIC SYMBOLS", 2598 "ARABICMATHEMATICALALPHABETICSYMBOLS"); 2599 2600 /** 2601 * Constant for the "Combining Diacritical Marks Extended" Unicode 2602 * character block. 2603 * @since 9 2604 */ 2605 public static final UnicodeBlock COMBINING_DIACRITICAL_MARKS_EXTENDED = 2606 new UnicodeBlock("COMBINING_DIACRITICAL_MARKS_EXTENDED", 2607 "COMBINING DIACRITICAL MARKS EXTENDED", 2608 "COMBININGDIACRITICALMARKSEXTENDED"); 2609 2610 /** 2611 * Constant for the "Myanmar Extended-B" Unicode character block. 2612 * @since 9 2613 */ 2614 public static final UnicodeBlock MYANMAR_EXTENDED_B = 2615 new UnicodeBlock("MYANMAR_EXTENDED_B", 2616 "MYANMAR EXTENDED-B", 2617 "MYANMAREXTENDED-B"); 2618 2619 /** 2620 * Constant for the "Latin Extended-E" Unicode character block. 2621 * @since 9 2622 */ 2623 public static final UnicodeBlock LATIN_EXTENDED_E = 2624 new UnicodeBlock("LATIN_EXTENDED_E", 2625 "LATIN EXTENDED-E", 2626 "LATINEXTENDED-E"); 2627 2628 /** 2629 * Constant for the "Coptic Epact Numbers" Unicode character block. 2630 * @since 9 2631 */ 2632 public static final UnicodeBlock COPTIC_EPACT_NUMBERS = 2633 new UnicodeBlock("COPTIC_EPACT_NUMBERS", 2634 "COPTIC EPACT NUMBERS", 2635 "COPTICEPACTNUMBERS"); 2636 2637 /** 2638 * Constant for the "Old Permic" Unicode character block. 2639 * @since 9 2640 */ 2641 public static final UnicodeBlock OLD_PERMIC = 2642 new UnicodeBlock("OLD_PERMIC", 2643 "OLD PERMIC", 2644 "OLDPERMIC"); 2645 2646 /** 2647 * Constant for the "Elbasan" Unicode character block. 2648 * @since 9 2649 */ 2650 public static final UnicodeBlock ELBASAN = 2651 new UnicodeBlock("ELBASAN"); 2652 2653 /** 2654 * Constant for the "Caucasian Albanian" Unicode character block. 2655 * @since 9 2656 */ 2657 public static final UnicodeBlock CAUCASIAN_ALBANIAN = 2658 new UnicodeBlock("CAUCASIAN_ALBANIAN", 2659 "CAUCASIAN ALBANIAN", 2660 "CAUCASIANALBANIAN"); 2661 2662 /** 2663 * Constant for the "Linear A" Unicode character block. 2664 * @since 9 2665 */ 2666 public static final UnicodeBlock LINEAR_A = 2667 new UnicodeBlock("LINEAR_A", 2668 "LINEAR A", 2669 "LINEARA"); 2670 2671 /** 2672 * Constant for the "Palmyrene" Unicode character block. 2673 * @since 9 2674 */ 2675 public static final UnicodeBlock PALMYRENE = 2676 new UnicodeBlock("PALMYRENE"); 2677 2678 /** 2679 * Constant for the "Nabataean" Unicode character block. 2680 * @since 9 2681 */ 2682 public static final UnicodeBlock NABATAEAN = 2683 new UnicodeBlock("NABATAEAN"); 2684 2685 /** 2686 * Constant for the "Old North Arabian" Unicode character block. 2687 * @since 9 2688 */ 2689 public static final UnicodeBlock OLD_NORTH_ARABIAN = 2690 new UnicodeBlock("OLD_NORTH_ARABIAN", 2691 "OLD NORTH ARABIAN", 2692 "OLDNORTHARABIAN"); 2693 2694 /** 2695 * Constant for the "Manichaean" Unicode character block. 2696 * @since 9 2697 */ 2698 public static final UnicodeBlock MANICHAEAN = 2699 new UnicodeBlock("MANICHAEAN"); 2700 2701 /** 2702 * Constant for the "Psalter Pahlavi" Unicode character block. 2703 * @since 9 2704 */ 2705 public static final UnicodeBlock PSALTER_PAHLAVI = 2706 new UnicodeBlock("PSALTER_PAHLAVI", 2707 "PSALTER PAHLAVI", 2708 "PSALTERPAHLAVI"); 2709 2710 /** 2711 * Constant for the "Mahajani" Unicode character block. 2712 * @since 9 2713 */ 2714 public static final UnicodeBlock MAHAJANI = 2715 new UnicodeBlock("MAHAJANI"); 2716 2717 /** 2718 * Constant for the "Sinhala Archaic Numbers" Unicode character block. 2719 * @since 9 2720 */ 2721 public static final UnicodeBlock SINHALA_ARCHAIC_NUMBERS = 2722 new UnicodeBlock("SINHALA_ARCHAIC_NUMBERS", 2723 "SINHALA ARCHAIC NUMBERS", 2724 "SINHALAARCHAICNUMBERS"); 2725 2726 /** 2727 * Constant for the "Khojki" Unicode character block. 2728 * @since 9 2729 */ 2730 public static final UnicodeBlock KHOJKI = 2731 new UnicodeBlock("KHOJKI"); 2732 2733 /** 2734 * Constant for the "Khudawadi" Unicode character block. 2735 * @since 9 2736 */ 2737 public static final UnicodeBlock KHUDAWADI = 2738 new UnicodeBlock("KHUDAWADI"); 2739 2740 /** 2741 * Constant for the "Grantha" Unicode character block. 2742 * @since 9 2743 */ 2744 public static final UnicodeBlock GRANTHA = 2745 new UnicodeBlock("GRANTHA"); 2746 2747 /** 2748 * Constant for the "Tirhuta" Unicode character block. 2749 * @since 9 2750 */ 2751 public static final UnicodeBlock TIRHUTA = 2752 new UnicodeBlock("TIRHUTA"); 2753 2754 /** 2755 * Constant for the "Siddham" Unicode character block. 2756 * @since 9 2757 */ 2758 public static final UnicodeBlock SIDDHAM = 2759 new UnicodeBlock("SIDDHAM"); 2760 2761 /** 2762 * Constant for the "Modi" Unicode character block. 2763 * @since 9 2764 */ 2765 public static final UnicodeBlock MODI = 2766 new UnicodeBlock("MODI"); 2767 2768 /** 2769 * Constant for the "Warang Citi" Unicode character block. 2770 * @since 9 2771 */ 2772 public static final UnicodeBlock WARANG_CITI = 2773 new UnicodeBlock("WARANG_CITI", 2774 "WARANG CITI", 2775 "WARANGCITI"); 2776 2777 /** 2778 * Constant for the "Pau Cin Hau" Unicode character block. 2779 * @since 9 2780 */ 2781 public static final UnicodeBlock PAU_CIN_HAU = 2782 new UnicodeBlock("PAU_CIN_HAU", 2783 "PAU CIN HAU", 2784 "PAUCINHAU"); 2785 2786 /** 2787 * Constant for the "Mro" Unicode character block. 2788 * @since 9 2789 */ 2790 public static final UnicodeBlock MRO = 2791 new UnicodeBlock("MRO"); 2792 2793 /** 2794 * Constant for the "Bassa Vah" Unicode character block. 2795 * @since 9 2796 */ 2797 public static final UnicodeBlock BASSA_VAH = 2798 new UnicodeBlock("BASSA_VAH", 2799 "BASSA VAH", 2800 "BASSAVAH"); 2801 2802 /** 2803 * Constant for the "Pahawh Hmong" Unicode character block. 2804 * @since 9 2805 */ 2806 public static final UnicodeBlock PAHAWH_HMONG = 2807 new UnicodeBlock("PAHAWH_HMONG", 2808 "PAHAWH HMONG", 2809 "PAHAWHHMONG"); 2810 2811 /** 2812 * Constant for the "Duployan" Unicode character block. 2813 * @since 9 2814 */ 2815 public static final UnicodeBlock DUPLOYAN = 2816 new UnicodeBlock("DUPLOYAN"); 2817 2818 /** 2819 * Constant for the "Shorthand Format Controls" Unicode character block. 2820 * @since 9 2821 */ 2822 public static final UnicodeBlock SHORTHAND_FORMAT_CONTROLS = 2823 new UnicodeBlock("SHORTHAND_FORMAT_CONTROLS", 2824 "SHORTHAND FORMAT CONTROLS", 2825 "SHORTHANDFORMATCONTROLS"); 2826 2827 /** 2828 * Constant for the "Mende Kikakui" Unicode character block. 2829 * @since 9 2830 */ 2831 public static final UnicodeBlock MENDE_KIKAKUI = 2832 new UnicodeBlock("MENDE_KIKAKUI", 2833 "MENDE KIKAKUI", 2834 "MENDEKIKAKUI"); 2835 2836 /** 2837 * Constant for the "Ornamental Dingbats" Unicode character block. 2838 * @since 9 2839 */ 2840 public static final UnicodeBlock ORNAMENTAL_DINGBATS = 2841 new UnicodeBlock("ORNAMENTAL_DINGBATS", 2842 "ORNAMENTAL DINGBATS", 2843 "ORNAMENTALDINGBATS"); 2844 2845 /** 2846 * Constant for the "Geometric Shapes Extended" Unicode character block. 2847 * @since 9 2848 */ 2849 public static final UnicodeBlock GEOMETRIC_SHAPES_EXTENDED = 2850 new UnicodeBlock("GEOMETRIC_SHAPES_EXTENDED", 2851 "GEOMETRIC SHAPES EXTENDED", 2852 "GEOMETRICSHAPESEXTENDED"); 2853 2854 /** 2855 * Constant for the "Supplemental Arrows-C" Unicode character block. 2856 * @since 9 2857 */ 2858 public static final UnicodeBlock SUPPLEMENTAL_ARROWS_C = 2859 new UnicodeBlock("SUPPLEMENTAL_ARROWS_C", 2860 "SUPPLEMENTAL ARROWS-C", 2861 "SUPPLEMENTALARROWS-C"); 2862 2863 /** 2864 * Constant for the "Cherokee Supplement" Unicode character block. 2865 * @since 9 2866 */ 2867 public static final UnicodeBlock CHEROKEE_SUPPLEMENT = 2868 new UnicodeBlock("CHEROKEE_SUPPLEMENT", 2869 "CHEROKEE SUPPLEMENT", 2870 "CHEROKEESUPPLEMENT"); 2871 2872 /** 2873 * Constant for the "Hatran" Unicode character block. 2874 * @since 9 2875 */ 2876 public static final UnicodeBlock HATRAN = 2877 new UnicodeBlock("HATRAN"); 2878 2879 /** 2880 * Constant for the "Old Hungarian" Unicode character block. 2881 * @since 9 2882 */ 2883 public static final UnicodeBlock OLD_HUNGARIAN = 2884 new UnicodeBlock("OLD_HUNGARIAN", 2885 "OLD HUNGARIAN", 2886 "OLDHUNGARIAN"); 2887 2888 /** 2889 * Constant for the "Multani" Unicode character block. 2890 * @since 9 2891 */ 2892 public static final UnicodeBlock MULTANI = 2893 new UnicodeBlock("MULTANI"); 2894 2895 /** 2896 * Constant for the "Ahom" Unicode character block. 2897 * @since 9 2898 */ 2899 public static final UnicodeBlock AHOM = 2900 new UnicodeBlock("AHOM"); 2901 2902 /** 2903 * Constant for the "Early Dynastic Cuneiform" Unicode character block. 2904 * @since 9 2905 */ 2906 public static final UnicodeBlock EARLY_DYNASTIC_CUNEIFORM = 2907 new UnicodeBlock("EARLY_DYNASTIC_CUNEIFORM", 2908 "EARLY DYNASTIC CUNEIFORM", 2909 "EARLYDYNASTICCUNEIFORM"); 2910 2911 /** 2912 * Constant for the "Anatolian Hieroglyphs" Unicode character block. 2913 * @since 9 2914 */ 2915 public static final UnicodeBlock ANATOLIAN_HIEROGLYPHS = 2916 new UnicodeBlock("ANATOLIAN_HIEROGLYPHS", 2917 "ANATOLIAN HIEROGLYPHS", 2918 "ANATOLIANHIEROGLYPHS"); 2919 2920 /** 2921 * Constant for the "Sutton SignWriting" Unicode character block. 2922 * @since 9 2923 */ 2924 public static final UnicodeBlock SUTTON_SIGNWRITING = 2925 new UnicodeBlock("SUTTON_SIGNWRITING", 2926 "SUTTON SIGNWRITING", 2927 "SUTTONSIGNWRITING"); 2928 2929 /** 2930 * Constant for the "Supplemental Symbols and Pictographs" Unicode 2931 * character block. 2932 * @since 9 2933 */ 2934 public static final UnicodeBlock SUPPLEMENTAL_SYMBOLS_AND_PICTOGRAPHS = 2935 new UnicodeBlock("SUPPLEMENTAL_SYMBOLS_AND_PICTOGRAPHS", 2936 "SUPPLEMENTAL SYMBOLS AND PICTOGRAPHS", 2937 "SUPPLEMENTALSYMBOLSANDPICTOGRAPHS"); 2938 2939 /** 2940 * Constant for the "CJK Unified Ideographs Extension E" Unicode 2941 * character block. 2942 * @since 9 2943 */ 2944 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_E = 2945 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_E", 2946 "CJK UNIFIED IDEOGRAPHS EXTENSION E", 2947 "CJKUNIFIEDIDEOGRAPHSEXTENSIONE"); 2948 2949 /** 2950 * Constant for the "Syriac Supplement" Unicode 2951 * character block. 2952 * @since 11 2953 */ 2954 public static final UnicodeBlock SYRIAC_SUPPLEMENT = 2955 new UnicodeBlock("SYRIAC_SUPPLEMENT", 2956 "SYRIAC SUPPLEMENT", 2957 "SYRIACSUPPLEMENT"); 2958 2959 /** 2960 * Constant for the "Cyrillic Extended-C" Unicode 2961 * character block. 2962 * @since 11 2963 */ 2964 public static final UnicodeBlock CYRILLIC_EXTENDED_C = 2965 new UnicodeBlock("CYRILLIC_EXTENDED_C", 2966 "CYRILLIC EXTENDED-C", 2967 "CYRILLICEXTENDED-C"); 2968 2969 /** 2970 * Constant for the "Osage" Unicode 2971 * character block. 2972 * @since 11 2973 */ 2974 public static final UnicodeBlock OSAGE = 2975 new UnicodeBlock("OSAGE"); 2976 2977 /** 2978 * Constant for the "Newa" Unicode 2979 * character block. 2980 * @since 11 2981 */ 2982 public static final UnicodeBlock NEWA = 2983 new UnicodeBlock("NEWA"); 2984 2985 /** 2986 * Constant for the "Mongolian Supplement" Unicode 2987 * character block. 2988 * @since 11 2989 */ 2990 public static final UnicodeBlock MONGOLIAN_SUPPLEMENT = 2991 new UnicodeBlock("MONGOLIAN_SUPPLEMENT", 2992 "MONGOLIAN SUPPLEMENT", 2993 "MONGOLIANSUPPLEMENT"); 2994 2995 /** 2996 * Constant for the "Marchen" Unicode 2997 * character block. 2998 * @since 11 2999 */ 3000 public static final UnicodeBlock MARCHEN = 3001 new UnicodeBlock("MARCHEN"); 3002 3003 /** 3004 * Constant for the "Ideographic Symbols and Punctuation" Unicode 3005 * character block. 3006 * @since 11 3007 */ 3008 public static final UnicodeBlock IDEOGRAPHIC_SYMBOLS_AND_PUNCTUATION = 3009 new UnicodeBlock("IDEOGRAPHIC_SYMBOLS_AND_PUNCTUATION", 3010 "IDEOGRAPHIC SYMBOLS AND PUNCTUATION", 3011 "IDEOGRAPHICSYMBOLSANDPUNCTUATION"); 3012 3013 /** 3014 * Constant for the "Tangut" Unicode 3015 * character block. 3016 * @since 11 3017 */ 3018 public static final UnicodeBlock TANGUT = 3019 new UnicodeBlock("TANGUT"); 3020 3021 /** 3022 * Constant for the "Tangut Components" Unicode 3023 * character block. 3024 * @since 11 3025 */ 3026 public static final UnicodeBlock TANGUT_COMPONENTS = 3027 new UnicodeBlock("TANGUT_COMPONENTS", 3028 "TANGUT COMPONENTS", 3029 "TANGUTCOMPONENTS"); 3030 3031 /** 3032 * Constant for the "Kana Extended-A" Unicode 3033 * character block. 3034 * @since 11 3035 */ 3036 public static final UnicodeBlock KANA_EXTENDED_A = 3037 new UnicodeBlock("KANA_EXTENDED_A", 3038 "KANA EXTENDED-A", 3039 "KANAEXTENDED-A"); 3040 /** 3041 * Constant for the "Glagolitic Supplement" Unicode 3042 * character block. 3043 * @since 11 3044 */ 3045 public static final UnicodeBlock GLAGOLITIC_SUPPLEMENT = 3046 new UnicodeBlock("GLAGOLITIC_SUPPLEMENT", 3047 "GLAGOLITIC SUPPLEMENT", 3048 "GLAGOLITICSUPPLEMENT"); 3049 /** 3050 * Constant for the "Adlam" Unicode 3051 * character block. 3052 * @since 11 3053 */ 3054 public static final UnicodeBlock ADLAM = 3055 new UnicodeBlock("ADLAM"); 3056 3057 /** 3058 * Constant for the "Masaram Gondi" Unicode 3059 * character block. 3060 * @since 11 3061 */ 3062 public static final UnicodeBlock MASARAM_GONDI = 3063 new UnicodeBlock("MASARAM_GONDI", 3064 "MASARAM GONDI", 3065 "MASARAMGONDI"); 3066 3067 /** 3068 * Constant for the "Zanabazar Square" Unicode 3069 * character block. 3070 * @since 11 3071 */ 3072 public static final UnicodeBlock ZANABAZAR_SQUARE = 3073 new UnicodeBlock("ZANABAZAR_SQUARE", 3074 "ZANABAZAR SQUARE", 3075 "ZANABAZARSQUARE"); 3076 3077 /** 3078 * Constant for the "Nushu" Unicode 3079 * character block. 3080 * @since 11 3081 */ 3082 public static final UnicodeBlock NUSHU = 3083 new UnicodeBlock("NUSHU"); 3084 3085 /** 3086 * Constant for the "Soyombo" Unicode 3087 * character block. 3088 * @since 11 3089 */ 3090 public static final UnicodeBlock SOYOMBO = 3091 new UnicodeBlock("SOYOMBO"); 3092 3093 /** 3094 * Constant for the "Bhaiksuki" Unicode 3095 * character block. 3096 * @since 11 3097 */ 3098 public static final UnicodeBlock BHAIKSUKI = 3099 new UnicodeBlock("BHAIKSUKI"); 3100 3101 /** 3102 * Constant for the "CJK Unified Ideographs Extension F" Unicode 3103 * character block. 3104 * @since 11 3105 */ 3106 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_F = 3107 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_F", 3108 "CJK UNIFIED IDEOGRAPHS EXTENSION F", 3109 "CJKUNIFIEDIDEOGRAPHSEXTENSIONF"); 3110 /** 3111 * Constant for the "Georgian Extended" Unicode 3112 * character block. 3113 * @since 12 3114 */ 3115 public static final UnicodeBlock GEORGIAN_EXTENDED = 3116 new UnicodeBlock("GEORGIAN_EXTENDED", 3117 "GEORGIAN EXTENDED", 3118 "GEORGIANEXTENDED"); 3119 3120 /** 3121 * Constant for the "Hanifi Rohingya" Unicode 3122 * character block. 3123 * @since 12 3124 */ 3125 public static final UnicodeBlock HANIFI_ROHINGYA = 3126 new UnicodeBlock("HANIFI_ROHINGYA", 3127 "HANIFI ROHINGYA", 3128 "HANIFIROHINGYA"); 3129 3130 /** 3131 * Constant for the "Old Sogdian" Unicode 3132 * character block. 3133 * @since 12 3134 */ 3135 public static final UnicodeBlock OLD_SOGDIAN = 3136 new UnicodeBlock("OLD_SOGDIAN", 3137 "OLD SOGDIAN", 3138 "OLDSOGDIAN"); 3139 3140 /** 3141 * Constant for the "Sogdian" Unicode 3142 * character block. 3143 * @since 12 3144 */ 3145 public static final UnicodeBlock SOGDIAN = 3146 new UnicodeBlock("SOGDIAN"); 3147 3148 /** 3149 * Constant for the "Dogra" Unicode 3150 * character block. 3151 * @since 12 3152 */ 3153 public static final UnicodeBlock DOGRA = 3154 new UnicodeBlock("DOGRA"); 3155 3156 /** 3157 * Constant for the "Gunjala Gondi" Unicode 3158 * character block. 3159 * @since 12 3160 */ 3161 public static final UnicodeBlock GUNJALA_GONDI = 3162 new UnicodeBlock("GUNJALA_GONDI", 3163 "GUNJALA GONDI", 3164 "GUNJALAGONDI"); 3165 3166 /** 3167 * Constant for the "Makasar" Unicode 3168 * character block. 3169 * @since 12 3170 */ 3171 public static final UnicodeBlock MAKASAR = 3172 new UnicodeBlock("MAKASAR"); 3173 3174 /** 3175 * Constant for the "Medefaidrin" Unicode 3176 * character block. 3177 * @since 12 3178 */ 3179 public static final UnicodeBlock MEDEFAIDRIN = 3180 new UnicodeBlock("MEDEFAIDRIN"); 3181 3182 /** 3183 * Constant for the "Mayan Numerals" Unicode 3184 * character block. 3185 * @since 12 3186 */ 3187 public static final UnicodeBlock MAYAN_NUMERALS = 3188 new UnicodeBlock("MAYAN_NUMERALS", 3189 "MAYAN NUMERALS", 3190 "MAYANNUMERALS"); 3191 3192 /** 3193 * Constant for the "Indic Siyaq Numbers" Unicode 3194 * character block. 3195 * @since 12 3196 */ 3197 public static final UnicodeBlock INDIC_SIYAQ_NUMBERS = 3198 new UnicodeBlock("INDIC_SIYAQ_NUMBERS", 3199 "INDIC SIYAQ NUMBERS", 3200 "INDICSIYAQNUMBERS"); 3201 3202 /** 3203 * Constant for the "Chess Symbols" Unicode 3204 * character block. 3205 * @since 12 3206 */ 3207 public static final UnicodeBlock CHESS_SYMBOLS = 3208 new UnicodeBlock("CHESS_SYMBOLS", 3209 "CHESS SYMBOLS", 3210 "CHESSSYMBOLS"); 3211 3212 3213 private static final int blockStarts[] = { 3214 0x0000, // 0000..007F; Basic Latin 3215 0x0080, // 0080..00FF; Latin-1 Supplement 3216 0x0100, // 0100..017F; Latin Extended-A 3217 0x0180, // 0180..024F; Latin Extended-B 3218 0x0250, // 0250..02AF; IPA Extensions 3219 0x02B0, // 02B0..02FF; Spacing Modifier Letters 3220 0x0300, // 0300..036F; Combining Diacritical Marks 3221 0x0370, // 0370..03FF; Greek and Coptic 3222 0x0400, // 0400..04FF; Cyrillic 3223 0x0500, // 0500..052F; Cyrillic Supplement 3224 0x0530, // 0530..058F; Armenian 3225 0x0590, // 0590..05FF; Hebrew 3226 0x0600, // 0600..06FF; Arabic 3227 0x0700, // 0700..074F; Syriac 3228 0x0750, // 0750..077F; Arabic Supplement 3229 0x0780, // 0780..07BF; Thaana 3230 0x07C0, // 07C0..07FF; NKo 3231 0x0800, // 0800..083F; Samaritan 3232 0x0840, // 0840..085F; Mandaic 3233 0x0860, // 0860..086F; Syriac Supplement 3234 0x0870, // unassigned 3235 0x08A0, // 08A0..08FF; Arabic Extended-A 3236 0x0900, // 0900..097F; Devanagari 3237 0x0980, // 0980..09FF; Bengali 3238 0x0A00, // 0A00..0A7F; Gurmukhi 3239 0x0A80, // 0A80..0AFF; Gujarati 3240 0x0B00, // 0B00..0B7F; Oriya 3241 0x0B80, // 0B80..0BFF; Tamil 3242 0x0C00, // 0C00..0C7F; Telugu 3243 0x0C80, // 0C80..0CFF; Kannada 3244 0x0D00, // 0D00..0D7F; Malayalam 3245 0x0D80, // 0D80..0DFF; Sinhala 3246 0x0E00, // 0E00..0E7F; Thai 3247 0x0E80, // 0E80..0EFF; Lao 3248 0x0F00, // 0F00..0FFF; Tibetan 3249 0x1000, // 1000..109F; Myanmar 3250 0x10A0, // 10A0..10FF; Georgian 3251 0x1100, // 1100..11FF; Hangul Jamo 3252 0x1200, // 1200..137F; Ethiopic 3253 0x1380, // 1380..139F; Ethiopic Supplement 3254 0x13A0, // 13A0..13FF; Cherokee 3255 0x1400, // 1400..167F; Unified Canadian Aboriginal Syllabics 3256 0x1680, // 1680..169F; Ogham 3257 0x16A0, // 16A0..16FF; Runic 3258 0x1700, // 1700..171F; Tagalog 3259 0x1720, // 1720..173F; Hanunoo 3260 0x1740, // 1740..175F; Buhid 3261 0x1760, // 1760..177F; Tagbanwa 3262 0x1780, // 1780..17FF; Khmer 3263 0x1800, // 1800..18AF; Mongolian 3264 0x18B0, // 18B0..18FF; Unified Canadian Aboriginal Syllabics Extended 3265 0x1900, // 1900..194F; Limbu 3266 0x1950, // 1950..197F; Tai Le 3267 0x1980, // 1980..19DF; New Tai Lue 3268 0x19E0, // 19E0..19FF; Khmer Symbols 3269 0x1A00, // 1A00..1A1F; Buginese 3270 0x1A20, // 1A20..1AAF; Tai Tham 3271 0x1AB0, // 1AB0..1AFF; Combining Diacritical Marks Extended 3272 0x1B00, // 1B00..1B7F; Balinese 3273 0x1B80, // 1B80..1BBF; Sundanese 3274 0x1BC0, // 1BC0..1BFF; Batak 3275 0x1C00, // 1C00..1C4F; Lepcha 3276 0x1C50, // 1C50..1C7F; Ol Chiki 3277 0x1C80, // 1C80..1C8F; Cyrillic Extended-C 3278 0x1C90, // 1C90..1CBF; Georgian Extended 3279 0x1CC0, // 1CC0..1CCF; Sundanese Supplement 3280 0x1CD0, // 1CD0..1CFF; Vedic Extensions 3281 0x1D00, // 1D00..1D7F; Phonetic Extensions 3282 0x1D80, // 1D80..1DBF; Phonetic Extensions Supplement 3283 0x1DC0, // 1DC0..1DFF; Combining Diacritical Marks Supplement 3284 0x1E00, // 1E00..1EFF; Latin Extended Additional 3285 0x1F00, // 1F00..1FFF; Greek Extended 3286 0x2000, // 2000..206F; General Punctuation 3287 0x2070, // 2070..209F; Superscripts and Subscripts 3288 0x20A0, // 20A0..20CF; Currency Symbols 3289 0x20D0, // 20D0..20FF; Combining Diacritical Marks for Symbols 3290 0x2100, // 2100..214F; Letterlike Symbols 3291 0x2150, // 2150..218F; Number Forms 3292 0x2190, // 2190..21FF; Arrows 3293 0x2200, // 2200..22FF; Mathematical Operators 3294 0x2300, // 2300..23FF; Miscellaneous Technical 3295 0x2400, // 2400..243F; Control Pictures 3296 0x2440, // 2440..245F; Optical Character Recognition 3297 0x2460, // 2460..24FF; Enclosed Alphanumerics 3298 0x2500, // 2500..257F; Box Drawing 3299 0x2580, // 2580..259F; Block Elements 3300 0x25A0, // 25A0..25FF; Geometric Shapes 3301 0x2600, // 2600..26FF; Miscellaneous Symbols 3302 0x2700, // 2700..27BF; Dingbats 3303 0x27C0, // 27C0..27EF; Miscellaneous Mathematical Symbols-A 3304 0x27F0, // 27F0..27FF; Supplemental Arrows-A 3305 0x2800, // 2800..28FF; Braille Patterns 3306 0x2900, // 2900..297F; Supplemental Arrows-B 3307 0x2980, // 2980..29FF; Miscellaneous Mathematical Symbols-B 3308 0x2A00, // 2A00..2AFF; Supplemental Mathematical Operators 3309 0x2B00, // 2B00..2BFF; Miscellaneous Symbols and Arrows 3310 0x2C00, // 2C00..2C5F; Glagolitic 3311 0x2C60, // 2C60..2C7F; Latin Extended-C 3312 0x2C80, // 2C80..2CFF; Coptic 3313 0x2D00, // 2D00..2D2F; Georgian Supplement 3314 0x2D30, // 2D30..2D7F; Tifinagh 3315 0x2D80, // 2D80..2DDF; Ethiopic Extended 3316 0x2DE0, // 2DE0..2DFF; Cyrillic Extended-A 3317 0x2E00, // 2E00..2E7F; Supplemental Punctuation 3318 0x2E80, // 2E80..2EFF; CJK Radicals Supplement 3319 0x2F00, // 2F00..2FDF; Kangxi Radicals 3320 0x2FE0, // unassigned 3321 0x2FF0, // 2FF0..2FFF; Ideographic Description Characters 3322 0x3000, // 3000..303F; CJK Symbols and Punctuation 3323 0x3040, // 3040..309F; Hiragana 3324 0x30A0, // 30A0..30FF; Katakana 3325 0x3100, // 3100..312F; Bopomofo 3326 0x3130, // 3130..318F; Hangul Compatibility Jamo 3327 0x3190, // 3190..319F; Kanbun 3328 0x31A0, // 31A0..31BF; Bopomofo Extended 3329 0x31C0, // 31C0..31EF; CJK Strokes 3330 0x31F0, // 31F0..31FF; Katakana Phonetic Extensions 3331 0x3200, // 3200..32FF; Enclosed CJK Letters and Months 3332 0x3300, // 3300..33FF; CJK Compatibility 3333 0x3400, // 3400..4DBF; CJK Unified Ideographs Extension A 3334 0x4DC0, // 4DC0..4DFF; Yijing Hexagram Symbols 3335 0x4E00, // 4E00..9FFF; CJK Unified Ideographs 3336 0xA000, // A000..A48F; Yi Syllables 3337 0xA490, // A490..A4CF; Yi Radicals 3338 0xA4D0, // A4D0..A4FF; Lisu 3339 0xA500, // A500..A63F; Vai 3340 0xA640, // A640..A69F; Cyrillic Extended-B 3341 0xA6A0, // A6A0..A6FF; Bamum 3342 0xA700, // A700..A71F; Modifier Tone Letters 3343 0xA720, // A720..A7FF; Latin Extended-D 3344 0xA800, // A800..A82F; Syloti Nagri 3345 0xA830, // A830..A83F; Common Indic Number Forms 3346 0xA840, // A840..A87F; Phags-pa 3347 0xA880, // A880..A8DF; Saurashtra 3348 0xA8E0, // A8E0..A8FF; Devanagari Extended 3349 0xA900, // A900..A92F; Kayah Li 3350 0xA930, // A930..A95F; Rejang 3351 0xA960, // A960..A97F; Hangul Jamo Extended-A 3352 0xA980, // A980..A9DF; Javanese 3353 0xA9E0, // A9E0..A9FF; Myanmar Extended-B 3354 0xAA00, // AA00..AA5F; Cham 3355 0xAA60, // AA60..AA7F; Myanmar Extended-A 3356 0xAA80, // AA80..AADF; Tai Viet 3357 0xAAE0, // AAE0..AAFF; Meetei Mayek Extensions 3358 0xAB00, // AB00..AB2F; Ethiopic Extended-A 3359 0xAB30, // AB30..AB6F; Latin Extended-E 3360 0xAB70, // AB70..ABBF; Cherokee Supplement 3361 0xABC0, // ABC0..ABFF; Meetei Mayek 3362 0xAC00, // AC00..D7AF; Hangul Syllables 3363 0xD7B0, // D7B0..D7FF; Hangul Jamo Extended-B 3364 0xD800, // D800..DB7F; High Surrogates 3365 0xDB80, // DB80..DBFF; High Private Use Surrogates 3366 0xDC00, // DC00..DFFF; Low Surrogates 3367 0xE000, // E000..F8FF; Private Use Area 3368 0xF900, // F900..FAFF; CJK Compatibility Ideographs 3369 0xFB00, // FB00..FB4F; Alphabetic Presentation Forms 3370 0xFB50, // FB50..FDFF; Arabic Presentation Forms-A 3371 0xFE00, // FE00..FE0F; Variation Selectors 3372 0xFE10, // FE10..FE1F; Vertical Forms 3373 0xFE20, // FE20..FE2F; Combining Half Marks 3374 0xFE30, // FE30..FE4F; CJK Compatibility Forms 3375 0xFE50, // FE50..FE6F; Small Form Variants 3376 0xFE70, // FE70..FEFF; Arabic Presentation Forms-B 3377 0xFF00, // FF00..FFEF; Halfwidth and Fullwidth Forms 3378 0xFFF0, // FFF0..FFFF; Specials 3379 0x10000, // 10000..1007F; Linear B Syllabary 3380 0x10080, // 10080..100FF; Linear B Ideograms 3381 0x10100, // 10100..1013F; Aegean Numbers 3382 0x10140, // 10140..1018F; Ancient Greek Numbers 3383 0x10190, // 10190..101CF; Ancient Symbols 3384 0x101D0, // 101D0..101FF; Phaistos Disc 3385 0x10200, // unassigned 3386 0x10280, // 10280..1029F; Lycian 3387 0x102A0, // 102A0..102DF; Carian 3388 0x102E0, // 102E0..102FF; Coptic Epact Numbers 3389 0x10300, // 10300..1032F; Old Italic 3390 0x10330, // 10330..1034F; Gothic 3391 0x10350, // 10350..1037F; Old Permic 3392 0x10380, // 10380..1039F; Ugaritic 3393 0x103A0, // 103A0..103DF; Old Persian 3394 0x103E0, // unassigned 3395 0x10400, // 10400..1044F; Deseret 3396 0x10450, // 10450..1047F; Shavian 3397 0x10480, // 10480..104AF; Osmanya 3398 0x104B0, // 104B0..104FF; Osage 3399 0x10500, // 10500..1052F; Elbasan 3400 0x10530, // 10530..1056F; Caucasian Albanian 3401 0x10570, // unassigned 3402 0x10600, // 10600..1077F; Linear A 3403 0x10780, // unassigned 3404 0x10800, // 10800..1083F; Cypriot Syllabary 3405 0x10840, // 10840..1085F; Imperial Aramaic 3406 0x10860, // 10860..1087F; Palmyrene 3407 0x10880, // 10880..108AF; Nabataean 3408 0x108B0, // unassigned 3409 0x108E0, // 108E0..108FF; Hatran 3410 0x10900, // 10900..1091F; Phoenician 3411 0x10920, // 10920..1093F; Lydian 3412 0x10940, // unassigned 3413 0x10980, // 10980..1099F; Meroitic Hieroglyphs 3414 0x109A0, // 109A0..109FF; Meroitic Cursive 3415 0x10A00, // 10A00..10A5F; Kharoshthi 3416 0x10A60, // 10A60..10A7F; Old South Arabian 3417 0x10A80, // 10A80..10A9F; Old North Arabian 3418 0x10AA0, // unassigned 3419 0x10AC0, // 10AC0..10AFF; Manichaean 3420 0x10B00, // 10B00..10B3F; Avestan 3421 0x10B40, // 10B40..10B5F; Inscriptional Parthian 3422 0x10B60, // 10B60..10B7F; Inscriptional Pahlavi 3423 0x10B80, // 10B80..10BAF; Psalter Pahlavi 3424 0x10BB0, // unassigned 3425 0x10C00, // 10C00..10C4F; Old Turkic 3426 0x10C50, // unassigned 3427 0x10C80, // 10C80..10CFF; Old Hungarian 3428 0x10D00, // 10D00..10D3F; Hanifi Rohingya 3429 0x10D40, // unassigned 3430 0x10E60, // 10E60..10E7F; Rumi Numeral Symbols 3431 0x10E80, // unassigned 3432 0x10F00, // 10F00..10F2F; Old Sogdian 3433 0x10F30, // 10F30..10F6F; Sogdian 3434 0x10F70, // unassigned 3435 0x11000, // 11000..1107F; Brahmi 3436 0x11080, // 11080..110CF; Kaithi 3437 0x110D0, // 110D0..110FF; Sora Sompeng 3438 0x11100, // 11100..1114F; Chakma 3439 0x11150, // 11150..1117F; Mahajani 3440 0x11180, // 11180..111DF; Sharada 3441 0x111E0, // 111E0..111FF; Sinhala Archaic Numbers 3442 0x11200, // 11200..1124F; Khojki 3443 0x11250, // unassigned 3444 0x11280, // 11280..112AF; Multani 3445 0x112B0, // 112B0..112FF; Khudawadi 3446 0x11300, // 11300..1137F; Grantha 3447 0x11380, // unassigned 3448 0x11400, // 11400..1147F; Newa 3449 0x11480, // 11480..114DF; Tirhuta 3450 0x114E0, // unassigned 3451 0x11580, // 11580..115FF; Siddham 3452 0x11600, // 11600..1165F; Modi 3453 0x11660, // 11660..1167F; Mongolian Supplement 3454 0x11680, // 11680..116CF; Takri 3455 0x116D0, // unassigned 3456 0x11700, // 11700..1173F; Ahom 3457 0x11740, // unassigned 3458 0x11800, // 11800..1184F; Dogra 3459 0x11850, // unassigned 3460 0x118A0, // 118A0..118FF; Warang Citi 3461 0x11900, // unassigned 3462 0x11A00, // 11A00..11A4F; Zanabazar Square 3463 0x11A50, // 11A50..11AAF; Soyombo 3464 0x11AB0, // unassigned 3465 0x11AC0, // 11AC0..11AFF; Pau Cin Hau 3466 0x11B00, // unassigned 3467 0x11C00, // 11C00..11C6F; Bhaiksuki 3468 0x11C70, // 11C70..11CBF; Marchen 3469 0x11CC0, // unassigned 3470 0x11D00, // 11D00..11D5F; Masaram Gondi 3471 0x11D60, // 11D60..11DAF; Gunjala Gondi 3472 0x11DB0, // unassigned 3473 0x11EE0, // 11EE0..11EFF; Makasar 3474 0x11F00, // unassigned 3475 0x12000, // 12000..123FF; Cuneiform 3476 0x12400, // 12400..1247F; Cuneiform Numbers and Punctuation 3477 0x12480, // 12480..1254F; Early Dynastic Cuneiform 3478 0x12550, // unassigned 3479 0x13000, // 13000..1342F; Egyptian Hieroglyphs 3480 0x13430, // unassigned 3481 0x14400, // 14400..1467F; Anatolian Hieroglyphs 3482 0x14680, // unassigned 3483 0x16800, // 16800..16A3F; Bamum Supplement 3484 0x16A40, // 16A40..16A6F; Mro 3485 0x16A70, // unassigned 3486 0x16AD0, // 16AD0..16AFF; Bassa Vah 3487 0x16B00, // 16B00..16B8F; Pahawh Hmong 3488 0x16B90, // unassigned 3489 0x16E40, // 16E40..16E9F; Medefaidrin 3490 0x16EA0, // unassigned 3491 0x16F00, // 16F00..16F9F; Miao 3492 0x16FA0, // unassigned 3493 0x16FE0, // 16FE0..16FFF; Ideographic Symbols and Punctuation 3494 0x17000, // 17000..187FF; Tangut 3495 0x18800, // 18800..18AFF; Tangut Components 3496 0x18B00, // unassigned 3497 0x1B000, // 1B000..1B0FF; Kana Supplement 3498 0x1B100, // 1B100..1B12F; Kana Extended-A 3499 0x1B130, // unassigned 3500 0x1B170, // 1B170..1B2FF; Nushu 3501 0x1B300, // unassigned 3502 0x1BC00, // 1BC00..1BC9F; Duployan 3503 0x1BCA0, // 1BCA0..1BCAF; Shorthand Format Controls 3504 0x1BCB0, // unassigned 3505 0x1D000, // 1D000..1D0FF; Byzantine Musical Symbols 3506 0x1D100, // 1D100..1D1FF; Musical Symbols 3507 0x1D200, // 1D200..1D24F; Ancient Greek Musical Notation 3508 0x1D250, // unassigned 3509 0x1D2E0, // 1D2E0..1D2FF; Mayan Numerals 3510 0x1D300, // 1D300..1D35F; Tai Xuan Jing Symbols 3511 0x1D360, // 1D360..1D37F; Counting Rod Numerals 3512 0x1D380, // unassigned 3513 0x1D400, // 1D400..1D7FF; Mathematical Alphanumeric Symbols 3514 0x1D800, // 1D800..1DAAF; Sutton SignWriting 3515 0x1DAB0, // unassigned 3516 0x1E000, // 1E000..1E02F; Glagolitic Supplement 3517 0x1E030, // unassigned 3518 0x1E800, // 1E800..1E8DF; Mende Kikakui 3519 0x1E8E0, // unassigned 3520 0x1E900, // 1E900..1E95F; Adlam 3521 0x1E960, // unassigned 3522 0x1EC70, // 1EC70..1ECBF; Indic Siyaq Numbers 3523 0x1ECC0, // unassigned 3524 0x1EE00, // 1EE00..1EEFF; Arabic Mathematical Alphabetic Symbols 3525 0x1EF00, // unassigned 3526 0x1F000, // 1F000..1F02F; Mahjong Tiles 3527 0x1F030, // 1F030..1F09F; Domino Tiles 3528 0x1F0A0, // 1F0A0..1F0FF; Playing Cards 3529 0x1F100, // 1F100..1F1FF; Enclosed Alphanumeric Supplement 3530 0x1F200, // 1F200..1F2FF; Enclosed Ideographic Supplement 3531 0x1F300, // 1F300..1F5FF; Miscellaneous Symbols and Pictographs 3532 0x1F600, // 1F600..1F64F; Emoticons 3533 0x1F650, // 1F650..1F67F; Ornamental Dingbats 3534 0x1F680, // 1F680..1F6FF; Transport and Map Symbols 3535 0x1F700, // 1F700..1F77F; Alchemical Symbols 3536 0x1F780, // 1F780..1F7FF; Geometric Shapes Extended 3537 0x1F800, // 1F800..1F8FF; Supplemental Arrows-C 3538 0x1F900, // 1F900..1F9FF; Supplemental Symbols and Pictographs 3539 0x1FA00, // 1FA00..1FA6F; Chess Symbols 3540 0x1FA70, // unassigned 3541 0x20000, // 20000..2A6DF; CJK Unified Ideographs Extension B 3542 0x2A6E0, // unassigned 3543 0x2A700, // 2A700..2B73F; CJK Unified Ideographs Extension C 3544 0x2B740, // 2B740..2B81F; CJK Unified Ideographs Extension D 3545 0x2B820, // 2B820..2CEAF; CJK Unified Ideographs Extension E 3546 0x2CEB0, // 2CEB0..2EBEF; CJK Unified Ideographs Extension F 3547 0x2EBF0, // unassigned 3548 0x2F800, // 2F800..2FA1F; CJK Compatibility Ideographs Supplement 3549 0x2FA20, // unassigned 3550 0xE0000, // E0000..E007F; Tags 3551 0xE0080, // unassigned 3552 0xE0100, // E0100..E01EF; Variation Selectors Supplement 3553 0xE01F0, // unassigned 3554 0xF0000, // F0000..FFFFF; Supplementary Private Use Area-A 3555 0x100000 // 100000..10FFFF; Supplementary Private Use Area-B 3556 }; 3557 3558 private static final UnicodeBlock[] blocks = { 3559 BASIC_LATIN, 3560 LATIN_1_SUPPLEMENT, 3561 LATIN_EXTENDED_A, 3562 LATIN_EXTENDED_B, 3563 IPA_EXTENSIONS, 3564 SPACING_MODIFIER_LETTERS, 3565 COMBINING_DIACRITICAL_MARKS, 3566 GREEK, 3567 CYRILLIC, 3568 CYRILLIC_SUPPLEMENTARY, 3569 ARMENIAN, 3570 HEBREW, 3571 ARABIC, 3572 SYRIAC, 3573 ARABIC_SUPPLEMENT, 3574 THAANA, 3575 NKO, 3576 SAMARITAN, 3577 MANDAIC, 3578 SYRIAC_SUPPLEMENT, 3579 null, 3580 ARABIC_EXTENDED_A, 3581 DEVANAGARI, 3582 BENGALI, 3583 GURMUKHI, 3584 GUJARATI, 3585 ORIYA, 3586 TAMIL, 3587 TELUGU, 3588 KANNADA, 3589 MALAYALAM, 3590 SINHALA, 3591 THAI, 3592 LAO, 3593 TIBETAN, 3594 MYANMAR, 3595 GEORGIAN, 3596 HANGUL_JAMO, 3597 ETHIOPIC, 3598 ETHIOPIC_SUPPLEMENT, 3599 CHEROKEE, 3600 UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS, 3601 OGHAM, 3602 RUNIC, 3603 TAGALOG, 3604 HANUNOO, 3605 BUHID, 3606 TAGBANWA, 3607 KHMER, 3608 MONGOLIAN, 3609 UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED, 3610 LIMBU, 3611 TAI_LE, 3612 NEW_TAI_LUE, 3613 KHMER_SYMBOLS, 3614 BUGINESE, 3615 TAI_THAM, 3616 COMBINING_DIACRITICAL_MARKS_EXTENDED, 3617 BALINESE, 3618 SUNDANESE, 3619 BATAK, 3620 LEPCHA, 3621 OL_CHIKI, 3622 CYRILLIC_EXTENDED_C, 3623 GEORGIAN_EXTENDED, 3624 SUNDANESE_SUPPLEMENT, 3625 VEDIC_EXTENSIONS, 3626 PHONETIC_EXTENSIONS, 3627 PHONETIC_EXTENSIONS_SUPPLEMENT, 3628 COMBINING_DIACRITICAL_MARKS_SUPPLEMENT, 3629 LATIN_EXTENDED_ADDITIONAL, 3630 GREEK_EXTENDED, 3631 GENERAL_PUNCTUATION, 3632 SUPERSCRIPTS_AND_SUBSCRIPTS, 3633 CURRENCY_SYMBOLS, 3634 COMBINING_MARKS_FOR_SYMBOLS, 3635 LETTERLIKE_SYMBOLS, 3636 NUMBER_FORMS, 3637 ARROWS, 3638 MATHEMATICAL_OPERATORS, 3639 MISCELLANEOUS_TECHNICAL, 3640 CONTROL_PICTURES, 3641 OPTICAL_CHARACTER_RECOGNITION, 3642 ENCLOSED_ALPHANUMERICS, 3643 BOX_DRAWING, 3644 BLOCK_ELEMENTS, 3645 GEOMETRIC_SHAPES, 3646 MISCELLANEOUS_SYMBOLS, 3647 DINGBATS, 3648 MISCELLANEOUS_MATHEMATICAL_SYMBOLS_A, 3649 SUPPLEMENTAL_ARROWS_A, 3650 BRAILLE_PATTERNS, 3651 SUPPLEMENTAL_ARROWS_B, 3652 MISCELLANEOUS_MATHEMATICAL_SYMBOLS_B, 3653 SUPPLEMENTAL_MATHEMATICAL_OPERATORS, 3654 MISCELLANEOUS_SYMBOLS_AND_ARROWS, 3655 GLAGOLITIC, 3656 LATIN_EXTENDED_C, 3657 COPTIC, 3658 GEORGIAN_SUPPLEMENT, 3659 TIFINAGH, 3660 ETHIOPIC_EXTENDED, 3661 CYRILLIC_EXTENDED_A, 3662 SUPPLEMENTAL_PUNCTUATION, 3663 CJK_RADICALS_SUPPLEMENT, 3664 KANGXI_RADICALS, 3665 null, 3666 IDEOGRAPHIC_DESCRIPTION_CHARACTERS, 3667 CJK_SYMBOLS_AND_PUNCTUATION, 3668 HIRAGANA, 3669 KATAKANA, 3670 BOPOMOFO, 3671 HANGUL_COMPATIBILITY_JAMO, 3672 KANBUN, 3673 BOPOMOFO_EXTENDED, 3674 CJK_STROKES, 3675 KATAKANA_PHONETIC_EXTENSIONS, 3676 ENCLOSED_CJK_LETTERS_AND_MONTHS, 3677 CJK_COMPATIBILITY, 3678 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A, 3679 YIJING_HEXAGRAM_SYMBOLS, 3680 CJK_UNIFIED_IDEOGRAPHS, 3681 YI_SYLLABLES, 3682 YI_RADICALS, 3683 LISU, 3684 VAI, 3685 CYRILLIC_EXTENDED_B, 3686 BAMUM, 3687 MODIFIER_TONE_LETTERS, 3688 LATIN_EXTENDED_D, 3689 SYLOTI_NAGRI, 3690 COMMON_INDIC_NUMBER_FORMS, 3691 PHAGS_PA, 3692 SAURASHTRA, 3693 DEVANAGARI_EXTENDED, 3694 KAYAH_LI, 3695 REJANG, 3696 HANGUL_JAMO_EXTENDED_A, 3697 JAVANESE, 3698 MYANMAR_EXTENDED_B, 3699 CHAM, 3700 MYANMAR_EXTENDED_A, 3701 TAI_VIET, 3702 MEETEI_MAYEK_EXTENSIONS, 3703 ETHIOPIC_EXTENDED_A, 3704 LATIN_EXTENDED_E, 3705 CHEROKEE_SUPPLEMENT, 3706 MEETEI_MAYEK, 3707 HANGUL_SYLLABLES, 3708 HANGUL_JAMO_EXTENDED_B, 3709 HIGH_SURROGATES, 3710 HIGH_PRIVATE_USE_SURROGATES, 3711 LOW_SURROGATES, 3712 PRIVATE_USE_AREA, 3713 CJK_COMPATIBILITY_IDEOGRAPHS, 3714 ALPHABETIC_PRESENTATION_FORMS, 3715 ARABIC_PRESENTATION_FORMS_A, 3716 VARIATION_SELECTORS, 3717 VERTICAL_FORMS, 3718 COMBINING_HALF_MARKS, 3719 CJK_COMPATIBILITY_FORMS, 3720 SMALL_FORM_VARIANTS, 3721 ARABIC_PRESENTATION_FORMS_B, 3722 HALFWIDTH_AND_FULLWIDTH_FORMS, 3723 SPECIALS, 3724 LINEAR_B_SYLLABARY, 3725 LINEAR_B_IDEOGRAMS, 3726 AEGEAN_NUMBERS, 3727 ANCIENT_GREEK_NUMBERS, 3728 ANCIENT_SYMBOLS, 3729 PHAISTOS_DISC, 3730 null, 3731 LYCIAN, 3732 CARIAN, 3733 COPTIC_EPACT_NUMBERS, 3734 OLD_ITALIC, 3735 GOTHIC, 3736 OLD_PERMIC, 3737 UGARITIC, 3738 OLD_PERSIAN, 3739 null, 3740 DESERET, 3741 SHAVIAN, 3742 OSMANYA, 3743 OSAGE, 3744 ELBASAN, 3745 CAUCASIAN_ALBANIAN, 3746 null, 3747 LINEAR_A, 3748 null, 3749 CYPRIOT_SYLLABARY, 3750 IMPERIAL_ARAMAIC, 3751 PALMYRENE, 3752 NABATAEAN, 3753 null, 3754 HATRAN, 3755 PHOENICIAN, 3756 LYDIAN, 3757 null, 3758 MEROITIC_HIEROGLYPHS, 3759 MEROITIC_CURSIVE, 3760 KHAROSHTHI, 3761 OLD_SOUTH_ARABIAN, 3762 OLD_NORTH_ARABIAN, 3763 null, 3764 MANICHAEAN, 3765 AVESTAN, 3766 INSCRIPTIONAL_PARTHIAN, 3767 INSCRIPTIONAL_PAHLAVI, 3768 PSALTER_PAHLAVI, 3769 null, 3770 OLD_TURKIC, 3771 null, 3772 OLD_HUNGARIAN, 3773 HANIFI_ROHINGYA, 3774 null, 3775 RUMI_NUMERAL_SYMBOLS, 3776 null, 3777 OLD_SOGDIAN, 3778 SOGDIAN, 3779 null, 3780 BRAHMI, 3781 KAITHI, 3782 SORA_SOMPENG, 3783 CHAKMA, 3784 MAHAJANI, 3785 SHARADA, 3786 SINHALA_ARCHAIC_NUMBERS, 3787 KHOJKI, 3788 null, 3789 MULTANI, 3790 KHUDAWADI, 3791 GRANTHA, 3792 null, 3793 NEWA, 3794 TIRHUTA, 3795 null, 3796 SIDDHAM, 3797 MODI, 3798 MONGOLIAN_SUPPLEMENT, 3799 TAKRI, 3800 null, 3801 AHOM, 3802 null, 3803 DOGRA, 3804 null, 3805 WARANG_CITI, 3806 null, 3807 ZANABAZAR_SQUARE, 3808 SOYOMBO, 3809 null, 3810 PAU_CIN_HAU, 3811 null, 3812 BHAIKSUKI, 3813 MARCHEN, 3814 null, 3815 MASARAM_GONDI, 3816 GUNJALA_GONDI, 3817 null, 3818 MAKASAR, 3819 null, 3820 CUNEIFORM, 3821 CUNEIFORM_NUMBERS_AND_PUNCTUATION, 3822 EARLY_DYNASTIC_CUNEIFORM, 3823 null, 3824 EGYPTIAN_HIEROGLYPHS, 3825 null, 3826 ANATOLIAN_HIEROGLYPHS, 3827 null, 3828 BAMUM_SUPPLEMENT, 3829 MRO, 3830 null, 3831 BASSA_VAH, 3832 PAHAWH_HMONG, 3833 null, 3834 MEDEFAIDRIN, 3835 null, 3836 MIAO, 3837 null, 3838 IDEOGRAPHIC_SYMBOLS_AND_PUNCTUATION, 3839 TANGUT, 3840 TANGUT_COMPONENTS, 3841 null, 3842 KANA_SUPPLEMENT, 3843 KANA_EXTENDED_A, 3844 null, 3845 NUSHU, 3846 null, 3847 DUPLOYAN, 3848 SHORTHAND_FORMAT_CONTROLS, 3849 null, 3850 BYZANTINE_MUSICAL_SYMBOLS, 3851 MUSICAL_SYMBOLS, 3852 ANCIENT_GREEK_MUSICAL_NOTATION, 3853 null, 3854 MAYAN_NUMERALS, 3855 TAI_XUAN_JING_SYMBOLS, 3856 COUNTING_ROD_NUMERALS, 3857 null, 3858 MATHEMATICAL_ALPHANUMERIC_SYMBOLS, 3859 SUTTON_SIGNWRITING, 3860 null, 3861 GLAGOLITIC_SUPPLEMENT, 3862 null, 3863 MENDE_KIKAKUI, 3864 null, 3865 ADLAM, 3866 null, 3867 INDIC_SIYAQ_NUMBERS, 3868 null, 3869 ARABIC_MATHEMATICAL_ALPHABETIC_SYMBOLS, 3870 null, 3871 MAHJONG_TILES, 3872 DOMINO_TILES, 3873 PLAYING_CARDS, 3874 ENCLOSED_ALPHANUMERIC_SUPPLEMENT, 3875 ENCLOSED_IDEOGRAPHIC_SUPPLEMENT, 3876 MISCELLANEOUS_SYMBOLS_AND_PICTOGRAPHS, 3877 EMOTICONS, 3878 ORNAMENTAL_DINGBATS, 3879 TRANSPORT_AND_MAP_SYMBOLS, 3880 ALCHEMICAL_SYMBOLS, 3881 GEOMETRIC_SHAPES_EXTENDED, 3882 SUPPLEMENTAL_ARROWS_C, 3883 SUPPLEMENTAL_SYMBOLS_AND_PICTOGRAPHS, 3884 CHESS_SYMBOLS, 3885 null, 3886 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_B, 3887 null, 3888 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_C, 3889 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_D, 3890 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_E, 3891 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_F, 3892 null, 3893 CJK_COMPATIBILITY_IDEOGRAPHS_SUPPLEMENT, 3894 null, 3895 TAGS, 3896 null, 3897 VARIATION_SELECTORS_SUPPLEMENT, 3898 null, 3899 SUPPLEMENTARY_PRIVATE_USE_AREA_A, 3900 SUPPLEMENTARY_PRIVATE_USE_AREA_B 3901 }; 3902 3903 3904 /** 3905 * Returns the object representing the Unicode block containing the 3906 * given character, or {@code null} if the character is not a 3907 * member of a defined block. 