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 16.0.
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 24</th>
80 * <td>Unicode 16.0</td></tr>
81 * <tr><th scope="row" style="text-align:left">Java SE 22</th>
82 * <td>Unicode 15.1</td></tr>
83 * <tr><th scope="row" style="text-align:left">Java SE 20</th>
84 * <td>Unicode 15.0</td></tr>
85 * <tr><th scope="row" style="text-align:left">Java SE 19</th>
86 * <td>Unicode 14.0</td></tr>
87 * <tr><th scope="row" style="text-align:left">Java SE 15</th>
88 * <td>Unicode 13.0</td></tr>
89 * <tr><th scope="row" style="text-align:left">Java SE 13</th>
90 * <td>Unicode 12.1</td></tr>
91 * <tr><th scope="row" style="text-align:left">Java SE 12</th>
92 * <td>Unicode 11.0</td></tr>
93 * <tr><th scope="row" style="text-align:left">Java SE 11</th>
94 * <td>Unicode 10.0</td></tr>
95 * <tr><th scope="row" style="text-align:left">Java SE 9</th>
96 * <td>Unicode 8.0</td></tr>
97 * <tr><th scope="row" style="text-align:left">Java SE 8</th>
98 * <td>Unicode 6.2</td></tr>
99 * <tr><th scope="row" style="text-align:left">Java SE 7</th>
100 * <td>Unicode 6.0</td></tr>
101 * <tr><th scope="row" style="text-align:left">Java SE 5.0</th>
102 * <td>Unicode 4.0</td></tr>
103 * <tr><th scope="row" style="text-align:left">Java SE 1.4</th>
104 * <td>Unicode 3.0</td></tr>
105 * <tr><th scope="row" style="text-align:left">JDK 1.1</th>
106 * <td>Unicode 2.0</td></tr>
107 * <tr><th scope="row" style="text-align:left">JDK 1.0.2</th>
108 * <td>Unicode 1.1.5</td></tr>
109 * </tbody>
110 * </table>
111 * Variations from these base Unicode versions, such as recognized appendixes,
112 * are documented elsewhere.
113 * <h2><a id="unicode">Unicode Character Representations</a></h2>
114 *
115 * <p>The {@code char} data type (and therefore the value that a
116 * {@code Character} object encapsulates) are based on the
117 * original Unicode specification, which defined characters as
118 * fixed-width 16-bit entities. The Unicode Standard has since been
119 * changed to allow for characters whose representation requires more
120 * than 16 bits. The range of legal <em>code point</em>s is now
121 * U+0000 to U+10FFFF, known as <em>Unicode scalar value</em>.
122 * (Refer to the <a
123 * href="http://www.unicode.org/reports/tr27/#notation"><i>
124 * definition</i></a> of the U+<i>n</i> notation in the Unicode
125 * Standard.)
126 *
127 * <p><a id="BMP">The set of characters from U+0000 to U+FFFF</a> is
128 * sometimes referred to as the <em>Basic Multilingual Plane (BMP)</em>.
129 * <a id="supplementary">Characters</a> whose code points are greater
130 * than U+FFFF are called <em>supplementary character</em>s. The Java
131 * platform uses the UTF-16 representation in {@code char} arrays and
132 * in the {@code String} and {@code StringBuffer} classes. In
133 * this representation, supplementary characters are represented as a pair
134 * of {@code char} values, the first from the <em>high-surrogates</em>
135 * range, (\uD800-\uDBFF), the second from the
136 * <em>low-surrogates</em> range (\uDC00-\uDFFF).
137 *
138 * <p>A {@code char} value, therefore, represents Basic
139 * Multilingual Plane (BMP) code points, including the surrogate
140 * code points, or code units of the UTF-16 encoding. An
141 * {@code int} value represents all Unicode code points,
142 * including supplementary code points. The lower (least significant)
143 * 21 bits of {@code int} are used to represent Unicode code
144 * points and the upper (most significant) 11 bits must be zero.
145 * Unless otherwise specified, the behavior with respect to
146 * supplementary characters and surrogate {@code char} values is
147 * as follows:
148 *
149 * <ul>
150 * <li>The methods that only accept a {@code char} value cannot support
151 * supplementary characters. They treat {@code char} values from the
152 * surrogate ranges as undefined characters. For example,
153 * {@code Character.isLetter('\u005CuD840')} returns {@code false}, even though
154 * this specific value if followed by any low-surrogate value in a string
155 * would represent a letter.
156 *
157 * <li>The methods that accept an {@code int} value support all
158 * Unicode characters, including supplementary characters. For
159 * example, {@code Character.isLetter(0x2F81A)} returns
160 * {@code true} because the code point value represents a letter
161 * (a CJK ideograph).
162 * </ul>
163 *
164 * <p>In the Java SE API documentation, <em>Unicode code point</em> is
165 * used for character values in the range between U+0000 and U+10FFFF,
166 * and <em>Unicode code unit</em> is used for 16-bit
167 * {@code char} values that are code units of the <em>UTF-16</em>
168 * encoding. For more information on Unicode terminology, refer to the
169 * <a href="http://www.unicode.org/glossary/">Unicode Glossary</a>.
170 *
171 * <p>This is a <a href="{@docRoot}/java.base/java/lang/doc-files/ValueBased.html">value-based</a>
172 * class; programmers should treat instances that are {@linkplain #equals(Object) equal}
173 * as interchangeable and should not use instances for synchronization, mutexes, or
174 * with {@linkplain java.lang.ref.Reference object references}.
175 *
176 * <div class="preview-block">
177 * <div class="preview-comment">
178 * When preview features are enabled, {@code Character} is a {@linkplain Class#isValue value class}.
179 * Use of value class instances for synchronization, mutexes, or with
180 * {@linkplain java.lang.ref.Reference object references} result in
181 * {@link IdentityException}.
182 * </div>
183 * </div>
184 *
185 * @spec https://www.unicode.org/reports/tr27 Unicode 3.1.0
186 * @author Lee Boynton
187 * @author Guy Steele
188 * @author Akira Tanaka
189 * @author Martin Buchholz
190 * @author Ulf Zibis
191 * @since 1.0
192 */
193 @jdk.internal.MigratedValueClass
194 @jdk.internal.ValueBased
195 public final class Character implements java.io.Serializable, Comparable<Character>, Constable {
196 /**
197 * The minimum radix available for conversion to and from strings.
198 * The constant value of this field is the smallest value permitted
199 * for the radix argument in radix-conversion methods such as the
200 * {@code digit} method, the {@code forDigit} method, and the
201 * {@code toString} method of class {@code Integer}.
202 *
203 * @see Character#digit(char, int)
204 * @see Character#forDigit(int, int)
205 * @see Integer#toString(int, int)
206 * @see Integer#valueOf(String)
207 */
208 public static final int MIN_RADIX = 2;
209
210 /**
211 * The maximum radix available for conversion to and from strings.
212 * The constant value of this field is the largest value permitted
213 * for the radix argument in radix-conversion methods such as the
214 * {@code digit} method, the {@code forDigit} method, and the
215 * {@code toString} method of class {@code Integer}.
216 *
217 * @see Character#digit(char, int)
218 * @see Character#forDigit(int, int)
219 * @see Integer#toString(int, int)
220 * @see Integer#valueOf(String)
221 */
222 public static final int MAX_RADIX = 36;
223
224 /**
225 * The constant value of this field is the smallest value of type
226 * {@code char}, {@code '\u005Cu0000'}.
227 *
228 * @since 1.0.2
229 */
230 public static final char MIN_VALUE = '\u0000';
231
232 /**
233 * The constant value of this field is the largest value of type
234 * {@code char}, {@code '\u005CuFFFF'}.
235 *
236 * @since 1.0.2
237 */
238 public static final char MAX_VALUE = '\uFFFF';
239
240 /**
241 * The {@code Class} instance representing the primitive type
242 * {@code char}.
243 *
244 * @since 1.1
245 */
246 public static final Class<Character> TYPE = Class.getPrimitiveClass("char");
247
248 /*
249 * Normative general types
250 */
251
252 /*
253 * General character types
254 */
255
256 /**
257 * General category "Cn" in the Unicode specification.
258 * @since 1.1
259 */
260 public static final byte UNASSIGNED = 0;
261
262 /**
263 * General category "Lu" in the Unicode specification.
264 * @since 1.1
265 */
266 public static final byte UPPERCASE_LETTER = 1;
267
268 /**
269 * General category "Ll" in the Unicode specification.
270 * @since 1.1
271 */
272 public static final byte LOWERCASE_LETTER = 2;
273
274 /**
275 * General category "Lt" in the Unicode specification.
276 * @since 1.1
277 */
278 public static final byte TITLECASE_LETTER = 3;
279
280 /**
281 * General category "Lm" in the Unicode specification.
282 * @since 1.1
283 */
284 public static final byte MODIFIER_LETTER = 4;
285
286 /**
287 * General category "Lo" in the Unicode specification.
288 * @since 1.1
289 */
290 public static final byte OTHER_LETTER = 5;
291
292 /**
293 * General category "Mn" in the Unicode specification.
294 * @since 1.1
295 */
296 public static final byte NON_SPACING_MARK = 6;
297
298 /**
299 * General category "Me" in the Unicode specification.
300 * @since 1.1
301 */
302 public static final byte ENCLOSING_MARK = 7;
303
304 /**
305 * General category "Mc" in the Unicode specification.
306 * @since 1.1
307 */
308 public static final byte COMBINING_SPACING_MARK = 8;
309
310 /**
311 * General category "Nd" in the Unicode specification.
312 * @since 1.1
313 */
314 public static final byte DECIMAL_DIGIT_NUMBER = 9;
315
316 /**
317 * General category "Nl" in the Unicode specification.
318 * @since 1.1
319 */
320 public static final byte LETTER_NUMBER = 10;
321
322 /**
323 * General category "No" in the Unicode specification.
324 * @since 1.1
325 */
326 public static final byte OTHER_NUMBER = 11;
327
328 /**
329 * General category "Zs" in the Unicode specification.
330 * @since 1.1
331 */
332 public static final byte SPACE_SEPARATOR = 12;
333
334 /**
335 * General category "Zl" in the Unicode specification.
336 * @since 1.1
337 */
338 public static final byte LINE_SEPARATOR = 13;
339
340 /**
341 * General category "Zp" in the Unicode specification.
342 * @since 1.1
343 */
344 public static final byte PARAGRAPH_SEPARATOR = 14;
345
346 /**
347 * General category "Cc" in the Unicode specification.
348 * @since 1.1
349 */
350 public static final byte CONTROL = 15;
351
352 /**
353 * General category "Cf" in the Unicode specification.
354 * @since 1.1
355 */
356 public static final byte FORMAT = 16;
357
358 /**
359 * General category "Co" in the Unicode specification.
360 * @since 1.1
361 */
362 public static final byte PRIVATE_USE = 18;
363
364 /**
365 * General category "Cs" in the Unicode specification.
366 * @since 1.1
367 */
368 public static final byte SURROGATE = 19;
369
370 /**
371 * General category "Pd" in the Unicode specification.
372 * @since 1.1
373 */
374 public static final byte DASH_PUNCTUATION = 20;
375
376 /**
377 * General category "Ps" in the Unicode specification.
378 * @since 1.1
379 */
380 public static final byte START_PUNCTUATION = 21;
381
382 /**
383 * General category "Pe" in the Unicode specification.
384 * @since 1.1
385 */
386 public static final byte END_PUNCTUATION = 22;
387
388 /**
389 * General category "Pc" in the Unicode specification.
390 * @since 1.1
391 */
392 public static final byte CONNECTOR_PUNCTUATION = 23;
393
394 /**
395 * General category "Po" in the Unicode specification.
396 * @since 1.1
397 */
398 public static final byte OTHER_PUNCTUATION = 24;
399
400 /**
401 * General category "Sm" in the Unicode specification.
402 * @since 1.1
403 */
404 public static final byte MATH_SYMBOL = 25;
405
406 /**
407 * General category "Sc" in the Unicode specification.
408 * @since 1.1
409 */
410 public static final byte CURRENCY_SYMBOL = 26;
411
412 /**
413 * General category "Sk" in the Unicode specification.
414 * @since 1.1
415 */
416 public static final byte MODIFIER_SYMBOL = 27;
417
418 /**
419 * General category "So" in the Unicode specification.
420 * @since 1.1
421 */
422 public static final byte OTHER_SYMBOL = 28;
423
424 /**
425 * General category "Pi" in the Unicode specification.
426 * @since 1.4
427 */
428 public static final byte INITIAL_QUOTE_PUNCTUATION = 29;
429
430 /**
431 * General category "Pf" in the Unicode specification.
432 * @since 1.4
433 */
434 public static final byte FINAL_QUOTE_PUNCTUATION = 30;
435
436 /**
437 * Error flag. Use int (code point) to avoid confusion with U+FFFF.
438 */
439 static final int ERROR = 0xFFFFFFFF;
440
441
442 /**
443 * Undefined bidirectional character type. Undefined {@code char}
444 * values have undefined directionality in the Unicode specification.
445 * @since 1.4
446 */
447 public static final byte DIRECTIONALITY_UNDEFINED = -1;
448
449 /**
450 * Strong bidirectional character type "L" in the Unicode specification.
451 * @since 1.4
452 */
453 public static final byte DIRECTIONALITY_LEFT_TO_RIGHT = 0;
454
455 /**
456 * Strong bidirectional character type "R" in the Unicode specification.
457 * @since 1.4
458 */
459 public static final byte DIRECTIONALITY_RIGHT_TO_LEFT = 1;
460
461 /**
462 * Strong bidirectional character type "AL" in the Unicode specification.
463 * @since 1.4
464 */
465 public static final byte DIRECTIONALITY_RIGHT_TO_LEFT_ARABIC = 2;
466
467 /**
468 * Weak bidirectional character type "EN" in the Unicode specification.
469 * @since 1.4
470 */
471 public static final byte DIRECTIONALITY_EUROPEAN_NUMBER = 3;
472
473 /**
474 * Weak bidirectional character type "ES" in the Unicode specification.
475 * @since 1.4
476 */
477 public static final byte DIRECTIONALITY_EUROPEAN_NUMBER_SEPARATOR = 4;
478
479 /**
480 * Weak bidirectional character type "ET" in the Unicode specification.
481 * @since 1.4
482 */
483 public static final byte DIRECTIONALITY_EUROPEAN_NUMBER_TERMINATOR = 5;
484
485 /**
486 * Weak bidirectional character type "AN" in the Unicode specification.
487 * @since 1.4
488 */
489 public static final byte DIRECTIONALITY_ARABIC_NUMBER = 6;
490
491 /**
492 * Weak bidirectional character type "CS" in the Unicode specification.
493 * @since 1.4
494 */
495 public static final byte DIRECTIONALITY_COMMON_NUMBER_SEPARATOR = 7;
496
497 /**
498 * Weak bidirectional character type "NSM" in the Unicode specification.
499 * @since 1.4
500 */
501 public static final byte DIRECTIONALITY_NONSPACING_MARK = 8;
502
503 /**
504 * Weak bidirectional character type "BN" in the Unicode specification.
505 * @since 1.4
506 */
507 public static final byte DIRECTIONALITY_BOUNDARY_NEUTRAL = 9;
508
509 /**
510 * Neutral bidirectional character type "B" in the Unicode specification.
511 * @since 1.4
512 */
513 public static final byte DIRECTIONALITY_PARAGRAPH_SEPARATOR = 10;
514
515 /**
516 * Neutral bidirectional character type "S" in the Unicode specification.
517 * @since 1.4
518 */
519 public static final byte DIRECTIONALITY_SEGMENT_SEPARATOR = 11;
520
521 /**
522 * Neutral bidirectional character type "WS" in the Unicode specification.
523 * @since 1.4
524 */
525 public static final byte DIRECTIONALITY_WHITESPACE = 12;
526
527 /**
528 * Neutral bidirectional character type "ON" in the Unicode specification.
529 * @since 1.4
530 */
531 public static final byte DIRECTIONALITY_OTHER_NEUTRALS = 13;
532
533 /**
534 * Strong bidirectional character type "LRE" in the Unicode specification.
535 * @since 1.4
536 */
537 public static final byte DIRECTIONALITY_LEFT_TO_RIGHT_EMBEDDING = 14;
538
539 /**
540 * Strong bidirectional character type "LRO" in the Unicode specification.
541 * @since 1.4
542 */
543 public static final byte DIRECTIONALITY_LEFT_TO_RIGHT_OVERRIDE = 15;
544
545 /**
546 * Strong bidirectional character type "RLE" in the Unicode specification.
547 * @since 1.4
548 */
549 public static final byte DIRECTIONALITY_RIGHT_TO_LEFT_EMBEDDING = 16;
550
551 /**
552 * Strong bidirectional character type "RLO" in the Unicode specification.
553 * @since 1.4
554 */
555 public static final byte DIRECTIONALITY_RIGHT_TO_LEFT_OVERRIDE = 17;
556
557 /**
558 * Weak bidirectional character type "PDF" in the Unicode specification.
559 * @since 1.4
560 */
561 public static final byte DIRECTIONALITY_POP_DIRECTIONAL_FORMAT = 18;
562
563 /**
564 * Weak bidirectional character type "LRI" in the Unicode specification.
565 * @since 9
566 */
567 public static final byte DIRECTIONALITY_LEFT_TO_RIGHT_ISOLATE = 19;
568
569 /**
570 * Weak bidirectional character type "RLI" in the Unicode specification.
571 * @since 9
572 */
573 public static final byte DIRECTIONALITY_RIGHT_TO_LEFT_ISOLATE = 20;
574
575 /**
576 * Weak bidirectional character type "FSI" in the Unicode specification.
577 * @since 9
578 */
579 public static final byte DIRECTIONALITY_FIRST_STRONG_ISOLATE = 21;
580
581 /**
582 * Weak bidirectional character type "PDI" in the Unicode specification.
583 * @since 9
584 */
585 public static final byte DIRECTIONALITY_POP_DIRECTIONAL_ISOLATE = 22;
586
587 /**
588 * The minimum value of a
589 * <a href="http://www.unicode.org/glossary/#high_surrogate_code_unit">
590 * Unicode high-surrogate code unit</a>
591 * in the UTF-16 encoding, constant {@code '\u005CuD800'}.
592 * A high-surrogate is also known as a <i>leading-surrogate</i>.
593 *
594 * @since 1.5
595 */
596 public static final char MIN_HIGH_SURROGATE = '\uD800';
597
598 /**
599 * The maximum value of a
600 * <a href="http://www.unicode.org/glossary/#high_surrogate_code_unit">
601 * Unicode high-surrogate code unit</a>
602 * in the UTF-16 encoding, constant {@code '\u005CuDBFF'}.
603 * A high-surrogate is also known as a <i>leading-surrogate</i>.
604 *
605 * @since 1.5
606 */
607 public static final char MAX_HIGH_SURROGATE = '\uDBFF';
608
609 /**
610 * The minimum value of a
611 * <a href="http://www.unicode.org/glossary/#low_surrogate_code_unit">
612 * Unicode low-surrogate code unit</a>
613 * in the UTF-16 encoding, constant {@code '\u005CuDC00'}.
614 * A low-surrogate is also known as a <i>trailing-surrogate</i>.
615 *
616 * @since 1.5
617 */
618 public static final char MIN_LOW_SURROGATE = '\uDC00';
619
620 /**
621 * The maximum value of a
622 * <a href="http://www.unicode.org/glossary/#low_surrogate_code_unit">
623 * Unicode low-surrogate code unit</a>
624 * in the UTF-16 encoding, constant {@code '\u005CuDFFF'}.
625 * A low-surrogate is also known as a <i>trailing-surrogate</i>.
626 *
627 * @since 1.5
628 */
629 public static final char MAX_LOW_SURROGATE = '\uDFFF';
630
631 /**
632 * The minimum value of a Unicode surrogate code unit in the
633 * UTF-16 encoding, constant {@code '\u005CuD800'}.
634 *
635 * @since 1.5
636 */
637 public static final char MIN_SURROGATE = MIN_HIGH_SURROGATE;
638
639 /**
640 * The maximum value of a Unicode surrogate code unit in the
641 * UTF-16 encoding, constant {@code '\u005CuDFFF'}.
642 *
643 * @since 1.5
644 */
645 public static final char MAX_SURROGATE = MAX_LOW_SURROGATE;
646
647 /**
648 * The minimum value of a
649 * <a href="http://www.unicode.org/glossary/#supplementary_code_point">
650 * Unicode supplementary code point</a>, constant {@code U+10000}.
651 *
652 * @since 1.5
653 */
654 public static final int MIN_SUPPLEMENTARY_CODE_POINT = 0x010000;
655
656 /**
657 * The minimum value of a
658 * <a href="http://www.unicode.org/glossary/#code_point">
659 * Unicode code point</a>, constant {@code U+0000}.
660 *
661 * @since 1.5
662 */
663 public static final int MIN_CODE_POINT = 0x000000;
664
665 /**
666 * The maximum value of a
667 * <a href="http://www.unicode.org/glossary/#code_point">
668 * Unicode code point</a>, constant {@code U+10FFFF}.
669 *
670 * @since 1.5
671 */
672 public static final int MAX_CODE_POINT = 0X10FFFF;
673
674 /**
675 * Returns an {@link Optional} containing the nominal descriptor for this
676 * instance.
677 *
678 * @return an {@link Optional} describing the {@linkplain Character} instance
679 * @since 15
680 */
681 @Override
682 public Optional<DynamicConstantDesc<Character>> describeConstable() {
683 return Optional.of(DynamicConstantDesc.ofNamed(BSM_EXPLICIT_CAST, DEFAULT_NAME, CD_char, (int) value));
684 }
685
686 /**
687 * Instances of this class represent particular subsets of the Unicode
688 * character set. The only family of subsets defined in the
689 * {@code Character} class is {@link Character.UnicodeBlock}.
690 * Other portions of the Java API may define other subsets for their
691 * own purposes.
692 *
693 * @since 1.2
694 */
695 public static class Subset {
696
697 private String name;
698
699 /**
700 * Constructs a new {@code Subset} instance.
701 *
702 * @param name The name of this subset
703 * @throws NullPointerException if name is {@code null}
704 */
705 protected Subset(String name) {
706 if (name == null) {
707 throw new NullPointerException("name");
708 }
709 this.name = name;
710 }
711
712 /**
713 * Compares two {@code Subset} objects for equality.
714 * This method returns {@code true} if and only if
715 * {@code this} and the argument refer to the same
716 * object; since this method is {@code final}, this
717 * guarantee holds for all subclasses.
718 */
719 public final boolean equals(Object obj) {
720 return (this == obj);
721 }
722
723 /**
724 * Returns the standard hash code as defined by the
725 * {@link Object#hashCode} method. This method
726 * is {@code final} in order to ensure that the
727 * {@code equals} and {@code hashCode} methods will
728 * be consistent in all subclasses.
729 */
730 public final int hashCode() {
731 return super.hashCode();
732 }
733
734 /**
735 * Returns the name of this subset.
736 */
737 public final String toString() {
738 return name;
739 }
740 }
741
742 // See http://www.unicode.org/Public/UNIDATA/Blocks.txt
743 // for the latest specification of Unicode Blocks.
744
745 /**
746 * A family of character subsets representing the character blocks in the
747 * Unicode specification. Character blocks generally define characters
748 * used for a specific script or purpose. A character is contained by
749 * at most one Unicode block.
750 *
751 * @since 1.2
752 */
753 public static final class UnicodeBlock extends Subset {
754 /**
755 * NUM_ENTITIES should match the total number of UnicodeBlocks.
756 * It should be adjusted whenever the Unicode Character Database
757 * is upgraded.
758 */
759 private static final int NUM_ENTITIES = 782;
760 private static Map<String, UnicodeBlock> map = HashMap.newHashMap(NUM_ENTITIES);
761
762 /**
763 * Creates a UnicodeBlock with the given identifier name.
764 * This name must be the same as the block identifier.
765 */
766 private UnicodeBlock(String idName) {
767 super(idName);
768 map.put(idName, this);
769 }
770
771 /**
772 * Creates a UnicodeBlock with the given identifier name and
773 * alias name.
774 */
775 private UnicodeBlock(String idName, String alias) {
776 this(idName);
777 map.put(alias, this);
778 }
779
780 /**
781 * Creates a UnicodeBlock with the given identifier name and
782 * alias names.
783 */
784 private UnicodeBlock(String idName, String... aliases) {
785 this(idName);
786 for (String alias : aliases)
787 map.put(alias, this);
788 }
789
790 /**
791 * Constant for the "Basic Latin" Unicode character block.
792 * @since 1.2
793 */
794 public static final UnicodeBlock BASIC_LATIN =
795 new UnicodeBlock("BASIC_LATIN",
796 "BASIC LATIN",
797 "BASICLATIN");
798
799 /**
800 * Constant for the "Latin-1 Supplement" Unicode character block.
801 * @since 1.2
802 */
803 public static final UnicodeBlock LATIN_1_SUPPLEMENT =
804 new UnicodeBlock("LATIN_1_SUPPLEMENT",
805 "LATIN-1 SUPPLEMENT",
806 "LATIN-1SUPPLEMENT");
807
808 /**
809 * Constant for the "Latin Extended-A" Unicode character block.
810 * @since 1.2
811 */
812 public static final UnicodeBlock LATIN_EXTENDED_A =
813 new UnicodeBlock("LATIN_EXTENDED_A",
814 "LATIN EXTENDED-A",
815 "LATINEXTENDED-A");
816
817 /**
818 * Constant for the "Latin Extended-B" Unicode character block.
819 * @since 1.2
820 */
821 public static final UnicodeBlock LATIN_EXTENDED_B =
822 new UnicodeBlock("LATIN_EXTENDED_B",
823 "LATIN EXTENDED-B",
824 "LATINEXTENDED-B");
825
826 /**
827 * Constant for the "IPA Extensions" Unicode character block.
828 * @since 1.2
829 */
830 public static final UnicodeBlock IPA_EXTENSIONS =
831 new UnicodeBlock("IPA_EXTENSIONS",
832 "IPA EXTENSIONS",
833 "IPAEXTENSIONS");
834
835 /**
836 * Constant for the "Spacing Modifier Letters" Unicode character block.
837 * @since 1.2
838 */
839 public static final UnicodeBlock SPACING_MODIFIER_LETTERS =
840 new UnicodeBlock("SPACING_MODIFIER_LETTERS",
841 "SPACING MODIFIER LETTERS",
842 "SPACINGMODIFIERLETTERS");
843
844 /**
845 * Constant for the "Combining Diacritical Marks" Unicode character block.
846 * @since 1.2
847 */
848 public static final UnicodeBlock COMBINING_DIACRITICAL_MARKS =
849 new UnicodeBlock("COMBINING_DIACRITICAL_MARKS",
850 "COMBINING DIACRITICAL MARKS",
851 "COMBININGDIACRITICALMARKS");
852
853 /**
854 * Constant for the "Greek and Coptic" Unicode character block.
855 * <p>
856 * This block was previously known as the "Greek" block.
857 *
858 * @since 1.2
859 */
860 public static final UnicodeBlock GREEK =
861 new UnicodeBlock("GREEK",
862 "GREEK AND COPTIC",
863 "GREEKANDCOPTIC");
864
865 /**
866 * Constant for the "Cyrillic" Unicode character block.
867 * @since 1.2
868 */
869 public static final UnicodeBlock CYRILLIC =
870 new UnicodeBlock("CYRILLIC");
871
872 /**
873 * Constant for the "Armenian" Unicode character block.
874 * @since 1.2
875 */
876 public static final UnicodeBlock ARMENIAN =
877 new UnicodeBlock("ARMENIAN");
878
879 /**
880 * Constant for the "Hebrew" Unicode character block.
881 * @since 1.2
882 */
883 public static final UnicodeBlock HEBREW =
884 new UnicodeBlock("HEBREW");
885
886 /**
887 * Constant for the "Arabic" Unicode character block.
888 * @since 1.2
889 */
890 public static final UnicodeBlock ARABIC =
891 new UnicodeBlock("ARABIC");
892
893 /**
894 * Constant for the "Devanagari" Unicode character block.
895 * @since 1.2
896 */
897 public static final UnicodeBlock DEVANAGARI =
898 new UnicodeBlock("DEVANAGARI");
899
900 /**
901 * Constant for the "Bengali" Unicode character block.
902 * @since 1.2
903 */
904 public static final UnicodeBlock BENGALI =
905 new UnicodeBlock("BENGALI");
906
907 /**
908 * Constant for the "Gurmukhi" Unicode character block.
909 * @since 1.2
910 */
911 public static final UnicodeBlock GURMUKHI =
912 new UnicodeBlock("GURMUKHI");
913
914 /**
915 * Constant for the "Gujarati" Unicode character block.
916 * @since 1.2
917 */
918 public static final UnicodeBlock GUJARATI =
919 new UnicodeBlock("GUJARATI");
920
921 /**
922 * Constant for the "Oriya" Unicode character block.
923 * @since 1.2
924 */
925 public static final UnicodeBlock ORIYA =
926 new UnicodeBlock("ORIYA");
927
928 /**
929 * Constant for the "Tamil" Unicode character block.
930 * @since 1.2
931 */
932 public static final UnicodeBlock TAMIL =
933 new UnicodeBlock("TAMIL");
934
935 /**
936 * Constant for the "Telugu" Unicode character block.
937 * @since 1.2
938 */
939 public static final UnicodeBlock TELUGU =
940 new UnicodeBlock("TELUGU");
941
942 /**
943 * Constant for the "Kannada" Unicode character block.
944 * @since 1.2
945 */
946 public static final UnicodeBlock KANNADA =
947 new UnicodeBlock("KANNADA");
948
949 /**
950 * Constant for the "Malayalam" Unicode character block.
951 * @since 1.2
952 */
953 public static final UnicodeBlock MALAYALAM =
954 new UnicodeBlock("MALAYALAM");
955
956 /**
957 * Constant for the "Thai" Unicode character block.
958 * @since 1.2
959 */
960 public static final UnicodeBlock THAI =
961 new UnicodeBlock("THAI");
962
963 /**
964 * Constant for the "Lao" Unicode character block.
965 * @since 1.2
966 */
967 public static final UnicodeBlock LAO =
968 new UnicodeBlock("LAO");
969
970 /**
971 * Constant for the "Tibetan" Unicode character block.
972 * @since 1.2
973 */
974 public static final UnicodeBlock TIBETAN =
975 new UnicodeBlock("TIBETAN");
976
977 /**
978 * Constant for the "Georgian" Unicode character block.
979 * @since 1.2
980 */
981 public static final UnicodeBlock GEORGIAN =
982 new UnicodeBlock("GEORGIAN");
983
984 /**
985 * Constant for the "Hangul Jamo" Unicode character block.
986 * @since 1.2
987 */
988 public static final UnicodeBlock HANGUL_JAMO =
989 new UnicodeBlock("HANGUL_JAMO",
990 "HANGUL JAMO",
991 "HANGULJAMO");
992
993 /**
994 * Constant for the "Latin Extended Additional" Unicode character block.
995 * @since 1.2
996 */
997 public static final UnicodeBlock LATIN_EXTENDED_ADDITIONAL =
998 new UnicodeBlock("LATIN_EXTENDED_ADDITIONAL",
999 "LATIN EXTENDED ADDITIONAL",
1000 "LATINEXTENDEDADDITIONAL");
1001
1002 /**
1003 * Constant for the "Greek Extended" Unicode character block.
1004 * @since 1.2
1005 */
1006 public static final UnicodeBlock GREEK_EXTENDED =
1007 new UnicodeBlock("GREEK_EXTENDED",
1008 "GREEK EXTENDED",
1009 "GREEKEXTENDED");
1010
1011 /**
1012 * Constant for the "General Punctuation" Unicode character block.
1013 * @since 1.2
1014 */
1015 public static final UnicodeBlock GENERAL_PUNCTUATION =
1016 new UnicodeBlock("GENERAL_PUNCTUATION",
1017 "GENERAL PUNCTUATION",
1018 "GENERALPUNCTUATION");
1019
1020 /**
1021 * Constant for the "Superscripts and Subscripts" Unicode character
1022 * block.
1023 * @since 1.2
1024 */
1025 public static final UnicodeBlock SUPERSCRIPTS_AND_SUBSCRIPTS =
1026 new UnicodeBlock("SUPERSCRIPTS_AND_SUBSCRIPTS",
1027 "SUPERSCRIPTS AND SUBSCRIPTS",
1028 "SUPERSCRIPTSANDSUBSCRIPTS");
1029
1030 /**
1031 * Constant for the "Currency Symbols" Unicode character block.
1032 * @since 1.2
1033 */
1034 public static final UnicodeBlock CURRENCY_SYMBOLS =
1035 new UnicodeBlock("CURRENCY_SYMBOLS",
1036 "CURRENCY SYMBOLS",
1037 "CURRENCYSYMBOLS");
1038
1039 /**
1040 * Constant for the "Combining Diacritical Marks for Symbols" Unicode
1041 * character block.
1042 * <p>
1043 * This block was previously known as "Combining Marks for Symbols".
1044 * @since 1.2
1045 */
1046 public static final UnicodeBlock COMBINING_MARKS_FOR_SYMBOLS =
1047 new UnicodeBlock("COMBINING_MARKS_FOR_SYMBOLS",
1048 "COMBINING DIACRITICAL MARKS FOR SYMBOLS",
1049 "COMBININGDIACRITICALMARKSFORSYMBOLS",
1050 "COMBINING MARKS FOR SYMBOLS",
1051 "COMBININGMARKSFORSYMBOLS");
1052
1053 /**
1054 * Constant for the "Letterlike Symbols" Unicode character block.
1055 * @since 1.2
1056 */
1057 public static final UnicodeBlock LETTERLIKE_SYMBOLS =
1058 new UnicodeBlock("LETTERLIKE_SYMBOLS",
1059 "LETTERLIKE SYMBOLS",
1060 "LETTERLIKESYMBOLS");
1061
1062 /**
1063 * Constant for the "Number Forms" Unicode character block.
1064 * @since 1.2
1065 */
1066 public static final UnicodeBlock NUMBER_FORMS =
1067 new UnicodeBlock("NUMBER_FORMS",
1068 "NUMBER FORMS",
1069 "NUMBERFORMS");
1070
1071 /**
1072 * Constant for the "Arrows" Unicode character block.
1073 * @since 1.2
1074 */
1075 public static final UnicodeBlock ARROWS =
1076 new UnicodeBlock("ARROWS");
1077
1078 /**
1079 * Constant for the "Mathematical Operators" Unicode character block.
1080 * @since 1.2
1081 */
1082 public static final UnicodeBlock MATHEMATICAL_OPERATORS =
1083 new UnicodeBlock("MATHEMATICAL_OPERATORS",
1084 "MATHEMATICAL OPERATORS",
1085 "MATHEMATICALOPERATORS");
1086
1087 /**
1088 * Constant for the "Miscellaneous Technical" Unicode character block.
1089 * @since 1.2
1090 */
1091 public static final UnicodeBlock MISCELLANEOUS_TECHNICAL =
1092 new UnicodeBlock("MISCELLANEOUS_TECHNICAL",
1093 "MISCELLANEOUS TECHNICAL",
1094 "MISCELLANEOUSTECHNICAL");
1095
1096 /**
1097 * Constant for the "Control Pictures" Unicode character block.
1098 * @since 1.2
1099 */
1100 public static final UnicodeBlock CONTROL_PICTURES =
1101 new UnicodeBlock("CONTROL_PICTURES",
1102 "CONTROL PICTURES",
1103 "CONTROLPICTURES");
1104
1105 /**
1106 * Constant for the "Optical Character Recognition" Unicode character block.
1107 * @since 1.2
1108 */
1109 public static final UnicodeBlock OPTICAL_CHARACTER_RECOGNITION =
1110 new UnicodeBlock("OPTICAL_CHARACTER_RECOGNITION",
1111 "OPTICAL CHARACTER RECOGNITION",
1112 "OPTICALCHARACTERRECOGNITION");
1113
1114 /**
1115 * Constant for the "Enclosed Alphanumerics" Unicode character block.
1116 * @since 1.2
1117 */
1118 public static final UnicodeBlock ENCLOSED_ALPHANUMERICS =
1119 new UnicodeBlock("ENCLOSED_ALPHANUMERICS",
1120 "ENCLOSED ALPHANUMERICS",
1121 "ENCLOSEDALPHANUMERICS");
1122
1123 /**
1124 * Constant for the "Box Drawing" Unicode character block.
1125 * @since 1.2
1126 */
1127 public static final UnicodeBlock BOX_DRAWING =
1128 new UnicodeBlock("BOX_DRAWING",
1129 "BOX DRAWING",
1130 "BOXDRAWING");
1131
1132 /**
1133 * Constant for the "Block Elements" Unicode character block.
1134 * @since 1.2
1135 */
1136 public static final UnicodeBlock BLOCK_ELEMENTS =
1137 new UnicodeBlock("BLOCK_ELEMENTS",
1138 "BLOCK ELEMENTS",
1139 "BLOCKELEMENTS");
1140
1141 /**
1142 * Constant for the "Geometric Shapes" Unicode character block.
1143 * @since 1.2
1144 */
1145 public static final UnicodeBlock GEOMETRIC_SHAPES =
1146 new UnicodeBlock("GEOMETRIC_SHAPES",
1147 "GEOMETRIC SHAPES",
1148 "GEOMETRICSHAPES");
1149
1150 /**
1151 * Constant for the "Miscellaneous Symbols" Unicode character block.
1152 * @since 1.2
1153 */
1154 public static final UnicodeBlock MISCELLANEOUS_SYMBOLS =
1155 new UnicodeBlock("MISCELLANEOUS_SYMBOLS",
1156 "MISCELLANEOUS SYMBOLS",
1157 "MISCELLANEOUSSYMBOLS");
1158
1159 /**
1160 * Constant for the "Dingbats" Unicode character block.
1161 * @since 1.2
1162 */
1163 public static final UnicodeBlock DINGBATS =
1164 new UnicodeBlock("DINGBATS");
1165
1166 /**
1167 * Constant for the "CJK Symbols and Punctuation" Unicode character block.
1168 * @since 1.2
1169 */
1170 public static final UnicodeBlock CJK_SYMBOLS_AND_PUNCTUATION =
1171 new UnicodeBlock("CJK_SYMBOLS_AND_PUNCTUATION",
1172 "CJK SYMBOLS AND PUNCTUATION",
1173 "CJKSYMBOLSANDPUNCTUATION");
1174
1175 /**
1176 * Constant for the "Hiragana" Unicode character block.
1177 * @since 1.2
1178 */
1179 public static final UnicodeBlock HIRAGANA =
1180 new UnicodeBlock("HIRAGANA");
1181
1182 /**
1183 * Constant for the "Katakana" Unicode character block.
1184 * @since 1.2
1185 */
1186 public static final UnicodeBlock KATAKANA =
1187 new UnicodeBlock("KATAKANA");
1188
1189 /**
1190 * Constant for the "Bopomofo" Unicode character block.
1191 * @since 1.2
1192 */
1193 public static final UnicodeBlock BOPOMOFO =
1194 new UnicodeBlock("BOPOMOFO");
1195
1196 /**
1197 * Constant for the "Hangul Compatibility Jamo" Unicode character block.
1198 * @since 1.2
1199 */
1200 public static final UnicodeBlock HANGUL_COMPATIBILITY_JAMO =
1201 new UnicodeBlock("HANGUL_COMPATIBILITY_JAMO",
1202 "HANGUL COMPATIBILITY JAMO",
1203 "HANGULCOMPATIBILITYJAMO");
1204
1205 /**
1206 * Constant for the "Kanbun" Unicode character block.
1207 * @since 1.2
1208 */
1209 public static final UnicodeBlock KANBUN =
1210 new UnicodeBlock("KANBUN");
1211
1212 /**
1213 * Constant for the "Enclosed CJK Letters and Months" Unicode character block.
1214 * @since 1.2
1215 */
1216 public static final UnicodeBlock ENCLOSED_CJK_LETTERS_AND_MONTHS =
1217 new UnicodeBlock("ENCLOSED_CJK_LETTERS_AND_MONTHS",
1218 "ENCLOSED CJK LETTERS AND MONTHS",
1219 "ENCLOSEDCJKLETTERSANDMONTHS");
1220
1221 /**
1222 * Constant for the "CJK Compatibility" Unicode character block.
1223 * @since 1.2
1224 */
1225 public static final UnicodeBlock CJK_COMPATIBILITY =
1226 new UnicodeBlock("CJK_COMPATIBILITY",
1227 "CJK COMPATIBILITY",
1228 "CJKCOMPATIBILITY");
1229
1230 /**
1231 * Constant for the "CJK Unified Ideographs" Unicode character block.
1232 * @since 1.2
1233 */
1234 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS =
1235 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS",
1236 "CJK UNIFIED IDEOGRAPHS",
1237 "CJKUNIFIEDIDEOGRAPHS");
1238
1239 /**
1240 * Constant for the "Hangul Syllables" Unicode character block.
1241 * @since 1.2
1242 */
1243 public static final UnicodeBlock HANGUL_SYLLABLES =
1244 new UnicodeBlock("HANGUL_SYLLABLES",
1245 "HANGUL SYLLABLES",
1246 "HANGULSYLLABLES");
1247
1248 /**
1249 * Constant for the "Private Use Area" Unicode character block.
1250 * @since 1.2
1251 */
1252 public static final UnicodeBlock PRIVATE_USE_AREA =
1253 new UnicodeBlock("PRIVATE_USE_AREA",
1254 "PRIVATE USE AREA",
1255 "PRIVATEUSEAREA");
1256
1257 /**
1258 * Constant for the "CJK Compatibility Ideographs" Unicode character
1259 * block.
1260 * @since 1.2
1261 */
1262 public static final UnicodeBlock CJK_COMPATIBILITY_IDEOGRAPHS =
1263 new UnicodeBlock("CJK_COMPATIBILITY_IDEOGRAPHS",
1264 "CJK COMPATIBILITY IDEOGRAPHS",
1265 "CJKCOMPATIBILITYIDEOGRAPHS");
1266
1267 /**
1268 * Constant for the "Alphabetic Presentation Forms" Unicode character block.
1269 * @since 1.2
1270 */
1271 public static final UnicodeBlock ALPHABETIC_PRESENTATION_FORMS =
1272 new UnicodeBlock("ALPHABETIC_PRESENTATION_FORMS",
1273 "ALPHABETIC PRESENTATION FORMS",
1274 "ALPHABETICPRESENTATIONFORMS");
1275
1276 /**
1277 * Constant for the "Arabic Presentation Forms-A" Unicode character
1278 * block.
1279 * @since 1.2
1280 */
1281 public static final UnicodeBlock ARABIC_PRESENTATION_FORMS_A =
1282 new UnicodeBlock("ARABIC_PRESENTATION_FORMS_A",
1283 "ARABIC PRESENTATION FORMS-A",
1284 "ARABICPRESENTATIONFORMS-A");
1285
1286 /**
1287 * Constant for the "Combining Half Marks" Unicode character block.
1288 * @since 1.2
1289 */
1290 public static final UnicodeBlock COMBINING_HALF_MARKS =
1291 new UnicodeBlock("COMBINING_HALF_MARKS",
1292 "COMBINING HALF MARKS",
1293 "COMBININGHALFMARKS");
1294
1295 /**
1296 * Constant for the "CJK Compatibility Forms" Unicode character block.
1297 * @since 1.2
1298 */
1299 public static final UnicodeBlock CJK_COMPATIBILITY_FORMS =
1300 new UnicodeBlock("CJK_COMPATIBILITY_FORMS",
1301 "CJK COMPATIBILITY FORMS",
1302 "CJKCOMPATIBILITYFORMS");
1303
1304 /**
1305 * Constant for the "Small Form Variants" Unicode character block.
1306 * @since 1.2
1307 */
1308 public static final UnicodeBlock SMALL_FORM_VARIANTS =
1309 new UnicodeBlock("SMALL_FORM_VARIANTS",
1310 "SMALL FORM VARIANTS",
1311 "SMALLFORMVARIANTS");
1312
1313 /**
1314 * Constant for the "Arabic Presentation Forms-B" Unicode character block.
1315 * @since 1.2
1316 */
1317 public static final UnicodeBlock ARABIC_PRESENTATION_FORMS_B =
1318 new UnicodeBlock("ARABIC_PRESENTATION_FORMS_B",
1319 "ARABIC PRESENTATION FORMS-B",
1320 "ARABICPRESENTATIONFORMS-B");
1321
1322 /**
1323 * Constant for the "Halfwidth and Fullwidth Forms" Unicode character
1324 * block.
1325 * @since 1.2
1326 */
1327 public static final UnicodeBlock HALFWIDTH_AND_FULLWIDTH_FORMS =
1328 new UnicodeBlock("HALFWIDTH_AND_FULLWIDTH_FORMS",
1329 "HALFWIDTH AND FULLWIDTH FORMS",
1330 "HALFWIDTHANDFULLWIDTHFORMS");
1331
1332 /**
1333 * Constant for the "Specials" Unicode character block.
1334 * @since 1.2
1335 */
1336 public static final UnicodeBlock SPECIALS =
1337 new UnicodeBlock("SPECIALS");
1338
1339 /**
1340 * @deprecated
1341 * Instead of {@code SURROGATES_AREA}, use {@link #HIGH_SURROGATES},
1342 * {@link #HIGH_PRIVATE_USE_SURROGATES}, and {@link #LOW_SURROGATES}.
1343 * These constants match the block definitions of the Unicode Standard.
1344 * The {@link #of(char)} and {@link #of(int)} methods return the
1345 * standard constants.
1346 */
1347 @Deprecated(since="1.5")
1348 public static final UnicodeBlock SURROGATES_AREA =
1349 new UnicodeBlock("SURROGATES_AREA");
1350
1351 /**
1352 * Constant for the "Syriac" Unicode character block.
1353 * @since 1.4
1354 */
1355 public static final UnicodeBlock SYRIAC =
1356 new UnicodeBlock("SYRIAC");
1357
1358 /**
1359 * Constant for the "Thaana" Unicode character block.
1360 * @since 1.4
1361 */
1362 public static final UnicodeBlock THAANA =
1363 new UnicodeBlock("THAANA");
1364
1365 /**
1366 * Constant for the "Sinhala" Unicode character block.
1367 * @since 1.4
1368 */
1369 public static final UnicodeBlock SINHALA =
1370 new UnicodeBlock("SINHALA");
1371
1372 /**
1373 * Constant for the "Myanmar" Unicode character block.
1374 * @since 1.4
1375 */
1376 public static final UnicodeBlock MYANMAR =
1377 new UnicodeBlock("MYANMAR");
1378
1379 /**
1380 * Constant for the "Ethiopic" Unicode character block.
1381 * @since 1.4
1382 */
1383 public static final UnicodeBlock ETHIOPIC =
1384 new UnicodeBlock("ETHIOPIC");
1385
1386 /**
1387 * Constant for the "Cherokee" Unicode character block.
1388 * @since 1.4
1389 */
1390 public static final UnicodeBlock CHEROKEE =
1391 new UnicodeBlock("CHEROKEE");
1392
1393 /**
1394 * Constant for the "Unified Canadian Aboriginal Syllabics" Unicode character block.
1395 * @since 1.4
1396 */
1397 public static final UnicodeBlock UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS =
1398 new UnicodeBlock("UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS",
1399 "UNIFIED CANADIAN ABORIGINAL SYLLABICS",
1400 "UNIFIEDCANADIANABORIGINALSYLLABICS");
1401
1402 /**
1403 * Constant for the "Ogham" Unicode character block.
1404 * @since 1.4
1405 */
1406 public static final UnicodeBlock OGHAM =
1407 new UnicodeBlock("OGHAM");
1408
1409 /**
1410 * Constant for the "Runic" Unicode character block.
1411 * @since 1.4
1412 */
1413 public static final UnicodeBlock RUNIC =
1414 new UnicodeBlock("RUNIC");
1415
1416 /**
1417 * Constant for the "Khmer" Unicode character block.
1418 * @since 1.4
1419 */
1420 public static final UnicodeBlock KHMER =
1421 new UnicodeBlock("KHMER");
1422
1423 /**
1424 * Constant for the "Mongolian" Unicode character block.
1425 * @since 1.4
1426 */
1427 public static final UnicodeBlock MONGOLIAN =
1428 new UnicodeBlock("MONGOLIAN");
1429
1430 /**
1431 * Constant for the "Braille Patterns" Unicode character block.
1432 * @since 1.4
1433 */
1434 public static final UnicodeBlock BRAILLE_PATTERNS =
1435 new UnicodeBlock("BRAILLE_PATTERNS",
1436 "BRAILLE PATTERNS",
1437 "BRAILLEPATTERNS");
1438
1439 /**
1440 * Constant for the "CJK Radicals Supplement" Unicode character block.
1441 * @since 1.4
1442 */
1443 public static final UnicodeBlock CJK_RADICALS_SUPPLEMENT =
1444 new UnicodeBlock("CJK_RADICALS_SUPPLEMENT",
1445 "CJK RADICALS SUPPLEMENT",
1446 "CJKRADICALSSUPPLEMENT");
1447
1448 /**
1449 * Constant for the "Kangxi Radicals" Unicode character block.
1450 * @since 1.4
1451 */
1452 public static final UnicodeBlock KANGXI_RADICALS =
1453 new UnicodeBlock("KANGXI_RADICALS",
1454 "KANGXI RADICALS",
1455 "KANGXIRADICALS");
1456
1457 /**
1458 * Constant for the "Ideographic Description Characters" Unicode character block.
1459 * @since 1.4
1460 */
1461 public static final UnicodeBlock IDEOGRAPHIC_DESCRIPTION_CHARACTERS =
1462 new UnicodeBlock("IDEOGRAPHIC_DESCRIPTION_CHARACTERS",
1463 "IDEOGRAPHIC DESCRIPTION CHARACTERS",
1464 "IDEOGRAPHICDESCRIPTIONCHARACTERS");
1465
1466 /**
1467 * Constant for the "Bopomofo Extended" Unicode character block.
1468 * @since 1.4
1469 */
1470 public static final UnicodeBlock BOPOMOFO_EXTENDED =
1471 new UnicodeBlock("BOPOMOFO_EXTENDED",
1472 "BOPOMOFO EXTENDED",
1473 "BOPOMOFOEXTENDED");
1474
1475 /**
1476 * Constant for the "CJK Unified Ideographs Extension A" Unicode character block.
1477 * @since 1.4
1478 */
1479 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A =
1480 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A",
1481 "CJK UNIFIED IDEOGRAPHS EXTENSION A",
1482 "CJKUNIFIEDIDEOGRAPHSEXTENSIONA");
1483
1484 /**
1485 * Constant for the "Yi Syllables" Unicode character block.
1486 * @since 1.4
1487 */
1488 public static final UnicodeBlock YI_SYLLABLES =
1489 new UnicodeBlock("YI_SYLLABLES",
1490 "YI SYLLABLES",
1491 "YISYLLABLES");
1492
1493 /**
1494 * Constant for the "Yi Radicals" Unicode character block.
1495 * @since 1.4
1496 */
1497 public static final UnicodeBlock YI_RADICALS =
1498 new UnicodeBlock("YI_RADICALS",
1499 "YI RADICALS",
1500 "YIRADICALS");
1501
1502 /**
1503 * Constant for the "Cyrillic Supplement" Unicode character block.
1504 * This block was previously known as the "Cyrillic Supplementary" block.
1505 * @since 1.5
1506 */
1507 public static final UnicodeBlock CYRILLIC_SUPPLEMENTARY =
1508 new UnicodeBlock("CYRILLIC_SUPPLEMENTARY",
1509 "CYRILLIC SUPPLEMENTARY",
1510 "CYRILLICSUPPLEMENTARY",
1511 "CYRILLIC SUPPLEMENT",
1512 "CYRILLICSUPPLEMENT");
1513
1514 /**
1515 * Constant for the "Tagalog" Unicode character block.
1516 * @since 1.5
1517 */
1518 public static final UnicodeBlock TAGALOG =
1519 new UnicodeBlock("TAGALOG");
1520
1521 /**
1522 * Constant for the "Hanunoo" Unicode character block.
1523 * @since 1.5
1524 */
1525 public static final UnicodeBlock HANUNOO =
1526 new UnicodeBlock("HANUNOO");
1527
1528 /**
1529 * Constant for the "Buhid" Unicode character block.
1530 * @since 1.5
1531 */
1532 public static final UnicodeBlock BUHID =
1533 new UnicodeBlock("BUHID");
1534
1535 /**
1536 * Constant for the "Tagbanwa" Unicode character block.
1537 * @since 1.5
1538 */
1539 public static final UnicodeBlock TAGBANWA =
1540 new UnicodeBlock("TAGBANWA");
1541
1542 /**
1543 * Constant for the "Limbu" Unicode character block.
1544 * @since 1.5
1545 */
1546 public static final UnicodeBlock LIMBU =
1547 new UnicodeBlock("LIMBU");
1548
1549 /**
1550 * Constant for the "Tai Le" Unicode character block.
1551 * @since 1.5
1552 */
1553 public static final UnicodeBlock TAI_LE =
1554 new UnicodeBlock("TAI_LE",
1555 "TAI LE",
1556 "TAILE");
1557
1558 /**
1559 * Constant for the "Khmer Symbols" Unicode character block.
1560 * @since 1.5
1561 */
1562 public static final UnicodeBlock KHMER_SYMBOLS =
1563 new UnicodeBlock("KHMER_SYMBOLS",
1564 "KHMER SYMBOLS",
1565 "KHMERSYMBOLS");
1566
1567 /**
1568 * Constant for the "Phonetic Extensions" Unicode character block.
1569 * @since 1.5
1570 */
1571 public static final UnicodeBlock PHONETIC_EXTENSIONS =
1572 new UnicodeBlock("PHONETIC_EXTENSIONS",
1573 "PHONETIC EXTENSIONS",
1574 "PHONETICEXTENSIONS");
1575
1576 /**
1577 * Constant for the "Miscellaneous Mathematical Symbols-A" Unicode character block.
1578 * @since 1.5
1579 */
1580 public static final UnicodeBlock MISCELLANEOUS_MATHEMATICAL_SYMBOLS_A =
1581 new UnicodeBlock("MISCELLANEOUS_MATHEMATICAL_SYMBOLS_A",
1582 "MISCELLANEOUS MATHEMATICAL SYMBOLS-A",
1583 "MISCELLANEOUSMATHEMATICALSYMBOLS-A");
1584
1585 /**
1586 * Constant for the "Supplemental Arrows-A" Unicode character block.
1587 * @since 1.5
1588 */
1589 public static final UnicodeBlock SUPPLEMENTAL_ARROWS_A =
1590 new UnicodeBlock("SUPPLEMENTAL_ARROWS_A",
1591 "SUPPLEMENTAL ARROWS-A",
1592 "SUPPLEMENTALARROWS-A");
1593
1594 /**
1595 * Constant for the "Supplemental Arrows-B" Unicode character block.
1596 * @since 1.5
1597 */
1598 public static final UnicodeBlock SUPPLEMENTAL_ARROWS_B =
1599 new UnicodeBlock("SUPPLEMENTAL_ARROWS_B",
1600 "SUPPLEMENTAL ARROWS-B",
1601 "SUPPLEMENTALARROWS-B");
1602
1603 /**
1604 * Constant for the "Miscellaneous Mathematical Symbols-B" Unicode
1605 * character block.
1606 * @since 1.5
1607 */
1608 public static final UnicodeBlock MISCELLANEOUS_MATHEMATICAL_SYMBOLS_B =
1609 new UnicodeBlock("MISCELLANEOUS_MATHEMATICAL_SYMBOLS_B",
1610 "MISCELLANEOUS MATHEMATICAL SYMBOLS-B",
1611 "MISCELLANEOUSMATHEMATICALSYMBOLS-B");
1612
1613 /**
1614 * Constant for the "Supplemental Mathematical Operators" Unicode
1615 * character block.
1616 * @since 1.5
1617 */
1618 public static final UnicodeBlock SUPPLEMENTAL_MATHEMATICAL_OPERATORS =
1619 new UnicodeBlock("SUPPLEMENTAL_MATHEMATICAL_OPERATORS",
1620 "SUPPLEMENTAL MATHEMATICAL OPERATORS",
1621 "SUPPLEMENTALMATHEMATICALOPERATORS");
1622
1623 /**
1624 * Constant for the "Miscellaneous Symbols and Arrows" Unicode character
1625 * block.
1626 * @since 1.5
1627 */
1628 public static final UnicodeBlock MISCELLANEOUS_SYMBOLS_AND_ARROWS =
1629 new UnicodeBlock("MISCELLANEOUS_SYMBOLS_AND_ARROWS",
1630 "MISCELLANEOUS SYMBOLS AND ARROWS",
1631 "MISCELLANEOUSSYMBOLSANDARROWS");
1632
1633 /**
1634 * Constant for the "Katakana Phonetic Extensions" Unicode character
1635 * block.
1636 * @since 1.5
1637 */
1638 public static final UnicodeBlock KATAKANA_PHONETIC_EXTENSIONS =
1639 new UnicodeBlock("KATAKANA_PHONETIC_EXTENSIONS",
1640 "KATAKANA PHONETIC EXTENSIONS",
1641 "KATAKANAPHONETICEXTENSIONS");
1642
1643 /**
1644 * Constant for the "Yijing Hexagram Symbols" Unicode character block.
1645 * @since 1.5
1646 */
1647 public static final UnicodeBlock YIJING_HEXAGRAM_SYMBOLS =
1648 new UnicodeBlock("YIJING_HEXAGRAM_SYMBOLS",
1649 "YIJING HEXAGRAM SYMBOLS",
1650 "YIJINGHEXAGRAMSYMBOLS");
1651
1652 /**
1653 * Constant for the "Variation Selectors" Unicode character block.
1654 * @since 1.5
1655 */
1656 public static final UnicodeBlock VARIATION_SELECTORS =
1657 new UnicodeBlock("VARIATION_SELECTORS",
1658 "VARIATION SELECTORS",
1659 "VARIATIONSELECTORS");
1660
1661 /**
1662 * Constant for the "Linear B Syllabary" Unicode character block.
1663 * @since 1.5
1664 */
1665 public static final UnicodeBlock LINEAR_B_SYLLABARY =
1666 new UnicodeBlock("LINEAR_B_SYLLABARY",
1667 "LINEAR B SYLLABARY",
1668 "LINEARBSYLLABARY");
1669
1670 /**
1671 * Constant for the "Linear B Ideograms" Unicode character block.
1672 * @since 1.5
1673 */
1674 public static final UnicodeBlock LINEAR_B_IDEOGRAMS =
1675 new UnicodeBlock("LINEAR_B_IDEOGRAMS",
1676 "LINEAR B IDEOGRAMS",
1677 "LINEARBIDEOGRAMS");
1678
1679 /**
1680 * Constant for the "Aegean Numbers" Unicode character block.
1681 * @since 1.5
1682 */
1683 public static final UnicodeBlock AEGEAN_NUMBERS =
1684 new UnicodeBlock("AEGEAN_NUMBERS",
1685 "AEGEAN NUMBERS",
1686 "AEGEANNUMBERS");
1687
1688 /**
1689 * Constant for the "Old Italic" Unicode character block.
1690 * @since 1.5
1691 */
1692 public static final UnicodeBlock OLD_ITALIC =
1693 new UnicodeBlock("OLD_ITALIC",
1694 "OLD ITALIC",
1695 "OLDITALIC");
1696
1697 /**
1698 * Constant for the "Gothic" Unicode character block.
1699 * @since 1.5
1700 */
1701 public static final UnicodeBlock GOTHIC =
1702 new UnicodeBlock("GOTHIC");
1703
1704 /**
1705 * Constant for the "Ugaritic" Unicode character block.
1706 * @since 1.5
1707 */
1708 public static final UnicodeBlock UGARITIC =
1709 new UnicodeBlock("UGARITIC");
1710
1711 /**
1712 * Constant for the "Deseret" Unicode character block.
1713 * @since 1.5
1714 */
1715 public static final UnicodeBlock DESERET =
1716 new UnicodeBlock("DESERET");
1717
1718 /**
1719 * Constant for the "Shavian" Unicode character block.
1720 * @since 1.5
1721 */
1722 public static final UnicodeBlock SHAVIAN =
1723 new UnicodeBlock("SHAVIAN");
1724
1725 /**
1726 * Constant for the "Osmanya" Unicode character block.
1727 * @since 1.5
1728 */
1729 public static final UnicodeBlock OSMANYA =
1730 new UnicodeBlock("OSMANYA");
1731
1732 /**
1733 * Constant for the "Cypriot Syllabary" Unicode character block.
1734 * @since 1.5
1735 */
1736 public static final UnicodeBlock CYPRIOT_SYLLABARY =
1737 new UnicodeBlock("CYPRIOT_SYLLABARY",
1738 "CYPRIOT SYLLABARY",
1739 "CYPRIOTSYLLABARY");
1740
1741 /**
1742 * Constant for the "Byzantine Musical Symbols" Unicode character block.
1743 * @since 1.5
1744 */
1745 public static final UnicodeBlock BYZANTINE_MUSICAL_SYMBOLS =
1746 new UnicodeBlock("BYZANTINE_MUSICAL_SYMBOLS",
1747 "BYZANTINE MUSICAL SYMBOLS",
1748 "BYZANTINEMUSICALSYMBOLS");
1749
1750 /**
1751 * Constant for the "Musical Symbols" Unicode character block.
1752 * @since 1.5
1753 */
1754 public static final UnicodeBlock MUSICAL_SYMBOLS =
1755 new UnicodeBlock("MUSICAL_SYMBOLS",
1756 "MUSICAL SYMBOLS",
1757 "MUSICALSYMBOLS");
1758
1759 /**
1760 * Constant for the "Tai Xuan Jing Symbols" Unicode character block.
1761 * @since 1.5
1762 */
1763 public static final UnicodeBlock TAI_XUAN_JING_SYMBOLS =
1764 new UnicodeBlock("TAI_XUAN_JING_SYMBOLS",
1765 "TAI XUAN JING SYMBOLS",
1766 "TAIXUANJINGSYMBOLS");
1767
1768 /**
1769 * Constant for the "Mathematical Alphanumeric Symbols" Unicode
1770 * character block.
1771 * @since 1.5
1772 */
1773 public static final UnicodeBlock MATHEMATICAL_ALPHANUMERIC_SYMBOLS =
1774 new UnicodeBlock("MATHEMATICAL_ALPHANUMERIC_SYMBOLS",
1775 "MATHEMATICAL ALPHANUMERIC SYMBOLS",
1776 "MATHEMATICALALPHANUMERICSYMBOLS");
1777
1778 /**
1779 * Constant for the "CJK Unified Ideographs Extension B" Unicode
1780 * character block.
1781 * @since 1.5
1782 */
1783 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_B =
1784 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_B",
1785 "CJK UNIFIED IDEOGRAPHS EXTENSION B",
1786 "CJKUNIFIEDIDEOGRAPHSEXTENSIONB");
1787
1788 /**
1789 * Constant for the "CJK Compatibility Ideographs Supplement" Unicode character block.
1790 * @since 1.5
1791 */
1792 public static final UnicodeBlock CJK_COMPATIBILITY_IDEOGRAPHS_SUPPLEMENT =
1793 new UnicodeBlock("CJK_COMPATIBILITY_IDEOGRAPHS_SUPPLEMENT",
1794 "CJK COMPATIBILITY IDEOGRAPHS SUPPLEMENT",
1795 "CJKCOMPATIBILITYIDEOGRAPHSSUPPLEMENT");
1796
1797 /**
1798 * Constant for the "Tags" Unicode character block.
1799 * @since 1.5
1800 */
1801 public static final UnicodeBlock TAGS =
1802 new UnicodeBlock("TAGS");
1803
1804 /**
1805 * Constant for the "Variation Selectors Supplement" Unicode character
1806 * block.
1807 * @since 1.5
1808 */
1809 public static final UnicodeBlock VARIATION_SELECTORS_SUPPLEMENT =
1810 new UnicodeBlock("VARIATION_SELECTORS_SUPPLEMENT",
1811 "VARIATION SELECTORS SUPPLEMENT",
1812 "VARIATIONSELECTORSSUPPLEMENT");
1813
1814 /**
1815 * Constant for the "Supplementary Private Use Area-A" Unicode character
1816 * block.
1817 * @since 1.5
1818 */
1819 public static final UnicodeBlock SUPPLEMENTARY_PRIVATE_USE_AREA_A =
1820 new UnicodeBlock("SUPPLEMENTARY_PRIVATE_USE_AREA_A",
1821 "SUPPLEMENTARY PRIVATE USE AREA-A",
1822 "SUPPLEMENTARYPRIVATEUSEAREA-A");
1823
1824 /**
1825 * Constant for the "Supplementary Private Use Area-B" Unicode character
1826 * block.
1827 * @since 1.5
1828 */
1829 public static final UnicodeBlock SUPPLEMENTARY_PRIVATE_USE_AREA_B =
1830 new UnicodeBlock("SUPPLEMENTARY_PRIVATE_USE_AREA_B",
1831 "SUPPLEMENTARY PRIVATE USE AREA-B",
1832 "SUPPLEMENTARYPRIVATEUSEAREA-B");
1833
1834 /**
1835 * Constant for the "High Surrogates" Unicode character block.
1836 * This block represents codepoint values in the high surrogate
1837 * range: U+D800 through U+DB7F
1838 *
1839 * @since 1.5
1840 */
1841 public static final UnicodeBlock HIGH_SURROGATES =
1842 new UnicodeBlock("HIGH_SURROGATES",
1843 "HIGH SURROGATES",
1844 "HIGHSURROGATES");
1845
1846 /**
1847 * Constant for the "High Private Use Surrogates" Unicode character
1848 * block.
1849 * This block represents codepoint values in the private use high
1850 * surrogate range: U+DB80 through U+DBFF
1851 *
1852 * @since 1.5
1853 */
1854 public static final UnicodeBlock HIGH_PRIVATE_USE_SURROGATES =
1855 new UnicodeBlock("HIGH_PRIVATE_USE_SURROGATES",
1856 "HIGH PRIVATE USE SURROGATES",
1857 "HIGHPRIVATEUSESURROGATES");
1858
1859 /**
1860 * Constant for the "Low Surrogates" Unicode character block.
1861 * This block represents codepoint values in the low surrogate
1862 * range: U+DC00 through U+DFFF
1863 *
1864 * @since 1.5
1865 */
1866 public static final UnicodeBlock LOW_SURROGATES =
1867 new UnicodeBlock("LOW_SURROGATES",
1868 "LOW SURROGATES",
1869 "LOWSURROGATES");
1870
1871 /**
1872 * Constant for the "Arabic Supplement" Unicode character block.
1873 * @since 1.7
1874 */
1875 public static final UnicodeBlock ARABIC_SUPPLEMENT =
1876 new UnicodeBlock("ARABIC_SUPPLEMENT",
1877 "ARABIC SUPPLEMENT",
1878 "ARABICSUPPLEMENT");
1879
1880 /**
1881 * Constant for the "NKo" Unicode character block.
1882 * @since 1.7
1883 */
1884 public static final UnicodeBlock NKO =
1885 new UnicodeBlock("NKO");
1886
1887 /**
1888 * Constant for the "Samaritan" Unicode character block.
