1 /*
2 * Copyright (c) 2002, 2024, 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 jdk.internal.misc.CDS;
29 import jdk.internal.value.DeserializeConstructor;
30 import jdk.internal.vm.annotation.IntrinsicCandidate;
31 import jdk.internal.vm.annotation.Stable;
32
33 import java.lang.constant.Constable;
34 import java.lang.constant.DynamicConstantDesc;
35 import java.util.Arrays;
36 import java.util.HashMap;
37 import java.util.Locale;
38 import java.util.Map;
39 import java.util.Objects;
40 import java.util.Optional;
41
42 import static java.lang.constant.ConstantDescs.BSM_EXPLICIT_CAST;
43 import static java.lang.constant.ConstantDescs.CD_char;
44 import static java.lang.constant.ConstantDescs.DEFAULT_NAME;
45
46 /**
47 * The {@code Character} class is the {@linkplain
48 * java.lang##wrapperClass wrapper class} for values of the primitive
49 * type {@code char}. An object of type {@code Character} contains a
50 * single field whose type is {@code char}.
51 *
52 * <p>In addition, this class provides a large number of static methods for
53 * determining a character's category (lowercase letter, digit, etc.)
54 * and for converting characters from uppercase to lowercase and vice
55 * versa.
56 *
57 * <h2><a id="conformance">Unicode Conformance</a></h2>
58 * <p>
59 * The fields and methods of class {@code Character} are defined in terms
60 * of character information from the Unicode Standard, specifically the
61 * <i>UnicodeData</i> file that is part of the Unicode Character Database.
62 * This file specifies properties including name and category for every
63 * assigned Unicode code point or character range. The file is available
64 * from the Unicode Consortium at
65 * <a href="http://www.unicode.org">http://www.unicode.org</a>.
66 * <p>
67 * Character information is based on the Unicode Standard, version 15.1.
68 * <p>
69 * The Java platform has supported different versions of the Unicode
70 * Standard over time. Upgrades to newer versions of the Unicode Standard
71 * occurred in the following Java releases, each indicating the new version:
72 * <table class="striped">
73 * <caption style="display:none">Shows Java releases and supported Unicode versions</caption>
74 * <thead>
75 * <tr><th scope="col">Java release</th>
76 * <th scope="col">Unicode version</th></tr>
77 * </thead>
78 * <tbody>
79 * <tr><th scope="row" style="text-align:left">Java SE 22</th>
80 * <td>Unicode 15.1</td></tr>
81 * <tr><th scope="row" style="text-align:left">Java SE 20</th>
82 * <td>Unicode 15.0</td></tr>
83 * <tr><th scope="row" style="text-align:left">Java SE 19</th>
84 * <td>Unicode 14.0</td></tr>
85 * <tr><th scope="row" style="text-align:left">Java SE 15</th>
86 * <td>Unicode 13.0</td></tr>
87 * <tr><th scope="row" style="text-align:left">Java SE 13</th>
88 * <td>Unicode 12.1</td></tr>
89 * <tr><th scope="row" style="text-align:left">Java SE 12</th>
90 * <td>Unicode 11.0</td></tr>
91 * <tr><th scope="row" style="text-align:left">Java SE 11</th>
92 * <td>Unicode 10.0</td></tr>
93 * <tr><th scope="row" style="text-align:left">Java SE 9</th>
94 * <td>Unicode 8.0</td></tr>
95 * <tr><th scope="row" style="text-align:left">Java SE 8</th>
96 * <td>Unicode 6.2</td></tr>
97 * <tr><th scope="row" style="text-align:left">Java SE 7</th>
98 * <td>Unicode 6.0</td></tr>
99 * <tr><th scope="row" style="text-align:left">Java SE 5.0</th>
100 * <td>Unicode 4.0</td></tr>
101 * <tr><th scope="row" style="text-align:left">Java SE 1.4</th>
102 * <td>Unicode 3.0</td></tr>
103 * <tr><th scope="row" style="text-align:left">JDK 1.1</th>
104 * <td>Unicode 2.0</td></tr>
105 * <tr><th scope="row" style="text-align:left">JDK 1.0.2</th>
106 * <td>Unicode 1.1.5</td></tr>
107 * </tbody>
108 * </table>
109 * Variations from these base Unicode versions, such as recognized appendixes,
110 * are documented elsewhere.
111 * <h2><a id="unicode">Unicode Character Representations</a></h2>
112 *
113 * <p>The {@code char} data type (and therefore the value that a
114 * {@code Character} object encapsulates) are based on the
115 * original Unicode specification, which defined characters as
116 * fixed-width 16-bit entities. The Unicode Standard has since been
117 * changed to allow for characters whose representation requires more
118 * than 16 bits. The range of legal <em>code point</em>s is now
119 * U+0000 to U+10FFFF, known as <em>Unicode scalar value</em>.
120 * (Refer to the <a
121 * href="http://www.unicode.org/reports/tr27/#notation"><i>
122 * definition</i></a> of the U+<i>n</i> notation in the Unicode
123 * Standard.)
124 *
125 * <p><a id="BMP">The set of characters from U+0000 to U+FFFF</a> is
126 * sometimes referred to as the <em>Basic Multilingual Plane (BMP)</em>.
127 * <a id="supplementary">Characters</a> whose code points are greater
128 * than U+FFFF are called <em>supplementary character</em>s. The Java
129 * platform uses the UTF-16 representation in {@code char} arrays and
130 * in the {@code String} and {@code StringBuffer} classes. In
131 * this representation, supplementary characters are represented as a pair
132 * of {@code char} values, the first from the <em>high-surrogates</em>
133 * range, (\uD800-\uDBFF), the second from the
134 * <em>low-surrogates</em> range (\uDC00-\uDFFF).
135 *
136 * <p>A {@code char} value, therefore, represents Basic
137 * Multilingual Plane (BMP) code points, including the surrogate
138 * code points, or code units of the UTF-16 encoding. An
139 * {@code int} value represents all Unicode code points,
140 * including supplementary code points. The lower (least significant)
141 * 21 bits of {@code int} are used to represent Unicode code
142 * points and the upper (most significant) 11 bits must be zero.
143 * Unless otherwise specified, the behavior with respect to
144 * supplementary characters and surrogate {@code char} values is
145 * as follows:
146 *
147 * <ul>
148 * <li>The methods that only accept a {@code char} value cannot support
149 * supplementary characters. They treat {@code char} values from the
150 * surrogate ranges as undefined characters. For example,
151 * {@code Character.isLetter('\u005CuD840')} returns {@code false}, even though
152 * this specific value if followed by any low-surrogate value in a string
153 * would represent a letter.
154 *
155 * <li>The methods that accept an {@code int} value support all
156 * Unicode characters, including supplementary characters. For
157 * example, {@code Character.isLetter(0x2F81A)} returns
158 * {@code true} because the code point value represents a letter
159 * (a CJK ideograph).
160 * </ul>
161 *
162 * <p>In the Java SE API documentation, <em>Unicode code point</em> is
163 * used for character values in the range between U+0000 and U+10FFFF,
164 * and <em>Unicode code unit</em> is used for 16-bit
165 * {@code char} values that are code units of the <em>UTF-16</em>
166 * encoding. For more information on Unicode terminology, refer to the
167 * <a href="http://www.unicode.org/glossary/">Unicode Glossary</a>.
168 *
169 * <p>This is a <a href="{@docRoot}/java.base/java/lang/doc-files/ValueBased.html">value-based</a>
170 * class; programmers should treat instances that are {@linkplain #equals(Object) equal}
171 * as interchangeable and should not use instances for synchronization, mutexes, or
172 * with {@linkplain java.lang.ref.Reference object references}.
173 *
174 * <div class="preview-block">
175 * <div class="preview-comment">
176 * When preview features are enabled, {@code Character} is a {@linkplain Class#isValue value class}.
177 * Use of value class instances for synchronization, mutexes, or with
178 * {@linkplain java.lang.ref.Reference object references} result in
179 * {@link IdentityException}.
180 * </div>
181 * </div>
182 *
183 * @spec https://www.unicode.org/reports/tr27 Unicode 3.1.0
184 * @author Lee Boynton
185 * @author Guy Steele
186 * @author Akira Tanaka
187 * @author Martin Buchholz
188 * @author Ulf Zibis
189 * @since 1.0
190 */
191 @jdk.internal.MigratedValueClass
192 @jdk.internal.ValueBased
193 public final class Character implements java.io.Serializable, Comparable<Character>, Constable {
194 /**
195 * The minimum radix available for conversion to and from strings.
196 * The constant value of this field is the smallest value permitted
197 * for the radix argument in radix-conversion methods such as the
198 * {@code digit} method, the {@code forDigit} method, and the
199 * {@code toString} method of class {@code Integer}.
200 *
201 * @see Character#digit(char, int)
202 * @see Character#forDigit(int, int)
203 * @see Integer#toString(int, int)
204 * @see Integer#valueOf(String)
205 */
206 public static final int MIN_RADIX = 2;
207
208 /**
209 * The maximum radix available for conversion to and from strings.
210 * The constant value of this field is the largest value permitted
211 * for the radix argument in radix-conversion methods such as the
212 * {@code digit} method, the {@code forDigit} method, and the
213 * {@code toString} method of class {@code Integer}.
214 *
215 * @see Character#digit(char, int)
216 * @see Character#forDigit(int, int)
217 * @see Integer#toString(int, int)
218 * @see Integer#valueOf(String)
219 */
220 public static final int MAX_RADIX = 36;
221
222 /**
223 * The constant value of this field is the smallest value of type
224 * {@code char}, {@code '\u005Cu0000'}.
225 *
226 * @since 1.0.2
227 */
228 public static final char MIN_VALUE = '\u0000';
229
230 /**
231 * The constant value of this field is the largest value of type
232 * {@code char}, {@code '\u005CuFFFF'}.
233 *
234 * @since 1.0.2
235 */
236 public static final char MAX_VALUE = '\uFFFF';
237
238 /**
239 * The {@code Class} instance representing the primitive type
240 * {@code char}.
241 *
242 * @since 1.1
243 */
244 public static final Class<Character> TYPE = Class.getPrimitiveClass("char");
245
246 /*
247 * Normative general types
248 */
249
250 /*
251 * General character types
252 */
253
254 /**
255 * General category "Cn" in the Unicode specification.
256 * @since 1.1
257 */
258 public static final byte UNASSIGNED = 0;
259
260 /**
261 * General category "Lu" in the Unicode specification.
262 * @since 1.1
263 */
264 public static final byte UPPERCASE_LETTER = 1;
265
266 /**
267 * General category "Ll" in the Unicode specification.
268 * @since 1.1
269 */
270 public static final byte LOWERCASE_LETTER = 2;
271
272 /**
273 * General category "Lt" in the Unicode specification.
274 * @since 1.1
275 */
276 public static final byte TITLECASE_LETTER = 3;
277
278 /**
279 * General category "Lm" in the Unicode specification.
280 * @since 1.1
281 */
282 public static final byte MODIFIER_LETTER = 4;
283
284 /**
285 * General category "Lo" in the Unicode specification.
286 * @since 1.1
287 */
288 public static final byte OTHER_LETTER = 5;
289
290 /**
291 * General category "Mn" in the Unicode specification.
292 * @since 1.1
293 */
294 public static final byte NON_SPACING_MARK = 6;
295
296 /**
297 * General category "Me" in the Unicode specification.
298 * @since 1.1
299 */
300 public static final byte ENCLOSING_MARK = 7;
301
302 /**
303 * General category "Mc" in the Unicode specification.
304 * @since 1.1
305 */
306 public static final byte COMBINING_SPACING_MARK = 8;
307
308 /**
309 * General category "Nd" in the Unicode specification.
310 * @since 1.1
311 */
312 public static final byte DECIMAL_DIGIT_NUMBER = 9;
313
314 /**
315 * General category "Nl" in the Unicode specification.
316 * @since 1.1
317 */
318 public static final byte LETTER_NUMBER = 10;
319
320 /**
321 * General category "No" in the Unicode specification.
322 * @since 1.1
323 */
324 public static final byte OTHER_NUMBER = 11;
325
326 /**
327 * General category "Zs" in the Unicode specification.
328 * @since 1.1
329 */
330 public static final byte SPACE_SEPARATOR = 12;
331
332 /**
333 * General category "Zl" in the Unicode specification.
334 * @since 1.1
335 */
336 public static final byte LINE_SEPARATOR = 13;
337
338 /**
339 * General category "Zp" in the Unicode specification.
340 * @since 1.1
341 */
342 public static final byte PARAGRAPH_SEPARATOR = 14;
343
344 /**
345 * General category "Cc" in the Unicode specification.
346 * @since 1.1
347 */
348 public static final byte CONTROL = 15;
349
350 /**
351 * General category "Cf" in the Unicode specification.
352 * @since 1.1
353 */
354 public static final byte FORMAT = 16;
355
356 /**
357 * General category "Co" in the Unicode specification.
358 * @since 1.1
359 */
360 public static final byte PRIVATE_USE = 18;
361
362 /**
363 * General category "Cs" in the Unicode specification.
364 * @since 1.1
365 */
366 public static final byte SURROGATE = 19;
367
368 /**
369 * General category "Pd" in the Unicode specification.
370 * @since 1.1
371 */
372 public static final byte DASH_PUNCTUATION = 20;
373
374 /**
375 * General category "Ps" in the Unicode specification.
376 * @since 1.1
377 */
378 public static final byte START_PUNCTUATION = 21;
379
380 /**
381 * General category "Pe" in the Unicode specification.
382 * @since 1.1
383 */
384 public static final byte END_PUNCTUATION = 22;
385
386 /**
387 * General category "Pc" in the Unicode specification.
388 * @since 1.1
389 */
390 public static final byte CONNECTOR_PUNCTUATION = 23;
391
392 /**
393 * General category "Po" in the Unicode specification.
394 * @since 1.1
395 */
396 public static final byte OTHER_PUNCTUATION = 24;
397
398 /**
399 * General category "Sm" in the Unicode specification.
400 * @since 1.1
401 */
402 public static final byte MATH_SYMBOL = 25;
403
404 /**
405 * General category "Sc" in the Unicode specification.
406 * @since 1.1
407 */
408 public static final byte CURRENCY_SYMBOL = 26;
409
410 /**
411 * General category "Sk" in the Unicode specification.
412 * @since 1.1
413 */
414 public static final byte MODIFIER_SYMBOL = 27;
415
416 /**
417 * General category "So" in the Unicode specification.
418 * @since 1.1
419 */
420 public static final byte OTHER_SYMBOL = 28;
421
422 /**
423 * General category "Pi" in the Unicode specification.
424 * @since 1.4
425 */
426 public static final byte INITIAL_QUOTE_PUNCTUATION = 29;
427
428 /**
429 * General category "Pf" in the Unicode specification.
430 * @since 1.4
431 */
432 public static final byte FINAL_QUOTE_PUNCTUATION = 30;
433
434 /**
435 * Error flag. Use int (code point) to avoid confusion with U+FFFF.
436 */
437 static final int ERROR = 0xFFFFFFFF;
438
439
440 /**
441 * Undefined bidirectional character type. Undefined {@code char}
442 * values have undefined directionality in the Unicode specification.
443 * @since 1.4
444 */
445 public static final byte DIRECTIONALITY_UNDEFINED = -1;
446
447 /**
448 * Strong bidirectional character type "L" in the Unicode specification.
449 * @since 1.4
450 */
451 public static final byte DIRECTIONALITY_LEFT_TO_RIGHT = 0;
452
453 /**
454 * Strong bidirectional character type "R" in the Unicode specification.
455 * @since 1.4
456 */
457 public static final byte DIRECTIONALITY_RIGHT_TO_LEFT = 1;
458
459 /**
460 * Strong bidirectional character type "AL" in the Unicode specification.
461 * @since 1.4
462 */
463 public static final byte DIRECTIONALITY_RIGHT_TO_LEFT_ARABIC = 2;
464
465 /**
466 * Weak bidirectional character type "EN" in the Unicode specification.
467 * @since 1.4
468 */
469 public static final byte DIRECTIONALITY_EUROPEAN_NUMBER = 3;
470
471 /**
472 * Weak bidirectional character type "ES" in the Unicode specification.
473 * @since 1.4
474 */
475 public static final byte DIRECTIONALITY_EUROPEAN_NUMBER_SEPARATOR = 4;
476
477 /**
478 * Weak bidirectional character type "ET" in the Unicode specification.
479 * @since 1.4
480 */
481 public static final byte DIRECTIONALITY_EUROPEAN_NUMBER_TERMINATOR = 5;
482
483 /**
484 * Weak bidirectional character type "AN" in the Unicode specification.
485 * @since 1.4
486 */
487 public static final byte DIRECTIONALITY_ARABIC_NUMBER = 6;
488
489 /**
490 * Weak bidirectional character type "CS" in the Unicode specification.
491 * @since 1.4
492 */
493 public static final byte DIRECTIONALITY_COMMON_NUMBER_SEPARATOR = 7;
494
495 /**
496 * Weak bidirectional character type "NSM" in the Unicode specification.
497 * @since 1.4
498 */
499 public static final byte DIRECTIONALITY_NONSPACING_MARK = 8;
500
501 /**
502 * Weak bidirectional character type "BN" in the Unicode specification.
503 * @since 1.4
504 */
505 public static final byte DIRECTIONALITY_BOUNDARY_NEUTRAL = 9;
506
507 /**
508 * Neutral bidirectional character type "B" in the Unicode specification.
509 * @since 1.4
510 */
511 public static final byte DIRECTIONALITY_PARAGRAPH_SEPARATOR = 10;
512
513 /**
514 * Neutral bidirectional character type "S" in the Unicode specification.
515 * @since 1.4
516 */
517 public static final byte DIRECTIONALITY_SEGMENT_SEPARATOR = 11;
518
519 /**
520 * Neutral bidirectional character type "WS" in the Unicode specification.
521 * @since 1.4
522 */
523 public static final byte DIRECTIONALITY_WHITESPACE = 12;
524
525 /**
526 * Neutral bidirectional character type "ON" in the Unicode specification.
527 * @since 1.4
528 */
529 public static final byte DIRECTIONALITY_OTHER_NEUTRALS = 13;
530
531 /**
532 * Strong bidirectional character type "LRE" in the Unicode specification.
533 * @since 1.4
534 */
535 public static final byte DIRECTIONALITY_LEFT_TO_RIGHT_EMBEDDING = 14;
536
537 /**
538 * Strong bidirectional character type "LRO" in the Unicode specification.
539 * @since 1.4
540 */
541 public static final byte DIRECTIONALITY_LEFT_TO_RIGHT_OVERRIDE = 15;
542
543 /**
544 * Strong bidirectional character type "RLE" in the Unicode specification.
545 * @since 1.4
546 */
547 public static final byte DIRECTIONALITY_RIGHT_TO_LEFT_EMBEDDING = 16;
548
549 /**
550 * Strong bidirectional character type "RLO" in the Unicode specification.
551 * @since 1.4
552 */
553 public static final byte DIRECTIONALITY_RIGHT_TO_LEFT_OVERRIDE = 17;
554
555 /**
556 * Weak bidirectional character type "PDF" in the Unicode specification.
557 * @since 1.4
558 */
559 public static final byte DIRECTIONALITY_POP_DIRECTIONAL_FORMAT = 18;
560
561 /**
562 * Weak bidirectional character type "LRI" in the Unicode specification.
563 * @since 9
564 */
565 public static final byte DIRECTIONALITY_LEFT_TO_RIGHT_ISOLATE = 19;
566
567 /**
568 * Weak bidirectional character type "RLI" in the Unicode specification.
569 * @since 9
570 */
571 public static final byte DIRECTIONALITY_RIGHT_TO_LEFT_ISOLATE = 20;
572
573 /**
574 * Weak bidirectional character type "FSI" in the Unicode specification.
575 * @since 9
576 */
577 public static final byte DIRECTIONALITY_FIRST_STRONG_ISOLATE = 21;
578
579 /**
580 * Weak bidirectional character type "PDI" in the Unicode specification.
581 * @since 9
582 */
583 public static final byte DIRECTIONALITY_POP_DIRECTIONAL_ISOLATE = 22;
584
585 /**
586 * The minimum value of a
587 * <a href="http://www.unicode.org/glossary/#high_surrogate_code_unit">
588 * Unicode high-surrogate code unit</a>
589 * in the UTF-16 encoding, constant {@code '\u005CuD800'}.
590 * A high-surrogate is also known as a <i>leading-surrogate</i>.
591 *
592 * @since 1.5
593 */
594 public static final char MIN_HIGH_SURROGATE = '\uD800';
595
596 /**
597 * The maximum value of a
598 * <a href="http://www.unicode.org/glossary/#high_surrogate_code_unit">
599 * Unicode high-surrogate code unit</a>
600 * in the UTF-16 encoding, constant {@code '\u005CuDBFF'}.
601 * A high-surrogate is also known as a <i>leading-surrogate</i>.
602 *
603 * @since 1.5
604 */
605 public static final char MAX_HIGH_SURROGATE = '\uDBFF';
606
607 /**
608 * The minimum value of a
609 * <a href="http://www.unicode.org/glossary/#low_surrogate_code_unit">
610 * Unicode low-surrogate code unit</a>
611 * in the UTF-16 encoding, constant {@code '\u005CuDC00'}.
612 * A low-surrogate is also known as a <i>trailing-surrogate</i>.
613 *
614 * @since 1.5
615 */
616 public static final char MIN_LOW_SURROGATE = '\uDC00';
617
618 /**
619 * The maximum value of a
620 * <a href="http://www.unicode.org/glossary/#low_surrogate_code_unit">
621 * Unicode low-surrogate code unit</a>
622 * in the UTF-16 encoding, constant {@code '\u005CuDFFF'}.
623 * A low-surrogate is also known as a <i>trailing-surrogate</i>.
624 *
625 * @since 1.5
626 */
627 public static final char MAX_LOW_SURROGATE = '\uDFFF';
628
629 /**
630 * The minimum value of a Unicode surrogate code unit in the
631 * UTF-16 encoding, constant {@code '\u005CuD800'}.
632 *
633 * @since 1.5
634 */
635 public static final char MIN_SURROGATE = MIN_HIGH_SURROGATE;
636
637 /**
638 * The maximum value of a Unicode surrogate code unit in the
639 * UTF-16 encoding, constant {@code '\u005CuDFFF'}.
640 *
641 * @since 1.5
642 */
643 public static final char MAX_SURROGATE = MAX_LOW_SURROGATE;
644
645 /**
646 * The minimum value of a
647 * <a href="http://www.unicode.org/glossary/#supplementary_code_point">
648 * Unicode supplementary code point</a>, constant {@code U+10000}.
649 *
650 * @since 1.5
651 */
652 public static final int MIN_SUPPLEMENTARY_CODE_POINT = 0x010000;
653
654 /**
655 * The minimum value of a
656 * <a href="http://www.unicode.org/glossary/#code_point">
657 * Unicode code point</a>, constant {@code U+0000}.
658 *
659 * @since 1.5
660 */
661 public static final int MIN_CODE_POINT = 0x000000;
662
663 /**
664 * The maximum value of a
665 * <a href="http://www.unicode.org/glossary/#code_point">
666 * Unicode code point</a>, constant {@code U+10FFFF}.
667 *
668 * @since 1.5
669 */
670 public static final int MAX_CODE_POINT = 0X10FFFF;
671
672 /**
673 * Returns an {@link Optional} containing the nominal descriptor for this
674 * instance.
675 *
676 * @return an {@link Optional} describing the {@linkplain Character} instance
677 * @since 15
678 */
679 @Override
680 public Optional<DynamicConstantDesc<Character>> describeConstable() {
681 return Optional.of(DynamicConstantDesc.ofNamed(BSM_EXPLICIT_CAST, DEFAULT_NAME, CD_char, (int) value));
682 }
683
684 /**
685 * Instances of this class represent particular subsets of the Unicode
686 * character set. The only family of subsets defined in the
687 * {@code Character} class is {@link Character.UnicodeBlock}.
688 * Other portions of the Java API may define other subsets for their
689 * own purposes.
690 *
691 * @since 1.2
692 */
693 public static class Subset {
694
695 private String name;
696
697 /**
698 * Constructs a new {@code Subset} instance.
699 *
700 * @param name The name of this subset
701 * @throws NullPointerException if name is {@code null}
702 */
703 protected Subset(String name) {
704 if (name == null) {
705 throw new NullPointerException("name");
706 }
707 this.name = name;
708 }
709
710 /**
711 * Compares two {@code Subset} objects for equality.
712 * This method returns {@code true} if and only if
713 * {@code this} and the argument refer to the same
714 * object; since this method is {@code final}, this
715 * guarantee holds for all subclasses.
716 */
717 public final boolean equals(Object obj) {
718 return (this == obj);
719 }
720
721 /**
722 * Returns the standard hash code as defined by the
723 * {@link Object#hashCode} method. This method
724 * is {@code final} in order to ensure that the
725 * {@code equals} and {@code hashCode} methods will
726 * be consistent in all subclasses.
727 */
728 public final int hashCode() {
729 return super.hashCode();
730 }
731
732 /**
733 * Returns the name of this subset.
734 */
735 public final String toString() {
736 return name;
737 }
738 }
739
740 // See http://www.unicode.org/Public/UNIDATA/Blocks.txt
741 // for the latest specification of Unicode Blocks.
742
743 /**
744 * A family of character subsets representing the character blocks in the
745 * Unicode specification. Character blocks generally define characters
746 * used for a specific script or purpose. A character is contained by
747 * at most one Unicode block.
748 *
749 * @since 1.2
750 */
751 public static final class UnicodeBlock extends Subset {
752 /**
753 * NUM_ENTITIES should match the total number of UnicodeBlocks.
754 * It should be adjusted whenever the Unicode Character Database
755 * is upgraded.
756 */
757 private static final int NUM_ENTITIES = 759;
758 private static Map<String, UnicodeBlock> map = HashMap.newHashMap(NUM_ENTITIES);
759
760 /**
761 * Creates a UnicodeBlock with the given identifier name.
762 * This name must be the same as the block identifier.
763 */
764 private UnicodeBlock(String idName) {
765 super(idName);
766 map.put(idName, this);
767 }
768
769 /**
770 * Creates a UnicodeBlock with the given identifier name and
771 * alias name.
772 */
773 private UnicodeBlock(String idName, String alias) {
774 this(idName);
775 map.put(alias, this);
776 }
777
778 /**
779 * Creates a UnicodeBlock with the given identifier name and
780 * alias names.
781 */
782 private UnicodeBlock(String idName, String... aliases) {
783 this(idName);
784 for (String alias : aliases)
785 map.put(alias, this);
786 }
787
788 /**
789 * Constant for the "Basic Latin" Unicode character block.
790 * @since 1.2
791 */
792 public static final UnicodeBlock BASIC_LATIN =
793 new UnicodeBlock("BASIC_LATIN",
794 "BASIC LATIN",
795 "BASICLATIN");
796
797 /**
798 * Constant for the "Latin-1 Supplement" Unicode character block.
799 * @since 1.2
800 */
801 public static final UnicodeBlock LATIN_1_SUPPLEMENT =
802 new UnicodeBlock("LATIN_1_SUPPLEMENT",
803 "LATIN-1 SUPPLEMENT",
804 "LATIN-1SUPPLEMENT");
805
806 /**
807 * Constant for the "Latin Extended-A" Unicode character block.
808 * @since 1.2
809 */
810 public static final UnicodeBlock LATIN_EXTENDED_A =
811 new UnicodeBlock("LATIN_EXTENDED_A",
812 "LATIN EXTENDED-A",
813 "LATINEXTENDED-A");
814
815 /**
816 * Constant for the "Latin Extended-B" Unicode character block.
817 * @since 1.2
818 */
819 public static final UnicodeBlock LATIN_EXTENDED_B =
820 new UnicodeBlock("LATIN_EXTENDED_B",
821 "LATIN EXTENDED-B",
822 "LATINEXTENDED-B");
823
824 /**
825 * Constant for the "IPA Extensions" Unicode character block.
826 * @since 1.2
827 */
828 public static final UnicodeBlock IPA_EXTENSIONS =
829 new UnicodeBlock("IPA_EXTENSIONS",
830 "IPA EXTENSIONS",
831 "IPAEXTENSIONS");
832
833 /**
834 * Constant for the "Spacing Modifier Letters" Unicode character block.
835 * @since 1.2
836 */
837 public static final UnicodeBlock SPACING_MODIFIER_LETTERS =
838 new UnicodeBlock("SPACING_MODIFIER_LETTERS",
839 "SPACING MODIFIER LETTERS",
840 "SPACINGMODIFIERLETTERS");
841
842 /**
843 * Constant for the "Combining Diacritical Marks" Unicode character block.
844 * @since 1.2
845 */
846 public static final UnicodeBlock COMBINING_DIACRITICAL_MARKS =
847 new UnicodeBlock("COMBINING_DIACRITICAL_MARKS",
848 "COMBINING DIACRITICAL MARKS",
849 "COMBININGDIACRITICALMARKS");
850
851 /**
852 * Constant for the "Greek and Coptic" Unicode character block.
853 * <p>
854 * This block was previously known as the "Greek" block.
855 *
856 * @since 1.2
857 */
858 public static final UnicodeBlock GREEK =
859 new UnicodeBlock("GREEK",
860 "GREEK AND COPTIC",
861 "GREEKANDCOPTIC");
862
863 /**
864 * Constant for the "Cyrillic" Unicode character block.
865 * @since 1.2
866 */
867 public static final UnicodeBlock CYRILLIC =
868 new UnicodeBlock("CYRILLIC");
869
870 /**
871 * Constant for the "Armenian" Unicode character block.
872 * @since 1.2
873 */
874 public static final UnicodeBlock ARMENIAN =
875 new UnicodeBlock("ARMENIAN");
876
877 /**
878 * Constant for the "Hebrew" Unicode character block.
879 * @since 1.2
880 */
881 public static final UnicodeBlock HEBREW =
882 new UnicodeBlock("HEBREW");
883
884 /**
885 * Constant for the "Arabic" Unicode character block.
886 * @since 1.2
887 */
888 public static final UnicodeBlock ARABIC =
889 new UnicodeBlock("ARABIC");
890
891 /**
892 * Constant for the "Devanagari" Unicode character block.
893 * @since 1.2
894 */
895 public static final UnicodeBlock DEVANAGARI =
896 new UnicodeBlock("DEVANAGARI");
897
898 /**
899 * Constant for the "Bengali" Unicode character block.
900 * @since 1.2
901 */
902 public static final UnicodeBlock BENGALI =
903 new UnicodeBlock("BENGALI");
904
905 /**
906 * Constant for the "Gurmukhi" Unicode character block.
907 * @since 1.2
908 */
909 public static final UnicodeBlock GURMUKHI =
910 new UnicodeBlock("GURMUKHI");
911
912 /**
913 * Constant for the "Gujarati" Unicode character block.
914 * @since 1.2
915 */
916 public static final UnicodeBlock GUJARATI =
917 new UnicodeBlock("GUJARATI");
918
919 /**
920 * Constant for the "Oriya" Unicode character block.
921 * @since 1.2
922 */
923 public static final UnicodeBlock ORIYA =
924 new UnicodeBlock("ORIYA");
925
926 /**
927 * Constant for the "Tamil" Unicode character block.
928 * @since 1.2
929 */
930 public static final UnicodeBlock TAMIL =
931 new UnicodeBlock("TAMIL");
932
933 /**
934 * Constant for the "Telugu" Unicode character block.
935 * @since 1.2
936 */
937 public static final UnicodeBlock TELUGU =
938 new UnicodeBlock("TELUGU");
939
940 /**
941 * Constant for the "Kannada" Unicode character block.
942 * @since 1.2
943 */
944 public static final UnicodeBlock KANNADA =
945 new UnicodeBlock("KANNADA");
946
947 /**
948 * Constant for the "Malayalam" Unicode character block.
949 * @since 1.2
950 */
951 public static final UnicodeBlock MALAYALAM =
952 new UnicodeBlock("MALAYALAM");
953
954 /**
955 * Constant for the "Thai" Unicode character block.
956 * @since 1.2
957 */
958 public static final UnicodeBlock THAI =
959 new UnicodeBlock("THAI");
960
961 /**
962 * Constant for the "Lao" Unicode character block.
963 * @since 1.2
964 */
965 public static final UnicodeBlock LAO =
966 new UnicodeBlock("LAO");
967
968 /**
969 * Constant for the "Tibetan" Unicode character block.
970 * @since 1.2
971 */
972 public static final UnicodeBlock TIBETAN =
973 new UnicodeBlock("TIBETAN");
974
975 /**
976 * Constant for the "Georgian" Unicode character block.
977 * @since 1.2
978 */
979 public static final UnicodeBlock GEORGIAN =
980 new UnicodeBlock("GEORGIAN");
981
982 /**
983 * Constant for the "Hangul Jamo" Unicode character block.
984 * @since 1.2
985 */
986 public static final UnicodeBlock HANGUL_JAMO =
987 new UnicodeBlock("HANGUL_JAMO",
988 "HANGUL JAMO",
989 "HANGULJAMO");
990
991 /**
992 * Constant for the "Latin Extended Additional" Unicode character block.
993 * @since 1.2
994 */
995 public static final UnicodeBlock LATIN_EXTENDED_ADDITIONAL =
996 new UnicodeBlock("LATIN_EXTENDED_ADDITIONAL",
997 "LATIN EXTENDED ADDITIONAL",
998 "LATINEXTENDEDADDITIONAL");
999
1000 /**
1001 * Constant for the "Greek Extended" Unicode character block.
1002 * @since 1.2
1003 */
1004 public static final UnicodeBlock GREEK_EXTENDED =
1005 new UnicodeBlock("GREEK_EXTENDED",
1006 "GREEK EXTENDED",
1007 "GREEKEXTENDED");
1008
1009 /**
1010 * Constant for the "General Punctuation" Unicode character block.
1011 * @since 1.2
1012 */
1013 public static final UnicodeBlock GENERAL_PUNCTUATION =
1014 new UnicodeBlock("GENERAL_PUNCTUATION",
1015 "GENERAL PUNCTUATION",
1016 "GENERALPUNCTUATION");
1017
1018 /**
1019 * Constant for the "Superscripts and Subscripts" Unicode character
1020 * block.
1021 * @since 1.2
1022 */
1023 public static final UnicodeBlock SUPERSCRIPTS_AND_SUBSCRIPTS =
1024 new UnicodeBlock("SUPERSCRIPTS_AND_SUBSCRIPTS",
1025 "SUPERSCRIPTS AND SUBSCRIPTS",
1026 "SUPERSCRIPTSANDSUBSCRIPTS");
1027
1028 /**
1029 * Constant for the "Currency Symbols" Unicode character block.
1030 * @since 1.2
1031 */
1032 public static final UnicodeBlock CURRENCY_SYMBOLS =
1033 new UnicodeBlock("CURRENCY_SYMBOLS",
1034 "CURRENCY SYMBOLS",
1035 "CURRENCYSYMBOLS");
1036
1037 /**
1038 * Constant for the "Combining Diacritical Marks for Symbols" Unicode
1039 * character block.
1040 * <p>
1041 * This block was previously known as "Combining Marks for Symbols".
1042 * @since 1.2
1043 */
1044 public static final UnicodeBlock COMBINING_MARKS_FOR_SYMBOLS =
1045 new UnicodeBlock("COMBINING_MARKS_FOR_SYMBOLS",
1046 "COMBINING DIACRITICAL MARKS FOR SYMBOLS",
1047 "COMBININGDIACRITICALMARKSFORSYMBOLS",
1048 "COMBINING MARKS FOR SYMBOLS",
1049 "COMBININGMARKSFORSYMBOLS");
1050
1051 /**
1052 * Constant for the "Letterlike Symbols" Unicode character block.
1053 * @since 1.2
1054 */
1055 public static final UnicodeBlock LETTERLIKE_SYMBOLS =
1056 new UnicodeBlock("LETTERLIKE_SYMBOLS",
1057 "LETTERLIKE SYMBOLS",
1058 "LETTERLIKESYMBOLS");
1059
1060 /**
1061 * Constant for the "Number Forms" Unicode character block.
1062 * @since 1.2
1063 */
1064 public static final UnicodeBlock NUMBER_FORMS =
1065 new UnicodeBlock("NUMBER_FORMS",
1066 "NUMBER FORMS",
1067 "NUMBERFORMS");
1068
1069 /**
1070 * Constant for the "Arrows" Unicode character block.
1071 * @since 1.2
1072 */
1073 public static final UnicodeBlock ARROWS =
1074 new UnicodeBlock("ARROWS");
1075
1076 /**
1077 * Constant for the "Mathematical Operators" Unicode character block.
1078 * @since 1.2
1079 */
1080 public static final UnicodeBlock MATHEMATICAL_OPERATORS =
1081 new UnicodeBlock("MATHEMATICAL_OPERATORS",
1082 "MATHEMATICAL OPERATORS",
1083 "MATHEMATICALOPERATORS");
1084
1085 /**
1086 * Constant for the "Miscellaneous Technical" Unicode character block.
1087 * @since 1.2
1088 */
1089 public static final UnicodeBlock MISCELLANEOUS_TECHNICAL =
1090 new UnicodeBlock("MISCELLANEOUS_TECHNICAL",
1091 "MISCELLANEOUS TECHNICAL",
1092 "MISCELLANEOUSTECHNICAL");
1093
1094 /**
1095 * Constant for the "Control Pictures" Unicode character block.
1096 * @since 1.2
1097 */
1098 public static final UnicodeBlock CONTROL_PICTURES =
1099 new UnicodeBlock("CONTROL_PICTURES",
1100 "CONTROL PICTURES",
1101 "CONTROLPICTURES");
1102
1103 /**
1104 * Constant for the "Optical Character Recognition" Unicode character block.
1105 * @since 1.2
1106 */
1107 public static final UnicodeBlock OPTICAL_CHARACTER_RECOGNITION =
1108 new UnicodeBlock("OPTICAL_CHARACTER_RECOGNITION",
1109 "OPTICAL CHARACTER RECOGNITION",
1110 "OPTICALCHARACTERRECOGNITION");
1111
1112 /**
1113 * Constant for the "Enclosed Alphanumerics" Unicode character block.
1114 * @since 1.2
1115 */
1116 public static final UnicodeBlock ENCLOSED_ALPHANUMERICS =
1117 new UnicodeBlock("ENCLOSED_ALPHANUMERICS",
1118 "ENCLOSED ALPHANUMERICS",
1119 "ENCLOSEDALPHANUMERICS");
1120
1121 /**
1122 * Constant for the "Box Drawing" Unicode character block.
1123 * @since 1.2
1124 */
1125 public static final UnicodeBlock BOX_DRAWING =
1126 new UnicodeBlock("BOX_DRAWING",
1127 "BOX DRAWING",
1128 "BOXDRAWING");
1129
1130 /**
1131 * Constant for the "Block Elements" Unicode character block.
1132 * @since 1.2
1133 */
1134 public static final UnicodeBlock BLOCK_ELEMENTS =
1135 new UnicodeBlock("BLOCK_ELEMENTS",
1136 "BLOCK ELEMENTS",
1137 "BLOCKELEMENTS");
1138
1139 /**
1140 * Constant for the "Geometric Shapes" Unicode character block.
1141 * @since 1.2
1142 */
1143 public static final UnicodeBlock GEOMETRIC_SHAPES =
1144 new UnicodeBlock("GEOMETRIC_SHAPES",
1145 "GEOMETRIC SHAPES",
1146 "GEOMETRICSHAPES");
1147
1148 /**
1149 * Constant for the "Miscellaneous Symbols" Unicode character block.
1150 * @since 1.2
1151 */
1152 public static final UnicodeBlock MISCELLANEOUS_SYMBOLS =
1153 new UnicodeBlock("MISCELLANEOUS_SYMBOLS",
1154 "MISCELLANEOUS SYMBOLS",
1155 "MISCELLANEOUSSYMBOLS");
1156
1157 /**
1158 * Constant for the "Dingbats" Unicode character block.
1159 * @since 1.2
1160 */
1161 public static final UnicodeBlock DINGBATS =
1162 new UnicodeBlock("DINGBATS");
1163
1164 /**
1165 * Constant for the "CJK Symbols and Punctuation" Unicode character block.
1166 * @since 1.2
1167 */
1168 public static final UnicodeBlock CJK_SYMBOLS_AND_PUNCTUATION =
1169 new UnicodeBlock("CJK_SYMBOLS_AND_PUNCTUATION",
1170 "CJK SYMBOLS AND PUNCTUATION",
1171 "CJKSYMBOLSANDPUNCTUATION");
1172
1173 /**
1174 * Constant for the "Hiragana" Unicode character block.
1175 * @since 1.2
1176 */
1177 public static final UnicodeBlock HIRAGANA =
1178 new UnicodeBlock("HIRAGANA");
1179
1180 /**
1181 * Constant for the "Katakana" Unicode character block.
1182 * @since 1.2
1183 */
1184 public static final UnicodeBlock KATAKANA =
1185 new UnicodeBlock("KATAKANA");
1186
1187 /**
1188 * Constant for the "Bopomofo" Unicode character block.
1189 * @since 1.2
1190 */
1191 public static final UnicodeBlock BOPOMOFO =
1192 new UnicodeBlock("BOPOMOFO");
1193
1194 /**
1195 * Constant for the "Hangul Compatibility Jamo" Unicode character block.
1196 * @since 1.2
1197 */
1198 public static final UnicodeBlock HANGUL_COMPATIBILITY_JAMO =
1199 new UnicodeBlock("HANGUL_COMPATIBILITY_JAMO",
1200 "HANGUL COMPATIBILITY JAMO",
1201 "HANGULCOMPATIBILITYJAMO");
1202
1203 /**
1204 * Constant for the "Kanbun" Unicode character block.
1205 * @since 1.2
1206 */
1207 public static final UnicodeBlock KANBUN =
1208 new UnicodeBlock("KANBUN");
1209
1210 /**
1211 * Constant for the "Enclosed CJK Letters and Months" Unicode character block.
1212 * @since 1.2
1213 */
1214 public static final UnicodeBlock ENCLOSED_CJK_LETTERS_AND_MONTHS =
1215 new UnicodeBlock("ENCLOSED_CJK_LETTERS_AND_MONTHS",
1216 "ENCLOSED CJK LETTERS AND MONTHS",
1217 "ENCLOSEDCJKLETTERSANDMONTHS");
1218
1219 /**
1220 * Constant for the "CJK Compatibility" Unicode character block.
1221 * @since 1.2
1222 */
1223 public static final UnicodeBlock CJK_COMPATIBILITY =
1224 new UnicodeBlock("CJK_COMPATIBILITY",
1225 "CJK COMPATIBILITY",
1226 "CJKCOMPATIBILITY");
1227
1228 /**
1229 * Constant for the "CJK Unified Ideographs" Unicode character block.
1230 * @since 1.2
1231 */
1232 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS =
1233 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS",
1234 "CJK UNIFIED IDEOGRAPHS",
1235 "CJKUNIFIEDIDEOGRAPHS");
1236
1237 /**
1238 * Constant for the "Hangul Syllables" Unicode character block.
1239 * @since 1.2
1240 */
1241 public static final UnicodeBlock HANGUL_SYLLABLES =
1242 new UnicodeBlock("HANGUL_SYLLABLES",
1243 "HANGUL SYLLABLES",
1244 "HANGULSYLLABLES");
1245
1246 /**
1247 * Constant for the "Private Use Area" Unicode character block.
1248 * @since 1.2
1249 */
1250 public static final UnicodeBlock PRIVATE_USE_AREA =
1251 new UnicodeBlock("PRIVATE_USE_AREA",
1252 "PRIVATE USE AREA",
1253 "PRIVATEUSEAREA");
1254
1255 /**
1256 * Constant for the "CJK Compatibility Ideographs" Unicode character
1257 * block.
1258 * @since 1.2
1259 */
1260 public static final UnicodeBlock CJK_COMPATIBILITY_IDEOGRAPHS =
1261 new UnicodeBlock("CJK_COMPATIBILITY_IDEOGRAPHS",
1262 "CJK COMPATIBILITY IDEOGRAPHS",
1263 "CJKCOMPATIBILITYIDEOGRAPHS");
1264
1265 /**
1266 * Constant for the "Alphabetic Presentation Forms" Unicode character block.
1267 * @since 1.2
1268 */
1269 public static final UnicodeBlock ALPHABETIC_PRESENTATION_FORMS =
1270 new UnicodeBlock("ALPHABETIC_PRESENTATION_FORMS",
1271 "ALPHABETIC PRESENTATION FORMS",
1272 "ALPHABETICPRESENTATIONFORMS");
1273
1274 /**
1275 * Constant for the "Arabic Presentation Forms-A" Unicode character
1276 * block.
1277 * @since 1.2
1278 */
1279 public static final UnicodeBlock ARABIC_PRESENTATION_FORMS_A =
1280 new UnicodeBlock("ARABIC_PRESENTATION_FORMS_A",
1281 "ARABIC PRESENTATION FORMS-A",
1282 "ARABICPRESENTATIONFORMS-A");
1283
1284 /**
1285 * Constant for the "Combining Half Marks" Unicode character block.
1286 * @since 1.2
1287 */
1288 public static final UnicodeBlock COMBINING_HALF_MARKS =
1289 new UnicodeBlock("COMBINING_HALF_MARKS",
1290 "COMBINING HALF MARKS",
1291 "COMBININGHALFMARKS");
1292
1293 /**
1294 * Constant for the "CJK Compatibility Forms" Unicode character block.
1295 * @since 1.2
1296 */
1297 public static final UnicodeBlock CJK_COMPATIBILITY_FORMS =
1298 new UnicodeBlock("CJK_COMPATIBILITY_FORMS",
1299 "CJK COMPATIBILITY FORMS",
1300 "CJKCOMPATIBILITYFORMS");
1301
1302 /**
1303 * Constant for the "Small Form Variants" Unicode character block.
1304 * @since 1.2
1305 */
1306 public static final UnicodeBlock SMALL_FORM_VARIANTS =
1307 new UnicodeBlock("SMALL_FORM_VARIANTS",
1308 "SMALL FORM VARIANTS",
1309 "SMALLFORMVARIANTS");
1310
1311 /**
1312 * Constant for the "Arabic Presentation Forms-B" Unicode character block.
1313 * @since 1.2
1314 */
1315 public static final UnicodeBlock ARABIC_PRESENTATION_FORMS_B =
1316 new UnicodeBlock("ARABIC_PRESENTATION_FORMS_B",
1317 "ARABIC PRESENTATION FORMS-B",
1318 "ARABICPRESENTATIONFORMS-B");
1319
1320 /**
1321 * Constant for the "Halfwidth and Fullwidth Forms" Unicode character
1322 * block.
1323 * @since 1.2
1324 */
1325 public static final UnicodeBlock HALFWIDTH_AND_FULLWIDTH_FORMS =
1326 new UnicodeBlock("HALFWIDTH_AND_FULLWIDTH_FORMS",
1327 "HALFWIDTH AND FULLWIDTH FORMS",
1328 "HALFWIDTHANDFULLWIDTHFORMS");
1329
1330 /**
1331 * Constant for the "Specials" Unicode character block.
1332 * @since 1.2
1333 */
1334 public static final UnicodeBlock SPECIALS =
1335 new UnicodeBlock("SPECIALS");
1336
1337 /**
1338 * @deprecated
1339 * Instead of {@code SURROGATES_AREA}, use {@link #HIGH_SURROGATES},
1340 * {@link #HIGH_PRIVATE_USE_SURROGATES}, and {@link #LOW_SURROGATES}.
1341 * These constants match the block definitions of the Unicode Standard.
1342 * The {@link #of(char)} and {@link #of(int)} methods return the
1343 * standard constants.
1344 */
1345 @Deprecated(since="1.5")
1346 public static final UnicodeBlock SURROGATES_AREA =
1347 new UnicodeBlock("SURROGATES_AREA");
1348
1349 /**
1350 * Constant for the "Syriac" Unicode character block.
1351 * @since 1.4
1352 */
1353 public static final UnicodeBlock SYRIAC =
1354 new UnicodeBlock("SYRIAC");
1355
1356 /**
1357 * Constant for the "Thaana" Unicode character block.
1358 * @since 1.4
1359 */
1360 public static final UnicodeBlock THAANA =
1361 new UnicodeBlock("THAANA");
1362
1363 /**
1364 * Constant for the "Sinhala" Unicode character block.
1365 * @since 1.4
1366 */
1367 public static final UnicodeBlock SINHALA =
1368 new UnicodeBlock("SINHALA");
1369
1370 /**
1371 * Constant for the "Myanmar" Unicode character block.
1372 * @since 1.4
1373 */
1374 public static final UnicodeBlock MYANMAR =
1375 new UnicodeBlock("MYANMAR");
1376
1377 /**
1378 * Constant for the "Ethiopic" Unicode character block.
1379 * @since 1.4
1380 */
1381 public static final UnicodeBlock ETHIOPIC =
1382 new UnicodeBlock("ETHIOPIC");
1383
1384 /**
1385 * Constant for the "Cherokee" Unicode character block.
1386 * @since 1.4
1387 */
1388 public static final UnicodeBlock CHEROKEE =
1389 new UnicodeBlock("CHEROKEE");
1390
1391 /**
1392 * Constant for the "Unified Canadian Aboriginal Syllabics" Unicode character block.
1393 * @since 1.4
1394 */
1395 public static final UnicodeBlock UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS =
1396 new UnicodeBlock("UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS",
1397 "UNIFIED CANADIAN ABORIGINAL SYLLABICS",
1398 "UNIFIEDCANADIANABORIGINALSYLLABICS");
1399
1400 /**
1401 * Constant for the "Ogham" Unicode character block.
1402 * @since 1.4
1403 */
1404 public static final UnicodeBlock OGHAM =
1405 new UnicodeBlock("OGHAM");
1406
1407 /**
1408 * Constant for the "Runic" Unicode character block.
1409 * @since 1.4
1410 */
1411 public static final UnicodeBlock RUNIC =
1412 new UnicodeBlock("RUNIC");
1413
1414 /**
1415 * Constant for the "Khmer" Unicode character block.
1416 * @since 1.4
1417 */
1418 public static final UnicodeBlock KHMER =
1419 new UnicodeBlock("KHMER");
1420
1421 /**
1422 * Constant for the "Mongolian" Unicode character block.
1423 * @since 1.4
1424 */
1425 public static final UnicodeBlock MONGOLIAN =
1426 new UnicodeBlock("MONGOLIAN");
1427
1428 /**
1429 * Constant for the "Braille Patterns" Unicode character block.
1430 * @since 1.4
1431 */
1432 public static final UnicodeBlock BRAILLE_PATTERNS =
1433 new UnicodeBlock("BRAILLE_PATTERNS",
1434 "BRAILLE PATTERNS",
1435 "BRAILLEPATTERNS");
1436
1437 /**
1438 * Constant for the "CJK Radicals Supplement" Unicode character block.
1439 * @since 1.4
1440 */
1441 public static final UnicodeBlock CJK_RADICALS_SUPPLEMENT =
1442 new UnicodeBlock("CJK_RADICALS_SUPPLEMENT",
1443 "CJK RADICALS SUPPLEMENT",
1444 "CJKRADICALSSUPPLEMENT");
1445
1446 /**
1447 * Constant for the "Kangxi Radicals" Unicode character block.
1448 * @since 1.4
1449 */
1450 public static final UnicodeBlock KANGXI_RADICALS =
1451 new UnicodeBlock("KANGXI_RADICALS",
1452 "KANGXI RADICALS",
1453 "KANGXIRADICALS");
1454
1455 /**
1456 * Constant for the "Ideographic Description Characters" Unicode character block.
1457 * @since 1.4
1458 */
1459 public static final UnicodeBlock IDEOGRAPHIC_DESCRIPTION_CHARACTERS =
1460 new UnicodeBlock("IDEOGRAPHIC_DESCRIPTION_CHARACTERS",
1461 "IDEOGRAPHIC DESCRIPTION CHARACTERS",
1462 "IDEOGRAPHICDESCRIPTIONCHARACTERS");
1463
1464 /**
1465 * Constant for the "Bopomofo Extended" Unicode character block.
1466 * @since 1.4
1467 */
1468 public static final UnicodeBlock BOPOMOFO_EXTENDED =
1469 new UnicodeBlock("BOPOMOFO_EXTENDED",
1470 "BOPOMOFO EXTENDED",
1471 "BOPOMOFOEXTENDED");
1472
1473 /**
1474 * Constant for the "CJK Unified Ideographs Extension A" Unicode character block.
1475 * @since 1.4
1476 */
1477 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A =
1478 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A",
1479 "CJK UNIFIED IDEOGRAPHS EXTENSION A",
1480 "CJKUNIFIEDIDEOGRAPHSEXTENSIONA");
1481
1482 /**
1483 * Constant for the "Yi Syllables" Unicode character block.
1484 * @since 1.4
1485 */
1486 public static final UnicodeBlock YI_SYLLABLES =
1487 new UnicodeBlock("YI_SYLLABLES",
1488 "YI SYLLABLES",
1489 "YISYLLABLES");
1490
1491 /**
1492 * Constant for the "Yi Radicals" Unicode character block.
1493 * @since 1.4
1494 */
1495 public static final UnicodeBlock YI_RADICALS =
1496 new UnicodeBlock("YI_RADICALS",
1497 "YI RADICALS",
1498 "YIRADICALS");
1499
1500 /**
1501 * Constant for the "Cyrillic Supplement" Unicode character block.
1502 * This block was previously known as the "Cyrillic Supplementary" block.
1503 * @since 1.5
1504 */
1505 public static final UnicodeBlock CYRILLIC_SUPPLEMENTARY =
1506 new UnicodeBlock("CYRILLIC_SUPPLEMENTARY",
1507 "CYRILLIC SUPPLEMENTARY",
1508 "CYRILLICSUPPLEMENTARY",
1509 "CYRILLIC SUPPLEMENT",
1510 "CYRILLICSUPPLEMENT");
1511
1512 /**
1513 * Constant for the "Tagalog" Unicode character block.
1514 * @since 1.5
1515 */
1516 public static final UnicodeBlock TAGALOG =
1517 new UnicodeBlock("TAGALOG");
1518
1519 /**
1520 * Constant for the "Hanunoo" Unicode character block.
1521 * @since 1.5
1522 */
1523 public static final UnicodeBlock HANUNOO =
1524 new UnicodeBlock("HANUNOO");
1525
1526 /**
1527 * Constant for the "Buhid" Unicode character block.
1528 * @since 1.5
1529 */
1530 public static final UnicodeBlock BUHID =
1531 new UnicodeBlock("BUHID");
1532
1533 /**
1534 * Constant for the "Tagbanwa" Unicode character block.
1535 * @since 1.5
1536 */
1537 public static final UnicodeBlock TAGBANWA =
1538 new UnicodeBlock("TAGBANWA");
1539
1540 /**
1541 * Constant for the "Limbu" Unicode character block.
1542 * @since 1.5
1543 */
1544 public static final UnicodeBlock LIMBU =
1545 new UnicodeBlock("LIMBU");
1546
1547 /**
1548 * Constant for the "Tai Le" Unicode character block.
1549 * @since 1.5
1550 */
1551 public static final UnicodeBlock TAI_LE =
1552 new UnicodeBlock("TAI_LE",
1553 "TAI LE",
1554 "TAILE");
1555
1556 /**
1557 * Constant for the "Khmer Symbols" Unicode character block.
1558 * @since 1.5
1559 */
1560 public static final UnicodeBlock KHMER_SYMBOLS =
1561 new UnicodeBlock("KHMER_SYMBOLS",
1562 "KHMER SYMBOLS",
1563 "KHMERSYMBOLS");
1564
1565 /**
1566 * Constant for the "Phonetic Extensions" Unicode character block.
1567 * @since 1.5
1568 */
1569 public static final UnicodeBlock PHONETIC_EXTENSIONS =
1570 new UnicodeBlock("PHONETIC_EXTENSIONS",
1571 "PHONETIC EXTENSIONS",
1572 "PHONETICEXTENSIONS");
1573
1574 /**
1575 * Constant for the "Miscellaneous Mathematical Symbols-A" Unicode character block.
1576 * @since 1.5
1577 */
1578 public static final UnicodeBlock MISCELLANEOUS_MATHEMATICAL_SYMBOLS_A =
1579 new UnicodeBlock("MISCELLANEOUS_MATHEMATICAL_SYMBOLS_A",
1580 "MISCELLANEOUS MATHEMATICAL SYMBOLS-A",
1581 "MISCELLANEOUSMATHEMATICALSYMBOLS-A");
1582
1583 /**
1584 * Constant for the "Supplemental Arrows-A" Unicode character block.
1585 * @since 1.5
1586 */
1587 public static final UnicodeBlock SUPPLEMENTAL_ARROWS_A =
1588 new UnicodeBlock("SUPPLEMENTAL_ARROWS_A",
1589 "SUPPLEMENTAL ARROWS-A",
1590 "SUPPLEMENTALARROWS-A");
1591
1592 /**
1593 * Constant for the "Supplemental Arrows-B" Unicode character block.
1594 * @since 1.5
1595 */
1596 public static final UnicodeBlock SUPPLEMENTAL_ARROWS_B =
1597 new UnicodeBlock("SUPPLEMENTAL_ARROWS_B",
1598 "SUPPLEMENTAL ARROWS-B",
1599 "SUPPLEMENTALARROWS-B");
1600
1601 /**
1602 * Constant for the "Miscellaneous Mathematical Symbols-B" Unicode
1603 * character block.
1604 * @since 1.5
1605 */
1606 public static final UnicodeBlock MISCELLANEOUS_MATHEMATICAL_SYMBOLS_B =
1607 new UnicodeBlock("MISCELLANEOUS_MATHEMATICAL_SYMBOLS_B",
1608 "MISCELLANEOUS MATHEMATICAL SYMBOLS-B",
1609 "MISCELLANEOUSMATHEMATICALSYMBOLS-B");
1610
1611 /**
1612 * Constant for the "Supplemental Mathematical Operators" Unicode
1613 * character block.
1614 * @since 1.5
1615 */
1616 public static final UnicodeBlock SUPPLEMENTAL_MATHEMATICAL_OPERATORS =
1617 new UnicodeBlock("SUPPLEMENTAL_MATHEMATICAL_OPERATORS",
1618 "SUPPLEMENTAL MATHEMATICAL OPERATORS",
1619 "SUPPLEMENTALMATHEMATICALOPERATORS");
1620
1621 /**
1622 * Constant for the "Miscellaneous Symbols and Arrows" Unicode character
1623 * block.
1624 * @since 1.5
1625 */
1626 public static final UnicodeBlock MISCELLANEOUS_SYMBOLS_AND_ARROWS =
1627 new UnicodeBlock("MISCELLANEOUS_SYMBOLS_AND_ARROWS",
1628 "MISCELLANEOUS SYMBOLS AND ARROWS",
1629 "MISCELLANEOUSSYMBOLSANDARROWS");
1630
1631 /**
1632 * Constant for the "Katakana Phonetic Extensions" Unicode character
1633 * block.
1634 * @since 1.5
1635 */
1636 public static final UnicodeBlock KATAKANA_PHONETIC_EXTENSIONS =
1637 new UnicodeBlock("KATAKANA_PHONETIC_EXTENSIONS",
1638 "KATAKANA PHONETIC EXTENSIONS",
1639 "KATAKANAPHONETICEXTENSIONS");
1640
1641 /**
1642 * Constant for the "Yijing Hexagram Symbols" Unicode character block.
1643 * @since 1.5
1644 */
1645 public static final UnicodeBlock YIJING_HEXAGRAM_SYMBOLS =
1646 new UnicodeBlock("YIJING_HEXAGRAM_SYMBOLS",
1647 "YIJING HEXAGRAM SYMBOLS",
1648 "YIJINGHEXAGRAMSYMBOLS");
1649
1650 /**
1651 * Constant for the "Variation Selectors" Unicode character block.
1652 * @since 1.5
1653 */
1654 public static final UnicodeBlock VARIATION_SELECTORS =
1655 new UnicodeBlock("VARIATION_SELECTORS",
1656 "VARIATION SELECTORS",
1657 "VARIATIONSELECTORS");
1658
1659 /**
1660 * Constant for the "Linear B Syllabary" Unicode character block.
1661 * @since 1.5
1662 */
1663 public static final UnicodeBlock LINEAR_B_SYLLABARY =
1664 new UnicodeBlock("LINEAR_B_SYLLABARY",
1665 "LINEAR B SYLLABARY",
1666 "LINEARBSYLLABARY");
1667
1668 /**
1669 * Constant for the "Linear B Ideograms" Unicode character block.
1670 * @since 1.5
1671 */
1672 public static final UnicodeBlock LINEAR_B_IDEOGRAMS =
1673 new UnicodeBlock("LINEAR_B_IDEOGRAMS",
1674 "LINEAR B IDEOGRAMS",
1675 "LINEARBIDEOGRAMS");
1676
1677 /**
1678 * Constant for the "Aegean Numbers" Unicode character block.
1679 * @since 1.5
1680 */
1681 public static final UnicodeBlock AEGEAN_NUMBERS =
1682 new UnicodeBlock("AEGEAN_NUMBERS",
1683 "AEGEAN NUMBERS",
1684 "AEGEANNUMBERS");
1685
1686 /**
1687 * Constant for the "Old Italic" Unicode character block.
1688 * @since 1.5
1689 */
1690 public static final UnicodeBlock OLD_ITALIC =
1691 new UnicodeBlock("OLD_ITALIC",
1692 "OLD ITALIC",
1693 "OLDITALIC");
1694
1695 /**
1696 * Constant for the "Gothic" Unicode character block.
1697 * @since 1.5
1698 */
1699 public static final UnicodeBlock GOTHIC =
1700 new UnicodeBlock("GOTHIC");
1701
1702 /**
1703 * Constant for the "Ugaritic" Unicode character block.
1704 * @since 1.5
1705 */
1706 public static final UnicodeBlock UGARITIC =
1707 new UnicodeBlock("UGARITIC");
1708
1709 /**
1710 * Constant for the "Deseret" Unicode character block.
1711 * @since 1.5
1712 */
1713 public static final UnicodeBlock DESERET =
1714 new UnicodeBlock("DESERET");
1715
1716 /**
1717 * Constant for the "Shavian" Unicode character block.
1718 * @since 1.5
1719 */
1720 public static final UnicodeBlock SHAVIAN =
1721 new UnicodeBlock("SHAVIAN");
1722
1723 /**
1724 * Constant for the "Osmanya" Unicode character block.
1725 * @since 1.5
1726 */
1727 public static final UnicodeBlock OSMANYA =
1728 new UnicodeBlock("OSMANYA");
1729
1730 /**
1731 * Constant for the "Cypriot Syllabary" Unicode character block.
1732 * @since 1.5
1733 */
1734 public static final UnicodeBlock CYPRIOT_SYLLABARY =
1735 new UnicodeBlock("CYPRIOT_SYLLABARY",
1736 "CYPRIOT SYLLABARY",
1737 "CYPRIOTSYLLABARY");
1738
1739 /**
1740 * Constant for the "Byzantine Musical Symbols" Unicode character block.
1741 * @since 1.5
1742 */
1743 public static final UnicodeBlock BYZANTINE_MUSICAL_SYMBOLS =
1744 new UnicodeBlock("BYZANTINE_MUSICAL_SYMBOLS",
1745 "BYZANTINE MUSICAL SYMBOLS",
1746 "BYZANTINEMUSICALSYMBOLS");
1747
1748 /**
1749 * Constant for the "Musical Symbols" Unicode character block.
1750 * @since 1.5
1751 */
1752 public static final UnicodeBlock MUSICAL_SYMBOLS =
1753 new UnicodeBlock("MUSICAL_SYMBOLS",
1754 "MUSICAL SYMBOLS",
1755 "MUSICALSYMBOLS");
1756
1757 /**
1758 * Constant for the "Tai Xuan Jing Symbols" Unicode character block.
1759 * @since 1.5
1760 */
1761 public static final UnicodeBlock TAI_XUAN_JING_SYMBOLS =
1762 new UnicodeBlock("TAI_XUAN_JING_SYMBOLS",
1763 "TAI XUAN JING SYMBOLS",
1764 "TAIXUANJINGSYMBOLS");
1765
1766 /**
1767 * Constant for the "Mathematical Alphanumeric Symbols" Unicode
1768 * character block.
1769 * @since 1.5
1770 */
1771 public static final UnicodeBlock MATHEMATICAL_ALPHANUMERIC_SYMBOLS =
1772 new UnicodeBlock("MATHEMATICAL_ALPHANUMERIC_SYMBOLS",
1773 "MATHEMATICAL ALPHANUMERIC SYMBOLS",
1774 "MATHEMATICALALPHANUMERICSYMBOLS");
1775
1776 /**
1777 * Constant for the "CJK Unified Ideographs Extension B" Unicode
1778 * character block.
1779 * @since 1.5
1780 */
1781 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_B =
1782 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_B",
1783 "CJK UNIFIED IDEOGRAPHS EXTENSION B",
1784 "CJKUNIFIEDIDEOGRAPHSEXTENSIONB");
1785
1786 /**
1787 * Constant for the "CJK Compatibility Ideographs Supplement" Unicode character block.
1788 * @since 1.5
1789 */
1790 public static final UnicodeBlock CJK_COMPATIBILITY_IDEOGRAPHS_SUPPLEMENT =
1791 new UnicodeBlock("CJK_COMPATIBILITY_IDEOGRAPHS_SUPPLEMENT",
1792 "CJK COMPATIBILITY IDEOGRAPHS SUPPLEMENT",
1793 "CJKCOMPATIBILITYIDEOGRAPHSSUPPLEMENT");
1794
1795 /**
1796 * Constant for the "Tags" Unicode character block.
1797 * @since 1.5
1798 */
1799 public static final UnicodeBlock TAGS =
1800 new UnicodeBlock("TAGS");
1801
1802 /**
1803 * Constant for the "Variation Selectors Supplement" Unicode character
1804 * block.