3908 * 3909 * <p><b>Note:</b> This method cannot handle 3910 * <a href="Character.html#supplementary"> supplementary 3911 * characters</a>. To support all Unicode characters, including 3912 * supplementary characters, use the {@link #of(int)} method. 3913 * 3914 * @param c The character in question 3915 * @return The {@code UnicodeBlock} instance representing the 3916 * Unicode block of which this character is a member, or 3917 * {@code null} if the character is not a member of any 3918 * Unicode block 3919 */ 3920 public static UnicodeBlock of(char c) { 3921 return of((int)c); 3922 } 3923 3924 /** 3925 * Returns the object representing the Unicode block 3926 * containing the given character (Unicode code point), or 3927 * {@code null} if the character is not a member of a 3928 * defined block. 3929 * 3930 * @param codePoint the character (Unicode code point) in question. 3931 * @return The {@code UnicodeBlock} instance representing the 3932 * Unicode block of which this character is a member, or 3933 * {@code null} if the character is not a member of any 3934 * Unicode block 3935 * @throws IllegalArgumentException if the specified 3936 * {@code codePoint} is an invalid Unicode code point. 3937 * @see Character#isValidCodePoint(int) 3938 * @since 1.5 3939 */ 3940 public static UnicodeBlock of(int codePoint) { 3941 if (!isValidCodePoint(codePoint)) { 3942 throw new IllegalArgumentException( 3943 String.format("Not a valid Unicode code point: 0x%X", codePoint)); 3944 } 3945 3946 int top, bottom, current; 3947 bottom = 0; 3948 top = blockStarts.length; 3949 current = top/2; 3950 3951 // invariant: top > current >= bottom && codePoint >= unicodeBlockStarts[bottom] 3952 while (top - bottom > 1) { 3953 if (codePoint >= blockStarts[current]) { 3954 bottom = current; 3955 } else { 3956 top = current; 3957 } 3958 current = (top + bottom) / 2; 3959 } 3960 return blocks[current]; 3961 } 3962 3963 /** 3964 * Returns the UnicodeBlock with the given name. Block 3965 * names are determined by The Unicode Standard. The file 3966 * {@code Blocks-<version>.txt} defines blocks for a particular 3967 * version of the standard. The {@link Character} class specifies 3968 * the version of the standard that it supports. 3969 * <p> 3970 * This method accepts block names in the following forms: 3971 * <ol> 3972 * <li> Canonical block names as defined by the Unicode Standard. 3973 * For example, the standard defines a "Basic Latin" block. Therefore, this 3974 * method accepts "Basic Latin" as a valid block name. The documentation of 3975 * each UnicodeBlock provides the canonical name. 3976 * <li>Canonical block names with all spaces removed. For example, "BasicLatin" 3977 * is a valid block name for the "Basic Latin" block. 3978 * <li>The text representation of each constant UnicodeBlock identifier. 3979 * For example, this method will return the {@link #BASIC_LATIN} block if 3980 * provided with the "BASIC_LATIN" name. This form replaces all spaces and 3981 * hyphens in the canonical name with underscores. 3982 * </ol> 3983 * Finally, character case is ignored for all of the valid block name forms. 3984 * For example, "BASIC_LATIN" and "basic_latin" are both valid block names. 3985 * The en_US locale's case mapping rules are used to provide case-insensitive 3986 * string comparisons for block name validation. 3987 * <p> 3988 * If the Unicode Standard changes block names, both the previous and 3989 * current names will be accepted. 3990 * 3991 * @param blockName A {@code UnicodeBlock} name. 3992 * @return The {@code UnicodeBlock} instance identified 3993 * by {@code blockName} 3994 * @throws IllegalArgumentException if {@code blockName} is an 3995 * invalid name 3996 * @throws NullPointerException if {@code blockName} is null 3997 * @since 1.5 3998 */ 3999 public static final UnicodeBlock forName(String blockName) { 4000 UnicodeBlock block = map.get(blockName.toUpperCase(Locale.US)); 4001 if (block == null) { 4002 throw new IllegalArgumentException("Not a valid block name: " 4003 + blockName); 4004 } 4005 return block; 4006 } 4007 } 4008 4009 4010 /** 4011 * A family of character subsets representing the character scripts 4012 * defined in the <a href="http://www.unicode.org/reports/tr24/"> 4013 * <i>Unicode Standard Annex #24: Script Names</i></a>. Every Unicode 4014 * character is assigned to a single Unicode script, either a specific 4015 * script, such as {@link Character.UnicodeScript#LATIN Latin}, or 4016 * one of the following three special values, 4017 * {@link Character.UnicodeScript#INHERITED Inherited}, 4018 * {@link Character.UnicodeScript#COMMON Common} or 4019 * {@link Character.UnicodeScript#UNKNOWN Unknown}. 4020 * 4021 * @since 1.7 4022 */ 4023 public static enum UnicodeScript { 4024 /** 4025 * Unicode script "Common". 4026 */ 4027 COMMON, 4028 4029 /** 4030 * Unicode script "Latin". 4031 */ 4032 LATIN, 4033 4034 /** 4035 * Unicode script "Greek". 4036 */ 4037 GREEK, 4038 4039 /** 4040 * Unicode script "Cyrillic". 4041 */ 4042 CYRILLIC, 4043 4044 /** 4045 * Unicode script "Armenian". 4046 */ 4047 ARMENIAN, 4048 4049 /** 4050 * Unicode script "Hebrew". 4051 */ 4052 HEBREW, 4053 4054 /** 4055 * Unicode script "Arabic". 4056 */ 4057 ARABIC, 4058 4059 /** 4060 * Unicode script "Syriac". 4061 */ 4062 SYRIAC, 4063 4064 /** 4065 * Unicode script "Thaana". 4066 */ 4067 THAANA, 4068 4069 /** 4070 * Unicode script "Devanagari". 4071 */ 4072 DEVANAGARI, 4073 4074 /** 4075 * Unicode script "Bengali". 4076 */ 4077 BENGALI, 4078 4079 /** 4080 * Unicode script "Gurmukhi". 4081 */ 4082 GURMUKHI, 4083 4084 /** 4085 * Unicode script "Gujarati". 4086 */ 4087 GUJARATI, 4088 4089 /** 4090 * Unicode script "Oriya". 4091 */ 4092 ORIYA, 4093 4094 /** 4095 * Unicode script "Tamil". 4096 */ 4097 TAMIL, 4098 4099 /** 4100 * Unicode script "Telugu". 4101 */ 4102 TELUGU, 4103 4104 /** 4105 * Unicode script "Kannada". 4106 */ 4107 KANNADA, 4108 4109 /** 4110 * Unicode script "Malayalam". 4111 */ 4112 MALAYALAM, 4113 4114 /** 4115 * Unicode script "Sinhala". 4116 */ 4117 SINHALA, 4118 4119 /** 4120 * Unicode script "Thai". 4121 */ 4122 THAI, 4123 4124 /** 4125 * Unicode script "Lao". 4126 */ 4127 LAO, 4128 4129 /** 4130 * Unicode script "Tibetan". 4131 */ 4132 TIBETAN, 4133 4134 /** 4135 * Unicode script "Myanmar". 4136 */ 4137 MYANMAR, 4138 4139 /** 4140 * Unicode script "Georgian". 4141 */ 4142 GEORGIAN, 4143 4144 /** 4145 * Unicode script "Hangul". 4146 */ 4147 HANGUL, 4148 4149 /** 4150 * Unicode script "Ethiopic". 4151 */ 4152 ETHIOPIC, 4153 4154 /** 4155 * Unicode script "Cherokee". 4156 */ 4157 CHEROKEE, 4158 4159 /** 4160 * Unicode script "Canadian_Aboriginal". 4161 */ 4162 CANADIAN_ABORIGINAL, 4163 4164 /** 4165 * Unicode script "Ogham". 4166 */ 4167 OGHAM, 4168 4169 /** 4170 * Unicode script "Runic". 4171 */ 4172 RUNIC, 4173 4174 /** 4175 * Unicode script "Khmer". 4176 */ 4177 KHMER, 4178 4179 /** 4180 * Unicode script "Mongolian". 4181 */ 4182 MONGOLIAN, 4183 4184 /** 4185 * Unicode script "Hiragana". 4186 */ 4187 HIRAGANA, 4188 4189 /** 4190 * Unicode script "Katakana". 4191 */ 4192 KATAKANA, 4193 4194 /** 4195 * Unicode script "Bopomofo". 4196 */ 4197 BOPOMOFO, 4198 4199 /** 4200 * Unicode script "Han". 4201 */ 4202 HAN, 4203 4204 /** 4205 * Unicode script "Yi". 4206 */ 4207 YI, 4208 4209 /** 4210 * Unicode script "Old_Italic". 4211 */ 4212 OLD_ITALIC, 4213 4214 /** 4215 * Unicode script "Gothic". 4216 */ 4217 GOTHIC, 4218 4219 /** 4220 * Unicode script "Deseret". 4221 */ 4222 DESERET, 4223 4224 /** 4225 * Unicode script "Inherited". 4226 */ 4227 INHERITED, 4228 4229 /** 4230 * Unicode script "Tagalog". 4231 */ 4232 TAGALOG, 4233 4234 /** 4235 * Unicode script "Hanunoo". 4236 */ 4237 HANUNOO, 4238 4239 /** 4240 * Unicode script "Buhid". 4241 */ 4242 BUHID, 4243 4244 /** 4245 * Unicode script "Tagbanwa". 4246 */ 4247 TAGBANWA, 4248 4249 /** 4250 * Unicode script "Limbu". 4251 */ 4252 LIMBU, 4253 4254 /** 4255 * Unicode script "Tai_Le". 4256 */ 4257 TAI_LE, 4258 4259 /** 4260 * Unicode script "Linear_B". 4261 */ 4262 LINEAR_B, 4263 4264 /** 4265 * Unicode script "Ugaritic". 4266 */ 4267 UGARITIC, 4268 4269 /** 4270 * Unicode script "Shavian". 4271 */ 4272 SHAVIAN, 4273 4274 /** 4275 * Unicode script "Osmanya". 4276 */ 4277 OSMANYA, 4278 4279 /** 4280 * Unicode script "Cypriot". 4281 */ 4282 CYPRIOT, 4283 4284 /** 4285 * Unicode script "Braille". 4286 */ 4287 BRAILLE, 4288 4289 /** 4290 * Unicode script "Buginese". 4291 */ 4292 BUGINESE, 4293 4294 /** 4295 * Unicode script "Coptic". 4296 */ 4297 COPTIC, 4298 4299 /** 4300 * Unicode script "New_Tai_Lue". 4301 */ 4302 NEW_TAI_LUE, 4303 4304 /** 4305 * Unicode script "Glagolitic". 4306 */ 4307 GLAGOLITIC, 4308 4309 /** 4310 * Unicode script "Tifinagh". 4311 */ 4312 TIFINAGH, 4313 4314 /** 4315 * Unicode script "Syloti_Nagri". 4316 */ 4317 SYLOTI_NAGRI, 4318 4319 /** 4320 * Unicode script "Old_Persian". 4321 */ 4322 OLD_PERSIAN, 4323 4324 /** 4325 * Unicode script "Kharoshthi". 4326 */ 4327 KHAROSHTHI, 4328 4329 /** 4330 * Unicode script "Balinese". 4331 */ 4332 BALINESE, 4333 4334 /** 4335 * Unicode script "Cuneiform". 4336 */ 4337 CUNEIFORM, 4338 4339 /** 4340 * Unicode script "Phoenician". 4341 */ 4342 PHOENICIAN, 4343 4344 /** 4345 * Unicode script "Phags_Pa". 4346 */ 4347 PHAGS_PA, 4348 4349 /** 4350 * Unicode script "Nko". 4351 */ 4352 NKO, 4353 4354 /** 4355 * Unicode script "Sundanese". 4356 */ 4357 SUNDANESE, 4358 4359 /** 4360 * Unicode script "Batak". 4361 */ 4362 BATAK, 4363 4364 /** 4365 * Unicode script "Lepcha". 4366 */ 4367 LEPCHA, 4368 4369 /** 4370 * Unicode script "Ol_Chiki". 4371 */ 4372 OL_CHIKI, 4373 4374 /** 4375 * Unicode script "Vai". 4376 */ 4377 VAI, 4378 4379 /** 4380 * Unicode script "Saurashtra". 4381 */ 4382 SAURASHTRA, 4383 4384 /** 4385 * Unicode script "Kayah_Li". 4386 */ 4387 KAYAH_LI, 4388 4389 /** 4390 * Unicode script "Rejang". 4391 */ 4392 REJANG, 4393 4394 /** 4395 * Unicode script "Lycian". 4396 */ 4397 LYCIAN, 4398 4399 /** 4400 * Unicode script "Carian". 4401 */ 4402 CARIAN, 4403 4404 /** 4405 * Unicode script "Lydian". 4406 */ 4407 LYDIAN, 4408 4409 /** 4410 * Unicode script "Cham". 4411 */ 4412 CHAM, 4413 4414 /** 4415 * Unicode script "Tai_Tham". 4416 */ 4417 TAI_THAM, 4418 4419 /** 4420 * Unicode script "Tai_Viet". 4421 */ 4422 TAI_VIET, 4423 4424 /** 4425 * Unicode script "Avestan". 4426 */ 4427 AVESTAN, 4428 4429 /** 4430 * Unicode script "Egyptian_Hieroglyphs". 4431 */ 4432 EGYPTIAN_HIEROGLYPHS, 4433 4434 /** 4435 * Unicode script "Samaritan". 4436 */ 4437 SAMARITAN, 4438 4439 /** 4440 * Unicode script "Mandaic". 4441 */ 4442 MANDAIC, 4443 4444 /** 4445 * Unicode script "Lisu". 4446 */ 4447 LISU, 4448 4449 /** 4450 * Unicode script "Bamum". 4451 */ 4452 BAMUM, 4453 4454 /** 4455 * Unicode script "Javanese". 4456 */ 4457 JAVANESE, 4458 4459 /** 4460 * Unicode script "Meetei_Mayek". 4461 */ 4462 MEETEI_MAYEK, 4463 4464 /** 4465 * Unicode script "Imperial_Aramaic". 4466 */ 4467 IMPERIAL_ARAMAIC, 4468 4469 /** 4470 * Unicode script "Old_South_Arabian". 4471 */ 4472 OLD_SOUTH_ARABIAN, 4473 4474 /** 4475 * Unicode script "Inscriptional_Parthian". 4476 */ 4477 INSCRIPTIONAL_PARTHIAN, 4478 4479 /** 4480 * Unicode script "Inscriptional_Pahlavi". 4481 */ 4482 INSCRIPTIONAL_PAHLAVI, 4483 4484 /** 4485 * Unicode script "Old_Turkic". 4486 */ 4487 OLD_TURKIC, 4488 4489 /** 4490 * Unicode script "Brahmi". 4491 */ 4492 BRAHMI, 4493 4494 /** 4495 * Unicode script "Kaithi". 4496 */ 4497 KAITHI, 4498 4499 /** 4500 * Unicode script "Meroitic Hieroglyphs". 4501 * @since 1.8 4502 */ 4503 MEROITIC_HIEROGLYPHS, 4504 4505 /** 4506 * Unicode script "Meroitic Cursive". 4507 * @since 1.8 4508 */ 4509 MEROITIC_CURSIVE, 4510 4511 /** 4512 * Unicode script "Sora Sompeng". 4513 * @since 1.8 4514 */ 4515 SORA_SOMPENG, 4516 4517 /** 4518 * Unicode script "Chakma". 4519 * @since 1.8 4520 */ 4521 CHAKMA, 4522 4523 /** 4524 * Unicode script "Sharada". 4525 * @since 1.8 4526 */ 4527 SHARADA, 4528 4529 /** 4530 * Unicode script "Takri". 4531 * @since 1.8 4532 */ 4533 TAKRI, 4534 4535 /** 4536 * Unicode script "Miao". 4537 * @since 1.8 4538 */ 4539 MIAO, 4540 4541 /** 4542 * Unicode script "Caucasian Albanian". 4543 * @since 9 4544 */ 4545 CAUCASIAN_ALBANIAN, 4546 4547 /** 4548 * Unicode script "Bassa Vah". 4549 * @since 9 4550 */ 4551 BASSA_VAH, 4552 4553 /** 4554 * Unicode script "Duployan". 4555 * @since 9 4556 */ 4557 DUPLOYAN, 4558 4559 /** 4560 * Unicode script "Elbasan". 4561 * @since 9 4562 */ 4563 ELBASAN, 4564 4565 /** 4566 * Unicode script "Grantha". 4567 * @since 9 4568 */ 4569 GRANTHA, 4570 4571 /** 4572 * Unicode script "Pahawh Hmong". 4573 * @since 9 4574 */ 4575 PAHAWH_HMONG, 4576 4577 /** 4578 * Unicode script "Khojki". 4579 * @since 9 4580 */ 4581 KHOJKI, 4582 4583 /** 4584 * Unicode script "Linear A". 4585 * @since 9 4586 */ 4587 LINEAR_A, 4588 4589 /** 4590 * Unicode script "Mahajani". 4591 * @since 9 4592 */ 4593 MAHAJANI, 4594 4595 /** 4596 * Unicode script "Manichaean". 4597 * @since 9 4598 */ 4599 MANICHAEAN, 4600 4601 /** 4602 * Unicode script "Mende Kikakui". 4603 * @since 9 4604 */ 4605 MENDE_KIKAKUI, 4606 4607 /** 4608 * Unicode script "Modi". 4609 * @since 9 4610 */ 4611 MODI, 4612 4613 /** 4614 * Unicode script "Mro". 4615 * @since 9 4616 */ 4617 MRO, 4618 4619 /** 4620 * Unicode script "Old North Arabian". 4621 * @since 9 4622 */ 4623 OLD_NORTH_ARABIAN, 4624 4625 /** 4626 * Unicode script "Nabataean". 4627 * @since 9 4628 */ 4629 NABATAEAN, 4630 4631 /** 4632 * Unicode script "Palmyrene". 4633 * @since 9 4634 */ 4635 PALMYRENE, 4636 4637 /** 4638 * Unicode script "Pau Cin Hau". 4639 * @since 9 4640 */ 4641 PAU_CIN_HAU, 4642 4643 /** 4644 * Unicode script "Old Permic". 4645 * @since 9 4646 */ 4647 OLD_PERMIC, 4648 4649 /** 4650 * Unicode script "Psalter Pahlavi". 4651 * @since 9 4652 */ 4653 PSALTER_PAHLAVI, 4654 4655 /** 4656 * Unicode script "Siddham". 4657 * @since 9 4658 */ 4659 SIDDHAM, 4660 4661 /** 4662 * Unicode script "Khudawadi". 4663 * @since 9 4664 */ 4665 KHUDAWADI, 4666 4667 /** 4668 * Unicode script "Tirhuta". 4669 * @since 9 4670 */ 4671 TIRHUTA, 4672 4673 /** 4674 * Unicode script "Warang Citi". 4675 * @since 9 4676 */ 4677 WARANG_CITI, 4678 4679 /** 4680 * Unicode script "Ahom". 4681 * @since 9 4682 */ 4683 AHOM, 4684 4685 /** 4686 * Unicode script "Anatolian Hieroglyphs". 4687 * @since 9 4688 */ 4689 ANATOLIAN_HIEROGLYPHS, 4690 4691 /** 4692 * Unicode script "Hatran". 4693 * @since 9 4694 */ 4695 HATRAN, 4696 4697 /** 4698 * Unicode script "Multani". 4699 * @since 9 4700 */ 4701 MULTANI, 4702 4703 /** 4704 * Unicode script "Old Hungarian". 4705 * @since 9 4706 */ 4707 OLD_HUNGARIAN, 4708 4709 /** 4710 * Unicode script "SignWriting". 4711 * @since 9 4712 */ 4713 SIGNWRITING, 4714 4715 /** 4716 * Unicode script "Adlam". 4717 * @since 11 4718 */ 4719 ADLAM, 4720 4721 /** 4722 * Unicode script "Bhaiksuki". 4723 * @since 11 4724 */ 4725 BHAIKSUKI, 4726 4727 /** 4728 * Unicode script "Marchen". 4729 * @since 11 4730 */ 4731 MARCHEN, 4732 4733 /** 4734 * Unicode script "Newa". 4735 * @since 11 4736 */ 4737 NEWA, 4738 4739 /** 4740 * Unicode script "Osage". 4741 * @since 11 4742 */ 4743 OSAGE, 4744 4745 /** 4746 * Unicode script "Tangut". 4747 * @since 11 4748 */ 4749 TANGUT, 4750 4751 /** 4752 * Unicode script "Masaram Gondi". 4753 * @since 11 4754 */ 4755 MASARAM_GONDI, 4756 4757 /** 4758 * Unicode script "Nushu". 4759 * @since 11 4760 */ 4761 NUSHU, 4762 4763 /** 4764 * Unicode script "Soyombo". 4765 * @since 11 4766 */ 4767 SOYOMBO, 4768 4769 /** 4770 * Unicode script "Zanabazar Square". 4771 * @since 11 4772 */ 4773 ZANABAZAR_SQUARE, 4774 4775 /** 4776 * Unicode script "Hanifi Rohingya". 4777 * @since 12 4778 */ 4779 HANIFI_ROHINGYA, 4780 4781 /** 4782 * Unicode script "Old Sogdian". 4783 * @since 12 4784 */ 4785 OLD_SOGDIAN, 4786 4787 /** 4788 * Unicode script "Sogdian". 4789 * @since 12 4790 */ 4791 SOGDIAN, 4792 4793 /** 4794 * Unicode script "Dogra". 4795 * @since 12 4796 */ 4797 DOGRA, 4798 4799 /** 4800 * Unicode script "Gunjala Gondi". 4801 * @since 12 4802 */ 4803 GUNJALA_GONDI, 4804 4805 /** 4806 * Unicode script "Makasar". 4807 * @since 12 4808 */ 4809 MAKASAR, 4810 4811 /** 4812 * Unicode script "Medefaidrin". 4813 * @since 12 4814 */ 4815 MEDEFAIDRIN, 4816 4817 /** 4818 * Unicode script "Unknown". 4819 */ 4820 UNKNOWN; 4821 4822 private static final int[] scriptStarts = { 4823 0x0000, // 0000..0040; COMMON 4824 0x0041, // 0041..005A; LATIN 4825 0x005B, // 005B..0060; COMMON 4826 0x0061, // 0061..007A; LATIN 4827 0x007B, // 007B..00A9; COMMON 4828 0x00AA, // 00AA ; LATIN 4829 0x00AB, // 00AB..00B9; COMMON 4830 0x00BA, // 00BA ; LATIN 4831 0x00BB, // 00BB..00BF; COMMON 4832 0x00C0, // 00C0..00D6; LATIN 4833 0x00D7, // 00D7 ; COMMON 4834 0x00D8, // 00D8..00F6; LATIN 4835 0x00F7, // 00F7 ; COMMON 4836 0x00F8, // 00F8..02B8; LATIN 4837 0x02B9, // 02B9..02DF; COMMON 4838 0x02E0, // 02E0..02E4; LATIN 4839 0x02E5, // 02E5..02E9; COMMON 4840 0x02EA, // 02EA..02EB; BOPOMOFO 4841 0x02EC, // 02EC..02FF; COMMON 4842 0x0300, // 0300..036F; INHERITED 4843 0x0370, // 0370..0373; GREEK 4844 0x0374, // 0374 ; COMMON 4845 0x0375, // 0375..0377; GREEK 4846 0x0378, // 0378..0379; UNKNOWN 4847 0x037A, // 037A..037D; GREEK 4848 0x037E, // 037E ; COMMON 4849 0x037F, // 037F ; GREEK 4850 0x0380, // 0380..0383; UNKNOWN 4851 0x0384, // 0384 ; GREEK 4852 0x0385, // 0385 ; COMMON 4853 0x0386, // 0386 ; GREEK 4854 0x0387, // 0387 ; COMMON 4855 0x0388, // 0388..038A; GREEK 4856 0x038B, // 038B ; UNKNOWN 4857 0x038C, // 038C ; GREEK 4858 0x038D, // 038D ; UNKNOWN 4859 0x038E, // 038E..03A1; GREEK 4860 0x03A2, // 03A2 ; UNKNOWN 4861 0x03A3, // 03A3..03E1; GREEK 4862 0x03E2, // 03E2..03EF; COPTIC 4863 0x03F0, // 03F0..03FF; GREEK 4864 0x0400, // 0400..0484; CYRILLIC 4865 0x0485, // 0485..0486; INHERITED 4866 0x0487, // 0487..052F; CYRILLIC 4867 0x0530, // 0530 ; UNKNOWN 4868 0x0531, // 0531..0556; ARMENIAN 4869 0x0557, // 0557..0558; UNKNOWN 4870 0x0559, // 0559..0588; ARMENIAN 4871 0x0589, // 0589 ; COMMON 4872 0x058A, // 058A ; ARMENIAN 4873 0x058B, // 058B..058C; UNKNOWN 4874 0x058D, // 058D..058F; ARMENIAN 4875 0x0590, // 0590 ; UNKNOWN 4876 0x0591, // 0591..05C7; HEBREW 4877 0x05C8, // 05C8..05CF; UNKNOWN 4878 0x05D0, // 05D0..05EA; HEBREW 4879 0x05EB, // 05EB..05EE; UNKNOWN 4880 0x05EF, // 05EF..05F4; HEBREW 4881 0x05F5, // 05F5..05FF; UNKNOWN 4882 0x0600, // 0600..0604; ARABIC 4883 0x0605, // 0605 ; COMMON 4884 0x0606, // 0606..060B; ARABIC 4885 0x060C, // 060C ; COMMON 4886 0x060D, // 060D..061A; ARABIC 4887 0x061B, // 061B ; COMMON 4888 0x061C, // 061C ; ARABIC 4889 0x061D, // 061D ; UNKNOWN 4890 0x061E, // 061E ; ARABIC 4891 0x061F, // 061F ; COMMON 4892 0x0620, // 0620..063F; ARABIC 4893 0x0640, // 0640 ; COMMON 4894 0x0641, // 0641..064A; ARABIC 4895 0x064B, // 064B..0655; INHERITED 4896 0x0656, // 0656..066F; ARABIC 4897 0x0670, // 0670 ; INHERITED 4898 0x0671, // 0671..06DC; ARABIC 4899 0x06DD, // 06DD ; COMMON 4900 0x06DE, // 06DE..06FF; ARABIC 4901 0x0700, // 0700..070D; SYRIAC 4902 0x070E, // 070E ; UNKNOWN 4903 0x070F, // 070F..074A; SYRIAC 4904 0x074B, // 074B..074C; UNKNOWN 4905 0x074D, // 074D..074F; SYRIAC 4906 0x0750, // 0750..077F; ARABIC 4907 0x0780, // 0780..07B1; THAANA 4908 0x07B2, // 07B2..07BF; UNKNOWN 4909 0x07C0, // 07C0..07FA; NKO 4910 0x07FB, // 07FB..07FC; UNKNOWN 4911 0X07FD, // 07FD..07FF; NKO 4912 0x0800, // 0800..082D; SAMARITAN 4913 0x082E, // 082E..082F; UNKNOWN 4914 0x0830, // 0830..083E; SAMARITAN 4915 0x083F, // 083F ; UNKNOWN 4916 0x0840, // 0840..085B; MANDAIC 4917 0x085C, // 085C..085D; UNKNOWN 4918 0x085E, // 085E ; MANDAIC 4919 0x085F, // 085F ; UNKNOWN 4920 0x0860, // 0860..086A; SYRIAC 4921 0x086B, // 086B..089F; UNKNOWN 4922 0x08A0, // 08A0..08B4; ARABIC 4923 0x08B5, // 08B5 ; UNKNOWN 4924 0x08B6, // 08B6..08BD; ARABIC 4925 0x08BE, // 08BE..08D2; UNKNOWN 4926 0x08D3, // 08D3..08E1; ARABIC 4927 0x08E2, // 08E2 ; COMMON 4928 0x08E3, // 08E3..08FF; ARABIC 4929 0x0900, // 0900..0950; DEVANAGARI 4930 0x0951, // 0951..0952; INHERITED 4931 0x0953, // 0953..0963; DEVANAGARI 4932 0x0964, // 0964..0965; COMMON 4933 0x0966, // 0966..097F; DEVANAGARI 4934 0x0980, // 0980..0983; BENGALI 4935 0x0984, // 0984 ; UNKNOWN 4936 0x0985, // 0985..098C; BENGALI 4937 0x098D, // 098D..098E; UNKNOWN 4938 0x098F, // 098F..0990; BENGALI 4939 0x0991, // 0991..0992; UNKNOWN 4940 0x0993, // 0993..09A8; BENGALI 4941 0x09A9, // 09A9 ; UNKNOWN 4942 0x09AA, // 09AA..09B0; BENGALI 4943 0x09B1, // 09B1 ; UNKNOWN 4944 0x09B2, // 09B2 ; BENGALI 4945 0x09B3, // 09B3..09B5; UNKNOWN 4946 0x09B6, // 09B6..09B9; BENGALI 4947 0x09BA, // 09BA..09BB; UNKNOWN 4948 0x09BC, // 09BC..09C4; BENGALI 4949 0x09C5, // 09C5..09C6; UNKNOWN 4950 0x09C7, // 09C7..09C8; BENGALI 4951 0x09C9, // 09C9..09CA; UNKNOWN 4952 0x09CB, // 09CB..09CE; BENGALI 4953 0x09CF, // 09CF..09D6; UNKNOWN 4954 0x09D7, // 09D7 ; BENGALI 4955 0x09D8, // 09D8..09DB; UNKNOWN 4956 0x09DC, // 09DC..09DD; BENGALI 4957 0x09DE, // 09DE ; UNKNOWN 4958 0x09DF, // 09DF..09E3; BENGALI 4959 0x09E4, // 09E4..09E5; UNKNOWN 4960 0x09E6, // 09E6..09FE; BENGALI 4961 0x09FF, // 09FF..0A00; UNKNOWN 4962 0x0A01, // 0A01..0A03; GURMUKHI 4963 0x0A04, // 0A04 ; UNKNOWN 4964 0x0A05, // 0A05..0A0A; GURMUKHI 4965 0x0A0B, // 0A0B..0A0E; UNKNOWN 4966 0x0A0F, // 0A0F..0A10; GURMUKHI 4967 0x0A11, // 0A11..0A12; UNKNOWN 4968 0x0A13, // 0A13..0A28; GURMUKHI 4969 0x0A29, // 0A29 ; UNKNOWN 4970 0x0A2A, // 0A2A..0A30; GURMUKHI 4971 0x0A31, // 0A31 ; UNKNOWN 4972 0x0A32, // 0A32..0A33; GURMUKHI 4973 0x0A34, // 0A34 ; UNKNOWN 4974 0x0A35, // 0A35..0A36; GURMUKHI 4975 0x0A37, // 0A37 ; UNKNOWN 4976 0x0A38, // 0A38..0A39; GURMUKHI 4977 0x0A3A, // 0A3A..0A3B; UNKNOWN 4978 0x0A3C, // 0A3C ; GURMUKHI 4979 0x0A3D, // 0A3D ; UNKNOWN 4980 0x0A3E, // 0A3E..0A42; GURMUKHI 4981 0x0A43, // 0A43..0A46; UNKNOWN 4982 0x0A47, // 0A47..0A48; GURMUKHI 4983 0x0A49, // 0A49..0A4A; UNKNOWN 4984 0x0A4B, // 0A4B..0A4D; GURMUKHI 4985 0x0A4E, // 0A4E..0A50; UNKNOWN 4986 0x0A51, // 0A51 ; GURMUKHI 4987 0x0A52, // 0A52..0A58; UNKNOWN 4988 0x0A59, // 0A59..0A5C; GURMUKHI 4989 0x0A5D, // 0A5D ; UNKNOWN 4990 0x0A5E, // 0A5E ; GURMUKHI 4991 0x0A5F, // 0A5F..0A65; UNKNOWN 4992 0x0A66, // 0A66..0A76; GURMUKHI 4993 0x0A77, // 0A77..0A80; UNKNOWN 4994 0x0A81, // 0A81..0A83; GUJARATI 4995 0x0A84, // 0A84 ; UNKNOWN 4996 0x0A85, // 0A85..0A8D; GUJARATI 4997 0x0A8E, // 0A8E ; UNKNOWN 4998 0x0A8F, // 0A8F..0A91; GUJARATI 4999 0x0A92, // 0A92 ; UNKNOWN 5000 0x0A93, // 0A93..0AA8; GUJARATI 5001 0x0AA9, // 0AA9 ; UNKNOWN 5002 0x0AAA, // 0AAA..0AB0; GUJARATI 5003 0x0AB1, // 0AB1 ; UNKNOWN 5004 0x0AB2, // 0AB2..0AB3; GUJARATI 5005 0x0AB4, // 0AB4 ; UNKNOWN 5006 0x0AB5, // 0AB5..0AB9; GUJARATI 5007 0x0ABA, // 0ABA..0ABB; UNKNOWN 5008 0x0ABC, // 0ABC..0AC5; GUJARATI 5009 0x0AC6, // 0AC6 ; UNKNOWN 5010 0x0AC7, // 0AC7..0AC9; GUJARATI 5011 0x0ACA, // 0ACA ; UNKNOWN 5012 0x0ACB, // 0ACB..0ACD; GUJARATI 5013 0x0ACE, // 0ACE..0ACF; UNKNOWN 5014 0x0AD0, // 0AD0 ; GUJARATI 5015 0x0AD1, // 0AD1..0ADF; UNKNOWN 5016 0x0AE0, // 0AE0..0AE3; GUJARATI 5017 0x0AE4, // 0AE4..0AE5; UNKNOWN 5018 0x0AE6, // 0AE6..0AF1; GUJARATI 5019 0x0AF2, // 0AF2..0AF8; UNKNOWN 5020 0x0AF9, // 0AF9..0AFF; GUJARATI 5021 0x0B00, // 0B00 ; UNKNOWN 5022 0x0B01, // 0B01..0B03; ORIYA 5023 0x0B04, // 0B04 ; UNKNOWN 5024 0x0B05, // 0B05..0B0C; ORIYA 5025 0x0B0D, // 0B0D..0B0E; UNKNOWN 5026 0x0B0F, // 0B0F..0B10; ORIYA 5027 0x0B11, // 0B11..0B12; UNKNOWN 5028 0x0B13, // 0B13..0B28; ORIYA 5029 0x0B29, // 0B29 ; UNKNOWN 5030 0x0B2A, // 0B2A..0B30; ORIYA 5031 0x0B31, // 0B31 ; UNKNOWN 5032 0x0B32, // 0B32..0B33; ORIYA 5033 0x0B34, // 0B34 ; UNKNOWN 5034 0x0B35, // 0B35..0B39; ORIYA 5035 0x0B3A, // 0B3A..0B3B; UNKNOWN 5036 0x0B3C, // 0B3C..0B44; ORIYA 5037 0x0B45, // 0B45..0B46; UNKNOWN 5038 0x0B47, // 0B47..0B48; ORIYA 5039 0x0B49, // 0B49..0B4A; UNKNOWN 5040 0x0B4B, // 0B4B..0B4D; ORIYA 5041 0x0B4E, // 0B4E..0B55; UNKNOWN 5042 0x0B56, // 0B56..0B57; ORIYA 5043 0x0B58, // 0B58..0B5B; UNKNOWN 5044 0x0B5C, // 0B5C..0B5D; ORIYA 5045 0x0B5E, // 0B5E ; UNKNOWN 5046 0x0B5F, // 0B5F..0B63; ORIYA 5047 0x0B64, // 0B64..0B65; UNKNOWN 5048 0x0B66, // 0B66..0B77; ORIYA 5049 0x0B78, // 0B78..0B81; UNKNOWN 5050 0x0B82, // 0B82..0B83; TAMIL 5051 0x0B84, // 0B84 ; UNKNOWN 5052 0x0B85, // 0B85..0B8A; TAMIL 5053 0x0B8B, // 0B8B..0B8D; UNKNOWN 5054 0x0B8E, // 0B8E..0B90; TAMIL 5055 0x0B91, // 0B91 ; UNKNOWN 5056 0x0B92, // 0B92..0B95; TAMIL 5057 0x0B96, // 0B96..0B98; UNKNOWN 5058 0x0B99, // 0B99..0B9A; TAMIL 5059 0x0B9B, // 0B9B ; UNKNOWN 5060 0x0B9C, // 0B9C ; TAMIL 5061 0x0B9D, // 0B9D ; UNKNOWN 5062 0x0B9E, // 0B9E..0B9F; TAMIL 5063 0x0BA0, // 0BA0..0BA2; UNKNOWN 5064 0x0BA3, // 0BA3..0BA4; TAMIL 5065 0x0BA5, // 0BA5..0BA7; UNKNOWN 5066 0x0BA8, // 0BA8..0BAA; TAMIL 5067 0x0BAB, // 0BAB..0BAD; UNKNOWN 5068 0x0BAE, // 0BAE..0BB9; TAMIL 5069 0x0BBA, // 0BBA..0BBD; UNKNOWN 5070 0x0BBE, // 0BBE..0BC2; TAMIL 5071 0x0BC3, // 0BC3..0BC5; UNKNOWN 5072 0x0BC6, // 0BC6..0BC8; TAMIL 5073 0x0BC9, // 0BC9 ; UNKNOWN 5074 0x0BCA, // 0BCA..0BCD; TAMIL 5075 0x0BCE, // 0BCE..0BCF; UNKNOWN 5076 0x0BD0, // 0BD0 ; TAMIL 5077 0x0BD1, // 0BD1..0BD6; UNKNOWN 5078 0x0BD7, // 0BD7 ; TAMIL 5079 0x0BD8, // 0BD8..0BE5; UNKNOWN 5080 0x0BE6, // 0BE6..0BFA; TAMIL 5081 0x0BFB, // 0BFB..0BFF; UNKNOWN 5082 0x0C00, // 0C00..0C0C; TELUGU 5083 0x0C0D, // 0C0D ; UNKNOWN 5084 0x0C0E, // 0C0E..0C10; TELUGU 5085 0x0C11, // 0C11 ; UNKNOWN 5086 0x0C12, // 0C12..0C28; TELUGU 5087 0x0C29, // 0C29 ; UNKNOWN 5088 0x0C2A, // 0C2A..0C39; TELUGU 5089 0x0C3A, // 0C3A..0C3C; UNKNOWN 5090 0x0C3D, // 0C3D..0C44; TELUGU 5091 0x0C45, // 0C45 ; UNKNOWN 5092 0x0C46, // 0C46..0C48; TELUGU 5093 0x0C49, // 0C49 ; UNKNOWN 5094 0x0C4A, // 0C4A..0C4D; TELUGU 5095 0x0C4E, // 0C4E..0C54; UNKNOWN 5096 0x0C55, // 0C55..0C56; TELUGU 5097 0x0C57, // 0C57 ; UNKNOWN 5098 0x0C58, // 0C58..0C5A; TELUGU 5099 0x0C5B, // 0C5B..0C5F; UNKNOWN 5100 0x0C60, // 0C60..0C63; TELUGU 5101 0x0C64, // 0C64..0C65; UNKNOWN 5102 0x0C66, // 0C66..0C6F; TELUGU 5103 0x0C70, // 0C70..0C77; UNKNOWN 5104 0x0C78, // 0C78..0C7F; TELUGU 5105 0x0C80, // 0C80..0C8C; KANNADA 5106 0x0C8D, // 0C8D ; UNKNOWN 5107 0x0C8E, // 0C8E..0C90; KANNADA 5108 0x0C91, // 0C91 ; UNKNOWN 5109 0x0C92, // 0C92..0CA8; KANNADA 5110 0x0CA9, // 0CA9 ; UNKNOWN 5111 0x0CAA, // 0CAA..0CB3; KANNADA 5112 0x0CB4, // 0CB4 ; UNKNOWN 5113 0x0CB5, // 0CB5..0CB9; KANNADA 5114 0x0CBA, // 0CBA..0CBB; UNKNOWN 5115 0x0CBC, // 0CBC..0CC4; KANNADA 5116 0x0CC5, // 0CC5 ; UNKNOWN 5117 0x0CC6, // 0CC6..0CC8; KANNADA 5118 0x0CC9, // 0CC9 ; UNKNOWN 5119 0x0CCA, // 0CCA..0CCD; KANNADA 5120 0x0CCE, // 0CCE..0CD4; UNKNOWN 5121 0x0CD5, // 0CD5..0CD6; KANNADA 5122 0x0CD7, // 0CD7..0CDD; UNKNOWN 5123 0x0CDE, // 0CDE ; KANNADA 5124 0x0CDF, // 0CDF ; UNKNOWN 5125 0x0CE0, // 0CE0..0CE3; KANNADA 5126 0x0CE4, // 0CE4..0CE5; UNKNOWN 5127 0x0CE6, // 0CE6..0CEF; KANNADA 5128 0x0CF0, // 0CF0 ; UNKNOWN 5129 0x0CF1, // 0CF1..0CF2; KANNADA 5130 0x0CF3, // 0CF3..0CFF; UNKNOWN 5131 0x0D00, // 0D00..0D03; MALAYALAM 5132 0x0D04, // 0D04 ; UNKNOWN 5133 0x0D05, // 0D05..0D0C; MALAYALAM 5134 0x0D0D, // 0D0D ; UNKNOWN 5135 0x0D0E, // 0D0E..0D10; MALAYALAM 5136 0x0D11, // 0D11 ; UNKNOWN 5137 0x0D12, // 0D12..0D44; MALAYALAM 5138 0x0D45, // 0D45 ; UNKNOWN 5139 0x0D46, // 0D46..0D48; MALAYALAM 5140 0x0D49, // 0D49 ; UNKNOWN 5141 0x0D4A, // 0D4A..0D4F; MALAYALAM 5142 0x0D50, // 0D50..0D53; UNKNOWN 5143 0x0D54, // 0D54..0D63; MALAYALAM 5144 0x0D64, // 0D64..0D65; UNKNOWN 5145 0x0D66, // 0D66..0D7F; MALAYALAM 5146 0x0D80, // 0D80..0D81; UNKNOWN 5147 0x0D82, // 0D82..0D83; SINHALA 5148 0x0D84, // 0D84 ; UNKNOWN 5149 0x0D85, // 0D85..0D96; SINHALA 5150 0x0D97, // 0D97..0D99; UNKNOWN 5151 0x0D9A, // 0D9A..0DB1; SINHALA 5152 0x0DB2, // 0DB2 ; UNKNOWN 5153 0x0DB3, // 0DB3..0DBB; SINHALA 5154 0x0DBC, // 0DBC ; UNKNOWN 5155 0x0DBD, // 0DBD ; SINHALA 5156 0x0DBE, // 0DBE..0DBF; UNKNOWN 5157 0x0DC0, // 0DC0..0DC6; SINHALA 5158 0x0DC7, // 0DC7..0DC9; UNKNOWN 5159 0x0DCA, // 0DCA ; SINHALA 5160 0x0DCB, // 0DCB..0DCE; UNKNOWN 5161 0x0DCF, // 0DCF..0DD4; SINHALA 5162 0x0DD5, // 0DD5 ; UNKNOWN 5163 0x0DD6, // 0DD6 ; SINHALA 5164 0x0DD7, // 0DD7 ; UNKNOWN 5165 0x0DD8, // 0DD8..0DDF; SINHALA 5166 0x0DE0, // 0DE0..0DE5; UNKNOWN 5167 0x0DE6, // 0DE6..0DEF; SINHALA 5168 0x0DF0, // 0DF0..0DF1; UNKNOWN 5169 0x0DF2, // 0DF2..0DF4; SINHALA 5170 0x0DF5, // 0DF5..0E00; UNKNOWN 5171 0x0E01, // 0E01..0E3A; THAI 5172 0x0E3B, // 0E3B..0E3E; UNKNOWN 5173 0x0E3F, // 0E3F ; COMMON 5174 0x0E40, // 0E40..0E5B; THAI 5175 0x0E5C, // 0E5C..0E80; UNKNOWN 5176 0x0E81, // 0E81..0E82; LAO 5177 0x0E83, // 0E83 ; UNKNOWN 5178 0x0E84, // 0E84 ; LAO 5179 0x0E85, // 0E85..0E86; UNKNOWN 5180 0x0E87, // 0E87..0E88; LAO 5181 0x0E89, // 0E89 ; UNKNOWN 5182 0x0E8A, // 0E8A ; LAO 5183 0x0E8B, // 0E8B..0E8C; UNKNOWN 5184 0x0E8D, // 0E8D ; LAO 5185 0x0E8E, // 0E8E..0E93; UNKNOWN 5186 0x0E94, // 0E94..0E97; LAO 5187 0x0E98, // 0E98 ; UNKNOWN 5188 0x0E99, // 0E99..0E9F; LAO 5189 0x0EA0, // 0EA0 ; UNKNOWN 5190 0x0EA1, // 0EA1..0EA3; LAO 5191 0x0EA4, // 0EA4 ; UNKNOWN 5192 0x0EA5, // 0EA5 ; LAO 5193 0x0EA6, // 0EA6 ; UNKNOWN 5194 0x0EA7, // 0EA7 ; LAO 5195 0x0EA8, // 0EA8..0EA9; UNKNOWN 5196 0x0EAA, // 0EAA..0EAB; LAO 5197 0x0EAC, // 0EAC ; UNKNOWN 5198 0x0EAD, // 0EAD..0EB9; LAO 5199 0x0EBA, // 0EBA ; UNKNOWN 5200 0x0EBB, // 0EBB..0EBD; LAO 5201 0x0EBE, // 0EBE..0EBF; UNKNOWN 5202 0x0EC0, // 0EC0..0EC4; LAO 5203 0x0EC5, // 0EC5 ; UNKNOWN 5204 0x0EC6, // 0EC6 ; LAO 5205 0x0EC7, // 0EC7 ; UNKNOWN 5206 0x0EC8, // 0EC8..0ECD; LAO 5207 0x0ECE, // 0ECE..0ECF; UNKNOWN 5208 0x0ED0, // 0ED0..0ED9; LAO 5209 0x0EDA, // 0EDA..0EDB; UNKNOWN 5210 0x0EDC, // 0EDC..0EDF; LAO 5211 0x0EE0, // 0EE0..0EFF; UNKNOWN 5212 0x0F00, // 0F00..0F47; TIBETAN 5213 0x0F48, // 0F48 ; UNKNOWN 5214 0x0F49, // 0F49..0F6C; TIBETAN 5215 0x0F6D, // 0F6D..0F70; UNKNOWN 5216 0x0F71, // 0F71..0F97; TIBETAN 5217 0x0F98, // 0F98 ; UNKNOWN 5218 0x0F99, // 0F99..0FBC; TIBETAN 5219 0x0FBD, // 0FBD ; UNKNOWN 5220 0x0FBE, // 0FBE..0FCC; TIBETAN 5221 0x0FCD, // 0FCD ; UNKNOWN 5222 0x0FCE, // 0FCE..0FD4; TIBETAN 5223 0x0FD5, // 0FD5..0FD8; COMMON 5224 0x0FD9, // 0FD9..0FDA; TIBETAN 5225 0x0FDB, // 0FDB..FFF; UNKNOWN 