1889 * @since 1.7
1890 */
1891 public static final UnicodeBlock SAMARITAN =
1892 new UnicodeBlock("SAMARITAN");
1893
1894 /**
1895 * Constant for the "Mandaic" Unicode character block.
1896 * @since 1.7
1897 */
1898 public static final UnicodeBlock MANDAIC =
1899 new UnicodeBlock("MANDAIC");
1900
1901 /**
1902 * Constant for the "Ethiopic Supplement" Unicode character block.
1903 * @since 1.7
1904 */
1905 public static final UnicodeBlock ETHIOPIC_SUPPLEMENT =
1906 new UnicodeBlock("ETHIOPIC_SUPPLEMENT",
1907 "ETHIOPIC SUPPLEMENT",
1908 "ETHIOPICSUPPLEMENT");
1909
1910 /**
1911 * Constant for the "Unified Canadian Aboriginal Syllabics Extended"
1912 * Unicode character block.
1913 * @since 1.7
1914 */
1915 public static final UnicodeBlock UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED =
1916 new UnicodeBlock("UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED",
1917 "UNIFIED CANADIAN ABORIGINAL SYLLABICS EXTENDED",
1918 "UNIFIEDCANADIANABORIGINALSYLLABICSEXTENDED");
1919
1920 /**
1921 * Constant for the "New Tai Lue" Unicode character block.
1922 * @since 1.7
1923 */
1924 public static final UnicodeBlock NEW_TAI_LUE =
1925 new UnicodeBlock("NEW_TAI_LUE",
1926 "NEW TAI LUE",
1927 "NEWTAILUE");
1928
1929 /**
1930 * Constant for the "Buginese" Unicode character block.
1931 * @since 1.7
1932 */
1933 public static final UnicodeBlock BUGINESE =
1934 new UnicodeBlock("BUGINESE");
1935
1936 /**
1937 * Constant for the "Tai Tham" Unicode character block.
1938 * @since 1.7
1939 */
1940 public static final UnicodeBlock TAI_THAM =
1941 new UnicodeBlock("TAI_THAM",
1942 "TAI THAM",
1943 "TAITHAM");
1944
1945 /**
1946 * Constant for the "Balinese" Unicode character block.
1947 * @since 1.7
1948 */
1949 public static final UnicodeBlock BALINESE =
1950 new UnicodeBlock("BALINESE");
1951
1952 /**
1953 * Constant for the "Sundanese" Unicode character block.
1954 * @since 1.7
1955 */
1956 public static final UnicodeBlock SUNDANESE =
1957 new UnicodeBlock("SUNDANESE");
1958
1959 /**
1960 * Constant for the "Batak" Unicode character block.
1961 * @since 1.7
1962 */
1963 public static final UnicodeBlock BATAK =
1964 new UnicodeBlock("BATAK");
1965
1966 /**
1967 * Constant for the "Lepcha" Unicode character block.
1968 * @since 1.7
1969 */
1970 public static final UnicodeBlock LEPCHA =
1971 new UnicodeBlock("LEPCHA");
1972
1973 /**
1974 * Constant for the "Ol Chiki" Unicode character block.
1975 * @since 1.7
1976 */
1977 public static final UnicodeBlock OL_CHIKI =
1978 new UnicodeBlock("OL_CHIKI",
1979 "OL CHIKI",
1980 "OLCHIKI");
1981
1982 /**
1983 * Constant for the "Vedic Extensions" Unicode character block.
1984 * @since 1.7
1985 */
1986 public static final UnicodeBlock VEDIC_EXTENSIONS =
1987 new UnicodeBlock("VEDIC_EXTENSIONS",
1988 "VEDIC EXTENSIONS",
1989 "VEDICEXTENSIONS");
1990
1991 /**
1992 * Constant for the "Phonetic Extensions Supplement" Unicode character
1993 * block.
1994 * @since 1.7
1995 */
1996 public static final UnicodeBlock PHONETIC_EXTENSIONS_SUPPLEMENT =
1997 new UnicodeBlock("PHONETIC_EXTENSIONS_SUPPLEMENT",
1998 "PHONETIC EXTENSIONS SUPPLEMENT",
1999 "PHONETICEXTENSIONSSUPPLEMENT");
2000
2001 /**
2002 * Constant for the "Combining Diacritical Marks Supplement" Unicode
2003 * character block.
2004 * @since 1.7
2005 */
2006 public static final UnicodeBlock COMBINING_DIACRITICAL_MARKS_SUPPLEMENT =
2007 new UnicodeBlock("COMBINING_DIACRITICAL_MARKS_SUPPLEMENT",
2008 "COMBINING DIACRITICAL MARKS SUPPLEMENT",
2009 "COMBININGDIACRITICALMARKSSUPPLEMENT");
2010
2011 /**
2012 * Constant for the "Glagolitic" Unicode character block.
2013 * @since 1.7
2014 */
2015 public static final UnicodeBlock GLAGOLITIC =
2016 new UnicodeBlock("GLAGOLITIC");
2017
2018 /**
2019 * Constant for the "Latin Extended-C" Unicode character block.
2020 * @since 1.7
2021 */
2022 public static final UnicodeBlock LATIN_EXTENDED_C =
2023 new UnicodeBlock("LATIN_EXTENDED_C",
2024 "LATIN EXTENDED-C",
2025 "LATINEXTENDED-C");
2026
2027 /**
2028 * Constant for the "Coptic" Unicode character block.
2029 * @since 1.7
2030 */
2031 public static final UnicodeBlock COPTIC =
2032 new UnicodeBlock("COPTIC");
2033
2034 /**
2035 * Constant for the "Georgian Supplement" Unicode character block.
2036 * @since 1.7
2037 */
2038 public static final UnicodeBlock GEORGIAN_SUPPLEMENT =
2039 new UnicodeBlock("GEORGIAN_SUPPLEMENT",
2040 "GEORGIAN SUPPLEMENT",
2041 "GEORGIANSUPPLEMENT");
2042
2043 /**
2044 * Constant for the "Tifinagh" Unicode character block.
2045 * @since 1.7
2046 */
2047 public static final UnicodeBlock TIFINAGH =
2048 new UnicodeBlock("TIFINAGH");
2049
2050 /**
2051 * Constant for the "Ethiopic Extended" Unicode character block.
2052 * @since 1.7
2053 */
2054 public static final UnicodeBlock ETHIOPIC_EXTENDED =
2055 new UnicodeBlock("ETHIOPIC_EXTENDED",
2056 "ETHIOPIC EXTENDED",
2057 "ETHIOPICEXTENDED");
2058
2059 /**
2060 * Constant for the "Cyrillic Extended-A" Unicode character block.
2061 * @since 1.7
2062 */
2063 public static final UnicodeBlock CYRILLIC_EXTENDED_A =
2064 new UnicodeBlock("CYRILLIC_EXTENDED_A",
2065 "CYRILLIC EXTENDED-A",
2066 "CYRILLICEXTENDED-A");
2067
2068 /**
2069 * Constant for the "Supplemental Punctuation" Unicode character block.
2070 * @since 1.7
2071 */
2072 public static final UnicodeBlock SUPPLEMENTAL_PUNCTUATION =
2073 new UnicodeBlock("SUPPLEMENTAL_PUNCTUATION",
2074 "SUPPLEMENTAL PUNCTUATION",
2075 "SUPPLEMENTALPUNCTUATION");
2076
2077 /**
2078 * Constant for the "CJK Strokes" Unicode character block.
2079 * @since 1.7
2080 */
2081 public static final UnicodeBlock CJK_STROKES =
2082 new UnicodeBlock("CJK_STROKES",
2083 "CJK STROKES",
2084 "CJKSTROKES");
2085
2086 /**
2087 * Constant for the "Lisu" Unicode character block.
2088 * @since 1.7
2089 */
2090 public static final UnicodeBlock LISU =
2091 new UnicodeBlock("LISU");
2092
2093 /**
2094 * Constant for the "Vai" Unicode character block.
2095 * @since 1.7
2096 */
2097 public static final UnicodeBlock VAI =
2098 new UnicodeBlock("VAI");
2099
2100 /**
2101 * Constant for the "Cyrillic Extended-B" Unicode character block.
2102 * @since 1.7
2103 */
2104 public static final UnicodeBlock CYRILLIC_EXTENDED_B =
2105 new UnicodeBlock("CYRILLIC_EXTENDED_B",
2106 "CYRILLIC EXTENDED-B",
2107 "CYRILLICEXTENDED-B");
2108
2109 /**
2110 * Constant for the "Bamum" Unicode character block.
2111 * @since 1.7
2112 */
2113 public static final UnicodeBlock BAMUM =
2114 new UnicodeBlock("BAMUM");
2115
2116 /**
2117 * Constant for the "Modifier Tone Letters" Unicode character block.
2118 * @since 1.7
2119 */
2120 public static final UnicodeBlock MODIFIER_TONE_LETTERS =
2121 new UnicodeBlock("MODIFIER_TONE_LETTERS",
2122 "MODIFIER TONE LETTERS",
2123 "MODIFIERTONELETTERS");
2124
2125 /**
2126 * Constant for the "Latin Extended-D" Unicode character block.
2127 * @since 1.7
2128 */
2129 public static final UnicodeBlock LATIN_EXTENDED_D =
2130 new UnicodeBlock("LATIN_EXTENDED_D",
2131 "LATIN EXTENDED-D",
2132 "LATINEXTENDED-D");
2133
2134 /**
2135 * Constant for the "Syloti Nagri" Unicode character block.
2136 * @since 1.7
2137 */
2138 public static final UnicodeBlock SYLOTI_NAGRI =
2139 new UnicodeBlock("SYLOTI_NAGRI",
2140 "SYLOTI NAGRI",
2141 "SYLOTINAGRI");
2142
2143 /**
2144 * Constant for the "Common Indic Number Forms" Unicode character block.
2145 * @since 1.7
2146 */
2147 public static final UnicodeBlock COMMON_INDIC_NUMBER_FORMS =
2148 new UnicodeBlock("COMMON_INDIC_NUMBER_FORMS",
2149 "COMMON INDIC NUMBER FORMS",
2150 "COMMONINDICNUMBERFORMS");
2151
2152 /**
2153 * Constant for the "Phags-pa" Unicode character block.
2154 * @since 1.7
2155 */
2156 public static final UnicodeBlock PHAGS_PA =
2157 new UnicodeBlock("PHAGS_PA",
2158 "PHAGS-PA");
2159
2160 /**
2161 * Constant for the "Saurashtra" Unicode character block.
2162 * @since 1.7
2163 */
2164 public static final UnicodeBlock SAURASHTRA =
2165 new UnicodeBlock("SAURASHTRA");
2166
2167 /**
2168 * Constant for the "Devanagari Extended" Unicode character block.
2169 * @since 1.7
2170 */
2171 public static final UnicodeBlock DEVANAGARI_EXTENDED =
2172 new UnicodeBlock("DEVANAGARI_EXTENDED",
2173 "DEVANAGARI EXTENDED",
2174 "DEVANAGARIEXTENDED");
2175
2176 /**
2177 * Constant for the "Kayah Li" Unicode character block.
2178 * @since 1.7
2179 */
2180 public static final UnicodeBlock KAYAH_LI =
2181 new UnicodeBlock("KAYAH_LI",
2182 "KAYAH LI",
2183 "KAYAHLI");
2184
2185 /**
2186 * Constant for the "Rejang" Unicode character block.
2187 * @since 1.7
2188 */
2189 public static final UnicodeBlock REJANG =
2190 new UnicodeBlock("REJANG");
2191
2192 /**
2193 * Constant for the "Hangul Jamo Extended-A" Unicode character block.
2194 * @since 1.7
2195 */
2196 public static final UnicodeBlock HANGUL_JAMO_EXTENDED_A =
2197 new UnicodeBlock("HANGUL_JAMO_EXTENDED_A",
2198 "HANGUL JAMO EXTENDED-A",
2199 "HANGULJAMOEXTENDED-A");
2200
2201 /**
2202 * Constant for the "Javanese" Unicode character block.
2203 * @since 1.7
2204 */
2205 public static final UnicodeBlock JAVANESE =
2206 new UnicodeBlock("JAVANESE");
2207
2208 /**
2209 * Constant for the "Cham" Unicode character block.
2210 * @since 1.7
2211 */
2212 public static final UnicodeBlock CHAM =
2213 new UnicodeBlock("CHAM");
2214
2215 /**
2216 * Constant for the "Myanmar Extended-A" Unicode character block.
2217 * @since 1.7
2218 */
2219 public static final UnicodeBlock MYANMAR_EXTENDED_A =
2220 new UnicodeBlock("MYANMAR_EXTENDED_A",
2221 "MYANMAR EXTENDED-A",
2222 "MYANMAREXTENDED-A");
2223
2224 /**
2225 * Constant for the "Tai Viet" Unicode character block.
2226 * @since 1.7
2227 */
2228 public static final UnicodeBlock TAI_VIET =
2229 new UnicodeBlock("TAI_VIET",
2230 "TAI VIET",
2231 "TAIVIET");
2232
2233 /**
2234 * Constant for the "Ethiopic Extended-A" Unicode character block.
2235 * @since 1.7
2236 */
2237 public static final UnicodeBlock ETHIOPIC_EXTENDED_A =
2238 new UnicodeBlock("ETHIOPIC_EXTENDED_A",
2239 "ETHIOPIC EXTENDED-A",
2240 "ETHIOPICEXTENDED-A");
2241
2242 /**
2243 * Constant for the "Meetei Mayek" Unicode character block.
2244 * @since 1.7
2245 */
2246 public static final UnicodeBlock MEETEI_MAYEK =
2247 new UnicodeBlock("MEETEI_MAYEK",
2248 "MEETEI MAYEK",
2249 "MEETEIMAYEK");
2250
2251 /**
2252 * Constant for the "Hangul Jamo Extended-B" Unicode character block.
2253 * @since 1.7
2254 */
2255 public static final UnicodeBlock HANGUL_JAMO_EXTENDED_B =
2256 new UnicodeBlock("HANGUL_JAMO_EXTENDED_B",
2257 "HANGUL JAMO EXTENDED-B",
2258 "HANGULJAMOEXTENDED-B");
2259
2260 /**
2261 * Constant for the "Vertical Forms" Unicode character block.
2262 * @since 1.7
2263 */
2264 public static final UnicodeBlock VERTICAL_FORMS =
2265 new UnicodeBlock("VERTICAL_FORMS",
2266 "VERTICAL FORMS",
2267 "VERTICALFORMS");
2268
2269 /**
2270 * Constant for the "Ancient Greek Numbers" Unicode character block.
2271 * @since 1.7
2272 */
2273 public static final UnicodeBlock ANCIENT_GREEK_NUMBERS =
2274 new UnicodeBlock("ANCIENT_GREEK_NUMBERS",
2275 "ANCIENT GREEK NUMBERS",
2276 "ANCIENTGREEKNUMBERS");
2277
2278 /**
2279 * Constant for the "Ancient Symbols" Unicode character block.
2280 * @since 1.7
2281 */
2282 public static final UnicodeBlock ANCIENT_SYMBOLS =
2283 new UnicodeBlock("ANCIENT_SYMBOLS",
2284 "ANCIENT SYMBOLS",
2285 "ANCIENTSYMBOLS");
2286
2287 /**
2288 * Constant for the "Phaistos Disc" Unicode character block.
2289 * @since 1.7
2290 */
2291 public static final UnicodeBlock PHAISTOS_DISC =
2292 new UnicodeBlock("PHAISTOS_DISC",
2293 "PHAISTOS DISC",
2294 "PHAISTOSDISC");
2295
2296 /**
2297 * Constant for the "Lycian" Unicode character block.
2298 * @since 1.7
2299 */
2300 public static final UnicodeBlock LYCIAN =
2301 new UnicodeBlock("LYCIAN");
2302
2303 /**
2304 * Constant for the "Carian" Unicode character block.
2305 * @since 1.7
2306 */
2307 public static final UnicodeBlock CARIAN =
2308 new UnicodeBlock("CARIAN");
2309
2310 /**
2311 * Constant for the "Old Persian" Unicode character block.
2312 * @since 1.7
2313 */
2314 public static final UnicodeBlock OLD_PERSIAN =
2315 new UnicodeBlock("OLD_PERSIAN",
2316 "OLD PERSIAN",
2317 "OLDPERSIAN");
2318
2319 /**
2320 * Constant for the "Imperial Aramaic" Unicode character block.
2321 * @since 1.7
2322 */
2323 public static final UnicodeBlock IMPERIAL_ARAMAIC =
2324 new UnicodeBlock("IMPERIAL_ARAMAIC",
2325 "IMPERIAL ARAMAIC",
2326 "IMPERIALARAMAIC");
2327
2328 /**
2329 * Constant for the "Phoenician" Unicode character block.
2330 * @since 1.7
2331 */
2332 public static final UnicodeBlock PHOENICIAN =
2333 new UnicodeBlock("PHOENICIAN");
2334
2335 /**
2336 * Constant for the "Lydian" Unicode character block.
2337 * @since 1.7
2338 */
2339 public static final UnicodeBlock LYDIAN =
2340 new UnicodeBlock("LYDIAN");
2341
2342 /**
2343 * Constant for the "Kharoshthi" Unicode character block.
2344 * @since 1.7
2345 */
2346 public static final UnicodeBlock KHAROSHTHI =
2347 new UnicodeBlock("KHAROSHTHI");
2348
2349 /**
2350 * Constant for the "Old South Arabian" Unicode character block.
2351 * @since 1.7
2352 */
2353 public static final UnicodeBlock OLD_SOUTH_ARABIAN =
2354 new UnicodeBlock("OLD_SOUTH_ARABIAN",
2355 "OLD SOUTH ARABIAN",
2356 "OLDSOUTHARABIAN");
2357
2358 /**
2359 * Constant for the "Avestan" Unicode character block.
2360 * @since 1.7
2361 */
2362 public static final UnicodeBlock AVESTAN =
2363 new UnicodeBlock("AVESTAN");
2364
2365 /**
2366 * Constant for the "Inscriptional Parthian" Unicode character block.
2367 * @since 1.7
2368 */
2369 public static final UnicodeBlock INSCRIPTIONAL_PARTHIAN =
2370 new UnicodeBlock("INSCRIPTIONAL_PARTHIAN",
2371 "INSCRIPTIONAL PARTHIAN",
2372 "INSCRIPTIONALPARTHIAN");
2373
2374 /**
2375 * Constant for the "Inscriptional Pahlavi" Unicode character block.
2376 * @since 1.7
2377 */
2378 public static final UnicodeBlock INSCRIPTIONAL_PAHLAVI =
2379 new UnicodeBlock("INSCRIPTIONAL_PAHLAVI",
2380 "INSCRIPTIONAL PAHLAVI",
2381 "INSCRIPTIONALPAHLAVI");
2382
2383 /**
2384 * Constant for the "Old Turkic" Unicode character block.
2385 * @since 1.7
2386 */
2387 public static final UnicodeBlock OLD_TURKIC =
2388 new UnicodeBlock("OLD_TURKIC",
2389 "OLD TURKIC",
2390 "OLDTURKIC");
2391
2392 /**
2393 * Constant for the "Rumi Numeral Symbols" Unicode character block.
2394 * @since 1.7
2395 */
2396 public static final UnicodeBlock RUMI_NUMERAL_SYMBOLS =
2397 new UnicodeBlock("RUMI_NUMERAL_SYMBOLS",
2398 "RUMI NUMERAL SYMBOLS",
2399 "RUMINUMERALSYMBOLS");
2400
2401 /**
2402 * Constant for the "Brahmi" Unicode character block.
2403 * @since 1.7
2404 */
2405 public static final UnicodeBlock BRAHMI =
2406 new UnicodeBlock("BRAHMI");
2407
2408 /**
2409 * Constant for the "Kaithi" Unicode character block.
2410 * @since 1.7
2411 */
2412 public static final UnicodeBlock KAITHI =
2413 new UnicodeBlock("KAITHI");
2414
2415 /**
2416 * Constant for the "Cuneiform" Unicode character block.
2417 * @since 1.7
2418 */
2419 public static final UnicodeBlock CUNEIFORM =
2420 new UnicodeBlock("CUNEIFORM");
2421
2422 /**
2423 * Constant for the "Cuneiform Numbers and Punctuation" Unicode
2424 * character block.
2425 * @since 1.7
2426 */
2427 public static final UnicodeBlock CUNEIFORM_NUMBERS_AND_PUNCTUATION =
2428 new UnicodeBlock("CUNEIFORM_NUMBERS_AND_PUNCTUATION",
2429 "CUNEIFORM NUMBERS AND PUNCTUATION",
2430 "CUNEIFORMNUMBERSANDPUNCTUATION");
2431
2432 /**
2433 * Constant for the "Egyptian Hieroglyphs" Unicode character block.
2434 * @since 1.7
2435 */
2436 public static final UnicodeBlock EGYPTIAN_HIEROGLYPHS =
2437 new UnicodeBlock("EGYPTIAN_HIEROGLYPHS",
2438 "EGYPTIAN HIEROGLYPHS",
2439 "EGYPTIANHIEROGLYPHS");
2440
2441 /**
2442 * Constant for the "Bamum Supplement" Unicode character block.
2443 * @since 1.7
2444 */
2445 public static final UnicodeBlock BAMUM_SUPPLEMENT =
2446 new UnicodeBlock("BAMUM_SUPPLEMENT",
2447 "BAMUM SUPPLEMENT",
2448 "BAMUMSUPPLEMENT");
2449
2450 /**
2451 * Constant for the "Kana Supplement" Unicode character block.
2452 * @since 1.7
2453 */
2454 public static final UnicodeBlock KANA_SUPPLEMENT =
2455 new UnicodeBlock("KANA_SUPPLEMENT",
2456 "KANA SUPPLEMENT",
2457 "KANASUPPLEMENT");
2458
2459 /**
2460 * Constant for the "Ancient Greek Musical Notation" Unicode character
2461 * block.
2462 * @since 1.7
2463 */
2464 public static final UnicodeBlock ANCIENT_GREEK_MUSICAL_NOTATION =
2465 new UnicodeBlock("ANCIENT_GREEK_MUSICAL_NOTATION",
2466 "ANCIENT GREEK MUSICAL NOTATION",
2467 "ANCIENTGREEKMUSICALNOTATION");
2468
2469 /**
2470 * Constant for the "Counting Rod Numerals" Unicode character block.
2471 * @since 1.7
2472 */
2473 public static final UnicodeBlock COUNTING_ROD_NUMERALS =
2474 new UnicodeBlock("COUNTING_ROD_NUMERALS",
2475 "COUNTING ROD NUMERALS",
2476 "COUNTINGRODNUMERALS");
2477
2478 /**
2479 * Constant for the "Mahjong Tiles" Unicode character block.
2480 * @since 1.7
2481 */
2482 public static final UnicodeBlock MAHJONG_TILES =
2483 new UnicodeBlock("MAHJONG_TILES",
2484 "MAHJONG TILES",
2485 "MAHJONGTILES");
2486
2487 /**
2488 * Constant for the "Domino Tiles" Unicode character block.
2489 * @since 1.7
2490 */
2491 public static final UnicodeBlock DOMINO_TILES =
2492 new UnicodeBlock("DOMINO_TILES",
2493 "DOMINO TILES",
2494 "DOMINOTILES");
2495
2496 /**
2497 * Constant for the "Playing Cards" Unicode character block.
2498 * @since 1.7
2499 */
2500 public static final UnicodeBlock PLAYING_CARDS =
2501 new UnicodeBlock("PLAYING_CARDS",
2502 "PLAYING CARDS",
2503 "PLAYINGCARDS");
2504
2505 /**
2506 * Constant for the "Enclosed Alphanumeric Supplement" Unicode character
2507 * block.
2508 * @since 1.7
2509 */
2510 public static final UnicodeBlock ENCLOSED_ALPHANUMERIC_SUPPLEMENT =
2511 new UnicodeBlock("ENCLOSED_ALPHANUMERIC_SUPPLEMENT",
2512 "ENCLOSED ALPHANUMERIC SUPPLEMENT",
2513 "ENCLOSEDALPHANUMERICSUPPLEMENT");
2514
2515 /**
2516 * Constant for the "Enclosed Ideographic Supplement" Unicode character
2517 * block.
2518 * @since 1.7
2519 */
2520 public static final UnicodeBlock ENCLOSED_IDEOGRAPHIC_SUPPLEMENT =
2521 new UnicodeBlock("ENCLOSED_IDEOGRAPHIC_SUPPLEMENT",
2522 "ENCLOSED IDEOGRAPHIC SUPPLEMENT",
2523 "ENCLOSEDIDEOGRAPHICSUPPLEMENT");
2524
2525 /**
2526 * Constant for the "Miscellaneous Symbols And Pictographs" Unicode
2527 * character block.
2528 * @since 1.7
2529 */
2530 public static final UnicodeBlock MISCELLANEOUS_SYMBOLS_AND_PICTOGRAPHS =
2531 new UnicodeBlock("MISCELLANEOUS_SYMBOLS_AND_PICTOGRAPHS",
2532 "MISCELLANEOUS SYMBOLS AND PICTOGRAPHS",
2533 "MISCELLANEOUSSYMBOLSANDPICTOGRAPHS");
2534
2535 /**
2536 * Constant for the "Emoticons" Unicode character block.
2537 * @since 1.7
2538 */
2539 public static final UnicodeBlock EMOTICONS =
2540 new UnicodeBlock("EMOTICONS");
2541
2542 /**
2543 * Constant for the "Transport And Map Symbols" Unicode character block.
2544 * @since 1.7
2545 */
2546 public static final UnicodeBlock TRANSPORT_AND_MAP_SYMBOLS =
2547 new UnicodeBlock("TRANSPORT_AND_MAP_SYMBOLS",
2548 "TRANSPORT AND MAP SYMBOLS",
2549 "TRANSPORTANDMAPSYMBOLS");
2550
2551 /**
2552 * Constant for the "Alchemical Symbols" Unicode character block.
2553 * @since 1.7
2554 */
2555 public static final UnicodeBlock ALCHEMICAL_SYMBOLS =
2556 new UnicodeBlock("ALCHEMICAL_SYMBOLS",
2557 "ALCHEMICAL SYMBOLS",
2558 "ALCHEMICALSYMBOLS");
2559
2560 /**
2561 * Constant for the "CJK Unified Ideographs Extension C" Unicode
2562 * character block.
2563 * @since 1.7
2564 */
2565 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_C =
2566 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_C",
2567 "CJK UNIFIED IDEOGRAPHS EXTENSION C",
2568 "CJKUNIFIEDIDEOGRAPHSEXTENSIONC");
2569
2570 /**
2571 * Constant for the "CJK Unified Ideographs Extension D" Unicode
2572 * character block.
2573 * @since 1.7
2574 */
2575 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_D =
2576 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_D",
2577 "CJK UNIFIED IDEOGRAPHS EXTENSION D",
2578 "CJKUNIFIEDIDEOGRAPHSEXTENSIOND");
2579
2580 /**
2581 * Constant for the "Arabic Extended-A" Unicode character block.
2582 * @since 1.8
2583 */
2584 public static final UnicodeBlock ARABIC_EXTENDED_A =
2585 new UnicodeBlock("ARABIC_EXTENDED_A",
2586 "ARABIC EXTENDED-A",
2587 "ARABICEXTENDED-A");
2588
2589 /**
2590 * Constant for the "Sundanese Supplement" Unicode character block.
2591 * @since 1.8
2592 */
2593 public static final UnicodeBlock SUNDANESE_SUPPLEMENT =
2594 new UnicodeBlock("SUNDANESE_SUPPLEMENT",
2595 "SUNDANESE SUPPLEMENT",
2596 "SUNDANESESUPPLEMENT");
2597
2598 /**
2599 * Constant for the "Meetei Mayek Extensions" Unicode character block.
2600 * @since 1.8
2601 */
2602 public static final UnicodeBlock MEETEI_MAYEK_EXTENSIONS =
2603 new UnicodeBlock("MEETEI_MAYEK_EXTENSIONS",
2604 "MEETEI MAYEK EXTENSIONS",
2605 "MEETEIMAYEKEXTENSIONS");
2606
2607 /**
2608 * Constant for the "Meroitic Hieroglyphs" Unicode character block.
2609 * @since 1.8
2610 */
2611 public static final UnicodeBlock MEROITIC_HIEROGLYPHS =
2612 new UnicodeBlock("MEROITIC_HIEROGLYPHS",
2613 "MEROITIC HIEROGLYPHS",
2614 "MEROITICHIEROGLYPHS");
2615
2616 /**
2617 * Constant for the "Meroitic Cursive" Unicode character block.
2618 * @since 1.8
2619 */
2620 public static final UnicodeBlock MEROITIC_CURSIVE =
2621 new UnicodeBlock("MEROITIC_CURSIVE",
2622 "MEROITIC CURSIVE",
2623 "MEROITICCURSIVE");
2624
2625 /**
2626 * Constant for the "Sora Sompeng" Unicode character block.
2627 * @since 1.8
2628 */
2629 public static final UnicodeBlock SORA_SOMPENG =
2630 new UnicodeBlock("SORA_SOMPENG",
2631 "SORA SOMPENG",
2632 "SORASOMPENG");
2633
2634 /**
2635 * Constant for the "Chakma" Unicode character block.
2636 * @since 1.8
2637 */
2638 public static final UnicodeBlock CHAKMA =
2639 new UnicodeBlock("CHAKMA");
2640
2641 /**
2642 * Constant for the "Sharada" Unicode character block.
2643 * @since 1.8
2644 */
2645 public static final UnicodeBlock SHARADA =
2646 new UnicodeBlock("SHARADA");
2647
2648 /**
2649 * Constant for the "Takri" Unicode character block.
2650 * @since 1.8
2651 */
2652 public static final UnicodeBlock TAKRI =
2653 new UnicodeBlock("TAKRI");
2654
2655 /**
2656 * Constant for the "Miao" Unicode character block.
2657 * @since 1.8
2658 */
2659 public static final UnicodeBlock MIAO =
2660 new UnicodeBlock("MIAO");
2661
2662 /**
2663 * Constant for the "Arabic Mathematical Alphabetic Symbols" Unicode
2664 * character block.
2665 * @since 1.8
2666 */
2667 public static final UnicodeBlock ARABIC_MATHEMATICAL_ALPHABETIC_SYMBOLS =
2668 new UnicodeBlock("ARABIC_MATHEMATICAL_ALPHABETIC_SYMBOLS",
2669 "ARABIC MATHEMATICAL ALPHABETIC SYMBOLS",
2670 "ARABICMATHEMATICALALPHABETICSYMBOLS");
2671
2672 /**
2673 * Constant for the "Combining Diacritical Marks Extended" Unicode
2674 * character block.
2675 * @since 9
2676 */
2677 public static final UnicodeBlock COMBINING_DIACRITICAL_MARKS_EXTENDED =
2678 new UnicodeBlock("COMBINING_DIACRITICAL_MARKS_EXTENDED",
2679 "COMBINING DIACRITICAL MARKS EXTENDED",
2680 "COMBININGDIACRITICALMARKSEXTENDED");
2681
2682 /**
2683 * Constant for the "Myanmar Extended-B" Unicode character block.
2684 * @since 9
2685 */
2686 public static final UnicodeBlock MYANMAR_EXTENDED_B =
2687 new UnicodeBlock("MYANMAR_EXTENDED_B",
2688 "MYANMAR EXTENDED-B",
2689 "MYANMAREXTENDED-B");
2690
2691 /**
2692 * Constant for the "Latin Extended-E" Unicode character block.
2693 * @since 9
2694 */
2695 public static final UnicodeBlock LATIN_EXTENDED_E =
2696 new UnicodeBlock("LATIN_EXTENDED_E",
2697 "LATIN EXTENDED-E",
2698 "LATINEXTENDED-E");
2699
2700 /**
2701 * Constant for the "Coptic Epact Numbers" Unicode character block.
2702 * @since 9
2703 */
2704 public static final UnicodeBlock COPTIC_EPACT_NUMBERS =
2705 new UnicodeBlock("COPTIC_EPACT_NUMBERS",
2706 "COPTIC EPACT NUMBERS",
2707 "COPTICEPACTNUMBERS");
2708
2709 /**
2710 * Constant for the "Old Permic" Unicode character block.
2711 * @since 9
2712 */
2713 public static final UnicodeBlock OLD_PERMIC =
2714 new UnicodeBlock("OLD_PERMIC",
2715 "OLD PERMIC",
2716 "OLDPERMIC");
2717
2718 /**
2719 * Constant for the "Elbasan" Unicode character block.
2720 * @since 9
2721 */
2722 public static final UnicodeBlock ELBASAN =
2723 new UnicodeBlock("ELBASAN");
2724
2725 /**
2726 * Constant for the "Caucasian Albanian" Unicode character block.
2727 * @since 9
2728 */
2729 public static final UnicodeBlock CAUCASIAN_ALBANIAN =
2730 new UnicodeBlock("CAUCASIAN_ALBANIAN",
2731 "CAUCASIAN ALBANIAN",
2732 "CAUCASIANALBANIAN");
2733
2734 /**
2735 * Constant for the "Linear A" Unicode character block.
2736 * @since 9
2737 */
2738 public static final UnicodeBlock LINEAR_A =
2739 new UnicodeBlock("LINEAR_A",
2740 "LINEAR A",
2741 "LINEARA");
2742
2743 /**
2744 * Constant for the "Palmyrene" Unicode character block.
2745 * @since 9
2746 */
2747 public static final UnicodeBlock PALMYRENE =
2748 new UnicodeBlock("PALMYRENE");
2749
2750 /**
2751 * Constant for the "Nabataean" Unicode character block.
2752 * @since 9
2753 */
2754 public static final UnicodeBlock NABATAEAN =
2755 new UnicodeBlock("NABATAEAN");
2756
2757 /**
2758 * Constant for the "Old North Arabian" Unicode character block.
2759 * @since 9
2760 */
2761 public static final UnicodeBlock OLD_NORTH_ARABIAN =
2762 new UnicodeBlock("OLD_NORTH_ARABIAN",
2763 "OLD NORTH ARABIAN",
2764 "OLDNORTHARABIAN");
2765
2766 /**
2767 * Constant for the "Manichaean" Unicode character block.
2768 * @since 9
2769 */
2770 public static final UnicodeBlock MANICHAEAN =
2771 new UnicodeBlock("MANICHAEAN");
2772
2773 /**
2774 * Constant for the "Psalter Pahlavi" Unicode character block.
2775 * @since 9
2776 */
2777 public static final UnicodeBlock PSALTER_PAHLAVI =
2778 new UnicodeBlock("PSALTER_PAHLAVI",
2779 "PSALTER PAHLAVI",
2780 "PSALTERPAHLAVI");
2781
2782 /**
2783 * Constant for the "Mahajani" Unicode character block.
2784 * @since 9
2785 */
2786 public static final UnicodeBlock MAHAJANI =
2787 new UnicodeBlock("MAHAJANI");
2788
2789 /**
2790 * Constant for the "Sinhala Archaic Numbers" Unicode character block.
2791 * @since 9
2792 */
2793 public static final UnicodeBlock SINHALA_ARCHAIC_NUMBERS =
2794 new UnicodeBlock("SINHALA_ARCHAIC_NUMBERS",
2795 "SINHALA ARCHAIC NUMBERS",
2796 "SINHALAARCHAICNUMBERS");
2797
2798 /**
2799 * Constant for the "Khojki" Unicode character block.
2800 * @since 9
2801 */
2802 public static final UnicodeBlock KHOJKI =
2803 new UnicodeBlock("KHOJKI");
2804
2805 /**
2806 * Constant for the "Khudawadi" Unicode character block.
2807 * @since 9
2808 */
2809 public static final UnicodeBlock KHUDAWADI =
2810 new UnicodeBlock("KHUDAWADI");
2811
2812 /**
2813 * Constant for the "Grantha" Unicode character block.
2814 * @since 9
2815 */
2816 public static final UnicodeBlock GRANTHA =
2817 new UnicodeBlock("GRANTHA");
2818
2819 /**
2820 * Constant for the "Tirhuta" Unicode character block.
2821 * @since 9
2822 */
2823 public static final UnicodeBlock TIRHUTA =
2824 new UnicodeBlock("TIRHUTA");
2825
2826 /**
2827 * Constant for the "Siddham" Unicode character block.
2828 * @since 9
2829 */
2830 public static final UnicodeBlock SIDDHAM =
2831 new UnicodeBlock("SIDDHAM");
2832
2833 /**
2834 * Constant for the "Modi" Unicode character block.
2835 * @since 9
2836 */
2837 public static final UnicodeBlock MODI =
2838 new UnicodeBlock("MODI");
2839
2840 /**
2841 * Constant for the "Warang Citi" Unicode character block.
2842 * @since 9
2843 */
2844 public static final UnicodeBlock WARANG_CITI =
2845 new UnicodeBlock("WARANG_CITI",
2846 "WARANG CITI",
2847 "WARANGCITI");
2848
2849 /**
2850 * Constant for the "Pau Cin Hau" Unicode character block.
2851 * @since 9
2852 */
2853 public static final UnicodeBlock PAU_CIN_HAU =
2854 new UnicodeBlock("PAU_CIN_HAU",
2855 "PAU CIN HAU",
2856 "PAUCINHAU");
2857
2858 /**
2859 * Constant for the "Mro" Unicode character block.
2860 * @since 9
2861 */
2862 public static final UnicodeBlock MRO =
2863 new UnicodeBlock("MRO");
2864
2865 /**
2866 * Constant for the "Bassa Vah" Unicode character block.
2867 * @since 9
2868 */
2869 public static final UnicodeBlock BASSA_VAH =
2870 new UnicodeBlock("BASSA_VAH",
2871 "BASSA VAH",
2872 "BASSAVAH");
2873
2874 /**
2875 * Constant for the "Pahawh Hmong" Unicode character block.
2876 * @since 9
2877 */
2878 public static final UnicodeBlock PAHAWH_HMONG =
2879 new UnicodeBlock("PAHAWH_HMONG",
2880 "PAHAWH HMONG",
2881 "PAHAWHHMONG");
2882
2883 /**
2884 * Constant for the "Duployan" Unicode character block.
2885 * @since 9
2886 */
2887 public static final UnicodeBlock DUPLOYAN =
2888 new UnicodeBlock("DUPLOYAN");
2889
2890 /**
2891 * Constant for the "Shorthand Format Controls" Unicode character block.
2892 * @since 9
2893 */
2894 public static final UnicodeBlock SHORTHAND_FORMAT_CONTROLS =
2895 new UnicodeBlock("SHORTHAND_FORMAT_CONTROLS",
2896 "SHORTHAND FORMAT CONTROLS",
2897 "SHORTHANDFORMATCONTROLS");
2898
2899 /**
2900 * Constant for the "Mende Kikakui" Unicode character block.
2901 * @since 9
2902 */
2903 public static final UnicodeBlock MENDE_KIKAKUI =
2904 new UnicodeBlock("MENDE_KIKAKUI",
2905 "MENDE KIKAKUI",
2906 "MENDEKIKAKUI");
2907
2908 /**
2909 * Constant for the "Ornamental Dingbats" Unicode character block.
2910 * @since 9
2911 */
2912 public static final UnicodeBlock ORNAMENTAL_DINGBATS =
2913 new UnicodeBlock("ORNAMENTAL_DINGBATS",
2914 "ORNAMENTAL DINGBATS",
2915 "ORNAMENTALDINGBATS");
2916
2917 /**
2918 * Constant for the "Geometric Shapes Extended" Unicode character block.
2919 * @since 9
2920 */
2921 public static final UnicodeBlock GEOMETRIC_SHAPES_EXTENDED =
2922 new UnicodeBlock("GEOMETRIC_SHAPES_EXTENDED",
2923 "GEOMETRIC SHAPES EXTENDED",
2924 "GEOMETRICSHAPESEXTENDED");
2925
2926 /**
2927 * Constant for the "Supplemental Arrows-C" Unicode character block.
2928 * @since 9
2929 */
2930 public static final UnicodeBlock SUPPLEMENTAL_ARROWS_C =
2931 new UnicodeBlock("SUPPLEMENTAL_ARROWS_C",
2932 "SUPPLEMENTAL ARROWS-C",
2933 "SUPPLEMENTALARROWS-C");
2934
2935 /**
2936 * Constant for the "Cherokee Supplement" Unicode character block.
2937 * @since 9
2938 */
2939 public static final UnicodeBlock CHEROKEE_SUPPLEMENT =
2940 new UnicodeBlock("CHEROKEE_SUPPLEMENT",
2941 "CHEROKEE SUPPLEMENT",
2942 "CHEROKEESUPPLEMENT");
2943
2944 /**
2945 * Constant for the "Hatran" Unicode character block.
2946 * @since 9
2947 */
2948 public static final UnicodeBlock HATRAN =
2949 new UnicodeBlock("HATRAN");
2950
2951 /**
2952 * Constant for the "Old Hungarian" Unicode character block.
2953 * @since 9
2954 */
2955 public static final UnicodeBlock OLD_HUNGARIAN =
2956 new UnicodeBlock("OLD_HUNGARIAN",
2957 "OLD HUNGARIAN",
2958 "OLDHUNGARIAN");
2959
2960 /**
2961 * Constant for the "Multani" Unicode character block.
2962 * @since 9
2963 */
2964 public static final UnicodeBlock MULTANI =
2965 new UnicodeBlock("MULTANI");
2966
2967 /**
2968 * Constant for the "Ahom" Unicode character block.
2969 * @since 9
2970 */
2971 public static final UnicodeBlock AHOM =
2972 new UnicodeBlock("AHOM");
2973
2974 /**
2975 * Constant for the "Early Dynastic Cuneiform" Unicode character block.
2976 * @since 9
2977 */
2978 public static final UnicodeBlock EARLY_DYNASTIC_CUNEIFORM =
2979 new UnicodeBlock("EARLY_DYNASTIC_CUNEIFORM",
2980 "EARLY DYNASTIC CUNEIFORM",
2981 "EARLYDYNASTICCUNEIFORM");
2982
2983 /**
2984 * Constant for the "Anatolian Hieroglyphs" Unicode character block.
2985 * @since 9
2986 */
2987 public static final UnicodeBlock ANATOLIAN_HIEROGLYPHS =
2988 new UnicodeBlock("ANATOLIAN_HIEROGLYPHS",
2989 "ANATOLIAN HIEROGLYPHS",
2990 "ANATOLIANHIEROGLYPHS");
2991
2992 /**
2993 * Constant for the "Sutton SignWriting" Unicode character block.
2994 * @since 9
2995 */
2996 public static final UnicodeBlock SUTTON_SIGNWRITING =
2997 new UnicodeBlock("SUTTON_SIGNWRITING",
2998 "SUTTON SIGNWRITING",
2999 "SUTTONSIGNWRITING");
3000
3001 /**
3002 * Constant for the "Supplemental Symbols and Pictographs" Unicode
3003 * character block.
3004 * @since 9
3005 */
3006 public static final UnicodeBlock SUPPLEMENTAL_SYMBOLS_AND_PICTOGRAPHS =
3007 new UnicodeBlock("SUPPLEMENTAL_SYMBOLS_AND_PICTOGRAPHS",
3008 "SUPPLEMENTAL SYMBOLS AND PICTOGRAPHS",
3009 "SUPPLEMENTALSYMBOLSANDPICTOGRAPHS");
3010
3011 /**
3012 * Constant for the "CJK Unified Ideographs Extension E" Unicode
3013 * character block.
3014 * @since 9
3015 */
3016 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_E =
3017 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_E",
3018 "CJK UNIFIED IDEOGRAPHS EXTENSION E",
3019 "CJKUNIFIEDIDEOGRAPHSEXTENSIONE");
3020
3021 /**
3022 * Constant for the "Syriac Supplement" Unicode
3023 * character block.
3024 * @since 11
3025 */
3026 public static final UnicodeBlock SYRIAC_SUPPLEMENT =
3027 new UnicodeBlock("SYRIAC_SUPPLEMENT",
3028 "SYRIAC SUPPLEMENT",
3029 "SYRIACSUPPLEMENT");
3030
3031 /**
3032 * Constant for the "Cyrillic Extended-C" Unicode
3033 * character block.
3034 * @since 11
3035 */
3036 public static final UnicodeBlock CYRILLIC_EXTENDED_C =
3037 new UnicodeBlock("CYRILLIC_EXTENDED_C",
3038 "CYRILLIC EXTENDED-C",
3039 "CYRILLICEXTENDED-C");
3040
3041 /**
3042 * Constant for the "Osage" Unicode
3043 * character block.
3044 * @since 11
3045 */
3046 public static final UnicodeBlock OSAGE =
3047 new UnicodeBlock("OSAGE");
3048
3049 /**
3050 * Constant for the "Newa" Unicode
3051 * character block.
3052 * @since 11
3053 */
3054 public static final UnicodeBlock NEWA =
3055 new UnicodeBlock("NEWA");
3056
3057 /**
3058 * Constant for the "Mongolian Supplement" Unicode
3059 * character block.
3060 * @since 11
3061 */
3062 public static final UnicodeBlock MONGOLIAN_SUPPLEMENT =
3063 new UnicodeBlock("MONGOLIAN_SUPPLEMENT",
3064 "MONGOLIAN SUPPLEMENT",
3065 "MONGOLIANSUPPLEMENT");
3066
3067 /**
3068 * Constant for the "Marchen" Unicode
3069 * character block.
3070 * @since 11
3071 */
3072 public static final UnicodeBlock MARCHEN =
3073 new UnicodeBlock("MARCHEN");
3074
3075 /**
3076 * Constant for the "Ideographic Symbols and Punctuation" Unicode
3077 * character block.
3078 * @since 11
3079 */
3080 public static final UnicodeBlock IDEOGRAPHIC_SYMBOLS_AND_PUNCTUATION =
3081 new UnicodeBlock("IDEOGRAPHIC_SYMBOLS_AND_PUNCTUATION",
3082 "IDEOGRAPHIC SYMBOLS AND PUNCTUATION",
3083 "IDEOGRAPHICSYMBOLSANDPUNCTUATION");
3084
3085 /**
3086 * Constant for the "Tangut" Unicode
3087 * character block.
3088 * @since 11
3089 */
3090 public static final UnicodeBlock TANGUT =
3091 new UnicodeBlock("TANGUT");
3092
3093 /**
3094 * Constant for the "Tangut Components" Unicode
3095 * character block.
3096 * @since 11
3097 */
3098 public static final UnicodeBlock TANGUT_COMPONENTS =
3099 new UnicodeBlock("TANGUT_COMPONENTS",
3100 "TANGUT COMPONENTS",
3101 "TANGUTCOMPONENTS");
3102
3103 /**
3104 * Constant for the "Kana Extended-A" Unicode
3105 * character block.
3106 * @since 11
3107 */
3108 public static final UnicodeBlock KANA_EXTENDED_A =
3109 new UnicodeBlock("KANA_EXTENDED_A",
3110 "KANA EXTENDED-A",
3111 "KANAEXTENDED-A");
3112 /**
3113 * Constant for the "Glagolitic Supplement" Unicode
3114 * character block.
3115 * @since 11
3116 */
3117 public static final UnicodeBlock GLAGOLITIC_SUPPLEMENT =
3118 new UnicodeBlock("GLAGOLITIC_SUPPLEMENT",
3119 "GLAGOLITIC SUPPLEMENT",
3120 "GLAGOLITICSUPPLEMENT");
3121 /**
3122 * Constant for the "Adlam" Unicode
3123 * character block.
3124 * @since 11
3125 */
3126 public static final UnicodeBlock ADLAM =
3127 new UnicodeBlock("ADLAM");
3128
3129 /**
3130 * Constant for the "Masaram Gondi" Unicode
3131 * character block.
3132 * @since 11
3133 */
3134 public static final UnicodeBlock MASARAM_GONDI =
3135 new UnicodeBlock("MASARAM_GONDI",
3136 "MASARAM GONDI",
3137 "MASARAMGONDI");
3138
3139 /**
3140 * Constant for the "Zanabazar Square" Unicode
3141 * character block.
3142 * @since 11
3143 */
3144 public static final UnicodeBlock ZANABAZAR_SQUARE =
3145 new UnicodeBlock("ZANABAZAR_SQUARE",
3146 "ZANABAZAR SQUARE",
3147 "ZANABAZARSQUARE");
3148
3149 /**
3150 * Constant for the "Nushu" Unicode
3151 * character block.
3152 * @since 11
3153 */
3154 public static final UnicodeBlock NUSHU =
3155 new UnicodeBlock("NUSHU");
3156
3157 /**
3158 * Constant for the "Soyombo" Unicode
3159 * character block.
3160 * @since 11
3161 */
3162 public static final UnicodeBlock SOYOMBO =
3163 new UnicodeBlock("SOYOMBO");
3164
3165 /**
3166 * Constant for the "Bhaiksuki" Unicode
3167 * character block.
3168 * @since 11
3169 */
3170 public static final UnicodeBlock BHAIKSUKI =
3171 new UnicodeBlock("BHAIKSUKI");
3172
3173 /**
3174 * Constant for the "CJK Unified Ideographs Extension F" Unicode
3175 * character block.
3176 * @since 11
3177 */
3178 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_F =
3179 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_F",
3180 "CJK UNIFIED IDEOGRAPHS EXTENSION F",
3181 "CJKUNIFIEDIDEOGRAPHSEXTENSIONF");
3182 /**
3183 * Constant for the "Georgian Extended" Unicode
3184 * character block.
3185 * @since 12
3186 */
3187 public static final UnicodeBlock GEORGIAN_EXTENDED =
3188 new UnicodeBlock("GEORGIAN_EXTENDED",
3189 "GEORGIAN EXTENDED",
3190 "GEORGIANEXTENDED");
3191
3192 /**
3193 * Constant for the "Hanifi Rohingya" Unicode
3194 * character block.
3195 * @since 12
3196 */
3197 public static final UnicodeBlock HANIFI_ROHINGYA =
3198 new UnicodeBlock("HANIFI_ROHINGYA",
3199 "HANIFI ROHINGYA",
3200 "HANIFIROHINGYA");
3201
3202 /**
3203 * Constant for the "Old Sogdian" Unicode
3204 * character block.
3205 * @since 12
3206 */
3207 public static final UnicodeBlock OLD_SOGDIAN =
3208 new UnicodeBlock("OLD_SOGDIAN",
3209 "OLD SOGDIAN",
3210 "OLDSOGDIAN");
3211
3212 /**
3213 * Constant for the "Sogdian" Unicode
3214 * character block.
3215 * @since 12
3216 */
3217 public static final UnicodeBlock SOGDIAN =
3218 new UnicodeBlock("SOGDIAN");
3219
3220 /**
3221 * Constant for the "Dogra" Unicode
3222 * character block.
3223 * @since 12
3224 */
3225 public static final UnicodeBlock DOGRA =
3226 new UnicodeBlock("DOGRA");
3227
3228 /**
3229 * Constant for the "Gunjala Gondi" Unicode
3230 * character block.
3231 * @since 12
3232 */
3233 public static final UnicodeBlock GUNJALA_GONDI =
3234 new UnicodeBlock("GUNJALA_GONDI",
3235 "GUNJALA GONDI",
3236 "GUNJALAGONDI");
3237
3238 /**
3239 * Constant for the "Makasar" Unicode
3240 * character block.
3241 * @since 12
3242 */
3243 public static final UnicodeBlock MAKASAR =
3244 new UnicodeBlock("MAKASAR");
3245
3246 /**
3247 * Constant for the "Medefaidrin" Unicode
3248 * character block.
3249 * @since 12
3250 */
3251 public static final UnicodeBlock MEDEFAIDRIN =
3252 new UnicodeBlock("MEDEFAIDRIN");
3253
3254 /**
3255 * Constant for the "Mayan Numerals" Unicode
3256 * character block.
3257 * @since 12
3258 */
3259 public static final UnicodeBlock MAYAN_NUMERALS =
3260 new UnicodeBlock("MAYAN_NUMERALS",
3261 "MAYAN NUMERALS",
3262 "MAYANNUMERALS");
3263
3264 /**
3265 * Constant for the "Indic Siyaq Numbers" Unicode
3266 * character block.
3267 * @since 12
3268 */
3269 public static final UnicodeBlock INDIC_SIYAQ_NUMBERS =
3270 new UnicodeBlock("INDIC_SIYAQ_NUMBERS",
3271 "INDIC SIYAQ NUMBERS",
3272 "INDICSIYAQNUMBERS");
3273
3274 /**
3275 * Constant for the "Chess Symbols" Unicode
3276 * character block.
3277 * @since 12
3278 */
3279 public static final UnicodeBlock CHESS_SYMBOLS =
3280 new UnicodeBlock("CHESS_SYMBOLS",
3281 "CHESS SYMBOLS",
3282 "CHESSSYMBOLS");
3283
3284 /**
3285 * Constant for the "Elymaic" Unicode
3286 * character block.
3287 * @since 13
3288 */
3289 public static final UnicodeBlock ELYMAIC =
3290 new UnicodeBlock("ELYMAIC");
3291
3292 /**
3293 * Constant for the "Nandinagari" Unicode
3294 * character block.
3295 * @since 13
3296 */
3297 public static final UnicodeBlock NANDINAGARI =
3298 new UnicodeBlock("NANDINAGARI");
3299
3300 /**
3301 * Constant for the "Tamil Supplement" Unicode
3302 * character block.
3303 * @since 13
3304 */
3305 public static final UnicodeBlock TAMIL_SUPPLEMENT =
3306 new UnicodeBlock("TAMIL_SUPPLEMENT",
3307 "TAMIL SUPPLEMENT",
3308 "TAMILSUPPLEMENT");
3309
3310 /**
3311 * Constant for the "Egyptian Hieroglyph Format Controls" Unicode
3312 * character block.
3313 * @since 13
3314 */
3315 public static final UnicodeBlock EGYPTIAN_HIEROGLYPH_FORMAT_CONTROLS =
3316 new UnicodeBlock("EGYPTIAN_HIEROGLYPH_FORMAT_CONTROLS",
3317 "EGYPTIAN HIEROGLYPH FORMAT CONTROLS",
3318 "EGYPTIANHIEROGLYPHFORMATCONTROLS");
3319
3320 /**
3321 * Constant for the "Small Kana Extension" Unicode
3322 * character block.
3323 * @since 13
3324 */
3325 public static final UnicodeBlock SMALL_KANA_EXTENSION =
3326 new UnicodeBlock("SMALL_KANA_EXTENSION",
3327 "SMALL KANA EXTENSION",
3328 "SMALLKANAEXTENSION");
3329
3330 /**
3331 * Constant for the "Nyiakeng Puachue Hmong" Unicode
3332 * character block.
3333 * @since 13
3334 */
3335 public static final UnicodeBlock NYIAKENG_PUACHUE_HMONG =
3336 new UnicodeBlock("NYIAKENG_PUACHUE_HMONG",
3337 "NYIAKENG PUACHUE HMONG",
3338 "NYIAKENGPUACHUEHMONG");
3339
3340 /**
3341 * Constant for the "Wancho" Unicode
3342 * character block.
3343 * @since 13
3344 */
3345 public static final UnicodeBlock WANCHO =
3346 new UnicodeBlock("WANCHO");
3347
3348 /**
3349 * Constant for the "Ottoman Siyaq Numbers" Unicode
3350 * character block.
3351 * @since 13
3352 */
3353 public static final UnicodeBlock OTTOMAN_SIYAQ_NUMBERS =
3354 new UnicodeBlock("OTTOMAN_SIYAQ_NUMBERS",
3355 "OTTOMAN SIYAQ NUMBERS",
3356 "OTTOMANSIYAQNUMBERS");
3357
3358 /**
3359 * Constant for the "Symbols and Pictographs Extended-A" Unicode
3360 * character block.
3361 * @since 13
3362 */
3363 public static final UnicodeBlock SYMBOLS_AND_PICTOGRAPHS_EXTENDED_A =
3364 new UnicodeBlock("SYMBOLS_AND_PICTOGRAPHS_EXTENDED_A",
3365 "SYMBOLS AND PICTOGRAPHS EXTENDED-A",
3366 "SYMBOLSANDPICTOGRAPHSEXTENDED-A");
3367
3368 /**
3369 * Constant for the "Yezidi" Unicode
3370 * character block.
3371 * @since 15
3372 */
3373 public static final UnicodeBlock YEZIDI =
3374 new UnicodeBlock("YEZIDI");
3375
3376 /**
3377 * Constant for the "Chorasmian" Unicode
3378 * character block.
3379 * @since 15
3380 */
3381 public static final UnicodeBlock CHORASMIAN =
3382 new UnicodeBlock("CHORASMIAN");
3383
3384 /**
3385 * Constant for the "Dives Akuru" Unicode
3386 * character block.
3387 * @since 15
3388 */
3389 public static final UnicodeBlock DIVES_AKURU =
3390 new UnicodeBlock("DIVES_AKURU",
3391 "DIVES AKURU",
3392 "DIVESAKURU");
3393
3394 /**
3395 * Constant for the "Lisu Supplement" Unicode
3396 * character block.
3397 * @since 15
3398 */
3399 public static final UnicodeBlock LISU_SUPPLEMENT =
3400 new UnicodeBlock("LISU_SUPPLEMENT",
3401 "LISU SUPPLEMENT",
3402 "LISUSUPPLEMENT");
3403
3404 /**
3405 * Constant for the "Khitan Small Script" Unicode
3406 * character block.
3407 * @since 15
3408 */
3409 public static final UnicodeBlock KHITAN_SMALL_SCRIPT =
3410 new UnicodeBlock("KHITAN_SMALL_SCRIPT",
3411 "KHITAN SMALL SCRIPT",
3412 "KHITANSMALLSCRIPT");
3413
3414 /**
3415 * Constant for the "Tangut Supplement" Unicode
3416 * character block.
3417 * @since 15
3418 */
3419 public static final UnicodeBlock TANGUT_SUPPLEMENT =
3420 new UnicodeBlock("TANGUT_SUPPLEMENT",
3421 "TANGUT SUPPLEMENT",
3422 "TANGUTSUPPLEMENT");
3423
3424 /**
3425 * Constant for the "Symbols for Legacy Computing" Unicode
3426 * character block.
3427 * @since 15
3428 */
3429 public static final UnicodeBlock SYMBOLS_FOR_LEGACY_COMPUTING =
3430 new UnicodeBlock("SYMBOLS_FOR_LEGACY_COMPUTING",
3431 "SYMBOLS FOR LEGACY COMPUTING",
3432 "SYMBOLSFORLEGACYCOMPUTING");
3433
3434 /**
3435 * Constant for the "CJK Unified Ideographs Extension G" Unicode
3436 * character block.
3437 * @since 15
3438 */
3439 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_G =
3440 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_G",
3441 "CJK UNIFIED IDEOGRAPHS EXTENSION G",
3442 "CJKUNIFIEDIDEOGRAPHSEXTENSIONG");
3443
3444 /**
3445 * Constant for the "Arabic Extended-B" Unicode
3446 * character block.
3447 * @since 19
3448 */
3449 public static final UnicodeBlock ARABIC_EXTENDED_B =
3450 new UnicodeBlock("ARABIC_EXTENDED_B",
3451 "ARABIC EXTENDED-B",
3452 "ARABICEXTENDED-B");
3453
3454 /**
3455 * Constant for the "Vithkuqi" Unicode
3456 * character block.
3457 * @since 19
3458 */
3459 public static final UnicodeBlock VITHKUQI =
3460 new UnicodeBlock("VITHKUQI");
3461
3462 /**
3463 * Constant for the "Latin Extended-F" Unicode
3464 * character block.
3465 * @since 19
3466 */
3467 public static final UnicodeBlock LATIN_EXTENDED_F =
3468 new UnicodeBlock("LATIN_EXTENDED_F",
3469 "LATIN EXTENDED-F",
3470 "LATINEXTENDED-F");
3471
3472 /**
3473 * Constant for the "Old Uyghur" Unicode
3474 * character block.
3475 * @since 19
3476 */
3477 public static final UnicodeBlock OLD_UYGHUR =
3478 new UnicodeBlock("OLD_UYGHUR",
3479 "OLD UYGHUR",
3480 "OLDUYGHUR");
3481
3482 /**
3483 * Constant for the "Unified Canadian Aboriginal Syllabics Extended-A" Unicode
3484 * character block.
3485 * @since 19
3486 */
3487 public static final UnicodeBlock UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED_A =
3488 new UnicodeBlock("UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED_A",
3489 "UNIFIED CANADIAN ABORIGINAL SYLLABICS EXTENDED-A",
3490 "UNIFIEDCANADIANABORIGINALSYLLABICSEXTENDED-A");
3491
3492 /**
3493 * Constant for the "Cypro-Minoan" Unicode
3494 * character block.
3495 * @since 19
3496 */
3497 public static final UnicodeBlock CYPRO_MINOAN =
3498 new UnicodeBlock("CYPRO_MINOAN",
3499 "CYPRO-MINOAN",
3500 "CYPRO-MINOAN");
3501
3502 /**
3503 * Constant for the "Tangsa" Unicode
3504 * character block.
3505 * @since 19
3506 */
3507 public static final UnicodeBlock TANGSA =
3508 new UnicodeBlock("TANGSA");
3509
3510 /**
3511 * Constant for the "Kana Extended-B" Unicode
3512 * character block.
3513 * @since 19
3514 */
3515 public static final UnicodeBlock KANA_EXTENDED_B =
3516 new UnicodeBlock("KANA_EXTENDED_B",
3517 "KANA EXTENDED-B",
3518 "KANAEXTENDED-B");
3519
3520 /**
3521 * Constant for the "Znamenny Musical Notation" Unicode
3522 * character block.
3523 * @since 19
3524 */
3525 public static final UnicodeBlock ZNAMENNY_MUSICAL_NOTATION =
3526 new UnicodeBlock("ZNAMENNY_MUSICAL_NOTATION",
3527 "ZNAMENNY MUSICAL NOTATION",
3528 "ZNAMENNYMUSICALNOTATION");
3529
3530 /**
3531 * Constant for the "Latin Extended-G" Unicode
3532 * character block.
3533 * @since 19
3534 */
3535 public static final UnicodeBlock LATIN_EXTENDED_G =
3536 new UnicodeBlock("LATIN_EXTENDED_G",
3537 "LATIN EXTENDED-G",
3538 "LATINEXTENDED-G");
3539
3540 /**
3541 * Constant for the "Toto" Unicode
3542 * character block.
3543 * @since 19
3544 */
3545 public static final UnicodeBlock TOTO =
3546 new UnicodeBlock("TOTO");
3547
3548 /**
3549 * Constant for the "Ethiopic Extended-B" Unicode
3550 * character block.
3551 * @since 19
3552 */
3553 public static final UnicodeBlock ETHIOPIC_EXTENDED_B =
3554 new UnicodeBlock("ETHIOPIC_EXTENDED_B",
3555 "ETHIOPIC EXTENDED-B",
3556 "ETHIOPICEXTENDED-B");
3557
3558 /**
3559 * Constant for the "Arabic Extended-C" Unicode
3560 * character block.
3561 * @since 20
3562 */
3563 public static final UnicodeBlock ARABIC_EXTENDED_C =
3564 new UnicodeBlock("ARABIC_EXTENDED_C",
3565 "ARABIC EXTENDED-C",
3566 "ARABICEXTENDED-C");
3567
3568 /**
3569 * Constant for the "Devanagari Extended-A" Unicode
3570 * character block.
3571 * @since 20
3572 */
3573 public static final UnicodeBlock DEVANAGARI_EXTENDED_A =
3574 new UnicodeBlock("DEVANAGARI_EXTENDED_A",
3575 "DEVANAGARI EXTENDED-A",
3576 "DEVANAGARIEXTENDED-A");
3577
3578 /**
3579 * Constant for the "Kawi" Unicode
3580 * character block.
3581 * @since 20
3582 */
3583 public static final UnicodeBlock KAWI =
3584 new UnicodeBlock("KAWI");
3585
3586 /**
3587 * Constant for the "Kaktovik Numerals" Unicode
3588 * character block.
3589 * @since 20
3590 */
3591 public static final UnicodeBlock KAKTOVIK_NUMERALS =
3592 new UnicodeBlock("KAKTOVIK_NUMERALS",
3593 "KAKTOVIK NUMERALS",
3594 "KAKTOVIKNUMERALS");
3595
3596 /**
3597 * Constant for the "Cyrillic Extended-D" Unicode
3598 * character block.
3599 * @since 20
3600 */
3601 public static final UnicodeBlock CYRILLIC_EXTENDED_D =
3602 new UnicodeBlock("CYRILLIC_EXTENDED_D",
3603 "CYRILLIC EXTENDED-D",
3604 "CYRILLICEXTENDED-D");
3605
3606 /**
3607 * Constant for the "Nag Mundari" Unicode
3608 * character block.
3609 * @since 20
3610 */
3611 public static final UnicodeBlock NAG_MUNDARI =
3612 new UnicodeBlock("NAG_MUNDARI",
3613 "NAG MUNDARI",
3614 "NAGMUNDARI");
3615
3616 /**
3617 * Constant for the "CJK Unified Ideographs Extension H" Unicode
3618 * character block.
3619 * @since 20
3620 */
3621 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_H =
3622 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_H",
3623 "CJK UNIFIED IDEOGRAPHS EXTENSION H",
3624 "CJKUNIFIEDIDEOGRAPHSEXTENSIONH");
3625
3626 /**
3627 * Constant for the "CJK Unified Ideographs Extension I" Unicode
3628 * character block.
3629 * @since 22
3630 */
3631 public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_I =
3632 new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_I",
3633 "CJK UNIFIED IDEOGRAPHS EXTENSION I",
3634 "CJKUNIFIEDIDEOGRAPHSEXTENSIONI");
3635
3636 /**
3637 * Constant for the "Todhri" Unicode
3638 * character block.
3639 * @since 24
3640 */
3641 public static final UnicodeBlock TODHRI =
3642 new UnicodeBlock("TODHRI");
3643
3644 /**
3645 * Constant for the "Garay" Unicode
3646 * character block.
3647 * @since 24
3648 */
3649 public static final UnicodeBlock GARAY =
3650 new UnicodeBlock("GARAY");
3651
3652 /**
3653 * Constant for the "Tulu-Tigalari" Unicode
3654 * character block.
3655 * @since 24
3656 */
3657 public static final UnicodeBlock TULU_TIGALARI =
3658 new UnicodeBlock("TULU_TIGALARI",
3659 "TULU-TIGALARI");
3660
3661 /**
3662 * Constant for the "Myanmar Extended-C" Unicode
3663 * character block.
3664 * @since 24
3665 */
3666 public static final UnicodeBlock MYANMAR_EXTENDED_C =
3667 new UnicodeBlock("MYANMAR_EXTENDED_C",
3668 "MYANMAR EXTENDED-C",
3669 "MYANMAREXTENDED-C");
3670
3671 /**
3672 * Constant for the "Sunuwar" Unicode
3673 * character block.
3674 * @since 24
3675 */
3676 public static final UnicodeBlock SUNUWAR =
3677 new UnicodeBlock("SUNUWAR");
3678
3679 /**
3680 * Constant for the "Egyptian Hieroglyphs Extended-A" Unicode
3681 * character block.