1805 * @since 1.5
1806 */
1807 public static final UnicodeBlock VARIATION_SELECTORS_SUPPLEMENT =
1808 new UnicodeBlock("VARIATION_SELECTORS_SUPPLEMENT",
1809 "VARIATION SELECTORS SUPPLEMENT",
1810 "VARIATIONSELECTORSSUPPLEMENT");
1811
1812 /**
1813 * Constant for the "Supplementary Private Use Area-A" Unicode character
1814 * block.
1815 * @since 1.5
1816 */
1817 public static final UnicodeBlock SUPPLEMENTARY_PRIVATE_USE_AREA_A =
1818 new UnicodeBlock("SUPPLEMENTARY_PRIVATE_USE_AREA_A",
1819 "SUPPLEMENTARY PRIVATE USE AREA-A",
1820 "SUPPLEMENTARYPRIVATEUSEAREA-A");
1821
1822 /**
1823 * Constant for the "Supplementary Private Use Area-B" Unicode character
1824 * block.
1825 * @since 1.5
1826 */
1827 public static final UnicodeBlock SUPPLEMENTARY_PRIVATE_USE_AREA_B =
1828 new UnicodeBlock("SUPPLEMENTARY_PRIVATE_USE_AREA_B",
1829 "SUPPLEMENTARY PRIVATE USE AREA-B",
1830 "SUPPLEMENTARYPRIVATEUSEAREA-B");
1831
1832 /**
1833 * Constant for the "High Surrogates" Unicode character block.
1834 * This block represents codepoint values in the high surrogate
1835 * range: U+D800 through U+DB7F
1836 *
1837 * @since 1.5
1838 */
1839 public static final UnicodeBlock HIGH_SURROGATES =
1840 new UnicodeBlock("HIGH_SURROGATES",
1841 "HIGH SURROGATES",
1842 "HIGHSURROGATES");
1843
1844 /**
1845 * Constant for the "High Private Use Surrogates" Unicode character
1846 * block.
1847 * This block represents codepoint values in the private use high
1848 * surrogate range: U+DB80 through U+DBFF
1849 *
1850 * @since 1.5
1851 */
1852 public static final UnicodeBlock HIGH_PRIVATE_USE_SURROGATES =
1853 new UnicodeBlock("HIGH_PRIVATE_USE_SURROGATES",
1854 "HIGH PRIVATE USE SURROGATES",
1855 "HIGHPRIVATEUSESURROGATES");
1856
1857 /**
1858 * Constant for the "Low Surrogates" Unicode character block.
1859 * This block represents codepoint values in the low surrogate
1860 * range: U+DC00 through U+DFFF
1861 *
1862 * @since 1.5
1863 */
1864 public static final UnicodeBlock LOW_SURROGATES =
1865 new UnicodeBlock("LOW_SURROGATES",
1866 "LOW SURROGATES",
1867 "LOWSURROGATES");
1868
1869 /**
1870 * Constant for the "Arabic Supplement" Unicode character block.
1871 * @since 1.7
1872 */
1873 public static final UnicodeBlock ARABIC_SUPPLEMENT =
1874 new UnicodeBlock("ARABIC_SUPPLEMENT",
1875 "ARABIC SUPPLEMENT",
1876 "ARABICSUPPLEMENT");
1877
1878 /**
1879 * Constant for the "NKo" Unicode character block.
1880 * @since 1.7
1881 */
1882 public static final UnicodeBlock NKO =
1883 new UnicodeBlock("NKO");
1884
1885 /**
1886 * Constant for the "Samaritan" Unicode character block.
1887 * @since 1.7
1888 */
1889 public static final UnicodeBlock SAMARITAN =
1890 new UnicodeBlock("SAMARITAN");
1891
1892 /**
1893 * Constant for the "Mandaic" Unicode character block.
1894 * @since 1.7
1895 */
1896 public static final UnicodeBlock MANDAIC =
1897 new UnicodeBlock("MANDAIC");
1898
1899 /**
1900 * Constant for the "Ethiopic Supplement" Unicode character block.
1901 * @since 1.7
1902 */
1903 public static final UnicodeBlock ETHIOPIC_SUPPLEMENT =
1904 new UnicodeBlock("ETHIOPIC_SUPPLEMENT",
1905 "ETHIOPIC SUPPLEMENT",
1906 "ETHIOPICSUPPLEMENT");
1907
1908 /**
1909 * Constant for the "Unified Canadian Aboriginal Syllabics Extended"
1910 * Unicode character block.
1911 * @since 1.7
1912 */
1913 public static final UnicodeBlock UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED =
1914 new UnicodeBlock("UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED",
1915 "UNIFIED CANADIAN ABORIGINAL SYLLABICS EXTENDED",
1916 "UNIFIEDCANADIANABORIGINALSYLLABICSEXTENDED");
1917
1918 /**
1919 * Constant for the "New Tai Lue" Unicode character block.
1920 * @since 1.7
1921 */
1922 public static final UnicodeBlock NEW_TAI_LUE =
1923 new UnicodeBlock("NEW_TAI_LUE",
1924 "NEW TAI LUE",
1925 "NEWTAILUE");
1926
1927 /**
1928 * Constant for the "Buginese" Unicode character block.
1929 * @since 1.7
1930 */
1931 public static final UnicodeBlock BUGINESE =
1932 new UnicodeBlock("BUGINESE");
1933
1934 /**
1935 * Constant for the "Tai Tham" Unicode character block.
1936 * @since 1.7
1937 */
1938 public static final UnicodeBlock TAI_THAM =
1939 new UnicodeBlock("TAI_THAM",
1940 "TAI THAM",
1941 "TAITHAM");
1942
1943 /**
1944 * Constant for the "Balinese" Unicode character block.
1945 * @since 1.7
1946 */
1947 public static final UnicodeBlock BALINESE =
1948 new UnicodeBlock("BALINESE");
1949
1950 /**
1951 * Constant for the "Sundanese" Unicode character block.
1952 * @since 1.7
1953 */
1954 public static final UnicodeBlock SUNDANESE =
1955 new UnicodeBlock("SUNDANESE");
1956
1957 /**
1958 * Constant for the "Batak" Unicode character block.
1959 * @since 1.7
1960 */
1961 public static final UnicodeBlock BATAK =
1962 new UnicodeBlock("BATAK");
1963
1964 /**
1965 * Constant for the "Lepcha" Unicode character block.
1966 * @since 1.7
1967 */
1968 public static final UnicodeBlock LEPCHA =
1969 new UnicodeBlock("LEPCHA");
1970
1971 /**
1972 * Constant for the "Ol Chiki" Unicode character block.
1973 * @since 1.7
1974 */
1975 public static final UnicodeBlock OL_CHIKI =
1976 new UnicodeBlock("OL_CHIKI",
1977 "OL CHIKI",
1978 "OLCHIKI");
1979
1980 /**
1981 * Constant for the "Vedic Extensions" Unicode character block.
1982 * @since 1.7
1983 */
1984 public static final UnicodeBlock VEDIC_EXTENSIONS =
1985 new UnicodeBlock("VEDIC_EXTENSIONS",
1986 "VEDIC EXTENSIONS",
1987 "VEDICEXTENSIONS");
1988
1989 /**
1990 * Constant for the "Phonetic Extensions Supplement" Unicode character
1991 * block.
1992 * @since 1.7
1993 */
1994 public static final UnicodeBlock PHONETIC_EXTENSIONS_SUPPLEMENT =
1995 new UnicodeBlock("PHONETIC_EXTENSIONS_SUPPLEMENT",
1996 "PHONETIC EXTENSIONS SUPPLEMENT",
1997 "PHONETICEXTENSIONSSUPPLEMENT");
1998
1999 /**
2000 * Constant for the "Combining Diacritical Marks Supplement" Unicode
2001 * character block.
2002 * @since 1.7
2003 */
2004 public static final UnicodeBlock COMBINING_DIACRITICAL_MARKS_SUPPLEMENT =
2005 new UnicodeBlock("COMBINING_DIACRITICAL_MARKS_SUPPLEMENT",
2006 "COMBINING DIACRITICAL MARKS SUPPLEMENT",
2007 "COMBININGDIACRITICALMARKSSUPPLEMENT");
2008
2009 /**
2010 * Constant for the "Glagolitic" Unicode character block.
2011 * @since 1.7
2012 */
2013 public static final UnicodeBlock GLAGOLITIC =
2014 new UnicodeBlock("GLAGOLITIC");
2015
2016 /**
2017 * Constant for the "Latin Extended-C" Unicode character block.
2018 * @since 1.7
2019 */
2020 public static final UnicodeBlock LATIN_EXTENDED_C =
2021 new UnicodeBlock("LATIN_EXTENDED_C",
2022 "LATIN EXTENDED-C",
2023 "LATINEXTENDED-C");
2024
2025 /**
2026 * Constant for the "Coptic" Unicode character block.
2027 * @since 1.7
2028 */
2029 public static final UnicodeBlock COPTIC =
2030 new UnicodeBlock("COPTIC");
2031
2032 /**
2033 * Constant for the "Georgian Supplement" Unicode character block.
2034 * @since 1.7
2035 */
2036 public static final UnicodeBlock GEORGIAN_SUPPLEMENT =
2037 new UnicodeBlock("GEORGIAN_SUPPLEMENT",
2038 "GEORGIAN SUPPLEMENT",
2039 "GEORGIANSUPPLEMENT");
2040
2041 /**
2042 * Constant for the "Tifinagh" Unicode character block.
2043 * @since 1.7
2044 */
2045 public static final UnicodeBlock TIFINAGH =
2046 new UnicodeBlock("TIFINAGH");
2047
2048 /**
2049 * Constant for the "Ethiopic Extended" Unicode character block.
2050 * @since 1.7
2051 */
2052 public static final UnicodeBlock ETHIOPIC_EXTENDED =
2053 new UnicodeBlock("ETHIOPIC_EXTENDED",
2054 "ETHIOPIC EXTENDED",
2055 "ETHIOPICEXTENDED");
2056
2057 /**
2058 * Constant for the "Cyrillic Extended-A" Unicode character block.
2059 * @since 1.7
2060 */
2061 public static final UnicodeBlock CYRILLIC_EXTENDED_A =
2062 new UnicodeBlock("CYRILLIC_EXTENDED_A",
2063 "CYRILLIC EXTENDED-A",
2064 "CYRILLICEXTENDED-A");
2065
2066 /**
2067 * Constant for the "Supplemental Punctuation" Unicode character block.
2068 * @since 1.7
2069 */
2070 public static final UnicodeBlock SUPPLEMENTAL_PUNCTUATION =
2071 new UnicodeBlock("SUPPLEMENTAL_PUNCTUATION",
2072 "SUPPLEMENTAL PUNCTUATION",
2073 "SUPPLEMENTALPUNCTUATION");
2074
2075 /**
2076 * Constant for the "CJK Strokes" Unicode character block.
2077 * @since 1.7
2078 */
2079 public static final UnicodeBlock CJK_STROKES =
2080 new UnicodeBlock("CJK_STROKES",
2081 "CJK STROKES",
2082 "CJKSTROKES");
2083
2084 /**
2085 * Constant for the "Lisu" Unicode character block.
2086 * @since 1.7
2087 */
2088 public static final UnicodeBlock LISU =
2089 new UnicodeBlock("LISU");
2090
2091 /**
2092 * Constant for the "Vai" Unicode character block.
2093 * @since 1.7
2094 */
2095 public static final UnicodeBlock VAI =
2096 new UnicodeBlock("VAI");
2097
2098 /**
2099 * Constant for the "Cyrillic Extended-B" Unicode character block.
2100 * @since 1.7
2101 */
2102 public static final UnicodeBlock CYRILLIC_EXTENDED_B =
2103 new UnicodeBlock("CYRILLIC_EXTENDED_B",
2104 "CYRILLIC EXTENDED-B",
2105 "CYRILLICEXTENDED-B");
2106
2107 /**
2108 * Constant for the "Bamum" Unicode character block.
2109 * @since 1.7
2110 */
2111 public static final UnicodeBlock BAMUM =
2112 new UnicodeBlock("BAMUM");
2113
2114 /**
2115 * Constant for the "Modifier Tone Letters" Unicode character block.
2116 * @since 1.7
2117 */
2118 public static final UnicodeBlock MODIFIER_TONE_LETTERS =
2119 new UnicodeBlock("MODIFIER_TONE_LETTERS",
2120 "MODIFIER TONE LETTERS",
2121 "MODIFIERTONELETTERS");
2122
2123 /**
2124 * Constant for the "Latin Extended-D" Unicode character block.
2125 * @since 1.7
2126 */
2127 public static final UnicodeBlock LATIN_EXTENDED_D =
2128 new UnicodeBlock("LATIN_EXTENDED_D",
2129 "LATIN EXTENDED-D",
2130 "LATINEXTENDED-D");
2131
2132 /**
2133 * Constant for the "Syloti Nagri" Unicode character block.
2134 * @since 1.7
2135 */
2136 public static final UnicodeBlock SYLOTI_NAGRI =
2137 new UnicodeBlock("SYLOTI_NAGRI",
2138 "SYLOTI NAGRI",
2139 "SYLOTINAGRI");
2140
2141 /**
2142 * Constant for the "Common Indic Number Forms" Unicode character block.
2143 * @since 1.7
2144 */
2145 public static final UnicodeBlock COMMON_INDIC_NUMBER_FORMS =
2146 new UnicodeBlock("COMMON_INDIC_NUMBER_FORMS",
2147 "COMMON INDIC NUMBER FORMS",
2148 "COMMONINDICNUMBERFORMS");
2149
2150 /**
2151 * Constant for the "Phags-pa" Unicode character block.
2152 * @since 1.7
2153 */
2154 public static final UnicodeBlock PHAGS_PA =
2155 new UnicodeBlock("PHAGS_PA",
2156 "PHAGS-PA");
2157
2158 /**
2159 * Constant for the "Saurashtra" Unicode character block.
2160 * @since 1.7
2161 */
2162 public static final UnicodeBlock SAURASHTRA =
2163 new UnicodeBlock("SAURASHTRA");
2164
2165 /**
2166 * Constant for the "Devanagari Extended" Unicode character block.
2167 * @since 1.7
2168 */
2169 public static final UnicodeBlock DEVANAGARI_EXTENDED =
2170 new UnicodeBlock("DEVANAGARI_EXTENDED",
2171 "DEVANAGARI EXTENDED",
2172 "DEVANAGARIEXTENDED");
2173
2174 /**
2175 * Constant for the "Kayah Li" Unicode character block.
2176 * @since 1.7
2177 */
2178 public static final UnicodeBlock KAYAH_LI =
2179 new UnicodeBlock("KAYAH_LI",
2180 "KAYAH LI",
2181 "KAYAHLI");
2182
2183 /**
2184 * Constant for the "Rejang" Unicode character block.
2185 * @since 1.7
2186 */
2187 public static final UnicodeBlock REJANG =
2188 new UnicodeBlock("REJANG");
2189
2190 /**
2191 * Constant for the "Hangul Jamo Extended-A" Unicode character block.
2192 * @since 1.7
2193 */
2194 public static final UnicodeBlock HANGUL_JAMO_EXTENDED_A =
2195 new UnicodeBlock("HANGUL_JAMO_EXTENDED_A",
2196 "HANGUL JAMO EXTENDED-A",
2197 "HANGULJAMOEXTENDED-A");
2198
2199 /**
2200 * Constant for the "Javanese" Unicode character block.
2201 * @since 1.7
2202 */
2203 public static final UnicodeBlock JAVANESE =
2204 new UnicodeBlock("JAVANESE");
2205
2206 /**
2207 * Constant for the "Cham" Unicode character block.
2208 * @since 1.7
2209 */
2210 public static final UnicodeBlock CHAM =
2211 new UnicodeBlock("CHAM");
2212
2213 /**
2214 * Constant for the "Myanmar Extended-A" Unicode character block.
2215 * @since 1.7
2216 */
2217 public static final UnicodeBlock MYANMAR_EXTENDED_A =
2218 new UnicodeBlock("MYANMAR_EXTENDED_A",
2219 "MYANMAR EXTENDED-A",
2220 "MYANMAREXTENDED-A");
2221
2222 /**
2223 * Constant for the "Tai Viet" Unicode character block.
2224 * @since 1.7
2225 */
2226 public static final UnicodeBlock TAI_VIET =
2227 new UnicodeBlock("TAI_VIET",
2228 "TAI VIET",
2229 "TAIVIET");
2230
2231 /**
2232 * Constant for the "Ethiopic Extended-A" Unicode character block.
2233 * @since 1.7
2234 */
2235 public static final UnicodeBlock ETHIOPIC_EXTENDED_A =
2236 new UnicodeBlock("ETHIOPIC_EXTENDED_A",
2237 "ETHIOPIC EXTENDED-A",
2238 "ETHIOPICEXTENDED-A");
2239
2240 /**
2241 * Constant for the "Meetei Mayek" Unicode character block.
2242 * @since 1.7
2243 */
2244 public static final UnicodeBlock MEETEI_MAYEK =
2245 new UnicodeBlock("MEETEI_MAYEK",
2246 "MEETEI MAYEK",
2247 "MEETEIMAYEK");
2248
2249 /**
2250 * Constant for the "Hangul Jamo Extended-B" Unicode character block.
2251 * @since 1.7
2252 */
2253 public static final UnicodeBlock HANGUL_JAMO_EXTENDED_B =
2254 new UnicodeBlock("HANGUL_JAMO_EXTENDED_B",
2255 "HANGUL JAMO EXTENDED-B",
2256 "HANGULJAMOEXTENDED-B");
2257
2258 /**
2259 * Constant for the "Vertical Forms" Unicode character block.
2260 * @since 1.7
2261 */
2262 public static final UnicodeBlock VERTICAL_FORMS =
2263 new UnicodeBlock("VERTICAL_FORMS",
2264 "VERTICAL FORMS",
2265 "VERTICALFORMS");
2266
2267 /**
2268 * Constant for the "Ancient Greek Numbers" Unicode character block.
2269 * @since 1.7
2270 */
2271 public static final UnicodeBlock ANCIENT_GREEK_NUMBERS =
2272 new UnicodeBlock("ANCIENT_GREEK_NUMBERS",
2273 "ANCIENT GREEK NUMBERS",
2274 "ANCIENTGREEKNUMBERS");
2275
2276 /**
2277 * Constant for the "Ancient Symbols" Unicode character block.
2278 * @since 1.7
2279 */
2280 public static final UnicodeBlock ANCIENT_SYMBOLS =
2281 new UnicodeBlock("ANCIENT_SYMBOLS",
2282 "ANCIENT SYMBOLS",
2283 "ANCIENTSYMBOLS");
2284
2285 /**
2286 * Constant for the "Phaistos Disc" Unicode character block.
2287 * @since 1.7
2288 */
2289 public static final UnicodeBlock PHAISTOS_DISC =
2290 new UnicodeBlock("PHAISTOS_DISC",
2291 "PHAISTOS DISC",
2292 "PHAISTOSDISC");
2293
2294 /**
2295 * Constant for the "Lycian" Unicode character block.
2296 * @since 1.7
2297 */
2298 public static final UnicodeBlock LYCIAN =
2299 new UnicodeBlock("LYCIAN");
2300
2301 /**
2302 * Constant for the "Carian" Unicode character block.
2303 * @since 1.7
2304 */
2305 public static final UnicodeBlock CARIAN =
2306 new UnicodeBlock("CARIAN");
2307
2308 /**
2309 * Constant for the "Old Persian" Unicode character block.
2310 * @since 1.7
2311 */
2312 public static final UnicodeBlock OLD_PERSIAN =
2313 new UnicodeBlock("OLD_PERSIAN",
2314 "OLD PERSIAN",
2315 "OLDPERSIAN");
2316
2317 /**
2318 * Constant for the "Imperial Aramaic" Unicode character block.
2319 * @since 1.7
2320 */
2321 public static final UnicodeBlock IMPERIAL_ARAMAIC =
2322 new UnicodeBlock("IMPERIAL_ARAMAIC",
2323 "IMPERIAL ARAMAIC",
2324 "IMPERIALARAMAIC");
2325
2326 /**
2327 * Constant for the "Phoenician" Unicode character block.
2328 * @since 1.7
2329 */
2330 public static final UnicodeBlock PHOENICIAN =
2331 new UnicodeBlock("PHOENICIAN");
2332
2333 /**
2334 * Constant for the "Lydian" Unicode character block.
2335 * @since 1.7
2336 */
2337 public static final UnicodeBlock LYDIAN =
2338 new UnicodeBlock("LYDIAN");
2339
2340 /**
2341 * Constant for the "Kharoshthi" Unicode character block.
2342 * @since 1.7
2343 */
2344 public static final UnicodeBlock KHAROSHTHI =
2345 new UnicodeBlock("KHAROSHTHI");
2346
2347 /**
2348 * Constant for the "Old South Arabian" Unicode character block.
2349 * @since 1.7
2350 */
2351 public static final UnicodeBlock OLD_SOUTH_ARABIAN =
2352 new UnicodeBlock("OLD_SOUTH_ARABIAN",
2353 "OLD SOUTH ARABIAN",
2354 "OLDSOUTHARABIAN");
2355
2356 /**
2357 * Constant for the "Avestan" Unicode character block.
2358 * @since 1.7
2359 */
2360 public static final UnicodeBlock AVESTAN =
2361 new UnicodeBlock("AVESTAN");
2362
2363 /**
2364 * Constant for the "Inscriptional Parthian" Unicode character block.
2365 * @since 1.7
2366 */
2367 public static final UnicodeBlock INSCRIPTIONAL_PARTHIAN =
2368 new UnicodeBlock("INSCRIPTIONAL_PARTHIAN",
2369 "INSCRIPTIONAL PARTHIAN",
2370 "INSCRIPTIONALPARTHIAN");
2371
2372 /**
2373 * Constant for the "Inscriptional Pahlavi" Unicode character block.
2374 * @since 1.7
2375 */
2376 public static final UnicodeBlock INSCRIPTIONAL_PAHLAVI =
2377 new UnicodeBlock("INSCRIPTIONAL_PAHLAVI",
2378 "INSCRIPTIONAL PAHLAVI",
2379 "INSCRIPTIONALPAHLAVI");
2380
2381 /**
2382 * Constant for the "Old Turkic" Unicode character block.
2383 * @since 1.7
2384 */
2385 public static final UnicodeBlock OLD_TURKIC =
2386 new UnicodeBlock("OLD_TURKIC",
2387 "OLD TURKIC",
2388 "OLDTURKIC");
2389
2390 /**
2391 * Constant for the "Rumi Numeral Symbols" Unicode character block.
2392 * @since 1.7
2393 */
2394 public static final UnicodeBlock RUMI_NUMERAL_SYMBOLS =
2395 new UnicodeBlock("RUMI_NUMERAL_SYMBOLS",
2396 "RUMI NUMERAL SYMBOLS",
2397 "RUMINUMERALSYMBOLS");
2398
2399 /**
2400 * Constant for the "Brahmi" Unicode character block.
2401 * @since 1.7
2402 */
2403 public static final UnicodeBlock BRAHMI =
2404 new UnicodeBlock("BRAHMI");
2405
2406 /**
2407 * Constant for the "Kaithi" Unicode character block.
2408 * @since 1.7
2409 */
2410 public static final UnicodeBlock KAITHI =
2411 new UnicodeBlock("KAITHI");
2412
2413 /**
2414 * Constant for the "Cuneiform" Unicode character block.
2415 * @since 1.7
2416 */
2417 public static final UnicodeBlock CUNEIFORM =
2418 new UnicodeBlock("CUNEIFORM");
2419
2420 /**
2421 * Constant for the "Cuneiform Numbers and Punctuation" Unicode
2422 * character block.
2423 * @since 1.7
2424 */
2425 public static final UnicodeBlock CUNEIFORM_NUMBERS_AND_PUNCTUATION =
2426 new UnicodeBlock("CUNEIFORM_NUMBERS_AND_PUNCTUATION",
2427 "CUNEIFORM NUMBERS AND PUNCTUATION",
2428 "CUNEIFORMNUMBERSANDPUNCTUATION");
2429
2430 /**
2431 * Constant for the "Egyptian Hieroglyphs" Unicode character block.
2432 * @since 1.7
2433 */
2434 public static final UnicodeBlock EGYPTIAN_HIEROGLYPHS =
2435 new UnicodeBlock("EGYPTIAN_HIEROGLYPHS",
2436 "EGYPTIAN HIEROGLYPHS",
2437 "EGYPTIANHIEROGLYPHS");
2438
2439 /**
2440 * Constant for the "Bamum Supplement" Unicode character block.
2441 * @since 1.7
2442 */
2443 public static final UnicodeBlock BAMUM_SUPPLEMENT =
2444 new UnicodeBlock("BAMUM_SUPPLEMENT",
2445 "BAMUM SUPPLEMENT",
2446 "BAMUMSUPPLEMENT");
2447
2448 /**
2449 * Constant for the "Kana Supplement" Unicode character block.
2450 * @since 1.7
2451 */
2452 public static final UnicodeBlock KANA_SUPPLEMENT =
2453 new UnicodeBlock("KANA_SUPPLEMENT",
2454 "KANA SUPPLEMENT",
2455 "KANASUPPLEMENT");
2456
2457 /**
2458 * Constant for the "Ancient Greek Musical Notation" Unicode character
2459 * block.
2460 * @since 1.7
2461 */
2462 public static final UnicodeBlock ANCIENT_GREEK_MUSICAL_NOTATION =
2463 new UnicodeBlock("ANCIENT_GREEK_MUSICAL_NOTATION",
2464 "ANCIENT GREEK MUSICAL NOTATION",
2465 "ANCIENTGREEKMUSICALNOTATION");
2466
2467 /**
2468 * Constant for the "Counting Rod Numerals" Unicode character block.
2469 * @since 1.7
2470 */
2471 public static final UnicodeBlock COUNTING_ROD_NUMERALS =
2472 new UnicodeBlock("COUNTING_ROD_NUMERALS",
2473 "COUNTING ROD NUMERALS",
2474 "COUNTINGRODNUMERALS");
2475
2476 /**
2477 * Constant for the "Mahjong Tiles" Unicode character block.
2478 * @since 1.7
2479 */
2480 public static final UnicodeBlock MAHJONG_TILES =
2481 new UnicodeBlock("MAHJONG_TILES",
2482 "MAHJONG TILES",
2483 "MAHJONGTILES");
2484
2485 /**
2486 * Constant for the "Domino Tiles" Unicode character block.
2487 * @since 1.7
2488 */
2489 public static final UnicodeBlock DOMINO_TILES =
2490 new UnicodeBlock("DOMINO_TILES",
2491 "DOMINO TILES",
2492 "DOMINOTILES");
2493
2494 /**
2495 * Constant for the "Playing Cards" Unicode character block.
2496 * @since 1.7
2497 */
2498 public static final UnicodeBlock PLAYING_CARDS =
2499 new UnicodeBlock("PLAYING_CARDS",
2500 "PLAYING CARDS",
2501 "PLAYINGCARDS");
2502
2503 /**
2504 * Constant for the "Enclosed Alphanumeric Supplement" Unicode character
2505 * block.
2506 * @since 1.7
2507 */
2508 public static final UnicodeBlock ENCLOSED_ALPHANUMERIC_SUPPLEMENT =
2509 new UnicodeBlock("ENCLOSED_ALPHANUMERIC_SUPPLEMENT",
2510 "ENCLOSED ALPHANUMERIC SUPPLEMENT",
2511 "ENCLOSEDALPHANUMERICSUPPLEMENT");
2512
2513 /**
2514 * Constant for the "Enclosed Ideographic Supplement" Unicode character
2515 * block.
2516 * @since 1.7
2517 */
2518 public static final UnicodeBlock ENCLOSED_IDEOGRAPHIC_SUPPLEMENT =
2519 new UnicodeBlock("ENCLOSED_IDEOGRAPHIC_SUPPLEMENT",
2520 "ENCLOSED IDEOGRAPHIC SUPPLEMENT",
2521 "ENCLOSEDIDEOGRAPHICSUPPLEMENT");
2522
2523 /**
2524 * Constant for the "Miscellaneous Symbols And Pictographs" Unicode
2525 * character block.
2526 * @since 1.7
2527 */
2528 public static final UnicodeBlock MISCELLANEOUS_SYMBOLS_AND_PICTOGRAPHS =
2529 new UnicodeBlock("MISCELLANEOUS_SYMBOLS_AND_PICTOGRAPHS",
2530 "MISCELLANEOUS SYMBOLS AND PICTOGRAPHS",
2531 "MISCELLANEOUSSYMBOLSANDPICTOGRAPHS");
2532
2533 /**
2534 * Constant for the "Emoticons" Unicode character block.
2535 * @since 1.7
2536 */
2537 public static final UnicodeBlock EMOTICONS =
2538 new UnicodeBlock("EMOTICONS");
2539
2540 /**
2541 * Constant for the "Transport And Map Symbols" Unicode character block.
2542 * @since 1.7
2543 */
2544 public static final UnicodeBlock TRANSPORT_AND_MAP_SYMBOLS =
2545 new UnicodeBlock("TRANSPORT_AND_MAP_SYMBOLS",
2546 "TRANSPORT AND MAP SYMBOLS",
2547 "TRANSPORTANDMAPSYMBOLS");
2548
2549 /**
2550 * Constant for the "Alchemical Symbols" Unicode character block.
2551 * @since 1.7
2552 */
2553 public static final UnicodeBlock ALCHEMICAL_SYMBOLS =
2554 new UnicodeBlock("ALCHEMICAL_SYMBOLS",
2555 "ALCHEMICAL SYMBOLS",
2556 "ALCHEMICALSYMBOLS");
2557
2558 /**
2559 * Constant for the "CJK Unified Ideographs Extension C" Unicode
2560 * character block.
2561 * @since 1.7
2562 */
2563 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_C =
2564 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_C",
2565 "CJK UNIFIED IDEOGRAPHS EXTENSION C",
2566 "CJKUNIFIEDIDEOGRAPHSEXTENSIONC");
2567
2568 /**
2569 * Constant for the "CJK Unified Ideographs Extension D" Unicode
2570 * character block.
2571 * @since 1.7
2572 */
2573 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_D =
2574 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_D",
2575 "CJK UNIFIED IDEOGRAPHS EXTENSION D",
2576 "CJKUNIFIEDIDEOGRAPHSEXTENSIOND");
2577
2578 /**
2579 * Constant for the "Arabic Extended-A" Unicode character block.
2580 * @since 1.8
2581 */
2582 public static final UnicodeBlock ARABIC_EXTENDED_A =
2583 new UnicodeBlock("ARABIC_EXTENDED_A",
2584 "ARABIC EXTENDED-A",
2585 "ARABICEXTENDED-A");
2586
2587 /**
2588 * Constant for the "Sundanese Supplement" Unicode character block.
2589 * @since 1.8
2590 */
2591 public static final UnicodeBlock SUNDANESE_SUPPLEMENT =
2592 new UnicodeBlock("SUNDANESE_SUPPLEMENT",
2593 "SUNDANESE SUPPLEMENT",
2594 "SUNDANESESUPPLEMENT");
2595
2596 /**
2597 * Constant for the "Meetei Mayek Extensions" Unicode character block.
2598 * @since 1.8
2599 */
2600 public static final UnicodeBlock MEETEI_MAYEK_EXTENSIONS =
2601 new UnicodeBlock("MEETEI_MAYEK_EXTENSIONS",
2602 "MEETEI MAYEK EXTENSIONS",
2603 "MEETEIMAYEKEXTENSIONS");
2604
2605 /**
2606 * Constant for the "Meroitic Hieroglyphs" Unicode character block.
2607 * @since 1.8
2608 */
2609 public static final UnicodeBlock MEROITIC_HIEROGLYPHS =
2610 new UnicodeBlock("MEROITIC_HIEROGLYPHS",
2611 "MEROITIC HIEROGLYPHS",
2612 "MEROITICHIEROGLYPHS");
2613
2614 /**
2615 * Constant for the "Meroitic Cursive" Unicode character block.
2616 * @since 1.8
2617 */
2618 public static final UnicodeBlock MEROITIC_CURSIVE =
2619 new UnicodeBlock("MEROITIC_CURSIVE",
2620 "MEROITIC CURSIVE",
2621 "MEROITICCURSIVE");
2622
2623 /**
2624 * Constant for the "Sora Sompeng" Unicode character block.
2625 * @since 1.8
2626 */
2627 public static final UnicodeBlock SORA_SOMPENG =
2628 new UnicodeBlock("SORA_SOMPENG",
2629 "SORA SOMPENG",
2630 "SORASOMPENG");
2631
2632 /**
2633 * Constant for the "Chakma" Unicode character block.
2634 * @since 1.8
2635 */
2636 public static final UnicodeBlock CHAKMA =
2637 new UnicodeBlock("CHAKMA");
2638
2639 /**
2640 * Constant for the "Sharada" Unicode character block.
2641 * @since 1.8
2642 */
2643 public static final UnicodeBlock SHARADA =
2644 new UnicodeBlock("SHARADA");
2645
2646 /**
2647 * Constant for the "Takri" Unicode character block.
2648 * @since 1.8
2649 */
2650 public static final UnicodeBlock TAKRI =
2651 new UnicodeBlock("TAKRI");
2652
2653 /**
2654 * Constant for the "Miao" Unicode character block.
2655 * @since 1.8
2656 */
2657 public static final UnicodeBlock MIAO =
2658 new UnicodeBlock("MIAO");
2659
2660 /**
2661 * Constant for the "Arabic Mathematical Alphabetic Symbols" Unicode
2662 * character block.
2663 * @since 1.8
2664 */
2665 public static final UnicodeBlock ARABIC_MATHEMATICAL_ALPHABETIC_SYMBOLS =
2666 new UnicodeBlock("ARABIC_MATHEMATICAL_ALPHABETIC_SYMBOLS",
2667 "ARABIC MATHEMATICAL ALPHABETIC SYMBOLS",
2668 "ARABICMATHEMATICALALPHABETICSYMBOLS");
2669
2670 /**
2671 * Constant for the "Combining Diacritical Marks Extended" Unicode
2672 * character block.
2673 * @since 9
2674 */
2675 public static final UnicodeBlock COMBINING_DIACRITICAL_MARKS_EXTENDED =
2676 new UnicodeBlock("COMBINING_DIACRITICAL_MARKS_EXTENDED",
2677 "COMBINING DIACRITICAL MARKS EXTENDED",
2678 "COMBININGDIACRITICALMARKSEXTENDED");
2679
2680 /**
2681 * Constant for the "Myanmar Extended-B" Unicode character block.
2682 * @since 9
2683 */
2684 public static final UnicodeBlock MYANMAR_EXTENDED_B =
2685 new UnicodeBlock("MYANMAR_EXTENDED_B",
2686 "MYANMAR EXTENDED-B",
2687 "MYANMAREXTENDED-B");
2688
2689 /**
2690 * Constant for the "Latin Extended-E" Unicode character block.
2691 * @since 9
2692 */
2693 public static final UnicodeBlock LATIN_EXTENDED_E =
2694 new UnicodeBlock("LATIN_EXTENDED_E",
2695 "LATIN EXTENDED-E",
2696 "LATINEXTENDED-E");
2697
2698 /**
2699 * Constant for the "Coptic Epact Numbers" Unicode character block.
2700 * @since 9
2701 */
2702 public static final UnicodeBlock COPTIC_EPACT_NUMBERS =
2703 new UnicodeBlock("COPTIC_EPACT_NUMBERS",
2704 "COPTIC EPACT NUMBERS",
2705 "COPTICEPACTNUMBERS");
2706
2707 /**
2708 * Constant for the "Old Permic" Unicode character block.
2709 * @since 9
2710 */
2711 public static final UnicodeBlock OLD_PERMIC =
2712 new UnicodeBlock("OLD_PERMIC",
2713 "OLD PERMIC",
2714 "OLDPERMIC");
2715
2716 /**
2717 * Constant for the "Elbasan" Unicode character block.
2718 * @since 9
2719 */
2720 public static final UnicodeBlock ELBASAN =
2721 new UnicodeBlock("ELBASAN");
2722
2723 /**
2724 * Constant for the "Caucasian Albanian" Unicode character block.
2725 * @since 9
2726 */
2727 public static final UnicodeBlock CAUCASIAN_ALBANIAN =
2728 new UnicodeBlock("CAUCASIAN_ALBANIAN",
2729 "CAUCASIAN ALBANIAN",
2730 "CAUCASIANALBANIAN");
2731
2732 /**
2733 * Constant for the "Linear A" Unicode character block.
2734 * @since 9
2735 */
2736 public static final UnicodeBlock LINEAR_A =
2737 new UnicodeBlock("LINEAR_A",
2738 "LINEAR A",
2739 "LINEARA");
2740
2741 /**
2742 * Constant for the "Palmyrene" Unicode character block.
2743 * @since 9
2744 */
2745 public static final UnicodeBlock PALMYRENE =
2746 new UnicodeBlock("PALMYRENE");
2747
2748 /**
2749 * Constant for the "Nabataean" Unicode character block.
2750 * @since 9
2751 */
2752 public static final UnicodeBlock NABATAEAN =
2753 new UnicodeBlock("NABATAEAN");
2754
2755 /**
2756 * Constant for the "Old North Arabian" Unicode character block.
2757 * @since 9
2758 */
2759 public static final UnicodeBlock OLD_NORTH_ARABIAN =
2760 new UnicodeBlock("OLD_NORTH_ARABIAN",
2761 "OLD NORTH ARABIAN",
2762 "OLDNORTHARABIAN");
2763
2764 /**
2765 * Constant for the "Manichaean" Unicode character block.
2766 * @since 9
2767 */
2768 public static final UnicodeBlock MANICHAEAN =
2769 new UnicodeBlock("MANICHAEAN");
2770
2771 /**
2772 * Constant for the "Psalter Pahlavi" Unicode character block.
2773 * @since 9
2774 */
2775 public static final UnicodeBlock PSALTER_PAHLAVI =
2776 new UnicodeBlock("PSALTER_PAHLAVI",
2777 "PSALTER PAHLAVI",
2778 "PSALTERPAHLAVI");
2779
2780 /**
2781 * Constant for the "Mahajani" Unicode character block.
2782 * @since 9
2783 */
2784 public static final UnicodeBlock MAHAJANI =
2785 new UnicodeBlock("MAHAJANI");
2786
2787 /**
2788 * Constant for the "Sinhala Archaic Numbers" Unicode character block.
2789 * @since 9
2790 */
2791 public static final UnicodeBlock SINHALA_ARCHAIC_NUMBERS =
2792 new UnicodeBlock("SINHALA_ARCHAIC_NUMBERS",
2793 "SINHALA ARCHAIC NUMBERS",
2794 "SINHALAARCHAICNUMBERS");
2795
2796 /**
2797 * Constant for the "Khojki" Unicode character block.
2798 * @since 9
2799 */
2800 public static final UnicodeBlock KHOJKI =
2801 new UnicodeBlock("KHOJKI");
2802
2803 /**
2804 * Constant for the "Khudawadi" Unicode character block.
2805 * @since 9
2806 */
2807 public static final UnicodeBlock KHUDAWADI =
2808 new UnicodeBlock("KHUDAWADI");
2809
2810 /**
2811 * Constant for the "Grantha" Unicode character block.
2812 * @since 9
2813 */
2814 public static final UnicodeBlock GRANTHA =
2815 new UnicodeBlock("GRANTHA");
2816
2817 /**
2818 * Constant for the "Tirhuta" Unicode character block.
2819 * @since 9
2820 */
2821 public static final UnicodeBlock TIRHUTA =
2822 new UnicodeBlock("TIRHUTA");
2823
2824 /**
2825 * Constant for the "Siddham" Unicode character block.
2826 * @since 9
2827 */
2828 public static final UnicodeBlock SIDDHAM =
2829 new UnicodeBlock("SIDDHAM");
2830
2831 /**
2832 * Constant for the "Modi" Unicode character block.
2833 * @since 9
2834 */
2835 public static final UnicodeBlock MODI =
2836 new UnicodeBlock("MODI");
2837
2838 /**
2839 * Constant for the "Warang Citi" Unicode character block.
2840 * @since 9
2841 */
2842 public static final UnicodeBlock WARANG_CITI =
2843 new UnicodeBlock("WARANG_CITI",
2844 "WARANG CITI",
2845 "WARANGCITI");
2846
2847 /**
2848 * Constant for the "Pau Cin Hau" Unicode character block.
2849 * @since 9
2850 */
2851 public static final UnicodeBlock PAU_CIN_HAU =
2852 new UnicodeBlock("PAU_CIN_HAU",
2853 "PAU CIN HAU",
2854 "PAUCINHAU");
2855
2856 /**
2857 * Constant for the "Mro" Unicode character block.
2858 * @since 9
2859 */
2860 public static final UnicodeBlock MRO =
2861 new UnicodeBlock("MRO");
2862
2863 /**
2864 * Constant for the "Bassa Vah" Unicode character block.
2865 * @since 9
2866 */
2867 public static final UnicodeBlock BASSA_VAH =
2868 new UnicodeBlock("BASSA_VAH",
2869 "BASSA VAH",
2870 "BASSAVAH");
2871
2872 /**
2873 * Constant for the "Pahawh Hmong" Unicode character block.
2874 * @since 9
2875 */
2876 public static final UnicodeBlock PAHAWH_HMONG =
2877 new UnicodeBlock("PAHAWH_HMONG",
2878 "PAHAWH HMONG",
2879 "PAHAWHHMONG");
2880
2881 /**
2882 * Constant for the "Duployan" Unicode character block.
2883 * @since 9
2884 */
2885 public static final UnicodeBlock DUPLOYAN =
2886 new UnicodeBlock("DUPLOYAN");
2887
2888 /**
2889 * Constant for the "Shorthand Format Controls" Unicode character block.
2890 * @since 9
2891 */
2892 public static final UnicodeBlock SHORTHAND_FORMAT_CONTROLS =
2893 new UnicodeBlock("SHORTHAND_FORMAT_CONTROLS",
2894 "SHORTHAND FORMAT CONTROLS",
2895 "SHORTHANDFORMATCONTROLS");
2896
2897 /**
2898 * Constant for the "Mende Kikakui" Unicode character block.
2899 * @since 9
2900 */
2901 public static final UnicodeBlock MENDE_KIKAKUI =
2902 new UnicodeBlock("MENDE_KIKAKUI",
2903 "MENDE KIKAKUI",
2904 "MENDEKIKAKUI");
2905
2906 /**
2907 * Constant for the "Ornamental Dingbats" Unicode character block.
2908 * @since 9
2909 */
2910 public static final UnicodeBlock ORNAMENTAL_DINGBATS =
2911 new UnicodeBlock("ORNAMENTAL_DINGBATS",
2912 "ORNAMENTAL DINGBATS",
2913 "ORNAMENTALDINGBATS");
2914
2915 /**
2916 * Constant for the "Geometric Shapes Extended" Unicode character block.
2917 * @since 9
2918 */
2919 public static final UnicodeBlock GEOMETRIC_SHAPES_EXTENDED =
2920 new UnicodeBlock("GEOMETRIC_SHAPES_EXTENDED",
2921 "GEOMETRIC SHAPES EXTENDED",
2922 "GEOMETRICSHAPESEXTENDED");
2923
2924 /**
2925 * Constant for the "Supplemental Arrows-C" Unicode character block.
2926 * @since 9
2927 */
2928 public static final UnicodeBlock SUPPLEMENTAL_ARROWS_C =
2929 new UnicodeBlock("SUPPLEMENTAL_ARROWS_C",
2930 "SUPPLEMENTAL ARROWS-C",
2931 "SUPPLEMENTALARROWS-C");
2932
2933 /**
2934 * Constant for the "Cherokee Supplement" Unicode character block.
2935 * @since 9
2936 */
2937 public static final UnicodeBlock CHEROKEE_SUPPLEMENT =
2938 new UnicodeBlock("CHEROKEE_SUPPLEMENT",
2939 "CHEROKEE SUPPLEMENT",
2940 "CHEROKEESUPPLEMENT");
2941
2942 /**
2943 * Constant for the "Hatran" Unicode character block.
2944 * @since 9
2945 */
2946 public static final UnicodeBlock HATRAN =
2947 new UnicodeBlock("HATRAN");
2948
2949 /**
2950 * Constant for the "Old Hungarian" Unicode character block.
2951 * @since 9
2952 */
2953 public static final UnicodeBlock OLD_HUNGARIAN =
2954 new UnicodeBlock("OLD_HUNGARIAN",
2955 "OLD HUNGARIAN",
2956 "OLDHUNGARIAN");
2957
2958 /**
2959 * Constant for the "Multani" Unicode character block.
2960 * @since 9
2961 */
2962 public static final UnicodeBlock MULTANI =
2963 new UnicodeBlock("MULTANI");
2964
2965 /**
2966 * Constant for the "Ahom" Unicode character block.
2967 * @since 9
2968 */
2969 public static final UnicodeBlock AHOM =
2970 new UnicodeBlock("AHOM");
2971
2972 /**
2973 * Constant for the "Early Dynastic Cuneiform" Unicode character block.
2974 * @since 9
2975 */
2976 public static final UnicodeBlock EARLY_DYNASTIC_CUNEIFORM =
2977 new UnicodeBlock("EARLY_DYNASTIC_CUNEIFORM",
2978 "EARLY DYNASTIC CUNEIFORM",
2979 "EARLYDYNASTICCUNEIFORM");
2980
2981 /**
2982 * Constant for the "Anatolian Hieroglyphs" Unicode character block.
2983 * @since 9
2984 */
2985 public static final UnicodeBlock ANATOLIAN_HIEROGLYPHS =
2986 new UnicodeBlock("ANATOLIAN_HIEROGLYPHS",
2987 "ANATOLIAN HIEROGLYPHS",
2988 "ANATOLIANHIEROGLYPHS");
2989
2990 /**
2991 * Constant for the "Sutton SignWriting" Unicode character block.
2992 * @since 9
2993 */
2994 public static final UnicodeBlock SUTTON_SIGNWRITING =
2995 new UnicodeBlock("SUTTON_SIGNWRITING",
2996 "SUTTON SIGNWRITING",
2997 "SUTTONSIGNWRITING");
2998
2999 /**
3000 * Constant for the "Supplemental Symbols and Pictographs" Unicode
3001 * character block.
3002 * @since 9
3003 */
3004 public static final UnicodeBlock SUPPLEMENTAL_SYMBOLS_AND_PICTOGRAPHS =
3005 new UnicodeBlock("SUPPLEMENTAL_SYMBOLS_AND_PICTOGRAPHS",
3006 "SUPPLEMENTAL SYMBOLS AND PICTOGRAPHS",
3007 "SUPPLEMENTALSYMBOLSANDPICTOGRAPHS");
3008
3009 /**
3010 * Constant for the "CJK Unified Ideographs Extension E" Unicode
3011 * character block.
3012 * @since 9
3013 */
3014 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_E =
3015 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_E",
3016 "CJK UNIFIED IDEOGRAPHS EXTENSION E",
3017 "CJKUNIFIEDIDEOGRAPHSEXTENSIONE");
3018
3019 /**
3020 * Constant for the "Syriac Supplement" Unicode
3021 * character block.
3022 * @since 11
3023 */
3024 public static final UnicodeBlock SYRIAC_SUPPLEMENT =
3025 new UnicodeBlock("SYRIAC_SUPPLEMENT",
3026 "SYRIAC SUPPLEMENT",
3027 "SYRIACSUPPLEMENT");
3028
3029 /**
3030 * Constant for the "Cyrillic Extended-C" Unicode
3031 * character block.
3032 * @since 11
3033 */
3034 public static final UnicodeBlock CYRILLIC_EXTENDED_C =
3035 new UnicodeBlock("CYRILLIC_EXTENDED_C",
3036 "CYRILLIC EXTENDED-C",
3037 "CYRILLICEXTENDED-C");
3038
3039 /**
3040 * Constant for the "Osage" Unicode
3041 * character block.
3042 * @since 11
3043 */
3044 public static final UnicodeBlock OSAGE =
3045 new UnicodeBlock("OSAGE");
3046
3047 /**
3048 * Constant for the "Newa" Unicode
3049 * character block.
3050 * @since 11
3051 */
3052 public static final UnicodeBlock NEWA =
3053 new UnicodeBlock("NEWA");
3054
3055 /**
3056 * Constant for the "Mongolian Supplement" Unicode
3057 * character block.
3058 * @since 11
3059 */
3060 public static final UnicodeBlock MONGOLIAN_SUPPLEMENT =
3061 new UnicodeBlock("MONGOLIAN_SUPPLEMENT",
3062 "MONGOLIAN SUPPLEMENT",
3063 "MONGOLIANSUPPLEMENT");
3064
3065 /**
3066 * Constant for the "Marchen" Unicode
3067 * character block.
3068 * @since 11
3069 */
3070 public static final UnicodeBlock MARCHEN =
3071 new UnicodeBlock("MARCHEN");
3072
3073 /**
3074 * Constant for the "Ideographic Symbols and Punctuation" Unicode
3075 * character block.
3076 * @since 11
3077 */
3078 public static final UnicodeBlock IDEOGRAPHIC_SYMBOLS_AND_PUNCTUATION =
3079 new UnicodeBlock("IDEOGRAPHIC_SYMBOLS_AND_PUNCTUATION",
3080 "IDEOGRAPHIC SYMBOLS AND PUNCTUATION",
3081 "IDEOGRAPHICSYMBOLSANDPUNCTUATION");
3082
3083 /**
3084 * Constant for the "Tangut" Unicode
3085 * character block.
3086 * @since 11
3087 */
3088 public static final UnicodeBlock TANGUT =
3089 new UnicodeBlock("TANGUT");
3090
3091 /**
3092 * Constant for the "Tangut Components" Unicode
3093 * character block.
3094 * @since 11
3095 */
3096 public static final UnicodeBlock TANGUT_COMPONENTS =
3097 new UnicodeBlock("TANGUT_COMPONENTS",
3098 "TANGUT COMPONENTS",
3099 "TANGUTCOMPONENTS");
3100
3101 /**
3102 * Constant for the "Kana Extended-A" Unicode
3103 * character block.
3104 * @since 11
3105 */
3106 public static final UnicodeBlock KANA_EXTENDED_A =
3107 new UnicodeBlock("KANA_EXTENDED_A",
3108 "KANA EXTENDED-A",
3109 "KANAEXTENDED-A");
3110 /**
3111 * Constant for the "Glagolitic Supplement" Unicode
3112 * character block.
3113 * @since 11
3114 */
3115 public static final UnicodeBlock GLAGOLITIC_SUPPLEMENT =
3116 new UnicodeBlock("GLAGOLITIC_SUPPLEMENT",
3117 "GLAGOLITIC SUPPLEMENT",
3118 "GLAGOLITICSUPPLEMENT");
3119 /**
3120 * Constant for the "Adlam" Unicode
3121 * character block.
3122 * @since 11
3123 */
3124 public static final UnicodeBlock ADLAM =
3125 new UnicodeBlock("ADLAM");
3126
3127 /**
3128 * Constant for the "Masaram Gondi" Unicode
3129 * character block.
3130 * @since 11
3131 */
3132 public static final UnicodeBlock MASARAM_GONDI =
3133 new UnicodeBlock("MASARAM_GONDI",
3134 "MASARAM GONDI",
3135 "MASARAMGONDI");
3136
3137 /**
3138 * Constant for the "Zanabazar Square" Unicode
3139 * character block.
3140 * @since 11
3141 */
3142 public static final UnicodeBlock ZANABAZAR_SQUARE =
3143 new UnicodeBlock("ZANABAZAR_SQUARE",
3144 "ZANABAZAR SQUARE",
3145 "ZANABAZARSQUARE");
3146
3147 /**
3148 * Constant for the "Nushu" Unicode
3149 * character block.
3150 * @since 11
3151 */
3152 public static final UnicodeBlock NUSHU =
3153 new UnicodeBlock("NUSHU");
3154
3155 /**
3156 * Constant for the "Soyombo" Unicode
3157 * character block.
3158 * @since 11
3159 */
3160 public static final UnicodeBlock SOYOMBO =
3161 new UnicodeBlock("SOYOMBO");
3162
3163 /**
3164 * Constant for the "Bhaiksuki" Unicode
3165 * character block.
3166 * @since 11
3167 */
3168 public static final UnicodeBlock BHAIKSUKI =
3169 new UnicodeBlock("BHAIKSUKI");
3170
3171 /**
3172 * Constant for the "CJK Unified Ideographs Extension F" Unicode
3173 * character block.
3174 * @since 11
3175 */
3176 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_F =
3177 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_F",
3178 "CJK UNIFIED IDEOGRAPHS EXTENSION F",
3179 "CJKUNIFIEDIDEOGRAPHSEXTENSIONF");
3180 /**
3181 * Constant for the "Georgian Extended" Unicode
3182 * character block.
3183 * @since 12
3184 */
3185 public static final UnicodeBlock GEORGIAN_EXTENDED =
3186 new UnicodeBlock("GEORGIAN_EXTENDED",
3187 "GEORGIAN EXTENDED",
3188 "GEORGIANEXTENDED");
3189
3190 /**
3191 * Constant for the "Hanifi Rohingya" Unicode
3192 * character block.
3193 * @since 12
3194 */
3195 public static final UnicodeBlock HANIFI_ROHINGYA =
3196 new UnicodeBlock("HANIFI_ROHINGYA",
3197 "HANIFI ROHINGYA",
3198 "HANIFIROHINGYA");
3199
3200 /**
3201 * Constant for the "Old Sogdian" Unicode
3202 * character block.
3203 * @since 12
3204 */
3205 public static final UnicodeBlock OLD_SOGDIAN =
3206 new UnicodeBlock("OLD_SOGDIAN",
3207 "OLD SOGDIAN",
3208 "OLDSOGDIAN");
3209
3210 /**
3211 * Constant for the "Sogdian" Unicode
3212 * character block.
3213 * @since 12
3214 */
3215 public static final UnicodeBlock SOGDIAN =
3216 new UnicodeBlock("SOGDIAN");
3217
3218 /**
3219 * Constant for the "Dogra" Unicode
3220 * character block.
3221 * @since 12
3222 */
3223 public static final UnicodeBlock DOGRA =
3224 new UnicodeBlock("DOGRA");
3225
3226 /**
3227 * Constant for the "Gunjala Gondi" Unicode
3228 * character block.
3229 * @since 12
3230 */
3231 public static final UnicodeBlock GUNJALA_GONDI =
3232 new UnicodeBlock("GUNJALA_GONDI",
3233 "GUNJALA GONDI",
3234 "GUNJALAGONDI");
3235
3236 /**
3237 * Constant for the "Makasar" Unicode
3238 * character block.
3239 * @since 12
3240 */
3241 public static final UnicodeBlock MAKASAR =
3242 new UnicodeBlock("MAKASAR");
3243
3244 /**
3245 * Constant for the "Medefaidrin" Unicode
3246 * character block.
3247 * @since 12
3248 */
3249 public static final UnicodeBlock MEDEFAIDRIN =
3250 new UnicodeBlock("MEDEFAIDRIN");
3251
3252 /**
3253 * Constant for the "Mayan Numerals" Unicode
3254 * character block.
3255 * @since 12
3256 */
3257 public static final UnicodeBlock MAYAN_NUMERALS =
3258 new UnicodeBlock("MAYAN_NUMERALS",
3259 "MAYAN NUMERALS",
3260 "MAYANNUMERALS");
3261
3262 /**
3263 * Constant for the "Indic Siyaq Numbers" Unicode
3264 * character block.
3265 * @since 12
3266 */
3267 public static final UnicodeBlock INDIC_SIYAQ_NUMBERS =
3268 new UnicodeBlock("INDIC_SIYAQ_NUMBERS",
3269 "INDIC SIYAQ NUMBERS",
3270 "INDICSIYAQNUMBERS");
3271
3272 /**
3273 * Constant for the "Chess Symbols" Unicode
3274 * character block.
3275 * @since 12
3276 */
3277 public static final UnicodeBlock CHESS_SYMBOLS =
3278 new UnicodeBlock("CHESS_SYMBOLS",
3279 "CHESS SYMBOLS",
3280 "CHESSSYMBOLS");
3281
3282 /**
3283 * Constant for the "Elymaic" Unicode
3284 * character block.
3285 * @since 13
3286 */
3287 public static final UnicodeBlock ELYMAIC =
3288 new UnicodeBlock("ELYMAIC");
3289
3290 /**
3291 * Constant for the "Nandinagari" Unicode
3292 * character block.
3293 * @since 13
3294 */
3295 public static final UnicodeBlock NANDINAGARI =
3296 new UnicodeBlock("NANDINAGARI");
3297
3298 /**
3299 * Constant for the "Tamil Supplement" Unicode
3300 * character block.
3301 * @since 13
3302 */
3303 public static final UnicodeBlock TAMIL_SUPPLEMENT =
3304 new UnicodeBlock("TAMIL_SUPPLEMENT",
3305 "TAMIL SUPPLEMENT",
3306 "TAMILSUPPLEMENT");
3307
3308 /**
3309 * Constant for the "Egyptian Hieroglyph Format Controls" Unicode
3310 * character block.
3311 * @since 13
3312 */
3313 public static final UnicodeBlock EGYPTIAN_HIEROGLYPH_FORMAT_CONTROLS =
3314 new UnicodeBlock("EGYPTIAN_HIEROGLYPH_FORMAT_CONTROLS",
3315 "EGYPTIAN HIEROGLYPH FORMAT CONTROLS",
3316 "EGYPTIANHIEROGLYPHFORMATCONTROLS");
3317
3318 /**
3319 * Constant for the "Small Kana Extension" Unicode
3320 * character block.
3321 * @since 13
3322 */
3323 public static final UnicodeBlock SMALL_KANA_EXTENSION =
3324 new UnicodeBlock("SMALL_KANA_EXTENSION",
3325 "SMALL KANA EXTENSION",
3326 "SMALLKANAEXTENSION");
3327
3328 /**
3329 * Constant for the "Nyiakeng Puachue Hmong" Unicode
3330 * character block.
3331 * @since 13
3332 */
3333 public static final UnicodeBlock NYIAKENG_PUACHUE_HMONG =
3334 new UnicodeBlock("NYIAKENG_PUACHUE_HMONG",
3335 "NYIAKENG PUACHUE HMONG",
3336 "NYIAKENGPUACHUEHMONG");
3337
3338 /**
3339 * Constant for the "Wancho" Unicode
3340 * character block.
3341 * @since 13
3342 */
3343 public static final UnicodeBlock WANCHO =
3344 new UnicodeBlock("WANCHO");
3345
3346 /**
3347 * Constant for the "Ottoman Siyaq Numbers" Unicode
3348 * character block.
3349 * @since 13
3350 */
3351 public static final UnicodeBlock OTTOMAN_SIYAQ_NUMBERS =
3352 new UnicodeBlock("OTTOMAN_SIYAQ_NUMBERS",
3353 "OTTOMAN SIYAQ NUMBERS",
3354 "OTTOMANSIYAQNUMBERS");
3355
3356 /**
3357 * Constant for the "Symbols and Pictographs Extended-A" Unicode
3358 * character block.
3359 * @since 13
3360 */
3361 public static final UnicodeBlock SYMBOLS_AND_PICTOGRAPHS_EXTENDED_A =
3362 new UnicodeBlock("SYMBOLS_AND_PICTOGRAPHS_EXTENDED_A",
3363 "SYMBOLS AND PICTOGRAPHS EXTENDED-A",
3364 "SYMBOLSANDPICTOGRAPHSEXTENDED-A");
3365
3366 /**
3367 * Constant for the "Yezidi" Unicode
3368 * character block.
3369 * @since 15
3370 */
3371 public static final UnicodeBlock YEZIDI =
3372 new UnicodeBlock("YEZIDI");
3373
3374 /**
3375 * Constant for the "Chorasmian" Unicode
3376 * character block.
3377 * @since 15
3378 */
3379 public static final UnicodeBlock CHORASMIAN =
3380 new UnicodeBlock("CHORASMIAN");
3381
3382 /**
3383 * Constant for the "Dives Akuru" Unicode
3384 * character block.
3385 * @since 15
3386 */
3387 public static final UnicodeBlock DIVES_AKURU =
3388 new UnicodeBlock("DIVES_AKURU",
3389 "DIVES AKURU",
3390 "DIVESAKURU");
3391
3392 /**
3393 * Constant for the "Lisu Supplement" Unicode
3394 * character block.
3395 * @since 15
3396 */
3397 public static final UnicodeBlock LISU_SUPPLEMENT =
3398 new UnicodeBlock("LISU_SUPPLEMENT",
3399 "LISU SUPPLEMENT",
3400 "LISUSUPPLEMENT");
3401
3402 /**
3403 * Constant for the "Khitan Small Script" Unicode
3404 * character block.
3405 * @since 15
3406 */
3407 public static final UnicodeBlock KHITAN_SMALL_SCRIPT =
3408 new UnicodeBlock("KHITAN_SMALL_SCRIPT",
3409 "KHITAN SMALL SCRIPT",
3410 "KHITANSMALLSCRIPT");
3411
3412 /**
3413 * Constant for the "Tangut Supplement" Unicode
3414 * character block.
3415 * @since 15
3416 */
3417 public static final UnicodeBlock TANGUT_SUPPLEMENT =
3418 new UnicodeBlock("TANGUT_SUPPLEMENT",
3419 "TANGUT SUPPLEMENT",
3420 "TANGUTSUPPLEMENT");
3421
3422 /**
3423 * Constant for the "Symbols for Legacy Computing" Unicode
3424 * character block.
3425 * @since 15
3426 */
3427 public static final UnicodeBlock SYMBOLS_FOR_LEGACY_COMPUTING =
3428 new UnicodeBlock("SYMBOLS_FOR_LEGACY_COMPUTING",
3429 "SYMBOLS FOR LEGACY COMPUTING",
3430 "SYMBOLSFORLEGACYCOMPUTING");
3431
3432 /**
3433 * Constant for the "CJK Unified Ideographs Extension G" Unicode
3434 * character block.
3435 * @since 15
3436 */
3437 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_G =
3438 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_G",
3439 "CJK UNIFIED IDEOGRAPHS EXTENSION G",
3440 "CJKUNIFIEDIDEOGRAPHSEXTENSIONG");
3441
3442 /**
3443 * Constant for the "Arabic Extended-B" Unicode
3444 * character block.
3445 * @since 19
3446 */
3447 public static final UnicodeBlock ARABIC_EXTENDED_B =
3448 new UnicodeBlock("ARABIC_EXTENDED_B",
3449 "ARABIC EXTENDED-B",
3450 "ARABICEXTENDED-B");
3451
3452 /**
3453 * Constant for the "Vithkuqi" Unicode
3454 * character block.
3455 * @since 19
3456 */
3457 public static final UnicodeBlock VITHKUQI =
3458 new UnicodeBlock("VITHKUQI");
3459
3460 /**
3461 * Constant for the "Latin Extended-F" Unicode
3462 * character block.
3463 * @since 19
3464 */
3465 public static final UnicodeBlock LATIN_EXTENDED_F =
3466 new UnicodeBlock("LATIN_EXTENDED_F",
3467 "LATIN EXTENDED-F",
3468 "LATINEXTENDED-F");
3469
3470 /**
3471 * Constant for the "Old Uyghur" Unicode
3472 * character block.
3473 * @since 19
3474 */
3475 public static final UnicodeBlock OLD_UYGHUR =
3476 new UnicodeBlock("OLD_UYGHUR",
3477 "OLD UYGHUR",
3478 "OLDUYGHUR");
3479
3480 /**
3481 * Constant for the "Unified Canadian Aboriginal Syllabics Extended-A" Unicode
3482 * character block.
3483 * @since 19
3484 */
3485 public static final UnicodeBlock UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED_A =
3486 new UnicodeBlock("UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED_A",
3487 "UNIFIED CANADIAN ABORIGINAL SYLLABICS EXTENDED-A",
3488 "UNIFIEDCANADIANABORIGINALSYLLABICSEXTENDED-A");
3489
3490 /**
3491 * Constant for the "Cypro-Minoan" Unicode
3492 * character block.
3493 * @since 19
3494 */
3495 public static final UnicodeBlock CYPRO_MINOAN =
3496 new UnicodeBlock("CYPRO_MINOAN",
3497 "CYPRO-MINOAN",
3498 "CYPRO-MINOAN");
3499
3500 /**
3501 * Constant for the "Tangsa" Unicode
3502 * character block.
3503 * @since 19
3504 */
3505 public static final UnicodeBlock TANGSA =
3506 new UnicodeBlock("TANGSA");
3507
3508 /**
3509 * Constant for the "Kana Extended-B" Unicode
3510 * character block.
3511 * @since 19
3512 */
3513 public static final UnicodeBlock KANA_EXTENDED_B =
3514 new UnicodeBlock("KANA_EXTENDED_B",
3515 "KANA EXTENDED-B",
3516 "KANAEXTENDED-B");
3517
3518 /**
3519 * Constant for the "Znamenny Musical Notation" Unicode
3520 * character block.
3521 * @since 19
3522 */
3523 public static final UnicodeBlock ZNAMENNY_MUSICAL_NOTATION =
3524 new UnicodeBlock("ZNAMENNY_MUSICAL_NOTATION",
3525 "ZNAMENNY MUSICAL NOTATION",
3526 "ZNAMENNYMUSICALNOTATION");
3527
3528 /**
3529 * Constant for the "Latin Extended-G" Unicode
3530 * character block.
3531 * @since 19
3532 */
3533 public static final UnicodeBlock LATIN_EXTENDED_G =
3534 new UnicodeBlock("LATIN_EXTENDED_G",
3535 "LATIN EXTENDED-G",
3536 "LATINEXTENDED-G");
3537
3538 /**
3539 * Constant for the "Toto" Unicode
3540 * character block.
3541 * @since 19
3542 */
3543 public static final UnicodeBlock TOTO =
3544 new UnicodeBlock("TOTO");
3545
3546 /**
3547 * Constant for the "Ethiopic Extended-B" Unicode
3548 * character block.