5226 0x1000, // 1000..109F; MYANMAR 5227 0x10A0, // 10A0..10C5; GEORGIAN 5228 0x10C6, // 10C6 ; UNKNOWN 5229 0x10C7, // 10C7 ; GEORGIAN 5230 0x10C8, // 10C8..10CC; UNKNOWN 5231 0x10CD, // 10CD ; GEORGIAN 5232 0x10CE, // 10CE..10CF; UNKNOWN 5233 0x10D0, // 10D0..10FA; GEORGIAN 5234 0x10FB, // 10FB ; COMMON 5235 0x10FC, // 10FC..10FF; GEORGIAN 5236 0x1100, // 1100..11FF; HANGUL 5237 0x1200, // 1200..1248; ETHIOPIC 5238 0x1249, // 1249 ; UNKNOWN 5239 0x124A, // 124A..124D; ETHIOPIC 5240 0x124E, // 124E..124F; UNKNOWN 5241 0x1250, // 1250..1256; ETHIOPIC 5242 0x1257, // 1257 ; UNKNOWN 5243 0x1258, // 1258 ; ETHIOPIC 5244 0x1259, // 1259 ; UNKNOWN 5245 0x125A, // 125A..125D; ETHIOPIC 5246 0x125E, // 125E..125F; UNKNOWN 5247 0x1260, // 1260..1288; ETHIOPIC 5248 0x1289, // 1289 ; UNKNOWN 5249 0x128A, // 128A..128D; ETHIOPIC 5250 0x128E, // 128E..128F; UNKNOWN 5251 0x1290, // 1290..12B0; ETHIOPIC 5252 0x12B1, // 12B1 ; UNKNOWN 5253 0x12B2, // 12B2..12B5; ETHIOPIC 5254 0x12B6, // 12B6..12B7; UNKNOWN 5255 0x12B8, // 12B8..12BE; ETHIOPIC 5256 0x12BF, // 12BF ; UNKNOWN 5257 0x12C0, // 12C0 ; ETHIOPIC 5258 0x12C1, // 12C1 ; UNKNOWN 5259 0x12C2, // 12C2..12C5; ETHIOPIC 5260 0x12C6, // 12C6..12C7; UNKNOWN 5261 0x12C8, // 12C8..12D6; ETHIOPIC 5262 0x12D7, // 12D7 ; UNKNOWN 5263 0x12D8, // 12D8..1310; ETHIOPIC 5264 0x1311, // 1311 ; UNKNOWN 5265 0x1312, // 1312..1315; ETHIOPIC 5266 0x1316, // 1316..1317; UNKNOWN 5267 0x1318, // 1318..135A; ETHIOPIC 5268 0x135B, // 135B..135C; UNKNOWN 5269 0x135D, // 135D..137C; ETHIOPIC 5270 0x137D, // 137D..137F; UNKNOWN 5271 0x1380, // 1380..1399; ETHIOPIC 5272 0x139A, // 139A..139F; UNKNOWN 5273 0x13A0, // 13A0..13F5; CHEROKEE 5274 0x13F6, // 13F6..13F7; UNKNOWN 5275 0x13F8, // 13F8..13FD; CHEROKEE 5276 0x13FE, // 13FE..13FF; UNKNOWN 5277 0x1400, // 1400..167F; CANADIAN_ABORIGINAL 5278 0x1680, // 1680..169C; OGHAM 5279 0x169D, // 169D..169F; UNKNOWN 5280 0x16A0, // 16A0..16EA; RUNIC 5281 0x16EB, // 16EB..16ED; COMMON 5282 0x16EE, // 16EE..16F8; RUNIC 5283 0x16F9, // 16F9..16FF; UNKNOWN 5284 0x1700, // 1700..170C; TAGALOG 5285 0x170D, // 170D ; UNKNOWN 5286 0x170E, // 170E..1714; TAGALOG 5287 0x1715, // 1715..171F; UNKNOWN 5288 0x1720, // 1720..1734; HANUNOO 5289 0x1735, // 1735..1736; COMMON 5290 0x1737, // 1737..173F; UNKNOWN 5291 0x1740, // 1740..1753; BUHID 5292 0x1754, // 1754..175F; UNKNOWN 5293 0x1760, // 1760..176C; TAGBANWA 5294 0x176D, // 176D ; UNKNOWN 5295 0x176E, // 176E..1770; TAGBANWA 5296 0x1771, // 1771 ; UNKNOWN 5297 0x1772, // 1772..1773; TAGBANWA 5298 0x1774, // 1774..177F; UNKNOWN 5299 0x1780, // 1780..17DD; KHMER 5300 0x17DE, // 17DE..17DF; UNKNOWN 5301 0x17E0, // 17E0..17E9; KHMER 5302 0x17EA, // 17EA..17EF; UNKNOWN 5303 0x17F0, // 17F0..17F9; KHMER 5304 0x17FA, // 17FA..17FF; UNKNOWN 5305 0x1800, // 1800..1801; MONGOLIAN 5306 0x1802, // 1802..1803; COMMON 5307 0x1804, // 1804 ; MONGOLIAN 5308 0x1805, // 1805 ; COMMON 5309 0x1806, // 1806..180E; MONGOLIAN 5310 0x180F, // 180F ; UNKNOWN 5311 0x1810, // 1810..1819; MONGOLIAN 5312 0x181A, // 181A..181F; UNKNOWN 5313 0x1820, // 1820..1878; MONGOLIAN 5314 0x1879, // 1879..187F; UNKNOWN 5315 0x1880, // 1880..18AA; MONGOLIAN 5316 0x18AB, // 18AB..18AF; UNKNOWN 5317 0x18B0, // 18B0..18F5; CANADIAN_ABORIGINAL 5318 0x18F6, // 18F6..18FF; UNKNOWN 5319 0x1900, // 1900..191E; LIMBU 5320 0x191F, // 191F ; UNKNOWN 5321 0x1920, // 1920..192B; LIMBU 5322 0x192C, // 192C..192F; UNKNOWN 5323 0x1930, // 1930..193B; LIMBU 5324 0x193C, // 193C..193F; UNKNOWN 5325 0x1940, // 1940 ; LIMBU 5326 0x1941, // 1941..1943; UNKNOWN 5327 0x1944, // 1944..194F; LIMBU 5328 0x1950, // 1950..196D; TAI_LE 5329 0x196E, // 196E..196F; UNKNOWN 5330 0x1970, // 1970..1974; TAI_LE 5331 0x1975, // 1975..197F; UNKNOWN 5332 0x1980, // 1980..19AB; NEW_TAI_LUE 5333 0x19AC, // 19AC..19AF; UNKNOWN 5334 0x19B0, // 19B0..19C9; NEW_TAI_LUE 5335 0x19CA, // 19CA..19CF; UNKNOWN 5336 0x19D0, // 19D0..19DA; NEW_TAI_LUE 5337 0x19DB, // 19DB..19DD; UNKNOWN 5338 0x19DE, // 19DE..19DF; NEW_TAI_LUE 5339 0x19E0, // 19E0..19FF; KHMER 5340 0x1A00, // 1A00..1A1B; BUGINESE 5341 0x1A1C, // 1A1C..1A1D; UNKNOWN 5342 0x1A1E, // 1A1E..1A1F; BUGINESE 5343 0x1A20, // 1A20..1A5E; TAI_THAM 5344 0x1A5F, // 1A5F ; UNKNOWN 5345 0x1A60, // 1A60..1A7C; TAI_THAM 5346 0x1A7D, // 1A7D..1A7E; UNKNOWN 5347 0x1A7F, // 1A7F..1A89; TAI_THAM 5348 0x1A8A, // 1A8A..1A8F; UNKNOWN 5349 0x1A90, // 1A90..1A99; TAI_THAM 5350 0x1A9A, // 1A9A..1A9F; UNKNOWN 5351 0x1AA0, // 1AA0..1AAD; TAI_THAM 5352 0x1AAE, // 1AAE..1AAF; UNKNOWN 5353 0x1AB0, // 1AB0..1ABE; INHERITED 5354 0x1ABF, // 1ABF..1AFF; UNKNOWN 5355 0x1B00, // 1B00..1B4B; BALINESE 5356 0x1B4C, // 1B4C..1B4F; UNKNOWN 5357 0x1B50, // 1B50..1B7C; BALINESE 5358 0x1B7D, // 1B7D..1B7F; UNKNOWN 5359 0x1B80, // 1B80..1BBF; SUNDANESE 5360 0x1BC0, // 1BC0..1BF3; BATAK 5361 0x1BF4, // 1BF4..1BFB; UNKNOWN 5362 0x1BFC, // 1BFC..1BFF; BATAK 5363 0x1C00, // 1C00..1C37; LEPCHA 5364 0x1C38, // 1C38..1C3A; UNKNOWN 5365 0x1C3B, // 1C3B..1C49; LEPCHA 5366 0x1C4A, // 1C4A..1C4C; UNKNOWN 5367 0x1C4D, // 1C4D..1C4F; LEPCHA 5368 0x1C50, // 1C50..1C7F; OL_CHIKI 5369 0x1C80, // 1C80..1C88; CYRILLIC 5370 0x1C89, // 1C89 ; UNKNOWN 5371 0x1C90, // 1C90..1CBA; GEORGIAN 5372 0x1CBB, // 1CBB..1CBC; UNKNOWN 5373 0x1CBD, // 1CBD..1CBF; GEORGIAN 5374 0x1CC0, // 1CC0..1CC7; SUNDANESE 5375 0x1CC8, // 1CC8..1CCF; UNKNOWN 5376 0x1CD0, // 1CD0..1CD2; INHERITED 5377 0x1CD3, // 1CD3 ; COMMON 5378 0x1CD4, // 1CD4..1CE0; INHERITED 5379 0x1CE1, // 1CE1 ; COMMON 5380 0x1CE2, // 1CE2..1CE8; INHERITED 5381 0x1CE9, // 1CE9..1CEC; COMMON 5382 0x1CED, // 1CED ; INHERITED 5383 0x1CEE, // 1CEE..1CF3; COMMON 5384 0x1CF4, // 1CF4 ; INHERITED 5385 0x1CF5, // 1CF5..1CF7; COMMON 5386 0x1CF8, // 1CF8..1CF9; INHERITED 5387 0x1CFA, // 1CFA..1CFF; UNKNOWN 5388 0x1D00, // 1D00..1D25; LATIN 5389 0x1D26, // 1D26..1D2A; GREEK 5390 0x1D2B, // 1D2B ; CYRILLIC 5391 0x1D2C, // 1D2C..1D5C; LATIN 5392 0x1D5D, // 1D5D..1D61; GREEK 5393 0x1D62, // 1D62..1D65; LATIN 5394 0x1D66, // 1D66..1D6A; GREEK 5395 0x1D6B, // 1D6B..1D77; LATIN 5396 0x1D78, // 1D78 ; CYRILLIC 5397 0x1D79, // 1D79..1DBE; LATIN 5398 0x1DBF, // 1DBF ; GREEK 5399 0x1DC0, // 1DC0..1DF9; INHERITED 5400 0x1DFA, // 1DFA ; UNKNOWN 5401 0x1DFB, // 1DFB..1DFF; INHERITED 5402 0x1E00, // 1E00..1EFF; LATIN 5403 0x1F00, // 1F00..1F15; GREEK 5404 0x1F16, // 1F16..1F17; UNKNOWN 5405 0x1F18, // 1F18..1F1D; GREEK 5406 0x1F1E, // 1F1E..1F1F; UNKNOWN 5407 0x1F20, // 1F20..1F45; GREEK 5408 0x1F46, // 1F46..1F47; UNKNOWN 5409 0x1F48, // 1F48..1F4D; GREEK 5410 0x1F4E, // 1F4E..1F4F; UNKNOWN 5411 0x1F50, // 1F50..1F57; GREEK 5412 0x1F58, // 1F58 ; UNKNOWN 5413 0x1F59, // 1F59 ; GREEK 5414 0x1F5A, // 1F5A ; UNKNOWN 5415 0x1F5B, // 1F5B ; GREEK 5416 0x1F5C, // 1F5C ; UNKNOWN 5417 0x1F5D, // 1F5D ; GREEK 5418 0x1F5E, // 1F5E ; UNKNOWN 5419 0x1F5F, // 1F5F..1F7D; GREEK 5420 0x1F7E, // 1F7E..1F7F; UNKNOWN 5421 0x1F80, // 1F80..1FB4; GREEK 5422 0x1FB5, // 1FB5 ; UNKNOWN 5423 0x1FB6, // 1FB6..1FC4; GREEK 5424 0x1FC5, // 1FC5 ; UNKNOWN 5425 0x1FC6, // 1FC6..1FD3; GREEK 5426 0x1FD4, // 1FD4..1FD5; UNKNOWN 5427 0x1FD6, // 1FD6..1FDB; GREEK 5428 0x1FDC, // 1FDC ; UNKNOWN 5429 0x1FDD, // 1FDD..1FEF; GREEK 5430 0x1FF0, // 1FF0..1FF1; UNKNOWN 5431 0x1FF2, // 1FF2..1FF4; GREEK 5432 0x1FF5, // 1FF5 ; UNKNOWN 5433 0x1FF6, // 1FF6..1FFE; GREEK 5434 0x1FFF, // 1FFF ; UNKNOWN 5435 0x2000, // 2000..200B; COMMON 5436 0x200C, // 200C..200D; INHERITED 5437 0x200E, // 200E..2064; COMMON 5438 0x2065, // 2065 ; UNKNOWN 5439 0x2066, // 2066..2070; COMMON 5440 0x2071, // 2071 ; LATIN 5441 0x2072, // 2072..2073; UNKNOWN 5442 0x2074, // 2074..207E; COMMON 5443 0x207F, // 207F ; LATIN 5444 0x2080, // 2080..208E; COMMON 5445 0x208F, // 208F ; UNKNOWN 5446 0x2090, // 2090..209C; LATIN 5447 0x209D, // 209D..209F; UNKNOWN 5448 0x20A0, // 20A0..20BF; COMMON 5449 0x20C0, // 20C0..20CF; UNKNOWN 5450 0x20D0, // 20D0..20F0; INHERITED 5451 0x20F1, // 20F1..20FF; UNKNOWN 5452 0x2100, // 2100..2125; COMMON 5453 0x2126, // 2126 ; GREEK 5454 0x2127, // 2127..2129; COMMON 5455 0x212A, // 212A..212B; LATIN 5456 0x212C, // 212C..2131; COMMON 5457 0x2132, // 2132 ; LATIN 5458 0x2133, // 2133..214D; COMMON 5459 0x214E, // 214E ; LATIN 5460 0x214F, // 214F..215F; COMMON 5461 0x2160, // 2160..2188; LATIN 5462 0x2189, // 2189..218B; COMMON 5463 0x218C, // 218C..218F; UNKNOWN 5464 0x2190, // 2190..2426; COMMON 5465 0x2427, // 2427..243F; UNKNOWN 5466 0x2440, // 2440..244A; COMMON 5467 0x244B, // 244B..245F; UNKNOWN 5468 0x2460, // 2460..27FF; COMMON 5469 0x2800, // 2800..28FF; BRAILLE 5470 0x2900, // 2900..2B73; COMMON 5471 0x2B74, // 2B74..2B75; UNKNOWN 5472 0x2B76, // 2B76..2B95; COMMON 5473 0x2B96, // 2B96..2B97; UNKNOWN 5474 0x2B98, // 2B98..2BC8; COMMON 5475 0x2BC9, // 2BC9 ; UNKNOWN 5476 0x2BCA, // 2BCA..2BFE; COMMON 5477 0x2BFF, // 2BFF; UNKNOWN 5478 0x2C00, // 2C00..2C2E; GLAGOLITIC 5479 0x2C2F, // 2C2F ; UNKNOWN 5480 0x2C30, // 2C30..2C5E; GLAGOLITIC 5481 0x2C5F, // 2C5F ; UNKNOWN 5482 0x2C60, // 2C60..2C7F; LATIN 5483 0x2C80, // 2C80..2CF3; COPTIC 5484 0x2CF4, // 2CF4..2CF8; UNKNOWN 5485 0x2CF9, // 2CF9..2CFF; COPTIC 5486 0x2D00, // 2D00..2D25; GEORGIAN 5487 0x2D26, // 2D26 ; UNKNOWN 5488 0x2D27, // 2D27 ; GEORGIAN 5489 0x2D28, // 2D28..2D2C; UNKNOWN 5490 0x2D2D, // 2D2D ; GEORGIAN 5491 0x2D2E, // 2D2E..2D2F; UNKNOWN 5492 0x2D30, // 2D30..2D67; TIFINAGH 5493 0x2D68, // 2D68..2D6E; UNKNOWN 5494 0x2D6F, // 2D6F..2D70; TIFINAGH 5495 0x2D71, // 2D71..2D7E; UNKNOWN 5496 0x2D7F, // 2D7F ; TIFINAGH 5497 0x2D80, // 2D80..2D96; ETHIOPIC 5498 0x2D97, // 2D97..2D9F; UNKNOWN 5499 0x2DA0, // 2DA0..2DA6; ETHIOPIC 5500 0x2DA7, // 2DA7 ; UNKNOWN 5501 0x2DA8, // 2DA8..2DAE; ETHIOPIC 5502 0x2DAF, // 2DAF ; UNKNOWN 5503 0x2DB0, // 2DB0..2DB6; ETHIOPIC 5504 0x2DB7, // 2DB7 ; UNKNOWN 5505 0x2DB8, // 2DB8..2DBE; ETHIOPIC 5506 0x2DBF, // 2DBF ; UNKNOWN 5507 0x2DC0, // 2DC0..2DC6; ETHIOPIC 5508 0x2DC7, // 2DC7 ; UNKNOWN 5509 0x2DC8, // 2DC8..2DCE; ETHIOPIC 5510 0x2DCF, // 2DCF ; UNKNOWN 5511 0x2DD0, // 2DD0..2DD6; ETHIOPIC 5512 0x2DD7, // 2DD7 ; UNKNOWN 5513 0x2DD8, // 2DD8..2DDE; ETHIOPIC 5514 0x2DDF, // 2DDF ; UNKNOWN 5515 0x2DE0, // 2DE0..2DFF; CYRILLIC 5516 0x2E00, // 2E00..2E4E; COMMON 5517 0x2E4F, // 2E4F..2E7F; UNKNOWN 5518 0x2E80, // 2E80..2E99; HAN 5519 0x2E9A, // 2E9A ; UNKNOWN 5520 0x2E9B, // 2E9B..2EF3; HAN 5521 0x2EF4, // 2EF4..2EFF; UNKNOWN 5522 0x2F00, // 2F00..2FD5; HAN 5523 0x2FD6, // 2FD6..2FEF; UNKNOWN 5524 0x2FF0, // 2FF0..2FFB; COMMON 5525 0x2FFC, // 2FFC..2FFF; UNKNOWN 5526 0x3000, // 3000..3004; COMMON 5527 0x3005, // 3005 ; HAN 5528 0x3006, // 3006 ; COMMON 5529 0x3007, // 3007 ; HAN 5530 0x3008, // 3008..3020; COMMON 5531 0x3021, // 3021..3029; HAN 5532 0x302A, // 302A..302D; INHERITED 5533 0x302E, // 302E..302F; HANGUL 5534 0x3030, // 3030..3037; COMMON 5535 0x3038, // 3038..303B; HAN 5536 0x303C, // 303C..303F; COMMON 5537 0x3040, // 3040 ; UNKNOWN 5538 0x3041, // 3041..3096; HIRAGANA 5539 0x3097, // 3097..3098; UNKNOWN 5540 0x3099, // 3099..309A; INHERITED 5541 0x309B, // 309B..309C; COMMON 5542 0x309D, // 309D..309F; HIRAGANA 5543 0x30A0, // 30A0 ; COMMON 5544 0x30A1, // 30A1..30FA; KATAKANA 5545 0x30FB, // 30FB..30FC; COMMON 5546 0x30FD, // 30FD..30FF; KATAKANA 5547 0x3100, // 3100..3104; UNKNOWN 5548 0x3105, // 3105..312F; BOPOMOFO 5549 0x3130, // 3130; UNKNOWN 5550 0x3131, // 3131..318E; HANGUL 5551 0x318F, // 318F ; UNKNOWN 5552 0x3190, // 3190..319F; COMMON 5553 0x31A0, // 31A0..31BA; BOPOMOFO 5554 0x31BB, // 31BB..31BF; UNKNOWN 5555 0x31C0, // 31C0..31E3; COMMON 5556 0x31E4, // 31E4..31EF; UNKNOWN 5557 0x31F0, // 31F0..31FF; KATAKANA 5558 0x3200, // 3200..321E; HANGUL 5559 0x321F, // 321F ; UNKNOWN 5560 0x3220, // 3220..325F; COMMON 5561 0x3260, // 3260..327E; HANGUL 5562 0x327F, // 327F..32CF; COMMON 5563 0x32D0, // 32D0..32FE; KATAKANA 5564 0x32FF, // 32FF ; COMMON 5565 0x3300, // 3300..3357; KATAKANA 5566 0x3358, // 3358..33FF; COMMON 5567 0x3400, // 3400..4DB5; HAN 5568 0x4DB6, // 4DB6..4DBF; UNKNOWN 5569 0x4DC0, // 4DC0..4DFF; COMMON 5570 0x4E00, // 4E00..9FEF; HAN 5571 0x9FF0, // 9FF0..9FFF; UNKNOWN 5572 0xA000, // A000..A48C; YI 5573 0xA48D, // A48D..A48F; UNKNOWN 5574 0xA490, // A490..A4C6; YI 5575 0xA4C7, // A4C7..A4CF; UNKNOWN 5576 0xA4D0, // A4D0..A4FF; LISU 5577 0xA500, // A500..A62B; VAI 5578 0xA62C, // A62C..A63F; UNKNOWN 5579 0xA640, // A640..A69F; CYRILLIC 5580 0xA6A0, // A6A0..A6F7; BAMUM 5581 0xA6F8, // A6F8..A6FF; UNKNOWN 5582 0xA700, // A700..A721; COMMON 5583 0xA722, // A722..A787; LATIN 5584 0xA788, // A788..A78A; COMMON 5585 0xA78B, // A78B..A7B9; LATIN 5586 0xA7C0, // A7C0..A7F6; UNKNOWN 5587 0xA7F7, // A7F7..A7FF; LATIN 5588 0xA800, // A800..A82B; SYLOTI_NAGRI 5589 0xA82C, // A82C..A82F; UNKNOWN 5590 0xA830, // A830..A839; COMMON 5591 0xA83A, // A83A..A83F; UNKNOWN 5592 0xA840, // A840..A877; PHAGS_PA 5593 0xA878, // A878..A87F; UNKNOWN 5594 0xA880, // A880..A8C5; SAURASHTRA 5595 0xA8C6, // A8C6..A8CD; UNKNOWN 5596 0xA8CE, // A8CE..A8D9; SAURASHTRA 5597 0xA8DA, // A8DA..A8DF; UNKNOWN 5598 0xA8E0, // A8E0..A8FF; DEVANAGARI 5599 0xA900, // A900..A92D; KAYAH_LI 5600 0xA92E, // A92E ; COMMON 5601 0xA92F, // A92F ; KAYAH_LI 5602 0xA930, // A930..A953; REJANG 5603 0xA954, // A954..A95E; UNKNOWN 5604 0xA95F, // A95F ; REJANG 5605 0xA960, // A960..A97C; HANGUL 5606 0xA97D, // A97D..A97F; UNKNOWN 5607 0xA980, // A980..A9CD; JAVANESE 5608 0xA9CE, // A9CE ; UNKNOWN 5609 0xA9CF, // A9CF ; COMMON 5610 0xA9D0, // A9D0..A9D9; JAVANESE 5611 0xA9DA, // A9DA..A9DD; UNKNOWN 5612 0xA9DE, // A9DE..A9DF; JAVANESE 5613 0xA9E0, // A9E0..A9FE; MYANMAR 5614 0xA9FF, // A9FF ; UNKNOWN 5615 0xAA00, // AA00..AA36; CHAM 5616 0xAA37, // AA37..AA3F; UNKNOWN 5617 0xAA40, // AA40..AA4D; CHAM 5618 0xAA4E, // AA4E..AA4F; UNKNOWN 5619 0xAA50, // AA50..AA59; CHAM 5620 0xAA5A, // AA5A..AA5B; UNKNOWN 5621 0xAA5C, // AA5C..AA5F; CHAM 5622 0xAA60, // AA60..AA7F; MYANMAR 5623 0xAA80, // AA80..AAC2; TAI_VIET 5624 0xAAC3, // AAC3..AADA; UNKNOWN 5625 0xAADB, // AADB..AADF; TAI_VIET 5626 0xAAE0, // AAE0..AAF6; MEETEI_MAYEK 5627 0xAAF7, // AAF7..AB00; UNKNOWN 5628 0xAB01, // AB01..AB06; ETHIOPIC 5629 0xAB07, // AB07..AB08; UNKNOWN 5630 0xAB09, // AB09..AB0E; ETHIOPIC 5631 0xAB0F, // AB0F..AB10; UNKNOWN 5632 0xAB11, // AB11..AB16; ETHIOPIC 5633 0xAB17, // AB17..AB1F; UNKNOWN 5634 0xAB20, // AB20..AB26; ETHIOPIC 5635 0xAB27, // AB27 ; UNKNOWN 5636 0xAB28, // AB28..AB2E; ETHIOPIC 5637 0xAB2F, // AB2F ; UNKNOWN 5638 0xAB30, // AB30..AB5A; LATIN 5639 0xAB5B, // AB5B ; COMMON 5640 0xAB5C, // AB5C..AB64; LATIN 5641 0xAB65, // AB65 ; GREEK 5642 0xAB66, // AB66..AB6F; UNKNOWN 5643 0xAB70, // AB70..ABBF; CHEROKEE 5644 0xABC0, // ABC0..ABED; MEETEI_MAYEK 5645 0xABEE, // ABEE..ABEF; UNKNOWN 5646 0xABF0, // ABF0..ABF9; MEETEI_MAYEK 5647 0xABFA, // ABFA..ABFF; UNKNOWN 5648 0xAC00, // AC00..D7A3; HANGUL 5649 0xD7A4, // D7A4..D7AF; UNKNOWN 5650 0xD7B0, // D7B0..D7C6; HANGUL 5651 0xD7C7, // D7C7..D7CA; UNKNOWN 5652 0xD7CB, // D7CB..D7FB; HANGUL 5653 0xD7FC, // D7FC..F8FF; UNKNOWN 5654 0xF900, // F900..FA6D; HAN 5655 0xFA6E, // FA6E..FA6F; UNKNOWN 5656 0xFA70, // FA70..FAD9; HAN 5657 0xFADA, // FADA..FAFF; UNKNOWN 5658 0xFB00, // FB00..FB06; LATIN 5659 0xFB07, // FB07..FB12; UNKNOWN 5660 0xFB13, // FB13..FB17; ARMENIAN 5661 0xFB18, // FB18..FB1C; UNKNOWN 5662 0xFB1D, // FB1D..FB36; HEBREW 5663 0xFB37, // FB37 ; UNKNOWN 5664 0xFB38, // FB38..FB3C; HEBREW 5665 0xFB3D, // FB3D ; UNKNOWN 5666 0xFB3E, // FB3E ; HEBREW 5667 0xFB3F, // FB3F ; UNKNOWN 5668 0xFB40, // FB40..FB41; HEBREW 5669 0xFB42, // FB42 ; UNKNOWN 5670 0xFB43, // FB43..FB44; HEBREW 5671 0xFB45, // FB45 ; UNKNOWN 5672 0xFB46, // FB46..FB4F; HEBREW 5673 0xFB50, // FB50..FBC1; ARABIC 5674 0xFBC2, // FBC2..FBD2; UNKNOWN 5675 0xFBD3, // FBD3..FD3D; ARABIC 5676 0xFD3E, // FD3E..FD3F; COMMON 5677 0xFD40, // FD40..FD4F; UNKNOWN 5678 0xFD50, // FD50..FD8F; ARABIC 5679 0xFD90, // FD90..FD91; UNKNOWN 5680 0xFD92, // FD92..FDC7; ARABIC 5681 0xFDC8, // FDC8..FDEF; UNKNOWN 5682 0xFDF0, // FDF0..FDFD; ARABIC 5683 0xFDFE, // FDFE..FDFF; UNKNOWN 5684 0xFE00, // FE00..FE0F; INHERITED 5685 0xFE10, // FE10..FE19; COMMON 5686 0xFE1A, // FE1A..FE1F; UNKNOWN 5687 0xFE20, // FE20..FE2D; INHERITED 5688 0xFE2E, // FE2E..FE2F; CYRILLIC 5689 0xFE30, // FE30..FE52; COMMON 5690 0xFE53, // FE53 ; UNKNOWN 5691 0xFE54, // FE54..FE66; COMMON 5692 0xFE67, // FE67 ; UNKNOWN 5693 0xFE68, // FE68..FE6B; COMMON 5694 0xFE6C, // FE6C..FE6F; UNKNOWN 5695 0xFE70, // FE70..FE74; ARABIC 5696 0xFE75, // FE75 ; UNKNOWN 5697 0xFE76, // FE76..FEFC; ARABIC 5698 0xFEFD, // FEFD..FEFE; UNKNOWN 5699 0xFEFF, // FEFF ; COMMON 5700 0xFF00, // FF00 ; UNKNOWN 5701 0xFF01, // FF01..FF20; COMMON 5702 0xFF21, // FF21..FF3A; LATIN 5703 0xFF3B, // FF3B..FF40; COMMON 5704 0xFF41, // FF41..FF5A; LATIN 5705 0xFF5B, // FF5B..FF65; COMMON 5706 0xFF66, // FF66..FF6F; KATAKANA 5707 0xFF70, // FF70 ; COMMON 5708 0xFF71, // FF71..FF9D; KATAKANA 5709 0xFF9E, // FF9E..FF9F; COMMON 5710 0xFFA0, // FFA0..FFBE; HANGUL 5711 0xFFBF, // FFBF..FFC1; UNKNOWN 5712 0xFFC2, // FFC2..FFC7; HANGUL 5713 0xFFC8, // FFC8..FFC9; UNKNOWN 5714 0xFFCA, // FFCA..FFCF; HANGUL 5715 0xFFD0, // FFD0..FFD1; UNKNOWN 5716 0xFFD2, // FFD2..FFD7; HANGUL 5717 0xFFD8, // FFD8..FFD9; UNKNOWN 5718 0xFFDA, // FFDA..FFDC; HANGUL 5719 0xFFDD, // FFDD..FFDF; UNKNOWN 5720 0xFFE0, // FFE0..FFE6; COMMON 5721 0xFFE7, // FFE7 ; UNKNOWN 5722 0xFFE8, // FFE8..FFEE; COMMON 5723 0xFFEF, // FFEF..FFF8; UNKNOWN 5724 0xFFF9, // FFF9..FFFD; COMMON 5725 0xFFFE, // FFFE..FFFF; UNKNOWN 5726 0x10000, // 10000..1000B; LINEAR_B 5727 0x1000C, // 1000C ; UNKNOWN 5728 0x1000D, // 1000D..10026; LINEAR_B 5729 0x10027, // 10027 ; UNKNOWN 5730 0x10028, // 10028..1003A; LINEAR_B 5731 0x1003B, // 1003B ; UNKNOWN 5732 0x1003C, // 1003C..1003D; LINEAR_B 5733 0x1003E, // 1003E ; UNKNOWN 5734 0x1003F, // 1003F..1004D; LINEAR_B 5735 0x1004E, // 1004E..1004F; UNKNOWN 5736 0x10050, // 10050..1005D; LINEAR_B 5737 0x1005E, // 1005E..1007F; UNKNOWN 5738 0x10080, // 10080..100FA; LINEAR_B 5739 0x100FB, // 100FB..100FF; UNKNOWN 5740 0x10100, // 10100..10102; COMMON 5741 0x10103, // 10103..10106; UNKNOWN 5742 0x10107, // 10107..10133; COMMON 5743 0x10134, // 10134..10136; UNKNOWN 5744 0x10137, // 10137..1013F; COMMON 5745 0x10140, // 10140..1018E; GREEK 5746 0x1018F, // 1018F ; UNKNOWN 5747 0x10190, // 10190..1019B; COMMON 5748 0x1019C, // 1019C..1019F; UNKNOWN 5749 0x101A0, // 101A0 ; GREEK 5750 0x101A1, // 101A1..101CF; UNKNOWN 5751 0x101D0, // 101D0..101FC; COMMON 5752 0x101FD, // 101FD ; INHERITED 5753 0x101FE, // 101FE..1027F; UNKNOWN 5754 0x10280, // 10280..1029C; LYCIAN 5755 0x1029D, // 1029D..1029F; UNKNOWN 5756 0x102A0, // 102A0..102D0; CARIAN 5757 0x102D1, // 102D1..102DF; UNKNOWN 5758 0x102E0, // 102E0 ; INHERITED 5759 0x102E1, // 102E1..102FB; COMMON 5760 0x102FC, // 102FC..102FF; UNKNOWN 5761 0x10300, // 10300..10323; OLD_ITALIC 5762 0x10324, // 10324..1032C; UNKNOWN 5763 0x1032D, // 1032D..1032F; OLD_ITALIC 5764 0x10330, // 10330..1034A; GOTHIC 5765 0x1034B, // 1034B..1034F; UNKNOWN 5766 0x10350, // 10350..1037A; OLD_PERMIC 5767 0x1037B, // 1037B..1037F; UNKNOWN 5768 0x10380, // 10380..1039D; UGARITIC 5769 0x1039E, // 1039E ; UNKNOWN 5770 0x1039F, // 1039F ; UGARITIC 5771 0x103A0, // 103A0..103C3; OLD_PERSIAN 5772 0x103C4, // 103C4..103C7; UNKNOWN 5773 0x103C8, // 103C8..103D5; OLD_PERSIAN 5774 0x103D6, // 103D6..103FF; UNKNOWN 5775 0x10400, // 10400..1044F; DESERET 5776 0x10450, // 10450..1047F; SHAVIAN 5777 0x10480, // 10480..1049D; OSMANYA 5778 0x1049E, // 1049E..1049F; UNKNOWN 5779 0x104A0, // 104A0..104A9; OSMANYA 5780 0x104AA, // 104AA..104AF; UNKNOWN 5781 0x104B0, // 104B0..104D3; OSAGE 5782 0x104D4, // 104D4..104D7; UNKNOWN 5783 0x104D8, // 104D8..104FB; OSAGE 5784 0x104FC, // 104FC..104FF; UNKNOWN 5785 0x10500, // 10500..10527; ELBASAN 5786 0x10528, // 10528..1052F; UNKNOWN 5787 0x10530, // 10530..10563; CAUCASIAN_ALBANIAN 5788 0x10564, // 10564..1056E; UNKNOWN 5789 0x1056F, // 1056F ; CAUCASIAN_ALBANIAN 5790 0x10570, // 10570..105FF; UNKNOWN 5791 0x10600, // 10600..10736; LINEAR_A 5792 0x10737, // 10737..1073F; UNKNOWN 5793 0x10740, // 10740..10755; LINEAR_A 5794 0x10756, // 10756..1075F; UNKNOWN 5795 0x10760, // 10760..10767; LINEAR_A 5796 0x10768, // 10768..107FF; UNKNOWN 5797 0x10800, // 10800..10805; CYPRIOT 5798 0x10806, // 10806..10807; UNKNOWN 5799 0x10808, // 10808 ; CYPRIOT 5800 0x10809, // 10809 ; UNKNOWN 5801 0x1080A, // 1080A..10835; CYPRIOT 5802 0x10836, // 10836 ; UNKNOWN 5803 0x10837, // 10837..10838; CYPRIOT 5804 0x10839, // 10839..1083B; UNKNOWN 5805 0x1083C, // 1083C ; CYPRIOT 5806 0x1083D, // 1083D..1083E; UNKNOWN 5807 0x1083F, // 1083F ; CYPRIOT 5808 0x10840, // 10840..10855; IMPERIAL_ARAMAIC 5809 0x10856, // 10856 ; UNKNOWN 5810 0x10857, // 10857..1085F; IMPERIAL_ARAMAIC 5811 0x10860, // 10860..1087F; PALMYRENE 5812 0x10880, // 10880..1089E; NABATAEAN 5813 0x1089F, // 1089F..108A6; UNKNOWN 5814 0x108A7, // 108A7..108AF; NABATAEAN 5815 0x108B0, // 108B0..108DF; UNKNOWN 5816 0x108E0, // 108E0..108F2; HATRAN 5817 0x108F3, // 108F3 ; UNKNOWN 5818 0x108F4, // 108F4..108F5; HATRAN 5819 0x108F6, // 108F6..108FA; UNKNOWN 5820 0x108FB, // 108FB..108FF; HATRAN 5821 0x10900, // 10900..1091B; PHOENICIAN 5822 0x1091C, // 1091C..1091E; UNKNOWN 5823 0x1091F, // 1091F ; PHOENICIAN 5824 0x10920, // 10920..10939; LYDIAN 5825 0x1093A, // 1093A..1093E; UNKNOWN 5826 0x1093F, // 1093F ; LYDIAN 5827 0x10940, // 10940..1097F; UNKNOWN 5828 0x10980, // 10980..1099F; MEROITIC_HIEROGLYPHS 5829 0x109A0, // 109A0..109B7; MEROITIC_CURSIVE 5830 0x109B8, // 109B8..109BB; UNKNOWN 5831 0x109BC, // 109BC..109CF; MEROITIC_CURSIVE 5832 0x109D0, // 109D0..109D1; UNKNOWN 5833 0x109D2, // 109D2..109FF; MEROITIC_CURSIVE 5834 0x10A00, // 10A00..10A03; KHAROSHTHI 5835 0x10A04, // 10A04 ; UNKNOWN 5836 0x10A05, // 10A05..10A06; KHAROSHTHI 5837 0x10A07, // 10A07..10A0B; UNKNOWN 5838 0x10A0C, // 10A0C..10A13; KHAROSHTHI 5839 0x10A14, // 10A14 ; UNKNOWN 5840 0x10A15, // 10A15..10A17; KHAROSHTHI 5841 0x10A18, // 10A18 ; UNKNOWN 5842 0x10A19, // 10A19..10A35; KHAROSHTHI 5843 0x10A36, // 10A36..10A37; UNKNOWN 5844 0x10A38, // 10A38..10A3A; KHAROSHTHI 5845 0x10A3B, // 10A3B..10A3E; UNKNOWN 5846 0x10A3F, // 10A3F..10A48; KHAROSHTHI 5847 0x10A49, // 10A49..10A4F; UNKNOWN 5848 0x10A50, // 10A50..10A58; KHAROSHTHI 5849 0x10A59, // 10A59..10A5F; UNKNOWN 5850 0x10A60, // 10A60..10A7F; OLD_SOUTH_ARABIAN 5851 0x10A80, // 10A80..10A9F; OLD_NORTH_ARABIAN 5852 0x10AA0, // 10AA0..10ABF; UNKNOWN 5853 0x10AC0, // 10AC0..10AE6; MANICHAEAN 5854 0x10AE7, // 10AE7..10AEA; UNKNOWN 5855 0x10AEB, // 10AEB..10AF6; MANICHAEAN 5856 0x10AF7, // 10AF7..10AFF; UNKNOWN 5857 0x10B00, // 10B00..10B35; AVESTAN 5858 0x10B36, // 10B36..10B38; UNKNOWN 5859 0x10B39, // 10B39..10B3F; AVESTAN 5860 0x10B40, // 10B40..10B55; INSCRIPTIONAL_PARTHIAN 5861 0x10B56, // 10B56..10B57; UNKNOWN 5862 0x10B58, // 10B58..10B5F; INSCRIPTIONAL_PARTHIAN 5863 0x10B60, // 10B60..10B72; INSCRIPTIONAL_PAHLAVI 5864 0x10B73, // 10B73..10B77; UNKNOWN 5865 0x10B78, // 10B78..10B7F; INSCRIPTIONAL_PAHLAVI 5866 0x10B80, // 10B80..10B91; PSALTER_PAHLAVI 5867 0x10B92, // 10B92..10B98; UNKNOWN 5868 0x10B99, // 10B99..10B9C; PSALTER_PAHLAVI 5869 0x10B9D, // 10B9D..10BA8; UNKNOWN 5870 0x10BA9, // 10BA9..10BAF; PSALTER_PAHLAVI 5871 0x10BB0, // 10BB0..10BFF; UNKNOWN 5872 0x10C00, // 10C00..10C48; OLD_TURKIC 5873 0x10C49, // 10C49..10C7F; UNKNOWN 5874 0x10C80, // 10C80..10CB2; OLD_HUNGARIAN 5875 0x10CB3, // 10CB3..10CBF; UNKNOWN 5876 0x10CC0, // 10CC0..10CF2; OLD_HUNGARIAN 5877 0x10CF3, // 10CF3..10CF9; UNKNOWN 5878 0x10CFA, // 10CFA..10CFF; OLD_HUNGARIAN 5879 0x10D00, // 10D00..10D27; HANIFI ROHINGYA 5880 0x10D28, // 10D28..10D29; UNKNOWN 5881 0x10D30, // 10D30..10D39; HANIFI ROHINGYA 5882 0x10D3A, // 10D3A..10E5F; UNKNOWN 5883 0x10E60, // 10E60..10E7E; ARABIC 5884 0x10E7F, // 10E7F..10EFF; UNKNOWN 5885 0x10F00, // 10F00..10F27; OLD SOGDIAN 5886 0x10F28, // 10F28..10F2F; UNKNOWN 5887 0x10F30, // 10F30..10F59; SOGDIAN 5888 0x10F5A, // 10F5A..10FFF; UNKNOWN 5889 0x11000, // 11000..1104D; BRAHMI 5890 0x1104E, // 1104E..11051; UNKNOWN 5891 0x11052, // 11052..1106F; BRAHMI 5892 0x11070, // 11070..1107E; UNKNOWN 5893 0x1107F, // 1107F ; BRAHMI 5894 0x11080, // 11080..110C1; KAITHI 5895 0x110C2, // 110C2..110CC; UNKNOWN 5896 0x110CD, // 110CD ; KAITHI 5897 0x110CE, // 110CE..110CF; UNKNOWN 5898 0x110D0, // 110D0..110E8; SORA_SOMPENG 5899 0x110E9, // 110E9..110EF; UNKNOWN 5900 0x110F0, // 110F0..110F9; SORA_SOMPENG 5901 0x110FA, // 110FA..110FF; UNKNOWN 5902 0x11100, // 11100..11134; CHAKMA 5903 0x11135, // 11135 ; UNKNOWN 5904 0x11136, // 11136..11146; CHAKMA 5905 0x11147, // 11147..1114F; UNKNOWN 5906 0x11150, // 11150..11176; MAHAJANI 5907 0x11177, // 11177..1117F; UNKNOWN 5908 0x11180, // 11180..111CD; SHARADA 5909 0x111CE, // 111CE..111CF; UNKNOWN 5910 0x111D0, // 111D0..111DF; SHARADA 5911 0x111E0, // 111E0 ; UNKNOWN 5912 0x111E1, // 111E1..111F4; SINHALA 5913 0x111F5, // 111F5..111FF; UNKNOWN 5914 0x11200, // 11200..11211; KHOJKI 5915 0x11212, // 11212 ; UNKNOWN 5916 0x11213, // 11213..1123E; KHOJKI 5917 0x1123F, // 1123F..1127F; UNKNOWN 5918 0x11280, // 11280..11286; MULTANI 5919 0x11287, // 11287 ; UNKNOWN 5920 0x11288, // 11288 ; MULTANI 5921 0x11289, // 11289 ; UNKNOWN 5922 0x1128A, // 1128A..1128D; MULTANI 5923 0x1128E, // 1128E ; UNKNOWN 5924 0x1128F, // 1128F..1129D; MULTANI 5925 0x1129E, // 1129E ; UNKNOWN 5926 0x1129F, // 1129F..112A9; MULTANI 5927 0x112AA, // 112AA..112AF; UNKNOWN 5928 0x112B0, // 112B0..112EA; KHUDAWADI 5929 0x112EB, // 112EB..112EF; UNKNOWN 5930 0x112F0, // 112F0..112F9; KHUDAWADI 5931 0x112FA, // 112FA..112FF; UNKNOWN 5932 0x11300, // 11300..11303; GRANTHA 5933 0x11304, // 11304 ; UNKNOWN 5934 0x11305, // 11305..1130C; GRANTHA 5935 0x1130D, // 1130D..1130E; UNKNOWN 5936 0x1130F, // 1130F..11310; GRANTHA 5937 0x11311, // 11311..11312; UNKNOWN 5938 0x11313, // 11313..11328; GRANTHA 5939 0x11329, // 11329 ; UNKNOWN 5940 0x1132A, // 1132A..11330; GRANTHA 5941 0x11331, // 11331 ; UNKNOWN 5942 0x11332, // 11332..11333; GRANTHA 5943 0x11334, // 11334 ; UNKNOWN 5944 0x11335, // 11335..11339; GRANTHA 5945 0x1133A, // 1133A ; UNKNOWN 5946 0x1133B, // 1133B ; INHERITED 5947 0x1133C, // 1133C..11344; GRANTHA 5948 0x11345, // 11345..11346; UNKNOWN 5949 0x11347, // 11347..11348; GRANTHA 5950 0x11349, // 11349..1134A; UNKNOWN 5951 0x1134B, // 1134B..1134D; GRANTHA 5952 0x1134E, // 1134E..1134F; UNKNOWN 5953 0x11350, // 11350 ; GRANTHA 5954 0x11351, // 11351..11356; UNKNOWN 5955 0x11357, // 11357 ; GRANTHA 5956 0x11358, // 11358..1135C; UNKNOWN 5957 0x1135D, // 1135D..11363; GRANTHA 5958 0x11364, // 11364..11365; UNKNOWN 5959 0x11366, // 11366..1136C; GRANTHA 5960 0x1136D, // 1136D..1136F; UNKNOWN 5961 0x11370, // 11370..11374; GRANTHA 5962 0x11375, // 11375..113FF; UNKNOWN 5963 0x11400, // 11400..11459; NEWA 5964 0x1145A, // 1145A ; UNKNOWN 5965 0x1145B, // 1145B ; NEWA 5966 0x1145C, // 1145C ; UNKNOWN 5967 0x1145D, // 1145D..1145E; NEWA 5968 0x1145F, // 1145F..1147F; UNKNOWN 5969 0x11480, // 11480..114C7; TIRHUTA 5970 0x114C8, // 114C8..114CF; UNKNOWN 5971 0x114D0, // 114D0..114D9; TIRHUTA 5972 0x114DA, // 114DA..1157F; UNKNOWN 5973 0x11580, // 11580..115B5; SIDDHAM 5974 0x115B6, // 115B6..115B7; UNKNOWN 5975 0x115B8, // 115B8..115DD; SIDDHAM 5976 0x115DE, // 115DE..115FF; UNKNOWN 5977 0x11600, // 11600..11644; MODI 5978 0x11645, // 11645..1164F; UNKNOWN 5979 0x11650, // 11650..11659; MODI 5980 0x1165A, // 1165A..1165F; UNKNOWN 5981 0x11660, // 11660..1166C; MONGOLIAN 5982 0X1166D, // 1166D..1167F; UNKNOWN 5983 0x11680, // 11680..116B7; TAKRI 5984 0x116B8, // 116B8..116BF; UNKNOWN 5985 0x116C0, // 116C0..116C9; TAKRI 5986 0x116CA, // 116CA..116FF; UNKNOWN 5987 0x11700, // 11700..1171A; AHOM 5988 0x1171B, // 1171B..1171C; UNKNOWN 5989 0x1171D, // 1171D..1172B; AHOM 5990 0x1172C, // 1172C..1172F; UNKNOWN 5991 0x11730, // 11730..1173F; AHOM 5992 0x11740, // 11740..117FF; UNKNOWN 5993 0x11800, // 11800..1183B; DOGRA 5994 0x1183C, // 1183C..1189F; UNKNOWN 5995 0x118A0, // 118A0..118F2; WARANG_CITI 5996 0x118F3, // 118F3..118FE; UNKNOWN 5997 0x118FF, // 118FF ; WARANG_CITI 5998 0x11900, // 11900..119FF; UNKNOWN 5999 0x11A00, // 11A00..11A47; ZANABAZAR_SQUARE 6000 0X11A48, // 11A48..11A4F; UNKNOWN 6001 0x11A50, // 11A50..11A83; SOYOMBO 6002 0x11A84, // 11A84..11A85; UNKNOWN 6003 0x11A86, // 11A86..11AA2; SOYOMBO 6004 0x11AA3, // 11AA3..11ABF; UNKNOWN 6005 0x11AC0, // 11AC0..11AF8; PAU_CIN_HAU 6006 0x11AF9, // 11AF9..11BFF; UNKNOWN 6007 0x11C00, // 11C00..11C08; BHAIKSUKI 6008 0x11C09, // 11C09 ; UNKNOWN 6009 0x11C0A, // 11C0A..11C36; BHAIKSUKI 6010 0x11C37, // 11C37 ; UNKNOWN 6011 0x11C38, // 11C38..11C45; BHAIKSUKI 6012 0x11C46, // 11C46..11C49; UNKNOWN 6013 0x11C50, // 11C50..11C6C; BHAIKSUKI 6014 0x11C6D, // 11C6D..11C6F; UNKNOWN 6015 0x11C70, // 11C70..11C8F; MARCHEN 6016 0x11C90, // 11C90..11C91; UNKNOWN 6017 0x11C92, // 11C92..11CA7; MARCHEN 6018 0x11CA8, // 11CA8 ; UNKNOWN 6019 0x11CA9, // 11CA9..11CB6; MARCHEN 6020 0x11CB7, // 11CB7..11CFF; UNKNOWN 6021 0x11D00, // 11D00..11D06; MASARAM_GONDI 6022 0x11D07, // 11D07 ; UNKNOWN 6023 0x11D08, // 11D08..11D09; MASARAM_GONDI 6024 0x11D0A, // 11D0A ; UNKNOWN 6025 0x11D0B, // 11D0B..11D36; MASARAM_GONDI 6026 0x11D37, // 11D37..11D39; UNKNOWN 6027 0x11D3A, // 11D3A ; MASARAM_GONDI 6028 0x11D3B, // 11D3B ; UNKNOWN 6029 0x11D3C, // 11D3C..11D3D; MASARAM_GONDI 6030 0x11D3E, // 11D3E ; UNKNOWN 6031 0x11D3F, // 11D3F..11D47; MASARAM_GONDI 6032 0x11D48, // 11D48..11D49, UNKNOWN 6033 0x11D50, // 11D50..11D59; MASARAM_GONDI 6034 0x11D5A, // 11D5A..11D5F; UNKNOWN 6035 0x11D60, // 11D60..11D68; GUNJALA GONDI 6036 0x11D69, // ; UNKNOWN 6037 0x11D6A, // 11D6A..11D8E; GUNJALA GONDI 6038 0x11D8F, // ; UNKNOWN 6039 0x11D90, // 11D90..11D91; GUNJALA GONDI 6040 0x11D92, // ; UNKNOWN 6041 0x11D93, // 11D93..11D98; GUNJALA GONDI 6042 0x11D99, // 11D99 ; UNKNOWN 6043 0x11DA0, // 11DA0..11DA9; GUNJALA GONDI 6044 0x11DAA, // 11DAA..11DFF; UNKNOWN 6045 0x11EE0, // 11EE0..11EF8; MAKASAR 6046 0x11EF9, // 11EF9..11FFF; UNKNOWN 6047 0x12000, // 12000..12399; CUNEIFORM 6048 0x1239A, // 1239A..123FF; UNKNOWN 6049 0x12400, // 12400..1246E; CUNEIFORM 6050 0x1246F, // 1246F ; UNKNOWN 6051 0x12470, // 12470..12474; CUNEIFORM 6052 0x12475, // 12475..1247F; UNKNOWN 6053 0x12480, // 12480..12543; CUNEIFORM 6054 0x12544, // 12544..12FFF; UNKNOWN 6055 0x13000, // 13000..1342E; EGYPTIAN_HIEROGLYPHS 6056 0x1342F, // 1342F..143FF; UNKNOWN 6057 0x14400, // 14400..14646; ANATOLIAN_HIEROGLYPHS 6058 0x14647, // 14647..167FF; UNKNOWN 6059 0x16800, // 16800..16A38; BAMUM 6060 0x16A39, // 16A39..16A3F; UNKNOWN 6061 0x16A40, // 16A40..16A5E; MRO 6062 0x16A5F, // 16A5F ; UNKNOWN 6063 0x16A60, // 16A60..16A69; MRO 6064 0x16A6A, // 16A6A..16A6D; UNKNOWN 6065 0x16A6E, // 16A6E..16A6F; MRO 6066 0x16A70, // 16A70..16ACF; UNKNOWN 6067 0x16AD0, // 16AD0..16AED; BASSA_VAH 6068 0x16AEE, // 16AEE..16AEF; UNKNOWN 6069 0x16AF0, // 16AF0..16AF5; BASSA_VAH 6070 0x16AF6, // 16AF6..16AFF; UNKNOWN 6071 0x16B00, // 16B00..16B45; PAHAWH_HMONG 6072 0x16B46, // 16B46..16B4F; UNKNOWN 6073 0x16B50, // 16B50..16B59; PAHAWH_HMONG 6074 0x16B5A, // 16B5A ; UNKNOWN 6075 0x16B5B, // 16B5B..16B61; PAHAWH_HMONG 6076 0x16B62, // 16B62 ; UNKNOWN 6077 0x16B63, // 16B63..16B77; PAHAWH_HMONG 6078 0x16B78, // 16B78..16B7C; UNKNOWN 6079 0x16B7D, // 16B7D..16B8F; PAHAWH_HMONG 6080 0x16B90, // 16B90..16E3F; UNKNOWN 6081 0x16E40, // 16E40..16E9A; MEDEFAIDRIN 6082 0x16E9B, // 16E9B..16EFF; UNKNOWN 6083 0x16F00, // 16F00..16F44; MIAO 6084 0x16F45, // 16F45..16F4F; UNKNOWN 6085 0x16F50, // 16F50..16F7E; MIAO 6086 0x16F7F, // 16F7F..16F8E; UNKNOWN 6087 0x16F8F, // 16F8F..16F9F; MIAO 6088 0x16FA0, // 16FA0..16FDF; UNKNOWN 6089 0x16FE0, // 16FE0 ; TANGUT 6090 0x16FE1, // 16FE1 ; NUSHU 6091 0x16FE2, // 16FE2..16FFF; UNKNOWN 6092 0x17000, // 17000..187F1; TANGUT 6093 0x187F2, // 187F2..187FF; UNKNOWN 6094 0x18800, // 18800..18AF2; TANGUT 6095 0x18AF3, // 18AF3..1AFFF; UNKNOWN 6096 0x1B000, // 1B000 ; KATAKANA 6097 0x1B001, // 1B001..1B11E; HIRAGANA 6098 0x1B11F, // 1B11F..1B16F; UNKNOWN 6099 0x1B170, // 1B170..1B2FB; NUSHU 6100 0x1B2FC, // 1B2FC..1BBFF; UNKNOWN 6101 0x1BC00, // 1BC00..1BC6A; DUPLOYAN 6102 0x1BC6B, // 1BC6B..1BC6F; UNKNOWN 6103 0x1BC70, // 1BC70..1BC7C; DUPLOYAN 6104 0x1BC7D, // 1BC7D..1BC7F; UNKNOWN 6105 0x1BC80, // 1BC80..1BC88; DUPLOYAN 6106 0x1BC89, // 1BC89..1BC8F; UNKNOWN 6107 0x1BC90, // 1BC90..1BC99; DUPLOYAN 6108 0x1BC9A, // 1BC9A..1BC9B; UNKNOWN 6109 0x1BC9C, // 1BC9C..1BC9F; DUPLOYAN 6110 0x1BCA0, // 1BCA0..1BCA3; COMMON 6111 0x1BCA4, // 1BCA4..1CFFF; UNKNOWN 6112 0x1D000, // 1D000..1D0F5; COMMON 6113 0x1D0F6, // 1D0F6..1D0FF; UNKNOWN 6114 0x1D100, // 1D100..1D126; COMMON 6115 0x1D127, // 1D127..1D128; UNKNOWN 6116 0x1D129, // 1D129..1D166; COMMON 6117 0x1D167, // 1D167..1D169; INHERITED 6118 0x1D16A, // 1D16A..1D17A; COMMON 6119 0x1D17B, // 1D17B..1D182; INHERITED 6120 0x1D183, // 1D183..1D184; COMMON 6121 0x1D185, // 1D185..1D18B; INHERITED 6122 0x1D18C, // 1D18C..1D1A9; COMMON 6123 0x1D1AA, // 1D1AA..1D1AD; INHERITED 6124 0x1D1AE, // 1D1AE..1D1E8; COMMON 6125 0x1D1E9, // 1D1E9..1D1FF; UNKNOWN 6126 0x1D200, // 1D200..1D245; GREEK 6127 0x1D246, // 1D246..1D2DF; UNKNOWN 6128 0x1D2E0, // 1D2E0..1D2F3; COMMON 6129 0x1D2F4, // 1D2F4..1D2FF; UNKNOWN 6130 0x1D300, // 1D300..1D356; COMMON 6131 0x1D357, // 1D357..1D35F; UNKNOWN 6132 0x1D360, // 1D360..1D378; COMMON 6133 0x1D379, // 1D379..1D3FF; UNKNOWN 6134 0x1D400, // 1D400..1D454; COMMON 6135 0x1D455, // 1D455 ; UNKNOWN 6136 0x1D456, // 1D456..1D49C; COMMON 6137 0x1D49D, // 1D49D ; UNKNOWN 6138 0x1D49E, // 1D49E..1D49F; COMMON 6139 0x1D4A0, // 1D4A0..1D4A1; UNKNOWN 6140 0x1D4A2, // 1D4A2 ; COMMON 6141 0x1D4A3, // 1D4A3..1D4A4; UNKNOWN 6142 0x1D4A5, // 1D4A5..1D4A6; COMMON 6143 0x1D4A7, // 1D4A7..1D4A8; UNKNOWN 6144 0x1D4A9, // 1D4A9..1D4AC; COMMON 6145 0x1D4AD, // 1D4AD ; UNKNOWN 6146 0x1D4AE, // 1D4AE..1D4B9; COMMON 6147 0x1D4BA, // 1D4BA ; UNKNOWN 6148 0x1D4BB, // 1D4BB ; COMMON 6149 0x1D4BC, // 1D4BC ; UNKNOWN 6150 0x1D4BD, // 1D4BD..1D4C3; COMMON 6151 0x1D4C4, // 1D4C4 ; UNKNOWN 6152 0x1D4C5, // 1D4C5..1D505; COMMON 6153 0x1D506, // 1D506 ; UNKNOWN 6154 0x1D507, // 1D507..1D50A; COMMON 6155 0x1D50B, // 1D50B..1D50C; UNKNOWN 6156 0x1D50D, // 1D50D..1D514; COMMON 6157 0x1D515, // 1D515 ; UNKNOWN 6158 0x1D516, // 1D516..1D51C; COMMON 6159 0x1D51D, // 1D51D ; UNKNOWN 6160 0x1D51E, // 1D51E..1D539; COMMON 6161 0x1D53A, // 1D53A ; UNKNOWN 6162 0x1D53B, // 1D53B..1D53E; COMMON 6163 0x1D53F, // 1D53F ; UNKNOWN 6164 0x1D540, // 1D540..1D544; COMMON 6165 0x1D545, // 1D545 ; UNKNOWN 6166 0x1D546, // 1D546 ; COMMON 6167 0x1D547, // 1D547..1D549; UNKNOWN 6168 0x1D54A, // 1D54A..1D550; COMMON 6169 0x1D551, // 