3682 * @since 24
3683 */
3684 public static final UnicodeBlock EGYPTIAN_HIEROGLYPHS_EXTENDED_A =
3685 new UnicodeBlock("EGYPTIAN_HIEROGLYPHS_EXTENDED_A",
3686 "EGYPTIAN HIEROGLYPHS EXTENDED-A",
3687 "EGYPTIANHIEROGLYPHSEXTENDED-A");
3688
3689 /**
3690 * Constant for the "Gurung Khema" Unicode
3691 * character block.
3692 * @since 24
3693 */
3694 public static final UnicodeBlock GURUNG_KHEMA =
3695 new UnicodeBlock("GURUNG_KHEMA",
3696 "GURUNG KHEMA",
3697 "GURUNGKHEMA");
3698
3699 /**
3700 * Constant for the "Kirat Rai" Unicode
3701 * character block.
3702 * @since 24
3703 */
3704 public static final UnicodeBlock KIRAT_RAI =
3705 new UnicodeBlock("KIRAT_RAI",
3706 "KIRAT RAI",
3707 "KIRATRAI");
3708
3709 /**
3710 * Constant for the "Symbols for Legacy Computing Supplement" Unicode
3711 * character block.
3712 * @since 24
3713 */
3714 public static final UnicodeBlock SYMBOLS_FOR_LEGACY_COMPUTING_SUPPLEMENT =
3715 new UnicodeBlock("SYMBOLS_FOR_LEGACY_COMPUTING_SUPPLEMENT",
3716 "SYMBOLS FOR LEGACY COMPUTING SUPPLEMENT",
3717 "SYMBOLSFORLEGACYCOMPUTINGSUPPLEMENT");
3718
3719 /**
3720 * Constant for the "Ol Onal" Unicode
3721 * character block.
3722 * @since 24
3723 */
3724 public static final UnicodeBlock OL_ONAL =
3725 new UnicodeBlock("OL_ONAL",
3726 "OL ONAL",
3727 "OLONAL");
3728
3729 private static final int[] blockStarts = {
3730 0x0000, // 0000..007F; Basic Latin
3731 0x0080, // 0080..00FF; Latin-1 Supplement
3732 0x0100, // 0100..017F; Latin Extended-A
3733 0x0180, // 0180..024F; Latin Extended-B
3734 0x0250, // 0250..02AF; IPA Extensions
3735 0x02B0, // 02B0..02FF; Spacing Modifier Letters
3736 0x0300, // 0300..036F; Combining Diacritical Marks
3737 0x0370, // 0370..03FF; Greek and Coptic
3738 0x0400, // 0400..04FF; Cyrillic
3739 0x0500, // 0500..052F; Cyrillic Supplement
3740 0x0530, // 0530..058F; Armenian
3741 0x0590, // 0590..05FF; Hebrew
3742 0x0600, // 0600..06FF; Arabic
3743 0x0700, // 0700..074F; Syriac
3744 0x0750, // 0750..077F; Arabic Supplement
3745 0x0780, // 0780..07BF; Thaana
3746 0x07C0, // 07C0..07FF; NKo
3747 0x0800, // 0800..083F; Samaritan
3748 0x0840, // 0840..085F; Mandaic
3749 0x0860, // 0860..086F; Syriac Supplement
3750 0x0870, // 0870..089F; Arabic Extended-B
3751 0x08A0, // 08A0..08FF; Arabic Extended-A
3752 0x0900, // 0900..097F; Devanagari
3753 0x0980, // 0980..09FF; Bengali
3754 0x0A00, // 0A00..0A7F; Gurmukhi
3755 0x0A80, // 0A80..0AFF; Gujarati
3756 0x0B00, // 0B00..0B7F; Oriya
3757 0x0B80, // 0B80..0BFF; Tamil
3758 0x0C00, // 0C00..0C7F; Telugu
3759 0x0C80, // 0C80..0CFF; Kannada
3760 0x0D00, // 0D00..0D7F; Malayalam
3761 0x0D80, // 0D80..0DFF; Sinhala
3762 0x0E00, // 0E00..0E7F; Thai
3763 0x0E80, // 0E80..0EFF; Lao
3764 0x0F00, // 0F00..0FFF; Tibetan
3765 0x1000, // 1000..109F; Myanmar
3766 0x10A0, // 10A0..10FF; Georgian
3767 0x1100, // 1100..11FF; Hangul Jamo
3768 0x1200, // 1200..137F; Ethiopic
3769 0x1380, // 1380..139F; Ethiopic Supplement
3770 0x13A0, // 13A0..13FF; Cherokee
3771 0x1400, // 1400..167F; Unified Canadian Aboriginal Syllabics
3772 0x1680, // 1680..169F; Ogham
3773 0x16A0, // 16A0..16FF; Runic
3774 0x1700, // 1700..171F; Tagalog
3775 0x1720, // 1720..173F; Hanunoo
3776 0x1740, // 1740..175F; Buhid
3777 0x1760, // 1760..177F; Tagbanwa
3778 0x1780, // 1780..17FF; Khmer
3779 0x1800, // 1800..18AF; Mongolian
3780 0x18B0, // 18B0..18FF; Unified Canadian Aboriginal Syllabics Extended
3781 0x1900, // 1900..194F; Limbu
3782 0x1950, // 1950..197F; Tai Le
3783 0x1980, // 1980..19DF; New Tai Lue
3784 0x19E0, // 19E0..19FF; Khmer Symbols
3785 0x1A00, // 1A00..1A1F; Buginese
3786 0x1A20, // 1A20..1AAF; Tai Tham
3787 0x1AB0, // 1AB0..1AFF; Combining Diacritical Marks Extended
3788 0x1B00, // 1B00..1B7F; Balinese
3789 0x1B80, // 1B80..1BBF; Sundanese
3790 0x1BC0, // 1BC0..1BFF; Batak
3791 0x1C00, // 1C00..1C4F; Lepcha
3792 0x1C50, // 1C50..1C7F; Ol Chiki
3793 0x1C80, // 1C80..1C8F; Cyrillic Extended-C
3794 0x1C90, // 1C90..1CBF; Georgian Extended
3795 0x1CC0, // 1CC0..1CCF; Sundanese Supplement
3796 0x1CD0, // 1CD0..1CFF; Vedic Extensions
3797 0x1D00, // 1D00..1D7F; Phonetic Extensions
3798 0x1D80, // 1D80..1DBF; Phonetic Extensions Supplement
3799 0x1DC0, // 1DC0..1DFF; Combining Diacritical Marks Supplement
3800 0x1E00, // 1E00..1EFF; Latin Extended Additional
3801 0x1F00, // 1F00..1FFF; Greek Extended
3802 0x2000, // 2000..206F; General Punctuation
3803 0x2070, // 2070..209F; Superscripts and Subscripts
3804 0x20A0, // 20A0..20CF; Currency Symbols
3805 0x20D0, // 20D0..20FF; Combining Diacritical Marks for Symbols
3806 0x2100, // 2100..214F; Letterlike Symbols
3807 0x2150, // 2150..218F; Number Forms
3808 0x2190, // 2190..21FF; Arrows
3809 0x2200, // 2200..22FF; Mathematical Operators
3810 0x2300, // 2300..23FF; Miscellaneous Technical
3811 0x2400, // 2400..243F; Control Pictures
3812 0x2440, // 2440..245F; Optical Character Recognition
3813 0x2460, // 2460..24FF; Enclosed Alphanumerics
3814 0x2500, // 2500..257F; Box Drawing
3815 0x2580, // 2580..259F; Block Elements
3816 0x25A0, // 25A0..25FF; Geometric Shapes
3817 0x2600, // 2600..26FF; Miscellaneous Symbols
3818 0x2700, // 2700..27BF; Dingbats
3819 0x27C0, // 27C0..27EF; Miscellaneous Mathematical Symbols-A
3820 0x27F0, // 27F0..27FF; Supplemental Arrows-A
3821 0x2800, // 2800..28FF; Braille Patterns
3822 0x2900, // 2900..297F; Supplemental Arrows-B
3823 0x2980, // 2980..29FF; Miscellaneous Mathematical Symbols-B
3824 0x2A00, // 2A00..2AFF; Supplemental Mathematical Operators
3825 0x2B00, // 2B00..2BFF; Miscellaneous Symbols and Arrows
3826 0x2C00, // 2C00..2C5F; Glagolitic
3827 0x2C60, // 2C60..2C7F; Latin Extended-C
3828 0x2C80, // 2C80..2CFF; Coptic
3829 0x2D00, // 2D00..2D2F; Georgian Supplement
3830 0x2D30, // 2D30..2D7F; Tifinagh
3831 0x2D80, // 2D80..2DDF; Ethiopic Extended
3832 0x2DE0, // 2DE0..2DFF; Cyrillic Extended-A
3833 0x2E00, // 2E00..2E7F; Supplemental Punctuation
3834 0x2E80, // 2E80..2EFF; CJK Radicals Supplement
3835 0x2F00, // 2F00..2FDF; Kangxi Radicals
3836 0x2FE0, // unassigned
3837 0x2FF0, // 2FF0..2FFF; Ideographic Description Characters
3838 0x3000, // 3000..303F; CJK Symbols and Punctuation
3839 0x3040, // 3040..309F; Hiragana
3840 0x30A0, // 30A0..30FF; Katakana
3841 0x3100, // 3100..312F; Bopomofo
3842 0x3130, // 3130..318F; Hangul Compatibility Jamo
3843 0x3190, // 3190..319F; Kanbun
3844 0x31A0, // 31A0..31BF; Bopomofo Extended
3845 0x31C0, // 31C0..31EF; CJK Strokes
3846 0x31F0, // 31F0..31FF; Katakana Phonetic Extensions
3847 0x3200, // 3200..32FF; Enclosed CJK Letters and Months
3848 0x3300, // 3300..33FF; CJK Compatibility
3849 0x3400, // 3400..4DBF; CJK Unified Ideographs Extension A
3850 0x4DC0, // 4DC0..4DFF; Yijing Hexagram Symbols
3851 0x4E00, // 4E00..9FFF; CJK Unified Ideographs
3852 0xA000, // A000..A48F; Yi Syllables
3853 0xA490, // A490..A4CF; Yi Radicals
3854 0xA4D0, // A4D0..A4FF; Lisu
3855 0xA500, // A500..A63F; Vai
3856 0xA640, // A640..A69F; Cyrillic Extended-B
3857 0xA6A0, // A6A0..A6FF; Bamum
3858 0xA700, // A700..A71F; Modifier Tone Letters
3859 0xA720, // A720..A7FF; Latin Extended-D
3860 0xA800, // A800..A82F; Syloti Nagri
3861 0xA830, // A830..A83F; Common Indic Number Forms
3862 0xA840, // A840..A87F; Phags-pa
3863 0xA880, // A880..A8DF; Saurashtra
3864 0xA8E0, // A8E0..A8FF; Devanagari Extended
3865 0xA900, // A900..A92F; Kayah Li
3866 0xA930, // A930..A95F; Rejang
3867 0xA960, // A960..A97F; Hangul Jamo Extended-A
3868 0xA980, // A980..A9DF; Javanese
3869 0xA9E0, // A9E0..A9FF; Myanmar Extended-B
3870 0xAA00, // AA00..AA5F; Cham
3871 0xAA60, // AA60..AA7F; Myanmar Extended-A
3872 0xAA80, // AA80..AADF; Tai Viet
3873 0xAAE0, // AAE0..AAFF; Meetei Mayek Extensions
3874 0xAB00, // AB00..AB2F; Ethiopic Extended-A
3875 0xAB30, // AB30..AB6F; Latin Extended-E
3876 0xAB70, // AB70..ABBF; Cherokee Supplement
3877 0xABC0, // ABC0..ABFF; Meetei Mayek
3878 0xAC00, // AC00..D7AF; Hangul Syllables
3879 0xD7B0, // D7B0..D7FF; Hangul Jamo Extended-B
3880 0xD800, // D800..DB7F; High Surrogates
3881 0xDB80, // DB80..DBFF; High Private Use Surrogates
3882 0xDC00, // DC00..DFFF; Low Surrogates
3883 0xE000, // E000..F8FF; Private Use Area
3884 0xF900, // F900..FAFF; CJK Compatibility Ideographs
3885 0xFB00, // FB00..FB4F; Alphabetic Presentation Forms
3886 0xFB50, // FB50..FDFF; Arabic Presentation Forms-A
3887 0xFE00, // FE00..FE0F; Variation Selectors
3888 0xFE10, // FE10..FE1F; Vertical Forms
3889 0xFE20, // FE20..FE2F; Combining Half Marks
3890 0xFE30, // FE30..FE4F; CJK Compatibility Forms
3891 0xFE50, // FE50..FE6F; Small Form Variants
3892 0xFE70, // FE70..FEFF; Arabic Presentation Forms-B
3893 0xFF00, // FF00..FFEF; Halfwidth and Fullwidth Forms
3894 0xFFF0, // FFF0..FFFF; Specials
3895 0x10000, // 10000..1007F; Linear B Syllabary
3896 0x10080, // 10080..100FF; Linear B Ideograms
3897 0x10100, // 10100..1013F; Aegean Numbers
3898 0x10140, // 10140..1018F; Ancient Greek Numbers
3899 0x10190, // 10190..101CF; Ancient Symbols
3900 0x101D0, // 101D0..101FF; Phaistos Disc
3901 0x10200, // unassigned
3902 0x10280, // 10280..1029F; Lycian
3903 0x102A0, // 102A0..102DF; Carian
3904 0x102E0, // 102E0..102FF; Coptic Epact Numbers
3905 0x10300, // 10300..1032F; Old Italic
3906 0x10330, // 10330..1034F; Gothic
3907 0x10350, // 10350..1037F; Old Permic
3908 0x10380, // 10380..1039F; Ugaritic
3909 0x103A0, // 103A0..103DF; Old Persian
3910 0x103E0, // unassigned
3911 0x10400, // 10400..1044F; Deseret
3912 0x10450, // 10450..1047F; Shavian
3913 0x10480, // 10480..104AF; Osmanya
3914 0x104B0, // 104B0..104FF; Osage
3915 0x10500, // 10500..1052F; Elbasan
3916 0x10530, // 10530..1056F; Caucasian Albanian
3917 0x10570, // 10570..105BF; Vithkuqi
3918 0x105C0, // 105C0..105FF; Todhri
3919 0x10600, // 10600..1077F; Linear A
3920 0x10780, // 10780..107BF; Latin Extended-F
3921 0x107C0, // unassigned
3922 0x10800, // 10800..1083F; Cypriot Syllabary
3923 0x10840, // 10840..1085F; Imperial Aramaic
3924 0x10860, // 10860..1087F; Palmyrene
3925 0x10880, // 10880..108AF; Nabataean
3926 0x108B0, // unassigned
3927 0x108E0, // 108E0..108FF; Hatran
3928 0x10900, // 10900..1091F; Phoenician
3929 0x10920, // 10920..1093F; Lydian
3930 0x10940, // unassigned
3931 0x10980, // 10980..1099F; Meroitic Hieroglyphs
3932 0x109A0, // 109A0..109FF; Meroitic Cursive
3933 0x10A00, // 10A00..10A5F; Kharoshthi
3934 0x10A60, // 10A60..10A7F; Old South Arabian
3935 0x10A80, // 10A80..10A9F; Old North Arabian
3936 0x10AA0, // unassigned
3937 0x10AC0, // 10AC0..10AFF; Manichaean
3938 0x10B00, // 10B00..10B3F; Avestan
3939 0x10B40, // 10B40..10B5F; Inscriptional Parthian
3940 0x10B60, // 10B60..10B7F; Inscriptional Pahlavi
3941 0x10B80, // 10B80..10BAF; Psalter Pahlavi
3942 0x10BB0, // unassigned
3943 0x10C00, // 10C00..10C4F; Old Turkic
3944 0x10C50, // unassigned
3945 0x10C80, // 10C80..10CFF; Old Hungarian
3946 0x10D00, // 10D00..10D3F; Hanifi Rohingya
3947 0x10D40, // 10D40..10D8F; Garay
3948 0x10D90, // unassigned
3949 0x10E60, // 10E60..10E7F; Rumi Numeral Symbols
3950 0x10E80, // 10E80..10EBF; Yezidi
3951 0x10EC0, // 10EC0..10EFF; Arabic Extended-C
3952 0x10F00, // 10F00..10F2F; Old Sogdian
3953 0x10F30, // 10F30..10F6F; Sogdian
3954 0x10F70, // 10F70..10FAF; Old Uyghur
3955 0x10FB0, // 10FB0..10FDF; Chorasmian
3956 0x10FE0, // 10FE0..10FFF; Elymaic
3957 0x11000, // 11000..1107F; Brahmi
3958 0x11080, // 11080..110CF; Kaithi
3959 0x110D0, // 110D0..110FF; Sora Sompeng
3960 0x11100, // 11100..1114F; Chakma
3961 0x11150, // 11150..1117F; Mahajani
3962 0x11180, // 11180..111DF; Sharada
3963 0x111E0, // 111E0..111FF; Sinhala Archaic Numbers
3964 0x11200, // 11200..1124F; Khojki
3965 0x11250, // unassigned
3966 0x11280, // 11280..112AF; Multani
3967 0x112B0, // 112B0..112FF; Khudawadi
3968 0x11300, // 11300..1137F; Grantha
3969 0x11380, // 11380..113FF; Tulu-Tigalari
3970 0x11400, // 11400..1147F; Newa
3971 0x11480, // 11480..114DF; Tirhuta
3972 0x114E0, // unassigned
3973 0x11580, // 11580..115FF; Siddham
3974 0x11600, // 11600..1165F; Modi
3975 0x11660, // 11660..1167F; Mongolian Supplement
3976 0x11680, // 11680..116CF; Takri
3977 0x116D0, // 116D0..116FF; Myanmar Extended-C
3978 0x11700, // 11700..1174F; Ahom
3979 0x11750, // unassigned
3980 0x11800, // 11800..1184F; Dogra
3981 0x11850, // unassigned
3982 0x118A0, // 118A0..118FF; Warang Citi
3983 0x11900, // 11900..1195F; Dives Akuru
3984 0x11960, // unassigned
3985 0x119A0, // 119A0..119FF; Nandinagari
3986 0x11A00, // 11A00..11A4F; Zanabazar Square
3987 0x11A50, // 11A50..11AAF; Soyombo
3988 0x11AB0, // 11AB0..11ABF; Unified Canadian Aboriginal Syllabics Extended-A
3989 0x11AC0, // 11AC0..11AFF; Pau Cin Hau
3990 0x11B00, // 11B00..11B5F; Devanagari Extended-A
3991 0x11B60, // unassigned
3992 0x11BC0, // 11BC0..11BFF; Sunuwar
3993 0x11C00, // 11C00..11C6F; Bhaiksuki
3994 0x11C70, // 11C70..11CBF; Marchen
3995 0x11CC0, // unassigned
3996 0x11D00, // 11D00..11D5F; Masaram Gondi
3997 0x11D60, // 11D60..11DAF; Gunjala Gondi
3998 0x11DB0, // unassigned
3999 0x11EE0, // 11EE0..11EFF; Makasar
4000 0x11F00, // 11F00..11F5F; Kawi
4001 0x11F60, // unassigned
4002 0x11FB0, // 11FB0..11FBF; Lisu Supplement
4003 0x11FC0, // 11FC0..11FFF; Tamil Supplement
4004 0x12000, // 12000..123FF; Cuneiform
4005 0x12400, // 12400..1247F; Cuneiform Numbers and Punctuation
4006 0x12480, // 12480..1254F; Early Dynastic Cuneiform
4007 0x12550, // unassigned
4008 0x12F90, // 12F90..12FFF; Cypro-Minoan
4009 0x13000, // 13000..1342F; Egyptian Hieroglyphs
4010 0x13430, // 13430..1345F; Egyptian Hieroglyph Format Controls
4011 0x13460, // 13460..143FF; Egyptian Hieroglyphs Extended-A
4012 0x14400, // 14400..1467F; Anatolian Hieroglyphs
4013 0x14680, // unassigned
4014 0x16100, // 16100..1613F; Gurung Khema
4015 0x16140, // unassigned
4016 0x16800, // 16800..16A3F; Bamum Supplement
4017 0x16A40, // 16A40..16A6F; Mro
4018 0x16A70, // 16A70..16ACF; Tangsa
4019 0x16AD0, // 16AD0..16AFF; Bassa Vah
4020 0x16B00, // 16B00..16B8F; Pahawh Hmong
4021 0x16B90, // unassigned
4022 0x16D40, // 16D40..16D7F; Kirat Rai
4023 0x16D80, // unassigned
4024 0x16E40, // 16E40..16E9F; Medefaidrin
4025 0x16EA0, // unassigned
4026 0x16F00, // 16F00..16F9F; Miao
4027 0x16FA0, // unassigned
4028 0x16FE0, // 16FE0..16FFF; Ideographic Symbols and Punctuation
4029 0x17000, // 17000..187FF; Tangut
4030 0x18800, // 18800..18AFF; Tangut Components
4031 0x18B00, // 18B00..18CFF; Khitan Small Script
4032 0x18D00, // 18D00..18D7F; Tangut Supplement
4033 0x18D80, // unassigned
4034 0x1AFF0, // 1AFF0..1AFFF; Kana Extended-B
4035 0x1B000, // 1B000..1B0FF; Kana Supplement
4036 0x1B100, // 1B100..1B12F; Kana Extended-A
4037 0x1B130, // 1B130..1B16F; Small Kana Extension
4038 0x1B170, // 1B170..1B2FF; Nushu
4039 0x1B300, // unassigned
4040 0x1BC00, // 1BC00..1BC9F; Duployan
4041 0x1BCA0, // 1BCA0..1BCAF; Shorthand Format Controls
4042 0x1BCB0, // unassigned
4043 0x1CC00, // 1CC00..1CEBF; Symbols for Legacy Computing Supplement
4044 0x1CEC0, // unassigned
4045 0x1CF00, // 1CF00..1CFCF; Znamenny Musical Notation
4046 0x1CFD0, // unassigned
4047 0x1D000, // 1D000..1D0FF; Byzantine Musical Symbols
4048 0x1D100, // 1D100..1D1FF; Musical Symbols
4049 0x1D200, // 1D200..1D24F; Ancient Greek Musical Notation
4050 0x1D250, // unassigned
4051 0x1D2C0, // 1D2C0..1D2DF; Kaktovik Numerals
4052 0x1D2E0, // 1D2E0..1D2FF; Mayan Numerals
4053 0x1D300, // 1D300..1D35F; Tai Xuan Jing Symbols
4054 0x1D360, // 1D360..1D37F; Counting Rod Numerals
4055 0x1D380, // unassigned
4056 0x1D400, // 1D400..1D7FF; Mathematical Alphanumeric Symbols
4057 0x1D800, // 1D800..1DAAF; Sutton SignWriting
4058 0x1DAB0, // unassigned
4059 0x1DF00, // 1DF00..1DFFF; Latin Extended-G
4060 0x1E000, // 1E000..1E02F; Glagolitic Supplement
4061 0x1E030, // 1E030..1E08F; Cyrillic Extended-D
4062 0x1E090, // unassigned
4063 0x1E100, // 1E100..1E14F; Nyiakeng Puachue Hmong
4064 0x1E150, // unassigned
4065 0x1E290, // 1E290..1E2BF; Toto
4066 0x1E2C0, // 1E2C0..1E2FF; Wancho
4067 0x1E300, // unassigned
4068 0x1E4D0, // 1E4D0..1E4FF; Nag Mundari
4069 0x1E500, // unassigned
4070 0x1E5D0, // 1E5D0..1E5FF; Ol Onal
4071 0x1E600, // unassigned
4072 0x1E7E0, // 1E7E0..1E7FF; Ethiopic Extended-B
4073 0x1E800, // 1E800..1E8DF; Mende Kikakui
4074 0x1E8E0, // unassigned
4075 0x1E900, // 1E900..1E95F; Adlam
4076 0x1E960, // unassigned
4077 0x1EC70, // 1EC70..1ECBF; Indic Siyaq Numbers
4078 0x1ECC0, // unassigned
4079 0x1ED00, // 1ED00..1ED4F; Ottoman Siyaq Numbers
4080 0x1ED50, // unassigned
4081 0x1EE00, // 1EE00..1EEFF; Arabic Mathematical Alphabetic Symbols
4082 0x1EF00, // unassigned
4083 0x1F000, // 1F000..1F02F; Mahjong Tiles
4084 0x1F030, // 1F030..1F09F; Domino Tiles
4085 0x1F0A0, // 1F0A0..1F0FF; Playing Cards
4086 0x1F100, // 1F100..1F1FF; Enclosed Alphanumeric Supplement
4087 0x1F200, // 1F200..1F2FF; Enclosed Ideographic Supplement
4088 0x1F300, // 1F300..1F5FF; Miscellaneous Symbols and Pictographs
4089 0x1F600, // 1F600..1F64F; Emoticons
4090 0x1F650, // 1F650..1F67F; Ornamental Dingbats
4091 0x1F680, // 1F680..1F6FF; Transport and Map Symbols
4092 0x1F700, // 1F700..1F77F; Alchemical Symbols
4093 0x1F780, // 1F780..1F7FF; Geometric Shapes Extended
4094 0x1F800, // 1F800..1F8FF; Supplemental Arrows-C
4095 0x1F900, // 1F900..1F9FF; Supplemental Symbols and Pictographs
4096 0x1FA00, // 1FA00..1FA6F; Chess Symbols
4097 0x1FA70, // 1FA70..1FAFF; Symbols and Pictographs Extended-A
4098 0x1FB00, // 1FB00..1FBFF; Symbols for Legacy Computing
4099 0x1FC00, // unassigned
4100 0x20000, // 20000..2A6DF; CJK Unified Ideographs Extension B
4101 0x2A6E0, // unassigned
4102 0x2A700, // 2A700..2B73F; CJK Unified Ideographs Extension C
4103 0x2B740, // 2B740..2B81F; CJK Unified Ideographs Extension D
4104 0x2B820, // 2B820..2CEAF; CJK Unified Ideographs Extension E
4105 0x2CEB0, // 2CEB0..2EBEF; CJK Unified Ideographs Extension F
4106 0x2EBF0, // 2EBF0..2EE5F; CJK Unified Ideographs Extension I
4107 0x2EE60, // unassigned
4108 0x2F800, // 2F800..2FA1F; CJK Compatibility Ideographs Supplement
4109 0x2FA20, // unassigned
4110 0x30000, // 30000..3134F; CJK Unified Ideographs Extension G
4111 0x31350, // 31350..323AF; CJK Unified Ideographs Extension H
4112 0x323B0, // unassigned
4113 0xE0000, // E0000..E007F; Tags
4114 0xE0080, // unassigned
4115 0xE0100, // E0100..E01EF; Variation Selectors Supplement
4116 0xE01F0, // unassigned
4117 0xF0000, // F0000..FFFFF; Supplementary Private Use Area-A
4118 0x100000, // 100000..10FFFF; Supplementary Private Use Area-B
4119 };
4120
4121 private static final UnicodeBlock[] blocks = {
4122 BASIC_LATIN,
4123 LATIN_1_SUPPLEMENT,
4124 LATIN_EXTENDED_A,
4125 LATIN_EXTENDED_B,
4126 IPA_EXTENSIONS,
4127 SPACING_MODIFIER_LETTERS,
4128 COMBINING_DIACRITICAL_MARKS,
4129 GREEK,
4130 CYRILLIC,
4131 CYRILLIC_SUPPLEMENTARY,
4132 ARMENIAN,
4133 HEBREW,
4134 ARABIC,
4135 SYRIAC,
4136 ARABIC_SUPPLEMENT,
4137 THAANA,
4138 NKO,
4139 SAMARITAN,
4140 MANDAIC,
4141 SYRIAC_SUPPLEMENT,
4142 ARABIC_EXTENDED_B,
4143 ARABIC_EXTENDED_A,
4144 DEVANAGARI,
4145 BENGALI,
4146 GURMUKHI,
4147 GUJARATI,
4148 ORIYA,
4149 TAMIL,
4150 TELUGU,
4151 KANNADA,
4152 MALAYALAM,
4153 SINHALA,
4154 THAI,
4155 LAO,
4156 TIBETAN,
4157 MYANMAR,
4158 GEORGIAN,
4159 HANGUL_JAMO,
4160 ETHIOPIC,
4161 ETHIOPIC_SUPPLEMENT,
4162 CHEROKEE,
4163 UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS,
4164 OGHAM,
4165 RUNIC,
4166 TAGALOG,
4167 HANUNOO,
4168 BUHID,
4169 TAGBANWA,
4170 KHMER,
4171 MONGOLIAN,
4172 UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED,
4173 LIMBU,
4174 TAI_LE,
4175 NEW_TAI_LUE,
4176 KHMER_SYMBOLS,
4177 BUGINESE,
4178 TAI_THAM,
4179 COMBINING_DIACRITICAL_MARKS_EXTENDED,
4180 BALINESE,
4181 SUNDANESE,
4182 BATAK,
4183 LEPCHA,
4184 OL_CHIKI,
4185 CYRILLIC_EXTENDED_C,
4186 GEORGIAN_EXTENDED,
4187 SUNDANESE_SUPPLEMENT,
4188 VEDIC_EXTENSIONS,
4189 PHONETIC_EXTENSIONS,
4190 PHONETIC_EXTENSIONS_SUPPLEMENT,
4191 COMBINING_DIACRITICAL_MARKS_SUPPLEMENT,
4192 LATIN_EXTENDED_ADDITIONAL,
4193 GREEK_EXTENDED,
4194 GENERAL_PUNCTUATION,
4195 SUPERSCRIPTS_AND_SUBSCRIPTS,
4196 CURRENCY_SYMBOLS,
4197 COMBINING_MARKS_FOR_SYMBOLS,
4198 LETTERLIKE_SYMBOLS,
4199 NUMBER_FORMS,
4200 ARROWS,
4201 MATHEMATICAL_OPERATORS,
4202 MISCELLANEOUS_TECHNICAL,
4203 CONTROL_PICTURES,
4204 OPTICAL_CHARACTER_RECOGNITION,
4205 ENCLOSED_ALPHANUMERICS,
4206 BOX_DRAWING,
4207 BLOCK_ELEMENTS,
4208 GEOMETRIC_SHAPES,
4209 MISCELLANEOUS_SYMBOLS,
4210 DINGBATS,
4211 MISCELLANEOUS_MATHEMATICAL_SYMBOLS_A,
4212 SUPPLEMENTAL_ARROWS_A,
4213 BRAILLE_PATTERNS,
4214 SUPPLEMENTAL_ARROWS_B,
4215 MISCELLANEOUS_MATHEMATICAL_SYMBOLS_B,
4216 SUPPLEMENTAL_MATHEMATICAL_OPERATORS,
4217 MISCELLANEOUS_SYMBOLS_AND_ARROWS,
4218 GLAGOLITIC,
4219 LATIN_EXTENDED_C,
4220 COPTIC,
4221 GEORGIAN_SUPPLEMENT,
4222 TIFINAGH,
4223 ETHIOPIC_EXTENDED,
4224 CYRILLIC_EXTENDED_A,
4225 SUPPLEMENTAL_PUNCTUATION,
4226 CJK_RADICALS_SUPPLEMENT,
4227 KANGXI_RADICALS,
4228 null,
4229 IDEOGRAPHIC_DESCRIPTION_CHARACTERS,
4230 CJK_SYMBOLS_AND_PUNCTUATION,
4231 HIRAGANA,
4232 KATAKANA,
4233 BOPOMOFO,
4234 HANGUL_COMPATIBILITY_JAMO,
4235 KANBUN,
4236 BOPOMOFO_EXTENDED,
4237 CJK_STROKES,
4238 KATAKANA_PHONETIC_EXTENSIONS,
4239 ENCLOSED_CJK_LETTERS_AND_MONTHS,
4240 CJK_COMPATIBILITY,
4241 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A,
4242 YIJING_HEXAGRAM_SYMBOLS,
4243 CJK_UNIFIED_IDEOGRAPHS,
4244 YI_SYLLABLES,
4245 YI_RADICALS,
4246 LISU,
4247 VAI,
4248 CYRILLIC_EXTENDED_B,
4249 BAMUM,
4250 MODIFIER_TONE_LETTERS,
4251 LATIN_EXTENDED_D,
4252 SYLOTI_NAGRI,
4253 COMMON_INDIC_NUMBER_FORMS,
4254 PHAGS_PA,
4255 SAURASHTRA,
4256 DEVANAGARI_EXTENDED,
4257 KAYAH_LI,
4258 REJANG,
4259 HANGUL_JAMO_EXTENDED_A,
4260 JAVANESE,
4261 MYANMAR_EXTENDED_B,
4262 CHAM,
4263 MYANMAR_EXTENDED_A,
4264 TAI_VIET,
4265 MEETEI_MAYEK_EXTENSIONS,
4266 ETHIOPIC_EXTENDED_A,
4267 LATIN_EXTENDED_E,
4268 CHEROKEE_SUPPLEMENT,
4269 MEETEI_MAYEK,
4270 HANGUL_SYLLABLES,
4271 HANGUL_JAMO_EXTENDED_B,
4272 HIGH_SURROGATES,
4273 HIGH_PRIVATE_USE_SURROGATES,
4274 LOW_SURROGATES,
4275 PRIVATE_USE_AREA,
4276 CJK_COMPATIBILITY_IDEOGRAPHS,
4277 ALPHABETIC_PRESENTATION_FORMS,
4278 ARABIC_PRESENTATION_FORMS_A,
4279 VARIATION_SELECTORS,
4280 VERTICAL_FORMS,
4281 COMBINING_HALF_MARKS,
4282 CJK_COMPATIBILITY_FORMS,
4283 SMALL_FORM_VARIANTS,
4284 ARABIC_PRESENTATION_FORMS_B,
4285 HALFWIDTH_AND_FULLWIDTH_FORMS,
4286 SPECIALS,
4287 LINEAR_B_SYLLABARY,
4288 LINEAR_B_IDEOGRAMS,
4289 AEGEAN_NUMBERS,
4290 ANCIENT_GREEK_NUMBERS,
4291 ANCIENT_SYMBOLS,
4292 PHAISTOS_DISC,
4293 null,
4294 LYCIAN,
4295 CARIAN,
4296 COPTIC_EPACT_NUMBERS,
4297 OLD_ITALIC,
4298 GOTHIC,
4299 OLD_PERMIC,
4300 UGARITIC,
4301 OLD_PERSIAN,
4302 null,
4303 DESERET,
4304 SHAVIAN,
4305 OSMANYA,
4306 OSAGE,
4307 ELBASAN,
4308 CAUCASIAN_ALBANIAN,
4309 VITHKUQI,
4310 TODHRI,
4311 LINEAR_A,
4312 LATIN_EXTENDED_F,
4313 null,
4314 CYPRIOT_SYLLABARY,
4315 IMPERIAL_ARAMAIC,
4316 PALMYRENE,
4317 NABATAEAN,
4318 null,
4319 HATRAN,
4320 PHOENICIAN,
4321 LYDIAN,
4322 null,
4323 MEROITIC_HIEROGLYPHS,
4324 MEROITIC_CURSIVE,
4325 KHAROSHTHI,
4326 OLD_SOUTH_ARABIAN,
4327 OLD_NORTH_ARABIAN,
4328 null,
4329 MANICHAEAN,
4330 AVESTAN,
4331 INSCRIPTIONAL_PARTHIAN,
4332 INSCRIPTIONAL_PAHLAVI,
4333 PSALTER_PAHLAVI,
4334 null,
4335 OLD_TURKIC,
4336 null,
4337 OLD_HUNGARIAN,
4338 HANIFI_ROHINGYA,
4339 GARAY,
4340 null,
4341 RUMI_NUMERAL_SYMBOLS,
4342 YEZIDI,
4343 ARABIC_EXTENDED_C,
4344 OLD_SOGDIAN,
4345 SOGDIAN,
4346 OLD_UYGHUR,
4347 CHORASMIAN,
4348 ELYMAIC,
4349 BRAHMI,
4350 KAITHI,
4351 SORA_SOMPENG,
4352 CHAKMA,
4353 MAHAJANI,
4354 SHARADA,
4355 SINHALA_ARCHAIC_NUMBERS,
4356 KHOJKI,
4357 null,
4358 MULTANI,
4359 KHUDAWADI,
4360 GRANTHA,
4361 TULU_TIGALARI,
4362 NEWA,
4363 TIRHUTA,
4364 null,
4365 SIDDHAM,
4366 MODI,
4367 MONGOLIAN_SUPPLEMENT,
4368 TAKRI,
4369 MYANMAR_EXTENDED_C,
4370 AHOM,
4371 null,
4372 DOGRA,
4373 null,
4374 WARANG_CITI,
4375 DIVES_AKURU,
4376 null,
4377 NANDINAGARI,
4378 ZANABAZAR_SQUARE,
4379 SOYOMBO,
4380 UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED_A,
4381 PAU_CIN_HAU,
4382 DEVANAGARI_EXTENDED_A,
4383 null,
4384 SUNUWAR,
4385 BHAIKSUKI,
4386 MARCHEN,
4387 null,
4388 MASARAM_GONDI,
4389 GUNJALA_GONDI,
4390 null,
4391 MAKASAR,
4392 KAWI,
4393 null,
4394 LISU_SUPPLEMENT,
4395 TAMIL_SUPPLEMENT,
4396 CUNEIFORM,
4397 CUNEIFORM_NUMBERS_AND_PUNCTUATION,
4398 EARLY_DYNASTIC_CUNEIFORM,
4399 null,
4400 CYPRO_MINOAN,
4401 EGYPTIAN_HIEROGLYPHS,
4402 EGYPTIAN_HIEROGLYPH_FORMAT_CONTROLS,
4403 EGYPTIAN_HIEROGLYPHS_EXTENDED_A,
4404 ANATOLIAN_HIEROGLYPHS,
4405 null,
4406 GURUNG_KHEMA,
4407 null,
4408 BAMUM_SUPPLEMENT,
4409 MRO,
4410 TANGSA,
4411 BASSA_VAH,
4412 PAHAWH_HMONG,
4413 null,
4414 KIRAT_RAI,
4415 null,
4416 MEDEFAIDRIN,
4417 null,
4418 MIAO,
4419 null,
4420 IDEOGRAPHIC_SYMBOLS_AND_PUNCTUATION,
4421 TANGUT,
4422 TANGUT_COMPONENTS,
4423 KHITAN_SMALL_SCRIPT,
4424 TANGUT_SUPPLEMENT,
4425 null,
4426 KANA_EXTENDED_B,
4427 KANA_SUPPLEMENT,
4428 KANA_EXTENDED_A,
4429 SMALL_KANA_EXTENSION,
4430 NUSHU,
4431 null,
4432 DUPLOYAN,
4433 SHORTHAND_FORMAT_CONTROLS,
4434 null,
4435 SYMBOLS_FOR_LEGACY_COMPUTING_SUPPLEMENT,
4436 null,
4437 ZNAMENNY_MUSICAL_NOTATION,
4438 null,
4439 BYZANTINE_MUSICAL_SYMBOLS,
4440 MUSICAL_SYMBOLS,
4441 ANCIENT_GREEK_MUSICAL_NOTATION,
4442 null,
4443 KAKTOVIK_NUMERALS,
4444 MAYAN_NUMERALS,
4445 TAI_XUAN_JING_SYMBOLS,
4446 COUNTING_ROD_NUMERALS,
4447 null,
4448 MATHEMATICAL_ALPHANUMERIC_SYMBOLS,
4449 SUTTON_SIGNWRITING,
4450 null,
4451 LATIN_EXTENDED_G,
4452 GLAGOLITIC_SUPPLEMENT,
4453 CYRILLIC_EXTENDED_D,
4454 null,
4455 NYIAKENG_PUACHUE_HMONG,
4456 null,
4457 TOTO,
4458 WANCHO,
4459 null,
4460 NAG_MUNDARI,
4461 null,
4462 OL_ONAL,
4463 null,
4464 ETHIOPIC_EXTENDED_B,
4465 MENDE_KIKAKUI,
4466 null,
4467 ADLAM,
4468 null,
4469 INDIC_SIYAQ_NUMBERS,
4470 null,
4471 OTTOMAN_SIYAQ_NUMBERS,
4472 null,
4473 ARABIC_MATHEMATICAL_ALPHABETIC_SYMBOLS,
4474 null,
4475 MAHJONG_TILES,
4476 DOMINO_TILES,
4477 PLAYING_CARDS,
4478 ENCLOSED_ALPHANUMERIC_SUPPLEMENT,
4479 ENCLOSED_IDEOGRAPHIC_SUPPLEMENT,
4480 MISCELLANEOUS_SYMBOLS_AND_PICTOGRAPHS,
4481 EMOTICONS,
4482 ORNAMENTAL_DINGBATS,
4483 TRANSPORT_AND_MAP_SYMBOLS,
4484 ALCHEMICAL_SYMBOLS,
4485 GEOMETRIC_SHAPES_EXTENDED,
4486 SUPPLEMENTAL_ARROWS_C,
4487 SUPPLEMENTAL_SYMBOLS_AND_PICTOGRAPHS,
4488 CHESS_SYMBOLS,
4489 SYMBOLS_AND_PICTOGRAPHS_EXTENDED_A,
4490 SYMBOLS_FOR_LEGACY_COMPUTING,
4491 null,
4492 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_B,
4493 null,
4494 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_C,
4495 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_D,
4496 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_E,
4497 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_F,
4498 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_I,
4499 null,
4500 CJK_COMPATIBILITY_IDEOGRAPHS_SUPPLEMENT,
4501 null,
4502 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_G,
4503 CJK_UNIFIED_IDEOGRAPHS_EXTENSION_H,
4504 null,
4505 TAGS,
4506 null,
4507 VARIATION_SELECTORS_SUPPLEMENT,
4508 null,
4509 SUPPLEMENTARY_PRIVATE_USE_AREA_A,
4510 SUPPLEMENTARY_PRIVATE_USE_AREA_B,
4511 };
4512
4513
4514 /**
4515 * Returns the object representing the Unicode block containing the
4516 * given character, or {@code null} if the character is not a
4517 * member of a defined block.
4518 *
4519 * <p><b>Note:</b> This method cannot handle
4520 * <a href="Character.html#supplementary"> supplementary
4521 * characters</a>. To support all Unicode characters, including
4522 * supplementary characters, use the {@link #of(int)} method.
4523 *
4524 * @param c The character in question
4525 * @return The {@code UnicodeBlock} instance representing the
4526 * Unicode block of which this character is a member, or
4527 * {@code null} if the character is not a member of any
4528 * Unicode block
4529 */
4530 public static UnicodeBlock of(char c) {
4531 return of((int)c);
4532 }
4533
4534 /**
4535 * Returns the object representing the Unicode block
4536 * containing the given character (Unicode code point), or
4537 * {@code null} if the character is not a member of a
4538 * defined block.
4539 *
4540 * @param codePoint the character (Unicode code point) in question.
4541 * @return The {@code UnicodeBlock} instance representing the
4542 * Unicode block of which this character is a member, or
4543 * {@code null} if the character is not a member of any
4544 * Unicode block
4545 * @throws IllegalArgumentException if the specified
4546 * {@code codePoint} is an invalid Unicode code point.
4547 * @see Character#isValidCodePoint(int)
4548 * @since 1.5
4549 */
4550 public static UnicodeBlock of(int codePoint) {
4551 if (!isValidCodePoint(codePoint)) {
4552 throw new IllegalArgumentException(
4553 String.format("Not a valid Unicode code point: 0x%X", codePoint));
4554 }
4555
4556 int top, bottom, current;
4557 bottom = 0;
4558 top = blockStarts.length;
4559 current = top/2;
4560
4561 // invariant: top > current >= bottom && codePoint >= unicodeBlockStarts[bottom]
4562 while (top - bottom > 1) {
4563 if (codePoint >= blockStarts[current]) {
4564 bottom = current;
4565 } else {
4566 top = current;
4567 }
4568 current = (top + bottom) / 2;
4569 }
4570 return blocks[current];
4571 }
4572
4573 /**
4574 * Returns the UnicodeBlock with the given name. Block
4575 * names are determined by The Unicode Standard. The file
4576 * {@code Blocks.txt} defines blocks for a particular
4577 * version of the standard. The {@link Character} class specifies
4578 * the version of the standard that it supports.
4579 * <p>
4580 * This method accepts block names in the following forms:
4581 * <ol>
4582 * <li> Canonical block names as defined by the Unicode Standard.
4583 * For example, the standard defines a "Basic Latin" block. Therefore, this
4584 * method accepts "Basic Latin" as a valid block name. The documentation of
4585 * each UnicodeBlock provides the canonical name.
4586 * <li>Canonical block names with all spaces removed. For example, "BasicLatin"
4587 * is a valid block name for the "Basic Latin" block.
4588 * <li>The text representation of each constant UnicodeBlock identifier.
4589 * For example, this method will return the {@link #BASIC_LATIN} block if
4590 * provided with the "BASIC_LATIN" name. This form replaces all spaces and
4591 * hyphens in the canonical name with underscores.
4592 * </ol>
4593 * Finally, character case is ignored for all of the valid block name forms.
4594 * For example, "BASIC_LATIN" and "basic_latin" are both valid block names.
4595 * The en_US locale's case mapping rules are used to provide case-insensitive
4596 * string comparisons for block name validation.
4597 * <p>
4598 * If the Unicode Standard changes block names, both the previous and
4599 * current names will be accepted.
4600 *
4601 * @param blockName A {@code UnicodeBlock} name.
4602 * @return The {@code UnicodeBlock} instance identified
4603 * by {@code blockName}
4604 * @throws IllegalArgumentException if {@code blockName} is an
4605 * invalid name
4606 * @throws NullPointerException if {@code blockName} is null
4607 * @since 1.5
4608 */
4609 public static final UnicodeBlock forName(String blockName) {
4610 UnicodeBlock block = map.get(blockName.toUpperCase(Locale.US));
4611 if (block == null) {
4612 throw new IllegalArgumentException("Not a valid block name: "
4613 + blockName);
4614 }
4615 return block;
4616 }
4617 }
4618
4619
4620 /**
4621 * A family of character subsets representing the character scripts
4622 * defined in the <a href="http://www.unicode.org/reports/tr24/">
4623 * <i>Unicode Standard Annex #24: Script Names</i></a>. Every Unicode
4624 * character is assigned to a single Unicode script, either a specific
4625 * script, such as {@link Character.UnicodeScript#LATIN Latin}, or
4626 * one of the following three special values,
4627 * {@link Character.UnicodeScript#INHERITED Inherited},
4628 * {@link Character.UnicodeScript#COMMON Common} or
4629 * {@link Character.UnicodeScript#UNKNOWN Unknown}.
4630 *
4631 * @spec https://www.unicode.org/reports/tr24 Unicode Script Property
4632 * @since 1.7
4633 */
4634 public static enum UnicodeScript {
4635
4636 /**
4637 * Unicode script "Common".
4638 */
4639 COMMON,
4640
4641 /**
4642 * Unicode script "Latin".
4643 */
4644 LATIN,
4645
4646 /**
4647 * Unicode script "Greek".
4648 */
4649 GREEK,
4650
4651 /**
4652 * Unicode script "Cyrillic".
4653 */
4654 CYRILLIC,
4655
4656 /**
4657 * Unicode script "Armenian".
4658 */
4659 ARMENIAN,
4660
4661 /**
4662 * Unicode script "Hebrew".
4663 */
4664 HEBREW,
4665
4666 /**
4667 * Unicode script "Arabic".
4668 */
4669 ARABIC,
4670
4671 /**
4672 * Unicode script "Syriac".
4673 */
4674 SYRIAC,
4675
4676 /**
4677 * Unicode script "Thaana".
4678 */
4679 THAANA,
4680
4681 /**
4682 * Unicode script "Devanagari".
4683 */
4684 DEVANAGARI,
4685
4686 /**
4687 * Unicode script "Bengali".
4688 */
4689 BENGALI,
4690
4691 /**
4692 * Unicode script "Gurmukhi".
4693 */
4694 GURMUKHI,
4695
4696 /**
4697 * Unicode script "Gujarati".
4698 */
4699 GUJARATI,
4700
4701 /**
4702 * Unicode script "Oriya".
4703 */
4704 ORIYA,
4705
4706 /**
4707 * Unicode script "Tamil".
4708 */
4709 TAMIL,
4710
4711 /**
4712 * Unicode script "Telugu".
4713 */
4714 TELUGU,
4715
4716 /**
4717 * Unicode script "Kannada".
4718 */
4719 KANNADA,
4720
4721 /**
4722 * Unicode script "Malayalam".
4723 */
4724 MALAYALAM,
4725
4726 /**
4727 * Unicode script "Sinhala".
4728 */
4729 SINHALA,
4730
4731 /**
4732 * Unicode script "Thai".
4733 */
4734 THAI,
4735
4736 /**
4737 * Unicode script "Lao".
4738 */
4739 LAO,
4740
4741 /**
4742 * Unicode script "Tibetan".
4743 */
4744 TIBETAN,
4745
4746 /**
4747 * Unicode script "Myanmar".
4748 */
4749 MYANMAR,
4750
4751 /**
4752 * Unicode script "Georgian".
4753 */
4754 GEORGIAN,
4755
4756 /**
4757 * Unicode script "Hangul".
4758 */
4759 HANGUL,
4760
4761 /**
4762 * Unicode script "Ethiopic".
4763 */
4764 ETHIOPIC,
4765
4766 /**
4767 * Unicode script "Cherokee".
4768 */
4769 CHEROKEE,
4770
4771 /**
4772 * Unicode script "Canadian_Aboriginal".
4773 */
4774 CANADIAN_ABORIGINAL,
4775
4776 /**
4777 * Unicode script "Ogham".
4778 */
4779 OGHAM,
4780
4781 /**
4782 * Unicode script "Runic".
4783 */
4784 RUNIC,
4785
4786 /**
4787 * Unicode script "Khmer".
4788 */
4789 KHMER,
4790
4791 /**
4792 * Unicode script "Mongolian".
4793 */
4794 MONGOLIAN,
4795
4796 /**
4797 * Unicode script "Hiragana".
4798 */
4799 HIRAGANA,
4800
4801 /**
4802 * Unicode script "Katakana".
4803 */
4804 KATAKANA,
4805
4806 /**
4807 * Unicode script "Bopomofo".
4808 */
4809 BOPOMOFO,
4810
4811 /**
4812 * Unicode script "Han".
4813 */
4814 HAN,
4815
4816 /**
4817 * Unicode script "Yi".
4818 */
4819 YI,
4820
4821 /**
4822 * Unicode script "Old_Italic".
4823 */
4824 OLD_ITALIC,
4825
4826 /**
4827 * Unicode script "Gothic".
4828 */
4829 GOTHIC,
4830
4831 /**
4832 * Unicode script "Deseret".
4833 */
4834 DESERET,
4835
4836 /**
4837 * Unicode script "Inherited".
4838 */
4839 INHERITED,
4840
4841 /**
4842 * Unicode script "Tagalog".
4843 */
4844 TAGALOG,
4845
4846 /**
4847 * Unicode script "Hanunoo".
4848 */
4849 HANUNOO,
4850
4851 /**
4852 * Unicode script "Buhid".
4853 */
4854 BUHID,
4855
4856 /**
4857 * Unicode script "Tagbanwa".
4858 */
4859 TAGBANWA,
4860
4861 /**
4862 * Unicode script "Limbu".
4863 */
4864 LIMBU,
4865
4866 /**
4867 * Unicode script "Tai_Le".
4868 */
4869 TAI_LE,
4870
4871 /**
4872 * Unicode script "Linear_B".
4873 */
4874 LINEAR_B,
4875
4876 /**
4877 * Unicode script "Ugaritic".
4878 */
4879 UGARITIC,
4880
4881 /**
4882 * Unicode script "Shavian".
4883 */
4884 SHAVIAN,
4885
4886 /**
4887 * Unicode script "Osmanya".
4888 */
4889 OSMANYA,
4890
4891 /**
4892 * Unicode script "Cypriot".
4893 */
4894 CYPRIOT,
4895
4896 /**
4897 * Unicode script "Braille".
4898 */
4899 BRAILLE,
4900
4901 /**
4902 * Unicode script "Buginese".
4903 */
4904 BUGINESE,
4905
4906 /**
4907 * Unicode script "Coptic".
4908 */
4909 COPTIC,
4910
4911 /**
4912 * Unicode script "New_Tai_Lue".
4913 */
4914 NEW_TAI_LUE,
4915
4916 /**
4917 * Unicode script "Glagolitic".
4918 */
4919 GLAGOLITIC,
4920
4921 /**
4922 * Unicode script "Tifinagh".
4923 */
4924 TIFINAGH,
4925
4926 /**
4927 * Unicode script "Syloti_Nagri".
4928 */
4929 SYLOTI_NAGRI,
4930
4931 /**
4932 * Unicode script "Old_Persian".
4933 */
4934 OLD_PERSIAN,
4935
4936 /**
4937 * Unicode script "Kharoshthi".
4938 */
4939 KHAROSHTHI,
4940
4941 /**
4942 * Unicode script "Balinese".
4943 */
4944 BALINESE,
4945
4946 /**
4947 * Unicode script "Cuneiform".
4948 */
4949 CUNEIFORM,
4950
4951 /**
4952 * Unicode script "Phoenician".
4953 */
4954 PHOENICIAN,
4955
4956 /**
4957 * Unicode script "Phags_Pa".
4958 */
4959 PHAGS_PA,
4960
4961 /**
4962 * Unicode script "Nko".
4963 */
4964 NKO,
4965
4966 /**
4967 * Unicode script "Sundanese".
4968 */
4969 SUNDANESE,
4970
4971 /**
4972 * Unicode script "Batak".
4973 */
4974 BATAK,
4975
4976 /**
4977 * Unicode script "Lepcha".
4978 */
4979 LEPCHA,
4980
4981 /**
4982 * Unicode script "Ol_Chiki".
4983 */
4984 OL_CHIKI,
4985
4986 /**
4987 * Unicode script "Vai".
4988 */
4989 VAI,
4990
4991 /**
4992 * Unicode script "Saurashtra".
4993 */
4994 SAURASHTRA,
4995
4996 /**
4997 * Unicode script "Kayah_Li".
4998 */
4999 KAYAH_LI,
5000
5001 /**
5002 * Unicode script "Rejang".
5003 */
5004 REJANG,
5005
5006 /**
5007 * Unicode script "Lycian".
5008 */
5009 LYCIAN,
5010
5011 /**
5012 * Unicode script "Carian".
5013 */
5014 CARIAN,
5015
5016 /**
5017 * Unicode script "Lydian".
5018 */
5019 LYDIAN,
5020
5021 /**
5022 * Unicode script "Cham".
5023 */
5024 CHAM,
5025
5026 /**
5027 * Unicode script "Tai_Tham".
5028 */
5029 TAI_THAM,
5030
5031 /**
5032 * Unicode script "Tai_Viet".
5033 */
5034 TAI_VIET,
5035
5036 /**
5037 * Unicode script "Avestan".
5038 */
5039 AVESTAN,
5040
5041 /**
5042 * Unicode script "Egyptian_Hieroglyphs".
5043 */
5044 EGYPTIAN_HIEROGLYPHS,
5045
5046 /**
5047 * Unicode script "Samaritan".
5048 */
5049 SAMARITAN,
5050
5051 /**
5052 * Unicode script "Mandaic".
5053 */
5054 MANDAIC,
5055
5056 /**
5057 * Unicode script "Lisu".
5058 */
5059 LISU,
5060
5061 /**
5062 * Unicode script "Bamum".
5063 */
5064 BAMUM,
5065
5066 /**
5067 * Unicode script "Javanese".
5068 */
5069 JAVANESE,
5070
5071 /**
5072 * Unicode script "Meetei_Mayek".
5073 */
5074 MEETEI_MAYEK,
5075
5076 /**
5077 * Unicode script "Imperial_Aramaic".
5078 */
5079 IMPERIAL_ARAMAIC,
5080
5081 /**
5082 * Unicode script "Old_South_Arabian".
5083 */
5084 OLD_SOUTH_ARABIAN,
5085
5086 /**
5087 * Unicode script "Inscriptional_Parthian".
5088 */
5089 INSCRIPTIONAL_PARTHIAN,
5090
5091 /**
5092 * Unicode script "Inscriptional_Pahlavi".
5093 */
5094 INSCRIPTIONAL_PAHLAVI,
5095
5096 /**
5097 * Unicode script "Old_Turkic".
5098 */
5099 OLD_TURKIC,
5100
5101 /**
5102 * Unicode script "Brahmi".
5103 */
5104 BRAHMI,
5105
5106 /**
5107 * Unicode script "Kaithi".
5108 */
5109 KAITHI,
5110
5111 /**
5112 * Unicode script "Meroitic Hieroglyphs".
5113 * @since 1.8
5114 */
5115 MEROITIC_HIEROGLYPHS,
5116
5117 /**
5118 * Unicode script "Meroitic Cursive".
5119 * @since 1.8
5120 */
5121 MEROITIC_CURSIVE,
5122
5123 /**
5124 * Unicode script "Sora Sompeng".
5125 * @since 1.8
5126 */
5127 SORA_SOMPENG,
5128
5129 /**
5130 * Unicode script "Chakma".
5131 * @since 1.8
5132 */
5133 CHAKMA,
5134
5135 /**
5136 * Unicode script "Sharada".
5137 * @since 1.8
5138 */
5139 SHARADA,
5140
5141 /**
5142 * Unicode script "Takri".
5143 * @since 1.8
5144 */
5145 TAKRI,
5146
5147 /**
5148 * Unicode script "Miao".
5149 * @since 1.8
5150 */
5151 MIAO,
5152
5153 /**
5154 * Unicode script "Caucasian Albanian".
5155 * @since 9
5156 */
5157 CAUCASIAN_ALBANIAN,
5158
5159 /**
5160 * Unicode script "Bassa Vah".
5161 * @since 9
5162 */
5163 BASSA_VAH,
5164
5165 /**
5166 * Unicode script "Duployan".
5167 * @since 9
5168 */
5169 DUPLOYAN,
5170
5171 /**
5172 * Unicode script "Elbasan".
5173 * @since 9
5174 */
5175 ELBASAN,
5176
5177 /**
5178 * Unicode script "Grantha".
5179 * @since 9
5180 */
5181 GRANTHA,
5182
5183 /**
5184 * Unicode script "Pahawh Hmong".
5185 * @since 9
5186 */
5187 PAHAWH_HMONG,
5188
5189 /**
5190 * Unicode script "Khojki".
5191 * @since 9
5192 */
5193 KHOJKI,
5194
5195 /**
5196 * Unicode script "Linear A".
5197 * @since 9
5198 */
5199 LINEAR_A,
5200
5201 /**
5202 * Unicode script "Mahajani".
5203 * @since 9
5204 */
5205 MAHAJANI,
5206
5207 /**
5208 * Unicode script "Manichaean".
5209 * @since 9
5210 */
5211 MANICHAEAN,
5212
5213 /**
5214 * Unicode script "Mende Kikakui".
5215 * @since 9
5216 */
5217 MENDE_KIKAKUI,
5218
5219 /**
5220 * Unicode script "Modi".
5221 * @since 9
5222 */
5223 MODI,
5224
5225 /**
5226 * Unicode script "Mro".
5227 * @since 9
5228 */
5229 MRO,
5230
5231 /**
5232 * Unicode script "Old North Arabian".
5233 * @since 9
5234 */
5235 OLD_NORTH_ARABIAN,
5236
5237 /**
5238 * Unicode script "Nabataean".
5239 * @since 9
5240 */
5241 NABATAEAN,
5242
5243 /**
5244 * Unicode script "Palmyrene".
5245 * @since 9
5246 */
5247 PALMYRENE,
5248
5249 /**
5250 * Unicode script "Pau Cin Hau".
5251 * @since 9
5252 */
5253 PAU_CIN_HAU,
5254
5255 /**
5256 * Unicode script "Old Permic".
5257 * @since 9
5258 */
5259 OLD_PERMIC,
5260
5261 /**
5262 * Unicode script "Psalter Pahlavi".
5263 * @since 9
5264 */
5265 PSALTER_PAHLAVI,
5266
5267 /**
5268 * Unicode script "Siddham".
5269 * @since 9
5270 */
5271 SIDDHAM,
5272
5273 /**
5274 * Unicode script "Khudawadi".
5275 * @since 9
5276 */
5277 KHUDAWADI,
5278
5279 /**
5280 * Unicode script "Tirhuta".
5281 * @since 9
5282 */
5283 TIRHUTA,
5284
5285 /**
5286 * Unicode script "Warang Citi".
5287 * @since 9
5288 */
5289 WARANG_CITI,
5290
5291 /**
5292 * Unicode script "Ahom".
5293 * @since 9
5294 */
5295 AHOM,
5296
5297 /**
5298 * Unicode script "Anatolian Hieroglyphs".
5299 * @since 9
5300 */
5301 ANATOLIAN_HIEROGLYPHS,
5302
5303 /**
5304 * Unicode script "Hatran".
5305 * @since 9
5306 */
5307 HATRAN,
5308
5309 /**
5310 * Unicode script "Multani".
5311 * @since 9
5312 */
5313 MULTANI,
5314
5315 /**
5316 * Unicode script "Old Hungarian".
5317 * @since 9
5318 */
5319 OLD_HUNGARIAN,
5320
5321 /**
5322 * Unicode script "SignWriting".
5323 * @since 9
5324 */
5325 SIGNWRITING,
5326
5327 /**
5328 * Unicode script "Adlam".
5329 * @since 11
5330 */
5331 ADLAM,
5332
5333 /**
5334 * Unicode script "Bhaiksuki".
5335 * @since 11
5336 */
5337 BHAIKSUKI,
5338
5339 /**
5340 * Unicode script "Marchen".
5341 * @since 11
5342 */
5343 MARCHEN,
5344
5345 /**
5346 * Unicode script "Newa".
5347 * @since 11
5348 */
5349 NEWA,
5350
5351 /**
5352 * Unicode script "Osage".
5353 * @since 11
5354 */
5355 OSAGE,
5356
5357 /**
5358 * Unicode script "Tangut".
5359 * @since 11
5360 */
5361 TANGUT,
5362
5363 /**
5364 * Unicode script "Masaram Gondi".
5365 * @since 11
5366 */
5367 MASARAM_GONDI,
5368
5369 /**
5370 * Unicode script "Nushu".
5371 * @since 11
5372 */
5373 NUSHU,
5374
5375 /**
5376 * Unicode script "Soyombo".
5377 * @since 11
5378 */
5379 SOYOMBO,
5380
5381 /**
5382 * Unicode script "Zanabazar Square".
5383 * @since 11
5384 */
5385 ZANABAZAR_SQUARE,
5386
5387 /**
5388 * Unicode script "Hanifi Rohingya".
5389 * @since 12
5390 */
5391 HANIFI_ROHINGYA,
5392
5393 /**
5394 * Unicode script "Old Sogdian".
5395 * @since 12
5396 */
5397 OLD_SOGDIAN,
5398
5399 /**
5400 * Unicode script "Sogdian".
5401 * @since 12
5402 */
5403 SOGDIAN,
5404
5405 /**
5406 * Unicode script "Dogra".
5407 * @since 12
5408 */
5409 DOGRA,
5410
5411 /**
5412 * Unicode script "Gunjala Gondi".
5413 * @since 12
5414 */
5415 GUNJALA_GONDI,
5416
5417 /**
5418 * Unicode script "Makasar".
5419 * @since 12
5420 */
5421 MAKASAR,
5422
5423 /**
5424 * Unicode script "Medefaidrin".
5425 * @since 12
5426 */
5427 MEDEFAIDRIN,
5428
5429 /**
5430 * Unicode script "Elymaic".
5431 * @since 13
5432 */
5433 ELYMAIC,
5434
5435 /**
5436 * Unicode script "Nandinagari".
5437 * @since 13
5438 */
5439 NANDINAGARI,
5440
5441 /**
5442 * Unicode script "Nyiakeng Puachue Hmong".
5443 * @since 13
5444 */
5445 NYIAKENG_PUACHUE_HMONG,
5446
5447 /**
5448 * Unicode script "Wancho".
5449 * @since 13
5450 */
5451 WANCHO,
5452
5453 /**
5454 * Unicode script "Yezidi".
5455 * @since 15
5456 */
5457 YEZIDI,
5458
5459 /**
5460 * Unicode script "Chorasmian".
5461 * @since 15
5462 */
5463 CHORASMIAN,
5464
5465 /**
5466 * Unicode script "Dives Akuru".
5467 * @since 15
5468 */
5469 DIVES_AKURU,
5470
5471 /**
5472 * Unicode script "Khitan Small Script".
5473 * @since 15
5474 */
5475 KHITAN_SMALL_SCRIPT,
5476
5477 /**
5478 * Unicode script "Vithkuqi".
5479 * @since 19
5480 */
5481 VITHKUQI,
5482
5483 /**
5484 * Unicode script "Old Uyghur".
5485 * @since 19
5486 */
5487 OLD_UYGHUR,
5488
5489 /**
5490 * Unicode script "Cypro Minoan".
5491 * @since 19
5492 */
5493 CYPRO_MINOAN,
5494
5495 /**
5496 * Unicode script "Tangsa".
5497 * @since 19
5498 */
5499 TANGSA,
5500
5501 /**
5502 * Unicode script "Toto".
5503 * @since 19
5504 */
5505 TOTO,
5506
5507 /**
5508 * Unicode script "Kawi".
5509 * @since 20
5510 */
5511 KAWI,
5512
5513 /**
5514 * Unicode script "Nag Mundari".
5515 * @since 20
5516 */
5517 NAG_MUNDARI,
5518
5519 /**
5520 * Unicode script "Todhri".
5521 * @since 24
5522 */
5523 TODHRI,
5524
5525 /**
5526 * Unicode script "Garay".
5527 * @since 24
5528 */
5529 GARAY,
5530
5531 /**
5532 * Unicode script "Tulu Tigalari".
5533 * @since 24
5534 */
5535 TULU_TIGALARI,
5536
5537 /**
5538 * Unicode script "Sunuwar".
5539 * @since 24
5540 */
5541 SUNUWAR,
5542
5543 /**
5544 * Unicode script "Gurung Khema".
5545 * @since 24
5546 */
5547 GURUNG_KHEMA,
5548
5549 /**
5550 * Unicode script "Kirat Rai".
5551 * @since 24
5552 */
5553 KIRAT_RAI,
5554
5555 /**
5556 * Unicode script "Ol Onal".
5557 * @since 24
5558 */
5559 OL_ONAL,
5560
5561 /**
5562 * Unicode script "Unknown".