3549 * @since 19
3550 */
3551 public static final UnicodeBlock ETHIOPIC_EXTENDED_B =
3552 new UnicodeBlock("ETHIOPIC_EXTENDED_B",
3553 "ETHIOPIC EXTENDED-B",
3554 "ETHIOPICEXTENDED-B");
3555
3556 /**
3557 * Constant for the "Arabic Extended-C" Unicode
3558 * character block.
3559 * @since 20
3560 */
3561 public static final UnicodeBlock ARABIC_EXTENDED_C =
3562 new UnicodeBlock("ARABIC_EXTENDED_C",
3563 "ARABIC EXTENDED-C",
3564 "ARABICEXTENDED-C");
3565
3566 /**
3567 * Constant for the "Devanagari Extended-A" Unicode
3568 * character block.
3569 * @since 20
3570 */
3571 public static final UnicodeBlock DEVANAGARI_EXTENDED_A =
3572 new UnicodeBlock("DEVANAGARI_EXTENDED_A",
3573 "DEVANAGARI EXTENDED-A",
3574 "DEVANAGARIEXTENDED-A");
3575
3576 /**
3577 * Constant for the "Kawi" Unicode
3578 * character block.
3579 * @since 20
3580 */
3581 public static final UnicodeBlock KAWI =
3582 new UnicodeBlock("KAWI");
3583
3584 /**
3585 * Constant for the "Kaktovik Numerals" Unicode
3586 * character block.
3587 * @since 20
3588 */
3589 public static final UnicodeBlock KAKTOVIK_NUMERALS =
3590 new UnicodeBlock("KAKTOVIK_NUMERALS",
3591 "KAKTOVIK NUMERALS",
3592 "KAKTOVIKNUMERALS");
3593
3594 /**
3595 * Constant for the "Cyrillic Extended-D" Unicode
3596 * character block.
3597 * @since 20
3598 */
3599 public static final UnicodeBlock CYRILLIC_EXTENDED_D =
3600 new UnicodeBlock("CYRILLIC_EXTENDED_D",
3601 "CYRILLIC EXTENDED-D",
3602 "CYRILLICEXTENDED-D");
3603
3604 /**
3605 * Constant for the "Nag Mundari" Unicode
3606 * character block.
3607 * @since 20
3608 */
3609 public static final UnicodeBlock NAG_MUNDARI =
3610 new UnicodeBlock("NAG_MUNDARI",
3611 "NAG MUNDARI",
3612 "NAGMUNDARI");
3613
3614 /**
3615 * Constant for the "CJK Unified Ideographs Extension H" Unicode
3616 * character block.
3617 * @since 20
3618 */
3619 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_H =
3620 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_H",
3621 "CJK UNIFIED IDEOGRAPHS EXTENSION H",
3622 "CJKUNIFIEDIDEOGRAPHSEXTENSIONH");
3623
3624 /**
3625 * Constant for the "CJK Unified Ideographs Extension I" Unicode
3626 * character block.
3627 * @since 22
3628 */
3629 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_I =
3630 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_I",
3631 "CJK UNIFIED IDEOGRAPHS EXTENSION I",
3632 "CJKUNIFIEDIDEOGRAPHSEXTENSIONI");
3633
3634 private static final int[] blockStarts = {
3635 0x0000, // 0000..007F; Basic Latin
3636 0x0080, // 0080..00FF; Latin-1 Supplement
3637 0x0100, // 0100..017F; Latin Extended-A
3638 0x0180, // 0180..024F; Latin Extended-B
3639 0x0250, // 0250..02AF; IPA Extensions
3640 0x02B0, // 02B0..02FF; Spacing Modifier Letters
3641 0x0300, // 0300..036F; Combining Diacritical Marks
3642 0x0370, // 0370..03FF; Greek and Coptic
3643 0x0400, // 0400..04FF; Cyrillic
3644 0x0500, // 0500..052F; Cyrillic Supplement
3645 0x0530, // 0530..058F; Armenian
3646 0x0590, // 0590..05FF; Hebrew
3647 0x0600, // 0600..06FF; Arabic
3648 0x0700, // 0700..074F; Syriac
3649 0x0750, // 0750..077F; Arabic Supplement
3650 0x0780, // 0780..07BF; Thaana
3651 0x07C0, // 07C0..07FF; NKo
3652 0x0800, // 0800..083F; Samaritan
3653 0x0840, // 0840..085F; Mandaic
3654 0x0860, // 0860..086F; Syriac Supplement
3655 0x0870, // 0870..089F; Arabic Extended-B
3656 0x08A0, // 08A0..08FF; Arabic Extended-A
3657 0x0900, // 0900..097F; Devanagari
3658 0x0980, // 0980..09FF; Bengali
3659 0x0A00, // 0A00..0A7F; Gurmukhi
3660 0x0A80, // 0A80..0AFF; Gujarati
3661 0x0B00, // 0B00..0B7F; Oriya
3662 0x0B80, // 0B80..0BFF; Tamil
3663 0x0C00, // 0C00..0C7F; Telugu
3664 0x0C80, // 0C80..0CFF; Kannada
3665 0x0D00, // 0D00..0D7F; Malayalam
3666 0x0D80, // 0D80..0DFF; Sinhala
3667 0x0E00, // 0E00..0E7F; Thai
3668 0x0E80, // 0E80..0EFF; Lao
3669 0x0F00, // 0F00..0FFF; Tibetan
3670 0x1000, // 1000..109F; Myanmar
3671 0x10A0, // 10A0..10FF; Georgian
3672 0x1100, // 1100..11FF; Hangul Jamo
3673 0x1200, // 1200..137F; Ethiopic
3674 0x1380, // 1380..139F; Ethiopic Supplement
3675 0x13A0, // 13A0..13FF; Cherokee
3676 0x1400, // 1400..167F; Unified Canadian Aboriginal Syllabics
3677 0x1680, // 1680..169F; Ogham
3678 0x16A0, // 16A0..16FF; Runic
3679 0x1700, // 1700..171F; Tagalog
3680 0x1720, // 1720..173F; Hanunoo
3681 0x1740, // 1740..175F; Buhid
3682 0x1760, // 1760..177F; Tagbanwa
3683 0x1780, // 1780..17FF; Khmer
3684 0x1800, // 1800..18AF; Mongolian
3685 0x18B0, // 18B0..18FF; Unified Canadian Aboriginal Syllabics Extended
3686 0x1900, // 1900..194F; Limbu
3687 0x1950, // 1950..197F; Tai Le
3688 0x1980, // 1980..19DF; New Tai Lue
3689 0x19E0, // 19E0..19FF; Khmer Symbols
3690 0x1A00, // 1A00..1A1F; Buginese
3691 0x1A20, // 1A20..1AAF; Tai Tham
3692 0x1AB0, // 1AB0..1AFF; Combining Diacritical Marks Extended
3693 0x1B00, // 1B00..1B7F; Balinese
3694 0x1B80, // 1B80..1BBF; Sundanese
3695 0x1BC0, // 1BC0..1BFF; Batak
3696 0x1C00, // 1C00..1C4F; Lepcha
3697 0x1C50, // 1C50..1C7F; Ol Chiki
3698 0x1C80, // 1C80..1C8F; Cyrillic Extended-C
3699 0x1C90, // 1C90..1CBF; Georgian Extended
3700 0x1CC0, // 1CC0..1CCF; Sundanese Supplement
3701 0x1CD0, // 1CD0..1CFF; Vedic Extensions
3702 0x1D00, // 1D00..1D7F; Phonetic Extensions
3703 0x1D80, // 1D80..1DBF; Phonetic Extensions Supplement
3704 0x1DC0, // 1DC0..1DFF; Combining Diacritical Marks Supplement
3705 0x1E00, // 1E00..1EFF; Latin Extended Additional
3706 0x1F00, // 1F00..1FFF; Greek Extended
3707 0x2000, // 2000..206F; General Punctuation
3708 0x2070, // 2070..209F; Superscripts and Subscripts
3709 0x20A0, // 20A0..20CF; Currency Symbols
3710 0x20D0, // 20D0..20FF; Combining Diacritical Marks for Symbols
3711 0x2100, // 2100..214F; Letterlike Symbols
3712 0x2150, // 2150..218F; Number Forms
3713 0x2190, // 2190..21FF; Arrows
3714 0x2200, // 2200..22FF; Mathematical Operators
3715 0x2300, // 2300..23FF; Miscellaneous Technical
3716 0x2400, // 2400..243F; Control Pictures
3717 0x2440, // 2440..245F; Optical Character Recognition
3718 0x2460, // 2460..24FF; Enclosed Alphanumerics
3719 0x2500, // 2500..257F; Box Drawing
3720 0x2580, // 2580..259F; Block Elements
3721 0x25A0, // 25A0..25FF; Geometric Shapes
3722 0x2600, // 2600..26FF; Miscellaneous Symbols
3723 0x2700, // 2700..27BF; Dingbats
3724 0x27C0, // 27C0..27EF; Miscellaneous Mathematical Symbols-A
3725 0x27F0, // 27F0..27FF; Supplemental Arrows-A
3726 0x2800, // 2800..28FF; Braille Patterns
3727 0x2900, // 2900..297F; Supplemental Arrows-B
3728 0x2980, // 2980..29FF; Miscellaneous Mathematical Symbols-B
3729 0x2A00, // 2A00..2AFF; Supplemental Mathematical Operators
3730 0x2B00, // 2B00..2BFF; Miscellaneous Symbols and Arrows
3731 0x2C00, // 2C00..2C5F; Glagolitic
3732 0x2C60, // 2C60..2C7F; Latin Extended-C
3733 0x2C80, // 2C80..2CFF; Coptic
3734 0x2D00, // 2D00..2D2F; Georgian Supplement
3735 0x2D30, // 2D30..2D7F; Tifinagh
3736 0x2D80, // 2D80..2DDF; Ethiopic Extended
3737 0x2DE0, // 2DE0..2DFF; Cyrillic Extended-A
3738 0x2E00, // 2E00..2E7F; Supplemental Punctuation
3739 0x2E80, // 2E80..2EFF; CJK Radicals Supplement
3740 0x2F00, // 2F00..2FDF; Kangxi Radicals
3741 0x2FE0, // unassigned
3742 0x2FF0, // 2FF0..2FFF; Ideographic Description Characters
3743 0x3000, // 3000..303F; CJK Symbols and Punctuation
3744 0x3040, // 3040..309F; Hiragana
3745 0x30A0, // 30A0..30FF; Katakana
3746 0x3100, // 3100..312F; Bopomofo
3747 0x3130, // 3130..318F; Hangul Compatibility Jamo
3748 0x3190, // 3190..319F; Kanbun
3749 0x31A0, // 31A0..31BF; Bopomofo Extended
3750 0x31C0, // 31C0..31EF; CJK Strokes
3751 0x31F0, // 31F0..31FF; Katakana Phonetic Extensions
3752 0x3200, // 3200..32FF; Enclosed CJK Letters and Months
3753 0x3300, // 3300..33FF; CJK Compatibility
3754 0x3400, // 3400..4DBF; CJK Unified Ideographs Extension A
3755 0x4DC0, // 4DC0..4DFF; Yijing Hexagram Symbols
3756 0x4E00, // 4E00..9FFF; CJK Unified Ideographs
3757 0xA000, // A000..A48F; Yi Syllables
3758 0xA490, // A490..A4CF; Yi Radicals
3759 0xA4D0, // A4D0..A4FF; Lisu
3760 0xA500, // A500..A63F; Vai
3761 0xA640, // A640..A69F; Cyrillic Extended-B
3762 0xA6A0, // A6A0..A6FF; Bamum
3763 0xA700, // A700..A71F; Modifier Tone Letters
3764 0xA720, // A720..A7FF; Latin Extended-D
3765 0xA800, // A800..A82F; Syloti Nagri
3766 0xA830, // A830..A83F; Common Indic Number Forms
3767 0xA840, // A840..A87F; Phags-pa
3768 0xA880, // A880..A8DF; Saurashtra
3769 0xA8E0, // A8E0..A8FF; Devanagari Extended
3770 0xA900, // A900..A92F; Kayah Li
3771 0xA930, // A930..A95F; Rejang
3772 0xA960, // A960..A97F; Hangul Jamo Extended-A
3773 0xA980, // A980..A9DF; Javanese
3774 0xA9E0, // A9E0..A9FF; Myanmar Extended-B
3775 0xAA00, // AA00..AA5F; Cham
3776 0xAA60, // AA60..AA7F; Myanmar Extended-A
3777 0xAA80, // AA80..AADF; Tai Viet
3778 0xAAE0, // AAE0..AAFF; Meetei Mayek Extensions
3779 0xAB00, // AB00..AB2F; Ethiopic Extended-A
3780 0xAB30, // AB30..AB6F; Latin Extended-E
3781 0xAB70, // AB70..ABBF; Cherokee Supplement
3782 0xABC0, // ABC0..ABFF; Meetei Mayek
3783 0xAC00, // AC00..D7AF; Hangul Syllables
3784 0xD7B0, // D7B0..D7FF; Hangul Jamo Extended-B
3785 0xD800, // D800..DB7F; High Surrogates
3786 0xDB80, // DB80..DBFF; High Private Use Surrogates
3787 0xDC00, // DC00..DFFF; Low Surrogates
3788 0xE000, // E000..F8FF; Private Use Area
3789 0xF900, // F900..FAFF; CJK Compatibility Ideographs
3790 0xFB00, // FB00..FB4F; Alphabetic Presentation Forms
3791 0xFB50, // FB50..FDFF; Arabic Presentation Forms-A
3792 0xFE00, // FE00..FE0F; Variation Selectors
3793 0xFE10, // FE10..FE1F; Vertical Forms
3794 0xFE20, // FE20..FE2F; Combining Half Marks
3795 0xFE30, // FE30..FE4F; CJK Compatibility Forms
3796 0xFE50, // FE50..FE6F; Small Form Variants
3797 0xFE70, // FE70..FEFF; Arabic Presentation Forms-B
3798 0xFF00, // FF00..FFEF; Halfwidth and Fullwidth Forms
3799 0xFFF0, // FFF0..FFFF; Specials
3800 0x10000, // 10000..1007F; Linear B Syllabary
3801 0x10080, // 10080..100FF; Linear B Ideograms
3802 0x10100, // 10100..1013F; Aegean Numbers
3803 0x10140, // 10140..1018F; Ancient Greek Numbers
3804 0x10190, // 10190..101CF; Ancient Symbols
3805 0x101D0, // 101D0..101FF; Phaistos Disc
3806 0x10200, // unassigned
3807 0x10280, // 10280..1029F; Lycian
3808 0x102A0, // 102A0..102DF; Carian
3809 0x102E0, // 102E0..102FF; Coptic Epact Numbers
3810 0x10300, // 10300..1032F; Old Italic
3811 0x10330, // 10330..1034F; Gothic
3812 0x10350, // 10350..1037F; Old Permic
3813 0x10380, // 10380..1039F; Ugaritic
3814 0x103A0, // 103A0..103DF; Old Persian
3815 0x103E0, // unassigned
3816 0x10400, // 10400..1044F; Deseret
3817 0x10450, // 10450..1047F; Shavian
3818 0x10480, // 10480..104AF; Osmanya
3819 0x104B0, // 104B0..104FF; Osage
3820 0x10500, // 10500..1052F; Elbasan
3821 0x10530, // 10530..1056F; Caucasian Albanian
3822 0x10570, // 10570..105BF; Vithkuqi
3823 0x105C0, // unassigned
3824 0x10600, // 10600..1077F; Linear A
3825 0x10780, // 10780..107BF; Latin Extended-F
3826 0x107C0, // unassigned
3827 0x10800, // 10800..1083F; Cypriot Syllabary
3828 0x10840, // 10840..1085F; Imperial Aramaic
3829 0x10860, // 10860..1087F; Palmyrene
3830 0x10880, // 10880..108AF; Nabataean
3831 0x108B0, // unassigned
3832 0x108E0, // 108E0..108FF; Hatran
3833 0x10900, // 10900..1091F; Phoenician
3834 0x10920, // 10920..1093F; Lydian
3835 0x10940, // unassigned
3836 0x10980, // 10980..1099F; Meroitic Hieroglyphs
3837 0x109A0, // 109A0..109FF; Meroitic Cursive
3838 0x10A00, // 10A00..10A5F; Kharoshthi
3839 0x10A60, // 10A60..10A7F; Old South Arabian
3840 0x10A80, // 10A80..10A9F; Old North Arabian
3841 0x10AA0, // unassigned
3842 0x10AC0, // 10AC0..10AFF; Manichaean
3843 0x10B00, // 10B00..10B3F; Avestan
3844 0x10B40, // 10B40..10B5F; Inscriptional Parthian
3845 0x10B60, // 10B60..10B7F; Inscriptional Pahlavi
3846 0x10B80, // 10B80..10BAF; Psalter Pahlavi
3847 0x10BB0, // unassigned
3848 0x10C00, // 10C00..10C4F; Old Turkic
3849 0x10C50, // unassigned
3850 0x10C80, // 10C80..10CFF; Old Hungarian
3851 0x10D00, // 10D00..10D3F; Hanifi Rohingya
3852 0x10D40, // unassigned
3853 0x10E60, // 10E60..10E7F; Rumi Numeral Symbols
3854 0x10E80, // 10E80..10EBF; Yezidi
3855 0x10EC0, // 10EC0..10EFF; Arabic Extended-C
3856 0x10F00, // 10F00..10F2F; Old Sogdian
3857 0x10F30, // 10F30..10F6F; Sogdian
3858 0x10F70, // 10F70..10FAF; Old Uyghur
3859 0x10FB0, // 10FB0..10FDF; Chorasmian
3860 0x10FE0, // 10FE0..10FFF; Elymaic
3861 0x11000, // 11000..1107F; Brahmi
3862 0x11080, // 11080..110CF; Kaithi
3863 0x110D0, // 110D0..110FF; Sora Sompeng
3864 0x11100, // 11100..1114F; Chakma
3865 0x11150, // 11150..1117F; Mahajani
3866 0x11180, // 11180..111DF; Sharada
3867 0x111E0, // 111E0..111FF; Sinhala Archaic Numbers
3868 0x11200, // 11200..1124F; Khojki
3869 0x11250, // unassigned
3870 0x11280, // 11280..112AF; Multani
3871 0x112B0, // 112B0..112FF; Khudawadi
3872 0x11300, // 11300..1137F; Grantha
3873 0x11380, // unassigned
3874 0x11400, // 11400..1147F; Newa
3875 0x11480, // 11480..114DF; Tirhuta
3876 0x114E0, // unassigned
3877 0x11580, // 11580..115FF; Siddham
3878 0x11600, // 11600..1165F; Modi
3879 0x11660, // 11660..1167F; Mongolian Supplement
3880 0x11680, // 11680..116CF; Takri
3881 0x116D0, // unassigned
3882 0x11700, // 11700..1174F; Ahom
3883 0x11750, // unassigned
3884 0x11800, // 11800..1184F; Dogra
3885 0x11850, // unassigned
3886 0x118A0, // 118A0..118FF; Warang Citi
3887 0x11900, // 11900..1195F; Dives Akuru
3888 0x11960, // unassigned
3889 0x119A0, // 119A0..119FF; Nandinagari
3890 0x11A00, // 11A00..11A4F; Zanabazar Square
3891 0x11A50, // 11A50..11AAF; Soyombo
3892 0x11AB0, // 11AB0..11ABF; Unified Canadian Aboriginal Syllabics Extended-A
3893 0x11AC0, // 11AC0..11AFF; Pau Cin Hau
3894 0x11B00, // 11B00..11B5F; Devanagari Extended-A
3895 0x11B60, // unassigned
3896 0x11C00, // 11C00..11C6F; Bhaiksuki
3897 0x11C70, // 11C70..11CBF; Marchen
3898 0x11CC0, // unassigned
3899 0x11D00, // 11D00..11D5F; Masaram Gondi
3900 0x11D60, // 11D60..11DAF; Gunjala Gondi
3901 0x11DB0, // unassigned
3902 0x11EE0, // 11EE0..11EFF; Makasar
3903 0x11F00, // 11F00..11F5F; Kawi
3904 0x11F60, // unassigned
3905 0x11FB0, // 11FB0..11FBF; Lisu Supplement
3906 0x11FC0, // 11FC0..11FFF; Tamil Supplement
3907 0x12000, // 12000..123FF; Cuneiform
3908 0x12400, // 12400..1247F; Cuneiform Numbers and Punctuation
3909 0x12480, // 12480..1254F; Early Dynastic Cuneiform
3910 0x12550, // unassigned
3911 0x12F90, // 12F90..12FFF; Cypro-Minoan
3912 0x13000, // 13000..1342F; Egyptian Hieroglyphs
3913 0x13430, // 13430..1345F; Egyptian Hieroglyph Format Controls
3914 0x13460, // unassigned
3915 0x14400, // 14400..1467F; Anatolian Hieroglyphs
3916 0x14680, // unassigned
3917 0x16800, // 16800..16A3F; Bamum Supplement
3918 0x16A40, // 16A40..16A6F; Mro
3919 0x16A70, // 16A70..16ACF; Tangsa
3920 0x16AD0, // 16AD0..16AFF; Bassa Vah
3921 0x16B00, // 16B00..16B8F; Pahawh Hmong
3922 0x16B90, // unassigned
3923 0x16E40, // 16E40..16E9F; Medefaidrin
3924 0x16EA0, // unassigned
3925 0x16F00, // 16F00..16F9F; Miao
3926 0x16FA0, // unassigned
3927 0x16FE0, // 16FE0..16FFF; Ideographic Symbols and Punctuation
3928 0x17000, // 17000..187FF; Tangut
3929 0x18800, // 18800..18AFF; Tangut Components
3930 0x18B00, // 18B00..18CFF; Khitan Small Script
3931 0x18D00, // 18D00..18D7F; Tangut Supplement
3932 0x18D80, // unassigned
3933 0x1AFF0, // 1AFF0..1AFFF; Kana Extended-B
3934 0x1B000, // 1B000..1B0FF; Kana Supplement
3935 0x1B100, // 1B100..1B12F; Kana Extended-A
3936 0x1B130, // 1B130..1B16F; Small Kana Extension
3937 0x1B170, // 1B170..1B2FF; Nushu
3938 0x1B300, // unassigned
3939 0x1BC00, // 1BC00..1BC9F; Duployan
3940 0x1BCA0, // 1BCA0..1BCAF; Shorthand Format Controls
3941 0x1BCB0, // unassigned
3942 0x1CF00, // 1CF00..1CFCF; Znamenny Musical Notation
3943 0x1CFD0, // unassigned
3944 0x1D000, // 1D000..1D0FF; Byzantine Musical Symbols
3945 0x1D100, // 1D100..1D1FF; Musical Symbols
3946 0x1D200, // 1D200..1D24F; Ancient Greek Musical Notation
3947 0x1D250, // unassigned
3948 0x1D2C0, // 1D2C0..1D2DF; Kaktovik Numerals
3949 0x1D2E0, // 1D2E0..1D2FF; Mayan Numerals
3950 0x1D300, // 1D300..1D35F; Tai Xuan Jing Symbols
3951 0x1D360, // 1D360..1D37F; Counting Rod Numerals
3952 0x1D380, // unassigned
3953 0x1D400, // 1D400..1D7FF; Mathematical Alphanumeric Symbols
3954 0x1D800, // 1D800..1DAAF; Sutton SignWriting
3955 0x1DAB0, // unassigned
3956 0x1DF00, // 1DF00..1DFFF; Latin Extended-G
3957 0x1E000, // 1E000..1E02F; Glagolitic Supplement
3958 0x1E030, // 1E030..1E08F; Cyrillic Extended-D
3959 0x1E090, // unassigned
3960 0x1E100, // 1E100..1E14F; Nyiakeng Puachue Hmong
3961 0x1E150, // unassigned
3962 0x1E290, // 1E290..1E2BF; Toto
3963 0x1E2C0, // 1E2C0..1E2FF; Wancho
3964 0x1E300, // unassigned
3965 0x1E4D0, // 1E4D0..1E4FF; Nag Mundari
3966 0x1E500, // unassigned
3967 0x1E7E0, // 1E7E0..1E7FF; Ethiopic Extended-B
3968 0x1E800, // 1E800..1E8DF; Mende Kikakui
3969 0x1E8E0, // unassigned
3970 0x1E900, // 1E900..1E95F; Adlam
3971 0x1E960, // unassigned
3972 0x1EC70, // 1EC70..1ECBF; Indic Siyaq Numbers
3973 0x1ECC0, // unassigned
3974 0x1ED00, // 1ED00..1ED4F; Ottoman Siyaq Numbers
3975 0x1ED50, // unassigned
3976 0x1EE00, // 1EE00..1EEFF; Arabic Mathematical Alphabetic Symbols
3977 0x1EF00, // unassigned
3978 0x1F000, // 1F000..1F02F; Mahjong Tiles
3979 0x1F030, // 1F030..1F09F; Domino Tiles
3980 0x1F0A0, // 1F0A0..1F0FF; Playing Cards
3981 0x1F100, // 1F100..1F1FF; Enclosed Alphanumeric Supplement
3982 0x1F200, // 1F200..1F2FF; Enclosed Ideographic Supplement
3983 0x1F300, // 1F300..1F5FF; Miscellaneous Symbols and Pictographs
3984 0x1F600, // 1F600..1F64F; Emoticons
3985 0x1F650, // 1F650..1F67F; Ornamental Dingbats
3986 0x1F680, // 1F680..1F6FF; Transport and Map Symbols
3987 0x1F700, // 1F700..1F77F; Alchemical Symbols
3988 0x1F780, // 1F780..1F7FF; Geometric Shapes Extended
3989 0x1F800, // 1F800..1F8FF; Supplemental Arrows-C
3990 0x1F900, // 1F900..1F9FF; Supplemental Symbols and Pictographs
3991 0x1FA00, // 1FA00..1FA6F; Chess Symbols
3992 0x1FA70, // 1FA70..1FAFF; Symbols and Pictographs Extended-A
3993 0x1FB00, // 1FB00..1FBFF; Symbols for Legacy Computing
3994 0x1FC00, // unassigned
3995 0x20000, // 20000..2A6DF; CJK Unified Ideographs Extension B
3996 0x2A6E0, // unassigned
3997 0x2A700, // 2A700..2B73F; CJK Unified Ideographs Extension C
3998 0x2B740, // 2B740..2B81F; CJK Unified Ideographs Extension D
3999 0x2B820, // 2B820..2CEAF; CJK Unified Ideographs Extension E
4000 0x2CEB0, // 2CEB0..2EBEF; CJK Unified Ideographs Extension F
4001 0x2EBF0, // 2EBF0..2EE5F; CJK Unified Ideographs Extension I
4002 0x2EE60, // unassigned
4003 0x2F800, // 2F800..2FA1F; CJK Compatibility Ideographs Supplement
4004 0x2FA20, // unassigned
4005 0x30000, // 30000..3134F; CJK Unified Ideographs Extension G
4006 0x31350, // 31350..323AF; CJK Unified Ideographs Extension H
4007 0x323B0, // unassigned
4008 0xE0000, // E0000..E007F; Tags
4009 0xE0080, // unassigned
4010 0xE0100, // E0100..E01EF; Variation Selectors Supplement
4011 0xE01F0, // unassigned
4012 0xF0000, // F0000..FFFFF; Supplementary Private Use Area-A
4013 0x100000, // 100000..10FFFF; Supplementary Private Use Area-B
4014 };
4015
4016 private static final UnicodeBlock[] blocks = {
4017 BASIC_LATIN,
4018 LATIN_1_SUPPLEMENT,
4019 LATIN_EXTENDED_A,
4020 LATIN_EXTENDED_B,
4021 IPA_EXTENSIONS,
4022 SPACING_MODIFIER_LETTERS,
4023 COMBINING_DIACRITICAL_MARKS,
4024 GREEK,
4025 CYRILLIC,
4026 CYRILLIC_SUPPLEMENTARY,
4027 ARMENIAN,
4028 HEBREW,
4029 ARABIC,
4030 SYRIAC,
4031 ARABIC_SUPPLEMENT,
4032 THAANA,
4033 NKO,
4034 SAMARITAN,
4035 MANDAIC,
4036 SYRIAC_SUPPLEMENT,
4037 ARABIC_EXTENDED_B,
4038 ARABIC_EXTENDED_A,
4039 DEVANAGARI,
4040 BENGALI,
4041 GURMUKHI,
4042 GUJARATI,
4043 ORIYA,
4044 TAMIL,
4045 TELUGU,
4046 KANNADA,
4047 MALAYALAM,
4048 SINHALA,
4049 THAI,
4050 LAO,
4051 TIBETAN,
4052 MYANMAR,
4053 GEORGIAN,
4054 HANGUL_JAMO,
4055 ETHIOPIC,
4056 ETHIOPIC_SUPPLEMENT,
4057 CHEROKEE,
4058 UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS,
4059 OGHAM,
4060 RUNIC,
4061 TAGALOG,
4062 HANUNOO,
4063 BUHID,
4064 TAGBANWA,
4065 KHMER,
4066 MONGOLIAN,
4067 UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED,
4068 LIMBU,
4069 TAI_LE,
4070 NEW_TAI_LUE,
4071 KHMER_SYMBOLS,
4072 BUGINESE,
4073 TAI_THAM,
4074 COMBINING_DIACRITICAL_MARKS_EXTENDED,
4075 BALINESE,
4076 SUNDANESE,
4077 BATAK,
4078 LEPCHA,
4079 OL_CHIKI,
4080 CYRILLIC_EXTENDED_C,
4081 GEORGIAN_EXTENDED,
4082 SUNDANESE_SUPPLEMENT,
4083 VEDIC_EXTENSIONS,
4084 PHONETIC_EXTENSIONS,
4085 PHONETIC_EXTENSIONS_SUPPLEMENT,
4086 COMBINING_DIACRITICAL_MARKS_SUPPLEMENT,
4087 LATIN_EXTENDED_ADDITIONAL,
4088 GREEK_EXTENDED,
4089 GENERAL_PUNCTUATION,
4090 SUPERSCRIPTS_AND_SUBSCRIPTS,
4091 CURRENCY_SYMBOLS,
4092 COMBINING_MARKS_FOR_SYMBOLS,
4093 LETTERLIKE_SYMBOLS,
4094 NUMBER_FORMS,
4095 ARROWS,
4096 MATHEMATICAL_OPERATORS,
4097 MISCELLANEOUS_TECHNICAL,
4098 CONTROL_PICTURES,
4099 OPTICAL_CHARACTER_RECOGNITION,
4100 ENCLOSED_ALPHANUMERICS,
4101 BOX_DRAWING,
4102 BLOCK_ELEMENTS,
4103 GEOMETRIC_SHAPES,
4104 MISCELLANEOUS_SYMBOLS,
4105 DINGBATS,
4106 MISCELLANEOUS_MATHEMATICAL_SYMBOLS_A,
4107 SUPPLEMENTAL_ARROWS_A,
4108 BRAILLE_PATTERNS,
4109 SUPPLEMENTAL_ARROWS_B,
4110 MISCELLANEOUS_MATHEMATICAL_SYMBOLS_B,
4111 SUPPLEMENTAL_MATHEMATICAL_OPERATORS,
4112 MISCELLANEOUS_SYMBOLS_AND_ARROWS,
4113 GLAGOLITIC,
4114 LATIN_EXTENDED_C,
4115 COPTIC,
4116 GEORGIAN_SUPPLEMENT,
4117 TIFINAGH,
4118 ETHIOPIC_EXTENDED,
4119 CYRILLIC_EXTENDED_A,
4120 SUPPLEMENTAL_PUNCTUATION,
4121 CJK_RADICALS_SUPPLEMENT,
4122 KANGXI_RADICALS,
4123 null,
4124 IDEOGRAPHIC_DESCRIPTION_CHARACTERS,
4125 CJK_SYMBOLS_AND_PUNCTUATION,
4126 HIRAGANA,
4127 KATAKANA,
4128 BOPOMOFO,
4129 HANGUL_COMPATIBILITY_JAMO,
4130 KANBUN,
4131 BOPOMOFO_EXTENDED,
4132 CJK_STROKES,
4133 KATAKANA_PHONETIC_EXTENSIONS,
4134 ENCLOSED_CJK_LETTERS_AND_MONTHS,
4135 CJK_COMPATIBILITY,
4136 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A,
4137 YIJING_HEXAGRAM_SYMBOLS,
4138 CJK_UNIFIED_IDEOGRAPHS,
4139 YI_SYLLABLES,
4140 YI_RADICALS,
4141 LISU,
4142 VAI,
4143 CYRILLIC_EXTENDED_B,
4144 BAMUM,
4145 MODIFIER_TONE_LETTERS,
4146 LATIN_EXTENDED_D,
4147 SYLOTI_NAGRI,
4148 COMMON_INDIC_NUMBER_FORMS,
4149 PHAGS_PA,
4150 SAURASHTRA,
4151 DEVANAGARI_EXTENDED,
4152 KAYAH_LI,
4153 REJANG,
4154 HANGUL_JAMO_EXTENDED_A,
4155 JAVANESE,
4156 MYANMAR_EXTENDED_B,
4157 CHAM,
4158 MYANMAR_EXTENDED_A,
4159 TAI_VIET,
4160 MEETEI_MAYEK_EXTENSIONS,
4161 ETHIOPIC_EXTENDED_A,
4162 LATIN_EXTENDED_E,
4163 CHEROKEE_SUPPLEMENT,
4164 MEETEI_MAYEK,
4165 HANGUL_SYLLABLES,
4166 HANGUL_JAMO_EXTENDED_B,
4167 HIGH_SURROGATES,
4168 HIGH_PRIVATE_USE_SURROGATES,
4169 LOW_SURROGATES,
4170 PRIVATE_USE_AREA,
4171 CJK_COMPATIBILITY_IDEOGRAPHS,
4172 ALPHABETIC_PRESENTATION_FORMS,
4173 ARABIC_PRESENTATION_FORMS_A,
4174 VARIATION_SELECTORS,
4175 VERTICAL_FORMS,
4176 COMBINING_HALF_MARKS,
4177 CJK_COMPATIBILITY_FORMS,
4178 SMALL_FORM_VARIANTS,
4179 ARABIC_PRESENTATION_FORMS_B,
4180 HALFWIDTH_AND_FULLWIDTH_FORMS,
4181 SPECIALS,
4182 LINEAR_B_SYLLABARY,
4183 LINEAR_B_IDEOGRAMS,
4184 AEGEAN_NUMBERS,
4185 ANCIENT_GREEK_NUMBERS,
4186 ANCIENT_SYMBOLS,
4187 PHAISTOS_DISC,
4188 null,
4189 LYCIAN,
4190 CARIAN,
4191 COPTIC_EPACT_NUMBERS,
4192 OLD_ITALIC,
4193 GOTHIC,
4194 OLD_PERMIC,
4195 UGARITIC,
4196 OLD_PERSIAN,
4197 null,
4198 DESERET,
4199 SHAVIAN,
4200 OSMANYA,
4201 OSAGE,
4202 ELBASAN,
4203 CAUCASIAN_ALBANIAN,
4204 VITHKUQI,
4205 null,
4206 LINEAR_A,
4207 LATIN_EXTENDED_F,
4208 null,
4209 CYPRIOT_SYLLABARY,
4210 IMPERIAL_ARAMAIC,
4211 PALMYRENE,
4212 NABATAEAN,
4213 null,
4214 HATRAN,
4215 PHOENICIAN,
4216 LYDIAN,
4217 null,
4218 MEROITIC_HIEROGLYPHS,
4219 MEROITIC_CURSIVE,
4220 KHAROSHTHI,
4221 OLD_SOUTH_ARABIAN,
4222 OLD_NORTH_ARABIAN,
4223 null,
4224 MANICHAEAN,
4225 AVESTAN,
4226 INSCRIPTIONAL_PARTHIAN,
4227 INSCRIPTIONAL_PAHLAVI,
4228 PSALTER_PAHLAVI,
4229 null,
4230 OLD_TURKIC,
4231 null,
4232 OLD_HUNGARIAN,
4233 HANIFI_ROHINGYA,
4234 null,
4235 RUMI_NUMERAL_SYMBOLS,
4236 YEZIDI,
4237 ARABIC_EXTENDED_C,
4238 OLD_SOGDIAN,
4239 SOGDIAN,
4240 OLD_UYGHUR,
4241 CHORASMIAN,
4242 ELYMAIC,
4243 BRAHMI,
4244 KAITHI,
4245 SORA_SOMPENG,
4246 CHAKMA,
4247 MAHAJANI,
4248 SHARADA,
4249 SINHALA_ARCHAIC_NUMBERS,
4250 KHOJKI,
4251 null,
4252 MULTANI,
4253 KHUDAWADI,
4254 GRANTHA,
4255 null,
4256 NEWA,
4257 TIRHUTA,
4258 null,
4259 SIDDHAM,
4260 MODI,
4261 MONGOLIAN_SUPPLEMENT,
4262 TAKRI,
4263 null,
4264 AHOM,
4265 null,
4266 DOGRA,
4267 null,
4268 WARANG_CITI,
4269 DIVES_AKURU,
4270 null,
4271 NANDINAGARI,
4272 ZANABAZAR_SQUARE,
4273 SOYOMBO,
4274 UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED_A,
4275 PAU_CIN_HAU,
4276 DEVANAGARI_EXTENDED_A,
4277 null,
4278 BHAIKSUKI,
4279 MARCHEN,
4280 null,
4281 MASARAM_GONDI,
4282 GUNJALA_GONDI,
4283 null,
4284 MAKASAR,
4285 KAWI,
4286 null,
4287 LISU_SUPPLEMENT,
4288 TAMIL_SUPPLEMENT,
4289 CUNEIFORM,
4290 CUNEIFORM_NUMBERS_AND_PUNCTUATION,
4291 EARLY_DYNASTIC_CUNEIFORM,
4292 null,
4293 CYPRO_MINOAN,
4294 EGYPTIAN_HIEROGLYPHS,
4295 EGYPTIAN_HIEROGLYPH_FORMAT_CONTROLS,
4296 null,
4297 ANATOLIAN_HIEROGLYPHS,
4298 null,
4299 BAMUM_SUPPLEMENT,
4300 MRO,
4301 TANGSA,
4302 BASSA_VAH,
4303 PAHAWH_HMONG,
4304 null,
4305 MEDEFAIDRIN,
4306 null,
4307 MIAO,
4308 null,
4309 IDEOGRAPHIC_SYMBOLS_AND_PUNCTUATION,
4310 TANGUT,
4311 TANGUT_COMPONENTS,
4312 KHITAN_SMALL_SCRIPT,
4313 TANGUT_SUPPLEMENT,
4314 null,
4315 KANA_EXTENDED_B,
4316 KANA_SUPPLEMENT,
4317 KANA_EXTENDED_A,
4318 SMALL_KANA_EXTENSION,
4319 NUSHU,
4320 null,
4321 DUPLOYAN,
4322 SHORTHAND_FORMAT_CONTROLS,
4323 null,
4324 ZNAMENNY_MUSICAL_NOTATION,
4325 null,
4326 BYZANTINE_MUSICAL_SYMBOLS,
4327 MUSICAL_SYMBOLS,
4328 ANCIENT_GREEK_MUSICAL_NOTATION,
4329 null,
4330 KAKTOVIK_NUMERALS,
4331 MAYAN_NUMERALS,
4332 TAI_XUAN_JING_SYMBOLS,
4333 COUNTING_ROD_NUMERALS,
4334 null,
4335 MATHEMATICAL_ALPHANUMERIC_SYMBOLS,
4336 SUTTON_SIGNWRITING,
4337 null,
4338 LATIN_EXTENDED_G,
4339 GLAGOLITIC_SUPPLEMENT,
4340 CYRILLIC_EXTENDED_D,
4341 null,
4342 NYIAKENG_PUACHUE_HMONG,
4343 null,
4344 TOTO,
4345 WANCHO,
4346 null,
4347 NAG_MUNDARI,
4348 null,
4349 ETHIOPIC_EXTENDED_B,
4350 MENDE_KIKAKUI,
4351 null,
4352 ADLAM,
4353 null,
4354 INDIC_SIYAQ_NUMBERS,
4355 null,
4356 OTTOMAN_SIYAQ_NUMBERS,
4357 null,
4358 ARABIC_MATHEMATICAL_ALPHABETIC_SYMBOLS,
4359 null,
4360 MAHJONG_TILES,
4361 DOMINO_TILES,
4362 PLAYING_CARDS,
4363 ENCLOSED_ALPHANUMERIC_SUPPLEMENT,
4364 ENCLOSED_IDEOGRAPHIC_SUPPLEMENT,
4365 MISCELLANEOUS_SYMBOLS_AND_PICTOGRAPHS,
4366 EMOTICONS,
4367 ORNAMENTAL_DINGBATS,
4368 TRANSPORT_AND_MAP_SYMBOLS,
4369 ALCHEMICAL_SYMBOLS,
4370 GEOMETRIC_SHAPES_EXTENDED,
4371 SUPPLEMENTAL_ARROWS_C,
4372 SUPPLEMENTAL_SYMBOLS_AND_PICTOGRAPHS,
4373 CHESS_SYMBOLS,
4374 SYMBOLS_AND_PICTOGRAPHS_EXTENDED_A,
4375 SYMBOLS_FOR_LEGACY_COMPUTING,
4376 null,
4377 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_B,
4378 null,
4379 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_C,
4380 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_D,
4381 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_E,
4382 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_F,
4383 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_I,
4384 null,
4385 CJK_COMPATIBILITY_IDEOGRAPHS_SUPPLEMENT,
4386 null,
4387 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_G,
4388 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_H,
4389 null,
4390 TAGS,
4391 null,
4392 VARIATION_SELECTORS_SUPPLEMENT,
4393 null,
4394 SUPPLEMENTARY_PRIVATE_USE_AREA_A,
4395 SUPPLEMENTARY_PRIVATE_USE_AREA_B,
4396 };
4397
4398
4399 /**
4400 * Returns the object representing the Unicode block containing the
4401 * given character, or {@code null} if the character is not a
4402 * member of a defined block.
4403 *
4404 * <p><b>Note:</b> This method cannot handle
4405 * <a href="Character.html#supplementary"> supplementary
4406 * characters</a>. To support all Unicode characters, including
4407 * supplementary characters, use the {@link #of(int)} method.
4408 *
4409 * @param c The character in question
4410 * @return The {@code UnicodeBlock} instance representing the
4411 * Unicode block of which this character is a member, or
4412 * {@code null} if the character is not a member of any
4413 * Unicode block
4414 */
4415 public static UnicodeBlock of(char c) {
4416 return of((int)c);
4417 }
4418
4419 /**
4420 * Returns the object representing the Unicode block
4421 * containing the given character (Unicode code point), or
4422 * {@code null} if the character is not a member of a
4423 * defined block.
4424 *
4425 * @param codePoint the character (Unicode code point) in question.
4426 * @return The {@code UnicodeBlock} instance representing the
4427 * Unicode block of which this character is a member, or
4428 * {@code null} if the character is not a member of any
4429 * Unicode block
4430 * @throws IllegalArgumentException if the specified
4431 * {@code codePoint} is an invalid Unicode code point.
4432 * @see Character#isValidCodePoint(int)
4433 * @since 1.5
4434 */
4435 public static UnicodeBlock of(int codePoint) {
4436 if (!isValidCodePoint(codePoint)) {
4437 throw new IllegalArgumentException(
4438 String.format("Not a valid Unicode code point: 0x%X", codePoint));
4439 }
4440
4441 int top, bottom, current;
4442 bottom = 0;
4443 top = blockStarts.length;
4444 current = top/2;
4445
4446 // invariant: top > current >= bottom && codePoint >= unicodeBlockStarts[bottom]
4447 while (top - bottom > 1) {
4448 if (codePoint >= blockStarts[current]) {
4449 bottom = current;
4450 } else {
4451 top = current;
4452 }
4453 current = (top + bottom) / 2;
4454 }
4455 return blocks[current];
4456 }
4457
4458 /**
4459 * Returns the UnicodeBlock with the given name. Block
4460 * names are determined by The Unicode Standard. The file
4461 * {@code Blocks.txt} defines blocks for a particular
4462 * version of the standard. The {@link Character} class specifies
4463 * the version of the standard that it supports.
4464 * <p>
4465 * This method accepts block names in the following forms:
4466 * <ol>
4467 * <li> Canonical block names as defined by the Unicode Standard.
4468 * For example, the standard defines a "Basic Latin" block. Therefore, this
4469 * method accepts "Basic Latin" as a valid block name. The documentation of
4470 * each UnicodeBlock provides the canonical name.
4471 * <li>Canonical block names with all spaces removed. For example, "BasicLatin"
4472 * is a valid block name for the "Basic Latin" block.
4473 * <li>The text representation of each constant UnicodeBlock identifier.
4474 * For example, this method will return the {@link #BASIC_LATIN} block if
4475 * provided with the "BASIC_LATIN" name. This form replaces all spaces and
4476 * hyphens in the canonical name with underscores.
4477 * </ol>
4478 * Finally, character case is ignored for all of the valid block name forms.
4479 * For example, "BASIC_LATIN" and "basic_latin" are both valid block names.
4480 * The en_US locale's case mapping rules are used to provide case-insensitive
4481 * string comparisons for block name validation.
4482 * <p>
4483 * If the Unicode Standard changes block names, both the previous and
4484 * current names will be accepted.
4485 *
4486 * @param blockName A {@code UnicodeBlock} name.
4487 * @return The {@code UnicodeBlock} instance identified
4488 * by {@code blockName}
4489 * @throws IllegalArgumentException if {@code blockName} is an
4490 * invalid name
4491 * @throws NullPointerException if {@code blockName} is null
4492 * @since 1.5
4493 */
4494 public static final UnicodeBlock forName(String blockName) {
4495 UnicodeBlock block = map.get(blockName.toUpperCase(Locale.US));
4496 if (block == null) {
4497 throw new IllegalArgumentException("Not a valid block name: "
4498 + blockName);
4499 }
4500 return block;
4501 }
4502 }
4503
4504
4505 /**
4506 * A family of character subsets representing the character scripts
4507 * defined in the <a href="http://www.unicode.org/reports/tr24/">
4508 * <i>Unicode Standard Annex #24: Script Names</i></a>. Every Unicode
4509 * character is assigned to a single Unicode script, either a specific
4510 * script, such as {@link Character.UnicodeScript#LATIN Latin}, or
4511 * one of the following three special values,
4512 * {@link Character.UnicodeScript#INHERITED Inherited},
4513 * {@link Character.UnicodeScript#COMMON Common} or
4514 * {@link Character.UnicodeScript#UNKNOWN Unknown}.
4515 *
4516 * @spec https://www.unicode.org/reports/tr24 Unicode Script Property
4517 * @since 1.7
4518 */
4519 public static enum UnicodeScript {
4520 /**
4521 * Unicode script "Common".
4522 */
4523 COMMON,
4524
4525 /**
4526 * Unicode script "Latin".
4527 */
4528 LATIN,
4529
4530 /**
4531 * Unicode script "Greek".
4532 */
4533 GREEK,
4534
4535 /**
4536 * Unicode script "Cyrillic".
4537 */
4538 CYRILLIC,
4539
4540 /**
4541 * Unicode script "Armenian".
4542 */
4543 ARMENIAN,
4544
4545 /**
4546 * Unicode script "Hebrew".
4547 */
4548 HEBREW,
4549
4550 /**
4551 * Unicode script "Arabic".
4552 */
4553 ARABIC,
4554
4555 /**
4556 * Unicode script "Syriac".
4557 */
4558 SYRIAC,
4559
4560 /**
4561 * Unicode script "Thaana".
4562 */
4563 THAANA,
4564
4565 /**
4566 * Unicode script "Devanagari".
4567 */
4568 DEVANAGARI,
4569
4570 /**
4571 * Unicode script "Bengali".
4572 */
4573 BENGALI,
4574
4575 /**
4576 * Unicode script "Gurmukhi".
4577 */
4578 GURMUKHI,
4579
4580 /**
4581 * Unicode script "Gujarati".
4582 */
4583 GUJARATI,
4584
4585 /**
4586 * Unicode script "Oriya".
4587 */
4588 ORIYA,
4589
4590 /**
4591 * Unicode script "Tamil".
4592 */
4593 TAMIL,
4594
4595 /**
4596 * Unicode script "Telugu".
4597 */
4598 TELUGU,
4599
4600 /**
4601 * Unicode script "Kannada".
4602 */
4603 KANNADA,
4604
4605 /**
4606 * Unicode script "Malayalam".
4607 */
4608 MALAYALAM,
4609
4610 /**
4611 * Unicode script "Sinhala".
4612 */
4613 SINHALA,
4614
4615 /**
4616 * Unicode script "Thai".
4617 */
4618 THAI,
4619
4620 /**
4621 * Unicode script "Lao".
4622 */
4623 LAO,
4624
4625 /**
4626 * Unicode script "Tibetan".
4627 */
4628 TIBETAN,
4629
4630 /**
4631 * Unicode script "Myanmar".
4632 */
4633 MYANMAR,
4634
4635 /**
4636 * Unicode script "Georgian".
4637 */
4638 GEORGIAN,
4639
4640 /**
4641 * Unicode script "Hangul".
4642 */
4643 HANGUL,
4644
4645 /**
4646 * Unicode script "Ethiopic".
4647 */
4648 ETHIOPIC,
4649
4650 /**
4651 * Unicode script "Cherokee".
4652 */
4653 CHEROKEE,
4654
4655 /**
4656 * Unicode script "Canadian_Aboriginal".
4657 */
4658 CANADIAN_ABORIGINAL,
4659
4660 /**
4661 * Unicode script "Ogham".
4662 */
4663 OGHAM,
4664
4665 /**
4666 * Unicode script "Runic".
4667 */
4668 RUNIC,
4669
4670 /**
4671 * Unicode script "Khmer".
4672 */
4673 KHMER,
4674
4675 /**
4676 * Unicode script "Mongolian".
4677 */
4678 MONGOLIAN,
4679
4680 /**
4681 * Unicode script "Hiragana".
4682 */
4683 HIRAGANA,
4684
4685 /**
4686 * Unicode script "Katakana".
4687 */
4688 KATAKANA,
4689
4690 /**
4691 * Unicode script "Bopomofo".
4692 */
4693 BOPOMOFO,
4694
4695 /**
4696 * Unicode script "Han".
4697 */
4698 HAN,
4699
4700 /**
4701 * Unicode script "Yi".
4702 */
4703 YI,
4704
4705 /**
4706 * Unicode script "Old_Italic".
4707 */
4708 OLD_ITALIC,
4709
4710 /**
4711 * Unicode script "Gothic".
4712 */
4713 GOTHIC,
4714
4715 /**
4716 * Unicode script "Deseret".
4717 */
4718 DESERET,
4719
4720 /**
4721 * Unicode script "Inherited".
4722 */
4723 INHERITED,
4724
4725 /**
4726 * Unicode script "Tagalog".
4727 */
4728 TAGALOG,
4729
4730 /**
4731 * Unicode script "Hanunoo".
4732 */
4733 HANUNOO,
4734
4735 /**
4736 * Unicode script "Buhid".
4737 */
4738 BUHID,
4739
4740 /**
4741 * Unicode script "Tagbanwa".
4742 */
4743 TAGBANWA,
4744
4745 /**
4746 * Unicode script "Limbu".
4747 */
4748 LIMBU,
4749
4750 /**
4751 * Unicode script "Tai_Le".
4752 */
4753 TAI_LE,
4754
4755 /**
4756 * Unicode script "Linear_B".
4757 */
4758 LINEAR_B,
4759
4760 /**
4761 * Unicode script "Ugaritic".
4762 */
4763 UGARITIC,
4764
4765 /**
4766 * Unicode script "Shavian".
4767 */
4768 SHAVIAN,
4769
4770 /**
4771 * Unicode script "Osmanya".
4772 */
4773 OSMANYA,
4774
4775 /**
4776 * Unicode script "Cypriot".
4777 */
4778 CYPRIOT,
4779
4780 /**
4781 * Unicode script "Braille".
4782 */
4783 BRAILLE,
4784
4785 /**
4786 * Unicode script "Buginese".
4787 */
4788 BUGINESE,
4789
4790 /**
4791 * Unicode script "Coptic".
4792 */
4793 COPTIC,
4794
4795 /**
4796 * Unicode script "New_Tai_Lue".
4797 */
4798 NEW_TAI_LUE,
4799
4800 /**
4801 * Unicode script "Glagolitic".
4802 */
4803 GLAGOLITIC,
4804
4805 /**
4806 * Unicode script "Tifinagh".
4807 */
4808 TIFINAGH,
4809
4810 /**
4811 * Unicode script "Syloti_Nagri".
4812 */
4813 SYLOTI_NAGRI,
4814
4815 /**
4816 * Unicode script "Old_Persian".
4817 */
4818 OLD_PERSIAN,
4819
4820 /**
4821 * Unicode script "Kharoshthi".
4822 */
4823 KHAROSHTHI,
4824
4825 /**
4826 * Unicode script "Balinese".
4827 */
4828 BALINESE,
4829
4830 /**
4831 * Unicode script "Cuneiform".
4832 */
4833 CUNEIFORM,
4834
4835 /**
4836 * Unicode script "Phoenician".
4837 */
4838 PHOENICIAN,
4839
4840 /**
4841 * Unicode script "Phags_Pa".
4842 */
4843 PHAGS_PA,
4844
4845 /**
4846 * Unicode script "Nko".
4847 */
4848 NKO,
4849
4850 /**
4851 * Unicode script "Sundanese".
4852 */
4853 SUNDANESE,
4854
4855 /**
4856 * Unicode script "Batak".
4857 */
4858 BATAK,
4859
4860 /**
4861 * Unicode script "Lepcha".
4862 */
4863 LEPCHA,
4864
4865 /**
4866 * Unicode script "Ol_Chiki".
4867 */
4868 OL_CHIKI,
4869
4870 /**
4871 * Unicode script "Vai".
4872 */
4873 VAI,
4874
4875 /**
4876 * Unicode script "Saurashtra".
4877 */
4878 SAURASHTRA,
4879
4880 /**
4881 * Unicode script "Kayah_Li".
4882 */
4883 KAYAH_LI,
4884
4885 /**
4886 * Unicode script "Rejang".
4887 */
4888 REJANG,
4889
4890 /**
4891 * Unicode script "Lycian".
4892 */
4893 LYCIAN,
4894
4895 /**
4896 * Unicode script "Carian".
4897 */
4898 CARIAN,
4899
4900 /**
4901 * Unicode script "Lydian".
4902 */
4903 LYDIAN,
4904
4905 /**
4906 * Unicode script "Cham".
4907 */
4908 CHAM,
4909
4910 /**
4911 * Unicode script "Tai_Tham".
4912 */
4913 TAI_THAM,
4914
4915 /**
4916 * Unicode script "Tai_Viet".
4917 */
4918 TAI_VIET,
4919
4920 /**
4921 * Unicode script "Avestan".
4922 */
4923 AVESTAN,
4924
4925 /**
4926 * Unicode script "Egyptian_Hieroglyphs".
4927 */
4928 EGYPTIAN_HIEROGLYPHS,
4929
4930 /**
4931 * Unicode script "Samaritan".
4932 */
4933 SAMARITAN,
4934
4935 /**
4936 * Unicode script "Mandaic".
4937 */
4938 MANDAIC,
4939
4940 /**
4941 * Unicode script "Lisu".
4942 */
4943 LISU,
4944
4945 /**
4946 * Unicode script "Bamum".
4947 */
4948 BAMUM,
4949
4950 /**
4951 * Unicode script "Javanese".
4952 */
4953 JAVANESE,
4954
4955 /**
4956 * Unicode script "Meetei_Mayek".
4957 */
4958 MEETEI_MAYEK,
4959
4960 /**
4961 * Unicode script "Imperial_Aramaic".
4962 */
4963 IMPERIAL_ARAMAIC,
4964
4965 /**
4966 * Unicode script "Old_South_Arabian".
4967 */
4968 OLD_SOUTH_ARABIAN,
4969
4970 /**
4971 * Unicode script "Inscriptional_Parthian".
4972 */
4973 INSCRIPTIONAL_PARTHIAN,
4974
4975 /**
4976 * Unicode script "Inscriptional_Pahlavi".
4977 */
4978 INSCRIPTIONAL_PAHLAVI,
4979
4980 /**
4981 * Unicode script "Old_Turkic".
4982 */
4983 OLD_TURKIC,
4984
4985 /**
4986 * Unicode script "Brahmi".
4987 */
4988 BRAHMI,
4989
4990 /**
4991 * Unicode script "Kaithi".
4992 */
4993 KAITHI,
4994
4995 /**
4996 * Unicode script "Meroitic Hieroglyphs".
4997 * @since 1.8
4998 */
4999 MEROITIC_HIEROGLYPHS,
5000
5001 /**
5002 * Unicode script "Meroitic Cursive".
5003 * @since 1.8
5004 */
5005 MEROITIC_CURSIVE,
5006
5007 /**
5008 * Unicode script "Sora Sompeng".
5009 * @since 1.8
5010 */
5011 SORA_SOMPENG,
5012
5013 /**
5014 * Unicode script "Chakma".
5015 * @since 1.8
5016 */
5017 CHAKMA,
5018
5019 /**
5020 * Unicode script "Sharada".
5021 * @since 1.8
5022 */
5023 SHARADA,
5024
5025 /**
5026 * Unicode script "Takri".
5027 * @since 1.8
5028 */
5029 TAKRI,
5030
5031 /**
5032 * Unicode script "Miao".
5033 * @since 1.8
5034 */
5035 MIAO,
5036
5037 /**
5038 * Unicode script "Caucasian Albanian".
5039 * @since 9
5040 */
5041 CAUCASIAN_ALBANIAN,
5042
5043 /**
5044 * Unicode script "Bassa Vah".
5045 * @since 9
5046 */
5047 BASSA_VAH,
5048
5049 /**
5050 * Unicode script "Duployan".
5051 * @since 9
5052 */
5053 DUPLOYAN,
5054
5055 /**
5056 * Unicode script "Elbasan".
5057 * @since 9
5058 */
5059 ELBASAN,
5060
5061 /**
5062 * Unicode script "Grantha".
5063 * @since 9
5064 */
5065 GRANTHA,
5066
5067 /**
5068 * Unicode script "Pahawh Hmong".
5069 * @since 9
5070 */
5071 PAHAWH_HMONG,
5072
5073 /**
5074 * Unicode script "Khojki".
5075 * @since 9
5076 */
5077 KHOJKI,
5078
5079 /**
5080 * Unicode script "Linear A".
5081 * @since 9
5082 */
5083 LINEAR_A,
5084
5085 /**
5086 * Unicode script "Mahajani".
5087 * @since 9
5088 */
5089 MAHAJANI,
5090
5091 /**
5092 * Unicode script "Manichaean".
5093 * @since 9
5094 */
5095 MANICHAEAN,
5096
5097 /**
5098 * Unicode script "Mende Kikakui".
5099 * @since 9
5100 */
5101 MENDE_KIKAKUI,
5102
5103 /**
5104 * Unicode script "Modi".
5105 * @since 9
5106 */
5107 MODI,
5108
5109 /**
5110 * Unicode script "Mro".
5111 * @since 9
5112 */
5113 MRO,
5114
5115 /**
5116 * Unicode script "Old North Arabian".
5117 * @since 9
5118 */
5119 OLD_NORTH_ARABIAN,
5120
5121 /**
5122 * Unicode script "Nabataean".
5123 * @since 9
5124 */
5125 NABATAEAN,
5126
5127 /**
5128 * Unicode script "Palmyrene".
5129 * @since 9
5130 */
5131 PALMYRENE,
5132
5133 /**
5134 * Unicode script "Pau Cin Hau".
5135 * @since 9
5136 */
5137 PAU_CIN_HAU,
5138
5139 /**
5140 * Unicode script "Old Permic".
5141 * @since 9
5142 */
5143 OLD_PERMIC,
5144
5145 /**
5146 * Unicode script "Psalter Pahlavi".
5147 * @since 9
5148 */
5149 PSALTER_PAHLAVI,
5150
5151 /**
5152 * Unicode script "Siddham".
5153 * @since 9
5154 */
5155 SIDDHAM,
5156
5157 /**
5158 * Unicode script "Khudawadi".
5159 * @since 9
5160 */
5161 KHUDAWADI,
5162
5163 /**
5164 * Unicode script "Tirhuta".
5165 * @since 9
5166 */
5167 TIRHUTA,
5168
5169 /**
5170 * Unicode script "Warang Citi".
5171 * @since 9
5172 */
5173 WARANG_CITI,
5174
5175 /**
5176 * Unicode script "Ahom".
5177 * @since 9
5178 */
5179 AHOM,
5180
5181 /**
5182 * Unicode script "Anatolian Hieroglyphs".
5183 * @since 9
5184 */
5185 ANATOLIAN_HIEROGLYPHS,
5186
5187 /**
5188 * Unicode script "Hatran".
5189 * @since 9
5190 */
5191 HATRAN,
5192
5193 /**
5194 * Unicode script "Multani".
5195 * @since 9
5196 */
5197 MULTANI,
5198
5199 /**
5200 * Unicode script "Old Hungarian".
5201 * @since 9
5202 */
5203 OLD_HUNGARIAN,
5204
5205 /**
5206 * Unicode script "SignWriting".
5207 * @since 9
5208 */
5209 SIGNWRITING,
5210
5211 /**
5212 * Unicode script "Adlam".
5213 * @since 11
5214 */
5215 ADLAM,
5216
5217 /**
5218 * Unicode script "Bhaiksuki".
5219 * @since 11
5220 */
5221 BHAIKSUKI,
5222
5223 /**
5224 * Unicode script "Marchen".
5225 * @since 11
5226 */
5227 MARCHEN,
5228
5229 /**
5230 * Unicode script "Newa".
5231 * @since 11
5232 */
5233 NEWA,
5234
5235 /**
5236 * Unicode script "Osage".
5237 * @since 11
5238 */
5239 OSAGE,
5240
5241 /**
5242 * Unicode script "Tangut".
5243 * @since 11
5244 */
5245 TANGUT,
5246
5247 /**
5248 * Unicode script "Masaram Gondi".
5249 * @since 11
5250 */
5251 MASARAM_GONDI,
5252
5253 /**
5254 * Unicode script "Nushu".
5255 * @since 11
5256 */
5257 NUSHU,
5258
5259 /**
5260 * Unicode script "Soyombo".
5261 * @since 11
5262 */
5263 SOYOMBO,
5264
5265 /**
5266 * Unicode script "Zanabazar Square".
5267 * @since 11
5268 */
5269 ZANABAZAR_SQUARE,
5270
5271 /**
5272 * Unicode script "Hanifi Rohingya".
5273 * @since 12
5274 */
5275 HANIFI_ROHINGYA,
5276
5277 /**
5278 * Unicode script "Old Sogdian".
5279 * @since 12
5280 */
5281 OLD_SOGDIAN,
5282
5283 /**
5284 * Unicode script "Sogdian".
5285 * @since 12
5286 */
5287 SOGDIAN,
5288
5289 /**
5290 * Unicode script "Dogra".
5291 * @since 12
5292 */
5293 DOGRA,
5294
5295 /**
5296 * Unicode script "Gunjala Gondi".
5297 * @since 12
5298 */
5299 GUNJALA_GONDI,
5300
5301 /**
5302 * Unicode script "Makasar".
5303 * @since 12
5304 */
5305 MAKASAR,
5306
5307 /**
5308 * Unicode script "Medefaidrin".
5309 * @since 12
5310 */
5311 MEDEFAIDRIN,
5312
5313 /**
5314 * Unicode script "Elymaic".
5315 * @since 13
5316 */
5317 ELYMAIC,
5318
5319 /**
5320 * Unicode script "Nandinagari".
5321 * @since 13
5322 */
5323 NANDINAGARI,
5324
5325 /**
5326 * Unicode script "Nyiakeng Puachue Hmong".
5327 * @since 13
5328 */
5329 NYIAKENG_PUACHUE_HMONG,
5330
5331 /**
5332 * Unicode script "Wancho".
5333 * @since 13
5334 */
5335 WANCHO,
5336
5337 /**
5338 * Unicode script "Yezidi".
5339 * @since 15
5340 */
5341 YEZIDI,
5342
5343 /**
5344 * Unicode script "Chorasmian".
5345 * @since 15
5346 */
5347 CHORASMIAN,
5348
5349 /**
5350 * Unicode script "Dives Akuru".
5351 * @since 15
5352 */
5353 DIVES_AKURU,
5354
5355 /**
5356 * Unicode script "Khitan Small Script".
5357 * @since 15
5358 */
5359 KHITAN_SMALL_SCRIPT,
5360
5361 /**
5362 * Unicode script "Vithkuqi".
5363 * @since 19
5364 */
5365 VITHKUQI,
5366
5367 /**
5368 * Unicode script "Old Uyghur".
5369 * @since 19
5370 */
5371 OLD_UYGHUR,
5372
5373 /**
5374 * Unicode script "Cypro Minoan".
5375 * @since 19
5376 */
5377 CYPRO_MINOAN,
5378
5379 /**
5380 * Unicode script "Tangsa".
5381 * @since 19
5382 */
5383 TANGSA,
5384
5385 /**
5386 * Unicode script "Toto".
5387 * @since 19
5388 */
5389 TOTO,
5390
5391 /**
5392 * Unicode script "Kawi".
5393 * @since 20
5394 */
5395 KAWI,
5396
5397 /**
5398 * Unicode script "Nag Mundari".
5399 * @since 20
5400 */
5401 NAG_MUNDARI,
5402
5403 /**
5404 * Unicode script "Unknown".