1D551 ; UNKNOWN 6170 0x1D552, // 1D552..1D6A5; COMMON 6171 0x1D6A6, // 1D6A6..1D6A7; UNKNOWN 6172 0x1D6A8, // 1D6A8..1D7CB; COMMON 6173 0x1D7CC, // 1D7CC..1D7CD; UNKNOWN 6174 0x1D7CE, // 1D7CE..1D7FF; COMMON 6175 0x1D800, // 1D800..1DA8B; SIGNWRITING 6176 0x1DA8C, // 1DA8C..1DA9A; UNKNOWN 6177 0x1DA9B, // 1DA9B..1DA9F; SIGNWRITING 6178 0x1DAA0, // 1DAA0 ; UNKNOWN 6179 0x1DAA1, // 1DAA1..1DAAF; SIGNWRITING 6180 0x1DAB0, // 1DAB0..1DFFF; UNKNOWN 6181 0x1E000, // 1E000..1E006; GLAGOLITIC 6182 0x1E007, // 1E007 ; UNKNOWN 6183 0x1E008, // 1E008..1E018; GLAGOLITIC 6184 0x1E019, // 1E019..1E01A; UNKNOWN 6185 0x1E01B, // 1E01B..1E021; GLAGOLITIC 6186 0x1E022, // 1E022 ; UNKNOWN 6187 0x1E023, // 1E023..1E024; GLAGOLITIC 6188 0x1E025, // 1E025 ; UNKNOWN 6189 0x1E026, // 1E026..1E02A; GLAGOLITIC 6190 0x1E02B, // 1E02B..1E7FF; UNKNOWN 6191 0x1E800, // 1E800..1E8C4; MENDE_KIKAKUI 6192 0x1E8C5, // 1E8C5..1E8C6; UNKNOWN 6193 0x1E8C7, // 1E8C7..1E8D6; MENDE_KIKAKUI 6194 0x1E8D7, // 1E8D7..1E8FF; UNKNOWN 6195 0x1E900, // 1E900..1E94A; ADLAM 6196 0x1E94B, // 1E94B..1E94F; UNKNOWN 6197 0x1E950, // 1E950..1E959; ADLAM 6198 0x1E95A, // 1E95A..1E95D; UNKNOWN 6199 0x1E95E, // 1E95E..1E95F; ADLAM 6200 0x1E960, // 1E960..1EC70; UNKNOWN 6201 0x1EC71, // 1EC71..1ECB4; COMMON 6202 0x1ECB5, // 1ECB5..1EDFF; UNKNOWN 6203 0x1EE00, // 1EE00..1EE03; ARABIC 6204 0x1EE04, // 1EE04 ; UNKNOWN 6205 0x1EE05, // 1EE05..1EE1F; ARABIC 6206 0x1EE20, // 1EE20 ; UNKNOWN 6207 0x1EE21, // 1EE21..1EE22; ARABIC 6208 0x1EE23, // 1EE23 ; UNKNOWN 6209 0x1EE24, // 1EE24 ; ARABIC 6210 0x1EE25, // 1EE25..1EE26; UNKNOWN 6211 0x1EE27, // 1EE27 ; ARABIC 6212 0x1EE28, // 1EE28 ; UNKNOWN 6213 0x1EE29, // 1EE29..1EE32; ARABIC 6214 0x1EE33, // 1EE33 ; UNKNOWN 6215 0x1EE34, // 1EE34..1EE37; ARABIC 6216 0x1EE38, // 1EE38 ; UNKNOWN 6217 0x1EE39, // 1EE39 ; ARABIC 6218 0x1EE3A, // 1EE3A ; UNKNOWN 6219 0x1EE3B, // 1EE3B ; ARABIC 6220 0x1EE3C, // 1EE3C..1EE41; UNKNOWN 6221 0x1EE42, // 1EE42 ; ARABIC 6222 0x1EE43, // 1EE43..1EE46; UNKNOWN 6223 0x1EE47, // 1EE47 ; ARABIC 6224 0x1EE48, // 1EE48 ; UNKNOWN 6225 0x1EE49, // 1EE49 ; ARABIC 6226 0x1EE4A, // 1EE4A ; UNKNOWN 6227 0x1EE4B, // 1EE4B ; ARABIC 6228 0x1EE4C, // 1EE4C ; UNKNOWN 6229 0x1EE4D, // 1EE4D..1EE4F; ARABIC 6230 0x1EE50, // 1EE50 ; UNKNOWN 6231 0x1EE51, // 1EE51..1EE52; ARABIC 6232 0x1EE53, // 1EE53 ; UNKNOWN 6233 0x1EE54, // 1EE54 ; ARABIC 6234 0x1EE55, // 1EE55..1EE56; UNKNOWN 6235 0x1EE57, // 1EE57 ; ARABIC 6236 0x1EE58, // 1EE58 ; UNKNOWN 6237 0x1EE59, // 1EE59 ; ARABIC 6238 0x1EE5A, // 1EE5A ; UNKNOWN 6239 0x1EE5B, // 1EE5B ; ARABIC 6240 0x1EE5C, // 1EE5C ; UNKNOWN 6241 0x1EE5D, // 1EE5D ; ARABIC 6242 0x1EE5E, // 1EE5E ; UNKNOWN 6243 0x1EE5F, // 1EE5F ; ARABIC 6244 0x1EE60, // 1EE60 ; UNKNOWN 6245 0x1EE61, // 1EE61..1EE62; ARABIC 6246 0x1EE63, // 1EE63 ; UNKNOWN 6247 0x1EE64, // 1EE64 ; ARABIC 6248 0x1EE65, // 1EE65..1EE66; UNKNOWN 6249 0x1EE67, // 1EE67..1EE6A; ARABIC 6250 0x1EE6B, // 1EE6B ; UNKNOWN 6251 0x1EE6C, // 1EE6C..1EE72; ARABIC 6252 0x1EE73, // 1EE73 ; UNKNOWN 6253 0x1EE74, // 1EE74..1EE77; ARABIC 6254 0x1EE78, // 1EE78 ; UNKNOWN 6255 0x1EE79, // 1EE79..1EE7C; ARABIC 6256 0x1EE7D, // 1EE7D ; UNKNOWN 6257 0x1EE7E, // 1EE7E ; ARABIC 6258 0x1EE7F, // 1EE7F ; UNKNOWN 6259 0x1EE80, // 1EE80..1EE89; ARABIC 6260 0x1EE8A, // 1EE8A ; UNKNOWN 6261 0x1EE8B, // 1EE8B..1EE9B; ARABIC 6262 0x1EE9C, // 1EE9C..1EEA0; UNKNOWN 6263 0x1EEA1, // 1EEA1..1EEA3; ARABIC 6264 0x1EEA4, // 1EEA4 ; UNKNOWN 6265 0x1EEA5, // 1EEA5..1EEA9; ARABIC 6266 0x1EEAA, // 1EEAA ; UNKNOWN 6267 0x1EEAB, // 1EEAB..1EEBB; ARABIC 6268 0x1EEBC, // 1EEBC..1EEEF; UNKNOWN 6269 0x1EEF0, // 1EEF0..1EEF1; ARABIC 6270 0x1EEF2, // 1EEF2..1EFFF; UNKNOWN 6271 0x1F000, // 1F000..1F02B; COMMON 6272 0x1F02C, // 1F02C..1F02F; UNKNOWN 6273 0x1F030, // 1F030..1F093; COMMON 6274 0x1F094, // 1F094..1F09F; UNKNOWN 6275 0x1F0A0, // 1F0A0..1F0AE; COMMON 6276 0x1F0AF, // 1F0AF..1F0B0; UNKNOWN 6277 0x1F0B1, // 1F0B1..1F0BF; COMMON 6278 0x1F0C0, // 1F0C0 ; UNKNOWN 6279 0x1F0C1, // 1F0C1..1F0CF; COMMON 6280 0x1F0D0, // 1F0D0 ; UNKNOWN 6281 0x1F0D1, // 1F0D1..1F0F5; COMMON 6282 0x1F0F6, // 1F0F6..1F0FF; UNKNOWN 6283 0x1F100, // 1F100..1F10C; COMMON 6284 0x1F10D, // 1F10D..1F10F; UNKNOWN 6285 0x1F110, // 1F110..1F16B; COMMON 6286 0x1F16C, // 1F16C..1F16F; UNKNOWN 6287 0x1F170, // 1F170..1F1AC; COMMON 6288 0x1F1AD, // 1F1AD..1F1E5; UNKNOWN 6289 0x1F1E6, // 1F1E6..1F1FF; COMMON 6290 0x1F200, // 1F200 ; HIRAGANA 6291 0x1F201, // 1F201..1F202; COMMON 6292 0x1F203, // 1F203..1F20F; UNKNOWN 6293 0x1F210, // 1F210..1F23B; COMMON 6294 0x1F23C, // 1F23C..1F23F; UNKNOWN 6295 0x1F240, // 1F240..1F248; COMMON 6296 0x1F249, // 1F249..1F24F; UNKNOWN 6297 0x1F250, // 1F250..1F251; COMMON 6298 0x1F252, // 1F252..1F25F; UNKNOWN 6299 0x1F260, // 1F260..1F265; COMMON 6300 0x1F266, // 1F266..1F2FF; UNKNOWN 6301 0x1F300, // 1F300..1F6D4; COMMON 6302 0x1F6D5, // 1F6D5..1F6DF; UNKNOWN 6303 0x1F6E0, // 1F6E0..1F6EC; COMMON 6304 0x1F6ED, // 1F6ED..1F6EF; UNKNOWN 6305 0x1F6F0, // 1F6F0..1F6F9; COMMON 6306 0x1F6FA, // 1F6FA..1F6FF; UNKNOWN 6307 0x1F700, // 1F700..1F773; COMMON 6308 0x1F774, // 1F774..1F77F; UNKNOWN 6309 0x1F780, // 1F780..1F7D8; COMMON 6310 0x1F7D9, // 1F7D9..1F7FF; UNKNOWN 6311 0x1F800, // 1F800..1F80B; COMMON 6312 0x1F80C, // 1F80C..1F80F; UNKNOWN 6313 0x1F810, // 1F810..1F847; COMMON 6314 0x1F848, // 1F848..1F84F; UNKNOWN 6315 0x1F850, // 1F850..1F859; COMMON 6316 0x1F85A, // 1F85A..1F85F; UNKNOWN 6317 0x1F860, // 1F860..1F887; COMMON 6318 0x1F888, // 1F888..1F88F; UNKNOWN 6319 0x1F890, // 1F890..1F8AD; COMMON 6320 0x1F8AE, // 1F8AE..1F8FF; UNKNOWN 6321 0x1F900, // 1F900..1F90B; COMMON 6322 0x1F90C, // 1F90C..1F90F; UNKNOWN 6323 0x1F910, // 1F910..1F93E; COMMON 6324 0x1F93F, // 1F93F ; UNKNOWN 6325 0x1F940, // 1F940..1F970; COMMON 6326 0x1F971, // 1F971..1F972; UNKNOWN 6327 0x1F973, // 1F973..1F976; COMMON 6328 0x1F977, // 1F977..1F979; UNKNOWN 6329 0x1F97A, // 1F97A ; COMMON 6330 0x1F97B, // 1F97B ; UNKNOWN 6331 0x1F97C, // 1F97C..1F9A2; COMMON 6332 0x1F9A3, // 1F9A3..1F9AF; UNKNOWN 6333 0x1F9B0, // 1F9B0..1F9B9; COMMON 6334 0x1F9BA, // 1F9BA..1F9BF; UNKNOWN 6335 0x1F9C0, // 1F9C0..1F9C2; COMMON 6336 0x1F9C3, // 1F9C3..1F9CF; UNKNOWN 6337 0x1F9D0, // 1F9D0..1F9FF; COMMON 6338 0x1FA00, // 1FA00..1FA5F; UNKNOWN 6339 0x1FA60, // 1FA60..1FA6D; COMMON 6340 0x1FA6E, // 1FA6E..1FFFF; UNKNOWN 6341 0x20000, // 20000..2A6D6; HAN 6342 0x2A6D7, // 2A6D7..2A6FF; UNKNOWN 6343 0x2A700, // 2A700..2B734; HAN 6344 0x2B735, // 2B735..2B73F; UNKNOWN 6345 0x2B740, // 2B740..2B81D; HAN 6346 0x2B81E, // 2B81E..2B81F; UNKNOWN 6347 0x2B820, // 2B820..2CEA1; HAN 6348 0x2CEA2, // 2CEA2..2CEAF; UNKNOWN 6349 0x2CEB0, // 2CEB0..2EBE0; HAN 6350 0x2EBE1, // 2EBE1..2F7FF; UNKNOWN 6351 0x2F800, // 2F800..2FA1D; HAN 6352 0x2FA1E, // 2FA1E..E0000; UNKNOWN 6353 0xE0001, // E0001 ; COMMON 6354 0xE0002, // E0002..E001F; UNKNOWN 6355 0xE0020, // E0020..E007F; COMMON 6356 0xE0080, // E0080..E00FF; UNKNOWN 6357 0xE0100, // E0100..E01EF; INHERITED 6358 0xE01F0 // E01F0..10FFFF; UNKNOWN 6359 }; 6360 6361 private static final UnicodeScript[] scripts = { 6362 COMMON, // 0000..0040 6363 LATIN, // 0041..005A 6364 COMMON, // 005B..0060 6365 LATIN, // 0061..007A 6366 COMMON, // 007B..00A9 6367 LATIN, // 00AA 6368 COMMON, // 00AB..00B9 6369 LATIN, // 00BA 6370 COMMON, // 00BB..00BF 6371 LATIN, // 00C0..00D6 6372 COMMON, // 00D7 6373 LATIN, // 00D8..00F6 6374 COMMON, // 00F7 6375 LATIN, // 00F8..02B8 6376 COMMON, // 02B9..02DF 6377 LATIN, // 02E0..02E4 6378 COMMON, // 02E5..02E9 6379 BOPOMOFO, // 02EA..02EB 6380 COMMON, // 02EC..02FF 6381 INHERITED, // 0300..036F 6382 GREEK, // 0370..0373 6383 COMMON, // 0374 6384 GREEK, // 0375..0377 6385 UNKNOWN, // 0378..0379 6386 GREEK, // 037A..037D 6387 COMMON, // 037E 6388 GREEK, // 037F 6389 UNKNOWN, // 0380..0383 6390 GREEK, // 0384 6391 COMMON, // 0385 6392 GREEK, // 0386 6393 COMMON, // 0387 6394 GREEK, // 0388..038A 6395 UNKNOWN, // 038B 6396 GREEK, // 038C 6397 UNKNOWN, // 038D 6398 GREEK, // 038E..03A1 6399 UNKNOWN, // 03A2 6400 GREEK, // 03A3..03E1 6401 COPTIC, // 03E2..03EF 6402 GREEK, // 03F0..03FF 6403 CYRILLIC, // 0400..0484 6404 INHERITED, // 0485..0486 6405 CYRILLIC, // 0487..052F 6406 UNKNOWN, // 0530 6407 ARMENIAN, // 0531..0556 6408 UNKNOWN, // 0557..0558 6409 ARMENIAN, // 0559..0588 6410 COMMON, // 0589 6411 ARMENIAN, // 058A 6412 UNKNOWN, // 058B..058C 6413 ARMENIAN, // 058D..058F 6414 UNKNOWN, // 0590 6415 HEBREW, // 0591..05C7 6416 UNKNOWN, // 05C8..05CF 6417 HEBREW, // 05D0..05EA 6418 UNKNOWN, // 05EB..05EE 6419 HEBREW, // 05EF..05F4 6420 UNKNOWN, // 05F5..05FF 6421 ARABIC, // 0600..0604 6422 COMMON, // 0605 6423 ARABIC, // 0606..060B 6424 COMMON, // 060C 6425 ARABIC, // 060D..061A 6426 COMMON, // 061B 6427 ARABIC, // 061C 6428 UNKNOWN, // 061D 6429 ARABIC, // 061E 6430 COMMON, // 061F 6431 ARABIC, // 0620..063F 6432 COMMON, // 0640 6433 ARABIC, // 0641..064A 6434 INHERITED, // 064B..0655 6435 ARABIC, // 0656..066F 6436 INHERITED, // 0670 6437 ARABIC, // 0671..06DC 6438 COMMON, // 06DD 6439 ARABIC, // 06DE..06FF 6440 SYRIAC, // 0700..070D 6441 UNKNOWN, // 070E 6442 SYRIAC, // 070F..074A 6443 UNKNOWN, // 074B..074C 6444 SYRIAC, // 074D..074F 6445 ARABIC, // 0750..077F 6446 THAANA, // 0780..07B1 6447 UNKNOWN, // 07B2..07BF 6448 NKO, // 07C0..07FA 6449 UNKNOWN, // 07FB..07FC 6450 NKO, // 07FD..07FF 6451 SAMARITAN, // 0800..082D 6452 UNKNOWN, // 082E..082F 6453 SAMARITAN, // 0830..083E 6454 UNKNOWN, // 083F 6455 MANDAIC, // 0840..085B 6456 UNKNOWN, // 085C..085D 6457 MANDAIC, // 085E 6458 UNKNOWN, // 085F 6459 SYRIAC, // 0860..086A 6460 UNKNOWN, // 086B..089F 6461 ARABIC, // 08A0..08B4 6462 UNKNOWN, // 08B5 6463 ARABIC, // 08B6..08BD 6464 UNKNOWN, // 08BE..08D2 6465 ARABIC, // 08D3..08E1 6466 COMMON, // 08E2 6467 ARABIC, // 08E3..08FF 6468 DEVANAGARI, // 0900..0950 6469 INHERITED, // 0951..0952 6470 DEVANAGARI, // 0953..0963 6471 COMMON, // 0964..0965 6472 DEVANAGARI, // 0966..097F 6473 BENGALI, // 0980..0983 6474 UNKNOWN, // 0984 6475 BENGALI, // 0985..098C 6476 UNKNOWN, // 098D..098E 6477 BENGALI, // 098F..0990 6478 UNKNOWN, // 0991..0992 6479 BENGALI, // 0993..09A8 6480 UNKNOWN, // 09A9 6481 BENGALI, // 09AA..09B0 6482 UNKNOWN, // 09B1 6483 BENGALI, // 09B2 6484 UNKNOWN, // 09B3..09B5 6485 BENGALI, // 09B6..09B9 6486 UNKNOWN, // 09BA..09BB 6487 BENGALI, // 09BC..09C4 6488 UNKNOWN, // 09C5..09C6 6489 BENGALI, // 09C7..09C8 6490 UNKNOWN, // 09C9..09CA 6491 BENGALI, // 09CB..09CE 6492 UNKNOWN, // 09CF..09D6 6493 BENGALI, // 09D7 6494 UNKNOWN, // 09D8..09DB 6495 BENGALI, // 09DC..09DD 6496 UNKNOWN, // 09DE 6497 BENGALI, // 09DF..09E3 6498 UNKNOWN, // 09E4..09E5 6499 BENGALI, // 09E6..09FE 6500 UNKNOWN, // 09FF..0A00 6501 GURMUKHI, // 0A01..0A03 6502 UNKNOWN, // 0A04 6503 GURMUKHI, // 0A05..0A0A 6504 UNKNOWN, // 0A0B..0A0E 6505 GURMUKHI, // 0A0F..0A10 6506 UNKNOWN, // 0A11..0A12 6507 GURMUKHI, // 0A13..0A28 6508 UNKNOWN, // 0A29 6509 GURMUKHI, // 0A2A..0A30 6510 UNKNOWN, // 0A31 6511 GURMUKHI, // 0A32..0A33 6512 UNKNOWN, // 0A34 6513 GURMUKHI, // 0A35..0A36 6514 UNKNOWN, // 0A37 6515 GURMUKHI, // 0A38..0A39 6516 UNKNOWN, // 0A3A..0A3B 6517 GURMUKHI, // 0A3C 6518 UNKNOWN, // 0A3D 6519 GURMUKHI, // 0A3E..0A42 6520 UNKNOWN, // 0A43..0A46 6521 GURMUKHI, // 0A47..0A48 6522 UNKNOWN, // 0A49..0A4A 6523 GURMUKHI, // 0A4B..0A4D 6524 UNKNOWN, // 0A4E..0A50 6525 GURMUKHI, // 0A51 6526 UNKNOWN, // 0A52..0A58 6527 GURMUKHI, // 0A59..0A5C 6528 UNKNOWN, // 0A5D 6529 GURMUKHI, // 0A5E 6530 UNKNOWN, // 0A5F..0A65 6531 GURMUKHI, // 0A66..0A76 6532 UNKNOWN, // 0A77..0A80 6533 GUJARATI, // 0A81..0A83 6534 UNKNOWN, // 0A84 6535 GUJARATI, // 0A85..0A8D 6536 UNKNOWN, // 0A8E 6537 GUJARATI, // 0A8F..0A91 6538 UNKNOWN, // 0A92 6539 GUJARATI, // 0A93..0AA8 6540 UNKNOWN, // 0AA9 6541 GUJARATI, // 0AAA..0AB0 6542 UNKNOWN, // 0AB1 6543 GUJARATI, // 0AB2..0AB3 6544 UNKNOWN, // 0AB4 6545 GUJARATI, // 0AB5..0AB9 6546 UNKNOWN, // 0ABA..0ABB 6547 GUJARATI, // 0ABC..0AC5 6548 UNKNOWN, // 0AC6 6549 GUJARATI, // 0AC7..0AC9 6550 UNKNOWN, // 0ACA 6551 GUJARATI, // 0ACB..0ACD 6552 UNKNOWN, // 0ACE..0ACF 6553 GUJARATI, // 0AD0 6554 UNKNOWN, // 0AD1..0ADF 6555 GUJARATI, // 0AE0..0AE3 6556 UNKNOWN, // 0AE4..0AE5 6557 GUJARATI, // 0AE6..0AF1 6558 UNKNOWN, // 0AF2..0AF8 6559 GUJARATI, // 0AF9..0AFF 6560 UNKNOWN, // 0B00 6561 ORIYA, // 0B01..0B03 6562 UNKNOWN, // 0B04 6563 ORIYA, // 0B05..0B0C 6564 UNKNOWN, // 0B0D..0B0E 6565 ORIYA, // 0B0F..0B10 6566 UNKNOWN, // 0B11..0B12 6567 ORIYA, // 0B13..0B28 6568 UNKNOWN, // 0B29 6569 ORIYA, // 0B2A..0B30 6570 UNKNOWN, // 0B31 6571 ORIYA, // 0B32..0B33 6572 UNKNOWN, // 0B34 6573 ORIYA, // 0B35..0B39 6574 UNKNOWN, // 0B3A..0B3B 6575 ORIYA, // 0B3C..0B44 6576 UNKNOWN, // 0B45..0B46 6577 ORIYA, // 0B47..0B48 6578 UNKNOWN, // 0B49..0B4A 6579 ORIYA, // 0B4B..0B4D 6580 UNKNOWN, // 0B4E..0B55 6581 ORIYA, // 0B56..0B57 6582 UNKNOWN, // 0B58..0B5B 6583 ORIYA, // 0B5C..0B5D 6584 UNKNOWN, // 0B5E 6585 ORIYA, // 0B5F..0B63 6586 UNKNOWN, // 0B64..0B65 6587 ORIYA, // 0B66..0B77 6588 UNKNOWN, // 0B78..0B81 6589 TAMIL, // 0B82..0B83 6590 UNKNOWN, // 0B84 6591 TAMIL, // 0B85..0B8A 6592 UNKNOWN, // 0B8B..0B8D 6593 TAMIL, // 0B8E..0B90 6594 UNKNOWN, // 0B91 6595 TAMIL, // 0B92..0B95 6596 UNKNOWN, // 0B96..0B98 6597 TAMIL, // 0B99..0B9A 6598 UNKNOWN, // 0B9B 6599 TAMIL, // 0B9C 6600 UNKNOWN, // 0B9D 6601 TAMIL, // 0B9E..0B9F 6602 UNKNOWN, // 0BA0..0BA2 6603 TAMIL, // 0BA3..0BA4 6604 UNKNOWN, // 0BA5..0BA7 6605 TAMIL, // 0BA8..0BAA 6606 UNKNOWN, // 0BAB..0BAD 6607 TAMIL, // 0BAE..0BB9 6608 UNKNOWN, // 0BBA..0BBD 6609 TAMIL, // 0BBE..0BC2 6610 UNKNOWN, // 0BC3..0BC5 6611 TAMIL, // 0BC6..0BC8 6612 UNKNOWN, // 0BC9 6613 TAMIL, // 0BCA..0BCD 6614 UNKNOWN, // 0BCE..0BCF 6615 TAMIL, // 0BD0 6616 UNKNOWN, // 0BD1..0BD6 6617 TAMIL, // 0BD7 6618 UNKNOWN, // 0BD8..0BE5 6619 TAMIL, // 0BE6..0BFA 6620 UNKNOWN, // 0BFB..0BFF 6621 TELUGU, // 0C00..0C0C 6622 UNKNOWN, // 0C0D 6623 TELUGU, // 0C0E..0C10 6624 UNKNOWN, // 0C11 6625 TELUGU, // 0C12..0C28 6626 UNKNOWN, // 0C29 6627 TELUGU, // 0C2A..0C39 6628 UNKNOWN, // 0C3A..0C3C 6629 TELUGU, // 0C3D..0C44 6630 UNKNOWN, // 0C45 6631 TELUGU, // 0C46..0C48 6632 UNKNOWN, // 0C49 6633 TELUGU, // 0C4A..0C4D 6634 UNKNOWN, // 0C4E..0C54 6635 TELUGU, // 0C55..0C56 6636 UNKNOWN, // 0C57 6637 TELUGU, // 0C58..0C5A 6638 UNKNOWN, // 0C5B..0C5F 6639 TELUGU, // 0C60..0C63 6640 UNKNOWN, // 0C64..0C65 6641 TELUGU, // 0C66..0C6F 6642 UNKNOWN, // 0C70..0C77 6643 TELUGU, // 0C78..0C7F 6644 KANNADA, // 0C80..0C8C 6645 UNKNOWN, // 0C8D 6646 KANNADA, // 0C8E..0C90 6647 UNKNOWN, // 0C91 6648 KANNADA, // 0C92..0CA8 6649 UNKNOWN, // 0CA9 6650 KANNADA, // 0CAA..0CB3 6651 UNKNOWN, // 0CB4 6652 KANNADA, // 0CB5..0CB9 6653 UNKNOWN, // 0CBA..0CBB 6654 KANNADA, // 0CBC..0CC4 6655 UNKNOWN, // 0CC5 6656 KANNADA, // 0CC6..0CC8 6657 UNKNOWN, // 0CC9 6658 KANNADA, // 0CCA..0CCD 6659 UNKNOWN, // 0CCE..0CD4 6660 KANNADA, // 0CD5..0CD6 6661 UNKNOWN, // 0CD7..0CDD 6662 KANNADA, // 0CDE 6663 UNKNOWN, // 0CDF 6664 KANNADA, // 0CE0..0CE3 6665 UNKNOWN, // 0CE4..0CE5 6666 KANNADA, // 0CE6..0CEF 6667 UNKNOWN, // 0CF0 6668 KANNADA, // 0CF1..0CF2 6669 UNKNOWN, // 0CF3..0CFF 6670 MALAYALAM, // 0D00..0D03 6671 UNKNOWN, // 0D04 6672 MALAYALAM, // 0D05..0D0C 6673 UNKNOWN, // 0D0D 6674 MALAYALAM, // 0D0E..0D10 6675 UNKNOWN, // 0D11 6676 MALAYALAM, // 0D12..0D44 6677 UNKNOWN, // 0D45 6678 MALAYALAM, // 0D46..0D48 6679 UNKNOWN, // 0D49 6680 MALAYALAM, // 0D4A..0D4F 6681 UNKNOWN, // 0D50..0D53 6682 MALAYALAM, // 0D54..0D63 6683 UNKNOWN, // 0D64..0D65 6684 MALAYALAM, // 0D66..0D7F 6685 UNKNOWN, // 0D80..0D81 6686 SINHALA, // 0D82..0D83 6687 UNKNOWN, // 0D84 6688 SINHALA, // 0D85..0D96 6689 UNKNOWN, // 0D97..0D99 6690 SINHALA, // 0D9A..0DB1 6691 UNKNOWN, // 0DB2 6692 SINHALA, // 0DB3..0DBB 6693 UNKNOWN, // 0DBC 6694 SINHALA, // 0DBD 6695 UNKNOWN, // 0DBE..0DBF 6696 SINHALA, // 0DC0..0DC6 6697 UNKNOWN, // 0DC7..0DC9 6698 SINHALA, // 0DCA 6699 UNKNOWN, // 0DCB..0DCE 6700 SINHALA, // 0DCF..0DD4 6701 UNKNOWN, // 0DD5 6702 SINHALA, // 0DD6 6703 UNKNOWN, // 0DD7 6704 SINHALA, // 0DD8..0DDF 6705 UNKNOWN, // 0DE0..0DE5 6706 SINHALA, // 0DE6..0DEF 6707 UNKNOWN, // 0DF0..0DF1 6708 SINHALA, // 0DF2..0DF4 6709 UNKNOWN, // 0DF5..0E00 6710 THAI, // 0E01..0E3A 6711 UNKNOWN, // 0E3B..0E3E 6712 COMMON, // 0E3F 6713 THAI, // 0E40..0E5B 6714 UNKNOWN, // 0E5C..0E80 6715 LAO, // 0E81..0E82 6716 UNKNOWN, // 0E83 6717 LAO, // 0E84 6718 UNKNOWN, // 0E85..0E86 6719 LAO, // 0E87..0E88 6720 UNKNOWN, // 0E89 6721 LAO, // 0E8A 6722 UNKNOWN, // 0E8B..0E8C 6723 LAO, // 0E8D 6724 UNKNOWN, // 0E8E..0E93 6725 LAO, // 0E94..0E97 6726 UNKNOWN, // 0E98 6727 LAO, // 0E99..0E9F 6728 UNKNOWN, // 0EA0 6729 LAO, // 0EA1..0EA3 6730 UNKNOWN, // 0EA4 6731 LAO, // 0EA5 6732 UNKNOWN, // 0EA6 6733 LAO, // 0EA7 6734 UNKNOWN, // 0EA8..0EA9 6735 LAO, // 0EAA..0EAB 6736 UNKNOWN, // 0EAC 6737 LAO, // 0EAD..0EB9 6738 UNKNOWN, // 0EBA 6739 LAO, // 0EBB..0EBD 6740 UNKNOWN, // 0EBE..0EBF 6741 LAO, // 0EC0..0EC4 6742 UNKNOWN, // 0EC5 6743 LAO, // 0EC6 6744 UNKNOWN, // 0EC7 6745 LAO, // 0EC8..0ECD 6746 UNKNOWN, // 0ECE..0ECF 6747 LAO, // 0ED0..0ED9 6748 UNKNOWN, // 0EDA..0EDB 6749 LAO, // 0EDC..0EDF 6750 UNKNOWN, // 0EE0..0EFF 6751 TIBETAN, // 0F00..0F47 6752 UNKNOWN, // 0F48 6753 TIBETAN, // 0F49..0F6C 6754 UNKNOWN, // 0F6D..0F70 6755 TIBETAN, // 0F71..0F97 6756 UNKNOWN, // 0F98 6757 TIBETAN, // 0F99..0FBC 6758 UNKNOWN, // 0FBD 6759 TIBETAN, // 0FBE..0FCC 6760 UNKNOWN, // 0FCD 6761 TIBETAN, // 0FCE..0FD4 6762 COMMON, // 0FD5..0FD8 6763 TIBETAN, // 0FD9..0FDA 6764 UNKNOWN, // 0FDB..FFF 6765 MYANMAR, // 1000..109F 6766 GEORGIAN, // 10A0..10C5 6767 UNKNOWN, // 10C6 6768 GEORGIAN, // 10C7 6769 UNKNOWN, // 10C8..10CC 6770 GEORGIAN, // 10CD 6771 UNKNOWN, // 10CE..10CF 6772 GEORGIAN, // 10D0..10FA 6773 COMMON, // 10FB 6774 GEORGIAN, // 10FC..10FF 6775 HANGUL, // 1100..11FF 6776 ETHIOPIC, // 1200..1248 6777 UNKNOWN, // 1249 6778 ETHIOPIC, // 124A..124D 6779 UNKNOWN, // 124E..124F 6780 ETHIOPIC, // 1250..1256 6781 UNKNOWN, // 1257 6782 ETHIOPIC, // 1258 6783 UNKNOWN, // 1259 6784 ETHIOPIC, // 125A..125D 6785 UNKNOWN, // 125E..125F 6786 ETHIOPIC, // 1260..1288 6787 UNKNOWN, // 1289 6788 ETHIOPIC, // 128A..128D 6789 UNKNOWN, // 128E..128F 6790 ETHIOPIC, // 1290..12B0 6791 UNKNOWN, // 12B1 6792 ETHIOPIC, // 12B2..12B5 6793 UNKNOWN, // 12B6..12B7 6794 ETHIOPIC, // 12B8..12BE 6795 UNKNOWN, // 12BF 6796 ETHIOPIC, // 12C0 6797 UNKNOWN, // 12C1 6798 ETHIOPIC, // 12C2..12C5 6799 UNKNOWN, // 12C6..12C7 6800 ETHIOPIC, // 12C8..12D6 6801 UNKNOWN, // 12D7 6802 ETHIOPIC, // 12D8..1310 6803 UNKNOWN, // 1311 6804 ETHIOPIC, // 1312..1315 6805 UNKNOWN, // 1316..1317 6806 ETHIOPIC, // 1318..135A 6807 UNKNOWN, // 135B..135C 6808 ETHIOPIC, // 135D..137C 6809 UNKNOWN, // 137D..137F 6810 ETHIOPIC, // 1380..1399 6811 UNKNOWN, // 139A..139F 6812 CHEROKEE, // 13A0..13F5 6813 UNKNOWN, // 13F6..13F7 6814 CHEROKEE, // 13F8..13FD 6815 UNKNOWN, // 13FE..13FF 6816 CANADIAN_ABORIGINAL, // 1400..167F 6817 OGHAM, // 1680..169C 6818 UNKNOWN, // 169D..169F 6819 RUNIC, // 16A0..16EA 6820 COMMON, // 16EB..16ED 6821 RUNIC, // 16EE..16F8 6822 UNKNOWN, // 16F9..16FF 6823 TAGALOG, // 1700..170C 6824 UNKNOWN, // 170D 6825 TAGALOG, // 170E..1714 6826 UNKNOWN, // 1715..171F 6827 HANUNOO, // 1720..1734 6828 COMMON, // 1735..1736 6829 UNKNOWN, // 1737..173F 6830 BUHID, // 1740..1753 6831 UNKNOWN, // 1754..175F 6832 TAGBANWA, // 1760..176C 6833 UNKNOWN, // 176D 6834 TAGBANWA, // 176E..1770 6835 UNKNOWN, // 1771 6836 TAGBANWA, // 1772..1773 6837 UNKNOWN, // 1774..177F 6838 KHMER, // 1780..17DD 6839 UNKNOWN, // 17DE..17DF 6840 KHMER, // 17E0..17E9 6841 UNKNOWN, // 17EA..17EF 6842 KHMER, // 17F0..17F9 6843 UNKNOWN, // 17FA..17FF 6844 MONGOLIAN, // 1800..1801 6845 COMMON, // 1802..1803 6846 MONGOLIAN, // 1804 6847 COMMON, // 1805 6848 MONGOLIAN, // 1806..180E 6849 UNKNOWN, // 180F 6850 MONGOLIAN, // 1810..1819 6851 UNKNOWN, // 181A..181F 6852 MONGOLIAN, // 1820..1878 6853 UNKNOWN, // 1879..187F 6854 MONGOLIAN, // 1880..18AA 6855 UNKNOWN, // 18AB..18AF 6856 CANADIAN_ABORIGINAL, // 18B0..18F5 6857 UNKNOWN, // 18F6..18FF 6858 LIMBU, // 1900..191E 6859 UNKNOWN, // 191F 6860 LIMBU, // 1920..192B 6861 UNKNOWN, // 192C..192F 6862 LIMBU, // 1930..193B 6863 UNKNOWN, // 193C..193F 6864 LIMBU, // 1940 6865 UNKNOWN, // 1941..1943 6866 LIMBU, // 1944..194F 6867 TAI_LE, // 1950..196D 6868 UNKNOWN, // 196E..196F 6869 TAI_LE, // 1970..1974 6870 UNKNOWN, // 1975..197F 6871 NEW_TAI_LUE, // 1980..19AB 6872 UNKNOWN, // 19AC..19AF 6873 NEW_TAI_LUE, // 19B0..19C9 6874 UNKNOWN, // 19CA..19CF 6875 NEW_TAI_LUE, // 19D0..19DA 6876 UNKNOWN, // 19DB..19DD 6877 NEW_TAI_LUE, // 19DE..19DF 6878 KHMER, // 19E0..19FF 6879 BUGINESE, // 1A00..1A1B 6880 UNKNOWN, // 1A1C..1A1D 6881 BUGINESE, // 1A1E..1A1F 6882 TAI_THAM, // 1A20..1A5E 6883 UNKNOWN, // 1A5F 6884 TAI_THAM, // 1A60..1A7C 6885 UNKNOWN, // 1A7D..1A7E 6886 TAI_THAM, // 1A7F..1A89 6887 UNKNOWN, // 1A8A..1A8F 6888 TAI_THAM, // 1A90..1A99 6889 UNKNOWN, // 1A9A..1A9F 6890 TAI_THAM, // 1AA0..1AAD 6891 UNKNOWN, // 1AAE..1AAF 6892 INHERITED, // 1AB0..1ABE 6893 UNKNOWN, // 1ABF..1AFF 6894 BALINESE, // 1B00..1B4B 6895 UNKNOWN, // 1B4C..1B4F 6896 BALINESE, // 1B50..1B7C 6897 UNKNOWN, // 1B7D..1B7F 6898 SUNDANESE, // 1B80..1BBF 6899 BATAK, // 1BC0..1BF3 6900 UNKNOWN, // 1BF4..1BFB 6901 BATAK, // 1BFC..1BFF 6902 LEPCHA, // 1C00..1C37 6903 UNKNOWN, // 1C38..1C3A 6904 LEPCHA, // 1C3B..1C49 6905 UNKNOWN, // 1C4A..1C4C 6906 LEPCHA, // 1C4D..1C4F 6907 OL_CHIKI, // 1C50..1C7F 6908 CYRILLIC, // 1C80..1C88 6909 UNKNOWN, // 1C89 6910 GEORGIAN, // 1C90..1CBA 6911 UNKNOWN, // 1CBB..1CBC 6912 GEORGIAN, // 1CBD..1CBF 6913 SUNDANESE, // 1CC0..1CC7 6914 UNKNOWN, // 1CC8..1CCF 6915 INHERITED, // 1CD0..1CD2 6916 COMMON, // 1CD3 6917 INHERITED, // 1CD4..1CE0 6918 COMMON, // 1CE1 6919 INHERITED, // 1CE2..1CE8 6920 COMMON, // 1CE9..1CEC 6921 INHERITED, // 1CED 6922 COMMON, // 1CEE..1CF3 6923 INHERITED, // 1CF4 6924 COMMON, // 1CF5..1CF7 6925 INHERITED, // 1CF8..1CF9 6926 UNKNOWN, // 1CFA..1CFF 6927 LATIN, // 1D00..1D25 6928 GREEK, // 1D26..1D2A 6929 CYRILLIC, // 1D2B 6930 LATIN, // 1D2C..1D5C 6931 GREEK, // 1D5D..1D61 6932 LATIN, // 1D62..1D65 6933 GREEK, // 1D66..1D6A 6934 LATIN, // 1D6B..1D77 6935 CYRILLIC, // 1D78 6936 LATIN, // 1D79..1DBE 6937 GREEK, // 1DBF 6938 INHERITED, // 1DC0..1DF9 6939 UNKNOWN, // 1DFA 6940 INHERITED, // 1DFB..1DFF 6941 LATIN, // 1E00..1EFF 6942 GREEK, // 1F00..1F15 6943 UNKNOWN, // 1F16..1F17 6944 GREEK, // 1F18..1F1D 6945 UNKNOWN, // 1F1E..1F1F 6946 GREEK, // 1F20..1F45 6947 UNKNOWN, // 1F46..1F47 6948 GREEK, // 1F48..1F4D 6949 UNKNOWN, // 1F4E..1F4F 6950 GREEK, // 1F50..1F57 6951 UNKNOWN, // 1F58 6952 GREEK, // 1F59 6953 UNKNOWN, // 1F5A 6954 GREEK, // 1F5B 6955 UNKNOWN, // 1F5C 6956 GREEK, // 1F5D 6957 UNKNOWN, // 1F5E 6958 GREEK, // 1F5F..1F7D 6959 UNKNOWN, // 1F7E..1F7F 6960 GREEK, // 1F80..1FB4 6961 UNKNOWN, // 1FB5 6962 GREEK, // 1FB6..1FC4 6963 UNKNOWN, // 1FC5 6964 GREEK, // 1FC6..1FD3 6965 UNKNOWN, // 1FD4..1FD5 6966 GREEK, // 1FD6..1FDB 6967 UNKNOWN, // 1FDC 6968 GREEK, // 1FDD..1FEF 6969 UNKNOWN, // 1FF0..1FF1 6970 GREEK, // 1FF2..1FF4 6971 UNKNOWN, // 1FF5 6972 GREEK, // 1FF6..1FFE 6973 UNKNOWN, // 1FFF 6974 COMMON, // 2000..200B 6975 INHERITED, // 200C..200D 6976 COMMON, // 200E..2064 6977 UNKNOWN, // 2065 6978 COMMON, // 2066..2070 6979 LATIN, // 2071 6980 UNKNOWN, // 2072..2073 6981 COMMON, // 2074..207E 6982 LATIN, // 207F 6983 COMMON, // 2080..208E 6984 UNKNOWN, // 208F 6985 LATIN, // 2090..209C 6986 UNKNOWN, // 209D..209F 6987 COMMON, // 20A0..20BF 6988 UNKNOWN, // 20C0..20CF 6989 INHERITED, // 20D0..20F0 6990 UNKNOWN, // 20F1..20FF 6991 COMMON, // 2100..2125 6992 GREEK, // 2126 6993 COMMON, // 2127..2129 6994 LATIN, // 212A..212B 6995 COMMON, // 212C..2131 6996 LATIN, // 2132 6997 COMMON, // 2133..214D 6998 LATIN, // 214E 6999 COMMON, // 214F..215F 7000 LATIN, // 2160..2188 7001 COMMON, // 2189..218B 7002 UNKNOWN, // 218C..218F 7003 COMMON, // 2190..2426 7004 UNKNOWN, // 2427..243F 7005 COMMON, // 2440..244A 7006 UNKNOWN, // 244B..245F 7007 COMMON, // 2460..27FF 7008 BRAILLE, // 2800..28FF 7009 COMMON, // 2900..2B73 7010 UNKNOWN, // 2B74..2B75 7011 COMMON, // 2B76..2B95 7012 UNKNOWN, // 2B96..2B97 7013 COMMON, // 2B98..2BC8 7014 UNKNOWN, // 2BC9 7015 COMMON, // 2BCA..2BFE 7016 UNKNOWN, // 0x2BFF 7017 GLAGOLITIC, // 2C00..2C2E 7018 UNKNOWN, // 2C2F 7019 GLAGOLITIC, // 2C30..2C5E 7020 UNKNOWN, // 2C5F 7021 LATIN, // 2C60..2C7F 7022 COPTIC, // 2C80..2CF3 7023 UNKNOWN, // 2CF4..2CF8 7024 COPTIC, // 2CF9..2CFF 7025 GEORGIAN, // 2D00..2D25 7026 UNKNOWN, // 2D26 7027 GEORGIAN, // 2D27 7028 UNKNOWN, // 2D28..2D2C 7029 GEORGIAN, // 2D2D 7030 UNKNOWN, // 2D2E..2D2F 7031 TIFINAGH, // 2D30..2D67 7032 UNKNOWN, // 2D68..2D6E 7033 TIFINAGH, // 2D6F..2D70 7034 UNKNOWN, // 2D71..2D7E 7035 TIFINAGH, // 2D7F 7036 ETHIOPIC, // 2D80..2D96 7037 UNKNOWN, // 2D97..2D9F 7038 ETHIOPIC, // 2DA0..2DA6 7039 UNKNOWN, // 2DA7 7040 ETHIOPIC, // 2DA8..2DAE 7041 UNKNOWN, // 2DAF 7042 ETHIOPIC, // 2DB0..2DB6 7043 UNKNOWN, // 2DB7 7044 ETHIOPIC, // 2DB8..2DBE 7045 UNKNOWN, // 2DBF 7046 ETHIOPIC, // 2DC0..2DC6 7047 UNKNOWN, // 2DC7 7048 ETHIOPIC, // 2DC8..2DCE 7049 UNKNOWN, // 2DCF 7050 ETHIOPIC, // 2DD0..2DD6 7051 UNKNOWN, // 2DD7 7052 ETHIOPIC, // 2DD8..2DDE 7053 UNKNOWN, // 2DDF 7054 CYRILLIC, // 2DE0..2DFF 7055 COMMON, // 2E00..2E4E 7056 UNKNOWN, // 2E4F..2E7F 7057 HAN, // 2E80..2E99 7058 UNKNOWN, // 2E9A 7059 HAN, // 2E9B..2EF3 7060 UNKNOWN, // 2EF4..2EFF 7061 HAN, // 2F00..2FD5 7062 UNKNOWN, // 2FD6..2FEF 7063 COMMON, // 2FF0..2FFB 7064 UNKNOWN, // 2FFC..2FFF 7065 COMMON, // 3000..3004 7066 HAN, // 3005 7067 COMMON, // 3006 7068 HAN, // 3007 7069 COMMON, // 3008..3020 7070 HAN, // 3021..3029 7071 INHERITED, // 302A..302D 7072 HANGUL, // 302E..302F 7073 COMMON, // 3030..3037 7074 HAN, // 3038..303B 7075 COMMON, // 303C..303F 7076 UNKNOWN, // 3040 7077 HIRAGANA, // 3041..3096 7078 UNKNOWN, // 3097..3098 7079 INHERITED, // 3099..309A 7080 COMMON, // 309B..309C 7081 HIRAGANA, // 309D..309F 7082 COMMON, // 30A0 7083 KATAKANA, // 30A1..30FA 7084 COMMON, // 30FB..30FC 7085 KATAKANA, // 30FD..30FF 7086 UNKNOWN, // 3100..3104 7087 BOPOMOFO, // 3105..312F 7088 UNKNOWN, // 3130 7089 HANGUL, // 3131..318E 7090 UNKNOWN, // 318F 7091 COMMON, // 3190..319F 7092 BOPOMOFO, // 31A0..31BA 7093 UNKNOWN, // 31BB..31BF 7094 COMMON, // 31C0..31E3 7095 UNKNOWN, // 31E4..31EF 7096 KATAKANA, // 31F0..31FF 7097 HANGUL, // 3200..321E 7098 UNKNOWN, // 321F 7099 COMMON, // 3220..325F 7100 HANGUL, // 3260..327E 7101 COMMON, // 327F..32CF 7102 KATAKANA, // 32D0..32FE 7103 COMMON, // 32FF 7104 KATAKANA, // 3300..3357 7105 COMMON, // 3358..33FF 7106 HAN, // 3400..4DB5 7107 UNKNOWN, // 4DB6..4DBF 7108 COMMON, // 4DC0..4DFF 7109 HAN, // 4E00..9FEF 7110 UNKNOWN, // 9FF0..9FFF 7111 YI, // A000..A48C 7112 UNKNOWN, // A48D..A48F 7113 YI, // A490..A4C6 7114 UNKNOWN, // A4C7..A4CF 7115 LISU, // A4D0..A4FF 7116 VAI, // A500..A62B 7117 UNKNOWN, // A62C..A63F 7118 CYRILLIC, // A640..A69F 7119 BAMUM, // A6A0..A6F7 7120 UNKNOWN, // A6F8..A6FF 7121 COMMON, // A700..A721 7122 LATIN, // A722..A787 7123 COMMON, // A788..A78A 7124 LATIN, // A78B..A7B9 7125 UNKNOWN, // A7C0..A7F6 7126 LATIN, // A7F7..A7FF 7127 SYLOTI_NAGRI, // A800..A82B 7128 UNKNOWN, // A82C..A82F 7129 COMMON, // A830..A839 7130 UNKNOWN, // A83A..A83F 7131 PHAGS_PA, // A840..A877 7132 UNKNOWN, // A878..A87F 7133 SAURASHTRA, // A880..A8C5 7134 UNKNOWN, // A8C6..A8CD 7135 SAURASHTRA, // A8CE..A8D9 7136 UNKNOWN, // A8DA..A8DF 7137 DEVANAGARI, // A8E0..A8FF 7138 KAYAH_LI, // A900..A92D 7139 COMMON, // A92E 7140 KAYAH_LI, // A92F 7141 REJANG, // A930..A953 7142 UNKNOWN, // A954..A95E 7143 REJANG, // A95F 7144 HANGUL, // A960..A97C 7145 UNKNOWN, // A97D..A97F 7146 JAVANESE, // A980..A9CD 7147 UNKNOWN, // A9CE 7148 COMMON, // A9CF 7149 JAVANESE, // A9D0..A9D9 7150 UNKNOWN, // A9DA..A9DD 7151 JAVANESE, // A9DE..A9DF 7152 MYANMAR, // A9E0..A9FE 7153 UNKNOWN, // A9FF 7154 CHAM, // AA00..AA36 7155 UNKNOWN, // AA37..AA3F 7156 CHAM, // AA40..AA4D 7157 UNKNOWN, // AA4E..AA4F 7158 CHAM, // AA50..AA59 7159 UNKNOWN, // AA5A..AA5B 7160 CHAM, // AA5C..AA5F 7161 MYANMAR, // AA60..AA7F 7162 TAI_VIET, // AA80..AAC2 7163 UNKNOWN, // AAC3..AADA 7164 TAI_VIET, // AADB..AADF 7165 MEETEI_MAYEK, // AAE0..AAF6 7166 UNKNOWN, // AAF7..AB00 7167 ETHIOPIC, // AB01..AB06 7168 UNKNOWN, // AB07..AB08 7169 ETHIOPIC, // AB09..AB0E 7170 UNKNOWN, // AB0F..AB10 7171 ETHIOPIC, // AB11..AB16 7172 UNKNOWN, // AB17..AB1F 7173 ETHIOPIC, // AB20..AB26 7174 UNKNOWN, // AB27 7175 ETHIOPIC, // AB28..AB2E 7176 UNKNOWN, // AB2F 7177 LATIN, // AB30..AB5A 7178 COMMON, // AB5B 7179 LATIN, // AB5C..AB64 7180 GREEK, // AB65 7181 UNKNOWN, // AB66..AB6F 7182 CHEROKEE, // AB70..ABBF 7183 MEETEI_MAYEK, // ABC0..ABED 7184 UNKNOWN, // ABEE..ABEF 7185 MEETEI_MAYEK, // ABF0..ABF9 7186 UNKNOWN, // ABFA..ABFF 7187 HANGUL, // AC00..D7A3 7188 UNKNOWN, // D7A4..D7AF 7189 HANGUL, // D7B0..D7C6 7190 UNKNOWN, // D7C7..D7CA 7191 HANGUL, // D7CB..D7FB 7192 UNKNOWN, // D7FC..F8FF 7193 HAN, // F900..FA6D 7194 UNKNOWN, // FA6E..FA6F 7195 HAN, // FA70..FAD9 7196 UNKNOWN, // FADA..FAFF 7197 LATIN, // FB00..FB06 7198 UNKNOWN, // FB07..FB12 7199 ARMENIAN, // FB13..FB17 7200 UNKNOWN, // FB18..FB1C 7201 HEBREW, // FB1D..FB36 7202 UNKNOWN, // FB37 7203 HEBREW, // FB38..FB3C 7204 UNKNOWN, // FB3D 7205 HEBREW, // FB3E 7206 UNKNOWN, // FB3F 7207 HEBREW, // FB40..FB41 7208 UNKNOWN, // FB42 7209 HEBREW, // FB43..FB44 7210 UNKNOWN, // FB45 7211 HEBREW, // FB46..FB4F 7212 ARABIC, // FB50..FBC1 7213 UNKNOWN, // FBC2..FBD2 7214 ARABIC, // FBD3..FD3D 7215 COMMON, // FD3E..FD3F 7216 UNKNOWN, // FD40..FD4F 7217 ARABIC, // FD50..FD8F 7218 UNKNOWN, // FD90..FD91 7219 ARABIC, // FD92..FDC7 7220 UNKNOWN, // FDC8..FDEF 7221 ARABIC, // FDF0..FDFD 7222 UNKNOWN, // FDFE..FDFF 7223 INHERITED, // FE00..FE0F 7224 COMMON, // FE10..FE19 7225 UNKNOWN, // FE1A..FE1F 7226 INHERITED, // FE20..FE2D 7227 CYRILLIC, // FE2E..FE2F 7228 COMMON, // FE30..FE52 7229 UNKNOWN, // FE53 7230 COMMON, // FE54..FE66 7231 UNKNOWN, // FE67 7232 COMMON, // FE68..FE6B 7233 UNKNOWN, // FE6C..FE6F 7234 ARABIC, // FE70..FE74 7235 UNKNOWN, // FE75 7236 ARABIC, // FE76..FEFC 7237 UNKNOWN, // FEFD..FEFE 7238 COMMON, // FEFF 7239 UNKNOWN, // FF00 7240 COMMON, // FF01..FF20 7241 LATIN, // FF21..FF3A 7242 COMMON, // FF3B..FF40 7243 LATIN, // FF41..FF5A 7244 COMMON, // FF5B..FF65 7245 KATAKANA, // FF66..FF6F 7246 COMMON, // FF70 7247 KATAKANA, // FF71..FF9D 7248 COMMON, // FF9E..FF9F 7249 HANGUL, // FFA0..FFBE 7250 UNKNOWN, // FFBF..FFC1 7251 HANGUL, // FFC2..FFC7 7252 UNKNOWN, // FFC8..FFC9 7253 HANGUL, // FFCA..FFCF 7254 UNKNOWN, // FFD0..FFD1 7255 HANGUL, // FFD2..FFD7 7256 UNKNOWN, // FFD8..FFD9 7257 HANGUL, // FFDA..FFDC 7258 UNKNOWN, // FFDD..FFDF 7259 COMMON, // FFE0..FFE6 7260 UNKNOWN, // FFE7 7261 COMMON, // FFE8..FFEE 7262 UNKNOWN, // FFEF..FFF8 7263 COMMON, // FFF9..FFFD 7264 UNKNOWN, // FFFE..FFFF 7265 LINEAR_B, // 10000..1000B 7266 UNKNOWN, // 1000C 7267 LINEAR_B, // 1000D..10026 7268 UNKNOWN, // 10027 7269 LINEAR_B, // 10028..1003A 7270 UNKNOWN, // 1003B 7271 LINEAR_B, // 1003C..1003D 7272 UNKNOWN, // 1003E 7273 LINEAR_B, // 1003F..1004D 7274 UNKNOWN, // 1004E..1004F 7275 LINEAR_B, // 10050..1005D 7276 UNKNOWN, // 1005E..1007F 7277 LINEAR_B, // 10080..100FA 7278 UNKNOWN, // 100FB..100FF 7279 COMMON, // 10100..10102 7280 UNKNOWN, // 10103..10106 7281 COMMON, // 10107..10133 7282 UNKNOWN, // 10134..10136 7283 COMMON, // 10137..1013F 7284 GREEK, // 10140..1018E 7285 UNKNOWN, // 1018F 7286 COMMON, // 10190..1019B 7287 UNKNOWN, // 1019C..1019F 7288 GREEK, // 101A0 7289 UNKNOWN, // 101A1..101CF 7290 COMMON, // 101D0..101FC 7291 INHERITED, // 101FD 7292 UNKNOWN, // 101FE..1027F 7293 LYCIAN, // 10280..1029C 7294 UNKNOWN, // 1029D..1029F 7295 CARIAN, // 102A0..102D0 7296 UNKNOWN, // 102D1..102DF 7297 INHERITED, // 102E0 7298 COMMON, // 102E1..102FB 7299 UNKNOWN, // 102FC..102FF 7300 OLD_ITALIC, // 10300..10323 7301 UNKNOWN, // 10324..1032C 7302 OLD_ITALIC, // 1032D..1032F 7303 GOTHIC, // 10330..1034A 7304 UNKNOWN, // 1034B..1034F 7305 OLD_PERMIC, // 10350..1037A 7306 UNKNOWN, // 1037B..1037F 7307 UGARITIC, // 10380..1039D 7308 UNKNOWN, // 1039E 7309 UGARITIC, // 1039F 7310 OLD_PERSIAN, // 103A0..103C3 7311 UNKNOWN, // 103C4..103C7 7312 OLD_PERSIAN, // 103C8..103D5 7313 UNKNOWN, // 103D6..103FF 7314 DESERET, // 10400..1044F 7315 SHAVIAN, // 10450..1047F 7316 OSMANYA, // 10480..1049D 7317 UNKNOWN, // 1049E..1049F 7318 OSMANYA, // 104A0..104A9 7319 UNKNOWN, // 104AA..104AF 7320 OSAGE, // 104B0..104D3; 7321 UNKNOWN, // 104D4..104D7; 7322 OSAGE, // 104D8..104FB; 7323 UNKNOWN, // 104FC..104FF; 7324 ELBASAN, // 10500..10527 7325 UNKNOWN, // 10528..1052F 7326 CAUCASIAN_ALBANIAN, // 10530..10563 7327 UNKNOWN, // 10564..1056E 7328 CAUCASIAN_ALBANIAN, // 1056F 7329 UNKNOWN, // 10570..105FF 7330 LINEAR_A, // 10600..10736 7331 UNKNOWN, // 10737..1073F 7332 LINEAR_A, // 10740..10755 7333 UNKNOWN, // 10756..1075F 7334 LINEAR_A, // 10760..10767 7335 UNKNOWN, // 10768..107FF 7336 CYPRIOT, // 10800..10805 7337 UNKNOWN, // 10806..10807 7338 CYPRIOT, // 10808 7339 UNKNOWN, // 10809 7340 CYPRIOT, // 1080A..10835 7341 UNKNOWN, // 10836 7342 CYPRIOT, // 10837..10838 7343 UNKNOWN, // 10839..1083B 7344 CYPRIOT, // 1083C 7345 UNKNOWN, // 1083D..1083E 7346 CYPRIOT, // 1083F 7347 IMPERIAL_ARAMAIC, // 10840..10855 7348 UNKNOWN, // 10856 7349 IMPERIAL_ARAMAIC, // 10857..1085F 7350 PALMYRENE, // 10860..1087F 7351 NABATAEAN, // 10880..1089E 7352 UNKNOWN, // 1089F..108A6 7353 NABATAEAN, // 108A7..108AF 7354 UNKNOWN, // 108B0..108DF 7355 HATRAN, // 108E0..108F2 7356 UNKNOWN, // 108F3 7357 HATRAN, // 108F4..108F5 7358 UNKNOWN, // 108F6..108FA 7359 HATRAN, // 108FB..108FF 7360 PHOENICIAN, // 10900..1091B 7361 UNKNOWN, // 1091C..1091E 7362 PHOENICIAN, // 1091F 7363 LYDIAN, // 10920..10939 7364 UNKNOWN, // 1093A..1093E 7365 LYDIAN, // 1093F 7366 UNKNOWN, // 10940..1097F 7367 MEROITIC_HIEROGLYPHS, // 10980..1099F 7368 MEROITIC_CURSIVE, // 109A0..109B7 7369 UNKNOWN, // 109B8..109BB 7370 MEROITIC_CURSIVE, // 109BC..109CF 7371 UNKNOWN, // 109D0..109D1 7372 MEROITIC_CURSIVE, // 109D2..109FF 7373 KHAROSHTHI, // 10A00..10A03 7374 UNKNOWN, // 10A04 7375 KHAROSHTHI, // 10A05..10A06 7376 UNKNOWN, // 10A07..10A0B 7377 KHAROSHTHI, // 10A0C..10A13 7378 UNKNOWN, // 10A14 7379 KHAROSHTHI, // 10A15..10A17 7380 UNKNOWN, // 10A18 7381 KHAROSHTHI, // 10A19..10A35 7382 UNKNOWN, // 10A36..10A37 7383 KHAROSHTHI, // 10A38..10A3A 7384 UNKNOWN, // 10A3B..10A3E 7385 KHAROSHTHI, // 10A3F..10A48 7386 UNKNOWN, // 10A49..10A4F 7387 KHAROSHTHI, // 10A50..10A58 7388 UNKNOWN, // 10A59..10A5F 7389 OLD_SOUTH_ARABIAN, // 10A60..10A7F 7390 OLD_NORTH_ARABIAN, // 10A80..10A9F 7391 UNKNOWN, // 10AA0..10ABF 7392 MANICHAEAN, // 10AC0..10AE6 