5563 */
5564 UNKNOWN; // must be the last enum constant for calculating the size of "aliases" hash map.
5565
5566 private static final int[] scriptStarts = {
5567 0x0000, // 0000..0040; COMMON
5568 0x0041, // 0041..005A; LATIN
5569 0x005B, // 005B..0060; COMMON
5570 0x0061, // 0061..007A; LATIN
5571 0x007B, // 007B..00A9; COMMON
5572 0x00AA, // 00AA ; LATIN
5573 0x00AB, // 00AB..00B9; COMMON
5574 0x00BA, // 00BA ; LATIN
5575 0x00BB, // 00BB..00BF; COMMON
5576 0x00C0, // 00C0..00D6; LATIN
5577 0x00D7, // 00D7 ; COMMON
5578 0x00D8, // 00D8..00F6; LATIN
5579 0x00F7, // 00F7 ; COMMON
5580 0x00F8, // 00F8..02B8; LATIN
5581 0x02B9, // 02B9..02DF; COMMON
5582 0x02E0, // 02E0..02E4; LATIN
5583 0x02E5, // 02E5..02E9; COMMON
5584 0x02EA, // 02EA..02EB; BOPOMOFO
5585 0x02EC, // 02EC..02FF; COMMON
5586 0x0300, // 0300..036F; INHERITED
5587 0x0370, // 0370..0373; GREEK
5588 0x0374, // 0374 ; COMMON
5589 0x0375, // 0375..0377; GREEK
5590 0x0378, // 0378..0379; UNKNOWN
5591 0x037A, // 037A..037D; GREEK
5592 0x037E, // 037E ; COMMON
5593 0x037F, // 037F ; GREEK
5594 0x0380, // 0380..0383; UNKNOWN
5595 0x0384, // 0384 ; GREEK
5596 0x0385, // 0385 ; COMMON
5597 0x0386, // 0386 ; GREEK
5598 0x0387, // 0387 ; COMMON
5599 0x0388, // 0388..038A; GREEK
5600 0x038B, // 038B ; UNKNOWN
5601 0x038C, // 038C ; GREEK
5602 0x038D, // 038D ; UNKNOWN
5603 0x038E, // 038E..03A1; GREEK
5604 0x03A2, // 03A2 ; UNKNOWN
5605 0x03A3, // 03A3..03E1; GREEK
5606 0x03E2, // 03E2..03EF; COPTIC
5607 0x03F0, // 03F0..03FF; GREEK
5608 0x0400, // 0400..0484; CYRILLIC
5609 0x0485, // 0485..0486; INHERITED
5610 0x0487, // 0487..052F; CYRILLIC
5611 0x0530, // 0530 ; UNKNOWN
5612 0x0531, // 0531..0556; ARMENIAN
5613 0x0557, // 0557..0558; UNKNOWN
5614 0x0559, // 0559..058A; ARMENIAN
5615 0x058B, // 058B..058C; UNKNOWN
5616 0x058D, // 058D..058F; ARMENIAN
5617 0x0590, // 0590 ; UNKNOWN
5618 0x0591, // 0591..05C7; HEBREW
5619 0x05C8, // 05C8..05CF; UNKNOWN
5620 0x05D0, // 05D0..05EA; HEBREW
5621 0x05EB, // 05EB..05EE; UNKNOWN
5622 0x05EF, // 05EF..05F4; HEBREW
5623 0x05F5, // 05F5..05FF; UNKNOWN
5624 0x0600, // 0600..0604; ARABIC
5625 0x0605, // 0605 ; COMMON
5626 0x0606, // 0606..060B; ARABIC
5627 0x060C, // 060C ; COMMON
5628 0x060D, // 060D..061A; ARABIC
5629 0x061B, // 061B ; COMMON
5630 0x061C, // 061C..061E; ARABIC
5631 0x061F, // 061F ; COMMON
5632 0x0620, // 0620..063F; ARABIC
5633 0x0640, // 0640 ; COMMON
5634 0x0641, // 0641..064A; ARABIC
5635 0x064B, // 064B..0655; INHERITED
5636 0x0656, // 0656..066F; ARABIC
5637 0x0670, // 0670 ; INHERITED
5638 0x0671, // 0671..06DC; ARABIC
5639 0x06DD, // 06DD ; COMMON
5640 0x06DE, // 06DE..06FF; ARABIC
5641 0x0700, // 0700..070D; SYRIAC
5642 0x070E, // 070E ; UNKNOWN
5643 0x070F, // 070F..074A; SYRIAC
5644 0x074B, // 074B..074C; UNKNOWN
5645 0x074D, // 074D..074F; SYRIAC
5646 0x0750, // 0750..077F; ARABIC
5647 0x0780, // 0780..07B1; THAANA
5648 0x07B2, // 07B2..07BF; UNKNOWN
5649 0x07C0, // 07C0..07FA; NKO
5650 0x07FB, // 07FB..07FC; UNKNOWN
5651 0x07FD, // 07FD..07FF; NKO
5652 0x0800, // 0800..082D; SAMARITAN
5653 0x082E, // 082E..082F; UNKNOWN
5654 0x0830, // 0830..083E; SAMARITAN
5655 0x083F, // 083F ; UNKNOWN
5656 0x0840, // 0840..085B; MANDAIC
5657 0x085C, // 085C..085D; UNKNOWN
5658 0x085E, // 085E ; MANDAIC
5659 0x085F, // 085F ; UNKNOWN
5660 0x0860, // 0860..086A; SYRIAC
5661 0x086B, // 086B..086F; UNKNOWN
5662 0x0870, // 0870..088E; ARABIC
5663 0x088F, // 088F ; UNKNOWN
5664 0x0890, // 0890..0891; ARABIC
5665 0x0892, // 0892..0896; UNKNOWN
5666 0x0897, // 0897..08E1; ARABIC
5667 0x08E2, // 08E2 ; COMMON
5668 0x08E3, // 08E3..08FF; ARABIC
5669 0x0900, // 0900..0950; DEVANAGARI
5670 0x0951, // 0951..0954; INHERITED
5671 0x0955, // 0955..0963; DEVANAGARI
5672 0x0964, // 0964..0965; COMMON
5673 0x0966, // 0966..097F; DEVANAGARI
5674 0x0980, // 0980..0983; BENGALI
5675 0x0984, // 0984 ; UNKNOWN
5676 0x0985, // 0985..098C; BENGALI
5677 0x098D, // 098D..098E; UNKNOWN
5678 0x098F, // 098F..0990; BENGALI
5679 0x0991, // 0991..0992; UNKNOWN
5680 0x0993, // 0993..09A8; BENGALI
5681 0x09A9, // 09A9 ; UNKNOWN
5682 0x09AA, // 09AA..09B0; BENGALI
5683 0x09B1, // 09B1 ; UNKNOWN
5684 0x09B2, // 09B2 ; BENGALI
5685 0x09B3, // 09B3..09B5; UNKNOWN
5686 0x09B6, // 09B6..09B9; BENGALI
5687 0x09BA, // 09BA..09BB; UNKNOWN
5688 0x09BC, // 09BC..09C4; BENGALI
5689 0x09C5, // 09C5..09C6; UNKNOWN
5690 0x09C7, // 09C7..09C8; BENGALI
5691 0x09C9, // 09C9..09CA; UNKNOWN
5692 0x09CB, // 09CB..09CE; BENGALI
5693 0x09CF, // 09CF..09D6; UNKNOWN
5694 0x09D7, // 09D7 ; BENGALI
5695 0x09D8, // 09D8..09DB; UNKNOWN
5696 0x09DC, // 09DC..09DD; BENGALI
5697 0x09DE, // 09DE ; UNKNOWN
5698 0x09DF, // 09DF..09E3; BENGALI
5699 0x09E4, // 09E4..09E5; UNKNOWN
5700 0x09E6, // 09E6..09FE; BENGALI
5701 0x09FF, // 09FF..0A00; UNKNOWN
5702 0x0A01, // 0A01..0A03; GURMUKHI
5703 0x0A04, // 0A04 ; UNKNOWN
5704 0x0A05, // 0A05..0A0A; GURMUKHI
5705 0x0A0B, // 0A0B..0A0E; UNKNOWN
5706 0x0A0F, // 0A0F..0A10; GURMUKHI
5707 0x0A11, // 0A11..0A12; UNKNOWN
5708 0x0A13, // 0A13..0A28; GURMUKHI
5709 0x0A29, // 0A29 ; UNKNOWN
5710 0x0A2A, // 0A2A..0A30; GURMUKHI
5711 0x0A31, // 0A31 ; UNKNOWN
5712 0x0A32, // 0A32..0A33; GURMUKHI
5713 0x0A34, // 0A34 ; UNKNOWN
5714 0x0A35, // 0A35..0A36; GURMUKHI
5715 0x0A37, // 0A37 ; UNKNOWN
5716 0x0A38, // 0A38..0A39; GURMUKHI
5717 0x0A3A, // 0A3A..0A3B; UNKNOWN
5718 0x0A3C, // 0A3C ; GURMUKHI
5719 0x0A3D, // 0A3D ; UNKNOWN
5720 0x0A3E, // 0A3E..0A42; GURMUKHI
5721 0x0A43, // 0A43..0A46; UNKNOWN
5722 0x0A47, // 0A47..0A48; GURMUKHI
5723 0x0A49, // 0A49..0A4A; UNKNOWN
5724 0x0A4B, // 0A4B..0A4D; GURMUKHI
5725 0x0A4E, // 0A4E..0A50; UNKNOWN
5726 0x0A51, // 0A51 ; GURMUKHI
5727 0x0A52, // 0A52..0A58; UNKNOWN
5728 0x0A59, // 0A59..0A5C; GURMUKHI
5729 0x0A5D, // 0A5D ; UNKNOWN
5730 0x0A5E, // 0A5E ; GURMUKHI
5731 0x0A5F, // 0A5F..0A65; UNKNOWN
5732 0x0A66, // 0A66..0A76; GURMUKHI
5733 0x0A77, // 0A77..0A80; UNKNOWN
5734 0x0A81, // 0A81..0A83; GUJARATI
5735 0x0A84, // 0A84 ; UNKNOWN
5736 0x0A85, // 0A85..0A8D; GUJARATI
5737 0x0A8E, // 0A8E ; UNKNOWN
5738 0x0A8F, // 0A8F..0A91; GUJARATI
5739 0x0A92, // 0A92 ; UNKNOWN
5740 0x0A93, // 0A93..0AA8; GUJARATI
5741 0x0AA9, // 0AA9 ; UNKNOWN
5742 0x0AAA, // 0AAA..0AB0; GUJARATI
5743 0x0AB1, // 0AB1 ; UNKNOWN
5744 0x0AB2, // 0AB2..0AB3; GUJARATI
5745 0x0AB4, // 0AB4 ; UNKNOWN
5746 0x0AB5, // 0AB5..0AB9; GUJARATI
5747 0x0ABA, // 0ABA..0ABB; UNKNOWN
5748 0x0ABC, // 0ABC..0AC5; GUJARATI
5749 0x0AC6, // 0AC6 ; UNKNOWN
5750 0x0AC7, // 0AC7..0AC9; GUJARATI
5751 0x0ACA, // 0ACA ; UNKNOWN
5752 0x0ACB, // 0ACB..0ACD; GUJARATI
5753 0x0ACE, // 0ACE..0ACF; UNKNOWN
5754 0x0AD0, // 0AD0 ; GUJARATI
5755 0x0AD1, // 0AD1..0ADF; UNKNOWN
5756 0x0AE0, // 0AE0..0AE3; GUJARATI
5757 0x0AE4, // 0AE4..0AE5; UNKNOWN
5758 0x0AE6, // 0AE6..0AF1; GUJARATI
5759 0x0AF2, // 0AF2..0AF8; UNKNOWN
5760 0x0AF9, // 0AF9..0AFF; GUJARATI
5761 0x0B00, // 0B00 ; UNKNOWN
5762 0x0B01, // 0B01..0B03; ORIYA
5763 0x0B04, // 0B04 ; UNKNOWN
5764 0x0B05, // 0B05..0B0C; ORIYA
5765 0x0B0D, // 0B0D..0B0E; UNKNOWN
5766 0x0B0F, // 0B0F..0B10; ORIYA
5767 0x0B11, // 0B11..0B12; UNKNOWN
5768 0x0B13, // 0B13..0B28; ORIYA
5769 0x0B29, // 0B29 ; UNKNOWN
5770 0x0B2A, // 0B2A..0B30; ORIYA
5771 0x0B31, // 0B31 ; UNKNOWN
5772 0x0B32, // 0B32..0B33; ORIYA
5773 0x0B34, // 0B34 ; UNKNOWN
5774 0x0B35, // 0B35..0B39; ORIYA
5775 0x0B3A, // 0B3A..0B3B; UNKNOWN
5776 0x0B3C, // 0B3C..0B44; ORIYA
5777 0x0B45, // 0B45..0B46; UNKNOWN
5778 0x0B47, // 0B47..0B48; ORIYA
5779 0x0B49, // 0B49..0B4A; UNKNOWN
5780 0x0B4B, // 0B4B..0B4D; ORIYA
5781 0x0B4E, // 0B4E..0B54; UNKNOWN
5782 0x0B55, // 0B55..0B57; ORIYA
5783 0x0B58, // 0B58..0B5B; UNKNOWN
5784 0x0B5C, // 0B5C..0B5D; ORIYA
5785 0x0B5E, // 0B5E ; UNKNOWN
5786 0x0B5F, // 0B5F..0B63; ORIYA
5787 0x0B64, // 0B64..0B65; UNKNOWN
5788 0x0B66, // 0B66..0B77; ORIYA
5789 0x0B78, // 0B78..0B81; UNKNOWN
5790 0x0B82, // 0B82..0B83; TAMIL
5791 0x0B84, // 0B84 ; UNKNOWN
5792 0x0B85, // 0B85..0B8A; TAMIL
5793 0x0B8B, // 0B8B..0B8D; UNKNOWN
5794 0x0B8E, // 0B8E..0B90; TAMIL
5795 0x0B91, // 0B91 ; UNKNOWN
5796 0x0B92, // 0B92..0B95; TAMIL
5797 0x0B96, // 0B96..0B98; UNKNOWN
5798 0x0B99, // 0B99..0B9A; TAMIL
5799 0x0B9B, // 0B9B ; UNKNOWN
5800 0x0B9C, // 0B9C ; TAMIL
5801 0x0B9D, // 0B9D ; UNKNOWN
5802 0x0B9E, // 0B9E..0B9F; TAMIL
5803 0x0BA0, // 0BA0..0BA2; UNKNOWN
5804 0x0BA3, // 0BA3..0BA4; TAMIL
5805 0x0BA5, // 0BA5..0BA7; UNKNOWN
5806 0x0BA8, // 0BA8..0BAA; TAMIL
5807 0x0BAB, // 0BAB..0BAD; UNKNOWN
5808 0x0BAE, // 0BAE..0BB9; TAMIL
5809 0x0BBA, // 0BBA..0BBD; UNKNOWN
5810 0x0BBE, // 0BBE..0BC2; TAMIL
5811 0x0BC3, // 0BC3..0BC5; UNKNOWN
5812 0x0BC6, // 0BC6..0BC8; TAMIL
5813 0x0BC9, // 0BC9 ; UNKNOWN
5814 0x0BCA, // 0BCA..0BCD; TAMIL
5815 0x0BCE, // 0BCE..0BCF; UNKNOWN
5816 0x0BD0, // 0BD0 ; TAMIL
5817 0x0BD1, // 0BD1..0BD6; UNKNOWN
5818 0x0BD7, // 0BD7 ; TAMIL
5819 0x0BD8, // 0BD8..0BE5; UNKNOWN
5820 0x0BE6, // 0BE6..0BFA; TAMIL
5821 0x0BFB, // 0BFB..0BFF; UNKNOWN
5822 0x0C00, // 0C00..0C0C; TELUGU
5823 0x0C0D, // 0C0D ; UNKNOWN
5824 0x0C0E, // 0C0E..0C10; TELUGU
5825 0x0C11, // 0C11 ; UNKNOWN
5826 0x0C12, // 0C12..0C28; TELUGU
5827 0x0C29, // 0C29 ; UNKNOWN
5828 0x0C2A, // 0C2A..0C39; TELUGU
5829 0x0C3A, // 0C3A..0C3B; UNKNOWN
5830 0x0C3C, // 0C3C..0C44; TELUGU
5831 0x0C45, // 0C45 ; UNKNOWN
5832 0x0C46, // 0C46..0C48; TELUGU
5833 0x0C49, // 0C49 ; UNKNOWN
5834 0x0C4A, // 0C4A..0C4D; TELUGU
5835 0x0C4E, // 0C4E..0C54; UNKNOWN
5836 0x0C55, // 0C55..0C56; TELUGU
5837 0x0C57, // 0C57 ; UNKNOWN
5838 0x0C58, // 0C58..0C5A; TELUGU
5839 0x0C5B, // 0C5B..0C5C; UNKNOWN
5840 0x0C5D, // 0C5D ; TELUGU
5841 0x0C5E, // 0C5E..0C5F; UNKNOWN
5842 0x0C60, // 0C60..0C63; TELUGU
5843 0x0C64, // 0C64..0C65; UNKNOWN
5844 0x0C66, // 0C66..0C6F; TELUGU
5845 0x0C70, // 0C70..0C76; UNKNOWN
5846 0x0C77, // 0C77..0C7F; TELUGU
5847 0x0C80, // 0C80..0C8C; KANNADA
5848 0x0C8D, // 0C8D ; UNKNOWN
5849 0x0C8E, // 0C8E..0C90; KANNADA
5850 0x0C91, // 0C91 ; UNKNOWN
5851 0x0C92, // 0C92..0CA8; KANNADA
5852 0x0CA9, // 0CA9 ; UNKNOWN
5853 0x0CAA, // 0CAA..0CB3; KANNADA
5854 0x0CB4, // 0CB4 ; UNKNOWN
5855 0x0CB5, // 0CB5..0CB9; KANNADA
5856 0x0CBA, // 0CBA..0CBB; UNKNOWN
5857 0x0CBC, // 0CBC..0CC4; KANNADA
5858 0x0CC5, // 0CC5 ; UNKNOWN
5859 0x0CC6, // 0CC6..0CC8; KANNADA
5860 0x0CC9, // 0CC9 ; UNKNOWN
5861 0x0CCA, // 0CCA..0CCD; KANNADA
5862 0x0CCE, // 0CCE..0CD4; UNKNOWN
5863 0x0CD5, // 0CD5..0CD6; KANNADA
5864 0x0CD7, // 0CD7..0CDC; UNKNOWN
5865 0x0CDD, // 0CDD..0CDE; KANNADA
5866 0x0CDF, // 0CDF ; UNKNOWN
5867 0x0CE0, // 0CE0..0CE3; KANNADA
5868 0x0CE4, // 0CE4..0CE5; UNKNOWN
5869 0x0CE6, // 0CE6..0CEF; KANNADA
5870 0x0CF0, // 0CF0 ; UNKNOWN
5871 0x0CF1, // 0CF1..0CF3; KANNADA
5872 0x0CF4, // 0CF4..0CFF; UNKNOWN
5873 0x0D00, // 0D00..0D0C; MALAYALAM
5874 0x0D0D, // 0D0D ; UNKNOWN
5875 0x0D0E, // 0D0E..0D10; MALAYALAM
5876 0x0D11, // 0D11 ; UNKNOWN
5877 0x0D12, // 0D12..0D44; MALAYALAM
5878 0x0D45, // 0D45 ; UNKNOWN
5879 0x0D46, // 0D46..0D48; MALAYALAM
5880 0x0D49, // 0D49 ; UNKNOWN
5881 0x0D4A, // 0D4A..0D4F; MALAYALAM
5882 0x0D50, // 0D50..0D53; UNKNOWN
5883 0x0D54, // 0D54..0D63; MALAYALAM
5884 0x0D64, // 0D64..0D65; UNKNOWN
5885 0x0D66, // 0D66..0D7F; MALAYALAM
5886 0x0D80, // 0D80 ; UNKNOWN
5887 0x0D81, // 0D81..0D83; SINHALA
5888 0x0D84, // 0D84 ; UNKNOWN
5889 0x0D85, // 0D85..0D96; SINHALA
5890 0x0D97, // 0D97..0D99; UNKNOWN
5891 0x0D9A, // 0D9A..0DB1; SINHALA
5892 0x0DB2, // 0DB2 ; UNKNOWN
5893 0x0DB3, // 0DB3..0DBB; SINHALA
5894 0x0DBC, // 0DBC ; UNKNOWN
5895 0x0DBD, // 0DBD ; SINHALA
5896 0x0DBE, // 0DBE..0DBF; UNKNOWN
5897 0x0DC0, // 0DC0..0DC6; SINHALA
5898 0x0DC7, // 0DC7..0DC9; UNKNOWN
5899 0x0DCA, // 0DCA ; SINHALA
5900 0x0DCB, // 0DCB..0DCE; UNKNOWN
5901 0x0DCF, // 0DCF..0DD4; SINHALA
5902 0x0DD5, // 0DD5 ; UNKNOWN
5903 0x0DD6, // 0DD6 ; SINHALA
5904 0x0DD7, // 0DD7 ; UNKNOWN
5905 0x0DD8, // 0DD8..0DDF; SINHALA
5906 0x0DE0, // 0DE0..0DE5; UNKNOWN
5907 0x0DE6, // 0DE6..0DEF; SINHALA
5908 0x0DF0, // 0DF0..0DF1; UNKNOWN
5909 0x0DF2, // 0DF2..0DF4; SINHALA
5910 0x0DF5, // 0DF5..0E00; UNKNOWN
5911 0x0E01, // 0E01..0E3A; THAI
5912 0x0E3B, // 0E3B..0E3E; UNKNOWN
5913 0x0E3F, // 0E3F ; COMMON
5914 0x0E40, // 0E40..0E5B; THAI
5915 0x0E5C, // 0E5C..0E80; UNKNOWN
5916 0x0E81, // 0E81..0E82; LAO
5917 0x0E83, // 0E83 ; UNKNOWN
5918 0x0E84, // 0E84 ; LAO
5919 0x0E85, // 0E85 ; UNKNOWN
5920 0x0E86, // 0E86..0E8A; LAO
5921 0x0E8B, // 0E8B ; UNKNOWN
5922 0x0E8C, // 0E8C..0EA3; LAO
5923 0x0EA4, // 0EA4 ; UNKNOWN
5924 0x0EA5, // 0EA5 ; LAO
5925 0x0EA6, // 0EA6 ; UNKNOWN
5926 0x0EA7, // 0EA7..0EBD; LAO
5927 0x0EBE, // 0EBE..0EBF; UNKNOWN
5928 0x0EC0, // 0EC0..0EC4; LAO
5929 0x0EC5, // 0EC5 ; UNKNOWN
5930 0x0EC6, // 0EC6 ; LAO
5931 0x0EC7, // 0EC7 ; UNKNOWN
5932 0x0EC8, // 0EC8..0ECE; LAO
5933 0x0ECF, // 0ECF ; UNKNOWN
5934 0x0ED0, // 0ED0..0ED9; LAO
5935 0x0EDA, // 0EDA..0EDB; UNKNOWN
5936 0x0EDC, // 0EDC..0EDF; LAO
5937 0x0EE0, // 0EE0..0EFF; UNKNOWN
5938 0x0F00, // 0F00..0F47; TIBETAN
5939 0x0F48, // 0F48 ; UNKNOWN
5940 0x0F49, // 0F49..0F6C; TIBETAN
5941 0x0F6D, // 0F6D..0F70; UNKNOWN
5942 0x0F71, // 0F71..0F97; TIBETAN
5943 0x0F98, // 0F98 ; UNKNOWN
5944 0x0F99, // 0F99..0FBC; TIBETAN
5945 0x0FBD, // 0FBD ; UNKNOWN
5946 0x0FBE, // 0FBE..0FCC; TIBETAN
5947 0x0FCD, // 0FCD ; UNKNOWN
5948 0x0FCE, // 0FCE..0FD4; TIBETAN
5949 0x0FD5, // 0FD5..0FD8; COMMON
5950 0x0FD9, // 0FD9..0FDA; TIBETAN
5951 0x0FDB, // 0FDB..0FFF; UNKNOWN
5952 0x1000, // 1000..109F; MYANMAR
5953 0x10A0, // 10A0..10C5; GEORGIAN
5954 0x10C6, // 10C6 ; UNKNOWN
5955 0x10C7, // 10C7 ; GEORGIAN
5956 0x10C8, // 10C8..10CC; UNKNOWN
5957 0x10CD, // 10CD ; GEORGIAN
5958 0x10CE, // 10CE..10CF; UNKNOWN
5959 0x10D0, // 10D0..10FA; GEORGIAN
5960 0x10FB, // 10FB ; COMMON
5961 0x10FC, // 10FC..10FF; GEORGIAN
5962 0x1100, // 1100..11FF; HANGUL
5963 0x1200, // 1200..1248; ETHIOPIC
5964 0x1249, // 1249 ; UNKNOWN
5965 0x124A, // 124A..124D; ETHIOPIC
5966 0x124E, // 124E..124F; UNKNOWN
5967 0x1250, // 1250..1256; ETHIOPIC
5968 0x1257, // 1257 ; UNKNOWN
5969 0x1258, // 1258 ; ETHIOPIC
5970 0x1259, // 1259 ; UNKNOWN
5971 0x125A, // 125A..125D; ETHIOPIC
5972 0x125E, // 125E..125F; UNKNOWN
5973 0x1260, // 1260..1288; ETHIOPIC
5974 0x1289, // 1289 ; UNKNOWN
5975 0x128A, // 128A..128D; ETHIOPIC
5976 0x128E, // 128E..128F; UNKNOWN
5977 0x1290, // 1290..12B0; ETHIOPIC
5978 0x12B1, // 12B1 ; UNKNOWN
5979 0x12B2, // 12B2..12B5; ETHIOPIC
5980 0x12B6, // 12B6..12B7; UNKNOWN
5981 0x12B8, // 12B8..12BE; ETHIOPIC
5982 0x12BF, // 12BF ; UNKNOWN
5983 0x12C0, // 12C0 ; ETHIOPIC
5984 0x12C1, // 12C1 ; UNKNOWN
5985 0x12C2, // 12C2..12C5; ETHIOPIC
5986 0x12C6, // 12C6..12C7; UNKNOWN
5987 0x12C8, // 12C8..12D6; ETHIOPIC
5988 0x12D7, // 12D7 ; UNKNOWN
5989 0x12D8, // 12D8..1310; ETHIOPIC
5990 0x1311, // 1311 ; UNKNOWN
5991 0x1312, // 1312..1315; ETHIOPIC
5992 0x1316, // 1316..1317; UNKNOWN
5993 0x1318, // 1318..135A; ETHIOPIC
5994 0x135B, // 135B..135C; UNKNOWN
5995 0x135D, // 135D..137C; ETHIOPIC
5996 0x137D, // 137D..137F; UNKNOWN
5997 0x1380, // 1380..1399; ETHIOPIC
5998 0x139A, // 139A..139F; UNKNOWN
5999 0x13A0, // 13A0..13F5; CHEROKEE
6000 0x13F6, // 13F6..13F7; UNKNOWN
6001 0x13F8, // 13F8..13FD; CHEROKEE
6002 0x13FE, // 13FE..13FF; UNKNOWN
6003 0x1400, // 1400..167F; CANADIAN_ABORIGINAL
6004 0x1680, // 1680..169C; OGHAM
6005 0x169D, // 169D..169F; UNKNOWN
6006 0x16A0, // 16A0..16EA; RUNIC
6007 0x16EB, // 16EB..16ED; COMMON
6008 0x16EE, // 16EE..16F8; RUNIC
6009 0x16F9, // 16F9..16FF; UNKNOWN
6010 0x1700, // 1700..1715; TAGALOG
6011 0x1716, // 1716..171E; UNKNOWN
6012 0x171F, // 171F ; TAGALOG
6013 0x1720, // 1720..1734; HANUNOO
6014 0x1735, // 1735..1736; COMMON
6015 0x1737, // 1737..173F; UNKNOWN
6016 0x1740, // 1740..1753; BUHID
6017 0x1754, // 1754..175F; UNKNOWN
6018 0x1760, // 1760..176C; TAGBANWA
6019 0x176D, // 176D ; UNKNOWN
6020 0x176E, // 176E..1770; TAGBANWA
6021 0x1771, // 1771 ; UNKNOWN
6022 0x1772, // 1772..1773; TAGBANWA
6023 0x1774, // 1774..177F; UNKNOWN
6024 0x1780, // 1780..17DD; KHMER
6025 0x17DE, // 17DE..17DF; UNKNOWN
6026 0x17E0, // 17E0..17E9; KHMER
6027 0x17EA, // 17EA..17EF; UNKNOWN
6028 0x17F0, // 17F0..17F9; KHMER
6029 0x17FA, // 17FA..17FF; UNKNOWN
6030 0x1800, // 1800..1801; MONGOLIAN
6031 0x1802, // 1802..1803; COMMON
6032 0x1804, // 1804 ; MONGOLIAN
6033 0x1805, // 1805 ; COMMON
6034 0x1806, // 1806..1819; MONGOLIAN
6035 0x181A, // 181A..181F; UNKNOWN
6036 0x1820, // 1820..1878; MONGOLIAN
6037 0x1879, // 1879..187F; UNKNOWN
6038 0x1880, // 1880..18AA; MONGOLIAN
6039 0x18AB, // 18AB..18AF; UNKNOWN
6040 0x18B0, // 18B0..18F5; CANADIAN_ABORIGINAL
6041 0x18F6, // 18F6..18FF; UNKNOWN
6042 0x1900, // 1900..191E; LIMBU
6043 0x191F, // 191F ; UNKNOWN
6044 0x1920, // 1920..192B; LIMBU
6045 0x192C, // 192C..192F; UNKNOWN
6046 0x1930, // 1930..193B; LIMBU
6047 0x193C, // 193C..193F; UNKNOWN
6048 0x1940, // 1940 ; LIMBU
6049 0x1941, // 1941..1943; UNKNOWN
6050 0x1944, // 1944..194F; LIMBU
6051 0x1950, // 1950..196D; TAI_LE
6052 0x196E, // 196E..196F; UNKNOWN
6053 0x1970, // 1970..1974; TAI_LE
6054 0x1975, // 1975..197F; UNKNOWN
6055 0x1980, // 1980..19AB; NEW_TAI_LUE
6056 0x19AC, // 19AC..19AF; UNKNOWN
6057 0x19B0, // 19B0..19C9; NEW_TAI_LUE
6058 0x19CA, // 19CA..19CF; UNKNOWN
6059 0x19D0, // 19D0..19DA; NEW_TAI_LUE
6060 0x19DB, // 19DB..19DD; UNKNOWN
6061 0x19DE, // 19DE..19DF; NEW_TAI_LUE
6062 0x19E0, // 19E0..19FF; KHMER
6063 0x1A00, // 1A00..1A1B; BUGINESE
6064 0x1A1C, // 1A1C..1A1D; UNKNOWN
6065 0x1A1E, // 1A1E..1A1F; BUGINESE
6066 0x1A20, // 1A20..1A5E; TAI_THAM
6067 0x1A5F, // 1A5F ; UNKNOWN
6068 0x1A60, // 1A60..1A7C; TAI_THAM
6069 0x1A7D, // 1A7D..1A7E; UNKNOWN
6070 0x1A7F, // 1A7F..1A89; TAI_THAM
6071 0x1A8A, // 1A8A..1A8F; UNKNOWN
6072 0x1A90, // 1A90..1A99; TAI_THAM
6073 0x1A9A, // 1A9A..1A9F; UNKNOWN
6074 0x1AA0, // 1AA0..1AAD; TAI_THAM
6075 0x1AAE, // 1AAE..1AAF; UNKNOWN
6076 0x1AB0, // 1AB0..1ACE; INHERITED
6077 0x1ACF, // 1ACF..1AFF; UNKNOWN
6078 0x1B00, // 1B00..1B4C; BALINESE
6079 0x1B4D, // 1B4D ; UNKNOWN
6080 0x1B4E, // 1B4E..1B7F; BALINESE
6081 0x1B80, // 1B80..1BBF; SUNDANESE
6082 0x1BC0, // 1BC0..1BF3; BATAK
6083 0x1BF4, // 1BF4..1BFB; UNKNOWN
6084 0x1BFC, // 1BFC..1BFF; BATAK
6085 0x1C00, // 1C00..1C37; LEPCHA
6086 0x1C38, // 1C38..1C3A; UNKNOWN
6087 0x1C3B, // 1C3B..1C49; LEPCHA
6088 0x1C4A, // 1C4A..1C4C; UNKNOWN
6089 0x1C4D, // 1C4D..1C4F; LEPCHA
6090 0x1C50, // 1C50..1C7F; OL_CHIKI
6091 0x1C80, // 1C80..1C8A; CYRILLIC
6092 0x1C8B, // 1C8B..1C8F; UNKNOWN
6093 0x1C90, // 1C90..1CBA; GEORGIAN
6094 0x1CBB, // 1CBB..1CBC; UNKNOWN
6095 0x1CBD, // 1CBD..1CBF; GEORGIAN
6096 0x1CC0, // 1CC0..1CC7; SUNDANESE
6097 0x1CC8, // 1CC8..1CCF; UNKNOWN
6098 0x1CD0, // 1CD0..1CD2; INHERITED
6099 0x1CD3, // 1CD3 ; COMMON
6100 0x1CD4, // 1CD4..1CE0; INHERITED
6101 0x1CE1, // 1CE1 ; COMMON
6102 0x1CE2, // 1CE2..1CE8; INHERITED
6103 0x1CE9, // 1CE9..1CEC; COMMON
6104 0x1CED, // 1CED ; INHERITED
6105 0x1CEE, // 1CEE..1CF3; COMMON
6106 0x1CF4, // 1CF4 ; INHERITED
6107 0x1CF5, // 1CF5..1CF7; COMMON
6108 0x1CF8, // 1CF8..1CF9; INHERITED
6109 0x1CFA, // 1CFA ; COMMON
6110 0x1CFB, // 1CFB..1CFF; UNKNOWN
6111 0x1D00, // 1D00..1D25; LATIN
6112 0x1D26, // 1D26..1D2A; GREEK
6113 0x1D2B, // 1D2B ; CYRILLIC
6114 0x1D2C, // 1D2C..1D5C; LATIN
6115 0x1D5D, // 1D5D..1D61; GREEK
6116 0x1D62, // 1D62..1D65; LATIN
6117 0x1D66, // 1D66..1D6A; GREEK
6118 0x1D6B, // 1D6B..1D77; LATIN
6119 0x1D78, // 1D78 ; CYRILLIC
6120 0x1D79, // 1D79..1DBE; LATIN
6121 0x1DBF, // 1DBF ; GREEK
6122 0x1DC0, // 1DC0..1DFF; INHERITED
6123 0x1E00, // 1E00..1EFF; LATIN
6124 0x1F00, // 1F00..1F15; GREEK
6125 0x1F16, // 1F16..1F17; UNKNOWN
6126 0x1F18, // 1F18..1F1D; GREEK
6127 0x1F1E, // 1F1E..1F1F; UNKNOWN
6128 0x1F20, // 1F20..1F45; GREEK
6129 0x1F46, // 1F46..1F47; UNKNOWN
6130 0x1F48, // 1F48..1F4D; GREEK
6131 0x1F4E, // 1F4E..1F4F; UNKNOWN
6132 0x1F50, // 1F50..1F57; GREEK
6133 0x1F58, // 1F58 ; UNKNOWN
6134 0x1F59, // 1F59 ; GREEK
6135 0x1F5A, // 1F5A ; UNKNOWN
6136 0x1F5B, // 1F5B ; GREEK
6137 0x1F5C, // 1F5C ; UNKNOWN
6138 0x1F5D, // 1F5D ; GREEK
6139 0x1F5E, // 1F5E ; UNKNOWN
6140 0x1F5F, // 1F5F..1F7D; GREEK
6141 0x1F7E, // 1F7E..1F7F; UNKNOWN
6142 0x1F80, // 1F80..1FB4; GREEK
6143 0x1FB5, // 1FB5 ; UNKNOWN
6144 0x1FB6, // 1FB6..1FC4; GREEK
6145 0x1FC5, // 1FC5 ; UNKNOWN
6146 0x1FC6, // 1FC6..1FD3; GREEK
6147 0x1FD4, // 1FD4..1FD5; UNKNOWN
6148 0x1FD6, // 1FD6..1FDB; GREEK
6149 0x1FDC, // 1FDC ; UNKNOWN
6150 0x1FDD, // 1FDD..1FEF; GREEK
6151 0x1FF0, // 1FF0..1FF1; UNKNOWN
6152 0x1FF2, // 1FF2..1FF4; GREEK
6153 0x1FF5, // 1FF5 ; UNKNOWN
6154 0x1FF6, // 1FF6..1FFE; GREEK
6155 0x1FFF, // 1FFF ; UNKNOWN
6156 0x2000, // 2000..200B; COMMON
6157 0x200C, // 200C..200D; INHERITED
6158 0x200E, // 200E..2064; COMMON
6159 0x2065, // 2065 ; UNKNOWN
6160 0x2066, // 2066..2070; COMMON
6161 0x2071, // 2071 ; LATIN
6162 0x2072, // 2072..2073; UNKNOWN
6163 0x2074, // 2074..207E; COMMON
6164 0x207F, // 207F ; LATIN
6165 0x2080, // 2080..208E; COMMON
6166 0x208F, // 208F ; UNKNOWN
6167 0x2090, // 2090..209C; LATIN
6168 0x209D, // 209D..209F; UNKNOWN
6169 0x20A0, // 20A0..20C0; COMMON
6170 0x20C1, // 20C1..20CF; UNKNOWN
6171 0x20D0, // 20D0..20F0; INHERITED
6172 0x20F1, // 20F1..20FF; UNKNOWN
6173 0x2100, // 2100..2125; COMMON
6174 0x2126, // 2126 ; GREEK
6175 0x2127, // 2127..2129; COMMON
6176 0x212A, // 212A..212B; LATIN
6177 0x212C, // 212C..2131; COMMON
6178 0x2132, // 2132 ; LATIN
6179 0x2133, // 2133..214D; COMMON
6180 0x214E, // 214E ; LATIN
6181 0x214F, // 214F..215F; COMMON
6182 0x2160, // 2160..2188; LATIN
6183 0x2189, // 2189..218B; COMMON
6184 0x218C, // 218C..218F; UNKNOWN
6185 0x2190, // 2190..2429; COMMON
6186 0x242A, // 242A..243F; UNKNOWN
6187 0x2440, // 2440..244A; COMMON
6188 0x244B, // 244B..245F; UNKNOWN
6189 0x2460, // 2460..27FF; COMMON
6190 0x2800, // 2800..28FF; BRAILLE
6191 0x2900, // 2900..2B73; COMMON
6192 0x2B74, // 2B74..2B75; UNKNOWN
6193 0x2B76, // 2B76..2B95; COMMON
6194 0x2B96, // 2B96 ; UNKNOWN
6195 0x2B97, // 2B97..2BFF; COMMON
6196 0x2C00, // 2C00..2C5F; GLAGOLITIC
6197 0x2C60, // 2C60..2C7F; LATIN
6198 0x2C80, // 2C80..2CF3; COPTIC
6199 0x2CF4, // 2CF4..2CF8; UNKNOWN
6200 0x2CF9, // 2CF9..2CFF; COPTIC
6201 0x2D00, // 2D00..2D25; GEORGIAN
6202 0x2D26, // 2D26 ; UNKNOWN
6203 0x2D27, // 2D27 ; GEORGIAN
6204 0x2D28, // 2D28..2D2C; UNKNOWN
6205 0x2D2D, // 2D2D ; GEORGIAN
6206 0x2D2E, // 2D2E..2D2F; UNKNOWN
6207 0x2D30, // 2D30..2D67; TIFINAGH
6208 0x2D68, // 2D68..2D6E; UNKNOWN
6209 0x2D6F, // 2D6F..2D70; TIFINAGH
6210 0x2D71, // 2D71..2D7E; UNKNOWN
6211 0x2D7F, // 2D7F ; TIFINAGH
6212 0x2D80, // 2D80..2D96; ETHIOPIC
6213 0x2D97, // 2D97..2D9F; UNKNOWN
6214 0x2DA0, // 2DA0..2DA6; ETHIOPIC
6215 0x2DA7, // 2DA7 ; UNKNOWN
6216 0x2DA8, // 2DA8..2DAE; ETHIOPIC
6217 0x2DAF, // 2DAF ; UNKNOWN
6218 0x2DB0, // 2DB0..2DB6; ETHIOPIC
6219 0x2DB7, // 2DB7 ; UNKNOWN
6220 0x2DB8, // 2DB8..2DBE; ETHIOPIC
6221 0x2DBF, // 2DBF ; UNKNOWN
6222 0x2DC0, // 2DC0..2DC6; ETHIOPIC
6223 0x2DC7, // 2DC7 ; UNKNOWN
6224 0x2DC8, // 2DC8..2DCE; ETHIOPIC
6225 0x2DCF, // 2DCF ; UNKNOWN
6226 0x2DD0, // 2DD0..2DD6; ETHIOPIC
6227 0x2DD7, // 2DD7 ; UNKNOWN
6228 0x2DD8, // 2DD8..2DDE; ETHIOPIC
6229 0x2DDF, // 2DDF ; UNKNOWN
6230 0x2DE0, // 2DE0..2DFF; CYRILLIC
6231 0x2E00, // 2E00..2E5D; COMMON
6232 0x2E5E, // 2E5E..2E7F; UNKNOWN
6233 0x2E80, // 2E80..2E99; HAN
6234 0x2E9A, // 2E9A ; UNKNOWN
6235 0x2E9B, // 2E9B..2EF3; HAN
6236 0x2EF4, // 2EF4..2EFF; UNKNOWN
6237 0x2F00, // 2F00..2FD5; HAN
6238 0x2FD6, // 2FD6..2FEF; UNKNOWN
6239 0x2FF0, // 2FF0..3004; COMMON
6240 0x3005, // 3005 ; HAN
6241 0x3006, // 3006 ; COMMON
6242 0x3007, // 3007 ; HAN
6243 0x3008, // 3008..3020; COMMON
6244 0x3021, // 3021..3029; HAN
6245 0x302A, // 302A..302D; INHERITED
6246 0x302E, // 302E..302F; HANGUL
6247 0x3030, // 3030..3037; COMMON
6248 0x3038, // 3038..303B; HAN
6249 0x303C, // 303C..303F; COMMON
6250 0x3040, // 3040 ; UNKNOWN
6251 0x3041, // 3041..3096; HIRAGANA
6252 0x3097, // 3097..3098; UNKNOWN
6253 0x3099, // 3099..309A; INHERITED
6254 0x309B, // 309B..309C; COMMON
6255 0x309D, // 309D..309F; HIRAGANA
6256 0x30A0, // 30A0 ; COMMON
6257 0x30A1, // 30A1..30FA; KATAKANA
6258 0x30FB, // 30FB..30FC; COMMON
6259 0x30FD, // 30FD..30FF; KATAKANA
6260 0x3100, // 3100..3104; UNKNOWN
6261 0x3105, // 3105..312F; BOPOMOFO
6262 0x3130, // 3130 ; UNKNOWN
6263 0x3131, // 3131..318E; HANGUL
6264 0x318F, // 318F ; UNKNOWN
6265 0x3190, // 3190..319F; COMMON
6266 0x31A0, // 31A0..31BF; BOPOMOFO
6267 0x31C0, // 31C0..31E5; COMMON
6268 0x31E6, // 31E6..31EE; UNKNOWN
6269 0x31EF, // 31EF ; COMMON
6270 0x31F0, // 31F0..31FF; KATAKANA
6271 0x3200, // 3200..321E; HANGUL
6272 0x321F, // 321F ; UNKNOWN
6273 0x3220, // 3220..325F; COMMON
6274 0x3260, // 3260..327E; HANGUL
6275 0x327F, // 327F..32CF; COMMON
6276 0x32D0, // 32D0..32FE; KATAKANA
6277 0x32FF, // 32FF ; COMMON
6278 0x3300, // 3300..3357; KATAKANA
6279 0x3358, // 3358..33FF; COMMON
6280 0x3400, // 3400..4DBF; HAN
6281 0x4DC0, // 4DC0..4DFF; COMMON
6282 0x4E00, // 4E00..9FFF; HAN
6283 0xA000, // A000..A48C; YI
6284 0xA48D, // A48D..A48F; UNKNOWN
6285 0xA490, // A490..A4C6; YI
6286 0xA4C7, // A4C7..A4CF; UNKNOWN
6287 0xA4D0, // A4D0..A4FF; LISU
6288 0xA500, // A500..A62B; VAI
6289 0xA62C, // A62C..A63F; UNKNOWN
6290 0xA640, // A640..A69F; CYRILLIC
6291 0xA6A0, // A6A0..A6F7; BAMUM
6292 0xA6F8, // A6F8..A6FF; UNKNOWN
6293 0xA700, // A700..A721; COMMON
6294 0xA722, // A722..A787; LATIN
6295 0xA788, // A788..A78A; COMMON
6296 0xA78B, // A78B..A7CD; LATIN
6297 0xA7CE, // A7CE..A7CF; UNKNOWN
6298 0xA7D0, // A7D0..A7D1; LATIN
6299 0xA7D2, // A7D2 ; UNKNOWN
6300 0xA7D3, // A7D3 ; LATIN
6301 0xA7D4, // A7D4 ; UNKNOWN
6302 0xA7D5, // A7D5..A7DC; LATIN
6303 0xA7DD, // A7DD..A7F1; UNKNOWN
6304 0xA7F2, // A7F2..A7FF; LATIN
6305 0xA800, // A800..A82C; SYLOTI_NAGRI
6306 0xA82D, // A82D..A82F; UNKNOWN
6307 0xA830, // A830..A839; COMMON
6308 0xA83A, // A83A..A83F; UNKNOWN
6309 0xA840, // A840..A877; PHAGS_PA
6310 0xA878, // A878..A87F; UNKNOWN
6311 0xA880, // A880..A8C5; SAURASHTRA
6312 0xA8C6, // A8C6..A8CD; UNKNOWN
6313 0xA8CE, // A8CE..A8D9; SAURASHTRA
6314 0xA8DA, // A8DA..A8DF; UNKNOWN
6315 0xA8E0, // A8E0..A8FF; DEVANAGARI
6316 0xA900, // A900..A92D; KAYAH_LI
6317 0xA92E, // A92E ; COMMON
6318 0xA92F, // A92F ; KAYAH_LI
6319 0xA930, // A930..A953; REJANG
6320 0xA954, // A954..A95E; UNKNOWN
6321 0xA95F, // A95F ; REJANG
6322 0xA960, // A960..A97C; HANGUL
6323 0xA97D, // A97D..A97F; UNKNOWN
6324 0xA980, // A980..A9CD; JAVANESE
6325 0xA9CE, // A9CE ; UNKNOWN
6326 0xA9CF, // A9CF ; COMMON
6327 0xA9D0, // A9D0..A9D9; JAVANESE
6328 0xA9DA, // A9DA..A9DD; UNKNOWN
6329 0xA9DE, // A9DE..A9DF; JAVANESE
6330 0xA9E0, // A9E0..A9FE; MYANMAR
6331 0xA9FF, // A9FF ; UNKNOWN
6332 0xAA00, // AA00..AA36; CHAM
6333 0xAA37, // AA37..AA3F; UNKNOWN
6334 0xAA40, // AA40..AA4D; CHAM
6335 0xAA4E, // AA4E..AA4F; UNKNOWN
6336 0xAA50, // AA50..AA59; CHAM
6337 0xAA5A, // AA5A..AA5B; UNKNOWN
6338 0xAA5C, // AA5C..AA5F; CHAM
6339 0xAA60, // AA60..AA7F; MYANMAR
6340 0xAA80, // AA80..AAC2; TAI_VIET
6341 0xAAC3, // AAC3..AADA; UNKNOWN
6342 0xAADB, // AADB..AADF; TAI_VIET
6343 0xAAE0, // AAE0..AAF6; MEETEI_MAYEK
6344 0xAAF7, // AAF7..AB00; UNKNOWN
6345 0xAB01, // AB01..AB06; ETHIOPIC
6346 0xAB07, // AB07..AB08; UNKNOWN
6347 0xAB09, // AB09..AB0E; ETHIOPIC
6348 0xAB0F, // AB0F..AB10; UNKNOWN
6349 0xAB11, // AB11..AB16; ETHIOPIC
6350 0xAB17, // AB17..AB1F; UNKNOWN
6351 0xAB20, // AB20..AB26; ETHIOPIC
6352 0xAB27, // AB27 ; UNKNOWN
6353 0xAB28, // AB28..AB2E; ETHIOPIC
6354 0xAB2F, // AB2F ; UNKNOWN
6355 0xAB30, // AB30..AB5A; LATIN
6356 0xAB5B, // AB5B ; COMMON
6357 0xAB5C, // AB5C..AB64; LATIN
6358 0xAB65, // AB65 ; GREEK
6359 0xAB66, // AB66..AB69; LATIN
6360 0xAB6A, // AB6A..AB6B; COMMON
6361 0xAB6C, // AB6C..AB6F; UNKNOWN
6362 0xAB70, // AB70..ABBF; CHEROKEE
6363 0xABC0, // ABC0..ABED; MEETEI_MAYEK
6364 0xABEE, // ABEE..ABEF; UNKNOWN
6365 0xABF0, // ABF0..ABF9; MEETEI_MAYEK
6366 0xABFA, // ABFA..ABFF; UNKNOWN
6367 0xAC00, // AC00..D7A3; HANGUL
6368 0xD7A4, // D7A4..D7AF; UNKNOWN
6369 0xD7B0, // D7B0..D7C6; HANGUL
6370 0xD7C7, // D7C7..D7CA; UNKNOWN
6371 0xD7CB, // D7CB..D7FB; HANGUL
6372 0xD7FC, // D7FC..F8FF; UNKNOWN
6373 0xF900, // F900..FA6D; HAN
6374 0xFA6E, // FA6E..FA6F; UNKNOWN
6375 0xFA70, // FA70..FAD9; HAN
6376 0xFADA, // FADA..FAFF; UNKNOWN
6377 0xFB00, // FB00..FB06; LATIN
6378 0xFB07, // FB07..FB12; UNKNOWN
6379 0xFB13, // FB13..FB17; ARMENIAN
6380 0xFB18, // FB18..FB1C; UNKNOWN
6381 0xFB1D, // FB1D..FB36; HEBREW
6382 0xFB37, // FB37 ; UNKNOWN
6383 0xFB38, // FB38..FB3C; HEBREW
6384 0xFB3D, // FB3D ; UNKNOWN
6385 0xFB3E, // FB3E ; HEBREW
6386 0xFB3F, // FB3F ; UNKNOWN
6387 0xFB40, // FB40..FB41; HEBREW
6388 0xFB42, // FB42 ; UNKNOWN
6389 0xFB43, // FB43..FB44; HEBREW
6390 0xFB45, // FB45 ; UNKNOWN
6391 0xFB46, // FB46..FB4F; HEBREW
6392 0xFB50, // FB50..FBC2; ARABIC
6393 0xFBC3, // FBC3..FBD2; UNKNOWN
6394 0xFBD3, // FBD3..FD3D; ARABIC
6395 0xFD3E, // FD3E..FD3F; COMMON
6396 0xFD40, // FD40..FD8F; ARABIC
6397 0xFD90, // FD90..FD91; UNKNOWN
6398 0xFD92, // FD92..FDC7; ARABIC
6399 0xFDC8, // FDC8..FDCE; UNKNOWN
6400 0xFDCF, // FDCF ; ARABIC
6401 0xFDD0, // FDD0..FDEF; UNKNOWN
6402 0xFDF0, // FDF0..FDFF; ARABIC
6403 0xFE00, // FE00..FE0F; INHERITED
6404 0xFE10, // FE10..FE19; COMMON
6405 0xFE1A, // FE1A..FE1F; UNKNOWN
6406 0xFE20, // FE20..FE2D; INHERITED
6407 0xFE2E, // FE2E..FE2F; CYRILLIC
6408 0xFE30, // FE30..FE52; COMMON
6409 0xFE53, // FE53 ; UNKNOWN
6410 0xFE54, // FE54..FE66; COMMON
6411 0xFE67, // FE67 ; UNKNOWN
6412 0xFE68, // FE68..FE6B; COMMON
6413 0xFE6C, // FE6C..FE6F; UNKNOWN
6414 0xFE70, // FE70..FE74; ARABIC
6415 0xFE75, // FE75 ; UNKNOWN
6416 0xFE76, // FE76..FEFC; ARABIC
6417 0xFEFD, // FEFD..FEFE; UNKNOWN
6418 0xFEFF, // FEFF ; COMMON
6419 0xFF00, // FF00 ; UNKNOWN
6420 0xFF01, // FF01..FF20; COMMON
6421 0xFF21, // FF21..FF3A; LATIN
6422 0xFF3B, // FF3B..FF40; COMMON
6423 0xFF41, // FF41..FF5A; LATIN
6424 0xFF5B, // FF5B..FF65; COMMON
6425 0xFF66, // FF66..FF6F; KATAKANA
6426 0xFF70, // FF70 ; COMMON
6427 0xFF71, // FF71..FF9D; KATAKANA
6428 0xFF9E, // FF9E..FF9F; COMMON
6429 0xFFA0, // FFA0..FFBE; HANGUL
6430 0xFFBF, // FFBF..FFC1; UNKNOWN
6431 0xFFC2, // FFC2..FFC7; HANGUL
6432 0xFFC8, // FFC8..FFC9; UNKNOWN
6433 0xFFCA, // FFCA..FFCF; HANGUL
6434 0xFFD0, // FFD0..FFD1; UNKNOWN
6435 0xFFD2, // FFD2..FFD7; HANGUL
6436 0xFFD8, // FFD8..FFD9; UNKNOWN
6437 0xFFDA, // FFDA..FFDC; HANGUL
6438 0xFFDD, // FFDD..FFDF; UNKNOWN
6439 0xFFE0, // FFE0..FFE6; COMMON
6440 0xFFE7, // FFE7 ; UNKNOWN
6441 0xFFE8, // FFE8..FFEE; COMMON
6442 0xFFEF, // FFEF..FFF8; UNKNOWN
6443 0xFFF9, // FFF9..FFFD; COMMON
6444 0xFFFE, // FFFE..FFFF; UNKNOWN
6445 0x10000, // 10000..1000B; LINEAR_B
6446 0x1000C, // 1000C ; UNKNOWN
6447 0x1000D, // 1000D..10026; LINEAR_B
6448 0x10027, // 10027 ; UNKNOWN
6449 0x10028, // 10028..1003A; LINEAR_B
6450 0x1003B, // 1003B ; UNKNOWN
6451 0x1003C, // 1003C..1003D; LINEAR_B
6452 0x1003E, // 1003E ; UNKNOWN
6453 0x1003F, // 1003F..1004D; LINEAR_B
6454 0x1004E, // 1004E..1004F; UNKNOWN
6455 0x10050, // 10050..1005D; LINEAR_B
6456 0x1005E, // 1005E..1007F; UNKNOWN
6457 0x10080, // 10080..100FA; LINEAR_B
6458 0x100FB, // 100FB..100FF; UNKNOWN
6459 0x10100, // 10100..10102; COMMON
6460 0x10103, // 10103..10106; UNKNOWN
6461 0x10107, // 10107..10133; COMMON
6462 0x10134, // 10134..10136; UNKNOWN
6463 0x10137, // 10137..1013F; COMMON
6464 0x10140, // 10140..1018E; GREEK
6465 0x1018F, // 1018F ; UNKNOWN
6466 0x10190, // 10190..1019C; COMMON
6467 0x1019D, // 1019D..1019F; UNKNOWN
6468 0x101A0, // 101A0 ; GREEK
6469 0x101A1, // 101A1..101CF; UNKNOWN
6470 0x101D0, // 101D0..101FC; COMMON
6471 0x101FD, // 101FD ; INHERITED
6472 0x101FE, // 101FE..1027F; UNKNOWN
6473 0x10280, // 10280..1029C; LYCIAN
6474 0x1029D, // 1029D..1029F; UNKNOWN
6475 0x102A0, // 102A0..102D0; CARIAN
6476 0x102D1, // 102D1..102DF; UNKNOWN
6477 0x102E0, // 102E0 ; INHERITED
6478 0x102E1, // 102E1..102FB; COMMON
6479 0x102FC, // 102FC..102FF; UNKNOWN
6480 0x10300, // 10300..10323; OLD_ITALIC
6481 0x10324, // 10324..1032C; UNKNOWN
6482 0x1032D, // 1032D..1032F; OLD_ITALIC
6483 0x10330, // 10330..1034A; GOTHIC
6484 0x1034B, // 1034B..1034F; UNKNOWN
6485 0x10350, // 10350..1037A; OLD_PERMIC
6486 0x1037B, // 1037B..1037F; UNKNOWN
6487 0x10380, // 10380..1039D; UGARITIC
6488 0x1039E, // 1039E ; UNKNOWN
6489 0x1039F, // 1039F ; UGARITIC
6490 0x103A0, // 103A0..103C3; OLD_PERSIAN
6491 0x103C4, // 103C4..103C7; UNKNOWN
6492 0x103C8, // 103C8..103D5; OLD_PERSIAN
6493 0x103D6, // 103D6..103FF; UNKNOWN
6494 0x10400, // 10400..1044F; DESERET
6495 0x10450, // 10450..1047F; SHAVIAN
6496 0x10480, // 10480..1049D; OSMANYA
6497 0x1049E, // 1049E..1049F; UNKNOWN
6498 0x104A0, // 104A0..104A9; OSMANYA
6499 0x104AA, // 104AA..104AF; UNKNOWN
6500 0x104B0, // 104B0..104D3; OSAGE
6501 0x104D4, // 104D4..104D7; UNKNOWN
6502 0x104D8, // 104D8..104FB; OSAGE
6503 0x104FC, // 104FC..104FF; UNKNOWN
6504 0x10500, // 10500..10527; ELBASAN
6505 0x10528, // 10528..1052F; UNKNOWN
6506 0x10530, // 10530..10563; CAUCASIAN_ALBANIAN
6507 0x10564, // 10564..1056E; UNKNOWN
6508 0x1056F, // 1056F ; CAUCASIAN_ALBANIAN
6509 0x10570, // 10570..1057A; VITHKUQI
6510 0x1057B, // 1057B ; UNKNOWN
6511 0x1057C, // 1057C..1058A; VITHKUQI
6512 0x1058B, // 1058B ; UNKNOWN
6513 0x1058C, // 1058C..10592; VITHKUQI
6514 0x10593, // 10593 ; UNKNOWN
6515 0x10594, // 10594..10595; VITHKUQI
6516 0x10596, // 10596 ; UNKNOWN
6517 0x10597, // 10597..105A1; VITHKUQI
6518 0x105A2, // 105A2 ; UNKNOWN
6519 0x105A3, // 105A3..105B1; VITHKUQI
6520 0x105B2, // 105B2 ; UNKNOWN
6521 0x105B3, // 105B3..105B9; VITHKUQI
6522 0x105BA, // 105BA ; UNKNOWN
6523 0x105BB, // 105BB..105BC; VITHKUQI
6524 0x105BD, // 105BD..105BF; UNKNOWN
6525 0x105C0, // 105C0..105F3; TODHRI
6526 0x105F4, // 105F4..105FF; UNKNOWN
6527 0x10600, // 10600..10736; LINEAR_A
6528 0x10737, // 10737..1073F; UNKNOWN
6529 0x10740, // 10740..10755; LINEAR_A
6530 0x10756, // 10756..1075F; UNKNOWN
6531 0x10760, // 10760..10767; LINEAR_A
6532 0x10768, // 10768..1077F; UNKNOWN
6533 0x10780, // 10780..10785; LATIN
6534 0x10786, // 10786 ; UNKNOWN
6535 0x10787, // 10787..107B0; LATIN
6536 0x107B1, // 107B1 ; UNKNOWN
6537 0x107B2, // 107B2..107BA; LATIN
6538 0x107BB, // 107BB..107FF; UNKNOWN
6539 0x10800, // 10800..10805; CYPRIOT
6540 0x10806, // 10806..10807; UNKNOWN
6541 0x10808, // 10808 ; CYPRIOT
6542 0x10809, // 10809 ; UNKNOWN
6543 0x1080A, // 1080A..10835; CYPRIOT
6544 0x10836, // 10836 ; UNKNOWN
6545 0x10837, // 10837..10838; CYPRIOT
6546 0x10839, // 10839..1083B; UNKNOWN
6547 0x1083C, // 1083C ; CYPRIOT
6548 0x1083D, // 1083D..1083E; UNKNOWN
6549 0x1083F, // 1083F ; CYPRIOT
6550 0x10840, // 10840..10855; IMPERIAL_ARAMAIC
6551 0x10856, // 10856 ; UNKNOWN
6552 0x10857, // 10857..1085F; IMPERIAL_ARAMAIC
6553 0x10860, // 10860..1087F; PALMYRENE
6554 0x10880, // 10880..1089E; NABATAEAN
6555 0x1089F, // 1089F..108A6; UNKNOWN
6556 0x108A7, // 108A7..108AF; NABATAEAN
6557 0x108B0, // 108B0..108DF; UNKNOWN
6558 0x108E0, // 108E0..108F2; HATRAN
6559 0x108F3, // 108F3 ; UNKNOWN
6560 0x108F4, // 108F4..108F5; HATRAN
6561 0x108F6, // 108F6..108FA; UNKNOWN
6562 0x108FB, // 108FB..108FF; HATRAN
6563 0x10900, // 10900..1091B; PHOENICIAN
6564 0x1091C, // 1091C..1091E; UNKNOWN
6565 0x1091F, // 1091F ; PHOENICIAN
6566 0x10920, // 10920..10939; LYDIAN
6567 0x1093A, // 1093A..1093E; UNKNOWN
6568 0x1093F, // 1093F ; LYDIAN
6569 0x10940, // 10940..1097F; UNKNOWN
6570 0x10980, // 10980..1099F; MEROITIC_HIEROGLYPHS
6571 0x109A0, // 109A0..109B7; MEROITIC_CURSIVE
6572 0x109B8, // 109B8..109BB; UNKNOWN
6573 0x109BC, // 109BC..109CF; MEROITIC_CURSIVE
6574 0x109D0, // 109D0..109D1; UNKNOWN
6575 0x109D2, // 109D2..109FF; MEROITIC_CURSIVE
6576 0x10A00, // 10A00..10A03; KHAROSHTHI
6577 0x10A04, // 10A04 ; UNKNOWN
6578 0x10A05, // 10A05..10A06; KHAROSHTHI
6579 0x10A07, // 10A07..10A0B; UNKNOWN
6580 0x10A0C, // 10A0C..10A13; KHAROSHTHI
6581 0x10A14, // 10A14 ; UNKNOWN
6582 0x10A15, // 10A15..10A17; KHAROSHTHI
6583 0x10A18, // 10A18 ; UNKNOWN
6584 0x10A19, // 10A19..10A35; KHAROSHTHI
6585 0x10A36, // 10A36..10A37; UNKNOWN
6586 0x10A38, // 10A38..10A3A; KHAROSHTHI
6587 0x10A3B, // 10A3B..10A3E; UNKNOWN
6588 0x10A3F, // 10A3F..10A48; KHAROSHTHI
6589 0x10A49, // 10A49..10A4F; UNKNOWN
6590 0x10A50, // 10A50..10A58; KHAROSHTHI
6591 0x10A59, // 10A59..10A5F; UNKNOWN
6592 0x10A60, // 10A60..10A7F; OLD_SOUTH_ARABIAN
6593 0x10A80, // 10A80..10A9F; OLD_NORTH_ARABIAN
6594 0x10AA0, // 10AA0..10ABF; UNKNOWN
6595 0x10AC0, // 10AC0..10AE6; MANICHAEAN
6596 0x10AE7, // 10AE7..10AEA; UNKNOWN
6597 0x10AEB, // 10AEB..10AF6; MANICHAEAN
6598 0x10AF7, // 10AF7..10AFF; UNKNOWN
6599 0x10B00, // 10B00..10B35; AVESTAN
6600 0x10B36, // 10B36..10B38; UNKNOWN
6601 0x10B39, // 10B39..10B3F; AVESTAN
6602 0x10B40, // 10B40..10B55; INSCRIPTIONAL_PARTHIAN
6603 0x10B56, // 10B56..10B57; UNKNOWN
6604 0x10B58, // 10B58..10B5F; INSCRIPTIONAL_PARTHIAN
6605 0x10B60, // 10B60..10B72; INSCRIPTIONAL_PAHLAVI
6606 0x10B73, // 10B73..10B77; UNKNOWN
6607 0x10B78, // 10B78..10B7F; INSCRIPTIONAL_PAHLAVI
6608 0x10B80, // 10B80..10B91; PSALTER_PAHLAVI
6609 0x10B92, // 10B92..10B98; UNKNOWN
6610 0x10B99, // 10B99..10B9C; PSALTER_PAHLAVI
6611 0x10B9D, // 10B9D..10BA8; UNKNOWN
6612 0x10BA9, // 10BA9..10BAF; PSALTER_PAHLAVI
6613 0x10BB0, // 10BB0..10BFF; UNKNOWN
6614 0x10C00, // 10C00..10C48; OLD_TURKIC
6615 0x10C49, // 10C49..10C7F; UNKNOWN
6616 0x10C80, // 10C80..10CB2; OLD_HUNGARIAN
6617 0x10CB3, // 10CB3..10CBF; UNKNOWN
6618 0x10CC0, // 10CC0..10CF2; OLD_HUNGARIAN
6619 0x10CF3, // 10CF3..10CF9; UNKNOWN
6620 0x10CFA, // 10CFA..10CFF; OLD_HUNGARIAN
6621 0x10D00, // 10D00..10D27; HANIFI_ROHINGYA
6622 0x10D28, // 10D28..10D2F; UNKNOWN
6623 0x10D30, // 10D30..10D39; HANIFI_ROHINGYA
6624 0x10D3A, // 10D3A..10D3F; UNKNOWN
6625 0x10D40, // 10D40..10D65; GARAY
6626 0x10D66, // 10D66..10D68; UNKNOWN
6627 0x10D69, // 10D69..10D85; GARAY
6628 0x10D86, // 10D86..10D8D; UNKNOWN
6629 0x10D8E, // 10D8E..10D8F; GARAY
6630 0x10D90, // 10D90..10E5F; UNKNOWN
6631 0x10E60, // 10E60..10E7E; ARABIC
6632 0x10E7F, // 10E7F ; UNKNOWN
6633 0x10E80, // 10E80..10EA9; YEZIDI
6634 0x10EAA, // 10EAA ; UNKNOWN
6635 0x10EAB, // 10EAB..10EAD; YEZIDI
6636 0x10EAE, // 10EAE..10EAF; UNKNOWN
6637 0x10EB0, // 10EB0..10EB1; YEZIDI
6638 0x10EB2, // 10EB2..10EC1; UNKNOWN
6639 0x10EC2, // 10EC2..10EC4; ARABIC
6640 0x10EC5, // 10EC5..10EFB; UNKNOWN
6641 0x10EFC, // 10EFC..10EFF; ARABIC
6642 0x10F00, // 10F00..10F27; OLD_SOGDIAN
6643 0x10F28, // 10F28..10F2F; UNKNOWN
6644 0x10F30, // 10F30..10F59; SOGDIAN
6645 0x10F5A, // 10F5A..10F6F; UNKNOWN
6646 0x10F70, // 10F70..10F89; OLD_UYGHUR
6647 0x10F8A, // 10F8A..10FAF; UNKNOWN
6648 0x10FB0, // 10FB0..10FCB; CHORASMIAN
6649 0x10FCC, // 10FCC..10FDF; UNKNOWN
6650 0x10FE0, // 10FE0..10FF6; ELYMAIC
6651 0x10FF7, // 10FF7..10FFF; UNKNOWN
6652 0x11000, // 11000..1104D; BRAHMI
6653 0x1104E, // 1104E..11051; UNKNOWN
6654 0x11052, // 11052..11075; BRAHMI
6655 0x11076, // 11076..1107E; UNKNOWN