5405 */
5406 UNKNOWN; // must be the last enum constant for calculating the size of "aliases" hash map.
5407
5408 private static final int[] scriptStarts = {
5409 0x0000, // 0000..0040; COMMON
5410 0x0041, // 0041..005A; LATIN
5411 0x005B, // 005B..0060; COMMON
5412 0x0061, // 0061..007A; LATIN
5413 0x007B, // 007B..00A9; COMMON
5414 0x00AA, // 00AA ; LATIN
5415 0x00AB, // 00AB..00B9; COMMON
5416 0x00BA, // 00BA ; LATIN
5417 0x00BB, // 00BB..00BF; COMMON
5418 0x00C0, // 00C0..00D6; LATIN
5419 0x00D7, // 00D7 ; COMMON
5420 0x00D8, // 00D8..00F6; LATIN
5421 0x00F7, // 00F7 ; COMMON
5422 0x00F8, // 00F8..02B8; LATIN
5423 0x02B9, // 02B9..02DF; COMMON
5424 0x02E0, // 02E0..02E4; LATIN
5425 0x02E5, // 02E5..02E9; COMMON
5426 0x02EA, // 02EA..02EB; BOPOMOFO
5427 0x02EC, // 02EC..02FF; COMMON
5428 0x0300, // 0300..036F; INHERITED
5429 0x0370, // 0370..0373; GREEK
5430 0x0374, // 0374 ; COMMON
5431 0x0375, // 0375..0377; GREEK
5432 0x0378, // 0378..0379; UNKNOWN
5433 0x037A, // 037A..037D; GREEK
5434 0x037E, // 037E ; COMMON
5435 0x037F, // 037F ; GREEK
5436 0x0380, // 0380..0383; UNKNOWN
5437 0x0384, // 0384 ; GREEK
5438 0x0385, // 0385 ; COMMON
5439 0x0386, // 0386 ; GREEK
5440 0x0387, // 0387 ; COMMON
5441 0x0388, // 0388..038A; GREEK
5442 0x038B, // 038B ; UNKNOWN
5443 0x038C, // 038C ; GREEK
5444 0x038D, // 038D ; UNKNOWN
5445 0x038E, // 038E..03A1; GREEK
5446 0x03A2, // 03A2 ; UNKNOWN
5447 0x03A3, // 03A3..03E1; GREEK
5448 0x03E2, // 03E2..03EF; COPTIC
5449 0x03F0, // 03F0..03FF; GREEK
5450 0x0400, // 0400..0484; CYRILLIC
5451 0x0485, // 0485..0486; INHERITED
5452 0x0487, // 0487..052F; CYRILLIC
5453 0x0530, // 0530 ; UNKNOWN
5454 0x0531, // 0531..0556; ARMENIAN
5455 0x0557, // 0557..0558; UNKNOWN
5456 0x0559, // 0559..058A; ARMENIAN
5457 0x058B, // 058B..058C; UNKNOWN
5458 0x058D, // 058D..058F; ARMENIAN
5459 0x0590, // 0590 ; UNKNOWN
5460 0x0591, // 0591..05C7; HEBREW
5461 0x05C8, // 05C8..05CF; UNKNOWN
5462 0x05D0, // 05D0..05EA; HEBREW
5463 0x05EB, // 05EB..05EE; UNKNOWN
5464 0x05EF, // 05EF..05F4; HEBREW
5465 0x05F5, // 05F5..05FF; UNKNOWN
5466 0x0600, // 0600..0604; ARABIC
5467 0x0605, // 0605 ; COMMON
5468 0x0606, // 0606..060B; ARABIC
5469 0x060C, // 060C ; COMMON
5470 0x060D, // 060D..061A; ARABIC
5471 0x061B, // 061B ; COMMON
5472 0x061C, // 061C..061E; ARABIC
5473 0x061F, // 061F ; COMMON
5474 0x0620, // 0620..063F; ARABIC
5475 0x0640, // 0640 ; COMMON
5476 0x0641, // 0641..064A; ARABIC
5477 0x064B, // 064B..0655; INHERITED
5478 0x0656, // 0656..066F; ARABIC
5479 0x0670, // 0670 ; INHERITED
5480 0x0671, // 0671..06DC; ARABIC
5481 0x06DD, // 06DD ; COMMON
5482 0x06DE, // 06DE..06FF; ARABIC
5483 0x0700, // 0700..070D; SYRIAC
5484 0x070E, // 070E ; UNKNOWN
5485 0x070F, // 070F..074A; SYRIAC
5486 0x074B, // 074B..074C; UNKNOWN
5487 0x074D, // 074D..074F; SYRIAC
5488 0x0750, // 0750..077F; ARABIC
5489 0x0780, // 0780..07B1; THAANA
5490 0x07B2, // 07B2..07BF; UNKNOWN
5491 0x07C0, // 07C0..07FA; NKO
5492 0x07FB, // 07FB..07FC; UNKNOWN
5493 0x07FD, // 07FD..07FF; NKO
5494 0x0800, // 0800..082D; SAMARITAN
5495 0x082E, // 082E..082F; UNKNOWN
5496 0x0830, // 0830..083E; SAMARITAN
5497 0x083F, // 083F ; UNKNOWN
5498 0x0840, // 0840..085B; MANDAIC
5499 0x085C, // 085C..085D; UNKNOWN
5500 0x085E, // 085E ; MANDAIC
5501 0x085F, // 085F ; UNKNOWN
5502 0x0860, // 0860..086A; SYRIAC
5503 0x086B, // 086B..086F; UNKNOWN
5504 0x0870, // 0870..088E; ARABIC
5505 0x088F, // 088F ; UNKNOWN
5506 0x0890, // 0890..0891; ARABIC
5507 0x0892, // 0892..0897; UNKNOWN
5508 0x0898, // 0898..08E1; ARABIC
5509 0x08E2, // 08E2 ; COMMON
5510 0x08E3, // 08E3..08FF; ARABIC
5511 0x0900, // 0900..0950; DEVANAGARI
5512 0x0951, // 0951..0954; INHERITED
5513 0x0955, // 0955..0963; DEVANAGARI
5514 0x0964, // 0964..0965; COMMON
5515 0x0966, // 0966..097F; DEVANAGARI
5516 0x0980, // 0980..0983; BENGALI
5517 0x0984, // 0984 ; UNKNOWN
5518 0x0985, // 0985..098C; BENGALI
5519 0x098D, // 098D..098E; UNKNOWN
5520 0x098F, // 098F..0990; BENGALI
5521 0x0991, // 0991..0992; UNKNOWN
5522 0x0993, // 0993..09A8; BENGALI
5523 0x09A9, // 09A9 ; UNKNOWN
5524 0x09AA, // 09AA..09B0; BENGALI
5525 0x09B1, // 09B1 ; UNKNOWN
5526 0x09B2, // 09B2 ; BENGALI
5527 0x09B3, // 09B3..09B5; UNKNOWN
5528 0x09B6, // 09B6..09B9; BENGALI
5529 0x09BA, // 09BA..09BB; UNKNOWN
5530 0x09BC, // 09BC..09C4; BENGALI
5531 0x09C5, // 09C5..09C6; UNKNOWN
5532 0x09C7, // 09C7..09C8; BENGALI
5533 0x09C9, // 09C9..09CA; UNKNOWN
5534 0x09CB, // 09CB..09CE; BENGALI
5535 0x09CF, // 09CF..09D6; UNKNOWN
5536 0x09D7, // 09D7 ; BENGALI
5537 0x09D8, // 09D8..09DB; UNKNOWN
5538 0x09DC, // 09DC..09DD; BENGALI
5539 0x09DE, // 09DE ; UNKNOWN
5540 0x09DF, // 09DF..09E3; BENGALI
5541 0x09E4, // 09E4..09E5; UNKNOWN
5542 0x09E6, // 09E6..09FE; BENGALI
5543 0x09FF, // 09FF..0A00; UNKNOWN
5544 0x0A01, // 0A01..0A03; GURMUKHI
5545 0x0A04, // 0A04 ; UNKNOWN
5546 0x0A05, // 0A05..0A0A; GURMUKHI
5547 0x0A0B, // 0A0B..0A0E; UNKNOWN
5548 0x0A0F, // 0A0F..0A10; GURMUKHI
5549 0x0A11, // 0A11..0A12; UNKNOWN
5550 0x0A13, // 0A13..0A28; GURMUKHI
5551 0x0A29, // 0A29 ; UNKNOWN
5552 0x0A2A, // 0A2A..0A30; GURMUKHI
5553 0x0A31, // 0A31 ; UNKNOWN
5554 0x0A32, // 0A32..0A33; GURMUKHI
5555 0x0A34, // 0A34 ; UNKNOWN
5556 0x0A35, // 0A35..0A36; GURMUKHI
5557 0x0A37, // 0A37 ; UNKNOWN
5558 0x0A38, // 0A38..0A39; GURMUKHI
5559 0x0A3A, // 0A3A..0A3B; UNKNOWN
5560 0x0A3C, // 0A3C ; GURMUKHI
5561 0x0A3D, // 0A3D ; UNKNOWN
5562 0x0A3E, // 0A3E..0A42; GURMUKHI
5563 0x0A43, // 0A43..0A46; UNKNOWN
5564 0x0A47, // 0A47..0A48; GURMUKHI
5565 0x0A49, // 0A49..0A4A; UNKNOWN
5566 0x0A4B, // 0A4B..0A4D; GURMUKHI
5567 0x0A4E, // 0A4E..0A50; UNKNOWN
5568 0x0A51, // 0A51 ; GURMUKHI
5569 0x0A52, // 0A52..0A58; UNKNOWN
5570 0x0A59, // 0A59..0A5C; GURMUKHI
5571 0x0A5D, // 0A5D ; UNKNOWN
5572 0x0A5E, // 0A5E ; GURMUKHI
5573 0x0A5F, // 0A5F..0A65; UNKNOWN
5574 0x0A66, // 0A66..0A76; GURMUKHI
5575 0x0A77, // 0A77..0A80; UNKNOWN
5576 0x0A81, // 0A81..0A83; GUJARATI
5577 0x0A84, // 0A84 ; UNKNOWN
5578 0x0A85, // 0A85..0A8D; GUJARATI
5579 0x0A8E, // 0A8E ; UNKNOWN
5580 0x0A8F, // 0A8F..0A91; GUJARATI
5581 0x0A92, // 0A92 ; UNKNOWN
5582 0x0A93, // 0A93..0AA8; GUJARATI
5583 0x0AA9, // 0AA9 ; UNKNOWN
5584 0x0AAA, // 0AAA..0AB0; GUJARATI
5585 0x0AB1, // 0AB1 ; UNKNOWN
5586 0x0AB2, // 0AB2..0AB3; GUJARATI
5587 0x0AB4, // 0AB4 ; UNKNOWN
5588 0x0AB5, // 0AB5..0AB9; GUJARATI
5589 0x0ABA, // 0ABA..0ABB; UNKNOWN
5590 0x0ABC, // 0ABC..0AC5; GUJARATI
5591 0x0AC6, // 0AC6 ; UNKNOWN
5592 0x0AC7, // 0AC7..0AC9; GUJARATI
5593 0x0ACA, // 0ACA ; UNKNOWN
5594 0x0ACB, // 0ACB..0ACD; GUJARATI
5595 0x0ACE, // 0ACE..0ACF; UNKNOWN
5596 0x0AD0, // 0AD0 ; GUJARATI
5597 0x0AD1, // 0AD1..0ADF; UNKNOWN
5598 0x0AE0, // 0AE0..0AE3; GUJARATI
5599 0x0AE4, // 0AE4..0AE5; UNKNOWN
5600 0x0AE6, // 0AE6..0AF1; GUJARATI
5601 0x0AF2, // 0AF2..0AF8; UNKNOWN
5602 0x0AF9, // 0AF9..0AFF; GUJARATI
5603 0x0B00, // 0B00 ; UNKNOWN
5604 0x0B01, // 0B01..0B03; ORIYA
5605 0x0B04, // 0B04 ; UNKNOWN
5606 0x0B05, // 0B05..0B0C; ORIYA
5607 0x0B0D, // 0B0D..0B0E; UNKNOWN
5608 0x0B0F, // 0B0F..0B10; ORIYA
5609 0x0B11, // 0B11..0B12; UNKNOWN
5610 0x0B13, // 0B13..0B28; ORIYA
5611 0x0B29, // 0B29 ; UNKNOWN
5612 0x0B2A, // 0B2A..0B30; ORIYA
5613 0x0B31, // 0B31 ; UNKNOWN
5614 0x0B32, // 0B32..0B33; ORIYA
5615 0x0B34, // 0B34 ; UNKNOWN
5616 0x0B35, // 0B35..0B39; ORIYA
5617 0x0B3A, // 0B3A..0B3B; UNKNOWN
5618 0x0B3C, // 0B3C..0B44; ORIYA
5619 0x0B45, // 0B45..0B46; UNKNOWN
5620 0x0B47, // 0B47..0B48; ORIYA
5621 0x0B49, // 0B49..0B4A; UNKNOWN
5622 0x0B4B, // 0B4B..0B4D; ORIYA
5623 0x0B4E, // 0B4E..0B54; UNKNOWN
5624 0x0B55, // 0B55..0B57; ORIYA
5625 0x0B58, // 0B58..0B5B; UNKNOWN
5626 0x0B5C, // 0B5C..0B5D; ORIYA
5627 0x0B5E, // 0B5E ; UNKNOWN
5628 0x0B5F, // 0B5F..0B63; ORIYA
5629 0x0B64, // 0B64..0B65; UNKNOWN
5630 0x0B66, // 0B66..0B77; ORIYA
5631 0x0B78, // 0B78..0B81; UNKNOWN
5632 0x0B82, // 0B82..0B83; TAMIL
5633 0x0B84, // 0B84 ; UNKNOWN
5634 0x0B85, // 0B85..0B8A; TAMIL
5635 0x0B8B, // 0B8B..0B8D; UNKNOWN
5636 0x0B8E, // 0B8E..0B90; TAMIL
5637 0x0B91, // 0B91 ; UNKNOWN
5638 0x0B92, // 0B92..0B95; TAMIL
5639 0x0B96, // 0B96..0B98; UNKNOWN
5640 0x0B99, // 0B99..0B9A; TAMIL
5641 0x0B9B, // 0B9B ; UNKNOWN
5642 0x0B9C, // 0B9C ; TAMIL
5643 0x0B9D, // 0B9D ; UNKNOWN
5644 0x0B9E, // 0B9E..0B9F; TAMIL
5645 0x0BA0, // 0BA0..0BA2; UNKNOWN
5646 0x0BA3, // 0BA3..0BA4; TAMIL
5647 0x0BA5, // 0BA5..0BA7; UNKNOWN
5648 0x0BA8, // 0BA8..0BAA; TAMIL
5649 0x0BAB, // 0BAB..0BAD; UNKNOWN
5650 0x0BAE, // 0BAE..0BB9; TAMIL
5651 0x0BBA, // 0BBA..0BBD; UNKNOWN
5652 0x0BBE, // 0BBE..0BC2; TAMIL
5653 0x0BC3, // 0BC3..0BC5; UNKNOWN
5654 0x0BC6, // 0BC6..0BC8; TAMIL
5655 0x0BC9, // 0BC9 ; UNKNOWN
5656 0x0BCA, // 0BCA..0BCD; TAMIL
5657 0x0BCE, // 0BCE..0BCF; UNKNOWN
5658 0x0BD0, // 0BD0 ; TAMIL
5659 0x0BD1, // 0BD1..0BD6; UNKNOWN
5660 0x0BD7, // 0BD7 ; TAMIL
5661 0x0BD8, // 0BD8..0BE5; UNKNOWN
5662 0x0BE6, // 0BE6..0BFA; TAMIL
5663 0x0BFB, // 0BFB..0BFF; UNKNOWN
5664 0x0C00, // 0C00..0C0C; TELUGU
5665 0x0C0D, // 0C0D ; UNKNOWN
5666 0x0C0E, // 0C0E..0C10; TELUGU
5667 0x0C11, // 0C11 ; UNKNOWN
5668 0x0C12, // 0C12..0C28; TELUGU
5669 0x0C29, // 0C29 ; UNKNOWN
5670 0x0C2A, // 0C2A..0C39; TELUGU
5671 0x0C3A, // 0C3A..0C3B; UNKNOWN
5672 0x0C3C, // 0C3C..0C44; TELUGU
5673 0x0C45, // 0C45 ; UNKNOWN
5674 0x0C46, // 0C46..0C48; TELUGU
5675 0x0C49, // 0C49 ; UNKNOWN
5676 0x0C4A, // 0C4A..0C4D; TELUGU
5677 0x0C4E, // 0C4E..0C54; UNKNOWN
5678 0x0C55, // 0C55..0C56; TELUGU
5679 0x0C57, // 0C57 ; UNKNOWN
5680 0x0C58, // 0C58..0C5A; TELUGU
5681 0x0C5B, // 0C5B..0C5C; UNKNOWN
5682 0x0C5D, // 0C5D ; TELUGU
5683 0x0C5E, // 0C5E..0C5F; UNKNOWN
5684 0x0C60, // 0C60..0C63; TELUGU
5685 0x0C64, // 0C64..0C65; UNKNOWN
5686 0x0C66, // 0C66..0C6F; TELUGU
5687 0x0C70, // 0C70..0C76; UNKNOWN
5688 0x0C77, // 0C77..0C7F; TELUGU
5689 0x0C80, // 0C80..0C8C; KANNADA
5690 0x0C8D, // 0C8D ; UNKNOWN
5691 0x0C8E, // 0C8E..0C90; KANNADA
5692 0x0C91, // 0C91 ; UNKNOWN
5693 0x0C92, // 0C92..0CA8; KANNADA
5694 0x0CA9, // 0CA9 ; UNKNOWN
5695 0x0CAA, // 0CAA..0CB3; KANNADA
5696 0x0CB4, // 0CB4 ; UNKNOWN
5697 0x0CB5, // 0CB5..0CB9; KANNADA
5698 0x0CBA, // 0CBA..0CBB; UNKNOWN
5699 0x0CBC, // 0CBC..0CC4; KANNADA
5700 0x0CC5, // 0CC5 ; UNKNOWN
5701 0x0CC6, // 0CC6..0CC8; KANNADA
5702 0x0CC9, // 0CC9 ; UNKNOWN
5703 0x0CCA, // 0CCA..0CCD; KANNADA
5704 0x0CCE, // 0CCE..0CD4; UNKNOWN
5705 0x0CD5, // 0CD5..0CD6; KANNADA
5706 0x0CD7, // 0CD7..0CDC; UNKNOWN
5707 0x0CDD, // 0CDD..0CDE; KANNADA
5708 0x0CDF, // 0CDF ; UNKNOWN
5709 0x0CE0, // 0CE0..0CE3; KANNADA
5710 0x0CE4, // 0CE4..0CE5; UNKNOWN
5711 0x0CE6, // 0CE6..0CEF; KANNADA
5712 0x0CF0, // 0CF0 ; UNKNOWN
5713 0x0CF1, // 0CF1..0CF3; KANNADA
5714 0x0CF4, // 0CF4..0CFF; UNKNOWN
5715 0x0D00, // 0D00..0D0C; MALAYALAM
5716 0x0D0D, // 0D0D ; UNKNOWN
5717 0x0D0E, // 0D0E..0D10; MALAYALAM
5718 0x0D11, // 0D11 ; UNKNOWN
5719 0x0D12, // 0D12..0D44; MALAYALAM
5720 0x0D45, // 0D45 ; UNKNOWN
5721 0x0D46, // 0D46..0D48; MALAYALAM
5722 0x0D49, // 0D49 ; UNKNOWN
5723 0x0D4A, // 0D4A..0D4F; MALAYALAM
5724 0x0D50, // 0D50..0D53; UNKNOWN
5725 0x0D54, // 0D54..0D63; MALAYALAM
5726 0x0D64, // 0D64..0D65; UNKNOWN
5727 0x0D66, // 0D66..0D7F; MALAYALAM
5728 0x0D80, // 0D80 ; UNKNOWN
5729 0x0D81, // 0D81..0D83; SINHALA
5730 0x0D84, // 0D84 ; UNKNOWN
5731 0x0D85, // 0D85..0D96; SINHALA
5732 0x0D97, // 0D97..0D99; UNKNOWN
5733 0x0D9A, // 0D9A..0DB1; SINHALA
5734 0x0DB2, // 0DB2 ; UNKNOWN
5735 0x0DB3, // 0DB3..0DBB; SINHALA
5736 0x0DBC, // 0DBC ; UNKNOWN
5737 0x0DBD, // 0DBD ; SINHALA
5738 0x0DBE, // 0DBE..0DBF; UNKNOWN
5739 0x0DC0, // 0DC0..0DC6; SINHALA
5740 0x0DC7, // 0DC7..0DC9; UNKNOWN
5741 0x0DCA, // 0DCA ; SINHALA
5742 0x0DCB, // 0DCB..0DCE; UNKNOWN
5743 0x0DCF, // 0DCF..0DD4; SINHALA
5744 0x0DD5, // 0DD5 ; UNKNOWN
5745 0x0DD6, // 0DD6 ; SINHALA
5746 0x0DD7, // 0DD7 ; UNKNOWN
5747 0x0DD8, // 0DD8..0DDF; SINHALA
5748 0x0DE0, // 0DE0..0DE5; UNKNOWN
5749 0x0DE6, // 0DE6..0DEF; SINHALA
5750 0x0DF0, // 0DF0..0DF1; UNKNOWN
5751 0x0DF2, // 0DF2..0DF4; SINHALA
5752 0x0DF5, // 0DF5..0E00; UNKNOWN
5753 0x0E01, // 0E01..0E3A; THAI
5754 0x0E3B, // 0E3B..0E3E; UNKNOWN
5755 0x0E3F, // 0E3F ; COMMON
5756 0x0E40, // 0E40..0E5B; THAI
5757 0x0E5C, // 0E5C..0E80; UNKNOWN
5758 0x0E81, // 0E81..0E82; LAO
5759 0x0E83, // 0E83 ; UNKNOWN
5760 0x0E84, // 0E84 ; LAO
5761 0x0E85, // 0E85 ; UNKNOWN
5762 0x0E86, // 0E86..0E8A; LAO
5763 0x0E8B, // 0E8B ; UNKNOWN
5764 0x0E8C, // 0E8C..0EA3; LAO
5765 0x0EA4, // 0EA4 ; UNKNOWN
5766 0x0EA5, // 0EA5 ; LAO
5767 0x0EA6, // 0EA6 ; UNKNOWN
5768 0x0EA7, // 0EA7..0EBD; LAO
5769 0x0EBE, // 0EBE..0EBF; UNKNOWN
5770 0x0EC0, // 0EC0..0EC4; LAO
5771 0x0EC5, // 0EC5 ; UNKNOWN
5772 0x0EC6, // 0EC6 ; LAO
5773 0x0EC7, // 0EC7 ; UNKNOWN
5774 0x0EC8, // 0EC8..0ECE; LAO
5775 0x0ECF, // 0ECF ; UNKNOWN
5776 0x0ED0, // 0ED0..0ED9; LAO
5777 0x0EDA, // 0EDA..0EDB; UNKNOWN
5778 0x0EDC, // 0EDC..0EDF; LAO
5779 0x0EE0, // 0EE0..0EFF; UNKNOWN
5780 0x0F00, // 0F00..0F47; TIBETAN
5781 0x0F48, // 0F48 ; UNKNOWN
5782 0x0F49, // 0F49..0F6C; TIBETAN
5783 0x0F6D, // 0F6D..0F70; UNKNOWN
5784 0x0F71, // 0F71..0F97; TIBETAN
5785 0x0F98, // 0F98 ; UNKNOWN
5786 0x0F99, // 0F99..0FBC; TIBETAN
5787 0x0FBD, // 0FBD ; UNKNOWN
5788 0x0FBE, // 0FBE..0FCC; TIBETAN
5789 0x0FCD, // 0FCD ; UNKNOWN
5790 0x0FCE, // 0FCE..0FD4; TIBETAN
5791 0x0FD5, // 0FD5..0FD8; COMMON
5792 0x0FD9, // 0FD9..0FDA; TIBETAN
5793 0x0FDB, // 0FDB..0FFF; UNKNOWN
5794 0x1000, // 1000..109F; MYANMAR
5795 0x10A0, // 10A0..10C5; GEORGIAN
5796 0x10C6, // 10C6 ; UNKNOWN
5797 0x10C7, // 10C7 ; GEORGIAN
5798 0x10C8, // 10C8..10CC; UNKNOWN
5799 0x10CD, // 10CD ; GEORGIAN
5800 0x10CE, // 10CE..10CF; UNKNOWN
5801 0x10D0, // 10D0..10FA; GEORGIAN
5802 0x10FB, // 10FB ; COMMON
5803 0x10FC, // 10FC..10FF; GEORGIAN
5804 0x1100, // 1100..11FF; HANGUL
5805 0x1200, // 1200..1248; ETHIOPIC
5806 0x1249, // 1249 ; UNKNOWN
5807 0x124A, // 124A..124D; ETHIOPIC
5808 0x124E, // 124E..124F; UNKNOWN
5809 0x1250, // 1250..1256; ETHIOPIC
5810 0x1257, // 1257 ; UNKNOWN
5811 0x1258, // 1258 ; ETHIOPIC
5812 0x1259, // 1259 ; UNKNOWN
5813 0x125A, // 125A..125D; ETHIOPIC
5814 0x125E, // 125E..125F; UNKNOWN
5815 0x1260, // 1260..1288; ETHIOPIC
5816 0x1289, // 1289 ; UNKNOWN
5817 0x128A, // 128A..128D; ETHIOPIC
5818 0x128E, // 128E..128F; UNKNOWN
5819 0x1290, // 1290..12B0; ETHIOPIC
5820 0x12B1, // 12B1 ; UNKNOWN
5821 0x12B2, // 12B2..12B5; ETHIOPIC
5822 0x12B6, // 12B6..12B7; UNKNOWN
5823 0x12B8, // 12B8..12BE; ETHIOPIC
5824 0x12BF, // 12BF ; UNKNOWN
5825 0x12C0, // 12C0 ; ETHIOPIC
5826 0x12C1, // 12C1 ; UNKNOWN
5827 0x12C2, // 12C2..12C5; ETHIOPIC
5828 0x12C6, // 12C6..12C7; UNKNOWN
5829 0x12C8, // 12C8..12D6; ETHIOPIC
5830 0x12D7, // 12D7 ; UNKNOWN
5831 0x12D8, // 12D8..1310; ETHIOPIC
5832 0x1311, // 1311 ; UNKNOWN
5833 0x1312, // 1312..1315; ETHIOPIC
5834 0x1316, // 1316..1317; UNKNOWN
5835 0x1318, // 1318..135A; ETHIOPIC
5836 0x135B, // 135B..135C; UNKNOWN
5837 0x135D, // 135D..137C; ETHIOPIC
5838 0x137D, // 137D..137F; UNKNOWN
5839 0x1380, // 1380..1399; ETHIOPIC
5840 0x139A, // 139A..139F; UNKNOWN
5841 0x13A0, // 13A0..13F5; CHEROKEE
5842 0x13F6, // 13F6..13F7; UNKNOWN
5843 0x13F8, // 13F8..13FD; CHEROKEE
5844 0x13FE, // 13FE..13FF; UNKNOWN
5845 0x1400, // 1400..167F; CANADIAN_ABORIGINAL
5846 0x1680, // 1680..169C; OGHAM
5847 0x169D, // 169D..169F; UNKNOWN
5848 0x16A0, // 16A0..16EA; RUNIC
5849 0x16EB, // 16EB..16ED; COMMON
5850 0x16EE, // 16EE..16F8; RUNIC
5851 0x16F9, // 16F9..16FF; UNKNOWN
5852 0x1700, // 1700..1715; TAGALOG
5853 0x1716, // 1716..171E; UNKNOWN
5854 0x171F, // 171F ; TAGALOG
5855 0x1720, // 1720..1734; HANUNOO
5856 0x1735, // 1735..1736; COMMON
5857 0x1737, // 1737..173F; UNKNOWN
5858 0x1740, // 1740..1753; BUHID
5859 0x1754, // 1754..175F; UNKNOWN
5860 0x1760, // 1760..176C; TAGBANWA
5861 0x176D, // 176D ; UNKNOWN
5862 0x176E, // 176E..1770; TAGBANWA
5863 0x1771, // 1771 ; UNKNOWN
5864 0x1772, // 1772..1773; TAGBANWA
5865 0x1774, // 1774..177F; UNKNOWN
5866 0x1780, // 1780..17DD; KHMER
5867 0x17DE, // 17DE..17DF; UNKNOWN
5868 0x17E0, // 17E0..17E9; KHMER
5869 0x17EA, // 17EA..17EF; UNKNOWN
5870 0x17F0, // 17F0..17F9; KHMER
5871 0x17FA, // 17FA..17FF; UNKNOWN
5872 0x1800, // 1800..1801; MONGOLIAN
5873 0x1802, // 1802..1803; COMMON
5874 0x1804, // 1804 ; MONGOLIAN
5875 0x1805, // 1805 ; COMMON
5876 0x1806, // 1806..1819; MONGOLIAN
5877 0x181A, // 181A..181F; UNKNOWN
5878 0x1820, // 1820..1878; MONGOLIAN
5879 0x1879, // 1879..187F; UNKNOWN
5880 0x1880, // 1880..18AA; MONGOLIAN
5881 0x18AB, // 18AB..18AF; UNKNOWN
5882 0x18B0, // 18B0..18F5; CANADIAN_ABORIGINAL
5883 0x18F6, // 18F6..18FF; UNKNOWN
5884 0x1900, // 1900..191E; LIMBU
5885 0x191F, // 191F ; UNKNOWN
5886 0x1920, // 1920..192B; LIMBU
5887 0x192C, // 192C..192F; UNKNOWN
5888 0x1930, // 1930..193B; LIMBU
5889 0x193C, // 193C..193F; UNKNOWN
5890 0x1940, // 1940 ; LIMBU
5891 0x1941, // 1941..1943; UNKNOWN
5892 0x1944, // 1944..194F; LIMBU
5893 0x1950, // 1950..196D; TAI_LE
5894 0x196E, // 196E..196F; UNKNOWN
5895 0x1970, // 1970..1974; TAI_LE
5896 0x1975, // 1975..197F; UNKNOWN
5897 0x1980, // 1980..19AB; NEW_TAI_LUE
5898 0x19AC, // 19AC..19AF; UNKNOWN
5899 0x19B0, // 19B0..19C9; NEW_TAI_LUE
5900 0x19CA, // 19CA..19CF; UNKNOWN
5901 0x19D0, // 19D0..19DA; NEW_TAI_LUE
5902 0x19DB, // 19DB..19DD; UNKNOWN
5903 0x19DE, // 19DE..19DF; NEW_TAI_LUE
5904 0x19E0, // 19E0..19FF; KHMER
5905 0x1A00, // 1A00..1A1B; BUGINESE
5906 0x1A1C, // 1A1C..1A1D; UNKNOWN
5907 0x1A1E, // 1A1E..1A1F; BUGINESE
5908 0x1A20, // 1A20..1A5E; TAI_THAM
5909 0x1A5F, // 1A5F ; UNKNOWN
5910 0x1A60, // 1A60..1A7C; TAI_THAM
5911 0x1A7D, // 1A7D..1A7E; UNKNOWN
5912 0x1A7F, // 1A7F..1A89; TAI_THAM
5913 0x1A8A, // 1A8A..1A8F; UNKNOWN
5914 0x1A90, // 1A90..1A99; TAI_THAM
5915 0x1A9A, // 1A9A..1A9F; UNKNOWN
5916 0x1AA0, // 1AA0..1AAD; TAI_THAM
5917 0x1AAE, // 1AAE..1AAF; UNKNOWN
5918 0x1AB0, // 1AB0..1ACE; INHERITED
5919 0x1ACF, // 1ACF..1AFF; UNKNOWN
5920 0x1B00, // 1B00..1B4C; BALINESE
5921 0x1B4D, // 1B4D..1B4F; UNKNOWN
5922 0x1B50, // 1B50..1B7E; BALINESE
5923 0x1B7F, // 1B7F ; UNKNOWN
5924 0x1B80, // 1B80..1BBF; SUNDANESE
5925 0x1BC0, // 1BC0..1BF3; BATAK
5926 0x1BF4, // 1BF4..1BFB; UNKNOWN
5927 0x1BFC, // 1BFC..1BFF; BATAK
5928 0x1C00, // 1C00..1C37; LEPCHA
5929 0x1C38, // 1C38..1C3A; UNKNOWN
5930 0x1C3B, // 1C3B..1C49; LEPCHA
5931 0x1C4A, // 1C4A..1C4C; UNKNOWN
5932 0x1C4D, // 1C4D..1C4F; LEPCHA
5933 0x1C50, // 1C50..1C7F; OL_CHIKI
5934 0x1C80, // 1C80..1C88; CYRILLIC
5935 0x1C89, // 1C89..1C8F; UNKNOWN
5936 0x1C90, // 1C90..1CBA; GEORGIAN
5937 0x1CBB, // 1CBB..1CBC; UNKNOWN
5938 0x1CBD, // 1CBD..1CBF; GEORGIAN
5939 0x1CC0, // 1CC0..1CC7; SUNDANESE
5940 0x1CC8, // 1CC8..1CCF; UNKNOWN
5941 0x1CD0, // 1CD0..1CD2; INHERITED
5942 0x1CD3, // 1CD3 ; COMMON
5943 0x1CD4, // 1CD4..1CE0; INHERITED
5944 0x1CE1, // 1CE1 ; COMMON
5945 0x1CE2, // 1CE2..1CE8; INHERITED
5946 0x1CE9, // 1CE9..1CEC; COMMON
5947 0x1CED, // 1CED ; INHERITED
5948 0x1CEE, // 1CEE..1CF3; COMMON
5949 0x1CF4, // 1CF4 ; INHERITED
5950 0x1CF5, // 1CF5..1CF7; COMMON
5951 0x1CF8, // 1CF8..1CF9; INHERITED
5952 0x1CFA, // 1CFA ; COMMON
5953 0x1CFB, // 1CFB..1CFF; UNKNOWN
5954 0x1D00, // 1D00..1D25; LATIN
5955 0x1D26, // 1D26..1D2A; GREEK
5956 0x1D2B, // 1D2B ; CYRILLIC
5957 0x1D2C, // 1D2C..1D5C; LATIN
5958 0x1D5D, // 1D5D..1D61; GREEK
5959 0x1D62, // 1D62..1D65; LATIN
5960 0x1D66, // 1D66..1D6A; GREEK
5961 0x1D6B, // 1D6B..1D77; LATIN
5962 0x1D78, // 1D78 ; CYRILLIC
5963 0x1D79, // 1D79..1DBE; LATIN
5964 0x1DBF, // 1DBF ; GREEK
5965 0x1DC0, // 1DC0..1DFF; INHERITED
5966 0x1E00, // 1E00..1EFF; LATIN
5967 0x1F00, // 1F00..1F15; GREEK
5968 0x1F16, // 1F16..1F17; UNKNOWN
5969 0x1F18, // 1F18..1F1D; GREEK
5970 0x1F1E, // 1F1E..1F1F; UNKNOWN
5971 0x1F20, // 1F20..1F45; GREEK
5972 0x1F46, // 1F46..1F47; UNKNOWN
5973 0x1F48, // 1F48..1F4D; GREEK
5974 0x1F4E, // 1F4E..1F4F; UNKNOWN
5975 0x1F50, // 1F50..1F57; GREEK
5976 0x1F58, // 1F58 ; UNKNOWN
5977 0x1F59, // 1F59 ; GREEK
5978 0x1F5A, // 1F5A ; UNKNOWN
5979 0x1F5B, // 1F5B ; GREEK
5980 0x1F5C, // 1F5C ; UNKNOWN
5981 0x1F5D, // 1F5D ; GREEK
5982 0x1F5E, // 1F5E ; UNKNOWN
5983 0x1F5F, // 1F5F..1F7D; GREEK
5984 0x1F7E, // 1F7E..1F7F; UNKNOWN
5985 0x1F80, // 1F80..1FB4; GREEK
5986 0x1FB5, // 1FB5 ; UNKNOWN
5987 0x1FB6, // 1FB6..1FC4; GREEK
5988 0x1FC5, // 1FC5 ; UNKNOWN
5989 0x1FC6, // 1FC6..1FD3; GREEK
5990 0x1FD4, // 1FD4..1FD5; UNKNOWN
5991 0x1FD6, // 1FD6..1FDB; GREEK
5992 0x1FDC, // 1FDC ; UNKNOWN
5993 0x1FDD, // 1FDD..1FEF; GREEK
5994 0x1FF0, // 1FF0..1FF1; UNKNOWN
5995 0x1FF2, // 1FF2..1FF4; GREEK
5996 0x1FF5, // 1FF5 ; UNKNOWN
5997 0x1FF6, // 1FF6..1FFE; GREEK
5998 0x1FFF, // 1FFF ; UNKNOWN
5999 0x2000, // 2000..200B; COMMON
6000 0x200C, // 200C..200D; INHERITED
6001 0x200E, // 200E..2064; COMMON
6002 0x2065, // 2065 ; UNKNOWN
6003 0x2066, // 2066..2070; COMMON
6004 0x2071, // 2071 ; LATIN
6005 0x2072, // 2072..2073; UNKNOWN
6006 0x2074, // 2074..207E; COMMON
6007 0x207F, // 207F ; LATIN
6008 0x2080, // 2080..208E; COMMON
6009 0x208F, // 208F ; UNKNOWN
6010 0x2090, // 2090..209C; LATIN
6011 0x209D, // 209D..209F; UNKNOWN
6012 0x20A0, // 20A0..20C0; COMMON
6013 0x20C1, // 20C1..20CF; UNKNOWN
6014 0x20D0, // 20D0..20F0; INHERITED
6015 0x20F1, // 20F1..20FF; UNKNOWN
6016 0x2100, // 2100..2125; COMMON
6017 0x2126, // 2126 ; GREEK
6018 0x2127, // 2127..2129; COMMON
6019 0x212A, // 212A..212B; LATIN
6020 0x212C, // 212C..2131; COMMON
6021 0x2132, // 2132 ; LATIN
6022 0x2133, // 2133..214D; COMMON
6023 0x214E, // 214E ; LATIN
6024 0x214F, // 214F..215F; COMMON
6025 0x2160, // 2160..2188; LATIN
6026 0x2189, // 2189..218B; COMMON
6027 0x218C, // 218C..218F; UNKNOWN
6028 0x2190, // 2190..2426; COMMON
6029 0x2427, // 2427..243F; UNKNOWN
6030 0x2440, // 2440..244A; COMMON
6031 0x244B, // 244B..245F; UNKNOWN
6032 0x2460, // 2460..27FF; COMMON
6033 0x2800, // 2800..28FF; BRAILLE
6034 0x2900, // 2900..2B73; COMMON
6035 0x2B74, // 2B74..2B75; UNKNOWN
6036 0x2B76, // 2B76..2B95; COMMON
6037 0x2B96, // 2B96 ; UNKNOWN
6038 0x2B97, // 2B97..2BFF; COMMON
6039 0x2C00, // 2C00..2C5F; GLAGOLITIC
6040 0x2C60, // 2C60..2C7F; LATIN
6041 0x2C80, // 2C80..2CF3; COPTIC
6042 0x2CF4, // 2CF4..2CF8; UNKNOWN
6043 0x2CF9, // 2CF9..2CFF; COPTIC
6044 0x2D00, // 2D00..2D25; GEORGIAN
6045 0x2D26, // 2D26 ; UNKNOWN
6046 0x2D27, // 2D27 ; GEORGIAN
6047 0x2D28, // 2D28..2D2C; UNKNOWN
6048 0x2D2D, // 2D2D ; GEORGIAN
6049 0x2D2E, // 2D2E..2D2F; UNKNOWN
6050 0x2D30, // 2D30..2D67; TIFINAGH
6051 0x2D68, // 2D68..2D6E; UNKNOWN
6052 0x2D6F, // 2D6F..2D70; TIFINAGH
6053 0x2D71, // 2D71..2D7E; UNKNOWN
6054 0x2D7F, // 2D7F ; TIFINAGH
6055 0x2D80, // 2D80..2D96; ETHIOPIC
6056 0x2D97, // 2D97..2D9F; UNKNOWN
6057 0x2DA0, // 2DA0..2DA6; ETHIOPIC
6058 0x2DA7, // 2DA7 ; UNKNOWN
6059 0x2DA8, // 2DA8..2DAE; ETHIOPIC
6060 0x2DAF, // 2DAF ; UNKNOWN
6061 0x2DB0, // 2DB0..2DB6; ETHIOPIC
6062 0x2DB7, // 2DB7 ; UNKNOWN
6063 0x2DB8, // 2DB8..2DBE; ETHIOPIC
6064 0x2DBF, // 2DBF ; UNKNOWN
6065 0x2DC0, // 2DC0..2DC6; ETHIOPIC
6066 0x2DC7, // 2DC7 ; UNKNOWN
6067 0x2DC8, // 2DC8..2DCE; ETHIOPIC
6068 0x2DCF, // 2DCF ; UNKNOWN
6069 0x2DD0, // 2DD0..2DD6; ETHIOPIC
6070 0x2DD7, // 2DD7 ; UNKNOWN
6071 0x2DD8, // 2DD8..2DDE; ETHIOPIC
6072 0x2DDF, // 2DDF ; UNKNOWN
6073 0x2DE0, // 2DE0..2DFF; CYRILLIC
6074 0x2E00, // 2E00..2E5D; COMMON
6075 0x2E5E, // 2E5E..2E7F; UNKNOWN
6076 0x2E80, // 2E80..2E99; HAN
6077 0x2E9A, // 2E9A ; UNKNOWN
6078 0x2E9B, // 2E9B..2EF3; HAN
6079 0x2EF4, // 2EF4..2EFF; UNKNOWN
6080 0x2F00, // 2F00..2FD5; HAN
6081 0x2FD6, // 2FD6..2FEF; UNKNOWN
6082 0x2FF0, // 2FF0..3004; COMMON
6083 0x3005, // 3005 ; HAN
6084 0x3006, // 3006 ; COMMON
6085 0x3007, // 3007 ; HAN
6086 0x3008, // 3008..3020; COMMON
6087 0x3021, // 3021..3029; HAN
6088 0x302A, // 302A..302D; INHERITED
6089 0x302E, // 302E..302F; HANGUL
6090 0x3030, // 3030..3037; COMMON
6091 0x3038, // 3038..303B; HAN
6092 0x303C, // 303C..303F; COMMON
6093 0x3040, // 3040 ; UNKNOWN
6094 0x3041, // 3041..3096; HIRAGANA
6095 0x3097, // 3097..3098; UNKNOWN
6096 0x3099, // 3099..309A; INHERITED
6097 0x309B, // 309B..309C; COMMON
6098 0x309D, // 309D..309F; HIRAGANA
6099 0x30A0, // 30A0 ; COMMON
6100 0x30A1, // 30A1..30FA; KATAKANA
6101 0x30FB, // 30FB..30FC; COMMON
6102 0x30FD, // 30FD..30FF; KATAKANA
6103 0x3100, // 3100..3104; UNKNOWN
6104 0x3105, // 3105..312F; BOPOMOFO
6105 0x3130, // 3130 ; UNKNOWN
6106 0x3131, // 3131..318E; HANGUL
6107 0x318F, // 318F ; UNKNOWN
6108 0x3190, // 3190..319F; COMMON
6109 0x31A0, // 31A0..31BF; BOPOMOFO
6110 0x31C0, // 31C0..31E3; COMMON
6111 0x31E4, // 31E4..31EE; UNKNOWN
6112 0x31EF, // 31EF ; COMMON
6113 0x31F0, // 31F0..31FF; KATAKANA
6114 0x3200, // 3200..321E; HANGUL
6115 0x321F, // 321F ; UNKNOWN
6116 0x3220, // 3220..325F; COMMON
6117 0x3260, // 3260..327E; HANGUL
6118 0x327F, // 327F..32CF; COMMON
6119 0x32D0, // 32D0..32FE; KATAKANA
6120 0x32FF, // 32FF ; COMMON
6121 0x3300, // 3300..3357; KATAKANA
6122 0x3358, // 3358..33FF; COMMON
6123 0x3400, // 3400..4DBF; HAN
6124 0x4DC0, // 4DC0..4DFF; COMMON
6125 0x4E00, // 4E00..9FFF; HAN
6126 0xA000, // A000..A48C; YI
6127 0xA48D, // A48D..A48F; UNKNOWN
6128 0xA490, // A490..A4C6; YI
6129 0xA4C7, // A4C7..A4CF; UNKNOWN
6130 0xA4D0, // A4D0..A4FF; LISU
6131 0xA500, // A500..A62B; VAI
6132 0xA62C, // A62C..A63F; UNKNOWN
6133 0xA640, // A640..A69F; CYRILLIC
6134 0xA6A0, // A6A0..A6F7; BAMUM
6135 0xA6F8, // A6F8..A6FF; UNKNOWN
6136 0xA700, // A700..A721; COMMON
6137 0xA722, // A722..A787; LATIN
6138 0xA788, // A788..A78A; COMMON
6139 0xA78B, // A78B..A7CA; LATIN
6140 0xA7CB, // A7CB..A7CF; UNKNOWN
6141 0xA7D0, // A7D0..A7D1; LATIN
6142 0xA7D2, // A7D2 ; UNKNOWN
6143 0xA7D3, // A7D3 ; LATIN
6144 0xA7D4, // A7D4 ; UNKNOWN
6145 0xA7D5, // A7D5..A7D9; LATIN
6146 0xA7DA, // A7DA..A7F1; UNKNOWN
6147 0xA7F2, // A7F2..A7FF; LATIN
6148 0xA800, // A800..A82C; SYLOTI_NAGRI
6149 0xA82D, // A82D..A82F; UNKNOWN
6150 0xA830, // A830..A839; COMMON
6151 0xA83A, // A83A..A83F; UNKNOWN
6152 0xA840, // A840..A877; PHAGS_PA
6153 0xA878, // A878..A87F; UNKNOWN
6154 0xA880, // A880..A8C5; SAURASHTRA
6155 0xA8C6, // A8C6..A8CD; UNKNOWN
6156 0xA8CE, // A8CE..A8D9; SAURASHTRA
6157 0xA8DA, // A8DA..A8DF; UNKNOWN
6158 0xA8E0, // A8E0..A8FF; DEVANAGARI
6159 0xA900, // A900..A92D; KAYAH_LI
6160 0xA92E, // A92E ; COMMON
6161 0xA92F, // A92F ; KAYAH_LI
6162 0xA930, // A930..A953; REJANG
6163 0xA954, // A954..A95E; UNKNOWN
6164 0xA95F, // A95F ; REJANG
6165 0xA960, // A960..A97C; HANGUL
6166 0xA97D, // A97D..A97F; UNKNOWN
6167 0xA980, // A980..A9CD; JAVANESE
6168 0xA9CE, // A9CE ; UNKNOWN
6169 0xA9CF, // A9CF ; COMMON
6170 0xA9D0, // A9D0..A9D9; JAVANESE
6171 0xA9DA, // A9DA..A9DD; UNKNOWN
6172 0xA9DE, // A9DE..A9DF; JAVANESE
6173 0xA9E0, // A9E0..A9FE; MYANMAR
6174 0xA9FF, // A9FF ; UNKNOWN
6175 0xAA00, // AA00..AA36; CHAM
6176 0xAA37, // AA37..AA3F; UNKNOWN
6177 0xAA40, // AA40..AA4D; CHAM
6178 0xAA4E, // AA4E..AA4F; UNKNOWN
6179 0xAA50, // AA50..AA59; CHAM
6180 0xAA5A, // AA5A..AA5B; UNKNOWN
6181 0xAA5C, // AA5C..AA5F; CHAM
6182 0xAA60, // AA60..AA7F; MYANMAR
6183 0xAA80, // AA80..AAC2; TAI_VIET
6184 0xAAC3, // AAC3..AADA; UNKNOWN
6185 0xAADB, // AADB..AADF; TAI_VIET
6186 0xAAE0, // AAE0..AAF6; MEETEI_MAYEK
6187 0xAAF7, // AAF7..AB00; UNKNOWN
6188 0xAB01, // AB01..AB06; ETHIOPIC
6189 0xAB07, // AB07..AB08; UNKNOWN
6190 0xAB09, // AB09..AB0E; ETHIOPIC
6191 0xAB0F, // AB0F..AB10; UNKNOWN
6192 0xAB11, // AB11..AB16; ETHIOPIC
6193 0xAB17, // AB17..AB1F; UNKNOWN
6194 0xAB20, // AB20..AB26; ETHIOPIC
6195 0xAB27, // AB27 ; UNKNOWN
6196 0xAB28, // AB28..AB2E; ETHIOPIC
6197 0xAB2F, // AB2F ; UNKNOWN
6198 0xAB30, // AB30..AB5A; LATIN
6199 0xAB5B, // AB5B ; COMMON
6200 0xAB5C, // AB5C..AB64; LATIN
6201 0xAB65, // AB65 ; GREEK
6202 0xAB66, // AB66..AB69; LATIN
6203 0xAB6A, // AB6A..AB6B; COMMON
6204 0xAB6C, // AB6C..AB6F; UNKNOWN
6205 0xAB70, // AB70..ABBF; CHEROKEE
6206 0xABC0, // ABC0..ABED; MEETEI_MAYEK
6207 0xABEE, // ABEE..ABEF; UNKNOWN
6208 0xABF0, // ABF0..ABF9; MEETEI_MAYEK
6209 0xABFA, // ABFA..ABFF; UNKNOWN
6210 0xAC00, // AC00..D7A3; HANGUL
6211 0xD7A4, // D7A4..D7AF; UNKNOWN
6212 0xD7B0, // D7B0..D7C6; HANGUL
6213 0xD7C7, // D7C7..D7CA; UNKNOWN
6214 0xD7CB, // D7CB..D7FB; HANGUL
6215 0xD7FC, // D7FC..F8FF; UNKNOWN
6216 0xF900, // F900..FA6D; HAN
6217 0xFA6E, // FA6E..FA6F; UNKNOWN
6218 0xFA70, // FA70..FAD9; HAN
6219 0xFADA, // FADA..FAFF; UNKNOWN
6220 0xFB00, // FB00..FB06; LATIN
6221 0xFB07, // FB07..FB12; UNKNOWN
6222 0xFB13, // FB13..FB17; ARMENIAN
6223 0xFB18, // FB18..FB1C; UNKNOWN
6224 0xFB1D, // FB1D..FB36; HEBREW
6225 0xFB37, // FB37 ; UNKNOWN
6226 0xFB38, // FB38..FB3C; HEBREW
6227 0xFB3D, // FB3D ; UNKNOWN
6228 0xFB3E, // FB3E ; HEBREW
6229 0xFB3F, // FB3F ; UNKNOWN
6230 0xFB40, // FB40..FB41; HEBREW
6231 0xFB42, // FB42 ; UNKNOWN
6232 0xFB43, // FB43..FB44; HEBREW
6233 0xFB45, // FB45 ; UNKNOWN
6234 0xFB46, // FB46..FB4F; HEBREW
6235 0xFB50, // FB50..FBC2; ARABIC
6236 0xFBC3, // FBC3..FBD2; UNKNOWN
6237 0xFBD3, // FBD3..FD3D; ARABIC
6238 0xFD3E, // FD3E..FD3F; COMMON
6239 0xFD40, // FD40..FD8F; ARABIC
6240 0xFD90, // FD90..FD91; UNKNOWN
6241 0xFD92, // FD92..FDC7; ARABIC
6242 0xFDC8, // FDC8..FDCE; UNKNOWN
6243 0xFDCF, // FDCF ; ARABIC
6244 0xFDD0, // FDD0..FDEF; UNKNOWN
6245 0xFDF0, // FDF0..FDFF; ARABIC
6246 0xFE00, // FE00..FE0F; INHERITED
6247 0xFE10, // FE10..FE19; COMMON
6248 0xFE1A, // FE1A..FE1F; UNKNOWN
6249 0xFE20, // FE20..FE2D; INHERITED
6250 0xFE2E, // FE2E..FE2F; CYRILLIC
6251 0xFE30, // FE30..FE52; COMMON
6252 0xFE53, // FE53 ; UNKNOWN
6253 0xFE54, // FE54..FE66; COMMON
6254 0xFE67, // FE67 ; UNKNOWN
6255 0xFE68, // FE68..FE6B; COMMON
6256 0xFE6C, // FE6C..FE6F; UNKNOWN
6257 0xFE70, // FE70..FE74; ARABIC
6258 0xFE75, // FE75 ; UNKNOWN
6259 0xFE76, // FE76..FEFC; ARABIC
6260 0xFEFD, // FEFD..FEFE; UNKNOWN
6261 0xFEFF, // FEFF ; COMMON
6262 0xFF00, // FF00 ; UNKNOWN
6263 0xFF01, // FF01..FF20; COMMON
6264 0xFF21, // FF21..FF3A; LATIN
6265 0xFF3B, // FF3B..FF40; COMMON
6266 0xFF41, // FF41..FF5A; LATIN
6267 0xFF5B, // FF5B..FF65; COMMON
6268 0xFF66, // FF66..FF6F; KATAKANA
6269 0xFF70, // FF70 ; COMMON
6270 0xFF71, // FF71..FF9D; KATAKANA
6271 0xFF9E, // FF9E..FF9F; COMMON
6272 0xFFA0, // FFA0..FFBE; HANGUL
6273 0xFFBF, // FFBF..FFC1; UNKNOWN
6274 0xFFC2, // FFC2..FFC7; HANGUL
6275 0xFFC8, // FFC8..FFC9; UNKNOWN
6276 0xFFCA, // FFCA..FFCF; HANGUL
6277 0xFFD0, // FFD0..FFD1; UNKNOWN
6278 0xFFD2, // FFD2..FFD7; HANGUL
6279 0xFFD8, // FFD8..FFD9; UNKNOWN
6280 0xFFDA, // FFDA..FFDC; HANGUL
6281 0xFFDD, // FFDD..FFDF; UNKNOWN
6282 0xFFE0, // FFE0..FFE6; COMMON
6283 0xFFE7, // FFE7 ; UNKNOWN
6284 0xFFE8, // FFE8..FFEE; COMMON
6285 0xFFEF, // FFEF..FFF8; UNKNOWN
6286 0xFFF9, // FFF9..FFFD; COMMON
6287 0xFFFE, // FFFE..FFFF; UNKNOWN
6288 0x10000, // 10000..1000B; LINEAR_B
6289 0x1000C, // 1000C ; UNKNOWN
6290 0x1000D, // 1000D..10026; LINEAR_B
6291 0x10027, // 10027 ; UNKNOWN
6292 0x10028, // 10028..1003A; LINEAR_B
6293 0x1003B, // 1003B ; UNKNOWN
6294 0x1003C, // 1003C..1003D; LINEAR_B
6295 0x1003E, // 1003E ; UNKNOWN
6296 0x1003F, // 1003F..1004D; LINEAR_B
6297 0x1004E, // 1004E..1004F; UNKNOWN
6298 0x10050, // 10050..1005D; LINEAR_B
6299 0x1005E, // 1005E..1007F; UNKNOWN
6300 0x10080, // 10080..100FA; LINEAR_B
6301 0x100FB, // 100FB..100FF; UNKNOWN
6302 0x10100, // 10100..10102; COMMON
6303 0x10103, // 10103..10106; UNKNOWN
6304 0x10107, // 10107..10133; COMMON
6305 0x10134, // 10134..10136; UNKNOWN
6306 0x10137, // 10137..1013F; COMMON
6307 0x10140, // 10140..1018E; GREEK
6308 0x1018F, // 1018F ; UNKNOWN
6309 0x10190, // 10190..1019C; COMMON
6310 0x1019D, // 1019D..1019F; UNKNOWN
6311 0x101A0, // 101A0 ; GREEK
6312 0x101A1, // 101A1..101CF; UNKNOWN
6313 0x101D0, // 101D0..101FC; COMMON
6314 0x101FD, // 101FD ; INHERITED
6315 0x101FE, // 101FE..1027F; UNKNOWN
6316 0x10280, // 10280..1029C; LYCIAN
6317 0x1029D, // 1029D..1029F; UNKNOWN
6318 0x102A0, // 102A0..102D0; CARIAN
6319 0x102D1, // 102D1..102DF; UNKNOWN
6320 0x102E0, // 102E0 ; INHERITED
6321 0x102E1, // 102E1..102FB; COMMON
6322 0x102FC, // 102FC..102FF; UNKNOWN
6323 0x10300, // 10300..10323; OLD_ITALIC
6324 0x10324, // 10324..1032C; UNKNOWN
6325 0x1032D, // 1032D..1032F; OLD_ITALIC
6326 0x10330, // 10330..1034A; GOTHIC
6327 0x1034B, // 1034B..1034F; UNKNOWN
6328 0x10350, // 10350..1037A; OLD_PERMIC
6329 0x1037B, // 1037B..1037F; UNKNOWN
6330 0x10380, // 10380..1039D; UGARITIC
6331 0x1039E, // 1039E ; UNKNOWN
6332 0x1039F, // 1039F ; UGARITIC
6333 0x103A0, // 103A0..103C3; OLD_PERSIAN
6334 0x103C4, // 103C4..103C7; UNKNOWN
6335 0x103C8, // 103C8..103D5; OLD_PERSIAN
6336 0x103D6, // 103D6..103FF; UNKNOWN
6337 0x10400, // 10400..1044F; DESERET
6338 0x10450, // 10450..1047F; SHAVIAN
6339 0x10480, // 10480..1049D; OSMANYA
6340 0x1049E, // 1049E..1049F; UNKNOWN
6341 0x104A0, // 104A0..104A9; OSMANYA
6342 0x104AA, // 104AA..104AF; UNKNOWN
6343 0x104B0, // 104B0..104D3; OSAGE
6344 0x104D4, // 104D4..104D7; UNKNOWN
6345 0x104D8, // 104D8..104FB; OSAGE
6346 0x104FC, // 104FC..104FF; UNKNOWN
6347 0x10500, // 10500..10527; ELBASAN
6348 0x10528, // 10528..1052F; UNKNOWN
6349 0x10530, // 10530..10563; CAUCASIAN_ALBANIAN
6350 0x10564, // 10564..1056E; UNKNOWN
6351 0x1056F, // 1056F ; CAUCASIAN_ALBANIAN
6352 0x10570, // 10570..1057A; VITHKUQI
6353 0x1057B, // 1057B ; UNKNOWN
6354 0x1057C, // 1057C..1058A; VITHKUQI
6355 0x1058B, // 1058B ; UNKNOWN
6356 0x1058C, // 1058C..10592; VITHKUQI
6357 0x10593, // 10593 ; UNKNOWN
6358 0x10594, // 10594..10595; VITHKUQI
6359 0x10596, // 10596 ; UNKNOWN
6360 0x10597, // 10597..105A1; VITHKUQI
6361 0x105A2, // 105A2 ; UNKNOWN
6362 0x105A3, // 105A3..105B1; VITHKUQI
6363 0x105B2, // 105B2 ; UNKNOWN
6364 0x105B3, // 105B3..105B9; VITHKUQI
6365 0x105BA, // 105BA ; UNKNOWN
6366 0x105BB, // 105BB..105BC; VITHKUQI
6367 0x105BD, // 105BD..105FF; UNKNOWN
6368 0x10600, // 10600..10736; LINEAR_A
6369 0x10737, // 10737..1073F; UNKNOWN
6370 0x10740, // 10740..10755; LINEAR_A
6371 0x10756, // 10756..1075F; UNKNOWN
6372 0x10760, // 10760..10767; LINEAR_A
6373 0x10768, // 10768..1077F; UNKNOWN
6374 0x10780, // 10780..10785; LATIN
6375 0x10786, // 10786 ; UNKNOWN
6376 0x10787, // 10787..107B0; LATIN
6377 0x107B1, // 107B1 ; UNKNOWN
6378 0x107B2, // 107B2..107BA; LATIN
6379 0x107BB, // 107BB..107FF; UNKNOWN
6380 0x10800, // 10800..10805; CYPRIOT
6381 0x10806, // 10806..10807; UNKNOWN
6382 0x10808, // 10808 ; CYPRIOT
6383 0x10809, // 10809 ; UNKNOWN
6384 0x1080A, // 1080A..10835; CYPRIOT
6385 0x10836, // 10836 ; UNKNOWN
6386 0x10837, // 10837..10838; CYPRIOT
6387 0x10839, // 10839..1083B; UNKNOWN
6388 0x1083C, // 1083C ; CYPRIOT
6389 0x1083D, // 1083D..1083E; UNKNOWN
6390 0x1083F, // 1083F ; CYPRIOT
6391 0x10840, // 10840..10855; IMPERIAL_ARAMAIC
6392 0x10856, // 10856 ; UNKNOWN
6393 0x10857, // 10857..1085F; IMPERIAL_ARAMAIC
6394 0x10860, // 10860..1087F; PALMYRENE
6395 0x10880, // 10880..1089E; NABATAEAN
6396 0x1089F, // 1089F..108A6; UNKNOWN
6397 0x108A7, // 108A7..108AF; NABATAEAN
6398 0x108B0, // 108B0..108DF; UNKNOWN
6399 0x108E0, // 108E0..108F2; HATRAN
6400 0x108F3, // 108F3 ; UNKNOWN
6401 0x108F4, // 108F4..108F5; HATRAN
6402 0x108F6, // 108F6..108FA; UNKNOWN
6403 0x108FB, // 108FB..108FF; HATRAN
6404 0x10900, // 10900..1091B; PHOENICIAN
6405 0x1091C, // 1091C..1091E; UNKNOWN
6406 0x1091F, // 1091F ; PHOENICIAN
6407 0x10920, // 10920..10939; LYDIAN
6408 0x1093A, // 1093A..1093E; UNKNOWN
6409 0x1093F, // 1093F ; LYDIAN
6410 0x10940, // 10940..1097F; UNKNOWN
6411 0x10980, // 10980..1099F; MEROITIC_HIEROGLYPHS
6412 0x109A0, // 109A0..109B7; MEROITIC_CURSIVE
6413 0x109B8, // 109B8..109BB; UNKNOWN
6414 0x109BC, // 109BC..109CF; MEROITIC_CURSIVE
6415 0x109D0, // 109D0..109D1; UNKNOWN
6416 0x109D2, // 109D2..109FF; MEROITIC_CURSIVE
6417 0x10A00, // 10A00..10A03; KHAROSHTHI
6418 0x10A04, // 10A04 ; UNKNOWN
6419 0x10A05, // 10A05..10A06; KHAROSHTHI
6420 0x10A07, // 10A07..10A0B; UNKNOWN
6421 0x10A0C, // 10A0C..10A13; KHAROSHTHI
6422 0x10A14, // 10A14 ; UNKNOWN
6423 0x10A15, // 10A15..10A17; KHAROSHTHI
6424 0x10A18, // 10A18 ; UNKNOWN
6425 0x10A19, // 10A19..10A35; KHAROSHTHI
6426 0x10A36, // 10A36..10A37; UNKNOWN
6427 0x10A38, // 10A38..10A3A; KHAROSHTHI
6428 0x10A3B, // 10A3B..10A3E; UNKNOWN
6429 0x10A3F, // 10A3F..10A48; KHAROSHTHI
6430 0x10A49, // 10A49..10A4F; UNKNOWN
6431 0x10A50, // 10A50..10A58; KHAROSHTHI
6432 0x10A59, // 10A59..10A5F; UNKNOWN
6433 0x10A60, // 10A60..10A7F; OLD_SOUTH_ARABIAN
6434 0x10A80, // 10A80..10A9F; OLD_NORTH_ARABIAN
6435 0x10AA0, // 10AA0..10ABF; UNKNOWN
6436 0x10AC0, // 10AC0..10AE6; MANICHAEAN
6437 0x10AE7, // 10AE7..10AEA; UNKNOWN
6438 0x10AEB, // 10AEB..10AF6; MANICHAEAN
6439 0x10AF7, // 10AF7..10AFF; UNKNOWN
6440 0x10B00, // 10B00..10B35; AVESTAN
6441 0x10B36, // 10B36..10B38; UNKNOWN
6442 0x10B39, // 10B39..10B3F; AVESTAN
6443 0x10B40, // 10B40..10B55; INSCRIPTIONAL_PARTHIAN
6444 0x10B56, // 10B56..10B57; UNKNOWN
6445 0x10B58, // 10B58..10B5F; INSCRIPTIONAL_PARTHIAN
6446 0x10B60, // 10B60..10B72; INSCRIPTIONAL_PAHLAVI
6447 0x10B73, // 10B73..10B77; UNKNOWN
6448 0x10B78, // 10B78..10B7F; INSCRIPTIONAL_PAHLAVI
6449 0x10B80, // 10B80..10B91; PSALTER_PAHLAVI
6450 0x10B92, // 10B92..10B98; UNKNOWN
6451 0x10B99, // 10B99..10B9C; PSALTER_PAHLAVI
6452 0x10B9D, // 10B9D..10BA8; UNKNOWN
6453 0x10BA9, // 10BA9..10BAF; PSALTER_PAHLAVI
6454 0x10BB0, // 10BB0..10BFF; UNKNOWN
6455 0x10C00, // 10C00..10C48; OLD_TURKIC
6456 0x10C49, // 10C49..10C7F; UNKNOWN
6457 0x10C80, // 10C80..10CB2; OLD_HUNGARIAN
6458 0x10CB3, // 10CB3..10CBF; UNKNOWN
6459 0x10CC0, // 10CC0..10CF2; OLD_HUNGARIAN
6460 0x10CF3, // 10CF3..10CF9; UNKNOWN
6461 0x10CFA, // 10CFA..10CFF; OLD_HUNGARIAN
6462 0x10D00, // 10D00..10D27; HANIFI_ROHINGYA
6463 0x10D28, // 10D28..10D2F; UNKNOWN
6464 0x10D30, // 10D30..10D39; HANIFI_ROHINGYA
6465 0x10D3A, // 10D3A..10E5F; UNKNOWN
6466 0x10E60, // 10E60..10E7E; ARABIC
6467 0x10E7F, // 10E7F ; UNKNOWN
6468 0x10E80, // 10E80..10EA9; YEZIDI
6469 0x10EAA, // 10EAA ; UNKNOWN
6470 0x10EAB, // 10EAB..10EAD; YEZIDI
6471 0x10EAE, // 10EAE..10EAF; UNKNOWN
6472 0x10EB0, // 10EB0..10EB1; YEZIDI
6473 0x10EB2, // 10EB2..10EFC; UNKNOWN
6474 0x10EFD, // 10EFD..10EFF; ARABIC
6475 0x10F00, // 10F00..10F27; OLD_SOGDIAN
6476 0x10F28, // 10F28..10F2F; UNKNOWN
6477 0x10F30, // 10F30..10F59; SOGDIAN
6478 0x10F5A, // 10F5A..10F6F; UNKNOWN
6479 0x10F70, // 10F70..10F89; OLD_UYGHUR
6480 0x10F8A, // 10F8A..10FAF; UNKNOWN
6481 0x10FB0, // 10FB0..10FCB; CHORASMIAN
6482 0x10FCC, // 10FCC..10FDF; UNKNOWN
6483 0x10FE0, // 10FE0..10FF6; ELYMAIC
6484 0x10FF7, // 10FF7..10FFF; UNKNOWN
