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