6656 0x1107F, // 1107F ; BRAHMI
6657 0x11080, // 11080..110C2; KAITHI
6658 0x110C3, // 110C3..110CC; UNKNOWN
6659 0x110CD, // 110CD ; KAITHI
6660 0x110CE, // 110CE..110CF; UNKNOWN
6661 0x110D0, // 110D0..110E8; SORA_SOMPENG
6662 0x110E9, // 110E9..110EF; UNKNOWN
6663 0x110F0, // 110F0..110F9; SORA_SOMPENG
6664 0x110FA, // 110FA..110FF; UNKNOWN
6665 0x11100, // 11100..11134; CHAKMA
6666 0x11135, // 11135 ; UNKNOWN
6667 0x11136, // 11136..11147; CHAKMA
6668 0x11148, // 11148..1114F; UNKNOWN
6669 0x11150, // 11150..11176; MAHAJANI
6670 0x11177, // 11177..1117F; UNKNOWN
6671 0x11180, // 11180..111DF; SHARADA
6672 0x111E0, // 111E0 ; UNKNOWN
6673 0x111E1, // 111E1..111F4; SINHALA
6674 0x111F5, // 111F5..111FF; UNKNOWN
6675 0x11200, // 11200..11211; KHOJKI
6676 0x11212, // 11212 ; UNKNOWN
6677 0x11213, // 11213..11241; KHOJKI
6678 0x11242, // 11242..1127F; UNKNOWN
6679 0x11280, // 11280..11286; MULTANI
6680 0x11287, // 11287 ; UNKNOWN
6681 0x11288, // 11288 ; MULTANI
6682 0x11289, // 11289 ; UNKNOWN
6683 0x1128A, // 1128A..1128D; MULTANI
6684 0x1128E, // 1128E ; UNKNOWN
6685 0x1128F, // 1128F..1129D; MULTANI
6686 0x1129E, // 1129E ; UNKNOWN
6687 0x1129F, // 1129F..112A9; MULTANI
6688 0x112AA, // 112AA..112AF; UNKNOWN
6689 0x112B0, // 112B0..112EA; KHUDAWADI
6690 0x112EB, // 112EB..112EF; UNKNOWN
6691 0x112F0, // 112F0..112F9; KHUDAWADI
6692 0x112FA, // 112FA..112FF; UNKNOWN
6693 0x11300, // 11300..11303; GRANTHA
6694 0x11304, // 11304 ; UNKNOWN
6695 0x11305, // 11305..1130C; GRANTHA
6696 0x1130D, // 1130D..1130E; UNKNOWN
6697 0x1130F, // 1130F..11310; GRANTHA
6698 0x11311, // 11311..11312; UNKNOWN
6699 0x11313, // 11313..11328; GRANTHA
6700 0x11329, // 11329 ; UNKNOWN
6701 0x1132A, // 1132A..11330; GRANTHA
6702 0x11331, // 11331 ; UNKNOWN
6703 0x11332, // 11332..11333; GRANTHA
6704 0x11334, // 11334 ; UNKNOWN
6705 0x11335, // 11335..11339; GRANTHA
6706 0x1133A, // 1133A ; UNKNOWN
6707 0x1133B, // 1133B ; INHERITED
6708 0x1133C, // 1133C..11344; GRANTHA
6709 0x11345, // 11345..11346; UNKNOWN
6710 0x11347, // 11347..11348; GRANTHA
6711 0x11349, // 11349..1134A; UNKNOWN
6712 0x1134B, // 1134B..1134D; GRANTHA
6713 0x1134E, // 1134E..1134F; UNKNOWN
6714 0x11350, // 11350 ; GRANTHA
6715 0x11351, // 11351..11356; UNKNOWN
6716 0x11357, // 11357 ; GRANTHA
6717 0x11358, // 11358..1135C; UNKNOWN
6718 0x1135D, // 1135D..11363; GRANTHA
6719 0x11364, // 11364..11365; UNKNOWN
6720 0x11366, // 11366..1136C; GRANTHA
6721 0x1136D, // 1136D..1136F; UNKNOWN
6722 0x11370, // 11370..11374; GRANTHA
6723 0x11375, // 11375..1137F; UNKNOWN
6724 0x11380, // 11380..11389; TULU_TIGALARI
6725 0x1138A, // 1138A ; UNKNOWN
6726 0x1138B, // 1138B ; TULU_TIGALARI
6727 0x1138C, // 1138C..1138D; UNKNOWN
6728 0x1138E, // 1138E ; TULU_TIGALARI
6729 0x1138F, // 1138F ; UNKNOWN
6730 0x11390, // 11390..113B5; TULU_TIGALARI
6731 0x113B6, // 113B6 ; UNKNOWN
6732 0x113B7, // 113B7..113C0; TULU_TIGALARI
6733 0x113C1, // 113C1 ; UNKNOWN
6734 0x113C2, // 113C2 ; TULU_TIGALARI
6735 0x113C3, // 113C3..113C4; UNKNOWN
6736 0x113C5, // 113C5 ; TULU_TIGALARI
6737 0x113C6, // 113C6 ; UNKNOWN
6738 0x113C7, // 113C7..113CA; TULU_TIGALARI
6739 0x113CB, // 113CB ; UNKNOWN
6740 0x113CC, // 113CC..113D5; TULU_TIGALARI
6741 0x113D6, // 113D6 ; UNKNOWN
6742 0x113D7, // 113D7..113D8; TULU_TIGALARI
6743 0x113D9, // 113D9..113E0; UNKNOWN
6744 0x113E1, // 113E1..113E2; TULU_TIGALARI
6745 0x113E3, // 113E3..113FF; UNKNOWN
6746 0x11400, // 11400..1145B; NEWA
6747 0x1145C, // 1145C ; UNKNOWN
6748 0x1145D, // 1145D..11461; NEWA
6749 0x11462, // 11462..1147F; UNKNOWN
6750 0x11480, // 11480..114C7; TIRHUTA
6751 0x114C8, // 114C8..114CF; UNKNOWN
6752 0x114D0, // 114D0..114D9; TIRHUTA
6753 0x114DA, // 114DA..1157F; UNKNOWN
6754 0x11580, // 11580..115B5; SIDDHAM
6755 0x115B6, // 115B6..115B7; UNKNOWN
6756 0x115B8, // 115B8..115DD; SIDDHAM
6757 0x115DE, // 115DE..115FF; UNKNOWN
6758 0x11600, // 11600..11644; MODI
6759 0x11645, // 11645..1164F; UNKNOWN
6760 0x11650, // 11650..11659; MODI
6761 0x1165A, // 1165A..1165F; UNKNOWN
6762 0x11660, // 11660..1166C; MONGOLIAN
6763 0x1166D, // 1166D..1167F; UNKNOWN
6764 0x11680, // 11680..116B9; TAKRI
6765 0x116BA, // 116BA..116BF; UNKNOWN
6766 0x116C0, // 116C0..116C9; TAKRI
6767 0x116CA, // 116CA..116CF; UNKNOWN
6768 0x116D0, // 116D0..116E3; MYANMAR
6769 0x116E4, // 116E4..116FF; UNKNOWN
6770 0x11700, // 11700..1171A; AHOM
6771 0x1171B, // 1171B..1171C; UNKNOWN
6772 0x1171D, // 1171D..1172B; AHOM
6773 0x1172C, // 1172C..1172F; UNKNOWN
6774 0x11730, // 11730..11746; AHOM
6775 0x11747, // 11747..117FF; UNKNOWN
6776 0x11800, // 11800..1183B; DOGRA
6777 0x1183C, // 1183C..1189F; UNKNOWN
6778 0x118A0, // 118A0..118F2; WARANG_CITI
6779 0x118F3, // 118F3..118FE; UNKNOWN
6780 0x118FF, // 118FF ; WARANG_CITI
6781 0x11900, // 11900..11906; DIVES_AKURU
6782 0x11907, // 11907..11908; UNKNOWN
6783 0x11909, // 11909 ; DIVES_AKURU
6784 0x1190A, // 1190A..1190B; UNKNOWN
6785 0x1190C, // 1190C..11913; DIVES_AKURU
6786 0x11914, // 11914 ; UNKNOWN
6787 0x11915, // 11915..11916; DIVES_AKURU
6788 0x11917, // 11917 ; UNKNOWN
6789 0x11918, // 11918..11935; DIVES_AKURU
6790 0x11936, // 11936 ; UNKNOWN
6791 0x11937, // 11937..11938; DIVES_AKURU
6792 0x11939, // 11939..1193A; UNKNOWN
6793 0x1193B, // 1193B..11946; DIVES_AKURU
6794 0x11947, // 11947..1194F; UNKNOWN
6795 0x11950, // 11950..11959; DIVES_AKURU
6796 0x1195A, // 1195A..1199F; UNKNOWN
6797 0x119A0, // 119A0..119A7; NANDINAGARI
6798 0x119A8, // 119A8..119A9; UNKNOWN
6799 0x119AA, // 119AA..119D7; NANDINAGARI
6800 0x119D8, // 119D8..119D9; UNKNOWN
6801 0x119DA, // 119DA..119E4; NANDINAGARI
6802 0x119E5, // 119E5..119FF; UNKNOWN
6803 0x11A00, // 11A00..11A47; ZANABAZAR_SQUARE
6804 0x11A48, // 11A48..11A4F; UNKNOWN
6805 0x11A50, // 11A50..11AA2; SOYOMBO
6806 0x11AA3, // 11AA3..11AAF; UNKNOWN
6807 0x11AB0, // 11AB0..11ABF; CANADIAN_ABORIGINAL
6808 0x11AC0, // 11AC0..11AF8; PAU_CIN_HAU
6809 0x11AF9, // 11AF9..11AFF; UNKNOWN
6810 0x11B00, // 11B00..11B09; DEVANAGARI
6811 0x11B0A, // 11B0A..11BBF; UNKNOWN
6812 0x11BC0, // 11BC0..11BE1; SUNUWAR
6813 0x11BE2, // 11BE2..11BEF; UNKNOWN
6814 0x11BF0, // 11BF0..11BF9; SUNUWAR
6815 0x11BFA, // 11BFA..11BFF; UNKNOWN
6816 0x11C00, // 11C00..11C08; BHAIKSUKI
6817 0x11C09, // 11C09 ; UNKNOWN
6818 0x11C0A, // 11C0A..11C36; BHAIKSUKI
6819 0x11C37, // 11C37 ; UNKNOWN
6820 0x11C38, // 11C38..11C45; BHAIKSUKI
6821 0x11C46, // 11C46..11C4F; UNKNOWN
6822 0x11C50, // 11C50..11C6C; BHAIKSUKI
6823 0x11C6D, // 11C6D..11C6F; UNKNOWN
6824 0x11C70, // 11C70..11C8F; MARCHEN
6825 0x11C90, // 11C90..11C91; UNKNOWN
6826 0x11C92, // 11C92..11CA7; MARCHEN
6827 0x11CA8, // 11CA8 ; UNKNOWN
6828 0x11CA9, // 11CA9..11CB6; MARCHEN
6829 0x11CB7, // 11CB7..11CFF; UNKNOWN
6830 0x11D00, // 11D00..11D06; MASARAM_GONDI
6831 0x11D07, // 11D07 ; UNKNOWN
6832 0x11D08, // 11D08..11D09; MASARAM_GONDI
6833 0x11D0A, // 11D0A ; UNKNOWN
6834 0x11D0B, // 11D0B..11D36; MASARAM_GONDI
6835 0x11D37, // 11D37..11D39; UNKNOWN
6836 0x11D3A, // 11D3A ; MASARAM_GONDI
6837 0x11D3B, // 11D3B ; UNKNOWN
6838 0x11D3C, // 11D3C..11D3D; MASARAM_GONDI
6839 0x11D3E, // 11D3E ; UNKNOWN
6840 0x11D3F, // 11D3F..11D47; MASARAM_GONDI
6841 0x11D48, // 11D48..11D4F; UNKNOWN
6842 0x11D50, // 11D50..11D59; MASARAM_GONDI
6843 0x11D5A, // 11D5A..11D5F; UNKNOWN
6844 0x11D60, // 11D60..11D65; GUNJALA_GONDI
6845 0x11D66, // 11D66 ; UNKNOWN
6846 0x11D67, // 11D67..11D68; GUNJALA_GONDI
6847 0x11D69, // 11D69 ; UNKNOWN
6848 0x11D6A, // 11D6A..11D8E; GUNJALA_GONDI
6849 0x11D8F, // 11D8F ; UNKNOWN
6850 0x11D90, // 11D90..11D91; GUNJALA_GONDI
6851 0x11D92, // 11D92 ; UNKNOWN
6852 0x11D93, // 11D93..11D98; GUNJALA_GONDI
6853 0x11D99, // 11D99..11D9F; UNKNOWN
6854 0x11DA0, // 11DA0..11DA9; GUNJALA_GONDI
6855 0x11DAA, // 11DAA..11EDF; UNKNOWN
6856 0x11EE0, // 11EE0..11EF8; MAKASAR
6857 0x11EF9, // 11EF9..11EFF; UNKNOWN
6858 0x11F00, // 11F00..11F10; KAWI
6859 0x11F11, // 11F11 ; UNKNOWN
6860 0x11F12, // 11F12..11F3A; KAWI
6861 0x11F3B, // 11F3B..11F3D; UNKNOWN
6862 0x11F3E, // 11F3E..11F5A; KAWI
6863 0x11F5B, // 11F5B..11FAF; UNKNOWN
6864 0x11FB0, // 11FB0 ; LISU
6865 0x11FB1, // 11FB1..11FBF; UNKNOWN
6866 0x11FC0, // 11FC0..11FF1; TAMIL
6867 0x11FF2, // 11FF2..11FFE; UNKNOWN
6868 0x11FFF, // 11FFF ; TAMIL
6869 0x12000, // 12000..12399; CUNEIFORM
6870 0x1239A, // 1239A..123FF; UNKNOWN
6871 0x12400, // 12400..1246E; CUNEIFORM
6872 0x1246F, // 1246F ; UNKNOWN
6873 0x12470, // 12470..12474; CUNEIFORM
6874 0x12475, // 12475..1247F; UNKNOWN
6875 0x12480, // 12480..12543; CUNEIFORM
6876 0x12544, // 12544..12F8F; UNKNOWN
6877 0x12F90, // 12F90..12FF2; CYPRO_MINOAN
6878 0x12FF3, // 12FF3..12FFF; UNKNOWN
6879 0x13000, // 13000..13455; EGYPTIAN_HIEROGLYPHS
6880 0x13456, // 13456..1345F; UNKNOWN
6881 0x13460, // 13460..143FA; EGYPTIAN_HIEROGLYPHS
6882 0x143FB, // 143FB..143FF; UNKNOWN
6883 0x14400, // 14400..14646; ANATOLIAN_HIEROGLYPHS
6884 0x14647, // 14647..160FF; UNKNOWN
6885 0x16100, // 16100..16139; GURUNG_KHEMA
6886 0x1613A, // 1613A..167FF; UNKNOWN
6887 0x16800, // 16800..16A38; BAMUM
6888 0x16A39, // 16A39..16A3F; UNKNOWN
6889 0x16A40, // 16A40..16A5E; MRO
6890 0x16A5F, // 16A5F ; UNKNOWN
6891 0x16A60, // 16A60..16A69; MRO
6892 0x16A6A, // 16A6A..16A6D; UNKNOWN
6893 0x16A6E, // 16A6E..16A6F; MRO
6894 0x16A70, // 16A70..16ABE; TANGSA
6895 0x16ABF, // 16ABF ; UNKNOWN
6896 0x16AC0, // 16AC0..16AC9; TANGSA
6897 0x16ACA, // 16ACA..16ACF; UNKNOWN
6898 0x16AD0, // 16AD0..16AED; BASSA_VAH
6899 0x16AEE, // 16AEE..16AEF; UNKNOWN
6900 0x16AF0, // 16AF0..16AF5; BASSA_VAH
6901 0x16AF6, // 16AF6..16AFF; UNKNOWN
6902 0x16B00, // 16B00..16B45; PAHAWH_HMONG
6903 0x16B46, // 16B46..16B4F; UNKNOWN
6904 0x16B50, // 16B50..16B59; PAHAWH_HMONG
6905 0x16B5A, // 16B5A ; UNKNOWN
6906 0x16B5B, // 16B5B..16B61; PAHAWH_HMONG
6907 0x16B62, // 16B62 ; UNKNOWN
6908 0x16B63, // 16B63..16B77; PAHAWH_HMONG
6909 0x16B78, // 16B78..16B7C; UNKNOWN
6910 0x16B7D, // 16B7D..16B8F; PAHAWH_HMONG
6911 0x16B90, // 16B90..16D3F; UNKNOWN
6912 0x16D40, // 16D40..16D79; KIRAT_RAI
6913 0x16D7A, // 16D7A..16E3F; UNKNOWN
6914 0x16E40, // 16E40..16E9A; MEDEFAIDRIN
6915 0x16E9B, // 16E9B..16EFF; UNKNOWN
6916 0x16F00, // 16F00..16F4A; MIAO
6917 0x16F4B, // 16F4B..16F4E; UNKNOWN
6918 0x16F4F, // 16F4F..16F87; MIAO
6919 0x16F88, // 16F88..16F8E; UNKNOWN
6920 0x16F8F, // 16F8F..16F9F; MIAO
6921 0x16FA0, // 16FA0..16FDF; UNKNOWN
6922 0x16FE0, // 16FE0 ; TANGUT
6923 0x16FE1, // 16FE1 ; NUSHU
6924 0x16FE2, // 16FE2..16FE3; HAN
6925 0x16FE4, // 16FE4 ; KHITAN_SMALL_SCRIPT
6926 0x16FE5, // 16FE5..16FEF; UNKNOWN
6927 0x16FF0, // 16FF0..16FF1; HAN
6928 0x16FF2, // 16FF2..16FFF; UNKNOWN
6929 0x17000, // 17000..187F7; TANGUT
6930 0x187F8, // 187F8..187FF; UNKNOWN
6931 0x18800, // 18800..18AFF; TANGUT
6932 0x18B00, // 18B00..18CD5; KHITAN_SMALL_SCRIPT
6933 0x18CD6, // 18CD6..18CFE; UNKNOWN
6934 0x18CFF, // 18CFF ; KHITAN_SMALL_SCRIPT
6935 0x18D00, // 18D00..18D08; TANGUT
6936 0x18D09, // 18D09..1AFEF; UNKNOWN
6937 0x1AFF0, // 1AFF0..1AFF3; KATAKANA
6938 0x1AFF4, // 1AFF4 ; UNKNOWN
6939 0x1AFF5, // 1AFF5..1AFFB; KATAKANA
6940 0x1AFFC, // 1AFFC ; UNKNOWN
6941 0x1AFFD, // 1AFFD..1AFFE; KATAKANA
6942 0x1AFFF, // 1AFFF ; UNKNOWN
6943 0x1B000, // 1B000 ; KATAKANA
6944 0x1B001, // 1B001..1B11F; HIRAGANA
6945 0x1B120, // 1B120..1B122; KATAKANA
6946 0x1B123, // 1B123..1B131; UNKNOWN
6947 0x1B132, // 1B132 ; HIRAGANA
6948 0x1B133, // 1B133..1B14F; UNKNOWN
6949 0x1B150, // 1B150..1B152; HIRAGANA
6950 0x1B153, // 1B153..1B154; UNKNOWN
6951 0x1B155, // 1B155 ; KATAKANA
6952 0x1B156, // 1B156..1B163; UNKNOWN
6953 0x1B164, // 1B164..1B167; KATAKANA
6954 0x1B168, // 1B168..1B16F; UNKNOWN
6955 0x1B170, // 1B170..1B2FB; NUSHU
6956 0x1B2FC, // 1B2FC..1BBFF; UNKNOWN
6957 0x1BC00, // 1BC00..1BC6A; DUPLOYAN
6958 0x1BC6B, // 1BC6B..1BC6F; UNKNOWN
6959 0x1BC70, // 1BC70..1BC7C; DUPLOYAN
6960 0x1BC7D, // 1BC7D..1BC7F; UNKNOWN
6961 0x1BC80, // 1BC80..1BC88; DUPLOYAN
6962 0x1BC89, // 1BC89..1BC8F; UNKNOWN
6963 0x1BC90, // 1BC90..1BC99; DUPLOYAN
6964 0x1BC9A, // 1BC9A..1BC9B; UNKNOWN
6965 0x1BC9C, // 1BC9C..1BC9F; DUPLOYAN
6966 0x1BCA0, // 1BCA0..1BCA3; COMMON
6967 0x1BCA4, // 1BCA4..1CBFF; UNKNOWN
6968 0x1CC00, // 1CC00..1CCF9; COMMON
6969 0x1CCFA, // 1CCFA..1CCFF; UNKNOWN
6970 0x1CD00, // 1CD00..1CEB3; COMMON
6971 0x1CEB4, // 1CEB4..1CEFF; UNKNOWN
6972 0x1CF00, // 1CF00..1CF2D; INHERITED
6973 0x1CF2E, // 1CF2E..1CF2F; UNKNOWN
6974 0x1CF30, // 1CF30..1CF46; INHERITED
6975 0x1CF47, // 1CF47..1CF4F; UNKNOWN
6976 0x1CF50, // 1CF50..1CFC3; COMMON
6977 0x1CFC4, // 1CFC4..1CFFF; UNKNOWN
6978 0x1D000, // 1D000..1D0F5; COMMON
6979 0x1D0F6, // 1D0F6..1D0FF; UNKNOWN
6980 0x1D100, // 1D100..1D126; COMMON
6981 0x1D127, // 1D127..1D128; UNKNOWN
6982 0x1D129, // 1D129..1D166; COMMON
6983 0x1D167, // 1D167..1D169; INHERITED
6984 0x1D16A, // 1D16A..1D17A; COMMON
6985 0x1D17B, // 1D17B..1D182; INHERITED
6986 0x1D183, // 1D183..1D184; COMMON
6987 0x1D185, // 1D185..1D18B; INHERITED
6988 0x1D18C, // 1D18C..1D1A9; COMMON
6989 0x1D1AA, // 1D1AA..1D1AD; INHERITED
6990 0x1D1AE, // 1D1AE..1D1EA; COMMON
6991 0x1D1EB, // 1D1EB..1D1FF; UNKNOWN
6992 0x1D200, // 1D200..1D245; GREEK
6993 0x1D246, // 1D246..1D2BF; UNKNOWN
6994 0x1D2C0, // 1D2C0..1D2D3; COMMON
6995 0x1D2D4, // 1D2D4..1D2DF; UNKNOWN
6996 0x1D2E0, // 1D2E0..1D2F3; COMMON
6997 0x1D2F4, // 1D2F4..1D2FF; UNKNOWN
6998 0x1D300, // 1D300..1D356; COMMON
6999 0x1D357, // 1D357..1D35F; UNKNOWN
7000 0x1D360, // 1D360..1D378; COMMON
7001 0x1D379, // 1D379..1D3FF; UNKNOWN
7002 0x1D400, // 1D400..1D454; COMMON
7003 0x1D455, // 1D455 ; UNKNOWN
7004 0x1D456, // 1D456..1D49C; COMMON
7005 0x1D49D, // 1D49D ; UNKNOWN
7006 0x1D49E, // 1D49E..1D49F; COMMON
7007 0x1D4A0, // 1D4A0..1D4A1; UNKNOWN
7008 0x1D4A2, // 1D4A2 ; COMMON
7009 0x1D4A3, // 1D4A3..1D4A4; UNKNOWN
7010 0x1D4A5, // 1D4A5..1D4A6; COMMON
7011 0x1D4A7, // 1D4A7..1D4A8; UNKNOWN
7012 0x1D4A9, // 1D4A9..1D4AC; COMMON
7013 0x1D4AD, // 1D4AD ; UNKNOWN
7014 0x1D4AE, // 1D4AE..1D4B9; COMMON
7015 0x1D4BA, // 1D4BA ; UNKNOWN
7016 0x1D4BB, // 1D4BB ; COMMON
7017 0x1D4BC, // 1D4BC ; UNKNOWN
7018 0x1D4BD, // 1D4BD..1D4C3; COMMON
7019 0x1D4C4, // 1D4C4 ; UNKNOWN
7020 0x1D4C5, // 1D4C5..1D505; COMMON
7021 0x1D506, // 1D506 ; UNKNOWN
7022 0x1D507, // 1D507..1D50A; COMMON
7023 0x1D50B, // 1D50B..1D50C; UNKNOWN
7024 0x1D50D, // 1D50D..1D514; COMMON
7025 0x1D515, // 1D515 ; UNKNOWN
7026 0x1D516, // 1D516..1D51C; COMMON
7027 0x1D51D, // 1D51D ; UNKNOWN
7028 0x1D51E, // 1D51E..1D539; COMMON
7029 0x1D53A, // 1D53A ; UNKNOWN
7030 0x1D53B, // 1D53B..1D53E; COMMON
7031 0x1D53F, // 1D53F ; UNKNOWN
7032 0x1D540, // 1D540..1D544; COMMON
7033 0x1D545, // 1D545 ; UNKNOWN
7034 0x1D546, // 1D546 ; COMMON
7035 0x1D547, // 1D547..1D549; UNKNOWN
7036 0x1D54A, // 1D54A..1D550; COMMON
7037 0x1D551, // 1D551 ; UNKNOWN
7038 0x1D552, // 1D552..1D6A5; COMMON
7039 0x1D6A6, // 1D6A6..1D6A7; UNKNOWN
7040 0x1D6A8, // 1D6A8..1D7CB; COMMON
7041 0x1D7CC, // 1D7CC..1D7CD; UNKNOWN
7042 0x1D7CE, // 1D7CE..1D7FF; COMMON
7043 0x1D800, // 1D800..1DA8B; SIGNWRITING
7044 0x1DA8C, // 1DA8C..1DA9A; UNKNOWN
7045 0x1DA9B, // 1DA9B..1DA9F; SIGNWRITING
7046 0x1DAA0, // 1DAA0 ; UNKNOWN
7047 0x1DAA1, // 1DAA1..1DAAF; SIGNWRITING
7048 0x1DAB0, // 1DAB0..1DEFF; UNKNOWN
7049 0x1DF00, // 1DF00..1DF1E; LATIN
7050 0x1DF1F, // 1DF1F..1DF24; UNKNOWN
7051 0x1DF25, // 1DF25..1DF2A; LATIN
7052 0x1DF2B, // 1DF2B..1DFFF; UNKNOWN
7053 0x1E000, // 1E000..1E006; GLAGOLITIC
7054 0x1E007, // 1E007 ; UNKNOWN
7055 0x1E008, // 1E008..1E018; GLAGOLITIC
7056 0x1E019, // 1E019..1E01A; UNKNOWN
7057 0x1E01B, // 1E01B..1E021; GLAGOLITIC
7058 0x1E022, // 1E022 ; UNKNOWN
7059 0x1E023, // 1E023..1E024; GLAGOLITIC
7060 0x1E025, // 1E025 ; UNKNOWN
7061 0x1E026, // 1E026..1E02A; GLAGOLITIC
7062 0x1E02B, // 1E02B..1E02F; UNKNOWN
7063 0x1E030, // 1E030..1E06D; CYRILLIC
7064 0x1E06E, // 1E06E..1E08E; UNKNOWN
7065 0x1E08F, // 1E08F ; CYRILLIC
7066 0x1E090, // 1E090..1E0FF; UNKNOWN
7067 0x1E100, // 1E100..1E12C; NYIAKENG_PUACHUE_HMONG
7068 0x1E12D, // 1E12D..1E12F; UNKNOWN
7069 0x1E130, // 1E130..1E13D; NYIAKENG_PUACHUE_HMONG
7070 0x1E13E, // 1E13E..1E13F; UNKNOWN
7071 0x1E140, // 1E140..1E149; NYIAKENG_PUACHUE_HMONG
7072 0x1E14A, // 1E14A..1E14D; UNKNOWN
7073 0x1E14E, // 1E14E..1E14F; NYIAKENG_PUACHUE_HMONG
7074 0x1E150, // 1E150..1E28F; UNKNOWN
7075 0x1E290, // 1E290..1E2AE; TOTO
7076 0x1E2AF, // 1E2AF..1E2BF; UNKNOWN
7077 0x1E2C0, // 1E2C0..1E2F9; WANCHO
7078 0x1E2FA, // 1E2FA..1E2FE; UNKNOWN
7079 0x1E2FF, // 1E2FF ; WANCHO
7080 0x1E300, // 1E300..1E4CF; UNKNOWN
7081 0x1E4D0, // 1E4D0..1E4F9; NAG_MUNDARI
7082 0x1E4FA, // 1E4FA..1E5CF; UNKNOWN
7083 0x1E5D0, // 1E5D0..1E5FA; OL_ONAL
7084 0x1E5FB, // 1E5FB..1E5FE; UNKNOWN
7085 0x1E5FF, // 1E5FF ; OL_ONAL
7086 0x1E600, // 1E600..1E7DF; UNKNOWN
7087 0x1E7E0, // 1E7E0..1E7E6; ETHIOPIC
7088 0x1E7E7, // 1E7E7 ; UNKNOWN
7089 0x1E7E8, // 1E7E8..1E7EB; ETHIOPIC
7090 0x1E7EC, // 1E7EC ; UNKNOWN
7091 0x1E7ED, // 1E7ED..1E7EE; ETHIOPIC
7092 0x1E7EF, // 1E7EF ; UNKNOWN
7093 0x1E7F0, // 1E7F0..1E7FE; ETHIOPIC
7094 0x1E7FF, // 1E7FF ; UNKNOWN
7095 0x1E800, // 1E800..1E8C4; MENDE_KIKAKUI
7096 0x1E8C5, // 1E8C5..1E8C6; UNKNOWN
7097 0x1E8C7, // 1E8C7..1E8D6; MENDE_KIKAKUI
7098 0x1E8D7, // 1E8D7..1E8FF; UNKNOWN
7099 0x1E900, // 1E900..1E94B; ADLAM
7100 0x1E94C, // 1E94C..1E94F; UNKNOWN
7101 0x1E950, // 1E950..1E959; ADLAM
7102 0x1E95A, // 1E95A..1E95D; UNKNOWN
7103 0x1E95E, // 1E95E..1E95F; ADLAM
7104 0x1E960, // 1E960..1EC70; UNKNOWN
7105 0x1EC71, // 1EC71..1ECB4; COMMON
7106 0x1ECB5, // 1ECB5..1ED00; UNKNOWN
7107 0x1ED01, // 1ED01..1ED3D; COMMON
7108 0x1ED3E, // 1ED3E..1EDFF; UNKNOWN
7109 0x1EE00, // 1EE00..1EE03; ARABIC
7110 0x1EE04, // 1EE04 ; UNKNOWN
7111 0x1EE05, // 1EE05..1EE1F; ARABIC
7112 0x1EE20, // 1EE20 ; UNKNOWN
7113 0x1EE21, // 1EE21..1EE22; ARABIC
7114 0x1EE23, // 1EE23 ; UNKNOWN
7115 0x1EE24, // 1EE24 ; ARABIC
7116 0x1EE25, // 1EE25..1EE26; UNKNOWN
7117 0x1EE27, // 1EE27 ; ARABIC
7118 0x1EE28, // 1EE28 ; UNKNOWN
7119 0x1EE29, // 1EE29..1EE32; ARABIC
7120 0x1EE33, // 1EE33 ; UNKNOWN
7121 0x1EE34, // 1EE34..1EE37; ARABIC
7122 0x1EE38, // 1EE38 ; UNKNOWN
7123 0x1EE39, // 1EE39 ; ARABIC
7124 0x1EE3A, // 1EE3A ; UNKNOWN
7125 0x1EE3B, // 1EE3B ; ARABIC
7126 0x1EE3C, // 1EE3C..1EE41; UNKNOWN
7127 0x1EE42, // 1EE42 ; ARABIC
7128 0x1EE43, // 1EE43..1EE46; UNKNOWN
7129 0x1EE47, // 1EE47 ; ARABIC
7130 0x1EE48, // 1EE48 ; UNKNOWN
7131 0x1EE49, // 1EE49 ; ARABIC
7132 0x1EE4A, // 1EE4A ; UNKNOWN
7133 0x1EE4B, // 1EE4B ; ARABIC
7134 0x1EE4C, // 1EE4C ; UNKNOWN
7135 0x1EE4D, // 1EE4D..1EE4F; ARABIC
7136 0x1EE50, // 1EE50 ; UNKNOWN
7137 0x1EE51, // 1EE51..1EE52; ARABIC
7138 0x1EE53, // 1EE53 ; UNKNOWN
7139 0x1EE54, // 1EE54 ; ARABIC
7140 0x1EE55, // 1EE55..1EE56; UNKNOWN
7141 0x1EE57, // 1EE57 ; ARABIC
7142 0x1EE58, // 1EE58 ; UNKNOWN
7143 0x1EE59, // 1EE59 ; ARABIC
7144 0x1EE5A, // 1EE5A ; UNKNOWN
7145 0x1EE5B, // 1EE5B ; ARABIC
7146 0x1EE5C, // 1EE5C ; UNKNOWN
7147 0x1EE5D, // 1EE5D ; ARABIC
7148 0x1EE5E, // 1EE5E ; UNKNOWN
7149 0x1EE5F, // 1EE5F ; ARABIC
7150 0x1EE60, // 1EE60 ; UNKNOWN
7151 0x1EE61, // 1EE61..1EE62; ARABIC
7152 0x1EE63, // 1EE63 ; UNKNOWN
7153 0x1EE64, // 1EE64 ; ARABIC
7154 0x1EE65, // 1EE65..1EE66; UNKNOWN
7155 0x1EE67, // 1EE67..1EE6A; ARABIC
7156 0x1EE6B, // 1EE6B ; UNKNOWN
7157 0x1EE6C, // 1EE6C..1EE72; ARABIC
7158 0x1EE73, // 1EE73 ; UNKNOWN
7159 0x1EE74, // 1EE74..1EE77; ARABIC
7160 0x1EE78, // 1EE78 ; UNKNOWN
7161 0x1EE79, // 1EE79..1EE7C; ARABIC
7162 0x1EE7D, // 1EE7D ; UNKNOWN
7163 0x1EE7E, // 1EE7E ; ARABIC
7164 0x1EE7F, // 1EE7F ; UNKNOWN
7165 0x1EE80, // 1EE80..1EE89; ARABIC
7166 0x1EE8A, // 1EE8A ; UNKNOWN
7167 0x1EE8B, // 1EE8B..1EE9B; ARABIC
7168 0x1EE9C, // 1EE9C..1EEA0; UNKNOWN
7169 0x1EEA1, // 1EEA1..1EEA3; ARABIC
7170 0x1EEA4, // 1EEA4 ; UNKNOWN
7171 0x1EEA5, // 1EEA5..1EEA9; ARABIC
7172 0x1EEAA, // 1EEAA ; UNKNOWN
7173 0x1EEAB, // 1EEAB..1EEBB; ARABIC
7174 0x1EEBC, // 1EEBC..1EEEF; UNKNOWN
7175 0x1EEF0, // 1EEF0..1EEF1; ARABIC
7176 0x1EEF2, // 1EEF2..1EFFF; UNKNOWN
7177 0x1F000, // 1F000..1F02B; COMMON
7178 0x1F02C, // 1F02C..1F02F; UNKNOWN
7179 0x1F030, // 1F030..1F093; COMMON
7180 0x1F094, // 1F094..1F09F; UNKNOWN
7181 0x1F0A0, // 1F0A0..1F0AE; COMMON
7182 0x1F0AF, // 1F0AF..1F0B0; UNKNOWN
7183 0x1F0B1, // 1F0B1..1F0BF; COMMON
7184 0x1F0C0, // 1F0C0 ; UNKNOWN
7185 0x1F0C1, // 1F0C1..1F0CF; COMMON
7186 0x1F0D0, // 1F0D0 ; UNKNOWN
7187 0x1F0D1, // 1F0D1..1F0F5; COMMON
7188 0x1F0F6, // 1F0F6..1F0FF; UNKNOWN
7189 0x1F100, // 1F100..1F1AD; COMMON
7190 0x1F1AE, // 1F1AE..1F1E5; UNKNOWN
7191 0x1F1E6, // 1F1E6..1F1FF; COMMON
7192 0x1F200, // 1F200 ; HIRAGANA
7193 0x1F201, // 1F201..1F202; COMMON
7194 0x1F203, // 1F203..1F20F; UNKNOWN
7195 0x1F210, // 1F210..1F23B; COMMON
7196 0x1F23C, // 1F23C..1F23F; UNKNOWN
7197 0x1F240, // 1F240..1F248; COMMON
7198 0x1F249, // 1F249..1F24F; UNKNOWN
7199 0x1F250, // 1F250..1F251; COMMON
7200 0x1F252, // 1F252..1F25F; UNKNOWN
7201 0x1F260, // 1F260..1F265; COMMON
7202 0x1F266, // 1F266..1F2FF; UNKNOWN
7203 0x1F300, // 1F300..1F6D7; COMMON
7204 0x1F6D8, // 1F6D8..1F6DB; UNKNOWN
7205 0x1F6DC, // 1F6DC..1F6EC; COMMON
7206 0x1F6ED, // 1F6ED..1F6EF; UNKNOWN
7207 0x1F6F0, // 1F6F0..1F6FC; COMMON
7208 0x1F6FD, // 1F6FD..1F6FF; UNKNOWN
7209 0x1F700, // 1F700..1F776; COMMON
7210 0x1F777, // 1F777..1F77A; UNKNOWN
7211 0x1F77B, // 1F77B..1F7D9; COMMON
7212 0x1F7DA, // 1F7DA..1F7DF; UNKNOWN
7213 0x1F7E0, // 1F7E0..1F7EB; COMMON
7214 0x1F7EC, // 1F7EC..1F7EF; UNKNOWN
7215 0x1F7F0, // 1F7F0 ; COMMON
7216 0x1F7F1, // 1F7F1..1F7FF; UNKNOWN
7217 0x1F800, // 1F800..1F80B; COMMON
7218 0x1F80C, // 1F80C..1F80F; UNKNOWN
7219 0x1F810, // 1F810..1F847; COMMON
7220 0x1F848, // 1F848..1F84F; UNKNOWN
7221 0x1F850, // 1F850..1F859; COMMON
7222 0x1F85A, // 1F85A..1F85F; UNKNOWN
7223 0x1F860, // 1F860..1F887; COMMON
7224 0x1F888, // 1F888..1F88F; UNKNOWN
7225 0x1F890, // 1F890..1F8AD; COMMON
7226 0x1F8AE, // 1F8AE..1F8AF; UNKNOWN
7227 0x1F8B0, // 1F8B0..1F8BB; COMMON
7228 0x1F8BC, // 1F8BC..1F8BF; UNKNOWN
7229 0x1F8C0, // 1F8C0..1F8C1; COMMON
7230 0x1F8C2, // 1F8C2..1F8FF; UNKNOWN
7231 0x1F900, // 1F900..1FA53; COMMON
7232 0x1FA54, // 1FA54..1FA5F; UNKNOWN
7233 0x1FA60, // 1FA60..1FA6D; COMMON
7234 0x1FA6E, // 1FA6E..1FA6F; UNKNOWN
7235 0x1FA70, // 1FA70..1FA7C; COMMON
7236 0x1FA7D, // 1FA7D..1FA7F; UNKNOWN
7237 0x1FA80, // 1FA80..1FA89; COMMON
7238 0x1FA8A, // 1FA8A..1FA8E; UNKNOWN
7239 0x1FA8F, // 1FA8F..1FAC6; COMMON
7240 0x1FAC7, // 1FAC7..1FACD; UNKNOWN
7241 0x1FACE, // 1FACE..1FADC; COMMON
7242 0x1FADD, // 1FADD..1FADE; UNKNOWN
7243 0x1FADF, // 1FADF..1FAE9; COMMON
7244 0x1FAEA, // 1FAEA..1FAEF; UNKNOWN
7245 0x1FAF0, // 1FAF0..1FAF8; COMMON
7246 0x1FAF9, // 1FAF9..1FAFF; UNKNOWN
7247 0x1FB00, // 1FB00..1FB92; COMMON
7248 0x1FB93, // 1FB93 ; UNKNOWN
7249 0x1FB94, // 1FB94..1FBF9; COMMON
7250 0x1FBFA, // 1FBFA..1FFFF; UNKNOWN
7251 0x20000, // 20000..2A6DF; HAN
7252 0x2A6E0, // 2A6E0..2A6FF; UNKNOWN
7253 0x2A700, // 2A700..2B739; HAN
7254 0x2B73A, // 2B73A..2B73F; UNKNOWN
7255 0x2B740, // 2B740..2B81D; HAN
7256 0x2B81E, // 2B81E..2B81F; UNKNOWN
7257 0x2B820, // 2B820..2CEA1; HAN
7258 0x2CEA2, // 2CEA2..2CEAF; UNKNOWN
7259 0x2CEB0, // 2CEB0..2EBE0; HAN
7260 0x2EBE1, // 2EBE1..2EBEF; UNKNOWN
7261 0x2EBF0, // 2EBF0..2EE5D; HAN
7262 0x2EE5E, // 2EE5E..2F7FF; UNKNOWN
7263 0x2F800, // 2F800..2FA1D; HAN
7264 0x2FA1E, // 2FA1E..2FFFF; UNKNOWN
7265 0x30000, // 30000..3134A; HAN
7266 0x3134B, // 3134B..3134F; UNKNOWN
7267 0x31350, // 31350..323AF; HAN
7268 0x323B0, // 323B0..E0000; UNKNOWN
7269 0xE0001, // E0001 ; COMMON
7270 0xE0002, // E0002..E001F; UNKNOWN
7271 0xE0020, // E0020..E007F; COMMON
7272 0xE0080, // E0080..E00FF; UNKNOWN
7273 0xE0100, // E0100..E01EF; INHERITED
7274 0xE01F0, // E01F0..10FFFF; UNKNOWN
7275 };
7276
7277 private static final UnicodeScript[] scripts = {
7278 COMMON, // 0000..0040
7279 LATIN, // 0041..005A
7280 COMMON, // 005B..0060
7281 LATIN, // 0061..007A
7282 COMMON, // 007B..00A9
7283 LATIN, // 00AA
7284 COMMON, // 00AB..00B9
7285 LATIN, // 00BA
7286 COMMON, // 00BB..00BF
7287 LATIN, // 00C0..00D6
7288 COMMON, // 00D7
7289 LATIN, // 00D8..00F6
7290 COMMON, // 00F7
7291 LATIN, // 00F8..02B8
7292 COMMON, // 02B9..02DF
7293 LATIN, // 02E0..02E4
7294 COMMON, // 02E5..02E9
7295 BOPOMOFO, // 02EA..02EB
7296 COMMON, // 02EC..02FF
7297 INHERITED, // 0300..036F
7298 GREEK, // 0370..0373
7299 COMMON, // 0374
7300 GREEK, // 0375..0377
7301 UNKNOWN, // 0378..0379
7302 GREEK, // 037A..037D
7303 COMMON, // 037E
7304 GREEK, // 037F
7305 UNKNOWN, // 0380..0383
7306 GREEK, // 0384
7307 COMMON, // 0385
7308 GREEK, // 0386
7309 COMMON, // 0387
7310 GREEK, // 0388..038A
7311 UNKNOWN, // 038B
7312 GREEK, // 038C
7313 UNKNOWN, // 038D
7314 GREEK, // 038E..03A1
7315 UNKNOWN, // 03A2
7316 GREEK, // 03A3..03E1
7317 COPTIC, // 03E2..03EF
7318 GREEK, // 03F0..03FF
7319 CYRILLIC, // 0400..0484
7320 INHERITED, // 0485..0486
7321 CYRILLIC, // 0487..052F
7322 UNKNOWN, // 0530
7323 ARMENIAN, // 0531..0556
7324 UNKNOWN, // 0557..0558
7325 ARMENIAN, // 0559..058A
7326 UNKNOWN, // 058B..058C
7327 ARMENIAN, // 058D..058F
7328 UNKNOWN, // 0590
7329 HEBREW, // 0591..05C7
7330 UNKNOWN, // 05C8..05CF
7331 HEBREW, // 05D0..05EA
7332 UNKNOWN, // 05EB..05EE
7333 HEBREW, // 05EF..05F4
7334 UNKNOWN, // 05F5..05FF
7335 ARABIC, // 0600..0604
7336 COMMON, // 0605
7337 ARABIC, // 0606..060B
7338 COMMON, // 060C
7339 ARABIC, // 060D..061A
7340 COMMON, // 061B
7341 ARABIC, // 061C..061E
7342 COMMON, // 061F
7343 ARABIC, // 0620..063F
7344 COMMON, // 0640
7345 ARABIC, // 0641..064A
7346 INHERITED, // 064B..0655
7347 ARABIC, // 0656..066F
7348 INHERITED, // 0670
7349 ARABIC, // 0671..06DC
7350 COMMON, // 06DD
7351 ARABIC, // 06DE..06FF
7352 SYRIAC, // 0700..070D
7353 UNKNOWN, // 070E
7354 SYRIAC, // 070F..074A
7355 UNKNOWN, // 074B..074C
7356 SYRIAC, // 074D..074F
7357 ARABIC, // 0750..077F
7358 THAANA, // 0780..07B1
7359 UNKNOWN, // 07B2..07BF
7360 NKO, // 07C0..07FA
7361 UNKNOWN, // 07FB..07FC
7362 NKO, // 07FD..07FF
7363 SAMARITAN, // 0800..082D
7364 UNKNOWN, // 082E..082F
7365 SAMARITAN, // 0830..083E
7366 UNKNOWN, // 083F
7367 MANDAIC, // 0840..085B
7368 UNKNOWN, // 085C..085D
7369 MANDAIC, // 085E
7370 UNKNOWN, // 085F
7371 SYRIAC, // 0860..086A
7372 UNKNOWN, // 086B..086F
7373 ARABIC, // 0870..088E
7374 UNKNOWN, // 088F
7375 ARABIC, // 0890..0891
7376 UNKNOWN, // 0892..0896
7377 ARABIC, // 0897..08E1
7378 COMMON, // 08E2
7379 ARABIC, // 08E3..08FF
7380 DEVANAGARI, // 0900..0950
7381 INHERITED, // 0951..0954
7382 DEVANAGARI, // 0955..0963
7383 COMMON, // 0964..0965
7384 DEVANAGARI, // 0966..097F
7385 BENGALI, // 0980..0983
7386 UNKNOWN, // 0984
7387 BENGALI, // 0985..098C
7388 UNKNOWN, // 098D..098E
7389 BENGALI, // 098F..0990
7390 UNKNOWN, // 0991..0992
7391 BENGALI, // 0993..09A8
7392 UNKNOWN, // 09A9
7393 BENGALI, // 09AA..09B0
7394 UNKNOWN, // 09B1
7395 BENGALI, // 09B2
7396 UNKNOWN, // 09B3..09B5
7397 BENGALI, // 09B6..09B9
7398 UNKNOWN, // 09BA..09BB
7399 BENGALI, // 09BC..09C4
7400 UNKNOWN, // 09C5..09C6
7401 BENGALI, // 09C7..09C8
7402 UNKNOWN, // 09C9..09CA
7403 BENGALI, // 09CB..09CE
7404 UNKNOWN, // 09CF..09D6
7405 BENGALI, // 09D7
7406 UNKNOWN, // 09D8..09DB
7407 BENGALI, // 09DC..09DD
7408 UNKNOWN, // 09DE
7409 BENGALI, // 09DF..09E3
7410 UNKNOWN, // 09E4..09E5
7411 BENGALI, // 09E6..09FE
7412 UNKNOWN, // 09FF..0A00
7413 GURMUKHI, // 0A01..0A03
7414 UNKNOWN, // 0A04
7415 GURMUKHI, // 0A05..0A0A
7416 UNKNOWN, // 0A0B..0A0E
7417 GURMUKHI, // 0A0F..0A10
7418 UNKNOWN, // 0A11..0A12
7419 GURMUKHI, // 0A13..0A28
7420 UNKNOWN, // 0A29
7421 GURMUKHI, // 0A2A..0A30
7422 UNKNOWN, // 0A31
7423 GURMUKHI, // 0A32..0A33
7424 UNKNOWN, // 0A34
7425 GURMUKHI, // 0A35..0A36
7426 UNKNOWN, // 0A37
7427 GURMUKHI, // 0A38..0A39
7428 UNKNOWN, // 0A3A..0A3B
7429 GURMUKHI, // 0A3C
7430 UNKNOWN, // 0A3D
7431 GURMUKHI, // 0A3E..0A42
7432 UNKNOWN, // 0A43..0A46
7433 GURMUKHI, // 0A47..0A48
7434 UNKNOWN, // 0A49..0A4A
7435 GURMUKHI, // 0A4B..0A4D
7436 UNKNOWN, // 0A4E..0A50
7437 GURMUKHI, // 0A51
7438 UNKNOWN, // 0A52..0A58
7439 GURMUKHI, // 0A59..0A5C
7440 UNKNOWN, // 0A5D
7441 GURMUKHI, // 0A5E
7442 UNKNOWN, // 0A5F..0A65
7443 GURMUKHI, // 0A66..0A76
7444 UNKNOWN, // 0A77..0A80
7445 GUJARATI, // 0A81..0A83
7446 UNKNOWN, // 0A84
7447 GUJARATI, // 0A85..0A8D
7448 UNKNOWN, // 0A8E
7449 GUJARATI, // 0A8F..0A91
7450 UNKNOWN, // 0A92
7451 GUJARATI, // 0A93..0AA8
7452 UNKNOWN, // 0AA9
7453 GUJARATI, // 0AAA..0AB0
7454 UNKNOWN, // 0AB1
7455 GUJARATI, // 0AB2..0AB3
7456 UNKNOWN, // 0AB4
7457 GUJARATI, // 0AB5..0AB9
7458 UNKNOWN, // 0ABA..0ABB
7459 GUJARATI, // 0ABC..0AC5
7460 UNKNOWN, // 0AC6
7461 GUJARATI, // 0AC7..0AC9
7462 UNKNOWN, // 0ACA
7463 GUJARATI, // 0ACB..0ACD
7464 UNKNOWN, // 0ACE..0ACF
7465 GUJARATI, // 0AD0
7466 UNKNOWN, // 0AD1..0ADF
7467 GUJARATI, // 0AE0..0AE3
7468 UNKNOWN, // 0AE4..0AE5
7469 GUJARATI, // 0AE6..0AF1
7470 UNKNOWN, // 0AF2..0AF8
7471 GUJARATI, // 0AF9..0AFF
7472 UNKNOWN, // 0B00
7473 ORIYA, // 0B01..0B03
7474 UNKNOWN, // 0B04
7475 ORIYA, // 0B05..0B0C
7476 UNKNOWN, // 0B0D..0B0E
7477 ORIYA, // 0B0F..0B10
7478 UNKNOWN, // 0B11..0B12
7479 ORIYA, // 0B13..0B28
7480 UNKNOWN, // 0B29
7481 ORIYA, // 0B2A..0B30
7482 UNKNOWN, // 0B31
7483 ORIYA, // 0B32..0B33
7484 UNKNOWN, // 0B34
7485 ORIYA, // 0B35..0B39
7486 UNKNOWN, // 0B3A..0B3B
7487 ORIYA, // 0B3C..0B44
7488 UNKNOWN, // 0B45..0B46
7489 ORIYA, // 0B47..0B48
7490 UNKNOWN, // 0B49..0B4A
7491 ORIYA, // 0B4B..0B4D
7492 UNKNOWN, // 0B4E..0B54
7493 ORIYA, // 0B55..0B57
7494 UNKNOWN, // 0B58..0B5B
7495 ORIYA, // 0B5C..0B5D
7496 UNKNOWN, // 0B5E
7497 ORIYA, // 0B5F..0B63
7498 UNKNOWN, // 0B64..0B65
7499 ORIYA, // 0B66..0B77
7500 UNKNOWN, // 0B78..0B81
7501 TAMIL, // 0B82..0B83
7502 UNKNOWN, // 0B84
7503 TAMIL, // 0B85..0B8A
7504 UNKNOWN, // 0B8B..0B8D
7505 TAMIL, // 0B8E..0B90
7506 UNKNOWN, // 0B91
7507 TAMIL, // 0B92..0B95
7508 UNKNOWN, // 0B96..0B98
7509 TAMIL, // 0B99..0B9A
7510 UNKNOWN, // 0B9B
7511 TAMIL, // 0B9C
7512 UNKNOWN, // 0B9D
7513 TAMIL, // 0B9E..0B9F
7514 UNKNOWN, // 0BA0..0BA2
7515 TAMIL, // 0BA3..0BA4
7516 UNKNOWN, // 0BA5..0BA7
7517 TAMIL, // 0BA8..0BAA
7518 UNKNOWN, // 0BAB..0BAD
7519 TAMIL, // 0BAE..0BB9
7520 UNKNOWN, // 0BBA..0BBD
7521 TAMIL, // 0BBE..0BC2
7522 UNKNOWN, // 0BC3..0BC5
7523 TAMIL, // 0BC6..0BC8
7524 UNKNOWN, // 0BC9
7525 TAMIL, // 0BCA..0BCD
7526 UNKNOWN, // 0BCE..0BCF
7527 TAMIL, // 0BD0
7528 UNKNOWN, // 0BD1..0BD6
7529 TAMIL, // 0BD7
7530 UNKNOWN, // 0BD8..0BE5
7531 TAMIL, // 0BE6..0BFA
7532 UNKNOWN, // 0BFB..0BFF
7533 TELUGU, // 0C00..0C0C
7534 UNKNOWN, // 0C0D
7535 TELUGU, // 0C0E..0C10
7536 UNKNOWN, // 0C11
7537 TELUGU, // 0C12..0C28
7538 UNKNOWN, // 0C29
7539 TELUGU, // 0C2A..0C39
7540 UNKNOWN, // 0C3A..0C3B
7541 TELUGU, // 0C3C..0C44
7542 UNKNOWN, // 0C45
7543 TELUGU, // 0C46..0C48
7544 UNKNOWN, // 0C49
7545 TELUGU, // 0C4A..0C4D
7546 UNKNOWN, // 0C4E..0C54
7547 TELUGU, // 0C55..0C56
7548 UNKNOWN, // 0C57
7549 TELUGU, // 0C58..0C5A
7550 UNKNOWN, // 0C5B..0C5C
7551 TELUGU, // 0C5D
7552 UNKNOWN, // 0C5E..0C5F
7553 TELUGU, // 0C60..0C63
7554 UNKNOWN, // 0C64..0C65
7555 TELUGU, // 0C66..0C6F
7556 UNKNOWN, // 0C70..0C76
7557 TELUGU, // 0C77..0C7F
7558 KANNADA, // 0C80..0C8C
7559 UNKNOWN, // 0C8D
7560 KANNADA, // 0C8E..0C90
7561 UNKNOWN, // 0C91
7562 KANNADA, // 0C92..0CA8
7563 UNKNOWN, // 0CA9
7564 KANNADA, // 0CAA..0CB3
7565 UNKNOWN, // 0CB4
7566 KANNADA, // 0CB5..0CB9
7567 UNKNOWN, // 0CBA..0CBB
7568 KANNADA, // 0CBC..0CC4
7569 UNKNOWN, // 0CC5
7570 KANNADA, // 0CC6..0CC8
7571 UNKNOWN, // 0CC9
7572 KANNADA, // 0CCA..0CCD
7573 UNKNOWN, // 0CCE..0CD4
7574 KANNADA, // 0CD5..0CD6
7575 UNKNOWN, // 0CD7..0CDC
7576 KANNADA, // 0CDD..0CDE
7577 UNKNOWN, // 0CDF
7578 KANNADA, // 0CE0..0CE3
7579 UNKNOWN, // 0CE4..0CE5
7580 KANNADA, // 0CE6..0CEF
7581 UNKNOWN, // 0CF0
7582 KANNADA, // 0CF1..0CF3
7583 UNKNOWN, // 0CF4..0CFF
7584 MALAYALAM, // 0D00..0D0C
7585 UNKNOWN, // 0D0D
7586 MALAYALAM, // 0D0E..0D10
7587 UNKNOWN, // 0D11
7588 MALAYALAM, // 0D12..0D44
7589 UNKNOWN, // 0D45
7590 MALAYALAM, // 0D46..0D48
7591 UNKNOWN, // 0D49
7592 MALAYALAM, // 0D4A..0D4F
7593 UNKNOWN, // 0D50..0D53
7594 MALAYALAM, // 0D54..0D63
7595 UNKNOWN, // 0D64..0D65
7596 MALAYALAM, // 0D66..0D7F
7597 UNKNOWN, // 0D80
7598 SINHALA, // 0D81..0D83
7599 UNKNOWN, // 0D84
7600 SINHALA, // 0D85..0D96
7601 UNKNOWN, // 0D97..0D99
7602 SINHALA, // 0D9A..0DB1
7603 UNKNOWN, // 0DB2
7604 SINHALA, // 0DB3..0DBB
7605 UNKNOWN, // 0DBC
7606 SINHALA, // 0DBD
7607 UNKNOWN, // 0DBE..0DBF
7608 SINHALA, // 0DC0..0DC6
7609 UNKNOWN, // 0DC7..0DC9
7610 SINHALA, // 0DCA
7611 UNKNOWN, // 0DCB..0DCE
7612 SINHALA, // 0DCF..0DD4
7613 UNKNOWN, // 0DD5
7614 SINHALA, // 0DD6
7615 UNKNOWN, // 0DD7
7616 SINHALA, // 0DD8..0DDF
7617 UNKNOWN, // 0DE0..0DE5
7618 SINHALA, // 0DE6..0DEF
7619 UNKNOWN, // 0DF0..0DF1
7620 SINHALA, // 0DF2..0DF4
7621 UNKNOWN, // 0DF5..0E00
7622 THAI, // 0E01..0E3A
7623 UNKNOWN, // 0E3B..0E3E
7624 COMMON, // 0E3F
7625 THAI, // 0E40..0E5B
7626 UNKNOWN, // 0E5C..0E80
7627 LAO, // 0E81..0E82
7628 UNKNOWN, // 0E83
7629 LAO, // 0E84
7630 UNKNOWN, // 0E85
7631 LAO, // 0E86..0E8A
7632 UNKNOWN, // 0E8B
7633 LAO, // 0E8C..0EA3
7634 UNKNOWN, // 0EA4
7635 LAO, // 0EA5
7636 UNKNOWN, // 0EA6
7637 LAO, // 0EA7..0EBD
7638 UNKNOWN, // 0EBE..0EBF
7639 LAO, // 0EC0..0EC4
7640 UNKNOWN, // 0EC5
7641 LAO, // 0EC6
7642 UNKNOWN, // 0EC7
7643 LAO, // 0EC8..0ECE
7644 UNKNOWN, // 0ECF
7645 LAO, // 0ED0..0ED9
7646 UNKNOWN, // 0EDA..0EDB
7647 LAO, // 0EDC..0EDF
7648 UNKNOWN, // 0EE0..0EFF
7649 TIBETAN, // 0F00..0F47
7650 UNKNOWN, // 0F48
7651 TIBETAN, // 0F49..0F6C
7652 UNKNOWN, // 0F6D..0F70
7653 TIBETAN, // 0F71..0F97
7654 UNKNOWN, // 0F98
7655 TIBETAN, // 0F99..0FBC
7656 UNKNOWN, // 0FBD
7657 TIBETAN, // 0FBE..0FCC
7658 UNKNOWN, // 0FCD
7659 TIBETAN, // 0FCE..0FD4
7660 COMMON, // 0FD5..0FD8
7661 TIBETAN, // 0FD9..0FDA
7662 UNKNOWN, // 0FDB..0FFF
7663 MYANMAR, // 1000..109F
7664 GEORGIAN, // 10A0..10C5
7665 UNKNOWN, // 10C6
7666 GEORGIAN, // 10C7
7667 UNKNOWN, // 10C8..10CC
7668 GEORGIAN, // 10CD
7669 UNKNOWN, // 10CE..10CF
7670 GEORGIAN, // 10D0..10FA
7671 COMMON, // 10FB
7672 GEORGIAN, // 10FC..10FF
7673 HANGUL, // 1100..11FF
7674 ETHIOPIC, // 1200..1248
7675 UNKNOWN, // 1249
7676 ETHIOPIC, // 124A..124D
7677 UNKNOWN, // 124E..124F
7678 ETHIOPIC, // 1250..1256
7679 UNKNOWN, // 1257
7680 ETHIOPIC, // 1258
7681 UNKNOWN, // 1259
7682 ETHIOPIC, // 125A..125D
7683 UNKNOWN, // 125E..125F
7684 ETHIOPIC, // 1260..1288
7685 UNKNOWN, // 1289
7686 ETHIOPIC, // 128A..128D
7687 UNKNOWN, // 128E..128F
7688 ETHIOPIC, // 1290..12B0
7689 UNKNOWN, // 12B1
7690 ETHIOPIC, // 12B2..12B5
7691 UNKNOWN, // 12B6..12B7
7692 ETHIOPIC, // 12B8..12BE
7693 UNKNOWN, // 12BF
7694 ETHIOPIC, // 12C0
7695 UNKNOWN, // 12C1
7696 ETHIOPIC, // 12C2..12C5
7697 UNKNOWN, // 12C6..12C7
7698 ETHIOPIC, // 12C8..12D6
7699 UNKNOWN, // 12D7
7700 ETHIOPIC, // 12D8..1310
7701 UNKNOWN, // 1311
7702 ETHIOPIC, // 1312..1315
7703 UNKNOWN, // 1316..1317
7704 ETHIOPIC, // 1318..135A
7705 UNKNOWN, // 135B..135C
7706 ETHIOPIC, // 135D..137C
7707 UNKNOWN, // 137D..137F
7708 ETHIOPIC, // 1380..1399
7709 UNKNOWN, // 139A..139F
7710 CHEROKEE, // 13A0..13F5
7711 UNKNOWN, // 13F6..13F7
7712 CHEROKEE, // 13F8..13FD
7713 UNKNOWN, // 13FE..13FF
7714 CANADIAN_ABORIGINAL, // 1400..167F
7715 OGHAM, // 1680..169C
7716 UNKNOWN, // 169D..169F
7717 RUNIC, // 16A0..16EA
7718 COMMON, // 16EB..16ED
7719 RUNIC, // 16EE..16F8
7720 UNKNOWN, // 16F9..16FF
7721 TAGALOG, // 1700..1715
7722 UNKNOWN, // 1716..171E
7723 TAGALOG, // 171F
7724 HANUNOO, // 1720..1734
7725 COMMON, // 1735..1736
7726 UNKNOWN, // 1737..173F
7727 BUHID, // 1740..1753
7728 UNKNOWN, // 1754..175F
7729 TAGBANWA, // 1760..176C
7730 UNKNOWN, // 176D
7731 TAGBANWA, // 176E..1770
7732 UNKNOWN, // 1771
7733 TAGBANWA, // 1772..1773
7734 UNKNOWN, // 1774..177F
7735 KHMER, // 1780..17DD
7736 UNKNOWN, // 17DE..17DF
7737 KHMER, // 17E0..17E9
7738 UNKNOWN, // 17EA..17EF
7739 KHMER, // 17F0..17F9
7740 UNKNOWN, // 17FA..17FF
7741 MONGOLIAN, // 1800..1801
7742 COMMON, // 1802..1803
7743 MONGOLIAN, // 1804
7744 COMMON, // 1805
7745 MONGOLIAN, // 1806..1819
7746 UNKNOWN, // 181A..181F
7747 MONGOLIAN, // 1820..1878
7748 UNKNOWN, // 1879..187F
7749 MONGOLIAN, // 1880..18AA
7750 UNKNOWN, // 18AB..18AF
7751 CANADIAN_ABORIGINAL, // 18B0..18F5
7752 UNKNOWN, // 18F6..18FF
7753 LIMBU, // 1900..191E
7754 UNKNOWN, // 191F
7755 LIMBU, // 1920..192B
7756 UNKNOWN, // 192C..192F
7757 LIMBU, // 1930..193B
7758 UNKNOWN, // 193C..193F
7759 LIMBU, // 1940
7760 UNKNOWN, // 1941..1943
7761 LIMBU, // 1944..194F
7762 TAI_LE, // 1950..196D
7763 UNKNOWN, // 196E..196F
7764 TAI_LE, // 1970..1974
7765 UNKNOWN, // 1975..197F
7766 NEW_TAI_LUE, // 1980..19AB
7767 UNKNOWN, // 19AC..19AF
7768 NEW_TAI_LUE, // 19B0..19C9
7769 UNKNOWN, // 19CA..19CF
7770 NEW_TAI_LUE, // 19D0..19DA
7771 UNKNOWN, // 19DB..19DD
7772 NEW_TAI_LUE, // 19DE..19DF
7773 KHMER, // 19E0..19FF
7774 BUGINESE, // 1A00..1A1B
7775 UNKNOWN, // 1A1C..1A1D
7776 BUGINESE, // 1A1E..1A1F
7777 TAI_THAM, // 1A20..1A5E
7778 UNKNOWN, // 1A5F
7779 TAI_THAM, // 1A60..1A7C
7780 UNKNOWN, // 1A7D..1A7E
7781 TAI_THAM, // 1A7F..1A89
7782 UNKNOWN, // 1A8A..1A8F
7783 TAI_THAM, // 1A90..1A99
7784 UNKNOWN, // 1A9A..1A9F
7785 TAI_THAM, // 1AA0..1AAD
7786 UNKNOWN, // 1AAE..1AAF
7787 INHERITED, // 1AB0..1ACE
7788 UNKNOWN, // 1ACF..1AFF
7789 BALINESE, // 1B00..1B4C
7790 UNKNOWN, // 1B4D
7791 BALINESE, // 1B4E..1B7F
7792 SUNDANESE, // 1B80..1BBF
7793 BATAK, // 1BC0..1BF3
7794 UNKNOWN, // 1BF4..1BFB
7795 BATAK, // 1BFC..1BFF
7796 LEPCHA, // 1C00..1C37
7797 UNKNOWN, // 1C38..1C3A
7798 LEPCHA, // 1C3B..1C49
7799 UNKNOWN, // 1C4A..1C4C
7800 LEPCHA, // 1C4D..1C4F
7801 OL_CHIKI, // 1C50..1C7F
7802 CYRILLIC, // 1C80..1C8A
7803 UNKNOWN, // 1C8B..1C8F
7804 GEORGIAN, // 1C90..1CBA
7805 UNKNOWN, // 1CBB..1CBC
7806 GEORGIAN, // 1CBD..1CBF
7807 SUNDANESE, // 1CC0..1CC7
7808 UNKNOWN, // 1CC8..1CCF
7809 INHERITED, // 1CD0..1CD2
7810 COMMON, // 1CD3
7811 INHERITED, // 1CD4..1CE0
7812 COMMON, // 1CE1
7813 INHERITED, // 1CE2..1CE8
7814 COMMON, // 1CE9..1CEC
7815 INHERITED, // 1CED
7816 COMMON, // 1CEE..1CF3
7817 INHERITED, // 1CF4
7818 COMMON, // 1CF5..1CF7
7819 INHERITED, // 1CF8..1CF9
7820 COMMON, // 1CFA
7821 UNKNOWN, // 1CFB..1CFF
7822 LATIN, // 1D00..1D25
7823 GREEK, // 1D26..1D2A
7824 CYRILLIC, // 1D2B
7825 LATIN, // 1D2C..1D5C
7826 GREEK, // 1D5D..1D61
7827 LATIN, // 1D62..1D65
7828 GREEK, // 1D66..1D6A
7829 LATIN, // 1D6B..1D77
7830 CYRILLIC, // 1D78
7831 LATIN, // 1D79..1DBE
7832 GREEK, // 1DBF
7833 INHERITED, // 1DC0..1DFF
7834 LATIN, // 1E00..1EFF
7835 GREEK, // 1F00..1F15
7836 UNKNOWN, // 1F16..1F17
7837 GREEK, // 1F18..1F1D
7838 UNKNOWN, // 1F1E..1F1F
7839 GREEK, // 1F20..1F45
7840 UNKNOWN, // 1F46..1F47
7841 GREEK, // 1F48..1F4D
7842 UNKNOWN, // 1F4E..1F4F
7843 GREEK, // 1F50..1F57
7844 UNKNOWN, // 1F58
7845 GREEK, // 1F59
7846 UNKNOWN, // 1F5A
7847 GREEK, // 1F5B
7848 UNKNOWN, // 1F5C
7849 GREEK, // 1F5D
7850 UNKNOWN, // 1F5E
7851 GREEK, // 1F5F..1F7D
7852 UNKNOWN, // 1F7E..1F7F
7853 GREEK, // 1F80..1FB4