6485 0x11000, // 11000..1104D; BRAHMI
6486 0x1104E, // 1104E..11051; UNKNOWN
6487 0x11052, // 11052..11075; BRAHMI
6488 0x11076, // 11076..1107E; UNKNOWN
6489 0x1107F, // 1107F ; BRAHMI
6490 0x11080, // 11080..110C2; KAITHI
6491 0x110C3, // 110C3..110CC; UNKNOWN
6492 0x110CD, // 110CD ; KAITHI
6493 0x110CE, // 110CE..110CF; UNKNOWN
6494 0x110D0, // 110D0..110E8; SORA_SOMPENG
6495 0x110E9, // 110E9..110EF; UNKNOWN
6496 0x110F0, // 110F0..110F9; SORA_SOMPENG
6497 0x110FA, // 110FA..110FF; UNKNOWN
6498 0x11100, // 11100..11134; CHAKMA
6499 0x11135, // 11135 ; UNKNOWN
6500 0x11136, // 11136..11147; CHAKMA
6501 0x11148, // 11148..1114F; UNKNOWN
6502 0x11150, // 11150..11176; MAHAJANI
6503 0x11177, // 11177..1117F; UNKNOWN
6504 0x11180, // 11180..111DF; SHARADA
6505 0x111E0, // 111E0 ; UNKNOWN
6506 0x111E1, // 111E1..111F4; SINHALA
6507 0x111F5, // 111F5..111FF; UNKNOWN
6508 0x11200, // 11200..11211; KHOJKI
6509 0x11212, // 11212 ; UNKNOWN
6510 0x11213, // 11213..11241; KHOJKI
6511 0x11242, // 11242..1127F; UNKNOWN
6512 0x11280, // 11280..11286; MULTANI
6513 0x11287, // 11287 ; UNKNOWN
6514 0x11288, // 11288 ; MULTANI
6515 0x11289, // 11289 ; UNKNOWN
6516 0x1128A, // 1128A..1128D; MULTANI
6517 0x1128E, // 1128E ; UNKNOWN
6518 0x1128F, // 1128F..1129D; MULTANI
6519 0x1129E, // 1129E ; UNKNOWN
6520 0x1129F, // 1129F..112A9; MULTANI
6521 0x112AA, // 112AA..112AF; UNKNOWN
6522 0x112B0, // 112B0..112EA; KHUDAWADI
6523 0x112EB, // 112EB..112EF; UNKNOWN
6524 0x112F0, // 112F0..112F9; KHUDAWADI
6525 0x112FA, // 112FA..112FF; UNKNOWN
6526 0x11300, // 11300..11303; GRANTHA
6527 0x11304, // 11304 ; UNKNOWN
6528 0x11305, // 11305..1130C; GRANTHA
6529 0x1130D, // 1130D..1130E; UNKNOWN
6530 0x1130F, // 1130F..11310; GRANTHA
6531 0x11311, // 11311..11312; UNKNOWN
6532 0x11313, // 11313..11328; GRANTHA
6533 0x11329, // 11329 ; UNKNOWN
6534 0x1132A, // 1132A..11330; GRANTHA
6535 0x11331, // 11331 ; UNKNOWN
6536 0x11332, // 11332..11333; GRANTHA
6537 0x11334, // 11334 ; UNKNOWN
6538 0x11335, // 11335..11339; GRANTHA
6539 0x1133A, // 1133A ; UNKNOWN
6540 0x1133B, // 1133B ; INHERITED
6541 0x1133C, // 1133C..11344; GRANTHA
6542 0x11345, // 11345..11346; UNKNOWN
6543 0x11347, // 11347..11348; GRANTHA
6544 0x11349, // 11349..1134A; UNKNOWN
6545 0x1134B, // 1134B..1134D; GRANTHA
6546 0x1134E, // 1134E..1134F; UNKNOWN
6547 0x11350, // 11350 ; GRANTHA
6548 0x11351, // 11351..11356; UNKNOWN
6549 0x11357, // 11357 ; GRANTHA
6550 0x11358, // 11358..1135C; UNKNOWN
6551 0x1135D, // 1135D..11363; GRANTHA
6552 0x11364, // 11364..11365; UNKNOWN
6553 0x11366, // 11366..1136C; GRANTHA
6554 0x1136D, // 1136D..1136F; UNKNOWN
6555 0x11370, // 11370..11374; GRANTHA
6556 0x11375, // 11375..113FF; UNKNOWN
6557 0x11400, // 11400..1145B; NEWA
6558 0x1145C, // 1145C ; UNKNOWN
6559 0x1145D, // 1145D..11461; NEWA
6560 0x11462, // 11462..1147F; UNKNOWN
6561 0x11480, // 11480..114C7; TIRHUTA
6562 0x114C8, // 114C8..114CF; UNKNOWN
6563 0x114D0, // 114D0..114D9; TIRHUTA
6564 0x114DA, // 114DA..1157F; UNKNOWN
6565 0x11580, // 11580..115B5; SIDDHAM
6566 0x115B6, // 115B6..115B7; UNKNOWN
6567 0x115B8, // 115B8..115DD; SIDDHAM
6568 0x115DE, // 115DE..115FF; UNKNOWN
6569 0x11600, // 11600..11644; MODI
6570 0x11645, // 11645..1164F; UNKNOWN
6571 0x11650, // 11650..11659; MODI
6572 0x1165A, // 1165A..1165F; UNKNOWN
6573 0x11660, // 11660..1166C; MONGOLIAN
6574 0x1166D, // 1166D..1167F; UNKNOWN
6575 0x11680, // 11680..116B9; TAKRI
6576 0x116BA, // 116BA..116BF; UNKNOWN
6577 0x116C0, // 116C0..116C9; TAKRI
6578 0x116CA, // 116CA..116FF; UNKNOWN
6579 0x11700, // 11700..1171A; AHOM
6580 0x1171B, // 1171B..1171C; UNKNOWN
6581 0x1171D, // 1171D..1172B; AHOM
6582 0x1172C, // 1172C..1172F; UNKNOWN
6583 0x11730, // 11730..11746; AHOM
6584 0x11747, // 11747..117FF; UNKNOWN
6585 0x11800, // 11800..1183B; DOGRA
6586 0x1183C, // 1183C..1189F; UNKNOWN
6587 0x118A0, // 118A0..118F2; WARANG_CITI
6588 0x118F3, // 118F3..118FE; UNKNOWN
6589 0x118FF, // 118FF ; WARANG_CITI
6590 0x11900, // 11900..11906; DIVES_AKURU
6591 0x11907, // 11907..11908; UNKNOWN
6592 0x11909, // 11909 ; DIVES_AKURU
6593 0x1190A, // 1190A..1190B; UNKNOWN
6594 0x1190C, // 1190C..11913; DIVES_AKURU
6595 0x11914, // 11914 ; UNKNOWN
6596 0x11915, // 11915..11916; DIVES_AKURU
6597 0x11917, // 11917 ; UNKNOWN
6598 0x11918, // 11918..11935; DIVES_AKURU
6599 0x11936, // 11936 ; UNKNOWN
6600 0x11937, // 11937..11938; DIVES_AKURU
6601 0x11939, // 11939..1193A; UNKNOWN
6602 0x1193B, // 1193B..11946; DIVES_AKURU
6603 0x11947, // 11947..1194F; UNKNOWN
6604 0x11950, // 11950..11959; DIVES_AKURU
6605 0x1195A, // 1195A..1199F; UNKNOWN
6606 0x119A0, // 119A0..119A7; NANDINAGARI
6607 0x119A8, // 119A8..119A9; UNKNOWN
6608 0x119AA, // 119AA..119D7; NANDINAGARI
6609 0x119D8, // 119D8..119D9; UNKNOWN
6610 0x119DA, // 119DA..119E4; NANDINAGARI
6611 0x119E5, // 119E5..119FF; UNKNOWN
6612 0x11A00, // 11A00..11A47; ZANABAZAR_SQUARE
6613 0x11A48, // 11A48..11A4F; UNKNOWN
6614 0x11A50, // 11A50..11AA2; SOYOMBO
6615 0x11AA3, // 11AA3..11AAF; UNKNOWN
6616 0x11AB0, // 11AB0..11ABF; CANADIAN_ABORIGINAL
6617 0x11AC0, // 11AC0..11AF8; PAU_CIN_HAU
6618 0x11AF9, // 11AF9..11AFF; UNKNOWN
6619 0x11B00, // 11B00..11B09; DEVANAGARI
6620 0x11B0A, // 11B0A..11BFF; UNKNOWN
6621 0x11C00, // 11C00..11C08; BHAIKSUKI
6622 0x11C09, // 11C09 ; UNKNOWN
6623 0x11C0A, // 11C0A..11C36; BHAIKSUKI
6624 0x11C37, // 11C37 ; UNKNOWN
6625 0x11C38, // 11C38..11C45; BHAIKSUKI
6626 0x11C46, // 11C46..11C4F; UNKNOWN
6627 0x11C50, // 11C50..11C6C; BHAIKSUKI
6628 0x11C6D, // 11C6D..11C6F; UNKNOWN
6629 0x11C70, // 11C70..11C8F; MARCHEN
6630 0x11C90, // 11C90..11C91; UNKNOWN
6631 0x11C92, // 11C92..11CA7; MARCHEN
6632 0x11CA8, // 11CA8 ; UNKNOWN
6633 0x11CA9, // 11CA9..11CB6; MARCHEN
6634 0x11CB7, // 11CB7..11CFF; UNKNOWN
6635 0x11D00, // 11D00..11D06; MASARAM_GONDI
6636 0x11D07, // 11D07 ; UNKNOWN
6637 0x11D08, // 11D08..11D09; MASARAM_GONDI
6638 0x11D0A, // 11D0A ; UNKNOWN
6639 0x11D0B, // 11D0B..11D36; MASARAM_GONDI
6640 0x11D37, // 11D37..11D39; UNKNOWN
6641 0x11D3A, // 11D3A ; MASARAM_GONDI
6642 0x11D3B, // 11D3B ; UNKNOWN
6643 0x11D3C, // 11D3C..11D3D; MASARAM_GONDI
6644 0x11D3E, // 11D3E ; UNKNOWN
6645 0x11D3F, // 11D3F..11D47; MASARAM_GONDI
6646 0x11D48, // 11D48..11D4F; UNKNOWN
6647 0x11D50, // 11D50..11D59; MASARAM_GONDI
6648 0x11D5A, // 11D5A..11D5F; UNKNOWN
6649 0x11D60, // 11D60..11D65; GUNJALA_GONDI
6650 0x11D66, // 11D66 ; UNKNOWN
6651 0x11D67, // 11D67..11D68; GUNJALA_GONDI
6652 0x11D69, // 11D69 ; UNKNOWN
6653 0x11D6A, // 11D6A..11D8E; GUNJALA_GONDI
6654 0x11D8F, // 11D8F ; UNKNOWN
6655 0x11D90, // 11D90..11D91; GUNJALA_GONDI
6656 0x11D92, // 11D92 ; UNKNOWN
6657 0x11D93, // 11D93..11D98; GUNJALA_GONDI
6658 0x11D99, // 11D99..11D9F; UNKNOWN
6659 0x11DA0, // 11DA0..11DA9; GUNJALA_GONDI
6660 0x11DAA, // 11DAA..11EDF; UNKNOWN
6661 0x11EE0, // 11EE0..11EF8; MAKASAR
6662 0x11EF9, // 11EF9..11EFF; UNKNOWN
6663 0x11F00, // 11F00..11F10; KAWI
6664 0x11F11, // 11F11 ; UNKNOWN
6665 0x11F12, // 11F12..11F3A; KAWI
6666 0x11F3B, // 11F3B..11F3D; UNKNOWN
6667 0x11F3E, // 11F3E..11F59; KAWI
6668 0x11F5A, // 11F5A..11FAF; UNKNOWN
6669 0x11FB0, // 11FB0 ; LISU
6670 0x11FB1, // 11FB1..11FBF; UNKNOWN
6671 0x11FC0, // 11FC0..11FF1; TAMIL
6672 0x11FF2, // 11FF2..11FFE; UNKNOWN
6673 0x11FFF, // 11FFF ; TAMIL
6674 0x12000, // 12000..12399; CUNEIFORM
6675 0x1239A, // 1239A..123FF; UNKNOWN
6676 0x12400, // 12400..1246E; CUNEIFORM
6677 0x1246F, // 1246F ; UNKNOWN
6678 0x12470, // 12470..12474; CUNEIFORM
6679 0x12475, // 12475..1247F; UNKNOWN
6680 0x12480, // 12480..12543; CUNEIFORM
6681 0x12544, // 12544..12F8F; UNKNOWN
6682 0x12F90, // 12F90..12FF2; CYPRO_MINOAN
6683 0x12FF3, // 12FF3..12FFF; UNKNOWN
6684 0x13000, // 13000..13455; EGYPTIAN_HIEROGLYPHS
6685 0x13456, // 13456..143FF; UNKNOWN
6686 0x14400, // 14400..14646; ANATOLIAN_HIEROGLYPHS
6687 0x14647, // 14647..167FF; UNKNOWN
6688 0x16800, // 16800..16A38; BAMUM
6689 0x16A39, // 16A39..16A3F; UNKNOWN
6690 0x16A40, // 16A40..16A5E; MRO
6691 0x16A5F, // 16A5F ; UNKNOWN
6692 0x16A60, // 16A60..16A69; MRO
6693 0x16A6A, // 16A6A..16A6D; UNKNOWN
6694 0x16A6E, // 16A6E..16A6F; MRO
6695 0x16A70, // 16A70..16ABE; TANGSA
6696 0x16ABF, // 16ABF ; UNKNOWN
6697 0x16AC0, // 16AC0..16AC9; TANGSA
6698 0x16ACA, // 16ACA..16ACF; UNKNOWN
6699 0x16AD0, // 16AD0..16AED; BASSA_VAH
6700 0x16AEE, // 16AEE..16AEF; UNKNOWN
6701 0x16AF0, // 16AF0..16AF5; BASSA_VAH
6702 0x16AF6, // 16AF6..16AFF; UNKNOWN
6703 0x16B00, // 16B00..16B45; PAHAWH_HMONG
6704 0x16B46, // 16B46..16B4F; UNKNOWN
6705 0x16B50, // 16B50..16B59; PAHAWH_HMONG
6706 0x16B5A, // 16B5A ; UNKNOWN
6707 0x16B5B, // 16B5B..16B61; PAHAWH_HMONG
6708 0x16B62, // 16B62 ; UNKNOWN
6709 0x16B63, // 16B63..16B77; PAHAWH_HMONG
6710 0x16B78, // 16B78..16B7C; UNKNOWN
6711 0x16B7D, // 16B7D..16B8F; PAHAWH_HMONG
6712 0x16B90, // 16B90..16E3F; UNKNOWN
6713 0x16E40, // 16E40..16E9A; MEDEFAIDRIN
6714 0x16E9B, // 16E9B..16EFF; UNKNOWN
6715 0x16F00, // 16F00..16F4A; MIAO
6716 0x16F4B, // 16F4B..16F4E; UNKNOWN
6717 0x16F4F, // 16F4F..16F87; MIAO
6718 0x16F88, // 16F88..16F8E; UNKNOWN
6719 0x16F8F, // 16F8F..16F9F; MIAO
6720 0x16FA0, // 16FA0..16FDF; UNKNOWN
6721 0x16FE0, // 16FE0 ; TANGUT
6722 0x16FE1, // 16FE1 ; NUSHU
6723 0x16FE2, // 16FE2..16FE3; HAN
6724 0x16FE4, // 16FE4 ; KHITAN_SMALL_SCRIPT
6725 0x16FE5, // 16FE5..16FEF; UNKNOWN
6726 0x16FF0, // 16FF0..16FF1; HAN
6727 0x16FF2, // 16FF2..16FFF; UNKNOWN
6728 0x17000, // 17000..187F7; TANGUT
6729 0x187F8, // 187F8..187FF; UNKNOWN
6730 0x18800, // 18800..18AFF; TANGUT
6731 0x18B00, // 18B00..18CD5; KHITAN_SMALL_SCRIPT
6732 0x18CD6, // 18CD6..18CFF; UNKNOWN
6733 0x18D00, // 18D00..18D08; TANGUT
6734 0x18D09, // 18D09..1AFEF; UNKNOWN
6735 0x1AFF0, // 1AFF0..1AFF3; KATAKANA
6736 0x1AFF4, // 1AFF4 ; UNKNOWN
6737 0x1AFF5, // 1AFF5..1AFFB; KATAKANA
6738 0x1AFFC, // 1AFFC ; UNKNOWN
6739 0x1AFFD, // 1AFFD..1AFFE; KATAKANA
6740 0x1AFFF, // 1AFFF ; UNKNOWN
6741 0x1B000, // 1B000 ; KATAKANA
6742 0x1B001, // 1B001..1B11F; HIRAGANA
6743 0x1B120, // 1B120..1B122; KATAKANA
6744 0x1B123, // 1B123..1B131; UNKNOWN
6745 0x1B132, // 1B132 ; HIRAGANA
6746 0x1B133, // 1B133..1B14F; UNKNOWN
6747 0x1B150, // 1B150..1B152; HIRAGANA
6748 0x1B153, // 1B153..1B154; UNKNOWN
6749 0x1B155, // 1B155 ; KATAKANA
6750 0x1B156, // 1B156..1B163; UNKNOWN
6751 0x1B164, // 1B164..1B167; KATAKANA
6752 0x1B168, // 1B168..1B16F; UNKNOWN
6753 0x1B170, // 1B170..1B2FB; NUSHU
6754 0x1B2FC, // 1B2FC..1BBFF; UNKNOWN
6755 0x1BC00, // 1BC00..1BC6A; DUPLOYAN
6756 0x1BC6B, // 1BC6B..1BC6F; UNKNOWN
6757 0x1BC70, // 1BC70..1BC7C; DUPLOYAN
6758 0x1BC7D, // 1BC7D..1BC7F; UNKNOWN
6759 0x1BC80, // 1BC80..1BC88; DUPLOYAN
6760 0x1BC89, // 1BC89..1BC8F; UNKNOWN
6761 0x1BC90, // 1BC90..1BC99; DUPLOYAN
6762 0x1BC9A, // 1BC9A..1BC9B; UNKNOWN
6763 0x1BC9C, // 1BC9C..1BC9F; DUPLOYAN
6764 0x1BCA0, // 1BCA0..1BCA3; COMMON
6765 0x1BCA4, // 1BCA4..1CEFF; UNKNOWN
6766 0x1CF00, // 1CF00..1CF2D; INHERITED
6767 0x1CF2E, // 1CF2E..1CF2F; UNKNOWN
6768 0x1CF30, // 1CF30..1CF46; INHERITED
6769 0x1CF47, // 1CF47..1CF4F; UNKNOWN
6770 0x1CF50, // 1CF50..1CFC3; COMMON
6771 0x1CFC4, // 1CFC4..1CFFF; UNKNOWN
6772 0x1D000, // 1D000..1D0F5; COMMON
6773 0x1D0F6, // 1D0F6..1D0FF; UNKNOWN
6774 0x1D100, // 1D100..1D126; COMMON
6775 0x1D127, // 1D127..1D128; UNKNOWN
6776 0x1D129, // 1D129..1D166; COMMON
6777 0x1D167, // 1D167..1D169; INHERITED
6778 0x1D16A, // 1D16A..1D17A; COMMON
6779 0x1D17B, // 1D17B..1D182; INHERITED
6780 0x1D183, // 1D183..1D184; COMMON
6781 0x1D185, // 1D185..1D18B; INHERITED
6782 0x1D18C, // 1D18C..1D1A9; COMMON
6783 0x1D1AA, // 1D1AA..1D1AD; INHERITED
6784 0x1D1AE, // 1D1AE..1D1EA; COMMON
6785 0x1D1EB, // 1D1EB..1D1FF; UNKNOWN
6786 0x1D200, // 1D200..1D245; GREEK
6787 0x1D246, // 1D246..1D2BF; UNKNOWN
6788 0x1D2C0, // 1D2C0..1D2D3; COMMON
6789 0x1D2D4, // 1D2D4..1D2DF; UNKNOWN
6790 0x1D2E0, // 1D2E0..1D2F3; COMMON
6791 0x1D2F4, // 1D2F4..1D2FF; UNKNOWN
6792 0x1D300, // 1D300..1D356; COMMON
6793 0x1D357, // 1D357..1D35F; UNKNOWN
6794 0x1D360, // 1D360..1D378; COMMON
6795 0x1D379, // 1D379..1D3FF; UNKNOWN
6796 0x1D400, // 1D400..1D454; COMMON
6797 0x1D455, // 1D455 ; UNKNOWN
6798 0x1D456, // 1D456..1D49C; COMMON
6799 0x1D49D, // 1D49D ; UNKNOWN
6800 0x1D49E, // 1D49E..1D49F; COMMON
6801 0x1D4A0, // 1D4A0..1D4A1; UNKNOWN
6802 0x1D4A2, // 1D4A2 ; COMMON
6803 0x1D4A3, // 1D4A3..1D4A4; UNKNOWN
6804 0x1D4A5, // 1D4A5..1D4A6; COMMON
6805 0x1D4A7, // 1D4A7..1D4A8; UNKNOWN
6806 0x1D4A9, // 1D4A9..1D4AC; COMMON
6807 0x1D4AD, // 1D4AD ; UNKNOWN
6808 0x1D4AE, // 1D4AE..1D4B9; COMMON
6809 0x1D4BA, // 1D4BA ; UNKNOWN
6810 0x1D4BB, // 1D4BB ; COMMON
6811 0x1D4BC, // 1D4BC ; UNKNOWN
6812 0x1D4BD, // 1D4BD..1D4C3; COMMON
6813 0x1D4C4, // 1D4C4 ; UNKNOWN
6814 0x1D4C5, // 1D4C5..1D505; COMMON
6815 0x1D506, // 1D506 ; UNKNOWN
6816 0x1D507, // 1D507..1D50A; COMMON
6817 0x1D50B, // 1D50B..1D50C; UNKNOWN
6818 0x1D50D, // 1D50D..1D514; COMMON
6819 0x1D515, // 1D515 ; UNKNOWN
6820 0x1D516, // 1D516..1D51C; COMMON
6821 0x1D51D, // 1D51D ; UNKNOWN
6822 0x1D51E, // 1D51E..1D539; COMMON
6823 0x1D53A, // 1D53A ; UNKNOWN
6824 0x1D53B, // 1D53B..1D53E; COMMON
6825 0x1D53F, // 1D53F ; UNKNOWN
6826 0x1D540, // 1D540..1D544; COMMON
6827 0x1D545, // 1D545 ; UNKNOWN
6828 0x1D546, // 1D546 ; COMMON
6829 0x1D547, // 1D547..1D549; UNKNOWN
6830 0x1D54A, // 1D54A..1D550; COMMON
6831 0x1D551, // 1D551 ; UNKNOWN
6832 0x1D552, // 1D552..1D6A5; COMMON
6833 0x1D6A6, // 1D6A6..1D6A7; UNKNOWN
6834 0x1D6A8, // 1D6A8..1D7CB; COMMON
6835 0x1D7CC, // 1D7CC..1D7CD; UNKNOWN
6836 0x1D7CE, // 1D7CE..1D7FF; COMMON
6837 0x1D800, // 1D800..1DA8B; SIGNWRITING
6838 0x1DA8C, // 1DA8C..1DA9A; UNKNOWN
6839 0x1DA9B, // 1DA9B..1DA9F; SIGNWRITING
6840 0x1DAA0, // 1DAA0 ; UNKNOWN
6841 0x1DAA1, // 1DAA1..1DAAF; SIGNWRITING
6842 0x1DAB0, // 1DAB0..1DEFF; UNKNOWN
6843 0x1DF00, // 1DF00..1DF1E; LATIN
6844 0x1DF1F, // 1DF1F..1DF24; UNKNOWN
6845 0x1DF25, // 1DF25..1DF2A; LATIN
6846 0x1DF2B, // 1DF2B..1DFFF; UNKNOWN
6847 0x1E000, // 1E000..1E006; GLAGOLITIC
6848 0x1E007, // 1E007 ; UNKNOWN
6849 0x1E008, // 1E008..1E018; GLAGOLITIC
6850 0x1E019, // 1E019..1E01A; UNKNOWN
6851 0x1E01B, // 1E01B..1E021; GLAGOLITIC
6852 0x1E022, // 1E022 ; UNKNOWN
6853 0x1E023, // 1E023..1E024; GLAGOLITIC
6854 0x1E025, // 1E025 ; UNKNOWN
6855 0x1E026, // 1E026..1E02A; GLAGOLITIC
6856 0x1E02B, // 1E02B..1E02F; UNKNOWN
6857 0x1E030, // 1E030..1E06D; CYRILLIC
6858 0x1E06E, // 1E06E..1E08E; UNKNOWN
6859 0x1E08F, // 1E08F ; CYRILLIC
6860 0x1E090, // 1E090..1E0FF; UNKNOWN
6861 0x1E100, // 1E100..1E12C; NYIAKENG_PUACHUE_HMONG
6862 0x1E12D, // 1E12D..1E12F; UNKNOWN
6863 0x1E130, // 1E130..1E13D; NYIAKENG_PUACHUE_HMONG
6864 0x1E13E, // 1E13E..1E13F; UNKNOWN
6865 0x1E140, // 1E140..1E149; NYIAKENG_PUACHUE_HMONG
6866 0x1E14A, // 1E14A..1E14D; UNKNOWN
6867 0x1E14E, // 1E14E..1E14F; NYIAKENG_PUACHUE_HMONG
6868 0x1E150, // 1E150..1E28F; UNKNOWN
6869 0x1E290, // 1E290..1E2AE; TOTO
6870 0x1E2AF, // 1E2AF..1E2BF; UNKNOWN
6871 0x1E2C0, // 1E2C0..1E2F9; WANCHO
6872 0x1E2FA, // 1E2FA..1E2FE; UNKNOWN
6873 0x1E2FF, // 1E2FF ; WANCHO
6874 0x1E300, // 1E300..1E4CF; UNKNOWN
6875 0x1E4D0, // 1E4D0..1E4F9; NAG_MUNDARI
6876 0x1E4FA, // 1E4FA..1E7DF; UNKNOWN
6877 0x1E7E0, // 1E7E0..1E7E6; ETHIOPIC
6878 0x1E7E7, // 1E7E7 ; UNKNOWN
6879 0x1E7E8, // 1E7E8..1E7EB; ETHIOPIC
6880 0x1E7EC, // 1E7EC ; UNKNOWN
6881 0x1E7ED, // 1E7ED..1E7EE; ETHIOPIC
6882 0x1E7EF, // 1E7EF ; UNKNOWN
6883 0x1E7F0, // 1E7F0..1E7FE; ETHIOPIC
6884 0x1E7FF, // 1E7FF ; UNKNOWN
6885 0x1E800, // 1E800..1E8C4; MENDE_KIKAKUI
6886 0x1E8C5, // 1E8C5..1E8C6; UNKNOWN
6887 0x1E8C7, // 1E8C7..1E8D6; MENDE_KIKAKUI
6888 0x1E8D7, // 1E8D7..1E8FF; UNKNOWN
6889 0x1E900, // 1E900..1E94B; ADLAM
6890 0x1E94C, // 1E94C..1E94F; UNKNOWN
6891 0x1E950, // 1E950..1E959; ADLAM
6892 0x1E95A, // 1E95A..1E95D; UNKNOWN
6893 0x1E95E, // 1E95E..1E95F; ADLAM
6894 0x1E960, // 1E960..1EC70; UNKNOWN
6895 0x1EC71, // 1EC71..1ECB4; COMMON
6896 0x1ECB5, // 1ECB5..1ED00; UNKNOWN
6897 0x1ED01, // 1ED01..1ED3D; COMMON
6898 0x1ED3E, // 1ED3E..1EDFF; UNKNOWN
6899 0x1EE00, // 1EE00..1EE03; ARABIC
6900 0x1EE04, // 1EE04 ; UNKNOWN
6901 0x1EE05, // 1EE05..1EE1F; ARABIC
6902 0x1EE20, // 1EE20 ; UNKNOWN
6903 0x1EE21, // 1EE21..1EE22; ARABIC
6904 0x1EE23, // 1EE23 ; UNKNOWN
6905 0x1EE24, // 1EE24 ; ARABIC
6906 0x1EE25, // 1EE25..1EE26; UNKNOWN
6907 0x1EE27, // 1EE27 ; ARABIC
6908 0x1EE28, // 1EE28 ; UNKNOWN
6909 0x1EE29, // 1EE29..1EE32; ARABIC
6910 0x1EE33, // 1EE33 ; UNKNOWN
6911 0x1EE34, // 1EE34..1EE37; ARABIC
6912 0x1EE38, // 1EE38 ; UNKNOWN
6913 0x1EE39, // 1EE39 ; ARABIC
6914 0x1EE3A, // 1EE3A ; UNKNOWN
6915 0x1EE3B, // 1EE3B ; ARABIC
6916 0x1EE3C, // 1EE3C..1EE41; UNKNOWN
6917 0x1EE42, // 1EE42 ; ARABIC
6918 0x1EE43, // 1EE43..1EE46; UNKNOWN
6919 0x1EE47, // 1EE47 ; ARABIC
6920 0x1EE48, // 1EE48 ; UNKNOWN
6921 0x1EE49, // 1EE49 ; ARABIC
6922 0x1EE4A, // 1EE4A ; UNKNOWN
6923 0x1EE4B, // 1EE4B ; ARABIC
6924 0x1EE4C, // 1EE4C ; UNKNOWN
6925 0x1EE4D, // 1EE4D..1EE4F; ARABIC
6926 0x1EE50, // 1EE50 ; UNKNOWN
6927 0x1EE51, // 1EE51..1EE52; ARABIC
6928 0x1EE53, // 1EE53 ; UNKNOWN
6929 0x1EE54, // 1EE54 ; ARABIC
6930 0x1EE55, // 1EE55..1EE56; UNKNOWN
6931 0x1EE57, // 1EE57 ; ARABIC
6932 0x1EE58, // 1EE58 ; UNKNOWN
6933 0x1EE59, // 1EE59 ; ARABIC
6934 0x1EE5A, // 1EE5A ; UNKNOWN
6935 0x1EE5B, // 1EE5B ; ARABIC
6936 0x1EE5C, // 1EE5C ; UNKNOWN
6937 0x1EE5D, // 1EE5D ; ARABIC
6938 0x1EE5E, // 1EE5E ; UNKNOWN
6939 0x1EE5F, // 1EE5F ; ARABIC
6940 0x1EE60, // 1EE60 ; UNKNOWN
6941 0x1EE61, // 1EE61..1EE62; ARABIC
6942 0x1EE63, // 1EE63 ; UNKNOWN
6943 0x1EE64, // 1EE64 ; ARABIC
6944 0x1EE65, // 1EE65..1EE66; UNKNOWN
6945 0x1EE67, // 1EE67..1EE6A; ARABIC
6946 0x1EE6B, // 1EE6B ; UNKNOWN
6947 0x1EE6C, // 1EE6C..1EE72; ARABIC
6948 0x1EE73, // 1EE73 ; UNKNOWN
6949 0x1EE74, // 1EE74..1EE77; ARABIC
6950 0x1EE78, // 1EE78 ; UNKNOWN
6951 0x1EE79, // 1EE79..1EE7C; ARABIC
6952 0x1EE7D, // 1EE7D ; UNKNOWN
6953 0x1EE7E, // 1EE7E ; ARABIC
6954 0x1EE7F, // 1EE7F ; UNKNOWN
6955 0x1EE80, // 1EE80..1EE89; ARABIC
6956 0x1EE8A, // 1EE8A ; UNKNOWN
6957 0x1EE8B, // 1EE8B..1EE9B; ARABIC
6958 0x1EE9C, // 1EE9C..1EEA0; UNKNOWN
6959 0x1EEA1, // 1EEA1..1EEA3; ARABIC
6960 0x1EEA4, // 1EEA4 ; UNKNOWN
6961 0x1EEA5, // 1EEA5..1EEA9; ARABIC
6962 0x1EEAA, // 1EEAA ; UNKNOWN
6963 0x1EEAB, // 1EEAB..1EEBB; ARABIC
6964 0x1EEBC, // 1EEBC..1EEEF; UNKNOWN
6965 0x1EEF0, // 1EEF0..1EEF1; ARABIC
6966 0x1EEF2, // 1EEF2..1EFFF; UNKNOWN
6967 0x1F000, // 1F000..1F02B; COMMON
6968 0x1F02C, // 1F02C..1F02F; UNKNOWN
6969 0x1F030, // 1F030..1F093; COMMON
6970 0x1F094, // 1F094..1F09F; UNKNOWN
6971 0x1F0A0, // 1F0A0..1F0AE; COMMON
6972 0x1F0AF, // 1F0AF..1F0B0; UNKNOWN
6973 0x1F0B1, // 1F0B1..1F0BF; COMMON
6974 0x1F0C0, // 1F0C0 ; UNKNOWN
6975 0x1F0C1, // 1F0C1..1F0CF; COMMON
6976 0x1F0D0, // 1F0D0 ; UNKNOWN
6977 0x1F0D1, // 1F0D1..1F0F5; COMMON
6978 0x1F0F6, // 1F0F6..1F0FF; UNKNOWN
6979 0x1F100, // 1F100..1F1AD; COMMON
6980 0x1F1AE, // 1F1AE..1F1E5; UNKNOWN
6981 0x1F1E6, // 1F1E6..1F1FF; COMMON
6982 0x1F200, // 1F200 ; HIRAGANA
6983 0x1F201, // 1F201..1F202; COMMON
6984 0x1F203, // 1F203..1F20F; UNKNOWN
6985 0x1F210, // 1F210..1F23B; COMMON
6986 0x1F23C, // 1F23C..1F23F; UNKNOWN
6987 0x1F240, // 1F240..1F248; COMMON
6988 0x1F249, // 1F249..1F24F; UNKNOWN
6989 0x1F250, // 1F250..1F251; COMMON
6990 0x1F252, // 1F252..1F25F; UNKNOWN
6991 0x1F260, // 1F260..1F265; COMMON
6992 0x1F266, // 1F266..1F2FF; UNKNOWN
6993 0x1F300, // 1F300..1F6D7; COMMON
6994 0x1F6D8, // 1F6D8..1F6DB; UNKNOWN
6995 0x1F6DC, // 1F6DC..1F6EC; COMMON
6996 0x1F6ED, // 1F6ED..1F6EF; UNKNOWN
6997 0x1F6F0, // 1F6F0..1F6FC; COMMON
6998 0x1F6FD, // 1F6FD..1F6FF; UNKNOWN
6999 0x1F700, // 1F700..1F776; COMMON
7000 0x1F777, // 1F777..1F77A; UNKNOWN
7001 0x1F77B, // 1F77B..1F7D9; COMMON
7002 0x1F7DA, // 1F7DA..1F7DF; UNKNOWN
7003 0x1F7E0, // 1F7E0..1F7EB; COMMON
7004 0x1F7EC, // 1F7EC..1F7EF; UNKNOWN
7005 0x1F7F0, // 1F7F0 ; COMMON
7006 0x1F7F1, // 1F7F1..1F7FF; UNKNOWN
7007 0x1F800, // 1F800..1F80B; COMMON
7008 0x1F80C, // 1F80C..1F80F; UNKNOWN
7009 0x1F810, // 1F810..1F847; COMMON
7010 0x1F848, // 1F848..1F84F; UNKNOWN
7011 0x1F850, // 1F850..1F859; COMMON
7012 0x1F85A, // 1F85A..1F85F; UNKNOWN
7013 0x1F860, // 1F860..1F887; COMMON
7014 0x1F888, // 1F888..1F88F; UNKNOWN
7015 0x1F890, // 1F890..1F8AD; COMMON
7016 0x1F8AE, // 1F8AE..1F8AF; UNKNOWN
7017 0x1F8B0, // 1F8B0..1F8B1; COMMON
7018 0x1F8B2, // 1F8B2..1F8FF; UNKNOWN
7019 0x1F900, // 1F900..1FA53; COMMON
7020 0x1FA54, // 1FA54..1FA5F; UNKNOWN
7021 0x1FA60, // 1FA60..1FA6D; COMMON
7022 0x1FA6E, // 1FA6E..1FA6F; UNKNOWN
7023 0x1FA70, // 1FA70..1FA7C; COMMON
7024 0x1FA7D, // 1FA7D..1FA7F; UNKNOWN
7025 0x1FA80, // 1FA80..1FA88; COMMON
7026 0x1FA89, // 1FA89..1FA8F; UNKNOWN
7027 0x1FA90, // 1FA90..1FABD; COMMON
7028 0x1FABE, // 1FABE ; UNKNOWN
7029 0x1FABF, // 1FABF..1FAC5; COMMON
7030 0x1FAC6, // 1FAC6..1FACD; UNKNOWN
7031 0x1FACE, // 1FACE..1FADB; COMMON
7032 0x1FADC, // 1FADC..1FADF; UNKNOWN
7033 0x1FAE0, // 1FAE0..1FAE8; COMMON
7034 0x1FAE9, // 1FAE9..1FAEF; UNKNOWN
7035 0x1FAF0, // 1FAF0..1FAF8; COMMON
7036 0x1FAF9, // 1FAF9..1FAFF; UNKNOWN
7037 0x1FB00, // 1FB00..1FB92; COMMON
7038 0x1FB93, // 1FB93 ; UNKNOWN
7039 0x1FB94, // 1FB94..1FBCA; COMMON
7040 0x1FBCB, // 1FBCB..1FBEF; UNKNOWN
7041 0x1FBF0, // 1FBF0..1FBF9; COMMON
7042 0x1FBFA, // 1FBFA..1FFFF; UNKNOWN
7043 0x20000, // 20000..2A6DF; HAN
7044 0x2A6E0, // 2A6E0..2A6FF; UNKNOWN
7045 0x2A700, // 2A700..2B739; HAN
7046 0x2B73A, // 2B73A..2B73F; UNKNOWN
7047 0x2B740, // 2B740..2B81D; HAN
7048 0x2B81E, // 2B81E..2B81F; UNKNOWN
7049 0x2B820, // 2B820..2CEA1; HAN
7050 0x2CEA2, // 2CEA2..2CEAF; UNKNOWN
7051 0x2CEB0, // 2CEB0..2EBE0; HAN
7052 0x2EBE1, // 2EBE1..2EBEF; UNKNOWN
7053 0x2EBF0, // 2EBF0..2EE5D; HAN
7054 0x2EE5E, // 2EE5E..2F7FF; UNKNOWN
7055 0x2F800, // 2F800..2FA1D; HAN
7056 0x2FA1E, // 2FA1E..2FFFF; UNKNOWN
7057 0x30000, // 30000..3134A; HAN
7058 0x3134B, // 3134B..3134F; UNKNOWN
7059 0x31350, // 31350..323AF; HAN
7060 0x323B0, // 323B0..E0000; UNKNOWN
7061 0xE0001, // E0001 ; COMMON
7062 0xE0002, // E0002..E001F; UNKNOWN
7063 0xE0020, // E0020..E007F; COMMON
7064 0xE0080, // E0080..E00FF; UNKNOWN
7065 0xE0100, // E0100..E01EF; INHERITED
7066 0xE01F0, // E01F0..10FFFF; UNKNOWN
7067 };
7068
7069 private static final UnicodeScript[] scripts = {
7070 COMMON, // 0000..0040
7071 LATIN, // 0041..005A
7072 COMMON, // 005B..0060
7073 LATIN, // 0061..007A
7074 COMMON, // 007B..00A9
7075 LATIN, // 00AA
7076 COMMON, // 00AB..00B9
7077 LATIN, // 00BA
7078 COMMON, // 00BB..00BF
7079 LATIN, // 00C0..00D6
7080 COMMON, // 00D7
7081 LATIN, // 00D8..00F6
7082 COMMON, // 00F7
7083 LATIN, // 00F8..02B8
7084 COMMON, // 02B9..02DF
7085 LATIN, // 02E0..02E4
7086 COMMON, // 02E5..02E9
7087 BOPOMOFO, // 02EA..02EB
7088 COMMON, // 02EC..02FF
7089 INHERITED, // 0300..036F
7090 GREEK, // 0370..0373
7091 COMMON, // 0374
7092 GREEK, // 0375..0377
7093 UNKNOWN, // 0378..0379
7094 GREEK, // 037A..037D
7095 COMMON, // 037E
7096 GREEK, // 037F
7097 UNKNOWN, // 0380..0383
7098 GREEK, // 0384
7099 COMMON, // 0385
7100 GREEK, // 0386
7101 COMMON, // 0387
7102 GREEK, // 0388..038A
7103 UNKNOWN, // 038B
7104 GREEK, // 038C
7105 UNKNOWN, // 038D
7106 GREEK, // 038E..03A1
7107 UNKNOWN, // 03A2
7108 GREEK, // 03A3..03E1
7109 COPTIC, // 03E2..03EF
7110 GREEK, // 03F0..03FF
7111 CYRILLIC, // 0400..0484
7112 INHERITED, // 0485..0486
7113 CYRILLIC, // 0487..052F
7114 UNKNOWN, // 0530
7115 ARMENIAN, // 0531..0556
7116 UNKNOWN, // 0557..0558
7117 ARMENIAN, // 0559..058A
7118 UNKNOWN, // 058B..058C
7119 ARMENIAN, // 058D..058F
7120 UNKNOWN, // 0590
7121 HEBREW, // 0591..05C7
7122 UNKNOWN, // 05C8..05CF
7123 HEBREW, // 05D0..05EA
7124 UNKNOWN, // 05EB..05EE
7125 HEBREW, // 05EF..05F4
7126 UNKNOWN, // 05F5..05FF
7127 ARABIC, // 0600..0604
7128 COMMON, // 0605
7129 ARABIC, // 0606..060B
7130 COMMON, // 060C
7131 ARABIC, // 060D..061A
7132 COMMON, // 061B
7133 ARABIC, // 061C..061E
7134 COMMON, // 061F
7135 ARABIC, // 0620..063F
7136 COMMON, // 0640
7137 ARABIC, // 0641..064A
7138 INHERITED, // 064B..0655
7139 ARABIC, // 0656..066F
7140 INHERITED, // 0670
7141 ARABIC, // 0671..06DC
7142 COMMON, // 06DD
7143 ARABIC, // 06DE..06FF
7144 SYRIAC, // 0700..070D
7145 UNKNOWN, // 070E
7146 SYRIAC, // 070F..074A
7147 UNKNOWN, // 074B..074C
7148 SYRIAC, // 074D..074F
7149 ARABIC, // 0750..077F
7150 THAANA, // 0780..07B1
7151 UNKNOWN, // 07B2..07BF
7152 NKO, // 07C0..07FA
7153 UNKNOWN, // 07FB..07FC
7154 NKO, // 07FD..07FF
7155 SAMARITAN, // 0800..082D
7156 UNKNOWN, // 082E..082F
7157 SAMARITAN, // 0830..083E
7158 UNKNOWN, // 083F
7159 MANDAIC, // 0840..085B
7160 UNKNOWN, // 085C..085D
7161 MANDAIC, // 085E
7162 UNKNOWN, // 085F
7163 SYRIAC, // 0860..086A
7164 UNKNOWN, // 086B..086F
7165 ARABIC, // 0870..088E
7166 UNKNOWN, // 088F
7167 ARABIC, // 0890..0891
7168 UNKNOWN, // 0892..0897
7169 ARABIC, // 0898..08E1
7170 COMMON, // 08E2
7171 ARABIC, // 08E3..08FF
7172 DEVANAGARI, // 0900..0950
7173 INHERITED, // 0951..0954
7174 DEVANAGARI, // 0955..0963
7175 COMMON, // 0964..0965
7176 DEVANAGARI, // 0966..097F
7177 BENGALI, // 0980..0983
7178 UNKNOWN, // 0984
7179 BENGALI, // 0985..098C
7180 UNKNOWN, // 098D..098E
7181 BENGALI, // 098F..0990
7182 UNKNOWN, // 0991..0992
7183 BENGALI, // 0993..09A8
7184 UNKNOWN, // 09A9
7185 BENGALI, // 09AA..09B0
7186 UNKNOWN, // 09B1
7187 BENGALI, // 09B2
7188 UNKNOWN, // 09B3..09B5
7189 BENGALI, // 09B6..09B9
7190 UNKNOWN, // 09BA..09BB
7191 BENGALI, // 09BC..09C4
7192 UNKNOWN, // 09C5..09C6
7193 BENGALI, // 09C7..09C8
7194 UNKNOWN, // 09C9..09CA
7195 BENGALI, // 09CB..09CE
7196 UNKNOWN, // 09CF..09D6
7197 BENGALI, // 09D7
7198 UNKNOWN, // 09D8..09DB
7199 BENGALI, // 09DC..09DD
7200 UNKNOWN, // 09DE
7201 BENGALI, // 09DF..09E3
7202 UNKNOWN, // 09E4..09E5
7203 BENGALI, // 09E6..09FE
7204 UNKNOWN, // 09FF..0A00
7205 GURMUKHI, // 0A01..0A03
7206 UNKNOWN, // 0A04
7207 GURMUKHI, // 0A05..0A0A
7208 UNKNOWN, // 0A0B..0A0E
7209 GURMUKHI, // 0A0F..0A10
7210 UNKNOWN, // 0A11..0A12
7211 GURMUKHI, // 0A13..0A28
7212 UNKNOWN, // 0A29
7213 GURMUKHI, // 0A2A..0A30
7214 UNKNOWN, // 0A31
7215 GURMUKHI, // 0A32..0A33
7216 UNKNOWN, // 0A34
7217 GURMUKHI, // 0A35..0A36
7218 UNKNOWN, // 0A37
7219 GURMUKHI, // 0A38..0A39
7220 UNKNOWN, // 0A3A..0A3B
7221 GURMUKHI, // 0A3C
7222 UNKNOWN, // 0A3D
7223 GURMUKHI, // 0A3E..0A42
7224 UNKNOWN, // 0A43..0A46
7225 GURMUKHI, // 0A47..0A48
7226 UNKNOWN, // 0A49..0A4A
7227 GURMUKHI, // 0A4B..0A4D
7228 UNKNOWN, // 0A4E..0A50
7229 GURMUKHI, // 0A51
7230 UNKNOWN, // 0A52..0A58
7231 GURMUKHI, // 0A59..0A5C
7232 UNKNOWN, // 0A5D
7233 GURMUKHI, // 0A5E
7234 UNKNOWN, // 0A5F..0A65
7235 GURMUKHI, // 0A66..0A76
7236 UNKNOWN, // 0A77..0A80
7237 GUJARATI, // 0A81..0A83
7238 UNKNOWN, // 0A84
7239 GUJARATI, // 0A85..0A8D
7240 UNKNOWN, // 0A8E
7241 GUJARATI, // 0A8F..0A91
7242 UNKNOWN, // 0A92
7243 GUJARATI, // 0A93..0AA8
7244 UNKNOWN, // 0AA9
7245 GUJARATI, // 0AAA..0AB0
7246 UNKNOWN, // 0AB1
7247 GUJARATI, // 0AB2..0AB3
7248 UNKNOWN, // 0AB4
7249 GUJARATI, // 0AB5..0AB9
7250 UNKNOWN, // 0ABA..0ABB
7251 GUJARATI, // 0ABC..0AC5
7252 UNKNOWN, // 0AC6
7253 GUJARATI, // 0AC7..0AC9
7254 UNKNOWN, // 0ACA
7255 GUJARATI, // 0ACB..0ACD
7256 UNKNOWN, // 0ACE..0ACF
7257 GUJARATI, // 0AD0
7258 UNKNOWN, // 0AD1..0ADF
7259 GUJARATI, // 0AE0..0AE3
7260 UNKNOWN, // 0AE4..0AE5
7261 GUJARATI, // 0AE6..0AF1
7262 UNKNOWN, // 0AF2..0AF8
7263 GUJARATI, // 0AF9..0AFF
7264 UNKNOWN, // 0B00
7265 ORIYA, // 0B01..0B03
7266 UNKNOWN, // 0B04
7267 ORIYA, // 0B05..0B0C
7268 UNKNOWN, // 0B0D..0B0E
7269 ORIYA, // 0B0F..0B10
7270 UNKNOWN, // 0B11..0B12
7271 ORIYA, // 0B13..0B28
7272 UNKNOWN, // 0B29
7273 ORIYA, // 0B2A..0B30
7274 UNKNOWN, // 0B31
7275 ORIYA, // 0B32..0B33
7276 UNKNOWN, // 0B34
7277 ORIYA, // 0B35..0B39
7278 UNKNOWN, // 0B3A..0B3B
7279 ORIYA, // 0B3C..0B44
7280 UNKNOWN, // 0B45..0B46
7281 ORIYA, // 0B47..0B48
7282 UNKNOWN, // 0B49..0B4A
7283 ORIYA, // 0B4B..0B4D
7284 UNKNOWN, // 0B4E..0B54
7285 ORIYA, // 0B55..0B57
7286 UNKNOWN, // 0B58..0B5B
7287 ORIYA, // 0B5C..0B5D
7288 UNKNOWN, // 0B5E
7289 ORIYA, // 0B5F..0B63
7290 UNKNOWN, // 0B64..0B65
7291 ORIYA, // 0B66..0B77
7292 UNKNOWN, // 0B78..0B81
7293 TAMIL, // 0B82..0B83
7294 UNKNOWN, // 0B84
7295 TAMIL, // 0B85..0B8A
7296 UNKNOWN, // 0B8B..0B8D
7297 TAMIL, // 0B8E..0B90
7298 UNKNOWN, // 0B91
7299 TAMIL, // 0B92..0B95
7300 UNKNOWN, // 0B96..0B98
7301 TAMIL, // 0B99..0B9A
7302 UNKNOWN, // 0B9B
7303 TAMIL, // 0B9C
7304 UNKNOWN, // 0B9D
7305 TAMIL, // 0B9E..0B9F
7306 UNKNOWN, // 0BA0..0BA2
7307 TAMIL, // 0BA3..0BA4
7308 UNKNOWN, // 0BA5..0BA7
7309 TAMIL, // 0BA8..0BAA
7310 UNKNOWN, // 0BAB..0BAD
7311 TAMIL, // 0BAE..0BB9
7312 UNKNOWN, // 0BBA..0BBD
7313 TAMIL, // 0BBE..0BC2
7314 UNKNOWN, // 0BC3..0BC5
7315 TAMIL, // 0BC6..0BC8
7316 UNKNOWN, // 0BC9
7317 TAMIL, // 0BCA..0BCD
7318 UNKNOWN, // 0BCE..0BCF
7319 TAMIL, // 0BD0
7320 UNKNOWN, // 0BD1..0BD6
7321 TAMIL, // 0BD7
7322 UNKNOWN, // 0BD8..0BE5
7323 TAMIL, // 0BE6..0BFA
7324 UNKNOWN, // 0BFB..0BFF
7325 TELUGU, // 0C00..0C0C
7326 UNKNOWN, // 0C0D
7327 TELUGU, // 0C0E..0C10
7328 UNKNOWN, // 0C11
7329 TELUGU, // 0C12..0C28
7330 UNKNOWN, // 0C29
7331 TELUGU, // 0C2A..0C39
7332 UNKNOWN, // 0C3A..0C3B
7333 TELUGU, // 0C3C..0C44
7334 UNKNOWN, // 0C45
7335 TELUGU, // 0C46..0C48
7336 UNKNOWN, // 0C49
7337 TELUGU, // 0C4A..0C4D
7338 UNKNOWN, // 0C4E..0C54
7339 TELUGU, // 0C55..0C56
7340 UNKNOWN, // 0C57
7341 TELUGU, // 0C58..0C5A
7342 UNKNOWN, // 0C5B..0C5C
7343 TELUGU, // 0C5D
7344 UNKNOWN, // 0C5E..0C5F
7345 TELUGU, // 0C60..0C63
7346 UNKNOWN, // 0C64..0C65
7347 TELUGU, // 0C66..0C6F
7348 UNKNOWN, // 0C70..0C76
7349 TELUGU, // 0C77..0C7F
7350 KANNADA, // 0C80..0C8C
7351 UNKNOWN, // 0C8D
7352 KANNADA, // 0C8E..0C90
7353 UNKNOWN, // 0C91
7354 KANNADA, // 0C92..0CA8
7355 UNKNOWN, // 0CA9
7356 KANNADA, // 0CAA..0CB3
7357 UNKNOWN, // 0CB4
7358 KANNADA, // 0CB5..0CB9
7359 UNKNOWN, // 0CBA..0CBB
7360 KANNADA, // 0CBC..0CC4
7361 UNKNOWN, // 0CC5
7362 KANNADA, // 0CC6..0CC8
7363 UNKNOWN, // 0CC9
7364 KANNADA, // 0CCA..0CCD
7365 UNKNOWN, // 0CCE..0CD4
7366 KANNADA, // 0CD5..0CD6
7367 UNKNOWN, // 0CD7..0CDC
7368 KANNADA, // 0CDD..0CDE
7369 UNKNOWN, // 0CDF
7370 KANNADA, // 0CE0..0CE3
7371 UNKNOWN, // 0CE4..0CE5
7372 KANNADA, // 0CE6..0CEF
7373 UNKNOWN, // 0CF0
7374 KANNADA, // 0CF1..0CF3
7375 UNKNOWN, // 0CF4..0CFF
7376 MALAYALAM, // 0D00..0D0C
7377 UNKNOWN, // 0D0D
7378 MALAYALAM, // 0D0E..0D10
7379 UNKNOWN, // 0D11
7380 MALAYALAM, // 0D12..0D44
7381 UNKNOWN, // 0D45
7382 MALAYALAM, // 0D46..0D48
7383 UNKNOWN, // 0D49
7384 MALAYALAM, // 0D4A..0D4F
7385 UNKNOWN, // 0D50..0D53
7386 MALAYALAM, // 0D54..0D63
7387 UNKNOWN, // 0D64..0D65
7388 MALAYALAM, // 0D66..0D7F
7389 UNKNOWN, // 0D80
7390 SINHALA, // 0D81..0D83
7391 UNKNOWN, // 0D84
7392 SINHALA, // 0D85..0D96
7393 UNKNOWN, // 0D97..0D99
7394 SINHALA, // 0D9A..0DB1
7395 UNKNOWN, // 0DB2
7396 SINHALA, // 0DB3..0DBB
7397 UNKNOWN, // 0DBC
7398 SINHALA, // 0DBD
7399 UNKNOWN, // 0DBE..0DBF
7400 SINHALA, // 0DC0..0DC6
7401 UNKNOWN, // 0DC7..0DC9
7402 SINHALA, // 0DCA
7403 UNKNOWN, // 0DCB..0DCE
7404 SINHALA, // 0DCF..0DD4
7405 UNKNOWN, // 0DD5
7406 SINHALA, // 0DD6
7407 UNKNOWN, // 0DD7
7408 SINHALA, // 0DD8..0DDF
7409 UNKNOWN, // 0DE0..0DE5
7410 SINHALA, // 0DE6..0DEF
7411 UNKNOWN, // 0DF0..0DF1
7412 SINHALA, // 0DF2..0DF4
7413 UNKNOWN, // 0DF5..0E00
7414 THAI, // 0E01..0E3A
7415 UNKNOWN, // 0E3B..0E3E
7416 COMMON, // 0E3F
7417 THAI, // 0E40..0E5B
7418 UNKNOWN, // 0E5C..0E80
7419 LAO, // 0E81..0E82
7420 UNKNOWN, // 0E83
7421 LAO, // 0E84
7422 UNKNOWN, // 0E85
7423 LAO, // 0E86..0E8A
7424 UNKNOWN, // 0E8B
7425 LAO, // 0E8C..0EA3
7426 UNKNOWN, // 0EA4
7427 LAO, // 0EA5
7428 UNKNOWN, // 0EA6
7429 LAO, // 0EA7..0EBD
7430 UNKNOWN, // 0EBE..0EBF
7431 LAO, // 0EC0..0EC4
7432 UNKNOWN, // 0EC5
7433 LAO, // 0EC6
7434 UNKNOWN, // 0EC7
7435 LAO, // 0EC8..0ECE
7436 UNKNOWN, // 0ECF
7437 LAO, // 0ED0..0ED9
7438 UNKNOWN, // 0EDA..0EDB
7439 LAO, // 0EDC..0EDF
7440 UNKNOWN, // 0EE0..0EFF
7441 TIBETAN, // 0F00..0F47
7442 UNKNOWN, // 0F48
7443 TIBETAN, // 0F49..0F6C
7444 UNKNOWN, // 0F6D..0F70
7445 TIBETAN, // 0F71..0F97
7446 UNKNOWN, // 0F98
7447 TIBETAN, // 0F99..0FBC
7448 UNKNOWN, // 0FBD
7449 TIBETAN, // 0FBE..0FCC
7450 UNKNOWN, // 0FCD
7451 TIBETAN, // 0FCE..0FD4
7452 COMMON, // 0FD5..0FD8
7453 TIBETAN, // 0FD9..0FDA
7454 UNKNOWN, // 0FDB..0FFF
7455 MYANMAR, // 1000..109F
7456 GEORGIAN, // 10A0..10C5
7457 UNKNOWN, // 10C6
7458 GEORGIAN, // 10C7
7459 UNKNOWN, // 10C8..10CC
7460 GEORGIAN, // 10CD
7461 UNKNOWN, // 10CE..10CF
7462 GEORGIAN, // 10D0..10FA
7463 COMMON, // 10FB
7464 GEORGIAN, // 10FC..10FF
7465 HANGUL, // 1100..11FF
7466 ETHIOPIC, // 1200..1248
7467 UNKNOWN, // 1249
7468 ETHIOPIC, // 124A..124D
7469 UNKNOWN, // 124E..124F
7470 ETHIOPIC, // 1250..1256
7471 UNKNOWN, // 1257
7472 ETHIOPIC, // 1258
7473 UNKNOWN, // 1259
7474 ETHIOPIC, // 125A..125D
7475 UNKNOWN, // 125E..125F
7476 ETHIOPIC, // 1260..1288
7477 UNKNOWN, // 1289
7478 ETHIOPIC, // 128A..128D
7479 UNKNOWN, // 128E..128F
7480 ETHIOPIC, // 1290..12B0
7481 UNKNOWN, // 12B1
7482 ETHIOPIC, // 12B2..12B5
7483 UNKNOWN, // 12B6..12B7
7484 ETHIOPIC, // 12B8..12BE
7485 UNKNOWN, // 12BF
7486 ETHIOPIC, // 12C0
7487 UNKNOWN, // 12C1
7488 ETHIOPIC, // 12C2..12C5
7489 UNKNOWN, // 12C6..12C7
7490 ETHIOPIC, // 12C8..12D6
7491 UNKNOWN, // 12D7
7492 ETHIOPIC, // 12D8..1310
7493 UNKNOWN, // 1311
7494 ETHIOPIC, // 1312..1315
7495 UNKNOWN, // 1316..1317
7496 ETHIOPIC, // 1318..135A
7497 UNKNOWN, // 135B..135C
7498 ETHIOPIC, // 135D..137C
7499 UNKNOWN, // 137D..137F
7500 ETHIOPIC, // 1380..1399
7501 UNKNOWN, // 139A..139F
7502 CHEROKEE, // 13A0..13F5
7503 UNKNOWN, // 13F6..13F7
7504 CHEROKEE, // 13F8..13FD
7505 UNKNOWN, // 13FE..13FF
7506 CANADIAN_ABORIGINAL, // 1400..167F
7507 OGHAM, // 1680..169C
7508 UNKNOWN, // 169D..169F
7509 RUNIC, // 16A0..16EA
7510 COMMON, // 16EB..16ED
7511 RUNIC, // 16EE..16F8
7512 UNKNOWN, // 16F9..16FF
7513 TAGALOG, // 1700..1715
7514 UNKNOWN, // 1716..171E
7515 TAGALOG, // 171F
7516 HANUNOO, // 1720..1734
7517 COMMON, // 1735..1736
7518 UNKNOWN, // 1737..173F
7519 BUHID, // 1740..1753
7520 UNKNOWN, // 1754..175F
7521 TAGBANWA, // 1760..176C
7522 UNKNOWN, // 176D
7523 TAGBANWA, // 176E..1770
7524 UNKNOWN, // 1771
7525 TAGBANWA, // 1772..1773
7526 UNKNOWN, // 1774..177F
7527 KHMER, // 1780..17DD
7528 UNKNOWN, // 17DE..17DF
7529 KHMER, // 17E0..17E9
7530 UNKNOWN, // 17EA..17EF
7531 KHMER, // 17F0..17F9
7532 UNKNOWN, // 17FA..17FF
7533 MONGOLIAN, // 1800..1801
7534 COMMON, // 1802..1803
7535 MONGOLIAN, // 1804
7536 COMMON, // 1805
7537 MONGOLIAN, // 1806..1819
7538 UNKNOWN, // 181A..181F
7539 MONGOLIAN, // 1820..1878
7540 UNKNOWN, // 1879..187F
7541 MONGOLIAN, // 1880..18AA
7542 UNKNOWN, // 18AB..18AF
7543 CANADIAN_ABORIGINAL, // 18B0..18F5
7544 UNKNOWN, // 18F6..18FF
7545 LIMBU, // 1900..191E
7546 UNKNOWN, // 191F
7547 LIMBU, // 1920..192B
7548 UNKNOWN, // 192C..192F
7549 LIMBU, // 1930..193B
7550 UNKNOWN, // 193C..193F
7551 LIMBU, // 1940
7552 UNKNOWN, // 1941..1943
7553 LIMBU, // 1944..194F
7554 TAI_LE, // 1950..196D
7555 UNKNOWN, // 196E..196F
7556 TAI_LE, // 1970..1974
7557 UNKNOWN, // 1975..197F
7558 NEW_TAI_LUE, // 1980..19AB
7559 UNKNOWN, // 19AC..19AF
7560 NEW_TAI_LUE, // 19B0..19C9
7561 UNKNOWN, // 19CA..19CF
7562 NEW_TAI_LUE, // 19D0..19DA
7563 UNKNOWN, // 19DB..19DD
7564 NEW_TAI_LUE, // 19DE..19DF
7565 KHMER, // 19E0..19FF
7566 BUGINESE, // 1A00..1A1B
7567 UNKNOWN, // 1A1C..1A1D
7568 BUGINESE, // 1A1E..1A1F
7569 TAI_THAM, // 1A20..1A5E
7570 UNKNOWN, // 1A5F
7571 TAI_THAM, // 1A60..1A7C
7572 UNKNOWN, // 1A7D..1A7E
7573 TAI_THAM, // 1A7F..1A89
7574 UNKNOWN, // 1A8A..1A8F
7575 TAI_THAM, // 1A90..1A99
7576 UNKNOWN, // 1A9A..1A9F
7577 TAI_THAM, // 1AA0..1AAD
7578 UNKNOWN, // 1AAE..1AAF
7579 INHERITED, // 1AB0..1ACE
7580 UNKNOWN, // 1ACF..1AFF
7581 BALINESE, // 1B00..1B4C
7582 UNKNOWN, // 1B4D..1B4F
7583 BALINESE, // 1B50..1B7E
7584 UNKNOWN, // 1B7F
7585 SUNDANESE, // 1B80..1BBF
7586 BATAK, // 1BC0..1BF3
7587 UNKNOWN, // 1BF4..1BFB
7588 BATAK, // 1BFC..1BFF
7589 LEPCHA, // 1C00..1C37
7590 UNKNOWN, // 1C38..1C3A
7591 LEPCHA, // 1C3B..1C49
7592 UNKNOWN, // 1C4A..1C4C
7593 LEPCHA, // 1C4D..1C4F
7594 OL_CHIKI, // 1C50..1C7F
7595 CYRILLIC, // 1C80..1C88
7596 UNKNOWN, // 1C89..1C8F
7597 GEORGIAN, // 1C90..1CBA
7598 UNKNOWN, // 1CBB..1CBC
7599 GEORGIAN, // 1CBD..1CBF
7600 SUNDANESE, // 1CC0..1CC7
7601 UNKNOWN, // 1CC8..1CCF
7602 INHERITED, // 1CD0..1CD2
7603 COMMON, // 1CD3
7604 INHERITED, // 1CD4..1CE0
7605 COMMON, // 1CE1
7606 INHERITED, // 1CE2..1CE8
7607 COMMON, // 1CE9..1CEC
7608 INHERITED, // 1CED
7609 COMMON, // 1CEE..1CF3
7610 INHERITED, // 1CF4
7611 COMMON, // 1CF5..1CF7
7612 INHERITED, // 1CF8..1CF9
7613 COMMON, // 1CFA
7614 UNKNOWN, // 1CFB..1CFF
7615 LATIN, // 1D00..1D25
7616 GREEK, // 1D26..1D2A
7617 CYRILLIC, // 1D2B
7618 LATIN, // 1D2C..1D5C
7619 GREEK, // 1D5D..1D61
7620 LATIN, // 1D62..1D65
7621 GREEK, // 1D66..1D6A
7622 LATIN, // 1D6B..1D77
7623 CYRILLIC, // 1D78
7624 LATIN, // 1D79..1DBE
7625 GREEK, // 1DBF
7626 INHERITED, // 1DC0..1DFF
7627 LATIN, // 1E00..1EFF
7628 GREEK, // 1F00..1F15
7629 UNKNOWN, // 1F16..1F17
7630 GREEK, // 1F18..1F1D
7631 UNKNOWN, // 1F1E..1F1F
7632 GREEK, // 1F20..1F45
7633 UNKNOWN, // 1F46..1F47
7634 GREEK, // 1F48..1F4D
7635 UNKNOWN, // 1F4E..1F4F
7636 GREEK, // 1F50..1F57
7637 UNKNOWN, // 1F58
7638 GREEK, // 1F59
7639 UNKNOWN, // 1F5A
7640 GREEK, // 1F5B
7641 UNKNOWN, // 1F5C
7642 GREEK, // 1F5D
7643 UNKNOWN, // 1F5E
7644 GREEK, // 1F5F..1F7D
7645 UNKNOWN, // 1F7E..1F7F
7646 GREEK, // 1F80..1FB4
7647 UNKNOWN, // 1FB5
7648 GREEK, // 1FB6..1FC4
7649 UNKNOWN, // 1FC5
7650 GREEK, // 1FC6..1FD3
7651 UNKNOWN, // 1FD4..1FD5
7652 GREEK, // 1FD6..1FDB
7653 UNKNOWN, // 1FDC
7654 GREEK, // 1FDD..1FEF
7655 UNKNOWN, // 1FF0..1FF1
7656 GREEK, // 1FF2..1FF4
7657 UNKNOWN, // 1FF5
7658 GREEK, // 1FF6..1FFE
7659 UNKNOWN, // 1FFF
7660 COMMON, // 2000..200B
7661 INHERITED, // 200C..200D
7662 COMMON, // 200E..2064
7663 UNKNOWN, // 2065
7664 COMMON, // 2066..2070
7665 LATIN, // 2071
7666 UNKNOWN, // 2072..2073
7667 COMMON, // 2074..207E
7668 LATIN, // 207F
7669 COMMON, // 2080..208E
7670 UNKNOWN, // 208F
7671 LATIN, // 2090..209C
7672 UNKNOWN, // 209D..209F
7673 COMMON, // 20A0..20C0
7674 UNKNOWN, // 20C1..20CF
7675 INHERITED, // 20D0..20F0
7676 UNKNOWN, // 20F1..20FF
7677 COMMON, // 2100..2125
7678 GREEK, // 2126
7679 COMMON, // 2127..2129
7680 LATIN, // 212A..212B
7681 COMMON, // 212C..2131
7682 LATIN, // 2132
7683 COMMON, // 2133..214D