7393 UNKNOWN, // 10AE7..10AEA 7394 MANICHAEAN, // 10AEB..10AF6 7395 UNKNOWN, // 10AF7..10AFF 7396 AVESTAN, // 10B00..10B35 7397 UNKNOWN, // 10B36..10B38 7398 AVESTAN, // 10B39..10B3F 7399 INSCRIPTIONAL_PARTHIAN, // 10B40..10B55 7400 UNKNOWN, // 10B56..10B57 7401 INSCRIPTIONAL_PARTHIAN, // 10B58..10B5F 7402 INSCRIPTIONAL_PAHLAVI, // 10B60..10B72 7403 UNKNOWN, // 10B73..10B77 7404 INSCRIPTIONAL_PAHLAVI, // 10B78..10B7F 7405 PSALTER_PAHLAVI, // 10B80..10B91 7406 UNKNOWN, // 10B92..10B98 7407 PSALTER_PAHLAVI, // 10B99..10B9C 7408 UNKNOWN, // 10B9D..10BA8 7409 PSALTER_PAHLAVI, // 10BA9..10BAF 7410 UNKNOWN, // 10BB0..10BFF 7411 OLD_TURKIC, // 10C00..10C48 7412 UNKNOWN, // 10C49..10C7F 7413 OLD_HUNGARIAN, // 10C80..10CB2 7414 UNKNOWN, // 10CB3..10CBF 7415 OLD_HUNGARIAN, // 10CC0..10CF2 7416 UNKNOWN, // 10CF3..10CF9 7417 OLD_HUNGARIAN, // 10CFA..10CFF 7418 HANIFI_ROHINGYA, // 10D00..10D27 7419 UNKNOWN, // 10D28..10D29 7420 HANIFI_ROHINGYA, // 10D30..10D39 7421 UNKNOWN, // 10D3A..10E5F 7422 ARABIC, // 10E60..10E7E 7423 UNKNOWN, // 10E7F..10EFF 7424 OLD_SOGDIAN, // 10F00..10F27 7425 UNKNOWN, // 10F28..10F2F 7426 SOGDIAN, // 10F30..10F59 7427 UNKNOWN, // 10F5A..10FFF 7428 BRAHMI, // 11000..1104D 7429 UNKNOWN, // 1104E..11051 7430 BRAHMI, // 11052..1106F 7431 UNKNOWN, // 11070..1107E 7432 BRAHMI, // 1107F 7433 KAITHI, // 11080..110C1 7434 UNKNOWN, // 110C2..110CC 7435 KAITHI, // 110CD 7436 UNKNOWN, // 110CE..110CF 7437 SORA_SOMPENG, // 110D0..110E8 7438 UNKNOWN, // 110E9..110EF 7439 SORA_SOMPENG, // 110F0..110F9 7440 UNKNOWN, // 110FA..110FF 7441 CHAKMA, // 11100..11134 7442 UNKNOWN, // 11135 7443 CHAKMA, // 11136..11146 7444 UNKNOWN, // 11147..1114F 7445 MAHAJANI, // 11150..11176 7446 UNKNOWN, // 11177..1117F 7447 SHARADA, // 11180..111CD 7448 UNKNOWN, // 111CE..111CF 7449 SHARADA, // 111D0..111DF 7450 UNKNOWN, // 111E0 7451 SINHALA, // 111E1..111F4 7452 UNKNOWN, // 111F5..111FF 7453 KHOJKI, // 11200..11211 7454 UNKNOWN, // 11212 7455 KHOJKI, // 11213..1123E 7456 UNKNOWN, // 1123F..1127F 7457 MULTANI, // 11280..11286 7458 UNKNOWN, // 11287 7459 MULTANI, // 11288 7460 UNKNOWN, // 11289 7461 MULTANI, // 1128A..1128D 7462 UNKNOWN, // 1128E 7463 MULTANI, // 1128F..1129D 7464 UNKNOWN, // 1129E 7465 MULTANI, // 1129F..112A9 7466 UNKNOWN, // 112AA..112AF 7467 KHUDAWADI, // 112B0..112EA 7468 UNKNOWN, // 112EB..112EF 7469 KHUDAWADI, // 112F0..112F9 7470 UNKNOWN, // 112FA..112FF 7471 GRANTHA, // 11300..11303 7472 UNKNOWN, // 11304 7473 GRANTHA, // 11305..1130C 7474 UNKNOWN, // 1130D..1130E 7475 GRANTHA, // 1130F..11310 7476 UNKNOWN, // 11311..11312 7477 GRANTHA, // 11313..11328 7478 UNKNOWN, // 11329 7479 GRANTHA, // 1132A..11330 7480 UNKNOWN, // 11331 7481 GRANTHA, // 11332..11333 7482 UNKNOWN, // 11334 7483 GRANTHA, // 11335..11339 7484 UNKNOWN, // 1133A 7485 INHERITED, // 1133B 7486 GRANTHA, // 1133C..11344 7487 UNKNOWN, // 11345..11346 7488 GRANTHA, // 11347..11348 7489 UNKNOWN, // 11349..1134A 7490 GRANTHA, // 1134B..1134D 7491 UNKNOWN, // 1134E..1134F 7492 GRANTHA, // 11350 7493 UNKNOWN, // 11351..11356 7494 GRANTHA, // 11357 7495 UNKNOWN, // 11358..1135C 7496 GRANTHA, // 1135D..11363 7497 UNKNOWN, // 11364..11365 7498 GRANTHA, // 11366..1136C 7499 UNKNOWN, // 1136D..1136F 7500 GRANTHA, // 11370..11374 7501 UNKNOWN, // 11375..113FF 7502 NEWA, // 11400..11459 7503 UNKNOWN, // 1145A 7504 NEWA, // 1145B 7505 UNKNOWN, // 1145C 7506 NEWA, // 1145D..1145E 7507 UNKNOWN, // 1145F..1147F 7508 TIRHUTA, // 11480..114C7 7509 UNKNOWN, // 114C8..114CF 7510 TIRHUTA, // 114D0..114D9 7511 UNKNOWN, // 114DA..1157F 7512 SIDDHAM, // 11580..115B5 7513 UNKNOWN, // 115B6..115B7 7514 SIDDHAM, // 115B8..115DD 7515 UNKNOWN, // 115DE..115FF 7516 MODI, // 11600..11644 7517 UNKNOWN, // 11645..1164F 7518 MODI, // 11650..11659 7519 UNKNOWN, // 1165A..1165F 7520 MONGOLIAN, // 11660..1166C 7521 UNKNOWN, // 1166D..1167F 7522 TAKRI, // 11680..116B7 7523 UNKNOWN, // 116B8..116BF 7524 TAKRI, // 116C0..116C9 7525 UNKNOWN, // 116CA..116FF 7526 AHOM, // 11700..1171A 7527 UNKNOWN, // 1171B..1171C 7528 AHOM, // 1171D..1172B 7529 UNKNOWN, // 1172C..1172F 7530 AHOM, // 11730..1173F 7531 UNKNOWN, // 11740..117FF 7532 DOGRA, // 11800..1183B 7533 UNKNOWN, // 1183C..1189F 7534 WARANG_CITI, // 118A0..118F2 7535 UNKNOWN, // 118F3..118FE 7536 WARANG_CITI, // 118FF 7537 UNKNOWN, // 11900..119FF 7538 ZANABAZAR_SQUARE, // 11A00..11A47 7539 UNKNOWN, // 11A48..11A4F 7540 SOYOMBO, // 11A50..11A83 7541 UNKNOWN, // 11A84..11A85 7542 SOYOMBO, // 11A86..11AA2 7543 UNKNOWN, // 11AA3..11ABF 7544 PAU_CIN_HAU, // 11AC0..11AF8 7545 UNKNOWN, // 11AF9..11BFF 7546 BHAIKSUKI, // 11C00..11C08 7547 UNKNOWN, // 11C09 7548 BHAIKSUKI, // 11C0A..11C36 7549 UNKNOWN, // 11C37 7550 BHAIKSUKI, // 11C38..11C45 7551 UNKNOWN, // 11C46..11C49 7552 BHAIKSUKI, // 11C50..11C6C 7553 UNKNOWN, // 11C6D..11C6F 7554 MARCHEN, // 11C70..11C8F 7555 UNKNOWN, // 11C90..11C91 7556 MARCHEN, // 11C92..11CA7 7557 UNKNOWN, // 11CA8 7558 MARCHEN, // 11CA9..11CB6 7559 UNKNOWN, // 11CB7..11CFF 7560 MASARAM_GONDI, // 11D00..11D06 7561 UNKNOWN, // 11D07 7562 MASARAM_GONDI, // 11D08..11D09 7563 UNKNOWN, // 11D0A 7564 MASARAM_GONDI, // 11D0B..11D36 7565 UNKNOWN, // 11D37..11D39 7566 MASARAM_GONDI, // 11D3A 7567 UNKNOWN, // 11D3B 7568 MASARAM_GONDI, // 11D3C..11D3D 7569 UNKNOWN, // 11D3E 7570 MASARAM_GONDI, // 11D3F..11D47 7571 UNKNOWN, // 11D48..11D49 7572 MASARAM_GONDI, // 11D50..11D59 7573 UNKNOWN, // 11D5A..11D5F 7574 GUNJALA_GONDI, // 11D60..11D68 7575 UNKNOWN, // 11D69 7576 GUNJALA_GONDI, // 11D6A..11D8E 7577 UNKNOWN, // 11D8F 7578 GUNJALA_GONDI, // 11D90..11D91 7579 UNKNOWN, // 11D92 7580 GUNJALA_GONDI, // 11D93..11D98 7581 UNKNOWN, // 11D99 7582 GUNJALA_GONDI, // 11DA0..11DA9 7583 UNKNOWN, // 11DAA..11DFF 7584 MAKASAR, // 11EE0..11EF8 7585 UNKNOWN, // 11EF9..11FFF 7586 CUNEIFORM, // 12000..12399 7587 UNKNOWN, // 1239A..123FF 7588 CUNEIFORM, // 12400..1246E 7589 UNKNOWN, // 1246F 7590 CUNEIFORM, // 12470..12474 7591 UNKNOWN, // 12475..1247F 7592 CUNEIFORM, // 12480..12543 7593 UNKNOWN, // 12544..12FFF 7594 EGYPTIAN_HIEROGLYPHS, // 13000..1342E 7595 UNKNOWN, // 1342F..143FF 7596 ANATOLIAN_HIEROGLYPHS, // 14400..14646 7597 UNKNOWN, // 14647..167FF 7598 BAMUM, // 16800..16A38 7599 UNKNOWN, // 16A39..16A3F 7600 MRO, // 16A40..16A5E 7601 UNKNOWN, // 16A5F 7602 MRO, // 16A60..16A69 7603 UNKNOWN, // 16A6A..16A6D 7604 MRO, // 16A6E..16A6F 7605 UNKNOWN, // 16A70..16ACF 7606 BASSA_VAH, // 16AD0..16AED 7607 UNKNOWN, // 16AEE..16AEF 7608 BASSA_VAH, // 16AF0..16AF5 7609 UNKNOWN, // 16AF6..16AFF 7610 PAHAWH_HMONG, // 16B00..16B45 7611 UNKNOWN, // 16B46..16B4F 7612 PAHAWH_HMONG, // 16B50..16B59 7613 UNKNOWN, // 16B5A 7614 PAHAWH_HMONG, // 16B5B..16B61 7615 UNKNOWN, // 16B62 7616 PAHAWH_HMONG, // 16B63..16B77 7617 UNKNOWN, // 16B78..16B7C 7618 PAHAWH_HMONG, // 16B7D..16B8F 7619 UNKNOWN, // 16B90..16E3F 7620 MEDEFAIDRIN, // 16E40..16E9A 7621 UNKNOWN, // 16E9B..16EFF 7622 MIAO, // 16F00..16F44 7623 UNKNOWN, // 16F45..16F4F 7624 MIAO, // 16F50..16F7E 7625 UNKNOWN, // 16F7F..16F8E 7626 MIAO, // 16F8F..16F9F 7627 UNKNOWN, // 16FA0..16FDF 7628 TANGUT, // 16FE0 7629 NUSHU, // 16FE1 7630 UNKNOWN, // 16FE2..16FFF 7631 TANGUT, // 17000..187F1 7632 UNKNOWN, // 187F2..187FF 7633 TANGUT, // 18800..18AF2 7634 UNKNOWN, // 18AF3..1AFFF 7635 KATAKANA, // 1B000 7636 HIRAGANA, // 1B001..1B11E 7637 UNKNOWN, // 1B11F..1B16F 7638 NUSHU, // 1B170..1B2FB 7639 UNKNOWN, // 1B2FC..1BBFF 7640 DUPLOYAN, // 1BC00..1BC6A 7641 UNKNOWN, // 1BC6B..1BC6F 7642 DUPLOYAN, // 1BC70..1BC7C 7643 UNKNOWN, // 1BC7D..1BC7F 7644 DUPLOYAN, // 1BC80..1BC88 7645 UNKNOWN, // 1BC89..1BC8F 7646 DUPLOYAN, // 1BC90..1BC99 7647 UNKNOWN, // 1BC9A..1BC9B 7648 DUPLOYAN, // 1BC9C..1BC9F 7649 COMMON, // 1BCA0..1BCA3 7650 UNKNOWN, // 1BCA4..1CFFF 7651 COMMON, // 1D000..1D0F5 7652 UNKNOWN, // 1D0F6..1D0FF 7653 COMMON, // 1D100..1D126 7654 UNKNOWN, // 1D127..1D128 7655 COMMON, // 1D129..1D166 7656 INHERITED, // 1D167..1D169 7657 COMMON, // 1D16A..1D17A 7658 INHERITED, // 1D17B..1D182 7659 COMMON, // 1D183..1D184 7660 INHERITED, // 1D185..1D18B 7661 COMMON, // 1D18C..1D1A9 7662 INHERITED, // 1D1AA..1D1AD 7663 COMMON, // 1D1AE..1D1E8 7664 UNKNOWN, // 1D1E9..1D1FF 7665 GREEK, // 1D200..1D245 7666 UNKNOWN, // 1D246..1D2DF 7667 COMMON, // 1D2E0..1D2F3 7668 UNKNOWN, // 1D2F4..1D2FF 7669 COMMON, // 1D300..1D356 7670 UNKNOWN, // 1D357..1D35F 7671 COMMON, // 1D360..1D378 7672 UNKNOWN, // 1D379..1D3FF 7673 COMMON, // 1D400..1D454 7674 UNKNOWN, // 1D455 7675 COMMON, // 1D456..1D49C 7676 UNKNOWN, // 1D49D 7677 COMMON, // 1D49E..1D49F 7678 UNKNOWN, // 1D4A0..1D4A1 7679 COMMON, // 1D4A2 7680 UNKNOWN, // 1D4A3..1D4A4 7681 COMMON, // 1D4A5..1D4A6 7682 UNKNOWN, // 1D4A7..1D4A8 7683 COMMON, // 1D4A9..1D4AC 7684 UNKNOWN, // 1D4AD 7685 COMMON, // 1D4AE..1D4B9 7686 UNKNOWN, // 1D4BA 7687 COMMON, // 1D4BB 7688 UNKNOWN, // 1D4BC 7689 COMMON, // 1D4BD..1D4C3 7690 UNKNOWN, // 1D4C4 7691 COMMON, // 1D4C5..1D505 7692 UNKNOWN, // 1D506 7693 COMMON, // 1D507..1D50A 7694 UNKNOWN, // 1D50B..1D50C 7695 COMMON, // 1D50D..1D514 7696 UNKNOWN, // 1D515 7697 COMMON, // 1D516..1D51C 7698 UNKNOWN, // 1D51D 7699 COMMON, // 1D51E..1D539 7700 UNKNOWN, // 1D53A 7701 COMMON, // 1D53B..1D53E 7702 UNKNOWN, // 1D53F 7703 COMMON, // 1D540..1D544 7704 UNKNOWN, // 1D545 7705 COMMON, // 1D546 7706 UNKNOWN, // 1D547..1D549 7707 COMMON, // 1D54A..1D550 7708 UNKNOWN, // 1D551 7709 COMMON, // 1D552..1D6A5 7710 UNKNOWN, // 1D6A6..1D6A7 7711 COMMON, // 1D6A8..1D7CB 7712 UNKNOWN, // 1D7CC..1D7CD 7713 COMMON, // 1D7CE..1D7FF 7714 SIGNWRITING, // 1D800..1DA8B 7715 UNKNOWN, // 1DA8C..1DA9A 7716 SIGNWRITING, // 1DA9B..1DA9F 7717 UNKNOWN, // 1DAA0 7718 SIGNWRITING, // 1DAA1..1DAAF 7719 UNKNOWN, // 1DAB0..1DFFF 7720 GLAGOLITIC, // 1E000..1E006 7721 UNKNOWN, // 1E007 7722 GLAGOLITIC, // 1E008..1E018 7723 UNKNOWN, // 1E019..1E01A 7724 GLAGOLITIC, // 1E01B..1E021 7725 UNKNOWN, // 1E022 7726 GLAGOLITIC, // 1E023..1E024 7727 UNKNOWN, // 1E025 7728 GLAGOLITIC, // 1E026..1E02A 7729 UNKNOWN, // 1E02B..1E7FF 7730 MENDE_KIKAKUI, // 1E800..1E8C4 7731 UNKNOWN, // 1E8C5..1E8C6 7732 MENDE_KIKAKUI, // 1E8C7..1E8D6 7733 UNKNOWN, // 1E8D7..1E8FF 7734 ADLAM, // 1E900..1E94A 7735 UNKNOWN, // 1E94B..1E94F 7736 ADLAM, // 1E950..1E959 7737 UNKNOWN, // 1E95A..1E95D 7738 ADLAM, // 1E95E..1E95F 7739 UNKNOWN, // 1E960..1EC70 7740 COMMON, // 1EC71..1ECB4 7741 UNKNOWN, // 1ECB5..1EDFF 7742 ARABIC, // 1EE00..1EE03 7743 UNKNOWN, // 1EE04 7744 ARABIC, // 1EE05..1EE1F 7745 UNKNOWN, // 1EE20 7746 ARABIC, // 1EE21..1EE22 7747 UNKNOWN, // 1EE23 7748 ARABIC, // 1EE24 7749 UNKNOWN, // 1EE25..1EE26 7750 ARABIC, // 1EE27 7751 UNKNOWN, // 1EE28 7752 ARABIC, // 1EE29..1EE32 7753 UNKNOWN, // 1EE33 7754 ARABIC, // 1EE34..1EE37 7755 UNKNOWN, // 1EE38 7756 ARABIC, // 1EE39 7757 UNKNOWN, // 1EE3A 7758 ARABIC, // 1EE3B 7759 UNKNOWN, // 1EE3C..1EE41 7760 ARABIC, // 1EE42 7761 UNKNOWN, // 1EE43..1EE46 7762 ARABIC, // 1EE47 7763 UNKNOWN, // 1EE48 7764 ARABIC, // 1EE49 7765 UNKNOWN, // 1EE4A 7766 ARABIC, // 1EE4B 7767 UNKNOWN, // 1EE4C 7768 ARABIC, // 1EE4D..1EE4F 7769 UNKNOWN, // 1EE50 7770 ARABIC, // 1EE51..1EE52 7771 UNKNOWN, // 1EE53 7772 ARABIC, // 1EE54 7773 UNKNOWN, // 1EE55..1EE56 7774 ARABIC, // 1EE57 7775 UNKNOWN, // 1EE58 7776 ARABIC, // 1EE59 7777 UNKNOWN, // 1EE5A 7778 ARABIC, // 1EE5B 7779 UNKNOWN, // 1EE5C 7780 ARABIC, // 1EE5D 7781 UNKNOWN, // 1EE5E 7782 ARABIC, // 1EE5F 7783 UNKNOWN, // 1EE60 7784 ARABIC, // 1EE61..1EE62 7785 UNKNOWN, // 1EE63 7786 ARABIC, // 1EE64 7787 UNKNOWN, // 1EE65..1EE66 7788 ARABIC, // 1EE67..1EE6A 7789 UNKNOWN, // 1EE6B 7790 ARABIC, // 1EE6C..1EE72 7791 UNKNOWN, // 1EE73 7792 ARABIC, // 1EE74..1EE77 7793 UNKNOWN, // 1EE78 7794 ARABIC, // 1EE79..1EE7C 7795 UNKNOWN, // 1EE7D 7796 ARABIC, // 1EE7E 7797 UNKNOWN, // 1EE7F 7798 ARABIC, // 1EE80..1EE89 7799 UNKNOWN, // 1EE8A 7800 ARABIC, // 1EE8B..1EE9B 7801 UNKNOWN, // 1EE9C..1EEA0 7802 ARABIC, // 1EEA1..1EEA3 7803 UNKNOWN, // 1EEA4 7804 ARABIC, // 1EEA5..1EEA9 7805 UNKNOWN, // 1EEAA 7806 ARABIC, // 1EEAB..1EEBB 7807 UNKNOWN, // 1EEBC..1EEEF 7808 ARABIC, // 1EEF0..1EEF1 7809 UNKNOWN, // 1EEF2..1EFFF 7810 COMMON, // 1F000..1F02B 7811 UNKNOWN, // 1F02C..1F02F 7812 COMMON, // 1F030..1F093 7813 UNKNOWN, // 1F094..1F09F 7814 COMMON, // 1F0A0..1F0AE 7815 UNKNOWN, // 1F0AF..1F0B0 7816 COMMON, // 1F0B1..1F0BF 7817 UNKNOWN, // 1F0C0 7818 COMMON, // 1F0C1..1F0CF 7819 UNKNOWN, // 1F0D0 7820 COMMON, // 1F0D1..1F0F5 7821 UNKNOWN, // 1F0F6..1F0FF 7822 COMMON, // 1F100..1F10C 7823 UNKNOWN, // 1F10D..1F10F 7824 COMMON, // 1F110..1F16B 7825 UNKNOWN, // 1F16C..1F16F 7826 COMMON, // 1F170..1F1AC 7827 UNKNOWN, // 1F1AD..1F1E5 7828 COMMON, // 1F1E6..1F1FF 7829 HIRAGANA, // 1F200 7830 COMMON, // 1F201..1F202 7831 UNKNOWN, // 1F203..1F20F 7832 COMMON, // 1F210..1F23B 7833 UNKNOWN, // 1F23C..1F23F 7834 COMMON, // 1F240..1F248 7835 UNKNOWN, // 1F249..1F24F 7836 COMMON, // 1F250..1F251 7837 UNKNOWN, // 1F252..1F25F 7838 COMMON, // 1F260..1F265 7839 UNKNOWN, // 1F266..1F2FF 7840 COMMON, // 1F300..1F6D4 7841 UNKNOWN, // 1F6D5..1F6DF 7842 COMMON, // 1F6E0..1F6EC 7843 UNKNOWN, // 1F6ED..1F6EF 7844 COMMON, // 1F6F0..1F6F9 7845 UNKNOWN, // 1F6FA..1F6FF 7846 COMMON, // 1F700..1F773 7847 UNKNOWN, // 1F774..1F77F 7848 COMMON, // 1F780..1F7D8 7849 UNKNOWN, // 1F7D9..1F7FF 7850 COMMON, // 1F800..1F80B 7851 UNKNOWN, // 1F80C..1F80F 7852 COMMON, // 1F810..1F847 7853 UNKNOWN, // 1F848..1F84F 7854 COMMON, // 1F850..1F859 7855 UNKNOWN, // 1F85A..1F85F 7856 COMMON, // 1F860..1F887 7857 UNKNOWN, // 1F888..1F88F 7858 COMMON, // 1F890..1F8AD 7859 UNKNOWN, // 1F8AE..1F8FF 7860 COMMON, // 1F900..1F90B 7861 UNKNOWN, // 1F90C..1F90F 7862 COMMON, // 1F910..1F93E 7863 UNKNOWN, // 1F93F 7864 COMMON, // 1F940..1F970 7865 UNKNOWN, // 1F971..1F972 7866 COMMON, // 1F973..1F976 7867 UNKNOWN, // 1F977..1F979 7868 COMMON, // 1F97A 7869 UNKNOWN, // 1F97B 7870 COMMON, // 1F97C..1F9A2 7871 UNKNOWN, // 1F9A3..1F9AF 7872 COMMON, // 1F9B0..1F9B9 7873 UNKNOWN, // 1F9BA..1F9BF 7874 COMMON, // 1F9C0..1F9C2 7875 UNKNOWN, // 1F9C3..1F9CF 7876 COMMON, // 1F9D0..1F9FF 7877 UNKNOWN, // 1FA00..1FA5F 7878 COMMON, // 1FA60..1FA6D 7879 UNKNOWN, // 1FA6E..1FFFF 7880 HAN, // 20000..2A6D6 7881 UNKNOWN, // 2A6D7..2A6FF 7882 HAN, // 2A700..2B734 7883 UNKNOWN, // 2B735..2B73F 7884 HAN, // 2B740..2B81D 7885 UNKNOWN, // 2B81E..2B81F 7886 HAN, // 2B820..2CEA1 7887 UNKNOWN, // 2CEA2..2CEAF 7888 HAN, // 2CEB0..2EBE0 7889 UNKNOWN, // 2EBE1..2F7FF 7890 HAN, // 2F800..2FA1D 7891 UNKNOWN, // 2FA1E..E0000 7892 COMMON, // E0001 7893 UNKNOWN, // E0002..E001F 7894 COMMON, // E0020..E007F 7895 UNKNOWN, // E0080..E00FF 7896 INHERITED, // E0100..E01EF 7897 UNKNOWN // E01F0..10FFFF 7898 }; 7899 7900 private static HashMap<String, Character.UnicodeScript> aliases; 7901 static { 7902 aliases = new HashMap<>((int)(149 / 0.75f + 1.0f)); 7903 aliases.put("ADLM", ADLAM); 7904 aliases.put("AGHB", CAUCASIAN_ALBANIAN); 7905 aliases.put("AHOM", AHOM); 7906 aliases.put("ARAB", ARABIC); 7907 aliases.put("ARMI", IMPERIAL_ARAMAIC); 7908 aliases.put("ARMN", ARMENIAN); 7909 aliases.put("AVST", AVESTAN); 7910 aliases.put("BALI", BALINESE); 7911 aliases.put("BAMU", BAMUM); 7912 aliases.put("BASS", BASSA_VAH); 7913 aliases.put("BATK", BATAK); 7914 aliases.put("BENG", BENGALI); 7915 aliases.put("BHKS", BHAIKSUKI); 7916 aliases.put("BOPO", BOPOMOFO); 7917 aliases.put("BRAH", BRAHMI); 7918 aliases.put("BRAI", BRAILLE); 7919 aliases.put("BUGI", BUGINESE); 7920 aliases.put("BUHD", BUHID); 7921 aliases.put("CAKM", CHAKMA); 7922 aliases.put("CANS", CANADIAN_ABORIGINAL); 7923 aliases.put("CARI", CARIAN); 7924 aliases.put("CHAM", CHAM); 7925 aliases.put("CHER", CHEROKEE); 7926 aliases.put("COPT", COPTIC); 7927 aliases.put("CPRT", CYPRIOT); 7928 aliases.put("CYRL", CYRILLIC); 7929 aliases.put("DEVA", DEVANAGARI); 7930 aliases.put("DOGR", DOGRA); 7931 aliases.put("DSRT", DESERET); 7932 aliases.put("DUPL", DUPLOYAN); 7933 aliases.put("EGYP", EGYPTIAN_HIEROGLYPHS); 7934 aliases.put("ELBA", ELBASAN); 7935 aliases.put("ETHI", ETHIOPIC); 7936 aliases.put("GEOR", GEORGIAN); 7937 aliases.put("GLAG", GLAGOLITIC); 7938 aliases.put("GONM", MASARAM_GONDI); 7939 aliases.put("GOTH", GOTHIC); 7940 aliases.put("GONG", GUNJALA_GONDI); 7941 aliases.put("GRAN", GRANTHA); 7942 aliases.put("GREK", GREEK); 7943 aliases.put("GUJR", GUJARATI); 7944 aliases.put("GURU", GURMUKHI); 7945 aliases.put("HANG", HANGUL); 7946 aliases.put("HANI", HAN); 7947 aliases.put("HANO", HANUNOO); 7948 aliases.put("HATR", HATRAN); 7949 aliases.put("HEBR", HEBREW); 7950 aliases.put("HIRA", HIRAGANA); 7951 aliases.put("HLUW", ANATOLIAN_HIEROGLYPHS); 7952 aliases.put("HMNG", PAHAWH_HMONG); 7953 // it appears we don't have the KATAKANA_OR_HIRAGANA 7954 //aliases.put("HRKT", KATAKANA_OR_HIRAGANA); 7955 aliases.put("HUNG", OLD_HUNGARIAN); 7956 aliases.put("ITAL", OLD_ITALIC); 7957 aliases.put("JAVA", JAVANESE); 7958 aliases.put("KALI", KAYAH_LI); 7959 aliases.put("KANA", KATAKANA); 7960 aliases.put("KHAR", KHAROSHTHI); 7961 aliases.put("KHMR", KHMER); 7962 aliases.put("KHOJ", KHOJKI); 7963 aliases.put("KNDA", KANNADA); 7964 aliases.put("KTHI", KAITHI); 7965 aliases.put("LANA", TAI_THAM); 7966 aliases.put("LAOO", LAO); 7967 aliases.put("LATN", LATIN); 7968 aliases.put("LEPC", LEPCHA); 7969 aliases.put("LIMB", LIMBU); 7970 aliases.put("LINA", LINEAR_A); 7971 aliases.put("LINB", LINEAR_B); 7972 aliases.put("LISU", LISU); 7973 aliases.put("LYCI", LYCIAN); 7974 aliases.put("LYDI", LYDIAN); 7975 aliases.put("MAHJ", MAHAJANI); 7976 aliases.put("MAKA", MAKASAR); 7977 aliases.put("MARC", MARCHEN); 7978 aliases.put("MAND", MANDAIC); 7979 aliases.put("MANI", MANICHAEAN); 7980 aliases.put("MEDF", MEDEFAIDRIN); 7981 aliases.put("MEND", MENDE_KIKAKUI); 7982 aliases.put("MERC", MEROITIC_CURSIVE); 7983 aliases.put("MERO", MEROITIC_HIEROGLYPHS); 7984 aliases.put("MLYM", MALAYALAM); 7985 aliases.put("MODI", MODI); 7986 aliases.put("MONG", MONGOLIAN); 7987 aliases.put("MROO", MRO); 7988 aliases.put("MTEI", MEETEI_MAYEK); 7989 aliases.put("MULT", MULTANI); 7990 aliases.put("MYMR", MYANMAR); 7991 aliases.put("NARB", OLD_NORTH_ARABIAN); 7992 aliases.put("NBAT", NABATAEAN); 7993 aliases.put("NEWA", NEWA); 7994 aliases.put("NKOO", NKO); 7995 aliases.put("NSHU", NUSHU); 7996 aliases.put("OGAM", OGHAM); 7997 aliases.put("OLCK", OL_CHIKI); 7998 aliases.put("ORKH", OLD_TURKIC); 7999 aliases.put("ORYA", ORIYA); 8000 aliases.put("OSGE", OSAGE); 8001 aliases.put("OSMA", OSMANYA); 8002 aliases.put("PALM", PALMYRENE); 8003 aliases.put("PAUC", PAU_CIN_HAU); 8004 aliases.put("PERM", OLD_PERMIC); 8005 aliases.put("PHAG", PHAGS_PA); 8006 aliases.put("PHLI", INSCRIPTIONAL_PAHLAVI); 8007 aliases.put("PHLP", PSALTER_PAHLAVI); 8008 aliases.put("PHNX", PHOENICIAN); 8009 aliases.put("PLRD", MIAO); 8010 aliases.put("PRTI", INSCRIPTIONAL_PARTHIAN); 8011 aliases.put("RJNG", REJANG); 8012 aliases.put("ROHG", HANIFI_ROHINGYA); 8013 aliases.put("RUNR", RUNIC); 8014 aliases.put("SAMR", SAMARITAN); 8015 aliases.put("SARB", OLD_SOUTH_ARABIAN); 8016 aliases.put("SAUR", SAURASHTRA); 8017 aliases.put("SGNW", SIGNWRITING); 8018 aliases.put("SHAW", SHAVIAN); 8019 aliases.put("SHRD", SHARADA); 8020 aliases.put("SIDD", SIDDHAM); 8021 aliases.put("SIND", KHUDAWADI); 8022 aliases.put("SINH", SINHALA); 8023 aliases.put("SOGD", SOGDIAN); 8024 aliases.put("SOGO", OLD_SOGDIAN); 8025 aliases.put("SORA", SORA_SOMPENG); 8026 aliases.put("SOYO", SOYOMBO); 8027 aliases.put("SUND", SUNDANESE); 8028 aliases.put("SYLO", SYLOTI_NAGRI); 8029 aliases.put("SYRC", SYRIAC); 8030 aliases.put("TAGB", TAGBANWA); 8031 aliases.put("TAKR", TAKRI); 8032 aliases.put("TALE", TAI_LE); 8033 aliases.put("TALU", NEW_TAI_LUE); 8034 aliases.put("TAML", TAMIL); 8035 aliases.put("TANG", TANGUT); 8036 aliases.put("TAVT", TAI_VIET); 8037 aliases.put("TELU", TELUGU); 8038 aliases.put("TFNG", TIFINAGH); 8039 aliases.put("TGLG", TAGALOG); 8040 aliases.put("THAA", THAANA); 8041 aliases.put("THAI", THAI); 8042 aliases.put("TIBT", TIBETAN); 8043 aliases.put("TIRH", TIRHUTA); 8044 aliases.put("UGAR", UGARITIC); 8045 aliases.put("VAII", VAI); 8046 aliases.put("WARA", WARANG_CITI); 8047 aliases.put("XPEO", OLD_PERSIAN); 8048 aliases.put("XSUX", CUNEIFORM); 8049 aliases.put("YIII", YI); 8050 aliases.put("ZANB", ZANABAZAR_SQUARE); 8051 aliases.put("ZINH", INHERITED); 8052 aliases.put("ZYYY", COMMON); 8053 aliases.put("ZZZZ", UNKNOWN); 8054 } 8055 8056 /** 8057 * Returns the enum constant representing the Unicode script of which 8058 * the given character (Unicode code point) is assigned to. 8059 * 8060 * @param codePoint the character (Unicode code point) in question. 8061 * @return The {@code UnicodeScript} constant representing the 8062 * Unicode script of which this character is assigned to. 8063 * 8064 * @throws IllegalArgumentException if the specified 8065 * {@code codePoint} is an invalid Unicode code point. 8066 * @see Character#isValidCodePoint(int) 8067 * 8068 */ 8069 public static UnicodeScript of(int codePoint) { 8070 if (!isValidCodePoint(codePoint)) 8071 throw new IllegalArgumentException( 8072 String.format("Not a valid Unicode code point: 0x%X", codePoint)); 8073 int type = getType(codePoint); 8074 // leave SURROGATE and PRIVATE_USE for table lookup 8075 if (type == UNASSIGNED) 8076 return UNKNOWN; 8077 int index = Arrays.binarySearch(scriptStarts, codePoint); 8078 if (index < 0) 8079 index = -index - 2; 8080 return scripts[index]; 8081 } 8082 8083 /** 8084 * Returns the UnicodeScript constant with the given Unicode script 8085 * name or the script name alias. Script names and their aliases are 8086 * determined by The Unicode Standard. The files {@code Scripts<version>.txt} 8087 * and {@code PropertyValueAliases<version>.txt} define script names 8088 * and the script name aliases for a particular version of the 8089 * standard. The {@link Character} class specifies the version of 8090 * the standard that it supports. 8091 * <p> 8092 * Character case is ignored for all of the valid script names. 8093 * The en_US locale's case mapping rules are used to provide 8094 * case-insensitive string comparisons for script name validation. 8095 * 8096 * @param scriptName A {@code UnicodeScript} name. 8097 * @return The {@code UnicodeScript} constant identified 8098 * by {@code scriptName} 8099 * @throws IllegalArgumentException if {@code scriptName} is an 8100 * invalid name 8101 * @throws NullPointerException if {@code scriptName} is null 8102 */ 8103 public static final UnicodeScript forName(String scriptName) { 8104 scriptName = scriptName.toUpperCase(Locale.ENGLISH); 8105 //.replace(' ', '_')); 8106 UnicodeScript sc = aliases.get(scriptName); 8107 if (sc != null) 8108 return sc; 8109 return valueOf(scriptName); 8110 } 8111 } 8112 8113 /** 8114 * The value of the {@code Character}. 8115 * 8116 * @serial 8117 */ 8118 private final char value; 8119 8120 /** use serialVersionUID from JDK 1.0.2 for interoperability */ 8121 private static final long serialVersionUID = 3786198910865385080L; 8122 8123 /** 8124 * Constructs a newly allocated {@code Character} object that 8125 * represents the specified {@code char} value. 8126 * 8127 * @param value the value to be represented by the 8128 * {@code Character} object. 8129 * 8130 * @deprecated 8131 * It is rarely appropriate to use this constructor. The static factory 8132 * {@link #valueOf(char)} is generally a better choice, as it is 8133 * likely to yield significantly better space and time performance. 8134 */ 8135 @Deprecated(since="9") 8136 public Character(char value) { 8137 this.value = value; 8138 } 8139 8140 private static class CharacterCache { 8141 private CharacterCache(){} 8142 8143 static final Character[] cache; 8144 static Character[] archivedCache; 8145 8146 static { 8147 int size = 127 + 1; 8148 8149 // Load and use the archived cache if it exists 8150 VM.initializeFromArchive(CharacterCache.class); 8151 if (archivedCache == null || archivedCache.length != size) { 8152 Character[] c = new Character[size]; 8153 for (int i = 0; i < size; i++) { 8154 c[i] = new Character((char) i); 8155 } 8156 archivedCache = c; 8157 } 8158 cache = archivedCache; 8159 } 8160 } 8161 8162 /** 8163 * Returns a {@code Character} instance representing the specified 8164 * {@code char} value. 8165 * If a new {@code Character} instance is not required, this method 8166 * should generally be used in preference to the constructor 8167 * {@link #Character(char)}, as this method is likely to yield 8168 * significantly better space and time performance by caching 8169 * frequently requested values. 8170 * 8171 * This method will always cache values in the range {@code 8172 * '\u005Cu0000'} to {@code '\u005Cu007F'}, inclusive, and may 8173 * cache other values outside of this range. 8174 * 8175 * @param c a char value. 8176 * @return a {@code Character} instance representing {@code c}. 8177 * @since 1.5 8178 */ 8179 @HotSpotIntrinsicCandidate 8180 public static Character valueOf(char c) { 8181 if (c <= 127) { // must cache 8182 return CharacterCache.cache[(int)c]; 8183 } 8184 return new Character(c); 8185 } 8186 8187 /** 8188 * Returns the value of this {@code Character} object. 8189 * @return the primitive {@code char} value represented by 8190 * this object. 8191 */ 8192 @HotSpotIntrinsicCandidate 8193 public char charValue() { 8194 return value; 8195 } 8196 8197 /** 8198 * Returns a hash code for this {@code Character}; equal to the result 8199 * of invoking {@code charValue()}. 8200 * 8201 * @return a hash code value for this {@code Character} 8202 */ 8203 @Override 8204 public int hashCode() { 8205 return Character.hashCode(value); 8206 } 8207 8208 /** 8209 * Returns a hash code for a {@code char} value; compatible with 8210 * {@code Character.hashCode()}. 8211 * 8212 * @since 1.8 8213 * 8214 * @param value The {@code char} for which to return a hash code. 8215 * @return a hash code value for a {@code char} value. 8216 */ 8217 public static int hashCode(char value) { 8218 return (int)value; 8219 } 8220 8221 /** 8222 * Compares this object against the specified object. 8223 * The result is {@code true} if and only if the argument is not 8224 * {@code null} and is a {@code Character} object that 8225 * represents the same {@code char} value as this object. 8226 * 8227 * @param obj the object to compare with. 8228 * @return {@code true} if the objects are the same; 8229 * {@code false} otherwise. 8230 */ 8231 public boolean equals(Object obj) { 8232 if (obj instanceof Character) { 8233 return value == ((Character)obj).charValue(); 8234 } 8235 return false; 8236 } 8237 8238 /** 8239 * Returns a {@code String} object representing this 8240 * {@code Character}'s value. The result is a string of 8241 * length 1 whose sole component is the primitive 8242 * {@code char} value represented by this 8243 * {@code Character} object. 8244 * 8245 * @return a string representation of this object. 8246 */ 8247 public String toString() { 8248 char buf[] = {value}; 8249 return String.valueOf(buf); 8250 } 8251 8252 /** 8253 * Returns a {@code String} object representing the 8254 * specified {@code char}. The result is a string of length 8255 * 1 consisting solely of the specified {@code char}. 8256 * 8257 * @apiNote This method cannot handle <a 8258 * href="#supplementary"> supplementary characters</a>. To support 8259 * all Unicode characters, including supplementary characters, use 8260 * the {@link #toString(int)} method. 8261 * 8262 * @param c the {@code char} to be converted 8263 * @return the string representation of the specified {@code char} 8264 * @since 1.4 8265 */ 8266 public static String toString(char c) { 8267 return String.valueOf(c); 8268 } 8269 8270 /** 8271 * Returns a {@code String} object representing the 8272 * specified character (Unicode code point). The result is a string of 8273 * length 1 or 2, consisting solely of the specified {@code codePoint}. 8274 * 8275 * @param codePoint the {@code codePoint} to be converted 8276 * @return the string representation of the specified {@code codePoint} 8277 * @throws IllegalArgumentException if the specified 8278 * {@code codePoint} is not a {@linkplain #isValidCodePoint 8279 * valid Unicode code point}. 8280 * @since 11 8281 */ 8282 public static String toString(int codePoint) { 8283 return String.valueOfCodePoint(codePoint); 8284 } 8285 8286 /** 8287 * Determines whether the specified code point is a valid 8288 * <a href="http://www.unicode.org/glossary/#code_point"> 8289 * Unicode code point value</a>. 8290 * 8291 * @param codePoint the Unicode code point to be tested 8292 * @return {@code true} if the specified code point value is between 8293 * {@link #MIN_CODE_POINT} and 8294 * {@link #MAX_CODE_POINT} inclusive; 8295 * {@code false} otherwise. 8296 * @since 1.5 8297 */ 8298 public static boolean isValidCodePoint(int codePoint) { 8299 // Optimized form of: 8300 // codePoint >= MIN_CODE_POINT && codePoint <= MAX_CODE_POINT 8301 int plane = codePoint >>> 16; 8302 return plane < ((MAX_CODE_POINT + 1) >>> 16); 8303 } 8304 8305 /** 8306 * Determines whether the specified character (Unicode code point) 8307 * is in the <a href="#BMP">Basic Multilingual Plane (BMP)</a>. 8308 * Such code points can be represented using a single {@code char}. 8309 * 8310 * @param codePoint the character (Unicode code point) to be tested 8311 * @return {@code true} if the specified code point is between 8312 * {@link #MIN_VALUE} and {@link #MAX_VALUE} inclusive; 8313 * {@code false} otherwise. 8314 * @since 1.7 8315 */ 8316 public static boolean isBmpCodePoint(int codePoint) { 8317 return codePoint >>> 16 == 0; 8318 // Optimized form of: 8319 // codePoint >= MIN_VALUE && codePoint <= MAX_VALUE 8320 // We consistently use logical shift (>>>) to facilitate 8321 // additional runtime optimizations. 8322 } 8323 8324 /** 8325 * Determines whether the specified character (Unicode code point) 8326 * is in the <a href="#supplementary">supplementary character</a> range. 8327 * 8328 * @param codePoint the character (Unicode code point) to be tested 8329 * @return {@code true} if the specified code point is between 8330 * {@link #MIN_SUPPLEMENTARY_CODE_POINT} and 8331 * {@link #MAX_CODE_POINT} inclusive; 8332 * {@code false} otherwise. 8333 * @since 1.5 8334 */ 8335 public static boolean isSupplementaryCodePoint(int codePoint) { 8336 return codePoint >= MIN_SUPPLEMENTARY_CODE_POINT 8337 && codePoint < MAX_CODE_POINT + 1; 8338 } 8339 8340 /** 8341 * Determines if the given {@code char} value is a 8342 * <a href="http://www.unicode.org/glossary/#high_surrogate_code_unit"> 8343 * Unicode high-surrogate code unit</a> 8344 * (also known as <i>leading-surrogate code unit</i>). 8345 * 8346 * <p>Such values do not represent characters by themselves, 8347 * but are used in the representation of 8348 * <a href="#supplementary">supplementary characters</a> 8349 * in the UTF-16 encoding. 8350 * 8351 * @param ch the {@code char} value to be tested. 8352 * @return {@code true} if the {@code char} value is between 8353 * {@link #MIN_HIGH_SURROGATE} and 8354 * {@link #MAX_HIGH_SURROGATE} inclusive; 8355 * {@code false} otherwise. 8356 * @see Character#isLowSurrogate(char) 8357 * @see Character.UnicodeBlock#of(int) 8358 * @since 1.5 8359 */ 8360 public static boolean isHighSurrogate(char ch) { 8361 // Help VM constant-fold; MAX_HIGH_SURROGATE + 1 == MIN_LOW_SURROGATE 8362 return ch >= MIN_HIGH_SURROGATE && ch < (MAX_HIGH_SURROGATE + 1); 8363 } 8364 8365 /** 8366 * Determines if the given {@code char} value is a 8367 * <a href="http://www.unicode.org/glossary/#low_surrogate_code_unit"> 8368 * Unicode low-surrogate code unit</a> 8369 * (also known as <i>trailing-surrogate code unit</i>). 8370 * 8371 * <p>Such values do not represent characters by themselves, 8372 * but are used in the representation of 8373 * <a href="#supplementary">supplementary characters</a> 8374 * in the UTF-16 encoding. 8375 * 8376 * @param ch the {@code char} value to be tested. 8377 * @return {@code true} if the {@code char} value is between 8378 * {@link #MIN_LOW_SURROGATE} and 8379 * {@link #MAX_LOW_SURROGATE} inclusive; 8380 * {@code false} otherwise. 8381 * @see Character#isHighSurrogate(char) 8382 * @since 1.5 8383 */ 8384 public static boolean isLowSurrogate(char ch) { 8385 return ch >= MIN_LOW_SURROGATE && ch < (MAX_LOW_SURROGATE + 1); 8386 } 8387 8388 /** 8389 * Determines if the given {@code char} value is a Unicode 8390 * <i>surrogate code unit</i>. 8391 * 8392 * <p>Such values do not represent characters by themselves, 8393 * but are used in the representation of 8394 * <a href="#supplementary">supplementary characters</a> 8395 * in the UTF-16 encoding. 8396 * 8397 * <p>A char value is a surrogate code unit if and only if it is either 8398 * a {@linkplain #isLowSurrogate(char) low-surrogate code unit} or 8399 * a {@linkplain #isHighSurrogate(char) high-surrogate code unit}. 8400 * 8401 * @param ch the {@code char} value to be tested. 8402 * @return {@code true} if the {@code char} value is between 8403 * {@link #MIN_SURROGATE} and 8404 * {@link #MAX_SURROGATE} inclusive; 8405 * {@code false} otherwise. 8406 * @since 1.7 8407 */ 8408 public static boolean isSurrogate(char ch) { 8409 return ch >= MIN_SURROGATE && ch < (MAX_SURROGATE + 1); 8410 } 8411 8412 /** 8413 * Determines whether the specified pair of {@code char} 8414 * values is a valid 8415 * <a href="http://www.unicode.org/glossary/#surrogate_pair"> 8416 * Unicode surrogate pair</a>. 8417 8418 * <p>This method is equivalent to the expression: 8419 * <blockquote><pre>{@code 8420 * isHighSurrogate(high) && isLowSurrogate(low) 8421 * }</pre></blockquote> 8422 * 8423 * @param high the high-surrogate code value to be tested 8424 * @param low the low-surrogate code value to be tested 8425 * @return {@code true} if the specified high and 8426 * low-surrogate code values represent a valid surrogate pair; 8427 * {@code false} otherwise. 8428 * @since 1.5 8429 */ 8430 public static boolean isSurrogatePair(char high, char low) { 8431 return isHighSurrogate(high) && isLowSurrogate(low); 8432 } 8433 8434 /** 8435 * Determines the number of {@code char} values needed to 8436 * represent the specified character (Unicode code point). If the 8437 * specified character is equal to or greater than 0x10000, then 8438 * the method returns 2. Otherwise, the method returns 1. 8439 * 8440 * <p>This method doesn't validate the specified character to be a 8441 * valid Unicode code point. The caller must validate the 8442 * character value using {@link #isValidCodePoint(int) isValidCodePoint} 8443 * if necessary. 8444 * 8445 * @param codePoint the character (Unicode code point) to be tested. 8446 * @return 2 if the character is a valid supplementary character; 1 otherwise. 