7854 UNKNOWN, // 1FB5
7855 GREEK, // 1FB6..1FC4
7856 UNKNOWN, // 1FC5
7857 GREEK, // 1FC6..1FD3
7858 UNKNOWN, // 1FD4..1FD5
7859 GREEK, // 1FD6..1FDB
7860 UNKNOWN, // 1FDC
7861 GREEK, // 1FDD..1FEF
7862 UNKNOWN, // 1FF0..1FF1
7863 GREEK, // 1FF2..1FF4
7864 UNKNOWN, // 1FF5
7865 GREEK, // 1FF6..1FFE
7866 UNKNOWN, // 1FFF
7867 COMMON, // 2000..200B
7868 INHERITED, // 200C..200D
7869 COMMON, // 200E..2064
7870 UNKNOWN, // 2065
7871 COMMON, // 2066..2070
7872 LATIN, // 2071
7873 UNKNOWN, // 2072..2073
7874 COMMON, // 2074..207E
7875 LATIN, // 207F
7876 COMMON, // 2080..208E
7877 UNKNOWN, // 208F
7878 LATIN, // 2090..209C
7879 UNKNOWN, // 209D..209F
7880 COMMON, // 20A0..20C0
7881 UNKNOWN, // 20C1..20CF
7882 INHERITED, // 20D0..20F0
7883 UNKNOWN, // 20F1..20FF
7884 COMMON, // 2100..2125
7885 GREEK, // 2126
7886 COMMON, // 2127..2129
7887 LATIN, // 212A..212B
7888 COMMON, // 212C..2131
7889 LATIN, // 2132
7890 COMMON, // 2133..214D
7891 LATIN, // 214E
7892 COMMON, // 214F..215F
7893 LATIN, // 2160..2188
7894 COMMON, // 2189..218B
7895 UNKNOWN, // 218C..218F
7896 COMMON, // 2190..2429
7897 UNKNOWN, // 242A..243F
7898 COMMON, // 2440..244A
7899 UNKNOWN, // 244B..245F
7900 COMMON, // 2460..27FF
7901 BRAILLE, // 2800..28FF
7902 COMMON, // 2900..2B73
7903 UNKNOWN, // 2B74..2B75
7904 COMMON, // 2B76..2B95
7905 UNKNOWN, // 2B96
7906 COMMON, // 2B97..2BFF
7907 GLAGOLITIC, // 2C00..2C5F
7908 LATIN, // 2C60..2C7F
7909 COPTIC, // 2C80..2CF3
7910 UNKNOWN, // 2CF4..2CF8
7911 COPTIC, // 2CF9..2CFF
7912 GEORGIAN, // 2D00..2D25
7913 UNKNOWN, // 2D26
7914 GEORGIAN, // 2D27
7915 UNKNOWN, // 2D28..2D2C
7916 GEORGIAN, // 2D2D
7917 UNKNOWN, // 2D2E..2D2F
7918 TIFINAGH, // 2D30..2D67
7919 UNKNOWN, // 2D68..2D6E
7920 TIFINAGH, // 2D6F..2D70
7921 UNKNOWN, // 2D71..2D7E
7922 TIFINAGH, // 2D7F
7923 ETHIOPIC, // 2D80..2D96
7924 UNKNOWN, // 2D97..2D9F
7925 ETHIOPIC, // 2DA0..2DA6
7926 UNKNOWN, // 2DA7
7927 ETHIOPIC, // 2DA8..2DAE
7928 UNKNOWN, // 2DAF
7929 ETHIOPIC, // 2DB0..2DB6
7930 UNKNOWN, // 2DB7
7931 ETHIOPIC, // 2DB8..2DBE
7932 UNKNOWN, // 2DBF
7933 ETHIOPIC, // 2DC0..2DC6
7934 UNKNOWN, // 2DC7
7935 ETHIOPIC, // 2DC8..2DCE
7936 UNKNOWN, // 2DCF
7937 ETHIOPIC, // 2DD0..2DD6
7938 UNKNOWN, // 2DD7
7939 ETHIOPIC, // 2DD8..2DDE
7940 UNKNOWN, // 2DDF
7941 CYRILLIC, // 2DE0..2DFF
7942 COMMON, // 2E00..2E5D
7943 UNKNOWN, // 2E5E..2E7F
7944 HAN, // 2E80..2E99
7945 UNKNOWN, // 2E9A
7946 HAN, // 2E9B..2EF3
7947 UNKNOWN, // 2EF4..2EFF
7948 HAN, // 2F00..2FD5
7949 UNKNOWN, // 2FD6..2FEF
7950 COMMON, // 2FF0..3004
7951 HAN, // 3005
7952 COMMON, // 3006
7953 HAN, // 3007
7954 COMMON, // 3008..3020
7955 HAN, // 3021..3029
7956 INHERITED, // 302A..302D
7957 HANGUL, // 302E..302F
7958 COMMON, // 3030..3037
7959 HAN, // 3038..303B
7960 COMMON, // 303C..303F
7961 UNKNOWN, // 3040
7962 HIRAGANA, // 3041..3096
7963 UNKNOWN, // 3097..3098
7964 INHERITED, // 3099..309A
7965 COMMON, // 309B..309C
7966 HIRAGANA, // 309D..309F
7967 COMMON, // 30A0
7968 KATAKANA, // 30A1..30FA
7969 COMMON, // 30FB..30FC
7970 KATAKANA, // 30FD..30FF
7971 UNKNOWN, // 3100..3104
7972 BOPOMOFO, // 3105..312F
7973 UNKNOWN, // 3130
7974 HANGUL, // 3131..318E
7975 UNKNOWN, // 318F
7976 COMMON, // 3190..319F
7977 BOPOMOFO, // 31A0..31BF
7978 COMMON, // 31C0..31E5
7979 UNKNOWN, // 31E6..31EE
7980 COMMON, // 31EF
7981 KATAKANA, // 31F0..31FF
7982 HANGUL, // 3200..321E
7983 UNKNOWN, // 321F
7984 COMMON, // 3220..325F
7985 HANGUL, // 3260..327E
7986 COMMON, // 327F..32CF
7987 KATAKANA, // 32D0..32FE
7988 COMMON, // 32FF
7989 KATAKANA, // 3300..3357
7990 COMMON, // 3358..33FF
7991 HAN, // 3400..4DBF
7992 COMMON, // 4DC0..4DFF
7993 HAN, // 4E00..9FFF
7994 YI, // A000..A48C
7995 UNKNOWN, // A48D..A48F
7996 YI, // A490..A4C6
7997 UNKNOWN, // A4C7..A4CF
7998 LISU, // A4D0..A4FF
7999 VAI, // A500..A62B
8000 UNKNOWN, // A62C..A63F
8001 CYRILLIC, // A640..A69F
8002 BAMUM, // A6A0..A6F7
8003 UNKNOWN, // A6F8..A6FF
8004 COMMON, // A700..A721
8005 LATIN, // A722..A787
8006 COMMON, // A788..A78A
8007 LATIN, // A78B..A7CD
8008 UNKNOWN, // A7CE..A7CF
8009 LATIN, // A7D0..A7D1
8010 UNKNOWN, // A7D2
8011 LATIN, // A7D3
8012 UNKNOWN, // A7D4
8013 LATIN, // A7D5..A7DC
8014 UNKNOWN, // A7DD..A7F1
8015 LATIN, // A7F2..A7FF
8016 SYLOTI_NAGRI, // A800..A82C
8017 UNKNOWN, // A82D..A82F
8018 COMMON, // A830..A839
8019 UNKNOWN, // A83A..A83F
8020 PHAGS_PA, // A840..A877
8021 UNKNOWN, // A878..A87F
8022 SAURASHTRA, // A880..A8C5
8023 UNKNOWN, // A8C6..A8CD
8024 SAURASHTRA, // A8CE..A8D9
8025 UNKNOWN, // A8DA..A8DF
8026 DEVANAGARI, // A8E0..A8FF
8027 KAYAH_LI, // A900..A92D
8028 COMMON, // A92E
8029 KAYAH_LI, // A92F
8030 REJANG, // A930..A953
8031 UNKNOWN, // A954..A95E
8032 REJANG, // A95F
8033 HANGUL, // A960..A97C
8034 UNKNOWN, // A97D..A97F
8035 JAVANESE, // A980..A9CD
8036 UNKNOWN, // A9CE
8037 COMMON, // A9CF
8038 JAVANESE, // A9D0..A9D9
8039 UNKNOWN, // A9DA..A9DD
8040 JAVANESE, // A9DE..A9DF
8041 MYANMAR, // A9E0..A9FE
8042 UNKNOWN, // A9FF
8043 CHAM, // AA00..AA36
8044 UNKNOWN, // AA37..AA3F
8045 CHAM, // AA40..AA4D
8046 UNKNOWN, // AA4E..AA4F
8047 CHAM, // AA50..AA59
8048 UNKNOWN, // AA5A..AA5B
8049 CHAM, // AA5C..AA5F
8050 MYANMAR, // AA60..AA7F
8051 TAI_VIET, // AA80..AAC2
8052 UNKNOWN, // AAC3..AADA
8053 TAI_VIET, // AADB..AADF
8054 MEETEI_MAYEK, // AAE0..AAF6
8055 UNKNOWN, // AAF7..AB00
8056 ETHIOPIC, // AB01..AB06
8057 UNKNOWN, // AB07..AB08
8058 ETHIOPIC, // AB09..AB0E
8059 UNKNOWN, // AB0F..AB10
8060 ETHIOPIC, // AB11..AB16
8061 UNKNOWN, // AB17..AB1F
8062 ETHIOPIC, // AB20..AB26
8063 UNKNOWN, // AB27
8064 ETHIOPIC, // AB28..AB2E
8065 UNKNOWN, // AB2F
8066 LATIN, // AB30..AB5A
8067 COMMON, // AB5B
8068 LATIN, // AB5C..AB64
8069 GREEK, // AB65
8070 LATIN, // AB66..AB69
8071 COMMON, // AB6A..AB6B
8072 UNKNOWN, // AB6C..AB6F
8073 CHEROKEE, // AB70..ABBF
8074 MEETEI_MAYEK, // ABC0..ABED
8075 UNKNOWN, // ABEE..ABEF
8076 MEETEI_MAYEK, // ABF0..ABF9
8077 UNKNOWN, // ABFA..ABFF
8078 HANGUL, // AC00..D7A3
8079 UNKNOWN, // D7A4..D7AF
8080 HANGUL, // D7B0..D7C6
8081 UNKNOWN, // D7C7..D7CA
8082 HANGUL, // D7CB..D7FB
8083 UNKNOWN, // D7FC..F8FF
8084 HAN, // F900..FA6D
8085 UNKNOWN, // FA6E..FA6F
8086 HAN, // FA70..FAD9
8087 UNKNOWN, // FADA..FAFF
8088 LATIN, // FB00..FB06
8089 UNKNOWN, // FB07..FB12
8090 ARMENIAN, // FB13..FB17
8091 UNKNOWN, // FB18..FB1C
8092 HEBREW, // FB1D..FB36
8093 UNKNOWN, // FB37
8094 HEBREW, // FB38..FB3C
8095 UNKNOWN, // FB3D
8096 HEBREW, // FB3E
8097 UNKNOWN, // FB3F
8098 HEBREW, // FB40..FB41
8099 UNKNOWN, // FB42
8100 HEBREW, // FB43..FB44
8101 UNKNOWN, // FB45
8102 HEBREW, // FB46..FB4F
8103 ARABIC, // FB50..FBC2
8104 UNKNOWN, // FBC3..FBD2
8105 ARABIC, // FBD3..FD3D
8106 COMMON, // FD3E..FD3F
8107 ARABIC, // FD40..FD8F
8108 UNKNOWN, // FD90..FD91
8109 ARABIC, // FD92..FDC7
8110 UNKNOWN, // FDC8..FDCE
8111 ARABIC, // FDCF
8112 UNKNOWN, // FDD0..FDEF
8113 ARABIC, // FDF0..FDFF
8114 INHERITED, // FE00..FE0F
8115 COMMON, // FE10..FE19
8116 UNKNOWN, // FE1A..FE1F
8117 INHERITED, // FE20..FE2D
8118 CYRILLIC, // FE2E..FE2F
8119 COMMON, // FE30..FE52
8120 UNKNOWN, // FE53
8121 COMMON, // FE54..FE66
8122 UNKNOWN, // FE67
8123 COMMON, // FE68..FE6B
8124 UNKNOWN, // FE6C..FE6F
8125 ARABIC, // FE70..FE74
8126 UNKNOWN, // FE75
8127 ARABIC, // FE76..FEFC
8128 UNKNOWN, // FEFD..FEFE
8129 COMMON, // FEFF
8130 UNKNOWN, // FF00
8131 COMMON, // FF01..FF20
8132 LATIN, // FF21..FF3A
8133 COMMON, // FF3B..FF40
8134 LATIN, // FF41..FF5A
8135 COMMON, // FF5B..FF65
8136 KATAKANA, // FF66..FF6F
8137 COMMON, // FF70
8138 KATAKANA, // FF71..FF9D
8139 COMMON, // FF9E..FF9F
8140 HANGUL, // FFA0..FFBE
8141 UNKNOWN, // FFBF..FFC1
8142 HANGUL, // FFC2..FFC7
8143 UNKNOWN, // FFC8..FFC9
8144 HANGUL, // FFCA..FFCF
8145 UNKNOWN, // FFD0..FFD1
8146 HANGUL, // FFD2..FFD7
8147 UNKNOWN, // FFD8..FFD9
8148 HANGUL, // FFDA..FFDC
8149 UNKNOWN, // FFDD..FFDF
8150 COMMON, // FFE0..FFE6
8151 UNKNOWN, // FFE7
8152 COMMON, // FFE8..FFEE
8153 UNKNOWN, // FFEF..FFF8
8154 COMMON, // FFF9..FFFD
8155 UNKNOWN, // FFFE..FFFF
8156 LINEAR_B, // 10000..1000B
8157 UNKNOWN, // 1000C
8158 LINEAR_B, // 1000D..10026
8159 UNKNOWN, // 10027
8160 LINEAR_B, // 10028..1003A
8161 UNKNOWN, // 1003B
8162 LINEAR_B, // 1003C..1003D
8163 UNKNOWN, // 1003E
8164 LINEAR_B, // 1003F..1004D
8165 UNKNOWN, // 1004E..1004F
8166 LINEAR_B, // 10050..1005D
8167 UNKNOWN, // 1005E..1007F
8168 LINEAR_B, // 10080..100FA
8169 UNKNOWN, // 100FB..100FF
8170 COMMON, // 10100..10102
8171 UNKNOWN, // 10103..10106
8172 COMMON, // 10107..10133
8173 UNKNOWN, // 10134..10136
8174 COMMON, // 10137..1013F
8175 GREEK, // 10140..1018E
8176 UNKNOWN, // 1018F
8177 COMMON, // 10190..1019C
8178 UNKNOWN, // 1019D..1019F
8179 GREEK, // 101A0
8180 UNKNOWN, // 101A1..101CF
8181 COMMON, // 101D0..101FC
8182 INHERITED, // 101FD
8183 UNKNOWN, // 101FE..1027F
8184 LYCIAN, // 10280..1029C
8185 UNKNOWN, // 1029D..1029F
8186 CARIAN, // 102A0..102D0
8187 UNKNOWN, // 102D1..102DF
8188 INHERITED, // 102E0
8189 COMMON, // 102E1..102FB
8190 UNKNOWN, // 102FC..102FF
8191 OLD_ITALIC, // 10300..10323
8192 UNKNOWN, // 10324..1032C
8193 OLD_ITALIC, // 1032D..1032F
8194 GOTHIC, // 10330..1034A
8195 UNKNOWN, // 1034B..1034F
8196 OLD_PERMIC, // 10350..1037A
8197 UNKNOWN, // 1037B..1037F
8198 UGARITIC, // 10380..1039D
8199 UNKNOWN, // 1039E
8200 UGARITIC, // 1039F
8201 OLD_PERSIAN, // 103A0..103C3
8202 UNKNOWN, // 103C4..103C7
8203 OLD_PERSIAN, // 103C8..103D5
8204 UNKNOWN, // 103D6..103FF
8205 DESERET, // 10400..1044F
8206 SHAVIAN, // 10450..1047F
8207 OSMANYA, // 10480..1049D
8208 UNKNOWN, // 1049E..1049F
8209 OSMANYA, // 104A0..104A9
8210 UNKNOWN, // 104AA..104AF
8211 OSAGE, // 104B0..104D3
8212 UNKNOWN, // 104D4..104D7
8213 OSAGE, // 104D8..104FB
8214 UNKNOWN, // 104FC..104FF
8215 ELBASAN, // 10500..10527
8216 UNKNOWN, // 10528..1052F
8217 CAUCASIAN_ALBANIAN, // 10530..10563
8218 UNKNOWN, // 10564..1056E
8219 CAUCASIAN_ALBANIAN, // 1056F
8220 VITHKUQI, // 10570..1057A
8221 UNKNOWN, // 1057B
8222 VITHKUQI, // 1057C..1058A
8223 UNKNOWN, // 1058B
8224 VITHKUQI, // 1058C..10592
8225 UNKNOWN, // 10593
8226 VITHKUQI, // 10594..10595
8227 UNKNOWN, // 10596
8228 VITHKUQI, // 10597..105A1
8229 UNKNOWN, // 105A2
8230 VITHKUQI, // 105A3..105B1
8231 UNKNOWN, // 105B2
8232 VITHKUQI, // 105B3..105B9
8233 UNKNOWN, // 105BA
8234 VITHKUQI, // 105BB..105BC
8235 UNKNOWN, // 105BD..105BF
8236 TODHRI, // 105C0..105F3
8237 UNKNOWN, // 105F4..105FF
8238 LINEAR_A, // 10600..10736
8239 UNKNOWN, // 10737..1073F
8240 LINEAR_A, // 10740..10755
8241 UNKNOWN, // 10756..1075F
8242 LINEAR_A, // 10760..10767
8243 UNKNOWN, // 10768..1077F
8244 LATIN, // 10780..10785
8245 UNKNOWN, // 10786
8246 LATIN, // 10787..107B0
8247 UNKNOWN, // 107B1
8248 LATIN, // 107B2..107BA
8249 UNKNOWN, // 107BB..107FF
8250 CYPRIOT, // 10800..10805
8251 UNKNOWN, // 10806..10807
8252 CYPRIOT, // 10808
8253 UNKNOWN, // 10809
8254 CYPRIOT, // 1080A..10835
8255 UNKNOWN, // 10836
8256 CYPRIOT, // 10837..10838
8257 UNKNOWN, // 10839..1083B
8258 CYPRIOT, // 1083C
8259 UNKNOWN, // 1083D..1083E
8260 CYPRIOT, // 1083F
8261 IMPERIAL_ARAMAIC, // 10840..10855
8262 UNKNOWN, // 10856
8263 IMPERIAL_ARAMAIC, // 10857..1085F
8264 PALMYRENE, // 10860..1087F
8265 NABATAEAN, // 10880..1089E
8266 UNKNOWN, // 1089F..108A6
8267 NABATAEAN, // 108A7..108AF
8268 UNKNOWN, // 108B0..108DF
8269 HATRAN, // 108E0..108F2
8270 UNKNOWN, // 108F3
8271 HATRAN, // 108F4..108F5
8272 UNKNOWN, // 108F6..108FA
8273 HATRAN, // 108FB..108FF
8274 PHOENICIAN, // 10900..1091B
8275 UNKNOWN, // 1091C..1091E
8276 PHOENICIAN, // 1091F
8277 LYDIAN, // 10920..10939
8278 UNKNOWN, // 1093A..1093E
8279 LYDIAN, // 1093F
8280 UNKNOWN, // 10940..1097F
8281 MEROITIC_HIEROGLYPHS, // 10980..1099F
8282 MEROITIC_CURSIVE, // 109A0..109B7
8283 UNKNOWN, // 109B8..109BB
8284 MEROITIC_CURSIVE, // 109BC..109CF
8285 UNKNOWN, // 109D0..109D1
8286 MEROITIC_CURSIVE, // 109D2..109FF
8287 KHAROSHTHI, // 10A00..10A03
8288 UNKNOWN, // 10A04
8289 KHAROSHTHI, // 10A05..10A06
8290 UNKNOWN, // 10A07..10A0B
8291 KHAROSHTHI, // 10A0C..10A13
8292 UNKNOWN, // 10A14
8293 KHAROSHTHI, // 10A15..10A17
8294 UNKNOWN, // 10A18
8295 KHAROSHTHI, // 10A19..10A35
8296 UNKNOWN, // 10A36..10A37
8297 KHAROSHTHI, // 10A38..10A3A
8298 UNKNOWN, // 10A3B..10A3E
8299 KHAROSHTHI, // 10A3F..10A48
8300 UNKNOWN, // 10A49..10A4F
8301 KHAROSHTHI, // 10A50..10A58
8302 UNKNOWN, // 10A59..10A5F
8303 OLD_SOUTH_ARABIAN, // 10A60..10A7F
8304 OLD_NORTH_ARABIAN, // 10A80..10A9F
8305 UNKNOWN, // 10AA0..10ABF
8306 MANICHAEAN, // 10AC0..10AE6
8307 UNKNOWN, // 10AE7..10AEA
8308 MANICHAEAN, // 10AEB..10AF6
8309 UNKNOWN, // 10AF7..10AFF
8310 AVESTAN, // 10B00..10B35
8311 UNKNOWN, // 10B36..10B38
8312 AVESTAN, // 10B39..10B3F
8313 INSCRIPTIONAL_PARTHIAN, // 10B40..10B55
8314 UNKNOWN, // 10B56..10B57
8315 INSCRIPTIONAL_PARTHIAN, // 10B58..10B5F
8316 INSCRIPTIONAL_PAHLAVI, // 10B60..10B72
8317 UNKNOWN, // 10B73..10B77
8318 INSCRIPTIONAL_PAHLAVI, // 10B78..10B7F
8319 PSALTER_PAHLAVI, // 10B80..10B91
8320 UNKNOWN, // 10B92..10B98
8321 PSALTER_PAHLAVI, // 10B99..10B9C
8322 UNKNOWN, // 10B9D..10BA8
8323 PSALTER_PAHLAVI, // 10BA9..10BAF
8324 UNKNOWN, // 10BB0..10BFF
8325 OLD_TURKIC, // 10C00..10C48
8326 UNKNOWN, // 10C49..10C7F
8327 OLD_HUNGARIAN, // 10C80..10CB2
8328 UNKNOWN, // 10CB3..10CBF
8329 OLD_HUNGARIAN, // 10CC0..10CF2
8330 UNKNOWN, // 10CF3..10CF9
8331 OLD_HUNGARIAN, // 10CFA..10CFF
8332 HANIFI_ROHINGYA, // 10D00..10D27
8333 UNKNOWN, // 10D28..10D2F
8334 HANIFI_ROHINGYA, // 10D30..10D39
8335 UNKNOWN, // 10D3A..10D3F
8336 GARAY, // 10D40..10D65
8337 UNKNOWN, // 10D66..10D68
8338 GARAY, // 10D69..10D85
8339 UNKNOWN, // 10D86..10D8D
8340 GARAY, // 10D8E..10D8F
8341 UNKNOWN, // 10D90..10E5F
8342 ARABIC, // 10E60..10E7E
8343 UNKNOWN, // 10E7F
8344 YEZIDI, // 10E80..10EA9
8345 UNKNOWN, // 10EAA
8346 YEZIDI, // 10EAB..10EAD
8347 UNKNOWN, // 10EAE..10EAF
8348 YEZIDI, // 10EB0..10EB1
8349 UNKNOWN, // 10EB2..10EC1
8350 ARABIC, // 10EC2..10EC4
8351 UNKNOWN, // 10EC5..10EFB
8352 ARABIC, // 10EFC..10EFF
8353 OLD_SOGDIAN, // 10F00..10F27
8354 UNKNOWN, // 10F28..10F2F
8355 SOGDIAN, // 10F30..10F59
8356 UNKNOWN, // 10F5A..10F6F
8357 OLD_UYGHUR, // 10F70..10F89
8358 UNKNOWN, // 10F8A..10FAF
8359 CHORASMIAN, // 10FB0..10FCB
8360 UNKNOWN, // 10FCC..10FDF
8361 ELYMAIC, // 10FE0..10FF6
8362 UNKNOWN, // 10FF7..10FFF
8363 BRAHMI, // 11000..1104D
8364 UNKNOWN, // 1104E..11051
8365 BRAHMI, // 11052..11075
8366 UNKNOWN, // 11076..1107E
8367 BRAHMI, // 1107F
8368 KAITHI, // 11080..110C2
8369 UNKNOWN, // 110C3..110CC
8370 KAITHI, // 110CD
8371 UNKNOWN, // 110CE..110CF
8372 SORA_SOMPENG, // 110D0..110E8
8373 UNKNOWN, // 110E9..110EF
8374 SORA_SOMPENG, // 110F0..110F9
8375 UNKNOWN, // 110FA..110FF
8376 CHAKMA, // 11100..11134
8377 UNKNOWN, // 11135
8378 CHAKMA, // 11136..11147
8379 UNKNOWN, // 11148..1114F
8380 MAHAJANI, // 11150..11176
8381 UNKNOWN, // 11177..1117F
8382 SHARADA, // 11180..111DF
8383 UNKNOWN, // 111E0
8384 SINHALA, // 111E1..111F4
8385 UNKNOWN, // 111F5..111FF
8386 KHOJKI, // 11200..11211
8387 UNKNOWN, // 11212
8388 KHOJKI, // 11213..11241
8389 UNKNOWN, // 11242..1127F
8390 MULTANI, // 11280..11286
8391 UNKNOWN, // 11287
8392 MULTANI, // 11288
8393 UNKNOWN, // 11289
8394 MULTANI, // 1128A..1128D
8395 UNKNOWN, // 1128E
8396 MULTANI, // 1128F..1129D
8397 UNKNOWN, // 1129E
8398 MULTANI, // 1129F..112A9
8399 UNKNOWN, // 112AA..112AF
8400 KHUDAWADI, // 112B0..112EA
8401 UNKNOWN, // 112EB..112EF
8402 KHUDAWADI, // 112F0..112F9
8403 UNKNOWN, // 112FA..112FF
8404 GRANTHA, // 11300..11303
8405 UNKNOWN, // 11304
8406 GRANTHA, // 11305..1130C
8407 UNKNOWN, // 1130D..1130E
8408 GRANTHA, // 1130F..11310
8409 UNKNOWN, // 11311..11312
8410 GRANTHA, // 11313..11328
8411 UNKNOWN, // 11329
8412 GRANTHA, // 1132A..11330
8413 UNKNOWN, // 11331
8414 GRANTHA, // 11332..11333
8415 UNKNOWN, // 11334
8416 GRANTHA, // 11335..11339
8417 UNKNOWN, // 1133A
8418 INHERITED, // 1133B
8419 GRANTHA, // 1133C..11344
8420 UNKNOWN, // 11345..11346
8421 GRANTHA, // 11347..11348
8422 UNKNOWN, // 11349..1134A
8423 GRANTHA, // 1134B..1134D
8424 UNKNOWN, // 1134E..1134F
8425 GRANTHA, // 11350
8426 UNKNOWN, // 11351..11356
8427 GRANTHA, // 11357
8428 UNKNOWN, // 11358..1135C
8429 GRANTHA, // 1135D..11363
8430 UNKNOWN, // 11364..11365
8431 GRANTHA, // 11366..1136C
8432 UNKNOWN, // 1136D..1136F
8433 GRANTHA, // 11370..11374
8434 UNKNOWN, // 11375..1137F
8435 TULU_TIGALARI, // 11380..11389
8436 UNKNOWN, // 1138A
8437 TULU_TIGALARI, // 1138B
8438 UNKNOWN, // 1138C..1138D
8439 TULU_TIGALARI, // 1138E
8440 UNKNOWN, // 1138F
8441 TULU_TIGALARI, // 11390..113B5
8442 UNKNOWN, // 113B6
8443 TULU_TIGALARI, // 113B7..113C0
8444 UNKNOWN, // 113C1
8445 TULU_TIGALARI, // 113C2
8446 UNKNOWN, // 113C3..113C4
8447 TULU_TIGALARI, // 113C5
8448 UNKNOWN, // 113C6
8449 TULU_TIGALARI, // 113C7..113CA
8450 UNKNOWN, // 113CB
8451 TULU_TIGALARI, // 113CC..113D5
8452 UNKNOWN, // 113D6
8453 TULU_TIGALARI, // 113D7..113D8
8454 UNKNOWN, // 113D9..113E0
8455 TULU_TIGALARI, // 113E1..113E2
8456 UNKNOWN, // 113E3..113FF
8457 NEWA, // 11400..1145B
8458 UNKNOWN, // 1145C
8459 NEWA, // 1145D..11461
8460 UNKNOWN, // 11462..1147F
8461 TIRHUTA, // 11480..114C7
8462 UNKNOWN, // 114C8..114CF
8463 TIRHUTA, // 114D0..114D9
8464 UNKNOWN, // 114DA..1157F
8465 SIDDHAM, // 11580..115B5
8466 UNKNOWN, // 115B6..115B7
8467 SIDDHAM, // 115B8..115DD
8468 UNKNOWN, // 115DE..115FF
8469 MODI, // 11600..11644
8470 UNKNOWN, // 11645..1164F
8471 MODI, // 11650..11659
8472 UNKNOWN, // 1165A..1165F
8473 MONGOLIAN, // 11660..1166C
8474 UNKNOWN, // 1166D..1167F
8475 TAKRI, // 11680..116B9
8476 UNKNOWN, // 116BA..116BF
8477 TAKRI, // 116C0..116C9
8478 UNKNOWN, // 116CA..116CF
8479 MYANMAR, // 116D0..116E3
8480 UNKNOWN, // 116E4..116FF
8481 AHOM, // 11700..1171A
8482 UNKNOWN, // 1171B..1171C
8483 AHOM, // 1171D..1172B
8484 UNKNOWN, // 1172C..1172F
8485 AHOM, // 11730..11746
8486 UNKNOWN, // 11747..117FF
8487 DOGRA, // 11800..1183B
8488 UNKNOWN, // 1183C..1189F
8489 WARANG_CITI, // 118A0..118F2
8490 UNKNOWN, // 118F3..118FE
8491 WARANG_CITI, // 118FF
8492 DIVES_AKURU, // 11900..11906
8493 UNKNOWN, // 11907..11908
8494 DIVES_AKURU, // 11909
8495 UNKNOWN, // 1190A..1190B
8496 DIVES_AKURU, // 1190C..11913
8497 UNKNOWN, // 11914
8498 DIVES_AKURU, // 11915..11916
8499 UNKNOWN, // 11917
8500 DIVES_AKURU, // 11918..11935
8501 UNKNOWN, // 11936
8502 DIVES_AKURU, // 11937..11938
8503 UNKNOWN, // 11939..1193A
8504 DIVES_AKURU, // 1193B..11946
8505 UNKNOWN, // 11947..1194F
8506 DIVES_AKURU, // 11950..11959
8507 UNKNOWN, // 1195A..1199F
8508 NANDINAGARI, // 119A0..119A7
8509 UNKNOWN, // 119A8..119A9
8510 NANDINAGARI, // 119AA..119D7
8511 UNKNOWN, // 119D8..119D9
8512 NANDINAGARI, // 119DA..119E4
8513 UNKNOWN, // 119E5..119FF
8514 ZANABAZAR_SQUARE, // 11A00..11A47
8515 UNKNOWN, // 11A48..11A4F
8516 SOYOMBO, // 11A50..11AA2
8517 UNKNOWN, // 11AA3..11AAF
8518 CANADIAN_ABORIGINAL, // 11AB0..11ABF
8519 PAU_CIN_HAU, // 11AC0..11AF8
8520 UNKNOWN, // 11AF9..11AFF
8521 DEVANAGARI, // 11B00..11B09
8522 UNKNOWN, // 11B0A..11BBF
8523 SUNUWAR, // 11BC0..11BE1
8524 UNKNOWN, // 11BE2..11BEF
8525 SUNUWAR, // 11BF0..11BF9
8526 UNKNOWN, // 11BFA..11BFF
8527 BHAIKSUKI, // 11C00..11C08
8528 UNKNOWN, // 11C09
8529 BHAIKSUKI, // 11C0A..11C36
8530 UNKNOWN, // 11C37
8531 BHAIKSUKI, // 11C38..11C45
8532 UNKNOWN, // 11C46..11C4F
8533 BHAIKSUKI, // 11C50..11C6C
8534 UNKNOWN, // 11C6D..11C6F
8535 MARCHEN, // 11C70..11C8F
8536 UNKNOWN, // 11C90..11C91
8537 MARCHEN, // 11C92..11CA7
8538 UNKNOWN, // 11CA8
8539 MARCHEN, // 11CA9..11CB6
8540 UNKNOWN, // 11CB7..11CFF
8541 MASARAM_GONDI, // 11D00..11D06
8542 UNKNOWN, // 11D07
8543 MASARAM_GONDI, // 11D08..11D09
8544 UNKNOWN, // 11D0A
8545 MASARAM_GONDI, // 11D0B..11D36
8546 UNKNOWN, // 11D37..11D39
8547 MASARAM_GONDI, // 11D3A
8548 UNKNOWN, // 11D3B
8549 MASARAM_GONDI, // 11D3C..11D3D
8550 UNKNOWN, // 11D3E
8551 MASARAM_GONDI, // 11D3F..11D47
8552 UNKNOWN, // 11D48..11D4F
8553 MASARAM_GONDI, // 11D50..11D59
8554 UNKNOWN, // 11D5A..11D5F
8555 GUNJALA_GONDI, // 11D60..11D65
8556 UNKNOWN, // 11D66
8557 GUNJALA_GONDI, // 11D67..11D68
8558 UNKNOWN, // 11D69
8559 GUNJALA_GONDI, // 11D6A..11D8E
8560 UNKNOWN, // 11D8F
8561 GUNJALA_GONDI, // 11D90..11D91
8562 UNKNOWN, // 11D92
8563 GUNJALA_GONDI, // 11D93..11D98
8564 UNKNOWN, // 11D99..11D9F
8565 GUNJALA_GONDI, // 11DA0..11DA9
8566 UNKNOWN, // 11DAA..11EDF
8567 MAKASAR, // 11EE0..11EF8
8568 UNKNOWN, // 11EF9..11EFF
8569 KAWI, // 11F00..11F10
8570 UNKNOWN, // 11F11
8571 KAWI, // 11F12..11F3A
8572 UNKNOWN, // 11F3B..11F3D
8573 KAWI, // 11F3E..11F5A
8574 UNKNOWN, // 11F5B..11FAF
8575 LISU, // 11FB0
8576 UNKNOWN, // 11FB1..11FBF
8577 TAMIL, // 11FC0..11FF1
8578 UNKNOWN, // 11FF2..11FFE
8579 TAMIL, // 11FFF
8580 CUNEIFORM, // 12000..12399
8581 UNKNOWN, // 1239A..123FF
8582 CUNEIFORM, // 12400..1246E
8583 UNKNOWN, // 1246F
8584 CUNEIFORM, // 12470..12474
8585 UNKNOWN, // 12475..1247F
8586 CUNEIFORM, // 12480..12543
8587 UNKNOWN, // 12544..12F8F
8588 CYPRO_MINOAN, // 12F90..12FF2
8589 UNKNOWN, // 12FF3..12FFF
8590 EGYPTIAN_HIEROGLYPHS, // 13000..13455
8591 UNKNOWN, // 13456..1345F
8592 EGYPTIAN_HIEROGLYPHS, // 13460..143FA
8593 UNKNOWN, // 143FB..143FF
8594 ANATOLIAN_HIEROGLYPHS, // 14400..14646
8595 UNKNOWN, // 14647..160FF
8596 GURUNG_KHEMA, // 16100..16139
8597 UNKNOWN, // 1613A..167FF
8598 BAMUM, // 16800..16A38
8599 UNKNOWN, // 16A39..16A3F
8600 MRO, // 16A40..16A5E
8601 UNKNOWN, // 16A5F
8602 MRO, // 16A60..16A69
8603 UNKNOWN, // 16A6A..16A6D
8604 MRO, // 16A6E..16A6F
8605 TANGSA, // 16A70..16ABE
8606 UNKNOWN, // 16ABF
8607 TANGSA, // 16AC0..16AC9
8608 UNKNOWN, // 16ACA..16ACF
8609 BASSA_VAH, // 16AD0..16AED
8610 UNKNOWN, // 16AEE..16AEF
8611 BASSA_VAH, // 16AF0..16AF5
8612 UNKNOWN, // 16AF6..16AFF
8613 PAHAWH_HMONG, // 16B00..16B45
8614 UNKNOWN, // 16B46..16B4F
8615 PAHAWH_HMONG, // 16B50..16B59
8616 UNKNOWN, // 16B5A
8617 PAHAWH_HMONG, // 16B5B..16B61
8618 UNKNOWN, // 16B62
8619 PAHAWH_HMONG, // 16B63..16B77
8620 UNKNOWN, // 16B78..16B7C
8621 PAHAWH_HMONG, // 16B7D..16B8F
8622 UNKNOWN, // 16B90..16D3F
8623 KIRAT_RAI, // 16D40..16D79
8624 UNKNOWN, // 16D7A..16E3F
8625 MEDEFAIDRIN, // 16E40..16E9A
8626 UNKNOWN, // 16E9B..16EFF
8627 MIAO, // 16F00..16F4A
8628 UNKNOWN, // 16F4B..16F4E
8629 MIAO, // 16F4F..16F87
8630 UNKNOWN, // 16F88..16F8E
8631 MIAO, // 16F8F..16F9F
8632 UNKNOWN, // 16FA0..16FDF
8633 TANGUT, // 16FE0
8634 NUSHU, // 16FE1
8635 HAN, // 16FE2..16FE3
8636 KHITAN_SMALL_SCRIPT, // 16FE4
8637 UNKNOWN, // 16FE5..16FEF
8638 HAN, // 16FF0..16FF1
8639 UNKNOWN, // 16FF2..16FFF
8640 TANGUT, // 17000..187F7
8641 UNKNOWN, // 187F8..187FF
8642 TANGUT, // 18800..18AFF
8643 KHITAN_SMALL_SCRIPT, // 18B00..18CD5
8644 UNKNOWN, // 18CD6..18CFE
8645 KHITAN_SMALL_SCRIPT, // 18CFF
8646 TANGUT, // 18D00..18D08
8647 UNKNOWN, // 18D09..1AFEF
8648 KATAKANA, // 1AFF0..1AFF3
8649 UNKNOWN, // 1AFF4
8650 KATAKANA, // 1AFF5..1AFFB
8651 UNKNOWN, // 1AFFC
8652 KATAKANA, // 1AFFD..1AFFE
8653 UNKNOWN, // 1AFFF
8654 KATAKANA, // 1B000
8655 HIRAGANA, // 1B001..1B11F
8656 KATAKANA, // 1B120..1B122
8657 UNKNOWN, // 1B123..1B131
8658 HIRAGANA, // 1B132
8659 UNKNOWN, // 1B133..1B14F
8660 HIRAGANA, // 1B150..1B152
8661 UNKNOWN, // 1B153..1B154
8662 KATAKANA, // 1B155
8663 UNKNOWN, // 1B156..1B163
8664 KATAKANA, // 1B164..1B167
8665 UNKNOWN, // 1B168..1B16F
8666 NUSHU, // 1B170..1B2FB
8667 UNKNOWN, // 1B2FC..1BBFF
8668 DUPLOYAN, // 1BC00..1BC6A
8669 UNKNOWN, // 1BC6B..1BC6F
8670 DUPLOYAN, // 1BC70..1BC7C
8671 UNKNOWN, // 1BC7D..1BC7F
8672 DUPLOYAN, // 1BC80..1BC88
8673 UNKNOWN, // 1BC89..1BC8F
8674 DUPLOYAN, // 1BC90..1BC99
8675 UNKNOWN, // 1BC9A..1BC9B
8676 DUPLOYAN, // 1BC9C..1BC9F
8677 COMMON, // 1BCA0..1BCA3
8678 UNKNOWN, // 1BCA4..1CBFF
8679 COMMON, // 1CC00..1CCF9
8680 UNKNOWN, // 1CCFA..1CCFF
8681 COMMON, // 1CD00..1CEB3
8682 UNKNOWN, // 1CEB4..1CEFF
8683 INHERITED, // 1CF00..1CF2D
8684 UNKNOWN, // 1CF2E..1CF2F
8685 INHERITED, // 1CF30..1CF46
8686 UNKNOWN, // 1CF47..1CF4F
8687 COMMON, // 1CF50..1CFC3
8688 UNKNOWN, // 1CFC4..1CFFF
8689 COMMON, // 1D000..1D0F5
8690 UNKNOWN, // 1D0F6..1D0FF
8691 COMMON, // 1D100..1D126
8692 UNKNOWN, // 1D127..1D128
8693 COMMON, // 1D129..1D166
8694 INHERITED, // 1D167..1D169
8695 COMMON, // 1D16A..1D17A
8696 INHERITED, // 1D17B..1D182
8697 COMMON, // 1D183..1D184
8698 INHERITED, // 1D185..1D18B
8699 COMMON, // 1D18C..1D1A9
8700 INHERITED, // 1D1AA..1D1AD
8701 COMMON, // 1D1AE..1D1EA
8702 UNKNOWN, // 1D1EB..1D1FF
8703 GREEK, // 1D200..1D245
8704 UNKNOWN, // 1D246..1D2BF
8705 COMMON, // 1D2C0..1D2D3
8706 UNKNOWN, // 1D2D4..1D2DF
8707 COMMON, // 1D2E0..1D2F3
8708 UNKNOWN, // 1D2F4..1D2FF
8709 COMMON, // 1D300..1D356
8710 UNKNOWN, // 1D357..1D35F
8711 COMMON, // 1D360..1D378
8712 UNKNOWN, // 1D379..1D3FF
8713 COMMON, // 1D400..1D454
8714 UNKNOWN, // 1D455
8715 COMMON, // 1D456..1D49C
8716 UNKNOWN, // 1D49D
8717 COMMON, // 1D49E..1D49F
8718 UNKNOWN, // 1D4A0..1D4A1
8719 COMMON, // 1D4A2
8720 UNKNOWN, // 1D4A3..1D4A4
8721 COMMON, // 1D4A5..1D4A6
8722 UNKNOWN, // 1D4A7..1D4A8
8723 COMMON, // 1D4A9..1D4AC
8724 UNKNOWN, // 1D4AD
8725 COMMON, // 1D4AE..1D4B9
8726 UNKNOWN, // 1D4BA
8727 COMMON, // 1D4BB
8728 UNKNOWN, // 1D4BC
8729 COMMON, // 1D4BD..1D4C3
8730 UNKNOWN, // 1D4C4
8731 COMMON, // 1D4C5..1D505
8732 UNKNOWN, // 1D506
8733 COMMON, // 1D507..1D50A
8734 UNKNOWN, // 1D50B..1D50C
8735 COMMON, // 1D50D..1D514
8736 UNKNOWN, // 1D515
8737 COMMON, // 1D516..1D51C
8738 UNKNOWN, // 1D51D
8739 COMMON, // 1D51E..1D539
8740 UNKNOWN, // 1D53A
8741 COMMON, // 1D53B..1D53E
8742 UNKNOWN, // 1D53F
8743 COMMON, // 1D540..1D544
8744 UNKNOWN, // 1D545
8745 COMMON, // 1D546
8746 UNKNOWN, // 1D547..1D549
8747 COMMON, // 1D54A..1D550
8748 UNKNOWN, // 1D551
8749 COMMON, // 1D552..1D6A5
8750 UNKNOWN, // 1D6A6..1D6A7
8751 COMMON, // 1D6A8..1D7CB
8752 UNKNOWN, // 1D7CC..1D7CD
8753 COMMON, // 1D7CE..1D7FF
8754 SIGNWRITING, // 1D800..1DA8B
8755 UNKNOWN, // 1DA8C..1DA9A
8756 SIGNWRITING, // 1DA9B..1DA9F
8757 UNKNOWN, // 1DAA0
8758 SIGNWRITING, // 1DAA1..1DAAF
8759 UNKNOWN, // 1DAB0..1DEFF
8760 LATIN, // 1DF00..1DF1E
8761 UNKNOWN, // 1DF1F..1DF24
8762 LATIN, // 1DF25..1DF2A
8763 UNKNOWN, // 1DF2B..1DFFF
8764 GLAGOLITIC, // 1E000..1E006
8765 UNKNOWN, // 1E007
8766 GLAGOLITIC, // 1E008..1E018
8767 UNKNOWN, // 1E019..1E01A
8768 GLAGOLITIC, // 1E01B..1E021
8769 UNKNOWN, // 1E022
8770 GLAGOLITIC, // 1E023..1E024
8771 UNKNOWN, // 1E025
8772 GLAGOLITIC, // 1E026..1E02A
8773 UNKNOWN, // 1E02B..1E02F
8774 CYRILLIC, // 1E030..1E06D
8775 UNKNOWN, // 1E06E..1E08E
8776 CYRILLIC, // 1E08F
8777 UNKNOWN, // 1E090..1E0FF
8778 NYIAKENG_PUACHUE_HMONG, // 1E100..1E12C
8779 UNKNOWN, // 1E12D..1E12F
8780 NYIAKENG_PUACHUE_HMONG, // 1E130..1E13D
8781 UNKNOWN, // 1E13E..1E13F
8782 NYIAKENG_PUACHUE_HMONG, // 1E140..1E149
8783 UNKNOWN, // 1E14A..1E14D
8784 NYIAKENG_PUACHUE_HMONG, // 1E14E..1E14F
8785 UNKNOWN, // 1E150..1E28F
8786 TOTO, // 1E290..1E2AE
8787 UNKNOWN, // 1E2AF..1E2BF
8788 WANCHO, // 1E2C0..1E2F9
8789 UNKNOWN, // 1E2FA..1E2FE
8790 WANCHO, // 1E2FF
8791 UNKNOWN, // 1E300..1E4CF
8792 NAG_MUNDARI, // 1E4D0..1E4F9
8793 UNKNOWN, // 1E4FA..1E5CF
8794 OL_ONAL, // 1E5D0..1E5FA
8795 UNKNOWN, // 1E5FB..1E5FE
8796 OL_ONAL, // 1E5FF
8797 UNKNOWN, // 1E600..1E7DF
8798 ETHIOPIC, // 1E7E0..1E7E6
8799 UNKNOWN, // 1E7E7
8800 ETHIOPIC, // 1E7E8..1E7EB
8801 UNKNOWN, // 1E7EC
8802 ETHIOPIC, // 1E7ED..1E7EE
8803 UNKNOWN, // 1E7EF
8804 ETHIOPIC, // 1E7F0..1E7FE
8805 UNKNOWN, // 1E7FF
8806 MENDE_KIKAKUI, // 1E800..1E8C4
8807 UNKNOWN, // 1E8C5..1E8C6
8808 MENDE_KIKAKUI, // 1E8C7..1E8D6
8809 UNKNOWN, // 1E8D7..1E8FF
8810 ADLAM, // 1E900..1E94B
8811 UNKNOWN, // 1E94C..1E94F
8812 ADLAM, // 1E950..1E959
8813 UNKNOWN, // 1E95A..1E95D
8814 ADLAM, // 1E95E..1E95F
8815 UNKNOWN, // 1E960..1EC70
8816 COMMON, // 1EC71..1ECB4
8817 UNKNOWN, // 1ECB5..1ED00
8818 COMMON, // 1ED01..1ED3D
8819 UNKNOWN, // 1ED3E..1EDFF
8820 ARABIC, // 1EE00..1EE03
8821 UNKNOWN, // 1EE04
8822 ARABIC, // 1EE05..1EE1F
8823 UNKNOWN, // 1EE20
8824 ARABIC, // 1EE21..1EE22
8825 UNKNOWN, // 1EE23
8826 ARABIC, // 1EE24
8827 UNKNOWN, // 1EE25..1EE26
8828 ARABIC, // 1EE27
8829 UNKNOWN, // 1EE28
8830 ARABIC, // 1EE29..1EE32
8831 UNKNOWN, // 1EE33
8832 ARABIC, // 1EE34..1EE37
8833 UNKNOWN, // 1EE38
8834 ARABIC, // 1EE39
8835 UNKNOWN, // 1EE3A
8836 ARABIC, // 1EE3B
8837 UNKNOWN, // 1EE3C..1EE41
8838 ARABIC, // 1EE42
8839 UNKNOWN, // 1EE43..1EE46
8840 ARABIC, // 1EE47
8841 UNKNOWN, // 1EE48
8842 ARABIC, // 1EE49
8843 UNKNOWN, // 1EE4A
8844 ARABIC, // 1EE4B
8845 UNKNOWN, // 1EE4C
8846 ARABIC, // 1EE4D..1EE4F
8847 UNKNOWN, // 1EE50
8848 ARABIC, // 1EE51..1EE52
8849 UNKNOWN, // 1EE53
8850 ARABIC, // 1EE54
8851 UNKNOWN, // 1EE55..1EE56
8852 ARABIC, // 1EE57
8853 UNKNOWN, // 1EE58
8854 ARABIC, // 1EE59
8855 UNKNOWN, // 1EE5A
8856 ARABIC, // 1EE5B
8857 UNKNOWN, // 1EE5C
8858 ARABIC, // 1EE5D
8859 UNKNOWN, // 1EE5E
8860 ARABIC, // 1EE5F
8861 UNKNOWN, // 1EE60
8862 ARABIC, // 1EE61..1EE62
8863 UNKNOWN, // 1EE63
8864 ARABIC, // 1EE64
8865 UNKNOWN, // 1EE65..1EE66
8866 ARABIC, // 1EE67..1EE6A
8867 UNKNOWN, // 1EE6B
8868 ARABIC, // 1EE6C..1EE72
8869 UNKNOWN, // 1EE73
8870 ARABIC, // 1EE74..1EE77
8871 UNKNOWN, // 1EE78
8872 ARABIC, // 1EE79..1EE7C
8873 UNKNOWN, // 1EE7D
8874 ARABIC, // 1EE7E
8875 UNKNOWN, // 1EE7F
8876 ARABIC, // 1EE80..1EE89
8877 UNKNOWN, // 1EE8A
8878 ARABIC, // 1EE8B..1EE9B
8879 UNKNOWN, // 1EE9C..1EEA0
8880 ARABIC, // 1EEA1..1EEA3
8881 UNKNOWN, // 1EEA4
8882 ARABIC, // 1EEA5..1EEA9
8883 UNKNOWN, // 1EEAA
8884 ARABIC, // 1EEAB..1EEBB
8885 UNKNOWN, // 1EEBC..1EEEF
8886 ARABIC, // 1EEF0..1EEF1
8887 UNKNOWN, // 1EEF2..1EFFF
8888 COMMON, // 1F000..1F02B
8889 UNKNOWN, // 1F02C..1F02F
8890 COMMON, // 1F030..1F093
8891 UNKNOWN, // 1F094..1F09F
8892 COMMON, // 1F0A0..1F0AE
8893 UNKNOWN, // 1F0AF..1F0B0
8894 COMMON, // 1F0B1..1F0BF
8895 UNKNOWN, // 1F0C0
8896 COMMON, // 1F0C1..1F0CF
8897 UNKNOWN, // 1F0D0
8898 COMMON, // 1F0D1..1F0F5
8899 UNKNOWN, // 1F0F6..1F0FF
8900 COMMON, // 1F100..1F1AD
8901 UNKNOWN, // 1F1AE..1F1E5
8902 COMMON, // 1F1E6..1F1FF
8903 HIRAGANA, // 1F200
8904 COMMON, // 1F201..1F202
8905 UNKNOWN, // 1F203..1F20F
8906 COMMON, // 1F210..1F23B
8907 UNKNOWN, // 1F23C..1F23F
8908 COMMON, // 1F240..1F248
8909 UNKNOWN, // 1F249..1F24F
8910 COMMON, // 1F250..1F251
8911 UNKNOWN, // 1F252..1F25F
8912 COMMON, // 1F260..1F265
8913 UNKNOWN, // 1F266..1F2FF
8914 COMMON, // 1F300..1F6D7
8915 UNKNOWN, // 1F6D8..1F6DB
8916 COMMON, // 1F6DC..1F6EC
8917 UNKNOWN, // 1F6ED..1F6EF
8918 COMMON, // 1F6F0..1F6FC
8919 UNKNOWN, // 1F6FD..1F6FF
8920 COMMON, // 1F700..1F776
8921 UNKNOWN, // 1F777..1F77A
8922 COMMON, // 1F77B..1F7D9
8923 UNKNOWN, // 1F7DA..1F7DF
8924 COMMON, // 1F7E0..1F7EB
8925 UNKNOWN, // 1F7EC..1F7EF
8926 COMMON, // 1F7F0
8927 UNKNOWN, // 1F7F1..1F7FF
8928 COMMON, // 1F800..1F80B
8929 UNKNOWN, // 1F80C..1F80F
8930 COMMON, // 1F810..1F847
8931 UNKNOWN, // 1F848..1F84F
8932 COMMON, // 1F850..1F859
8933 UNKNOWN, // 1F85A..1F85F
8934 COMMON, // 1F860..1F887
8935 UNKNOWN, // 1F888..1F88F
8936 COMMON, // 1F890..1F8AD
8937 UNKNOWN, // 1F8AE..1F8AF
8938 COMMON, // 1F8B0..1F8BB
8939 UNKNOWN, // 1F8BC..1F8BF
8940 COMMON, // 1F8C0..1F8C1
8941 UNKNOWN, // 1F8C2..1F8FF
8942 COMMON, // 1F900..1FA53
8943 UNKNOWN, // 1FA54..1FA5F
8944 COMMON, // 1FA60..1FA6D
8945 UNKNOWN, // 1FA6E..1FA6F
8946 COMMON, // 1FA70..1FA7C
8947 UNKNOWN, // 1FA7D..1FA7F
8948 COMMON, // 1FA80..1FA89
8949 UNKNOWN, // 1FA8A..1FA8E
8950 COMMON, // 1FA8F..1FAC6
8951 UNKNOWN, // 1FAC7..1FACD
8952 COMMON, // 1FACE..1FADC
8953 UNKNOWN, // 1FADD..1FADE
8954 COMMON, // 1FADF..1FAE9
8955 UNKNOWN, // 1FAEA..1FAEF
8956 COMMON, // 1FAF0..1FAF8
8957 UNKNOWN, // 1FAF9..1FAFF
8958 COMMON, // 1FB00..1FB92
8959 UNKNOWN, // 1FB93
8960 COMMON, // 1FB94..1FBF9
8961 UNKNOWN, // 1FBFA..1FFFF
8962 HAN, // 20000..2A6DF
8963 UNKNOWN, // 2A6E0..2A6FF
8964 HAN, // 2A700..2B739
8965 UNKNOWN, // 2B73A..2B73F
8966 HAN, // 2B740..2B81D
8967 UNKNOWN, // 2B81E..2B81F
8968 HAN, // 2B820..2CEA1
8969 UNKNOWN, // 2CEA2..2CEAF
8970 HAN, // 2CEB0..2EBE0
8971 UNKNOWN, // 2EBE1..2EBEF
8972 HAN, // 2EBF0..2EE5D
8973 UNKNOWN, // 2EE5E..2F7FF
8974 HAN, // 2F800..2FA1D
8975 UNKNOWN, // 2FA1E..2FFFF
8976 HAN, // 30000..3134A
8977 UNKNOWN, // 3134B..3134F
8978 HAN, // 31350..323AF
8979 UNKNOWN, // 323B0..E0000
8980 COMMON, // E0001
8981 UNKNOWN, // E0002..E001F
8982 COMMON, // E0020..E007F
8983 UNKNOWN, // E0080..E00FF
8984 INHERITED, // E0100..E01EF
8985 UNKNOWN, // E01F0..10FFFF
8986 };
8987
8988 private static final HashMap<String, Character.UnicodeScript> aliases;
8989 static {
8990 aliases = HashMap.newHashMap(UNKNOWN.ordinal() + 1);
8991 aliases.put("ADLM", ADLAM);
8992 aliases.put("AGHB", CAUCASIAN_ALBANIAN);
8993 aliases.put("AHOM", AHOM);
8994 aliases.put("ARAB", ARABIC);
8995 aliases.put("ARMI", IMPERIAL_ARAMAIC);
8996 aliases.put("ARMN", ARMENIAN);
8997 aliases.put("AVST", AVESTAN);
8998 aliases.put("BALI", BALINESE);
8999 aliases.put("BAMU", BAMUM);
9000 aliases.put("BASS", BASSA_VAH);
9001 aliases.put("BATK", BATAK);
9002 aliases.put("BENG", BENGALI);
9003 aliases.put("BHKS", BHAIKSUKI);
9004 aliases.put("BOPO", BOPOMOFO);
9005 aliases.put("BRAH", BRAHMI);
9006 aliases.put("BRAI", BRAILLE);
9007 aliases.put("BUGI", BUGINESE);
9008 aliases.put("BUHD", BUHID);
9009 aliases.put("CAKM", CHAKMA);
9010 aliases.put("CANS", CANADIAN_ABORIGINAL);
9011 aliases.put("CARI", CARIAN);
9012 aliases.put("CHAM", CHAM);
9013 aliases.put("CHER", CHEROKEE);
9014 aliases.put("CHRS", CHORASMIAN);
9015 aliases.put("COPT", COPTIC);
9016 aliases.put("CPMN", CYPRO_MINOAN);
9017 aliases.put("CPRT", CYPRIOT);
9018 aliases.put("CYRL", CYRILLIC);
9019 aliases.put("DEVA", DEVANAGARI);
9020 aliases.put("DIAK", DIVES_AKURU);
9021 aliases.put("DOGR", DOGRA);
9022 aliases.put("DSRT", DESERET);
9023 aliases.put("DUPL", DUPLOYAN);
9024 aliases.put("EGYP", EGYPTIAN_HIEROGLYPHS);
9025 aliases.put("ELBA", ELBASAN);
9026 aliases.put("ELYM", ELYMAIC);
9027 aliases.put("ETHI", ETHIOPIC);
9028 aliases.put("GARA", GARAY);
9029 aliases.put("GEOR", GEORGIAN);
9030 aliases.put("GLAG", GLAGOLITIC);
9031 aliases.put("GONG", GUNJALA_GONDI);
9032 aliases.put("GONM", MASARAM_GONDI);
9033 aliases.put("GOTH", GOTHIC);
9034 aliases.put("GRAN", GRANTHA);
9035 aliases.put("GREK", GREEK);
9036 aliases.put("GUJR", GUJARATI);
9037 aliases.put("GUKH", GURUNG_KHEMA);
9038 aliases.put("GURU", GURMUKHI);
9039 aliases.put("HANG", HANGUL);
9040 aliases.put("HANI", HAN);
9041 aliases.put("HANO", HANUNOO);
9042 aliases.put("HATR", HATRAN);
9043 aliases.put("HEBR", HEBREW);
9044 aliases.put("HIRA", HIRAGANA);
9045 aliases.put("HLUW", ANATOLIAN_HIEROGLYPHS);
9046 aliases.put("HMNG", PAHAWH_HMONG);
9047 aliases.put("HMNP", NYIAKENG_PUACHUE_HMONG);
9048 aliases.put("HUNG", OLD_HUNGARIAN);
9049 aliases.put("ITAL", OLD_ITALIC);
9050 aliases.put("JAVA", JAVANESE);
9051 aliases.put("KALI", KAYAH_LI);
9052 aliases.put("KANA", KATAKANA);
9053 aliases.put("KAWI", KAWI);
9054 aliases.put("KHAR", KHAROSHTHI);
9055 aliases.put("KHMR", KHMER);
9056 aliases.put("KHOJ", KHOJKI);
9057 aliases.put("KITS", KHITAN_SMALL_SCRIPT);
9058 aliases.put("KNDA", KANNADA);
9059 aliases.put("KRAI", KIRAT_RAI);
9060 aliases.put("KTHI", KAITHI);
9061 aliases.put("LANA", TAI_THAM);
9062 aliases.put("LAOO", LAO);
9063 aliases.put("LATN", LATIN);
9064 aliases.put("LEPC", LEPCHA);
9065 aliases.put("LIMB", LIMBU);
9066 aliases.put("LINA", LINEAR_A);
9067 aliases.put("LINB", LINEAR_B);
9068 aliases.put("LISU", LISU);
9069 aliases.put("LYCI", LYCIAN);
9070 aliases.put("LYDI", LYDIAN);
9071 aliases.put("MAHJ", MAHAJANI);
9072 aliases.put("MAKA", MAKASAR);
9073 aliases.put("MAND", MANDAIC);
9074 aliases.put("MANI", MANICHAEAN);
9075 aliases.put("MARC", MARCHEN);
9076 aliases.put("MEDF", MEDEFAIDRIN);
9077 aliases.put("MEND", MENDE_KIKAKUI);
9078 aliases.put("MERC", MEROITIC_CURSIVE);
9079 aliases.put("MERO", MEROITIC_HIEROGLYPHS);
9080 aliases.put("MLYM", MALAYALAM);
9081 aliases.put("MODI", MODI);
9082 aliases.put("MONG", MONGOLIAN);
9083 aliases.put("MROO", MRO);
9084 aliases.put("MTEI", MEETEI_MAYEK);
9085 aliases.put("MULT", MULTANI);
9086 aliases.put("MYMR", MYANMAR);
9087 aliases.put("NAGM", NAG_MUNDARI);
9088 aliases.put("NAND", NANDINAGARI);
9089 aliases.put("NARB", OLD_NORTH_ARABIAN);
9090 aliases.put("NBAT", NABATAEAN);
9091 aliases.put("NEWA", NEWA);
9092 aliases.put("NKOO", NKO);
9093 aliases.put("NSHU", NUSHU);
9094 aliases.put("OGAM", OGHAM);
9095 aliases.put("OLCK", OL_CHIKI);
9096 aliases.put("ONAO", OL_ONAL);
9097 aliases.put("ORKH", OLD_TURKIC);
9098 aliases.put("ORYA", ORIYA);
9099 aliases.put("OSGE", OSAGE);
9100 aliases.put("OSMA", OSMANYA);
9101 aliases.put("OUGR", OLD_UYGHUR);
9102 aliases.put("PALM", PALMYRENE);
9103 aliases.put("PAUC", PAU_CIN_HAU);
9104 aliases.put("PERM", OLD_PERMIC);
9105 aliases.put("PHAG", PHAGS_PA);
9106 aliases.put("PHLI", INSCRIPTIONAL_PAHLAVI);
9107 aliases.put("PHLP", PSALTER_PAHLAVI);
9108 aliases.put("PHNX", PHOENICIAN);
9109 aliases.put("PLRD", MIAO);
9110 aliases.put("PRTI", INSCRIPTIONAL_PARTHIAN);
9111 aliases.put("RJNG", REJANG);
9112 aliases.put("ROHG", HANIFI_ROHINGYA);
9113 aliases.put("RUNR", RUNIC);
9114 aliases.put("SAMR", SAMARITAN);
9115 aliases.put("SARB", OLD_SOUTH_ARABIAN);
9116 aliases.put("SAUR", SAURASHTRA);
9117 aliases.put("SGNW", SIGNWRITING);
9118 aliases.put("SHAW", SHAVIAN);
9119 aliases.put("SHRD", SHARADA);
9120 aliases.put("SIDD", SIDDHAM);
9121 aliases.put("SIND", KHUDAWADI);
9122 aliases.put("SINH", SINHALA);
9123 aliases.put("SOGD", SOGDIAN);
9124 aliases.put("SOGO", OLD_SOGDIAN);
9125 aliases.put("SORA", SORA_SOMPENG);
9126 aliases.put("SOYO", SOYOMBO);
9127 aliases.put("SUND", SUNDANESE);
9128 aliases.put("SUNU", SUNUWAR);
9129 aliases.put("SYLO", SYLOTI_NAGRI);
9130 aliases.put("SYRC", SYRIAC);
9131 aliases.put("TAGB", TAGBANWA);
9132 aliases.put("TAKR", TAKRI);
9133 aliases.put("TALE", TAI_LE);
9134 aliases.put("TALU", NEW_TAI_LUE);
9135 aliases.put("TAML", TAMIL);
9136 aliases.put("TANG", TANGUT);
9137 aliases.put("TAVT", TAI_VIET);
9138 aliases.put("TELU", TELUGU);
9139 aliases.put("TFNG", TIFINAGH);
9140 aliases.put("TGLG", TAGALOG);
9141 aliases.put("THAA", THAANA);
9142 aliases.put("THAI", THAI);
9143 aliases.put("TIBT", TIBETAN);
9144 aliases.put("TIRH", TIRHUTA);
9145 aliases.put("TNSA", TANGSA);
9146 aliases.put("TODR", TODHRI);
9147 aliases.put("TOTO", TOTO);
9148 aliases.put("TUTG", TULU_TIGALARI);
9149 aliases.put("UGAR", UGARITIC);
9150 aliases.put("VAII", VAI);
9151 aliases.put("VITH", VITHKUQI);
9152 aliases.put("WARA", WARANG_CITI);
9153 aliases.put("WCHO", WANCHO);
9154 aliases.put("XPEO", OLD_PERSIAN);
9155 aliases.put("XSUX", CUNEIFORM);
9156 aliases.put("YEZI", YEZIDI);
9157 aliases.put("YIII", YI);
9158 aliases.put("ZANB", ZANABAZAR_SQUARE);
9159 aliases.put("ZINH", INHERITED);
9160 aliases.put("ZYYY", COMMON);
9161 aliases.put("ZZZZ", UNKNOWN);
9162 }
9163
9164 /**
9165 * Returns the enum constant representing the Unicode script of which
9166 * the given character (Unicode code point) is assigned to.