7684 LATIN, // 214E
7685 COMMON, // 214F..215F
7686 LATIN, // 2160..2188
7687 COMMON, // 2189..218B
7688 UNKNOWN, // 218C..218F
7689 COMMON, // 2190..2426
7690 UNKNOWN, // 2427..243F
7691 COMMON, // 2440..244A
7692 UNKNOWN, // 244B..245F
7693 COMMON, // 2460..27FF
7694 BRAILLE, // 2800..28FF
7695 COMMON, // 2900..2B73
7696 UNKNOWN, // 2B74..2B75
7697 COMMON, // 2B76..2B95
7698 UNKNOWN, // 2B96
7699 COMMON, // 2B97..2BFF
7700 GLAGOLITIC, // 2C00..2C5F
7701 LATIN, // 2C60..2C7F
7702 COPTIC, // 2C80..2CF3
7703 UNKNOWN, // 2CF4..2CF8
7704 COPTIC, // 2CF9..2CFF
7705 GEORGIAN, // 2D00..2D25
7706 UNKNOWN, // 2D26
7707 GEORGIAN, // 2D27
7708 UNKNOWN, // 2D28..2D2C
7709 GEORGIAN, // 2D2D
7710 UNKNOWN, // 2D2E..2D2F
7711 TIFINAGH, // 2D30..2D67
7712 UNKNOWN, // 2D68..2D6E
7713 TIFINAGH, // 2D6F..2D70
7714 UNKNOWN, // 2D71..2D7E
7715 TIFINAGH, // 2D7F
7716 ETHIOPIC, // 2D80..2D96
7717 UNKNOWN, // 2D97..2D9F
7718 ETHIOPIC, // 2DA0..2DA6
7719 UNKNOWN, // 2DA7
7720 ETHIOPIC, // 2DA8..2DAE
7721 UNKNOWN, // 2DAF
7722 ETHIOPIC, // 2DB0..2DB6
7723 UNKNOWN, // 2DB7
7724 ETHIOPIC, // 2DB8..2DBE
7725 UNKNOWN, // 2DBF
7726 ETHIOPIC, // 2DC0..2DC6
7727 UNKNOWN, // 2DC7
7728 ETHIOPIC, // 2DC8..2DCE
7729 UNKNOWN, // 2DCF
7730 ETHIOPIC, // 2DD0..2DD6
7731 UNKNOWN, // 2DD7
7732 ETHIOPIC, // 2DD8..2DDE
7733 UNKNOWN, // 2DDF
7734 CYRILLIC, // 2DE0..2DFF
7735 COMMON, // 2E00..2E5D
7736 UNKNOWN, // 2E5E..2E7F
7737 HAN, // 2E80..2E99
7738 UNKNOWN, // 2E9A
7739 HAN, // 2E9B..2EF3
7740 UNKNOWN, // 2EF4..2EFF
7741 HAN, // 2F00..2FD5
7742 UNKNOWN, // 2FD6..2FEF
7743 COMMON, // 2FF0..3004
7744 HAN, // 3005
7745 COMMON, // 3006
7746 HAN, // 3007
7747 COMMON, // 3008..3020
7748 HAN, // 3021..3029
7749 INHERITED, // 302A..302D
7750 HANGUL, // 302E..302F
7751 COMMON, // 3030..3037
7752 HAN, // 3038..303B
7753 COMMON, // 303C..303F
7754 UNKNOWN, // 3040
7755 HIRAGANA, // 3041..3096
7756 UNKNOWN, // 3097..3098
7757 INHERITED, // 3099..309A
7758 COMMON, // 309B..309C
7759 HIRAGANA, // 309D..309F
7760 COMMON, // 30A0
7761 KATAKANA, // 30A1..30FA
7762 COMMON, // 30FB..30FC
7763 KATAKANA, // 30FD..30FF
7764 UNKNOWN, // 3100..3104
7765 BOPOMOFO, // 3105..312F
7766 UNKNOWN, // 3130
7767 HANGUL, // 3131..318E
7768 UNKNOWN, // 318F
7769 COMMON, // 3190..319F
7770 BOPOMOFO, // 31A0..31BF
7771 COMMON, // 31C0..31E3
7772 UNKNOWN, // 31E4..31EE
7773 COMMON, // 31EF
7774 KATAKANA, // 31F0..31FF
7775 HANGUL, // 3200..321E
7776 UNKNOWN, // 321F
7777 COMMON, // 3220..325F
7778 HANGUL, // 3260..327E
7779 COMMON, // 327F..32CF
7780 KATAKANA, // 32D0..32FE
7781 COMMON, // 32FF
7782 KATAKANA, // 3300..3357
7783 COMMON, // 3358..33FF
7784 HAN, // 3400..4DBF
7785 COMMON, // 4DC0..4DFF
7786 HAN, // 4E00..9FFF
7787 YI, // A000..A48C
7788 UNKNOWN, // A48D..A48F
7789 YI, // A490..A4C6
7790 UNKNOWN, // A4C7..A4CF
7791 LISU, // A4D0..A4FF
7792 VAI, // A500..A62B
7793 UNKNOWN, // A62C..A63F
7794 CYRILLIC, // A640..A69F
7795 BAMUM, // A6A0..A6F7
7796 UNKNOWN, // A6F8..A6FF
7797 COMMON, // A700..A721
7798 LATIN, // A722..A787
7799 COMMON, // A788..A78A
7800 LATIN, // A78B..A7CA
7801 UNKNOWN, // A7CB..A7CF
7802 LATIN, // A7D0..A7D1
7803 UNKNOWN, // A7D2
7804 LATIN, // A7D3
7805 UNKNOWN, // A7D4
7806 LATIN, // A7D5..A7D9
7807 UNKNOWN, // A7DA..A7F1
7808 LATIN, // A7F2..A7FF
7809 SYLOTI_NAGRI, // A800..A82C
7810 UNKNOWN, // A82D..A82F
7811 COMMON, // A830..A839
7812 UNKNOWN, // A83A..A83F
7813 PHAGS_PA, // A840..A877
7814 UNKNOWN, // A878..A87F
7815 SAURASHTRA, // A880..A8C5
7816 UNKNOWN, // A8C6..A8CD
7817 SAURASHTRA, // A8CE..A8D9
7818 UNKNOWN, // A8DA..A8DF
7819 DEVANAGARI, // A8E0..A8FF
7820 KAYAH_LI, // A900..A92D
7821 COMMON, // A92E
7822 KAYAH_LI, // A92F
7823 REJANG, // A930..A953
7824 UNKNOWN, // A954..A95E
7825 REJANG, // A95F
7826 HANGUL, // A960..A97C
7827 UNKNOWN, // A97D..A97F
7828 JAVANESE, // A980..A9CD
7829 UNKNOWN, // A9CE
7830 COMMON, // A9CF
7831 JAVANESE, // A9D0..A9D9
7832 UNKNOWN, // A9DA..A9DD
7833 JAVANESE, // A9DE..A9DF
7834 MYANMAR, // A9E0..A9FE
7835 UNKNOWN, // A9FF
7836 CHAM, // AA00..AA36
7837 UNKNOWN, // AA37..AA3F
7838 CHAM, // AA40..AA4D
7839 UNKNOWN, // AA4E..AA4F
7840 CHAM, // AA50..AA59
7841 UNKNOWN, // AA5A..AA5B
7842 CHAM, // AA5C..AA5F
7843 MYANMAR, // AA60..AA7F
7844 TAI_VIET, // AA80..AAC2
7845 UNKNOWN, // AAC3..AADA
7846 TAI_VIET, // AADB..AADF
7847 MEETEI_MAYEK, // AAE0..AAF6
7848 UNKNOWN, // AAF7..AB00
7849 ETHIOPIC, // AB01..AB06
7850 UNKNOWN, // AB07..AB08
7851 ETHIOPIC, // AB09..AB0E
7852 UNKNOWN, // AB0F..AB10
7853 ETHIOPIC, // AB11..AB16
7854 UNKNOWN, // AB17..AB1F
7855 ETHIOPIC, // AB20..AB26
7856 UNKNOWN, // AB27
7857 ETHIOPIC, // AB28..AB2E
7858 UNKNOWN, // AB2F
7859 LATIN, // AB30..AB5A
7860 COMMON, // AB5B
7861 LATIN, // AB5C..AB64
7862 GREEK, // AB65
7863 LATIN, // AB66..AB69
7864 COMMON, // AB6A..AB6B
7865 UNKNOWN, // AB6C..AB6F
7866 CHEROKEE, // AB70..ABBF
7867 MEETEI_MAYEK, // ABC0..ABED
7868 UNKNOWN, // ABEE..ABEF
7869 MEETEI_MAYEK, // ABF0..ABF9
7870 UNKNOWN, // ABFA..ABFF
7871 HANGUL, // AC00..D7A3
7872 UNKNOWN, // D7A4..D7AF
7873 HANGUL, // D7B0..D7C6
7874 UNKNOWN, // D7C7..D7CA
7875 HANGUL, // D7CB..D7FB
7876 UNKNOWN, // D7FC..F8FF
7877 HAN, // F900..FA6D
7878 UNKNOWN, // FA6E..FA6F
7879 HAN, // FA70..FAD9
7880 UNKNOWN, // FADA..FAFF
7881 LATIN, // FB00..FB06
7882 UNKNOWN, // FB07..FB12
7883 ARMENIAN, // FB13..FB17
7884 UNKNOWN, // FB18..FB1C
7885 HEBREW, // FB1D..FB36
7886 UNKNOWN, // FB37
7887 HEBREW, // FB38..FB3C
7888 UNKNOWN, // FB3D
7889 HEBREW, // FB3E
7890 UNKNOWN, // FB3F
7891 HEBREW, // FB40..FB41
7892 UNKNOWN, // FB42
7893 HEBREW, // FB43..FB44
7894 UNKNOWN, // FB45
7895 HEBREW, // FB46..FB4F
7896 ARABIC, // FB50..FBC2
7897 UNKNOWN, // FBC3..FBD2
7898 ARABIC, // FBD3..FD3D
7899 COMMON, // FD3E..FD3F
7900 ARABIC, // FD40..FD8F
7901 UNKNOWN, // FD90..FD91
7902 ARABIC, // FD92..FDC7
7903 UNKNOWN, // FDC8..FDCE
7904 ARABIC, // FDCF
7905 UNKNOWN, // FDD0..FDEF
7906 ARABIC, // FDF0..FDFF
7907 INHERITED, // FE00..FE0F
7908 COMMON, // FE10..FE19
7909 UNKNOWN, // FE1A..FE1F
7910 INHERITED, // FE20..FE2D
7911 CYRILLIC, // FE2E..FE2F
7912 COMMON, // FE30..FE52
7913 UNKNOWN, // FE53
7914 COMMON, // FE54..FE66
7915 UNKNOWN, // FE67
7916 COMMON, // FE68..FE6B
7917 UNKNOWN, // FE6C..FE6F
7918 ARABIC, // FE70..FE74
7919 UNKNOWN, // FE75
7920 ARABIC, // FE76..FEFC
7921 UNKNOWN, // FEFD..FEFE
7922 COMMON, // FEFF
7923 UNKNOWN, // FF00
7924 COMMON, // FF01..FF20
7925 LATIN, // FF21..FF3A
7926 COMMON, // FF3B..FF40
7927 LATIN, // FF41..FF5A
7928 COMMON, // FF5B..FF65
7929 KATAKANA, // FF66..FF6F
7930 COMMON, // FF70
7931 KATAKANA, // FF71..FF9D
7932 COMMON, // FF9E..FF9F
7933 HANGUL, // FFA0..FFBE
7934 UNKNOWN, // FFBF..FFC1
7935 HANGUL, // FFC2..FFC7
7936 UNKNOWN, // FFC8..FFC9
7937 HANGUL, // FFCA..FFCF
7938 UNKNOWN, // FFD0..FFD1
7939 HANGUL, // FFD2..FFD7
7940 UNKNOWN, // FFD8..FFD9
7941 HANGUL, // FFDA..FFDC
7942 UNKNOWN, // FFDD..FFDF
7943 COMMON, // FFE0..FFE6
7944 UNKNOWN, // FFE7
7945 COMMON, // FFE8..FFEE
7946 UNKNOWN, // FFEF..FFF8
7947 COMMON, // FFF9..FFFD
7948 UNKNOWN, // FFFE..FFFF
7949 LINEAR_B, // 10000..1000B
7950 UNKNOWN, // 1000C
7951 LINEAR_B, // 1000D..10026
7952 UNKNOWN, // 10027
7953 LINEAR_B, // 10028..1003A
7954 UNKNOWN, // 1003B
7955 LINEAR_B, // 1003C..1003D
7956 UNKNOWN, // 1003E
7957 LINEAR_B, // 1003F..1004D
7958 UNKNOWN, // 1004E..1004F
7959 LINEAR_B, // 10050..1005D
7960 UNKNOWN, // 1005E..1007F
7961 LINEAR_B, // 10080..100FA
7962 UNKNOWN, // 100FB..100FF
7963 COMMON, // 10100..10102
7964 UNKNOWN, // 10103..10106
7965 COMMON, // 10107..10133
7966 UNKNOWN, // 10134..10136
7967 COMMON, // 10137..1013F
7968 GREEK, // 10140..1018E
7969 UNKNOWN, // 1018F
7970 COMMON, // 10190..1019C
7971 UNKNOWN, // 1019D..1019F
7972 GREEK, // 101A0
7973 UNKNOWN, // 101A1..101CF
7974 COMMON, // 101D0..101FC
7975 INHERITED, // 101FD
7976 UNKNOWN, // 101FE..1027F
7977 LYCIAN, // 10280..1029C
7978 UNKNOWN, // 1029D..1029F
7979 CARIAN, // 102A0..102D0
7980 UNKNOWN, // 102D1..102DF
7981 INHERITED, // 102E0
7982 COMMON, // 102E1..102FB
7983 UNKNOWN, // 102FC..102FF
7984 OLD_ITALIC, // 10300..10323
7985 UNKNOWN, // 10324..1032C
7986 OLD_ITALIC, // 1032D..1032F
7987 GOTHIC, // 10330..1034A
7988 UNKNOWN, // 1034B..1034F
7989 OLD_PERMIC, // 10350..1037A
7990 UNKNOWN, // 1037B..1037F
7991 UGARITIC, // 10380..1039D
7992 UNKNOWN, // 1039E
7993 UGARITIC, // 1039F
7994 OLD_PERSIAN, // 103A0..103C3
7995 UNKNOWN, // 103C4..103C7
7996 OLD_PERSIAN, // 103C8..103D5
7997 UNKNOWN, // 103D6..103FF
7998 DESERET, // 10400..1044F
7999 SHAVIAN, // 10450..1047F
8000 OSMANYA, // 10480..1049D
8001 UNKNOWN, // 1049E..1049F
8002 OSMANYA, // 104A0..104A9
8003 UNKNOWN, // 104AA..104AF
8004 OSAGE, // 104B0..104D3
8005 UNKNOWN, // 104D4..104D7
8006 OSAGE, // 104D8..104FB
8007 UNKNOWN, // 104FC..104FF
8008 ELBASAN, // 10500..10527
8009 UNKNOWN, // 10528..1052F
8010 CAUCASIAN_ALBANIAN, // 10530..10563
8011 UNKNOWN, // 10564..1056E
8012 CAUCASIAN_ALBANIAN, // 1056F
8013 VITHKUQI, // 10570..1057A
8014 UNKNOWN, // 1057B
8015 VITHKUQI, // 1057C..1058A
8016 UNKNOWN, // 1058B
8017 VITHKUQI, // 1058C..10592
8018 UNKNOWN, // 10593
8019 VITHKUQI, // 10594..10595
8020 UNKNOWN, // 10596
8021 VITHKUQI, // 10597..105A1
8022 UNKNOWN, // 105A2
8023 VITHKUQI, // 105A3..105B1
8024 UNKNOWN, // 105B2
8025 VITHKUQI, // 105B3..105B9
8026 UNKNOWN, // 105BA
8027 VITHKUQI, // 105BB..105BC
8028 UNKNOWN, // 105BD..105FF
8029 LINEAR_A, // 10600..10736
8030 UNKNOWN, // 10737..1073F
8031 LINEAR_A, // 10740..10755
8032 UNKNOWN, // 10756..1075F
8033 LINEAR_A, // 10760..10767
8034 UNKNOWN, // 10768..1077F
8035 LATIN, // 10780..10785
8036 UNKNOWN, // 10786
8037 LATIN, // 10787..107B0
8038 UNKNOWN, // 107B1
8039 LATIN, // 107B2..107BA
8040 UNKNOWN, // 107BB..107FF
8041 CYPRIOT, // 10800..10805
8042 UNKNOWN, // 10806..10807
8043 CYPRIOT, // 10808
8044 UNKNOWN, // 10809
8045 CYPRIOT, // 1080A..10835
8046 UNKNOWN, // 10836
8047 CYPRIOT, // 10837..10838
8048 UNKNOWN, // 10839..1083B
8049 CYPRIOT, // 1083C
8050 UNKNOWN, // 1083D..1083E
8051 CYPRIOT, // 1083F
8052 IMPERIAL_ARAMAIC, // 10840..10855
8053 UNKNOWN, // 10856
8054 IMPERIAL_ARAMAIC, // 10857..1085F
8055 PALMYRENE, // 10860..1087F
8056 NABATAEAN, // 10880..1089E
8057 UNKNOWN, // 1089F..108A6
8058 NABATAEAN, // 108A7..108AF
8059 UNKNOWN, // 108B0..108DF
8060 HATRAN, // 108E0..108F2
8061 UNKNOWN, // 108F3
8062 HATRAN, // 108F4..108F5
8063 UNKNOWN, // 108F6..108FA
8064 HATRAN, // 108FB..108FF
8065 PHOENICIAN, // 10900..1091B
8066 UNKNOWN, // 1091C..1091E
8067 PHOENICIAN, // 1091F
8068 LYDIAN, // 10920..10939
8069 UNKNOWN, // 1093A..1093E
8070 LYDIAN, // 1093F
8071 UNKNOWN, // 10940..1097F
8072 MEROITIC_HIEROGLYPHS, // 10980..1099F
8073 MEROITIC_CURSIVE, // 109A0..109B7
8074 UNKNOWN, // 109B8..109BB
8075 MEROITIC_CURSIVE, // 109BC..109CF
8076 UNKNOWN, // 109D0..109D1
8077 MEROITIC_CURSIVE, // 109D2..109FF
8078 KHAROSHTHI, // 10A00..10A03
8079 UNKNOWN, // 10A04
8080 KHAROSHTHI, // 10A05..10A06
8081 UNKNOWN, // 10A07..10A0B
8082 KHAROSHTHI, // 10A0C..10A13
8083 UNKNOWN, // 10A14
8084 KHAROSHTHI, // 10A15..10A17
8085 UNKNOWN, // 10A18
8086 KHAROSHTHI, // 10A19..10A35
8087 UNKNOWN, // 10A36..10A37
8088 KHAROSHTHI, // 10A38..10A3A
8089 UNKNOWN, // 10A3B..10A3E
8090 KHAROSHTHI, // 10A3F..10A48
8091 UNKNOWN, // 10A49..10A4F
8092 KHAROSHTHI, // 10A50..10A58
8093 UNKNOWN, // 10A59..10A5F
8094 OLD_SOUTH_ARABIAN, // 10A60..10A7F
8095 OLD_NORTH_ARABIAN, // 10A80..10A9F
8096 UNKNOWN, // 10AA0..10ABF
8097 MANICHAEAN, // 10AC0..10AE6
8098 UNKNOWN, // 10AE7..10AEA
8099 MANICHAEAN, // 10AEB..10AF6
8100 UNKNOWN, // 10AF7..10AFF
8101 AVESTAN, // 10B00..10B35
8102 UNKNOWN, // 10B36..10B38
8103 AVESTAN, // 10B39..10B3F
8104 INSCRIPTIONAL_PARTHIAN, // 10B40..10B55
8105 UNKNOWN, // 10B56..10B57
8106 INSCRIPTIONAL_PARTHIAN, // 10B58..10B5F
8107 INSCRIPTIONAL_PAHLAVI, // 10B60..10B72
8108 UNKNOWN, // 10B73..10B77
8109 INSCRIPTIONAL_PAHLAVI, // 10B78..10B7F
8110 PSALTER_PAHLAVI, // 10B80..10B91
8111 UNKNOWN, // 10B92..10B98
8112 PSALTER_PAHLAVI, // 10B99..10B9C
8113 UNKNOWN, // 10B9D..10BA8
8114 PSALTER_PAHLAVI, // 10BA9..10BAF
8115 UNKNOWN, // 10BB0..10BFF
8116 OLD_TURKIC, // 10C00..10C48
8117 UNKNOWN, // 10C49..10C7F
8118 OLD_HUNGARIAN, // 10C80..10CB2
8119 UNKNOWN, // 10CB3..10CBF
8120 OLD_HUNGARIAN, // 10CC0..10CF2
8121 UNKNOWN, // 10CF3..10CF9
8122 OLD_HUNGARIAN, // 10CFA..10CFF
8123 HANIFI_ROHINGYA, // 10D00..10D27
8124 UNKNOWN, // 10D28..10D2F
8125 HANIFI_ROHINGYA, // 10D30..10D39
8126 UNKNOWN, // 10D3A..10E5F
8127 ARABIC, // 10E60..10E7E
8128 UNKNOWN, // 10E7F
8129 YEZIDI, // 10E80..10EA9
8130 UNKNOWN, // 10EAA
8131 YEZIDI, // 10EAB..10EAD
8132 UNKNOWN, // 10EAE..10EAF
8133 YEZIDI, // 10EB0..10EB1
8134 UNKNOWN, // 10EB2..10EFC
8135 ARABIC, // 10EFD..10EFF
8136 OLD_SOGDIAN, // 10F00..10F27
8137 UNKNOWN, // 10F28..10F2F
8138 SOGDIAN, // 10F30..10F59
8139 UNKNOWN, // 10F5A..10F6F
8140 OLD_UYGHUR, // 10F70..10F89
8141 UNKNOWN, // 10F8A..10FAF
8142 CHORASMIAN, // 10FB0..10FCB
8143 UNKNOWN, // 10FCC..10FDF
8144 ELYMAIC, // 10FE0..10FF6
8145 UNKNOWN, // 10FF7..10FFF
8146 BRAHMI, // 11000..1104D
8147 UNKNOWN, // 1104E..11051
8148 BRAHMI, // 11052..11075
8149 UNKNOWN, // 11076..1107E
8150 BRAHMI, // 1107F
8151 KAITHI, // 11080..110C2
8152 UNKNOWN, // 110C3..110CC
8153 KAITHI, // 110CD
8154 UNKNOWN, // 110CE..110CF
8155 SORA_SOMPENG, // 110D0..110E8
8156 UNKNOWN, // 110E9..110EF
8157 SORA_SOMPENG, // 110F0..110F9
8158 UNKNOWN, // 110FA..110FF
8159 CHAKMA, // 11100..11134
8160 UNKNOWN, // 11135
8161 CHAKMA, // 11136..11147
8162 UNKNOWN, // 11148..1114F
8163 MAHAJANI, // 11150..11176
8164 UNKNOWN, // 11177..1117F
8165 SHARADA, // 11180..111DF
8166 UNKNOWN, // 111E0
8167 SINHALA, // 111E1..111F4
8168 UNKNOWN, // 111F5..111FF
8169 KHOJKI, // 11200..11211
8170 UNKNOWN, // 11212
8171 KHOJKI, // 11213..11241
8172 UNKNOWN, // 11242..1127F
8173 MULTANI, // 11280..11286
8174 UNKNOWN, // 11287
8175 MULTANI, // 11288
8176 UNKNOWN, // 11289
8177 MULTANI, // 1128A..1128D
8178 UNKNOWN, // 1128E
8179 MULTANI, // 1128F..1129D
8180 UNKNOWN, // 1129E
8181 MULTANI, // 1129F..112A9
8182 UNKNOWN, // 112AA..112AF
8183 KHUDAWADI, // 112B0..112EA
8184 UNKNOWN, // 112EB..112EF
8185 KHUDAWADI, // 112F0..112F9
8186 UNKNOWN, // 112FA..112FF
8187 GRANTHA, // 11300..11303
8188 UNKNOWN, // 11304
8189 GRANTHA, // 11305..1130C
8190 UNKNOWN, // 1130D..1130E
8191 GRANTHA, // 1130F..11310
8192 UNKNOWN, // 11311..11312
8193 GRANTHA, // 11313..11328
8194 UNKNOWN, // 11329
8195 GRANTHA, // 1132A..11330
8196 UNKNOWN, // 11331
8197 GRANTHA, // 11332..11333
8198 UNKNOWN, // 11334
8199 GRANTHA, // 11335..11339
8200 UNKNOWN, // 1133A
8201 INHERITED, // 1133B
8202 GRANTHA, // 1133C..11344
8203 UNKNOWN, // 11345..11346
8204 GRANTHA, // 11347..11348
8205 UNKNOWN, // 11349..1134A
8206 GRANTHA, // 1134B..1134D
8207 UNKNOWN, // 1134E..1134F
8208 GRANTHA, // 11350
8209 UNKNOWN, // 11351..11356
8210 GRANTHA, // 11357
8211 UNKNOWN, // 11358..1135C
8212 GRANTHA, // 1135D..11363
8213 UNKNOWN, // 11364..11365
8214 GRANTHA, // 11366..1136C
8215 UNKNOWN, // 1136D..1136F
8216 GRANTHA, // 11370..11374
8217 UNKNOWN, // 11375..113FF
8218 NEWA, // 11400..1145B
8219 UNKNOWN, // 1145C
8220 NEWA, // 1145D..11461
8221 UNKNOWN, // 11462..1147F
8222 TIRHUTA, // 11480..114C7
8223 UNKNOWN, // 114C8..114CF
8224 TIRHUTA, // 114D0..114D9
8225 UNKNOWN, // 114DA..1157F
8226 SIDDHAM, // 11580..115B5
8227 UNKNOWN, // 115B6..115B7
8228 SIDDHAM, // 115B8..115DD
8229 UNKNOWN, // 115DE..115FF
8230 MODI, // 11600..11644
8231 UNKNOWN, // 11645..1164F
8232 MODI, // 11650..11659
8233 UNKNOWN, // 1165A..1165F
8234 MONGOLIAN, // 11660..1166C
8235 UNKNOWN, // 1166D..1167F
8236 TAKRI, // 11680..116B9
8237 UNKNOWN, // 116BA..116BF
8238 TAKRI, // 116C0..116C9
8239 UNKNOWN, // 116CA..116FF
8240 AHOM, // 11700..1171A
8241 UNKNOWN, // 1171B..1171C
8242 AHOM, // 1171D..1172B
8243 UNKNOWN, // 1172C..1172F
8244 AHOM, // 11730..11746
8245 UNKNOWN, // 11747..117FF
8246 DOGRA, // 11800..1183B
8247 UNKNOWN, // 1183C..1189F
8248 WARANG_CITI, // 118A0..118F2
8249 UNKNOWN, // 118F3..118FE
8250 WARANG_CITI, // 118FF
8251 DIVES_AKURU, // 11900..11906
8252 UNKNOWN, // 11907..11908
8253 DIVES_AKURU, // 11909
8254 UNKNOWN, // 1190A..1190B
8255 DIVES_AKURU, // 1190C..11913
8256 UNKNOWN, // 11914
8257 DIVES_AKURU, // 11915..11916
8258 UNKNOWN, // 11917
8259 DIVES_AKURU, // 11918..11935
8260 UNKNOWN, // 11936
8261 DIVES_AKURU, // 11937..11938
8262 UNKNOWN, // 11939..1193A
8263 DIVES_AKURU, // 1193B..11946
8264 UNKNOWN, // 11947..1194F
8265 DIVES_AKURU, // 11950..11959
8266 UNKNOWN, // 1195A..1199F
8267 NANDINAGARI, // 119A0..119A7
8268 UNKNOWN, // 119A8..119A9
8269 NANDINAGARI, // 119AA..119D7
8270 UNKNOWN, // 119D8..119D9
8271 NANDINAGARI, // 119DA..119E4
8272 UNKNOWN, // 119E5..119FF
8273 ZANABAZAR_SQUARE, // 11A00..11A47
8274 UNKNOWN, // 11A48..11A4F
8275 SOYOMBO, // 11A50..11AA2
8276 UNKNOWN, // 11AA3..11AAF
8277 CANADIAN_ABORIGINAL, // 11AB0..11ABF
8278 PAU_CIN_HAU, // 11AC0..11AF8
8279 UNKNOWN, // 11AF9..11AFF
8280 DEVANAGARI, // 11B00..11B09
8281 UNKNOWN, // 11B0A..11BFF
8282 BHAIKSUKI, // 11C00..11C08
8283 UNKNOWN, // 11C09
8284 BHAIKSUKI, // 11C0A..11C36
8285 UNKNOWN, // 11C37
8286 BHAIKSUKI, // 11C38..11C45
8287 UNKNOWN, // 11C46..11C4F
8288 BHAIKSUKI, // 11C50..11C6C
8289 UNKNOWN, // 11C6D..11C6F
8290 MARCHEN, // 11C70..11C8F
8291 UNKNOWN, // 11C90..11C91
8292 MARCHEN, // 11C92..11CA7
8293 UNKNOWN, // 11CA8
8294 MARCHEN, // 11CA9..11CB6
8295 UNKNOWN, // 11CB7..11CFF
8296 MASARAM_GONDI, // 11D00..11D06
8297 UNKNOWN, // 11D07
8298 MASARAM_GONDI, // 11D08..11D09
8299 UNKNOWN, // 11D0A
8300 MASARAM_GONDI, // 11D0B..11D36
8301 UNKNOWN, // 11D37..11D39
8302 MASARAM_GONDI, // 11D3A
8303 UNKNOWN, // 11D3B
8304 MASARAM_GONDI, // 11D3C..11D3D
8305 UNKNOWN, // 11D3E
8306 MASARAM_GONDI, // 11D3F..11D47
8307 UNKNOWN, // 11D48..11D4F
8308 MASARAM_GONDI, // 11D50..11D59
8309 UNKNOWN, // 11D5A..11D5F
8310 GUNJALA_GONDI, // 11D60..11D65
8311 UNKNOWN, // 11D66
8312 GUNJALA_GONDI, // 11D67..11D68
8313 UNKNOWN, // 11D69
8314 GUNJALA_GONDI, // 11D6A..11D8E
8315 UNKNOWN, // 11D8F
8316 GUNJALA_GONDI, // 11D90..11D91
8317 UNKNOWN, // 11D92
8318 GUNJALA_GONDI, // 11D93..11D98
8319 UNKNOWN, // 11D99..11D9F
8320 GUNJALA_GONDI, // 11DA0..11DA9
8321 UNKNOWN, // 11DAA..11EDF
8322 MAKASAR, // 11EE0..11EF8
8323 UNKNOWN, // 11EF9..11EFF
8324 KAWI, // 11F00..11F10
8325 UNKNOWN, // 11F11
8326 KAWI, // 11F12..11F3A
8327 UNKNOWN, // 11F3B..11F3D
8328 KAWI, // 11F3E..11F59
8329 UNKNOWN, // 11F5A..11FAF
8330 LISU, // 11FB0
8331 UNKNOWN, // 11FB1..11FBF
8332 TAMIL, // 11FC0..11FF1
8333 UNKNOWN, // 11FF2..11FFE
8334 TAMIL, // 11FFF
8335 CUNEIFORM, // 12000..12399
8336 UNKNOWN, // 1239A..123FF
8337 CUNEIFORM, // 12400..1246E
8338 UNKNOWN, // 1246F
8339 CUNEIFORM, // 12470..12474
8340 UNKNOWN, // 12475..1247F
8341 CUNEIFORM, // 12480..12543
8342 UNKNOWN, // 12544..12F8F
8343 CYPRO_MINOAN, // 12F90..12FF2
8344 UNKNOWN, // 12FF3..12FFF
8345 EGYPTIAN_HIEROGLYPHS, // 13000..13455
8346 UNKNOWN, // 13456..143FF
8347 ANATOLIAN_HIEROGLYPHS, // 14400..14646
8348 UNKNOWN, // 14647..167FF
8349 BAMUM, // 16800..16A38
8350 UNKNOWN, // 16A39..16A3F
8351 MRO, // 16A40..16A5E
8352 UNKNOWN, // 16A5F
8353 MRO, // 16A60..16A69
8354 UNKNOWN, // 16A6A..16A6D
8355 MRO, // 16A6E..16A6F
8356 TANGSA, // 16A70..16ABE
8357 UNKNOWN, // 16ABF
8358 TANGSA, // 16AC0..16AC9
8359 UNKNOWN, // 16ACA..16ACF
8360 BASSA_VAH, // 16AD0..16AED
8361 UNKNOWN, // 16AEE..16AEF
8362 BASSA_VAH, // 16AF0..16AF5
8363 UNKNOWN, // 16AF6..16AFF
8364 PAHAWH_HMONG, // 16B00..16B45
8365 UNKNOWN, // 16B46..16B4F
8366 PAHAWH_HMONG, // 16B50..16B59
8367 UNKNOWN, // 16B5A
8368 PAHAWH_HMONG, // 16B5B..16B61
8369 UNKNOWN, // 16B62
8370 PAHAWH_HMONG, // 16B63..16B77
8371 UNKNOWN, // 16B78..16B7C
8372 PAHAWH_HMONG, // 16B7D..16B8F
8373 UNKNOWN, // 16B90..16E3F
8374 MEDEFAIDRIN, // 16E40..16E9A
8375 UNKNOWN, // 16E9B..16EFF
8376 MIAO, // 16F00..16F4A
8377 UNKNOWN, // 16F4B..16F4E
8378 MIAO, // 16F4F..16F87
8379 UNKNOWN, // 16F88..16F8E
8380 MIAO, // 16F8F..16F9F
8381 UNKNOWN, // 16FA0..16FDF
8382 TANGUT, // 16FE0
8383 NUSHU, // 16FE1
8384 HAN, // 16FE2..16FE3
8385 KHITAN_SMALL_SCRIPT, // 16FE4
8386 UNKNOWN, // 16FE5..16FEF
8387 HAN, // 16FF0..16FF1
8388 UNKNOWN, // 16FF2..16FFF
8389 TANGUT, // 17000..187F7
8390 UNKNOWN, // 187F8..187FF
8391 TANGUT, // 18800..18AFF
8392 KHITAN_SMALL_SCRIPT, // 18B00..18CD5
8393 UNKNOWN, // 18CD6..18CFF
8394 TANGUT, // 18D00..18D08
8395 UNKNOWN, // 18D09..1AFEF
8396 KATAKANA, // 1AFF0..1AFF3
8397 UNKNOWN, // 1AFF4
8398 KATAKANA, // 1AFF5..1AFFB
8399 UNKNOWN, // 1AFFC
8400 KATAKANA, // 1AFFD..1AFFE
8401 UNKNOWN, // 1AFFF
8402 KATAKANA, // 1B000
8403 HIRAGANA, // 1B001..1B11F
8404 KATAKANA, // 1B120..1B122
8405 UNKNOWN, // 1B123..1B131
8406 HIRAGANA, // 1B132
8407 UNKNOWN, // 1B133..1B14F
8408 HIRAGANA, // 1B150..1B152
8409 UNKNOWN, // 1B153..1B154
8410 KATAKANA, // 1B155
8411 UNKNOWN, // 1B156..1B163
8412 KATAKANA, // 1B164..1B167
8413 UNKNOWN, // 1B168..1B16F
8414 NUSHU, // 1B170..1B2FB
8415 UNKNOWN, // 1B2FC..1BBFF
8416 DUPLOYAN, // 1BC00..1BC6A
8417 UNKNOWN, // 1BC6B..1BC6F
8418 DUPLOYAN, // 1BC70..1BC7C
8419 UNKNOWN, // 1BC7D..1BC7F
8420 DUPLOYAN, // 1BC80..1BC88
8421 UNKNOWN, // 1BC89..1BC8F
8422 DUPLOYAN, // 1BC90..1BC99
8423 UNKNOWN, // 1BC9A..1BC9B
8424 DUPLOYAN, // 1BC9C..1BC9F
8425 COMMON, // 1BCA0..1BCA3
8426 UNKNOWN, // 1BCA4..1CEFF
8427 INHERITED, // 1CF00..1CF2D
8428 UNKNOWN, // 1CF2E..1CF2F
8429 INHERITED, // 1CF30..1CF46
8430 UNKNOWN, // 1CF47..1CF4F
8431 COMMON, // 1CF50..1CFC3
8432 UNKNOWN, // 1CFC4..1CFFF
8433 COMMON, // 1D000..1D0F5
8434 UNKNOWN, // 1D0F6..1D0FF
8435 COMMON, // 1D100..1D126
8436 UNKNOWN, // 1D127..1D128
8437 COMMON, // 1D129..1D166
8438 INHERITED, // 1D167..1D169
8439 COMMON, // 1D16A..1D17A
8440 INHERITED, // 1D17B..1D182
8441 COMMON, // 1D183..1D184
8442 INHERITED, // 1D185..1D18B
8443 COMMON, // 1D18C..1D1A9
8444 INHERITED, // 1D1AA..1D1AD
8445 COMMON, // 1D1AE..1D1EA
8446 UNKNOWN, // 1D1EB..1D1FF
8447 GREEK, // 1D200..1D245
8448 UNKNOWN, // 1D246..1D2BF
8449 COMMON, // 1D2C0..1D2D3
8450 UNKNOWN, // 1D2D4..1D2DF
8451 COMMON, // 1D2E0..1D2F3
8452 UNKNOWN, // 1D2F4..1D2FF
8453 COMMON, // 1D300..1D356
8454 UNKNOWN, // 1D357..1D35F
8455 COMMON, // 1D360..1D378
8456 UNKNOWN, // 1D379..1D3FF
8457 COMMON, // 1D400..1D454
8458 UNKNOWN, // 1D455
8459 COMMON, // 1D456..1D49C
8460 UNKNOWN, // 1D49D
8461 COMMON, // 1D49E..1D49F
8462 UNKNOWN, // 1D4A0..1D4A1
8463 COMMON, // 1D4A2
8464 UNKNOWN, // 1D4A3..1D4A4
8465 COMMON, // 1D4A5..1D4A6
8466 UNKNOWN, // 1D4A7..1D4A8
8467 COMMON, // 1D4A9..1D4AC
8468 UNKNOWN, // 1D4AD
8469 COMMON, // 1D4AE..1D4B9
8470 UNKNOWN, // 1D4BA
8471 COMMON, // 1D4BB
8472 UNKNOWN, // 1D4BC
8473 COMMON, // 1D4BD..1D4C3
8474 UNKNOWN, // 1D4C4
8475 COMMON, // 1D4C5..1D505
8476 UNKNOWN, // 1D506
8477 COMMON, // 1D507..1D50A
8478 UNKNOWN, // 1D50B..1D50C
8479 COMMON, // 1D50D..1D514
8480 UNKNOWN, // 1D515
8481 COMMON, // 1D516..1D51C
8482 UNKNOWN, // 1D51D
8483 COMMON, // 1D51E..1D539
8484 UNKNOWN, // 1D53A
8485 COMMON, // 1D53B..1D53E
8486 UNKNOWN, // 1D53F
8487 COMMON, // 1D540..1D544
8488 UNKNOWN, // 1D545
8489 COMMON, // 1D546
8490 UNKNOWN, // 1D547..1D549
8491 COMMON, // 1D54A..1D550
8492 UNKNOWN, // 1D551
8493 COMMON, // 1D552..1D6A5
8494 UNKNOWN, // 1D6A6..1D6A7
8495 COMMON, // 1D6A8..1D7CB
8496 UNKNOWN, // 1D7CC..1D7CD
8497 COMMON, // 1D7CE..1D7FF
8498 SIGNWRITING, // 1D800..1DA8B
8499 UNKNOWN, // 1DA8C..1DA9A
8500 SIGNWRITING, // 1DA9B..1DA9F
8501 UNKNOWN, // 1DAA0
8502 SIGNWRITING, // 1DAA1..1DAAF
8503 UNKNOWN, // 1DAB0..1DEFF
8504 LATIN, // 1DF00..1DF1E
8505 UNKNOWN, // 1DF1F..1DF24
8506 LATIN, // 1DF25..1DF2A
8507 UNKNOWN, // 1DF2B..1DFFF
8508 GLAGOLITIC, // 1E000..1E006
8509 UNKNOWN, // 1E007
8510 GLAGOLITIC, // 1E008..1E018
8511 UNKNOWN, // 1E019..1E01A
8512 GLAGOLITIC, // 1E01B..1E021
8513 UNKNOWN, // 1E022
8514 GLAGOLITIC, // 1E023..1E024
8515 UNKNOWN, // 1E025
8516 GLAGOLITIC, // 1E026..1E02A
8517 UNKNOWN, // 1E02B..1E02F
8518 CYRILLIC, // 1E030..1E06D
8519 UNKNOWN, // 1E06E..1E08E
8520 CYRILLIC, // 1E08F
8521 UNKNOWN, // 1E090..1E0FF
8522 NYIAKENG_PUACHUE_HMONG, // 1E100..1E12C
8523 UNKNOWN, // 1E12D..1E12F
8524 NYIAKENG_PUACHUE_HMONG, // 1E130..1E13D
8525 UNKNOWN, // 1E13E..1E13F
8526 NYIAKENG_PUACHUE_HMONG, // 1E140..1E149
8527 UNKNOWN, // 1E14A..1E14D
8528 NYIAKENG_PUACHUE_HMONG, // 1E14E..1E14F
8529 UNKNOWN, // 1E150..1E28F
8530 TOTO, // 1E290..1E2AE
8531 UNKNOWN, // 1E2AF..1E2BF
8532 WANCHO, // 1E2C0..1E2F9
8533 UNKNOWN, // 1E2FA..1E2FE
8534 WANCHO, // 1E2FF
8535 UNKNOWN, // 1E300..1E4CF
8536 NAG_MUNDARI, // 1E4D0..1E4F9
8537 UNKNOWN, // 1E4FA..1E7DF
8538 ETHIOPIC, // 1E7E0..1E7E6
8539 UNKNOWN, // 1E7E7
8540 ETHIOPIC, // 1E7E8..1E7EB
8541 UNKNOWN, // 1E7EC
8542 ETHIOPIC, // 1E7ED..1E7EE
8543 UNKNOWN, // 1E7EF
8544 ETHIOPIC, // 1E7F0..1E7FE
8545 UNKNOWN, // 1E7FF
8546 MENDE_KIKAKUI, // 1E800..1E8C4
8547 UNKNOWN, // 1E8C5..1E8C6
8548 MENDE_KIKAKUI, // 1E8C7..1E8D6
8549 UNKNOWN, // 1E8D7..1E8FF
8550 ADLAM, // 1E900..1E94B
8551 UNKNOWN, // 1E94C..1E94F
8552 ADLAM, // 1E950..1E959
8553 UNKNOWN, // 1E95A..1E95D
8554 ADLAM, // 1E95E..1E95F
8555 UNKNOWN, // 1E960..1EC70
8556 COMMON, // 1EC71..1ECB4
8557 UNKNOWN, // 1ECB5..1ED00
8558 COMMON, // 1ED01..1ED3D
8559 UNKNOWN, // 1ED3E..1EDFF
8560 ARABIC, // 1EE00..1EE03
8561 UNKNOWN, // 1EE04
8562 ARABIC, // 1EE05..1EE1F
8563 UNKNOWN, // 1EE20
8564 ARABIC, // 1EE21..1EE22
8565 UNKNOWN, // 1EE23
8566 ARABIC, // 1EE24
8567 UNKNOWN, // 1EE25..1EE26
8568 ARABIC, // 1EE27
8569 UNKNOWN, // 1EE28
8570 ARABIC, // 1EE29..1EE32
8571 UNKNOWN, // 1EE33
8572 ARABIC, // 1EE34..1EE37
8573 UNKNOWN, // 1EE38
8574 ARABIC, // 1EE39
8575 UNKNOWN, // 1EE3A
8576 ARABIC, // 1EE3B
8577 UNKNOWN, // 1EE3C..1EE41
8578 ARABIC, // 1EE42
8579 UNKNOWN, // 1EE43..1EE46
8580 ARABIC, // 1EE47
8581 UNKNOWN, // 1EE48
8582 ARABIC, // 1EE49
8583 UNKNOWN, // 1EE4A
8584 ARABIC, // 1EE4B
8585 UNKNOWN, // 1EE4C
8586 ARABIC, // 1EE4D..1EE4F
8587 UNKNOWN, // 1EE50
8588 ARABIC, // 1EE51..1EE52
8589 UNKNOWN, // 1EE53
8590 ARABIC, // 1EE54
8591 UNKNOWN, // 1EE55..1EE56
8592 ARABIC, // 1EE57
8593 UNKNOWN, // 1EE58
8594 ARABIC, // 1EE59
8595 UNKNOWN, // 1EE5A
8596 ARABIC, // 1EE5B
8597 UNKNOWN, // 1EE5C
8598 ARABIC, // 1EE5D
8599 UNKNOWN, // 1EE5E
8600 ARABIC, // 1EE5F
8601 UNKNOWN, // 1EE60
8602 ARABIC, // 1EE61..1EE62
8603 UNKNOWN, // 1EE63
8604 ARABIC, // 1EE64
8605 UNKNOWN, // 1EE65..1EE66
8606 ARABIC, // 1EE67..1EE6A
8607 UNKNOWN, // 1EE6B
8608 ARABIC, // 1EE6C..1EE72
8609 UNKNOWN, // 1EE73
8610 ARABIC, // 1EE74..1EE77
8611 UNKNOWN, // 1EE78
8612 ARABIC, // 1EE79..1EE7C
8613 UNKNOWN, // 1EE7D
8614 ARABIC, // 1EE7E
8615 UNKNOWN, // 1EE7F
8616 ARABIC, // 1EE80..1EE89
8617 UNKNOWN, // 1EE8A
8618 ARABIC, // 1EE8B..1EE9B
8619 UNKNOWN, // 1EE9C..1EEA0
8620 ARABIC, // 1EEA1..1EEA3
8621 UNKNOWN, // 1EEA4
8622 ARABIC, // 1EEA5..1EEA9
8623 UNKNOWN, // 1EEAA
8624 ARABIC, // 1EEAB..1EEBB
8625 UNKNOWN, // 1EEBC..1EEEF
8626 ARABIC, // 1EEF0..1EEF1
8627 UNKNOWN, // 1EEF2..1EFFF
8628 COMMON, // 1F000..1F02B
8629 UNKNOWN, // 1F02C..1F02F
8630 COMMON, // 1F030..1F093
8631 UNKNOWN, // 1F094..1F09F
8632 COMMON, // 1F0A0..1F0AE
8633 UNKNOWN, // 1F0AF..1F0B0
8634 COMMON, // 1F0B1..1F0BF
8635 UNKNOWN, // 1F0C0
8636 COMMON, // 1F0C1..1F0CF
8637 UNKNOWN, // 1F0D0
8638 COMMON, // 1F0D1..1F0F5
8639 UNKNOWN, // 1F0F6..1F0FF
8640 COMMON, // 1F100..1F1AD
8641 UNKNOWN, // 1F1AE..1F1E5
8642 COMMON, // 1F1E6..1F1FF
8643 HIRAGANA, // 1F200
8644 COMMON, // 1F201..1F202
8645 UNKNOWN, // 1F203..1F20F
8646 COMMON, // 1F210..1F23B
8647 UNKNOWN, // 1F23C..1F23F
8648 COMMON, // 1F240..1F248
8649 UNKNOWN, // 1F249..1F24F
8650 COMMON, // 1F250..1F251
8651 UNKNOWN, // 1F252..1F25F
8652 COMMON, // 1F260..1F265
8653 UNKNOWN, // 1F266..1F2FF
8654 COMMON, // 1F300..1F6D7
8655 UNKNOWN, // 1F6D8..1F6DB
8656 COMMON, // 1F6DC..1F6EC
8657 UNKNOWN, // 1F6ED..1F6EF
8658 COMMON, // 1F6F0..1F6FC
8659 UNKNOWN, // 1F6FD..1F6FF
8660 COMMON, // 1F700..1F776
8661 UNKNOWN, // 1F777..1F77A
8662 COMMON, // 1F77B..1F7D9
8663 UNKNOWN, // 1F7DA..1F7DF
8664 COMMON, // 1F7E0..1F7EB
8665 UNKNOWN, // 1F7EC..1F7EF
8666 COMMON, // 1F7F0
8667 UNKNOWN, // 1F7F1..1F7FF
8668 COMMON, // 1F800..1F80B
8669 UNKNOWN, // 1F80C..1F80F
8670 COMMON, // 1F810..1F847
8671 UNKNOWN, // 1F848..1F84F
8672 COMMON, // 1F850..1F859
8673 UNKNOWN, // 1F85A..1F85F
8674 COMMON, // 1F860..1F887
8675 UNKNOWN, // 1F888..1F88F
8676 COMMON, // 1F890..1F8AD
8677 UNKNOWN, // 1F8AE..1F8AF
8678 COMMON, // 1F8B0..1F8B1
8679 UNKNOWN, // 1F8B2..1F8FF
8680 COMMON, // 1F900..1FA53
8681 UNKNOWN, // 1FA54..1FA5F
8682 COMMON, // 1FA60..1FA6D
8683 UNKNOWN, // 1FA6E..1FA6F
8684 COMMON, // 1FA70..1FA7C
8685 UNKNOWN, // 1FA7D..1FA7F
8686 COMMON, // 1FA80..1FA88
8687 UNKNOWN, // 1FA89..1FA8F
8688 COMMON, // 1FA90..1FABD
8689 UNKNOWN, // 1FABE
8690 COMMON, // 1FABF..1FAC5
8691 UNKNOWN, // 1FAC6..1FACD
8692 COMMON, // 1FACE..1FADB
8693 UNKNOWN, // 1FADC..1FADF
8694 COMMON, // 1FAE0..1FAE8
8695 UNKNOWN, // 1FAE9..1FAEF
8696 COMMON, // 1FAF0..1FAF8
8697 UNKNOWN, // 1FAF9..1FAFF
8698 COMMON, // 1FB00..1FB92
8699 UNKNOWN, // 1FB93
8700 COMMON, // 1FB94..1FBCA
8701 UNKNOWN, // 1FBCB..1FBEF
8702 COMMON, // 1FBF0..1FBF9
8703 UNKNOWN, // 1FBFA..1FFFF
8704 HAN, // 20000..2A6DF
8705 UNKNOWN, // 2A6E0..2A6FF
8706 HAN, // 2A700..2B739
8707 UNKNOWN, // 2B73A..2B73F
8708 HAN, // 2B740..2B81D
8709 UNKNOWN, // 2B81E..2B81F
8710 HAN, // 2B820..2CEA1
8711 UNKNOWN, // 2CEA2..2CEAF
8712 HAN, // 2CEB0..2EBE0
8713 UNKNOWN, // 2EBE1..2EBEF
8714 HAN, // 2EBF0..2EE5D
8715 UNKNOWN, // 2EE5E..2F7FF
8716 HAN, // 2F800..2FA1D
8717 UNKNOWN, // 2FA1E..2FFFF
8718 HAN, // 30000..3134A
8719 UNKNOWN, // 3134B..3134F
8720 HAN, // 31350..323AF
8721 UNKNOWN, // 323B0..E0000
8722 COMMON, // E0001
8723 UNKNOWN, // E0002..E001F
8724 COMMON, // E0020..E007F
8725 UNKNOWN, // E0080..E00FF
8726 INHERITED, // E0100..E01EF
8727 UNKNOWN, // E01F0..10FFFF
8728 };
8729
8730 private static final HashMap<String, Character.UnicodeScript> aliases;
8731 static {
8732 aliases = HashMap.newHashMap(UNKNOWN.ordinal() + 1);
8733 aliases.put("ADLM", ADLAM);
8734 aliases.put("AGHB", CAUCASIAN_ALBANIAN);
8735 aliases.put("AHOM", AHOM);
8736 aliases.put("ARAB", ARABIC);
8737 aliases.put("ARMI", IMPERIAL_ARAMAIC);
8738 aliases.put("ARMN", ARMENIAN);
8739 aliases.put("AVST", AVESTAN);
8740 aliases.put("BALI", BALINESE);
8741 aliases.put("BAMU", BAMUM);
8742 aliases.put("BASS", BASSA_VAH);
8743 aliases.put("BATK", BATAK);
8744 aliases.put("BENG", BENGALI);
8745 aliases.put("BHKS", BHAIKSUKI);
8746 aliases.put("BOPO", BOPOMOFO);
8747 aliases.put("BRAH", BRAHMI);
8748 aliases.put("BRAI", BRAILLE);
8749 aliases.put("BUGI", BUGINESE);
8750 aliases.put("BUHD", BUHID);
8751 aliases.put("CAKM", CHAKMA);
8752 aliases.put("CANS", CANADIAN_ABORIGINAL);
8753 aliases.put("CARI", CARIAN);
8754 aliases.put("CHAM", CHAM);
8755 aliases.put("CHER", CHEROKEE);
8756 aliases.put("CHRS", CHORASMIAN);
8757 aliases.put("COPT", COPTIC);
8758 aliases.put("CPMN", CYPRO_MINOAN);
8759 aliases.put("CPRT", CYPRIOT);
8760 aliases.put("CYRL", CYRILLIC);
8761 aliases.put("DEVA", DEVANAGARI);
8762 aliases.put("DIAK", DIVES_AKURU);
8763 aliases.put("DOGR", DOGRA);
8764 aliases.put("DSRT", DESERET);
8765 aliases.put("DUPL", DUPLOYAN);
8766 aliases.put("EGYP", EGYPTIAN_HIEROGLYPHS);
8767 aliases.put("ELBA", ELBASAN);
8768 aliases.put("ELYM", ELYMAIC);
8769 aliases.put("ETHI", ETHIOPIC);
8770 aliases.put("GEOR", GEORGIAN);
8771 aliases.put("GLAG", GLAGOLITIC);
8772 aliases.put("GONG", GUNJALA_GONDI);
8773 aliases.put("GONM", MASARAM_GONDI);
8774 aliases.put("GOTH", GOTHIC);
8775 aliases.put("GRAN", GRANTHA);
8776 aliases.put("GREK", GREEK);
8777 aliases.put("GUJR", GUJARATI);
8778 aliases.put("GURU", GURMUKHI);
8779 aliases.put("HANG", HANGUL);
8780 aliases.put("HANI", HAN);
8781 aliases.put("HANO", HANUNOO);
8782 aliases.put("HATR", HATRAN);
8783 aliases.put("HEBR", HEBREW);
8784 aliases.put("HIRA", HIRAGANA);
8785 aliases.put("HLUW", ANATOLIAN_HIEROGLYPHS);
8786 aliases.put("HMNG", PAHAWH_HMONG);
8787 aliases.put("HMNP", NYIAKENG_PUACHUE_HMONG);
8788 aliases.put("HUNG", OLD_HUNGARIAN);
8789 aliases.put("ITAL", OLD_ITALIC);
8790 aliases.put("JAVA", JAVANESE);
8791 aliases.put("KALI", KAYAH_LI);
8792 aliases.put("KANA", KATAKANA);
8793 aliases.put("KAWI", KAWI);
8794 aliases.put("KHAR", KHAROSHTHI);
8795 aliases.put("KHMR", KHMER);
8796 aliases.put("KHOJ", KHOJKI);
8797 aliases.put("KITS", KHITAN_SMALL_SCRIPT);
8798 aliases.put("KNDA", KANNADA);
8799 aliases.put("KTHI", KAITHI);
8800 aliases.put("LANA", TAI_THAM);
8801 aliases.put("LAOO", LAO);
8802 aliases.put("LATN", LATIN);
8803 aliases.put("LEPC", LEPCHA);
8804 aliases.put("LIMB", LIMBU);
8805 aliases.put("LINA", LINEAR_A);
8806 aliases.put("LINB", LINEAR_B);
8807 aliases.put("LISU", LISU);
8808 aliases.put("LYCI", LYCIAN);
8809 aliases.put("LYDI", LYDIAN);
8810 aliases.put("MAHJ", MAHAJANI);
8811 aliases.put("MAKA", MAKASAR);
8812 aliases.put("MAND", MANDAIC);
8813 aliases.put("MANI", MANICHAEAN);
8814 aliases.put("MARC", MARCHEN);
8815 aliases.put("MEDF", MEDEFAIDRIN);
8816 aliases.put("MEND", MENDE_KIKAKUI);
8817 aliases.put("MERC", MEROITIC_CURSIVE);
8818 aliases.put("MERO", MEROITIC_HIEROGLYPHS);
8819 aliases.put("MLYM", MALAYALAM);
8820 aliases.put("MODI", MODI);
8821 aliases.put("MONG", MONGOLIAN);
8822 aliases.put("MROO", MRO);
8823 aliases.put("MTEI", MEETEI_MAYEK);
8824 aliases.put("MULT", MULTANI);
8825 aliases.put("MYMR", MYANMAR);
8826 aliases.put("NAGM", NAG_MUNDARI);
8827 aliases.put("NAND", NANDINAGARI);
8828 aliases.put("NARB", OLD_NORTH_ARABIAN);
8829 aliases.put("NBAT", NABATAEAN);
8830 aliases.put("NEWA", NEWA);
8831 aliases.put("NKOO", NKO);
8832 aliases.put("NSHU", NUSHU);
8833 aliases.put("OGAM", OGHAM);
8834 aliases.put("OLCK", OL_CHIKI);
8835 aliases.put("ORKH", OLD_TURKIC);
8836 aliases.put("ORYA", ORIYA);
8837 aliases.put("OSGE", OSAGE);
8838 aliases.put("OSMA", OSMANYA);
8839 aliases.put("OUGR", OLD_UYGHUR);
8840 aliases.put("PALM", PALMYRENE);
8841 aliases.put("PAUC", PAU_CIN_HAU);
8842 aliases.put("PERM", OLD_PERMIC);
8843 aliases.put("PHAG", PHAGS_PA);
8844 aliases.put("PHLI", INSCRIPTIONAL_PAHLAVI);
8845 aliases.put("PHLP", PSALTER_PAHLAVI);
8846 aliases.put("PHNX", PHOENICIAN);
8847 aliases.put("PLRD", MIAO);
8848 aliases.put("PRTI", INSCRIPTIONAL_PARTHIAN);
8849 aliases.put("RJNG", REJANG);
8850 aliases.put("ROHG", HANIFI_ROHINGYA);
8851 aliases.put("RUNR", RUNIC);
8852 aliases.put("SAMR", SAMARITAN);
8853 aliases.put("SARB", OLD_SOUTH_ARABIAN);
8854 aliases.put("SAUR", SAURASHTRA);
8855 aliases.put("SGNW", SIGNWRITING);
8856 aliases.put("SHAW", SHAVIAN);
8857 aliases.put("SHRD", SHARADA);
8858 aliases.put("SIDD", SIDDHAM);
8859 aliases.put("SIND", KHUDAWADI);
8860 aliases.put("SINH", SINHALA);
8861 aliases.put("SOGD", SOGDIAN);
8862 aliases.put("SOGO", OLD_SOGDIAN);
8863 aliases.put("SORA", SORA_SOMPENG);
8864 aliases.put("SOYO", SOYOMBO);
8865 aliases.put("SUND", SUNDANESE);
8866 aliases.put("SYLO", SYLOTI_NAGRI);
8867 aliases.put("SYRC", SYRIAC);
8868 aliases.put("TAGB", TAGBANWA);
8869 aliases.put("TAKR", TAKRI);
8870 aliases.put("TALE", TAI_LE);
8871 aliases.put("TALU", NEW_TAI_LUE);
8872 aliases.put("TAML", TAMIL);
8873 aliases.put("TANG", TANGUT);
8874 aliases.put("TAVT", TAI_VIET);
8875 aliases.put("TELU", TELUGU);
8876 aliases.put("TFNG", TIFINAGH);
8877 aliases.put("TGLG", TAGALOG);
8878 aliases.put("THAA", THAANA);
8879 aliases.put("THAI", THAI);
8880 aliases.put("TIBT", TIBETAN);
8881 aliases.put("TIRH", TIRHUTA);
8882 aliases.put("TNSA", TANGSA);
8883 aliases.put("TOTO", TOTO);
8884 aliases.put("UGAR", UGARITIC);
8885 aliases.put("VAII", VAI);
8886 aliases.put("VITH", VITHKUQI);
8887 aliases.put("WARA", WARANG_CITI);
8888 aliases.put("WCHO", WANCHO);
8889 aliases.put("XPEO", OLD_PERSIAN);
8890 aliases.put("XSUX", CUNEIFORM);
8891 aliases.put("YEZI", YEZIDI);
8892 aliases.put("YIII", YI);
8893 aliases.put("ZANB", ZANABAZAR_SQUARE);
8894 aliases.put("ZINH", INHERITED);
8895 aliases.put("ZYYY", COMMON);
8896 aliases.put("ZZZZ", UNKNOWN);
8897 }
8898
8899 /**
8900 * Returns the enum constant representing the Unicode script of which
8901 * the given character (Unicode code point) is assigned to.
8902 *
8903 * @param codePoint the character (Unicode code point) in question.
8904 * @return The {@code UnicodeScript} constant representing the
8905 * Unicode script of which this character is assigned to.
8906 *
8907 * @throws IllegalArgumentException if the specified
8908 * {@code codePoint} is an invalid Unicode code point.
8909 * @see Character#isValidCodePoint(int)
8910 *
8911 */
8912 public static UnicodeScript of(int codePoint) {
8913 if (!isValidCodePoint(codePoint))
8914 throw new IllegalArgumentException(
8915 String.format("Not a valid Unicode code point: 0x%X", codePoint));
8916 int type = getType(codePoint);
8917 // leave SURROGATE and PRIVATE_USE for table lookup
8918 if (type == UNASSIGNED)
8919 return UNKNOWN;
8920 int index = Arrays.binarySearch(scriptStarts, codePoint);
8921 if (index < 0)
8922 index = -index - 2;
8923 return scripts[index];
8924 }
8925
8926 /**
8927 * Returns the UnicodeScript constant with the given Unicode script
8928 * name or the script name alias. Script names and their aliases are
8929 * determined by The Unicode Standard. The files {@code Scripts.txt}
8930 * and {@code PropertyValueAliases.txt} define script names
8931 * and the script name aliases for a particular version of the
8932 * standard. The {@link Character} class specifies the version of
8933 * the standard that it supports.
8934 * <p>
8935 * Character case is ignored for all of the valid script names.
8936 * The en_US locale's case mapping rules are used to provide
8937 * case-insensitive string comparisons for script name validation.
8938 *
8939 * @param scriptName A {@code UnicodeScript} name.
8940 * @return The {@code UnicodeScript} constant identified
8941 * by {@code scriptName}
8942 * @throws IllegalArgumentException if {@code scriptName} is an
8943 * invalid name
8944 * @throws NullPointerException if {@code scriptName} is null
8945 */
8946 public static final UnicodeScript forName(String scriptName) {
8947 scriptName = scriptName.toUpperCase(Locale.ENGLISH);
8948 //.replace(' ', '_'));
8949 UnicodeScript sc = aliases.get(scriptName);
8950 if (sc != null)
8951 return sc;
8952 return valueOf(scriptName);
8953 }
8954 }
8955
8956 /**
8957 * The value of the {@code Character}.