8447 * @see Character#isSupplementaryCodePoint(int) 8448 * @since 1.5 8449 */ 8450 public static int charCount(int codePoint) { 8451 return codePoint >= MIN_SUPPLEMENTARY_CODE_POINT ? 2 : 1; 8452 } 8453 8454 /** 8455 * Converts the specified surrogate pair to its supplementary code 8456 * point value. This method does not validate the specified 8457 * surrogate pair. The caller must validate it using {@link 8458 * #isSurrogatePair(char, char) isSurrogatePair} if necessary. 8459 * 8460 * @param high the high-surrogate code unit 8461 * @param low the low-surrogate code unit 8462 * @return the supplementary code point composed from the 8463 * specified surrogate pair. 8464 * @since 1.5 8465 */ 8466 public static int toCodePoint(char high, char low) { 8467 // Optimized form of: 8468 // return ((high - MIN_HIGH_SURROGATE) << 10) 8469 // + (low - MIN_LOW_SURROGATE) 8470 // + MIN_SUPPLEMENTARY_CODE_POINT; 8471 return ((high << 10) + low) + (MIN_SUPPLEMENTARY_CODE_POINT 8472 - (MIN_HIGH_SURROGATE << 10) 8473 - MIN_LOW_SURROGATE); 8474 } 8475 8476 /** 8477 * Returns the code point at the given index of the 8478 * {@code CharSequence}. If the {@code char} value at 8479 * the given index in the {@code CharSequence} is in the 8480 * high-surrogate range, the following index is less than the 8481 * length of the {@code CharSequence}, and the 8482 * {@code char} value at the following index is in the 8483 * low-surrogate range, then the supplementary code point 8484 * corresponding to this surrogate pair is returned. Otherwise, 8485 * the {@code char} value at the given index is returned. 8486 * 8487 * @param seq a sequence of {@code char} values (Unicode code 8488 * units) 8489 * @param index the index to the {@code char} values (Unicode 8490 * code units) in {@code seq} to be converted 8491 * @return the Unicode code point at the given index 8492 * @throws NullPointerException if {@code seq} is null. 8493 * @throws IndexOutOfBoundsException if the value 8494 * {@code index} is negative or not less than 8495 * {@link CharSequence#length() seq.length()}. 8496 * @since 1.5 8497 */ 8498 public static int codePointAt(CharSequence seq, int index) { 8499 char c1 = seq.charAt(index); 8500 if (isHighSurrogate(c1) && ++index < seq.length()) { 8501 char c2 = seq.charAt(index); 8502 if (isLowSurrogate(c2)) { 8503 return toCodePoint(c1, c2); 8504 } 8505 } 8506 return c1; 8507 } 8508 8509 /** 8510 * Returns the code point at the given index of the 8511 * {@code char} array. If the {@code char} value at 8512 * the given index in the {@code char} array is in the 8513 * high-surrogate range, the following index is less than the 8514 * length of the {@code char} array, and the 8515 * {@code char} value at the following index is in the 8516 * low-surrogate range, then the supplementary code point 8517 * corresponding to this surrogate pair is returned. Otherwise, 8518 * the {@code char} value at the given index is returned. 8519 * 8520 * @param a the {@code char} array 8521 * @param index the index to the {@code char} values (Unicode 8522 * code units) in the {@code char} array to be converted 8523 * @return the Unicode code point at the given index 8524 * @throws NullPointerException if {@code a} is null. 8525 * @throws IndexOutOfBoundsException if the value 8526 * {@code index} is negative or not less than 8527 * the length of the {@code char} array. 8528 * @since 1.5 8529 */ 8530 public static int codePointAt(char[] a, int index) { 8531 return codePointAtImpl(a, index, a.length); 8532 } 8533 8534 /** 8535 * Returns the code point at the given index of the 8536 * {@code char} array, where only array elements with 8537 * {@code index} less than {@code limit} can be used. If 8538 * the {@code char} value at the given index in the 8539 * {@code char} array is in the high-surrogate range, the 8540 * following index is less than the {@code limit}, and the 8541 * {@code char} value at the following index is in the 8542 * low-surrogate range, then the supplementary code point 8543 * corresponding to this surrogate pair is returned. Otherwise, 8544 * the {@code char} value at the given index is returned. 8545 * 8546 * @param a the {@code char} array 8547 * @param index the index to the {@code char} values (Unicode 8548 * code units) in the {@code char} array to be converted 8549 * @param limit the index after the last array element that 8550 * can be used in the {@code char} array 8551 * @return the Unicode code point at the given index 8552 * @throws NullPointerException if {@code a} is null. 8553 * @throws IndexOutOfBoundsException if the {@code index} 8554 * argument is negative or not less than the {@code limit} 8555 * argument, or if the {@code limit} argument is negative or 8556 * greater than the length of the {@code char} array. 8557 * @since 1.5 8558 */ 8559 public static int codePointAt(char[] a, int index, int limit) { 8560 if (index >= limit || limit < 0 || limit > a.length) { 8561 throw new IndexOutOfBoundsException(); 8562 } 8563 return codePointAtImpl(a, index, limit); 8564 } 8565 8566 // throws ArrayIndexOutOfBoundsException if index out of bounds 8567 static int codePointAtImpl(char[] a, int index, int limit) { 8568 char c1 = a[index]; 8569 if (isHighSurrogate(c1) && ++index < limit) { 8570 char c2 = a[index]; 8571 if (isLowSurrogate(c2)) { 8572 return toCodePoint(c1, c2); 8573 } 8574 } 8575 return c1; 8576 } 8577 8578 /** 8579 * Returns the code point preceding the given index of the 8580 * {@code CharSequence}. If the {@code char} value at 8581 * {@code (index - 1)} in the {@code CharSequence} is in 8582 * the low-surrogate range, {@code (index - 2)} is not 8583 * negative, and the {@code char} value at {@code (index - 2)} 8584 * in the {@code CharSequence} is in the 8585 * high-surrogate range, then the supplementary code point 8586 * corresponding to this surrogate pair is returned. Otherwise, 8587 * the {@code char} value at {@code (index - 1)} is 8588 * returned. 8589 * 8590 * @param seq the {@code CharSequence} instance 8591 * @param index the index following the code point that should be returned 8592 * @return the Unicode code point value before the given index. 8593 * @throws NullPointerException if {@code seq} is null. 8594 * @throws IndexOutOfBoundsException if the {@code index} 8595 * argument is less than 1 or greater than {@link 8596 * CharSequence#length() seq.length()}. 8597 * @since 1.5 8598 */ 8599 public static int codePointBefore(CharSequence seq, int index) { 8600 char c2 = seq.charAt(--index); 8601 if (isLowSurrogate(c2) && index > 0) { 8602 char c1 = seq.charAt(--index); 8603 if (isHighSurrogate(c1)) { 8604 return toCodePoint(c1, c2); 8605 } 8606 } 8607 return c2; 8608 } 8609 8610 /** 8611 * Returns the code point preceding the given index of the 8612 * {@code char} array. If the {@code char} value at 8613 * {@code (index - 1)} in the {@code char} array is in 8614 * the low-surrogate range, {@code (index - 2)} is not 8615 * negative, and the {@code char} value at {@code (index - 2)} 8616 * in the {@code char} array is in the 8617 * high-surrogate range, then the supplementary code point 8618 * corresponding to this surrogate pair is returned. Otherwise, 8619 * the {@code char} value at {@code (index - 1)} is 8620 * returned. 8621 * 8622 * @param a the {@code char} array 8623 * @param index the index following the code point that should be returned 8624 * @return the Unicode code point value before the given index. 8625 * @throws NullPointerException if {@code a} is null. 8626 * @throws IndexOutOfBoundsException if the {@code index} 8627 * argument is less than 1 or greater than the length of the 8628 * {@code char} array 8629 * @since 1.5 8630 */ 8631 public static int codePointBefore(char[] a, int index) { 8632 return codePointBeforeImpl(a, index, 0); 8633 } 8634 8635 /** 8636 * Returns the code point preceding the given index of the 8637 * {@code char} array, where only array elements with 8638 * {@code index} greater than or equal to {@code start} 8639 * can be used. If the {@code char} value at {@code (index - 1)} 8640 * in the {@code char} array is in the 8641 * low-surrogate range, {@code (index - 2)} is not less than 8642 * {@code start}, and the {@code char} value at 8643 * {@code (index - 2)} in the {@code char} array is in 8644 * the high-surrogate range, then the supplementary code point 8645 * corresponding to this surrogate pair is returned. Otherwise, 8646 * the {@code char} value at {@code (index - 1)} is 8647 * returned. 8648 * 8649 * @param a the {@code char} array 8650 * @param index the index following the code point that should be returned 8651 * @param start the index of the first array element in the 8652 * {@code char} array 8653 * @return the Unicode code point value before the given index. 8654 * @throws NullPointerException if {@code a} is null. 8655 * @throws IndexOutOfBoundsException if the {@code index} 8656 * argument is not greater than the {@code start} argument or 8657 * is greater than the length of the {@code char} array, or 8658 * if the {@code start} argument is negative or not less than 8659 * the length of the {@code char} array. 8660 * @since 1.5 8661 */ 8662 public static int codePointBefore(char[] a, int index, int start) { 8663 if (index <= start || start < 0 || start >= a.length) { 8664 throw new IndexOutOfBoundsException(); 8665 } 8666 return codePointBeforeImpl(a, index, start); 8667 } 8668 8669 // throws ArrayIndexOutOfBoundsException if index-1 out of bounds 8670 static int codePointBeforeImpl(char[] a, int index, int start) { 8671 char c2 = a[--index]; 8672 if (isLowSurrogate(c2) && index > start) { 8673 char c1 = a[--index]; 8674 if (isHighSurrogate(c1)) { 8675 return toCodePoint(c1, c2); 8676 } 8677 } 8678 return c2; 8679 } 8680 8681 /** 8682 * Returns the leading surrogate (a 8683 * <a href="http://www.unicode.org/glossary/#high_surrogate_code_unit"> 8684 * high surrogate code unit</a>) of the 8685 * <a href="http://www.unicode.org/glossary/#surrogate_pair"> 8686 * surrogate pair</a> 8687 * representing the specified supplementary character (Unicode 8688 * code point) in the UTF-16 encoding. If the specified character 8689 * is not a 8690 * <a href="Character.html#supplementary">supplementary character</a>, 8691 * an unspecified {@code char} is returned. 8692 * 8693 * <p>If 8694 * {@link #isSupplementaryCodePoint isSupplementaryCodePoint(x)} 8695 * is {@code true}, then 8696 * {@link #isHighSurrogate isHighSurrogate}{@code (highSurrogate(x))} and 8697 * {@link #toCodePoint toCodePoint}{@code (highSurrogate(x), }{@link #lowSurrogate lowSurrogate}{@code (x)) == x} 8698 * are also always {@code true}. 8699 * 8700 * @param codePoint a supplementary character (Unicode code point) 8701 * @return the leading surrogate code unit used to represent the 8702 * character in the UTF-16 encoding 8703 * @since 1.7 8704 */ 8705 public static char highSurrogate(int codePoint) { 8706 return (char) ((codePoint >>> 10) 8707 + (MIN_HIGH_SURROGATE - (MIN_SUPPLEMENTARY_CODE_POINT >>> 10))); 8708 } 8709 8710 /** 8711 * Returns the trailing surrogate (a 8712 * <a href="http://www.unicode.org/glossary/#low_surrogate_code_unit"> 8713 * low surrogate code unit</a>) of the 8714 * <a href="http://www.unicode.org/glossary/#surrogate_pair"> 8715 * surrogate pair</a> 8716 * representing the specified supplementary character (Unicode 8717 * code point) in the UTF-16 encoding. If the specified character 8718 * is not a 8719 * <a href="Character.html#supplementary">supplementary character</a>, 8720 * an unspecified {@code char} is returned. 8721 * 8722 * <p>If 8723 * {@link #isSupplementaryCodePoint isSupplementaryCodePoint(x)} 8724 * is {@code true}, then 8725 * {@link #isLowSurrogate isLowSurrogate}{@code (lowSurrogate(x))} and 8726 * {@link #toCodePoint toCodePoint}{@code (}{@link #highSurrogate highSurrogate}{@code (x), lowSurrogate(x)) == x} 8727 * are also always {@code true}. 8728 * 8729 * @param codePoint a supplementary character (Unicode code point) 8730 * @return the trailing surrogate code unit used to represent the 8731 * character in the UTF-16 encoding 8732 * @since 1.7 8733 */ 8734 public static char lowSurrogate(int codePoint) { 8735 return (char) ((codePoint & 0x3ff) + MIN_LOW_SURROGATE); 8736 } 8737 8738 /** 8739 * Converts the specified character (Unicode code point) to its 8740 * UTF-16 representation. If the specified code point is a BMP 8741 * (Basic Multilingual Plane or Plane 0) value, the same value is 8742 * stored in {@code dst[dstIndex]}, and 1 is returned. If the 8743 * specified code point is a supplementary character, its 8744 * surrogate values are stored in {@code dst[dstIndex]} 8745 * (high-surrogate) and {@code dst[dstIndex+1]} 8746 * (low-surrogate), and 2 is returned. 8747 * 8748 * @param codePoint the character (Unicode code point) to be converted. 8749 * @param dst an array of {@code char} in which the 8750 * {@code codePoint}'s UTF-16 value is stored. 8751 * @param dstIndex the start index into the {@code dst} 8752 * array where the converted value is stored. 8753 * @return 1 if the code point is a BMP code point, 2 if the 8754 * code point is a supplementary code point. 8755 * @throws IllegalArgumentException if the specified 8756 * {@code codePoint} is not a valid Unicode code point. 8757 * @throws NullPointerException if the specified {@code dst} is null. 8758 * @throws IndexOutOfBoundsException if {@code dstIndex} 8759 * is negative or not less than {@code dst.length}, or if 8760 * {@code dst} at {@code dstIndex} doesn't have enough 8761 * array element(s) to store the resulting {@code char} 8762 * value(s). (If {@code dstIndex} is equal to 8763 * {@code dst.length-1} and the specified 8764 * {@code codePoint} is a supplementary character, the 8765 * high-surrogate value is not stored in 8766 * {@code dst[dstIndex]}.) 8767 * @since 1.5 8768 */ 8769 public static int toChars(int codePoint, char[] dst, int dstIndex) { 8770 if (isBmpCodePoint(codePoint)) { 8771 dst[dstIndex] = (char) codePoint; 8772 return 1; 8773 } else if (isValidCodePoint(codePoint)) { 8774 toSurrogates(codePoint, dst, dstIndex); 8775 return 2; 8776 } else { 8777 throw new IllegalArgumentException( 8778 String.format("Not a valid Unicode code point: 0x%X", codePoint)); 8779 } 8780 } 8781 8782 /** 8783 * Converts the specified character (Unicode code point) to its 8784 * UTF-16 representation stored in a {@code char} array. If 8785 * the specified code point is a BMP (Basic Multilingual Plane or 8786 * Plane 0) value, the resulting {@code char} array has 8787 * the same value as {@code codePoint}. If the specified code 8788 * point is a supplementary code point, the resulting 8789 * {@code char} array has the corresponding surrogate pair. 8790 * 8791 * @param codePoint a Unicode code point 8792 * @return a {@code char} array having 8793 * {@code codePoint}'s UTF-16 representation. 8794 * @throws IllegalArgumentException if the specified 8795 * {@code codePoint} is not a valid Unicode code point. 8796 * @since 1.5 8797 */ 8798 public static char[] toChars(int codePoint) { 8799 if (isBmpCodePoint(codePoint)) { 8800 return new char[] { (char) codePoint }; 8801 } else if (isValidCodePoint(codePoint)) { 8802 char[] result = new char[2]; 8803 toSurrogates(codePoint, result, 0); 8804 return result; 8805 } else { 8806 throw new IllegalArgumentException( 8807 String.format("Not a valid Unicode code point: 0x%X", codePoint)); 8808 } 8809 } 8810 8811 static void toSurrogates(int codePoint, char[] dst, int index) { 8812 // We write elements "backwards" to guarantee all-or-nothing 8813 dst[index+1] = lowSurrogate(codePoint); 8814 dst[index] = highSurrogate(codePoint); 8815 } 8816 8817 /** 8818 * Returns the number of Unicode code points in the text range of 8819 * the specified char sequence. The text range begins at the 8820 * specified {@code beginIndex} and extends to the 8821 * {@code char} at index {@code endIndex - 1}. Thus the 8822 * length (in {@code char}s) of the text range is 8823 * {@code endIndex-beginIndex}. Unpaired surrogates within 8824 * the text range count as one code point each. 8825 * 8826 * @param seq the char sequence 8827 * @param beginIndex the index to the first {@code char} of 8828 * the text range. 8829 * @param endIndex the index after the last {@code char} of 8830 * the text range. 8831 * @return the number of Unicode code points in the specified text 8832 * range 8833 * @throws NullPointerException if {@code seq} is null. 8834 * @throws IndexOutOfBoundsException if the 8835 * {@code beginIndex} is negative, or {@code endIndex} 8836 * is larger than the length of the given sequence, or 8837 * {@code beginIndex} is larger than {@code endIndex}. 8838 * @since 1.5 8839 */ 8840 public static int codePointCount(CharSequence seq, int beginIndex, int endIndex) { 8841 int length = seq.length(); 8842 if (beginIndex < 0 || endIndex > length || beginIndex > endIndex) { 8843 throw new IndexOutOfBoundsException(); 8844 } 8845 int n = endIndex - beginIndex; 8846 for (int i = beginIndex; i < endIndex; ) { 8847 if (isHighSurrogate(seq.charAt(i++)) && i < endIndex && 8848 isLowSurrogate(seq.charAt(i))) { 8849 n--; 8850 i++; 8851 } 8852 } 8853 return n; 8854 } 8855 8856 /** 8857 * Returns the number of Unicode code points in a subarray of the 8858 * {@code char} array argument. The {@code offset} 8859 * argument is the index of the first {@code char} of the 8860 * subarray and the {@code count} argument specifies the 8861 * length of the subarray in {@code char}s. Unpaired 8862 * surrogates within the subarray count as one code point each. 8863 * 8864 * @param a the {@code char} array 8865 * @param offset the index of the first {@code char} in the 8866 * given {@code char} array 8867 * @param count the length of the subarray in {@code char}s 8868 * @return the number of Unicode code points in the specified subarray 8869 * @throws NullPointerException if {@code a} is null. 8870 * @throws IndexOutOfBoundsException if {@code offset} or 8871 * {@code count} is negative, or if {@code offset + 8872 * count} is larger than the length of the given array. 8873 * @since 1.5 8874 */ 8875 public static int codePointCount(char[] a, int offset, int count) { 8876 if (count > a.length - offset || offset < 0 || count < 0) { 8877 throw new IndexOutOfBoundsException(); 8878 } 8879 return codePointCountImpl(a, offset, count); 8880 } 8881 8882 static int codePointCountImpl(char[] a, int offset, int count) { 8883 int endIndex = offset + count; 8884 int n = count; 8885 for (int i = offset; i < endIndex; ) { 8886 if (isHighSurrogate(a[i++]) && i < endIndex && 8887 isLowSurrogate(a[i])) { 8888 n--; 8889 i++; 8890 } 8891 } 8892 return n; 8893 } 8894 8895 /** 8896 * Returns the index within the given char sequence that is offset 8897 * from the given {@code index} by {@code codePointOffset} 8898 * code points. Unpaired surrogates within the text range given by 8899 * {@code index} and {@code codePointOffset} count as 8900 * one code point each. 8901 * 8902 * @param seq the char sequence 8903 * @param index the index to be offset 8904 * @param codePointOffset the offset in code points 8905 * @return the index within the char sequence 8906 * @throws NullPointerException if {@code seq} is null. 8907 * @throws IndexOutOfBoundsException if {@code index} 8908 * is negative or larger then the length of the char sequence, 8909 * or if {@code codePointOffset} is positive and the 8910 * subsequence starting with {@code index} has fewer than 8911 * {@code codePointOffset} code points, or if 8912 * {@code codePointOffset} is negative and the subsequence 8913 * before {@code index} has fewer than the absolute value 8914 * of {@code codePointOffset} code points. 8915 * @since 1.5 8916 */ 8917 public static int offsetByCodePoints(CharSequence seq, int index, 8918 int codePointOffset) { 8919 int length = seq.length(); 8920 if (index < 0 || index > length) { 8921 throw new IndexOutOfBoundsException(); 8922 } 8923 8924 int x = index; 8925 if (codePointOffset >= 0) { 8926 int i; 8927 for (i = 0; x < length && i < codePointOffset; i++) { 8928 if (isHighSurrogate(seq.charAt(x++)) && x < length && 8929 isLowSurrogate(seq.charAt(x))) { 8930 x++; 8931 } 8932 } 8933 if (i < codePointOffset) { 8934 throw new IndexOutOfBoundsException(); 8935 } 8936 } else { 8937 int i; 8938 for (i = codePointOffset; x > 0 && i < 0; i++) { 8939 if (isLowSurrogate(seq.charAt(--x)) && x > 0 && 8940 isHighSurrogate(seq.charAt(x-1))) { 8941 x--; 8942 } 8943 } 8944 if (i < 0) { 8945 throw new IndexOutOfBoundsException(); 8946 } 8947 } 8948 return x; 8949 } 8950 8951 /** 8952 * Returns the index within the given {@code char} subarray 8953 * that is offset from the given {@code index} by 8954 * {@code codePointOffset} code points. The 8955 * {@code start} and {@code count} arguments specify a 8956 * subarray of the {@code char} array. Unpaired surrogates 8957 * within the text range given by {@code index} and 8958 * {@code codePointOffset} count as one code point each. 8959 * 8960 * @param a the {@code char} array 8961 * @param start the index of the first {@code char} of the 8962 * subarray 8963 * @param count the length of the subarray in {@code char}s 8964 * @param index the index to be offset 8965 * @param codePointOffset the offset in code points 8966 * @return the index within the subarray 8967 * @throws NullPointerException if {@code a} is null. 8968 * @throws IndexOutOfBoundsException 8969 * if {@code start} or {@code count} is negative, 8970 * or if {@code start + count} is larger than the length of 8971 * the given array, 8972 * or if {@code index} is less than {@code start} or 8973 * larger then {@code start + count}, 8974 * or if {@code codePointOffset} is positive and the text range 8975 * starting with {@code index} and ending with {@code start + count - 1} 8976 * has fewer than {@code codePointOffset} code 8977 * points, 8978 * or if {@code codePointOffset} is negative and the text range 8979 * starting with {@code start} and ending with {@code index - 1} 8980 * has fewer than the absolute value of 8981 * {@code codePointOffset} code points. 8982 * @since 1.5 8983 */ 8984 public static int offsetByCodePoints(char[] a, int start, int count, 8985 int index, int codePointOffset) { 8986 if (count > a.length-start || start < 0 || count < 0 8987 || index < start || index > start+count) { 8988 throw new IndexOutOfBoundsException(); 8989 } 8990 return offsetByCodePointsImpl(a, start, count, index, codePointOffset); 8991 } 8992 8993 static int offsetByCodePointsImpl(char[]a, int start, int count, 8994 int index, int codePointOffset) { 8995 int x = index; 8996 if (codePointOffset >= 0) { 8997 int limit = start + count; 8998 int i; 8999 for (i = 0; x < limit && i < codePointOffset; i++) { 9000 if (isHighSurrogate(a[x++]) && x < limit && 9001 isLowSurrogate(a[x])) { 9002 x++; 9003 } 9004 } 9005 if (i < codePointOffset) { 9006 throw new IndexOutOfBoundsException(); 9007 } 9008 } else { 9009 int i; 9010 for (i = codePointOffset; x > start && i < 0; i++) { 9011 if (isLowSurrogate(a[--x]) && x > start && 9012 isHighSurrogate(a[x-1])) { 9013 x--; 9014 } 9015 } 9016 if (i < 0) { 9017 throw new IndexOutOfBoundsException(); 9018 } 9019 } 9020 return x; 9021 } 9022 9023 /** 9024 * Determines if the specified character is a lowercase character. 9025 * <p> 9026 * A character is lowercase if its general category type, provided 9027 * by {@code Character.getType(ch)}, is 9028 * {@code LOWERCASE_LETTER}, or it has contributory property 9029 * Other_Lowercase as defined by the Unicode Standard. 9030 * <p> 9031 * The following are examples of lowercase characters: 9032 * <blockquote><pre> 9033 * 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 9034 * '\u00DF' '\u00E0' '\u00E1' '\u00E2' '\u00E3' '\u00E4' '\u00E5' '\u00E6' 9035 * '\u00E7' '\u00E8' '\u00E9' '\u00EA' '\u00EB' '\u00EC' '\u00ED' '\u00EE' 9036 * '\u00EF' '\u00F0' '\u00F1' '\u00F2' '\u00F3' '\u00F4' '\u00F5' '\u00F6' 9037 * '\u00F8' '\u00F9' '\u00FA' '\u00FB' '\u00FC' '\u00FD' '\u00FE' '\u00FF' 9038 * </pre></blockquote> 9039 * <p> Many other Unicode characters are lowercase too. 9040 * 9041 * <p><b>Note:</b> This method cannot handle <a 9042 * href="#supplementary"> supplementary characters</a>. To support 9043 * all Unicode characters, including supplementary characters, use 9044 * the {@link #isLowerCase(int)} method. 9045 * 9046 * @param ch the character to be tested. 9047 * @return {@code true} if the character is lowercase; 9048 * {@code false} otherwise. 9049 * @see Character#isLowerCase(char) 9050 * @see Character#isTitleCase(char) 9051 * @see Character#toLowerCase(char) 9052 * @see Character#getType(char) 9053 */ 9054 public static boolean isLowerCase(char ch) { 9055 return isLowerCase((int)ch); 9056 } 9057 9058 /** 9059 * Determines if the specified character (Unicode code point) is a 9060 * lowercase character. 9061 * <p> 9062 * A character is lowercase if its general category type, provided 9063 * by {@link Character#getType getType(codePoint)}, is 9064 * {@code LOWERCASE_LETTER}, or it has contributory property 9065 * Other_Lowercase as defined by the Unicode Standard. 9066 * <p> 9067 * The following are examples of lowercase characters: 9068 * <blockquote><pre> 9069 * 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 9070 * '\u00DF' '\u00E0' '\u00E1' '\u00E2' '\u00E3' '\u00E4' '\u00E5' '\u00E6' 9071 * '\u00E7' '\u00E8' '\u00E9' '\u00EA' '\u00EB' '\u00EC' '\u00ED' '\u00EE' 9072 * '\u00EF' '\u00F0' '\u00F1' '\u00F2' '\u00F3' '\u00F4' '\u00F5' '\u00F6' 9073 * '\u00F8' '\u00F9' '\u00FA' '\u00FB' '\u00FC' '\u00FD' '\u00FE' '\u00FF' 9074 * </pre></blockquote> 9075 * <p> Many other Unicode characters are lowercase too. 9076 * 9077 * @param codePoint the character (Unicode code point) to be tested. 9078 * @return {@code true} if the character is lowercase; 9079 * {@code false} otherwise. 9080 * @see Character#isLowerCase(int) 9081 * @see Character#isTitleCase(int) 9082 * @see Character#toLowerCase(int) 9083 * @see Character#getType(int) 9084 * @since 1.5 9085 */ 9086 public static boolean isLowerCase(int codePoint) { 9087 return getType(codePoint) == Character.LOWERCASE_LETTER || 9088 CharacterData.of(codePoint).isOtherLowercase(codePoint); 9089 } 9090 9091 /** 9092 * Determines if the specified character is an uppercase character. 9093 * <p> 9094 * A character is uppercase if its general category type, provided by 9095 * {@code Character.getType(ch)}, is {@code UPPERCASE_LETTER}. 9096 * or it has contributory property Other_Uppercase as defined by the Unicode Standard. 9097 * <p> 9098 * The following are examples of uppercase characters: 9099 * <blockquote><pre> 9100 * 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 9101 * '\u00C0' '\u00C1' '\u00C2' '\u00C3' '\u00C4' '\u00C5' '\u00C6' '\u00C7' 9102 * '\u00C8' '\u00C9' '\u00CA' '\u00CB' '\u00CC' '\u00CD' '\u00CE' '\u00CF' 9103 * '\u00D0' '\u00D1' '\u00D2' '\u00D3' '\u00D4' '\u00D5' '\u00D6' '\u00D8' 9104 * '\u00D9' '\u00DA' '\u00DB' '\u00DC' '\u00DD' '\u00DE' 9105 * </pre></blockquote> 9106 * <p> Many other Unicode characters are uppercase too. 9107 * 9108 * <p><b>Note:</b> This method cannot handle <a 9109 * href="#supplementary"> supplementary characters</a>. To support 9110 * all Unicode characters, including supplementary characters, use 9111 * the {@link #isUpperCase(int)} method. 9112 * 9113 * @param ch the character to be tested. 9114 * @return {@code true} if the character is uppercase; 9115 * {@code false} otherwise. 9116 * @see Character#isLowerCase(char) 9117 * @see Character#isTitleCase(char) 9118 * @see Character#toUpperCase(char) 9119 * @see Character#getType(char) 9120 * @since 1.0 9121 */ 9122 public static boolean isUpperCase(char ch) { 9123 return isUpperCase((int)ch); 9124 } 9125 9126 /** 9127 * Determines if the specified character (Unicode code point) is an uppercase character. 9128 * <p> 9129 * A character is uppercase if its general category type, provided by 9130 * {@link Character#getType(int) getType(codePoint)}, is {@code UPPERCASE_LETTER}, 9131 * or it has contributory property Other_Uppercase as defined by the Unicode Standard. 9132 * <p> 9133 * The following are examples of uppercase characters: 9134 * <blockquote><pre> 9135 * 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 9136 * '\u00C0' '\u00C1' '\u00C2' '\u00C3' '\u00C4' '\u00C5' '\u00C6' '\u00C7' 9137 * '\u00C8' '\u00C9' '\u00CA' '\u00CB' '\u00CC' '\u00CD' '\u00CE' '\u00CF' 9138 * '\u00D0' '\u00D1' '\u00D2' '\u00D3' '\u00D4' '\u00D5' '\u00D6' '\u00D8' 9139 * '\u00D9' '\u00DA' '\u00DB' '\u00DC' '\u00DD' '\u00DE' 9140 * </pre></blockquote> 9141 * <p> Many other Unicode characters are uppercase too. 9142 * 9143 * @param codePoint the character (Unicode code point) to be tested. 9144 * @return {@code true} if the character is uppercase; 9145 * {@code false} otherwise. 9146 * @see Character#isLowerCase(int) 9147 * @see Character#isTitleCase(int) 9148 * @see Character#toUpperCase(int) 9149 * @see Character#getType(int) 9150 * @since 1.5 9151 */ 9152 public static boolean isUpperCase(int codePoint) { 9153 return getType(codePoint) == Character.UPPERCASE_LETTER || 9154 CharacterData.of(codePoint).isOtherUppercase(codePoint); 9155 } 9156 9157 /** 9158 * Determines if the specified character is a titlecase character. 9159 * <p> 9160 * A character is a titlecase character if its general 9161 * category type, provided by {@code Character.getType(ch)}, 9162 * is {@code TITLECASE_LETTER}. 9163 * <p> 9164 * Some characters look like pairs of Latin letters. For example, there 9165 * is an uppercase letter that looks like "LJ" and has a corresponding 9166 * lowercase letter that looks like "lj". A third form, which looks like "Lj", 9167 * is the appropriate form to use when rendering a word in lowercase 9168 * with initial capitals, as for a book title. 9169 * <p> 9170 * These are some of the Unicode characters for which this method returns 9171 * {@code true}: 9172 * <ul> 9173 * <li>{@code LATIN CAPITAL LETTER D WITH SMALL LETTER Z WITH CARON} 9174 * <li>{@code LATIN CAPITAL LETTER L WITH SMALL LETTER J} 9175 * <li>{@code LATIN CAPITAL LETTER N WITH SMALL LETTER J} 9176 * <li>{@code LATIN CAPITAL LETTER D WITH SMALL LETTER Z} 9177 * </ul> 9178 * <p> Many other Unicode characters are titlecase too. 9179 * 9180 * <p><b>Note:</b> This method cannot handle <a 9181 * href="#supplementary"> supplementary characters</a>. To support 9182 * all Unicode characters, including supplementary characters, use 9183 * the {@link #isTitleCase(int)} method. 9184 * 9185 * @param ch the character to be tested. 9186 * @return {@code true} if the character is titlecase; 9187 * {@code false} otherwise. 9188 * @see Character#isLowerCase(char) 9189 * @see Character#isUpperCase(char) 9190 * @see Character#toTitleCase(char) 9191 * @see Character#getType(char) 9192 * @since 1.0.2 9193 */ 9194 public static boolean isTitleCase(char ch) { 9195 return isTitleCase((int)ch); 9196 } 9197 9198 /** 9199 * Determines if the specified character (Unicode code point) is a titlecase character. 9200 * <p> 9201 * A character is a titlecase character if its general 9202 * category type, provided by {@link Character#getType(int) getType(codePoint)}, 9203 * is {@code TITLECASE_LETTER}. 9204 * <p> 9205 * Some characters look like pairs of Latin letters. For example, there 9206 * is an uppercase letter that looks like "LJ" and has a corresponding 9207 * lowercase letter that looks like "lj". A third form, which looks like "Lj", 9208 * is the appropriate form to use when rendering a word in lowercase 9209 * with initial capitals, as for a book title. 9210 * <p> 9211 * These are some of the Unicode characters for which this method returns 9212 * {@code true}: 9213 * <ul> 9214 * <li>{@code LATIN CAPITAL LETTER D WITH SMALL LETTER Z WITH CARON} 9215 * <li>{@code LATIN CAPITAL LETTER L WITH SMALL LETTER J} 9216 * <li>{@code LATIN CAPITAL LETTER N WITH SMALL LETTER J} 9217 * <li>{@code LATIN CAPITAL LETTER D WITH SMALL LETTER Z} 9218 * </ul> 9219 * <p> Many other Unicode characters are titlecase too. 9220 * 9221 * @param codePoint the character (Unicode code point) to be tested. 9222 * @return {@code true} if the character is titlecase; 9223 * {@code false} otherwise. 9224 * @see Character#isLowerCase(int) 9225 * @see Character#isUpperCase(int) 9226 * @see Character#toTitleCase(int) 9227 * @see Character#getType(int) 9228 * @since 1.5 9229 */ 9230 public static boolean isTitleCase(int codePoint) { 9231 return getType(codePoint) == Character.TITLECASE_LETTER; 9232 } 9233 9234 /** 9235 * Determines if the specified character is a digit. 9236 * <p> 9237 * A character is a digit if its general category type, provided 9238 * by {@code Character.getType(ch)}, is 9239 * {@code DECIMAL_DIGIT_NUMBER}. 9240 * <p> 9241 * Some Unicode character ranges that contain digits: 9242 * <ul> 9243 * <li>{@code '\u005Cu0030'} through {@code '\u005Cu0039'}, 9244 * ISO-LATIN-1 digits ({@code '0'} through {@code '9'}) 9245 * <li>{@code '\u005Cu0660'} through {@code '\u005Cu0669'}, 9246 * Arabic-Indic digits 9247 * <li>{@code '\u005Cu06F0'} through {@code '\u005Cu06F9'}, 9248 * Extended Arabic-Indic digits 9249 * <li>{@code '\u005Cu0966'} through {@code '\u005Cu096F'}, 9250 * Devanagari digits 9251 * <li>{@code '\u005CuFF10'} through {@code '\u005CuFF19'}, 9252 * Fullwidth digits 9253 * </ul> 9254 * 9255 * Many other character ranges contain digits as well. 9256 * 9257 * <p><b>Note:</b> This method cannot handle <a 9258 * href="#supplementary"> supplementary characters</a>. To support 9259 * all Unicode characters, including supplementary characters, use 9260 * the {@link #isDigit(int)} method. 9261 * 9262 * @param ch the character to be tested. 9263 * @return {@code true} if the character is a digit; 9264 * {@code false} otherwise. 9265 * @see Character#digit(char, int) 9266 * @see Character#forDigit(int, int) 9267 * @see Character#getType(char) 9268 */ 9269 public static boolean isDigit(char ch) { 9270 return isDigit((int)ch); 9271 } 9272 9273 /** 9274 * Determines if the specified character (Unicode code point) is a digit. 9275 * <p> 9276 * A character is a digit if its general category type, provided 9277 * by {@link Character#getType(int) getType(codePoint)}, is 9278 * {@code DECIMAL_DIGIT_NUMBER}. 