9167 *
9168 * @param codePoint the character (Unicode code point) in question.
9169 * @return The {@code UnicodeScript} constant representing the
9170 * Unicode script of which this character is assigned to.
9171 *
9172 * @throws IllegalArgumentException if the specified
9173 * {@code codePoint} is an invalid Unicode code point.
9174 * @see Character#isValidCodePoint(int)
9175 *
9176 */
9177 public static UnicodeScript of(int codePoint) {
9178 if (!isValidCodePoint(codePoint))
9179 throw new IllegalArgumentException(
9180 String.format("Not a valid Unicode code point: 0x%X", codePoint));
9181 int type = getType(codePoint);
9182 // leave SURROGATE and PRIVATE_USE for table lookup
9183 if (type == UNASSIGNED)
9184 return UNKNOWN;
9185 int index = Arrays.binarySearch(scriptStarts, codePoint);
9186 if (index < 0)
9187 index = -index - 2;
9188 return scripts[index];
9189 }
9190
9191 /**
9192 * Returns the UnicodeScript constant with the given Unicode script
9193 * name or the script name alias. Script names and their aliases are
9194 * determined by The Unicode Standard. The files {@code Scripts.txt}
9195 * and {@code PropertyValueAliases.txt} define script names
9196 * and the script name aliases for a particular version of the
9197 * standard. The {@link Character} class specifies the version of
9198 * the standard that it supports.
9199 * <p>
9200 * Character case is ignored for all of the valid script names.
9201 * The en_US locale's case mapping rules are used to provide
9202 * case-insensitive string comparisons for script name validation.
9203 *
9204 * @param scriptName A {@code UnicodeScript} name.
9205 * @return The {@code UnicodeScript} constant identified
9206 * by {@code scriptName}
9207 * @throws IllegalArgumentException if {@code scriptName} is an
9208 * invalid name
9209 * @throws NullPointerException if {@code scriptName} is null
9210 */
9211 public static final UnicodeScript forName(String scriptName) {
9212 scriptName = scriptName.toUpperCase(Locale.ENGLISH);
9213 //.replace(' ', '_'));
9214 UnicodeScript sc = aliases.get(scriptName);
9215 if (sc != null)
9216 return sc;
9217 return valueOf(scriptName);
9218 }
9219 }
9220
9221 /**
9222 * The value of the {@code Character}.
9223 *
9224 * @serial
9225 */
9226 private final char value;
9227
9228 /** use serialVersionUID from JDK 1.0.2 for interoperability */
9229 @java.io.Serial
9230 private static final long serialVersionUID = 3786198910865385080L;
9231
9232 /**
9233 * Constructs a newly allocated {@code Character} object that
9234 * represents the specified {@code char} value.
9235 *
9236 * @param value the value to be represented by the
9237 * {@code Character} object.
9238 *
9239 * @deprecated
9240 * It is rarely appropriate to use this constructor. The static factory
9241 * {@link #valueOf(char)} is generally a better choice, as it is
9242 * likely to yield significantly better space and time performance.
9243 */
9244 @Deprecated(since="9", forRemoval = true)
9245 public Character(char value) {
9246 this.value = value;
9247 }
9248
9249 private static final class CharacterCache {
9250 private CharacterCache(){}
9251
9252 @Stable
9253 static final Character[] cache;
9254 static Character[] archivedCache;
9255
9256 static {
9257 int size = 127 + 1;
9258
9259 // Load and use the archived cache if it exists
9260 CDS.initializeFromArchive(CharacterCache.class);
9261 if (archivedCache == null) {
9262 Character[] c = new Character[size];
9263 for (int i = 0; i < size; i++) {
9264 c[i] = new Character((char) i);
9265 }
9266 archivedCache = c;
9267 }
9268 cache = archivedCache;
9269 assert cache.length == size;
9270 }
9271 }
9272
9273 /**
9274 * Returns a {@code Character} instance representing the specified
9275 * {@code char} value.
9276 * If a new {@code Character} instance is not required, this method
9277 * should generally be used in preference to the constructor
9278 * {@link #Character(char)}, as this method is likely to yield
9279 * significantly better space and time performance by caching
9280 * frequently requested values.
9281 *
9282 * This method will always cache values in the range {@code
9283 * '\u005Cu0000'} to {@code '\u005Cu007F'}, inclusive, and may
9284 * cache other values outside of this range.
9285 *
9286 * @param c a char value.
9287 * @return a {@code Character} instance representing {@code c}.
9288 * @since 1.5
9289 */
9290 @IntrinsicCandidate
9291 @DeserializeConstructor
9292 public static Character valueOf(char c) {
9293 if (c <= 127) { // must cache
9294 return CharacterCache.cache[(int)c];
9295 }
9296 return new Character(c);
9297 }
9298
9299 /**
9300 * Returns the value of this {@code Character} object.
9301 * @return the primitive {@code char} value represented by
9302 * this object.
9303 */
9304 @IntrinsicCandidate
9305 public char charValue() {
9306 return value;
9307 }
9308
9309 /**
9310 * Returns a hash code for this {@code Character}; equal to the result
9311 * of invoking {@code charValue()}.
9312 *
9313 * @return a hash code value for this {@code Character}
9314 */
9315 @Override
9316 public int hashCode() {
9317 return Character.hashCode(value);
9318 }
9319
9320 /**
9321 * Returns a hash code for a {@code char} value; compatible with
9322 * {@code Character.hashCode()}.
9323 *
9324 * @since 1.8
9325 *
9326 * @param value The {@code char} for which to return a hash code.
9327 * @return a hash code value for a {@code char} value.
9328 */
9329 public static int hashCode(char value) {
9330 return (int)value;
9331 }
9332
9333 /**
9334 * Compares this object against the specified object.
9335 * The result is {@code true} if and only if the argument is not
9336 * {@code null} and is a {@code Character} object that
9337 * represents the same {@code char} value as this object.
9338 *
9339 * @param obj the object to compare with.
9340 * @return {@code true} if the objects are the same;
9341 * {@code false} otherwise.
9342 */
9343 public boolean equals(Object obj) {
9344 if (obj instanceof Character c) {
9345 return value == c.charValue();
9346 }
9347 return false;
9348 }
9349
9350 /**
9351 * Returns a {@code String} object representing this
9352 * {@code Character}'s value. The result is a string of
9353 * length 1 whose sole component is the primitive
9354 * {@code char} value represented by this
9355 * {@code Character} object.
9356 *
9357 * @return a string representation of this object.
9358 */
9359 @Override
9360 public String toString() {
9361 return String.valueOf(value);
9362 }
9363
9364 /**
9365 * Returns a {@code String} object representing the
9366 * specified {@code char}. The result is a string of length
9367 * 1 consisting solely of the specified {@code char}.
9368 *
9369 * @apiNote This method cannot handle <a
9370 * href="#supplementary"> supplementary characters</a>. To support
9371 * all Unicode characters, including supplementary characters, use
9372 * the {@link #toString(int)} method.
9373 *
9374 * @param c the {@code char} to be converted
9375 * @return the string representation of the specified {@code char}
9376 * @since 1.4
9377 */
9378 public static String toString(char c) {
9379 return String.valueOf(c);
9380 }
9381
9382 /**
9383 * Returns a {@code String} object representing the
9384 * specified character (Unicode code point). The result is a string of
9385 * length 1 or 2, consisting solely of the specified {@code codePoint}.
9386 *
9387 * @param codePoint the {@code codePoint} to be converted
9388 * @return the string representation of the specified {@code codePoint}
9389 * @throws IllegalArgumentException if the specified
9390 * {@code codePoint} is not a {@linkplain #isValidCodePoint
9391 * valid Unicode code point}.
9392 * @since 11
9393 */
9394 public static String toString(int codePoint) {
9395 return String.valueOfCodePoint(codePoint);
9396 }
9397
9398 /**
9399 * Determines whether the specified code point is a valid
9400 * <a href="http://www.unicode.org/glossary/#code_point">
9401 * Unicode code point value</a>.
9402 *
9403 * @param codePoint the Unicode code point to be tested
9404 * @return {@code true} if the specified code point value is between
9405 * {@link #MIN_CODE_POINT} and
9406 * {@link #MAX_CODE_POINT} inclusive;
9407 * {@code false} otherwise.
9408 * @since 1.5
9409 */
9410 public static boolean isValidCodePoint(int codePoint) {
9411 // Optimized form of:
9412 // codePoint >= MIN_CODE_POINT && codePoint <= MAX_CODE_POINT
9413 int plane = codePoint >>> 16;
9414 return plane < ((MAX_CODE_POINT + 1) >>> 16);
9415 }
9416
9417 /**
9418 * Determines whether the specified character (Unicode code point)
9419 * is in the <a href="#BMP">Basic Multilingual Plane (BMP)</a>.
9420 * Such code points can be represented using a single {@code char}.
9421 *
9422 * @param codePoint the character (Unicode code point) to be tested
9423 * @return {@code true} if the specified code point is between
9424 * {@link #MIN_VALUE} and {@link #MAX_VALUE} inclusive;
9425 * {@code false} otherwise.
9426 * @since 1.7
9427 */
9428 public static boolean isBmpCodePoint(int codePoint) {
9429 return codePoint >>> 16 == 0;
9430 // Optimized form of:
9431 // codePoint >= MIN_VALUE && codePoint <= MAX_VALUE
9432 // We consistently use logical shift (>>>) to facilitate
9433 // additional runtime optimizations.
9434 }
9435
9436 /**
9437 * Determines whether the specified character (Unicode code point)
9438 * is in the <a href="#supplementary">supplementary character</a> range.
9439 *
9440 * @param codePoint the character (Unicode code point) to be tested
9441 * @return {@code true} if the specified code point is between
9442 * {@link #MIN_SUPPLEMENTARY_CODE_POINT} and
9443 * {@link #MAX_CODE_POINT} inclusive;
9444 * {@code false} otherwise.
9445 * @since 1.5
9446 */
9447 public static boolean isSupplementaryCodePoint(int codePoint) {
9448 return codePoint >= MIN_SUPPLEMENTARY_CODE_POINT
9449 && codePoint < MAX_CODE_POINT + 1;
9450 }
9451
9452 /**
9453 * Determines if the given {@code char} value is a
9454 * <a href="http://www.unicode.org/glossary/#high_surrogate_code_unit">
9455 * Unicode high-surrogate code unit</a>
9456 * (also known as <i>leading-surrogate code unit</i>).
9457 *
9458 * <p>Such values do not represent characters by themselves,
9459 * but are used in the representation of
9460 * <a href="#supplementary">supplementary characters</a>
9461 * in the UTF-16 encoding.
9462 *
9463 * @param ch the {@code char} value to be tested.
9464 * @return {@code true} if the {@code char} value is between
9465 * {@link #MIN_HIGH_SURROGATE} and
9466 * {@link #MAX_HIGH_SURROGATE} inclusive;
9467 * {@code false} otherwise.
9468 * @see Character#isLowSurrogate(char)
9469 * @see Character.UnicodeBlock#of(int)
9470 * @since 1.5
9471 */
9472 public static boolean isHighSurrogate(char ch) {
9473 // Help VM constant-fold; MAX_HIGH_SURROGATE + 1 == MIN_LOW_SURROGATE
9474 return ch >= MIN_HIGH_SURROGATE && ch < (MAX_HIGH_SURROGATE + 1);
9475 }
9476
9477 /**
9478 * Determines if the given {@code char} value is a
9479 * <a href="http://www.unicode.org/glossary/#low_surrogate_code_unit">
9480 * Unicode low-surrogate code unit</a>
9481 * (also known as <i>trailing-surrogate code unit</i>).
9482 *
9483 * <p>Such values do not represent characters by themselves,
9484 * but are used in the representation of
9485 * <a href="#supplementary">supplementary characters</a>
9486 * in the UTF-16 encoding.
9487 *
9488 * @param ch the {@code char} value to be tested.
9489 * @return {@code true} if the {@code char} value is between
9490 * {@link #MIN_LOW_SURROGATE} and
9491 * {@link #MAX_LOW_SURROGATE} inclusive;
9492 * {@code false} otherwise.
9493 * @see Character#isHighSurrogate(char)
9494 * @since 1.5
9495 */
9496 public static boolean isLowSurrogate(char ch) {
9497 return ch >= MIN_LOW_SURROGATE && ch < (MAX_LOW_SURROGATE + 1);
9498 }
9499
9500 /**
9501 * Determines if the given {@code char} value is a Unicode
9502 * <i>surrogate code unit</i>.
9503 *
9504 * <p>Such values do not represent characters by themselves,
9505 * but are used in the representation of
9506 * <a href="#supplementary">supplementary characters</a>
9507 * in the UTF-16 encoding.
9508 *
9509 * <p>A char value is a surrogate code unit if and only if it is either
9510 * a {@linkplain #isLowSurrogate(char) low-surrogate code unit} or
9511 * a {@linkplain #isHighSurrogate(char) high-surrogate code unit}.
9512 *
9513 * @param ch the {@code char} value to be tested.
9514 * @return {@code true} if the {@code char} value is between
9515 * {@link #MIN_SURROGATE} and
9516 * {@link #MAX_SURROGATE} inclusive;
9517 * {@code false} otherwise.
9518 * @since 1.7
9519 */
9520 public static boolean isSurrogate(char ch) {
9521 return ch >= MIN_SURROGATE && ch < (MAX_SURROGATE + 1);
9522 }
9523
9524 /**
9525 * Determines whether the specified pair of {@code char}
9526 * values is a valid
9527 * <a href="http://www.unicode.org/glossary/#surrogate_pair">
9528 * Unicode surrogate pair</a>.
9529 *
9530 * <p>This method is equivalent to the expression:
9531 * <blockquote><pre>{@code
9532 * isHighSurrogate(high) && isLowSurrogate(low)
9533 * }</pre></blockquote>
9534 *
9535 * @param high the high-surrogate code value to be tested
9536 * @param low the low-surrogate code value to be tested
9537 * @return {@code true} if the specified high and
9538 * low-surrogate code values represent a valid surrogate pair;
9539 * {@code false} otherwise.
9540 * @since 1.5
9541 */
9542 public static boolean isSurrogatePair(char high, char low) {
9543 return isHighSurrogate(high) && isLowSurrogate(low);
9544 }
9545
9546 /**
9547 * Determines the number of {@code char} values needed to
9548 * represent the specified character (Unicode code point). If the
9549 * specified character is equal to or greater than 0x10000, then
9550 * the method returns 2. Otherwise, the method returns 1.
9551 *
9552 * <p>This method doesn't validate the specified character to be a
9553 * valid Unicode code point. The caller must validate the
9554 * character value using {@link #isValidCodePoint(int) isValidCodePoint}
9555 * if necessary.
9556 *
9557 * @param codePoint the character (Unicode code point) to be tested.
9558 * @return 2 if the character is a valid supplementary character; 1 otherwise.
9559 * @see Character#isSupplementaryCodePoint(int)
9560 * @since 1.5
9561 */
9562 public static int charCount(int codePoint) {
9563 return codePoint >= MIN_SUPPLEMENTARY_CODE_POINT ? 2 : 1;
9564 }
9565
9566 /**
9567 * Converts the specified surrogate pair to its supplementary code
9568 * point value. This method does not validate the specified
9569 * surrogate pair. The caller must validate it using {@link
9570 * #isSurrogatePair(char, char) isSurrogatePair} if necessary.
9571 *
9572 * @param high the high-surrogate code unit
9573 * @param low the low-surrogate code unit
9574 * @return the supplementary code point composed from the
9575 * specified surrogate pair.
9576 * @since 1.5
9577 */
9578 public static int toCodePoint(char high, char low) {
9579 // Optimized form of:
9580 // return ((high - MIN_HIGH_SURROGATE) << 10)
9581 // + (low - MIN_LOW_SURROGATE)
9582 // + MIN_SUPPLEMENTARY_CODE_POINT;
9583 return ((high << 10) + low) + (MIN_SUPPLEMENTARY_CODE_POINT
9584 - (MIN_HIGH_SURROGATE << 10)
9585 - MIN_LOW_SURROGATE);
9586 }
9587
9588 /**
9589 * Returns the code point at the given index of the
9590 * {@code CharSequence}. If the {@code char} value at
9591 * the given index in the {@code CharSequence} is in the
9592 * high-surrogate range, the following index is less than the
9593 * length of the {@code CharSequence}, and the
9594 * {@code char} value at the following index is in the
9595 * low-surrogate range, then the supplementary code point
9596 * corresponding to this surrogate pair is returned. Otherwise,
9597 * the {@code char} value at the given index is returned.
9598 *
9599 * @param seq a sequence of {@code char} values (Unicode code
9600 * units)
9601 * @param index the index to the {@code char} values (Unicode
9602 * code units) in {@code seq} to be converted
9603 * @return the Unicode code point at the given index
9604 * @throws NullPointerException if {@code seq} is null.
9605 * @throws IndexOutOfBoundsException if the value
9606 * {@code index} is negative or not less than
9607 * {@link CharSequence#length() seq.length()}.
9608 * @since 1.5
9609 */
9610 public static int codePointAt(CharSequence seq, int index) {
9611 char c1 = seq.charAt(index);
9612 if (isHighSurrogate(c1) && ++index < seq.length()) {
9613 char c2 = seq.charAt(index);
9614 if (isLowSurrogate(c2)) {
9615 return toCodePoint(c1, c2);
9616 }
9617 }
9618 return c1;
9619 }
9620
9621 /**
9622 * Returns the code point at the given index of the
9623 * {@code char} array. If the {@code char} value at
9624 * the given index in the {@code char} array is in the
9625 * high-surrogate range, the following index is less than the
9626 * length of the {@code char} array, and the
9627 * {@code char} value at the following index is in the
9628 * low-surrogate range, then the supplementary code point
9629 * corresponding to this surrogate pair is returned. Otherwise,
9630 * the {@code char} value at the given index is returned.
9631 *
9632 * @param a the {@code char} array
9633 * @param index the index to the {@code char} values (Unicode
9634 * code units) in the {@code char} array to be converted
9635 * @return the Unicode code point at the given index
9636 * @throws NullPointerException if {@code a} is null.
9637 * @throws IndexOutOfBoundsException if the value
9638 * {@code index} is negative or not less than
9639 * the length of the {@code char} array.
9640 * @since 1.5
9641 */
9642 public static int codePointAt(char[] a, int index) {
9643 return codePointAtImpl(a, index, a.length);
9644 }
9645
9646 /**
9647 * Returns the code point at the given index of the
9648 * {@code char} array, where only array elements with
9649 * {@code index} less than {@code limit} can be used. If
9650 * the {@code char} value at the given index in the
9651 * {@code char} array is in the high-surrogate range, the
9652 * following index is less than the {@code limit}, and the
9653 * {@code char} value at the following index is in the
9654 * low-surrogate range, then the supplementary code point
9655 * corresponding to this surrogate pair is returned. Otherwise,
9656 * the {@code char} value at the given index is returned.
9657 *
9658 * @param a the {@code char} array
9659 * @param index the index to the {@code char} values (Unicode
9660 * code units) in the {@code char} array to be converted
9661 * @param limit the index after the last array element that
9662 * can be used in the {@code char} array
9663 * @return the Unicode code point at the given index
9664 * @throws NullPointerException if {@code a} is null.
9665 * @throws IndexOutOfBoundsException if the {@code index}
9666 * argument is negative or not less than the {@code limit}
9667 * argument, or if the {@code limit} argument is negative or
9668 * greater than the length of the {@code char} array.
9669 * @since 1.5
9670 */
9671 public static int codePointAt(char[] a, int index, int limit) {
9672 if (index >= limit || index < 0 || limit > a.length) {
9673 throw new IndexOutOfBoundsException();
9674 }
9675 return codePointAtImpl(a, index, limit);
9676 }
9677
9678 // throws ArrayIndexOutOfBoundsException if index out of bounds
9679 static int codePointAtImpl(char[] a, int index, int limit) {
9680 char c1 = a[index];
9681 if (isHighSurrogate(c1) && ++index < limit) {
9682 char c2 = a[index];
9683 if (isLowSurrogate(c2)) {
9684 return toCodePoint(c1, c2);
9685 }
9686 }
9687 return c1;
9688 }
9689
9690 /**
9691 * Returns the code point preceding the given index of the
9692 * {@code CharSequence}. If the {@code char} value at
9693 * {@code (index - 1)} in the {@code CharSequence} is in
9694 * the low-surrogate range, {@code (index - 2)} is not
9695 * negative, and the {@code char} value at {@code (index - 2)}
9696 * in the {@code CharSequence} is in the
9697 * high-surrogate range, then the supplementary code point
9698 * corresponding to this surrogate pair is returned. Otherwise,
9699 * the {@code char} value at {@code (index - 1)} is
9700 * returned.
9701 *
9702 * @param seq the {@code CharSequence} instance
9703 * @param index the index following the code point that should be returned
9704 * @return the Unicode code point value before the given index.
9705 * @throws NullPointerException if {@code seq} is null.
9706 * @throws IndexOutOfBoundsException if the {@code index}
9707 * argument is less than 1 or greater than {@link
9708 * CharSequence#length() seq.length()}.
9709 * @since 1.5
9710 */
9711 public static int codePointBefore(CharSequence seq, int index) {
9712 char c2 = seq.charAt(--index);
9713 if (isLowSurrogate(c2) && index > 0) {
9714 char c1 = seq.charAt(--index);
9715 if (isHighSurrogate(c1)) {
9716 return toCodePoint(c1, c2);
9717 }
9718 }
9719 return c2;
9720 }
9721
9722 /**
9723 * Returns the code point preceding the given index of the
9724 * {@code char} array. If the {@code char} value at
9725 * {@code (index - 1)} in the {@code char} array is in
9726 * the low-surrogate range, {@code (index - 2)} is not
9727 * negative, and the {@code char} value at {@code (index - 2)}
9728 * in the {@code char} array is in the
9729 * high-surrogate range, then the supplementary code point
9730 * corresponding to this surrogate pair is returned. Otherwise,
9731 * the {@code char} value at {@code (index - 1)} is
9732 * returned.
9733 *
9734 * @param a the {@code char} array
9735 * @param index the index following the code point that should be returned
9736 * @return the Unicode code point value before the given index.
9737 * @throws NullPointerException if {@code a} is null.
9738 * @throws IndexOutOfBoundsException if the {@code index}
9739 * argument is less than 1 or greater than the length of the
9740 * {@code char} array
9741 * @since 1.5
9742 */
9743 public static int codePointBefore(char[] a, int index) {
9744 return codePointBeforeImpl(a, index, 0);
9745 }
9746
9747 /**
9748 * Returns the code point preceding the given index of the
9749 * {@code char} array, where only array elements with
9750 * {@code index} greater than or equal to {@code start}
9751 * can be used. If the {@code char} value at {@code (index - 1)}
9752 * in the {@code char} array is in the
9753 * low-surrogate range, {@code (index - 2)} is not less than
9754 * {@code start}, and the {@code char} value at
9755 * {@code (index - 2)} in the {@code char} array is in
9756 * the high-surrogate range, then the supplementary code point
9757 * corresponding to this surrogate pair is returned. Otherwise,
9758 * the {@code char} value at {@code (index - 1)} is
9759 * returned.
9760 *
9761 * @param a the {@code char} array
9762 * @param index the index following the code point that should be returned
9763 * @param start the index of the first array element in the
9764 * {@code char} array
9765 * @return the Unicode code point value before the given index.
9766 * @throws NullPointerException if {@code a} is null.
9767 * @throws IndexOutOfBoundsException if the {@code index}
9768 * argument is not greater than the {@code start} argument or
9769 * is greater than the length of the {@code char} array, or
9770 * if the {@code start} argument is negative or not less than
9771 * the length of the {@code char} array.
9772 * @since 1.5
9773 */
9774 public static int codePointBefore(char[] a, int index, int start) {
9775 if (index <= start || start < 0 || index > a.length) {
9776 throw new IndexOutOfBoundsException();
9777 }
9778 return codePointBeforeImpl(a, index, start);
9779 }
9780
9781 // throws ArrayIndexOutOfBoundsException if index-1 out of bounds
9782 static int codePointBeforeImpl(char[] a, int index, int start) {
9783 char c2 = a[--index];
9784 if (isLowSurrogate(c2) && index > start) {
9785 char c1 = a[--index];
9786 if (isHighSurrogate(c1)) {
9787 return toCodePoint(c1, c2);
9788 }
9789 }
9790 return c2;
9791 }
9792
9793 /**
9794 * Returns the leading surrogate (a
9795 * <a href="http://www.unicode.org/glossary/#high_surrogate_code_unit">
9796 * high surrogate code unit</a>) of the
9797 * <a href="http://www.unicode.org/glossary/#surrogate_pair">
9798 * surrogate pair</a>
9799 * representing the specified supplementary character (Unicode
9800 * code point) in the UTF-16 encoding. If the specified character
9801 * is not a
9802 * <a href="Character.html#supplementary">supplementary character</a>,
9803 * an unspecified {@code char} is returned.
9804 *
9805 * <p>If
9806 * {@link #isSupplementaryCodePoint isSupplementaryCodePoint(x)}
9807 * is {@code true}, then
9808 * {@link #isHighSurrogate isHighSurrogate}{@code (highSurrogate(x))} and
9809 * {@link #toCodePoint toCodePoint}{@code (highSurrogate(x), }{@link #lowSurrogate lowSurrogate}{@code (x)) == x}
9810 * are also always {@code true}.
9811 *
9812 * @param codePoint a supplementary character (Unicode code point)
9813 * @return the leading surrogate code unit used to represent the
9814 * character in the UTF-16 encoding
9815 * @since 1.7
9816 */
9817 public static char highSurrogate(int codePoint) {
9818 return (char) ((codePoint >>> 10)
9819 + (MIN_HIGH_SURROGATE - (MIN_SUPPLEMENTARY_CODE_POINT >>> 10)));
9820 }
9821
9822 /**
9823 * Returns the trailing surrogate (a
9824 * <a href="http://www.unicode.org/glossary/#low_surrogate_code_unit">
9825 * low surrogate code unit</a>) of the
9826 * <a href="http://www.unicode.org/glossary/#surrogate_pair">
9827 * surrogate pair</a>
9828 * representing the specified supplementary character (Unicode
9829 * code point) in the UTF-16 encoding. If the specified character
9830 * is not a
9831 * <a href="Character.html#supplementary">supplementary character</a>,
9832 * an unspecified {@code char} is returned.
9833 *
9834 * <p>If
9835 * {@link #isSupplementaryCodePoint isSupplementaryCodePoint(x)}
9836 * is {@code true}, then
9837 * {@link #isLowSurrogate isLowSurrogate}{@code (lowSurrogate(x))} and
9838 * {@link #toCodePoint toCodePoint}{@code (}{@link #highSurrogate highSurrogate}{@code (x), lowSurrogate(x)) == x}
9839 * are also always {@code true}.
9840 *
9841 * @param codePoint a supplementary character (Unicode code point)
9842 * @return the trailing surrogate code unit used to represent the
9843 * character in the UTF-16 encoding
9844 * @since 1.7
9845 */
9846 public static char lowSurrogate(int codePoint) {
9847 return (char) ((codePoint & 0x3ff) + MIN_LOW_SURROGATE);
9848 }
9849
9850 /**
9851 * Converts the specified character (Unicode code point) to its
9852 * UTF-16 representation. If the specified code point is a BMP
9853 * (Basic Multilingual Plane or Plane 0) value, the same value is
9854 * stored in {@code dst[dstIndex]}, and 1 is returned. If the
9855 * specified code point is a supplementary character, its
9856 * surrogate values are stored in {@code dst[dstIndex]}
9857 * (high-surrogate) and {@code dst[dstIndex+1]}
9858 * (low-surrogate), and 2 is returned.
9859 *
9860 * @param codePoint the character (Unicode code point) to be converted.
9861 * @param dst an array of {@code char} in which the
9862 * {@code codePoint}'s UTF-16 value is stored.
9863 * @param dstIndex the start index into the {@code dst}
9864 * array where the converted value is stored.
9865 * @return 1 if the code point is a BMP code point, 2 if the
9866 * code point is a supplementary code point.
9867 * @throws IllegalArgumentException if the specified
9868 * {@code codePoint} is not a valid Unicode code point.
9869 * @throws NullPointerException if the specified {@code dst} is null.
9870 * @throws IndexOutOfBoundsException if {@code dstIndex}
9871 * is negative or not less than {@code dst.length}, or if
9872 * {@code dst} at {@code dstIndex} doesn't have enough
9873 * array element(s) to store the resulting {@code char}
9874 * value(s). (If {@code dstIndex} is equal to
9875 * {@code dst.length-1} and the specified
9876 * {@code codePoint} is a supplementary character, the
9877 * high-surrogate value is not stored in
9878 * {@code dst[dstIndex]}.)
9879 * @since 1.5
9880 */
9881 public static int toChars(int codePoint, char[] dst, int dstIndex) {
9882 if (isBmpCodePoint(codePoint)) {
9883 dst[dstIndex] = (char) codePoint;
9884 return 1;
9885 } else if (isValidCodePoint(codePoint)) {
9886 toSurrogates(codePoint, dst, dstIndex);
9887 return 2;
9888 } else {
9889 throw new IllegalArgumentException(
9890 String.format("Not a valid Unicode code point: 0x%X", codePoint));
9891 }
9892 }
9893
9894 /**
9895 * Converts the specified character (Unicode code point) to its
9896 * UTF-16 representation stored in a {@code char} array. If
9897 * the specified code point is a BMP (Basic Multilingual Plane or
9898 * Plane 0) value, the resulting {@code char} array has
9899 * the same value as {@code codePoint}. If the specified code
9900 * point is a supplementary code point, the resulting
9901 * {@code char} array has the corresponding surrogate pair.
9902 *
9903 * @param codePoint a Unicode code point
9904 * @return a {@code char} array having
9905 * {@code codePoint}'s UTF-16 representation.
9906 * @throws IllegalArgumentException if the specified
9907 * {@code codePoint} is not a valid Unicode code point.
9908 * @since 1.5
9909 */
9910 public static char[] toChars(int codePoint) {
9911 if (isBmpCodePoint(codePoint)) {
9912 return new char[] { (char) codePoint };
9913 } else if (isValidCodePoint(codePoint)) {
9914 char[] result = new char[2];
9915 toSurrogates(codePoint, result, 0);
9916 return result;
9917 } else {
9918 throw new IllegalArgumentException(
9919 String.format("Not a valid Unicode code point: 0x%X", codePoint));
9920 }
9921 }
9922
9923 static void toSurrogates(int codePoint, char[] dst, int index) {
9924 // We write elements "backwards" to guarantee all-or-nothing
9925 dst[index+1] = lowSurrogate(codePoint);
9926 dst[index] = highSurrogate(codePoint);
9927 }
9928
9929 /**
9930 * Returns the number of Unicode code points in the text range of
9931 * the specified char sequence. The text range begins at the
9932 * specified {@code beginIndex} and extends to the
9933 * {@code char} at index {@code endIndex - 1}. Thus the
9934 * length (in {@code char}s) of the text range is
9935 * {@code endIndex-beginIndex}. Unpaired surrogates within
9936 * the text range count as one code point each.
9937 *
9938 * @param seq the char sequence
9939 * @param beginIndex the index to the first {@code char} of
9940 * the text range.
9941 * @param endIndex the index after the last {@code char} of
9942 * the text range.
9943 * @return the number of Unicode code points in the specified text
9944 * range
9945 * @throws NullPointerException if {@code seq} is null.
9946 * @throws IndexOutOfBoundsException if the
9947 * {@code beginIndex} is negative, or {@code endIndex}
9948 * is larger than the length of the given sequence, or
9949 * {@code beginIndex} is larger than {@code endIndex}.
9950 * @since 1.5
9951 */
9952 public static int codePointCount(CharSequence seq, int beginIndex, int endIndex) {
9953 Objects.checkFromToIndex(beginIndex, endIndex, seq.length());
9954 int n = endIndex - beginIndex;
9955 for (int i = beginIndex; i < endIndex; ) {
9956 if (isHighSurrogate(seq.charAt(i++)) && i < endIndex &&
9957 isLowSurrogate(seq.charAt(i))) {
9958 n--;
9959 i++;
9960 }
9961 }
9962 return n;
9963 }
9964
9965 /**
9966 * Returns the number of Unicode code points in a subarray of the
9967 * {@code char} array argument. The {@code offset}
9968 * argument is the index of the first {@code char} of the
9969 * subarray and the {@code count} argument specifies the
9970 * length of the subarray in {@code char}s. Unpaired
9971 * surrogates within the subarray count as one code point each.
9972 *
9973 * @param a the {@code char} array
9974 * @param offset the index of the first {@code char} in the
9975 * given {@code char} array
9976 * @param count the length of the subarray in {@code char}s
9977 * @return the number of Unicode code points in the specified subarray
9978 * @throws NullPointerException if {@code a} is null.
9979 * @throws IndexOutOfBoundsException if {@code offset} or
9980 * {@code count} is negative, or if {@code offset +
9981 * count} is larger than the length of the given array.
9982 * @since 1.5
9983 */
9984 public static int codePointCount(char[] a, int offset, int count) {
9985 Objects.checkFromIndexSize(offset, count, a.length);
9986 return codePointCountImpl(a, offset, count);
9987 }
9988
9989 static int codePointCountImpl(char[] a, int offset, int count) {
9990 int endIndex = offset + count;
9991 int n = count;
9992 for (int i = offset; i < endIndex; ) {
9993 if (isHighSurrogate(a[i++]) && i < endIndex &&
9994 isLowSurrogate(a[i])) {
9995 n--;
9996 i++;
9997 }
9998 }
9999 return n;
10000 }
10001
10002 /**
10003 * Returns the index within the given char sequence that is offset
10004 * from the given {@code index} by {@code codePointOffset}
10005 * code points. Unpaired surrogates within the text range given by
10006 * {@code index} and {@code codePointOffset} count as
10007 * one code point each.
10008 *
10009 * @param seq the char sequence
10010 * @param index the index to be offset
10011 * @param codePointOffset the offset in code points
10012 * @return the index within the char sequence
10013 * @throws NullPointerException if {@code seq} is null.
10014 * @throws IndexOutOfBoundsException if {@code index}
10015 * is negative or larger than the length of the char sequence,
10016 * or if {@code codePointOffset} is positive and the
10017 * subsequence starting with {@code index} has fewer than
10018 * {@code codePointOffset} code points, or if
10019 * {@code codePointOffset} is negative and the subsequence
10020 * before {@code index} has fewer than the absolute value
10021 * of {@code codePointOffset} code points.
10022 * @since 1.5
10023 */
10024 public static int offsetByCodePoints(CharSequence seq, int index,
10025 int codePointOffset) {
10026 int length = seq.length();
10027 if (index < 0 || index > length) {
10028 throw new IndexOutOfBoundsException();
10029 }
10030
10031 int x = index;
10032 if (codePointOffset >= 0) {
10033 int i;
10034 for (i = 0; x < length && i < codePointOffset; i++) {
10035 if (isHighSurrogate(seq.charAt(x++)) && x < length &&
10036 isLowSurrogate(seq.charAt(x))) {
10037 x++;
10038 }
10039 }
10040 if (i < codePointOffset) {
10041 throw new IndexOutOfBoundsException();
10042 }
10043 } else {
10044 int i;
10045 for (i = codePointOffset; x > 0 && i < 0; i++) {
10046 if (isLowSurrogate(seq.charAt(--x)) && x > 0 &&
10047 isHighSurrogate(seq.charAt(x-1))) {
10048 x--;
10049 }
10050 }
10051 if (i < 0) {
10052 throw new IndexOutOfBoundsException();
10053 }
10054 }
10055 return x;
10056 }
10057
10058 /**
10059 * Returns the index within the given {@code char} subarray
10060 * that is offset from the given {@code index} by
10061 * {@code codePointOffset} code points. The
10062 * {@code start} and {@code count} arguments specify a
10063 * subarray of the {@code char} array. Unpaired surrogates
10064 * within the text range given by {@code index} and
10065 * {@code codePointOffset} count as one code point each.
10066 *
10067 * @param a the {@code char} array
10068 * @param start the index of the first {@code char} of the
10069 * subarray
10070 * @param count the length of the subarray in {@code char}s
10071 * @param index the index to be offset
10072 * @param codePointOffset the offset in code points
10073 * @return the index within the subarray
10074 * @throws NullPointerException if {@code a} is null.
10075 * @throws IndexOutOfBoundsException
10076 * if {@code start} or {@code count} is negative,
10077 * or if {@code start + count} is larger than the length of
10078 * the given array,
10079 * or if {@code index} is less than {@code start} or
10080 * larger then {@code start + count},
10081 * or if {@code codePointOffset} is positive and the text range
10082 * starting with {@code index} and ending with {@code start + count - 1}
10083 * has fewer than {@code codePointOffset} code
10084 * points,
10085 * or if {@code codePointOffset} is negative and the text range
10086 * starting with {@code start} and ending with {@code index - 1}
10087 * has fewer than the absolute value of
10088 * {@code codePointOffset} code points.
10089 * @since 1.5
10090 */
10091 public static int offsetByCodePoints(char[] a, int start, int count,
10092 int index, int codePointOffset) {
10093 if (count > a.length-start || start < 0 || count < 0
10094 || index < start || index > start+count) {
10095 throw new IndexOutOfBoundsException();
10096 }
10097 return offsetByCodePointsImpl(a, start, count, index, codePointOffset);
10098 }
10099
10100 static int offsetByCodePointsImpl(char[]a, int start, int count,
10101 int index, int codePointOffset) {
10102 int x = index;
10103 if (codePointOffset >= 0) {
10104 int limit = start + count;
10105 int i;
10106 for (i = 0; x < limit && i < codePointOffset; i++) {
10107 if (isHighSurrogate(a[x++]) && x < limit &&
10108 isLowSurrogate(a[x])) {
10109 x++;
10110 }
10111 }
10112 if (i < codePointOffset) {
10113 throw new IndexOutOfBoundsException();
10114 }
10115 } else {
10116 int i;
10117 for (i = codePointOffset; x > start && i < 0; i++) {
10118 if (isLowSurrogate(a[--x]) && x > start &&
10119 isHighSurrogate(a[x-1])) {
10120 x--;
10121 }
10122 }
10123 if (i < 0) {
10124 throw new IndexOutOfBoundsException();
10125 }
10126 }
10127 return x;
10128 }
10129
10130 /**
10131 * Determines if the specified character is a lowercase character.
10132 * <p>
10133 * A character is lowercase if its general category type, provided
10134 * by {@code Character.getType(ch)}, is
10135 * {@code LOWERCASE_LETTER}, or it has contributory property
10136 * Other_Lowercase as defined by the Unicode Standard.
10137 * <p>
10138 * The following are examples of lowercase characters:
10139 * <blockquote><pre>
10140 * 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
10141 * '\u00DF' '\u00E0' '\u00E1' '\u00E2' '\u00E3' '\u00E4' '\u00E5' '\u00E6'
10142 * '\u00E7' '\u00E8' '\u00E9' '\u00EA' '\u00EB' '\u00EC' '\u00ED' '\u00EE'
10143 * '\u00EF' '\u00F0' '\u00F1' '\u00F2' '\u00F3' '\u00F4' '\u00F5' '\u00F6'
10144 * '\u00F8' '\u00F9' '\u00FA' '\u00FB' '\u00FC' '\u00FD' '\u00FE' '\u00FF'
10145 * </pre></blockquote>
10146 * <p> Many other Unicode characters are lowercase too.
10147 *
10148 * <p><b>Note:</b> This method cannot handle <a
10149 * href="#supplementary"> supplementary characters</a>. To support
10150 * all Unicode characters, including supplementary characters, use
10151 * the {@link #isLowerCase(int)} method.
10152 *
10153 * @param ch the character to be tested.
10154 * @return {@code true} if the character is lowercase;
10155 * {@code false} otherwise.
10156 * @see Character#isLowerCase(char)
10157 * @see Character#isTitleCase(char)
10158 * @see Character#toLowerCase(char)
10159 * @see Character#getType(char)
10160 */
10161 public static boolean isLowerCase(char ch) {
10162 return isLowerCase((int)ch);
10163 }
10164
10165 /**
10166 * Determines if the specified character (Unicode code point) is a
10167 * lowercase character.
10168 * <p>
10169 * A character is lowercase if its general category type, provided
10170 * by {@link Character#getType getType(codePoint)}, is
10171 * {@code LOWERCASE_LETTER}, or it has contributory property
10172 * Other_Lowercase as defined by the Unicode Standard.
10173 * <p>
10174 * The following are examples of lowercase characters:
10175 * <blockquote><pre>
10176 * 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
10177 * '\u00DF' '\u00E0' '\u00E1' '\u00E2' '\u00E3' '\u00E4' '\u00E5' '\u00E6'
10178 * '\u00E7' '\u00E8' '\u00E9' '\u00EA' '\u00EB' '\u00EC' '\u00ED' '\u00EE'
10179 * '\u00EF' '\u00F0' '\u00F1' '\u00F2' '\u00F3' '\u00F4' '\u00F5' '\u00F6'
10180 * '\u00F8' '\u00F9' '\u00FA' '\u00FB' '\u00FC' '\u00FD' '\u00FE' '\u00FF'
10181 * </pre></blockquote>
10182 * <p> Many other Unicode characters are lowercase too.
10183 *
10184 * @param codePoint the character (Unicode code point) to be tested.
10185 * @return {@code true} if the character is lowercase;
10186 * {@code false} otherwise.
10187 * @see Character#isLowerCase(int)
10188 * @see Character#isTitleCase(int)
10189 * @see Character#toLowerCase(int)
10190 * @see Character#getType(int)
10191 * @since 1.5
10192 */
10193 public static boolean isLowerCase(int codePoint) {
10194 return CharacterData.of(codePoint).isLowerCase(codePoint);
10195 }
10196
10197 /**
10198 * Determines if the specified character is an uppercase character.
10199 * <p>
10200 * A character is uppercase if its general category type, provided by
10201 * {@code Character.getType(ch)}, is {@code UPPERCASE_LETTER}.
10202 * or it has contributory property Other_Uppercase as defined by the Unicode Standard.
10203 * <p>
10204 * The following are examples of uppercase characters:
10205 * <blockquote><pre>
10206 * 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
10207 * '\u00C0' '\u00C1' '\u00C2' '\u00C3' '\u00C4' '\u00C5' '\u00C6' '\u00C7'
10208 * '\u00C8' '\u00C9' '\u00CA' '\u00CB' '\u00CC' '\u00CD' '\u00CE' '\u00CF'
10209 * '\u00D0' '\u00D1' '\u00D2' '\u00D3' '\u00D4' '\u00D5' '\u00D6' '\u00D8'
10210 * '\u00D9' '\u00DA' '\u00DB' '\u00DC' '\u00DD' '\u00DE'
10211 * </pre></blockquote>
10212 * <p> Many other Unicode characters are uppercase too.
10213 *
10214 * <p><b>Note:</b> This method cannot handle <a
10215 * href="#supplementary"> supplementary characters</a>. To support
10216 * all Unicode characters, including supplementary characters, use
10217 * the {@link #isUpperCase(int)} method.
10218 *
10219 * @param ch the character to be tested.
10220 * @return {@code true} if the character is uppercase;
10221 * {@code false} otherwise.
10222 * @see Character#isLowerCase(char)
10223 * @see Character#isTitleCase(char)
10224 * @see Character#toUpperCase(char)
10225 * @see Character#getType(char)
10226 * @since 1.0
10227 */
10228 public static boolean isUpperCase(char ch) {
10229 return isUpperCase((int)ch);
10230 }
10231
10232 /**
10233 * Determines if the specified character (Unicode code point) is an uppercase character.
10234 * <p>
10235 * A character is uppercase if its general category type, provided by
10236 * {@link Character#getType(int) getType(codePoint)}, is {@code UPPERCASE_LETTER},
10237 * or it has contributory property Other_Uppercase as defined by the Unicode Standard.
10238 * <p>
10239 * The following are examples of uppercase characters:
10240 * <blockquote><pre>
10241 * 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
10242 * '\u00C0' '\u00C1' '\u00C2' '\u00C3' '\u00C4' '\u00C5' '\u00C6' '\u00C7'
10243 * '\u00C8' '\u00C9' '\u00CA' '\u00CB' '\u00CC' '\u00CD' '\u00CE' '\u00CF'
10244 * '\u00D0' '\u00D1' '\u00D2' '\u00D3' '\u00D4' '\u00D5' '\u00D6' '\u00D8'
10245 * '\u00D9' '\u00DA' '\u00DB' '\u00DC' '\u00DD' '\u00DE'
10246 * </pre></blockquote>
10247 * <p> Many other Unicode characters are uppercase too.
10248 *
10249 * @param codePoint the character (Unicode code point) to be tested.
10250 * @return {@code true} if the character is uppercase;
10251 * {@code false} otherwise.
10252 * @see Character#isLowerCase(int)
10253 * @see Character#isTitleCase(int)
10254 * @see Character#toUpperCase(int)
10255 * @see Character#getType(int)
10256 * @since 1.5
10257 */
10258 public static boolean isUpperCase(int codePoint) {
10259 return CharacterData.of(codePoint).isUpperCase(codePoint);
10260 }
10261
10262 /**
10263 * Determines if the specified character is a titlecase character.
10264 * <p>
10265 * A character is a titlecase character if its general
10266 * category type, provided by {@code Character.getType(ch)},
10267 * is {@code TITLECASE_LETTER}.
10268 * <p>
10269 * Some characters look like pairs of Latin letters. For example, there
10270 * is an uppercase letter that looks like "LJ" and has a corresponding
10271 * lowercase letter that looks like "lj". A third form, which looks like "Lj",
10272 * is the appropriate form to use when rendering a word in lowercase
10273 * with initial capitals, as for a book title.
10274 * <p>
10275 * These are some of the Unicode characters for which this method returns
10276 * {@code true}:
10277 * <ul>
10278 * <li>{@code LATIN CAPITAL LETTER D WITH SMALL LETTER Z WITH CARON}
10279 * <li>{@code LATIN CAPITAL LETTER L WITH SMALL LETTER J}
10280 * <li>{@code LATIN CAPITAL LETTER N WITH SMALL LETTER J}
10281 * <li>{@code LATIN CAPITAL LETTER D WITH SMALL LETTER Z}
10282 * </ul>
10283 * <p> Many other Unicode characters are titlecase too.
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 #isTitleCase(int)} method.
10289 *
10290 * @param ch the character to be tested.
10291 * @return {@code true} if the character is titlecase;
10292 * {@code false} otherwise.
10293 * @see Character#isLowerCase(char)
10294 * @see Character#isUpperCase(char)
10295 * @see Character#toTitleCase(char)
10296 * @see Character#getType(char)
10297 * @since 1.0.2
10298 */
10299 public static boolean isTitleCase(char ch) {
10300 return isTitleCase((int)ch);
10301 }
10302
10303 /**
10304 * Determines if the specified character (Unicode code point) is a titlecase character.
10305 * <p>
10306 * A character is a titlecase character if its general
10307 * category type, provided by {@link Character#getType(int) getType(codePoint)},
10308 * is {@code TITLECASE_LETTER}.
10309 * <p>
10310 * Some characters look like pairs of Latin letters. For example, there
10311 * is an uppercase letter that looks like "LJ" and has a corresponding
10312 * lowercase letter that looks like "lj". A third form, which looks like "Lj",
10313 * is the appropriate form to use when rendering a word in lowercase
10314 * with initial capitals, as for a book title.
10315 * <p>
10316 * These are some of the Unicode characters for which this method returns
10317 * {@code true}:
10318 * <ul>
10319 * <li>{@code LATIN CAPITAL LETTER D WITH SMALL LETTER Z WITH CARON}
10320 * <li>{@code LATIN CAPITAL LETTER L WITH SMALL LETTER J}
10321 * <li>{@code LATIN CAPITAL LETTER N WITH SMALL LETTER J}
10322 * <li>{@code LATIN CAPITAL LETTER D WITH SMALL LETTER Z}
10323 * </ul>
10324 * <p> Many other Unicode characters are titlecase too.
10325 *
10326 * @param codePoint the character (Unicode code point) to be tested.
10327 * @return {@code true} if the character is titlecase;
10328 * {@code false} otherwise.
10329 * @see Character#isLowerCase(int)
10330 * @see Character#isUpperCase(int)
10331 * @see Character#toTitleCase(int)
10332 * @see Character#getType(int)
10333 * @since 1.5
10334 */
10335 public static boolean isTitleCase(int codePoint) {
10336 return getType(codePoint) == Character.TITLECASE_LETTER;
10337 }
10338
10339 /**
10340 * Determines if the specified character is a digit.
10341 * <p>
10342 * A character is a digit if its general category type, provided
10343 * by {@code Character.getType(ch)}, is
10344 * {@code DECIMAL_DIGIT_NUMBER}.
10345 * <p>
10346 * Some Unicode character ranges that contain digits:
10347 * <ul>
10348 * <li>{@code '\u005Cu0030'} through {@code '\u005Cu0039'},
10349 * ISO-LATIN-1 digits ({@code '0'} through {@code '9'})
10350 * <li>{@code '\u005Cu0660'} through {@code '\u005Cu0669'},
10351 * Arabic-Indic digits
10352 * <li>{@code '\u005Cu06F0'} through {@code '\u005Cu06F9'},
10353 * Extended Arabic-Indic digits
10354 * <li>{@code '\u005Cu0966'} through {@code '\u005Cu096F'},
10355 * Devanagari digits
10356 * <li>{@code '\u005CuFF10'} through {@code '\u005CuFF19'},
10357 * Fullwidth digits
10358 * </ul>
10359 *
10360 * Many other character ranges contain digits as well.
10361 *
10362 * <p><b>Note:</b> This method cannot handle <a
10363 * href="#supplementary"> supplementary characters</a>. To support
10364 * all Unicode characters, including supplementary characters, use
10365 * the {@link #isDigit(int)} method.
10366 *
10367 * @param ch the character to be tested.
10368 * @return {@code true} if the character is a digit;
10369 * {@code false} otherwise.
10370 * @see Character#digit(char, int)
10371 * @see Character#forDigit(int, int)
10372 * @see Character#getType(char)
10373 */
10374 public static boolean isDigit(char ch) {
10375 return isDigit((int)ch);
10376 }
10377
10378 /**
10379 * Determines if the specified character (Unicode code point) is a digit.
10380 * <p>
10381 * A character is a digit if its general category type, provided
10382 * by {@link Character#getType(int) getType(codePoint)}, is
10383 * {@code DECIMAL_DIGIT_NUMBER}.
10384 * <p>
10385 * Some Unicode character ranges that contain digits:
10386 * <ul>
10387 * <li>{@code '\u005Cu0030'} through {@code '\u005Cu0039'},
10388 * ISO-LATIN-1 digits ({@code '0'} through {@code '9'})
10389 * <li>{@code '\u005Cu0660'} through {@code '\u005Cu0669'},
10390 * Arabic-Indic digits
10391 * <li>{@code '\u005Cu06F0'} through {@code '\u005Cu06F9'},
10392 * Extended Arabic-Indic digits
10393 * <li>{@code '\u005Cu0966'} through {@code '\u005Cu096F'},
10394 * Devanagari digits
10395 * <li>{@code '\u005CuFF10'} through {@code '\u005CuFF19'},
10396 * Fullwidth digits
10397 * </ul>
10398 *
10399 * Many other character ranges contain digits as well.
10400 *
10401 * @param codePoint the character (Unicode code point) to be tested.
10402 * @return {@code true} if the character is a digit;
10403 * {@code false} otherwise.
10404 * @see Character#forDigit(int, int)
10405 * @see Character#getType(int)
10406 * @since 1.5
10407 */
10408 public static boolean isDigit(int codePoint) {
10409 return CharacterData.of(codePoint).isDigit(codePoint);
10410 }
10411
10412 /**
10413 * Determines if a character is defined in Unicode.
10414 * <p>
10415 * A character is defined if at least one of the following is true:
10416 * <ul>
10417 * <li>It has an entry in the UnicodeData file.
10418 * <li>It has a value in a range defined by the UnicodeData file.
10419 * </ul>
10420 *
10421 * <p><b>Note:</b> This method cannot handle <a
10422 * href="#supplementary"> supplementary characters</a>. To support
10423 * all Unicode characters, including supplementary characters, use
10424 * the {@link #isDefined(int)} method.
10425 *
10426 * @param ch the character to be tested
10427 * @return {@code true} if the character has a defined meaning
10428 * in Unicode; {@code false} otherwise.
10429 * @see Character#isDigit(char)
10430 * @see Character#isLetter(char)
10431 * @see Character#isLetterOrDigit(char)
10432 * @see Character#isLowerCase(char)
10433 * @see Character#isTitleCase(char)
10434 * @see Character#isUpperCase(char)
10435 * @since 1.0.2
10436 */
10437 public static boolean isDefined(char ch) {
10438 return isDefined((int)ch);
10439 }
10440
10441 /**
10442 * Determines if a character (Unicode code point) is defined in Unicode.
10443 * <p>
10444 * A character is defined if at least one of the following is true:
10445 * <ul>
10446 * <li>It has an entry in the UnicodeData file.
10447 * <li>It has a value in a range defined by the UnicodeData file.
10448 * </ul>
10449 *
10450 * @param codePoint the character (Unicode code point) to be tested.
10451 * @return {@code true} if the character has a defined meaning
10452 * in Unicode; {@code false} otherwise.
10453 * @see Character#isDigit(int)
10454 * @see Character#isLetter(int)
10455 * @see Character#isLetterOrDigit(int)
10456 * @see Character#isLowerCase(int)
10457 * @see Character#isTitleCase(int)
10458 * @see Character#isUpperCase(int)
10459 * @since 1.5
10460 */
10461 public static boolean isDefined(int codePoint) {
10462 return getType(codePoint) != Character.UNASSIGNED;
10463 }
10464
10465 /**
10466 * Determines if the specified character is a letter.
10467 * <p>
10468 * A character is considered to be a letter if its general
10469 * category type, provided by {@code Character.getType(ch)},
10470 * is any of the following:
10471 * <ul>
10472 * <li> {@code UPPERCASE_LETTER}
10473 * <li> {@code LOWERCASE_LETTER}
10474 * <li> {@code TITLECASE_LETTER}
10475 * <li> {@code MODIFIER_LETTER}
10476 * <li> {@code OTHER_LETTER}
10477 * </ul>
10478 *
10479 * Not all letters have case. Many characters are
10480 * letters but are neither uppercase nor lowercase nor titlecase.
10481 *
10482 * <p><b>Note:</b> This method cannot handle <a
10483 * href="#supplementary"> supplementary characters</a>. To support
10484 * all Unicode characters, including supplementary characters, use
10485 * the {@link #isLetter(int)} method.
10486 *
10487 * @param ch the character to be tested.
10488 * @return {@code true} if the character is a letter;
10489 * {@code false} otherwise.
10490 * @see Character#isDigit(char)
10491 * @see Character#isJavaIdentifierStart(char)
10492 * @see Character#isJavaLetter(char)
10493 * @see Character#isJavaLetterOrDigit(char)
10494 * @see Character#isLetterOrDigit(char)
10495 * @see Character#isLowerCase(char)
10496 * @see Character#isTitleCase(char)
10497 * @see Character#isUnicodeIdentifierStart(char)
10498 * @see Character#isUpperCase(char)
10499 */
10500 public static boolean isLetter(char ch) {
10501 return isLetter((int)ch);
10502 }
10503
10504 /**
10505 * Determines if the specified character (Unicode code point) is a letter.
10506 * <p>
10507 * A character is considered to be a letter if its general
10508 * category type, provided by {@link Character#getType(int) getType(codePoint)},
10509 * is any of the following:
10510 * <ul>
10511 * <li> {@code UPPERCASE_LETTER}
10512 * <li> {@code LOWERCASE_LETTER}
10513 * <li> {@code TITLECASE_LETTER}
10514 * <li> {@code MODIFIER_LETTER}
10515 * <li> {@code OTHER_LETTER}
10516 * </ul>
10517 *
10518 * Not all letters have case. Many characters are
10519 * letters but are neither uppercase nor lowercase nor titlecase.
10520 *
10521 * @param codePoint the character (Unicode code point) to be tested.
10522 * @return {@code true} if the character is a letter;
10523 * {@code false} otherwise.
10524 * @see Character#isDigit(int)
10525 * @see Character#isJavaIdentifierStart(int)
10526 * @see Character#isLetterOrDigit(int)
10527 * @see Character#isLowerCase(int)
10528 * @see Character#isTitleCase(int)
10529 * @see Character#isUnicodeIdentifierStart(int)
10530 * @see Character#isUpperCase(int)
10531 * @since 1.5
10532 */
10533 public static boolean isLetter(int codePoint) {
10534 return ((((1 << Character.UPPERCASE_LETTER) |
10535 (1 << Character.LOWERCASE_LETTER) |
10536 (1 << Character.TITLECASE_LETTER) |
10537 (1 << Character.MODIFIER_LETTER) |
10538 (1 << Character.OTHER_LETTER)) >> getType(codePoint)) & 1)
10539 != 0;
10540 }
10541
10542 /**
10543 * Determines if the specified character is a letter or digit.
10544 * <p>
10545 * A character is considered to be a letter or digit if either
10546 * {@code Character.isLetter(char ch)} or
10547 * {@code Character.isDigit(char ch)} returns
10548 * {@code true} for the character.
10549 *
10550 * <p><b>Note:</b> This method cannot handle <a
10551 * href="#supplementary"> supplementary characters</a>. To support
10552 * all Unicode characters, including supplementary characters, use
10553 * the {@link #isLetterOrDigit(int)} method.
10554 *
10555 * @param ch the character to be tested.
10556 * @return {@code true} if the character is a letter or digit;
10557 * {@code false} otherwise.
10558 * @see Character#isDigit(char)
10559 * @see Character#isJavaIdentifierPart(char)
10560 * @see Character#isJavaLetter(char)
10561 * @see Character#isJavaLetterOrDigit(char)
10562 * @see Character#isLetter(char)
10563 * @see Character#isUnicodeIdentifierPart(char)
10564 * @since 1.0.2
10565 */
10566 public static boolean isLetterOrDigit(char ch) {
10567 return isLetterOrDigit((int)ch);
10568 }
10569
10570 /**
10571 * Determines if the specified character (Unicode code point) is a letter or digit.
10572 * <p>
10573 * A character is considered to be a letter or digit if either
10574 * {@link #isLetter(int) isLetter(codePoint)} or
10575 * {@link #isDigit(int) isDigit(codePoint)} returns
10576 * {@code true} for the character.
10577 *
10578 * @param codePoint the character (Unicode code point) to be tested.
10579 * @return {@code true} if the character is a letter or digit;
10580 * {@code false} otherwise.
10581 * @see Character#isDigit(int)
10582 * @see Character#isJavaIdentifierPart(int)
10583 * @see Character#isLetter(int)
10584 * @see Character#isUnicodeIdentifierPart(int)
10585 * @since 1.5
10586 */
10587 public static boolean isLetterOrDigit(int codePoint) {
10588 return ((((1 << Character.UPPERCASE_LETTER) |
10589 (1 << Character.LOWERCASE_LETTER) |
10590 (1 << Character.TITLECASE_LETTER) |
10591 (1 << Character.MODIFIER_LETTER) |
10592 (1 << Character.OTHER_LETTER) |
10593 (1 << Character.DECIMAL_DIGIT_NUMBER)) >> getType(codePoint)) & 1)
10594 != 0;
10595 }
10596
10597 /**
10598 * Determines if the specified character is permissible as the first
10599 * character in a Java identifier.
10600 * <p>
10601 * A character may start a Java identifier if and only if
10602 * one of the following conditions is true:
10603 * <ul>
10604 * <li> {@link #isLetter(char) isLetter(ch)} returns {@code true}
10605 * <li> {@link #getType(char) getType(ch)} returns {@code LETTER_NUMBER}
10606 * <li> {@code ch} is a currency symbol (such as {@code '$'})
10607 * <li> {@code ch} is a connecting punctuation character (such as {@code '_'}).
10608 * </ul>
10609 *
10610 * @param ch the character to be tested.
10611 * @return {@code true} if the character may start a Java
10612 * identifier; {@code false} otherwise.
10613 * @see Character#isJavaLetterOrDigit(char)
10614 * @see Character#isJavaIdentifierStart(char)
10615 * @see Character#isJavaIdentifierPart(char)
10616 * @see Character#isLetter(char)
10617 * @see Character#isLetterOrDigit(char)
10618 * @see Character#isUnicodeIdentifierStart(char)
10619 * @since 1.0.2
10620 * @deprecated Replaced by isJavaIdentifierStart(char).
10621 */
10622 @Deprecated(since="1.1")
10623 public static boolean isJavaLetter(char ch) {
10624 return isJavaIdentifierStart(ch);
10625 }
10626
10627 /**
10628 * Determines if the specified character may be part of a Java
10629 * identifier as other than the first character.
10630 * <p>
10631 * A character may be part of a Java identifier if and only if one
10632 * of the following conditions is true:
10633 * <ul>
10634 * <li> it is a letter
10635 * <li> it is a currency symbol (such as {@code '$'})
10636 * <li> it is a connecting punctuation character (such as {@code '_'})
10637 * <li> it is a digit
10638 * <li> it is a numeric letter (such as a Roman numeral character)
10639 * <li> it is a combining mark
10640 * <li> it is a non-spacing mark
10641 * <li> {@code isIdentifierIgnorable} returns
10642 * {@code true} for the character.
10643 * </ul>
10644 *
10645 * @param ch the character to be tested.
10646 * @return {@code true} if the character may be part of a
10647 * Java identifier; {@code false} otherwise.
10648 * @see Character#isJavaLetter(char)
10649 * @see Character#isJavaIdentifierStart(char)
10650 * @see Character#isJavaIdentifierPart(char)
10651 * @see Character#isLetter(char)
10652 * @see Character#isLetterOrDigit(char)
10653 * @see Character#isUnicodeIdentifierPart(char)
10654 * @see Character#isIdentifierIgnorable(char)
10655 * @since 1.0.2
10656 * @deprecated Replaced by isJavaIdentifierPart(char).
10657 */
10658 @Deprecated(since="1.1")
10659 public static boolean isJavaLetterOrDigit(char ch) {
10660 return isJavaIdentifierPart(ch);
10661 }
10662
10663 /**
10664 * Determines if the specified character (Unicode code point) is alphabetic.
10665 * <p>
10666 * A character is considered to be alphabetic if its general category type,
10667 * provided by {@link Character#getType(int) getType(codePoint)}, is any of
10668 * the following:
10669 * <ul>
10670 * <li> {@code UPPERCASE_LETTER}
10671 * <li> {@code LOWERCASE_LETTER}
10672 * <li> {@code TITLECASE_LETTER}
10673 * <li> {@code MODIFIER_LETTER}
10674 * <li> {@code OTHER_LETTER}
10675 * <li> {@code LETTER_NUMBER}
10676 * </ul>
10677 * or it has contributory property Other_Alphabetic as defined by the
10678 * Unicode Standard.
10679 *
10680 * @param codePoint the character (Unicode code point) to be tested.
10681 * @return {@code true} if the character is a Unicode alphabet
10682 * character, {@code false} otherwise.
10683 * @since 1.7
10684 */
10685 public static boolean isAlphabetic(int codePoint) {
10686 return (((((1 << Character.UPPERCASE_LETTER) |
10687 (1 << Character.LOWERCASE_LETTER) |
10688 (1 << Character.TITLECASE_LETTER) |
10689 (1 << Character.MODIFIER_LETTER) |
10690 (1 << Character.OTHER_LETTER) |
10691 (1 << Character.LETTER_NUMBER)) >> getType(codePoint)) & 1) != 0) ||
10692 CharacterData.of(codePoint).isOtherAlphabetic(codePoint);
10693 }
10694
10695 /**
10696 * Determines if the specified character (Unicode code point) is a CJKV
10697 * (Chinese, Japanese, Korean and Vietnamese) ideograph, as defined by
10698 * the Unicode Standard.
10699 *
10700 * @param codePoint the character (Unicode code point) to be tested.
10701 * @return {@code true} if the character is a Unicode ideograph
10702 * character, {@code false} otherwise.
10703 * @since 1.7
10704 */
10705 public static boolean isIdeographic(int codePoint) {
10706 return CharacterData.of(codePoint).isIdeographic(codePoint);
10707 }
10708
10709 /**
10710 * Determines if the specified character is
10711 * permissible as the first character in a Java identifier.
10712 * <p>
10713 * A character may start a Java identifier if and only if
10714 * one of the following conditions is true:
10715 * <ul>
10716 * <li> {@link #isLetter(char) isLetter(ch)} returns {@code true}
10717 * <li> {@link #getType(char) getType(ch)} returns {@code LETTER_NUMBER}
10718 * <li> {@code ch} is a currency symbol (such as {@code '$'})
10719 * <li> {@code ch} is a connecting punctuation character (such as {@code '_'}).
10720 * </ul>
10721 *
10722 * <p><b>Note:</b> This method cannot handle <a
10723 * href="#supplementary"> supplementary characters</a>. To support
10724 * all Unicode characters, including supplementary characters, use
10725 * the {@link #isJavaIdentifierStart(int)} method.
10726 *
10727 * @param ch the character to be tested.
10728 * @return {@code true} if the character may start a Java identifier;
10729 * {@code false} otherwise.
10730 * @see Character#isJavaIdentifierPart(char)
10731 * @see Character#isLetter(char)
10732 * @see Character#isUnicodeIdentifierStart(char)
10733 * @see java.compiler/javax.lang.model.SourceVersion#isIdentifier(CharSequence)
10734 * @since 1.1
10735 */
10736 @SuppressWarnings("doclint:reference") // cross-module links
10737 public static boolean isJavaIdentifierStart(char ch) {
10738 return isJavaIdentifierStart((int)ch);
10739 }
10740
10741 /**
10742 * Determines if the character (Unicode code point) is
10743 * permissible as the first character in a Java identifier.
10744 * <p>
10745 * A character may start a Java identifier if and only if
10746 * one of the following conditions is true:
10747 * <ul>
10748 * <li> {@link #isLetter(int) isLetter(codePoint)}
10749 * returns {@code true}
10750 * <li> {@link #getType(int) getType(codePoint)}
10751 * returns {@code LETTER_NUMBER}
10752 * <li> the referenced character is a currency symbol (such as {@code '$'})
10753 * <li> the referenced character is a connecting punctuation character
10754 * (such as {@code '_'}).
10755 * </ul>
10756 *
10757 * @param codePoint the character (Unicode code point) to be tested.
10758 * @return {@code true} if the character may start a Java identifier;
10759 * {@code false} otherwise.