8958 *
8959 * @serial
8960 */
8961 private final char value;
8962
8963 /** use serialVersionUID from JDK 1.0.2 for interoperability */
8964 @java.io.Serial
8965 private static final long serialVersionUID = 3786198910865385080L;
8966
8967 /**
8968 * Constructs a newly allocated {@code Character} object that
8969 * represents the specified {@code char} value.
8970 *
8971 * @param value the value to be represented by the
8972 * {@code Character} object.
8973 *
8974 * @deprecated
8975 * It is rarely appropriate to use this constructor. The static factory
8976 * {@link #valueOf(char)} is generally a better choice, as it is
8977 * likely to yield significantly better space and time performance.
8978 */
8979 @Deprecated(since="9", forRemoval = true)
8980 public Character(char value) {
8981 this.value = value;
8982 }
8983
8984 private static final class CharacterCache {
8985 private CharacterCache(){}
8986
8987 @Stable
8988 static final Character[] cache;
8989 static Character[] archivedCache;
8990
8991 static {
8992 int size = 127 + 1;
8993
8994 // Load and use the archived cache if it exists
8995 CDS.initializeFromArchive(CharacterCache.class);
8996 if (archivedCache == null) {
8997 Character[] c = new Character[size];
8998 for (int i = 0; i < size; i++) {
8999 c[i] = new Character((char) i);
9000 }
9001 archivedCache = c;
9002 }
9003 cache = archivedCache;
9004 assert cache.length == size;
9005 }
9006 }
9007
9008 /**
9009 * Returns a {@code Character} instance representing the specified
9010 * {@code char} value.
9011 * If a new {@code Character} instance is not required, this method
9012 * should generally be used in preference to the constructor
9013 * {@link #Character(char)}, as this method is likely to yield
9014 * significantly better space and time performance by caching
9015 * frequently requested values.
9016 *
9017 * This method will always cache values in the range {@code
9018 * '\u005Cu0000'} to {@code '\u005Cu007F'}, inclusive, and may
9019 * cache other values outside of this range.
9020 *
9021 * @param c a char value.
9022 * @return a {@code Character} instance representing {@code c}.
9023 * @since 1.5
9024 */
9025 @IntrinsicCandidate
9026 @DeserializeConstructor
9027 public static Character valueOf(char c) {
9028 if (c <= 127) { // must cache
9029 return CharacterCache.cache[(int)c];
9030 }
9031 return new Character(c);
9032 }
9033
9034 /**
9035 * Returns the value of this {@code Character} object.
9036 * @return the primitive {@code char} value represented by
9037 * this object.
9038 */
9039 @IntrinsicCandidate
9040 public char charValue() {
9041 return value;
9042 }
9043
9044 /**
9045 * Returns a hash code for this {@code Character}; equal to the result
9046 * of invoking {@code charValue()}.
9047 *
9048 * @return a hash code value for this {@code Character}
9049 */
9050 @Override
9051 public int hashCode() {
9052 return Character.hashCode(value);
9053 }
9054
9055 /**
9056 * Returns a hash code for a {@code char} value; compatible with
9057 * {@code Character.hashCode()}.
9058 *
9059 * @since 1.8
9060 *
9061 * @param value The {@code char} for which to return a hash code.
9062 * @return a hash code value for a {@code char} value.
9063 */
9064 public static int hashCode(char value) {
9065 return (int)value;
9066 }
9067
9068 /**
9069 * Compares this object against the specified object.
9070 * The result is {@code true} if and only if the argument is not
9071 * {@code null} and is a {@code Character} object that
9072 * represents the same {@code char} value as this object.
9073 *
9074 * @param obj the object to compare with.
9075 * @return {@code true} if the objects are the same;
9076 * {@code false} otherwise.
9077 */
9078 public boolean equals(Object obj) {
9079 if (obj instanceof Character c) {
9080 return value == c.charValue();
9081 }
9082 return false;
9083 }
9084
9085 /**
9086 * Returns a {@code String} object representing this
9087 * {@code Character}'s value. The result is a string of
9088 * length 1 whose sole component is the primitive
9089 * {@code char} value represented by this
9090 * {@code Character} object.
9091 *
9092 * @return a string representation of this object.
9093 */
9094 @Override
9095 public String toString() {
9096 return String.valueOf(value);
9097 }
9098
9099 /**
9100 * Returns a {@code String} object representing the
9101 * specified {@code char}. The result is a string of length
9102 * 1 consisting solely of the specified {@code char}.
9103 *
9104 * @apiNote This method cannot handle <a
9105 * href="#supplementary"> supplementary characters</a>. To support
9106 * all Unicode characters, including supplementary characters, use
9107 * the {@link #toString(int)} method.
9108 *
9109 * @param c the {@code char} to be converted
9110 * @return the string representation of the specified {@code char}
9111 * @since 1.4
9112 */
9113 public static String toString(char c) {
9114 return String.valueOf(c);
9115 }
9116
9117 /**
9118 * Returns a {@code String} object representing the
9119 * specified character (Unicode code point). The result is a string of
9120 * length 1 or 2, consisting solely of the specified {@code codePoint}.
9121 *
9122 * @param codePoint the {@code codePoint} to be converted
9123 * @return the string representation of the specified {@code codePoint}
9124 * @throws IllegalArgumentException if the specified
9125 * {@code codePoint} is not a {@linkplain #isValidCodePoint
9126 * valid Unicode code point}.
9127 * @since 11
9128 */
9129 public static String toString(int codePoint) {
9130 return String.valueOfCodePoint(codePoint);
9131 }
9132
9133 /**
9134 * Determines whether the specified code point is a valid
9135 * <a href="http://www.unicode.org/glossary/#code_point">
9136 * Unicode code point value</a>.
9137 *
9138 * @param codePoint the Unicode code point to be tested
9139 * @return {@code true} if the specified code point value is between
9140 * {@link #MIN_CODE_POINT} and
9141 * {@link #MAX_CODE_POINT} inclusive;
9142 * {@code false} otherwise.
9143 * @since 1.5
9144 */
9145 public static boolean isValidCodePoint(int codePoint) {
9146 // Optimized form of:
9147 // codePoint >= MIN_CODE_POINT && codePoint <= MAX_CODE_POINT
9148 int plane = codePoint >>> 16;
9149 return plane < ((MAX_CODE_POINT + 1) >>> 16);
9150 }
9151
9152 /**
9153 * Determines whether the specified character (Unicode code point)
9154 * is in the <a href="#BMP">Basic Multilingual Plane (BMP)</a>.
9155 * Such code points can be represented using a single {@code char}.
9156 *
9157 * @param codePoint the character (Unicode code point) to be tested
9158 * @return {@code true} if the specified code point is between
9159 * {@link #MIN_VALUE} and {@link #MAX_VALUE} inclusive;
9160 * {@code false} otherwise.
9161 * @since 1.7
9162 */
9163 public static boolean isBmpCodePoint(int codePoint) {
9164 return codePoint >>> 16 == 0;
9165 // Optimized form of:
9166 // codePoint >= MIN_VALUE && codePoint <= MAX_VALUE
9167 // We consistently use logical shift (>>>) to facilitate
9168 // additional runtime optimizations.
9169 }
9170
9171 /**
9172 * Determines whether the specified character (Unicode code point)
9173 * is in the <a href="#supplementary">supplementary character</a> range.
9174 *
9175 * @param codePoint the character (Unicode code point) to be tested
9176 * @return {@code true} if the specified code point is between
9177 * {@link #MIN_SUPPLEMENTARY_CODE_POINT} and
9178 * {@link #MAX_CODE_POINT} inclusive;
9179 * {@code false} otherwise.
9180 * @since 1.5
9181 */
9182 public static boolean isSupplementaryCodePoint(int codePoint) {
9183 return codePoint >= MIN_SUPPLEMENTARY_CODE_POINT
9184 && codePoint < MAX_CODE_POINT + 1;
9185 }
9186
9187 /**
9188 * Determines if the given {@code char} value is a
9189 * <a href="http://www.unicode.org/glossary/#high_surrogate_code_unit">
9190 * Unicode high-surrogate code unit</a>
9191 * (also known as <i>leading-surrogate code unit</i>).
9192 *
9193 * <p>Such values do not represent characters by themselves,
9194 * but are used in the representation of
9195 * <a href="#supplementary">supplementary characters</a>
9196 * in the UTF-16 encoding.
9197 *
9198 * @param ch the {@code char} value to be tested.
9199 * @return {@code true} if the {@code char} value is between
9200 * {@link #MIN_HIGH_SURROGATE} and
9201 * {@link #MAX_HIGH_SURROGATE} inclusive;
9202 * {@code false} otherwise.
9203 * @see Character#isLowSurrogate(char)
9204 * @see Character.UnicodeBlock#of(int)
9205 * @since 1.5
9206 */
9207 public static boolean isHighSurrogate(char ch) {
9208 // Help VM constant-fold; MAX_HIGH_SURROGATE + 1 == MIN_LOW_SURROGATE
9209 return ch >= MIN_HIGH_SURROGATE && ch < (MAX_HIGH_SURROGATE + 1);
9210 }
9211
9212 /**
9213 * Determines if the given {@code char} value is a
9214 * <a href="http://www.unicode.org/glossary/#low_surrogate_code_unit">
9215 * Unicode low-surrogate code unit</a>
9216 * (also known as <i>trailing-surrogate code unit</i>).
9217 *
9218 * <p>Such values do not represent characters by themselves,
9219 * but are used in the representation of
9220 * <a href="#supplementary">supplementary characters</a>
9221 * in the UTF-16 encoding.
9222 *
9223 * @param ch the {@code char} value to be tested.
9224 * @return {@code true} if the {@code char} value is between
9225 * {@link #MIN_LOW_SURROGATE} and
9226 * {@link #MAX_LOW_SURROGATE} inclusive;
9227 * {@code false} otherwise.
9228 * @see Character#isHighSurrogate(char)
9229 * @since 1.5
9230 */
9231 public static boolean isLowSurrogate(char ch) {
9232 return ch >= MIN_LOW_SURROGATE && ch < (MAX_LOW_SURROGATE + 1);
9233 }
9234
9235 /**
9236 * Determines if the given {@code char} value is a Unicode
9237 * <i>surrogate code unit</i>.
9238 *
9239 * <p>Such values do not represent characters by themselves,
9240 * but are used in the representation of
9241 * <a href="#supplementary">supplementary characters</a>
9242 * in the UTF-16 encoding.
9243 *
9244 * <p>A char value is a surrogate code unit if and only if it is either
9245 * a {@linkplain #isLowSurrogate(char) low-surrogate code unit} or
9246 * a {@linkplain #isHighSurrogate(char) high-surrogate code unit}.
9247 *
9248 * @param ch the {@code char} value to be tested.
9249 * @return {@code true} if the {@code char} value is between
9250 * {@link #MIN_SURROGATE} and
9251 * {@link #MAX_SURROGATE} inclusive;
9252 * {@code false} otherwise.
9253 * @since 1.7
9254 */
9255 public static boolean isSurrogate(char ch) {
9256 return ch >= MIN_SURROGATE && ch < (MAX_SURROGATE + 1);
9257 }
9258
9259 /**
9260 * Determines whether the specified pair of {@code char}
9261 * values is a valid
9262 * <a href="http://www.unicode.org/glossary/#surrogate_pair">
9263 * Unicode surrogate pair</a>.
9264 *
9265 * <p>This method is equivalent to the expression:
9266 * <blockquote><pre>{@code
9267 * isHighSurrogate(high) && isLowSurrogate(low)
9268 * }</pre></blockquote>
9269 *
9270 * @param high the high-surrogate code value to be tested
9271 * @param low the low-surrogate code value to be tested
9272 * @return {@code true} if the specified high and
9273 * low-surrogate code values represent a valid surrogate pair;
9274 * {@code false} otherwise.
9275 * @since 1.5
9276 */
9277 public static boolean isSurrogatePair(char high, char low) {
9278 return isHighSurrogate(high) && isLowSurrogate(low);
9279 }
9280
9281 /**
9282 * Determines the number of {@code char} values needed to
9283 * represent the specified character (Unicode code point). If the
9284 * specified character is equal to or greater than 0x10000, then
9285 * the method returns 2. Otherwise, the method returns 1.
9286 *
9287 * <p>This method doesn't validate the specified character to be a
9288 * valid Unicode code point. The caller must validate the
9289 * character value using {@link #isValidCodePoint(int) isValidCodePoint}
9290 * if necessary.
9291 *
9292 * @param codePoint the character (Unicode code point) to be tested.
9293 * @return 2 if the character is a valid supplementary character; 1 otherwise.
9294 * @see Character#isSupplementaryCodePoint(int)
9295 * @since 1.5
9296 */
9297 public static int charCount(int codePoint) {
9298 return codePoint >= MIN_SUPPLEMENTARY_CODE_POINT ? 2 : 1;
9299 }
9300
9301 /**
9302 * Converts the specified surrogate pair to its supplementary code
9303 * point value. This method does not validate the specified
9304 * surrogate pair. The caller must validate it using {@link
9305 * #isSurrogatePair(char, char) isSurrogatePair} if necessary.
9306 *
9307 * @param high the high-surrogate code unit
9308 * @param low the low-surrogate code unit
9309 * @return the supplementary code point composed from the
9310 * specified surrogate pair.
9311 * @since 1.5
9312 */
9313 public static int toCodePoint(char high, char low) {
9314 // Optimized form of:
9315 // return ((high - MIN_HIGH_SURROGATE) << 10)
9316 // + (low - MIN_LOW_SURROGATE)
9317 // + MIN_SUPPLEMENTARY_CODE_POINT;
9318 return ((high << 10) + low) + (MIN_SUPPLEMENTARY_CODE_POINT
9319 - (MIN_HIGH_SURROGATE << 10)
9320 - MIN_LOW_SURROGATE);
9321 }
9322
9323 /**
9324 * Returns the code point at the given index of the
9325 * {@code CharSequence}. If the {@code char} value at
9326 * the given index in the {@code CharSequence} is in the
9327 * high-surrogate range, the following index is less than the
9328 * length of the {@code CharSequence}, and the
9329 * {@code char} value at the following index is in the
9330 * low-surrogate range, then the supplementary code point
9331 * corresponding to this surrogate pair is returned. Otherwise,
9332 * the {@code char} value at the given index is returned.
9333 *
9334 * @param seq a sequence of {@code char} values (Unicode code
9335 * units)
9336 * @param index the index to the {@code char} values (Unicode
9337 * code units) in {@code seq} to be converted
9338 * @return the Unicode code point at the given index
9339 * @throws NullPointerException if {@code seq} is null.
9340 * @throws IndexOutOfBoundsException if the value
9341 * {@code index} is negative or not less than
9342 * {@link CharSequence#length() seq.length()}.
9343 * @since 1.5
9344 */
9345 public static int codePointAt(CharSequence seq, int index) {
9346 char c1 = seq.charAt(index);
9347 if (isHighSurrogate(c1) && ++index < seq.length()) {
9348 char c2 = seq.charAt(index);
9349 if (isLowSurrogate(c2)) {
9350 return toCodePoint(c1, c2);
9351 }
9352 }
9353 return c1;
9354 }
9355
9356 /**
9357 * Returns the code point at the given index of the
9358 * {@code char} array. If the {@code char} value at
9359 * the given index in the {@code char} array is in the
9360 * high-surrogate range, the following index is less than the
9361 * length of the {@code char} array, and the
9362 * {@code char} value at the following index is in the
9363 * low-surrogate range, then the supplementary code point
9364 * corresponding to this surrogate pair is returned. Otherwise,
9365 * the {@code char} value at the given index is returned.
9366 *
9367 * @param a the {@code char} array
9368 * @param index the index to the {@code char} values (Unicode
9369 * code units) in the {@code char} array to be converted
9370 * @return the Unicode code point at the given index
9371 * @throws NullPointerException if {@code a} is null.
9372 * @throws IndexOutOfBoundsException if the value
9373 * {@code index} is negative or not less than
9374 * the length of the {@code char} array.
9375 * @since 1.5
9376 */
9377 public static int codePointAt(char[] a, int index) {
9378 return codePointAtImpl(a, index, a.length);
9379 }
9380
9381 /**
9382 * Returns the code point at the given index of the
9383 * {@code char} array, where only array elements with
9384 * {@code index} less than {@code limit} can be used. If
9385 * the {@code char} value at the given index in the
9386 * {@code char} array is in the high-surrogate range, the
9387 * following index is less than the {@code limit}, and the
9388 * {@code char} value at the following index is in the
9389 * low-surrogate range, then the supplementary code point
9390 * corresponding to this surrogate pair is returned. Otherwise,
9391 * the {@code char} value at the given index is returned.
9392 *
9393 * @param a the {@code char} array
9394 * @param index the index to the {@code char} values (Unicode
9395 * code units) in the {@code char} array to be converted
9396 * @param limit the index after the last array element that
9397 * can be used in the {@code char} array
9398 * @return the Unicode code point at the given index
9399 * @throws NullPointerException if {@code a} is null.
9400 * @throws IndexOutOfBoundsException if the {@code index}
9401 * argument is negative or not less than the {@code limit}
9402 * argument, or if the {@code limit} argument is negative or
9403 * greater than the length of the {@code char} array.
9404 * @since 1.5
9405 */
9406 public static int codePointAt(char[] a, int index, int limit) {
9407 if (index >= limit || index < 0 || limit > a.length) {
9408 throw new IndexOutOfBoundsException();
9409 }
9410 return codePointAtImpl(a, index, limit);
9411 }
9412
9413 // throws ArrayIndexOutOfBoundsException if index out of bounds
9414 static int codePointAtImpl(char[] a, int index, int limit) {
9415 char c1 = a[index];
9416 if (isHighSurrogate(c1) && ++index < limit) {
9417 char c2 = a[index];
9418 if (isLowSurrogate(c2)) {
9419 return toCodePoint(c1, c2);
9420 }
9421 }
9422 return c1;
9423 }
9424
9425 /**
9426 * Returns the code point preceding the given index of the
9427 * {@code CharSequence}. If the {@code char} value at
9428 * {@code (index - 1)} in the {@code CharSequence} is in
9429 * the low-surrogate range, {@code (index - 2)} is not
9430 * negative, and the {@code char} value at {@code (index - 2)}
9431 * in the {@code CharSequence} is in the
9432 * high-surrogate range, then the supplementary code point
9433 * corresponding to this surrogate pair is returned. Otherwise,
9434 * the {@code char} value at {@code (index - 1)} is
9435 * returned.
9436 *
9437 * @param seq the {@code CharSequence} instance
9438 * @param index the index following the code point that should be returned
9439 * @return the Unicode code point value before the given index.
9440 * @throws NullPointerException if {@code seq} is null.
9441 * @throws IndexOutOfBoundsException if the {@code index}
9442 * argument is less than 1 or greater than {@link
9443 * CharSequence#length() seq.length()}.
9444 * @since 1.5
9445 */
9446 public static int codePointBefore(CharSequence seq, int index) {
9447 char c2 = seq.charAt(--index);
9448 if (isLowSurrogate(c2) && index > 0) {
9449 char c1 = seq.charAt(--index);
9450 if (isHighSurrogate(c1)) {
9451 return toCodePoint(c1, c2);
9452 }
9453 }
9454 return c2;
9455 }
9456
9457 /**
9458 * Returns the code point preceding the given index of the
9459 * {@code char} array. If the {@code char} value at
9460 * {@code (index - 1)} in the {@code char} array is in
9461 * the low-surrogate range, {@code (index - 2)} is not
9462 * negative, and the {@code char} value at {@code (index - 2)}
9463 * in the {@code char} array is in the
9464 * high-surrogate range, then the supplementary code point
9465 * corresponding to this surrogate pair is returned. Otherwise,
9466 * the {@code char} value at {@code (index - 1)} is
9467 * returned.
9468 *
9469 * @param a the {@code char} array
9470 * @param index the index following the code point that should be returned
9471 * @return the Unicode code point value before the given index.
9472 * @throws NullPointerException if {@code a} is null.
9473 * @throws IndexOutOfBoundsException if the {@code index}
9474 * argument is less than 1 or greater than the length of the
9475 * {@code char} array
9476 * @since 1.5
9477 */
9478 public static int codePointBefore(char[] a, int index) {
9479 return codePointBeforeImpl(a, index, 0);
9480 }
9481
9482 /**
9483 * Returns the code point preceding the given index of the
9484 * {@code char} array, where only array elements with
9485 * {@code index} greater than or equal to {@code start}
9486 * can be used. If the {@code char} value at {@code (index - 1)}
9487 * in the {@code char} array is in the
9488 * low-surrogate range, {@code (index - 2)} is not less than
9489 * {@code start}, and the {@code char} value at
9490 * {@code (index - 2)} in the {@code char} array is in
9491 * the high-surrogate range, then the supplementary code point
9492 * corresponding to this surrogate pair is returned. Otherwise,
9493 * the {@code char} value at {@code (index - 1)} is
9494 * returned.
9495 *
9496 * @param a the {@code char} array
9497 * @param index the index following the code point that should be returned
9498 * @param start the index of the first array element in the
9499 * {@code char} array
9500 * @return the Unicode code point value before the given index.
9501 * @throws NullPointerException if {@code a} is null.
9502 * @throws IndexOutOfBoundsException if the {@code index}
9503 * argument is not greater than the {@code start} argument or
9504 * is greater than the length of the {@code char} array, or
9505 * if the {@code start} argument is negative or not less than
9506 * the length of the {@code char} array.
9507 * @since 1.5
9508 */
9509 public static int codePointBefore(char[] a, int index, int start) {
9510 if (index <= start || start < 0 || index > a.length) {
9511 throw new IndexOutOfBoundsException();
9512 }
9513 return codePointBeforeImpl(a, index, start);
9514 }
9515
9516 // throws ArrayIndexOutOfBoundsException if index-1 out of bounds
9517 static int codePointBeforeImpl(char[] a, int index, int start) {
9518 char c2 = a[--index];
9519 if (isLowSurrogate(c2) && index > start) {
9520 char c1 = a[--index];
9521 if (isHighSurrogate(c1)) {
9522 return toCodePoint(c1, c2);
9523 }
9524 }
9525 return c2;
9526 }
9527
9528 /**
9529 * Returns the leading surrogate (a
9530 * <a href="http://www.unicode.org/glossary/#high_surrogate_code_unit">
9531 * high surrogate code unit</a>) of the
9532 * <a href="http://www.unicode.org/glossary/#surrogate_pair">
9533 * surrogate pair</a>
9534 * representing the specified supplementary character (Unicode
9535 * code point) in the UTF-16 encoding. If the specified character
9536 * is not a
9537 * <a href="Character.html#supplementary">supplementary character</a>,
9538 * an unspecified {@code char} is returned.
9539 *
9540 * <p>If
9541 * {@link #isSupplementaryCodePoint isSupplementaryCodePoint(x)}
9542 * is {@code true}, then
9543 * {@link #isHighSurrogate isHighSurrogate}{@code (highSurrogate(x))} and
9544 * {@link #toCodePoint toCodePoint}{@code (highSurrogate(x), }{@link #lowSurrogate lowSurrogate}{@code (x)) == x}
9545 * are also always {@code true}.
9546 *
9547 * @param codePoint a supplementary character (Unicode code point)
9548 * @return the leading surrogate code unit used to represent the
9549 * character in the UTF-16 encoding
9550 * @since 1.7
9551 */
9552 public static char highSurrogate(int codePoint) {
9553 return (char) ((codePoint >>> 10)
9554 + (MIN_HIGH_SURROGATE - (MIN_SUPPLEMENTARY_CODE_POINT >>> 10)));
9555 }
9556
9557 /**
9558 * Returns the trailing surrogate (a
9559 * <a href="http://www.unicode.org/glossary/#low_surrogate_code_unit">
9560 * low surrogate code unit</a>) of the
9561 * <a href="http://www.unicode.org/glossary/#surrogate_pair">
9562 * surrogate pair</a>
9563 * representing the specified supplementary character (Unicode
9564 * code point) in the UTF-16 encoding. If the specified character
9565 * is not a
9566 * <a href="Character.html#supplementary">supplementary character</a>,
9567 * an unspecified {@code char} is returned.
9568 *
9569 * <p>If
9570 * {@link #isSupplementaryCodePoint isSupplementaryCodePoint(x)}
9571 * is {@code true}, then
9572 * {@link #isLowSurrogate isLowSurrogate}{@code (lowSurrogate(x))} and
9573 * {@link #toCodePoint toCodePoint}{@code (}{@link #highSurrogate highSurrogate}{@code (x), lowSurrogate(x)) == x}
9574 * are also always {@code true}.
9575 *
9576 * @param codePoint a supplementary character (Unicode code point)
9577 * @return the trailing surrogate code unit used to represent the
9578 * character in the UTF-16 encoding
9579 * @since 1.7
9580 */
9581 public static char lowSurrogate(int codePoint) {
9582 return (char) ((codePoint & 0x3ff) + MIN_LOW_SURROGATE);
9583 }
9584
9585 /**
9586 * Converts the specified character (Unicode code point) to its
9587 * UTF-16 representation. If the specified code point is a BMP
9588 * (Basic Multilingual Plane or Plane 0) value, the same value is
9589 * stored in {@code dst[dstIndex]}, and 1 is returned. If the
9590 * specified code point is a supplementary character, its
9591 * surrogate values are stored in {@code dst[dstIndex]}
9592 * (high-surrogate) and {@code dst[dstIndex+1]}
9593 * (low-surrogate), and 2 is returned.
9594 *
9595 * @param codePoint the character (Unicode code point) to be converted.
9596 * @param dst an array of {@code char} in which the
9597 * {@code codePoint}'s UTF-16 value is stored.
9598 * @param dstIndex the start index into the {@code dst}
9599 * array where the converted value is stored.
9600 * @return 1 if the code point is a BMP code point, 2 if the
9601 * code point is a supplementary code point.
9602 * @throws IllegalArgumentException if the specified
9603 * {@code codePoint} is not a valid Unicode code point.
9604 * @throws NullPointerException if the specified {@code dst} is null.
9605 * @throws IndexOutOfBoundsException if {@code dstIndex}
9606 * is negative or not less than {@code dst.length}, or if
9607 * {@code dst} at {@code dstIndex} doesn't have enough
9608 * array element(s) to store the resulting {@code char}
9609 * value(s). (If {@code dstIndex} is equal to
9610 * {@code dst.length-1} and the specified
9611 * {@code codePoint} is a supplementary character, the
9612 * high-surrogate value is not stored in
9613 * {@code dst[dstIndex]}.)
9614 * @since 1.5
9615 */
9616 public static int toChars(int codePoint, char[] dst, int dstIndex) {
9617 if (isBmpCodePoint(codePoint)) {
9618 dst[dstIndex] = (char) codePoint;
9619 return 1;
9620 } else if (isValidCodePoint(codePoint)) {
9621 toSurrogates(codePoint, dst, dstIndex);
9622 return 2;
9623 } else {
9624 throw new IllegalArgumentException(
9625 String.format("Not a valid Unicode code point: 0x%X", codePoint));
9626 }
9627 }
9628
9629 /**
9630 * Converts the specified character (Unicode code point) to its
9631 * UTF-16 representation stored in a {@code char} array. If
9632 * the specified code point is a BMP (Basic Multilingual Plane or
9633 * Plane 0) value, the resulting {@code char} array has
9634 * the same value as {@code codePoint}. If the specified code
9635 * point is a supplementary code point, the resulting
9636 * {@code char} array has the corresponding surrogate pair.
9637 *
9638 * @param codePoint a Unicode code point
9639 * @return a {@code char} array having
9640 * {@code codePoint}'s UTF-16 representation.
9641 * @throws IllegalArgumentException if the specified
9642 * {@code codePoint} is not a valid Unicode code point.
9643 * @since 1.5
9644 */
9645 public static char[] toChars(int codePoint) {
9646 if (isBmpCodePoint(codePoint)) {
9647 return new char[] { (char) codePoint };
9648 } else if (isValidCodePoint(codePoint)) {
9649 char[] result = new char[2];
9650 toSurrogates(codePoint, result, 0);
9651 return result;
9652 } else {
9653 throw new IllegalArgumentException(
9654 String.format("Not a valid Unicode code point: 0x%X", codePoint));
9655 }
9656 }
9657
9658 static void toSurrogates(int codePoint, char[] dst, int index) {
9659 // We write elements "backwards" to guarantee all-or-nothing
9660 dst[index+1] = lowSurrogate(codePoint);
9661 dst[index] = highSurrogate(codePoint);
9662 }
9663
9664 /**
9665 * Returns the number of Unicode code points in the text range of
9666 * the specified char sequence. The text range begins at the
9667 * specified {@code beginIndex} and extends to the
9668 * {@code char} at index {@code endIndex - 1}. Thus the
9669 * length (in {@code char}s) of the text range is
9670 * {@code endIndex-beginIndex}. Unpaired surrogates within
9671 * the text range count as one code point each.
9672 *
9673 * @param seq the char sequence
9674 * @param beginIndex the index to the first {@code char} of
9675 * the text range.
9676 * @param endIndex the index after the last {@code char} of
9677 * the text range.
9678 * @return the number of Unicode code points in the specified text
9679 * range
9680 * @throws NullPointerException if {@code seq} is null.
9681 * @throws IndexOutOfBoundsException if the
9682 * {@code beginIndex} is negative, or {@code endIndex}
9683 * is larger than the length of the given sequence, or
9684 * {@code beginIndex} is larger than {@code endIndex}.
9685 * @since 1.5
9686 */
9687 public static int codePointCount(CharSequence seq, int beginIndex, int endIndex) {
9688 Objects.checkFromToIndex(beginIndex, endIndex, seq.length());
9689 int n = endIndex - beginIndex;
9690 for (int i = beginIndex; i < endIndex; ) {
9691 if (isHighSurrogate(seq.charAt(i++)) && i < endIndex &&
9692 isLowSurrogate(seq.charAt(i))) {
9693 n--;
9694 i++;
9695 }
9696 }
9697 return n;
9698 }
9699
9700 /**
9701 * Returns the number of Unicode code points in a subarray of the
9702 * {@code char} array argument. The {@code offset}
9703 * argument is the index of the first {@code char} of the
9704 * subarray and the {@code count} argument specifies the
9705 * length of the subarray in {@code char}s. Unpaired
9706 * surrogates within the subarray count as one code point each.
9707 *
9708 * @param a the {@code char} array
9709 * @param offset the index of the first {@code char} in the
9710 * given {@code char} array
9711 * @param count the length of the subarray in {@code char}s
9712 * @return the number of Unicode code points in the specified subarray
9713 * @throws NullPointerException if {@code a} is null.
9714 * @throws IndexOutOfBoundsException if {@code offset} or
9715 * {@code count} is negative, or if {@code offset +
9716 * count} is larger than the length of the given array.
9717 * @since 1.5
9718 */
9719 public static int codePointCount(char[] a, int offset, int count) {
9720 Objects.checkFromIndexSize(offset, count, a.length);
9721 return codePointCountImpl(a, offset, count);
9722 }
9723
9724 static int codePointCountImpl(char[] a, int offset, int count) {
9725 int endIndex = offset + count;
9726 int n = count;
9727 for (int i = offset; i < endIndex; ) {
9728 if (isHighSurrogate(a[i++]) && i < endIndex &&
9729 isLowSurrogate(a[i])) {
9730 n--;
9731 i++;
9732 }
9733 }
9734 return n;
9735 }
9736
9737 /**
9738 * Returns the index within the given char sequence that is offset
9739 * from the given {@code index} by {@code codePointOffset}
9740 * code points. Unpaired surrogates within the text range given by
9741 * {@code index} and {@code codePointOffset} count as
9742 * one code point each.
9743 *
9744 * @param seq the char sequence
9745 * @param index the index to be offset
9746 * @param codePointOffset the offset in code points
9747 * @return the index within the char sequence
9748 * @throws NullPointerException if {@code seq} is null.
9749 * @throws IndexOutOfBoundsException if {@code index}
9750 * is negative or larger than the length of the char sequence,
9751 * or if {@code codePointOffset} is positive and the
9752 * subsequence starting with {@code index} has fewer than
9753 * {@code codePointOffset} code points, or if
9754 * {@code codePointOffset} is negative and the subsequence
9755 * before {@code index} has fewer than the absolute value
9756 * of {@code codePointOffset} code points.
9757 * @since 1.5
9758 */
9759 public static int offsetByCodePoints(CharSequence seq, int index,
9760 int codePointOffset) {
9761 int length = seq.length();
9762 if (index < 0 || index > length) {
9763 throw new IndexOutOfBoundsException();
9764 }
9765
9766 int x = index;
9767 if (codePointOffset >= 0) {
9768 int i;
9769 for (i = 0; x < length && i < codePointOffset; i++) {
9770 if (isHighSurrogate(seq.charAt(x++)) && x < length &&
9771 isLowSurrogate(seq.charAt(x))) {
9772 x++;
9773 }
9774 }
9775 if (i < codePointOffset) {
9776 throw new IndexOutOfBoundsException();
9777 }
9778 } else {
9779 int i;
9780 for (i = codePointOffset; x > 0 && i < 0; i++) {
9781 if (isLowSurrogate(seq.charAt(--x)) && x > 0 &&
9782 isHighSurrogate(seq.charAt(x-1))) {
9783 x--;
9784 }
9785 }
9786 if (i < 0) {
9787 throw new IndexOutOfBoundsException();
9788 }
9789 }
9790 return x;
9791 }
9792
9793 /**
9794 * Returns the index within the given {@code char} subarray
9795 * that is offset from the given {@code index} by
9796 * {@code codePointOffset} code points. The
9797 * {@code start} and {@code count} arguments specify a
9798 * subarray of the {@code char} array. Unpaired surrogates
9799 * within the text range given by {@code index} and
9800 * {@code codePointOffset} count as one code point each.
9801 *
9802 * @param a the {@code char} array
9803 * @param start the index of the first {@code char} of the
9804 * subarray
9805 * @param count the length of the subarray in {@code char}s
9806 * @param index the index to be offset
9807 * @param codePointOffset the offset in code points
9808 * @return the index within the subarray
9809 * @throws NullPointerException if {@code a} is null.
9810 * @throws IndexOutOfBoundsException
9811 * if {@code start} or {@code count} is negative,
9812 * or if {@code start + count} is larger than the length of
9813 * the given array,
9814 * or if {@code index} is less than {@code start} or
9815 * larger then {@code start + count},
9816 * or if {@code codePointOffset} is positive and the text range
9817 * starting with {@code index} and ending with {@code start + count - 1}
9818 * has fewer than {@code codePointOffset} code
9819 * points,
9820 * or if {@code codePointOffset} is negative and the text range
9821 * starting with {@code start} and ending with {@code index - 1}
9822 * has fewer than the absolute value of
9823 * {@code codePointOffset} code points.
9824 * @since 1.5
9825 */
9826 public static int offsetByCodePoints(char[] a, int start, int count,
9827 int index, int codePointOffset) {
9828 if (count > a.length-start || start < 0 || count < 0
9829 || index < start || index > start+count) {
9830 throw new IndexOutOfBoundsException();
9831 }
9832 return offsetByCodePointsImpl(a, start, count, index, codePointOffset);
9833 }
9834
9835 static int offsetByCodePointsImpl(char[]a, int start, int count,
9836 int index, int codePointOffset) {
9837 int x = index;
9838 if (codePointOffset >= 0) {
9839 int limit = start + count;
9840 int i;
9841 for (i = 0; x < limit && i < codePointOffset; i++) {
9842 if (isHighSurrogate(a[x++]) && x < limit &&
9843 isLowSurrogate(a[x])) {
9844 x++;
9845 }
9846 }
9847 if (i < codePointOffset) {
9848 throw new IndexOutOfBoundsException();
9849 }
9850 } else {
9851 int i;
9852 for (i = codePointOffset; x > start && i < 0; i++) {
9853 if (isLowSurrogate(a[--x]) && x > start &&
9854 isHighSurrogate(a[x-1])) {
9855 x--;
9856 }
9857 }
9858 if (i < 0) {
9859 throw new IndexOutOfBoundsException();
9860 }
9861 }
9862 return x;
9863 }
9864
9865 /**
9866 * Determines if the specified character is a lowercase character.
9867 * <p>
9868 * A character is lowercase if its general category type, provided
9869 * by {@code Character.getType(ch)}, is
9870 * {@code LOWERCASE_LETTER}, or it has contributory property
9871 * Other_Lowercase as defined by the Unicode Standard.
9872 * <p>
9873 * The following are examples of lowercase characters:
9874 * <blockquote><pre>
9875 * 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
9876 * '\u00DF' '\u00E0' '\u00E1' '\u00E2' '\u00E3' '\u00E4' '\u00E5' '\u00E6'
9877 * '\u00E7' '\u00E8' '\u00E9' '\u00EA' '\u00EB' '\u00EC' '\u00ED' '\u00EE'
9878 * '\u00EF' '\u00F0' '\u00F1' '\u00F2' '\u00F3' '\u00F4' '\u00F5' '\u00F6'
9879 * '\u00F8' '\u00F9' '\u00FA' '\u00FB' '\u00FC' '\u00FD' '\u00FE' '\u00FF'
9880 * </pre></blockquote>
9881 * <p> Many other Unicode characters are lowercase too.
9882 *
9883 * <p><b>Note:</b> This method cannot handle <a
9884 * href="#supplementary"> supplementary characters</a>. To support
9885 * all Unicode characters, including supplementary characters, use
9886 * the {@link #isLowerCase(int)} method.
9887 *
9888 * @param ch the character to be tested.
9889 * @return {@code true} if the character is lowercase;
9890 * {@code false} otherwise.
9891 * @see Character#isLowerCase(char)
9892 * @see Character#isTitleCase(char)
9893 * @see Character#toLowerCase(char)
9894 * @see Character#getType(char)
9895 */
9896 public static boolean isLowerCase(char ch) {
9897 return isLowerCase((int)ch);
9898 }
9899
9900 /**
9901 * Determines if the specified character (Unicode code point) is a
9902 * lowercase character.
9903 * <p>
9904 * A character is lowercase if its general category type, provided
9905 * by {@link Character#getType getType(codePoint)}, is
9906 * {@code LOWERCASE_LETTER}, or it has contributory property
9907 * Other_Lowercase as defined by the Unicode Standard.
9908 * <p>
9909 * The following are examples of lowercase characters:
9910 * <blockquote><pre>
9911 * 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
9912 * '\u00DF' '\u00E0' '\u00E1' '\u00E2' '\u00E3' '\u00E4' '\u00E5' '\u00E6'
9913 * '\u00E7' '\u00E8' '\u00E9' '\u00EA' '\u00EB' '\u00EC' '\u00ED' '\u00EE'
9914 * '\u00EF' '\u00F0' '\u00F1' '\u00F2' '\u00F3' '\u00F4' '\u00F5' '\u00F6'
9915 * '\u00F8' '\u00F9' '\u00FA' '\u00FB' '\u00FC' '\u00FD' '\u00FE' '\u00FF'
9916 * </pre></blockquote>
9917 * <p> Many other Unicode characters are lowercase too.
9918 *
9919 * @param codePoint the character (Unicode code point) to be tested.
9920 * @return {@code true} if the character is lowercase;
9921 * {@code false} otherwise.
9922 * @see Character#isLowerCase(int)
9923 * @see Character#isTitleCase(int)
9924 * @see Character#toLowerCase(int)
9925 * @see Character#getType(int)
9926 * @since 1.5
9927 */
9928 public static boolean isLowerCase(int codePoint) {
9929 return CharacterData.of(codePoint).isLowerCase(codePoint);
9930 }
9931
9932 /**
9933 * Determines if the specified character is an uppercase character.
9934 * <p>
9935 * A character is uppercase if its general category type, provided by
9936 * {@code Character.getType(ch)}, is {@code UPPERCASE_LETTER}.
9937 * or it has contributory property Other_Uppercase as defined by the Unicode Standard.
9938 * <p>
9939 * The following are examples of uppercase characters:
9940 * <blockquote><pre>
9941 * 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
9942 * '\u00C0' '\u00C1' '\u00C2' '\u00C3' '\u00C4' '\u00C5' '\u00C6' '\u00C7'
9943 * '\u00C8' '\u00C9' '\u00CA' '\u00CB' '\u00CC' '\u00CD' '\u00CE' '\u00CF'
9944 * '\u00D0' '\u00D1' '\u00D2' '\u00D3' '\u00D4' '\u00D5' '\u00D6' '\u00D8'
9945 * '\u00D9' '\u00DA' '\u00DB' '\u00DC' '\u00DD' '\u00DE'
9946 * </pre></blockquote>
9947 * <p> Many other Unicode characters are uppercase too.
9948 *
9949 * <p><b>Note:</b> This method cannot handle <a
9950 * href="#supplementary"> supplementary characters</a>. To support
9951 * all Unicode characters, including supplementary characters, use
9952 * the {@link #isUpperCase(int)} method.
9953 *
9954 * @param ch the character to be tested.
9955 * @return {@code true} if the character is uppercase;
9956 * {@code false} otherwise.
9957 * @see Character#isLowerCase(char)
9958 * @see Character#isTitleCase(char)
9959 * @see Character#toUpperCase(char)
9960 * @see Character#getType(char)
9961 * @since 1.0
9962 */
9963 public static boolean isUpperCase(char ch) {
9964 return isUpperCase((int)ch);
9965 }
9966
9967 /**
9968 * Determines if the specified character (Unicode code point) is an uppercase character.
9969 * <p>
9970 * A character is uppercase if its general category type, provided by
9971 * {@link Character#getType(int) getType(codePoint)}, is {@code UPPERCASE_LETTER},
9972 * or it has contributory property Other_Uppercase as defined by the Unicode Standard.
9973 * <p>
9974 * The following are examples of uppercase characters:
9975 * <blockquote><pre>
9976 * 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
9977 * '\u00C0' '\u00C1' '\u00C2' '\u00C3' '\u00C4' '\u00C5' '\u00C6' '\u00C7'
9978 * '\u00C8' '\u00C9' '\u00CA' '\u00CB' '\u00CC' '\u00CD' '\u00CE' '\u00CF'
9979 * '\u00D0' '\u00D1' '\u00D2' '\u00D3' '\u00D4' '\u00D5' '\u00D6' '\u00D8'
9980 * '\u00D9' '\u00DA' '\u00DB' '\u00DC' '\u00DD' '\u00DE'
9981 * </pre></blockquote>
9982 * <p> Many other Unicode characters are uppercase too.
9983 *
9984 * @param codePoint the character (Unicode code point) to be tested.
9985 * @return {@code true} if the character is uppercase;
9986 * {@code false} otherwise.
9987 * @see Character#isLowerCase(int)
9988 * @see Character#isTitleCase(int)
9989 * @see Character#toUpperCase(int)
9990 * @see Character#getType(int)
9991 * @since 1.5
9992 */
9993 public static boolean isUpperCase(int codePoint) {
9994 return CharacterData.of(codePoint).isUpperCase(codePoint);
9995 }
9996
9997 /**
9998 * Determines if the specified character is a titlecase character.
9999 * <p>
10000 * A character is a titlecase character if its general
10001 * category type, provided by {@code Character.getType(ch)},
10002 * is {@code TITLECASE_LETTER}.
10003 * <p>
10004 * Some characters look like pairs of Latin letters. For example, there
10005 * is an uppercase letter that looks like "LJ" and has a corresponding
10006 * lowercase letter that looks like "lj". A third form, which looks like "Lj",
10007 * is the appropriate form to use when rendering a word in lowercase
10008 * with initial capitals, as for a book title.
10009 * <p>
10010 * These are some of the Unicode characters for which this method returns
10011 * {@code true}:
10012 * <ul>
10013 * <li>{@code LATIN CAPITAL LETTER D WITH SMALL LETTER Z WITH CARON}
10014 * <li>{@code LATIN CAPITAL LETTER L WITH SMALL LETTER J}
10015 * <li>{@code LATIN CAPITAL LETTER N WITH SMALL LETTER J}
10016 * <li>{@code LATIN CAPITAL LETTER D WITH SMALL LETTER Z}
10017 * </ul>
10018 * <p> Many other Unicode characters are titlecase too.
10019 *
10020 * <p><b>Note:</b> This method cannot handle <a
10021 * href="#supplementary"> supplementary characters</a>. To support
10022 * all Unicode characters, including supplementary characters, use
10023 * the {@link #isTitleCase(int)} method.
10024 *
10025 * @param ch the character to be tested.
10026 * @return {@code true} if the character is titlecase;
10027 * {@code false} otherwise.
10028 * @see Character#isLowerCase(char)
10029 * @see Character#isUpperCase(char)
10030 * @see Character#toTitleCase(char)
10031 * @see Character#getType(char)
10032 * @since 1.0.2
10033 */
10034 public static boolean isTitleCase(char ch) {
10035 return isTitleCase((int)ch);
10036 }
10037
10038 /**
10039 * Determines if the specified character (Unicode code point) is a titlecase character.
10040 * <p>
10041 * A character is a titlecase character if its general
10042 * category type, provided by {@link Character#getType(int) getType(codePoint)},
10043 * is {@code TITLECASE_LETTER}.
10044 * <p>
10045 * Some characters look like pairs of Latin letters. For example, there
10046 * is an uppercase letter that looks like "LJ" and has a corresponding
10047 * lowercase letter that looks like "lj". A third form, which looks like "Lj",
10048 * is the appropriate form to use when rendering a word in lowercase
10049 * with initial capitals, as for a book title.
10050 * <p>
10051 * These are some of the Unicode characters for which this method returns
10052 * {@code true}:
10053 * <ul>
10054 * <li>{@code LATIN CAPITAL LETTER D WITH SMALL LETTER Z WITH CARON}
10055 * <li>{@code LATIN CAPITAL LETTER L WITH SMALL LETTER J}
10056 * <li>{@code LATIN CAPITAL LETTER N WITH SMALL LETTER J}
10057 * <li>{@code LATIN CAPITAL LETTER D WITH SMALL LETTER Z}
10058 * </ul>
10059 * <p> Many other Unicode characters are titlecase too.
10060 *
10061 * @param codePoint the character (Unicode code point) to be tested.
10062 * @return {@code true} if the character is titlecase;
10063 * {@code false} otherwise.
10064 * @see Character#isLowerCase(int)
10065 * @see Character#isUpperCase(int)
10066 * @see Character#toTitleCase(int)
10067 * @see Character#getType(int)
10068 * @since 1.5
10069 */
10070 public static boolean isTitleCase(int codePoint) {
10071 return getType(codePoint) == Character.TITLECASE_LETTER;
10072 }
10073
10074 /**
10075 * Determines if the specified character is a digit.
10076 * <p>
10077 * A character is a digit if its general category type, provided
10078 * by {@code Character.getType(ch)}, is
10079 * {@code DECIMAL_DIGIT_NUMBER}.
10080 * <p>
10081 * Some Unicode character ranges that contain digits:
10082 * <ul>
10083 * <li>{@code '\u005Cu0030'} through {@code '\u005Cu0039'},
10084 * ISO-LATIN-1 digits ({@code '0'} through {@code '9'})
10085 * <li>{@code '\u005Cu0660'} through {@code '\u005Cu0669'},
10086 * Arabic-Indic digits
10087 * <li>{@code '\u005Cu06F0'} through {@code '\u005Cu06F9'},
10088 * Extended Arabic-Indic digits
10089 * <li>{@code '\u005Cu0966'} through {@code '\u005Cu096F'},
10090 * Devanagari digits
10091 * <li>{@code '\u005CuFF10'} through {@code '\u005CuFF19'},
10092 * Fullwidth digits
10093 * </ul>
10094 *
10095 * Many other character ranges contain digits as well.
10096 *
10097 * <p><b>Note:</b> This method cannot handle <a
10098 * href="#supplementary"> supplementary characters</a>. To support
10099 * all Unicode characters, including supplementary characters, use
10100 * the {@link #isDigit(int)} method.
10101 *
10102 * @param ch the character to be tested.
10103 * @return {@code true} if the character is a digit;
10104 * {@code false} otherwise.
10105 * @see Character#digit(char, int)
10106 * @see Character#forDigit(int, int)
10107 * @see Character#getType(char)
10108 */
10109 public static boolean isDigit(char ch) {
10110 return isDigit((int)ch);
10111 }
10112
10113 /**
10114 * Determines if the specified character (Unicode code point) is a digit.
10115 * <p>
10116 * A character is a digit if its general category type, provided
10117 * by {@link Character#getType(int) getType(codePoint)}, is
10118 * {@code DECIMAL_DIGIT_NUMBER}.
10119 * <p>
10120 * Some Unicode character ranges that contain digits:
10121 * <ul>
10122 * <li>{@code '\u005Cu0030'} through {@code '\u005Cu0039'},
10123 * ISO-LATIN-1 digits ({@code '0'} through {@code '9'})
10124 * <li>{@code '\u005Cu0660'} through {@code '\u005Cu0669'},
10125 * Arabic-Indic digits
10126 * <li>{@code '\u005Cu06F0'} through {@code '\u005Cu06F9'},
10127 * Extended Arabic-Indic digits
10128 * <li>{@code '\u005Cu0966'} through {@code '\u005Cu096F'},
10129 * Devanagari digits
10130 * <li>{@code '\u005CuFF10'} through {@code '\u005CuFF19'},
10131 * Fullwidth digits
10132 * </ul>
10133 *
10134 * Many other character ranges contain digits as well.
10135 *
10136 * @param codePoint the character (Unicode code point) to be tested.
10137 * @return {@code true} if the character is a digit;
10138 * {@code false} otherwise.
10139 * @see Character#forDigit(int, int)
10140 * @see Character#getType(int)
10141 * @since 1.5
10142 */
10143 public static boolean isDigit(int codePoint) {
10144 return CharacterData.of(codePoint).isDigit(codePoint);
10145 }
10146
10147 /**
10148 * Determines if a character is defined in Unicode.
10149 * <p>
10150 * A character is defined if at least one of the following is true:
10151 * <ul>
10152 * <li>It has an entry in the UnicodeData file.
10153 * <li>It has a value in a range defined by the UnicodeData file.
10154 * </ul>
10155 *
10156 * <p><b>Note:</b> This method cannot handle <a
10157 * href="#supplementary"> supplementary characters</a>. To support
10158 * all Unicode characters, including supplementary characters, use
10159 * the {@link #isDefined(int)} method.
10160 *
10161 * @param ch the character to be tested
10162 * @return {@code true} if the character has a defined meaning
10163 * in Unicode; {@code false} otherwise.
10164 * @see Character#isDigit(char)
10165 * @see Character#isLetter(char)
10166 * @see Character#isLetterOrDigit(char)
10167 * @see Character#isLowerCase(char)
10168 * @see Character#isTitleCase(char)
10169 * @see Character#isUpperCase(char)
10170 * @since 1.0.2
10171 */
10172 public static boolean isDefined(char ch) {
10173 return isDefined((int)ch);
10174 }
10175
10176 /**
10177 * Determines if a character (Unicode code point) is defined in Unicode.
10178 * <p>
10179 * A character is defined if at least one of the following is true:
10180 * <ul>
10181 * <li>It has an entry in the UnicodeData file.
10182 * <li>It has a value in a range defined by the UnicodeData file.
10183 * </ul>
10184 *
10185 * @param codePoint the character (Unicode code point) to be tested.
10186 * @return {@code true} if the character has a defined meaning
10187 * in Unicode; {@code false} otherwise.
10188 * @see Character#isDigit(int)
10189 * @see Character#isLetter(int)
10190 * @see Character#isLetterOrDigit(int)
10191 * @see Character#isLowerCase(int)
10192 * @see Character#isTitleCase(int)
10193 * @see Character#isUpperCase(int)
10194 * @since 1.5
10195 */
10196 public static boolean isDefined(int codePoint) {
10197 return getType(codePoint) != Character.UNASSIGNED;
10198 }
10199
10200 /**
10201 * Determines if the specified character is a letter.
10202 * <p>
10203 * A character is considered to be a letter if its general
10204 * category type, provided by {@code Character.getType(ch)},
10205 * is any of the following:
10206 * <ul>
10207 * <li> {@code UPPERCASE_LETTER}
10208 * <li> {@code LOWERCASE_LETTER}
10209 * <li> {@code TITLECASE_LETTER}
10210 * <li> {@code MODIFIER_LETTER}
10211 * <li> {@code OTHER_LETTER}
10212 * </ul>
10213 *
10214 * Not all letters have case. Many characters are
10215 * letters but are neither uppercase nor lowercase nor titlecase.
10216 *
10217 * <p><b>Note:</b> This method cannot handle <a
10218 * href="#supplementary"> supplementary characters</a>. To support
10219 * all Unicode characters, including supplementary characters, use
10220 * the {@link #isLetter(int)} method.
10221 *
10222 * @param ch the character to be tested.
10223 * @return {@code true} if the character is a letter;
10224 * {@code false} otherwise.
10225 * @see Character#isDigit(char)
10226 * @see Character#isJavaIdentifierStart(char)
10227 * @see Character#isJavaLetter(char)
10228 * @see Character#isJavaLetterOrDigit(char)
10229 * @see Character#isLetterOrDigit(char)
10230 * @see Character#isLowerCase(char)
10231 * @see Character#isTitleCase(char)
10232 * @see Character#isUnicodeIdentifierStart(char)
10233 * @see Character#isUpperCase(char)
10234 */
10235 public static boolean isLetter(char ch) {
10236 return isLetter((int)ch);
10237 }
10238
10239 /**
10240 * Determines if the specified character (Unicode code point) is a letter.
10241 * <p>
10242 * A character is considered to be a letter if its general
10243 * category type, provided by {@link Character#getType(int) getType(codePoint)},
10244 * is any of the following:
10245 * <ul>
10246 * <li> {@code UPPERCASE_LETTER}
10247 * <li> {@code LOWERCASE_LETTER}
10248 * <li> {@code TITLECASE_LETTER}
10249 * <li> {@code MODIFIER_LETTER}
10250 * <li> {@code OTHER_LETTER}
10251 * </ul>
10252 *
10253 * Not all letters have case. Many characters are
10254 * letters but are neither uppercase nor lowercase nor titlecase.
10255 *
10256 * @param codePoint the character (Unicode code point) to be tested.
10257 * @return {@code true} if the character is a letter;
10258 * {@code false} otherwise.
10259 * @see Character#isDigit(int)
10260 * @see Character#isJavaIdentifierStart(int)
10261 * @see Character#isLetterOrDigit(int)
10262 * @see Character#isLowerCase(int)
10263 * @see Character#isTitleCase(int)
10264 * @see Character#isUnicodeIdentifierStart(int)
10265 * @see Character#isUpperCase(int)
10266 * @since 1.5
10267 */
10268 public static boolean isLetter(int codePoint) {
10269 return ((((1 << Character.UPPERCASE_LETTER) |
10270 (1 << Character.LOWERCASE_LETTER) |
10271 (1 << Character.TITLECASE_LETTER) |
10272 (1 << Character.MODIFIER_LETTER) |
10273 (1 << Character.OTHER_LETTER)) >> getType(codePoint)) & 1)
10274 != 0;
10275 }
10276
10277 /**
10278 * Determines if the specified character is a letter or digit.
10279 * <p>
10280 * A character is considered to be a letter or digit if either
10281 * {@code Character.isLetter(char ch)} or
10282 * {@code Character.isDigit(char ch)} returns
10283 * {@code true} for the character.
10284 *
10285 * <p><b>Note:</b> This method cannot handle <a
10286 * href="#supplementary"> supplementary characters</a>. To support
10287 * all Unicode characters, including supplementary characters, use
10288 * the {@link #isLetterOrDigit(int)} method.
10289 *
10290 * @param ch the character to be tested.
10291 * @return {@code true} if the character is a letter or digit;
10292 * {@code false} otherwise.
10293 * @see Character#isDigit(char)
10294 * @see Character#isJavaIdentifierPart(char)
10295 * @see Character#isJavaLetter(char)
10296 * @see Character#isJavaLetterOrDigit(char)
10297 * @see Character#isLetter(char)
10298 * @see Character#isUnicodeIdentifierPart(char)
10299 * @since 1.0.2
10300 */
10301 public static boolean isLetterOrDigit(char ch) {
10302 return isLetterOrDigit((int)ch);
10303 }
10304
10305 /**
10306 * Determines if the specified character (Unicode code point) is a letter or digit.
10307 * <p>
10308 * A character is considered to be a letter or digit if either
10309 * {@link #isLetter(int) isLetter(codePoint)} or
10310 * {@link #isDigit(int) isDigit(codePoint)} returns
10311 * {@code true} for the character.
10312 *
10313 * @param codePoint the character (Unicode code point) to be tested.
10314 * @return {@code true} if the character is a letter or digit;
10315 * {@code false} otherwise.
10316 * @see Character#isDigit(int)
10317 * @see Character#isJavaIdentifierPart(int)
10318 * @see Character#isLetter(int)
10319 * @see Character#isUnicodeIdentifierPart(int)
10320 * @since 1.5
10321 */
10322 public static boolean isLetterOrDigit(int codePoint) {
10323 return ((((1 << Character.UPPERCASE_LETTER) |
10324 (1 << Character.LOWERCASE_LETTER) |
10325 (1 << Character.TITLECASE_LETTER) |
10326 (1 << Character.MODIFIER_LETTER) |
10327 (1 << Character.OTHER_LETTER) |
10328 (1 << Character.DECIMAL_DIGIT_NUMBER)) >> getType(codePoint)) & 1)
10329 != 0;
10330 }
10331
10332 /**
10333 * Determines if the specified character is permissible as the first
10334 * character in a Java identifier.
10335 * <p>
10336 * A character may start a Java identifier if and only if
10337 * one of the following conditions is true:
10338 * <ul>
10339 * <li> {@link #isLetter(char) isLetter(ch)} returns {@code true}
10340 * <li> {@link #getType(char) getType(ch)} returns {@code LETTER_NUMBER}
10341 * <li> {@code ch} is a currency symbol (such as {@code '$'})
10342 * <li> {@code ch} is a connecting punctuation character (such as {@code '_'}).
10343 * </ul>
10344 *
10345 * @param ch the character to be tested.
10346 * @return {@code true} if the character may start a Java
10347 * identifier; {@code false} otherwise.
10348 * @see Character#isJavaLetterOrDigit(char)
10349 * @see Character#isJavaIdentifierStart(char)
10350 * @see Character#isJavaIdentifierPart(char)
10351 * @see Character#isLetter(char)
10352 * @see Character#isLetterOrDigit(char)
10353 * @see Character#isUnicodeIdentifierStart(char)
10354 * @since 1.0.2
10355 * @deprecated Replaced by isJavaIdentifierStart(char).
10356 */
10357 @Deprecated(since="1.1")
10358 public static boolean isJavaLetter(char ch) {
10359 return isJavaIdentifierStart(ch);
10360 }
10361
10362 /**
10363 * Determines if the specified character may be part of a Java
10364 * identifier as other than the first character.
10365 * <p>
10366 * A character may be part of a Java identifier if and only if one
10367 * of the following conditions is true:
10368 * <ul>
10369 * <li> it is a letter
10370 * <li> it is a currency symbol (such as {@code '$'})
10371 * <li> it is a connecting punctuation character (such as {@code '_'})
10372 * <li> it is a digit
10373 * <li> it is a numeric letter (such as a Roman numeral character)
10374 * <li> it is a combining mark
10375 * <li> it is a non-spacing mark
10376 * <li> {@code isIdentifierIgnorable} returns
10377 * {@code true} for the character.
10378 * </ul>
10379 *
10380 * @param ch the character to be tested.
10381 * @return {@code true} if the character may be part of a
10382 * Java identifier; {@code false} otherwise.
10383 * @see Character#isJavaLetter(char)
10384 * @see Character#isJavaIdentifierStart(char)
10385 * @see Character#isJavaIdentifierPart(char)
10386 * @see Character#isLetter(char)
10387 * @see Character#isLetterOrDigit(char)
10388 * @see Character#isUnicodeIdentifierPart(char)
10389 * @see Character#isIdentifierIgnorable(char)
10390 * @since 1.0.2
10391 * @deprecated Replaced by isJavaIdentifierPart(char).
10392 */
10393 @Deprecated(since="1.1")
10394 public static boolean isJavaLetterOrDigit(char ch) {
10395 return isJavaIdentifierPart(ch);
10396 }
10397
10398 /**
10399 * Determines if the specified character (Unicode code point) is alphabetic.
10400 * <p>
10401 * A character is considered to be alphabetic if its general category type,
10402 * provided by {@link Character#getType(int) getType(codePoint)}, is any of
10403 * the following:
10404 * <ul>
10405 * <li> {@code UPPERCASE_LETTER}
10406 * <li> {@code LOWERCASE_LETTER}
10407 * <li> {@code TITLECASE_LETTER}
10408 * <li> {@code MODIFIER_LETTER}
10409 * <li> {@code OTHER_LETTER}
10410 * <li> {@code LETTER_NUMBER}
10411 * </ul>
10412 * or it has contributory property Other_Alphabetic as defined by the
10413 * Unicode Standard.
10414 *
10415 * @param codePoint the character (Unicode code point) to be tested.
10416 * @return {@code true} if the character is a Unicode alphabet
10417 * character, {@code false} otherwise.
10418 * @since 1.7
10419 */
10420 public static boolean isAlphabetic(int codePoint) {
10421 return (((((1 << Character.UPPERCASE_LETTER) |
10422 (1 << Character.LOWERCASE_LETTER) |
10423 (1 << Character.TITLECASE_LETTER) |
10424 (1 << Character.MODIFIER_LETTER) |
10425 (1 << Character.OTHER_LETTER) |
10426 (1 << Character.LETTER_NUMBER)) >> getType(codePoint)) & 1) != 0) ||
10427 CharacterData.of(codePoint).isOtherAlphabetic(codePoint);
10428 }
10429
10430 /**
10431 * Determines if the specified character (Unicode code point) is a CJKV
10432 * (Chinese, Japanese, Korean and Vietnamese) ideograph, as defined by
10433 * the Unicode Standard.
10434 *
10435 * @param codePoint the character (Unicode code point) to be tested.
10436 * @return {@code true} if the character is a Unicode ideograph
10437 * character, {@code false} otherwise.
10438 * @since 1.7
10439 */
10440 public static boolean isIdeographic(int codePoint) {
10441 return CharacterData.of(codePoint).isIdeographic(codePoint);
10442 }
10443
10444 /**
10445 * Determines if the specified character is
10446 * permissible as the first character in a Java identifier.
10447 * <p>
10448 * A character may start a Java identifier if and only if
10449 * one of the following conditions is true:
10450 * <ul>
10451 * <li> {@link #isLetter(char) isLetter(ch)} returns {@code true}
10452 * <li> {@link #getType(char) getType(ch)} returns {@code LETTER_NUMBER}
10453 * <li> {@code ch} is a currency symbol (such as {@code '$'})
10454 * <li> {@code ch} is a connecting punctuation character (such as {@code '_'}).
10455 * </ul>
10456 *
10457 * <p><b>Note:</b> This method cannot handle <a
10458 * href="#supplementary"> supplementary characters</a>. To support
10459 * all Unicode characters, including supplementary characters, use
10460 * the {@link #isJavaIdentifierStart(int)} method.
10461 *
10462 * @param ch the character to be tested.
10463 * @return {@code true} if the character may start a Java identifier;
10464 * {@code false} otherwise.
10465 * @see Character#isJavaIdentifierPart(char)
10466 * @see Character#isLetter(char)
10467 * @see Character#isUnicodeIdentifierStart(char)
10468 * @see java.compiler/javax.lang.model.SourceVersion#isIdentifier(CharSequence)
10469 * @since 1.1
10470 */
10471 @SuppressWarnings("doclint:reference") // cross-module links
10472 public static boolean isJavaIdentifierStart(char ch) {
10473 return isJavaIdentifierStart((int)ch);
10474 }
10475
10476 /**
10477 * Determines if the character (Unicode code point) is
10478 * permissible as the first character in a Java identifier.
10479 * <p>
10480 * A character may start a Java identifier if and only if
10481 * one of the following conditions is true:
10482 * <ul>
10483 * <li> {@link #isLetter(int) isLetter(codePoint)}
10484 * returns {@code true}
10485 * <li> {@link #getType(int) getType(codePoint)}
10486 * returns {@code LETTER_NUMBER}
10487 * <li> the referenced character is a currency symbol (such as {@code '$'})
10488 * <li> the referenced character is a connecting punctuation character
10489 * (such as {@code '_'}).
10490 * </ul>
10491 *
10492 * @param codePoint the character (Unicode code point) to be tested.
10493 * @return {@code true} if the character may start a Java identifier;
10494 * {@code false} otherwise.
10495 * @see Character#isJavaIdentifierPart(int)
10496 * @see Character#isLetter(int)
10497 * @see Character#isUnicodeIdentifierStart(int)
10498 * @see java.compiler/javax.lang.model.SourceVersion#isIdentifier(CharSequence)
10499 * @since 1.5
10500 */
10501 @SuppressWarnings("doclint:reference") // cross-module links
10502 public static boolean isJavaIdentifierStart(int codePoint) {
10503 return CharacterData.of(codePoint).isJavaIdentifierStart(codePoint);
10504 }
10505
10506 /**
10507 * Determines if the specified character may be part of a Java
10508 * identifier as other than the first character.
10509 * <p>
10510 * A character may be part of a Java identifier if any of the following
10511 * conditions are true:
10512 * <ul>
10513 * <li> it is a letter
10514 * <li> it is a currency symbol (such as {@code '$'})
10515 * <li> it is a connecting punctuation character (such as {@code '_'})
10516 * <li> it is a digit
10517 * <li> it is a numeric letter (such as a Roman numeral character)
10518 * <li> it is a combining mark
10519 * <li> it is a non-spacing mark
10520 * <li> {@code isIdentifierIgnorable} returns
10521 * {@code true} for the character
10522 * </ul>
10523 *
10524 * <p><b>Note:</b> This method cannot handle <a
10525 * href="#supplementary"> supplementary characters</a>. To support
10526 * all Unicode characters, including supplementary characters, use
10527 * the {@link #isJavaIdentifierPart(int)} method.