9279 * <p> 9280 * Some Unicode character ranges that contain digits: 9281 * <ul> 9282 * <li>{@code '\u005Cu0030'} through {@code '\u005Cu0039'}, 9283 * ISO-LATIN-1 digits ({@code '0'} through {@code '9'}) 9284 * <li>{@code '\u005Cu0660'} through {@code '\u005Cu0669'}, 9285 * Arabic-Indic digits 9286 * <li>{@code '\u005Cu06F0'} through {@code '\u005Cu06F9'}, 9287 * Extended Arabic-Indic digits 9288 * <li>{@code '\u005Cu0966'} through {@code '\u005Cu096F'}, 9289 * Devanagari digits 9290 * <li>{@code '\u005CuFF10'} through {@code '\u005CuFF19'}, 9291 * Fullwidth digits 9292 * </ul> 9293 * 9294 * Many other character ranges contain digits as well. 9295 * 9296 * @param codePoint the character (Unicode code point) to be tested. 9297 * @return {@code true} if the character is a digit; 9298 * {@code false} otherwise. 9299 * @see Character#forDigit(int, int) 9300 * @see Character#getType(int) 9301 * @since 1.5 9302 */ 9303 public static boolean isDigit(int codePoint) { 9304 return getType(codePoint) == Character.DECIMAL_DIGIT_NUMBER; 9305 } 9306 9307 /** 9308 * Determines if a character is defined in Unicode. 9309 * <p> 9310 * A character is defined if at least one of the following is true: 9311 * <ul> 9312 * <li>It has an entry in the UnicodeData file. 9313 * <li>It has a value in a range defined by the UnicodeData file. 9314 * </ul> 9315 * 9316 * <p><b>Note:</b> This method cannot handle <a 9317 * href="#supplementary"> supplementary characters</a>. To support 9318 * all Unicode characters, including supplementary characters, use 9319 * the {@link #isDefined(int)} method. 9320 * 9321 * @param ch the character to be tested 9322 * @return {@code true} if the character has a defined meaning 9323 * in Unicode; {@code false} otherwise. 9324 * @see Character#isDigit(char) 9325 * @see Character#isLetter(char) 9326 * @see Character#isLetterOrDigit(char) 9327 * @see Character#isLowerCase(char) 9328 * @see Character#isTitleCase(char) 9329 * @see Character#isUpperCase(char) 9330 * @since 1.0.2 9331 */ 9332 public static boolean isDefined(char ch) { 9333 return isDefined((int)ch); 9334 } 9335 9336 /** 9337 * Determines if a character (Unicode code point) is defined in Unicode. 9338 * <p> 9339 * A character is defined if at least one of the following is true: 9340 * <ul> 9341 * <li>It has an entry in the UnicodeData file. 9342 * <li>It has a value in a range defined by the UnicodeData file. 9343 * </ul> 9344 * 9345 * @param codePoint the character (Unicode code point) to be tested. 9346 * @return {@code true} if the character has a defined meaning 9347 * in Unicode; {@code false} otherwise. 9348 * @see Character#isDigit(int) 9349 * @see Character#isLetter(int) 9350 * @see Character#isLetterOrDigit(int) 9351 * @see Character#isLowerCase(int) 9352 * @see Character#isTitleCase(int) 9353 * @see Character#isUpperCase(int) 9354 * @since 1.5 9355 */ 9356 public static boolean isDefined(int codePoint) { 9357 return getType(codePoint) != Character.UNASSIGNED; 9358 } 9359 9360 /** 9361 * Determines if the specified character is a letter. 9362 * <p> 9363 * A character is considered to be a letter if its general 9364 * category type, provided by {@code Character.getType(ch)}, 9365 * is any of the following: 9366 * <ul> 9367 * <li> {@code UPPERCASE_LETTER} 9368 * <li> {@code LOWERCASE_LETTER} 9369 * <li> {@code TITLECASE_LETTER} 9370 * <li> {@code MODIFIER_LETTER} 9371 * <li> {@code OTHER_LETTER} 9372 * </ul> 9373 * 9374 * Not all letters have case. Many characters are 9375 * letters but are neither uppercase nor lowercase nor titlecase. 9376 * 9377 * <p><b>Note:</b> This method cannot handle <a 9378 * href="#supplementary"> supplementary characters</a>. To support 9379 * all Unicode characters, including supplementary characters, use 9380 * the {@link #isLetter(int)} method. 9381 * 9382 * @param ch the character to be tested. 9383 * @return {@code true} if the character is a letter; 9384 * {@code false} otherwise. 9385 * @see Character#isDigit(char) 9386 * @see Character#isJavaIdentifierStart(char) 9387 * @see Character#isJavaLetter(char) 9388 * @see Character#isJavaLetterOrDigit(char) 9389 * @see Character#isLetterOrDigit(char) 9390 * @see Character#isLowerCase(char) 9391 * @see Character#isTitleCase(char) 9392 * @see Character#isUnicodeIdentifierStart(char) 9393 * @see Character#isUpperCase(char) 9394 */ 9395 public static boolean isLetter(char ch) { 9396 return isLetter((int)ch); 9397 } 9398 9399 /** 9400 * Determines if the specified character (Unicode code point) is a letter. 9401 * <p> 9402 * A character is considered to be a letter if its general 9403 * category type, provided by {@link Character#getType(int) getType(codePoint)}, 9404 * is any of the following: 9405 * <ul> 9406 * <li> {@code UPPERCASE_LETTER} 9407 * <li> {@code LOWERCASE_LETTER} 9408 * <li> {@code TITLECASE_LETTER} 9409 * <li> {@code MODIFIER_LETTER} 9410 * <li> {@code OTHER_LETTER} 9411 * </ul> 9412 * 9413 * Not all letters have case. Many characters are 9414 * letters but are neither uppercase nor lowercase nor titlecase. 9415 * 9416 * @param codePoint the character (Unicode code point) to be tested. 9417 * @return {@code true} if the character is a letter; 9418 * {@code false} otherwise. 9419 * @see Character#isDigit(int) 9420 * @see Character#isJavaIdentifierStart(int) 9421 * @see Character#isLetterOrDigit(int) 9422 * @see Character#isLowerCase(int) 9423 * @see Character#isTitleCase(int) 9424 * @see Character#isUnicodeIdentifierStart(int) 9425 * @see Character#isUpperCase(int) 9426 * @since 1.5 9427 */ 9428 public static boolean isLetter(int codePoint) { 9429 return ((((1 << Character.UPPERCASE_LETTER) | 9430 (1 << Character.LOWERCASE_LETTER) | 9431 (1 << Character.TITLECASE_LETTER) | 9432 (1 << Character.MODIFIER_LETTER) | 9433 (1 << Character.OTHER_LETTER)) >> getType(codePoint)) & 1) 9434 != 0; 9435 } 9436 9437 /** 9438 * Determines if the specified character is a letter or digit. 9439 * <p> 9440 * A character is considered to be a letter or digit if either 9441 * {@code Character.isLetter(char ch)} or 9442 * {@code Character.isDigit(char ch)} returns 9443 * {@code true} for the character. 9444 * 9445 * <p><b>Note:</b> This method cannot handle <a 9446 * href="#supplementary"> supplementary characters</a>. To support 9447 * all Unicode characters, including supplementary characters, use 9448 * the {@link #isLetterOrDigit(int)} method. 9449 * 9450 * @param ch the character to be tested. 9451 * @return {@code true} if the character is a letter or digit; 9452 * {@code false} otherwise. 9453 * @see Character#isDigit(char) 9454 * @see Character#isJavaIdentifierPart(char) 9455 * @see Character#isJavaLetter(char) 9456 * @see Character#isJavaLetterOrDigit(char) 9457 * @see Character#isLetter(char) 9458 * @see Character#isUnicodeIdentifierPart(char) 9459 * @since 1.0.2 9460 */ 9461 public static boolean isLetterOrDigit(char ch) { 9462 return isLetterOrDigit((int)ch); 9463 } 9464 9465 /** 9466 * Determines if the specified character (Unicode code point) is a letter or digit. 9467 * <p> 9468 * A character is considered to be a letter or digit if either 9469 * {@link #isLetter(int) isLetter(codePoint)} or 9470 * {@link #isDigit(int) isDigit(codePoint)} returns 9471 * {@code true} for the character. 9472 * 9473 * @param codePoint the character (Unicode code point) to be tested. 9474 * @return {@code true} if the character is a letter or digit; 9475 * {@code false} otherwise. 9476 * @see Character#isDigit(int) 9477 * @see Character#isJavaIdentifierPart(int) 9478 * @see Character#isLetter(int) 9479 * @see Character#isUnicodeIdentifierPart(int) 9480 * @since 1.5 9481 */ 9482 public static boolean isLetterOrDigit(int codePoint) { 9483 return ((((1 << Character.UPPERCASE_LETTER) | 9484 (1 << Character.LOWERCASE_LETTER) | 9485 (1 << Character.TITLECASE_LETTER) | 9486 (1 << Character.MODIFIER_LETTER) | 9487 (1 << Character.OTHER_LETTER) | 9488 (1 << Character.DECIMAL_DIGIT_NUMBER)) >> getType(codePoint)) & 1) 9489 != 0; 9490 } 9491 9492 /** 9493 * Determines if the specified character is permissible as the first 9494 * character in a Java identifier. 9495 * <p> 9496 * A character may start a Java identifier if and only if 9497 * one of the following is true: 9498 * <ul> 9499 * <li> {@link #isLetter(char) isLetter(ch)} returns {@code true} 9500 * <li> {@link #getType(char) getType(ch)} returns {@code LETTER_NUMBER} 9501 * <li> {@code ch} is a currency symbol (such as {@code '$'}) 9502 * <li> {@code ch} is a connecting punctuation character (such as {@code '_'}). 9503 * </ul> 9504 * 9505 * @param ch the character to be tested. 9506 * @return {@code true} if the character may start a Java 9507 * identifier; {@code false} otherwise. 9508 * @see Character#isJavaLetterOrDigit(char) 9509 * @see Character#isJavaIdentifierStart(char) 9510 * @see Character#isJavaIdentifierPart(char) 9511 * @see Character#isLetter(char) 9512 * @see Character#isLetterOrDigit(char) 9513 * @see Character#isUnicodeIdentifierStart(char) 9514 * @since 1.0.2 9515 * @deprecated Replaced by isJavaIdentifierStart(char). 9516 */ 9517 @Deprecated(since="1.1") 9518 public static boolean isJavaLetter(char ch) { 9519 return isJavaIdentifierStart(ch); 9520 } 9521 9522 /** 9523 * Determines if the specified character may be part of a Java 9524 * identifier as other than the first character. 9525 * <p> 9526 * A character may be part of a Java identifier if and only if any 9527 * of the following are true: 9528 * <ul> 9529 * <li> it is a letter 9530 * <li> it is a currency symbol (such as {@code '$'}) 9531 * <li> it is a connecting punctuation character (such as {@code '_'}) 9532 * <li> it is a digit 9533 * <li> it is a numeric letter (such as a Roman numeral character) 9534 * <li> it is a combining mark 9535 * <li> it is a non-spacing mark 9536 * <li> {@code isIdentifierIgnorable} returns 9537 * {@code true} for the character. 9538 * </ul> 9539 * 9540 * @param ch the character to be tested. 9541 * @return {@code true} if the character may be part of a 9542 * Java identifier; {@code false} otherwise. 9543 * @see Character#isJavaLetter(char) 9544 * @see Character#isJavaIdentifierStart(char) 9545 * @see Character#isJavaIdentifierPart(char) 9546 * @see Character#isLetter(char) 9547 * @see Character#isLetterOrDigit(char) 9548 * @see Character#isUnicodeIdentifierPart(char) 9549 * @see Character#isIdentifierIgnorable(char) 9550 * @since 1.0.2 9551 * @deprecated Replaced by isJavaIdentifierPart(char). 9552 */ 9553 @Deprecated(since="1.1") 9554 public static boolean isJavaLetterOrDigit(char ch) { 9555 return isJavaIdentifierPart(ch); 9556 } 9557 9558 /** 9559 * Determines if the specified character (Unicode code point) is an alphabet. 9560 * <p> 9561 * A character is considered to be alphabetic if its general category type, 9562 * provided by {@link Character#getType(int) getType(codePoint)}, is any of 9563 * the following: 9564 * <ul> 9565 * <li> {@code UPPERCASE_LETTER} 9566 * <li> {@code LOWERCASE_LETTER} 9567 * <li> {@code TITLECASE_LETTER} 9568 * <li> {@code MODIFIER_LETTER} 9569 * <li> {@code OTHER_LETTER} 9570 * <li> {@code LETTER_NUMBER} 9571 * </ul> 9572 * or it has contributory property Other_Alphabetic as defined by the 9573 * Unicode Standard. 9574 * 9575 * @param codePoint the character (Unicode code point) to be tested. 9576 * @return {@code true} if the character is a Unicode alphabet 9577 * character, {@code false} otherwise. 9578 * @since 1.7 9579 */ 9580 public static boolean isAlphabetic(int codePoint) { 9581 return (((((1 << Character.UPPERCASE_LETTER) | 9582 (1 << Character.LOWERCASE_LETTER) | 9583 (1 << Character.TITLECASE_LETTER) | 9584 (1 << Character.MODIFIER_LETTER) | 9585 (1 << Character.OTHER_LETTER) | 9586 (1 << Character.LETTER_NUMBER)) >> getType(codePoint)) & 1) != 0) || 9587 CharacterData.of(codePoint).isOtherAlphabetic(codePoint); 9588 } 9589 9590 /** 9591 * Determines if the specified character (Unicode code point) is a CJKV 9592 * (Chinese, Japanese, Korean and Vietnamese) ideograph, as defined by 9593 * the Unicode Standard. 9594 * 9595 * @param codePoint the character (Unicode code point) to be tested. 9596 * @return {@code true} if the character is a Unicode ideograph 9597 * character, {@code false} otherwise. 9598 * @since 1.7 9599 */ 9600 public static boolean isIdeographic(int codePoint) { 9601 return CharacterData.of(codePoint).isIdeographic(codePoint); 9602 } 9603 9604 /** 9605 * Determines if the specified character is 9606 * permissible as the first character in a Java identifier. 9607 * <p> 9608 * A character may start a Java identifier if and only if 9609 * one of the following conditions is true: 9610 * <ul> 9611 * <li> {@link #isLetter(char) isLetter(ch)} returns {@code true} 9612 * <li> {@link #getType(char) getType(ch)} returns {@code LETTER_NUMBER} 9613 * <li> {@code ch} is a currency symbol (such as {@code '$'}) 9614 * <li> {@code ch} is a connecting punctuation character (such as {@code '_'}). 9615 * </ul> 9616 * 9617 * <p><b>Note:</b> This method cannot handle <a 9618 * href="#supplementary"> supplementary characters</a>. To support 9619 * all Unicode characters, including supplementary characters, use 9620 * the {@link #isJavaIdentifierStart(int)} method. 9621 * 9622 * @param ch the character to be tested. 9623 * @return {@code true} if the character may start a Java identifier; 9624 * {@code false} otherwise. 9625 * @see Character#isJavaIdentifierPart(char) 9626 * @see Character#isLetter(char) 9627 * @see Character#isUnicodeIdentifierStart(char) 9628 * @see javax.lang.model.SourceVersion#isIdentifier(CharSequence) 9629 * @since 1.1 9630 */ 9631 public static boolean isJavaIdentifierStart(char ch) { 9632 return isJavaIdentifierStart((int)ch); 9633 } 9634 9635 /** 9636 * Determines if the character (Unicode code point) is 9637 * permissible as the first character in a Java identifier. 9638 * <p> 9639 * A character may start a Java identifier if and only if 9640 * one of the following conditions is true: 9641 * <ul> 9642 * <li> {@link #isLetter(int) isLetter(codePoint)} 9643 * returns {@code true} 9644 * <li> {@link #getType(int) getType(codePoint)} 9645 * returns {@code LETTER_NUMBER} 9646 * <li> the referenced character is a currency symbol (such as {@code '$'}) 9647 * <li> the referenced character is a connecting punctuation character 9648 * (such as {@code '_'}). 9649 * </ul> 9650 * 9651 * @param codePoint the character (Unicode code point) to be tested. 9652 * @return {@code true} if the character may start a Java identifier; 9653 * {@code false} otherwise. 9654 * @see Character#isJavaIdentifierPart(int) 9655 * @see Character#isLetter(int) 9656 * @see Character#isUnicodeIdentifierStart(int) 9657 * @see javax.lang.model.SourceVersion#isIdentifier(CharSequence) 9658 * @since 1.5 9659 */ 9660 public static boolean isJavaIdentifierStart(int codePoint) { 9661 return CharacterData.of(codePoint).isJavaIdentifierStart(codePoint); 9662 } 9663 9664 /** 9665 * Determines if the specified character may be part of a Java 9666 * identifier as other than the first character. 9667 * <p> 9668 * A character may be part of a Java identifier if any of the following 9669 * are true: 9670 * <ul> 9671 * <li> it is a letter 9672 * <li> it is a currency symbol (such as {@code '$'}) 9673 * <li> it is a connecting punctuation character (such as {@code '_'}) 9674 * <li> it is a digit 9675 * <li> it is a numeric letter (such as a Roman numeral character) 9676 * <li> it is a combining mark 9677 * <li> it is a non-spacing mark 9678 * <li> {@code isIdentifierIgnorable} returns 9679 * {@code true} for the character 9680 * </ul> 9681 * 9682 * <p><b>Note:</b> This method cannot handle <a 9683 * href="#supplementary"> supplementary characters</a>. To support 9684 * all Unicode characters, including supplementary characters, use 9685 * the {@link #isJavaIdentifierPart(int)} method. 9686 * 9687 * @param ch the character to be tested. 9688 * @return {@code true} if the character may be part of a 9689 * Java identifier; {@code false} otherwise. 9690 * @see Character#isIdentifierIgnorable(char) 9691 * @see Character#isJavaIdentifierStart(char) 9692 * @see Character#isLetterOrDigit(char) 9693 * @see Character#isUnicodeIdentifierPart(char) 9694 * @see javax.lang.model.SourceVersion#isIdentifier(CharSequence) 9695 * @since 1.1 9696 */ 9697 public static boolean isJavaIdentifierPart(char ch) { 9698 return isJavaIdentifierPart((int)ch); 9699 } 9700 9701 /** 9702 * Determines if the character (Unicode code point) may be part of a Java 9703 * identifier as other than the first character. 9704 * <p> 9705 * A character may be part of a Java identifier if any of the following 9706 * are true: 9707 * <ul> 9708 * <li> it is a letter 9709 * <li> it is a currency symbol (such as {@code '$'}) 9710 * <li> it is a connecting punctuation character (such as {@code '_'}) 9711 * <li> it is a digit 9712 * <li> it is a numeric letter (such as a Roman numeral character) 9713 * <li> it is a combining mark 9714 * <li> it is a non-spacing mark 9715 * <li> {@link #isIdentifierIgnorable(int) 9716 * isIdentifierIgnorable(codePoint)} returns {@code true} for 9717 * the character 9718 * </ul> 9719 * 9720 * @param codePoint the character (Unicode code point) to be tested. 9721 * @return {@code true} if the character may be part of a 9722 * Java identifier; {@code false} otherwise. 9723 * @see Character#isIdentifierIgnorable(int) 9724 * @see Character#isJavaIdentifierStart(int) 9725 * @see Character#isLetterOrDigit(int) 9726 * @see Character#isUnicodeIdentifierPart(int) 9727 * @see javax.lang.model.SourceVersion#isIdentifier(CharSequence) 9728 * @since 1.5 9729 */ 9730 public static boolean isJavaIdentifierPart(int codePoint) { 9731 return CharacterData.of(codePoint).isJavaIdentifierPart(codePoint); 9732 } 9733 9734 /** 9735 * Determines if the specified character is permissible as the 9736 * first character in a Unicode identifier. 9737 * <p> 9738 * A character may start a Unicode identifier if and only if 9739 * one of the following conditions is true: 9740 * <ul> 9741 * <li> {@link #isLetter(char) isLetter(ch)} returns {@code true} 9742 * <li> {@link #getType(char) getType(ch)} returns 9743 * {@code LETTER_NUMBER}. 9744 * </ul> 9745 * 9746 * <p><b>Note:</b> This method cannot handle <a 9747 * href="#supplementary"> supplementary characters</a>. To support 9748 * all Unicode characters, including supplementary characters, use 9749 * the {@link #isUnicodeIdentifierStart(int)} method. 9750 * 9751 * @param ch the character to be tested. 9752 * @return {@code true} if the character may start a Unicode 9753 * identifier; {@code false} otherwise. 9754 * @see Character#isJavaIdentifierStart(char) 9755 * @see Character#isLetter(char) 9756 * @see Character#isUnicodeIdentifierPart(char) 9757 * @since 1.1 9758 */ 9759 public static boolean isUnicodeIdentifierStart(char ch) { 9760 return isUnicodeIdentifierStart((int)ch); 9761 } 9762 9763 /** 9764 * Determines if the specified character (Unicode code point) is permissible as the 9765 * first character in a Unicode identifier. 9766 * <p> 9767 * A character may start a Unicode identifier if and only if 9768 * one of the following conditions is true: 9769 * <ul> 9770 * <li> {@link #isLetter(int) isLetter(codePoint)} 9771 * returns {@code true} 9772 * <li> {@link #getType(int) getType(codePoint)} 9773 * returns {@code LETTER_NUMBER}. 9774 * </ul> 9775 * @param codePoint the character (Unicode code point) to be tested. 9776 * @return {@code true} if the character may start a Unicode 9777 * identifier; {@code false} otherwise. 9778 * @see Character#isJavaIdentifierStart(int) 9779 * @see Character#isLetter(int) 9780 * @see Character#isUnicodeIdentifierPart(int) 9781 * @since 1.5 9782 */ 9783 public static boolean isUnicodeIdentifierStart(int codePoint) { 9784 return CharacterData.of(codePoint).isUnicodeIdentifierStart(codePoint); 9785 } 9786 9787 /** 9788 * Determines if the specified character may be part of a Unicode 9789 * identifier as other than the first character. 9790 * <p> 9791 * A character may be part of a Unicode identifier if and only if 9792 * one of the following statements is true: 9793 * <ul> 9794 * <li> it is a letter 9795 * <li> it is a connecting punctuation character (such as {@code '_'}) 9796 * <li> it is a digit 9797 * <li> it is a numeric letter (such as a Roman numeral character) 9798 * <li> it is a combining mark 9799 * <li> it is a non-spacing mark 9800 * <li> {@code isIdentifierIgnorable} returns 9801 * {@code true} for this character. 9802 * </ul> 9803 * 9804 * <p><b>Note:</b> This method cannot handle <a 9805 * href="#supplementary"> supplementary characters</a>. To support 9806 * all Unicode characters, including supplementary characters, use 9807 * the {@link #isUnicodeIdentifierPart(int)} method. 9808 * 9809 * @param ch the character to be tested. 9810 * @return {@code true} if the character may be part of a 9811 * Unicode identifier; {@code false} otherwise. 9812 * @see Character#isIdentifierIgnorable(char) 9813 * @see Character#isJavaIdentifierPart(char) 9814 * @see Character#isLetterOrDigit(char) 9815 * @see Character#isUnicodeIdentifierStart(char) 9816 * @since 1.1 9817 */ 9818 public static boolean isUnicodeIdentifierPart(char ch) { 9819 return isUnicodeIdentifierPart((int)ch); 9820 } 9821 9822 /** 9823 * Determines if the specified character (Unicode code point) may be part of a Unicode 9824 * identifier as other than the first character. 9825 * <p> 9826 * A character may be part of a Unicode identifier if and only if 9827 * one of the following statements is true: 9828 * <ul> 9829 * <li> it is a letter 9830 * <li> it is a connecting punctuation character (such as {@code '_'}) 9831 * <li> it is a digit 9832 * <li> it is a numeric letter (such as a Roman numeral character) 9833 * <li> it is a combining mark 9834 * <li> it is a non-spacing mark 9835 * <li> {@code isIdentifierIgnorable} returns 9836 * {@code true} for this character. 9837 * </ul> 9838 * @param codePoint the character (Unicode code point) to be tested. 9839 * @return {@code true} if the character may be part of a 9840 * Unicode identifier; {@code false} otherwise. 9841 * @see Character#isIdentifierIgnorable(int) 9842 * @see Character#isJavaIdentifierPart(int) 9843 * @see Character#isLetterOrDigit(int) 9844 * @see Character#isUnicodeIdentifierStart(int) 9845 * @since 1.5 9846 */ 9847 public static boolean isUnicodeIdentifierPart(int codePoint) { 9848 return CharacterData.of(codePoint).isUnicodeIdentifierPart(codePoint); 9849 } 9850 9851 /** 9852 * Determines if the specified character should be regarded as 9853 * an ignorable character in a Java identifier or a Unicode identifier. 9854 * <p> 9855 * The following Unicode characters are ignorable in a Java identifier 9856 * or a Unicode identifier: 9857 * <ul> 9858 * <li>ISO control characters that are not whitespace 9859 * <ul> 9860 * <li>{@code '\u005Cu0000'} through {@code '\u005Cu0008'} 9861 * <li>{@code '\u005Cu000E'} through {@code '\u005Cu001B'} 9862 * <li>{@code '\u005Cu007F'} through {@code '\u005Cu009F'} 9863 * </ul> 9864 * 9865 * <li>all characters that have the {@code FORMAT} general 9866 * category value 9867 * </ul> 9868 * 9869 * <p><b>Note:</b> This method cannot handle <a 9870 * href="#supplementary"> supplementary characters</a>. To support 9871 * all Unicode characters, including supplementary characters, use 9872 * the {@link #isIdentifierIgnorable(int)} method. 9873 * 9874 * @param ch the character to be tested. 9875 * @return {@code true} if the character is an ignorable control 9876 * character that may be part of a Java or Unicode identifier; 9877 * {@code false} otherwise. 9878 * @see Character#isJavaIdentifierPart(char) 9879 * @see Character#isUnicodeIdentifierPart(char) 9880 * @since 1.1 9881 */ 9882 public static boolean isIdentifierIgnorable(char ch) { 9883 return isIdentifierIgnorable((int)ch); 9884 } 9885 9886 /** 9887 * Determines if the specified character (Unicode code point) should be regarded as 9888 * an ignorable character in a Java identifier or a Unicode identifier. 9889 * <p> 9890 * The following Unicode characters are ignorable in a Java identifier 9891 * or a Unicode identifier: 9892 * <ul> 9893 * <li>ISO control characters that are not whitespace 9894 * <ul> 9895 * <li>{@code '\u005Cu0000'} through {@code '\u005Cu0008'} 9896 * <li>{@code '\u005Cu000E'} through {@code '\u005Cu001B'} 9897 * <li>{@code '\u005Cu007F'} through {@code '\u005Cu009F'} 9898 * </ul> 9899 * 9900 * <li>all characters that have the {@code FORMAT} general 9901 * category value 9902 * </ul> 9903 * 9904 * @param codePoint the character (Unicode code point) to be tested. 9905 * @return {@code true} if the character is an ignorable control 9906 * character that may be part of a Java or Unicode identifier; 9907 * {@code false} otherwise. 9908 * @see Character#isJavaIdentifierPart(int) 9909 * @see Character#isUnicodeIdentifierPart(int) 9910 * @since 1.5 9911 */ 9912 public static boolean isIdentifierIgnorable(int codePoint) { 9913 return CharacterData.of(codePoint).isIdentifierIgnorable(codePoint); 9914 } 9915 9916 /** 9917 * Converts the character argument to lowercase using case 9918 * mapping information from the UnicodeData file. 9919 * <p> 9920 * Note that 9921 * {@code Character.isLowerCase(Character.toLowerCase(ch))} 9922 * does not always return {@code true} for some ranges of 9923 * characters, particularly those that are symbols or ideographs. 9924 * 9925 * <p>In general, {@link String#toLowerCase()} should be used to map 9926 * characters to lowercase. {@code String} case mapping methods 9927 * have several benefits over {@code Character} case mapping methods. 9928 * {@code String} case mapping methods can perform locale-sensitive 9929 * mappings, context-sensitive mappings, and 1:M character mappings, whereas 9930 * the {@code Character} case mapping methods cannot. 9931 * 9932 * <p><b>Note:</b> This method cannot handle <a 9933 * href="#supplementary"> supplementary characters</a>. To support 9934 * all Unicode characters, including supplementary characters, use 9935 * the {@link #toLowerCase(int)} method. 9936 * 9937 * @param ch the character to be converted. 9938 * @return the lowercase equivalent of the character, if any; 9939 * otherwise, the character itself. 9940 * @see Character#isLowerCase(char) 9941 * @see String#toLowerCase() 9942 */ 9943 public static char toLowerCase(char ch) { 9944 return (char)toLowerCase((int)ch); 9945 } 9946 9947 /** 9948 * Converts the character (Unicode code point) argument to 9949 * lowercase using case mapping information from the UnicodeData 9950 * file. 9951 * 9952 * <p> Note that 9953 * {@code Character.isLowerCase(Character.toLowerCase(codePoint))} 9954 * does not always return {@code true} for some ranges of 9955 * characters, particularly those that are symbols or ideographs. 9956 * 9957 * <p>In general, {@link String#toLowerCase()} should be used to map 9958 * characters to lowercase. {@code String} case mapping methods 9959 * have several benefits over {@code Character} case mapping methods. 9960 * {@code String} case mapping methods can perform locale-sensitive 9961 * mappings, context-sensitive mappings, and 1:M character mappings, whereas 9962 * the {@code Character} case mapping methods cannot. 9963 * 9964 * @param codePoint the character (Unicode code point) to be converted. 9965 * @return the lowercase equivalent of the character (Unicode code 9966 * point), if any; otherwise, the character itself. 9967 * @see Character#isLowerCase(int) 9968 * @see String#toLowerCase() 9969 * 9970 * @since 1.5 9971 */ 9972 public static int toLowerCase(int codePoint) { 9973 return CharacterData.of(codePoint).toLowerCase(codePoint); 9974 } 9975 9976 /** 9977 * Converts the character argument to uppercase using case mapping 9978 * information from the UnicodeData file. 9979 * <p> 9980 * Note that 9981 * {@code Character.isUpperCase(Character.toUpperCase(ch))} 9982 * does not always return {@code true} for some ranges of 9983 * characters, particularly those that are symbols or ideographs. 9984 * 9985 * <p>In general, {@link String#toUpperCase()} should be used to map 9986 * characters to uppercase. {@code String} case mapping methods 9987 * have several benefits over {@code Character} case mapping methods. 9988 * {@code String} case mapping methods can perform locale-sensitive 9989 * mappings, context-sensitive mappings, and 1:M character mappings, whereas 9990 * the {@code Character} case mapping methods cannot. 9991 * 9992 * <p><b>Note:</b> This method cannot handle <a 9993 * href="#supplementary"> supplementary characters</a>. To support 9994 * all Unicode characters, including supplementary characters, use 9995 * the {@link #toUpperCase(int)} method. 9996 * 9997 * @param ch the character to be converted. 9998 * @return the uppercase equivalent of the character, if any; 9999 * otherwise, the character itself. 10000 * @see Character#isUpperCase(char) 10001 * @see String#toUpperCase() 10002 */ 10003 public static char toUpperCase(char ch) { 10004 return (char)toUpperCase((int)ch); 10005 } 10006 10007 /** 10008 * Converts the character (Unicode code point) argument to 10009 * uppercase using case mapping information from the UnicodeData 10010 * file. 10011 * 10012 * <p>Note that 10013 * {@code Character.isUpperCase(Character.toUpperCase(codePoint))} 10014 * does not always return {@code true} for some ranges of 10015 * characters, particularly those that are symbols or ideographs. 10016 * 10017 * <p>In general, {@link String#toUpperCase()} should be used to map 10018 * characters to uppercase. {@code String} case mapping methods 10019 * have several benefits over {@code Character} case mapping methods. 10020 * {@code String} case mapping methods can perform locale-sensitive 10021 * mappings, context-sensitive mappings, and 1:M character mappings, whereas 10022 * the {@code Character} case mapping methods cannot. 10023 * 10024 * @param codePoint the character (Unicode code point) to be converted. 10025 * @return the uppercase equivalent of the character, if any; 10026 * otherwise, the character itself. 10027 * @see Character#isUpperCase(int) 10028 * @see String#toUpperCase() 10029 * 10030 * @since 1.5 10031 */ 10032 public static int toUpperCase(int codePoint) { 10033 return CharacterData.of(codePoint).toUpperCase(codePoint); 10034 } 10035 10036 /** 10037 * Converts the character argument to titlecase using case mapping 10038 * information from the UnicodeData file. If a character has no 10039 * explicit titlecase mapping and is not itself a titlecase char 10040 * according to UnicodeData, then the uppercase mapping is 10041 * returned as an equivalent titlecase mapping. If the 10042 * {@code char} argument is already a titlecase 10043 * {@code char}, the same {@code char} value will be 10044 * returned. 10045 * <p> 10046 * Note that 10047 * {@code Character.isTitleCase(Character.toTitleCase(ch))} 10048 * does not always return {@code true} for some ranges of 10049 * characters. 10050 * 10051 * <p><b>Note:</b> This method cannot handle <a 10052 * href="#supplementary"> supplementary characters</a>. To support 10053 * all Unicode characters, including supplementary characters, use 10054 * the {@link #toTitleCase(int)} method. 10055 * 10056 * @param ch the character to be converted. 10057 * @return the titlecase equivalent of the character, if any; 10058 * otherwise, the character itself. 10059 * @see Character#isTitleCase(char) 10060 * @see Character#toLowerCase(char) 10061 * @see Character#toUpperCase(char) 10062 * @since 1.0.2 10063 */ 10064 public static char toTitleCase(char ch) { 10065 return (char)toTitleCase((int)ch); 10066 } 10067 10068 /** 10069 * Converts the character (Unicode code point) argument to titlecase using case mapping 10070 * information from the UnicodeData file. If a character has no 10071 * explicit titlecase mapping and is not itself a titlecase char 10072 * according to UnicodeData, then the uppercase mapping is 10073 * returned as an equivalent titlecase mapping. If the 10074 * character argument is already a titlecase 10075 * character, the same character value will be 10076 * returned. 10077 * 10078 * <p>Note that 10079 * {@code Character.isTitleCase(Character.toTitleCase(codePoint))} 10080 * does not always return {@code true} for some ranges of 10081 * characters. 10082 * 10083 * @param codePoint the character (Unicode code point) to be converted. 10084 * @return the titlecase equivalent of the character, if any; 10085 * otherwise, the character itself. 10086 * @see Character#isTitleCase(int) 10087 * @see Character#toLowerCase(int) 10088 * @see Character#toUpperCase(int) 10089 * @since 1.5 10090 */ 10091 public static int toTitleCase(int codePoint) { 10092 return CharacterData.of(codePoint).toTitleCase(codePoint); 10093 } 10094 10095 /** 10096 * Returns the numeric value of the character {@code ch} in the 10097 * specified radix. 10098 * <p> 10099 * If the radix is not in the range {@code MIN_RADIX} ≤ 10100 * {@code radix} ≤ {@code MAX_RADIX} or if the 10101 * value of {@code ch} is not a valid digit in the specified 10102 * radix, {@code -1} is returned. A character is a valid digit 10103 * if at least one of the following is true: 10104 * <ul> 10105 * <li>The method {@code isDigit} is {@code true} of the character 10106 * and the Unicode decimal digit value of the character (or its 10107 * single-character decomposition) is less than the specified radix. 10108 * In this case the decimal digit value is returned. 10109 * <li>The character is one of the uppercase Latin letters 10110 * {@code 'A'} through {@code 'Z'} and its code is less than 10111 * {@code radix + 'A' - 10}. 10112 * In this case, {@code ch - 'A' + 10} 10113 * is returned. 10114 * <li>The character is one of the lowercase Latin letters 10115 * {@code 'a'} through {@code 'z'} and its code is less than 10116 * {@code radix + 'a' - 10}. 10117 * In this case, {@code ch - 'a' + 10} 10118 * is returned. 10119 * <li>The character is one of the fullwidth uppercase Latin letters A 10120 * ({@code '\u005CuFF21'}) through Z ({@code '\u005CuFF3A'}) 10121 * and its code is less than 10122 * {@code radix + '\u005CuFF21' - 10}. 10123 * In this case, {@code ch - '\u005CuFF21' + 10} 10124 * is returned. 10125 * <li>The character is one of the fullwidth lowercase Latin letters a 10126 * ({@code '\u005CuFF41'}) through z ({@code '\u005CuFF5A'}) 10127 * and its code is less than 10128 * {@code radix + '\u005CuFF41' - 10}. 10129 * In this case, {@code ch - '\u005CuFF41' + 10} 10130 * is returned. 10131 * </ul> 10132 * 10133 * <p><b>Note:</b> This method cannot handle <a 10134 * href="#supplementary"> supplementary characters</a>. To support 10135 * all Unicode characters, including supplementary characters, use 10136 * the {@link #digit(int, int)} method. 