10760 * @see Character#isJavaIdentifierPart(int)
10761 * @see Character#isLetter(int)
10762 * @see Character#isUnicodeIdentifierStart(int)
10763 * @see java.compiler/javax.lang.model.SourceVersion#isIdentifier(CharSequence)
10764 * @since 1.5
10765 */
10766 @SuppressWarnings("doclint:reference") // cross-module links
10767 public static boolean isJavaIdentifierStart(int codePoint) {
10768 return CharacterData.of(codePoint).isJavaIdentifierStart(codePoint);
10769 }
10770
10771 /**
10772 * Determines if the specified character may be part of a Java
10773 * identifier as other than the first character.
10774 * <p>
10775 * A character may be part of a Java identifier if any of the following
10776 * conditions are true:
10777 * <ul>
10778 * <li> it is a letter
10779 * <li> it is a currency symbol (such as {@code '$'})
10780 * <li> it is a connecting punctuation character (such as {@code '_'})
10781 * <li> it is a digit
10782 * <li> it is a numeric letter (such as a Roman numeral character)
10783 * <li> it is a combining mark
10784 * <li> it is a non-spacing mark
10785 * <li> {@code isIdentifierIgnorable} returns
10786 * {@code true} for the character
10787 * </ul>
10788 *
10789 * <p><b>Note:</b> This method cannot handle <a
10790 * href="#supplementary"> supplementary characters</a>. To support
10791 * all Unicode characters, including supplementary characters, use
10792 * the {@link #isJavaIdentifierPart(int)} method.
10793 *
10794 * @param ch the character to be tested.
10795 * @return {@code true} if the character may be part of a
10796 * Java identifier; {@code false} otherwise.
10797 * @see Character#isIdentifierIgnorable(char)
10798 * @see Character#isJavaIdentifierStart(char)
10799 * @see Character#isLetterOrDigit(char)
10800 * @see Character#isUnicodeIdentifierPart(char)
10801 * @see java.compiler/javax.lang.model.SourceVersion#isIdentifier(CharSequence)
10802 * @since 1.1
10803 */
10804 @SuppressWarnings("doclint:reference") // cross-module links
10805 public static boolean isJavaIdentifierPart(char ch) {
10806 return isJavaIdentifierPart((int)ch);
10807 }
10808
10809 /**
10810 * Determines if the character (Unicode code point) may be part of a Java
10811 * identifier as other than the first character.
10812 * <p>
10813 * A character may be part of a Java identifier if any of the following
10814 * conditions are true:
10815 * <ul>
10816 * <li> it is a letter
10817 * <li> it is a currency symbol (such as {@code '$'})
10818 * <li> it is a connecting punctuation character (such as {@code '_'})
10819 * <li> it is a digit
10820 * <li> it is a numeric letter (such as a Roman numeral character)
10821 * <li> it is a combining mark
10822 * <li> it is a non-spacing mark
10823 * <li> {@link #isIdentifierIgnorable(int)
10824 * isIdentifierIgnorable(codePoint)} returns {@code true} for
10825 * the code point
10826 * </ul>
10827 *
10828 * @param codePoint the character (Unicode code point) to be tested.
10829 * @return {@code true} if the character may be part of a
10830 * Java identifier; {@code false} otherwise.
10831 * @see Character#isIdentifierIgnorable(int)
10832 * @see Character#isJavaIdentifierStart(int)
10833 * @see Character#isLetterOrDigit(int)
10834 * @see Character#isUnicodeIdentifierPart(int)
10835 * @see java.compiler/javax.lang.model.SourceVersion#isIdentifier(CharSequence)
10836 * @since 1.5
10837 */
10838 @SuppressWarnings("doclint:reference") // cross-module links
10839 public static boolean isJavaIdentifierPart(int codePoint) {
10840 return CharacterData.of(codePoint).isJavaIdentifierPart(codePoint);
10841 }
10842
10843 /**
10844 * Determines if the specified character is permissible as the
10845 * first character in a Unicode identifier.
10846 * <p>
10847 * A character may start a Unicode identifier if and only if
10848 * one of the following conditions is true:
10849 * <ul>
10850 * <li> {@link #isLetter(char) isLetter(ch)} returns {@code true}
10851 * <li> {@link #getType(char) getType(ch)} returns
10852 * {@code LETTER_NUMBER}.
10853 * <li> it is an <a href="http://www.unicode.org/reports/tr44/#Other_ID_Start">
10854 * {@code Other_ID_Start}</a> character.
10855 * </ul>
10856 * <p>
10857 * This method conforms to <a href="https://unicode.org/reports/tr31/#R1">
10858 * UAX31-R1: Default Identifiers</a> requirement of the Unicode Standard,
10859 * with the following profile of UAX31:
10860 * <pre>
10861 * Start := ID_Start + 'VERTICAL TILDE' (U+2E2F)
10862 * </pre>
10863 * {@code 'VERTICAL TILDE'} is added to {@code Start} for backward
10864 * compatibility.
10865 *
10866 * <p><b>Note:</b> This method cannot handle <a
10867 * href="#supplementary"> supplementary characters</a>. To support
10868 * all Unicode characters, including supplementary characters, use
10869 * the {@link #isUnicodeIdentifierStart(int)} method.
10870 *
10871 * @param ch the character to be tested.
10872 * @return {@code true} if the character may start a Unicode
10873 * identifier; {@code false} otherwise.
10874 *
10875 * @spec https://www.unicode.org/reports/tr44 Unicode Character Database
10876 * @spec https://www.unicode.org/reports/tr31 Unicode Identifier and Pattern Syntax
10877 * @see Character#isJavaIdentifierStart(char)
10878 * @see Character#isLetter(char)
10879 * @see Character#isUnicodeIdentifierPart(char)
10880 * @since 1.1
10881 */
10882 public static boolean isUnicodeIdentifierStart(char ch) {
10883 return isUnicodeIdentifierStart((int)ch);
10884 }
10885
10886 /**
10887 * Determines if the specified character (Unicode code point) is permissible as the
10888 * first character in a Unicode identifier.
10889 * <p>
10890 * A character may start a Unicode identifier if and only if
10891 * one of the following conditions is true:
10892 * <ul>
10893 * <li> {@link #isLetter(int) isLetter(codePoint)}
10894 * returns {@code true}
10895 * <li> {@link #getType(int) getType(codePoint)}
10896 * returns {@code LETTER_NUMBER}.
10897 * <li> it is an <a href="http://www.unicode.org/reports/tr44/#Other_ID_Start">
10898 * {@code Other_ID_Start}</a> character.
10899 * </ul>
10900 * <p>
10901 * This method conforms to <a href="https://unicode.org/reports/tr31/#R1">
10902 * UAX31-R1: Default Identifiers</a> requirement of the Unicode Standard,
10903 * with the following profile of UAX31:
10904 * <pre>
10905 * Start := ID_Start + 'VERTICAL TILDE' (U+2E2F)
10906 * </pre>
10907 * {@code 'VERTICAL TILDE'} is added to {@code Start} for backward
10908 * compatibility.
10909 *
10910 * @param codePoint the character (Unicode code point) to be tested.
10911 * @return {@code true} if the character may start a Unicode
10912 * identifier; {@code false} otherwise.
10913 *
10914 * @spec https://www.unicode.org/reports/tr44 Unicode Character Database
10915 * @spec https://www.unicode.org/reports/tr31 Unicode Identifier and Pattern Syntax
10916 * @see Character#isJavaIdentifierStart(int)
10917 * @see Character#isLetter(int)
10918 * @see Character#isUnicodeIdentifierPart(int)
10919 * @since 1.5
10920 */
10921 public static boolean isUnicodeIdentifierStart(int codePoint) {
10922 return CharacterData.of(codePoint).isUnicodeIdentifierStart(codePoint);
10923 }
10924
10925 /**
10926 * Determines if the specified character may be part of a Unicode
10927 * identifier as other than the first character.
10928 * <p>
10929 * A character may be part of a Unicode identifier if and only if
10930 * one of the following statements is true:
10931 * <ul>
10932 * <li> it is a letter
10933 * <li> it is a connecting punctuation character (such as {@code '_'})
10934 * <li> it is a digit
10935 * <li> it is a numeric letter (such as a Roman numeral character)
10936 * <li> it is a combining mark
10937 * <li> it is a non-spacing mark
10938 * <li> {@code isIdentifierIgnorable} returns
10939 * {@code true} for this character.
10940 * <li> it is an <a href="http://www.unicode.org/reports/tr44/#Other_ID_Start">
10941 * {@code Other_ID_Start}</a> character.
10942 * <li> it is an <a href="http://www.unicode.org/reports/tr44/#Other_ID_Continue">
10943 * {@code Other_ID_Continue}</a> character.
10944 * </ul>
10945 * <p>
10946 * This method conforms to <a href="https://unicode.org/reports/tr31/#R1">
10947 * UAX31-R1: Default Identifiers</a> requirement of the Unicode Standard,
10948 * with the following profile of UAX31:
10949 * <pre>
10950 * Continue := Start + ID_Continue + ignorable
10951 * Medial := empty
10952 * ignorable := isIdentifierIgnorable(char) returns true for the character
10953 * </pre>
10954 * {@code ignorable} is added to {@code Continue} for backward
10955 * compatibility.
10956 *
10957 * <p><b>Note:</b> This method cannot handle <a
10958 * href="#supplementary"> supplementary characters</a>. To support
10959 * all Unicode characters, including supplementary characters, use
10960 * the {@link #isUnicodeIdentifierPart(int)} method.
10961 *
10962 * @param ch the character to be tested.
10963 * @return {@code true} if the character may be part of a
10964 * Unicode identifier; {@code false} otherwise.
10965 *
10966 * @spec https://www.unicode.org/reports/tr44 Unicode Character Database
10967 * @spec https://www.unicode.org/reports/tr31 Unicode Identifier and Pattern Syntax
10968 * @see Character#isIdentifierIgnorable(char)
10969 * @see Character#isJavaIdentifierPart(char)
10970 * @see Character#isLetterOrDigit(char)
10971 * @see Character#isUnicodeIdentifierStart(char)
10972 * @since 1.1
10973 */
10974 public static boolean isUnicodeIdentifierPart(char ch) {
10975 return isUnicodeIdentifierPart((int)ch);
10976 }
10977
10978 /**
10979 * Determines if the specified character (Unicode code point) may be part of a Unicode
10980 * identifier as other than the first character.
10981 * <p>
10982 * A character may be part of a Unicode identifier if and only if
10983 * one of the following statements is true:
10984 * <ul>
10985 * <li> it is a letter
10986 * <li> it is a connecting punctuation character (such as {@code '_'})
10987 * <li> it is a digit
10988 * <li> it is a numeric letter (such as a Roman numeral character)
10989 * <li> it is a combining mark
10990 * <li> it is a non-spacing mark
10991 * <li> {@code isIdentifierIgnorable} returns
10992 * {@code true} for this character.
10993 * <li> it is an <a href="http://www.unicode.org/reports/tr44/#Other_ID_Start">
10994 * {@code Other_ID_Start}</a> character.
10995 * <li> it is an <a href="http://www.unicode.org/reports/tr44/#Other_ID_Continue">
10996 * {@code Other_ID_Continue}</a> character.
10997 * </ul>
10998 * <p>
10999 * This method conforms to <a href="https://unicode.org/reports/tr31/#R1">
11000 * UAX31-R1: Default Identifiers</a> requirement of the Unicode Standard,
11001 * with the following profile of UAX31:
11002 * <pre>
11003 * Continue := Start + ID_Continue + ignorable
11004 * Medial := empty
11005 * ignorable := isIdentifierIgnorable(int) returns true for the character
11006 * </pre>
11007 * {@code ignorable} is added to {@code Continue} for backward
11008 * compatibility.
11009 *
11010 * @param codePoint the character (Unicode code point) to be tested.
11011 * @return {@code true} if the character may be part of a
11012 * Unicode identifier; {@code false} otherwise.
11013 *
11014 * @spec https://www.unicode.org/reports/tr44 Unicode Character Database
11015 * @spec https://www.unicode.org/reports/tr31 Unicode Identifier and Pattern Syntax
11016 * @see Character#isIdentifierIgnorable(int)
11017 * @see Character#isJavaIdentifierPart(int)
11018 * @see Character#isLetterOrDigit(int)
11019 * @see Character#isUnicodeIdentifierStart(int)
11020 * @since 1.5
11021 */
11022 public static boolean isUnicodeIdentifierPart(int codePoint) {
11023 return CharacterData.of(codePoint).isUnicodeIdentifierPart(codePoint);
11024 }
11025
11026 /**
11027 * Determines if the specified character should be regarded as
11028 * an ignorable character in a Java identifier or a Unicode identifier.
11029 * <p>
11030 * The following Unicode characters are ignorable in a Java identifier
11031 * or a Unicode identifier:
11032 * <ul>
11033 * <li>ISO control characters that are not whitespace
11034 * <ul>
11035 * <li>{@code '\u005Cu0000'} through {@code '\u005Cu0008'}
11036 * <li>{@code '\u005Cu000E'} through {@code '\u005Cu001B'}
11037 * <li>{@code '\u005Cu007F'} through {@code '\u005Cu009F'}
11038 * </ul>
11039 *
11040 * <li>all characters that have the {@code FORMAT} general
11041 * category value
11042 * </ul>
11043 *
11044 * <p><b>Note:</b> This method cannot handle <a
11045 * href="#supplementary"> supplementary characters</a>. To support
11046 * all Unicode characters, including supplementary characters, use
11047 * the {@link #isIdentifierIgnorable(int)} method.
11048 *
11049 * @param ch the character to be tested.
11050 * @return {@code true} if the character is an ignorable control
11051 * character that may be part of a Java or Unicode identifier;
11052 * {@code false} otherwise.
11053 * @see Character#isJavaIdentifierPart(char)
11054 * @see Character#isUnicodeIdentifierPart(char)
11055 * @since 1.1
11056 */
11057 public static boolean isIdentifierIgnorable(char ch) {
11058 return isIdentifierIgnorable((int)ch);
11059 }
11060
11061 /**
11062 * Determines if the specified character (Unicode code point) should be regarded as
11063 * an ignorable character in a Java identifier or a Unicode identifier.
11064 * <p>
11065 * The following Unicode characters are ignorable in a Java identifier
11066 * or a Unicode identifier:
11067 * <ul>
11068 * <li>ISO control characters that are not whitespace
11069 * <ul>
11070 * <li>{@code '\u005Cu0000'} through {@code '\u005Cu0008'}
11071 * <li>{@code '\u005Cu000E'} through {@code '\u005Cu001B'}
11072 * <li>{@code '\u005Cu007F'} through {@code '\u005Cu009F'}
11073 * </ul>
11074 *
11075 * <li>all characters that have the {@code FORMAT} general
11076 * category value
11077 * </ul>
11078 *
11079 * @param codePoint the character (Unicode code point) to be tested.
11080 * @return {@code true} if the character is an ignorable control
11081 * character that may be part of a Java or Unicode identifier;
11082 * {@code false} otherwise.
11083 * @see Character#isJavaIdentifierPart(int)
11084 * @see Character#isUnicodeIdentifierPart(int)
11085 * @since 1.5
11086 */
11087 public static boolean isIdentifierIgnorable(int codePoint) {
11088 return CharacterData.of(codePoint).isIdentifierIgnorable(codePoint);
11089 }
11090
11091 /**
11092 * Determines if the specified character (Unicode code point) is an Emoji.
11093 * <p>
11094 * A character is considered to be an Emoji if and only if it has the {@code Emoji}
11095 * property, defined in
11096 * <a href="https://unicode.org/reports/tr51/#Emoji_Properties_and_Data_Files">
11097 * Unicode Emoji (Technical Standard #51)</a>.
11098 *
11099 * @param codePoint the character (Unicode code point) to be tested.
11100 * @return {@code true} if the character is an Emoji;
11101 * {@code false} otherwise.
11102 * @since 21
11103 */
11104 public static boolean isEmoji(int codePoint) {
11105 return CharacterData.of(codePoint).isEmoji(codePoint);
11106 }
11107
11108 /**
11109 * Determines if the specified character (Unicode code point) has the
11110 * Emoji Presentation property by default.
11111 * <p>
11112 * A character is considered to have the Emoji Presentation property if and
11113 * only if it has the {@code Emoji_Presentation} property, defined in
11114 * <a href="https://unicode.org/reports/tr51/#Emoji_Properties_and_Data_Files">
11115 * Unicode Emoji (Technical Standard #51)</a>.
11116 *
11117 * @param codePoint the character (Unicode code point) to be tested.
11118 * @return {@code true} if the character has the Emoji Presentation
11119 * property; {@code false} otherwise.
11120 * @since 21
11121 */
11122 public static boolean isEmojiPresentation(int codePoint) {
11123 return CharacterData.of(codePoint).isEmojiPresentation(codePoint);
11124 }
11125
11126 /**
11127 * Determines if the specified character (Unicode code point) is an
11128 * Emoji Modifier.
11129 * <p>
11130 * A character is considered to be an Emoji Modifier if and only if it has
11131 * the {@code Emoji_Modifier} property, defined in
11132 * <a href="https://unicode.org/reports/tr51/#Emoji_Properties_and_Data_Files">
11133 * Unicode Emoji (Technical Standard #51)</a>.
11134 *
11135 * @param codePoint the character (Unicode code point) to be tested.
11136 * @return {@code true} if the character is an Emoji Modifier;
11137 * {@code false} otherwise.
11138 * @since 21
11139 */
11140 public static boolean isEmojiModifier(int codePoint) {
11141 return CharacterData.of(codePoint).isEmojiModifier(codePoint);
11142 }
11143
11144 /**
11145 * Determines if the specified character (Unicode code point) is an
11146 * Emoji Modifier Base.
11147 * <p>
11148 * A character is considered to be an Emoji Modifier Base if and only if it has
11149 * the {@code Emoji_Modifier_Base} property, defined in
11150 * <a href="https://unicode.org/reports/tr51/#Emoji_Properties_and_Data_Files">
11151 * Unicode Emoji (Technical Standard #51)</a>.
11152 *
11153 * @param codePoint the character (Unicode code point) to be tested.
11154 * @return {@code true} if the character is an Emoji Modifier Base;
11155 * {@code false} otherwise.
11156 * @since 21
11157 */
11158 public static boolean isEmojiModifierBase(int codePoint) {
11159 return CharacterData.of(codePoint).isEmojiModifierBase(codePoint);
11160 }
11161
11162 /**
11163 * Determines if the specified character (Unicode code point) is an
11164 * Emoji Component.
11165 * <p>
11166 * A character is considered to be an Emoji Component if and only if it has
11167 * the {@code Emoji_Component} property, defined in
11168 * <a href="https://unicode.org/reports/tr51/#Emoji_Properties_and_Data_Files">
11169 * Unicode Emoji (Technical Standard #51)</a>.
11170 *
11171 * @param codePoint the character (Unicode code point) to be tested.
11172 * @return {@code true} if the character is an Emoji Component;
11173 * {@code false} otherwise.
11174 * @since 21
11175 */
11176 public static boolean isEmojiComponent(int codePoint) {
11177 return CharacterData.of(codePoint).isEmojiComponent(codePoint);
11178 }
11179
11180 /**
11181 * Determines if the specified character (Unicode code point) is
11182 * an Extended Pictographic.
11183 * <p>
11184 * A character is considered to be an Extended Pictographic if and only if it has
11185 * the {@code Extended_Pictographic} property, defined in
11186 * <a href="https://unicode.org/reports/tr51/#Emoji_Properties_and_Data_Files">
11187 * Unicode Emoji (Technical Standard #51)</a>.
11188 *
11189 * @param codePoint the character (Unicode code point) to be tested.
11190 * @return {@code true} if the character is an Extended Pictographic;
11191 * {@code false} otherwise.
11192 * @since 21
11193 */
11194 public static boolean isExtendedPictographic(int codePoint) {
11195 return CharacterData.of(codePoint).isExtendedPictographic(codePoint);
11196 }
11197
11198 /**
11199 * Converts the character argument to lowercase using case
11200 * mapping information from the UnicodeData file.
11201 * <p>
11202 * Note that
11203 * {@code Character.isLowerCase(Character.toLowerCase(ch))}
11204 * does not always return {@code true} for some ranges of
11205 * characters, particularly those that are symbols or ideographs.
11206 *
11207 * <p>In general, {@link String#toLowerCase()} should be used to map
11208 * characters to lowercase. {@code String} case mapping methods
11209 * have several benefits over {@code Character} case mapping methods.
11210 * {@code String} case mapping methods can perform locale-sensitive
11211 * mappings, context-sensitive mappings, and 1:M character mappings, whereas
11212 * the {@code Character} case mapping methods cannot.
11213 *
11214 * <p><b>Note:</b> This method cannot handle <a
11215 * href="#supplementary"> supplementary characters</a>. To support
11216 * all Unicode characters, including supplementary characters, use
11217 * the {@link #toLowerCase(int)} method.
11218 *
11219 * @param ch the character to be converted.
11220 * @return the lowercase equivalent of the character, if any;
11221 * otherwise, the character itself.
11222 * @see Character#isLowerCase(char)
11223 * @see String#toLowerCase()
11224 */
11225 public static char toLowerCase(char ch) {
11226 return (char)toLowerCase((int)ch);
11227 }
11228
11229 /**
11230 * Converts the character (Unicode code point) argument to
11231 * lowercase using case mapping information from the UnicodeData
11232 * file.
11233 *
11234 * <p> Note that
11235 * {@code Character.isLowerCase(Character.toLowerCase(codePoint))}
11236 * does not always return {@code true} for some ranges of
11237 * characters, particularly those that are symbols or ideographs.
11238 *
11239 * <p>In general, {@link String#toLowerCase()} should be used to map
11240 * characters to lowercase. {@code String} case mapping methods
11241 * have several benefits over {@code Character} case mapping methods.
11242 * {@code String} case mapping methods can perform locale-sensitive
11243 * mappings, context-sensitive mappings, and 1:M character mappings, whereas
11244 * the {@code Character} case mapping methods cannot.
11245 *
11246 * @param codePoint the character (Unicode code point) to be converted.
11247 * @return the lowercase equivalent of the character (Unicode code
11248 * point), if any; otherwise, the character itself.
11249 * @see Character#isLowerCase(int)
11250 * @see String#toLowerCase()
11251 *
11252 * @since 1.5
11253 */
11254 public static int toLowerCase(int codePoint) {
11255 return CharacterData.of(codePoint).toLowerCase(codePoint);
11256 }
11257
11258 /**
11259 * Converts the character argument to uppercase using case mapping
11260 * information from the UnicodeData file.
11261 * <p>
11262 * Note that
11263 * {@code Character.isUpperCase(Character.toUpperCase(ch))}
11264 * does not always return {@code true} for some ranges of
11265 * characters, particularly those that are symbols or ideographs.
11266 *
11267 * <p>In general, {@link String#toUpperCase()} should be used to map
11268 * characters to uppercase. {@code String} case mapping methods
11269 * have several benefits over {@code Character} case mapping methods.
11270 * {@code String} case mapping methods can perform locale-sensitive
11271 * mappings, context-sensitive mappings, and 1:M character mappings, whereas
11272 * the {@code Character} case mapping methods cannot.
11273 *
11274 * <p><b>Note:</b> This method cannot handle <a
11275 * href="#supplementary"> supplementary characters</a>. To support
11276 * all Unicode characters, including supplementary characters, use
11277 * the {@link #toUpperCase(int)} method.
11278 *
11279 * @param ch the character to be converted.
11280 * @return the uppercase equivalent of the character, if any;
11281 * otherwise, the character itself.
11282 * @see Character#isUpperCase(char)
11283 * @see String#toUpperCase()
11284 */
11285 public static char toUpperCase(char ch) {
11286 return (char)toUpperCase((int)ch);
11287 }
11288
11289 /**
11290 * Converts the character (Unicode code point) argument to
11291 * uppercase using case mapping information from the UnicodeData
11292 * file.
11293 *
11294 * <p>Note that
11295 * {@code Character.isUpperCase(Character.toUpperCase(codePoint))}
11296 * does not always return {@code true} for some ranges of
11297 * characters, particularly those that are symbols or ideographs.
11298 *
11299 * <p>In general, {@link String#toUpperCase()} should be used to map
11300 * characters to uppercase. {@code String} case mapping methods
11301 * have several benefits over {@code Character} case mapping methods.
11302 * {@code String} case mapping methods can perform locale-sensitive
11303 * mappings, context-sensitive mappings, and 1:M character mappings, whereas
11304 * the {@code Character} case mapping methods cannot.
11305 *
11306 * @param codePoint the character (Unicode code point) to be converted.
11307 * @return the uppercase equivalent of the character, if any;
11308 * otherwise, the character itself.
11309 * @see Character#isUpperCase(int)
11310 * @see String#toUpperCase()
11311 *
11312 * @since 1.5
11313 */
11314 public static int toUpperCase(int codePoint) {
11315 return CharacterData.of(codePoint).toUpperCase(codePoint);
11316 }
11317
11318 /**
11319 * Converts the character argument to titlecase using case mapping
11320 * information from the UnicodeData file. If a character has no
11321 * explicit titlecase mapping and is not itself a titlecase char
11322 * according to UnicodeData, then the uppercase mapping is
11323 * returned as an equivalent titlecase mapping. If the
11324 * {@code char} argument is already a titlecase
11325 * {@code char}, the same {@code char} value will be
11326 * returned.
11327 * <p>
11328 * Note that
11329 * {@code Character.isTitleCase(Character.toTitleCase(ch))}
11330 * does not always return {@code true} for some ranges of
11331 * characters.
11332 *
11333 * <p><b>Note:</b> This method cannot handle <a
11334 * href="#supplementary"> supplementary characters</a>. To support
11335 * all Unicode characters, including supplementary characters, use
11336 * the {@link #toTitleCase(int)} method.
11337 *
11338 * @param ch the character to be converted.
11339 * @return the titlecase equivalent of the character, if any;
11340 * otherwise, the character itself.
11341 * @see Character#isTitleCase(char)
11342 * @see Character#toLowerCase(char)
11343 * @see Character#toUpperCase(char)
11344 * @since 1.0.2
11345 */
11346 public static char toTitleCase(char ch) {
11347 return (char)toTitleCase((int)ch);
11348 }
11349
11350 /**
11351 * Converts the character (Unicode code point) argument to titlecase using case mapping
11352 * information from the UnicodeData file. If a character has no
11353 * explicit titlecase mapping and is not itself a titlecase char
11354 * according to UnicodeData, then the uppercase mapping is
11355 * returned as an equivalent titlecase mapping. If the
11356 * character argument is already a titlecase
11357 * character, the same character value will be
11358 * returned.
11359 *
11360 * <p>Note that
11361 * {@code Character.isTitleCase(Character.toTitleCase(codePoint))}
11362 * does not always return {@code true} for some ranges of
11363 * characters.
11364 *
11365 * @param codePoint the character (Unicode code point) to be converted.
11366 * @return the titlecase equivalent of the character, if any;
11367 * otherwise, the character itself.
11368 * @see Character#isTitleCase(int)
11369 * @see Character#toLowerCase(int)
11370 * @see Character#toUpperCase(int)
11371 * @since 1.5
11372 */
11373 public static int toTitleCase(int codePoint) {
11374 return CharacterData.of(codePoint).toTitleCase(codePoint);
11375 }
11376
11377 /**
11378 * Returns the numeric value of the character {@code ch} in the
11379 * specified radix.
11380 * <p>
11381 * If the radix is not in the range {@code MIN_RADIX} ≤
11382 * {@code radix} ≤ {@code MAX_RADIX} or if the
11383 * value of {@code ch} is not a valid digit in the specified
11384 * radix, {@code -1} is returned. A character is a valid digit
11385 * if at least one of the following is true:
11386 * <ul>
11387 * <li>The method {@code isDigit} is {@code true} of the character
11388 * and the Unicode decimal digit value of the character (or its
11389 * single-character decomposition) is less than the specified radix.
11390 * In this case the decimal digit value is returned.
11391 * <li>The character is one of the uppercase Latin letters
11392 * {@code 'A'} through {@code 'Z'} and its code is less than
11393 * {@code radix + 'A' - 10}.
11394 * In this case, {@code ch - 'A' + 10}
11395 * is returned.
11396 * <li>The character is one of the lowercase Latin letters
11397 * {@code 'a'} through {@code 'z'} and its code is less than
11398 * {@code radix + 'a' - 10}.
11399 * In this case, {@code ch - 'a' + 10}
11400 * is returned.
11401 * <li>The character is one of the fullwidth uppercase Latin letters A
11402 * ({@code '\u005CuFF21'}) through Z ({@code '\u005CuFF3A'})
11403 * and its code is less than
11404 * {@code radix + '\u005CuFF21' - 10}.
11405 * In this case, {@code ch - '\u005CuFF21' + 10}
11406 * is returned.
11407 * <li>The character is one of the fullwidth lowercase Latin letters a
11408 * ({@code '\u005CuFF41'}) through z ({@code '\u005CuFF5A'})
11409 * and its code is less than
11410 * {@code radix + '\u005CuFF41' - 10}.
11411 * In this case, {@code ch - '\u005CuFF41' + 10}
11412 * is returned.
11413 * </ul>
11414 *
11415 * <p><b>Note:</b> This method cannot handle <a
11416 * href="#supplementary"> supplementary characters</a>. To support
11417 * all Unicode characters, including supplementary characters, use
11418 * the {@link #digit(int, int)} method.
11419 *
11420 * @param ch the character to be converted.
11421 * @param radix the radix.
11422 * @return the numeric value represented by the character in the
11423 * specified radix.
11424 * @see Character#forDigit(int, int)
11425 * @see Character#isDigit(char)
11426 */
11427 public static int digit(char ch, int radix) {
11428 return digit((int)ch, radix);
11429 }
11430
11431 /**
11432 * Returns the numeric value of the specified character (Unicode
11433 * code point) in the specified radix.
11434 *
11435 * <p>If the radix is not in the range {@code MIN_RADIX} ≤
11436 * {@code radix} ≤ {@code MAX_RADIX} or if the
11437 * character is not a valid digit in the specified
11438 * radix, {@code -1} is returned. A character is a valid digit
11439 * if at least one of the following is true:
11440 * <ul>
11441 * <li>The method {@link #isDigit(int) isDigit(codePoint)} is {@code true} of the character
11442 * and the Unicode decimal digit value of the character (or its
11443 * single-character decomposition) is less than the specified radix.
11444 * In this case the decimal digit value is returned.
11445 * <li>The character is one of the uppercase Latin letters
11446 * {@code 'A'} through {@code 'Z'} and its code is less than
11447 * {@code radix + 'A' - 10}.
11448 * In this case, {@code codePoint - 'A' + 10}
11449 * is returned.
11450 * <li>The character is one of the lowercase Latin letters
11451 * {@code 'a'} through {@code 'z'} and its code is less than
11452 * {@code radix + 'a' - 10}.
11453 * In this case, {@code codePoint - 'a' + 10}
11454 * is returned.
11455 * <li>The character is one of the fullwidth uppercase Latin letters A
11456 * ({@code '\u005CuFF21'}) through Z ({@code '\u005CuFF3A'})
11457 * and its code is less than
11458 * {@code radix + '\u005CuFF21' - 10}.
11459 * In this case,
11460 * {@code codePoint - '\u005CuFF21' + 10}
11461 * is returned.
11462 * <li>The character is one of the fullwidth lowercase Latin letters a
11463 * ({@code '\u005CuFF41'}) through z ({@code '\u005CuFF5A'})
11464 * and its code is less than
11465 * {@code radix + '\u005CuFF41'- 10}.
11466 * In this case,
11467 * {@code codePoint - '\u005CuFF41' + 10}
11468 * is returned.
11469 * </ul>
11470 *
11471 * @param codePoint the character (Unicode code point) to be converted.
11472 * @param radix the radix.
11473 * @return the numeric value represented by the character in the
11474 * specified radix.
11475 * @see Character#forDigit(int, int)
11476 * @see Character#isDigit(int)
11477 * @since 1.5
11478 */
11479 public static int digit(int codePoint, int radix) {
11480 return CharacterData.of(codePoint).digit(codePoint, radix);
11481 }
11482
11483 /**
11484 * Returns the {@code int} value that the specified Unicode
11485 * character represents. For example, the character
11486 * {@code '\u005Cu216C'} (the roman numeral fifty) will return
11487 * an int with a value of 50.
11488 * <p>
11489 * The letters A-Z in their uppercase ({@code '\u005Cu0041'} through
11490 * {@code '\u005Cu005A'}), lowercase
11491 * ({@code '\u005Cu0061'} through {@code '\u005Cu007A'}), and
11492 * full width variant ({@code '\u005CuFF21'} through
11493 * {@code '\u005CuFF3A'} and {@code '\u005CuFF41'} through
11494 * {@code '\u005CuFF5A'}) forms have numeric values from 10
11495 * through 35. This is independent of the Unicode specification,
11496 * which does not assign numeric values to these {@code char}
11497 * values.
11498 * <p>
11499 * If the character does not have a numeric value, then -1 is returned.
11500 * If the character has a numeric value that cannot be represented as a
11501 * nonnegative integer (for example, a fractional value), then -2
11502 * is returned.
11503 *
11504 * <p><b>Note:</b> This method cannot handle <a
11505 * href="#supplementary"> supplementary characters</a>. To support
11506 * all Unicode characters, including supplementary characters, use
11507 * the {@link #getNumericValue(int)} method.
11508 *
11509 * @param ch the character to be converted.
11510 * @return the numeric value of the character, as a nonnegative {@code int}
11511 * value; -2 if the character has a numeric value but the value
11512 * can not be represented as a nonnegative {@code int} value;
11513 * -1 if the character has no numeric value.
11514 * @see Character#forDigit(int, int)
11515 * @see Character#isDigit(char)
11516 * @since 1.1
11517 */
11518 public static int getNumericValue(char ch) {
11519 return getNumericValue((int)ch);
11520 }
11521
11522 /**
11523 * Returns the {@code int} value that the specified
11524 * character (Unicode code point) represents. For example, the character
11525 * {@code '\u005Cu216C'} (the Roman numeral fifty) will return
11526 * an {@code int} with a value of 50.
11527 * <p>
11528 * The letters A-Z in their uppercase ({@code '\u005Cu0041'} through
11529 * {@code '\u005Cu005A'}), lowercase
11530 * ({@code '\u005Cu0061'} through {@code '\u005Cu007A'}), and
11531 * full width variant ({@code '\u005CuFF21'} through
11532 * {@code '\u005CuFF3A'} and {@code '\u005CuFF41'} through
11533 * {@code '\u005CuFF5A'}) forms have numeric values from 10
11534 * through 35. This is independent of the Unicode specification,
11535 * which does not assign numeric values to these {@code char}
11536 * values.
11537 * <p>
11538 * If the character does not have a numeric value, then -1 is returned.
11539 * If the character has a numeric value that cannot be represented as a
11540 * nonnegative integer (for example, a fractional value), then -2
11541 * is returned.
11542 *
11543 * @param codePoint the character (Unicode code point) to be converted.
11544 * @return the numeric value of the character, as a nonnegative {@code int}
11545 * value; -2 if the character has a numeric value but the value
11546 * can not be represented as a nonnegative {@code int} value;
11547 * -1 if the character has no numeric value.
11548 * @see Character#forDigit(int, int)
11549 * @see Character#isDigit(int)
11550 * @since 1.5
11551 */
11552 public static int getNumericValue(int codePoint) {
11553 return CharacterData.of(codePoint).getNumericValue(codePoint);
11554 }
11555
11556 /**
11557 * Determines if the specified character is ISO-LATIN-1 white space.
11558 * This method returns {@code true} for the following five
11559 * characters only:
11560 * <table class="striped">
11561 * <caption style="display:none">truechars</caption>
11562 * <thead>
11563 * <tr><th scope="col">Character
11564 * <th scope="col">Code
11565 * <th scope="col">Name
11566 * </thead>
11567 * <tbody>
11568 * <tr><th scope="row">{@code '\t'}</th> <td>{@code U+0009}</td>
11569 * <td>{@code HORIZONTAL TABULATION}</td></tr>
11570 * <tr><th scope="row">{@code '\n'}</th> <td>{@code U+000A}</td>
11571 * <td>{@code NEW LINE}</td></tr>
11572 * <tr><th scope="row">{@code '\f'}</th> <td>{@code U+000C}</td>
11573 * <td>{@code FORM FEED}</td></tr>
11574 * <tr><th scope="row">{@code '\r'}</th> <td>{@code U+000D}</td>
11575 * <td>{@code CARRIAGE RETURN}</td></tr>
11576 * <tr><th scope="row">{@code ' '}</th> <td>{@code U+0020}</td>
11577 * <td>{@code SPACE}</td></tr>
11578 * </tbody>
11579 * </table>
11580 *
11581 * @param ch the character to be tested.
11582 * @return {@code true} if the character is ISO-LATIN-1 white
11583 * space; {@code false} otherwise.
11584 * @see Character#isSpaceChar(char)
11585 * @see Character#isWhitespace(char)
11586 * @deprecated Replaced by isWhitespace(char).
11587 */
11588 @Deprecated(since="1.1")
11589 public static boolean isSpace(char ch) {
11590 return (ch <= 0x0020) &&
11591 (((((1L << 0x0009) |
11592 (1L << 0x000A) |
11593 (1L << 0x000C) |
11594 (1L << 0x000D) |
11595 (1L << 0x0020)) >> ch) & 1L) != 0);
11596 }
11597
11598
11599 /**
11600 * Determines if the specified character is a Unicode space character.
11601 * A character is considered to be a space character if and only if
11602 * it is specified to be a space character by the Unicode Standard. This
11603 * method returns true if the character's general category type is any of
11604 * the following:
11605 * <ul>
11606 * <li> {@code SPACE_SEPARATOR}
11607 * <li> {@code LINE_SEPARATOR}
11608 * <li> {@code PARAGRAPH_SEPARATOR}
11609 * </ul>
11610 *
11611 * <p><b>Note:</b> This method cannot handle <a
11612 * href="#supplementary"> supplementary characters</a>. To support
11613 * all Unicode characters, including supplementary characters, use
11614 * the {@link #isSpaceChar(int)} method.
11615 *
11616 * @param ch the character to be tested.
11617 * @return {@code true} if the character is a space character;
11618 * {@code false} otherwise.
11619 * @see Character#isWhitespace(char)
11620 * @since 1.1
11621 */
11622 public static boolean isSpaceChar(char ch) {
11623 return isSpaceChar((int)ch);
11624 }
11625
11626 /**
11627 * Determines if the specified character (Unicode code point) is a
11628 * Unicode space character. A character is considered to be a
11629 * space character if and only if it is specified to be a space
11630 * character by the Unicode Standard. This method returns true if
11631 * the character's general category type is any of the following:
11632 *
11633 * <ul>
11634 * <li> {@link #SPACE_SEPARATOR}
11635 * <li> {@link #LINE_SEPARATOR}
11636 * <li> {@link #PARAGRAPH_SEPARATOR}
11637 * </ul>
11638 *
11639 * @param codePoint the character (Unicode code point) to be tested.
11640 * @return {@code true} if the character is a space character;
11641 * {@code false} otherwise.
11642 * @see Character#isWhitespace(int)
11643 * @since 1.5
11644 */
11645 public static boolean isSpaceChar(int codePoint) {
11646 return ((((1 << Character.SPACE_SEPARATOR) |
11647 (1 << Character.LINE_SEPARATOR) |
11648 (1 << Character.PARAGRAPH_SEPARATOR)) >> getType(codePoint)) & 1)
11649 != 0;
11650 }
11651
11652 /**
11653 * Determines if the specified character is white space according to Java.
11654 * A character is a Java whitespace character if and only if it satisfies
11655 * one of the following criteria:
11656 * <ul>
11657 * <li> It is a Unicode space character ({@code SPACE_SEPARATOR},
11658 * {@code LINE_SEPARATOR}, or {@code PARAGRAPH_SEPARATOR})
11659 * but is not also a non-breaking space ({@code '\u005Cu00A0'},
11660 * {@code '\u005Cu2007'}, {@code '\u005Cu202F'}).
11661 * <li> It is {@code '\u005Ct'}, U+0009 HORIZONTAL TABULATION.
11662 * <li> It is {@code '\u005Cn'}, U+000A LINE FEED.
11663 * <li> It is {@code '\u005Cu000B'}, U+000B VERTICAL TABULATION.
11664 * <li> It is {@code '\u005Cf'}, U+000C FORM FEED.
11665 * <li> It is {@code '\u005Cr'}, U+000D CARRIAGE RETURN.
11666 * <li> It is {@code '\u005Cu001C'}, U+001C FILE SEPARATOR.
11667 * <li> It is {@code '\u005Cu001D'}, U+001D GROUP SEPARATOR.
11668 * <li> It is {@code '\u005Cu001E'}, U+001E RECORD SEPARATOR.
11669 * <li> It is {@code '\u005Cu001F'}, U+001F UNIT SEPARATOR.
11670 * </ul>
11671 *
11672 * <p><b>Note:</b> This method cannot handle <a
11673 * href="#supplementary"> supplementary characters</a>. To support
11674 * all Unicode characters, including supplementary characters, use
11675 * the {@link #isWhitespace(int)} method.
11676 *
11677 * @param ch the character to be tested.
11678 * @return {@code true} if the character is a Java whitespace
11679 * character; {@code false} otherwise.
11680 * @see Character#isSpaceChar(char)
11681 * @since 1.1
11682 */
11683 public static boolean isWhitespace(char ch) {
11684 return isWhitespace((int)ch);
11685 }
11686
11687 /**
11688 * Determines if the specified character (Unicode code point) is
11689 * white space according to Java. A character is a Java
11690 * whitespace character if and only if it satisfies one of the
11691 * following criteria:
11692 * <ul>
11693 * <li> It is a Unicode space character ({@link #SPACE_SEPARATOR},
11694 * {@link #LINE_SEPARATOR}, or {@link #PARAGRAPH_SEPARATOR})
11695 * but is not also a non-breaking space ({@code '\u005Cu00A0'},
11696 * {@code '\u005Cu2007'}, {@code '\u005Cu202F'}).
11697 * <li> It is {@code '\u005Ct'}, U+0009 HORIZONTAL TABULATION.
11698 * <li> It is {@code '\u005Cn'}, U+000A LINE FEED.
11699 * <li> It is {@code '\u005Cu000B'}, U+000B VERTICAL TABULATION.
11700 * <li> It is {@code '\u005Cf'}, U+000C FORM FEED.
11701 * <li> It is {@code '\u005Cr'}, U+000D CARRIAGE RETURN.
11702 * <li> It is {@code '\u005Cu001C'}, U+001C FILE SEPARATOR.
11703 * <li> It is {@code '\u005Cu001D'}, U+001D GROUP SEPARATOR.
11704 * <li> It is {@code '\u005Cu001E'}, U+001E RECORD SEPARATOR.
11705 * <li> It is {@code '\u005Cu001F'}, U+001F UNIT SEPARATOR.
11706 * </ul>
11707 *
11708 * @param codePoint the character (Unicode code point) to be tested.
11709 * @return {@code true} if the character is a Java whitespace
11710 * character; {@code false} otherwise.
11711 * @see Character#isSpaceChar(int)
11712 * @since 1.5
11713 */
11714 public static boolean isWhitespace(int codePoint) {
11715 return CharacterData.of(codePoint).isWhitespace(codePoint);
11716 }
11717
11718 /**
11719 * Determines if the specified character is an ISO control
11720 * character. A character is considered to be an ISO control
11721 * character if its code is in the range {@code '\u005Cu0000'}
11722 * through {@code '\u005Cu001F'} or in the range
11723 * {@code '\u005Cu007F'} through {@code '\u005Cu009F'}.
11724 *
11725 * <p><b>Note:</b> This method cannot handle <a
11726 * href="#supplementary"> supplementary characters</a>. To support
11727 * all Unicode characters, including supplementary characters, use
11728 * the {@link #isISOControl(int)} method.
11729 *
11730 * @param ch the character to be tested.
11731 * @return {@code true} if the character is an ISO control character;
11732 * {@code false} otherwise.
11733 *
11734 * @see Character#isSpaceChar(char)
11735 * @see Character#isWhitespace(char)
11736 * @since 1.1
11737 */
11738 public static boolean isISOControl(char ch) {
11739 return isISOControl((int)ch);
11740 }
11741
11742 /**
11743 * Determines if the referenced character (Unicode code point) is an ISO control
11744 * character. A character is considered to be an ISO control
11745 * character if its code is in the range {@code '\u005Cu0000'}
11746 * through {@code '\u005Cu001F'} or in the range
11747 * {@code '\u005Cu007F'} through {@code '\u005Cu009F'}.
11748 *
11749 * @param codePoint the character (Unicode code point) to be tested.
11750 * @return {@code true} if the character is an ISO control character;
11751 * {@code false} otherwise.
11752 * @see Character#isSpaceChar(int)
11753 * @see Character#isWhitespace(int)
11754 * @since 1.5
11755 */
11756 public static boolean isISOControl(int codePoint) {
11757 // Optimized form of:
11758 // (codePoint >= 0x00 && codePoint <= 0x1F) ||
11759 // (codePoint >= 0x7F && codePoint <= 0x9F);
11760 return codePoint <= 0x9F &&
11761 (codePoint >= 0x7F || (codePoint >>> 5 == 0));
11762 }
11763
11764 /**
11765 * Returns a value indicating a character's general category.
11766 *
11767 * <p><b>Note:</b> This method cannot handle <a
11768 * href="#supplementary"> supplementary characters</a>. To support
11769 * all Unicode characters, including supplementary characters, use
11770 * the {@link #getType(int)} method.
11771 *
11772 * @param ch the character to be tested.
11773 * @return a value of type {@code int} representing the
11774 * character's general category.
11775 * @see Character#COMBINING_SPACING_MARK
11776 * @see Character#CONNECTOR_PUNCTUATION
11777 * @see Character#CONTROL
11778 * @see Character#CURRENCY_SYMBOL
11779 * @see Character#DASH_PUNCTUATION
11780 * @see Character#DECIMAL_DIGIT_NUMBER
11781 * @see Character#ENCLOSING_MARK
11782 * @see Character#END_PUNCTUATION
11783 * @see Character#FINAL_QUOTE_PUNCTUATION
11784 * @see Character#FORMAT
11785 * @see Character#INITIAL_QUOTE_PUNCTUATION
11786 * @see Character#LETTER_NUMBER
11787 * @see Character#LINE_SEPARATOR
11788 * @see Character#LOWERCASE_LETTER
11789 * @see Character#MATH_SYMBOL
11790 * @see Character#MODIFIER_LETTER
11791 * @see Character#MODIFIER_SYMBOL
11792 * @see Character#NON_SPACING_MARK
11793 * @see Character#OTHER_LETTER
11794 * @see Character#OTHER_NUMBER
11795 * @see Character#OTHER_PUNCTUATION
11796 * @see Character#OTHER_SYMBOL
11797 * @see Character#PARAGRAPH_SEPARATOR
11798 * @see Character#PRIVATE_USE
11799 * @see Character#SPACE_SEPARATOR
11800 * @see Character#START_PUNCTUATION
11801 * @see Character#SURROGATE
11802 * @see Character#TITLECASE_LETTER
11803 * @see Character#UNASSIGNED
11804 * @see Character#UPPERCASE_LETTER
11805 * @since 1.1
11806 */
11807 public static int getType(char ch) {
11808 return getType((int)ch);
11809 }
11810
11811 /**
11812 * Returns a value indicating a character's general category.
11813 *
11814 * @param codePoint the character (Unicode code point) to be tested.
11815 * @return a value of type {@code int} representing the
11816 * character's general category.
11817 * @see Character#COMBINING_SPACING_MARK COMBINING_SPACING_MARK
11818 * @see Character#CONNECTOR_PUNCTUATION CONNECTOR_PUNCTUATION
11819 * @see Character#CONTROL CONTROL
11820 * @see Character#CURRENCY_SYMBOL CURRENCY_SYMBOL
11821 * @see Character#DASH_PUNCTUATION DASH_PUNCTUATION
11822 * @see Character#DECIMAL_DIGIT_NUMBER DECIMAL_DIGIT_NUMBER
11823 * @see Character#ENCLOSING_MARK ENCLOSING_MARK
11824 * @see Character#END_PUNCTUATION END_PUNCTUATION
11825 * @see Character#FINAL_QUOTE_PUNCTUATION FINAL_QUOTE_PUNCTUATION
11826 * @see Character#FORMAT FORMAT
11827 * @see Character#INITIAL_QUOTE_PUNCTUATION INITIAL_QUOTE_PUNCTUATION
11828 * @see Character#LETTER_NUMBER LETTER_NUMBER
11829 * @see Character#LINE_SEPARATOR LINE_SEPARATOR
11830 * @see Character#LOWERCASE_LETTER LOWERCASE_LETTER
11831 * @see Character#MATH_SYMBOL MATH_SYMBOL
11832 * @see Character#MODIFIER_LETTER MODIFIER_LETTER
11833 * @see Character#MODIFIER_SYMBOL MODIFIER_SYMBOL
11834 * @see Character#NON_SPACING_MARK NON_SPACING_MARK
11835 * @see Character#OTHER_LETTER OTHER_LETTER
11836 * @see Character#OTHER_NUMBER OTHER_NUMBER
11837 * @see Character#OTHER_PUNCTUATION OTHER_PUNCTUATION
11838 * @see Character#OTHER_SYMBOL OTHER_SYMBOL
11839 * @see Character#PARAGRAPH_SEPARATOR PARAGRAPH_SEPARATOR
11840 * @see Character#PRIVATE_USE PRIVATE_USE
11841 * @see Character#SPACE_SEPARATOR SPACE_SEPARATOR
11842 * @see Character#START_PUNCTUATION START_PUNCTUATION
11843 * @see Character#SURROGATE SURROGATE
11844 * @see Character#TITLECASE_LETTER TITLECASE_LETTER
11845 * @see Character#UNASSIGNED UNASSIGNED
11846 * @see Character#UPPERCASE_LETTER UPPERCASE_LETTER
11847 * @since 1.5
11848 */
11849 public static int getType(int codePoint) {
11850 return CharacterData.of(codePoint).getType(codePoint);
11851 }
11852
11853 /**
11854 * Determines the character representation for a specific digit in
11855 * the specified radix. If the value of {@code radix} is not a
11856 * valid radix, or the value of {@code digit} is not a valid
11857 * digit in the specified radix, the null character
11858 * ({@code '\u005Cu0000'}) is returned.
11859 * <p>
11860 * The {@code radix} argument is valid if it is greater than or
11861 * equal to {@code MIN_RADIX} and less than or equal to
11862 * {@code MAX_RADIX}. The {@code digit} argument is valid if
11863 * {@code 0 <= digit < radix}.
11864 * <p>
11865 * If the digit is less than 10, then
11866 * {@code '0' + digit} is returned. Otherwise, the value
11867 * {@code 'a' + digit - 10} is returned.
11868 *
11869 * @param digit the number to convert to a character.
11870 * @param radix the radix.
11871 * @return the {@code char} representation of the specified digit
11872 * in the specified radix.
11873 * @see Character#MIN_RADIX
11874 * @see Character#MAX_RADIX
11875 * @see Character#digit(char, int)
11876 */
11877 public static char forDigit(int digit, int radix) {
11878 if ((digit >= radix) || (digit < 0)) {
11879 return '\0';
11880 }
11881 if ((radix < Character.MIN_RADIX) || (radix > Character.MAX_RADIX)) {
11882 return '\0';
11883 }
11884 if (digit < 10) {
11885 return (char)('0' + digit);
11886 }
11887 return (char)('a' - 10 + digit);
11888 }
11889
11890 /**
11891 * Returns the Unicode directionality property for the given
11892 * character. Character directionality is used to calculate the
11893 * visual ordering of text. The directionality value of undefined
11894 * {@code char} values is {@code DIRECTIONALITY_UNDEFINED}.
11895 *
11896 * <p><b>Note:</b> This method cannot handle <a
11897 * href="#supplementary"> supplementary characters</a>. To support
11898 * all Unicode characters, including supplementary characters, use
11899 * the {@link #getDirectionality(int)} method.
11900 *
11901 * @param ch {@code char} for which the directionality property
11902 * is requested.
11903 * @return the directionality property of the {@code char} value.
11904 *
11905 * @see Character#DIRECTIONALITY_UNDEFINED
11906 * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT
11907 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT
11908 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_ARABIC
11909 * @see Character#DIRECTIONALITY_EUROPEAN_NUMBER
11910 * @see Character#DIRECTIONALITY_EUROPEAN_NUMBER_SEPARATOR
11911 * @see Character#DIRECTIONALITY_EUROPEAN_NUMBER_TERMINATOR
11912 * @see Character#DIRECTIONALITY_ARABIC_NUMBER
11913 * @see Character#DIRECTIONALITY_COMMON_NUMBER_SEPARATOR
11914 * @see Character#DIRECTIONALITY_NONSPACING_MARK
11915 * @see Character#DIRECTIONALITY_BOUNDARY_NEUTRAL
11916 * @see Character#DIRECTIONALITY_PARAGRAPH_SEPARATOR
11917 * @see Character#DIRECTIONALITY_SEGMENT_SEPARATOR
11918 * @see Character#DIRECTIONALITY_WHITESPACE
11919 * @see Character#DIRECTIONALITY_OTHER_NEUTRALS
11920 * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT_EMBEDDING
11921 * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT_OVERRIDE
11922 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_EMBEDDING
11923 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_OVERRIDE
11924 * @see Character#DIRECTIONALITY_POP_DIRECTIONAL_FORMAT
11925 * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT_ISOLATE
11926 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_ISOLATE
11927 * @see Character#DIRECTIONALITY_FIRST_STRONG_ISOLATE
11928 * @see Character#DIRECTIONALITY_POP_DIRECTIONAL_ISOLATE
11929 * @since 1.4
11930 */
11931 public static byte getDirectionality(char ch) {
11932 return getDirectionality((int)ch);
11933 }
11934
11935 /**
11936 * Returns the Unicode directionality property for the given
11937 * character (Unicode code point). Character directionality is
11938 * used to calculate the visual ordering of text. The
11939 * directionality value of undefined character is {@link
11940 * #DIRECTIONALITY_UNDEFINED}.
11941 *
11942 * @param codePoint the character (Unicode code point) for which
11943 * the directionality property is requested.
11944 * @return the directionality property of the character.
11945 *
11946 * @see Character#DIRECTIONALITY_UNDEFINED DIRECTIONALITY_UNDEFINED
11947 * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT DIRECTIONALITY_LEFT_TO_RIGHT
11948 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT DIRECTIONALITY_RIGHT_TO_LEFT
11949 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_ARABIC DIRECTIONALITY_RIGHT_TO_LEFT_ARABIC
11950 * @see Character#DIRECTIONALITY_EUROPEAN_NUMBER DIRECTIONALITY_EUROPEAN_NUMBER
11951 * @see Character#DIRECTIONALITY_EUROPEAN_NUMBER_SEPARATOR DIRECTIONALITY_EUROPEAN_NUMBER_SEPARATOR
11952 * @see Character#DIRECTIONALITY_EUROPEAN_NUMBER_TERMINATOR DIRECTIONALITY_EUROPEAN_NUMBER_TERMINATOR
11953 * @see Character#DIRECTIONALITY_ARABIC_NUMBER DIRECTIONALITY_ARABIC_NUMBER
11954 * @see Character#DIRECTIONALITY_COMMON_NUMBER_SEPARATOR DIRECTIONALITY_COMMON_NUMBER_SEPARATOR
11955 * @see Character#DIRECTIONALITY_NONSPACING_MARK DIRECTIONALITY_NONSPACING_MARK
11956 * @see Character#DIRECTIONALITY_BOUNDARY_NEUTRAL DIRECTIONALITY_BOUNDARY_NEUTRAL
11957 * @see Character#DIRECTIONALITY_PARAGRAPH_SEPARATOR DIRECTIONALITY_PARAGRAPH_SEPARATOR
11958 * @see Character#DIRECTIONALITY_SEGMENT_SEPARATOR DIRECTIONALITY_SEGMENT_SEPARATOR
11959 * @see Character#DIRECTIONALITY_WHITESPACE DIRECTIONALITY_WHITESPACE
11960 * @see Character#DIRECTIONALITY_OTHER_NEUTRALS DIRECTIONALITY_OTHER_NEUTRALS
11961 * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT_EMBEDDING DIRECTIONALITY_LEFT_TO_RIGHT_EMBEDDING
11962 * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT_OVERRIDE DIRECTIONALITY_LEFT_TO_RIGHT_OVERRIDE
11963 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_EMBEDDING DIRECTIONALITY_RIGHT_TO_LEFT_EMBEDDING
11964 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_OVERRIDE DIRECTIONALITY_RIGHT_TO_LEFT_OVERRIDE
11965 * @see Character#DIRECTIONALITY_POP_DIRECTIONAL_FORMAT DIRECTIONALITY_POP_DIRECTIONAL_FORMAT
11966 * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT_ISOLATE DIRECTIONALITY_LEFT_TO_RIGHT_ISOLATE
11967 * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_ISOLATE DIRECTIONALITY_RIGHT_TO_LEFT_ISOLATE
11968 * @see Character#DIRECTIONALITY_FIRST_STRONG_ISOLATE DIRECTIONALITY_FIRST_STRONG_ISOLATE
11969 * @see Character#DIRECTIONALITY_POP_DIRECTIONAL_ISOLATE DIRECTIONALITY_POP_DIRECTIONAL_ISOLATE
11970 * @since 1.5
11971 */
11972 public static byte getDirectionality(int codePoint) {
11973 return CharacterData.of(codePoint).getDirectionality(codePoint);
11974 }
11975
11976 /**
11977 * Determines whether the character is mirrored according to the
11978 * Unicode specification. Mirrored characters should have their
11979 * glyphs horizontally mirrored when displayed in text that is
11980 * right-to-left. For example, {@code '\u005Cu0028'} LEFT
11981 * PARENTHESIS is semantically defined to be an <i>opening
11982 * parenthesis</i>. This will appear as a "(" in text that is
11983 * left-to-right but as a ")" in text that is right-to-left.
11984 *
11985 * <p><b>Note:</b> This method cannot handle <a
11986 * href="#supplementary"> supplementary characters</a>. To support
11987 * all Unicode characters, including supplementary characters, use
11988 * the {@link #isMirrored(int)} method.
11989 *
11990 * @param ch {@code char} for which the mirrored property is requested
11991 * @return {@code true} if the char is mirrored, {@code false}
11992 * if the {@code char} is not mirrored or is not defined.
11993 * @since 1.4
11994 */
11995 public static boolean isMirrored(char ch) {
11996 return isMirrored((int)ch);
11997 }
11998
11999 /**
12000 * Determines whether the specified character (Unicode code point)
12001 * is mirrored according to the Unicode specification. Mirrored
12002 * characters should have their glyphs horizontally mirrored when
12003 * displayed in text that is right-to-left. For example,
12004 * {@code '\u005Cu0028'} LEFT PARENTHESIS is semantically
12005 * defined to be an <i>opening parenthesis</i>. This will appear
12006 * as a "(" in text that is left-to-right but as a ")" in text
12007 * that is right-to-left.
12008 *
12009 * @param codePoint the character (Unicode code point) to be tested.
12010 * @return {@code true} if the character is mirrored, {@code false}
12011 * if the character is not mirrored or is not defined.
12012 * @since 1.5
12013 */
12014 public static boolean isMirrored(int codePoint) {
12015 return CharacterData.of(codePoint).isMirrored(codePoint);
12016 }
12017
12018 /**
12019 * Compares two {@code Character} objects numerically.
12020 *
12021 * @param anotherCharacter the {@code Character} to be compared.
12022 * @return the value {@code 0} if the argument {@code Character}
12023 * is equal to this {@code Character}; a value less than
12024 * {@code 0} if this {@code Character} is numerically less
12025 * than the {@code Character} argument; and a value greater than
12026 * {@code 0} if this {@code Character} is numerically greater
12027 * than the {@code Character} argument (unsigned comparison).
12028 * Note that this is strictly a numerical comparison; it is not
12029 * locale-dependent.
12030 * @since 1.2
12031 */
12032 public int compareTo(Character anotherCharacter) {
12033 return compare(this.value, anotherCharacter.value);
12034 }
12035
12036 /**
12037 * Compares two {@code char} values numerically.
12038 * The value returned is identical to what would be returned by:
12039 * <pre>
12040 * Character.valueOf(x).compareTo(Character.valueOf(y))
12041 * </pre>
12042 *
12043 * @param x the first {@code char} to compare
12044 * @param y the second {@code char} to compare
12045 * @return the value {@code 0} if {@code x == y};
12046 * a value less than {@code 0} if {@code x < y}; and
12047 * a value greater than {@code 0} if {@code x > y}
12048 * @since 1.7
12049 */
12050 public static int compare(char x, char y) {
12051 return x - y;
12052 }
12053
12054 /**
12055 * Converts the character (Unicode code point) argument to uppercase using
12056 * information from the UnicodeData file.
12057 *
12058 * @param codePoint the character (Unicode code point) to be converted.
12059 * @return either the uppercase equivalent of the character, if
12060 * any, or an error flag ({@code Character.ERROR})
12061 * that indicates that a 1:M {@code char} mapping exists.
12062 * @see Character#isLowerCase(char)
12063 * @see Character#isUpperCase(char)
12064 * @see Character#toLowerCase(char)
12065 * @see Character#toTitleCase(char)
12066 * @since 1.4
12067 */
12068 static int toUpperCaseEx(int codePoint) {
12069 assert isValidCodePoint(codePoint);
12070 return CharacterData.of(codePoint).toUpperCaseEx(codePoint);
12071 }
12072
12073 /**
12074 * Converts the character (Unicode code point) argument to uppercase using case
12075 * mapping information from the SpecialCasing file in the Unicode
12076 * specification. If a character has no explicit uppercase
12077 * mapping, then the {@code char} itself is returned in the
12078 * {@code char[]}.
12079 *
12080 * @param codePoint the character (Unicode code point) to be converted.
12081 * @return a {@code char[]} with the uppercased character.
12082 * @since 1.4
12083 */
12084 static char[] toUpperCaseCharArray(int codePoint) {
12085 // As of Unicode 6.0, 1:M uppercasings only happen in the BMP.
12086 assert isBmpCodePoint(codePoint);
12087 return CharacterData.of(codePoint).toUpperCaseCharArray(codePoint);
12088 }
12089
12090 /**
12091 * The number of bits used to represent a {@code char} value in unsigned
12092 * binary form, constant {@code 16}.
12093 *
12094 * @since 1.5
12095 */
12096 public static final int SIZE = 16;
12097
12098 /**
12099 * The number of bytes used to represent a {@code char} value in unsigned
12100 * binary form.
12101 *
12102 * @since 1.8
12103 */
12104 public static final int BYTES = SIZE / Byte.SIZE;
12105
12106 /**
12107 * Returns the value obtained by reversing the order of the bytes in the
12108 * specified {@code char} value.
12109 *
12110 * @param ch The {@code char} of which to reverse the byte order.
12111 * @return the value obtained by reversing (or, equivalently, swapping)
12112 * the bytes in the specified {@code char} value.
12113 * @since 1.5
12114 */
12115 @IntrinsicCandidate
12116 public static char reverseBytes(char ch) {
12117 return (char) (((ch & 0xFF00) >> 8) | (ch << 8));
12118 }
12119
12120 /**
12121 * Returns the name of the specified character
12122 * {@code codePoint}, or null if the code point is
12123 * {@link #UNASSIGNED unassigned}.
12124 * <p>
12125 * If the specified character is not assigned a name by
12126 * the <i>UnicodeData</i> file (part of the Unicode Character
12127 * Database maintained by the Unicode Consortium), the returned
12128 * name is the same as the result of the expression:
12129 *
12130 * <blockquote>{@code
12131 * Character.UnicodeBlock.of(codePoint).toString().replace('_', ' ')
12132 * + " "
12133 * + Integer.toHexString(codePoint).toUpperCase(Locale.ROOT);
12134 *
12135 * }</blockquote>
12136 *
12137 * For the {@code codePoint}s in the <i>UnicodeData</i> file, the name
12138 * returned by this method follows the naming scheme in the
12139 * "Unicode Name Property" section of the Unicode Standard. For other
12140 * code points, such as Hangul/Ideographs, The name generation rule above
12141 * differs from the one defined in the Unicode Standard.
12142 *
12143 * @param codePoint the character (Unicode code point)
12144 *
12145 * @return the name of the specified character, or null if
12146 * the code point is unassigned.
12147 *
12148 * @throws IllegalArgumentException if the specified
12149 * {@code codePoint} is not a valid Unicode
12150 * code point.
12151 *
12152 * @since 1.7
12153 */
12154 public static String getName(int codePoint) {
12155 if (!isValidCodePoint(codePoint)) {
12156 throw new IllegalArgumentException(
12157 String.format("Not a valid Unicode code point: 0x%X", codePoint));
12158 }
12159 String name = CharacterName.getInstance().getName(codePoint);
12160 if (name != null)
12161 return name;
12162 if (getType(codePoint) == UNASSIGNED)
12163 return null;
12164 UnicodeBlock block = UnicodeBlock.of(codePoint);
12165 if (block != null)
12166 return block.toString().replace('_', ' ') + " "
12167 + Integer.toHexString(codePoint).toUpperCase(Locale.ROOT);
12168 // should never come here
12169 return Integer.toHexString(codePoint).toUpperCase(Locale.ROOT);
12170 }
12171
12172 /**
12173 * Returns the code point value of the Unicode character specified by
12174 * the given character name.
12175 * <p>
12176 * If a character is not assigned a name by the <i>UnicodeData</i>
12177 * file (part of the Unicode Character Database maintained by the Unicode
12178 * Consortium), its name is defined as the result of the expression:
12179 *
12180 * <blockquote>{@code
12181 * Character.UnicodeBlock.of(codePoint).toString().replace('_', ' ')
12182 * + " "
12183 * + Integer.toHexString(codePoint).toUpperCase(Locale.ROOT);
12184 *
12185 * }</blockquote>
12186 * <p>
12187 * The {@code name} matching is case insensitive, with any leading and
12188 * trailing whitespace character removed.
12189 *
12190 * For the code points in the <i>UnicodeData</i> file, this method
12191 * recognizes the name which conforms to the name defined in the
12192 * "Unicode Name Property" section in the Unicode Standard. For other
12193 * code points, this method recognizes the name generated with
12194 * {@link #getName(int)} method.
12195 *
12196 * @param name the character name
12197 *
12198 * @return the code point value of the character specified by its name.
12199 *
12200 * @throws IllegalArgumentException if the specified {@code name}
12201 * is not a valid character name.
12202 * @throws NullPointerException if {@code name} is {@code null}
12203 *
12204 * @since 9
12205 */
12206 public static int codePointOf(String name) {
12207 name = name.trim().toUpperCase(Locale.ROOT);
12208 int cp = CharacterName.getInstance().getCodePoint(name);
12209 if (cp != -1)
12210 return cp;
12211 try {
12212 int off = name.lastIndexOf(' ');
12213 if (off != -1) {
12214 cp = Integer.parseInt(name, off + 1, name.length(), 16);
12215 if (isValidCodePoint(cp) && name.equals(getName(cp)))
12216 return cp;
12217 }
12218 } catch (Exception x) {}
12219 throw new IllegalArgumentException("Unrecognized character name :" + name);
12220 }
12221 }