10528 *
10529 * @param ch the character to be tested.
10530 * @return {@code true} if the character may be part of a
10531 * Java identifier; {@code false} otherwise.
10532 * @see Character#isIdentifierIgnorable(char)
10533 * @see Character#isJavaIdentifierStart(char)
10534 * @see Character#isLetterOrDigit(char)
10535 * @see Character#isUnicodeIdentifierPart(char)
10536 * @see java.compiler/javax.lang.model.SourceVersion#isIdentifier(CharSequence)
10537 * @since 1.1
10538 */
10539 @SuppressWarnings("doclint:reference") // cross-module links
10540 public static boolean isJavaIdentifierPart(char ch) {
10541 return isJavaIdentifierPart((int)ch);
10542 }
10543
10544 /**
10545 * Determines if the character (Unicode code point) may be part of a Java
10546 * identifier as other than the first character.
10547 * <p>
10548 * A character may be part of a Java identifier if any of the following
10549 * conditions are true:
10550 * <ul>
10551 * <li> it is a letter
10552 * <li> it is a currency symbol (such as {@code '$'})
10553 * <li> it is a connecting punctuation character (such as {@code '_'})
10554 * <li> it is a digit
10555 * <li> it is a numeric letter (such as a Roman numeral character)
10556 * <li> it is a combining mark
10557 * <li> it is a non-spacing mark
10558 * <li> {@link #isIdentifierIgnorable(int)
10559 * isIdentifierIgnorable(codePoint)} returns {@code true} for
10560 * the code point
10561 * </ul>
10562 *
10563 * @param codePoint the character (Unicode code point) to be tested.
10564 * @return {@code true} if the character may be part of a
10565 * Java identifier; {@code false} otherwise.
10566 * @see Character#isIdentifierIgnorable(int)
10567 * @see Character#isJavaIdentifierStart(int)
10568 * @see Character#isLetterOrDigit(int)
10569 * @see Character#isUnicodeIdentifierPart(int)
10570 * @see java.compiler/javax.lang.model.SourceVersion#isIdentifier(CharSequence)
10571 * @since 1.5
10572 */
10573 @SuppressWarnings("doclint:reference") // cross-module links
10574 public static boolean isJavaIdentifierPart(int codePoint) {
10575 return CharacterData.of(codePoint).isJavaIdentifierPart(codePoint);
10576 }
10577
10578 /**
10579 * Determines if the specified character is permissible as the
10580 * first character in a Unicode identifier.
10581 * <p>
10582 * A character may start a Unicode identifier if and only if
10583 * one of the following conditions is true:
10584 * <ul>
10585 * <li> {@link #isLetter(char) isLetter(ch)} returns {@code true}
10586 * <li> {@link #getType(char) getType(ch)} returns
10587 * {@code LETTER_NUMBER}.
10588 * <li> it is an <a href="http://www.unicode.org/reports/tr44/#Other_ID_Start">
10589 * {@code Other_ID_Start}</a> character.
10590 * </ul>
10591 * <p>
10592 * This method conforms to <a href="https://unicode.org/reports/tr31/#R1">
10593 * UAX31-R1: Default Identifiers</a> requirement of the Unicode Standard,
10594 * with the following profile of UAX31:
10595 * <pre>
10596 * Start := ID_Start + 'VERTICAL TILDE' (U+2E2F)
10597 * </pre>
10598 * {@code 'VERTICAL TILDE'} is added to {@code Start} for backward
10599 * compatibility.
10600 *
10601 * <p><b>Note:</b> This method cannot handle <a
10602 * href="#supplementary"> supplementary characters</a>. To support
10603 * all Unicode characters, including supplementary characters, use
10604 * the {@link #isUnicodeIdentifierStart(int)} method.
10605 *
10606 * @param ch the character to be tested.
10607 * @return {@code true} if the character may start a Unicode
10608 * identifier; {@code false} otherwise.
10609 *
10610 * @spec https://www.unicode.org/reports/tr44 Unicode Character Database
10611 * @spec https://www.unicode.org/reports/tr31 Unicode Identifier and Pattern Syntax
10612 * @see Character#isJavaIdentifierStart(char)
10613 * @see Character#isLetter(char)
10614 * @see Character#isUnicodeIdentifierPart(char)
10615 * @since 1.1
10616 */
10617 public static boolean isUnicodeIdentifierStart(char ch) {
10618 return isUnicodeIdentifierStart((int)ch);
10619 }
10620
10621 /**
10622 * Determines if the specified character (Unicode code point) is permissible as the
10623 * first character in a Unicode identifier.
10624 * <p>
10625 * A character may start a Unicode identifier if and only if
10626 * one of the following conditions is true:
10627 * <ul>
10628 * <li> {@link #isLetter(int) isLetter(codePoint)}
10629 * returns {@code true}
10630 * <li> {@link #getType(int) getType(codePoint)}
10631 * returns {@code LETTER_NUMBER}.
10632 * <li> it is an <a href="http://www.unicode.org/reports/tr44/#Other_ID_Start">
10633 * {@code Other_ID_Start}</a> character.
10634 * </ul>
10635 * <p>
10636 * This method conforms to <a href="https://unicode.org/reports/tr31/#R1">
10637 * UAX31-R1: Default Identifiers</a> requirement of the Unicode Standard,
10638 * with the following profile of UAX31:
10639 * <pre>
10640 * Start := ID_Start + 'VERTICAL TILDE' (U+2E2F)
10641 * </pre>
10642 * {@code 'VERTICAL TILDE'} is added to {@code Start} for backward
10643 * compatibility.
10644 *
10645 * @param codePoint the character (Unicode code point) to be tested.
10646 * @return {@code true} if the character may start a Unicode
10647 * identifier; {@code false} otherwise.
10648 *
10649 * @spec https://www.unicode.org/reports/tr44 Unicode Character Database
10650 * @spec https://www.unicode.org/reports/tr31 Unicode Identifier and Pattern Syntax
10651 * @see Character#isJavaIdentifierStart(int)
10652 * @see Character#isLetter(int)
10653 * @see Character#isUnicodeIdentifierPart(int)
10654 * @since 1.5
10655 */
10656 public static boolean isUnicodeIdentifierStart(int codePoint) {
10657 return CharacterData.of(codePoint).isUnicodeIdentifierStart(codePoint);
10658 }
10659
10660 /**
10661 * Determines if the specified character may be part of a Unicode
10662 * identifier as other than the first character.
10663 * <p>
10664 * A character may be part of a Unicode identifier if and only if
10665 * one of the following statements is true:
10666 * <ul>
10667 * <li> it is a letter
10668 * <li> it is a connecting punctuation character (such as {@code '_'})
10669 * <li> it is a digit
10670 * <li> it is a numeric letter (such as a Roman numeral character)
10671 * <li> it is a combining mark
10672 * <li> it is a non-spacing mark
10673 * <li> {@code isIdentifierIgnorable} returns
10674 * {@code true} for this character.
10675 * <li> it is an <a href="http://www.unicode.org/reports/tr44/#Other_ID_Start">
10676 * {@code Other_ID_Start}</a> character.
10677 * <li> it is an <a href="http://www.unicode.org/reports/tr44/#Other_ID_Continue">
10678 * {@code Other_ID_Continue}</a> character.
10679 * </ul>
10680 * <p>
10681 * This method conforms to <a href="https://unicode.org/reports/tr31/#R1">
10682 * UAX31-R1: Default Identifiers</a> requirement of the Unicode Standard,
10683 * with the following profile of UAX31:
10684 * <pre>
10685 * Continue := Start + ID_Continue + ignorable
10686 * Medial := empty
10687 * ignorable := isIdentifierIgnorable(char) returns true for the character
10688 * </pre>
10689 * {@code ignorable} is added to {@code Continue} for backward
10690 * compatibility.
10691 *
10692 * <p><b>Note:</b> This method cannot handle <a
10693 * href="#supplementary"> supplementary characters</a>. To support
10694 * all Unicode characters, including supplementary characters, use
10695 * the {@link #isUnicodeIdentifierPart(int)} method.
10696 *
10697 * @param ch the character to be tested.
10698 * @return {@code true} if the character may be part of a
10699 * Unicode identifier; {@code false} otherwise.
10700 *
10701 * @spec https://www.unicode.org/reports/tr44 Unicode Character Database
10702 * @spec https://www.unicode.org/reports/tr31 Unicode Identifier and Pattern Syntax
10703 * @see Character#isIdentifierIgnorable(char)
10704 * @see Character#isJavaIdentifierPart(char)
10705 * @see Character#isLetterOrDigit(char)
10706 * @see Character#isUnicodeIdentifierStart(char)
10707 * @since 1.1
10708 */
10709 public static boolean isUnicodeIdentifierPart(char ch) {
10710 return isUnicodeIdentifierPart((int)ch);
10711 }
10712
10713 /**
10714 * Determines if the specified character (Unicode code point) may be part of a Unicode
10715 * identifier as other than the first character.
10716 * <p>
10717 * A character may be part of a Unicode identifier if and only if
10718 * one of the following statements is true:
10719 * <ul>
10720 * <li> it is a letter
10721 * <li> it is a connecting punctuation character (such as {@code '_'})
10722 * <li> it is a digit
10723 * <li> it is a numeric letter (such as a Roman numeral character)
10724 * <li> it is a combining mark
10725 * <li> it is a non-spacing mark
10726 * <li> {@code isIdentifierIgnorable} returns
10727 * {@code true} for this character.
10728 * <li> it is an <a href="http://www.unicode.org/reports/tr44/#Other_ID_Start">
10729 * {@code Other_ID_Start}</a> character.
10730 * <li> it is an <a href="http://www.unicode.org/reports/tr44/#Other_ID_Continue">
10731 * {@code Other_ID_Continue}</a> character.
10732 * </ul>
10733 * <p>
10734 * This method conforms to <a href="https://unicode.org/reports/tr31/#R1">
10735 * UAX31-R1: Default Identifiers</a> requirement of the Unicode Standard,
10736 * with the following profile of UAX31:
10737 * <pre>
10738 * Continue := Start + ID_Continue + ignorable
10739 * Medial := empty
10740 * ignorable := isIdentifierIgnorable(int) returns true for the character
10741 * </pre>
10742 * {@code ignorable} is added to {@code Continue} for backward
10743 * compatibility.
10744 *
10745 * @param codePoint the character (Unicode code point) to be tested.
10746 * @return {@code true} if the character may be part of a
10747 * Unicode identifier; {@code false} otherwise.
10748 *
10749 * @spec https://www.unicode.org/reports/tr44 Unicode Character Database
10750 * @spec https://www.unicode.org/reports/tr31 Unicode Identifier and Pattern Syntax
10751 * @see Character#isIdentifierIgnorable(int)
10752 * @see Character#isJavaIdentifierPart(int)
10753 * @see Character#isLetterOrDigit(int)
10754 * @see Character#isUnicodeIdentifierStart(int)
10755 * @since 1.5
10756 */
10757 public static boolean isUnicodeIdentifierPart(int codePoint) {
10758 return CharacterData.of(codePoint).isUnicodeIdentifierPart(codePoint);
10759 }
10760
10761 /**
10762 * Determines if the specified character should be regarded as
10763 * an ignorable character in a Java identifier or a Unicode identifier.
10764 * <p>
10765 * The following Unicode characters are ignorable in a Java identifier
10766 * or a Unicode identifier:
10767 * <ul>
10768 * <li>ISO control characters that are not whitespace
10769 * <ul>
10770 * <li>{@code '\u005Cu0000'} through {@code '\u005Cu0008'}
10771 * <li>{@code '\u005Cu000E'} through {@code '\u005Cu001B'}
10772 * <li>{@code '\u005Cu007F'} through {@code '\u005Cu009F'}
10773 * </ul>
10774 *
10775 * <li>all characters that have the {@code FORMAT} general
10776 * category value
10777 * </ul>
10778 *
10779 * <p><b>Note:</b> This method cannot handle <a
10780 * href="#supplementary"> supplementary characters</a>. To support
10781 * all Unicode characters, including supplementary characters, use
10782 * the {@link #isIdentifierIgnorable(int)} method.
10783 *
10784 * @param ch the character to be tested.
10785 * @return {@code true} if the character is an ignorable control
10786 * character that may be part of a Java or Unicode identifier;
10787 * {@code false} otherwise.
10788 * @see Character#isJavaIdentifierPart(char)
10789 * @see Character#isUnicodeIdentifierPart(char)
10790 * @since 1.1
10791 */
10792 public static boolean isIdentifierIgnorable(char ch) {
10793 return isIdentifierIgnorable((int)ch);
10794 }
10795
10796 /**
10797 * Determines if the specified character (Unicode code point) should be regarded as
10798 * an ignorable character in a Java identifier or a Unicode identifier.
10799 * <p>
10800 * The following Unicode characters are ignorable in a Java identifier
10801 * or a Unicode identifier:
10802 * <ul>
10803 * <li>ISO control characters that are not whitespace
10804 * <ul>
10805 * <li>{@code '\u005Cu0000'} through {@code '\u005Cu0008'}
10806 * <li>{@code '\u005Cu000E'} through {@code '\u005Cu001B'}
10807 * <li>{@code '\u005Cu007F'} through {@code '\u005Cu009F'}
10808 * </ul>
10809 *
10810 * <li>all characters that have the {@code FORMAT} general
10811 * category value
10812 * </ul>
10813 *
10814 * @param codePoint the character (Unicode code point) to be tested.
10815 * @return {@code true} if the character is an ignorable control
10816 * character that may be part of a Java or Unicode identifier;
10817 * {@code false} otherwise.
10818 * @see Character#isJavaIdentifierPart(int)
10819 * @see Character#isUnicodeIdentifierPart(int)
10820 * @since 1.5
10821 */
10822 public static boolean isIdentifierIgnorable(int codePoint) {
10823 return CharacterData.of(codePoint).isIdentifierIgnorable(codePoint);
10824 }
10825
10826 /**
10827 * Determines if the specified character (Unicode code point) is an Emoji.
10828 * <p>
10829 * A character is considered to be an Emoji if and only if it has the {@code Emoji}
10830 * property, defined in
10831 * <a href="https://unicode.org/reports/tr51/#Emoji_Properties_and_Data_Files">
10832 * Unicode Emoji (Technical Standard #51)</a>.
10833 *
10834 * @param codePoint the character (Unicode code point) to be tested.
10835 * @return {@code true} if the character is an Emoji;
10836 * {@code false} otherwise.
10837 * @since 21
10838 */
10839 public static boolean isEmoji(int codePoint) {
10840 return CharacterData.of(codePoint).isEmoji(codePoint);
10841 }
10842
10843 /**
10844 * Determines if the specified character (Unicode code point) has the
10845 * Emoji Presentation property by default.
10846 * <p>
10847 * A character is considered to have the Emoji Presentation property if and
10848 * only if it has the {@code Emoji_Presentation} property, defined in
10849 * <a href="https://unicode.org/reports/tr51/#Emoji_Properties_and_Data_Files">
10850 * Unicode Emoji (Technical Standard #51)</a>.
10851 *
10852 * @param codePoint the character (Unicode code point) to be tested.
10853 * @return {@code true} if the character has the Emoji Presentation
10854 * property; {@code false} otherwise.
10855 * @since 21
10856 */
10857 public static boolean isEmojiPresentation(int codePoint) {
10858 return CharacterData.of(codePoint).isEmojiPresentation(codePoint);
10859 }
10860
10861 /**
10862 * Determines if the specified character (Unicode code point) is an
10863 * Emoji Modifier.
10864 * <p>
10865 * A character is considered to be an Emoji Modifier if and only if it has
10866 * the {@code Emoji_Modifier} property, defined in
10867 * <a href="https://unicode.org/reports/tr51/#Emoji_Properties_and_Data_Files">
10868 * Unicode Emoji (Technical Standard #51)</a>.
10869 *
10870 * @param codePoint the character (Unicode code point) to be tested.
10871 * @return {@code true} if the character is an Emoji Modifier;
10872 * {@code false} otherwise.
10873 * @since 21
10874 */
10875 public static boolean isEmojiModifier(int codePoint) {
10876 return CharacterData.of(codePoint).isEmojiModifier(codePoint);
10877 }
10878
10879 /**
10880 * Determines if the specified character (Unicode code point) is an
10881 * Emoji Modifier Base.
10882 * <p>
10883 * A character is considered to be an Emoji Modifier Base if and only if it has
10884 * the {@code Emoji_Modifier_Base} property, defined in
10885 * <a href="https://unicode.org/reports/tr51/#Emoji_Properties_and_Data_Files">
10886 * Unicode Emoji (Technical Standard #51)</a>.
10887 *
10888 * @param codePoint the character (Unicode code point) to be tested.
10889 * @return {@code true} if the character is an Emoji Modifier Base;
10890 * {@code false} otherwise.
10891 * @since 21
10892 */
10893 public static boolean isEmojiModifierBase(int codePoint) {
10894 return CharacterData.of(codePoint).isEmojiModifierBase(codePoint);
10895 }
10896
10897 /**
10898 * Determines if the specified character (Unicode code point) is an
10899 * Emoji Component.
10900 * <p>
10901 * A character is considered to be an Emoji Component if and only if it has
10902 * the {@code Emoji_Component} property, defined in
10903 * <a href="https://unicode.org/reports/tr51/#Emoji_Properties_and_Data_Files">
10904 * Unicode Emoji (Technical Standard #51)</a>.
10905 *
10906 * @param codePoint the character (Unicode code point) to be tested.
10907 * @return {@code true} if the character is an Emoji Component;
10908 * {@code false} otherwise.
10909 * @since 21
10910 */
10911 public static boolean isEmojiComponent(int codePoint) {
10912 return CharacterData.of(codePoint).isEmojiComponent(codePoint);
10913 }
10914
10915 /**
10916 * Determines if the specified character (Unicode code point) is
10917 * an Extended Pictographic.
10918 * <p>
10919 * A character is considered to be an Extended Pictographic if and only if it has
10920 * the {@code Extended_Pictographic} property, defined in
10921 * <a href="https://unicode.org/reports/tr51/#Emoji_Properties_and_Data_Files">
10922 * Unicode Emoji (Technical Standard #51)</a>.
10923 *
10924 * @param codePoint the character (Unicode code point) to be tested.
10925 * @return {@code true} if the character is an Extended Pictographic;
10926 * {@code false} otherwise.
10927 * @since 21
10928 */
10929 public static boolean isExtendedPictographic(int codePoint) {
10930 return CharacterData.of(codePoint).isExtendedPictographic(codePoint);
10931 }
10932
10933 /**
10934 * Converts the character argument to lowercase using case
10935 * mapping information from the UnicodeData file.
10936 * <p>
10937 * Note that
10938 * {@code Character.isLowerCase(Character.toLowerCase(ch))}
10939 * does not always return {@code true} for some ranges of
10940 * characters, particularly those that are symbols or ideographs.
10941 *
10942 * <p>In general, {@link String#toLowerCase()} should be used to map
10943 * characters to lowercase. {@code String} case mapping methods
10944 * have several benefits over {@code Character} case mapping methods.
10945 * {@code String} case mapping methods can perform locale-sensitive
10946 * mappings, context-sensitive mappings, and 1:M character mappings, whereas
10947 * the {@code Character} case mapping methods cannot.
10948 *
10949 * <p><b>Note:</b> This method cannot handle <a
10950 * href="#supplementary"> supplementary characters</a>. To support
10951 * all Unicode characters, including supplementary characters, use
10952 * the {@link #toLowerCase(int)} method.
10953 *
10954 * @param ch the character to be converted.
10955 * @return the lowercase equivalent of the character, if any;
10956 * otherwise, the character itself.
10957 * @see Character#isLowerCase(char)
10958 * @see String#toLowerCase()
10959 */
10960 public static char toLowerCase(char ch) {
10961 return (char)toLowerCase((int)ch);
10962 }
10963
10964 /**
10965 * Converts the character (Unicode code point) argument to
10966 * lowercase using case mapping information from the UnicodeData
10967 * file.
10968 *
10969 * <p> Note that
10970 * {@code Character.isLowerCase(Character.toLowerCase(codePoint))}
10971 * does not always return {@code true} for some ranges of
10972 * characters, particularly those that are symbols or ideographs.
10973 *
10974 * <p>In general, {@link String#toLowerCase()} should be used to map
10975 * characters to lowercase. {@code String} case mapping methods
10976 * have several benefits over {@code Character} case mapping methods.
10977 * {@code String} case mapping methods can perform locale-sensitive
10978 * mappings, context-sensitive mappings, and 1:M character mappings, whereas
10979 * the {@code Character} case mapping methods cannot.
10980 *
10981 * @param codePoint the character (Unicode code point) to be converted.
10982 * @return the lowercase equivalent of the character (Unicode code
10983 * point), if any; otherwise, the character itself.
10984 * @see Character#isLowerCase(int)
10985 * @see String#toLowerCase()
10986 *
10987 * @since 1.5
10988 */
10989 public static int toLowerCase(int codePoint) {
10990 return CharacterData.of(codePoint).toLowerCase(codePoint);
10991 }
10992
10993 /**
10994 * Converts the character argument to uppercase using case mapping
10995 * information from the UnicodeData file.
10996 * <p>
10997 * Note that
10998 * {@code Character.isUpperCase(Character.toUpperCase(ch))}
10999 * does not always return {@code true} for some ranges of
11000 * characters, particularly those that are symbols or ideographs.
11001 *
11002 * <p>In general, {@link String#toUpperCase()} should be used to map
11003 * characters to uppercase. {@code String} case mapping methods
11004 * have several benefits over {@code Character} case mapping methods.
11005 * {@code String} case mapping methods can perform locale-sensitive
11006 * mappings, context-sensitive mappings, and 1:M character mappings, whereas
11007 * the {@code Character} case mapping methods cannot.
11008 *
11009 * <p><b>Note:</b> This method cannot handle <a
11010 * href="#supplementary"> supplementary characters</a>. To support
11011 * all Unicode characters, including supplementary characters, use
11012 * the {@link #toUpperCase(int)} method.
11013 *
11014 * @param ch the character to be converted.
11015 * @return the uppercase equivalent of the character, if any;
11016 * otherwise, the character itself.
11017 * @see Character#isUpperCase(char)
11018 * @see String#toUpperCase()
11019 */
11020 public static char toUpperCase(char ch) {
11021 return (char)toUpperCase((int)ch);
11022 }
11023
11024 /**
11025 * Converts the character (Unicode code point) argument to
11026 * uppercase using case mapping information from the UnicodeData
11027 * file.
11028 *
11029 * <p>Note that
11030 * {@code Character.isUpperCase(Character.toUpperCase(codePoint))}
11031 * does not always return {@code true} for some ranges of
11032 * characters, particularly those that are symbols or ideographs.
11033 *
11034 * <p>In general, {@link String#toUpperCase()} should be used to map
11035 * characters to uppercase. {@code String} case mapping methods
11036 * have several benefits over {@code Character} case mapping methods.
11037 * {@code String} case mapping methods can perform locale-sensitive
11038 * mappings, context-sensitive mappings, and 1:M character mappings, whereas
11039 * the {@code Character} case mapping methods cannot.
11040 *
11041 * @param codePoint the character (Unicode code point) to be converted.
11042 * @return the uppercase equivalent of the character, if any;
11043 * otherwise, the character itself.
11044 * @see Character#isUpperCase(int)
11045 * @see String#toUpperCase()
11046 *
11047 * @since 1.5
11048 */
11049 public static int toUpperCase(int codePoint) {
11050 return CharacterData.of(codePoint).toUpperCase(codePoint);
11051 }
11052
11053 /**
11054 * Converts the character argument to titlecase using case mapping
11055 * information from the UnicodeData file. If a character has no
11056 * explicit titlecase mapping and is not itself a titlecase char
11057 * according to UnicodeData, then the uppercase mapping is
11058 * returned as an equivalent titlecase mapping. If the
11059 * {@code char} argument is already a titlecase
11060 * {@code char}, the same {@code char} value will be
11061 * returned.
11062 * <p>
11063 * Note that
11064 * {@code Character.isTitleCase(Character.toTitleCase(ch))}
11065 * does not always return {@code true} for some ranges of
11066 * characters.
11067 *
11068 * <p><b>Note:</b> This method cannot handle <a
11069 * href="#supplementary"> supplementary characters</a>. To support
11070 * all Unicode characters, including supplementary characters, use
11071 * the {@link #toTitleCase(int)} method.
11072 *
11073 * @param ch the character to be converted.
11074 * @return the titlecase equivalent of the character, if any;
11075 * otherwise, the character itself.
11076 * @see Character#isTitleCase(char)
11077 * @see Character#toLowerCase(char)
11078 * @see Character#toUpperCase(char)
11079 * @since 1.0.2
11080 */
11081 public static char toTitleCase(char ch) {
11082 return (char)toTitleCase((int)ch);
11083 }
11084
11085 /**
11086 * Converts the character (Unicode code point) argument to titlecase using case mapping
11087 * information from the UnicodeData file. If a character has no
11088 * explicit titlecase mapping and is not itself a titlecase char
11089 * according to UnicodeData, then the uppercase mapping is
11090 * returned as an equivalent titlecase mapping. If the
11091 * character argument is already a titlecase
11092 * character, the same character value will be
11093 * returned.
11094 *
11095 * <p>Note that
11096 * {@code Character.isTitleCase(Character.toTitleCase(codePoint))}
11097 * does not always return {@code true} for some ranges of
11098 * characters.
11099 *
11100 * @param codePoint the character (Unicode code point) to be converted.
11101 * @return the titlecase equivalent of the character, if any;
11102 * otherwise, the character itself.
11103 * @see Character#isTitleCase(int)
11104 * @see Character#toLowerCase(int)
11105 * @see Character#toUpperCase(int)
11106 * @since 1.5
11107 */
11108 public static int toTitleCase(int codePoint) {
11109 return CharacterData.of(codePoint).toTitleCase(codePoint);
11110 }
11111
11112 /**
11113 * Returns the numeric value of the character {@code ch} in the
11114 * specified radix.
11115 * <p>
11116 * If the radix is not in the range {@code MIN_RADIX} ≤
11117 * {@code radix} ≤ {@code MAX_RADIX} or if the
11118 * value of {@code ch} is not a valid digit in the specified
11119 * radix, {@code -1} is returned. A character is a valid digit
11120 * if at least one of the following is true:
11121 * <ul>
11122 * <li>The method {@code isDigit} is {@code true} of the character
11123 * and the Unicode decimal digit value of the character (or its
11124 * single-character decomposition) is less than the specified radix.
11125 * In this case the decimal digit value is returned.
11126 * <li>The character is one of the uppercase Latin letters
11127 * {@code 'A'} through {@code 'Z'} and its code is less than
11128 * {@code radix + 'A' - 10}.
11129 * In this case, {@code ch - 'A' + 10}
11130 * is returned.
11131 * <li>The character is one of the lowercase Latin letters
11132 * {@code 'a'} through {@code 'z'} and its code is less than
11133 * {@code radix + 'a' - 10}.
11134 * In this case, {@code ch - 'a' + 10}
11135 * is returned.
11136 * <li>The character is one of the fullwidth uppercase Latin letters A
11137 * ({@code '\u005CuFF21'}) through Z ({@code '\u005CuFF3A'})
11138 * and its code is less than
11139 * {@code radix + '\u005CuFF21' - 10}.
11140 * In this case, {@code ch - '\u005CuFF21' + 10}
11141 * is returned.
11142 * <li>The character is one of the fullwidth lowercase Latin letters a
11143 * ({@code '\u005CuFF41'}) through z ({@code '\u005CuFF5A'})
11144 * and its code is less than
11145 * {@code radix + '\u005CuFF41' - 10}.
11146 * In this case, {@code ch - '\u005CuFF41' + 10}
11147 * is returned.
11148 * </ul>
11149 *
11150 * <p><b>Note:</b> This method cannot handle <a
11151 * href="#supplementary"> supplementary characters</a>. To support
11152 * all Unicode characters, including supplementary characters, use
11153 * the {@link #digit(int, int)} method.
11154 *
11155 * @param ch the character to be converted.
11156 * @param radix the radix.
11157 * @return the numeric value represented by the character in the
11158 * specified radix.
11159 * @see Character#forDigit(int, int)
11160 * @see Character#isDigit(char)
11161 */
11162 public static int digit(char ch, int radix) {
11163 return digit((int)ch, radix);
11164 }
11165
11166 /**
11167 * Returns the numeric value of the specified character (Unicode
11168 * code point) in the specified radix.
11169 *
11170 * <p>If the radix is not in the range {@code MIN_RADIX} ≤
11171 * {@code radix} ≤ {@code MAX_RADIX} or if the
11172 * character is not a valid digit in the specified
11173 * radix, {@code -1} is returned. A character is a valid digit
11174 * if at least one of the following is true:
11175 * <ul>
11176 * <li>The method {@link #isDigit(int) isDigit(codePoint)} is {@code true} of the character
11177 * and the Unicode decimal digit value of the character (or its
11178 * single-character decomposition) is less than the specified radix.
11179 * In this case the decimal digit value is returned.
11180 * <li>The character is one of the uppercase Latin letters
11181 * {@code 'A'} through {@code 'Z'} and its code is less than
11182 * {@code radix + 'A' - 10}.
11183 * In this case, {@code codePoint - 'A' + 10}
11184 * is returned.
11185 * <li>The character is one of the lowercase Latin letters
11186 * {@code 'a'} through {@code 'z'} and its code is less than
11187 * {@code radix + 'a' - 10}.
11188 * In this case, {@code codePoint - 'a' + 10}
11189 * is returned.
11190 * <li>The character is one of the fullwidth uppercase Latin letters A
11191 * ({@code '\u005CuFF21'}) through Z ({@code '\u005CuFF3A'})
11192 * and its code is less than
11193 * {@code radix + '\u005CuFF21' - 10}.
11194 * In this case,
11195 * {@code codePoint - '\u005CuFF21' + 10}
11196 * is returned.
11197 * <li>The character is one of the fullwidth lowercase Latin letters a
11198 * ({@code '\u005CuFF41'}) through z ({@code '\u005CuFF5A'})
11199 * and its code is less than
11200 * {@code radix + '\u005CuFF41'- 10}.
11201 * In this case,
11202 * {@code codePoint - '\u005CuFF41' + 10}
11203 * is returned.
11204 * </ul>
11205 *
11206 * @param codePoint the character (Unicode code point) to be converted.
11207 * @param radix the radix.
11208 * @return the numeric value represented by the character in the
11209 * specified radix.
11210 * @see Character#forDigit(int, int)
11211 * @see Character#isDigit(int)
11212 * @since 1.5
11213 */
11214 public static int digit(int codePoint, int radix) {
11215 return CharacterData.of(codePoint).digit(codePoint, radix);
11216 }
11217
11218 /**
11219 * Returns the {@code int} value that the specified Unicode
11220 * character represents. For example, the character
11221 * {@code '\u005Cu216C'} (the roman numeral fifty) will return
11222 * an int with a value of 50.
11223 * <p>
11224 * The letters A-Z in their uppercase ({@code '\u005Cu0041'} through
11225 * {@code '\u005Cu005A'}), lowercase
11226 * ({@code '\u005Cu0061'} through {@code '\u005Cu007A'}), and
11227 * full width variant ({@code '\u005CuFF21'} through
11228 * {@code '\u005CuFF3A'} and {@code '\u005CuFF41'} through
11229 * {@code '\u005CuFF5A'}) forms have numeric values from 10
11230 * through 35. This is independent of the Unicode specification,
11231 * which does not assign numeric values to these {@code char}
11232 * values.
11233 * <p>
11234 * If the character does not have a numeric value, then -1 is returned.
11235 * If the character has a numeric value that cannot be represented as a
11236 * nonnegative integer (for example, a fractional value), then -2
11237 * is returned.
11238 *
11239 * <p><b>Note:</b> This method cannot handle <a
11240 * href="#supplementary"> supplementary characters</a>. To support
11241 * all Unicode characters, including supplementary characters, use
11242 * the {@link #getNumericValue(int)} method.
11243 *
11244 * @param ch the character to be converted.
11245 * @return the numeric value of the character, as a nonnegative {@code int}
11246 * value; -2 if the character has a numeric value but the value
11247 * can not be represented as a nonnegative {@code int} value;
11248 * -1 if the character has no numeric value.
11249 * @see Character#forDigit(int, int)
11250 * @see Character#isDigit(char)
11251 * @since 1.1
11252 */
11253 public static int getNumericValue(char ch) {
11254 return getNumericValue((int)ch);
11255 }
11256
11257 /**
11258 * Returns the {@code int} value that the specified
11259 * character (Unicode code point) represents. For example, the character
11260 * {@code '\u005Cu216C'} (the Roman numeral fifty) will return
11261 * an {@code int} with a value of 50.
11262 * <p>
11263 * The letters A-Z in their uppercase ({@code '\u005Cu0041'} through
11264 * {@code '\u005Cu005A'}), lowercase
11265 * ({@code '\u005Cu0061'} through {@code '\u005Cu007A'}), and
11266 * full width variant ({@code '\u005CuFF21'} through
11267 * {@code '\u005CuFF3A'} and {@code '\u005CuFF41'} through
11268 * {@code '\u005CuFF5A'}) forms have numeric values from 10
11269 * through 35. This is independent of the Unicode specification,
11270 * which does not assign numeric values to these {@code char}
11271 * values.
11272 * <p>
11273 * If the character does not have a numeric value, then -1 is returned.
11274 * If the character has a numeric value that cannot be represented as a
11275 * nonnegative integer (for example, a fractional value), then -2
11276 * is returned.
11277 *
11278 * @param codePoint the character (Unicode code point) to be converted.
11279 * @return the numeric value of the character, as a nonnegative {@code int}
11280 * value; -2 if the character has a numeric value but the value
11281 * can not be represented as a nonnegative {@code int} value;
11282 * -1 if the character has no numeric value.
11283 * @see Character#forDigit(int, int)
11284 * @see Character#isDigit(int)
11285 * @since 1.5
11286 */
11287 public static int getNumericValue(int codePoint) {
11288 return CharacterData.of(codePoint).getNumericValue(codePoint);
11289 }
11290
11291 /**
11292 * Determines if the specified character is ISO-LATIN-1 white space.
11293 * This method returns {@code true} for the following five
11294 * characters only:
11295 * <table class="striped">
11296 * <caption style="display:none">truechars</caption>
11297 * <thead>
11298 * <tr><th scope="col">Character
11299 * <th scope="col">Code
11300 * <th scope="col">Name
11301 * </thead>
11302 * <tbody>
11303 * <tr><th scope="row">{@code '\t'}</th> <td>{@code U+0009}</td>
11304 * <td>{@code HORIZONTAL TABULATION}</td></tr>
11305 * <tr><th scope="row">{@code '\n'}</th> <td>{@code U+000A}</td>
11306 * <td>{@code NEW LINE}</td></tr>
11307 * <tr><th scope="row">{@code '\f'}</th> <td>{@code U+000C}</td>
11308 * <td>{@code FORM FEED}</td></tr>
11309 * <tr><th scope="row">{@code '\r'}</th> <td>{@code U+000D}</td>
11310 * <td>{@code CARRIAGE RETURN}</td></tr>
11311 * <tr><th scope="row">{@code ' '}</th> <td>{@code U+0020}</td>
11312 * <td>{@code SPACE}</td></tr>
11313 * </tbody>
11314 * </table>
11315 *
11316 * @param ch the character to be tested.
11317 * @return {@code true} if the character is ISO-LATIN-1 white
11318 * space; {@code false} otherwise.
11319 * @see Character#isSpaceChar(char)
11320 * @see Character#isWhitespace(char)
11321 * @deprecated Replaced by isWhitespace(char).
11322 */
11323 @Deprecated(since="1.1")
11324 public static boolean isSpace(char ch) {
11325 return (ch <= 0x0020) &&
11326 (((((1L << 0x0009) |
11327 (1L << 0x000A) |
11328 (1L << 0x000C) |
11329 (1L << 0x000D) |
11330 (1L << 0x0020)) >> ch) & 1L) != 0);
11331 }
11332
11333
11334 /**
11335 * Determines if the specified character is a Unicode space character.
11336 * A character is considered to be a space character if and only if
11337 * it is specified to be a space character by the Unicode Standard. This
11338 * method returns true if the character's general category type is any of
11339 * the following:
11340 * <ul>
11341 * <li> {@code SPACE_SEPARATOR}
11342 * <li> {@code LINE_SEPARATOR}
11343 * <li> {@code PARAGRAPH_SEPARATOR}
11344 * </ul>
11345 *
11346 * <p><b>Note:</b> This method cannot handle <a
11347 * href="#supplementary"> supplementary characters</a>. To support
11348 * all Unicode characters, including supplementary characters, use
11349 * the {@link #isSpaceChar(int)} method.
11350 *
11351 * @param ch the character to be tested.
11352 * @return {@code true} if the character is a space character;
11353 * {@code false} otherwise.
11354 * @see Character#isWhitespace(char)
11355 * @since 1.1
11356 */
11357 public static boolean isSpaceChar(char ch) {
11358 return isSpaceChar((int)ch);
11359 }
11360
11361 /**
11362 * Determines if the specified character (Unicode code point) is a
11363 * Unicode space character. A character is considered to be a
11364 * space character if and only if it is specified to be a space
11365 * character by the Unicode Standard. This method returns true if
11366 * the character's general category type is any of the following:
11367 *
11368 * <ul>
11369 * <li> {@link #SPACE_SEPARATOR}
11370 * <li> {@link #LINE_SEPARATOR}
11371 * <li> {@link #PARAGRAPH_SEPARATOR}
11372 * </ul>
11373 *
11374 * @param codePoint the character (Unicode code point) to be tested.
11375 * @return {@code true} if the character is a space character;
11376 * {@code false} otherwise.
11377 * @see Character#isWhitespace(int)
11378 * @since 1.5
11379 */
11380 public static boolean isSpaceChar(int codePoint) {
11381 return ((((1 << Character.SPACE_SEPARATOR) |
11382 (1 << Character.LINE_SEPARATOR) |
11383 (1 << Character.PARAGRAPH_SEPARATOR)) >> getType(codePoint)) & 1)
11384 != 0;
11385 }
11386
11387 /**
11388 * Determines if the specified character is white space according to Java.
11389 * A character is a Java whitespace character if and only if it satisfies
11390 * one of the following criteria:
11391 * <ul>
11392 * <li> It is a Unicode space character ({@code SPACE_SEPARATOR},
11393 * {@code LINE_SEPARATOR}, or {@code PARAGRAPH_SEPARATOR})
11394 * but is not also a non-breaking space ({@code '\u005Cu00A0'},
11395 * {@code '\u005Cu2007'}, {@code '\u005Cu202F'}).
11396 * <li> It is {@code '\u005Ct'}, U+0009 HORIZONTAL TABULATION.
11397 * <li> It is {@code '\u005Cn'}, U+000A LINE FEED.
11398 * <li> It is {@code '\u005Cu000B'}, U+000B VERTICAL TABULATION.
11399 * <li> It is {@code '\u005Cf'}, U+000C FORM FEED.
11400 * <li> It is {@code '\u005Cr'}, U+000D CARRIAGE RETURN.
11401 * <li> It is {@code '\u005Cu001C'}, U+001C FILE SEPARATOR.
11402 * <li> It is {@code '\u005Cu001D'}, U+001D GROUP SEPARATOR.
11403 * <li> It is {@code '\u005Cu001E'}, U+001E RECORD SEPARATOR.
11404 * <li> It is {@code '\u005Cu001F'}, U+001F UNIT SEPARATOR.
11405 * </ul>
11406 *
11407 * <p><b>Note:</b> This method cannot handle <a
11408 * href="#supplementary"> supplementary characters</a>. To support
11409 * all Unicode characters, including supplementary characters, use
11410 * the {@link #isWhitespace(int)} method.
11411 *
11412 * @param ch the character to be tested.
11413 * @return {@code true} if the character is a Java whitespace
11414 * character; {@code false} otherwise.
11415 * @see Character#isSpaceChar(char)
11416 * @since 1.1
11417 */
11418 public static boolean isWhitespace(char ch) {
11419 return isWhitespace((int)ch);
11420 }
11421
11422 /**
11423 * Determines if the specified character (Unicode code point) is
11424 * white space according to Java. A character is a Java
11425 * whitespace character if and only if it satisfies one of the
11426 * following criteria:
11427 * <ul>
11428 * <li> It is a Unicode space character ({@link #SPACE_SEPARATOR},
11429 * {@link #LINE_SEPARATOR}, or {@link #PARAGRAPH_SEPARATOR})
11430 * but is not also a non-breaking space ({@code '\u005Cu00A0'},
11431 * {@code '\u005Cu2007'}, {@code '\u005Cu202F'}).
11432 * <li> It is {@code '\u005Ct'}, U+0009 HORIZONTAL TABULATION.
11433 * <li> It is {@code '\u005Cn'}, U+000A LINE FEED.
11434 * <li> It is {@code '\u005Cu000B'}, U+000B VERTICAL TABULATION.
11435 * <li> It is {@code '\u005Cf'}, U+000C FORM FEED.
11436 * <li> It is {@code '\u005Cr'}, U+000D CARRIAGE RETURN.
11437 * <li> It is {@code '\u005Cu001C'}, U+001C FILE SEPARATOR.
11438 * <li> It is {@code '\u005Cu001D'}, U+001D GROUP SEPARATOR.
11439 * <li> It is {@code '\u005Cu001E'}, U+001E RECORD SEPARATOR.
11440 * <li> It is {@code '\u005Cu001F'}, U+001F UNIT SEPARATOR.
11441 * </ul>
11442 *
11443 * @param codePoint the character (Unicode code point) to be tested.
11444 * @return {@code true} if the character is a Java whitespace
11445 * character; {@code false} otherwise.
11446 * @see Character#isSpaceChar(int)
11447 * @since 1.5
11448 */
11449 public static boolean isWhitespace(int codePoint) {
11450 return CharacterData.of(codePoint).isWhitespace(codePoint);
11451 }
11452
11453 /**
11454 * Determines if the specified character is an ISO control
11455 * character. A character is considered to be an ISO control
11456 * character if its code is in the range {@code '\u005Cu0000'}
11457 * through {@code '\u005Cu001F'} or in the range
11458 * {@code '\u005Cu007F'} through {@code '\u005Cu009F'}.
11459 *
11460 * <p><b>Note:</b> This method cannot handle <a
11461 * href="#supplementary"> supplementary characters</a>. To support
11462 * all Unicode characters, including supplementary characters, use
11463 * the {@link #isISOControl(int)} method.
11464 *
11465 * @param ch the character to be tested.
11466 * @return {@code true} if the character is an ISO control character;
11467 * {@code false} otherwise.
11468 *
11469 * @see Character#isSpaceChar(char)
11470 * @see Character#isWhitespace(char)
11471 * @since 1.1
11472 */
11473 public static boolean isISOControl(char ch) {
11474 return isISOControl((int)ch);
11475 }
11476
11477 /**
11478 * Determines if the referenced character (Unicode code point) is an ISO control
11479 * character. A character is considered to be an ISO control
11480 * character if its code is in the range {@code '\u005Cu0000'}
11481 * through {@code '\u005Cu001F'} or in the range
11482 * {@code '\u005Cu007F'} through {@code '\u005Cu009F'}.
11483 *
11484 * @param codePoint the character (Unicode code point) to be tested.
11485 * @return {@code true} if the character is an ISO control character;
11486 * {@code false} otherwise.
11487 * @see Character#isSpaceChar(int)
11488 * @see Character#isWhitespace(int)
11489 * @since 1.5
11490 */
11491 public static boolean isISOControl(int codePoint) {
11492 // Optimized form of:
11493 // (codePoint >= 0x00 && codePoint <= 0x1F) ||
11494 // (codePoint >= 0x7F && codePoint <= 0x9F);
11495 return codePoint <= 0x9F &&
11496 (codePoint >= 0x7F || (codePoint >>> 5 == 0));
11497 }
11498
11499 /**
11500 * Returns a value indicating a character's general category.
11501 *
11502 * <p><b>Note:</b> This method cannot handle <a
11503 * href="#supplementary"> supplementary characters</a>. To support
11504 * all Unicode characters, including supplementary characters, use
11505 * the {@link #getType(int)} method.
11506 *
11507 * @param ch the character to be tested.
11508 * @return a value of type {@code int} representing the
11509 * character's general category.
11510 * @see Character#COMBINING_SPACING_MARK
11511 * @see Character#CONNECTOR_PUNCTUATION
11512 * @see Character#CONTROL
11513 * @see Character#CURRENCY_SYMBOL
11514 * @see Character#DASH_PUNCTUATION
11515 * @see Character#DECIMAL_DIGIT_NUMBER
11516 * @see Character#ENCLOSING_MARK
11517 * @see Character#END_PUNCTUATION
11518 * @see Character#FINAL_QUOTE_PUNCTUATION
11519 * @see Character#FORMAT
11520 * @see Character#INITIAL_QUOTE_PUNCTUATION
11521 * @see Character#LETTER_NUMBER
11522 * @see Character#LINE_SEPARATOR
11523 * @see Character#LOWERCASE_LETTER
11524 * @see Character#MATH_SYMBOL
11525 * @see Character#MODIFIER_LETTER
11526 * @see Character#MODIFIER_SYMBOL
11527 * @see Character#NON_SPACING_MARK
11528 * @see Character#OTHER_LETTER
11529 * @see Character#OTHER_NUMBER
11530 * @see Character#OTHER_PUNCTUATION
11531 * @see Character#OTHER_SYMBOL
11532 * @see Character#PARAGRAPH_SEPARATOR
11533 * @see Character#PRIVATE_USE
11534 * @see Character#SPACE_SEPARATOR
11535 * @see Character#START_PUNCTUATION
11536 * @see Character#SURROGATE
11537 * @see Character#TITLECASE_LETTER
11538 * @see Character#UNASSIGNED
11539 * @see Character#UPPERCASE_LETTER
11540 * @since 1.1
11541 */
11542 public static int getType(char ch) {
11543 return getType((int)ch);
11544 }
11545
11546 /**
11547 * Returns a value indicating a character's general category.
11548 *
11549 * @param codePoint the character (Unicode code point) to be tested.
11550 * @return a value of type {@code int} representing the
11551 * character's general category.
11552 * @see Character#COMBINING_SPACING_MARK COMBINING_SPACING_MARK
11553 * @see Character#CONNECTOR_PUNCTUATION CONNECTOR_PUNCTUATION
11554 * @see Character#CONTROL CONTROL
11555 * @see Character#CURRENCY_SYMBOL CURRENCY_SYMBOL
11556 * @see Character#DASH_PUNCTUATION DASH_PUNCTUATION
11557 * @see Character#DECIMAL_DIGIT_NUMBER DECIMAL_DIGIT_NUMBER
11558 * @see Character#ENCLOSING_MARK ENCLOSING_MARK
11559 * @see Character#END_PUNCTUATION END_PUNCTUATION
11560 * @see Character#FINAL_QUOTE_PUNCTUATION FINAL_QUOTE_PUNCTUATION
11561 * @see Character#FORMAT FORMAT
11562 * @see Character#INITIAL_QUOTE_PUNCTUATION INITIAL_QUOTE_PUNCTUATION
11563 * @see Character#LETTER_NUMBER LETTER_NUMBER
11564 * @see Character#LINE_SEPARATOR LINE_SEPARATOR
11565 * @see Character#LOWERCASE_LETTER LOWERCASE_LETTER
11566 * @see Character#MATH_SYMBOL MATH_SYMBOL
11567 * @see Character#MODIFIER_LETTER MODIFIER_LETTER
11568 * @see Character#MODIFIER_SYMBOL MODIFIER_SYMBOL
11569 * @see Character#NON_SPACING_MARK NON_SPACING_MARK
11570 * @see Character#OTHER_LETTER OTHER_LETTER
11571 * @see Character#OTHER_NUMBER OTHER_NUMBER
11572 * @see Character#OTHER_PUNCTUATION OTHER_PUNCTUATION
11573 * @see Character#OTHER_SYMBOL OTHER_SYMBOL
11574 * @see Character#PARAGRAPH_SEPARATOR PARAGRAPH_SEPARATOR
11575 * @see Character#PRIVATE_USE PRIVATE_USE
11576 * @see Character#SPACE_SEPARATOR SPACE_SEPARATOR
11577 * @see Character#START_PUNCTUATION START_PUNCTUATION
11578 * @see Character#SURROGATE SURROGATE
11579 * @see Character#TITLECASE_LETTER TITLECASE_LETTER
11580 * @see Character#UNASSIGNED UNASSIGNED
11581 * @see Character#UPPERCASE_LETTER UPPERCASE_LETTER
11582 * @since 1.5
11583 */
11584 public static int getType(int codePoint) {
11585 return CharacterData.of(codePoint).getType(codePoint);
11586 }
11587
11588 /**
11589 * Determines the character representation for a specific digit in
11590 * the specified radix. If the value of {@code radix} is not a
11591 * valid radix, or the value of {@code digit} is not a valid
11592 * digit in the specified radix, the null character
11593 * ({@code '\u005Cu0000'}) is returned.
11594 * <p>
11595 * The {@code radix} argument is valid if it is greater than or
11596 * equal to {@code MIN_RADIX} and less than or equal to
11597 * {@code MAX_RADIX}. The {@code digit} argument is valid if
11598 * {@code 0 <= digit < radix}.
11599 * <p>
11600 * If the digit is less than 10, then
11601 * {@code '0' + digit} is returned. Otherwise, the value
11602 * {@code 'a' + digit - 10} is returned.
11603 *
11604 * @param digit the number to convert to a character.
11605 * @param radix the radix.
11606 * @return the {@code char} representation of the specified digit
11607 * in the specified radix.
11608 * @see Character#MIN_RADIX
11609 * @see Character#MAX_RADIX
11610 * @see Character#digit(char, int)
11611 */
11612 public static char forDigit(int digit, int radix) {
11613 if ((digit >= radix) || (digit < 0)) {
11614 return '\0';
11615 }
11616 if ((radix < Character.MIN_RADIX) || (radix > Character.MAX_RADIX)) {
11617 return '\0';
11618 }
11619 if (digit < 10) {
11620 return (char)('0' + digit);
11621 }
11622 return (char)('a' - 10 + digit);
11623 }
11624
11625 /**
11626 * Returns the Unicode directionality property for the given
11627 * character. Character directionality is used to calculate the
11628 * visual ordering of text. The directionality value of undefined
11629 * {@code char} values is {@code DIRECTIONALITY_UNDEFINED}.
11630 *
11631 * <p><b>Note:</b> This method cannot handle <a
11632 * href="#supplementary"> supplementary characters</a>. To support
11633 * all Unicode characters, including supplementary characters, use
11634 * the {@link #getDirectionality(int)} method.
11635 *
11636 * @param ch {@code char} for which the directionality property
11637 * is requested.
11638 * @return the directionality property of the {@code char} value.
11639 *
11640 * @see Character#DIRECTIONALITY_UNDEFINED
11641 * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT
11642 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT
11643 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_ARABIC
11644 * @see Character#DIRECTIONALITY_EUROPEAN_NUMBER
11645 * @see Character#DIRECTIONALITY_EUROPEAN_NUMBER_SEPARATOR
11646 * @see Character#DIRECTIONALITY_EUROPEAN_NUMBER_TERMINATOR
11647 * @see Character#DIRECTIONALITY_ARABIC_NUMBER
11648 * @see Character#DIRECTIONALITY_COMMON_NUMBER_SEPARATOR
11649 * @see Character#DIRECTIONALITY_NONSPACING_MARK
11650 * @see Character#DIRECTIONALITY_BOUNDARY_NEUTRAL
11651 * @see Character#DIRECTIONALITY_PARAGRAPH_SEPARATOR
11652 * @see Character#DIRECTIONALITY_SEGMENT_SEPARATOR
11653 * @see Character#DIRECTIONALITY_WHITESPACE
11654 * @see Character#DIRECTIONALITY_OTHER_NEUTRALS
11655 * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT_EMBEDDING
11656 * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT_OVERRIDE
11657 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_EMBEDDING
11658 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_OVERRIDE
11659 * @see Character#DIRECTIONALITY_POP_DIRECTIONAL_FORMAT
11660 * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT_ISOLATE
11661 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_ISOLATE
11662 * @see Character#DIRECTIONALITY_FIRST_STRONG_ISOLATE
11663 * @see Character#DIRECTIONALITY_POP_DIRECTIONAL_ISOLATE
11664 * @since 1.4
11665 */
11666 public static byte getDirectionality(char ch) {
11667 return getDirectionality((int)ch);
11668 }
11669
11670 /**
11671 * Returns the Unicode directionality property for the given
11672 * character (Unicode code point). Character directionality is
11673 * used to calculate the visual ordering of text. The
11674 * directionality value of undefined character is {@link
11675 * #DIRECTIONALITY_UNDEFINED}.
11676 *
11677 * @param codePoint the character (Unicode code point) for which
11678 * the directionality property is requested.
11679 * @return the directionality property of the character.
11680 *
11681 * @see Character#DIRECTIONALITY_UNDEFINED DIRECTIONALITY_UNDEFINED
11682 * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT DIRECTIONALITY_LEFT_TO_RIGHT
11683 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT DIRECTIONALITY_RIGHT_TO_LEFT
11684 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_ARABIC DIRECTIONALITY_RIGHT_TO_LEFT_ARABIC
11685 * @see Character#DIRECTIONALITY_EUROPEAN_NUMBER DIRECTIONALITY_EUROPEAN_NUMBER
11686 * @see Character#DIRECTIONALITY_EUROPEAN_NUMBER_SEPARATOR DIRECTIONALITY_EUROPEAN_NUMBER_SEPARATOR
11687 * @see Character#DIRECTIONALITY_EUROPEAN_NUMBER_TERMINATOR DIRECTIONALITY_EUROPEAN_NUMBER_TERMINATOR
11688 * @see Character#DIRECTIONALITY_ARABIC_NUMBER DIRECTIONALITY_ARABIC_NUMBER
11689 * @see Character#DIRECTIONALITY_COMMON_NUMBER_SEPARATOR DIRECTIONALITY_COMMON_NUMBER_SEPARATOR
11690 * @see Character#DIRECTIONALITY_NONSPACING_MARK DIRECTIONALITY_NONSPACING_MARK
11691 * @see Character#DIRECTIONALITY_BOUNDARY_NEUTRAL DIRECTIONALITY_BOUNDARY_NEUTRAL
11692 * @see Character#DIRECTIONALITY_PARAGRAPH_SEPARATOR DIRECTIONALITY_PARAGRAPH_SEPARATOR
11693 * @see Character#DIRECTIONALITY_SEGMENT_SEPARATOR DIRECTIONALITY_SEGMENT_SEPARATOR
11694 * @see Character#DIRECTIONALITY_WHITESPACE DIRECTIONALITY_WHITESPACE
11695 * @see Character#DIRECTIONALITY_OTHER_NEUTRALS DIRECTIONALITY_OTHER_NEUTRALS
11696 * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT_EMBEDDING DIRECTIONALITY_LEFT_TO_RIGHT_EMBEDDING
11697 * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT_OVERRIDE DIRECTIONALITY_LEFT_TO_RIGHT_OVERRIDE
11698 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_EMBEDDING DIRECTIONALITY_RIGHT_TO_LEFT_EMBEDDING
11699 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_OVERRIDE DIRECTIONALITY_RIGHT_TO_LEFT_OVERRIDE
11700 * @see Character#DIRECTIONALITY_POP_DIRECTIONAL_FORMAT DIRECTIONALITY_POP_DIRECTIONAL_FORMAT
11701 * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT_ISOLATE DIRECTIONALITY_LEFT_TO_RIGHT_ISOLATE
11702 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_ISOLATE DIRECTIONALITY_RIGHT_TO_LEFT_ISOLATE
11703 * @see Character#DIRECTIONALITY_FIRST_STRONG_ISOLATE DIRECTIONALITY_FIRST_STRONG_ISOLATE
11704 * @see Character#DIRECTIONALITY_POP_DIRECTIONAL_ISOLATE DIRECTIONALITY_POP_DIRECTIONAL_ISOLATE
11705 * @since 1.5
11706 */
11707 public static byte getDirectionality(int codePoint) {
11708 return CharacterData.of(codePoint).getDirectionality(codePoint);
11709 }
11710
11711 /**
11712 * Determines whether the character is mirrored according to the
11713 * Unicode specification. Mirrored characters should have their
11714 * glyphs horizontally mirrored when displayed in text that is
11715 * right-to-left. For example, {@code '\u005Cu0028'} LEFT
11716 * PARENTHESIS is semantically defined to be an <i>opening
11717 * parenthesis</i>. This will appear as a "(" in text that is
11718 * left-to-right but as a ")" in text that is right-to-left.
11719 *
11720 * <p><b>Note:</b> This method cannot handle <a
11721 * href="#supplementary"> supplementary characters</a>. To support
11722 * all Unicode characters, including supplementary characters, use
11723 * the {@link #isMirrored(int)} method.
11724 *
11725 * @param ch {@code char} for which the mirrored property is requested
11726 * @return {@code true} if the char is mirrored, {@code false}
11727 * if the {@code char} is not mirrored or is not defined.
11728 * @since 1.4
11729 */
11730 public static boolean isMirrored(char ch) {
11731 return isMirrored((int)ch);
11732 }
11733
11734 /**
11735 * Determines whether the specified character (Unicode code point)
11736 * is mirrored according to the Unicode specification. Mirrored
11737 * characters should have their glyphs horizontally mirrored when
11738 * displayed in text that is right-to-left. For example,
11739 * {@code '\u005Cu0028'} LEFT PARENTHESIS is semantically
11740 * defined to be an <i>opening parenthesis</i>. This will appear
11741 * as a "(" in text that is left-to-right but as a ")" in text
11742 * that is right-to-left.
11743 *
11744 * @param codePoint the character (Unicode code point) to be tested.
11745 * @return {@code true} if the character is mirrored, {@code false}
11746 * if the character is not mirrored or is not defined.
11747 * @since 1.5
11748 */
11749 public static boolean isMirrored(int codePoint) {
11750 return CharacterData.of(codePoint).isMirrored(codePoint);
11751 }
11752
11753 /**
11754 * Compares two {@code Character} objects numerically.
11755 *
11756 * @param anotherCharacter the {@code Character} to be compared.
11757 * @return the value {@code 0} if the argument {@code Character}
11758 * is equal to this {@code Character}; a value less than
11759 * {@code 0} if this {@code Character} is numerically less
11760 * than the {@code Character} argument; and a value greater than
11761 * {@code 0} if this {@code Character} is numerically greater
11762 * than the {@code Character} argument (unsigned comparison).
11763 * Note that this is strictly a numerical comparison; it is not
11764 * locale-dependent.
11765 * @since 1.2
11766 */
11767 public int compareTo(Character anotherCharacter) {
11768 return compare(this.value, anotherCharacter.value);
11769 }
11770
11771 /**
11772 * Compares two {@code char} values numerically.
11773 * The value returned is identical to what would be returned by:
11774 * <pre>
11775 * Character.valueOf(x).compareTo(Character.valueOf(y))
11776 * </pre>
11777 *
11778 * @param x the first {@code char} to compare
11779 * @param y the second {@code char} to compare
11780 * @return the value {@code 0} if {@code x == y};
11781 * a value less than {@code 0} if {@code x < y}; and
11782 * a value greater than {@code 0} if {@code x > y}
11783 * @since 1.7
11784 */
11785 public static int compare(char x, char y) {
11786 return x - y;
11787 }
11788
11789 /**
11790 * Converts the character (Unicode code point) argument to uppercase using
11791 * information from the UnicodeData file.
11792 *
11793 * @param codePoint the character (Unicode code point) to be converted.
11794 * @return either the uppercase equivalent of the character, if
11795 * any, or an error flag ({@code Character.ERROR})
11796 * that indicates that a 1:M {@code char} mapping exists.
11797 * @see Character#isLowerCase(char)
11798 * @see Character#isUpperCase(char)
11799 * @see Character#toLowerCase(char)
11800 * @see Character#toTitleCase(char)
11801 * @since 1.4
11802 */
11803 static int toUpperCaseEx(int codePoint) {
11804 assert isValidCodePoint(codePoint);
11805 return CharacterData.of(codePoint).toUpperCaseEx(codePoint);
11806 }
11807
11808 /**
11809 * Converts the character (Unicode code point) argument to uppercase using case
11810 * mapping information from the SpecialCasing file in the Unicode
11811 * specification. If a character has no explicit uppercase
11812 * mapping, then the {@code char} itself is returned in the
11813 * {@code char[]}.
11814 *
11815 * @param codePoint the character (Unicode code point) to be converted.
11816 * @return a {@code char[]} with the uppercased character.
11817 * @since 1.4
11818 */
11819 static char[] toUpperCaseCharArray(int codePoint) {
11820 // As of Unicode 6.0, 1:M uppercasings only happen in the BMP.
11821 assert isBmpCodePoint(codePoint);
11822 return CharacterData.of(codePoint).toUpperCaseCharArray(codePoint);
11823 }
11824
11825 /**
11826 * The number of bits used to represent a {@code char} value in unsigned
11827 * binary form, constant {@code 16}.
11828 *
11829 * @since 1.5
11830 */
11831 public static final int SIZE = 16;
11832
11833 /**
11834 * The number of bytes used to represent a {@code char} value in unsigned
11835 * binary form.
11836 *
11837 * @since 1.8
11838 */
11839 public static final int BYTES = SIZE / Byte.SIZE;
11840
11841 /**
11842 * Returns the value obtained by reversing the order of the bytes in the
11843 * specified {@code char} value.
11844 *
11845 * @param ch The {@code char} of which to reverse the byte order.
11846 * @return the value obtained by reversing (or, equivalently, swapping)
11847 * the bytes in the specified {@code char} value.
11848 * @since 1.5
11849 */
11850 @IntrinsicCandidate
11851 public static char reverseBytes(char ch) {
11852 return (char) (((ch & 0xFF00) >> 8) | (ch << 8));
11853 }
11854
11855 /**
11856 * Returns the name of the specified character
11857 * {@code codePoint}, or null if the code point is
11858 * {@link #UNASSIGNED unassigned}.
11859 * <p>
11860 * If the specified character is not assigned a name by
11861 * the <i>UnicodeData</i> file (part of the Unicode Character
11862 * Database maintained by the Unicode Consortium), the returned
11863 * name is the same as the result of the expression:
11864 *
11865 * <blockquote>{@code
11866 * Character.UnicodeBlock.of(codePoint).toString().replace('_', ' ')
11867 * + " "
11868 * + Integer.toHexString(codePoint).toUpperCase(Locale.ROOT);
11869 *
11870 * }</blockquote>
11871 *
11872 * For the {@code codePoint}s in the <i>UnicodeData</i> file, the name
11873 * returned by this method follows the naming scheme in the
11874 * "Unicode Name Property" section of the Unicode Standard. For other
11875 * code points, such as Hangul/Ideographs, The name generation rule above
11876 * differs from the one defined in the Unicode Standard.
11877 *
11878 * @param codePoint the character (Unicode code point)
11879 *
11880 * @return the name of the specified character, or null if
11881 * the code point is unassigned.
11882 *
11883 * @throws IllegalArgumentException if the specified
11884 * {@code codePoint} is not a valid Unicode
11885 * code point.
11886 *
11887 * @since 1.7
11888 */
11889 public static String getName(int codePoint) {
11890 if (!isValidCodePoint(codePoint)) {
11891 throw new IllegalArgumentException(
11892 String.format("Not a valid Unicode code point: 0x%X", codePoint));
11893 }
11894 String name = CharacterName.getInstance().getName(codePoint);
11895 if (name != null)
11896 return name;
11897 if (getType(codePoint) == UNASSIGNED)
11898 return null;
11899 UnicodeBlock block = UnicodeBlock.of(codePoint);
11900 if (block != null)
11901 return block.toString().replace('_', ' ') + " "
11902 + Integer.toHexString(codePoint).toUpperCase(Locale.ROOT);
11903 // should never come here
11904 return Integer.toHexString(codePoint).toUpperCase(Locale.ROOT);
11905 }
11906
11907 /**
11908 * Returns the code point value of the Unicode character specified by
11909 * the given character name.
11910 * <p>
11911 * If a character is not assigned a name by the <i>UnicodeData</i>
11912 * file (part of the Unicode Character Database maintained by the Unicode
11913 * Consortium), its name is defined as the result of the expression:
11914 *
11915 * <blockquote>{@code
11916 * Character.UnicodeBlock.of(codePoint).toString().replace('_', ' ')
11917 * + " "
11918 * + Integer.toHexString(codePoint).toUpperCase(Locale.ROOT);
11919 *
11920 * }</blockquote>
11921 * <p>
11922 * The {@code name} matching is case insensitive, with any leading and
11923 * trailing whitespace character removed.
11924 *
11925 * For the code points in the <i>UnicodeData</i> file, this method
11926 * recognizes the name which conforms to the name defined in the
11927 * "Unicode Name Property" section in the Unicode Standard. For other
11928 * code points, this method recognizes the name generated with
11929 * {@link #getName(int)} method.
11930 *
11931 * @param name the character name
11932 *
11933 * @return the code point value of the character specified by its name.
11934 *
11935 * @throws IllegalArgumentException if the specified {@code name}
11936 * is not a valid character name.
11937 * @throws NullPointerException if {@code name} is {@code null}
11938 *
11939 * @since 9
11940 */
11941 public static int codePointOf(String name) {
11942 name = name.trim().toUpperCase(Locale.ROOT);
11943 int cp = CharacterName.getInstance().getCodePoint(name);
11944 if (cp != -1)
11945 return cp;
11946 try {
11947 int off = name.lastIndexOf(' ');
11948 if (off != -1) {
11949 cp = Integer.parseInt(name, off + 1, name.length(), 16);
11950 if (isValidCodePoint(cp) && name.equals(getName(cp)))
11951 return cp;
11952 }
11953 } catch (Exception x) {}
11954 throw new IllegalArgumentException("Unrecognized character name :" + name);
11955 }
11956 }