10137 * 10138 * @param ch the character to be converted. 10139 * @param radix the radix. 10140 * @return the numeric value represented by the character in the 10141 * specified radix. 10142 * @see Character#forDigit(int, int) 10143 * @see Character#isDigit(char) 10144 */ 10145 public static int digit(char ch, int radix) { 10146 return digit((int)ch, radix); 10147 } 10148 10149 /** 10150 * Returns the numeric value of the specified character (Unicode 10151 * code point) in the specified radix. 10152 * 10153 * <p>If the radix is not in the range {@code MIN_RADIX} ≤ 10154 * {@code radix} ≤ {@code MAX_RADIX} or if the 10155 * character is not a valid digit in the specified 10156 * radix, {@code -1} is returned. A character is a valid digit 10157 * if at least one of the following is true: 10158 * <ul> 10159 * <li>The method {@link #isDigit(int) isDigit(codePoint)} is {@code true} of the character 10160 * and the Unicode decimal digit value of the character (or its 10161 * single-character decomposition) is less than the specified radix. 10162 * In this case the decimal digit value is returned. 10163 * <li>The character is one of the uppercase Latin letters 10164 * {@code 'A'} through {@code 'Z'} and its code is less than 10165 * {@code radix + 'A' - 10}. 10166 * In this case, {@code codePoint - 'A' + 10} 10167 * is returned. 10168 * <li>The character is one of the lowercase Latin letters 10169 * {@code 'a'} through {@code 'z'} and its code is less than 10170 * {@code radix + 'a' - 10}. 10171 * In this case, {@code codePoint - 'a' + 10} 10172 * is returned. 10173 * <li>The character is one of the fullwidth uppercase Latin letters A 10174 * ({@code '\u005CuFF21'}) through Z ({@code '\u005CuFF3A'}) 10175 * and its code is less than 10176 * {@code radix + '\u005CuFF21' - 10}. 10177 * In this case, 10178 * {@code codePoint - '\u005CuFF21' + 10} 10179 * is returned. 10180 * <li>The character is one of the fullwidth lowercase Latin letters a 10181 * ({@code '\u005CuFF41'}) through z ({@code '\u005CuFF5A'}) 10182 * and its code is less than 10183 * {@code radix + '\u005CuFF41'- 10}. 10184 * In this case, 10185 * {@code codePoint - '\u005CuFF41' + 10} 10186 * is returned. 10187 * </ul> 10188 * 10189 * @param codePoint the character (Unicode code point) to be converted. 10190 * @param radix the radix. 10191 * @return the numeric value represented by the character in the 10192 * specified radix. 10193 * @see Character#forDigit(int, int) 10194 * @see Character#isDigit(int) 10195 * @since 1.5 10196 */ 10197 public static int digit(int codePoint, int radix) { 10198 return CharacterData.of(codePoint).digit(codePoint, radix); 10199 } 10200 10201 /** 10202 * Returns the {@code int} value that the specified Unicode 10203 * character represents. For example, the character 10204 * {@code '\u005Cu216C'} (the roman numeral fifty) will return 10205 * an int with a value of 50. 10206 * <p> 10207 * The letters A-Z in their uppercase ({@code '\u005Cu0041'} through 10208 * {@code '\u005Cu005A'}), lowercase 10209 * ({@code '\u005Cu0061'} through {@code '\u005Cu007A'}), and 10210 * full width variant ({@code '\u005CuFF21'} through 10211 * {@code '\u005CuFF3A'} and {@code '\u005CuFF41'} through 10212 * {@code '\u005CuFF5A'}) forms have numeric values from 10 10213 * through 35. This is independent of the Unicode specification, 10214 * which does not assign numeric values to these {@code char} 10215 * values. 10216 * <p> 10217 * If the character does not have a numeric value, then -1 is returned. 10218 * If the character has a numeric value that cannot be represented as a 10219 * nonnegative integer (for example, a fractional value), then -2 10220 * is returned. 10221 * 10222 * <p><b>Note:</b> This method cannot handle <a 10223 * href="#supplementary"> supplementary characters</a>. To support 10224 * all Unicode characters, including supplementary characters, use 10225 * the {@link #getNumericValue(int)} method. 10226 * 10227 * @param ch the character to be converted. 10228 * @return the numeric value of the character, as a nonnegative {@code int} 10229 * value; -2 if the character has a numeric value but the value 10230 * can not be represented as a nonnegative {@code int} value; 10231 * -1 if the character has no numeric value. 10232 * @see Character#forDigit(int, int) 10233 * @see Character#isDigit(char) 10234 * @since 1.1 10235 */ 10236 public static int getNumericValue(char ch) { 10237 return getNumericValue((int)ch); 10238 } 10239 10240 /** 10241 * Returns the {@code int} value that the specified 10242 * character (Unicode code point) represents. For example, the character 10243 * {@code '\u005Cu216C'} (the Roman numeral fifty) will return 10244 * an {@code int} with a value of 50. 10245 * <p> 10246 * The letters A-Z in their uppercase ({@code '\u005Cu0041'} through 10247 * {@code '\u005Cu005A'}), lowercase 10248 * ({@code '\u005Cu0061'} through {@code '\u005Cu007A'}), and 10249 * full width variant ({@code '\u005CuFF21'} through 10250 * {@code '\u005CuFF3A'} and {@code '\u005CuFF41'} through 10251 * {@code '\u005CuFF5A'}) forms have numeric values from 10 10252 * through 35. This is independent of the Unicode specification, 10253 * which does not assign numeric values to these {@code char} 10254 * values. 10255 * <p> 10256 * If the character does not have a numeric value, then -1 is returned. 10257 * If the character has a numeric value that cannot be represented as a 10258 * nonnegative integer (for example, a fractional value), then -2 10259 * is returned. 10260 * 10261 * @param codePoint the character (Unicode code point) to be converted. 10262 * @return the numeric value of the character, as a nonnegative {@code int} 10263 * value; -2 if the character has a numeric value but the value 10264 * can not be represented as a nonnegative {@code int} value; 10265 * -1 if the character has no numeric value. 10266 * @see Character#forDigit(int, int) 10267 * @see Character#isDigit(int) 10268 * @since 1.5 10269 */ 10270 public static int getNumericValue(int codePoint) { 10271 return CharacterData.of(codePoint).getNumericValue(codePoint); 10272 } 10273 10274 /** 10275 * Determines if the specified character is ISO-LATIN-1 white space. 10276 * This method returns {@code true} for the following five 10277 * characters only: 10278 * <table class="striped"> 10279 * <caption style="display:none">truechars</caption> 10280 * <thead> 10281 * <tr><th scope="col">Character 10282 * <th scope="col">Code 10283 * <th scope="col">Name 10284 * </thead> 10285 * <tbody> 10286 * <tr><th scope="row">{@code '\t'}</th> <td>{@code U+0009}</td> 10287 * <td>{@code HORIZONTAL TABULATION}</td></tr> 10288 * <tr><th scope="row">{@code '\n'}</th> <td>{@code U+000A}</td> 10289 * <td>{@code NEW LINE}</td></tr> 10290 * <tr><th scope="row">{@code '\f'}</th> <td>{@code U+000C}</td> 10291 * <td>{@code FORM FEED}</td></tr> 10292 * <tr><th scope="row">{@code '\r'}</th> <td>{@code U+000D}</td> 10293 * <td>{@code CARRIAGE RETURN}</td></tr> 10294 * <tr><th scope="row">{@code ' '}</th> <td>{@code U+0020}</td> 10295 * <td>{@code SPACE}</td></tr> 10296 * </tbody> 10297 * </table> 10298 * 10299 * @param ch the character to be tested. 10300 * @return {@code true} if the character is ISO-LATIN-1 white 10301 * space; {@code false} otherwise. 10302 * @see Character#isSpaceChar(char) 10303 * @see Character#isWhitespace(char) 10304 * @deprecated Replaced by isWhitespace(char). 10305 */ 10306 @Deprecated(since="1.1") 10307 public static boolean isSpace(char ch) { 10308 return (ch <= 0x0020) && 10309 (((((1L << 0x0009) | 10310 (1L << 0x000A) | 10311 (1L << 0x000C) | 10312 (1L << 0x000D) | 10313 (1L << 0x0020)) >> ch) & 1L) != 0); 10314 } 10315 10316 10317 /** 10318 * Determines if the specified character is a Unicode space character. 10319 * A character is considered to be a space character if and only if 10320 * it is specified to be a space character by the Unicode Standard. This 10321 * method returns true if the character's general category type is any of 10322 * the following: 10323 * <ul> 10324 * <li> {@code SPACE_SEPARATOR} 10325 * <li> {@code LINE_SEPARATOR} 10326 * <li> {@code PARAGRAPH_SEPARATOR} 10327 * </ul> 10328 * 10329 * <p><b>Note:</b> This method cannot handle <a 10330 * href="#supplementary"> supplementary characters</a>. To support 10331 * all Unicode characters, including supplementary characters, use 10332 * the {@link #isSpaceChar(int)} method. 10333 * 10334 * @param ch the character to be tested. 10335 * @return {@code true} if the character is a space character; 10336 * {@code false} otherwise. 10337 * @see Character#isWhitespace(char) 10338 * @since 1.1 10339 */ 10340 public static boolean isSpaceChar(char ch) { 10341 return isSpaceChar((int)ch); 10342 } 10343 10344 /** 10345 * Determines if the specified character (Unicode code point) is a 10346 * Unicode space character. A character is considered to be a 10347 * space character if and only if it is specified to be a space 10348 * character by the Unicode Standard. This method returns true if 10349 * the character's general category type is any of the following: 10350 * 10351 * <ul> 10352 * <li> {@link #SPACE_SEPARATOR} 10353 * <li> {@link #LINE_SEPARATOR} 10354 * <li> {@link #PARAGRAPH_SEPARATOR} 10355 * </ul> 10356 * 10357 * @param codePoint the character (Unicode code point) to be tested. 10358 * @return {@code true} if the character is a space character; 10359 * {@code false} otherwise. 10360 * @see Character#isWhitespace(int) 10361 * @since 1.5 10362 */ 10363 public static boolean isSpaceChar(int codePoint) { 10364 return ((((1 << Character.SPACE_SEPARATOR) | 10365 (1 << Character.LINE_SEPARATOR) | 10366 (1 << Character.PARAGRAPH_SEPARATOR)) >> getType(codePoint)) & 1) 10367 != 0; 10368 } 10369 10370 /** 10371 * Determines if the specified character is white space according to Java. 10372 * A character is a Java whitespace character if and only if it satisfies 10373 * one of the following criteria: 10374 * <ul> 10375 * <li> It is a Unicode space character ({@code SPACE_SEPARATOR}, 10376 * {@code LINE_SEPARATOR}, or {@code PARAGRAPH_SEPARATOR}) 10377 * but is not also a non-breaking space ({@code '\u005Cu00A0'}, 10378 * {@code '\u005Cu2007'}, {@code '\u005Cu202F'}). 10379 * <li> It is {@code '\u005Ct'}, U+0009 HORIZONTAL TABULATION. 10380 * <li> It is {@code '\u005Cn'}, U+000A LINE FEED. 10381 * <li> It is {@code '\u005Cu000B'}, U+000B VERTICAL TABULATION. 10382 * <li> It is {@code '\u005Cf'}, U+000C FORM FEED. 10383 * <li> It is {@code '\u005Cr'}, U+000D CARRIAGE RETURN. 10384 * <li> It is {@code '\u005Cu001C'}, U+001C FILE SEPARATOR. 10385 * <li> It is {@code '\u005Cu001D'}, U+001D GROUP SEPARATOR. 10386 * <li> It is {@code '\u005Cu001E'}, U+001E RECORD SEPARATOR. 10387 * <li> It is {@code '\u005Cu001F'}, U+001F UNIT SEPARATOR. 10388 * </ul> 10389 * 10390 * <p><b>Note:</b> This method cannot handle <a 10391 * href="#supplementary"> supplementary characters</a>. To support 10392 * all Unicode characters, including supplementary characters, use 10393 * the {@link #isWhitespace(int)} method. 10394 * 10395 * @param ch the character to be tested. 10396 * @return {@code true} if the character is a Java whitespace 10397 * character; {@code false} otherwise. 10398 * @see Character#isSpaceChar(char) 10399 * @since 1.1 10400 */ 10401 public static boolean isWhitespace(char ch) { 10402 return isWhitespace((int)ch); 10403 } 10404 10405 /** 10406 * Determines if the specified character (Unicode code point) is 10407 * white space according to Java. A character is a Java 10408 * whitespace character if and only if it satisfies one of the 10409 * following criteria: 10410 * <ul> 10411 * <li> It is a Unicode space character ({@link #SPACE_SEPARATOR}, 10412 * {@link #LINE_SEPARATOR}, or {@link #PARAGRAPH_SEPARATOR}) 10413 * but is not also a non-breaking space ({@code '\u005Cu00A0'}, 10414 * {@code '\u005Cu2007'}, {@code '\u005Cu202F'}). 10415 * <li> It is {@code '\u005Ct'}, U+0009 HORIZONTAL TABULATION. 10416 * <li> It is {@code '\u005Cn'}, U+000A LINE FEED. 10417 * <li> It is {@code '\u005Cu000B'}, U+000B VERTICAL TABULATION. 10418 * <li> It is {@code '\u005Cf'}, U+000C FORM FEED. 10419 * <li> It is {@code '\u005Cr'}, U+000D CARRIAGE RETURN. 10420 * <li> It is {@code '\u005Cu001C'}, U+001C FILE SEPARATOR. 10421 * <li> It is {@code '\u005Cu001D'}, U+001D GROUP SEPARATOR. 10422 * <li> It is {@code '\u005Cu001E'}, U+001E RECORD SEPARATOR. 10423 * <li> It is {@code '\u005Cu001F'}, U+001F UNIT SEPARATOR. 10424 * </ul> 10425 * 10426 * @param codePoint the character (Unicode code point) to be tested. 10427 * @return {@code true} if the character is a Java whitespace 10428 * character; {@code false} otherwise. 10429 * @see Character#isSpaceChar(int) 10430 * @since 1.5 10431 */ 10432 public static boolean isWhitespace(int codePoint) { 10433 return CharacterData.of(codePoint).isWhitespace(codePoint); 10434 } 10435 10436 /** 10437 * Determines if the specified character is an ISO control 10438 * character. A character is considered to be an ISO control 10439 * character if its code is in the range {@code '\u005Cu0000'} 10440 * through {@code '\u005Cu001F'} or in the range 10441 * {@code '\u005Cu007F'} through {@code '\u005Cu009F'}. 10442 * 10443 * <p><b>Note:</b> This method cannot handle <a 10444 * href="#supplementary"> supplementary characters</a>. To support 10445 * all Unicode characters, including supplementary characters, use 10446 * the {@link #isISOControl(int)} method. 10447 * 10448 * @param ch the character to be tested. 10449 * @return {@code true} if the character is an ISO control character; 10450 * {@code false} otherwise. 10451 * 10452 * @see Character#isSpaceChar(char) 10453 * @see Character#isWhitespace(char) 10454 * @since 1.1 10455 */ 10456 public static boolean isISOControl(char ch) { 10457 return isISOControl((int)ch); 10458 } 10459 10460 /** 10461 * Determines if the referenced character (Unicode code point) is an ISO control 10462 * character. A character is considered to be an ISO control 10463 * character if its code is in the range {@code '\u005Cu0000'} 10464 * through {@code '\u005Cu001F'} or in the range 10465 * {@code '\u005Cu007F'} through {@code '\u005Cu009F'}. 10466 * 10467 * @param codePoint the character (Unicode code point) to be tested. 10468 * @return {@code true} if the character is an ISO control character; 10469 * {@code false} otherwise. 10470 * @see Character#isSpaceChar(int) 10471 * @see Character#isWhitespace(int) 10472 * @since 1.5 10473 */ 10474 public static boolean isISOControl(int codePoint) { 10475 // Optimized form of: 10476 // (codePoint >= 0x00 && codePoint <= 0x1F) || 10477 // (codePoint >= 0x7F && codePoint <= 0x9F); 10478 return codePoint <= 0x9F && 10479 (codePoint >= 0x7F || (codePoint >>> 5 == 0)); 10480 } 10481 10482 /** 10483 * Returns a value indicating a character's general category. 10484 * 10485 * <p><b>Note:</b> This method cannot handle <a 10486 * href="#supplementary"> supplementary characters</a>. To support 10487 * all Unicode characters, including supplementary characters, use 10488 * the {@link #getType(int)} method. 10489 * 10490 * @param ch the character to be tested. 10491 * @return a value of type {@code int} representing the 10492 * character's general category. 10493 * @see Character#COMBINING_SPACING_MARK 10494 * @see Character#CONNECTOR_PUNCTUATION 10495 * @see Character#CONTROL 10496 * @see Character#CURRENCY_SYMBOL 10497 * @see Character#DASH_PUNCTUATION 10498 * @see Character#DECIMAL_DIGIT_NUMBER 10499 * @see Character#ENCLOSING_MARK 10500 * @see Character#END_PUNCTUATION 10501 * @see Character#FINAL_QUOTE_PUNCTUATION 10502 * @see Character#FORMAT 10503 * @see Character#INITIAL_QUOTE_PUNCTUATION 10504 * @see Character#LETTER_NUMBER 10505 * @see Character#LINE_SEPARATOR 10506 * @see Character#LOWERCASE_LETTER 10507 * @see Character#MATH_SYMBOL 10508 * @see Character#MODIFIER_LETTER 10509 * @see Character#MODIFIER_SYMBOL 10510 * @see Character#NON_SPACING_MARK 10511 * @see Character#OTHER_LETTER 10512 * @see Character#OTHER_NUMBER 10513 * @see Character#OTHER_PUNCTUATION 10514 * @see Character#OTHER_SYMBOL 10515 * @see Character#PARAGRAPH_SEPARATOR 10516 * @see Character#PRIVATE_USE 10517 * @see Character#SPACE_SEPARATOR 10518 * @see Character#START_PUNCTUATION 10519 * @see Character#SURROGATE 10520 * @see Character#TITLECASE_LETTER 10521 * @see Character#UNASSIGNED 10522 * @see Character#UPPERCASE_LETTER 10523 * @since 1.1 10524 */ 10525 public static int getType(char ch) { 10526 return getType((int)ch); 10527 } 10528 10529 /** 10530 * Returns a value indicating a character's general category. 10531 * 10532 * @param codePoint the character (Unicode code point) to be tested. 10533 * @return a value of type {@code int} representing the 10534 * character's general category. 10535 * @see Character#COMBINING_SPACING_MARK COMBINING_SPACING_MARK 10536 * @see Character#CONNECTOR_PUNCTUATION CONNECTOR_PUNCTUATION 10537 * @see Character#CONTROL CONTROL 10538 * @see Character#CURRENCY_SYMBOL CURRENCY_SYMBOL 10539 * @see Character#DASH_PUNCTUATION DASH_PUNCTUATION 10540 * @see Character#DECIMAL_DIGIT_NUMBER DECIMAL_DIGIT_NUMBER 10541 * @see Character#ENCLOSING_MARK ENCLOSING_MARK 10542 * @see Character#END_PUNCTUATION END_PUNCTUATION 10543 * @see Character#FINAL_QUOTE_PUNCTUATION FINAL_QUOTE_PUNCTUATION 10544 * @see Character#FORMAT FORMAT 10545 * @see Character#INITIAL_QUOTE_PUNCTUATION INITIAL_QUOTE_PUNCTUATION 10546 * @see Character#LETTER_NUMBER LETTER_NUMBER 10547 * @see Character#LINE_SEPARATOR LINE_SEPARATOR 10548 * @see Character#LOWERCASE_LETTER LOWERCASE_LETTER 10549 * @see Character#MATH_SYMBOL MATH_SYMBOL 10550 * @see Character#MODIFIER_LETTER MODIFIER_LETTER 10551 * @see Character#MODIFIER_SYMBOL MODIFIER_SYMBOL 10552 * @see Character#NON_SPACING_MARK NON_SPACING_MARK 10553 * @see Character#OTHER_LETTER OTHER_LETTER 10554 * @see Character#OTHER_NUMBER OTHER_NUMBER 10555 * @see Character#OTHER_PUNCTUATION OTHER_PUNCTUATION 10556 * @see Character#OTHER_SYMBOL OTHER_SYMBOL 10557 * @see Character#PARAGRAPH_SEPARATOR PARAGRAPH_SEPARATOR 10558 * @see Character#PRIVATE_USE PRIVATE_USE 10559 * @see Character#SPACE_SEPARATOR SPACE_SEPARATOR 10560 * @see Character#START_PUNCTUATION START_PUNCTUATION 10561 * @see Character#SURROGATE SURROGATE 10562 * @see Character#TITLECASE_LETTER TITLECASE_LETTER 10563 * @see Character#UNASSIGNED UNASSIGNED 10564 * @see Character#UPPERCASE_LETTER UPPERCASE_LETTER 10565 * @since 1.5 10566 */ 10567 public static int getType(int codePoint) { 10568 return CharacterData.of(codePoint).getType(codePoint); 10569 } 10570 10571 /** 10572 * Determines the character representation for a specific digit in 10573 * the specified radix. If the value of {@code radix} is not a 10574 * valid radix, or the value of {@code digit} is not a valid 10575 * digit in the specified radix, the null character 10576 * ({@code '\u005Cu0000'}) is returned. 10577 * <p> 10578 * The {@code radix} argument is valid if it is greater than or 10579 * equal to {@code MIN_RADIX} and less than or equal to 10580 * {@code MAX_RADIX}. The {@code digit} argument is valid if 10581 * {@code 0 <= digit < radix}. 10582 * <p> 10583 * If the digit is less than 10, then 10584 * {@code '0' + digit} is returned. Otherwise, the value 10585 * {@code 'a' + digit - 10} is returned. 10586 * 10587 * @param digit the number to convert to a character. 10588 * @param radix the radix. 10589 * @return the {@code char} representation of the specified digit 10590 * in the specified radix. 10591 * @see Character#MIN_RADIX 10592 * @see Character#MAX_RADIX 10593 * @see Character#digit(char, int) 10594 */ 10595 public static char forDigit(int digit, int radix) { 10596 if ((digit >= radix) || (digit < 0)) { 10597 return '\0'; 10598 } 10599 if ((radix < Character.MIN_RADIX) || (radix > Character.MAX_RADIX)) { 10600 return '\0'; 10601 } 10602 if (digit < 10) { 10603 return (char)('0' + digit); 10604 } 10605 return (char)('a' - 10 + digit); 10606 } 10607 10608 /** 10609 * Returns the Unicode directionality property for the given 10610 * character. Character directionality is used to calculate the 10611 * visual ordering of text. The directionality value of undefined 10612 * {@code char} values is {@code DIRECTIONALITY_UNDEFINED}. 10613 * 10614 * <p><b>Note:</b> This method cannot handle <a 10615 * href="#supplementary"> supplementary characters</a>. To support 10616 * all Unicode characters, including supplementary characters, use 10617 * the {@link #getDirectionality(int)} method. 10618 * 10619 * @param ch {@code char} for which the directionality property 10620 * is requested. 10621 * @return the directionality property of the {@code char} value. 10622 * 10623 * @see Character#DIRECTIONALITY_UNDEFINED 10624 * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT 10625 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT 10626 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_ARABIC 10627 * @see Character#DIRECTIONALITY_EUROPEAN_NUMBER 10628 * @see Character#DIRECTIONALITY_EUROPEAN_NUMBER_SEPARATOR 10629 * @see Character#DIRECTIONALITY_EUROPEAN_NUMBER_TERMINATOR 10630 * @see Character#DIRECTIONALITY_ARABIC_NUMBER 10631 * @see Character#DIRECTIONALITY_COMMON_NUMBER_SEPARATOR 10632 * @see Character#DIRECTIONALITY_NONSPACING_MARK 10633 * @see Character#DIRECTIONALITY_BOUNDARY_NEUTRAL 10634 * @see Character#DIRECTIONALITY_PARAGRAPH_SEPARATOR 10635 * @see Character#DIRECTIONALITY_SEGMENT_SEPARATOR 10636 * @see Character#DIRECTIONALITY_WHITESPACE 10637 * @see Character#DIRECTIONALITY_OTHER_NEUTRALS 10638 * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT_EMBEDDING 10639 * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT_OVERRIDE 10640 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_EMBEDDING 10641 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_OVERRIDE 10642 * @see Character#DIRECTIONALITY_POP_DIRECTIONAL_FORMAT 10643 * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT_ISOLATE 10644 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_ISOLATE 10645 * @see Character#DIRECTIONALITY_FIRST_STRONG_ISOLATE 10646 * @see Character#DIRECTIONALITY_POP_DIRECTIONAL_ISOLATE 10647 * @since 1.4 10648 */ 10649 public static byte getDirectionality(char ch) { 10650 return getDirectionality((int)ch); 10651 } 10652 10653 /** 10654 * Returns the Unicode directionality property for the given 10655 * character (Unicode code point). Character directionality is 10656 * used to calculate the visual ordering of text. The 10657 * directionality value of undefined character is {@link 10658 * #DIRECTIONALITY_UNDEFINED}. 10659 * 10660 * @param codePoint the character (Unicode code point) for which 10661 * the directionality property is requested. 10662 * @return the directionality property of the character. 10663 * 10664 * @see Character#DIRECTIONALITY_UNDEFINED DIRECTIONALITY_UNDEFINED 10665 * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT DIRECTIONALITY_LEFT_TO_RIGHT 10666 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT DIRECTIONALITY_RIGHT_TO_LEFT 10667 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_ARABIC DIRECTIONALITY_RIGHT_TO_LEFT_ARABIC 10668 * @see Character#DIRECTIONALITY_EUROPEAN_NUMBER DIRECTIONALITY_EUROPEAN_NUMBER 10669 * @see Character#DIRECTIONALITY_EUROPEAN_NUMBER_SEPARATOR DIRECTIONALITY_EUROPEAN_NUMBER_SEPARATOR 10670 * @see Character#DIRECTIONALITY_EUROPEAN_NUMBER_TERMINATOR DIRECTIONALITY_EUROPEAN_NUMBER_TERMINATOR 10671 * @see Character#DIRECTIONALITY_ARABIC_NUMBER DIRECTIONALITY_ARABIC_NUMBER 10672 * @see Character#DIRECTIONALITY_COMMON_NUMBER_SEPARATOR DIRECTIONALITY_COMMON_NUMBER_SEPARATOR 10673 * @see Character#DIRECTIONALITY_NONSPACING_MARK DIRECTIONALITY_NONSPACING_MARK 10674 * @see Character#DIRECTIONALITY_BOUNDARY_NEUTRAL DIRECTIONALITY_BOUNDARY_NEUTRAL 10675 * @see Character#DIRECTIONALITY_PARAGRAPH_SEPARATOR DIRECTIONALITY_PARAGRAPH_SEPARATOR 10676 * @see Character#DIRECTIONALITY_SEGMENT_SEPARATOR DIRECTIONALITY_SEGMENT_SEPARATOR 10677 * @see Character#DIRECTIONALITY_WHITESPACE DIRECTIONALITY_WHITESPACE 10678 * @see Character#DIRECTIONALITY_OTHER_NEUTRALS DIRECTIONALITY_OTHER_NEUTRALS 10679 * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT_EMBEDDING DIRECTIONALITY_LEFT_TO_RIGHT_EMBEDDING 10680 * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT_OVERRIDE DIRECTIONALITY_LEFT_TO_RIGHT_OVERRIDE 10681 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_EMBEDDING DIRECTIONALITY_RIGHT_TO_LEFT_EMBEDDING 10682 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_OVERRIDE DIRECTIONALITY_RIGHT_TO_LEFT_OVERRIDE 10683 * @see Character#DIRECTIONALITY_POP_DIRECTIONAL_FORMAT DIRECTIONALITY_POP_DIRECTIONAL_FORMAT 10684 * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT_ISOLATE DIRECTIONALITY_LEFT_TO_RIGHT_ISOLATE 10685 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_ISOLATE DIRECTIONALITY_RIGHT_TO_LEFT_ISOLATE 10686 * @see Character#DIRECTIONALITY_FIRST_STRONG_ISOLATE DIRECTIONALITY_FIRST_STRONG_ISOLATE 10687 * @see Character#DIRECTIONALITY_POP_DIRECTIONAL_ISOLATE DIRECTIONALITY_POP_DIRECTIONAL_ISOLATE 10688 * @since 1.5 10689 */ 10690 public static byte getDirectionality(int codePoint) { 10691 return CharacterData.of(codePoint).getDirectionality(codePoint); 10692 } 10693 10694 /** 10695 * Determines whether the character is mirrored according to the 10696 * Unicode specification. Mirrored characters should have their 10697 * glyphs horizontally mirrored when displayed in text that is 10698 * right-to-left. For example, {@code '\u005Cu0028'} LEFT 10699 * PARENTHESIS is semantically defined to be an <i>opening 10700 * parenthesis</i>. This will appear as a "(" in text that is 10701 * left-to-right but as a ")" in text that is right-to-left. 10702 * 10703 * <p><b>Note:</b> This method cannot handle <a 10704 * href="#supplementary"> supplementary characters</a>. To support 10705 * all Unicode characters, including supplementary characters, use 10706 * the {@link #isMirrored(int)} method. 10707 * 10708 * @param ch {@code char} for which the mirrored property is requested 10709 * @return {@code true} if the char is mirrored, {@code false} 10710 * if the {@code char} is not mirrored or is not defined. 10711 * @since 1.4 10712 */ 10713 public static boolean isMirrored(char ch) { 10714 return isMirrored((int)ch); 10715 } 10716 10717 /** 10718 * Determines whether the specified character (Unicode code point) 10719 * is mirrored according to the Unicode specification. Mirrored 10720 * characters should have their glyphs horizontally mirrored when 10721 * displayed in text that is right-to-left. For example, 10722 * {@code '\u005Cu0028'} LEFT PARENTHESIS is semantically 10723 * defined to be an <i>opening parenthesis</i>. This will appear 10724 * as a "(" in text that is left-to-right but as a ")" in text 10725 * that is right-to-left. 10726 * 10727 * @param codePoint the character (Unicode code point) to be tested. 10728 * @return {@code true} if the character is mirrored, {@code false} 10729 * if the character is not mirrored or is not defined. 10730 * @since 1.5 10731 */ 10732 public static boolean isMirrored(int codePoint) { 10733 return CharacterData.of(codePoint).isMirrored(codePoint); 10734 } 10735 10736 /** 10737 * Compares two {@code Character} objects numerically. 10738 * 10739 * @param anotherCharacter the {@code Character} to be compared. 10740 10741 * @return the value {@code 0} if the argument {@code Character} 10742 * is equal to this {@code Character}; a value less than 10743 * {@code 0} if this {@code Character} is numerically less 10744 * than the {@code Character} argument; and a value greater than 10745 * {@code 0} if this {@code Character} is numerically greater 10746 * than the {@code Character} argument (unsigned comparison). 10747 * Note that this is strictly a numerical comparison; it is not 10748 * locale-dependent. 10749 * @since 1.2 10750 */ 10751 public int compareTo(Character anotherCharacter) { 10752 return compare(this.value, anotherCharacter.value); 10753 } 10754 10755 /** 10756 * Compares two {@code char} values numerically. 10757 * The value returned is identical to what would be returned by: 10758 * <pre> 10759 * Character.valueOf(x).compareTo(Character.valueOf(y)) 10760 * </pre> 10761 * 10762 * @param x the first {@code char} to compare 10763 * @param y the second {@code char} to compare 10764 * @return the value {@code 0} if {@code x == y}; 10765 * a value less than {@code 0} if {@code x < y}; and 10766 * a value greater than {@code 0} if {@code x > y} 10767 * @since 1.7 10768 */ 10769 public static int compare(char x, char y) { 10770 return x - y; 10771 } 10772 10773 /** 10774 * Converts the character (Unicode code point) argument to uppercase using 10775 * information from the UnicodeData file. 10776 * 10777 * @param codePoint the character (Unicode code point) to be converted. 10778 * @return either the uppercase equivalent of the character, if 10779 * any, or an error flag ({@code Character.ERROR}) 10780 * that indicates that a 1:M {@code char} mapping exists. 10781 * @see Character#isLowerCase(char) 10782 * @see Character#isUpperCase(char) 10783 * @see Character#toLowerCase(char) 10784 * @see Character#toTitleCase(char) 10785 * @since 1.4 10786 */ 10787 static int toUpperCaseEx(int codePoint) { 10788 assert isValidCodePoint(codePoint); 10789 return CharacterData.of(codePoint).toUpperCaseEx(codePoint); 10790 } 10791 10792 /** 10793 * Converts the character (Unicode code point) argument to uppercase using case 10794 * mapping information from the SpecialCasing file in the Unicode 10795 * specification. If a character has no explicit uppercase 10796 * mapping, then the {@code char} itself is returned in the 10797 * {@code char[]}. 10798 * 10799 * @param codePoint the character (Unicode code point) to be converted. 10800 * @return a {@code char[]} with the uppercased character. 10801 * @since 1.4 10802 */ 10803 static char[] toUpperCaseCharArray(int codePoint) { 10804 // As of Unicode 6.0, 1:M uppercasings only happen in the BMP. 10805 assert isBmpCodePoint(codePoint); 10806 return CharacterData.of(codePoint).toUpperCaseCharArray(codePoint); 10807 } 10808 10809 /** 10810 * The number of bits used to represent a {@code char} value in unsigned 10811 * binary form, constant {@code 16}. 10812 * 10813 * @since 1.5 10814 */ 10815 public static final int SIZE = 16; 10816 10817 /** 10818 * The number of bytes used to represent a {@code char} value in unsigned 10819 * binary form. 10820 * 10821 * @since 1.8 10822 */ 10823 public static final int BYTES = SIZE / Byte.SIZE; 10824 10825 /** 10826 * Returns the value obtained by reversing the order of the bytes in the 10827 * specified {@code char} value. 10828 * 10829 * @param ch The {@code char} of which to reverse the byte order. 10830 * @return the value obtained by reversing (or, equivalently, swapping) 10831 * the bytes in the specified {@code char} value. 10832 * @since 1.5 10833 */ 10834 @HotSpotIntrinsicCandidate 10835 public static char reverseBytes(char ch) { 10836 return (char) (((ch & 0xFF00) >> 8) | (ch << 8)); 10837 } 10838 10839 /** 10840 * Returns the Unicode name of the specified character 10841 * {@code codePoint}, or null if the code point is 10842 * {@link #UNASSIGNED unassigned}. 10843 * <p> 10844 * Note: if the specified character is not assigned a name by 10845 * the <i>UnicodeData</i> file (part of the Unicode Character 10846 * Database maintained by the Unicode Consortium), the returned 10847 * name is the same as the result of expression. 10848 * 10849 * <blockquote>{@code 10850 * Character.UnicodeBlock.of(codePoint).toString().replace('_', ' ') 10851 * + " " 10852 * + Integer.toHexString(codePoint).toUpperCase(Locale.ROOT); 10853 * 10854 * }</blockquote> 10855 * 10856 * @param codePoint the character (Unicode code point) 10857 * 10858 * @return the Unicode name of the specified character, or null if 10859 * the code point is unassigned. 10860 * 10861 * @throws IllegalArgumentException if the specified 10862 * {@code codePoint} is not a valid Unicode 10863 * code point. 10864 * 10865 * @since 1.7 10866 */ 10867 public static String getName(int codePoint) { 10868 if (!isValidCodePoint(codePoint)) { 10869 throw new IllegalArgumentException( 10870 String.format("Not a valid Unicode code point: 0x%X", codePoint)); 10871 } 10872 String name = CharacterName.getInstance().getName(codePoint); 10873 if (name != null) 10874 return name; 10875 if (getType(codePoint) == UNASSIGNED) 10876 return null; 10877 UnicodeBlock block = UnicodeBlock.of(codePoint); 10878 if (block != null) 10879 return block.toString().replace('_', ' ') + " " 10880 + Integer.toHexString(codePoint).toUpperCase(Locale.ROOT); 10881 // should never come here 10882 return Integer.toHexString(codePoint).toUpperCase(Locale.ROOT); 10883 } 10884 10885 /** 10886 * Returns the code point value of the Unicode character specified by 10887 * the given Unicode character name. 10888 * <p> 10889 * Note: if a character is not assigned a name by the <i>UnicodeData</i> 10890 * file (part of the Unicode Character Database maintained by the Unicode 10891 * Consortium), its name is defined as the result of expression 10892 * 10893 * <blockquote>{@code 10894 * Character.UnicodeBlock.of(codePoint).toString().replace('_', ' ') 10895 * + " " 10896 * + Integer.toHexString(codePoint).toUpperCase(Locale.ROOT); 10897 * 10898 * }</blockquote> 10899 * <p> 10900 * The {@code name} matching is case insensitive, with any leading and 10901 * trailing whitespace character removed. 10902 * 10903 * @param name the Unicode character name 10904 * 10905 * @return the code point value of the character specified by its name. 10906 * 10907 * @throws IllegalArgumentException if the specified {@code name} 10908 * is not a valid Unicode character name. 10909 * @throws NullPointerException if {@code name} is {@code null} 10910 * 10911 * @since 9 10912 */ 10913 public static int codePointOf(String name) { 10914 name = name.trim().toUpperCase(Locale.ROOT); 10915 int cp = CharacterName.getInstance().getCodePoint(name); 10916 if (cp != -1) 10917 return cp; 10918 try { 10919 int off = name.lastIndexOf(' '); 10920 if (off != -1) { 10921 cp = Integer.parseInt(name, off + 1, name.length(), 16); 10922 if (isValidCodePoint(cp) && name.equals(getName(cp))) 10923 return cp; 10924 } 10925 } catch (Exception x) {} 10926 throw new IllegalArgumentException("Unrecognized character name :" + name); 10927 } 10928 }